Initial plan

.agents/skills/adversarial-validation/SKILL.md

@@ -1,266 +0,0 @@
----
-name: adversarial-validation
-description: Execute the Adversarial Validation policy from the root AGENTS.md — run the six reviewer roles (correctness, security, concurrency/durability, compatibility, performance, test coverage) with RustFS-specific attack probes. Use on every behavior-affecting code change, bug fix, or design proposal before declaring it done.
----
-
-# Adversarial Validation Playbooks
-
-The policy — risk tiers, role list, protocol, exit criteria — lives in the
-root `AGENTS.md` under "Adversarial Validation (Default On)". Read it first;
-this skill does not restate it. This file adds the RustFS-specific probe
-playbook for each role: concrete attacks, where they apply, and the real
-shipped bug or rule that earns each probe its place.
-
-## How to run a role
-
-1. Pick the tier and the applicable roles per the root `AGENTS.md`.
-2. Run each role as an independent pass over the final diff — a parallel
-   reviewer agent where the tooling supports it, otherwise a fresh
-   sequential pass that starts from the diff and the nearest scoped
-   `AGENTS.md`, discarding the writing session's assumptions.
-3. Within a role, execute the probes whose domain the diff touches, plus any
-   attack the diff obviously invites that no probe lists — the playbook is a
-   floor, not a ceiling.
-4. Report findings (concrete failure scenario or named missing test, with
-   file:line) or the role's null report: "attacked X, Y, Z — no break
-   found". A bare pass is not a result.
-
-## Role playbooks
-
-### Correctness adversary
-
-- For any change touching error aggregation or quorum decisions, build the exact disk-error slice at the quorum boundary: N disks where successes == quorum, then flip one success to an error (quorum-1) and separately inject None/nil placeholder entries into the slice. Trace whether reduce_errs (or the new equivalent) picks the placeholder as the dominant error or lets quorum-1 pass as success. Also check heal/write paths: does a per-target failure at quorum-1 return an explicit error, or silently degrade to success?
-  - Where: crates/ecstore/src/disk/error_reduce.rs; crates/ecstore/src/set_disk/{core,ops}; crates/heal
-  - Evidence: Commit 20d61c73b 'stop reduce_errs leaking nil placeholder as dominant error' (#4551) and 47c1e730c 'make erasure heal write quorum best-effort per target' (#4545); crates/ecstore/AGENTS.md: 'Do not weaken quorum checks... Prefer explicit failure over silent data corruption or implicit success.'
-- For any change in EC read/reconstruct/streaming code, trace the mid-stream error path: the first K shards read fine, then a shard turns out bitrot-corrupt or inconsistent after N bytes have already been sent to the client. Verify the error propagates as a stream error (client sees failure), not a clean end-of-body — a silently truncated GET body is data corruption. Also re-check byte accounting: sum of per-part bytes vs object size, and partNumber-to-offset routing for the first and last part.
-  - Where: crates/ecstore/src/set_disk/read.rs (reconstruct-read, inconsistent_source_indexes handling ~line 3827); codec streaming paths in crates/ecstore/src/erasure_coding
-  - Evidence: Known live bug: EC reconstruct-read failing on inconsistent shards mid-stream silently truncates GET body → client 'unexpected EOF'; commit 15808254d 'correct codec-streaming byte accounting and partNumber routing' (#4535).
-- For any listing/pagination change, construct the exact-boundary inputs: (a) exactly max_keys/max_uploads matching entries — assert the response contains max and is_truncated=false, then max+1 entries — assert exactly max returned with is_truncated=true and a correct continuation marker; (b) a delimiter listing where folding into CommonPrefixes re-fills a full page; (c) an object 'a' coexisting with prefix dir 'a/'. Off-by-one and dropped-truncation bugs live exactly at these boundaries.
-  - Where: crates/ecstore listing/merge paths (metacache, list_objects, list_multipart_uploads); rustfs/src/storage
-  - Evidence: Three recent real bugs: fefa70b31 'stop ListMultipartUploads from returning one upload past max-uploads' (#4447), d91f4d455 'report truncation when delimiter list re-folds a full page' (#4538), 7e1f7f242 'preserve CommonPrefixes when an object and same-named prefix dir coexist' (#4563).
-- Run the diff's logic with a directory object key (trailing slash, e.g. 'pre/dir/') as input. Check which layer encodes/decodes __XLDIR__ — set_disk never sees the trailing slash, so any trailing-slash branch added below the store layer is dead code and a wrong-layer bug. For delete paths, check whether options force a nil versionId onto directory keys: the resulting miss surfaces as version-not-found, not object-not-found, so callers matching only ObjectNotFound leak ghost directory entries.
-  - Where: crates/ecstore/src/store*.rs (store layer) vs crates/ecstore/src/set_disk/*; delete option construction (del_opts) and its callers
-  - Evidence: trailing-slash branches must live at store layer; del_opts injects nil version for dir keys, PR#4220 ghost-directory cleanup never fired on the real path (rustfs#4307, backlog#798 still OPEN).
-- Feed every new binary-UUID metadata read the three degenerate values: key absent, zero-length bytes, and 16 zero bytes (nil UUID). All three must mean 'no value' — any path that produces Uuid::nil() and then acts on it (e.g. sends it as a versionId) is a finding. For tier code specifically: with remote-tier version None or "", assert the tier GET/DELETE request carries no versionId parameter at all — sending versionId="" or nil yields NoSuchVersion against unversioned tier buckets.
-  - Where: crates/filemeta/src/filemeta/version.rs; crates/ecstore/src/bucket/lifecycle/; crates/ecstore/src/services/tier/; any new consumer of crates/utils/src/http/metadata_compat.rs
-  - Evidence: AGENTS.md Cross-Cutting Domain Invariants (defensive Uuid read pattern + unversioned-tier rule); docs/operations/tier-ilm-debugging.md ('nil transition_ver_id = corrupt legacy write-back, readers must filter'); commit 726f3dc18 'accept empty remote version_id in tier recovery paths' (#4552).
-- For each match/if-let on an error or algorithm enum touched by the diff, enumerate what the wildcard/else arm swallows. Inject the variants the author didn't think of — DiskNotFound during listing, an unsupported checksum algorithm, an Err from a cleanup rename/delete — and trace whether they degrade into 'not found', a wrong-but-plausible value, or silent success. Any error path that converges with the success path without logging and propagating is a finding.
-  - Where: crates/ecstore (listing, delete/rename cleanup); crates/checksums; error-mapping layers in rustfs/src/storage
-  - Evidence: Three recent real bugs of this exact shape: e0619e355 'stop treating DiskNotFound as object not-found in listing' (#4536), afaf8c681 'reject md5 instead of silently returning crc32' (#4513), f7d2b2563 'propagate disk delete/rename failures instead of swallowing them' (#4546).
-- For any change to version ordering, index lookup, or shard/part indexing: (a) call the accessor with index == len() and len()-1 — a get_idx-style bound must reject, not panic or wrap; (b) construct two versions with identical mod-times and check the sort tie-break is total and deterministic (equal keys must not compare as both before each other); (c) for EC shard math, compute shard size for object sizes 0, 1, blockSize-1, blockSize, blockSize+1 and cross-check total reconstructed length against the object size.
-  - Where: crates/filemeta/src/filemeta/*.rs (version sort, get_idx); crates/ecstore/src/erasure_coding shard-size math
-  - Evidence: Commit 8bfb00bc0 'guard get_idx bound and fix sorts_before tie-break' (#4509) — both bug classes shipped before; ecstore AGENTS.md high-risk designation for read/write/repair correctness.
-- Exercise the zero/empty end of every new size or count parameter: zero-length object PUT then GET (body must be empty, not error), part count 0, empty Vec of disks/entries into aggregation functions, and env/config values of 0 (must clamp or reject, never divide-by-zero or 'scan nothing and report zero usage'). Anywhere the diff computes a ratio, capacity, or progress percentage, plug in 0 and the max value.
-  - Where: crates/ecstore aggregation and scanner paths; crates/object-capacity; config/env parsing in touched crates
-  - Evidence: Commits 787cc77a7 'clamp zero capacity env values to safe defaults' (#4559) and 32b1094ec 'resolve a symlinked scan root instead of silently counting zero' (#4564) — zero-as-silent-wrong-answer is a recurring repo bug class.
-- Smaller-diff attack: rewrite the diff's change mentally (or actually, in scratch) as the minimal in-place edit and compare. Flag as findings: a helper function with exactly one caller introduced by this diff; a file rewrite where a 3-line edit inside the existing control flow suffices; reshaped control flow in init/locking/metadata/quorum paths beyond what the fix requires; new string literals duplicating existing constants (grep the token first); #[path] module inclusion. If the smaller diff achieves identical behavior, report it with the concrete replacement.
-  - Where: Any diff; extra scrutiny for crates/ecstore, crates/lock, rustfs/src/storage where 'preserve the existing control-flow shape' is an explicit rule
-  - Evidence: AGENTS.md 'Change Style for Existing Logic' (one-off helper ban, preserve control-flow shape in distributed/locking/metadata paths, no #[path]) and 'Constant and String Usage'; Adversarial Validation section names the smaller-diff clause as a correctness-adversary finding.
-- For any diff touching multipart or object commit paths, order the operations on paper and attack the failure point between them: kill the process (or return Err) after the commit rename but before cleanup, and after cleanup but before commit. Verify the earlier-failure case leaves the object readable and the later-failure case leaves no half-visible object; part meta files must never be deleted before the commit is durable.
-  - Where: crates/ecstore multipart commit/cleanup (set_disk/ops); rustfs/src/storage multipart handlers
-  - Evidence: Commit c77c5f047 'defer multipart part.N.meta cleanup until after commit' (#4548) — cleanup-before-commit ordering already caused a real data-loss window; the #4221 durability work shows fsync/ordering bugs are endemic here.
-
-Null report example: "Attacked quorum-1 error reduction, exact max-keys listing boundary, trailing-slash dir keys, nil-UUID tier versionId, mid-stream reconstruct error propagation, and a minimal-diff rewrite — no break found; diff is already the minimal in-place edit."
-
-### Security reviewer
-
-- For every admin handler in the diff, grep the exact AdminAction constant it passes to validate_admin_request and confirm it names the operation the handler actually performs. Construct the escalation: a low-privileged user whose policy grants the wrong-but-adjacent action (e.g. Export while the handler Imports, or Update while it Lists) — if the mismatched constant lets them through, that is the bug. Also confirm read-only endpoints (metrics, list, server-info, diagnostics) still call an operation-specific admin authz path and not a mere 'credentials exist' check.
-  - Where: rustfs/src/admin/handlers/**, rustfs/src/admin/router registration; check_permissions / validate_admin_request / AdminAction::* call sites
-  - Evidence: GHSA-vcwh-pff9-64cc (ImportIam checked ExportIAMAction), GHSA-mm2q-qcmx-gw4w (ListServiceAccount used UpdateServiceAccountAdminAction), GHSA-f5cv-v44x-2xgf (/admin/v3/metrics accepted any authenticated IAM user). advisory-patterns.md 'Admin authorization and route exposure'; rustfs/src/admin/AGENTS.md 'route registration, whitelist, handler authz must agree'.
-- If the diff touches service-account or IAM import/update, treat parent, claims, accessKey, secretKey, status, policy names, and groups as attacker-controlled. Construct an ImportIam/create payload where parent points at root (or another user) and prove the code writes credentials without proving caller ownership or root authority. Separately, set deny_only=true (or 'no explicit deny') on a restricted account and check it does not skip the required allow check, letting it mint an unrestricted child.
-  - Where: crates/iam/, rustfs/src/admin/handlers (service account / import IAM), rustfs/src/auth.rs
-  - Evidence: GHSA-566f-q62r-wcr8 (attacker-controlled parent/claims/accessKey/secretKey → persistent backdoor under root), GHSA-xgr5-qc6w-vcg9 (deny_only=true skipped allow checks → privilege creation). crates/iam/AGENTS.md security boundaries; advisory-patterns.md 'IAM import, service accounts'.
-- For a changed protocol-frontend handler (FTP/FTPS/SFTP/WebDAV/gateway), enumerate ALL sibling command handlers in the same driver — not just the changed one. For each, confirm it calls the per-operation IAM authorize hook mapped to the correct S3 action (RETR→GetObject, SIZE/MDTM→HeadObject, MKD→CreateBucket, bucket probe→ListBucket/HeadBucket) BEFORE touching storage. Construct a denied-authz case and prove the storage backend is never reached.
-  - Where: crates/protocols/ (FtpsDriver, SftpDriver, WebDAV), authorize_operation call sites
-  - Evidence: GHSA-3g29-xff2-92vp (FTP RETR/SIZE/MDTM authenticated but skipped IAM), GHSA-g3vq-vv42-f647 (FTPS MKD called create_bucket without s3:CreateBucket). advisory-patterns.md: 'RustFS advisories show mixed guarded and unguarded siblings in the same driver.'
-- For any secret/token/signature/password comparison in the diff, check it uses a constant-time compare (e.g. subtle/constant_time_eq), not == or early-return byte loops. Then check the failure-response paths: construct an invalid-user request and an invalid-secret request and confirm they are indistinguishable (same error, no early length short-circuit) so an attacker cannot enumerate valid users or time-side-channel the secret.
-  - Where: crates/protocols/ (FTPS/WebDAV/FormPost auth), crates/credentials/, rustfs/src/auth.rs, RPC signature verification
-  - Evidence: GHSA-3p3x-734c-h5vx (FTPS/WebDAV early-return string equality + distinguishable invalid-user vs invalid-password). Fix commits 3c3113619 (constant-time FTPS/WebDAV) and c41062f27 (constant-time FormPost signature). 3p3x was fixed by PR #4403.
-- If the diff touches internode/RPC auth secret handling, trace whether the RPC HMAC secret can fall back to a public default (e.g. 'rustfsadmin', 'rustfs rpc') or be derived deterministically from the S3 root credentials. Construct the case where RUSTFS_RPC_SECRET is unset and confirm the code fails closed rather than silently using a default or a root-derived key. Verify RPC signing keys are independent random secrets, not reused across S3-root/RPC-HMAC/STS-JWT roles.
-  - Where: crates/credentials/, crates/ecstore/src/rpc/, internode auth setup
-  - Evidence: GHSA-r5qv-rc46-hv8q (fell back to 'rustfsadmin'), GHSA-75fx/68cw (RPC secret derivable from root creds → forgeable signatures), GHSA-h956 (hard-coded 'rustfs rpc'), GHSA-m77q (STS JWT reused root secret). Fix commit 7b2055405 (fail closed when deriving RPC secret from default credentials, PR#4402).
-- If the diff touches RPC/NodeService authentication, verify the HMAC payload binds the EXACT concrete gRPC method path (not a service prefix), the HTTP method surrogate, and a fresh timestamp. Construct captured valid metadata for method A and replay it to method B within the timestamp window — if it authorizes, the signature is under-bound. Also test stale timestamp, wrong path, wrong method, wrong secret.
-  - Where: crates/ecstore/src/rpc/, verify_rpc_signature / NodeServiceServer, x-rustfs-signature handling
-  - Evidence: GHSA-c667-rgrv-99vj (signed service prefix instead of concrete method path → cross-method replay in timestamp window). advisory-patterns.md 'RPC input validation and panic safety'; Minimum Regression Test Expectations lists replay across two methods.
-- For any RPC/gRPC handler or deserialization touched, feed empty bytes, truncated MessagePack/protobuf, invalid enum discriminants, and stale timestamps. Grep the deserialization path for unwrap()/expect()/panic-prone decode and prove malformed attacker payloads return a typed error, not a panic (remote DoS). Weak internode auth makes reachability worse, so combine with the RPC-secret probe.
-  - Where: crates/ecstore/src/rpc/, any #[derive(Deserialize)] decoded from wire bytes, RPC handler bodies
-  - Evidence: GHSA-gw2x-q739-qhcr (malformed GetMetrics reached unwrap() → remote DoS). advisory-patterns.md 'Treat all RPC payload bytes as attacker-controlled.' rust-code-quality skill: unwrap abuse.
-- Take any object key, RPC disk path, or archive/tar/zip entry name introduced or handled in the diff and construct traversal payloads: '../', URL-encoded '%2e%2e%2f', absolute paths, platform separators, empty components. Trace the value through parse → authz check → final storage path and prove (a) authz and storage normalize the SAME way, and (b) the canonicalized path cannot escape the bucket/prefix root. Attack the case where authz sees the raw attacker bucket but storage cleaning crosses into a victim bucket.
-  - Where: crates/ecstore (path join/canonicalize), rustfs/src/storage/, Snowball auto-extract / normalize_extract_entry_key, rpc read_file_stream
-  - Evidence: GHSA-pq29-69jg-9mxc (read_file_stream joined untrusted paths, no canonical boundary check), GHSA-8r6f-hmq2-28rg (traversal object keys bypassed authz), GHSA-f4vq-9ffr-m8m3 (Snowball '../victim-bucket/object' authorized raw path then storage crossed boundary). Note __XLDIR__ trailing-slash encoding is store-layer only.
-- If the diff touches multipart/copy or presigned POST, verify UploadPartCopy enforces source GetObject AND destination PutObject semantics equivalent to CopyObject, including copy-source policy conditions (not just independent source-read + dest-write). Construct a cross-bucket UploadPartCopy from a bucket the caller cannot read. For presigned POST, submit an upload that violates content-length-range, key prefix, or exact content-type and prove the server rejects it.
-  - Where: rustfs/src/storage / S3 API handlers: upload_part_copy, CompleteMultipartUpload, PostObject policy enforcement
-  - Evidence: GHSA-mx42-j6wv-px98 (UploadPartCopy missed source authz → cross-bucket exfil), GHSA-wfxj-ph3v-7mjf (missed destination copy-source policy constraint), GHSA-w5fh-f8xh-5x3p (presigned POST didn't enforce signed policy conditions). advisory-patterns.md 'S3 copy, multipart, and upload policy validation'.
-- Grep the diff for debug!/trace!/info!/error! and any ?value / {:?} on structs or response bodies that can carry secret_key, session_token, JWT claims, HMAC secrets, expected signatures, access keys beyond safe identifiers, or raw credential-bearing responses. Check custom Debug impls and merged-config dumps too. Construct the error path (invalid signature, failed auth) and confirm it does not log the secret or the derived authenticator. Verify audit/notify entries redact credential request headers.
-  - Where: rustfs/src/**, crates/iam/, crates/audit/, crates/notify/, crates/targets/, RPC signature error paths
-  - Evidence: GHSA-r54g (STS creds logged at info), GHSA-8cm2 (debug logs leaked tokens/secrets/JWT claims/raw STS bodies), GHSA-333v (invalid RPC signature log included HMAC secret + expected signature). Fix commit ee6f79110 (redact credential request headers from audit/notify, backlog#963). rustfs-logging-governance skill.
-- For any struct in the diff deserialized from untrusted input (S3 XML/JSON, lifecycle rules, bucket policy, replication config, RPC payload), check for #[serde(deny_unknown_fields)]. Construct a payload with a typo'd field (e.g. 'NoncurentDays') or an extra field and prove it is rejected, not silently ignored. Flag #[serde(default)] on security-critical fields (retention days, limits, permissions) lacking explicit post-deserialize validation, and any user-controlled integer cast with `as` (i32 as u32) — feed a negative value and check it doesn't wrap to a huge positive.
-  - Where: crates/policy/ (bucket policy), crates/ecstore lifecycle/ILM config, replication config structs, crates/protocols XML parsing
-  - Evidence: AGENTS.md 'Serde Safety'; advisory-patterns.md 'Serde deserialization' (no deny_unknown_fields found repo-wide; 'NoncurentDays' typo silently accepted; i32 as u32 wrap). Fix commit 1acd47f15 (SSE crash-loop DoS + credential reserved-char bypass, backlog#806).
-- If the diff touches SSE / encryption reader-writer composition, do not trust API metadata claiming encryption. Trace the reader wrapper order (HashReader / EncryptReader / compression / warp) and confirm EncryptReader is actually in the chain that writes to disk — construct the case where a helper unwraps a nested reader and bypasses encryption, storing plaintext. Require a regression test that inspects the ACTUAL stored bytes on disk, not just read-back. Also check encrypted-object checksums are not exposed.
-  - Where: rustfs/src/storage/ecfs.rs, crates/rio/ (reader wrappers), crates/kms/, SSE-C replication
-  - Evidence: GHSA-xrrf-67jm-3c2r (SSE metadata reported encryption while composition bypassed EncryptReader, stored plaintext). Fix commits a7b9659e7 (hide encrypted object checksums, #4529), 80cc3b1fc (preserve SSE-C checksum state, #4410). advisory-patterns.md 'SSE and on-disk storage invariants'.
-- If the diff touches CORS or the console/browser/object-preview surface: confirm default CORS does not reflect an arbitrary Origin while also sending Access-Control-Allow-Credentials: true — construct a request with a spoofed Origin and check the response. For preview, confirm attacker-controlled object content is origin-isolated (not rendered in a same-origin iframe with console creds), served with nosniff/CSP, and that preview trust derives from validated content-type + sandboxing, NOT from object name/extension (.pdf, .html). Separately, if aws:SourceIp is evaluated, spoof X-Forwarded-For / X-Real-IP as a direct (non-trusted-proxy) client and confirm the socket peer IP is used instead.
-  - Where: rustfs/src/server/layer.rs (CORS), console preview/auth code, aws:SourceIp / policy condition evaluation, X-Forwarded-For handling
-  - Evidence: GHSA-x5xv-223c-8vm7 (default CORS reflected arbitrary origins with credentials), GHSA-v9fg-3cr2-277j (preview rendered attacker HTML same-origin, exposed localStorage creds), GHSA-7gcx-wg4x-q9x6 (extension-based PDF detection bypassed sandbox), GHSA-fc6g-2gcp-2qrq (aws:SourceIp trusted client XFF). advisory-patterns.md 'Browser, CORS' + 'Trusted proxy'.
-
-Null report example: "Attacked admin action-constant matching in the two changed handlers (both call validate_admin_request with the exact AdminAction), the FTPS RETR/SIZE authz parity, and the new lifecycle struct's serde surface (has deny_unknown_fields) — no break found."
-
-### Concurrency/durability reviewer
-
-- For every new or moved lock acquisition, enumerate all other code paths that take any overlapping subset of those locks and construct the concrete ABBA interleaving (thread 1 holds A wants B, thread 2 holds B wants A). If the diff acquires 2+ locks without a comment documenting acquisition order, that alone is a finding.
-  - Where: crates/ecstore/** (namespace locks, set_disk, disk registry), crates/audit/**, crates/lock/**, any Mutex/RwLock pair in a diff
-  - Evidence: crates/ecstore/AGENTS.md 'Lock Ordering' (document order; same set in different orders = deadlock); real ABBA deadlock fixed in c0d5f938f (#4421, audit registry vs stream_cancellers)
-- If the diff touches the object write/commit path or a lock guard's lifetime, construct the timeline where the distributed lock is lost (heartbeat refresh fails / expiry) after shard writes but before the xl.meta rename commit — verify the commit is fenced on guard.is_lock_lost() (set_disk/ops/object.rs:874-880) and the diff does not move the commit outside the fenced region or drop the guard early.
-  - Where: crates/ecstore/src/set_disk/ops/object.rs, ops/multipart.rs, crates/lock/**
-  - Evidence: 1e6207c08 (#4406) fence write commit on lock loss; ddf197ba5 (#4388) heartbeat lock refresh; backlog#899 fencing comment in object.rs
-- For any change to file creation or write-then-rename: write out the exact syscall order (write tmp -> fdatasync tmp -> rename -> fsync parent dir -> fsync ancestor dirs on first object under a prefix) and simulate a power cut after each step. Flag any dropped/reordered sync, and check the change honors the durability gate (RUSTFS_DRIVE_SYNC_ENABLE, strict/relaxed/none modes, per-bucket overrides) instead of hardcoding one mode. The 'skip tmp parent fsync' optimization is only sound when the file is renamed out of tmp — verify that precondition still holds.
-  - Where: crates/ecstore/src/disk/local.rs, disk/os.rs, disk/fs.rs, crates/ecstore/src/bucket/durability.rs, set_disk/core/io_primitives.rs
-  - Evidence: PR #4221 (the repo previously had no fsync anywhere); 2df315baf/c081586e7 (#4493) fsync ancestor dirs; 062a68d15 (#4387) tmp-parent-fsync skip is rename-conditional; eaff17cad (#4397) durability modes; 54872d52d (#4478) rename_data crash harness exists — extend it for the diff
-- If the diff touches quorum counting or per-disk error aggregation, construct adversarial error vectors for reduce_errs: nil/placeholder entries, DiskNotFound mixed with FileNotFound, exactly quorum-1 agreeing errors — and show which dominant error wins. Specifically attack the case where offline-disk errors get counted as 'object does not exist', flipping a read/heal decision into data loss. Also check quorum monotonicity: a retry or heal pass must never conclude with a LOWER quorum than the original write.
-  - Where: crates/ecstore/src/disk/error_reduce.rs, crates/ecstore/src/api/mod.rs, set_disk read/heal paths
-  - Evidence: 20d61c73b (#4551) reduce_errs leaked nil placeholder as dominant error; e0619e355 (#4536) DiskNotFound treated as object-not-found in listing; quorum monotonicity flagged as open follow-up to #4221 (#4221 follow-up list); crates/ecstore/AGENTS.md 'Do not weaken quorum checks'
-- For any multi-disk fan-out (delete, rename, heal write, cleanup), trace each per-disk Result: find any `let _ =`, `.ok()`, or best-effort collapse that keeps a failed disk out of the quorum math. Construct the run where exactly write_quorum-1 disks succeed and prove the op still returns success — that is the bug. Conversely, for heal writes, check one bad target cannot fail the whole heal (best-effort per target).
-  - Where: crates/ecstore/src/set_disk/ops/*.rs, disk/disk_store.rs, crates/heal/**
-  - Evidence: f7d2b2563 (#4546) disk delete/rename failures were swallowed; 47c1e730c (#4545) heal write quorum made best-effort per target; 2b063b0c4 (#4400) disk-replacement heal missed versions
-- For every new .await placed between a state mutation and its cleanup/commit (or inside select!/timeout/spawned task that can be aborted), construct the cancellation point: client disconnects and the future is dropped exactly there. Enumerate what is left behind — tmp files, incremented counters never decremented, half-written xl.meta, a held permit/waiter — and verify cleanup runs in Drop or the state is re-entrant. Background loops the diff adds must have a hard outer timeout so a wedged awaitee cannot pin them forever.
-  - Where: crates/ecstore/** write paths, crates/object-capacity/** scanners, crates/audit/**, anything using tokio::select! or spawn+abort
-  - Evidence: d608e320f io_uring cancel-safety spike (cancellation known-hard here); 5a372557e (#4533) wedged scans needed hard outer timeout; 7b87d4d13 (#4520) waiter-count leak; e44bece00 (#4497) audit start race + paused drops
-- If the diff touches metacache/list producers or cursor resume, construct the interleaving where the producer task completes (or errors) while a reader with a saved cursor comes back for the next page — verify a completed producer is tolerated (no error, no hang) and that a re-folded/full page reports truncation instead of silently ending the listing early. Also feed a corrupt/oversized length prefix into any metacache decode the diff touches.
-  - Where: crates/ecstore/src/cache_value/metacache_set.rs, crates/ecstore/src/store/list_objects.rs, crates/filemeta/**
-  - Evidence: 91a23361e (#4531) tolerate completed metacache producers; d91f4d455 (#4538) delimiter re-fold dropped truncation flag; d2c100fd3 (#4226) corrupt length-prefix guard
-- For multipart changes, construct concurrent operations on the SAME uploadId: put_object_part racing put_object_part (same part number), abort racing complete between the parts listing and the commit rename, and list-parts racing cleanup. Verify every metadata read/list/abort holds the per-uploadId lock, and that part.N.meta cleanup is deferred until AFTER the commit rename — cleanup before commit loses parts on a crash between the two.
-  - Where: crates/ecstore/src/set_disk/ops/multipart.rs, rustfs/src/storage/
-  - Evidence: 3bc8d79fe (#4329) serialize put_object_part per uploadId; 7fb95d4fc (#4428) unlocked upload metadata reads/aborts; 93ffbdb9b (#4437) unlocked part listings; c77c5f047 (#4548) part.N.meta cleanup moved after commit
-- Any cleanup/rollback logic added near a commit: verify it runs strictly AFTER the commit is durable, is best-effort (its failure must not fail an already-committed write), and is safe under retry — i.e., re-running it after a partial first attempt must never delete the newly-committed data dir or the last surviving copy.
-  - Where: crates/ecstore/src/set_disk/ops/object.rs (rename_data tail), ops/multipart.rs, disk cleanup helpers
-  - Evidence: afc7f1d6f/d908243e6 (#4386, backlog#898) post-commit old-data-dir cleanup had to be made best-effort; e7cc719c1 (#4389) speculative tmp cleanup moved off hot path
-- If the diff does read-modify-write on any persisted shared state (bucket metadata, notify/target config, queue store), construct two concurrent writers: show whether the second write silently discards the first (lost update) — RMW must be serialized or CAS-guarded. For persisted queues/replay, construct crash-mid-replay and prove entries are neither lost nor delivered twice without an idempotency key.
-  - Where: crates/notify/**, crates/targets/** (queue store, SQL backends), crates/ecstore/src/bucket/metadata_sys.rs
-  - Evidence: 2490d4ee2 (#4425) persisted config RMW lost updates; 08e44b95f (#4505) queue store crash-safety + replay lifecycle; e008cc5da (#4500) SQL backend idempotency
-- If the diff touches erasure decode/reconstruct or streaming GET, construct the failure mid-stream: shards become inconsistent (or a disk read fails) after N bytes of the body have already been sent — verify the stream surfaces an error to the client instead of ending cleanly at a truncated length. Silent truncation on a 200 response is the known failure mode.
-  - Where: crates/ecstore/src/set_disk/read.rs (reconstruct-read validation, historically ~line 3117), crates/ecstore/src/erasure/coding/decode.rs
-  - Evidence: Known open bug: EC reconstruct-read 'inconsistent shards' mid-GET silently truncates body -> client unexpected EOF; crates/ecstore/AGENTS.md 'explicit failure over silent corruption'
-
-Null report example: "Attacked lock ordering on the new disk-registry mutex pair, lock-loss fencing across the moved commit, power-cut points around the added rename, and cancellation at the two new awaits — no break found; quorum math and metacache paths untouched by this diff."
-
-### Compatibility reviewer
-
-- Grep the diff for raw 'x-rustfs-internal-' or 'x-minio-internal-' string literals used with map.insert/remove/get instead of the metadata_compat helpers. If found, construct the MinIO-written object case: a metadata map containing ONLY 'X-Minio-Internal-<suffix>' (mixed case, no RustFS key) and trace the diff's read path — does it miss the value? Then construct the removal case: does remove leave the twin key behind so a stale MinIO-key value resurrects on next read? Also check the value-type trap: get_bytes has NO case-insensitive fallback (unlike get_str), so a diff that moves a suffix from FileInfo.metadata (String) to meta_sys (Vec<u8>) silently loses mixed-case MinIO keys.
-  - Where: Any code touching FileInfo.metadata / user_defined / meta_sys: crates/ecstore/, crates/filemeta/, rustfs/src/storage/, crates/utils/src/http/metadata_compat.rs
-  - Evidence: Repo-wide invariant in AGENTS.md 'Cross-Cutting Domain Invariants' and CLAUDE.md; helpers and the asymmetry are pinned by tests test_str_lookup_accepts_minio_metadata_case and test_get_bytes_no_case_insensitive_fallback in crates/utils/src/http/metadata_compat.rs
-- For any diff reading a binary UUID from internal metadata (transitioned-versionID, tier-free-versionID, data_dir), trace the three degenerate inputs — key absent, value empty (b""), value nil UUID — through to the outgoing tier/S3 request. The bug shape to hunt: unwrap_or_default() or Uuid::from_slice(..).unwrap_or(Uuid::nil()) turning 'no value' into Uuid::nil(), which then gets serialized as ?versionId=00000000-... and the remote tier returns NoSuchVersion. The required pattern is .and_then(|v| Uuid::from_slice(&v).ok()).filter(|u| !u.is_nil()).
-  - Where: crates/ecstore/src/bucket/lifecycle/ (bucket_lifecycle_ops.rs, tier_sweeper.rs), crates/ecstore/src/services/tier/warm_backend_*.rs, crates/filemeta/src/filemeta/version.rs
-  - Evidence: Historical production bug documented in docs/operations/tier-ilm-debugging.md ('Nil-UUID versionId sent to tier'); regression tests live in crates/filemeta/src/filemeta/version.rs; follow-up fix 726f3dc18 'accept empty remote version_id in tier recovery paths' (#4552)
-- For any diff touching tier or replication GET/DELETE against a remote S3 target, enumerate BOTH directions of the versionId contract and trace each: (a) remote version None/"" means the tier bucket is unversioned — the request must carry NO versionId parameter at all (not an empty one, not nil); (b) remote version Some(v) on a versioned target — the versionId MUST be sent, especially on version-purge deletes, or the delete lands on the wrong version / creates a delete marker instead of purging. Check whether the diff collapses these cases through a single Option/String conversion that loses the distinction.
-  - Where: crates/ecstore/src/services/tier/warm_backend*.rs, crates/ecstore/src/bucket/lifecycle/tier_sweeper.rs, replication code under crates/ecstore/src/bucket/
-  - Evidence: Invariant in AGENTS.md and docs/operations/tier-ilm-debugging.md; real bug fixed by 0fad35645 'send versionId on version-purge deletes to generic S3 targets' (#4401) — the versioned direction, and #4552 — the unversioned direction
-- If the diff changes xl.meta encoding (adds/reorders msgpack header fields, touches FileMeta::marshal_msg or codec.rs encode paths), attack downgrade and cross-vendor parse: encode an object with the new code and decode it with (a) the meta_ver<=3 read path and (b) the real-MinIO fixture tests from #4377. Then check the header signature: is it recomputed over the new bytes, or copied/hardcoded? MinIO validates it; a stale or zero signature makes MinIO reject the file. Finally verify XL_META_VERSION was not silently bumped — old RustFS/MinIO nodes reject meta_ver > 3 during a rolling upgrade.
-  - Where: crates/filemeta/src/filemeta.rs (XL_HEADER_VERSION/XL_META_VERSION, lines ~46-54), crates/filemeta/src/filemeta/codec.rs (check_xl2_v1, decode_xl_headers)
-  - Evidence: Real bug 073bc9675 'compute header signature instead of hardcoding zero' (#4343); format contract pinned in docs/architecture/minio-file-format-compat.md (write meta_ver 3, read <=3, XL2 magic); parity fixtures from a91d9cefc (#4377)
-- If the diff touches xl.meta / FileInfo decode (into_fileinfo, version parsing, part arrays), construct hostile foreign input: a MinIO- or corruption-shaped msgpack with a parts-count that disagrees with the etags/sizes array lengths, missing optional fields, and a meta_ver 2 object with legacy checksum. Trace whether the new code indexes past an array, panics, or fabricates default values instead of returning a decode error. Run the pinned legacy fixtures (test_issue_2265_legacy_meta_v2_object_compatibility, test_issue_2288) plus the #4377 real-MinIO xl.meta parse tests against the diff.
-  - Where: crates/filemeta/src/ (fileinfo.rs, filemeta.rs, filemeta/codec.rs, filemeta/version.rs)
-  - Evidence: Real bug 7efacbdf9 'validate part array lengths in into_fileinfo' (#4382); legacy meta_ver 2 regression fixtures at crates/filemeta/src/filemeta.rs (~:1130-:1174) cited by docs/architecture/minio-file-format-compat.md
-- If the diff 'corrects' a formula, constant, or layout that is a byte-for-byte MinIO port (shard-size math, bitrot hash interleaving, erasure distribution, inline-data prefix), treat the correction itself as the bug: verify against legacy on-disk data before accepting. Concretely: run crates/ecstore/tests/legacy_bitrot_read_test.rs and the ECA-18 pinning tests; check whether existing objects written by old RustFS or MinIO still verify byte-for-byte. Known trap examples: bitrot_shard_file_size's bare return for non-streaming algorithms is CORRECT MinIO whole-file behavior, and the 32-byte prefix on inline data is the HighwayHash256 bitrot hash, not corruption.
-  - Where: crates/ecstore/src/erasure/coding/bitrot.rs, crates/ecstore/src/io_support/bitrot.rs, crates/filemeta/src/fileinfo.rs
-  - Evidence: f96314a1d 'pin streaming-only bitrot layout invariant (ECA-18)' (#4553) — audit explicitly decided NOT to change the formula because it breaks legacy interop; #4377 proved the inline-data prefix is the bitrot hash
-- For any diff that copies object metadata into an S3-client-visible surface (GET/HEAD response headers, notification event userMetadata, ListObjects/replication payloads, copy-object metadata directives), construct an object carrying internal keys under BOTH prefixes and in non-canonical casing ('X-Minio-Internal-Compression') and confirm every one is stripped via is_internal_key (which is case-insensitive) — not by an exact-match filter on one prefix. Leaked internal keys are an API-semantics break and an information leak.
-  - Where: rustfs/src/storage/, crates/notify/, replication and copy_object paths in crates/ecstore/
-  - Evidence: Real bug cf8929189 'strip rustfs/minio internal metadata from event userMetadata' (#4419); is_internal_key contract in crates/utils/src/http/metadata_compat.rs
-- If the diff touches crates/protos (node.proto, models.fbs) or internode RPC request/response structs, attack the rolling-upgrade interleaving: an old node sends a message without the new field to a new node, and a new node sends the extended message to an old node. Verify proto field numbers are only appended (never reused/renumbered), FlatBuffers tables are only extended at the end, and that an absent new field decodes to a safe default on the receiving side — 'safe' meaning it must not be interpreted as success/authorization (RPC errors fail closed) and must not flip a quorum decision.
-  - Where: crates/protos/ (node.proto, models.fbs, generated/), gRPC transport and dispatch in the internode layer
-  - Evidence: 6f613317f 'optimize gRPC transport' (#4337) shows the wire layer churns; security advisory 68cw fixed by PR#4402 established RPC fail-closed as a repo rule (see .agents/skills/security-advisory-lessons)
-- For S3 handler diffs, replay the request shapes real clients actually send, not just the canonical one: mc and aws-sdk differ on path normalization (root '//' ListBuckets), virtual-host vs path style, and header casing. Then attack every pagination boundary the diff touches: request exactly max-keys/max-uploads/max-parts items and verify the response returns exactly N (not N+1), sets IsTruncated correctly, and yields a NextMarker/KeyMarker that resumes without skipping or duplicating — construct the N+1st-item case explicitly.
-  - Where: rustfs/src/storage/ S3 handlers, listing paths in crates/ecstore/src/store/ and set_disk/
-  - Evidence: Real bugs 511ad31ba 'normalize root double-slash ListBuckets requests' (#4336) and fefa70b31 'stop ListMultipartUploads from returning one upload past max-uploads' (#4447); docs/architecture/s3-compatibility-matrix.md is the compat source of truth
-- If the diff changes bucket-metadata (.metadata.bin) or IAM/config parsing structs, run it against the real MinIO RELEASE.2025-07-23 fixtures: the msgpack blob uses PascalCase field names, so any serde rename, field-type change, or derive tweak silently drops MinIO-written fields instead of erroring. Verify parse_all_configs still loads all ten config types from the fixture without loss, and that drop-in migration still decrypts MinIO-encrypted IAM/server config rather than treating ciphertext as corrupt.
-  - Where: crates/ecstore/src/bucket/metadata*, crates/ecstore/src/bucket/migration.rs, IAM/config load paths in crates/iam/ and crates/config/
-  - Evidence: Fixture parity test parses_real_minio_bucket_metadata_blob_without_loss from a91d9cefc (#4377); real bug 717cdd2ab 'decrypt MinIO IAM & server config on drop-in migration' (#4358); format matrix in docs/architecture/minio-file-format-compat.md
-- If the diff adds a compatibility shim, legacy fallback, wrapper, or old-endpoint alias (grep the diff for 'legacy', 'fallback', 'compat', 'deprecated'), verify two things: (1) it carries a RUSTFS_COMPAT_TODO(<task-id>) marker with an exact removal condition and a matching entry in the register — an unmarked shim becomes permanent dead weight; (2) the fallback's default direction is safe for old data: e.g. a new decode path must fall back to the legacy decode for old objects by default, not gate legacy reads behind an opt-in flag that makes existing data unreadable after upgrade.
-  - Where: Anywhere in the diff; register at docs/architecture/compat-cleanup-register.md; recent example: allow_inplace_legacy_fallback flag in the ecstore erasure codec streaming path
-  - Evidence: docs/architecture/compat-cleanup-register.md review checklist; d232a46b4 wired legacy decode prefetch behind a default-OFF gate while keeping legacy reads working (#4542), with arity fallout fixed in 05890d6e2 (#4573)
-
-Null report example: "Attacked dual-key metadata writes/removals against MinIO-only-key objects, nil/empty transitioned-versionID paths to the tier, xl.meta encode against meta_ver<=3 decoders and the #4377 real-MinIO fixtures, and proto field-number evolution for old-node/new-node RPC — no compatibility break found."
-
-### Performance reviewer
-
-- For every `.clone()` the diff adds or moves onto a per-request/per-object path, open the cloned type and count heap fields (String, Vec, HashMap, Bytes). If >5 heap fields or it contains an EC block buffer, construct the cost: N concurrent PUTs x M objects -> N*M deep copies per second. Demand Arc-wrapping of heavy fields or pass-by-reference; also flag new `String` allocations in header/path/signature parsing where `&str`/`Cow<str>` suffices.
-  - Where: crates/ecstore/src/set_disk/**, crates/ecstore/src/store*.rs, rustfs/src/storage/, crates/filemeta/, request handlers in rustfs/src/
-  - Evidence: crates/ecstore/AGENTS.md 'Allocation Discipline in Hot Paths' (no Clone on >5-heap-field structs, Arc for large buffers, &str/Cow for temporary computations); .agents/skills/rust-code-quality/SKILL.md ranks 'unnecessary clone in hot path' as P1 must-fix
-- For every new sync_all/sync_data/fdatasync/flush/File::sync call in the diff, trace the call chain to DurabilityMode / RUSTFS_DRIVE_SYNC_ENABLE resolution (crates/ecstore/src/disk/local.rs:291 DurabilityMode, :347 resolve_durability_mode) and to per-bucket durability overrides. Construct the run where the operator sets mode=none (or legacy RUSTFS_DRIVE_SYNC_ENABLE=false) and the new fsync still fires — that is an ungated durability cost and a regression on 4KiB writes.
-  - Where: crates/ecstore/src/disk/local.rs, crates/ecstore/src/bucket/durability.rs, crates/ecstore/src/set_disk/** (rename_data/commit paths), any crate doing tokio::fs or std::fs writes
-  - Evidence: #4221 fsync work caused a measured -10% 4KiB write regression (#814 investigation), later gated; durability modes added in eaff17cad (#4397), per-bucket tier overrides in 13e48d93a (#4407); 2df315baf (#4493) shows even ancestor-dir fsyncs are routed through the gate
-- Attack blocking-work placement from both directions: (a) find new synchronous fs calls, hashing, or EC encode/decode executed directly on an async runtime thread without spawn_blocking/block_in_place — construct the stall (a slow disk blocks a worker thread and every task queued on it); (b) find new code that splits one logical disk operation into multiple spawn_blocking hops per object — each hop is a threadpool round-trip, so K hops x N objects multiplies latency. Demand the author justify the placement with the size of the work, not habit.
-  - Where: crates/ecstore/src/disk/local.rs, crates/ecstore/src/erasure_coding/, crates/ecstore/src/bitrot/, crates/rio/
-  - Evidence: 608ab14d7 (#4554, HP-12) folded metadata open+fstat+read into a single spawn_blocking because per-op hops were measurably slow; 8fc637fb1 (#4484) moved the short EC encode inline because block_in_place cost exceeded the work — direction depends on measured work size
-- For each lock acquisition the diff adds or relocates, mark the guard's live range and list every .await and disk/RPC call inside it. Construct the contention interleaving: N concurrent requests serialize on the guard while the holder waits on IO; for namespace/multipart commit locks, compute worst-case hold time (fsync + rename per disk) against the lock's timeout. Also diff the acquisition order against other paths taking the same locks (ABBA).
-  - Where: crates/ecstore/src/set_disk/** (commit/rename paths), crates/lock/, crates/audit/ registry, any RwLock/Mutex in per-request paths
-  - Evidence: crates/ecstore/AGENTS.md 'Lock Ordering'; c0d5f938f (#4421) fixed a real ABBA deadlock between registry and stream_cancellers; #4370 history: fsync-heavy serial cross-disk commits held a lock long enough to blow test timeouts (#4370)
-- Trace exactly what executes inside the PUT commit critical section (under the object write lock, between tmp write and rename_data completion) before vs after the diff. Any newly added work there — cleanup, extra stat, additional rename, O_DIRECT write, logging — is an attack target: construct the per-PUT latency delta and demand it be moved off the critical section or parallelized across disks.
-  - Where: crates/ecstore/src/set_disk/ops/*, crates/ecstore/src/disk/local.rs rename_data path
-  - Evidence: Three real optimizations removed exactly this class of regression: e7cc719c1 (#4389) moved speculative PUT-tail tmp cleanup off the hot path, 92c8c6db7 (#4411) moved O_DIRECT shard-writes off the commit critical section, 651ccac13 (#4487) parallelized tmp xl.meta write and shard fdatasync on commit
-- Find any new loop in a batch API that performs a per-item stat/read/RPC sequentially. Construct the concrete blowup: a 1000-key DeleteObjects or a full listing page -> 1000 serial round-trips added by the diff. Demand either a gate (skip when not needed) or bounded parallelism; for startup/load paths, check for accidental O(n^2) (re-scanning the full list per item).
-  - Where: crates/ecstore/src/store_delete*.rs / batch object APIs, listing/metacache paths, crates/iam/ store loading, crates/heal/
-  - Evidence: a413729b1 (#4398) had to gate and parallelize the DeleteObjects per-object stat fanout after it shipped serial; 16a91c35e (#4537) fixed O(n^2) IAM startup load by chunking — both were diff-introduced fanouts of this exact shape
-- For every buffer the diff allocates on the encode/decode/shard path, check: is it sized with with_capacity to the EC-expanded block (not the logical size, not default-grown)? Does it copy into a fresh Vec where Bytes::slice/clone (refcount) or the io-core buffer pool would avoid the copy? Does the diff read hash and data in separate passes where one pass suffices? Construct the per-block byte-copy count before vs after. If the diff touches the io-core pool, verify gauge accounting still balances.
-  - Where: crates/ecstore/src/erasure_coding/, crates/ecstore/src/bitrot/, crates/io-core/src/pool.rs, crates/rio/
-  - Evidence: 92bf55ce6 (#4396) fixed a real regression by right-sizing BytesMut encode ingest capacity to the EC-expanded block; 47bee8b31 (#4475) merged bitrot hash+data into one read pass; 7fa3d0d4b (#4534) shows pool gauge accounting is easy to drift when touching buffer reuse
-- For every logging or instrumentation statement the diff adds, classify the call site frequency: per-request, per-object, per-shard, or per-block. Anything info!/warn!/error! at per-object frequency or higher is a finding — construct the flood (one listing under client cancellation, one 10k-object heal) and count emitted lines. New metrics/timers on the data path must be feature-gated, not always-on. Run scripts/check_logging_guardrails.sh on the diff.
-  - Where: any per-request/per-object code, especially crates/ecstore listing and heal loops, rustfs/src/storage/ handlers; scripts/check_logging_guardrails.sh
-  - Evidence: .agents/skills/rustfs-logging-governance/SKILL.md (trace level for hot-path/repetitive success events); d25ddb0e1 (#4372) fixed real listing-cancellation error-log noise; hotpath instrumentation is deliberately feature-gated (3f13d098b #4394, f262fcfce #4541 HP-14)
-- Count how many times the diff's request path parses or fetches the same metadata: xl.meta/FileMeta decoded more than once per object, bucket metadata (metadata_sys) re-fetched inside a per-object loop, or the dual x-rustfs-internal/x-minio-internal key lookup re-run repeatedly on the same map. Construct the per-request parse count before vs after; a second full FileMeta decode per GET is a finding.
-  - Where: crates/filemeta/, crates/ecstore/src/set_disk/** read paths, crates/ecstore/src/bucket/metadata_sys.rs, crates/utils/src/http/metadata_compat.rs
-  - Evidence: 608ab14d7 (#4554) exists because redundant metadata-read syscall sequences per object were measurable; CLAUDE.md dual-key metadata convention makes repeated get_bytes lookups an easy hidden double-parse
-- If the diff touches PUT/GET/commit/erasure paths and claims 'no perf impact', demand numbers, not assertion: run the criterion benches (cargo bench -p ecstore — comparison_benchmark, erasure_benchmark, rename_data_meta_benchmark, single_block_non_inline_benchmark per crates/ecstore/benches/) against origin/main, and for end-to-end paths the warp A/B relative-budget gate (scripts/run_hotpath_warp_ab.sh --baseline-ref origin/main, as .github/workflows/performance-ab.yml runs it). Probe specifically at 4KiB object size — that is where the last real regression hid.
-  - Where: crates/ecstore/benches/, .github/workflows/performance-ab.yml, scripts/run_hotpath_warp_ab.sh
-  - Evidence: crates/ecstore/AGENTS.md: 'Benchmark-sensitive changes should include measurable rationale'; performance-ab.yml (215747022 #4480) is the repo's own relative-budget gate; the #4221 regression was only visible at 4KiB writes (#814 bisect)
-
-Null report example: "Attacked the new rename_data commit-section work, durability-gate routing of the added fdatasync, guard live-range across the shard-write awaits, and per-object clone count in the PUT path; ran comparison_benchmark + rename_data_meta_benchmark vs origin/main (4KiB delta within noise) — no break found."
-
-### Test-coverage skeptic
-
-- For every behavior claim in the PR description, revert that hunk (git stash / manual undo of the changed lines) and name the exact test (`cargo test -p <crate> <test_name>`) that fails. If no test fails on revert, the behavior is untested — file a finding, not a note. Especially verify the test exercises the REAL production call path, not a lookalike helper.
-  - Where: All crates; highest value in crates/ecstore, rustfs/src/storage, crates/heal
-  - Evidence: AGENTS.md exit criterion 'Every behavior change has a test that fails without it'. Real bug: PR #4220 (ghost-directory cleanup) merged with green tests but its fix never executed on the real delete path — required follow-up rustfs#4307, backlog#798 stayed OPEN. The tests exercised a path the production flow never took.
-- Read each added/modified test and confirm it asserts the real outcome (returned value, stored bytes, error variant), not merely 'call succeeded' or 'no panic'. Flag any test whose only observable is that the function returned, and any `assert!(result.is_err())` that never checks WHICH error. Then check: does the test prove the exploit/failure form is denied, or only that the intended form still works?
-  - Where: crates/e2e_test (security_boundary_test.rs pattern), and every #[cfg(test)] module in the diff
-  - Evidence: Commit dee8e4e63 (#4466) had to rewrite 277 lines of crates/e2e_test/src/security_boundary_test.rs because 'security boundary tests' passed without asserting real outcomes. .agents/skills/rust-code-quality/SKILL.md checklist: 'Every test function has at least one assert!'; .agents/skills/security-advisory-lessons/SKILL.md: 'Does the test prove the exploit form is denied, or only that the intended form still works?'
-- When the diff adds a boolean/mode parameter or config flag, find the test that fails if the flag's effect is INVERTED inside the changed function. Tests that were mechanically updated to pass `false`/default at every call site assert nothing about the new behavior. Execute the check: flip the flag's branch in the source and confirm at least one test goes red for each branch.
-  - Where: crates/ecstore/src/set_disk/ (e.g. build_codec_streaming_part_reader), any function gaining a parameter
-  - Evidence: Commit 05890d6e2 (#4573): PR #4560 added a 15th param allow_inplace_legacy_fallback; the arity tests were fixed by passing `false` everywhere — they assert Err outcomes independent of the flag, so the fallback behavior itself has no revert-detecting test at those sites.
-- Mutation spot-check on error propagation: for each newly added `?`, `return Err`, or error-mapping line, mentally replace it with `Ok(default)`/ignore and ask which test fails. The swallowed-error bug class recurs in this repo and always ships with green tests — a fix that propagates errors needs a test that injects the failure (faulty disk, failed rename, dispatch error) and asserts the caller sees Err.
-  - Where: crates/ecstore (disk delete/rename, reduce_errs), crates/audit, crates/notify, crates/targets
-  - Evidence: Three recent fixes for the same class: f7d2b2563 (#4546, disk delete/rename failures swallowed), dbc628f16 (#4424, audit dispatch failures swallowed), 20d61c73b (#4551, reduce_errs leaking nil placeholder as dominant error). All existed while tests were green.
-- Any test touching GET/read/reconstruct/stream paths must assert the FULL body content and exact length against a known value, not status-ok or first-bytes. Construct the degraded-read case (missing/inconsistent shards forcing EC reconstruction) and assert byte-for-byte equality; a mid-stream failure that truncates the body passes every test that only checks headers or the first chunk.
-  - Where: crates/ecstore/src/set_disk/read.rs and ops/, crates/rio, crates/e2e_test GET scenarios
-  - Evidence: Known live bug: EC reconstruct-read verification failure mid-GET at set_disk read path silently truncates the body → client 'unexpected EOF'; version-independent, undetected by existing suites because none assert full-body integrity under shard inconsistency.
-- For on-disk / on-wire format changes (xl.meta, .metadata.bin, bitrot framing), reject round-trip-only tests: a struct serialized and deserialized by the same code under test cannot catch format drift. Demand the test parse a REAL captured fixture from crates/filemeta/tests/fixtures, crates/ecstore/tests/fixtures, or crates/rio-v2/tests/minio_fixture_lab — or capture a new one from a single-disk MinIO instance (RELEASE.2025-07-23 procedure from #4377).
-  - Where: crates/filemeta, crates/ecstore (headers, msgpack bucket metadata), crates/rio-v2, migration code
-  - Evidence: Commit 073bc9675 (#4343): filemeta header signature was hardcoded to zero — round-trip tests passed for months. Commit a91d9cefc (#4377) established the real-MinIO fixture convention (inline/versioned/multipart xl.meta, HighwayHash256-prefixed inline bodies) precisely because synthetic fixtures proved nothing about interop.
-- Attack new concurrency tests for flakiness-by-construction: grep the added tests for `sleep(`, fixed timeouts under ~30s on lock acquisition, and use of shared global state (disk registry, lock client, GLOBAL_*). Serialized cross-disk commits exceed small lock timeouts under full-suite CI disk load. If the test shares global state or saturates IO, it must join the `ecstore-serial-flaky` nextest test-group in .config/nextest.toml (note: serial_test's #[serial] does NOT work — nextest runs each test in its own process). Require readiness polling, never fixed sleeps.
-  - Where: crates/ecstore tests, crates/e2e_test, .config/nextest.toml
-  - Evidence: Commit 2dfa3d3c3 (#4370): concurrent_resend test flaked with Lock(Timeout 5s) on CI — six legitimate serialized cross-disk commits under IO pressure needed 30s. Commit 7c701d9f2 (#4558) created the nextest test-group after bucket_delete_* raced make_bucket into InsufficientWriteQuorum. 65849740f (#4213) deflaked global-state contamination. crates/e2e_test/AGENTS.md: 'readiness checks and explicit polling over fixed sleep-based timing'.
-- If the diff writes internal object metadata, run the dual-key mutation: delete the `x-minio-internal-<suffix>` write (keeping only `x-rustfs-internal-`) and check whether any test fails. Because `get_bytes` prefers the RustFS key, every read-back test stays green while MinIO interop is silently broken — coverage must include an assertion that BOTH keys are present in the stored metadata map.
-  - Where: crates/utils/src/http/metadata_compat.rs and all its callers in crates/ecstore and rustfs/src/storage
-  - Evidence: CLAUDE.md domain convention: metadata must be written under both x-rustfs-internal- and x-minio-internal- keys for MinIO interop; get_bytes prefers the RustFS key, making the MinIO-key half of the invariant invisible to read-back tests.
-- For changed quorum/version/UUID logic, name the tests covering the specific poison values: quorum−1 disks, nil UUID, absent vs empty vs nil-serialized UUID bytes, and remote-tier version_id of None/"" (unversioned tier bucket → no versionId sent). Mutation check: remove a `.filter(|u| !u.is_nil())` guard from the diff and confirm a test fails; if none does, the nil-UUID class is uncovered.
-  - Where: crates/ecstore (tier recovery, heal, quorum paths), crates/filemeta, code reading UUIDs from xl.meta metadata
-  - Evidence: Commit 726f3dc18 (#4552) fixed rejection of empty remote version_id in tier recovery. CLAUDE.md invariant: absent/empty/nil UUID all mean 'no value', not Uuid::nil(). docs/operations/tier-ilm-debugging.md: None/"" tier version means unversioned bucket. df9cbc4ed (#4427): unvalidated distribution values caused shuffle index panic — edge values reached production untested.
-- For any pagination/limit/truncation change, construct the exact-boundary test: result count == max (page exactly full), max+1, and a delimiter re-fold that lands precisely on the page boundary — assert both the item count AND the is_truncated/continuation marker. Off-by-one at the page boundary is a recurring shipped bug here.
-  - Where: crates/ecstore listing paths (list_objects, ListMultipartUploads, metacache), S3 handlers in rustfs/src/storage
-  - Evidence: Two shipped boundary bugs: fefa70b31 (#4447) ListMultipartUploads returned one upload past max-uploads; d91f4d455 (#4538) delimiter re-fold of a full page lost the truncation flag. Both survived existing tests because no test pinned n == max exactly.
-- Green `cargo test -p <crate>` on the touched crate is not a coverage verdict for the diff's test code itself: run `cargo clippy --all-targets -p <crate>` and a workspace-wide test BUILD (`cargo check --workspace --all-targets` at minimum) before accepting the tests as evidence. Test-only code that doesn't compile workspace-wide or fails clippy has repeatedly broken main and masked whether tests ran at all.
-  - Where: All crates; especially concurrent-branch merges into crates/ecstore
-  - Evidence: #4322 broke main because only cargo test ran (field_reassign_with_default is clippy-only). b06f3df6b (#4441) and 05890d6e2 (#4573): test code broke the workspace test build (E0061) on main after textually-clean merges, failing CI for every open PR.
-
-Null report example: "Attacked revert-detection for all 3 claimed behaviors (each has a named test that fails on revert), flag-inversion on the new fallback parameter (both branches covered in codec_streaming tests), full-body assertions on the changed GET path, and n==max pagination boundary — no coverage gap found."
-
-## Sources and maintenance
-
-Probes are distilled from shipped bugs in git history (commit/PR references
-above), GitHub security advisories (see the security-advisory-lessons
-skill), scoped `AGENTS.md` rules, and invariants under `docs/architecture/`
-and `docs/operations/`. Line numbers drift; when a cited location no longer
-matches, trust the invariant and re-locate the code. When a new bug class
-ships, add a probe with its evidence here rather than growing the policy
-section in `AGENTS.md`.

.agents/skills/arch-checks/SKILL.md

@@ -1,58 +0,0 @@
----
-name: arch-checks
-description: Resolve failures from the repository's architecture guard scripts — check_layer_dependencies.sh, check_architecture_migration_rules.sh, check_unsafe_code_allowances.sh, check_logging_guardrails.sh, check_doc_paths.sh. Use when make pre-commit / pre-pr or CI fails on one of these checks.
----
-
-# Architecture Guard Checks
-
-All five run in `make pre-commit` / `make pre-pr` and in CI. Fix the cause;
-never weaken a check to get green.
-
-## `check_layer_dependencies.sh` — layer DAG in `rustfs/src`
-
-Enforces `interface (admin, storage/ecfs, storage/s3_api) → app → infra`; no
-upward imports. Known legacy violations live in
-`scripts/layer-dependency-baseline.txt`.
-
-- **New violation**: restructure your change so the dependency points
-  downward (move the shared type/function to the lower layer).
-- **You legitimately removed a baseline entry**: run
-  `./scripts/check_layer_dependencies.sh --update-baseline` and commit the
-  shrunken baseline. Never add new entries to the baseline to make a new
-  violation pass.
-
-## `check_architecture_migration_rules.sh` — required doc sections
-
-Asserts that the core docs under `docs/architecture/` (overview,
-crate-boundaries, runtime-lifecycle, readiness-matrix,
-storage-control-data-plane, global-state-crate-split-plan,
-ecstore-module-split-plan, …) still contain specific headings and exact
-source lines. If it fails after a doc edit, you reworded or removed a
-guarded line — restore the wording or update the script deliberately in the
-same PR, with rationale.
-
-## `check_unsafe_code_allowances.sh`
-
-Every `#[allow(unsafe_code)]` needs a `SAFETY:` comment within a few lines.
-Write the actual safety argument; don't add a placeholder.
-
-## `check_logging_guardrails.sh`
-
-A fixed list of security-sensitive files (auth, IAM, KMS, admin handlers…)
-is scanned for logging violations. If you created a new sensitive file,
-consider adding it to the script's `checked_files` list.
-
-## `check_doc_paths.sh`
-
-Instruction/architecture docs (`AGENTS.md`, `CLAUDE.md`, `ARCHITECTURE.md`,
-`docs/architecture/*.md`) must not reference repo file paths that no longer
-exist. If your refactor moved code, update the docs that point at it — the
-error message lists `doc -> stale-path` pairs.
-
-## `check_no_planning_docs.sh`
-
-Planning-type documents must not be committed (see AGENTS.md "Sources of
-Truth"). The guard fails if anything is tracked under `docs/superpowers/` —
-`.gitignore` already ignores it, but `git add -f` bypasses that, so this closes
-the hole. Fix by removing the listed file(s) with `git rm`; keep the plan or
-spec in the issue tracker or a local worktree instead.

.agents/skills/code-change-verification/SKILL.md

@@ -1,91 +0,0 @@
----
-name: code-change-verification
-description: Verify code changes by identifying correctness, regression, security, and performance risks from diffs or patches, then produce prioritized findings with file/line evidence and concrete fixes. Use when reviewing commits, PRs, and merged patches before/after release.
----
-
-# Code Change Verification
-
-Use this skill to review code changes consistently before merge, before release, and during incident follow-up.
-
-## Quick Start
-
-1. Read the scope: commit, PR, patch, or file list.
-2. Map each changed area by risk and user impact.
-3. Inspect each risky change in context.
-4. Report findings first, ordered by severity.
-5. Close with residual risks and verification recommendations.
-
-## Core Workflow
-
-### 1) Scope and assumptions
-- Confirm change source (diff, commit, PR, files), target branch, language/runtime, and version.
-- If context is missing, state assumptions before deeper analysis.
-- Focus only on requested scope; avoid reviewing unrelated files.
-
-### 2) Risk map
-- Prioritize in this order:
-  - Data correctness and user-visible behavior
-  - API/contract compatibility
-  - Security and authz/authn boundaries
-  - Concurrency and lifecycle correctness
-  - Performance and resource usage
-- Give higher priority to stateful paths, migration logic, defaults, and error handling.
-
-### 3) Evidence-based inspection
-- Read each modified hunk with neighboring context.
-- Trace call paths and call-site expectations.
-- Check for:
-  - invariant breaks and missing guards
-  - unchecked assumptions and null/empty/error-path handling
-  - stale tests, fixtures, and configs
-  - hidden coupling to shared helpers/constants/features
-- If a point is uncertain, mark it as an open question instead of guessing.
-
-#### Rust-specific checks (apply to all Rust changes)
-
-- **unwrap/expect in production**: Search changed files for `.unwrap()` and `.expect(` outside test modules. Every `unwrap()` in production code must have a justification comment or be replaced with `?`.
-- **Silent type truncation**: Search for `as u8/u16/u32/u64/usize/i8/i16/i32/i64/isize` casts. Every `as` cast must be justified; negative-to-unsigned and large-to-small are bugs by default. Use `try_into()` or explicit clamping.
-- **Unnecessary cloning**: Check `.clone()` calls in loops, per-request paths, and on structs with >5 heap-allocated fields. Consider `Arc`, references, or `Cow<str>`.
-- **Lock ordering**: If the change acquires multiple locks, verify the order matches all other call sites. Document the order in a comment.
-- **Locks across .await**: Flag any `tokio::sync::RwLock`/`Mutex` guard held across an `.await` point without bounded hold time.
-- **Recursion depth**: If the change adds or modifies a recursive function, verify it has a depth limit or uses iterative traversal with an explicit stack.
-- **Error types**: Flag `Result<_, String>`, `Box<dyn Error>`, and missing `Error::source()` implementations in public APIs.
-- **Test assertions**: Every test function must have at least one `assert!`. Flag tests that only call code without verifying results.
-- **println/eprintln**: Search changed files for `println!`/`eprintln!` outside test modules. Production code must use `tracing` macros.
-- **Serde safety**: Structs deserialized from untrusted input (S3 API, user config) should have `#[serde(deny_unknown_fields)]`.
-
-### 4) Findings-first output
-- Order findings by severity:
-  - P0: critical failure, security breach, or data loss risk
-  - P1: high-impact regression
-  - P2: medium risk correctness gap
-  - P3: low risk/quality debt
-- For each finding include:
-  - Severity
-  - `path:line` reference
-  - concise issue statement
-  - impact and likely failure mode
-  - specific fix or mitigation
-  - validation step to confirm
-- If no issues exist, explicitly state `No findings` and why.
-
-### 5) Close
-- Report assumptions and unknowns.
-- Suggest targeted checks (tests, canary checks, logs/metrics, migration validation).
-
-## Output Template
-
-1. Findings
-2. No findings (if applicable)
-3. Assumptions / Unknowns
-4. Recommended verification steps
-
-## Finding Template
-
-- `[P1] Missing timeout for downstream call`
-  - Location: `path/to/file.rs:123`
-  - Issue: ...
-  - Impact: ...
-  - Fix suggestion: ...
-  - Validation: ...
-

.agents/skills/code-change-verification/agents/openai.yaml

@@ -1,4 +0,0 @@
-interface:
-  display_name: "Code Change Verification"
-  short_description: "Prioritize risks and verify code changes before merge."
-  default_prompt: "Inspect a patch or diff, identify correctness/security/regression risks, and return prioritized findings with file/line evidence and fixes."

.agents/skills/plugin-contract-guard/SKILL.md

@@ -1,83 +0,0 @@
----
-name: plugin-contract-guard
-description: Invariants and change procedure for the target-plugin / extension system — plugin manifests, admin plugin/extension catalog and instance APIs, secret redaction, external-plugin install policy. Use when editing crates/targets (manifest, plugin, control_plane, catalog, runtime), crates/extension-schema, or rustfs/src/admin plugin_contract.rs / plugins_*.rs / extensions.rs / target_descriptor.rs.
----
-
-# Plugin & Extension Contract Guard
-
-The "plugin system" spans four surfaces that must stay consistent:
-
-| Surface | Location |
-|---|---|
-| Manifests & registry | `crates/targets/src/{manifest,plugin}.rs` |
-| Install/enable planning (control plane) | `crates/targets/src/control_plane.rs` |
-| Extension schemas | `crates/extension-schema/src/lib.rs`, `crates/targets/src/catalog/extension.rs` |
-| Admin API contract | `rustfs/src/admin/plugin_contract.rs`, `handlers/{plugins_catalog,plugins_instances,extensions,target_descriptor}.rs` |
-
-## Hard invariants (verify before merging)
-
-1. **Secrets have one source of truth.** Secret config keys are declared only
-   in the plugin manifest (`TargetPluginManifest.secret_fields`,
-   `crates/targets/src/manifest.rs`) and flow to admin via
-   `AdminTargetSpec.secret_fields`. Never add a hand-maintained per-service
-   secret table in a handler; if redaction misses a field, fix the manifest.
-
-2. **Redaction must round-trip.** Instance GET responses replace secret values
-   with `***redacted***` (`REDACTED_SECRET_VALUE` in `plugins_instances.rs`).
-   Instance PUT restores the stored secret when it receives that placeholder
-   back (`restore_redacted_secret_values`). Any new read or write path for
-   target config must keep both halves: redact on the way out, restore the
-   placeholder on the way in. The placeholder literal must never be persisted.
-
-3. **Fixtures never reach production responses.**
-   `example_external_webhook_plugin()` (`crates/targets/src/catalog/mod.rs`)
-   is a test/demo fixture for control-plane planning tests. Production
-   catalog/extension handlers must not include it; regression tests
-   (`plugin_catalog_never_exposes_example_or_external_fixtures`,
-   `extension_catalog_never_exposes_example_or_external_fixtures`) enforce it.
-
-4. **External plugin flow is planning-only and deny-by-default.**
-   `plan_external_target_plugin_action` returns decisions, it executes
-   nothing. `TargetPluginExternalFlowGate::default()` is fully closed and
-   `TargetPluginInstallPolicy::default().allowed_download_hosts` is empty —
-   keep it that way; tests opt in via explicit policies. Install validation
-   requires https, an allowlisted host, a full 64-hex-char sha256 digest,
-   signature and provenance URIs, and an artifact matching the host
-   `target_triple`.
-
-5. **Custom target types must not collide.** Unknown target types get an
-   interned unique `custom:<type>` plugin id (`custom_plugin_id` in
-   `manifest.rs`). Custom plugins with secrets must register via
-   `TargetPluginDescriptor::with_manifest` and declare `secret_fields`;
-   `::new` derives a manifest with no secrets.
-
-## Changing the admin JSON contract
-
-- Shapes are locked twice in `plugin_contract.rs` tests: insta snapshots
-  (`rustfs/src/admin/snapshots/`) plus literal `json!` assertions. Update
-  both deliberately; a shape change is a console-facing API change.
-- Field naming is `snake_case`, except discovery blocks
-  (`runtimeCapabilities`, `clusterSnapshot`, `extensionsCatalog`) which are
-  camelCase **by cross-endpoint convention** (same shape in `system.rs`,
-  `console.rs`, `pools.rs`). Do not "fix" that inconsistency locally.
-- Contract types deliberately duplicate `rustfs_targets` types
-  (anti-corruption layer). Add a `From` impl; do not serialize internal
-  types directly.
-
-## Handler conventions
-
-- Every new admin plugin/extension route needs authorization at the top of
-  `call` and an `include_str!` guard test asserting it (repo-wide pattern —
-  see `plugin_instance_handlers_require_admin_authorization_contract`).
-- Reads use `GetBucketTargetAction` (instances) or `ServerInfoAdminAction`
-  (catalogs); writes use `SetBucketTargetAction`.
-- Refresh persisted module switches once per request
-  (`refresh_persisted_module_switches`), then evaluate the sync
-  `module_disabled_block_reason` per domain — do not re-read the store per
-  domain or per instance.
-
-## Generic bounds
-
-Event-payload generics use the `PluginEvent` blanket trait
-(`crates/targets/src/plugin.rs`). Do not respell
-`Send + Sync + 'static + Clone + Serialize + DeserializeOwned`.

.agents/skills/pr-creation-checker/SKILL.md

@@ -1,94 +0,0 @@
----
-name: pr-creation-checker
-description: Prepare PR-ready diffs by validating scope, checking required verification steps, drafting a compliant English PR title/body, and surfacing blockers before opening or updating a pull request in RustFS.
----
-
-# PR Creation Checker
-
-Use this skill before `gh pr create`, before `gh pr edit`, or when reviewing whether a branch is ready for PR.
-
-## Read sources of truth first
-
-- Read `AGENTS.md`.
-- Read `.github/pull_request_template.md`.
-- Use `Makefile` and `.config/make/` for local quality commands.
-- Use `.github/workflows/ci.yml` for CI expectations.
-- Do not restate long command matrices or template sections from memory when the files exist.
-
-## Workflow
-
-1. Collect PR context
-- Confirm base branch, current branch, change goal, and scope.
-- Confirm whether the task is: draft a new PR, update an existing PR, or preflight-check readiness.
-- Confirm whether the branch includes only intended changes.
-
-2. Inspect change scope
-- Review the diff and summarize what changed.
-- Call out unrelated edits, generated artifacts, logs, or secrets as blockers.
-- Mark risky areas explicitly: auth, storage, config, network, migrations, breaking changes.
-- Scan the diff for newly added string literals and confirm whether they duplicate values already defined as constants/enums/typed wrappers in the same module or shared modules.
-- Treat introducing a new hardcoded literal where a project constant already exists as a likely regression risk; require either a refactor to reuse the constant or an explicit exception explanation in the PR body.
-
-3. Verify readiness requirements
-- Require `make pre-commit` before marking PRs ready when the diff changes Rust code, product behavior, CI behavior, runtime configuration, security-sensitive logic, migrations, storage, auth, networking, or other high-risk paths.
-- For documentation-only, agent-instruction-only, or local developer-tooling-only changes, allow focused verification instead of `make pre-commit` when it directly validates the changed surface.
-- For focused verification, explain why the full gate was not run and list the scope-specific commands in the PR body.
-- If `make` is unavailable, use the equivalent commands from `.config/make/`.
-- Add scope-specific verification commands when the changed area needs more than the baseline.
-- If required checks fail, stop and return `BLOCKED`.
-
-4. Draft PR metadata
-- Write the PR title in English using Conventional Commits and keep it within 72 characters.
-- If a generic PR workflow suggests a different title format, ignore it and follow the repository rule instead.
-- In RustFS, do not use tool-specific prefixes such as `[codex]` when the repository requires Conventional Commits.
-- Keep the PR body in English.
-- Use the exact section headings from `.github/pull_request_template.md`.
-- Fill non-applicable sections with `N/A`.
-- Include verification commands in the PR description.
-- Do not include local filesystem paths in the PR body unless the user explicitly asks for them.
-- Prefer repo-relative paths, command names, and concise summaries over machine-specific paths such as `/Users/...`.
-
-5. Prepare reviewer context
-- Summarize why the change exists.
-- Summarize what was verified.
-- Call out risks, rollout notes, config impact, and rollback notes when applicable.
-- Mention assumptions or missing context instead of guessing.
-
-6. Prepare CLI-safe output
-- When proposing `gh pr create` or `gh pr edit`, use `--body-file`, never inline `--body` for multiline markdown.
-- Return a ready-to-save PR body plus a short title.
-- If not ready, return blockers first and list the minimum steps needed to unblock.
-
-## Output format
-
-### Status
-- `READY` or `BLOCKED`
-
-### Title
-- `<type>(<scope>): <summary>`
-
-### PR Body
-- Reproduce the repository template headings exactly.
-- Fill every section.
-- Omit local absolute paths unless explicitly required.
-
-### Verification
-- List each command run.
-- State pass/fail.
-
-### Risks
-- List breaking changes, config changes, migration impact, or `N/A`.
-
-## Blocker rules
-
-- Return `BLOCKED` if a code, behavior, CI, runtime configuration, security-sensitive, migration, storage, auth, networking, or other high-risk change has not passed `make pre-commit`.
-- Return `BLOCKED` if a documentation-only, agent-instruction-only, or local developer-tooling-only change lacks focused verification for the changed surface.
-- Return `BLOCKED` if the diff contains unrelated changes that are not acknowledged.
-- Return `BLOCKED` if required template sections are missing.
-- Return `BLOCKED` if the title/body is not in English.
-- Return `BLOCKED` if the title does not follow the repository's Conventional Commit rule.
-- Return `BLOCKED` if the diff introduces string literals that should use existing constants but did not.
-
-## Reference
-
-- Use [pr-readiness-checklist.md](references/pr-readiness-checklist.md) for a short final pass before opening or editing the PR.

.agents/skills/pr-creation-checker/agents/openai.yaml

@@ -1,4 +0,0 @@
-interface:
-  display_name: "PR Creation Checker"
-  short_description: "Draft RustFS-ready PRs with checks, template, and blockers."
-  default_prompt: "Inspect a branch or diff, verify required PR checks, and produce a compliant English PR title/body plus blockers or readiness status."

.agents/skills/pr-creation-checker/references/pr-readiness-checklist.md

@@ -1,16 +0,0 @@
-# PR Readiness Checklist
-
-- Confirm the branch is based on current `main`.
-- Confirm the diff matches the stated scope.
-- Confirm no secrets, logs, temp files, or unrelated refactors are included.
-- Confirm `make pre-commit` passed for code, behavior, CI, runtime configuration, security-sensitive, migration, storage, auth, networking, or other high-risk changes.
-- For documentation-only, agent-instruction-only, or local developer-tooling-only changes, confirm focused verification covered the changed surface and the PR body explains why the full gate was not run.
-- Confirm extra verification commands are listed for risky changes.
-- Confirm the PR title uses Conventional Commits and stays within 72 characters.
-- Confirm the PR title does not use tool-specific prefixes such as `[codex]`.
-- Confirm the PR body is in English.
-- Confirm the PR body keeps the exact headings from `.github/pull_request_template.md`.
-- Confirm non-applicable sections are filled with `N/A`.
-- Confirm the PR body does not include local absolute paths unless explicitly required.
-- Confirm multiline GitHub CLI commands use `--body-file`.
-- Confirm new hardcoded string literals were not introduced for values already represented by existing constants/enums (including protocol labels, error identifiers, headers, and metric names), or record a justified exception.

.agents/skills/rust-code-quality/SKILL.md

@@ -1,112 +0,0 @@
----
-name: rust-code-quality
-description: Enforce Rust-specific code quality rules on every code change. Use before merge to catch unwrap abuse, silent truncation, unnecessary cloning, lock ordering violations, recursion risks, and error type anti-patterns.
----
-
-# Rust Code Quality Gate
-
-Use this skill on every Rust code change to enforce quality rules that `cargo clippy` does not catch.
-
-## Quick Start
-
-1. Identify changed `.rs` files.
-2. Run automated checks on changed files.
-3. Run manual review checklist on the diff.
-4. Report findings; block merge if P0/P1 issues exist.
-
-## Automated Checks
-
-Run these on every changed `.rs` file (excluding test modules):
-
-```bash
-# 1. unwrap/expect in production code
-rg -n '\.unwrap\(\)|\.expect\(' <changed-files> | grep -v '#\[cfg(test)\]' | grep -v 'test' | grep -v 'bench'
-
-# 2. Silent type truncation via `as` cast
-rg -n ' as (u8|u16|u32|u64|usize|i8|i16|i32|i64|isize)\b' <changed-files>
-
-# 3. String as error type
-rg -n 'Result<.*String>' <changed-files> | grep -v test
-
-# 4. Box<dyn Error> in public APIs
-rg -n 'Box<dyn.*Error' <changed-files> | grep -v test
-
-# 5. println/eprintln in production
-rg -n 'println!\|eprintln!' <changed-files> | grep -v test
-
-# 6. Ordering::Relaxed usage (verify each is intentional)
-rg -n 'Ordering::Relaxed' <changed-files>
-```
-
-## Manual Review Checklist
-
-For every Rust code change, verify:
-
-### Error Handling
-- [ ] No `unwrap()` or `expect()` in production code without justification comment
-- [ ] No `Result<_, String>` in public API signatures
-- [ ] No `Box<dyn Error>` in public trait/struct methods
-- [ ] `Error::source()` is overridden when inner error is stored
-- [ ] Error messages are actionable (what failed, with what input)
-
-### Type Safety
-- [ ] No silent `as` truncation (negative→unsigned, large→small)
-- [ ] `try_into()` or explicit clamping used for numeric conversions
-- [ ] No `f64 as usize` without prior clamping
-
-### Concurrency
-- [ ] Lock acquisition order is documented when multiple locks are used
-- [ ] No `tokio::sync` write guards held across `.await` without bounded hold time
-- [ ] Concurrent counters use `compare_exchange` loops, not load-then-store
-- [ ] `std::sync::Mutex` in async context is held only briefly, never across `.await`
-
-### Memory and Performance
-- [ ] No `.clone()` on structs with >5 heap-allocated fields in hot paths
-- [ ] `HashMap::with_capacity()` / `Vec::with_capacity()` used when size is known
-- [ ] Large buffers wrapped in `Arc` rather than cloned
-- [ ] Temporary string computations use `&str` or `Cow<str>` instead of `String`
-
-### Recursion Safety
-- [ ] Recursive functions have a depth limit or use iterative traversal
-- [ ] Tree/cache traversals handle corrupted/cyclic input safely
-
-### Testing
-- [ ] Every test function has at least one `assert!`
-- [ ] Tests use `.expect("context")` not bare `.unwrap()`
-- [ ] No `println!`/`eprintln!` in production code (use `tracing`)
-
-### Serde
-- [ ] Structs from untrusted input have `#[serde(deny_unknown_fields)]`
-- [ ] `#[serde(default)]` not used on security-critical fields without validation
-
-### Code Hygiene
-- [ ] No `#![allow(dead_code)]` at crate root
-- [ ] No camelCase statics or Hungarian notation
-- [ ] New string literals don't duplicate existing constants
-
-## Severity Classification
-
-- **P0 (Block merge)**: `unwrap()` in request hot path, silent truncation on user input, lock ordering violation, recursion without depth limit
-- **P1 (Must fix)**: `Result<_, String>` in public API, unnecessary clone in hot path, `Box<dyn Error>` in trait method
-- **P2 (Should fix)**: Missing `assert!` in test, `println!` in production, missing `with_capacity`
-- **P3 (Nice to fix)**: Naming convention violation, missing doc comment, `as_ptr()` vs `Arc::ptr_eq`
-
-## Output Template
-
-```
-## Rust Code Quality Report
-
-### Automated Scan
-- unwrap/expect in production: N found
-- as casts: N found
-- String errors: N found
-- println/eprintln: N found
-
-### Findings
-- [P1] `path:line` — description
-  - Fix: ...
-  - Validation: ...
-
-### Verdict
-PASS / BLOCKED (list blocking findings)
-```

.agents/skills/rust-code-quality/references/checklist.md

@@ -1,52 +0,0 @@
-# Rust Code Quality Checklist
-
-Use this as a quick pre-merge checklist for every Rust code change.
-
-## Critical (P0 — block merge)
-
-| Check | Command |
-|-------|---------|
-| No `unwrap()` in request/storage hot path | `rg '\.unwrap\(\)' <files> \| grep -v test` |
-| No `as` truncation on user input | `rg ' as (u32\|usize\|i32)' <files>` |
-| Lock order consistent across call sites | Manual: trace all lock acquisitions |
-| Recursive functions have depth limit | Manual: check for `max_depth` or iterative pattern |
-| No `panic!`/`unwrap_or_else(panic!)` in production | `rg 'panic!\|unwrap_or_else.*panic' <files> \| grep -v test` |
-
-## High (P1 — must fix)
-
-| Check | Command |
-|-------|---------|
-| No `Result<_, String>` in public API | `rg 'Result<.*String>' <files> \| grep -v test` |
-| No `Box<dyn Error>` in public trait | `rg 'Box<dyn.*Error' <files> \| grep -v test` |
-| No unnecessary `.clone()` in hot path | Manual: check loops and per-request paths |
-| `Error::source()` implemented when inner error stored | Manual: check `impl Error` |
-| No `eprintln!`/`println!` in production | `rg 'println!\|eprintln!' <files> \| grep -v test` |
-
-## Medium (P2 — should fix)
-
-| Check | Command |
-|-------|---------|
-| Tests have assertions | Manual: check for `assert` in test functions |
-| `HashMap`/`Vec` use `with_capacity` when size known | Manual: check `::new()` in loops |
-| No `#![allow(dead_code)]` at crate root | `rg 'allow.dead_code' <files> \| grep 'lib.rs'` |
-| Serde structs from untrusted input have `deny_unknown_fields` | Manual: check `#[derive(Deserialize)]` |
-
-## Low (P3 — nice to fix)
-
-| Check | Command |
-|-------|---------|
-| No camelCase statics | `rg 'static ref [a-z]' <files>` |
-| `Arc::ptr_eq` instead of `as_ptr + ptr::eq` | `rg 'as_ptr\|ptr::eq' <files>` |
-| Public functions have doc comments | `rg 'pub fn' <files> \| grep -v '///'` |
-
-## Quick One-Liner
-
-```bash
-# Run all automated checks on changed files
-CHANGED=$(git diff --name-only HEAD~1 -- '*.rs' | grep -v test | grep -v bench)
-echo "=== unwrap/expect ===" && rg -c '\.unwrap\(\)|\.expect\(' $CHANGED 2>/dev/null
-echo "=== as casts ===" && rg -c ' as (u8|u16|u32|u64|usize|i8|i16|i32|i64|isize)\b' $CHANGED 2>/dev/null
-echo "=== String errors ===" && rg -c 'Result<.*String>' $CHANGED 2>/dev/null
-echo "=== println ===" && rg -c 'println!|eprintln!' $CHANGED 2>/dev/null
-echo "=== Ordering::Relaxed ===" && rg -c 'Ordering::Relaxed' $CHANGED 2>/dev/null
-```

.agents/skills/rustfs-logging-governance/SKILL.md

@@ -1,107 +0,0 @@
----
-name: rustfs-logging-governance
-description: Standardize and review RustFS logging with structured `tracing` events, lower noise on hot paths, preserve security-sensitive diagnostics, and extend guardrails to prevent legacy logging patterns from returning. Use when editing or reviewing RustFS logs, startup/config diagnostics, cloud metadata logs, request validation logs, or `scripts/check_logging_guardrails.sh`.
----
-
-# RustFS Logging Governance
-
-Use this skill when RustFS logging needs to be added, cleaned up, reviewed, or protected against regressions.
-
-## Quick Start
-
-1. Identify the files whose logs are changing.
-2. Scan current `tracing` or `log` macros before editing.
-3. Convert sentence-style logs to short event-style logs.
-4. Demote hot-path success logs unless operators truly need them at `info`.
-5. Preserve failure, fallback, and security-relevant diagnostics.
-6. Update `scripts/check_logging_guardrails.sh` when a broad cleanup removes a legacy pattern class.
-7. Validate with formatting, targeted checks/tests, and the logging guardrail script.
-
-## Core Workflow
-
-### 1. Scope the logging surface
-
-- Read the changed module in full before touching log lines.
-- Classify the log site:
-  - lifecycle/startup
-  - request or validation path
-  - background loop or hot path
-  - fallback/degraded behavior
-  - cloud metadata or external fetch path
-  - metrics/config summary
-- Do not rewrite business logic to make logging easier.
-
-### 2. Use the RustFS event shape
-
-- Prefer fields first, message second.
-- Use short labels, not prose paragraphs.
-- Default field shape:
-  - `event`
-  - `component`
-  - `subsystem`
-  - `state` or `result`
-  - key context fields
-- Reuse stable field names and avoid inventing near-duplicates.
-
-See `references/logging-governance.md` for the event model, level policy, and anti-pattern list.
-
-### 3. Choose the right level
-
-- `error`: operation failure that affects behavior or security guarantees.
-- `warn`: degraded path, fallback, suspicious input, or operator-actionable misconfiguration.
-- `info`: low-frequency lifecycle or mode selection.
-- `debug`: targeted diagnostics and low-volume detail.
-- `trace`: hot-path and repetitive success-path events.
-
-When in doubt, lower the verbosity of normal success paths and keep structured detail in fields.
-
-### 4. Preserve security and privacy boundaries
-
-- Do not log secrets, tokens, auth headers, raw credential payloads, or merged config dumps.
-- Avoid logging raw forwarded headers or full trusted network inventories above `debug`.
-- Keep warning/error logs useful without echoing attacker-controlled payloads unnecessarily.
-
-### 5. Keep summaries aggregated
-
-- Replace multi-line startup banners or checklist logs with one structured event.
-- If metrics already express a concept, avoid duplicating it with many `info!` lines.
-- Prefer counts, modes, and sources over inventories unless debug detail is truly needed.
-
-### 6. Update guardrails when needed
-
-- Broad logging cleanup should usually extend `scripts/check_logging_guardrails.sh`.
-- Add forbidden patterns only for styles the repo has intentionally retired:
-  - sentence-style lifecycle logs
-  - noisy hot-path `info!`
-  - checklist-style summary logs
-  - legacy fallback wording that has been replaced by structured fields
-- Keep guardrails concrete and grep-friendly.
-
-### 7. Validate manually
-
-Use the smallest relevant set:
-
-```bash
-cargo fmt --all --check
-./scripts/check_logging_guardrails.sh
-cargo check -p <affected-crate>
-cargo test -p <affected-crate>
-```
-
-For broader Rust changes, add:
-
-```bash
-./scripts/check_unsafe_code_allowances.sh
-./scripts/check_architecture_migration_rules.sh
-cargo clippy -p <affected-crates> --all-targets -- -D warnings
-```
-
-## RustFS-Specific Notes
-
-- The durable RustFS logging direction is `event + component + subsystem + state/result + key context fields`.
-- `crates/concurrency` and `crates/trusted-proxies` are examples of this style for lifecycle, fallback, and cloud metadata logs.
-- `scripts/check_logging_guardrails.sh` is the enforcement point for preventing removed log styles from returning.
-
-## References
-
-- Read `references/logging-governance.md` when you need the detailed field set, anti-pattern examples, or guardrail update checklist.

.agents/skills/rustfs-logging-governance/agents/openai.yaml

@@ -1,4 +0,0 @@
-interface:
-  display_name: "RustFS Logging Governance"
-  short_description: "Standardize RustFS logs with structured events and guardrails."
-  default_prompt: "Use $rustfs-logging-governance to standardize or review RustFS logging, reduce noise, and update guardrails."

.agents/skills/rustfs-logging-governance/references/logging-governance.md

@@ -1,285 +0,0 @@
-# RustFS Logging Governance Reference
-
-## Workspace Scope Map
-
-Use `Cargo.toml` `[workspace].members` as the source of truth for crate membership. When doing a broad logging sweep, classify crates by operational role so logs stay consistent within each role.
-
-### Core Server And Request Handling
-
-- `rustfs`
-  - Role: top-level server, startup, auth, admin wiring, S3 request handling.
-  - Logging focus: startup lifecycle, config summaries, authn/authz failures, protocol entrypoints, degraded subsystems.
-- `crates/protocols`
-  - Role: protocol integrations such as FTP, SFTP, WebDAV, and related server-side protocol layers.
-  - Logging focus: listener lifecycle, per-protocol enablement/disablement, request bridge failures.
-- `crates/madmin`
-  - Role: admin API contracts and management interfaces.
-  - Logging focus: admin action boundaries, validation failures, compatibility warnings.
-- `crates/trusted-proxies`
-  - Role: forwarded IP trust, proxy chain validation, cloud metadata sources.
-  - Logging focus: direct/trusted/fallback decisions, degraded metadata fetches, aggregated config summaries.
-- `crates/keystone`
-  - Role: Keystone auth integration.
-  - Logging focus: integration enablement, upstream auth failures, config safety without credential leakage.
-
-### Storage, Healing, And Data Plane
-
-- `crates/ecstore`
-  - Role: erasure-coded storage implementation and peer/store initialization.
-  - Logging focus: disk/peer lifecycle, storage fallback, object I/O failures, avoid per-object noise.
-- `crates/heal`
-  - Role: healing orchestration and repair workflows.
-  - Logging focus: scheduler lifecycle, repair decisions, backlog or skipped work summaries, avoid repetitive task spam at `info`.
-- `crates/scanner`
-  - Role: data integrity scanning and health monitoring.
-  - Logging focus: scan lifecycle, compaction/deep-heal transitions, lag/backlog, noisy folder iteration should stay at `debug/trace`.
-- `crates/object-capacity`
-  - Role: capacity scan and refresh core.
-  - Logging focus: refresh lifecycle, degraded capacity sources, aggregate stats rather than per-object chatter.
-- `crates/filemeta`
-  - Role: file metadata parsing and helpers.
-  - Logging focus: parse failures, schema/format mismatch, avoid dumping raw metadata payloads.
-- `crates/storage-api`
-  - Role: storage contracts and shared data plane interfaces.
-  - Logging focus: contract mismatch and boundary diagnostics, usually low-volume.
-- `crates/checksums`
-  - Role: checksum helpers and validation.
-  - Logging focus: integrity failures and compatibility mismatches, not per-chunk success logs.
-- `crates/zip`
-  - Role: ZIP handling and compression helpers.
-  - Logging focus: parse/extract failures, archive path safety issues, avoid verbose file-by-file success logs.
-
-### Security, Identity, And Policy
-
-- `crates/iam`
-  - Role: identity and access management.
-  - Logging focus: authz decision boundaries, imported payload safety, do not leak principals, secrets, or claims.
-- `crates/policy`
-  - Role: policy modeling and evaluation.
-  - Logging focus: deny/allow decision context, parser/validation failures, no raw secret-bearing request dumps.
-- `crates/credentials`
-  - Role: credential handling.
-  - Logging focus: never log secrets or tokens; only safe identifiers and redacted states.
-- `crates/kms`
-  - Role: key management service integration.
-  - Logging focus: init/health/fallback, key-source availability, never log key material.
-- `crates/crypto`
-  - Role: cryptographic helpers and security primitives.
-  - Logging focus: only algorithm or mode state, not plaintext, ciphertext, or secret-derived material.
-- `crates/security-governance`
-  - Role: security governance contracts.
-  - Logging focus: policy/state transitions and enforcement diagnostics.
-- `crates/signer`
-  - Role: request signing helpers.
-  - Logging focus: signature validation failures without expected-signature leakage.
-
-### Notifications, Audit, And Targets
-
-- `crates/notify`
-  - Role: notification dispatch, runtime facade, notifier implementations.
-  - Logging focus: target lifecycle, dispatch summaries, stream lag/backpressure, avoid per-event success spam.
-- `crates/audit`
-  - Role: audit target fan-out and audit pipeline management.
-  - Logging focus: pipeline lifecycle, target availability, batch dispatch summaries, avoid noisy "started successfully" prose.
-- `crates/targets`
-  - Role: target-specific configuration and utilities used by fan-out style systems.
-  - Logging focus: target selection, config validation, per-target degraded state.
-- `crates/s3-types`
-  - Role: S3 event and type definitions.
-  - Logging focus: usually minimal; keep logging at integration boundaries rather than low-level type crates.
-- `crates/s3-ops`
-  - Role: S3 operation definitions and mapping.
-  - Logging focus: mapping/contract failures, unsupported combinations, not normal-path request spam.
-
-### Concurrency, Locking, And Runtime Foundations
-
-- `crates/concurrency`
-  - Role: timeout, locking, backpressure, and I/O scheduling facade.
-  - Logging focus: lifecycle transitions and degraded states, not high-frequency worker/permit churn at `info`.
-- `crates/lock`
-  - Role: distributed locking implementation.
-  - Logging focus: lock lifecycle, contention anomalies, lock ordering or timeout diagnostics.
-- `crates/tls-runtime`
-  - Role: shared TLS runtime foundation.
-  - Logging focus: certificate lifecycle, reload/fallback, validation failures without sensitive dumps.
-- `crates/obs`
-  - Role: observability helpers.
-  - Logging focus: this crate shapes other crates' telemetry conventions; avoid recursive or redundant summaries.
-- `crates/io-core`
-  - Role: zero-copy I/O core primitives.
-  - Logging focus: keep very sparse; prefer metrics unless failures are actionable.
-- `crates/io-metrics`
-  - Role: I/O metrics collection.
-  - Logging focus: typically minimal; metrics should carry the hot-path signal.
-- `crates/rio`
-  - Role: Rust I/O utility layer.
-  - Logging focus: compatibility or runtime boundary failures, not fast-path internals.
-- `crates/rio-v2`
-  - Role: next-generation I/O compatibility layer.
-  - Logging focus: migration/feature-mode differences and degraded fallback between I/O paths.
-- `crates/utils`
-  - Role: shared helpers.
-  - Logging focus: usually avoid direct logging in generic helpers unless the helper is itself an operational boundary.
-- `crates/common`
-  - Role: shared data structures and helpers.
-  - Logging focus: same principle as `utils`; prefer callers to log context-rich events.
-- `crates/config`
-  - Role: configuration management.
-  - Logging focus: config source, fallback, validation, and summary aggregation; avoid dumping merged configs.
-- `crates/data-usage`
-  - Role: shared data usage models and algorithms.
-  - Logging focus: refresh lifecycle, summary stats, and degraded reads.
-
-### Schema, Contracts, And API Support
-
-- `crates/protos`
-  - Role: protobuf definitions.
-  - Logging focus: usually none inside the crate; emit logs at decode/use boundaries.
-- `crates/extension-schema`
-  - Role: extension schema contracts.
-  - Logging focus: schema validation and compatibility mismatches.
-- `crates/s3select-api`
-  - Role: S3 Select API interfaces.
-  - Logging focus: request validation and unsupported feature boundaries.
-- `crates/s3select-query`
-  - Role: S3 Select query engine.
-  - Logging focus: query parse/planning/execution failures, avoid row-level spam.
-- `crates/protocols`
-  - Role: non-S3 protocol support.
-  - Logging focus: see core server section; keep per-request verbosity below `info`.
-
-### Testing And Non-Production Crates
-
-- `crates/e2e_test`
-  - Role: end-to-end tests.
-  - Logging focus: test clarity matters more than production governance, but avoid copying test-only logging style into production crates.
-
-## Current Guardrail Coverage Map
-
-`scripts/check_logging_guardrails.sh` currently enforces retired patterns in these high-signal areas:
-
-- `rustfs/src/main.rs`
-- `rustfs/src/startup_iam.rs`
-- `rustfs/src/auth.rs`
-- `rustfs/src/protocols/client.rs`
-- `crates/audit/src/pipeline.rs`
-- `crates/audit/src/system.rs`
-- `crates/audit/src/global.rs`
-- `crates/notify/src/config_manager.rs`
-- `crates/notify/src/runtime_facade.rs`
-- `crates/notify/src/notifier.rs`
-- `crates/ecstore/src/store/peer.rs`
-- `crates/ecstore/src/store/init.rs`
-- `crates/ecstore/src/tier/tier.rs`
-- `crates/concurrency/src/workers.rs`
-- `crates/concurrency/src/manager.rs`
-- `crates/concurrency/src/lock.rs`
-- `crates/concurrency/src/deadlock.rs`
-- `crates/trusted-proxies/src/global.rs`
-- `crates/trusted-proxies/src/config/loader.rs`
-- `crates/trusted-proxies/src/proxy/metrics.rs`
-- `crates/trusted-proxies/src/proxy/validator.rs`
-- `crates/trusted-proxies/src/proxy/chain.rs`
-- `crates/trusted-proxies/src/middleware/service.rs`
-- `crates/trusted-proxies/src/cloud/detector.rs`
-- `crates/trusted-proxies/src/cloud/ranges.rs`
-- `crates/trusted-proxies/src/cloud/metadata/aws.rs`
-- `crates/trusted-proxies/src/cloud/metadata/azure.rs`
-- `crates/trusted-proxies/src/cloud/metadata/gcp.rs`
-
-When expanding coverage, prefer crates with:
-
-- repeated sentence-style lifecycle logs
-- high-frequency success-path `info!`
-- startup/config checklist banners
-- security-sensitive fallback wording
-- external fetch/retry/fallback flows
-
-That typically means the next broad candidates are `rustfs`, `crates/notify`, `crates/audit`, `crates/targets`, `crates/heal`, and `crates/scanner`.
-
-## Event Model
-
-Prefer this structure when the fields are available:
-
-- `event`
-- `component`
-- `subsystem`
-- `state` or `result`
-- stable context fields such as:
-  - `enabled`
-  - `implementation`
-  - `validation_mode`
-  - `peer_ip`
-  - `client_ip`
-  - `proxy_hops`
-  - `duration_ms`
-  - `fallback`
-  - `reason`
-  - `range_count`
-  - `hold_time_ms`
-  - `available_slots`
-  - `total_slots`
-  - `permits_in_use`
-
-## Level Policy
-
-- `error`: the operation fails and callers or security guarantees are affected.
-- `warn`: a degraded path, fallback, suspicious request, or operator-actionable config issue occurs.
-- `info`: a low-frequency lifecycle or mode transition occurs.
-- `debug`: useful diagnostics exist but normal operators do not need them all the time.
-- `trace`: hot-path and repetitive success-path details occur.
-
-## Preferred Patterns
-
-- Use a short message label:
-  - `"trusted proxy validation failed"`
-  - `"concurrency manager state changed"`
-  - `"trusted proxy cloud metadata loaded"`
-- Put key meaning into fields, not only the message text.
-- Aggregate config or metrics summaries into one log event.
-
-## Retired Patterns
-
-These should usually be removed or replaced:
-
-- Sentence-style lifecycle logs:
-  - `info!("Concurrency manager stopped")`
-  - `info!("Trusted Proxies module initialized")`
-- Checklist or banner logs:
-  - `info!("=== Application Configuration ===")`
-  - `info!("Available metrics:")`
-- Hot-path noise:
-  - `info!("worker take, {}", *available)`
-  - `debug!("Proxy validation successful in {:?}", duration)`
-- Legacy fallback prose:
-  - `"Request from private network but not trusted: ..."`
-  - `"Cloud metadata fetching is disabled"`
-
-## Guardrail Update Checklist
-
-When extending `scripts/check_logging_guardrails.sh`:
-
-1. Add the touched files to `checked_files`.
-2. Add only legacy patterns that have been intentionally retired.
-3. Keep patterns literal and grep-friendly.
-4. Run the guardrail script after changes.
-5. Avoid adding patterns for logs that are still valid elsewhere in the repo.
-
-## Validation Checklist
-
-For logging-only changes:
-
-```bash
-cargo fmt --all --check
-./scripts/check_logging_guardrails.sh
-cargo check -p <affected-crate>
-cargo test -p <affected-crate>
-```
-
-For broader Rust changes:
-
-```bash
-./scripts/check_unsafe_code_allowances.sh
-./scripts/check_architecture_migration_rules.sh
-cargo clippy -p <affected-crates> --all-targets -- -D warnings
-```

.agents/skills/rustfs-release-version-bump/SKILL.md

@@ -1,124 +0,0 @@
----
-name: rustfs-release-version-bump
-description: "Publish a RustFS alpha/beta/stable release with an auditable flow: confirm target version and scope, update workspace and release assets (including strict rustfs.spec changelog identity/date/version format), run required verification, and finish with commit, push, and GitHub PR creation."
----
-# RustFS Release Version Bump
-
-Use this skill to publish a RustFS release (alpha, beta, or stable) with a minimal, auditable diff and a complete ship flow (`edit -> verify -> commit -> push -> PR`).
-
-Validated baseline: release pattern used in PR `#2957`.
-
-## Required inputs
-
-- Exact target version, for example `1.0.0-beta.4`.
-- Delivery scope:
-- Local only (`edit/verify`).
-- Local + git (`commit/push`).
-- Full GitHub flow (`commit/push/PR`).
-
-If target version is missing or ambiguous, stop and ask before editing.
-
-## Read before editing
-
-- `AGENTS.md` (root and nearest path-specific files).
-- `.github/pull_request_template.md`.
-- Current branch status and diff against `origin/main`.
-
-## Default release file scope
-
-Treat the following file list as the default checklist for each release bump:
-
-- `Cargo.toml`
-- `Cargo.lock`
-- `README.md`
-- `README_ZH.md`
-- `flake.nix`
-- `helm/rustfs/Chart.yaml`
-- `rustfs.spec`
-
-Only drop a file when the current repository release process clearly no longer requires it.
-
-## Hard release policy
-
-- Docker doc tags use `<version>` (for example `rustfs/rustfs:1.0.0-beta.4`), not `v<version>`.
-- Helm chart version mapping follows `beta.N -> 0.N.0`.
-- `rustfs.spec` `Release` uses prerelease suffix only (for example `beta.4`).
-- Do not change these rules without explicit confirmation.
-
-## Step-by-step workflow
-
-1. Confirm intent and isolate scope
-- Confirm target version string exactly.
-- Confirm whether user requested local-only or full GitHub flow.
-- Inspect current branch and ensure only release-related files are touched for this task.
-
-2. Update workspace versions
-- Bump `[workspace.package].version` in `Cargo.toml`.
-- Bump internal workspace crate dependency versions in `Cargo.toml`.
-- Update `Cargo.lock` so workspace package versions match target version.
-- Re-scan for partial leftovers.
-
-3. Update release assets
-- `README.md` and `README_ZH.md`: update versioned Docker examples to target version.
-- `flake.nix`: update package version to target version.
-- `helm/rustfs/Chart.yaml`:
-- `appVersion` = target version.
-- `version` follows chart mapping rule, for example:
-- `1.0.0-beta.3` -> `0.3.0`
-- `1.0.0-beta.4` -> `0.4.0`
-- `rustfs.spec`:
-- Set `Release` to prerelease suffix (example `beta.4`).
-- Add/update top changelog entry with exact format:
-- `* Thu May 20 2026 houseme <housemecn@gmail.com>`
-- `- Update RPM package to RustFS 1.0.0-beta.4`
-- Changelog identity and time must come from current environment:
-- `git config --get user.name`
-- `git config --get user.email`
-- `date '+%a %b %d %Y'`
-- Changelog version text must match target release version exactly.
-
-4. Verify before shipping
-- Run:
-- `cargo fmt --all`
-- `cargo fmt --all --check`
-- `make pre-commit`
-- If verification passes, run `cargo clean`.
-- If `make pre-commit` fails, return `BLOCKED` with root cause and do not silently widen scope to fix unrelated issues unless user asks.
-
-5. Commit strategy
-- Preferred split when both parts changed:
-- `chore(release): prepare <version>` for `Cargo.toml` and `Cargo.lock`.
-- `chore(release): align release assets for <version>` for docs and packaging files.
-- If user asks for one commit, use one commit.
-- Stage only intended release files; do not include unrelated working tree changes.
-
-6. Push and PR
-- Push branch:
-- `git push -u origin <branch>` (first push), or `git push` (tracking already exists).
-- Create PR with template headings unchanged:
-- `gh pr create --base main --head <branch> --title ... --body-file ...`
-- PR title/body must be English.
-- Use `N/A` for non-applicable template sections.
-- Include verification commands and any `BLOCKED` reason clearly.
-
-## Recommended check commands
-
-- `git status --short --branch`
-- `git diff --name-only origin/main...HEAD`
-- `git diff --stat origin/main...HEAD`
-- `rg -n "<old_version>|<new_version>" Cargo.toml Cargo.lock README.md README_ZH.md flake.nix helm/rustfs/Chart.yaml rustfs.spec`
-- `cargo fmt --all`
-- `cargo fmt --all --check`
-- `make pre-commit`
-- `cargo clean`
-
-## Output contract
-
-When using this skill, always report:
-
-- Target version.
-- Files changed.
-- Any assumptions or uncertainties requiring confirmation.
-- Verification result (`PASSED` or `BLOCKED`) with key evidence.
-- Commit message(s) used.
-- Push status and PR URL when GitHub flow is requested.

.agents/skills/rustfs-release-version-bump/agents/openai.yaml

@@ -1,4 +0,0 @@
-interface:
-  display_name: "RustFS Release Bump"
-  short_description: "Prepare RustFS release branches like PR #2957."
-  default_prompt: "Use $rustfs-release-version-bump to prepare a RustFS release version, ask about any unclear version policy, and finish the commit/push/PR flow."

.agents/skills/security-advisory-lessons/SKILL.md

@@ -1,145 +0,0 @@
----
-name: security-advisory-lessons
-description: Apply RustFS security lessons distilled from repository GitHub Security Advisories. Use when making or reviewing RustFS code changes, doing security checks, handling PR review for auth/authz, IAM, storage, RPC, logging, CORS, console/browser, encryption, policy, or endpoint changes, and when deciding which security regression tests are required.
----
-
-# RustFS Security Advisory Lessons
-
-Use this skill as a RustFS-specific security lens before changing or approving code. For the distilled advisory lessons and review patterns, read [advisory-patterns.md](references/advisory-patterns.md).
-
-When currentness matters, fetch the live advisory inventory instead of relying on this skill as a status mirror:
-
-```bash
-gh api repos/rustfs/rustfs/security-advisories --paginate \
-  --jq '.[] | {ghsa_id,state,severity,summary,updated_at}'
-```
-
-Fetch full advisory details only when the live summary suggests a new or changed lesson:
-
-```bash
-gh api repos/rustfs/rustfs/security-advisories/<GHSA_ID>
-```
-
-For the full pattern map, read [advisory-patterns.md](references/advisory-patterns.md).
-
-## Workflow
-
-### 1. Scope the change
-- Identify touched routes, protocol frontends, handlers, storage paths, credentials, logs, browser surfaces, CI/release code, and policy checks.
-- Treat these paths as security-sensitive by default: `rustfs/src/admin/`, `rustfs/src/storage/`, `rustfs/src/auth.rs`, `rustfs/src/server/layer.rs`, `crates/iam/`, `crates/policy/`, `crates/credentials/`, `crates/ecstore/src/rpc/`, `crates/protocols/`, `crates/rio/`, OIDC/STS federation code, and console preview/auth code.
-
-### 2. Map to advisory classes
-- Read [advisory-patterns.md](references/advisory-patterns.md) for matching GHSA lessons.
-- Do not rely on advisory titles alone. Confirm whether the issue is authentication, authorization, input validation, storage invariant, browser isolation, logging, or operational hardening.
-
-### 3. Verify fail-closed behavior
-- Check that unauthenticated, wrong-permission, cross-user, cross-bucket, malformed-input, and default-config cases fail explicitly.
-- Prefer exact action/permission checks over broad helper calls or inferred ownership.
-- Confirm lower storage/RPC layers do not bypass checks done in upper layers.
-
-### 4. Require regression evidence
-- For behavior changes, add focused negative tests that reproduce the advisory class.
-- For sensitive fixes, include tests for the bypass form, not only the happy path.
-- If a test is impractical, explain the residual risk and provide a manual verification command.
-
-### 5. Report clearly
-- Lead with concrete findings and file/line evidence.
-- Separate proven vulnerabilities from hardening risks.
-- Avoid exaggerating unauthenticated impact when the code actually rejects unauthenticated requests but allows a low-privileged authenticated bypass.
-
-## Advisory-Derived Guardrails
-
-### Auth and admin authorization
-- Every admin or diagnostic route needs an explicit authn and authz story. Route registration, router whitelist, and handler-level authorization must agree.
-- Match the admin action to the operation exactly. Copy-paste action constants are a known RustFS vulnerability class.
-- Avoid authentication-only helpers for state-changing admin APIs; use `validate_admin_request` or the established equivalent with the right `AdminAction`.
-- Read-only admin APIs such as metrics, server info, and diagnostics still require admin authorization; checking only that credentials exist is not enough.
-- Replication admin reads can expose remote target credentials; list/get target endpoints require replication/admin authorization and must not return secrets to low-privilege callers.
-- Do not assume admin-action `Resource` scoping constrains blast radius unless the policy engine actually enforces resources for that action.
-
-### IAM and service accounts
-- Treat imported IAM payload fields as attacker-controlled: `parent`, `claims`, `accessKey`, `secretKey`, status, policy names, and groups.
-- For service account create/update/import, prove parent ownership or root/admin authority before writing credentials or claims; an action permission alone must not allow choosing root or another user as `target_user`.
-- Do not let `deny_only` or "no explicit deny" become an allow decision that skips required allow checks.
-- Test cross-user list/update/import flows with wrong, correct, self, parent, and root identities.
-
-### STS, OIDC, and federation flows
-- Every STS endpoint must have an explicit authentication story: SigV4 where required, OIDC token verification for web identity, and role/session policy validation before issuing credentials.
-- JWT session tokens must be signed and verified by a trusted issuer/key path, not by service-account-controlled material or a reused root secret.
-- Public OIDC bootstrap and callback routes must treat `Host`, `X-Forwarded-Proto`, redirect targets, `state`, and callback parameters as untrusted; credential-bearing redirects require a configured, allowlisted origin.
-- OIDC discovery and validation URLs are SSRF sinks. Resolve and classify hostnames at connection time, reject rebinding to loopback/private/link-local ranges, and do not rely on literal string checks.
-
-### S3 copy, multipart, and presigned POST
-- Multipart copy must enforce source `GetObject` and destination `PutObject` semantics equivalent to `CopyObject`, including copy-source and policy conditions.
-- Do not let `CreateMultipartUpload`, `UploadPartCopy`, `CompleteMultipartUpload`, or `AbortMultipartUpload` return success without authorization.
-- Presigned POST policies are server-side contracts. Enforce `content-length-range`, key prefix, exact metadata/content-type, and all signed policy conditions.
-
-### Protocol frontends and IAM parity
-- FTP/FTPS, SFTP, gateway, and other protocol drivers must enforce IAM per operation before calling storage backends; authentication to a protocol listener is not authorization.
-- Match protocol commands to the same S3 actions as HTTP, such as `RETR` to `GetObject`, `SIZE`/`MDTM` to `HeadObject`, `MKD` to `CreateBucket`, and bucket probes to `ListBucket` or `HeadBucket`.
-- Review every handler in a protocol driver, not only the changed handler, because RustFS advisories show mixed guarded and unguarded siblings in the same driver.
-- Regression tests for protocol frontends should deny the shared authorization hook and prove the backend is not reached for the denied command.
-- Compare protocol secrets in constant time, normalize invalid-user and invalid-secret failures where practical, and add rate limiting before exposing password-style protocol endpoints.
-
-### Paths, object keys, and filesystem access
-- Never join untrusted bucket/object/RPC path strings onto filesystem roots without normalization and boundary checks.
-- Reject or safely handle `..`, absolute paths, URL-encoded traversal, platform separators, empty components, and paths that canonicalize outside the intended root.
-- Validate both S3 object-key paths and internode/RPC disk paths; storage helpers can bypass S3 authorization if they trust already-parsed paths.
-- Archive auto-extract paths are object keys too. Validate tar/zip entry names before IAM checks and before storage writes, and prove cleaned paths cannot cross bucket or prefix boundaries.
-
-### Secrets, default credentials, and crypto
-- Do not ship hard-coded shared tokens, HMAC secrets, private keys, or production test keys.
-- Defaults for root credentials and internode/RPC auth must fail closed for network-reachable deployments or generate per-install random secrets; warnings alone are not a security boundary.
-- Keep cryptographic roles separated: root S3 credentials, RPC HMAC keys, and STS/JWT signing keys must not be reused or deterministically derived from each other.
-- License or token validation must use signatures with embedded public/verifying keys only; do not use private-key decryption as authenticity.
-- Plan key rotation and key IDs when removing exposed keys.
-
-### Logging and debug output
-- Logs must never include access keys beyond safe identifiers, secret keys, session tokens, JWT claims, HMAC secrets, expected signatures, license secrets, or raw response bodies containing credentials.
-- Treat `Debug` implementations, `?value` tracing, merged config dumps, and dependency-level HTTP body logging as leak surfaces.
-- Add log-capture tests or targeted unit tests for redaction wrappers when changing credential structs or response bodies.
-
-### RPC, parsing, and panic safety
-- Treat all RPC payload bytes as attacker-controlled. Replace `unwrap`, `expect`, and panic-prone deserialization with typed errors.
-- Malformed request tests should cover empty bytes, truncated MessagePack/protobuf, invalid enum values, stale timestamps, and invalid signatures.
-- RPC authentication must be independently strong; do not depend on S3 admin credentials unless the fallback is explicit and safe.
-- RPC signatures must bind the exact generated gRPC method path, timestamp, and request method. Service-prefix signatures must not authorize a different concrete NodeService call.
-
-### Browser, CORS, and console surfaces
-- Do not reflect arbitrary `Origin` while also allowing credentials. Default CORS should be no CORS unless explicitly configured.
-- Do not render user-controlled object content in a same-origin iframe with console credentials available to JavaScript.
-- Prefer origin separation for object preview/download, `nosniff`, CSP, strict content-type handling, and avoiding durable credentials in `localStorage`.
-- Preview safety must be based on trusted content type and sandboxing, not object names or extensions such as `.pdf`.
-- Console license/version-like metadata endpoints should expose only coarse public data unless authenticated, especially subject names and expiration timestamps.
-
-### Profiling, debug, and health endpoints
-- Profiling and debug endpoints are not health checks. They require admin auth, opt-in enablement, rate limiting, and safe responses.
-- Do not return absolute filesystem paths or other deployment layout in unauthenticated or low-privilege responses.
-- Ensure health endpoint allowlists cannot accidentally include expensive diagnostics.
-
-### Trusted proxy and network identity
-- Only honor `X-Forwarded-For` or `X-Real-IP` when the request came from a configured trusted proxy.
-- Apply the same trusted-proxy rule to scheme and host derivation; direct clients must not control security-sensitive redirects through `Host`, `X-Forwarded-Host`, or `X-Forwarded-Proto`.
-- Direct clients must use the socket peer address for `aws:SourceIp` and policy condition evaluation.
-- Add tests for direct spoofed headers and trusted-proxy headers.
-
-### SSE and storage invariants
-- Encryption metadata is not proof that bytes were encrypted on disk.
-- When touching reader/writer wrappers such as hashing, encryption, compression, or warp readers, verify wrapper order and inspect stored bytes in regression tests.
-- Avoid helper shortcuts that unwrap nested readers and accidentally bypass encryption or integrity layers.
-
-## Review Prompts
-
-Use these prompts while reviewing a diff:
-
-- Could a low-privileged authenticated user reach this path with the wrong action, parent, bucket, or source object?
-- Does a non-HTTP protocol path call the same authorization boundary as the S3 API before touching storage?
-- Does a public/default/empty config change security behavior from fail-closed to fail-open?
-- Is any attacker-controlled value later used as a path, policy condition, credential identity, log field, URL, Origin, or response body?
-- Does this response contain stored replication, remote target, or service credentials that need redaction or stricter authorization?
-- Can this STS/OIDC path issue credentials without SigV4, trusted issuer validation, allowlisted redirects, or trusted-proxy host/scheme handling?
-- Does this outbound validation path resolve attacker-supplied hostnames and reject private, loopback, link-local, and rebound addresses at the actual connection boundary?
-- Is an archive entry, object key, or policy resource normalized differently between authorization and storage?
-- Is the same operation implemented in multiple paths, such as `CopyObject` vs `UploadPartCopy`, and do all paths enforce the same security contract?
-- Does a preview or browser-surface fix preserve the original security invariant when adding alternate viewers or file-type detection?
-- Does the test prove the exploit form is denied, or only that the intended form still works?

.agents/skills/security-advisory-lessons/agents/openai.yaml

@@ -1,4 +0,0 @@
-interface:
-  display_name: "Security Advisory Lessons"
-  short_description: "Apply advisory lessons in reviews."
-  default_prompt: "Review code changes against past RustFS security advisory lessons and report concrete risks, missing tests, and recommended fixes."

.agents/skills/security-advisory-lessons/references/advisory-patterns.md

@@ -1,127 +0,0 @@
-# RustFS Advisory Pattern Map
-
-This file is a lesson map, not an advisory inventory mirror. It keeps durable security patterns distilled from RustFS GitHub Security Advisories.
-
-When current advisory state, severity, URLs, or full text matters, fetch it live:
-
-```bash
-gh api repos/rustfs/rustfs/security-advisories --paginate \
-  --jq '.[] | {ghsa_id,state,severity,summary,updated_at}'
-gh api repos/rustfs/rustfs/security-advisories/<GHSA_ID>
-```
-
-Update this file only when an advisory adds or changes a reusable lesson, affected surface, validation pattern, or regression-test expectation. Do not update it for state-only, URL-only, count-only, or timestamp-only changes.
-
-## Pattern Index
-
-### Admin authorization and route exposure
-
-- `GHSA-pfcq-4gjr-6gjm`: notification target endpoints accepted authenticated users but skipped admin authorization. Lesson: distinguish authn from authz; admin target CRUD must call the operation-specific admin authorization path.
-- `GHSA-mm2q-qcmx-gw4w`: `ListServiceAccount` used `UpdateServiceAccountAdminAction`, while update lacked target ownership checks. Lesson: exact action constants and ownership checks are both required; information disclosure can chain into secret rotation and takeover.
-- `GHSA-vcwh-pff9-64cc`: `ImportIam` checked `ExportIAMAction` for an import/write operation. Lesson: every admin handler must authorize the action it actually performs.
-- `GHSA-jqmc-mg33-v45g` and `GHSA-8784-9m7f-c6p6`: `/profile/cpu` and `/profile/memory` were whitelisted from auth and allowed expensive diagnostics plus path disclosure. Lesson: profiling/debug endpoints need admin auth, opt-in, rate limits, and non-sensitive responses.
-- `GHSA-f5cv-v44x-2xgf`: `/rustfs/admin/v3/metrics` accepted any authenticated IAM user and skipped admin authorization. Lesson: read-only metrics and diagnostic admin endpoints still require an operation-specific admin action check.
-- `GHSA-796f-j7xp-hwf4`: `/rustfs/admin/v3/list-remote-targets` checked only that credentials existed and leaked replication target credentials. Lesson: replication target reads are privileged admin operations, and stored remote credentials require strict authz plus response redaction review.
-- `GHSA-xp32-gxq2-3v52`: console license metadata endpoint was public and exposed subject and expiration fields. Lesson: management metadata endpoints should require admin auth or return only coarse public status.
-
-### IAM import, service accounts, and privilege boundaries
-
-- `GHSA-566f-q62r-wcr8`: `ImportIam` accepted attacker-controlled service account `parent`, `claims`, `accessKey`, and `secretKey`, enabling persistent backdoor accounts under root. Lesson: imported IAM payloads are untrusted data and must be validated against privilege boundaries.
-- `GHSA-5354-r3w2-34m8`: `AddServiceAccount` checked `CreateServiceAccountAdminAction` but trusted caller-supplied `target_user`, allowing service accounts under the root parent. Lesson: service-account create paths must validate parent ownership or root/admin authority, not only the create action.
-- `GHSA-xgr5-qc6w-vcg9`: `deny_only=true` skipped allow checks and let restricted service accounts mint unrestricted children. Lesson: deny-only logic must never become implicit allow for privilege creation.
-- `GHSA-mm2q-qcmx-gw4w`: leaked service account access keys plus update-without-ownership formed an escalation chain. Lesson: service-account identifiers are security-sensitive because update APIs consume them.
-
-### STS, OIDC, and federation flows
-
-- `GHSA-5qfg-mf7r-jp3w`: `AssumeRoleWithWebIdentity` was reachable without the required request authentication and could issue temporary credentials from crafted web identity input. Lesson: every STS route needs explicit SigV4 or trusted identity-provider validation before role assumption.
-- `GHSA-ccrv-v8v9-ch9q`: service-account-controlled material could self-sign JWT session tokens with forged policy claims. Lesson: session tokens must be signed by a trusted issuer/key path and validation must reject self-signed or principal-controlled tokens.
-- `GHSA-9pjf-w3c2-m32r`, `GHSA-4x2q-cpx9-9h26`, and `GHSA-xvpm-p3f7-34c3`: public OIDC authorize/callback flows trusted request `Host` or forwarded scheme when building credential-bearing redirects. Lesson: OIDC redirects must use configured allowlisted origins and trusted-proxy handling; never derive the post-login credential destination from direct client headers.
-- `GHSA-m479-9x88-94w6`, `GHSA-frwq-mfqx-83p8`, `GHSA-q9q8-rf9r-fg9f`, and `GHSA-j5c2-hhf7-6gf5`: OIDC validation accepted attacker-controlled discovery URLs because hostname checks rejected only literal forbidden IPs, allowing DNS rebinding SSRF. Lesson: outbound federation URL validation must resolve and classify hostnames at the connection boundary and reject loopback, private, link-local, and rebound addresses.
-
-### S3 copy, multipart, and upload policy validation
-
-- `GHSA-mx42-j6wv-px98`: `UploadPartCopy` missed source authorization and allowed cross-bucket object exfiltration. Lesson: multipart copy must enforce the same source and destination contract as `CopyObject`.
-- `GHSA-wfxj-ph3v-7mjf`: `UploadPartCopy` checked source and destination independently but missed destination copy-source policy constraints. Lesson: source read and destination write checks are not sufficient when policy constrains allowed copy sources.
-- `GHSA-w5fh-f8xh-5x3p`: presigned POST accepted uploads without enforcing signed policy conditions. Lesson: parse and enforce all POST policy constraints server-side, including size, key prefix, and content type.
-
-### Protocol frontends and IAM parity
-
-- `GHSA-3g29-xff2-92vp`: FTP `RETR` and `SIZE`/`MDTM` read paths authenticated the user but skipped IAM before calling storage. Lesson: non-HTTP protocol frontends must enforce the same per-operation authorization as the S3 API before backend access.
-- `GHSA-g3vq-vv42-f647`: FTPS `MKD` called `create_bucket` without checking `s3:CreateBucket`. Lesson: protocol command handlers need action-specific checks even when sibling handlers already authorize correctly.
-- `GHSA-3p3x-734c-h5vx`: FTPS and WebDAV compared secret keys with early-return string equality, while FTPS also returned distinguishable invalid-user and invalid-password failures. Lesson: password-style protocol auth needs constant-time secret comparison, indistinguishable failures where practical, and rate limiting.
-
-### Filesystem paths and object key traversal
-
-- `GHSA-pq29-69jg-9mxc`: RPC `read_file_stream` joined untrusted paths under a volume directory without canonical boundary checks. Lesson: `PathBuf::join` plus length checks are not path security.
-- `GHSA-8r6f-hmq2-28rg`: object keys containing traversal sequences bypassed bucket/object authorization when mapped to filesystem paths. Lesson: reject traversal at object-key parsing and verify final storage paths remain under the expected bucket/key root.
-- `GHSA-f4vq-9ffr-m8m3`: Snowball auto-extract accepted archive entries such as `../victim-bucket/object`, authorized the raw attacker-bucket path, then storage path cleaning crossed bucket boundaries. Lesson: archive entries become object keys and need traversal rejection plus consistent authz/storage normalization before writes.
-
-### Secrets, defaults, and cryptographic misuse
-
-- `GHSA-j59h-h7q5-q348`, `GHSA-3wm5-wpm5-hmfm`, `GHSA-6wc8-xm48-qhmx`, and `GHSA-9gf3-jx4p-4xxf`: RustFS shipped known default root credentials that could authenticate to S3, admin APIs, IAM, KMS, console, and token-signing surfaces. Lesson: root credentials must be operator-provided or generated per install; known defaults and warnings are not acceptable for network-reachable deployments.
-- `GHSA-h956-rh7x-ppgj`: gRPC used the hard-coded token `rustfs rpc` on both client and server. Lesson: source-visible shared tokens are authentication bypasses.
-- `GHSA-r5qv-rc46-hv8q`: internode RPC HMAC secret fell back to the public default `rustfsadmin`. Lesson: RPC/internode auth must fail closed instead of silently using public defaults.
-- `GHSA-75fx-qg6f-8rm7` and `GHSA-68cw-96m3-h2cf`: internode RPC secrets were derivable from known root credentials, making raw storage RPC signatures forgeable when explicit RPC secrets were unset. Lesson: RPC auth keys must be independent random secrets, never derived from S3 root credentials, and raw storage RPC should not share the public S3 listener without an internode-only boundary.
-- `GHSA-m77q-r63m-pj89`: STS JWTs used the root secret key as the shared token signing key, allowing token forgery when the root secret was known. Lesson: STS signing keys need key separation, rotation, and key IDs; do not reuse root credentials for JWT/HMAC signing.
-- `GHSA-923g-jp7v-f97f`: license verification embedded a production RSA private key and used private-key decryption as authenticity. Lesson: ship verifying/public keys only and use real signature verification.
-
-### Sensitive logging and debug output
-
-- `GHSA-r54g-49rx-98cr`: STS credentials were logged at info level. Lesson: generated credentials must never be logged in plaintext.
-- `GHSA-8cm2-h255-v749`: debug logs leaked session tokens, secret keys, JWT claims, and raw STS response bodies. Lesson: redaction must cover custom `Debug` implementations and dependency response-body logging.
-- `GHSA-333v-68xh-8mmq`: invalid RPC signature logging included the shared HMAC secret and expected signature. Lesson: error paths often leak secrets; never log raw secrets or derived authenticators.
-
-### RPC input validation and panic safety
-
-- `GHSA-gw2x-q739-qhcr`: malformed gRPC `GetMetrics` payloads reached `unwrap()` on deserialization and caused remote DoS. Lesson: every network/RPC deserialization failure returns an error, not a panic.
-- `GHSA-h956-rh7x-ppgj` and `GHSA-r5qv-rc46-hv8q`: weak RPC auth increased reachability of otherwise internal handlers. Lesson: panic bugs become more severe when internode auth is weak or defaulted.
-- `GHSA-c667-rgrv-99vj`: NodeService authentication signed the service prefix instead of the concrete generated method path, so valid metadata for one RPC could be replayed to another method during the timestamp window. Lesson: RPC HMAC payloads must bind exact gRPC method path, HTTP method surrogate, timestamp, and secret.
-
-### Browser, CORS, and console isolation
-
-- `GHSA-v9fg-3cr2-277j`: object preview rendered attacker-controlled HTML in a same-origin iframe, exposing console credentials stored in `localStorage`. Lesson: user content must be origin-isolated from the console and protected with `nosniff`, CSP, and strict content-type handling.
-- `GHSA-7gcx-wg4x-q9x6`: an incomplete preview fix reintroduced extension-based PDF detection and bypassed the sandboxed fallback for attacker-controlled content. Lesson: browser-surface fixes need regression tests for alternate viewers and file-type branches, and preview trust must come from validated content type plus sandboxing rather than object names.
-- `GHSA-x5xv-223c-8vm7`: default CORS reflected arbitrary origins with credentials. Lesson: never combine reflected origins with `Access-Control-Allow-Credentials: true`; default should be fail-closed.
-
-### Trusted proxy and source IP conditions
-
-- `GHSA-fc6g-2gcp-2qrq`: `aws:SourceIp` trusted client-supplied `X-Forwarded-For` or `X-Real-IP`. Lesson: forwarded IP headers are valid only behind configured trusted proxies; direct clients use socket peer IP.
-
-### SSE and on-disk storage invariants
-
-- `GHSA-xrrf-67jm-3c2r`: SSE metadata reported encryption while reader composition bypassed `EncryptReader` and stored plaintext. Lesson: test actual bytes on disk and wrapper order, not only API metadata.
-
-### Serde deserialization and input validation
-
-- No `#[serde(deny_unknown_fields)]` found across the entire codebase. Lesson: all structs deserialized from untrusted input (S3 API XML/JSON, lifecycle rules, bucket policies, replication configs) should have `#[serde(deny_unknown_fields)]` to reject malformed or adversarial payloads.
-- `#[serde(default)]` on security-critical fields silently accepts missing values as zero/empty. Lesson: when a field has security implications (retention days, permissions, limits), validate the deserialized value explicitly rather than relying on defaults.
-- Integer fields deserialized from user input and cast with `as` (e.g., `i32 as u32`) can wrap negative values to large positives. Lesson: validate ranges before casting; use `try_into()` or clamp.
-- XML config typos (e.g., `"NoncurentDays"` instead of `"NoncurrentDays"`) are silently accepted when `deny_unknown_fields` is absent. Lesson: strict deserialization prevents silent misconfiguration that could cause data loss or unexpected retention behavior.
-
-## Useful Search Seeds
-
-Use these targeted searches when a diff touches security-sensitive code:
-
-```bash
-rg -n "validate_admin_request|check_permissions|AdminAction::|deny_only|is_allowed" rustfs crates
-rg -n "authorize_operation|FtpsDriver|SftpDriver|RETR|MKD|SIZE|MDTM|CreateBucket|GetObject|HeadObject" crates/protocols rustfs
-rg -n "UploadPartCopy|upload_part_copy|CompleteMultipart|PostObject|content-length-range|starts-with" rustfs crates
-rg -n "normalize_extract_entry_key|Snowball|auto-extract|PathBuf::join|canonicalize|\\.\\.|x-forwarded-for|x-real-ip|SourceIp" rustfs crates
-rg -n "DEFAULT_SECRET|DEFAULT_ACCESS|TEST_PRIVATE_KEY|rustfs rpc|RUSTFS_RPC_SECRET" rustfs crates
-rg -n "TONIC_RPC_PREFIX|verify_rpc_signature|check_auth|NodeServiceServer|x-rustfs-signature" rustfs crates
-rg -n "debug!|trace!|info!|error!|\\?resp|\\?merged_config|session_token|secret_key" rustfs crates
-rg -n "HashReader|EncryptReader|SSE|server-side encryption|Access-Control-Allow-Credentials|Origin" rustfs crates
-rg -n "deny_unknown_fields|serde.default|as u32|as usize|as i32" rustfs crates
-```
-
-## Minimum Regression Test Expectations
-
-- Authz fixes: include unauthenticated, valid low-privilege, wrong-action, correct-action, owner, non-owner, and root/admin cases as applicable.
-- Protocol frontend authz fixes: include denied `RETR`, `SIZE`/`MDTM`, `MKD`, bucket probe, and sibling allowed-operation cases, and assert denied paths do not reach the storage backend.
-- IAM fixes: include import/update/list service-account cases with attacker-controlled parent, claims, access key, secret key, and policy.
-- Copy/upload fixes: include cross-bucket, cross-user, source-denied, destination-denied, copy-source-condition, and multipart completion cases.
-- Path fixes: include encoded traversal, absolute path, nested traversal, archive entries with `..`, valid object keys that resemble traversal text but should be rejected, and canonical bucket/prefix boundary checks.
-- Logging fixes: assert redacted output for structs and response bodies that may contain credentials.
-- RPC auth fixes: include captured metadata replay across two concrete methods, stale timestamps, wrong path, wrong method surrogate, wrong secret, and valid same-method calls.
-- Browser/CORS fixes: assert no credentials on reflected/default origins, correct behavior for explicit allowlists, and no same-origin script execution for previewed object content.
-- SSE fixes: inspect stored bytes and verify API metadata, read-back behavior, and on-disk ciphertext together.

.agents/skills/test-coverage-improver/SKILL.md

@@ -1,66 +0,0 @@
----
-name: test-coverage-improver
-description: Run project coverage checks, rank high-risk gaps, and propose high-impact tests to improve regression confidence for changed and critical code paths before release.
----
-
-# Test Coverage Improver
-
-Use this skill when you need a prioritized, risk-aware plan to improve tests from coverage results.
-
-## Usage assumptions
-- Focus scope is either changed lines/files, a module, or the whole repository.
-- Coverage artifact must be generated or provided in a supported format.
-- If required context is missing, call out assumptions explicitly before proposing work.
-
-## Workflow
-
-1. Define scope and baseline
-   - Confirm target language, framework, and branch.
-   - Confirm whether the scope is changed files only or full-repo.
-
-2. Produce coverage snapshot
-   - Rust: `cargo llvm-cov` (or `cargo tarpaulin`) with existing repo config.
-   - JavaScript/TypeScript: `npm test -- --coverage` and read `coverage/coverage-final.json`.
-   - Python: `pytest --cov=<pkg> --cov-report=json` and read `coverage.json`.
-   - Collect total, per-file, and changed-line coverage.
-
-3. Rank highest-risk gaps
-   - Prioritize changed code, branch coverage gaps, and low-confidence boundaries.
-   - Apply the risk rubric in [coverage-prioritization.md](references/coverage-prioritization.md).
-   - Keep shortlist to 5–8 gaps.
-   - For each gap, capture: file, lines, uncovered branches, and estimated risk score.
-
-4. Propose high-impact tests
-   - For each shortlisted gap, output:
-     - Intent and expected behavior.
-     - Normal, edge, and failure scenarios.
-     - Assertions and side effects to verify.
-     - Setup needs (fixtures, mocks, integration dependencies).
-     - Estimated effort (`S/M/L`).
-
-5. Close with validation plan
-   - State which gaps remain after proposals.
-   - Provide concrete verification command and acceptance threshold.
-   - List assumptions or blockers (environment, fixtures, flaky dependencies).
-
-## Output template
-
-### Coverage Snapshot
-- total / branch coverage
-- changed-file coverage
-- top missing regions by size
-
-### Top Gaps (ranked)
-- `path:line-range` | risk score | why critical
-
-### Test Proposals
-- `path:line-range`
-  - Test name
-  - scenarios
-  - assertions
-  - effort
-
-### Validation Plan
-- command
-- pass criteria
-- remaining risk

.agents/skills/test-coverage-improver/agents/openai.yaml

@@ -1,4 +0,0 @@
-interface:
-  display_name: "Test Coverage Improver"
-  short_description: "Find top uncovered risk areas and propose high-impact tests."
-  default_prompt: "Run coverage checks, identify largest gaps, and recommend highest-impact test cases to improve risk coverage."

.agents/skills/test-coverage-improver/references/coverage-prioritization.md

@@ -1,25 +0,0 @@
-# Coverage Gap Prioritization Guide
-
-Use this rubric for each uncovered area.
-
-Score = (Criticality × 2) + CoverageDebt + (Volatility × 0.5)
-
-- Criticality:
-  - 5: authz/authn, data-loss, payment/consistency path
-  - 4: state mutation, cache invalidation, scheduling
-  - 3: error handling + fallbacks in user-visible flows
-  - 2: parsing/format conversion paths
-  - 1: logging-only or low-impact utilities
-
-- CoverageDebt:
-  - 0: 0–5 uncovered lines
-  - 1: 6–20 uncovered lines
-  - 2: 21–40 uncovered lines
-  - 3: 41+ uncovered lines
-
-- Volatility:
-  - 1: stable legacy code with few recent edits
-  - 2: changed in last 2 releases
-  - 3: touched in last 30 days or currently in active PR
-
-Sort by score descending, then by business impact.

.agents/skills/tier-debug/SKILL.md

@@ -1,34 +0,0 @@
----
-name: tier-debug
-description: Debug ILM tiering / lifecycle transition issues — NoSuchVersion on tier GET, restore failures, xl.meta inspection, remote-tier versionId tracing. Use when investigating tiered/transitioned objects, warm backends, or transition metadata.
----
-
-# Tier / ILM Debugging
-
-Full playbook: [docs/operations/tier-ilm-debugging.md](../../../docs/operations/tier-ilm-debugging.md)
-— read it before changing tier code.
-
-Quick moves:
-
-```bash
-# Inspect transition metadata on disk (one xl.meta per erasure shard disk)
-cargo run -p rustfs-filemeta --example dump_fileinfo -- "/path/to/{bucket}/{object}/xl.meta"
-
-# Trace what versionId is sent to the remote tier
-RUST_LOG=rustfs_ecstore::bucket::lifecycle=debug ./target/debug/rustfs …
-```
-
-Interpretation:
-
-- `transition_ver_id: <none>` → correct for an unversioned tier bucket; no
-  `versionId` must be sent on tier GET/DELETE.
-- `transition_ver_id: 00000000-…` (nil) → corrupt legacy write-back; readers
-  must filter it out, never send it.
-- Empty-string `transitioned-versionID` metadata under both
-  `x-rustfs-internal-*` and `x-minio-internal-*` keys → object went to an
-  unversioned tier bucket.
-
-Code entry points: `crates/ecstore/src/bucket/lifecycle/bucket_lifecycle_ops.rs`
-(ILM actions), `crates/ecstore/src/services/tier/` (warm backends),
-`crates/filemeta/src/filemeta/version.rs` (metadata read/write + regression
-tests).

.cargo/config.toml

@@ -1,33 +0,0 @@
-# Copyright 2024 RustFS Team
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-
-# RustFS Cargo configuration
-
-# NOTE: `--cfg tokio_unstable` is deliberately NOT set here.
-#
-# It used to be a global `[build] rustflags` entry so that the (default-off)
-# `dial9` telemetry feature could compile. That made every build depend on
-# Tokio's unstable, non-semver API, and it broke silently whenever a caller
-# exported their own RUSTFLAGS — an environment RUSTFLAGS replaces the value
-# from this file rather than appending to it.
-#
-# The flag is now scoped to telemetry builds, which opt in explicitly:
-#
-#     make build-profiling
-#     RUSTFLAGS="--cfg tokio_unstable" cargo build --features dial9
-#
-# `crates/obs/build.rs` fails the compile if the `dial9` feature is on without
-# the flag, so the two can no longer drift apart unnoticed.
-#
-# For CPU profiling, add `-C force-frame-pointers=yes` to that RUSTFLAGS value.

.claude/skills

@@ -1 +0,0 @@
-../.agents/skills

.config/make/build-docker-buildx-dev.mak

@@ -1,64 +0,0 @@
-## —— Development/Source builds using direct buildx commands ---------------------------------------
-
-.PHONY: docker-dev
-docker-dev: ## Build dev multi-arch image (cannot load locally)
-	@echo "🏗️ Building multi-architecture development Docker images with buildx..."
-	@echo "💡 This builds from source code and is intended for local development and testing"
-	@echo "⚠️  Multi-arch images cannot be loaded locally, use docker-dev-push to push to registry"
-	$(DOCKER_CLI) buildx build \
-		--platform linux/amd64,linux/arm64 \
-		--file $(DOCKERFILE_SOURCE) \
-		--tag rustfs:source-latest \
-		--tag rustfs:dev-latest \
-		.
-
-.PHONY: docker-dev-local
-docker-dev-local: ## Build dev single-arch image (local load)
-	@echo "🏗️ Building single-architecture development Docker image for local use..."
-	@echo "💡 This builds from source code for the current platform and loads locally"
-	$(DOCKER_CLI) buildx build \
-		--file $(DOCKERFILE_SOURCE) \
-		--tag rustfs:source-latest \
-		--tag rustfs:dev-latest \
-		--load \
-		.
-
-.PHONY: docker-dev-push
-docker-dev-push: ## Build and push multi-arch development image # e.g (make docker-dev-push REGISTRY=xxx)
-	@if [ -z "$(REGISTRY)" ]; then \
-		echo "❌ Error: Please specify registry, example: make docker-dev-push REGISTRY=ghcr.io/username"; \
-		exit 1; \
-	fi
-	@echo "🚀 Building and pushing multi-architecture development Docker images..."
-	@echo "💡 Pushing to registry: $(REGISTRY)"
-	$(DOCKER_CLI) buildx build \
-		--platform linux/amd64,linux/arm64 \
-		--file $(DOCKERFILE_SOURCE) \
-		--tag $(REGISTRY)/rustfs:source-latest \
-		--tag $(REGISTRY)/rustfs:dev-latest \
-		--push \
-		.
-
-.PHONY: dev-env-start
-dev-env-start: ## Start development container environment
-	@echo "🚀 Starting development environment..."
-	$(DOCKER_CLI) buildx build \
-		--file $(DOCKERFILE_SOURCE) \
-		--tag rustfs:dev \
-		--load \
-		.
-	$(DOCKER_CLI) stop $(CONTAINER_NAME) 2>/dev/null || true
-	$(DOCKER_CLI) rm $(CONTAINER_NAME) 2>/dev/null || true
-	$(DOCKER_CLI) run -d --name $(CONTAINER_NAME) \
-		-p 9010:9010 -p 9000:9000 \
-		-v $(shell pwd):/workspace \
-		-it rustfs:dev
-
-.PHONY: dev-env-stop
-dev-env-stop: ## Stop development container environment
-	@echo "🛑 Stopping development environment..."
-	$(DOCKER_CLI) stop $(CONTAINER_NAME) 2>/dev/null || true
-	$(DOCKER_CLI) rm $(CONTAINER_NAME) 2>/dev/null || true
-
-.PHONY: dev-env-restart
-dev-env-restart: dev-env-stop dev-env-start ## Restart development container environment

.config/make/build-docker-buildx-production.mak

@@ -1,41 +0,0 @@
-## —— Production builds using docker buildx (for CI/CD and production) -----------------------------
-
-.PHONY: docker-buildx
-docker-buildx: ## Build production multi-arch image (no push)
-	@echo "🏗️ Building multi-architecture production Docker images with buildx..."
-	./docker-buildx.sh
-
-.PHONY: docker-buildx-push
-docker-buildx-push: ## Build and push production multi-arch image
-	@echo "🚀 Building and pushing multi-architecture production Docker images with buildx..."
-	./docker-buildx.sh --push
-
-.PHONY: docker-buildx-version
-docker-buildx-version: ## Build and version production multi-arch image # e.g (make docker-buildx-version VERSION=v1.0.0)
-	@if [ -z "$(VERSION)" ]; then \
-		echo "❌ Error: Please specify version, example: make docker-buildx-version VERSION=v1.0.0"; \
-		exit 1; \
-	fi
-	@echo "🏗️ Building multi-architecture production Docker images (version: $(VERSION))..."
-	./docker-buildx.sh --release $(VERSION)
-
-.PHONY: docker-buildx-push-version
-docker-buildx-push-version: ## Build and version and push production multi-arch image # e.g (make docker-buildx-push-version VERSION=v1.0.0)
-	@if [ -z "$(VERSION)" ]; then \
-		echo "❌ Error: Please specify version, example: make docker-buildx-push-version VERSION=v1.0.0"; \
-		exit 1; \
-	fi
-	@echo "🚀 Building and pushing multi-architecture production Docker images (version: $(VERSION))..."
-	./docker-buildx.sh --release $(VERSION) --push
-
-.PHONY: docker-buildx-production-local
-docker-buildx-production-local: ## Build production single-arch image locally
-	@echo "🏗️ Building single-architecture production Docker image locally..."
-	@echo "💡 Alternative to docker-buildx.sh for local testing"
-	$(DOCKER_CLI) buildx build \
-		--file $(DOCKERFILE_PRODUCTION) \
-		--tag rustfs:production-latest \
-		--tag rustfs:latest \
-		--load \
-		--build-arg RELEASE=latest \
-		.

.config/make/build-docker-production.mak

@@ -1,16 +0,0 @@
-## —— Single Architecture Docker Builds (Traditional) ----------------------------------------------
-
-.PHONY: docker-build-production
-docker-build-production: ## Build single-arch production image
-	@echo "🏗️ Building single-architecture production Docker image..."
-	@echo "💡 Consider using 'make docker-buildx-production-local' for multi-arch support"
-	$(DOCKER_CLI) build -f $(DOCKERFILE_PRODUCTION) -t rustfs:latest .
-
-.PHONY: docker-build-source
-docker-build-source: ## Build single-arch source image
-	@echo "🏗️ Building single-architecture source Docker image..."
-	@echo "💡 Consider using 'make docker-dev-local' for multi-arch support"
-	DOCKER_BUILDKIT=1 $(DOCKER_CLI) build \
-		--build-arg BUILDKIT_INLINE_CACHE=1 \
-		-f $(DOCKERFILE_SOURCE) -t rustfs:source .
-

.config/make/build-docker.mak

@@ -1,22 +0,0 @@
-## —— Docker-based build (alternative approach) ----------------------------------------------------
-
-# Usage: make BUILD_OS=ubuntu22.04 build-docker
-# Output: target/ubuntu22.04/release/rustfs
-
-.PHONY: build-docker
-build-docker: SOURCE_BUILD_IMAGE_NAME = rustfs-$(BUILD_OS):v1
-build-docker: SOURCE_BUILD_CONTAINER_NAME = rustfs-$(BUILD_OS)-build
-build-docker: BUILD_CMD = /root/.cargo/bin/cargo build --release --bin rustfs --target-dir /root/s3-rustfs/target/$(BUILD_OS)
-build-docker: ## Build using Docker container # e.g (make build-docker BUILD_OS=ubuntu22.04)
-	@echo "🐳 Building RustFS using Docker ($(BUILD_OS))..."
-	$(DOCKER_CLI) buildx build -t $(SOURCE_BUILD_IMAGE_NAME) -f $(DOCKERFILE_SOURCE) --load .
-	$(DOCKER_CLI) run --rm --name $(SOURCE_BUILD_CONTAINER_NAME) -v $(shell pwd):/root/s3-rustfs -it $(SOURCE_BUILD_IMAGE_NAME) $(BUILD_CMD)
-
-.PHONY: docker-inspect-multiarch
-docker-inspect-multiarch: ## Check image architecture support
-	@if [ -z "$(IMAGE)" ]; then \
-		echo "❌ Error: Please specify image, example: make docker-inspect-multiarch IMAGE=rustfs/rustfs:latest"; \
-		exit 1; \
-	fi
-	@echo "🔍 Inspecting multi-architecture image: $(IMAGE)"
-	docker buildx imagetools inspect $(IMAGE)

.config/make/build.mak

@@ -1,74 +0,0 @@
-## —— Local Native Build using build-rustfs.sh script (Recommended) --------------------------------
-
-.PHONY: build
-build: ## Build RustFS binary (includes console by default)
-	@echo "🔨 Building RustFS using build-rustfs.sh script..."
-	./build-rustfs.sh
-
-.PHONY: build-dev
-build-dev: ## Build RustFS in Development mode
-	@echo "🔨 Building RustFS in development mode..."
-	./build-rustfs.sh --dev
-
-.PHONY: build-musl
-build-musl: ## Build x86_64 musl version
-	@echo "🔨 Building rustfs for x86_64-unknown-linux-musl..."
-	@echo "💡 On macOS/Windows, use 'make build-docker' or 'make docker-dev' instead"
-	./build-rustfs.sh --platform x86_64-unknown-linux-musl
-
-.PHONY: build-gnu
-build-gnu: ## Build x86_64 GNU version
-	@echo "🔨 Building rustfs for x86_64-unknown-linux-gnu..."
-	@echo "💡 On macOS/Windows, use 'make build-docker' or 'make docker-dev' instead"
-	./build-rustfs.sh --platform x86_64-unknown-linux-gnu
-
-.PHONY: build-musl-arm64
-build-musl-arm64: ## Build aarch64 musl version
-	@echo "🔨 Building rustfs for aarch64-unknown-linux-musl..."
-	@echo "💡 On macOS/Windows, use 'make build-docker' or 'make docker-dev' instead"
-	./build-rustfs.sh --platform aarch64-unknown-linux-musl
-
-.PHONY: build-gnu-arm64
-build-gnu-arm64: ## Build aarch64 GNU version
-	@echo "🔨 Building rustfs for aarch64-unknown-linux-gnu..."
-	@echo "💡 On macOS/Windows, use 'make build-docker' or 'make docker-dev' instead"
-	./build-rustfs.sh --platform aarch64-unknown-linux-gnu
-
-
-## —— Profiling build (dial9 Tokio runtime telemetry) ------------------------------------------
-
-# dial9 hooks Tokio's unstable runtime instrumentation, so it needs
-# `--cfg tokio_unstable`. That flag is deliberately absent from
-# .cargo/config.toml: it is not free, and release binaries do not carry it.
-# Setting RUSTFLAGS here replaces (never appends to) the config-file value, and
-# crates/obs/build.rs fails the build if the feature and the flag disagree.
-#
-# There are no task-dump or S3-upload features — see the notes in
-# crates/obs/Cargo.toml for why.
-DIAL9_FEATURES ?= dial9
-DIAL9_RUSTFLAGS ?= --cfg tokio_unstable
-
-.PHONY: build-profiling
-build-profiling: ## Build RustFS with dial9 Tokio runtime telemetry (diagnostic builds only)
-	@echo "🔬 Building RustFS with dial9 telemetry (features: $(DIAL9_FEATURES))..."
-	@echo "⚠️  Diagnostic build: telemetry writes trace segments to disk continuously."
-	RUSTFLAGS="$(DIAL9_RUSTFLAGS)" cargo build --release --bin rustfs --features $(DIAL9_FEATURES)
-
-.PHONY: build-cross-all
-build-cross-all: core-deps ## Build binaries for all architectures
-	@echo "🔧 Building all target architectures..."
-	@echo "💡 On macOS/Windows, use 'make docker-dev' for reliable multi-arch builds"
-	@echo "🔨 Generating protobuf code..."
-	cargo run --bin gproto || true
-
-	@echo "🔨 Building rustfs for x86_64-unknown-linux-musl..."
-	./build-rustfs.sh --platform x86_64-unknown-linux-musl
-
-	@echo "🔨 Building rustfs for x86_64-unknown-linux-gnu..."
-	./build-rustfs.sh --platform x86_64-unknown-linux-gnu
-
-	@echo "🔨 Building rustfs for aarch64-unknown-linux-musl..."
-	./build-rustfs.sh --platform aarch64-unknown-linux-musl
-
-	@echo "🔨 Building rustfs for aarch64-unknown-linux-gnu..."
-	./build-rustfs.sh --platform aarch64-unknown-linux-gnu

.config/make/check.mak

@@ -1,26 +0,0 @@
-## —— Check and Inform Dependencies ----------------------------------------------------------------
-
-# Fatal check
-# Checks all required dependencies and exits with error if not found
-# (e.g., cargo, rustfmt)
-check-%:
-	@command -v $* >/dev/null 2>&1 || { \
-		echo >&2 "❌ '$*' is not installed."; \
-		exit 1; \
-	}
-
-# Warning-only check
-# Checks for optional dependencies and issues a warning if not found
-warn-%:
-	@command -v $* >/dev/null 2>&1 || { \
-		echo >&2 "⚠️ '$*' is not installed."; \
-	}
-
-# For checking dependencies use check-<dep-name> or warn-<dep-name>
-#
-# NOTE: cargo-nextest is a HARD dependency of `make test`, gated inside the
-# test recipe itself (with a RUSTFS_ALLOW_CARGO_TEST_FALLBACK=1 escape hatch)
-# rather than a warn-only prerequisite here — see .config/make/tests.mak.
-.PHONY: core-deps fmt-deps
-core-deps: check-cargo ## Check core dependencies
-fmt-deps: check-rustfmt ## Check lint and formatting dependencies

.config/make/deploy.mak

@@ -1,6 +0,0 @@
-## —— Deploy using dev_deploy.sh script ------------------------------------------------------------
-
-.PHONY: deploy-dev
-deploy-dev: build-musl ## Deploy to dev server
-	@echo "🚀 Deploying to dev server: $${IP}"
-	./scripts/dev_deploy.sh $${IP}

.config/make/help.mak

@@ -1,38 +0,0 @@
-## —— Help, Help Build and Help Docker -------------------------------------------------------------
-
-
-.PHONY: help
-help: ## Shows This Help Menu
-	echo -e "$$HEADER"
-	grep -E '(^[a-zA-Z0-9_-]+:.*?## .*$$)|(^## )' $(MAKEFILE_LIST) | sed 's/^[^:]*://g' | awk 'BEGIN {FS = ":.*?## | #"} /^## / {printf "\n${green}%s${reset}\n", $$0; next} {printf "${cyan}%-30s${reset} ${white}%s${reset} ${green}%s${reset}\n", $$1, $$2, $$3}'
-
-.PHONY: help-build
-help-build: ## Shows RustFS build help
-	@echo ""
-	@echo "💡 build-rustfs.sh script provides more options, smart detection and binary verification"
-	@echo ""
-	@echo "🔧 Direct usage of build-rustfs.sh script:"
-	@echo ""
-	@echo "	./build-rustfs.sh --help                                # View script help"
-	@echo "	./build-rustfs.sh --no-console                          # Build without console resources"
-	@echo "	./build-rustfs.sh --force-console-update                # Force update console resources"
-	@echo "	./build-rustfs.sh --dev                                 # Development mode build"
-	@echo "	./build-rustfs.sh --sign                                # Sign binary files"
-	@echo "	./build-rustfs.sh --platform x86_64-unknown-linux-gnu   # Specify target platform"
-	@echo "	./build-rustfs.sh --skip-verification                   # Skip binary verification"
-	@echo ""
-
-.PHONY: help-docker
-help-docker: ## Shows docker environment and suggestion help
-	@echo ""
-	@echo "📋 Environment Variables:"
-	@echo "	REGISTRY                 Image registry address (required for push)"
-	@echo "	DOCKERHUB_USERNAME       Docker Hub username"
-	@echo "	DOCKERHUB_TOKEN          Docker Hub access token"
-	@echo "	GITHUB_TOKEN             GitHub access token"
-	@echo ""
-	@echo "💡 Suggestions:"
-	@echo "	Production use:          Use docker-buildx* commands (based on precompiled binaries)"
-	@echo "	Local development:       Use docker-dev* commands (build from source)"
-	@echo "	Development environment: Use dev-env-* commands to manage dev containers"
-	@echo ""

.config/make/lint-fmt.mak

@@ -1,66 +0,0 @@
-## —— Code quality and Formatting ------------------------------------------------------------------
-
-.NOTPARALLEL: fix
-
-.PHONY: fmt
-fmt: core-deps fmt-deps ## Format code
-	@echo "🔧 Formatting code..."
-	cargo fmt --all
-
-.PHONY: fmt-check
-fmt-check: core-deps fmt-deps ## Check code formatting
-	@echo "📝 Checking code formatting..."
-	cargo fmt --all --check
-
-.PHONY: clippy-check
-clippy-check: core-deps ## Run clippy checks
-	@echo "🔍 Running clippy checks..."
-	cargo clippy --all-targets -- -D warnings
-
-.PHONY: clippy-fix
-clippy-fix: core-deps ## Apply clippy fixes
-	@echo "🔧 Applying clippy fixes..."
-	cargo clippy --fix --allow-dirty
-
-.PHONY: fix
-fix: fmt clippy-fix ## Format code and apply clippy fixes
-
-.PHONY: quick-check
-quick-check: core-deps ## Run fast workspace compilation check
-	@echo "🔨 Running fast compilation check..."
-	cargo check --workspace --exclude e2e_test
-
-.PHONY: unsafe-code-check
-unsafe-code-check: ## Check unsafe_code allowances have SAFETY comments
-	@echo "🔒 Checking unsafe_code allowances..."
-	./scripts/check_unsafe_code_allowances.sh
-
-.PHONY: architecture-migration-check
-architecture-migration-check: ## Check architecture migration guardrails
-	@echo "🏗️ Checking architecture migration guardrails..."
-	./scripts/check_architecture_migration_rules.sh
-
-.PHONY: logging-guardrails-check
-logging-guardrails-check: ## Check logging guardrails for redaction and noise regressions
-	@echo "🪵 Checking logging guardrails..."
-	./scripts/check_logging_guardrails.sh
-
-.PHONY: tokio-io-uring-check
-tokio-io-uring-check: ## Check tokio io-uring runtime feature stays removed
-	@echo "🚫 Checking tokio io-uring feature guard..."
-	./scripts/check_no_tokio_io_uring.sh
-
-.PHONY: extension-schema-check
-extension-schema-check: ## Check extension-schema stays a lightweight contract crate
-	@echo "🧩 Checking extension schema boundaries..."
-	./scripts/check_extension_schema_boundaries.sh
-
-.PHONY: body-cache-whitelist-check
-body-cache-whitelist-check: ## Check the body-cache eligibility gate stays a fail-closed allow-list
-	@echo "🧱 Checking body-cache whitelist guard..."
-	./scripts/check_body_cache_whitelist.sh
-
-.PHONY: compilation-check
-compilation-check: core-deps ## Run compilation check
-	@echo "🔨 Running compilation check..."
-	cargo check --all-targets

.config/make/pre-commit.mak

@@ -1,31 +0,0 @@
-## —— Pre Commit Checks ----------------------------------------------------------------------------
-
-.NOTPARALLEL: pre-commit pre-pr dev-check
-
-.PHONY: setup-hooks
-setup-hooks: ## Set up git hooks
-	@echo "🔧 Setting up git hooks..."
-	chmod +x .git/hooks/pre-commit
-	@echo "✅ Git hooks setup complete!"
-
-.PHONY: doc-paths-check
-doc-paths-check: ## Check that instruction/architecture docs reference existing file paths
-	@echo "📄 Checking doc path references..."
-	./scripts/check_doc_paths.sh
-
-.PHONY: planning-docs-check
-planning-docs-check: ## Check that no planning-type documents are committed
-	@echo "📄 Checking for committed planning docs..."
-	./scripts/check_no_planning_docs.sh
-
-.PHONY: pre-commit
-pre-commit: fmt-check unsafe-code-check architecture-migration-check logging-guardrails-check tokio-io-uring-check extension-schema-check body-cache-whitelist-check doc-paths-check planning-docs-check quick-check ## Run fast pre-commit checks without clippy/full tests
-	@echo "✅ All pre-commit checks passed!"
-
-.PHONY: pre-pr
-pre-pr: fmt-check unsafe-code-check architecture-migration-check logging-guardrails-check tokio-io-uring-check extension-schema-check body-cache-whitelist-check doc-paths-check planning-docs-check clippy-check test ## Run full pre-PR checks with clippy and tests
-	@echo "✅ All pre-PR checks passed!"
-
-.PHONY: dev-check
-dev-check: fmt-check unsafe-code-check architecture-migration-check logging-guardrails-check tokio-io-uring-check extension-schema-check body-cache-whitelist-check doc-paths-check planning-docs-check quick-check ## Run fast local development checks
-	@echo "✅ Fast development checks passed!"

.config/make/tests.mak

@@ -1,72 +0,0 @@
-## —— Tests and e2e test ---------------------------------------------------------------------------
-
-TEST_THREADS ?= 1
-
-# cargo-nextest is a HARD dependency of `make test`.
-#
-# nextest changes test semantics vs plain `cargo test`: it runs every test in
-# its own process (so serial_test's #[serial] mutex does not serialize across
-# tests) and it is the only runner that honours .config/nextest.toml
-# [test-groups] (e.g. the ecstore-serial-flaky serialization guard). CI runs
-# nextest (.github/actions/setup/action.yml installs it), so a silent fallback
-# to `cargo test` would run with different serialization behaviour than CI and
-# mask (or invent) flakes.
-#
-# Installing cargo-nextest:
-#   cargo install cargo-nextest --locked          # from source
-#   # or a prebuilt binary (faster) via the taiki-e installer / get.nexte.st:
-#   #   https://nexte.st/docs/installation/
-#
-# Escape hatch: set RUSTFS_ALLOW_CARGO_TEST_FALLBACK=1 to run the plain
-# `cargo test` fallback anyway. Results are NOT authoritative — semantics
-# differ from CI and .config/nextest.toml test-groups will NOT apply.
-
-.PHONY: script-tests
-script-tests: ## Run shell script tests
-	@echo "Running script tests..."
-	./scripts/test_build_rustfs_options.sh
-	./scripts/test_entrypoint_credentials.sh
-
-.PHONY: test
-test: core-deps script-tests ## Run all tests (needs cargo-nextest; RUSTFS_ALLOW_CARGO_TEST_FALLBACK=1 to override)
-	@echo "🧪 Running tests..."
-	@if command -v cargo-nextest >/dev/null 2>&1; then \
-		cargo nextest run --all --exclude e2e_test; \
-	elif [ "$${RUSTFS_ALLOW_CARGO_TEST_FALLBACK:-0}" = "1" ]; then \
-		echo >&2 "⚠️  ============================================================================"; \
-		echo >&2 "⚠️  cargo-nextest NOT found — running the 'cargo test' fallback (opt-in)."; \
-		echo >&2 "⚠️  TEST SEMANTICS DIFFER FROM CI; results are NOT authoritative:"; \
-		echo >&2 "⚠️    * nextest runs each test in its own process; 'cargo test' does not,"; \
-		echo >&2 "⚠️      so serial_test #[serial] serialization behaves differently."; \
-		echo >&2 "⚠️    * .config/nextest.toml [test-groups] will NOT apply (e.g. the"; \
-		echo >&2 "⚠️      ecstore-serial-flaky group), so load-sensitive tests may flake here"; \
-		echo >&2 "⚠️      but pass on CI (or vice versa)."; \
-		echo >&2 "⚠️  Install cargo-nextest and re-run before trusting these results."; \
-		echo >&2 "⚠️  ============================================================================"; \
-		cargo test --workspace --exclude e2e_test -- --nocapture --test-threads="$(TEST_THREADS)"; \
-	else \
-		echo >&2 "❌ cargo-nextest is required for 'make test' but was not found."; \
-		echo >&2 ""; \
-		echo >&2 "   RustFS tests run under cargo-nextest (process-per-test isolation)."; \
-		echo >&2 "   CI runs nextest and .config/nextest.toml [test-groups] only take effect"; \
-		echo >&2 "   under nextest. Plain 'cargo test' has different serialization semantics"; \
-		echo >&2 "   and is NOT a faithful substitute."; \
-		echo >&2 ""; \
-		echo >&2 "   Install it with either:"; \
-		echo >&2 "     cargo install cargo-nextest --locked"; \
-		echo >&2 "   or a prebuilt binary (faster) — see https://nexte.st/docs/installation/"; \
-		echo >&2 ""; \
-		echo >&2 "   To run the plain 'cargo test' fallback anyway (results NOT authoritative;"; \
-		echo >&2 "   serialization semantics differ from CI), re-run with:"; \
-		echo >&2 "     RUSTFS_ALLOW_CARGO_TEST_FALLBACK=1 make test"; \
-		exit 1; \
-	fi
-	cargo test --all --doc
-
-.PHONY: e2e-server
-e2e-server: ## Run e2e-server tests
-	sh $(shell pwd)/scripts/run.sh
-
-.PHONY: probe-e2e
-probe-e2e: ## Probe e2e tests
-	sh $(shell pwd)/scripts/probe.sh

.config/migration-gate-floor.txt

@@ -1,10 +0,0 @@
-# Committed floor for the number of tests selected by the migration-critical
-# CI gate (see scripts/check_migration_gate_count.sh, backlog#1153 infra-12).
-#
-# The floor equals the exact count of rustfs-ecstore --lib tests matching the
-# gate filter (name substrings: data_movement, rebalance, decommission,
-# source_cleanup, delete_marker) at the time this file was last updated.
-# CI fails if the selected count drops below this number, so renames or
-# removals that thin the gate must update this file in the same PR.
-# Adding tests does not require a bump, but bumping keeps the guard tight.
-571

.config/nextest.toml

@@ -1,201 +0,0 @@
-# nextest configuration for RustFS.
-#
-# Serialize two known load-sensitive / global-state-sharing ecstore test groups
-# so the full parallel nextest suite stops producing spurious failures
-# (backlog #937). These tests pass in isolation but flake under the loaded
-# parallel run for two distinct reasons:
-#
-#   * store::bucket::tests::bucket_delete_* share process/global state (disk
-#     registry, lock client) and race make_bucket into InsufficientWriteQuorum
-#     when run concurrently with other ecstore tests.
-#   * bucket_lifecycle_ops::tests::concurrent_resend_same_part_commits_one_generation
-#     asserts a lock-acquire correctness property whose serialized cross-disk
-#     commits exceed the (already max'd, 60s) acquire deadline only when the
-#     suite saturates disk I/O.
-#
-# serial_test's #[serial] attribute does NOT serialize these across runs:
-# nextest executes each test in its own process, where the in-process
-# serial_test mutex has no effect. A nextest test-group with max-threads = 1 is
-# the mechanism that actually serializes across nextest's process boundary.
-#
-# ---------------------------------------------------------------------------
-# Profiles
-# ---------------------------------------------------------------------------
-# The `default` profile is what local `cargo nextest run` uses. It NEVER
-# retries: a red test locally means a real failure to investigate, not noise to
-# paper over. The `ci` profile (below) is the strict CI gate: global
-# retries = 0 so a new race's first occurrence is never masked, plus a
-# narrowly-scoped quarantine list (retries = 2) for tests with a tracked OPEN
-# flake issue. Flake policy lives in docs/testing/README.md.
-
-[test-groups]
-ecstore-serial-flaky = { max-threads = 1 }
-
-# Reliability / fault-injection e2e tests each spawn a single-node 4-disk RustFS
-# server and manipulate its disk directories at runtime (crates/e2e_test:
-# reliability_disk_fault_test, degraded_read_eof_regression_test / dist-13). They
-# are correct in isolation but resource-heavy; serialize them under nextest's
-# process boundary (serial_test's #[serial] does not cross it) so several 4-disk
-# servers never run at once. ci-7's nightly picks these up via the e2e suite;
-# they are deliberately NOT in the fast PR `e2e-smoke` filter.
-e2e-reliability = { max-threads = 1 }
-
-# --- default profile (local): serialize the flaky groups, never retry --------
-[[profile.default.overrides]]
-filter = 'package(rustfs-ecstore) & (test(concurrent_resend_same_part_commits_one_generation) | test(/^store::bucket::tests::bucket_delete_(mark_delete_marks|purge_removes|default_s3_delete)/))'
-test-group = 'ecstore-serial-flaky'
-
-# Serialize the 4-disk reliability / degraded-read e2e tests (see the
-# e2e-reliability test-group note above). The matching ci-profile override is at
-# the end of the file, after [profile.ci] is declared.
-[[profile.default.overrides]]
-filter = 'package(e2e_test) & test(/^(reliability_disk_fault|degraded_read_eof_regression)_test::/)'
-test-group = 'e2e-reliability'
-
-# ---------------------------------------------------------------------------
-# ci profile — the strict CI gate (ci.yml `cargo nextest run --profile ci`)
-# ---------------------------------------------------------------------------
-[profile.ci]
-# Strict: a new race must fail on its first occurrence, never be retried away.
-retries = 0
-# Report every failure in one run instead of bailing on the first.
-fail-fast = false
-
-[profile.ci.junit]
-# Emitted to target/nextest/ci/junit.xml; uploaded as a CI artifact.
-# Tests that pass only after a quarantine retry are marked `flaky` here — that
-# marker is the observable signal the flake policy is built around.
-path = "junit.xml"
-
-# ===========================================================================
-# QUARANTINE — flaky tests granted retries = 2 under the ci profile ONLY.
-#
-# RULES (enforced by review, see docs/testing/README.md):
-#   * Every entry MUST link exactly one OPEN issue tracking the flake.
-#   * An entry stays until the issue is fixed (test made robust) or the test is
-#     deleted — 30-day policy. No entry may exist without a live issue link.
-#
-# Each entry also re-declares the `ecstore-serial-flaky` test-group so the
-# serialization holds under the ci profile (nextest evaluates a named
-# profile's own overrides list, not the default profile's).
-# ===========================================================================
-
-# QUARANTINE: OPEN backlog#937 — concurrent_resend lock-acquire deadline flakes
-# under saturated disk I/O in the full parallel suite.
-[[profile.ci.overrides]]
-filter = 'package(rustfs-ecstore) & test(concurrent_resend_same_part_commits_one_generation)'
-test-group = 'ecstore-serial-flaky'
-retries = 2
-
-# QUARANTINE: OPEN backlog#937 — store::bucket::tests::bucket_delete_* race
-# make_bucket into InsufficientWriteQuorum via shared global state under load.
-[[profile.ci.overrides]]
-filter = 'package(rustfs-ecstore) & test(/^store::bucket::tests::bucket_delete_(mark_delete_marks|purge_removes|default_s3_delete)/)'
-test-group = 'ecstore-serial-flaky'
-retries = 2
-
-# QUARANTINE: OPEN rustfs#4690 — walk_dir stall-budget accounting test depends
-# on producer/consumer timing windows that stretch past the budget on loaded
-# CI runners (regression test for rustfs#4644; failed on a zero-Rust-diff PR).
-[[profile.ci.overrides]]
-filter = 'package(rustfs-ecstore) & test(walk_dir_does_not_charge_consumer_backpressure_to_the_stall_budget)'
-retries = 2
-
-# Serialize the 4-disk reliability / degraded-read e2e tests under the ci
-# profile too (see the e2e-reliability test-group note near the top). Not a
-# quarantine: no retries, just single-threaded so several 4-disk servers never
-# run concurrently when ci-7's nightly runs the full e2e suite.
-[[profile.ci.overrides]]
-filter = 'package(e2e_test) & test(/^(reliability_disk_fault|degraded_read_eof_regression)_test::/)'
-test-group = 'e2e-reliability'
-
-# ---------------------------------------------------------------------------
-# e2e-smoke profile — PR smoke subset of the e2e_test crate (backlog#1149 ci-4)
-# ---------------------------------------------------------------------------
-# PR smoke subset of the e2e_test crate (backlog#1149 ci-4). This profile is
-# the single wiring mechanism for e2e tests in CI: other suites join by
-# extending this filter (or a sibling profile), never by adding ad-hoc e2e
-# jobs to ci.yml. Admission criteria (see crates/e2e_test/README.md): fast,
-# single-node topology, no external dependencies (no awscurl / Vault / fixed
-# ports / pre-started server), no #[ignore].
-#
-# Each e2e test spawns its own rustfs server on a random port with an isolated
-# temp dir (crates/e2e_test/src/common.rs), so the subset is parallel-safe.
-#
-# Replication PR subset (backlog#1147 repl-1): the second clause admits the 20
-# FAST bucket-replication tests from replication_extension_test — the
-# target-registration / replication-check / list / remove / delete admin paths
-# that validate config synchronously and never wait for asynchronous
-# replication convergence. Each spawns its own single-node rustfs server(s) on
-# random ports (source, plus an independent single-node target for the pair
-# checks — NOT a cluster), so the subset stays parallel-safe and single-digit
-# seconds. The data-plane tests that poll for convergence and all
-# `_real_dual_node` / `_real_single_node`
-# site-replication tests run in the [profile.e2e-repl-nightly] lane below, NOT
-# here. This allowlist is the single source of truth for the PR/nightly split:
-# the nightly profile derives its set as "the replication module MINUS this
-# allowlist", so any new replication test lands in nightly by default (never
-# silently unrun) until it is explicitly blessed as fast here. Keep the two
-# regexes byte-identical. Count invariant: 20 here + 18 nightly = 38 total
-# (authority: `cargo nextest list`; docs/testing/e2e-suite-inventory.md).
-# HISTORY (2026-07-11): the 20 fast tests were briefly pulled out of this lane
-# (#4724) because they set a loopback (127.0.0.1) replication target that the
-# SSRF egress guard rejected on every PR after repl-1 (#4712). That is fixed —
-# the guard now honours an off-by-default opt-in and this suite's source servers
-# set it (RUSTFS_REPLICATION_ALLOW_LOOPBACK_TARGET) — so the allowlist below is
-# restored.
-[profile.e2e-smoke]
-default-filter = """
-    package(e2e_test) & (
-        test(/^(delete_marker_migration_semantics|version_id_regression|list_objects_v2_pagination|list_object_versions_regression|list_objects_duplicates|list_buckets_double_slash|leading_slash_key|special_chars|create_bucket_region|delete_objects_versioning|head_object_consistency|head_object_range|copy_object_metadata|copy_source_invalid_date|content_encoding|anonymous_access|bucket_policy_check|presigned_negative)_test::/)
-        | test(/^replication_extension_test::(test_replication_check_succeeds_with_remote_target|test_replication_check_rejects_target_without_object_lock|test_set_remote_target_rejects_unversioned_source_bucket|test_replication_check_rejects_unversioned_source_bucket|test_replication_check_rejects_missing_replication_config|test_replication_check_rejects_invalid_bucket|test_set_remote_target_rejects_same_bucket_on_same_deployment|test_set_remote_target_rejects_unversioned_target_bucket|test_set_remote_target_update_requires_arn|test_set_remote_target_update_rejects_missing_target|test_set_remote_target_rejects_invalid_target_url|test_set_remote_target_rejects_self_signed_https_target_without_skip_tls_verify|test_set_remote_target_rejects_private_ca_https_target_without_ca_cert_pem|test_list_remote_targets_rejects_empty_bucket|test_list_remote_targets_rejects_invalid_bucket|test_remove_remote_target_rejects_missing_target|test_remove_remote_target_rejects_missing_arn|test_remove_remote_target_rejects_invalid_bucket|test_remove_remote_target_rejects_target_used_by_replication|test_delete_bucket_replication_removes_remote_target)$/)
-        | test(/^reliant::lifecycle::/)
-    )
-"""
-fail-fast = false
-
-# ---------------------------------------------------------------------------
-# e2e-repl-nightly profile — scheduled full replication e2e lane (repl-1)
-# ---------------------------------------------------------------------------
-# backlog#1147 repl-1 (deps: ci-4). Runs the SLOW / cross-process replication
-# tests that are unfit for the per-PR e2e-smoke gate:
-#
-#   * 8 bucket-replication data-plane tests — they PUT/delete objects and poll
-#     until source and target converge; two replicate over HTTPS.
-#   * 9 `_real_dual_node` site-replication tests — each spawns TWO full rustfs
-#     servers and drives the cross-process site-replication control plane.
-#   * 1 `_real_single_node` service-account round-trip test.
-#
-# The set is defined as "everything in replication_extension_test that is NOT
-# in the e2e-smoke PR allowlist above" (the negated clause is byte-identical to
-# the allowlist), so a newly added replication test automatically runs here
-# until it is explicitly promoted to the fast PR subset — no replication test
-# is ever silently left out of CI.
-#
-# #[serial] does NOT serialize under nextest (process-per-test; see the file
-# header). These tests need no cross-test serialization: each spawns its own
-# server(s) on random ports with isolated temp dirs, so they are parallel-safe
-# by construction — the same property the e2e-smoke subset relies on. If load
-# on the runner surfaces a real flake, quarantine the specific test with an
-# OPEN issue link (ci-10 / backlog#937 policy), never blanket-retry or exclude.
-#
-# Wired by .github/workflows/e2e-replication-nightly.yml (schedule +
-# workflow_dispatch), which builds the rustfs binary once, installs awscurl so
-# the STS dual-node test actually exercises its path (it skips gracefully with
-# a visible log line when awscurl is absent), and routes scheduled failures
-# through .github/actions/schedule-failure-issue (ci-8). Explicit division of
-# labor with ci-5's future e2e-full merge gate: these tests run ONLY here, not
-# double-run there. TODO(ci-7): fold this interim repl-owned lane into the ci
-# domain's consolidated scheduled e2e workflow once it exists.
-[profile.e2e-repl-nightly]
-default-filter = """
-    package(e2e_test)
-    & test(/^replication_extension_test::/)
-    & !test(/^replication_extension_test::(test_replication_check_succeeds_with_remote_target|test_replication_check_rejects_target_without_object_lock|test_set_remote_target_rejects_unversioned_source_bucket|test_replication_check_rejects_unversioned_source_bucket|test_replication_check_rejects_missing_replication_config|test_replication_check_rejects_invalid_bucket|test_set_remote_target_rejects_same_bucket_on_same_deployment|test_set_remote_target_rejects_unversioned_target_bucket|test_set_remote_target_update_requires_arn|test_set_remote_target_update_rejects_missing_target|test_set_remote_target_rejects_invalid_target_url|test_set_remote_target_rejects_self_signed_https_target_without_skip_tls_verify|test_set_remote_target_rejects_private_ca_https_target_without_ca_cert_pem|test_list_remote_targets_rejects_empty_bucket|test_list_remote_targets_rejects_invalid_bucket|test_remove_remote_target_rejects_missing_target|test_remove_remote_target_rejects_missing_arn|test_remove_remote_target_rejects_invalid_bucket|test_remove_remote_target_rejects_target_used_by_replication|test_delete_bucket_replication_removes_remote_target)$/)
-"""
-fail-fast = false
-
-[profile.e2e-repl-nightly.junit]
-# Emitted to target/nextest/e2e-repl-nightly/junit.xml; uploaded by the nightly
-# workflow as the failure-triage artifact.
-path = "junit.xml"

.docker/README.md

@@ -1,131 +1,261 @@
-# RustFS Docker Infrastructure
+# RustFS Docker Images
 
-This directory contains the complete Docker infrastructure for building, deploying, and monitoring RustFS. It provides ready-to-use configurations for development, testing, and production-grade observability.
+This directory contains Docker configuration files and supporting infrastructure for building and running RustFS container images.
 
-## 📂 Directory Structure
+## 📁 Directory Structure
 
-| Directory | Description | Status |
-| :--- | :--- | :--- |
-| **[`observability/`](observability/README.md)** | **[RECOMMENDED]** Full-stack observability (Prometheus, Grafana, Tempo, Loki). | ✅ Production-Ready |
-| **[`compose/`](compose/README.md)** | Specialized setups (e.g., 4-node distributed cluster testing). | ⚠️ Testing Only |
-| **[`mqtt/`](mqtt/README.md)** | EMQX Broker configuration for MQTT integration testing. | 🧪 Development |
-| **[`openobserve-otel/`](openobserve-otel/README.md)** | Alternative lightweight observability stack using OpenObserve. | 🔄 Alternative |
-
----
-
-## 📄 Root Directory Files
-
-The following files in the project root are essential for Docker operations:
-
-### Build Scripts & Dockerfiles
-
-| File | Description | Usage |
-| :--- | :--- | :--- |
-| **`docker-buildx.sh`** | **Multi-Arch Build Script**<br>Automates building and pushing Docker images for `amd64` and `arm64`. Supports release and dev channels. | `./docker-buildx.sh --push` |
-| **`Dockerfile`** | **Production Image (Alpine)**<br>Lightweight image using musl libc. Downloads pre-built binaries from GitHub Releases. | `docker build -t rustfs:latest .` |
-| **`Dockerfile.glibc`** | **Production Image (Ubuntu)**<br>Standard image using glibc. Useful if you need specific dynamic libraries. | `docker build -f Dockerfile.glibc .` |
-| **`Dockerfile.source`** | **Development Image**<br>Builds RustFS from source code. Includes build tools. Ideal for local development and CI. | `docker build -f Dockerfile.source .` |
-
-### Docker Compose Configurations
-
-| File | Description | Usage |
-| :--- | :--- | :--- |
-| **`docker-compose.yml`** | **Main Development Setup**<br>Comprehensive setup with profiles for development, observability, and proxying. | `docker compose up -d`<br>`docker compose --profile observability up -d` |
-| **`docker-compose-simple.yml`** | **Quick Start Setup**<br>Minimal configuration running a single RustFS instance with 4 volumes. Perfect for first-time users. | `docker compose -f docker-compose-simple.yml up -d` |
-
----
-
-## 🌟 Observability Stack (Recommended)
-
-Located in: [`.docker/observability/`](observability/README.md)
-
-We provide a comprehensive, industry-standard observability stack designed for deep insights into RustFS performance. This is the recommended setup for both development and production monitoring.
-
-### Components
-- **Metrics**: Prometheus (Collection) + Grafana (Visualization)
-- **Traces**: Tempo (Storage) + Jaeger (UI)
-- **Logs**: Loki
-- **Ingestion**: OpenTelemetry Collector
-
-### Key Features
-- **Full Persistence**: All metrics, logs, and traces are saved to Docker volumes, ensuring no data loss on restarts.
-- **Correlation**: Seamlessly jump between Logs, Traces, and Metrics in Grafana.
-- **High Performance**: Optimized configurations for batching, compression, and memory management.
-
-### Quick Start
-```bash
-cd .docker/observability
-docker compose up -d
+```
+rustfs/
+├── Dockerfile           # Production image (Alpine + pre-built binaries)
+├── Dockerfile.source    # Development image (Debian + source build)
+├── docker-buildx.sh     # Multi-architecture build script
+├── Makefile             # Build automation with simplified commands
+└── .docker/             # Supporting infrastructure
+    ├── observability/   # Monitoring and observability configs
+    ├── compose/         # Docker Compose configurations
+    ├── mqtt/            # MQTT broker configs
+    └── openobserve-otel/ # OpenObserve + OpenTelemetry configs
 ```
 
----
+## 🎯 Image Variants
 
-## 🧪 Specialized Environments
+### Core Images
 
-Located in: [`.docker/compose/`](compose/README.md)
+| Image | Base OS | Build Method | Size | Use Case |
+|-------|---------|--------------|------|----------|
+| `production` (default) | Alpine 3.18 | GitHub Releases | Smallest | Production deployment |
+| `source` | Debian Bookworm | Source build | Medium | Custom builds with cross-compilation |
+| `dev` | Debian Bookworm | Development tools | Large | Interactive development |
 
-These configurations are tailored for specific testing scenarios that require complex topologies.
+## 🚀 Usage Examples
+
+### Quick Start (Production)
 
-### Distributed Cluster (4-Nodes)
-Simulates a real-world distributed environment with 4 RustFS nodes running locally.
 ```bash
-docker compose -f .docker/compose/docker-compose.cluster.yaml up -d
+# Default production image (Alpine + GitHub Releases)
+docker run -p 9000:9000 rustfs/rustfs:latest
+
+# Specific version
+docker run -p 9000:9000 rustfs/rustfs:1.2.3
 ```
 
-### Integrated Observability Test
-A self-contained environment running 4 RustFS nodes alongside the full observability stack. Useful for end-to-end testing of telemetry.
+### Complete Tag Strategy Examples
+
 ```bash
-docker compose -f .docker/compose/docker-compose.observability.yaml up -d
+# Stable Releases
+docker run rustfs/rustfs:1.2.3           # Main version (production)
+docker run rustfs/rustfs:1.2.3-production # Explicit production variant
+docker run rustfs/rustfs:1.2.3-source   # Source build variant
+docker run rustfs/rustfs:latest          # Latest stable
+
+# Prerelease Versions
+docker run rustfs/rustfs:1.3.0-alpha.2  # Specific alpha version
+docker run rustfs/rustfs:alpha           # Latest alpha
+docker run rustfs/rustfs:beta            # Latest beta
+docker run rustfs/rustfs:rc              # Latest release candidate
+
+# Development Versions
+docker run rustfs/rustfs:dev             # Latest main branch development
+docker run rustfs/rustfs:dev-13e4a0b     # Specific commit
+docker run rustfs/rustfs:dev-latest      # Latest development
+docker run rustfs/rustfs:main-latest     # Main branch latest
 ```
 
----
+### Development Environment
 
-## 📡 MQTT Integration
-
-Located in: [`.docker/mqtt/`](mqtt/README.md)
-
-Provides an EMQX broker for testing RustFS MQTT features.
-
-### Quick Start
 ```bash
-cd .docker/mqtt
-docker compose up -d
-```
-- **Dashboard**: [http://localhost:18083](http://localhost:18083) (Default: `admin` / `public`)
-- **MQTT Port**: `1883`
+# Quick setup using Makefile (recommended)
+make docker-dev-local     # Build development image locally
+make dev-env-start        # Start development container
 
----
+# Manual Docker commands
+docker run -it -v $(pwd):/workspace -p 9000:9000 rustfs/rustfs:latest-dev
 
-## 👁️ Alternative: OpenObserve
+# Build from source locally
+docker build -f Dockerfile.source -t rustfs:custom .
 
-Located in: [`.docker/openobserve-otel/`](openobserve-otel/README.md)
-
-For users preferring a lightweight, all-in-one solution, we support OpenObserve. It combines logs, metrics, and traces into a single binary and UI.
-
-### Quick Start
-```bash
-cd .docker/openobserve-otel
-docker compose up -d
+# Development with hot reload
+docker-compose up rustfs-dev
 ```
 
----
+## 🏗️ Build Arguments and Scripts
 
-## 🔧 Common Operations
+### Using Makefile Commands (Recommended)
+
+The easiest way to build images using simplified commands:
 
-### Cleaning Up
-To stop all containers and remove volumes (**WARNING**: deletes all persisted data):
 ```bash
-docker compose down -v
+# Development images (build from source)
+make docker-dev-local             # Build for local use (single arch)
+make docker-dev                   # Build multi-arch (for CI/CD)
+make docker-dev-push REGISTRY=xxx # Build and push to registry
+
+# Production images (using pre-built binaries)
+make docker-buildx                # Build multi-arch production images
+make docker-buildx-push           # Build and push production images
+make docker-buildx-version VERSION=v1.0.0  # Build specific version
+
+# Development environment
+make dev-env-start                # Start development container
+make dev-env-stop                 # Stop development container
+make dev-env-restart              # Restart development container
+
+# Help
+make help-docker                  # Show all Docker-related commands
 ```
 
-### Viewing Logs
-To follow logs for a specific service:
+### Using docker-buildx.sh (Advanced)
+
+For direct script usage and advanced scenarios:
+
 ```bash
-docker compose logs -f [service_name]
+# Build latest version for all architectures
+./docker-buildx.sh
+
+# Build and push to registry
+./docker-buildx.sh --push
+
+# Build specific version
+./docker-buildx.sh --release v1.2.3
+
+# Build and push specific version
+./docker-buildx.sh --release v1.2.3 --push
 ```
 
-### Checking Status
-To see the status of all running containers:
+### Manual Docker Builds
+
+All images support dynamic version selection:
+
 ```bash
-docker compose ps
+# Build production image with latest release
+docker build --build-arg RELEASE="latest" -t rustfs:latest .
+
+# Build from source with specific target
+docker build -f Dockerfile.source \
+  --build-arg TARGETPLATFORM="linux/amd64" \
+  -t rustfs:source .
+
+# Development build
+docker build -f Dockerfile.source -t rustfs:dev .
 ```
+
+## 🔧 Binary Download Sources
+
+### Unified GitHub Releases
+
+The production image downloads from GitHub Releases for reliability and transparency:
+
+- ✅ **production** → GitHub Releases API with automatic latest detection
+- ✅ **Checksum verification** → SHA256SUMS validation when available
+- ✅ **Multi-architecture** → Supports amd64 and arm64
+
+### Source Build
+
+The source variant compiles from source code with advanced features:
+
+- 🔧 **Cross-compilation** → Supports multiple target platforms via `TARGETPLATFORM`
+- ⚡ **Build caching** → sccache for faster compilation
+- 🎯 **Optimized builds** → Release optimizations with LTO and symbol stripping
+
+## 📋 Architecture Support
+
+All variants support multi-architecture builds:
+
+- **linux/amd64** (x86_64)
+- **linux/arm64** (aarch64)
+
+Architecture is automatically detected during build using Docker's `TARGETARCH` build argument.
+
+## 🔐 Security Features
+
+- **Checksum Verification**: Production image verifies SHA256SUMS when available
+- **Non-root User**: All images run as user `rustfs` (UID 1000)
+- **Minimal Runtime**: Production image only includes necessary dependencies
+- **Secure Defaults**: No hardcoded credentials or keys
+
+## 🛠️ Development Workflow
+
+### Quick Start with Makefile (Recommended)
+
+```bash
+# 1. Start development environment
+make dev-env-start
+
+# 2. Your development container is now running with:
+#    - Port 9000 exposed for RustFS
+#    - Port 9010 exposed for admin console
+#    - Current directory mounted as /workspace
+
+# 3. Stop when done
+make dev-env-stop
+```
+
+### Manual Development Setup
+
+```bash
+# Build development image from source
+make docker-dev-local
+
+# Or use traditional Docker commands
+docker build -f Dockerfile.source -t rustfs:dev .
+
+# Run with development tools
+docker run -it -v $(pwd):/workspace -p 9000:9000 rustfs:dev bash
+
+# Or use docker-compose for complex setups
+docker-compose up rustfs-dev
+```
+
+### Common Development Tasks
+
+```bash
+# Build and test locally
+make build                        # Build binary natively
+make docker-dev-local            # Build development Docker image
+make test                        # Run tests
+make fmt                         # Format code
+make clippy                      # Run linter
+
+# Get help
+make help                        # General help
+make help-docker                 # Docker-specific help
+make help-build                  # Build-specific help
+```
+
+## 🚀 CI/CD Integration
+
+The project uses GitHub Actions for automated multi-architecture Docker builds:
+
+### Automated Builds
+
+- **Tags**: Automatic builds triggered on version tags (e.g., `v1.2.3`)
+- **Main Branch**: Development builds with `dev-latest` and `main-latest` tags
+- **Pull Requests**: Test builds without registry push
+
+### Build Variants
+
+Each build creates three image variants:
+
+- `rustfs/rustfs:v1.2.3` (production - Alpine-based)
+- `rustfs/rustfs:v1.2.3-source` (source build - Debian-based)
+- `rustfs/rustfs:v1.2.3-dev` (development - Debian-based with tools)
+
+### Manual Builds
+
+Trigger custom builds via GitHub Actions:
+
+```bash
+# Use workflow_dispatch to build specific versions
+# Available options: latest, main-latest, dev-latest, v1.2.3, dev-abc123
+```
+
+## 📦 Supporting Infrastructure
+
+The `.docker/` directory contains supporting configuration files:
+
+- **observability/** - Prometheus, Grafana, OpenTelemetry configs
+- **compose/** - Multi-service Docker Compose setups
+- **mqtt/** - MQTT broker configurations
+- **openobserve-otel/** - Log aggregation and tracing setup
+
+See individual README files in each subdirectory for specific usage instructions.

.docker/compose/README.md

@@ -1,102 +1,80 @@
-# Specialized Docker Compose Configurations
+# Docker Compose Configurations
 
-This directory contains specialized Docker Compose configurations for specific testing scenarios.
-
-## ⚠️ Important Note
-
-**For Observability:**
-We **strongly recommend** using the new, fully integrated observability stack located in `../observability/`. It provides a production-ready setup with Prometheus, Grafana, Tempo, Loki, and OpenTelemetry Collector, all with persistent storage and optimized configurations.
-
-The `docker-compose.observability.yaml` in this directory is kept for legacy reference or specific minimal testing needs but is **not** the primary recommended setup.
+This directory contains specialized Docker Compose configurations for different use cases.
 
 ## 📁 Configuration Files
 
-### Cluster Testing
+This directory contains specialized Docker Compose configurations and their associated Dockerfiles, keeping related files organized together.
 
-- **`docker-compose.cluster.yaml`**
-  - **Purpose**: Simulates a 4-node RustFS distributed cluster.
-  - **Use Case**: Testing distributed storage logic, consensus, and failover.
-  - **Nodes**: 4 RustFS instances.
-  - **Storage**: Uses local HTTP endpoints.
+### Main Configuration (Root Directory)
 
-### Legacy / Minimal Observability
+- **`../../docker-compose.yml`** - **Default Production Setup**
+  - Complete production-ready configuration
+  - Includes RustFS server + full observability stack
+  - Supports multiple profiles: `dev`, `observability`, `cache`, `proxy`
+  - Recommended for most users
 
-- **`docker-compose.observability.yaml`**
-  - **Purpose**: A minimal observability setup.
-  - **Status**: **Deprecated**. Please use `../observability/docker-compose.yml` instead.
+### Specialized Configurations
+
+- **`docker-compose.cluster.yaml`** - **Distributed Testing**
+  - 4-node cluster setup for testing distributed storage
+  - Uses local compiled binaries
+  - Simulates multi-node environment
+  - Ideal for development and cluster testing
+
+- **`docker-compose.observability.yaml`** - **Observability Focus**
+  - Specialized setup for testing observability features
+  - Includes OpenTelemetry, Jaeger, Prometheus, Loki, Grafana
+  - Uses `../../Dockerfile.source` for builds
+  - Perfect for observability development
 
 ## 🚀 Usage Examples
 
+### Production Setup
+
+```bash
+# Start main service
+docker-compose up -d
+
+# Start with development profile
+docker-compose --profile dev up -d
+
+# Start with full observability
+docker-compose --profile observability up -d
+```
+
 ### Cluster Testing
 
-To start a 4-node cluster for distributed testing:
-
 ```bash
-# From project root
-docker compose -f .docker/compose/docker-compose.cluster.yaml up -d
+# Build and start 4-node cluster (run from project root)
+cd .docker/compose
+docker-compose -f docker-compose.cluster.yaml up -d
+
+# Or run directly from project root
+docker-compose -f .docker/compose/docker-compose.cluster.yaml up -d
 ```
 
-### Script-Based 4-Node Validation (Recommended)
-
-Use the local validation script when you need local-source image build, failover checks,
-and benchmark workflow in one command:
+### Observability Testing
 
 ```bash
-# Default mode: WAIT_PROBE_MODE=service
-# This avoids false negatives where /health/ready remains 503 locally
-# while the service path is already available.
-./scripts/run_four_node_cluster_failover_bench.sh
+# Start observability-focused environment (run from project root)
+cd .docker/compose
+docker-compose -f docker-compose.observability.yaml up -d
+
+# Or run directly from project root
+docker-compose -f .docker/compose/docker-compose.observability.yaml up -d
 ```
 
-Strict mode is available when you explicitly want `/health/ready == 200` as the gate:
+## 🔧 Configuration Overview
 
-```bash
-WAIT_PROBE_MODE=ready ./scripts/run_four_node_cluster_failover_bench.sh
-```
+| Configuration | Nodes | Storage | Observability | Use Case |
+|---------------|-------|---------|---------------|----------|
+| **Main** | 1 | Volume mounts | Full stack | Production |
+| **Cluster** | 4 | HTTP endpoints | Basic | Testing |
+| **Observability** | 4 | Local data | Advanced | Development |
 
-### Profiling + Trace Validation
+## 📝 Notes
 
-The profiling-focused 4-node compose keeps profiling enabled and points RustFS
-to an OTLP/HTTP collector endpoint:
-
-```bash
-docker compose -f .docker/compose/docker-compose.cluster.local-build.profiling-amd64.yml up -d
-```
-
-Important behavior notes:
-
-- `RUSTFS_OBS_ENDPOINT` is the OTLP/HTTP base URL. RustFS automatically sends
-  traces to `/v1/traces`, metrics to `/v1/metrics`, and logs to `/v1/logs`.
-- Startup usually produces logs and metrics first. That does not guarantee
-  visible traces yet.
-- Trace data becomes obvious only after real HTTP/S3/gRPC requests hit RustFS.
-- `RUSTFS_OBS_LOGGER_LEVEL=info` keeps the top-level request span but filters
-  many nested `debug` spans. If Tempo/Jaeger looks sparse, retry with
-  `RUSTFS_OBS_LOGGER_LEVEL=debug` before suspecting the collector.
-
-Minimal trace verification flow:
-
-```bash
-# 1. Start the profiling compose with richer span visibility.
-RUSTFS_OBS_LOGGER_LEVEL=debug \
-docker compose -f .docker/compose/docker-compose.cluster.local-build.profiling-amd64.yml up -d
-
-# 2. Generate real request traffic after startup.
-curl -I http://127.0.0.1:9000/health
-curl -I http://127.0.0.1:9000/health/ready
-
-# 3. Then inspect Tempo or Jaeger.
-# Grafana: http://localhost:3000
-# Jaeger:  http://localhost:16686
-```
-
-If logs and metrics are present but traces are sparse, the most common cause is
-"no real request traffic yet" or "`info` level filtered nested spans", not an
-OTLP routing failure.
-
-### (Deprecated) Minimal Observability
-
-```bash
-# From project root
-docker compose -f .docker/compose/docker-compose.observability.yaml up -d
-```
+- Always ensure you have built the required binaries before starting cluster tests
+- The main configuration is sufficient for most use cases
+- Specialized configurations are for specific testing scenarios

.docker/compose/docker-compose.cluster.local-build.profiling-amd64.yml

@@ -1,236 +0,0 @@
-# Copyright 2024 RustFS Team
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-
-# Profiling-first 4-node local-build compose.
-#
-# Goals:
-# - force linux/amd64 runtime/build on Apple Silicon hosts;
-# - enable RustFS built-in CPU profiling;
-# - keep all tuning knobs host-overridable via env.
-#
-# Observability notes:
-# - `RUSTFS_OBS_ENDPOINT` is the OTLP/HTTP base URL. RustFS appends
-#   `/v1/traces`, `/v1/metrics`, and `/v1/logs` automatically.
-# - Logs and metrics usually appear during startup. Traces mainly appear after
-#   real HTTP/S3/gRPC requests create spans.
-# - `RUSTFS_OBS_LOGGER_LEVEL=info` keeps the top-level request trace span but
-#   filters many `debug`-level nested spans. Use `debug` when validating trace
-#   richness rather than collector reachability.
-
-services:
-  node1:
-    platform: ${RUSTFS_DOCKER_PLATFORM:-linux/amd64}
-    image: ${RUSTFS_IMAGE:-rustfs/rustfs:local-4node}
-    build:
-      context: ../..
-      dockerfile: Dockerfile.source
-    hostname: node1
-    environment:
-      - RUSTFS_VOLUMES=http://node{1...4}:9000/data/rustfs{0...3}
-      - RUSTFS_ADDRESS=:9000
-      - RUSTFS_CONSOLE_ENABLE=true
-      - RUSTFS_ACCESS_KEY=${RUSTFS_ACCESS_KEY:-rustfs-cluster-admin}
-      - RUSTFS_SECRET_KEY=${RUSTFS_SECRET_KEY:-rustfs-cluster-secret}
-      - RUSTFS_OBS_ENDPOINT=${RUSTFS_OBS_ENDPOINT:-http://host.docker.internal:4318}
-      # `info` is enough for startup logs/metrics. Use `debug` if Tempo/Jaeger
-      # should show richer nested spans during request-path verification.
-      - RUSTFS_OBS_LOGGER_LEVEL=${RUSTFS_OBS_LOGGER_LEVEL:-info}
-      - RUSTFS_OBS_PROFILING_ENDPOINT=${RUSTFS_OBS_PROFILING_ENDPOINT:-http://host.docker.internal:4040}
-      - RUSTFS_OBS_PROFILING_EXPORT_ENABLED=${RUSTFS_OBS_PROFILING_EXPORT_ENABLED:-true}
-      - RUSTFS_UNSAFE_BYPASS_DISK_CHECK=${RUSTFS_UNSAFE_BYPASS_DISK_CHECK:-true}
-      - RUSTFS_ENABLE_PROFILING=${RUSTFS_ENABLE_PROFILING:-true}
-      - RUSTFS_PROF_CPU_MODE=${RUSTFS_PROF_CPU_MODE:-continuous}
-      - RUSTFS_PROF_CPU_FREQ=${RUSTFS_PROF_CPU_FREQ:-99}
-      - RUSTFS_PROF_OUTPUT_DIR=${RUSTFS_PROF_OUTPUT_DIR:-/tmp/rustfs-profiles}
-      - RUSTFS_OBJECT_MAX_CONCURRENT_DISK_READS=${RUSTFS_OBJECT_MAX_CONCURRENT_DISK_READS:-48}
-      - RUSTFS_OBJECT_IO_BUFFER_SIZE=${RUSTFS_OBJECT_IO_BUFFER_SIZE:-262144}
-      - RUSTFS_OBJECT_MEDIUM_CONCURRENCY_THRESHOLD=${RUSTFS_OBJECT_MEDIUM_CONCURRENCY_THRESHOLD:-6}
-      - RUSTFS_OBJECT_HIGH_CONCURRENCY_THRESHOLD=${RUSTFS_OBJECT_HIGH_CONCURRENCY_THRESHOLD:-12}
-      - RUSTFS_OBJECT_IO_RANDOM_READAHEAD_DISABLE_CONCURRENCY=${RUSTFS_OBJECT_IO_RANDOM_READAHEAD_DISABLE_CONCURRENCY:-8}
-      - RUSTFS_OBJECT_DUPLEX_BUFFER_SIZE=${RUSTFS_OBJECT_DUPLEX_BUFFER_SIZE:-8388608}
-      - RUSTFS_ERASURE_ENCODE_MAX_INFLIGHT_BYTES=${RUSTFS_ERASURE_ENCODE_MAX_INFLIGHT_BYTES:-25165824}
-      - RUSTFS_RUNTIME_WORKER_THREADS=${RUSTFS_RUNTIME_WORKER_THREADS:-12}
-      - RUSTFS_RUNTIME_MAX_BLOCKING_THREADS=${RUSTFS_RUNTIME_MAX_BLOCKING_THREADS:-512}
-      - RUSTFS_ALLOCATOR_RECLAIM_ENABLED=${RUSTFS_ALLOCATOR_RECLAIM_ENABLED:-false}
-    extra_hosts:
-      - "host.docker.internal:host-gateway"
-    volumes:
-      - node1_data_0:/data/rustfs0
-      - node1_data_1:/data/rustfs1
-      - node1_data_2:/data/rustfs2
-      - node1_data_3:/data/rustfs3
-    ports:
-      - "9000:9000"
-    networks:
-      - rustfs-cluster-net
-
-  node2:
-    platform: ${RUSTFS_DOCKER_PLATFORM:-linux/amd64}
-    image: ${RUSTFS_IMAGE:-rustfs/rustfs:local-4node}
-    build:
-      context: ../..
-      dockerfile: Dockerfile.source
-    hostname: node2
-    environment:
-      - RUSTFS_VOLUMES=http://node{1...4}:9000/data/rustfs{0...3}
-      - RUSTFS_ADDRESS=:9000
-      - RUSTFS_CONSOLE_ENABLE=true
-      - RUSTFS_ACCESS_KEY=${RUSTFS_ACCESS_KEY:-rustfs-cluster-admin}
-      - RUSTFS_SECRET_KEY=${RUSTFS_SECRET_KEY:-rustfs-cluster-secret}
-      - RUSTFS_OBS_ENDPOINT=${RUSTFS_OBS_ENDPOINT:-http://host.docker.internal:4318}
-      # `info` is enough for startup logs/metrics. Use `debug` if Tempo/Jaeger
-      # should show richer nested spans during request-path verification.
-      - RUSTFS_OBS_LOGGER_LEVEL=${RUSTFS_OBS_LOGGER_LEVEL:-info}
-      - RUSTFS_OBS_PROFILING_ENDPOINT=${RUSTFS_OBS_PROFILING_ENDPOINT:-http://host.docker.internal:4040}
-      - RUSTFS_OBS_PROFILING_EXPORT_ENABLED=${RUSTFS_OBS_PROFILING_EXPORT_ENABLED:-true}
-      - RUSTFS_UNSAFE_BYPASS_DISK_CHECK=${RUSTFS_UNSAFE_BYPASS_DISK_CHECK:-true}
-      - RUSTFS_ENABLE_PROFILING=${RUSTFS_ENABLE_PROFILING:-true}
-      - RUSTFS_PROF_CPU_MODE=${RUSTFS_PROF_CPU_MODE:-continuous}
-      - RUSTFS_PROF_CPU_FREQ=${RUSTFS_PROF_CPU_FREQ:-99}
-      - RUSTFS_PROF_OUTPUT_DIR=${RUSTFS_PROF_OUTPUT_DIR:-/tmp/rustfs-profiles}
-      - RUSTFS_OBJECT_MAX_CONCURRENT_DISK_READS=${RUSTFS_OBJECT_MAX_CONCURRENT_DISK_READS:-48}
-      - RUSTFS_OBJECT_IO_BUFFER_SIZE=${RUSTFS_OBJECT_IO_BUFFER_SIZE:-262144}
-      - RUSTFS_OBJECT_MEDIUM_CONCURRENCY_THRESHOLD=${RUSTFS_OBJECT_MEDIUM_CONCURRENCY_THRESHOLD:-6}
-      - RUSTFS_OBJECT_HIGH_CONCURRENCY_THRESHOLD=${RUSTFS_OBJECT_HIGH_CONCURRENCY_THRESHOLD:-12}
-      - RUSTFS_OBJECT_IO_RANDOM_READAHEAD_DISABLE_CONCURRENCY=${RUSTFS_OBJECT_IO_RANDOM_READAHEAD_DISABLE_CONCURRENCY:-8}
-      - RUSTFS_OBJECT_DUPLEX_BUFFER_SIZE=${RUSTFS_OBJECT_DUPLEX_BUFFER_SIZE:-8388608}
-      - RUSTFS_ERASURE_ENCODE_MAX_INFLIGHT_BYTES=${RUSTFS_ERASURE_ENCODE_MAX_INFLIGHT_BYTES:-25165824}
-      - RUSTFS_RUNTIME_WORKER_THREADS=${RUSTFS_RUNTIME_WORKER_THREADS:-12}
-      - RUSTFS_RUNTIME_MAX_BLOCKING_THREADS=${RUSTFS_RUNTIME_MAX_BLOCKING_THREADS:-512}
-      - RUSTFS_ALLOCATOR_RECLAIM_ENABLED=${RUSTFS_ALLOCATOR_RECLAIM_ENABLED:-false}
-    extra_hosts:
-      - "host.docker.internal:host-gateway"
-    volumes:
-      - node2_data_0:/data/rustfs0
-      - node2_data_1:/data/rustfs1
-      - node2_data_2:/data/rustfs2
-      - node2_data_3:/data/rustfs3
-    ports:
-      - "9001:9000"
-    networks:
-      - rustfs-cluster-net
-
-  node3:
-    platform: ${RUSTFS_DOCKER_PLATFORM:-linux/amd64}
-    image: ${RUSTFS_IMAGE:-rustfs/rustfs:local-4node}
-    build:
-      context: ../..
-      dockerfile: Dockerfile.source
-    hostname: node3
-    environment:
-      - RUSTFS_VOLUMES=http://node{1...4}:9000/data/rustfs{0...3}
-      - RUSTFS_ADDRESS=:9000
-      - RUSTFS_CONSOLE_ENABLE=true
-      - RUSTFS_ACCESS_KEY=${RUSTFS_ACCESS_KEY:-rustfs-cluster-admin}
-      - RUSTFS_SECRET_KEY=${RUSTFS_SECRET_KEY:-rustfs-cluster-secret}
-      - RUSTFS_OBS_ENDPOINT=${RUSTFS_OBS_ENDPOINT:-http://host.docker.internal:4318}
-      # `info` is enough for startup logs/metrics. Use `debug` if Tempo/Jaeger
-      # should show richer nested spans during request-path verification.
-      - RUSTFS_OBS_LOGGER_LEVEL=${RUSTFS_OBS_LOGGER_LEVEL:-info}
-      - RUSTFS_OBS_PROFILING_ENDPOINT=${RUSTFS_OBS_PROFILING_ENDPOINT:-http://host.docker.internal:4040}
-      - RUSTFS_OBS_PROFILING_EXPORT_ENABLED=${RUSTFS_OBS_PROFILING_EXPORT_ENABLED:-true}
-      - RUSTFS_UNSAFE_BYPASS_DISK_CHECK=${RUSTFS_UNSAFE_BYPASS_DISK_CHECK:-true}
-      - RUSTFS_ENABLE_PROFILING=${RUSTFS_ENABLE_PROFILING:-true}
-      - RUSTFS_PROF_CPU_MODE=${RUSTFS_PROF_CPU_MODE:-continuous}
-      - RUSTFS_PROF_CPU_FREQ=${RUSTFS_PROF_CPU_FREQ:-99}
-      - RUSTFS_PROF_OUTPUT_DIR=${RUSTFS_PROF_OUTPUT_DIR:-/tmp/rustfs-profiles}
-      - RUSTFS_OBJECT_MAX_CONCURRENT_DISK_READS=${RUSTFS_OBJECT_MAX_CONCURRENT_DISK_READS:-48}
-      - RUSTFS_OBJECT_IO_BUFFER_SIZE=${RUSTFS_OBJECT_IO_BUFFER_SIZE:-262144}
-      - RUSTFS_OBJECT_MEDIUM_CONCURRENCY_THRESHOLD=${RUSTFS_OBJECT_MEDIUM_CONCURRENCY_THRESHOLD:-6}
-      - RUSTFS_OBJECT_HIGH_CONCURRENCY_THRESHOLD=${RUSTFS_OBJECT_HIGH_CONCURRENCY_THRESHOLD:-12}
-      - RUSTFS_OBJECT_IO_RANDOM_READAHEAD_DISABLE_CONCURRENCY=${RUSTFS_OBJECT_IO_RANDOM_READAHEAD_DISABLE_CONCURRENCY:-8}
-      - RUSTFS_OBJECT_DUPLEX_BUFFER_SIZE=${RUSTFS_OBJECT_DUPLEX_BUFFER_SIZE:-8388608}
-      - RUSTFS_ERASURE_ENCODE_MAX_INFLIGHT_BYTES=${RUSTFS_ERASURE_ENCODE_MAX_INFLIGHT_BYTES:-25165824}
-      - RUSTFS_RUNTIME_WORKER_THREADS=${RUSTFS_RUNTIME_WORKER_THREADS:-12}
-      - RUSTFS_RUNTIME_MAX_BLOCKING_THREADS=${RUSTFS_RUNTIME_MAX_BLOCKING_THREADS:-512}
-      - RUSTFS_ALLOCATOR_RECLAIM_ENABLED=${RUSTFS_ALLOCATOR_RECLAIM_ENABLED:-false}
-    extra_hosts:
-      - "host.docker.internal:host-gateway"
-    volumes:
-      - node3_data_0:/data/rustfs0
-      - node3_data_1:/data/rustfs1
-      - node3_data_2:/data/rustfs2
-      - node3_data_3:/data/rustfs3
-    ports:
-      - "9002:9000"
-    networks:
-      - rustfs-cluster-net
-
-  node4:
-    platform: ${RUSTFS_DOCKER_PLATFORM:-linux/amd64}
-    image: ${RUSTFS_IMAGE:-rustfs/rustfs:local-4node}
-    build:
-      context: ../..
-      dockerfile: Dockerfile.source
-    hostname: node4
-    environment:
-      - RUSTFS_VOLUMES=http://node{1...4}:9000/data/rustfs{0...3}
-      - RUSTFS_ADDRESS=:9000
-      - RUSTFS_CONSOLE_ENABLE=true
-      - RUSTFS_ACCESS_KEY=${RUSTFS_ACCESS_KEY:-rustfs-cluster-admin}
-      - RUSTFS_SECRET_KEY=${RUSTFS_SECRET_KEY:-rustfs-cluster-secret}
-      - RUSTFS_OBS_ENDPOINT=${RUSTFS_OBS_ENDPOINT:-http://host.docker.internal:4318}
-      # `info` is enough for startup logs/metrics. Use `debug` if Tempo/Jaeger
-      # should show richer nested spans during request-path verification.
-      - RUSTFS_OBS_LOGGER_LEVEL=${RUSTFS_OBS_LOGGER_LEVEL:-info}
-      - RUSTFS_OBS_PROFILING_ENDPOINT=${RUSTFS_OBS_PROFILING_ENDPOINT:-http://host.docker.internal:4040}
-      - RUSTFS_OBS_PROFILING_EXPORT_ENABLED=${RUSTFS_OBS_PROFILING_EXPORT_ENABLED:-true}
-      - RUSTFS_UNSAFE_BYPASS_DISK_CHECK=${RUSTFS_UNSAFE_BYPASS_DISK_CHECK:-true}
-      - RUSTFS_ENABLE_PROFILING=${RUSTFS_ENABLE_PROFILING:-true}
-      - RUSTFS_PROF_CPU_MODE=${RUSTFS_PROF_CPU_MODE:-continuous}
-      - RUSTFS_PROF_CPU_FREQ=${RUSTFS_PROF_CPU_FREQ:-99}
-      - RUSTFS_PROF_OUTPUT_DIR=${RUSTFS_PROF_OUTPUT_DIR:-/tmp/rustfs-profiles}
-      - RUSTFS_OBJECT_MAX_CONCURRENT_DISK_READS=${RUSTFS_OBJECT_MAX_CONCURRENT_DISK_READS:-48}
-      - RUSTFS_OBJECT_IO_BUFFER_SIZE=${RUSTFS_OBJECT_IO_BUFFER_SIZE:-262144}
-      - RUSTFS_OBJECT_MEDIUM_CONCURRENCY_THRESHOLD=${RUSTFS_OBJECT_MEDIUM_CONCURRENCY_THRESHOLD:-6}
-      - RUSTFS_OBJECT_HIGH_CONCURRENCY_THRESHOLD=${RUSTFS_OBJECT_HIGH_CONCURRENCY_THRESHOLD:-12}
-      - RUSTFS_OBJECT_IO_RANDOM_READAHEAD_DISABLE_CONCURRENCY=${RUSTFS_OBJECT_IO_RANDOM_READAHEAD_DISABLE_CONCURRENCY:-8}
-      - RUSTFS_OBJECT_DUPLEX_BUFFER_SIZE=${RUSTFS_OBJECT_DUPLEX_BUFFER_SIZE:-8388608}
-      - RUSTFS_ERASURE_ENCODE_MAX_INFLIGHT_BYTES=${RUSTFS_ERASURE_ENCODE_MAX_INFLIGHT_BYTES:-25165824}
-      - RUSTFS_RUNTIME_WORKER_THREADS=${RUSTFS_RUNTIME_WORKER_THREADS:-12}
-      - RUSTFS_RUNTIME_MAX_BLOCKING_THREADS=${RUSTFS_RUNTIME_MAX_BLOCKING_THREADS:-512}
-      - RUSTFS_ALLOCATOR_RECLAIM_ENABLED=${RUSTFS_ALLOCATOR_RECLAIM_ENABLED:-false}
-    extra_hosts:
-      - "host.docker.internal:host-gateway"
-    volumes:
-      - node4_data_0:/data/rustfs0
-      - node4_data_1:/data/rustfs1
-      - node4_data_2:/data/rustfs2
-      - node4_data_3:/data/rustfs3
-    ports:
-      - "9003:9000"
-    networks:
-      - rustfs-cluster-net
-
-volumes:
-  node1_data_0:
-  node1_data_1:
-  node1_data_2:
-  node1_data_3:
-  node2_data_0:
-  node2_data_1:
-  node2_data_2:
-  node2_data_3:
-  node3_data_0:
-  node3_data_1:
-  node3_data_2:
-  node3_data_3:
-  node4_data_0:
-  node4_data_1:
-  node4_data_2:
-  node4_data_3:
-
-networks:
-  rustfs-cluster-net:
-    driver: bridge

.docker/compose/docker-compose.cluster.local-build.yml

@@ -1,220 +0,0 @@
-# Copyright 2024 RustFS Team
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-
-services:
-  node1:
-    image: ${RUSTFS_IMAGE:-rustfs/rustfs:local-4node}
-    build:
-      context: ../..
-      dockerfile: Dockerfile.source
-    hostname: node1
-    environment:
-      - RUSTFS_VOLUMES=${RUSTFS_VOLUMES:-http://node{1...4}:9000/data/rustfs{0...3}}
-      - RUSTFS_ADDRESS=:9000
-      - RUSTFS_CONSOLE_ENABLE=true
-      - RUSTFS_ACCESS_KEY=${RUSTFS_ACCESS_KEY:-rustfsadmin-local}
-      - RUSTFS_SECRET_KEY=${RUSTFS_SECRET_KEY:-rustfssecret-local}
-      - RUSTFS_OBS_ENDPOINT=${RUSTFS_OBS_ENDPOINT:-http://host.docker.internal:4318}
-      - RUSTFS_OBS_LOGGER_LEVEL=${RUSTFS_OBS_LOGGER_LEVEL:-info}
-      - RUSTFS_OBS_USE_STDOUT=${RUSTFS_OBS_USE_STDOUT:-false}
-      - RUSTFS_OBS_LOG_STDOUT_ENABLED=${RUSTFS_OBS_LOG_STDOUT_ENABLED:-false}
-      - RUSTFS_ISSUE3031_DIAG_ENABLE=${RUSTFS_ISSUE3031_DIAG_ENABLE:-false}
-      - RUSTFS_OBJECT_LOCK_ACQUIRE_TIMEOUT=${RUSTFS_OBJECT_LOCK_ACQUIRE_TIMEOUT:-5}
-      - RUSTFS_LOCK_ACQUIRE_TIMEOUT=${RUSTFS_LOCK_ACQUIRE_TIMEOUT:-5}
-      - RUSTFS_UNSAFE_BYPASS_DISK_CHECK=${RUSTFS_UNSAFE_BYPASS_DISK_CHECK:-true}
-      # Internode gRPC optimization knobs (grpc-optimization P0-P3). Defaults match the binary
-      # defaults, so leaving these unset is a no-op; the A/B driver exports them to toggle a stage.
-      - RUSTFS_INTERNODE_RPC_TCP_NODELAY=${RUSTFS_INTERNODE_RPC_TCP_NODELAY:-true}
-      - RUSTFS_INTERNODE_RPC_HTTP2_STREAM_WINDOW_SIZE=${RUSTFS_INTERNODE_RPC_HTTP2_STREAM_WINDOW_SIZE:-1048576}
-      - RUSTFS_INTERNODE_RPC_HTTP2_CONN_WINDOW_SIZE=${RUSTFS_INTERNODE_RPC_HTTP2_CONN_WINDOW_SIZE:-2097152}
-      - RUSTFS_INTERNODE_RPC_MAX_MESSAGE_SIZE=${RUSTFS_INTERNODE_RPC_MAX_MESSAGE_SIZE:-104857600}
-      - RUSTFS_INTERNODE_CHANNEL_ISOLATION=${RUSTFS_INTERNODE_CHANNEL_ISOLATION:-false}
-      - RUSTFS_INTERNODE_BULK_CHANNELS=${RUSTFS_INTERNODE_BULK_CHANNELS:-2}
-      - RUSTFS_INTERNODE_RPC_MSGPACK_ONLY=${RUSTFS_INTERNODE_RPC_MSGPACK_ONLY:-false}
-      - RUSTFS_INTERNODE_PREWARM=${RUSTFS_INTERNODE_PREWARM:-false}
-      - RUSTFS_INTERNODE_OFFLINE_BYPASS=${RUSTFS_INTERNODE_OFFLINE_BYPASS:-false}
-      - RUSTFS_INTERNODE_OFFLINE_REPROBE_SECS=${RUSTFS_INTERNODE_OFFLINE_REPROBE_SECS:-5}
-      - RUSTFS_INTERNODE_OFFLINE_FAILURE_THRESHOLD=${RUSTFS_INTERNODE_OFFLINE_FAILURE_THRESHOLD:-3}
-      - RUSTFS_INTERNODE_IDEMPOTENT_READ_RETRIES=${RUSTFS_INTERNODE_IDEMPOTENT_READ_RETRIES:-1}
-    extra_hosts:
-      - "host.docker.internal:host-gateway"
-    volumes:
-      - node1_data_0:/data/rustfs0
-      - node1_data_1:/data/rustfs1
-      - node1_data_2:/data/rustfs2
-      - node1_data_3:/data/rustfs3
-    ports:
-      - "9000:9000"
-    networks:
-      - rustfs-cluster-net
-
-  node2:
-    image: ${RUSTFS_IMAGE:-rustfs/rustfs:local-4node}
-    build:
-      context: ../..
-      dockerfile: Dockerfile.source
-    hostname: node2
-    environment:
-      - RUSTFS_VOLUMES=${RUSTFS_VOLUMES:-http://node{1...4}:9000/data/rustfs{0...3}}
-      - RUSTFS_ADDRESS=:9000
-      - RUSTFS_CONSOLE_ENABLE=true
-      - RUSTFS_ACCESS_KEY=${RUSTFS_ACCESS_KEY:-rustfsadmin-local}
-      - RUSTFS_SECRET_KEY=${RUSTFS_SECRET_KEY:-rustfssecret-local}
-      - RUSTFS_OBS_ENDPOINT=${RUSTFS_OBS_ENDPOINT:-http://host.docker.internal:4318}
-      - RUSTFS_OBS_LOGGER_LEVEL=${RUSTFS_OBS_LOGGER_LEVEL:-info}
-      - RUSTFS_OBS_USE_STDOUT=${RUSTFS_OBS_USE_STDOUT:-false}
-      - RUSTFS_OBS_LOG_STDOUT_ENABLED=${RUSTFS_OBS_LOG_STDOUT_ENABLED:-false}
-      - RUSTFS_ISSUE3031_DIAG_ENABLE=${RUSTFS_ISSUE3031_DIAG_ENABLE:-false}
-      - RUSTFS_OBJECT_LOCK_ACQUIRE_TIMEOUT=${RUSTFS_OBJECT_LOCK_ACQUIRE_TIMEOUT:-5}
-      - RUSTFS_LOCK_ACQUIRE_TIMEOUT=${RUSTFS_LOCK_ACQUIRE_TIMEOUT:-5}
-      - RUSTFS_UNSAFE_BYPASS_DISK_CHECK=${RUSTFS_UNSAFE_BYPASS_DISK_CHECK:-true}
-      # Internode gRPC optimization knobs (grpc-optimization P0-P3). Defaults match the binary
-      # defaults, so leaving these unset is a no-op; the A/B driver exports them to toggle a stage.
-      - RUSTFS_INTERNODE_RPC_TCP_NODELAY=${RUSTFS_INTERNODE_RPC_TCP_NODELAY:-true}
-      - RUSTFS_INTERNODE_RPC_HTTP2_STREAM_WINDOW_SIZE=${RUSTFS_INTERNODE_RPC_HTTP2_STREAM_WINDOW_SIZE:-1048576}
-      - RUSTFS_INTERNODE_RPC_HTTP2_CONN_WINDOW_SIZE=${RUSTFS_INTERNODE_RPC_HTTP2_CONN_WINDOW_SIZE:-2097152}
-      - RUSTFS_INTERNODE_RPC_MAX_MESSAGE_SIZE=${RUSTFS_INTERNODE_RPC_MAX_MESSAGE_SIZE:-104857600}
-      - RUSTFS_INTERNODE_CHANNEL_ISOLATION=${RUSTFS_INTERNODE_CHANNEL_ISOLATION:-false}
-      - RUSTFS_INTERNODE_BULK_CHANNELS=${RUSTFS_INTERNODE_BULK_CHANNELS:-2}
-      - RUSTFS_INTERNODE_RPC_MSGPACK_ONLY=${RUSTFS_INTERNODE_RPC_MSGPACK_ONLY:-false}
-      - RUSTFS_INTERNODE_PREWARM=${RUSTFS_INTERNODE_PREWARM:-false}
-      - RUSTFS_INTERNODE_OFFLINE_BYPASS=${RUSTFS_INTERNODE_OFFLINE_BYPASS:-false}
-      - RUSTFS_INTERNODE_OFFLINE_REPROBE_SECS=${RUSTFS_INTERNODE_OFFLINE_REPROBE_SECS:-5}
-      - RUSTFS_INTERNODE_OFFLINE_FAILURE_THRESHOLD=${RUSTFS_INTERNODE_OFFLINE_FAILURE_THRESHOLD:-3}
-      - RUSTFS_INTERNODE_IDEMPOTENT_READ_RETRIES=${RUSTFS_INTERNODE_IDEMPOTENT_READ_RETRIES:-1}
-    extra_hosts:
-      - "host.docker.internal:host-gateway"
-    volumes:
-      - node2_data_0:/data/rustfs0
-      - node2_data_1:/data/rustfs1
-      - node2_data_2:/data/rustfs2
-      - node2_data_3:/data/rustfs3
-    ports:
-      - "9001:9000"
-    networks:
-      - rustfs-cluster-net
-
-  node3:
-    image: ${RUSTFS_IMAGE:-rustfs/rustfs:local-4node}
-    build:
-      context: ../..
-      dockerfile: Dockerfile.source
-    hostname: node3
-    environment:
-      - RUSTFS_VOLUMES=${RUSTFS_VOLUMES:-http://node{1...4}:9000/data/rustfs{0...3}}
-      - RUSTFS_ADDRESS=:9000
-      - RUSTFS_CONSOLE_ENABLE=true
-      - RUSTFS_ACCESS_KEY=${RUSTFS_ACCESS_KEY:-rustfsadmin-local}
-      - RUSTFS_SECRET_KEY=${RUSTFS_SECRET_KEY:-rustfssecret-local}
-      - RUSTFS_OBS_ENDPOINT=${RUSTFS_OBS_ENDPOINT:-http://host.docker.internal:4318}
-      - RUSTFS_OBS_LOGGER_LEVEL=${RUSTFS_OBS_LOGGER_LEVEL:-info}
-      - RUSTFS_OBS_USE_STDOUT=${RUSTFS_OBS_USE_STDOUT:-false}
-      - RUSTFS_OBS_LOG_STDOUT_ENABLED=${RUSTFS_OBS_LOG_STDOUT_ENABLED:-false}
-      - RUSTFS_ISSUE3031_DIAG_ENABLE=${RUSTFS_ISSUE3031_DIAG_ENABLE:-false}
-      - RUSTFS_OBJECT_LOCK_ACQUIRE_TIMEOUT=${RUSTFS_OBJECT_LOCK_ACQUIRE_TIMEOUT:-5}
-      - RUSTFS_LOCK_ACQUIRE_TIMEOUT=${RUSTFS_LOCK_ACQUIRE_TIMEOUT:-5}
-      - RUSTFS_UNSAFE_BYPASS_DISK_CHECK=${RUSTFS_UNSAFE_BYPASS_DISK_CHECK:-true}
-      # Internode gRPC optimization knobs (grpc-optimization P0-P3). Defaults match the binary
-      # defaults, so leaving these unset is a no-op; the A/B driver exports them to toggle a stage.
-      - RUSTFS_INTERNODE_RPC_TCP_NODELAY=${RUSTFS_INTERNODE_RPC_TCP_NODELAY:-true}
-      - RUSTFS_INTERNODE_RPC_HTTP2_STREAM_WINDOW_SIZE=${RUSTFS_INTERNODE_RPC_HTTP2_STREAM_WINDOW_SIZE:-1048576}
-      - RUSTFS_INTERNODE_RPC_HTTP2_CONN_WINDOW_SIZE=${RUSTFS_INTERNODE_RPC_HTTP2_CONN_WINDOW_SIZE:-2097152}
-      - RUSTFS_INTERNODE_RPC_MAX_MESSAGE_SIZE=${RUSTFS_INTERNODE_RPC_MAX_MESSAGE_SIZE:-104857600}
-      - RUSTFS_INTERNODE_CHANNEL_ISOLATION=${RUSTFS_INTERNODE_CHANNEL_ISOLATION:-false}
-      - RUSTFS_INTERNODE_BULK_CHANNELS=${RUSTFS_INTERNODE_BULK_CHANNELS:-2}
-      - RUSTFS_INTERNODE_RPC_MSGPACK_ONLY=${RUSTFS_INTERNODE_RPC_MSGPACK_ONLY:-false}
-      - RUSTFS_INTERNODE_PREWARM=${RUSTFS_INTERNODE_PREWARM:-false}
-      - RUSTFS_INTERNODE_OFFLINE_BYPASS=${RUSTFS_INTERNODE_OFFLINE_BYPASS:-false}
-      - RUSTFS_INTERNODE_OFFLINE_REPROBE_SECS=${RUSTFS_INTERNODE_OFFLINE_REPROBE_SECS:-5}
-      - RUSTFS_INTERNODE_OFFLINE_FAILURE_THRESHOLD=${RUSTFS_INTERNODE_OFFLINE_FAILURE_THRESHOLD:-3}
-      - RUSTFS_INTERNODE_IDEMPOTENT_READ_RETRIES=${RUSTFS_INTERNODE_IDEMPOTENT_READ_RETRIES:-1}
-    extra_hosts:
-      - "host.docker.internal:host-gateway"
-    volumes:
-      - node3_data_0:/data/rustfs0
-      - node3_data_1:/data/rustfs1
-      - node3_data_2:/data/rustfs2
-      - node3_data_3:/data/rustfs3
-    ports:
-      - "9002:9000"
-    networks:
-      - rustfs-cluster-net
-
-  node4:
-    image: ${RUSTFS_IMAGE:-rustfs/rustfs:local-4node}
-    build:
-      context: ../..
-      dockerfile: Dockerfile.source
-    hostname: node4
-    environment:
-      - RUSTFS_VOLUMES=${RUSTFS_VOLUMES:-http://node{1...4}:9000/data/rustfs{0...3}}
-      - RUSTFS_ADDRESS=:9000
-      - RUSTFS_CONSOLE_ENABLE=true
-      - RUSTFS_ACCESS_KEY=${RUSTFS_ACCESS_KEY:-rustfsadmin-local}
-      - RUSTFS_SECRET_KEY=${RUSTFS_SECRET_KEY:-rustfssecret-local}
-      - RUSTFS_OBS_ENDPOINT=${RUSTFS_OBS_ENDPOINT:-http://host.docker.internal:4318}
-      - RUSTFS_OBS_LOGGER_LEVEL=${RUSTFS_OBS_LOGGER_LEVEL:-info}
-      - RUSTFS_OBS_USE_STDOUT=${RUSTFS_OBS_USE_STDOUT:-false}
-      - RUSTFS_OBS_LOG_STDOUT_ENABLED=${RUSTFS_OBS_LOG_STDOUT_ENABLED:-false}
-      - RUSTFS_ISSUE3031_DIAG_ENABLE=${RUSTFS_ISSUE3031_DIAG_ENABLE:-false}
-      - RUSTFS_OBJECT_LOCK_ACQUIRE_TIMEOUT=${RUSTFS_OBJECT_LOCK_ACQUIRE_TIMEOUT:-5}
-      - RUSTFS_LOCK_ACQUIRE_TIMEOUT=${RUSTFS_LOCK_ACQUIRE_TIMEOUT:-5}
-      - RUSTFS_UNSAFE_BYPASS_DISK_CHECK=${RUSTFS_UNSAFE_BYPASS_DISK_CHECK:-true}
-      # Internode gRPC optimization knobs (grpc-optimization P0-P3). Defaults match the binary
-      # defaults, so leaving these unset is a no-op; the A/B driver exports them to toggle a stage.
-      - RUSTFS_INTERNODE_RPC_TCP_NODELAY=${RUSTFS_INTERNODE_RPC_TCP_NODELAY:-true}
-      - RUSTFS_INTERNODE_RPC_HTTP2_STREAM_WINDOW_SIZE=${RUSTFS_INTERNODE_RPC_HTTP2_STREAM_WINDOW_SIZE:-1048576}
-      - RUSTFS_INTERNODE_RPC_HTTP2_CONN_WINDOW_SIZE=${RUSTFS_INTERNODE_RPC_HTTP2_CONN_WINDOW_SIZE:-2097152}
-      - RUSTFS_INTERNODE_RPC_MAX_MESSAGE_SIZE=${RUSTFS_INTERNODE_RPC_MAX_MESSAGE_SIZE:-104857600}
-      - RUSTFS_INTERNODE_CHANNEL_ISOLATION=${RUSTFS_INTERNODE_CHANNEL_ISOLATION:-false}
-      - RUSTFS_INTERNODE_BULK_CHANNELS=${RUSTFS_INTERNODE_BULK_CHANNELS:-2}
-      - RUSTFS_INTERNODE_RPC_MSGPACK_ONLY=${RUSTFS_INTERNODE_RPC_MSGPACK_ONLY:-false}
-      - RUSTFS_INTERNODE_PREWARM=${RUSTFS_INTERNODE_PREWARM:-false}
-      - RUSTFS_INTERNODE_OFFLINE_BYPASS=${RUSTFS_INTERNODE_OFFLINE_BYPASS:-false}
-      - RUSTFS_INTERNODE_OFFLINE_REPROBE_SECS=${RUSTFS_INTERNODE_OFFLINE_REPROBE_SECS:-5}
-      - RUSTFS_INTERNODE_OFFLINE_FAILURE_THRESHOLD=${RUSTFS_INTERNODE_OFFLINE_FAILURE_THRESHOLD:-3}
-      - RUSTFS_INTERNODE_IDEMPOTENT_READ_RETRIES=${RUSTFS_INTERNODE_IDEMPOTENT_READ_RETRIES:-1}
-    extra_hosts:
-      - "host.docker.internal:host-gateway"
-    volumes:
-      - node4_data_0:/data/rustfs0
-      - node4_data_1:/data/rustfs1
-      - node4_data_2:/data/rustfs2
-      - node4_data_3:/data/rustfs3
-    ports:
-      - "9003:9000"
-    networks:
-      - rustfs-cluster-net
-
-volumes:
-  node1_data_0:
-  node1_data_1:
-  node1_data_2:
-  node1_data_3:
-  node2_data_0:
-  node2_data_1:
-  node2_data_2:
-  node2_data_3:
-  node3_data_0:
-  node3_data_1:
-  node3_data_2:
-  node3_data_3:
-  node4_data_0:
-  node4_data_1:
-  node4_data_2:
-  node4_data_3:
-
-networks:
-  rustfs-cluster-net:
-    driver: bridge

.docker/compose/docker-compose.cluster.perf-round1-linux-32c64g-latency-stable.override.yml

@@ -1,56 +0,0 @@
-services:
-  node1:
-    environment:
-      - RUSTFS_OBJECT_MAX_CONCURRENT_DISK_READS=56
-      - RUSTFS_OBJECT_IO_BUFFER_SIZE=131072
-      - RUSTFS_OBJECT_MEDIUM_CONCURRENCY_THRESHOLD=10
-      - RUSTFS_OBJECT_HIGH_CONCURRENCY_THRESHOLD=20
-      - RUSTFS_OBJECT_IO_RANDOM_READAHEAD_DISABLE_CONCURRENCY=10
-      - RUSTFS_OBJECT_DUPLEX_BUFFER_SIZE=8388608
-      - RUSTFS_ERASURE_ENCODE_MAX_INFLIGHT_BYTES=25165824
-      - RUSTFS_RUNTIME_WORKER_THREADS=16
-      - RUSTFS_RUNTIME_MAX_BLOCKING_THREADS=768
-      - RUSTFS_CAPACITY_SCHEDULED_INTERVAL=420
-      - RUSTFS_CAPACITY_WRITE_FREQUENCY_THRESHOLD=50
-
-  node2:
-    environment:
-      - RUSTFS_OBJECT_MAX_CONCURRENT_DISK_READS=56
-      - RUSTFS_OBJECT_IO_BUFFER_SIZE=131072
-      - RUSTFS_OBJECT_MEDIUM_CONCURRENCY_THRESHOLD=10
-      - RUSTFS_OBJECT_HIGH_CONCURRENCY_THRESHOLD=20
-      - RUSTFS_OBJECT_IO_RANDOM_READAHEAD_DISABLE_CONCURRENCY=10
-      - RUSTFS_OBJECT_DUPLEX_BUFFER_SIZE=8388608
-      - RUSTFS_ERASURE_ENCODE_MAX_INFLIGHT_BYTES=25165824
-      - RUSTFS_RUNTIME_WORKER_THREADS=16
-      - RUSTFS_RUNTIME_MAX_BLOCKING_THREADS=768
-      - RUSTFS_CAPACITY_SCHEDULED_INTERVAL=420
-      - RUSTFS_CAPACITY_WRITE_FREQUENCY_THRESHOLD=50
-
-  node3:
-    environment:
-      - RUSTFS_OBJECT_MAX_CONCURRENT_DISK_READS=56
-      - RUSTFS_OBJECT_IO_BUFFER_SIZE=131072
-      - RUSTFS_OBJECT_MEDIUM_CONCURRENCY_THRESHOLD=10
-      - RUSTFS_OBJECT_HIGH_CONCURRENCY_THRESHOLD=20
-      - RUSTFS_OBJECT_IO_RANDOM_READAHEAD_DISABLE_CONCURRENCY=10
-      - RUSTFS_OBJECT_DUPLEX_BUFFER_SIZE=8388608
-      - RUSTFS_ERASURE_ENCODE_MAX_INFLIGHT_BYTES=25165824
-      - RUSTFS_RUNTIME_WORKER_THREADS=16
-      - RUSTFS_RUNTIME_MAX_BLOCKING_THREADS=768
-      - RUSTFS_CAPACITY_SCHEDULED_INTERVAL=420
-      - RUSTFS_CAPACITY_WRITE_FREQUENCY_THRESHOLD=50
-
-  node4:
-    environment:
-      - RUSTFS_OBJECT_MAX_CONCURRENT_DISK_READS=56
-      - RUSTFS_OBJECT_IO_BUFFER_SIZE=131072
-      - RUSTFS_OBJECT_MEDIUM_CONCURRENCY_THRESHOLD=10
-      - RUSTFS_OBJECT_HIGH_CONCURRENCY_THRESHOLD=20
-      - RUSTFS_OBJECT_IO_RANDOM_READAHEAD_DISABLE_CONCURRENCY=10
-      - RUSTFS_OBJECT_DUPLEX_BUFFER_SIZE=8388608
-      - RUSTFS_ERASURE_ENCODE_MAX_INFLIGHT_BYTES=25165824
-      - RUSTFS_RUNTIME_WORKER_THREADS=16
-      - RUSTFS_RUNTIME_MAX_BLOCKING_THREADS=768
-      - RUSTFS_CAPACITY_SCHEDULED_INTERVAL=420
-      - RUSTFS_CAPACITY_WRITE_FREQUENCY_THRESHOLD=50

.docker/compose/docker-compose.cluster.perf-round1-linux-32c64g-throughput-max.override.yml

@@ -1,56 +0,0 @@
-services:
-  node1:
-    environment:
-      - RUSTFS_OBJECT_MAX_CONCURRENT_DISK_READS=96
-      - RUSTFS_OBJECT_IO_BUFFER_SIZE=524288
-      - RUSTFS_OBJECT_MEDIUM_CONCURRENCY_THRESHOLD=16
-      - RUSTFS_OBJECT_HIGH_CONCURRENCY_THRESHOLD=32
-      - RUSTFS_OBJECT_IO_RANDOM_READAHEAD_DISABLE_CONCURRENCY=24
-      - RUSTFS_OBJECT_DUPLEX_BUFFER_SIZE=33554432
-      - RUSTFS_ERASURE_ENCODE_MAX_INFLIGHT_BYTES=50331648
-      - RUSTFS_RUNTIME_WORKER_THREADS=24
-      - RUSTFS_RUNTIME_MAX_BLOCKING_THREADS=1536
-      - RUSTFS_CAPACITY_SCHEDULED_INTERVAL=600
-      - RUSTFS_CAPACITY_WRITE_FREQUENCY_THRESHOLD=80
-
-  node2:
-    environment:
-      - RUSTFS_OBJECT_MAX_CONCURRENT_DISK_READS=96
-      - RUSTFS_OBJECT_IO_BUFFER_SIZE=524288
-      - RUSTFS_OBJECT_MEDIUM_CONCURRENCY_THRESHOLD=16
-      - RUSTFS_OBJECT_HIGH_CONCURRENCY_THRESHOLD=32
-      - RUSTFS_OBJECT_IO_RANDOM_READAHEAD_DISABLE_CONCURRENCY=24
-      - RUSTFS_OBJECT_DUPLEX_BUFFER_SIZE=33554432
-      - RUSTFS_ERASURE_ENCODE_MAX_INFLIGHT_BYTES=50331648
-      - RUSTFS_RUNTIME_WORKER_THREADS=24
-      - RUSTFS_RUNTIME_MAX_BLOCKING_THREADS=1536
-      - RUSTFS_CAPACITY_SCHEDULED_INTERVAL=600
-      - RUSTFS_CAPACITY_WRITE_FREQUENCY_THRESHOLD=80
-
-  node3:
-    environment:
-      - RUSTFS_OBJECT_MAX_CONCURRENT_DISK_READS=96
-      - RUSTFS_OBJECT_IO_BUFFER_SIZE=524288
-      - RUSTFS_OBJECT_MEDIUM_CONCURRENCY_THRESHOLD=16
-      - RUSTFS_OBJECT_HIGH_CONCURRENCY_THRESHOLD=32
-      - RUSTFS_OBJECT_IO_RANDOM_READAHEAD_DISABLE_CONCURRENCY=24
-      - RUSTFS_OBJECT_DUPLEX_BUFFER_SIZE=33554432
-      - RUSTFS_ERASURE_ENCODE_MAX_INFLIGHT_BYTES=50331648
-      - RUSTFS_RUNTIME_WORKER_THREADS=24
-      - RUSTFS_RUNTIME_MAX_BLOCKING_THREADS=1536
-      - RUSTFS_CAPACITY_SCHEDULED_INTERVAL=600
-      - RUSTFS_CAPACITY_WRITE_FREQUENCY_THRESHOLD=80
-
-  node4:
-    environment:
-      - RUSTFS_OBJECT_MAX_CONCURRENT_DISK_READS=96
-      - RUSTFS_OBJECT_IO_BUFFER_SIZE=524288
-      - RUSTFS_OBJECT_MEDIUM_CONCURRENCY_THRESHOLD=16
-      - RUSTFS_OBJECT_HIGH_CONCURRENCY_THRESHOLD=32
-      - RUSTFS_OBJECT_IO_RANDOM_READAHEAD_DISABLE_CONCURRENCY=24
-      - RUSTFS_OBJECT_DUPLEX_BUFFER_SIZE=33554432
-      - RUSTFS_ERASURE_ENCODE_MAX_INFLIGHT_BYTES=50331648
-      - RUSTFS_RUNTIME_WORKER_THREADS=24
-      - RUSTFS_RUNTIME_MAX_BLOCKING_THREADS=1536
-      - RUSTFS_CAPACITY_SCHEDULED_INTERVAL=600
-      - RUSTFS_CAPACITY_WRITE_FREQUENCY_THRESHOLD=80

.docker/compose/docker-compose.cluster.perf-round1-linux-32c64g.override.yml

@@ -1,56 +0,0 @@
-services:
-  node1:
-    environment:
-      - RUSTFS_OBJECT_MAX_CONCURRENT_DISK_READS=64
-      - RUSTFS_OBJECT_IO_BUFFER_SIZE=262144
-      - RUSTFS_OBJECT_MEDIUM_CONCURRENCY_THRESHOLD=12
-      - RUSTFS_OBJECT_HIGH_CONCURRENCY_THRESHOLD=24
-      - RUSTFS_OBJECT_IO_RANDOM_READAHEAD_DISABLE_CONCURRENCY=16
-      - RUSTFS_OBJECT_DUPLEX_BUFFER_SIZE=16777216
-      - RUSTFS_ERASURE_ENCODE_MAX_INFLIGHT_BYTES=33554432
-      - RUSTFS_RUNTIME_WORKER_THREADS=20
-      - RUSTFS_RUNTIME_MAX_BLOCKING_THREADS=1024
-      - RUSTFS_CAPACITY_SCHEDULED_INTERVAL=300
-      - RUSTFS_CAPACITY_WRITE_FREQUENCY_THRESHOLD=60
-
-  node2:
-    environment:
-      - RUSTFS_OBJECT_MAX_CONCURRENT_DISK_READS=64
-      - RUSTFS_OBJECT_IO_BUFFER_SIZE=262144
-      - RUSTFS_OBJECT_MEDIUM_CONCURRENCY_THRESHOLD=12
-      - RUSTFS_OBJECT_HIGH_CONCURRENCY_THRESHOLD=24
-      - RUSTFS_OBJECT_IO_RANDOM_READAHEAD_DISABLE_CONCURRENCY=16
-      - RUSTFS_OBJECT_DUPLEX_BUFFER_SIZE=16777216
-      - RUSTFS_ERASURE_ENCODE_MAX_INFLIGHT_BYTES=33554432
-      - RUSTFS_RUNTIME_WORKER_THREADS=20
-      - RUSTFS_RUNTIME_MAX_BLOCKING_THREADS=1024
-      - RUSTFS_CAPACITY_SCHEDULED_INTERVAL=300
-      - RUSTFS_CAPACITY_WRITE_FREQUENCY_THRESHOLD=60
-
-  node3:
-    environment:
-      - RUSTFS_OBJECT_MAX_CONCURRENT_DISK_READS=64
-      - RUSTFS_OBJECT_IO_BUFFER_SIZE=262144
-      - RUSTFS_OBJECT_MEDIUM_CONCURRENCY_THRESHOLD=12
-      - RUSTFS_OBJECT_HIGH_CONCURRENCY_THRESHOLD=24
-      - RUSTFS_OBJECT_IO_RANDOM_READAHEAD_DISABLE_CONCURRENCY=16
-      - RUSTFS_OBJECT_DUPLEX_BUFFER_SIZE=16777216
-      - RUSTFS_ERASURE_ENCODE_MAX_INFLIGHT_BYTES=33554432
-      - RUSTFS_RUNTIME_WORKER_THREADS=20
-      - RUSTFS_RUNTIME_MAX_BLOCKING_THREADS=1024
-      - RUSTFS_CAPACITY_SCHEDULED_INTERVAL=300
-      - RUSTFS_CAPACITY_WRITE_FREQUENCY_THRESHOLD=60
-
-  node4:
-    environment:
-      - RUSTFS_OBJECT_MAX_CONCURRENT_DISK_READS=64
-      - RUSTFS_OBJECT_IO_BUFFER_SIZE=262144
-      - RUSTFS_OBJECT_MEDIUM_CONCURRENCY_THRESHOLD=12
-      - RUSTFS_OBJECT_HIGH_CONCURRENCY_THRESHOLD=24
-      - RUSTFS_OBJECT_IO_RANDOM_READAHEAD_DISABLE_CONCURRENCY=16
-      - RUSTFS_OBJECT_DUPLEX_BUFFER_SIZE=16777216
-      - RUSTFS_ERASURE_ENCODE_MAX_INFLIGHT_BYTES=33554432
-      - RUSTFS_RUNTIME_WORKER_THREADS=20
-      - RUSTFS_RUNTIME_MAX_BLOCKING_THREADS=1024
-      - RUSTFS_CAPACITY_SCHEDULED_INTERVAL=300
-      - RUSTFS_CAPACITY_WRITE_FREQUENCY_THRESHOLD=60

.docker/compose/docker-compose.cluster.perf-round1-linux.override.yml

@@ -1,56 +0,0 @@
-services:
-  node1:
-    environment:
-      - RUSTFS_OBJECT_MAX_CONCURRENT_DISK_READS=48
-      - RUSTFS_OBJECT_IO_BUFFER_SIZE=262144
-      - RUSTFS_OBJECT_MEDIUM_CONCURRENCY_THRESHOLD=8
-      - RUSTFS_OBJECT_HIGH_CONCURRENCY_THRESHOLD=16
-      - RUSTFS_OBJECT_IO_RANDOM_READAHEAD_DISABLE_CONCURRENCY=12
-      - RUSTFS_OBJECT_DUPLEX_BUFFER_SIZE=8388608
-      - RUSTFS_ERASURE_ENCODE_MAX_INFLIGHT_BYTES=25165824
-      - RUSTFS_RUNTIME_WORKER_THREADS=12
-      - RUSTFS_RUNTIME_MAX_BLOCKING_THREADS=512
-      - RUSTFS_CAPACITY_SCHEDULED_INTERVAL=300
-      - RUSTFS_CAPACITY_WRITE_FREQUENCY_THRESHOLD=40
-
-  node2:
-    environment:
-      - RUSTFS_OBJECT_MAX_CONCURRENT_DISK_READS=48
-      - RUSTFS_OBJECT_IO_BUFFER_SIZE=262144
-      - RUSTFS_OBJECT_MEDIUM_CONCURRENCY_THRESHOLD=8
-      - RUSTFS_OBJECT_HIGH_CONCURRENCY_THRESHOLD=16
-      - RUSTFS_OBJECT_IO_RANDOM_READAHEAD_DISABLE_CONCURRENCY=12
-      - RUSTFS_OBJECT_DUPLEX_BUFFER_SIZE=8388608
-      - RUSTFS_ERASURE_ENCODE_MAX_INFLIGHT_BYTES=25165824
-      - RUSTFS_RUNTIME_WORKER_THREADS=12
-      - RUSTFS_RUNTIME_MAX_BLOCKING_THREADS=512
-      - RUSTFS_CAPACITY_SCHEDULED_INTERVAL=300
-      - RUSTFS_CAPACITY_WRITE_FREQUENCY_THRESHOLD=40
-
-  node3:
-    environment:
-      - RUSTFS_OBJECT_MAX_CONCURRENT_DISK_READS=48
-      - RUSTFS_OBJECT_IO_BUFFER_SIZE=262144
-      - RUSTFS_OBJECT_MEDIUM_CONCURRENCY_THRESHOLD=8
-      - RUSTFS_OBJECT_HIGH_CONCURRENCY_THRESHOLD=16
-      - RUSTFS_OBJECT_IO_RANDOM_READAHEAD_DISABLE_CONCURRENCY=12
-      - RUSTFS_OBJECT_DUPLEX_BUFFER_SIZE=8388608
-      - RUSTFS_ERASURE_ENCODE_MAX_INFLIGHT_BYTES=25165824
-      - RUSTFS_RUNTIME_WORKER_THREADS=12
-      - RUSTFS_RUNTIME_MAX_BLOCKING_THREADS=512
-      - RUSTFS_CAPACITY_SCHEDULED_INTERVAL=300
-      - RUSTFS_CAPACITY_WRITE_FREQUENCY_THRESHOLD=40
-
-  node4:
-    environment:
-      - RUSTFS_OBJECT_MAX_CONCURRENT_DISK_READS=48
-      - RUSTFS_OBJECT_IO_BUFFER_SIZE=262144
-      - RUSTFS_OBJECT_MEDIUM_CONCURRENCY_THRESHOLD=8
-      - RUSTFS_OBJECT_HIGH_CONCURRENCY_THRESHOLD=16
-      - RUSTFS_OBJECT_IO_RANDOM_READAHEAD_DISABLE_CONCURRENCY=12
-      - RUSTFS_OBJECT_DUPLEX_BUFFER_SIZE=8388608
-      - RUSTFS_ERASURE_ENCODE_MAX_INFLIGHT_BYTES=25165824
-      - RUSTFS_RUNTIME_WORKER_THREADS=12
-      - RUSTFS_RUNTIME_MAX_BLOCKING_THREADS=512
-      - RUSTFS_CAPACITY_SCHEDULED_INTERVAL=300
-      - RUSTFS_CAPACITY_WRITE_FREQUENCY_THRESHOLD=40

.docker/compose/docker-compose.cluster.perf-round1.override.yml

@@ -1,56 +0,0 @@
-services:
-  node1:
-    environment:
-      - RUSTFS_OBJECT_MAX_CONCURRENT_DISK_READS=32
-      - RUSTFS_OBJECT_IO_BUFFER_SIZE=262144
-      - RUSTFS_OBJECT_MEDIUM_CONCURRENCY_THRESHOLD=6
-      - RUSTFS_OBJECT_HIGH_CONCURRENCY_THRESHOLD=12
-      - RUSTFS_OBJECT_IO_RANDOM_READAHEAD_DISABLE_CONCURRENCY=8
-      - RUSTFS_OBJECT_DUPLEX_BUFFER_SIZE=8388608
-      - RUSTFS_ERASURE_ENCODE_MAX_INFLIGHT_BYTES=16777216
-      - RUSTFS_RUNTIME_WORKER_THREADS=6
-      - RUSTFS_RUNTIME_MAX_BLOCKING_THREADS=256
-      - RUSTFS_CAPACITY_SCHEDULED_INTERVAL=300
-      - RUSTFS_CAPACITY_WRITE_FREQUENCY_THRESHOLD=30
-
-  node2:
-    environment:
-      - RUSTFS_OBJECT_MAX_CONCURRENT_DISK_READS=32
-      - RUSTFS_OBJECT_IO_BUFFER_SIZE=262144
-      - RUSTFS_OBJECT_MEDIUM_CONCURRENCY_THRESHOLD=6
-      - RUSTFS_OBJECT_HIGH_CONCURRENCY_THRESHOLD=12
-      - RUSTFS_OBJECT_IO_RANDOM_READAHEAD_DISABLE_CONCURRENCY=8
-      - RUSTFS_OBJECT_DUPLEX_BUFFER_SIZE=8388608
-      - RUSTFS_ERASURE_ENCODE_MAX_INFLIGHT_BYTES=16777216
-      - RUSTFS_RUNTIME_WORKER_THREADS=6
-      - RUSTFS_RUNTIME_MAX_BLOCKING_THREADS=256
-      - RUSTFS_CAPACITY_SCHEDULED_INTERVAL=300
-      - RUSTFS_CAPACITY_WRITE_FREQUENCY_THRESHOLD=30
-
-  node3:
-    environment:
-      - RUSTFS_OBJECT_MAX_CONCURRENT_DISK_READS=32
-      - RUSTFS_OBJECT_IO_BUFFER_SIZE=262144
-      - RUSTFS_OBJECT_MEDIUM_CONCURRENCY_THRESHOLD=6
-      - RUSTFS_OBJECT_HIGH_CONCURRENCY_THRESHOLD=12
-      - RUSTFS_OBJECT_IO_RANDOM_READAHEAD_DISABLE_CONCURRENCY=8
-      - RUSTFS_OBJECT_DUPLEX_BUFFER_SIZE=8388608
-      - RUSTFS_ERASURE_ENCODE_MAX_INFLIGHT_BYTES=16777216
-      - RUSTFS_RUNTIME_WORKER_THREADS=6
-      - RUSTFS_RUNTIME_MAX_BLOCKING_THREADS=256
-      - RUSTFS_CAPACITY_SCHEDULED_INTERVAL=300
-      - RUSTFS_CAPACITY_WRITE_FREQUENCY_THRESHOLD=30
-
-  node4:
-    environment:
-      - RUSTFS_OBJECT_MAX_CONCURRENT_DISK_READS=32
-      - RUSTFS_OBJECT_IO_BUFFER_SIZE=262144
-      - RUSTFS_OBJECT_MEDIUM_CONCURRENCY_THRESHOLD=6
-      - RUSTFS_OBJECT_HIGH_CONCURRENCY_THRESHOLD=12
-      - RUSTFS_OBJECT_IO_RANDOM_READAHEAD_DISABLE_CONCURRENCY=8
-      - RUSTFS_OBJECT_DUPLEX_BUFFER_SIZE=8388608
-      - RUSTFS_ERASURE_ENCODE_MAX_INFLIGHT_BYTES=16777216
-      - RUSTFS_RUNTIME_WORKER_THREADS=6
-      - RUSTFS_RUNTIME_MAX_BLOCKING_THREADS=256
-      - RUSTFS_CAPACITY_SCHEDULED_INTERVAL=300
-      - RUSTFS_CAPACITY_WRITE_FREQUENCY_THRESHOLD=30

.docker/compose/docker-compose.cluster.yaml

@@ -21,8 +21,8 @@ services:
       - RUSTFS_VOLUMES=http://node{0...3}:9000/data/rustfs{0...3}
       - RUSTFS_ADDRESS=0.0.0.0:9000
       - RUSTFS_CONSOLE_ENABLE=true
-      - RUSTFS_ACCESS_KEY=${RUSTFS_ACCESS_KEY:-rustfsadmin-local}
-      - RUSTFS_SECRET_KEY=${RUSTFS_SECRET_KEY:-rustfssecret-local}
+      - RUSTFS_ACCESS_KEY=rustfsadmin
+      - RUSTFS_SECRET_KEY=rustfsadmin
     platform: linux/amd64
     ports:
       - "9000:9000" # Map port 9001 of the host to port 9000 of the container
@@ -38,8 +38,8 @@ services:
       - RUSTFS_VOLUMES=http://node{0...3}:9000/data/rustfs{0...3}
       - RUSTFS_ADDRESS=0.0.0.0:9000
       - RUSTFS_CONSOLE_ENABLE=true
-      - RUSTFS_ACCESS_KEY=${RUSTFS_ACCESS_KEY:-rustfsadmin-local}
-      - RUSTFS_SECRET_KEY=${RUSTFS_SECRET_KEY:-rustfssecret-local}
+      - RUSTFS_ACCESS_KEY=rustfsadmin
+      - RUSTFS_SECRET_KEY=rustfsadmin
     platform: linux/amd64
     ports:
       - "9001:9000" # Map port 9002 of the host to port 9000 of the container
@@ -55,8 +55,8 @@ services:
       - RUSTFS_VOLUMES=http://node{0...3}:9000/data/rustfs{0...3}
       - RUSTFS_ADDRESS=0.0.0.0:9000
       - RUSTFS_CONSOLE_ENABLE=true
-      - RUSTFS_ACCESS_KEY=${RUSTFS_ACCESS_KEY:-rustfsadmin-local}
-      - RUSTFS_SECRET_KEY=${RUSTFS_SECRET_KEY:-rustfssecret-local}
+      - RUSTFS_ACCESS_KEY=rustfsadmin
+      - RUSTFS_SECRET_KEY=rustfsadmin
     platform: linux/amd64
     ports:
       - "9002:9000" # Map port 9003 of the host to port 9000 of the container
@@ -72,8 +72,8 @@ services:
       - RUSTFS_VOLUMES=http://node{0...3}:9000/data/rustfs{0...3}
       - RUSTFS_ADDRESS=0.0.0.0:9000
       - RUSTFS_CONSOLE_ENABLE=true
-      - RUSTFS_ACCESS_KEY=${RUSTFS_ACCESS_KEY:-rustfsadmin-local}
-      - RUSTFS_SECRET_KEY=${RUSTFS_SECRET_KEY:-rustfssecret-local}
+      - RUSTFS_ACCESS_KEY=rustfsadmin
+      - RUSTFS_SECRET_KEY=rustfsadmin
     platform: linux/amd64
     ports:
       - "9003:9000" # Map port 9004 of the host to port 9000 of the container

.docker/compose/docker-compose.observability.yaml

@@ -13,183 +13,62 @@
 # limitations under the License.
 
 services:
-  # --- Observability Stack ---
-
-  tempo-init:
-    image: busybox:latest
-    command: [ "sh", "-c", "chown -R 10001:10001 /var/tempo" ]
-    volumes:
-      - tempo-data:/var/tempo
-    user: root
-    networks:
-      - rustfs-network
-    restart: "no"
-
-  tempo:
-    image: grafana/tempo:2.10.5
-    user: "10001"
-    command: [ "-config.file=/etc/tempo.yaml" ]
-    volumes:
-      - ../../.docker/observability/tempo.yaml:/etc/tempo.yaml:ro
-      - tempo-data:/var/tempo
-    ports:
-      - "3200:3200" # tempo
-      - "4317"      # otlp grpc
-      - "4318"      # otlp http
-      - "7946"      # memberlist
-    restart: unless-stopped
-    networks:
-      - rustfs-network
-    depends_on:
-      tempo-init:
-        condition: service_completed_successfully
-    healthcheck:
-      test: [ "CMD", "/tempo", "-version" ]
-      interval: 10s
-      timeout: 5s
-      retries: 3
-      start_period: 15s
-
   otel-collector:
-    image: otel/opentelemetry-collector-contrib:latest
+    image: otel/opentelemetry-collector-contrib:0.129.1
     environment:
       - TZ=Asia/Shanghai
     volumes:
-      - ../../.docker/observability/otel-collector-config.yaml:/etc/otelcol-contrib/config.yaml:ro
+      - ../../.docker/observability/otel-collector-config.yaml:/etc/otelcol-contrib/config.yaml
     ports:
-      - "1888:1888"   # pprof
-      - "8888:8888"   # Prometheus metrics for Collector
-      - "8889:8889"   # Prometheus metrics for application indicators
-      - "13133:13133" # health check
-      - "4317:4317"   # OTLP gRPC
-      - "4318:4318"   # OTLP HTTP
-      - "55679:55679" # zpages
+      - 1888:1888
+      - 8888:8888
+      - 8889:8889
+      - 13133:13133
+      - 4317:4317
+      - 4318:4318
+      - 55679:55679
     networks:
       - rustfs-network
-    depends_on:
-      - tempo
-      - jaeger
-      - prometheus
-      - loki
-    restart: unless-stopped
-    healthcheck:
-      test: [ "CMD", "/otelcol-contrib", "--version" ]
-      interval: 10s
-      timeout: 5s
-      retries: 3
-
   jaeger:
-    image: jaegertracing/jaeger:latest
+    image: jaegertracing/jaeger:2.8.0
     environment:
       - TZ=Asia/Shanghai
-      - SPAN_STORAGE_TYPE=badger
-      - BADGER_EPHEMERAL=false
-      - BADGER_DIRECTORY_VALUE=/badger/data
-      - BADGER_DIRECTORY_KEY=/badger/key
-      - COLLECTOR_OTLP_ENABLED=true
-    volumes:
-      - ../../.docker/observability/jaeger.yaml:/etc/jaeger/config.yml:ro
-      - jaeger-data:/badger
     ports:
-      - "16686:16686" # Web UI
-      - "14269:14269" # Admin/Metrics
-      - "4317"        # otlp grpc
-      - "4318"        # otlp http
-    command: [ "--config", "/etc/jaeger/config.yml" ]
+      - "16686:16686"
+      - "14317:4317"
+      - "14318:4318"
     networks:
       - rustfs-network
-    restart: unless-stopped
-    healthcheck:
-      test: [ "CMD", "wget", "--spider", "-q", "http://localhost:14269" ]
-      interval: 10s
-      timeout: 5s
-      retries: 3
-      start_period: 15s
-
   prometheus:
-    image: prom/prometheus:latest
+    image: prom/prometheus:v3.4.2
     environment:
       - TZ=Asia/Shanghai
     volumes:
-      - ../../.docker/observability/prometheus.yml:/etc/prometheus/prometheus.yml:ro
-      - ../../.docker/observability/prometheus-rules:/etc/prometheus/rules:ro
-      - prometheus-data:/prometheus
+      - ../../.docker/observability/prometheus.yml:/etc/prometheus/prometheus.yml
     ports:
       - "9090:9090"
-    command:
-      - '--config.file=/etc/prometheus/prometheus.yml'
-      - '--web.enable-otlp-receiver'
-      - '--web.enable-remote-write-receiver'
-      - '--enable-feature=promql-experimental-functions'
-      - '--storage.tsdb.path=/prometheus'
-      - '--storage.tsdb.retention.time=30d'
     networks:
       - rustfs-network
-    restart: unless-stopped
-    healthcheck:
-      test: [ "CMD", "wget", "--spider", "-q", "http://localhost:9090/-/healthy" ]
-      interval: 10s
-      timeout: 5s
-      retries: 3
-
   loki:
-    image: grafana/loki:latest
+    image: grafana/loki:3.5.1
     environment:
       - TZ=Asia/Shanghai
     volumes:
-      - ../../.docker/observability/loki.yaml:/etc/loki/loki.yaml:ro
-      - loki-data:/loki
+      - ../../.docker/observability/loki-config.yaml:/etc/loki/local-config.yaml
     ports:
       - "3100:3100"
-    command: -config.file=/etc/loki/loki.yaml
+    command: -config.file=/etc/loki/local-config.yaml
     networks:
       - rustfs-network
-    restart: unless-stopped
-    healthcheck:
-      test: [ "CMD", "wget", "--spider", "-q", "http://localhost:3100/ready" ]
-      interval: 15s
-      timeout: 10s
-      retries: 5
-      start_period: 60s
-
-  pyroscope:
-    image: grafana/pyroscope:latest
-    ports:
-      - "4040:4040"
-    command:
-      - -self-profiling.disable-push=true
-    networks:
-      - rustfs-network
-    restart: unless-stopped
-
   grafana:
-    image: grafana/grafana:latest
+    image: grafana/grafana:12.0.2
     ports:
       - "3000:3000" # Web UI
     environment:
       - GF_SECURITY_ADMIN_PASSWORD=admin
-      - GF_SECURITY_ADMIN_USER=admin
       - TZ=Asia/Shanghai
-      - GF_INSTALL_PLUGINS=grafana-pyroscope-datasource
-      - GF_DASHBOARDS_DEFAULT_HOME_DASHBOARD_PATH=/var/lib/grafana/dashboards/home.json
     networks:
       - rustfs-network
-    volumes:
-      - ../../.docker/observability/grafana/provisioning:/etc/grafana/provisioning:ro
-      - ../../.docker/observability/grafana/dashboards:/var/lib/grafana/dashboards:ro
-      - grafana-data:/var/lib/grafana
-    depends_on:
-      - prometheus
-      - tempo
-      - loki
-    restart: unless-stopped
-    healthcheck:
-      test: [ "CMD", "wget", "--spider", "-q", "http://localhost:3000/api/health" ]
-      interval: 10s
-      timeout: 5s
-      retries: 3
-
-  # --- RustFS Cluster ---
 
   node1:
     build:
@@ -200,15 +79,13 @@ services:
       - RUSTFS_VOLUMES=http://node{1...4}:9000/root/data/target/volume/test{1...4}
       - RUSTFS_ADDRESS=:9000
       - RUSTFS_CONSOLE_ENABLE=true
-      - RUSTFS_OBS_ENDPOINT=http://otel-collector:4318
+      - RUSTFS_OBS_ENDPOINT=http://otel-collector:4317
       - RUSTFS_OBS_LOGGER_LEVEL=debug
     platform: linux/amd64
     ports:
-      - "9001:9000"
+      - "9001:9000" # Map port 9001 of the host to port 9000 of the container
     networks:
       - rustfs-network
-    depends_on:
-      - otel-collector
 
   node2:
     build:
@@ -219,15 +96,13 @@ services:
       - RUSTFS_VOLUMES=http://node{1...4}:9000/root/data/target/volume/test{1...4}
       - RUSTFS_ADDRESS=:9000
       - RUSTFS_CONSOLE_ENABLE=true
-      - RUSTFS_OBS_ENDPOINT=http://otel-collector:4318
+      - RUSTFS_OBS_ENDPOINT=http://otel-collector:4317
       - RUSTFS_OBS_LOGGER_LEVEL=debug
     platform: linux/amd64
     ports:
-      - "9002:9000"
+      - "9002:9000" # Map port 9002 of the host to port 9000 of the container
     networks:
       - rustfs-network
-    depends_on:
-      - otel-collector
 
   node3:
     build:
@@ -238,15 +113,13 @@ services:
       - RUSTFS_VOLUMES=http://node{1...4}:9000/root/data/target/volume/test{1...4}
       - RUSTFS_ADDRESS=:9000
       - RUSTFS_CONSOLE_ENABLE=true
-      - RUSTFS_OBS_ENDPOINT=http://otel-collector:4318
+      - RUSTFS_OBS_ENDPOINT=http://otel-collector:4317
       - RUSTFS_OBS_LOGGER_LEVEL=debug
     platform: linux/amd64
     ports:
-      - "9003:9000"
+      - "9003:9000" # Map port 9003 of the host to port 9000 of the container
     networks:
       - rustfs-network
-    depends_on:
-      - otel-collector
 
   node4:
     build:
@@ -257,22 +130,13 @@ services:
       - RUSTFS_VOLUMES=http://node{1...4}:9000/root/data/target/volume/test{1...4}
       - RUSTFS_ADDRESS=:9000
       - RUSTFS_CONSOLE_ENABLE=true
-      - RUSTFS_OBS_ENDPOINT=http://otel-collector:4318
+      - RUSTFS_OBS_ENDPOINT=http://otel-collector:4317
       - RUSTFS_OBS_LOGGER_LEVEL=debug
     platform: linux/amd64
     ports:
-      - "9004:9000"
+      - "9004:9000" # Map port 9004 of the host to port 9000 of the container
     networks:
       - rustfs-network
-    depends_on:
-      - otel-collector
-
-volumes:
-  prometheus-data:
-  tempo-data:
-  loki-data:
-  jaeger-data:
-  grafana-data:
 
 networks:
   rustfs-network:

.docker/mqtt/README.md

@@ -1,30 +0,0 @@
-# MQTT Broker (EMQX)
-
-This directory contains the configuration for running an EMQX MQTT broker, which can be used for testing RustFS's MQTT integration.
-
-## 🚀 Quick Start
-
-To start the EMQX broker:
-
-```bash
-docker compose up -d
-```
-
-## 📊 Access
-
-- **Dashboard**: [http://localhost:18083](http://localhost:18083)
-- **Default Credentials**: `admin` / `public`
-- **MQTT Port**: `1883`
-- **WebSocket Port**: `8083`
-
-## 🛠️ Configuration
-
-The `docker-compose.yml` file sets up a single-node EMQX instance.
-
-- **Persistence**: Data is not persisted by default (for testing).
-- **Network**: Uses the default bridge network.
-
-## 📝 Notes
-
-- This setup is intended for development and testing purposes.
-- For production deployments, please refer to the official [EMQX Documentation](https://www.emqx.io/docs/en/latest/).

.docker/nginx/nginx.conf

@@ -1,93 +0,0 @@
-# Copyright 2024 RustFS Team
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-
-worker_processes auto;
-pid /var/run/nginx.pid;
-
-events {
-    worker_connections 1024;
-}
-
-http {
-    include /etc/nginx/mime.types;
-    default_type application/octet-stream;
-
-    log_format main '$remote_addr - $remote_user [$time_local] "$request" '
-                    '$status $body_bytes_sent "$http_referer" '
-                    '"$http_user_agent" "$http_x_forwarded_for"';
-
-    access_log /var/log/nginx/access.log main;
-    error_log /var/log/nginx/error.log warn;
-
-    sendfile on;
-    keepalive_timeout 65;
-
-    # RustFS Server Block
-    server {
-        listen 80;
-        server_name localhost;
-
-        # Redirect HTTP to HTTPS (optional, uncomment if SSL is configured)
-        # return 301 https://$host$request_uri;
-
-        location / {
-            proxy_pass http://rustfs:9000;
-            proxy_set_header Host $host;
-            proxy_set_header X-Real-IP $remote_addr;
-            proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
-            proxy_set_header X-Forwarded-Proto $scheme;
-
-            # S3 specific headers
-            proxy_set_header X-Amz-Date $http_x_amz_date;
-            proxy_set_header Authorization $http_authorization;
-
-            # Disable buffering for large uploads
-            proxy_request_buffering off;
-            client_max_body_size 0;
-        }
-
-        location /rustfs/console {
-            proxy_pass http://rustfs:9001;
-            proxy_set_header Host $host;
-            proxy_set_header X-Real-IP $remote_addr;
-            proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
-            proxy_set_header X-Forwarded-Proto $scheme;
-        }
-    }
-
-    # SSL Configuration (Example)
-    # server {
-    #     listen 443 ssl;
-    #     server_name localhost;
-    #
-    #     ssl_certificate /etc/nginx/ssl/server.crt;
-    #     ssl_certificate_key /etc/nginx/ssl/server.key;
-    #
-    #     # Restrict to modern TLS versions and ciphers. Operators copying this
-    #     # example must keep at least these directives — without them, nginx
-    #     # may negotiate older protocol versions that have known weaknesses.
-    #     ssl_protocols TLSv1.2 TLSv1.3;
-    #     ssl_prefer_server_ciphers on;
-    #     ssl_ciphers 'ECDHE-ECDSA-AES128-GCM-SHA256:ECDHE-RSA-AES128-GCM-SHA256:ECDHE-ECDSA-AES256-GCM-SHA384:ECDHE-RSA-AES256-GCM-SHA384:ECDHE-ECDSA-CHACHA20-POLY1305:ECDHE-RSA-CHACHA20-POLY1305';
-    #     ssl_session_timeout 1d;
-    #     ssl_session_cache shared:SSL:10m;
-    #     ssl_session_tickets off;
-    #     # add_header Strict-Transport-Security "max-age=63072000" always;
-    #
-    #     location / {
-    #         proxy_pass http://rustfs:9000;
-    #         ...
-    #     }
-    # }
-}

.docker/observability/.gitignore

@@ -1,5 +0,0 @@
-jaeger-data/*
-loki-data/*
-prometheus-data/*
-tempo-data/*
-grafana-data/*

.docker/observability/README.md

@@ -1,196 +1,109 @@
-# RustFS Observability Stack
+# Observability
 
-This directory contains the comprehensive observability stack for RustFS, designed to provide deep insights into application performance, logs, and traces.
+This directory contains the observability stack for the application. The stack is composed of the following components:
 
-## Components
+- Prometheus v3.2.1
+- Grafana 11.6.0
+- Loki 3.4.2
+- Jaeger 2.4.0
+- Otel Collector 0.120.0 # 0.121.0 remove loki
 
-The stack is composed of the following best-in-class open-source components:
+## Prometheus
 
-- **Prometheus** (v2.53.1): The industry standard for metric collection and alerting.
-- **Grafana** (v11.1.0): The leading platform for observability visualization.
-- **Loki** (v3.1.0): A horizontally-scalable, highly-available, multi-tenant log aggregation system.
-- **Tempo** (v2.5.0): A high-volume, minimal dependency distributed tracing backend.
-- **Jaeger** (v1.59.0): Distributed tracing system (configured as a secondary UI/storage).
-- **OpenTelemetry Collector** (v0.104.0): A vendor-agnostic implementation for receiving, processing, and exporting telemetry data.
+Prometheus is a monitoring and alerting toolkit. It scrapes metrics from instrumented jobs, either directly or via an
+intermediary push gateway for short-lived jobs. It stores all scraped samples locally and runs rules over this data to
+either aggregate and record new time series from existing data or generate alerts. Grafana or other API consumers can be
+used to visualize the collected data.
 
-By default, this stack uses Tempo in single-binary mode and does not require Kafka/Redpanda.
-If you want the Kafka-backed HA Tempo path, use `docker-compose-example-for-rustfs.yml` together with `docker-compose-tempo-ha-override.yml`.
+## Grafana
 
-## Architecture
+Grafana is a multi-platform open-source analytics and interactive visualization web application. It provides charts,
+graphs, and alerts for the web when connected to supported data sources.
 
-1. **Telemetry Collection**: Applications send OTLP (OpenTelemetry Protocol) data (Metrics, Logs, Traces) to the **OpenTelemetry Collector**.
-2. **Processing & Exporting**: The Collector processes the data (batching, memory limiting) and exports it to the respective backends:
-    - **Traces** -> **Tempo** (Primary) & **Jaeger** (Secondary/Optional)
-    - **Metrics** -> **Prometheus** (via scraping the Collector's exporter)
-    - **Logs** -> **Loki**
-3. **Visualization**: **Grafana** connects to all backends (Prometheus, Tempo, Loki, Jaeger) to provide a unified dashboard experience.
+## Loki
 
-## Features
+Loki is a horizontally-scalable, highly-available, multi-tenant log aggregation system inspired by Prometheus. It is
+designed to be very cost-effective and easy to operate. It does not index the contents of the logs, but rather a set of
+labels for each log stream.
 
-- **Full Persistence**: All data (Metrics, Logs, Traces) is persisted to Docker volumes, ensuring no data loss on restart.
-- **Correlation**: Seamless navigation between Metrics, Logs, and Traces in Grafana.
-  - Jump from a Metric spike to relevant Traces.
-  - Jump from a Trace to relevant Logs.
-- **High Performance**: Optimized configurations for batching, compression, and memory management.
-- **Standardized Protocols**: Built entirely on OpenTelemetry standards.
+## Jaeger
 
-## GET Performance Optimization Dashboards
+Jaeger is a distributed tracing system released as open source by Uber Technologies. It is used for monitoring and
+troubleshooting microservices-based distributed systems, including:
 
-Three pre-built Grafana dashboards are included for monitoring RustFS GET performance optimization rollout:
+- Distributed context propagation
+- Distributed transaction monitoring
+- Root cause analysis
+- Service dependency analysis
+- Performance / latency optimization
 
-### Available Dashboards
+## Otel Collector
 
-| Dashboard | File | Description |
-|-----------|------|-------------|
-| **GET Rollout Health** | `grafana-get-rollout-health.json` | Monitors optimization rollout: latency by reader path, early-stop hit rate, codec streaming usage, pipeline failures |
-| **GET Data Integrity** | `grafana-get-data-integrity.json` | Monitors data safety: bitrot verify failures, decode errors, short reads, shard read outcomes |
-| **GET Resource Impact** | `grafana-get-resource-impact.json` | Monitors resource usage: concurrent requests, IO queue utilization, disk permit wait, RSS trend |
-| **Object Data Cache** | `grafana-object-data-cache.json` | Monitors the GET body cache (`rustfs_object_data_cache_*`): hit ratio, lookup/plan/fill outcomes, fill duration quantiles, hit vs fill throughput, entries/weighted bytes, inflight fills, memory-pressure skips, invalidations, and size-class breakdowns |
+The OpenTelemetry Collector offers a vendor-agnostic implementation on how to receive, process, and export telemetry
+data. It removes the need to run, operate, and maintain multiple agents/collectors in order to support open-source
+observability data formats (e.g. Jaeger, Prometheus, etc.) sending to one or more open-source or commercial back-ends.
 
-### Prometheus Alert Rules
+## How to use
 
-The file `prometheus-rules/rustfs-get-optimization-alerts.yaml` contains pre-configured alerting rules:
+To deploy the observability stack, run the following command:
 
-| Alert | Severity | Condition |
-|-------|----------|-----------|
-| `GetP99Regression` | Critical | GET p99 latency > 2x baseline for 10m |
-| `PipelineFailureSpike` | Critical | Pipeline failure rate > 5x baseline for 5m |
-| `BitrotMismatchSpike` | Critical | Bitrot mismatch rate > 3x baseline for 5m |
-| `EarlyStopInsufficientQuorum` | Warning | Early-stop insufficient quorum rate > 0.1/s for 5m |
-| `CodecStreamingFallbackSpike` | Warning | Codec streaming fallback > 10x baseline for 10m |
-| `IoQueueSaturation` | Warning | IO queue utilization > 90% for 5m |
+- docker latest version
 
-### Enabling Alert Rules
+```bash
+docker compose -f docker-compose.yml -f docker-compose.override.yml up -d
+```
 
-Add the alert rules file to your Prometheus configuration:
+- docker compose v2.0.0 or before
+
+```bash
+docke-compose -f docker-compose.yml -f docker-compose.override.yml up -d
+```
+
+To access the Grafana dashboard, navigate to `http://localhost:3000` in your browser. The default username and password
+are `admin` and `admin`, respectively.
+
+To access the Jaeger dashboard, navigate to `http://localhost:16686` in your browser.
+
+To access the Prometheus dashboard, navigate to `http://localhost:9090` in your browser.
+
+## How to stop
+
+To stop the observability stack, run the following command:
+
+```bash
+docker compose -f docker-compose.yml -f docker-compose.override.yml down
+```
+
+## How to remove data
+
+To remove the data generated by the observability stack, run the following command:
+
+```bash
+docker compose -f docker-compose.yml -f docker-compose.override.yml down -v
+```
+
+## How to configure
+
+To configure the observability stack, modify the `docker-compose.override.yml` file. The file contains the following
 
 ```yaml
-# prometheus.yml
-rule_files:
-  - "/etc/prometheus/rules/*.yml"
+services:
+  prometheus:
+    environment:
+      - PROMETHEUS_CONFIG_FILE=/etc/prometheus/prometheus.yml
+    volumes:
+      - ./prometheus.yml:/etc/prometheus/prometheus.yml
 
-# Or mount the file in docker-compose.yml:
-# volumes:
-#   - ./prometheus-rules:/etc/prometheus/rules
+  grafana:
+    environment:
+      - GF_SECURITY_ADMIN_PASSWORD=admin
+    volumes:
+      - ./grafana/provisioning:/etc/grafana/provisioning
 ```
 
-### Dashboard Usage
+The `prometheus` service mounts the `prometheus.yml` file to `/etc/prometheus/prometheus.yml`. The `grafana` service
+mounts the `grafana/provisioning` directory to `/etc/grafana/provisioning`. You can modify these files to configure the
+observability stack.
 
-The dashboards are automatically provisioned when Grafana starts. They use the `${DS_PROMETHEUS}` datasource variable, so you need a Prometheus datasource configured in Grafana.
 
-Key panels to monitor during optimization rollout:
 
-1. **GET Latency by Reader Path** - Compare `codec_streaming` vs `legacy_duplex` latency
-2. **Early-Stop Hit Rate** - Verify early-stop is triggering effectively
-3. **Pipeline Failure Rate** - Detect any new failure modes introduced by optimizations
-4. **Bitrot Verify Failures** - Ensure data integrity is maintained
-
-## Quick Start
-
-### Prerequisites
-
-- Docker
-- Docker Compose
-
-### Deploy
-
-Run the following command to start the entire stack:
-
-```bash
-docker compose up -d
-```
-
-### High Availability Tempo
-
-The default `docker-compose.yml` is the single-node stack.
-If you need the Kafka-backed HA Tempo configuration, start it with:
-
-```bash
-docker compose -f docker-compose-example-for-rustfs.yml -f docker-compose-tempo-ha-override.yml up -d
-```
-
-### Access Dashboards
-
-| Service        | URL                                              | Credentials       | Description                    |
-| :------------- | :----------------------------------------------- | :---------------- | :----------------------------- |
-| **Grafana**    | [http://localhost:3000](http://localhost:3000)   | `admin` / `admin` | Main visualization hub.        |
-| **Prometheus** | [http://localhost:9090](http://localhost:9090)   | -                 | Metric queries and status.     |
-| **Jaeger UI**  | [http://localhost:16686](http://localhost:16686) | -                 | Secondary trace visualization. |
-| **Tempo**      | [http://localhost:3200](http://localhost:3200)   | -                 | Tempo status/metrics.          |
-
-## Configuration
-
-### Data Persistence
-
-Data is stored in the following Docker volumes:
-
-- `prometheus-data`: Prometheus metrics
-- `tempo-data`: Tempo traces (WAL and Blocks)
-- `loki-data`: Loki logs (Chunks and Rules)
-- `jaeger-data`: Jaeger traces (Badger DB)
-
-To clear all data:
-
-```bash
-docker compose down -v
-```
-
-### Customization
-
-- **Prometheus**: Edit `prometheus.yml` to add scrape targets or alerting rules.
-- **Grafana**: Dashboards and datasources are provisioned from the `grafana/` directory.
-- **Collector**: Edit `otel-collector-config.yaml` to modify pipelines, processors, or exporters.
-
-### Verifying RustFS Traces
-
-When RustFS points `RUSTFS_OBS_ENDPOINT` at this stack, treat the value as the
-OTLP/HTTP base URL, for example:
-
-```bash
-export RUSTFS_OBS_ENDPOINT=http://host.docker.internal:4318
-```
-
-RustFS automatically expands that base URL to:
-
-- `/v1/traces`
-- `/v1/metrics`
-- `/v1/logs`
-
-Important behavior notes:
-
-- Logs and metrics usually appear during startup, so seeing those two signals
-  first is expected.
-- Visible trace data usually requires real HTTP/S3/gRPC request traffic after
-  startup, because request-path spans are created on demand.
-- `RUSTFS_OBS_LOGGER_LEVEL=info` keeps the top-level request span but filters
-  many nested `debug` spans. If Tempo or Jaeger looks sparse, retry with
-  `RUSTFS_OBS_LOGGER_LEVEL=debug` before suspecting collector or Tempo issues.
-
-Minimal validation flow:
-
-```bash
-# 1. Start this observability stack.
-docker compose up -d
-
-# 2. Start RustFS with OTLP/HTTP export and richer span visibility.
-export RUSTFS_OBS_ENDPOINT=http://host.docker.internal:4318
-export RUSTFS_OBS_LOGGER_LEVEL=debug
-
-# 3. Generate real request traffic.
-curl -I http://127.0.0.1:9000/health
-curl -I http://127.0.0.1:9000/health/ready
-
-# 4. Inspect Grafana or Jaeger.
-# Grafana: http://localhost:3000
-# Jaeger:  http://localhost:16686
-```
-
-If logs and metrics are present but traces are sparse, the most common cause is
-"no real request traffic yet" or "`info` level filtered nested spans", not an
-OTLP routing failure.
-
-## Troubleshooting
-
-- **Service Health**: Check the health of services using `docker compose ps`.
-- **Logs**: View logs for a specific service using `docker compose logs -f <service_name>`.
-- **Otel Collector**: Check `http://localhost:13133` for health status and `http://localhost:1888/debug/pprof/` for profiling.

.docker/observability/README_ZH.md

@@ -1,192 +1,27 @@
-# RustFS 可观测性技术栈
+## 部署可观测性系统
 
-本目录包含 RustFS 的全面可观测性技术栈，旨在提供对应用程序性能、日志和追踪的深入洞察。
+OpenTelemetry Collector 提供了一个厂商中立的遥测数据处理方案，用于接收、处理和导出遥测数据。它消除了为支持多种开源可观测性数据格式（如
+Jaeger、Prometheus 等）而需要运行和维护多个代理/收集器的必要性。
 
-## 组件
+### 快速部署
 
-该技术栈由以下一流的开源组件组成：
-
-- **Prometheus** (v2.53.1): 行业标准的指标收集和告警工具。
-- **Grafana** (v11.1.0): 领先的可观测性可视化平台。
-- **Loki** (v3.1.0): 水平可扩展、高可用、多租户的日志聚合系统。
-- **Tempo** (v2.5.0): 高吞吐量、最小依赖的分布式追踪后端。
-- **Jaeger** (v1.59.0): 分布式追踪系统（配置为辅助 UI/存储）。
-- **OpenTelemetry Collector** (v0.104.0): 接收、处理和导出遥测数据的供应商无关实现。
-
-默认情况下，这套技术栈使用 Tempo 单二进制模式，不依赖 Kafka/Redpanda。
-如果需要基于 Kafka 的 HA Tempo 路径，请使用 `docker-compose-example-for-rustfs.yml` 配合 `docker-compose-tempo-ha-override.yml`。
-
-## 架构
-
-1.  **遥测收集**: 应用程序将 OTLP (OpenTelemetry Protocol) 数据（指标、日志、追踪）发送到 **OpenTelemetry Collector**。
-2.  **处理与导出**: Collector 处理数据（批处理、内存限制）并将其导出到相应的后端：
-    -   **追踪** -> **Tempo** (主要) & **Jaeger** (辅助/可选)
-    -   **指标** -> **Prometheus** (通过抓取 Collector 的导出器)
-    -   **日志** -> **Loki**
-3.  **可视化**: **Grafana** 连接到所有后端（Prometheus, Tempo, Loki, Jaeger），提供统一的仪表盘体验。
-
-## 特性
-
--   **完全持久化**: 所有数据（指标、日志、追踪）都持久化到 Docker 卷，确保重启后无数据丢失。
--   **关联性**: 在 Grafana 中实现指标、日志和追踪之间的无缝导航。
-    -   从指标峰值跳转到相关追踪。
-    -   从追踪跳转到相关日志。
--   **高性能**: 针对批处理、压缩和内存管理进行了优化配置。
--   **标准化协议**: 完全基于 OpenTelemetry 标准构建。
-
-## GET 性能优化仪表盘
-
-包含三个预构建的 Grafana 仪表盘，用于监控 RustFS GET 性能优化发布：
-
-### 可用仪表盘
-
-| 仪表盘 | 文件 | 描述 |
-|--------|------|------|
-| **GET 发布健康度** | `grafana-get-rollout-health.json` | 监控优化发布：按 reader path 的延迟、early-stop 命中率、codec streaming 使用率、pipeline 失败率 |
-| **GET 数据完整性** | `grafana-get-data-integrity.json` | 监控数据安全：bitrot 校验失败、decode 错误、short read、shard 读取结果 |
-| **GET 资源影响** | `grafana-get-resource-impact.json` | 监控资源使用：并发请求数、IO 队列利用率、disk permit 等待、RSS 趋势 |
-| **对象数据缓存** | `grafana-object-data-cache.json` | 监控 GET body 缓存（`rustfs_object_data_cache_*`）：命中率、查找/规划/填充结果、填充耗时分位、命中 vs 填充吞吐、条目数/加权字节、在途填充、内存压力拒绝、失效、按尺寸档拆分 |
-
-### Prometheus 告警规则
-
-文件 `prometheus-rules/rustfs-get-optimization-alerts.yaml` 包含预配置的告警规则：
-
-| 告警 | 级别 | 条件 |
-|------|------|------|
-| `GetP99Regression` | 严重 | GET p99 延迟 > 2x 基线，持续 10 分钟 |
-| `PipelineFailureSpike` | 严重 | Pipeline 失败率 > 5x 基线，持续 5 分钟 |
-| `BitrotMismatchSpike` | 严重 | Bitrot 不匹配率 > 3x 基线，持续 5 分钟 |
-| `EarlyStopInsufficientQuorum` | 警告 | Early-stop quorum 不足率 > 0.1/s，持续 5 分钟 |
-| `CodecStreamingFallbackSpike` | 警告 | Codec streaming 回退 > 10x 基线，持续 10 分钟 |
-| `IoQueueSaturation` | 警告 | IO 队列利用率 > 90%，持续 5 分钟 |
-
-### 启用告警规则
-
-在 Prometheus 配置中添加告警规则文件：
-
-```yaml
-# prometheus.yml
-rule_files:
-  - "/etc/prometheus/rules/*.yml"
-
-# 或在 docker-compose.yml 中挂载文件：
-# volumes:
-#   - ./prometheus-rules:/etc/prometheus/rules
-```
-
-### 仪表盘使用
-
-仪表盘在 Grafana 启动时自动预置。它们使用 `${DS_PROMETHEUS}` 数据源变量，因此需要在 Grafana 中配置 Prometheus 数据源。
-
-优化发布期间需要关注的关键面板：
-
-1. **GET 延迟按 Reader Path** - 对比 `codec_streaming` vs `legacy_duplex` 延迟
-2. **Early-Stop 命中率** - 验证 early-stop 是否有效触发
-3. **Pipeline 失败率** - 检测优化引入的新故障模式
-4. **Bitrot 校验失败** - 确保数据完整性
-
-## 快速开始
-
-### 前置条件
-
--   Docker
--   Docker Compose
-
-### 部署
-
-运行以下命令启动整个技术栈：
+1. 进入 `.docker/observability` 目录
+2. 执行以下命令启动服务：
 
 ```bash
-docker compose up -d
+docker compose -f docker-compose.yml  up -d
 ```
 
-### Tempo 高可用模式
+### 访问监控面板
 
-默认的 `docker-compose.yml` 对应单机栈。
-如果需要基于 Kafka 的 HA Tempo 配置，请使用：
+服务启动后，可通过以下地址访问各个监控面板：
 
-```bash
-docker compose -f docker-compose-example-for-rustfs.yml -f docker-compose-tempo-ha-override.yml up -d
+- Grafana: `http://localhost:3000` (默认账号/密码：`admin`/`admin`)
+- Jaeger: `http://localhost:16686`
+- Prometheus: `http://localhost:9090`
+
+## 配置可观测性
+
+```shell
+export RUSTFS_OBS_ENDPOINT="http://localhost:4317" # OpenTelemetry Collector 地址
 ```
-
-### 访问仪表盘
-
-| 服务 | URL | 凭据 | 描述 |
-| :--- | :--- | :--- | :--- |
-| **Grafana** | [http://localhost:3000](http://localhost:3000) | `admin` / `admin` | 主要可视化中心。 |
-| **Prometheus** | [http://localhost:9090](http://localhost:9090) | - | 指标查询和状态。 |
-| **Jaeger UI** | [http://localhost:16686](http://localhost:16686) | - | 辅助追踪可视化。 |
-| **Tempo** | [http://localhost:3200](http://localhost:3200) | - | Tempo 状态/指标。 |
-
-## 配置
-
-### 数据持久化
-
-数据存储在以下 Docker 卷中：
-
--   `prometheus-data`: Prometheus 指标
--   `tempo-data`: Tempo 追踪 (WAL 和 Blocks)
--   `loki-data`: Loki 日志 (Chunks 和 Rules)
--   `jaeger-data`: Jaeger 追踪 (Badger DB)
-
-要清除所有数据：
-
-```bash
-docker compose down -v
-```
-
-### 自定义
-
--   **Prometheus**: 编辑 `prometheus.yml` 以添加抓取目标或告警规则。
--   **Grafana**: 仪表盘和数据源从 `grafana/` 目录预置。
--   **Collector**: 编辑 `otel-collector-config.yaml` 以修改管道、处理器或导出器。
-
-### 验证 RustFS Trace
-
-当 RustFS 将 `RUSTFS_OBS_ENDPOINT` 指向这套技术栈时，应将该值视为
-OTLP/HTTP 的基础 URL，例如：
-
-```bash
-export RUSTFS_OBS_ENDPOINT=http://host.docker.internal:4318
-```
-
-RustFS 会自动在该基础 URL 后补全：
-
-- `/v1/traces`
-- `/v1/metrics`
-- `/v1/logs`
-
-需要注意：
-
-- 启动阶段通常会先看到日志和指标，因此“先有日志/指标、后有 trace”是正常现象。
-- 可见的 trace 数据通常依赖启动后的真实 HTTP/S3/gRPC 请求流量，因为请求路径上的 span 是按需创建的。
-- `RUSTFS_OBS_LOGGER_LEVEL=info` 会保留顶层请求 span，但会过滤掉很多 `debug` 级别的嵌套 span。
-  如果 Tempo 或 Jaeger 中的 trace 看起来很稀疏，建议先改成 `RUSTFS_OBS_LOGGER_LEVEL=debug`，再判断是否是 collector 或 Tempo 问题。
-
-最小验证流程：
-
-```bash
-# 1. 启动本目录下的可观测性技术栈。
-docker compose up -d
-
-# 2. 以 OTLP/HTTP 导出方式启动 RustFS，并提高 span 可见性。
-export RUSTFS_OBS_ENDPOINT=http://host.docker.internal:4318
-export RUSTFS_OBS_LOGGER_LEVEL=debug
-
-# 3. 产生真实请求流量。
-curl -I http://127.0.0.1:9000/health
-curl -I http://127.0.0.1:9000/health/ready
-
-# 4. 到 Grafana 或 Jaeger 中检查。
-# Grafana: http://localhost:3000
-# Jaeger:  http://localhost:16686
-```
-
-如果日志和指标已经正常，但 trace 仍然稀疏，最常见的原因通常是
-“还没有真实请求流量”或“`info` 级别过滤了嵌套 span”，而不是 OTLP 路由失败。
-
-## 故障排除
-
--   **服务健康**: 使用 `docker compose ps` 检查服务健康状况。
--   **日志**: 使用 `docker compose logs -f <service_name>` 查看特定服务的日志。
--   **Otel Collector**: 检查 `http://localhost:13133` 获取健康状态，检查 `http://localhost:1888/debug/pprof/` 进行性能分析。

.docker/observability/docker-compose-example-for-rustfs.yml

@@ -1,268 +0,0 @@
-# Copyright 2024 RustFS Team
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-
-services:
-  rustfs:
-    security_opt:
-      - "no-new-privileges:true"
-    image: rustfs/rustfs:latest
-    container_name: rustfs-server
-    ports:
-      - "9000:9000" # S3 API port
-      - "9001:9001" # Console port
-    environment:
-      - RUSTFS_VOLUMES=/data/rustfs
-      - RUSTFS_ADDRESS=0.0.0.0:9000
-      - RUSTFS_CONSOLE_ADDRESS=0.0.0.0:9001
-      - RUSTFS_CONSOLE_ENABLE=true
-      - RUSTFS_CORS_ALLOWED_ORIGINS=*
-      - RUSTFS_CONSOLE_CORS_ALLOWED_ORIGINS=*
-      - RUSTFS_ACCESS_KEY=rustfsadmin
-      - RUSTFS_SECRET_KEY=rustfsadmin
-      - RUSTFS_OBS_LOGGER_LEVEL=info
-      - RUSTFS_OBS_ENDPOINT=http://otel-collector:4318
-      - RUSTFS_OBS_PROFILING_ENDPOINT=http://pyroscope:4040
-    volumes:
-      - rustfs-data:/data/rustfs
-    networks:
-      - otel-network
-    restart: unless-stopped
-    healthcheck:
-      test:
-        [
-          "CMD",
-          "sh",
-          "-c",
-          "curl -f http://127.0.0.1:9000/health && curl -f http://127.0.0.1:9001/rustfs/console/health",
-        ]
-      interval: 30s
-      timeout: 10s
-      retries: 3
-      start_period: 40s
-    depends_on:
-      otel-collector:
-        condition: service_started
-
-  rustfs-init:
-    image: alpine
-    container_name: rustfs-init
-    volumes:
-      - rustfs-data:/data
-    networks:
-      - otel-network
-    command: >
-      sh -c "
-        chown -R 10001:10001 /data &&
-        echo 'Volume Permissions fixed' &&
-        exit 0
-      "
-    restart: no
-
-  # --- Tracing ---
-
-  tempo:
-    image: grafana/tempo:latest
-    container_name: tempo
-    command: [ "-config.file=/etc/tempo.yaml" ]
-    volumes:
-      - ./tempo.yaml:/etc/tempo.yaml:ro
-      - tempo-data:/var/tempo
-    ports:
-      - "3200:3200" # tempo
-      - "4317" # otlp grpc
-      - "4318" # otlp http
-    networks:
-      - otel-network
-    restart: unless-stopped
-    healthcheck:
-      test: [ "CMD", "/tempo", "-version" ]
-      interval: 10s
-      timeout: 5s
-      retries: 3
-      start_period: 15s
-
-  redpanda:
-    image: redpandadata/redpanda:latest # for tempo ingest
-    container_name: redpanda
-    ports:
-      - "9092:9092"
-    networks:
-      - otel-network
-    restart: unless-stopped
-    command: >
-      redpanda start --overprovisioned
-      --mode=dev-container
-      --kafka-addr=PLAINTEXT://0.0.0.0:9092
-      --advertise-kafka-addr=PLAINTEXT://redpanda:9092
-
-  jaeger:
-    image: jaegertracing/jaeger:latest
-    container_name: jaeger
-    environment:
-      - SPAN_STORAGE_TYPE=badger
-      - BADGER_EPHEMERAL=false
-      - BADGER_DIRECTORY_VALUE=/badger/data
-      - BADGER_DIRECTORY_KEY=/badger/key
-      - COLLECTOR_OTLP_ENABLED=true
-    volumes:
-      - ./jaeger.yaml:/etc/jaeger/config.yml
-      - jaeger-data:/badger
-    ports:
-      - "16686:16686" # Web UI
-      - "14269:14269" # Admin/Metrics
-      - "4317" # otlp grpc
-      - "4318" # otlp http
-    command: [ "--config", "/etc/jaeger/config.yml" ]
-    networks:
-      - otel-network
-    restart: unless-stopped
-    healthcheck:
-      test: [ "CMD", "wget", "--spider", "-q", "http://localhost:14269" ]
-      interval: 10s
-      timeout: 5s
-      retries: 3
-      start_period: 15s
-
-  # --- Metrics ---
-
-  prometheus:
-    image: prom/prometheus:latest
-    container_name: prometheus
-    volumes:
-      - ./prometheus.yml:/etc/prometheus/prometheus.yml:ro
-      - prometheus-data:/prometheus
-    ports:
-      - "9090:9090"
-    command:
-      - "--config.file=/etc/prometheus/prometheus.yml"
-      - "--web.enable-otlp-receiver" # Enable OTLP
-      - "--web.enable-remote-write-receiver" # Enable remote write
-      - "--enable-feature=promql-experimental-functions" # Enable info()
-      - "--storage.tsdb.retention.time=30d"
-    restart: unless-stopped
-    networks:
-      - otel-network
-    healthcheck:
-      test: [ "CMD", "wget", "--spider", "-q", "http://localhost:9090/-/healthy" ]
-      interval: 10s
-      timeout: 5s
-      retries: 3
-
-  # --- Logging ---
-
-  loki:
-    image: grafana/loki:latest
-    container_name: loki
-    volumes:
-      - ./loki.yaml:/etc/loki/loki.yaml:ro
-      - loki-data:/loki
-    ports:
-      - "3100:3100"
-    command: -config.file=/etc/loki/loki.yaml
-    networks:
-      - otel-network
-    restart: unless-stopped
-    healthcheck:
-      test: [ "CMD", "wget", "--spider", "-q", "http://localhost:3100/ready" ]
-      interval: 15s
-      timeout: 10s
-      retries: 5
-      start_period: 60s
-
-  # --- Collection ---
-
-  otel-collector:
-    image: otel/opentelemetry-collector-contrib:latest
-    volumes:
-      - ./otel-collector-config.yaml:/etc/otelcol-contrib/config.yaml:ro
-    ports:
-      - "1888:1888" # pprof
-      - "8888:8888" # Prometheus metrics for Collector
-      - "8889:8889" # Prometheus metrics for application indicators
-      - "13133:13133" # health check
-      - "4317:4317" # OTLP gRPC
-      - "4318:4318" # OTLP HTTP
-      - "55679:55679" # zpages
-    networks:
-      - otel-network
-    restart: unless-stopped
-    depends_on:
-      - tempo
-      - jaeger
-      - prometheus
-      - loki
-    healthcheck:
-      test: [ "CMD", "/otelcol-contrib", "--version" ]
-      interval: 10s
-      timeout: 5s
-      retries: 3
-
-  # --- Profiles ---
-
-  pyroscope:
-    image: grafana/pyroscope:latest
-    container_name: pyroscope
-    ports:
-      - "4040:4040"
-    command:
-      - -self-profiling.disable-push=true
-    networks:
-      - otel-network
-    restart: unless-stopped
-
-  # --- Visualization ---
-
-  grafana:
-    image: grafana/grafana:latest
-    container_name: grafana
-    ports:
-      - "3000:3000"
-    environment:
-      - GF_SECURITY_ADMIN_PASSWORD=admin
-      - GF_SECURITY_ADMIN_USER=admin
-    volumes:
-      - ./grafana/provisioning:/etc/grafana/provisioning:ro
-      - ./grafana/dashboards:/etc/grafana/dashboards:ro
-      - grafana-data:/var/lib/grafana
-    networks:
-      - otel-network
-    restart: unless-stopped
-    depends_on:
-      - prometheus
-      - tempo
-      - loki
-    healthcheck:
-      test:
-        [ "CMD", "wget", "--spider", "-q", "http://localhost:3000/api/health" ]
-      interval: 10s
-      timeout: 5s
-      retries: 3
-
-volumes:
-  rustfs-data:
-  tempo-data:
-  jaeger-data:
-  prometheus-data:
-  loki-data:
-  grafana-data:
-
-networks:
-  otel-network:
-    driver: bridge
-    name: "network_otel"
-    ipam:
-      config:
-        - subnet: 172.28.0.0/16
-    driver_opts:
-      com.docker.network.enable_ipv6: "true"

.docker/observability/docker-compose-tempo-ha-override.yml

@@ -1,62 +0,0 @@
-# Copyright 2024 RustFS Team
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-
-# Docker Compose override file for High Availability Tempo setup
-#
-# Usage:
-# docker-compose -f docker-compose-example-for-rustfs.yml \
-#                -f docker-compose-tempo-ha-override.yml up
-
-services:
-  # Override Tempo to use high-availability configuration
-  tempo:
-    volumes:
-      - ./tempo-ha.yaml:/etc/tempo.yaml:ro
-      - tempo-data:/var/tempo
-    ports:
-      - "3200:3200"   # Tempo HTTP
-      - "4317:4317"   # OTLP gRPC
-      - "4318:4318"   # OTLP HTTP
-      - "7946:7946"   # Memberlist
-      - "14250:14250" # Jaeger gRPC
-      - "14268:14268" # Jaeger Thrift HTTP
-      - "9411:9411"   # Zipkin
-    environment:
-      - TEMPO_MEMBERLIST_BIND_PORT=7946
-    healthcheck:
-      test: [ "CMD", "wget", "--spider", "-q", "http://localhost:3200/ready" ]
-      interval: 10s
-      timeout: 5s
-      retries: 5
-      start_period: 30s
-    depends_on:
-      - redpanda
-
-volumes:
-  tempo-data:
-    driver: local
-    driver_opts:
-      type: tmpfs
-      device: tmpfs
-      o: "size=4g"  # Allocate 4GB tmpfs for Tempo data (adjust based on your needs)
-
-# Network configuration remains the same
-# networks:
-#   otel-network:
-#     driver: bridge
-#     name: "network_otel"
-#     ipam:
-#       config:
-#         - subnet: 172.28.0.0/16
-

.docker/observability/docker-compose.yml

@@ -14,198 +14,93 @@
 
 services:
 
-  # --- Tracing ---
+  tempo-init:
+    image: busybox:latest
+    command: ["sh", "-c", "chown -R 10001:10001 /var/tempo"]
+    volumes:
+      - ./tempo-data:/var/tempo
+    user: root
+    networks:
+      - otel-network
+    restart: "no"
+
   tempo:
-    image: grafana/tempo:2.10.5
-    container_name: tempo
-    command: [ "-config.file=/etc/tempo.yaml" ]
+    image: grafana/tempo:latest
+    user: "10001" # The container must be started with root to execute chown in the script
+    command: [ "-config.file=/etc/tempo.yaml" ] # This is passed as a parameter to the entry point script
     volumes:
       - ./tempo.yaml:/etc/tempo.yaml:ro
-      - tempo-data:/var/tempo
+      - ./tempo-data:/var/tempo
     ports:
       - "3200:3200" # tempo
-      - "4317" # otlp grpc
-      - "4318" # otlp http
-      - "7946" # memberlist
-    networks:
-      - otel-network
-    restart: unless-stopped
-    healthcheck:
-      test: [ "CMD", "/tempo", "-version" ]
-      interval: 10s
-      timeout: 5s
-      retries: 3
-      start_period: 15s
-
-  vulture:
-    image: grafana/tempo-vulture:latest
-    restart: always
-    command:
-      [
-        "-prometheus-listen-address=:8080",
-        "-tempo-query-url=http://tempo:3200",
-        "-tempo-push-url=http://tempo:4317",
-      ]
-    depends_on:
-      - tempo
-
-  jaeger:
-    image: jaegertracing/jaeger:latest
-    container_name: jaeger
-    environment:
-      - SPAN_STORAGE_TYPE=badger
-      - BADGER_EPHEMERAL=false
-      - BADGER_DIRECTORY_VALUE=/badger/data
-      - BADGER_DIRECTORY_KEY=/badger/key
-      - COLLECTOR_OTLP_ENABLED=true
-    volumes:
-      - ./jaeger.yaml:/etc/jaeger/config.yml
-      - jaeger-data:/badger
-    ports:
-      - "16686:16686" # Web UI
-      - "18888:8888" # Metrics
-      - "4317" # otlp grpc
-      - "4318" # otlp http
-    command: [ "--config", "/etc/jaeger/config.yml" ]
-    networks:
-      - otel-network
-    restart: unless-stopped
-    healthcheck:
-      test: [ "CMD", "wget", "--spider", "-q", "http://localhost:8888/metrics" ]
-      interval: 10s
-      timeout: 5s
-      retries: 3
-      start_period: 15s
-
-  # --- Metrics ---
-
-  prometheus:
-    image: prom/prometheus:latest
-    container_name: prometheus
-    volumes:
-      - ./prometheus.yml:/etc/prometheus/prometheus.yml:ro
-      - ./prometheus-rules:/etc/prometheus/rules:ro
-      - prometheus-data:/prometheus
-    ports:
-      - "9090:9090"
-    command:
-      - "--config.file=/etc/prometheus/prometheus.yml"
-      - "--web.enable-otlp-receiver" # Enable OTLP
-      - "--web.enable-remote-write-receiver" # Enable remote write
-      - "--enable-feature=promql-experimental-functions" # Enable info()
-      - "--storage.tsdb.retention.time=30d"
+      - "24317:4317" # otlp grpc
     restart: unless-stopped
     networks:
       - otel-network
-    healthcheck:
-      test: [ "CMD", "wget", "--spider", "-q", "http://localhost:9090/-/healthy" ]
-      interval: 10s
-      timeout: 5s
-      retries: 3
-
-  # --- Logging ---
-
-  loki:
-    image: grafana/loki:latest
-    container_name: loki
-    volumes:
-      - ./loki.yaml:/etc/loki/loki.yaml:ro
-      - loki-data:/loki
-    ports:
-      - "3100:3100"
-    command: -config.file=/etc/loki/loki.yaml
-    networks:
-      - otel-network
-    restart: unless-stopped
-    healthcheck:
-      test: [ "CMD", "/usr/bin/loki", "--version" ]
-      interval: 15s
-      timeout: 10s
-      retries: 5
-      start_period: 60s
-
-  # --- Collection ---
 
   otel-collector:
-    image: otel/opentelemetry-collector-contrib:latest
+    image: otel/opentelemetry-collector-contrib:0.129.1
+    environment:
+      - TZ=Asia/Shanghai
     volumes:
-      - ./otel-collector-config.yaml:/etc/otelcol-contrib/config.yaml:ro
+      - ./otel-collector-config.yaml:/etc/otelcol-contrib/config.yaml
     ports:
-      - "1888:1888" # pprof
-      - "8888:8888" # Prometheus metrics for Collector
-      - "8889:8889" # Prometheus metrics for application indicators
-      - "13133:13133" # health check
-      - "4317:4317" # OTLP gRPC
-      - "4318:4318" # OTLP HTTP
-      - "55679:55679" # zpages
+      - "1888:1888"
+      - "8888:8888"
+      - "8889:8889"
+      - "13133:13133"
+      - "4317:4317"
+      - "4318:4318"
+      - "55679:55679"
     networks:
       - otel-network
-    restart: unless-stopped
-    depends_on:
-      - tempo
-      - jaeger
-      - prometheus
-      - loki
-    healthcheck:
-      test: [ "CMD", "/otelcol-contrib", "--version" ]
-      interval: 10s
-      timeout: 5s
-      retries: 3
-
-  # --- Profiles ---
-
-  pyroscope:
-    image: grafana/pyroscope:latest
-    container_name: pyroscope
+  jaeger:
+    image: jaegertracing/jaeger:2.8.0
+    environment:
+      - TZ=Asia/Shanghai
     ports:
-      - "4040:4040"
-    command:
-      - -self-profiling.disable-push=true
+      - "16686:16686"
+      - "14317:4317"
+      - "14318:4318"
+    networks:
+      - otel-network
+  prometheus:
+    image: prom/prometheus:v3.4.2
+    environment:
+      - TZ=Asia/Shanghai
+    volumes:
+      - ./prometheus.yml:/etc/prometheus/prometheus.yml
+    ports:
+      - "9090:9090"
+    networks:
+      - otel-network
+  loki:
+    image: grafana/loki:3.5.1
+    environment:
+      - TZ=Asia/Shanghai
+    volumes:
+      - ./loki-config.yaml:/etc/loki/local-config.yaml
+    ports:
+      - "3100:3100"
+    command: -config.file=/etc/loki/local-config.yaml
     networks:
       - otel-network
-    restart: unless-stopped
-
-  # --- Visualization ---
-
   grafana:
-    image: grafana/grafana:latest
-    container_name: grafana
+    image: grafana/grafana:12.0.2
     ports:
-      - "3000:3000"
+      - "3000:3000"  # Web UI
+    volumes:
+      - ./grafana-datasources.yaml:/etc/grafana/provisioning/datasources/datasources.yaml
     environment:
       - GF_SECURITY_ADMIN_PASSWORD=admin
-      - GF_SECURITY_ADMIN_USER=admin
-    volumes:
-      - ./grafana/provisioning:/etc/grafana/provisioning:ro
-      - ./grafana/dashboards:/etc/grafana/dashboards:ro
-      - grafana-data:/var/lib/grafana
+      - TZ=Asia/Shanghai
     networks:
       - otel-network
-    restart: unless-stopped
-    depends_on:
-      - prometheus
-      - tempo
-      - loki
-    healthcheck:
-      test:
-        [ "CMD", "wget", "--spider", "-q", "http://localhost:3000/api/health" ]
-      interval: 10s
-      timeout: 5s
-      retries: 3
 
-volumes:
-  tempo-data:
-  jaeger-data:
-  prometheus-data:
-  loki-data:
-  grafana-data:
 
 networks:
   otel-network:
     driver: bridge
-    name: "network_otel"
-    ipam:
-      config:
-        - subnet: 172.28.0.0/16
+    name: "network_otel_config"
     driver_opts:
       com.docker.network.enable_ipv6: "true"

.docker/observability/grafana-datasources.yaml

@@ -0,0 +1,32 @@
+apiVersion: 1
+
+datasources:
+  - name: Prometheus
+    type: prometheus
+    uid: prometheus
+    access: proxy
+    orgId: 1
+    url: http://prometheus:9090
+    basicAuth: false
+    isDefault: false
+    version: 1
+    editable: false
+    jsonData:
+      httpMethod: GET
+  - name: Tempo
+    type: tempo
+    access: proxy
+    orgId: 1
+    url: http://tempo:3200
+    basicAuth: false
+    isDefault: true
+    version: 1
+    editable: false
+    apiVersion: 1
+    uid: tempo
+    jsonData:
+      httpMethod: GET
+      serviceMap:
+        datasourceUid: prometheus
+      streamingEnabled:
+        search: true

.docker/observability/grafana/dashboards/grafana-get-data-integrity.json

@@ -1,500 +0,0 @@
-{
-  "annotations": {
-    "list": []
-  },
-  "editable": true,
-  "fiscalYearStartMonth": 0,
-  "graphTooltip": 1,
-  "id": null,
-  "links": [],
-  "liveNow": false,
-  "panels": [
-    {
-      "datasource": {
-        "type": "prometheus",
-        "uid": "${DS_PROMETHEUS}"
-      },
-      "fieldConfig": {
-        "defaults": {
-          "unit": "ops",
-          "custom": {
-            "drawStyle": "line",
-            "lineInterpolation": "smooth",
-            "fillOpacity": 20,
-            "pointSize": 5,
-            "lineWidth": 1,
-            "showPoints": "auto",
-            "spanNulls": false,
-            "thresholdsStyle": {
-              "mode": "line+area"
-            }
-          },
-          "thresholds": {
-            "mode": "absolute",
-            "steps": [
-              {
-                "color": "transparent",
-                "value": null
-              },
-              {
-                "color": "red",
-                "value": 1
-              }
-            ]
-          }
-        },
-        "overrides": []
-      },
-      "gridPos": {
-        "h": 8,
-        "w": 12,
-        "x": 0,
-        "y": 0
-      },
-      "id": 1,
-      "options": {
-        "reduceOptions": {
-          "values": false,
-          "calcs": ["lastNotNull"],
-          "fields": ""
-        },
-        "tooltip": {
-          "mode": "multi",
-          "sort": "desc"
-        },
-        "legend": {
-          "displayMode": "table",
-          "placement": "bottom",
-          "calcs": ["mean", "max", "sum"]
-        }
-      },
-      "title": "Bitrot Verify Failures",
-      "type": "timeseries",
-      "targets": [
-        {
-          "datasource": {
-            "type": "prometheus",
-            "uid": "${DS_PROMETHEUS}"
-          },
-          "expr": "sum(rate(rustfs_io_get_object_pipeline_failures_total{stage=\"bitrot_verify\"}[$__rate_interval])) by (path, reason)",
-          "legendFormat": "bitrot_fail {{path}} / {{reason}}",
-          "refId": "A"
-        },
-        {
-          "datasource": {
-            "type": "prometheus",
-            "uid": "${DS_PROMETHEUS}"
-          },
-          "expr": "sum(rate(rustfs_io_get_object_pipeline_failures_total{reason=\"bitrot_verify_failed\"}[$__rate_interval])) by (path, stage)",
-          "legendFormat": "verify_failed {{path}} / {{stage}}",
-          "refId": "B"
-        }
-      ]
-    },
-    {
-      "datasource": {
-        "type": "prometheus",
-        "uid": "${DS_PROMETHEUS}"
-      },
-      "fieldConfig": {
-        "defaults": {
-          "unit": "s",
-          "custom": {
-            "drawStyle": "line",
-            "lineInterpolation": "smooth",
-            "fillOpacity": 10,
-            "pointSize": 5,
-            "lineWidth": 1,
-            "showPoints": "auto",
-            "spanNulls": false,
-            "thresholdsStyle": {
-              "mode": "off"
-            }
-          },
-          "thresholds": {
-            "mode": "absolute",
-            "steps": [
-              {
-                "color": "green",
-                "value": null
-              }
-            ]
-          }
-        },
-        "overrides": []
-      },
-      "gridPos": {
-        "h": 8,
-        "w": 12,
-        "x": 12,
-        "y": 0
-      },
-      "id": 2,
-      "options": {
-        "reduceOptions": {
-          "values": false,
-          "calcs": ["lastNotNull"],
-          "fields": ""
-        },
-        "tooltip": {
-          "mode": "multi",
-          "sort": "desc"
-        },
-        "legend": {
-          "displayMode": "table",
-          "placement": "bottom",
-          "calcs": ["mean", "max"]
-        }
-      },
-      "title": "Bitrot Verify Duration (p50 / p95 / p99)",
-      "type": "timeseries",
-      "targets": [
-        {
-          "datasource": {
-            "type": "prometheus",
-            "uid": "${DS_PROMETHEUS}"
-          },
-          "expr": "histogram_quantile(0.50, sum(rate(rustfs_io_get_object_shard_bitrot_verify_duration_seconds_bucket[$__rate_interval])) by (le))",
-          "legendFormat": "p50",
-          "refId": "A"
-        },
-        {
-          "datasource": {
-            "type": "prometheus",
-            "uid": "${DS_PROMETHEUS}"
-          },
-          "expr": "histogram_quantile(0.95, sum(rate(rustfs_io_get_object_shard_bitrot_verify_duration_seconds_bucket[$__rate_interval])) by (le))",
-          "legendFormat": "p95",
-          "refId": "B"
-        },
-        {
-          "datasource": {
-            "type": "prometheus",
-            "uid": "${DS_PROMETHEUS}"
-          },
-          "expr": "histogram_quantile(0.99, sum(rate(rustfs_io_get_object_shard_bitrot_verify_duration_seconds_bucket[$__rate_interval])) by (le))",
-          "legendFormat": "p99",
-          "refId": "C"
-        }
-      ]
-    },
-    {
-      "datasource": {
-        "type": "prometheus",
-        "uid": "${DS_PROMETHEUS}"
-      },
-      "fieldConfig": {
-        "defaults": {
-          "unit": "ops",
-          "custom": {
-            "drawStyle": "line",
-            "lineInterpolation": "smooth",
-            "fillOpacity": 20,
-            "pointSize": 5,
-            "lineWidth": 1,
-            "showPoints": "auto",
-            "spanNulls": false,
-            "thresholdsStyle": {
-              "mode": "line+area"
-            }
-          },
-          "thresholds": {
-            "mode": "absolute",
-            "steps": [
-              {
-                "color": "transparent",
-                "value": null
-              },
-              {
-                "color": "red",
-                "value": 1
-              }
-            ]
-          }
-        },
-        "overrides": []
-      },
-      "gridPos": {
-        "h": 8,
-        "w": 12,
-        "x": 0,
-        "y": 8
-      },
-      "id": 3,
-      "options": {
-        "reduceOptions": {
-          "values": false,
-          "calcs": ["lastNotNull"],
-          "fields": ""
-        },
-        "tooltip": {
-          "mode": "multi",
-          "sort": "desc"
-        },
-        "legend": {
-          "displayMode": "table",
-          "placement": "bottom",
-          "calcs": ["mean", "max", "sum"]
-        }
-      },
-      "title": "Decode Errors",
-      "type": "timeseries",
-      "targets": [
-        {
-          "datasource": {
-            "type": "prometheus",
-            "uid": "${DS_PROMETHEUS}"
-          },
-          "expr": "sum(rate(rustfs_io_get_object_pipeline_failures_total{reason=\"decode_error\"}[$__rate_interval])) by (path, stage)",
-          "legendFormat": "decode_error {{path}} / {{stage}}",
-          "refId": "A"
-        }
-      ]
-    },
-    {
-      "datasource": {
-        "type": "prometheus",
-        "uid": "${DS_PROMETHEUS}"
-      },
-      "fieldConfig": {
-        "defaults": {
-          "unit": "ops",
-          "custom": {
-            "drawStyle": "line",
-            "lineInterpolation": "smooth",
-            "fillOpacity": 20,
-            "pointSize": 5,
-            "lineWidth": 1,
-            "showPoints": "auto",
-            "spanNulls": false,
-            "thresholdsStyle": {
-              "mode": "line+area"
-            }
-          },
-          "thresholds": {
-            "mode": "absolute",
-            "steps": [
-              {
-                "color": "transparent",
-                "value": null
-              },
-              {
-                "color": "red",
-                "value": 1
-              }
-            ]
-          }
-        },
-        "overrides": []
-      },
-      "gridPos": {
-        "h": 8,
-        "w": 12,
-        "x": 12,
-        "y": 8
-      },
-      "id": 4,
-      "options": {
-        "reduceOptions": {
-          "values": false,
-          "calcs": ["lastNotNull"],
-          "fields": ""
-        },
-        "tooltip": {
-          "mode": "multi",
-          "sort": "desc"
-        },
-        "legend": {
-          "displayMode": "table",
-          "placement": "bottom",
-          "calcs": ["mean", "max", "sum"]
-        }
-      },
-      "title": "Short Reads",
-      "type": "timeseries",
-      "targets": [
-        {
-          "datasource": {
-            "type": "prometheus",
-            "uid": "${DS_PROMETHEUS}"
-          },
-          "expr": "sum(rate(rustfs_io_get_object_pipeline_failures_total{reason=\"short_read\"}[$__rate_interval])) by (path, stage)",
-          "legendFormat": "short_read {{path}} / {{stage}}",
-          "refId": "A"
-        }
-      ]
-    },
-    {
-      "datasource": {
-        "type": "prometheus",
-        "uid": "${DS_PROMETHEUS}"
-      },
-      "fieldConfig": {
-        "defaults": {
-          "unit": "ops",
-          "custom": {
-            "drawStyle": "line",
-            "lineInterpolation": "smooth",
-            "fillOpacity": 10,
-            "pointSize": 5,
-            "lineWidth": 1,
-            "showPoints": "auto",
-            "spanNulls": false,
-            "thresholdsStyle": {
-              "mode": "off"
-            }
-          },
-          "thresholds": {
-            "mode": "absolute",
-            "steps": [
-              {
-                "color": "green",
-                "value": null
-              }
-            ]
-          }
-        },
-        "overrides": []
-      },
-      "gridPos": {
-        "h": 8,
-        "w": 12,
-        "x": 0,
-        "y": 16
-      },
-      "id": 5,
-      "options": {
-        "reduceOptions": {
-          "values": false,
-          "calcs": ["lastNotNull"],
-          "fields": ""
-        },
-        "tooltip": {
-          "mode": "multi",
-          "sort": "desc"
-        },
-        "legend": {
-          "displayMode": "table",
-          "placement": "bottom",
-          "calcs": ["mean", "max"]
-        }
-      },
-      "title": "Shard Read Outcomes by Role",
-      "type": "timeseries",
-      "targets": [
-        {
-          "datasource": {
-            "type": "prometheus",
-            "uid": "${DS_PROMETHEUS}"
-          },
-          "expr": "sum(rate(rustfs_io_get_object_shard_read_total[$__rate_interval])) by (path, role, outcome)",
-          "legendFormat": "{{path}} {{role}}/{{outcome}}",
-          "refId": "A"
-        }
-      ]
-    },
-    {
-      "datasource": {
-        "type": "prometheus",
-        "uid": "${DS_PROMETHEUS}"
-      },
-      "fieldConfig": {
-        "defaults": {
-          "unit": "ops",
-          "custom": {
-            "drawStyle": "line",
-            "lineInterpolation": "smooth",
-            "fillOpacity": 10,
-            "pointSize": 5,
-            "lineWidth": 1,
-            "showPoints": "auto",
-            "spanNulls": false,
-            "thresholdsStyle": {
-              "mode": "off"
-            }
-          },
-          "thresholds": {
-            "mode": "absolute",
-            "steps": [
-              {
-                "color": "green",
-                "value": null
-              }
-            ]
-          }
-        },
-        "overrides": []
-      },
-      "gridPos": {
-        "h": 8,
-        "w": 12,
-        "x": 12,
-        "y": 16
-      },
-      "id": 6,
-      "options": {
-        "reduceOptions": {
-          "values": false,
-          "calcs": ["lastNotNull"],
-          "fields": ""
-        },
-        "tooltip": {
-          "mode": "multi",
-          "sort": "desc"
-        },
-        "legend": {
-          "displayMode": "table",
-          "placement": "bottom",
-          "calcs": ["mean", "max"]
-        }
-      },
-      "title": "Request Result Status Rate",
-      "type": "timeseries",
-      "targets": [
-        {
-          "datasource": {
-            "type": "prometheus",
-            "uid": "${DS_PROMETHEUS}"
-          },
-          "expr": "sum(rate(rustfs_io_get_object_request_results_total[$__rate_interval])) by (status)",
-          "legendFormat": "{{status}}",
-          "refId": "A"
-        }
-      ]
-    }
-  ],
-  "refresh": "30s",
-  "schemaVersion": 38,
-  "style": "dark",
-  "tags": ["rustfs", "get-optimization", "data-integrity"],
-  "templating": {
-    "list": [
-      {
-        "current": {
-          "selected": false,
-          "text": "Prometheus",
-          "value": "Prometheus"
-        },
-        "hide": 0,
-        "includeAll": false,
-        "multi": false,
-        "name": "DS_PROMETHEUS",
-        "options": [],
-        "query": "prometheus",
-        "refresh": 1,
-        "regex": "",
-        "skipUrlSync": false,
-        "type": "datasource"
-      }
-    ]
-  },
-  "time": {
-    "from": "now-1h",
-    "to": "now"
-  },
-  "timepicker": {},
-  "timezone": "",
-  "title": "RustFS GET Data Integrity",
-  "uid": "rustfs-get-data-integrity",
-  "version": 1
-}

.docker/observability/grafana/dashboards/grafana-get-performance-attribution.json

@@ -1,716 +0,0 @@
-{
-  "annotations": {
-    "list": []
-  },
-  "editable": true,
-  "fiscalYearStartMonth": 0,
-  "graphTooltip": 1,
-  "id": null,
-  "links": [],
-  "liveNow": false,
-  "panels": [
-    {
-      "datasource": {
-        "type": "prometheus",
-        "uid": "${DS_PROMETHEUS}"
-      },
-      "fieldConfig": {
-        "defaults": {
-          "unit": "ops",
-          "custom": {
-            "drawStyle": "line",
-            "lineInterpolation": "smooth",
-            "fillOpacity": 10,
-            "pointSize": 5,
-            "lineWidth": 1,
-            "showPoints": "auto",
-            "spanNulls": false,
-            "thresholdsStyle": {
-              "mode": "off"
-            }
-          },
-          "thresholds": {
-            "mode": "absolute",
-            "steps": [
-              {
-                "color": "green",
-                "value": null
-              }
-            ]
-          }
-        },
-        "overrides": []
-      },
-      "gridPos": {
-        "h": 8,
-        "w": 12,
-        "x": 0,
-        "y": 0
-      },
-      "id": 1,
-      "options": {
-        "legend": {
-          "calcs": [
-            "mean",
-            "max"
-          ],
-          "displayMode": "table",
-          "placement": "bottom"
-        },
-        "reduceOptions": {
-          "calcs": [
-            "lastNotNull"
-          ],
-          "fields": "",
-          "values": false
-        },
-        "tooltip": {
-          "mode": "multi",
-          "sort": "desc"
-        }
-      },
-      "targets": [
-        {
-          "datasource": {
-            "type": "prometheus",
-            "uid": "${DS_PROMETHEUS}"
-          },
-          "expr": "sum by (strategy, mode) (rate(rustfs_io_get_object_reader_setup_strategy_total[$__rate_interval])) or vector(0)",
-          "legendFormat": "{{strategy}} / {{mode}}",
-          "refId": "A"
-        }
-      ],
-      "title": "GET Reader Setup Strategy Rate",
-      "type": "timeseries"
-    },
-    {
-      "datasource": {
-        "type": "prometheus",
-        "uid": "${DS_PROMETHEUS}"
-      },
-      "fieldConfig": {
-        "defaults": {
-          "unit": "ops",
-          "custom": {
-            "drawStyle": "line",
-            "lineInterpolation": "smooth",
-            "fillOpacity": 10,
-            "pointSize": 5,
-            "lineWidth": 1,
-            "showPoints": "auto",
-            "spanNulls": false,
-            "thresholdsStyle": {
-              "mode": "off"
-            }
-          },
-          "thresholds": {
-            "mode": "absolute",
-            "steps": [
-              {
-                "color": "green",
-                "value": null
-              }
-            ]
-          }
-        },
-        "overrides": []
-      },
-      "gridPos": {
-        "h": 8,
-        "w": 12,
-        "x": 12,
-        "y": 0
-      },
-      "id": 2,
-      "options": {
-        "legend": {
-          "calcs": [
-            "mean",
-            "max"
-          ],
-          "displayMode": "table",
-          "placement": "bottom"
-        },
-        "reduceOptions": {
-          "calcs": [
-            "lastNotNull"
-          ],
-          "fields": "",
-          "values": false
-        },
-        "tooltip": {
-          "mode": "multi",
-          "sort": "desc"
-        }
-      },
-      "targets": [
-        {
-          "datasource": {
-            "type": "prometheus",
-            "uid": "${DS_PROMETHEUS}"
-          },
-          "expr": "sum by (path, strategy, size_bucket) (rate(rustfs_io_get_object_reader_setup_strategy_by_size_total[$__rate_interval])) or vector(0)",
-          "legendFormat": "{{path}} / {{strategy}} / {{size_bucket}}",
-          "refId": "A"
-        }
-      ],
-      "title": "GET Reader Setup Strategy by Size",
-      "type": "timeseries"
-    },
-    {
-      "datasource": {
-        "type": "prometheus",
-        "uid": "${DS_PROMETHEUS}"
-      },
-      "fieldConfig": {
-        "defaults": {
-          "unit": "none",
-          "custom": {
-            "drawStyle": "line",
-            "lineInterpolation": "smooth",
-            "fillOpacity": 10,
-            "pointSize": 5,
-            "lineWidth": 1,
-            "showPoints": "auto",
-            "spanNulls": false,
-            "thresholdsStyle": {
-              "mode": "off"
-            }
-          },
-          "thresholds": {
-            "mode": "absolute",
-            "steps": [
-              {
-                "color": "green",
-                "value": null
-              }
-            ]
-          }
-        },
-        "overrides": []
-      },
-      "gridPos": {
-        "h": 8,
-        "w": 12,
-        "x": 0,
-        "y": 8
-      },
-      "id": 3,
-      "options": {
-        "legend": {
-          "calcs": [
-            "mean",
-            "max"
-          ],
-          "displayMode": "table",
-          "placement": "bottom"
-        },
-        "reduceOptions": {
-          "calcs": [
-            "lastNotNull"
-          ],
-          "fields": "",
-          "values": false
-        },
-        "tooltip": {
-          "mode": "multi",
-          "sort": "desc"
-        }
-      },
-      "targets": [
-        {
-          "datasource": {
-            "type": "prometheus",
-            "uid": "${DS_PROMETHEUS}"
-          },
-          "expr": "sum by (strategy, mode) (rate(rustfs_io_get_object_reader_setup_scheduled_sum[$__rate_interval])) / clamp_min(sum by (strategy, mode) (rate(rustfs_io_get_object_reader_setup_scheduled_count[$__rate_interval])), 1) or vector(0)",
-          "legendFormat": "scheduled {{strategy}} / {{mode}}",
-          "refId": "A"
-        },
-        {
-          "datasource": {
-            "type": "prometheus",
-            "uid": "${DS_PROMETHEUS}"
-          },
-          "expr": "sum by (strategy, mode) (rate(rustfs_io_get_object_reader_setup_attempted_sum[$__rate_interval])) / clamp_min(sum by (strategy, mode) (rate(rustfs_io_get_object_reader_setup_attempted_count[$__rate_interval])), 1) or vector(0)",
-          "legendFormat": "attempted {{strategy}} / {{mode}}",
-          "refId": "B"
-        },
-        {
-          "datasource": {
-            "type": "prometheus",
-            "uid": "${DS_PROMETHEUS}"
-          },
-          "expr": "sum by (strategy, mode) (rate(rustfs_io_get_object_reader_setup_ready_sum[$__rate_interval])) / clamp_min(sum by (strategy, mode) (rate(rustfs_io_get_object_reader_setup_ready_count[$__rate_interval])), 1) or vector(0)",
-          "legendFormat": "ready {{strategy}} / {{mode}}",
-          "refId": "C"
-        },
-        {
-          "datasource": {
-            "type": "prometheus",
-            "uid": "${DS_PROMETHEUS}"
-          },
-          "expr": "sum by (strategy, mode) (rate(rustfs_io_get_object_reader_setup_deferred_sum[$__rate_interval])) / clamp_min(sum by (strategy, mode) (rate(rustfs_io_get_object_reader_setup_deferred_count[$__rate_interval])), 1) or vector(0)",
-          "legendFormat": "deferred {{strategy}} / {{mode}}",
-          "refId": "D"
-        }
-      ],
-      "title": "GET Reader Setup Fanout Average",
-      "type": "timeseries"
-    },
-    {
-      "datasource": {
-        "type": "prometheus",
-        "uid": "${DS_PROMETHEUS}"
-      },
-      "fieldConfig": {
-        "defaults": {
-          "unit": "none",
-          "custom": {
-            "drawStyle": "line",
-            "lineInterpolation": "smooth",
-            "fillOpacity": 10,
-            "pointSize": 5,
-            "lineWidth": 1,
-            "showPoints": "auto",
-            "spanNulls": false,
-            "thresholdsStyle": {
-              "mode": "off"
-            }
-          },
-          "thresholds": {
-            "mode": "absolute",
-            "steps": [
-              {
-                "color": "green",
-                "value": null
-              }
-            ]
-          }
-        },
-        "overrides": []
-      },
-      "gridPos": {
-        "h": 8,
-        "w": 12,
-        "x": 12,
-        "y": 8
-      },
-      "id": 4,
-      "options": {
-        "legend": {
-          "calcs": [
-            "mean",
-            "max"
-          ],
-          "displayMode": "table",
-          "placement": "bottom"
-        },
-        "reduceOptions": {
-          "calcs": [
-            "lastNotNull"
-          ],
-          "fields": "",
-          "values": false
-        },
-        "tooltip": {
-          "mode": "multi",
-          "sort": "desc"
-        }
-      },
-      "targets": [
-        {
-          "datasource": {
-            "type": "prometheus",
-            "uid": "${DS_PROMETHEUS}"
-          },
-          "expr": "sum by (path, strategy, size_bucket) (rate(rustfs_io_get_object_reader_setup_scheduled_by_size_sum[$__rate_interval])) / clamp_min(sum by (path, strategy, size_bucket) (rate(rustfs_io_get_object_reader_setup_scheduled_by_size_count[$__rate_interval])), 1) or vector(0)",
-          "legendFormat": "scheduled {{path}} / {{strategy}} / {{size_bucket}}",
-          "refId": "A"
-        },
-        {
-          "datasource": {
-            "type": "prometheus",
-            "uid": "${DS_PROMETHEUS}"
-          },
-          "expr": "sum by (path, strategy, size_bucket) (rate(rustfs_io_get_object_reader_setup_ready_by_size_sum[$__rate_interval])) / clamp_min(sum by (path, strategy, size_bucket) (rate(rustfs_io_get_object_reader_setup_ready_by_size_count[$__rate_interval])), 1) or vector(0)",
-          "legendFormat": "ready {{path}} / {{strategy}} / {{size_bucket}}",
-          "refId": "B"
-        }
-      ],
-      "title": "GET Reader Setup Fanout by Size",
-      "type": "timeseries"
-    },
-    {
-      "datasource": {
-        "type": "prometheus",
-        "uid": "${DS_PROMETHEUS}"
-      },
-      "fieldConfig": {
-        "defaults": {
-          "unit": "s",
-          "custom": {
-            "drawStyle": "line",
-            "lineInterpolation": "smooth",
-            "fillOpacity": 10,
-            "pointSize": 5,
-            "lineWidth": 1,
-            "showPoints": "auto",
-            "spanNulls": false,
-            "thresholdsStyle": {
-              "mode": "off"
-            }
-          },
-          "thresholds": {
-            "mode": "absolute",
-            "steps": [
-              {
-                "color": "green",
-                "value": null
-              }
-            ]
-          }
-        },
-        "overrides": []
-      },
-      "gridPos": {
-        "h": 8,
-        "w": 12,
-        "x": 0,
-        "y": 16
-      },
-      "id": 5,
-      "options": {
-        "legend": {
-          "calcs": [
-            "mean",
-            "max"
-          ],
-          "displayMode": "table",
-          "placement": "bottom"
-        },
-        "reduceOptions": {
-          "calcs": [
-            "lastNotNull"
-          ],
-          "fields": "",
-          "values": false
-        },
-        "tooltip": {
-          "mode": "multi",
-          "sort": "desc"
-        }
-      },
-      "targets": [
-        {
-          "datasource": {
-            "type": "prometheus",
-            "uid": "${DS_PROMETHEUS}"
-          },
-          "expr": "histogram_quantile(0.95, sum by (path, stage, size_bucket, le) (rate(rustfs_io_get_object_stage_duration_seconds_by_size_bucket{stage=~\"reader_setup|reader_setup_schedule|reader_setup_wait_quorum|reader_setup_drop_pending|reader_task_file_open|reader_task_reader_construction|reader_task_bitrot_reader_init\"}[$__rate_interval]))) or vector(0)",
-          "legendFormat": "p95 {{path}} / {{stage}} / {{size_bucket}}",
-          "refId": "A"
-        },
-        {
-          "datasource": {
-            "type": "prometheus",
-            "uid": "${DS_PROMETHEUS}"
-          },
-          "expr": "histogram_quantile(0.99, sum by (path, stage, size_bucket, le) (rate(rustfs_io_get_object_stage_duration_seconds_by_size_bucket{stage=~\"reader_setup|reader_setup_schedule|reader_setup_wait_quorum|reader_setup_drop_pending|reader_task_file_open|reader_task_reader_construction|reader_task_bitrot_reader_init\"}[$__rate_interval]))) or vector(0)",
-          "legendFormat": "p99 {{path}} / {{stage}} / {{size_bucket}}",
-          "refId": "B"
-        }
-      ],
-      "title": "GET Hot Stage Latency by Size",
-      "type": "timeseries"
-    },
-    {
-      "datasource": {
-        "type": "prometheus",
-        "uid": "${DS_PROMETHEUS}"
-      },
-      "fieldConfig": {
-        "defaults": {
-          "unit": "s",
-          "custom": {
-            "drawStyle": "line",
-            "lineInterpolation": "smooth",
-            "fillOpacity": 10,
-            "pointSize": 5,
-            "lineWidth": 1,
-            "showPoints": "auto",
-            "spanNulls": false,
-            "thresholdsStyle": {
-              "mode": "off"
-            }
-          },
-          "thresholds": {
-            "mode": "absolute",
-            "steps": [
-              {
-                "color": "green",
-                "value": null
-              }
-            ]
-          }
-        },
-        "overrides": []
-      },
-      "gridPos": {
-        "h": 8,
-        "w": 12,
-        "x": 12,
-        "y": 16
-      },
-      "id": 6,
-      "options": {
-        "legend": {
-          "calcs": [
-            "mean",
-            "max"
-          ],
-          "displayMode": "table",
-          "placement": "bottom"
-        },
-        "reduceOptions": {
-          "calcs": [
-            "lastNotNull"
-          ],
-          "fields": "",
-          "values": false
-        },
-        "tooltip": {
-          "mode": "multi",
-          "sort": "desc"
-        }
-      },
-      "targets": [
-        {
-          "datasource": {
-            "type": "prometheus",
-            "uid": "${DS_PROMETHEUS}"
-          },
-          "expr": "histogram_quantile(0.95, sum by (path, stage, le) (rate(rustfs_io_get_object_stage_duration_seconds_bucket{stage=~\"request_context|first_byte|response_handoff|full_body|body_build|output_poll|output_lock_wait|reader_open_mmap_copy_success|reader_open_mmap_copy_fallback|reader_open_stream|reader_stream_first_read|reader_mmap_blocking_wait|reader_mmap_blocking_task|reader_mmap_file_open|reader_mmap_map|reader_mmap_copy_buffer|reader_mmap_direct_read_copy\"}[$__rate_interval]))) or vector(0)",
-          "legendFormat": "p95 {{path}} / {{stage}}",
-          "refId": "A"
-        },
-        {
-          "datasource": {
-            "type": "prometheus",
-            "uid": "${DS_PROMETHEUS}"
-          },
-          "expr": "histogram_quantile(0.99, sum by (path, stage, le) (rate(rustfs_io_get_object_stage_duration_seconds_bucket{stage=~\"request_context|first_byte|response_handoff|full_body|body_build|output_poll|output_lock_wait|reader_open_mmap_copy_success|reader_open_mmap_copy_fallback|reader_open_stream|reader_stream_first_read|reader_mmap_blocking_wait|reader_mmap_blocking_task|reader_mmap_file_open|reader_mmap_map|reader_mmap_copy_buffer|reader_mmap_direct_read_copy\"}[$__rate_interval]))) or vector(0)",
-          "legendFormat": "p99 {{path}} / {{stage}}",
-          "refId": "B"
-        }
-      ],
-      "title": "GET Reader, Handler and Body Latency",
-      "type": "timeseries"
-    },
-    {
-      "datasource": {
-        "type": "prometheus",
-        "uid": "${DS_PROMETHEUS}"
-      },
-      "fieldConfig": {
-        "defaults": {
-          "unit": "ops",
-          "custom": {
-            "drawStyle": "line",
-            "lineInterpolation": "smooth",
-            "fillOpacity": 10,
-            "pointSize": 5,
-            "lineWidth": 1,
-            "showPoints": "auto",
-            "spanNulls": false,
-            "thresholdsStyle": {
-              "mode": "off"
-            }
-          },
-          "thresholds": {
-            "mode": "absolute",
-            "steps": [
-              {
-                "color": "green",
-                "value": null
-              }
-            ]
-          }
-        },
-        "overrides": []
-      },
-      "gridPos": {
-        "h": 8,
-        "w": 12,
-        "x": 0,
-        "y": 24
-      },
-      "id": 7,
-      "options": {
-        "legend": {
-          "calcs": [
-            "mean",
-            "max"
-          ],
-          "displayMode": "table",
-          "placement": "bottom"
-        },
-        "reduceOptions": {
-          "calcs": [
-            "lastNotNull"
-          ],
-          "fields": "",
-          "values": false
-        },
-        "tooltip": {
-          "mode": "multi",
-          "sort": "desc"
-        }
-      },
-      "targets": [
-        {
-          "datasource": {
-            "type": "prometheus",
-            "uid": "${DS_PROMETHEUS}"
-          },
-          "expr": "sum by (subpath) (rate(rustfs_io_get_object_direct_memory_subpath_total[$__rate_interval])) or vector(0)",
-          "legendFormat": "{{subpath}}",
-          "refId": "A"
-        },
-        {
-          "datasource": {
-            "type": "prometheus",
-            "uid": "${DS_PROMETHEUS}"
-          },
-          "expr": "sum by (subpath, size_bucket) (rate(rustfs_io_get_object_direct_memory_subpath_by_size_total[$__rate_interval])) or vector(0)",
-          "legendFormat": "{{subpath}} / {{size_bucket}}",
-          "refId": "B"
-        }
-      ],
-      "title": "GET Direct-Memory Subpath Rate",
-      "type": "timeseries"
-    },
-    {
-      "datasource": {
-        "type": "prometheus",
-        "uid": "${DS_PROMETHEUS}"
-      },
-      "fieldConfig": {
-        "defaults": {
-          "unit": "ops",
-          "custom": {
-            "drawStyle": "line",
-            "lineInterpolation": "smooth",
-            "fillOpacity": 10,
-            "pointSize": 5,
-            "lineWidth": 1,
-            "showPoints": "auto",
-            "spanNulls": false,
-            "thresholdsStyle": {
-              "mode": "off"
-            }
-          },
-          "thresholds": {
-            "mode": "absolute",
-            "steps": [
-              {
-                "color": "green",
-                "value": null
-              }
-            ]
-          }
-        },
-        "overrides": []
-      },
-      "gridPos": {
-        "h": 8,
-        "w": 12,
-        "x": 12,
-        "y": 24
-      },
-      "id": 8,
-      "options": {
-        "legend": {
-          "calcs": [
-            "mean",
-            "max"
-          ],
-          "displayMode": "table",
-          "placement": "bottom"
-        },
-        "reduceOptions": {
-          "calcs": [
-            "lastNotNull"
-          ],
-          "fields": "",
-          "values": false
-        },
-        "tooltip": {
-          "mode": "multi",
-          "sort": "desc"
-        }
-      },
-      "targets": [
-        {
-          "datasource": {
-            "type": "prometheus",
-            "uid": "${DS_PROMETHEUS}"
-          },
-          "expr": "sum by (path, stage, kind) (rate(rustfs_io_get_object_mmap_page_faults_total[$__rate_interval])) or vector(0)",
-          "legendFormat": "mmap {{path}} / {{stage}} / {{kind}}",
-          "refId": "A"
-        },
-        {
-          "datasource": {
-            "type": "prometheus",
-            "uid": "${DS_PROMETHEUS}"
-          },
-          "expr": "sum by (path, stage, kind) (rate(rustfs_io_get_object_direct_read_page_faults_total[$__rate_interval])) or vector(0)",
-          "legendFormat": "direct-read {{path}} / {{stage}} / {{kind}}",
-          "refId": "B"
-        }
-      ],
-      "title": "GET mmap vs Direct-Read Page Fault Rate",
-      "type": "timeseries"
-    }
-  ],
-  "refresh": "30s",
-  "schemaVersion": 38,
-  "style": "dark",
-  "tags": [
-    "rustfs",
-    "get",
-    "performance",
-    "attribution"
-  ],
-  "templating": {
-    "list": [
-      {
-        "current": {
-          "selected": false,
-          "text": "Prometheus",
-          "value": "Prometheus"
-        },
-        "hide": 0,
-        "includeAll": false,
-        "multi": false,
-        "name": "DS_PROMETHEUS",
-        "options": [],
-        "query": "prometheus",
-        "refresh": 1,
-        "regex": "",
-        "skipUrlSync": false,
-        "type": "datasource"
-      }
-    ]
-  },
-  "time": {
-    "from": "now-1h",
-    "to": "now"
-  },
-  "timezone": "",
-  "title": "RustFS GET Performance Attribution",
-  "uid": "rustfs-get-performance-attribution",
-  "version": 1,
-  "weekStart": ""
-}

.docker/observability/grafana/dashboards/grafana-get-resource-impact.json

@@ -1,525 +0,0 @@
-{
-  "annotations": {
-    "list": []
-  },
-  "editable": true,
-  "fiscalYearStartMonth": 0,
-  "graphTooltip": 1,
-  "id": null,
-  "links": [],
-  "liveNow": false,
-  "panels": [
-    {
-      "datasource": {
-        "type": "prometheus",
-        "uid": "${DS_PROMETHEUS}"
-      },
-      "fieldConfig": {
-        "defaults": {
-          "unit": "none",
-          "custom": {
-            "drawStyle": "line",
-            "lineInterpolation": "smooth",
-            "fillOpacity": 20,
-            "pointSize": 5,
-            "lineWidth": 1,
-            "showPoints": "auto",
-            "spanNulls": false,
-            "thresholdsStyle": {
-              "mode": "off"
-            }
-          },
-          "thresholds": {
-            "mode": "absolute",
-            "steps": [
-              {
-                "color": "green",
-                "value": null
-              }
-            ]
-          }
-        },
-        "overrides": []
-      },
-      "gridPos": {
-        "h": 8,
-        "w": 12,
-        "x": 0,
-        "y": 0
-      },
-      "id": 1,
-      "options": {
-        "reduceOptions": {
-          "values": false,
-          "calcs": ["lastNotNull"],
-          "fields": ""
-        },
-        "tooltip": {
-          "mode": "multi",
-          "sort": "desc"
-        },
-        "legend": {
-          "displayMode": "table",
-          "placement": "bottom",
-          "calcs": ["mean", "max"]
-        }
-      },
-      "title": "Concurrent GET Requests",
-      "type": "timeseries",
-      "targets": [
-        {
-          "datasource": {
-            "type": "prometheus",
-            "uid": "${DS_PROMETHEUS}"
-          },
-          "expr": "rustfs_io_get_object_concurrent_requests",
-          "legendFormat": "concurrent GETs",
-          "refId": "A"
-        }
-      ]
-    },
-    {
-      "datasource": {
-        "type": "prometheus",
-        "uid": "${DS_PROMETHEUS}"
-      },
-      "fieldConfig": {
-        "defaults": {
-          "unit": "percent",
-          "min": 0,
-          "max": 100,
-          "custom": {
-            "drawStyle": "line",
-            "lineInterpolation": "smooth",
-            "fillOpacity": 20,
-            "pointSize": 5,
-            "lineWidth": 1,
-            "showPoints": "auto",
-            "spanNulls": false,
-            "thresholdsStyle": {
-              "mode": "line+area"
-            }
-          },
-          "thresholds": {
-            "mode": "absolute",
-            "steps": [
-              {
-                "color": "transparent",
-                "value": null
-              },
-              {
-                "color": "yellow",
-                "value": 70
-              },
-              {
-                "color": "red",
-                "value": 90
-              }
-            ]
-          }
-        },
-        "overrides": []
-      },
-      "gridPos": {
-        "h": 8,
-        "w": 12,
-        "x": 12,
-        "y": 0
-      },
-      "id": 2,
-      "options": {
-        "reduceOptions": {
-          "values": false,
-          "calcs": ["lastNotNull"],
-          "fields": ""
-        },
-        "tooltip": {
-          "mode": "multi",
-          "sort": "desc"
-        },
-        "legend": {
-          "displayMode": "table",
-          "placement": "bottom",
-          "calcs": ["mean", "max"]
-        }
-      },
-      "title": "IO Queue Utilization",
-      "type": "timeseries",
-      "targets": [
-        {
-          "datasource": {
-            "type": "prometheus",
-            "uid": "${DS_PROMETHEUS}"
-          },
-          "expr": "rustfs_io_queue_utilization_percent",
-          "legendFormat": "queue utilization %",
-          "refId": "A"
-        },
-        {
-          "datasource": {
-            "type": "prometheus",
-            "uid": "${DS_PROMETHEUS}"
-          },
-          "expr": "rustfs_io_queue_permits_in_use",
-          "legendFormat": "permits in use",
-          "refId": "B"
-        },
-        {
-          "datasource": {
-            "type": "prometheus",
-            "uid": "${DS_PROMETHEUS}"
-          },
-          "expr": "rustfs_io_queue_permits_available",
-          "legendFormat": "permits available",
-          "refId": "C"
-        }
-      ]
-    },
-    {
-      "datasource": {
-        "type": "prometheus",
-        "uid": "${DS_PROMETHEUS}"
-      },
-      "fieldConfig": {
-        "defaults": {
-          "unit": "s",
-          "custom": {
-            "drawStyle": "line",
-            "lineInterpolation": "smooth",
-            "fillOpacity": 10,
-            "pointSize": 5,
-            "lineWidth": 1,
-            "showPoints": "auto",
-            "spanNulls": false,
-            "thresholdsStyle": {
-              "mode": "off"
-            }
-          },
-          "thresholds": {
-            "mode": "absolute",
-            "steps": [
-              {
-                "color": "green",
-                "value": null
-              }
-            ]
-          }
-        },
-        "overrides": []
-      },
-      "gridPos": {
-        "h": 8,
-        "w": 12,
-        "x": 0,
-        "y": 8
-      },
-      "id": 3,
-      "options": {
-        "reduceOptions": {
-          "values": false,
-          "calcs": ["lastNotNull"],
-          "fields": ""
-        },
-        "tooltip": {
-          "mode": "multi",
-          "sort": "desc"
-        },
-        "legend": {
-          "displayMode": "table",
-          "placement": "bottom",
-          "calcs": ["mean", "max"]
-        }
-      },
-      "title": "Disk Permit Wait Duration (p50 / p95 / p99)",
-      "type": "timeseries",
-      "targets": [
-        {
-          "datasource": {
-            "type": "prometheus",
-            "uid": "${DS_PROMETHEUS}"
-          },
-          "expr": "histogram_quantile(0.50, sum(rate(rustfs_io_disk_permit_wait_duration_seconds_bucket[$__rate_interval])) by (le))",
-          "legendFormat": "p50",
-          "refId": "A"
-        },
-        {
-          "datasource": {
-            "type": "prometheus",
-            "uid": "${DS_PROMETHEUS}"
-          },
-          "expr": "histogram_quantile(0.95, sum(rate(rustfs_io_disk_permit_wait_duration_seconds_bucket[$__rate_interval])) by (le))",
-          "legendFormat": "p95",
-          "refId": "B"
-        },
-        {
-          "datasource": {
-            "type": "prometheus",
-            "uid": "${DS_PROMETHEUS}"
-          },
-          "expr": "histogram_quantile(0.99, sum(rate(rustfs_io_disk_permit_wait_duration_seconds_bucket[$__rate_interval])) by (le))",
-          "legendFormat": "p99",
-          "refId": "C"
-        }
-      ]
-    },
-    {
-      "datasource": {
-        "type": "prometheus",
-        "uid": "${DS_PROMETHEUS}"
-      },
-      "fieldConfig": {
-        "defaults": {
-          "unit": "bytes",
-          "custom": {
-            "drawStyle": "line",
-            "lineInterpolation": "smooth",
-            "fillOpacity": 15,
-            "pointSize": 5,
-            "lineWidth": 1,
-            "showPoints": "auto",
-            "spanNulls": false,
-            "thresholdsStyle": {
-              "mode": "off"
-            }
-          },
-          "thresholds": {
-            "mode": "absolute",
-            "steps": [
-              {
-                "color": "green",
-                "value": null
-              }
-            ]
-          }
-        },
-        "overrides": []
-      },
-      "gridPos": {
-        "h": 8,
-        "w": 12,
-        "x": 12,
-        "y": 8
-      },
-      "id": 4,
-      "options": {
-        "reduceOptions": {
-          "values": false,
-          "calcs": ["lastNotNull"],
-          "fields": ""
-        },
-        "tooltip": {
-          "mode": "multi",
-          "sort": "desc"
-        },
-        "legend": {
-          "displayMode": "table",
-          "placement": "bottom",
-          "calcs": ["lastNotNull"]
-        }
-      },
-      "title": "RSS Trend (Process Memory)",
-      "type": "timeseries",
-      "targets": [
-        {
-          "datasource": {
-            "type": "prometheus",
-            "uid": "${DS_PROMETHEUS}"
-          },
-          "expr": "process_resident_memory_bytes{job=~\"rustfs.*\"}",
-          "legendFormat": "RSS {{instance}}",
-          "refId": "A"
-        },
-        {
-          "datasource": {
-            "type": "prometheus",
-            "uid": "${DS_PROMETHEUS}"
-          },
-          "expr": "rustfs_process_memory_bytes",
-          "legendFormat": "RustFS memory {{instance}}",
-          "refId": "B"
-        }
-      ]
-    },
-    {
-      "datasource": {
-        "type": "prometheus",
-        "uid": "${DS_PROMETHEUS}"
-      },
-      "fieldConfig": {
-        "defaults": {
-          "unit": "ops",
-          "custom": {
-            "drawStyle": "line",
-            "lineInterpolation": "smooth",
-            "fillOpacity": 10,
-            "pointSize": 5,
-            "lineWidth": 1,
-            "showPoints": "auto",
-            "spanNulls": false,
-            "thresholdsStyle": {
-              "mode": "off"
-            }
-          },
-          "thresholds": {
-            "mode": "absolute",
-            "steps": [
-              {
-                "color": "green",
-                "value": null
-              }
-            ]
-          }
-        },
-        "overrides": []
-      },
-      "gridPos": {
-        "h": 8,
-        "w": 12,
-        "x": 0,
-        "y": 16
-      },
-      "id": 5,
-      "options": {
-        "reduceOptions": {
-          "values": false,
-          "calcs": ["lastNotNull"],
-          "fields": ""
-        },
-        "tooltip": {
-          "mode": "multi",
-          "sort": "desc"
-        },
-        "legend": {
-          "displayMode": "table",
-          "placement": "bottom",
-          "calcs": ["mean", "max"]
-        }
-      },
-      "title": "IO Queue Operations by Priority",
-      "type": "timeseries",
-      "targets": [
-        {
-          "datasource": {
-            "type": "prometheus",
-            "uid": "${DS_PROMETHEUS}"
-          },
-          "expr": "sum(rate(rustfs_io_queue_operations[$__rate_interval])) by (operation, priority)",
-          "legendFormat": "{{operation}} / {{priority}}",
-          "refId": "A"
-        }
-      ]
-    },
-    {
-      "datasource": {
-        "type": "prometheus",
-        "uid": "${DS_PROMETHEUS}"
-      },
-      "fieldConfig": {
-        "defaults": {
-          "unit": "ops",
-          "custom": {
-            "drawStyle": "line",
-            "lineInterpolation": "smooth",
-            "fillOpacity": 15,
-            "pointSize": 5,
-            "lineWidth": 1,
-            "showPoints": "auto",
-            "spanNulls": false,
-            "thresholdsStyle": {
-              "mode": "off"
-            }
-          },
-          "thresholds": {
-            "mode": "absolute",
-            "steps": [
-              {
-                "color": "green",
-                "value": null
-              }
-            ]
-          }
-        },
-        "overrides": []
-      },
-      "gridPos": {
-        "h": 8,
-        "w": 12,
-        "x": 12,
-        "y": 16
-      },
-      "id": 6,
-      "options": {
-        "reduceOptions": {
-          "values": false,
-          "calcs": ["lastNotNull"],
-          "fields": ""
-        },
-        "tooltip": {
-          "mode": "multi",
-          "sort": "desc"
-        },
-        "legend": {
-          "displayMode": "table",
-          "placement": "bottom",
-          "calcs": ["sum"]
-        }
-      },
-      "title": "IO Queue Congestion Events",
-      "type": "timeseries",
-      "targets": [
-        {
-          "datasource": {
-            "type": "prometheus",
-            "uid": "${DS_PROMETHEUS}"
-          },
-          "expr": "sum(rate(rustfs_io_queue_congestion_total[$__rate_interval]))",
-          "legendFormat": "congestion events/s",
-          "refId": "A"
-        },
-        {
-          "datasource": {
-            "type": "prometheus",
-            "uid": "${DS_PROMETHEUS}"
-          },
-          "expr": "sum(rate(rustfs_io_get_object_timeout_total[$__rate_interval])) by (stage)",
-          "legendFormat": "timeout {{stage}}",
-          "refId": "B"
-        }
-      ]
-    }
-  ],
-  "refresh": "30s",
-  "schemaVersion": 38,
-  "style": "dark",
-  "tags": ["rustfs", "get-optimization", "resource-impact"],
-  "templating": {
-    "list": [
-      {
-        "current": {
-          "selected": false,
-          "text": "Prometheus",
-          "value": "Prometheus"
-        },
-        "hide": 0,
-        "includeAll": false,
-        "multi": false,
-        "name": "DS_PROMETHEUS",
-        "options": [],
-        "query": "prometheus",
-        "refresh": 1,
-        "regex": "",
-        "skipUrlSync": false,
-        "type": "datasource"
-      }
-    ]
-  },
-  "time": {
-    "from": "now-1h",
-    "to": "now"
-  },
-  "timepicker": {},
-  "timezone": "",
-  "title": "RustFS GET Resource Impact",
-  "uid": "rustfs-get-resource-impact",
-  "version": 1
-}

.docker/observability/grafana/dashboards/grafana-get-rollout-health.json

@@ -1,530 +0,0 @@
-{
-  "annotations": {
-    "list": []
-  },
-  "editable": true,
-  "fiscalYearStartMonth": 0,
-  "graphTooltip": 1,
-  "id": null,
-  "links": [],
-  "liveNow": false,
-  "panels": [
-    {
-      "datasource": {
-        "type": "prometheus",
-        "uid": "${DS_PROMETHEUS}"
-      },
-      "fieldConfig": {
-        "defaults": {
-          "unit": "s",
-          "custom": {
-            "drawStyle": "line",
-            "lineInterpolation": "smooth",
-            "fillOpacity": 10,
-            "pointSize": 5,
-            "lineWidth": 1,
-            "showPoints": "auto",
-            "spanNulls": false,
-            "axisLabel": "",
-            "axisColorMode": "text",
-            "scaleDistribution": {
-              "type": "linear"
-            },
-            "thresholdsStyle": {
-              "mode": "off"
-            }
-          },
-          "thresholds": {
-            "mode": "absolute",
-            "steps": [
-              {
-                "color": "green",
-                "value": null
-              }
-            ]
-          }
-        },
-        "overrides": []
-      },
-      "gridPos": {
-        "h": 8,
-        "w": 12,
-        "x": 0,
-        "y": 0
-      },
-      "id": 1,
-      "options": {
-        "reduceOptions": {
-          "values": false,
-          "calcs": ["lastNotNull"],
-          "fields": ""
-        },
-        "tooltip": {
-          "mode": "multi",
-          "sort": "desc"
-        },
-        "legend": {
-          "displayMode": "table",
-          "placement": "bottom",
-          "calcs": ["mean", "max"]
-        }
-      },
-      "title": "GET Latency by Reader Path (p50 / p95 / p99)",
-      "type": "timeseries",
-      "targets": [
-        {
-          "datasource": {
-            "type": "prometheus",
-            "uid": "${DS_PROMETHEUS}"
-          },
-          "expr": "histogram_quantile(0.50, sum(rate(rustfs_io_get_object_stage_duration_seconds_bucket{stage=\"total\"}[$__rate_interval])) by (le, path))",
-          "legendFormat": "p50 {{path}}",
-          "refId": "A"
-        },
-        {
-          "datasource": {
-            "type": "prometheus",
-            "uid": "${DS_PROMETHEUS}"
-          },
-          "expr": "histogram_quantile(0.95, sum(rate(rustfs_io_get_object_stage_duration_seconds_bucket{stage=\"total\"}[$__rate_interval])) by (le, path))",
-          "legendFormat": "p95 {{path}}",
-          "refId": "B"
-        },
-        {
-          "datasource": {
-            "type": "prometheus",
-            "uid": "${DS_PROMETHEUS}"
-          },
-          "expr": "histogram_quantile(0.99, sum(rate(rustfs_io_get_object_stage_duration_seconds_bucket{stage=\"total\"}[$__rate_interval])) by (le, path))",
-          "legendFormat": "p99 {{path}}",
-          "refId": "C"
-        }
-      ]
-    },
-    {
-      "datasource": {
-        "type": "prometheus",
-        "uid": "${DS_PROMETHEUS}"
-      },
-      "fieldConfig": {
-        "defaults": {
-          "unit": "percentunit",
-          "min": 0,
-          "max": 1,
-          "custom": {
-            "drawStyle": "line",
-            "lineInterpolation": "smooth",
-            "fillOpacity": 15,
-            "pointSize": 5,
-            "lineWidth": 1,
-            "showPoints": "auto",
-            "spanNulls": false,
-            "thresholdsStyle": {
-              "mode": "off"
-            }
-          },
-          "thresholds": {
-            "mode": "absolute",
-            "steps": [
-              {
-                "color": "green",
-                "value": null
-              },
-              {
-                "color": "yellow",
-                "value": 0.3
-              },
-              {
-                "color": "red",
-                "value": 0.7
-              }
-            ]
-          }
-        },
-        "overrides": []
-      },
-      "gridPos": {
-        "h": 8,
-        "w": 12,
-        "x": 12,
-        "y": 0
-      },
-      "id": 2,
-      "options": {
-        "reduceOptions": {
-          "values": false,
-          "calcs": ["lastNotNull"],
-          "fields": ""
-        },
-        "tooltip": {
-          "mode": "multi",
-          "sort": "desc"
-        },
-        "legend": {
-          "displayMode": "table",
-          "placement": "bottom",
-          "calcs": ["mean", "max"]
-        }
-      },
-      "title": "Early-Stop Hit Rate",
-      "type": "timeseries",
-      "targets": [
-        {
-          "datasource": {
-            "type": "prometheus",
-            "uid": "${DS_PROMETHEUS}"
-          },
-          "expr": "sum(rate(rustfs_io_get_object_metadata_early_stop_total{decision=\"hit\"}[$__rate_interval])) by (path) / clamp_min(sum(rate(rustfs_io_get_object_metadata_early_stop_total[$__rate_interval])) by (path), 1)",
-          "legendFormat": "hit rate {{path}}",
-          "refId": "A"
-        }
-      ]
-    },
-    {
-      "datasource": {
-        "type": "prometheus",
-        "uid": "${DS_PROMETHEUS}"
-      },
-      "fieldConfig": {
-        "defaults": {
-          "unit": "percentunit",
-          "min": 0,
-          "max": 1,
-          "custom": {
-            "drawStyle": "line",
-            "lineInterpolation": "smooth",
-            "fillOpacity": 15,
-            "pointSize": 5,
-            "lineWidth": 1,
-            "showPoints": "auto",
-            "spanNulls": false,
-            "thresholdsStyle": {
-              "mode": "off"
-            }
-          },
-          "thresholds": {
-            "mode": "absolute",
-            "steps": [
-              {
-                "color": "green",
-                "value": null
-              }
-            ]
-          }
-        },
-        "overrides": []
-      },
-      "gridPos": {
-        "h": 8,
-        "w": 12,
-        "x": 0,
-        "y": 8
-      },
-      "id": 3,
-      "options": {
-        "reduceOptions": {
-          "values": false,
-          "calcs": ["lastNotNull"],
-          "fields": ""
-        },
-        "tooltip": {
-          "mode": "multi",
-          "sort": "desc"
-        },
-        "legend": {
-          "displayMode": "table",
-          "placement": "bottom",
-          "calcs": ["mean", "max"]
-        }
-      },
-      "title": "Codec Streaming Usage Rate",
-      "type": "timeseries",
-      "targets": [
-        {
-          "datasource": {
-            "type": "prometheus",
-            "uid": "${DS_PROMETHEUS}"
-          },
-          "expr": "sum(rate(rustfs_io_get_object_codec_streaming_decision_total[$__rate_interval])) by (decision) / clamp_min(sum(rate(rustfs_io_get_object_codec_streaming_decision_total[$__rate_interval])), 1)",
-          "legendFormat": "codec_streaming {{decision}}",
-          "refId": "A"
-        },
-        {
-          "datasource": {
-            "type": "prometheus",
-            "uid": "${DS_PROMETHEUS}"
-          },
-          "expr": "sum(rate(rustfs_io_get_object_stream_strategy_total[$__rate_interval])) by (strategy) / clamp_min(sum(rate(rustfs_io_get_object_stream_strategy_total[$__rate_interval])), 1)",
-          "legendFormat": "stream_strategy {{strategy}}",
-          "refId": "B"
-        }
-      ]
-    },
-    {
-      "datasource": {
-        "type": "prometheus",
-        "uid": "${DS_PROMETHEUS}"
-      },
-      "fieldConfig": {
-        "defaults": {
-          "unit": "ops",
-          "custom": {
-            "drawStyle": "bars",
-            "fillOpacity": 80,
-            "lineWidth": 0,
-            "pointSize": 5,
-            "showPoints": "never",
-            "spanNulls": false,
-            "stacking": {
-              "mode": "normal",
-              "group": "A"
-            },
-            "thresholdsStyle": {
-              "mode": "off"
-            }
-          },
-          "thresholds": {
-            "mode": "absolute",
-            "steps": [
-              {
-                "color": "green",
-                "value": null
-              },
-              {
-                "color": "red",
-                "value": 1
-              }
-            ]
-          }
-        },
-        "overrides": []
-      },
-      "gridPos": {
-        "h": 8,
-        "w": 12,
-        "x": 12,
-        "y": 8
-      },
-      "id": 4,
-      "options": {
-        "reduceOptions": {
-          "values": false,
-          "calcs": ["lastNotNull"],
-          "fields": ""
-        },
-        "tooltip": {
-          "mode": "multi",
-          "sort": "desc"
-        },
-        "legend": {
-          "displayMode": "table",
-          "placement": "bottom",
-          "calcs": ["sum"]
-        }
-      },
-      "title": "Pipeline Failure Rate by Stage",
-      "type": "timeseries",
-      "targets": [
-        {
-          "datasource": {
-            "type": "prometheus",
-            "uid": "${DS_PROMETHEUS}"
-          },
-          "expr": "sum(rate(rustfs_io_get_object_pipeline_failures_total[$__rate_interval])) by (stage, reason)",
-          "legendFormat": "{{stage}} / {{reason}}",
-          "refId": "A"
-        }
-      ]
-    },
-    {
-      "datasource": {
-        "type": "prometheus",
-        "uid": "${DS_PROMETHEUS}"
-      },
-      "fieldConfig": {
-        "defaults": {
-          "unit": "reqps",
-          "custom": {
-            "drawStyle": "line",
-            "lineInterpolation": "smooth",
-            "fillOpacity": 10,
-            "pointSize": 5,
-            "lineWidth": 1,
-            "showPoints": "auto",
-            "spanNulls": false,
-            "thresholdsStyle": {
-              "mode": "off"
-            }
-          },
-          "thresholds": {
-            "mode": "absolute",
-            "steps": [
-              {
-                "color": "green",
-                "value": null
-              }
-            ]
-          }
-        },
-        "overrides": []
-      },
-      "gridPos": {
-        "h": 8,
-        "w": 12,
-        "x": 0,
-        "y": 16
-      },
-      "id": 5,
-      "options": {
-        "reduceOptions": {
-          "values": false,
-          "calcs": ["lastNotNull"],
-          "fields": ""
-        },
-        "tooltip": {
-          "mode": "multi",
-          "sort": "desc"
-        },
-        "legend": {
-          "displayMode": "table",
-          "placement": "bottom",
-          "calcs": ["mean", "max"]
-        }
-      },
-      "title": "GET Request Rate by Path",
-      "type": "timeseries",
-      "targets": [
-        {
-          "datasource": {
-            "type": "prometheus",
-            "uid": "${DS_PROMETHEUS}"
-          },
-          "expr": "sum(rate(rustfs_io_get_object_reader_path_total[$__rate_interval])) by (path)",
-          "legendFormat": "{{path}}",
-          "refId": "A"
-        }
-      ]
-    },
-    {
-      "datasource": {
-        "type": "prometheus",
-        "uid": "${DS_PROMETHEUS}"
-      },
-      "fieldConfig": {
-        "defaults": {
-          "unit": "ops",
-          "custom": {
-            "drawStyle": "line",
-            "lineInterpolation": "smooth",
-            "fillOpacity": 10,
-            "pointSize": 5,
-            "lineWidth": 1,
-            "showPoints": "auto",
-            "spanNulls": false,
-            "thresholdsStyle": {
-              "mode": "off"
-            }
-          },
-          "thresholds": {
-            "mode": "absolute",
-            "steps": [
-              {
-                "color": "green",
-                "value": null
-              }
-            ]
-          }
-        },
-        "overrides": []
-      },
-      "gridPos": {
-        "h": 8,
-        "w": 12,
-        "x": 12,
-        "y": 16
-      },
-      "id": 6,
-      "options": {
-        "reduceOptions": {
-          "values": false,
-          "calcs": ["lastNotNull"],
-          "fields": ""
-        },
-        "tooltip": {
-          "mode": "multi",
-          "sort": "desc"
-        },
-        "legend": {
-          "displayMode": "table",
-          "placement": "bottom",
-          "calcs": ["mean", "max"]
-        }
-      },
-      "title": "GET Total Latency (p50 / p95 / p99)",
-      "type": "timeseries",
-      "targets": [
-        {
-          "datasource": {
-            "type": "prometheus",
-            "uid": "${DS_PROMETHEUS}"
-          },
-          "expr": "histogram_quantile(0.50, sum(rate(rustfs_io_get_object_total_duration_seconds_bucket[$__rate_interval])) by (le))",
-          "legendFormat": "p50",
-          "refId": "A"
-        },
-        {
-          "datasource": {
-            "type": "prometheus",
-            "uid": "${DS_PROMETHEUS}"
-          },
-          "expr": "histogram_quantile(0.95, sum(rate(rustfs_io_get_object_total_duration_seconds_bucket[$__rate_interval])) by (le))",
-          "legendFormat": "p95",
-          "refId": "B"
-        },
-        {
-          "datasource": {
-            "type": "prometheus",
-            "uid": "${DS_PROMETHEUS}"
-          },
-          "expr": "histogram_quantile(0.99, sum(rate(rustfs_io_get_object_total_duration_seconds_bucket[$__rate_interval])) by (le))",
-          "legendFormat": "p99",
-          "refId": "C"
-        }
-      ]
-    }
-  ],
-  "refresh": "30s",
-  "schemaVersion": 38,
-  "style": "dark",
-  "tags": ["rustfs", "get-optimization"],
-  "templating": {
-    "list": [
-      {
-        "current": {
-          "selected": false,
-          "text": "Prometheus",
-          "value": "Prometheus"
-        },
-        "hide": 0,
-        "includeAll": false,
-        "multi": false,
-        "name": "DS_PROMETHEUS",
-        "options": [],
-        "query": "prometheus",
-        "refresh": 1,
-        "regex": "",
-        "skipUrlSync": false,
-        "type": "datasource"
-      }
-    ]
-  },
-  "time": {
-    "from": "now-1h",
-    "to": "now"
-  },
-  "timepicker": {},
-  "timezone": "",
-  "title": "RustFS GET Rollout Health",
-  "uid": "rustfs-get-rollout-health",
-  "version": 1
-}

.docker/observability/grafana/dashboards/grafana-put-performance-attribution.json

@@ -1,534 +0,0 @@
-{
-  "annotations": {
-    "list": []
-  },
-  "editable": true,
-  "fiscalYearStartMonth": 0,
-  "graphTooltip": 1,
-  "id": null,
-  "links": [],
-  "liveNow": false,
-  "panels": [
-    {
-      "datasource": {
-        "type": "prometheus",
-        "uid": "${DS_PROMETHEUS}"
-      },
-      "fieldConfig": {
-        "defaults": {
-          "unit": "ops",
-          "custom": {
-            "drawStyle": "line",
-            "lineInterpolation": "smooth",
-            "fillOpacity": 10,
-            "pointSize": 5,
-            "lineWidth": 1,
-            "showPoints": "auto",
-            "spanNulls": false,
-            "thresholdsStyle": {
-              "mode": "off"
-            }
-          },
-          "thresholds": {
-            "mode": "absolute",
-            "steps": [
-              {
-                "color": "green",
-                "value": null
-              }
-            ]
-          }
-        },
-        "overrides": []
-      },
-      "gridPos": {
-        "h": 8,
-        "w": 12,
-        "x": 0,
-        "y": 0
-      },
-      "id": 1,
-      "options": {
-        "legend": {
-          "calcs": [
-            "mean",
-            "max"
-          ],
-          "displayMode": "table",
-          "placement": "bottom"
-        },
-        "reduceOptions": {
-          "calcs": [
-            "lastNotNull"
-          ],
-          "fields": "",
-          "values": false
-        },
-        "tooltip": {
-          "mode": "multi",
-          "sort": "desc"
-        }
-      },
-      "targets": [
-        {
-          "datasource": {
-            "type": "prometheus",
-            "uid": "${DS_PROMETHEUS}"
-          },
-          "expr": "sum by (path, eager_status, size_bucket, buffer_bucket, large_concurrency_tuning) (rate(rustfs_s3_put_object_diagnostics_total[$__rate_interval])) or vector(0)",
-          "legendFormat": "{{path}} / {{eager_status}} / {{size_bucket}} / {{buffer_bucket}} / large={{large_concurrency_tuning}}",
-          "refId": "A"
-        }
-      ],
-      "title": "PUT Diagnostics Decision Rate",
-      "type": "timeseries"
-    },
-    {
-      "datasource": {
-        "type": "prometheus",
-        "uid": "${DS_PROMETHEUS}"
-      },
-      "fieldConfig": {
-        "defaults": {
-          "unit": "ops",
-          "custom": {
-            "drawStyle": "line",
-            "lineInterpolation": "smooth",
-            "fillOpacity": 10,
-            "pointSize": 5,
-            "lineWidth": 1,
-            "showPoints": "auto",
-            "spanNulls": false,
-            "thresholdsStyle": {
-              "mode": "off"
-            }
-          },
-          "thresholds": {
-            "mode": "absolute",
-            "steps": [
-              {
-                "color": "green",
-                "value": null
-              }
-            ]
-          }
-        },
-        "overrides": []
-      },
-      "gridPos": {
-        "h": 8,
-        "w": 12,
-        "x": 12,
-        "y": 0
-      },
-      "id": 2,
-      "options": {
-        "legend": {
-          "calcs": [
-            "mean",
-            "max"
-          ],
-          "displayMode": "table",
-          "placement": "bottom"
-        },
-        "reduceOptions": {
-          "calcs": [
-            "lastNotNull"
-          ],
-          "fields": "",
-          "values": false
-        },
-        "tooltip": {
-          "mode": "multi",
-          "sort": "desc"
-        }
-      },
-      "targets": [
-        {
-          "datasource": {
-            "type": "prometheus",
-            "uid": "${DS_PROMETHEUS}"
-          },
-          "expr": "sum by (path) (rate(rustfs_s3_put_object_path_total[$__rate_interval])) or vector(0)",
-          "legendFormat": "{{path}}",
-          "refId": "A"
-        }
-      ],
-      "title": "PUT Path Rate",
-      "type": "timeseries"
-    },
-    {
-      "datasource": {
-        "type": "prometheus",
-        "uid": "${DS_PROMETHEUS}"
-      },
-      "fieldConfig": {
-        "defaults": {
-          "unit": "ms",
-          "custom": {
-            "drawStyle": "line",
-            "lineInterpolation": "smooth",
-            "fillOpacity": 10,
-            "pointSize": 5,
-            "lineWidth": 1,
-            "showPoints": "auto",
-            "spanNulls": false,
-            "thresholdsStyle": {
-              "mode": "off"
-            }
-          },
-          "thresholds": {
-            "mode": "absolute",
-            "steps": [
-              {
-                "color": "green",
-                "value": null
-              }
-            ]
-          }
-        },
-        "overrides": []
-      },
-      "gridPos": {
-        "h": 8,
-        "w": 12,
-        "x": 0,
-        "y": 8
-      },
-      "id": 3,
-      "options": {
-        "legend": {
-          "calcs": [
-            "mean",
-            "max"
-          ],
-          "displayMode": "table",
-          "placement": "bottom"
-        },
-        "reduceOptions": {
-          "calcs": [
-            "lastNotNull"
-          ],
-          "fields": "",
-          "values": false
-        },
-        "tooltip": {
-          "mode": "multi",
-          "sort": "desc"
-        }
-      },
-      "targets": [
-        {
-          "datasource": {
-            "type": "prometheus",
-            "uid": "${DS_PROMETHEUS}"
-          },
-          "expr": "histogram_quantile(0.95, sum by (stage, le) (rate(rustfs_s3_put_object_stage_duration_ms_bucket{stage=~\"ingress_prepare|set_disk_writer_setup|set_disk_encode|set_disk_rename|set_disk_old_data_cleanup|multipart_ingress_prepare|multipart_set_disk_writer_setup|multipart_set_disk_encode|multipart_complete_tail\"}[$__rate_interval]))) or vector(0)",
-          "legendFormat": "p95 {{stage}}",
-          "refId": "A"
-        },
-        {
-          "datasource": {
-            "type": "prometheus",
-            "uid": "${DS_PROMETHEUS}"
-          },
-          "expr": "histogram_quantile(0.99, sum by (stage, le) (rate(rustfs_s3_put_object_stage_duration_ms_bucket{stage=~\"ingress_prepare|set_disk_writer_setup|set_disk_encode|set_disk_rename|set_disk_old_data_cleanup|multipart_ingress_prepare|multipart_set_disk_writer_setup|multipart_set_disk_encode|multipart_complete_tail\"}[$__rate_interval]))) or vector(0)",
-          "legendFormat": "p99 {{stage}}",
-          "refId": "B"
-        }
-      ],
-      "title": "PUT Hot Stage Latency",
-      "type": "timeseries"
-    },
-    {
-      "datasource": {
-        "type": "prometheus",
-        "uid": "${DS_PROMETHEUS}"
-      },
-      "fieldConfig": {
-        "defaults": {
-          "unit": "bytes",
-          "custom": {
-            "drawStyle": "line",
-            "lineInterpolation": "smooth",
-            "fillOpacity": 10,
-            "pointSize": 5,
-            "lineWidth": 1,
-            "showPoints": "auto",
-            "spanNulls": false,
-            "thresholdsStyle": {
-              "mode": "off"
-            }
-          },
-          "thresholds": {
-            "mode": "absolute",
-            "steps": [
-              {
-                "color": "green",
-                "value": null
-              }
-            ]
-          }
-        },
-        "overrides": []
-      },
-      "gridPos": {
-        "h": 8,
-        "w": 12,
-        "x": 12,
-        "y": 8
-      },
-      "id": 4,
-      "options": {
-        "legend": {
-          "calcs": [
-            "mean",
-            "max"
-          ],
-          "displayMode": "table",
-          "placement": "bottom"
-        },
-        "reduceOptions": {
-          "calcs": [
-            "lastNotNull"
-          ],
-          "fields": "",
-          "values": false
-        },
-        "tooltip": {
-          "mode": "multi",
-          "sort": "desc"
-        }
-      },
-      "targets": [
-        {
-          "datasource": {
-            "type": "prometheus",
-            "uid": "${DS_PROMETHEUS}"
-          },
-          "expr": "histogram_quantile(0.50, sum by (path, size_bucket, le) (rate(rustfs_s3_put_object_selected_buffer_size_bytes_bucket[$__rate_interval]))) or vector(0)",
-          "legendFormat": "p50 {{path}} / {{size_bucket}}",
-          "refId": "A"
-        },
-        {
-          "datasource": {
-            "type": "prometheus",
-            "uid": "${DS_PROMETHEUS}"
-          },
-          "expr": "histogram_quantile(0.95, sum by (path, size_bucket, le) (rate(rustfs_s3_put_object_selected_buffer_size_bytes_bucket[$__rate_interval]))) or vector(0)",
-          "legendFormat": "p95 {{path}} / {{size_bucket}}",
-          "refId": "B"
-        }
-      ],
-      "title": "PUT Selected Buffer Size",
-      "type": "timeseries"
-    },
-    {
-      "datasource": {
-        "type": "prometheus",
-        "uid": "${DS_PROMETHEUS}"
-      },
-      "fieldConfig": {
-        "defaults": {
-          "unit": "percentunit",
-          "min": 0,
-          "max": 1,
-          "custom": {
-            "drawStyle": "line",
-            "lineInterpolation": "smooth",
-            "fillOpacity": 15,
-            "pointSize": 5,
-            "lineWidth": 1,
-            "showPoints": "auto",
-            "spanNulls": false,
-            "thresholdsStyle": {
-              "mode": "off"
-            }
-          },
-          "thresholds": {
-            "mode": "absolute",
-            "steps": [
-              {
-                "color": "green",
-                "value": null
-              }
-            ]
-          }
-        },
-        "overrides": []
-      },
-      "gridPos": {
-        "h": 8,
-        "w": 12,
-        "x": 0,
-        "y": 16
-      },
-      "id": 5,
-      "options": {
-        "legend": {
-          "calcs": [
-            "mean",
-            "max"
-          ],
-          "displayMode": "table",
-          "placement": "bottom"
-        },
-        "reduceOptions": {
-          "calcs": [
-            "lastNotNull"
-          ],
-          "fields": "",
-          "values": false
-        },
-        "tooltip": {
-          "mode": "multi",
-          "sort": "desc"
-        }
-      },
-      "targets": [
-        {
-          "datasource": {
-            "type": "prometheus",
-            "uid": "${DS_PROMETHEUS}"
-          },
-          "expr": "sum(rate(rustfs_s3_put_object_zero_copy_eligible_total[$__rate_interval])) / clamp_min(sum(rate(rustfs_s3_put_object_total[$__rate_interval])), 1) or vector(0)",
-          "legendFormat": "eligible / total",
-          "refId": "A"
-        },
-        {
-          "datasource": {
-            "type": "prometheus",
-            "uid": "${DS_PROMETHEUS}"
-          },
-          "expr": "sum(rate(rustfs_s3_put_object_zero_copy_enabled_total[$__rate_interval])) / clamp_min(sum(rate(rustfs_s3_put_object_total[$__rate_interval])), 1) or vector(0)",
-          "legendFormat": "enabled / total",
-          "refId": "B"
-        }
-      ],
-      "title": "PUT Zero-Copy Eligibility Ratio",
-      "type": "timeseries"
-    },
-    {
-      "datasource": {
-        "type": "prometheus",
-        "uid": "${DS_PROMETHEUS}"
-      },
-      "fieldConfig": {
-        "defaults": {
-          "unit": "ops",
-          "custom": {
-            "drawStyle": "line",
-            "lineInterpolation": "smooth",
-            "fillOpacity": 10,
-            "pointSize": 5,
-            "lineWidth": 1,
-            "showPoints": "auto",
-            "spanNulls": false,
-            "thresholdsStyle": {
-              "mode": "off"
-            }
-          },
-          "thresholds": {
-            "mode": "absolute",
-            "steps": [
-              {
-                "color": "green",
-                "value": null
-              }
-            ]
-          }
-        },
-        "overrides": []
-      },
-      "gridPos": {
-        "h": 8,
-        "w": 12,
-        "x": 12,
-        "y": 16
-      },
-      "id": 6,
-      "options": {
-        "legend": {
-          "calcs": [
-            "mean",
-            "max"
-          ],
-          "displayMode": "table",
-          "placement": "bottom"
-        },
-        "reduceOptions": {
-          "calcs": [
-            "lastNotNull"
-          ],
-          "fields": "",
-          "values": false
-        },
-        "tooltip": {
-          "mode": "multi",
-          "sort": "desc"
-        }
-      },
-      "targets": [
-        {
-          "datasource": {
-            "type": "prometheus",
-            "uid": "${DS_PROMETHEUS}"
-          },
-          "expr": "sum(rate(rustfs_s3_put_object_total[$__rate_interval])) or vector(0)",
-          "legendFormat": "PUT total",
-          "refId": "A"
-        },
-        {
-          "datasource": {
-            "type": "prometheus",
-            "uid": "${DS_PROMETHEUS}"
-          },
-          "expr": "sum by (stage) (rate(rustfs_system_storage_erasure_write_quorum_failures_total[$__rate_interval])) or vector(0)",
-          "legendFormat": "write quorum failure {{stage}}",
-          "refId": "B"
-        }
-      ],
-      "title": "PUT Throughput and Quorum Failure Signals",
-      "type": "timeseries"
-    }
-  ],
-  "refresh": "30s",
-  "schemaVersion": 38,
-  "style": "dark",
-  "tags": [
-    "rustfs",
-    "put",
-    "performance",
-    "attribution"
-  ],
-  "templating": {
-    "list": [
-      {
-        "current": {
-          "selected": false,
-          "text": "Prometheus",
-          "value": "Prometheus"
-        },
-        "hide": 0,
-        "includeAll": false,
-        "multi": false,
-        "name": "DS_PROMETHEUS",
-        "options": [],
-        "query": "prometheus",
-        "refresh": 1,
-        "regex": "",
-        "skipUrlSync": false,
-        "type": "datasource"
-      }
-    ]
-  },
-  "time": {
-    "from": "now-1h",
-    "to": "now"
-  },
-  "timezone": "",
-  "title": "RustFS PUT Performance Attribution",
-  "uid": "rustfs-put-performance-attribution",
-  "version": 1,
-  "weekStart": ""
-}

.docker/observability/grafana/provisioning/dashboards/dashboard.yml

@@ -1,25 +0,0 @@
-# Copyright 2024 RustFS Team
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-
-apiVersion: 1
-
-providers:
-  - name: "default"
-    orgId: 1
-    folder: ""
-    type: file
-    disableDeletion: false
-    updateIntervalSeconds: 10
-    options:
-      path: /etc/grafana/dashboards

.docker/observability/grafana/provisioning/datasources/datasources.yaml

@@ -1,98 +0,0 @@
-# Copyright 2024 RustFS Team
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-
-apiVersion: 1
-
-datasources:
-  - name: Prometheus
-    type: prometheus
-    uid: prometheus
-    url: http://prometheus:9090
-    access: proxy
-    isDefault: true
-    editable: false
-    jsonData:
-      httpMethod: GET
-      exemplarTraceIdDestinations:
-        - name: trace_id
-          datasourceUid: tempo
-
-  - name: Tempo
-    type: tempo
-    uid: tempo
-    access: proxy
-    url: http://tempo:3200
-    isDefault: false
-    editable: false
-    jsonData:
-      httpMethod: GET
-      serviceMap:
-        datasourceUid: prometheus
-      tracesToLogs:
-        datasourceUid: loki
-        tags: [ 'job', 'instance', 'pod', 'namespace', 'service.name' ]
-        mappedTags: [ { key: 'service.name', value: 'app' } ]
-        spanStartTimeShift: '-1h'
-        spanEndTimeShift: '1h'
-        filterByTraceID: true
-        filterBySpanID: false
-      tracesToMetrics:
-        datasourceUid: prometheus
-        tags: [ { key: 'service.name' }, { key: 'job' } ]
-        queries:
-          - name: 'Service-Level Latency'
-            query: 'sum(rate(traces_spanmetrics_latency_bucket{$$__tags}[5m])) by (le)'
-          - name: 'Service-Level Calls'
-            query: 'sum(rate(traces_spanmetrics_calls_total{$$__tags}[5m]))'
-          - name: 'Service-Level Errors'
-            query: 'sum(rate(traces_spanmetrics_calls_total{status_code="ERROR", $$__tags}[5m]))'
-      nodeGraph:
-        enabled: true
-
-  - name: Loki
-    type: loki
-    uid: loki
-    url: http://loki:3100
-    basicAuth: false
-    isDefault: false
-    editable: false
-    jsonData:
-      derivedFields:
-        - datasourceUid: tempo
-          matcherRegex: 'trace_id=(\w+)'
-          name: 'TraceID'
-          url: '$${__value.raw}'
-
-  - name: Jaeger
-    type: jaeger
-    uid: jaeger
-    url: http://jaeger:16686
-    access: proxy
-    isDefault: false
-    editable: false
-    jsonData:
-      tracesToLogs:
-        datasourceUid: loki
-        tags: [ 'job', 'instance', 'pod', 'namespace', 'service.name' ]
-        mappedTags: [ { key: 'service.name', value: 'app' } ]
-        spanStartTimeShift: '1s'
-        spanEndTimeShift: '-1s'
-        filterByTraceID: true
-        filterBySpanID: false
-
-  - name: Pyroscope
-    type: grafana-pyroscope-datasource
-    url: http://pyroscope:4040
-    jsonData:
-      minStep: '15s'

.docker/observability/jaeger-config.yaml

@@ -0,0 +1,112 @@
+# Copyright 2024 RustFS Team
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+service:
+  extensions: [ jaeger_storage, jaeger_query, remote_sampling, healthcheckv2 ]
+  pipelines:
+    traces:
+      receivers: [ otlp, jaeger, zipkin ]
+      processors: [ batch, adaptive_sampling ]
+      exporters: [ jaeger_storage_exporter ]
+  telemetry:
+    resource:
+      service.name: jaeger
+    metrics:
+      level: detailed
+      readers:
+        - pull:
+            exporter:
+              prometheus:
+                host: 0.0.0.0
+                port: 8888
+    logs:
+      level: debug
+    # TODO Initialize telemetry tracer once OTEL released new feature.
+    # https://github.com/open-telemetry/opentelemetry-collector/issues/10663
+
+extensions:
+  healthcheckv2:
+    use_v2: true
+    http:
+
+  # pprof:
+  #   endpoint: 0.0.0.0:1777
+  # zpages:
+  #   endpoint: 0.0.0.0:55679
+
+  jaeger_query:
+    storage:
+      traces: some_store
+      traces_archive: another_store
+    ui:
+      config_file: ./cmd/jaeger/config-ui.json
+      log_access: true
+    # The maximum duration that is considered for clock skew adjustments.
+    # Defaults to 0 seconds, which means it's disabled.
+    max_clock_skew_adjust: 0s
+    grpc:
+      endpoint: 0.0.0.0:16685
+    http:
+      endpoint: 0.0.0.0:16686
+
+  jaeger_storage:
+    backends:
+      some_store:
+        memory:
+          max_traces: 1000000
+      another_store:
+        memory:
+          max_traces: 1000000
+    metric_backends:
+      some_metrics_storage:
+        prometheus:
+          endpoint: http://prometheus:9090
+          normalize_calls: true
+          normalize_duration: true
+
+  remote_sampling:
+    # You can either use file or adaptive sampling strategy in remote_sampling
+    # file:
+    #   path: ./cmd/jaeger/sampling-strategies.json
+    adaptive:
+      sampling_store: some_store
+      initial_sampling_probability: 0.1
+    http:
+    grpc:
+
+receivers:
+  otlp:
+    protocols:
+      grpc:
+      http:
+
+  jaeger:
+    protocols:
+      grpc:
+      thrift_binary:
+      thrift_compact:
+      thrift_http:
+
+  zipkin:
+
+processors:
+  batch:
+  # Adaptive Sampling Processor is required to support adaptive sampling.
+  # It expects remote_sampling extension with `adaptive:` config to be enabled.
+  adaptive_sampling:
+
+exporters:
+  jaeger_storage_exporter:
+    trace_storage: some_store
+

.docker/observability/jaeger.yaml

@@ -1,74 +0,0 @@
-# Copyright 2024 RustFS Team
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-
-service:
-  extensions: [jaeger_storage, jaeger_query]
-  pipelines:
-    traces:
-      receivers: [otlp]
-      processors: [batch]
-      exporters: [jaeger_storage_exporter, spanmetrics]
-    metrics/spanmetrics:
-      receivers: [spanmetrics]
-      exporters: [prometheus]
-  telemetry:
-    resource:
-      service.name: jaeger
-    metrics:
-      level: detailed
-      readers:
-        - pull:
-            exporter:
-              prometheus:
-                host: 0.0.0.0
-                port: 8888
-    logs:
-      level: DEBUG
-
-extensions:
-  jaeger_query:
-    storage:
-      traces: some_storage
-      metrics: some_metrics_storage
-  jaeger_storage:
-    backends:
-      some_storage:
-        memory:
-          max_traces: 100000
-    metric_backends:
-      some_metrics_storage:
-        prometheus:
-          endpoint: http://prometheus:9090
-          normalize_calls: true
-          normalize_duration: true
-
-connectors:
-  spanmetrics:
-
-receivers:
-  otlp:
-    protocols:
-      grpc:
-        endpoint: "0.0.0.0:4317"
-      http:
-        endpoint: "0.0.0.0:4318"
-
-processors:
-  batch:
-
-exporters:
-  jaeger_storage_exporter:
-    trace_storage: some_storage
-  prometheus:
-    endpoint: "0.0.0.0:8889"

.docker/observability/loki-config.yaml

@@ -11,21 +11,22 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
+
 auth_enabled: false
 
 server:
   http_listen_port: 3100
-  grpc_listen_port: 9095
-  log_level: info
+  grpc_listen_port: 9096
+  log_level: debug
   grpc_server_max_concurrent_streams: 1000
 
 common:
   instance_addr: 127.0.0.1
-  path_prefix: /loki
+  path_prefix: /tmp/loki
   storage:
     filesystem:
-      chunks_directory: /loki/chunks
-      rules_directory: /loki/rules
+      chunks_directory: /tmp/loki/chunks
+      rules_directory: /tmp/loki/rules
   replication_factor: 1
   ring:
     kvstore:
@@ -38,6 +39,9 @@ query_range:
         enabled: true
         max_size_mb: 100
 
+limits_config:
+  metric_aggregation_enabled: true
+
 schema_config:
   configs:
     - from: 2020-10-24
@@ -48,16 +52,26 @@ schema_config:
         prefix: index_
         period: 24h
 
-limits_config:
-  reject_old_samples: true
-  reject_old_samples_max_age: 168h
-  allow_structured_metadata: true
-  max_line_size: 256KB
-
 pattern_ingester:
   enabled: true
   metric_aggregation:
     loki_address: localhost:3100
 
+ruler:
+  alertmanager_url: http://localhost:9093
+
 frontend:
   encoding: protobuf
+
+# By default, Loki will send anonymous, but uniquely-identifiable usage and configuration
+# analytics to Grafana Labs. These statistics are sent to https://stats.grafana.org/
+#
+# Statistics help us better understand how Loki is used, and they show us performance
+# levels for most users. This helps us prioritize features and documentation.
+# For more information on what's sent, look at
+# https://github.com/grafana/loki/blob/main/pkg/analytics/stats.go
+# Refer to the buildReport method to see what goes into a report.
+#
+# If you would like to disable reporting, uncomment the following lines:
+#analytics:
+#  reporting_enabled: false

.docker/observability/otel-collector-config.yaml

@@ -15,102 +15,67 @@
 receivers:
   otlp:
     protocols:
-      grpc:
+      grpc: # OTLP gRPC 接收器
         endpoint: 0.0.0.0:4317
-      http:
+      http: # OTLP HTTP 接收器
         endpoint: 0.0.0.0:4318
 
 processors:
-  batch:
-    timeout: 1s
-    send_batch_size: 1024
+  batch: # 批处理处理器，提升吞吐量
+    timeout: 5s
+    send_batch_size: 1000
   memory_limiter:
     check_interval: 1s
-    limit_mib: 1024
-    spike_limit_mib: 256
-  transform/logs:
-    log_statements:
-      - context: log
-        statements:
-          - set(attributes["message"], body.string)
-          - set(attributes["log.body"], body.string)
+    limit_mib: 512
 
 exporters:
-  otlp/tempo:
-    endpoint: "tempo:4317"
+  otlp/traces: # OTLP 导出器，用于跟踪数据
+    endpoint: "jaeger:4317"  # Jaeger 的 OTLP gRPC 端点
+    tls:
+      insecure: true  # 开发环境禁用 TLS，生产环境需配置证书
+  otlp/tempo: # OTLP 导出器，用于跟踪数据
+    endpoint: "tempo:4317"  # tempo 的 OTLP gRPC 端点
+    tls:
+      insecure: true  # 开发环境禁用 TLS，生产环境需配置证书
+  prometheus: # Prometheus 导出器，用于指标数据
+    endpoint: "0.0.0.0:8889"  # Prometheus 刮取端点
+    namespace: "rustfs"  # 指标前缀
+    send_timestamps: true  # 发送时间戳
+    # enable_open_metrics: true
+  otlphttp/loki: # Loki 导出器，用于日志数据
+    # endpoint: "http://loki:3100/otlp/v1/logs"
+    endpoint: "http://loki:3100/otlp/v1/logs"
     tls:
       insecure: true
-    compression: gzip
-    retry_on_failure:
-      enabled: true
-      initial_interval: 1s
-      max_interval: 30s
-      max_elapsed_time: 300s
-    sending_queue:
-      enabled: true
-      num_consumers: 10
-      queue_size: 5000
-
-  otlp/jaeger:
-    endpoint: "jaeger:4317"
-    tls:
-      insecure: true
-    compression: gzip
-    retry_on_failure:
-      enabled: true
-      initial_interval: 1s
-      max_interval: 30s
-      max_elapsed_time: 300s
-    sending_queue:
-      enabled: true
-      num_consumers: 10
-      queue_size: 5000
-
-  prometheus:
-    endpoint: "0.0.0.0:8889"
-    send_timestamps: true
-    metric_expiration: 5m
-    resource_to_telemetry_conversion:
-      enabled: true
-
-  otlphttp/loki:
-    endpoint: "http://loki:3100/otlp"
-    tls:
-      insecure: true
-    compression: gzip
-
 extensions:
   health_check:
-    endpoint: 0.0.0.0:13133
   pprof:
-    endpoint: 0.0.0.0:1888
   zpages:
-    endpoint: 0.0.0.0:55679
-
 service:
-  extensions: [ health_check, pprof, zpages ]
+  extensions: [ health_check, pprof, zpages ]  # 启用扩展
   pipelines:
     traces:
       receivers: [ otlp ]
-      processors: [ memory_limiter, batch ]
-      exporters: [ otlp/tempo, otlp/jaeger ]
+      processors: [ memory_limiter,batch ]
+      exporters: [ otlp/traces,otlp/tempo ]
     metrics:
       receivers: [ otlp ]
       processors: [ batch ]
       exporters: [ prometheus ]
     logs:
       receivers: [ otlp ]
-      processors: [ batch, transform/logs ]
+      processors: [ batch ]
       exporters: [ otlphttp/loki ]
   telemetry:
     logs:
-      level: "info"
-      encoding: "json"
+      level: "info"  # Collector 日志级别
     metrics:
-      level: "normal"
+      level: "detailed" # 可以是 basic, normal, detailed
       readers:
-        - pull:
+        - periodic:
             exporter:
-              prometheus:
-                host: '0.0.0.0'
-                port: 8888
+              otlp:
+                protocol: http/protobuf
+                endpoint: http://otel-collector:4318
+
+

.docker/observability/prometheus-rules/rustfs-dashboard.yml

@@ -1,53 +0,0 @@
-groups:
-  - name: rustfs-dashboard
-    interval: 30s
-    rules:
-      - record: rustfs:http_server_requests:rate5m
-        expr: sum by (job) (rate(rustfs_http_server_requests_total[5m]))
-
-      - record: rustfs:http_server_request_duration_seconds:p50_5m
-        expr: histogram_quantile(0.50, sum by (le, job) (rate(rustfs_http_server_request_duration_seconds_bucket[5m])))
-      - record: rustfs:http_server_request_duration_seconds:p95_5m
-        expr: histogram_quantile(0.95, sum by (le, job) (rate(rustfs_http_server_request_duration_seconds_bucket[5m])))
-      - record: rustfs:http_server_request_duration_seconds:p99_5m
-        expr: histogram_quantile(0.99, sum by (le, job) (rate(rustfs_http_server_request_duration_seconds_bucket[5m])))
-
-      - record: rustfs:http_server_response_body_size_bytes:p50_5m
-        expr: histogram_quantile(0.50, sum by (le, job) (rate(rustfs_http_server_response_body_size_bytes_bucket[5m])))
-      - record: rustfs:http_server_response_body_size_bytes:p95_5m
-        expr: histogram_quantile(0.95, sum by (le, job) (rate(rustfs_http_server_response_body_size_bytes_bucket[5m])))
-      - record: rustfs:http_server_response_body_size_bytes:p99_5m
-        expr: histogram_quantile(0.99, sum by (le, job) (rate(rustfs_http_server_response_body_size_bytes_bucket[5m])))
-
-      - record: rustfs:log_cleaner_runs:rate15m
-        expr: sum by (job) (rate(rustfs_log_cleaner_runs_total[15m]))
-      - record: rustfs:log_cleaner_failure_ratio:rate5m
-        expr: sum by (job) (rate(rustfs_log_cleaner_run_failures_total[5m])) / clamp_min(sum by (job) (rate(rustfs_log_cleaner_runs_total[5m])), 1e-9)
-      - record: rustfs:log_cleaner_rotation_failure_ratio:rate5m
-        expr: sum by (job) (rate(rustfs_log_cleaner_rotation_failures_total[5m])) / clamp_min(sum by (job) (rate(rustfs_log_cleaner_rotation_total[5m])), 1e-9)
-      - record: rustfs:log_cleaner_rotation_duration_seconds:p95_5m
-        expr: histogram_quantile(0.95, sum by (le, job) (rate(rustfs_log_cleaner_rotation_duration_seconds_bucket[5m])))
-      - record: rustfs:log_cleaner_compress_duration_seconds:p95_5m
-        expr: histogram_quantile(0.95, sum by (le, job) (rate(rustfs_log_cleaner_compress_duration_seconds_bucket[5m])))
-
-      - record: rustfs:scanner_objects_scanned:rate5m
-        expr: sum by (job) (rate(rustfs_scanner_objects_scanned_total[5m]))
-      - record: rustfs:scanner_directories_scanned:rate5m
-        expr: sum by (job) (rate(rustfs_scanner_directories_scanned_total[5m]))
-      - record: rustfs:scanner_buckets_scanned:rate5m
-        expr: sum by (job) (rate(rustfs_scanner_buckets_scanned_total[5m]))
-      - record: rustfs:scanner_cycles_success:rate5m
-        expr: sum by (job) (rate(rustfs_scanner_cycles_total{result="success"}[5m]))
-
-      - record: rustfs:log_chain_op_event_mismatch:rate5m
-        expr: sum by (job) (rate(rustfs_log_chain_op_event_mismatch_total[5m]))
-
-      - alert: RustFSLogChainOpEventMismatchDetected
-        expr: rustfs:log_chain_op_event_mismatch:rate5m > 0
-        for: 10m
-        labels:
-          severity: warning
-          component: s3-log-chain
-        annotations:
-          summary: "RustFS log-chain op/event mismatch detected"
-          description: "job={{ $labels.job }} has non-zero rustfs_log_chain_op_event_mismatch_total rate for more than 10m. Check s3 op/event mapping changes."

.docker/observability/prometheus-rules/rustfs-get-optimization-alerts.yaml

@@ -1,260 +0,0 @@
-# =============================================================================
-# RustFS GET Optimization — Prometheus Alerting Rules
-# =============================================================================
-#
-# Import into Prometheus:
-#   1. Copy this file to your Prometheus rules directory
-#   2. Add to prometheus.yml:
-#        rule_files:
-#          - "prometheus-alert-rules.yaml"
-#   3. Validate: promtool check rules prometheus-alert-rules.yaml
-#   4. Reload:   curl -X POST http://localhost:9090/-/reload
-#
-# All metric names match those registered in crates/io-metrics/src/lib.rs
-# and documented in crates/ecstore/src/diagnostics/get.rs.
-#
-# Baseline comparison uses "offset 1d" — adjust to "offset 7d" for weekly
-# seasonality if your traffic pattern varies by day of week.
-# =============================================================================
-
-groups:
-  # ==========================================================================
-  # Critical alerts — immediate action required
-  # ==========================================================================
-  - name: rustfs-get-optimization-critical
-    interval: 30s
-    rules:
-      # ------------------------------------------------------------------
-      # 1. GetP99Regression
-      #    GET p99 latency exceeds 2x the baseline (same time yesterday)
-      #    sustained for 10 minutes.
-      #    Action: Roll back the GET optimization immediately.
-      # ------------------------------------------------------------------
-      - alert: GetP99Regression
-        expr: |
-          histogram_quantile(0.99,
-            sum(rate(rustfs_io_get_object_total_duration_seconds_bucket[5m])) by (le)
-          )
-          >
-          2
-          *
-          histogram_quantile(0.99,
-            sum(rate(rustfs_io_get_object_total_duration_seconds_bucket[5m] offset 1d)) by (le)
-          )
-        for: 10m
-        labels:
-          severity: critical
-          team: rustfs-storage
-          area: get-optimization
-        annotations:
-          summary: "GET p99 latency regression detected (>2x baseline for 10m)"
-          description: >-
-            The 99th-percentile GET object latency is {{ $value | humanizeDuration }}
-            which is more than double the baseline measured 24 hours ago.
-            This indicates a severe performance regression introduced by
-            a recent GET optimization change.
-          runbook_url: "https://internal.wiki/runbooks/rustfs/get-p99-regression"
-          action: >
-            1. Verify the regression is not caused by external factors
-               (disk health, network, load spike).
-            2. If confirmed optimization-related, roll back:
-               - Set RUSTFS_GET_CODEC_STREAMING=0
-               - Set RUSTFS_GET_METADATA_EARLY_STOP=0
-               - Restart affected nodes.
-            3. Collect flamegraphs and open a P0 incident.
-
-      # ------------------------------------------------------------------
-      # 2. PipelineFailureSpike
-      #    Pipeline failure rate exceeds 5x the baseline sustained for
-      #    5 minutes.  Covers all failure reasons: bitrot_mismatch,
-      #    decode_error, downstream_closed, io, read_quorum, timeout, etc.
-      #    Action: Investigate pipeline health and roll back if needed.
-      # ------------------------------------------------------------------
-      - alert: PipelineFailureSpike
-        expr: |
-          sum(rate(rustfs_io_get_object_pipeline_failures_total[5m]))
-          >
-          5
-          *
-          sum(rate(rustfs_io_get_object_pipeline_failures_total[5m] offset 1d))
-        for: 5m
-        labels:
-          severity: critical
-          team: rustfs-storage
-          area: get-optimization
-        annotations:
-          summary: "GET pipeline failure rate spike (>5x baseline for 5m)"
-          description: >-
-            The GET pipeline failure rate is {{ $value | printf "%.2f" }}/s,
-            more than 5x the baseline from 24 hours ago.
-            Failure reasons may include: bitrot_mismatch, decode_error,
-            downstream_closed, io, range_or_length_invalid, read_quorum,
-            short_read, timeout, unknown.
-          runbook_url: "https://internal.wiki/runbooks/rustfs/pipeline-failure-spike"
-          action: >
-            1. Check Grafana "GET Data Integrity" dashboard for failure
-               breakdown by reason label.
-            2. If decode_error or bitrot_mismatch dominates, stop
-               optimization and investigate data integrity.
-            3. If io or timeout dominates, check disk and network health.
-            4. Roll back optimization if failures persist.
-
-      # ------------------------------------------------------------------
-      # 3. BitrotMismatchSpike
-      #    Bitrot verification mismatch rate exceeds 3x baseline for
-      #    5 minutes.  This is a data-integrity signal — shard checksums
-      #    do not match after read.
-      #
-      #    The "bitrot_mismatch" reason is recorded on the
-      #    rustfs_io_get_object_pipeline_failures_total counter when a
-      #    StorageError::FileCorrupt or DiskError::FileCorrupt /
-      #    DiskError::PartMissingOrCorrupt is classified during the GET
-      #    pipeline (see classify_storage_error / classify_disk_error in
-      #    crates/ecstore/src/diagnostics/get.rs).
-      #
-      #    Action: Stop optimization, investigate data integrity urgently.
-      # ------------------------------------------------------------------
-      - alert: BitrotMismatchSpike
-        expr: |
-          sum(rate(rustfs_io_get_object_pipeline_failures_total{reason="bitrot_mismatch"}[5m]))
-          >
-          3
-          *
-          sum(rate(rustfs_io_get_object_pipeline_failures_total{reason="bitrot_mismatch"}[5m] offset 1d))
-        for: 5m
-        labels:
-          severity: critical
-          team: rustfs-storage
-          area: get-optimization
-        annotations:
-          summary: "Bitrot mismatch rate spike (>3x baseline for 5m)"
-          description: >-
-            The rate of pipeline failures classified as bitrot_mismatch is
-            {{ $value | printf "%.2f" }}/s, more than 3x the baseline from
-            24 hours ago.  This indicates shard checksum verification
-            failures (FileCorrupt / PartMissingOrCorrupt) which may point
-            to data corruption introduced by the GET optimization pipeline
-            (e.g., incorrect decode, buffer reuse bug).
-          runbook_url: "https://internal.wiki/runbooks/rustfs/bitrot-mismatch-spike"
-          action: >
-            1. Immediately disable codec streaming:
-               RUSTFS_GET_CODEC_STREAMING=0
-            2. Run "mc admin scan" on affected buckets to verify on-disk
-               integrity independent of the GET path.
-            3. Compare xl.meta checksums across erasure shards.
-            4. If corruption confirmed, initiate data recovery from parity.
-            5. Do NOT re-enable optimization until root cause is identified.
-
-  # ==========================================================================
-  # Warning alerts — investigation needed
-  # ==========================================================================
-  - name: rustfs-get-optimization-warning
-    interval: 30s
-    rules:
-      # ------------------------------------------------------------------
-      # 4. EarlyStopInsufficientQuorum
-      #    The metadata early-stop path is hitting "insufficient_quorum"
-      #    at a rate above 0.1/s for 5 minutes.  This means too many
-      #    disks are failing to return valid metadata in time.
-      #    Action: Check disk health and metadata fanout latency.
-      # ------------------------------------------------------------------
-      - alert: EarlyStopInsufficientQuorum
-        expr: |
-          sum(rate(rustfs_io_get_object_metadata_early_stop_total{reason="insufficient_quorum"}[5m]))
-          > 0.1
-        for: 5m
-        labels:
-          severity: warning
-          team: rustfs-storage
-          area: get-optimization
-        annotations:
-          summary: "Early-stop insufficient quorum rate elevated (>0.1/s for 5m)"
-          description: >-
-            The metadata early-stop path is returning "insufficient_quorum"
-            at {{ $value | printf "%.3f" }}/s.  This means the bounded
-            metadata fanout cannot gather enough valid responses before
-            the quorum deadline, suggesting disk or network issues.
-          runbook_url: "https://internal.wiki/runbooks/rustfs/early-stop-quorum"
-          action: >
-            1. Check disk health: mc admin info --json | jq '.disks'
-            2. Review rustfs_io_get_object_metadata_response_total by
-               outcome (error, timeout, disk_not_found) in Grafana.
-            3. Check rustfs_io_disk_permit_wait_duration_seconds for
-               I/O scheduler saturation.
-            4. If disks are healthy, consider increasing the early-stop
-               timeout or temporarily disabling early-stop.
-
-      # ------------------------------------------------------------------
-      # 5. CodecStreamingFallbackSpike
-      #    The codec streaming fallback rate is >10x baseline for 10
-      #    minutes.  This means the optimized codec streaming path is
-      #    being bypassed much more often than expected.
-      #    Action: Check fallback reasons and object eligibility.
-      # ------------------------------------------------------------------
-      - alert: CodecStreamingFallbackSpike
-        expr: |
-          sum(rate(rustfs_io_get_object_codec_streaming_fallback_total[5m]))
-          >
-          10
-          *
-          sum(rate(rustfs_io_get_object_codec_streaming_fallback_total[5m] offset 1d))
-        for: 10m
-        labels:
-          severity: warning
-          team: rustfs-storage
-          area: get-optimization
-        annotations:
-          summary: "Codec streaming fallback rate spike (>10x baseline for 10m)"
-          description: >-
-            The codec streaming fallback rate is {{ $value | printf "%.2f" }}/s,
-            more than 10x the baseline from 24 hours ago.  Fallback reasons
-            are labeled by "reason" — check Grafana for breakdown.
-            Common reasons: object too small, multipart not supported,
-            unsupported erasure layout, feature flag disabled.
-          runbook_url: "https://internal.wiki/runbooks/rustfs/codec-fallback-spike"
-          action: >
-            1. Query by reason label:
-               sum by (reason) (rate(rustfs_io_get_object_codec_streaming_fallback_total[5m]))
-            2. If dominated by a single reason, investigate why that
-               condition became more frequent (e.g., workload change,
-               configuration drift).
-            3. Cross-reference with rustfs_io_get_object_reader_path_total
-               to verify the fallback path (legacy_duplex) is healthy.
-            4. If fallback is expected (e.g., workload shifted to small
-               objects), update the alert baseline.
-
-      # ------------------------------------------------------------------
-      # 6. IoQueueSaturation
-      #    I/O queue utilization exceeds 90% for 5 minutes.  High
-      #    utilization causes disk permit wait latency to increase and
-      #    can cascade into pipeline timeouts.
-      #    Action: Check disk load and consider reducing concurrency.
-      # ------------------------------------------------------------------
-      - alert: IoQueueSaturation
-        expr: |
-          rustfs_io_queue_utilization_percent > 90
-        for: 5m
-        labels:
-          severity: warning
-          team: rustfs-storage
-          area: get-optimization
-        annotations:
-          summary: "I/O queue utilization >90% for 5m"
-          description: >-
-            The I/O queue utilization is {{ $value | printf "%.1f" }}%,
-            sustained above 90% for 5 minutes.  This indicates the disk
-            I/O scheduler is near saturation, which will increase
-            rustfs_io_disk_permit_wait_duration_seconds and may trigger
-            pipeline timeouts.
-          runbook_url: "https://internal.wiki/runbooks/rustfs/io-queue-saturation"
-          action: >
-            1. Check disk I/O metrics (iostat, node_exporter) for
-               individual disk saturation.
-            2. Review rustfs_io_queue_permits_in_use vs
-               rustfs_io_queue_permits_available for permit exhaustion.
-            3. Check rustfs_io_starvation_events for priority starvation.
-            4. If GET optimization increased concurrency, consider:
-               - Reducing RUSTFS_GET_PIPELINE_PARALLELISM
-               - Lowering RUSTFS_IO_QUEUE_PERMITS
-            5. If caused by background operations (ILM, healing), throttle
-               those before adjusting GET concurrency.

.docker/observability/prometheus.yml

@@ -13,72 +13,16 @@
 # limitations under the License.
 
 global:
-  scrape_interval: 15s # Evaluate rules every 15 seconds. The default is every 1 minute.
-  evaluation_interval: 15s
-  external_labels:
-    cluster: 'rustfs-dev'  # Label to identify the cluster
-    replica: '1'  # Replica identifier
-
-rule_files:
-  - /etc/prometheus/rules/*.yml
+  scrape_interval: 5s  # 刮取间隔
 
 scrape_configs:
   - job_name: 'otel-collector'
     static_configs:
-      - targets: [ 'otel-collector:8888' ]  # Scrape metrics from Collector
-    scrape_interval: 10s
-
-  - job_name: 'rustfs-app-metrics'
+      - targets: [ 'otel-collector:8888' ]  # 从 Collector 刮取指标
+  - job_name: 'otel-metrics'
     static_configs:
-      - targets: [ 'otel-collector:8889' ]  # Application indicators
-    scrape_interval: 15s
-    metric_relabel_configs:
-      - source_labels: [ __name__ ]
-        regex: 'go_.*'
-        action: drop  # Drop Go runtime metrics if not needed
-
+      - targets: [ 'otel-collector:8889' ]  # 应用指标
   - job_name: 'tempo'
     static_configs:
-      - targets: [ 'tempo:3200' ]  # Scrape metrics from Tempo
-
-  - job_name: 'jaeger'
-    static_configs:
-      - targets: [ 'jaeger:14269' ]  # Jaeger admin port (14269 is standard for admin/metrics)
-
-  - job_name: 'loki'
-    static_configs:
-      - targets: [ 'loki:3100' ]
-
-  - job_name: 'prometheus'
-    static_configs:
-      - targets: [ 'localhost:9090' ]
-
-  - job_name: 'vulture'
-    static_configs:
-      - targets:
-          - 'vulture:8080'
-
-otlp:
-  promote_resource_attributes:
-    - service.instance.id
-    - service.name
-    - service.namespace
-    - cloud.availability_zone
-    - cloud.region
-    - container.name
-    - deployment.environment.name
-    - k8s.cluster.name
-    - k8s.container.name
-    - k8s.cronjob.name
-    - k8s.daemonset.name
-    - k8s.deployment.name
-    - k8s.job.name
-    - k8s.namespace.name
-    - k8s.pod.name
-    - k8s.replicaset.name
-    - k8s.statefulset.name
-  translation_strategy: NoUTF8EscapingWithSuffixes
-
-storage:
-  tsdb:
-    out_of_order_time_window: 30m
+      - targets: [ 'tempo:3200' ]
+      

.docker/observability/redpanda-console.yaml

@@ -1,3 +0,0 @@
-kafka:
-  brokers:
-    - redpanda:9092

.docker/observability/tempo-data/.gitignore

@@ -0,0 +1 @@
+*

.docker/observability/tempo-ha.yaml

@@ -1,286 +0,0 @@
-# Copyright 2024 RustFS Team
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-
-# High Availability Tempo Configuration for docker-compose-example-for-rustfs.yml
-# Features:
-# - Distributed architecture with multiple components
-# - Kafka-based ingestion for fault tolerance
-# - Replication factor of 3 for data resilience
-# - Query frontend for load balancing
-# - Metrics generation from traces
-# - WAL for durability
-
-partition_ring_live_store: true
-stream_over_http_enabled: true
-
-server:
-  http_listen_port: 3200
-  http_server_read_timeout: 30s
-  http_server_write_timeout: 30s
-  grpc_server_max_recv_msg_size: 4194304  # 4MB
-  grpc_server_max_send_msg_size: 4194304
-  log_level: info
-  log_format: json
-
-# Memberlist configuration for distributed mode
-memberlist:
-  node_name: tempo
-  bind_port: 7946
-  join_members:
-    - tempo:7946
-  retransmit_factor: 4
-  node_timeout: 15s
-  retransmit_interval: 300ms
-  dead_node_reclaim_time: 30s
-
-# Distributor configuration - receives traces and routes to ingesters
-distributor:
-  ingester_write_path_enabled: true
-  kafka_write_path_enabled: true
-  rate_limit_bytes: 10MB
-  rate_limit_enabled: true
-  receivers:
-    otlp:
-      protocols:
-        grpc:
-          endpoint: "0.0.0.0:4317"
-          max_concurrent_streams: 0
-          max_receive_message_size: 4194304
-        http:
-          endpoint: "0.0.0.0:4318"
-          cors:
-            allowed_origins:
-              - "*"
-            max_age: 86400
-    jaeger:
-      protocols:
-        grpc:
-          endpoint: "0.0.0.0:14250"
-        thrift_http:
-          endpoint: "0.0.0.0:14268"
-    zipkin:
-      endpoint: "0.0.0.0:9411"
-  ring:
-    kvstore:
-      store: memberlist
-    heartbeat_timeout: 5s
-    replication_factor: 3
-    heartbeat_interval: 5s
-
-# Ingester configuration - stores traces and querying
-ingester:
-  lifecycler:
-    address: tempo
-    ring:
-      kvstore:
-        store: memberlist
-      replication_factor: 3
-      max_cache_freshness_per_sec: 10s
-      heartbeat_interval: 5s
-      heartbeat_timeout: 5s
-    num_tokens: 128
-    tokens_file_path: /var/tempo/tokens.json
-    claim_on_rollout: true
-  trace_idle_period: 20s
-  max_block_bytes: 10_000_000
-  max_block_duration: 10m
-  chunk_size_bytes: 1_000_000
-  chunk_encoding: snappy
-  wal:
-    checkpoint_duration: 5s
-    max_wal_blocks: 4
-  metrics:
-    enabled: true
-    level: block
-    target_info_duration: 15m
-
-# WAL configuration for data durability
-wal:
-  checkpoint_duration: 5s
-  flush_on_shutdown: true
-  path: /var/tempo/wal
-
-# Kafka ingestion configuration - for high throughput scenarios
-ingest:
-  enabled: true
-  kafka:
-    brokers: [ redpanda:9092 ]
-    topic: tempo-ingest
-    encoding: protobuf
-    consumer_group: tempo-ingest-consumer
-    session_timeout: 10s
-    rebalance_timeout: 1m
-    partition: auto
-    verbosity: 2
-
-# Query frontend configuration - distributed querying
-query_frontend:
-  compression: gzip
-  downstream_url: http://localhost:3200
-  log_queries_longer_than: 5s
-  cache_uncompressed_bytes: 100MB
-  max_outstanding_requests_per_tenant: 100
-  max_query_length: 48h
-  max_query_lookback: 30d
-  default_result_cache_ttl: 1m
-  result_cache:
-    cache:
-      enable_fifocache: true
-      default_validity: 1m
-  rf1_after: "1999-01-01T00:00:00Z"
-  mcp_server:
-    enabled: true
-
-# Querier configuration - queries traces
-querier:
-  frontend_worker:
-    frontend_address: localhost:3200
-    grpc_client_config:
-      max_recv_msg_size: 104857600
-  max_concurrent_queries: 20
-  max_metric_bytes_per_trace: 1MB
-
-# Query scheduler configuration - for distributed querying
-query_scheduler:
-  use_scheduler_ring: false
-
-# Metrics generator configuration - generates metrics from traces
-metrics_generator:
-  enabled: true
-  registry:
-    enabled: true
-    external_labels:
-      source: tempo
-      cluster: rustfs-docker-ha
-      environment: production
-  storage:
-    path: /var/tempo/generator/wal
-    remote_write:
-      - url: http://prometheus:9090/api/v1/write
-        send_exemplars: true
-        resource_to_telemetry_conversion:
-          enabled: true
-  processor:
-    batch:
-      timeout: 10s
-      send_batch_size: 1024
-    memory_limiter:
-      check_interval: 5s
-      limit_mib: 512
-      spike_limit_mib: 128
-  processors:
-    - span-metrics
-    - local-blocks
-    - service-graphs
-  generate_native_histograms: both
-
-# Backend worker configuration
-backend_worker:
-  backend_scheduler_addr: localhost:3200
-  compaction:
-    block_retention: 24h
-    compacted_block_retention: 1h
-  ring:
-    kvstore:
-      store: memberlist
-
-# Backend scheduler configuration
-backend_scheduler:
-  enabled: true
-  provider:
-    compaction:
-      compaction:
-        block_retention: 24h
-        compacted_block_retention: 1h
-        concurrency: 25
-        v2_out_path: /var/tempo/blocks/compaction
-
-# Storage configuration - local backend with proper retention
-storage:
-  trace:
-    backend: local
-    wal:
-      path: /var/tempo/wal
-      checkpoint_duration: 5s
-      flush_on_shutdown: true
-    local:
-      path: /var/tempo/blocks
-      bloom_filter_false_positive: 0.05
-      bloom_shift: 4
-      index:
-        downsample_bytes: 1000000
-        page_size_bytes: 0
-        cache_size_bytes: 0
-    pool:
-      max_workers: 400
-      queue_depth: 10000
-
-# Compactor configuration - manages block compaction
-compactor:
-  compaction:
-    block_retention: 168h  # 7 days
-    compacted_block_retention: 1h
-    concurrency: 25
-    v2_out_path: /var/tempo/blocks/compaction
-    shard_count: 32
-    max_block_bytes: 107374182400  # 100GB
-    max_compaction_objects: 6000000
-    max_time_per_tenant: 5m
-    block_size_bytes: 107374182400
-  ring:
-    kvstore:
-      store: memberlist
-    heartbeat_interval: 5s
-    heartbeat_timeout: 5s
-
-# Limits configuration - rate limiting and quotas
-limits:
-  max_traces_per_user: 10000
-  max_bytes_per_trace: 10485760  # 10MB
-  max_search_bytes_per_trace: 0
-  forgiving_oversize_traces: true
-  rate_limit_bytes: 10MB
-  rate_limit_enabled: true
-  ingestion_burst_size_bytes: 20MB
-  ingestion_rate_limit_bytes: 10MB
-  max_bytes_per_second: 10485760
-  metrics_generator_max_active_series: 10000
-  metrics_generator_max_churned_series: 10000
-  metrics_generator_forta_out_of_order_ttl: 5m
-
-# Override configuration
-overrides:
-  defaults:
-    metrics_generator:
-      processors:
-        - span-metrics
-        - local-blocks
-        - service-graphs
-      generate_native_histograms: both
-      max_active_series: 10000
-      max_churned_series: 10000
-
-# Usage reporting configuration
-usage_report:
-  reporting_enabled: false
-
-# Tracing configuration for debugging
-tracing:
-  enabled: true
-  jaeger:
-    sampler:
-      name: probabilistic
-      param: 0.1
-    reporter_log_spans: false
-

.docker/observability/tempo.yaml

@@ -1,72 +1,55 @@
-# Copyright 2024 RustFS Team
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-
 stream_over_http_enabled: true
-
 server:
   http_listen_port: 3200
   log_level: info
 
-memberlist:
-  node_name: tempo
-  bind_port: 7946
-  join_members:
-    - tempo:7946
+query_frontend:
+  search:
+    duration_slo: 5s
+    throughput_bytes_slo: 1.073741824e+09
+    metadata_slo:
+      duration_slo: 5s
+      throughput_bytes_slo: 1.073741824e+09
+  trace_by_id:
+    duration_slo: 5s
 
 distributor:
   receivers:
     otlp:
       protocols:
         grpc:
-          endpoint: "0.0.0.0:4317"
-        http:
-          endpoint: "0.0.0.0:4318"
+          endpoint: "tempo:4317"
 
 ingester:
-  max_block_duration: 5m
+  max_block_duration: 5m # cut the headblock when this much time passes. this is being set for demo purposes and should probably be left alone normally
+
+compactor:
+  compaction:
+    block_retention: 1h # overall Tempo trace retention. set for demo purposes
 
 metrics_generator:
   registry:
     external_labels:
       source: tempo
       cluster: docker-compose
-  traces_storage:
-    path: /var/tempo/generator/traces
   storage:
     path: /var/tempo/generator/wal
     remote_write:
       - url: http://prometheus:9090/api/v1/write
         send_exemplars: true
-
-query_frontend:
-  rf1_after: "1999-01-01T00:00:00Z"
-  mcp_server:
-    enabled: true
+  traces_storage:
+    path: /var/tempo/generator/traces
 
 storage:
   trace:
-    backend: local
+    backend: local # backend configuration to use
     wal:
       path: /var/tempo/wal # where to store the wal locally
     local:
-      path: /var/tempo/blocks # where to store the traces locally
+      path: /var/tempo/blocks
 
 overrides:
   defaults:
     metrics_generator:
-      processors: [ "span-metrics", "service-graphs", "local-blocks" ]
-      generate_native_histograms: both
-
-usage_report:
-  reporting_enabled: false
+      processors: [ service-graphs, span-metrics, local-blocks ] # enables metrics generator
+      generate_native_histograms: both

.docker/openobserve-otel/README.md

@@ -5,57 +5,71 @@
 
 English | [中文](README_ZH.md)
 
-This directory contains the configuration for an **alternative** observability stack using OpenObserve.
+This directory contains the configuration files for setting up an observability stack with OpenObserve and OpenTelemetry
+Collector.
 
-## ⚠️ Note
+### Overview
 
-For the **recommended** observability stack (Prometheus, Grafana, Tempo, Loki), please see `../observability/`.
+This setup provides a complete observability solution for your applications:
 
-## 🌟 Overview
+- **OpenObserve**: A modern, open-source observability platform for logs, metrics, and traces.
+- **OpenTelemetry Collector**: Collects and processes telemetry data before sending it to OpenObserve.
 
-OpenObserve is a lightweight, all-in-one observability platform that handles logs, metrics, and traces in a single binary. This setup is ideal for:
-- Resource-constrained environments.
-- Quick setup and testing.
-- Users who prefer a unified UI.
+### Setup Instructions
 
-## 🚀 Quick Start
+1. **Prerequisites**:
+    - Docker and Docker Compose installed
+    - Sufficient memory resources (minimum 2GB recommended)
 
-### 1. Start Services
+2. **Starting the Services**:
+   ```bash
+   cd .docker/openobserve-otel
+   docker compose -f docker-compose.yml  up -d
+   ```
+
+3. **Accessing the Dashboard**:
+    - OpenObserve UI: http://localhost:5080
+    - Default credentials:
+        - Username: root@rustfs.com
+        - Password: rustfs123
+
+### Configuration
+
+#### OpenObserve Configuration
+
+The OpenObserve service is configured with:
+
+- Root user credentials
+- Data persistence through a volume mount
+- Memory cache enabled
+- Health checks
+- Exposed ports:
+    - 5080: HTTP API and UI
+    - 5081: OTLP gRPC
+
+#### OpenTelemetry Collector Configuration
+
+The collector is configured to:
+
+- Receive telemetry data via OTLP (HTTP and gRPC)
+- Collect logs from files
+- Process data in batches
+- Export data to OpenObserve
+- Manage memory usage
+
+### Integration with Your Application
+
+To send telemetry data from your application, configure your OpenTelemetry SDK to send data to:
+
+- OTLP gRPC: `localhost:4317`
+- OTLP HTTP: `localhost:4318`
+
+For example, in a Rust application using the `rustfs-obs` library:
 
 ```bash
-cd .docker/openobserve-otel
-docker compose up -d
+export RUSTFS_OBS_ENDPOINT=http://localhost:4317
+export RUSTFS_OBS_SERVICE_NAME=yourservice
+export RUSTFS_OBS_SERVICE_VERSION=1.0.0
+export RUSTFS_OBS_ENVIRONMENT=development
 ```
 
-### 2. Access Dashboard
-
-- **URL**: [http://localhost:5080](http://localhost:5080)
-- **Username**: `root@rustfs.com`
-- **Password**: `rustfs123`
-
-## 🛠️ Configuration
-
-### OpenObserve
-
-- **Persistence**: Data is persisted to a Docker volume.
-- **Ports**:
-    - `5080`: HTTP API and UI
-    - `5081`: OTLP gRPC
-
-### OpenTelemetry Collector
-
-- **Receivers**: OTLP (gRPC `4317`, HTTP `4318`)
-- **Exporters**: Sends data to OpenObserve.
-
-## 🔗 Integration
-
-Configure your application to send OTLP data to the collector:
-
-- **Endpoint**: `http://localhost:4318` (HTTP) or `localhost:4317` (gRPC)
-
-Example for RustFS:
-
-```bash
-export RUSTFS_OBS_ENDPOINT=http://localhost:4318
-export RUSTFS_OBS_SERVICE_NAME=rustfs-node-1
-```

.docker/openobserve-otel/README_ZH.md

@@ -5,57 +5,71 @@
 
 [English](README.md) | 中文
 
-本目录包含使用 OpenObserve 的**替代**可观测性技术栈配置。
+## 中文
 
-## ⚠️ 注意
+本目录包含搭建 OpenObserve 和 OpenTelemetry Collector 可观测性栈的配置文件。
 
-对于**推荐**的可观测性技术栈（Prometheus, Grafana, Tempo, Loki），请参阅 `../observability/`。
+### 概述
 
-## 🌟 概览
+此设置为应用程序提供了完整的可观测性解决方案：
 
-OpenObserve 是一个轻量级、一体化的可观测性平台，在一个二进制文件中处理日志、指标和追踪。此设置非常适合：
-- 资源受限的环境。
-- 快速设置和测试。
-- 喜欢统一 UI 的用户。
+- **OpenObserve**：现代化、开源的可观测性平台，用于日志、指标和追踪。
+- **OpenTelemetry Collector**：收集和处理遥测数据，然后将其发送到 OpenObserve。
 
-## 🚀 快速开始
+### 设置说明
 
-### 1. 启动服务
+1. **前提条件**：
+    - 已安装 Docker 和 Docker Compose
+    - 足够的内存资源（建议至少 2GB）
+
+2. **启动服务**：
+   ```bash
+   cd .docker/openobserve-otel
+   docker compose -f docker-compose.yml  up -d
+   ```
+
+3. **访问仪表板**：
+    - OpenObserve UI：http://localhost:5080
+    - 默认凭据：
+        - 用户名：root@rustfs.com
+        - 密码：rustfs123
+
+### 配置
+
+#### OpenObserve 配置
+
+OpenObserve 服务配置：
+
+- 根用户凭据
+- 通过卷挂载实现数据持久化
+- 启用内存缓存
+- 健康检查
+- 暴露端口：
+    - 5080：HTTP API 和 UI
+    - 5081：OTLP gRPC
+
+#### OpenTelemetry Collector 配置
+
+收集器配置为：
+
+- 通过 OTLP（HTTP 和 gRPC）接收遥测数据
+- 从文件中收集日志
+- 批处理数据
+- 将数据导出到 OpenObserve
+- 管理内存使用
+
+### 与应用程序集成
+
+要从应用程序发送遥测数据，将 OpenTelemetry SDK 配置为发送数据到：
+
+- OTLP gRPC:`localhost:4317`
+- OTLP HTTP:`localhost:4318`
+
+例如，在使用 `rustfs-obs` 库的 Rust 应用程序中：
 
 ```bash
-cd .docker/openobserve-otel
-docker compose up -d
-```
-
-### 2. 访问仪表盘
-
-- **URL**: [http://localhost:5080](http://localhost:5080)
-- **用户名**: `root@rustfs.com`
-- **密码**: `rustfs123`
-
-## 🛠️ 配置
-
-### OpenObserve
-
-- **持久化**: 数据持久化到 Docker 卷。
-- **端口**:
-    - `5080`: HTTP API 和 UI
-    - `5081`: OTLP gRPC
-
-### OpenTelemetry Collector
-
-- **接收器**: OTLP (gRPC `4317`, HTTP `4318`)
-- **导出器**: 将数据发送到 OpenObserve。
-
-## 🔗 集成
-
-配置您的应用程序将 OTLP 数据发送到收集器：
-
-- **端点**: `http://localhost:4318` (HTTP) 或 `localhost:4317` (gRPC)
-
-RustFS 示例：
-
-```bash
-export RUSTFS_OBS_ENDPOINT=http://localhost:4318
-export RUSTFS_OBS_SERVICE_NAME=rustfs-node-1
-```
+export RUSTFS_OBS_ENDPOINT=http://localhost:4317
+export RUSTFS_OBS_SERVICE_NAME=yourservice
+export RUSTFS_OBS_SERVICE_VERSION=1.0.0
+export RUSTFS_OBS_ENVIRONMENT=development
+```

.docker/test/compat/README.md

@@ -1,91 +0,0 @@
-# Rio compatibility compose files
-
-These compose files prepare 4-node, 4-disk clusters for rio/rio-v2 storage format compatibility checks. All disks are bind-mounted under `.docker/compat/data` so the on-disk files remain available on the host.
-
-## Clusters
-
-```bash
-docker compose -f .docker/compat/docker-compose.rustfs-beta5.yml up -d --build
-docker compose -f .docker/compat/docker-compose.minio.yml up -d
-docker compose -f .docker/compat/docker-compose.rustfs-rio-v2.yml up -d --build
-```
-
-Default API endpoints:
-
-- RustFS `1.0.0-beta.5`: `http://127.0.0.1:9100`
-- MinIO: `http://127.0.0.1:9200`
-- current main with `rio-v2`: `http://127.0.0.1:9300`
-
-## Reading old datasets with rio-v2
-
-Stop the writer cluster before mounting its disks into the rio-v2 cluster.
-
-```bash
-docker compose -f .docker/compat/docker-compose.rustfs-beta5.yml down
-RUSTFS_RIO_V2_DATASET=./data/rustfs-beta5 \
-  docker compose -f .docker/compat/docker-compose.rustfs-rio-v2.yml up -d --build
-
-docker compose -f .docker/compat/docker-compose.minio.yml down
-RUSTFS_RIO_V2_DATASET=./data/minio \
-  docker compose -f .docker/compat/docker-compose.rustfs-rio-v2.yml up -d --build
-```
-
-## 200G object mix
-
-Use the same bucket/object matrix against the beta5 and MinIO endpoints, then read it back through the rio-v2 endpoint. A practical 200G mix is:
-
-- 1 KiB x 1024
-- 1 MiB x 1024
-- 64 MiB x 512
-- 1 GiB x 64
-- 8 GiB x 12
-- 6 GiB x 1
-
-Compression is enabled by default for RustFS and MinIO. Server-side KMS/SSE settings are intentionally left to environment variables or mounted key directories so real key material is not committed. For SSE-C cases, run the clusters with TLS because MinIO requires HTTPS for SSE-C.
-
-## High-concurrency write/read stress
-
-Use `run_rw_compat_stress.sh` to generate a manifest on an old endpoint, then verify the same objects through the rio-v2 endpoint after mounting the old disks.
-
-```bash
-.docker/compat/run_rw_compat_stress.sh \
-  --mode write \
-  --endpoint http://127.0.0.1:9100 \
-  --access-key rustfsadmin \
-  --secret-key rustfsadmin \
-  --bucket compat-beta5 \
-  --concurrency 96
-
-RUSTFS_RIO_V2_DATASET=./data/rustfs-beta5 \
-  docker compose -f .docker/compat/docker-compose.rustfs-rio-v2.yml up -d --build
-
-.docker/compat/run_rw_compat_stress.sh \
-  --mode verify \
-  --endpoint http://127.0.0.1:9300 \
-  --access-key rustfsadmin \
-  --secret-key rustfsadmin \
-  --bucket compat-beta5 \
-  --concurrency 96 \
-  --manifest target/compat/rw-stress-YYYYmmdd-HHMMSS/manifest.csv
-```
-
-For encrypted datasets, add `--encryption sse-s3`, `--encryption sse-kms --sse-kms-key-id <key-id>`, or `--encryption sse-c --sse-c-key-file <raw-32-byte-key-file>` to both the write and verify commands.
-
-## 5 GiB encrypted compatibility run
-
-The `5g` profile covers 1 KiB, 1 MiB, 16 MiB, 64 MiB, and 1 GiB objects and totals exactly 5 GiB. Generate `compat-key.key` under `.docker/compat/kms/rustfs-compat`, enable local KMS on both RustFS clusters, then use the same encryption arguments while writing with beta5 and verifying with rio-v2. Set non-default local test credentials first because distributed listeners reject the built-in default credentials.
-
-```bash
-export COMPAT_ACCESS_KEY='<non-default-access-key>'
-export COMPAT_SECRET_KEY='<non-default-secret-key>'
-
-RUSTFS_ACCESS_KEY="$COMPAT_ACCESS_KEY" RUSTFS_SECRET_KEY="$COMPAT_SECRET_KEY" \
-  RUSTFS_KMS_ENABLE=true RUSTFS_KMS_ALLOW_INSECURE_DEV_DEFAULTS=true \
-  docker compose -f .docker/compat/docker-compose.rustfs-beta5.yml up -d
-
-.docker/compat/run_rw_compat_stress.sh \
-  --mode write --endpoint http://127.0.0.1:9100 \
-  --access-key "$COMPAT_ACCESS_KEY" --secret-key "$COMPAT_SECRET_KEY" \
-  --bucket compat-beta5-sse-s3 --profile 5g --concurrency 16 \
-  --encryption sse-s3
-```

.docker/test/compat/docker-compose.minio.yml

@@ -1,88 +0,0 @@
-# Copyright 2024 RustFS Team
-#
-# Licensed under the Apache License, Version 2.0.
-
-x-minio-env: &minio-env
-  MINIO_ROOT_USER: "${MINIO_ROOT_USER:-minioadmin}"
-  MINIO_ROOT_PASSWORD: "${MINIO_ROOT_PASSWORD:-minioadmin}"
-  MINIO_COMPRESSION_ENABLE: "${MINIO_COMPRESSION_ENABLE:-on}"
-  MINIO_COMPRESSION_ALLOW_ENCRYPTION: "${MINIO_COMPRESSION_ALLOW_ENCRYPTION:-on}"
-  MINIO_COMPRESSION_EXTENSIONS: "${MINIO_COMPRESSION_EXTENSIONS:-.txt,.log,.csv,.json,.tar,.xml,.bin}"
-  MINIO_COMPRESSION_MIME_TYPES: "${MINIO_COMPRESSION_MIME_TYPES:-text/*,application/json,application/xml,binary/octet-stream}"
-
-x-minio-node: &minio-node
-  image: "${MINIO_IMAGE:-quay.io/minio/minio:latest}"
-  command: server --console-address ":9001" "http://minio{1...4}:9000/data/disk{1...4}"
-  environment: *minio-env
-  networks:
-    - minio-compat-net
-  restart: unless-stopped
-
-services:
-  minio-permission-helper:
-    image: alpine:3.23
-    command: sh -c "mkdir -p /compat-data && chown -R 1000:1000 /compat-data"
-    volumes:
-      - ./data/minio:/compat-data
-    restart: "no"
-
-  minio1:
-    <<: *minio-node
-    hostname: minio1
-    depends_on:
-      minio-permission-helper:
-        condition: service_completed_successfully
-    volumes:
-      - ./data/minio/node1/disk1:/data/disk1
-      - ./data/minio/node1/disk2:/data/disk2
-      - ./data/minio/node1/disk3:/data/disk3
-      - ./data/minio/node1/disk4:/data/disk4
-    ports:
-      - "${MINIO_API_PORT:-9200}:9000"
-      - "${MINIO_CONSOLE_PORT:-9201}:9001"
-
-  minio2:
-    <<: *minio-node
-    hostname: minio2
-    depends_on:
-      minio-permission-helper:
-        condition: service_completed_successfully
-    volumes:
-      - ./data/minio/node2/disk1:/data/disk1
-      - ./data/minio/node2/disk2:/data/disk2
-      - ./data/minio/node2/disk3:/data/disk3
-      - ./data/minio/node2/disk4:/data/disk4
-    ports:
-      - "${MINIO_NODE2_PORT:-9202}:9000"
-
-  minio3:
-    <<: *minio-node
-    hostname: minio3
-    depends_on:
-      minio-permission-helper:
-        condition: service_completed_successfully
-    volumes:
-      - ./data/minio/node3/disk1:/data/disk1
-      - ./data/minio/node3/disk2:/data/disk2
-      - ./data/minio/node3/disk3:/data/disk3
-      - ./data/minio/node3/disk4:/data/disk4
-    ports:
-      - "${MINIO_NODE3_PORT:-9203}:9000"
-
-  minio4:
-    <<: *minio-node
-    hostname: minio4
-    depends_on:
-      minio-permission-helper:
-        condition: service_completed_successfully
-    volumes:
-      - ./data/minio/node4/disk1:/data/disk1
-      - ./data/minio/node4/disk2:/data/disk2
-      - ./data/minio/node4/disk3:/data/disk3
-      - ./data/minio/node4/disk4:/data/disk4
-    ports:
-      - "${MINIO_NODE4_PORT:-9204}:9000"
-
-networks:
-  minio-compat-net:
-    driver: bridge

.docker/test/compat/docker-compose.rustfs-beta5.yml

@@ -1,104 +0,0 @@
-# Copyright 2024 RustFS Team
-#
-# Licensed under the Apache License, Version 2.0.
-
-x-rustfs-env: &rustfs-env
-  RUSTFS_VOLUMES: "http://rustfs-beta5-node{1...4}:9000/data/disk{1...4}"
-  RUSTFS_ADDRESS: ":9000"
-  RUSTFS_CONSOLE_ADDRESS: ":9001"
-  RUSTFS_CONSOLE_ENABLE: "true"
-  RUSTFS_CONSOLE_CORS_ALLOWED_ORIGINS: "*"
-  RUSTFS_ACCESS_KEY: "${RUSTFS_ACCESS_KEY:-rustfsadmin}"
-  RUSTFS_SECRET_KEY: "${RUSTFS_SECRET_KEY:-rustfsadmin}"
-  RUSTFS_OBS_LOGGER_LEVEL: "${RUSTFS_OBS_LOGGER_LEVEL:-info}"
-  RUSTFS_OBS_LOG_DIRECTORY: "/logs"
-  RUSTFS_COMPRESSION_ENABLED: "${RUSTFS_COMPRESSION_ENABLED:-true}"
-  RUSTFS_COMPRESSION_EXTENSIONS: "${RUSTFS_COMPRESSION_EXTENSIONS:-.txt,.log,.csv,.json,.tar,.xml,.bin}"
-  RUSTFS_COMPRESSION_MIME_TYPES: "${RUSTFS_COMPRESSION_MIME_TYPES:-text/*,application/json,application/xml,binary/octet-stream}"
-  RUSTFS_KMS_ENABLE: "${RUSTFS_KMS_ENABLE:-false}"
-  RUSTFS_KMS_BACKEND: "${RUSTFS_KMS_BACKEND:-local}"
-  RUSTFS_KMS_KEY_DIR: "${RUSTFS_KMS_KEY_DIR:-/kms}"
-  RUSTFS_KMS_DEFAULT_KEY_ID: "${RUSTFS_KMS_DEFAULT_KEY_ID:-compat-key}"
-  RUSTFS_KMS_ALLOW_INSECURE_DEV_DEFAULTS: "${RUSTFS_KMS_ALLOW_INSECURE_DEV_DEFAULTS:-false}"
-  RUSTFS_UNSAFE_BYPASS_DISK_CHECK: "${RUSTFS_UNSAFE_BYPASS_DISK_CHECK:-true}"
-
-x-rustfs-node: &rustfs-node
-  image: "${RUSTFS_BETA5_IMAGE:-rustfs/rustfs:1.0.0-beta.5}"
-  build:
-    context: ../..
-    dockerfile: Dockerfile
-    args:
-      RELEASE: "1.0.0-beta.5"
-  environment: *rustfs-env
-  depends_on:
-    rustfs-beta5-permission-helper:
-      condition: service_completed_successfully
-  networks:
-    - rustfs-beta5-net
-  restart: unless-stopped
-
-services:
-  rustfs-beta5-permission-helper:
-    image: alpine:3.23
-    command: sh -c "mkdir -p /compat-data /kms && chown -R 10001:10001 /compat-data /kms"
-    volumes:
-      - ./data/rustfs-beta5:/compat-data
-      - ./kms/rustfs-compat:/kms
-    restart: "no"
-
-  rustfs-beta5-node1:
-    <<: *rustfs-node
-    hostname: rustfs-beta5-node1
-    volumes:
-      - ./data/rustfs-beta5/node1/disk1:/data/disk1
-      - ./data/rustfs-beta5/node1/disk2:/data/disk2
-      - ./data/rustfs-beta5/node1/disk3:/data/disk3
-      - ./data/rustfs-beta5/node1/disk4:/data/disk4
-      - ./data/rustfs-beta5/logs/node1:/logs
-      - ./kms/rustfs-compat:/kms
-    ports:
-      - "${RUSTFS_BETA5_API_PORT:-9100}:9000"
-      - "${RUSTFS_BETA5_CONSOLE_PORT:-9101}:9001"
-
-  rustfs-beta5-node2:
-    <<: *rustfs-node
-    hostname: rustfs-beta5-node2
-    volumes:
-      - ./data/rustfs-beta5/node2/disk1:/data/disk1
-      - ./data/rustfs-beta5/node2/disk2:/data/disk2
-      - ./data/rustfs-beta5/node2/disk3:/data/disk3
-      - ./data/rustfs-beta5/node2/disk4:/data/disk4
-      - ./data/rustfs-beta5/logs/node2:/logs
-      - ./kms/rustfs-compat:/kms
-    ports:
-      - "${RUSTFS_BETA5_NODE2_PORT:-9102}:9000"
-
-  rustfs-beta5-node3:
-    <<: *rustfs-node
-    hostname: rustfs-beta5-node3
-    volumes:
-      - ./data/rustfs-beta5/node3/disk1:/data/disk1
-      - ./data/rustfs-beta5/node3/disk2:/data/disk2
-      - ./data/rustfs-beta5/node3/disk3:/data/disk3
-      - ./data/rustfs-beta5/node3/disk4:/data/disk4
-      - ./data/rustfs-beta5/logs/node3:/logs
-      - ./kms/rustfs-compat:/kms
-    ports:
-      - "${RUSTFS_BETA5_NODE3_PORT:-9103}:9000"
-
-  rustfs-beta5-node4:
-    <<: *rustfs-node
-    hostname: rustfs-beta5-node4
-    volumes:
-      - ./data/rustfs-beta5/node4/disk1:/data/disk1
-      - ./data/rustfs-beta5/node4/disk2:/data/disk2
-      - ./data/rustfs-beta5/node4/disk3:/data/disk3
-      - ./data/rustfs-beta5/node4/disk4:/data/disk4
-      - ./data/rustfs-beta5/logs/node4:/logs
-      - ./kms/rustfs-compat:/kms
-    ports:
-      - "${RUSTFS_BETA5_NODE4_PORT:-9104}:9000"
-
-networks:
-  rustfs-beta5-net:
-    driver: bridge

.docker/test/compat/docker-compose.rustfs-rio-v2.yml

@@ -1,115 +0,0 @@
-# Copyright 2024 RustFS Team
-#
-# Licensed under the Apache License, Version 2.0.
-
-x-rustfs-rio-v2-env: &rustfs-rio-v2-env
-  RUSTFS_VOLUMES: "http://rustfs-rio-v2-node{1...4}:9000/data/disk{1...4}"
-  RUSTFS_ADDRESS: ":9000"
-  RUSTFS_CONSOLE_ADDRESS: ":9001"
-  RUSTFS_CONSOLE_ENABLE: "true"
-  RUSTFS_CONSOLE_CORS_ALLOWED_ORIGINS: "*"
-  RUSTFS_ACCESS_KEY: "${RUSTFS_ACCESS_KEY:-rustfsadmin}"
-  RUSTFS_SECRET_KEY: "${RUSTFS_SECRET_KEY:-rustfsadmin}"
-  RUSTFS_OBS_LOGGER_LEVEL: "${RUSTFS_OBS_LOGGER_LEVEL:-info}"
-  RUSTFS_OBS_LOG_DIRECTORY: "/logs"
-  RUSTFS_COMPRESSION_ENABLED: "${RUSTFS_COMPRESSION_ENABLED:-true}"
-  RUSTFS_COMPRESSION_EXTENSIONS: "${RUSTFS_COMPRESSION_EXTENSIONS:-.txt,.log,.csv,.json,.tar,.xml,.bin}"
-  RUSTFS_COMPRESSION_MIME_TYPES: "${RUSTFS_COMPRESSION_MIME_TYPES:-text/*,application/json,application/xml,binary/octet-stream}"
-  RUSTFS_KMS_ENABLE: "${RUSTFS_KMS_ENABLE:-false}"
-  RUSTFS_KMS_BACKEND: "${RUSTFS_KMS_BACKEND:-local}"
-  RUSTFS_KMS_KEY_DIR: "${RUSTFS_KMS_KEY_DIR:-/kms}"
-  RUSTFS_KMS_DEFAULT_KEY_ID: "${RUSTFS_KMS_DEFAULT_KEY_ID:-compat-key}"
-  RUSTFS_KMS_ALLOW_INSECURE_DEV_DEFAULTS: "${RUSTFS_KMS_ALLOW_INSECURE_DEV_DEFAULTS:-false}"
-  RUSTFS_UNSAFE_BYPASS_DISK_CHECK: "${RUSTFS_UNSAFE_BYPASS_DISK_CHECK:-true}"
-
-x-rustfs-rio-v2-node: &rustfs-rio-v2-node
-  image: "${RUSTFS_RIO_V2_IMAGE:-rustfs/rustfs:compat-rio-v2}"
-  entrypoint:
-    - /bin/sh
-    - -c
-    - |
-      until getent hosts rustfs-rio-v2-node1 >/dev/null &&
-        getent hosts rustfs-rio-v2-node2 >/dev/null &&
-        getent hosts rustfs-rio-v2-node3 >/dev/null &&
-        getent hosts rustfs-rio-v2-node4 >/dev/null; do
-        sleep 1
-      done
-      exec /entrypoint.sh /usr/bin/rustfs
-  build:
-    context: ../..
-    dockerfile: Dockerfile.source
-    args:
-      RUSTFS_BUILD_FEATURES: "rio-v2"
-  environment: *rustfs-rio-v2-env
-  depends_on:
-    rustfs-rio-v2-permission-helper:
-      condition: service_completed_successfully
-  networks:
-    - rustfs-rio-v2-net
-  restart: unless-stopped
-
-services:
-  rustfs-rio-v2-permission-helper:
-    image: alpine:3.23
-    command: sh -c "mkdir -p /compat-data /kms && chown -R 10001:10001 /compat-data /kms"
-    volumes:
-      - ${RUSTFS_RIO_V2_DATASET:-./data/rustfs-rio-v2}:/compat-data
-      - ./kms/rustfs-compat:/kms
-    restart: "no"
-
-  rustfs-rio-v2-node1:
-    <<: *rustfs-rio-v2-node
-    hostname: rustfs-rio-v2-node1
-    volumes:
-      - ${RUSTFS_RIO_V2_DATASET:-./data/rustfs-rio-v2}/node1/disk1:/data/disk1
-      - ${RUSTFS_RIO_V2_DATASET:-./data/rustfs-rio-v2}/node1/disk2:/data/disk2
-      - ${RUSTFS_RIO_V2_DATASET:-./data/rustfs-rio-v2}/node1/disk3:/data/disk3
-      - ${RUSTFS_RIO_V2_DATASET:-./data/rustfs-rio-v2}/node1/disk4:/data/disk4
-      - ${RUSTFS_RIO_V2_DATASET:-./data/rustfs-rio-v2}/logs/node1:/logs
-      - ./kms/rustfs-compat:/kms
-    ports:
-      - "${RUSTFS_RIO_V2_API_PORT:-9300}:9000"
-      - "${RUSTFS_RIO_V2_CONSOLE_PORT:-9301}:9001"
-
-  rustfs-rio-v2-node2:
-    <<: *rustfs-rio-v2-node
-    hostname: rustfs-rio-v2-node2
-    volumes:
-      - ${RUSTFS_RIO_V2_DATASET:-./data/rustfs-rio-v2}/node2/disk1:/data/disk1
-      - ${RUSTFS_RIO_V2_DATASET:-./data/rustfs-rio-v2}/node2/disk2:/data/disk2
-      - ${RUSTFS_RIO_V2_DATASET:-./data/rustfs-rio-v2}/node2/disk3:/data/disk3
-      - ${RUSTFS_RIO_V2_DATASET:-./data/rustfs-rio-v2}/node2/disk4:/data/disk4
-      - ${RUSTFS_RIO_V2_DATASET:-./data/rustfs-rio-v2}/logs/node2:/logs
-      - ./kms/rustfs-compat:/kms
-    ports:
-      - "${RUSTFS_RIO_V2_NODE2_PORT:-9302}:9000"
-
-  rustfs-rio-v2-node3:
-    <<: *rustfs-rio-v2-node
-    hostname: rustfs-rio-v2-node3
-    volumes:
-      - ${RUSTFS_RIO_V2_DATASET:-./data/rustfs-rio-v2}/node3/disk1:/data/disk1
-      - ${RUSTFS_RIO_V2_DATASET:-./data/rustfs-rio-v2}/node3/disk2:/data/disk2
-      - ${RUSTFS_RIO_V2_DATASET:-./data/rustfs-rio-v2}/node3/disk3:/data/disk3
-      - ${RUSTFS_RIO_V2_DATASET:-./data/rustfs-rio-v2}/node3/disk4:/data/disk4
-      - ${RUSTFS_RIO_V2_DATASET:-./data/rustfs-rio-v2}/logs/node3:/logs
-      - ./kms/rustfs-compat:/kms
-    ports:
-      - "${RUSTFS_RIO_V2_NODE3_PORT:-9303}:9000"
-
-  rustfs-rio-v2-node4:
-    <<: *rustfs-rio-v2-node
-    hostname: rustfs-rio-v2-node4
-    volumes:
-      - ${RUSTFS_RIO_V2_DATASET:-./data/rustfs-rio-v2}/node4/disk1:/data/disk1
-      - ${RUSTFS_RIO_V2_DATASET:-./data/rustfs-rio-v2}/node4/disk2:/data/disk2
-      - ${RUSTFS_RIO_V2_DATASET:-./data/rustfs-rio-v2}/node4/disk3:/data/disk3
-      - ${RUSTFS_RIO_V2_DATASET:-./data/rustfs-rio-v2}/node4/disk4:/data/disk4
-      - ${RUSTFS_RIO_V2_DATASET:-./data/rustfs-rio-v2}/logs/node4:/logs
-      - ./kms/rustfs-compat:/kms
-    ports:
-      - "${RUSTFS_RIO_V2_NODE4_PORT:-9304}:9000"
-
-networks:
-  rustfs-rio-v2-net:
-    driver: bridge

.docker/test/compat/run_rw_compat_stress.sh

@@ -1,639 +0,0 @@
-#!/usr/bin/env bash
-set -euo pipefail
-
-# High-concurrency S3 read/write stress runner for rio/rio-v2 format compatibility.
-# Write a manifest on an old endpoint, then verify the same manifest through rio-v2.
-
-MODE="write"
-ENDPOINT=""
-ACCESS_KEY="${AWS_ACCESS_KEY_ID:-}"
-SECRET_KEY="${AWS_SECRET_ACCESS_KEY:-}"
-BUCKET="compat-rw-stress"
-REGION="us-east-1"
-CONCURRENCY=64
-OUT_DIR=""
-WORK_DIR=""
-MANIFEST=""
-PROFILE="200g"
-OBJECT_SPEC=""
-DATA_PATTERN="compressible"
-ENCRYPTION="none"
-SSE_KMS_KEY_ID=""
-SSE_C_KEY_FILE=""
-CLIENT="mc"
-AWS_BIN="${AWS_BIN:-aws}"
-MC_BIN="${MC_BIN:-}"
-KEEP_PAYLOADS=false
-DRY_RUN=false
-RESUME=false
-
-usage() {
-  cat <<'USAGE'
-Usage:
-  .docker/compat/run_rw_compat_stress.sh --mode <write|verify|mixed> \
-    --endpoint <url> --access-key <ak> --secret-key <sk> [options]
-
-Modes:
-  write     Create bucket, upload objects concurrently, and write manifest.csv.
-  verify    Read objects concurrently from --endpoint and verify against manifest.csv.
-  mixed     Write and verify against the same endpoint.
-
-Required:
-  --endpoint              S3 endpoint URL, for example http://127.0.0.1:9100
-  --access-key            S3 access key
-  --secret-key            S3 secret key
-
-Core options:
-  --bucket                Bucket name (default: compat-rw-stress)
-  --region                Region (default: us-east-1)
-  --concurrency           Parallel object operations (default: 64)
-  --out-dir               Output directory (default: target/compat/rw-stress-<timestamp>)
-  --work-dir              Payload scratch directory (default: <out-dir>/payloads)
-  --manifest              Manifest path (default: <out-dir>/manifest.csv for write/mixed)
-  --profile               compact | 5g | 200g (default: 200g)
-  --object-spec           Override profile. Format: size:count,size:count
-                         Example: 1KiB:1024,1MiB:1024,64MiB:512,1GiB:64
-  --data-pattern          compressible | random | mixed (default: compressible)
-  --keep-payloads         Do not delete local payload files after upload
-  --resume                Skip write tasks that already have rows in <out-dir>/tasks/write-rows
-  --dry-run               Print planned tasks and commands without executing S3 operations
-  --client                mc | aws (default: mc)
-  --mc-bin                Path to mc binary (default: first tmp/mc.* or mc in PATH)
-  --aws-bin               Path to aws binary (used with --client aws)
-
-Encryption options:
-  --encryption            none | sse-s3 | sse-kms | sse-c (default: none)
-  --sse-kms-key-id        KMS key id for --encryption sse-kms
-  --sse-c-key-file        Raw 32-byte SSE-C key file for --encryption sse-c
-
-Examples:
-  # Generate the old RustFS beta5 dataset.
-  .docker/compat/run_rw_compat_stress.sh \
-    --mode write --endpoint http://127.0.0.1:9100 \
-    --access-key rustfsadmin --secret-key rustfsadmin \
-    --bucket compat-beta5 --concurrency 96
-
-  # Verify that dataset after mounting beta5 disks into the rio-v2 compose.
-  .docker/compat/run_rw_compat_stress.sh \
-    --mode verify --endpoint http://127.0.0.1:9300 \
-    --access-key rustfsadmin --secret-key rustfsadmin \
-    --bucket compat-beta5 --concurrency 96 \
-    --manifest target/compat/rw-stress-YYYYmmdd-HHMMSS/manifest.csv
-
-  # Faster smoke run.
-  .docker/compat/run_rw_compat_stress.sh \
-    --mode mixed --endpoint http://127.0.0.1:9300 \
-    --access-key rustfsadmin --secret-key rustfsadmin \
-    --profile compact --concurrency 16
-USAGE
-}
-
-die() {
-  echo "ERROR: $*" >&2
-  exit 1
-}
-
-require_cmd() {
-  command -v "$1" >/dev/null 2>&1 || die "command not found: $1"
-}
-
-parse_args() {
-  while [[ $# -gt 0 ]]; do
-    case "$1" in
-      --mode) MODE="$2"; shift 2 ;;
-      --endpoint) ENDPOINT="$2"; shift 2 ;;
-      --access-key) ACCESS_KEY="$2"; shift 2 ;;
-      --secret-key) SECRET_KEY="$2"; shift 2 ;;
-      --bucket) BUCKET="$2"; shift 2 ;;
-      --region) REGION="$2"; shift 2 ;;
-      --concurrency) CONCURRENCY="$2"; shift 2 ;;
-      --out-dir) OUT_DIR="$2"; shift 2 ;;
-      --work-dir) WORK_DIR="$2"; shift 2 ;;
-      --manifest) MANIFEST="$2"; shift 2 ;;
-      --profile) PROFILE="$2"; shift 2 ;;
-      --object-spec) OBJECT_SPEC="$2"; shift 2 ;;
-      --data-pattern) DATA_PATTERN="$2"; shift 2 ;;
-      --encryption) ENCRYPTION="$2"; shift 2 ;;
-      --sse-kms-key-id) SSE_KMS_KEY_ID="$2"; shift 2 ;;
-      --sse-c-key-file) SSE_C_KEY_FILE="$2"; shift 2 ;;
-      --client) CLIENT="$2"; shift 2 ;;
-      --mc-bin) MC_BIN="$2"; shift 2 ;;
-      --aws-bin) AWS_BIN="$2"; shift 2 ;;
-      --keep-payloads) KEEP_PAYLOADS=true; shift ;;
-      --resume) RESUME=true; shift ;;
-      --dry-run) DRY_RUN=true; shift ;;
-      -h|--help) usage; exit 0 ;;
-      *) die "unknown arg: $1" ;;
-    esac
-  done
-}
-
-validate_args() {
-  [[ "$MODE" =~ ^(write|verify|mixed)$ ]] || die "--mode must be write, verify, or mixed"
-  [[ "$CLIENT" =~ ^(mc|aws)$ ]] || die "--client must be mc or aws"
-  [[ "$PROFILE" =~ ^(compact|5g|200g)$ ]] || die "--profile must be compact, 5g, or 200g"
-  [[ "$DATA_PATTERN" =~ ^(compressible|random|mixed)$ ]] || die "--data-pattern must be compressible, random, or mixed"
-  [[ "$ENCRYPTION" =~ ^(none|sse-s3|sse-kms|sse-c)$ ]] || die "--encryption must be none, sse-s3, sse-kms, or sse-c"
-  [[ -n "$ENDPOINT" && -n "$ACCESS_KEY" && -n "$SECRET_KEY" ]] || die "--endpoint/--access-key/--secret-key are required"
-  [[ "$CONCURRENCY" =~ ^[0-9]+$ && "$CONCURRENCY" -gt 0 ]] || die "--concurrency must be a positive integer"
-  if [[ "$ENCRYPTION" == "sse-kms" && -z "$SSE_KMS_KEY_ID" ]]; then
-    die "--sse-kms-key-id is required for --encryption sse-kms"
-  fi
-  if [[ "$ENCRYPTION" == "sse-c" ]]; then
-    [[ -n "$SSE_C_KEY_FILE" && -f "$SSE_C_KEY_FILE" ]] || die "--sse-c-key-file must point to an existing key file"
-  fi
-  if [[ "$MODE" == "verify" && -z "$MANIFEST" ]]; then
-    die "--manifest is required for --mode verify"
-  fi
-}
-
-setup_paths() {
-  if [[ -z "$OUT_DIR" ]]; then
-    OUT_DIR="target/compat/rw-stress-$(date +%Y%m%d-%H%M%S)"
-  fi
-  if [[ -z "$WORK_DIR" ]]; then
-    WORK_DIR="$OUT_DIR/payloads"
-  fi
-  if [[ -z "$MANIFEST" ]]; then
-    MANIFEST="$OUT_DIR/manifest.csv"
-  fi
-
-  mkdir -p "$OUT_DIR" "$WORK_DIR" "$OUT_DIR/tasks" "$OUT_DIR/logs"
-  TASKS_FILE="$OUT_DIR/tasks/tasks.tsv"
-  WRITE_ROWS_DIR="$OUT_DIR/tasks/write-rows"
-  VERIFY_ROWS_DIR="$OUT_DIR/tasks/verify-rows"
-  MC_CONFIG_DIR_LOCAL="$OUT_DIR/mc-config"
-  MC_ALIAS="compat"
-  mkdir -p "$WRITE_ROWS_DIR" "$VERIFY_ROWS_DIR"
-}
-
-resolve_mc_bin() {
-  if [[ -n "$MC_BIN" ]]; then
-    echo "$MC_BIN"
-    return
-  fi
-
-  local candidate
-  candidate="$(find tmp -maxdepth 1 -type f -name 'mc.*' -perm -111 2>/dev/null | sort | tail -n 1 || true)"
-  if [[ -n "$candidate" ]]; then
-    echo "$candidate"
-    return
-  fi
-
-  command -v mc 2>/dev/null || true
-}
-
-size_to_bytes() {
-  local raw="$1"
-  local num unit
-  if [[ "$raw" =~ ^([0-9]+)(B|KiB|MiB|GiB|KB|MB|GB)?$ ]]; then
-    num="${BASH_REMATCH[1]}"
-    unit="${BASH_REMATCH[2]:-B}"
-  else
-    die "invalid size: $raw"
-  fi
-
-  case "$unit" in
-    B) echo "$num" ;;
-    KiB) echo $((num * 1024)) ;;
-    MiB) echo $((num * 1024 * 1024)) ;;
-    GiB) echo $((num * 1024 * 1024 * 1024)) ;;
-    KB) echo $((num * 1000)) ;;
-    MB) echo $((num * 1000 * 1000)) ;;
-    GB) echo $((num * 1000 * 1000 * 1000)) ;;
-    *) die "invalid size unit: $unit" ;;
-  esac
-}
-
-profile_spec() {
-  if [[ -n "$OBJECT_SPEC" ]]; then
-    echo "$OBJECT_SPEC"
-    return
-  fi
-
-  case "$PROFILE" in
-    compact)
-      echo "1KiB:64,1MiB:64,16MiB:16,128MiB:4"
-      ;;
-    5g)
-      echo "1KiB:1024,1MiB:255,16MiB:64,64MiB:28,1GiB:2"
-      ;;
-    200g)
-      echo "1KiB:1024,1MiB:1024,64MiB:512,1GiB:64,8GiB:12,6GiB:1"
-      ;;
-  esac
-}
-
-content_for_index() {
-  local index="$1"
-  case $((index % 3)) in
-    0) echo "txt|text/plain" ;;
-    1) echo "json|application/json" ;;
-    2) echo "bin|binary/octet-stream" ;;
-  esac
-}
-
-generate_tasks() {
-  local spec item size count bytes i content ext mime key seed index=0
-  spec="$(profile_spec)"
-  : > "$TASKS_FILE"
-
-  IFS=',' read -r -a items <<< "$spec"
-  for item in "${items[@]}"; do
-    item="${item//[[:space:]]/}"
-    [[ -n "$item" ]] || continue
-    [[ "$item" =~ ^([^:]+):([0-9]+)$ ]] || die "invalid object spec item: $item"
-    size="${BASH_REMATCH[1]}"
-    count="${BASH_REMATCH[2]}"
-    bytes="$(size_to_bytes "$size")"
-
-    for ((i = 1; i <= count; i++)); do
-      content="$(content_for_index "$index")"
-      ext="${content%%|*}"
-      mime="${content#*|}"
-      key="rw-stress/${size}/obj-$(printf '%06d' "$i").${ext}"
-      seed="${BUCKET}:${key}:${bytes}"
-      printf '%s\t%s\t%s\t%s\t%s\n' "$key" "$size" "$bytes" "$mime" "$seed" >> "$TASKS_FILE"
-      index=$((index + 1))
-    done
-  done
-}
-
-write_row_file_for_key() {
-  local key="$1"
-  echo "$WRITE_ROWS_DIR/${key//\//_}.csv"
-}
-
-prepare_write_input() {
-  WRITE_INPUT="$TASKS_FILE"
-  if [[ "$RESUME" != "true" ]]; then
-    return
-  fi
-
-  WRITE_INPUT="$OUT_DIR/tasks/write-input.tsv"
-  : > "$WRITE_INPUT"
-
-  local line key _size _bytes _mime _seed row_file
-  while IFS= read -r line || [[ -n "$line" ]]; do
-    IFS=$'\t' read -r key _size _bytes _mime _seed <<< "$line"
-    row_file="$(write_row_file_for_key "$key")"
-    [[ -s "$row_file" ]] && continue
-    printf '%s\n' "$line" >> "$WRITE_INPUT"
-  done < "$TASKS_FILE"
-}
-
-print_plan() {
-  local total_objects total_bytes profile_label
-  if [[ -f "$TASKS_FILE" ]]; then
-    total_objects="$(wc -l < "$TASKS_FILE" | tr -d ' ')"
-    total_bytes="$(awk -F '\t' '{sum += $3} END {print sum + 0}' "$TASKS_FILE")"
-    profile_label="$(profile_spec)"
-  else
-    total_objects="$(awk 'END {count = NR - 1; if (count < 0) count = 0; print count}' "$MANIFEST")"
-    total_bytes="$(awk -F ',' 'NR > 1 {sum += $3} END {print sum + 0}' "$MANIFEST")"
-    profile_label="from manifest"
-  fi
-
-  cat <<PLAN
-Mode:        $MODE
-Endpoint:    $ENDPOINT
-Bucket:      $BUCKET
-Profile:     $profile_label
-Objects:     $total_objects
-Bytes:       $total_bytes
-Concurrency: $CONCURRENCY
-Encryption:  $ENCRYPTION
-Client:      $CLIENT
-Manifest:    $MANIFEST
-Out dir:     $OUT_DIR
-Work dir:    $WORK_DIR
-PLAN
-}
-
-aws_base() {
-  AWS_ACCESS_KEY_ID="$ACCESS_KEY" AWS_SECRET_ACCESS_KEY="$SECRET_KEY" AWS_DEFAULT_REGION="$REGION" \
-    "$AWS_BIN" --endpoint-url "$ENDPOINT" "$@"
-}
-
-mc_base() {
-  "$MC_BIN" --config-dir "$MC_CONFIG_DIR_LOCAL" "$@"
-}
-
-aws_cp_args() {
-  case "$ENCRYPTION" in
-    none) ;;
-    sse-s3) printf '%s\n' "--sse" "AES256" ;;
-    sse-kms) printf '%s\n' "--sse" "aws:kms" "--sse-kms-key-id" "$SSE_KMS_KEY_ID" ;;
-    sse-c) printf '%s\n' "--sse-c" "AES256" "--sse-c-key" "fileb://$SSE_C_KEY_FILE" ;;
-  esac
-}
-
-mc_enc_target() {
-  printf '%s/%s/rw-stress/' "$MC_ALIAS" "$BUCKET"
-}
-
-mc_cp_args() {
-  local target
-  target="$(mc_enc_target)"
-  case "$ENCRYPTION" in
-    none) ;;
-    sse-s3) printf '%s\n' "--enc-s3" "$target" ;;
-    sse-kms) printf '%s\n' "--enc-kms" "${target}=${SSE_KMS_KEY_ID}" ;;
-    sse-c)
-      local key_b64
-      key_b64="$(base64 < "$SSE_C_KEY_FILE" | tr -d '\n')"
-      printf '%s\n' "--enc-c" "${target}=${key_b64}"
-      ;;
-  esac
-}
-
-aws_get_args() {
-  if [[ "$ENCRYPTION" == "sse-c" ]]; then
-    printf '%s\n' "--sse-c" "AES256" "--sse-c-key" "fileb://$SSE_C_KEY_FILE"
-  fi
-}
-
-mc_get_args() {
-  if [[ "$ENCRYPTION" == "sse-c" ]]; then
-    local target key_b64
-    target="$(mc_enc_target)"
-    key_b64="$(base64 < "$SSE_C_KEY_FILE" | tr -d '\n')"
-    printf '%s\n' "--enc-c" "${target}=${key_b64}"
-  fi
-}
-
-setup_mc_alias() {
-  if [[ "$CLIENT" != "mc" || "$DRY_RUN" == "true" ]]; then
-    return
-  fi
-  mkdir -p "$MC_CONFIG_DIR_LOCAL"
-  mc_base alias set "$MC_ALIAS" "$ENDPOINT" "$ACCESS_KEY" "$SECRET_KEY" --api S3v4 --path auto >/dev/null
-}
-
-create_bucket_if_needed() {
-  if [[ "$DRY_RUN" == "true" ]]; then
-    echo "[DRY-RUN] create bucket if missing: $BUCKET"
-    return
-  fi
-
-  if [[ "$CLIENT" == "mc" ]]; then
-    mc_base mb --ignore-existing --region "$REGION" "$MC_ALIAS/$BUCKET" >/dev/null
-    return
-  fi
-
-  if aws_base s3api head-bucket --bucket "$BUCKET" >/dev/null 2>&1; then
-    return
-  fi
-
-  aws_base s3api create-bucket --bucket "$BUCKET" >/dev/null
-}
-
-payload_path_for_key() {
-  local key="$1"
-  echo "$WORK_DIR/${key//\//_}"
-}
-
-generate_payload() {
-  local file="$1"
-  local bytes="$2"
-  local seed="$3"
-  local pattern="$DATA_PATTERN"
-  mkdir -p "$(dirname "$file")"
-
-  if [[ "$pattern" == "mixed" ]]; then
-    if [[ $((bytes % 2)) -eq 0 ]]; then
-      pattern="compressible"
-    else
-      pattern="random"
-    fi
-  fi
-
-  if [[ "$pattern" == "random" ]]; then
-    head -c "$bytes" /dev/zero | openssl enc -aes-256-ctr -nosalt -pass "pass:$seed" -out "$file"
-  else
-    yes "$seed payload-for-rio-compatibility" | tr '\n' ' ' | head -c "$bytes" > "$file"
-  fi
-}
-
-sha256_file() {
-  shasum -a 256 "$1" | awk '{print $1}'
-}
-
-sha256_object() {
-  local key="$1"
-  shift
-  if [[ "$CLIENT" == "mc" ]]; then
-    mc_base cat "$@" "$MC_ALIAS/$BUCKET/$key" | shasum -a 256 | awk '{print $1}'
-  else
-    aws_base s3 cp "s3://$BUCKET/$key" - --no-progress "$@" | shasum -a 256 | awk '{print $1}'
-  fi
-}
-
-collect_args() {
-  local generator="$1"
-  extra_args=()
-  while IFS= read -r arg; do
-    extra_args+=("$arg")
-  done < <("$generator")
-}
-
-write_one() {
-  local line="$1"
-  local key size bytes mime seed file sha row_file
-  local -a extra_args
-  IFS=$'\t' read -r key size bytes mime seed <<< "$line"
-  file="$(payload_path_for_key "$key")"
-  row_file="$(write_row_file_for_key "$key")"
-
-  if [[ "$DRY_RUN" == "true" ]]; then
-    echo "[DRY-RUN] upload $bytes bytes to s3://$BUCKET/$key content-type=$mime"
-    printf '%s,%s,%s,%s,%s,%s\n' "$key" "$size" "$bytes" "$mime" "DRY_RUN" "$ENCRYPTION" > "$row_file"
-    return
-  fi
-
-  generate_payload "$file" "$bytes" "$seed"
-  sha="$(sha256_file "$file")"
-
-  if [[ "$CLIENT" == "mc" ]]; then
-    collect_args mc_cp_args
-    mc_base cp --quiet --attr "Content-Type=$mime" ${extra_args[@]+"${extra_args[@]}"} "$file" "$MC_ALIAS/$BUCKET/$key" \
-      > "$OUT_DIR/logs/${key//\//_}.put.log" 2>&1
-  else
-    collect_args aws_cp_args
-    aws_base s3 cp "$file" "s3://$BUCKET/$key" --no-progress --content-type "$mime" ${extra_args[@]+"${extra_args[@]}"} \
-      > "$OUT_DIR/logs/${key//\//_}.put.log" 2>&1
-  fi
-
-  printf '%s,%s,%s,%s,%s,%s\n' "$key" "$size" "$bytes" "$mime" "$sha" "$ENCRYPTION" > "$row_file"
-  if [[ "$KEEP_PAYLOADS" != "true" ]]; then
-    rm -f "$file"
-  fi
-}
-
-verify_one() {
-  local line="$1"
-  local key size bytes mime expected encryption actual row_file
-  local -a extra_args
-  IFS=',' read -r key size bytes mime expected encryption <<< "$line"
-  row_file="$VERIFY_ROWS_DIR/${key//\//_}.csv"
-
-  if [[ "$DRY_RUN" == "true" ]]; then
-    echo "[DRY-RUN] verify s3://$BUCKET/$key expected=$expected"
-    printf '%s,%s,%s,%s,%s,%s,%s\n' "$key" "$size" "$bytes" "$mime" "$expected" "DRY_RUN" "dry-run" > "$row_file"
-    return
-  fi
-
-  if [[ "$CLIENT" == "mc" ]]; then
-    collect_args mc_get_args
-  else
-    collect_args aws_get_args
-  fi
-  if ! actual="$(sha256_object "$key" ${extra_args[@]+"${extra_args[@]}"})"; then
-    printf '%s,%s,%s,%s,%s,%s,%s\n' "$key" "$size" "$bytes" "$mime" "$expected" "ERROR" "download failed" > "$row_file"
-    return 1
-  fi
-
-  if [[ "$actual" == "$expected" ]]; then
-    printf '%s,%s,%s,%s,%s,%s,%s\n' "$key" "$size" "$bytes" "$mime" "$expected" "$actual" "ok" > "$row_file"
-  else
-    printf '%s,%s,%s,%s,%s,%s,%s\n' "$key" "$size" "$bytes" "$mime" "$expected" "$actual" "sha256-mismatch" > "$row_file"
-    return 1
-  fi
-}
-
-run_parallel_tasks() {
-  local action="$1"
-  local input_file="$2"
-  local failure_file="$OUT_DIR/tasks/${action}.failed"
-  local line
-  rm -f "$failure_file"
-
-  while IFS= read -r line || [[ -n "$line" ]]; do
-    while [[ "$(jobs -rp | wc -l | tr -d ' ')" -ge "$CONCURRENCY" ]]; do
-      sleep 0.2
-    done
-
-    ({
-      if [[ "$action" == "write" ]]; then
-        write_one "$line"
-      else
-        verify_one "$line"
-      fi
-    } || touch "$failure_file") &
-  done < "$input_file"
-
-  wait
-  [[ ! -f "$failure_file" ]]
-}
-
-combine_write_manifest() {
-  echo "key,size,bytes,content_type,sha256,encryption" > "$MANIFEST"
-  find "$WRITE_ROWS_DIR" -type f -name '*.csv' -print0 | sort -z | xargs -0 cat >> "$MANIFEST"
-
-  local expected actual
-  expected="$(wc -l < "$TASKS_FILE" | tr -d ' ')"
-  actual="$(( $(wc -l < "$MANIFEST" | tr -d ' ') - 1 ))"
-  if [[ "$actual" -ne "$expected" ]]; then
-    die "manifest row count mismatch: expected $expected, got $actual"
-  fi
-}
-
-prepare_verify_input() {
-  VERIFY_INPUT="$OUT_DIR/tasks/verify-input.csv"
-  tail -n +2 "$MANIFEST" > "$VERIFY_INPUT"
-}
-
-combine_verify_summary() {
-  VERIFY_SUMMARY="$OUT_DIR/verify-summary.csv"
-  echo "key,size,bytes,content_type,expected_sha256,actual_sha256,status" > "$VERIFY_SUMMARY"
-  find "$VERIFY_ROWS_DIR" -type f -name '*.csv' -print0 | sort -z | xargs -0 cat >> "$VERIFY_SUMMARY"
-
-  local failed
-  if [[ "$DRY_RUN" == "true" ]]; then
-    echo "Verification dry run complete. Summary: $VERIFY_SUMMARY"
-    return
-  fi
-
-  failed="$(awk -F ',' 'NR > 1 && $7 != "ok" {count++} END {print count + 0}' "$VERIFY_SUMMARY")"
-  local expected actual
-  expected="$(wc -l < "$VERIFY_INPUT" | tr -d ' ')"
-  actual="$(( $(wc -l < "$VERIFY_SUMMARY" | tr -d ' ') - 1 ))"
-  if [[ "$actual" -ne "$expected" ]]; then
-    echo "Verification row count mismatch: expected $expected, got $actual" >&2
-    return 1
-  fi
-  if [[ "$failed" -ne 0 ]]; then
-    echo "Verification failed: $failed object(s). See $VERIFY_SUMMARY" >&2
-    return 1
-  fi
-  echo "Verification passed. Summary: $VERIFY_SUMMARY"
-}
-
-export_functions() {
-  export ENDPOINT ACCESS_KEY SECRET_KEY BUCKET REGION ENCRYPTION SSE_KMS_KEY_ID SSE_C_KEY_FILE AWS_BIN
-  export CLIENT MC_BIN MC_CONFIG_DIR_LOCAL MC_ALIAS
-  export WORK_DIR OUT_DIR WRITE_ROWS_DIR VERIFY_ROWS_DIR DATA_PATTERN KEEP_PAYLOADS DRY_RUN
-  export -f aws_base mc_base aws_cp_args aws_get_args mc_enc_target mc_cp_args mc_get_args payload_path_for_key generate_payload sha256_file sha256_object write_one verify_one
-}
-
-main() {
-  parse_args "$@"
-  validate_args
-  setup_paths
-
-  if [[ "$DRY_RUN" != "true" ]]; then
-    if [[ "$CLIENT" == "mc" ]]; then
-      MC_BIN="$(resolve_mc_bin)"
-      [[ -n "$MC_BIN" ]] || die "mc binary not found; pass --mc-bin or put mc in PATH"
-      require_cmd "$MC_BIN"
-    else
-      require_cmd "$AWS_BIN"
-    fi
-    require_cmd shasum
-    require_cmd head
-    require_cmd yes
-    require_cmd openssl
-  elif [[ "$CLIENT" == "mc" ]]; then
-    MC_BIN="$(resolve_mc_bin)"
-  fi
-
-  setup_mc_alias
-
-  if [[ "$MODE" == "write" || "$MODE" == "mixed" ]]; then
-    local write_failed=false
-    generate_tasks
-    prepare_write_input
-    print_plan
-    create_bucket_if_needed
-    export_functions
-    if ! run_parallel_tasks write "$WRITE_INPUT"; then
-      write_failed=true
-    fi
-    combine_write_manifest
-    echo "Write manifest: $MANIFEST"
-    if [[ "$write_failed" == "true" ]]; then
-      die "one or more write tasks failed; see $OUT_DIR/logs"
-    fi
-  fi
-
-  if [[ "$MODE" == "verify" || "$MODE" == "mixed" ]]; then
-    local verify_failed=false
-    [[ -f "$MANIFEST" ]] || die "manifest not found: $MANIFEST"
-    if [[ "$MODE" == "verify" ]]; then
-      cp "$MANIFEST" "$OUT_DIR/manifest.csv"
-      MANIFEST="$OUT_DIR/manifest.csv"
-    fi
-    prepare_verify_input
-    print_plan
-    export_functions
-    if ! run_parallel_tasks verify "$VERIFY_INPUT"; then
-      verify_failed=true
-    fi
-    combine_verify_summary
-    if [[ "$verify_failed" == "true" ]]; then
-      die "one or more verify tasks failed; see $VERIFY_SUMMARY"
-    fi
-  fi
-}
-
-main "$@"

.docker/test/issue-2715/docker-compose-test.yml

@@ -1,52 +0,0 @@
-services:
-  rustfs:
-    image: rustfs/rustfs:1.0.0-alpha.99-glibc
-    container_name: rustfs-issue-2715-test
-    security_opt:
-      - "no-new-privileges:true"
-    ports:
-      - "19000:9000"
-      - "19001:9001"
-    environment:
-      - RUSTFS_VOLUMES=/data/rustfs{0...8}
-      - RUSTFS_ADDRESS=0.0.0.0:9000
-      - RUSTFS_CONSOLE_ADDRESS=0.0.0.0:9001
-      - RUSTFS_CONSOLE_ENABLE=true
-      - RUSTFS_CORS_ALLOWED_ORIGINS=*
-      - RUSTFS_CONSOLE_CORS_ALLOWED_ORIGINS=*
-      - RUSTFS_ACCESS_KEY=admin
-      - RUSTFS_SECRET_KEY=admin
-      - RUSTFS_OBS_LOGGER_LEVEL=info
-      - RUSTFS_OBS_ENDPOINT=http://otel-collector:4318
-      - RUSTFS_OBS_PROFILING_ENDPOINT=http://pyroscope:4040
-      - RUSTFS_STORAGE_CLASS_STANDARD=EC:2
-      - RUSTFS_STORAGE_CLASS_RRS=EC:1
-      - RUSTFS_UNSAFE_BYPASS_DISK_CHECK=true
-      - RUSTFS_OBS_LOG_DIRECTORY=/opt/rustfs/logs
-    extra_hosts:
-      - "otel-collector:host-gateway"
-      - "pyroscope:host-gateway"
-    volumes:
-      - ./deploy/data/issue-2715/rustfs0:/data/rustfs0
-      - ./deploy/data/issue-2715/rustfs1:/data/rustfs1
-      - ./deploy/data/issue-2715/rustfs2:/data/rustfs2
-      - ./deploy/data/issue-2715/rustfs3:/data/rustfs3
-      - ./deploy/data/issue-2715/rustfs4:/data/rustfs4
-      - ./deploy/data/issue-2715/rustfs5:/data/rustfs5
-      - ./deploy/data/issue-2715/rustfs6:/data/rustfs6
-      - ./deploy/data/issue-2715/rustfs7:/data/rustfs7
-      - ./deploy/data/issue-2715/rustfs8:/data/rustfs8
-      - ./deploy/logs/issue-2715:/opt/rustfs/logs
-    restart: unless-stopped
-    healthcheck:
-      test:
-        [
-          "CMD",
-          "sh",
-          "-c",
-          "curl -f http://127.0.0.1:9000/health && curl -f http://127.0.0.1:9001/rustfs/console/health"
-        ]
-      interval: 30s
-      timeout: 10s
-      retries: 3
-      start_period: 40s

.docker/test/issues-2815/.gitignore

@@ -1 +0,0 @@
-data/

.docker/test/issues-2815/README.md

@@ -1,106 +0,0 @@
-# Issue 2815 Local Docker Verification
-
-## Purpose
-
-This directory contains the local distributed Docker verification assets used to validate issue `#2815` against the current source build.
-
-The target behavior is:
-
-- 4-node distributed cluster starts successfully
-- `/health/ready` becomes reachable on each node
-- logs no longer contain `storage_info failed: Io error: wrong msgpack marker FixArray(1)`
-- internode RPC authentication succeeds with an explicit non-default RPC secret
-
-## Files
-
-- `docker-compose.yml`: 4-node distributed cluster using a locally built image
-
-## Data Directories
-
-Create the bind-mount directories before `docker compose up`:
-
-```bash
-mkdir -p .docker/test/issues-2815/data/rustfs{1..4}-disk{0..3}
-```
-
-## Build
-
-Apple Silicon / arm64 host:
-
-```bash
-docker build --platform linux/arm64 -f Dockerfile.source -t rustfs-issue-2815-local .
-```
-
-If you intentionally want amd64 emulation:
-
-```bash
-docker build --platform linux/amd64 -f Dockerfile.source -t rustfs-issue-2815-local .
-```
-
-## Run
-
-```bash
-docker compose -f .docker/test/issues-2815/docker-compose.yml up -d
-```
-
-If the image platform is not `linux/arm64`, align compose explicitly:
-
-```bash
-RUSTFS_DOCKER_PLATFORM=linux/amd64 docker compose -f .docker/test/issues-2815/docker-compose.yml up -d
-```
-
-## Health Checks
-
-Container-level healthcheck is now included and probes:
-
-```bash
-curl -fsS http://127.0.0.1:9000/health
-```
-
-Manual checks:
-
-```bash
-curl -i http://127.0.0.1:9101/health/ready
-curl -i http://127.0.0.1:9102/health/ready
-curl -i http://127.0.0.1:9103/health/ready
-curl -i http://127.0.0.1:9104/health/ready
-```
-
-## RPC Secret Requirement
-
-The current source build no longer reproduces the original `FixArray(1)` decode error from issue `#2815`.
-
-Earlier local Docker attempts failed during erasure bootstrap with:
-
-```text
-No valid auth token
-store init failed to load formats after 10 retries: erasure read quorum
-```
-
-Root cause:
-
-- RPC authentication rejects the default secret `rustfsadmin`
-- distributed local Docker validation therefore needs an explicit non-default secret
-
-This compose now sets both:
-
-- `RUSTFS_SECRET_KEY=issue-2815-secret`
-- `RUSTFS_RPC_SECRET=issue-2815-rpc-secret`
-
-With those values in place, the current 4-node local Docker cluster reaches healthy state and `/health/ready` returns `200`.
-
-In other words:
-
-- `RUSTFS_ACCESS_KEY` may still be `rustfsadmin` for local service credentials if desired
-- `RUSTFS_SECRET_KEY` can still be used for service credentials
-- but RPC authentication must not resolve to the default secret value `rustfsadmin`
-- if `RUSTFS_RPC_SECRET` is unset, the code falls back to `RUSTFS_SECRET_KEY`
-- so at least one of them must provide a non-default shared secret for internode RPC signing
-
-## Suggested Debug Commands
-
-```bash
-docker compose -f .docker/test/issues-2815/docker-compose.yml ps
-docker compose -f .docker/test/issues-2815/docker-compose.yml logs --no-color --tail=200
-docker compose -f .docker/test/issues-2815/docker-compose.yml down -v
-```

.docker/test/issues-2815/docker-compose.yml

@@ -1,120 +0,0 @@
-services:
-  rustfs1:
-    image: rustfs-issue-2815-local
-    platform: ${RUSTFS_DOCKER_PLATFORM:-linux/arm64}
-    hostname: rustfs1
-    container_name: rustfs-issue-2815-rustfs1
-    environment:
-      RUSTFS_ADDRESS: "0.0.0.0:9000"
-      RUSTFS_ACCESS_KEY: "rustfsadmin"
-      RUSTFS_SECRET_KEY: "issue-2815-secret"
-      RUSTFS_RPC_SECRET: "issue-2815-rpc-secret"
-      RUSTFS_CONSOLE_ENABLE: "false"
-      RUST_LOG: "info"
-      RUSTFS_UNSAFE_BYPASS_DISK_CHECK: "true"
-      RUSTFS_VOLUMES: "http://rustfs{1...4}:9000/data/rustfs{0...3}"
-    volumes:
-      - ./data/rustfs1-disk0:/data/rustfs0
-      - ./data/rustfs1-disk1:/data/rustfs1
-      - ./data/rustfs1-disk2:/data/rustfs2
-      - ./data/rustfs1-disk3:/data/rustfs3
-    networks: [rustfs-issue-2815-net]
-    ports:
-      - "9101:9000"
-    healthcheck:
-      test: ["CMD", "sh", "-c", "curl -fsS http://127.0.0.1:9000/health || exit 1"]
-      interval: 15s
-      timeout: 5s
-      retries: 8
-      start_period: 30s
-
-  rustfs2:
-    image: rustfs-issue-2815-local
-    platform: ${RUSTFS_DOCKER_PLATFORM:-linux/arm64}
-    hostname: rustfs2
-    container_name: rustfs-issue-2815-rustfs2
-    environment:
-      RUSTFS_ADDRESS: "0.0.0.0:9000"
-      RUSTFS_ACCESS_KEY: "rustfsadmin"
-      RUSTFS_SECRET_KEY: "issue-2815-secret"
-      RUSTFS_RPC_SECRET: "issue-2815-rpc-secret"
-      RUSTFS_CONSOLE_ENABLE: "false"
-      RUST_LOG: "info"
-      RUSTFS_UNSAFE_BYPASS_DISK_CHECK: "true"
-      RUSTFS_VOLUMES: "http://rustfs{1...4}:9000/data/rustfs{0...3}"
-    volumes:
-      - ./data/rustfs2-disk0:/data/rustfs0
-      - ./data/rustfs2-disk1:/data/rustfs1
-      - ./data/rustfs2-disk2:/data/rustfs2
-      - ./data/rustfs2-disk3:/data/rustfs3
-    networks: [rustfs-issue-2815-net]
-    ports:
-      - "9102:9000"
-    healthcheck:
-      test: ["CMD", "sh", "-c", "curl -fsS http://127.0.0.1:9000/health || exit 1"]
-      interval: 15s
-      timeout: 5s
-      retries: 8
-      start_period: 30s
-
-  rustfs3:
-    image: rustfs-issue-2815-local
-    platform: ${RUSTFS_DOCKER_PLATFORM:-linux/arm64}
-    hostname: rustfs3
-    container_name: rustfs-issue-2815-rustfs3
-    environment:
-      RUSTFS_ADDRESS: "0.0.0.0:9000"
-      RUSTFS_ACCESS_KEY: "rustfsadmin"
-      RUSTFS_SECRET_KEY: "issue-2815-secret"
-      RUSTFS_RPC_SECRET: "issue-2815-rpc-secret"
-      RUSTFS_CONSOLE_ENABLE: "false"
-      RUST_LOG: "info"
-      RUSTFS_UNSAFE_BYPASS_DISK_CHECK: "true"
-      RUSTFS_VOLUMES: "http://rustfs{1...4}:9000/data/rustfs{0...3}"
-    volumes:
-      - ./data/rustfs3-disk0:/data/rustfs0
-      - ./data/rustfs3-disk1:/data/rustfs1
-      - ./data/rustfs3-disk2:/data/rustfs2
-      - ./data/rustfs3-disk3:/data/rustfs3
-    networks: [rustfs-issue-2815-net]
-    ports:
-      - "9103:9000"
-    healthcheck:
-      test: ["CMD", "sh", "-c", "curl -fsS http://127.0.0.1:9000/health || exit 1"]
-      interval: 15s
-      timeout: 5s
-      retries: 8
-      start_period: 30s
-
-  rustfs4:
-    image: rustfs-issue-2815-local
-    platform: ${RUSTFS_DOCKER_PLATFORM:-linux/arm64}
-    hostname: rustfs4
-    container_name: rustfs-issue-2815-rustfs4
-    environment:
-      RUSTFS_ADDRESS: "0.0.0.0:9000"
-      RUSTFS_ACCESS_KEY: "rustfsadmin"
-      RUSTFS_SECRET_KEY: "issue-2815-secret"
-      RUSTFS_RPC_SECRET: "issue-2815-rpc-secret"
-      RUSTFS_CONSOLE_ENABLE: "false"
-      RUST_LOG: "info"
-      RUSTFS_UNSAFE_BYPASS_DISK_CHECK: "true"
-      RUSTFS_VOLUMES: "http://rustfs{1...4}:9000/data/rustfs{0...3}"
-    volumes:
-      - ./data/rustfs4-disk0:/data/rustfs0
-      - ./data/rustfs4-disk1:/data/rustfs1
-      - ./data/rustfs4-disk2:/data/rustfs2
-      - ./data/rustfs4-disk3:/data/rustfs3
-    networks: [rustfs-issue-2815-net]
-    ports:
-      - "9104:9000"
-    healthcheck:
-      test: ["CMD", "sh", "-c", "curl -fsS http://127.0.0.1:9000/health || exit 1"]
-      interval: 15s
-      timeout: 5s
-      retries: 8
-      start_period: 30s
-
-networks:
-  rustfs-issue-2815-net:
-    name: rustfs-issue-2815-net

.docker/test/site-replication/README.md

@@ -1,183 +0,0 @@
-# Site Replication Docker Compose Test
-
-## Purpose
-
-This directory contains a local three-site RustFS site replication check. It is intended to verify the admin site-replication flow against real containers:
-
-- three independent RustFS sites start successfully
-- the MinIO-compatible `mc admin replicate add` command configures all three sites
-- a bucket and object written to site 1 are replicated to site 2 and site 3
-- `mc admin replicate status` can read the resulting site-replication state
-
-The compose file uses named volumes so the test does not require preparing host bind-mount directories.
-Because Docker named volumes usually share the same physical device in local desktop environments, this test compose defaults `RUSTFS_UNSAFE_BYPASS_DISK_CHECK=true`. Keep that setting limited to local test and CI environments.
-
-## Files
-
-- `docker-compose.yml`: three RustFS sites, a volume permission helper, and a one-shot setup/check container
-- `run-object-flow-check.sh`: host-side upload/download verification for replicated 10 MiB to 100 MiB objects
-
-## Ports
-
-Default host endpoints:
-
-- Site 1 API: `http://127.0.0.1:9000`
-- Site 1 Console: `http://127.0.0.1:9001`
-- Site 2 API: `http://127.0.0.1:9010`
-- Site 2 Console: `http://127.0.0.1:9011`
-- Site 3 API: `http://127.0.0.1:9020`
-- Site 3 Console: `http://127.0.0.1:9021`
-
-Default credentials are `rustfsadmin` / `rustfsadmin`. These are for local testing only.
-
-## Run
-
-From the repository root:
-
-```bash
-docker compose -f .docker/test/site-replication/docker-compose.yml up
-```
-
-To test a locally built image instead of Docker Hub `rustfs/rustfs:latest`, set `RUSTFS_SITE_REPL_IMAGE`:
-
-```bash
-docker build -f Dockerfile.source -t rustfs-site-repl-local:latest .
-RUSTFS_SITE_REPL_IMAGE=rustfs-site-repl-local:latest \
-docker compose -f .docker/test/site-replication/docker-compose.yml up
-```
-
-For a detached run:
-
-```bash
-docker compose -f .docker/test/site-replication/docker-compose.yml up -d
-docker compose -f .docker/test/site-replication/docker-compose.yml logs -f site-replication-setup
-```
-
-## Test Flow
-
-The compose stack performs these steps:
-
-1. `site-replication-volume-permission-helper` fixes ownership on all named volumes for the RustFS runtime user.
-2. `rustfs-site1`, `rustfs-site2`, and `rustfs-site3` start as separate RustFS sites.
-3. Each site exposes its S3 API and Console on a unique host port.
-4. Health checks wait for `/health/ready` on each RustFS container.
-5. `site-replication-setup` configures `mc` aliases for all three sites.
-6. The setup container waits until `mc admin info` succeeds for all sites.
-7. It runs:
-
-```bash
-mc admin replicate add site1 site2 site3
-```
-
-8. It creates the test bucket on site 1 and uploads `from-site1.txt`.
-9. It polls site 2 and site 3 until the replicated object is visible.
-10. It prints `mc admin replicate status site1`.
-
-The setup container exits with status `0` only after the object replication check passes.
-
-## Object Flow Check
-
-After the compose setup succeeds, run the larger object flow check from the repository root:
-
-```bash
-.docker/test/site-replication/run-object-flow-check.sh
-```
-
-The script creates five local files and uploads them from different sites:
-
-- 10 MiB from site 1
-- 25 MiB from site 2
-- 50 MiB from site 3
-- 75 MiB from site 1
-- 100 MiB from site 2
-
-For each uploaded object, the script waits for replication to the other two sites, downloads the object from those sites, and verifies both byte size and SHA-256 checksum. It uses a temporary `mc` config directory, so it does not overwrite existing host aliases.
-
-The default bucket is `site-repl-flow-check`. Override it when needed:
-
-```bash
-RUSTFS_SITE_REPL_FLOW_BUCKET='site-repl-large-flow' \
-.docker/test/site-replication/run-object-flow-check.sh
-```
-
-The script keeps uploaded objects under a timestamped prefix. Override the prefix for repeatable runs:
-
-```bash
-RUSTFS_SITE_REPL_FLOW_PREFIX='manual-check-001' \
-.docker/test/site-replication/run-object-flow-check.sh
-```
-
-If replication is slow on the local machine, increase polling:
-
-```bash
-RUSTFS_SITE_REPL_WAIT_ATTEMPTS=180 \
-RUSTFS_SITE_REPL_WAIT_SLEEP_SECONDS=2 \
-.docker/test/site-replication/run-object-flow-check.sh
-```
-
-## Optional Settings
-
-Override local test credentials:
-
-```bash
-RUSTFS_SITE_REPL_ACCESS_KEY='localadmin' \
-RUSTFS_SITE_REPL_SECRET_KEY='localadmin-secret' \
-docker compose -f .docker/test/site-replication/docker-compose.yml up
-```
-
-Use a different test bucket:
-
-```bash
-RUSTFS_SITE_REPL_BUCKET='site-repl-check' \
-docker compose -f .docker/test/site-replication/docker-compose.yml up
-```
-
-Enable ILM expiry rule replication during site setup:
-
-```bash
-RUSTFS_SITE_REPL_ENABLE_ILM_EXPIRY=true \
-docker compose -f .docker/test/site-replication/docker-compose.yml up
-```
-
-Use this only when the test needs lifecycle expiry metadata included in site replication.
-
-## Manual Checks
-
-After the setup container succeeds, you can inspect the sites with `mc` from the host:
-
-```bash
-mc alias set site1 http://127.0.0.1:9000 rustfsadmin rustfsadmin
-mc alias set site2 http://127.0.0.1:9010 rustfsadmin rustfsadmin
-mc alias set site3 http://127.0.0.1:9020 rustfsadmin rustfsadmin
-
-mc admin replicate info site1
-mc admin replicate status site1
-mc stat site2/site-repl-demo/from-site1.txt
-mc stat site3/site-repl-demo/from-site1.txt
-```
-
-After larger object flow checks, replication should converge without a growing queue:
-
-```bash
-mc admin replicate status site1
-mc admin replicate status site2
-mc admin replicate status site3
-```
-
-Useful Docker commands:
-
-```bash
-docker compose -f .docker/test/site-replication/docker-compose.yml ps
-docker compose -f .docker/test/site-replication/docker-compose.yml logs --no-color --tail=200
-docker compose -f .docker/test/site-replication/docker-compose.yml logs --no-color site-replication-setup
-```
-
-## Cleanup
-
-Remove containers and named volumes:
-
-```bash
-docker compose -f .docker/test/site-replication/docker-compose.yml down -v
-```
-
-Use `down -v` before rerunning the full setup from scratch. Site replication state is persisted in the named volumes, so rerunning without deleting volumes may attempt to add an already-configured replication topology.

.docker/test/site-replication/docker-compose.yml

@@ -1,243 +0,0 @@
-# Copyright 2024 RustFS Team
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-
-services:
-  rustfs-site1:
-    image: ${RUSTFS_SITE_REPL_IMAGE:-rustfs/rustfs:latest}
-    container_name: rustfs-site-repl-1
-    security_opt:
-      - "no-new-privileges:true"
-    ports:
-      - "9000:9000"
-      - "9001:9001"
-    environment:
-      - RUSTFS_VOLUMES=/data/rustfs{0...3}
-      - RUSTFS_ADDRESS=0.0.0.0:9000
-      - RUSTFS_CONSOLE_ADDRESS=0.0.0.0:9001
-      - RUSTFS_CONSOLE_ENABLE=true
-      - RUSTFS_CONSOLE_CORS_ALLOWED_ORIGINS=*
-      - RUSTFS_ACCESS_KEY=${RUSTFS_SITE_REPL_ACCESS_KEY:-rustfsadmin}
-      - RUSTFS_SECRET_KEY=${RUSTFS_SITE_REPL_SECRET_KEY:-rustfsadmin}
-      - RUSTFS_OBS_LOGGER_LEVEL=${RUSTFS_SITE_REPL_LOG_LEVEL:-info}
-      - RUSTFS_UNSAFE_BYPASS_DISK_CHECK=${RUSTFS_UNSAFE_BYPASS_DISK_CHECK:-true}
-    volumes:
-      - site1_data_0:/data/rustfs0
-      - site1_data_1:/data/rustfs1
-      - site1_data_2:/data/rustfs2
-      - site1_data_3:/data/rustfs3
-      - site1_logs:/app/logs
-    networks:
-      - rustfs-site-replication
-    restart: unless-stopped
-    healthcheck:
-      test: ["CMD", "curl", "-fsS", "http://127.0.0.1:9000/health/ready"]
-      interval: 10s
-      timeout: 5s
-      retries: 30
-      start_period: 20s
-    depends_on:
-      site-replication-volume-permission-helper:
-        condition: service_completed_successfully
-
-  rustfs-site2:
-    image: ${RUSTFS_SITE_REPL_IMAGE:-rustfs/rustfs:latest}
-    container_name: rustfs-site-repl-2
-    security_opt:
-      - "no-new-privileges:true"
-    ports:
-      - "9010:9000"
-      - "9011:9001"
-    environment:
-      - RUSTFS_VOLUMES=/data/rustfs{0...3}
-      - RUSTFS_ADDRESS=0.0.0.0:9000
-      - RUSTFS_CONSOLE_ADDRESS=0.0.0.0:9001
-      - RUSTFS_CONSOLE_ENABLE=true
-      - RUSTFS_CONSOLE_CORS_ALLOWED_ORIGINS=*
-      - RUSTFS_ACCESS_KEY=${RUSTFS_SITE_REPL_ACCESS_KEY:-rustfsadmin}
-      - RUSTFS_SECRET_KEY=${RUSTFS_SITE_REPL_SECRET_KEY:-rustfsadmin}
-      - RUSTFS_OBS_LOGGER_LEVEL=${RUSTFS_SITE_REPL_LOG_LEVEL:-info}
-      - RUSTFS_UNSAFE_BYPASS_DISK_CHECK=${RUSTFS_UNSAFE_BYPASS_DISK_CHECK:-true}
-    volumes:
-      - site2_data_0:/data/rustfs0
-      - site2_data_1:/data/rustfs1
-      - site2_data_2:/data/rustfs2
-      - site2_data_3:/data/rustfs3
-      - site2_logs:/app/logs
-    networks:
-      - rustfs-site-replication
-    restart: unless-stopped
-    healthcheck:
-      test: ["CMD", "curl", "-fsS", "http://127.0.0.1:9000/health/ready"]
-      interval: 10s
-      timeout: 5s
-      retries: 30
-      start_period: 20s
-    depends_on:
-      site-replication-volume-permission-helper:
-        condition: service_completed_successfully
-
-  rustfs-site3:
-    image: ${RUSTFS_SITE_REPL_IMAGE:-rustfs/rustfs:latest}
-    container_name: rustfs-site-repl-3
-    security_opt:
-      - "no-new-privileges:true"
-    ports:
-      - "9020:9000"
-      - "9021:9001"
-    environment:
-      - RUSTFS_VOLUMES=/data/rustfs{0...3}
-      - RUSTFS_ADDRESS=0.0.0.0:9000
-      - RUSTFS_CONSOLE_ADDRESS=0.0.0.0:9001
-      - RUSTFS_CONSOLE_ENABLE=true
-      - RUSTFS_CONSOLE_CORS_ALLOWED_ORIGINS=*
-      - RUSTFS_ACCESS_KEY=${RUSTFS_SITE_REPL_ACCESS_KEY:-rustfsadmin}
-      - RUSTFS_SECRET_KEY=${RUSTFS_SITE_REPL_SECRET_KEY:-rustfsadmin}
-      - RUSTFS_OBS_LOGGER_LEVEL=${RUSTFS_SITE_REPL_LOG_LEVEL:-info}
-      - RUSTFS_UNSAFE_BYPASS_DISK_CHECK=${RUSTFS_UNSAFE_BYPASS_DISK_CHECK:-true}
-    volumes:
-      - site3_data_0:/data/rustfs0
-      - site3_data_1:/data/rustfs1
-      - site3_data_2:/data/rustfs2
-      - site3_data_3:/data/rustfs3
-      - site3_logs:/app/logs
-    networks:
-      - rustfs-site-replication
-    restart: unless-stopped
-    healthcheck:
-      test: ["CMD", "curl", "-fsS", "http://127.0.0.1:9000/health/ready"]
-      interval: 10s
-      timeout: 5s
-      retries: 30
-      start_period: 20s
-    depends_on:
-      site-replication-volume-permission-helper:
-        condition: service_completed_successfully
-
-  site-replication-setup:
-    image: minio/mc:latest
-    container_name: rustfs-site-repl-setup
-    depends_on:
-      rustfs-site1:
-        condition: service_healthy
-      rustfs-site2:
-        condition: service_healthy
-      rustfs-site3:
-        condition: service_healthy
-    environment:
-      - RUSTFS_SITE_REPL_ACCESS_KEY=${RUSTFS_SITE_REPL_ACCESS_KEY:-rustfsadmin}
-      - RUSTFS_SITE_REPL_SECRET_KEY=${RUSTFS_SITE_REPL_SECRET_KEY:-rustfsadmin}
-      - RUSTFS_SITE_REPL_BUCKET=${RUSTFS_SITE_REPL_BUCKET:-site-repl-demo}
-      - RUSTFS_SITE_REPL_ENABLE_ILM_EXPIRY=${RUSTFS_SITE_REPL_ENABLE_ILM_EXPIRY:-false}
-    networks:
-      - rustfs-site-replication
-    entrypoint: ["/bin/sh", "-c"]
-    command:
-      - |
-        set -eu
-
-        access_key="$${RUSTFS_SITE_REPL_ACCESS_KEY}"
-        secret_key="$${RUSTFS_SITE_REPL_SECRET_KEY}"
-        bucket="$${RUSTFS_SITE_REPL_BUCKET}"
-
-        mc alias set site1 http://rustfs-site1:9000 "$${access_key}" "$${secret_key}"
-        mc alias set site2 http://rustfs-site2:9000 "$${access_key}" "$${secret_key}"
-        mc alias set site3 http://rustfs-site3:9000 "$${access_key}" "$${secret_key}"
-
-        for site in site1 site2 site3; do
-          until mc ls "$${site}" >/dev/null 2>&1; do
-            echo "waiting for $${site} S3 API"
-            sleep 2
-          done
-        done
-
-        ilm_flag=""
-        if [ "$${RUSTFS_SITE_REPL_ENABLE_ILM_EXPIRY}" = "true" ]; then
-          ilm_flag="--replicate-ilm-expiry"
-        fi
-
-        echo "configuring 3-site replication"
-        if ! mc admin replicate add site1 site2 site3 $${ilm_flag}; then
-          echo "replicate add failed; showing current replication info before exiting"
-          mc admin replicate info site1 || true
-          exit 1
-        fi
-
-        mc mb --ignore-existing "site1/$${bucket}"
-        printf 'rustfs 3-site replication check\n' > /tmp/site-replication-check.txt
-        mc cp /tmp/site-replication-check.txt "site1/$${bucket}/from-site1.txt"
-
-        for site in site2 site3; do
-          for attempt in $$(seq 1 60); do
-            if mc stat "$${site}/$${bucket}/from-site1.txt" >/dev/null 2>&1; then
-              echo "$${site} received replicated object"
-              break
-            fi
-            if [ "$${attempt}" = "60" ]; then
-              echo "$${site} did not receive replicated object in time"
-              exit 1
-            fi
-            sleep 2
-          done
-        done
-
-        mc admin replicate status site1
-        echo "3-site replication example is ready"
-    restart: "no"
-
-  site-replication-volume-permission-helper:
-    image: alpine:3.23.4
-    volumes:
-      - site1_data_0:/site1/data0
-      - site1_data_1:/site1/data1
-      - site1_data_2:/site1/data2
-      - site1_data_3:/site1/data3
-      - site1_logs:/site1/logs
-      - site2_data_0:/site2/data0
-      - site2_data_1:/site2/data1
-      - site2_data_2:/site2/data2
-      - site2_data_3:/site2/data3
-      - site2_logs:/site2/logs
-      - site3_data_0:/site3/data0
-      - site3_data_1:/site3/data1
-      - site3_data_2:/site3/data2
-      - site3_data_3:/site3/data3
-      - site3_logs:/site3/logs
-    command: >
-      sh -c "
-        chown -R 10001:10001 /site1 /site2 /site3 &&
-        echo 'site replication volume permissions fixed'
-      "
-    networks:
-      - rustfs-site-replication
-    restart: "no"
-
-networks:
-  rustfs-site-replication:
-
-volumes:
-  site1_data_0:
-  site1_data_1:
-  site1_data_2:
-  site1_data_3:
-  site1_logs:
-  site2_data_0:
-  site2_data_1:
-  site2_data_2:
-  site2_data_3:
-  site2_logs:
-  site3_data_0:
-  site3_data_1:
-  site3_data_2:
-  site3_data_3:
-  site3_logs:

.docker/test/site-replication/run-object-flow-check.sh

@@ -1,191 +0,0 @@
-#!/bin/sh
-# Copyright 2024 RustFS Team
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-
-set -eu
-
-ACCESS_KEY="${RUSTFS_SITE_REPL_ACCESS_KEY:-rustfsadmin}"
-SECRET_KEY="${RUSTFS_SITE_REPL_SECRET_KEY:-rustfsadmin}"
-BUCKET="${RUSTFS_SITE_REPL_FLOW_BUCKET:-site-repl-flow-check}"
-PREFIX="${RUSTFS_SITE_REPL_FLOW_PREFIX:-flow-$(date +%Y%m%d-%H%M%S)}"
-WAIT_ATTEMPTS="${RUSTFS_SITE_REPL_WAIT_ATTEMPTS:-90}"
-WAIT_SLEEP_SECONDS="${RUSTFS_SITE_REPL_WAIT_SLEEP_SECONDS:-2}"
-
-SITE1_ENDPOINT="${RUSTFS_SITE1_ENDPOINT:-http://127.0.0.1:9000}"
-SITE2_ENDPOINT="${RUSTFS_SITE2_ENDPOINT:-http://127.0.0.1:9010}"
-SITE3_ENDPOINT="${RUSTFS_SITE3_ENDPOINT:-http://127.0.0.1:9020}"
-
-command_exists() {
-  command -v "$1" >/dev/null 2>&1
-}
-
-require_command() {
-  if ! command_exists "$1"; then
-    echo "missing required command: $1" >&2
-    exit 1
-  fi
-}
-
-checksum_file() {
-  if command_exists sha256sum; then
-    sha256sum "$1" | awk '{print $1}'
-  elif command_exists shasum; then
-    shasum -a 256 "$1" | awk '{print $1}'
-  else
-    echo "missing required command: sha256sum or shasum" >&2
-    exit 1
-  fi
-}
-
-site_endpoint() {
-  case "$1" in
-    site1) printf '%s\n' "$SITE1_ENDPOINT" ;;
-    site2) printf '%s\n' "$SITE2_ENDPOINT" ;;
-    site3) printf '%s\n' "$SITE3_ENDPOINT" ;;
-    *) echo "unknown site alias: $1" >&2; exit 1 ;;
-  esac
-}
-
-other_sites() {
-  case "$1" in
-    site1) printf '%s\n' "site2 site3" ;;
-    site2) printf '%s\n' "site1 site3" ;;
-    site3) printf '%s\n' "site1 site2" ;;
-    *) echo "unknown source site: $1" >&2; exit 1 ;;
-  esac
-}
-
-wait_for_object() {
-  site="$1"
-  object="$2"
-  attempt=1
-
-  while [ "$attempt" -le "$WAIT_ATTEMPTS" ]; do
-    if mc stat "$site/$BUCKET/$object" >/dev/null 2>&1; then
-      return 0
-    fi
-    sleep "$WAIT_SLEEP_SECONDS"
-    attempt=$((attempt + 1))
-  done
-
-  echo "object was not replicated in time: $site/$BUCKET/$object" >&2
-  return 1
-}
-
-wait_for_bucket() {
-  site="$1"
-  attempt=1
-
-  while [ "$attempt" -le "$WAIT_ATTEMPTS" ]; do
-    if mc stat "$site/$BUCKET" >/dev/null 2>&1; then
-      return 0
-    fi
-    sleep "$WAIT_SLEEP_SECONDS"
-    attempt=$((attempt + 1))
-  done
-
-  echo "bucket was not replicated in time: $site/$BUCKET" >&2
-  return 1
-}
-
-require_command mc
-require_command dd
-require_command awk
-require_command date
-require_command mktemp
-require_command tr
-require_command wc
-
-WORK_DIR="$(mktemp -d "${TMPDIR:-/tmp}/rustfs-site-repl-flow.XXXXXX")"
-MC_CONFIG_DIR="$WORK_DIR/mc"
-export MC_CONFIG_DIR
-
-cleanup() {
-  rm -rf "$WORK_DIR"
-}
-trap cleanup EXIT INT TERM
-
-mkdir -p "$MC_CONFIG_DIR" "$WORK_DIR/src" "$WORK_DIR/downloads"
-
-for site in site1 site2 site3; do
-  mc alias set "$site" "$(site_endpoint "$site")" "$ACCESS_KEY" "$SECRET_KEY" >/dev/null
-done
-
-for site in site1 site2 site3; do
-  echo "checking S3 API for $site"
-  mc ls "$site" >/dev/null
-done
-
-echo "ensuring bucket exists on site1: $BUCKET"
-mc mb --ignore-existing "site1/$BUCKET" >/dev/null
-
-for site in site1 site2 site3; do
-  wait_for_bucket "$site"
-done
-
-cat <<'EOF' | while read -r size_mb source_site object_name; do
-10 site1 object-010m.bin
-25 site2 object-025m.bin
-50 site3 object-050m.bin
-75 site1 object-075m.bin
-100 site2 object-100m.bin
-EOF
-  src_file="$WORK_DIR/src/$object_name"
-  object="$PREFIX/$object_name"
-
-  echo "creating ${size_mb}MiB file: $object_name"
-  dd if=/dev/urandom of="$src_file" bs=1048576 count="$size_mb" >/dev/null 2>&1
-  src_checksum="$(checksum_file "$src_file")"
-  src_bytes="$(wc -c < "$src_file" | tr -d ' ')"
-
-  echo "uploading $object_name to $source_site ($src_bytes bytes)"
-  mc cp "$src_file" "$source_site/$BUCKET/$object" >/dev/null
-
-  for site in $(other_sites "$source_site"); do
-    wait_for_object "$site" "$object"
-
-    dst_file="$WORK_DIR/downloads/$site-$object_name"
-    verified=false
-    attempt=1
-    while [ "$attempt" -le "$WAIT_ATTEMPTS" ]; do
-      rm -f "$dst_file"
-      echo "downloading $object_name from $site"
-      if mc cp "$site/$BUCKET/$object" "$dst_file" >/dev/null 2>&1; then
-        dst_checksum="$(checksum_file "$dst_file")"
-        dst_bytes="$(wc -c < "$dst_file" | tr -d ' ')"
-
-        if [ "$dst_checksum" = "$src_checksum" ] && [ "$dst_bytes" = "$src_bytes" ]; then
-          verified=true
-          break
-        fi
-      fi
-
-      sleep "$WAIT_SLEEP_SECONDS"
-      attempt=$((attempt + 1))
-    done
-
-    if [ "$verified" != "true" ]; then
-      echo "download verification failed for $site/$BUCKET/$object" >&2
-      echo "expected checksum: $src_checksum" >&2
-      echo "expected bytes:    $src_bytes" >&2
-      exit 1
-    fi
-  done
-
-  echo "verified replicated downloads for $object_name"
-done
-
-echo "site replication object flow check passed"
-echo "bucket: $BUCKET"
-echo "prefix: $PREFIX"

.dockerignore

@@ -1,4 +1 @@
 target
-.docker/compat/data
-.docker/compat/kms
-target/compat

.envrc

@@ -1 +0,0 @@
-use flake

.github/AGENTS.md

@@ -1,32 +0,0 @@
-# GitHub Workflow Instructions
-
-Applies to `.github/`.
-
-## Pull Requests
-
-PR conventions (English title/body, template usage, `--body-file` with the
-heredoc pattern, review-thread etiquette) live in the root `AGENTS.md` under
-"Git and PR Baseline" — that section is the single normative home; do not
-duplicate its rules here.
-
-## Workflow Changes
-
-- Any change touching `.github/workflows/` must pass `actionlint` (run from
-  the repo root) with zero findings before commit/PR. Install via
-  `brew install actionlint`, or the download script in the actionlint repo
-  (rhysd/actionlint); `make pre-pr` does not cover workflow files, so this is
-  the required check for them.
-- Custom self-hosted runner labels (`sm-standard-*`, `dind-*`) are declared
-  in `.github/actionlint.yaml`. When introducing a new `runs-on:` label,
-  declare it there in the same change. Never use the config or `-ignore` to
-  silence real findings — fix the workflow (root `AGENTS.md`: make checks
-  pass by fixing the cause, not by weakening the gate).
-- If `shellcheck` is installed, actionlint also lints `run:` scripts; treat
-  those findings as part of the gate.
-
-## CI Alignment
-
-When changing CI-sensitive behavior, keep local validation aligned with
-`.github/workflows/ci.yml`. Read the workflow file directly for the current
-gate steps — do not rely on (or add) a copied command list here; copies go
-stale. `make pre-pr` is the local equivalent of the main gate.

.github/actionlint.yaml

@@ -1,7 +0,0 @@
-self-hosted-runner:
-  # Custom labels of this repository's self-hosted runners. Keep in sync with
-  # the labels actually used in `runs-on:` across .github/workflows/.
-  labels:
-    - sm-standard-2
-    - sm-standard-4
-    - dind-sm-standard-2

.github/actions/schedule-failure-issue/README.md

@@ -1,74 +0,0 @@
-# schedule-failure-issue
-
-Opens (or updates) a GitHub issue when a **scheduled** workflow run fails.
-This is the single alerting mechanism for all timed pipelines
-(rustfs/backlog#1149 ci-8, arbitration G3): scheduled workflows must consume
-this action instead of inventing their own notification paths.
-
-## Behavior
-
-- Issue title: `[scheduled-failure] <workflow name>` — the workflow name is
-  the dedupe key.
-- If an **open** issue with that exact title exists, the failure is appended
-  as a comment; otherwise a new issue is created (labeled `infrastructure` by
-  default). Closing the issue resets the cycle: the next failure opens a
-  fresh one.
-- The issue body / comment includes the run URL, run attempt, event, ref and
-  the names of the failed (or timed-out/cancelled) jobs of the current run
-  attempt.
-- Requires `gh` and `jq` on the runner (both preinstalled on GitHub-hosted
-  runners such as `ubuntu-latest`).
-
-## Usage
-
-Add a final job to the workflow. `always()` is required — without it the job
-is skipped when a needed job fails; `contains(needs.*.result, 'failure')`
-makes it act only when something actually failed. Scope `issues: write` to
-this job only; no other job may gain permissions.
-
-```yaml
-  alert-on-failure:
-    name: Alert on scheduled failure
-    needs: [<the jobs to watch>]
-    if: always() && github.event_name == 'schedule' && contains(needs.*.result, 'failure')
-    runs-on: ubuntu-latest
-    timeout-minutes: 10
-    permissions:
-      contents: read
-      issues: write
-    steps:
-      - uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7
-      - name: Open or update failure-tracking issue
-        uses: ./.github/actions/schedule-failure-issue
-        with:
-          github-token: ${{ secrets.GITHUB_TOKEN }}
-```
-
-Notes:
-
-- Upstream jobs that are *cancelled* (e.g. a manually cancelled run) do not
-  trigger the alert — a human was already looking. Job `timeout-minutes`
-  expiry surfaces as `failure` and does alert.
-- Manual `workflow_dispatch` runs never alert; a human is watching those.
-
-## Current consumers
-
-- `.github/workflows/e2e-s3tests.yml` (weekly full s3-tests sweep)
-- `.github/workflows/mint.yml` (weekly multi-SDK mint run)
-- `.github/workflows/fuzz.yml` (nightly fuzz corpus jobs)
-- `.github/workflows/performance-ab.yml` (nightly warp A/B gate)
-- **Pending:** the ci-7 e2e nightly-full workflow does not exist yet
-  (backlog#1149 ci-7). When it lands, wire it up with the snippet above.
-
-## Drill
-
-`.github/workflows/schedule-failure-alert-drill.yml` is a manual-only
-workflow that forces a job failure and runs this action through the exact
-consumer wiring. Use it to verify the alert path end to end:
-
-```bash
-gh workflow run schedule-failure-alert-drill.yml -R rustfs/rustfs --ref <branch>
-```
-
-Run it twice to verify both paths (issue creation, then comment dedupe), and
-close the `[scheduled-failure] Schedule Failure Alert Drill` issue afterwards.

.github/actions/schedule-failure-issue/action.yml

@@ -1,104 +0,0 @@
-# Copyright 2024 RustFS Team
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-
-name: "Schedule Failure Issue"
-description: >-
-  Open (or update) a tracking issue when a scheduled workflow run fails.
-  Dedupes by workflow name: if an open issue titled
-  "[scheduled-failure] <workflow name>" already exists, the failure is
-  appended as a comment; otherwise a new issue is created. This is the
-  single alerting mechanism for all scheduled pipelines (backlog#1149 ci-8).
-
-inputs:
-  github-token:
-    description: >-
-      Token with issues:write on the repository. Pass secrets.GITHUB_TOKEN
-      from a job that declares `permissions: issues: write` (scope the
-      permission to the alert job only, never workflow-wide).
-    required: true
-  workflow-name:
-    description: "Workflow name used for the issue title (the dedupe key)."
-    required: false
-    default: ${{ github.workflow }}
-  label:
-    description: >-
-      Label applied when a new issue is created. Must already exist in the
-      repository; if applying it fails, the issue is created without a label.
-      Set to an empty string to skip labeling.
-    required: false
-    default: "infrastructure"
-
-runs:
-  using: "composite"
-  steps:
-    - name: Open or update failure-tracking issue
-      shell: bash
-      env:
-        GH_TOKEN: ${{ inputs.github-token }}
-        WORKFLOW_NAME: ${{ inputs.workflow-name }}
-        ISSUE_LABEL: ${{ inputs.label }}
-      run: |
-        set -euo pipefail
-
-        title="[scheduled-failure] ${WORKFLOW_NAME}"
-        run_url="${GITHUB_SERVER_URL}/${GITHUB_REPOSITORY}/actions/runs/${GITHUB_RUN_ID}"
-
-        # Failed job names for this run attempt. The alert job runs while the
-        # run as a whole is still in progress, so inspect the jobs that have
-        # already completed with a non-success conclusion.
-        failed_jobs="$(gh api \
-          "repos/${GITHUB_REPOSITORY}/actions/runs/${GITHUB_RUN_ID}/attempts/${GITHUB_RUN_ATTEMPT}/jobs" \
-          --paginate \
-          --jq '.jobs[]
-                | select(.conclusion == "failure" or .conclusion == "timed_out" or .conclusion == "cancelled")
-                | "- `\(.name)` (\(.conclusion))"')"
-        if [ -z "${failed_jobs}" ]; then
-          failed_jobs="- (failed job not recorded yet — see the run page)"
-        fi
-
-        body="$(cat <<EOF
-        Scheduled run of **${WORKFLOW_NAME}** failed.
-
-        - Run: ${run_url} (attempt ${GITHUB_RUN_ATTEMPT})
-        - Event: \`${GITHUB_EVENT_NAME}\`
-        - Ref: \`${GITHUB_REF_NAME}\` @ \`${GITHUB_SHA}\`
-
-        Failed jobs:
-        ${failed_jobs}
-        EOF
-        )"
-
-        # Dedupe by exact title among OPEN issues (a closed issue means the
-        # earlier breakage was resolved; a new failure gets a fresh issue).
-        # GitHub search strips the [] characters, so search loosely and match
-        # the exact title with jq.
-        existing="$(gh issue list --repo "${GITHUB_REPOSITORY}" --state open --limit 100 \
-          --search "\"scheduled-failure\" in:title" --json number,title \
-          | jq -r --arg title "${title}" 'map(select(.title == $title)) | (.[0].number // empty)')"
-
-        if [ -n "${existing}" ]; then
-          echo "Appending comment to existing open issue #${existing}"
-          gh issue comment "${existing}" --repo "${GITHUB_REPOSITORY}" --body "${body}"
-          exit 0
-        fi
-
-        echo "Creating new issue: ${title}"
-        if [ -n "${ISSUE_LABEL}" ]; then
-          if gh issue create --repo "${GITHUB_REPOSITORY}" \
-               --title "${title}" --body "${body}" --label "${ISSUE_LABEL}"; then
-            exit 0
-          fi
-          echo "::warning::issue creation with label '${ISSUE_LABEL}' failed (missing label?); retrying without a label"
-        fi
-        gh issue create --repo "${GITHUB_REPOSITORY}" --title "${title}" --body "${body}"

.github/actions/setup/action.yml

@@ -52,25 +52,27 @@ runs:
         sudo apt-get install -y \
           musl-tools \
           build-essential \
+          lld \
+          libdbus-1-dev \
+          libwayland-dev \
+          libwebkit2gtk-4.1-dev \
+          libxdo-dev \
           pkg-config \
-          libssl-dev \
-          ripgrep \
-          unzip \
-          protobuf-compiler
+          libssl-dev
 
     - name: Install protoc
-      uses: rustfs/setup-protoc@a3705324d8f9bf5b6c3573fb6cf8ae421db55dd6 # v3.0.1
+      uses: arduino/setup-protoc@v3
       with:
-        version: "34.1"
-        repo-token: ${{ github.token }}
+        version: "31.1"
+        repo-token: ${{ inputs.github-token }}
 
     - name: Install flatc
-      uses: Nugine/setup-flatc@e7855e994773ce90094a3f1626d4afc9080c23ae # v1
+      uses: Nugine/setup-flatc@v1
       with:
-        version: "25.12.19"
+        version: "25.2.10"
 
     - name: Install Rust toolchain
-      uses: dtolnay/rust-toolchain@29eef336d9b2848a0b548edc03f92a220660cdb8 # stable
+      uses: dtolnay/rust-toolchain@stable
       with:
         toolchain: ${{ inputs.rust-version }}
         targets: ${{ inputs.target }}
@@ -78,17 +80,17 @@ runs:
 
     - name: Install Zig
       if: inputs.install-cross-tools == 'true'
-      uses: mlugg/setup-zig@d1434d08867e3ee9daa34448df10607b98908d29 # v2
+      uses: mlugg/setup-zig@v2
 
     - name: Install cargo-zigbuild
       if: inputs.install-cross-tools == 'true'
-      uses: taiki-e/install-action@a21ae4029b089b9ddc45704028756f51ab8abe48 # cargo-zigbuild
+      uses: taiki-e/install-action@cargo-zigbuild
 
     - name: Install cargo-nextest
-      uses: taiki-e/install-action@96c7780c1d8a2b8723e12031def873a434d39d8d # nextest
+      uses: taiki-e/install-action@cargo-nextest
 
     - name: Setup Rust cache
-      uses: Swatinem/rust-cache@e18b497796c12c097a38f9edb9d0641fb99eee32 # v2
+      uses: Swatinem/rust-cache@v2
       with:
         cache-all-crates: true
         cache-on-failure: true

.github/cla.yml

@@ -1,31 +0,0 @@
-# Copyright 2024 RustFS Team
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-
-enabled: true
-
-document:
-  version: v1
-  url: https://github.com/rustfs/cla/blob/main/cla/v1.md
-
-signing:
-  mode: comment
-  comment_pattern: I have read and agree to the CLA.
-
-registry:
-  type: json-repo
-  repository: rustfs/cla
-  path_prefix: signatures
-
-status:
-  check_name: CLA Check