The legacy erasure-decode overlap path drove the speculative next-stripe read and the current-stripe emit with `tokio::join!`, which runs both futures to completion. When the current stripe's emit terminated the loop — a client disconnect or any emit error — the join still waited for the prefetch read, so a `Stop` could stall for a full shard-read deadline on a slow or wedged remote shard before the GET could fail.
Drive the two futures with a biased `select!` instead and, the moment emit reports `Stop`, drop the in-flight read future. Because the entire read pipeline is structured async (a `FuturesUnordered` of `read_shard` futures inside `ParallelReader::read`/`read_lockstep`, with no `tokio::spawn`), dropping the read future is a real cancellation: it drops every in-flight shard read and propagates cancellation down to the RemoteDisk/HTTP reader, leaving no background read behind. The `select!` is scoped so both pinned futures drop before `reader`/`shards` are reused, which is what performs the cancellation in the `Stop` case.
This only affects the overlap-enabled path. The default remains OFF (`prefetch_count == 1` and bitrot-decode overlap disabled), and the strictly-serial read -> reconstruct -> emit default branch is untouched and byte-for-byte identical. The `Continue` path preserves offset, short-tail, buffer recycle, and bitrot/reconstruction error ordering exactly as before.
Scope: cancel-safety only. The rollout decision (whether to enable overlap by default) still requires the Linux multi-node high-RTT three-size A/B from https://github.com/rustfs/backlog/issues/1310 and is deferred; this change does not flip the default or introduce any behavior that A/B must adjudicate.
White-box test `test_legacy_prefetch_cancels_next_read_on_emit_failure` drives the real `Erasure::decode` path with overlap enabled, a writer that fails emit, and shards that serve the first stripe then stall the next-stripe read far beyond the assertion window. Under the paused clock the read future is dropped and decode returns at virtual t~=0; reverting cancel-safety makes it wait out the shard-read timeout, so the test fails closed.
Refs: https://github.com/rustfs/backlog/issues/1310
A PUT that fans out erasure shards to remote peers awaited every shard writer to completion on both the per-block write and the final shutdown, and the remote HttpWriter had no progress deadline. A peer that accepts the TCP connection but never drains the request body (or never sends a response) therefore wedges the writer forever once the bounded buffers fill, pinning an otherwise-healthy write quorum indefinitely — a cluster-level write-availability hazard triggered by a single bad peer (rustfs/backlog#1319, https://github.com/rustfs/backlog/issues/1319).
MultiWriter now wraps each shard write and each shard-writer shutdown in a forward-progress deadline. The budget is re-armed on every block, so it bounds a stall rather than the total transfer time of a large object: a slow-but-honest writer that keeps completing shards is never killed, while a writer that makes no progress within the budget is failed and its disk dropped before commit. An optional absolute per-object cap (disabled by default) backstops a slow-drip peer that dribbles just enough progress to reset the per-block timer without ever converging; it is off by default so a legitimate large upload over a slow link is not killed on total time alone. Both knobs come from RUSTFS_OBJECT_DISK_WRITE_STALL_TIMEOUT (default 30s) and RUSTFS_OBJECT_DISK_WRITE_ABSOLUTE_CAP (default 0 = disabled); setting the stall timeout to 0 restores the previous wait-forever behavior for a conservative rollback.
The deadline enforcement lives in MultiWriter (writer-agnostic), so it covers local and remote writers alike and keeps the existing control-flow shape: a timed-out shard is marked failed (Error::Timeout, which is not an ignored error) and excluded from the write quorum exactly like any other shard write failure, and the unchanged nil_count/quorum check then continues on quorum or fails cleanly. This deliberately stays out of the MultiWriter lifecycle / commit-coordinator territory owned by rustfs/backlog#1312.
When a stalled writer is dropped to fail its shard, the remote HttpWriter must stop holding the connection and its buffered body. HttpWriter previously left its spawned request task running on drop; it now aborts that background task in Drop (it is no longer pin-projected, since every field is Unpin and the AsyncWrite impl already used get_mut). Bytes already handed to the transport cannot be unsent, but they land only in this upload's unique tmp path and are reclaimed by tmp GC — they never touch a committed object.
Tests, all on a paused virtual clock so they are deterministic and non-flaky:
- one black-hole writer still meets a 3/4 write quorum without hanging; two black holes fail the quorum cleanly (both for the per-block write and the shutdown paths).
- a slow-but-honest writer that keeps making progress within the stall budget is never failed across many blocks.
- the absolute cap bounds a slow-drip writer within a finite budget while the healthy writers keep quorum.
- the default policy is armed by default and honors 0 as disabled.
- HttpWriter aborts its background request task on drop against a hanging peer.
The toxiproxy/black-hole 4x4 end-to-end acceptance depends on black-box test facilities from rustfs/backlog#1325, which are not built yet; that acceptance is deferred to #1325 and intentionally not faked here.
test(ecstore): add per-disk call-counter registry for metadata fan-out
First landable piece of the backlog#1325 test-infrastructure work: a test-only, per-disk call-counter registry that can observe `read_version` RPC counts recorded inside `tokio::spawn` tasks. This unblocks the RPC-count assertions in backlog #1309 / #1314 / #1315, which the thread-local `CapturingRecorder` cannot serve because it is blind to metrics emitted from spawned tasks.
The new `#[cfg(test)]` module `disk_call_counters` (modeled on the existing `cleanup_fault_injection` seam) is a process-global registry keyed by object name; an RAII `observe(object)` scope collects per-disk counts and clears only its own on drop, so parallel tests using distinct object names stay isolated. A dual-`cfg` `SetDisks::record_read_version_call` seam records from inside both metadata-fanout `read_version` spawn sites for online disks only; the `#[cfg(not(test))]` variant is an empty `#[inline(always)]` fn, so production runtime behavior is unchanged.
Two demo/regression tests prove the facility works across worker threads and is revert-detecting (neutralizing the recorder makes them fail).
Refs: https://github.com/rustfs/backlog/issues/1325
* test(ilm): fix restore test object key to match transition filter
restore_object_usecase_reports_ongoing_conflict_and_completion used the
object key "restore/api-object.bin", but the shared
set_bucket_lifecycle_transition_with_tier helper only transitions objects
under the "test/" prefix. enqueue_transition_for_existing_objects therefore
matched nothing and wait_for_transition timed out at 15s, failing the test
deterministically.
The test was added in #4860 but its ILM Integration (serial) lane is
skipped on regular PRs, so it merged red and has failed on every main run
since. Move the object under the test/ prefix like every passing sibling
test in this file.
* ci(ilm): exclude broken RestoreObject API test from serial lane
restore_object_usecase_reports_ongoing_conflict_and_completion exposes a
real regression, not a test bug: the RestoreObject copy-back
(handle_restore_transitioned_object) now holds the object write lock added
in #4877 across the entire tier read-back, so it never releases in time and
the test's concurrent get_object_info times out with Lock(Timeout, 5s). The
failure is deterministic and independent of the mock tier's injected latency.
This is the same class of known-broken restore/transition failure already
tracked under backlog#1148 (three sibling scanner tests are excluded here by
name for the same reason), so exclude this one the same way until the restore
copy-back path is fixed or the #4877 lock scope is revisited. The prior commit
keeps its correct fix (the object key must live under the test/ transition
prefix); that was masking this deeper issue by never letting the object
transition in the first place.
Restore copy-back deadlock/hang under the #4877 lock is escalated separately
for a product-level decision (fix the copy-back vs. narrow/revert #4877).
* test(ilm): fix scanner restore test object keys to match transition filter
test_restore_chain_local_read_expiry_keeps_remote_and_allows_re_restore and
test_multipart_restore_preserves_parts_and_etag (both added in #4860) keyed
their objects under restore/ instead of the test/ prefix that
set_bucket_lifecycle_transition_with_tier filters on, so the objects never
transitioned and wait_for_transition timed out at 15s.
These surfaced only after the prior commit excluded the rustfs-side restore
API test: nextest runs -j1 fail-fast, so that earlier failure stopped the run
before these scanner tests executed. Unlike the excluded API test, both call
restore_transitioned_object().await sequentially and only read afterwards, so
they don't hit the concurrent-read-vs-#4877-write-lock timeout; the key
prefix was their only problem.
* ci(ilm): exclude the two remaining #4877-broken restore tests
test_multipart_restore_preserves_parts_and_etag and
test_restore_chain_local_read_expiry_keeps_remote_and_allows_re_restore both
call restore_transitioned_object().await, which since #4877 acquires the
object write lock and deterministically times out (Lock Timeout, 5s) against
an already-held lock, so restore never completes. They surfaced one at a time
because nextest runs -j1 fail-fast. The earlier prefix fix was necessary but
only advanced them from the transition wait to this restore-lock timeout.
Exclude both by name alongside their already-excluded sibling
test_transition_and_restore_flows (same root cause, tracked under
backlog#1148) so the ILM Integration (serial) lane goes green. The #4877 lock
scope still needs a product fix before any of these re-enable.
* docs(ilm): describe the excluded restore tests' symptom as a lock timeout, not a deadlock
The #4877 write lock is held across the tier read-back and outlives the 5s
lock timeout; nothing proves a true deadlock. Wording flagged by Copilot
review.
* fix(ecstore): stop restore copy-back self-deadlocking on the #4877 write lock
#4877 made handle_restore_transitioned_object hold the object write lock for
the whole restore and forward no_lock=true so the set layer would not
reacquire it. But the set-level copy-back rebuilds its own options
(put_restore_opts -> ropts, and the complete_multipart_upload opts) that
default no_lock=false, so the inner put_object / new_multipart_upload /
complete_multipart_upload each re-acquire this object's write lock in their
commit phase and block on the lock the restore already holds -> Lock(Timeout,
5s), and restore never completes.
Confirmed via RUSTFS_OBJECT_LOCK_DIAG_ENABLE: restore_transitioned_object
acquires the write lock, then holds it ~10.5s across two nested 5s acquire
timeouts before failing. This is a real product deadlock: a RestoreObject on
any transitioned object (multipart especially) hangs, not just the tests.
Propagate no_lock into the copy-back options so the inner writes inherit the
already-held lock. Use opts.no_lock (not a hardcoded true) so a caller that
restores without the outer lock still locks correctly. put_object_part is left
as-is: it locks the multipart upload-id resource, not the object key, so it
does not conflict. Verified test_multipart_restore_preserves_parts_and_etag
now passes (3.6s, was a 15s+ hang).
* ci(ilm): re-enable multipart restore test; scope remaining exclusions
The prior commit fixes the #4877 restore self-deadlock, so
test_multipart_restore_preserves_parts_and_etag passes again - drop it from
the serial-lane exclusion list and remove its 'currently excluded' note.
The other restore/transition tests still fail, but each on a DIFFERENT,
independent issue unrelated to the (now-fixed) lock, verified locally:
- test_restore_chain_...: DeleteRestoredAction sets expire_restored but no
delete path reads it, so cleanup deletes the whole object (unimplemented
semantics), not the local restored copy only.
- test_transition_and_restore_flows: transition xl.meta missing on one drive
(EC metadata distribution), not restore.
- restore_object_usecase_reports_ongoing_conflict_and_completion: asserts a
concurrent mid-restore ongoing=true read that #4877's read-vs-restore
serialization rules out (backlog#1148 ilm-8 criterion 1, an API-semantics
decision).
Comments and #[ignore] reasons updated to reflect each real cause. All remain
tracked under backlog#1148.
feat(api): wire opt-in per-client S3 API rate limiting (backlog#1191)
RustFS shipped three rate-limiter implementations and none was wired to
any request path: the tower layer never returned 429 (its over-limit
branch passed requests through) and was never instantiated, the console
env switches only logged, and the Swift token bucket was never called.
Replace them with one working, default-off implementation:
- Rewrite rustfs/src/server/rate_limit.rs as a sharded per-client-IP
token-bucket limiter (32 mutex shards instead of one global RwLock
write per request), bounded at 100k tracked IPs with lossless
refilled-idle sweeps, returning 429 + Retry-After + x-ratelimit-*
headers and an S3-style XML body.
- Key on trusted-proxy-validated ClientInfo.real_ip, else the socket
peer address; never read spoofable X-Forwarded-For/X-Real-IP headers.
Requests without a resolvable identity fail open. The echoed request
id is charset-gated to prevent reflected XML injection.
- Wire the layer once at startup via option_layer between
CatchPanicLayer and ReadinessGateLayer (external stack only), gated by
new RUSTFS_API_RATE_LIMIT_ENABLE/_RPM/_BURST constants; health and
profiling probes, internode RPC/gRPC, and the console are exempt.
- Make RUSTFS_CONSOLE_RATE_LIMIT_ENABLE/_RPM actually enforce by
reusing the same limiter core through an axum middleware.
- Delete the dead Swift ratelimit module, its isolated tests, and the
stale logging-guardrail entry; keep the live SwiftError 429 mapping.
- Add unit tests (exhaustion/recovery with injected time, concurrency,
cap eviction, spoofed-header and fail-open behavior, env matrix) and
e2e tests proving 429 + Retry-After on the real server and zero
behavior change with default configuration.
* chore(deps): tighten crate dependency features
Narrow Tokio and dependency feature declarations for protocols, TLS runtime, utils, targets, and replication based on direct crate usage.
Co-Authored-By: heihutu <heihutu@gmail.com>
* chore(deps): trim hyper-rustls features
Keep direct hyper-rustls features aligned with the actual RustFS call sites. rustfs-targets only needs native root loading and the rustls provider/TLS policy features for MQTT TLS config construction, while rustfs-ecstore needs the HTTP connector protocol features but not webpki roots.
Co-Authored-By: heihutu <heihutu@gmail.com>
---------
Co-authored-by: heihutu <heihutu@gmail.com>
* chore(deps): remove redundant dependency features
Remove manifest feature entries that are implied by other requested features in the same dependency declaration.
Verified that the resolved Cargo feature graph is unchanged after the cleanup.
Co-Authored-By: heihutu <heihutu@gmail.com>
* chore(deps): narrow tokio and reqwest features
Co-Authored-By: heihutu <heihutu@gmail.com>
---------
Co-authored-by: heihutu <heihutu@gmail.com>
Move workspace-level dependency feature lists into the member crates that consume each dependency while keeping required default-features flags at the workspace root.
Also refresh starshard to 2.2.2 via cargo update and cargo upgrade --exclude ratelimit.
Co-authored-by: heihutu <heihutu@gmail.com>
`test_heal_resume_across_page_boundary_e2e` panicked whenever the
erasure-set healer deferred a single object version to a later heal
cycle. Under load a per-version `heal_object` can hit a transient error;
`ErasureSetHealer::heal_bucket_with_resume` then persists its
resume/checkpoint state and returns a terminal `Failed { .. "retry
scheduled" }`, expecting a fresh heal run to finish the job. In
production the background scanner is that next run — the e2e had no such
follow-up, so the first task's `Failed` state failed the test. This is a
pre-existing rare flake (the wiped-disk heal is otherwise correct); it is
unrelated to any policy/proptest work that happened to surface it in CI.
Drive the heal to a genuine `Completed` instead: on a `Failed` carrying
the `retry scheduled` marker (retry budget still remaining) re-submit the
idempotent heal (`force_start`), mirroring the production scanner, up to a
small bound. A `Failed` without that marker (e.g. `exhausted retries`) or
any other non-`Completed` terminal state still fails the test, and the
strict per-version data-restoration assertions still run only after a
real `Completed`. `wait_for_task` is refactored onto the shared
`await_terminal_status` poller; its panic-on-failure semantics for the
unversioned-bucket heal are unchanged.
Test-only change; no production heal code is touched.
Co-authored-by: heihutu <heihutu@gmail.com>
crates/policy had zero property tests: the wildcard Action/Resource matching
and Deny-first evaluation in Policy::is_allowed — the algebra authorization
safety rests on — were guarded only by example-based tests.
Add crates/policy/tests/policy_eval_proptest.rs with three generated-input
invariants (pure evaluation, no IO or global state, parallel-safe):
- explicit_deny_anywhere_denies: a Deny matching the request denies it no
matter how many broad Allow statements co-exist or at which index the Deny
sits; a built-in sanity assertion first proves the Allows alone would permit,
so the Deny is what flips the decision.
- wildcard_superset_implies_concrete_match: any request allowed by an
exact-action/exact-resource policy is also allowed after widening to s3:* on
bucket/* and to * on arn:aws:s3:::*, checked both on the built grant and on
random probe requests (implication form).
- empty_policy_denies_everything: a statement-less policy and Policy::default()
deny every non-owner request.
Statements are built from JSON exactly as production policies arrive via
PutPolicy. Generated names avoid wildcard metacharacters so the only wildcards
in play are the ones the properties introduce deliberately. proptest joins
crates/policy dev-deps following the filemeta/ecstore precedent.
Refs: backlog#1151 (sec-9)
First systematic HTTP e2e batch for the admin management surface
(backlog#1154 peri-2): full user -> canned-policy -> attach ->
service-account lifecycle with data-plane effect assertions (the
credential really gains and loses S3 access), plus a non-admin 403
probe per management endpoint targeting a different principal so
deny_only self-access semantics do not mask the gate. Wired into the
e2e-smoke nextest profile (ci-4 mechanism).
Pin the console listener's wire contract with a real binary on a random
port (backlog#1154 peri-4): unauthenticated version/license endpoints
answer complete JSON without credential material, the SPA prefix always
dispatches to the console static handler (never the S3 API), the admin
API and S3 root on the console listener stay 403 for anonymous callers,
and a console-disabled listener serves no console surface. Wired into
the e2e-smoke nextest profile (ci-4 mechanism).
* test(utils): add rustfs-test-utils crate, absorb heal/iam ECStore bootstrap
backlog#1153 infra-1. The ~50-line "build a real temp-disk ECStore"
bootstrap was copy-pasted (and drifting) across the heal and iam
integration tests. This adds crates/test-utils (rustfs-test-utils, a
dev-dependency-only crate) owning that bootstrap and converts the four
copies into thin wrappers:
- TestECStoreEnvBuilder: disk_count (default 4), prefix (uuid-suffixed
/tmp dir), base_dir (caller-owned dir, e.g. tempfile::TempDir),
init_bucket_metadata (default true; the iam bootstrap test opts out
to preserve its historical semantics). TestECStoreEnv exposes
temp_root/disk_paths/ecstore plus a versioned-bucket helper, and
init_tracing() replaces the per-file Once blocks.
- All rustfs_ecstore imports stay behind src/ecstore_test_compat.rs,
the sanctioned test-compat boundary pattern (mirrors
crates/iam/tests/ecstore_test_compat).
- heal: heal_integration_test / heal_b5_versioned_regression_test /
heal_b920_subquorum_union_test drop their setup_test_env{,_n} copies
for heal_env{,_n} wrappers; the tests/storage_api.rs integration
surface shrinks to what test bodies still touch.
- iam: iam_bootstrap_no_lock_test drops build_local_ecstore; its
ecstore_test_compat fixture shrinks to SetupType +
update_erasure_type.
rg 'async fn setup_test_env' crates/heal crates/iam now returns 0.
Scanner's lifecycle tests are deliberately NOT absorbed (gated on
ilm-1; 14 of 15 are #[ignore]d today). Net -230 lines.
* fix(heal): drop tokio::fs import orphaned by the b920 bootstrap move
* fix(heal): drop tokio::fs import orphaned by the b5 bootstrap move
Prove the swap-certificates-without-restart promise over real TLS
handshakes (backlog#1154 peri-5): new connections pick up the rotated
certificate within the reload interval, a session opened under the old
certificate survives the swap, and garbage material is fail-safe (the
old certificate keeps serving, the failure leaves a tls_reload_failed
log event, the process stays up). Wired into the e2e-smoke nextest
profile (ci-4 mechanism).
refactor(ecstore): make client base64 standard everywhere, drop the split
Self-review of the transition-client fixes: the Content-MD5 fix had only
converted the two transition call sites to a parallel base64_encode_standard,
leaving the same URL-safe, unpadded base64 bug on every other outbound value —
the SigV2/no-length multipart Content-MD5, the x-amz-checksum-* headers on the
parallel and no-length paths, api_remove's multi-delete Content-MD5, and the
checksum encode/decode helpers. Every base64 value this client emits or parses
is S3 wire format, which is standard base64; none is ever URL-safe.
Encode and decode both use base64_simd::STANDARD now, and the parallel
base64_encode_standard is gone. This fixes those seven latent call sites at the
root and removes the duplicate function. The transition path is functionally
unchanged (it already produced standard base64 via the helper), so the
end-to-end byte-for-byte result is preserved.
Also drop a stray Vec::with_capacity(part_size) that was allocated (up to
128 MiB) and immediately overwritten by read_multipart_part's own buffer.
Refs: rustfs/rustfs#4811, rustfs/backlog#1267
Co-authored-by: heihutu <heihutu@gmail.com>
xl.meta roundtrip coverage was one fixed example test plus byte-level no-panic
fuzz properties; nothing generated STRUCTURED version graphs, so a lossy
encoding bug in version headers, ordering, delete markers, or the dual
internal-metadata-key handling would only surface if the fixed example happened
to hit it.
Add crates/filemeta/tests/version_graph_roundtrip_proptest.rs with two
generated-input properties over multi-version graphs (1-7 versions, ~30% delete
markers, deliberately colliding mod_times to exercise tie-break ordering, user
metadata, and the AGENTS.md dual x-rustfs-internal-*/x-minio-internal-* keys
written via the real insert_bytes helper):
- version_graph_marshal_load_roundtrip: marshal -> load preserves version
count, meta_ver, the exact (id, type) sequence, full headers, fully decoded
per-version content, delete-marker payload shape, and both internal metadata
key forms with identical values.
- version_graph_marshal_is_idempotent: marshal(load(marshal(x))) is
byte-identical to marshal(x), catching encoders that mutate or reorder state
on the way out.
Complements the existing byte-level no-panic properties: those prove hostile
bytes cannot crash the decoder; these prove honest graphs are encoded
losslessly.
Refs: backlog#1151 (sec-10)
Register the webhook target while its endpoint is reachable, then drop
the listener before the PUT: registering against a dead endpoint stalls
behind the reachability probe timeout and flaked the ARN wait on the
rustfs#4821 merge run. Also widen the registration wait to 20s.
A single PUT can enqueue the same object for transition twice — immediately
(enqueue_transition_after_write) and again from the startup/lifecycle
compensation backfill. transition_object's own namespace lock is commented out,
so the two attempts are not serialized as same-object work: the winner
transitions the object and removes its local data, and the loser then reads that
already-removed data via get_object_fileinfo(read_data = true) and logs a
spurious "get_object_with_fileinfo err ... No such file" /
lifecycle_tier_operation_failed. For a large (multipart) object both attempts
can also race the source read, corrupting the transferred copy.
Guard the transition queue with an in-flight set keyed by
(bucket, object, version). queue_transition_task claims the key before sending;
a duplicate enqueue is reported handled without queueing a second task. The
worker releases the claim once the transition finishes, so a later lifecycle
pass can still re-transition the object, and a failed enqueue releases it
immediately. This is the sole path into the transition channel, so every
enqueue is covered.
Surfaced while validating the >128 MiB transition fix end-to-end in Docker
(rustfs/rustfs#4811); tracked as its own defect since it is unrelated to the
checksum/multipart-client bugs.
Tests: same-version enqueues dedupe (direct reserve and via queue_transition_task
with spare capacity), a distinct object still hits the full-queue path, and a
released claim can be re-acquired.
Refs: rustfs/backlog#1268
Co-authored-by: heihutu <heihutu@gmail.com>
* fix(ecstore): treat ChecksumNone as unset so >128 MiB ILM transitions succeed
ILM transition of any object larger than 128 MiB to a RustFS-native tier
(rustfs/minio/aliyun/tencent/r2/azure/huaweicloud/s3 backends that use the
built-in TransitionClient) failed with "unsupported checksum type", while
objects <=128 MiB transitioned fine.
Root cause: `ChecksumMode::is_set()` reported `ChecksumNone` as a configured
checksum. `ChecksumNone` is the zeroth enum variant, so it occupies bit 0 of
the EnumSet repr and the `len() == 1` check treated "no checksum" as set. The
128 MiB boundary is the warm backend's `MIN_PART_SIZE`, which selects a single
PUT (<=128 MiB) versus a multipart PUT (>128 MiB). On the multipart path,
`put_object_multipart_stream_optional_checksum` saw `checksum.is_set() == true`,
disabled the Content-MD5 branch, and called `ChecksumNone.hasher()`, which
returns the "unsupported checksum type" error. The single-PUT path hit the same
misjudgement but never calls `hasher()`, so it silently succeeded (without a
checksum), which is why only >128 MiB objects failed.
Fix:
- `is_set()` returns false for `ChecksumNone` (and the bare `ChecksumFullObject`
flag, which has no base algorithm). This is the sole callers' intended
meaning: a concrete algorithm with a real hasher is selected.
- Defense in depth: guard the multipart checksum branch on
`auto_checksum.is_set()` so an unset mode uploads the part without a per-part
checksum header instead of hard-failing in `hasher()`.
Only the TransitionClient consumes this `ChecksumMode::is_set()`; the
server-side data path uses the unrelated `rustfs_rio::ChecksumType`.
Tests: is_set()/set_default semantics, hasher parity for every set mode, and a
`build_transition_put_options` invariant (checksum unset + Content-MD5 on).
Refs: rustfs/rustfs#4811, rustfs/backlog#1267
Co-Authored-By: heihutu <heihutu@gmail.com>
* fix(ecstore): read exactly one part per multipart chunk in transition uploads
Second defect behind the >128 MiB ILM transition failure (rustfs/rustfs#4811),
uncovered while verifying the checksum fix.
`put_object_multipart_stream_optional_checksum` read each part with
`read_all()` / `to_vec()`, which drained the entire source into the first part
and left every later part empty. Any multipart upload of a streamed
(`ObjectBody`) source was therefore malformed. Objects <=128 MiB take the
single-part path and were unaffected; a 128 MiB + 1 byte object splits into a
128 MiB part plus a 1 byte part, so the first part received the whole object and
its declared Content-Length (part_size) did not match the body.
Verified empirically: `optimal_part_info(128 MiB + 1, 128 MiB)` yields 2 parts,
and `GetObjectReader::read_all()` on part 1 returns the full 134217729 bytes,
leaving 0 for part 2.
Fix:
- Add `read_multipart_part`, which reads exactly the requested part size (or
less at EOF) and advances the reader, for both `Body` (in-memory) and
`ObjectBody` (streamed) sources.
- Upload each part with the bytes actually read (`length`) as its size, and
account uploaded size by actual bytes, so a short read is detected instead of
masked.
The concurrent (`put_object_multipart_stream_parallel`) and SigV2
(`put_object_multipart`) paths share the same `read_all()` pattern but are not
exercised by transition; left untouched here and noted for follow-up.
Tests: `read_multipart_part` splits a 250-byte source into [100, 100, 50] for
both streamed and in-memory bodies, consumes the source fully, and stops at EOF
without overrun.
Refs: rustfs/rustfs#4811, rustfs/backlog#1267
Co-Authored-By: heihutu <heihutu@gmail.com>
* fix(ecstore): complete the >128 MiB ILM transition multipart client
Docker end-to-end reproduction of rustfs/rustfs#4811 (two RustFS tiers, a
128 MiB + 1 byte object, zero-day transition) surfaced four more defects on the
multipart transition path, each masked by the previous one. With the checksum
and part-splitting fixes in place the transition now failed later and later,
and finally produced a 0-byte object with no error at all. Fixed together:
- initiate_multipart_upload discarded the CreateMultipartUpload response and
returned an empty UploadId, so the first UploadPart failed with "UploadID
cannot be empty". Parse the response XML (InitiateMultipartUploadResult now
derives Deserialize with PascalCase).
- Content-MD5 / x-amz-checksum-* were encoded with URL-safe, unpadded base64,
which the remote rejected as "Invalid content MD5: Base64Error". Add
base64_encode_standard and use it for those outbound header values.
- PutObjectOptions::default() set legalhold to OFF, so header() attached
x-amz-object-lock-legal-hold to every request and CompleteMultipartUpload was
rejected with "does not accept object lock or governance bypass headers".
Default to an empty (unset) status.
- CompleteMultipartUpload / CompletePart had no serde renames, so the request
body used Rust field names (<parts>/<part_num>/<etag>). The remote parsed
zero <Part> elements and completed a 0-byte object while returning 200. Emit
S3 element names (<Part>/<PartNumber>/<ETag>) and skip empty checksum fields.
Verified end-to-end: a 128 MiB + 1 byte object now transitions to the remote
tier and reads back (transparently restored) byte-for-byte identical
(sha256 match), with none of the four prior errors in the logs.
Refs: rustfs/rustfs#4811, rustfs/backlog#1267
Co-Authored-By: heihutu <heihutu@gmail.com>
---------
Co-authored-by: heihutu <heihutu@gmail.com>
The individual policy layers were tested in isolation, but the cross-layer
resolution — which layer wins when IAM and bucket policy disagree — had no
coverage. A priority error there is a data-exposure or data-lockout bug.
Add crates/policy/tests/bucket_iam_authz_matrix.rs, a pure table-driven test
(no globals, no IAM store, no server) that drives the real Policy::is_allowed
and BucketPolicy::is_allowed through a helper modeling the request-layer
orchestration in rustfs::storage::access::authorize_request (bucket explicit-Deny
gate -> IAM allow -> bucket allow fallback; anonymous = bucket policy alone). It
pins all four Allow/Deny quadrants plus the anonymous case, and adds intra-policy
Deny-beats-Allow checks for both layers.
The matrix surfaces the resolution invariant explicitly: a BUCKET explicit Deny
is a hard gate and always wins, but an IAM explicit Deny is SOFT — a bucket Allow
fallback overrides it, which diverges from AWS "an explicit Deny in any policy
always wins". The test characterizes the current (MinIO-lineage) behavior; if IAM
Deny is later hardened into a gate, iam_deny_x_bucket_allow flips to false and
must be updated deliberately.
Refs: backlog#1151 (sec-8)
Co-authored-by: houseme <housemecn@gmail.com>
test(security): pin GHSA-m77q STS root-secret token signing (sec-7)
GHSA-m77q-r63m-pj89 (intentionally UNFIXED) is that STS session tokens are
signed with the shared root secret: crates/iam/src/root_credentials.rs
token_signing_key() returns the root secret_key, so anyone holding the root
secret can forge STS session tokens. No test named the advisory, and the
existing test_created_sts_credentials_authorize_with_session_token_claims uses
token_signing_key() for both signing and verifying, so it pins "same key signs
and verifies" but not the m77q-specific "signing key IS the root secret" — a
future fix that decouples the STS key from the root secret would pass it
silently.
Add a flow-level pin, test_ghsa_m77q_sts_session_token_signed_with_root_secret,
that captures the advisory's exact signature: (1) token_signing_key() == the
root secret; (2) an AssumeRole-style session token issued with that key decodes
with the root secret and NOT with any other secret; (3) it authorizes through
the STS path. All three assert CURRENT (by-design-vulnerable) behavior, so a
real m77q fix (a dedicated STS signing key) turns them red and forces a
red -> green regression update.
Also GHSA-name the existing characterization test and token_signing_key() with
doc comments and the advisory URL, and update the m77q row in
docs/testing/security-regressions.md. No production behavior changes.
Refs: backlog#1151 (sec-7)
Co-authored-by: houseme <housemecn@gmail.com>
* test(ecstore): assert decrypted_size for MinIO SSE interop round-trip
The ignored MinIO interop round-trip tests asserted `ObjectInfo.size`
against the plaintext length. For SSE objects `size` is the on-disk
DARE-encrypted size (plaintext + 32 bytes per 64 KiB block), so the
assertion can never hold once real fixtures are present — the two
`#[ignore]` tests failed the moment a real MinIO-written fixture was fed
in, even though the decoded data was byte-identical.
The client-visible object size comes from `decrypted_size()` /
`get_actual_size()`, which correctly reads MinIO's
`x-*-internal-actual-size` metadata (verified: both SSE-S3 and SSE-KMS
8 MiB multipart fixtures now report 8388608). Assert against that
instead and keep the plaintext length and SHA-256 data checks.
With real 4-drive MinIO fixtures (RELEASE.2025-09-07) all four tests
pass, confirming RustFS reads MinIO erasure-coded SSE objects with
byte-identical data and correct logical size.
Co-Authored-By: heihutu <heihutu@gmail.com>
* ci(ecstore): nightly MinIO interop check + dockerized fixture capture
Wire the ignored MinIO on-disk interop reader tests into a nightly,
non-required CI job, and make their fixtures reproducible without a host
MinIO install.
- Dockerfile + capture_via_docker.sh: build a throwaway image carrying
the official MinIO server binary (pinned RELEASE.2025-09-07) plus the
fixture lab on a small Python base, then run `lab.py capture-matrix` to
write the SSE-S3 / SSE-KMS multipart fixtures the tests consume. lab.py
drives MinIO's S3 API directly, so no `mc` is needed.
- .github/workflows/minio-interop.yml: nightly + manual workflow on
GitHub-hosted ubuntu-latest (reliable Docker + Python, unlike the
self-hosted fleet — see e2e-s3tests.yml infra note). Regenerates the
gitignored fixtures each run and executes the #[ignore] reader tests.
Not a PR gate.
- README: document the Docker capture path.
Validated end to end: the script builds the image, captures the two
multipart cases, and `cargo nextest run --run-ignored ignored-only`
passes all four interop tests.
Co-Authored-By: heihutu <heihutu@gmail.com>
---------
Co-authored-by: heihutu <heihutu@gmail.com>
test(replication): lock outbound checksum consistency for new algorithms (T3)
Adds a consistency test at the replication put-options boundary confirming that
the AWS 2026-04 additional checksum algorithms (XXHash3/64/128, SHA-512, MD5) are
forwarded into replication user_metadata identically to the classic five. The
outbound replication path routes a stored object checksum through the
algorithm-agnostic decrypt_checksums -> user_metadata flow, so the new algorithms
(already covered by rustfs-rio read_checksums) need no new-algorithm-specific
handling. This locks that behavior against regressions.
Investigation summary (no code change needed on the outbound side): the
per-algorithm ChecksumMode selection path is dormant (opts.checksum is never set
to a specific algorithm; tiering uses Content-MD5; the add_crc bool is dead
code), so extending ChecksumMode was unnecessary.
Co-authored-by: heihutu <heihutu@gmail.com>
* feat(rio): wire XXHash3/64/128 and SHA-512 into ChecksumType (S2)
Add the AWS 2026-04 additional checksum algorithms as base types in
rustfs-rio's ChecksumType, covering every dispatch site (key, raw_byte_len,
hasher, Display, from_string_with_obj_type, BASE_CHECKSUM_TYPES) so no path
silently strips them. Derive BASE_TYPE_MASK from BASE_CHECKSUM_TYPES as the
single source of truth, allocate the new base-type bits append-only above
bit 9 to preserve the on-disk varint format, and add streaming hashers whose
digest uses the S3 canonical big-endian encoding (seed 0).
The new algorithms are COMPOSITE-only: an explicit FULL_OBJECT request is
rejected and they are never routed through add_part()/can_merge(). A
round-trip guardrail test asserts every base type survives all dispatch
sites, failing loudly if a future algorithm is added but a match arm or the
mask is forgotten.
Refs rustfs/backlog#1254 rustfs/backlog#1252
Co-Authored-By: heihutu <heihutu@gmail.com>
* test(rio): pin XXHash/SHA-512 digests to official vectors, big-endian (S3)
Lock the byte order and seed of the new algorithms against the OFFICIAL
upstream xxHash / SHA-512 empty-input test vectors (XXH3-64, XXH64, XXH3-128,
SHA-512), in big-endian, so the stored and echoed checksum is byte-for-byte
identical to what AWS SDKs (awscrt) compute — the interop correctness this
feature hinges on. Add a non-empty regression lock (official "fox" vectors)
that also asserts the encoded field is the standard-base64 of the raw digest.
Refs rustfs/backlog#1255rustfs/backlog#1252
Co-Authored-By: heihutu <heihutu@gmail.com>
* test(rio): lock on-disk checksum round-trip and forward-compat degrade (S8)
Cover the xl.meta varint (de)serialization for the new algorithms:
to_bytes() -> read_checksums() must recover the value under the Display key
for XXHASH3/64/128 and SHA512. Pin the rolling-upgrade contract that a node
reading a future, unknown base-type bit degrades safely — skips the entry and
returns without panicking or mis-decoding a length. Combined with the
append-only bit allocation from S2, this protects mixed-version clusters.
Refs rustfs/backlog#1260rustfs/backlog#1252
Co-Authored-By: heihutu <heihutu@gmail.com>
* feat(head): echo XXHash/SHA-512 additional checksums on HeadObject (S5)
HeadObject with x-amz-checksum-mode: ENABLED now returns the XXHash3/64/128
and SHA-512 checksums that S3 stored, closing the head_object gap in #4800.
s3s HeadObjectOutput has no typed field for these, so they are emitted as raw
response headers via response.headers (the same mechanism RustFS already uses
for tagging-count), keyed by ChecksumType::key(). The existing five typed
algorithms are unchanged. Also carries the Cargo.lock update for the
xxhash-rust dependency introduced in S2.
Refs rustfs/backlog#1257rustfs/backlog#1252
Co-Authored-By: heihutu <heihutu@gmail.com>
* fix(checksums): fail-closed on unknown checksum algorithm (S7)
A. Harden unknown/unsupported checksum algorithms to fail closed instead of
panicking. ChecksumMode::base() in the outbound S3 client
(crates/ecstore/src/client/checksum.rs) previously did
`panic!("enum err.")` for any mode without a concrete base algorithm (e.g.
a bare ChecksumFullObject flag); it now falls back to ChecksumNone. Added
unit tests proving base() never panics and hasher() returns Err for
unsupported modes. rustfs-checksums FromStr already returns Err on unknown
names; added a regression test asserting garbage/unknown names fail closed.
B. Extend rustfs-checksums ChecksumAlgorithm with the AWS 2026-04 additional
algorithms Sha512/Xxhash3/Xxhash64/Xxhash128. Updated FromStr, as_str,
into_impl, name constants, the x-amz-checksum-* header constants and the
HttpChecksum impls. Byte order/seed matches the server-side rustfs-rio
spec: xxh3/xxh64 as u64 big-endian (8 bytes, seed 0), xxh128 as u128
big-endian (16 bytes), sha512 via sha2::Sha512. Added tests validating each
digest against a direct library computation. MD5 stays intentionally
rejected (PR #4513) and is left untouched.
C. crates/ecstore/src/client/checksum.rs ChecksumMode is enumset repr="u8"
with 7 variants already consuming 7 bits; adding the 4 new algorithms would
overflow u8 and require a breaking repr change, so ChecksumMode is left
unchanged. The new algorithms are available through the rustfs-checksums
ChecksumAlgorithm path.
Refs rustfs/backlog#1259rustfs/backlog#1252
Co-Authored-By: heihutu <heihutu@gmail.com>
* feat(get,put): echo XXHash/SHA-512 checksums on GetObject and PutObject (S5-GET, S4)
Complete the additional-checksum round-trip so AWS SDKs can verify integrity on
download and confirm it on upload:
- GetObject with x-amz-checksum-mode: ENABLED now returns XXHash3/64/128 and
SHA-512 checksums (the download-side path SDKs auto-verify). The values flow
from build_get_object_checksums through GetObjectOutputContext into
finalize_get_object_response and are emitted after wrap_response_with_cors.
- PutObject echoes the server-computed additional checksum on its response,
captured at the want_checksum set points before opts is moved.
Both reuse a single centralized helper, inject_additional_checksum_headers,
which HeadObject now also uses. This is the ONLY place that emits these headers,
so when s3s gains typed fields for these algorithms the migration is one spot
(fill the typed field, drop the insert) with no risk of duplicate headers.
The five s3s-typed algorithms are unchanged. Trailing-checksum PUT echo (value
lands after the body) is left for e2e coverage in S10.
Refs rustfs/backlog#1257rustfs/backlog#1256rustfs/backlog#1252
Co-Authored-By: heihutu <heihutu@gmail.com>
* feat(multipart): support XXHash/SHA-512 composite multipart checksums (S9)
Make multipart uploads work end-to-end for the composite-only algorithms
(XXHash3/64/128, SHA-512):
- complete_part_checksum previously returned the outer None for any algorithm
outside the five typed ones, which failed CompleteMultipartUpload with
InvalidPart. It now accepts any valid base type with no double-check value
(Some(None)) — mirroring the missing-value path of the typed algorithms —
since s3s CompletePart has no field to carry a client-supplied per-part
value and the part was already verified server-side at UploadPart. Genuinely
unset/invalid types are still rejected.
- The existing COMPOSITE assembly (Checksum::new_from_data over the
concatenated per-part raw digests; full_object_requested() is false so
add_part() is correctly bypassed) already works for these algorithms via the
S2 wiring. A rio test locks the assembly and that add_part refuses them.
- UploadPart and CompleteMultipartUpload echo the new-algorithm checksum on
their responses via the shared inject_additional_checksum_headers helper
(now pub(crate)), since s3s has no typed output field.
Refs rustfs/backlog#1261rustfs/backlog#1252
Co-Authored-By: heihutu <heihutu@gmail.com>
* feat(rio): add MD5 as an additional checksum (x-amz-checksum-md5) (S6)
Wire MD5 into ChecksumType as an additional (flexible) checksum, distinct from
the legacy Content-MD5 / ETag path: header x-amz-checksum-md5, 16-byte digest,
COMPOSITE-only, md-5 hasher. Pinned to the official empty-input MD5 vector.
Thanks to the single-source-of-truth wiring from S2, every dispatch site
(GetObject/HeadObject/PutObject echo, multipart complete_part_checksum and the
COMPOSITE assembly) picks MD5 up automatically via base()/key()/the catch-all
arm — no handler changes needed. Tests are extended to cover MD5 across them.
Coordination with #4513: that PR made the OUTBOUND rustfs-checksums client
reject "md5" so it could never silently fall back to CRC32. This change is on
the server-side rio path and never falls back — it implements MD5 correctly
rather than substituting another algorithm — so the #4513 intent is preserved,
and the outbound client keeps rejecting md5 (S7).
Refs rustfs/backlog#1258rustfs/backlog#1252
Co-Authored-By: heihutu <heihutu@gmail.com>
* perf(rio): drop per-request to_uppercase alloc in checksum parsing (S11)
from_string_with_obj_type ran alg.to_uppercase() on every checksummed request,
allocating a String just to compare against a fixed set of algorithm names.
Replace it with eq_ignore_ascii_case, which is allocation-free and, for the
ASCII algorithm names involved, exactly equivalent. A test locks that
case-insensitivity, the CRC64NVME full-object assumption, composite-only
FULL_OBJECT rejection, and unknown/empty handling are all unchanged.
The other S11 notes are intentionally not acted on: the Phase-0 header scan is
N/A (we chose full support over rejection, so there is no reject guard), and
parallelizing the serialized hash passes is deferred pending a measured need.
Refs rustfs/backlog#1263rustfs/backlog#1252
Co-Authored-By: heihutu <heihutu@gmail.com>
* refactor(checksums): collapse 5 duplicated response-checksum loops into one
Review of the accumulated commits found the same "iterate decrypted checksums,
match five typed algorithms, drop the rest" loop copy-pasted across five
response paths (GetObject, HeadObject, GetObjectAttributes object-level and
part-level, CompleteMultipartUpload). That was patch-on-patch duplication.
Collapse it into a single source of truth:
- rustfs-rio gains ChecksumType::is_s3s_typed() — the one place that defines the
five-typed vs additional-algorithm split.
- object_usecase gains ResponseChecksums + classify_response_checksums(), which
performs the typed/extra split once. All five call sites now destructure its
result; additional_checksum_echo_pairs() also uses is_s3s_typed() instead of a
hand-rolled five-way comparison.
Behaviour is unchanged (GetObjectAttributes still cannot surface the additional
algorithms — an s3s XML-body limitation, now documented in one spot). One pass
over the map; extra pairs pushed only when a new-algorithm checksum is present.
Refs rustfs/backlog#1252
Co-Authored-By: heihutu <heihutu@gmail.com>
* test(checksums): unit tests for classifier/echo helpers + fix unused import
Add direct unit tests for the refactored single-source-of-truth helpers:
- rio ChecksumType::is_s3s_typed() — exhaustive typed-vs-additional split, and
that flags (FULL_OBJECT/MULTIPART) on a base type don't change classification.
- object_usecase classify_response_checksums() — typed fields vs `extra` headers,
the checksum-type marker, and empty input.
- additional_checksum_echo_pairs() — echo pair only for additional algorithms,
none for the five typed ones, none for None.
- inject_additional_checksum_headers() — writes all pairs; empty is a no-op.
Also drop the now-unused AMZ_CHECKSUM_TYPE import in multipart_usecase.rs left
by the classifier refactor (would fail the -D warnings gate).
Refs rustfs/backlog#1252
Co-Authored-By: heihutu <heihutu@gmail.com>
* style(rio): fix typo flagged by CI (mis-decoding -> decoding a wrong length)
The Typos CI check flagged "mis-decoding" (it reads "mis" as a word). Reword
the S8 forward-compat comment; no code change.
Refs rustfs/backlog#1260
Co-Authored-By: heihutu <heihutu@gmail.com>
* test(e2e): integration test for XXHash/SHA-512/MD5 additional checksums (S10)
Permanent verify-on-write integration test in the e2e suite for the AWS 2026-04
additional algorithms. aws_sdk_s3 has no typed builder for these, so the
x-amz-checksum-<algo> header is injected via mutate_request (value from
rustfs-rio, byte-for-byte identical to awscrt). Uses a client with automatic
checksum calculation disabled (request_checksum_calculation=WhenRequired) so the
injected header is the only checksum on the wire. For each of XXHash3/64/128,
SHA-512 and MD5: a correct value is accepted and the object stored intact; a
mismatched value is rejected with BadDigest and nothing is stored.
Verified passing locally (1 passed) alongside a boto3+awscrt round-trip that
additionally confirms the HEAD/GET header echo (14/14).
Refs rustfs/backlog#1262rustfs/backlog#1252
Co-Authored-By: heihutu <heihutu@gmail.com>
* style(get): allow too_many_arguments on finalize_get_object_response
The classifier refactor added an extra_checksum_headers parameter, pushing
finalize_get_object_response to 8 args and tripping clippy::too_many_arguments
under CI's `-D warnings`. Add the same #[allow] the sibling GET helpers already
carry; no behavior change.
Refs rustfs/backlog#1252
Co-Authored-By: heihutu <heihutu@gmail.com>
---------
Co-authored-by: heihutu <heihutu@gmail.com>
feat(targets): add an opt-in NATS JetStream publish path for the notify and audit targets
The NATS notify and audit targets publish through NATS Core, which returns
before the server has durably accepted the message. A broker restart or a
connection drop between the publish and the flush loses the event, even though
the send queue has already cleared it, and no acknowledgement gates that clear.
An opt-in JetStream publish path clears a queued event only after the server
returns a durable PublishAck, so delivery is at-least-once across a broker
restart or a reconnect. It applies to both the notify and audit NATS targets, is
off by default, and is byte-identical to the NATS Core path when disabled.
The path includes durable store-and-forward, a stable dedup id sent as the
Nats-Msg-Id header so a replayed event is collapsed by the stream duplicate
window, pre-flight stream validation, and a bounded failed-events store for
terminally-failed and retry-exhausted events. Three configuration keys per
target select it: JETSTREAM_ENABLE, JETSTREAM_STREAM_NAME, and
JETSTREAM_ACK_TIMEOUT_SECS, under the RUSTFS_NOTIFY_NATS_ and RUSTFS_AUDIT_NATS_
prefixes.
The on-disk batch filename separator changes from colon to underscore so
batch names are valid on Windows filesystems, with transparent read-back
of files written under the previous separator. The migration affects the
shared queue store for every target type and lands with this feature
because the store gains its first Windows-exercised paths here.
Co-authored-by: houseme <housemecn@gmail.com>
The pulsar config validation rejected any non-`pulsar+ssl` broker whenever
`tls_allow_insecure` was set or `tls_hostname_verification` was disabled.
Both toggles are inert on a plaintext `pulsar://` broker — the Pulsar client
only applies them for `pulsar+ssl` — so treating a non-default value as fatal
is wrong.
This surfaced as issue #4796: the console persists `tls_hostname_verification`
as `false` (the checkbox defaults to unchecked while the server default is
`on`). At creation time the value is not present in the unmerged request and
falls back to the safe default, so the connectivity check passes and the
target comes online. On restart the persisted config is merged and validated,
the `false` is read back, and the target is rejected — permanently offline
even though Pulsar is reachable.
Relax both the loader-side (`validate_pulsar_broker_config`) and runtime-side
(`PulsarArgs::validate`) checks so only a `tls_ca` bundle — real TLS trust
material that is never defaulted to a non-empty value — requires a
`pulsar+ssl` scheme. The inert toggles no longer fail the target. This also
heals configs already persisted with the bad value. Add regression coverage
for both paths.
Co-authored-by: heihutu <heihutu@gmail.com>
Zhengchao An