mirror of
https://github.com/rustfs/rustfs.git
synced 2026-08-23 04:39:04 +00:00
Compare commits
6 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
| c45933fa1b | |||
| b6ba89d9e4 | |||
| 648d5166e2 | |||
| 84eb5aebef | |||
| ce7277a334 | |||
| d5ba6b4e16 |
@@ -30,7 +30,8 @@ make build-docker BUILD_OS=ubuntu22.04
|
||||
- Crate membership: `Cargo.toml` `[workspace].members`
|
||||
- Architecture, layering, crate map: [ARCHITECTURE.md](ARCHITECTURE.md)
|
||||
- Migration guardrails & readiness contracts: [docs/architecture/](docs/architecture/README.md)
|
||||
- CI gates: `.github/workflows/ci.yml` (source of truth; never copy its steps into docs)
|
||||
- CI workflow steps: `.github/workflows/`; event, timeout, and required-status
|
||||
matrix: [docs/testing/ci-gates.md](docs/testing/ci-gates.md)
|
||||
- Test-layer taxonomy, per-layer entry commands, serial/nextest rules, flake
|
||||
policy: [docs/testing/README.md](docs/testing/README.md)
|
||||
- Tier/ILM transition debugging (xl.meta inspection, versionId tracing):
|
||||
|
||||
@@ -70,6 +70,8 @@ make pre-pr
|
||||
|
||||
> For the full test-layer taxonomy (unit / ecstore black-box / e2e / s3s-e2e / S3 compatibility / chaos / fuzz / bench), each layer's entry command, the naming conventions the migration gate depends on, and the serial/nextest rules, see [docs/testing/README.md](docs/testing/README.md).
|
||||
|
||||
> For the event, timeout, required-status, and local reproduction matrix, see [docs/testing/ci-gates.md](docs/testing/ci-gates.md).
|
||||
|
||||
### 🔒 Automated Pre-commit Hooks
|
||||
#### What `make pre-commit` and `make pre-pr` actually run
|
||||
|
||||
|
||||
Generated
+22
-27
@@ -1858,9 +1858,9 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "cc"
|
||||
version = "1.4.3"
|
||||
version = "1.4.4"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "509591b7bcd67f4ef775afad7662703b4935daaa6ec0e5605cfb1090b32a2b6d"
|
||||
checksum = "0ad534f4357a5264cce5019c989cf66a4f0dc4e0d1b1d15f8aacec0ff7360273"
|
||||
dependencies = [
|
||||
"find-msvc-tools",
|
||||
"jobserver",
|
||||
@@ -2522,12 +2522,6 @@ dependencies = [
|
||||
"subtle",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "cty"
|
||||
version = "0.2.2"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "b365fabc795046672053e29c954733ec3b05e4be654ab130fe8f1f94d7051f35"
|
||||
|
||||
[[package]]
|
||||
name = "curve25519-dalek"
|
||||
version = "4.1.3"
|
||||
@@ -5988,15 +5982,6 @@ version = "0.2.16"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "b6d2cec3eae94f9f509c767b45932f1ada8350c4bdb85af2fcab4a3c14807981"
|
||||
|
||||
[[package]]
|
||||
name = "libmimalloc-sys"
|
||||
version = "0.1.49"
|
||||
source = "git+https://github.com/xonatius/mimalloc_rust.git?rev=6d4c41bb10c6d9da1d1b6f07b38c4cc051667f11#6d4c41bb10c6d9da1d1b6f07b38c4cc051667f11"
|
||||
dependencies = [
|
||||
"cc",
|
||||
"cty",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "libredox"
|
||||
version = "0.1.20"
|
||||
@@ -6397,14 +6382,6 @@ dependencies = [
|
||||
"synstructure 0.13.2",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "mimalloc"
|
||||
version = "0.1.52"
|
||||
source = "git+https://github.com/xonatius/mimalloc_rust.git?rev=6d4c41bb10c6d9da1d1b6f07b38c4cc051667f11#6d4c41bb10c6d9da1d1b6f07b38c4cc051667f11"
|
||||
dependencies = [
|
||||
"libmimalloc-sys",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "mime"
|
||||
version = "0.3.17"
|
||||
@@ -9162,13 +9139,11 @@ dependencies = [
|
||||
"insta",
|
||||
"jiff",
|
||||
"libc",
|
||||
"libmimalloc-sys",
|
||||
"libsystemd",
|
||||
"matchit 0.9.2",
|
||||
"md-5 0.11.0",
|
||||
"metrics",
|
||||
"metrics-util",
|
||||
"mimalloc",
|
||||
"mime_guess",
|
||||
"opentelemetry",
|
||||
"opentelemetry_sdk",
|
||||
@@ -9204,6 +9179,8 @@ dependencies = [
|
||||
"rustfs-lock",
|
||||
"rustfs-log-analyzer",
|
||||
"rustfs-madmin",
|
||||
"rustfs-mimalloc",
|
||||
"rustfs-mimalloc-sys",
|
||||
"rustfs-notify",
|
||||
"rustfs-object-capacity",
|
||||
"rustfs-object-data-cache",
|
||||
@@ -9875,6 +9852,24 @@ dependencies = [
|
||||
"tokio",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "rustfs-mimalloc"
|
||||
version = "0.5.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "a406f4aa07084301d485beec873af6dccc8e3f8762da244743df92038b1db1a6"
|
||||
dependencies = [
|
||||
"rustfs-mimalloc-sys",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "rustfs-mimalloc-sys"
|
||||
version = "0.5.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "c3051b819175f58445d4c369a72f0ab88149f3885ba8bea2aff3be01f53fe7cd"
|
||||
dependencies = [
|
||||
"cc",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "rustfs-notify"
|
||||
version = "1.0.0-rc.3"
|
||||
|
||||
+2
-2
@@ -350,8 +350,8 @@ russh-sftp = "2.4.0"
|
||||
dav-server = "0.11.0"
|
||||
|
||||
# Performance Analysis and Memory Profiling
|
||||
mimalloc = { version = "0.1.52", git = "https://github.com/xonatius/mimalloc_rust.git", rev = "6d4c41bb10c6d9da1d1b6f07b38c4cc051667f11" }
|
||||
libmimalloc-sys = { version = "0.1.49", git = "https://github.com/xonatius/mimalloc_rust.git", rev = "6d4c41bb10c6d9da1d1b6f07b38c4cc051667f11", features = ["extended"] }
|
||||
rustfs-mimalloc = { version = "0.5.0" }
|
||||
rustfs-mimalloc-sys = { version = "0.5.0" }
|
||||
hotpath = { version = "0.23.3", default-features = false }
|
||||
# Snapshot testing for output format regression detection
|
||||
insta = { version = "1.48" }
|
||||
|
||||
@@ -2124,26 +2124,13 @@ impl SetDisks {
|
||||
|
||||
let put_object_size = known_put_object_storage_size(data.size());
|
||||
let shard_file_size_raw = erasure.shard_file_size(put_object_size);
|
||||
let is_inline_buffer =
|
||||
storage_class_config.should_inline(shard_file_size_raw, erasure.data_shards, opts.versioned);
|
||||
let is_inline_buffer = storage_class_config.should_inline(shard_file_size_raw, erasure.data_shards, opts.versioned);
|
||||
|
||||
let collect_stage_timing = rustfs_io_metrics::put_stage_metrics_enabled() || issue3031_diag_enabled();
|
||||
let shard_file_size = shard_file_size_raw;
|
||||
let shard_size = erasure.shard_size();
|
||||
let write_path = classify_put_write_path(is_inline_buffer, put_object_size, fi.erasure.block_size);
|
||||
let direct_inline_commit = matches!(write_path, SmallWritePath::Inline);
|
||||
{
|
||||
use std::io::Write;
|
||||
let msg = format!(
|
||||
"INLINE_DEBUG: bucket={} obj={} size={} shard_fs={} ds={} bs={} inline={} direct={} path={} iblock={} ver={}\n",
|
||||
bucket, object, put_object_size, shard_file_size_raw, erasure.data_shards, fi.erasure.block_size,
|
||||
is_inline_buffer, direct_inline_commit, write_path.metric_label(), storage_class_config.inline_block(), opts.versioned
|
||||
);
|
||||
if let Ok(mut f) = std::fs::OpenOptions::new().create(true).append(true).open("/tmp/rustfs_inline_debug.log") {
|
||||
let _ = f.write_all(msg.as_bytes());
|
||||
}
|
||||
let _ = std::io::stderr().write_all(msg.as_bytes());
|
||||
}
|
||||
rustfs_io_metrics::record_put_object_path(write_path.metric_label());
|
||||
let writer_setup_stage_start = collect_stage_timing.then(Instant::now);
|
||||
let (mut writers, errors) = if direct_inline_commit {
|
||||
|
||||
@@ -3194,7 +3194,7 @@ impl ECStore {
|
||||
|
||||
// Default return value
|
||||
let mut del_objects = vec![DeletedObject::default(); objects.len()];
|
||||
let mut accounting = vec![None; objects.len()];
|
||||
let accounting = vec![None; objects.len()];
|
||||
|
||||
let mut del_errs = Vec::with_capacity(objects.len());
|
||||
for _ in 0..objects.len() {
|
||||
|
||||
@@ -271,7 +271,7 @@ pub(super) fn resolve_latest_object_info_candidates(
|
||||
.filter(|candidate| latest_candidate_mod_time(candidate) == Some(latest_mod_time))
|
||||
.collect::<Vec<_>>();
|
||||
|
||||
latest_candidates.sort_by(|left, right| right.idx.cmp(&left.idx));
|
||||
latest_candidates.sort_by_key(|candidate| std::cmp::Reverse(candidate.idx));
|
||||
|
||||
let Some(winner) = latest_candidates.first() else {
|
||||
return Err(Error::ErasureReadQuorum);
|
||||
|
||||
@@ -43,9 +43,6 @@ allow-git = [
|
||||
# RustFS fork carrying presigned expiry and constant-time authentication fixes.
|
||||
# owner: rustfs-maintainers review: 2026-10
|
||||
"https://github.com/rustfs/s3s.git",
|
||||
# MiMalloc fork pinned for hotpath allocation counting support.
|
||||
# owner: houseme review: 2026-10
|
||||
"https://github.com/xonatius/mimalloc_rust.git",
|
||||
]
|
||||
|
||||
[bans]
|
||||
|
||||
@@ -0,0 +1,149 @@
|
||||
# CI gate matrix
|
||||
|
||||
This file is the source of truth for which validation runs on each event, its
|
||||
configured wall-clock budget, and whether it can block a merge. Test taxonomy,
|
||||
naming, and nextest serialization rules remain in [README.md](README.md); e2e
|
||||
membership and counts remain in
|
||||
[e2e-suite-inventory.md](e2e-suite-inventory.md).
|
||||
|
||||
The distinction between **required** and **report-only** is load-bearing:
|
||||
a failing job blocks a merge only when its exact check name is present in the
|
||||
live `main` ruleset. A workflow name, a `merge_group` trigger, or a red PR check
|
||||
does not make a job required by itself.
|
||||
|
||||
## Required merge checks
|
||||
|
||||
The live `main` ruleset (`6436880`) currently requires exactly these contexts:
|
||||
|
||||
| Required context | Producer | Validation |
|
||||
|---|---|---|
|
||||
| `CLA Check` | `.github/workflows/cla.yml` | Contributor agreement |
|
||||
| `Quick Checks` | `.github/workflows/ci.yml` | Formatting and repository guard scripts |
|
||||
| `Test and Lint` | `.github/workflows/ci.yml` | Clippy, workspace nextest excluding `e2e_test`, doctests, and migration proofs |
|
||||
|
||||
For pull requests limited to the paths excluded by the main CI workflow,
|
||||
`.github/workflows/ci-docs-only.yml` reports `Quick Checks` and
|
||||
`Test and Lint` under the same names. It runs the real quick checks and the
|
||||
planning-document guard; it does not claim that Rust compilation or runtime
|
||||
tests ran. Despite the workflow name, these paths also include selected deploy,
|
||||
workflow, and lock files.
|
||||
|
||||
Verify the live rule rather than trusting this snapshot before changing merge
|
||||
policy:
|
||||
|
||||
```bash
|
||||
gh api repos/rustfs/rustfs/rulesets/6436880 \
|
||||
--jq '.rules[] | select(.type == "required_status_checks") | .parameters'
|
||||
```
|
||||
|
||||
The ruleset currently has `strict_required_status_checks_policy=false`.
|
||||
`Continuous Integration` accepts `merge_group` events and runs `e2e-full` for
|
||||
them, but `End-to-End Tests (full merge gate)` is not currently a required
|
||||
context. Therefore the repository is prepared to test a merge-queue SHA, but
|
||||
the workflow alone does not prove that every merge passed that lane.
|
||||
|
||||
## Pull request and merge matrix
|
||||
|
||||
Budgets below are job `timeout-minutes`, not typical runtimes. “Report-only”
|
||||
means the result is visible and actionable but is not in the live required
|
||||
context list.
|
||||
|
||||
| Event | Validation | Budget | Merge status | Reproduction |
|
||||
|---|---|---:|---|---|
|
||||
| PR, non-doc change | `Quick Checks` | 10 min | Required | `make pre-commit` (broader local umbrella) |
|
||||
| PR, non-doc change | `Test and Lint` | 90 min | Required | `cargo nextest run --profile ci --all --exclude e2e_test` |
|
||||
| PR, non-doc change | `Typos` | 10 min | Report-only | `typos` |
|
||||
| PR, non-doc change | `ILM Integration (serial)` | 90 min | Report-only | Use the exact command in `.github/workflows/ci.yml` |
|
||||
| PR, non-doc change | rio-v2 / swift / sftp test-and-lint variants | 90 min each | Report-only | `cargo nextest run` with the workflow's feature set |
|
||||
| PR, non-doc change | `Build RustFS Debug Binary` | 30 min | Report-only; prerequisite for black-box lanes | `cargo build -p rustfs --bins` |
|
||||
| PR, non-doc change | `io_uring Integration (real)` | 30 min | Report-only | `cargo test -p rustfs-ecstore --lib uring_ -- --test-threads=1 --nocapture` |
|
||||
| PR, non-doc change | `End-to-End Tests` (`e2e-smoke` plus `s3s-e2e`) | 30 min | Report-only | `cargo nextest run --profile e2e-smoke -p e2e_test`; then `./scripts/e2e-run.sh ./target/debug/rustfs <data-dir>` |
|
||||
| PR, non-doc change | `S3 Implemented Tests` | 60 min | Report-only | Build `rustfs`, then run `scripts/s3-tests/run.sh` with `DEPLOY_MODE=binary`, `TEST_MODE=single`, and `MAXFAIL=0` |
|
||||
| PR, non-doc change | `S3 Lifecycle Behavior Tests` | 30 min | Report-only | Use the accelerated scanner environment in `.github/workflows/ci.yml` with `scripts/s3-tests/run.sh` |
|
||||
| PR touching dependency or workflow inputs | Cargo Deny / Workflow Pin Report / Dependency Review | 20 / 5 / 30 min | Report-only | `cargo deny check`; `scripts/security/check_workflow_pins.sh` |
|
||||
| PR touching architecture rules or architecture docs | `Architecture Migration Rules` | 10 min | Report-only | `scripts/check_architecture_migration_rules.sh` |
|
||||
| PR touching Nix or workspace manifests | `Nix Build & Check` | 60 min | Report-only | `nix flake check` |
|
||||
| PR limited to main-CI-excluded paths | companion `Quick Checks` and `Test and Lint` | 10 min each | Required | `git diff --check`; `make doc-paths-check` when documentation paths changed |
|
||||
| `merge_group` | Standard CI plus `e2e-full` | 55 min for `e2e-full` | Standard required contexts only; `e2e-full` report-only | `cargo nextest run --profile e2e-full -p e2e_test` |
|
||||
| Push to `main` | Standard CI plus `e2e-full` | 55 min for `e2e-full` | Post-merge detection | Same as `merge_group` |
|
||||
| PR touching fuzz inputs or harness paths | Build plus five 60-second fuzz smoke targets | 60 min build; 30 min per target | Report-only | `MAX_TOTAL_TIME=60 ./scripts/fuzz/run.sh` |
|
||||
| PR touching selected ecstore disk/format paths | `Rename Safety` on Windows | 60 min | Report-only | Run the four `cargo test -p rustfs-ecstore --lib <filter>` commands in `windows-filesystem.yml` on Windows |
|
||||
|
||||
The authoritative e2e filters live in `.config/nextest.toml`; extend a profile
|
||||
instead of adding a second ad-hoc selector. Before a profile runs,
|
||||
`scripts/check_test_wiring.py` compares its exact membership to the committed
|
||||
digest so a silent test drop fails closed.
|
||||
|
||||
## Scheduled and manual validation
|
||||
|
||||
Scheduled lanes are independent fault domains. They do not block a pull
|
||||
request, but their workflow-local gate can fail the run and scheduled failures
|
||||
are routed to the shared failure-issue action. The scheduled-validation
|
||||
watchdog and freshness workflow separately detect incomplete runs and missing
|
||||
schedules.
|
||||
|
||||
| Cadence (UTC unless noted) | Workflow / validation | Budget | Verdict and artifacts | Reproduction |
|
||||
|---|---|---:|---|---|
|
||||
| Daily 02:17 | Fuzz: five nightly corpus targets | 60 min build; 60 min per target | Gate; corpus/crash artifacts, scheduled failure alert | `MAX_TOTAL_TIME=<seconds> ./scripts/fuzz/run.sh` |
|
||||
| Daily 03:17 | MinIO interop (EC + SSE read parity) | 40 min | Gate; scheduled failure alert | Dispatch `minio-interop.yml` or follow its pinned Docker fixture steps |
|
||||
| Daily 04:29 | Replication / cluster-fault / protocol e2e | 45 / 90 / 90 min | Three independent gates; JUnit, membership, and server logs | `cargo nextest run --profile e2e-repl-nightly -p e2e_test`; `--profile e2e-nightly`; `-j 1 --profile e2e-protocols` |
|
||||
| Daily 06:31 | Warp performance A/B | 180 min | Regression budget gate; A/B summaries and server logs | `bash scripts/run_hotpath_warp_abba.sh --help` |
|
||||
| Daily 00:07 Asia/Shanghai (16:07 UTC previous day) | Nightly GNU build and Vault lanes | 150 / 90 / 60 min | Build, live Vault, and HA failover gates | Use the commands and pinned Vault images in `nightly-gnu.yml` |
|
||||
| Daily 03:23 | Security Audit | 20 / 5 min, plus 30 min on PR dependency review | Cargo Deny and workflow-pin gates; scheduled failure alert | `cargo deny check`; `scripts/security/check_workflow_pins.sh` |
|
||||
| Daily 23:47 | Scheduled Validation Freshness | 10 min | Fails when a critical schedule was never created or is stale | Dispatch `scheduled-validation-freshness.yml` |
|
||||
| Sunday 00:11 | Full `Continuous Integration` matrix | Per-job budgets above | Weekly variant coverage, including dormant rio-v2 binary/e2e lanes | Dispatch `ci.yml` |
|
||||
| Sunday 01:13 | Seven-platform build matrix | 150 min per platform | Build/package integrity; scheduled failure alert | Dispatch `build.yml` with an exact platform set |
|
||||
| Sunday 02:19 | Ceph s3-tests full sweep: single and real four-node, four shards each | 180 min per shard | Compatibility gate; report, JUnit, exact node IDs, and server logs | `scripts/s3-tests/run.sh` against an existing single or distributed target |
|
||||
| Sunday 06:41 | Mint | 120 min | **Report-only by design**; per-suite PASS/FAIL/NA and raw `log.json` | Reproduce the pinned Docker sequence in `mint.yml` or dispatch it |
|
||||
| Sunday 07:43 | Workspace line coverage | 120 min | Report-only trend; lcov and JSON retained 90 days | `make coverage` |
|
||||
| Monthly, day 1 06:37 | Runner Hygiene | 15 min | Validates runner ephemerality; scheduled failure alert | Dispatch `runner-hygiene.yml` |
|
||||
|
||||
Manual `workflow_dispatch` exists for the scheduled workflows above. Manual
|
||||
runs are debugging evidence and intentionally do not open scheduled-failure
|
||||
issues. A manual performance run may explicitly allow a known regression; that
|
||||
override must not be treated as an ordinary passing baseline.
|
||||
|
||||
## Release validation
|
||||
|
||||
Release validation is post-merge and tag-driven; it does not substitute for a
|
||||
pull-request gate.
|
||||
|
||||
| Event | Validation | Budget | Result |
|
||||
|---|---|---:|---|
|
||||
| Push to `main` or weekly schedule | `Build and Release` platform matrix | 150 min per platform | Build artifacts for all selected targets; no release publication on a main push |
|
||||
| Valid release or preview tag | `Build and Release` plus asset checks | 150 min per platform | Draft release, checksummed assets, and publish step |
|
||||
| Successful non-preview release-tag build | Docker image build and image scan | 60 min build; 30 min scan | Multi-architecture images plus vulnerability report |
|
||||
| Successful release-tag build | DEB/RPM packaging | 30 min per architecture | Packages and checksum files uploaded to the release |
|
||||
| Successful non-preview release-tag build | Helm template test and package | 30 min build; 30 min publish | Versioned chart and repository index |
|
||||
|
||||
Use an exact preview tag for end-to-end release rehearsal. Manual dispatches
|
||||
are backfill/debug paths and do not prove the automatic `workflow_run` chain.
|
||||
|
||||
## Evidence requirements
|
||||
|
||||
A green check is useful only when it proves the intended behavior ran:
|
||||
|
||||
- Record the exact commit SHA and run URL.
|
||||
- Separate product failure from runner prerequisites, service readiness, and
|
||||
cancellation. Repair the precondition, then rerun the exact workload.
|
||||
- Preserve membership manifests, JUnit, raw compatibility logs, seeds, and
|
||||
server logs where the workflow provides them.
|
||||
- For a bug fix or a new fault checker, provide sensitivity evidence: the old
|
||||
behavior or an intentional mutation must fail the new oracle, and the fixed
|
||||
behavior must pass it.
|
||||
- Never promote a report-only lane to required from one green run. Require at
|
||||
least 14 days and 30 representative pull requests with at least 99% complete
|
||||
execution, then update the ruleset and this table together.
|
||||
|
||||
## Change checklist
|
||||
|
||||
Update this file in the same pull request when any of these change:
|
||||
|
||||
- workflow triggers, job names, timeouts, or nextest profile ownership;
|
||||
- required status contexts or strict/merge-queue policy;
|
||||
- scheduled cadence, alert routing, artifact contract, or local reproduction;
|
||||
- report-only versus gating semantics.
|
||||
|
||||
Do not copy per-module test counts here. Update
|
||||
[e2e-suite-inventory.md](e2e-suite-inventory.md) and its enforced membership
|
||||
digest instead.
|
||||
+2
-2
@@ -336,13 +336,13 @@ opentelemetry = { workspace = true }
|
||||
tracing-opentelemetry = { workspace = true }
|
||||
# Data structures
|
||||
hashbrown = { workspace = true, features = ["serde", "rayon"] }
|
||||
mimalloc = { workspace = true }
|
||||
rustfs-mimalloc = { workspace = true }
|
||||
|
||||
[target.'cfg(target_os = "linux")'.dependencies]
|
||||
libsystemd.workspace = true
|
||||
|
||||
[target.'cfg(not(target_os = "windows"))'.dependencies]
|
||||
libmimalloc-sys.workspace = true
|
||||
rustfs-mimalloc-sys.workspace = true
|
||||
|
||||
[dev-dependencies]
|
||||
uuid = { workspace = true, features = ["v4", "v5", "fast-rng", "macro-diagnostics"] }
|
||||
|
||||
@@ -70,6 +70,12 @@ const SITE_REPLICATION_EDIT_ROUTE: &str = "/rustfs/admin/v3/site-replication/edi
|
||||
const SITE_REPLICATION_RESYNC_ROUTE: &str = "/rustfs/admin/v3/site-replication/resync/op";
|
||||
const SITE_REPLICATION_REPAIR_ROUTE: &str = "/rustfs/admin/v3/site-replication/repair";
|
||||
const SITE_REPLICATION_REPAIR_STATUS_ROUTE: &str = "/rustfs/admin/v3/site-replication/repair/status";
|
||||
const IAM_POLICY_ATTACH_ROUTE: &str = "/rustfs/admin/v3/idp/builtin/policy/attach";
|
||||
const IAM_POLICY_DETACH_ROUTE: &str = "/rustfs/admin/v3/idp/builtin/policy/detach";
|
||||
const IAM_POLICY_ENTITIES_ROUTE: &str = "/rustfs/admin/v3/idp/builtin/policy-entities";
|
||||
const IAM_ACCESS_KEYS_BULK_ROUTE: &str = "/rustfs/admin/v3/list-access-keys-bulk";
|
||||
const IAM_ACCESS_KEYS_BULK_LDAP_ROUTE: &str = "/rustfs/admin/v3/idp/ldap/list-access-keys-bulk";
|
||||
const IAM_ACCESS_KEYS_BULK_OPENID_ROUTE: &str = "/rustfs/admin/v3/idp/openid/list-access-keys-bulk";
|
||||
|
||||
macro_rules! log_system_request_rejected {
|
||||
($operation:expr, $reason:expr) => {
|
||||
@@ -661,9 +667,24 @@ pub struct RuntimeCapabilitiesSummary {
|
||||
pub manual_transition_jobs: CapabilityStatus,
|
||||
}
|
||||
|
||||
/// One named admin capability advertised to management clients
|
||||
/// (rustfs/backlog#1900). `name` is a cross-repo wire contract: the rc
|
||||
/// client gates commands on these exact strings (see rustfs/cli
|
||||
/// `IAM_POLICY_DETACH_CAPABILITY` etc.), so entries may be added but
|
||||
/// existing names must never be renamed or removed.
|
||||
#[derive(Debug, Clone, PartialEq, Eq, Serialize)]
|
||||
pub struct AdvertisedAdminCapability {
|
||||
pub name: &'static str,
|
||||
pub status: CapabilityStatus,
|
||||
}
|
||||
|
||||
#[derive(Debug, Clone, PartialEq, Eq, Serialize)]
|
||||
pub struct RuntimeCapabilitiesResponse {
|
||||
pub summary: RuntimeCapabilitiesSummary,
|
||||
/// Additive field: absent in responses from older servers, so clients
|
||||
/// must treat a missing list as "no dynamic advertisement" and fall
|
||||
/// back to their pinned per-version contract.
|
||||
pub advertised: Vec<AdvertisedAdminCapability>,
|
||||
pub replication: ReplicationCapabilities,
|
||||
pub manual_transition_jobs: ManualTransitionJobCapabilities,
|
||||
pub diagnostic_probes: DiagnosticProbeCapabilities,
|
||||
@@ -986,6 +1007,7 @@ pub(crate) async fn build_runtime_capabilities_response()
|
||||
|
||||
Ok(RuntimeCapabilitiesResponse {
|
||||
summary,
|
||||
advertised: advertised_admin_capabilities(),
|
||||
replication: ReplicationCapabilities::current(),
|
||||
manual_transition_jobs: ManualTransitionJobCapabilities::current(),
|
||||
diagnostic_probes: DiagnosticProbeCapabilities::current(),
|
||||
@@ -1077,6 +1099,23 @@ fn admin_route_capability(method: HttpMethod, path: &str) -> CapabilityStatus {
|
||||
admin_route_capability_from_inventory(method, path, ADMIN_ROUTE_POLICY_SPECS, DEFERRED_ADMIN_ROUTE_POLICIES)
|
||||
}
|
||||
|
||||
fn advertised_admin_capabilities() -> Vec<AdvertisedAdminCapability> {
|
||||
[
|
||||
("admin.iam.policy-attach", HttpMethod::Post, IAM_POLICY_ATTACH_ROUTE),
|
||||
("admin.iam.policy-detach", HttpMethod::Post, IAM_POLICY_DETACH_ROUTE),
|
||||
("admin.iam.policy-entities", HttpMethod::Get, IAM_POLICY_ENTITIES_ROUTE),
|
||||
("admin.iam.access-keys-bulk", HttpMethod::Get, IAM_ACCESS_KEYS_BULK_ROUTE),
|
||||
("admin.iam.access-keys-bulk.ldap", HttpMethod::Get, IAM_ACCESS_KEYS_BULK_LDAP_ROUTE),
|
||||
("admin.iam.access-keys-bulk.openid", HttpMethod::Get, IAM_ACCESS_KEYS_BULK_OPENID_ROUTE),
|
||||
]
|
||||
.into_iter()
|
||||
.map(|(name, method, route)| AdvertisedAdminCapability {
|
||||
name,
|
||||
status: admin_route_capability(method, route),
|
||||
})
|
||||
.collect()
|
||||
}
|
||||
|
||||
fn admin_route_capability_from_inventory(
|
||||
method: HttpMethod,
|
||||
path: &str,
|
||||
@@ -1239,6 +1278,48 @@ mod tests {
|
||||
);
|
||||
}
|
||||
|
||||
/// Wire-contract pin (rustfs/backlog#1900): the rc client keys its
|
||||
/// command gates on these exact capability names, and parses each
|
||||
/// entry as `{name, status: {state, reason?}}`. Renaming or dropping
|
||||
/// a name silently disables the corresponding rc command.
|
||||
#[tokio::test]
|
||||
async fn runtime_capabilities_response_advertises_iam_capabilities() {
|
||||
let response = build_runtime_capabilities_response()
|
||||
.await
|
||||
.expect("runtime capabilities response should build");
|
||||
|
||||
let expected_supported = [
|
||||
"admin.iam.policy-attach",
|
||||
"admin.iam.policy-detach",
|
||||
"admin.iam.policy-entities",
|
||||
"admin.iam.access-keys-bulk",
|
||||
"admin.iam.access-keys-bulk.ldap",
|
||||
"admin.iam.access-keys-bulk.openid",
|
||||
];
|
||||
for name in expected_supported {
|
||||
let entry = response
|
||||
.advertised
|
||||
.iter()
|
||||
.find(|capability| capability.name == name)
|
||||
.unwrap_or_else(|| panic!("{name} must be advertised"));
|
||||
assert_eq!(entry.status.state, CapabilityState::Supported, "{name} must be supported");
|
||||
}
|
||||
|
||||
let mut names: Vec<&str> = response.advertised.iter().map(|capability| capability.name).collect();
|
||||
let total = names.len();
|
||||
names.sort_unstable();
|
||||
names.dedup();
|
||||
assert_eq!(names.len(), total, "advertised capability names must be unique");
|
||||
|
||||
let serialized = serde_json::to_value(&response).expect("response should serialize");
|
||||
let advertised = serialized["advertised"].as_array().expect("advertised must be an array");
|
||||
let detach = advertised
|
||||
.iter()
|
||||
.find(|entry| entry["name"] == "admin.iam.policy-detach")
|
||||
.expect("serialized detach entry must exist");
|
||||
assert_eq!(detach["status"]["state"], "supported");
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn runtime_capabilities_response_reports_missing_topology_before_storage_init() {
|
||||
let response = build_runtime_capabilities_response()
|
||||
|
||||
@@ -369,14 +369,8 @@ pub fn allocator_reclaim_controller_snapshot(ctx: &CancellationToken) -> Allocat
|
||||
}
|
||||
|
||||
#[cfg(not(target_os = "windows"))]
|
||||
#[allow(unsafe_code)]
|
||||
fn collect_allocator_memory(force: bool) -> Result<(), String> {
|
||||
// SAFETY: `mi_collect` is provided by the active global allocator backend
|
||||
// on this target family. It is explicitly intended to reclaim retained
|
||||
// pages/segments and does not require additional invariants from the caller.
|
||||
unsafe {
|
||||
libmimalloc_sys::mi_collect(force);
|
||||
}
|
||||
rustfs_mimalloc::MiMalloc::collect(force);
|
||||
Ok(())
|
||||
}
|
||||
|
||||
|
||||
+10
-8
@@ -26,22 +26,22 @@ struct MiMallocAllocator;
|
||||
unsafe impl GlobalAlloc for MiMallocAllocator {
|
||||
unsafe fn alloc(&self, layout: Layout) -> *mut u8 {
|
||||
// SAFETY: the caller upholds GlobalAlloc's contract for layout.
|
||||
unsafe { mimalloc::MiMalloc.alloc(layout) }
|
||||
unsafe { rustfs_mimalloc::MiMalloc.alloc(layout) }
|
||||
}
|
||||
|
||||
unsafe fn alloc_zeroed(&self, layout: Layout) -> *mut u8 {
|
||||
// SAFETY: the caller upholds GlobalAlloc's contract for layout.
|
||||
unsafe { mimalloc::MiMalloc.alloc_zeroed(layout) }
|
||||
unsafe { rustfs_mimalloc::MiMalloc.alloc_zeroed(layout) }
|
||||
}
|
||||
|
||||
unsafe fn dealloc(&self, ptr: *mut u8, layout: Layout) {
|
||||
// SAFETY: ptr and layout came from this allocator and are forwarded unchanged.
|
||||
unsafe { mimalloc::MiMalloc.dealloc(ptr, layout) }
|
||||
unsafe { rustfs_mimalloc::MiMalloc.dealloc(ptr, layout) }
|
||||
}
|
||||
|
||||
unsafe fn realloc(&self, ptr: *mut u8, layout: Layout, new_size: usize) -> *mut u8 {
|
||||
// SAFETY: ptr and layout came from this allocator and are forwarded unchanged.
|
||||
unsafe { mimalloc::MiMalloc.realloc(ptr, layout, new_size) }
|
||||
unsafe { rustfs_mimalloc::MiMalloc.realloc(ptr, layout, new_size) }
|
||||
}
|
||||
}
|
||||
|
||||
@@ -51,7 +51,7 @@ static GLOBAL: hotpath::CountingAllocator<MiMallocAllocator> = hotpath::Counting
|
||||
|
||||
#[cfg(not(all(feature = "hotpath", feature = "hotpath-alloc")))]
|
||||
#[global_allocator]
|
||||
static GLOBAL: mimalloc::MiMalloc = mimalloc::MiMalloc;
|
||||
static GLOBAL: rustfs_mimalloc::MiMalloc = rustfs_mimalloc::MiMalloc;
|
||||
|
||||
fn main() {
|
||||
let _hotpath_guard = hotpath::HotpathGuardBuilder::new("main").build();
|
||||
@@ -71,8 +71,9 @@ mod tests {
|
||||
allocation.extend_from_slice(&[7_u8; 64]);
|
||||
|
||||
assert_eq!(allocation.len(), 64);
|
||||
let heap = rustfs_mimalloc::heap::Heap::main();
|
||||
// SAFETY: the live Vec pointer is valid to inspect for heap ownership.
|
||||
assert!(unsafe { libmimalloc_sys::mi_is_in_heap_region(allocation.as_ptr().cast()) });
|
||||
assert!(unsafe { heap.contains(allocation.as_ptr()) });
|
||||
}
|
||||
|
||||
#[test]
|
||||
@@ -85,12 +86,13 @@ mod tests {
|
||||
let layout = Layout::from_size_align(32, 8).expect("valid test allocation layout");
|
||||
let grown_layout = Layout::from_size_align(64, 8).expect("valid grown test allocation layout");
|
||||
let allocator = super::MiMallocAllocator;
|
||||
let heap = rustfs_mimalloc::heap::Heap::main();
|
||||
|
||||
// SAFETY: The pointer is checked for null before use and later released
|
||||
// through the same allocator with the corresponding layout.
|
||||
let ptr = unsafe { allocator.alloc_zeroed(layout) };
|
||||
assert!(!ptr.is_null());
|
||||
assert!(unsafe { libmimalloc_sys::mi_is_in_heap_region(ptr.cast()) });
|
||||
assert!(unsafe { heap.contains(ptr) });
|
||||
assert!(unsafe { std::slice::from_raw_parts(ptr, 32).iter().all(|byte| *byte == 0) });
|
||||
|
||||
// SAFETY: `ptr` was allocated by `allocator` with `layout`; on failure
|
||||
@@ -102,7 +104,7 @@ mod tests {
|
||||
panic!("mimalloc realloc failed in allocator smoke test");
|
||||
}
|
||||
|
||||
assert!(unsafe { libmimalloc_sys::mi_is_in_heap_region(grown_ptr.cast()) });
|
||||
assert!(unsafe { heap.contains(grown_ptr) });
|
||||
// SAFETY: `grown_ptr` was reallocated by `allocator` and is released
|
||||
// with the matching grown layout.
|
||||
unsafe { allocator.dealloc(grown_ptr, grown_layout) };
|
||||
|
||||
@@ -17,10 +17,7 @@ use rustfs_io_metrics::{
|
||||
record_cpu_usage, record_memory_usage, record_process_memory_split,
|
||||
};
|
||||
use serde::Serialize;
|
||||
#[cfg(any(test, not(target_os = "windows")))]
|
||||
use serde_json::Value;
|
||||
#[cfg(not(target_os = "windows"))]
|
||||
use std::ffi::CStr;
|
||||
use std::path::Path;
|
||||
use std::sync::{Arc, Mutex, OnceLock};
|
||||
use std::time::Duration;
|
||||
@@ -231,7 +228,18 @@ fn read_cgroup_memory_snapshot() -> Option<CgroupMemorySnapshot> {
|
||||
read_cgroup_v2().or_else(read_cgroup_v1)
|
||||
}
|
||||
|
||||
#[cfg(any(test, not(target_os = "windows")))]
|
||||
fn read_allocator_memory_snapshot() -> Option<AllocatorMemorySnapshot> {
|
||||
let json = rustfs_mimalloc::MiMalloc::stats_json();
|
||||
if json.is_empty() {
|
||||
return None;
|
||||
}
|
||||
let observation = parse_mimalloc_stats_json(&json)?;
|
||||
Some(AllocatorMemorySnapshot {
|
||||
backend: crate::allocator_reclaim::allocator_backend(),
|
||||
observation,
|
||||
})
|
||||
}
|
||||
|
||||
fn numeric_json_value(value: &Value) -> Option<u64> {
|
||||
match value {
|
||||
Value::Number(number) => number
|
||||
@@ -242,7 +250,6 @@ fn numeric_json_value(value: &Value) -> Option<u64> {
|
||||
}
|
||||
}
|
||||
|
||||
#[cfg(any(test, not(target_os = "windows")))]
|
||||
fn numeric_json_field(value: &Value, field: &str) -> Option<u64> {
|
||||
match value {
|
||||
Value::Object(fields) => fields
|
||||
@@ -254,7 +261,6 @@ fn numeric_json_field(value: &Value, field: &str) -> Option<u64> {
|
||||
}
|
||||
}
|
||||
|
||||
#[cfg(any(test, not(target_os = "windows")))]
|
||||
fn mimalloc_stat_field(value: &Value, metric: &str, field: &str) -> Option<u64> {
|
||||
match value {
|
||||
Value::Object(fields) => {
|
||||
@@ -271,12 +277,10 @@ fn mimalloc_stat_field(value: &Value, metric: &str, field: &str) -> Option<u64>
|
||||
}
|
||||
}
|
||||
|
||||
#[cfg(any(test, not(target_os = "windows")))]
|
||||
fn mimalloc_stat_current(value: &Value, metric: &str) -> Option<u64> {
|
||||
mimalloc_stat_field(value, metric, "current")
|
||||
}
|
||||
|
||||
#[cfg(any(test, not(target_os = "windows")))]
|
||||
fn mimalloc_stat_sum(value: &Value, metrics: &[&str], field: &str) -> Option<u64> {
|
||||
metrics
|
||||
.iter()
|
||||
@@ -285,7 +289,6 @@ fn mimalloc_stat_sum(value: &Value, metrics: &[&str], field: &str) -> Option<u64
|
||||
.filter(|value| *value > 0)
|
||||
}
|
||||
|
||||
#[cfg(any(test, not(target_os = "windows")))]
|
||||
fn parse_mimalloc_stats_json(stats_json: &str) -> Option<AllocatorMemoryObservation> {
|
||||
let value = serde_json::from_str::<Value>(stats_json).ok()?;
|
||||
let malloc_metrics = ["malloc_normal", "malloc_huge"];
|
||||
@@ -312,33 +315,6 @@ fn parse_mimalloc_stats_json(stats_json: &str) -> Option<AllocatorMemoryObservat
|
||||
}
|
||||
}
|
||||
|
||||
#[cfg(not(target_os = "windows"))]
|
||||
#[allow(unsafe_code)]
|
||||
fn read_allocator_memory_snapshot() -> Option<AllocatorMemorySnapshot> {
|
||||
// SAFETY: `mi_stats_get_json` returns a null-terminated JSON buffer owned by
|
||||
// mimalloc when called with a null input buffer. The mimalloc API requires
|
||||
// freeing that buffer with `mi_free`; parsing finishes before the buffer is freed.
|
||||
let observation = unsafe {
|
||||
let stats_ptr = libmimalloc_sys::mi_stats_get_json(0, std::ptr::null_mut());
|
||||
if stats_ptr.is_null() {
|
||||
return None;
|
||||
}
|
||||
|
||||
let observation = CStr::from_ptr(stats_ptr).to_str().ok().and_then(parse_mimalloc_stats_json);
|
||||
libmimalloc_sys::mi_free(stats_ptr.cast());
|
||||
observation?
|
||||
};
|
||||
Some(AllocatorMemorySnapshot {
|
||||
backend: crate::allocator_reclaim::allocator_backend(),
|
||||
observation,
|
||||
})
|
||||
}
|
||||
|
||||
#[cfg(target_os = "windows")]
|
||||
fn read_allocator_memory_snapshot() -> Option<AllocatorMemorySnapshot> {
|
||||
None
|
||||
}
|
||||
|
||||
fn configured_memory_observability_interval_secs() -> u64 {
|
||||
rustfs_utils::get_env_u64(ENV_MEMORY_OBSERVABILITY_INTERVAL_SECS, DEFAULT_MEMORY_OBSERVABILITY_INTERVAL_SECS).max(1)
|
||||
}
|
||||
@@ -566,6 +542,13 @@ mod tests {
|
||||
assert_eq!(parse_mimalloc_stats_json(r#"{ "allocator": "unknown" }"#), None);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn read_allocator_memory_snapshot_uses_mimalloc_stats_json() {
|
||||
let snapshot = super::read_allocator_memory_snapshot();
|
||||
#[cfg(not(target_os = "windows"))]
|
||||
assert!(snapshot.is_some(), "allocator snapshot should be available on non-Windows");
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn memory_observability_snapshot_reports_disabled_when_metrics_are_disabled() {
|
||||
let snapshot = build_memory_observability_status_snapshot(false, 15, false);
|
||||
|
||||
@@ -34,8 +34,8 @@ CONCURRENCY=8
|
||||
DURATION="60s"
|
||||
ROUNDS=3
|
||||
COOLDOWN_SECS=20
|
||||
DATASET_SETUP_DURATION="10s"
|
||||
HEALTH_TIMEOUT_SECS=180
|
||||
DATASET_OBJECTS_PER_WORKER=8
|
||||
FAIL_PCT=10
|
||||
WARN_PCT=5
|
||||
ALLOW_REGRESSION=false
|
||||
@@ -100,6 +100,9 @@ Benchmark:
|
||||
--duration <dur> warp duration per cell (default 60s).
|
||||
--rounds <n> rounds per cell; must be >= 3 (default 3).
|
||||
--cooldown <n> cooldown seconds between rounds/sizes (default 20).
|
||||
--dataset-setup-duration <dur>
|
||||
isolated Warp PUT warm-up for get/mixed legs
|
||||
(default 10s; not included in the measurement).
|
||||
--concurrency <n> warp concurrency (default 8).
|
||||
--warp-bin <path> warp binary (default warp).
|
||||
|
||||
@@ -170,6 +173,7 @@ while [[ $# -gt 0 ]]; do
|
||||
--duration) DURATION="$2"; shift 2 ;;
|
||||
--rounds) ROUNDS="$2"; shift 2 ;;
|
||||
--cooldown) COOLDOWN_SECS="$2"; shift 2 ;;
|
||||
--dataset-setup-duration) DATASET_SETUP_DURATION="$2"; shift 2 ;;
|
||||
--health-timeout) HEALTH_TIMEOUT_SECS="$2"; shift 2 ;;
|
||||
--fail-pct) FAIL_PCT="$2"; shift 2 ;;
|
||||
--warn-pct) WARN_PCT="$2"; shift 2 ;;
|
||||
@@ -362,18 +366,29 @@ measure() {
|
||||
--duration "$DURATION" --rounds "$ROUNDS" --cooldown-secs "$COOLDOWN_SECS"
|
||||
--out-dir "$cell"
|
||||
)
|
||||
if [[ "$mode" != "put" ]]; then
|
||||
# Warp defaults to 2,500 setup objects per round. At 10 MiB that writes
|
||||
# 25 GiB before every 12-second measurement, so the matrix cannot finish
|
||||
# inside the workflow budget. Eight objects per worker keeps preparation
|
||||
# bounded while retaining a multi-object working set for relative A/B.
|
||||
args+=(--extra-args "--objects $((CONCURRENCY * DATASET_OBJECTS_PER_WORKER)) --noclear")
|
||||
fi
|
||||
[[ "$mode" == "put" ]] || args+=(--extra-args "--noclear")
|
||||
[[ -n "$baseline_csv" ]] && args+=(--baseline-csv "$baseline_csv")
|
||||
run "$ENHANCED_BENCH" "${args[@]}" >&2
|
||||
echo "$cell"
|
||||
}
|
||||
|
||||
prepare_dataset() {
|
||||
local leg="$1" workload="$2" mode="$3" size="$4" sync_label="$5" bucket="$6"
|
||||
[[ "$mode" != "put" ]] || return 0
|
||||
|
||||
local setup_cell="$OUT_DIR/$workload/$sync_label/$leg/dataset-setup"
|
||||
local args=(
|
||||
--tool warp --warp-bin "$WARP_BIN" --warp-mode put
|
||||
--endpoint "$ADDRESS" --access-key "$ACCESS_KEY" --secret-key "$SECRET_KEY"
|
||||
--region "$REGION" --bucket "$bucket" --sizes "$size" --concurrency "$CONCURRENCY"
|
||||
--duration "$DATASET_SETUP_DURATION" --rounds 1 --cooldown-secs 0
|
||||
--extra-args "--noclear"
|
||||
--out-dir "$setup_cell"
|
||||
)
|
||||
log "preparing isolated dataset: $sync_label/$workload/$leg bucket=$bucket"
|
||||
run "$ENHANCED_BENCH" "${args[@]}" >&2
|
||||
}
|
||||
|
||||
write_schedule_header() {
|
||||
echo "sync_label,drive_sync,workload,mode,size,leg,phase,binary,out_dir,bucket,dataset_setup" >"$OUT_DIR/abba_schedule.csv"
|
||||
}
|
||||
@@ -384,7 +399,7 @@ append_schedule() {
|
||||
phase="$(phase_for_leg "$leg")"
|
||||
bin="$(binary_for_leg "$leg")"
|
||||
local dataset_setup="none"
|
||||
[[ "$mode" == "put" ]] || dataset_setup="warp-native-bounded"
|
||||
[[ "$mode" == "put" ]] || dataset_setup="warp-put"
|
||||
echo "$sync_label,$drive_sync,$workload,$mode,$size,$leg,$phase,$bin,$OUT_DIR/$workload/$sync_label/$leg,$bucket,$dataset_setup" >>"$OUT_DIR/abba_schedule.csv"
|
||||
}
|
||||
|
||||
@@ -466,8 +481,7 @@ dataset_namespace=$DATASET_NAMESPACE
|
||||
local_run_data_root=$RUN_DATA_ROOT
|
||||
bucket_isolation=per-leg
|
||||
bucket_prefix=rustfs-abba-$DATASET_NAMESPACE
|
||||
dataset_setup=get-and-mixed-via-bounded-warp-native
|
||||
dataset_objects=$((CONCURRENCY * DATASET_OBJECTS_PER_WORKER))
|
||||
dataset_setup=get-and-mixed-via-warp-put
|
||||
endpoint=$ADDRESS
|
||||
warp_version=$("$WARP_BIN" --version 2>/dev/null | head -n1 || echo unknown)
|
||||
EOF
|
||||
@@ -488,6 +502,7 @@ for ds_spec in "${DRIVE_SYNC_MATRIX[@]}"; do
|
||||
log "=== $sync_label $workload leg $leg ($(phase_for_leg "$leg")) ==="
|
||||
bucket="$(bucket_for_leg "$sync_label" "$workload" "$leg")"
|
||||
bring_up "$leg" "$drive_sync" "$workload" "$mode" "$size" "$sync_label" "$bucket"
|
||||
prepare_dataset "$leg" "$workload" "$mode" "$size" "$sync_label" "$bucket"
|
||||
append_schedule "$sync_label" "$drive_sync" "$workload" "$mode" "$size" "$leg" "$bucket"
|
||||
|
||||
baseline_csv=""
|
||||
|
||||
@@ -672,7 +672,7 @@ extract_report_line() {
|
||||
local regex="$1"
|
||||
local file="$2"
|
||||
awk -v regex="$regex" '
|
||||
/^(Report|Operation):/ {
|
||||
/^Report:/ {
|
||||
in_report = 1
|
||||
next
|
||||
}
|
||||
@@ -703,9 +703,9 @@ normalize_duration_metric() {
|
||||
extract_metrics() {
|
||||
local log_file="$1"
|
||||
|
||||
local average_line request_line throughput reqps latency req_p90 req_p99 reqps_num
|
||||
local average_line reqs_line throughput reqps latency req_p90 req_p99 reqps_num
|
||||
average_line="$(extract_report_line '^[[:space:]]*[*][[:space:]]+Average:' "$log_file")"
|
||||
request_line="$(extract_report_line '^[[:space:]]*[*][[:space:]]+(Reqs:[[:space:]]+)?Avg:' "$log_file")"
|
||||
reqs_line="$(extract_report_line '^[[:space:]]*[*][[:space:]]+Reqs:' "$log_file")"
|
||||
|
||||
if [[ -n "$average_line" ]]; then
|
||||
throughput="$(echo "$average_line" | sed -E 's/^.*Average:[[:space:]]*//; s/,[[:space:]]*.*$//')"
|
||||
@@ -715,16 +715,20 @@ extract_metrics() {
|
||||
reqps="$(extract_first '[0-9]+(\.[0-9]+)?[[:space:]]*(obj/s|req/s|ops/s|requests/s)' "$log_file")"
|
||||
fi
|
||||
|
||||
if [[ -n "$request_line" ]]; then
|
||||
latency="$(echo "$request_line" | rg -o 'Avg:[[:space:]]+[0-9]+(\.[0-9]+)?(ms|us|µs|s)' | sed -E 's/^Avg:[[:space:]]+//')"
|
||||
req_p90="$(echo "$request_line" | rg -o '90%:[[:space:]]+[0-9]+(\.[0-9]+)?(ms|us|µs|s)' | sed -E 's/^90%:[[:space:]]+//')"
|
||||
req_p99="$(echo "$request_line" | rg -o '99%:[[:space:]]+[0-9]+(\.[0-9]+)?(ms|us|µs|s)' | sed -E 's/^99%:[[:space:]]+//')"
|
||||
if [[ -n "$reqs_line" ]]; then
|
||||
latency="$(echo "$reqs_line" | rg -o 'Avg:[[:space:]]+[0-9]+(\.[0-9]+)?(ms|us|µs|s)' | sed -E 's/^Avg:[[:space:]]+//')"
|
||||
req_p90="$(echo "$reqs_line" | rg -o '90%:[[:space:]]+[0-9]+(\.[0-9]+)?(ms|us|µs|s)' | sed -E 's/^90%:[[:space:]]+//')"
|
||||
req_p99="$(echo "$reqs_line" | rg -o '99%:[[:space:]]+[0-9]+(\.[0-9]+)?(ms|us|µs|s)' | sed -E 's/^99%:[[:space:]]+//')"
|
||||
else
|
||||
latency="$(rg -o 'Reqs:[[:space:]]+Avg:[[:space:]]+[0-9]+(\.[0-9]+)?(ms|us|µs|s)' "$log_file" | head -n1 | sed -E 's/^Reqs:[[:space:]]+Avg:[[:space:]]+//')"
|
||||
req_p90="$(rg -o '90%:[[:space:]]+[0-9]+(\.[0-9]+)?(ms|us|µs|s)' "$log_file" | head -n1 | sed -E 's/^90%:[[:space:]]+//')"
|
||||
req_p99="$(rg -o '99%:[[:space:]]+[0-9]+(\.[0-9]+)?(ms|us|µs|s)' "$log_file" | head -n1 | sed -E 's/^99%:[[:space:]]+//')"
|
||||
fi
|
||||
|
||||
if [[ -z "$latency" ]]; then
|
||||
latency="$(extract_first '[0-9]+(\.[0-9]+)?[[:space:]]*(ms|us|µs|s)' "$log_file")"
|
||||
fi
|
||||
|
||||
throughput="$(trim "${throughput:-N/A}")"
|
||||
reqps="$(trim "${reqps:-N/A}")"
|
||||
latency="$(trim "${latency:-N/A}")"
|
||||
@@ -1124,8 +1128,6 @@ run_one_attempt() {
|
||||
"--concurrent" "$CONCURRENCY"
|
||||
"--duration" "$DURATION"
|
||||
"--region" "$REGION"
|
||||
"--no-color"
|
||||
"--analyze.v"
|
||||
)
|
||||
if [[ "$INSECURE" == "true" ]]; then
|
||||
cmd+=("--insecure")
|
||||
@@ -1210,12 +1212,6 @@ run_one_attempt() {
|
||||
req_p99_ms="$(to_ms "$req_p99_human")"
|
||||
fi
|
||||
|
||||
if [[ "$DRY_RUN" != "true" && "$TOOL" == "warp" && "$status" == "ok" ]] \
|
||||
&& rg -q '^[[:space:]]*(Total[[:space:]]+)?Errors:[[:space:]]+[1-9][0-9]*[.]?([[:space:]]|$)' "$log_file"; then
|
||||
status="failed"
|
||||
exit_code=1
|
||||
fi
|
||||
|
||||
if [[ "$DRY_RUN" != "true" && "$status" == "ok" ]]; then
|
||||
if [[ "$throughput_bps" == "N/A" && "$reqps" == "N/A" ]]; then
|
||||
status="failed"
|
||||
@@ -1322,21 +1318,10 @@ compare_baseline() {
|
||||
|
||||
dr="N/A"; dl="N/A"; dt="N/A"; dp90="N/A"; dp99="N/A"; ne="N/A"; be="N/A"; de="N/A"
|
||||
if (br!="N/A" && n_req!="N/A" && br+0!=0) dr=sprintf("%.2f", ((n_req-br)/br)*100)
|
||||
if (bl!="N/A" && n_lat!="N/A") {
|
||||
if (bl+0!=0) dl=sprintf("%.2f", ((n_lat-bl)/bl)*100)
|
||||
else if (n_lat+0==0) dl="0.00"
|
||||
}
|
||||
if (bl!="N/A" && n_lat!="N/A" && bl+0!=0) dl=sprintf("%.2f", ((n_lat-bl)/bl)*100)
|
||||
if (bt!="N/A" && n_thr!="N/A" && bt+0!=0) dt=sprintf("%.2f", ((n_thr-bt)/bt)*100)
|
||||
# Warp v1 rounds sub-millisecond latency to 0s. Two zero readings are
|
||||
# the same below-resolution bucket; a nonzero candidate remains invalid.
|
||||
if (bp90!="N/A" && n_p90!="N/A") {
|
||||
if (bp90+0!=0) dp90=sprintf("%.2f", ((n_p90-bp90)/bp90)*100)
|
||||
else if (n_p90+0==0) dp90="0.00"
|
||||
}
|
||||
if (bp99!="N/A" && n_p99!="N/A") {
|
||||
if (bp99+0!=0) dp99=sprintf("%.2f", ((n_p99-bp99)/bp99)*100)
|
||||
else if (n_p99+0==0) dp99="0.00"
|
||||
}
|
||||
if (bp90!="N/A" && n_p90!="N/A" && bp90+0!=0) dp90=sprintf("%.2f", ((n_p90-bp90)/bp90)*100)
|
||||
if (bp99!="N/A" && n_p99!="N/A" && bp99+0!=0) dp99=sprintf("%.2f", ((n_p99-bp99)/bp99)*100)
|
||||
if (n_ok!="N/A" && n_fail!="N/A" && n_ok+n_fail>0) ne=sprintf("%.2f", (n_fail/(n_ok+n_fail))*100)
|
||||
if (bok!="N/A" && bfail!="N/A" && bok+bfail>0) be=sprintf("%.2f", (bfail/(bok+bfail))*100)
|
||||
if (ne!="N/A" && be!="N/A") de=sprintf("%.2f", ne-be)
|
||||
|
||||
@@ -58,13 +58,8 @@ rg -qx 'evidence_mode=dry-run' "$OUT_DIR/manifest.env"
|
||||
rg -qx 'formal_evidence=false' "$OUT_DIR/manifest.env"
|
||||
rg -qx 'performance_conclusion=not_measured_dry_run' "$OUT_DIR/manifest.env"
|
||||
rg -qx 'bucket_isolation=per-leg' "$OUT_DIR/manifest.env"
|
||||
rg -qx 'dataset_setup=get-and-mixed-via-bounded-warp-native' "$OUT_DIR/manifest.env"
|
||||
rg -qx 'dataset_objects=64' "$OUT_DIR/manifest.env"
|
||||
[[ "$(rg -c -- '--extra-args --objects\\ 64\\ --noclear' "$TRACE_FILE")" == "32" ]]
|
||||
if rg -q -- 'dataset-setup' "$TRACE_FILE"; then
|
||||
echo "unexpected redundant dataset setup command" >&2
|
||||
exit 1
|
||||
fi
|
||||
rg -qx 'dataset_setup=get-and-mixed-via-warp-put' "$OUT_DIR/manifest.env"
|
||||
[[ "$(rg -c -- '--extra-args --noclear' "$TRACE_FILE")" == "64" ]]
|
||||
! rg -q -- 'rustfs-bench' "$TRACE_FILE"
|
||||
|
||||
if "$RUNNER" \
|
||||
|
||||
@@ -74,28 +74,13 @@ FAKE_WARP="${TMP_DIR}/fake-warp"
|
||||
cat >"$FAKE_WARP" <<'EOF'
|
||||
#!/usr/bin/env bash
|
||||
set -euo pipefail
|
||||
[[ " $* " == *" --analyze.v "* ]]
|
||||
[[ " $* " == *" --no-color "* ]]
|
||||
if [[ "${FAKE_WARP_ZERO_LATENCY:-0}" == "1" ]]; then
|
||||
cat <<'LOG'
|
||||
Operation: GET. Concurrency: 8. Ran: 7s
|
||||
Requests considered: 1000:
|
||||
* Average: 160.00 MiB/s, 40960.00 obj/s
|
||||
* Avg: 0s, 50%: 0s, 90%: 0s, 99%: 0s, Fastest: 0s, Slowest: 1ms, StdDev: 0s
|
||||
LOG
|
||||
exit 0
|
||||
fi
|
||||
cat <<'LOG'
|
||||
- PUT Average: 161 Obj/s, 5.0MiB/s; Current 161 Obj/s, 5.0MiB/s.
|
||||
Operation: GET. Concurrency: 64. Ran: 7s
|
||||
Requests considered: 1000:
|
||||
Report: GET. Concurrency: 64. Ran: 7s
|
||||
* Average: 653.90 MiB/s, 20925.58 obj/s
|
||||
* Avg: 3.5ms, 50%: 2.0ms, 90%: 3.6ms, 99%: 24.1ms, Fastest: 0.2ms, Slowest: 607.7ms, StdDev: 20.6ms
|
||||
* Reqs: Avg: 3.5ms, 50%: 2.0ms, 90%: 3.6ms, 99%: 24.1ms, Fastest: 0.2ms, Slowest: 607.7ms, StdDev: 20.6ms
|
||||
Throughput, split into 7 x 1s:
|
||||
LOG
|
||||
if [[ "${FAKE_WARP_ERRORS:-0}" == "1" ]]; then
|
||||
echo 'Total Errors: 1.'
|
||||
fi
|
||||
EOF
|
||||
chmod +x "$FAKE_WARP"
|
||||
|
||||
@@ -118,32 +103,6 @@ chmod +x "$FAKE_WARP"
|
||||
|
||||
rg -q '^32767B,warp,1,1,128,ok,0,[^,]+,[^,]+,653.90 MiB/s,685663846.400000,20925.58,3.5 ms,3.500000,[^,]+,3.6 ms,3.600000,24.1 ms,24.100000$' "${TMP_DIR}/fake-warp-run/round_results.csv"
|
||||
|
||||
cat >"${TMP_DIR}/warp-no-details.log" <<'EOF'
|
||||
warp: Starting benchmark in 3s...
|
||||
Operation: PUT. Concurrency: 8
|
||||
* Average: 2.76 MiB/s, 707.03 obj/s
|
||||
EOF
|
||||
"$RUNNER" --extract-metrics-from-log "${TMP_DIR}/warp-no-details.log" >"${TMP_DIR}/warp-no-details.csv"
|
||||
rg -qx '2.76 MiB/s,2894069.760000,707.03,N/A,N/A,N/A,N/A,N/A,N/A' "${TMP_DIR}/warp-no-details.csv"
|
||||
|
||||
if FAKE_WARP_ERRORS=1 "$RUNNER" \
|
||||
--tool warp \
|
||||
--endpoint http://127.0.0.1:9000 \
|
||||
--access-key test-access \
|
||||
--secret-key test-secret \
|
||||
--sizes 32767B \
|
||||
--rounds 1 \
|
||||
--retry-per-round 1 \
|
||||
--retry-sleep-secs 1 \
|
||||
--cooldown-secs 0 \
|
||||
--duration 1s \
|
||||
--out-dir "${TMP_DIR}/fake-warp-errors" \
|
||||
--warp-bin "$FAKE_WARP" >/dev/null 2>&1; then
|
||||
echo "expected Warp request errors to fail the benchmark" >&2
|
||||
exit 1
|
||||
fi
|
||||
rg -q ',failed,1,' "${TMP_DIR}/fake-warp-errors/round_results.csv"
|
||||
|
||||
"$RUNNER" \
|
||||
--tool warp \
|
||||
--endpoint http://127.0.0.1:9000 \
|
||||
@@ -173,28 +132,4 @@ awk -F',' '
|
||||
END { exit found ? 0 : 1 }
|
||||
' "${TMP_DIR}/fake-warp-candidate/baseline_compare.csv"
|
||||
|
||||
for leg in baseline candidate; do
|
||||
zero_args=(
|
||||
--tool warp
|
||||
--endpoint http://127.0.0.1:9000
|
||||
--access-key test-access
|
||||
--secret-key test-secret
|
||||
--sizes 4KiB
|
||||
--rounds 1
|
||||
--retry-per-round 1
|
||||
--cooldown-secs 0
|
||||
--duration 1s
|
||||
--out-dir "${TMP_DIR}/fake-warp-zero-${leg}"
|
||||
--warp-bin "$FAKE_WARP"
|
||||
)
|
||||
if [[ "$leg" == "candidate" ]]; then
|
||||
zero_args+=(--baseline-csv "${TMP_DIR}/fake-warp-zero-baseline/median_summary.csv")
|
||||
fi
|
||||
FAKE_WARP_ZERO_LATENCY=1 "$RUNNER" "${zero_args[@]}" >/dev/null 2>&1
|
||||
done
|
||||
|
||||
"${SCRIPT_DIR}/hotpath_warp_ab_gate.sh" \
|
||||
--compare-csv "${TMP_DIR}/fake-warp-zero-candidate/baseline_compare.csv" \
|
||||
--require-tail-error >/dev/null
|
||||
|
||||
echo "object batch benchmark enhanced tests passed"
|
||||
|
||||
Reference in New Issue
Block a user