diff --git a/CLAUDE.md b/CLAUDE.md index 5e75fe3cb..59893c48b 100644 --- a/CLAUDE.md +++ b/CLAUDE.md @@ -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): diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md index 7882a486e..5842395f4 100644 --- a/CONTRIBUTING.md +++ b/CONTRIBUTING.md @@ -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 diff --git a/Cargo.lock b/Cargo.lock index b7b1ec220..517983884 100644 --- a/Cargo.lock +++ b/Cargo.lock @@ -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" diff --git a/Cargo.toml b/Cargo.toml index 918af3cce..717a0c6e6 100644 --- a/Cargo.toml +++ b/Cargo.toml @@ -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" } diff --git a/crates/ecstore/src/io_support/bitrot.rs b/crates/ecstore/src/io_support/bitrot.rs index 05c81c048..88a3da910 100644 --- a/crates/ecstore/src/io_support/bitrot.rs +++ b/crates/ecstore/src/io_support/bitrot.rs @@ -784,6 +784,24 @@ pub(crate) fn create_deferred_bitrot_reader_with_stripe_handle( /// /// # Returns /// A Result containing the BitrotWriterWrapper or an error +/// Size hint handed to `DiskAPI::create_file` for a bitrot-wrapped shard. +/// +/// A known length is grown by one checksum per shard so the on-disk file size +/// matches what the bitrot writer emits. A negative length is the +/// unknown-size sentinel (`HashReader::SIZE_PRESERVE_LAYER`, used by SSE and +/// compression) and must be preserved: `RemoteDisk::create_file` forwards it +/// in the `put_file_stream` query, and the receiver only treats `size > 0` as +/// a fixed body length when locating the authenticated trailer. Clamping it +/// to `0` would claim an empty body and misframe the stream. `0` stays `0` +/// because a genuinely empty object still means an empty body. +fn bitrot_create_file_size(length: i64, shard_size: usize, checksum_algo: &HashAlgorithm) -> i64 { + if length <= 0 { + return length; + } + let length = length as usize; + (length.div_ceil(shard_size) * checksum_algo.size() + length) as i64 +} + pub async fn create_bitrot_writer( is_inline_buffer: bool, disk: Option<&DiskStore>, @@ -796,12 +814,7 @@ pub async fn create_bitrot_writer( let writer = if is_inline_buffer { CustomWriter::new_inline_buffer() } else if let Some(disk) = disk { - let length = if length > 0 { - let length = length as usize; - (length.div_ceil(shard_size) * checksum_algo.size() + length) as i64 - } else { - 0 - }; + let length = bitrot_create_file_size(length, shard_size, &checksum_algo); let file = disk.create_file("", volume, path, length).await?; #[cfg(feature = "hotpath")] @@ -820,6 +833,25 @@ mod tests { use rustfs_rio::ChunkReader; use std::collections::VecDeque; + #[test] + fn bitrot_create_file_size_grows_known_length_by_checksums() { + // 10 bytes over 4-byte shards = 3 shards, each followed by a 32-byte hash. + assert_eq!(bitrot_create_file_size(10, 4, &HashAlgorithm::HighwayHash256), 10 + 3 * 32); + assert_eq!(bitrot_create_file_size(10, 4, &HashAlgorithm::None), 10); + } + + #[test] + fn bitrot_create_file_size_keeps_empty_and_unknown_distinct() { + assert_eq!(bitrot_create_file_size(0, 4, &HashAlgorithm::HighwayHash256), 0); + // SSE/compression streams advertise SIZE_PRESERVE_LAYER (-1); the remote + // put_file_stream receiver relies on a non-positive size to parse the auth + // trailer from the stream tail, so the sentinel must survive untouched. + assert_eq!( + bitrot_create_file_size(rustfs_rio::HashReader::SIZE_PRESERVE_LAYER, 4, &HashAlgorithm::HighwayHash256), + rustfs_rio::HashReader::SIZE_PRESERVE_LAYER + ); + } + struct TestChunkReader { chunks: VecDeque, } diff --git a/crates/ecstore/src/set_disk/ops/object.rs b/crates/ecstore/src/set_disk/ops/object.rs index 8f07a7ff7..bb3c9fbf9 100644 --- a/crates/ecstore/src/set_disk/ops/object.rs +++ b/crates/ecstore/src/set_disk/ops/object.rs @@ -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 { diff --git a/crates/ecstore/src/store/rebalance/support.rs b/crates/ecstore/src/store/rebalance/support.rs index 936cb01e4..3a3ff6c42 100644 --- a/crates/ecstore/src/store/rebalance/support.rs +++ b/crates/ecstore/src/store/rebalance/support.rs @@ -271,7 +271,8 @@ pub(super) fn resolve_latest_object_info_candidates( .filter(|candidate| latest_candidate_mod_time(candidate) == Some(latest_mod_time)) .collect::>(); - latest_candidates.sort_by_key(|left| std::cmp::Reverse(left.idx)); + latest_candidates.sort_by_key(|candidate| std::cmp::Reverse(candidate.idx)); + let Some(winner) = latest_candidates.first() else { return Err(Error::ErasureReadQuorum); diff --git a/deny.toml b/deny.toml index 296b229e4..c6fb8facc 100644 --- a/deny.toml +++ b/deny.toml @@ -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] diff --git a/docs/testing/ci-gates.md b/docs/testing/ci-gates.md new file mode 100644 index 000000000..d87ce1668 --- /dev/null +++ b/docs/testing/ci-gates.md @@ -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 ` | +| 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 ` 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= ./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. diff --git a/rustfs/Cargo.toml b/rustfs/Cargo.toml index af5514870..03afb5628 100644 --- a/rustfs/Cargo.toml +++ b/rustfs/Cargo.toml @@ -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"] } diff --git a/rustfs/src/allocator_reclaim.rs b/rustfs/src/allocator_reclaim.rs index 0c31390c3..eba1a8948 100644 --- a/rustfs/src/allocator_reclaim.rs +++ b/rustfs/src/allocator_reclaim.rs @@ -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(()) } diff --git a/rustfs/src/main.rs b/rustfs/src/main.rs index 5e9d5075b..7f4bea1d2 100644 --- a/rustfs/src/main.rs +++ b/rustfs/src/main.rs @@ -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 = 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) }; diff --git a/rustfs/src/memory_observability.rs b/rustfs/src/memory_observability.rs index 3e29d24a0..12bd4b3c5 100644 --- a/rustfs/src/memory_observability.rs +++ b/rustfs/src/memory_observability.rs @@ -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 { read_cgroup_v2().or_else(read_cgroup_v1) } -#[cfg(any(test, not(target_os = "windows")))] +fn read_allocator_memory_snapshot() -> Option { + 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 { match value { Value::Number(number) => number @@ -242,7 +250,6 @@ fn numeric_json_value(value: &Value) -> Option { } } -#[cfg(any(test, not(target_os = "windows")))] fn numeric_json_field(value: &Value, field: &str) -> Option { match value { Value::Object(fields) => fields @@ -254,7 +261,6 @@ fn numeric_json_field(value: &Value, field: &str) -> Option { } } -#[cfg(any(test, not(target_os = "windows")))] fn mimalloc_stat_field(value: &Value, metric: &str, field: &str) -> Option { match value { Value::Object(fields) => { @@ -271,12 +277,10 @@ fn mimalloc_stat_field(value: &Value, metric: &str, field: &str) -> Option } } -#[cfg(any(test, not(target_os = "windows")))] fn mimalloc_stat_current(value: &Value, metric: &str) -> Option { mimalloc_stat_field(value, metric, "current") } -#[cfg(any(test, not(target_os = "windows")))] fn mimalloc_stat_sum(value: &Value, metrics: &[&str], field: &str) -> Option { metrics .iter() @@ -285,7 +289,6 @@ fn mimalloc_stat_sum(value: &Value, metrics: &[&str], field: &str) -> Option 0) } -#[cfg(any(test, not(target_os = "windows")))] fn parse_mimalloc_stats_json(stats_json: &str) -> Option { let value = serde_json::from_str::(stats_json).ok()?; let malloc_metrics = ["malloc_normal", "malloc_huge"]; @@ -312,33 +315,6 @@ fn parse_mimalloc_stats_json(stats_json: &str) -> Option Option { - // 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 { - 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);