* perf(put): add eager path metrics and isolation tooling
* fix(decommission): persist progress adaptively (#3497)
Persist decommission progress after either the existing time interval or a migrated-item threshold, and flush progress baselines after bucket and terminal-state saves.
Also stabilize the OIDC discovery mock used by the pre-commit gate.
* refactor: move bucket operations contract (#3507)
* fix(s3): handle multipart flexible checksums (#3508)
* fix(io-core): avoid blocking on pooled buffer return
* perf(put): add slow inflight diagnostics
* perf(put): fix 16KiB regression with threshold and pool bypass
- Lower SMALL_EAGER_PUT_MAX_SIZE from 256KB to 8KB so objects >8KiB
use the streaming BufReader path (matches baseline behavior)
- Add POOL_BYPASE_MAX_SIZE (16KiB) to bypass BytesPool for very small
objects, avoiding Small-tier Mutex contention under high concurrency
- Add read_small_put_body_exact_direct() for direct Vec<u8> allocation
- Fix stale test assertions to match new 8KB threshold
Root cause analysis: the 16KiB regression was primarily caused by
instrumentation overhead in set_disk.rs (4x Instant::now() + metrics
per PUT), not BytesPool contention. Lowering the threshold eliminates
the eager-path overhead for 16KiB+ objects.
* perf(put): gate stage metrics behind observability flag
Add put_stage_metrics_enabled() AtomicBool switch in io-metrics crate.
When disabled (default), record_put_object_path() and
record_put_object_stage_duration() are no-ops, avoiding unnecessary
histogram/counter macro overhead in the PUT hot path.
The flag is set to true during startup when OTEL metric export is
enabled (rustfs_obs::observability_metric_enabled() == true).
This eliminates the per-request metrics overhead that contributed
to the 16KiB PUT regression when metrics collection is not active.
* perf(put): comprehensive optimization - restore eager path, cache env, remove UUID
Change 1: Restore SMALL_EAGER_PUT_MAX_SIZE from 8KB to 1MB
- The try_lock() fix (d13a189e3) eliminates the blocking that caused
service health timeouts under 512KiB c64 load
- Eager path with BytesPool is now safe for objects up to 1MB
- Recovers the eager path benefit for 32KiB-256KiB objects
Change 2: Adjust POOL_BYPASE_MAX_SIZE from 16KB to 4KB
- With eager path restored to 1MB, objects 4KB-1MB benefit from pool reuse
- Only ≤4KB objects bypass the pool (allocation cost negligible)
Change 3: Cache RUSTFS_ERASURE_ENCODE_MAX_INFLIGHT_BYTES via OnceLock
- Eliminates per-encode std::env::var() syscall
- Env var still works (read once at first use)
Change 4: Replace Uuid::new_v4() with Uuid::nil() in Erasure construction
- _id field is unused in hot paths (documented in code)
- Eliminates CSPRNG syscall per PUT request
Change 5: Add concurrency-aware buffer sizing to PUT path
- Reuses get_concurrency_aware_buffer_size() from GET path
- Reduces buffer size under high concurrency (0.4x at >8 concurrent)
- Lowers memory pressure for >1MB streaming PUTs
* chore: add pyroscope feature flag and clean up imports
- Add pyroscope feature flag forwarding to rustfs-obs
- Remove unused allow(non_upper_case_globals) in globals.rs
- Sort imports and fix Cargo.toml formatting consistency
* style: fix import ordering and code formatting
- Sort imports alphabetically in globals.rs, encode.rs
- Fix indentation in erasure_coding encode/erasure
- Clean up HashReader formatting in object_usecase.rs
* fix(test): use tokio::test for request_logging_layer tests
The tests call tokio::spawn via RequestContextLayer, which requires a
Tokio runtime. Changed from #[test] + futures::executor::block_on to
#[tokio::test] + .await, and replaced tracing::subscriber::with_default
with tracing::subscriber::set_default to support async.
* fix(bench): normalize no-space throughput/latency parsing in to_bps/to_ms
When a benchmark tool prints throughput without a separator (e.g. 123MiB/s),
awk '{print $2}' returns empty because the whole string is one field,
causing to_bps to return N/A and losing valid measurements in CSV output.
Insert a space between number and unit via sed before awk field splitting.
Same fix applied to to_ms for latency values like '50ms'.
Also add TODO comment on PUT path noting that get_concurrency_aware_buffer_size
reads ACTIVE_GET_REQUESTS instead of PUT concurrency (PR #3514 review).
Refs: PR #3514 review comments by chatgpt-codex-connector
* fix(metrics): correct POOL_BYPASS comments and separate PUT vs generic stage metrics
- Fix 3 comment-code mismatches: POOL_BYPASS_MAX_SIZE is 4KiB, not 16KiB
- Add generic record_stage_duration() with separate histogram
(rustfs_internal_stage_duration_ms) for non-PUT paths
- Replace record_put_object_stage_duration with record_stage_duration in
metacache_set, store_list_objects, and bucket_lifecycle_ops to avoid
polluting PUT-specific dashboards with listing/lifecycle timings
- Fix flaky test: serialize tests mutating PUT_STAGE_METRICS_ENABLED with
METRICS_FLAG_LOCK mutex and explicitly set desired state at test start
Refs: PR #3514 review comments by chatgpt-codex-connector
* style: apply cargo fmt to metacache_set.rs
---------
Co-authored-by: cxymds <cxymds@gmail.com>
Co-authored-by: 安正超 <anzhengchao@gmail.com>
* perf(ecstore): reuse erasure-decode shard buffers across stripes
ParallelReader::read allocated and zero-filled a fresh
`vec![0u8; shard_size]` per shard on every erasure stripe. Erasure::decode
builds one ParallelReader and loops stripes, so those buffers can be
reused: BitrotReader::read overwrites buf[..n] and the caller truncates to
n, so leftover bytes from the prior stripe are never observed. The decode
loop now hands each stripe's shard buffers back to the reader, which
reuses them (resized to shard_size) on the next stripe. The heal path,
which consumes its buffers into Bytes, never hands them back and is
unchanged.
This path runs on every object GET. Streaming-decode benchmark
(Erasure::decode end-to-end, median):
4+2 16MiB 1MiB-block: -9.6% verify-on, -23.8% verify-off
6+3 24MiB 1MiB-block: -9.7% verify-on, -22.5% verify-off
4+2 4MiB 64KiB-block: -5.5% verify-on, -16.3% verify-off
Adds a streaming-decode benchmark covering the ParallelReader path and a
regression test that decodes a multi-stripe object with missing data
shards (so reconstructed buffers are recycled) with bitrot verification
both on and off, asserting byte-exact output.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* perf(ecstore): tighten decode buffer reuse and bench harness
Address PR review feedback on the erasure-decode buffer-reuse change:
- Only claim a recycled shard buffer inside the `Some(reader)` branch of
`ParallelReader::read`, so the take is co-located with the read that
uses it and missing shards no longer touch the recycle slot.
- Move per-shard `BitrotReader` construction into Criterion `iter_batched`
setup so reader/UUID construction stays out of the timed decode path,
and assert decode success plus full output length each iteration.
Re-measured with the cleaner harness (median, before -> after, all
p < 0.05): verify-on -5.3%..-11.7%, verify-off -15.8%..-25.3%.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* perf(ecstore): drop dead recycle slots and tidy decode bench
Address the second PR review pass:
- In `Erasure::decode`, clear recycled slots for missing-shard (None-reader)
indices before handing buffers back. `ParallelReader::read` only reuses
slots with an active reader, and `decode_data` always re-allocates the
reconstructed shard, so retaining those buffers only held memory that could
never be reused in degraded reads.
- Move the output sink into the benchmark's `iter_batched` setup and validate
decode success/output length once per config instead of inside the timed
loop, so neither sink construction nor assertions touch the measurement.
Re-measured with the final harness (median, before -> after, all p < 0.05):
verify-on -5.2%..-9.8%, verify-off -19.4%..-25.8%.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
---------
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* perf(erasure): remove UUID from clone + increase encode inflight budget
Two targeted optimizations for the erasure encoding hot path:
1. Erasure::clone() no longer generates Uuid::new_v4() per clone.
The _id field is unused in the hot path; reusing the original ID
eliminates a CSPRNG call per block encode (100 calls for a 100MB
object with 1MB blocks).
2. Default RUSTFS_ERASURE_ENCODE_MAX_INFLIGHT_BYTES raised from 8MB
to 32MB. This increases the encode pipeline depth from ~5 to ~20
blocks, allowing more read-ahead between the encoder and disk
writer stages. The per-request memory bound is still controlled
by the 8-block hard cap and the env var override.
3. Added encode_data_owned() utility method for zero-copy encoding
when the caller already owns a heap buffer (Vec<u8> → BytesMut
via Bytes::try_into_mut). Not used in the hot path yet but
available for future callers.
All 1157 ecstore tests pass. Criterion micro-benchmarks show no
regression (< 2% variance). Single-machine warp E2E tests were
inconclusive due to high variance; a dedicated multi-disk test
environment is needed for reliable E2E comparison.
Ref: https://github.com/rustfs/backlog/issues/659
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
* chore: update Cargo.lock
* fix(erasure): align encode inflight cap and tests
---------
Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>
* fix(ecstore): remove dead _buf field from Erasure struct
_buf was allocated in new(), clone(), and Default but never read or written.
Each clone() was allocating block_size bytes (typically 10MB) for nothing.
- Remove _buf from struct, Default, Clone, new_with_options
- 51 erasure tests pass
* fix: remove empty line after doc comment
---------
Co-authored-by: houseme <housemecn@gmail.com>
* fix(rio): surface incomplete put bodies
Propagate incomplete PUT request bodies as IncompleteBody instead of allowing erasure encode to treat truncated input as a normal EOF.\n\n- mark premature EOFs in HardLimitReader with an explicit IncompleteBody error\n- preserve EOF error chains through read_full and map them to S3 IncompleteBody\n- stop erasure encode from swallowing UnexpectedEof on truncated input\n- add regression tests for reader, erasure encode, and API error mapping\n\nRefs: rustfs/backlog#654
* fix(s3): honor decoded length for aws chunked put
Use x-amz-decoded-content-length for aws-chunked PutObject requests so trailer-checksum uploads are sized against the decoded payload instead of the wire-encoded content-length.\n\n- prefer decoded content length for aws-chunked put bodies\n- add a regression test covering the size selection logic\n- keeps the incomplete body fix working for truly truncated uploads while restoring checksum trailer compatibility\n\nRefs: rustfs/backlog#654
* fix(io): follow up review comments on incompletebody handling
Address PR review feedback by restoring read_full's existing EOF contract, adding a dedicated read_full_or_eof helper for erasure encoding, covering nested incomplete-body error chains, and documenting plus hardening aws-chunked size selection.\n\n- keep read_full returning early EOF on empty reads\n- use read_full_or_eof only in erasure encoding paths\n- detect aws-chunked via content-encoding or transfer-encoding\n- add nested error-chain and aws-chunked regression tests\n\nRefs: rustfs/backlog#654
* fix(rio): surface incomplete put bodies
Propagate incomplete PUT request bodies as IncompleteBody instead of allowing erasure encode to treat truncated input as a normal EOF.\n\n- mark premature EOFs in HardLimitReader with an explicit IncompleteBody error\n- preserve EOF error chains through read_full and map them to S3 IncompleteBody\n- stop erasure encode from swallowing UnexpectedEof on truncated input\n- add regression tests for reader, erasure encode, and API error mapping\n\nRefs: rustfs/backlog#654
* fix(s3): honor decoded length for aws chunked put
Use x-amz-decoded-content-length for aws-chunked PutObject requests so trailer-checksum uploads are sized against the decoded payload instead of the wire-encoded content-length.\n\n- prefer decoded content length for aws-chunked put bodies\n- add a regression test covering the size selection logic\n- keeps the incomplete body fix working for truly truncated uploads while restoring checksum trailer compatibility\n\nRefs: rustfs/backlog#654
* fix(io): follow up review comments on incompletebody handling
Address PR review feedback by restoring read_full's existing EOF contract, adding a dedicated read_full_or_eof helper for erasure encoding, covering nested incomplete-body error chains, and documenting plus hardening aws-chunked size selection.\n\n- keep read_full returning early EOF on empty reads\n- use read_full_or_eof only in erasure encoding paths\n- detect aws-chunked via content-encoding or transfer-encoding\n- add nested error-chain and aws-chunked regression tests\n\nRefs: rustfs/backlog#654
* fix(rio): reject bytes beyond hard limit
* fix(ecstore): reject zero-sized erasure blocks
* perf: reduce spawn_blocking contention in PUT path (~23% throughput gain)
Flame graph profiling identified tokio blocking pool mutex contention
as the #1 bottleneck (17.3% of CPU time). Each spawn_blocking call must
acquire parking_lot::raw_mutex to enqueue work. With 16 concurrent PUTs
× 4 disks × 3+ spawn_blocking per disk, this became a serialization point.
Optimizations applied:
- Merge make_dir_all + file write into single spawn_blocking
- Merge read_file + parse + write + rename into single spawn_blocking
for inline objects (small files)
- Optimize reliable_rename to try rename first, mkdir only on ENOENT
- Optimize remove/remove_std to try remove_file first, EISDIR fallback
- Add encode_inline_small fast path for small objects
- Parallelize bitrot writer creation with join_all
Benchmark (4KiB PUT, 4-disk EC, 16 concurrent, 8 rounds, randomized A/B):
Baseline: ~950 obj/s → Optimized: ~1173 obj/s (+23%)
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
* fix: address review comments
- Return old_data_dir for non-inline rename_data path (was incorrectly None)
- Restore delete_all cleanup of PUT temp data on failure paths
- Fix cargo fmt formatting
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
* style: apply rustfmt from stable 1.96.0
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
* fix: collapse nested if-let chains for clippy compliance
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
* fix: address Copilot review comments
- fs.rs: handle macOS EPERM from remove_file on directories
- os.rs: restore NotFound=Ok(()) semantics on first rename attempt
- local.rs: use try-rename-then-mkdir pattern for inline rename_data
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
* test: add unit tests for encode_inline_small fast path
* test: fix comment and line length in encode_inline_small tests
* fix: revert reliable_rename and write_all_internal to match original
Restore the original reliable_rename logic (check parent exists, then
rename in loop) and the original write_all_internal (make_dir_all outside
spawn_blocking). The optimization changes caused a CI-only test failure
in capacity_dirty_scope_test that could not be reproduced locally.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
* fix: update comment and fix formatting for CI
- Fix macOS/BSD comment to accurately say macOS only
- Fix encode_inline_small test formatting to match rustfmt 1.96.0
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
* fix: propagate inline rename errors
* fix: retry rename when parent missing
---------
Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>
Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
Object repair rebuilt missing data shards but left missing parity shards unrecreated. A parity-only repair could therefore complete without restoring the shard contents.
Add a repair-specific reconstruction path that regenerates parity after data shards are available, while keeping normal read decoding data-only. Also shut down repair writers after all blocks are written.
Constraint: Preserve read-path decode behavior and limit parity regeneration to repair.
Confidence: high
Scope-risk: moderate
Directive: Do not route read decoding through parity regeneration without measuring the cost.
Tested: cargo test -p rustfs-ecstore decode_data_and_parity -- --nocapture
Tested: cargo test -p rustfs-ecstore heal_reconstructs_missing_parity_shard -- --nocapture
Tested: cargo test -p rustfs-ecstore erasure_coding -- --nocapture
Tested: cargo test -p rustfs heal_object_marks_missing_shard_disk_dirty_for_capacity_manager -- --nocapture
Tested: cargo test -p rustfs-heal -- --nocapture
Tested: cargo clippy -p rustfs-ecstore --all-targets -- -D warnings
Tested: cargo fmt --all --check
Tested: make pre-commit
Not-tested: Live multi-node disk replacement outside local test harness
* feat(append): implement object append operations with state tracking
Signed-off-by: junxiang Mu <1948535941@qq.com>
* chore: rebase
Signed-off-by: junxiang Mu <1948535941@qq.com>
---------
Signed-off-by: junxiang Mu <1948535941@qq.com>
* Refactor: reimplement lock
Signed-off-by: junxiang Mu <1948535941@qq.com>
* Fix: fix test case failed
Signed-off-by: junxiang Mu <1948535941@qq.com>
* Improve: lock pref
Signed-off-by: junxiang Mu <1948535941@qq.com>
* fix(lock): Fix resource cleanup issue when batch lock acquisition fails
Ensure that the locks already acquired are properly released when batch lock acquisition fails to avoid memory leaks
Improve the lock protection mechanism to prevent double release issues
Add complete Apache license declarations to all files
Signed-off-by: junxiang Mu <1948535941@qq.com>
---------
Signed-off-by: junxiang Mu <1948535941@qq.com>
This commit introduces a significant reorganization of the project structure to improve maintainability and clarity.
Key changes include:
- Adjusted the directory layout for a more logical module organization.
- Removed unused crate dependencies, reducing the overall project size and potentially speeding up build times.
- Updated import paths and configuration files to reflect the structural changes.
houseme