Commit Graph

3782 Commits

Author SHA1 Message Date
houseme e2aa4f703e fix 2026-06-28 10:23:22 +08:00
houseme 9d5a2103c3 Merge branch 'main' of github.com:rustfs/rustfs into houseme/get-small-file-optimization
* 'main' of github.com:rustfs/rustfs:
  fix: correct misleading zero-copy/direct-io docs and internal naming (#733 Phase 1) (#3976)
  ci: remove --no-default-features from protocol test matrix (#3980)
  revert: restore #![allow(dead_code)] - CI clippy -D warnings conflict (#3979)
2026-06-28 09:46:53 +08:00
Zhengchao An 7238a937a9 fix: correct misleading zero-copy/direct-io docs and internal naming (#733 Phase 1) (#3976) 2026-06-28 09:12:49 +08:00
Zhengchao An 3c6dc2a633 ci: remove --no-default-features from protocol test matrix (#3980) 2026-06-28 09:12:23 +08:00
Zhengchao An e1272f2aba revert: restore #![allow(dead_code)] - CI clippy -D warnings conflict (#3979)
revert: restore #![allow(dead_code)] - clippy -D warnings treats warn as error

The #742 PR changed #![allow(dead_code)] to #![warn(dead_code)], but
CI runs clippy with -D warnings which turns warnings into errors.
This caused CI failures across multiple PRs.

Reverting to #![allow(dead_code)] until the dead code is actually
cleaned up. The 189 warnings in ecstore should be fixed incrementally
by deleting dead code and adding item-level allows, not by changing
the crate-level policy.
2026-06-28 08:32:34 +08:00
houseme 67d5620c22 Merge branch 'main' of github.com:rustfs/rustfs into houseme/get-small-file-optimization
* 'main' of github.com:rustfs/rustfs:
  fix(data-usage): refresh versioned usage state (#3969)
  ci: add protocol feature test matrix (swift, sftp, no-default) (#736) (#3975)
  chore: replace blanket #![allow(dead_code)] with #![warn(dead_code)] (#742) (#3974)
2026-06-28 08:18:46 +08:00
Henry Guo 1e303e5be0 fix(data-usage): refresh versioned usage state (#3969)
fix(data-usage): refresh versioned usage from authoritative state

Co-authored-by: Henry Guo <marshawcoco@users.noreply.github.com>
Co-authored-by: houseme <housemecn@gmail.com>
2026-06-28 07:58:07 +08:00
houseme 2c493fb5fd refactor: translate Chinese comments to English
Translate all Chinese comments to English in modified files:
- rustfs/src/storage/ecfs_extend.rs
- rustfs/src/app/bucket_usecase.rs

Co-Authored-By: heihutu <heihutu@gmail.com>
2026-06-28 07:53:34 +08:00
Zhengchao An 129ad2296b ci: add protocol feature test matrix (swift, sftp, no-default) (#736) (#3975) 2026-06-28 07:51:15 +08:00
Zhengchao An 113058af54 chore: replace blanket #![allow(dead_code)] with #![warn(dead_code)] (#742) (#3974) 2026-06-28 07:50:51 +08:00
houseme 096fadcb31 feat(get): SF02 - inline data fast path
Add fast path for small inline objects that bypasses duplex pipe,
tokio::spawn, and bitrot reader creation when data is already in memory.

Changes:
- Add inline data detection before codec streaming gate
- Direct in-memory erasure decode for inline objects <= 128KB
- Add GET_OBJECT_PATH_INLINE_DIRECT metric path
- Skip duplex pipe and background task for inline data

Conditions for fast path:
- Single part object
- Inline data available
- Size <= 128KB
- Not encrypted/compressed/remote
- No range request

Expected impact: 2-3x improvement for small file GET latency.

Closes rustfs/backlog#767

Co-Authored-By: heihutu <heihutu@gmail.com>
2026-06-28 07:48:17 +08:00
houseme 46e28cfac6 refactor(get): SF01 - use moka instead of dashmap for bucket cache
Replace OnceLock + RwLock + HashMap with moka::sync::Cache for bucket
validation cache. moka provides built-in TTL support and is already
available in the workspace.

Changes:
- Add moka dependency to rustfs crate
- Replace manual TTL management with moka's time_to_live
- Simplify cache operations

Closes rustfs/backlog#766

Co-Authored-By: heihutu <heihutu@gmail.com>
2026-06-28 07:40:38 +08:00
houseme 0bf32ab11a feat(get): SF07 - conditional metrics recording
Gate hot path metrics behind get_stage_metrics_enabled() to reduce
overhead when metrics are not needed.

Changes:
- Conditional record_zero_copy_read
- Conditional manager.record_disk_operation
- Conditional manager.record_access
- Conditional manager.record_transfer

Expected impact: 20-50us reduction per GET request.

Closes rustfs/backlog#772

Co-Authored-By: heihutu <heihutu@gmail.com>
2026-06-28 07:31:01 +08:00
houseme ce43a2189d feat(get): SF06 - conditional lifecycle check
Only call resolve_put_object_expiration when the object has an
x-amz-expiration metadata marker. This avoids unnecessary lifecycle
configuration reads on every GET request.

Expected impact: 50-100us reduction per GET request.

Closes rustfs/backlog#771

Co-Authored-By: heihutu <heihutu@gmail.com>
2026-06-28 07:29:40 +08:00
houseme c2acb9aeb6 feat(get): SF04 - remove unnecessary tokio::spawn in metadata fanout
Replace tokio::spawn with direct async future in read_all_fileinfo_full_wait.
join_all already provides concurrency, so tokio::spawn adds unnecessary
task creation and scheduling overhead.

Changes:
- Remove tokio::spawn from metadata fanout futures
- Update result handling for direct future results

Expected impact: 16-32us reduction per GET request.

Closes rustfs/backlog#769

Co-Authored-By: heihutu <heihutu@gmail.com>
2026-06-28 07:28:37 +08:00
houseme 295178df80 feat(get): SF03 - metadata cache TTL increase
Increase metadata cache TTL from 250ms to 2s and capacity from 1024
to 4096 entries.

Changes:
- GET_OBJECT_METADATA_CACHE_TTL: 250ms -> 2s
- GET_OBJECT_METADATA_CACHE_MAX_ENTRIES: 1024 -> 4096

All mutation paths already call invalidate_get_object_metadata_cache,
so the longer TTL is safe.

Expected impact: 10-50x improvement for hot objects.

Closes rustfs/backlog#768

Co-Authored-By: heihutu <heihutu@gmail.com>
2026-06-28 07:25:15 +08:00
houseme 6183775412 feat(get): SF01 - bucket validation cache
Add 5s TTL cache for bucket validation to avoid repeated stat_volume()
calls on every GET request.

Changes:
- Add BUCKET_VALIDATED_CACHE (OnceLock + RwLock + HashMap)
- Add invalidate_bucket_validation_cache() for cache invalidation
- Add invalidate_all_bucket_validation_cache() for bulk invalidation
- Update get_validated_store() to use cache
- Add cache invalidation in execute_delete_bucket()

Expected impact: 3-5x improvement for small file GET latency.

Closes rustfs/backlog#766

Co-Authored-By: heihutu <heihutu@gmail.com>
2026-06-28 07:23:36 +08:00
houseme 27468ebfa9 feat(get): consolidate GET performance optimization (#3972)
* feat(get): consolidate GET performance optimization

Consolidated implementation of all GET performance optimizations into
a single, well-organized commit replacing the previous patch-on-patch
approach.

## Changes

### Configuration (set_disk/mod.rs)
- Consolidated all GET optimization flags into a single organized section
- Enabled by default: codec streaming, metadata early-stop, page cache reclaim
- Added codec streaming multipart flag (default: disabled)
- Added version-aware early-stop flag (default: disabled)
- Added adaptive duplex buffer sizing based on object size
- All flags use OnceLock caching with rollout percentage support

### Metadata Early-Stop (set_disk/read.rs)
- Delete marker early-stop when quorum agrees
- Version-aware early-stop for versioned GET requests
- MetadataQuorumAccumulator enhanced with:
  - delete_marker_votes tracking
  - requested_version_id and matching_version_votes tracking
  - version_early_stop_decision() method
- 6 new tests for version early-stop scenarios

### Codec Streaming (erasure/coding/decode_reader.rs)
- DualInFlight (2-stripe lookahead) enabled by default

### Decode Pipeline (erasure/coding/decode.rs)
- Stripe prefetch count configuration
- Bitrot-decode overlap configuration

### Disk Layer (disk/local.rs)
- O_DIRECT read configuration constants (preparation)

### Metrics (io-metrics/lib.rs)
- BytesPool acquisition/return metrics
- Metadata phase duration with early-stop label
- Total duration with reader_path label

### Diagnostics (diagnostics/)
- Early-stop reason constants
- Pool tier/outcome label constants

### Observability (.docker/observability/)
- 3 Grafana dashboards for GET optimization monitoring
- Prometheus alert rules (6 alerts: 3 critical, 3 warning)
- Updated README.md and README_ZH.md with usage docs

### Config (config/src/constants/runtime.rs)
- Page cache reclaim read enabled by default

## Environment Variables

| Variable | Default | Description |
|----------|---------|-------------|
| RUSTFS_GET_CODEC_STREAMING_ENABLE | true | Codec streaming base flag |
| RUSTFS_GET_CODEC_STREAMING_ROLLOUT_PCT | 100 | Codec streaming rollout % |
| RUSTFS_GET_CODEC_STREAMING_MULTIPART_ENABLE | false | Multipart codec streaming |
| RUSTFS_GET_METADATA_EARLY_STOP_ENABLE | true | Early-stop base flag |
| RUSTFS_GET_METADATA_EARLY_STOP_ROLLOUT_PCT | 100 | Early-stop rollout % |
| RUSTFS_GET_METADATA_VERSION_EARLY_STOP_ENABLE | false | Version-aware early-stop |
| RUSTFS_OBJECT_FILE_CACHE_RECLAIM_READ_ENABLE | true | Page cache reclaim |
| RUSTFS_OBJECT_DIRECT_IO_READ_ENABLE | false | O_DIRECT (preparation) |
| RUSTFS_GET_DECODE_STRIPE_PREFETCH_COUNT | 1 | Stripe prefetch |
| RUSTFS_GET_BITROT_DECODE_OVERLAP_ENABLE | false | Bitrot-decode overlap |
| RUSTFS_GET_CODEC_STREAMING_MAX_INFLIGHT | 2 | DualInFlight stripes |

## Rollback

All optimizations can be disabled via environment variables:
RUSTFS_GET_CODEC_STREAMING_ENABLE=false
RUSTFS_GET_METADATA_EARLY_STOP_ENABLE=false
RUSTFS_OBJECT_FILE_CACHE_RECLAIM_READ_ENABLE=false

Co-Authored-By: heihutu <heihutu@gmail.com>

* test(get): add stress test scripts for GET optimization validation

- quick-validate-get-optimization.sh: Quick 5-minute validation
- stress-test-get-optimization.sh: Full 30+ minute stress test
- README-stress-test.md: Usage documentation

Co-Authored-By: heihutu <heihutu@gmail.com>

* test(ecstore): align file cache reclaim defaults

* chore(deps): update redis and erasure codec

* test(ecstore): align decode fill policy default

* test(ecstore): align metadata early-stop default

* fix(ecstore): keep metadata early stop opt-in

---------

Co-authored-by: heihutu <heihutu@gmail.com>
2026-06-28 07:14:07 +08:00
Zhengchao An 512418cda9 fix(ecstore): replace unbounded metadata cache with moka (#743) (#3970)
fix(ecstore): replace unbounded metadata cache with moka

Replace the manual Arc<RwLock<HashMap>> metadata cache with
moka::future::Cache, which provides:
- Built-in LRU eviction when max_capacity is reached
- Automatic TTL expiry via time_to_live (250ms)
- Lock-free concurrent reads
- Non-blocking invalidation

Fixes the memory leak risk from unbounded HashMap and the
all-or-nothing eviction logic that cleared all entries at once.

Closes #743

Co-authored-by: houseme <housemecn@gmail.com>
2026-06-28 03:01:32 +08:00
houseme 175566f037 docs(get): record default switch readiness (#3967)
* docs(get): record default switch readiness

* chore(docs): keep pr35 evaluation note local

* refactor(bench): trim pr35 readiness python
2026-06-28 01:12:44 +08:00
Zhengchao An 7ae9697d42 docs: close final architecture audit gaps (#3966) 2026-06-28 00:07:42 +08:00
Zhengchao An 79234c030d docs: close architecture migration validation (#3965) 2026-06-27 23:42:51 +08:00
Zhengchao An 82bbef0b60 test: cover runtime and repair preservation (#3964) 2026-06-27 23:34:59 +08:00
houseme bf03ff2869 feat(get): add limited opt-in rollout gates (#3963)
* feat(bench): harden cooled get ab harness

* feat(get): add limited opt-in rollout gates

* fix(get): tighten rollout gate fallbacks
2026-06-27 23:13:02 +08:00
Zhengchao An 66ad138505 docs: close phase 7 global split plan (#3962) 2026-06-27 22:25:16 +08:00
houseme 47d05a1d6a feat(bench): harden cooled get ab harness (#3960) 2026-06-27 22:23:09 +08:00
Zhengchao An c7dc3d7974 refactor: move runtime fallback defaults to owners (#3961) 2026-06-27 22:21:09 +08:00
houseme 20f56af09c feat(get): tune output response handoff (#3956) 2026-06-27 21:46:38 +08:00
Zhengchao An 68d5d1d41d refactor: isolate specialized runtime fallbacks (#3958) 2026-06-27 21:35:47 +08:00
Zhengchao An 672f6e9ea9 refactor: remove scalar runtime fallbacks (#3957) 2026-06-27 20:45:13 +08:00
Zhengchao An 243a20b14e refactor: remove service resolver fallbacks (#3955) 2026-06-27 19:35:43 +08:00
Zhengchao An 4732f4ee2d refactor: expose runtime fallback boundaries (#3954) 2026-06-27 18:57:51 +08:00
Zhengchao An cdebdeca61 refactor: clean app context fallback signatures (#3953) 2026-06-27 18:30:06 +08:00
Zhengchao An d66391636b refactor: remove optional runtime handle fallbacks (#3952) 2026-06-27 18:07:09 +08:00
Zhengchao An 430aa8e8cb refactor: remove notification config fallbacks (#3951) 2026-06-27 17:43:05 +08:00
Zhengchao An ab9e98a9ca refactor: align core runtime facade helpers (#3948) 2026-06-27 17:14:25 +08:00
houseme de86025f2c feat(get): overlap read verify decode (#3945) 2026-06-27 15:14:44 +08:00
Zhengchao An dff0e467f4 refactor: align app runtime facade helpers (#3947) 2026-06-27 15:14:29 +08:00
Zhengchao An 7979ecb545 refactor: align storage runtime facade helpers (#3946) 2026-06-27 14:55:37 +08:00
Zhengchao An 261e16a446 refactor: route admin runtime sources through current helpers (#3944) 2026-06-27 14:19:18 +08:00
Zhengchao An cc41a50efe refactor: route admin runtime consumers through app context (#3943) 2026-06-27 13:38:21 +08:00
houseme 58b76a3d45 feat(get): add codec engine ab matrix (#3940)
* upgrade version

* feat(get): add codec engine ab matrix

* chore(get): drop unrelated dependency drift

* upgrade version

* upgrade version

* fix cargo deny
2026-06-27 13:27:16 +08:00
Zhengchao An 996e58fd9a refactor: route admin runtime config through app context (#3942) 2026-06-27 13:10:00 +08:00
Zhengchao An 1b3dea012e refactor: route ecstore runtime globals through facade (#3941) 2026-06-27 12:27:03 +08:00
Zhengchao An d3f1ff36af docs: record global state cleanup plan (#3939) 2026-06-27 12:04:59 +08:00
Zhengchao An fe9c0daf0f docs: add architecture readiness matrix (#3938) 2026-06-27 11:23:07 +08:00
Zhengchao An e1a4b9e0b6 refactor: batch cluster lock and health readiness (#3936) 2026-06-27 10:51:06 +08:00
GatewayJ 675597ec16 fix(ecstore): handle stalled recovery reads and listings (#3790)
* fix(ecstore): handle stalled recovery reads and listings

* fix(rio): start HTTP stall timeout on read

* fix(ecstore): handle stalled reads and partial lists

* fix(ecstore): retire stalled shards and list errors

* fix(ecstore): preserve list merge lookahead entries

* fix(ecstore): bound zero-copy shard reads

* fix(ecstore): hedge stalled shard reads

* fix(ecstore): retire abandoned shard reads

* fix(ecstore): include part identity in metadata quorum

* fix(ecstore): validate heal shard sources

* fix(ecstore): verify reconstructed read shards

* chore(ecstore): log slow object read stages

* fix(heal): throttle auto heal during recovery

* fix(scanner): yield to foreground reads

* fix(scanner): track streaming object reads

* fix(ecstore): avoid false read heal fanout

* fix(ecstore): verify codec streaming reconstruction sources

* fix(ecstore): preserve quorum progress on slow shards

* fix(storage): restore read timeout facade

* fix(ecstore): retain fallback readers after quorum

* chore: allow decode helper argument lists

---------

Co-authored-by: overtrue <anzhengchao@gmail.com>
2026-06-27 10:21:09 +08:00
Zhengchao An 3fb4dcd52e refactor: route cluster control plane readiness (#3935) 2026-06-27 09:47:30 +08:00
Zhengchao An 0a5b1b1b3a refactor: consolidate ecstore owner module layout (#3934)
* refactor: shrink ecstore root owner facades

* refactor: remove ecstore core store root shims

* refactor: move ecstore erasure owner modules

* refactor: remove ecstore root rpc facade

* refactor: move ecstore services domain modules
2026-06-27 09:03:20 +08:00