f3a7a4b0da
chore(deps): localize workspace dependency features ( #4888 )
...
Move workspace-level dependency feature lists into the member crates that consume each dependency while keeping required default-features flags at the workspace root.
Also refresh starshard to 2.2.2 via cargo update and cargo upgrade --exclude ratelimit.
Co-authored-by: heihutu <heihutu@gmail.com >
2026-07-16 03:55:27 +00:00
05833063c7
refactor(concurrency): remove zero-caller facade modules, fix feature build ( #4530 )
...
refactor(concurrency): remove zero-caller facade modules and fix no-default-features build (backlog#1025)
The audit in rustfs/backlog#1010 (consistent with #805 ) established that most of crates/concurrency was a decorative facade with zero production callers; the real runtime concurrency control lives in rustfs/src/storage/*. This deletes the dead facades and keeps only what the workspace actually consumes.
Deleted (zero callers verified by workspace-wide grep):
- manager.rs: ConcurrencyManager, lifecycle start/stop, misleading 'started' lifecycle logs
- config.rs: ConcurrencyConfig, ConcurrencyFeatures, from_env
- timeout.rs: TimeoutManager, TimeoutGuard, TimeoutManagerPolicy
- lock.rs: LockManager, LockScopeGuard, OptimizedLockGuard
- scheduler.rs: SchedulerManager, SchedulerPolicy, IoStrategy
- deadlock.rs facade: DeadlockManager, RequestTracker
- backpressure.rs facade: BackpressureManager, BackpressurePipe
- the prelude module, unused io-core re-exports, and all feature flags
Kept (real callers in ecstore/heal/rustfs):
- workload.rs admission contract types (unchanged)
- workers.rs Workers pool (unchanged, retained per #4498 )
- GetObjectQueueSnapshot (moved from manager.rs to new queue.rs)
- PipeBackpressurePolicy (used by rustfs/src/storage/backpressure.rs)
- DeadlockMonitorPolicy (used by rustfs/src/storage/deadlock_detector.rs)
- OperationProgress re-export (used by rustfs/src/storage/timeout_wrapper.rs)
Removing the feature flags fixes the previously broken cargo check -p rustfs-concurrency --no-default-features (E0432). Docs and the logging guardrail file list are updated to match.
Ref: rustfs/backlog#1025
2026-07-09 01:12:43 +08:00
e829430d89
fix(concurrency): rewrite Workers on tokio Semaphore to fix lost wakeups ( #4498 )
...
fix(concurrency): rewrite Workers on tokio Semaphore to fix lost wakeups (backlog#1023)
2026-07-09 00:31:06 +08:00
20447422cf
fix: harden io-core and concurrency boundaries against panics ( #4503 )
...
fix(io-core,concurrency): harden boundary validation and arithmetic against panics (backlog#1024)
2026-07-09 00:15:36 +08:00
e1c1d8edcb
test: expand snapshot coverage ( #4024 )
2026-06-29 07:56:37 +08:00
46775ae019
feat: harden runtime capability snapshots ( #3784 )
...
* feat(admin): expose runtime capability snapshots
* feat(runtime): refine workload admission snapshots
* test(ci): align architecture migration checks
* build(deps): bump memmap2 for RUSTSEC-2026-0186
* build(deps): refresh cargo deny lockfile
2026-06-23 18:10:49 +08:00
a6878e8fce
fix(runtime): remove startup panic fallbacks ( #3754 )
...
* fix(runtime): remove startup panic fallbacks
* test(runtime): cover buffer profile fallback safety
* test(runtime): reduce panic-style assertions
* fix(runtime): expose fallible env config setup
* test(runtime): simplify permit acquisition assertion
* test(runtime): tighten operation helper assertions
* fix(filemeta): stop panicking on invalid free version ids
* fix(init): satisfy buffer profile clippy lints
* fix(lock): harden fast lock config construction
* chore(checks): refresh layer dependency baseline
---------
Signed-off-by: houseme <housemecn@gmail.com >
2026-06-23 12:31:26 +08:00
32d7e55564
refactor: compose workload admission providers ( #3685 )
2026-06-21 13:36:12 +08:00
56c3cf50ae
feat: add scheduler workload admission contracts ( #3602 )
2026-06-19 08:41:22 +08:00
9059a9c68d
refactor(logging): standardize concurrency and trusted proxy events ( #3417 )
...
* refactor(logging): standardize concurrency and proxy events
* chore(logging): extend guardrails for concurrency and proxies
* feat(skill): add rustfs logging governance skill
2026-06-14 01:00:26 +08:00
375482a4b6
refactor: converge storage io hot paths ( #3029 )
...
* refactor(issue-633): clarify layered io control policies
* refactor(issue-633): consolidate timeout and deadlock layers
* refactor(issue-633): align storage backpressure metadata
* refactor(issue-633): unify storage backpressure transitions
* refactor(issue-633): simplify watermark transition API
* test(issue-633): add storage backpressure transition test
* refactor(issue-633): align storage pipe meta shape
* refactor(issue-633): enrich storage monitor metadata
* refactor(issue-633): finalize storage backpressure convergence
* refactor(issue-633): complete scheduler layer convergence
* refactor(issue-633): reduce concurrency facade config duplication
* refactor(issue-633): migrate storage callsites to final policy names
* chore(issue-633): apply final pre-commit normalization
* refactor(issue-633): unify timeout wrapper dynamic size path
* refactor(issue-633): make concurrency policies copyable
* refactor(issue-633): converge storage io hot paths
* fix(issue-633): honor storage timeout min bound
* fix(storage): avoid timeout calc panic on huge sizes
* refactor(storage): consolidate timeout checks and test attrs
* fix(storage): harden io scheduler core config mapping
* refactor(storage): eliminate patch-on-patch patterns and dead code
- Remove trivial accessor methods on ConcurrencyConfig that just return pub fields
- Remove dead BackpressureEvent/BackpressureEventType types from concurrency crate
- Fix io_schedule test using wrong constructor (from_core_config -> from_scheduler_config)
- Update manager.rs to use config fields directly instead of removed accessors
* fix: adopt review feedback for config guards
* test: remove needless struct update defaults
* fix: harden timeout policy and preserve api alias
2026-05-20 12:00:23 +00:00
73bde843d6
refactor(s3): consolidate semantic boundaries and remove s3-common ( #3012 )
...
* refactor(common): introduce rustfs-data-usage core crate
* refactor(concurrency): migrate workers crate into concurrency
* refactor(crypto): migrate appauth token APIs into crypto
* fix docs urls
* remove unused crate
* refactor(data-usage): switch consumers to rustfs-data-usage
* chore(fmt): apply cargo fmt and lockfile sync
* refactor(common): remove data_usage compatibility re-export
* refactor(capacity): move capacity_scope to object-capacity
* refactor(io-metrics): relocate internode metrics from common
* refactor(common): decouple scanner report from madmin
* chore(fmt): normalize import ordering after pre-commit
* refactor(s3): split s3 types and ops crates
* refactor(s3): centralize event version and safe parsing
* refactor(s3): add op-event compatibility guardrails
* refactor(s3): add runtime op-event mismatch observability
* refactor(s3): extract delete event mapping helper
* refactor(s3): extract put event mapping helper
* refactor(s3): consolidate remaining event semantic helpers
* refactor(s3): add op-event coverage checks and observability alerts
* refactor(s3-ops): consolidate op-event semantic mapping
* refactor(scanner): remove last_minute wrapper module
* refactor(scanner): consolidate duplicated data usage models
2026-05-19 12:50:25 +00:00
f77ccd5b23
chore: move mcp crate to standalone repository ( #2578 )
2026-04-17 12:42:26 +00:00
79ffecbf14
refactor(storage): remove object cache plumbing ( #2422 )
...
Co-authored-by: heihutu <heihutu@gmail.com >
2026-04-07 22:00:53 +08:00
7172e151de
fix: address correctness, safety, and concurrency issues ( #2327 )
...
Co-authored-by: heihutu <heihutu@gmail.com >
Co-authored-by: houseme <housemecn@gmail.com >
2026-03-30 00:30:57 +08:00
houseme