mirror of
https://github.com/seaweedfs/seaweedfs.git
synced 2026-09-08 15:41:15 +02:00
056cf6fa5bc809bc92aaeb06e810f2de14047197
100
Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
 Chris Lu
|
056cf6fa5b |
docker: default published images to seaweed user (#8819)
* ci: add Trivy CVE scan to container release workflow
* docker: default published images to seaweed user
* Revert "ci: add Trivy CVE scan to container release workflow"
This reverts commit
|
||
|
Chris Lu
|
0884acd70c |
ci: add S3 mutation regression coverage (#8804)
* test/s3: stabilize distributed lock regression * ci: add S3 mutation regression workflow * test: fix delete regression readiness probe * test: address mutation regression review comments |
||
|
Chris LuandCopilot
|
297cdef1a3 |
s3api: accept all supported lifecycle rule types (#8813)
* s3api: accept NoncurrentVersionExpiration, AbortIncompleteMultipartUpload, Expiration.Date Update PutBucketLifecycleConfigurationHandler to accept all newly-supported lifecycle rule types. Only Transition and NoncurrentVersionTransition are still rejected (require storage class tier infrastructure). Changes: - Remove ErrNotImplemented for Expiration.Date (handled by worker at scan time) - Only reject rules with Transition.set or NoncurrentVersionTransition.set - Extract prefix from Filter.And when present - Add comment explaining that non-Expiration.Days rules are evaluated by the lifecycle worker from stored lifecycle XML, not via filer.conf TTL The lifecycle XML is already stored verbatim in bucket metadata, so new rule types are preserved on Get even without explicit handler support. Filer.conf TTL entries are only created for Expiration.Days (fast path). * s3api: skip TTL fast path for rules with tag or size filters Rules with tag or size constraints (Filter.Tag, Filter.And with tags or size bounds, Filter.ObjectSizeGreaterThan/LessThan) must not be lowered to filer.conf TTL entries, because TTL applies unconditionally to all objects under the prefix. These rules are evaluated at scan time by the lifecycle worker which checks each object's tags and size. Only simple Expiration.Days rules with prefix-only filters use the TTL fast path (RocksDB compaction filter). --------- Co-authored-by: Copilot <copilot@github.com> |
||
|
Chris Lu
|
55318fe5ec | lifecycle worker: add integration tests with in-memory filer (#8818) | ||
|
Chris LuandCopilot
|
782ab84f95 |
lifecycle worker: drive MPU abort from lifecycle rules (#8812)
* lifecycle worker: drive MPU abort from lifecycle rules Update the multipart upload abort phase to read AbortIncompleteMultipartUpload.DaysAfterInitiation from the parsed lifecycle rules. Falls back to the worker config abort_mpu_days when no lifecycle XML rule specifies the value. This means per-bucket MPU abort thresholds are now respected when set via PutBucketLifecycleConfiguration, instead of using a single global worker config value for all buckets. * lifecycle worker: only use config AbortMPUDays when no lifecycle XML exists When a bucket has lifecycle XML (useRuleEval=true) but no AbortIncompleteMultipartUpload rule, mpuAbortDays should be 0 (no abort), not the worker config default. The config fallback should only apply to buckets without lifecycle XML. * lifecycle worker: only skip .uploads at bucket root * lifecycle worker: use per-upload rule evaluation for MPU abort Replace the single bucket-wide mpuAbortDays with per-upload evaluation using s3lifecycle.EvaluateMPUAbort, which respects each rule's prefix filter and DaysAfterInitiation threshold. Previously the code took the first enabled abort rule's days value and applied it to all uploads, ignoring prefix scoping and multiple rules with different thresholds. Config fallback (abort_mpu_days) now only applies when lifecycle XML is truly absent (xmlPresent=false), not when XML exists but has no abort rules. Also fix EvaluateMPUAbort to use expectedExpiryTime for midnight-UTC semantics matching other lifecycle cutoffs. --------- Co-authored-by: Copilot <copilot@github.com> |
||
|
Chris LuandCopilot
|
f52a3c87ce |
lifecycle worker: fix ExpiredObjectDeleteMarker to match AWS semantics (#8811)
* lifecycle worker: add NoncurrentVersionExpiration support Add version-aware scanning to the rule-based execution path. When the walker encounters a .versions directory, processVersionsDirectory(): - Lists all version entries (v_<versionId>) - Sorts by version timestamp (newest first) - Walks non-current versions with ShouldExpireNoncurrentVersion() which handles both NoncurrentDays and NewerNoncurrentVersions - Extracts successor time from version IDs (both old/new format) - Skips delete markers in noncurrent version counting - Falls back to entry Mtime when version ID timestamp is unavailable Helper functions: - sortVersionsByTimestamp: insertion sort by version ID timestamp - getEntryVersionTimestamp: extracts timestamp with Mtime fallback * lifecycle worker: address review feedback for noncurrent versions - Use sentinel errLimitReached in versions directory handler - Set NoncurrentIndex on ObjectInfo for proper NewerNoncurrentVersions evaluation * lifecycle worker: fail closed on XML parse error, guard zero Mtime - Fail closed when lifecycle XML exists but fails to parse, instead of falling back to TTL which could apply broader rules - Guard Mtime > 0 before using time.Unix(mtime, 0) to avoid mapping unset Mtime to 1970, which would misorder versions and cause premature expiration * lifecycle worker: count delete markers toward NoncurrentIndex Noncurrent delete markers should count toward the NewerNoncurrentVersions retention threshold so data versions get the correct position index. Previously, skipping delete markers without incrementing the index could retain too many versions after delete/recreate cycles. * lifecycle worker: fix version ordering, error propagation, and fail-closed scope 1. Use full version ID comparison (CompareVersionIds) for sorting .versions entries, not just decoded timestamps. Two versions with the same timestamp prefix but different random suffixes were previously misordered, potentially treating the newest version as noncurrent and deleting it. 2. Propagate .versions listing failures to the caller instead of swallowing them with (nil, 0). Transient filer errors on a .versions directory now surface in the job result. 3. Narrow the fail-closed path to only malformed lifecycle XML (errMalformedLifecycleXML). Transient filer LookupEntry errors now fall back to TTL with a warning, matching the original intent of "fail closed on bad config, not on network blips." * lifecycle worker: only skip .uploads at bucket root * lifecycle worker: sort.Slice, mixed-format test, XML presence tracking - Replace manual insertion sort with sort.Slice in sortVersionsByVersionId - Add TestCompareVersionIdsMixedFormats covering old/new format ordering - Distinguish "no lifecycle XML" (nil) from "XML present but no effective rules" (non-nil empty slice) so buckets with all-disabled rules don't incorrectly fall back to filer.conf TTL expiration * lifecycle worker: guard nil Attributes, use TrimSuffix in test - Guard entry.Attributes != nil before accessing GetFileSize() and Mtime in both listExpiredObjectsByRules and processVersionsDirectory - Use strings.TrimPrefix/TrimSuffix in TestVersionsDirectoryNaming to match the production code pattern * lifecycle worker: skip TTL scan when XML present, fix test assertions - When lifecycle XML is present but has no effective rules, skip object scanning entirely instead of falling back to TTL path - Test sort output against concrete expected names instead of re-using the same comparator as the sort itself * lifecycle worker: fix ExpiredObjectDeleteMarker to match AWS semantics Rewrite cleanupDeleteMarkers() to only remove delete markers that are the sole remaining version of an object. Previously, delete markers were removed unconditionally which could resurface older versions in versioned buckets. New algorithm: 1. Walk bucket tree looking for .versions directories 2. Check ExtLatestVersionIsDeleteMarker from directory metadata 3. Count versions in the .versions directory 4. Only remove if count == 1 (delete marker is sole version) 5. Require an ExpiredObjectDeleteMarker=true rule (when lifecycle XML rules are present) 6. Remove the empty .versions directory after cleanup This phase runs after NoncurrentVersionExpiration so version counts are accurate. * lifecycle worker: respect prefix filter in ExpiredObjectDeleteMarker rules Previously hasDeleteMarkerRule was a bucket-wide boolean that ignored rule prefixes. A prefix-scoped rule like "logs/" would incorrectly clean up delete markers in all paths. Add matchesDeleteMarkerRule() that checks if a matching enabled ExpiredObjectDeleteMarker rule exists for the specific object key, respecting the rule's prefix filter. Falls back to legacy behavior (allow cleanup) when no lifecycle XML rules are provided. * lifecycle worker: only skip .uploads at bucket root Check dir == bucketPath before skipping directories named .uploads. Previously a user-created directory like data/.uploads/ at any depth would be incorrectly skipped during lifecycle scanning. * lifecycle worker: fix delete marker cleanup with XML-present empty rules 1. matchesDeleteMarkerRule now uses nil check (not len==0) for legacy fallback. A non-nil empty slice means lifecycle XML was present but had no ExpiredObjectDeleteMarker rules, so cleanup is blocked. Previously, an empty slice triggered the legacy true path. 2. Use per-directory removedHere flag instead of cumulative cleaned counter when deciding to remove .versions directories. Previously, after the first successful cleanup anywhere in the bucket, every subsequent .versions directory would be removed even if its own delete marker was not actually deleted. * lifecycle worker: use full filter matching for delete marker rules matchesDeleteMarkerRule now uses s3lifecycle.MatchesFilter (exported) instead of prefix-only matching. This ensures tag and size filters on ExpiredObjectDeleteMarker rules are respected, preventing broader deletions than the configured policy intends. Add TestMatchesDeleteMarkerRule covering: nil rules (legacy), empty rules (XML present), prefix match/mismatch, disabled rules, rules without the flag, and tag-filtered rules against tagless markers. --------- Co-authored-by: Copilot <copilot@github.com> |
||
|
Chris LuandCopilot
|
f6ec9941cb |
lifecycle worker: NoncurrentVersionExpiration support (#8810)
* lifecycle worker: add NoncurrentVersionExpiration support Add version-aware scanning to the rule-based execution path. When the walker encounters a .versions directory, processVersionsDirectory(): - Lists all version entries (v_<versionId>) - Sorts by version timestamp (newest first) - Walks non-current versions with ShouldExpireNoncurrentVersion() which handles both NoncurrentDays and NewerNoncurrentVersions - Extracts successor time from version IDs (both old/new format) - Skips delete markers in noncurrent version counting - Falls back to entry Mtime when version ID timestamp is unavailable Helper functions: - sortVersionsByTimestamp: insertion sort by version ID timestamp - getEntryVersionTimestamp: extracts timestamp with Mtime fallback * lifecycle worker: address review feedback for noncurrent versions - Use sentinel errLimitReached in versions directory handler - Set NoncurrentIndex on ObjectInfo for proper NewerNoncurrentVersions evaluation * lifecycle worker: fail closed on XML parse error, guard zero Mtime - Fail closed when lifecycle XML exists but fails to parse, instead of falling back to TTL which could apply broader rules - Guard Mtime > 0 before using time.Unix(mtime, 0) to avoid mapping unset Mtime to 1970, which would misorder versions and cause premature expiration * lifecycle worker: count delete markers toward NoncurrentIndex Noncurrent delete markers should count toward the NewerNoncurrentVersions retention threshold so data versions get the correct position index. Previously, skipping delete markers without incrementing the index could retain too many versions after delete/recreate cycles. * lifecycle worker: fix version ordering, error propagation, and fail-closed scope 1. Use full version ID comparison (CompareVersionIds) for sorting .versions entries, not just decoded timestamps. Two versions with the same timestamp prefix but different random suffixes were previously misordered, potentially treating the newest version as noncurrent and deleting it. 2. Propagate .versions listing failures to the caller instead of swallowing them with (nil, 0). Transient filer errors on a .versions directory now surface in the job result. 3. Narrow the fail-closed path to only malformed lifecycle XML (errMalformedLifecycleXML). Transient filer LookupEntry errors now fall back to TTL with a warning, matching the original intent of "fail closed on bad config, not on network blips." * lifecycle worker: only skip .uploads at bucket root * lifecycle worker: sort.Slice, mixed-format test, XML presence tracking - Replace manual insertion sort with sort.Slice in sortVersionsByVersionId - Add TestCompareVersionIdsMixedFormats covering old/new format ordering - Distinguish "no lifecycle XML" (nil) from "XML present but no effective rules" (non-nil empty slice) so buckets with all-disabled rules don't incorrectly fall back to filer.conf TTL expiration * lifecycle worker: guard nil Attributes, use TrimSuffix in test - Guard entry.Attributes != nil before accessing GetFileSize() and Mtime in both listExpiredObjectsByRules and processVersionsDirectory - Use strings.TrimPrefix/TrimSuffix in TestVersionsDirectoryNaming to match the production code pattern * lifecycle worker: skip TTL scan when XML present, fix test assertions - When lifecycle XML is present but has no effective rules, skip object scanning entirely instead of falling back to TTL path - Test sort output against concrete expected names instead of re-using the same comparator as the sort itself --------- Co-authored-by: Copilot <copilot@github.com> |
||
|
Chris LuandCopilot
|
9c3bc138a0 |
lifecycle worker: scan-time rule evaluation for object expiration (#8809)
* s3api: extend lifecycle XML types with NoncurrentVersionExpiration, AbortIncompleteMultipartUpload Add missing S3 lifecycle rule types to the XML data model: - NoncurrentVersionExpiration with NoncurrentDays and NewerNoncurrentVersions - NoncurrentVersionTransition with NoncurrentDays and StorageClass - AbortIncompleteMultipartUpload with DaysAfterInitiation - Filter.ObjectSizeGreaterThan and ObjectSizeLessThan - And.ObjectSizeGreaterThan and ObjectSizeLessThan - Filter.UnmarshalXML to properly parse Tag, And, and size filter elements Each new type follows the existing set-field pattern for conditional XML marshaling. No behavior changes - these types are not yet wired into handlers or the lifecycle worker. * s3lifecycle: add lifecycle rule evaluator package New package weed/s3api/s3lifecycle/ provides a pure-function lifecycle rule evaluation engine. The evaluator accepts flattened Rule structs and ObjectInfo metadata, and returns the appropriate Action. Components: - evaluator.go: Evaluate() for per-object actions with S3 priority ordering (delete marker > noncurrent version > current expiration), ShouldExpireNoncurrentVersion() with NewerNoncurrentVersions support, EvaluateMPUAbort() for multipart upload rules - filter.go: prefix, tag, and size-based filter matching - tags.go: ExtractTags() extracts S3 tags from filer Extended metadata, HasTagRules() for scan-time optimization - version_time.go: GetVersionTimestamp() extracts timestamps from SeaweedFS version IDs (both old and new format) Comprehensive test coverage: 54 tests covering all action types, filter combinations, edge cases, and version ID formats. * s3api: add UnmarshalXML for Expiration, Transition, ExpireDeleteMarker Add UnmarshalXML methods that set the internal 'set' flag during XML parsing. Previously these flags were only set programmatically, causing XML round-trip to drop elements. This ensures lifecycle configurations stored as XML survive unmarshal/marshal cycles correctly. Add comprehensive XML round-trip tests for all lifecycle rule types including NoncurrentVersionExpiration, AbortIncompleteMultipartUpload, Filter with Tag/And/size constraints, and a complete Terraform-style lifecycle configuration. * s3lifecycle: address review feedback - Fix version_time.go overflow: guard timestampPart > MaxInt64 before the inversion subtraction to prevent uint64 wrap - Make all expiry checks inclusive (!now.Before instead of now.After) so actions trigger at the exact scheduled instant - Add NoncurrentIndex to ObjectInfo so Evaluate() can properly handle NewerNoncurrentVersions via ShouldExpireNoncurrentVersion() - Add test for high-bit overflow version ID * s3lifecycle: guard ShouldExpireNoncurrentVersion against zero SuccessorModTime Add early return when obj.IsLatest or obj.SuccessorModTime.IsZero() to prevent premature expiration of versions with uninitialized successor timestamps (zero value would compute to epoch, always expired). * lifecycle worker: detect buckets with lifecycle XML, not just filer.conf TTLs Update the detection phase to check for stored lifecycle XML in bucket metadata (key: s3-bucket-lifecycle-configuration-xml) in addition to filer.conf TTL entries. A bucket is proposed for lifecycle processing if it has lifecycle XML OR filer.conf TTLs (backward compatible). New proposal parameters: - has_lifecycle_xml: whether the bucket has stored lifecycle XML - versioning_status: the bucket's versioning state (Enabled/Suspended/"") These parameters will be used by the execution phase (subsequent PR) to determine which evaluation path to use. * lifecycle worker: update detection function comment to reflect XML support * lifecycle worker: add lifecycle XML parsing and rule conversion Add rules.go with: - parseLifecycleXML() converts stored lifecycle XML to evaluator-friendly s3lifecycle.Rule structs, handling Filter.Prefix, Filter.Tag, Filter.And, size constraints, NoncurrentVersionExpiration, AbortIncompleteMultipartUpload, Expiration.Date, and ExpiredObjectDeleteMarker - loadLifecycleRulesFromBucket() reads lifecycle XML from bucket metadata - parseExpirationDate() supports RFC3339 and ISO 8601 date-only formats Comprehensive tests for all XML variants, filter types, and date formats. * lifecycle worker: add scan-time rule evaluation for object expiration Update executeLifecycleForBucket to try lifecycle XML evaluation first, falling back to TTL-only evaluation when no lifecycle XML exists. New listExpiredObjectsByRules() function: - Walks the bucket directory tree - Builds s3lifecycle.ObjectInfo from each filer entry - Calls s3lifecycle.Evaluate() to check lifecycle rules - Skips objects already handled by TTL fast path (TtlSec set) - Extracts tags only when rules use tag-based filters (optimization) - Skips .uploads and .versions directories (handled by other phases) Supports Expiration.Days, Expiration.Date, Filter.Prefix, Filter.Tag, Filter.And, and Filter.ObjectSize* in the scan-time evaluation path. Existing TTL-based path remains for backward compatibility. * lifecycle worker: address review feedback - Use sentinel error (errLimitReached) instead of string matching for scan limit detection - Fix loadLifecycleRulesFromBucket path: use bucketsPath directly as directory for LookupEntry instead of path.Dir which produced the wrong parent * lifecycle worker: fix And filter detection for size-only constraints The And branch condition only triggered when Prefix or Tags were present, missing the case where And contains only ObjectSizeGreaterThan or ObjectSizeLessThan without a prefix or tags. * lifecycle worker: address review feedback round 3 - rules.go: pass through Filter-level size constraints when Tag is present without And (Tag+size combination was dropping sizes) - execution.go: add doc comment to listExpiredObjectsByRules noting that it handles non-versioned objects only; versioned objects are handled by processVersionsDirectory - rules_test.go: add bounds checks before indexing rules[0] --------- Co-authored-by: Copilot <copilot@github.com> |
||
|
Chris LuandCopilot
|
98f545c7fa |
lifecycle worker: detect buckets via lifecycle XML metadata (#8808)
* s3api: extend lifecycle XML types with NoncurrentVersionExpiration, AbortIncompleteMultipartUpload Add missing S3 lifecycle rule types to the XML data model: - NoncurrentVersionExpiration with NoncurrentDays and NewerNoncurrentVersions - NoncurrentVersionTransition with NoncurrentDays and StorageClass - AbortIncompleteMultipartUpload with DaysAfterInitiation - Filter.ObjectSizeGreaterThan and ObjectSizeLessThan - And.ObjectSizeGreaterThan and ObjectSizeLessThan - Filter.UnmarshalXML to properly parse Tag, And, and size filter elements Each new type follows the existing set-field pattern for conditional XML marshaling. No behavior changes - these types are not yet wired into handlers or the lifecycle worker. * s3lifecycle: add lifecycle rule evaluator package New package weed/s3api/s3lifecycle/ provides a pure-function lifecycle rule evaluation engine. The evaluator accepts flattened Rule structs and ObjectInfo metadata, and returns the appropriate Action. Components: - evaluator.go: Evaluate() for per-object actions with S3 priority ordering (delete marker > noncurrent version > current expiration), ShouldExpireNoncurrentVersion() with NewerNoncurrentVersions support, EvaluateMPUAbort() for multipart upload rules - filter.go: prefix, tag, and size-based filter matching - tags.go: ExtractTags() extracts S3 tags from filer Extended metadata, HasTagRules() for scan-time optimization - version_time.go: GetVersionTimestamp() extracts timestamps from SeaweedFS version IDs (both old and new format) Comprehensive test coverage: 54 tests covering all action types, filter combinations, edge cases, and version ID formats. * s3api: add UnmarshalXML for Expiration, Transition, ExpireDeleteMarker Add UnmarshalXML methods that set the internal 'set' flag during XML parsing. Previously these flags were only set programmatically, causing XML round-trip to drop elements. This ensures lifecycle configurations stored as XML survive unmarshal/marshal cycles correctly. Add comprehensive XML round-trip tests for all lifecycle rule types including NoncurrentVersionExpiration, AbortIncompleteMultipartUpload, Filter with Tag/And/size constraints, and a complete Terraform-style lifecycle configuration. * s3lifecycle: address review feedback - Fix version_time.go overflow: guard timestampPart > MaxInt64 before the inversion subtraction to prevent uint64 wrap - Make all expiry checks inclusive (!now.Before instead of now.After) so actions trigger at the exact scheduled instant - Add NoncurrentIndex to ObjectInfo so Evaluate() can properly handle NewerNoncurrentVersions via ShouldExpireNoncurrentVersion() - Add test for high-bit overflow version ID * s3lifecycle: guard ShouldExpireNoncurrentVersion against zero SuccessorModTime Add early return when obj.IsLatest or obj.SuccessorModTime.IsZero() to prevent premature expiration of versions with uninitialized successor timestamps (zero value would compute to epoch, always expired). * lifecycle worker: detect buckets with lifecycle XML, not just filer.conf TTLs Update the detection phase to check for stored lifecycle XML in bucket metadata (key: s3-bucket-lifecycle-configuration-xml) in addition to filer.conf TTL entries. A bucket is proposed for lifecycle processing if it has lifecycle XML OR filer.conf TTLs (backward compatible). New proposal parameters: - has_lifecycle_xml: whether the bucket has stored lifecycle XML - versioning_status: the bucket's versioning state (Enabled/Suspended/"") These parameters will be used by the execution phase (subsequent PR) to determine which evaluation path to use. * lifecycle worker: update detection function comment to reflect XML support --------- Co-authored-by: Copilot <copilot@github.com> |
||
|
Chris LuandCopilot
|
54dd4f091d |
s3lifecycle: add lifecycle rule evaluator package and extend XML types (#8807)
* s3api: extend lifecycle XML types with NoncurrentVersionExpiration, AbortIncompleteMultipartUpload Add missing S3 lifecycle rule types to the XML data model: - NoncurrentVersionExpiration with NoncurrentDays and NewerNoncurrentVersions - NoncurrentVersionTransition with NoncurrentDays and StorageClass - AbortIncompleteMultipartUpload with DaysAfterInitiation - Filter.ObjectSizeGreaterThan and ObjectSizeLessThan - And.ObjectSizeGreaterThan and ObjectSizeLessThan - Filter.UnmarshalXML to properly parse Tag, And, and size filter elements Each new type follows the existing set-field pattern for conditional XML marshaling. No behavior changes - these types are not yet wired into handlers or the lifecycle worker. * s3lifecycle: add lifecycle rule evaluator package New package weed/s3api/s3lifecycle/ provides a pure-function lifecycle rule evaluation engine. The evaluator accepts flattened Rule structs and ObjectInfo metadata, and returns the appropriate Action. Components: - evaluator.go: Evaluate() for per-object actions with S3 priority ordering (delete marker > noncurrent version > current expiration), ShouldExpireNoncurrentVersion() with NewerNoncurrentVersions support, EvaluateMPUAbort() for multipart upload rules - filter.go: prefix, tag, and size-based filter matching - tags.go: ExtractTags() extracts S3 tags from filer Extended metadata, HasTagRules() for scan-time optimization - version_time.go: GetVersionTimestamp() extracts timestamps from SeaweedFS version IDs (both old and new format) Comprehensive test coverage: 54 tests covering all action types, filter combinations, edge cases, and version ID formats. * s3api: add UnmarshalXML for Expiration, Transition, ExpireDeleteMarker Add UnmarshalXML methods that set the internal 'set' flag during XML parsing. Previously these flags were only set programmatically, causing XML round-trip to drop elements. This ensures lifecycle configurations stored as XML survive unmarshal/marshal cycles correctly. Add comprehensive XML round-trip tests for all lifecycle rule types including NoncurrentVersionExpiration, AbortIncompleteMultipartUpload, Filter with Tag/And/size constraints, and a complete Terraform-style lifecycle configuration. * s3lifecycle: address review feedback - Fix version_time.go overflow: guard timestampPart > MaxInt64 before the inversion subtraction to prevent uint64 wrap - Make all expiry checks inclusive (!now.Before instead of now.After) so actions trigger at the exact scheduled instant - Add NoncurrentIndex to ObjectInfo so Evaluate() can properly handle NewerNoncurrentVersions via ShouldExpireNoncurrentVersion() - Add test for high-bit overflow version ID * s3lifecycle: guard ShouldExpireNoncurrentVersion against zero SuccessorModTime Add early return when obj.IsLatest or obj.SuccessorModTime.IsZero() to prevent premature expiration of versions with uninitialized successor timestamps (zero value would compute to epoch, always expired). --------- Co-authored-by: Copilot <copilot@github.com> |
||
|
Chris Lu
|
7d5cbfd547 |
s3: support s3:x-amz-server-side-encryption policy condition (#8806)
* s3: support s3:x-amz-server-side-encryption policy condition (#7680) - Normalize x-amz-server-side-encryption header values to canonical form (aes256 → AES256, aws:kms mixed-case → aws:kms) so StringEquals conditions work regardless of client capitalisation - Exempt UploadPart and UploadPartCopy from SSE Null conditions: these actions inherit SSE from the initial CreateMultipartUpload request and do not re-send the header, so Deny/Null("true") should not block them - Add sse_condition_test.go covering StringEquals, Null, case-insensitive normalisation, and multipart continuation action exemption * s3: address review comments on SSE condition support - Replace "inherited" sentinel in injectSSEForMultipart with "AES256" so that StringEquals/Null conditions evaluate against a meaningful value; add TODO noting that KMS multipart uploads need the actual algorithm looked up from the upload state - Rewrite TestSSECaseInsensitiveNormalization to drive normalisation through EvaluatePolicyForRequest with a real *http.Request so regressions in the production code path are caught; split into AES256 and aws:kms variants to cover both normalisation branches * s3: plumb real inherited SSE from multipart upload state into policy eval Instead of injecting a static "AES256" sentinel for UploadPart/UploadPartCopy, look up the actual SSE algorithm from the stored CreateMultipartUpload entry and pass it through the evaluation chain. Changes: - PolicyEvaluationArgs gains InheritedSSEAlgorithm string; set by the BucketPolicyEngine wrapper for multipart continuation actions - injectSSEForMultipart(conditions, inheritedSSE) now accepts the real algorithm; empty string means no SSE → Null("true") fires correctly - IsMultipartContinuationAction exported so the s3api wrapper can use it - BucketPolicyEngine gets a MultipartSSELookup callback (set by S3ApiServer) that fetches the upload entry and reads SeaweedFSSSEKMSKeyID / SeaweedFSSSES3Encryption to determine the algorithm - S3ApiServer.getMultipartSSEAlgorithm implements the lookup via getEntry - Tests updated: three multipart cases (AES256, aws:kms, no-SSE-must-deny) plus UploadPartCopy coverage |
||
|
Chris Lu
|
e3f052cd84 |
s3api: preserve lifecycle config responses for Terraform (#8805)
* s3api: preserve lifecycle configs for terraform * s3api: bound lifecycle config request bodies * s3api: make bucket config updates copy-on-write * s3api: tighten string slice cloning |
||
|
Chris Lu
|
0adb78bc6b |
s3api: make conditional mutations atomic and AWS-compatible (#8802)
* s3api: serialize conditional write finalization * s3api: add conditional delete mutation checks * s3api: enforce destination conditions for copy * s3api: revalidate multipart completion under lock * s3api: rollback failed put finalization hooks * s3api: report delete-marker version deletions * s3api: fix copy destination versioning edge cases * s3api: make versioned multipart completion idempotent * test/s3: cover conditional mutation regressions * s3api: rollback failed copy version finalization * s3api: resolve suspended delete conditions via latest entry * s3api: remove copy test null-version injection * s3api: reject out-of-order multipart completions * s3api: preserve multipart replay version metadata * s3api: surface copy destination existence errors * s3api: simplify delete condition target resolution * test/s3: make conditional delete assertions order independent * test/s3: add distributed lock gateway integration * s3api: fail closed multipart versioned completion * s3api: harden copy metadata and overwrite paths * s3api: create delete markers for suspended deletes * s3api: allow duplicate multipart completion parts |
||
|
Chris Lu
|
bf2a2d2538 |
test: preserve branch when recovering bare git repo (#8803)
* test: preserve branch when recovering bare git repo * Replaced the standalone ensureMountClone + gitRun in Phase 5 with a new resetToCommitWithRecovery function that mirrors the existing pullFromCommitWithRecovery pattern |
||
|
Chris Lu
|
f256002d0b |
fix ec.balance failing to rebalance when all nodes share all volumes (#8796)
* fix ec.balance failing to rebalance when all nodes share all volumes (#8793) Two bugs in doBalanceEcRack prevented rebalancing: 1. Sorting by freeEcSlot instead of actual shard count caused incorrect empty/full node selection when nodes have different total capacities. 2. The volume-level check skipped any volume already present on the target node. When every node has a shard of every volume (common with many EC volumes across N nodes with N shards each), no moves were possible. Fix: sort by actual shard count, and use a two-pass approach - first prefer moving shards of volumes not on the target (best diversity), then fall back to moving specific shard IDs not yet on the target. * add test simulating real cluster topology from issue #8793 Uses the actual node addresses and mixed max capacities (80 vs 33) from the reporter's 14-node cluster to verify ec.balance correctly rebalances with heterogeneous node sizes. * fix pass comments to match 0-indexed loop variable |
||
|
Chris LuandCopilot
|
c2c58419b8 |
filer.sync: send log file chunk fids to clients for direct volume server reads (#8792)
* filer.sync: send log file chunk fids to clients for direct volume server reads Instead of the server reading persisted log files from volume servers, parsing entries, and streaming them over gRPC (serial bottleneck), clients that opt in via client_supports_metadata_chunks receive log file chunk references (fids) and read directly from volume servers in parallel. New proto messages: - LogFileChunkRef: chunk fids + timestamp + filer ID for one log file - SubscribeMetadataRequest.client_supports_metadata_chunks: client opt-in - SubscribeMetadataResponse.log_file_refs: server sends refs during backlog Server changes: - CollectLogFileRefs: lists log files and returns chunk refs without any volume server I/O (metadata-only operation) - SubscribeMetadata/SubscribeLocalMetadata: when client opts in, sends refs during persisted log phase, then falls back to normal streaming for in-memory events Client changes: - ReadLogFileRefs: reads log files from volume servers, parses entries, filters by path prefix, invokes processEventFn - MetadataFollowOption.LogFileReaderFn: factory for chunk readers, enables metadata chunks when non-nil - Both filer_pb_tail.go and meta_aggregator.go recv loops accumulate refs then process them at the disk→memory transition Backward compatible: old clients don't set the flag, get existing behavior. Ref: #8771 * filer.sync: merge entries across filers in timestamp order on client side ReadLogFileRefs now groups refs by filer ID and merges entries from multiple filers using a min-heap priority queue — the same algorithm the server uses in OrderedLogVisitor + LogEntryItemPriorityQueue. This ensures events are processed in correct timestamp order even when log files from different filers have interleaved timestamps. Single-filer case takes the fast path (no heap allocation). * filer.sync: integration tests for direct-read metadata chunks Three test categories: 1. Merge correctness (TestReadLogFileRefsMergeOrder): Verifies entries from 3 filers are delivered in strict timestamp order, matching the server-side OrderedLogVisitor guarantee. 2. Path filtering (TestReadLogFileRefsPathFilter): Verifies client-side path prefix filtering works correctly. 3. Throughput comparison (TestDirectReadVsServerSideThroughput): 3 filers × 7 files × 300 events = 6300 events, 2ms per file read: server-side: 6300 events 218ms 28,873 events/sec direct-read: 6300 events 51ms 123,566 events/sec (4.3x) parallel: 6300 events 17ms 378,628 events/sec (13.1x) Direct-read eliminates gRPC send overhead per event (4.3x). Parallel per-filer reading eliminates serial file I/O (13.1x). * filer.sync: parallel per-filer reads with prefetching in ReadLogFileRefs ReadLogFileRefs now has two levels of I/O overlap: 1. Cross-filer parallelism: one goroutine per filer reads its files concurrently. Entries feed into per-filer channels, merged by the main goroutine via min-heap (same ordering guarantee as the server's OrderedLogVisitor). 2. Within-filer prefetching: while the current file's entries are being consumed by the merge heap, the next file is already being read from the volume server in a background goroutine. Single-filer fast path avoids the heap and channels. Test results (3 filers × 7 files × 300 events, 2ms per file read): server-side sequential: 6300 events 212ms 29,760 events/sec parallel + prefetch: 6300 events 36ms 177,443 events/sec Speedup: 6.0x * filer.sync: address all review comments on metadata chunks PR Critical fixes: - sendLogFileRefs: bypass pipelinedSender, send directly on gRPC stream. Ref messages have TsNs=0 and were being incorrectly batched into the Events field by the adaptive batching logic, corrupting ref delivery. - readLogFileEntries: use io.ReadFull instead of reader.Read to prevent partial reads from corrupting size values or protobuf data. - Error handling: only skip chunk-not-found errors (matching server-side isChunkNotFoundError). Other I/O or decode failures are propagated so the follower can retry. High-priority fixes: - CollectLogFileRefs: remove incorrect +24h padding from stopTime. The extra day caused unnecessary log file refs to be collected. - Path filtering: ReadLogFileRefs now accepts PathFilter struct with PathPrefix, AdditionalPathPrefixes, and DirectoriesToWatch. Uses util.Join for path construction (avoids "//foo" on root). Excludes /.system/log/ internal entries. Matches server-side eachEventNotificationFn filtering logic. Medium-priority fixes: - CollectLogFileRefs: accept context.Context, propagate to ListDirectoryEntries calls for cancellation support. - NewChunkStreamReaderFromLookup: accept context.Context, propagate to doNewChunkStreamReader. Test fixes: - Check error returns from ReadLogFileRefs in all test call sites. --------- Co-authored-by: Copilot <copilot@github.com> |
||
|
Chris Lu
|
e52a94a3a7 |
sftpd: use global TLS-aware HTTP client for filer uploads (#8795)
* sftpd: use global TLS-aware HTTP client for filer uploads (#8794) putFile() hardcoded http:// and used http.DefaultClient, which broke file uploads when the filer has HTTPS/TLS enabled. Switch to the global HTTP client which reads [https.client] from security.toml and automatically normalizes the URL scheme. * sftpd: propagate NormalizeUrl error instead of swallowing it |
||
|
Chris LuandCopilot
|
d97660d0cd |
filer.sync: pipelined subscription with adaptive batching for faster catch-up (#8791)
* filer.sync: pipelined subscription with adaptive batching for faster catch-up The SubscribeMetadata pipeline was fully serial: reading a log entry from a volume server, unmarshaling, filtering, and calling stream.Send() all happened one-at-a-time. stream.Send() blocked the entire pipeline until the client acknowledged each event, limiting throughput to ~80 events/sec regardless of the -concurrency setting. Three server-side optimizations that stack: 1. Pipelined sender: decouple stream.Send() from the read loop via a buffered channel (1024 messages). A dedicated goroutine handles gRPC delivery while the reader continues processing the next events. 2. Adaptive batching: when event timestamps are >2min behind wall clock (backlog catch-up), drain multiple events from the channel and pack them into a single stream.Send() using a new `repeated events` field on SubscribeMetadataResponse. When events are recent (real-time), send one-by-one for low latency. Old clients ignore the new field (backward compatible). 3. Persisted log readahead: run the OrderedLogVisitor in a background goroutine so volume server I/O for the next log file overlaps with event processing and gRPC delivery. 4. Event-driven aggregated subscription: replace time.Sleep(1127ms) polling in SubscribeMetadata with notification-driven wake-up using the MetaLogBuffer subscriber mechanism, reducing real-time latency from ~1127ms to sub-millisecond. Combined, these create a 3-stage pipeline: [Volume I/O → readahead buffer] → [Filter → send buffer] → [gRPC Send] Test results (simulated backlog with 50µs gRPC latency per Send): direct (old): 2100 events 2100 sends 168ms 12,512 events/sec pipelined+batched: 2100 events 14 sends 40ms 52,856 events/sec Speedup: 4.2x single-stream throughput Ref: #8771 * filer.sync: require client opt-in for batch event delivery Add ClientSupportsBatching field to SubscribeMetadataRequest. The server only packs events into the Events batch field when the client explicitly sets this flag to true. Old clients (Java SDK, third-party) that don't set the flag get one-event-per-Send, preserving backward compatibility. All Go callers (FollowMetadata, MetaAggregator) set the flag to true since their recv loops already unpack batched events. * filer.sync: clear batch Events field after Send to release references Prevents the envelope message from holding references to the rest of the batch after gRPC serialization, allowing the GC to collect them sooner. * filer.sync: fix Send deadlock, add error propagation test, event-driven local subscribe - pipelinedSender.Send: add case <-s.done to unblock when sender goroutine exits (fixes deadlock when errCh was already consumed by a prior Send). - pipelinedSender.reportErr: remove for-range drain on sendCh that could block indefinitely. Send() now detects exit via s.done instead. - SubscribeLocalMetadata: replace remaining time.Sleep(1127ms) in the gap-detected-no-memory-data path with event-driven listenersCond.Wait(), consistent with the rest of the subscription paths. - Add TestPipelinedSenderErrorPropagation: verifies error surfaces via Send and Close when the underlying stream fails. - Replace goto with labeled break in test simulatePipeline. * filer.sync: check error returns in test code - direct_send: check slowStream.Send error return - pipelined_batched_send: check sender.Close error return - simulatePipeline: return error from sender.Close, propagate to callers --------- Co-authored-by: Copilot <copilot@github.com> |
||
|
Chris Lu
|
2604ec7deb |
Remove min_interval_seconds from plugin workers; vacuum default to 17m (#8790)
remove min_interval_seconds from plugin workers and default vacuum interval to 17m The worker-level min_interval_seconds was redundant with the admin-side DetectionIntervalSeconds, complicating scheduling logic. Remove it from vacuum, volume_balance, erasure_coding, and ec_balance handlers. Also change the vacuum default DetectionIntervalSeconds from 2 hours to 17 minutes to match the previous default behavior. |
||
|
Chris Lu
|
db9ea7c87c |
fix(fuse-test): recover from FUSE directory loss in git pull test (#8789)
* fix(fuse-test): harden ensureMountClone to verify .git/HEAD On FUSE, the kernel dcache can retain a stale directory entry after heavy git operations. Checking only os.Stat(mountClone) may find the top-level directory but the clone internals (.git/HEAD) are gone. Now ensureMountClone verifies .git/HEAD exists, cleans up stale remnants with os.RemoveAll before re-cloning, and adds a brief settle delay for the FUSE metadata cache. * fix(fuse-test): add pull recovery loop for Phase 6 git operations After git reset --hard on a FUSE mount, the kernel dcache can permanently lose the clone directory entry. The existing retry logic polls for 60+ seconds but the directory never recovers. Add pullFromCommitWithRecovery which wraps the Phase 6 pull in a recovery loop: if the clone directory vanishes, it removes the stale clone, re-creates it from the bare repo, resets to the target commit, and retries the pull (up to 3 attempts). Also adds tryGitCommand, a non-fatal git runner that returns (output, error) instead of calling require.NoError, enabling the recovery loop to handle failures gracefully without aborting the test. Fixes flaky TestGitOperations/CloneAndPull on CI. * fix(fuse-test): make recovery loop fully non-fatal Address review feedback: - Extract tryEnsureMountClone (returns error) so a transient FUSE failure during re-clone doesn't abort the test — the recovery loop can retry instead. - Check waitForDirEventually return after git reset --hard and return a specific error if the directory doesn't recover. * style(fuse-test): simplify ensureMountClone error check * fix(fuse-test): recover bare repo when FUSE mount loses it CI showed that not just the working clone but also the bare repo on the FUSE mount can vanish after heavy git operations. The recovery loop now re-creates the bare repo from the local clone (which lives on local disk and is always available) before attempting to re-clone. Adds tryEnsureBareRepo: checks HEAD exists in the bare repo, and if not, re-inits and force-pushes from the local clone. |
||
|
Chris LuandCopilot Autofix powered by AI
|
d95df76bca |
feat: separate scheduler lanes for iceberg, lifecycle, and volume management (#8787)
* feat: introduce scheduler lanes for independent per-workload scheduling
Split the single plugin scheduler loop into independent per-lane
goroutines so that volume management, iceberg compaction, and lifecycle
operations never block each other.
Each lane has its own:
- Goroutine (laneSchedulerLoop)
- Wake channel for immediate scheduling
- Admin lock scope (e.g. "plugin scheduler:default")
- Configurable idle sleep duration
- Loop state tracking
Three lanes are defined:
- default: vacuum, volume_balance, ec_balance, erasure_coding, admin_script
- iceberg: iceberg_maintenance
- lifecycle: s3_lifecycle (new, handler coming in a later commit)
Job types are mapped to lanes via a hardcoded map with LaneDefault as
the fallback. The SchedulerJobTypeState and SchedulerStatus types now
include a Lane field for API consumers.
* feat: per-lane execution reservation pools for resource isolation
Each scheduler lane now maintains its own execution reservation map
so that a busy volume lane cannot consume execution slots needed by
iceberg or lifecycle lanes. The per-lane pool is used by default when
dispatching jobs through the lane scheduler; the global pool remains
as a fallback for the public DispatchProposals API.
* feat: add per-lane scheduler status API and lane worker UI pages
- GET /api/plugin/lanes returns all lanes with status and job types
- GET /api/plugin/workers?lane=X filters workers by lane
- GET /api/plugin/scheduler-states?lane=X filters job types by lane
- GET /api/plugin/scheduler-status?lane=X returns lane-scoped status
- GET /plugin/lanes/{lane}/workers renders per-lane worker page
- SchedulerJobTypeState now includes a "lane" field
The lane worker pages show scheduler status, job type configuration,
and connected workers scoped to a single lane, with links back to
the main plugin overview.
* feat: add s3_lifecycle worker handler for object store lifecycle management
Implements a full plugin worker handler for S3 lifecycle management,
assigned to the new "lifecycle" scheduler lane.
Detection phase:
- Reads filer.conf to find buckets with TTL lifecycle rules
- Creates one job proposal per bucket with active lifecycle rules
- Supports bucket_filter wildcard pattern from admin config
Execution phase:
- Walks the bucket directory tree breadth-first
- Identifies expired objects by checking TtlSec + Crtime < now
- Deletes expired objects in configurable batches
- Reports progress with scanned/expired/error counts
- Supports dry_run mode for safe testing
Configurable via admin UI:
- batch_size: entries per filer listing page (default 1000)
- max_deletes_per_bucket: safety cap per run (default 10000)
- dry_run: detect without deleting
- delete_marker_cleanup: clean expired delete markers
- abort_mpu_days: abort stale multipart uploads
The handler integrates with the existing PutBucketLifecycle flow which
sets TtlSec on entries via filer.conf path rules.
* feat: add per-lane submenu items under Workers sidebar menu
Replace the single "Workers" sidebar link with a collapsible submenu
containing three lane entries:
- Default (volume management + admin scripts) -> /plugin
- Iceberg (table compaction) -> /plugin/lanes/iceberg/workers
- Lifecycle (S3 object expiration) -> /plugin/lanes/lifecycle/workers
The submenu auto-expands when on any /plugin page and highlights the
active lane. Icons match each lane's job type descriptor (server,
snowflake, hourglass).
* feat: scope plugin pages to their scheduler lane
The plugin overview, configuration, detection, queue, and execution
pages now filter workers, job types, scheduler states, and scheduler
status to only show data for their lane.
- Plugin() templ function accepts a lane parameter (default: "default")
- JavaScript appends ?lane= to /api/plugin/workers, /job-types,
/scheduler-states, and /scheduler-status API calls
- GET /api/plugin/job-types now supports ?lane= filtering
- When ?job= is provided (e.g. ?job=iceberg_maintenance), the lane is
auto-derived from the job type so the page scopes correctly
This ensures /plugin shows only default-lane workers and
/plugin/configuration?job=iceberg_maintenance scopes to the iceberg lane.
* fix: remove "Lane" from lane worker page titles and capitalize properly
"lifecycle Lane Workers" -> "Lifecycle Workers"
"iceberg Lane Workers" -> "Iceberg Workers"
* refactor: promote lane items to top-level sidebar menu entries
Move Default, Iceberg, and Lifecycle from a collapsible submenu to
direct top-level items under the WORKERS heading. Removes the
intermediate "Workers" parent link and collapse toggle.
* admin: unify plugin lane routes and handlers
* admin: filter plugin jobs and activities by lane
* admin: reuse plugin UI for worker lane pages
* fix: use ServerAddress.ToGrpcAddress() for filer connections in lifecycle handler
ClusterContext addresses use ServerAddress format (host:port.grpcPort).
Convert to the actual gRPC address via ToGrpcAddress() before dialing,
and add a Ping verification after connecting.
Fixes: "dial tcp: lookup tcp/8888.18888: unknown port"
* fix: resolve ServerAddress gRPC port in iceberg and lifecycle filer connections
ClusterContext addresses use ServerAddress format (host:httpPort.grpcPort).
Both the iceberg and lifecycle handlers now detect the compound format
and extract the gRPC port via ToGrpcAddress() before dialing. Plain
host:port addresses (e.g. from tests) are passed through unchanged.
Fixes: "dial tcp: lookup tcp/8888.18888: unknown port"
* align url
* Potential fix for code scanning alert no. 335: Incorrect conversion between integer types
Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>
* fix: address PR review findings across scheduler lanes and lifecycle handler
- Fix variable shadowing: rename loop var `w` to `worker` in
GetPluginWorkersAPI to avoid shadowing the http.ResponseWriter param
- Fix stale GetSchedulerStatus: aggregate loop states across all lanes
instead of reading never-updated legacy schedulerLoopState
- Scope InProcessJobs to lane in GetLaneSchedulerStatus
- Fix AbortMPUDays=0 treated as unset: change <= 0 to < 0 so 0 disables
- Propagate listing errors in lifecycle bucket walk instead of swallowing
- Implement DeleteMarkerCleanup: scan for S3 delete marker entries and
remove them
- Implement AbortMPUDays: scan .uploads directory and remove stale
multipart uploads older than the configured threshold
- Fix success determination: mark job failed when result.errors > 0
even if no fatal error occurred
- Add regression test for jobTypeLaneMap to catch drift from handler
registrations
* fix: guard against nil result in lifecycle completion and trim filer addresses
- Guard result dereference in completion summary: use local vars
defaulting to 0 when result is nil to prevent panic
- Append trimmed filer addresses instead of originals so whitespace
is not passed to the gRPC dialer
* fix: propagate ctx cancellation from deleteExpiredObjects and add config logging
- deleteExpiredObjects now returns a third error value when the context
is canceled mid-batch; the caller stops processing further batches
and returns the cancellation error to the job completion handler
- readBoolConfig and readInt64Config now log unexpected ConfigValue
types at V(1) for debugging, consistent with readStringConfig
* fix: propagate errors in lifecycle cleanup helpers and use correct delete marker key
- cleanupDeleteMarkers: return error on ctx cancellation and SeaweedList
failures instead of silently continuing
- abortIncompleteMPUs: log SeaweedList errors instead of discarding
- isDeleteMarker: use ExtDeleteMarkerKey ("Seaweed-X-Amz-Delete-Marker")
instead of ExtLatestVersionIsDeleteMarker which is for the parent entry
- batchSize cap: use math.MaxInt instead of math.MaxInt32
* fix: propagate ctx cancellation from abortIncompleteMPUs and log unrecognized bool strings
- abortIncompleteMPUs now returns (aborted, errors, ctxErr) matching
cleanupDeleteMarkers; caller stops on cancellation or listing failure
- readBoolConfig logs unrecognized string values before falling back
* fix: shared per-bucket budget across lifecycle phases and allow cleanup without expired objects
- Thread a shared remaining counter through TTL deletion, delete marker
cleanup, and MPU abort so the total operations per bucket never exceed
MaxDeletesPerBucket
- Remove early return when no TTL-expired objects found so delete marker
cleanup and MPU abort still run
- Add NOTE on cleanupDeleteMarkers about version-safety limitation
---------
Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>
|
||
|
Chris Lu
|
ba624f1f34 |
Rust volume server implementation with CI (#8539)
* Match Go gRPC client transport defaults
* Honor Go HTTP idle timeout
* Honor maintenanceMBps during volume copy
* Honor images.fix.orientation on uploads
* Honor cpuprofile when pprof is disabled
* Match Go memory status payloads
* Propagate request IDs across gRPC calls
* Format pending Rust source updates
* Match Go stats endpoint payloads
* Serve Go volume server UI assets
* Enforce Go HTTP whitelist guards
* Align Rust metrics admin-port test with Go behavior
* Format pending Rust server updates
* Honor access.ui without per-request JWT checks
* Honor keepLocalDatFile in tier upload shortcut
* Honor Go remote volume write mode
* Load tier backends from master config
* Check master config before loading volumes
* Remove vif files on volume destroy
* Delete remote tier data on volume destroy
* Honor vif version defaults and overrides
* Reject mismatched vif bytes offsets
* Load remote-only tiered volumes
* Report Go tail offsets in sync status
* Stream remote dat in incremental copy
* Honor collection vif for EC shard config
* Persist EC expireAtSec in vif metadata
* Stream remote volume reads through HTTP
* Serve HTTP ranges from backend source
* Match Go ReadAllNeedles scan order
* Match Go CopyFile zero-stop metadata
* Delete EC volumes with collection cleanup
* Drop deleted collection metrics
* Match Go tombstone ReadNeedleMeta
* Match Go TTL parsing: all-digit default to minutes, two-pass fit algorithm
* Match Go needle ID/cookie formatting and name size computation
* Match Go image ext checks: webp resize only, no crop; empty healthz body
* Match Go Prometheus metric names and add missing handler counter constants
* Match Go ReplicaPlacement short string parsing with zero-padding
* Add missing EC constants MAX_SHARD_COUNT and MIN_TOTAL_DISKS
* Add walk_ecx_stats for accurate EC volume file counts and size
* Match Go VolumeStatus dat file size, EC shard stats, and disk pct precision
* Match Go needle map: unconditional delete counter, fix redb idx walk offset
* Add CompactMapSegment overflow panic guard matching Go
* Match Go volume: vif creation, version from superblock, TTL expiry, dedup data_size, garbage_level fallback
* Match Go 304 Not Modified: return bare status with no headers
* Match Go JWT error message: use "wrong jwt" instead of detailed error
* Match Go read handler bare 400, delete error prefix, download throttle timeout
* Match Go pretty JSON 1-space indent and "Deletion Failed:" error prefix
* Match Go heartbeat: keep is_heartbeating on error, add EC shard identification
* Match Go needle ReadBytes V2: tolerate EOF on truncated body
* Match Go volume: cookie check on any existing needle, return DataSize, 128KB meta guard
* Match Go DeleteCollection: propagate destroy errors
* Match Go gRPC: BatchDelete no flag, IncrementalCopy error, FetchAndWrite concurrent, VolumeUnmount/DeleteCollection errors, tail draining, query error code
* Match Go Content-Disposition RFC 6266 formatting with RFC 2231 encoding
* Match Go Guard isWriteActive: combine whitelist and signing key check
* Match Go DeleteCollectionMetrics: use partial label matching
* Match Go heartbeat: send state-only delta on volume state changes
* Match Go ReadNeedleMeta paged I/O: read header+tail only, skip data; add EIO tracking
* Match Go ScrubVolume INDEX mode dispatch; add VolumeCopy preallocation and EC NeedleStatus TODOs
* Add read_ec_shard_needle for full needle reconstruction from local EC shards
* Make heartbeat master config helpers pub for VolumeCopy preallocation
* Match Go gRPC: VolumeCopy preallocation, EC NeedleStatus full read, error message wording
* Match Go HTTP responses: omitempty fields, 2-space JSON indent, JWT JSON error, delete pretty/JSONP, 304 Last-Modified, raw write error
* Match Go WriteNeedleBlob V3 timestamp patching, fix makeup_diff double padding, count==0 read handling
* Add rebuild_ecx_file for EC index reconstruction from data shards
* Match Go gRPC: tail header first-chunk-only, EC cleanup on failure, copy append mode, ecx rebuild, compact cancellation
* Add EC volume read and delete support in HTTP handlers
* Add per-shard EC mount/unmount, location predicate search, idx directory for EC
* Add CheckVolumeDataIntegrity on volume load matching Go
* Match Go gRPC: EC multi-disk placement, per-shard mount/unmount, no auto-mount on reconstruct, streaming ReadAll/EcShardRead, ReceiveFile cleanup, version check, proxy streaming, redirect Content-Type
* Match Go heartbeat metric accounting
* Match Go duplicate UUID heartbeat retries
* Delete expired EC volumes during heartbeat
* Match Go volume heartbeat pruning
* Honor master preallocate in volume max
* Report remote storage info in heartbeats
* Emit EC heartbeat deltas on shard changes
* Match Go throttle boundary: use <= instead of <, fix pretty JSON to 1-space
* Match Go write_needle_blob monotonic appendAtNs via get_append_at_ns
* Match Go VolumeUnmount: idempotent success when volume not found
* Match Go TTL Display: return empty string when unit is Empty
Go checks `t.Unit == Empty` separately and returns "" for TTLs
with nonzero count but Empty unit. Rust only checked is_empty()
(count==0 && unit==0), so count>0 with unit=0 would format as
"5 " instead of "".
* Match Go error behavior for truncated needle data in read_body_v2
Go's readNeedleDataVersion2 returns "index out of range %d" errors
(indices 1-7) when needle body or metadata fields are truncated.
Rust was silently tolerating truncation and returning Ok. Now returns
NeedleError::IndexOutOfRange with the matching index for each field.
* Match Go download throttle: return JSON error instead of plain text
* Match Go crop params: default x1/y1 to 0 when not provided
* Match Go ScrubEcVolume: accumulate total_files from EC shards
* Match Go ScrubVolume: count total_files even on scrub error
* Match Go VolumeEcShardsCopy: set ignore_source_file_not_found for .vif
* Match Go VolumeTailSender: send needle_header on every chunk
* Match Go read_super_block: apply replication override from .vif
* Match Go check_volume_data_integrity: verify all 10 entries, detect trailing corruption
* Match Go WriteNeedleBlob: dedup check before writing during replication
* handlers: use meta-only reads for HEAD
* handlers: align range parsing and responses with Go
* handlers: align upload parsing with Go
* deps: enable webp support
* Make 5bytes the default feature for idx entry compatibility
* Match Go TTL: preserve original unit when count fits in byte
* Fix EC locate_needle: use get_actual_size for full needle size
* Fix raw body POST: only parse multipart when Content-Type contains form-data
* Match Go ReceiveFile: return protocol errors in response body, not gRPC status
* add docs
* Match Go VolumeEcShardsCopy: append to .ecj file instead of truncating
* Match Go ParsePath: support _delta suffix on file IDs for sub-file addressing
* Match Go chunk manifest: add Accept-Ranges, Content-Disposition, filename fallback, MIME detection
* Match Go privateStoreHandler: use proper JSON error for unsupported methods
* Match Go Destroy: add only_empty parameter to reject non-empty volume deletion
* Fix compilation: set_read_only_persist and set_writable return ()
These methods fire-and-forget save_vif internally, so gRPC callers
should not try to chain .map_err() on the unit return type.
* Match Go SaveVolumeInfo: check writability and propagate errors in save_vif
* Match Go VolumeDelete: propagate only_empty to delete_volume for defense in depth
The gRPC VolumeDelete handler had a pre-check for only_empty but then
passed false to store.delete_volume(), bypassing the store-level check.
Go passes req.OnlyEmpty directly to DeleteVolume. Now Rust does the same
for defense in depth against TOCTOU races (though the store write lock
makes this unlikely).
* Match Go ProcessRangeRequest: return full content for empty/oversized ranges
Go returns nil from ProcessRangeRequest when ranges are empty or total
range size exceeds content length, causing the caller to serve the full
content as a normal 200 response. Rust was returning an empty 200 body.
* Match Go Query: quote JSON keys in output records
Go's ToJson produces valid JSON with quoted keys like {"name":"Alice"}.
Rust was producing invalid JSON with unquoted keys like {name:"Alice"}.
* Match Go VolumeCopy: reject when no suitable disk location exists
Go returns ErrVolumeNoSpaceLeft when no location matches the disk type
and has sufficient space. Rust had an unsafe fallback that silently
picked the first location regardless of type or available space.
* Match Go DeleteVolumeNeedle: check noWriteOrDelete before allowing delete
Go checks v.noWriteOrDelete before proceeding with needle deletion,
returning "volume is read only" if true. Rust was skipping this check.
* Match Go ReceiveFile: prefer HardDrive location for EC and use response-level write errors
Two fixes: (1) Go prefers HardDriveType disk location for EC volumes,
falling back to first location. Returns "no storage location available"
when no locations exist. (2) Write failures are now response-level
errors (in response body) instead of gRPC status errors, matching Go.
* Match Go CopyFile: sync EC volume journal to disk before copying
Go calls ecVolume.Sync() before copying EC volume files to ensure the
.ecj journal is flushed to disk. Added sync_to_disk() to EcVolume and
call it in the CopyFile EC branch.
* Match Go readSuperBlock: propagate replication parse errors
Go returns an error when parsing the replication string from the .vif
file fails. Rust was silently ignoring the parse failure and using the
super block's replication as-is.
* Match Go TTL expiry: remove append_at_ns > 0 guard
Go computes TTL expiry from AppendAtNs without guarding against zero.
When append_at_ns is 0, the expiry is epoch + TTL which is in the past,
correctly returning NotFound. Rust's extra guard skipped the check,
incorrectly returning success for such needles.
* Match Go delete_collection: skip volumes with compaction in progress
Go checks !v.isCompactionInProgress.Load() before destroying a volume
during collection deletion, skipping compacting volumes. Also changed
destroy errors to log instead of aborting the entire collection delete.
* Match Go MarkReadonly/MarkWritable: always notify master even on local error
Go always notifies the master regardless of whether the local
set_read_only_persist or set_writable step fails. The Rust code was
using `?` which short-circuited on error, skipping the final master
notification. Save the result and defer the `?` until after the
notify call.
* Match Go PostHandler: return 500 for all write errors
Go returns 500 (InternalServerError) for all write failures. Rust was
returning 404 for volume-not-found and 403 for read-only volumes.
* Match Go makeupDiff: validate .cpd compaction revision is old + 1
Go reads the new .cpd file's super block and verifies the compaction
revision is exactly old + 1. Rust only validated the old revision.
* Match Go VolumeStatus: check data backend before returning status
Go checks v.DataBackend != nil before building the status response,
returning an error if missing. Rust was silently returning size 0.
* Match Go PostHandler: always include mime field in upload response JSON
Go always serializes the mime field even when empty ("mime":""). Rust was
omitting it when empty due to Option<String> with skip_serializing_if.
* Match Go FindFreeLocation: account for EC shards in free slot calculation
Go subtracts EC shard equivalents when computing available volume slots.
Rust was only comparing volume count, potentially over-counting free
slots on locations with many EC shards.
* Match Go privateStoreHandler: use INVALID as metrics label for unsupported methods
Go records the method as INVALID in metrics for unsupported HTTP methods.
Rust was using the actual method name.
* Match Go volume: add commit_compact guard and scrub data size validation
Two fixes: (1) commit_compact now checks/sets is_compacting flag to
prevent concurrent commits, matching Go's CompareAndSwap guard.
(2) scrub now validates total needle sizes against .dat file size.
* Match Go gRPC: fix TailSender error propagation, EcShardsInfo all slots, EcShardRead .ecx check
Three fixes: (1) VolumeTailSender now propagates binary search errors
instead of silently falling back to start. (2) VolumeEcShardsInfo
returns entries for all shard slots including unmounted. (3)
VolumeEcShardRead checks .ecx index for deletions instead of .ecj.
* Match Go metrics: add BuildInfo gauge and connection tracking functions
Go exposes a BuildInfo Prometheus metric with version labels, and tracks
open connections via stats.ConnectionOpen/Close. Added both to Rust.
* Match Go NeedleMap.Delete: use !is_deleted() instead of is_valid()
Go's CompactMap.Delete checks !IsDeleted() not IsValid(), so needles
with size==0 (live but anomalous) can still be deleted. The Rust code
was using is_valid() which returns false for size==0, preventing
deletion of such needles.
* Match Go fitTtlCount: always normalize TTL to coarsest unit
Go's fitTtlCount always converts to seconds first, then finds the
coarsest unit that fits in one byte (e.g., 120m → 2h). Rust had an
early return for count<=255 that skipped normalization, producing
different binary encodings for the same duration.
* Match Go BuildInfo metric: correct name and add missing labels
Go uses SeaweedFS_build_info (Namespace=SeaweedFS, Subsystem=build,
Name=info) with labels [version, commit, sizelimit, goos, goarch].
Rust had SeaweedFS_volumeServer_buildInfo with only [version].
* Match Go HTTP handlers: fix UploadResult fields, DiskStatus JSON, chunk manifest ETag
- UploadResult.mime: add skip_serializing_if to omit empty MIME (Go uses omitempty)
- UploadResult.contentMd5: only include when request provided Content-MD5 header
- Content-MD5 response header: only set when request provided it
- DiskStatuses: use camelCase field names (percentFree, percentUsed, diskType)
to match Go's protobuf JSON marshaling
- Chunk manifest: preserve needle ETag in expanded response headers
* Match Go volume: fix version(), integrity check, scrub, and commit_compact
- version(): use self.version() instead of self.super_block.version in
read_all_needles, check_volume_data_integrity, scan_raw_needles_from
to respect volumeInfo.version override
- check_volume_data_integrity: initialize healthy_index_size to idx_size
(matching Go) and continue on EOF instead of returning error
- scrub(): count deleted needles in total_read since they still occupy
space in the .dat file (matches Go's totalRead += actualSize for deleted)
- commit_compact: clean up .cpd/.cpx files on makeup_diff failure
(matches Go's error path cleanup)
* Match Go write queue: add 4MB batch byte limit
Go's startWorker breaks the batch at either 128 requests or 4MB of
accumulated write data. Rust only had the 128-request limit, allowing
large writes to accumulate unbounded latency.
* Add TTL normalization tests for Go parity verification
Test that fit_ttl_count normalizes 120m→2h, 24h→1d, 7d→1w even
when count fits in a byte, matching Go's fitTtlCount behavior.
* Match Go FindFreeLocation: account for EC shards in free slot calculation
Go's free volume count subtracts both regular volumes and EC volumes
from max_volume_count. Rust was only counting regular volumes, which
could over-report available slots when EC shards are mounted.
* Match Go EC volume: mark deletions in .ecx and replay .ecj at startup
Go's DeleteNeedleFromEcx marks needles as deleted in the .ecx index
in-place (writing TOMBSTONE_FILE_SIZE at the size field) in addition
to appending to the .ecj journal. Go's RebuildEcxFile replays .ecj
entries into .ecx on startup, then removes the .ecj file.
Rust was only appending to .ecj without marking .ecx, which meant
deleted EC needles remained readable via .ecx binary search. This
fix:
- Opens .ecx in read/write mode (was read-only)
- Adds mark_needle_deleted_in_ecx: binary search + in-place write
- Calls it from journal_delete before appending to .ecj
- Adds rebuild_ecx_from_journal: replays .ecj into .ecx on startup
* Match Go check_all_ec_shards_deleted: use MAX_SHARD_COUNT instead of hardcoded 14
Go's TotalShardsCount is DataShardsCount + ParityShardsCount = 14 by
default, but custom EC configs via .vif can have more shards (up to
MaxShardCount = 32). Using MAX_SHARD_COUNT ensures all shard files
are checked regardless of EC configuration.
* Match Go EC locate: subtract 1 from shard size and use datFileSize override
Go's LocateEcShardNeedleInterval passes shard.ecdFileSize-1 to
LocateData (shards are padded, -1 avoids overcounting large block
rows). When datFileSize is known, Go uses datFileSize/DataShards
instead. Rust was passing the raw shard file size without adjustment.
* Fix TTL parsing and DiskStatus field names to match Go exactly
TTL::read: Go's ReadTTL preserves the original unit (7d stays 7d,
not 1w) and errors on count > 255. The previous normalization change
was incorrect — Go only normalizes internally via fitTtlCount, not
during string parsing.
DiskStatus: Go uses encoding/json on protobuf structs, which reads
the json struct tags (snake_case: percent_free, percent_used,
disk_type), not the protobuf JSON names (camelCase). Revert to
snake_case to match Go's actual output.
* Fix heartbeat: check leader != current master before redirect, process duplicated UUIDs first
Match Go's volume_grpc_client_to_master.go behavior:
1. Only trigger leader redirect when the leader address differs from the
current master (prevents unnecessary reconnect loops when master confirms
its own address).
2. Process duplicated_uuids before leader redirect check, matching Go's
ordering where duplicate UUID detection takes priority.
* Remove SetState version check to match Go behavior
Go's SetState unconditionally applies the state without any version
mismatch check. The Rust version had an extra optimistic concurrency
check that would reject valid requests from Go clients that don't
track versions.
* Fix TTL::read() to normalize via fit_ttl_count matching Go's ReadTTL
Go's ReadTTL calls fitTtlCount which converts to seconds and normalizes
to the coarsest unit that fits in a byte count (e.g. 120m->2h, 7d->1w,
24h->1d). The Rust version was preserving the original unit, producing
different binary encodings on disk and in heartbeat messages.
* Always return Content-MD5 header and JSON field on successful writes
Go always sets Content-MD5 in the response regardless of whether the
request included it. The Rust version was conditionally including it
only when the request provided Content-MD5.
* Include name and size in UploadResult JSON even when empty/zero
Go's encoding/json always includes empty strings and zero values in
the upload response. The Rust version was using skip_serializing_if
to omit them, causing JSON structure differences.
* Include deleted needles in scan_raw_needles_from to match Go
Go's ScanVolumeFileFrom visits ALL needles including deleted ones.
Skipping deleted entries during incremental copy would cause tombstones
to not be propagated, making deleted files reappear on the receiving side.
* Match Go NeedleMap.Delete: always write tombstone to idx file
Go's NeedleMap.Delete unconditionally writes a tombstone entry to the
idx file and updates metrics, even if the needle doesn't exist or is
already deleted. This is important for replication where every delete
operation must produce an idx write. The Rust version was skipping the
tombstone write for non-existent or already-deleted needles.
* Limit MIME type to 255 bytes matching Go's CreateNeedleFromRequest
* Title-case Seaweed-* pair keys to match Go HTTP header canonicalization
* Unify DiskType::Hdd into HardDrive to match Go's single HardDriveType
* Skip tombstone entries in walk_ecx_stats total_size matching Go's Raw()
* Return EMPTY TTL when computed seconds is zero matching Go's fitTtlCount
* Include disk-space-low in Volume.is_read_only() matching Go
* Log error on CIDR parse failure in whitelist matching Go's glog.Errorf
* Log cookie mismatch in gRPC Query matching Go's V(0).Infof
* Fix is_expired volume_size comparison to use < matching Go
Go checks `volumeSize < super_block.SuperBlockSize` (strict less-than),
but Rust used `<=`. This meant Rust would fail to expire a volume that
is exactly SUPER_BLOCK_SIZE bytes.
* Apply Go's JWT expiry defaults: 10s write, 60s read
Go calls v.SetDefault("jwt.signing.expires_after_seconds", 10) and
v.SetDefault("jwt.signing.read.expires_after_seconds", 60). Rust
defaulted to 0 for both, which meant tokens would never expire when
security.toml has a signing key but omits expires_after_seconds.
* Stop [grpc.volume].ca from overriding [grpc].ca matching Go
Go reads the gRPC CA file only from config.GetString("grpc.ca"), i.e.
the [grpc] section. The [grpc.volume] section only provides cert and
key. Rust was also reading ca from [grpc.volume] which would silently
override the [grpc].ca value when both were present.
* Fix free_volume_count to use EC shard count matching Go
Was counting EC volumes instead of EC shards, which underestimates EC
space usage. One EC volume with 14 shards uses ~1.4 volume slots, not 1.
Now uses Go's formula: ((max - volumes) * DataShardsCount - ecShardCount) / DataShardsCount.
* Include preallocate in compaction space check matching Go
Go uses max(preallocate, estimatedCompactSize) for the free space check.
Rust was only using the estimated volume size, which could start a
compaction that fails mid-way if preallocate exceeds the volume size.
* Check gzip magic bytes before setting Content-Encoding matching Go
Go checks both Accept-Encoding contains "gzip" AND IsGzippedContent
(data starts with 0x1f 0x8b) before setting Content-Encoding: gzip.
Rust only checked Accept-Encoding, which could incorrectly declare
gzip encoding for non-gzip compressed data.
* Only set upload response name when needle HasName matching Go
Go checks reqNeedle.HasName() before setting ret.Name. Rust always set
the name from the filename variable, which could return the fid portion
of the path as the name for raw PUT requests without a filename.
* Treat MaxVolumeCount==0 as unlimited matching Go's hasFreeDiskLocation
Go's hasFreeDiskLocation returns true immediately when MaxVolumeCount
is 0, treating it as unlimited. Rust was computing effective_free as
<= 0 for max==0, rejecting the location. This could fail volume
creation during early startup before the first heartbeat adjusts max.
* Read lastAppendAtNs from deleted V3 entries in integrity check
Go's doCheckAndFixVolumeData reads AppendAtNs from both live entries
(verifyNeedleIntegrity) and deleted tombstones (verifyDeletedNeedleIntegrity).
Rust was skipping deleted entries, which could result in a stale
last_append_at_ns if the last index entry is a deletion.
* Return empty body for empty/oversized range requests matching Go
Go's ProcessRangeRequest returns nil (empty body, 200 OK) when
parsed ranges are empty or combined range size exceeds total content
size. The Rust buffered path incorrectly returned the full file data
for both cases. The streaming path already handled this correctly.
* Dispatch ScrubEcVolume by mode matching Go's INDEX/LOCAL/FULL
Go's ScrubEcVolume switches on mode: INDEX calls v.ScrubIndex()
(ecx integrity only), LOCAL calls v.ScrubLocal(), FULL calls
vs.store.ScrubEcVolume(). Rust was ignoring the mode and always
running verify_ec_shards. Now INDEX mode checks ecx index integrity
(sorted overlap detection + file size validation) without shard I/O,
while LOCAL/FULL modes run the existing shard verification.
* Fix TTL test expectation: 7d normalizes to 1w matching Go's fitTtlCount
Go's ReadTTL calls fitTtlCount which normalizes to the coarsest unit
that fits: 7 days = 1 week, so "7d" becomes {Count:1, Unit:Week}
which displays as "1w". Both Go and Rust normalize identically.
* Add version mismatch check to SetState matching Go's State.Update
Go's State.Update compares the incoming version with the stored
version and returns "version mismatch" error if they differ. This
provides optimistic concurrency control. The Rust implementation
was accepting any version unconditionally.
* Use unquoted keys in Query JSON output matching Go's json.ToJson
Go's json.ToJson produces records with unquoted keys like
{score:12} not {"score":12}. This is a custom format used
internally by SeaweedFS for query results.
* Fix TTL test expectation in VolumeNeedleStatus: 7d normalizes to 1w
Same normalization as the HTTP test: Go's ReadTTL calls fitTtlCount
which converts 7 days to 1 week.
* Include ETag header in 304 Not Modified responses matching Go behavior
Go sets ETag on the response writer (via SetEtag) before the
If-Modified-Since and If-None-Match conditional checks, so both
304 response paths include the ETag header. The Rust implementation
was only adding ETag to 200 responses.
* Remove needle-name fallback in chunk manifest filename resolution
Go's tryHandleChunkedFile only falls back from URL filename to
manifest name. Rust had an extra fallback to needle.name that
Go does not perform, which could produce different
Content-Disposition filenames for chunk manifests.
* Validate JWT nbf (Not Before) claim matching Go's jwt-go/v5
Go's jwt.ParseWithClaims validates the nbf claim when present,
rejecting tokens whose nbf is in the future. The Rust jsonwebtoken
crate defaults validate_nbf to false, so tokens with future nbf
were incorrectly accepted.
* Set isHeartbeating to true at startup matching Go's VolumeServer init
Go unconditionally sets isHeartbeating: true in the VolumeServer
struct literal. Rust was starting with false when masters are
configured, causing /healthz to return 503 until the first
heartbeat succeeds.
* Call store.close() on shutdown matching Go's Shutdown()
Go's Shutdown() calls vs.store.Close() which closes all volumes
and flushes file handles. The Rust server was relying on process
exit for cleanup, which could leave data unflushed.
* Include server ID in maintenance mode error matching Go's format
Go returns "volume server %s is in maintenance mode" with the
store ID. Rust was returning a generic "maintenance mode" message.
* Fix DiskType test: use HardDrive variant matching Go's HddType=""
Go maps both "" and "hdd" to HardDriveType (empty string). The
Rust enum variant is HardDrive, not Hdd. The test referenced a
nonexistent Hdd variant causing compilation failure.
* Do not include ETag in 304 responses matching Go's GetOrHeadHandler
Go sets ETag at L235 AFTER the If-Modified-Since and If-None-Match
304 return paths, so Go's 304 responses do not include the ETag header.
The Rust code was incorrectly including ETag in both 304 response paths.
* Return 400 on malformed query strings in PostHandler matching Go's ParseForm
Go's r.ParseForm() returns HTTP 400 with "form parse error: ..." when
the query string is malformed. Rust was silently falling back to empty
query params via unwrap_or_default().
* Load EC volume version from .vif matching Go's NewEcVolume
Go sets ev.Version = needle.Version(volumeInfo.Version) from the .vif
file. Rust was always using Version::current() (V3), which would produce
wrong needle actual size calculations for volumes created with V1 or V2.
* Sync .ecx file before close matching Go's EcVolume.Close
Go calls ev.ecxFile.Sync() before closing to ensure in-place deletion
marks are flushed to disk. Without this, deletion marks written via
MarkNeedleDeleted could be lost on crash.
* Validate SuperBlock extra data size matching Go's Bytes() guard
Go checks extraSize > 256*256-2 and calls glog.Fatalf to prevent
corrupt super block headers. Rust was silently truncating via u16 cast,
which would write an incorrect extra_size field.
* Update quinn-proto 0.11.13 -> 0.11.14 to fix GHSA-6xvm-j4wr-6v98
Fixes Dependency Review CI failure: quinn-proto < 0.11.14 is vulnerable
to unauthenticated remote DoS via panic in QUIC transport parameter
parsing.
* Skip TestMultipartUploadUsesFormFieldsForTimestampAndTTL for Go server
Go's r.FormValue() cannot read multipart text fields after
r.MultipartReader() consumes the body, so ts/ttl sent as multipart
form fields only work with the Rust volume server. Skip this test
when VOLUME_SERVER_IMPL != "rust" to fix CI failure.
* Flush .ecx in EC volume sync_to_disk matching Go's Sync()
Go's EcVolume.Sync() flushes both the .ecj journal and the .ecx index
to disk. The Rust version only flushed .ecj, leaving in-place deletion
marks in .ecx unpersisted until close(). This could cause data
inconsistency if the server crashes after marking a needle deleted in
.ecx but before close().
* Remove .vif file in EC volume destroy matching Go's Destroy()
Go's EcVolume.Destroy() removes .ecx, .ecj, and .vif files. The Rust
version only removed .ecx and .ecj, leaving orphaned .vif files on
disk after EC volume destruction (e.g., after TTL expiry).
* Fix is_expired to use <= for SuperBlockSize check matching Go
Go checks contentSize <= SuperBlockSize to detect empty volumes (no
needles). Rust used < which would incorrectly allow a volume with
exactly SuperBlockSize bytes (header only, no data) to proceed to
the TTL expiry check and potentially be marked as expired.
* Fix read_append_at_ns to read timestamps from tombstone entries
Go reads the full needle body for all entries including tombstones
(deleted needles with size=0) to extract the actual AppendAtNs
timestamp. The Rust version returned 0 early for size <= 0 entries,
which would cause the binary search in incremental copy to produce
incorrect results for positions containing deleted needles.
Now uses get_actual_size to compute the on-disk size (which handles
tombstones correctly) and only returns 0 when the actual size is 0.
* Add X-Request-Id response header matching Go's requestIDMiddleware
Go sets both X-Request-Id and x-amz-request-id response headers.
The Rust server only set x-amz-request-id, missing X-Request-Id.
* Add skip_serializing_if for UploadResult name and size fields
Go's UploadResult uses json:"name,omitempty" and json:"size,omitempty",
omitting these fields from JSON when they are zero values (empty
string / 0). The Rust struct always serialized them, producing
"name":"" and "size":0 where Go would omit them.
* Support JSONP/pretty-print for write success responses
Go's writeJsonQuiet checks for callback (JSONP) and pretty query
parameters on all JSON responses including write success. The Rust
write success path used axum::Json directly, bypassing JSONP and
pretty-print support. Now uses json_result_with_query to match Go.
* Include actual limit in file size limit error message
Go returns "file over the limited %d bytes" with the actual limit
value included. Rust returned a generic "file size limit exceeded"
without the limit value, making it harder to debug.
* Extract extension from 2-segment URL paths for image operations
Go's parseURLPath extracts the file extension from all URL formats
including 2-segment paths like /vid,fid.jpg. The Rust version only
handled 3-segment paths (/vid/fid/filename.ext), so extensions in
2-segment paths were lost. This caused image resize/crop operations
requested via query params to be silently skipped for those paths.
* Add size_hint to TrackedBody so throttled downloads get Content-Length
TrackedBody (used for download throttling) did not implement
size_hint(), causing HTTP/1.1 to fall back to chunked transfer
encoding instead of setting Content-Length. Go always sets
Content-Length explicitly for non-range responses.
* Add Last-Modified, pairs, and S3 headers to chunk manifest responses
Go sets Last-Modified, needle pairs, and S3 pass-through headers on
the response writer BEFORE calling tryHandleChunkedFile. Since the
Rust chunk manifest handler created fresh response headers and
returned early, these headers were missing from chunk manifest
responses. Now passes last_modified_str into the chunk manifest
handler and applies pairs and S3 pass-through query params
(response-cache-control, response-content-encoding, etc.) to the
chunk manifest response headers.
* Fix multipart fallback to use first part data when no filename
Go reads the first part's data unconditionally, then looks for a
part with a filename. If none found, Go uses the first part's data
(with empty filename). Rust only captured parts with filenames, so
when no part had a filename it fell back to the raw multipart body
bytes (including boundary delimiters), producing corrupt needle data.
* Set HasName and HasMime flags for empty values matching Go
Go's CreateNeedleFromRequest sets HasName and HasMime flags even when
the filename or MIME type is empty (len < 256 is true for len 0).
Rust skipped empty values, causing the on-disk needle format to
differ: Go-written needles include extra bytes for the empty name/mime
size fields, changing the serialized needle size in the idx entry.
This ensures binary format compatibility between Go and Rust servers.
* Add is_stopping guard to vacuum_volume_commit matching Go
Go's CommitCompactVolume (store_vacuum.go L53-54) checks
s.isStopping before committing compaction to prevent file
swaps during shutdown. The Rust handler was missing this
check, which could allow compaction commits while the
server is stopping.
* Remove disk_type from required status fields since Go omits it
Go's default DiskType is "" (HardDriveType), and protobuf's omitempty
tag causes empty strings to be dropped from JSON output.
* test: honor rust env in dual volume harness
* grpc: notify master after volume lifecycle changes
* http: proxy to replicas before download-limit timeout
* test: pass readMode to rust volume harnesses
* fix store free-location predicate selection
* fix volume copy disk placement and heartbeat notification
* fix chunk manifest delete replication
* fix write replication to survive client disconnects
* fix download limit proxy and wait flow
* fix crop gating for streamed reads
* fix upload limit wait counter behavior
* fix chunk manifest image transforms
* fix has_resize_ops to check width/height > 0 instead of is_some()
Go's shouldResizeImages condition is `width > 0 || height > 0`, so
`?width=0` correctly evaluates to false. Rust was using `is_some()`
which made `?width=0` evaluate to true, unnecessarily disabling
streaming reads for those requests.
* fix Content-MD5 to only compute and return when provided by client
Go only computes the MD5 of uncompressed data when a Content-MD5
header or multipart field is provided. Rust was always computing and
returning it. Also fix the mismatch error message to include size,
matching Go's format.
* fix save_vif to compute ExpireAtSec from TTL
Go's SaveVolumeInfo always computes ExpireAtSec = now + ttlSeconds
when the volume has a TTL. The save_vif path (used by set_read_only
and set_writable) was missing this computation, causing .vif files
to be written without the correct expiration timestamp for TTL volumes.
* fix set_writable to not modify no_write_can_delete
Go's MarkVolumeWritable only sets noWriteOrDelete=false and persists.
Rust was additionally setting no_write_can_delete=has_remote_file,
which could incorrectly change the write mode for remote-file volumes
when the master explicitly asks to make the volume writable.
* fix write_needle_blob_and_index to error on too-small V3 blob
Go returns an error when the needle blob is too small for timestamp
patching. Rust was silently skipping the patch and writing the blob
with a stale/zero timestamp, which could cause data integrity issues
during incremental replication that relies on AppendAtNs ordering.
* fix VolumeEcShardsToVolume to validate dataShards range
Go validates that dataShards is > 0 and <= MaxShardCount before
proceeding with EC-to-volume reconstruction. Without this check,
a zero or excessively large data_shards value could cause confusing
downstream failures.
* fix destroy to use VolumeError::NotEmpty instead of generic Io error
The dedicated NotEmpty variant exists in the enum but was not being
used. This makes error matching consistent with Go's ErrVolumeNotEmpty.
* fix SetState to persist state to disk with rollback on failure
Go's State.Update saves VolumeServerState to a state.pb file after
each SetState call, and rolls back the in-memory state if persistence
fails. Rust was only updating in-memory atomics, so maintenance mode
would be lost on server restart. Now saves protobuf-encoded state.pb
and loads it on startup.
* fix VolumeTierMoveDatToRemote to close local dat backend after upload
Go calls v.LoadRemoteFile() after saving volume info, which closes
the local DataBackend before transitioning to remote storage. Without
this, the volume holds a stale file handle to the deleted local .dat
file, causing reads to fail until server restart.
* fix VolumeTierMoveDatFromRemote to close remote dat backend after download
Go calls v.DataBackend.Close() and sets DataBackend=nil after removing
the remote file reference. Without this, the stale remote backend
state lingers and reads may not discover the newly downloaded local
.dat file until server restart.
* fix redirect to use internal url instead of public_url
Go's proxyReqToTargetServer builds the redirect Location header from
loc.Url (the internal URL), not publicUrl. Using public_url could
cause redirect failures when internal and external URLs differ.
* fix redirect test and add state_file_path to integration test
Update redirect unit test to expect internal url (matching the
previous fix). Add missing state_file_path field to the integration
test VolumeServerState constructor.
* fix FetchAndWriteNeedle to await all writes before checking errors
Go uses a WaitGroup to await all writes (local + replicas) before
checking errors. Rust was short-circuiting on local write failure,
which could leave replica writes in-flight without waiting for
completion.
* fix shutdown to send deregister heartbeat before pre_stop delay
Go's StopHeartbeat() closes stopChan immediately on interrupt, causing
the heartbeat goroutine to send the deregister heartbeat right away,
before the preStopSeconds delay. Rust was only setting is_stopping=true
without waking the heartbeat loop, so the deregister was delayed until
after the pre_stop sleep. Now we call volume_state_notify.notify_one()
to wake the heartbeat immediately.
* fix heartbeat response ordering to check duplicate UUIDs first
Go processes heartbeat responses in this order: DuplicatedUuids first,
then volume options (prealloc/size limit), then leader redirect. Rust
was applying volume options before checking for duplicate UUIDs, which
meant volume option changes would take effect even when the response
contained a duplicate UUID error that should cause an immediate return.
* the test thread was blocked
* fix(deps): update aws-lc-sys 0.38.0 → 0.39.0 to resolve security advisories
Bumps aws-lc-rs 1.16.1 → 1.16.2, pulling in aws-lc-sys 0.39.0 which
fixes GHSA-394x-vwmw-crm3 (X.509 Name Constraints wildcard/unicode
bypass) and GHSA-9f94-5g5w-gf6r (CRL Distribution Point scope check
logic error).
* fix: match Go Content-MD5 mismatch error message format
Go uses "Content-MD5 did not match md5 of file data expected [X]
received [Y] size Z" while Rust had a shorter format. Match the
exact Go error string so clients see identical messages.
* fix: match Go Bearer token length check (> 7, not >= 7)
Go requires len(bearer) > 7 ensuring at least one char after
"Bearer ". Rust used >= 7 which would accept an empty token.
* fix(deps): drop legacy rustls 0.21 to resolve rustls-webpki GHSA-pwjx-qhcg-rvj4
aws-sdk-s3's default "rustls" feature enables tls-rustls in
aws-smithy-runtime, which pulls in legacy-rustls-ring (rustls 0.21
→ rustls-webpki 0.101.7, moderate CRL advisory). Replace with
explicit default-https-client which uses only rustls 0.23 /
rustls-webpki 0.103.9.
* fix: use uploaded filename for auto-compression extension detection
Go extracts the file extension from pu.FileName (the uploaded
filename) for auto-compression decisions. Rust was using the URL
path, which typically has no extension for SeaweedFS file IDs.
* fix: add CRC legacy Value() backward-compat check on needle read
Go double-checks CRC: n.Checksum != crc && uint32(n.Checksum) !=
crc.Value(). The Value() path is a deprecated transform for compat
with seaweed versions prior to commit
|
||
|
Chris Lu
|
5fa5507234 |
Add Prometheus metric to count upload errors (#8788)
Add Prometheus metric to count upload errors (#8775) Add SeaweedFS_upload_error_total counter labeled by HTTP status code, so operators can alert on write/replication failures. Code "0" indicates a transport error (no HTTP response received). Also add an "Upload Errors" panel to the Grafana dashboard. |
||
|
Chris Luandcoderabbitai[bot]
|
17028fbf59 |
fix: serialize SSE-KMS metadata when bucket default encryption applies KMS (#8780)
* fix: serialize SSE-KMS metadata when bucket default encryption applies KMS When a bucket has default SSE-KMS encryption enabled and a file is uploaded without explicit SSE headers, the encryption was applied correctly but the SSE-KMS metadata (x-seaweedfs-sse-kms-key) was not serialized. This caused downloads to fail with "empty SSE-KMS metadata" because the entry's Extended map stored an empty byte slice. The existing code already handled this for SSE-S3 bucket defaults (SerializeSSES3Metadata) but was missing the equivalent call to SerializeSSEKMSMetadata for the KMS path. Fixes seaweedfs/seaweedfs#8776 * ci: add KMS integration tests to GitHub Actions Add a kms-tests.yml workflow that runs on changes to KMS/SSE code with two jobs: 1. KMS provider tests: starts OpenBao via Docker, runs Go integration tests in test/kms/ against a real KMS backend 2. S3 KMS e2e tests: starts OpenBao + weed mini built from source, runs test_s3_kms.sh which covers bucket-default SSE-KMS upload/download (the exact scenario from #8776) Supporting changes: - test/kms/Makefile: add CI targets (test-provider-ci, test-s3-kms-ci) that manage OpenBao via plain Docker and run weed from source - test/kms/s3-config-openbao-template.json: S3 config template with OpenBao KMS provider for weed mini * refactor: combine SSE-S3 and SSE-KMS metadata serialization into else-if SSE-S3 and SSE-KMS bucket default encryption are mutually exclusive, so use a single if/else-if block instead of two independent if blocks. * Update .github/workflows/kms-tests.yml Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com> * fix(ci): start weed mini from data dir to avoid Docker filer.toml weed mini reads filer.toml from the current working directory first. When running from test/kms/, it picked up the Docker-targeted filer.toml which has dir="/data/filerdb" (a path that doesn't exist in CI), causing a fatal crash at filer store initialization. Fix by cd-ing to the data directory before starting weed mini. Also improve log visibility on failure. --------- Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com> |
||
|
Chris Lu
|
3a3fff1399 |
Fix TUS chunked upload and resume failures (#8783) (#8786)
* Fix TUS chunked upload and resume failures caused by request context cancellation (#8783) The filer's TCP connections use a 10-second inactivity timeout (net_timeout.go). After the TUS PATCH request body is fully consumed, internal operations (assigning file IDs via gRPC to the master, uploading data to volume servers, completing uploads) do not generate any activity on the client connection, so the inactivity timer fires and Go's HTTP server cancels the request context. This caused HTTP 500 errors on PATCH requests where body reading + internal processing exceeded the timeout. Fix by using context.WithoutCancel in TUS create and patch handlers, matching the existing pattern used by assignNewFileInfo. This ensures internal operations complete regardless of client connection state. Fixes seaweedfs/seaweedfs#8783 * Add comment to tusCreateHandler explaining context.WithoutCancel rationale * Run TUS integration tests on all PRs, not just TUS file changes The previous path filter meant these tests only ran when TUS-specific files changed. This allowed regressions from changes to shared infrastructure (net_timeout.go, upload paths, gRPC) to go undetected — which is exactly how the context cancellation bug in #8783 was missed. Matches the pattern used by s3-go-tests.yml. |
||
|
Chris LuandCopilot
|
92c2fc0d52 |
Add insecure_skip_verify option for HTTPS client in security.toml (#8781)
* Add -insecureSkipVerify flag and config option for filer.sync HTTPS connections When using filer.sync between clusters with different CAs (e.g., separate OpenShift clusters), TLS certificate verification fails with "x509: certificate signed by unknown authority". This adds two ways to skip TLS certificate verification: 1. CLI flag: `weed filer.sync -insecureSkipVerify ...` 2. Config option: `insecure_skip_verify = true` under [https.client] in security.toml Closes #8778 * Add insecure_skip_verify option for HTTPS client in security.toml When using filer.sync between clusters with different CAs (e.g., separate OpenShift clusters), TLS certificate verification fails. Adding insecure_skip_verify = true under [https.client] in security.toml allows skipping TLS certificate verification. The option is read during global HTTP client initialization so it applies to all HTTPS connections including filer.sync proxy reads and writes. Closes #8778 --------- Co-authored-by: Copilot <copilot@github.com> |
||
|
Chris Lu
|
aa12b51cbf |
test: restore coverage removed in PR #8360 (#8779)
* test: restore maintenance mode coverage in TestVolumeMarkReadonlyWritableErrorPaths PR #8360 removed the maintenance mode assertions because the refactored check ordering (volume lookup before maintenance check) caused the original test to hit "not found" instead of "maintenance mode" — the test used a non-existent volume ID. Restore coverage by allocating a real volume, then verifying: - existing volume in maintenance mode returns "maintenance mode" - non-existent volume in maintenance mode still returns "not found" (validating the new check ordering) * test: add coverage for ScrubVolume MarkBrokenVolumesReadonly flag PR #8360 added the mark_broken_volumes_readonly field to ScrubVolumeRequest but no tests exercised the new logic paths. Add three integration tests: - HealthyVolume: flag is a no-op when scrub finds no broken volumes - CorruptVolume: corrupted .idx triggers broken detection; without the flag the volume stays writable, with the flag it becomes read-only - MaintenanceMode: makeVolumeReadonly fails under maintenance and ScrubVolume propagates the error via errors.Join * refactor: extract CorruptIndexFile and EnableMaintenanceMode test helpers Move duplicated idx corruption and maintenance mode setup into framework.CorruptIndexFile() and framework.EnableMaintenanceMode() helpers. Use defer for file close in the corruption helper. |
||
|
Chris Lu
|
ccc662b90b |
shell: add s3.bucket.access command for anonymous access policy (#8774)
* shell: add s3.bucket.access command for anonymous access policy (#7738) Add a new weed shell command to view or change the anonymous access policy of an S3 bucket without external tools. Usage: s3.bucket.access -name <bucket> -access read,list s3.bucket.access -name <bucket> -access none Supported permissions: read, write, list. The command writes a standard bucket policy with Principal "*" and warns if no anonymous IAM identity exists. * shell: fix anonymous identity hint in s3.bucket.access warning The anonymous identity doesn't need IAM actions — the bucket policy controls what anonymous users can do. * shell: only warn about anonymous identity when write access is set Read and list operations use AuthWithPublicRead which evaluates bucket policies directly without requiring the anonymous identity. Only write operations go through the normal auth flow that needs it. * shell: rewrite s3.bucket.access to use IAM actions instead of bucket policies Replace the bucket policy approach with direct IAM identity actions, matching the s3.configure pattern. The user is auto-created if it does not exist. Usage: s3.bucket.access -name <bucket> -user anonymous -access Read,List s3.bucket.access -name <bucket> -user anonymous -access none s3.bucket.access -name <bucket> -user anonymous Actions are stored as "Action:bucket" on the identity, same as s3.configure -actions=Read -buckets=my-bucket. * shell: return flag parse errors instead of swallowing them * shell: normalize action names case-insensitively in s3.bucket.access Accept actions in any case (read, READ, Read) and normalize to canonical form (Read, Write, List, etc.) before storing. This matches the case-insensitive handling of "none" and avoids confusing rejections. |
||
|
Chris Lu
|
67a551fd62 |
admin UI: add anonymous user creation checkbox (#8773)
Add an "Anonymous" checkbox next to the username field in the Create User modal. When checked, the username is set to "anonymous" and the credential generation checkbox is disabled since anonymous users do not need keys. The checkbox is only shown when no anonymous user exists yet. The manage-access-keys button in the users table is hidden for the anonymous user. |
||
|
Chris Lu
|
94bfa2b340 |
mount: stream all filer mutations over single ordered gRPC stream (#8770)
* filer: add StreamMutateEntry bidi streaming RPC Add a bidirectional streaming RPC that carries all filer mutation types (create, update, delete, rename) over a single ordered stream. This eliminates per-request connection overhead for pipelined operations and guarantees mutation ordering within a stream. The server handler delegates each request to the existing unary handlers (CreateEntry, UpdateEntry, DeleteEntry) and uses a proxy stream adapter for rename operations to reuse StreamRenameEntry logic. The is_last field signals completion for multi-response operations (rename sends multiple events per request; create/update/delete always send exactly one response with is_last=true). * mount: add streaming mutation multiplexer (streamMutateMux) Implement a client-side multiplexer that routes all filer mutation RPCs (create, update, delete, rename) over a single bidirectional gRPC stream. Multiple goroutines submit requests through a send channel; a dedicated sendLoop serializes them on the stream; a recvLoop dispatches responses to waiting callers via per-request channels. Key features: - Lazy stream opening on first use - Automatic reconnection on stream failure - Permanent fallback to unary RPCs if filer returns Unimplemented - Monotonic request_id for response correlation - Multi-response support for rename operations (is_last signaling) The mux is initialized on WFS and closed during unmount cleanup. No call sites use it yet — wiring comes in subsequent commits. * mount: route CreateEntry and UpdateEntry through streaming mux Wire all CreateEntry call sites to use wfs.streamCreateEntry() which routes through the StreamMutateEntry stream when available, falling back to unary RPCs otherwise. Also wire Link's UpdateEntry calls through wfs.streamUpdateEntry(). Updated call sites: - flushMetadataToFiler (file flush after write) - Mkdir (directory creation) - Symlink (symbolic link creation) - createRegularFile non-deferred path (Mknod) - flushFileMetadata (periodic metadata flush) - Link (hard link: update source + create link + rollback) * mount: route UpdateEntry and DeleteEntry through streaming mux Wire remaining mutation call sites through the streaming mux: - saveEntry (Setattr/chmod/chown/utimes) → streamUpdateEntry - Unlink → streamDeleteEntry (replaces RemoveWithResponse) - Rmdir → streamDeleteEntry (replaces RemoveWithResponse) All filer mutations except Rename now go through StreamMutateEntry when the filer supports it, with automatic unary RPC fallback. * mount: route Rename through streaming mux Wire Rename to use streamMutate.Rename() when available, with fallback to the existing StreamRenameEntry unary stream. The streaming mux sends rename as a StreamRenameEntryRequest oneof variant. The server processes it through the existing rename logic and sends multiple StreamRenameEntryResponse events (one per moved entry), with is_last=true on the final response. All filer mutations now go through a single ordered stream. * mount: fix stream mux connection ownership WithGrpcClient(streamingMode=true) closes the gRPC connection when the callback returns, destroying the stream. Own the connection directly via pb.GrpcDial so it stays alive for the stream's lifetime. Close it explicitly in recvLoop on stream failure and in Close on shutdown. * mount: fix rename failure for deferred-create files Three fixes for rename operations over the streaming mux: 1. lookupEntry: fall back to local metadata store when filer returns "not found" for entries in uncached directories. Files created with deferFilerCreate=true exist only in the local leveldb store until flushed; lookupEntry skipped the local store when the parent directory had never been readdir'd, causing rename to fail with ENOENT. 2. Rename: wait for pending async flushes and force synchronous flush of dirty metadata before sending rename to the filer. Covers the writebackCache case where close() defers the flush to a background worker that may not complete before rename fires. 3. StreamMutateEntry: propagate rename errors from server to client. Add error/errno fields to StreamMutateEntryResponse so the mount can map filer errors to correct FUSE status codes instead of silently returning OK. Also fix the existing Rename error handler which could return fuse.OK on unrecognized errors. * mount: fix streaming mux error handling, sendLoop lifecycle, and fallback Address PR review comments: 1. Server: populate top-level Error/Errno on StreamMutateEntryResponse for create/update/delete errors, not just rename. Previously update errors were silently dropped and create/delete errors were only in nested response fields that the client didn't check. 2. Client: check nested error fields in CreateEntry (ErrorCode, Error) and DeleteEntry (Error) responses, matching CreateEntryWithResponse behavior. 3. Fix sendLoop lifecycle: give each stream generation a stopSend channel. recvLoop closes it on error to stop the paired sendLoop. Previously a reconnect left the old sendLoop draining sendCh, breaking ordering. 4. Transparent fallback: stream helpers and doRename fall back to unary RPCs on transport errors (ErrStreamTransport), including the first Unimplemented from ensureStream. Previously the first call failed instead of degrading. 5. Filer rotation in openStream: try all filer addresses on dial failure, matching WithFilerClient behavior. Stop early on Unimplemented. 6. Pass metadata-bearing context to StreamMutateEntry RPC call so sw-client-id header is actually sent. 7. Gate lookupEntry local-cache fallback on open dirty handle or pending async flush to avoid resurrecting deleted/renamed entries. 8. Remove dead code in flushFileMetadata (err=nil followed by if err!=nil). 9. Use string matching for rename error-to-errno mapping in the mount to stay portable across Linux/macOS (numeric errno values differ). * mount: make failAllPending idempotent with delete-before-close Change failAllPending to collect pending entries into a local slice (deleting from the sync.Map first) before closing channels. This prevents double-close panics if called concurrently. Also remove the unused err parameter. * mount: add stream generation tracking and teardownStream Introduce a generation counter on streamMutateMux that increments each time a new stream is created. Requests carry the generation they were enqueued for so sendLoop can reject stale requests after reconnect. Add teardownStream(gen) which is idempotent (only acts when gen matches current generation and stream is non-nil). Both sendLoop and recvLoop call it on error, replacing the inline cleanup in recvLoop. sendLoop now actively triggers teardown on send errors instead of silently exiting. ensureStream waits for the prior generation's recvDone before creating a new stream, ensuring all old pending waiters are failed before reconnect. recvLoop now takes the stream, generation, and recvDone channel as parameters to avoid accessing shared fields without the lock. * mount: harden Close to prevent races with teardownStream Nil out stream, cancel, and grpcConn under the lock so that any concurrent teardownStream call from recvLoop/sendLoop becomes a no-op. Call failAllPending before closing sendCh to unblock waiters promptly. Guard recvDone with a nil check for the case where Close is called before any stream was ever opened. * mount: make errCh receive ctx-aware in doUnary and Rename Replace the blocking <-sendReq.errCh with a select that also observes ctx.Done(). If sendLoop exits via stopSend without consuming a buffered request, the caller now returns ctx.Err() instead of blocking forever. The buffered errCh (capacity 1) ensures late acknowledgements from sendLoop don't block the sender. * mount: fix sendLoop/Close race and recvLoop/teardown pending channel race Three related fixes: 1. Stop closing sendCh in Close(). Closing the shared producer channel races with callers who passed ensureStream() but haven't sent yet, causing send-on-closed-channel panics. sendCh is now left open; ensureStream checks m.closed to reject new callers. 2. Drain buffered sendCh items on shutdown. sendLoop defers drainSendCh() on exit so buffered requests get an ErrStreamTransport on their errCh instead of blocking forever. Close() drains again for any stragglers enqueued between sendLoop's drain and the final shutdown. 3. Move failAllPending from teardownStream into recvLoop's defer. teardownStream (called from sendLoop on send error) was closing pending response channels while recvLoop could be between pending.Load and the channel send — a send-on-closed-channel panic. recvLoop is now the sole closer of pending channels, eliminating the race. Close() waits on recvDone (with cancel() to guarantee Recv unblocks) so pending cleanup always completes. * filer/mount: add debug logging for hardlink lifecycle Add V(0) logging at every point where a HardLinkId is created, stored, read, or deleted to trace orphaned hardlink references. Logging covers: - gRPC server: CreateEntry/UpdateEntry when request carries HardLinkId - FilerStoreWrapper: InsertEntry/UpdateEntry when entry has HardLinkId - handleUpdateToHardLinks: entry path, HardLinkId, counter, chunk count - setHardLink: KvPut with blob size - maybeReadHardLink: V(1) on read attempt and successful decode - DeleteHardLink: counter decrement/deletion events - Mount Link(): when NewHardLinkId is generated and link is created This helps diagnose how a git pack .rev file ended up with a HardLinkId during a clone (no hard links should be involved). * test: add git clone/pull integration test for FUSE mount Shell script that exercises git operations on a SeaweedFS mount: 1. Creates a bare repo on the mount 2. Clones locally, makes 3 commits, pushes to mount 3. Clones from mount bare repo into an on-mount working dir 4. Verifies clone integrity (files, content, commit hashes) 5. Pushes 2 more commits with renames and deletes 6. Checks out an older revision on the mount clone 7. Returns to branch and pulls with real changes 8. Verifies file content, renames, deletes after pull 9. Checks git log integrity and clean status 27 assertions covering file existence, content, commit hashes, file counts, renames, deletes, and git status. Run against any existing mount: bash test-git-on-mount.sh /path/to/mount * test: add git clone/pull FUSE integration test to CI suite Add TestGitOperations to the existing fuse_integration test framework. The test exercises git's full file operation surface on the mount: 1. Creates a bare repo on the mount (acts as remote) 2. Clones locally, makes 3 commits (files, bulk data, renames), pushes 3. Clones from mount bare repo into an on-mount working dir 4. Verifies clone integrity (content, commit hash, file count) 5. Pushes 2 more commits with new files, renames, and deletes 6. Checks out an older revision on the mount clone 7. Returns to branch and pulls with real fast-forward changes 8. Verifies post-pull state: content, renames, deletes, file counts 9. Checks git log integrity (5 commits) and clean status Runs automatically in the existing fuse-integration.yml CI workflow. * mount: fix permission check with uid/gid mapping The permission checks in createRegularFile() and Access() compared the caller's local uid/gid against the entry's filer-side uid/gid without applying the uid/gid mapper. With -map.uid 501:0, a directory created as uid 0 on the filer would not match the local caller uid 501, causing hasAccess() to fall through to "other" permission bits and reject write access (0755 → other has r-x, no w). Fix: map entry uid/gid from filer-space to local-space before the hasAccess() call so both sides are in the same namespace. This fixes rsync -a failing with "Permission denied" on mkstempat when using uid/gid mapping. * mount: fix Mkdir/Symlink returning filer-side uid/gid to kernel Mkdir and Symlink used `defer wfs.mapPbIdFromFilerToLocal(entry)` to restore local uid/gid, but `outputPbEntry` writes the kernel response before the function returns — so the kernel received filer-side uid/gid (e.g., 0:0). macFUSE then caches these and rejects subsequent child operations (mkdir, create) because the caller uid (501) doesn't match the directory owner (0), and "other" bits (0755 → r-x) lack write permission. Fix: replace the defer with an explicit call to mapPbIdFromFilerToLocal before outputPbEntry, so the kernel gets local uid/gid. Also add nil guards for UidGidMapper in Access and createRegularFile to prevent panics in tests that don't configure a mapper. This fixes rsync -a "Permission denied" on mkpathat for nested directories when using uid/gid mapping. * mount: fix Link outputting filer-side uid/gid to kernel, add nil guards Link had the same defer-before-outputPbEntry bug as Mkdir and Symlink: the kernel received filer-side uid/gid because the defer hadn't run yet when outputPbEntry wrote the response. Also add nil guards for UidGidMapper in Access and createRegularFile so tests without a mapper don't panic. Audit of all outputPbEntry/outputFilerEntry call sites: - Mkdir: fixed in prior commit (explicit map before output) - Symlink: fixed in prior commit (explicit map before output) - Link: fixed here (explicit map before output) - Create (existing file): entry from maybeLoadEntry (already mapped) - Create (deferred): entry has local uid/gid (never mapped to filer) - Create (non-deferred): createRegularFile defer runs before return - Mknod: createRegularFile defer runs before return - Lookup: entry from lookupEntry (already mapped) - GetAttr: entry from maybeReadEntry/maybeLoadEntry (already mapped) - readdir: entry from cache (mapIdFromFilerToLocal) or filer (mapped) - saveEntry: no kernel output - flushMetadataToFiler: no kernel output - flushFileMetadata: no kernel output * test: fix git test for same-filesystem FUSE clone When both the bare repo and working clone live on the same FUSE mount, git's local transport uses hardlinks and cross-repo stat calls that fail on FUSE. Fix: - Use --no-local on clone to disable local transport optimizations - Use reset --hard instead of checkout to stay on branch - Use fetch + reset --hard origin/<branch> instead of git pull to avoid local transport stat failures during fetch * adjust logging * test: use plain git clone/pull to exercise real FUSE behavior Remove --no-local and fetch+reset workarounds. The test should use the same git commands users run (clone, reset --hard, pull) so it reveals real FUSE issues rather than hiding them. * test: enable V(1) logging for filer/mount and collect logs on failure - Run filer and mount with -v=1 so hardlink lifecycle logs (V(0): create/delete/insert, V(1): read attempts) are captured - On test failure, automatically dump last 16KB of all process logs (master, volume, filer, mount) to test output - Copy process logs to /tmp/seaweedfs-fuse-logs/ for CI artifact upload - Update CI workflow to upload SeaweedFS process logs alongside test output * mount: clone entry for filer flush to prevent uid/gid race flushMetadataToFiler and flushFileMetadata used entry.GetEntry() which returns the file handle's live proto entry pointer, then mutated it in-place via mapPbIdFromLocalToFiler. During the gRPC call window, a concurrent Lookup (which takes entryLock.RLock but NOT fhLockTable) could observe filer-side uid/gid (e.g., 0:0) on the file handle entry and return it to the kernel. The kernel caches these attributes, so subsequent opens by the local user (uid 501) fail with EACCES. Fix: proto.Clone the entry before mapping uid/gid for the filer request. The file handle's live entry is never mutated, so concurrent Lookup always sees local uid/gid. This fixes the intermittent "Permission denied" on .git/FETCH_HEAD after the first git pull on a mount with uid/gid mapping. * mount: add debug logging for stale lock file investigation Add V(0) logging to trace the HEAD.lock recreation issue: - Create: log when O_EXCL fails (file already exists) with uid/gid/mode - completeAsyncFlush: log resolved path, saved path, dirtyMetadata, isDeleted at entry to trace whether async flush fires after rename - flushMetadataToFiler: log the dir/name/fullpath being flushed This will show whether the async flush is recreating the lock file after git renames HEAD.lock → HEAD. * mount: prevent async flush from recreating renamed .lock files When git renames HEAD.lock → HEAD, the async flush from the prior close() can run AFTER the rename and re-insert HEAD.lock into the meta cache via its CreateEntryRequest response event. The next git pull then sees HEAD.lock and fails with "File exists". Fix: add isRenamed flag on FileHandle, set by Rename before waiting for the pending async flush. The async flush checks this flag and skips the metadata flush for renamed files (same pattern as isDeleted for unlinked files). The data pages still flush normally. The Rename handler flushes deferred metadata synchronously (Case 1) before setting isRenamed, ensuring the entry exists on the filer for the rename to proceed. For already-released handles (Case 2), the entry was created by a prior flush. * mount: also mark renamed inodes via entry.Attributes.Inode fallback When GetInode fails (Forget already removed the inode mapping), the Rename handler couldn't find the pending async flush to set isRenamed. The async flush then recreated the .lock file on the filer. Fix: fall back to oldEntry.Attributes.Inode to find the pending async flush when the inode-to-path mapping is gone. Also extract MarkInodeRenamed into a method on FileHandleToInode for clarity. * mount: skip async metadata flush when saved path no longer maps to inode The isRenamed flag approach failed for refs/remotes/origin/HEAD.lock because neither GetInode nor oldEntry.Attributes.Inode could find the inode (Forget already evicted the mapping, and the entry's stored inode was 0). Add a direct check in completeAsyncFlush: before flushing metadata, verify that the saved path still maps to this inode in the inode-to-path table. If the path was renamed or removed (inode mismatch or not found), skip the metadata flush to avoid recreating a stale entry. This catches all rename cases regardless of whether the Rename handler could set the isRenamed flag. * mount: wait for pending async flush in Unlink before filer delete Unlink was deleting the filer entry first, then marking the draining async-flush handle as deleted. The async flush worker could race between these two operations and recreate the just-unlinked entry on the filer. This caused git's .lock files (e.g. refs/remotes/origin/HEAD.lock) to persist after git pull, breaking subsequent git operations. Move the isDeleted marking and add waitForPendingAsyncFlush() before the filer delete so any in-flight flush completes first. Even if the worker raced past the isDeleted check, the wait ensures it finishes before the filer delete cleans up any recreated entry. * mount: reduce async flush and metadata flush log verbosity Raise completeAsyncFlush entry log, saved-path-mismatch skip log, and flushMetadataToFiler entry log from V(0) to V(3)/V(4). These fire for every file close with writebackCache and are too noisy for normal use. * filer: reduce hardlink debug log verbosity from V(0) to V(4) HardLinkId logs in filerstore_wrapper, filerstore_hardlink, and filer_grpc_server fire on every hardlinked file operation (git pack files use hardlinks extensively) and produce excessive noise. * mount/filer: reduce noisy V(0) logs for link, rmdir, and empty folder check - weedfs_link.go: hardlink creation logs V(0) → V(4) - weedfs_dir_mkrm.go: non-empty folder rmdir error V(0) → V(1) - empty_folder_cleaner.go: "not empty" check log V(0) → V(4) * filer: handle missing hardlink KV as expected, not error A "kv: not found" on hardlink read is normal when the link blob was already cleaned up but a stale entry still references it. Log at V(1) for not-found; keep Error level for actual KV failures. * test: add waitForDir before git pull in FUSE git operations test After git reset --hard, the FUSE mount's metadata cache may need a moment to settle on slow CI. The git pull subprocess (unpack-objects) could fail to stat the working directory. Poll for up to 5s. * Update git_operations_test.go * wait * test: simplify FUSE test framework to use weed mini Replace the 4-process setup (master + volume + filer + mount) with 2 processes: "weed mini" (all-in-one) + "weed mount". This simplifies startup, reduces port allocation, and is faster on CI. * test: fix mini flag -admin → -admin.ui |
||
|
Chris Lu
|
29bdbb3c48 |
filer.sync: replace O(n) conflict check with O(depth) index lookups (#8772)
* filer.sync: replace O(n) conflict check with O(depth) index lookups The MetadataProcessor.conflictsWith() scanned all active jobs linearly for every new event dispatch. At high concurrency (256-1024), this O(n) scan under the activeJobsLock became a bottleneck that throttled the event dispatch pipeline, negating the benefit of higher -concurrency values. Replace the linear scan with three index maps: - activeFilePaths: O(1) exact file path lookup - activeDirPaths: O(1) directory path lookup per ancestor - descendantCount: O(1) check for active jobs under a directory Conflict check is now O(depth) where depth is the path depth (typically 3-6 levels), constant regardless of active job count. Benchmark confirms ~81ns per check whether there are 32 or 1024 active jobs. Also replace the O(n) watermark scan with minActiveTs tracking so non-oldest job completions are O(1). Ref: #8771 * filer.sync: replace O(n) watermark rescan with min-heap lazy deletion Address review feedback: - Replace minActiveTs O(n) rescan with a tsMinHeap using lazy deletion. Each TsNs is pushed once and popped once, giving O(log n) amortized watermark tracking regardless of completion order. - Fix benchmark to consume conflictsWith result via package-level sink variable to prevent compiler elision. The watermark advancement semantics (conservative, sets to completing job's TsNs) are unchanged from the original code. This is intentionally safe for idempotent replay on restart. |
||
|
Chris Lu
|
e47054a7e7 |
mount: improve small file write performance (#8769)
* mount: defer file creation gRPC to flush time for faster small file writes When creating a file via FUSE Create(), skip the synchronous gRPC CreateEntry call to the filer. Instead, allocate the inode and build the entry locally, deferring the filer create to the Flush/Release path where flushMetadataToFiler already sends a CreateEntry with chunk data. This eliminates one synchronous gRPC round-trip per file during creation. For workloads with many small files (e.g. 30K files), this reduces the per-file overhead from ~2 gRPC calls to ~1. Mknod retains synchronous filer creation since it has no file handle and thus no flush path. * mount: use bounded worker pool for async flush operations Replace unbounded goroutine spawning in writebackCache async flush with a fixed-size worker pool backed by a channel. When many files are closed rapidly (e.g., cp -r of 30K files), the previous approach spawned one goroutine per file, leading to resource contention on gRPC/HTTP connections and high goroutine overhead. The worker pool size matches ConcurrentWriters (default 128), which provides good parallelism while bounding resource usage. Work items are queued into a buffered channel and processed by persistent worker goroutines. * mount: fix deferred create cache visibility and async flush race Three fixes for the deferred create and async flush changes: 1. Insert a local placeholder entry into the metadata cache during deferred file creation so that maybeLoadEntry() can find the file for duplicate-create checks, stat, and readdir. Uses InsertEntry directly (not applyLocalMetadataEvent) to avoid triggering the directory hot-threshold eviction that would wipe the entry. 2. Fix race in ReleaseHandle where asyncFlushWg.Add(1) and the channel send happened after pendingAsyncFlushMu was unlocked. A concurrent WaitForAsyncFlush could observe a zero counter, close the channel, and cause a send-on-closed panic. Move Add(1) before the unlock; keep the send after unlock to avoid deadlock with workers that acquire the same mutex during cleanup. 3. Update TestCreateCreatesAndOpensFile to flush the file handle before verifying the CreateEntry gRPC call, since file creation is now deferred to flush time. |
||
|
Chris LuandCopilot
|
28fe92065a |
S3: reject part uploads after AbortMultipartUpload (#8768)
* S3: reject part uploads after AbortMultipartUpload PutObjectPartHandler did not verify that the multipart upload session still exists before accepting parts. After AbortMultipartUpload deleted the upload directory, the ErrNotFound from getEntry was silently ignored (treated as "may be non-SSE upload"), allowing parts to be stored as orphaned files. Now return ErrNoSuchUpload when the upload directory is not found, matching AWS S3 behavior. Fixes #8766 * S3: check upload existence unconditionally in PutObjectPartHandler Move the getEntry call out of the SSE-type conditional so the upload existence check runs for all part uploads, including SSE-C. Previously the SSE-C path skipped the check entirely, allowing parts to be uploaded after abort when SSE-C headers were present. Also flattens the nested SSE branching by one level now that getEntry is called once upfront. * S3: address PR review feedback for PutObjectPartHandler - Log at error level when getEntry fails with an unexpected error, since we return ErrInternalError to the client - Distinguish base IV decode errors from length validation failures with separate, clearer error messages --------- Co-authored-by: Copilot <copilot@github.com> |
||
|
Chris Lu
|
0b3867dca3 |
filer: add structured error codes to CreateEntryResponse (#8767)
* filer: add FilerError enum and error_code field to CreateEntryResponse Add a machine-readable error code alongside the existing string error field. This follows the precedent set by PublishMessageResponse in the MQ broker proto. The string field is kept for human readability and backward compatibility. Defined codes: OK, ENTRY_NAME_TOO_LONG, PARENT_IS_FILE, EXISTING_IS_DIRECTORY, EXISTING_IS_FILE, ENTRY_ALREADY_EXISTS. * filer: add sentinel errors and error code mapping in filer_pb Define sentinel errors (ErrEntryNameTooLong, ErrParentIsFile, etc.) in the filer_pb package so both the filer and consumers can reference them without circular imports. Add FilerErrorToSentinel() to map proto error codes to sentinels, and update CreateEntryWithResponse() to check error_code first, falling back to the string-based path for backward compatibility with old servers. * filer: return wrapped sentinel errors and set proto error codes Replace fmt.Errorf string errors in filer.CreateEntry, UpdateEntry, and ensureParentDirectoryEntry with wrapped filer_pb sentinel errors (using %w). This preserves errors.Is() traversal on the server side. In the gRPC CreateEntry handler, map sentinel errors to the corresponding FilerError proto codes using errors.Is(), setting both resp.Error (string, for backward compat) and resp.ErrorCode (enum). * S3: use errors.Is() with filer sentinels instead of string matching Replace fragile string-based error matching in filerErrorToS3Error and other S3 API consumers with errors.Is() checks against filer_pb sentinel errors. This works because the updated CreateEntryWithResponse helper reconstructs sentinel errors from the proto FilerError code. Update iceberg stage_create and metadata_files to check resp.ErrorCode instead of parsing resp.Error strings. Update SSE-S3 to use errors.Is() for the already-exists check. String matching is retained only for non-filer errors (gRPC transport errors, checksum validation) that don't go through CreateEntryResponse. * filer: remove backward-compat string fallbacks for error codes Clients and servers are always deployed together, so there is no need for backward-compatibility fallback paths that parse resp.Error strings when resp.ErrorCode is unset. Simplify all consumers to rely solely on the structured error code. * iceberg: ensure unknown non-OK error codes are not silently ignored When FilerErrorToSentinel returns nil for an unrecognized error code, return an error including the code and message rather than falling through to return nil. * filer: fix redundant error message and restore error wrapping in helper Use request path instead of resp.Error in the sentinel error format string to avoid duplicating the sentinel message (e.g. "entry already exists: entry already exists"). Restore %w wrapping with errors.New() in the fallback paths so callers can use errors.Is()/errors.As(). * filer: promote file to directory on path conflict instead of erroring S3 allows both "foo/bar" (object) and "foo/bar/xyzzy" (another object) to coexist because S3 has a flat key space. When ensureParentDirectoryEntry finds a parent path that is a file instead of a directory, promote it to a directory by setting ModeDir while preserving the original content and chunks. Use Store.UpdateEntry directly to bypass the Filer.UpdateEntry type-change guard. This fixes the S3 compatibility test failures where creating overlapping keys (e.g. "foo/bar" then "foo/bar/xyzzy") returned ExistingObjectIsFile. |
||
|
Chris Lu
|
152884eff2 |
S3: add s3: prefix to x-amz-* condition keys for AWS compatibility (#8765)
AWS S3 policy conditions reference request headers with the s3: namespace prefix (e.g., s3:x-amz-server-side-encryption). The extraction code was storing these headers without the prefix, so bucket policy conditions using the standard AWS key names would never match. |
||
|
Chris Lu
|
2877febd73 |
S3: fix silent PutObject failure and enforce 1024-byte key limit (#8764)
* S3: add KeyTooLongError error code Add ErrKeyTooLongError (HTTP 400, code "KeyTooLongError") to match the standard AWS S3 error for object keys that exceed length limits. * S3: fix silent PutObject failure when entry name exceeds max_file_name_length putToFiler called client.CreateEntry() directly and discarded the gRPC response. The filer embeds application errors like "entry name too long" in resp.Error (not as gRPC transport errors), so the error was silently swallowed and clients received HTTP 200 with an ETag for objects that were never stored. Switch to the filer_pb.CreateEntry() helper which properly checks resp.Error, and map "entry name too long" to KeyTooLongError (HTTP 400). To avoid fragile string parsing across the gRPC boundary, define shared error message constants in weed/util/constants and use them in both the filer (producing errors) and S3 API (matching errors). Switch filerErrorToS3Error to use strings.Contains/HasSuffix with these constants so matches work regardless of any wrapper prefix. Apply filerErrorToS3Error to the mkdir path for directory markers. Fixes #8759 * S3: enforce 1024-byte maximum object key length AWS S3 limits object keys to 1024 bytes. Add early validation on write paths (PutObject, CopyObject, CreateMultipartUpload) to reject keys exceeding the limit with the standard KeyTooLongError (HTTP 400). The key length check runs before bucket auto-creation to prevent overlong keys from triggering unnecessary side effects. Also use filerErrorToS3Error for CopyObject's mkFile error paths so name-too-long errors from the filer return KeyTooLongError instead of InternalError. Ref #8758 * S3: add handler-level tests for key length validation and error mapping Add tests for filerErrorToS3Error mapping "entry name too long" to KeyTooLongError, including a regression test for the CreateEntry-prefixed "existing ... is a directory" form. Add handler-level integration tests that exercise PutObjectHandler, CopyObjectHandler, and NewMultipartUploadHandler via httptest, verifying HTTP 400 and KeyTooLongError XML response for overlong keys and acceptance of keys at the 1024-byte limit. |
||
|
Chris Lu
|
7f3f61ea28 |
fix: resolve Kafka gateway response deadlocks causing Sarama client hangs (#8762)
* fix: resolve Kafka gateway response deadlocks causing Sarama client hangs
Fix three bugs in the Kafka protocol handler that caused sequential
clients (notably Sarama) to hang during E2E tests:
1. Race condition in correlation queue ordering: the correlation ID was
added to the response ordering queue AFTER sending the request to
the processing channel. A fast processor (e.g. ApiVersions) could
finish and send its response before the ID was in the queue, causing
the response writer to miss it — permanently deadlocking the
connection. Now the ID is added BEFORE the channel send, with error
response injection on send failure.
2. Silent error response drops: when processRequestSync returned an
error, the response writer logged it but never sent anything back to
the client. The client would block forever waiting for bytes that
never arrived. Now sends a Kafka UNKNOWN_SERVER_ERROR response.
3. Produce V0/V1 missing timeout_ms parsing: the handler skipped the
4-byte timeout field, reading it as topicsCount instead. This caused
incorrect parsing of the entire produce request for V0/V1 clients.
* fix: API-versioned error responses, unsupported-version queue fix, V0V1 header alignment
1. errors.go — BuildAPIErrorResponse: emits a minimal-but-valid error
body whose layout matches the schema the client expects for each API
key and version (throttle_time position, array fields, etc.). The
old 2-byte generic body corrupted the protocol stream for APIs whose
response begins with throttle_time_ms or an array.
2. handler.go — unsupported-version path: the correlationID was never
added to correlationQueue before sending to responseChan, so the
response writer could never match it and the client hung. Now
appends the ID under correlationQueueMu before the send.
3. produce.go — handleProduceV0V1: requestBody is already post-header
(HandleConn strips client_id). The handler was erroneously parsing
acks bytes as a client_id length, misaligning all subsequent field
reads. Removed the client_id parsing; offset now starts at 0 with
acks(2) + timeout_ms(4) + topicsCount(4), matching handleProduceV2Plus.
* fix: free pooled message buffer per-iteration instead of deferring
The read loop allocated messageBuf via mem.Allocate and deferred
mem.Free. Since the defer only runs when HandleConn returns, pool
buffers accumulated for the entire connection lifetime — one per
request. Worse, the deferred frees ran in LIFO order before
wg.Wait(), so processing goroutines could read from already-freed
pool buffers.
Now: read into a pooled buffer, immediately copy to Go-managed
memory, and return the pool buffer. messageBuf is a regular slice
safe for async goroutine access with no defer accumulation.
* fix: cancel context before wg.Wait and on worker response-send timeout
Two related issues:
1. Cleanup defer ordering deadlock: defers run LIFO — the cleanup defer
(close channels, wg.Wait) ran before the cancel() defer. The
response writer is in the WaitGroup and exits only on ctx.Done() or
responseChan close, but both signals came after wg.Wait(). Deadlock
on every normal connection close (EOF, read error, queue-full).
Fix: call cancel() at the start of the cleanup defer, before
wg.Wait().
2. Worker 5s response-send timeout: when the timeout fired, the
response was silently dropped but the correlationID remained in the
ordered queue. The response writer could never advance past it,
stalling all subsequent responses permanently.
Fix: call cancel() to tear down the connection — if we cannot
deliver a response in 5s the connection is irrecoverable.
* chore: remove empty no-op ListOffsets conditional
The `if apiKey == 2 {}` block had no body — leftover debug code.
ListOffsets routing is handled by isDataPlaneAPI (returns false,
sending it to the control channel). No behavior change.
|
||
|
Chris Lu
|
6c35a3724a | weed/mount: simplify metadata flush retry returns (#8763) | ||
|
Chris LuandCopilot
|
cca1555cc7 |
mount: implement create for rsync temp files (#8749)
* mount: implement create for rsync temp files * mount: move access implementation out of unsupported * mount: tighten access checks * mount: log access group lookup failures * mount: reset dirty pages on truncate * mount: tighten create and root access handling * mount: handle existing creates before quota checks * mount: restrict access fallback when group lookup fails When lookupSupplementaryGroupIDs returns an error, the previous code fell through to checking only the "other" permission bits, which could overgrant access. Require both group and other permission classes to satisfy the mask so access is never broader than intended. * mount: guard against nil entry in Create existing-file path maybeLoadEntry can return OK with a nil entry or nil Attributes in edge cases. Check before dereferencing to prevent a panic. * mount: reopen existing file on create race without O_EXCL When createRegularFile returns EEXIST because another process won the race, and O_EXCL is not set, reload the winner's entry and open it instead of propagating the error to the caller. * mount: check parent directory permission in createRegularFile Verify the caller has write+search (W_OK|X_OK) permission on the parent directory before creating a file. This applies to both Create and Mknod. Update test fixture mount mode to 0o777 so the existing tests pass with the new check. * mount: enforce file permission bits in AcquireHandle Map the open flags (O_RDONLY/O_WRONLY/O_RDWR) to an access mask and call hasAccess before handing out a file handle. This makes AcquireHandle the single source of truth for mode-based access control across Open, Create-existing, and Create-new paths. --------- Co-authored-by: Copilot <copilot@github.com> |
||
|
Chris Lu
|
805625d06e |
Add FUSE integration tests for POSIX file locking (#8752)
* Add FUSE integration tests for POSIX file locking Test flock() and fcntl() advisory locks over the FUSE mount: - Exclusive and shared flock with conflict detection - flock upgrade (shared to exclusive) and release on close - fcntl F_SETLK write lock conflicts and shared read locks - fcntl F_GETLK conflict reporting on overlapping byte ranges - Non-overlapping byte-range locks held independently - F_SETLKW blocking until conflicting lock is released - Lock release on file descriptor close - Concurrent lock contention with multiple workers * Fix review feedback in POSIX lock integration tests - Assert specific EAGAIN error on fcntl lock conflicts instead of generic Error - Use O_APPEND in concurrent contention test so workers append rather than overwrite - Verify exact line count (numWorkers * writesPerWorker) after concurrent test - Check unlock error in F_SETLKW blocking test goroutine * Refactor fcntl tests to use subprocesses for inter-process semantics POSIX fcntl locks use the process's files_struct as lock owner, so all fds in the same process share the same owner and never conflict. This caused the fcntl tests to silently pass without exercising lock conflicts. Changes: - Add TestFcntlLockHelper subprocess entry point with hold/try/getlk actions - Add lockHolder with channel-based coordination (no scanner race) - Rewrite all fcntl tests to run contenders in separate subprocesses - Fix F_UNLCK int16 cast in GetLk assertion for type-safe comparison - Fix concurrent test: use non-blocking flock with retry to avoid exhausting go-fuse server reader goroutines (blocking FUSE SETLKW can starve unlock request processing, causing deadlock) flock tests remain same-process since flock uses per-struct-file owners. * Fix misleading comment and error handling in lock test subprocess - Fix comment: tryLockInSubprocess tests a subprocess, not the test process - Distinguish EAGAIN/EACCES from unexpected errors in subprocess try mode so real failures aren't silently masked as lock conflicts * Fix CI race in FcntlReleaseOnClose and increase flock retry budget - FcntlReleaseOnClose: retry lock acquisition after subprocess exits since the FUSE server may not process Release immediately - ConcurrentLockContention: increase retry limit from 500 to 3000 (5s → 30s budget) to handle CI load * separating flock and fcntl in the in-memory lock table and cleaning them up through the right release path: PID for POSIX locks, lock owner for flock * ReleasePosixOwner * weed/mount: flush before releasing posix close owner * weed/mount: keep woken lock waiters from losing inode state * test/fuse: make blocking fcntl helper state explicit * test/fuse: assert flock contention never overlaps * test/fuse: stabilize concurrent lock contention check * test/fuse: make concurrent contention writes deterministic * weed/mount: retry synchronous metadata flushes |
||
|
Chris Lu
|
3d872e86f8 |
Implement POSIX file locking for FUSE mount (#8750)
* Add POSIX byte-range lock table for FUSE mount Implement PosixLockTable with per-inode range lock tracking supporting: - Shared (F_RDLCK) and exclusive (F_WRLCK) byte-range locks - Conflict detection across different lock owners - Lock coalescing for adjacent/overlapping same-owner same-type locks - Lock splitting on partial-range unlock - Blocking waiter support for SetLkw with cancellation - Owner-based cleanup for Release * Wire POSIX lock handlers into FUSE mount Implement GetLk, SetLk, SetLkw on WFS delegating to PosixLockTable. Add posixLocks field to WFS and initialize in constructor. Clean up locks on Release via ReleaseOwner using ReleaseIn.LockOwner. Remove ENOSYS stubs from weedfs_unsupported.go. * Enable POSIX and flock lock capabilities in FUSE mount Set EnableLocks: true in mount options to advertise CAP_POSIX_LOCKS and CAP_FLOCK_LOCKS during FUSE INIT. * Avoid thundering herd in lock waiter wake-up Replace broadcast-all wakeWaiters with selective wakeEligibleWaiters that checks each waiter's requested lock against remaining held locks. Only waiters whose request no longer conflicts are woken; others stay queued. Store the requested lockRange in each lockWaiter to enable this. * Fix uint64 overflow in adjacency check for lock coalescing Guard h.End+1 and lk.End+1 with < ^uint64(0) checks so that End == math.MaxUint64 (EOF) does not wrap to 0 and falsely merge non-adjacent locks. * Add test for non-adjacent ranges with gap not being coalesced |
||
|
Chris Lu
|
e5f72077ee |
fix: resolve CORS cache race condition causing stale 404 responses (#8748)
The metadata subscription handler (updateBucketConfigCacheFromEntry) was making a separate RPC call via loadCORSFromBucketContent to load CORS configuration. This created a race window where a slow CreateBucket subscription event could re-cache stale data after PutBucketCors had already cleared the cache, causing subsequent GetBucketCors to return 404 NoSuchCORSConfiguration. Parse CORS directly from the subscription entry's Content field instead of making a separate RPC. Also fix getBucketConfig to parse CORS from the already-fetched entry, eliminating a redundant RPC call. Fix TestCORSCaching to use require.NoError to prevent nil pointer dereference panics when GetBucketCors fails. |
||
|
Chris LuandCopilot
|
c31e6b4684 |
Use filer-side copy for mounted whole-file copy_file_range (#8747)
* Optimize mounted whole-file copy_file_range * Address mounted copy review feedback * Harden mounted copy fast path --------- Co-authored-by: Copilot <copilot@github.com> |
||
|
Chris Lu
|
6bf654c25c |
fix: keep metadata subscriptions progressing (#8730) (#8746)
* fix: keep metadata subscriptions progressing (#8730) * test: cancel slow metadata writers with parent context * filer: ignore missing persisted log chunks |
||
|
Chris Lu
|
d5ee35c8df |
Fix S3 delete for non-empty directory markers (#8740)
* Fix S3 delete for non-empty directory markers * Address review feedback on directory marker deletes * Stabilize FUSE concurrent directory operations |
||
|
Chris LuandCopilot
|
9434d3733d |
mount: async flush on close() when writebackCache is enabled (#8727)
* mount: async flush on close() when writebackCache is enabled When -writebackCache is enabled, defer data upload and metadata flush from Flush() (triggered by close()) to a background goroutine in Release(). This allows processes like rsync that write many small files to proceed to the next file immediately instead of blocking on two network round-trips (volume upload + filer metadata) per file. Fixes #8718 * mount: add retry with backoff for async metadata flush The metadata flush in completeAsyncFlush now retries up to 3 times with exponential backoff (1s, 2s, 4s) on transient gRPC errors. Since the chunk data is already safely on volume servers at this point, only the filer metadata reference needs persisting — retrying is both safe and effective. Data flush (FlushData) is not retried externally because UploadWithRetry already handles transient HTTP/gRPC errors internally; if it still fails, the chunk memory has been freed. * test: add integration tests for writebackCache async flush Add comprehensive FUSE integration tests for the writebackCache async flush feature (issue #8718): - Basic operations: write/read, sequential files, large files, empty files, overwrites - Fsync correctness: fsync forces synchronous flush even in writeback mode, immediate read-after-fsync - Concurrent small files: multi-worker parallel writes (rsync-like workload), multi-directory, rapid create/close - Data integrity: append after close, partial writes, file size correctness, binary data preservation - Performance comparison: writeback vs synchronous flush throughput - Stress test: 16 workers x 100 files with content verification - Mixed concurrent operations: reads, writes, creates running together Also fix pre-existing test infrastructure issues: - Rename framework.go to framework_test.go (fixes Go package conflict) - Fix undefined totalSize variable in concurrent_operations_test.go * ci: update fuse-integration workflow to run full test suite The workflow previously only ran placeholder tests (simple_test.go, working_demo_test.go) in a temp directory due to a Go module conflict. Now that framework.go is renamed to framework_test.go, the full test suite compiles and runs correctly from test/fuse_integration/. Changes: - Run go test directly in test/fuse_integration/ (no temp dir copy) - Install weed binary to /usr/local/bin for test framework discovery - Configure /etc/fuse.conf with user_allow_other for FUSE mounts - Install fuse3 for modern FUSE support - Stream test output to log file for artifact upload * mount: fix three P1 races in async flush P1-1: Reopen overwrites data still flushing in background ReleaseByHandle removes the old handle from fhMap before the deferred flush finishes. A reopen of the same inode during that window would build from stale filer metadata, overwriting the async flush. Fix: Track in-flight async flushes per inode via pendingAsyncFlush map. AcquireHandle now calls waitForPendingAsyncFlush(inode) to block until any pending flush completes before reading filer metadata. P1-2: Deferred flush races rename and unlink after close completeAsyncFlush captured the path once at entry, but rename or unlink after close() could cause metadata to be written under the wrong name or recreate a deleted file. Fix: Re-resolve path from inode via GetPath right before metadata flush. GetPath returns the current path (reflecting renames) or ENOENT (if unlinked), in which case we skip the metadata flush. P1-3: SIGINT/SIGTERM bypasses the async-flush drain grace.OnInterrupt runs hooks then calls os.Exit(0), so WaitForAsyncFlush after server.Serve() never executes on signal. Fix: Add WaitForAsyncFlush (with 10s timeout) to the WFS interrupt handler, before cache cleanup. The timeout prevents hanging on Ctrl-C when the filer is unreachable. * mount: fix P1 races — draining handle stays in fhMap P1-1: Reopen TOCTOU The gap between ReleaseByHandle removing from fhMap and submitAsyncFlush registering in pendingAsyncFlush allowed a concurrent AcquireHandle to slip through with stale metadata. Fix: Hold pendingAsyncFlushMu across both the counter decrement (ReleaseByHandle) and the pending registration. The handle is registered as pending before the lock is released, so waitForPendingAsyncFlush always sees it. P1-2: Rename/unlink can't find draining handle ReleaseByHandle deleted from fhMap immediately. Rename's FindFileHandle(inode) at line 251 could not find the handle to update entry.Name. Unlink could not coordinate either. Fix: When asyncFlushPending is true, ReleaseByHandle/ReleaseByInode leave the handle in fhMap (counter=0 but maps intact). The handle stays visible to FindFileHandle so rename can update entry.Name. completeAsyncFlush re-resolves the path from the inode (GetPath) right before metadata flush for correctness after rename/unlink. After drain, RemoveFileHandle cleans up the maps. Double-return prevention: ReleaseByHandle/ReleaseByInode return nil if counter is already <= 0, so Forget after Release doesn't start a second drain goroutine. P1-3: SIGINT deletes swap files under running goroutines After the 10s timeout, os.RemoveAll deleted the write cache dir (containing swap files) while FlushData goroutines were still reading from them. Fix: Increase timeout to 30s. If timeout expires, skip write cache dir removal so in-flight goroutines can finish reading swap files. The OS (or next mount) cleans them up. Read cache is always removed. * mount: never skip metadata flush when Forget drops inode mapping Forget removes the inode→path mapping when the kernel's lookup count reaches zero, but this does NOT mean the file was unlinked — it only means the kernel evicted its cache entry. completeAsyncFlush was treating GetPath failure as "file unlinked" and skipping the metadata flush, which orphaned the just-uploaded chunks for live files. Fix: Save dir and name at doFlush defer time. In completeAsyncFlush, try GetPath first to pick up renames; if the mapping is gone, fall back to the saved dir/name. Always attempt the metadata flush — the filer is the authority on whether the file exists, not the local inode cache. * mount: distinguish Forget from Unlink in async flush path fallback The saved-path fallback (from the previous fix) always flushed metadata when GetPath failed, which recreated files that were explicitly unlinked after close(). The same stale fallback could recreate the pre-rename path if Forget dropped the inode mapping after a rename. Root cause: GetPath failure has two meanings: 1. Forget — kernel evicted the cache entry (file still exists) 2. Unlink — file was explicitly deleted (should not recreate) Fix (three coordinated changes): Unlink (weedfs_file_mkrm.go): Before RemovePath, look up the inode and find any draining handle via FindFileHandle. Set fh.isDeleted = true so the async flush knows the file was explicitly removed. Rename (weedfs_rename.go): When renaming a file with a draining handle, update asyncFlushDir/asyncFlushName to the post-rename location. This keeps the saved-path fallback current so Forget after rename doesn't flush to the old (pre-rename) path. completeAsyncFlush (weedfs_async_flush.go): Check fh.isDeleted first — if true, skip metadata flush (file was unlinked, chunks become orphans for volume.fsck). Otherwise, try GetPath for the current path (renames); fall back to saved path if Forget dropped the mapping (file is live, just evicted from kernel cache). * test/ci: address PR review nitpicks concurrent_operations_test.go: - Restore precise totalSize assertion instead of info.Size() > 0 writeback_cache_test.go: - Check rand.Read errors in all 3 locations (lines 310, 512, 757) - Check os.MkdirAll error in stress test (line 752) - Remove dead verifyErrors variable (line 332) - Replace both time.Sleep(5s) with polling via waitForFileContent to avoid flaky tests under CI load (lines 638, 700) fuse-integration.yml: - Add set -o pipefail so go test failures propagate through tee * ci: fix fuse3/fuse package conflict on ubuntu-22.04 runner fuse3 is pre-installed on ubuntu-22.04 runners and conflicts with the legacy fuse package. Only install libfuse3-dev for the headers. * mount/page_writer: remove debug println statements Remove leftover debug println("read new data1/2") from ReadDataAt in MemChunk and SwapFileChunk. * test: fix findWeedBinary matching source directory instead of binary findWeedBinary() matched ../../weed (the source directory) via os.Stat before checking PATH, then tried to exec a directory which fails with "permission denied" on the CI runner. Fix: Check PATH first (reliable in CI where the binary is installed to /usr/local/bin). For relative paths, verify the candidate is a regular file (!info.IsDir()). Add ../../weed/weed as a candidate for in-tree builds. * test: fix framework — dynamic ports, output capture, data dirs The integration test framework was failing in CI because: 1. All tests used hardcoded ports (19333/18080/18888), so sequential tests could conflict when prior processes hadn't fully released their ports yet. 2. Data subdirectories (data/master, data/volume) were not created before starting processes. 3. Master was started with -peers=none which is not a valid address. 4. Process stdout/stderr was not captured, making failures opaque ("service not ready within timeout" with no diagnostics). 5. The unmount fallback used 'umount' instead of 'fusermount -u'. 6. The mount used -cacheSizeMB (nonexistent) instead of -cacheCapacityMB and was missing -allowOthers=false for unprivileged CI runners. Fixes: - Dynamic port allocation via freePort() (net.Listen ":0") - Explicit gRPC ports via -port.grpc to avoid default port conflicts - Create data/master and data/volume directories in Setup() - Remove invalid -peers=none and -raftBootstrap flags - Capture process output to logDir/*.log via startProcess() helper - dumpLog() prints tail of log file on service startup failure - Use fusermount3/fusermount -u for unmount - Fix mount flag names (-cacheCapacityMB, -allowOthers=false) * test: remove explicit -port.grpc flags from test framework SeaweedFS convention: gRPC port = HTTP port + 10000. Volume and filer discover the master gRPC port by this convention. Setting explicit -port.grpc on master/volume/filer broke inter-service communication because the volume server computed master gRPC as HTTP+10000 but the actual gRPC was on a different port. Remove all -port.grpc flags and let the default convention work. Dynamic HTTP ports already ensure uniqueness; the derived gRPC ports (HTTP+10000) will also be unique. --------- Co-authored-by: Copilot <copilot@github.com> |
||
|
Chris Lu
|
d6a872c4b9 |
Preserve explicit directory markers with octet-stream MIME (#8726)
* Preserve octet-stream MIME on explicit directory markers * Run empty directory marker regression in CI * Run S3 Spark workflow for filer changes |
||
|
Chris Lu
|
7fbdb9b7b7 |
feat(shell): add volume.tier.compact command to reclaim cloud storage space (#8715)
* feat(shell): add volume.tier.compact command to reclaim cloud storage space Adds a new shell command that automates compaction of cloud tier volumes. When files are deleted from remote-tiered volumes, space is not reclaimed on the cloud storage. This command orchestrates: download from remote, compact locally, and re-upload to reclaim deleted space. Closes #8563 * fix: log cleanup errors in compactVolumeOnServer instead of discarding them Helps operators diagnose leftover temp files (.cpd/.cpx) if cleanup fails after a compaction or commit failure. * fix: return aggregate error from loop and use regex for collection filter - Track and return error count when one or more volumes fail to compact, so callers see partial failures instead of always getting nil. - Use compileCollectionPattern for -collection in -volumeId mode too, so regex patterns work consistently with the flag description. Empty pattern (no -collection given) matches all collections. |
||
|
Chris Lu
|
ba855f9962 |
fix(telemetry): use correct TopologyId field in integration test (#8714)
* fix(telemetry): use correct TopologyId field in integration test The proto field was renamed from cluster_id to topology_id but the integration test was not updated, causing a compilation error. * ci: add telemetry integration test workflow Runs the telemetry integration test (server startup, protobuf marshaling, client send, metrics/stats/instances API checks) on changes to telemetry/ or weed/telemetry/. * fix(telemetry): improve error message specificity in integration test * fix(ci): pre-build telemetry server binary for integration test go run compiles the server on the fly, which exceeds the 15s startup timeout in CI. Build the binary first so the test starts instantly. * fix(telemetry): fix ClusterId references in server and CI build path - Replace ClusterId with TopologyId in server storage and API handler (same rename as the integration test fix) - Fix CI build: telemetry server has its own go.mod, so build from within its directory * ci(telemetry): add least-privilege permissions to workflow Scope the workflow token to read-only repository contents, matching the convention used in go.yml. * fix(telemetry): set TopologyId in client integration test The client only populates TopologyId when SetTopologyId has been called. The test was missing this call, causing the server to reject the request with 400 (missing required field). * fix(telemetry): delete clusterInfo metric on instance cleanup The cleanup loop removed all per-instance metrics except clusterInfo, leaking that label set after eviction. |
||
|
Chris Lu
|
002e325b74 |
build(deps): upgrade apache/iceberg-go from v0.4.0 to v0.5.0 (#8713)
Key improvements: - Fix concurrent map write panic in partition type cache - Fix data races in yieldDataFiles and key map getter - Fix response body leaks in REST catalog - Fix index out of range in buildManifestEvaluator - Table Metadata V3 support - Schema evolution API - Partitioned write throughput optimizations - Gzipped metadata read/write support |
||
|
Chris Lu
|
51ec0d2122 |
fix(remote_gateway): prevent double-versioning when syncing to versioned central bucket (#8710)
* fix(remote_gateway): prevent double-versioning when syncing to versioned central bucket
When a file is uploaded to a versioned bucket on edge, SeaweedFS stores
it internally as {object}.versions/v_{versionId}. The remote_gateway was
syncing this internal path directly to the central S3 endpoint. When
central's bucket also has versioning enabled, this caused central to
apply its own versioning on top, producing corrupt paths like:
object.versions/v_{edgeId}.versions/v_{centralId}
Fix: rewrite internal .versions/v_{id} paths to the original S3 object
key before uploading to the remote. Skip version file delete/update
events that are internal bookkeeping.
Fixes https://github.com/seaweedfs/seaweedfs/discussions/8481#discussioncomment-16209342
* fix(remote_gateway): propagate delete markers to remote as deletions
Delete markers are zero-content version entries (ExtDeleteMarkerKey=true)
created by S3 DELETE on a versioned bucket. Previously they were silently
dropped by the HasData() filter, so deletions on edge never reached
central.
Now: detect delete markers before the HasData check, rewrite the
.versions path to the original S3 key, and issue client.DeleteFile()
on the remote.
* fix(remote_gateway): tighten isVersionedPath to avoid false positives
Address PR review feedback:
- Add isDir parameter to isVersionedPath so it only matches the exact
internal shapes: directories whose name ends with .versions (isDir=true),
and files with the v_ prefix inside a .versions parent (isDir=false).
Previously the function was too broad and could match user-created paths
like "my.versions/data.txt".
- Update all 4 call sites to pass the entry's IsDirectory field.
- Rename TestVersionedDirectoryNotFilteredByHasData to
TestVersionsDirectoryFilteredByHasData so the name reflects the
actual assertion (directories ARE filtered by HasData).
- Expand TestIsVersionedPath with isDir cases and false-positive checks.
* fix(remote_gateway): persist sync marker after delete-marker propagation
The delete-marker branch was calling client.DeleteFile() and returning
without updating the local entry, making event replay re-issue the
remote delete. Now call updateLocalEntry after a successful DeleteFile
to stamp the delete-marker entry with a RemoteEntry, matching the
pattern used by the normal create path.
* refactor(remote_gateway): extract syncDeleteMarker and fix root path edge case
- Extract syncDeleteMarker() shared helper used by both bucketed and
mounted-dir event processors, replacing the duplicated delete + persist
local marker logic.
- Fix rewriteVersionedSourcePath for root-level objects: when lastSlash
is 0 (e.g. "/file.xml.versions"), return "/" as the parent dir instead
of an empty string.
- The strings.Contains(dir, ".versions/") condition flagged in review was
already removed in a prior commit that tightened isVersionedPath.
* fix(remote_gateway): skip updateLocalEntry for versioned path rewrites
After rewriting a .versions/v_{id} path to the logical S3 key and
uploading, the code was calling updateLocalEntry on the original v_*
entry, stamping it with a RemoteEntry for the logical key. This is
semantically wrong: the logical object has no filer entry in versioned
buckets, and the internal v_* entry should not carry a RemoteEntry for
a different path.
Skip updateLocalEntry when the path was rewritten from a versioned
source. Replay safety is preserved because S3 PutObject is idempotent.
* fix(remote_gateway): scope versioning checks to /buckets/ namespace
isVersionedPath and rewriteVersionedSourcePath could wrongly match
paths in non-bucket mounts (e.g. /mnt/remote/file.xml.versions).
Add the same /buckets/ prefix guard used by isMultipartUploadDir so
the .versions / v_ logic only applies within the bucket namespace.
|
||
|
Chris Lu
|
6ccda3e809 |
fix(s3): allow deleting the anonymous user from admin webui (#8706)
Remove the block that prevented deleting the "anonymous" identity and stop auto-creating it when absent. If no anonymous identity exists (or it is disabled), LookupAnonymous returns not-found and both auth paths return ErrAccessDenied for anonymous requests. To enable anonymous access, explicitly create the "anonymous" user. To revoke it, delete the user like any other identity. Closes #8694 |
||
|
Chris Lu
|
08b79a30f6 |
Fix lock table shared wait condition (#8707)
* Fix lock table shared wait condition (#8696) * Refactor lock table waiter check * Add exclusive lock wait helper test |
||
|
Chris Lu
|
80f3079d2a |
fix(s3): include directory markers in ListObjects without delimiter (#8704)
* fix(s3): include directory markers in ListObjects without delimiter (#8698) Directory key objects (zero-byte objects with keys ending in "/") created via PutObject were omitted from ListObjects/ListObjectsV2 results when no delimiter was specified. AWS S3 includes these as regular keys in Contents. The issue was in doListFilerEntries: when recursing into directories in non-delimiter mode, directory key objects were only emitted when prefixEndsOnDelimiter was true. Added an else branch to emit them in the general recursive case as well. * remove issue reference from inline comment * test: add child-under-marker and paginated listing coverage Extend test 6 to place a child object under the directory marker and paginate with MaxKeys=1 so the emit-then-recurse truncation path is exercised. * fix(test): skip directory markers in Spark temporary artifacts check The listing check now correctly shows directory markers (keys ending in "/") after the ListObjects fix. These 0-byte metadata objects are not data artifacts — filter them from the listing check since the HeadObject-based check already verifies their cleanup with a timeout. |
||
|
Chris LuandCopilot
|
5e76f55077 |
fix(helm): namespace app-specific global values under global.seaweedfs (#8700)
* fix(helm): namespace app-specific values under global.seaweedfs Move all app-specific values from the global namespace to global.seaweedfs.* to avoid polluting the shared .Values.global namespace when the chart is used as a subchart. Standard Helm conventions (global.imageRegistry, global.imagePullSecrets) remain at the global level as they are designed to be shared across subcharts. Fixes seaweedfs/seaweedfs#8699 BREAKING CHANGE: global values have been restructured. Users must update their values files to use the new paths: - global.registry → global.imageRegistry - global.repository → global.seaweedfs.image.repository - global.imageName → global.seaweedfs.image.name - global.<key> → global.seaweedfs.<key> (for all other app-specific values) * fix(ci): update helm CI tests to use new global.seaweedfs.* value paths Update all --set flags in helm_ci.yml to use the new namespaced global.seaweedfs.* paths matching the values.yaml restructuring. * fix(ci): install Claude Code via npm to avoid install.sh 403 The claude-code-action's built-in installer uses `curl https://claude.ai/install.sh | bash` which can fail with 403. Due to the pipe, bash exits 0 on empty input, masking the curl failure and leaving the `claude` binary missing. Work around this by installing Claude Code via npm before invoking the action, and passing the executable path via path_to_claude_code_executable. * revert: remove claude-code-review.yml changes from this PR The claude-code-action OIDC token exchange validates that the workflow file matches the version on the default branch. Modifying it in a PR causes the review job to fail with "Workflow validation failed". The Claude Code install fix will need to be applied directly to master or in a separate PR. * fix: update stale references to old global.* value paths - admin-statefulset.yaml: fix fail message to reference global.seaweedfs.masterServer - values.yaml: fix comment to reference image.name instead of imageName - helm_ci.yml: fix diagnostic message to reference global.seaweedfs.enableSecurity * feat(helm): add backward-compat shim for old global.* value paths Add _compat.tpl with a seaweedfs.compat helper that detects old-style global.* keys (e.g. global.enableSecurity, global.registry) and merges them into the new global.seaweedfs.* namespace. Since the old keys no longer have defaults in values.yaml, their presence means the user explicitly provided them. The helper uses in-place mutation via `set` so all templates see the merged values. This ensures existing deployments using old value paths continue to work without changes after upgrading. * fix: update stale comment references in values.yaml Update comments referencing global.enableSecurity and global.masterServer to the new global.seaweedfs.* paths. --------- Co-authored-by: Copilot <copilot@github.com> |
||
|
Chris LuandCopilot
|
5606557c6b |
fix(ci): install Claude Code via npm to avoid install.sh 403 (#8701)
The claude-code-action's built-in installer uses `curl https://claude.ai/install.sh | bash` which can fail with 403. Due to the pipe, bash exits 0 on empty input, masking the curl failure and leaving the `claude` binary missing. Work around this by installing Claude Code via npm before invoking the action, and passing the executable path via path_to_claude_code_executable. Co-authored-by: Copilot <copilot@github.com> |
||
|
Chris Lu
|
15f4a97029 |
fix: improve raft leader election reliability and failover speed (#8692)
* fix: clear raft vote state file on non-resume startup The seaweedfs/raft library v1.1.7 added a persistent `state` file for currentTerm and votedFor. When RaftResumeState=false (the default), the log, conf, and snapshot directories are cleared but this state file was not. On repeated restarts, different masters accumulate divergent terms, causing AppendEntries rejections and preventing leader election. Fixes #8690 * fix: recover TopologyId from snapshot before clearing raft state When RaftResumeState=false clears log/conf/snapshot, the TopologyId (used for license validation) was lost. Now extract it from the latest snapshot before cleanup and restore it on the topology. Both seaweedfs/raft and hashicorp/raft paths are handled, with a shared recoverTopologyIdFromState helper in raft_common.go. * fix: stagger multi-master bootstrap delay by peer index Previously all masters used a fixed 1500ms delay before the bootstrap check. Now the delay is proportional to the peer's sorted index with randomization (matching the hashicorp raft path), giving the designated bootstrap node (peer 0) a head start while later peers wait for gRPC servers to be ready. Also adds diagnostic logging showing why DoJoinCommand was or wasn't called, making leader election issues easier to diagnose from logs. * fix: skip unreachable masters during leader reconnection When a master leader goes down, non-leader masters still redirect clients to the stale leader address. The masterClient would follow these redirects, fail, and retry — wasting round-trips each cycle. Now tryAllMasters tracks which masters failed within a cycle and skips redirects pointing to them, reducing log spam and connection overhead during leader failover. * fix: take snapshot after TopologyId generation for recovery After generating a new TopologyId on the leader, immediately take a raft snapshot so the ID can be recovered from the snapshot on future restarts with RaftResumeState=false. Without this, short-lived clusters would lose the TopologyId on restart since no automatic snapshot had been taken yet. * test: add multi-master raft failover integration tests Integration test framework and 5 test scenarios for 3-node master clusters: - TestLeaderConsistencyAcrossNodes: all nodes agree on leader and TopologyId - TestLeaderDownAndRecoverQuickly: leader stops, new leader elected, old leader rejoins as follower - TestLeaderDownSlowRecover: leader gone for extended period, cluster continues with 2/3 quorum - TestTwoMastersDownAndRestart: quorum lost (2/3 down), recovered when both restart - TestAllMastersDownAndRestart: full cluster restart, leader elected, all nodes agree on TopologyId * fix: address PR review comments - peerIndex: return -1 (not 0) when self not found, add warning log - recoverTopologyIdFromSnapshot: defer dir.Close() - tests: check GetTopologyId errors instead of discarding them * fix: address review comments on failover tests - Assert no leader after quorum loss (was only logging) - Verify follower cs.Leader matches expected leader via ServerAddress.ToHttpAddress() comparison - Check GetTopologyId error in TestTwoMastersDownAndRestart |
||
|
Chris Lu
|
c197206897 |
fix(s3): return ETag header for directory marker PutObject requests (#8688)
* fix(s3): return ETag header for directory marker PutObject requests The PutObject handler has a special path for keys ending with "/" (directory markers) that creates the entry via mkdir. This path never computed or set the ETag response header, unlike the regular PutObject path. AWS S3 always returns an ETag header, even for empty-body puts. Compute the MD5 of the content (empty or otherwise), store it in the entry attributes and extended attributes, and set the ETag response header. Fixes #8682 * fix: handle io.ReadAll error and chunked encoding for directory markers Address review feedback: - Handle error from io.ReadAll instead of silently discarding it - Change condition from ContentLength > 0 to ContentLength != 0 to correctly handle chunked transfer encoding (ContentLength == -1) * fix hanging tests |
||
|
Chris Lu
|
e59bcfebcc |
Add Claude Code GitHub Workflow (#8687)
* "Claude PR Assistant workflow" * "Claude Code Review workflow" |
||
|
Chris LuandCopilot
|
248a92dce0 |
deps: upgrade seaweedfs/raft to v1.1.7 (#8677)
Picks up critical fixes from seaweedfs/raft#9: - Persist currentTerm and votedFor to prevent split-brain after restart - Fix checkQuorumActive truncating sub-second election timeouts to 0 - Upgrade grpc to v1.72.2 (HTTP/2 Rapid Reset fix) Co-authored-by: Copilot <copilot@github.com> |
||
|
Chris Lu
|
81369b8a83 |
improve: large file sync throughput for remote.cache and filer.sync (#8676)
* improve large file sync throughput for remote.cache and filer.sync
Three main throughput improvements:
1. Adaptive chunk sizing for remote.cache: targets ~32 chunks per file
instead of always starting at 5MB. A 500MB file now uses ~16MB chunks
(32 chunks) instead of 5MB chunks (100 chunks), reducing per-chunk
overhead (volume assign, gRPC call, needle write) by 3x.
2. Configurable concurrency at every layer:
- remote.cache chunk concurrency: -chunkConcurrency flag (default 8)
- remote.cache S3 download concurrency: -downloadConcurrency flag
(default raised from 1 to 5 per chunk)
- filer.sync chunk concurrency: -chunkConcurrency flag (default 32)
3. S3 multipart download concurrency raised from 1 to 5: the S3 manager
downloader was using Concurrency=1, serializing all part downloads
within each chunk. This alone can 5x per-chunk download speed.
The concurrency values flow through the gRPC request chain:
shell command → CacheRemoteObjectToLocalClusterRequest →
FetchAndWriteNeedleRequest → S3 downloader
Zero values in the request mean "use server defaults", maintaining
full backward compatibility with existing callers.
Ref #8481
* fix: use full maxMB for chunk size cap and remove loop guard
Address review feedback:
- Use full maxMB instead of maxMB/2 for maxChunkSize to avoid
unnecessarily limiting chunk size for very large files.
- Remove chunkSize < maxChunkSize guard from the safety loop so it
can always grow past maxChunkSize when needed to stay under 1000
chunks (e.g., extremely large files with small maxMB).
* address review feedback: help text, validation, naming, docs
- Fix help text for -chunkConcurrency and -downloadConcurrency flags
to say "0 = server default" instead of advertising specific numeric
defaults that could drift from the server implementation.
- Validate chunkConcurrency and downloadConcurrency are within int32
range before narrowing, returning a user-facing error if out of range.
- Rename ReadRemoteErr to readRemoteErr to follow Go naming conventions.
- Add doc comment to SetChunkConcurrency noting it must be called
during initialization before replication goroutines start.
- Replace doubling loop in chunk size safety check with direct
ceil(remoteSize/1000) computation to guarantee the 1000-chunk cap.
* address Copilot review: clamp concurrency, fix chunk count, clarify proto docs
- Use ceiling division for chunk count check to avoid overcounting
when file size is an exact multiple of chunk size.
- Clamp chunkConcurrency (max 1024) and downloadConcurrency (max 1024
at filer, max 64 at volume server) to prevent excessive goroutines.
- Always use ReadFileWithConcurrency when the client supports it,
falling back to the implementation's default when value is 0.
- Clarify proto comments that download_concurrency only applies when
the remote storage client supports it (currently S3).
- Include specific server defaults in help text (e.g., "0 = server
default 8") so users see the actual values in -h output.
* fix data race on executionErr and use %w for error wrapping
- Protect concurrent writes to executionErr in remote.cache worker
goroutines with a sync.Mutex to eliminate the data race.
- Use %w instead of %v in volume_grpc_remote.go error formatting
to preserve the error chain for errors.Is/errors.As callers.
|
||
|
Chris Lu
|
f4073107cb |
fix: clean up orphaned needles on remote.cache partial download failure (#8675)
When remote.cache downloads a file in parallel chunks and a gRPC connection drops mid-transfer, chunks already written to volume servers were not cleaned up. Since the filer metadata was never updated, these needles became orphaned — invisible to volume.vacuum and never referenced by the filer. On subsequent cache cycles the file was still treated as uncached, creating more orphans each attempt. Call DeleteUncommittedChunks on the download-error path, matching the cleanup already present for the metadata-update-failure path. Fixes #8481 |
||
|
Chris Lu
|
55e988a7ee |
iceberg: add sort-aware compaction rewrite (#8666)
* iceberg: add sort-aware compaction rewrite * iceberg: share filtered row iteration in compaction * iceberg: rely on table sort order for sort rewrites * iceberg: harden sort compaction planning * iceberg: include rewrite strategy in planning config hash compactionPlanningConfigHash now incorporates RewriteStrategy and SortMaxInputBytes so cached planning results are invalidated when sort strategy settings change. Also use the bytesPerMB constant in compactionNoEligibleMessage. |
||
|
Chris Lu
|
e5c0889473 |
iceberg: add delete file rewrite maintenance (#8664)
* iceberg: add delete file rewrite maintenance * iceberg: preserve untouched delete files during rewrites * iceberg: share detection threshold defaults * iceberg: add partition-scoped maintenance filters (#8665) * iceberg: add partition-scoped maintenance filters * iceberg: tighten where-filter partition matching |
||
|
Chris LuandCopilot
|
a3717cd4b5 |
fix(admin): show anonymous user in Object Store Users UI (#8671)
The anonymous identity was explicitly filtered out of the user listing, making it invisible in the admin console. Users could not view or edit its permissions. Attempting to recreate it failed with "already exists". Remove the anonymous skip in GetObjectStoreUsers so it appears like any other identity. Add a guard in DeleteObjectStoreUser to prevent deletion of the anonymous system identity, which would break unauthenticated S3 access. Fixes #8466 Co-authored-by: Copilot <copilot@github.com> |
||
|
Chris Lu
|
6e45fc0055 |
iceberg: cache detection planning results (#8667)
* iceberg: cache detection planning results * iceberg: tighten planning index cache handling * iceberg: remove dead planning-index metadata fallback * iceberg: preserve partial planning index caches * iceberg: scope planning index caching per op * iceberg: rename copy vars to avoid shadowing builtin |
||
|
Chris Lu
|
f71cef2dc8 |
iceberg: add resource-group proposal controls (#8668)
* iceberg: add resource-group proposal controls * iceberg: tighten resource group config validation |
||
|
Chris Lu
|
e8914ac879 |
feat(admin): add -urlPrefix flag for subdirectory deployment (#8670)
Allow the admin server to run behind a reverse proxy under a subdirectory by adding a -urlPrefix flag (e.g. -urlPrefix=/seaweedfs). Closes #8646 |
||
|
Chris Lu
|
9984ce7dcb |
fix(s3): omit NotResource:null from bucket policy JSON response (#8658)
* fix(s3): omit NotResource:null from bucket policy JSON response (#8657) Change NotResource from value type to pointer (*StringOrStringSlice) so that omitempty properly omits it when unset, matching the existing Principal field pattern. This prevents IaC tools (Terraform, Ansible) from detecting false configuration drift. Add bucket policy round-trip idempotency integration tests. * simplify JSON comparison in bucket policy idempotency test Use require.JSONEq directly on the raw JSON strings instead of round-tripping through unmarshal/marshal, since JSONEq already handles normalization internally. * fix bucket policy test cases that locked out the admin user The Deny+NotResource test cases used Action:"s3:*" which denied the admin's own GetBucketPolicy call. Scope deny to s3:GetObject only, and add an Allow+NotResource variant instead. * fix(s3): also make Resource a pointer to fix empty string in JSON Apply the same omitempty pointer fix to the Resource field, which was emitting "Resource":"" when only NotResource was set. Add NewStringOrStringSlicePtr helper, make Strings() nil-safe, and handle *StringOrStringSlice in normalizeToStringSliceWithError. * improve bucket policy integration tests per review feedback - Replace time.Sleep with waitForClusterReady using ListBuckets - Use structural hasKey check instead of brittle substring NotContains - Assert specific NoSuchBucketPolicy error code after delete - Handle single-statement policies in hasKey helper |
||
|
Chris Lu
|
acea36a181 |
filer: add conditional update preconditions (#8647)
* filer: add conditional update preconditions * iceberg: tighten metadata CAS preconditions |
||
|
Chris LuandCopilot Autofix powered by AI
|
6b2b442450 |
iceberg: detect maintenance work per operation (#8639)
* iceberg: detect maintenance work per operation * iceberg: ignore delete manifests during detection * iceberg: clean up detection maintenance planning * iceberg: tighten detection manifest heuristics * Potential fix for code scanning alert no. 330: Incorrect conversion between integer types Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com> * iceberg: tolerate per-operation detection errors * iceberg: fix fake metadata location versioning * iceberg: check snapshot expiry before manifest loads * iceberg: make expire-snapshots switch case explicit --------- Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com> |
||
|
Chris LuandCopilot
|
a00eddb525 |
Iceberg table maintenance Phase 3: multi-spec compaction, delete handling, and metrics (#8643)
* Add multi-partition-spec compaction and delete-aware compaction (Phase 3) Multi-partition-spec compaction: - Add SpecID to compactionBin struct and group by spec+partition key - Remove the len(specIDs) > 1 skip that blocked spec-evolved tables - Write per-spec manifests in compaction commit using specByID map - Use per-bin PartitionSpec when calling NewDataFileBuilder Delete-aware compaction: - Add ApplyDeletes config (default: true) with readBoolConfig helper - Implement position delete collection (file_path + pos Parquet columns) - Implement equality delete collection (field ID to column mapping) - Update mergeParquetFiles to filter rows via position deletes (binary search) and equality deletes (hash set lookup) - Smart delete manifest carry-forward: drop when all data files compacted - Fix EXISTING/DELETED entries to include sequence numbers Tests for multi-spec bins, delete collection, merge filtering, and end-to-end compaction with position/equality/mixed deletes. * Add structured metrics and per-bin progress to iceberg maintenance - Change return type of all four operations from (string, error) to (string, map[string]int64, error) with structured metric counts (files_merged, snapshots_expired, orphans_removed, duration_ms, etc.) - Add onProgress callback to compactDataFiles for per-bin progress - In Execute, pass progress callback that sends JobProgressUpdate with per-bin stage messages - Accumulate per-operation metrics with dot-prefixed keys (e.g. compact.files_merged) into OutputValues on completion - Update testing_api.go wrappers and integration test call sites - Add tests: TestCompactDataFilesMetrics, TestExpireSnapshotsMetrics, TestExecuteCompletionOutputValues * Address review feedback: group equality deletes by field IDs, use metric constants - Group equality deletes by distinct equality_ids sets so different delete files with different equality columns are handled correctly - Use length-prefixed type-aware encoding in buildEqualityKey to avoid ambiguity between types and collisions from null bytes - Extract metric key strings into package-level constants * Fix buildEqualityKey to use length-prefixed type-aware encoding The previous implementation used plain String() concatenation with null byte separators, which caused type ambiguity (int 123 vs string "123") and separator collisions when values contain null bytes. Now each value is serialized as "kind:length:value" for unambiguous composite keys. This fix was missed in the prior cherry-pick due to a merge conflict. * Address nitpick review comments - Document patchManifestContentToDeletes workaround: explain that iceberg-go WriteManifest cannot create delete manifests, and note the fail-fast validation on pattern match - Document makeTestEntries: note that specID field is ignored and callers should use makeTestEntriesWithSpec for multi-spec testing * fmt * Fix path normalization, manifest threshold, and artifact filename collisions - Normalize file paths in position delete collection and lookup so that absolute S3 URLs and relative paths match correctly - Fix rewriteManifests threshold check to count only data manifests (was including delete manifests in the count and metric) - Add random suffix to artifact filenames in compactDataFiles and rewriteManifests to prevent collisions between concurrent runs - Sort compaction bins by SpecID then PartitionKey for deterministic ordering across specs * Fix pos delete read, deduplicate column resolution, minor cleanups - Remove broken Column() guard in position delete reading that silently defaulted pos to 0; unconditionally extract Int64() instead - Deduplicate column resolution in readEqualityDeleteFile by calling resolveEqualityColIndices instead of inlining the same logic - Add warning log in readBoolConfig for unrecognized string values - Fix CompactDataFiles call site in integration test to capture 3 return values * Advance progress on all bins, deterministic manifest order, assert metrics - Call onProgress for every bin iteration including skipped/failed bins so progress reporting never appears stalled - Sort spec IDs before iterating specEntriesMap to produce deterministic manifest list ordering across runs - Assert expected metric keys in CompactDataFiles integration test --------- Co-authored-by: Copilot <copilot@github.com> |
||
|
Chris Lu
|
e24630251c |
iceberg: handle filer-backed compaction inputs (#8638)
* iceberg: handle filer-backed compaction inputs * iceberg: preserve upsert creation times * iceberg: align compaction test schema * iceberg: tighten compact output assertion * iceberg: document compact output match * iceberg: clear stale chunks in upsert helper * iceberg: strengthen compaction integration coverage |
||
|
Chris Lu
|
0afc675a55 |
iceberg: validate filer failover targets (#8637)
* iceberg: validate filer failover targets * iceberg: tighten filer liveness checks * iceberg: relax filer test readiness deadline |
||
|
Chris Lu
|
b868980260 |
fix(remote): don't send empty StorageClass in S3 uploads (#8645)
When S3StorageClass is empty (the default), aws.String("") was passed
as the StorageClass in PutObject requests. While AWS S3 treats this as
"use default," S3-compatible providers (e.g. SharkTech) reject it with
InvalidStorageClass. Only set StorageClass when a non-empty value is
configured, letting the provider use its default.
Fixes #8644
|
||
|
Chris Lu
|
5f19e3259f | iceberg: keep split bins within target size (#8640) | ||
|
Chris LuandCopilot
|
d9d6707401 |
Change iceberg compaction target file size config from bytes to MB (#8636)
Change iceberg target_file_size config from bytes to MB Rename the config field from target_file_size_bytes to target_file_size_mb with a default of 256 (MB). The value is converted to bytes internally. This makes the config more user-friendly — entering 256 is clearer than 268435456. Co-authored-by: Copilot <copilot@github.com> |
||
|
|
8cde3d4486 |
Add data file compaction to iceberg maintenance (Phase 2) (#8503)
* Add iceberg_maintenance plugin worker handler (Phase 1) Implement automated Iceberg table maintenance as a new plugin worker job type. The handler scans S3 table buckets for tables needing maintenance and executes operations in the correct Iceberg order: expire snapshots, remove orphan files, and rewrite manifests. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * Add data file compaction to iceberg maintenance handler (Phase 2) Implement bin-packing compaction for small Parquet data files: - Enumerate data files from manifests, group by partition - Merge small files using parquet-go (read rows, write merged output) - Create new manifest with ADDED/DELETED/EXISTING entries - Commit new snapshot with compaction metadata Add 'compact' operation to maintenance order (runs before expire_snapshots), configurable via target_file_size_bytes and min_input_files thresholds. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * Fix memory exhaustion in mergeParquetFiles by processing files sequentially Previously all source Parquet files were loaded into memory simultaneously, risking OOM when a compaction bin contained many small files. Now each file is loaded, its rows are streamed into the output writer, and its data is released before the next file is loaded — keeping peak memory proportional to one input file plus the output buffer. * Validate bucket/namespace/table names against path traversal Reject names containing '..', '/', or '\' in Execute to prevent directory traversal via crafted job parameters. * Add filer address failover in iceberg maintenance handler Try each filer address from cluster context in order instead of only using the first one. This improves resilience when the primary filer is temporarily unreachable. * Add separate MinManifestsToRewrite config for manifest rewrite threshold The rewrite_manifests operation was reusing MinInputFiles (meant for compaction bin file counts) as its manifest count threshold. Add a dedicated MinManifestsToRewrite field with its own config UI section and default value (5) so the two thresholds can be tuned independently. * Fix risky mtime fallback in orphan removal that could delete new files When entry.Attributes is nil, mtime defaulted to Unix epoch (1970), which would always be older than the safety threshold, causing the file to be treated as eligible for deletion. Skip entries with nil Attributes instead, matching the safer logic in operations.go. * Fix undefined function references in iceberg_maintenance_handler.go Use the exported function names (ShouldSkipDetectionByInterval, BuildDetectorActivity, BuildExecutorActivity) matching their definitions in vacuum_handler.go. * Remove duplicated iceberg maintenance handler in favor of iceberg/ subpackage The IcebergMaintenanceHandler and its compaction code in the parent pluginworker package duplicated the logic already present in the iceberg/ subpackage (which self-registers via init()). The old code lacked stale-plan guards, proper path normalization, CAS-based xattr updates, and error-returning parseOperations. Since the registry pattern (default "all") makes the old handler unreachable, remove it entirely. All functionality is provided by iceberg.Handler with the reviewed improvements. * Fix MinManifestsToRewrite clamping to match UI minimum of 2 The clamp reset values below 2 to the default of 5, contradicting the UI's advertised MinValue of 2. Clamp to 2 instead. * Sort entries by size descending in splitOversizedBin for better packing Entries were processed in insertion order which is non-deterministic from map iteration. Sorting largest-first before the splitting loop improves bin packing efficiency by filling bins more evenly. * Add context cancellation check to drainReader loop The row-streaming loop in drainReader did not check ctx between iterations, making long compaction merges uncancellable. Check ctx.Done() at the top of each iteration. * Fix splitOversizedBin to always respect targetSize limit The minFiles check in the split condition allowed bins to grow past targetSize when they had fewer than minFiles entries, defeating the OOM protection. Now bins always split at targetSize, and a trailing runt with fewer than minFiles entries is merged into the previous bin. * Add integration tests for iceberg table maintenance plugin worker Tests start a real weed mini cluster, create S3 buckets and Iceberg table metadata via filer gRPC, then exercise the iceberg.Handler operations (ExpireSnapshots, RemoveOrphans, RewriteManifests) against the live filer. A full maintenance cycle test runs all operations in sequence and verifies metadata consistency. Also adds exported method wrappers (testing_api.go) so the integration test package can call the unexported handler methods. * Fix splitOversizedBin dropping files and add source path to drainReader errors The runt-merge step could leave leading bins with fewer than minFiles entries (e.g. [80,80,10,10] with targetSize=100, minFiles=2 would drop the first 80-byte file). Replace the filter-based approach with an iterative merge that folds any sub-minFiles bin into its smallest neighbor, preserving all eligible files. Also add the source file path to drainReader error messages so callers can identify which Parquet file caused a read/write failure. * Harden integration test error handling - s3put: fail immediately on HTTP 4xx/5xx instead of logging and continuing - lookupEntry: distinguish NotFound (return nil) from unexpected RPC errors (fail the test) - writeOrphan and orphan creation in FullMaintenanceCycle: check CreateEntryResponse.Error in addition to the RPC error * go fmt --------- Co-authored-by: Copilot <copilot@github.com> Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com> |
||
|
Chris Lu
|
1f2014568f |
fix(mini): use "all" job type for plugin worker (#8634)
The mini command previously hardcoded a list of specific job types (vacuum, volume_balance, erasure_coding, admin_script). Use the "all" category instead so that newly registered handlers are automatically picked up without requiring changes to the mini command. |
||
|
Chris Lu
|
a838661b83 |
feat(plugin): EC shard balance handler for plugin worker (#8629)
* feat(ec_balance): add TaskTypeECBalance constant and protobuf definitions Add the ec_balance task type constant to both topology and worker type systems. Define EcBalanceTaskParams, EcShardMoveSpec, and EcBalanceTaskConfig protobuf messages for EC shard balance operations. * feat(ec_balance): add configuration for EC shard balance task Config includes imbalance threshold, min server count, collection filter, disk type, and preferred tags for tag-aware placement. * feat(ec_balance): add multi-phase EC shard balance detection algorithm Implements four detection phases adapted from the ec.balance shell command: 1. Duplicate shard detection and removal proposals 2. Cross-rack shard distribution balancing 3. Within-rack node-level shard balancing 4. Global shard count equalization across nodes Detection is side-effect-free: it builds an EC topology view from ActiveTopology and generates move proposals without executing them. * feat(ec_balance): add EC shard move task execution Implements the shard move sequence using the same VolumeEcShardsCopy, VolumeEcShardsMount, VolumeEcShardsUnmount, and VolumeEcShardsDelete RPCs as the shell ec.balance command. Supports both regular shard moves and dedup-phase deletions (unmount+delete without copy). * feat(ec_balance): add task registration and scheduling Register EC balance task definition with auto-config update support. Scheduling respects max concurrent limits and worker capabilities. * feat(ec_balance): add plugin handler for EC shard balance Implements the full plugin handler with detection, execution, admin and worker config forms, proposal building, and decision trace reporting. Supports collection/DC/disk type filtering, preferred tag placement, and configurable detection intervals. Auto-registered via init() with the handler registry. * test(ec_balance): add tests for detection algorithm and plugin handler Detection tests cover: duplicate shard detection, cross-rack imbalance, within-rack imbalance, global rebalancing, topology building, collection filtering, and edge cases. Handler tests cover: config derivation with clamping, proposal building, protobuf encode/decode round-trip, fallback parameter decoding, capability, and config policy round-trip. * fix(ec_balance): address PR review feedback and fix CI test failure - Update TestWorkerDefaultJobTypes to expect 6 handlers (was 5) - Extract threshold constants (ecBalanceMinImbalanceThreshold, etc.) to eliminate magic numbers in Descriptor and config derivation - Remove duplicate ShardIdsToUint32 helper (use erasure_coding package) - Add bounds checks for int64→int/uint32 conversions to fix CodeQL integer conversion warnings * fix(ec_balance): address code review findings storage_impact.go: - Add TaskTypeECBalance case returning shard-level reservation (ShardSlots: -1/+1) instead of falling through to default which incorrectly reserves a full volume slot on target. detection.go: - Use dc:rack composite key to avoid cross-DC rack name collisions. Only create rack entries after confirming node has matching disks. - Add exceedsImbalanceThreshold check to cross-rack, within-rack, and global phases so trivial skews below the configured threshold are ignored. Dedup phase always runs since duplicates are errors. - Reserve destination capacity after each planned move (decrement destNode.freeSlots, update rackShardCount/nodeShardCount) to prevent overbooking the same destination. - Skip nodes with freeSlots <= 0 when selecting minNode in global balance to avoid proposing moves to full nodes. - Include loop index and source/target node IDs in TaskID to guarantee uniqueness across moves with the same volumeID/shardID. ec_balance_handler.go: - Fail fast with error when shard_id is absent in fallback parameter decoding instead of silently defaulting to shard 0. ec_balance_task.go: - Delegate GetProgress() to BaseTask.GetProgress() so progress updates from ReportProgressWithStage are visible to callers. - Add fail-fast guard rejecting multiple sources/targets until batch execution is implemented. Findings verified but not changed (matches existing codebase pattern in vacuum/balance/erasure_coding handlers): - register.go globalTaskDef.Config race: same unsynchronized pattern in all 4 task packages. - CreateTask using generated ID: same fmt.Sprintf pattern in all 4 task packages. * fix(ec_balance): harden parameter decoding, progress tracking, and validation ec_balance_handler.go (decodeECBalanceTaskParams): - Validate execution-critical fields (Sources[0].Node, ShardIds, Targets[0].Node, ShardIds) after protobuf deserialization. - Require source_disk_id and target_disk_id in legacy fallback path so Targets[0].DiskId is populated for VolumeEcShardsCopyRequest. - All error messages reference decodeECBalanceTaskParams and the specific missing field (TaskParams, shard_id, Targets[0].DiskId, EcBalanceTaskParams) for debuggability. ec_balance_task.go: - Track progress in ECBalanceTask.progress field, updated via reportProgress() helper called before ReportProgressWithStage(), so GetProgress() returns real stage progress instead of stale 0. - Validate: require exactly 1 source and 1 target (mirrors Execute guard), require ShardIds on both, with error messages referencing ECBalanceTask.Validate and the specific field. * fix(ec_balance): fix dedup execution path, stale topology, collection filter, timeout, and dedupeKey detection.go: - Dedup moves now set target=source so isDedupPhase() triggers the unmount+delete-only execution path instead of attempting a copy. - Apply moves to in-memory topology between phases via applyMovesToTopology() so subsequent phases see updated shard placement and don't conflict with already-planned moves. - detectGlobalImbalance now accepts allowedVids and filters both shard counting and shard selection to respect CollectionFilter. ec_balance_task.go: - Apply EcBalanceTaskParams.TimeoutSeconds to the context via context.WithTimeout so all RPC operations respect the configured timeout instead of hanging indefinitely. ec_balance_handler.go: - Include source node ID in dedupeKey so dedup deletions from different source nodes for the same shard aren't collapsed. - Clamp minServerCountRaw and minIntervalRaw lower bounds on int64 before narrowing to int, preventing undefined overflow on 32-bit. * fix(ec_balance): log warning before cancelling on progress send failure Log the error, job ID, job type, progress percentage, and stage before calling execCancel() in the progress callback so failed progress sends are diagnosable instead of silently cancelling. |
||
|
Chris Lu
|
c4d642b8aa |
fix(ec): gather shards from all disk locations before rebuild (#8633)
* fix(ec): gather shards from all disk locations before rebuild (#8631)
Fix "too few shards given" error during ec.rebuild on multi-disk volume
servers. The root cause has two parts:
1. VolumeEcShardsRebuild only looked at a single disk location for shard
files. On multi-disk servers, the existing local shards could be on one
disk while copied shards were placed on another, causing the rebuild to
see fewer shards than actually available.
2. VolumeEcShardsCopy had a DiskId condition (req.DiskId == 0 &&
len(vs.store.Locations) > 0) that was always true, making the
FindFreeLocation fallback dead code. This meant copies always went to
Locations[0] regardless of where existing shards were.
Changes:
- VolumeEcShardsRebuild now finds the location with the most shards,
then gathers shard files from other locations via hard links (or
symlinks for cross-device) before rebuilding. Gathered files are
cleaned up after rebuild.
- VolumeEcShardsCopy now only uses Locations[DiskId] when DiskId > 0
(explicitly set). Otherwise, it prefers the location that already has
the EC volume, falling back to HDD then any free location.
- generateMissingEcFiles now logs shard counts and provides a clear
error message when not enough shards are found, instead of passing
through to the opaque reedsolomon "too few shards given" error.
* fix(ec): update test to match skip behavior for unrepairable volumes
The test expected an error for volumes with insufficient shards, but
commit
|
||
|
Chris LuandCopilot
|
5acb4578ab |
Fix ec.rebuild failing on unrepairable volumes instead of skipping (#8632)
* Fix ec.rebuild failing on unrepairable volumes instead of skipping them When an EC volume has fewer shards than DataShardsCount, ec.rebuild would return an error and abort the entire operation. Now it logs a warning and continues rebuilding the remaining volumes. Fixes #8630 * Remove duplicate volume ID in unrepairable log message --------- Co-authored-by: Copilot <copilot@github.com> |
||
|
Chris Lu
|
2f51a94416 |
feat(vacuum): add volume state and location filters to vacuum handler (#8625)
* feat(vacuum): add volume state, location, and enhanced collection filters Align the vacuum handler's admin config with the balance handler by adding: - volume_state filter (ALL/ACTIVE/FULL) to scope vacuum to writable or read-only volumes - data_center_filter, rack_filter, node_filter to scope vacuum to specific infrastructure locations - Enhanced collection_filter description matching the balance handler's ALL_COLLECTIONS/EACH_COLLECTION/regex modes The new filters reuse filterMetricsByVolumeState() and filterMetricsByLocation() already defined in the same package. * use wildcard matchers for DC/rack/node filters Replace exact-match and CSV set lookups with wildcard matching from util/wildcard package. Patterns like "dc*", "rack-1?", or "node-a*" are now supported in all location filter fields for both balance and vacuum handlers. * add nil guard in filterMetricsByLocation |
||
|
Chris Lu
|
6fc0489dd8 |
feat(plugin): make page tabs and sub-tabs addressable by URLs (#8626)
* feat(plugin): make page tabs and sub-tabs addressable by URLs Update the plugin page so that clicking tabs and sub-tabs pushes browser history via history.pushState(), enabling bookmarkable URLs, browser back/forward navigation, and shareable links. URL mapping: - /plugin → Overview tab - /plugin/configuration → Configuration sub-tab - /plugin/detection → Job Detection sub-tab - /plugin/queue → Job Queue sub-tab - /plugin/execution → Job Execution sub-tab Job-type-specific URLs use the ?job= query parameter (e.g., /plugin/configuration?job=vacuum) so that a specific job type tab is pre-selected on page load. Changes: - Add initialJob parameter to Plugin() template and handler - Extract ?job= query param in renderPluginPage handler - Add buildPluginURL/updateURL helpers in JavaScript - Push history state on top-tab, sub-tab, and job-type clicks - Listen for popstate to restore tab state on back/forward - Replace initial history entry on page load via replaceState * make popstate handler async with proper error handling Await loadDescriptorAndConfig so data loading completes before rendering dependent views. Log errors instead of silently swallowing them. |
||
|
Chris Lu
|
baae672b6f |
feat: auto-disable master vacuum when plugin worker is active (#8624)
* feat: auto-disable master vacuum when plugin vacuum worker is active When a vacuum-capable plugin worker connects to the admin server, the admin server calls DisableVacuum on the master to prevent the automatic scheduled vacuum from conflicting with the plugin worker's vacuum. When the worker disconnects, EnableVacuum is called to restore the default behavior. A safety net in the topology refresh loop re-enables vacuum if the admin server disconnects without cleanup. * rename isAdminServerConnected to isAdminServerConnectedFunc * add 5s timeout to DisableVacuum/EnableVacuum gRPC calls Prevents the monitor goroutine from blocking indefinitely if the master is unresponsive. * track plugin ownership of vacuum disable to avoid overriding operator - Add vacuumDisabledByPlugin flag to Topology, set when DisableVacuum is called while admin server is connected (i.e., by plugin monitor) - Safety net only re-enables vacuum when it was disabled by plugin, not when an operator intentionally disabled it via shell command - EnableVacuum clears the plugin flag * extract syncVacuumState for testability, add fake toggler tests Extract the single sync step into syncVacuumState() with a vacuumToggler interface. Add TestSyncVacuumState with a fake toggler that verifies disable/enable calls on state transitions. * use atomic.Bool for isDisableVacuum and vacuumDisabledByPlugin Both fields are written by gRPC handlers and read by the vacuum goroutine, causing a data race. Use atomic.Bool with Store/Load for thread-safe access. * use explicit by_plugin field instead of connection heuristic Add by_plugin bool to DisableVacuumRequest proto so the caller declares intent explicitly. The admin server monitor sets it to true; shell commands leave it false. This prevents an operator's intentional disable from being auto-reversed by the safety net. * use setter for admin server callback instead of function parameter Move isAdminServerConnected from StartRefreshWritableVolumes parameter to Topology.SetAdminServerConnectedFunc() setter. Keeps the function signature stable and decouples the topology layer from the admin server concept. * suppress repeated log messages on persistent sync failures Add retrying parameter to syncVacuumState so the initial state transition is logged at V(0) but subsequent retries of the same transition are silent until the call succeeds. * clear plugin ownership flag on manual DisableVacuum Prevents stale plugin flag from causing incorrect auto-enable when an operator manually disables vacuum after a plugin had previously disabled it. * add by_plugin to EnableVacuumRequest for symmetric ownership tracking Plugin-driven EnableVacuum now only re-enables if the plugin was the one that disabled it. If an operator manually disabled vacuum after the plugin, the plugin's EnableVacuum is a no-op. This prevents the plugin monitor from overriding operator intent on worker disconnect. * use cancellable context for monitorVacuumWorker goroutine Replace context.Background() with a cancellable context stored as bgCancel on AdminServer. Shutdown() calls bgCancel() so monitorVacuumWorker exits cleanly via ctx.Done(). * track operator and plugin vacuum disables independently Replace single isDisableVacuum flag with two independent flags: vacuumDisabledByOperator and vacuumDisabledByPlugin. Each caller only flips its own flag. The effective disabled state is the OR of both. This prevents a plugin connect/disconnect cycle from overriding an operator's manual disable, and vice versa. * fix safety net to clear plugin flag, not operator flag The safety net should call EnableVacuumByPlugin() to clear only the plugin disable flag when the admin server disconnects. The previous call to EnableVacuum() incorrectly cleared the operator flag instead. |
||
|
Chris Lu
|
8056b702ba |
feat(balance): replica placement validation for volume moves (#8622)
* feat(balance): add replica placement validation for volume moves When the volume balance detection proposes moving a volume, validate that the move does not violate the volume's replication policy (e.g., ReplicaPlacement=010 requires replicas on different racks). If the preferred destination violates the policy, fall back to score-based planning; if that also violates, skip the volume entirely. - Add ReplicaLocation type and VolumeReplicaMap to ClusterInfo - Build replica map from all volumes before collection filtering - Port placement validation logic from command_volume_fix_replication.go - Thread replica map through collectVolumeMetrics call chain - Add IsGoodMove check in createBalanceTask before destination use * address PR review: extract validation closure, add defensive checks - Extract validateMove closure to eliminate duplicated ReplicaLocation construction and IsGoodMove calls - Add defensive check for empty replica map entries (len(replicas) == 0) - Add bounds check for int-to-byte cast on ExpectedReplicas (0-255) * address nitpick: rp test helper accepts *testing.T and fails on error Prevents silent failures from typos in replica placement codes. * address review: add composite replica placement tests (011, 110) Test multi-constraint placement policies where both rack and DC rules must be satisfied simultaneously. * address review: use struct keys instead of string concatenation Replace string-concatenated map keys with typed rackKey/nodeKey structs to eliminate allocations and avoid ambiguity if IDs contain spaces. * address review: simplify bounds check, log fallback error, guard source - Remove unreachable ExpectedReplicas < 0 branch (outer condition already guarantees > 0), fold bounds check into single condition - Log error from planBalanceDestination in replica validation fallback - Return false from IsGoodMove when sourceNodeID not found in existing replicas (inconsistent cluster state) * address review: use slices.Contains instead of hand-rolled helpers Replace isAmongDC and isAmongRack with slices.Contains from the standard library, reducing boilerplate. |
||
|
Chris Lu
|
47ddf05d95 |
feat(plugin): DC/rack/node filtering for volume balance (#8621)
* feat(plugin): add DC/rack/node filtering for volume balance detection Add scoping filters so balance detection can be limited to specific data centers, racks, or nodes. Filters are applied both at the metrics level (in the handler) and at the topology seeding level (in detection) to ensure only the targeted infrastructure participates in balancing. * address PR review: use set lookups, deduplicate test helpers, add target checks * address review: assert non-empty tasks in filter tests Prevent vacuous test passes by requiring len(tasks) > 0 before checking source/target exclusions. * address review: enforce filter scope in fallback, clarify DC filter - Thread allowedServers into createBalanceTask so the fallback planner cannot produce out-of-scope targets when DC/rack/node filters are active - Update data_center_filter description to clarify single-DC usage * address review: centralize parseCSVSet, fix filter scope leak, iterate all targets - Extract ParseCSVSet to shared weed/worker/tasks/util package, remove duplicates from detection.go and volume_balance_handler.go - Fix metric accumulation re-introducing filtered-out servers by only counting metrics for servers that passed DC/rack/node filters - Trim DataCenterFilter before matching to handle trailing spaces - Iterate all task.TypedParams.Targets in filter tests, not just [0] * remove useless descriptor string test |
||
|
Chris Lu
|
00ce1c6eba |
feat(plugin): enhanced collection filtering for volume balance (#8620)
* feat(plugin): enhanced collection filtering for volume balance Replace wildcard matching with three collection filter modes: - ALL_COLLECTIONS (default): treat all volumes as one pool - EACH_COLLECTION: run detection separately per collection - Regex pattern: filter volumes by matching collection names The EACH_COLLECTION mode extracts distinct collections from metrics and calls Detection() per collection, sharing the maxResults budget and clusterInfo (with ActiveTopology) across all calls. * address PR review: fix wildcard→regexp replacement, optimize EACH_COLLECTION * address nitpick: fail fast on config errors (invalid regex) Add configError type so invalid collection_filter regex returns immediately instead of retrying across all masters with the same bad config. Transient errors still retry. * address review: constants, unbounded maxResults, wildcard compat - Define collectionFilterAll/collectionFilterEach constants to eliminate magic strings across handler and metrics code - Fix EACH_COLLECTION budget loop to treat maxResults <= 0 as unbounded, matching Detection's existing semantics - Treat "*" as ALL_COLLECTIONS for backward compat with wildcard * address review: nil guard in EACH_COLLECTION grouping loop * remove useless descriptor string test |
||
|
Chris Lu
|
34fe289f32 |
feat(balance): add volume state filter (ALL/ACTIVE/FULL) (#8619)
* feat(balance): add volume state filter (ALL/ACTIVE/FULL) Add a volume_state admin config field to the plugin worker volume balance handler, matching the shell's -volumeBy flag. This allows filtering volumes by state before balance detection: - ALL (default): consider all volumes - ACTIVE: only writable volumes below the size limit (FullnessRatio < 1.01) - FULL: only read-only volumes above the size limit (FullnessRatio >= 1.01) The 1.01 threshold mirrors the shell's thresholdVolumeSize constant. * address PR review: use enum/select widget, switch-based filter, nil safety - Change volume_state field from string/text to enum/select with dropdown options (ALL, ACTIVE, FULL) - Refactor filterMetricsByVolumeState to use switch with predicate function for clearer extensibility - Add nil-check guard to prevent panic on nil metric elements - Add TestFilterMetricsByVolumeState_NilElement regression test |
||
|
Chris Lu
|
f3c5ba3cd6 |
feat(filer): add lazy directory listing for remote mounts (#8615)
* feat(filer): add lazy directory listing for remote mounts Directory listings on remote mounts previously only queried the local filer store. With lazy mounts the listing was empty; with eager mounts it went stale over time. Add on-demand directory listing that fetches from remote and caches results with a 5-minute TTL: - Add `ListDirectory` to `RemoteStorageClient` interface (delimiter-based, single-level listing, separate from recursive `Traverse`) - Implement in S3, GCS, and Azure backends using each platform's hierarchical listing API - Add `maybeLazyListFromRemote` to filer: before each directory listing, check if the directory is under a remote mount with an expired cache, fetch from remote, persist entries to the local store, then let existing listing logic run on the populated store - Use singleflight to deduplicate concurrent requests for the same directory - Skip local-only entries (no RemoteEntry) to avoid overwriting unsynced uploads - Errors are logged and swallowed (availability over consistency) * refactor: extract xattr key to constant xattrRemoteListingSyncedAt * feat: make listing cache TTL configurable per mount via listing_cache_ttl_seconds Add listing_cache_ttl_seconds field to RemoteStorageLocation protobuf. When 0 (default), lazy directory listing is disabled for that mount. When >0, enables on-demand directory listing with the specified TTL. Expose as -listingCacheTTL flag on remote.mount command. * refactor: address review feedback for lazy directory listing - Add context.Context to ListDirectory interface and all implementations - Capture startTime before remote call for accurate TTL tracking - Simplify S3 ListDirectory using ListObjectsV2PagesWithContext - Make maybeLazyListFromRemote return void (errors always swallowed) - Remove redundant trailing-slash path manipulation in caller - Update tests to match new signatures * When an existing entry has Remote != nil, we should merge remote metadata into it rather than replacing it. * fix(gcs): wrap ListDirectory iterator error with context The raw iterator error was returned without bucket/path context, making it harder to debug. Wrap it consistently with the S3 pattern. * fix(s3): guard against nil pointer dereference in Traverse and ListDirectory Some S3-compatible backends may return nil for LastModified, Size, or ETag fields. Check for nil before dereferencing to prevent panics. * fix(filer): remove blanket 2-minute timeout from lazy listing context Individual SDK operations (S3, GCS, Azure) already have per-request timeouts and retry policies. The blanket timeout could cut off large directory listings mid-operation even though individual pages were succeeding. * fix(filer): preserve trace context in lazy listing with WithoutCancel Use context.WithoutCancel(ctx) instead of context.Background() so trace/span values from the incoming request are retained for distributed tracing, while still decoupling cancellation. * fix(filer): use Store.FindEntry for internal lookups, add Uid/Gid to files, fix updateDirectoryListingSyncedAt - Use f.Store.FindEntry instead of f.FindEntry for staleness check and child lookups to avoid unnecessary lazy-fetch overhead - Set OS_UID/OS_GID on new file entries for consistency with directories - In updateDirectoryListingSyncedAt, use Store.UpdateEntry for existing directories instead of CreateEntry to avoid deleteChunksIfNotNew and NotifyUpdateEvent side effects * fix(filer): distinguish not-found from store errors in lazy listing Previously, any error from Store.FindEntry was treated as "not found," which could cause entry recreation/overwrite on transient DB failures. Now check for filer_pb.ErrNotFound explicitly and skip entries or bail out on real store errors. * refactor(filer): use errors.Is for ErrNotFound comparisons |
||
|
Chris Lu
|
0443b66a75 |
fix(helm): trim whitespace before s3 TLS args to prevent command breakage (#8614)
* fix(helm): trim whitespace before s3 TLS args to prevent command breakage (#8613) When global.enableSecurity is enabled, the `{{ include }}` call for s3 TLS args lacked the leading dash (`{{-`), producing an extra blank line in the rendered shell command. This broke shell continuation and caused the filer (and s3/all-in-one) to crash because arguments after the blank line were silently dropped. * ci(helm): assert no blank lines in security+S3 command blocks Renders the chart with global.enableSecurity=true and S3 enabled for normal mode (filer + s3 deployments) and all-in-one mode, then parses every /bin/sh -ec command block and fails if any contains blank lines. This catches the whitespace regression from #8613 where a missing {{- dash on the seaweedfs.s3.tlsArgs include produced a blank line that broke shell continuation. * ci(helm): enable S3 in all-in-one security render test The s3.tlsArgs include is gated by allInOne.s3.enabled, so without this flag the all-in-one command block wasn't actually exercising the TLS args path. |
||
|
Chris Lu
|
bfd0d5c084 |
fix(helm): use componentName for all service names to fix truncation mismatch (#8612)
* fix(helm): use componentName for all service names to fix truncation mismatch (#8610) PR #8143 updated statefulsets and deployments to use the componentName helper (which truncates the fullname before appending the suffix), but left service definitions using the old `printf + trunc 63` pattern. When release names are long enough, these two strategies produce different names, causing DNS resolution failures (e.g., S3 cannot find the filer-client service and falls back to localhost:8888). Unify all service name definitions and cluster address helpers to use the componentName helper consistently. * refactor(helm): simplify cluster address helpers with ternary * test(helm): add regression test for service name truncation with long release names Renders the chart with a >63-char fullname in both normal and all-in-one modes, then asserts that Service metadata.name values match the hostnames produced by cluster.masterAddress, cluster.filerAddress, and the S3 deployment's -filer= argument. Prevents future truncation/DNS mismatch regressions like #8610. * fix(helm-ci): limit S3_FILER_HOST extraction to first match |
||
|
|
92a76fc1a2 |
fix(filer): limit concurrent proxy reads per volume server (#8608)
* fix(filer): limit concurrent proxy reads per volume server Add a per-volume-server semaphore (default 16) to proxyToVolumeServer to prevent replication bursts from overwhelming individual volume servers with hundreds of concurrent connections, which causes them to drop connections with "unexpected EOF". Excess requests queue up and respect the client's context, returning 503 if the client disconnects while waiting. Also log io.CopyBuffer errors that were previously silently discarded. * Apply suggestion from @gemini-code-assist[bot] Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> * fix(filer): use non-blocking release for proxy semaphore Prevents a goroutine from blocking forever if releaseProxySemaphore is ever called without a matching acquire. * test(filer): clean up proxySemaphores entries in all proxy tests --------- Co-authored-by: Copilot <copilot@github.com> Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> |
||
|
Chris LuandCopilot
|
b665c329bc |
fix(replication): resume partial chunk reads on EOF instead of re-downloading (#8607)
* fix(replication): resume partial chunk reads on EOF instead of re-downloading When replicating chunks and the source connection drops mid-transfer, accumulate the bytes already received and retry with a Range header to fetch only the remaining bytes. This avoids re-downloading potentially large chunks from scratch on each retry, reducing load on busy source servers and speeding up recovery. * test(replication): add tests for downloadWithRange including gzip partial reads Tests cover: - No offset (no Range header sent) - With offset (Range header verified) - Content-Disposition filename extraction - Partial read + resume: server drops connection mid-transfer, client resumes with Range from the offset of received bytes - Gzip partial read + resume: first response is gzip-encoded (Go auto- decompresses), connection drops, resume request gets decompressed data (Go doesn't add Accept-Encoding when Range is set, so the server decompresses), combined bytes match original * fix(replication): address PR review comments - Consolidate downloadWithRange into DownloadFile with optional offset parameter (variadic), eliminating code duplication (DRY) - Validate HTTP response status: require 206 + correct Content-Range when offset > 0, reject when server ignores Range header - Use if/else for fullData assignment for clarity - Add test for rejected Range (server returns 200 instead of 206) * refactor(replication): remove unused ReplicationSource interface The interface was never referenced and its signature didn't match the actual FilerSource.ReadPart method. --------- Co-authored-by: Copilot <copilot@github.com> |
||
|
Chris LuandCopilot
|
e4a77b8b16 |
feat(admin): support env var and security.toml for credentials (#8606)
* feat(security): add [admin] section to security.toml scaffold Add admin credential fields (user, password, readonly.user, readonly.password) to security.toml. Via viper's WEED_ env prefix and AutomaticEnv(), these are automatically overridable as WEED_ADMIN_USER, WEED_ADMIN_PASSWORD, etc. Ref: https://github.com/seaweedfs/seaweedfs/discussions/8586 * feat(admin): support env var and security.toml fallbacks for credentials Add applyViperFallback() to read admin credentials from security.toml / WEED_* environment variables when CLI flags are not explicitly set. This allows systems like NixOS to pass secrets via env vars instead of CLI flags, which appear in process listings. Precedence: CLI flag > env var / security.toml > default value. Also change -adminUser default from "admin" to "" so that credentials are fully opt-in. Ref: https://github.com/seaweedfs/seaweedfs/discussions/8586 * feat(helm): use WEED_ env vars for admin credentials instead of CLI flags Rename SEAWEEDFS_ADMIN_USER/PASSWORD to WEED_ADMIN_USER/PASSWORD so viper picks them up natively. Remove -adminUser/-adminPassword shell expansion from command args since the Go binary now reads these directly via viper. * docs(admin): document env var and security.toml credential support Add environment variable mapping table, security.toml example, and precedence rules to the admin README. * style(security): use nested [admin.readonly] table in security.toml Use a nested TOML table instead of dotted keys for the readonly credentials. More idiomatic and easier to read; no change in how Viper parses it. * fix(admin): use util.GetViper() for env var support and fix README example applyViperFallback() was using viper.GetString() directly, which bypasses the WEED_ env prefix and AutomaticEnv setup that only happens in util.GetViper(). Switch to util.GetViper().GetString() so WEED_ADMIN_* environment variables are actually picked up. Also fix the README example to include WEED_ADMIN_USER alongside WEED_ADMIN_PASSWORD, since runAdmin() rejects an empty username when a password is set. * fix(admin): restore default adminUser to "admin" Defaulting adminUser to "" broke the common flow of setting only WEED_ADMIN_PASSWORD — runAdmin() rejects an empty username when a password is set. Restore "admin" as the default so that setting only the password works out of the box. * docs(admin): align README security.toml example with scaffold format Use nested [admin.readonly] table instead of flat dotted keys to match the format in weed/command/scaffold/security.toml. * docs(admin): remove README.md in favor of wiki page Admin documentation lives at the wiki (Admin-UI.md). Remove the in-repo README to avoid maintaining duplicate docs. --------- Co-authored-by: Copilot <copilot@github.com> |
||
|
Chris Lu
|
d1a631123f |
fix(s3api): allow bucket recreation when orphaned collection exists (#8605)
* fix(s3api): allow bucket recreation when orphaned collection exists (#8601) When a bucket is deleted, its filer directory is removed but the underlying collection/volumes may not be fully cleaned up yet. If the bucket is immediately recreated, PutBucketHandler was returning ErrBucketAlreadyExists due to the orphaned collection, blocking bucket recreation and causing subsequent uploads to fail with InternalError. Allow bucket creation to proceed when a collection exists without a corresponding bucket directory, since this is a transient orphaned state from a previous deletion. * fix(s3api): handle concurrent bucket creation race in mkdir On mkdir failure, re-check whether the bucket directory now exists and return BucketAlreadyExists instead of InternalError when another request created the bucket concurrently. |
||
|
Chris Lu
|
b799650357 |
fix(shell): set LastLocalSyncTsNs in remote.copy.local so remote.uncache works (#8604)
remote.uncache checks LastLocalSyncTsNs to determine if a file has been synced to remote. remote.copy.local was not setting this field, leaving it at 0, which caused uncache to skip all files uploaded via remote.copy.local. Fixes #8602 |
||
|
Chris Lu
|
2ff4a07544 |
Reduce task logger glog noise and remove per-write fsync (#8603)
* Reduce task logger noise: stop duplicating every log entry to glog and stderr Every task log entry was being tripled: written to the task log file, forwarded to glog (which writes to /tmp by default with no rotation), and echoed to stderr. This caused glog files to fill /tmp on long-running workers. - Remove INFO/DEBUG forwarding to glog (only ERROR/WARNING remain) - Remove stderr echo of every log line - Remove fsync on every single log write (unnecessary for log files) * Fix glog call depth for correct source file attribution The call stack is: caller → Error() → log() → writeLogEntry() → glog.ErrorDepth(), so depth=4 is needed for glog to report the original caller's file and line number. |
||
|
Chris Lu
|
e1e4c9437a |
fix(s3api): ListObjects with trailing-slash prefix matches sibling directories (#8599)
fix(s3api): ListObjects with trailing-slash prefix returns wrong results When ListObjectsV2 is called with a prefix ending in "/" (e.g., "foo/"), normalizePrefixMarker strips the trailing slash and splits into dir="parent" and prefix="foo". The filer then lists entries matching prefix "foo", which returns both directory "foo" and "foo1000". The prefixEndsOnDelimiter guard correctly identifies directory "foo" as the target and recurses into it, but then resets the guard to false. The loop continues and incorrectly recurses into "foo1000" as well, causing the listing to return objects from unrelated directories. Fix: after recursing into the exact directory targeted by the trailing-slash prefix, return immediately from the listing loop. There is no reason to process sibling entries since the original prefix specifically targeted one directory. |
||
|
Chris Lu
|
f950a941e3 |
Fix trust policy validation for specific AWS user principals (#8597)
* Add tests for AWS user principal in AssumeRole trust policies Add test cases that verify trust policy validation when using specific AWS user principals (e.g., "arn:aws:iam::000000000000:user/backend") in the Principal field of trust policies for AssumeRole. Covers single user, multiple users (array), wildcard, and plain string principal formats. These tests demonstrate the bug reported in #8588 where specific user principals always fail validation. * Populate RequestContext in ValidateTrustPolicyForPrincipal ValidateTrustPolicyForPrincipal was creating an EvaluationContext with a nil RequestContext. The policy engine's principal matching logic looks up "aws:PrincipalArn" in RequestContext for non-wildcard principals, so specific user ARNs like "arn:aws:iam::000000000000:user/backend" always failed to match, while wildcard "*" worked because it short-circuits before the lookup. Populate RequestContext with both "principal" and "aws:PrincipalArn" keys, consistent with how IsActionAllowed already does it. Fixes #8588 * Remove GitHub discussion URL from source code comments * Add specific error message assertions in trust policy tests |