mirror of
https://github.com/seaweedfs/seaweedfs.git
synced 2026-08-16 20:26:45 +00:00
filer-conditional-create
1057
Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
  Chris LuandGitHub
|
d1665750e1 |
Delete the EC placement package now that encode/repair use ecbalancer.Place (#9624)
Delete the EC placement package and the dead encode planner code Now that encode (and repair) place via ecbalancer.Place, nothing uses the erasure_coding/placement package or the EC-only planner machinery (ecPlacementPlanner, diskInfosToCandidates, calculateECScoreCandidate, distributeECShards) in detection.go. Removes them and the package, along with the planner-direct unit tests. |
||
|
Chris LuandGitHub
|
d4e39b499b |
EC placement: shared replica-placement resolver, snapshot + Place core, capacity fixes, tiering (#9621)
* Add shared super_block.ResolveReplicaPlacement; use it in ec_balance * Add ecbalancer.FromActiveTopology snapshot constructor for EC encode/repair * Add ecbalancer.Place greenfield/repair placement core (strict + durability-first) * topology: add GetEffectiveAvailableEcShardSlots; FromActiveTopology uses shard-granular free slots GetDisksWithEffectiveCapacity flattens reserved shard slots into volume slots via integer truncation, so an in-flight EC task reserving a non-multiple-of- DataShardsCount number of shards was lost from the snapshot and freeSlots was over-reported. GetEffectiveAvailableEcShardSlots subtracts the full reservation impact at shard granularity. * ecbalancer.Place: reject nodes without a free disk of the requested type FromActiveTopology keeps all disk types in the snapshot, so an SSD-only request could be routed to a node with only HDD capacity (pickBestDiskOnNode then returns disk 0 on the wrong tier). Filter rack/node selection to those with a free disk of the requested type. * ecbalancer.Place: enforce ReplicaPlacement DiffDataCenterCount (per-DC shard cap) * ecbalancer: enforce DiffDataCenterCount in balance (cross-DC phase + cross-rack DC cap) Adds a cross-DC corrective phase that drains data centers holding more than DiffDataCenterCount shards of a volume, and a per-DC cap on cross-rack move targets. Both are no-ops when DiffDataCenterCount is unset, so balance output is unchanged for non-DC placements. * topology: ratio-aware EC shard slots and provisional empty-disk slot GetEffectiveAvailableEcShardSlots now takes the target collection's data-shard count, so a 4+2 volume's larger shards are not over-counted at 10 per volume slot; and it keeps the one provisional slot for freshly started empty servers that report max=0, matching getEffectiveAvailableCapacityUnsafe. FromActiveTopology threads the ratio through. * ecbalancer.Place: explicit disk-type filter signal (fix HDD vs any ambiguity) HardDriveType normalizes to "", which collided with "" meaning any disk. Add Constraints.FilterDiskType and normalize both sides so a hdd request matches disks reported as "" and never leaks to SSD, while filter=false still means any. * ecbalancer: add clearShardAccounting for repair snapshot reconciliation Clears one disk's copy of a shard from per-domain accounting and recomputes the node-level union (preserving a kept copy on another disk of the same node), without crediting capacity. Repair uses it to drop to-be-deleted copies before placing missing shards. * ecbalancer: don't cap cross-DC target racks when DiffRackCount is unset len(racks)+1 wrongly limited each target rack (3 in a 2-rack cluster), so draining a DC could stop short of the DiffDataCenterCount cap. Use MaxShardCount+1 as the effectively-unlimited default. * topology/ecbalancer: ratio-correct EC capacity accounting Reservation shard slots (default ShardsPerVolumeSlot units) are now converted to the target ratio before subtracting, and existing EC shards are charged by size (targetDataShards/shardDataShards) so a 2+1 shard isn't counted as one 10+4 slot. Per-shard ratio lookup is behind shardDataShards (OSS uses the standard ratio). * ecbalancer.Place: candidate tiering and eligible-rack caps Adds a per-disk eligibility/preference abstraction so Place supports: - preferred-tag whole-plan retry (try disks carrying the earliest tags first, widen to all only if a tier cannot place every shard; reports SpilledOutsidePreferredTags), - soft disk-type spill via DiskTypePolicy (Any/Prefer/Require): Prefer fills the preferred type then spills, reporting SpilledToOtherDiskType; Require filters, - even per-rack caps that divide by racks holding an eligible disk, so a tiered cluster (e.g. SSDs in 2 of 4 racks) isn't capped impossibly low. Disk tags carried via Node.AddDiskTags + FromActiveTopology. * ecbalancer: export ClearShardAccounting for repair snapshot reconciliation * ecbalancer: address review feedback (ratio rounding, bitmap walk, same-DC moves) - topology/ecbalancer: round shard-reservation and existing-shard footprint up when converting to target-ratio shard slots, so a sub-slot reservation is not truncated to zero and free capacity is not overstated for low-data-shard layouts (targetDataShards < ds). - erasure_coding: add ShardBits.All iterator and use it across the balancer, cross-DC phase, and placement scoring instead of scanning 0..MaxShardCount and probing Has on every id. - ecbalancer: allow same-DC cross-rack moves when a DC already sits at its DiffDataCenterCount cap; a same-DC move leaves the DC total unchanged. Add a regression test that fails without the guard. - ecbalancer cross-DC phase: pick targets via the eligible-aware pickNodeInRackEligible/pickBestDiskEligible helpers so the disk-type filter is honored and a 0 disk id is not mistaken for a valid selection. * ecbalancer: test ecShardSlotsOnDisk fractional round-up Cover the mixed-ratio path (targetDataShards < existing data shards) so a shard's fractional footprint is never floored to zero and free capacity is not overstated. Exercises the round-up via the targetDataShards parameter; OSS uses the standard ratio at runtime while the enterprise build hits it with real per-volume ratios. * ecbalancer: assert node B rack in TestFromActiveTopology * ecbalancer: split Destination into separate DataCenter and bare Rack Replace the composite "dc:rack" Rack field on Destination with separate DataCenter and bare Rack values, matching topology.DiskInfo and the worker-task convention. Callers (and tests) read the data center directly instead of parsing the composite with strings.SplitN. * shell ec.balance: use utilization-based global balancing (parity with worker) The shell's global rebalance phase balanced by raw shard count; switch it to fractional fullness (shards/capacity), as the worker already does. On uniform capacity the two agree; on heterogeneous capacity it fills nodes proportionally instead of driving small-capacity nodes toward full. Updates the heterogeneous-capacity regression test to assert even fullness (~equal shards/capacity per node) rather than even shard count. * ecbalancer: bounded-proportional per-DC shard spread DiffDataCenterCount was enforced only as a ceiling (drain-to-cap), which could leave a within-cap-but-lopsided DC distribution under a loose cap (e.g. 10/4 of 14 with cap=10). Now the cross-DC phase, the cross-rack DC guard, and Place all target boundedMaxPerDC = min(DiffDataCenterCount, max(ceil(total/numDCs), parityShards)): shards spread proportionally across DCs, but no tighter than the durability floor (once each DC holds <= parityShards a DC loss is recoverable, so further spreading only adds cross-DC/WAN traffic). No-op when DiffDataCenterCount is 0; identical to before when the cap is the binding constraint. * ecbalancer: drop DiffDataCenterCount enforcement for EC placement The 1-byte volume ReplicaPlacement packs xyz into x*100+y*10+z<=255, so the DC digit can only be 0-2 -- far too small to be a meaningful per-DC EC shard cap (a cap of 1-2 would demand 7-14 DCs for a 10+4 volume). It's volume replica-placement, not an EC spec. Removes the cross-DC balance phase, the DC guard in the cross-rack phase, and the per-DC cap in Place (and the just-added bounded-proportional logic); EC relies on the RP-independent rack/node even spread instead. Rack/node caps (DiffRackCount/SameRackCount) are unchanged. Per-domain EC caps are left for a real EC placement spec. * ecbalancer: enforce per-disk durability cap; symmetric reserve/release Place now refuses to put more than parityShards shards of a volume on a single disk (pickBestDiskEligible skips a disk once it holds parityShards of the volume, a hard cap not relaxed even in durability-first). Previously Place assigned by free capacity, so a skewed near-full cluster could pile >parityShards onto one disk -> losing it loses the volume; only distinct-disk count was checked. This covers encode and repair (both route through Place); the caller skips/leaves the volume rather than minting an unrecoverable layout. Also makes reserveShard decrement freeSlots unconditionally, symmetric with releaseShard's unconditional increment (the old guarded decrement could credit a phantom slot on release if a shard were ever reserved onto a full disk). * ecbalancer: add Topology.ReleaseVolumeShards (clear + credit) for greenfield encode Releases all of a volume's shards from the snapshot and credits the freed disk capacity, so a greenfield encode can plan as if stale EC shards from a prior failed attempt are gone. Safe to credit because the encode task deletes stale shards (cleanupStaleEcShards) before distributing the new ones. Distinct from ClearShardAccounting (repair), which does not credit. * ecbalancer: ReleaseVolumeShards credits node freeSlots, not just disks releaseShard only increments per-disk freeSlots, but rack capacity is summed from node freeSlots (buildRacks) and node freeSlots gates node eligibility. Crediting only disks left a node/rack looking full after releasing stale shards, so a greenfield encode still couldn't use the freed capacity. Now credits the node by the total disk-slots freed. * ecbalancer: correct PlacementMode docs (encode uses durability-first) PlaceStrict was labeled '(encode)' but encode uses PlaceDurabilityFirst. Clarify that durability-first is used by both encode and repair, reports relaxations in PlaceResult.Relaxed, and never relaxes the per-disk durability cap. * ecbalancer: treat SameRackCount as a direct per-node shard cap The 3rd ReplicaPlacement digit now caps shards per node at exactly the digit value, matching how DiffRackCount (2nd digit) caps per rack, instead of allowing digit+1 per node. This makes the per-rack and per-node caps consistent and matches the documented "digits cap EC shards per rack and per node" semantics; e.g. 011 now means at most one shard per rack and one per node. |
||
|
Chris LuandGitHub
|
5b42287c22 |
fix(storage): surface stat error on zero-size idx scrub, mirror to rust (#9612)
fix(storage): harden zero-size idx scrub and mirror to rust When a zero-size .idx is found, openIndex stats the backing .dat through v.DataBackend: wrap that GetStat failure with %w, fix the indices typo, and guard both openIndex and scrubVolumeData against a nil DataBackend (closed or remote-only volumes) instead of panicking. Add rust scrub tests for empty (superblock-only .dat, zero-size .idx) and healthy volumes, keeping the volume server in parity with the go zero-size scrub handling. |
||
 Lisandro PinandGitHub
|
39e9294907 |
Have volume scrubs account for zero-sized volumes. (#9609)
Fixes scrubbing for pre-allocated volumes with zero-size indeces by reworking the validation code to allow zero-size indeces on zero-size volumes. |
||
|
Chris LuandGitHub
|
cd15ae1395 |
fix(ec): bring ec.encode worker and EC/volume helpers to parity with shell (#9599)
* refactor(volume): extract replica sync/select into shared volume_replica package Move the volume replica reconciliation helpers (status, union builder, SyncAndSelectBestReplica, ReadNeedleMeta) out of the shell into a new weed/storage/volume_replica package so both the shell (ec.encode, volume.tier.move, volume.check.disk) and the EC encode worker can reuse them. No behavior change. * fix(ec): bring ec.encode worker to parity with the shell - Sync replicas and encode the most-complete one (via the shared volume_replica.SyncAndSelectBestReplica) instead of a possibly-stale replica, marking all replicas readonly first. Prevents silent data loss when a stale replica is encoded and the originals deleted. - Skip remote/tiered volumes in detection (shell ec.encode excludes them). - Min-node safety gate: refuse to encode when cluster nodes < parity shards. - Align default thresholds with the shell (fullness 0.95, quiet 1h). * fix(vacuum): plugin path honors min_volume_age_seconds override deriveVacuumConfig hard-coded MinVolumeAgeSeconds=0, dropping any configured value. Read it from worker config (default 0, matching the shell/master vacuum which has no age gate) so an explicit override is honored. * address review feedback - config.go: align GetConfigSpec schema defaults (quiet_for_seconds=3600, fullness_ratio=0.95) with the runtime defaults so UI/bootstrap flows match the shell (coderabbitai). - ec_task.go: roll back readonly when markReplicasReadonly fails partway, so already-marked replicas don't stay readonly (coderabbitai). - volume_replica: pass the caller's replica statuses into buildUnionReplica instead of re-fetching them, and skip the per-needle ReadNeedleMeta RPC when the source replica is read-only (gemini-code-assist). * test(plugin_workers/ec): make fixtures eligible under the new defaults The default EC encode thresholds were raised to match the shell (fullness 0.95, quiet 1h), but the plugin-worker integration fixtures still used 90%-full / 10-minute-old volumes, so detection found no eligible volumes and the tests failed in CI. Bump the eligible fixtures to 96% full and 2h old. |
||
|
Chris LuandGitHub
|
303c2be38d |
feat(fix): rebuild lost EC index (.ecx) and .vif from local shards (#9596)
weed fix -ecx reconstructs the .dat from the local data shards, scans the needles, and writes a fresh ascending-sorted .ecx containing only live entries — the same on-disk index WriteSortedFileFromIdx emits at encode time. When the .vif is also missing it is regenerated from the inferred EC ratio (flags > .vif > shard-count inference / 10+4) and the .dat size recovered from the scan. When some data shards are missing but at least dataShards shards survive, the missing shards are first reconstructed from the survivors via Reed-Solomon, so a partial shard set is repaired too. Also makes erasure_coding.WriteDatFile de-stripe using len(shardFileNames) instead of the DataShardsCount constant, so the caller's actual data-shard count is honored (behavior-preserving for the default 10, and fixing the existing caller that already passes ECContext.DataShards). This recovers an EC volume whose sealed index was lost from every node while enough shards survive, a state neither ec.rebuild nor ec.decode can repair because both require an existing .ecx. Flags: -ecx, -ecDataShards, -ecParityShards. Run with the volume server stopped. |
||
|
Chris LuandGitHub
|
391f543ff2 |
fix(ec): correct multi-disk disk counting and EC balance shard attribution (#9594)
* fix(shell): count physical disks in cluster.status on multi-disk nodes
The master keys DataNodeInfo.DiskInfos by disk type, so several same-type
physical disks on one node collapse into a single DiskInfo entry. cluster.status
(printClusterInfo) and CountTopologyResources counted len(DiskInfos), reporting
one disk per node instead of the real physical disk count, while volume.list and
the admin ActiveTopology already split per physical disk.
Route both counters through DiskInfo.SplitByPhysicalDisk so a node with N
same-type disks reports N. Cosmetic/diagnostic only; placement already uses the
per-disk activeDisk map.
* fix(ec): attribute EC balance source disk per shard and reject same-node moves
On multi-disk nodes the EC balance worker built a node-level view that kept only
the first physical disk id per (node, volume), so a move of a shard living on a
different disk reported the wrong source disk. That source disk drives the
per-disk capacity reservation, so the wrong disk drifts the capacity model the
EC placement planner relies on. Track shards per physical disk and resolve the
actual source disk for every emitted move (dedup, cross-rack, within-rack,
global), keeping the per-disk view consistent as simulated moves are applied.
Also close a data-loss trap: VolumeEcShardsDelete is node-wide (it removes the
shard from every disk on the node) and copyAndMountShard skips the copy when
source and target addresses match, so a same-node move would erase a shard it
never copied. isDedupPhase now requires the same node AND disk, and Validate /
Execute reject same-node cross-disk moves outright.
* fix(ec): spread EC balance moves across destination disks
Port the shell ec.balance pickBestDiskOnNode heuristic to the EC balance
worker so a moved shard is placed on a good physical disk instead of always
deferring to the volume server (target disk 0). The detection now builds a
per-physical-disk view of each node (free slots split from the node total, exact
EC shard count, disk type, discovered from both regular volumes and EC shards)
and, for each cross-rack, within-rack, and global move, chooses the destination
disk by ascending score:
- fewer total EC shards on the disk,
- far fewer shards of the same volume on the disk (spread a volume's shards
across disks for fault tolerance), and
- data/parity anti-affinity (a data shard avoids disks holding the volume's
parity shards and vice versa).
Planned placements are reserved on the in-memory model during a run so multiple
shards moved to the same node spread across its disks rather than piling on one.
* fix(ec): bring EC balance worker to parity with shell ec.balance
The worker's cross-rack and within-rack balancing balanced shards by total
count; the shell balances data and parity shards separately with anti-affinity
and honors replica placement. Port that logic so the automatic balancer makes
the same fault-tolerance-aware decisions as the manual command:
- Cross-rack and within-rack now run a two-pass balance: data shards spread
first, then parity shards spread while avoiding racks/nodes that already hold
the volume's data shards (anti-affinity), mirroring doBalanceEcShardsAcrossRacks
and doBalanceEcShardsWithinOneRack.
- Optional replica placement: a new replica_placement config (e.g. "020")
constrains shards per rack (DiffRackCount) and per node (SameRackCount); empty
keeps the previous even-spread behavior.
- The data/parity boundary is resolved from a per-collection EC ratio (standard
10+4 here), replacing the previously hardcoded constant at the call sites.
Selection is deterministic (sorted keys) to keep behavior reproducible.
* refactor(ec): extract shared ecbalancer package for shell and worker
The EC shard balancing policy was duplicated between the shell ec.balance
command and the admin EC balance worker, and the two had drifted (multi-disk
handling, data/parity anti-affinity, replica placement). Extract the policy into
a new pure package, weed/storage/erasure_coding/ecbalancer, that both callers
share so it cannot drift again.
- ecbalancer.Plan(topology, options) runs the full policy (dedup, cross-rack and
within-rack data/parity two-pass with anti-affinity, global per-rack balance,
and diversity-aware disk selection) over a caller-built Topology snapshot and
returns the shard Moves. It depends only on erasure_coding and super_block.
- The worker builds the Topology from the master topology and turns Moves into
task proposals; the shell builds it from its EcNode model and executes Moves
via the existing move/delete RPCs. Per-collection EC ratio resolution stays in
each caller (passed as Options.Ratio).
- Options expose the two genuine policy differences: GlobalUtilizationBased
(worker balances by fractional fullness; shell by raw count) and
GlobalMaxMovesPerRack (worker moves incrementally across cycles; shell drains
in one pass).
The shell keeps pickBestDiskOnNode for the evacuate command. Policy tests move to
the ecbalancer package; the shell and worker keep their adapter/execution tests.
* fix(ec): restore parallelism and per-type/full-range balancing after ecbalancer refactor
Address regressions and gaps from the ecbalancer extraction:
- Shell ec.balance honors -maxParallelization again: planned moves run phase by
phase (preserving cross-phase dependencies) with bounded concurrency within a
phase. Apply mode does only the RPCs concurrently; dry-run stays sequential and
updates the in-memory model for inspection.
- Rack and node balancing gate on per-type spread (data and parity separately)
instead of combined totals, so a data/parity skew is corrected even when the
per-rack/node totals are even.
- Global rack balancing iterates the full shard-id space (MaxShardCount) so
custom EC ratios with more than the standard total are candidates.
- Cross-rack planning decrements the destination node's free slots per planned
move, so limited-capacity targets are no longer over-planned.
* fix(ec): make EC dedup keeper deterministic and capacity-aware
When a shard is duplicated across nodes, keep the copy on the node with the most
free slots and delete the duplicates from the more-constrained nodes, relieving
capacity pressure where it is tightest. Tie-break on node id so the choice is
deterministic. This unifies the shell and worker (the shell previously kept the
least-free node, an incidental default) on the more sensible behavior.
* fix(ec): restore global volume-diversity and per-volume move serialization
Two more behaviors lost in the ecbalancer refactor:
- Global rack balancing again prefers moving a shard of a volume the destination
does not hold at all before adding another shard of an already-present volume
(two-pass, mirroring the old balanceEcRack), keeping each volume's shards
spread across nodes.
- Shell apply-mode execution serializes a single volume's moves within a phase
while still running different volumes in parallel, so concurrent moves of the
same volume cannot race on its shared .ecx/.ecj/.vif sidecar files.
* fix(ec): key EC balance shards by (collection, volume id)
A numeric volume id can be reused across collections, and EC identity is
(collection, vid) (see store_ec_attach_reservation.go). The ecbalancer keyed
Node.shards by vid alone, so volumes sharing an id across collections merged into
one entry — letting dedup delete a "duplicate" that is actually a different
collection's shard, and letting moves act across collections. Key shards by
(collection, vid) throughout so each volume stays distinct.
* fix(ec): credit freed capacity from dedup before later balance phases
Dedup deletions are simulated only by applyMovesToTopology, which cleared shard
bits but did not return the freed disk/node/rack slots. Later phases reject
destinations with no free slots, so a slot opened by dedup could not be reused in
the same Plan/ec.balance run. applyMovesToTopology now credits the freed
disk/node/rack capacity for dedup moves (non-dedup moves still rely on the inline
accounting their phase already did).
* test(ec): add multi-disk EC balance integration test
Cover issue 9593 end-to-end at the unit level the old tests missed: build the
master's actual multi-disk wire format (same-type disks collapsed into one
DiskInfo, real DiskId only in per-shard records), run it through a real
ActiveTopology and the Detection entry point, then replay the planned moves with
the volume server's true semantics (node-wide VolumeEcShardsDelete) and assert no
EC shard is ever lost. Covers a balanced spread, a one-node-concentrated volume,
and a multi-rack spread, and asserts moves are safe (no same-node cross-disk),
correctly attributed to the source disk, and redistribute concentrated volumes
across both other racks and multiple destination disks.
* fix(ec): aggregate per-disk EC shards when verifying multi-disk volumes
collectEcNodeShardsInfo overwrote its per-server entry for each EcShardInfo of a
volume. A multi-disk node reports one EcShardInfo per physical disk holding shards
of the volume, so only the last disk's shards survived — the node looked like it
was missing shards it actually had. This made ec.encode's pre-delete verification
(and ec.decode) under-count volumes whose shards are spread across disks on one
server, falsely aborting the encode on multi-disk clusters. Union the per-disk
shard sets per server instead.
Also make verifyEcShardsBeforeDelete poll briefly: shard relocations reach the
master via volume-server heartbeats, so a freshly distributed shard set may not be
fully visible the instant the balance returns. Retry before concluding the set is
incomplete; genuine loss still fails after the retries are exhausted.
* test(ec): end-to-end multi-disk EC balance shard-loss regression
Start a real cluster of multi-disk volume servers (3 servers x 4 disks),
EC-encode a volume, run ec.balance, and assert hard invariants the prior
integration tests only logged: after encode all 14 shards exist, ec.balance loses
no shard, shards span more than one disk per node, and cluster.status counts
physical disks (not one per node). This reproduces issue 9593 end to end and would
have caught the multi-disk shard-aggregation bug fixed alongside it.
* fix(ec): bring EC balance worker/plugin path to parity with shell
- Per-volume serialization and phase order: key the plugin proposal dedupe by
(collection, volume) instead of (volume, shard, source), so the scheduler runs
only one of a volume's moves at a time (within a run and against in-flight jobs).
Concurrent same-volume moves raced on the volume's .ecx/.ecj/.vif sidecars; and
because the planner emits a volume's moves in phase order, they now execute in
order across detection cycles, matching the shell.
- disk_type "hdd": normalize via ToDiskType (hdd -> "" HardDriveType) while keeping
a "filter requested" flag, so disk_type=hdd matches the empty-keyed HDD disks
instead of nothing; apply the canonical type to planner options and move params.
- Replica placement: expose shard_replica_placement in the admin config form and
read it into the worker config, mirroring ec.balance -shardReplicaPlacement.
* test(ec): rename worker in-process test (not a real integration test)
The worker-package multi-disk tests build a fake master topology and simulate
move execution; they are not real-cluster integration tests. Rename
integration_test.go -> multidisk_detection_test.go and drop the Integration
prefix so 'integration' refers only to the real-cluster E2Es in test/erasure_coding.
* ci(ec): remove redundant ec-integration workflow
ec-integration.yml duplicated EC Integration Tests under the same workflow name
but ran only 'go test ec_integration_test.go' (one file), so it never ran new
test files (e.g. multidisk_shardloss_test.go) and was a strict, path-filtered
subset of ec-integration-tests.yml, which already runs 'go test -v' over the whole
test/erasure_coding package on every push/PR.
* fix(ec): worker falls back to master default replication for EC balance
For strict parity with the shell, the EC balance worker now uses the master's
configured default replication as the replica-placement fallback when no explicit
shard_replica_placement is set, instead of always defaulting to even spread.
The maintenance scanner reads it via GetMasterConfiguration each cycle and passes
it through ClusterInfo.DefaultReplicaPlacement; detection resolves the constraint
(explicit config wins, else master default, else none) in resolveReplicaPlacement.
A zero-replication default (the common 000 case) still means even spread, so the
common configuration is unchanged.
* fix(ec): plugin path populates master default replication too
The plugin worker built ClusterInfo with only ActiveTopology, so the master
default replication fallback added for the maintenance path never reached
plugin-driven EC balance detection — empty shard_replica_placement still meant
even spread there. Fetch the master default via GetMasterConfiguration (new
pluginworker.FetchDefaultReplicaPlacement) and set ClusterInfo.DefaultReplicaPlacement
so both detection paths resolve replica placement identically to the shell.
* docs(ec): empty shard replica placement uses master default, not even spread
The EC balance config text (admin plugin form, legacy form help text, and
the struct/proto field comments) still said an empty shard_replica_placement
spreads evenly. The runtime resolves empty to the master default replication
(resolveReplicaPlacement), matching shell ec.balance, with even spread only
when that default is empty or zero. Update the text to match and regenerate
worker_pb for the proto comment change.
|
||
|
Chris LuandGitHub
|
cfc08fbf6c |
fix(volume): tombstone integrity check no longer flips volumes read-only (fixes #9563) (#9565)
* fix(volume): pass on-disk tombstone size to ReadData in verifyDeletedNeedleIntegrity verifyDeletedNeedleIntegrity was forwarding TombstoneFileSize (-1) into Needle.ReadData. A deletion tombstone is appended to .dat with DataSize=0 so the on-disk needle header carries Size=0; TombstoneFileSize is only the .idx sentinel for "this entry is deleted" and is never written into a needle header. ReadBytes' size check therefore mismatched on every tombstone (-1 != 0), returned ErrorSizeMismatch, and triggered the 4-byte-offset wrap-around retry in ReadData (offset + 32 GB). On any volume large enough that offset+32 GB exceeds dat fileSize the retry read EOF, CheckVolumeDataIntegrity reported corruption, and the loader set noWriteOrDelete = true. Every volume whose last 10 .idx entries included a deletion went read-only on startup — i.e. any healthy volume where the most recent operations included a delete. Pass Size(0) so the size check matches the on-disk tombstone header. Add a regression test that writes three needles, deletes one, and asserts CheckVolumeDataIntegrity succeeds with a tombstone at the .idx tail. Without this fix the test reproduces the exact log shape from the bug report: read 0 dataSize 32 offset <orig+32GB> fileSize <much smaller>: EOF verifyDeletedNeedleIntegrity ...idx failed: read data [N,N+32) : EOF The Rust port guards its integrity-check size comparison with !size.is_deleted() (seaweed-volume/src/storage/volume.rs) and never hits this path, so no Rust mirror change is needed. * test(seaweed-volume): mirror Go regression for deletion-tombstone integrity The Rust integrity check already guards its size-mismatch comparison with !size.is_deleted() (volume.rs:1859) and reads tombstone AppendAtNs with body_size=0, so the Go regression fixed in the previous commit does not apply. Lock that guarantee in with a parallel reload test: write three needles, delete one, sync, reopen via Volume::new, assert the volume is not flipped read-only. Catches any future change that removes the deleted-entry guard or re-introduces a size-strict path in check_volume_data_integrity for tombstones. * fix(volume): propagate io.EOF and ErrorSizeMismatch from verifyDeletedNeedleIntegrity CheckVolumeDataIntegrity relies on identity comparison against io.EOF and ErrorSizeMismatch to walk back through the last ten .idx entries and tolerate a partial truncation at the tail (the "fix and continue" loop). The live-needle branch in doCheckAndFixVolumeData already returns those sentinels unwrapped; the deletion branch wrapped them in fmt.Errorf, so a genuine .dat truncation past a tombstone offset broke the recovery and flipped the volume read-only. Mirror the live-needle handling: both verifyDeletedNeedleIntegrity and doCheckAndFixVolumeData now short-circuit on io.EOF / ErrorSizeMismatch and pass them through unwrapped. Other errors keep their existing context wrapping. Also tighten the regression test to capture lastAppendAtNs and assert it's non-zero, so a future regression that skips the tombstone body (and therefore never populates AppendAtNs) is caught even when the err check still passes. |
||
|
Chris LuandGitHub
|
b63610cf8f |
volume: accept legacy needle CRC encoding on read (#9564)
Volumes written by versions before 3.09 (commit
|
||
|
Chris LuandGitHub
|
7c252e1f16 |
fix(volume): reopen .idx writable after MarkVolumeWritable (fixes #9515) (#9526)
* fix(volume): reopen .idx writable after MarkVolumeWritable When .vif has ReadOnly=true, load() opens .idx as O_RDONLY and builds a SortedFileNeedleMap whose Put returns os.ErrInvalid. MarkVolumeWritable only flipped noWriteOrDelete back to false and rewrote .vif, so writes still failed at v.nm.Put. Reopen .idx in O_RDWR and rebuild v.nm in its writable form (in-memory or leveldb small/medium/large) before flipping the flag. Mirror the same fix in seaweed-volume: the Rust load path leaves CompactNeedleMap/RedbNeedleMap with no idx_file writer when the volume boots read-only, so post-MarkVolumeWritable puts silently succeeded in-memory only and were lost on the next restart. set_writable now reattaches an append-mode writer when one is missing. * fix(volume): keep old needle map until replacement is built; defer writable flag Go: build the writable needle map into a local before swapping. A construction failure now leaves v.nm pointing at the original SortedFileNeedleMap so MarkVolumeWritable can roll back, instead of stranding the volume with v.nm == nil. Rust: attach the .idx writer before flipping no_write_or_delete to false. A transient open/metadata failure used to leave the volume marked writable with no writer attached, and subsequent puts would silently skip the on-disk append. |
||
|
Chris LuandGitHub
|
af8d4e00ee |
fix(ec_mount): reject 0-byte .ecx and aggregate cross-disk failures (#9542)
* fix(ec_mount): reject 0-byte .ecx and aggregate cross-disk failures MountEcShards's per-disk loop bailed on the first disk returning a non-ENOENT error, and NewEcVolume wrapped its ENOENT with %v so the caller's `err == os.ErrNotExist` check never matched. On a multi-disk volume server where ec.balance / ec.rebuild had distributed shards across sibling disks while the matching .ecx never arrived, the mount loop bailed after disk 0 with "cannot open ec volume index" and the operator never saw that the rest of the disks were also empty. The companion failure mode is a 0-byte .ecx stub left by EC distribute's writeToFile after a mid-stream copy failure: Stat() succeeds, treating the stub as a valid index, and downstream mount work proceeds against an empty file. Wrap the ec-volume open errors with %w, treat a 0-byte .ecx as os.ErrNotExist (in NewEcVolume, findEcxIdxDirForVolume, and HasEcxFileOnDisk), and have MountEcShards collect per-disk failures before returning a single aggregated error. The "no .ecx anywhere" case gets a distinct error so the orchestrator can re-copy the index from a healthy replica rather than retry against the same broken state. * fix(ec_reconcile): indexEcxOwners also rejects 0-byte .ecx stubs findEcxIdxDirForVolume already skipped 0-byte .ecx during MountEcShards, but indexEcxOwners (used by reconcileEcShardsAcrossDisks at startup) still recorded the first .ecx by name only. On a store where one disk holds a 0-byte stub left by a failed EC distribute and a sibling disk holds the real index, the stub would win the owner selection — and NewEcVolume's new size check would then refuse to load against it, leaving the orphan shards unloaded even though a valid index exists. Mirror the size check from findEcxIdxDirForVolume: skip directory entries whose .ecx Info() reports size 0 or whose Info() call fails. * fix(ec_mount): accept 0-byte .ecx as valid empty index The previous commit treated a 0-byte .ecx in NewEcVolume as os.ErrNotExist, on the assumption that any empty .ecx was a stub left by a failed copy stream. That broke the legitimate empty-volume case: when an EC volume's source .idx has no live entries (e.g. all needles deleted before WriteSortedFileFromIdx), the sorted .ecx is genuinely 0 bytes and must mount. The integration test TestEcShardsToVolumeMissingShardAndNoLiveEntries fails with "MountEcShards: no .ecx index found on any local disk" because the mount path now refuses the legitimate empty index. A 0-byte .ecx left by a failed copy stream is indistinguishable from the legitimate empty case by file size alone. Preventing stub files from being written is the receiver-side cleanup in writeToFile's job (the companion EC distribute PR), not NewEcVolume's at mount time. The cross-disk lookup helpers (findEcxIdxDirForVolume, HasEcxFileOnDisk, indexEcxOwners) keep their size > 0 preference: when a real .ecx exists on a sibling disk alongside a stub, we still want to route mounts and reconcile at the real one. If no non-zero .ecx exists anywhere, the per-disk fallback in MountEcShards can still open the 0-byte .ecx and the volume mounts. Replace TestMountEcShards_ZeroByteEcxOnlyDisk with TestMountEcShards_EmptyEcxMountsSuccessfully, which pins the empty-volume invariant. |
||
|
Chris LuandGitHub
|
c11ff6657b |
fix(ec): mirror EC sidecars onto every shard-bearing disk at startup (#9525)
* fix(ec): mirror EC sidecars onto every shard-bearing disk at startup
In a multi-disk volume server, ec.balance and ec.rebuild can land shards
on a disk that does not also hold the matching .ecx / .ecj / .vif index
files. The orphan-shard reconciler in reconcileEcShardsAcrossDisks
already loads those shards by pointing the EcVolume at the sibling
disk's index files; reads work, but any failure on the index-owning
disk silently disables every shard on the other disk, even though those
shards are physically fine.
This change adds mirrorEcMetadataToShardDisks, a startup pass that
physically replicates .ecx / .ecj / .vif onto each disk that holds
shards but is missing them. Each copy is atomic (tmp + fsync + rename)
and idempotent (a destination that already has the sidecar is
preserved). After mirroring, the cross-disk reconciler prefers the
local IdxDirectory so the EcVolume mounts self-contained; the
cross-disk virtual mount remains as a fallback for volumes whose mirror
failed (read-only target, out of space, partial copy on a previous
boot).
The same-disk invariant the EC lifecycle (encode / decode / balance /
vacuum / repair) was already documented as promising is now actually
restored at boot, so a future failure of one disk in a split-shards
layout no longer takes the other disk's shards with it.
Tests cover the orphan-layout mirror (dir0 receives the .ecx / .ecj /
.vif from dir1) and idempotency (an existing destination .ecx is not
overwritten with the owner's copy).
* fix(ec): handle legacy pre-dir.idx sidecar layout in mirror skip-check
hasAllEcSidecarsLocally checked only the modern destination path
(IdxDirectory for .ecx/.ecj, Directory for .vif). A destination disk
that still had a legacy .ecx in its data dir (written before -dir.idx
was set) would report "not present" and the mirror would write a
second copy to IdxDirectory, leaving two .ecx files on disk.
Matches HasEcxFileOnDisk's open-with-fallback contract: check the
modern path first, then the opposite directory. Factored the
exists-and-not-a-dir check into a small statRegular helper so the
fallback ladder stays readable.
* rust(seaweed-volume): mirror EC sidecars onto shard-bearing disks at startup
Port of the Go fix (commit
|
||
|
Chris LuandGitHub
|
2a41e76101 |
fix(ec): blanket-clean every destination over the full shard range (#9512)
* fix(ec): blanket-clean every destination over the full shard range The previous cleanup pass walked t.sources only, with the shard ids the topology had reported at detection time. In the wild, a destination can end up with EC shards mounted that the topology snapshot didn't list — shards on a sibling disk that hadn't heartbeated, or shards left over from a concurrent attempt's mount step. FindEcVolume still returns true, so the next ReceiveFile trips the mounted-volume guard. Cleanup now unions t.sources (with ShardIds) and t.targets and issues unmount + delete over [0..totalShards-1] on each. Both RPCs are idempotent on missing shards, so the wider sweep is free. Two new tests cover the gap: shards mounted beyond what t.sources lists, and a target-only destination with no source row. * log(ec): include disk_id in EC unmount/delete/refusal log lines The current logs identify the volume and shard but leave disk_id off, which makes the cross-server cleanup story hard to follow when multiple disks of one server hold pieces of the same volume: UnmountEcShards 4121.1 -> add disk_id ec volume video-recordings_4121 shard delete [1 5] -> add per-loc disk_id volume server X:Y deletes ec shards from 4121 [...] -> add disk_id ReceiveFile: ec volume 4121 is mounted; refusing... -> add disk_ids ReceiveFile's refusal now names the disk_ids actually holding the mount so operators can see whether the next cleanup pass needs to target a sibling disk. Added Store.FindEcVolumeDiskIds / Store::find_ec_volume_disk_ids as the supporting primitive. Mirrored in seaweed-volume/src/ (unmount log in Store::unmount_ec_shard, heartbeat delete log in diff_ec_shard_delta_messages, refusal in the ReceiveFile handler). * test(ec): stub VolumeEcShardsUnmount/Delete on the fake volume server The plugin-worker EC tests boot a fake volume server that embeds UnimplementedVolumeServerServer. After the worker started calling VolumeEcShardsUnmount + VolumeEcShardsDelete pre-distribute, the default Unimplemented response surfaced as fourteen "method not implemented" errors and TestErasureCodingExecutionEncodesShards failed. Both RPCs are no-ops here — nothing on the fake server has mounted state or persisted shard files to remove. |
||
|
Chris LuandGitHub
|
bf9110ebd3 |
fix(ec): mount falls back to sibling-disk .ecx (fixes #9519) (#9521)
* fix(ec): mount falls back to sibling-disk .ecx (fixes #9519) MountEcShards iterated DiskLocations and on each disk called LoadEcShard with that disk's IdxDirectory as the .ecx home. When ec.balance lands the .ec?? shard on disk A but the .ecx on sibling disk B of the same volume server, NewEcVolume ENOENTs the .ecx and returns "cannot open ec volume index ...". That error is not os.ErrNotExist, so the per-disk continue branch did not engage and the mount loop bailed before trying any other disk. The startup reconciliation in reconcileEcShardsAcrossDisks already handles this layout for orphan shards discovered on boot (issue #9212). This change mirrors the same primitive on the mount path: look up the .ecx owner across all DiskLocations once and route NewEcVolume at that directory whenever the disk being mounted does not own its own copy of the .ecx. Same-disk mounts are unaffected because HasEcxFileOnDisk keeps LocalIdxDirectory in play. Adds a regression test that plants the index files on a sibling disk AFTER NewStore returns (so the startup reconcile is a no-op for that vid) and verifies MountEcShards succeeds; also pins the same-disk baseline against accidental re-routing. * fix(ec): skip redundant stats in cross-disk .ecx lookup (review) Two follow-ups from gemini-code-assist on #9521: 1. MountEcShards: when findEcxIdxDirForVolume already returned a path that lives on this disk's IdxDirectory or Directory, the disk owns the .ecx — skip the HasEcxFileOnDisk stat and use the local idx dir directly. Only re-check when the disk's directories are neither, so the duplicate-.ecx-on-multiple-disks edge case is still honored. 2. findEcxIdxDirForVolume: hoist the seen map across the location loop so a shared IdxDirectory (one -dir.idx paired with several -dir entries) is only stat'd once per call. Both are I/O optimizations; behavior is unchanged. Existing cross-disk and same-disk regression tests still pass. * docs(ec): drop issue/PR references from cross-disk mount comments Comments and test docstrings stand on their own; the issue number adds nothing a reader can act on and goes stale across forks. Keep the description of *what* the layout is and *why* the fallback exists, just without the reference. |
||
|
Chris LuandGitHub
|
3a8389cd68 |
fix(ec): verify full shard set before deleting source volume (#9490) (#9493)
* fix(ec): verify full shard set before deleting source volume (#9490) Before this change, both the worker EC task and the shell ec.encode command would delete the source .dat as soon as MountEcShards returned — even if distribute/mount failed partway, leaving fewer than 14 shards in the cluster. The deletion was logged at V(2), so by the time someone noticed missing data the only trace was a 0-byte .dat synthesized by disk_location at next restart. - Worker path adds Step 6: poll VolumeEcShardsInfo on every destination, union the bitmaps, and refuse to call deleteOriginalVolume unless all TotalShardsCount distinct shard ids are observed. A failed gate leaves the source readonly so the next detection scan can retry. - Shell ec.encode adds the same gate after EcBalance, walking the master topology with collectEcNodeShardsInfo. - VolumeDelete RPC success and .dat/.idx unlinks now log at V(0) so any source destruction is traceable in default-verbosity production logs. The EC-balance-vs-in-flight-encode race is intentionally left for a follow-up; balance should refuse to move shards for a volume whose encode job is not in Completed state. * fix(ec): trim doc comments on the new shard-verification path Drop WHAT-describing godoc on freshly added helpers; keep only the WHY notes (query-error policy in VerifyShardsAcrossServers, the #9490 reference at the call sites). * fix(ec): drop issue-number anchors from new comments Issue references age poorly — the why behind each comment already stands on its own. * fix(ec): parametrize RequireFullShardSet on totalShards Take totalShards as an argument instead of reading the package-level TotalShardsCount constant. The OSS callers continue to pass 14, but the helper is now usable with any DataShards+ParityShards ratio. * test(plugin_workers): make fake volume server respond to VolumeEcShardsInfo The new pre-delete verification gate calls VolumeEcShardsInfo on every destination after mount, and the fake server's UnimplementedVolumeServer returns Unimplemented — the verifier read that as zero shards on every node and aborted source deletion. Build the response from recorded mount requests so the integration test exercises the gate end-to-end. * fix(rust/volume): log .dat/.idx unlink with size in remove_volume_files Mirror the Go-side change in weed/storage/volume_write.go: stat each file before removing and emit an info-level log for .dat/.idx so a destructive call is always traceable. The OSS Rust crate previously unlinked them silently. * fix(ec/decode): verify regenerated .dat before deleting EC shards After mountDecodedVolume succeeds, the previous code immediately unmounts and deletes every EC shard. A silent failure in generate or mount could leave the cluster with neither shards nor a valid normal volume. Probe ReadVolumeFileStatus on the target and refuse to proceed if dat or idx is 0 bytes. Also make the fake volume server's VolumeEcShardsInfo reflect whichever shard files exist on disk (seeded for tests as well as mounted via RPC), so the new gate can be exercised end-to-end. * fix(ec): address PR review nits in verification + fake server - Drop unused ServerShardInventory.Sizes field. - Skip shard ids >= MaxShardCount before bitmap Set so the ShardBits bound is explicit (Set already no-ops on overflow, this is for clarity). - Nil-guard the fake server's VolumeEcShardsInfo so a malformed call doesn't panic the test process. |
||
|
Chris LuandGitHub
|
d5c0a7b153 |
fix(ec): make multi-disk same-server EC reads work + full-lifecycle integration test (#9487)
* fix(master): include GrpcPort in LookupEcVolume response LookupVolume already passes loc.GrpcPort through to the client; LookupEcVolume builds Location with only Url / PublicUrl / DataCenter, so callers fall back to ServerToGrpcAddress (httpPort + 10000). On any deployment where that convention does not hold — multi-disk integration tests, custom port layouts — EC reads dial the wrong port and quietly degrade to parity recovery. * fix(volume/ec): probe every DiskLocation when serving local shard reads reconcileEcShardsAcrossDisks (issue 9212) registers each .ec?? against the DiskLocation that physically owns it, so a multi-disk volume server can hold shards for the same vid in two separate ecVolumes — one per disk — with .ecx on whichever disk owned the original .dat. The read path only consulted the single EcVolume FindEcVolume picked, so requests for shards on the sibling disk fell through to errShardNotLocal and then to remote/loopback recovery. Walk all DiskLocations after the first probe in both readLocalEcShardInterval and the VolumeEcShardRead gRPC handler; the latter also covers the loopback that recoverOneRemoteEcShardInterval falls back to when a peer dial fails. * test(volume/ec): cover the multi-disk EC lifecycle end-to-end Two integration tests against a real volume server with two data dirs: TestEcLifecycleAcrossMultipleDisks drives encode -> mount -> HTTP read -> drop .dat -> stop -> redistribute shards across disks -> restart -> verify reconcileEcShardsAcrossDisks attached the orphan shards and reads still work -> blob delete -> stop -> drop a shard -> restart -> VolumeEcShardsRebuild pulls input from both disks -> reads still work. TestEcPartialShardsOnSiblingDiskCleanedUpOnRestart is the issue 9478 reproducer at the cluster level: seed a healthy .dat on disk 0, plant the on-disk footprint of an interrupted EC encode on disk 1, restart, and assert pruneIncompleteEcWithSiblingDat wipes disk 1 without touching disk 0. Framework gets RestartVolumeServer / StopVolumeServer helpers; the previous run's volume.log is rotated to volume.log.previous so a startup regression on the second run does not lose the first run's diagnostics. * review: trim verbose comments * review: drop racy fast-path, use locked findEcShard directly gemini-code-assist flagged the two-step lookup in readLocalEcShardInterval and VolumeEcShardRead: the first probe (ecVolume.FindEcVolumeShard) reads the EcVolume's Shards slice without holding ecVolumesLock, so a concurrent mount / unmount could race with it. findEcShard already walks every DiskLocation under the right lock, so the fast-path adds nothing but the race. Collapse both call sites to a single locked call. Also note in RestartVolumeServer why the log-rotation error is swallowed: absence on first call is benign; anything else surfaces in the next os.Create in startVolume. |
||
|
Chris LuandGitHub
|
e025ec2334 |
fix(volume): seed indexFileOffset in SortedFileNeedleMap so Delete appends (#9483)
* fix(volume): seed indexFileOffset in SortedFileNeedleMap so Delete appends NewSortedFileNeedleMap never initialised the inherited baseNeedleMapper.indexFileOffset, so it stayed at zero. The compact and leveldb constructors both seed it from stat().Size(); this one did not. When a read-only or noWriteCanDelete volume processed a Delete, the inherited appendToIndexFile wrote the tombstone via WriteAt at indexFileOffset=0 and advanced 16 bytes at a time. Every delete since the SortedFileNeedleMap path was first exercised for writes (#5633, which switched .sdx to O_RDWR) overwrote the front of .idx with tombstones for unrelated keys. Net effect on disk: the first N entries of .idx become sequentially written tombstones with .dat offsets at the tail, while the original Put records that lived in slots [0..N) are gone. fsck sees ~N phantom orphans whose keys' runtime needle-map entries are already tombstoned in .sdx, so the volume server replies 304 to every purge and the orphan count is stable across retries. Stat the .idx at open and seed indexFileOffset = size. The .idx now grows on delete instead of being clobbered. Add a regression test that populates .idx via the compact map, opens it as a SortedFileNeedleMap, deletes one needle, and verifies the file grew by one entry, the original Put records survived, and the tombstone landed at the tail. The fix only stops further corruption. .idx files already damaged by this bug have to be rebuilt from .dat before the next restart, or isSortedFileFresh will regenerate .sdx from the bad .idx and propagate the damage. Refs #9479 * test: harden SortedFileNeedleMap regression assertions Address PR review (gemini-code-assist, coderabbit): - Close the writer before t.Fatalf in the Put loop so a failing seed doesn't leak the .idx file descriptor. - Verify offset and size of preserved Put records, not just the key. Front-overwrite damage would clobber all three fields, but a key-only check would miss a different regression that corrupted offset/size while leaving the key intact. |
||
|
Chris LuandGitHub
|
de28c4df61 |
fix(storage): prune partial EC shards when sibling disk has healthy .dat (#9478) (#9480)
* fix(storage): prune partial EC shards when sibling disk has healthy .dat (#9478) handleFoundEcxFile only checks for .dat in the same disk location as the EC shards. In a multi-disk volume server an interrupted encode can leave .ec?? + .ecx on disk B while the source .dat still lives on disk A: the per-disk loader sees no .dat next to .ecx, mistakes the leftover for a distributed-EC layout, and mounts the partial shards. The volume server then heartbeats both a regular replica and an EC shard for the same vid and the master keeps both. Sweep the store after per-disk loading and before the cross-disk reconcile to delete partial EC files when a healthy .dat for the same (collection, vid) exists on a sibling disk. Push DeletedEcShardsChan for every pruned shard so master forgets the new-shard message the per-disk pass already emitted, instead of waiting for the next periodic heartbeat. * fix(seaweed-volume): mirror prune of partial EC with sibling .dat (#9478) Rust port of the same Store-level prune added to weed/storage. The per-disk EC loader in disk_location.rs only checks for .dat in the same disk as the EC shards, so an interrupted encode that leaves .ec?? + .ecx on disk B while the source .dat sits on disk A is mounted as if it were a distributed-EC layout. The volume server then heartbeats both a regular replica and an EC shard for the same vid. Sweep the store after per-disk loading and before the cross-disk reconcile, dropping in-memory EcVolumes with fewer than DATA_SHARDS_COUNT shards when a .dat for the same (collection, vid) exists on a sibling disk, and remove all on-disk EC artefacts for them. The Rust heartbeat path already diff-emits deletes from the next ec_volumes snapshot, so no explicit delete-channel push is needed here. Tests cover both the issue 9478 layout and a distributed-EC layout with no .dat anywhere on the store, which must be left alone. * fix(storage): validate sibling .dat size before deleting partial EC (#9478) The earlier prune deleted partial EC files whenever any .dat for the same vid existed on a sibling disk — including a zero-byte shell. A shell is no more useful than the partial shard it would replace, and the partial shard might still combine with shards on other servers in a recoverable distributed-EC layout. Wiping it based on a corrupt sibling .dat is data loss masquerading as cleanup. Tighten the check: when the EC's .vif recorded a non-zero source size in datFileSize, require the sibling .dat to be at least that many bytes; otherwise fall back to "at least a superblock". The .vif value is what the encoder wrote at the moment the source was sealed, so a sibling .dat smaller than that is provably truncated. Carry the size through indexDatOwners alongside the location. The Rust port had the same gap and an additional bug behind it: EcVolume::new wasn't reading datFileSize from .vif, so the safety check always fell back to the superblock floor. Wire datFileSize through. The existing shard-size calculation in LocateEcShardNeedleInterval already uses dat_file_size when non-zero, so populating it also matches Go's behaviour there. Tests cover the truncated-sibling case in both ports. |
||
|
Chris LuandGitHub
|
18677a8430 |
fix(storage): refuse to load .vif-only entry as regular volume when .ecx exists (#9448) (#9461)
fix(storage): refuse to load .vif-only entry as regular volume when .ecx exists Defensive root-cause fix for issue #9448. The detection-side guard in the EC plugin worker already breaks the infinite re-encode loop, but the underlying volume-server state — `.vif` preserved next to EC shards when the source replica is destroyed — can still re-arm a phantom regular volume via the MountVolume / LoadVolume path. In loadExistingVolume, the existing `.ecx`-present check is gated on the caller passing `skipIfEcVolumesExists=true`. The startup-scan path (concurrentLoadingVolumes) does pass that flag and correctly skips the `.vif`. The LoadVolume → loadExistingVolume(…, false, …) path used by VolumeMount does NOT, so it falls through to NewVolume, which calls v.load with createDatIfMissing=true and creates a phantom empty `.dat`. The master then reports the volume as regular and EC detection re-proposes it. Hoist the `.ecx`-present check so it runs unconditionally for `.vif` entries: if the EC index is on the disk, the `.vif` belongs to those EC shards, never to a regular volume that should be resurrected. Pure OSS clusters never reach this exact state today (OSS deletes `.vif` unconditionally during Destroy), but the guard hardens the load path against any future path that leaves the same state. Test: - TestLoadExistingVolumeSkipsVifWhenEcxPresent builds the exact post-#9448 disk layout (`.vif` + `.ecx`, no `.dat`) and asserts loadExistingVolume(skipIfEcVolumesExists=false) returns false, does not create a placeholder `.dat`, and does not register a phantom volume in l.volumes. |
||
|
Chris LuandGitHub
|
532b088262 |
fix(ec): preserve source disk type across EC encoding (#9423) (#9449)
* fix(ec): carry source disk type on VolumeEcShardsMount (#9423) When EC shards land on a target whose disk type differs from the source volume's, master heartbeats wrongly reported under the target disk's type. Add source_disk_type to VolumeEcShardsMountRequest; the target server applies it to the in-memory EcVolume via SetDiskType so the mount notification and steady-state heartbeat both carry the source's disk type. Empty value falls back to the location's disk type (used by disk-scan reload paths). The override is not persisted with the volume — disk type stays an environmental property and .vif remains portable. * fix(ec): plumb source disk type through plugin worker (#9423) Add source_disk_type to ErasureCodingTaskParams (field 8; 7 reserved), populate it from the metric the detector already collects, thread it through ec_task into the MountEcShards helper, and forward it on the VolumeEcShardsMount RPC. * fix(ec): mirror source disk type plumbing in rust volume server (#9423) The volume_ec_shards_mount handler now forwards source_disk_type into mount_ec_shard → DiskLocation::mount_ec_shards. When non-empty it overrides ec_vol.disk_type (and each mounted shard's disk_type) via the new set_disk_type method; empty value keeps the location's disk type, so disk-scan reload and reconcile paths are unchanged. Also picks up two pre-existing proto drifts that 'make gen' synced from weed/pb (LockRingUpdate in master.proto, listing_cache_ttl_seconds in remote.proto). * feat(ec): bias placement toward preferred disk type (#9423) Add DiskCandidate.DiskType and PlacementRequest.PreferredDiskType. When PreferredDiskType is non-empty, SelectDestinations partitions suitable disks into matching/fallback tiers and runs the rack/server/ disk-diversity passes on the matching tier first; the fallback tier is only consulted if the matching pool can't satisfy ShardsNeeded. PlacementResult.SpilledToOtherDiskType lets callers warn on spillover. Empty PreferredDiskType keeps the existing single-pool behavior. * fix(ec): plumb source disk type into placement planner (#9423) diskInfosToCandidates now copies DiskInfo.DiskType into the placement candidate, and ecPlacementPlanner.selectDestinations forwards metric.DiskType as PreferredDiskType so EC shards land on disks matching the source volume's disk type when possible. A glog warning fires when placement had to spill to other disk types. * test(ec): integration coverage for source-disk-type plumbing (#9423) store_ec_disk_type_test exercises Store.MountEcShards end-to-end: a shard physically lives on an HDD location, MountEcShards is called with sourceDiskType="ssd", and the test asserts that the in-memory EcVolume, the mounted shard, the NewEcShardsChan notification, and the steady-state heartbeat all report under the source's disk type. A companion test pins the empty-source path so disk-scan reload keeps the location's disk type. detection_disk_type_test exercises the worker plumbing: with a cluster of nodes carrying both HDD and SSD disks, planECDestinations must place every shard on SSD when metric.DiskType="ssd"; with only one SSD node and 13 HDD nodes it must still satisfy a 10+4 layout via spillover (and log a warning). * revert(ec): drop unrelated proto drift in seaweed-volume/proto (#9423) make gen pulled two pre-existing OSS changes into the rust proto tree (LockRingUpdate / by_plugin in master.proto, listing_cache_ttl_seconds in remote.proto). Reviewers flagged it as scope creep — none of the rust EC fix references those fields. Restore both files to origin/master so this branch only touches EC-related symbols. * fix(ec placement): treat empty disk type as hdd and skip used racks on spill (#9423) partitionByDiskType used raw string comparison, so a PreferredDiskType of "hdd" never matched candidates whose DiskType is "" (the HardDriveType sentinel that weed/storage/types uses). EC encoding of an HDD source would spill onto any HDD reporting "" even when the cluster has plenty of matching capacity. Normalize both sides through normalizeDiskType, which lowercases and folds "" → "hdd", mirroring types.ToDiskType without taking a dependency on it. selectFromTier's rack-diversity pass also kept revisiting racks the preferred tier had already used when running on the fallback tier, which negated PreferDifferentRacks on spillover. Skip racks already in usedRacks so fallback placements still spread onto new racks. * fix(ec): empty-source remount must not clobber existing disk type (#9423) mount_ec_shards_with_idx_dir runs more than once per vid (RPC mount, disk-scan reload, orphan-shard reconcile). After an RPC sets the source-derived disk type, any later call passing source_disk_type="" was resetting ec_vol.disk_type back to the location's value, which reintroduces the heartbeat drift this PR is meant to fix. Only default to the location's disk type when the EC volume is fresh (no shards mounted yet); otherwise leave the recorded type alone so empty-source reloads preserve whatever the original mount RPC set. |
||
|
Chris LuandGitHub
|
6001d65206 |
perf(volume): stream-count the gzip size when no Content-MD5 is set (#9433)
ParseUpload runs util.DecompressData on every gzipped multipart upload just to record OriginalDataSize. The decompress materializes the full uncompressed slice via bytes.Buffer.ReadFrom inside util.GunzipStream; for a 64 MiB chunk that's a ~128 MiB heap spike per call (geometric grow). On 6-way concurrent UploadPartCopy the spike dominated the remaining heap profile after #9420/#9421/#9422/#9424/#9425. When no Content-MD5 verification is requested the uncompressed bytes aren't needed — only the length is. Stream the gunzip through io.Discard and count: the pooled gzip.Reader's working set replaces the materialized slice. Unlike the previous attempt in #9426 the size still comes from the real bytes, not from a client-set header. TotalAlloc per call, 4 MiB uncompressed body: materialize (was, still runs when MD5 is set): ~16.8 MiB stream-count (no MD5): ~28 KiB Refs #6541, #9426 (reverted in #9432). |
||
|
Chris LuandGitHub
|
ac65c6c2ca |
revert(volume): drop X-Seaweedfs-Original-Size hint (#9432)
Reverts #9426. The header had the volume server record OriginalDataSize from a value set by the multipart upstream — a client-controlled metadata field. On a volume server that isn't JWT-protected, a caller can lie and the needle stores the lie; bounds-checking the value doesn't change the trust shape, only the magnitude of the lie. Derive the size from the bytes again. The optimization only fired on multipart Content-Encoding: gzip parts (the s3 chunk-copy fast path), a narrow case that doesn't justify the trust dependency. A future change can attack the same heap profile by stream-decompressing to count bytes instead of materializing the uncompressed slice — no client-trust surface. Refs https://github.com/seaweedfs/seaweedfs/pull/9426#issuecomment-4417862793 |
||
|
Chris LuandGitHub
|
8efa32258a |
feat(volume): X-Seaweedfs-Original-Size hint skips redundant gunzip (#9426)
* feat(volume): X-Seaweedfs-Original-Size hint skips redundant gunzip The full-chunk gzip pass-through (#9425) fixed source-volume decompression but moved the cost to the destination volume: parseUpload still ran util.DecompressData on the forwarded gzipped bytes, just to learn the uncompressed length so it could record OriginalDataSize in the needle metadata. For 6-way concurrent 64 MiB UploadPartCopy that decompress-and-discard pass dominated the remaining heap profile after the streaming chain landed (~297 MiB inuse via bytes.Buffer.ReadFrom inside util.GunzipStream). Add an X-Seaweedfs-Original-Size header on the multipart part. When the upstream sets it (the s3 chunk-copy fast path always knows the uncompressed size — it's the source chunk's logical size) and no Content-MD5 verification is requested (which would require decompressed bytes to compute against), parseUpload uses the hint directly and skips the decompress. Header is X-* prefixed (not Seaweed-*) so it doesn't get auto-stored as a needle pair by PairNamePrefix. Backward compatible: - old s3 servers don't set the header, parseUpload decompresses as before - new s3 servers talking to old volumes: header is ignored, volume decompresses - bad header values (non-numeric, negative, garbage) fall back to the existing decompress path End-to-end repro impact (512 MiB src, 6 parallel UploadPartCopy, post-#9420/#9421/#9422/#9424/#9425 baseline): RSS, round 2: 1149 MiB → 594 MiB heap inuse_space: 545 MiB → 349 MiB HeapSys: 1.35 GiB → 777 MiB TotalAlloc cum: ~9 GiB → 3.5 GiB Total reduction from pre-#9420 baseline: 3134 → 594 MiB (-81%). Test exercises the four matrix corners (hint+no-MD5, hint+part-MD5, hint+req-MD5, no-hint, garbage-hint) and bounds allocation per case so a regression that re-introduces the unconditional decompress fails the hint-present-no-MD5 case. * review: bound X-Seaweedfs-Original-Size by sizeLimit and uint32 CodeQL on PR 9426 traced a new taint flow: the strconv.Atoi(hint) value flows into pu.OriginalDataSize -> originalSize -> the existing uint32(originalSize) cast in volume_server_handlers_write.go:73. The cast was always there but its input was previously bounded by the ParseUpload read path (capped at sizeLimit). Adding a user-controlled hint bypassed that bound, so a malicious header could overflow the uint32 silently. Bound the hint at parse time by sizeLimit (the largest needle this volume will accept anyway) and by math.MaxUint32 (belt-and-suspenders in case sizeLimit is configured > 4 GiB). |
||
|
Chris LuandGitHub
|
c917110124 |
fix(volume): pre-size ParseUpload buffer to request ContentLength (#9421)
* fix(volume): pre-size ParseUpload buffer to request ContentLength The volume server's PostHandler reads the multipart upload body via bytes.Buffer.ReadFrom inside parseUpload. The buffer comes from a sync.Pool and may have cap=0 when the pool dropped the prior entry, which makes ReadFrom geometric-grow on each chunk: a 64 MiB upload allocates roughly 1+2+4+...+64 ≈ 128 MiB just to receive the body. Under concurrent uploads (every s3 chunk-copy lands here on the destination volume) this is one of the main contributors to the runaway-RSS pattern in #6541 — pprof shows ~458 MiB cum in parseUpload's bytes.Buffer.ReadFrom under Harbor-style assemble load. Grow the buffer once up front, bounded by the existing sizeLimit so a misreported Content-Length can't over-allocate. The receive then fills in place. Add a regression test that drives ParseUpload with a 16 MiB multipart body and bounds TotalAlloc at 1.5x the chunk size (pre-fix measures ~4x, so the bound trips deterministically). * fix(volume): guard ParseUpload pre-grow against int overflow on 32-bit Address PR review feedback: r.ContentLength is int64, and on 32-bit platforms int is 32 bits wide, so int(r.ContentLength) for a value above math.MaxInt32 wraps negative and bytes.Buffer.Grow panics with "bytes.Buffer.Grow: negative count". Skip the pre-grow optimization in that range; the existing geometric-grow path remains correct, just slightly more allocator pressure for that one call. 64-bit platforms (math.MaxInt == math.MaxInt64) are unaffected — the guard only kicks in for 32-bit builds with very large sizeLimit. * fix(volume): cap ParseUpload pre-grow at 4 MiB to bound DoS surface Address PR review: pre-growing the receive buffer to r.ContentLength trusts the header before any body bytes arrive. A bad header or slow / idle client could declare a large Content-Length up to sizeLimit (256 MiB by default for volume writes) and force per-request preallocation without sending data, turning many concurrent slow connections into avoidable memory pressure. Cap eager pre-grow at maxEagerPreGrow (4 MiB). Larger uploads still benefit from the higher starting cap and fall back to ReadFrom's grow path for the remainder. Per-request waste from a misreported Content-Length is now bounded at 4 MiB regardless of sizeLimit. Extract the policy as eagerPreGrow so the unit test can exercise the gates structurally — replaces the prior TotalAlloc bound (which became uninformative once savings were capped at 4 MiB). |
||
|
Chris LuandGitHub
|
1c917ffacb |
fix(volume): sticky EIO quarantine; track streamed reads (#9384)
Two follow-ups on PR #9382: 1. Quarantine wasn't sticky. Once CollectHeartbeat crossed the streak threshold and hid the replica, a subsequent successful read called checkReadWriteError(nil), wiping the streak; the next heartbeat then re-announced the suspect replica as read-only and master could send reads back to a disk that already failed IoErrorTolerance. Added an ioErrorQuarantined sticky flag set on the first heartbeat that observes the threshold and cleared only by MarkVolumeWritable (resetIoErrorState). clearIoError continues to reset just the streak so successful ops don't accumulate phantom errors. 2. Streamed reads bypassed the EIO counter. readNeedleDataInto and ReadNeedleBlob — the hot paths for large/range GETs — returned ReadNeedleData / needle.ReadNeedleBlob errors without threading them through checkReadWriteError, so a disk failing only on those paths would never trip IoErrorTolerance. Both now route the backend error through the tracker, and a fully clean readNeedleDataInto call clears the streak. Tests cover the sticky flag (TestQuarantineIsSticky) and the streamed read path (TestReadNeedleBlobTracksEIO via a fake EIO backend). |
||
|
Chris LuandGitHub
|
7c60407897 |
fix(volume): don't nuke local data on transient IO error (#9378) (#9382)
* fix(volume): don't nuke local data on transient IO error (#9378) A single syscall.EIO from any read/write/delete set v.lastIoError, and the next CollectHeartbeat then called Volume.Destroy on the replica — removing the .dat/.idx/.vif/.sdx/.ldb/.rdb files. A brief NFS / fabric / controller blip hitting several replicas at once could cascade into removal of the last healthy copy, with no recovery for non-tiered volumes. Now require IoErrorTolerance (3) consecutive EIOs before acting, and on that threshold mark the volume read-only and stop announcing it to the master so re-replication kicks in from healthy peers — never delete the data files. The on-disk copy stays for operator inspection / recovery. * review: fix race, accounting, recovery, non-EIO streak break Addressing PR #9382 review: - Data race on lastIoError: guard lastIoError + lastIoErrorCount with a RWMutex and expose them through note/clear/get helpers so the heartbeat reader sees a consistent snapshot. Verified with -race. - Collection-size accounting: when a volume is quarantined for sustained EIO, skip the entire per-volume bookkeeping (`continue`) instead of flipping shouldDeleteVolume — the old branch subtracted a size that was never added, dragging the collection gauge to zero / negative. - Recoverability: MarkVolumeWritable now also calls clearIoError so an operator can rejoin a quarantined replica. The next failed op re-arms the streak if the disk is still bad. - Non-EIO streak break: a non-EIO error (e.g. ENOSPC) now resets the consecutive-EIO counter, so a sequence EIO,EIO,ENOSPC,EIO is treated as a streak of one — the counter only tracks consecutive EIOs. Reads already call checkReadWriteError (volume_read.go), so successful reads also clear the streak — no change needed there. |
||
|
Chris LuandGitHub
|
487b93eb49 |
fix(volume): don't panic on read when needle map is nil (#9342)
* fix(volume): don't panic on read when needle map is nil A failed CommitCompact reload (and #9335's new error path for a remote-tiered volume with a stray .vif but no .idx) leaves v.nm == nil on a volume that's still in the store. readNeedle / readNeedleDataInto dereferenced v.nm with no guard, so the next GET segfaulted the http handler instead of returning an error the client could retry on another replica. Add the same v.nm == nil check the other Volume accessors already use, including the slow-read inner loop where the lock is released between iterations and a failed reload can race in. Fixes #9339. * match rust nm-nil read behavior; trim comments seaweed-volume's read_needle_with_option / re_lookup_needle_data_offset already lift Option<NeedleMap> through ok_or(NotFound). Use ErrorNotFound on the Go side too instead of a generic 500-mapped error so both volume servers respond identically when v.nm is nil. * log once when reads hit nil needle map ErrorNotFound alone hides the real cause: a half-loaded volume just returns 404s and the operator has nothing to grep for. Add a once-per- volume Errorf on the nil path, reset on successful load. Mirror the same in seaweed-volume via nm_or_not_found(). * trim comments * drop once-flag, log inline on every nil-nm read |
||
|
1c0e24f06a |
fix(balance): don't move remote-tiered volumes; don't fatal on missing .idx (#9335)
* fix(volume): don't fatal on missing .idx for remote-tiered volume A .vif left behind without its .idx (orphaned by a crashed move, partial copy, or hand-edit) would trip glog.Fatalf in checkIdxFile and take the whole volume server down on boot, killing every healthy volume on it too. For remote-tiered volumes treat it as a per-volume load error so the server can come up and the operator can clean up the stray .vif. Refs #9331. * fix(balance): skip remote-tiered volumes in admin balance detection The admin/worker balance detector had no equivalent of the shell-side guard ("does not move volume in remote storage" in command_volume_balance.go), so it scheduled moves on remote-tiered volumes. The "move" copies .idx/.vif to the destination and then calls Volume.Destroy on the source, which calls backendStorage.DeleteFile — deleting the remote object the destination's new .vif now points at. Populate HasRemoteCopy on the metrics emitted by both the admin maintenance scanner and the worker's master poll, then drop those volumes at the top of Detection. Fixes #9331. * Apply suggestion from @gemini-code-assist[bot] Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> * fix(volume): keep remote data on volume-move-driven delete The on-source delete after a volume move (admin/worker balance and shell volume.move) ran Volume.Destroy with no way to opt out of the remote-object cleanup. Volume.Destroy unconditionally calls backendStorage.DeleteFile for remote-tiered volumes, so a successful move would copy .idx/.vif to the destination and then nuke the cloud object the destination's new .vif was already pointing at. Add VolumeDeleteRequest.keep_remote_data and plumb it through Store.DeleteVolume / DiskLocation.DeleteVolume / Volume.Destroy. The balance task and shell volume.move set it to true; the post-tier-upload cleanup of other replicas and the over-replication trim in volume.fix.replication also set it to true since the remote object is still referenced. Other real-delete callers keep the default. The delete-before-receive path in VolumeCopy also sets it: the inbound copy carries a .vif that may reference the same cloud object as the existing volume. Refs #9331. * test(storage): in-process remote-tier integration tests Cover the four operations the user is most likely to run against a cloud-tiered volume — balance/move, vacuum, EC encode, EC decode — by registering a local-disk-backed BackendStorage as the "remote" tier and exercising the real Volume / DiskLocation / EC encoder code paths. Locks in: - Destroy(keepRemoteData=true) preserves the remote object (move case) - Destroy(keepRemoteData=false) deletes it (real-delete case) - Vacuum/compact on a remote-tier volume never deletes the remote object - EC encode requires the local .dat (callers must download first) - EC encode + rebuild round-trips after a tier-down Tests run in-process and finish in under a second total — no cluster, binary, or external storage required. * fix(rust-volume): keep remote data on volume-move-driven delete Mirror the Go fix in seaweed-volume: plumb keep_remote_data through grpc volume_delete → Store.delete_volume → DiskLocation.delete_volume → Volume.destroy, and skip the s3-tier delete_file call when the flag is set. The pre-receive cleanup in volume_copy passes true for the same reason as the Go side: the inbound copy carries a .vif that may reference the same cloud object as the existing volume. The Rust loader already warns rather than fataling on a stray .vif without an .idx (volume.rs load_index_inmemory / load_index_redb), so no counterpart to the Go fatal-on-missing-idx fix is needed. Refs #9331. * fix(volume): preserve remote tier on IO-error eviction; fix EC test target Two review nits: - Store.MaybeAddVolumes' periodic cleanup pass deleted IO-errored volumes with keepRemoteData=false, so a transient local fault on a remote-tiered volume would also nuke the cloud object. Track the delete reason via a parallel slice and pass keepRemoteData=v.HasRemoteFile() for IO-error evictions; TTL-expired evictions still pass false. - TestRemoteTier_ECEncodeDecode_AfterDownload deleted shards 0..3 but called them "parity" — by the klauspost/reedsolomon convention shards 0..DataShardsCount-1 are data and DataShardsCount..TotalShardsCount-1 are parity. Switch the loop to delete the parity range so the intent matches the indices. --------- Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> |
||
|
Chris LuandGitHub
|
57bb7b2f39 |
quiet noisy 'shard X not found' log when EC shard lives on another server (#9316)
quiet "shard X not found" log when EC shard lives on another server When EC shards are spread across multiple volume servers, every read that targets a shard not present locally was logging at V(0) with the same wording as a real read failure. Under rclone-style traffic this floods the logs and makes a healthy EC cluster look broken (issue #9310). Distinguish the two cases with an errShardNotLocal sentinel: the expected fall-through-to-remote path now logs at V(4); genuine local read failures still log at V(0). |
||
 Lars LehtonenandGitHub
|
913f98db10 | refactor(weed/storage): log volume file removal failures (#9297) | ||
 
|
eebffd9df6 |
fix(storage): fix verifyDeletedNeedleIntegrity using wrong offset (#9273)
* fix(storage): fix verifyDeletedNeedleIntegrity using wrong offset verifyDeletedNeedleIntegrity was ignoring the offset recorded in the index file and instead always reading from fileSize-DiskSize(0), which is only correct when the deleted needle happens to be the very last entry in the .dat file. When a deletion tombstone is written in the middle of the volume (e.g. after subsequent writes), the function reads the wrong bytes, causing the key-mismatch check to either silently pass (if the bytes happen to form a valid needle with the same ID) or produce a spurious integrity error. Fix: accept the actual offset from the index entry and use types.TombstoneFileSize as the size, mirroring the approach used by verifyNeedleIntegrity for live needles. * fix(storage): fix error message in doCheckAndFixVolumeData The error message in the deleted-needle branch referenced verifyNeedleIntegrity, but the function being called is verifyDeletedNeedleIntegrity. This makes log output misleading when a deleted-needle integrity check fails. Suggested by gemini-code-assist review on PR #9273. --------- Co-authored-by: chenshi5012 <chenshi5012@github.com> |
||
|
Chris LuandGitHub
|
cba2f7b1dd |
fix(volume_server): load orphan EC shards across disks on startup (#9212) (#9244)
* fix(volume_server): load orphan EC shards across disks on startup (#9212) When ec.balance / ec.rebuild copies an EC shard onto a destination node without also pinning subsequent shards to the disk that holds .ecx, the shard ends up on a different physical disk than its index files. The per-disk loadAllEcShards has no visibility into other DiskLocations on the same store, so those orphan shards were silently left out of ecVolumes and never reported to master — volume.list showed partial counts, and ec.rebuild reported the volume as unrepairable even though all shards were physically present. After every DiskLocation finishes its initial pass, sweep the store for shard files that are on disk but not yet in any EcVolume, look up the .ecx-owning sibling disk, and load each shard against its physical disk with dirIdx pointing at the sibling. Each shard is still registered on its own disk's ecVolumes map so heartbeat reporting carries the right DiskId per shard (master fix #9219 already aggregates per-disk messages correctly). Also fall back to dirIdx for .vif lookup when dir != dirIdx, so the reconciliation path doesn't write a stub .vif on the shard disk and lose the real EC config and datFileSize. * fix(volume_server): track actual .ecx dir in cross-disk reconcile indexEcxOwners scans both IdxDirectory and Directory to find each volume's .ecx — the second scan covers the legacy case where index files were written into the data dir before -dir.idx was configured (removeEcVolumeFiles already accounts for this in disk_location_ec.go). But the returned map dropped which directory matched, and reconcile unconditionally passed owner.IdxDirectory to loadEcShardsWithIdxDir. When the owner's .ecx is in Directory and IdxDirectory != Directory (server later re-configured with -dir.idx pointing at a fresh path), NewEcVolume opens IdxDirectory/.ecx → ENOENT, retries the same-disk fallback at dataBaseFileName+.ecx — but dataBaseFileName uses the *orphan* disk's data dir, not the owner's, so it ENOENTs again and the orphan shards stay unloaded. Track which scan dir matched in indexEcxOwners and pass it through. Adds TestLoadEcShardsWhenOwnerEcxIsInDataDir as the regression. Reported in PR #9244 review by @gemini-code-assist and @coderabbitai. * refactor(storage): thread dataShardCount as a parameter into calculateExpectedShardSize The helper used erasure_coding.DataShardsCount directly, but tests in store_ec_orphan_shard_test.go save .vif with a local dataShards=10 constant. If the package default ever diverged from 10 (e.g. an enterprise build), the test would write a .vif for one layout while sizing shard files for another and silently break. Take dataShardCount as a parameter. Existing callers (validateEcVolume + size-validation tests + real-world tests) pass erasure_coding.DataShardsCount unchanged. The orphan-shard tests pass the same dataShards local they save into .vif, so the persisted shape and the on-disk shape stay consistent. Reported in PR #9244 review by @coderabbitai. |
||
|
Chris LuandGitHub
|
5fbe39320c |
fix(volume_server): pin EC shard auto-select to the .ecx-owning disk (#9212) (#9245)
* fix(volume_server): pin EC shard auto-select to the .ecx-owning disk (#9212) ec.rebuild only sets CopyEcxFile=true on the first shard sent to the rebuilder; subsequent shards rely on VolumeEcShardsCopy / ReceiveFile auto-select to land on the same disk. The old auto-select used FindEcVolume (in-memory) to detect the "already has this volume" case. Mid-rebuild, no EC volume has been mounted yet on the destination, so FindEcVolume returns nothing and the fallback picks "any HDD with free space" — which can split shards from their .ecx across disks of the same node and feed the orphan-shard layout reported in #9212 / fixed on the loader side in #9244. Add Store.FindEcShardTargetLocation as the canonical placement primitive: prefer a mounted EC volume, then a disk that has the .ecx on disk, then any HDD, then any disk. DiskLocation.HasEcxFileOnDisk is the new on-disk check, and it looks at IdxDirectory first with a fallback to Directory to handle .ecx written before -dir.idx was configured. Both VolumeEcShardsCopy and ReceiveFile now route through the new helper, dropping their duplicated 4-level fallback ladder. No protocol changes; explicit DiskId callers are unaffected. * fix(volume_server): treat directories named *.ecx as no-match in HasEcxFileOnDisk os.Stat(".ecx") succeeds for both files and directories. If something happens to leave a directory named X.ecx in the data or idx folder, HasEcxFileOnDisk would currently report true and FindEcShardTargetLocation would route shards to that disk — where NewEcVolume's eventual OpenFile(O_RDWR) on the same path errors out. Add a !info.IsDir() check on both stat sites. Cheap and conservative. Suggested in PR #9245 review by @gemini-code-assist. * refactor(volume_server): collapse EC placement helper to a single pass FindEcShardTargetLocation called FindFreeLocation up to four times. Each call iterates s.Locations and acquires VolumesLen / EcShardCount RLocks per disk — for a typical 4-disk node that's 32 RLock cycles per placement decision. Walk s.Locations once, score each disk by tier (mounted > .ecx-on-disk > HDD > any-disk), break ties by free count. The free-slot math is factored into a small helper that mirrors FindFreeLocation's formula without re-entering the location's locks. Behaviour is unchanged: each existing tier still wins over later tiers, and within a tier the disk with the most free count still wins, matching the original max-tracking in FindFreeLocation. Suggested in PR #9245 review by @gemini-code-assist. * refactor(volume_server): thread dataShardCount as a parameter through EC placement ecFreeShardCount and FindEcShardTargetLocation referenced erasure_coding.DataShardsCount directly. Take it as a parameter so custom-ratio builds (e.g. enterprise) can swap the default without touching the helper itself, and so unit tests can pin a specific ratio independent of the package constant. Default callsites in VolumeEcShardsCopy and ReceiveFile now pass the package default explicitly; tests pass a literal 10 for clarity. * fix(volume_server): treat MaxVolumeCount=0 as unlimited in EC placement ecFreeShardCount computed `MaxVolumeCount - VolumesLen()` and went negative when MaxVolumeCount was 0 — the "unlimited disk" sentinel already honoured by Store.hasFreeDiskLocation and friends. With a negative free count, FindEcShardTargetLocation's `freeCount <= 0` guard skipped the disk entirely, so unlimited disks could never receive EC shards via the placement helper. Special-case MaxVolumeCount<=0: report a synthetic large free count that decrements with current usage, so unlimited disks are eligible and tie-breaks still prefer the less-loaded one. Added TestFindEcShardTargetLocation_HonoursUnlimitedDisk as the regression. Reported in PR #9245 review by @gemini-code-assist. * fix(volume_server): account in shard slots, not volume slots, in ecFreeShardCount FindFreeLocation in store.go ends with `free /= DataShardsCount`, converting "shard slots free" back to "volume-equivalent slots." The truncation is harmless there, but my new ecFreeShardCount inherited the same final divide and re-introduced exactly the orphan-shard hazard #9245 was meant to prevent: with MaxVolumeCount=1, VolumesLen=0, EcShardCount=1 the formula reports 0 even though the disk has room for 9 more shards, so subsequent shards route off the .ecx-owning disk into the HDD-fallback tier. Drop the trailing divide and return the count directly in shard slots. Same shape, finer granularity; tie-breaks still order by free count. The unlimited branch's "used" calculation is updated to match (mix volume-slots and shard-slots in shard units). Added TestFindEcShardTargetLocation_TightProvisioningKeepsEcxDisk as the regression. Reported in PR #9245 review by @coderabbitai. |
||
|
Chris LuandGitHub
|
654292b57d |
fix(volume): cap leveldb OpenFilesCacheCapacity per index DB (#9139) (#9223)
* fix(volume): cap leveldb OpenFilesCacheCapacity per index DB (#9139) The leveldb opt.Options for NeedleMapLevelDb / Medium / Large never set OpenFilesCacheCapacity, so each leveldb instance defaulted to goleveldb's 500. On servers with thousands of volumes, that ceiling stacks across DBs and exhausts even high ulimits, starving WAL rotation: failed to write leveldb: open .../000006.log: too many open files CompactionTableSizeMultiplier=10 already keeps the SST count low, so a small per-DB cache is sufficient. Cap at 16 / 32 / 64 for the small / medium / large variants so per-DB FD usage is bounded. * storage: hoist leveldb FD-cap values into named constants Per review feedback: replace the inline 16/32/64 literals with LevelDb{,Medium,Large}OpenFilesCacheCapacity, and move the rationale (why 500 is too high per-DB on busy servers, what the tradeoff is) into a package-level comment so future readers see the memory vs. performance picture at the constant declaration instead of inline. |
||
|
Chris LuandGitHub
|
f1f720f5da |
fix(master): register EC shards per physical disk on full heartbeat sync (#9212) (#9219)
* refactor(types): add DiskId type for physical-disk identifiers Names the uint32 physical-disk index that volume servers carry in VolumeEcShardInformationMessage / VolumeInformationMessage, so EC shard tracking that needs to distinguish disks within a DataNode can use a dedicated type instead of an untyped uint32. No behaviour change. * fix(master): register EC shards per physical disk on full heartbeat sync (#9212) When a volume's EC shards are spread across multiple physical disks on the same volume server (common after ec.balance / ec.rebuild on multi-disk nodes), the volume server emits one VolumeEcShardInformationMessage per (disk, volume) in its heartbeat. The master's DataNode.UpdateEcShards was building a `map[VolumeId]*EcVolumeInfo` with last-write-wins, and doUpdateEcShards then overwrote `disk.ecShards[vid]` once per message, so all but the final disk's shards were silently dropped. Only the topology-global ecShardMap (built via RegisterEcShards in a per-message loop) stayed correct, which hid the problem from `topo.LookupEcShards` but broke everything that reads the DataNode/Disk view — volume.list, admin UI, ec.rebuild dry-run ("only 6 shards, skipping"), and `DiskInfo.EcShardInfos` which the shell's ec.balance / ec.rebuild planners group by `eci.DiskId`. Change the shape of `Disk.ecShards` from map[VolumeId]*EcVolumeInfo to map[VolumeId]map[types.DiskId]*EcVolumeInfo so every physical disk keeps its own entry. UpdateEcShards aggregates incoming messages by (vid, diskId) rather than vid alone; Add/Delete/ HasVolumesById and HasEcShards consult the nested map; doUpdateEcShards rewrites the nested structure from the aggregated map. Per-physical-disk attribution survives through DataNode.ToDataNodeInfo -> DiskInfo.EcShardInfos, matching the wire format the volume server produces and what downstream admin tooling expects. Delta sync (AddOrUpdateEcShard / DeleteEcShard) already merged via ShardsInfo.Add, so this only affects the full-sync path that runs on heartbeat reconnect. Adds data_node_ec_multi_disk_test.go with two regression tests that fail on pre-fix master: - TestEcShardsAcrossMultipleDisksOnSameNode: volume 15 spread over 3 disks (matches the bug report's volume-2 row); asserts every shard visible via LookupEcShards, DataNode.GetEcShards, and ToDataNodeInfo's per-disk EcShardInfos entries. - TestEcShardsAfterRestartHeartbeat: minimal 2-disk full sync case. * fix(topology): tighten locking around EC shard map access Addresses review comments on #9219: * DataNode.UpdateEcShards now holds dn.Lock for the full read-diff-write cycle, matching UpdateVolumes' model, so concurrent heartbeats can no longer interleave their getOrCreateDisk / UpAdjustDiskUsageDelta updates with each other. Introduces a private getEcShardsLocked helper for reads under the held lock; renames doUpdateEcShards to doUpdateEcShardsLocked for the same reason. * DataNode.HasEcShards now takes each disk's ecShardsLock while reading disk.ecShards, closing a pre-existing map race with concurrent Add/Delete/Update writers. * doUpdateEcShardsLocked takes each disk's ecShardsLock around the reset-and-rewrite so readers (GetEcShards, HasEcShards) see a consistent map state rather than a partially-rebuilt one. * Disk.GetEcShards' slice-capacity hint now accounts for the nested per-physical-disk entries (sum of inner lengths) instead of underestimating by the unique-volume count. |
||
 
|
20f4fd9985 |
fix(storage): use ceil division for EC shard slots in maxVolumeCount (#9196)
* fix(storage): use ceil division for EC shard slots in maxVolumeCount * fix(topology): use ceil division for EC shard slots consistently Applies the same ceiling-division formula used in store.go to the four remaining master-side sites that computed volume-slots consumed by EC shards with off-by-one approximations: - disk.go ToDiskInfo / Disk.ToDiskInfo used (n+1)/d, which under-counts slots for non-multiples of DataShardsCount, over-reporting FreeVolumeCount. - DiskUsageCounts.FreeSpace and NodeImpl.AvailableSpaceFor subtracted n/d + 1, which over-counts slots at multiples of DataShardsCount, under-reporting free space (and suppressing volume growth on nodes that still had room). All four now use (n + DataShardsCount - 1) / DataShardsCount, matching store.go:393, store.go:810, and command_ec_decode.go:422. * refactor(topology): extract ecShardSlots helper Deduplicates the (n + DataShardsCount - 1) / DataShardsCount ceiling expression now used by ToDiskInfo, DiskUsageCounts.FreeSpace, Disk.ToDiskInfo, and AvailableSpaceFor. Addresses PR review feedback. --------- Co-authored-by: Chris Lu <chris.lu@gmail.com> |
||
|
Chris LuandGitHub
|
c4e1885053 |
fix(ec): honor disk_id in ReceiveFile so EC shards respect admin placement (#9184) (#9185)
* test(volume_server): reproduce #9184 EC ReceiveFile disk-placement bug The plugin-worker EC task sends shards via ReceiveFile, which picks Locations[0] as the target directory regardless of the admin planner's TargetDisk assignment. ReceiveFileInfo has no disk_id field, so there is no wire channel to honor the plan. Adds StartSingleVolumeClusterWithDataDirs to the integration framework so tests can launch a volume server with N data directories. The new repro asserts the current (buggy) behavior: sending three distinct EC shards via ReceiveFile leaves all three files in dir[0] and the other dirs empty. When the fix adds disk_id to ReceiveFileInfo, this assertion must flip to verify the planned placement is respected. * fix(ec): honor disk_id in ReceiveFile so EC shards respect admin placement Before this change, VolumeServer.ReceiveFile for EC shards always selected the first HDD location (Locations[0]). The plugin-worker EC task had no way to pass the admin planner's per-shard disk assignment — ReceiveFileInfo carried no disk_id field — so every received EC shard piled onto a single disk per destination server. On multi-disk servers this caused uneven load (one disk absorbing all EC shard I/O), frequent ENOSPC retries, and a growing EC backlog under sustained ingest (see issue #9184). Changes: - proto: add disk_id to ReceiveFileInfo, mirroring VolumeEcShardsCopyRequest.disk_id. - worker: DistributeEcShards tracks the planner-assigned disk per shard; sendShardFileToDestination forwards that disk id. Metadata files (ecx/ecj/vif) inherit the disk of the first data shard targeting the same node so they land next to the shards. - server: ReceiveFile honors disk_id when > 0 with bounds validation; disk_id=0 (unset) falls back to the same auto-selection pattern as VolumeEcShardsCopy (prefer disk that already has shards for this volume, then any HDD with free space, then any location with free space). Tests updated: - TestReceiveFileEcShardHonorsDiskID asserts three shards sent with disk_id={1,2,0} land on data dirs 1, 2, and 0 respectively. - TestReceiveFileEcShardRejectsInvalidDiskID pins the out-of-range disk_id rejection path. * fix(volume-rust): honor disk_id in ReceiveFile for EC shards Mirror the Go-side change: when disk_id > 0 place the EC shard on the requested disk; when unset, auto-select with the same preference order as volume_ec_shards_copy (disk already holding shards, then any HDD, then any disk). * fix(volume): compare disk_id as uint32 to avoid 32-bit overflow On 32-bit Go builds `int(fileInfo.DiskId) >= len(Locations)` can wrap a high-bit uint32 to a negative int, bypassing the bounds check before the index operation. Compare in the uint32 domain instead. * test(ec): fail invalid-disk_id test on transport error Previously a transport-level error from CloseAndRecv silently passed the test by returning early, masking any real gRPC failure. Fail loudly so only the structured ReceiveFileResponse rejection path counts as a pass. * docs(test): explain why DiskId=0 auto-selects dir 0 in EC placement test Documents the load-bearing assumption that shards are never mounted in this test, so loc.FindEcVolume always returns false and auto-select falls through to the first HDD. Saves future readers from re-deriving the expected directory for the DiskId=0 case. * fix(test): preserve baseDir/volume path for single-dir clusters StartSingleVolumeClusterWithDataDirs started naming the data directory volume0 even in the dataDirCount=1 case, which broke Scrub tests that reach into baseDir/volume via CorruptDatFile / CorruptEcShardFile / CorruptEcxFile. Keep the legacy name for single-dir clusters; only use the indexed "volumeN" layout when multiple disks are requested. |
||
|
Chris LuandGitHub
|
7364f148bd |
fix(s3/shell): factor EC volumes into bucket size metrics and collection.list (#9182)
* fix(s3/shell): include EC volumes in bucket size metrics and collection.list S3 bucket size metrics exported to Prometheus (and fed through stats.UpdateBucketSizeMetrics) are computed by collectCollectionInfoFromTopology, which only walked diskInfo.VolumeInfos. As soon as a volume was encoded to EC it dropped out of every aggregate, so Grafana showed bucket sizes shrinking while physical disk usage kept climbing. The shell helper collectCollectionInfo — used by collection.list and s3.bucket.quota.enforce — had the same gap, with the EC branch left as a commented-out TODO. Fold EC shards into both paths using the same approach the admin dashboard already uses (PR #9093): - PhysicalSize / Size sum across shard holders: EC shards are node-local (not replicas), so per-node TotalSize() and MinusParityShards().TotalSize() sum to the whole-volume physical and logical sizes respectively. - FileCount is deduped via max across reporters (every shard holder reports the same .ecx count; a slow node with a not-yet-loaded .ecx reports 0 and must not pin the aggregate). - DeleteCount is summed (each delete tombstones exactly one node's .ecj). - VolumeCount increments once per unique EC volume id. Adds regression tests covering pure-EC, mixed regular+EC, and the slow-reporter FileCount dedupe case. Refs #9086 * Address PR review feedback: EC size helpers, composite key, VolumeCount dedupe - Add EcShardsTotalSize / EcShardsDataSize helpers in the erasure_coding package that walk the shard bitmap directly instead of materializing a ShardsInfo and copying it via MinusParityShards(). Keeps the DataShardsCount dependency encapsulated in one place and avoids the per-shard allocation/copy overhead in the metrics hot path. - Switch shell collectCollectionInfo ecVolumes map to a composite {collection, volumeId} key, matching the bucket_size_metrics collector and defending against any cross-collection volume id aliasing. - Dedupe VolumeCount in shell addToCollection by volume id so regular volumes aren't counted once per replica presence. Aligns the shell's collection.list output with the S3 metrics collector and the EC branch, all of which now report logical volume counts. - Add unit tests for the new helpers and for the regular-volume VolumeCount dedupe. * Parameterize EcShardsDataSize with dataShards for custom EC ratios Add a dataShards parameter to EcShardsDataSize so forks with per-volume ratio metadata (e.g. the enterprise data_shards field carried on an extended VolumeEcShardInformationMessage) can pass the configured value and get accurate logical sizes under custom EC policies like 6+3 or 16+6. Passing 0 or a negative value falls back to the upstream DataShardsCount default, which is correct for the fixed 10+4 layout — so OSS callers in s3api and shell pass 0 and keep their current behavior. Added table cases covering the custom 6+3 and 16+6 paths so the parameterization is pinned by tests. |
||
|
Chris LuandGitHub
|
45ba71a189 |
fix(volume): write state.pb into a real dir when -dir.idx is unset (#9178)
* fix(volume): write state.pb into a real dir when -dir.idx is unset When -dir.idx is not set, NewStore passed the empty default to NewState, making the state.pb path resolve to a relative "state.pb" against the process CWD. Under systemd (where CWD is typically /), this caused "open state.pb: permission denied" for operations such as `volumeServer.state -maintenanceOn`, even though the configured user owned the data dirs. Fall back to the first disk location's IdxDirectory so state.pb lives next to the volume data, consistent with other per-server artifacts. Fixes #9173 * fix(volume): always resolve state.pb dir via first disk location Use s.Locations[0].IdxDirectory unconditionally when a location exists so state.pb inherits the same resolution (~ expansion and empty-idxFolder fallback) already applied for the .idx files. Fall back to util.ResolvePath(idxFolder) in the location-less case so a relative or tilde-prefixed -dir.idx is still normalized. Addresses PR feedback on #9178. |
||
|
Chris LuandGitHub
|
45578a42e9 |
fix(volume): keep vacuum running past dangling .idx entries (#9115)
* fix(volume): keep vacuum running past dangling .idx entries Vacuum compaction aborted entirely on the first .idx entry whose offset pointed past the end of the .dat file, surfacing as `cannot hydrate needle from file: EOF` and stalling progress on every other volume. In both Go and Rust: - During compaction, skip an unreadable needle and continue. The bytes it pointed at were already unreachable via reads, so dropping the index reference makes the post-vacuum volume consistent. Real EIO still bails out so a disk fault is not silently papered over. - At volume load, do a single linear scan of the .idx and confirm every (offset + actual size) fits inside .dat. The pre-existing integrity check only looked at the last 10 entries, so deeper corruption (e.g. left over from a crashed batched write) went undetected and only surfaced later as a vacuum EOF. A failure now marks the volume read-only at load time so an operator can react. Refs #8928 * fix(volume): only skip permanent-corruption needle reads during vacuum Address PR review feedback (gemini-code-assist + coderabbit): The original patch skipped any non-EIO read failure, which would silently drop needles on transient errors — Windows hardware bad-sector errors (ERROR_CRC etc.) never surface as syscall.EIO; tiered-storage network timeouts and EROFS would also slip through and shrink the volume. Switch to an explicit whitelist of permanent-corruption shapes: - Add needle.ErrorCorrupted sentinel and wrap CRC and "index out of range" errors with %w so callers can match via errors.Is. - copyDataBasedOnIndexFile now skips only when the read failure is io.EOF, io.ErrUnexpectedEOF, ErrorSizeMismatch, ErrorSizeInvalid, or ErrorCorrupted. Anything else (real disk faults, environmental errors, Windows hardware codes) aborts the compaction so an operator notices. - Mirror the same whitelist in the Rust volume server, matching on io::ErrorKind::UnexpectedEof and the NeedleError corruption variants (SizeMismatch, CrcMismatch, IndexOutOfRange, TailTooShort). Also add `defer v.Close()` in TestVerifyIndexFitsInDat so Windows t.TempDir() cleanup can release the .dat/.idx handles. Refs #8928 * fix(volume): wrap entry-not-found size-mismatch with ErrorSizeMismatch Address PR review: the fallback branch in ReadBytes returned an unwrapped fmt.Errorf, so isSkippableNeedleReadError (and any caller using errors.Is(..., ErrorSizeMismatch)) could not match it. Wrap with %w so the whitelist applies, while leaving the existing direct sentinel return for the OffsetSize==4 / offset<MaxPossibleVolumeSize retry path unchanged so ReadData's `err == ErrorSizeMismatch` retry still triggers. Refs #8928 * fix(volume): integrate dangling-idx check into existing index load walk Address PR review (gemini-code-assist, medium): the structural .idx check used to do a second linear scan of the index file at every volume load, doubling the disk-I/O cost on servers managing many volumes. Track the largest (offset + actual size) seen during the existing needle-map load walks (`LoadCompactNeedleMap`, `NewLevelDbNeedleMap`, `NewSortedFileNeedleMap`'s `newNeedleMapMetricFromIndexFile`, `DoOffsetLoading`) on a new `MaximumNeedleEnd` field on `mapMetric`, exposed as `MaxNeedleEnd()` on the NeedleMapper interface. `volume.load()` then compares `nm.MaxNeedleEnd()` to the .dat size after the load is complete — pure numeric comparison, no extra I/O. The standalone `verifyIndexFitsInDat` helper and its caller in `CheckVolumeDataIntegrity` are removed; the test that used to drive the helper directly now exercises the new path via `LoadCompactNeedleMap`. Mirror the same change in the Rust volume server: track `max_needle_end` on `NeedleMapMetric`, expose via `max_needle_end()` on `CompactNeedleMap`, `RedbNeedleMap`, and the `NeedleMap` enum. The Rust load walk already happens in `load_from_idx` for both map kinds, so the structural check becomes free. Refs #8928 |
||
|
Chris LuandGitHub
|
e1fa4ec756 |
perf(cache): drop OS page cache after disk cache reads (#9098)
* perf(cache): drop OS page cache after disk cache reads After reading from the on-disk chunk cache, advise the kernel via FADV_DONTNEED to release the corresponding page cache pages. This prevents double-caching the same data in both user-space and kernel page caches, freeing RAM for other uses on systems with large disk caches. * fix(cache): guard dropReadCache against zero length and invalid fd A zero-length fadvise is interpreted as "to end of file" on Linux, which would inadvertently drop the page cache for the entire remainder of the cache volume. Also check fd >= 0 to avoid unnecessary syscalls when the backend file is closed. * perf(cache): only apply FADV_DONTNEED for reads >= 1 MiB For small needle reads the syscall overhead outweighs the memory savings, and the kernel page cache is more beneficial for warm data. Restrict fadvise to reads of at least 1 MiB where the freed page cache is meaningful. |
||
|
Chris LuandGitHub
|
300e906330 |
admin: report file and delete counts for EC volumes (#9060)
* admin: report file and delete counts for EC volumes The admin bucket size fix (#9058) left object counts at zero for EC-encoded data because VolumeEcShardInformationMessage carried no file count. Billing/monitoring dashboards therefore still under-report objects once a bucket is EC-encoded. Thread file_count and delete_count end-to-end: - Add file_count/delete_count to VolumeEcShardInformationMessage (proto fields 8 and 9) and regenerate master_pb. - Compute them lazily on volume servers by walking the .ecx index once per EcVolume, cache on the struct, and keep the cache in sync inside DeleteNeedleFromEcx (distinguishing live vs already-tombstoned entries so idempotent deletes do not drift the counts). - Populate the new proto fields from EcVolume.ToVolumeEcShardInformationMessage and carry them through the master-side EcVolumeInfo / topology sync. - Aggregate in admin collectCollectionStats, deduping per volume id: every node holding shards of an EC volume reports the same counts, so summing across nodes would otherwise multiply the object count by the number of shard holders. Regression tests cover the initial .ecx walk, live/tombstoned delete bookkeeping (including idempotent and missing-key cases), and the admin dedup path for an EC volume reported by multiple nodes. * ec: include .ecj journal in EcVolume delete count The initial delete count only reflected .ecx tombstones, missing any needle that was journaled in .ecj but not yet folded into .ecx — e.g. on partial recovery. Expand initCountsLocked to take the union of .ecx tombstones and .ecj journal entries, deduped by needle id, so: - an id that is both tombstoned in .ecx and listed in .ecj counts once - a duplicate .ecj entry counts once - an .ecj id with a live .ecx entry is counted as deleted (not live) - an .ecj id with no matching .ecx entry is still counted Covered by TestEcVolumeFileAndDeleteCountEcjUnion. * ec: report delete count authoritatively and tombstone once per delete Address two issues with the previous EcVolume file/delete count work: 1. The delete count was computed lazily on first heartbeat and mixed in a .ecj-union fallback to "recover" partial state. That diverged from how regular volumes report counts (always live from the needle map) and had drift cases when .ecj got reconciled. Replace with an eager walk of .ecx at NewEcVolume time, maintained incrementally on every DeleteNeedleFromEcx call. Semantics now match needle_map_metric: FileCount is the total number of needles ever recorded in .ecx (live + tombstoned), DeleteCount is the tombstones — so live = FileCount - DeleteCount. Drop the .ecj-union logic entirely. 2. A single EC needle delete fanned out to every node holding a replica of the primary data shard and called DeleteNeedleFromEcx on each, which inflated the per-volume delete total by the replica factor. Rewrite doDeleteNeedleFromRemoteEcShardServers to try replicas in order and stop at the first success (one tombstone per delete), and only fall back to other shards when the primary shard has no home (ErrEcShardMissing sentinel), not on transient RPC errors. Admin aggregation now folds EC counts correctly: FileCount is deduped per volume id (every shard holder has an identical .ecx) and DeleteCount is summed across nodes (each delete tombstones exactly one node). Live object count = deduped FileCount - summed DeleteCount. Tests updated to match the new semantics: - EC volume counts seed FileCount as total .ecx entries (live + tombstoned), DeleteCount as tombstones. - DeleteNeedleFromEcx keeps FileCount constant and increments DeleteCount only on live->tombstone transitions. - Admin dedup test uses distinct per-node delete counts (5 + 3 + 2) to prove they're summed, while FileCount=100 is applied once. * ec: test fixture uses real vid; admin warns on skewed ec counts - writeFixture now builds the .ecx/.ecj/.ec00/.vif filenames from the actual vid passed in, instead of hardcoding "_1". The existing tests all use vid=1 so behaviour is unchanged, but the helper no longer silently diverges from its documented parameter. - collectCollectionStats logs a glog warning when an EC volume's summed delete count exceeds its deduped file count, surfacing the anomaly (stale heartbeat, counter drift, etc.) instead of silently dropping the volume from the object count. * ec: derive file/delete counts from .ecx/.ecj file sizes seedCountsFromEcx walked the full .ecx index at volume load, which is wasted work: .ecx has fixed-size entries (NeedleMapEntrySize) and .ecj has fixed-size deletion records (NeedleIdSize), so both counts are pure file-size arithmetic. fileCount = ecxFileSize / NeedleMapEntrySize deleteCount = ecjFileSize / NeedleIdSize Rip out the cached counters, countsLock, seedCountsFromEcx, and the recordDelete helper. Track ecjFileSize directly on the EcVolume struct, seed it from Stat() at load, and bump it on every successful .ecj append inside DeleteNeedleFromEcx under ecjFileAccessLock. Skip the .ecj write entirely when the needle is already tombstoned so the derived delete count stays idempotent on repeat deletes. Heartbeats now compute counts in O(1). Tests updated: the initial fixture pre-populates .ecj with two ids to verify the file-size derivation end-to-end, and the delete test keeps its idempotent-re-delete / missing-needle invariants (unchanged externally, now enforced by the early return rather than a cache guard). * ec: sync Rust volume server with Go file/delete count semantics Mirror the Go-side EC file/delete count work in the Rust volume server so mixed Go/Rust clusters report consistent bucket object counts in the admin dashboard. - Add file_count (8) and delete_count (9) to the Rust copy of VolumeEcShardInformationMessage (seaweed-volume/proto/master.proto). - EcVolume gains ecj_file_size, seeded from the journal's metadata on open and bumped inside journal_delete on every successful append. - file_and_delete_count() returns counts derived in O(1) from ecx_file_size / NEEDLE_MAP_ENTRY_SIZE and ecj_file_size / NEEDLE_ID_SIZE, matching Go's FileAndDeleteCount. - to_volume_ec_shard_information_messages populates the new proto fields instead of defaulting them to zero. - mark_needle_deleted_in_ecx now returns a DeleteOutcome enum (NotFound / AlreadyDeleted / Tombstoned) so journal_delete can skip both the .ecj append and the size bump when the needle is missing or already tombstoned, keeping the derived delete_count idempotent on repeat or no-op deletes. - Rust's EcVolume::new no longer replays .ecj into .ecx on load. Go's RebuildEcxFile is only called from specific decode/rebuild gRPC handlers, not on volume open, and replaying on load was hiding the deletion journal from the new file-size-derived delete counter. rebuild_ecx_from_journal is kept as dead_code for future decode paths that may want the same replay semantics. Also clean up the Go FileAndDeleteCount to drop unnecessary runtime guards against zero constants — NeedleMapEntrySize and NeedleIdSize are compile-time non-zero. test_ec_volume_journal updated to pre-populate the .ecx with the needles it deletes, and extended to verify that repeat and missing-id deletes do not drift the derived counts. * ec: document enterprise-reserved proto field range on ec shard info Both OSS master.proto copies now note that fields 10-19 are reserved for future upstream additions while 20+ are owned by the enterprise fork. Enterprise already pins data_shards/parity_shards at 20/21, so keeping OSS additions inside 8-19 avoids wire-level collisions for mixed deployments. * ec(rust): resolve .ecx/.ecj helpers from ecx_actual_dir ecx_file_name() and ecj_file_name() resolved from self.dir_idx, but new() opens the actual files from ecx_actual_dir (which may fall back to the data dir when the idx dir does not contain the index). After a fallback, read_deleted_needles() and rebuild_ecx_from_journal() would read/rebuild the wrong (nonexistent) path while heartbeats reported counts from the file actually in use — silently dropping deletes. Point idx_base_name() at ecx_actual_dir, which is initialized to dir_idx and only diverges after a successful fallback, so every call site agrees with the file new() has open. The pre-fallback call in new() (line 142) still returns the dir_idx path because ecx_actual_dir == dir_idx at that point. Update the destroy() sweep to build the dir_idx cleanup paths explicitly instead of leaning on the helpers, so post-fallback stale files in the idx dir are still removed. * ec: reset ecj size after rebuild; rollback ecx tombstone on ecj failure Two EC delete-count correctness fixes applied symmetrically to Go and Rust volume servers. 1. rebuild_ecx_from_journal (Rust) now sets ecj_file_size = 0 after recreating the empty journal, matching the on-disk truth. Previously the cached size still reflected the pre-rebuild journal and file_and_delete_count() would keep reporting stale delete counts. The Go side has no equivalent bug because RebuildEcxFile runs in an offline helper that does not touch an EcVolume struct. 2. DeleteNeedleFromEcx / journal_delete used to tombstone the .ecx entry before writing the .ecj record. If the .ecj append then failed, the needle was permanently marked deleted but the heartbeat-reported delete_count never advanced (it is derived from .ecj file size), and a retry would see AlreadyDeleted and early- return, leaving the drift permanent. Both languages now capture the entry's file offset and original size bytes during the mark step, attempt the .ecj append, and on failure roll the .ecx tombstone back by writing the original size bytes at the known offset. A rollback that itself errors is logged (glog / tracing) but cannot re-sync the files — this is the same failure mode a double disk error would produce, and is unavoidable without a full on-disk transaction log. Go: wrap MarkNeedleDeleted in a closure that captures the file offset into an outer variable, then pass the offset + oldSize to the new rollbackEcxTombstone helper on .ecj seek/write errors. Rust: DeleteOutcome::Tombstoned now carries the size_offset and a [u8; SIZE_SIZE] copy of the pre-tombstone size field. journal_delete destructures on Tombstoned and calls restore_ecx_size on .ecj append failure. * test(ec): widen admin /health wait to 180s for cold CI TestEcEndToEnd starts master, 14 volume servers, filer, 2 workers and admin in sequence, then waited only 60s for admin's HTTP server to come up. On cold GitHub runners the tail of the earlier subprocess startups eats most of that budget and the wait occasionally times out (last hit on run 24374773031). The local fast path is still ~20s total, so the bump only extends the timeout ceiling, not the happy path. * test(ec): fork volume servers in parallel in TestEcEndToEnd startWeed is non-blocking (just cmd.Start()), so the per-process fork + mkdir + log-file-open overhead for 14 volume servers was serialized for no reason. On cold CI disks that overhead stacks up and eats into the subsequent admin /health wait, which is how run 24374773031 flaked. Wrap the volume-server loop in a sync.WaitGroup and guard runningCmds with a mutex so concurrent appends are safe. startWeed still calls t.Fatalf on failure, which is fine from a goroutine for a fatal test abort; the fail-fast isn't something we rely on for precise ordering. * ec: fsync ecx before ecj, truncate on failure, harden rebuild Four correctness fixes covering both volume servers. 1. Durability ordering (Go + Rust). After marking the .ecx tombstone we now fsync .ecx before touching .ecj, so a crash between the two files cannot leave the journal with an entry for a needle whose tombstone is still sitting in page cache. Once the fsync returns, the tombstone is the source of truth: reads see "deleted", delete_count may under-count by one (benign, idempotent retries) but never over-reports. If the fsync itself fails we restore the original size bytes and surface the error. The .ecj append is then followed by its own Sync so the reported delete_count matches the on-disk journal once the write returns. 2. .ecj truncation on append failure. write_all may have extended the journal on disk before sync_all / Sync errors out, leaving the cached ecj_file_size out of sync with the physical length and drifting delete_count permanently after restart. Both languages now capture the pre-append size, truncate the file back via set_len / Truncate on any write or sync failure, and only then restore the .ecx tombstone. Truncation errors are logged — same-fd length resets cannot realistically fail — but cannot themselves re-sync the files. 3. Atomic rebuild_ecx_from_journal (Rust, dead code today but wired up on any future decode path). Previously a failed mark_needle_deleted_in_ecx call was swallowed with `let _ = ...` and the journal was still removed, silently losing tombstones. We now bubble up any non-NotFound error, fsync .ecx after the whole replay succeeds, and only then drop and recreate .ecj. NotFound is still ignored (expected race between delete and encode). 4. Missing-.ecx hardening (Rust). mark_needle_deleted_in_ecx used to return Ok(NotFound) when self.ecx_file was None, hiding a closed or corrupt volume behind what looks like an idempotent no-op. It now returns an io::Error carrying the volume id so callers (e.g. journal_delete) fail loudly instead. Existing Go and Rust EC test suites stay green. * ec: make .ecx immutable at runtime; track deletes in memory + .ecj Refactors both volume servers so the sealed sorted .ecx index is never mutated during normal operation. Runtime deletes are committed to the .ecj deletion journal and tracked in an in-memory deleted-needle set; read-path lookups consult that set to mask out deleted ids on top of the immutable .ecx record. Mirrors the intended design on both Go and Rust sides. EcVolume gains a `deletedNeedles` / `deleted_needles` set seeded from .ecj in NewEcVolume / EcVolume::new. DeleteNeedleFromEcx / journal_delete: 1. Looks the needle up read-only in .ecx. 2. Missing needle -> no-op. 3. Pre-existing .ecx tombstone (from a prior decode/rebuild) -> mirror into the in-memory set, no .ecj append. 4. Otherwise append the id to .ecj, fsync, and only then publish the id into the set. A partial write is truncated back to the pre-append length so the on-disk journal and the in-memory set cannot drift. FindNeedleFromEcx / find_needle_from_ecx now return TombstoneFileSize when the id is in the in-memory set, even though the bytes on disk still show the original size. FileAndDeleteCount: fileCount = .ecx size / NeedleMapEntrySize (unchanged) deleteCount = len(deletedNeedles) (was: .ecj size / NeedleIdSize) The RebuildEcxFile / rebuild_ecx_from_journal decode-time helpers still fold .ecj into .ecx — that is the one place tombstones land in the physical index, and it runs offline on closed files. Rust's rebuild helper now also clears the in-memory set when it succeeds. Dead code removed on the Rust side: `DeleteOutcome`, `mark_needle_deleted_in_ecx`, `restore_ecx_size`. Go drops the runtime `rollbackEcxTombstone` path. Neither helper was needed once .ecx stopped being a runtime mutation target. TestEcVolumeSyncEnsuresDeletionsVisible (issue #7751) is rewritten as TestEcVolumeDeleteDurableToJournal, which exercises the full durability chain: delete -> .ecj fsync -> FindNeedleFromEcx masks via the in-memory set -> raw .ecx bytes are *unchanged* -> Close + RebuildEcxFile folds the journal into .ecx -> raw bytes now show the tombstone, as CopyFile in the decode path expects. |
||
|
Chris Lu
|
e648c76bcf | go fmt | ||
|
Chris LuandGitHub
|
940eed0bd3 |
fix(ec): generate .ecx before EC shards to prevent data inconsistency (#8972)
* fix(ec): generate .ecx before EC shards to prevent data inconsistency In VolumeEcShardsGenerate, the .ecx index was generated from .idx AFTER the EC shards were generated from .dat. If any write occurred between these two steps (e.g. WriteNeedleBlob during replica sync, which bypasses the read-only check), the .ecx would contain entries pointing to data that doesn't exist in the EC shards, causing "shard too short" and "size mismatch" errors on subsequent reads and scrubs. Fix by generating .ecx FIRST, then snapshotting datFileSize, then encoding EC shards. If a write sneaks in after .ecx generation, the EC shards contain more data than .ecx references — which is harmless (the extra data is simply not indexed). Also snapshot datFileSize before EC encoding to ensure the .vif reflects the same .dat state that .ecx was generated from. Add TestEcConsistency_WritesBetweenEncodeAndEcx that reproduces the race condition by appending data between EC encoding and .ecx generation. * fix: pass actual offset to ReadBytes, improve test quality - Pass offset.ToActualOffset() to ReadBytes instead of 0 to preserve correct error metrics and error messages within ReadBytes - Handle Stat() error in assembleFromIntervalsAllowError - Rename TestEcConsistency_DatFileGrowsDuringEncoding to TestEcConsistency_ExactLargeRowEncoding (test verifies fixed-size encoding, not concurrent growth) - Update test comment to clarify it reproduces the old buggy sequence - Fix verification loop to advance by readSize for full data coverage * fix(ec): add dat/idx consistency check in worker EC encoding The erasure_coding worker copies .dat and .idx as separate network transfers. If a write lands on the source between these copies, the .idx may have entries pointing past the end of .dat, leading to EC volumes with .ecx entries that reference non-existent shard data. Add verifyDatIdxConsistency() that walks the .idx and verifies no entry's offset+size exceeds the .dat file size. This fails the EC task early with a clear error instead of silently producing corrupt EC volumes. * test(ec): add integration test verifying .ecx/.ecd consistency TestEcIndexConsistencyAfterEncode uploads multiple needles of varying sizes (14B to 256KB), EC-encodes the volume, mounts data shards, then reads every needle back via the EC read path and verifies payload correctness. This catches any inconsistency between .ecx index entries and EC shard data. * fix(test): account for needle overhead in test volume fixture WriteTestVolumeFiles created a .dat of exactly datSize bytes but the .idx entry claimed a needle of that same size. GetActualSize adds header + checksum + timestamp overhead, so the consistency check correctly rejects this as the needle extends past the .dat file. Fix by sizing the .dat to GetActualSize(datSize) so the .idx entry is consistent with the .dat contents. * fix(test): remove flaky shard ID assertion in EC scrub test When shard 0 is truncated on disk after mount, the volume server may detect corruption via parity mismatches (shards 10-13) rather than a direct read failure on shard 0, depending on OS caching/mmap behavior. Replace the brittle shard-0-specific check with a volume ID validation. * fix(test): close upload response bodies and tighten file count assertion Wrap UploadBytes calls with ReadAllAndClose to prevent connection/fd leaks during test execution. Also tighten TotalFiles check from >= 1 to == 1 since ecSetup uploads exactly one file. |
||
|
Chris LuandGitHub
|
d4548376a1 |
fix(ec): off-by-one in nLargeBlockRows causes EC read corruption (#8957)
* fix(ec): off-by-one in nLargeBlockRows causes EC read corruption (#8947) The nLargeBlockRows formula in locateOffset used (shardDatSize-1)/largeBlockLength, which produces an off-by-one error when shardDatSize is an exact multiple of largeBlockLength (e.g. a 30GB volume with 10 data shards = 3GB per shard). This causes needles in the last large block row to be mislocated as small blocks, reading from completely wrong shard positions and returning garbage data. Fix: remove the -1 from locateOffset and only apply it in the ecdFileSize fallback path (old volumes without datFileSize in .vif), where it's needed to handle the ambiguous case conservatively. Also fix ReadEcShardNeedle to pass offset=0 to ReadBytes, consistent with the scrub path, since the bytes buffer already starts at position 0. * fix: add volume context to EC read errors, remove contextless glog The glog.Errorf in ReadBytes logged "entry not found" without any volume ID, making it impossible to identify which volume was affected. Remove this contextless log and instead add volume ID, needle ID, offset, and size to the error returned from the EC read path. The EC scrub callers already wrap errors with volume context. |
||
|
Chris LuandGitHub
|
995dfc4d5d |
chore: remove ~50k lines of unreachable dead code (#8913)
* chore: remove unreachable dead code across the codebase Remove ~50,000 lines of unreachable code identified by static analysis. Major removals: - weed/filer/redis_lua: entire unused Redis Lua filer store implementation - weed/wdclient/net2, resource_pool: unused connection/resource pool packages - weed/plugin/worker/lifecycle: unused lifecycle plugin worker - weed/s3api: unused S3 policy templates, presigned URL IAM, streaming copy, multipart IAM, key rotation, and various SSE helper functions - weed/mq/kafka: unused partition mapping, compression, schema, and protocol functions - weed/mq/offset: unused SQL storage and migration code - weed/worker: unused registry, task, and monitoring functions - weed/query: unused SQL engine, parquet scanner, and type functions - weed/shell: unused EC proportional rebalance functions - weed/storage/erasure_coding/distribution: unused distribution analysis functions - Individual unreachable functions removed from 150+ files across admin, credential, filer, iam, kms, mount, mq, operation, pb, s3api, server, shell, storage, topology, and util packages * fix(s3): reset shared memory store in IAM test to prevent flaky failure TestLoadIAMManagerFromConfig_EmptyConfigWithFallbackKey was flaky because the MemoryStore credential backend is a singleton registered via init(). Earlier tests that create anonymous identities pollute the shared store, causing LookupAnonymous() to unexpectedly return true. Fix by calling Reset() on the memory store before the test runs. * style: run gofmt on changed files * fix: restore KMS functions used by integration tests * fix(plugin): prevent panic on send to closed worker session channel The Plugin.sendToWorker method could panic with "send on closed channel" when a worker disconnected while a message was being sent. The race was between streamSession.close() closing the outgoing channel and sendToWorker writing to it concurrently. Add a done channel to streamSession that is closed before the outgoing channel, and check it in sendToWorker's select to safely detect closed sessions without panicking. |
||
|
af68449a26 |
Process .ecj deletions during EC decode and vacuum decoded volume (#8863)
* Process .ecj deletions during EC decode and vacuum decoded volume (#8798) When decoding EC volumes back to normal volumes, deletions recorded in the .ecj journal were not being applied before computing the dat file size or checking for live needles. This caused the decoded volume to include data for deleted files and could produce false positives in the all-deleted check. - Call RebuildEcxFile before HasLiveNeedles/FindDatFileSize in VolumeEcShardsToVolume so .ecj deletions are merged into .ecx first - Vacuum the decoded volume after mounting in ec.decode to compact out deleted needle data from the .dat file - Add integration tests for decoding with non-empty .ecj files * storage: add offline volume compaction helper Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * ec: compact decoded volumes before deleting shards Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * ec: address PR review comments - Fall back to data directory for .ecx when idx directory lacks it - Make compaction failure non-fatal during EC decode - Remove misleading "buffer: 10%" from space check error message * ec: collect .ecj from all shard locations during decode Each server's .ecj only contains deletions for needles whose data resides in shards held by that server. Previously, sources with no new data shards to contribute were skipped entirely, losing their .ecj deletion entries. Now .ecj is always appended from every shard location so RebuildEcxFile sees the full set of deletions. * ec: add integration tests for .ecj collection during decode TestEcDecodePreservesDeletedNeedles: verifies that needles deleted via VolumeEcBlobDelete are excluded from the decoded volume. TestEcDecodeCollectsEcjFromPeer: regression test for the fix in collectEcShards. Deletes a needle only on a peer server that holds no new data shards, then verifies the deletion survives decode via .ecj collection. * ec: address review nits in decode and tests - Remove double error wrapping in mountDecodedVolume - Check VolumeUnmount error in peer ecj test - Assert 404 specifically for deleted needles, fail on 5xx --------- Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> |
||
|
Chris LuandGitHub
|
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 LuandGitHub
|
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 LuandGitHub
|
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
|