ec: fall back to data dir when ecx file not found in idx dir (#8541)

* ec: fall back to data dir when ecx file not found in idx dir (#8540)

When -dir.idx is configured after EC encoding, the .ecx/.ecj files
remain in the data directory. NewEcVolume now falls back to the data
directory when the index file is not found in dirIdx.

* ec: add fallback logging and improved error message for ecx lookup

* ec: preserve configured dirIdx, track actual ecx location separately

The previous fallback set ev.dirIdx = dir when finding .ecx in the data
directory, which corrupted IndexBaseFileName() for future writes (e.g.,
WriteIdxFileFromEcIndex during EC-to-volume conversion would write the
.idx file to the data directory instead of the configured index directory).

Introduce ecxActualDir to track where .ecx/.ecj were actually found,
used only by FileName() for cleanup/destroy. IndexBaseFileName() continues
to use the configured dirIdx for new file creation.

* ec: check both idx and data dirs for .ecx in all cleanup and lookup paths

When -dir.idx is configured after EC encoding, .ecx/.ecj files may
reside in the data directory. Several code paths only checked
l.IdxDirectory, causing them to miss these files:

- removeEcVolumeFiles: now removes .ecx/.ecj from both directories
- loadExistingVolume: ecx existence check falls back to data dir
- deleteEcShardIdsForEachLocation: ecx existence check and cleanup
  both cover the data directory
- VolumeEcShardsRebuild: ecx lookup falls back to data directory
  so RebuildEcxFile operates on the correct file
This commit is contained in:
Chris Lu
2026-03-07 09:18:48 -08:00
committed by GitHub
parent bfc430afbd
commit af4c3fcb31
4 changed files with 43 additions and 7 deletions

View File

@@ -154,7 +154,12 @@ func (vs *VolumeServer) VolumeEcShardsRebuild(ctx context.Context, req *volume_s
continue
}
if util.FileExists(path.Join(location.IdxDirectory, baseFileName+".ecx")) {
indexBaseFileName := path.Join(location.IdxDirectory, baseFileName)
if !util.FileExists(indexBaseFileName+".ecx") && location.IdxDirectory != location.Directory {
// .ecx may be in the data directory if created before -dir.idx was configured
indexBaseFileName = path.Join(location.Directory, baseFileName)
}
if util.FileExists(indexBaseFileName + ".ecx") {
// write .ec00 ~ .ec13 files
dataBaseFileName := path.Join(location.Directory, baseFileName)
if generatedShardIds, err := erasure_coding.RebuildEcFiles(dataBaseFileName); err != nil {
@@ -163,9 +168,8 @@ func (vs *VolumeServer) VolumeEcShardsRebuild(ctx context.Context, req *volume_s
rebuiltShardIds = generatedShardIds
}
indexBaseFileName := path.Join(location.IdxDirectory, baseFileName)
if err := erasure_coding.RebuildEcxFile(indexBaseFileName); err != nil {
return nil, fmt.Errorf("RebuildEcxFile %s: %v", dataBaseFileName, err)
return nil, fmt.Errorf("RebuildEcxFile %s: %v", indexBaseFileName, err)
}
break
@@ -283,7 +287,11 @@ func deleteEcShardIdsForEachLocation(bName string, location *storage.DiskLocatio
indexBaseFilename := path.Join(location.IdxDirectory, bName)
dataBaseFilename := path.Join(location.Directory, bName)
if util.FileExists(path.Join(location.IdxDirectory, bName+".ecx")) {
ecxExists := util.FileExists(path.Join(location.IdxDirectory, bName+".ecx"))
if !ecxExists && location.IdxDirectory != location.Directory {
ecxExists = util.FileExists(path.Join(location.Directory, bName+".ecx"))
}
if ecxExists {
for _, shardId := range shardIds {
shardFileName := dataBaseFilename + erasure_coding.ToExt(int(shardId))
if util.FileExists(shardFileName) {
@@ -303,10 +311,16 @@ func deleteEcShardIdsForEachLocation(bName string, location *storage.DiskLocatio
}
if hasEcxFile && existingShardCount == 0 {
if err := os.Remove(indexBaseFilename + ".ecx"); err != nil {
// Remove .ecx/.ecj from both idx and data directories
// since they may be in either location depending on when -dir.idx was configured
if err := os.Remove(indexBaseFilename + ".ecx"); err != nil && !os.IsNotExist(err) {
return err
}
os.Remove(indexBaseFilename + ".ecj")
if location.IdxDirectory != location.Directory {
os.Remove(dataBaseFilename + ".ecx")
os.Remove(dataBaseFilename + ".ecj")
}
if !hasIdxFile {
// .vif is used for ec volumes and normal volumes