mirror of
https://github.com/seaweedfs/seaweedfs.git
synced 2026-11-07 04:27:49 +01:00
Chris LuandClaude Opus 5.5
cdea7e79e0
* filer: fold small chunks into manifests 256 at a time Every metadata event carries the file's whole chunk list, so a file grown by small appends re-sent each chunk record on every append until the list reached ManifestBatch (10000). Chunks under 1 MiB now fold once 256 of them build up; full-size chunks still fold at ManifestBatch, so large files keep their flat lists and read without a manifest fetch. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * filer: merge appended small chunks at the small-chunk fold count The append path merges small chunks into full-size ones, but only at 1000 of them; the fold now hides small chunks in a manifest at 256, so the merge would never see enough of them. Merging at the same count keeps rewriting them into full chunks first. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
78 lines
2.6 KiB
Go
78 lines
2.6 KiB
Go
package weed_server
|
|
|
|
import (
|
|
"context"
|
|
"io"
|
|
"math"
|
|
|
|
"github.com/seaweedfs/seaweedfs/weed/filer"
|
|
"github.com/seaweedfs/seaweedfs/weed/glog"
|
|
"github.com/seaweedfs/seaweedfs/weed/operation"
|
|
"github.com/seaweedfs/seaweedfs/weed/pb/filer_pb"
|
|
"github.com/seaweedfs/seaweedfs/weed/stats"
|
|
)
|
|
|
|
// MergeChunkMinCount matches the small-chunk fold so a merge rewrites them
|
|
// before MaybeManifestize hides them in a manifest.
|
|
const MergeChunkMinCount int = filer.SmallChunkManifestBatch
|
|
|
|
func (fs *FilerServer) maybeMergeChunks(ctx context.Context, so *operation.StorageOption, inputChunks []*filer_pb.FileChunk) (mergedChunks []*filer_pb.FileChunk, err error) {
|
|
// Don't merge SSE-encrypted chunks to preserve per-chunk metadata
|
|
for _, chunk := range inputChunks {
|
|
if chunk.GetSseType() != 0 { // Any SSE type (SSE-C or SSE-KMS)
|
|
glog.V(3).InfofCtx(ctx, "Skipping chunk merge for SSE-encrypted chunks")
|
|
return inputChunks, nil
|
|
}
|
|
}
|
|
|
|
// Only merge small chunks more than half of the file
|
|
var chunkSize = fs.option.MaxMB * 1024 * 1024
|
|
var smallChunk, sumChunk int
|
|
var minOffset int64 = math.MaxInt64
|
|
for _, chunk := range inputChunks {
|
|
if chunk.IsChunkManifest {
|
|
continue
|
|
}
|
|
if chunk.Size < uint64(chunkSize/2) {
|
|
smallChunk++
|
|
if chunk.Offset < minOffset {
|
|
minOffset = chunk.Offset
|
|
}
|
|
}
|
|
sumChunk++
|
|
}
|
|
if smallChunk < MergeChunkMinCount || smallChunk < sumChunk/2 {
|
|
return inputChunks, nil
|
|
}
|
|
|
|
return fs.mergeChunks(ctx, so, inputChunks, minOffset)
|
|
}
|
|
|
|
func (fs *FilerServer) mergeChunks(ctx context.Context, so *operation.StorageOption, inputChunks []*filer_pb.FileChunk, chunkOffset int64) (mergedChunks []*filer_pb.FileChunk, mergeErr error) {
|
|
chunkedFileReader := filer.NewChunkStreamReaderFromFiler(ctx, fs.filer.MasterClient, inputChunks)
|
|
_, mergeErr = chunkedFileReader.Seek(chunkOffset, io.SeekCurrent)
|
|
if mergeErr != nil {
|
|
return nil, mergeErr
|
|
}
|
|
mergedChunks, _, _, mergeErr, _ = fs.uploadReaderToChunks(ctx, nil, chunkedFileReader, chunkOffset, int32(fs.option.MaxMB*1024*1024), "", "", true, so)
|
|
if mergeErr != nil {
|
|
return
|
|
}
|
|
|
|
stats.FilerHandlerCounter.WithLabelValues(stats.ChunkMerge).Inc()
|
|
for _, chunk := range inputChunks {
|
|
if chunk.Offset < chunkOffset || chunk.IsChunkManifest {
|
|
mergedChunks = append(mergedChunks, chunk)
|
|
}
|
|
}
|
|
|
|
garbage, err := filer.MinusChunks(ctx, fs.lookupFileId, inputChunks, mergedChunks, fs.filer.MasterClient)
|
|
if err != nil {
|
|
glog.ErrorfCtx(ctx, "Failed to resolve old entry chunks when delete old entry chunks. new: %s, old: %s",
|
|
mergedChunks, inputChunks)
|
|
return mergedChunks, err
|
|
}
|
|
fs.filer.DeleteChunksNotRecursive(garbage)
|
|
return
|
|
}
|