Files
seaweedfs/weed/filer/filer_delete_entry.go
Chris Lu f530102c45 filer: do not sweep children when deleting a folder non-recursively (#10782)
* filer: do not sweep children when deleting a folder non-recursively

doBatchDeleteFolderMetaAndData lists a folder and bails out if it has any
children, then calls Store.DeleteFolderChildren unconditionally. On the
non-recursive path that bulk sweep has nothing legitimate to remove: it only
runs once the listing came back empty, so the sole rows it can delete are
ones inserted after the check.

The S3 empty-folder cleaner deletes through this path, so a PUT landing
between the listing and the sweep loses its entry after the write was already
acknowledged. Neither side sees an error - the client has its 200 and the
cleaner logs an ordinary empty-folder deletion - and the chunks leak, since
the cleaner passes shouldDeleteChunks=false and nothing was enumerated to
collect. Workloads that scatter objects over many shallow prefixes empty and
refill those folders constantly, which is what makes the window reachable.

Sweep only when the delete is recursive, or when the whole-bucket shortcut
skipped the listing and depends on it.

Claude-Session: https://claude.ai/code/session_01HdLXMUopwgofPb1ZEmiE6r

* filer: pin the folder entry removal left by the racing-child test

The surviving entry is reachable by path but drops out of listings until the
folder comes back, and nothing in the test said so. Assert it, so the exposure
that remains after this change is visible rather than implied.

Claude-Session: https://claude.ai/code/session_01HdLXMUopwgofPb1ZEmiE6r
2026-08-16 22:09:23 -07:00

191 lines
6.4 KiB
Go

package filer
import (
"context"
"fmt"
"github.com/seaweedfs/seaweedfs/weed/glog"
"github.com/seaweedfs/seaweedfs/weed/pb/filer_pb"
"github.com/seaweedfs/seaweedfs/weed/pb/master_pb"
"github.com/seaweedfs/seaweedfs/weed/stats"
"github.com/seaweedfs/seaweedfs/weed/util"
)
const (
MsgFailDelNonEmptyFolder = "fail to delete non-empty folder"
)
type OnChunksFunc func([]*filer_pb.FileChunk) error
type OnHardLinkIdsFunc func([]HardLinkId) error
func (f *Filer) DeleteEntryMetaAndData(ctx context.Context, p util.FullPath, isRecursive, ignoreRecursiveError, shouldDeleteChunks, isFromOtherCluster bool, signatures []int32, ifNotModifiedAfter int64) (err error) {
if p == "/" {
return nil
}
entry, findErr := f.FindEntry(ctx, p)
if findErr != nil {
return findErr
}
if ifNotModifiedAfter > 0 && entry.Attr.Mtime.Unix() > ifNotModifiedAfter {
return nil
}
isDeleteCollection := f.IsBucket(entry)
if entry.IsDirectory() {
// delete the folder children, not including the folder itself
err = f.doBatchDeleteFolderMetaAndData(ctx, entry, isRecursive, ignoreRecursiveError, shouldDeleteChunks && !isDeleteCollection, isDeleteCollection, isFromOtherCluster, signatures, func(hardLinkIds []HardLinkId) error {
// A case not handled:
// what if the chunk is in a different collection?
if shouldDeleteChunks {
f.maybeDeleteHardLinks(ctx, hardLinkIds)
}
return nil
})
if err != nil {
glog.V(2).InfofCtx(ctx, "delete directory %s: %v", p, err)
return fmt.Errorf("delete directory %s: %v", p, err)
}
}
// delete the file or folder
err = f.doDeleteEntryMetaAndData(ctx, entry, shouldDeleteChunks, isFromOtherCluster, signatures)
if err != nil {
return fmt.Errorf("delete file %s: %v", p, err)
}
if shouldDeleteChunks && !isDeleteCollection {
if len(entry.HardLinkId) != 0 && entry.HardLinkCounter > 1 {
// if the file is a hard link and there are other hard links, do not delete the chunks
} else {
f.DeleteChunks(ctx, p, entry.GetChunks())
}
}
if isDeleteCollection {
collectionName := entry.Name()
f.DoDeleteCollection(collectionName)
// drop bucket-labeled series held by this process; the S3 gateway
// only cleans its own registry
stats.DeleteBucketMetrics(collectionName)
}
return nil
}
func (f *Filer) doBatchDeleteFolderMetaAndData(ctx context.Context, entry *Entry, isRecursive, ignoreRecursiveError, shouldDeleteChunks, isDeletingBucket, isFromOtherCluster bool, signatures []int32, onHardLinkIdsFn OnHardLinkIdsFunc) (err error) {
//collect all the chunks of this layer and delete them together at the end
var chunksToDelete []*filer_pb.FileChunk
lastFileName := ""
includeLastFile := false
listedChildren := !isDeletingBucket || !f.Store.CanDropWholeBucket()
if listedChildren {
for {
entries, _, err := f.ListDirectoryEntries(ctx, entry.FullPath, lastFileName, includeLastFile, PaginationSize, "", "", "")
if err != nil {
glog.ErrorfCtx(ctx, "list folder %s: %v", entry.FullPath, err)
return fmt.Errorf("list folder %s: %v", entry.FullPath, err)
}
if lastFileName == "" && !isRecursive && len(entries) > 0 {
// only for first iteration in the loop
glog.V(2).InfofCtx(ctx, "deleting a folder %s has children: %+v ...", entry.FullPath, entries[0].Name())
return fmt.Errorf("%s: %s", MsgFailDelNonEmptyFolder, entry.FullPath)
}
for _, sub := range entries {
lastFileName = sub.Name()
if sub.IsDirectory() {
subIsDeletingBucket := f.IsBucket(sub)
err = f.doBatchDeleteFolderMetaAndData(ctx, sub, isRecursive, ignoreRecursiveError, shouldDeleteChunks, subIsDeletingBucket, isFromOtherCluster, nil, onHardLinkIdsFn)
} else {
if !isFromOtherCluster {
if _, remoteErr := f.maybeDeleteFromRemote(ctx, sub); remoteErr != nil {
glog.Warningf("remote delete child %s: %v", sub.FullPath, remoteErr)
if !ignoreRecursiveError {
err = remoteErr
}
}
}
if err != nil && !ignoreRecursiveError {
break
}
f.NotifyUpdateEvent(ctx, sub, nil, shouldDeleteChunks, isFromOtherCluster, nil)
if len(sub.HardLinkId) != 0 {
// hard link chunk data are deleted separately
err = onHardLinkIdsFn([]HardLinkId{sub.HardLinkId})
} else {
if shouldDeleteChunks {
chunksToDelete = append(chunksToDelete, sub.GetChunks()...)
}
}
}
if err != nil && !ignoreRecursiveError {
return err
}
}
if len(entries) < PaginationSize {
break
}
}
}
glog.V(3).InfofCtx(ctx, "deleting directory %v delete chunks: %v", entry.FullPath, shouldDeleteChunks)
// a non-recursive delete already proved the folder empty above, so sweeping the
// children now can only remove entries that raced in after that listing
if isRecursive || !listedChildren {
if storeDeletionErr := f.Store.DeleteFolderChildren(ctx, entry.FullPath); storeDeletionErr != nil {
return fmt.Errorf("filer store delete: %w", storeDeletionErr)
}
}
f.NotifyUpdateEvent(ctx, entry, nil, shouldDeleteChunks, isFromOtherCluster, signatures)
f.DeleteChunks(ctx, entry.FullPath, chunksToDelete)
return nil
}
func (f *Filer) doDeleteEntryMetaAndData(ctx context.Context, entry *Entry, shouldDeleteChunks bool, isFromOtherCluster bool, signatures []int32) (err error) {
glog.V(3).InfofCtx(ctx, "deleting entry %v, delete chunks: %v", entry.FullPath, shouldDeleteChunks)
if !isFromOtherCluster {
if _, remoteDeletionErr := f.maybeDeleteFromRemote(ctx, entry); remoteDeletionErr != nil {
return remoteDeletionErr
}
}
if storeDeletionErr := f.Store.DeleteOneEntry(ctx, entry); storeDeletionErr != nil {
return fmt.Errorf("filer store delete: %w", storeDeletionErr)
}
if !entry.IsDirectory() {
f.NotifyUpdateEvent(ctx, entry, nil, shouldDeleteChunks, isFromOtherCluster, signatures)
}
return nil
}
func (f *Filer) DoDeleteCollection(collectionName string) (err error) {
return f.MasterClient.WithClient(false, func(client master_pb.SeaweedClient) error {
_, err := client.CollectionDelete(context.Background(), &master_pb.CollectionDeleteRequest{
Name: collectionName,
})
if err != nil {
glog.Infof("delete collection %s: %v", collectionName, err)
}
return err
})
}
func (f *Filer) maybeDeleteHardLinks(ctx context.Context, hardLinkIds []HardLinkId) {
for _, hardLinkId := range hardLinkIds {
if err := f.Store.DeleteHardLink(ctx, hardLinkId); err != nil {
glog.ErrorfCtx(ctx, "delete hard link id %d : %v", hardLinkId, err)
}
}
}