Github-Mirror/seaweedfs
1
0 Fork 0
mirror of https://github.com/seaweedfs/seaweedfs.git synced 2026-11-07 04:27:49 +01:00
Code Issues Packages Projects Releases Wiki Activity

s3: commit the delete marker in the owner's finalize transaction (#12432)

Browse Source 
* s3: commit the delete marker in the owner's finalize transaction

createDeleteMarker wrote the marker with mkFile to the gateway's current
filer and then sent RECOMPUTE_LATEST to the object's ring owner. When the
two differ, the owner scans .versions before peer metadata sync delivers
the marker, re-derives the pointer to the previous version, and the
marker stays non-current on every filer.

routedVersionedFinalize now takes an optional version entry and PUTs it
in the same ObjectTransaction ahead of the recompute, the way PutObject
and CompleteMultipartUpload already do. The copy destination keeps
passing nil: its version file is already written on the owner.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* s3: test a versioned delete when the gateway's filer is not the owner

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* s3: assert the delete marker and the pointer flip share one transaction

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
Chris LuandClaude Opus 5.5 authored and GitHub committed 2026-11-06 09:10:10 -08:00
1 parent a8766f5177
commit 3a579ece3b
4 files changed
+105 -13
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

weed/s3api/s3api_object_versioning.go
+22 -8
View File
@@ -215,13 +215,33 @@ func (s3a *S3ApiServer) createDeleteMarker(bucket, object string) (string, error
bucketDir := s3a.bucketDir(bucket)
versionsDir := bucketDir + "/" + cleanObject + s3_constants.VersionsFolder
// Create the delete marker entry in the .versions directory
deleteMarkerMtime := time.Now().Unix()
deleteMarkerExtended := map[string][]byte{
s3_constants.ExtVersionIdKey: []byte(versionId),
s3_constants.ExtDeleteMarkerKey: []byte("true"),
}
// On the owner filer the marker and the pointer flip commit in one
// transaction; RECOMPUTE_LATEST picks the marker as the new latest.
if owner := s3a.objectWriteOwner(bucket, cleanObject); owner != "" {
deleteMarkerEntry := &filer_pb.Entry{
Name: versionFileName,
Attributes: &filer_pb.FuseAttributes{
Mtime: deleteMarkerMtime,
Crtime: deleteMarkerMtime,
FileMode: uint32(0770),
Uid: filer_pb.OS_UID,
Gid: filer_pb.OS_GID,
},
Extended: deleteMarkerExtended,
}
if code := s3a.routedVersionedFinalize(owner, bucket, cleanObject, useInvertedFormat, deleteMarkerEntry); code != s3err.ErrNone {
return "", fmt.Errorf("createDeleteMarker: routed finalize failed for %s/%s: code %d", bucket, object, code)
}
glog.V(2).Infof("createDeleteMarker: successfully created delete marker %s for %s/%s", versionId, bucket, object)
return versionId, nil
}
err := s3a.mkFile(versionsDir, versionFileName, nil, func(entry *filer_pb.Entry) {
entry.IsDirectory = false
if entry.Attributes == nil {
@@ -249,13 +269,7 @@ func (s3a *S3ApiServer) createDeleteMarker(bucket, object string) (string, error
},
Extended: deleteMarkerExtended,
}
// Route the pointer flip to the owner filer when known (off the distributed
// lock); RECOMPUTE_LATEST picks the just-written marker as the new latest.
if owner := s3a.objectWriteOwner(bucket, cleanObject); owner != "" {
if code := s3a.routedVersionedFinalize(owner, bucket, cleanObject, useInvertedFormat); code != s3err.ErrNone {
return "", fmt.Errorf("createDeleteMarker: routed finalize failed for %s/%s: code %d", bucket, object, code)
}
} else if err = s3a.updateLatestVersionInDirectory(bucket, cleanObject, versionId, versionFileName, deleteMarkerEntry); err != nil {
if err = s3a.updateLatestVersionInDirectory(bucket, cleanObject, versionId, versionFileName, deleteMarkerEntry); err != nil {
glog.Errorf("createDeleteMarker: failed to update latest version in directory: %v", err)
return "", fmt.Errorf("failed to update latest version in directory: %w", err)
}