Files
seaweedfs/weed/replication/replicator.go
T
Chris LuandDevin 8a2fec8610 filer.sync: skip superseded replays before fetching any chunks (#12212)
* filer.sync: skip superseded replays before fetching any chunks

On a directory under heavy overwrite, most entries the sync replays are
already superseded on the source. The sink only learned that after chunk
reads failed — or worse, after fetching and uploading bytes a later event
replaces — so the backlog drained slowly and the log filled with 404s.

CreateEntry and UpdateEntry now check sourceMovedOn before touching a
chunk: one entry lookup skips a stale replay entirely. A mid-replication
supersession is still caught by the existing retry gates.

Generated with [Devin](https://devin.ai)

Co-Authored-By: Devin <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* replication: bound the source liveness probes with a timeout

The supersession checks added a source entry lookup to the replication
path, and every lookup ran on context.Background() with no deadline. A
source that accepts the call but whose metadata store stalls would hold
the sync forever — before a single chunk fetch, even when every chunk is
still readable. Bound the probe at 30s; an unanswered lookup proves
nothing, so replication proceeds and the existing retry gates decide.

Generated with [Devin](https://devin.ai)

Co-Authored-By: Devin <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* replication: sync the live version a superseded replay points at

Skipping a stale replay assumed a later event always re-carries the
current content. It does not when the superseding write was itself
replicated in from another cluster: those events are dropped before they
reach a filer sink, so the destination could be left missing the file.
When the source reports a live entry newer than the replay, commit that
version through the normal path instead — equivalent to applying the
later event, with no dependence on its delivery. A gone source entry
still skips, since the destination already matches the source.

Generated with [Devin](https://devin.ai)

Co-Authored-By: Devin <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* replication: reconcile moved entry content after a native rename

AtomicRenameEntry relocates whatever version the destination held. If the
preceding update replay was skipped because the source had already moved
to the new name, the moved entry keeps the old bytes and — with no
further writes — stays stale forever. MoveEntry now runs the same
reconciliation as an in-place update against the rename's snapshot, so
the moved entry picks up pending content changes.

Generated with [Devin](https://devin.ai)

Co-Authored-By: Devin <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* replication: repair from the live snapshot a superseded replay resolves to

An incremental diff against the replayed oldEntry can resolve manifests the
overwrite already vacuumed, which fails every retry of the event.

---------

Co-authored-by: Devin <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-10-29 13:37:27 -07:00

188 lines
6.4 KiB
Go

package replication
import (
"context"
"fmt"
"time"
"github.com/seaweedfs/seaweedfs/weed/filer"
"github.com/seaweedfs/seaweedfs/weed/glog"
"github.com/seaweedfs/seaweedfs/weed/pb"
"github.com/seaweedfs/seaweedfs/weed/pb/filer_pb"
"github.com/seaweedfs/seaweedfs/weed/replication/repl_util"
"github.com/seaweedfs/seaweedfs/weed/replication/sink"
"github.com/seaweedfs/seaweedfs/weed/replication/source"
"github.com/seaweedfs/seaweedfs/weed/util"
"google.golang.org/grpc"
)
type Replicator struct {
sink sink.ReplicationSink
source *source.FilerSource
excludeDirs []string
}
func NewReplicator(sourceConfig util.Configuration, configPrefix string, dataSink sink.ReplicationSink) *Replicator {
source := &source.FilerSource{}
source.Initialize(sourceConfig, configPrefix)
if err := repl_util.InitializeSSEForReplication(source); err != nil {
glog.Warningf("SSE initialization failed: %v (encrypted objects may fail to replicate)", err)
}
dataSink.SetSourceFiler(source)
return &Replicator{
sink: dataSink,
source: source,
excludeDirs: sourceConfig.GetStringSlice(configPrefix + "excludeDirectories"),
}
}
func (r *Replicator) Replicate(ctx context.Context, key string, message *filer_pb.EventNotification) error {
if message.IsFromOtherCluster && r.sink.GetName() == "filer" {
return nil
}
oldEntry := message.OldEntry
newEntry := message.NewEntry
newParentPath := message.NewParentPath
oldInSource := util.IsEqualOrUnder(key, r.source.Dir) && !r.isExcluded(key)
// For rename events (both old and new entry present), check both paths
// against the source directory. Convert cross-boundary renames to
// create or delete so the sink stays consistent.
if oldEntry != nil && newEntry != nil {
newFullPath, targetParent := metadataEventTarget(key, newEntry, newParentPath)
newInSource := util.IsEqualOrUnder(newFullPath, r.source.Dir) && !r.isExcluded(newFullPath)
if !oldInSource && !newInSource {
return nil
}
if !oldInSource {
// Rename into watched directory: treat as create
oldEntry = nil
key = newFullPath
newParentPath = targetParent
} else if !newInSource {
// Rename out of watched directory: treat as delete
newEntry = nil
newParentPath = ""
}
} else if !oldInSource {
glog.V(4).Infof("skipping %v outside of %v", key, r.source.Dir)
return nil
}
var dateKey string
if r.sink.IsIncremental() {
var mTime int64
if newEntry != nil {
mTime = newEntry.Attributes.Mtime
} else if oldEntry != nil {
mTime = oldEntry.Attributes.Mtime
}
dateKey = time.Unix(mTime, 0).Format("2006-01-02")
}
oldSinkKey := r.sourceToSinkKey(key, dateKey)
glog.V(3).Infof("replicate %s => %s", key, oldSinkKey)
newSinkKey := oldSinkKey
newSinkParentPath := newParentPath
if oldEntry != nil && newEntry != nil {
targetSourceKey, targetSourceParent := metadataEventTarget(key, newEntry, newParentPath)
newSinkKey = r.sourceToSinkKey(targetSourceKey, dateKey)
newSinkParentPath = r.sourceToSinkPath(targetSourceParent, dateKey)
} else if newParentPath != "" && util.IsEqualOrUnder(newParentPath, r.source.Dir) {
newSinkParentPath = r.sourceToSinkPath(newParentPath, dateKey)
}
if oldEntry != nil && newEntry == nil {
glog.V(4).Infof("deleting %v", oldSinkKey)
return sink.DeleteEntry(r.sink, oldSinkKey, oldEntry.IsDirectory, message.DeleteChunks, filer.IsMetadataOnlyDelete(oldEntry), message.Signatures)
}
if oldEntry == nil && newEntry != nil {
glog.V(4).Infof("creating %v", oldSinkKey)
return r.sink.CreateEntry(oldSinkKey, newEntry, message.Signatures)
}
if oldEntry == nil && newEntry == nil {
glog.V(0).Infof("weird message %v: no old or new entry", key)
return nil
}
if oldSinkKey != newSinkKey {
// A real move: the path changed. UpdateEntry cannot move an entry.
if mover, ok := r.sink.(sink.EntryMover); ok {
glog.V(4).Infof("moving %v => %v", oldSinkKey, newSinkKey)
return mover.MoveEntry(oldSinkKey, newSinkKey, oldEntry, newEntry, message.Signatures)
}
// Sinks without a native move: create at the new key first, then delete the
// old, so a crash between the two leaves the entry visible under both names
// rather than gone.
glog.V(4).Infof("creating renamed %v", newSinkKey)
if err := r.sink.CreateEntry(newSinkKey, newEntry, message.Signatures); err != nil {
return fmt.Errorf("create renamed entry %v: %w", newSinkKey, err)
}
return r.sink.DeleteEntry(oldSinkKey, oldEntry.IsDirectory, false, message.Signatures)
}
// oldSinkKey == newSinkKey: pure in-place update (same path, content/attrs changed).
foundExisting, err := r.sink.UpdateEntry(oldSinkKey, oldEntry, newSinkParentPath, newEntry, message.DeleteChunks, message.Signatures)
if foundExisting {
glog.V(4).Infof("updated %v", oldSinkKey)
return err
}
err = r.sink.DeleteEntry(oldSinkKey, oldEntry.IsDirectory, false, message.Signatures)
if err != nil {
return fmt.Errorf("delete old entry %v: %w", oldSinkKey, err)
}
glog.V(4).Infof("creating missing %v", newSinkKey)
return r.sink.CreateEntry(newSinkKey, newEntry, message.Signatures)
}
func (r *Replicator) isExcluded(path string) bool {
for _, excludeDir := range r.excludeDirs {
if util.IsEqualOrUnder(path, excludeDir) {
return true
}
}
return false
}
func (r *Replicator) sourceToSinkKey(sourceKey, dateKey string) string {
return util.Join(r.sink.GetSinkToDirectory(), dateKey, sourceKey[len(r.source.Dir):])
}
func (r *Replicator) sourceToSinkPath(sourcePath, dateKey string) string {
return util.Join(r.sink.GetSinkToDirectory(), dateKey, sourcePath[len(r.source.Dir):])
}
func metadataEventTarget(key string, newEntry *filer_pb.Entry, newParentPath string) (targetKey, targetParent string) {
if newEntry == nil {
return "", ""
}
targetParent = newParentPath
if targetParent == "" {
targetParent, _ = util.FullPath(key).DirAndName()
}
return util.Join(targetParent, newEntry.Name), targetParent
}
func ReadFilerSignature(grpcDialOption grpc.DialOption, filer pb.ServerAddress) (filerSignature int32, readErr error) {
if readErr = pb.WithFilerClient(false, 0, filer, grpcDialOption, func(client filer_pb.SeaweedFilerClient) error {
if resp, err := client.GetFilerConfiguration(context.Background(), &filer_pb.GetFilerConfigurationRequest{}); err != nil {
return fmt.Errorf("GetFilerConfiguration %s: %v", filer, err)
} else {
filerSignature = resp.Signature
}
return nil
}); readErr != nil {
return 0, readErr
}
return filerSignature, nil
}