Files
seaweedfs/weed/storage/vid_stamp.go
T
Chris Lu 4feb30deff Federated volume-id bound via heartbeat stamps (#11763) (#11819)
* pb: heartbeat fields for the federated volume-id bound (#11763)

Heartbeat carries max_volume_id_seen and last_seen_topology_id up, and
HeartbeatResponse echoes max_volume_id and topology_id down, so the
allocation bound is replicated to every volume server.

* master: echo the volume-id bound and fold reported bounds in (#11763)

Every heartbeat response carries the leader current max volume id and
topology id; every heartbeat reported max_volume_id_seen is folded into
the topology bound via UpAdjustMaxVolumeId.

* volume: persist a per-dir vid stamp of the highest id ever seen (#11763)

The store keeps max_volume_id_seen + last_seen_topology_id in a
.vid_stamp file per volume dir, fed by heartbeat echoes, AllocateVolume,
and local volume/EC creation, seeded at boot from stamps and local
holdings, and reported in every heartbeat. A rebuilt master recovers
the bound from the first surviving veteran report.

* volume-rust: mirror the vid stamp and heartbeat echo handling (#11763)

Same mechanism as the Go volume server: .vid_stamp per dir, bound folded
in from add_location scans and allocate/mount calls, echoed fields
applied on heartbeat responses, reported on every heartbeat.

* volume: serialize vid stamp writes and fsync the directory (#11763)

* volume-rust: serialize vid stamp writes and fsync the directory (#11763)

* master: echo the allocation bound to connected servers on change

The bound was only sent at connect time or on digest mismatch, so a
healthy stream never learned later increases. If the high-id server then
went offline and the master lost state, survivors restored a stale bound
and the id could be reissued. Resend the heartbeat response whenever the
bound or topology id moved.

* volume: retry failed vid stamp saves on later updates

A transient write failure left the in-memory bound raised but the stamp
stale, and repeat updates at the same bound never retried. Track a dirty
flag so any later update re-attempts the save.

* volume: cover stamp bootstrap for pre-stamp dirs in test

* volume-rust: retry failed vid stamp saves, mirroring Go

* volume-rust: stamp every dir with the combined bound on add_location

A dir whose own stamp sat below the combined bound kept its stale value
after fold; losing the higher-stamped disk then restarted the server
below ids it had already learned. Rewrite all stamps after each location
folds in.

* volume: stamp mounted volume and ec shard ids (#11763)

* volume-rust: stamp mounted volume ids, mirroring Go (#11763)

* volume: retry dirty vid stamp save on unchanged topology id (#11763)

* volume-rust: retry dirty vid stamp save on unchanged topology id (#11763)

* master: record echoed bound from the sent heartbeat response (#11763)
2026-10-19 17:01:19 -07:00

149 lines
3.6 KiB
Go

package storage
import (
"encoding/json"
"os"
"path/filepath"
"github.com/seaweedfs/seaweedfs/weed/glog"
"github.com/seaweedfs/seaweedfs/weed/storage/needle"
"github.com/seaweedfs/seaweedfs/weed/util"
)
const vidStampFileName = ".vid_stamp"
type vidStamp struct {
MaxVolumeId uint32 `json:"maxVolumeId"`
TopologyId string `json:"topologyId,omitempty"`
}
func (s *Store) MaxVolumeIdSeen() needle.VolumeId {
return needle.VolumeId(s.maxVolumeIdSeen.Load())
}
func (s *Store) LastSeenTopologyId() string {
if v := s.lastSeenTopologyId.Load(); v != nil {
return v.(string)
}
return ""
}
// UpdateMaxVolumeIdSeen raises the server's persisted bound and stamps every
// volume dir when it grows. Feeds: heartbeat echoes, AllocateVolume, local
// volume and EC shard creation.
func (s *Store) UpdateMaxVolumeIdSeen(vid needle.VolumeId) {
grew := false
for {
current := s.maxVolumeIdSeen.Load()
if current >= uint32(vid) {
break
}
if s.maxVolumeIdSeen.CompareAndSwap(current, uint32(vid)) {
grew = true
break
}
}
if s.vidStampReady.Load() && (grew || s.vidStampDirty.Load()) {
s.saveVidStamps()
}
}
func (s *Store) UpdateLastSeenTopologyId(id string) {
if id == "" || (s.LastSeenTopologyId() == id && !s.vidStampDirty.Load()) {
return
}
s.lastSeenTopologyId.Store(id)
if s.vidStampReady.Load() {
s.saveVidStamps()
}
}
// bootstrapMaxVolumeIdSeen seeds the bound from persisted stamps plus the max
// of every volume and EC shard id on disk, so a server upgraded mid-incident
// still reports a bound covering its own holdings.
func (s *Store) bootstrapMaxVolumeIdSeen() {
var maxVid needle.VolumeId
for _, location := range s.Locations {
if stamp, err := readVidStamp(location.Directory); err == nil {
if needle.VolumeId(stamp.MaxVolumeId) > maxVid {
maxVid = needle.VolumeId(stamp.MaxVolumeId)
}
if stamp.TopologyId != "" && s.LastSeenTopologyId() == "" {
s.lastSeenTopologyId.Store(stamp.TopologyId)
}
}
location.volumesLock.RLock()
for vid := range location.volumes {
if vid > maxVid {
maxVid = vid
}
}
location.volumesLock.RUnlock()
location.ecVolumesLock.RLock()
for vid := range location.ecVolumes {
if vid > maxVid {
maxVid = vid
}
}
location.ecVolumesLock.RUnlock()
}
s.maxVolumeIdSeen.Store(uint32(maxVid))
s.vidStampReady.Store(true)
s.saveVidStamps()
}
func (s *Store) saveVidStamps() {
s.vidStampLock.Lock()
defer s.vidStampLock.Unlock()
stamp, err := json.Marshal(vidStamp{
MaxVolumeId: s.maxVolumeIdSeen.Load(),
TopologyId: s.LastSeenTopologyId(),
})
if err != nil {
return
}
failed := false
for _, location := range s.Locations {
if err := writeVidStamp(location.Directory, stamp); err != nil {
glog.Warningf("write vid stamp in %s: %v", location.Directory, err)
failed = true
}
}
s.vidStampDirty.Store(failed)
}
func readVidStamp(dir string) (*vidStamp, error) {
data, err := os.ReadFile(filepath.Join(dir, vidStampFileName))
if err != nil {
return nil, err
}
stamp := &vidStamp{}
if err := json.Unmarshal(data, stamp); err != nil {
return nil, err
}
return stamp, nil
}
func writeVidStamp(dir string, stamp []byte) error {
tmp := filepath.Join(dir, vidStampFileName+".tmp")
f, err := os.OpenFile(tmp, os.O_WRONLY|os.O_CREATE|os.O_TRUNC, 0644)
if err != nil {
return err
}
if _, err := f.Write(stamp); err != nil {
f.Close()
return err
}
if err := f.Sync(); err != nil {
f.Close()
return err
}
if err := f.Close(); err != nil {
return err
}
if err := os.Rename(tmp, filepath.Join(dir, vidStampFileName)); err != nil {
return err
}
return util.FsyncDir(dir)
}