gsh-digital-services/seaweedFS
5
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix reading

Browse Source 
Gap detection and skipping to earliest memory time
Time-based reads that include events at boundary times for first reads (offset ≤ 0)
Aggregated subscriber wake-up via ListenersWaits signaling
This commit is contained in:
chrislu
2025-10-24 00:48:24 -07:00
parent 832df5265f
commit 64a4ce9358
6 changed files with 182 additions and 58 deletions
Download Patch File Download Diff File Expand all files Collapse all files

78
weed/server/filer_grpc_server_sub_meta.go
View File

@@ -69,14 +69,30 @@ func (fs *FilerServer) SubscribeMetadata(req *filer_pb.SubscribeMetadataRequest,
if processedTsNs != 0 {
lastReadTime = log_buffer.NewMessagePosition(processedTsNs, -2)
} else {
nextDayTs := util.GetNextDayTsNano(lastReadTime.Time.UnixNano())
position := log_buffer.NewMessagePosition(nextDayTs, -2)
found, err := fs.filer.HasPersistedLogFiles(position)
if err != nil {
return fmt.Errorf("checking persisted log files: %w", err)
}
if found {
lastReadTime = position
// No data found on disk
// Check if we previously got ResumeFromDiskError from memory, meaning we're in a gap
if errors.Is(readInMemoryLogErr, log_buffer.ResumeFromDiskError) {
// We have a gap: requested time < earliest memory time, but no data on disk
// Skip forward to earliest memory time to avoid infinite loop
earliestTime := fs.filer.MetaAggregator.MetaLogBuffer.GetEarliestTime()
if !earliestTime.IsZero() && earliestTime.After(lastReadTime.Time) {
glog.V(3).Infof("gap detected: skipping from %v to earliest memory time %v for %v",
lastReadTime.Time, earliestTime, clientName)
// Position at earliest time; time-based reader will include it
lastReadTime = log_buffer.NewMessagePosition(earliestTime.UnixNano(), -2)
readInMemoryLogErr = nil // Clear the error since we're skipping forward
}
} else {
// First pass or no ResumeFromDiskError yet - check the next day for logs
nextDayTs := util.GetNextDayTsNano(lastReadTime.Time.UnixNano())
position := log_buffer.NewMessagePosition(nextDayTs, -2)
found, err := fs.filer.HasPersistedLogFiles(position)
if err != nil {
return fmt.Errorf("checking persisted log files: %w", err)
}
if found {
lastReadTime = position
}
}
}
@@ -91,12 +107,16 @@ func (fs *FilerServer) SubscribeMetadata(req *filer_pb.SubscribeMetadataRequest,
}
fs.filer.MetaAggregator.ListenersLock.Lock()
atomic.AddInt64(&fs.filer.MetaAggregator.ListenersWaits, 1)
fs.filer.MetaAggregator.ListenersCond.Wait()
atomic.AddInt64(&fs.filer.MetaAggregator.ListenersWaits, -1)
fs.filer.MetaAggregator.ListenersLock.Unlock()
return fs.hasClient(req.ClientId, req.ClientEpoch)
}, eachLogEntryFn)
if readInMemoryLogErr != nil {
if errors.Is(readInMemoryLogErr, log_buffer.ResumeFromDiskError) {
// Memory says data is too old - will read from disk on next iteration
// But if disk also has no data (gap in history), we'll skip forward
continue
}
glog.Errorf("processed to %v: %v", lastReadTime, readInMemoryLogErr)
@@ -166,23 +186,39 @@ func (fs *FilerServer) SubscribeLocalMetadata(req *filer_pb.SubscribeMetadataReq
if processedTsNs != 0 {
lastReadTime = log_buffer.NewMessagePosition(processedTsNs, -2)
} else {
// No data found on disk
// Check if we previously got ResumeFromDiskError from memory, meaning we're in a gap
if readInMemoryLogErr == log_buffer.ResumeFromDiskError {
time.Sleep(1127 * time.Millisecond)
continue
}
// If no persisted entries were read for this day, check the next day for logs
nextDayTs := util.GetNextDayTsNano(lastReadTime.Time.UnixNano())
position := log_buffer.NewMessagePosition(nextDayTs, -2)
found, err := fs.filer.HasPersistedLogFiles(position)
if err != nil {
return fmt.Errorf("checking persisted log files: %w", err)
}
if found {
lastReadTime = position
// We have a gap: requested time < earliest memory time, but no data on disk
// Skip forward to earliest memory time to avoid infinite loop
earliestTime := fs.filer.LocalMetaLogBuffer.GetEarliestTime()
if !earliestTime.IsZero() && earliestTime.After(lastReadTime.Time) {
glog.V(3).Infof("gap detected: skipping from %v to earliest memory time %v for %v",
lastReadTime.Time, earliestTime, clientName)
// Position at earliest time; time-based reader will include it
lastReadTime = log_buffer.NewMessagePosition(earliestTime.UnixNano(), -2)
readInMemoryLogErr = nil // Clear the error since we're skipping forward
} else {
// No memory data yet, just wait
time.Sleep(1127 * time.Millisecond)
continue
}
} else {
// First pass or no ResumeFromDiskError yet
// Check the next day for logs
nextDayTs := util.GetNextDayTsNano(lastReadTime.Time.UnixNano())
position := log_buffer.NewMessagePosition(nextDayTs, -2)
found, err := fs.filer.HasPersistedLogFiles(position)
if err != nil {
return fmt.Errorf("checking persisted log files: %w", err)
}
if found {
lastReadTime = position
}
}
}
glog.V(0).Infof("read in memory %v local subscribe %s from %+v", clientName, req.PathPrefix, lastReadTime)
glog.V(3).Infof("read in memory %v local subscribe %s from %+v", clientName, req.PathPrefix, lastReadTime)
lastReadTime, isDone, readInMemoryLogErr = fs.filer.LocalMetaLogBuffer.LoopProcessLogData("localMeta:"+clientName, lastReadTime, req.UntilNs, func() bool {