mirror of
https://github.com/seaweedfs/seaweedfs.git
synced 2026-09-18 04:20:53 +02:00
Chris Lu
d7865909ba
* feat(mount): proactive flush of idle writable chunks Add a background goroutine that periodically scans writable chunks across all open file handles and seals those that are idle and unlikely to receive further writes, submitting them for async upload. A writable chunk is proactively flushed when it has been idle for 500ms AND meets one of: nearly full (>=90%), behind the sequential write frontier by 2+ chunks, or stale for 5+ seconds. Flushing only happens when the upload pipeline has spare capacity (< half of concurrent writer slots in use). This prevents partial chunks from accumulating until fsync/close, which is particularly beneficial for bursty or small-file workloads where chunks may never reach IsComplete(). Also fixes a latent bug in ActivityScore where MarkRead/MarkWrite used value receivers, silently discarding all mutations. * refactor(mount): reuse WriterPattern instead of duplicating sequential detection Remove the isSequential atomic from UploadPipeline. The proactive flusher now reads IsSequentialMode() from the existing WriterPattern on PageWriter and passes it as a parameter to ProactiveFlush. This avoids duplicating the sequential/random detection that WriterPattern already maintains. * fix(mount): address PR review feedback - Make ActivityScore thread-safe using atomics (CAS loop for score updates, atomic load/swap for timestamp). Previously MarkRead was called under RLock while MarkWrite held a write lock, creating a data race on the shared fields. - Fix ProactiveFlush half-capacity guard: use multiplication (uploaderCount*2 >= max) instead of floor division (max/2) which misbehaves for odd or small concurrentWriterMax values. * fix(mount): review fixes for proactive flush - Fix TOCTOU race in lastWriteChunkIndex update: use CAS loop so concurrent writers cannot regress the frontier. - Remove unused UploaderCount() getter. - Reuse the caller-provided tsNs instead of calling time.Now() again in WriteDataAt for lastWriteTsNs, eliminating a redundant syscall per write.
104 lines
2.6 KiB
Go
104 lines
2.6 KiB
Go
package mount
|
|
|
|
import (
|
|
"github.com/seaweedfs/seaweedfs/weed/glog"
|
|
"github.com/seaweedfs/seaweedfs/weed/mount/page_writer"
|
|
)
|
|
|
|
type PageWriter struct {
|
|
fh *FileHandle
|
|
collection string
|
|
replication string
|
|
chunkSize int64
|
|
writerPattern *WriterPattern
|
|
|
|
randomWriter page_writer.DirtyPages
|
|
}
|
|
|
|
var (
|
|
_ = page_writer.DirtyPages(&PageWriter{})
|
|
)
|
|
|
|
func newPageWriter(fh *FileHandle, chunkSize int64) *PageWriter {
|
|
pw := &PageWriter{
|
|
fh: fh,
|
|
chunkSize: chunkSize,
|
|
writerPattern: NewWriterPattern(chunkSize),
|
|
randomWriter: newMemoryChunkPages(fh, chunkSize),
|
|
}
|
|
return pw
|
|
}
|
|
|
|
func (pw *PageWriter) AddPage(offset int64, data []byte, isSequential bool, tsNs int64) error {
|
|
|
|
glog.V(4).Infof("%v AddPage [%d, %d)", pw.fh.fh, offset, offset+int64(len(data)))
|
|
|
|
chunkIndex := offset / pw.chunkSize
|
|
for i := chunkIndex; len(data) > 0; i++ {
|
|
writeSize := min(int64(len(data)), (i+1)*pw.chunkSize-offset)
|
|
if err := pw.addToOneChunk(i, offset, data[:writeSize], isSequential, tsNs); err != nil {
|
|
return err
|
|
}
|
|
offset += writeSize
|
|
data = data[writeSize:]
|
|
}
|
|
return nil
|
|
}
|
|
|
|
func (pw *PageWriter) addToOneChunk(chunkIndex, offset int64, data []byte, isSequential bool, tsNs int64) error {
|
|
return pw.randomWriter.AddPage(offset, data, isSequential, tsNs)
|
|
}
|
|
|
|
func (pw *PageWriter) FlushData() error {
|
|
return pw.randomWriter.FlushData()
|
|
}
|
|
|
|
func (pw *PageWriter) ReadDirtyDataAt(data []byte, offset int64, tsNs int64) (maxStop int64) {
|
|
glog.V(4).Infof("ReadDirtyDataAt %v [%d, %d)", pw.fh.inode, offset, offset+int64(len(data)))
|
|
|
|
chunkIndex := offset / pw.chunkSize
|
|
for i := chunkIndex; len(data) > 0; i++ {
|
|
readSize := min(int64(len(data)), (i+1)*pw.chunkSize-offset)
|
|
|
|
maxStop = pw.randomWriter.ReadDirtyDataAt(data[:readSize], offset, tsNs)
|
|
|
|
offset += readSize
|
|
data = data[readSize:]
|
|
}
|
|
|
|
return
|
|
}
|
|
|
|
func (pw *PageWriter) LockForRead(startOffset, stopOffset int64) {
|
|
pw.randomWriter.LockForRead(startOffset, stopOffset)
|
|
}
|
|
|
|
func (pw *PageWriter) UnlockForRead(startOffset, stopOffset int64) {
|
|
pw.randomWriter.UnlockForRead(startOffset, stopOffset)
|
|
}
|
|
|
|
func (pw *PageWriter) Destroy() {
|
|
pw.randomWriter.Destroy()
|
|
}
|
|
|
|
func (pw *PageWriter) EvictOneWritableChunk() bool {
|
|
return pw.randomWriter.EvictOneWritableChunk()
|
|
}
|
|
|
|
func (pw *PageWriter) ProactiveFlush(nowNs, idleThresholdNs, maxHoldNs, fillRatio int64, frontierLag int, isSequential bool) bool {
|
|
return pw.randomWriter.ProactiveFlush(nowNs, idleThresholdNs, maxHoldNs, fillRatio, frontierLag, isSequential)
|
|
}
|
|
|
|
func max(x, y int64) int64 {
|
|
if x > y {
|
|
return x
|
|
}
|
|
return y
|
|
}
|
|
func min(x, y int64) int64 {
|
|
if x < y {
|
|
return x
|
|
}
|
|
return y
|
|
}
|