1
0
Fork 0
mirror of https://github.com/chrislusf/seaweedfs synced 2024-05-21 19:01:26 +02:00
seaweedfs/weed/mount/dirty_pages_chunked.go
Chris Lu d4566d4aaa
more solid weed mount (#4089)
* compare chunks by timestamp

* fix slab clearing error

* fix test compilation

* move oldest chunk to sealed, instead of by fullness

* lock on fh.entryViewCache

* remove verbose logs

* revert slat clearing

* less logs

* less logs

* track write and read by timestamp

* remove useless logic

* add entry lock on file handle release

* use mem chunk only, swap file chunk has problems

* comment out code that maybe used later

* add debug mode to compare data read and write

* more efficient readResolvedChunks with linked list

* small optimization

* fix test compilation

* minor fix on writer

* add SeparateGarbageChunks

* group chunks into sections

* turn off debug mode

* fix tests

* fix tests

* tmp enable swap file chunk

* Revert "tmp enable swap file chunk"

This reverts commit 985137ec47.

* simple refactoring

* simple refactoring

* do not re-use swap file chunk. Sealed chunks should not be re-used.

* comment out debugging facilities

* either mem chunk or swap file chunk is fine now

* remove orderedMutex  as *semaphore.Weighted

not found impactful

* optimize size calculation for changing large files

* optimize performance to avoid going through the long list of chunks

* still problems with swap file chunk

* rename

* tiny optimization

* swap file chunk save only successfully read data

* fix

* enable both mem and swap file chunk

* resolve chunks with range

* rename

* fix chunk interval list

* also change file handle chunk group when adding chunks

* pick in-active chunk with time-decayed counter

* fix compilation

* avoid nil with empty fh.entry

* refactoring

* rename

* rename

* refactor visible intervals to *list.List

* refactor chunkViews to *list.List

* add IntervalList for generic interval list

* change visible interval to use IntervalList in generics

* cahnge chunkViews to *IntervalList[*ChunkView]

* use NewFileChunkSection to create

* rename variables

* refactor

* fix renaming leftover

* renaming

* renaming

* add insert interval

* interval list adds lock

* incrementally add chunks to readers

Fixes:
1. set start and stop offset for the value object
2. clone the value object
3. use pointer instead of copy-by-value when passing to interval.Value
4. use insert interval since adding chunk could be out of order

* fix tests compilation

* fix tests compilation
2023-01-02 23:20:45 -08:00

95 lines
2.6 KiB
Go

package mount
import (
"fmt"
"github.com/seaweedfs/seaweedfs/weed/glog"
"github.com/seaweedfs/seaweedfs/weed/mount/page_writer"
"github.com/seaweedfs/seaweedfs/weed/pb/filer_pb"
"io"
"sync"
)
type ChunkedDirtyPages struct {
fh *FileHandle
writeWaitGroup sync.WaitGroup
lastErr error
collection string
replication string
uploadPipeline *page_writer.UploadPipeline
hasWrites bool
}
var (
_ = page_writer.DirtyPages(&ChunkedDirtyPages{})
)
func newMemoryChunkPages(fh *FileHandle, chunkSize int64) *ChunkedDirtyPages {
dirtyPages := &ChunkedDirtyPages{
fh: fh,
}
swapFileDir := fh.wfs.option.getTempFilePageDir()
dirtyPages.uploadPipeline = page_writer.NewUploadPipeline(fh.wfs.concurrentWriters, chunkSize,
dirtyPages.saveChunkedFileIntervalToStorage, fh.wfs.option.ConcurrentWriters, swapFileDir)
return dirtyPages
}
func (pages *ChunkedDirtyPages) AddPage(offset int64, data []byte, isSequential bool, tsNs int64) {
pages.hasWrites = true
glog.V(4).Infof("%v memory AddPage [%d, %d)", pages.fh.fh, offset, offset+int64(len(data)))
pages.uploadPipeline.SaveDataAt(data, offset, isSequential, tsNs)
return
}
func (pages *ChunkedDirtyPages) FlushData() error {
if !pages.hasWrites {
return nil
}
pages.uploadPipeline.FlushAll()
if pages.lastErr != nil {
return fmt.Errorf("flush data: %v", pages.lastErr)
}
return nil
}
func (pages *ChunkedDirtyPages) ReadDirtyDataAt(data []byte, startOffset int64, tsNs int64) (maxStop int64) {
if !pages.hasWrites {
return
}
return pages.uploadPipeline.MaybeReadDataAt(data, startOffset, tsNs)
}
func (pages *ChunkedDirtyPages) saveChunkedFileIntervalToStorage(reader io.Reader, offset int64, size int64, modifiedTsNs int64, cleanupFn func()) {
defer cleanupFn()
fileFullPath := pages.fh.FullPath()
fileName := fileFullPath.Name()
chunk, err := pages.fh.wfs.saveDataAsChunk(fileFullPath)(reader, fileName, offset, modifiedTsNs)
if err != nil {
glog.V(0).Infof("%v saveToStorage [%d,%d): %v", fileFullPath, offset, offset+size, err)
pages.lastErr = err
return
}
pages.fh.AddChunks([]*filer_pb.FileChunk{chunk})
pages.fh.entryChunkGroup.AddChunk(chunk)
glog.V(3).Infof("%v saveToStorage %s [%d,%d)", fileFullPath, chunk.FileId, offset, offset+size)
}
func (pages ChunkedDirtyPages) Destroy() {
pages.uploadPipeline.Shutdown()
}
func (pages *ChunkedDirtyPages) LockForRead(startOffset, stopOffset int64) {
pages.uploadPipeline.LockForRead(startOffset, stopOffset)
}
func (pages *ChunkedDirtyPages) UnlockForRead(startOffset, stopOffset int64) {
pages.uploadPipeline.UnlockForRead(startOffset, stopOffset)
}