seaweedfs/weed/mount/weedfs_file_sync.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

191 lines
5.2 KiB
Go

package mount
import (
"context"
"fmt"
"github.com/hanwen/go-fuse/v2/fuse"
"github.com/seaweedfs/seaweedfs/weed/filer"
"github.com/seaweedfs/seaweedfs/weed/glog"
"github.com/seaweedfs/seaweedfs/weed/pb/filer_pb"
"syscall"
"time"
)
/**
* Flush method
*
* This is called on each close() of the opened file.
*
* Since file descriptors can be duplicated (dup, dup2, fork), for
* one open call there may be many flush calls.
*
* Filesystems shouldn't assume that flush will always be called
* after some writes, or that if will be called at all.
*
* fi->fh will contain the value set by the open method, or will
* be undefined if the open method didn't set any value.
*
* NOTE: the name of the method is misleading, since (unlike
* fsync) the filesystem is not forced to flush pending writes.
* One reason to flush data is if the filesystem wants to return
* write errors during close. However, such use is non-portable
* because POSIX does not require [close] to wait for delayed I/O to
* complete.
*
* If the filesystem supports file locking operations (setlk,
* getlk) it should remove all locks belonging to 'fi->owner'.
*
* If this request is answered with an error code of ENOSYS,
* this is treated as success and future calls to flush() will
* succeed automatically without being send to the filesystem
* process.
*
* Valid replies:
* fuse_reply_err
*
* @param req request handle
* @param ino the inode number
* @param fi file information
*
* [close]: http://pubs.opengroup.org/onlinepubs/9699919799/functions/close.html
*/
func (wfs *WFS) Flush(cancel <-chan struct{}, in *fuse.FlushIn) fuse.Status {
fh := wfs.GetHandle(FileHandleId(in.Fh))
if fh == nil {
return fuse.ENOENT
}
return wfs.doFlush(fh, in.Uid, in.Gid)
}
/**
* Synchronize file contents
*
* If the datasync parameter is non-zero, then only the user data
* should be flushed, not the meta data.
*
* If this request is answered with an error code of ENOSYS,
* this is treated as success and future calls to fsync() will
* succeed automatically without being send to the filesystem
* process.
*
* Valid replies:
* fuse_reply_err
*
* @param req request handle
* @param ino the inode number
* @param datasync flag indicating if only data should be flushed
* @param fi file information
*/
func (wfs *WFS) Fsync(cancel <-chan struct{}, in *fuse.FsyncIn) (code fuse.Status) {
fh := wfs.GetHandle(FileHandleId(in.Fh))
if fh == nil {
return fuse.ENOENT
}
return wfs.doFlush(fh, in.Uid, in.Gid)
}
func (wfs *WFS) doFlush(fh *FileHandle, uid, gid uint32) fuse.Status {
fh.Lock()
defer fh.Unlock()
// flush works at fh level
fileFullPath := fh.FullPath()
dir, name := fileFullPath.DirAndName()
// send the data to the OS
glog.V(4).Infof("doFlush %s fh %d", fileFullPath, fh.handle)
if !wfs.IsOverQuota {
if err := fh.dirtyPages.FlushData(); err != nil {
glog.Errorf("%v doFlush: %v", fileFullPath, err)
return fuse.EIO
}
}
if !fh.dirtyMetadata {
return fuse.OK
}
if wfs.IsOverQuota {
return fuse.Status(syscall.ENOSPC)
}
err := wfs.WithFilerClient(false, func(client filer_pb.SeaweedFilerClient) error {
fh.entryLock.Lock()
defer fh.entryLock.Unlock()
entry := fh.GetEntry()
if entry == nil {
return nil
}
entry.Name = name // this flush may be just after a rename operation
if entry.Attributes != nil {
entry.Attributes.Mime = fh.contentType
if entry.Attributes.Uid == 0 {
entry.Attributes.Uid = uid
}
if entry.Attributes.Gid == 0 {
entry.Attributes.Gid = gid
}
if entry.Attributes.Crtime == 0 {
entry.Attributes.Crtime = time.Now().Unix()
}
entry.Attributes.Mtime = time.Now().Unix()
}
request := &filer_pb.CreateEntryRequest{
Directory: string(dir),
Entry: entry,
Signatures: []int32{wfs.signature},
SkipCheckParentDirectory: true,
}
glog.V(4).Infof("%s set chunks: %v", fileFullPath, len(entry.GetChunks()))
//for i, chunk := range entry.GetChunks() {
// glog.V(4).Infof("%s chunks %d: %v [%d,%d)", fileFullPath, i, chunk.GetFileIdString(), chunk.Offset, chunk.Offset+int64(chunk.Size))
//}
manifestChunks, nonManifestChunks := filer.SeparateManifestChunks(entry.GetChunks())
chunks, _ := filer.CompactFileChunks(wfs.LookupFn(), nonManifestChunks)
chunks, manifestErr := filer.MaybeManifestize(wfs.saveDataAsChunk(fileFullPath), chunks)
if manifestErr != nil {
// not good, but should be ok
glog.V(0).Infof("MaybeManifestize: %v", manifestErr)
}
entry.Chunks = append(chunks, manifestChunks...)
fh.entryChunkGroup.SetChunks(entry.Chunks)
wfs.mapPbIdFromLocalToFiler(request.Entry)
defer wfs.mapPbIdFromFilerToLocal(request.Entry)
if err := filer_pb.CreateEntry(client, request); err != nil {
glog.Errorf("fh flush create %s: %v", fileFullPath, err)
return fmt.Errorf("fh flush create %s: %v", fileFullPath, err)
}
wfs.metaCache.InsertEntry(context.Background(), filer.FromPbEntry(request.Directory, request.Entry))
return nil
})
if err == nil {
fh.dirtyMetadata = false
}
if err != nil {
glog.Errorf("%v fh %d flush: %v", fileFullPath, fh.handle, err)
return fuse.EIO
}
if IsDebugFileReadWrite {
fh.mirrorFile.Sync()
}
return fuse.OK
}