1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
|
package mount
import (
"context"
"fmt"
"sync"
"time"
"github.com/seaweedfs/seaweedfs/weed/filer"
"github.com/seaweedfs/seaweedfs/weed/glog"
"github.com/seaweedfs/seaweedfs/weed/pb/filer_pb"
"github.com/seaweedfs/seaweedfs/weed/util"
)
// loopFlushDirtyMetadata periodically flushes dirty file metadata to the filer.
// This protects newly uploaded chunks from being purged by volume.fsck orphan cleanup
// for files that remain open for extended periods without being closed.
//
// The problem: When a file is opened and written to continuously, chunks are uploaded
// to volume servers but the file metadata (containing chunk references) is only saved
// to the filer on file close or fsync. If volume.fsck runs during this window, it may
// identify these chunks as orphans (since they're not referenced in filer metadata)
// and purge them.
//
// This background task periodically flushes metadata for open files, ensuring chunk
// references are visible to volume.fsck even before files are closed.
func (wfs *WFS) loopFlushDirtyMetadata() {
if wfs.option.MetadataFlushSeconds <= 0 {
glog.V(0).Infof("periodic metadata flush disabled")
return
}
flushInterval := time.Duration(wfs.option.MetadataFlushSeconds) * time.Second
glog.V(0).Infof("periodic metadata flush enabled, interval: %v", flushInterval)
ticker := time.NewTicker(flushInterval)
defer ticker.Stop()
for range ticker.C {
wfs.flushAllDirtyMetadata()
}
}
// flushAllDirtyMetadata iterates through all open file handles and flushes
// metadata for files that have dirty metadata (chunks uploaded but not yet persisted).
func (wfs *WFS) flushAllDirtyMetadata() {
// Collect file handles with dirty metadata under a read lock
var dirtyHandles []*FileHandle
wfs.fhMap.RLock()
for _, fh := range wfs.fhMap.inode2fh {
if fh.dirtyMetadata {
dirtyHandles = append(dirtyHandles, fh)
}
}
wfs.fhMap.RUnlock()
if len(dirtyHandles) == 0 {
return
}
glog.V(3).Infof("flushing metadata for %d open files", len(dirtyHandles))
// Process dirty handles in parallel with limited concurrency
var wg sync.WaitGroup
concurrency := wfs.option.ConcurrentWriters
if concurrency <= 0 {
concurrency = 16
}
sem := make(chan struct{}, concurrency)
for _, fh := range dirtyHandles {
wg.Add(1)
sem <- struct{}{}
go func(handle *FileHandle) {
defer wg.Done()
defer func() { <-sem }()
if err := wfs.flushFileMetadata(handle); err != nil {
glog.Warningf("failed to flush metadata for %s: %v", handle.FullPath(), err)
}
}(fh)
}
wg.Wait()
}
// flushFileMetadata flushes the current file metadata to the filer without
// flushing dirty pages from memory. This updates chunk references in the filer
// so volume.fsck can see them, while keeping data in the write buffer.
func (wfs *WFS) flushFileMetadata(fh *FileHandle) error {
// Acquire exclusive lock on the file handle
fhActiveLock := fh.wfs.fhLockTable.AcquireLock("flushMetadata", fh.fh, util.ExclusiveLock)
defer fh.wfs.fhLockTable.ReleaseLock(fh.fh, fhActiveLock)
// Double-check dirty flag under lock
if !fh.dirtyMetadata {
return nil
}
fileFullPath := fh.FullPath()
dir, name := fileFullPath.DirAndName()
glog.V(4).Infof("flushFileMetadata %s fh %d", fileFullPath, fh.fh)
err := wfs.WithFilerClient(false, func(client filer_pb.SeaweedFilerClient) error {
entry := fh.GetEntry()
if entry == nil {
return nil
}
entry.Name = name
if entry.Attributes != nil {
entry.Attributes.Mtime = time.Now().Unix()
}
// Get current chunks - these include chunks that have been uploaded
// but not yet persisted to filer metadata
chunks := entry.GetChunks()
if len(chunks) == 0 {
return nil
}
// Separate manifest and non-manifest chunks
manifestChunks, nonManifestChunks := filer.SeparateManifestChunks(chunks)
// Compact chunks to remove fully overlapped ones
compactedChunks, _ := filer.CompactFileChunks(context.Background(), wfs.LookupFn(), nonManifestChunks)
// Try to create manifest chunks for large files
compactedChunks, manifestErr := filer.MaybeManifestize(wfs.saveDataAsChunk(fileFullPath), compactedChunks)
if manifestErr != nil {
glog.V(0).Infof("flushFileMetadata MaybeManifestize: %v", manifestErr)
}
entry.Chunks = append(compactedChunks, manifestChunks...)
request := &filer_pb.CreateEntryRequest{
Directory: string(dir),
Entry: entry.GetEntry(),
Signatures: []int32{wfs.signature},
SkipCheckParentDirectory: true,
}
wfs.mapPbIdFromLocalToFiler(request.Entry)
defer wfs.mapPbIdFromFilerToLocal(request.Entry)
if err := filer_pb.CreateEntry(context.Background(), client, request); err != nil {
return err
}
// Update meta cache
if err := wfs.metaCache.InsertEntry(context.Background(), filer.FromPbEntry(request.Directory, request.Entry)); err != nil {
return fmt.Errorf("update meta cache for %s: %w", fileFullPath, err)
}
glog.V(3).Infof("flushed metadata for %s with %d chunks", fileFullPath, len(entry.GetChunks()))
return nil
})
if err != nil {
return err
}
// Note: We do NOT clear dirtyMetadata here because:
// 1. There may still be dirty pages in the write buffer
// 2. The file may receive more writes before close
// 3. dirtyMetadata will be cleared on the final flush when the file is closed
return nil
}
|
