Files
seaweedFS/weed/mount/weedfs_dir_mkrm.go
Chris Lu 6442da6f17 mount: efficient file lookup in large directories, skipping directory caching (#7818)
* mount: skip directory caching on file lookup and write

When opening or creating a file in a directory that hasn't been cached yet,
don't list the entire directory. Instead:
- For reads: fetch only the single file's metadata directly from the filer
- For writes: create on filer but skip local cache insertion

This fixes a performance issue where opening a file in a directory
with millions of files would hang because EnsureVisited() had to
list all entries before the open could complete.

The directory will still be cached when explicitly listed (ReadDir),
but individual file operations now bypass the full directory caching.

Key optimizations:
- Extract shared lookupEntry() method to eliminate code duplication
- Skip EnsureVisited on Lookup (file open)
- Skip cache insertion on Mknod, Mkdir, Symlink, Link if dir not cached
- Skip cache update on file sync/flush if dir not cached
- If directory IS cached and entry not found, return ENOENT immediately

Fixes #7145

* mount: add error handling for meta cache insert/update operations

Handle errors from metaCache.InsertEntry and metaCache.UpdateEntry calls
instead of silently ignoring them. This prevents silent cache inconsistencies
and ensures errors are properly propagated.

Files updated:
- filehandle_read.go: handle InsertEntry error in downloadRemoteEntry
- weedfs_file_sync.go: handle InsertEntry error in doFlush
- weedfs_link.go: handle UpdateEntry and InsertEntry errors in Link
- weedfs_symlink.go: handle InsertEntry error in Symlink

* mount: use error wrapping (%w) for consistent error handling

Use %w instead of %v in fmt.Errorf to preserve the original error,
allowing it to be inspected up the call stack with errors.Is/As.
2025-12-18 21:19:15 -08:00

129 lines
3.3 KiB
Go

package mount
import (
"context"
"fmt"
"os"
"strings"
"syscall"
"time"
"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"
)
/** Create a directory
*
* Note that the mode argument may not have the type specification
* bits set, i.e. S_ISDIR(mode) can be false. To obtain the
* correct directory type bits use mode|S_IFDIR
* */
func (wfs *WFS) Mkdir(cancel <-chan struct{}, in *fuse.MkdirIn, name string, out *fuse.EntryOut) (code fuse.Status) {
if wfs.IsOverQuotaWithUncommitted() {
return fuse.Status(syscall.ENOSPC)
}
if s := checkName(name); s != fuse.OK {
return s
}
newEntry := &filer_pb.Entry{
Name: name,
IsDirectory: true,
Attributes: &filer_pb.FuseAttributes{
Mtime: time.Now().Unix(),
Crtime: time.Now().Unix(),
FileMode: uint32(os.ModeDir) | in.Mode&^uint32(wfs.option.Umask),
Uid: in.Uid,
Gid: in.Gid,
},
}
dirFullPath, code := wfs.inodeToPath.GetPath(in.NodeId)
if code != fuse.OK {
return
}
entryFullPath := dirFullPath.Child(name)
err := wfs.WithFilerClient(false, func(client filer_pb.SeaweedFilerClient) error {
wfs.mapPbIdFromLocalToFiler(newEntry)
defer wfs.mapPbIdFromFilerToLocal(newEntry)
request := &filer_pb.CreateEntryRequest{
Directory: string(dirFullPath),
Entry: newEntry,
Signatures: []int32{wfs.signature},
SkipCheckParentDirectory: true,
}
glog.V(1).Infof("mkdir: %v", request)
if err := filer_pb.CreateEntry(context.Background(), client, request); err != nil {
glog.V(0).Infof("mkdir %s: %v", entryFullPath, err)
return err
}
// Only cache the entry if the parent directory is already cached.
// This avoids polluting the cache with partial directory data.
if wfs.metaCache.IsDirectoryCached(dirFullPath) {
if err := wfs.metaCache.InsertEntry(context.Background(), filer.FromPbEntry(request.Directory, request.Entry)); err != nil {
return fmt.Errorf("local mkdir dir %s: %w", entryFullPath, err)
}
}
return nil
})
glog.V(3).Infof("mkdir %s: %v", entryFullPath, err)
if err != nil {
return fuse.EIO
}
inode := wfs.inodeToPath.Lookup(entryFullPath, newEntry.Attributes.Crtime, true, false, 0, true)
wfs.outputPbEntry(out, inode, newEntry)
return fuse.OK
}
/** Remove a directory */
func (wfs *WFS) Rmdir(cancel <-chan struct{}, header *fuse.InHeader, name string) (code fuse.Status) {
if name == "." {
return fuse.Status(syscall.EINVAL)
}
if name == ".." {
return fuse.Status(syscall.ENOTEMPTY)
}
dirFullPath, code := wfs.inodeToPath.GetPath(header.NodeId)
if code != fuse.OK {
return
}
entryFullPath := dirFullPath.Child(name)
glog.V(3).Infof("remove directory: %v", entryFullPath)
ignoreRecursiveErr := true // ignore recursion error since the OS should manage it
err := filer_pb.Remove(context.Background(), wfs, string(dirFullPath), name, true, false, ignoreRecursiveErr, false, []int32{wfs.signature})
if err != nil {
glog.V(0).Infof("remove %s: %v", entryFullPath, err)
if strings.Contains(err.Error(), filer.MsgFailDelNonEmptyFolder) {
return fuse.Status(syscall.ENOTEMPTY)
}
return fuse.ENOENT
}
wfs.metaCache.DeleteEntry(context.Background(), entryFullPath)
wfs.inodeToPath.RemovePath(entryFullPath)
return fuse.OK
}