X-Git-Url: https://git.arvados.org/arvados.git/blobdiff_plain/a78762353971ea3707bcf92960a12557d66fb9af..7ebe828a435dcaa1b5668b72adbaad495059f211:/services/keepstore/unix_volume.go

diff --git a/services/keepstore/unix_volume.go b/services/keepstore/unix_volume.go
index f076ccf184..dd62cf1319 100644
--- a/services/keepstore/unix_volume.go
+++ b/services/keepstore/unix_volume.go
@@ -321,7 +321,12 @@ func (v *UnixVolume) Status() *VolumeStatus {
 		v.logger.WithError(err).Error("stat failed")
 		return nil
 	}
-	devnum := fi.Sys().(*syscall.Stat_t).Dev
+	// uint64() cast here supports GOOS=darwin where Dev is
+	// int32. If the device number is negative, the unsigned
+	// devnum won't be the real device number any more, but that's
+	// fine -- all we care about is getting the same number each
+	// time.
+	devnum := uint64(fi.Sys().(*syscall.Stat_t).Dev)
 
 	var fs syscall.Statfs_t
 	if err := syscall.Statfs(v.Root, &fs); err != nil {
@@ -359,47 +364,55 @@ var blockFileRe = regexp.MustCompile(`^[0-9a-f]{32}$`)
 //     e4de7a2810f5554cd39b36d8ddb132ff+67108864 1388701136
 //
 func (v *UnixVolume) IndexTo(prefix string, w io.Writer) error {
-	var lastErr error
 	rootdir, err := v.os.Open(v.Root)
 	if err != nil {
 		return err
 	}
-	defer rootdir.Close()
 	v.os.stats.TickOps("readdir")
 	v.os.stats.Tick(&v.os.stats.ReaddirOps)
-	for {
-		names, err := rootdir.Readdirnames(1)
-		if err == io.EOF {
-			return lastErr
-		} else if err != nil {
-			return err
-		}
-		if !strings.HasPrefix(names[0], prefix) && !strings.HasPrefix(prefix, names[0]) {
+	subdirs, err := rootdir.Readdirnames(-1)
+	rootdir.Close()
+	if err != nil {
+		return err
+	}
+	for _, subdir := range subdirs {
+		if !strings.HasPrefix(subdir, prefix) && !strings.HasPrefix(prefix, subdir) {
 			// prefix excludes all blocks stored in this dir
 			continue
 		}
-		if !blockDirRe.MatchString(names[0]) {
+		if !blockDirRe.MatchString(subdir) {
 			continue
 		}
-		blockdirpath := filepath.Join(v.Root, names[0])
-		blockdir, err := v.os.Open(blockdirpath)
-		if err != nil {
-			v.logger.WithError(err).Errorf("error reading %q", blockdirpath)
-			lastErr = fmt.Errorf("error reading %q: %s", blockdirpath, err)
-			continue
-		}
-		v.os.stats.TickOps("readdir")
-		v.os.stats.Tick(&v.os.stats.ReaddirOps)
-		for {
-			fileInfo, err := blockdir.Readdir(1)
-			if err == io.EOF {
+		blockdirpath := filepath.Join(v.Root, subdir)
+
+		var dirents []os.DirEntry
+		for attempt := 0; ; attempt++ {
+			v.os.stats.TickOps("readdir")
+			v.os.stats.Tick(&v.os.stats.ReaddirOps)
+			dirents, err = os.ReadDir(blockdirpath)
+			if err == nil {
 				break
+			} else if attempt < 5 && strings.Contains(err.Error(), "errno 523") {
+				// EBADCOOKIE (NFS stopped accepting
+				// our readdirent cookie) -- retry a
+				// few times before giving up
+				v.logger.WithError(err).Printf("retry after error reading %s", blockdirpath)
+				continue
+			} else {
+				return err
+			}
+		}
+
+		for _, dirent := range dirents {
+			fileInfo, err := dirent.Info()
+			if os.IsNotExist(err) {
+				// File disappeared between ReadDir() and now
+				continue
 			} else if err != nil {
-				v.logger.WithError(err).Errorf("error reading %q", blockdirpath)
-				lastErr = fmt.Errorf("error reading %q: %s", blockdirpath, err)
-				break
+				v.logger.WithError(err).Errorf("error getting FileInfo for %q in %q", dirent.Name(), blockdirpath)
+				return err
 			}
-			name := fileInfo[0].Name()
+			name := fileInfo.Name()
 			if !strings.HasPrefix(name, prefix) {
 				continue
 			}
@@ -408,16 +421,15 @@ func (v *UnixVolume) IndexTo(prefix string, w io.Writer) error {
 			}
 			_, err = fmt.Fprint(w,
 				name,
-				"+", fileInfo[0].Size(),
-				" ", fileInfo[0].ModTime().UnixNano(),
+				"+", fileInfo.Size(),
+				" ", fileInfo.ModTime().UnixNano(),
 				"\n")
 			if err != nil {
-				blockdir.Close()
 				return fmt.Errorf("error writing: %s", err)
 			}
 		}
-		blockdir.Close()
 	}
+	return nil
 }
 
 // Trash trashes the block data from the unix storage