Compare commits

..
1 Commits
Author SHA1 Message Date
sneak 5ce257cef4 Make remote nuke delete leftover .partial uploads (closes #281)
check / check (push) Waiting to run
Every listing skips an object whose name ends in `.partial`, the
temporary name a `file://` or rclone upload writes before moving the
object into place. `remote nuke` deletes only what the listings return,
so it left the `.partial` objects killed uploads leave behind and still
reported the destination store empty.

Storer gains DeletePartialUploads. The file and rclone backends remove
every `.partial` object under the prefix; S3 has none to remove, since
it shows an object only once its upload completes. `remote nuke` calls
it for `metadata/` and `blobs/` as its last step.

Empty directories under a `file://` destination are still left behind.

Model: opus-5-5
2026-10-08 07:20:54 +00:00
8 changed files with 14 additions and 172 deletions
+4 -13
View File
@@ -24,19 +24,10 @@ the tag exists and is exercised; what is left is merging `next` to
- 2026-10-08: Made `remote nuke` delete the `.partial` files that
uploads cut off part-way leave on the destination store
([issue #281](https://git.eeqj.de/sneak/vaultik/issues/281)). The
file and rclone listings skip such a file, so the command left it in
place and still reported the store empty. It now removes them under
`metadata/` and `blobs/` as its last step.
- 2026-10-08: Counted a file that a backup could not store as failed
([issue #280](https://git.eeqj.de/sneak/vaultik/issues/280)). A file
that phase 1 counted and phase 2 could not open, because it was
unreadable under `--skip-errors` or removed in between, was reported
in the summary as unchanged with its bytes as backed up, and the
`snapshots` row's `file_count` and `total_size` included it. The
summary now counts it as failed, and its data total and the row leave
it out.
([issue #281](https://git.eeqj.de/sneak/vaultik/issues/281)). Every
listing skips such a file, so the command left it in place and still
reported the store empty. It now removes them under `metadata/` and
`blobs/` as its last step.
- 2026-10-08: Made `remote info` report a snapshot's blob count and
blob size as unknown when its manifest cannot be read
+3 -18
View File
@@ -133,13 +133,10 @@ type ScannerConfig struct {
// ScanResult contains the results of a scan operation. Files and bytes
// are counted per file: BytesScanned is the size of the new and changed
// files, BytesSkipped that of the unchanged ones. FilesFailed counts the
// new and changed files that phase 2 could not store; FilesScanned
// includes them and BytesScanned does not.
// files, BytesSkipped that of the unchanged ones.
type ScanResult struct {
FilesScanned int
FilesSkipped int
FilesFailed int
FilesDeleted int
BytesScanned int64
BytesSkipped int64
@@ -1368,7 +1365,7 @@ func (s *Scanner) processFileWithErrorHandling(
log.Warn("File was deleted during backup, skipping",
"path", fileToProcess.Path)
countFailedFile(fileToProcess, result)
result.FilesSkipped++
return true, nil
}
@@ -1379,7 +1376,7 @@ func (s *Scanner) processFileWithErrorHandling(
s.ui.Errorf("Failed to process %s: %v. Skipping (--skip-errors).",
s.ui.Path(fileToProcess.Path), err)
countFailedFile(fileToProcess, result)
result.FilesSkipped++
return true, nil
}
@@ -1390,18 +1387,6 @@ func (s *Scanner) processFileWithErrorHandling(
return false, nil
}
// countFailedFile counts a file that phase 2 could not store as failed
// and takes its size back out of BytesScanned, where phase 1 put it.
// Phase 1 counts no directories, so a directory is not counted here.
func countFailedFile(fileToProcess *FileToProcess, result *ScanResult) {
if fileToProcess.FileInfo.IsDir() {
return
}
result.FilesFailed++
result.BytesScanned -= fileToProcess.FileInfo.Size()
}
// printProcessingProgress prints a periodic progress line during the process phase,
// showing files processed, bytes transferred, throughput, and ETA
func (s *Scanner) printProcessingProgress(
+1 -1
View File
@@ -892,7 +892,7 @@ func (sm *SnapshotManager) getFileSize(path string) int64 {
// BackupStats contains statistics from a backup operation
type BackupStats struct {
FilesScanned int
TotalSize int64 // Total size of the files in the snapshot
TotalSize int64 // Total size of all files examined
ChunksCreated int
BlobsCreated int
BytesUploaded int64
+1 -1
View File
@@ -272,7 +272,7 @@ func (f *FileStorer) DeletePartialUploads(ctx context.Context, prefix string) er
return f.fs.Remove(path)
})
if err != nil {
return fmt.Errorf("walking directory: %w", err)
return fmt.Errorf("deleting partial uploads: %w", err)
}
return nil
+1 -2
View File
@@ -73,8 +73,7 @@ type Storer interface {
// DeletePartialUploads removes every object under prefix that an
// upload cut off part-way left under a temporary name ending in
// `.partial`. The file and rclone backends' List and ListStream skip
// such an object.
// `.partial`. List and ListStream never return such an object.
DeletePartialUploads(ctx context.Context, prefix string) error
// Info returns human-readable storage location information.
+2 -2
View File
@@ -49,8 +49,8 @@ func (v *Vaultik) NukeRemote(force bool) error {
return fmt.Errorf("pruning blobs: %w", err)
}
// The file and rclone listings skip `.partial` objects, so the two
// steps above never delete them.
// Listings skip `.partial` objects, so the two steps above never
// delete them.
for _, prefix := range []string{"metadata/", "blobs/"} {
err = v.Storage.DeletePartialUploads(v.ctx, prefix)
if err != nil {
+2 -12
View File
@@ -185,7 +185,6 @@ type snapshotStats struct {
totalBlobs int
totalBytesSkipped int64
totalFilesSkipped int
totalFilesFailed int
totalFilesDeleted int
totalBytesDeleted int64
totalBytesUploaded int64
@@ -316,7 +315,6 @@ func (v *Vaultik) scanAllDirectories(
stats.totalChunks += result.ChunksCreated
stats.totalBlobs += result.BlobsCreated
stats.totalFilesSkipped += result.FilesSkipped
stats.totalFilesFailed += result.FilesFailed
stats.totalBytesSkipped += result.BytesSkipped
stats.totalFilesDeleted += result.FilesDeleted
stats.totalBytesDeleted += result.BytesDeleted
@@ -328,7 +326,6 @@ func (v *Vaultik) scanAllDirectories(
"path", dir,
"files", result.FilesScanned,
"files_skipped", result.FilesSkipped,
"files_failed", result.FilesFailed,
"bytes", result.BytesScanned,
"bytes_skipped", result.BytesSkipped,
"chunks", result.ChunksCreated,
@@ -362,11 +359,9 @@ func (v *Vaultik) finalizeSnapshotMetadata(
return fmt.Errorf("getting snapshot blob sizes: %w", err)
}
// file_count and total_size leave out the files that could not be
// stored; stats.totalBytes already does.
extStats := snapshot.ExtendedBackupStats{
BackupStats: snapshot.BackupStats{
FilesScanned: stats.totalFiles - stats.totalFilesFailed,
FilesScanned: stats.totalFiles,
TotalSize: stats.totalBytes + stats.totalBytesSkipped,
ChunksCreated: stats.totalChunks,
BlobsCreated: stats.totalBlobs,
@@ -414,8 +409,7 @@ func (v *Vaultik) printSnapshotSummary(
snapshotID string, startTime time.Time, stats *snapshotStats,
) {
snapshotDuration := time.Since(startTime)
totalFilesChanged := stats.totalFiles - stats.totalFilesSkipped -
stats.totalFilesFailed
totalFilesChanged := stats.totalFiles - stats.totalFilesSkipped
totalBytesAll := stats.totalBytes + stats.totalBytesSkipped
var compressionRatio float64
@@ -432,10 +426,6 @@ func (v *Vaultik) printSnapshotSummary(
v.UI.Count(stats.totalFiles),
v.UI.Count(totalFilesChanged),
v.UI.Count(stats.totalFilesSkipped))
if stats.totalFilesFailed > 0 {
filesMsg += fmt.Sprintf(", %s failed", v.UI.Count(stats.totalFilesFailed))
}
if stats.totalFilesDeleted > 0 {
filesMsg += fmt.Sprintf(", %s deleted", v.UI.Count(stats.totalFilesDeleted))
}
@@ -1,123 +0,0 @@
package vaultik_test
import (
"bytes"
"context"
"fmt"
"os"
"path/filepath"
"testing"
"github.com/spf13/afero"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
"sneak.berlin/go/vaultik/internal/config"
"sneak.berlin/go/vaultik/internal/database"
"sneak.berlin/go/vaultik/internal/log"
"sneak.berlin/go/vaultik/internal/storage"
"sneak.berlin/go/vaultik/internal/ui"
"sneak.berlin/go/vaultik/internal/vaultik"
)
// openFailFs is the real filesystem, except that opening path fails
// with err. Phase 1 of a backup only lstats a file, so it still counts
// path; phase 2 is the first to open it.
type openFailFs struct {
afero.OsFs
path string
err error
}
//nolint:ireturn // afero.Fs.Open is defined to return the interface.
func (f *openFailFs) Open(name string) (afero.File, error) {
if name == f.path {
return nil, &os.PathError{Op: "open", Path: name, Err: f.err}
}
return f.OsFs.Open(name)
}
// A file that phase 2 cannot open is reported as failed, not as
// unchanged, and neither the summary's data total nor the snapshots row
// counts it. See https://git.eeqj.de/sneak/vaultik/issues/280.
func TestSnapshotSummaryCountsFileNotStoredAsFailed(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
tests := []struct {
name string
openErr error
skipErrors bool
}{
// What a normal user gets opening a file with mode 000.
{name: "unopenable under skip-errors",
openErr: os.ErrPermission, skipErrors: true},
// What opening a file removed after phase 1 gives.
{name: "removed between the phases",
openErr: os.ErrNotExist, skipErrors: false},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
t.Parallel()
ctx := context.Background()
// The scan walks the source path with symlinks resolved, so
// failedPath must be spelled the same way to match.
tempDir, err := filepath.EvalSymlinks(t.TempDir())
require.NoError(t, err)
srcDir := filepath.Join(tempDir, "src")
failedPath := filepath.Join(srcDir, "failed.txt")
storedContent := []byte("this file is backed up")
storedSize := int64(len(storedContent))
fs := &openFailFs{path: failedPath, err: tt.openErr}
require.NoError(t, fs.MkdirAll(srcDir, 0o755))
require.NoError(t, afero.WriteFile(fs,
filepath.Join(srcDir, "stored.txt"), storedContent, 0o644))
require.NoError(t, afero.WriteFile(fs,
failedPath, []byte("this file cannot be opened"), 0o644))
cfg := faultTestConfig()
cfg.IndexPath = filepath.Join(tempDir, "index.sqlite")
cfg.Snapshots = map[string]config.SnapshotConfig{
"src": {Paths: []string{srcDir}},
}
store, err := storage.NewFileStorer(filepath.Join(tempDir, "remote"))
require.NoError(t, err)
db, err := database.New(ctx, cfg.IndexPath)
require.NoError(t, err)
t.Cleanup(func() { _ = db.Close() })
repos := database.NewRepositories(db)
out := &bytes.Buffer{}
v := newBackupVaultik(ctx, cfg, store, repos, db, fs)
v.UI = ui.NewWithColor(out, false)
require.NoError(t, v.CreateSnapshot(&vaultik.SnapshotCreateOptions{
SkipErrors: tt.skipErrors,
Snapshots: []string{"src"},
}))
summary := out.String()
assert.Contains(t, summary,
"Files: 2 examined, 1 backed up, 0 unchanged, 1 failed.")
assert.Contains(t, summary,
fmt.Sprintf("Data: %s total (%s backed up).",
v.UI.Size(storedSize), v.UI.Size(storedSize)))
snap, err := repos.Snapshots.GetByID(ctx,
localSnapshotID(ctx, t, repos, "src"))
require.NoError(t, err)
require.NotNil(t, snap)
assert.Equal(t, int64(1), snap.FileCount)
assert.Equal(t, storedSize, snap.TotalSize)
})
}
}