Compare commits

..
Author SHA1 Message Date
clawbot d71be0b4c8 Retry a failed blob upload five times, 3 seconds apart (closes #476)
check / check (push) Waiting to run
A blob upload that failed, such as one cut off by a lost connection,
ended the backup at once. It is now tried again from the start of the
blob up to five times, 3 seconds apart, with a warning before each
retry; an interrupt still stops it at once. The panic in the report,
"close of closed channel" from the progress reporter, was already fixed
on next by the commit for issue 253; a test now covers a failing upload
with the progress reporter on.

Model: opus-5-5
2026-11-19 09:28:57 +00:00
sneak 4605eae024 next: integrate accumulated work into main (#203)
check / check (push) Waiting to run
Reviewed-on: #203
2026-11-19 10:27:45 +01:00
clawbot 5b09271751 Report no device number for a zeroed stat (closes #462)
check / check (push) Waiting to run
deviceNumberFromStat returned device 0 and true for a stat whose device
and inode numbers are both zero. afero's unreleased master gives such a
stat for every in-memory file; the pinned v1.15.0 gives none. It now
returns false for it, as its comment says, and a test covers both
in-memory shapes.

Model: opus-5-5
2026-11-19 09:53:18 +01:00
10 changed files with 312 additions and 149 deletions

No files matched your search

+4 -6
View File
@@ -554,12 +554,6 @@ count and blob size unknown, `null` in `--json`. A file under `blobs/` whose
name is not a blob hash is not counted as a blob, since `prune` never deletes name is not a blob hash is not counted as a blob, since `prune` never deletes
it. it.
A blob that a manifest lists but the destination does not hold is reported as
missing, with a count and size. The report names each snapshot that lists a
missing blob, since that snapshot cannot be restored. The command then exits
non-zero. `--json` gives these in `missing_blob_count`, `missing_blob_size` and
`snapshots_missing_blobs`.
- `--json`: Output as JSON - `--json`: Output as JSON
**`remote nuke`**: Delete every object under `metadata/` and `blobs/` on the **`remote nuke`**: Delete every object under `metadata/` and `blobs/` on the
@@ -624,6 +618,10 @@ being written, a killed upload can leave a truncated object under its name,
which a later backup takes for complete. A leftover `.partial` file is ignored which a later backup takes for complete. A leftover `.partial` file is ignored
and can be deleted. and can be deleted.
A blob upload that fails, such as one cut off by a lost connection, is tried
again up to five times, three seconds apart. Each new try is announced with a
warning. If the last try fails too, the backup stops with the upload's error.
A destination shared between hosts or users, each with its own local index, A destination shared between hosts or users, each with its own local index,
relies on `prune_grace_period` to keep one's prune from deleting the blobs of relies on `prune_grace_period` to keep one's prune from deleting the blobs of
another's backup still running, or its directory under `metadata/` that has no another's backup still running, or its directory under `metadata/` that has no
+1 -3
View File
@@ -75,9 +75,7 @@ func newRemoteInfoCommand() *cobra.Command {
- Size of all snapshot metadata (per snapshot and total) - Size of all snapshot metadata (per snapshot and total)
- Count and total size of all blobs - Count and total size of all blobs
- Count and size of referenced blobs (from all manifests) - Count and size of referenced blobs (from all manifests)
- Count and size of orphaned blobs (not referenced by any manifest) - Count and size of orphaned blobs (not referenced by any manifest)`,
- Count and size of referenced blobs missing from remote storage, and the
snapshots that list them; the command exits non-zero when any are missing`,
Args: cobra.NoArgs, Args: cobra.NoArgs,
RunE: func(cmd *cobra.Command, _ []string) error { RunE: func(cmd *cobra.Command, _ []string) error {
// Use unified config resolution // Use unified config resolution
+154
View File
@@ -0,0 +1,154 @@
//nolint:testpackage // exercises the unexported uploadBlobIfNeeded
package snapshot
import (
"bytes"
"context"
"io"
"path/filepath"
"testing"
"time"
"github.com/spf13/afero"
"github.com/stretchr/testify/require"
"sneak.berlin/go/vaultik/internal/blob"
"sneak.berlin/go/vaultik/internal/config"
"sneak.berlin/go/vaultik/internal/storage"
"sneak.berlin/go/vaultik/internal/storage/faultstore"
"sneak.berlin/go/vaultik/internal/ui"
)
// retryTestBlobSize is larger than what a failing faultstore Put reads,
// so a new try that did not rewind the blob would store a short object.
const retryTestBlobSize = 4096
// retryTestBlobKey is where the retry tests upload their blob.
const retryTestBlobKey = "blobs/retry"
// uploadRetryTestBlob uploads a retryTestBlobSize blob through store,
// waiting delay between tries, and returns the blob's bytes, the warnings
// the upload printed and its error.
func uploadRetryTestBlob(
ctx context.Context, store storage.Storer, delay time.Duration,
) ([]byte, int, error) {
data := bytes.Repeat([]byte("0123456789abcdef"), retryTestBlobSize/16)
output := ui.NewWithColor(io.Discard, false)
s := &Scanner{storage: store, ui: output, blobUploadRetryDelay: delay}
_, _, err := s.uploadBlobIfNeeded(ctx, retryTestBlobKey, &blob.WithReader{
FinishedBlob: &blob.FinishedBlob{
Hash: "retry",
Compressed: int64(len(data)),
},
Reader: bytes.NewReader(data),
}, time.Now(), &ScanResult{})
return data, output.WarningCount(), err
}
// A blob upload that fails is tried again from the start of the blob,
// and each failure is a warning. See
// https://git.eeqj.de/sneak/vaultik/issues/476.
func TestFailedBlobUploadIsTriedAgain(t *testing.T) {
t.Parallel()
inner, err := storage.NewFileStorer(t.TempDir())
require.NoError(t, err)
puts := 0
store := faultstore.New(inner)
store.OnPut = func(string) faultstore.PutAction {
puts++
if puts <= 2 {
return faultstore.PutFail
}
return faultstore.PutNormal
}
data, warnings, err := uploadRetryTestBlob(context.Background(), store, 0)
require.NoError(t, err)
require.Equal(t, 3, puts)
require.Equal(t, 2, warnings)
rc, err := inner.Get(context.Background(), retryTestBlobKey)
require.NoError(t, err)
defer func() { _ = rc.Close() }()
stored, err := io.ReadAll(rc)
require.NoError(t, err)
require.Equal(t, data, stored)
}
// A blob upload that keeps failing is tried blobUploadRetries more times,
// BlobUploadRetryDelay apart, and then the backup stops with its error.
func TestBlobUploadStopsAfterRetries(t *testing.T) {
t.Parallel()
inner, err := storage.NewFileStorer(t.TempDir())
require.NoError(t, err)
puts := 0
store := faultstore.New(inner)
store.OnPut = func(string) faultstore.PutAction {
puts++
return faultstore.PutFail
}
const delay = 10 * time.Millisecond
start := time.Now()
_, warnings, err := uploadRetryTestBlob(context.Background(), store, delay)
require.ErrorIs(t, err, faultstore.ErrInjectedUpload)
require.Equal(t, 1+blobUploadRetries, puts)
require.Equal(t, blobUploadRetries, warnings)
require.GreaterOrEqual(t, time.Since(start), blobUploadRetries*delay)
}
// An upload stopped by Ctrl-C or SIGTERM is not tried again.
func TestInterruptedBlobUploadIsNotTriedAgain(t *testing.T) {
t.Parallel()
inner, err := storage.NewFileStorer(t.TempDir())
require.NoError(t, err)
ctx, cancel := context.WithCancel(context.Background())
t.Cleanup(cancel)
puts := 0
store := faultstore.New(inner)
store.OnPut = func(string) faultstore.PutAction {
puts++
cancel()
return faultstore.PutFail
}
_, warnings, err := uploadRetryTestBlob(ctx, store, 0)
require.Error(t, err)
require.Equal(t, 1, puts)
require.Zero(t, warnings)
}
// Backups wait BlobUploadRetryDelay before each new try.
func TestBackupScannerWaitsBetweenBlobUploadRetries(t *testing.T) {
t.Parallel()
cfg := &config.Config{
AgeRecipients: []string{testAgeRecipient},
ChunkSize: config.Size(1024 * 1024),
BlobSizeLimit: config.Size(4 * 1024 * 1024),
IndexPath: filepath.Join(t.TempDir(), "index.sqlite"),
}
scanner := provideScannerFactory(cfg, nil, nil)(ScannerParams{
Fs: afero.NewMemMapFs(),
})
require.NotNil(t, scanner)
require.Equal(t, BlobUploadRetryDelay, scanner.blobUploadRetryDelay)
}
+35
View File
@@ -4,8 +4,10 @@ package snapshot
import ( import (
"os" "os"
"path/filepath" "path/filepath"
"syscall"
"testing" "testing"
"github.com/spf13/afero"
"github.com/stretchr/testify/assert" "github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require" "github.com/stretchr/testify/require"
) )
@@ -38,3 +40,36 @@ func TestDeviceNumberFromStat(t *testing.T) {
// /dev is a different filesystem from the temp dir on Linux, macOS and in Docker. // /dev is a different filesystem from the temp dir on Linux, macOS and in Docker.
assert.NotEqual(t, deviceOf(dir), deviceOf("/dev")) assert.NotEqual(t, deviceOf(dir), deviceOf("/dev"))
} }
// fileInfoWithStat is a file's info whose Sys returns stat.
type fileInfoWithStat struct {
os.FileInfo
stat *syscall.Stat_t
}
func (i fileInfoWithStat) Sys() any { return i.stat }
// The in-memory test filesystem has no device numbers. The pinned afero
// gives no stat; its unreleased master gives a stat holding only uid, gid
// and size. See https://git.eeqj.de/sneak/vaultik/issues/462.
func TestDeviceNumberFromStatInMemory(t *testing.T) {
t.Parallel()
fs := afero.NewMemMapFs()
require.NoError(t, afero.WriteFile(fs, "/file.txt", []byte("data"), 0o600))
info, err := fs.Stat("/file.txt")
require.NoError(t, err)
_, ok := deviceNumberFromStat(info)
assert.False(t, ok, "device number read from a file info with no stat")
zeroed := fileInfoWithStat{
FileInfo: info,
stat: &syscall.Stat_t{Uid: 1000, Gid: 1000, Size: 4},
}
_, ok = deviceNumberFromStat(zeroed)
assert.False(t, ok, "device number read from a stat with no device or inode number")
}
+1
View File
@@ -67,6 +67,7 @@ func provideScannerFactory(
IndexAndLockFiles: indexAndLockFiles(cfg.IndexPath, pidlock.Dir()), IndexAndLockFiles: indexAndLockFiles(cfg.IndexPath, pidlock.Dir()),
SkipErrors: params.SkipErrors, SkipErrors: params.SkipErrors,
PreviousSnapshotID: params.PreviousSnapshotID, PreviousSnapshotID: params.PreviousSnapshotID,
BlobUploadRetryDelay: BlobUploadRetryDelay,
DeviceNumber: params.DeviceNumber, DeviceNumber: params.DeviceNumber,
}) })
} }
+58 -7
View File
@@ -75,6 +75,8 @@ type Scanner struct {
// skipErrors skips files that cannot be opened or read (logged loudly); // skipErrors skips files that cannot be opened or read (logged loudly);
// packer, database, encryption, and upload errors still abort the run. // packer, database, encryption, and upload errors still abort the run.
skipErrors bool skipErrors bool
// blobUploadRetryDelay is ScannerConfig.BlobUploadRetryDelay.
blobUploadRetryDelay time.Duration
// ui is the user-facing output; never nil (defaults to a discarding writer). // ui is the user-facing output; never nil (defaults to a discarding writer).
ui *ui.Writer ui *ui.Writer
// deviceNumber returns the number of the device that holds a file; // deviceNumber returns the number of the device that holds a file;
@@ -123,8 +125,16 @@ const (
// snapshotAssocBatchSize is how many file IDs are associated with the // snapshotAssocBatchSize is how many file IDs are associated with the
// snapshot per transaction. // snapshot per transaction.
snapshotAssocBatchSize = 1000 snapshotAssocBatchSize = 1000
// blobUploadRetries is how many more times a failed blob upload is
// tried before the backup stops with the error.
blobUploadRetries = 5
) )
// BlobUploadRetryDelay is the wait before each new try of a failed blob
// upload.
const BlobUploadRetryDelay = 3 * time.Second
// ScannerConfig contains configuration for the scanner // ScannerConfig contains configuration for the scanner
type ScannerConfig struct { type ScannerConfig struct {
FS afero.Fs FS afero.Fs
@@ -148,6 +158,10 @@ type ScannerConfig struct {
// PreviousSnapshotID is the most recent completed snapshot of the // PreviousSnapshotID is the most recent completed snapshot of the
// same name, "" for none. // same name, "" for none.
PreviousSnapshotID string PreviousSnapshotID string
// BlobUploadRetryDelay is the wait before each new try of a failed
// blob upload. Backups use snapshot.BlobUploadRetryDelay; tests leave
// it zero to try again at once.
BlobUploadRetryDelay time.Duration
// DeviceNumber returns the number of the device that holds a file, // DeviceNumber returns the number of the device that holds a file,
// and false when there is none to read. nil reads it from the file's // and false when there is none to read. nil reads it from the file's
// stat; tests replace it, since the in-memory test filesystem has none. // stat; tests replace it, since the in-memory test filesystem has none.
@@ -259,6 +273,7 @@ func NewScanner(cfg ScannerConfig) *Scanner {
progress: progress, progress: progress,
skipErrors: cfg.SkipErrors, skipErrors: cfg.SkipErrors,
previousSnapshotID: cfg.PreviousSnapshotID, previousSnapshotID: cfg.PreviousSnapshotID,
blobUploadRetryDelay: cfg.BlobUploadRetryDelay,
ui: uiw, ui: uiw,
deviceNumber: deviceNumber, deviceNumber: deviceNumber,
pendingChunkHashes: make(map[string]struct{}), pendingChunkHashes: make(map[string]struct{}),
@@ -1438,11 +1453,12 @@ func (s *Scanner) deviceNumberAt(path string) (uint64, bool) {
} }
// deviceNumberFromStat returns the number of the device that holds the // deviceNumberFromStat returns the number of the device that holds the
// file info describes, and false when info carries no stat, as from the // file info describes, and false when info carries no stat from a real
// in-memory test filesystem. // filesystem. The in-memory test filesystem gives either no stat or one
// whose device and inode numbers are both zero, which no real file has.
func deviceNumberFromStat(info os.FileInfo) (uint64, bool) { func deviceNumberFromStat(info os.FileInfo) (uint64, bool) {
stat, ok := info.Sys().(*syscall.Stat_t) stat, ok := info.Sys().(*syscall.Stat_t)
if !ok { if !ok || (stat.Dev == 0 && stat.Ino == 0) {
return 0, false return 0, false
} }
@@ -1875,10 +1891,7 @@ func (s *Scanner) uploadBlobIfNeeded(
s.ui.Hex(finishedBlob.Hash), s.ui.Size(finishedBlob.Compressed), s.ui.Hex(finishedBlob.Hash), s.ui.Size(finishedBlob.Compressed),
s.ui.Path(destination)) s.ui.Path(destination))
progressCallback := s.makeUploadProgressCallback(ctx, finishedBlob, startTime) err = s.putBlob(ctx, blobPath, blobWithReader)
err = s.storage.PutWithProgress(ctx, blobPath, blobWithReader.Reader,
finishedBlob.Compressed, progressCallback)
if err != nil { if err != nil {
// The record is at info level: the returned error ends the backup // The record is at info level: the returned error ends the backup
// and is printed as its ERROR: line. Only an interrupt cancels // and is printed as its ERROR: line. Only an interrupt cancels
@@ -1922,6 +1935,44 @@ func (s *Scanner) uploadBlobIfNeeded(
return finishedBlob.Compressed, false, nil return finishedBlob.Compressed, false, nil
} }
// putBlob uploads the blob to blobPath. After a failed upload it waits
// s.blobUploadRetryDelay and uploads the whole blob again, up to
// blobUploadRetries times, and then returns the last error. An interrupt
// stops it at once.
func (s *Scanner) putBlob(
ctx context.Context, blobPath string, blobWithReader *blob.WithReader,
) error {
finishedBlob := blobWithReader.FinishedBlob
for retries := 0; ; retries++ {
_, err := blobWithReader.Reader.Seek(0, io.SeekStart)
if err != nil {
return fmt.Errorf("rewinding blob for upload: %w", err)
}
progressCallback := s.makeUploadProgressCallback(
ctx, finishedBlob, time.Now().UTC())
err = s.storage.PutWithProgress(ctx, blobPath, blobWithReader.Reader,
finishedBlob.Compressed, progressCallback)
if err == nil || ctx.Err() != nil || retries == blobUploadRetries {
return err
}
log.Info("Blob upload failed, trying again",
"hash", finishedBlob.Hash, "retry", retries+1, "error", err)
s.ui.Warningf("Upload of blob %s failed: %v. Trying again in %s (retry %d of %d).",
s.ui.Hex(finishedBlob.Hash), err,
s.ui.Duration(s.blobUploadRetryDelay), retries+1, blobUploadRetries)
select {
case <-ctx.Done():
return err
case <-time.After(s.blobUploadRetryDelay):
}
}
}
// makeUploadProgressCallback creates a progress callback for blob uploads. // makeUploadProgressCallback creates a progress callback for blob uploads.
// It updates the live progress reporter ~twice/sec for ETAs and prints a // It updates the live progress reporter ~twice/sec for ETAs and prints a
// human-readable status line to s.output at most every 15 seconds. // human-readable status line to s.output at most every 15 seconds.
+5 -72
View File
@@ -9,7 +9,6 @@ import (
"github.com/dustin/go-humanize" "github.com/dustin/go-humanize"
"sneak.berlin/go/vaultik/internal/log" "sneak.berlin/go/vaultik/internal/log"
"sneak.berlin/go/vaultik/internal/storage"
) )
// ShowInfo displays system and configuration information // ShowInfo displays system and configuration information
@@ -188,9 +187,6 @@ type SnapshotMetadataInfo struct {
// backup interrupted before its manifest upload leaves a directory // backup interrupted before its manifest upload leaves a directory
// without one, which prune does not treat as a snapshot. // without one, which prune does not treat as a snapshot.
hasManifest bool hasManifest bool
// Hashes of the blobs the snapshot's manifest lists.
blobHashes []string
} }
// RemoteInfoResult contains all remote storage information // RemoteInfoResult contains all remote storage information
@@ -220,13 +216,6 @@ type RemoteInfoResult struct {
OrphanedBlobCount *int `json:"orphaned_blob_count"` OrphanedBlobCount *int `json:"orphaned_blob_count"`
OrphanedBlobSize *int64 `json:"orphaned_blob_size"` OrphanedBlobSize *int64 `json:"orphaned_blob_size"`
// Blobs that a manifest lists but the destination does not hold,
// and the remote key of each snapshot whose manifest lists one.
// Those snapshots cannot be restored.
MissingBlobCount int `json:"missing_blob_count"`
MissingBlobSize int64 `json:"missing_blob_size"`
SnapshotsMissingBlobs []string `json:"snapshots_missing_blobs,omitempty"`
// Remote key of each snapshot whose manifest could not be read // Remote key of each snapshot whose manifest could not be read
UnreadableManifests []string `json:"unreadable_manifests,omitempty"` UnreadableManifests []string `json:"unreadable_manifests,omitempty"`
@@ -294,30 +283,19 @@ func (v *Vaultik) RemoteInfo(jsonOutput bool) error {
"snapshots", result.TotalMetadataCount, "snapshots", result.TotalMetadataCount,
"total_blobs", result.TotalBlobCount, "total_blobs", result.TotalBlobCount,
"referenced_blobs", result.ReferencedBlobCount, "referenced_blobs", result.ReferencedBlobCount,
"missing_blobs", result.MissingBlobCount,
"unreadable_manifests", len(result.UnreadableManifests)) "unreadable_manifests", len(result.UnreadableManifests))
if jsonOutput { if jsonOutput {
enc := json.NewEncoder(v.Stdout) enc := json.NewEncoder(v.Stdout)
enc.SetIndent("", " ") enc.SetIndent("", " ")
err = enc.Encode(result) return enc.Encode(result)
if err != nil {
return fmt.Errorf("encoding JSON: %w", err)
}
} }
if showText { if showText {
v.printRemoteInfoTable(result) v.printRemoteInfoTable(result)
} }
// The report is written first, so the exit status adds to it.
if result.MissingBlobCount > 0 {
return fmt.Errorf("%w: %d blob(s) that snapshots list are missing; "+
"%d snapshot(s) cannot be restored", errProblemsInStorage,
result.MissingBlobCount, len(result.SnapshotsMissingBlobs))
}
return nil return nil
} }
@@ -427,7 +405,6 @@ func (v *Vaultik) collectReferencedBlobsFromManifests(
for _, blob := range manifest.Blobs { for _, blob := range manifest.Blobs {
referencedBlobs[blob.Hash] = blob.CompressedSize referencedBlobs[blob.Hash] = blob.CompressedSize
blobsSize += blob.CompressedSize blobsSize += blob.CompressedSize
info.blobHashes = append(info.blobHashes, blob.Hash)
} }
info.BlobCount = &blobCount info.BlobCount = &blobCount
@@ -485,8 +462,6 @@ func (v *Vaultik) scanRemoteBlobStorage(
result.TotalBlobSize += blob.Size result.TotalBlobSize += blob.Size
} }
countMissingBlobs(result, referencedBlobs, allBlobs)
// A blob named only by a manifest that could not be read, or by one // A blob named only by a manifest that could not be read, or by one
// under a skipped name, would be counted as orphaned, so the orphan // under a skipped name, would be counted as orphaned, so the orphan
// figures stay unknown. // figures stay unknown.
@@ -512,33 +487,6 @@ func (v *Vaultik) scanRemoteBlobStorage(
return nil return nil
} }
// countMissingBlobs records in result the referenced blobs that
// allBlobs, the listing of the destination, does not hold, and the
// snapshots whose manifests list one of them. It reads the snapshots
// from result.Snapshots, so populateRemoteInfoResult must run first.
func countMissingBlobs(
result *RemoteInfoResult, referencedBlobs map[string]int64,
allBlobs map[string]storage.ObjectInfo,
) {
for hash, size := range referencedBlobs {
if _, present := allBlobs[hash]; !present {
result.MissingBlobCount++
result.MissingBlobSize += size
}
}
for _, info := range result.Snapshots {
for _, hash := range info.blobHashes {
if _, present := allBlobs[hash]; !present {
result.SnapshotsMissingBlobs = append(
result.SnapshotsMissingBlobs, info.SnapshotID)
break
}
}
}
}
// printRemoteInfoTable renders the human-readable remote info output // printRemoteInfoTable renders the human-readable remote info output
func (v *Vaultik) printRemoteInfoTable(result *RemoteInfoResult) { func (v *Vaultik) printRemoteInfoTable(result *RemoteInfoResult) {
const ( const (
@@ -591,12 +539,6 @@ func (v *Vaultik) printRemoteInfoTable(result *RemoteInfoResult) {
"", "", ubytes(result.TotalMetadataSize)) "", "", ubytes(result.TotalMetadataSize))
} }
v.printBlobStorageSummary(result)
}
// printBlobStorageSummary renders the blob storage section that ends
// the human-readable remote info output.
func (v *Vaultik) printBlobStorageSummary(result *RemoteInfoResult) {
v.stdoutf("\n=== Blob Storage ===\n") v.stdoutf("\n=== Blob Storage ===\n")
v.stdoutf("Total blobs on remote: %s (%s)\n", v.stdoutf("Total blobs on remote: %s (%s)\n",
humanize.Comma(int64(result.TotalBlobCount)), humanize.Comma(int64(result.TotalBlobCount)),
@@ -604,16 +546,16 @@ func (v *Vaultik) printBlobStorageSummary(result *RemoteInfoResult) {
v.stdoutf("Referenced by snapshots: %s (%s)\n", v.stdoutf("Referenced by snapshots: %s (%s)\n",
humanize.Comma(int64(result.ReferencedBlobCount)), humanize.Comma(int64(result.ReferencedBlobCount)),
ubytes(result.ReferencedBlobSize)) ubytes(result.ReferencedBlobSize))
v.stdoutf("Missing from remote: %s (%s)\n",
humanize.Comma(int64(result.MissingBlobCount)),
ubytes(result.MissingBlobSize))
if result.OrphanedBlobCount == nil { if result.OrphanedBlobCount == nil {
v.stdoutf("Orphaned (unreferenced): unknown "+ v.stdoutf("Orphaned (unreferenced): unknown "+
"(%d manifest(s) could not be read, "+ "(%d manifest(s) could not be read, "+
"%d manifest(s) under a non-conforming name skipped)\n", "%d manifest(s) under a non-conforming name skipped)\n",
len(result.UnreadableManifests), result.SkippedManifestCount) len(result.UnreadableManifests), result.SkippedManifestCount)
} else {
return
}
v.stdoutf("Orphaned (unreferenced): %s (%s)\n", v.stdoutf("Orphaned (unreferenced): %s (%s)\n",
humanize.Comma(int64(*result.OrphanedBlobCount)), humanize.Comma(int64(*result.OrphanedBlobCount)),
ubytes(*result.OrphanedBlobSize)) ubytes(*result.OrphanedBlobSize))
@@ -623,15 +565,6 @@ func (v *Vaultik) printBlobStorageSummary(result *RemoteInfoResult) {
} }
} }
if len(result.SnapshotsMissingBlobs) > 0 {
v.stdoutf("\nSnapshots that cannot be restored (blobs missing):\n")
for _, id := range result.SnapshotsMissingBlobs {
v.stdoutf(" %s\n", id)
}
}
}
// ellipsis is appended by truncateString when it shortens a string. // ellipsis is appended by truncateString when it shortens a string.
const ellipsis = "..." const ellipsis = "..."
-60
View File
@@ -83,7 +83,6 @@ func TestRemoteInfo_UnreadableManifestLeavesSnapshotBlobsUnknown(t *testing.T) {
env := newListEnv(t) env := newListEnv(t)
readableKey := env.addRemote(t, listRemoteID, readableKey := env.addRemote(t, listRemoteID,
time.Date(2026, 3, 2, 0, 0, 0, 0, time.UTC)) time.Date(2026, 3, 2, 0, 0, 0, 0, time.UTC))
addBlob(t, env.store.testStorer, testBlobHashA)
unreadableKey := snapshot.RemoteSnapshotKey(listLocalID) unreadableKey := snapshot.RemoteSnapshotKey(listLocalID)
require.NoError(t, env.store.Put(context.Background(), require.NoError(t, env.store.Put(context.Background(),
@@ -271,7 +270,6 @@ func TestRemoteInfo_StatusLineUsesUIMarker(t *testing.T) {
env := newListEnv(t) env := newListEnv(t)
env.addRemote(t, listRemoteID, time.Date(2026, 3, 2, 0, 0, 0, 0, time.UTC)) env.addRemote(t, listRemoteID, time.Date(2026, 3, 2, 0, 0, 0, 0, time.UTC))
addBlob(t, env.store.testStorer, testBlobHashA)
const statusLine = ui.Marker + " Scanning snapshot metadata...\n" const statusLine = ui.Marker + " Scanning snapshot metadata...\n"
@@ -283,61 +281,3 @@ func TestRemoteInfo_StatusLineUsesUIMarker(t *testing.T) {
require.NoError(t, env.v.RemoteInfo(false)) require.NoError(t, env.v.RemoteInfo(false))
assert.NotContains(t, env.stdout.String(), "Scanning snapshot metadata") assert.NotContains(t, env.stdout.String(), "Scanning snapshot metadata")
} }
// TestRemoteInfo_ReportsBlobsMissingFromDestination checks that a blob a
// manifest lists but the destination does not hold is counted as
// missing, that the snapshot listing it is named, and that remote info
// then fails after writing its report.
func TestRemoteInfo_ReportsBlobsMissingFromDestination(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
env := newListEnv(t)
// The first snapshot lists blob A, which is not stored. The second
// lists blob B, which is.
brokenKey := env.addRemote(t, listRemoteID,
time.Date(2026, 3, 2, 0, 0, 0, 0, time.UTC))
addManifest(t, env.store.testStorer, listLocalID, []string{testBlobHashB})
addBlob(t, env.store.testStorer, testBlobHashB)
const wantError = "1 blob(s) that snapshots list are missing; " +
"1 snapshot(s) cannot be restored"
err := env.v.RemoteInfo(false)
require.ErrorContains(t, err, wantError)
text := env.stdout.String()
assert.Contains(t, text, "Missing from remote: 1 (5.0 MB)")
assert.Contains(t, text, "Snapshots that cannot be restored (blobs missing):\n"+
" "+brokenKey+"\n")
assert.NotContains(t, text, snapshot.RemoteSnapshotKey(listLocalID)+"\n")
env.stdout.Reset()
require.ErrorContains(t, env.v.RemoteInfo(true), wantError)
var doc map[string]any
require.NoError(t, json.Unmarshal(env.stdout.Bytes(), &doc))
assert.InDelta(t, 1, doc["missing_blob_count"], 0)
assert.InDelta(t, fiveMegabytes, doc["missing_blob_size"], 0)
assert.Equal(t, []any{brokenKey}, doc["snapshots_missing_blobs"])
// --quiet drops the report, not the failure.
env.stdout.Reset()
env.v.UI.SetQuiet(true)
require.ErrorContains(t, env.v.RemoteInfo(false), wantError)
assert.Empty(t, env.stdout.String())
env.v.UI.SetQuiet(false)
// With blob A stored again nothing is missing.
addBlob(t, env.store.testStorer, testBlobHashA)
env.stdout.Reset()
require.NoError(t, env.v.RemoteInfo(true))
doc = nil
require.NoError(t, json.Unmarshal(env.stdout.Bytes(), &doc))
assert.InDelta(t, 0, doc["missing_blob_count"], 0)
assert.InDelta(t, 0, doc["missing_blob_size"], 0)
assert.NotContains(t, doc, "snapshots_missing_blobs")
}
-1
View File
@@ -349,7 +349,6 @@ func TestSnapshotListAndPurgePrintSizesLikeRemoteInfo(t *testing.T) {
env.addRemote(t, listLocalID, start) env.addRemote(t, listLocalID, start)
require.NoError(t, env.v.Repositories.Snapshots.UpdateCounts( require.NoError(t, env.v.Repositories.Snapshots.UpdateCounts(
context.Background(), nil, listLocalID, 0, 0, 0, 0, fiveMegabytes)) context.Background(), nil, listLocalID, 0, 0, 0, 0, fiveMegabytes))
addBlob(t, env.store.testStorer, testBlobHashA)
require.NoError(t, env.v.RemoteInfo(false)) require.NoError(t, env.v.RemoteInfo(false))
assert.Contains(t, findTableRow(t, env.stdout.String(), remoteKey[:16]), assert.Contains(t, findTableRow(t, env.stdout.String(), remoteKey[:16]),
@@ -4,6 +4,7 @@ import (
"context" "context"
"maps" "maps"
"path/filepath" "path/filepath"
"strings"
"testing" "testing"
"github.com/spf13/afero" "github.com/spf13/afero"
@@ -12,6 +13,7 @@ import (
"sneak.berlin/go/vaultik/internal/database" "sneak.berlin/go/vaultik/internal/database"
"sneak.berlin/go/vaultik/internal/log" "sneak.berlin/go/vaultik/internal/log"
"sneak.berlin/go/vaultik/internal/storage" "sneak.berlin/go/vaultik/internal/storage"
"sneak.berlin/go/vaultik/internal/storage/faultstore"
"sneak.berlin/go/vaultik/internal/vaultik" "sneak.berlin/go/vaultik/internal/vaultik"
) )
@@ -68,3 +70,55 @@ func TestBackupWithoutCronOfTwoPathSnapshotRestoresBothPaths(t *testing.T) {
assertRestoredTree(t, fs, restoreDir, files) assertRestoredTree(t, fs, restoreDir, files)
} }
// A backup without --cron whose blob uploads keep failing stops with the
// upload's error, and stops the progress reporter once. See
// https://git.eeqj.de/sneak/vaultik/issues/476.
//
//nolint:paralleltest // installs the global logger via log.Initialize
func TestBackupWithoutCronStopsWithBlobUploadError(t *testing.T) {
log.Initialize(log.Config{})
const snapshotName = "data"
fs := afero.NewOsFs()
tempDir := t.TempDir()
firstDir := filepath.Join(tempDir, "first")
secondDir := filepath.Join(tempDir, "second")
dbPath := filepath.Join(tempDir, "index.sqlite")
ctx := context.Background()
writeFaultSourceTree(t, fs, firstDir)
writeFaultSourceTree(t, fs, secondDir)
cfg := faultTestConfig()
cfg.IndexPath = dbPath
cfg.ChunkSize = config.Size(faultChunkSize)
cfg.Snapshots = map[string]config.SnapshotConfig{
snapshotName: {Paths: []string{firstDir, secondDir}},
}
inner, err := storage.NewFileStorer(t.TempDir())
require.NoError(t, err)
store := faultstore.New(inner)
store.OnPut = func(key string) faultstore.PutAction {
if strings.HasPrefix(key, "blobs/") {
return faultstore.PutFail
}
return faultstore.PutNormal
}
db, err := database.New(ctx, dbPath)
require.NoError(t, err)
t.Cleanup(func() { _ = db.Close() })
v := newBackupVaultik(ctx, cfg, store, database.NewRepositories(db), db, fs)
err = v.CreateSnapshot(&vaultik.SnapshotCreateOptions{
Snapshots: []string{snapshotName},
})
require.ErrorIs(t, err, faultstore.ErrInjectedUpload)
}