Compare commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
2aa6fc8f66 |
No files matched your search
@@ -554,6 +554,12 @@ 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
|
||||
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
|
||||
|
||||
**`remote nuke`**: Delete every object under `metadata/` and `blobs/` on the
|
||||
@@ -618,10 +624,6 @@ 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
|
||||
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,
|
||||
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
|
||||
|
||||
@@ -75,7 +75,9 @@ func newRemoteInfoCommand() *cobra.Command {
|
||||
- Size of all snapshot metadata (per snapshot and total)
|
||||
- Count and total size of all blobs
|
||||
- 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,
|
||||
RunE: func(cmd *cobra.Command, _ []string) error {
|
||||
// Use unified config resolution
|
||||
|
||||
@@ -1,154 +0,0 @@
|
||||
//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)
|
||||
}
|
||||
@@ -4,10 +4,8 @@ package snapshot
|
||||
import (
|
||||
"os"
|
||||
"path/filepath"
|
||||
"syscall"
|
||||
"testing"
|
||||
|
||||
"github.com/spf13/afero"
|
||||
"github.com/stretchr/testify/assert"
|
||||
"github.com/stretchr/testify/require"
|
||||
)
|
||||
@@ -40,36 +38,3 @@ func TestDeviceNumberFromStat(t *testing.T) {
|
||||
// /dev is a different filesystem from the temp dir on Linux, macOS and in Docker.
|
||||
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")
|
||||
}
|
||||
+14
-15
@@ -54,21 +54,20 @@ func provideScannerFactory(
|
||||
}
|
||||
|
||||
return NewScanner(ScannerConfig{
|
||||
FS: params.Fs,
|
||||
ChunkSize: cfg.ChunkSize.Int64(),
|
||||
Repositories: repos,
|
||||
Storage: storer,
|
||||
MaxBlobSize: cfg.BlobSizeLimit.Int64(),
|
||||
CompressionLevel: cfg.CompressionLevel,
|
||||
AgeRecipients: cfg.AgeRecipients,
|
||||
EnableProgress: params.EnableProgress,
|
||||
UI: params.UI,
|
||||
Exclude: excludes,
|
||||
IndexAndLockFiles: indexAndLockFiles(cfg.IndexPath, pidlock.Dir()),
|
||||
SkipErrors: params.SkipErrors,
|
||||
PreviousSnapshotID: params.PreviousSnapshotID,
|
||||
BlobUploadRetryDelay: BlobUploadRetryDelay,
|
||||
DeviceNumber: params.DeviceNumber,
|
||||
FS: params.Fs,
|
||||
ChunkSize: cfg.ChunkSize.Int64(),
|
||||
Repositories: repos,
|
||||
Storage: storer,
|
||||
MaxBlobSize: cfg.BlobSizeLimit.Int64(),
|
||||
CompressionLevel: cfg.CompressionLevel,
|
||||
AgeRecipients: cfg.AgeRecipients,
|
||||
EnableProgress: params.EnableProgress,
|
||||
UI: params.UI,
|
||||
Exclude: excludes,
|
||||
IndexAndLockFiles: indexAndLockFiles(cfg.IndexPath, pidlock.Dir()),
|
||||
SkipErrors: params.SkipErrors,
|
||||
PreviousSnapshotID: params.PreviousSnapshotID,
|
||||
DeviceNumber: params.DeviceNumber,
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
@@ -75,8 +75,6 @@ type Scanner struct {
|
||||
// skipErrors skips files that cannot be opened or read (logged loudly);
|
||||
// packer, database, encryption, and upload errors still abort the run.
|
||||
skipErrors bool
|
||||
// blobUploadRetryDelay is ScannerConfig.BlobUploadRetryDelay.
|
||||
blobUploadRetryDelay time.Duration
|
||||
// ui is the user-facing output; never nil (defaults to a discarding writer).
|
||||
ui *ui.Writer
|
||||
// deviceNumber returns the number of the device that holds a file;
|
||||
@@ -125,16 +123,8 @@ const (
|
||||
// snapshotAssocBatchSize is how many file IDs are associated with the
|
||||
// snapshot per transaction.
|
||||
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
|
||||
type ScannerConfig struct {
|
||||
FS afero.Fs
|
||||
@@ -158,10 +148,6 @@ type ScannerConfig struct {
|
||||
// PreviousSnapshotID is the most recent completed snapshot of the
|
||||
// same name, "" for none.
|
||||
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,
|
||||
// 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.
|
||||
@@ -259,24 +245,23 @@ func NewScanner(cfg ScannerConfig) *Scanner {
|
||||
}
|
||||
|
||||
return &Scanner{
|
||||
fs: cfg.FS,
|
||||
chunker: chunker.NewChunker(cfg.ChunkSize),
|
||||
packer: packer,
|
||||
repos: cfg.Repositories,
|
||||
storage: cfg.Storage,
|
||||
maxBlobSize: cfg.MaxBlobSize,
|
||||
compressionLevel: cfg.CompressionLevel,
|
||||
ageRecipient: strings.Join(cfg.AgeRecipients, ","),
|
||||
exclude: cfg.Exclude,
|
||||
compiledExclude: compiledExclude,
|
||||
indexAndLockFiles: indexAndLockFiles,
|
||||
progress: progress,
|
||||
skipErrors: cfg.SkipErrors,
|
||||
previousSnapshotID: cfg.PreviousSnapshotID,
|
||||
blobUploadRetryDelay: cfg.BlobUploadRetryDelay,
|
||||
ui: uiw,
|
||||
deviceNumber: deviceNumber,
|
||||
pendingChunkHashes: make(map[string]struct{}),
|
||||
fs: cfg.FS,
|
||||
chunker: chunker.NewChunker(cfg.ChunkSize),
|
||||
packer: packer,
|
||||
repos: cfg.Repositories,
|
||||
storage: cfg.Storage,
|
||||
maxBlobSize: cfg.MaxBlobSize,
|
||||
compressionLevel: cfg.CompressionLevel,
|
||||
ageRecipient: strings.Join(cfg.AgeRecipients, ","),
|
||||
exclude: cfg.Exclude,
|
||||
compiledExclude: compiledExclude,
|
||||
indexAndLockFiles: indexAndLockFiles,
|
||||
progress: progress,
|
||||
skipErrors: cfg.SkipErrors,
|
||||
previousSnapshotID: cfg.PreviousSnapshotID,
|
||||
ui: uiw,
|
||||
deviceNumber: deviceNumber,
|
||||
pendingChunkHashes: make(map[string]struct{}),
|
||||
}
|
||||
}
|
||||
|
||||
@@ -1453,12 +1438,11 @@ func (s *Scanner) deviceNumberAt(path string) (uint64, bool) {
|
||||
}
|
||||
|
||||
// deviceNumberFromStat returns the number of the device that holds the
|
||||
// file info describes, and false when info carries no stat from a real
|
||||
// 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.
|
||||
// file info describes, and false when info carries no stat, as from the
|
||||
// in-memory test filesystem.
|
||||
func deviceNumberFromStat(info os.FileInfo) (uint64, bool) {
|
||||
stat, ok := info.Sys().(*syscall.Stat_t)
|
||||
if !ok || (stat.Dev == 0 && stat.Ino == 0) {
|
||||
if !ok {
|
||||
return 0, false
|
||||
}
|
||||
|
||||
@@ -1891,7 +1875,10 @@ func (s *Scanner) uploadBlobIfNeeded(
|
||||
s.ui.Hex(finishedBlob.Hash), s.ui.Size(finishedBlob.Compressed),
|
||||
s.ui.Path(destination))
|
||||
|
||||
err = s.putBlob(ctx, blobPath, blobWithReader)
|
||||
progressCallback := s.makeUploadProgressCallback(ctx, finishedBlob, startTime)
|
||||
|
||||
err = s.storage.PutWithProgress(ctx, blobPath, blobWithReader.Reader,
|
||||
finishedBlob.Compressed, progressCallback)
|
||||
if err != nil {
|
||||
// The record is at info level: the returned error ends the backup
|
||||
// and is printed as its ERROR: line. Only an interrupt cancels
|
||||
@@ -1935,44 +1922,6 @@ func (s *Scanner) uploadBlobIfNeeded(
|
||||
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.
|
||||
// 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.
|
||||
|
||||
@@ -9,6 +9,7 @@ import (
|
||||
|
||||
"github.com/dustin/go-humanize"
|
||||
"sneak.berlin/go/vaultik/internal/log"
|
||||
"sneak.berlin/go/vaultik/internal/storage"
|
||||
)
|
||||
|
||||
// ShowInfo displays system and configuration information
|
||||
@@ -187,6 +188,9 @@ type SnapshotMetadataInfo struct {
|
||||
// backup interrupted before its manifest upload leaves a directory
|
||||
// without one, which prune does not treat as a snapshot.
|
||||
hasManifest bool
|
||||
|
||||
// Hashes of the blobs the snapshot's manifest lists.
|
||||
blobHashes []string
|
||||
}
|
||||
|
||||
// RemoteInfoResult contains all remote storage information
|
||||
@@ -216,6 +220,13 @@ type RemoteInfoResult struct {
|
||||
OrphanedBlobCount *int `json:"orphaned_blob_count"`
|
||||
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
|
||||
UnreadableManifests []string `json:"unreadable_manifests,omitempty"`
|
||||
|
||||
@@ -283,19 +294,30 @@ func (v *Vaultik) RemoteInfo(jsonOutput bool) error {
|
||||
"snapshots", result.TotalMetadataCount,
|
||||
"total_blobs", result.TotalBlobCount,
|
||||
"referenced_blobs", result.ReferencedBlobCount,
|
||||
"missing_blobs", result.MissingBlobCount,
|
||||
"unreadable_manifests", len(result.UnreadableManifests))
|
||||
|
||||
if jsonOutput {
|
||||
enc := json.NewEncoder(v.Stdout)
|
||||
enc.SetIndent("", " ")
|
||||
|
||||
return enc.Encode(result)
|
||||
err = enc.Encode(result)
|
||||
if err != nil {
|
||||
return fmt.Errorf("encoding JSON: %w", err)
|
||||
}
|
||||
}
|
||||
|
||||
if showText {
|
||||
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
|
||||
}
|
||||
|
||||
@@ -405,6 +427,7 @@ func (v *Vaultik) collectReferencedBlobsFromManifests(
|
||||
for _, blob := range manifest.Blobs {
|
||||
referencedBlobs[blob.Hash] = blob.CompressedSize
|
||||
blobsSize += blob.CompressedSize
|
||||
info.blobHashes = append(info.blobHashes, blob.Hash)
|
||||
}
|
||||
|
||||
info.BlobCount = &blobCount
|
||||
@@ -462,6 +485,8 @@ func (v *Vaultik) scanRemoteBlobStorage(
|
||||
result.TotalBlobSize += blob.Size
|
||||
}
|
||||
|
||||
countMissingBlobs(result, referencedBlobs, allBlobs)
|
||||
|
||||
// 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
|
||||
// figures stay unknown.
|
||||
@@ -487,6 +512,33 @@ func (v *Vaultik) scanRemoteBlobStorage(
|
||||
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
|
||||
func (v *Vaultik) printRemoteInfoTable(result *RemoteInfoResult) {
|
||||
const (
|
||||
@@ -539,6 +591,12 @@ func (v *Vaultik) printRemoteInfoTable(result *RemoteInfoResult) {
|
||||
"", "", 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("Total blobs on remote: %s (%s)\n",
|
||||
humanize.Comma(int64(result.TotalBlobCount)),
|
||||
@@ -546,22 +604,31 @@ func (v *Vaultik) printRemoteInfoTable(result *RemoteInfoResult) {
|
||||
v.stdoutf("Referenced by snapshots: %s (%s)\n",
|
||||
humanize.Comma(int64(result.ReferencedBlobCount)),
|
||||
ubytes(result.ReferencedBlobSize))
|
||||
v.stdoutf("Missing from remote: %s (%s)\n",
|
||||
humanize.Comma(int64(result.MissingBlobCount)),
|
||||
ubytes(result.MissingBlobSize))
|
||||
|
||||
if result.OrphanedBlobCount == nil {
|
||||
v.stdoutf("Orphaned (unreferenced): unknown "+
|
||||
"(%d manifest(s) could not be read, "+
|
||||
"%d manifest(s) under a non-conforming name skipped)\n",
|
||||
len(result.UnreadableManifests), result.SkippedManifestCount)
|
||||
} else {
|
||||
v.stdoutf("Orphaned (unreferenced): %s (%s)\n",
|
||||
humanize.Comma(int64(*result.OrphanedBlobCount)),
|
||||
ubytes(*result.OrphanedBlobSize))
|
||||
|
||||
return
|
||||
if *result.OrphanedBlobCount > 0 {
|
||||
v.stdoutf("\nRun 'vaultik prune' to remove orphaned blobs.\n")
|
||||
}
|
||||
}
|
||||
|
||||
v.stdoutf("Orphaned (unreferenced): %s (%s)\n",
|
||||
humanize.Comma(int64(*result.OrphanedBlobCount)),
|
||||
ubytes(*result.OrphanedBlobSize))
|
||||
if len(result.SnapshotsMissingBlobs) > 0 {
|
||||
v.stdoutf("\nSnapshots that cannot be restored (blobs missing):\n")
|
||||
|
||||
if *result.OrphanedBlobCount > 0 {
|
||||
v.stdoutf("\nRun 'vaultik prune' to remove orphaned blobs.\n")
|
||||
for _, id := range result.SnapshotsMissingBlobs {
|
||||
v.stdoutf(" %s\n", id)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
@@ -83,6 +83,7 @@ func TestRemoteInfo_UnreadableManifestLeavesSnapshotBlobsUnknown(t *testing.T) {
|
||||
env := newListEnv(t)
|
||||
readableKey := env.addRemote(t, listRemoteID,
|
||||
time.Date(2026, 3, 2, 0, 0, 0, 0, time.UTC))
|
||||
addBlob(t, env.store.testStorer, testBlobHashA)
|
||||
|
||||
unreadableKey := snapshot.RemoteSnapshotKey(listLocalID)
|
||||
require.NoError(t, env.store.Put(context.Background(),
|
||||
@@ -270,6 +271,7 @@ func TestRemoteInfo_StatusLineUsesUIMarker(t *testing.T) {
|
||||
|
||||
env := newListEnv(t)
|
||||
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"
|
||||
|
||||
@@ -281,3 +283,61 @@ func TestRemoteInfo_StatusLineUsesUIMarker(t *testing.T) {
|
||||
require.NoError(t, env.v.RemoteInfo(false))
|
||||
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")
|
||||
}
|
||||
@@ -349,6 +349,7 @@ func TestSnapshotListAndPurgePrintSizesLikeRemoteInfo(t *testing.T) {
|
||||
env.addRemote(t, listLocalID, start)
|
||||
require.NoError(t, env.v.Repositories.Snapshots.UpdateCounts(
|
||||
context.Background(), nil, listLocalID, 0, 0, 0, 0, fiveMegabytes))
|
||||
addBlob(t, env.store.testStorer, testBlobHashA)
|
||||
|
||||
require.NoError(t, env.v.RemoteInfo(false))
|
||||
assert.Contains(t, findTableRow(t, env.stdout.String(), remoteKey[:16]),
|
||||
|
||||
@@ -4,7 +4,6 @@ import (
|
||||
"context"
|
||||
"maps"
|
||||
"path/filepath"
|
||||
"strings"
|
||||
"testing"
|
||||
|
||||
"github.com/spf13/afero"
|
||||
@@ -13,7 +12,6 @@ import (
|
||||
"sneak.berlin/go/vaultik/internal/database"
|
||||
"sneak.berlin/go/vaultik/internal/log"
|
||||
"sneak.berlin/go/vaultik/internal/storage"
|
||||
"sneak.berlin/go/vaultik/internal/storage/faultstore"
|
||||
"sneak.berlin/go/vaultik/internal/vaultik"
|
||||
)
|
||||
|
||||
@@ -70,55 +68,3 @@ func TestBackupWithoutCronOfTwoPathSnapshotRestoresBothPaths(t *testing.T) {
|
||||
|
||||
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)
|
||||
}
|
||||
Reference in new issue
Block a user