Compare commits
5
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
d71be0b4c8 | ||
|
|
4605eae024 | ||
|
|
5b09271751 | ||
|
|
9fedcbeb0a | ||
|
|
d747ddef3a |
No files matched your search
@@ -468,10 +468,12 @@ destination store. Blobs are NOT touched — deleting blobs requires reading eve
|
||||
remaining remote manifest (the destination store may hold snapshots this host
|
||||
doesn't know about), which is what `vaultik prune` does. The command prints the
|
||||
`vaultik prune` invocation to run as a follow-up only when it removed the
|
||||
snapshot's metadata from the destination store, and never under `--json`. An ID
|
||||
that names no snapshot in the local index or on the destination store is an
|
||||
error; with `--local-only`, the snapshot must be in the local index. Local row
|
||||
cleanup (files, chunks, blobs the snapshot was the last referrer for) runs
|
||||
snapshot's metadata from the destination store, and never under `--json`. It
|
||||
accepts the same identifiers as `snapshot restore`: a snapshot ID, or a
|
||||
remote-only snapshot's remote key (or an unambiguous leading part of it). An
|
||||
identifier that names no snapshot in the local index or on the destination store
|
||||
is an error; with `--local-only`, the snapshot must be in the local index. Local
|
||||
row cleanup (files, chunks, blobs the snapshot was the last referrer for) runs
|
||||
automatically. If removing the snapshot's metadata from the destination store
|
||||
fails (for example because the store is unreachable, or the local index holds
|
||||
snapshots and the destination answers that it has no `vaultik-destination.txt`),
|
||||
@@ -600,7 +602,11 @@ only `vaultik-destination.txt` stops such a backup, and only while the local
|
||||
index holds snapshots.
|
||||
|
||||
**Rclone** (`rclone://remote/path`): Uses rclone's 70+ supported cloud
|
||||
providers. Requires rclone to be configured separately (`rclone config`).
|
||||
providers. Requires rclone to be configured separately (`rclone config`). The
|
||||
path after the remote name is relative: rclone resolves it on the remote, for
|
||||
example against the login directory on sftp. A second slash makes it absolute,
|
||||
as in `rclone://remote//srv/backup`. A remote of type `local` needs an absolute
|
||||
path; a relative one is refused.
|
||||
|
||||
An upload cut off part-way leaves nothing under the object's name on S3, which
|
||||
shows an object only once its upload has completed, and on the local filesystem
|
||||
@@ -612,6 +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
|
||||
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
|
||||
|
||||
@@ -331,8 +331,10 @@ know about), which is what 'vaultik prune' does. The command prints the
|
||||
'vaultik prune' invocation to run as a follow-up only when it removed the
|
||||
snapshot's metadata from the destination store, and never under --json.
|
||||
|
||||
An ID that names no snapshot in the local index or on the destination
|
||||
store is an error.
|
||||
The snapshot may be named by its ID or by its remote key, which
|
||||
'snapshot list' prints for a remote-only snapshot. An unambiguous
|
||||
leading part of the key is enough. An identifier that names no snapshot
|
||||
in the local index or on the destination store is an error.
|
||||
|
||||
Use --local-only to skip the remote half (e.g. when you want to forget a
|
||||
snapshot locally without touching the destination store); the snapshot
|
||||
|
||||
@@ -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)
|
||||
}
|
||||
@@ -4,8 +4,10 @@ package snapshot
|
||||
import (
|
||||
"os"
|
||||
"path/filepath"
|
||||
"syscall"
|
||||
"testing"
|
||||
|
||||
"github.com/spf13/afero"
|
||||
"github.com/stretchr/testify/assert"
|
||||
"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.
|
||||
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")
|
||||
}
|
||||
@@ -67,6 +67,7 @@ func provideScannerFactory(
|
||||
IndexAndLockFiles: indexAndLockFiles(cfg.IndexPath, pidlock.Dir()),
|
||||
SkipErrors: params.SkipErrors,
|
||||
PreviousSnapshotID: params.PreviousSnapshotID,
|
||||
BlobUploadRetryDelay: BlobUploadRetryDelay,
|
||||
DeviceNumber: params.DeviceNumber,
|
||||
})
|
||||
}
|
||||
|
||||
@@ -75,6 +75,8 @@ 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;
|
||||
@@ -123,8 +125,16 @@ 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
|
||||
@@ -148,6 +158,10 @@ 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.
|
||||
@@ -259,6 +273,7 @@ func NewScanner(cfg ScannerConfig) *Scanner {
|
||||
progress: progress,
|
||||
skipErrors: cfg.SkipErrors,
|
||||
previousSnapshotID: cfg.PreviousSnapshotID,
|
||||
blobUploadRetryDelay: cfg.BlobUploadRetryDelay,
|
||||
ui: uiw,
|
||||
deviceNumber: deviceNumber,
|
||||
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
|
||||
// file info describes, and false when info carries no stat, as from the
|
||||
// in-memory test filesystem.
|
||||
// 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.
|
||||
func deviceNumberFromStat(info os.FileInfo) (uint64, bool) {
|
||||
stat, ok := info.Sys().(*syscall.Stat_t)
|
||||
if !ok {
|
||||
if !ok || (stat.Dev == 0 && stat.Ino == 0) {
|
||||
return 0, false
|
||||
}
|
||||
|
||||
@@ -1875,10 +1891,7 @@ func (s *Scanner) uploadBlobIfNeeded(
|
||||
s.ui.Hex(finishedBlob.Hash), s.ui.Size(finishedBlob.Compressed),
|
||||
s.ui.Path(destination))
|
||||
|
||||
progressCallback := s.makeUploadProgressCallback(ctx, finishedBlob, startTime)
|
||||
|
||||
err = s.storage.PutWithProgress(ctx, blobPath, blobWithReader.Reader,
|
||||
finishedBlob.Compressed, progressCallback)
|
||||
err = s.putBlob(ctx, blobPath, blobWithReader)
|
||||
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
|
||||
@@ -1922,6 +1935,44 @@ 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.
|
||||
|
||||
@@ -8,6 +8,7 @@ import (
|
||||
"fmt"
|
||||
"io"
|
||||
"os"
|
||||
"path/filepath"
|
||||
"strings"
|
||||
"time"
|
||||
|
||||
@@ -23,6 +24,15 @@ import (
|
||||
// ErrRemoteNotFound is returned when an rclone remote is not configured.
|
||||
var ErrRemoteNotFound = errors.New("rclone remote not found in config")
|
||||
|
||||
// ErrRcloneRelativeLocalPath is returned when the path on an rclone remote
|
||||
// of type local is relative. rclone would resolve it against the working
|
||||
// directory, so the destination would move with it.
|
||||
var ErrRcloneRelativeLocalPath = errors.New(
|
||||
"the path on an rclone remote of type local must be absolute")
|
||||
|
||||
// rcloneLocalBackend is the type of rclone's local disk backend.
|
||||
const rcloneLocalBackend = "local"
|
||||
|
||||
// RcloneStorer implements Storer using rclone's filesystem abstraction.
|
||||
// This allows vaultik to use any of rclone's 70+ supported storage providers.
|
||||
type RcloneStorer struct {
|
||||
@@ -53,6 +63,19 @@ func NewRcloneStorer(ctx context.Context, remote, path string) (*RcloneStorer, e
|
||||
rclonePath += path
|
||||
}
|
||||
|
||||
// A remote rclone cannot find is reported by fs.NewFs below. Only the
|
||||
// backend of what fs.ParseRemote returns is needed here.
|
||||
backend, _, _, _, err := fs.ParseRemote(rclonePath) //nolint:dogsled
|
||||
if err == nil && backend.Name == rcloneLocalBackend && !filepath.IsAbs(path) {
|
||||
example := path
|
||||
if example == "" {
|
||||
example = "path/to/backup"
|
||||
}
|
||||
|
||||
return nil, fmt.Errorf("%w: use rclone://%s//%s",
|
||||
ErrRcloneRelativeLocalPath, remote, example)
|
||||
}
|
||||
|
||||
// On S3, Swift and some other remotes rclone keeps a time of its own in
|
||||
// each object's metadata, which costs one request per object to read.
|
||||
// rclone's use_server_modtime setting makes ModTime the time the
|
||||
|
||||
@@ -436,6 +436,79 @@ func TestNewRcloneStorerReadsRcloneConfigEnv(t *testing.T) {
|
||||
}
|
||||
}
|
||||
|
||||
// useRcloneConfig points rclone at a config file holding contents for the
|
||||
// rest of the test.
|
||||
func useRcloneConfig(t *testing.T, contents string) {
|
||||
t.Helper()
|
||||
|
||||
previous := config.GetConfigPath()
|
||||
|
||||
t.Cleanup(func() { _ = config.SetConfigPath(previous) })
|
||||
|
||||
confFile := filepath.Join(t.TempDir(), "rclone.conf")
|
||||
|
||||
err := os.WriteFile(confFile, []byte(contents), 0o600)
|
||||
if err != nil {
|
||||
t.Fatalf("writing rclone config: %v", err)
|
||||
}
|
||||
|
||||
t.Setenv("RCLONE_CONFIG", confFile)
|
||||
}
|
||||
|
||||
// TestNewRcloneStorerRefusesRelativeLocalPath checks that a relative path
|
||||
// on a remote of type local is refused, with the absolute form in the
|
||||
// error, and that nothing is created under the working directory. rclone
|
||||
// would otherwise resolve the path against the working directory.
|
||||
//
|
||||
//nolint:paralleltest // changes the working directory and the rclone config
|
||||
func TestNewRcloneStorerRefusesRelativeLocalPath(t *testing.T) {
|
||||
useRcloneConfig(t, "[localfs]\ntype = local\n")
|
||||
|
||||
workdir := t.TempDir()
|
||||
t.Chdir(workdir)
|
||||
|
||||
for path, wantInError := range map[string]string{
|
||||
"srv/backup": "rclone://localfs//srv/backup",
|
||||
"": "rclone://localfs//path/to/backup",
|
||||
} {
|
||||
_, err := storage.NewRcloneStorer(context.Background(), "localfs", path)
|
||||
if !errors.Is(err, storage.ErrRcloneRelativeLocalPath) {
|
||||
t.Errorf("path %q: error = %v, want ErrRcloneRelativeLocalPath",
|
||||
path, err)
|
||||
|
||||
continue
|
||||
}
|
||||
|
||||
if !strings.Contains(err.Error(), wantInError) {
|
||||
t.Errorf("path %q: error %q does not show %q",
|
||||
path, err, wantInError)
|
||||
}
|
||||
}
|
||||
|
||||
entries, err := os.ReadDir(workdir)
|
||||
if err != nil {
|
||||
t.Fatalf("reading working directory: %v", err)
|
||||
}
|
||||
|
||||
if len(entries) != 0 {
|
||||
t.Errorf("working directory holds %d entries, want none", len(entries))
|
||||
}
|
||||
}
|
||||
|
||||
// TestNewRcloneStorerKeepsRelativePathOnOtherRemotes checks that a relative
|
||||
// path is accepted on a remote not of type local, where rclone resolves it
|
||||
// on the remote itself, as sftp does against the login directory.
|
||||
//
|
||||
//nolint:paralleltest // changes the process-global rclone config
|
||||
func TestNewRcloneStorerKeepsRelativePathOnOtherRemotes(t *testing.T) {
|
||||
useRcloneConfig(t, "[mem]\ntype = memory\n")
|
||||
|
||||
_, err := storage.NewRcloneStorer(context.Background(), "mem", "backups")
|
||||
if err != nil {
|
||||
t.Errorf("NewRcloneStorer: %v", err)
|
||||
}
|
||||
}
|
||||
|
||||
// TestRcloneListStreamOnS3MakesNoRequestPerObject checks that listing an
|
||||
// rclone S3 remote takes each object's time from the listing itself. By
|
||||
// default rclone reads the time it keeps in each object's metadata, one
|
||||
|
||||
@@ -472,6 +472,68 @@ func TestRemoveSnapshot_NotInLocalIndex(t *testing.T) {
|
||||
assert.Contains(t, out, "Removed snapshot metadata from remote storage")
|
||||
}
|
||||
|
||||
// TestRemoveSnapshot_ByRemoteKey checks that a snapshot only the
|
||||
// destination store holds can be removed by the remote key that
|
||||
// `snapshot list` shows for it, or by a leading part of that key.
|
||||
func TestRemoveSnapshot_ByRemoteKey(t *testing.T) {
|
||||
log.Initialize(log.Config{})
|
||||
t.Parallel()
|
||||
|
||||
remoteKey := snapshot.RemoteSnapshotKey("snapshot-001")
|
||||
|
||||
for name, identifier := range map[string]string{
|
||||
"full key": remoteKey,
|
||||
"leading part": remoteKey[:8],
|
||||
} {
|
||||
t.Run(name, func(t *testing.T) {
|
||||
t.Parallel()
|
||||
|
||||
store := newTestStorer()
|
||||
addManifest(t, store, "snapshot-001", nil)
|
||||
|
||||
tv := vaultik.NewForTesting(store)
|
||||
tv.Repositories = newLocalIndex(t)
|
||||
|
||||
result, err := tv.RemoveSnapshot(identifier,
|
||||
&vaultik.RemoveOptions{Force: true})
|
||||
|
||||
require.NoError(t, err)
|
||||
assert.True(t, result.RemoteRemoved)
|
||||
assert.False(t, store.hasKey(remoteKeyPath("snapshot-001")))
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
// TestRemoveSnapshot_ByRemoteKeyInLocalIndex checks that a snapshot the
|
||||
// local index holds, named by its remote key, is removed from the local
|
||||
// index as well as from the destination store.
|
||||
func TestRemoveSnapshot_ByRemoteKeyInLocalIndex(t *testing.T) {
|
||||
log.Initialize(log.Config{})
|
||||
t.Parallel()
|
||||
|
||||
store := newTestStorer()
|
||||
addManifest(t, store, "snapshot-001", nil)
|
||||
|
||||
// A backup wrote to this destination, so it carries the marker.
|
||||
require.NoError(t, store.Put(context.Background(), markerFile,
|
||||
bytes.NewReader(nil)))
|
||||
|
||||
tv := vaultik.NewForTesting(store)
|
||||
tv.Repositories = newLocalIndex(t, "snapshot-001")
|
||||
|
||||
result, err := tv.RemoveSnapshot(snapshot.RemoteSnapshotKey("snapshot-001"),
|
||||
&vaultik.RemoveOptions{Force: true})
|
||||
|
||||
require.NoError(t, err)
|
||||
assert.True(t, result.RemoteRemoved)
|
||||
assert.False(t, store.hasKey(remoteKeyPath("snapshot-001")))
|
||||
|
||||
snap, err := tv.Repositories.Snapshots.GetByID(context.Background(),
|
||||
"snapshot-001")
|
||||
require.NoError(t, err)
|
||||
assert.Nil(t, snap)
|
||||
}
|
||||
|
||||
// TestRemoveSnapshot_NotInLocalIndexDeleteFails checks that removing a
|
||||
// snapshot only the destination store holds fails when its metadata
|
||||
// cannot be deleted there, under --force and under --json: nothing was
|
||||
|
||||
@@ -31,9 +31,10 @@ var (
|
||||
errPathsNotInSnapshot = errors.New("requested path(s) not in the snapshot")
|
||||
errFilesFailedVerify = errors.New("files failed verification")
|
||||
errDecryptionKeyRequired = errors.New(
|
||||
"age secret key is missing; set it in the " +
|
||||
"VAULTIK_AGE_SECRET_KEY environment variable or the " +
|
||||
"age_secret_key config file field")
|
||||
"decryption key required\n\n" +
|
||||
"Set the VAULTIK_AGE_SECRET_KEY environment variable to your " +
|
||||
"age private key file:\n" +
|
||||
" export VAULTIK_AGE_SECRET_KEY=\"$(cat vaultik_backup_private_key.txt)\"")
|
||||
// errInvalidAgeSecretKey is returned when the configured key does not
|
||||
// parse as any age identity. It names the source but never the value,
|
||||
// which is secret, so the message is safe to print and log.
|
||||
|
||||
@@ -106,23 +106,3 @@ func TestRestoreIdentitiesMissingKey(t *testing.T) {
|
||||
_, err := v.restoreIdentities()
|
||||
require.ErrorIs(t, err, errDecryptionKeyRequired)
|
||||
}
|
||||
|
||||
// TestMissingKeyErrorsNameBothSources asserts restore and deep verify
|
||||
// return the same missing-key error, whose text names both places the key
|
||||
// can be set: the VAULTIK_AGE_SECRET_KEY environment variable first since
|
||||
// it is preferred, then the age_secret_key config file field.
|
||||
func TestMissingKeyErrorsNameBothSources(t *testing.T) {
|
||||
t.Parallel()
|
||||
|
||||
const want = "age secret key is missing; set it in " +
|
||||
"the VAULTIK_AGE_SECRET_KEY environment variable or the " +
|
||||
"age_secret_key config file field"
|
||||
|
||||
v := &Vaultik{Config: &config.Config{}}
|
||||
|
||||
_, err := v.restoreIdentities()
|
||||
require.EqualError(t, err, want)
|
||||
|
||||
err = v.RunDeepVerify("any-snapshot", &VerifyOptions{})
|
||||
require.EqualError(t, err, want)
|
||||
}
|
||||
@@ -1467,7 +1467,8 @@ func (v *Vaultik) RemoveSnapshot(
|
||||
return result, err
|
||||
}
|
||||
|
||||
inLocalIndex, err := v.checkSnapshotExists(snapshotID, opts.LocalOnly)
|
||||
snapshotID, remoteKey, inLocalIndex, err := v.findSnapshotToRemove(
|
||||
snapshotID, opts.LocalOnly)
|
||||
if err != nil {
|
||||
return result, err
|
||||
}
|
||||
@@ -1498,7 +1499,7 @@ func (v *Vaultik) RemoveSnapshot(
|
||||
}
|
||||
|
||||
result.RemoteRemoved, err = v.removeSnapshotRemote(
|
||||
snapshotID, inLocalIndex, markerErr, opts)
|
||||
snapshotID, remoteKey, inLocalIndex, markerErr, opts)
|
||||
if err != nil {
|
||||
return result, err
|
||||
}
|
||||
@@ -1530,6 +1531,41 @@ func (v *Vaultik) RemoveSnapshot(
|
||||
return result, nil
|
||||
}
|
||||
|
||||
// findSnapshotToRemove returns the ID of the snapshot that identifier
|
||||
// names, its remote key, and whether the local index holds it. A remote
|
||||
// key, or the leading part of one, is resolved on the destination store;
|
||||
// when the local index holds the snapshot with that key, its ID is
|
||||
// returned, so it is removed from both.
|
||||
func (v *Vaultik) findSnapshotToRemove(
|
||||
identifier string, localOnly bool,
|
||||
) (string, string, bool, error) {
|
||||
if !isRemoteKeyOrPrefix(identifier) || localOnly {
|
||||
inLocalIndex, err := v.checkSnapshotExists(identifier, localOnly)
|
||||
|
||||
return identifier, snapshot.RemoteSnapshotKey(identifier),
|
||||
inLocalIndex, err
|
||||
}
|
||||
|
||||
remoteKey, err := v.resolveSnapshotRemoteKey(identifier)
|
||||
if err != nil {
|
||||
return "", "", false, err
|
||||
}
|
||||
|
||||
localIDs, err := v.localSnapshotIDs()
|
||||
if err != nil {
|
||||
return "", "", false, fmt.Errorf(
|
||||
"looking up snapshot in local index: %w", err)
|
||||
}
|
||||
|
||||
for _, id := range localIDs {
|
||||
if snapshot.RemoteSnapshotKey(id) == remoteKey {
|
||||
return id, remoteKey, true, nil
|
||||
}
|
||||
}
|
||||
|
||||
return identifier, remoteKey, false, nil
|
||||
}
|
||||
|
||||
// checkSnapshotExists returns errSnapshotNotFound when the local index
|
||||
// has no row for snapshotID and, unless localOnly is set, the
|
||||
// destination store has no metadata for it either. inLocalIndex reports
|
||||
@@ -1638,8 +1674,8 @@ func (v *Vaultik) confirmRemoveSnapshot(snapshotID string, opts *RemoveOptions)
|
||||
return true
|
||||
}
|
||||
|
||||
// removeSnapshotRemote strips the snapshot's metadata from the
|
||||
// destination store. It returns true only when the delete finished
|
||||
// removeSnapshotRemote strips the snapshot's metadata, under remoteKey,
|
||||
// from the destination store. It returns true only when the delete finished
|
||||
// without an error and removed at least one object; under LocalOnly it
|
||||
// does nothing. markerErr is the result of checkDestinationMarker; when
|
||||
// it is set, nothing is deleted and it is the failure. When the snapshot
|
||||
@@ -1651,7 +1687,7 @@ func (v *Vaultik) confirmRemoveSnapshot(snapshotID string, opts *RemoveOptions)
|
||||
// (`vaultik prune` never removes snapshot metadata that has its
|
||||
// manifest).
|
||||
func (v *Vaultik) removeSnapshotRemote(
|
||||
snapshotID string, inLocalIndex bool, markerErr error,
|
||||
snapshotID, remoteKey string, inLocalIndex bool, markerErr error,
|
||||
opts *RemoveOptions,
|
||||
) (bool, error) {
|
||||
if opts.LocalOnly {
|
||||
@@ -1665,8 +1701,7 @@ func (v *Vaultik) removeSnapshotRemote(
|
||||
|
||||
err := markerErr
|
||||
if err == nil {
|
||||
deleted, err = v.deleteRemoteSnapshotByKey(
|
||||
snapshot.RemoteSnapshotKey(snapshotID))
|
||||
deleted, err = v.deleteRemoteSnapshotByKey(remoteKey)
|
||||
}
|
||||
|
||||
if err != nil && !inLocalIndex {
|
||||
|
||||
@@ -4,6 +4,7 @@ import (
|
||||
"context"
|
||||
"maps"
|
||||
"path/filepath"
|
||||
"strings"
|
||||
"testing"
|
||||
|
||||
"github.com/spf13/afero"
|
||||
@@ -12,6 +13,7 @@ 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"
|
||||
)
|
||||
|
||||
@@ -68,3 +70,55 @@ 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)
|
||||
}
|
||||
@@ -163,6 +163,11 @@ func (v *Vaultik) StartOperation(fn func()) func(context.Context) bool {
|
||||
}
|
||||
}
|
||||
|
||||
// CanDecrypt returns true if this Vaultik instance has decryption capabilities
|
||||
func (v *Vaultik) CanDecrypt() bool {
|
||||
return v.Config.AgeSecretKey != ""
|
||||
}
|
||||
|
||||
// GetFilesystem returns the filesystem instance used by Vaultik
|
||||
//
|
||||
//nolint:ireturn // afero.Fs is the filesystem abstraction by design
|
||||
|
||||
@@ -23,6 +23,8 @@ import (
|
||||
// Sentinel errors for snapshot verification failures.
|
||||
var (
|
||||
errVerificationFailed = errors.New("verification failed")
|
||||
errSecretKeyRequired = errors.New(
|
||||
"VAULTIK_AGE_SECRET_KEY not set; required for deep verification")
|
||||
errChunksOutOfOrder = errors.New("chunks out of order")
|
||||
errChunkHashMismatch = errors.New("chunk hash mismatch")
|
||||
errNegativeChunkLength = errors.New("chunk length is negative")
|
||||
@@ -104,9 +106,13 @@ func (v *Vaultik) RunDeepVerify(snapshotID string, opts *VerifyOptions) error {
|
||||
Mode: "deep",
|
||||
}
|
||||
|
||||
if !v.CanDecrypt() {
|
||||
return v.deepVerifyFailure(result, opts,
|
||||
errSecretKeyRequired.Error(), errSecretKeyRequired)
|
||||
}
|
||||
|
||||
// Parse the age secret key once, the same way restore does, and reuse
|
||||
// the identities for the database and every blob. A missing key fails
|
||||
// here, before anything is downloaded.
|
||||
// the identities for the database and every blob.
|
||||
identities, err := v.restoreIdentities()
|
||||
if err != nil {
|
||||
return v.deepVerifyFailure(result, opts, err.Error(), err)
|
||||
|
||||
Reference in new issue
Block a user