Compare commits
1
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
1954080faf |
No files matched your search
+1205
-3
File diff suppressed because it is too large.
Load diff
@@ -22,10 +22,6 @@ var errBlobHashMismatch = errors.New("blob hash mismatch")
|
||||
var errBlobNotFullyRead = errors.New(
|
||||
"blob closed before fully read; hash not verified")
|
||||
|
||||
// errWrongPrivateKeyForBlob is returned when the configured key parses
|
||||
// but is not one of the keys a blob was encrypted to.
|
||||
var errWrongPrivateKeyForBlob = errors.New("cannot decrypt this blob")
|
||||
|
||||
// hashVerifyReader wraps a blobgen.Reader and verifies the double-SHA-256 hash
|
||||
// of decrypted plaintext when Close is called. It reuses the hash that
|
||||
// blobgen.Reader already computes internally via its TeeReader, avoiding
|
||||
@@ -91,14 +87,10 @@ func (v *Vaultik) FetchAndDecryptBlob(
|
||||
return nil, err
|
||||
}
|
||||
|
||||
reader, err := v.newBlobReader(rc, identities)
|
||||
reader, err := blobgen.NewReader(rc, identities...)
|
||||
if err != nil {
|
||||
_ = rc.Close()
|
||||
|
||||
if errors.Is(err, errWrongPrivateKeyForBlob) {
|
||||
return nil, err
|
||||
}
|
||||
|
||||
return nil, fmt.Errorf("creating blob reader: %w", err)
|
||||
}
|
||||
|
||||
@@ -110,28 +102,6 @@ func (v *Vaultik) FetchAndDecryptBlob(
|
||||
}, nil
|
||||
}
|
||||
|
||||
// newBlobReader opens the decrypting reader for a blob. When none of the
|
||||
// identities can decrypt it, the error says in plain words that the
|
||||
// configured private key is not one of the keys the blob was encrypted
|
||||
// to and names where the key was configured.
|
||||
func (v *Vaultik) newBlobReader(
|
||||
r io.Reader, identities []age.Identity,
|
||||
) (*blobgen.Reader, error) {
|
||||
blobReader, err := blobgen.NewReader(r, identities...)
|
||||
|
||||
if _, ok := errors.AsType[*age.NoIdentityMatchError](err); ok {
|
||||
return nil, fmt.Errorf(
|
||||
"%w: the private key in %s is not one of the keys the blob was encrypted to",
|
||||
errWrongPrivateKeyForBlob, v.Config.AgeSecretKeySourceName())
|
||||
}
|
||||
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
|
||||
return blobReader, nil
|
||||
}
|
||||
|
||||
// FetchBlob downloads a blob and returns a reader for the encrypted data.
|
||||
// The reader is closed as soon as ctx is cancelled, which ends a read
|
||||
// blocked inside it. A storage error is returned as is: restore and deep
|
||||
|
||||
@@ -7,7 +7,6 @@ import (
|
||||
"os"
|
||||
"path/filepath"
|
||||
"strings"
|
||||
"sync"
|
||||
"testing"
|
||||
|
||||
"github.com/spf13/afero"
|
||||
@@ -25,28 +24,19 @@ import (
|
||||
// that is not plugged in, cannot be listed. It is not an empty store, so
|
||||
// no command may conclude from it that the local snapshots are gone.
|
||||
|
||||
// newFileDestinationVaultik writes the fault source tree and returns a
|
||||
// Vaultik that backs it up to a file:// destination at storeDir.
|
||||
// newFileDestinationVaultik returns a Vaultik that backs up the
|
||||
// snapshot named "first" to a file:// destination at storeDir.
|
||||
func newFileDestinationVaultik(
|
||||
ctx context.Context, t *testing.T, storeDir string,
|
||||
) (*vaultik.Vaultik, *database.Repositories) {
|
||||
t.Helper()
|
||||
|
||||
osFs := afero.NewOsFs()
|
||||
tempDir := t.TempDir()
|
||||
dataDir := filepath.Join(tempDir, "src")
|
||||
writeFaultSourceTree(t, afero.NewOsFs(), dataDir)
|
||||
dbPath := filepath.Join(tempDir, "index.sqlite")
|
||||
|
||||
return openFileDestinationVaultik(ctx, t, storeDir, dataDir,
|
||||
filepath.Join(tempDir, "index.sqlite"))
|
||||
}
|
||||
|
||||
// openFileDestinationVaultik returns a Vaultik that backs up dataDir to a
|
||||
// file:// destination at storeDir, with its local index at dbPath. The
|
||||
// index is closed when the test ends.
|
||||
func openFileDestinationVaultik(
|
||||
ctx context.Context, t *testing.T, storeDir, dataDir, dbPath string,
|
||||
) (*vaultik.Vaultik, *database.Repositories) {
|
||||
t.Helper()
|
||||
writeFaultSourceTree(t, osFs, dataDir)
|
||||
|
||||
store, err := storage.NewFileStorer(storeDir)
|
||||
require.NoError(t, err)
|
||||
@@ -58,84 +48,22 @@ func openFileDestinationVaultik(
|
||||
repos := database.NewRepositories(db)
|
||||
cfg := changedFileConfig(dataDir, dbPath)
|
||||
|
||||
return newBackupVaultik(ctx, cfg, store, repos, db, afero.NewOsFs()), repos
|
||||
}
|
||||
|
||||
// firstBackup is one backup of the snapshot named "first" to a file://
|
||||
// destination. dir holds its source tree in src, its store in store and
|
||||
// its closed local index in index/index.sqlite. The first test that
|
||||
// needs it makes it, and TestMain removes it. Every test that copies it
|
||||
// backs up the same source tree, so no test may change that tree.
|
||||
//
|
||||
//nolint:gochecknoglobals // made once and shared by the tests that copy it
|
||||
var firstBackup struct {
|
||||
once sync.Once
|
||||
dir string
|
||||
ready bool
|
||||
}
|
||||
|
||||
// TestMain removes firstBackup once every test has run.
|
||||
func TestMain(m *testing.M) {
|
||||
code := m.Run()
|
||||
|
||||
_ = os.RemoveAll(firstBackup.dir)
|
||||
|
||||
os.Exit(code)
|
||||
}
|
||||
|
||||
// makeFirstBackup writes the fault source tree and backs it up as the
|
||||
// snapshot named "first", all in a new directory that it records in
|
||||
// firstBackup.
|
||||
func makeFirstBackup(ctx context.Context, t *testing.T) {
|
||||
t.Helper()
|
||||
|
||||
dir, err := os.MkdirTemp("", "vaultik-first-backup-")
|
||||
require.NoError(t, err)
|
||||
|
||||
firstBackup.dir = dir
|
||||
storeDir := filepath.Join(dir, "store")
|
||||
dataDir := filepath.Join(dir, "src")
|
||||
indexDir := filepath.Join(dir, "index")
|
||||
|
||||
require.NoError(t, os.Mkdir(storeDir, 0o750))
|
||||
require.NoError(t, os.Mkdir(indexDir, 0o750))
|
||||
writeFaultSourceTree(t, afero.NewOsFs(), dataDir)
|
||||
|
||||
v, _ := openFileDestinationVaultik(ctx, t, storeDir, dataDir,
|
||||
filepath.Join(indexDir, "index.sqlite"))
|
||||
require.NoError(t, backUp(v, "first"))
|
||||
require.NoError(t, v.DB.Close())
|
||||
|
||||
firstBackup.ready = true
|
||||
return newBackupVaultik(ctx, cfg, store, repos, db, osFs), repos
|
||||
}
|
||||
|
||||
// backUpToFileDestination creates the directory storeDir, as a user must
|
||||
// before the first backup, and returns a Vaultik whose file://
|
||||
// destination there holds a backup of the snapshot named "first". The
|
||||
// store and the local index are copies of firstBackup's, which is faster
|
||||
// than backing up in every test. The returned Vaultik backs up a source
|
||||
// tree shared with every other caller, so no test may change that tree.
|
||||
// Everything the returned Vaultik prints after the backup goes to the
|
||||
// returned buffer.
|
||||
// before the first backup, and backs up the snapshot named "first" to a
|
||||
// file:// destination there. Everything the returned Vaultik prints
|
||||
// after the backup goes to the returned buffer.
|
||||
func backUpToFileDestination(
|
||||
ctx context.Context, t *testing.T, storeDir string,
|
||||
) (*vaultik.Vaultik, *database.Repositories, *bytes.Buffer) {
|
||||
t.Helper()
|
||||
|
||||
firstBackup.once.Do(func() { makeFirstBackup(ctx, t) })
|
||||
require.True(t, firstBackup.ready, "another test failed to make firstBackup")
|
||||
|
||||
require.NoError(t, os.MkdirAll(storeDir, 0o750))
|
||||
require.NoError(t, os.CopyFS(storeDir,
|
||||
os.DirFS(filepath.Join(firstBackup.dir, "store"))))
|
||||
|
||||
indexDir := t.TempDir()
|
||||
require.NoError(t, os.CopyFS(indexDir,
|
||||
os.DirFS(filepath.Join(firstBackup.dir, "index"))))
|
||||
|
||||
v, repos := openFileDestinationVaultik(ctx, t, storeDir,
|
||||
filepath.Join(firstBackup.dir, "src"),
|
||||
filepath.Join(indexDir, "index.sqlite"))
|
||||
v, repos := newFileDestinationVaultik(ctx, t, storeDir)
|
||||
require.NoError(t, backUp(v, "first"))
|
||||
|
||||
out := &bytes.Buffer{}
|
||||
v.Stdout = out
|
||||
|
||||
@@ -46,11 +46,11 @@ import (
|
||||
// slice out a few KB — currently the dominant cost in restore.
|
||||
//
|
||||
// The test deliberately constructs an adversarial scenario: three
|
||||
// blobs A/B/C of five 64 KiB chunks each, nine files distributed across
|
||||
// them, and path-ordered names that interleave the blobs (a1, b1, c1,
|
||||
// a2, b2, c2, …) so naive path-order processing would touch every blob
|
||||
// before finishing any of them.
|
||||
// localitySource is one 64 KiB fixture file used by the locality test.
|
||||
// blobs A/B/C of ~6 MB each, nine files distributed across them, and
|
||||
// path-ordered names that interleave the blobs (a1, b1, c1, a2, b2,
|
||||
// c2, …) so naive path-order processing would touch every blob before
|
||||
// finishing any of them.
|
||||
// localitySource is one 1 MiB fixture file used by the locality test.
|
||||
type localitySource struct {
|
||||
path string
|
||||
data []byte
|
||||
@@ -65,10 +65,10 @@ type localityCopy struct {
|
||||
|
||||
// localitySourceBytes is the size of each source file of the locality
|
||||
// fixture.
|
||||
const localitySourceBytes = 64 * 1024
|
||||
const localitySourceBytes = 1024 * 1024
|
||||
|
||||
// buildLocalityFixture writes the adversarial source layout described
|
||||
// in TestRestoreLocalityAndReadAt: 15 sources of 64 KiB each (which the
|
||||
// in TestRestoreLocalityAndReadAt: 15 sources of 1 MiB each (which the
|
||||
// backup packs into 3 blobs of 5 chunks) plus 9 interleaved-name copies
|
||||
// (3 per blob group).
|
||||
func buildLocalityFixture(
|
||||
|
||||
@@ -27,10 +27,10 @@ import (
|
||||
// TestRestoreSweeperEvictsBlobs exercises the reference-counted blob
|
||||
// disk cache eviction during restore.
|
||||
//
|
||||
// The scenario: 30 unique 128 KiB random files plus 10 duplicates of
|
||||
// those (40 files total, 3.75 MiB of unique content) get backed up with
|
||||
// a 1 MiB blob_size_limit. After backup the snapshot's encrypted blobs
|
||||
// are restored through Vaultik.Restore, and per-key Get counts on the
|
||||
// The scenario: 30 unique 1 MB random files plus 10 duplicates of those
|
||||
// (40 files total, 30 MB of unique content) get backed up with a 10 MB
|
||||
// blob_size_limit. After backup the snapshot's encrypted blobs are
|
||||
// restored through Vaultik.Restore, and per-key Get counts on the
|
||||
// storage layer are recorded. Each blob in the snapshot MUST be
|
||||
// downloaded exactly once — re-downloads would mean the sweeper either
|
||||
// evicted a blob that was still needed (LRU regression) or that the
|
||||
@@ -41,7 +41,7 @@ import (
|
||||
// original AND every duplicate referencing its chunks have been
|
||||
// restored.
|
||||
// buildSweeperFixture writes the source layout for the sweeper test: 30
|
||||
// unique 128 KiB random files plus 10 duplicates of a random subset. The
|
||||
// unique 1 MB random files plus 10 duplicates of a random subset. The
|
||||
// PRNG seed is fixed so failures are reproducible; the entropy is what
|
||||
// matters here — the FastCDC chunker needs realistic-looking data to
|
||||
// pick chunk boundaries naturally. Returns the expected content by
|
||||
@@ -51,7 +51,7 @@ func buildSweeperFixture(
|
||||
) map[string][]byte {
|
||||
t.Helper()
|
||||
|
||||
const fileSize = 128 * 1024
|
||||
const fileSize = 1 * 1024 * 1024
|
||||
|
||||
rng := rand.New(rand.NewSource(42)) //nolint:gosec // G404: fixture data only
|
||||
|
||||
@@ -159,7 +159,7 @@ func runSweeperBackup(
|
||||
require.NoError(t, err)
|
||||
require.Equal(t, uniqueFiles+duplicateFiles, scanResult.FilesScanned)
|
||||
require.Greater(t, scanResult.BlobsCreated, 1,
|
||||
"3.75 MiB of unique data at 1 MiB blob size should yield multiple blobs")
|
||||
"30 MB of unique data at 10 MB blob size should yield multiple blobs")
|
||||
|
||||
require.NoError(t, sm.CompleteSnapshot(ctx, snapshotID))
|
||||
require.NoError(t, sm.ExportSnapshotMetadata(ctx, dbPath, snapshotID))
|
||||
@@ -199,8 +199,8 @@ func TestRestoreSweeperEvictsBlobs(t *testing.T) {
|
||||
|
||||
expected := buildSweeperFixture(t, fs, dataDir, uniqueFiles, duplicateFiles)
|
||||
|
||||
chunkSize := int64(16 * 1024)
|
||||
maxBlobSize := int64(1024 * 1024)
|
||||
chunkSize := int64(64 * 1024)
|
||||
maxBlobSize := int64(10 * 1024 * 1024)
|
||||
|
||||
storer, err := storage.NewFileStorer(storeDir)
|
||||
require.NoError(t, err)
|
||||
|
||||
@@ -4,8 +4,6 @@ import (
|
||||
"bytes"
|
||||
"context"
|
||||
"io"
|
||||
"path"
|
||||
"path/filepath"
|
||||
"testing"
|
||||
|
||||
"filippo.io/age"
|
||||
@@ -13,7 +11,6 @@ import (
|
||||
"github.com/stretchr/testify/require"
|
||||
"sneak.berlin/go/vaultik/internal/blobgen"
|
||||
"sneak.berlin/go/vaultik/internal/config"
|
||||
"sneak.berlin/go/vaultik/internal/log"
|
||||
"sneak.berlin/go/vaultik/internal/snapshot"
|
||||
"sneak.berlin/go/vaultik/internal/ui"
|
||||
"sneak.berlin/go/vaultik/internal/vaultik"
|
||||
@@ -77,85 +74,3 @@ func TestWrongPrivateKeyError(t *testing.T) {
|
||||
err = v.RunDeepVerify(snapshotID, &vaultik.VerifyOptions{Deep: true})
|
||||
require.EqualError(t, err, want)
|
||||
}
|
||||
|
||||
// TestWrongPrivateKeyForBlobError backs up a file, then backs it up again
|
||||
// from an empty local index with a second recipient added. The second
|
||||
// snapshot reuses the stored blob, which stays encrypted to the first
|
||||
// recipient only. With only the added key configured, restore and deep
|
||||
// verify read the database but fail on the blob with one plain sentence
|
||||
// that names where the key was configured.
|
||||
func TestWrongPrivateKeyForBlobError(t *testing.T) {
|
||||
log.Initialize(log.Config{})
|
||||
t.Parallel()
|
||||
|
||||
fs := afero.NewOsFs()
|
||||
tempDir := t.TempDir()
|
||||
dataDir := filepath.Join(tempDir, "source")
|
||||
dataPath := filepath.Join(dataDir, "data.bin")
|
||||
storeDir := t.TempDir()
|
||||
secondDBPath := filepath.Join(tempDir, "second.sqlite")
|
||||
|
||||
chunkSize := int64(64 * 1024)
|
||||
maxBlobSize := int64(512 * 1024)
|
||||
|
||||
require.NoError(t, fs.MkdirAll(dataDir, 0o755))
|
||||
require.NoError(t, afero.WriteFile(fs, dataPath,
|
||||
bytesPattern("key-", int(chunkSize)), 0o644))
|
||||
|
||||
ctx := context.Background()
|
||||
|
||||
runFileStorageBackup(ctx, t, fs, dataDir, storeDir,
|
||||
filepath.Join(tempDir, "first.sqlite"), chunkSize, maxBlobSize)
|
||||
|
||||
env := setupDedupBackupEnv(
|
||||
ctx, t, fs, storeDir, secondDBPath, chunkSize, maxBlobSize)
|
||||
|
||||
defer func() { _ = env.db.Close() }()
|
||||
|
||||
addedKey, err := age.GenerateX25519Identity()
|
||||
require.NoError(t, err)
|
||||
|
||||
env.cfg.AgeRecipients = append(env.cfg.AgeRecipients,
|
||||
addedKey.Recipient().String())
|
||||
|
||||
snapshotID, result := runDedupSnapshot(ctx, t, env.sm, env.makeScanner(),
|
||||
env.cfg.Hostname, "second", dataDir, secondDBPath)
|
||||
require.Zero(t, result.BlobsUploaded,
|
||||
"the second backup should reuse the stored blob")
|
||||
|
||||
require.NoError(t, env.db.Close())
|
||||
|
||||
blobKeys, err := env.storer.List(ctx, "blobs/")
|
||||
require.NoError(t, err)
|
||||
require.Len(t, blobKeys, 1)
|
||||
|
||||
blobHash := path.Base(blobKeys[0])
|
||||
|
||||
env.cfg.AgeSecretKey = addedKey.String()
|
||||
|
||||
v := &vaultik.Vaultik{
|
||||
Config: env.cfg,
|
||||
Storage: env.storer,
|
||||
Fs: fs,
|
||||
Stdout: io.Discard,
|
||||
Stderr: io.Discard,
|
||||
UI: ui.NewWithColor(io.Discard, false),
|
||||
}
|
||||
v.SetContext(ctx)
|
||||
|
||||
const sentence = "cannot decrypt this blob: the private key in " +
|
||||
"age_secret_key is not one of the keys the blob was encrypted to"
|
||||
|
||||
// Restore names the blob by the first 16 characters of its hash.
|
||||
err = v.Restore(&vaultik.RestoreOptions{
|
||||
SnapshotID: snapshotID,
|
||||
TargetDir: t.TempDir(),
|
||||
})
|
||||
require.EqualError(t, err, "restoring "+dataPath+": downloading blob "+
|
||||
blobHash[:16]+": "+sentence+
|
||||
" (pass --skip-errors to continue past restore failures)")
|
||||
|
||||
err = v.RunDeepVerify(snapshotID, &vaultik.VerifyOptions{Deep: true})
|
||||
require.EqualError(t, err,
|
||||
"blob "+blobHash+" verification failed: "+sentence)
|
||||
}
|
||||
@@ -187,17 +187,6 @@ func (e *listEnv) addRemoteRawTimestamp(
|
||||
t.Helper()
|
||||
|
||||
remoteKey := snapshot.RemoteSnapshotKey(snapshotID)
|
||||
e.putRemoteManifest(t, remoteKey,
|
||||
encodeRemoteManifest(t, remoteKey, timestamp))
|
||||
|
||||
return remoteKey
|
||||
}
|
||||
|
||||
// encodeRemoteManifest returns the encoded manifest of a one-blob
|
||||
// snapshot whose remote key is remoteKey.
|
||||
func encodeRemoteManifest(t *testing.T, remoteKey, timestamp string) []byte {
|
||||
t.Helper()
|
||||
|
||||
manifest := &snapshot.Manifest{
|
||||
// Note: the hashed key, never the human ID. That is precisely
|
||||
// why a remote-only snapshot cannot be named.
|
||||
@@ -213,17 +202,11 @@ func encodeRemoteManifest(t *testing.T, remoteKey, timestamp string) []byte {
|
||||
data, err := snapshot.EncodeManifest(manifest, 3)
|
||||
require.NoError(t, err)
|
||||
|
||||
return data
|
||||
}
|
||||
|
||||
// putRemoteManifest stores an encoded manifest on the destination store
|
||||
// under remoteKey.
|
||||
func (e *listEnv) putRemoteManifest(t *testing.T, remoteKey string, data []byte) {
|
||||
t.Helper()
|
||||
|
||||
err := e.store.Put(context.Background(),
|
||||
err = e.store.Put(context.Background(),
|
||||
"metadata/"+remoteKey+"/manifest.json.zst", bytes.NewReader(data))
|
||||
require.NoError(t, err)
|
||||
|
||||
return remoteKey
|
||||
}
|
||||
|
||||
// Fixtures shared across the listing tests.
|
||||
@@ -808,17 +791,9 @@ func TestListSnapshots_JSONReportsTruncation(t *testing.T) {
|
||||
|
||||
timestamp := time.Date(2026, 3, 2, 11, 22, 33, 0, time.UTC)
|
||||
|
||||
// One past the cap, so exactly one snapshot is omitted. The listing
|
||||
// names a snapshot by the key its manifest is stored under, never by
|
||||
// the manifest's own ID. So all of them share one encoded manifest:
|
||||
// encoding 1001 took seconds.
|
||||
data := encodeRemoteManifest(t,
|
||||
snapshot.RemoteSnapshotKey("otherhost_bulk"),
|
||||
timestamp.Format(time.RFC3339))
|
||||
|
||||
// One past the cap, so exactly one snapshot is omitted.
|
||||
for i := range maxRemoteOnlyRowsForTest + 1 {
|
||||
env.putRemoteManifest(t, snapshot.RemoteSnapshotKey(
|
||||
fmt.Sprintf("otherhost_bulk_%04d", i)), data)
|
||||
env.addRemote(t, fmt.Sprintf("otherhost_bulk_%04d", i), timestamp)
|
||||
}
|
||||
|
||||
stderr := captureProcessStderr(t, func() {
|
||||
|
||||
@@ -430,11 +430,7 @@ func (v *Vaultik) verifyBlob(
|
||||
// the plaintext as it is read. A blob's hash — its remote name — is the
|
||||
// double SHA-256 of that plaintext (see blobgen.DoubleSHA256), not of the
|
||||
// encrypted bytes.
|
||||
blobReader, err := v.newBlobReader(reader, identities)
|
||||
if errors.Is(err, errWrongPrivateKeyForBlob) {
|
||||
return err
|
||||
}
|
||||
|
||||
blobReader, err := blobgen.NewReader(reader, identities...)
|
||||
if err != nil {
|
||||
return fmt.Errorf("failed to create blob reader: %w", err)
|
||||
}
|
||||
|
||||
Reference in new issue
Block a user