1 Commits
Author SHA1 Message Date
sneak b07dc44905 Exit as interrupted when Ctrl-C lands during a local index write (closes #301)
check / check (push) Canceled after 0s
Once the run's context is cancelled, database/sql rolls an open
transaction back itself, so the rollback in WithTx returned
sql.ErrTxDone. WithTx treated any rollback error as fatal and called
os.Exit(1): an interrupted backup printed "FATAL: failed to rollback
transaction", exited 1 instead of 130 and skipped its deferred cleanup.

WithTx now ignores sql.ErrTxDone from the rollback and returns the
body's error. A rollback that really fails is returned together with
the body's error instead of ending the process. On a panic the
rollback error is dropped and the panic carries on.

Model: opus-5-5
2026-10-13 05:23:05 +00:00
9 changed files with 31 additions and 263 deletions
+2 -6
View File
@@ -286,9 +286,7 @@ needed.
remove orphaned blobs from remote storage. By default keeps only the latest
snapshot per name; use `--keep-newer-than` for a rolling window.
* `--keep-newer-than <duration>`: With `--prune`, keep snapshots newer than
this duration instead of only the latest (e.g. `4w`, `30d`, `6mo`, `1y`).
Without `--prune`, or with a value that is not a valid duration, the
command fails before the backup starts.
this duration instead of only the latest (e.g. `4w`, `30d`, `6mo`, `1y`)
**`snapshot list`**: Show every snapshot known to this host — the union
of the local index and the backup destination store — with timestamps
@@ -403,9 +401,7 @@ orphaned blob figures are reported as unknown; `--json` gives them as
`null`, lists the remote key of each unreadable manifest in
`unreadable_manifests` and counts the manifests under skipped names in
`skipped_manifest_count`. An unreadable manifest also leaves its
snapshot's blob 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.
snapshot's blob count and blob size unknown, `null` in `--json`.
* `--json`: Output as JSON
**`remote nuke`**: Delete every snapshot's metadata and every blob from the
+9 -7
View File
@@ -22,13 +22,15 @@ the tag exists and is exercised; what is left is merging `next` to
# Completed Steps
- 2026-10-13: Stopped `remote info` counting a file under `blobs/` that
is not a blob as an orphaned blob
([issue #295](https://git.eeqj.de/sneak/vaultik/issues/295)). A stray
file such as `.DS_Store` was reported as an orphaned blob and the
report advised running `prune`, which skips such a file and deleted
nothing. `remote info` now takes its blob list from the same listing
`prune` uses, in the table and in `--json`.
- 2026-10-13: Made Ctrl-C or SIGTERM during a local index write end the
command as interrupted
([issue #301](https://git.eeqj.de/sneak/vaultik/issues/301)). Once the
run is cancelled, `database/sql` rolls an open transaction back itself,
so the rollback in `WithTx` failed with `sql.ErrTxDone` and the process
exited 1 with `FATAL: failed to rollback transaction`, skipping the
interrupted exit and message. That result is no longer an error, and a
rollback that does fail is returned with the transaction's error
instead of ending the process.
- 2026-10-13: Made `snapshot remove` fail for a snapshot that does not
exist ([issue #293](https://git.eeqj.de/sneak/vaultik/issues/293)).
@@ -1,108 +0,0 @@
package cli //nolint:testpackage // shares runEntry and the hermetic config helpers
import (
"os"
"path/filepath"
"strings"
"testing"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
)
// Flags of `snapshot create` used to build argument vectors below.
const (
flagPrune = "--prune"
flagKeepNewerThan = "--keep-newer-than"
)
// TestEntrySnapshotCreateRejectsKeepNewerThanBeforeBackup checks that a
// --keep-newer-than the post-backup prune could not use stops `snapshot
// create` before the backup: the command fails and the destination
// store stays empty. It used to be read only by the prune, after the
// snapshot was uploaded, and without --prune it was ignored.
//
//nolint:paralleltest // replaces os.Args, os.Stdout, os.Stderr and the xdg globals
func TestEntrySnapshotCreateRejectsKeepNewerThanBeforeBackup(t *testing.T) {
for _, testCase := range []struct {
name string
args []string
}{
{
name: "decimal in a day count",
args: []string{flagPrune, flagKeepNewerThan, "1.5d"},
},
{
name: "unknown unit",
args: []string{flagPrune, flagKeepNewerThan, "4x"},
},
{
name: "without --prune",
args: []string{flagKeepNewerThan, "4w"},
},
} {
t.Run(testCase.name, func(t *testing.T) {
configPath, storeDir := writeBackupConfig(t)
code, _, _ := runEntry(t, append(
[]string{flagConfig, configPath, cmdSnapshot, cmdCreate},
testCase.args...)...)
assert.Equal(t, 1, code)
stored, err := os.ReadDir(storeDir)
require.NoError(t, err)
assert.Empty(t, stored, "nothing may be uploaded")
})
}
}
// TestEntrySnapshotCreateReportsPostBackupPruneFailure makes the
// post-backup prune fail after a good backup, by planting a manifest
// that cannot be decoded, and checks that the failure is reported as the
// prune's and not as a failed snapshot creation.
//
//nolint:paralleltest // replaces os.Args, os.Stdout, os.Stderr and the xdg globals
func TestEntrySnapshotCreateReportsPostBackupPruneFailure(t *testing.T) {
configPath, storeDir := writeBackupConfig(t)
// A remote key is 64 lowercase hex characters. The prune reads every
// manifest on the store and fails on one it cannot decode.
plantedDir := filepath.Join(storeDir, "metadata", strings.Repeat("a", 64))
require.NoError(t, os.MkdirAll(plantedDir, 0o750))
require.NoError(t, os.WriteFile(
filepath.Join(plantedDir, "manifest.json.zst"),
[]byte("not a valid manifest"), 0o600))
code, _, stderr := runEntry(t,
flagConfig, configPath, cmdSnapshot, cmdCreate, flagPrune)
assert.Equal(t, 1, code)
assert.Contains(t, stderr, "Backup completed, but post-backup prune failed")
assert.NotContains(t, stderr, "Snapshot creation failed")
snapshots, err := os.ReadDir(filepath.Join(storeDir, "metadata"))
require.NoError(t, err)
assert.Len(t, snapshots, 2,
"the new snapshot is on the store beside the planted one")
}
// writeBackupConfig builds a hermetic config with one small file in its
// source directory and an empty destination store directory. Returns the
// config path and the store directory.
func writeBackupConfig(t *testing.T) (string, string) {
t.Helper()
configPath := writeHermeticPruneConfig(t, false)
// writeHermeticPruneConfig puts the source and store directories
// beside the config file.
dir := filepath.Dir(configPath)
sourceDir := filepath.Join(dir, "source")
require.NoError(t, os.Mkdir(sourceDir, 0o750))
require.NoError(t, os.WriteFile(
filepath.Join(sourceDir, "file.txt"), []byte("hello"), 0o600))
return configPath, filepath.Join(dir, "store")
}
-12
View File
@@ -71,11 +71,6 @@ otherwise from the platform config directory (~/.config/vaultik/config.yml
on Linux), then /etc/vaultik/config.yml.`,
Args: cobra.ArbitraryArgs,
RunE: func(cmd *cobra.Command, args []string) error {
err := opts.Validate()
if err != nil {
return err
}
// Pass snapshot names from args
opts.Snapshots = args
// --skip-errors is a global flag on the root command.
@@ -102,13 +97,6 @@ on Linux), then /etc/vaultik/config.yml.`,
}, func(v *vaultik.Vaultik) error {
return v.CreateSnapshot(opts)
}, func(err error) {
if errors.Is(err, vaultik.ErrPostBackupPruneFailed) {
log.Error("Post-backup prune failed", "error", err)
ReportErrorf("Backup completed, but %v", err)
return
}
log.Error("Snapshot creation failed", "error", err)
ReportErrorf("Snapshot creation failed: %v", err)
})
-58
View File
@@ -4,7 +4,6 @@ import (
"context"
"database/sql"
"errors"
"strings"
"testing"
"time"
@@ -294,63 +293,6 @@ func TestRepositoriesTransactionContextCancelled(t *testing.T) {
}
}
// A body that ends the transaction itself with ROLLBACK makes WithTx's
// own rollback fail. WithTx must return that failure together with the
// body's error.
func TestRepositoriesTransactionRollbackFails(t *testing.T) {
t.Parallel()
db, cleanup := setupTestDB(t)
defer cleanup()
ctx := context.Background()
repos := database.NewRepositories(db)
err := repos.WithTx(ctx, func(ctx context.Context, tx *sql.Tx) error {
_, err := tx.ExecContext(ctx, "ROLLBACK")
if err != nil {
return err
}
return errIntentionalRollback
})
if !errors.Is(err, errIntentionalRollback) {
t.Fatalf("expected the body's error, got: %v", err)
}
if !strings.Contains(err.Error(), "rolling back transaction") {
t.Errorf("expected the failed rollback in the error, got: %v", err)
}
}
// When the body ends the transaction itself with ROLLBACK and then
// panics, WithTx's own rollback fails; the panic must still reach the
// caller.
func TestRepositoriesTransactionPanicRollbackFails(t *testing.T) {
t.Parallel()
db, cleanup := setupTestDB(t)
defer cleanup()
ctx := context.Background()
repos := database.NewRepositories(db)
defer func() {
if recover() == nil {
t.Error("expected the body's panic to reach the caller")
}
}()
_ = repos.WithTx(ctx, func(ctx context.Context, tx *sql.Tx) error {
_, err := tx.ExecContext(ctx, "ROLLBACK")
if err != nil {
return err
}
panic(errIntentionalRollback)
})
}
func TestRepositoriesReadTransaction(t *testing.T) {
t.Parallel()
+19 -8
View File
@@ -167,6 +167,10 @@ const (
// metadataKeyParts is the minimum "/"-separated segment count of a
// metadata object key (metadata/<snapshot-id>/<filename>).
metadataKeyParts = 3
// blobKeyParts is the minimum "/"-separated segment count of a blob
// object key (blobs/<aa>/<bb>/<hash>).
blobKeyParts = 4
)
// SnapshotMetadataInfo contains information about a single snapshot's metadata
@@ -450,16 +454,23 @@ func (v *Vaultik) scanRemoteBlobStorage(
v.stdoutf("Scanning blobs...\n")
}
// Use prune's listing, so a file under blobs/ that prune would never
// delete is not counted as a blob, and so not as an orphaned one.
allBlobs, err := v.listAllRemoteBlobs()
if err != nil {
return err
}
blobCh := v.Storage.ListStream(v.ctx, "blobs/")
allBlobs := make(map[string]int64)
for _, size := range allBlobs {
for obj := range blobCh {
if obj.Err != nil {
return fmt.Errorf("listing blobs: %w", obj.Err)
}
parts := strings.Split(obj.Key, "/")
if len(parts) < blobKeyParts {
continue
}
hash := parts[3]
allBlobs[hash] = obj.Size
result.TotalBlobCount++
result.TotalBlobSize += size
result.TotalBlobSize += obj.Size
}
// A blob named only by a manifest that could not be read, or by one
-4
View File
@@ -23,10 +23,6 @@ var errNukeRequiresForce = errors.New(
// metadata.
const metadataDirName = "metadata"
// blobKeyParts is the "/"-separated segment count of a blob object key
// (blobs/<aa>/<bb>/<hash>).
const blobKeyParts = 4
// NukeRemote deletes every snapshot's metadata and every blob from remote
// storage, along with any object an upload cut off part-way left under a
// temporary `.partial` name. After this returns successfully the bucket
-33
View File
@@ -185,39 +185,6 @@ func TestRemoteInfo_SkipsNonConformingMetadataName(t *testing.T) {
assert.NotContains(t, doc, "unreadable_manifests")
}
// TestRemoteInfo_DoesNotCountNonBlobFileUnderBlobs checks that a file
// under blobs/ whose name is not a blob hash is not counted as a blob.
// prune never deletes such a file, so counting it as an orphaned blob
// would advise a prune that removes nothing.
func TestRemoteInfo_DoesNotCountNonBlobFileUnderBlobs(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
env := newListEnv(t)
env.addRemote(t, listRemoteID, time.Date(2026, 3, 2, 0, 0, 0, 0, time.UTC))
addBlob(t, env.store.testStorer, testBlobHashA)
require.NoError(t, env.store.Put(context.Background(),
"blobs/"+testBlobHashA[:2]+"/"+testBlobHashA[2:4]+"/.DS_Store",
bytes.NewReader([]byte("junk"))))
require.NoError(t, env.v.RemoteInfo(false))
text := env.stdout.String()
assert.Contains(t, text, "Total blobs on remote: 1 (")
assert.Contains(t, text, "Orphaned (unreferenced): 0 (")
assert.NotContains(t, text, "vaultik prune")
env.stdout.Reset()
require.NoError(t, env.v.RemoteInfo(true))
var doc map[string]any
require.NoError(t, json.Unmarshal(env.stdout.Bytes(), &doc))
assert.InDelta(t, 1, doc["total_blob_count"], 0)
assert.InDelta(t, 0, doc["orphaned_blob_count"], 0)
assert.InDelta(t, 0, doc["orphaned_blob_size"], 0)
}
// TestRemoteInfo_DirectoryWithoutManifestLeavesOrphansKnown checks that
// a directory under metadata/ holding no manifest.json.zst, such as one
// left by a backup interrupted before its manifest upload, leaves the
+1 -27
View File
@@ -28,14 +28,8 @@ var (
errNoAgeRecipients = errors.New(
"creating a snapshot needs at least one public key in " +
"age_recipients (generate a keypair with: age-keygen)")
errKeepNewerThanNeedsPrune = errors.New("--keep-newer-than requires --prune")
)
// ErrPostBackupPruneFailed wraps a failure of the post-backup prune,
// which runs only after every snapshot was created and uploaded, so the
// caller can report it apart from a failed backup.
var ErrPostBackupPruneFailed = errors.New("post-backup prune failed")
// listRecentLimit caps how many snapshot rows are fetched from the
// local index for listing and purge operations.
const listRecentLimit = 10000
@@ -51,26 +45,6 @@ type SnapshotCreateOptions struct {
Snapshots []string // Optional list of snapshot names to process (empty = all)
}
// Validate fails when KeepNewerThan is set without Prune or is not a
// valid duration. Only the post-backup prune reads KeepNewerThan, after
// the backup, so the caller checks it before starting one.
func (opts *SnapshotCreateOptions) Validate() error {
if opts.KeepNewerThan == "" {
return nil
}
if !opts.Prune {
return errKeepNewerThanNeedsPrune
}
_, err := parseDuration(opts.KeepNewerThan)
if err != nil {
return fmt.Errorf("--keep-newer-than: %w", err)
}
return nil
}
// CreateSnapshot executes the snapshot creation operation
func (v *Vaultik) CreateSnapshot(opts *SnapshotCreateOptions) error {
// config.Load accepts an empty list, since listing, verifying and
@@ -149,7 +123,7 @@ func (v *Vaultik) CreateSnapshot(opts *SnapshotCreateOptions) error {
if opts.Prune {
err = v.runPostBackupPrune(snapshotNames, opts.KeepNewerThan)
if err != nil {
return fmt.Errorf("%w: %w", ErrPostBackupPruneFailed, err)
return fmt.Errorf("post-backup prune: %w", err)
}
}