2026-11-11 03:25:42 +01:00
4 changed files with 130 additions and 33 deletions
@@ -7,6 +7,7 @@ import (
 	"os"
 	"path/filepath"
 	"strings"
+	"sync"
 	"testing"

 	"github.com/spf13/afero"
@@ -24,19 +25,28 @@ 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 returns a Vaultik that backs up the
-// snapshot named "first" to a file:// destination at storeDir.
+// newFileDestinationVaultik writes the fault source tree and returns a
+// Vaultik that backs it up 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")
-	dbPath := filepath.Join(tempDir, "index.sqlite")
+	writeFaultSourceTree(t, afero.NewOsFs(), dataDir)

-	writeFaultSourceTree(t, osFs, dataDir)
+	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()

 	store, err := storage.NewFileStorer(storeDir)
 	require.NoError(t, err)
@@ -48,22 +58,84 @@ func newFileDestinationVaultik(
 	repos := database.NewRepositories(db)
 	cfg := changedFileConfig(dataDir, dbPath)

-	return newBackupVaultik(ctx, cfg, store, repos, db, osFs), repos
+	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
 }

 // backUpToFileDestination creates the directory storeDir, as a user must
-// 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.
+// 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.
 func backUpToFileDestination(
 	ctx context.Context, t *testing.T, storeDir string,
 ) (*vaultik.Vaultik, *database.Repositories, *bytes.Buffer) {
 	t.Helper()

-	require.NoError(t, os.MkdirAll(storeDir, 0o750))
+	firstBackup.once.Do(func() { makeFirstBackup(ctx, t) })
+	require.True(t, firstBackup.ready, "another test failed to make firstBackup")

-	v, repos := newFileDestinationVaultik(ctx, t, storeDir)
-	require.NoError(t, backUp(v, "first"))
+	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"))

 	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 ~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.
+// 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.
 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 = 1024 * 1024
+const localitySourceBytes = 64 * 1024

 // buildLocalityFixture writes the adversarial source layout described
-// in TestRestoreLocalityAndReadAt: 15 sources of 1 MiB each (which the
+// in TestRestoreLocalityAndReadAt: 15 sources of 64 KiB 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 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
+// 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
 // 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 1 MB random files plus 10 duplicates of a random subset. The
+// unique 128 KiB 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 = 1 * 1024 * 1024
+	const fileSize = 128 * 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,
-		"30 MB of unique data at 10 MB blob size should yield multiple blobs")
+		"3.75 MiB of unique data at 1 MiB 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(64 * 1024)
-	maxBlobSize := int64(10 * 1024 * 1024)
+	chunkSize := int64(16 * 1024)
+	maxBlobSize := int64(1024 * 1024)

 	storer, err := storage.NewFileStorer(storeDir)
 	require.NoError(t, err)
@@ -187,6 +187,17 @@ 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.
@@ -202,11 +213,17 @@ func (e *listEnv) addRemoteRawTimestamp(
 	data, err := snapshot.EncodeManifest(manifest, 3)
 	require.NoError(t, err)

-	err = e.store.Put(context.Background(),
+	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(),
 		"metadata/"+remoteKey+"/manifest.json.zst", bytes.NewReader(data))
 	require.NoError(t, err)
-
-	return remoteKey
 }

 // Fixtures shared across the listing tests.
@@ -791,9 +808,17 @@ 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.
+	// 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))
+
 	for i := range maxRemoteOnlyRowsForTest + 1 {
-		env.addRemote(t, fmt.Sprintf("otherhost_bulk_%04d", i), timestamp)
+		env.putRemoteManifest(t, snapshot.RemoteSnapshotKey(
+			fmt.Sprintf("otherhost_bulk_%04d", i)), data)
 	}

 	stderr := captureProcessStderr(t, func() {