Fail snapshot remove when a destination-only snapshot's metadata cannot be deleted (closes #340)

When a snapshot was only on the destination store and deleting its
metadata there failed, snapshot remove warned and exited 0 having
removed nothing. That failure is now an error. A snapshot in the local
index keeps its behaviour: it is removed from the local index and the
failed delete on the destination store is a warning.

The README and the help text said the `vaultik prune` follow-up is
printed on every success; they now say it is printed only when metadata
was removed from the destination store, and never under --json. The
comments on RemoveSnapshot and removeSnapshotRemote describe both
cases; removeSnapshotRemote's also says it returns true only when the
delete finished without an error and removed at least one object.

Model: opus-5-5

go.mod

@@ -22,7 +22,6 @@ require (
 	github.com/spf13/cobra v1.10.1
 	github.com/spf13/pflag v1.0.10
 	github.com/stretchr/testify v1.11.1
-	go.uber.org/dig v1.19.0
 	go.uber.org/fx v1.24.0
 	golang.org/x/sync v0.18.0
 	golang.org/x/sys v0.38.0
@@ -257,6 +256,7 @@ require (
 	go.opentelemetry.io/otel/metric v1.38.0 // indirect
 	go.opentelemetry.io/otel/trace v1.38.0 // indirect
 	go.shabbyrobe.org/gocovmerge v0.0.0-20230507111327-fa4f82cfbf4d // indirect
+	go.uber.org/dig v1.19.0 // indirect
 	go.uber.org/multierr v1.11.0 // indirect
 	go.uber.org/zap v1.27.0 // indirect
 	go.yaml.in/yaml/v2 v2.4.3 // indirect

internal/cli/app.go

@@ -8,12 +8,12 @@ import (
 	"errors"
 	"fmt"
 	"path/filepath"
+	"strings"
 	"sync"
 	"time"
 
 	"github.com/adrg/xdg"
 	"github.com/spf13/cobra"
-	"go.uber.org/dig"
 	"go.uber.org/fx"
 	"sneak.berlin/go/vaultik/internal/config"
 	"sneak.berlin/go/vaultik/internal/database"
@@ -146,12 +146,16 @@ func (e *startupError) Error() string {
 //	could not build arguments for function "Y" (file:line): failed to build U:
 //	received non-nil error from function "Z" (file:line): <real error>
 //
-// Users care about the real error, not the DI plumbing. dig.RootCause,
+// Users care about the real error, not the DI plumbing. We strip everything
-// from the library fx is built on, unwraps those layers and returns the
+// up through the last "): " (which is always the close-paren of an fx
-// real error whole. Cutting the text at "): " instead would also cut a
+// function-location annotation followed by the wrapped error).
-// real error that contains it, such as the blob_size_limit one.
 func cleanStartupError(err error) error {
-	return &startupError{msg: dig.RootCause(err).Error()}
+	msg := err.Error()
+	if idx := strings.LastIndex(msg, "): "); idx >= 0 {
+		msg = msg[idx+3:]
+	}
+
+	return &startupError{msg: msg}
 }
 
 // RunApp starts the fx application, blocks until it is asked to stop, and

internal/cli/app_test.go

@@ -2,65 +2,58 @@ package cli //nolint:testpackage // needs access to unexported cleanStartupError
 
 import (
 	"errors"
-	"os"
 	"path/filepath"
 	"testing"
 
-	"go.uber.org/fx"
-	"sneak.berlin/go/vaultik/internal/config"
 	"sneak.berlin/go/vaultik/internal/pidlock"
 )
 
-// TestCleanStartupError starts a real fx app whose config has a
-// blob_size_limit below the minimum. fx puts annotations naming the
-// functions it was building in front of the config error; only those
-// may be removed, although the config error itself contains "): ".
 func TestCleanStartupError(t *testing.T) {
 	t.Parallel()
 
-	path := filepath.Join(t.TempDir(), "config.yml")
+	tests := []struct {
-
+		name string
-	err := os.WriteFile(path, []byte("snapshots:\n"+
+		in   string
-		"  test:\n"+
+		want string
-		"    paths: [/tmp/vaultik-test-source]\n"+
+	}{
-		"storage_url: file:///tmp/vaultik-test-storage\n"+
+		{
-		"chunk_size: 10MB\n"+
+			name: "real fx error chain",
-		"blob_size_limit: 30MB\n"), 0o600)
+			in: `could not build arguments for function ` +
-	if err != nil {
+				`"sneak.berlin/go/vaultik/internal/cli".newSnapshotCreateCommand.func1.1 ` +
-		t.Fatalf("write config: %v", err)
+				`(/Users/user/dev/vaultik/internal/cli/snapshot.go:71): ` +
+				`failed to build *vaultik.Vaultik: ` +
+				`could not build arguments for function ` +
+				`"sneak.berlin/go/vaultik/internal/vaultik".New ` +
+				`(/Users/user/dev/vaultik/internal/vaultik/vaultik.go:59): ` +
+				`failed to build storage.Storer: ` +
+				`received non-nil error from function ` +
+				`"sneak.berlin/go/vaultik/internal/storage".NewStorer ` +
+				`(/Users/user/dev/vaultik/internal/storage/module.go:23): ` +
+				`creating base path: mkdir /Volumes/BACKUPS: permission denied`,
+			want: `creating base path: mkdir /Volumes/BACKUPS: permission denied`,
+		},
+		{
+			name: "no fx wrapping",
+			in:   "plain error",
+			want: "plain error",
+		},
+		{
+			name: "single fx wrapping",
+			in:   `received non-nil error from function "foo" (file.go:1): underlying problem`,
+			want: "underlying problem",
+		},
 	}
 
-	app := fx.New(
+	for _, tt := range tests {
-		fx.NopLogger,
+		t.Run(tt.name, func(t *testing.T) {
-		fx.Supply(config.Path(path)),
-		config.Module,
-		fx.Invoke(func(*config.Config) {}),
-	)
-
-	err = app.Start(t.Context())
-	if err == nil {
-		t.Fatal("app started; want a blob_size_limit error")
-	}
-
-	want := "failed to load config: invalid config: blob_size_limit must " +
-		"be at least the largest chunk the chunker can emit (chunk_size " +
-		"times the FastCDC size spread): need at least 40000000 bytes"
-
-	got := cleanStartupError(err).Error()
-	if got != want {
-		t.Errorf("got %q, want %q", got, want)
-	}
-}
-
-// TestCleanStartupErrorNotFromFx checks that an error fx did not wrap is
-// shown unchanged.
-func TestCleanStartupErrorNotFromFx(t *testing.T) {
 			t.Parallel()
 
-	//nolint:err113 // a one-off error standing in for a startup failure
+			//nolint:err113 // test constructs errors from table input
-	got := cleanStartupError(errors.New("plain error")).Error()
+			got := cleanStartupError(errors.New(tt.in)).Error()
-	if got != "plain error" {
+			if got != tt.want {
-		t.Errorf("got %q, want %q", got, "plain error")
+				t.Errorf("got %q, want %q", got, tt.want)
+			}
+		})
 	}
 }
 

internal/vaultik/blobcache.go

@@ -39,9 +39,9 @@ type blobDiskCacheEntry struct {
 // internally and will fall back to LRU eviction if curBytes exceeds
 // maxBytes. Restore passes math.MaxInt64 as maxBytes and drives
 // eviction itself via Delete() through restoreSweeper, which deletes
-// each blob once no file still to be restored in this run needs it.
+// each blob the moment every file that references its chunks has been
-// LRU never fires under that configuration; it is kept as a safety net
+// written. LRU never fires under that configuration; it is kept as a
-// for callers that don't manage eviction themselves.
+// safety net for callers that don't manage eviction themselves.
 //
 // Get/ReadAt/peak-Len counters are debugging instrumentation used by
 // tests to assert that the restore code path uses ReadAt rather than

internal/vaultik/prune_count_test.go

@@ -1,17 +1,13 @@
 package vaultik //nolint:testpackage // exercises unexported count helpers
 
 import (
-	"bytes"
 	"context"
 	"testing"
-	"time"
 
 	"github.com/stretchr/testify/assert"
 	"github.com/stretchr/testify/require"
 	"sneak.berlin/go/vaultik/internal/database"
 	"sneak.berlin/go/vaultik/internal/log"
-	"sneak.berlin/go/vaultik/internal/snapshot"
-	"sneak.berlin/go/vaultik/internal/ui"
 )
 
 // TestTableCountForReportSurfacesReadFailure is the regression guard for
@@ -80,59 +76,3 @@ func TestCountDiffUnknownWhenEitherSideUnknown(t *testing.T) {
 	assert.Nil(t, countDiff(&before, nil), "unknown after yields unknown delta")
 	assert.Nil(t, countDiff(nil, nil))
 }
-
-// TestPruneDatabaseSummaryLabelsTotals removes the only incomplete
-// snapshot from an index that also holds a complete one. The figure in
-// brackets is every snapshot left in the local index, so the line must
-// say so rather than read as incomplete snapshots that remain.
-func TestPruneDatabaseSummaryLabelsTotals(t *testing.T) {
-	log.Initialize(log.Config{})
-	t.Parallel()
-
-	ctx := context.Background()
-
-	db, err := database.New(ctx, ":memory:")
-	require.NoError(t, err)
-	t.Cleanup(func() { _ = db.Close() })
-
-	repos := database.NewRepositories(db)
-
-	startedAt := time.Date(2026, 1, 2, 3, 4, 5, 0, time.UTC)
-	completedAt := startedAt.Add(time.Minute)
-
-	require.NoError(t, repos.Snapshots.Create(ctx, nil, &database.Snapshot{
-		ID:          "host_complete_2026-01-02T03:04:05Z",
-		Hostname:    "host",
-		StartedAt:   startedAt,
-		CompletedAt: &completedAt,
-	}))
-	require.NoError(t, repos.Snapshots.Create(ctx, nil, &database.Snapshot{
-		ID:        "host_incomplete_2026-01-02T03:04:05Z",
-		Hostname:  "host",
-		StartedAt: startedAt,
-	}))
-
-	var out bytes.Buffer
-
-	v := &Vaultik{
-		DB:           db,
-		Repositories: repos,
-		SnapshotManager: snapshot.NewSnapshotManager(
-			snapshot.SnapshotManagerParams{Repos: repos}),
-		UI: ui.NewWithColor(&out, false),
-	}
-	v.SetContext(ctx)
-
-	result, err := v.PruneDatabase()
-	require.NoError(t, err)
-	require.Equal(t, int64(1), result.SnapshotsDeleted)
-
-	assert.Contains(t, out.String(), "Incomplete snapshots: 1 removed "+
-		"(total snapshots left in the local index: 1).")
-	assert.Contains(t, out.String(), "Orphaned files: 0 removed "+
-		"(total files left in the local index: 0).")
-	assert.Contains(t, out.String(), "Orphaned chunks: 0 removed "+
-		"(total chunks left in the local index: 0).")
-	assert.Contains(t, out.String(), "Orphaned blobs: 0 removed "+
-		"(total blobs left in the local index: 0).")
-}

internal/vaultik/restore.go

@@ -323,6 +323,12 @@ func (v *Vaultik) restoreAllFiles(
 		_ = blobCache.Close()
 	}()
 
+	// Per-restore sweep state: every blob_size_limit/100 bytes written,
+	// scan the cache and delete any blob whose remaining file references
+	// are all already restored.
+	sweeper := newRestoreSweeper(v.ctx, repos, blobCache,
+		v.Config.BlobSizeLimit.Int64()/sweepIntervalDivisor)
+
 	blobByHash, blobIDToHash, err := v.buildBlobIndexes(repos)
 	if err != nil {
 		return nil, err
@@ -334,12 +340,6 @@ func (v *Vaultik) restoreAllFiles(
 		return nil, fmt.Errorf("building restore plan: %w", err)
 	}
 
-	// Per-restore sweep state: every blob_size_limit/100 bytes written,
-	// scan the cache and delete any blob that no pending file in the
-	// plan references.
-	sweeper := newRestoreSweeper(plan, blobCache,
-		v.Config.BlobSizeLimit.Int64()/sweepIntervalDivisor)
-
 	// Ranging over files rather than the map reports them in a stable order.
 	for _, file := range files {
 		if planErr, ok := unplanned[file.ID]; ok {
@@ -427,8 +427,10 @@ func (v *Vaultik) runRestoreLoop(
 			continue
 		}
 
-		// Drop the file from the plan's indexes so future picks ignore
+		// Record the file as restored so the sweeper can free blobs
-		// it and the sweeper can free blobs no pending file needs.
+		// once all referencing files are done, and drop it from the
+		// plan's indexes so future picks ignore it.
+		session.sweeper.fileRestored(fileID.String())
 		plan.finishFile(fileID)
 
 		processed++

internal/vaultik/restore_interrupt_test.go

@@ -74,8 +74,7 @@ func TestRestoreCleansTempDirOnInterrupt(t *testing.T) {
 	buildLocalityFixture(t, fs, dataDir)
 
 	cfg, storer, snapshotID := setupLocalityBackup(
-		context.Background(), t, fs, dataDir, storeDir, dbPath,
+		context.Background(), t, fs, dataDir, storeDir, dbPath)
-		localitySourceBytes)
 
 	// Point the "" temp paths (the blob cache directory and the
 	// snapshot-database directory) at a private directory so the test can

internal/vaultik/restore_locality_test.go

@@ -63,10 +63,6 @@ type localityCopy struct {
 	data []byte
 }
 
-// localitySourceBytes is the size of each source file of the locality
-// fixture.
-const localitySourceBytes = 1024 * 1024
-
 // buildLocalityFixture writes the adversarial source layout described
 // in TestRestoreLocalityAndReadAt: 15 sources of 1 MiB each (which the
 // backup packs into 3 blobs of 5 chunks) plus 9 interleaved-name copies
@@ -77,6 +73,7 @@ func buildLocalityFixture(
 	t.Helper()
 
 	const (
+		srcBytes   = 1024 * 1024
 		srcCount   = 15
 		blobsCount = 3
 		perBlob    = srcCount / blobsCount
@@ -86,7 +83,7 @@ func buildLocalityFixture(
 	for i := range srcCount {
 		s := &localitySource{
 			path: fmt.Sprintf("src-%03d.bin", i+1),
-			data: randomBytes(t, localitySourceBytes),
+			data: randomBytes(t, srcBytes),
 		}
 		sources[i] = s
 		require.NoError(t, afero.WriteFile(
@@ -118,20 +115,19 @@ func buildLocalityFixture(
 
 // setupLocalityBackup runs the backup half of the locality test: a
 // snapshot of dataDir into a file storer with sizes tuned so 15 one-chunk
-// files of srcBytes pack into 3 blobs. The index database is closed
+// files pack into 3 blobs. The index database is closed before returning
-// before returning so the restore half runs from remote bytes only.
+// so the restore half runs from remote bytes only.
 func setupLocalityBackup(
 	ctx context.Context, t *testing.T, fs afero.Fs,
-	dataDir, storeDir, dbPath string, srcBytes int64,
+	dataDir, storeDir, dbPath string,
 ) (*config.Config, *storage.FileStorer, string) {
 	t.Helper()
 
-	// An average chunk size of four times srcBytes makes the minimum
+	// chunkSize avg = 4 MiB makes minSize = 1 MiB, so a 1 MiB file
-	// chunk srcBytes, so each source file becomes one chunk. A blob limit
+	// becomes one chunk. maxBlobSize = 5 MiB packs exactly 5 chunks
-	// of five times srcBytes packs exactly 5 chunks per blob, yielding 3
+	// per blob, yielding 3 blobs from 15 source files.
-	// blobs from 15 source files.
+	chunkSize := int64(4 * 1024 * 1024)
-	chunkSize := 4 * srcBytes
+	maxBlobSize := int64(5 * 1024 * 1024)
-	maxBlobSize := 5 * srcBytes
 
 	storer, err := storage.NewFileStorer(storeDir)
 	require.NoError(t, err)
@@ -212,7 +208,7 @@ func TestRestoreLocalityAndReadAt(t *testing.T) {
 	ctx := context.Background()
 
 	cfg, storer, snapshotID := setupLocalityBackup(
-		ctx, t, fs, dataDir, storeDir, dbPath, localitySourceBytes)
+		ctx, t, fs, dataDir, storeDir, dbPath)
 
 	// Wrap the storer so we can count downloads per blob key.
 	counter := newCountingStorer(storer)

internal/vaultik/restore_plan.go

@@ -31,8 +31,7 @@ var (
 //     with no further downloads.
 //   - blobFiles: for each blob, the set of pending files referencing
 //     it. Used to short-circuit "when this blob lands, which files
-//     become ready" without a global scan, and by the sweeper to tell
+//     become ready" without a global scan.
-//     whether a cached blob is still needed.
 type restorePlan struct {
 	fileBlobs map[types.FileID]map[string]struct{}
 	blobFiles map[string]map[types.FileID]struct{}
@@ -238,12 +237,6 @@ func (p *restorePlan) filesReferencingBlob(blobHash string) []types.FileID {
 	return out
 }
 
-// pendingFileUsesBlob reports whether any pending file references the
-// named blob, whether or not the blob is cached.
-func (p *restorePlan) pendingFileUsesBlob(blobHash string) bool {
-	return len(p.blobFiles[blobHash]) > 0
-}
-
 // hasPending reports whether any unfinished files remain.
 func (p *restorePlan) hasPending() bool {
 	return len(p.fileBlobs) > 0

internal/vaultik/restore_plan_test.go

@@ -63,6 +63,15 @@ func TestRunRestoreLoopFailsOnAbandonedFiles(t *testing.T) {
 
 	t.Cleanup(func() { _ = cache.Close() })
 
+	v := &Vaultik{ctx: ctx}
+	session := &restoreSession{
+		v:       v,
+		ctx:     ctx,
+		repos:   repos,
+		sweeper: newRestoreSweeper(ctx, repos, cache, 1),
+		result:  &RestoreResult{},
+	}
+
 	// A file that is still pending but whose uncached-blob set is empty
 	// and which was never queued as ready: the loop can neither restore
 	// nor download it. This is the abandonment the guard must catch.
@@ -74,15 +83,6 @@ func TestRunRestoreLoopFailsOnAbandonedFiles(t *testing.T) {
 		cached:    map[string]struct{}{},
 	}
 
-	v := &Vaultik{ctx: ctx}
-	session := &restoreSession{
-		v:       v,
-		ctx:     ctx,
-		repos:   repos,
-		sweeper: newRestoreSweeper(plan, cache, 1),
-		result:  &RestoreResult{},
-	}
-
 	err = v.runRestoreLoop(session, plan, map[types.FileID]*database.File{}, 0)
 	require.ErrorIs(t, err, errRestoreIncomplete)
 }

internal/vaultik/restore_sweeper.go

@@ -1,30 +1,46 @@
 package vaultik
 
-// restoreSweeper frees cached blobs once no file still to be restored in
+import (
-// this run needs them. It works as follows:
+	"context"
+	"fmt"
+
+	"sneak.berlin/go/vaultik/internal/database"
+	"sneak.berlin/go/vaultik/internal/log"
+)
+
+// restoreSweeper frees cached blobs once all files that reference any of
+// their chunks have been restored. It works as follows:
 //
-//  1. After each chunk is restored, chunkRestored accumulates a running
+//  1. Callers add a file's ID to an in-memory restored set via
+//     fileRestored once the file is fully written to disk.
+//  2. After each chunk is restored, chunkRestored accumulates a running
 //     byte count.
-//  2. When the accumulator crosses a threshold (one hundredth of the
+//  3. When the accumulator crosses a threshold (one hundredth of the
 //     configured blob size — so a sweep runs about a hundred times per
 //     blob's worth of restored bytes), the sweeper iterates every key in
-//     the cache and deletes each blob that the restore plan no longer
+//     the cache. For each cached blob it asks the DB which files
-//     needs.
+//     reference any chunk in that blob, then compares that list against
+//     the in-memory restored set. If any referencing file is missing
+//     from the set the blob is kept; otherwise the cache entry is
+//     deleted.
 //
-// The plan drops a file once it is restored or has failed, and holds
+// All DB reads happen against the snapshot's temporary metadata DB,
-// only the files this run restores, so files outside the requested paths
+// which is local, indexed, and not under contention — the queries are
-// never keep a blob.
+// cheap and run at most once per blob per sweep interval.
 type restoreSweeper struct {
-	plan       *restorePlan
+	ctx        context.Context //nolint:containedctx // ctx bound at construction by design
+	repos      *database.Repositories
 	cache      *blobDiskCache
 	threshold  int64
 	bytesAccum int64
+	restored   map[string]struct{}
 }
 
 // newRestoreSweeper returns a sweeper that triggers eviction every
 // `threshold` bytes restored. Callers should pass blob_size_limit/100.
 func newRestoreSweeper(
-	plan *restorePlan,
+	ctx context.Context,
+	repos *database.Repositories,
 	cache *blobDiskCache,
 	threshold int64,
 ) *restoreSweeper {
@@ -33,12 +49,21 @@ func newRestoreSweeper(
 	}
 
 	return &restoreSweeper{
-		plan:      plan,
+		ctx:       ctx,
+		repos:     repos,
 		cache:     cache,
 		threshold: threshold,
+		restored:  make(map[string]struct{}),
 	}
 }
 
+// fileRestored records a file as fully restored. After this call, any
+// blob whose only remaining references come from files in the restored
+// set may be evicted on the next sweep.
+func (s *restoreSweeper) fileRestored(fileID string) {
+	s.restored[fileID] = struct{}{}
+}
+
 // chunkRestored accounts n bytes against the sweep threshold and runs a
 // sweep if the threshold has been crossed since the last sweep.
 func (s *restoreSweeper) chunkRestored(n int64) {
@@ -51,11 +76,60 @@ func (s *restoreSweeper) chunkRestored(n int64) {
 	s.sweep()
 }
 
-// sweep deletes every cached blob that no pending file references.
+// sweep deletes any cached blob whose chunks are no longer referenced
+// by an unrestored file. Per-blob DB failures are logged and the blob
+// is kept — we'd rather hold a blob longer than risk a re-download.
 func (s *restoreSweeper) sweep() {
 	for _, blobHash := range s.cache.Keys() {
-		if !s.plan.pendingFileUsesBlob(blobHash) {
+		needed, err := s.blobStillNeeded(blobHash)
+		if err != nil {
+			log.Debug("sweeper referencing-files query failed",
+				"blob_hash", blobHash[:16], "error", err)
+
+			continue
+		}
+
+		if !needed {
 			s.cache.Delete(blobHash)
 		}
 	}
 }
+
+// blobStillNeeded returns true if any file that references a chunk in
+// this blob has not yet been restored. On any error the function
+// returns true — keeping the blob is always the safe answer because we
+// can't prove we're done with it.
+func (s *restoreSweeper) blobStillNeeded(blobHash string) (bool, error) {
+	rows, err := s.repos.DB().Conn().QueryContext(s.ctx, `
+		SELECT DISTINCT fc.file_id
+		FROM file_chunks fc
+		JOIN blob_chunks bc ON bc.chunk_hash = fc.chunk_hash
+		JOIN blobs b ON b.id = bc.blob_id
+		WHERE b.blob_hash = ?
+	`, blobHash)
+	if err != nil {
+		return true, fmt.Errorf("querying referencing files: %w", err)
+	}
+
+	defer func() { _ = rows.Close() }()
+
+	for rows.Next() {
+		var fileID string
+
+		err := rows.Scan(&fileID)
+		if err != nil {
+			return true, fmt.Errorf("scanning file_id: %w", err)
+		}
+
+		if _, ok := s.restored[fileID]; !ok {
+			return true, nil
+		}
+	}
+
+	err = rows.Err()
+	if err != nil {
+		return true, err
+	}
+
+	return false, nil
+}

internal/vaultik/restore_sweeper_test.go

@@ -1,163 +0,0 @@
-package vaultik //nolint:testpackage // reads the restore blob cache's peak size
-
-import (
-	"context"
-	"fmt"
-	"io"
-	"path/filepath"
-	"testing"
-
-	"github.com/spf13/afero"
-	"github.com/stretchr/testify/assert"
-	"github.com/stretchr/testify/require"
-	"sneak.berlin/go/vaultik/internal/config"
-	"sneak.berlin/go/vaultik/internal/log"
-	"sneak.berlin/go/vaultik/internal/storage"
-	"sneak.berlin/go/vaultik/internal/ui"
-)
-
-// TestRestoreFreesBlobsNoPendingFileNeeds asserts that the restore cache
-// frees a blob once no file still to be restored in this run needs it.
-// Every original file has a copy with the same content, so every blob
-// holds chunks of copies: a restore that leaves the copies out of its
-// paths, or fails on them, must not keep the blobs for them.
-func TestRestoreFreesBlobsNoPendingFileNeeds(t *testing.T) {
-	log.Initialize(log.Config{})
-	t.Parallel()
-
-	// Small files keep the backup and both restores quick.
-	const fileBytes = 16 * 1024
-
-	fs := afero.NewOsFs()
-	tempDir := t.TempDir()
-
-	dataDir := filepath.Join(tempDir, "source")
-	originalsDir := filepath.Join(dataDir, "originals")
-	copiesDir := filepath.Join(dataDir, "copies")
-	storeDir := filepath.Join(tempDir, "remote")
-	dbPath := filepath.Join(tempDir, "index.sqlite")
-
-	originals := writeFilesWithCopies(t, fs, originalsDir, copiesDir, fileBytes)
-
-	ctx := context.Background()
-
-	cfg, storer, snapshotID := setupLocalityBackup(
-		ctx, t, fs, dataDir, storeDir, dbPath, fileBytes)
-
-	t.Run("restore by path", func(t *testing.T) {
-		t.Parallel()
-
-		restoreDir := filepath.Join(tempDir, "by-path")
-
-		peak, err := restorePeakCachedBlobs(ctx, t, fs, cfg, storer,
-			&RestoreOptions{
-				SnapshotID: snapshotID,
-				TargetDir:  restoreDir,
-				Paths:      []string{originalsDir},
-			})
-		require.NoError(t, err)
-
-		requireRestoredFiles(t, fs, restoreDir, originals)
-		assert.LessOrEqualf(t, peak, 1,
-			"peak cached blobs was %d; blobs were kept for unselected files",
-			peak)
-	})
-
-	t.Run("restore with failed files", func(t *testing.T) {
-		t.Parallel()
-
-		restoreDir := filepath.Join(tempDir, "with-failures")
-
-		// A regular file where the copies directory belongs makes every
-		// copy fail to restore.
-		blocker := filepath.Join(restoreDir, copiesDir)
-		require.NoError(t, fs.MkdirAll(filepath.Dir(blocker), 0o755))
-		require.NoError(t, afero.WriteFile(fs, blocker, nil, 0o644))
-
-		peak, err := restorePeakCachedBlobs(ctx, t, fs, cfg, storer,
-			&RestoreOptions{
-				SnapshotID: snapshotID,
-				TargetDir:  restoreDir,
-				SkipErrors: true,
-			})
-		require.ErrorIs(t, err, errFilesFailedRestore)
-
-		requireRestoredFiles(t, fs, restoreDir, originals)
-		assert.LessOrEqualf(t, peak, 1,
-			"peak cached blobs was %d; blobs were kept for failed files", peak)
-	})
-}
-
-// writeFilesWithCopies writes 15 random files of fileBytes into
-// originalsDir and a copy of each into copiesDir. With
-// setupLocalityBackup given the same size, each file is one chunk and the
-// 15 chunks fill 3 blobs. Returns the originals' content by path.
-func writeFilesWithCopies(
-	t *testing.T, fs afero.Fs, originalsDir, copiesDir string, fileBytes int,
-) map[string][]byte {
-	t.Helper()
-
-	const fileCount = 15
-
-	require.NoError(t, fs.MkdirAll(originalsDir, 0o755))
-	require.NoError(t, fs.MkdirAll(copiesDir, 0o755))
-
-	originals := make(map[string][]byte, fileCount)
-
-	for i := range fileCount {
-		name := fmt.Sprintf("file-%02d.bin", i)
-		data := randomBytes(t, fileBytes)
-		original := filepath.Join(originalsDir, name)
-		originals[original] = data
-
-		require.NoError(t, afero.WriteFile(fs, original, data, 0o644))
-		require.NoError(t, afero.WriteFile(
-			fs, filepath.Join(copiesDir, name), data, 0o644))
-	}
-
-	return originals
-}
-
-// requireRestoredFiles requires every file in want to have been restored
-// under restoreDir with its content intact.
-func requireRestoredFiles(
-	t *testing.T, fs afero.Fs, restoreDir string, want map[string][]byte,
-) {
-	t.Helper()
-
-	for path, data := range want {
-		got, err := afero.ReadFile(fs, filepath.Join(restoreDir, path))
-		require.NoErrorf(t, err, "file missing after restore: %s", path)
-		require.Equalf(t, data, got, "byte mismatch for %s", path)
-	}
-}
-
-// restorePeakCachedBlobs runs a restore and returns the most blobs its
-// cache held at once, together with the restore's error.
-func restorePeakCachedBlobs(
-	ctx context.Context, t *testing.T, fs afero.Fs,
-	cfg *config.Config, storer storage.Storer, opts *RestoreOptions,
-) (int, error) {
-	t.Helper()
-
-	var cache *blobDiskCache
-
-	v := &Vaultik{
-		Config:  cfg,
-		Storage: storer,
-		Fs:      fs,
-		Stdout:  io.Discard,
-		Stderr:  io.Discard,
-		UI:      ui.NewWithColor(io.Discard, false),
-		restoreCacheObserver: func(c *blobDiskCache) {
-			cache = c
-		},
-	}
-	v.SetContext(ctx)
-
-	err := v.Restore(opts)
-
-	require.NotNil(t, cache, "restoreCacheObserver must fire during restore")
-
-	return cache.PeakLen(), err
-}

internal/vaultik/snapshot.go

@@ -1920,17 +1920,13 @@ func (v *Vaultik) PruneDatabase() (*PruneResult, error) {
 	snapshotsRemain := countDiff(snapshotCountBefore, &result.SnapshotsDeleted)
 
 	v.UI.Completef("Pruned local index database.")
-	v.UI.Detailf("Incomplete snapshots: %s removed "+
+	v.UI.Detailf("Incomplete snapshots: %s removed (%s remain).",
-		"(total snapshots left in the local index: %s).",
 		countText(&result.SnapshotsDeleted), countText(snapshotsRemain))
-	v.UI.Detailf("Orphaned files: %s removed "+
+	v.UI.Detailf("Orphaned files: %s removed (%s remain).",
-		"(total files left in the local index: %s).",
 		countText(result.FilesDeleted), countText(fileCountAfter))
-	v.UI.Detailf("Orphaned chunks: %s removed "+
+	v.UI.Detailf("Orphaned chunks: %s removed (%s remain).",
-		"(total chunks left in the local index: %s).",
 		countText(result.ChunksDeleted), countText(chunkCountAfter))
-	v.UI.Detailf("Orphaned blobs: %s removed "+
+	v.UI.Detailf("Orphaned blobs: %s removed (%s remain).",
-		"(total blobs left in the local index: %s).",
 		countText(result.BlobsDeleted), countText(blobCountAfter))
 
 	return result, nil