Keep unreferenced blobs newer than prune_grace_period (closes #387)

A backup uploads its blobs before the manifest that lists them, and the
process lock covers one user on one machine, so a prune from another host
or user sharing the destination deleted a running backup's blobs.

Prune now deletes an unreferenced blob only once its listed time is older
than the new config key prune_grace_period (default 24h; a negative value
is refused). A newer blob, or one listed with no time, is kept and counted
(blobs_too_new). A backup uploads a blob already on the destination again
instead of skipping it, so it gets a fresh time. The rclone backend takes
each object's time from the listing (use_server_modtime).

Cost: after database delete, the next backup uploads all its data again.
Side effect: a rebuilt blob replaces the stored copy; if compression_level
or the recipients changed since, older snapshots listing it fail verify.

Model: opus-5-5

internal/config/config.go

@@ -11,6 +11,7 @@ import (
 	"path/filepath"
 	"sort"
 	"strings"
+	"time"
 
 	"filippo.io/age"
 	"git.eeqj.de/sneak/smartconfig"
@@ -38,6 +39,7 @@ const (
 	defaultChunkSize        = Size(10 * 1000 * 1000)        // 10MB
 	defaultS3PartSize       = Size(5 * 1024 * 1024)         // 5MiB
 	defaultCompressionLevel = 3
+	defaultPruneGracePeriod = 24 * time.Hour
 	minChunkSize            = 1000 * 1000 // 1MB
 	minCompressionLevel     = 1
 	maxCompressionLevel     = 19
@@ -67,6 +69,8 @@ var (
 	errFileURLNotAbsolute = errors.New(
 		"a file:// storage_url needs an absolute path, " +
 			"as in file:///path/to/backup")
+	errNegativePruneGracePeriod = errors.New(
+		"prune_grace_period must not be negative")
 	errStorageNotConfigured = errors.New(
 		"storage not configured; set storage_url or provide s3.endpoint + " +
 			"s3.bucket + credentials")
@@ -187,6 +191,13 @@ type Config struct {
 	Snapshots        map[string]SnapshotConfig `yaml:"snapshots"`
 	CompressionLevel int                       `yaml:"compression_level"`
 
+	// PruneGracePeriod is how old a blob no manifest lists must be before
+	// a prune deletes it. A backup lists its blobs in a manifest only
+	// once it has uploaded them all, so a younger one may belong to a
+	// backup still running, on this host or another sharing the
+	// destination store.
+	PruneGracePeriod time.Duration `yaml:"prune_grace_period"`
+
 	// StorageURL specifies the storage backend using a URL format.
 	// Takes precedence over S3Config if set.
 	// Supported formats:
@@ -288,6 +299,7 @@ func Parse(data []byte) (*Config, error) {
 		ChunkSize:        defaultChunkSize,
 		IndexPath:        filepath.Join(xdg.DataHome, appName, "index.sqlite"),
 		CompressionLevel: defaultCompressionLevel,
+		PruneGracePeriod: defaultPruneGracePeriod,
 		S3:               S3Config{PartSize: defaultS3PartSize},
 	}
 
@@ -356,6 +368,7 @@ func Parse(data []byte) (*Config, error) {
 //     exceeds the configured limit
 //   - Compression level must be between 1 and 19
 //   - S3 part size must be between 5MiB and 5GiB, the part sizes S3 accepts
+//   - Prune grace period must not be negative
 //
 // Returns an error describing the first validation failure encountered.
 func (c *Config) Validate() error {
@@ -405,6 +418,10 @@ func (c *Config) Validate() error {
 		return errBadS3PartSize
 	}
 
+	if c.PruneGracePeriod < 0 {
+		return errNegativePruneGracePeriod
+	}
+
 	return nil
 }
 

internal/config/config_test.go

@@ -412,6 +412,44 @@ func TestDocumentedSizeExamples(t *testing.T) {
 	}
 }
 
+// TestValidatePruneGracePeriod checks that a negative prune_grace_period
+// is refused rather than acting like 0s, which deletes unreferenced blobs
+// at once, and that 0s and the documented examples are accepted.
+func TestValidatePruneGracePeriod(t *testing.T) {
+	t.Parallel()
+
+	const withoutGracePeriod = "snapshots:\n" +
+		"  test:\n" +
+		"    paths: [/tmp/vaultik-test-source]\n" +
+		"storage_url: file:///tmp/vaultik-test-storage\n"
+
+	tests := []struct {
+		setting string
+		wantErr error
+	}{
+		{"prune_grace_period: 0s", nil},
+		{"prune_grace_period: 90m", nil},
+		{"prune_grace_period: 36h", nil},
+		{"prune_grace_period: -1h", errNegativePruneGracePeriod},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.setting, func(t *testing.T) {
+			t.Parallel()
+
+			cfg, err := Parse([]byte(withoutGracePeriod + tt.setting + "\n"))
+			if err != nil {
+				t.Fatalf("Parse() unexpected error: %v", err)
+			}
+
+			err = cfg.Validate()
+			if !errors.Is(err, tt.wantErr) {
+				t.Fatalf("Validate() error = %v, want %v", err, tt.wantErr)
+			}
+		})
+	}
+}
+
 // TestLoadRejectsRelativeFileURL checks that a file:// storage_url with a
 // relative path fails at load. Accepted, it would resolve against the
 // working directory, so a backup run from another directory would write