Files
vaultik/internal/vaultik/prune.go
sneak 7ae470e530 Remediate all lint findings under the canonical golangci-lint config
Fix every finding surfaced by the canonical .golangci.yml with
golangci-lint v2.12.2 (refs #61), behavior-preserving throughout:

- err113: dynamic errors replaced with package-level sentinels and %w
  wrapping; direct comparisons converted to errors.Is
- goprintffuncname: printf-style helpers renamed with an f suffix
  (ui.Writer message methods, cli.ReportErrorf, database.Fatalf,
  vaultik stdoutf) and all call sites updated
- revive: stuttering type names renamed (blob.Handler, blob.WithReader,
  blob.ChunkPosition, storage.URL, storage.Info), doc comments added,
  unused parameters blanked, package comments added
- contextcheck/noctx: ctx threaded through blob.Packer
  (AddChunk/Flush/FinalizeBlob/PackChunks) and scanner call sites;
  context-aware exec and sql variants used
- funlen/cyclop/gocognit/nestif/dupl: oversized or duplicated
  functions split into focused helpers across production and test code
- paralleltest/tparallel/thelper/usetesting/testpackage: tests
  parallelized where safe (global log.Initialize kept in the serial
  phase), helpers marked, t.TempDir adopted, external test packages
  where only exported API is used
- gosec: integer conversions clamped or justified, header timeouts
  added, remaining findings suppressed with per-site justifications
- mnd/goconst/lll/wsl_v5/nlreturn/noinlineerr/errcheck and other
  mechanical findings fixed directly

Remove the deprecated log.LogOptions alias (callers migrated to
log.Options). make check is green.
2026-08-07 18:51:21 +00:00

325 lines
8.6 KiB
Go

package vaultik
import (
"encoding/json"
"errors"
"fmt"
"strings"
"sneak.berlin/go/vaultik/internal/log"
)
// PruneOptions contains options for the prune command
type PruneOptions struct {
Force bool
JSON bool
}
// errNukeRequiresForce guards the destructive remote nuke operation.
var errNukeRequiresForce = errors.New(
"nuke requires --force (this deletes ALL remote snapshots and blobs)")
// metadataDirName is the top-level remote directory holding snapshot
// metadata.
const metadataDirName = "metadata"
// NukeRemote deletes every snapshot's metadata and every blob from remote
// storage. After this returns successfully the bucket prefix is empty and
// the next backup starts from scratch.
//
// Refuses to run unless force is true. The caller is responsible for
// confirming with the user.
func (v *Vaultik) NukeRemote(force bool) error {
if !force {
return errNukeRequiresForce
}
v.UI.Beginf("Removing all snapshot metadata from backup destination store.")
_, err := v.RemoveAllSnapshots(&RemoveOptions{Force: true})
if err != nil {
return fmt.Errorf("removing all snapshots: %w", err)
}
v.UI.Beginf("Removing any blobs still present in backup destination store.")
err = v.PruneBlobs(&PruneOptions{Force: true})
if err != nil {
return fmt.Errorf("pruning blobs: %w", err)
}
v.UI.Completef("Backup destination store is now empty.")
return nil
}
// PruneBlobsResult contains the result of a blob prune operation
//
//nolint:tagliatelle // snake_case is the established JSON output format
type PruneBlobsResult struct {
BlobsFound int `json:"blobs_found"`
BlobsDeleted int `json:"blobs_deleted"`
BlobsFailed int `json:"blobs_failed,omitempty"`
BytesFreed int64 `json:"bytes_freed"`
}
// Prune removes orphaned data from the local index database AND
// unreferenced blobs from the backup destination store. This is the
// single user-facing prune entry point — the split between local and
// remote cleanup is an implementation detail. Calling code should
// prefer this method over PruneDatabase or PruneBlobs individually
// unless it specifically wants one half.
func (v *Vaultik) Prune(opts *PruneOptions) error {
err := v.EnsureStorageBinding()
if err != nil {
return err
}
// First reconcile local snapshot records against remote metadata:
// any local snapshot whose manifest is missing from the destination
// store is treated as gone. This used to be the separate 'snapshot
// cleanup' command and is now folded in so a single 'vaultik prune'
// gets the local index fully back in sync with the destination.
err = v.CleanupLocalSnapshots()
if err != nil {
return fmt.Errorf("reconciling local snapshots with remote: %w", err)
}
_, err = v.PruneDatabase()
if err != nil {
return fmt.Errorf("pruning local database: %w", err)
}
return v.PruneBlobs(opts)
}
// PruneBlobs removes unreferenced blobs from storage
func (v *Vaultik) PruneBlobs(opts *PruneOptions) error {
log.Info("Starting prune operation")
allBlobsReferenced, err := v.collectReferencedBlobs()
if err != nil {
return err
}
allBlobs, err := v.listAllRemoteBlobs()
if err != nil {
return err
}
unreferencedBlobs, totalSize := v.findUnreferencedBlobs(allBlobs, allBlobsReferenced)
result := &PruneBlobsResult{BlobsFound: len(unreferencedBlobs)}
if len(unreferencedBlobs) == 0 {
log.Info("No unreferenced blobs found")
if opts.JSON {
return v.outputPruneBlobsJSON(result)
}
v.printlnStdout("No unreferenced blobs to remove.")
return nil
}
log.Info("Found unreferenced blobs",
"count", len(unreferencedBlobs), "total_size", ubytes(totalSize))
if !opts.JSON {
v.stdoutf("Found %d unreferenced blob(s) totaling %s\n",
len(unreferencedBlobs), ubytes(totalSize))
}
if !opts.Force && !opts.JSON {
v.stdoutf("\nDelete %d unreferenced blob(s)? [y/N] ", len(unreferencedBlobs))
var confirm string
_, err = v.scanStdin(&confirm)
if err != nil {
v.printlnStdout("Cancelled")
return nil //nolint:nilerr // read failure means no confirmation
}
if strings.ToLower(confirm) != "y" {
v.printlnStdout("Cancelled")
return nil
}
}
v.deleteUnreferencedBlobs(unreferencedBlobs, allBlobs, result)
if opts.JSON {
return v.outputPruneBlobsJSON(result)
}
v.stdoutf("\nDeleted %d blob(s) totaling %s\n",
result.BlobsDeleted, ubytes(result.BytesFreed))
if result.BlobsFailed > 0 {
v.stdoutf("Failed to delete %d blob(s)\n", result.BlobsFailed)
}
return nil
}
// collectReferencedBlobs downloads all manifests and returns the set of
// referenced blob hashes.
func (v *Vaultik) collectReferencedBlobs() (map[string]bool, error) {
log.Info("Listing remote snapshots")
// IDs returned by listUniqueSnapshotIDs are remote keys (hashed
// subdirectories under metadata/), not human snapshot IDs.
remoteKeys, err := v.listUniqueSnapshotIDs()
if err != nil {
return nil, fmt.Errorf("listing snapshot keys: %w", err)
}
log.Info("Found manifests in remote storage", "count", len(remoteKeys))
allBlobsReferenced := make(map[string]bool)
manifestCount := 0
for _, remoteKey := range remoteKeys {
log.Debug("Processing manifest", "remote_key", remoteKey)
manifest, err := v.downloadManifestByKey(remoteKey)
if err != nil {
log.Error("Failed to download manifest", "remote_key", remoteKey, "error", err)
continue
}
for _, blob := range manifest.Blobs {
allBlobsReferenced[blob.Hash] = true
}
manifestCount++
}
log.Info("Processed manifests",
"count", manifestCount, "unique_blobs_referenced", len(allBlobsReferenced))
return allBlobsReferenced, nil
}
// listUniqueSnapshotIDs returns deduplicated snapshot IDs from remote metadata
func (v *Vaultik) listUniqueSnapshotIDs() ([]string, error) {
objectCh := v.Storage.ListStream(v.ctx, "metadata/")
seen := make(map[string]bool)
var snapshotIDs []string
for object := range objectCh {
if object.Err != nil {
return nil, fmt.Errorf("listing metadata objects: %w", object.Err)
}
parts := strings.Split(object.Key, "/")
if len(parts) >= minSnapshotIDParts &&
parts[0] == metadataDirName && parts[1] != "" {
if strings.HasSuffix(object.Key, "/") ||
strings.Contains(object.Key, "/manifest.json.zst") {
snapshotID := parts[1]
if !seen[snapshotID] {
seen[snapshotID] = true
snapshotIDs = append(snapshotIDs, snapshotID)
}
}
}
}
return snapshotIDs, nil
}
// listAllRemoteBlobs returns a map of all blob hashes to their sizes in remote storage
func (v *Vaultik) listAllRemoteBlobs() (map[string]int64, error) {
log.Info("Listing all blobs in storage")
allBlobs := make(map[string]int64)
blobObjectCh := v.Storage.ListStream(v.ctx, "blobs/")
for object := range blobObjectCh {
if object.Err != nil {
return nil, fmt.Errorf("listing blobs: %w", object.Err)
}
parts := strings.Split(object.Key, "/")
if len(parts) == blobKeyParts && parts[0] == "blobs" {
allBlobs[parts[3]] = object.Size
}
}
log.Info("Found blobs in storage", "count", len(allBlobs))
return allBlobs, nil
}
// findUnreferencedBlobs returns blob hashes not referenced by any
// manifest and their total size.
func (v *Vaultik) findUnreferencedBlobs(
allBlobs map[string]int64, referenced map[string]bool,
) ([]string, int64) {
var (
unreferenced []string
totalSize int64
)
for hash, size := range allBlobs {
if !referenced[hash] {
unreferenced = append(unreferenced, hash)
totalSize += size
}
}
return unreferenced, totalSize
}
// deleteUnreferencedBlobs deletes the given blobs from storage and
// populates the result.
func (v *Vaultik) deleteUnreferencedBlobs(
unreferencedBlobs []string, allBlobs map[string]int64, result *PruneBlobsResult,
) {
log.Info("Deleting unreferenced blobs")
for i, hash := range unreferencedBlobs {
blobPath := fmt.Sprintf("blobs/%s/%s/%s", hash[:2], hash[2:4], hash)
err := v.Storage.Delete(v.ctx, blobPath)
if err != nil {
log.Error("Failed to delete blob", "hash", hash, "error", err)
continue
}
result.BlobsDeleted++
result.BytesFreed += allBlobs[hash]
if (i+1)%progressLogEvery == 0 || i == len(unreferencedBlobs)-1 {
log.Info("Deletion progress",
"deleted", i+1,
"total", len(unreferencedBlobs),
"percent", fmt.Sprintf("%.1f%%",
float64(i+1)/float64(len(unreferencedBlobs))*percentScale),
)
}
}
result.BlobsFailed = len(unreferencedBlobs) - result.BlobsDeleted
log.Info("Prune complete",
"deleted_count", result.BlobsDeleted,
"deleted_size", ubytes(result.BytesFreed),
"failed", result.BlobsFailed,
)
}
// outputPruneBlobsJSON outputs the prune result as JSON
func (v *Vaultik) outputPruneBlobsJSON(result *PruneBlobsResult) error {
encoder := json.NewEncoder(v.Stdout)
encoder.SetIndent("", " ")
return encoder.Encode(result)
}