Make remote nuke delete leftover .partial uploads (closes #281)
check / check (push) Canceled after 0s
check / check (push) Canceled after 0s
The file and rclone listings skip an object whose name ends in `.partial`, the temporary name a `file://` or rclone upload writes before moving the object into place. `remote nuke` deletes only what the listings return, so it left the `.partial` objects killed uploads leave behind and still reported the destination store empty. Storer gains DeletePartialUploads. The file and rclone backends remove every `.partial` object under the prefix; S3 has none to remove, since it shows an object only once its upload completes. `remote nuke` calls it for `metadata/` and `blobs/` as its last step. Empty directories under a `file://` destination are still left behind. Model: opus-5-5
This commit was merged in pull request #283.
This commit is contained in:
@@ -257,6 +257,10 @@ func (s *stubLister) List(_ context.Context, _ string) ([]string, error) {
|
||||
return nil, errStubUnused
|
||||
}
|
||||
|
||||
func (s *stubLister) DeletePartialUploads(_ context.Context, _ string) error {
|
||||
return errStubUnused
|
||||
}
|
||||
|
||||
func (s *stubLister) Info() storage.Info {
|
||||
return storage.Info{}
|
||||
}
|
||||
|
||||
@@ -155,6 +155,12 @@ func (m *MockStorer) ListStream(
|
||||
return ch
|
||||
}
|
||||
|
||||
// DeletePartialUploads has nothing to remove: Put stores each object
|
||||
// under its key at once.
|
||||
func (m *MockStorer) DeletePartialUploads(_ context.Context, _ string) error {
|
||||
return nil
|
||||
}
|
||||
|
||||
func (m *MockStorer) Info() storage.Info {
|
||||
return storage.Info{
|
||||
Type: "mock",
|
||||
|
||||
@@ -0,0 +1,64 @@
|
||||
package vaultik_test
|
||||
|
||||
import (
|
||||
"context"
|
||||
"io/fs"
|
||||
"os"
|
||||
"path/filepath"
|
||||
"testing"
|
||||
|
||||
"github.com/stretchr/testify/assert"
|
||||
"github.com/stretchr/testify/require"
|
||||
"sneak.berlin/go/vaultik/internal/log"
|
||||
"sneak.berlin/go/vaultik/internal/snapshot"
|
||||
)
|
||||
|
||||
// TestNukeRemoteLeavesNoFiles checks that remote nuke leaves no file
|
||||
// under a file:// destination, including the `.partial` files uploads
|
||||
// killed part-way leave next to a snapshot's metadata and next to where a
|
||||
// blob would have been.
|
||||
func TestNukeRemoteLeavesNoFiles(t *testing.T) {
|
||||
log.Initialize(log.Config{})
|
||||
t.Parallel()
|
||||
|
||||
ctx := context.Background()
|
||||
storeDir := filepath.Join(t.TempDir(), "store")
|
||||
v, repos, _ := backUpToFileDestination(ctx, t, storeDir)
|
||||
|
||||
snapshots, err := repos.Snapshots.ListRecent(ctx, listRecentTestLimit)
|
||||
require.NoError(t, err)
|
||||
require.Len(t, snapshots, 1)
|
||||
|
||||
snapshotKey := snapshot.RemoteSnapshotKey(snapshots[0].ID.String())
|
||||
hash := testBlobHashA
|
||||
leftovers := []string{
|
||||
filepath.Join(storeDir, "metadata", snapshotKey,
|
||||
"db.zst.age-123456.partial"),
|
||||
filepath.Join(storeDir, "blobs", hash[:2], hash[2:4],
|
||||
hash+"-123456.partial"),
|
||||
}
|
||||
|
||||
for _, leftover := range leftovers {
|
||||
require.NoError(t, os.MkdirAll(filepath.Dir(leftover), 0o750))
|
||||
require.NoError(t, os.WriteFile(leftover, []byte("half an upload"), 0o600))
|
||||
}
|
||||
|
||||
require.NoError(t, v.NukeRemote(true))
|
||||
|
||||
var files []string
|
||||
|
||||
err = filepath.WalkDir(storeDir,
|
||||
func(path string, entry fs.DirEntry, err error) error {
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
|
||||
if !entry.IsDir() {
|
||||
files = append(files, path)
|
||||
}
|
||||
|
||||
return nil
|
||||
})
|
||||
require.NoError(t, err)
|
||||
assert.Empty(t, files)
|
||||
}
|
||||
@@ -24,8 +24,9 @@ var errNukeRequiresForce = errors.New(
|
||||
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.
|
||||
// storage, along with any object an upload cut off part-way left under a
|
||||
// temporary `.partial` name. 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.
|
||||
@@ -48,6 +49,15 @@ func (v *Vaultik) NukeRemote(force bool) error {
|
||||
return fmt.Errorf("pruning blobs: %w", err)
|
||||
}
|
||||
|
||||
// The file and rclone listings skip `.partial` objects, so the two
|
||||
// steps above never delete them.
|
||||
for _, prefix := range []string{"metadata/", "blobs/"} {
|
||||
err = v.Storage.DeletePartialUploads(v.ctx, prefix)
|
||||
if err != nil {
|
||||
return fmt.Errorf("deleting partial uploads: %w", err)
|
||||
}
|
||||
}
|
||||
|
||||
v.UI.Completef("Backup destination store is now empty.")
|
||||
|
||||
return nil
|
||||
|
||||
@@ -125,6 +125,12 @@ func (s *testStorer) ListStream(
|
||||
return ch
|
||||
}
|
||||
|
||||
// DeletePartialUploads has nothing to remove: Put stores each object
|
||||
// under its key at once.
|
||||
func (s *testStorer) DeletePartialUploads(_ context.Context, _ string) error {
|
||||
return nil
|
||||
}
|
||||
|
||||
func (s *testStorer) Info() storage.Info {
|
||||
return storage.Info{
|
||||
Type: testLabel,
|
||||
|
||||
Reference in New Issue
Block a user