Compare commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
43483e21d4 |
@@ -401,9 +401,7 @@ orphaned blob figures are reported as unknown; `--json` gives them as
|
|||||||
`null`, lists the remote key of each unreadable manifest in
|
`null`, lists the remote key of each unreadable manifest in
|
||||||
`unreadable_manifests` and counts the manifests under skipped names in
|
`unreadable_manifests` and counts the manifests under skipped names in
|
||||||
`skipped_manifest_count`. An unreadable manifest also leaves its
|
`skipped_manifest_count`. An unreadable manifest also leaves its
|
||||||
snapshot's blob count and blob size unknown, `null` in `--json`. A file
|
snapshot's blob count and blob size unknown, `null` in `--json`.
|
||||||
under `blobs/` whose name is not a blob hash is not counted as a blob,
|
|
||||||
since `prune` never deletes it.
|
|
||||||
* `--json`: Output as JSON
|
* `--json`: Output as JSON
|
||||||
|
|
||||||
**`remote nuke`**: Delete every snapshot's metadata and every blob from the
|
**`remote nuke`**: Delete every snapshot's metadata and every blob from the
|
||||||
|
|||||||
@@ -22,24 +22,14 @@ the tag exists and is exercised; what is left is merging `next` to
|
|||||||
|
|
||||||
# Completed Steps
|
# Completed Steps
|
||||||
|
|
||||||
- 2026-10-13: Made a `file://` destination list through a symlinked
|
- 2026-10-13: Made an S3 listing that the server cuts short an error
|
||||||
directory ([issue #296](https://git.eeqj.de/sneak/vaultik/issues/296)).
|
([issue #297](https://git.eeqj.de/sneak/vaultik/issues/297)). A page
|
||||||
A `metadata/` or `blobs/` directory that was a symlink to a directory
|
marked truncated with no continuation token, as a server answering V2
|
||||||
elsewhere was listed as one file, so the destination store listed as
|
listings V1-style sends, ended the listing without an error, so
|
||||||
empty while backups and restores still worked through the link.
|
`prune` saw only the snapshots on the first page and could delete
|
||||||
`prune` then removed the local snapshot records and deleted every blob,
|
blobs the rest still use. Such a page is now a listing error, and
|
||||||
and `remote info` and `remote nuke` found no blobs. The listings now
|
`prune`, `snapshot list` and `remote nuke` handle it as a destination
|
||||||
read through the link as `Get` and `Stat` do. A link whose target is
|
that cannot be listed.
|
||||||
missing, such as one to a volume that is not mounted, or a link
|
|
||||||
pointing back up the tree makes them fail.
|
|
||||||
|
|
||||||
- 2026-10-13: Stopped `remote info` counting a file under `blobs/` that
|
|
||||||
is not a blob as an orphaned blob
|
|
||||||
([issue #295](https://git.eeqj.de/sneak/vaultik/issues/295)). A stray
|
|
||||||
file such as `.DS_Store` was reported as an orphaned blob and the
|
|
||||||
report advised running `prune`, which skips such a file and deleted
|
|
||||||
nothing. `remote info` now takes its blob list from the same listing
|
|
||||||
`prune` uses, in the table and in `--json`.
|
|
||||||
|
|
||||||
- 2026-10-13: Made `snapshot remove` fail for a snapshot that does not
|
- 2026-10-13: Made `snapshot remove` fail for a snapshot that does not
|
||||||
exist ([issue #293](https://git.eeqj.de/sneak/vaultik/issues/293)).
|
exist ([issue #293](https://git.eeqj.de/sneak/vaultik/issues/293)).
|
||||||
|
|||||||
+29
-2
@@ -18,6 +18,13 @@ import (
|
|||||||
"github.com/aws/smithy-go/logging"
|
"github.com/aws/smithy-go/logging"
|
||||||
)
|
)
|
||||||
|
|
||||||
|
// ErrNoContinuationToken is returned by ListObjects and ListObjectsStream
|
||||||
|
// when the server marks a page of a listing truncated but sends no
|
||||||
|
// continuation token to fetch the rest with, as a server answering V2
|
||||||
|
// listings V1-style does.
|
||||||
|
var ErrNoContinuationToken = errors.New(
|
||||||
|
"server marked the listing truncated but sent no continuation token")
|
||||||
|
|
||||||
// Client wraps the AWS S3 client for vaultik operations.
|
// Client wraps the AWS S3 client for vaultik operations.
|
||||||
// It provides a simplified interface for S3 operations with automatic
|
// It provides a simplified interface for S3 operations with automatic
|
||||||
// prefix handling and connection management. All operations are performed
|
// prefix handling and connection management. All operations are performed
|
||||||
@@ -214,7 +221,7 @@ func (c *Client) ListObjects(ctx context.Context, prefix string) ([]string, erro
|
|||||||
})
|
})
|
||||||
|
|
||||||
for paginator.HasMorePages() {
|
for paginator.HasMorePages() {
|
||||||
page, err := paginator.NextPage(ctx)
|
page, err := nextListPage(ctx, paginator)
|
||||||
if err != nil {
|
if err != nil {
|
||||||
return nil, err
|
return nil, err
|
||||||
}
|
}
|
||||||
@@ -235,6 +242,26 @@ func (c *Client) ListObjects(ctx context.Context, prefix string) ([]string, erro
|
|||||||
return keys, nil
|
return keys, nil
|
||||||
}
|
}
|
||||||
|
|
||||||
|
// nextListPage fetches the next page of a listing. The SDK paginator takes
|
||||||
|
// a page marked truncated without a continuation token for the last page
|
||||||
|
// and stops without an error, so such a page is ErrNoContinuationToken
|
||||||
|
// here instead.
|
||||||
|
func nextListPage(
|
||||||
|
ctx context.Context, paginator *s3.ListObjectsV2Paginator,
|
||||||
|
) (*s3.ListObjectsV2Output, error) {
|
||||||
|
page, err := paginator.NextPage(ctx)
|
||||||
|
if err != nil {
|
||||||
|
return nil, err
|
||||||
|
}
|
||||||
|
|
||||||
|
truncated := aws.ToBool(page.IsTruncated)
|
||||||
|
if truncated && aws.ToString(page.NextContinuationToken) == "" {
|
||||||
|
return nil, ErrNoContinuationToken
|
||||||
|
}
|
||||||
|
|
||||||
|
return page, nil
|
||||||
|
}
|
||||||
|
|
||||||
// HeadObject checks if an object exists in S3.
|
// HeadObject checks if an object exists in S3.
|
||||||
// Returns true if the object exists, false otherwise.
|
// Returns true if the object exists, false otherwise.
|
||||||
// The key is automatically prefixed with the configured prefix.
|
// The key is automatically prefixed with the configured prefix.
|
||||||
@@ -300,7 +327,7 @@ func (c *Client) ListObjectsStream(
|
|||||||
})
|
})
|
||||||
|
|
||||||
for paginator.HasMorePages() {
|
for paginator.HasMorePages() {
|
||||||
page, err := paginator.NextPage(ctx)
|
page, err := nextListPage(ctx, paginator)
|
||||||
if err != nil {
|
if err != nil {
|
||||||
ch <- ObjectInfo{Err: err}
|
ch <- ObjectInfo{Err: err}
|
||||||
|
|
||||||
|
|||||||
+10
-45
@@ -120,10 +120,9 @@ func (f *FileStorer) Delete(_ context.Context, key string) error {
|
|||||||
return nil
|
return nil
|
||||||
}
|
}
|
||||||
|
|
||||||
// List returns all keys with the given prefix, reading through symlinked
|
// List returns all keys with the given prefix. It fails when the
|
||||||
// directories. It fails when the destination directory is missing or the
|
// destination directory is missing; a missing prefix under it is an
|
||||||
// prefix is a symlink whose target is missing; a missing prefix under the
|
// empty listing.
|
||||||
// destination directory is an empty listing.
|
|
||||||
func (f *FileStorer) List(ctx context.Context, prefix string) ([]string, error) {
|
func (f *FileStorer) List(ctx context.Context, prefix string) ([]string, error) {
|
||||||
var keys []string
|
var keys []string
|
||||||
|
|
||||||
@@ -134,7 +133,8 @@ func (f *FileStorer) List(ctx context.Context, prefix string) ([]string, error)
|
|||||||
|
|
||||||
basePath := f.fullPath(prefix)
|
basePath := f.fullPath(prefix)
|
||||||
|
|
||||||
exists, err := f.prefixExists(basePath)
|
// Check if the prefix exists
|
||||||
|
exists, err := afero.Exists(f.fs, basePath)
|
||||||
if err != nil {
|
if err != nil {
|
||||||
return nil, fmt.Errorf("checking path: %w", err)
|
return nil, fmt.Errorf("checking path: %w", err)
|
||||||
}
|
}
|
||||||
@@ -143,7 +143,7 @@ func (f *FileStorer) List(ctx context.Context, prefix string) ([]string, error)
|
|||||||
return keys, nil // Empty list for non-existent prefix
|
return keys, nil // Empty list for non-existent prefix
|
||||||
}
|
}
|
||||||
|
|
||||||
err = f.walk(basePath, func(path string, info os.FileInfo, err error) error {
|
err = afero.Walk(f.fs, basePath, func(path string, info os.FileInfo, err error) error {
|
||||||
if err != nil {
|
if err != nil {
|
||||||
return err
|
return err
|
||||||
}
|
}
|
||||||
@@ -176,9 +176,7 @@ func (f *FileStorer) List(ctx context.Context, prefix string) ([]string, error)
|
|||||||
}
|
}
|
||||||
|
|
||||||
// ListStream returns a channel of ObjectInfo for large result sets. Like
|
// ListStream returns a channel of ObjectInfo for large result sets. Like
|
||||||
// List, it reads through symlinked directories and sends an error when
|
// List, it sends an error when the destination directory is missing.
|
||||||
// the destination directory is missing or the prefix is a symlink whose
|
|
||||||
// target is missing.
|
|
||||||
func (f *FileStorer) ListStream(ctx context.Context, prefix string) <-chan ObjectInfo {
|
func (f *FileStorer) ListStream(ctx context.Context, prefix string) <-chan ObjectInfo {
|
||||||
ch := make(chan ObjectInfo)
|
ch := make(chan ObjectInfo)
|
||||||
|
|
||||||
@@ -194,7 +192,8 @@ func (f *FileStorer) ListStream(ctx context.Context, prefix string) <-chan Objec
|
|||||||
|
|
||||||
basePath := f.fullPath(prefix)
|
basePath := f.fullPath(prefix)
|
||||||
|
|
||||||
exists, err := f.prefixExists(basePath)
|
// Check if the prefix exists
|
||||||
|
exists, err := afero.Exists(f.fs, basePath)
|
||||||
if err != nil {
|
if err != nil {
|
||||||
ch <- ObjectInfo{Err: fmt.Errorf("checking path: %w", err)}
|
ch <- ObjectInfo{Err: fmt.Errorf("checking path: %w", err)}
|
||||||
|
|
||||||
@@ -205,7 +204,7 @@ func (f *FileStorer) ListStream(ctx context.Context, prefix string) <-chan Objec
|
|||||||
return // Empty channel for non-existent prefix
|
return // Empty channel for non-existent prefix
|
||||||
}
|
}
|
||||||
|
|
||||||
_ = f.walk(basePath, func(path string, info os.FileInfo, err error) error {
|
_ = afero.Walk(f.fs, basePath, func(path string, info os.FileInfo, err error) error {
|
||||||
// Check context cancellation
|
// Check context cancellation
|
||||||
select {
|
select {
|
||||||
case <-ctx.Done():
|
case <-ctx.Done():
|
||||||
@@ -353,40 +352,6 @@ func (f *FileStorer) writeAtomic(
|
|||||||
return nil
|
return nil
|
||||||
}
|
}
|
||||||
|
|
||||||
// walk is afero.Walk, except that it reads through a symlinked directory
|
|
||||||
// the way Get and Stat do, where afero.Walk reports the link as one file.
|
|
||||||
// afero.Walk uses Lstat, which does not follow a link, whenever the
|
|
||||||
// filesystem has one; the struct below carries only the afero.Fs methods,
|
|
||||||
// so the walk uses Stat instead. A link back up the tree is followed until
|
|
||||||
// the operating system refuses the path for too many levels of links, and
|
|
||||||
// the walk then fails.
|
|
||||||
func (f *FileStorer) walk(root string, fn filepath.WalkFunc) error {
|
|
||||||
return afero.Walk(struct{ afero.Fs }{f.fs}, root, fn)
|
|
||||||
}
|
|
||||||
|
|
||||||
// prefixExists is afero.Exists, except that it does not follow a symlink
|
|
||||||
// at path. A symlinked prefix whose target is missing, such as a link to
|
|
||||||
// a volume that is not mounted, therefore exists, and walk then fails on
|
|
||||||
// it; with afero.Exists it would list as empty, and prune would delete
|
|
||||||
// every blob.
|
|
||||||
func (f *FileStorer) prefixExists(path string) (bool, error) {
|
|
||||||
lstater, ok := f.fs.(afero.Lstater)
|
|
||||||
if !ok {
|
|
||||||
return afero.Exists(f.fs, path)
|
|
||||||
}
|
|
||||||
|
|
||||||
_, _, err := lstater.LstatIfPossible(path)
|
|
||||||
if err == nil {
|
|
||||||
return true, nil
|
|
||||||
}
|
|
||||||
|
|
||||||
if os.IsNotExist(err) {
|
|
||||||
return false, nil
|
|
||||||
}
|
|
||||||
|
|
||||||
return false, err
|
|
||||||
}
|
|
||||||
|
|
||||||
// fullPath returns the full filesystem path for a key.
|
// fullPath returns the full filesystem path for a key.
|
||||||
func (f *FileStorer) fullPath(key string) string {
|
func (f *FileStorer) fullPath(key string) string {
|
||||||
return filepath.Join(f.basePath, key)
|
return filepath.Join(f.basePath, key)
|
||||||
|
|||||||
@@ -4,10 +4,7 @@ import (
|
|||||||
"context"
|
"context"
|
||||||
"errors"
|
"errors"
|
||||||
"io/fs"
|
"io/fs"
|
||||||
"os"
|
|
||||||
"path/filepath"
|
"path/filepath"
|
||||||
"reflect"
|
|
||||||
"strings"
|
|
||||||
"testing"
|
"testing"
|
||||||
|
|
||||||
"sneak.berlin/go/vaultik/internal/storage"
|
"sneak.berlin/go/vaultik/internal/storage"
|
||||||
@@ -63,151 +60,3 @@ func TestFileStorerListMissingDestination(t *testing.T) {
|
|||||||
t.Errorf("ListStream error = %v, want a not-exist error", streamErr)
|
t.Errorf("ListStream error = %v, want a not-exist error", streamErr)
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
// TestFileStorerListsThroughSymlinkedDirectory checks that List and
|
|
||||||
// ListStream read through a symlinked metadata/ or blobs/ directory, as Get
|
|
||||||
// and Stat do, instead of listing the link as one key. Listing the whole
|
|
||||||
// destination meets the link part-way through the walk; listing its prefix
|
|
||||||
// starts the walk at the link.
|
|
||||||
func TestFileStorerListsThroughSymlinkedDirectory(t *testing.T) {
|
|
||||||
t.Parallel()
|
|
||||||
|
|
||||||
for _, dir := range []string{"metadata", "blobs"} {
|
|
||||||
t.Run(dir, func(t *testing.T) {
|
|
||||||
t.Parallel()
|
|
||||||
|
|
||||||
base := t.TempDir()
|
|
||||||
key := dir + "/aa/bb/object"
|
|
||||||
|
|
||||||
s, err := storage.NewFileStorer(base)
|
|
||||||
if err != nil {
|
|
||||||
t.Fatalf("NewFileStorer: %v", err)
|
|
||||||
}
|
|
||||||
|
|
||||||
err = s.Put(context.Background(), key, strings.NewReader("data"))
|
|
||||||
if err != nil {
|
|
||||||
t.Fatalf("Put: %v", err)
|
|
||||||
}
|
|
||||||
|
|
||||||
linkPath := filepath.Join(base, dir)
|
|
||||||
movedPath := filepath.Join(t.TempDir(), dir)
|
|
||||||
|
|
||||||
err = os.Rename(linkPath, movedPath)
|
|
||||||
if err != nil {
|
|
||||||
t.Fatalf("moving %s away: %v", dir, err)
|
|
||||||
}
|
|
||||||
|
|
||||||
err = os.Symlink(movedPath, linkPath)
|
|
||||||
if err != nil {
|
|
||||||
t.Fatalf("linking %s: %v", dir, err)
|
|
||||||
}
|
|
||||||
|
|
||||||
want := []string{key}
|
|
||||||
|
|
||||||
for _, prefix := range []string{"", dir + "/"} {
|
|
||||||
got := listSorted(t, s, prefix)
|
|
||||||
if !reflect.DeepEqual(got, want) {
|
|
||||||
t.Errorf("List(%q) = %v, want %v", prefix, got, want)
|
|
||||||
}
|
|
||||||
|
|
||||||
got = listStreamKeys(t, s, prefix)
|
|
||||||
if !reflect.DeepEqual(got, want) {
|
|
||||||
t.Errorf("ListStream(%q) = %v, want %v", prefix, got, want)
|
|
||||||
}
|
|
||||||
}
|
|
||||||
})
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
// TestFileStorerListFailsOnSymlinkWithMissingTarget checks that List and
|
|
||||||
// ListStream fail on a symlinked metadata/ or blobs/ directory whose target
|
|
||||||
// is missing, such as a link to a volume that is not mounted, as they do on
|
|
||||||
// a missing destination directory, instead of listing it as empty.
|
|
||||||
func TestFileStorerListFailsOnSymlinkWithMissingTarget(t *testing.T) {
|
|
||||||
t.Parallel()
|
|
||||||
|
|
||||||
ctx := context.Background()
|
|
||||||
|
|
||||||
for _, dir := range []string{"metadata", "blobs"} {
|
|
||||||
t.Run(dir, func(t *testing.T) {
|
|
||||||
t.Parallel()
|
|
||||||
|
|
||||||
base := t.TempDir()
|
|
||||||
|
|
||||||
s, err := storage.NewFileStorer(base)
|
|
||||||
if err != nil {
|
|
||||||
t.Fatalf("NewFileStorer: %v", err)
|
|
||||||
}
|
|
||||||
|
|
||||||
unmounted := filepath.Join(t.TempDir(), "unmounted")
|
|
||||||
|
|
||||||
err = os.Symlink(unmounted, filepath.Join(base, dir))
|
|
||||||
if err != nil {
|
|
||||||
t.Fatalf("Symlink: %v", err)
|
|
||||||
}
|
|
||||||
|
|
||||||
for _, prefix := range []string{"", dir + "/"} {
|
|
||||||
keys, err := s.List(ctx, prefix)
|
|
||||||
if !errors.Is(err, fs.ErrNotExist) {
|
|
||||||
t.Errorf("List(%q) = %v, %v; want a not-exist error",
|
|
||||||
prefix, keys, err)
|
|
||||||
}
|
|
||||||
|
|
||||||
var streamErr error
|
|
||||||
|
|
||||||
for object := range s.ListStream(ctx, prefix) {
|
|
||||||
if object.Err != nil {
|
|
||||||
streamErr = object.Err
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
if !errors.Is(streamErr, fs.ErrNotExist) {
|
|
||||||
t.Errorf("ListStream(%q) error = %v, want a not-exist error",
|
|
||||||
prefix, streamErr)
|
|
||||||
}
|
|
||||||
}
|
|
||||||
})
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
// TestFileStorerListFailsOnSymlinkLoop checks that a symlink pointing back
|
|
||||||
// at the destination makes List and ListStream fail instead of walking it
|
|
||||||
// forever.
|
|
||||||
func TestFileStorerListFailsOnSymlinkLoop(t *testing.T) {
|
|
||||||
t.Parallel()
|
|
||||||
|
|
||||||
ctx := context.Background()
|
|
||||||
base := t.TempDir()
|
|
||||||
|
|
||||||
s, err := storage.NewFileStorer(base)
|
|
||||||
if err != nil {
|
|
||||||
t.Fatalf("NewFileStorer: %v", err)
|
|
||||||
}
|
|
||||||
|
|
||||||
err = s.Put(ctx, testBlobKey, strings.NewReader("data"))
|
|
||||||
if err != nil {
|
|
||||||
t.Fatalf("Put: %v", err)
|
|
||||||
}
|
|
||||||
|
|
||||||
err = os.Symlink(base, filepath.Join(base, "blobs", "loop"))
|
|
||||||
if err != nil {
|
|
||||||
t.Fatalf("Symlink: %v", err)
|
|
||||||
}
|
|
||||||
|
|
||||||
keys, err := s.List(ctx, "blobs/")
|
|
||||||
if err == nil {
|
|
||||||
t.Errorf("List = %d keys and no error, want an error", len(keys))
|
|
||||||
}
|
|
||||||
|
|
||||||
var streamErr error
|
|
||||||
|
|
||||||
for object := range s.ListStream(ctx, "blobs/") {
|
|
||||||
if object.Err != nil {
|
|
||||||
streamErr = object.Err
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
if streamErr == nil {
|
|
||||||
t.Error("ListStream sent no error, want one")
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|||||||
@@ -4,6 +4,7 @@ import (
|
|||||||
"bytes"
|
"bytes"
|
||||||
"context"
|
"context"
|
||||||
"errors"
|
"errors"
|
||||||
|
"io"
|
||||||
"net/http"
|
"net/http"
|
||||||
"net/http/httptest"
|
"net/http/httptest"
|
||||||
"slices"
|
"slices"
|
||||||
@@ -22,13 +23,16 @@ import (
|
|||||||
// s3TestBucket is the bucket created for each in-process S3 server.
|
// s3TestBucket is the bucket created for each in-process S3 server.
|
||||||
const s3TestBucket = "test-bucket"
|
const s3TestBucket = "test-bucket"
|
||||||
|
|
||||||
// Credentials for the tests that build a storer from a config.Config. The
|
// Credentials for the tests' S3 clients. The test servers accept any.
|
||||||
// in-process S3 server accepts any.
|
|
||||||
const (
|
const (
|
||||||
s3TestAccessKeyID = "key"
|
s3TestAccessKeyID = "key"
|
||||||
s3TestSecretAccessKey = "secret"
|
s3TestSecretAccessKey = "secret"
|
||||||
)
|
)
|
||||||
|
|
||||||
|
// s3TestRegion is the region of the S3 clients built here with
|
||||||
|
// s3.NewClient. The test servers ignore it.
|
||||||
|
const s3TestRegion = "us-east-1"
|
||||||
|
|
||||||
// newS3Storer builds an s3:// backend backed by a fresh in-process
|
// newS3Storer builds an s3:// backend backed by a fresh in-process
|
||||||
// S3 server. It reuses the same in-memory S3 harness (gofakes3 + s3mem
|
// S3 server. It reuses the same in-memory S3 harness (gofakes3 + s3mem
|
||||||
// over httptest) that internal/s3 and the not-found regression test use,
|
// over httptest) that internal/s3 and the not-found regression test use,
|
||||||
@@ -55,7 +59,7 @@ func newS3Storer(t *testing.T) storage.Storer {
|
|||||||
Bucket: s3TestBucket,
|
Bucket: s3TestBucket,
|
||||||
AccessKeyID: "test",
|
AccessKeyID: "test",
|
||||||
SecretAccessKey: "test",
|
SecretAccessKey: "test",
|
||||||
Region: "us-east-1",
|
Region: s3TestRegion,
|
||||||
})
|
})
|
||||||
if err != nil {
|
if err != nil {
|
||||||
t.Fatalf("new client: %v", err)
|
t.Fatalf("new client: %v", err)
|
||||||
@@ -93,6 +97,68 @@ func TestS3StorerMissingKeyMapsToErrNotFound(t *testing.T) {
|
|||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
|
// TestS3ListingCutShortIsAnError checks that List and ListStream fail on a
|
||||||
|
// listing page marked truncated that carries no continuation token, as a
|
||||||
|
// server answering V2 listings V1-style sends it. Taken as the last page,
|
||||||
|
// it would hide every later key, and prune would treat the blobs of the
|
||||||
|
// snapshots listed there as unreferenced.
|
||||||
|
func TestS3ListingCutShortIsAnError(t *testing.T) {
|
||||||
|
t.Parallel()
|
||||||
|
|
||||||
|
const (
|
||||||
|
prefix = "metadata/"
|
||||||
|
truncatedPage = `<?xml version="1.0" encoding="UTF-8"?>
|
||||||
|
<ListBucketResult xmlns="http://s3.amazonaws.com/doc/2006-03-01/">
|
||||||
|
<Name>test-bucket</Name>
|
||||||
|
<Prefix>metadata/</Prefix>
|
||||||
|
<KeyCount>1</KeyCount>
|
||||||
|
<MaxKeys>1</MaxKeys>
|
||||||
|
<IsTruncated>true</IsTruncated>
|
||||||
|
<Contents>
|
||||||
|
<Key>metadata/snap/manifest.json.zst</Key>
|
||||||
|
<Size>8</Size>
|
||||||
|
</Contents>
|
||||||
|
</ListBucketResult>`
|
||||||
|
)
|
||||||
|
|
||||||
|
srv := httptest.NewServer(http.HandlerFunc(
|
||||||
|
func(w http.ResponseWriter, _ *http.Request) {
|
||||||
|
_, _ = io.WriteString(w, truncatedPage)
|
||||||
|
}))
|
||||||
|
t.Cleanup(srv.Close)
|
||||||
|
|
||||||
|
client, err := s3.NewClient(context.Background(), s3.Config{
|
||||||
|
Endpoint: srv.URL,
|
||||||
|
Bucket: s3TestBucket,
|
||||||
|
AccessKeyID: s3TestAccessKeyID,
|
||||||
|
SecretAccessKey: s3TestSecretAccessKey,
|
||||||
|
Region: s3TestRegion,
|
||||||
|
})
|
||||||
|
if err != nil {
|
||||||
|
t.Fatalf("new client: %v", err)
|
||||||
|
}
|
||||||
|
|
||||||
|
storer := storage.NewS3Storer(client)
|
||||||
|
ctx := context.Background()
|
||||||
|
|
||||||
|
keys, err := storer.List(ctx, prefix)
|
||||||
|
if !errors.Is(err, s3.ErrNoContinuationToken) {
|
||||||
|
t.Errorf("List = %q, %v; want ErrNoContinuationToken", keys, err)
|
||||||
|
}
|
||||||
|
|
||||||
|
var streamErr error
|
||||||
|
|
||||||
|
for obj := range storer.ListStream(ctx, prefix) {
|
||||||
|
if obj.Err != nil {
|
||||||
|
streamErr = obj.Err
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
if !errors.Is(streamErr, s3.ErrNoContinuationToken) {
|
||||||
|
t.Errorf("ListStream error = %v, want ErrNoContinuationToken", streamErr)
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
// TestS3URLPrefixKeyLayout pins the bucket keys an s3:// URL reads and
|
// TestS3URLPrefixKeyLayout pins the bucket keys an s3:// URL reads and
|
||||||
// writes: the README's remote storage layout, with the prefix joined to
|
// writes: the README's remote storage layout, with the prefix joined to
|
||||||
// each key by one "/". s3://b/p and s3://b/p/ must be the same
|
// each key by one "/". s3://b/p and s3://b/p/ must be the same
|
||||||
|
|||||||
@@ -167,6 +167,10 @@ const (
|
|||||||
// metadataKeyParts is the minimum "/"-separated segment count of a
|
// metadataKeyParts is the minimum "/"-separated segment count of a
|
||||||
// metadata object key (metadata/<snapshot-id>/<filename>).
|
// metadata object key (metadata/<snapshot-id>/<filename>).
|
||||||
metadataKeyParts = 3
|
metadataKeyParts = 3
|
||||||
|
|
||||||
|
// blobKeyParts is the minimum "/"-separated segment count of a blob
|
||||||
|
// object key (blobs/<aa>/<bb>/<hash>).
|
||||||
|
blobKeyParts = 4
|
||||||
)
|
)
|
||||||
|
|
||||||
// SnapshotMetadataInfo contains information about a single snapshot's metadata
|
// SnapshotMetadataInfo contains information about a single snapshot's metadata
|
||||||
@@ -450,16 +454,23 @@ func (v *Vaultik) scanRemoteBlobStorage(
|
|||||||
v.stdoutf("Scanning blobs...\n")
|
v.stdoutf("Scanning blobs...\n")
|
||||||
}
|
}
|
||||||
|
|
||||||
// Use prune's listing, so a file under blobs/ that prune would never
|
blobCh := v.Storage.ListStream(v.ctx, "blobs/")
|
||||||
// delete is not counted as a blob, and so not as an orphaned one.
|
allBlobs := make(map[string]int64)
|
||||||
allBlobs, err := v.listAllRemoteBlobs()
|
|
||||||
if err != nil {
|
|
||||||
return err
|
|
||||||
}
|
|
||||||
|
|
||||||
for _, size := range allBlobs {
|
for obj := range blobCh {
|
||||||
|
if obj.Err != nil {
|
||||||
|
return fmt.Errorf("listing blobs: %w", obj.Err)
|
||||||
|
}
|
||||||
|
|
||||||
|
parts := strings.Split(obj.Key, "/")
|
||||||
|
if len(parts) < blobKeyParts {
|
||||||
|
continue
|
||||||
|
}
|
||||||
|
|
||||||
|
hash := parts[3]
|
||||||
|
allBlobs[hash] = obj.Size
|
||||||
result.TotalBlobCount++
|
result.TotalBlobCount++
|
||||||
result.TotalBlobSize += size
|
result.TotalBlobSize += obj.Size
|
||||||
}
|
}
|
||||||
|
|
||||||
// A blob named only by a manifest that could not be read, or by one
|
// A blob named only by a manifest that could not be read, or by one
|
||||||
|
|||||||
@@ -23,10 +23,6 @@ var errNukeRequiresForce = errors.New(
|
|||||||
// metadata.
|
// metadata.
|
||||||
const metadataDirName = "metadata"
|
const metadataDirName = "metadata"
|
||||||
|
|
||||||
// blobKeyParts is the "/"-separated segment count of a blob object key
|
|
||||||
// (blobs/<aa>/<bb>/<hash>).
|
|
||||||
const blobKeyParts = 4
|
|
||||||
|
|
||||||
// NukeRemote deletes every snapshot's metadata and every blob from remote
|
// NukeRemote deletes every snapshot's metadata and every blob from remote
|
||||||
// storage, along with any object an upload cut off part-way left under a
|
// storage, along with any object an upload cut off part-way left under a
|
||||||
// temporary `.partial` name. After this returns successfully the bucket
|
// temporary `.partial` name. After this returns successfully the bucket
|
||||||
|
|||||||
@@ -185,39 +185,6 @@ func TestRemoteInfo_SkipsNonConformingMetadataName(t *testing.T) {
|
|||||||
assert.NotContains(t, doc, "unreadable_manifests")
|
assert.NotContains(t, doc, "unreadable_manifests")
|
||||||
}
|
}
|
||||||
|
|
||||||
// TestRemoteInfo_DoesNotCountNonBlobFileUnderBlobs checks that a file
|
|
||||||
// under blobs/ whose name is not a blob hash is not counted as a blob.
|
|
||||||
// prune never deletes such a file, so counting it as an orphaned blob
|
|
||||||
// would advise a prune that removes nothing.
|
|
||||||
func TestRemoteInfo_DoesNotCountNonBlobFileUnderBlobs(t *testing.T) {
|
|
||||||
log.Initialize(log.Config{})
|
|
||||||
t.Parallel()
|
|
||||||
|
|
||||||
env := newListEnv(t)
|
|
||||||
env.addRemote(t, listRemoteID, time.Date(2026, 3, 2, 0, 0, 0, 0, time.UTC))
|
|
||||||
addBlob(t, env.store.testStorer, testBlobHashA)
|
|
||||||
require.NoError(t, env.store.Put(context.Background(),
|
|
||||||
"blobs/"+testBlobHashA[:2]+"/"+testBlobHashA[2:4]+"/.DS_Store",
|
|
||||||
bytes.NewReader([]byte("junk"))))
|
|
||||||
|
|
||||||
require.NoError(t, env.v.RemoteInfo(false))
|
|
||||||
|
|
||||||
text := env.stdout.String()
|
|
||||||
assert.Contains(t, text, "Total blobs on remote: 1 (")
|
|
||||||
assert.Contains(t, text, "Orphaned (unreferenced): 0 (")
|
|
||||||
assert.NotContains(t, text, "vaultik prune")
|
|
||||||
|
|
||||||
env.stdout.Reset()
|
|
||||||
require.NoError(t, env.v.RemoteInfo(true))
|
|
||||||
|
|
||||||
var doc map[string]any
|
|
||||||
|
|
||||||
require.NoError(t, json.Unmarshal(env.stdout.Bytes(), &doc))
|
|
||||||
assert.InDelta(t, 1, doc["total_blob_count"], 0)
|
|
||||||
assert.InDelta(t, 0, doc["orphaned_blob_count"], 0)
|
|
||||||
assert.InDelta(t, 0, doc["orphaned_blob_size"], 0)
|
|
||||||
}
|
|
||||||
|
|
||||||
// TestRemoteInfo_DirectoryWithoutManifestLeavesOrphansKnown checks that
|
// TestRemoteInfo_DirectoryWithoutManifestLeavesOrphansKnown checks that
|
||||||
// a directory under metadata/ holding no manifest.json.zst, such as one
|
// a directory under metadata/ holding no manifest.json.zst, such as one
|
||||||
// left by a backup interrupted before its manifest upload, leaves the
|
// left by a backup interrupted before its manifest upload, leaves the
|
||||||
|
|||||||
@@ -1,121 +0,0 @@
|
|||||||
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/vaultik"
|
|
||||||
)
|
|
||||||
|
|
||||||
// TestPruneDeletesNothingThroughSymlinkedDirectory checks that prune keeps
|
|
||||||
// every blob and the local snapshot record when the metadata/ or blobs/
|
|
||||||
// directory of a file:// destination is a symlink to a directory elsewhere
|
|
||||||
// (https://git.eeqj.de/sneak/vaultik/issues/296). A backup writes through
|
|
||||||
// such a link, so prune has to list through it too.
|
|
||||||
func TestPruneDeletesNothingThroughSymlinkedDirectory(t *testing.T) {
|
|
||||||
log.Initialize(log.Config{})
|
|
||||||
t.Parallel()
|
|
||||||
|
|
||||||
for _, dir := range []string{"metadata", "blobs"} {
|
|
||||||
t.Run(dir, func(t *testing.T) {
|
|
||||||
t.Parallel()
|
|
||||||
|
|
||||||
ctx := context.Background()
|
|
||||||
storeDir := filepath.Join(t.TempDir(), "store")
|
|
||||||
v, repos, _ := backUpToFileDestination(ctx, t, storeDir)
|
|
||||||
blobFiles := blobFilesIn(t, storeDir)
|
|
||||||
moveBehindSymlink(t, storeDir, dir)
|
|
||||||
|
|
||||||
require.NoError(t, v.Prune(&vaultik.PruneOptions{Force: true}))
|
|
||||||
|
|
||||||
// When blobs/ is the link, these paths run through it.
|
|
||||||
for _, blobFile := range blobFiles {
|
|
||||||
assert.FileExists(t, blobFile, "prune must delete no blob")
|
|
||||||
}
|
|
||||||
|
|
||||||
snapshots, err := repos.Snapshots.ListRecent(ctx, listRecentTestLimit)
|
|
||||||
require.NoError(t, err)
|
|
||||||
assert.Len(t, snapshots, 1, "prune must delete no local snapshot record")
|
|
||||||
})
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
// TestPruneFailsOnSymlinkedDirectoryWithMissingTarget checks that prune
|
|
||||||
// fails, deleting no blob and keeping the local snapshot record, when the
|
|
||||||
// metadata/ or blobs/ directory of a file:// destination is a symlink
|
|
||||||
// whose target is missing, as a link to a volume that is not mounted is.
|
|
||||||
func TestPruneFailsOnSymlinkedDirectoryWithMissingTarget(t *testing.T) {
|
|
||||||
log.Initialize(log.Config{})
|
|
||||||
t.Parallel()
|
|
||||||
|
|
||||||
for _, dir := range []string{"metadata", "blobs"} {
|
|
||||||
t.Run(dir, func(t *testing.T) {
|
|
||||||
t.Parallel()
|
|
||||||
|
|
||||||
ctx := context.Background()
|
|
||||||
storeDir := filepath.Join(t.TempDir(), "store")
|
|
||||||
v, repos, _ := backUpToFileDestination(ctx, t, storeDir)
|
|
||||||
blobFiles := blobFilesIn(t, storeDir)
|
|
||||||
targetPath := moveBehindSymlink(t, storeDir, dir)
|
|
||||||
|
|
||||||
// Unmount the volume the link points to, and mount it again
|
|
||||||
// once prune has run.
|
|
||||||
unmountedPath := targetPath + "-unmounted"
|
|
||||||
require.NoError(t, os.Rename(targetPath, unmountedPath))
|
|
||||||
|
|
||||||
err := v.Prune(&vaultik.PruneOptions{Force: true})
|
|
||||||
require.ErrorIs(t, err, fs.ErrNotExist)
|
|
||||||
|
|
||||||
require.NoError(t, os.Rename(unmountedPath, targetPath))
|
|
||||||
|
|
||||||
// When blobs/ is the link, these paths run through it.
|
|
||||||
for _, blobFile := range blobFiles {
|
|
||||||
assert.FileExists(t, blobFile, "prune must delete no blob")
|
|
||||||
}
|
|
||||||
|
|
||||||
snapshots, err := repos.Snapshots.ListRecent(ctx, listRecentTestLimit)
|
|
||||||
require.NoError(t, err)
|
|
||||||
assert.Len(t, snapshots, 1, "prune must delete no local snapshot record")
|
|
||||||
})
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
// blobFilesIn returns the paths of the blob files under storeDir/blobs, and
|
|
||||||
// fails the test when there are none.
|
|
||||||
func blobFilesIn(t *testing.T, storeDir string) []string {
|
|
||||||
t.Helper()
|
|
||||||
|
|
||||||
var blobFiles []string
|
|
||||||
|
|
||||||
err := filepath.WalkDir(filepath.Join(storeDir, "blobs"),
|
|
||||||
func(path string, entry fs.DirEntry, err error) error {
|
|
||||||
if err == nil && !entry.IsDir() {
|
|
||||||
blobFiles = append(blobFiles, path)
|
|
||||||
}
|
|
||||||
|
|
||||||
return err
|
|
||||||
})
|
|
||||||
require.NoError(t, err)
|
|
||||||
require.NotEmpty(t, blobFiles)
|
|
||||||
|
|
||||||
return blobFiles
|
|
||||||
}
|
|
||||||
|
|
||||||
// moveBehindSymlink moves storeDir/dir to a directory elsewhere, puts a
|
|
||||||
// symlink to it in its place, and returns where it went.
|
|
||||||
func moveBehindSymlink(t *testing.T, storeDir, dir string) string {
|
|
||||||
t.Helper()
|
|
||||||
|
|
||||||
linkPath := filepath.Join(storeDir, dir)
|
|
||||||
targetPath := filepath.Join(t.TempDir(), dir)
|
|
||||||
require.NoError(t, os.Rename(linkPath, targetPath))
|
|
||||||
require.NoError(t, os.Symlink(targetPath, linkPath))
|
|
||||||
|
|
||||||
return targetPath
|
|
||||||
}
|
|
||||||
Reference in New Issue
Block a user