2 Commits
Author SHA1 Message Date
clawbot 716fb0453d List a file:// destination through a symlinked directory (closes #296)
check / check (push) Successful in 10m57s
List and ListStream walked the destination with afero.Walk, which uses
Lstat and so reported a symlinked metadata/ or blobs/ directory as one
file, while Put, Get and Stat follow the link. The store then listed as
empty, and prune removed the local snapshot records and deleted every
blob. Both listings now walk a view of the filesystem without its Lstat
method, so afero falls back to Stat and enters the link. A listed prefix
that is a symlink whose target is missing, such as a link to a volume
that is not mounted, fails the listing, as a missing destination
directory does.

A symlink loop is not detected: it is followed until the system refuses
the path for too many levels of links, and the listing fails.

Model: opus-5-5
2026-10-13 07:35:41 +00:00
clawbot 07c957f84b Bind the local index to the s3.* destination too (closes #298)
check / check (push) Successful in 15m35s
The local index was bound to its destination only through storage_url.
With the s3.* form nothing was checked, so after s3.bucket or s3.prefix
changed the next backup treated every chunk as already stored, uploaded
nothing, and completed a snapshot that could not be restored.

Without storage_url, the binding now records the destination the s3.*
fields name, written as an s3:// URL from s3.endpoint, s3.bucket and
s3.prefix, and a change is refused with the same error and advice. The
advice line now names the s3.* fields as well as storage_url.

Judgement call: the fields are compared as written, so an equivalent
spelling (a trailing slash on the prefix, a scheme on the endpoint) is
also refused, as it already is for storage_url.

Model: opus-5-5
2026-10-13 03:48:36 +02:00
7 changed files with 229 additions and 38 deletions
+2 -1
View File
@@ -412,7 +412,8 @@ destination store.
entirely. Remote storage is unaffected; the next backup will do a full
scan and re-deduplicate against existing remote blobs, and the local
index will re-bind to the currently configured storage destination.
Use this after changing `storage_url` to a different destination.
Use this after changing `storage_url`, or `s3.endpoint`, `s3.bucket` or
`s3.prefix`, to a different destination.
* `--force`: Skip confirmation prompt
---
+12 -2
View File
@@ -29,8 +29,18 @@ the tag exists and is exercised; what is left is merging `next` to
empty while backups and restores still worked through the link.
`prune` then removed the local snapshot records and deleted every blob,
and `remote info` and `remote nuke` found no blobs. The listings now
read through the link as `Get` and `Stat` do; a link pointing back up
the tree makes them fail.
read through the link as `Get` and `Stat` do. A link whose target is
missing, such as one to a volume that is not mounted, or a link
pointing back up the tree makes them fail.
- 2026-10-12: Bound the local index to the destination an `s3.*` config
names ([issue #298](https://git.eeqj.de/sneak/vaultik/issues/298)).
Only `storage_url` was checked, so after `s3.bucket` or `s3.prefix`
changed, the next backup treated every chunk as already stored,
uploaded nothing, and completed a snapshot that could not be restored.
Without `storage_url`, the local index is now bound to `s3.endpoint`,
`s3.bucket` and `s3.prefix`, and a change is refused as a changed
`storage_url` is.
- 2026-10-12: Rejected a retention duration longer than about 292 years
([issue #289](https://git.eeqj.de/sneak/vaultik/issues/289)). The
+30 -7
View File
@@ -121,8 +121,9 @@ func (f *FileStorer) Delete(_ context.Context, key string) error {
}
// List returns all keys with the given prefix, reading through symlinked
// directories. It fails when the destination directory is missing; a
// missing prefix under it is an empty listing.
// directories. It fails when the destination directory is missing or the
// prefix is a symlink whose target is missing; a missing prefix under the
// destination directory is an empty listing.
func (f *FileStorer) List(ctx context.Context, prefix string) ([]string, error) {
var keys []string
@@ -133,8 +134,7 @@ func (f *FileStorer) List(ctx context.Context, prefix string) ([]string, error)
basePath := f.fullPath(prefix)
// Check if the prefix exists
exists, err := afero.Exists(f.fs, basePath)
exists, err := f.prefixExists(basePath)
if err != nil {
return nil, fmt.Errorf("checking path: %w", err)
}
@@ -177,7 +177,8 @@ func (f *FileStorer) List(ctx context.Context, prefix string) ([]string, error)
// ListStream returns a channel of ObjectInfo for large result sets. Like
// List, it reads through symlinked directories and 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 {
ch := make(chan ObjectInfo)
@@ -193,8 +194,7 @@ func (f *FileStorer) ListStream(ctx context.Context, prefix string) <-chan Objec
basePath := f.fullPath(prefix)
// Check if the prefix exists
exists, err := afero.Exists(f.fs, basePath)
exists, err := f.prefixExists(basePath)
if err != nil {
ch <- ObjectInfo{Err: fmt.Errorf("checking path: %w", err)}
@@ -364,6 +364,29 @@ 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.
func (f *FileStorer) fullPath(key string) string {
return filepath.Join(f.basePath, key)
+51
View File
@@ -119,6 +119,57 @@ func TestFileStorerListsThroughSymlinkedDirectory(t *testing.T) {
}
}
// 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.
+10 -10
View File
@@ -9,7 +9,7 @@ import (
)
// errStorageBindingMismatch is returned when the local index database is
// bound to a different destination than the configured storage_url.
// bound to a different destination than the configured one.
var errStorageBindingMismatch = errors.New(
"local index is bound to a different backup destination")
@@ -24,8 +24,9 @@ var errStorageBindingMismatch = errors.New(
//
// Behaviour:
// - On first use (empty stored value), record the configured
// storage_url and log the binding.
// - When the stored value matches the configured storage_url, do
// destination (storage_url, or the s3.* endpoint, bucket and
// prefix) and log the binding.
// - When the stored value matches the configured destination, do
// nothing and return nil.
// - When the two differ, refuse with an error that tells the user
// how to recover (revert the config, or run `vaultik database
@@ -46,12 +47,10 @@ func (v *Vaultik) EnsureStorageBinding() error {
configured := v.Config.StorageURL
if configured == "" {
// Some legacy configs still use the split s3.* keys instead of
// storage_url. Falling back to a synthetic URL for those would
// hide the fact that the binding is loose. Instead, treat
// unset as "nothing to bind against" — the check is
// necessarily best-effort for those configs.
return nil
// The s3.* form: bind on its endpoint, bucket and prefix,
// written the way storage_url would name the same destination.
s3 := v.Config.S3
configured = "s3://" + s3.Bucket + "/" + s3.Prefix + "?endpoint=" + s3.Endpoint
}
stored, err := v.Repositories.LocalMeta.Get(v.ctx, database.LocalMetaKeyStorageURL)
@@ -96,7 +95,8 @@ func buildBindingMismatchMessage(stored, configured string) string {
"future snapshots referencing blobs that don't exist at the new destination.\n" +
"\n" +
"To proceed, either:\n" +
" - revert storage_url in your config to the bound destination, or\n" +
" - revert storage_url (or the s3.* endpoint, bucket and prefix) in your\n" +
" config to the bound destination, or\n" +
" - run 'vaultik database delete' to discard the local index and rebuild it\n" +
" from a fresh full backup against the new destination"
}
+48
View File
@@ -76,3 +76,51 @@ func TestEnsureStorageBinding_MismatchRefuses(t *testing.T) {
assert.Contains(t, err.Error(), "file:///mnt/backups/new")
assert.Contains(t, err.Error(), "vaultik database delete")
}
// A config with no storage_url names its destination with s3.endpoint,
// s3.bucket and s3.prefix; a change to any of them must be refused just
// as a changed storage_url is.
func TestEnsureStorageBinding_S3FieldsChangeRefuses(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
bound := config.S3Config{
Endpoint: "https://s3.example.com",
Bucket: "bucket-a",
Prefix: "backups",
}
tests := []struct {
name string
changed config.S3Config
}{
{"bucket", config.S3Config{
Endpoint: bound.Endpoint, Bucket: "bucket-b", Prefix: bound.Prefix,
}},
{"prefix", config.S3Config{
Endpoint: bound.Endpoint, Bucket: bound.Bucket, Prefix: "other",
}},
{"endpoint", config.S3Config{
Endpoint: "https://s3.other.com", Bucket: bound.Bucket, Prefix: bound.Prefix,
}},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
t.Parallel()
tv, _ := buildBindTestVaultik(t, "")
tv.Config.S3 = bound
require.NoError(t, tv.EnsureStorageBinding(), "first use binds")
require.NoError(t, tv.EnsureStorageBinding(), "same destination passes")
tv.Config.S3 = tt.changed
err := tv.EnsureStorageBinding()
require.Error(t, err)
assert.Contains(t, err.Error(),
"local index is bound to a different backup destination")
assert.Contains(t, err.Error(), "vaultik database delete")
})
}
}
+76 -18
View File
@@ -29,24 +29,8 @@ func TestPruneDeletesNothingThroughSymlinkedDirectory(t *testing.T) {
ctx := context.Background()
storeDir := filepath.Join(t.TempDir(), "store")
v, repos, _ := backUpToFileDestination(ctx, t, storeDir)
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)
linkPath := filepath.Join(storeDir, dir)
movedPath := filepath.Join(t.TempDir(), dir)
require.NoError(t, os.Rename(linkPath, movedPath))
require.NoError(t, os.Symlink(movedPath, linkPath))
blobFiles := blobFilesIn(t, storeDir)
moveBehindSymlink(t, storeDir, dir)
require.NoError(t, v.Prune(&vaultik.PruneOptions{Force: true}))
@@ -61,3 +45,77 @@ func TestPruneDeletesNothingThroughSymlinkedDirectory(t *testing.T) {
})
}
}
// 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
}