Compare commits

..
Author SHA1 Message Date
sneak 4e084a2746 Check storage_url with the storage parser at config load (closes #468)
check / check (push) Successful in 11m20s
config set accepted rclone:// values that every command then refused:
no remote name, parameters in the remote name, a query parameter. The
config only checked the URL's prefix, because config could not import
the parser from storage, which imports config.

The parser moves from internal/storage to a new package,
internal/storageurl, that both import. ParseStorageURL becomes
storageurl.Parse. Loading the config now runs it on every storage_url,
so config set refuses such a value and leaves the file unchanged.

Model: opus-5-5
2026-11-19 07:24:47 +00:00
15 changed files with 172 additions and 567 deletions

No files matched your search

+1 -9
View File
@@ -602,11 +602,7 @@ only `vaultik-destination.txt` stops such a backup, and only while the local
index holds snapshots.
**Rclone** (`rclone://remote/path`): Uses rclone's 70+ supported cloud
providers. Requires rclone to be configured separately (`rclone config`). The
path after the remote name is relative: rclone resolves it on the remote, for
example against the login directory on sftp. A second slash makes it absolute,
as in `rclone://remote//srv/backup`. A remote of type `local` needs an absolute
path; a relative one is refused.
providers. Requires rclone to be configured separately (`rclone config`).
An upload cut off part-way leaves nothing under the object's name on S3, which
shows an object only once its upload has completed, and on the local filesystem
@@ -618,10 +614,6 @@ being written, a killed upload can leave a truncated object under its name,
which a later backup takes for complete. A leftover `.partial` file is ignored
and can be deleted.
A blob upload that fails, such as one cut off by a lost connection, is tried
again up to five times, three seconds apart. Each new try is announced with a
warning. If the last try fails too, the backup stops with the upload's error.
A destination shared between hosts or users, each with its own local index,
relies on `prune_grace_period` to keep one's prune from deleting the blobs of
another's backup still running, or its directory under `metadata/` that has no
+7
View File
@@ -282,6 +282,13 @@ func TestConfigSetKeepsFileThatWouldNotLoad(t *testing.T) {
storageURLKey, testS3URL,
"s3.secret_access_key is required for s3:// URLs; " +
"set s3.access_key_id and s3.secret_access_key first"},
// rclone:// URLs that no command could open.
{configWithoutRecipients, storageURLKey, "rclone:///backups",
"rclone URL missing remote name"},
{configWithoutRecipients, storageURLKey, "rclone://dav,user=x/backups",
"rclone URL must not carry parameters in the remote name"},
{configWithoutRecipients, storageURLKey, "rclone://dav/backups?x=1",
`unknown query parameter in storage URL: "x"`},
// With its reference filled in, the config loads.
{levelReference, "blob_size_limit", "1MB",
"blob_size_limit must be at least"},
+24 -37
View File
@@ -21,6 +21,7 @@ import (
"gopkg.in/yaml.v3"
"sneak.berlin/go/vaultik/internal/chunker"
"sneak.berlin/go/vaultik/internal/log"
"sneak.berlin/go/vaultik/internal/storageurl"
)
const appName = "vaultik"
@@ -63,13 +64,8 @@ var (
errBlobSizeTooSmall = errors.New(
"blob_size_limit must be at least the largest chunk the chunker can " +
"emit (chunk_size times the FastCDC size spread)")
errBadCompression = errors.New("compression_level must be between 1 and 19")
errBadS3PartSize = errors.New("s3.part_size must be between 5MiB and 5GiB")
errBadStorageScheme = errors.New(
"storage_url must start with s3://, file://, or rclone://")
errFileURLNotAbsolute = errors.New(
"a file:// storage_url needs an absolute path, " +
"as in file:///path/to/backup")
errBadCompression = errors.New("compression_level must be between 1 and 19")
errBadS3PartSize = errors.New("s3.part_size must be between 5MiB and 5GiB")
errIndexPathNotAbsolute = errors.New(
"index_path and VAULTIK_INDEX_PATH need an absolute path, " +
"as in ~/.local/share/vaultik/index.sqlite")
@@ -557,38 +553,29 @@ func (c *Config) validateStorage() error {
return nil
}
// validateStorageURL validates URL-based storage configuration. File and
// rclone URLs need no credentials; S3 URLs require the legacy s3.*
// credential fields. A file URL must name an absolute path: a relative one
// would resolve against the working directory, so the destination would
// move with it.
// validateStorageURL checks storage_url with the same parser that opens
// the destination, so a value every command would refuse fails at load.
// File and rclone URLs need no credentials; S3 URLs require the legacy
// s3.* credential fields.
func (c *Config) validateStorageURL() error {
switch {
case strings.HasPrefix(c.StorageURL, "file://"):
// storage.ParseStorageURL applies the same rule, but config
// cannot import storage, which imports config.
if !strings.HasPrefix(c.StorageURL, "file:///") {
return errFileURLNotAbsolute
}
return nil
case strings.HasPrefix(c.StorageURL, "rclone://"):
// Rclone storage uses rclone's own config
return nil
case strings.HasPrefix(c.StorageURL, "s3://"):
// S3 storage needs credentials
if c.S3.AccessKeyID == "" {
return fmt.Errorf("%w for s3:// URLs", ErrS3KeyIDRequired)
}
if c.S3.SecretAccessKey == "" {
return fmt.Errorf("%w for s3:// URLs", ErrS3SecretRequired)
}
return nil
default:
return errBadStorageScheme
parsed, err := storageurl.Parse(c.StorageURL)
if err != nil {
return fmt.Errorf("invalid storage_url: %w", err)
}
if parsed.Scheme != storageurl.SchemeS3 {
return nil
}
if c.S3.AccessKeyID == "" {
return fmt.Errorf("%w for s3:// URLs", ErrS3KeyIDRequired)
}
if c.S3.SecretAccessKey == "" {
return fmt.Errorf("%w for s3:// URLs", ErrS3SecretRequired)
}
return nil
}
// Module exports the config module for fx dependency injection.
+3 -2
View File
@@ -10,6 +10,7 @@ import (
"sneak.berlin/go/vaultik/internal/chunker"
"sneak.berlin/go/vaultik/internal/log"
"sneak.berlin/go/vaultik/internal/storageurl"
)
const (
@@ -502,8 +503,8 @@ func TestLoadRejectsRelativeFileURL(t *testing.T) {
}
_, err = Load(path)
if !errors.Is(err, errFileURLNotAbsolute) {
t.Fatalf("Load() error = %v, want errFileURLNotAbsolute", err)
if !errors.Is(err, storageurl.ErrRelativeFilePath) {
t.Fatalf("Load() error = %v, want storageurl.ErrRelativeFilePath", err)
}
if !strings.Contains(err.Error(), "absolute path") {
-154
View File
@@ -1,154 +0,0 @@
//nolint:testpackage // exercises the unexported uploadBlobIfNeeded
package snapshot
import (
"bytes"
"context"
"io"
"path/filepath"
"testing"
"time"
"github.com/spf13/afero"
"github.com/stretchr/testify/require"
"sneak.berlin/go/vaultik/internal/blob"
"sneak.berlin/go/vaultik/internal/config"
"sneak.berlin/go/vaultik/internal/storage"
"sneak.berlin/go/vaultik/internal/storage/faultstore"
"sneak.berlin/go/vaultik/internal/ui"
)
// retryTestBlobSize is larger than what a failing faultstore Put reads,
// so a new try that did not rewind the blob would store a short object.
const retryTestBlobSize = 4096
// retryTestBlobKey is where the retry tests upload their blob.
const retryTestBlobKey = "blobs/retry"
// uploadRetryTestBlob uploads a retryTestBlobSize blob through store,
// waiting delay between tries, and returns the blob's bytes, the warnings
// the upload printed and its error.
func uploadRetryTestBlob(
ctx context.Context, store storage.Storer, delay time.Duration,
) ([]byte, int, error) {
data := bytes.Repeat([]byte("0123456789abcdef"), retryTestBlobSize/16)
output := ui.NewWithColor(io.Discard, false)
s := &Scanner{storage: store, ui: output, blobUploadRetryDelay: delay}
_, _, err := s.uploadBlobIfNeeded(ctx, retryTestBlobKey, &blob.WithReader{
FinishedBlob: &blob.FinishedBlob{
Hash: "retry",
Compressed: int64(len(data)),
},
Reader: bytes.NewReader(data),
}, time.Now(), &ScanResult{})
return data, output.WarningCount(), err
}
// A blob upload that fails is tried again from the start of the blob,
// and each failure is a warning. See
// https://git.eeqj.de/sneak/vaultik/issues/476.
func TestFailedBlobUploadIsTriedAgain(t *testing.T) {
t.Parallel()
inner, err := storage.NewFileStorer(t.TempDir())
require.NoError(t, err)
puts := 0
store := faultstore.New(inner)
store.OnPut = func(string) faultstore.PutAction {
puts++
if puts <= 2 {
return faultstore.PutFail
}
return faultstore.PutNormal
}
data, warnings, err := uploadRetryTestBlob(context.Background(), store, 0)
require.NoError(t, err)
require.Equal(t, 3, puts)
require.Equal(t, 2, warnings)
rc, err := inner.Get(context.Background(), retryTestBlobKey)
require.NoError(t, err)
defer func() { _ = rc.Close() }()
stored, err := io.ReadAll(rc)
require.NoError(t, err)
require.Equal(t, data, stored)
}
// A blob upload that keeps failing is tried blobUploadRetries more times,
// BlobUploadRetryDelay apart, and then the backup stops with its error.
func TestBlobUploadStopsAfterRetries(t *testing.T) {
t.Parallel()
inner, err := storage.NewFileStorer(t.TempDir())
require.NoError(t, err)
puts := 0
store := faultstore.New(inner)
store.OnPut = func(string) faultstore.PutAction {
puts++
return faultstore.PutFail
}
const delay = 10 * time.Millisecond
start := time.Now()
_, warnings, err := uploadRetryTestBlob(context.Background(), store, delay)
require.ErrorIs(t, err, faultstore.ErrInjectedUpload)
require.Equal(t, 1+blobUploadRetries, puts)
require.Equal(t, blobUploadRetries, warnings)
require.GreaterOrEqual(t, time.Since(start), blobUploadRetries*delay)
}
// An upload stopped by Ctrl-C or SIGTERM is not tried again.
func TestInterruptedBlobUploadIsNotTriedAgain(t *testing.T) {
t.Parallel()
inner, err := storage.NewFileStorer(t.TempDir())
require.NoError(t, err)
ctx, cancel := context.WithCancel(context.Background())
t.Cleanup(cancel)
puts := 0
store := faultstore.New(inner)
store.OnPut = func(string) faultstore.PutAction {
puts++
cancel()
return faultstore.PutFail
}
_, warnings, err := uploadRetryTestBlob(ctx, store, 0)
require.Error(t, err)
require.Equal(t, 1, puts)
require.Zero(t, warnings)
}
// Backups wait BlobUploadRetryDelay before each new try.
func TestBackupScannerWaitsBetweenBlobUploadRetries(t *testing.T) {
t.Parallel()
cfg := &config.Config{
AgeRecipients: []string{testAgeRecipient},
ChunkSize: config.Size(1024 * 1024),
BlobSizeLimit: config.Size(4 * 1024 * 1024),
IndexPath: filepath.Join(t.TempDir(), "index.sqlite"),
}
scanner := provideScannerFactory(cfg, nil, nil)(ScannerParams{
Fs: afero.NewMemMapFs(),
})
require.NotNil(t, scanner)
require.Equal(t, BlobUploadRetryDelay, scanner.blobUploadRetryDelay)
}
-35
View File
@@ -4,10 +4,8 @@ package snapshot
import (
"os"
"path/filepath"
"syscall"
"testing"
"github.com/spf13/afero"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
)
@@ -40,36 +38,3 @@ func TestDeviceNumberFromStat(t *testing.T) {
// /dev is a different filesystem from the temp dir on Linux, macOS and in Docker.
assert.NotEqual(t, deviceOf(dir), deviceOf("/dev"))
}
// fileInfoWithStat is a file's info whose Sys returns stat.
type fileInfoWithStat struct {
os.FileInfo
stat *syscall.Stat_t
}
func (i fileInfoWithStat) Sys() any { return i.stat }
// The in-memory test filesystem has no device numbers. The pinned afero
// gives no stat; its unreleased master gives a stat holding only uid, gid
// and size. See https://git.eeqj.de/sneak/vaultik/issues/462.
func TestDeviceNumberFromStatInMemory(t *testing.T) {
t.Parallel()
fs := afero.NewMemMapFs()
require.NoError(t, afero.WriteFile(fs, "/file.txt", []byte("data"), 0o600))
info, err := fs.Stat("/file.txt")
require.NoError(t, err)
_, ok := deviceNumberFromStat(info)
assert.False(t, ok, "device number read from a file info with no stat")
zeroed := fileInfoWithStat{
FileInfo: info,
stat: &syscall.Stat_t{Uid: 1000, Gid: 1000, Size: 4},
}
_, ok = deviceNumberFromStat(zeroed)
assert.False(t, ok, "device number read from a stat with no device or inode number")
}
+14 -15
View File
@@ -54,21 +54,20 @@ func provideScannerFactory(
}
return NewScanner(ScannerConfig{
FS: params.Fs,
ChunkSize: cfg.ChunkSize.Int64(),
Repositories: repos,
Storage: storer,
MaxBlobSize: cfg.BlobSizeLimit.Int64(),
CompressionLevel: cfg.CompressionLevel,
AgeRecipients: cfg.AgeRecipients,
EnableProgress: params.EnableProgress,
UI: params.UI,
Exclude: excludes,
IndexAndLockFiles: indexAndLockFiles(cfg.IndexPath, pidlock.Dir()),
SkipErrors: params.SkipErrors,
PreviousSnapshotID: params.PreviousSnapshotID,
BlobUploadRetryDelay: BlobUploadRetryDelay,
DeviceNumber: params.DeviceNumber,
FS: params.Fs,
ChunkSize: cfg.ChunkSize.Int64(),
Repositories: repos,
Storage: storer,
MaxBlobSize: cfg.BlobSizeLimit.Int64(),
CompressionLevel: cfg.CompressionLevel,
AgeRecipients: cfg.AgeRecipients,
EnableProgress: params.EnableProgress,
UI: params.UI,
Exclude: excludes,
IndexAndLockFiles: indexAndLockFiles(cfg.IndexPath, pidlock.Dir()),
SkipErrors: params.SkipErrors,
PreviousSnapshotID: params.PreviousSnapshotID,
DeviceNumber: params.DeviceNumber,
})
}
}
+24 -75
View File
@@ -75,8 +75,6 @@ type Scanner struct {
// skipErrors skips files that cannot be opened or read (logged loudly);
// packer, database, encryption, and upload errors still abort the run.
skipErrors bool
// blobUploadRetryDelay is ScannerConfig.BlobUploadRetryDelay.
blobUploadRetryDelay time.Duration
// ui is the user-facing output; never nil (defaults to a discarding writer).
ui *ui.Writer
// deviceNumber returns the number of the device that holds a file;
@@ -125,16 +123,8 @@ const (
// snapshotAssocBatchSize is how many file IDs are associated with the
// snapshot per transaction.
snapshotAssocBatchSize = 1000
// blobUploadRetries is how many more times a failed blob upload is
// tried before the backup stops with the error.
blobUploadRetries = 5
)
// BlobUploadRetryDelay is the wait before each new try of a failed blob
// upload.
const BlobUploadRetryDelay = 3 * time.Second
// ScannerConfig contains configuration for the scanner
type ScannerConfig struct {
FS afero.Fs
@@ -158,10 +148,6 @@ type ScannerConfig struct {
// PreviousSnapshotID is the most recent completed snapshot of the
// same name, "" for none.
PreviousSnapshotID string
// BlobUploadRetryDelay is the wait before each new try of a failed
// blob upload. Backups use snapshot.BlobUploadRetryDelay; tests leave
// it zero to try again at once.
BlobUploadRetryDelay time.Duration
// DeviceNumber returns the number of the device that holds a file,
// and false when there is none to read. nil reads it from the file's
// stat; tests replace it, since the in-memory test filesystem has none.
@@ -259,24 +245,23 @@ func NewScanner(cfg ScannerConfig) *Scanner {
}
return &Scanner{
fs: cfg.FS,
chunker: chunker.NewChunker(cfg.ChunkSize),
packer: packer,
repos: cfg.Repositories,
storage: cfg.Storage,
maxBlobSize: cfg.MaxBlobSize,
compressionLevel: cfg.CompressionLevel,
ageRecipient: strings.Join(cfg.AgeRecipients, ","),
exclude: cfg.Exclude,
compiledExclude: compiledExclude,
indexAndLockFiles: indexAndLockFiles,
progress: progress,
skipErrors: cfg.SkipErrors,
previousSnapshotID: cfg.PreviousSnapshotID,
blobUploadRetryDelay: cfg.BlobUploadRetryDelay,
ui: uiw,
deviceNumber: deviceNumber,
pendingChunkHashes: make(map[string]struct{}),
fs: cfg.FS,
chunker: chunker.NewChunker(cfg.ChunkSize),
packer: packer,
repos: cfg.Repositories,
storage: cfg.Storage,
maxBlobSize: cfg.MaxBlobSize,
compressionLevel: cfg.CompressionLevel,
ageRecipient: strings.Join(cfg.AgeRecipients, ","),
exclude: cfg.Exclude,
compiledExclude: compiledExclude,
indexAndLockFiles: indexAndLockFiles,
progress: progress,
skipErrors: cfg.SkipErrors,
previousSnapshotID: cfg.PreviousSnapshotID,
ui: uiw,
deviceNumber: deviceNumber,
pendingChunkHashes: make(map[string]struct{}),
}
}
@@ -1453,12 +1438,11 @@ func (s *Scanner) deviceNumberAt(path string) (uint64, bool) {
}
// deviceNumberFromStat returns the number of the device that holds the
// file info describes, and false when info carries no stat from a real
// filesystem. The in-memory test filesystem gives either no stat or one
// whose device and inode numbers are both zero, which no real file has.
// file info describes, and false when info carries no stat, as from the
// in-memory test filesystem.
func deviceNumberFromStat(info os.FileInfo) (uint64, bool) {
stat, ok := info.Sys().(*syscall.Stat_t)
if !ok || (stat.Dev == 0 && stat.Ino == 0) {
if !ok {
return 0, false
}
@@ -1891,7 +1875,10 @@ func (s *Scanner) uploadBlobIfNeeded(
s.ui.Hex(finishedBlob.Hash), s.ui.Size(finishedBlob.Compressed),
s.ui.Path(destination))
err = s.putBlob(ctx, blobPath, blobWithReader)
progressCallback := s.makeUploadProgressCallback(ctx, finishedBlob, startTime)
err = s.storage.PutWithProgress(ctx, blobPath, blobWithReader.Reader,
finishedBlob.Compressed, progressCallback)
if err != nil {
// The record is at info level: the returned error ends the backup
// and is printed as its ERROR: line. Only an interrupt cancels
@@ -1935,44 +1922,6 @@ func (s *Scanner) uploadBlobIfNeeded(
return finishedBlob.Compressed, false, nil
}
// putBlob uploads the blob to blobPath. After a failed upload it waits
// s.blobUploadRetryDelay and uploads the whole blob again, up to
// blobUploadRetries times, and then returns the last error. An interrupt
// stops it at once.
func (s *Scanner) putBlob(
ctx context.Context, blobPath string, blobWithReader *blob.WithReader,
) error {
finishedBlob := blobWithReader.FinishedBlob
for retries := 0; ; retries++ {
_, err := blobWithReader.Reader.Seek(0, io.SeekStart)
if err != nil {
return fmt.Errorf("rewinding blob for upload: %w", err)
}
progressCallback := s.makeUploadProgressCallback(
ctx, finishedBlob, time.Now().UTC())
err = s.storage.PutWithProgress(ctx, blobPath, blobWithReader.Reader,
finishedBlob.Compressed, progressCallback)
if err == nil || ctx.Err() != nil || retries == blobUploadRetries {
return err
}
log.Info("Blob upload failed, trying again",
"hash", finishedBlob.Hash, "retry", retries+1, "error", err)
s.ui.Warningf("Upload of blob %s failed: %v. Trying again in %s (retry %d of %d).",
s.ui.Hex(finishedBlob.Hash), err,
s.ui.Duration(s.blobUploadRetryDelay), retries+1, blobUploadRetries)
select {
case <-ctx.Done():
return err
case <-time.After(s.blobUploadRetryDelay):
}
}
}
// makeUploadProgressCallback creates a progress callback for blob uploads.
// It updates the live progress reporter ~twice/sec for ETAs and prints a
// human-readable status line to s.output at most every 15 seconds.
+2 -1
View File
@@ -9,6 +9,7 @@ import (
"strings"
"github.com/spf13/afero"
"sneak.berlin/go/vaultik/internal/storageurl"
)
// FileStorer implements Storer using the local filesystem.
@@ -288,7 +289,7 @@ func (f *FileStorer) DeletePartialUploads(ctx context.Context, prefix string) er
// Info returns human-readable storage location information.
func (f *FileStorer) Info() Info {
return Info{
Type: schemeFile,
Type: storageurl.SchemeFile,
Location: f.basePath,
}
}
+11 -5
View File
@@ -2,14 +2,20 @@ package storage
import (
"context"
"errors"
"fmt"
"strings"
"go.uber.org/fx"
"sneak.berlin/go/vaultik/internal/config"
"sneak.berlin/go/vaultik/internal/s3"
"sneak.berlin/go/vaultik/internal/storageurl"
)
// ErrUnsupportedStorage is returned for a parsed storage URL whose scheme
// has no storage backend.
var ErrUnsupportedStorage = errors.New("unsupported storage scheme")
// defaultS3Region is used when neither the URL nor the config specify one.
const defaultS3Region = "us-east-1"
@@ -40,19 +46,19 @@ func NewStorer(cfg *config.Config) (Storer, error) {
//nolint:ireturn // factory intentionally returns the Storer interface
func storerFromURL(rawURL string, cfg *config.Config) (Storer, error) {
parsed, err := ParseStorageURL(rawURL)
parsed, err := storageurl.Parse(rawURL)
if err != nil {
return nil, fmt.Errorf("parsing storage URL: %w", err)
}
switch parsed.Scheme {
case schemeFile:
case storageurl.SchemeFile:
return NewFileStorer(parsed.Prefix)
case schemeS3:
case storageurl.SchemeS3:
return storerFromParsedS3URL(parsed, cfg)
case schemeRclone:
case storageurl.SchemeRclone:
return NewRcloneStorer(
context.Background(), parsed.RcloneRemote, parsed.Prefix)
@@ -65,7 +71,7 @@ func storerFromURL(rawURL string, cfg *config.Config) (Storer, error) {
// filling endpoint protocol and region defaults from the config.
//
//nolint:ireturn // factory intentionally returns the Storer interface
func storerFromParsedS3URL(parsed *URL, cfg *config.Config) (Storer, error) {
func storerFromParsedS3URL(parsed *storageurl.URL, cfg *config.Config) (Storer, error) {
// Build endpoint URL
endpoint := parsed.Endpoint
if endpoint == "" {
+2 -24
View File
@@ -8,7 +8,6 @@ import (
"fmt"
"io"
"os"
"path/filepath"
"strings"
"time"
@@ -16,6 +15,7 @@ import (
"github.com/rclone/rclone/fs/config"
"github.com/rclone/rclone/fs/config/configfile"
"github.com/rclone/rclone/fs/operations"
"sneak.berlin/go/vaultik/internal/storageurl"
// Import all rclone backends
_ "github.com/rclone/rclone/backend/all"
@@ -24,15 +24,6 @@ import (
// ErrRemoteNotFound is returned when an rclone remote is not configured.
var ErrRemoteNotFound = errors.New("rclone remote not found in config")
// ErrRcloneRelativeLocalPath is returned when the path on an rclone remote
// of type local is relative. rclone would resolve it against the working
// directory, so the destination would move with it.
var ErrRcloneRelativeLocalPath = errors.New(
"the path on an rclone remote of type local must be absolute")
// rcloneLocalBackend is the type of rclone's local disk backend.
const rcloneLocalBackend = "local"
// RcloneStorer implements Storer using rclone's filesystem abstraction.
// This allows vaultik to use any of rclone's 70+ supported storage providers.
type RcloneStorer struct {
@@ -63,19 +54,6 @@ func NewRcloneStorer(ctx context.Context, remote, path string) (*RcloneStorer, e
rclonePath += path
}
// A remote rclone cannot find is reported by fs.NewFs below. Only the
// backend of what fs.ParseRemote returns is needed here.
backend, _, _, _, err := fs.ParseRemote(rclonePath) //nolint:dogsled
if err == nil && backend.Name == rcloneLocalBackend && !filepath.IsAbs(path) {
example := path
if example == "" {
example = "path/to/backup"
}
return nil, fmt.Errorf("%w: use rclone://%s//%s",
ErrRcloneRelativeLocalPath, remote, example)
}
// On S3, Swift and some other remotes rclone keeps a time of its own in
// each object's metadata, which costs one request per object to read.
// rclone's use_server_modtime setting makes ModTime the time the
@@ -289,7 +267,7 @@ func (r *RcloneStorer) Info() Info {
}
return Info{
Type: schemeRclone,
Type: storageurl.SchemeRclone,
Location: location,
}
}
-73
View File
@@ -436,79 +436,6 @@ func TestNewRcloneStorerReadsRcloneConfigEnv(t *testing.T) {
}
}
// useRcloneConfig points rclone at a config file holding contents for the
// rest of the test.
func useRcloneConfig(t *testing.T, contents string) {
t.Helper()
previous := config.GetConfigPath()
t.Cleanup(func() { _ = config.SetConfigPath(previous) })
confFile := filepath.Join(t.TempDir(), "rclone.conf")
err := os.WriteFile(confFile, []byte(contents), 0o600)
if err != nil {
t.Fatalf("writing rclone config: %v", err)
}
t.Setenv("RCLONE_CONFIG", confFile)
}
// TestNewRcloneStorerRefusesRelativeLocalPath checks that a relative path
// on a remote of type local is refused, with the absolute form in the
// error, and that nothing is created under the working directory. rclone
// would otherwise resolve the path against the working directory.
//
//nolint:paralleltest // changes the working directory and the rclone config
func TestNewRcloneStorerRefusesRelativeLocalPath(t *testing.T) {
useRcloneConfig(t, "[localfs]\ntype = local\n")
workdir := t.TempDir()
t.Chdir(workdir)
for path, wantInError := range map[string]string{
"srv/backup": "rclone://localfs//srv/backup",
"": "rclone://localfs//path/to/backup",
} {
_, err := storage.NewRcloneStorer(context.Background(), "localfs", path)
if !errors.Is(err, storage.ErrRcloneRelativeLocalPath) {
t.Errorf("path %q: error = %v, want ErrRcloneRelativeLocalPath",
path, err)
continue
}
if !strings.Contains(err.Error(), wantInError) {
t.Errorf("path %q: error %q does not show %q",
path, err, wantInError)
}
}
entries, err := os.ReadDir(workdir)
if err != nil {
t.Fatalf("reading working directory: %v", err)
}
if len(entries) != 0 {
t.Errorf("working directory holds %d entries, want none", len(entries))
}
}
// TestNewRcloneStorerKeepsRelativePathOnOtherRemotes checks that a relative
// path is accepted on a remote not of type local, where rclone resolves it
// on the remote itself, as sftp does against the login directory.
//
//nolint:paralleltest // changes the process-global rclone config
func TestNewRcloneStorerKeepsRelativePathOnOtherRemotes(t *testing.T) {
useRcloneConfig(t, "[mem]\ntype = memory\n")
_, err := storage.NewRcloneStorer(context.Background(), "mem", "backups")
if err != nil {
t.Errorf("NewRcloneStorer: %v", err)
}
}
// TestRcloneListStreamOnS3MakesNoRequestPerObject checks that listing an
// rclone S3 remote takes each object's time from the listing itself. By
// default rclone reads the time it keeps in each object's metadata, one
@@ -1,4 +1,7 @@
package storage
// Package storageurl parses the storage_url config value. The config
// package uses it to refuse a bad value when the config loads; the storage
// package uses it to open the destination.
package storageurl
import (
"errors"
@@ -10,9 +13,9 @@ import (
// Storage URL scheme names.
const (
schemeFile = "file"
schemeS3 = "s3"
schemeRclone = "rclone"
SchemeFile = "file"
SchemeS3 = "s3"
SchemeRclone = "rclone"
)
// Sentinel errors for storage URL parsing.
@@ -25,8 +28,7 @@ var (
ErrMissingRemote = errors.New("rclone URL missing remote name")
ErrUnsupportedScheme = errors.New(
"unsupported URL scheme: must start with s3://, file://, or rclone://")
ErrUnsupportedStorage = errors.New("unsupported storage scheme")
ErrURLCredentials = errors.New(
ErrURLCredentials = errors.New(
"storage URL must not carry credentials; " +
"set s3.access_key_id and s3.secret_access_key in the config instead")
ErrURLUnknownParam = errors.New("unknown query parameter in storage URL")
@@ -49,12 +51,12 @@ type URL struct {
RcloneRemote string // rclone remote name (for rclone:// URLs)
}
// ParseStorageURL parses a storage URL string.
// Parse parses a storage URL string.
// Supported formats:
// - s3://bucket/prefix?endpoint=host&region=us-east-1&ssl=true
// - file:///absolute/path/to/backup
// - rclone://remote/path/to/backups
func ParseStorageURL(rawURL string) (*URL, error) {
func Parse(rawURL string) (*URL, error) {
if rawURL == "" {
return nil, ErrEmptyStorageURL
}
@@ -92,7 +94,7 @@ func parseFileURL(rawPath string) (*URL, error) {
return nil, fmt.Errorf("invalid file URL path: %w", err)
}
return &URL{Scheme: schemeFile, Prefix: path}, nil
return &URL{Scheme: SchemeFile, Prefix: path}, nil
}
// parseS3URL parses an s3://bucket/prefix URL. It rejects credentials in
@@ -135,7 +137,7 @@ func parseS3URL(rawURL string) (*URL, error) {
}
return &URL{
Scheme: schemeS3,
Scheme: SchemeS3,
Bucket: bucket,
Prefix: strings.TrimPrefix(u.Path, "/"),
Endpoint: query.Get("endpoint"),
@@ -189,7 +191,7 @@ func parseRcloneURL(rawURL string) (*URL, error) {
}
return &URL{
Scheme: schemeRclone,
Scheme: SchemeRclone,
Prefix: strings.TrimPrefix(u.Path, "/"),
RcloneRemote: remote,
}, nil
@@ -226,9 +228,9 @@ func wrapParseError(err error) error {
// String returns a human-readable representation of the storage URL.
func (u *URL) String() string {
switch u.Scheme {
case schemeFile:
case SchemeFile:
return "file://" + u.Prefix
case schemeS3:
case SchemeS3:
endpoint := u.Endpoint
if endpoint == "" {
endpoint = "s3.amazonaws.com"
@@ -239,7 +241,7 @@ func (u *URL) String() string {
}
return fmt.Sprintf("s3://%s (endpoint: %s)", u.Bucket, endpoint)
case schemeRclone:
case SchemeRclone:
if u.Prefix != "" {
return fmt.Sprintf("rclone://%s/%s", u.RcloneRemote, u.Prefix)
}
@@ -1,4 +1,4 @@
package storage_test
package storageurl_test
import (
"errors"
@@ -6,12 +6,12 @@ import (
"strings"
"testing"
"sneak.berlin/go/vaultik/internal/storage"
"sneak.berlin/go/vaultik/internal/storageurl"
)
// TestParseStorageURLValid checks that each supported scheme parses into
// the expected fields, since those fields decide which backend is built.
func TestParseStorageURLValid(t *testing.T) {
// TestParseValid checks that each supported scheme parses into the
// expected fields, since those fields decide which backend is built.
func TestParseValid(t *testing.T) {
t.Parallel()
const (
@@ -22,27 +22,27 @@ func TestParseStorageURLValid(t *testing.T) {
cases := []struct {
name string
raw string
want *storage.URL
want *storageurl.URL
}{
{
name: "file absolute path",
raw: "file:///var/backups/vaultik",
want: &storage.URL{Scheme: fileScheme, Prefix: "/var/backups/vaultik"},
want: &storageurl.URL{Scheme: fileScheme, Prefix: "/var/backups/vaultik"},
},
{
name: "file percent-escaped path is decoded",
raw: "file:///Volumes/my%20stick/backup",
want: &storage.URL{Scheme: fileScheme, Prefix: "/Volumes/my stick/backup"},
want: &storageurl.URL{Scheme: fileScheme, Prefix: "/Volumes/my stick/backup"},
},
{
name: "file path with a literal space",
raw: "file:///Volumes/my stick/backup",
want: &storage.URL{Scheme: fileScheme, Prefix: "/Volumes/my stick/backup"},
want: &storageurl.URL{Scheme: fileScheme, Prefix: "/Volumes/my stick/backup"},
},
{
name: "s3 bucket and prefix, ssl defaults on",
raw: "s3://mybucket/backups/host",
want: &storage.URL{
want: &storageurl.URL{
Scheme: "s3", Bucket: bucket,
Prefix: "backups/host", UseSSL: true,
},
@@ -50,12 +50,12 @@ func TestParseStorageURLValid(t *testing.T) {
{
name: "s3 bucket only",
raw: "s3://mybucket",
want: &storage.URL{Scheme: "s3", Bucket: bucket, UseSSL: true},
want: &storageurl.URL{Scheme: "s3", Bucket: bucket, UseSSL: true},
},
{
name: "s3 with endpoint, region, ssl off",
raw: "s3://mybucket?endpoint=minio.example.com&region=us-west-2&ssl=false",
want: &storage.URL{
want: &storageurl.URL{
Scheme: "s3", Bucket: bucket,
Endpoint: "minio.example.com", Region: "us-west-2", UseSSL: false,
},
@@ -63,14 +63,14 @@ func TestParseStorageURLValid(t *testing.T) {
{
name: "rclone remote and path",
raw: "rclone://gdrive/backups/host",
want: &storage.URL{
want: &storageurl.URL{
Scheme: "rclone", RcloneRemote: "gdrive", Prefix: "backups/host",
},
},
{
name: "rclone remote only",
raw: "rclone://gdrive",
want: &storage.URL{Scheme: "rclone", RcloneRemote: "gdrive"},
want: &storageurl.URL{Scheme: "rclone", RcloneRemote: "gdrive"},
},
}
@@ -78,22 +78,22 @@ func TestParseStorageURLValid(t *testing.T) {
t.Run(tc.name, func(t *testing.T) {
t.Parallel()
got, err := storage.ParseStorageURL(tc.raw)
got, err := storageurl.Parse(tc.raw)
if err != nil {
t.Fatalf("ParseStorageURL(%q) returned error: %v", tc.raw, err)
t.Fatalf("Parse(%q) returned error: %v", tc.raw, err)
}
if !reflect.DeepEqual(got, tc.want) {
t.Errorf("ParseStorageURL(%q) = %+v, want %+v", tc.raw, got, tc.want)
t.Errorf("Parse(%q) = %+v, want %+v", tc.raw, got, tc.want)
}
})
}
}
// TestParseStorageURLErrors checks that empty, missing, and unknown-scheme
// inputs fail with the documented sentinel errors instead of parsing to a
// wrong destination.
func TestParseStorageURLErrors(t *testing.T) {
// TestParseErrors checks that empty, missing, and unknown-scheme inputs
// fail with the documented sentinel errors instead of parsing to a wrong
// destination.
func TestParseErrors(t *testing.T) {
t.Parallel()
cases := []struct {
@@ -101,34 +101,33 @@ func TestParseStorageURLErrors(t *testing.T) {
raw string
wantErr error
}{
{"empty url", "", storage.ErrEmptyStorageURL},
{"file empty path", "file://", storage.ErrEmptyFilePath},
{"file relative path", "file://dest", storage.ErrRelativeFilePath},
{"s3 missing bucket", "s3://", storage.ErrMissingBucket},
{"s3 missing bucket with path", "s3:///justprefix", storage.ErrMissingBucket},
{"rclone missing remote", "rclone://", storage.ErrMissingRemote},
{"unknown scheme", "gs://bucket/x", storage.ErrUnsupportedScheme},
{"no scheme", "/local/path", storage.ErrUnsupportedScheme},
{"empty url", "", storageurl.ErrEmptyStorageURL},
{"file empty path", "file://", storageurl.ErrEmptyFilePath},
{"file relative path", "file://dest", storageurl.ErrRelativeFilePath},
{"s3 missing bucket", "s3://", storageurl.ErrMissingBucket},
{"s3 missing bucket with path", "s3:///justprefix", storageurl.ErrMissingBucket},
{"rclone missing remote", "rclone://", storageurl.ErrMissingRemote},
{"unknown scheme", "gs://bucket/x", storageurl.ErrUnsupportedScheme},
{"no scheme", "/local/path", storageurl.ErrUnsupportedScheme},
}
for _, tc := range cases {
t.Run(tc.name, func(t *testing.T) {
t.Parallel()
_, err := storage.ParseStorageURL(tc.raw)
_, err := storageurl.Parse(tc.raw)
if !errors.Is(err, tc.wantErr) {
t.Errorf("ParseStorageURL(%q) error = %v, want %v",
t.Errorf("Parse(%q) error = %v, want %v",
tc.raw, err, tc.wantErr)
}
})
}
}
// TestParseStorageURLRejectsCredentials checks that a URL carrying
// credentials in its userinfo or in an unknown query parameter is
// rejected, and that the error never echoes the secret-bearing URL back
// into logs or output.
func TestParseStorageURLRejectsCredentials(t *testing.T) {
// TestParseRejectsCredentials checks that a URL carrying credentials in
// its userinfo or in an unknown query parameter is rejected, and that the
// error never echoes the secret-bearing URL back into logs or output.
func TestParseRejectsCredentials(t *testing.T) {
t.Parallel()
// Split so the literals never form a "user:pass@" URL pattern that
@@ -147,44 +146,44 @@ func TestParseStorageURLRejectsCredentials(t *testing.T) {
{
name: "s3 userinfo",
raw: "s3://" + key + ":" + secret + "@mybucket/prefix",
wantErr: storage.ErrURLCredentials,
wantErr: storageurl.ErrURLCredentials,
secrets: []string{key, secret, "mybucket"},
},
{
name: "s3 userinfo in endpoint",
raw: "s3://mybucket?endpoint=https://" +
key + ":" + secret + "@minio.example.com",
wantErr: storage.ErrURLCredentials,
wantErr: storageurl.ErrURLCredentials,
secrets: []string{key, secret},
},
{
name: "s3 userinfo in endpoint without scheme",
raw: "s3://mybucket?endpoint=" + key + ":" + secret + "@minio.example.com",
wantErr: storage.ErrURLCredentials,
wantErr: storageurl.ErrURLCredentials,
secrets: []string{key, secret},
},
{
name: "s3 unknown query param",
raw: "s3://mybucket?access_key=" + key + "&secret=" + secret,
wantErr: storage.ErrURLUnknownParam,
wantErr: storageurl.ErrURLUnknownParam,
secrets: []string{key, secret},
},
{
name: "s3 misspelt endpoint",
raw: "s3://mybucket?endpiont=minio.example.com",
wantErr: storage.ErrURLUnknownParam,
wantErr: storageurl.ErrURLUnknownParam,
secrets: nil,
},
{
name: "rclone userinfo",
raw: "rclone://user:" + secret + "@gdrive/backups",
wantErr: storage.ErrURLCredentials,
wantErr: storageurl.ErrURLCredentials,
secrets: []string{secret},
},
{
name: "rclone query param",
raw: "rclone://gdrive/backups?token=" + secret,
wantErr: storage.ErrURLUnknownParam,
wantErr: storageurl.ErrURLUnknownParam,
secrets: []string{secret},
},
}
@@ -193,9 +192,9 @@ func TestParseStorageURLRejectsCredentials(t *testing.T) {
t.Run(tc.name, func(t *testing.T) {
t.Parallel()
_, err := storage.ParseStorageURL(tc.raw)
_, err := storageurl.Parse(tc.raw)
if !errors.Is(err, tc.wantErr) {
t.Fatalf("ParseStorageURL(%q) error = %v, want %v",
t.Fatalf("Parse(%q) error = %v, want %v",
tc.raw, err, tc.wantErr)
}
@@ -216,11 +215,11 @@ func TestParseStorageURLRejectsCredentials(t *testing.T) {
}
}
// TestParseStorageURLRejectsRcloneRemoteParams checks that an rclone
// remote name carrying parameters (rclone's "remote,param=value" form,
// which can hold a credential) is rejected without echoing the value,
// including the URLs that url.Parse itself refuses.
func TestParseStorageURLRejectsRcloneRemoteParams(t *testing.T) {
// TestParseRejectsRcloneRemoteParams checks that an rclone remote name
// carrying parameters (rclone's "remote,param=value" form, which can hold
// a credential) is rejected without echoing the value, including the URLs
// that url.Parse itself refuses.
func TestParseRejectsRcloneRemoteParams(t *testing.T) {
t.Parallel()
cases := []struct {
@@ -249,10 +248,10 @@ func TestParseStorageURLRejectsRcloneRemoteParams(t *testing.T) {
t.Run(tc.name, func(t *testing.T) {
t.Parallel()
_, err := storage.ParseStorageURL(tc.raw)
if !errors.Is(err, storage.ErrRcloneRemoteParams) {
t.Fatalf("ParseStorageURL(%q) error = %v, want %v",
tc.raw, err, storage.ErrRcloneRemoteParams)
_, err := storageurl.Parse(tc.raw)
if !errors.Is(err, storageurl.ErrRcloneRemoteParams) {
t.Fatalf("Parse(%q) error = %v, want %v",
tc.raw, err, storageurl.ErrRcloneRemoteParams)
}
for _, secret := range tc.secrets {
@@ -264,10 +263,10 @@ func TestParseStorageURLRejectsRcloneRemoteParams(t *testing.T) {
}
}
// TestParseStorageURLRejectsUndecodableQuery checks that an s3 or rclone
// URL whose query cannot be decoded is rejected, not read with that part
// of the query left out, and that the error does not echo it.
func TestParseStorageURLRejectsUndecodableQuery(t *testing.T) {
// TestParseRejectsUndecodableQuery checks that an s3 or rclone URL whose
// query cannot be decoded is rejected, not read with that part of the
// query left out, and that the error does not echo it.
func TestParseRejectsUndecodableQuery(t *testing.T) {
t.Parallel()
const (
@@ -303,14 +302,14 @@ func TestParseStorageURLRejectsUndecodableQuery(t *testing.T) {
t.Run(tc.name, func(t *testing.T) {
t.Parallel()
_, err := storage.ParseStorageURL(tc.raw)
_, err := storageurl.Parse(tc.raw)
if err == nil {
t.Fatalf("ParseStorageURL(%q) returned no error", tc.raw)
t.Fatalf("Parse(%q) returned no error", tc.raw)
}
if !errors.Is(err, storage.ErrURLBadQuery) {
t.Errorf("ParseStorageURL(%q) error = %v, want %v",
tc.raw, err, storage.ErrURLBadQuery)
if !errors.Is(err, storageurl.ErrURLBadQuery) {
t.Errorf("Parse(%q) error = %v, want %v",
tc.raw, err, storageurl.ErrURLBadQuery)
}
for _, s := range []string{key, secret, "minio.example.com"} {
@@ -322,17 +321,17 @@ func TestParseStorageURLRejectsUndecodableQuery(t *testing.T) {
}
}
// TestParseStorageURLParseFailureHidesURL checks that when url.Parse
// itself fails, the wrapped error carries only the inner cause, not the
// *url.Error whose text embeds the raw (possibly credential-bearing) URL.
func TestParseStorageURLParseFailureHidesURL(t *testing.T) {
// TestParseFailureHidesURL checks that when url.Parse itself fails, the
// wrapped error carries only the inner cause, not the *url.Error whose
// text embeds the raw (possibly credential-bearing) URL.
func TestParseFailureHidesURL(t *testing.T) {
t.Parallel()
const raw = "s3://mybucket/%zz"
_, err := storage.ParseStorageURL(raw)
_, err := storageurl.Parse(raw)
if err == nil {
t.Fatalf("ParseStorageURL(%q) returned no error", raw)
t.Fatalf("Parse(%q) returned no error", raw)
}
if strings.Contains(err.Error(), "mybucket") {
@@ -4,7 +4,6 @@ import (
"context"
"maps"
"path/filepath"
"strings"
"testing"
"github.com/spf13/afero"
@@ -13,7 +12,6 @@ import (
"sneak.berlin/go/vaultik/internal/database"
"sneak.berlin/go/vaultik/internal/log"
"sneak.berlin/go/vaultik/internal/storage"
"sneak.berlin/go/vaultik/internal/storage/faultstore"
"sneak.berlin/go/vaultik/internal/vaultik"
)
@@ -70,55 +68,3 @@ func TestBackupWithoutCronOfTwoPathSnapshotRestoresBothPaths(t *testing.T) {
assertRestoredTree(t, fs, restoreDir, files)
}
// A backup without --cron whose blob uploads keep failing stops with the
// upload's error, and stops the progress reporter once. See
// https://git.eeqj.de/sneak/vaultik/issues/476.
//
//nolint:paralleltest // installs the global logger via log.Initialize
func TestBackupWithoutCronStopsWithBlobUploadError(t *testing.T) {
log.Initialize(log.Config{})
const snapshotName = "data"
fs := afero.NewOsFs()
tempDir := t.TempDir()
firstDir := filepath.Join(tempDir, "first")
secondDir := filepath.Join(tempDir, "second")
dbPath := filepath.Join(tempDir, "index.sqlite")
ctx := context.Background()
writeFaultSourceTree(t, fs, firstDir)
writeFaultSourceTree(t, fs, secondDir)
cfg := faultTestConfig()
cfg.IndexPath = dbPath
cfg.ChunkSize = config.Size(faultChunkSize)
cfg.Snapshots = map[string]config.SnapshotConfig{
snapshotName: {Paths: []string{firstDir, secondDir}},
}
inner, err := storage.NewFileStorer(t.TempDir())
require.NoError(t, err)
store := faultstore.New(inner)
store.OnPut = func(key string) faultstore.PutAction {
if strings.HasPrefix(key, "blobs/") {
return faultstore.PutFail
}
return faultstore.PutNormal
}
db, err := database.New(ctx, dbPath)
require.NoError(t, err)
t.Cleanup(func() { _ = db.Close() })
v := newBackupVaultik(ctx, cfg, store, database.NewRepositories(db), db, fs)
err = v.CreateSnapshot(&vaultik.SnapshotCreateOptions{
Snapshots: []string{snapshotName},
})
require.ErrorIs(t, err, faultstore.ErrInjectedUpload)
}