next into main #481

Open
clawbot wants to merge 5 commits from next into main
pull from: next
34 changed files with 837 additions and 335 deletions

No files matched your search

+9 -2
View File
@@ -35,9 +35,16 @@ RUN for attempt in 1 2 3; do \
echo "module download failed: giving up after 3 attempts" >&2; \
exit 1
COPY . .
RUN go test -timeout 90s -race -cover ./... || \
# -race also turns on checkptr, which checks every pointer conversion. In
# the SQLite library's translated C code that is about a third of the test
# CPU time, much of it under one lock all SQLite work shares, and the
# tests that use SQLite time out on a busy host. The gcflags turn it off
# for that library only; our own packages keep it.
RUN go test -timeout 90s -race -gcflags='modernc.org/...=-d=checkptr=0' \
-cover ./... || \
{ echo "--- Rerunning with -v for details ---"; \
go test -timeout 90s -race -v ./...; exit 1; }
go test -timeout 90s -race -gcflags='modernc.org/...=-d=checkptr=0' \
-v ./...; exit 1; }
# Build stage. Nothing is wanted from either phase above; the copies
# are what make BuildKit build them first, so this stage cannot run
+45 -36
View File
@@ -183,6 +183,7 @@ vaultik [--config <path>] remote nuke --force
vaultik [--config <path>] database delete [--force]
vaultik completion <bash|zsh|fish|powershell>
vaultik version
vaultik --version
```
### global flags
@@ -340,31 +341,29 @@ In such a config, an unknown key or a value of the wrong type is refused.
error that explains how to fix it
- `--cron`: Silent on total success; warnings and errors are still printed (for
crontab)
- `--prune`: After backup, drop older snapshots of each backed-up name, remove
orphaned blobs older than `prune_grace_period` from remote storage, and delete
each directory under `metadata/` that has no `manifest.json.zst` once every
object in it is older than `prune_grace_period` and its snapshot is not in the
local index, as `prune` does. By default keeps only the latest snapshot per
name; use `--keep-newer-than` for a rolling window. When `--skip-errors`
skipped a file or directory it could not read or list, the prune does not run
and every older snapshot is kept, since one of them may be the only one that
holds what was skipped; the command says so and exits non-zero. When the
backup found nothing in a configured path, as in the mount point of a volume
that is not mounted, the prune does not run either: every older snapshot is
kept, and the command names the path and exits non-zero, on every run until
the path holds something again. Take a path that is empty on purpose out of
the config, or remove the older snapshots by hand with `snapshot purge`. When
an earlier snapshot of the same name in the local index found a volume mounted
at or below a configured path (a directory on a different filesystem from its
parent, with an entry in it that the backup does not exclude) and this backup
does not, the prune does not run either: every older snapshot is kept, and the
command names the directory and exits non-zero, on every run until the volume
is mounted again. A backup also does not find the volume when it finds no such
entry in its directory, as when an automounted volume cannot be mounted, or
when that directory is no longer backed up, because it is excluded or its
configured path was removed. If any of this is on purpose, as for a retired
volume, remove the older snapshots by hand with `snapshot purge`. A file
removed during the backup does not stop the prune.
- `--prune`: After backup, drop older snapshots of each backed-up name, then
delete from the destination store what `prune` deletes there. By default keeps
only the latest snapshot per name; use `--keep-newer-than` for a rolling
window. When `--skip-errors` skipped a file or directory it could not read or
list, the prune does not run and every older snapshot is kept, since one of
them may be the only one that holds what was skipped; the command says so and
exits non-zero. When the backup found nothing in a configured path, as in the
mount point of a volume that is not mounted, the prune does not run either:
every older snapshot is kept, and the command names the path and exits
non-zero, on every run until the path holds something again. Take a path that
is empty on purpose out of the config, or remove the older snapshots by hand
with `snapshot purge`. When an earlier snapshot of the same name in the local
index found a volume mounted at or below a configured path (a directory on a
different filesystem from its parent, with an entry in it that the backup does
not exclude) and this backup does not, the prune does not run either: every
older snapshot is kept, and the command names the directory and exits
non-zero, on every run until the volume is mounted again. A backup also does
not find the volume when it finds no such entry in its directory, as when an
automounted volume cannot be mounted, or when that directory is no longer
backed up, because it is excluded or its configured path was removed. If any
of this is on purpose, as for a retired volume, remove the older snapshots by
hand with `snapshot purge`. A file removed during the backup does not stop the
prune.
- `--keep-newer-than <duration>`: With `--prune`, keep snapshots newer than this
duration instead of only the latest (e.g. `4w`, `30d`, `6mo`, `1y`). Without
`--prune`, or with a value that is not a valid duration, the command fails
@@ -520,14 +519,16 @@ deleted. Step (3) also deletes each directory under `metadata/` that has no
`db.zst.age` but before its manifest, once every object in it is older than
`prune_grace_period` and its snapshot is not in the local index. An object the
listing gives no time for keeps its directory, and a directory whose name is not
a remote key is left alone. Step (3) reads all remote manifests — network cost
scales with the number of snapshots. `snapshot create --prune` runs the same
cleanup automatically; this is the manual entry point for the same work. If the
a remote key is left alone. Step (3) also deletes each `.partial` object under
`metadata/` and `blobs/` left by a killed upload, once it is older than
`prune_grace_period`. Step (3) reads all remote manifests — network cost scales
with the number of snapshots. `snapshot create --prune` runs the same cleanup
automatically; this is the manual entry point for the same work. If the
destination store cannot be listed, or the local index holds snapshots and the
destination answers that it has no `vaultik-destination.txt` (an unplugged
volume's empty mount point), prune fails and deletes nothing. `snapshot purge`
does the same. If a blob or such a directory cannot be deleted, the command (and
`snapshot create --prune`) exits non-zero.
does the same. If a blob, such a directory or such a `.partial` object cannot be
deleted, the command (and `snapshot create --prune`) exits non-zero.
- `--force`: Skip confirmation prompt
- `--json`: Output stats as JSON. Also skips the confirmation prompt, as
@@ -537,7 +538,10 @@ does the same. If a blob or such a directory cannot be deleted, the command (and
gives no time for it, is counted in `blobs_too_new` and not in `blobs_found`.
A directory under `metadata/` with no manifest is counted in
`metadata_dirs_deleted` once deleted, or in `metadata_dirs_failed` if it
cannot be.
cannot be. A `.partial` object is counted in `partial_uploads_deleted` once
deleted, or in `partial_uploads_failed` if it cannot be. One kept for being
newer than `prune_grace_period`, or of unknown age, is counted in
`partial_uploads_too_new`.
**`info`**: Display system configuration, storage settings, encryption
recipients, and local database statistics.
@@ -552,7 +556,9 @@ in `unreadable_manifests` and counts the manifests under skipped names in
`skipped_manifest_count`. An unreadable manifest also leaves its snapshot's blob
count and blob size unknown, `null` in `--json`. A file under `blobs/` whose
name is not a blob hash is not counted as a blob, since `prune` never deletes
it.
it. A leftover `.partial` object under `metadata/` or `blobs/` is not counted as
a blob either. Such objects are counted on their own line, and in
`partial_upload_count` and `partial_upload_size` in `--json`.
- `--json`: Output as JSON
@@ -615,8 +621,9 @@ with a server-side move (local and sftp among them) are written under a
temporary name ending in `.partial` and moved into place. Rclone remotes without
one are written in place: where such a remote shows a file while it is still
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.
which a later backup takes for complete. A backup ignores a leftover `.partial`
file. `prune` deletes it once it is older than `prune_grace_period`, and
`remote info` counts it.
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
@@ -725,6 +732,8 @@ format does and does not protect.
5. Delete each directory under `metadata/` with no manifest whose objects are
all older than `prune_grace_period`, unless its snapshot is in the local
index
6. Delete each `.partial` object under `metadata/` and `blobs/` older than
`prune_grace_period`
### chunking and deduplication
@@ -759,7 +768,7 @@ annotated example also lives in
[`configs/config.example.yml`](configs/config.example.yml). Key fields:
| Field | Default | Description |
| -------------------- | ------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| -------------------- | ------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `age_recipients` | (required by `snapshot create`) | Age public keys for encryption. Other commands run without one, so a machine that only restores can leave it empty |
| `age_secret_key` | (unset) | Age private key for decryption (`snapshot restore`, `snapshot files`, `snapshot verify --deep`). Setting it in the config file places the private key on the backed-up host, defeating the public-key-only design (see "why" above). Prefer the `VAULTIK_AGE_SECRET_KEY` environment variable, supplied only on the machine you restore from. |
| `snapshots` | (required) | Named snapshot definitions with paths and excludes |
@@ -769,7 +778,7 @@ annotated example also lives in
| `chunk_size` | `10MB` | Average chunk size for content-defined chunking |
| `blob_size_limit` | `10GB` | Maximum blob size before splitting. Must be at least four times `chunk_size` (the largest chunk the chunker can emit), otherwise a single-chunk blob could exceed the limit. A backup needs free temporary space, because each blob is written whole to a temporary file before it is uploaded (up to about `blob_size_limit`; an rclone destination that cannot stream uploads needs about twice that) and the metadata export writes copies of the local index. Temporary files go to `$TMPDIR` (default `/tmp`); with `TMPDIR` unset, SQLite writes one of those copies to `/var/tmp` |
| `compression_level` | `3` | zstd compression level (1-19) |
| `prune_grace_period` | `24h` | How old a blob that no snapshot lists must be before `prune` deletes it, and how old every object in a directory under `metadata/` with no manifest must be before `prune` deletes that directory. A backup uploads its blobs and its `db.zst.age` before its manifest, so on a destination shared between hosts or users this must be longer than the longest backup run (see [locking](#locking)). It does not protect a blob a backup reuses from an earlier run that stopped before its manifest: that blob keeps the time of its first upload, so a prune can delete it. A duration such as `36h` or `90m`; `0s` deletes such blobs and directories at once |
| `prune_grace_period` | `24h` | How old a blob that no snapshot lists must be before `prune` deletes it, and how old every object in a directory under `metadata/` with no manifest must be before `prune` deletes that directory. `prune` also deletes a `.partial` object left by a killed upload only once it is this old. A backup uploads its blobs and its `db.zst.age` before its manifest, so on a destination shared between hosts or users this must be longer than the longest backup run (see [locking](#locking)). It does not protect a blob a backup reuses from an earlier run that stopped before its manifest: that blob keeps the time of its first upload, so a prune can delete it. A duration such as `36h` or `90m`; `0s` deletes such blobs and directories at once |
| `hostname` | system hostname | Hostname used in snapshot IDs |
| `index_path` | platform data dir | Local SQLite index path |
+2
View File
@@ -333,6 +333,8 @@ compression_level: 5
# How old a blob that no snapshot lists must be before prune deletes it, and
# how old every object in a directory under metadata/ with no manifest must
# be before prune deletes that directory
# prune also deletes a .partial object left by a killed upload only once it is
# this old
# A backup uploads its blobs and its db.zst.age before its manifest, so on a
# destination shared between hosts or users this must be longer than the
# longest backup run
+3
View File
@@ -314,6 +314,9 @@ The restore process doesn't use the local database. Instead:
- Delete each directory under `metadata/` that has no `manifest.json.zst`
and no local snapshot record, once every object in it is older than
`prune_grace_period`
3. **Delete Partial Uploads**
- Delete each `.partial` object under `metadata/` or `blobs/` left by a
killed upload, once it is older than `prune_grace_period`
### 6. Incomplete Snapshot Cleanup
+5 -3
View File
@@ -329,7 +329,8 @@ The prune operation is safe because:
1. It keeps every blob listed in any snapshot's manifest and deletes only blobs
that no manifest references. Under `metadata/` it deletes only a directory
that has no `manifest.json.zst`, whose name is a remote key, and that no
local snapshot record claims
local snapshot record claims. It also deletes the `.partial` objects left by
killed uploads, which no backup or restore reads
2. Manifests are unencrypted and can be read without keys
3. If any manifest cannot be downloaded or decoded, prune deletes nothing and
exits with an error, rather than treating that snapshot's blobs as
@@ -343,8 +344,9 @@ The prune operation is safe because:
a backup reuses from an earlier run that stopped before its manifest: the
backup skips the upload of a blob already on the destination, so that blob
keeps the time of its first upload, and a prune before the backup's manifest
is written can delete it; the new snapshot then cannot be restored.
`remote nuke` has no such check
is written can delete it; the new snapshot then cannot be restored. Prune
deletes a `.partial` object only once it is older than `prune_grace_period`,
so an upload still running keeps its object. `remote nuke` has no such check
## Restoration Requirements
+5 -3
View File
@@ -269,9 +269,11 @@ storage_url: ""
# How old a blob that no snapshot lists must be before prune deletes it,
# and how old every object in a directory under metadata/ with no manifest
# must be before prune deletes that directory. A backup uploads its blobs
# and its db.zst.age before its manifest, so on a destination shared
# between hosts or users this must be longer than the longest backup run.
# must be before prune deletes that directory. prune also deletes a
# .partial object left by a killed upload only once it is this old. A
# backup uploads its blobs and its db.zst.age before its manifest, so on
# a destination shared between hosts or users this must be longer than
# the longest backup run.
# It does not protect a blob a backup reuses from an earlier run that
# stopped before its manifest: that blob keeps the time of its first
# upload, so a prune can delete it.
+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"},
+6 -4
View File
@@ -13,9 +13,10 @@ func NewPruneCommand() *cobra.Command {
cmd := &cobra.Command{
Use: "prune",
Short: "Tidy local database and remote storage",
Long: `Removes orphaned data from the local index database, and
unreferenced blobs and directories under metadata/ with no manifest
from the backup destination store.
Long: `Removes orphaned data from the local index database. From the
backup destination store it removes unreferenced blobs, directories
under metadata/ with no manifest, and .partial objects left by killed
uploads.
Local cleanup drops incomplete snapshots and any files, chunks, or
blobs no longer referenced by a completed snapshot. Remote cleanup
@@ -30,7 +31,8 @@ blob keeps the time of its first upload, so it can be deleted.
Remote cleanup also deletes each directory under metadata/ with no
manifest, as a backup that stopped before its manifest leaves, once
all its objects are older than prune_grace_period and its snapshot is
not in the local index.
not in the local index. It also deletes each .partial object under
metadata/ or blobs/ once it is older than prune_grace_period.
Snapshot create --prune runs the same cleanup automatically; this
command is the manual entry point for the same work (e.g. after a
+2 -1
View File
@@ -75,7 +75,8 @@ func newRemoteInfoCommand() *cobra.Command {
- Size of all snapshot metadata (per snapshot and total)
- Count and total size of all blobs
- Count and size of referenced blobs (from all manifests)
- Count and size of orphaned blobs (not referenced by any manifest)`,
- Count and size of orphaned blobs (not referenced by any manifest)
- Count and size of .partial objects left by killed uploads`,
Args: cobra.NoArgs,
RunE: func(cmd *cobra.Command, _ []string) error {
// Use unified config resolution
+18 -4
View File
@@ -32,6 +32,8 @@ var rootFlags RootFlags
// It sets up the command structure, global flags, and adds all subcommands.
// This is the main entry point for the CLI command hierarchy.
func NewRootCommand() *cobra.Command {
var showVersion bool
cmd := &cobra.Command{
Use: "vaultik",
Short: "Secure incremental backup tool with asymmetric encryption",
@@ -39,15 +41,27 @@ func NewRootCommand() *cobra.Command {
public keys and uploads to S3-compatible storage. No private keys are needed
on the source system.`,
SilenceUsage: true,
// Bare 'vaultik' (no subcommand): print help. The banner is
// printed once at process startup by Entry, before cobra
// parses arguments, so it appears even when cobra rejects
// args (e.g. "requires at least 2 arg(s)") and on --help.
// Bare 'vaultik' (no subcommand): print help, or with --version
// the report of the version command. The banner is printed once
// at process startup by Entry, before cobra parses arguments, so
// it appears even when cobra rejects args (e.g. "requires at
// least 2 arg(s)") and on --help.
Run: func(cmd *cobra.Command, _ []string) {
if showVersion {
writeVersion(commandUI(cmd))
return
}
_ = cmd.Help()
},
}
// cobra's own --version prints a template, not the version report,
// so vaultik defines the flag itself.
cmd.Flags().BoolVar(&showVersion, "version", false,
"Print version information (same as 'vaultik version')")
// Add global flags
cmd.PersistentFlags().StringVar(&rootFlags.ConfigPath, "config", "",
"Path to config file (default: $VAULTIK_CONFIG or platform config dir)")
+5 -7
View File
@@ -138,13 +138,11 @@ on Linux), then /etc/vaultik/config.yml.`,
cmd.Flags().BoolVar(&opts.Cron, "cron", false,
"Run in cron mode (silent unless warning or error)")
cmd.Flags().BoolVar(&opts.Prune, "prune", false,
"After backup, drop older snapshots of the same name, remove "+
"orphaned blobs older than prune_grace_period, and delete each "+
"directory under metadata/ with no manifest once all its "+
"objects are older than prune_grace_period and its snapshot is "+
"not in the local index (not after a backup that skipped "+
"unreadable files, found a configured path empty, or did not "+
"find a mount point an earlier snapshot found)")
"After backup, drop older snapshots of the same name, then delete "+
"from the destination store what prune deletes there (not "+
"after a backup that skipped unreadable files, found a "+
"configured path empty, or did not find a mount point an "+
"earlier snapshot found)")
cmd.Flags().StringVar(&opts.KeepNewerThan, "keep-newer-than", "",
"With --prune: keep snapshots newer than this duration "+
"(e.g. 30d, 4w, 6mo, 1y; m is minutes, mo is months) "+
+24
View File
@@ -86,6 +86,30 @@ func TestVersionCommandReportLines(t *testing.T) {
}
}
// TestVersionFlagPrintsVersionReport checks that `vaultik --version`
// prints exactly the report of `vaultik version`.
//
//nolint:paralleltest // executes commands that read the global rootFlags
func TestVersionFlagPrintsVersionReport(t *testing.T) {
cmd := cli.NewRootCommand()
var out bytes.Buffer
cmd.SetOut(&out)
cmd.SetErr(&out)
cmd.SetArgs([]string{"--version"})
err := cmd.Execute()
if err != nil {
t.Fatalf("vaultik --version failed: %v", err)
}
want := runVersionCommand(t)
if out.String() != want {
t.Errorf("vaultik --version printed:\n%s\nwant:\n%s", out.String(), want)
}
}
// TestVersionCommandFlagsDevelopmentBuild is the regression test for
// the thing this command exists to prevent: a build that is not a
// release must say so. The notice used to be gated on the version
+13 -25
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"
@@ -65,11 +66,6 @@ var (
"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")
errIndexPathNotAbsolute = errors.New(
"index_path and VAULTIK_INDEX_PATH need an absolute path, " +
"as in ~/.local/share/vaultik/index.sqlite")
@@ -206,7 +202,8 @@ type Config struct {
// directory. A backup writes its manifest only once it has uploaded
// all its blobs and its db.zst.age, so a younger blob or directory may
// belong to a backup still running, on this host or another sharing
// the destination store.
// the destination store. A prune also deletes a `.partial` object left
// by a killed upload only once it is this old.
PruneGracePeriod time.Duration `yaml:"prune_grace_period"`
// StorageURL specifies the storage backend using a URL format.
@@ -557,26 +554,20 @@ 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
parsed, err := storageurl.Parse(c.StorageURL)
if err != nil {
return fmt.Errorf("invalid storage_url: %w", err)
}
if parsed.Scheme != storageurl.SchemeS3 {
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)
}
@@ -586,9 +577,6 @@ func (c *Config) validateStorageURL() error {
}
return nil
default:
return errBadStorageScheme
}
}
// 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") {
+9 -4
View File
@@ -118,17 +118,22 @@ func ShortHostname(hostname string) string {
// hostname_timestamp if name is empty. The timestamp is in whole seconds.
// If the local index already has a snapshot with that ID, from a run of the
// same name that started in the same second, it waits a second and takes a
// new timestamp.
// new timestamp. The snapshot's start time is the moment in its ID, so a
// later run of one name always has a later start time.
func (sm *SnapshotManager) CreateSnapshotWithName(
ctx context.Context, hostname, name, version, gitRevision string,
) (string, error) {
shortHostname := ShortHostname(hostname)
var snapshotID string
var (
snapshotID string
startedAt time.Time
)
for {
// Build snapshot ID with optional name
timestamp := time.Now().UTC().Format("2006-01-02T15:04:05Z")
startedAt = time.Now().UTC()
timestamp := startedAt.Format("2006-01-02T15:04:05Z")
if name != "" {
snapshotID = fmt.Sprintf("%s_%s_%s", shortHostname, name, timestamp)
@@ -153,7 +158,7 @@ func (sm *SnapshotManager) CreateSnapshotWithName(
Hostname: types.Hostname(hostname),
VaultikVersion: types.Version(version),
VaultikGitRevision: types.GitRevision(gitRevision),
StartedAt: time.Now().UTC(),
StartedAt: startedAt,
CompletedAt: nil, // Not completed yet
FileCount: 0,
ChunkCount: 0,
+52
View File
@@ -492,3 +492,55 @@ func TestCreateSnapshotWithNameTwiceBackToBack(t *testing.T) {
t.Fatalf("both creates returned snapshot ID %s", first)
}
}
// Two creates of one snapshot name back to back list newest first. The
// start time is the moment in the ID, so the two cannot share a start
// time even when the clock crosses a second while the first is created.
// See https://git.eeqj.de/sneak/vaultik/issues/482.
func TestCreateSnapshotWithNameTwiceBackToBackListsNewestFirst(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
const created = 2
ctx := context.Background()
db, err := database.New(ctx, filepath.Join(t.TempDir(), "index.sqlite"))
if err != nil {
t.Fatalf("failed to create database: %v", err)
}
defer func() { _ = db.Close() }()
repos := database.NewRepositories(db)
sm := &SnapshotManager{repos: repos}
first, err := sm.CreateSnapshotWithName(ctx, "test-host", "data", "v", "g")
if err != nil {
t.Fatalf("first create failed: %v", err)
}
second, err := sm.CreateSnapshotWithName(ctx, "test-host", "data", "v", "g")
if err != nil {
t.Fatalf("second create failed: %v", err)
}
snapshots, err := repos.Snapshots.ListRecent(ctx, created)
if err != nil {
t.Fatalf("listing snapshots failed: %v", err)
}
if len(snapshots) != created {
t.Fatalf("listed %d snapshots, want %d", len(snapshots), created)
}
if !snapshots[0].StartedAt.After(snapshots[1].StartedAt) {
t.Fatalf("start times %v and %v are not in order",
snapshots[1].StartedAt, snapshots[0].StartedAt)
}
if snapshots[0].ID.String() != second || snapshots[1].ID.String() != first {
t.Fatalf("listed %s, %s; want %s, %s",
snapshots[0].ID, snapshots[1].ID, second, first)
}
}
+5 -3
View File
@@ -200,9 +200,11 @@ func (f *Storer) ListStream(
return f.inner.ListStream(ctx, prefix)
}
// DeletePartialUploads delegates unchanged.
func (f *Storer) DeletePartialUploads(ctx context.Context, prefix string) error {
return f.inner.DeletePartialUploads(ctx, prefix)
// ListPartialUploads delegates unchanged.
func (f *Storer) ListPartialUploads(
ctx context.Context, prefix string,
) ([]storage.ObjectInfo, error) {
return f.inner.ListPartialUploads(ctx, prefix)
}
// Info delegates unchanged.
+28 -14
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.
@@ -56,8 +57,8 @@ const storageDirPerm = 0o755
// truncated object at the key a later run would Stat and trust as a complete
// blob. The rclone backend's upload does the same on remotes with a
// server-side move. List and ListStream skip these files, so a leftover from
// an interrupted write is never listed or trusted as a blob; it is otherwise
// harmless.
// an interrupted write is never listed or trusted as a blob; prune deletes
// it once it is older than the prune grace period.
const tempSuffix = ".partial"
// Put stores data at the specified key.
@@ -248,22 +249,24 @@ func (f *FileStorer) ListStream(ctx context.Context, prefix string) <-chan Objec
return ch
}
// DeletePartialUploads removes every file under prefix whose name ends in
// ListPartialUploads returns each file under prefix whose name ends in
// tempSuffix. Like List, it reads through symlinked directories and fails
// on one whose target is missing. A missing prefix has none to remove.
func (f *FileStorer) DeletePartialUploads(ctx context.Context, prefix string) error {
basePath := f.fullPath(prefix)
// on one whose target is missing. A missing prefix has none.
func (f *FileStorer) ListPartialUploads(
ctx context.Context, prefix string,
) ([]ObjectInfo, error) {
exists, err := f.prefixExists(prefix)
if err != nil {
return fmt.Errorf("checking path: %w", err)
return nil, fmt.Errorf("checking path: %w", err)
}
if !exists {
return nil
return nil, nil
}
err = f.walk(basePath, func(path string, info os.FileInfo, err error) error {
var partial []ObjectInfo
err = f.walk(f.fullPath(prefix), func(path string, info os.FileInfo, err error) error {
if err != nil {
return err
}
@@ -276,19 +279,30 @@ func (f *FileStorer) DeletePartialUploads(ctx context.Context, prefix string) er
return nil
}
return f.fs.Remove(path)
})
relPath, err := filepath.Rel(f.basePath, path)
if err != nil {
return fmt.Errorf("walking directory: %w", err)
return fmt.Errorf("computing relative path: %w", err)
}
partial = append(partial, ObjectInfo{
Key: strings.ReplaceAll(relPath, string(filepath.Separator), "/"),
Size: info.Size(),
ModTime: info.ModTime(),
})
return nil
})
if err != nil {
return nil, fmt.Errorf("walking directory: %w", err)
}
return partial, nil
}
// Info returns human-readable storage location information.
func (f *FileStorer) Info() Info {
return Info{
Type: schemeFile,
Type: storageurl.SchemeFile,
Location: f.basePath,
}
}
+32 -8
View File
@@ -121,9 +121,10 @@ func TestFileStorer_ListSkipsPartialFiles(t *testing.T) {
}
}
// TestFileStorer_DeletePartialUploads checks that a leftover temp file is
// removed and the object at the real key is kept.
func TestFileStorer_DeletePartialUploads(t *testing.T) {
// TestFileStorer_ListPartialUploads checks that a leftover temp file is
// listed with its size and time, that the object at the real key is not,
// and that Delete removes the leftover by the listed key.
func TestFileStorer_ListPartialUploads(t *testing.T) {
t.Parallel()
base := t.TempDir()
@@ -133,23 +134,46 @@ func TestFileStorer_DeletePartialUploads(t *testing.T) {
t.Fatalf("NewFileStorer: %v", err)
}
checkListPartialUploads(t, f, base)
}
// checkListPartialUploads stores an object and writes a leftover temp
// file next to it in the directory base that s stores into. It checks
// that ListPartialUploads lists only the leftover, with its size and a
// time, and that Delete removes it by the listed key and keeps the
// object.
func checkListPartialUploads(t *testing.T, s storage.Storer, base string) {
t.Helper()
ctx := context.Background()
err = f.Put(ctx, testBlobKey, strings.NewReader("blob-bytes"))
err := s.Put(ctx, testBlobKey, strings.NewReader("blob-bytes"))
if err != nil {
t.Fatalf("Put: %v", err)
}
leftover := filepath.Join(base, testBlobKey+"-123456.partial")
leftoverKey := testBlobKey + "-123456.partial"
leftover := filepath.Join(base, leftoverKey)
err = os.WriteFile(leftover, []byte("half"), 0o600)
if err != nil {
t.Fatalf("writing leftover temp file: %v", err)
}
err = f.DeletePartialUploads(ctx, "blobs/")
partial, err := s.ListPartialUploads(ctx, "blobs/")
if err != nil {
t.Fatalf("DeletePartialUploads: %v", err)
t.Fatalf("ListPartialUploads: %v", err)
}
if len(partial) != 1 || partial[0].Key != leftoverKey ||
partial[0].Size != int64(len("half")) || partial[0].ModTime.IsZero() {
t.Fatalf("ListPartialUploads = %+v, want only %s, 4 bytes, "+
"with a time", partial, leftoverKey)
}
err = s.Delete(ctx, partial[0].Key)
if err != nil {
t.Fatalf("Delete: %v", err)
}
_, err = os.Stat(leftover)
@@ -157,7 +181,7 @@ func TestFileStorer_DeletePartialUploads(t *testing.T) {
t.Errorf("leftover temp file was not removed: %v", err)
}
_, err = f.Stat(ctx, testBlobKey)
_, err = s.Stat(ctx, testBlobKey)
if err != nil {
t.Errorf("Stat of the real key: %v", err)
}
+13 -18
View File
@@ -239,11 +239,11 @@ func TestFileStorerListFailsOnSymlinkLoop(t *testing.T) {
}
}
// TestFileStorerDeletePartialUploadsThroughSymlinkedDirectory checks that
// DeletePartialUploads, which remote nuke uses, removes a leftover temp
// file behind a symlinked metadata/ or blobs/ directory and keeps the
// object at the real key.
func TestFileStorerDeletePartialUploadsThroughSymlinkedDirectory(t *testing.T) {
// TestFileStorerListPartialUploadsThroughSymlinkedDirectory checks that
// ListPartialUploads, which prune and remote nuke use, lists a leftover
// temp file behind a symlinked metadata/ or blobs/ directory under its
// key, and leaves out the object at the real key.
func TestFileStorerListPartialUploadsThroughSymlinkedDirectory(t *testing.T) {
t.Parallel()
ctx := context.Background()
@@ -265,29 +265,24 @@ func TestFileStorerDeletePartialUploadsThroughSymlinkedDirectory(t *testing.T) {
t.Fatalf("Put: %v", err)
}
leftover := filepath.Join(base, key+"-123456.partial")
leftoverKey := key + "-123456.partial"
err = os.WriteFile(leftover, []byte("half"), 0o600)
err = os.WriteFile(filepath.Join(base, leftoverKey),
[]byte("half"), 0o600)
if err != nil {
t.Fatalf("writing leftover temp file: %v", err)
}
moveBehindSymlink(t, base, dir)
err = s.DeletePartialUploads(ctx, dir+"/")
partial, err := s.ListPartialUploads(ctx, dir+"/")
if err != nil {
t.Fatalf("DeletePartialUploads: %v", err)
t.Fatalf("ListPartialUploads: %v", err)
}
// leftover runs through the link.
_, err = os.Stat(leftover)
if !os.IsNotExist(err) {
t.Errorf("leftover temp file was not removed: %v", err)
}
_, err = s.Stat(ctx, key)
if err != nil {
t.Errorf("Stat of the real key: %v", err)
if len(partial) != 1 || partial[0].Key != leftoverKey {
t.Errorf("ListPartialUploads = %+v, want only %s",
partial, leftoverKey)
}
})
}
+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 == "" {
+15 -15
View File
@@ -16,6 +16,7 @@ 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"
@@ -256,29 +257,28 @@ func (r *RcloneStorer) ListStream(
return ch
}
// DeletePartialUploads removes every object under prefix whose name ends
// in tempSuffix.
func (r *RcloneStorer) DeletePartialUploads(ctx context.Context, prefix string) error {
var partial []fs.Object
// ListPartialUploads returns each object under prefix whose name ends in
// tempSuffix.
func (r *RcloneStorer) ListPartialUploads(
ctx context.Context, prefix string,
) ([]ObjectInfo, error) {
var partial []ObjectInfo
err := operations.ListFn(ctx, r.fsys, func(obj fs.Object) {
key := obj.Remote()
if strings.HasPrefix(key, prefix) && strings.HasSuffix(key, tempSuffix) {
partial = append(partial, obj)
partial = append(partial, ObjectInfo{
Key: key,
Size: obj.Size(),
ModTime: obj.ModTime(ctx),
})
}
})
if err != nil {
return fmt.Errorf("listing objects: %w", err)
return nil, fmt.Errorf("listing objects: %w", err)
}
for _, obj := range partial {
err = obj.Remove(ctx)
if err != nil {
return fmt.Errorf("removing object: %w", err)
}
}
return nil
return partial, nil
}
// Info returns human-readable storage location information.
@@ -289,7 +289,7 @@ func (r *RcloneStorer) Info() Info {
}
return Info{
Type: schemeRclone,
Type: storageurl.SchemeRclone,
Location: location,
}
}
+7 -31
View File
@@ -205,45 +205,21 @@ func TestRcloneStorerListSkipsPartialFiles(t *testing.T) {
}
}
// TestRcloneStorerDeletePartialUploads checks that a temporary file left
// by a killed upload is removed and the object at the real key is kept.
// TestRcloneStorerListPartialUploads checks that a temporary file left by
// a killed upload is listed with its size and time, that the object at
// the real key is not, and that Delete removes the leftover by the listed
// key.
//
//nolint:paralleltest // NewRcloneStorer installs the process-global rclone config
func TestRcloneStorerDeletePartialUploads(t *testing.T) {
func TestRcloneStorerListPartialUploads(t *testing.T) {
dir := t.TempDir()
ctx := context.Background()
s, err := storage.NewRcloneStorer(ctx, ":local", dir)
s, err := storage.NewRcloneStorer(context.Background(), ":local", dir)
if err != nil {
t.Fatalf("NewRcloneStorer: %v", err)
}
err = s.Put(ctx, testBlobKey, strings.NewReader("blob-bytes"))
if err != nil {
t.Fatalf("Put: %v", err)
}
leftover := filepath.Join(dir, testBlobKey+"-123456.partial")
err = os.WriteFile(leftover, []byte("half"), 0o600)
if err != nil {
t.Fatalf("writing leftover temp file: %v", err)
}
err = s.DeletePartialUploads(ctx, "blobs/")
if err != nil {
t.Fatalf("DeletePartialUploads: %v", err)
}
_, err = os.Stat(leftover)
if !os.IsNotExist(err) {
t.Errorf("leftover temp file was not removed: %v", err)
}
_, err = s.Stat(ctx, testBlobKey)
if err != nil {
t.Errorf("Stat of the real key: %v", err)
}
checkListPartialUploads(t, s, dir)
}
// newRcloneStorerOnWrappedLocal registers name as rclone's local backend
+6 -4
View File
@@ -100,10 +100,12 @@ func (s *S3Storer) ListStream(ctx context.Context, prefix string) <-chan ObjectI
return ch
}
// DeletePartialUploads has nothing to remove: S3 shows an object only once
// its upload has completed, so an upload cut off part-way leaves none.
func (s *S3Storer) DeletePartialUploads(_ context.Context, _ string) error {
return nil
// ListPartialUploads finds none: S3 shows an object only once its upload
// has completed, so an upload cut off part-way leaves none.
func (s *S3Storer) ListPartialUploads(
_ context.Context, _ string,
) ([]ObjectInfo, error) {
return nil, nil
}
// Info returns human-readable storage location information.
+6 -5
View File
@@ -77,11 +77,12 @@ type Storer interface {
// If an error occurs during listing, the final item will have Err set.
ListStream(ctx context.Context, prefix string) <-chan ObjectInfo
// DeletePartialUploads removes every object under prefix that an
// upload cut off part-way left under a temporary name ending in
// `.partial`. The file and rclone backends' List and ListStream skip
// such an object.
DeletePartialUploads(ctx context.Context, prefix string) error
// ListPartialUploads returns each object under prefix whose name ends
// in `.partial`, as a killed upload leaves it, with its key, size and
// modification time. The file and rclone
// backends' List and ListStream skip such an object; Delete removes
// it.
ListPartialUploads(ctx context.Context, prefix string) ([]ObjectInfo, error)
// Info returns human-readable storage location information.
Info() Info
@@ -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.
@@ -25,7 +28,6 @@ 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(
"storage URL must not carry credentials; " +
"set s3.access_key_id and s3.secret_access_key in the config instead")
@@ -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") {
@@ -258,8 +258,10 @@ 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) ListPartialUploads(
_ context.Context, _ string,
) ([]storage.ObjectInfo, error) {
return nil, errStubUnused
}
func (s *stubLister) Info() storage.Info {
+40 -6
View File
@@ -216,6 +216,11 @@ type RemoteInfoResult struct {
OrphanedBlobCount *int `json:"orphaned_blob_count"`
OrphanedBlobSize *int64 `json:"orphaned_blob_size"`
// `.partial` objects under metadata/ and blobs/ left by killed
// uploads. The blob figures above leave them out.
PartialUploadCount int `json:"partial_upload_count"`
PartialUploadSize int64 `json:"partial_upload_size"`
// Remote key of each snapshot whose manifest could not be read
UnreadableManifests []string `json:"unreadable_manifests,omitempty"`
@@ -279,6 +284,16 @@ func (v *Vaultik) RemoteInfo(jsonOutput bool) error {
return err
}
partialUploads, err := v.listPartialUploads()
if err != nil {
return err
}
for _, object := range partialUploads {
result.PartialUploadCount++
result.PartialUploadSize += object.Size
}
log.Info("Remote info complete",
"snapshots", result.TotalMetadataCount,
"total_blobs", result.TotalBlobCount,
@@ -539,6 +554,12 @@ func (v *Vaultik) printRemoteInfoTable(result *RemoteInfoResult) {
"", "", ubytes(result.TotalMetadataSize))
}
v.printRemoteBlobStorage(result)
}
// printRemoteBlobStorage renders the blob storage section of the
// human-readable remote info output.
func (v *Vaultik) printRemoteBlobStorage(result *RemoteInfoResult) {
v.stdoutf("\n=== Blob Storage ===\n")
v.stdoutf("Total blobs on remote: %s (%s)\n",
humanize.Comma(int64(result.TotalBlobCount)),
@@ -552,16 +573,29 @@ func (v *Vaultik) printRemoteInfoTable(result *RemoteInfoResult) {
"(%d manifest(s) could not be read, "+
"%d manifest(s) under a non-conforming name skipped)\n",
len(result.UnreadableManifests), result.SkippedManifestCount)
return
}
} else {
v.stdoutf("Orphaned (unreferenced): %s (%s)\n",
humanize.Comma(int64(*result.OrphanedBlobCount)),
ubytes(*result.OrphanedBlobSize))
}
if *result.OrphanedBlobCount > 0 {
v.stdoutf("\nRun 'vaultik prune' to remove orphaned blobs.\n")
v.stdoutf("Partial uploads: %s (%s)\n",
humanize.Comma(int64(result.PartialUploadCount)),
ubytes(result.PartialUploadSize))
var toRemove []string
if result.OrphanedBlobCount != nil && *result.OrphanedBlobCount > 0 {
toRemove = append(toRemove, "orphaned blobs")
}
if result.PartialUploadCount > 0 {
toRemove = append(toRemove, "partial uploads")
}
if len(toRemove) > 0 {
v.stdoutf("\nRun 'vaultik prune' to remove %s.\n",
strings.Join(toRemove, " and "))
}
}
+6 -4
View File
@@ -155,10 +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
// ListPartialUploads finds none: Put stores each object under its key at
// once.
func (m *MockStorer) ListPartialUploads(
_ context.Context, _ string,
) ([]storage.ObjectInfo, error) {
return nil, nil
}
func (m *MockStorer) Info() storage.Info {
+206 -39
View File
@@ -31,6 +31,11 @@ var errBlobDeleteFailed = errors.New("blob(s) could not be deleted")
var errMetadataDirDeleteFailed = errors.New(
"metadata director(ies) with no manifest could not be deleted")
// errPartialUploadDeleteFailed reports `.partial` objects prune could not
// delete.
var errPartialUploadDeleteFailed = errors.New(
"partial upload(s) could not be deleted")
// errObjectsLeft reports objects remote nuke still finds on the backup
// destination store after deleting.
var errObjectsLeft = errors.New(
@@ -138,9 +143,9 @@ func (v *Vaultik) emptyDestinationStore() error {
// that fails is logged and the others still run; that object then
// shows up in the listing afterwards.
func (v *Vaultik) deleteEverythingUnder(prefix string) ([]string, error) {
keys, err := v.Storage.List(v.ctx, prefix)
keys, err := v.listEverythingUnder(prefix)
if err != nil {
return nil, fmt.Errorf("listing %s: %w", prefix, err)
return nil, err
}
for _, key := range keys {
@@ -150,19 +155,47 @@ func (v *Vaultik) deleteEverythingUnder(prefix string) ([]string, error) {
}
}
// The file and rclone listings skip `.partial` objects, so the
// deletes above never reach them.
err = v.Storage.DeletePartialUploads(v.ctx, prefix)
if err != nil {
return nil, fmt.Errorf("deleting partial uploads: %w", err)
return v.listEverythingUnder(prefix)
}
left, err := v.Storage.List(v.ctx, prefix)
// listEverythingUnder returns the key of every object under prefix,
// including the `.partial` objects left by killed uploads, which the file
// and rclone backends' List skips.
func (v *Vaultik) listEverythingUnder(prefix string) ([]string, error) {
keys, err := v.Storage.List(v.ctx, prefix)
if err != nil {
return nil, fmt.Errorf("listing %s: %w", prefix, err)
}
return left, nil
partialUploads, err := v.Storage.ListPartialUploads(v.ctx, prefix)
if err != nil {
return nil, fmt.Errorf("listing partial uploads under %s: %w",
prefix, err)
}
for _, object := range partialUploads {
keys = append(keys, object.Key)
}
return keys, nil
}
// listPartialUploads returns the `.partial` objects under metadata/ and
// blobs/ left by killed uploads.
func (v *Vaultik) listPartialUploads() ([]storage.ObjectInfo, error) {
var partialUploads []storage.ObjectInfo
for _, prefix := range []string{"metadata/", "blobs/"} {
objects, err := v.Storage.ListPartialUploads(v.ctx, prefix)
if err != nil {
return nil, fmt.Errorf("listing partial uploads under %s: %w",
prefix, err)
}
partialUploads = append(partialUploads, objects...)
}
return partialUploads, nil
}
// PruneBlobsResult contains the result of a blob prune operation
@@ -182,11 +215,19 @@ type PruneBlobsResult struct {
// not delete.
MetadataDirsDeleted int `json:"metadata_dirs_deleted"`
MetadataDirsFailed int `json:"metadata_dirs_failed,omitempty"`
// PartialUploadsDeleted counts the `.partial` objects prune deleted,
// and PartialUploadsFailed those it could not delete.
// PartialUploadsTooNew counts those kept for being newer than the
// prune grace period, or of unknown age.
PartialUploadsDeleted int `json:"partial_uploads_deleted"`
PartialUploadsFailed int `json:"partial_uploads_failed,omitempty"`
PartialUploadsTooNew int `json:"partial_uploads_too_new"`
}
// Prune removes orphaned data from the local index database AND, from the
// backup destination store, unreferenced blobs and the directories under
// metadata/ with no manifest. This is the single user-facing prune entry
// backup destination store, unreferenced blobs, the directories under
// metadata/ with no manifest and the `.partial` objects left by killed
// uploads. This is the single user-facing prune entry
// point — the split between local and remote cleanup is an
// implementation detail. Calling code should prefer this method over
// PruneDatabase or PruneBlobs individually unless it specifically wants
@@ -214,8 +255,9 @@ func (v *Vaultik) Prune(opts *PruneOptions) error {
return v.PruneBlobs(opts)
}
// PruneBlobs removes unreferenced blobs from storage, and each directory
// under metadata/ that a backup left with no manifest.
// PruneBlobs removes unreferenced blobs from storage, each directory
// under metadata/ that a backup left with no manifest, and each
// `.partial` object left by a killed upload.
func (v *Vaultik) PruneBlobs(opts *PruneOptions) error {
log.Info("Starting prune operation")
@@ -242,14 +284,21 @@ func (v *Vaultik) PruneBlobs(opts *PruneOptions) error {
return err
}
partialUploads, partialTooNew, err := v.findOldPartialUploads()
if err != nil {
return err
}
result := &PruneBlobsResult{
BlobsFound: len(unreferencedBlobs),
BlobsTooNew: tooNew,
PartialUploadsTooNew: partialTooNew,
}
v.reportBlobsTooNew(tooNew, opts)
v.reportTooNew(result, opts)
if len(unreferencedBlobs) == 0 && len(dirsWithoutManifest) == 0 {
if len(unreferencedBlobs) == 0 && len(dirsWithoutManifest) == 0 &&
len(partialUploads) == 0 {
log.Info("No unreferenced blobs found")
if opts.JSON {
@@ -263,15 +312,17 @@ func (v *Vaultik) PruneBlobs(opts *PruneOptions) error {
log.Info("Found unreferenced blobs",
"count", len(unreferencedBlobs), "total_size", ubytes(totalSize),
"metadata_dirs_without_manifest", len(dirsWithoutManifest))
"metadata_dirs_without_manifest", len(dirsWithoutManifest),
"partial_uploads", len(partialUploads))
if !v.confirmPrune(opts, len(unreferencedBlobs), totalSize,
dirsWithoutManifest) {
dirsWithoutManifest, partialUploads) {
return ErrNotConfirmed
}
v.deleteUnreferencedBlobs(unreferencedBlobs, allBlobs, result)
v.deleteMetadataDirs(dirsWithoutManifest, result)
v.deletePartialUploads(partialUploads, result)
if opts.JSON {
err = v.outputPruneBlobsJSON(result)
@@ -279,9 +330,16 @@ func (v *Vaultik) PruneBlobs(opts *PruneOptions) error {
return err
}
} else {
v.reportPruneDeletions(result, len(dirsWithoutManifest))
v.reportPruneDeletions(result, len(dirsWithoutManifest),
len(partialUploads))
}
return pruneDeleteFailures(result)
}
// pruneDeleteFailures returns an error for each kind of object prune
// could not delete, or nil when every delete succeeded.
func pruneDeleteFailures(result *PruneBlobsResult) error {
var failures []error
if result.BlobsFailed > 0 {
@@ -294,26 +352,41 @@ func (v *Vaultik) PruneBlobs(opts *PruneOptions) error {
result.MetadataDirsFailed, errMetadataDirDeleteFailed))
}
if result.PartialUploadsFailed > 0 {
failures = append(failures, fmt.Errorf("%d %w",
result.PartialUploadsFailed, errPartialUploadDeleteFailed))
}
return errors.Join(failures...)
}
// confirmPrune states what prune found to delete, unreferenced blobs and
// confirmPrune states what prune found to delete, unreferenced blobs,
// directories under metadata/ with no manifest, naming each directory by
// its remote key, and, unless --force is given, asks the operator to
// confirm. Under --json it prints nothing and does not ask. It reports
// whether to go ahead.
// its remote key, and `.partial` objects, and, unless --force is given,
// asks the operator to confirm. Under --json it prints nothing and does
// not ask. It reports whether to go ahead.
func (v *Vaultik) confirmPrune(
opts *PruneOptions, blobCount int, blobsSize int64, dirs []string,
partialUploads []storage.ObjectInfo,
) bool {
if opts.JSON {
return true
}
var partialSize int64
for _, object := range partialUploads {
partialSize += object.Size
}
dirCount := len(dirs)
partialCount := len(partialUploads)
blobsFound := fmt.Sprintf("Found %d unreferenced blob(s) totaling %s.",
blobCount, ubytes(blobsSize))
dirsFound := fmt.Sprintf("Found %d metadata director(ies) left by "+
"backups that stopped before their manifest:", dirCount)
partialFound := fmt.Sprintf("Found %d partial upload(s) totaling %s, "+
"left by uploads cut off part-way.", partialCount, ubytes(partialSize))
if opts.Force {
if blobCount > 0 {
@@ -328,6 +401,10 @@ func (v *Vaultik) confirmPrune(
}
}
if partialCount > 0 {
v.UI.Infof("%s", partialFound)
}
return true
}
@@ -346,16 +423,13 @@ func (v *Vaultik) confirmPrune(
}
}
switch {
case dirCount == 0:
v.stdoutf("\nDelete %d unreferenced blob(s)? [y/N] ", blobCount)
case blobCount == 0:
v.stdoutf("\nDelete %d metadata director(ies)? [y/N] ", dirCount)
default:
v.stdoutf("\nDelete %d unreferenced blob(s) and %d metadata "+
"director(ies)? [y/N] ", blobCount, dirCount)
if partialCount > 0 {
v.stdoutf("%s\n", partialFound)
}
v.stdoutf("\nDelete %s? [y/N] ",
pruneTargets(blobCount, dirCount, partialCount))
var confirm string
// A failure to read the answer means no confirmation.
@@ -369,9 +443,36 @@ func (v *Vaultik) confirmPrune(
return true
}
// reportPruneDeletions says how many blobs and metadata directories
// prune deleted, naming each kind only when it found some to delete.
func (v *Vaultik) reportPruneDeletions(result *PruneBlobsResult, dirCount int) {
// pruneTargets names what the prune prompt offers to delete, such as
// "2 unreferenced blob(s) and 1 partial upload(s)", leaving out each kind
// with a count of zero.
func pruneTargets(blobCount, dirCount, partialCount int) string {
var targets []string
if blobCount > 0 {
targets = append(targets,
fmt.Sprintf("%d unreferenced blob(s)", blobCount))
}
if dirCount > 0 {
targets = append(targets,
fmt.Sprintf("%d metadata director(ies)", dirCount))
}
if partialCount > 0 {
targets = append(targets,
fmt.Sprintf("%d partial upload(s)", partialCount))
}
return strings.Join(targets, " and ")
}
// reportPruneDeletions says how many blobs, metadata directories and
// partial uploads prune deleted, naming each kind only when it found some
// to delete.
func (v *Vaultik) reportPruneDeletions(
result *PruneBlobsResult, dirCount, partialCount int,
) {
if result.BlobsFound > 0 {
v.UI.Infof("Deleted %d blob(s) totaling %s.",
result.BlobsDeleted, ubytes(result.BytesFreed))
@@ -381,6 +482,11 @@ func (v *Vaultik) reportPruneDeletions(result *PruneBlobsResult, dirCount int) {
v.UI.Infof("Deleted %d metadata director(ies) with no manifest.",
result.MetadataDirsDeleted)
}
if partialCount > 0 {
v.UI.Infof("Deleted %d partial upload(s).",
result.PartialUploadsDeleted)
}
}
// listMetadataObjects lists every object under metadata/ on the
@@ -611,18 +717,79 @@ func (v *Vaultik) deleteMetadataDirs(
}
}
// reportBlobsTooNew says how many unreferenced blobs prune kept for being
// newer than the grace period or of unknown age. Under --json the
// document carries the count instead.
func (v *Vaultik) reportBlobsTooNew(tooNew int, opts *PruneOptions) {
if tooNew == 0 || opts.JSON {
// reportTooNew says how many unreferenced blobs and partial uploads prune
// kept for being newer than the grace period or of unknown age. Under
// --json the document carries the counts instead.
func (v *Vaultik) reportTooNew(result *PruneBlobsResult, opts *PruneOptions) {
if opts.JSON {
return
}
if result.BlobsTooNew > 0 {
v.UI.Infof("Kept %d unreferenced blob(s) newer than "+
"prune_grace_period (%s), or of unknown age: a backup still "+
"running may need them.",
tooNew, v.Config.PruneGracePeriod)
result.BlobsTooNew, v.Config.PruneGracePeriod)
}
if result.PartialUploadsTooNew > 0 {
v.UI.Infof("Kept %d partial upload(s) newer than "+
"prune_grace_period (%s), or of unknown age: an upload may "+
"still be writing them.",
result.PartialUploadsTooNew, v.Config.PruneGracePeriod)
}
}
// findOldPartialUploads returns the `.partial` objects under metadata/
// and blobs/ that are older than the prune grace period. It also returns
// how many it left out for being newer than that, or of unknown age
// because the listing gave no time for them.
func (v *Vaultik) findOldPartialUploads() ([]storage.ObjectInfo, int, error) {
partialUploads, err := v.listPartialUploads()
if err != nil {
return nil, 0, err
}
cutoff := time.Now().UTC().Add(-v.Config.PruneGracePeriod)
var (
old []storage.ObjectInfo
tooNew int
)
for _, object := range partialUploads {
if object.ModTime.IsZero() || object.ModTime.After(cutoff) {
tooNew++
continue
}
old = append(old, object)
}
return old, tooNew, nil
}
// deletePartialUploads deletes the given `.partial` objects and counts
// in the result those deleted and those it could not delete.
func (v *Vaultik) deletePartialUploads(
partialUploads []storage.ObjectInfo, result *PruneBlobsResult,
) {
for _, object := range partialUploads {
err := v.Storage.Delete(v.ctx, object.Key)
if err != nil {
log.Error("Failed to delete partial upload",
"key", object.Key, "error", err)
result.PartialUploadsFailed++
continue
}
log.Info("Deleted partial upload", "key", object.Key)
result.PartialUploadsDeleted++
}
}
// deleteUnreferencedBlobs deletes the given blobs from storage and
@@ -0,0 +1,157 @@
package vaultik_test
import (
"bytes"
"context"
"encoding/json"
"os"
"path/filepath"
"testing"
"time"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
"sneak.berlin/go/vaultik/internal/config"
"sneak.berlin/go/vaultik/internal/log"
"sneak.berlin/go/vaultik/internal/storage"
"sneak.berlin/go/vaultik/internal/storage/faultstore"
"sneak.berlin/go/vaultik/internal/ui"
"sneak.berlin/go/vaultik/internal/vaultik"
)
// partialUploadGracePeriod is the prune grace period of the vaultik
// newPartialUploadStore returns.
const partialUploadGracePeriod = time.Hour
// newPartialUploadStore returns a vaultik on a file:// destination
// holding `.partial` files left by killed uploads: one under blobs/
// and one under metadata/ older than the prune grace period, and one
// under blobs/ newer than that. It also returns the buffer the vaultik
// writes its output to, the paths of the old files and the path of the
// new one.
func newPartialUploadStore(
t *testing.T,
) (*vaultik.Vaultik, *bytes.Buffer, []string, string) {
t.Helper()
storeDir := t.TempDir()
store, err := storage.NewFileStorer(storeDir)
require.NoError(t, err)
hash := testBlobHashA
oldFiles := []string{
filepath.Join(storeDir, "blobs", hash[:2], hash[2:4],
hash+"-123456.partial"),
filepath.Join(storeDir, metadataObjectKey(
"testhost_home_2026-01-01T00:00:00Z", "db.zst.age-123456.partial")),
}
newFile := filepath.Join(storeDir, "blobs", hash[:2], hash[2:4],
hash+"-654321.partial")
beforeGracePeriod := time.Now().Add(-partialUploadGracePeriod - time.Minute)
for _, path := range append([]string{newFile}, oldFiles...) {
require.NoError(t, os.MkdirAll(filepath.Dir(path), 0o750))
require.NoError(t, os.WriteFile(path, []byte("half an upload"), 0o600))
}
for _, path := range oldFiles {
require.NoError(t, os.Chtimes(path, beforeGracePeriod, beforeGracePeriod))
}
stdout := &bytes.Buffer{}
v := &vaultik.Vaultik{
Config: &config.Config{PruneGracePeriod: partialUploadGracePeriod},
Storage: store,
Stdout: stdout,
UI: ui.NewWithColor(stdout, false),
}
v.SetContext(context.Background())
return v, stdout, oldFiles, newFile
}
// TestPruneDeletesPartialUploadsOlderThanGracePeriod checks that prune
// deletes a `.partial` file under blobs/ or metadata/ left by a killed
// upload once it is older than the grace period, keeps a newer one,
// and counts both in the --json document.
func TestPruneDeletesPartialUploadsOlderThanGracePeriod(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
v, stdout, oldFiles, newFile := newPartialUploadStore(t)
require.NoError(t, v.PruneBlobs(&vaultik.PruneOptions{JSON: true}))
for _, path := range oldFiles {
_, err := os.Stat(path)
require.ErrorIs(t, err, os.ErrNotExist, "%s must be deleted", path)
}
_, err := os.Stat(newFile)
require.NoError(t, err, "a partial upload newer than the grace period "+
"must be kept")
var result vaultik.PruneBlobsResult
require.NoError(t, json.Unmarshal(stdout.Bytes(), &result))
assert.Equal(t, 2, result.PartialUploadsDeleted)
assert.Equal(t, 1, result.PartialUploadsTooNew)
}
// TestPruneFailedPartialUploadDeleteReturnsError checks that prune
// returns an error, and counts the failures in the --json document, when
// the `.partial` files it found cannot be deleted.
func TestPruneFailedPartialUploadDeleteReturnsError(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
v, stdout, oldFiles, _ := newPartialUploadStore(t)
store := faultstore.New(v.Storage)
store.OnDelete = func(string) bool { return true }
v.Storage = store
err := v.PruneBlobs(&vaultik.PruneOptions{JSON: true})
require.ErrorContains(t, err, "2 partial upload(s) could not be deleted")
for _, path := range oldFiles {
_, statErr := os.Stat(path)
require.NoError(t, statErr, "%s must still exist", path)
}
var result vaultik.PruneBlobsResult
require.NoError(t, json.Unmarshal(stdout.Bytes(), &result),
"stdout must hold the JSON document, got:\n%s", stdout.String())
assert.Equal(t, 2, result.PartialUploadsFailed)
assert.Equal(t, 0, result.PartialUploadsDeleted)
}
// TestRemoteInfoCountsPartialUploads checks that remote info counts
// every `.partial` file under blobs/ and metadata/, whatever its age, and
// advises running prune.
func TestRemoteInfoCountsPartialUploads(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
v, stdout, _, _ := newPartialUploadStore(t)
require.NoError(t, v.RemoteInfo(true))
var result vaultik.RemoteInfoResult
require.NoError(t, json.Unmarshal(stdout.Bytes(), &result))
assert.Equal(t, 3, result.PartialUploadCount)
assert.Equal(t, int64(3*len("half an upload")), result.PartialUploadSize)
assert.Equal(t, 0, result.TotalBlobCount)
stdout.Reset()
require.NoError(t, v.RemoteInfo(false))
text := stdout.String()
assert.Contains(t, text, "Partial uploads: 3 (")
assert.Contains(t, text, "Run 'vaultik prune' to remove partial uploads.")
}
+6 -4
View File
@@ -136,10 +136,12 @@ 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
// ListPartialUploads finds none: Put stores each object under its key at
// once.
func (s *testStorer) ListPartialUploads(
_ context.Context, _ string,
) ([]storage.ObjectInfo, error) {
return nil, nil
}
func (s *testStorer) Info() storage.Info {
+4 -4
View File
@@ -302,10 +302,10 @@ func (v *Vaultik) snapshotNamesToCreate(requested []string) ([]string, error) {
}
// runPostBackupPrune drops older snapshots of the given names and removes
// from remote storage the orphan blobs and the directories under
// metadata/ with no manifest, as PruneBlobs does. If keepNewerThan is set
// (e.g. "4w"), snapshots newer than that duration are kept. Otherwise only
// the latest snapshot of each name is kept.
// from remote storage the orphan blobs, the directories under metadata/
// with no manifest and the `.partial` objects, as PruneBlobs does. If
// keepNewerThan is set (e.g. "4w"), snapshots newer than that duration are
// kept. Otherwise only the latest snapshot of each name is kept.
func (v *Vaultik) runPostBackupPrune(
snapshotNames []string, keepNewerThan string,
) error {