Compare commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
e5b08b8638 | ||
|
|
be362080d3 | ||
|
|
aaa2219d6b | ||
|
|
547b9faf36 | ||
|
|
fbcb1b9fc6 | ||
|
|
4605eae024 | ||
|
|
5b09271751 | ||
|
|
9fedcbeb0a |
No files matched your search
+9
-2
@@ -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
|
||||
|
||||
@@ -169,7 +169,7 @@ vaultik [--config <path>] config init
|
||||
vaultik [--config <path>] config edit
|
||||
vaultik [--config <path>] config get <key>
|
||||
vaultik [--config <path>] config set <key> <value>
|
||||
vaultik [--config <path>] snapshot create [snapshot-names...] [--cron] [--prune] [--keep-newer-than <duration>] [--dry-run]
|
||||
vaultik [--config <path>] snapshot create [snapshot-names...] [--cron] [--prune] [--keep-newer-than <duration>]
|
||||
vaultik [--config <path>] snapshot list [--json] # alias: ls
|
||||
vaultik [--config <path>] snapshot files <snapshot-id> [path] [--json]
|
||||
vaultik [--config <path>] snapshot verify <snapshot-id> [--deep] [--json]
|
||||
@@ -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
|
||||
@@ -196,9 +197,10 @@ vaultik version
|
||||
that cannot be restored when restoring, instead of aborting. Packing and
|
||||
storage errors while creating a snapshot (which would leave a chunk recorded
|
||||
but not stored) still abort the run. A run that skipped anything still
|
||||
finishes but exits non-zero: `snapshot create` keeps the snapshot and counts
|
||||
each file or directory it skipped as failed. A file removed during the backup
|
||||
is also counted as failed but does not change the exit status.
|
||||
finishes but exits `3` (see [exit status](#exit-status)): `snapshot create`
|
||||
keeps the snapshot and counts each file or directory it skipped as failed. A
|
||||
file removed during the backup is also counted as failed but does not change
|
||||
the exit status.
|
||||
|
||||
### locking
|
||||
|
||||
@@ -271,6 +273,19 @@ Every `--json` command therefore pipes on its own, with no additional flag:
|
||||
`vaultik snapshot list --json | jq .` and `vaultik prune --json | jq .` both
|
||||
work as written.
|
||||
|
||||
### exit status
|
||||
|
||||
- `0`: the command succeeded.
|
||||
- `1`: the command failed.
|
||||
- `3`: `snapshot create` or `snapshot restore` finished, but `--skip-errors`
|
||||
skipped files it could not read or restore. `restic backup` uses the same
|
||||
status for this case.
|
||||
- `130`: Ctrl-C, `SIGINT` or `SIGTERM` stopped the command.
|
||||
|
||||
A cron job can page on `1` and only log `3`. A run that skipped files and also
|
||||
failed in another way exits `1`. For example, a restore that skipped files and
|
||||
was asked for a path the snapshot does not hold exits `1`.
|
||||
|
||||
### environment variables
|
||||
|
||||
- `VAULTIK_AGE_SECRET_KEY`: Age private key for decryption (required for
|
||||
@@ -340,46 +355,33 @@ 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. One of them may
|
||||
be the only one that holds what was skipped. The command says so and exits
|
||||
`3`. The prune does not run either when the backup found nothing in a
|
||||
configured path, as in the mount point of a volume that is not mounted. Every
|
||||
older snapshot is kept, and the command names the path and exits `1`, 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`. The prune does not run either when this backup does not find
|
||||
a volume that an earlier snapshot of the same name in the local index found.
|
||||
The volume's mount point is a directory at or below a configured path. That
|
||||
directory is on a different filesystem from its parent and holds an entry the
|
||||
backup does not exclude. Every older snapshot is kept, and the command names
|
||||
the directory and exits `1`, 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. Nor does it find
|
||||
the volume 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
|
||||
before the backup starts.
|
||||
- `--dry-run`: Scan the source paths and print what a backup would store,
|
||||
without storing it. The summary gives the files examined, to back up and
|
||||
unchanged, their sizes, and the count of excluded entries. An excluded
|
||||
directory counts once, since the scan does not enter it. With `--verbose`, it
|
||||
also prints each excluded entry and the exclude pattern that matched it. It
|
||||
writes nothing to the destination and records nothing in the local index, so
|
||||
it does not bind the index to the destination. Like the other commands that
|
||||
read the local index, it creates an empty one if there is none. When the local
|
||||
index holds an incomplete snapshot from an interrupted backup, it says so: the
|
||||
next backup drops that snapshot first and may back up more files than the dry
|
||||
run counts. It cannot be combined with `--prune`.
|
||||
- Fails before it writes anything when a `file://` destination directory does
|
||||
not exist, or when the local index holds snapshots and the destination answers
|
||||
that it has no `vaultik-destination.txt`. When that look-up fails for any
|
||||
@@ -531,14 +533,16 @@ 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
|
||||
@@ -548,7 +552,10 @@ 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.
|
||||
@@ -563,7 +570,9 @@ 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
|
||||
|
||||
@@ -613,7 +622,11 @@ 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`).
|
||||
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.
|
||||
|
||||
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
|
||||
@@ -622,8 +635,9 @@ 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
|
||||
@@ -732,6 +746,8 @@ 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
|
||||
|
||||
@@ -765,20 +781,20 @@ Run `vaultik config init` to generate a fully commented config file; a complete
|
||||
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 |
|
||||
| `storage_url` | | Storage backend URL (`s3://`, `file://`, `rclone://`) |
|
||||
| `s3.*` | | Legacy S3 configuration (endpoint, bucket, credentials) |
|
||||
| `exclude` | | Global exclude patterns (applied to all snapshots) |
|
||||
| `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 |
|
||||
| `hostname` | system hostname | Hostname used in snapshot IDs |
|
||||
| `index_path` | platform data dir | Local SQLite index path |
|
||||
| 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 |
|
||||
| `storage_url` | | Storage backend URL (`s3://`, `file://`, `rclone://`) |
|
||||
| `s3.*` | | Legacy S3 configuration (endpoint, bucket, credentials) |
|
||||
| `exclude` | | Global exclude patterns (applied to all snapshots) |
|
||||
| `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. `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 |
|
||||
|
||||
---
|
||||
|
||||
|
||||
@@ -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
|
||||
|
||||
@@ -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
|
||||
|
||||
|
||||
@@ -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
|
||||
|
||||
|
||||
+11
-10
@@ -39,10 +39,10 @@ const (
|
||||
// hold the PID lock so that at most one runs at a time.
|
||||
mutating lockMode = iota
|
||||
// readOnly commands (info, snapshot list, snapshot files, snapshot
|
||||
// verify, remote info, snapshot restore, snapshot create --dry-run)
|
||||
// do not write the local index or the remote store, so they run
|
||||
// without the lock and are never blocked by a running mutator.
|
||||
// restore writes only to the target directory it is given.
|
||||
// verify, remote info, snapshot restore) do not write the local index
|
||||
// or the remote store, so they run without the lock and are never
|
||||
// blocked by a running mutator. restore writes only to the target
|
||||
// directory it is given.
|
||||
readOnly
|
||||
)
|
||||
|
||||
@@ -198,7 +198,8 @@ func RunApp(ctx context.Context, app *fx.App) error {
|
||||
// (or, under `snapshot verify --json`, put in its document). Entry
|
||||
// turns it into a non-zero exit status without printing anything
|
||||
// further, so the error line is not doubled. It flows up from
|
||||
// RunOperation through cobra to Entry.
|
||||
// RunOperation through cobra to Entry, wrapping the operation's error
|
||||
// so that Entry can choose the exit status from it.
|
||||
var errReported = errors.New("operation failed")
|
||||
|
||||
// errInterrupted marks an operation that SIGINT or SIGTERM stopped
|
||||
@@ -232,8 +233,8 @@ func RunOperation(
|
||||
) error {
|
||||
var (
|
||||
mu sync.Mutex
|
||||
finished bool // op returned before any interrupt cancelled it
|
||||
failed bool // op finished with an error
|
||||
finished bool // op returned before any interrupt cancelled it
|
||||
opErr error // what op returned, when it finished
|
||||
)
|
||||
|
||||
opts.Invokes = append(opts.Invokes,
|
||||
@@ -258,7 +259,7 @@ func RunOperation(
|
||||
|
||||
mu.Lock()
|
||||
finished = true
|
||||
failed = err != nil
|
||||
opErr = err
|
||||
mu.Unlock()
|
||||
}
|
||||
|
||||
@@ -303,8 +304,8 @@ func RunOperation(
|
||||
switch {
|
||||
case !finished:
|
||||
return errInterrupted
|
||||
case failed:
|
||||
return errReported
|
||||
case opErr != nil:
|
||||
return fmt.Errorf("%w: %w", errReported, opErr)
|
||||
default:
|
||||
return nil
|
||||
}
|
||||
|
||||
@@ -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.
|
||||
|
||||
+16
-2
@@ -9,6 +9,7 @@ import (
|
||||
|
||||
"sneak.berlin/go/vaultik/internal/globals"
|
||||
"sneak.berlin/go/vaultik/internal/ui"
|
||||
"sneak.berlin/go/vaultik/internal/vaultik"
|
||||
)
|
||||
|
||||
// shortCommitLen is the number of git commit hash characters shown in
|
||||
@@ -20,6 +21,13 @@ const shortCommitLen = 12
|
||||
// shell reports for a command stopped by Ctrl-C.
|
||||
const exitCodeInterrupted = 130
|
||||
|
||||
// exitCodeSkippedFiles is the exit status of a `snapshot create` or
|
||||
// `snapshot restore` that finished but skipped files under
|
||||
// --skip-errors. It is the status `restic backup` uses for a snapshot
|
||||
// that could not read some files, so a cron job can tell such a run
|
||||
// from one that made no backup.
|
||||
const exitCodeSkippedFiles = 3
|
||||
|
||||
// Entry is the main entry point for the CLI application.
|
||||
// It first calls globals.FillUnsetFromBuildInfo, which fills in the
|
||||
// version, commit and commit date that the linker flags did not set.
|
||||
@@ -30,8 +38,9 @@ const exitCodeInterrupted = 130
|
||||
// The banner goes to stderr because stdout carries only the output the
|
||||
// user asked for, such as a completion script or a `config get` value.
|
||||
//
|
||||
// It returns the process exit code (0 on success, 130 when interrupted,
|
||||
// 1 on any other error) rather than calling os.Exit, so that main's
|
||||
// It returns the process exit code (0 on success, 3 when files were
|
||||
// skipped, 130 when interrupted, 1 on any other error) rather than
|
||||
// calling os.Exit, so that main's
|
||||
// deferred profile writers run before the process ends. See run in
|
||||
// cmd/vaultik/main.go.
|
||||
func Entry() int {
|
||||
@@ -58,6 +67,11 @@ func Entry() int {
|
||||
return exitCodeInterrupted
|
||||
}
|
||||
|
||||
if errors.Is(err, vaultik.ErrFilesUnreadable) ||
|
||||
errors.Is(err, vaultik.ErrFilesFailedRestore) {
|
||||
return exitCodeSkippedFiles
|
||||
}
|
||||
|
||||
return 1
|
||||
}
|
||||
|
||||
|
||||
@@ -0,0 +1,83 @@
|
||||
package cli //nolint:testpackage // shares runEntry and the hermetic config helpers
|
||||
|
||||
import (
|
||||
"os"
|
||||
"path/filepath"
|
||||
"testing"
|
||||
|
||||
"github.com/stretchr/testify/assert"
|
||||
"github.com/stretchr/testify/require"
|
||||
)
|
||||
|
||||
const flagSkipErrors = "--skip-errors"
|
||||
|
||||
// TestEntrySnapshotCreateSkipErrorsExitsNonZeroWhenItSkips backs up,
|
||||
// under --skip-errors, a source directory that does not exist, which the
|
||||
// walk skips. The command exits with exitCodeSkippedFiles and reports
|
||||
// the backup as completed, not as a failed snapshot creation. See
|
||||
// https://git.eeqj.de/sneak/vaultik/issues/310 and
|
||||
// https://git.eeqj.de/sneak/vaultik/issues/439.
|
||||
//
|
||||
//nolint:paralleltest // replaces os.Args, os.Stdout, os.Stderr and the xdg globals
|
||||
func TestEntrySnapshotCreateSkipErrorsExitsNonZeroWhenItSkips(t *testing.T) {
|
||||
// writeBackupConfig would create the source directory.
|
||||
configPath := writeHermeticPruneConfig(t, false)
|
||||
|
||||
code, stdout, stderr := runEntry(t,
|
||||
flagConfig, configPath, flagSkipErrors, cmdSnapshot, cmdCreate)
|
||||
|
||||
assert.Equal(t, exitCodeSkippedFiles, code)
|
||||
assert.Contains(t, stdout,
|
||||
"Files: 1 examined, 0 backed up, 0 unchanged, 1 failed.")
|
||||
assert.NotContains(t, stdout, "Finished successfully.")
|
||||
assert.Contains(t, stderr,
|
||||
"Backup completed, but 1 file(s) could not be read")
|
||||
assert.NotContains(t, stderr, "Snapshot creation failed")
|
||||
}
|
||||
|
||||
// TestEntrySnapshotRestoreSkipErrorsExitStatus backs up, deletes the
|
||||
// blobs from the destination, and restores under --skip-errors, so every
|
||||
// file is skipped. A restore that only skipped files exits with
|
||||
// exitCodeSkippedFiles. One that was also asked for a path the snapshot
|
||||
// does not hold exits 1. See
|
||||
// https://git.eeqj.de/sneak/vaultik/issues/439.
|
||||
//
|
||||
//nolint:paralleltest // replaces os.Args, os.Stdout, os.Stderr and the xdg globals
|
||||
func TestEntrySnapshotRestoreSkipErrorsExitStatus(t *testing.T) {
|
||||
for _, testCase := range []struct {
|
||||
name string
|
||||
missingPaths []string
|
||||
want int
|
||||
}{
|
||||
{name: "skipped files only", want: exitCodeSkippedFiles},
|
||||
{
|
||||
name: "and a path that matches nothing",
|
||||
missingPaths: []string{"/no/such/path"},
|
||||
want: 1,
|
||||
},
|
||||
} {
|
||||
t.Run(testCase.name, func(t *testing.T) {
|
||||
configPath, storeDir := writeBackupConfigWithPrivateKey(t)
|
||||
|
||||
code, _, _ := runEntry(t,
|
||||
flagConfig, configPath, cmdSnapshot, cmdCreate)
|
||||
require.Equal(t, 0, code)
|
||||
|
||||
require.NoError(t, os.RemoveAll(filepath.Join(storeDir, blobsDir)))
|
||||
|
||||
// writeBackupConfig puts the source directory beside the
|
||||
// config file.
|
||||
sourceDir := filepath.Join(filepath.Dir(configPath), "source")
|
||||
args := append([]string{
|
||||
flagConfig, configPath, flagSkipErrors, cmdSnapshot,
|
||||
cmdRestore, onlySnapshotID(t, configPath), t.TempDir(),
|
||||
sourceDir,
|
||||
}, testCase.missingPaths...)
|
||||
|
||||
code, _, stderr := runEntry(t, args...)
|
||||
|
||||
assert.Equal(t, testCase.want, code)
|
||||
assert.Contains(t, stderr, "1 file(s) failed to restore")
|
||||
})
|
||||
}
|
||||
}
|
||||
@@ -1,89 +0,0 @@
|
||||
package cli //nolint:testpackage // shares runEntry and the hermetic config helpers
|
||||
|
||||
import (
|
||||
"context"
|
||||
"io"
|
||||
"os"
|
||||
"path/filepath"
|
||||
"testing"
|
||||
|
||||
"github.com/stretchr/testify/assert"
|
||||
"github.com/stretchr/testify/require"
|
||||
"sneak.berlin/go/vaultik/internal/database"
|
||||
"sneak.berlin/go/vaultik/internal/ui"
|
||||
)
|
||||
|
||||
// TestEntrySnapshotCreateDryRun runs `snapshot create --dry-run
|
||||
// --verbose` on a source directory that holds one kept file, one file an
|
||||
// unanchored pattern excludes and one directory an anchored pattern
|
||||
// excludes. The summary counts the kept file and two excluded entries,
|
||||
// the excluded ones are listed with their patterns, and nothing is
|
||||
// written to the destination or recorded in the local index. See
|
||||
// https://git.eeqj.de/sneak/vaultik/issues/436.
|
||||
//
|
||||
//nolint:paralleltest // replaces os.Args, os.Stdout, os.Stderr and the xdg globals
|
||||
func TestEntrySnapshotCreateDryRun(t *testing.T) {
|
||||
configPath, storeDir := writeBackupConfig(t)
|
||||
sourceDir := filepath.Join(filepath.Dir(configPath), "source")
|
||||
cacheDir := filepath.Join(sourceDir, "cache")
|
||||
|
||||
require.NoError(t, os.WriteFile(
|
||||
filepath.Join(sourceDir, "debug.log"), []byte("log"), 0o600))
|
||||
require.NoError(t, os.Mkdir(cacheDir, 0o750))
|
||||
|
||||
for _, name := range []string{"a", "b"} {
|
||||
require.NoError(t, os.WriteFile(
|
||||
filepath.Join(cacheDir, name), []byte(name), 0o600))
|
||||
}
|
||||
|
||||
out := ui.NewWithColor(io.Discard, false)
|
||||
require.NoError(t, writeConfigSet(out, configPath, "exclude.0", "*.log"))
|
||||
require.NoError(t, writeConfigSet(out, configPath, "exclude.1", "/cache"))
|
||||
|
||||
code, stdout, stderr := runEntry(t, flagConfig, configPath, "--verbose",
|
||||
cmdSnapshot, cmdCreate, "--dry-run")
|
||||
|
||||
require.Equal(t, 0, code, stderr)
|
||||
assert.Contains(t, stdout, "Excluded "+filepath.Join(sourceDir, "debug.log")+
|
||||
`: matches exclude pattern "*.log".`)
|
||||
assert.Contains(t, stdout, "Excluded "+cacheDir+
|
||||
`: matches exclude pattern "/cache".`)
|
||||
assert.NotContains(t, stdout, filepath.Join(cacheDir, "a"))
|
||||
assert.Contains(t, stdout, "Files: 1 examined, 1 to back up, 0 unchanged.")
|
||||
assert.Contains(t, stdout, "Excluded: 2 entries.")
|
||||
|
||||
entries, err := os.ReadDir(storeDir)
|
||||
require.NoError(t, err)
|
||||
assert.Empty(t, entries, "a dry run writes nothing to the destination")
|
||||
|
||||
ctx := context.Background()
|
||||
db, err := database.New(ctx,
|
||||
filepath.Join(filepath.Dir(configPath), "index.sqlite"))
|
||||
require.NoError(t, err)
|
||||
|
||||
defer func() { require.NoError(t, db.Close()) }()
|
||||
|
||||
repos := database.NewRepositories(db)
|
||||
|
||||
snapshots, err := repos.Snapshots.ListRecent(ctx, 1)
|
||||
require.NoError(t, err)
|
||||
assert.Empty(t, snapshots, "a dry run records no snapshot")
|
||||
|
||||
binding, err := repos.LocalMeta.Get(ctx, database.LocalMetaKeyStorageURL)
|
||||
require.NoError(t, err)
|
||||
assert.Empty(t, binding, "a dry run does not bind the local index")
|
||||
}
|
||||
|
||||
// TestEntrySnapshotCreateDryRunRefusesPrune checks that --dry-run with
|
||||
// --prune fails before anything runs.
|
||||
//
|
||||
//nolint:paralleltest // replaces os.Args, os.Stdout, os.Stderr and the xdg globals
|
||||
func TestEntrySnapshotCreateDryRunRefusesPrune(t *testing.T) {
|
||||
configPath, _ := writeBackupConfig(t)
|
||||
|
||||
code, _, stderr := runEntry(t, flagConfig, configPath,
|
||||
cmdSnapshot, cmdCreate, "--dry-run", "--prune")
|
||||
|
||||
assert.NotEqual(t, 0, code)
|
||||
assert.Contains(t, stderr, "--dry-run cannot be used with --prune")
|
||||
}
|
||||
@@ -1,30 +0,0 @@
|
||||
package cli //nolint:testpackage // shares runEntry and the hermetic config helpers
|
||||
|
||||
import (
|
||||
"testing"
|
||||
|
||||
"github.com/stretchr/testify/assert"
|
||||
)
|
||||
|
||||
// TestEntrySnapshotCreateSkipErrorsExitsNonZeroWhenItSkips backs up,
|
||||
// under --skip-errors, a source directory that does not exist, which the
|
||||
// walk skips. The command exits non-zero and reports the backup as
|
||||
// completed, not as a failed snapshot creation. See
|
||||
// https://git.eeqj.de/sneak/vaultik/issues/310.
|
||||
//
|
||||
//nolint:paralleltest // replaces os.Args, os.Stdout, os.Stderr and the xdg globals
|
||||
func TestEntrySnapshotCreateSkipErrorsExitsNonZeroWhenItSkips(t *testing.T) {
|
||||
// writeBackupConfig would create the source directory.
|
||||
configPath := writeHermeticPruneConfig(t, false)
|
||||
|
||||
code, stdout, stderr := runEntry(t,
|
||||
flagConfig, configPath, "--skip-errors", cmdSnapshot, cmdCreate)
|
||||
|
||||
assert.Equal(t, 1, code)
|
||||
assert.Contains(t, stdout,
|
||||
"Files: 1 examined, 0 backed up, 0 unchanged, 1 failed.")
|
||||
assert.NotContains(t, stdout, "Finished successfully.")
|
||||
assert.Contains(t, stderr,
|
||||
"Backup completed, but 1 file(s) could not be read")
|
||||
assert.NotContains(t, stderr, "Snapshot creation failed")
|
||||
}
|
||||
@@ -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
|
||||
|
||||
@@ -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
@@ -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)")
|
||||
|
||||
+24
-42
@@ -99,13 +99,6 @@ on Linux), then /etc/vaultik/config.yml.`,
|
||||
|
||||
// Use the backup functionality from cli package
|
||||
rootFlags := GetRootFlags()
|
||||
opts.ListExcluded = rootFlags.Verbose
|
||||
|
||||
// A dry run writes nothing, so it does not take the lock.
|
||||
mode := mutating
|
||||
if opts.DryRun {
|
||||
mode = readOnly
|
||||
}
|
||||
|
||||
// --cron suppression is wired through v.UI by setupGlobals.
|
||||
return RunOperation(cmd.Context(), AppOptions{
|
||||
@@ -116,11 +109,28 @@ on Linux), then /etc/vaultik/config.yml.`,
|
||||
Cron: opts.Cron,
|
||||
Quiet: rootFlags.Quiet,
|
||||
},
|
||||
Mode: mode,
|
||||
Mode: mutating,
|
||||
}, func(v *vaultik.Vaultik) error {
|
||||
return v.CreateSnapshot(opts)
|
||||
}, func(err error) {
|
||||
reportSnapshotCreateFailure(opts.DryRun, err)
|
||||
if errors.Is(err, vaultik.ErrPostBackupPruneFailed) {
|
||||
log.Info("Post-backup prune failed", "error", err)
|
||||
ReportErrorf("Backup completed, but %v", err)
|
||||
|
||||
return
|
||||
}
|
||||
|
||||
if errors.Is(err, vaultik.ErrFilesUnreadable) ||
|
||||
errors.Is(err, vaultik.ErrSourcePathEmpty) ||
|
||||
errors.Is(err, vaultik.ErrVolumeNotMounted) {
|
||||
log.Info("Backup completed with an error", "error", err)
|
||||
ReportErrorf("Backup completed, but %v", err)
|
||||
|
||||
return
|
||||
}
|
||||
|
||||
log.Info("Snapshot creation failed", "error", err)
|
||||
ReportErrorf("Snapshot creation failed: %v", err)
|
||||
})
|
||||
},
|
||||
}
|
||||
@@ -128,47 +138,19 @@ 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) "+
|
||||
"instead of only the latest")
|
||||
cmd.Flags().BoolVar(&opts.DryRun, "dry-run", false,
|
||||
"Scan the snapshot source paths and print what a backup would store, "+
|
||||
"writing nothing to the local index or the backup destination; "+
|
||||
"with --verbose, also print each excluded entry and the exclude "+
|
||||
"pattern that matched it")
|
||||
|
||||
return cmd
|
||||
}
|
||||
|
||||
// reportSnapshotCreateFailure shows the user the error `snapshot create`
|
||||
// failed with. dryRun says whether it was given --dry-run.
|
||||
func reportSnapshotCreateFailure(dryRun bool, err error) {
|
||||
switch {
|
||||
case dryRun:
|
||||
log.Info("Dry run failed", "error", err)
|
||||
ReportErrorf("Dry run failed: %v", err)
|
||||
case errors.Is(err, vaultik.ErrPostBackupPruneFailed):
|
||||
log.Info("Post-backup prune failed", "error", err)
|
||||
ReportErrorf("Backup completed, but %v", err)
|
||||
case errors.Is(err, vaultik.ErrFilesUnreadable) ||
|
||||
errors.Is(err, vaultik.ErrSourcePathEmpty) ||
|
||||
errors.Is(err, vaultik.ErrVolumeNotMounted):
|
||||
log.Info("Backup completed with an error", "error", err)
|
||||
ReportErrorf("Backup completed, but %v", err)
|
||||
default:
|
||||
log.Info("Snapshot creation failed", "error", err)
|
||||
ReportErrorf("Snapshot creation failed: %v", err)
|
||||
}
|
||||
}
|
||||
|
||||
// newSnapshotListCommand creates the 'snapshot list' subcommand
|
||||
func newSnapshotListCommand() *cobra.Command {
|
||||
var jsonOutput bool
|
||||
|
||||
@@ -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
|
||||
|
||||
@@ -206,7 +206,8 @@ 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.
|
||||
|
||||
@@ -4,8 +4,10 @@ package snapshot
|
||||
import (
|
||||
"os"
|
||||
"path/filepath"
|
||||
"syscall"
|
||||
"testing"
|
||||
|
||||
"github.com/spf13/afero"
|
||||
"github.com/stretchr/testify/assert"
|
||||
"github.com/stretchr/testify/require"
|
||||
)
|
||||
@@ -38,3 +40,36 @@ 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")
|
||||
}
|
||||
+17
-106
@@ -71,10 +71,7 @@ type Scanner struct {
|
||||
// indexAndLockFiles holds the paths of vaultik's own working files,
|
||||
// which the scan treats as excluded (ScannerConfig.IndexAndLockFiles).
|
||||
indexAndLockFiles map[string]struct{}
|
||||
// listExcluded prints each excluded entry and why it is excluded
|
||||
// (DryRun).
|
||||
listExcluded bool
|
||||
progress *ProgressReporter
|
||||
progress *ProgressReporter
|
||||
// skipErrors skips files that cannot be opened or read (logged loudly);
|
||||
// packer, database, encryption, and upload errors still abort the run.
|
||||
skipErrors bool
|
||||
@@ -193,11 +190,6 @@ type ScanResult struct {
|
||||
// itself when it is a directory. It is zero for an empty directory,
|
||||
// such as the mount point of a volume that is not mounted.
|
||||
EntriesFound int
|
||||
|
||||
// EntriesExcluded counts the entries the walk found that an exclude
|
||||
// pattern matches or that are vaultik's own files. An excluded
|
||||
// directory counts once: the walk does not enter it.
|
||||
EntriesExcluded int
|
||||
}
|
||||
|
||||
// NewScanner creates a new scanner instance
|
||||
@@ -368,42 +360,6 @@ func (s *Scanner) Scan(
|
||||
return result, nil
|
||||
}
|
||||
|
||||
// DryRun walks path as Scan does and counts what a backup would store,
|
||||
// without storing it. It reads the local index to tell unchanged files
|
||||
// from new and changed ones, and writes nothing to the local index or
|
||||
// the backup destination store. With listExcluded it prints each
|
||||
// excluded entry and the exclude pattern that matched it.
|
||||
func (s *Scanner) DryRun(
|
||||
ctx context.Context, path string, listExcluded bool,
|
||||
) (*ScanResult, error) {
|
||||
s.currentSourcePath = path
|
||||
s.listExcluded = listExcluded
|
||||
result := &ScanResult{
|
||||
StartTime: time.Now().UTC(),
|
||||
}
|
||||
|
||||
knownFiles, err := s.loadDatabaseState(ctx, path)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
|
||||
existingFiles := make(map[string]struct{})
|
||||
|
||||
_, err = s.scanPhase(ctx, path, result, existingFiles, knownFiles)
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("scan phase failed: %w", err)
|
||||
}
|
||||
|
||||
err = s.detectDeletedFiles(ctx, path, existingFiles, result)
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("detecting deleted files: %w", err)
|
||||
}
|
||||
|
||||
result.EndTime = time.Now().UTC()
|
||||
|
||||
return result, nil
|
||||
}
|
||||
|
||||
// GetProgress returns the progress reporter for this scanner, or nil when
|
||||
// progress is off. Scan neither starts nor stops it: the caller does,
|
||||
// once for all the paths it scans, because a second Stop panics.
|
||||
@@ -988,8 +944,12 @@ func (s *Scanner) scanPhase(
|
||||
// or cannot be looked up is neither counted nor reported. For
|
||||
// directories, skip the entire subtree. info is nil when the
|
||||
// walk could not look the entry up.
|
||||
if excluded, walkErr := s.skipExcluded(filePath, path, info, result); excluded {
|
||||
return walkErr
|
||||
if s.shouldExclude(filePath, path) {
|
||||
if info != nil && info.IsDir() {
|
||||
return filepath.SkipDir
|
||||
}
|
||||
|
||||
return nil
|
||||
}
|
||||
|
||||
// The source path is in no directory listing, so its absence is
|
||||
@@ -1056,32 +1016,6 @@ func (s *Scanner) scanPhase(
|
||||
}, nil
|
||||
}
|
||||
|
||||
// skipExcluded reports whether the walk skips filePath, under rootPath,
|
||||
// because it is excluded, and counts it if so. The error is what the walk
|
||||
// function returns for it: filepath.SkipDir for a directory, so the walk
|
||||
// does not enter it, and nil otherwise. info is nil when the walk could
|
||||
// not look the entry up.
|
||||
func (s *Scanner) skipExcluded(
|
||||
filePath, rootPath string, info os.FileInfo, result *ScanResult,
|
||||
) (bool, error) {
|
||||
pattern, excluded := s.excludingPattern(filePath, rootPath)
|
||||
if !excluded {
|
||||
return false, nil
|
||||
}
|
||||
|
||||
result.EntriesExcluded++
|
||||
|
||||
if s.listExcluded {
|
||||
s.printExcluded(filePath, pattern)
|
||||
}
|
||||
|
||||
if info != nil && info.IsDir() {
|
||||
return true, filepath.SkipDir
|
||||
}
|
||||
|
||||
return true, nil
|
||||
}
|
||||
|
||||
// countNonDirectories returns how many of files are not directories.
|
||||
func countNonDirectories(files map[string]*database.File) int64 {
|
||||
var count int64
|
||||
@@ -1504,11 +1438,12 @@ 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, as from the
|
||||
// in-memory test filesystem.
|
||||
// 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.
|
||||
func deviceNumberFromStat(info os.FileInfo) (uint64, bool) {
|
||||
stat, ok := info.Sys().(*syscall.Stat_t)
|
||||
if !ok {
|
||||
if !ok || (stat.Dev == 0 && stat.Ino == 0) {
|
||||
return 0, false
|
||||
}
|
||||
|
||||
@@ -2417,32 +2352,23 @@ func compileExcludePatterns(patterns []string) ([]compiledPattern, error) {
|
||||
// filePath is the full path to the file
|
||||
// rootPath is the root of the backup source directory
|
||||
func (s *Scanner) shouldExclude(filePath, rootPath string) bool {
|
||||
_, excluded := s.excludingPattern(filePath, rootPath)
|
||||
|
||||
return excluded
|
||||
}
|
||||
|
||||
// excludingPattern reports whether shouldExclude excludes filePath and
|
||||
// returns the exclude pattern, as configured, that matches it. The
|
||||
// pattern is "" for one of vaultik's own working files.
|
||||
func (s *Scanner) excludingPattern(filePath, rootPath string) (string, bool) {
|
||||
if _, ok := s.indexAndLockFiles[filePath]; ok {
|
||||
return "", true
|
||||
return true
|
||||
}
|
||||
|
||||
if len(s.compiledExclude) == 0 {
|
||||
return "", false
|
||||
return false
|
||||
}
|
||||
|
||||
// Get the relative path from root
|
||||
relPath, err := filepath.Rel(rootPath, filePath)
|
||||
if err != nil {
|
||||
return "", false
|
||||
return false
|
||||
}
|
||||
|
||||
// Never exclude the root directory itself
|
||||
if relPath == "." {
|
||||
return "", false
|
||||
return false
|
||||
}
|
||||
|
||||
// Normalize path separators
|
||||
@@ -2451,26 +2377,11 @@ func (s *Scanner) excludingPattern(filePath, rootPath string) (string, bool) {
|
||||
// Check each pattern
|
||||
for _, cp := range s.compiledExclude {
|
||||
if cp.matches(relPath) {
|
||||
return cp.original, true
|
||||
return true
|
||||
}
|
||||
}
|
||||
|
||||
return "", false
|
||||
}
|
||||
|
||||
// printExcluded prints that the walk excluded filePath and why: pattern
|
||||
// is the exclude pattern that matched it, "" for one of vaultik's own
|
||||
// working files.
|
||||
func (s *Scanner) printExcluded(filePath, pattern string) {
|
||||
if pattern == "" {
|
||||
s.ui.Infof("Excluded %s: vaultik's own index or lock file.",
|
||||
s.ui.Path(filePath))
|
||||
|
||||
return
|
||||
}
|
||||
|
||||
s.ui.Infof("Excluded %s: matches exclude pattern %q.",
|
||||
s.ui.Path(filePath), pattern)
|
||||
return false
|
||||
}
|
||||
|
||||
// matches reports whether the compiled pattern matches the given
|
||||
|
||||
@@ -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,
|
||||
|
||||
@@ -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)
|
||||
}
|
||||
}
|
||||
@@ -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.
|
||||
|
||||
+26
-13
@@ -56,8 +56,8 @@ 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 +248,24 @@ 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
|
||||
}
|
||||
@@ -276,13 +278,24 @@ 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("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 fmt.Errorf("walking directory: %w", err)
|
||||
return nil, fmt.Errorf("walking directory: %w", err)
|
||||
}
|
||||
|
||||
return nil
|
||||
return partial, nil
|
||||
}
|
||||
|
||||
// Info returns human-readable storage location information.
|
||||
|
||||
@@ -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)
|
||||
}
|
||||
|
||||
@@ -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)
|
||||
}
|
||||
})
|
||||
}
|
||||
|
||||
+36
-14
@@ -8,6 +8,7 @@ import (
|
||||
"fmt"
|
||||
"io"
|
||||
"os"
|
||||
"path/filepath"
|
||||
"strings"
|
||||
"time"
|
||||
|
||||
@@ -23,6 +24,15 @@ 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 {
|
||||
@@ -53,6 +63,19 @@ 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
|
||||
@@ -233,29 +256,28 @@ 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.
|
||||
|
||||
@@ -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
|
||||
@@ -436,6 +412,79 @@ 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
|
||||
|
||||
@@ -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.
|
||||
|
||||
@@ -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
|
||||
|
||||
@@ -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 {
|
||||
|
||||
@@ -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))
|
||||
}
|
||||
|
||||
v.stdoutf("Orphaned (unreferenced): %s (%s)\n",
|
||||
humanize.Comma(int64(*result.OrphanedBlobCount)),
|
||||
ubytes(*result.OrphanedBlobSize))
|
||||
v.stdoutf("Partial uploads: %s (%s)\n",
|
||||
humanize.Comma(int64(result.PartialUploadCount)),
|
||||
ubytes(result.PartialUploadSize))
|
||||
|
||||
if *result.OrphanedBlobCount > 0 {
|
||||
v.stdoutf("\nRun 'vaultik prune' to remove orphaned blobs.\n")
|
||||
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 "))
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
@@ -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 {
|
||||
|
||||
+213
-46
@@ -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
|
||||
}
|
||||
|
||||
result := &PruneBlobsResult{
|
||||
BlobsFound: len(unreferencedBlobs),
|
||||
BlobsTooNew: tooNew,
|
||||
partialUploads, partialTooNew, err := v.findOldPartialUploads()
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
|
||||
v.reportBlobsTooNew(tooNew, opts)
|
||||
result := &PruneBlobsResult{
|
||||
BlobsFound: len(unreferencedBlobs),
|
||||
BlobsTooNew: tooNew,
|
||||
PartialUploadsTooNew: partialTooNew,
|
||||
}
|
||||
|
||||
if len(unreferencedBlobs) == 0 && len(dirsWithoutManifest) == 0 {
|
||||
v.reportTooNew(result, opts)
|
||||
|
||||
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
|
||||
}
|
||||
|
||||
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)
|
||||
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.",
|
||||
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.")
|
||||
}
|
||||
@@ -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 {
|
||||
|
||||
@@ -25,9 +25,13 @@ import (
|
||||
"sneak.berlin/go/vaultik/internal/types"
|
||||
)
|
||||
|
||||
// ErrFilesFailedRestore is returned when --skip-errors skipped files the
|
||||
// restore could not write. Every other file was restored, so the caller
|
||||
// can report it apart from a failed restore.
|
||||
var ErrFilesFailedRestore = errors.New("file(s) failed to restore")
|
||||
|
||||
// Sentinel errors for restore failures.
|
||||
var (
|
||||
errFilesFailedRestore = errors.New("file(s) failed to restore")
|
||||
errPathsNotInSnapshot = errors.New("requested path(s) not in the snapshot")
|
||||
errFilesFailedVerify = errors.New("files failed verification")
|
||||
errDecryptionKeyRequired = errors.New(
|
||||
@@ -201,9 +205,9 @@ func (v *Vaultik) Restore(opts *RestoreOptions) error {
|
||||
}
|
||||
|
||||
// finishRestore prints the restore summary and the post-restore
|
||||
// warnings, runs optional verification, and converts any failed-file
|
||||
// count into an error. Otherwise it returns unmatchedErr, the error for
|
||||
// the requested paths that matched nothing (nil when there are none).
|
||||
// warnings, runs optional verification, and returns the error the
|
||||
// restore ends with: one for the files --skip-errors skipped, one for
|
||||
// unmatchedErr, the requested paths that matched nothing, or nil.
|
||||
func (v *Vaultik) finishRestore(
|
||||
repos *database.Repositories,
|
||||
files []*database.File,
|
||||
@@ -250,11 +254,18 @@ func (v *Vaultik) finishRestore(
|
||||
}
|
||||
}
|
||||
|
||||
if result.FilesFailed > 0 {
|
||||
return fmt.Errorf("%d %w", result.FilesFailed, errFilesFailedRestore)
|
||||
switch {
|
||||
case result.FilesFailed > 0 && unmatchedErr != nil:
|
||||
// A requested path that matched nothing outweighs skipped files:
|
||||
// the error wraps only unmatchedErr, so the command does not exit
|
||||
// as a restore that only skipped files.
|
||||
return fmt.Errorf("%w; %d %s",
|
||||
unmatchedErr, result.FilesFailed, ErrFilesFailedRestore.Error())
|
||||
case result.FilesFailed > 0:
|
||||
return fmt.Errorf("%d %w", result.FilesFailed, ErrFilesFailedRestore)
|
||||
default:
|
||||
return unmatchedErr
|
||||
}
|
||||
|
||||
return unmatchedErr
|
||||
}
|
||||
|
||||
// warnIfOwnershipNotPreserved warns once if some entry restored under
|
||||
|
||||
@@ -80,7 +80,7 @@ func TestRestoreFreesBlobsNoPendingFileNeeds(t *testing.T) {
|
||||
TargetDir: restoreDir,
|
||||
SkipErrors: true,
|
||||
})
|
||||
require.ErrorIs(t, err, errFilesFailedRestore)
|
||||
require.ErrorIs(t, err, ErrFilesFailedRestore)
|
||||
|
||||
requireRestoredFiles(t, fs, restoreDir, originals)
|
||||
assert.LessOrEqualf(t, peak, 1,
|
||||
|
||||
@@ -33,7 +33,6 @@ var (
|
||||
"creating a snapshot needs at least one public key in " +
|
||||
"age_recipients (generate a keypair with: age-keygen)")
|
||||
errKeepNewerThanNeedsPrune = errors.New("--keep-newer-than requires --prune")
|
||||
errDryRunWithPrune = errors.New("--dry-run cannot be used with --prune")
|
||||
)
|
||||
|
||||
// ErrPostBackupPruneFailed wraps a failure of the post-backup prune,
|
||||
@@ -50,8 +49,7 @@ var ErrFilesUnreadable = errors.New("file(s) could not be read")
|
||||
// prune because the scan found nothing in a configured path of a
|
||||
// snapshot, as in the mount point of a volume that is not mounted. The
|
||||
// snapshots are complete and kept, so the caller can report it apart
|
||||
// from a failed backup. A run that also skipped unreadable files
|
||||
// returns ErrFilesUnreadable instead.
|
||||
// from a failed backup.
|
||||
var ErrSourcePathEmpty = errors.New("source path(s) were empty")
|
||||
|
||||
// ErrVolumeNotMounted is returned when --prune skipped the post-backup
|
||||
@@ -60,8 +58,8 @@ var ErrSourcePathEmpty = errors.New("source path(s) were empty")
|
||||
// mounted there is not mounted, the run found no entry in it, or the
|
||||
// directory is no longer backed up. The snapshots are complete and
|
||||
// kept, so the caller can report it apart from a failed backup. A run
|
||||
// that also skipped unreadable files or found a configured path empty
|
||||
// returns ErrFilesUnreadable or ErrSourcePathEmpty instead.
|
||||
// that also found a configured path empty returns ErrSourcePathEmpty
|
||||
// instead.
|
||||
var ErrVolumeNotMounted = errors.New(
|
||||
"mount point(s) an earlier snapshot recorded were not found")
|
||||
|
||||
@@ -78,24 +76,12 @@ type SnapshotCreateOptions struct {
|
||||
KeepNewerThan string
|
||||
SkipErrors bool // Skip file read errors (log them loudly but continue)
|
||||
Snapshots []string // Optional list of snapshot names to process (empty = all)
|
||||
// DryRun scans the snapshot source paths and prints what a backup
|
||||
// would store, writing nothing to the local index or the backup
|
||||
// destination store.
|
||||
DryRun bool
|
||||
// ListExcluded makes a dry run print each excluded entry and the
|
||||
// exclude pattern that matched it. A backup ignores it.
|
||||
ListExcluded bool
|
||||
}
|
||||
|
||||
// Validate fails when DryRun is set with Prune, or when KeepNewerThan is
|
||||
// set without Prune or is not a valid duration. Only the post-backup
|
||||
// prune reads KeepNewerThan, after the backup, so the caller checks it
|
||||
// before starting one.
|
||||
// Validate fails when KeepNewerThan is set without Prune or is not a
|
||||
// valid duration. Only the post-backup prune reads KeepNewerThan, after
|
||||
// the backup, so the caller checks it before starting one.
|
||||
func (opts *SnapshotCreateOptions) Validate() error {
|
||||
if opts.DryRun && opts.Prune {
|
||||
return errDryRunWithPrune
|
||||
}
|
||||
|
||||
if opts.KeepNewerThan == "" {
|
||||
return nil
|
||||
}
|
||||
@@ -120,10 +106,6 @@ func (v *Vaultik) CreateSnapshot(opts *SnapshotCreateOptions) error {
|
||||
return errNoAgeRecipients
|
||||
}
|
||||
|
||||
if opts.DryRun {
|
||||
return v.dryRunSnapshots(opts)
|
||||
}
|
||||
|
||||
overallStartTime := time.Now()
|
||||
|
||||
log.Info("Starting snapshot creation",
|
||||
@@ -260,15 +242,29 @@ func (v *Vaultik) skipPostBackupPrune(
|
||||
if filesUnreadable > 0 {
|
||||
v.UI.Warningf("Skipped the post-backup prune because %d file(s) "+
|
||||
"could not be read; older snapshots are kept.", filesUnreadable)
|
||||
}
|
||||
|
||||
var err error
|
||||
|
||||
switch {
|
||||
case len(emptyPaths) > 0:
|
||||
err = fmt.Errorf("%d %w", len(emptyPaths), ErrSourcePathEmpty)
|
||||
case len(unmountedPaths) > 0:
|
||||
err = fmt.Errorf("%d %w", len(unmountedPaths), ErrVolumeNotMounted)
|
||||
default:
|
||||
return fmt.Errorf("%d %w", filesUnreadable, ErrFilesUnreadable)
|
||||
}
|
||||
|
||||
if len(emptyPaths) > 0 {
|
||||
return fmt.Errorf("%d %w", len(emptyPaths), ErrSourcePathEmpty)
|
||||
// An empty path or a missing volume can mean a whole volume is not
|
||||
// in the backup, which outweighs skipped files: the error wraps only
|
||||
// the former, so the command does not exit as a backup that only
|
||||
// skipped files.
|
||||
if filesUnreadable > 0 {
|
||||
return fmt.Errorf("%w; %d %s",
|
||||
err, filesUnreadable, ErrFilesUnreadable.Error())
|
||||
}
|
||||
|
||||
return fmt.Errorf("%d %w", len(unmountedPaths), ErrVolumeNotMounted)
|
||||
return err
|
||||
}
|
||||
|
||||
// finishCreateSnapshot ends a run whose snapshots are all complete and
|
||||
@@ -319,10 +315,10 @@ 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 {
|
||||
@@ -375,9 +371,6 @@ type snapshotStats struct {
|
||||
// could not be read or listed.
|
||||
totalFilesUnreadable int
|
||||
|
||||
// The entries the scan excluded; an excluded directory counts once.
|
||||
totalEntriesExcluded int
|
||||
|
||||
// The configured paths in which the scan found nothing.
|
||||
emptyPaths []string
|
||||
|
||||
@@ -391,29 +384,6 @@ type snapshotStats struct {
|
||||
blobUncompressedSize int64
|
||||
}
|
||||
|
||||
// add adds the result of scanning the configured path dir to the totals.
|
||||
func (stats *snapshotStats) add(dir string, result *snapshot.ScanResult) {
|
||||
stats.totalFiles += result.FilesScanned
|
||||
stats.totalBytes += result.BytesScanned
|
||||
stats.totalChunks += result.ChunksCreated
|
||||
stats.newChunkSize += result.NewChunkSize
|
||||
stats.totalBlobs += result.BlobsCreated
|
||||
stats.totalFilesSkipped += result.FilesSkipped
|
||||
stats.totalFilesFailed += result.FilesFailed
|
||||
stats.totalFilesUnreadable += result.FilesUnreadable
|
||||
stats.totalBytesSkipped += result.BytesSkipped
|
||||
stats.totalFilesDeleted += result.FilesDeleted
|
||||
stats.totalBytesDeleted += result.BytesDeleted
|
||||
stats.totalBlobsUploaded += result.BlobsUploaded
|
||||
stats.totalBytesUploaded += result.BytesUploaded
|
||||
stats.uploadDuration += result.UploadDuration
|
||||
stats.totalEntriesExcluded += result.EntriesExcluded
|
||||
|
||||
if result.EntriesFound == 0 {
|
||||
stats.emptyPaths = append(stats.emptyPaths, dir)
|
||||
}
|
||||
}
|
||||
|
||||
// createNamedSnapshot creates a single named snapshot and returns the
|
||||
// statistics of its scan.
|
||||
func (v *Vaultik) createNamedSnapshot(
|
||||
@@ -607,7 +577,24 @@ func (v *Vaultik) scanAllDirectories(
|
||||
return nil, fmt.Errorf("failed to scan %s: %w", dir, err)
|
||||
}
|
||||
|
||||
stats.add(dir, result)
|
||||
stats.totalFiles += result.FilesScanned
|
||||
stats.totalBytes += result.BytesScanned
|
||||
stats.totalChunks += result.ChunksCreated
|
||||
stats.newChunkSize += result.NewChunkSize
|
||||
stats.totalBlobs += result.BlobsCreated
|
||||
stats.totalFilesSkipped += result.FilesSkipped
|
||||
stats.totalFilesFailed += result.FilesFailed
|
||||
stats.totalFilesUnreadable += result.FilesUnreadable
|
||||
stats.totalBytesSkipped += result.BytesSkipped
|
||||
stats.totalFilesDeleted += result.FilesDeleted
|
||||
stats.totalBytesDeleted += result.BytesDeleted
|
||||
stats.totalBlobsUploaded += result.BlobsUploaded
|
||||
stats.totalBytesUploaded += result.BytesUploaded
|
||||
stats.uploadDuration += result.UploadDuration
|
||||
|
||||
if result.EntriesFound == 0 {
|
||||
stats.emptyPaths = append(stats.emptyPaths, dir)
|
||||
}
|
||||
|
||||
log.Info("Directory scan complete",
|
||||
"path", dir,
|
||||
|
||||
@@ -1,133 +0,0 @@
|
||||
package vaultik
|
||||
|
||||
import (
|
||||
"fmt"
|
||||
|
||||
"sneak.berlin/go/vaultik/internal/snapshot"
|
||||
)
|
||||
|
||||
// dryRunSnapshots scans the source paths of each snapshot named in
|
||||
// opts, or of every configured one, and prints what a backup would
|
||||
// store. It writes nothing to the local index or the backup destination
|
||||
// store. It first makes the read-only checks a backup makes, so it fails
|
||||
// where a backup would: a local index bound to a different destination,
|
||||
// or a destination that answers it has no marker while the local index
|
||||
// holds snapshots stored there.
|
||||
func (v *Vaultik) dryRunSnapshots(opts *SnapshotCreateOptions) error {
|
||||
err := v.checkStorageBinding()
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
|
||||
err = v.checkDestinationMarker()
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
|
||||
// A backup first drops incomplete snapshots and the file records only
|
||||
// they list (PruneDatabase), so it backs up those files again; the
|
||||
// dry run counts them as unchanged.
|
||||
incomplete, err := v.Repositories.Snapshots.GetIncompleteSnapshots(v.ctx)
|
||||
if err != nil {
|
||||
return fmt.Errorf("getting incomplete snapshots: %w", err)
|
||||
}
|
||||
|
||||
if len(incomplete) > 0 {
|
||||
v.UI.Noticef("The local index holds %s incomplete snapshot(s) from "+
|
||||
"an interrupted backup. The next backup drops them first and may "+
|
||||
"back up more files than this dry run counts.",
|
||||
v.UI.Count(len(incomplete)))
|
||||
}
|
||||
|
||||
snapshotNames, err := v.snapshotNamesToCreate(opts.Snapshots)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
|
||||
for _, snapName := range snapshotNames {
|
||||
err = v.dryRunSnapshot(opts, snapName)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
}
|
||||
|
||||
return nil
|
||||
}
|
||||
|
||||
// dryRunSnapshot scans the source paths of the snapshot named snapName
|
||||
// and prints what a backup of it would store.
|
||||
func (v *Vaultik) dryRunSnapshot(
|
||||
opts *SnapshotCreateOptions, snapName string,
|
||||
) error {
|
||||
resolvedDirs, err := v.resolveSnapshotPaths(snapName)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
|
||||
previousSnapshotID, err := v.previousSnapshotID(snapName)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
|
||||
scanner := v.ScannerFactory(snapshot.ScannerParams{
|
||||
UI: v.UI,
|
||||
Fs: v.Fs,
|
||||
Exclude: v.Config.GetExcludes(snapName),
|
||||
SkipErrors: opts.SkipErrors,
|
||||
PreviousSnapshotID: previousSnapshotID,
|
||||
})
|
||||
|
||||
v.UI.Beginf("Dry run of snapshot %s.", snapName)
|
||||
|
||||
stats := &snapshotStats{}
|
||||
|
||||
for i, dir := range resolvedDirs {
|
||||
v.UI.Beginf("Enumerating snapshot source files in %s (%d of %d).",
|
||||
v.UI.Path(dir), i+1, len(resolvedDirs))
|
||||
|
||||
result, err := scanner.DryRun(v.ctx, dir, opts.ListExcluded)
|
||||
if err != nil {
|
||||
return fmt.Errorf("failed to scan %s: %w", dir, err)
|
||||
}
|
||||
|
||||
stats.add(dir, result)
|
||||
}
|
||||
|
||||
v.printDryRunSummary(snapName, stats)
|
||||
|
||||
return nil
|
||||
}
|
||||
|
||||
// printDryRunSummary prints what a backup of the snapshot named snapName
|
||||
// would store, in the terms of printSnapshotSummary.
|
||||
func (v *Vaultik) printDryRunSummary(snapName string, stats *snapshotStats) {
|
||||
filesToBackUp := stats.totalFiles - stats.totalFilesSkipped -
|
||||
stats.totalFilesFailed
|
||||
|
||||
v.UI.Completef("Dry run of snapshot %s complete; nothing was stored.",
|
||||
snapName)
|
||||
|
||||
filesMsg := fmt.Sprintf("Files: %s examined, %s to back up, %s unchanged",
|
||||
v.UI.Count(stats.totalFiles),
|
||||
v.UI.Count(filesToBackUp),
|
||||
v.UI.Count(stats.totalFilesSkipped))
|
||||
if stats.totalFilesFailed > 0 {
|
||||
filesMsg += fmt.Sprintf(", %s failed", v.UI.Count(stats.totalFilesFailed))
|
||||
}
|
||||
|
||||
if stats.totalFilesDeleted > 0 {
|
||||
filesMsg += fmt.Sprintf(", %s deleted", v.UI.Count(stats.totalFilesDeleted))
|
||||
}
|
||||
|
||||
v.UI.Detailf("%s.", filesMsg)
|
||||
|
||||
dataMsg := fmt.Sprintf("Data: %s total (%s to back up)",
|
||||
v.UI.Size(stats.totalBytes+stats.totalBytesSkipped),
|
||||
v.UI.Size(stats.totalBytes))
|
||||
if stats.totalBytesDeleted > 0 {
|
||||
dataMsg += fmt.Sprintf(", %s deleted", v.UI.Size(stats.totalBytesDeleted))
|
||||
}
|
||||
|
||||
v.UI.Detailf("%s.", dataMsg)
|
||||
v.UI.Detailf("Excluded: %s entries.", v.UI.Count(stats.totalEntriesExcluded))
|
||||
}
|
||||
@@ -1,69 +0,0 @@
|
||||
package vaultik_test
|
||||
|
||||
import (
|
||||
"context"
|
||||
"os"
|
||||
"testing"
|
||||
|
||||
"github.com/stretchr/testify/assert"
|
||||
"github.com/stretchr/testify/require"
|
||||
"sneak.berlin/go/vaultik/internal/vaultik"
|
||||
)
|
||||
|
||||
// dryRunSnapshotName is the newSummaryEnv snapshot the dry run test
|
||||
// backs up and then dry-runs.
|
||||
const dryRunSnapshotName = "first"
|
||||
|
||||
// TestDryRunCountsWhatABackupWouldStore runs a dry run after a backup:
|
||||
// the unchanged files count as unchanged, a rewritten one as to back up,
|
||||
// and the dry run records no snapshot. See
|
||||
// https://git.eeqj.de/sneak/vaultik/issues/436.
|
||||
func TestDryRunCountsWhatABackupWouldStore(t *testing.T) {
|
||||
t.Parallel()
|
||||
|
||||
env := newSummaryEnv(t)
|
||||
env.backUp(t, dryRunSnapshotName, false)
|
||||
|
||||
dryRun := func() string {
|
||||
env.out.Reset()
|
||||
require.NoError(t, env.v.CreateSnapshot(&vaultik.SnapshotCreateOptions{
|
||||
DryRun: true,
|
||||
Snapshots: []string{dryRunSnapshotName},
|
||||
}))
|
||||
|
||||
return env.out.String()
|
||||
}
|
||||
|
||||
assert.Contains(t, dryRun(),
|
||||
"Files: 3 examined, 0 to back up, 3 unchanged.")
|
||||
|
||||
require.NoError(t, os.WriteFile(env.aPath, []byte("rewritten"), 0o600))
|
||||
|
||||
assert.Contains(t, dryRun(),
|
||||
"Files: 3 examined, 1 to back up, 2 unchanged.")
|
||||
|
||||
// localSnapshotID fails unless exactly one snapshot has the name.
|
||||
localSnapshotID(context.Background(), t, env.repos, dryRunSnapshotName)
|
||||
}
|
||||
|
||||
// TestDryRunNamesIncompleteSnapshots checks that a dry run says so when
|
||||
// the local index holds an incomplete snapshot, which the next backup
|
||||
// drops before it scans.
|
||||
func TestDryRunNamesIncompleteSnapshots(t *testing.T) {
|
||||
t.Parallel()
|
||||
|
||||
env := newSummaryEnv(t)
|
||||
env.backUp(t, dryRunSnapshotName, false)
|
||||
|
||||
_, err := env.v.SnapshotManager.CreateSnapshotWithName(
|
||||
context.Background(), testHostname, "split", "v", "g")
|
||||
require.NoError(t, err)
|
||||
|
||||
env.out.Reset()
|
||||
require.NoError(t, env.v.CreateSnapshot(&vaultik.SnapshotCreateOptions{
|
||||
DryRun: true,
|
||||
Snapshots: []string{dryRunSnapshotName},
|
||||
}))
|
||||
assert.Contains(t, env.out.String(),
|
||||
"The local index holds 1 incomplete snapshot(s)")
|
||||
}
|
||||
@@ -176,8 +176,11 @@ func TestBackupThroughSymlinkWhoseTargetIsGoneDoesNotPrune(t *testing.T) {
|
||||
|
||||
// A backup under --skip-errors --prune that both skipped a file it could
|
||||
// not read and found nothing in a configured path names the empty path
|
||||
// too when it skips the prune. See
|
||||
// https://git.eeqj.de/sneak/vaultik/issues/388.
|
||||
// too when it skips the prune. It ends with the empty path's error, which
|
||||
// names the unreadable file too but does not wrap ErrFilesUnreadable, so
|
||||
// the command does not exit as a backup that only skipped files. See
|
||||
// https://git.eeqj.de/sneak/vaultik/issues/388 and
|
||||
// https://git.eeqj.de/sneak/vaultik/issues/439.
|
||||
func TestBackupWithEmptySourcePathAndUnreadableFileNamesBoth(t *testing.T) {
|
||||
log.Initialize(log.Config{})
|
||||
t.Parallel()
|
||||
@@ -207,7 +210,10 @@ func TestBackupWithEmptySourcePathAndUnreadableFileNamesBoth(t *testing.T) {
|
||||
SkipErrors: true,
|
||||
Snapshots: []string{snapshotName},
|
||||
})
|
||||
require.ErrorIs(t, err, vaultik.ErrFilesUnreadable)
|
||||
require.ErrorIs(t, err, vaultik.ErrSourcePathEmpty)
|
||||
require.NotErrorIs(t, err, vaultik.ErrFilesUnreadable)
|
||||
require.EqualError(t, err,
|
||||
"1 source path(s) were empty; 1 file(s) could not be read")
|
||||
assert.Contains(t, env.out.String(),
|
||||
"Skipped the post-backup prune because 1 file(s) could not be read")
|
||||
assert.Contains(t, env.out.String(),
|
||||
|
||||
Reference in new issue
Block a user