mirror of
https://github.com/kevinveenbirkenbach/docker-volume-backup.git
synced 2026-10-26 16:02:08 +00:00
Compare commits
15
Commits
v7.0.0
..
b43177f0e7
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
b43177f0e7 | ||
|
|
0735e5fa7b | ||
|
|
389b418f42 | ||
|
|
948b8347f4 | ||
|
|
f824fabea1 | ||
|
|
07d819cb41 | ||
|
|
022b096617 | ||
|
|
161db213cb | ||
|
|
9d4cc24a59 | ||
|
|
5bf6bc2afe | ||
|
|
4b47ceab30 | ||
|
|
a139f0faa1 | ||
|
|
b6ed45770b | ||
|
|
44b1f16f7c | ||
|
|
7f51748486 |
No files matched your search
@@ -1,5 +1,68 @@
|
|||||||
# Changelog
|
# Changelog
|
||||||
|
|
||||||
|
## [7.1.2] - 2026-10-18
|
||||||
|
|
||||||
|
Fixed:
|
||||||
|
|
||||||
|
- Backup: *--snapshot zfs* found no snapshot inside a container; now mounts it
|
||||||
|
- Tests: e2e zfs pool now sits on a loop device; a file vdev never worked
|
||||||
|
|
||||||
|
Upgrade notes:
|
||||||
|
|
||||||
|
- Backup: zfs snapshots mount at *.baudolo-TAG* in the subject, not *.zfs*
|
||||||
|
- Image: first ghcr image since 3.1.2; the 4.0.0 to 7.1.1 notes apply
|
||||||
|
|
||||||
|
## [7.1.1] - 2026-10-17
|
||||||
|
|
||||||
|
Fixed:
|
||||||
|
|
||||||
|
- Tests: e2e MariaDB probe ran root passwordless and timed out at random
|
||||||
|
- Tests: probe now logs in with the root password, skips the temp server
|
||||||
|
- Tests: anonymous-preemption bootstrap now uses the root password too
|
||||||
|
|
||||||
|
Upgrade notes:
|
||||||
|
|
||||||
|
- 7.1.0 never reached stable: its CI failed, no image was published
|
||||||
|
- 7.1.1 is the first published -aHAX build; 7.1.0 upgrade notes apply
|
||||||
|
|
||||||
|
## [7.1.0] - 2026-10-17
|
||||||
|
|
||||||
|
Fixed:
|
||||||
|
|
||||||
|
- Backup: rsync -a stored no xattrs, ACLs or hardlinks; now -aHAX
|
||||||
|
- Restore: restore_volume_files had the same gap; now -aHAX too
|
||||||
|
- An OpenCloud volume lost its storage metadata through a DR drill
|
||||||
|
|
||||||
|
Upgrade notes:
|
||||||
|
|
||||||
|
- First backup re-copies every attribute-carrying volume once in full
|
||||||
|
- A destination without xattr support now fails the backup run outright
|
||||||
|
- exFAT, xattr-less NFS and object-storage FUSE mounts must move first
|
||||||
|
|
||||||
|
## [7.0.2] - 2026-09-23
|
||||||
|
|
||||||
|
* Backup: failed live pre-copy no longer aborts when a stopped copy follows
|
||||||
|
* Backup: stopped --checksum copy replaces pre-copy hit by live writer (rc 23)
|
||||||
|
* Backup: failing sole live copy or failing stopped copy still fails the run
|
||||||
|
* Tests: e2e live writer shrinking files mid-read reproduces the rsync failure
|
||||||
|
|
||||||
|
## [7.0.1] - 2026-08-18
|
||||||
|
|
||||||
|
- Restore: *--empty* no longer aborts on a database that carries an extension.
|
||||||
|
The pre-clean picked its candidates by owner, on the stated assumption that
|
||||||
|
extension members are superuser-owned and would therefore never be selected.
|
||||||
|
That holds only when a superuser installed the extension: a role that
|
||||||
|
installs one itself owns its functions, so they were listed for a one-by-one
|
||||||
|
*DROP* that postgres refuses — *cannot drop function
|
||||||
|
vector_in(cstring,oid,integer) because extension vector requires it*. Under
|
||||||
|
*ON_ERROR_STOP* that ends the whole restore, which is how a generation of an
|
||||||
|
application declaring the *vector* extension became unreplayable. Membership
|
||||||
|
now comes from *pg_depend* rather than from ownership; each branch carries
|
||||||
|
its oid and classid so one *NOT EXISTS* covers all seven instead of seven
|
||||||
|
separate predicates, and the schema branch is guarded too because an
|
||||||
|
extension can own a schema. Skipping the members suffices — the dump's
|
||||||
|
*CREATE EXTENSION IF NOT EXISTS* finds the surviving extension either way.
|
||||||
|
|
||||||
## [7.0.0] - 2026-08-18
|
## [7.0.0] - 2026-08-18
|
||||||
|
|
||||||
Breaking:
|
Breaking:
|
||||||
|
|||||||
+2
-2
@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
|
|||||||
|
|
||||||
[project]
|
[project]
|
||||||
name = "backup-docker-to-local"
|
name = "backup-docker-to-local"
|
||||||
version = "7.0.0"
|
version = "7.1.2"
|
||||||
description = "Backup Docker volumes to local with rsync and optional DB dumps."
|
description = "Backup Docker volumes to local with rsync and optional DB dumps."
|
||||||
readme = "README.md"
|
readme = "README.md"
|
||||||
requires-python = ">=3.9"
|
requires-python = ">=3.9"
|
||||||
@@ -19,7 +19,7 @@ dependencies = [
|
|||||||
[project.optional-dependencies]
|
[project.optional-dependencies]
|
||||||
# Pinned: a ruff minor bump changes which rules fire, and `make test` gates on
|
# Pinned: a ruff minor bump changes which rules fire, and `make test` gates on
|
||||||
# a clean run, so an unpinned lint would fail the suite on an unrelated day.
|
# a clean run, so an unpinned lint would fail the suite on an unrelated day.
|
||||||
lint = ["ruff==0.16.1"]
|
lint = ["ruff==0.16.7"]
|
||||||
|
|
||||||
[project.scripts]
|
[project.scripts]
|
||||||
baudolo = "baudolo.backup.__main__:main"
|
baudolo = "baudolo.backup.__main__:main"
|
||||||
|
|||||||
@@ -23,6 +23,7 @@ from .layout import (
|
|||||||
write_manifest,
|
write_manifest,
|
||||||
)
|
)
|
||||||
from .policy import requires_stop, volume_is_fully_ignored
|
from .policy import requires_stop, volume_is_fully_ignored
|
||||||
|
from .shell import BackupError
|
||||||
from .snapshot import snapshot_source, volume_snapshot
|
from .snapshot import snapshot_source, volume_snapshot
|
||||||
from .volume import backup_volume, inspect_backing
|
from .volume import backup_volume, inspect_backing
|
||||||
|
|
||||||
@@ -125,8 +126,18 @@ def main() -> int:
|
|||||||
copy(authoritative=False)
|
copy(authoritative=False)
|
||||||
continue
|
continue
|
||||||
|
|
||||||
|
if not requires_stop(containers, args.images_no_stop_required):
|
||||||
copy(authoritative=False)
|
copy(authoritative=False)
|
||||||
if requires_stop(containers, args.images_no_stop_required):
|
continue
|
||||||
|
|
||||||
|
try:
|
||||||
|
copy(authoritative=False)
|
||||||
|
except BackupError as error:
|
||||||
|
print(
|
||||||
|
f"WARNING: live pre-copy of volume '{volume_name}' failed; "
|
||||||
|
f"the copy with its containers stopped replaces it.\n{error}",
|
||||||
|
flush=True,
|
||||||
|
)
|
||||||
stoppable = filter_stoppable(containers)
|
stoppable = filter_stoppable(containers)
|
||||||
change_containers_status(stoppable, "stop")
|
change_containers_status(stoppable, "stop")
|
||||||
copy(authoritative=True)
|
copy(authoritative=True)
|
||||||
|
|||||||
@@ -58,27 +58,50 @@ def _resolver(subject: str, root: str) -> Callable[[str], str]:
|
|||||||
return resolve
|
return resolve
|
||||||
|
|
||||||
|
|
||||||
|
def _remove(
|
||||||
|
root: str, commands: list[list[str]], run: Callable[[list[str]], list[str]]
|
||||||
|
) -> None:
|
||||||
|
try:
|
||||||
|
for command in commands:
|
||||||
|
run(command)
|
||||||
|
except BackupError as error:
|
||||||
|
# Raising here would also mask whatever the body raised.
|
||||||
|
print(f"WARNING: {root} could not be removed: {error}", flush=True)
|
||||||
|
|
||||||
|
|
||||||
def _btrfs(
|
def _btrfs(
|
||||||
subject: str, name: str, run: Callable[[list[str]], list[str]]
|
subject: str, name: str, run: Callable[[list[str]], list[str]]
|
||||||
) -> tuple[str, list[str]]:
|
) -> tuple[str, list[list[str]]]:
|
||||||
# The snapshot goes inside the subject, never beside it: the kernel rejects
|
# The snapshot goes inside the subject, never beside it: the kernel rejects
|
||||||
# a snapshot whose destination is on another filesystem, which is exactly
|
# a snapshot whose destination is on another filesystem, which is exactly
|
||||||
# what the parent directory is when the subject is a mountpoint of its own.
|
# what the parent directory is when the subject is a mountpoint of its own.
|
||||||
target = str(Path(os.path.abspath(subject)) / f".{name}") # noqa: PTH100 - see _resolver
|
target = str(Path(os.path.abspath(subject)) / f".{name}") # noqa: PTH100 - see _resolver
|
||||||
run(["btrfs", "subvolume", "snapshot", "-r", subject, target])
|
run(["btrfs", "subvolume", "snapshot", "-r", subject, target])
|
||||||
return target, ["btrfs", "subvolume", "delete", target]
|
return target, [["btrfs", "subvolume", "delete", target]]
|
||||||
|
|
||||||
|
|
||||||
def _zfs(
|
def _zfs(
|
||||||
subject: str, name: str, run: Callable[[list[str]], list[str]]
|
subject: str, name: str, run: Callable[[list[str]], list[str]]
|
||||||
) -> tuple[str, list[str]]:
|
) -> tuple[str, list[list[str]]]:
|
||||||
output = run(["zfs", "list", "-H", "-o", "name", subject])
|
output = run(["zfs", "list", "-H", "-o", "name", subject])
|
||||||
dataset = (output[0] if output else "").strip()
|
dataset = (output[0] if output else "").strip()
|
||||||
if not dataset:
|
if not dataset:
|
||||||
raise SnapshotError(f"no zfs dataset is mounted at {subject}")
|
raise SnapshotError(f"no zfs dataset is mounted at {subject}")
|
||||||
run(["zfs", "snapshot", f"{dataset}@{name}"])
|
snapshot = f"{dataset}@{name}"
|
||||||
root = str(Path(subject) / ".zfs" / "snapshot" / name)
|
# Exception: mounted here rather than read through .zfs/snapshot, which the
|
||||||
return root, ["zfs", "destroy", f"{dataset}@{name}"]
|
# kernel automounts via a usermode helper in the host's mount namespace,
|
||||||
|
# so a containerised run never sees it.
|
||||||
|
root = str(Path(os.path.abspath(subject)) / f".{name}") # noqa: PTH100 - see _resolver
|
||||||
|
run(["zfs", "snapshot", snapshot])
|
||||||
|
remove = [["zfs", "destroy", snapshot]]
|
||||||
|
try:
|
||||||
|
run(["mkdir", root])
|
||||||
|
remove.insert(0, ["rmdir", root])
|
||||||
|
run(["mount", "-t", "zfs", snapshot, root])
|
||||||
|
except BaseException:
|
||||||
|
_remove(root, remove, run)
|
||||||
|
raise
|
||||||
|
return root, [["umount", root], *remove]
|
||||||
|
|
||||||
|
|
||||||
_CREATE = {"btrfs": _btrfs, "zfs": _zfs}
|
_CREATE = {"btrfs": _btrfs, "zfs": _zfs}
|
||||||
@@ -169,8 +192,4 @@ def volume_snapshot(
|
|||||||
try:
|
try:
|
||||||
yield _resolver(subject, root)
|
yield _resolver(subject, root)
|
||||||
finally:
|
finally:
|
||||||
try:
|
_remove(root, remove, run)
|
||||||
run(remove)
|
|
||||||
except BackupError as error:
|
|
||||||
# Raising here would also mask whatever the body raised.
|
|
||||||
print(f"WARNING: {root} could not be removed: {error}", flush=True)
|
|
||||||
@@ -75,7 +75,7 @@ def backup_volume(
|
|||||||
pathlib.Path(dest).mkdir(parents=True, exist_ok=True)
|
pathlib.Path(dest).mkdir(parents=True, exist_ok=True)
|
||||||
|
|
||||||
last = get_last_backup_dir(versions_dir, volume_name, dest)
|
last = get_last_backup_dir(versions_dir, volume_name, dest)
|
||||||
cmd = ["rsync", "-aP", "--no-D", "--delete", "--delete-excluded"]
|
cmd = ["rsync", "-aHAX", "-P", "--no-D", "--delete", "--delete-excluded"]
|
||||||
if authoritative:
|
if authoritative:
|
||||||
cmd.append("--checksum")
|
cmd.append("--checksum")
|
||||||
if last:
|
if last:
|
||||||
|
|||||||
@@ -3,8 +3,12 @@
|
|||||||
-- would run every DROP in one transaction and exhaust max_locks_per_transaction on
|
-- would run every DROP in one transaction and exhaust max_locks_per_transaction on
|
||||||
-- large schemas (e.g. gitlab). Also drops user-owned non-public schemas so a dump
|
-- large schemas (e.g. gitlab). Also drops user-owned non-public schemas so a dump
|
||||||
-- that CREATE SCHEMAs (e.g. discourse's discourse_functions) does not fail on an
|
-- that CREATE SCHEMAs (e.g. discourse's discourse_functions) does not fail on an
|
||||||
-- already-existing schema. Extension members (pg_trgm's set_limit) are
|
-- already-existing schema. Objects belonging to an extension are skipped: postgres
|
||||||
-- superuser-owned; IF EXISTS absorbs the CASCADE fallout.
|
-- refuses to drop them one by one ("cannot drop function vector_in(...) because
|
||||||
|
-- extension vector requires it"), and the dump's CREATE EXTENSION IF NOT EXISTS
|
||||||
|
-- finds the surviving extension either way. Owning them is not enough to make them
|
||||||
|
-- droppable - an extension a role installed itself is owned by that role, so the
|
||||||
|
-- owner filter alone lets pgvector's members through.
|
||||||
SELECT format('DROP %s IF EXISTS public.%s CASCADE', obj.type, obj.name)
|
SELECT format('DROP %s IF EXISTS public.%s CASCADE', obj.type, obj.name)
|
||||||
FROM (
|
FROM (
|
||||||
SELECT format('%I', c.relname) AS name,
|
SELECT format('%I', c.relname) AS name,
|
||||||
@@ -13,7 +17,8 @@ SELECT format('DROP %s IF EXISTS public.%s CASCADE', obj.type, obj.name)
|
|||||||
WHEN 'm' THEN 'MATERIALIZED VIEW'
|
WHEN 'm' THEN 'MATERIALIZED VIEW'
|
||||||
WHEN 'f' THEN 'FOREIGN TABLE'
|
WHEN 'f' THEN 'FOREIGN TABLE'
|
||||||
ELSE 'TABLE'
|
ELSE 'TABLE'
|
||||||
END AS type
|
END AS type,
|
||||||
|
c.oid AS objid, 'pg_class'::regclass AS classid
|
||||||
FROM pg_class c JOIN pg_namespace n ON n.oid = c.relnamespace
|
FROM pg_class c JOIN pg_namespace n ON n.oid = c.relnamespace
|
||||||
WHERE n.nspname = 'public' AND c.relkind IN ('r', 'p', 'v', 'm', 'f')
|
WHERE n.nspname = 'public' AND c.relkind IN ('r', 'p', 'v', 'm', 'f')
|
||||||
AND pg_get_userbyid(c.relowner) = current_user
|
AND pg_get_userbyid(c.relowner) = current_user
|
||||||
@@ -21,17 +26,20 @@ SELECT format('DROP %s IF EXISTS public.%s CASCADE', obj.type, obj.name)
|
|||||||
-- Overloaded functions share a proname; DROP needs the identity
|
-- Overloaded functions share a proname; DROP needs the identity
|
||||||
-- signature or psql aborts with "function name is not unique".
|
-- signature or psql aborts with "function name is not unique".
|
||||||
SELECT format('%I(%s)', p.proname, pg_get_function_identity_arguments(p.oid)) AS name,
|
SELECT format('%I(%s)', p.proname, pg_get_function_identity_arguments(p.oid)) AS name,
|
||||||
CASE p.prokind WHEN 'p' THEN 'PROCEDURE' ELSE 'FUNCTION' END AS type
|
CASE p.prokind WHEN 'p' THEN 'PROCEDURE' ELSE 'FUNCTION' END AS type,
|
||||||
|
p.oid AS objid, 'pg_proc'::regclass AS classid
|
||||||
FROM pg_proc p JOIN pg_namespace n ON n.oid = p.pronamespace
|
FROM pg_proc p JOIN pg_namespace n ON n.oid = p.pronamespace
|
||||||
WHERE n.nspname = 'public' AND p.prokind IN ('f', 'p', 'w')
|
WHERE n.nspname = 'public' AND p.prokind IN ('f', 'p', 'w')
|
||||||
AND pg_get_userbyid(p.proowner) = current_user
|
AND pg_get_userbyid(p.proowner) = current_user
|
||||||
UNION ALL
|
UNION ALL
|
||||||
SELECT format('%I', c.relname) AS name, 'SEQUENCE' AS type
|
SELECT format('%I', c.relname) AS name, 'SEQUENCE' AS type,
|
||||||
|
c.oid AS objid, 'pg_class'::regclass AS classid
|
||||||
FROM pg_class c JOIN pg_namespace n ON n.oid = c.relnamespace
|
FROM pg_class c JOIN pg_namespace n ON n.oid = c.relnamespace
|
||||||
WHERE n.nspname = 'public' AND c.relkind = 'S'
|
WHERE n.nspname = 'public' AND c.relkind = 'S'
|
||||||
AND pg_get_userbyid(c.relowner) = current_user
|
AND pg_get_userbyid(c.relowner) = current_user
|
||||||
UNION ALL
|
UNION ALL
|
||||||
SELECT format('%I', t.typname) AS name, 'TYPE' AS type
|
SELECT format('%I', t.typname) AS name, 'TYPE' AS type,
|
||||||
|
t.oid AS objid, 'pg_type'::regclass AS classid
|
||||||
FROM pg_type t JOIN pg_namespace n ON n.oid = t.typnamespace
|
FROM pg_type t JOIN pg_namespace n ON n.oid = t.typnamespace
|
||||||
WHERE n.nspname = 'public'
|
WHERE n.nspname = 'public'
|
||||||
AND pg_get_userbyid(t.typowner) = current_user
|
AND pg_get_userbyid(t.typowner) = current_user
|
||||||
@@ -40,25 +48,36 @@ SELECT format('DROP %s IF EXISTS public.%s CASCADE', obj.type, obj.name)
|
|||||||
SELECT 1 FROM pg_class c2
|
SELECT 1 FROM pg_class c2
|
||||||
WHERE c2.oid = t.typrelid AND c2.relkind = 'c')))
|
WHERE c2.oid = t.typrelid AND c2.relkind = 'c')))
|
||||||
UNION ALL
|
UNION ALL
|
||||||
SELECT format('%I', col.collname) AS name, 'COLLATION' AS type
|
SELECT format('%I', col.collname) AS name, 'COLLATION' AS type,
|
||||||
|
col.oid AS objid, 'pg_collation'::regclass AS classid
|
||||||
FROM pg_collation col JOIN pg_namespace n ON n.oid = col.collnamespace
|
FROM pg_collation col JOIN pg_namespace n ON n.oid = col.collnamespace
|
||||||
WHERE n.nspname = 'public'
|
WHERE n.nspname = 'public'
|
||||||
AND pg_get_userbyid(col.collowner) = current_user
|
AND pg_get_userbyid(col.collowner) = current_user
|
||||||
UNION ALL
|
UNION ALL
|
||||||
SELECT format('%I', ts.cfgname) AS name, 'TEXT SEARCH CONFIGURATION' AS type
|
SELECT format('%I', ts.cfgname) AS name, 'TEXT SEARCH CONFIGURATION' AS type,
|
||||||
|
ts.oid AS objid, 'pg_ts_config'::regclass AS classid
|
||||||
FROM pg_ts_config ts JOIN pg_namespace n ON n.oid = ts.cfgnamespace
|
FROM pg_ts_config ts JOIN pg_namespace n ON n.oid = ts.cfgnamespace
|
||||||
WHERE n.nspname = 'public'
|
WHERE n.nspname = 'public'
|
||||||
AND pg_get_userbyid(ts.cfgowner) = current_user
|
AND pg_get_userbyid(ts.cfgowner) = current_user
|
||||||
UNION ALL
|
UNION ALL
|
||||||
SELECT format('%I', d.dictname) AS name, 'TEXT SEARCH DICTIONARY' AS type
|
SELECT format('%I', d.dictname) AS name, 'TEXT SEARCH DICTIONARY' AS type,
|
||||||
|
d.oid AS objid, 'pg_ts_dict'::regclass AS classid
|
||||||
FROM pg_ts_dict d JOIN pg_namespace n ON n.oid = d.dictnamespace
|
FROM pg_ts_dict d JOIN pg_namespace n ON n.oid = d.dictnamespace
|
||||||
WHERE n.nspname = 'public'
|
WHERE n.nspname = 'public'
|
||||||
AND pg_get_userbyid(d.dictowner) = current_user
|
AND pg_get_userbyid(d.dictowner) = current_user
|
||||||
) obj
|
) obj
|
||||||
|
WHERE NOT EXISTS (
|
||||||
|
SELECT 1 FROM pg_depend dep
|
||||||
|
WHERE dep.classid = obj.classid AND dep.objid = obj.objid
|
||||||
|
AND dep.deptype = 'e')
|
||||||
UNION ALL
|
UNION ALL
|
||||||
SELECT format('DROP SCHEMA IF EXISTS %I CASCADE', n.nspname)
|
SELECT format('DROP SCHEMA IF EXISTS %I CASCADE', n.nspname)
|
||||||
FROM pg_namespace n
|
FROM pg_namespace n
|
||||||
WHERE NOT starts_with(n.nspname, 'pg_')
|
WHERE NOT starts_with(n.nspname, 'pg_')
|
||||||
AND n.nspname NOT IN ('public', 'information_schema')
|
AND n.nspname NOT IN ('public', 'information_schema')
|
||||||
AND pg_get_userbyid(n.nspowner) = current_user
|
AND pg_get_userbyid(n.nspowner) = current_user
|
||||||
|
AND NOT EXISTS (
|
||||||
|
SELECT 1 FROM pg_depend dep
|
||||||
|
WHERE dep.classid = 'pg_namespace'::regclass AND dep.objid = n.oid
|
||||||
|
AND dep.deptype = 'e')
|
||||||
\gexec
|
\gexec
|
||||||
@@ -59,6 +59,6 @@ def restore_volume_files(volume_name: str, backup_files_dir: str) -> int:
|
|||||||
# rsync reads "dir/" as its contents and "dir" as the directory itself.
|
# rsync reads "dir/" as its contents and "dir" as the directory itself.
|
||||||
src = f"{Path(backup_files_dir)}{os.sep}"
|
src = f"{Path(backup_files_dir)}{os.sep}"
|
||||||
dest = f"{Path(mountpoint)}{os.sep}"
|
dest = f"{Path(mountpoint)}{os.sep}"
|
||||||
run(["rsync", "-avv", "--delete", src, dest])
|
run(["rsync", "-aHAX", "-vv", "--delete", src, dest])
|
||||||
print("File restore complete.")
|
print("File restore complete.")
|
||||||
return 0
|
return 0
|
||||||
@@ -25,7 +25,7 @@ def backup_run(
|
|||||||
images_no_stop_required: list[str],
|
images_no_stop_required: list[str],
|
||||||
images_no_backup_required: list[str] | None = None,
|
images_no_backup_required: list[str] | None = None,
|
||||||
only_sql: bool = False,
|
only_sql: bool = False,
|
||||||
) -> None:
|
) -> subprocess.CompletedProcess:
|
||||||
cmd = [
|
cmd = [
|
||||||
"baudolo",
|
"baudolo",
|
||||||
"--compose-dir",
|
"--compose-dir",
|
||||||
@@ -49,7 +49,7 @@ def backup_run(
|
|||||||
cmd += ["--only-sql"]
|
cmd += ["--only-sql"]
|
||||||
|
|
||||||
try:
|
try:
|
||||||
run(cmd, capture=True, check=True)
|
return run(cmd, capture=True, check=True)
|
||||||
except subprocess.CalledProcessError as e:
|
except subprocess.CalledProcessError as e:
|
||||||
print(">>> baudolo failed (exit code:", e.returncode, ")")
|
print(">>> baudolo failed (exit code:", e.returncode, ")")
|
||||||
if e.stdout:
|
if e.stdout:
|
||||||
|
|||||||
@@ -96,12 +96,13 @@ def wait_for_mariadb(
|
|||||||
container: str, *, root_password: str, timeout_s: int = 90
|
container: str, *, root_password: str, timeout_s: int = 90
|
||||||
) -> None:
|
) -> None:
|
||||||
"""
|
"""
|
||||||
Liveness probe for MariaDB.
|
Readiness probe for MariaDB, as root over the socket.
|
||||||
|
|
||||||
IMPORTANT (MariaDB 11):
|
The entrypoint drops root@127.0.0.1, so root is socket-only, and it
|
||||||
Root TCP auth is often restricted (unix_socket auth), so a TCP ping like
|
installs root@localhost without unix_socket auth: a probe without the
|
||||||
`mariadb-admin -uroot -p... -h localhost ping` can fail even though the server is up.
|
password only passes in the init window before the password is set.
|
||||||
We therefore check readiness via a socket-based query.
|
`@@skip_networking` must be 0 so the entrypoint's temporary server,
|
||||||
|
which shuts down right after init, does not count as ready.
|
||||||
"""
|
"""
|
||||||
deadline = time.time() + timeout_s
|
deadline = time.time() + timeout_s
|
||||||
while time.time() < deadline:
|
while time.time() < deadline:
|
||||||
@@ -112,12 +113,15 @@ def wait_for_mariadb(
|
|||||||
container,
|
container,
|
||||||
"sh",
|
"sh",
|
||||||
"-lc",
|
"-lc",
|
||||||
'mariadb -uroot --protocol=socket -e "SELECT 1;"',
|
(
|
||||||
|
f"mariadb -uroot -p{root_password} --protocol=socket "
|
||||||
|
'-N -e "SELECT @@skip_networking;"'
|
||||||
|
),
|
||||||
],
|
],
|
||||||
capture=True,
|
capture=True,
|
||||||
check=False,
|
check=False,
|
||||||
)
|
)
|
||||||
if p.returncode == 0:
|
if p.returncode == 0 and p.stdout.strip() == "0":
|
||||||
return
|
return
|
||||||
time.sleep(1)
|
time.sleep(1)
|
||||||
raise TimeoutError(
|
raise TimeoutError(
|
||||||
|
|||||||
@@ -0,0 +1,110 @@
|
|||||||
|
"""A writer that shrinks files mid-read fails the live pre-copy, not the run."""
|
||||||
|
|
||||||
|
import unittest
|
||||||
|
|
||||||
|
from .helpers import (
|
||||||
|
backup_path,
|
||||||
|
backup_run,
|
||||||
|
cleanup_docker,
|
||||||
|
create_minimal_compose_dir,
|
||||||
|
ensure_empty_dir,
|
||||||
|
latest_version_dir,
|
||||||
|
require_docker,
|
||||||
|
run,
|
||||||
|
unique,
|
||||||
|
wait_for_log,
|
||||||
|
write_databases_csv,
|
||||||
|
)
|
||||||
|
|
||||||
|
CHURN_FILES = 8
|
||||||
|
|
||||||
|
WRITER = f"""
|
||||||
|
trap 'exit 0' TERM
|
||||||
|
echo hello > /data/hello.txt
|
||||||
|
for i in $(seq 1 {CHURN_FILES}); do
|
||||||
|
(while :; do truncate -s 0 /data/churn$i; truncate -s 16M /data/churn$i; done) &
|
||||||
|
done
|
||||||
|
echo ready
|
||||||
|
wait
|
||||||
|
"""
|
||||||
|
|
||||||
|
|
||||||
|
class TestE2EFilesLiveWriterPreCopy(unittest.TestCase):
|
||||||
|
@classmethod
|
||||||
|
def setUpClass(cls) -> None:
|
||||||
|
require_docker()
|
||||||
|
cls.prefix = unique("baudolo-e2e-live-writer")
|
||||||
|
cls.backups_dir = f"/tmp/{cls.prefix}/Backups"
|
||||||
|
ensure_empty_dir(cls.backups_dir)
|
||||||
|
|
||||||
|
cls.compose_dir = create_minimal_compose_dir(f"/tmp/{cls.prefix}")
|
||||||
|
cls.repo_name = cls.prefix
|
||||||
|
|
||||||
|
cls.volume = f"{cls.prefix}-vol"
|
||||||
|
cls.writer = f"{cls.prefix}-writer"
|
||||||
|
cls.containers = [cls.writer]
|
||||||
|
cls.volumes = [cls.volume]
|
||||||
|
|
||||||
|
run(["docker", "volume", "create", cls.volume])
|
||||||
|
run(
|
||||||
|
[
|
||||||
|
"docker",
|
||||||
|
"run",
|
||||||
|
"-d",
|
||||||
|
"--name",
|
||||||
|
cls.writer,
|
||||||
|
"-v",
|
||||||
|
f"{cls.volume}:/data",
|
||||||
|
"alpine:3.20",
|
||||||
|
"sh",
|
||||||
|
"-c",
|
||||||
|
WRITER,
|
||||||
|
]
|
||||||
|
)
|
||||||
|
wait_for_log(cls.writer, "ready")
|
||||||
|
|
||||||
|
cls.databases_csv = f"/tmp/{cls.prefix}/databases.csv"
|
||||||
|
write_databases_csv(cls.databases_csv, [])
|
||||||
|
|
||||||
|
cls.result = backup_run(
|
||||||
|
backups_dir=cls.backups_dir,
|
||||||
|
repo_name=cls.repo_name,
|
||||||
|
compose_dir=cls.compose_dir,
|
||||||
|
databases_csv=cls.databases_csv,
|
||||||
|
database_containers=["dummy-db"],
|
||||||
|
images_no_stop_required=["dummy-image"],
|
||||||
|
)
|
||||||
|
|
||||||
|
cls.hash, cls.version = latest_version_dir(cls.backups_dir, cls.repo_name)
|
||||||
|
|
||||||
|
@classmethod
|
||||||
|
def tearDownClass(cls) -> None:
|
||||||
|
cleanup_docker(containers=cls.containers, volumes=cls.volumes)
|
||||||
|
|
||||||
|
def test_the_live_pre_copy_hit_the_writer(self) -> None:
|
||||||
|
self.assertIn(
|
||||||
|
f"WARNING: live pre-copy of volume '{self.volume}' failed",
|
||||||
|
self.result.stdout,
|
||||||
|
"the writer never shrank a file under rsync, so this run proves nothing",
|
||||||
|
)
|
||||||
|
|
||||||
|
def test_the_stopped_copy_captured_the_volume(self) -> None:
|
||||||
|
files = (
|
||||||
|
backup_path(self.backups_dir, self.repo_name, self.version, self.volume)
|
||||||
|
/ "files"
|
||||||
|
)
|
||||||
|
self.assertEqual((files / "hello.txt").read_text().strip(), "hello")
|
||||||
|
self.assertEqual(
|
||||||
|
sorted(p.name for p in files.glob("churn*")),
|
||||||
|
sorted(f"churn{i}" for i in range(1, CHURN_FILES + 1)),
|
||||||
|
)
|
||||||
|
|
||||||
|
def test_the_writer_runs_again_after_the_backup(self) -> None:
|
||||||
|
state = run(
|
||||||
|
["docker", "inspect", "-f", "{{.State.Running}}", self.writer]
|
||||||
|
).stdout.strip()
|
||||||
|
self.assertEqual(state, "true")
|
||||||
|
|
||||||
|
|
||||||
|
if __name__ == "__main__":
|
||||||
|
unittest.main()
|
||||||
@@ -100,7 +100,10 @@ class TestE2EMariaDBAnonymousPreemption(unittest.TestCase):
|
|||||||
cls.db_container,
|
cls.db_container,
|
||||||
"sh",
|
"sh",
|
||||||
"-lc",
|
"-lc",
|
||||||
f'mariadb -uroot --protocol=socket -e "{bootstrap_sql}"',
|
(
|
||||||
|
f"mariadb -uroot -p{cls.root_password} --protocol=socket "
|
||||||
|
f'-e "{bootstrap_sql}"'
|
||||||
|
),
|
||||||
]
|
]
|
||||||
)
|
)
|
||||||
|
|
||||||
|
|||||||
@@ -24,6 +24,7 @@ from .helpers import (
|
|||||||
# is not unique") and english_stem_nostop reproduces taiga's text search
|
# is not unique") and english_stem_nostop reproduces taiga's text search
|
||||||
# dictionary abort (duplicate pg_ts_dict_dictname_index).
|
# dictionary abort (duplicate pg_ts_dict_dictname_index).
|
||||||
SCENARIO_SQL = (
|
SCENARIO_SQL = (
|
||||||
|
"CREATE EXTENSION pg_trgm;"
|
||||||
"CREATE SCHEMA discourse_functions;"
|
"CREATE SCHEMA discourse_functions;"
|
||||||
"CREATE TABLE discourse_functions.helper (id int);"
|
"CREATE TABLE discourse_functions.helper (id int);"
|
||||||
"INSERT INTO discourse_functions.helper VALUES (1);"
|
"INSERT INTO discourse_functions.helper VALUES (1);"
|
||||||
@@ -166,6 +167,13 @@ class TestE2EPostgresEmptyDropHard(unittest.TestCase):
|
|||||||
)
|
)
|
||||||
self.assertEqual(self._scalar("SELECT public.f(41) + public.f();"), "42")
|
self.assertEqual(self._scalar("SELECT public.f(41) + public.f();"), "42")
|
||||||
|
|
||||||
|
def test_the_extension_survived_the_preclean(self) -> None:
|
||||||
|
self.assertEqual(
|
||||||
|
self._scalar("SELECT count(*) FROM pg_extension WHERE extname='pg_trgm';"),
|
||||||
|
"1",
|
||||||
|
)
|
||||||
|
self.assertEqual(self._scalar("SELECT similarity('abc','abc')::int;"), "1")
|
||||||
|
|
||||||
def test_text_search_dictionary_restored_once(self) -> None:
|
def test_text_search_dictionary_restored_once(self) -> None:
|
||||||
self.assertEqual(
|
self.assertEqual(
|
||||||
self._scalar(
|
self._scalar(
|
||||||
|
|||||||
@@ -36,9 +36,14 @@ ZFS_READY = "{ [ -c /dev/zfs ] || modprobe zfs 2>/dev/null; }; [ -c /dev/zfs ]"
|
|||||||
def mount_script(fstype: str) -> str:
|
def mount_script(fstype: str) -> str:
|
||||||
"""Build a filesystem on a loop device and carve out the snapshot subject."""
|
"""Build a filesystem on a loop device and carve out the snapshot subject."""
|
||||||
if fstype == "zfs":
|
if fstype == "zfs":
|
||||||
|
# Exception: a loop device, not the /img file, because the kernel opens
|
||||||
|
# vdevs from a taskq thread that resolves paths in the host's root.
|
||||||
|
# The pool is kernel-wide, so it is destroyed on exit, but only once
|
||||||
|
# this script created it.
|
||||||
return (
|
return (
|
||||||
f"{PACKAGES} && {ZFS_READY} && truncate -s 400M /img "
|
f"{PACKAGES} && {ZFS_READY} && truncate -s 400M /img && {ATTACH} "
|
||||||
"&& zpool create -m none baudolo /img "
|
'&& zpool create -m none baudolo "$LOOP" '
|
||||||
|
"&& trap 'zpool destroy -f baudolo; losetup -d \"$LOOP\"' EXIT "
|
||||||
"&& zfs create -o mountpoint=/subject/docker baudolo/docker"
|
"&& zfs create -o mountpoint=/subject/docker baudolo/docker"
|
||||||
)
|
)
|
||||||
return (
|
return (
|
||||||
|
|||||||
@@ -0,0 +1,70 @@
|
|||||||
|
"""Contract of app.main's live copy when no snapshot is taken."""
|
||||||
|
|
||||||
|
from __future__ import annotations
|
||||||
|
|
||||||
|
import unittest
|
||||||
|
from unittest import mock
|
||||||
|
|
||||||
|
from baudolo.backup import app
|
||||||
|
from baudolo.backup.shell import BackupError
|
||||||
|
from baudolo.backup.volume import Backing
|
||||||
|
|
||||||
|
from . import BASE_ARGV
|
||||||
|
|
||||||
|
|
||||||
|
def drive(*, stop: bool, fail_live: bool) -> list[str]:
|
||||||
|
events: list[str] = []
|
||||||
|
|
||||||
|
def record(versions_dir, volume_name, volume_dir, *, authoritative, source):
|
||||||
|
events.append("authoritative" if authoritative else "live")
|
||||||
|
if fail_live and not authoritative:
|
||||||
|
raise BackupError("rsync exit code 23")
|
||||||
|
|
||||||
|
with (
|
||||||
|
mock.patch("sys.argv", BASE_ARGV),
|
||||||
|
mock.patch.object(app, "get_machine_id", return_value="machine"),
|
||||||
|
mock.patch.object(app, "create_version_directory", return_value="/gen"),
|
||||||
|
mock.patch.object(app, "create_volume_directory", return_value="/gen/vol"),
|
||||||
|
mock.patch.object(app, "load_databases_df", return_value=None),
|
||||||
|
mock.patch.object(app, "docker_volume_names", return_value=["vol"]),
|
||||||
|
mock.patch.object(app, "containers_using_volume", return_value=["c"]),
|
||||||
|
mock.patch.object(app, "volume_is_fully_ignored", return_value=False),
|
||||||
|
mock.patch.object(app, "backup_dumps_for_volume", return_value=(False, False)),
|
||||||
|
mock.patch.object(
|
||||||
|
app,
|
||||||
|
"inspect_backing",
|
||||||
|
return_value=Backing("/var/lib/docker/volumes/vol/_data"),
|
||||||
|
),
|
||||||
|
mock.patch.object(app, "requires_stop", return_value=stop),
|
||||||
|
mock.patch.object(app, "filter_stoppable", return_value=["c"]),
|
||||||
|
mock.patch.object(
|
||||||
|
app,
|
||||||
|
"change_containers_status",
|
||||||
|
side_effect=lambda containers, status: events.append(status),
|
||||||
|
),
|
||||||
|
mock.patch.object(app, "write_manifest"),
|
||||||
|
mock.patch.object(app, "stamp_directory"),
|
||||||
|
mock.patch.object(app, "handle_docker_compose_services"),
|
||||||
|
mock.patch.object(app, "backup_volume", side_effect=record),
|
||||||
|
):
|
||||||
|
app.main()
|
||||||
|
return events
|
||||||
|
|
||||||
|
|
||||||
|
class TestLivePreCopy(unittest.TestCase):
|
||||||
|
def test_a_failed_pre_copy_is_replaced_by_the_stopped_copy(self) -> None:
|
||||||
|
self.assertEqual(
|
||||||
|
drive(stop=True, fail_live=True),
|
||||||
|
["live", "stop", "authoritative", "start"],
|
||||||
|
)
|
||||||
|
|
||||||
|
def test_a_failed_live_copy_without_a_stop_aborts_the_run(self) -> None:
|
||||||
|
with self.assertRaises(BackupError):
|
||||||
|
drive(stop=False, fail_live=True)
|
||||||
|
|
||||||
|
def test_a_volume_without_a_stop_is_copied_live_once(self) -> None:
|
||||||
|
self.assertEqual(drive(stop=False, fail_live=False), ["live"])
|
||||||
|
|
||||||
|
|
||||||
|
if __name__ == "__main__":
|
||||||
|
unittest.main()
|
||||||
@@ -21,6 +21,14 @@ class Runner:
|
|||||||
return []
|
return []
|
||||||
|
|
||||||
|
|
||||||
|
class Unmountable(Runner):
|
||||||
|
def __call__(self, command: list[str]) -> list[str]:
|
||||||
|
result = super().__call__(command)
|
||||||
|
if command[0] == "mount":
|
||||||
|
raise BackupError("permission denied")
|
||||||
|
return result
|
||||||
|
|
||||||
|
|
||||||
class TestBtrfs(unittest.TestCase):
|
class TestBtrfs(unittest.TestCase):
|
||||||
def test_it_creates_a_read_only_snapshot_inside_the_subject(self) -> None:
|
def test_it_creates_a_read_only_snapshot_inside_the_subject(self) -> None:
|
||||||
run = Runner()
|
run = Runner()
|
||||||
@@ -95,12 +103,55 @@ class TestZfs(unittest.TestCase):
|
|||||||
run.calls[-1], ["zfs", "destroy", "tank/docker@baudolo-20260731"]
|
run.calls[-1], ["zfs", "destroy", "tank/docker@baudolo-20260731"]
|
||||||
)
|
)
|
||||||
|
|
||||||
def test_it_maps_a_volume_path_through_the_dot_zfs_directory(self) -> None:
|
def test_it_mounts_the_snapshot_inside_the_subject(self) -> None:
|
||||||
|
run = self._run()
|
||||||
|
with volume_snapshot("zfs", "/var/lib/docker", "20260731", run=run):
|
||||||
|
pass
|
||||||
|
self.assertIn(
|
||||||
|
[
|
||||||
|
"mount",
|
||||||
|
"-t",
|
||||||
|
"zfs",
|
||||||
|
"tank/docker@baudolo-20260731",
|
||||||
|
"/var/lib/docker/.baudolo-20260731",
|
||||||
|
],
|
||||||
|
run.calls,
|
||||||
|
)
|
||||||
|
|
||||||
|
def test_it_maps_a_volume_path_into_the_mounted_snapshot(self) -> None:
|
||||||
run = self._run()
|
run = self._run()
|
||||||
with volume_snapshot("zfs", "/var/lib/docker", "20260731", run=run) as resolve:
|
with volume_snapshot("zfs", "/var/lib/docker", "20260731", run=run) as resolve:
|
||||||
self.assertEqual(
|
self.assertEqual(
|
||||||
resolve("/var/lib/docker/volumes/postgres_data/_data"),
|
resolve("/var/lib/docker/volumes/postgres_data/_data"),
|
||||||
"/var/lib/docker/.zfs/snapshot/baudolo-20260731/volumes/postgres_data/_data",
|
"/var/lib/docker/.baudolo-20260731/volumes/postgres_data/_data",
|
||||||
|
)
|
||||||
|
|
||||||
|
def test_it_unmounts_before_it_destroys(self) -> None:
|
||||||
|
run = self._run()
|
||||||
|
with volume_snapshot("zfs", "/var/lib/docker", "20260731", run=run):
|
||||||
|
pass
|
||||||
|
self.assertEqual(
|
||||||
|
run.calls[-3:],
|
||||||
|
[
|
||||||
|
["umount", "/var/lib/docker/.baudolo-20260731"],
|
||||||
|
["rmdir", "/var/lib/docker/.baudolo-20260731"],
|
||||||
|
["zfs", "destroy", "tank/docker@baudolo-20260731"],
|
||||||
|
],
|
||||||
|
)
|
||||||
|
|
||||||
|
def test_a_failed_mount_leaves_no_snapshot_behind(self) -> None:
|
||||||
|
run = Unmountable({"zfs list": ["tank/docker"]})
|
||||||
|
with (
|
||||||
|
self.assertRaises(BackupError),
|
||||||
|
volume_snapshot("zfs", "/var/lib/docker", "20260731", run=run),
|
||||||
|
):
|
||||||
|
pass
|
||||||
|
self.assertEqual(
|
||||||
|
run.calls[-2:],
|
||||||
|
[
|
||||||
|
["rmdir", "/var/lib/docker/.baudolo-20260731"],
|
||||||
|
["zfs", "destroy", "tank/docker@baudolo-20260731"],
|
||||||
|
],
|
||||||
)
|
)
|
||||||
|
|
||||||
def test_an_unmounted_dataset_is_an_error(self) -> None:
|
def test_an_unmounted_dataset_is_an_error(self) -> None:
|
||||||
|
|||||||
@@ -46,9 +46,12 @@ class TestBackupVolume(unittest.TestCase):
|
|||||||
def test_it_carries_no_kernel_objects_into_a_generation(self) -> None:
|
def test_it_carries_no_kernel_objects_into_a_generation(self) -> None:
|
||||||
self.assertIn("--no-D", self.copy())
|
self.assertIn("--no-D", self.copy())
|
||||||
|
|
||||||
|
def test_it_stores_the_metadata_a_restore_has_to_give_back(self) -> None:
|
||||||
|
self.assertIn("-aHAX", self.copy())
|
||||||
|
|
||||||
def test_it_keeps_no_twin_of_what_the_second_pass_replaces(self) -> None:
|
def test_it_keeps_no_twin_of_what_the_second_pass_replaces(self) -> None:
|
||||||
command = self.copy(authoritative=True)
|
command = self.copy(authoritative=True)
|
||||||
self.assertEqual(command[:2], ["rsync", "-aP"])
|
self.assertEqual(command[:3], ["rsync", "-aHAX", "-P"])
|
||||||
self.assertNotIn("--backup", command)
|
self.assertNotIn("--backup", command)
|
||||||
|
|
||||||
def test_it_creates_the_destination(self) -> None:
|
def test_it_creates_the_destination(self) -> None:
|
||||||
|
|||||||
Reference in new issue
Block a user