(release) Add explicit incomplete snapshot cleanup

Add a dedicated cleanup path for incomplete snapshots instead of letting
retention prune them implicitly. The retention plan now exposes a guarded
form that requires host and delete-count confirmation before removing
.incomplete snapshot directories and their SQL records.

Keep scheduled/manual retention behavior unchanged, add path safety checks,
and cover cleanup success, confirmation failures, max-delete limits, and
unexpected paths in tests.

Refs #10
This commit is contained in:
2026-05-21 03:26:21 +02:00
parent 4c8ed24561
commit d0c23deb72
7 changed files with 329 additions and 2 deletions

View File

@@ -12,7 +12,7 @@ from django.test import TestCase
from pobsync.errors import ConfigError
from pobsync_backend.models import HostConfig, SnapshotRecord
from pobsync_backend.retention import run_sql_retention_apply, run_sql_retention_plan
from pobsync_backend.retention import run_incomplete_cleanup, run_sql_retention_apply, run_sql_retention_plan
class SqlRetentionTests(TestCase):
@@ -152,6 +152,78 @@ class SqlRetentionTests(TestCase):
acquire_lock=False,
)
def test_incomplete_cleanup_deletes_directory_and_record(self) -> None:
with TemporaryDirectory() as tmp:
prefix = Path(tmp) / "home"
host = HostConfig.objects.create(host="web-01", address="web-01.example.test")
incomplete_dir = Path(tmp) / "backups" / host.host / ".incomplete" / "20260519-031500Z__BROKEN01"
incomplete_dir.mkdir(parents=True)
incomplete_dir.joinpath("partial-file").write_text("interrupted\n")
record = SnapshotRecord.objects.create(
host=host,
kind=SnapshotRecord.Kind.INCOMPLETE,
dirname=incomplete_dir.name,
path=str(incomplete_dir),
status="failed",
started_at=datetime(2026, 5, 19, 3, 15, tzinfo=timezone.utc),
)
result = run_incomplete_cleanup(
prefix=prefix,
host=host.host,
yes=True,
max_delete=1,
acquire_lock=False,
)
self.assertFalse(incomplete_dir.exists())
self.assertFalse(SnapshotRecord.objects.filter(pk=record.pk).exists())
self.assertEqual(
result["deleted"],
[{"dirname": incomplete_dir.name, "kind": SnapshotRecord.Kind.INCOMPLETE, "path": str(incomplete_dir)}],
)
self.assertEqual(result["planned_delete_count"], 1)
def test_incomplete_cleanup_respects_max_delete(self) -> None:
host = HostConfig.objects.create(host="web-01", address="web-01.example.test")
SnapshotRecord.objects.create(
host=host,
kind=SnapshotRecord.Kind.INCOMPLETE,
dirname="20260519-031500Z__BROKEN01",
path=f"/backups/{host.host}/.incomplete/20260519-031500Z__BROKEN01",
status="failed",
started_at=datetime(2026, 5, 19, 3, 15, tzinfo=timezone.utc),
)
with self.assertRaisesRegex(ConfigError, "blocked by --max-delete=0"):
run_incomplete_cleanup(
prefix=Path("/tmp/pobsync-test"),
host=host.host,
yes=True,
max_delete=0,
acquire_lock=False,
)
def test_incomplete_cleanup_rejects_unexpected_path(self) -> None:
host = HostConfig.objects.create(host="web-01", address="web-01.example.test")
SnapshotRecord.objects.create(
host=host,
kind=SnapshotRecord.Kind.INCOMPLETE,
dirname="20260519-031500Z__BROKEN01",
path=f"/backups/{host.host}/scheduled/20260519-031500Z__BROKEN01",
status="failed",
started_at=datetime(2026, 5, 19, 3, 15, tzinfo=timezone.utc),
)
with self.assertRaisesRegex(ConfigError, "unexpected incomplete snapshot path"):
run_incomplete_cleanup(
prefix=Path("/tmp/pobsync-test"),
host=host.host,
yes=True,
max_delete=1,
acquire_lock=False,
)
def test_management_command_plans_from_sql(self) -> None:
host = HostConfig.objects.create(
host="web-01",

View File

@@ -1620,6 +1620,68 @@ class ViewTests(TestCase):
self.assertContains(response, "Incomplete Snapshots")
self.assertContains(response, "20260519-031500Z__BROKEN01")
self.assertContains(response, "excluded from retention cleanup")
self.assertContains(response, "Delete incomplete snapshots")
self.assertContains(response, "Type 1 to confirm the current number of incomplete snapshots.")
def test_incomplete_cleanup_deletes_incomplete_snapshot_after_confirmation(self) -> None:
self.client.force_login(self.staff_user)
with TemporaryDirectory() as tmp:
home = Path(tmp) / "home"
host = HostConfig.objects.create(host="web-01", address="web-01.example.test")
incomplete_dir = Path(tmp) / "backups" / host.host / ".incomplete" / "20260519-031500Z__BROKEN01"
incomplete_dir.mkdir(parents=True)
incomplete_dir.joinpath("partial-file").write_text("interrupted\n")
record = SnapshotRecord.objects.create(
host=host,
kind=SnapshotRecord.Kind.INCOMPLETE,
dirname=incomplete_dir.name,
path=str(incomplete_dir),
status="failed",
started_at=datetime(2026, 5, 19, 3, 15, tzinfo=timezone.utc),
)
with override_settings(POBSYNC_HOME=str(home)):
response = self.client.post(
reverse("cleanup_host_incomplete_snapshots", args=[host.host]),
{
"max_delete": "1",
"confirm_host": host.host,
"confirm_delete_count": "1",
},
follow=True,
)
self.assertFalse(incomplete_dir.exists())
self.assertRedirects(response, reverse("host_retention_plan", args=[host.host]))
self.assertContains(response, "Deleted 1 incomplete snapshot(s) for web-01.")
self.assertFalse(SnapshotRecord.objects.filter(pk=record.pk).exists())
def test_incomplete_cleanup_rejects_bad_confirmation(self) -> None:
self.client.force_login(self.staff_user)
host = HostConfig.objects.create(host="web-01", address="web-01.example.test")
SnapshotRecord.objects.create(
host=host,
kind=SnapshotRecord.Kind.INCOMPLETE,
dirname="20260519-031500Z__BROKEN01",
path=f"/backups/{host.host}/.incomplete/20260519-031500Z__BROKEN01",
status="failed",
started_at=datetime(2026, 5, 19, 3, 15, tzinfo=timezone.utc),
)
response = self.client.post(
reverse("cleanup_host_incomplete_snapshots", args=[host.host]),
{
"max_delete": "1",
"confirm_host": "wrong",
"confirm_delete_count": "1",
},
follow=True,
)
self.assertRedirects(response, reverse("host_retention_plan", args=[host.host]))
self.assertContains(response, "Incomplete cleanup confirmation is invalid.")
self.assertEqual(SnapshotRecord.objects.filter(kind=SnapshotRecord.Kind.INCOMPLETE).count(), 1)
def test_host_detail_surfaces_retention_warnings(self) -> None:
self.client.force_login(self.staff_user)