refactor: inject config sources into scheduled backups

Introduce a ConfigSource interface so scheduled backups no longer need
to load host configuration directly from runtime YAML. Add a Django-backed
config source for SQL-driven backup runs, keep file-based config as the
CLI default, and make scheduled prune execution actually apply retention
after successful runs.
This commit is contained in:
2026-05-19 04:57:10 +02:00
parent 18082496e4
commit bb44f8a09c
9 changed files with 216 additions and 13 deletions

View File

@@ -145,6 +145,8 @@ Run a backup through Django while still using the existing pobsync engine:
python3 manage.py run_pobsync_backup <host> --prefix /opt/pobsync --prune python3 manage.py run_pobsync_backup <host> --prefix /opt/pobsync --prune
``` ```
The Django backup command reads config from SQL directly. Runtime YAML export is kept as a compatibility tool for older CLI flows and retention planning during the transition.
Export database configs to the runtime YAML files consumed by the current engine: Export database configs to the runtime YAML files consumed by the current engine:
``` ```
@@ -193,8 +195,8 @@ The MariaDB profile is optional. SQLite remains the default because it is enough
Recommended next steps: Recommended next steps:
- Move config reading/writing behind a repository interface that can use YAML or Django models. - Continue moving config reading/writing behind repository interfaces so YAML export can eventually disappear.
- Record `run-scheduled` results into `BackupRun`. - Record more engine-side run details into `BackupRun` and `SnapshotRecord`.
- Treat SQL as the source of truth and export YAML only as a compatibility layer for the current engine. - Treat SQL as the source of truth and export YAML only as a compatibility layer for the current engine.
- Run schedules from Django/Docker instead of writing host cron files. - Run schedules from Django/Docker instead of writing host cron files.
- Add a snapshot discovery command that syncs existing snapshot metadata into `SnapshotRecord`. - Add a snapshot discovery command that syncs existing snapshot metadata into `SnapshotRecord`.

View File

@@ -3,8 +3,7 @@ from __future__ import annotations
from pathlib import Path from pathlib import Path
from typing import Any from typing import Any
from ..config.load import load_global_config, load_host_config from ..config.source import ConfigSource, FileConfigSource
from ..config.merge import build_effective_config
from ..errors import ConfigError from ..errors import ConfigError
from ..lock import acquire_host_lock from ..lock import acquire_host_lock
from ..paths import PobsyncPaths from ..paths import PobsyncPaths
@@ -81,15 +80,21 @@ def _base_meta_from_path(base_dir: Path | None, link_dest: str | None) -> dict[s
} }
def run_scheduled(prefix: Path, host: str, dry_run: bool, prune: bool = False, prune_max_delete: int | None = None, prune_protect_bases: bool = False, ) -> dict[str, Any]: def run_scheduled(
prefix: Path,
host: str,
dry_run: bool,
prune: bool = False,
prune_max_delete: int | None = None,
prune_protect_bases: bool = False,
config_source: ConfigSource | None = None,
) -> dict[str, Any]:
host = sanitize_host(host) host = sanitize_host(host)
paths = PobsyncPaths(home=prefix) paths = PobsyncPaths(home=prefix)
# Load and merge config source = config_source or FileConfigSource(prefix=paths.home)
global_cfg = load_global_config(paths.global_config_path) cfg = source.effective_config_for_host(host)
host_cfg = load_host_config(paths.hosts_dir / f"{host}.yaml")
cfg = build_effective_config(global_cfg, host_cfg)
backup_root = cfg.get("backup_root") backup_root = cfg.get("backup_root")
if not isinstance(backup_root, str) or not backup_root.startswith("/"): if not isinstance(backup_root, str) or not backup_root.startswith("/"):
@@ -259,6 +264,20 @@ def run_scheduled(prefix: Path, host: str, dry_run: bool, prune: bool = False, p
final_dir = dirs.scheduled / snap_name final_dir = dirs.scheduled / snap_name
incomplete_dir.rename(final_dir) incomplete_dir.rename(final_dir)
prune_result = None
if prune:
from .retention_apply import run_retention_apply
prune_result = run_retention_apply(
prefix=paths.home,
host=host,
kind="scheduled",
protect_bases=bool(prune_protect_bases),
yes=True,
max_delete=10 if prune_max_delete is None else int(prune_max_delete),
acquire_lock=False,
)
return { return {
"ok": True, "ok": True,
"dry_run": False, "dry_run": False,
@@ -266,5 +285,5 @@ def run_scheduled(prefix: Path, host: str, dry_run: bool, prune: bool = False, p
"snapshot": str(final_dir), "snapshot": str(final_dir),
"base": str(base_dir) if base_dir else None, "base": str(base_dir) if base_dir else None,
"rsync": {"exit_code": result.exit_code}, "rsync": {"exit_code": result.exit_code},
"prune": prune_result,
} }

View File

@@ -0,0 +1,22 @@
from __future__ import annotations
from pathlib import Path
from typing import Any, Protocol
from .load import load_global_config, load_host_config
from .merge import build_effective_config
class ConfigSource(Protocol):
def effective_config_for_host(self, host: str) -> dict[str, Any]:
"""Return the fully merged effective config for a host."""
class FileConfigSource:
def __init__(self, prefix: Path) -> None:
self.prefix = prefix
def effective_config_for_host(self, host: str) -> dict[str, Any]:
global_cfg = load_global_config(self.prefix / "config" / "global.yaml")
host_cfg = load_host_config(self.prefix / "config" / "hosts" / f"{host}.yaml")
return build_effective_config(global_cfg, host_cfg)

View File

@@ -35,6 +35,6 @@ class SnapshotRecordAdmin(admin.ModelAdmin):
@admin.register(ScheduleConfig) @admin.register(ScheduleConfig)
class ScheduleConfigAdmin(admin.ModelAdmin): class ScheduleConfigAdmin(admin.ModelAdmin):
list_display = ("host", "cron_expr", "enabled", "prune", "updated_at") list_display = ("host", "cron_expr", "enabled", "prune", "last_status", "last_started_at", "updated_at")
list_filter = ("enabled", "prune") list_filter = ("enabled", "prune", "last_status")
search_fields = ("host__host", "cron_expr") search_fields = ("host__host", "cron_expr")

View File

@@ -31,6 +31,22 @@ def _host_yaml_data(host_config: HostConfig) -> dict[str, Any]:
return validate_dict(data, HOST_SCHEMA, path="host") return validate_dict(data, HOST_SCHEMA, path="host")
def global_config_data(name: str = "default") -> dict[str, Any]:
try:
global_config = GlobalConfig.objects.get(name=name)
except ObjectDoesNotExist as exc:
raise ConfigRepositoryError(f"Missing GlobalConfig {name!r}") from exc
return _global_yaml_data(global_config)
def host_config_data(host: str) -> dict[str, Any]:
try:
host_config = HostConfig.objects.get(host=host, enabled=True)
except ObjectDoesNotExist as exc:
raise ConfigRepositoryError(f"Missing enabled HostConfig {host!r}") from exc
return _host_yaml_data(host_config)
def export_global_config(prefix: Path, name: str = "default") -> Path: def export_global_config(prefix: Path, name: str = "default") -> Path:
try: try:
global_config = GlobalConfig.objects.get(name=name) global_config = GlobalConfig.objects.get(name=name)

View File

@@ -0,0 +1,12 @@
from __future__ import annotations
from typing import Any
from pobsync.config.merge import build_effective_config
from .config_repository import global_config_data, host_config_data
class DjangoConfigSource:
def effective_config_for_host(self, host: str) -> dict[str, Any]:
return build_effective_config(global_config_data(), host_config_data(host))

View File

@@ -10,6 +10,7 @@ from django.utils import timezone
from pobsync.commands.run_scheduled import run_scheduled from pobsync.commands.run_scheduled import run_scheduled
from pobsync.paths import PobsyncPaths from pobsync.paths import PobsyncPaths
from pobsync_backend.config_repository import export_runtime_configs from pobsync_backend.config_repository import export_runtime_configs
from pobsync_backend.config_source import DjangoConfigSource
from pobsync_backend.models import BackupRun, HostConfig from pobsync_backend.models import BackupRun, HostConfig
@@ -32,6 +33,9 @@ class Command(BaseCommand):
except HostConfig.DoesNotExist as exc: except HostConfig.DoesNotExist as exc:
raise CommandError(f"Missing enabled HostConfig {host_name!r}") from exc raise CommandError(f"Missing enabled HostConfig {host_name!r}") from exc
# Compatibility bridge: retention planning still reads runtime YAML.
# The backup run itself receives config directly from Django.
if options["prune"]:
export_runtime_configs(prefix=paths.home, host=host.host) export_runtime_configs(prefix=paths.home, host=host.host)
run = BackupRun.objects.create( run = BackupRun.objects.create(
@@ -49,6 +53,7 @@ class Command(BaseCommand):
prune=bool(options["prune"]), prune=bool(options["prune"]),
prune_max_delete=int(options["prune_max_delete"]), prune_max_delete=int(options["prune_max_delete"]),
prune_protect_bases=bool(options["prune_protect_bases"]), prune_protect_bases=bool(options["prune_protect_bases"]),
config_source=DjangoConfigSource(),
) )
except Exception as exc: except Exception as exc:
run.status = BackupRun.Status.FAILED run.status = BackupRun.Status.FAILED

View File

@@ -0,0 +1,48 @@
from __future__ import annotations
from django.test import TestCase
from pobsync_backend.config_source import DjangoConfigSource
from pobsync_backend.models import GlobalConfig, HostConfig
class DjangoConfigSourceTests(TestCase):
def test_returns_effective_config_from_database(self) -> None:
GlobalConfig.objects.create(
name="default",
backup_root="/backups",
pobsync_home="/opt/pobsync",
data={
"backup_root": "/ignored",
"pobsync_home": "/ignored",
"ssh": {"user": "root", "port": 22, "options": []},
"rsync": {
"binary": "rsync",
"args": ["--archive"],
"timeout_seconds": 0,
"bwlimit_kbps": 0,
"extra_args": ["--numeric-ids"],
},
"defaults": {"source_root": "/", "destination_subdir": ""},
"excludes_default": ["/proc/***"],
"retention_defaults": {"daily": 7, "weekly": 4, "monthly": 3, "yearly": 1},
},
)
HostConfig.objects.create(
host="web-01",
address="web-01.example.test",
config={
"retention": {"daily": 7, "weekly": 4, "monthly": 3, "yearly": 1},
"excludes_add": ["/tmp/***"],
"includes": [],
"rsync": {"extra_args": ["--delete"]},
},
)
cfg = DjangoConfigSource().effective_config_for_host("web-01")
self.assertEqual(cfg["backup_root"], "/backups")
self.assertEqual(cfg["host"], "web-01")
self.assertEqual(cfg["address"], "web-01.example.test")
self.assertEqual(cfg["excludes_effective"], ["/proc/***", "/tmp/***"])
self.assertEqual(cfg["rsync"]["args_effective"], ["--archive", "--numeric-ids", "--delete"])

View File

@@ -0,0 +1,79 @@
from __future__ import annotations
from pathlib import Path
from tempfile import TemporaryDirectory
from unittest.mock import patch
from django.test import SimpleTestCase
from pobsync.commands.run_scheduled import run_scheduled
from pobsync.rsync import RsyncResult
class FakeConfigSource:
def __init__(self, backup_root: str = "/tmp/pobsync-test-backups") -> None:
self.backup_root = backup_root
def effective_config_for_host(self, host: str) -> dict:
return {
"backup_root": self.backup_root,
"host": host,
"address": "example.test",
"ssh": {"user": "root", "port": 22, "options": []},
"rsync": {
"binary": "rsync",
"args_effective": ["--archive"],
"timeout_seconds": 0,
"bwlimit_kbps": 0,
},
"source_root": "/",
"includes": [],
"excludes_effective": [],
"retention": {"daily": 7, "weekly": 4, "monthly": 3, "yearly": 1},
}
class RunScheduledConfigSourceTests(SimpleTestCase):
def test_dry_run_uses_injected_config_source(self) -> None:
with patch("pobsync.commands.run_scheduled.run_rsync") as run_rsync:
run_rsync.return_value = RsyncResult(exit_code=0, command=["rsync", "--archive"])
result = run_scheduled(
prefix=Path("/missing-prefix"),
host="web-01",
dry_run=True,
config_source=FakeConfigSource(),
)
self.assertTrue(result["ok"])
self.assertEqual(result["host"], "web-01")
run_rsync.assert_called_once()
def test_successful_real_run_applies_prune_when_requested(self) -> None:
with TemporaryDirectory() as tmp:
prefix = Path(tmp) / "home"
with (
patch("pobsync.commands.run_scheduled.run_rsync") as run_rsync,
patch("pobsync.commands.retention_apply.run_retention_plan") as plan,
):
run_rsync.return_value = RsyncResult(exit_code=0, command=["rsync", "--archive"])
plan.return_value = {
"ok": True,
"delete": [],
"keep": [],
"reasons": {},
"protect_bases": False,
}
result = run_scheduled(
prefix=prefix,
host="web-01",
dry_run=False,
prune=True,
prune_max_delete=10,
config_source=FakeConfigSource(backup_root=str(Path(tmp) / "backups")),
)
self.assertTrue(result["ok"])
self.assertIsNotNone(result["prune"])
self.assertEqual(result["prune"]["deleted"], [])