A secondary syncs by rsync: the Controller runs it on its schedule, and both pages follow it (#995)

* A secondary syncs by rsync: the Controller runs it on its schedule, and both pages follow it

The third part of replacing the sync.

- The Controller syncs within the daily window (every 15 minutes after the last sync finished, in WROLPi's
  timezone), as the API did.  The API's loop no longer runs the old engine, and its /api/sync/run and
  /api/sync/cancel ask the Controller.
- The Sync page and the overlay that covers the app read the sync's status from the Controller, which is the only
  one that can answer while the API is stopped.  The overlay is also shown when the settings cannot be read, as
  happens while the API is stopped.  Sync Now and Stop go to the Controller.
- The Controller's fallback page, where Caddy sends the browser while the API is down, shows the sync's progress
  and a Stop button.
- New on the Sync page: how long files the primary deletes are kept (30 days by default, or never), and a note that
  an excluded folder's files are still listed on a secondary.

The old engine's code is removed in the next part.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* Remove SyncRunRequest, unused since a sync is asked of the Controller

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* In Docker, a sync's progress moves while a large file is copied

Docker's logs hold a line until it ends, and rsync's progress for one large file is a single line rewritten with
carriage returns, so the page showed 0% until the file was done (hours, for a large map).  The rsync helper's
output is now read by attaching to it, before it is started so that nothing is missed.

Found by a sync between two Docker WROLPis.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* A sync is recovered before the schedule can start another, and an empty days value is refused

Review found:

- The schedule and the recovery of an interrupted sync started side by side when the Controller started.  The state
  an interrupted sync leaves is due, so inside the window a new sync could start while the recovery restarted the
  API and wrote over the new sync's status.  Every tick of the schedule now recovers first, and only a status of
  "running" with no sync holding the lock counts as interrupted.  A sync records its outcome before it frees the
  lock, so a tick between the two cannot mistake it for an interrupted one.
- The Controller may start before the drive is mounted.  The empty record it read then was kept and saved over the
  real one, losing the last successful sync.  The state file is now read again until it can be.
- A cleared number of days was saved as 0, which empties the trash at the next sync.  It is now refused.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
lrnselfreliance 2026-11-19 15:06:25 -07:00 • committed by GitHub
parent 6772762ce9
commit 8cfe36b3ea
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
13 changed files with 708 additions and 128 deletions

View file

@ -2,8 +2,10 @@
Unit tests for controller.lib.sync: a secondary WROLPi copying its primary with rsync.
"""
import asyncio
import datetime
import os
import re
import shutil
import socket
import sqlite3
@ -35,6 +37,7 @@ def media(tmp_path, monkeypatch) -> Path:
(directory / "config/sync.yaml").write_text(yaml.safe_dump(dict(role="secondary", primary_url=PRIMARY)))
monkeypatch.setenv("MEDIA_DIRECTORY", str(directory))
monkeypatch.setattr(sync, "_status", None)
monkeypatch.setattr(sync, "_status_from_file", False)
sync._cancel.clear()
yield directory
assert not sync._run_lock.locked(), "the test left a sync running"
@ -352,7 +355,7 @@ class TestRunSync:
assert yaml.safe_load((media / sync.PRIMARY_INFO).read_text())["media_directory"] == "/media/wrolpi"
assert (media / sync.PRIMARY_WROLPI_CONFIG).is_file()
# A restarted Controller reads the state file.
sync._status = None
sync._status, sync._status_from_file = None, False
assert sync.get_status()["last_success_at"] == status["last_success_at"]
def test_leaves_out_the_playlists_of_both_machines(self, media, primary_api):
@ -428,7 +431,7 @@ class TestRunSync:
def test_interrupted_sync_is_recovered(self, media):
"""A Controller that stopped during a sync left the API stopped."""
sync.update_status(save=True, state="running", phase="files")
sync._status = None
sync._status, sync._status_from_file = None, False
runner = FakeRunner(media)
sync.recover_interrupted_sync(runner)
# In Docker rsync is its own container and is still replacing files: it is stopped before the API starts.
@ -671,3 +674,178 @@ def test_never_delete_still_removes_stale_logs(tmp_path):
assert (secondary / "kept folder/a.txt").read_text() == "kept"
assert read_database(secondary / "map/region.search.db") == "the primary's new index"
assert not (secondary / ".sync-trash").exists()
class TestSchedule:
@pytest.mark.parametrize("start, end, now, expected", [
("01:00", "05:00", "03:00", True),
("01:00", "05:00", "05:00", False),
("01:00", "05:00", "00:59", False),
# Past midnight.
("22:00", "02:00", "23:30", True),
("22:00", "02:00", "01:59", True),
("22:00", "02:00", "12:00", False),
(None, "02:00", "01:00", False),
("not a time", "02:00", "01:00", False),
])
def test_in_window(self, start, end, now, expected):
assert sync.in_window(start, end, datetime.time.fromisoformat(now)) is expected
def test_due_every_fifteen_minutes_inside_the_window(self):
tz = datetime.timezone(datetime.timedelta(hours=-7))
now = datetime.datetime(2026, 11, 19, 3, 0, tzinfo=tz)
config = dict(window_start="01:00", window_end="05:00")
assert sync.sync_is_due(config, dict(finished_at=None), now)
recent = (now - datetime.timedelta(minutes=14)).astimezone(datetime.timezone.utc).isoformat()
assert not sync.sync_is_due(config, dict(finished_at=recent), now)
older = (now - datetime.timedelta(minutes=15)).astimezone(datetime.timezone.utc).isoformat()
assert sync.sync_is_due(config, dict(finished_at=older), now)
assert not sync.sync_is_due(dict(window_start=None, window_end=None), dict(finished_at=None), now), \
"without a window a sync only runs when asked"
def test_local_now_uses_wrolpis_timezone(self, media):
(media / "config/wrolpi.yaml").write_text("timezone: Asia/Tokyo\n")
assert sync.local_now().utcoffset() == datetime.timedelta(hours=9)
(media / "config/wrolpi.yaml").write_text("timezone: Not/AZone\n")
assert sync.local_now().tzinfo is not None
def test_tick(self, media, monkeypatch):
runs = []
monkeypatch.setattr(sync, "run_sync", lambda: runs.append(1))
monkeypatch.setattr(sync, "local_now",
lambda: datetime.datetime(2026, 11, 19, 3, 0).astimezone())
sync.schedule_tick()
assert runs == [], "no window"
(media / "config/sync.yaml").write_text(yaml.safe_dump(dict(
role="secondary", primary_url=PRIMARY, window_start="01:00", window_end="05:00")))
sync.schedule_tick()
assert runs == [1]
(media / "config/.wrol_mode").touch()
sync.schedule_tick()
assert runs == [1], "WROL Mode stops the schedule"
@pytest.mark.asyncio
async def test_loop_survives_a_failure(self, monkeypatch):
ticks = []
def tick():
ticks.append(1)
raise RuntimeError("the drive went away")
monkeypatch.setattr(sync, "schedule_tick", tick)
monkeypatch.setattr(sync, "SCHEDULE_INTERVAL_SECONDS", 0.01)
task = asyncio.create_task(sync.sync_schedule_loop())
await asyncio.sleep(0.2)
task.cancel()
assert len(ticks) >= 3
def test_fallback_page_shows_the_sync(media):
"""The browser is sent to the Controller's page while the API is stopped; it says a sync is the reason."""
response = TestClient(app).get("/")
assert response.status_code == 200
assert b'id="sync-card"' in response.content and b"api/sync/status" in response.content
assert b"api/sync/cancel" in response.content
def test_frontend_fixture_matches_the_status():
"""The frontend's tests render the sync from controllerSyncStatusFixture; it must have the keys the Controller
sends, or a renamed field passes those tests and breaks the page."""
source = (Path(__file__).parent.parent.parent / "app/src/test-fixtures.js").read_text()
match = re.search(r"export const controllerSyncStatusFixture = \(overrides = \{}\) => \(\{(.*?)\n}\);",
source, re.S)
assert match, "controllerSyncStatusFixture is not in test-fixtures.js in the expected form"
keys = set(re.findall(r"^ ([a-z0-9_]+):", match.group(1), re.M))
assert keys == set(sync.default_status())
def test_docker_rsync_reads_progress_as_it_comes(media, monkeypatch):
"""The helper's output is read by attaching to it before it starts. Docker's logs would hold rsync's progress
for a large file (one line, rewritten with carriage returns) until the file was done."""
from unittest import mock
events = []
helper = mock.Mock()
helper.attach.side_effect = lambda **kwargs: events.append(("attach", kwargs)) or iter(
[b" 1000 10%\r", b" 5000 50%\r", b"Number of regular files transferred: 1\n"])
helper.start.side_effect = lambda: events.append(("start", None))
helper.wait.return_value = {"StatusCode": 0}
api = mock.Mock()
api.image.id, api.name, api.attrs = "sha256:image", "wrolpi-api-1", {"Config": {"User": "1000:1000"}}
client = mock.Mock()
client.containers.create.return_value = helper
client.containers.get.side_effect = lambda name: api if name == "wrolpi-api-1" else (_ for _ in ()).throw(
RuntimeError("no such container"))
monkeypatch.setattr(sync, "_get_client", lambda: client)
lines = []
assert sync.DockerRunner().rsync(["--version"], lines.append) == 0
assert [i[0] for i in events] == ["attach", "start"], "attached before it starts"
assert events[0][1]["stream"] is True
assert lines == [" 1000 10%", " 5000 50%", "Number of regular files transferred: 1"]
helper.logs.assert_not_called()
helper.remove.assert_called_once_with(force=True)
class TestRecoveryAndSchedule:
"""A Controller that starts after an interrupted sync must recover it before the schedule starts another."""
def interrupted(self, media):
(media / "config/sync.yaml").write_text(yaml.safe_dump(dict(
role="secondary", primary_url=PRIMARY, window_start="00:00", window_end="23:59")))
(media / "config/sync_state.yaml").write_text(yaml.safe_dump(dict(state="running", phase="files",
finished_at=None)))
def test_tick_recovers_first_and_starts_nothing(self, media, monkeypatch):
self.interrupted(media)
runner, runs = FakeRunner(media), []
monkeypatch.setattr(sync, "get_runner", lambda: runner)
monkeypatch.setattr(sync, "run_sync", lambda: runs.append(1))
monkeypatch.setattr(sync, "local_now", lambda: datetime.datetime.now().astimezone())
sync.schedule_tick()
assert runner.events == ["stop_rsync", "start_api"]
assert sync.get_status()["state"] == "error" and sync.get_status()["last_error"] == "The sync was interrupted"
assert runs == [], "the recovered sync just finished; the next one waits its 15 minutes"
def test_a_running_sync_is_not_recovered(self, media, monkeypatch):
"""A status of "running" while this Controller's own sync holds the lock is no interrupted sync."""
self.interrupted(media)
runner = FakeRunner(media)
assert sync._run_lock.acquire(blocking=False)
try:
sync.recover_interrupted_sync(runner)
finally:
sync._run_lock.release()
assert runner.events == [] and sync.get_status()["state"] == "running"
def test_state_file_read_once_the_drive_is_mounted(self, media):
"""The Controller may start before the drive is mounted: what it could not read is read later, not
replaced by an empty record."""
state = media / "config/sync_state.yaml"
assert not state.exists()
assert sync.get_status()["last_success_at"] is None
state.write_text(yaml.safe_dump(dict(state="idle", last_success_at="2026-11-18T03:00:00+00:00")))
assert sync.get_status()["last_success_at"] == "2026-11-18T03:00:00+00:00"
# Once read, what is in memory is the record.
sync.update_status(last_error="x")
state.write_text(yaml.safe_dump(dict(state="idle", last_success_at=None)))
assert sync.get_status()["last_success_at"] == "2026-11-18T03:00:00+00:00"
def test_outcome_is_recorded_before_the_lock_is_freed(self, media, primary_api, monkeypatch):
"""Otherwise a tick between the two would take the sync for an interrupted one."""
locked_when_saved = []
update_status = sync.update_status
def watch(save=False, **changes):
if save and changes.get("finished_at"):
locked_when_saved.append(sync._run_lock.locked())
return update_status(save=save, **changes)
monkeypatch.setattr(sync, "update_status", watch)
sync.run_sync(FakeRunner(media))
assert locked_when_saved == [True]