Files
stackpilot/backend/tests/test_stack_locking.py
menzeljandClaude Opus 5 09bed274eb
CI / check (push) Successful in 7m4s
CI / build-and-push (push) Successful in 1m47s
Lock stacks during compose runs, cache stats, persist runtime state (0.47.0)
F7 — Nothing stopped two compose operations landing on the same stack. There
was a busy flag, but is_busy() was only ever read to colour the status column;
no lifecycle handler consulted it before acting. Two tabs, or auto-update
picking up a stack somebody had just clicked, both ran pull + up -d against the
same project and raced over recreating containers.

Lifecycle calls, the two deploy WebSockets and the auto-update pass now take a
real lock; a second caller gets 409 (or an error frame and close 4409) and
auto-update skips and retries next cycle. The lock is a row rather than a set
in one worker's memory, so it holds across workers and across a restart, and it
carries an expiry — a worker killed mid-deploy would otherwise strand the stack
with no fix short of editing the database.

F10 — /api/stacks/stats sampled every running container on every call, one
blocking daemon request each, and both the dashboard and the stacks list poll
it every five seconds. Two tabs on a 40-container host meant a sustained ~16
samples a second. Cached for 4s behind a lock so concurrent callers share one
sweep, the same shape dashboard_service already used for its fleet aggregate.

F11 — Three module dicts assumed exactly one uvicorn worker without saying so
and were lost on restart. The busy set is the lock above. The image update
cache is now mirrored to SQLite, so a restart shows the badges immediately
instead of blanking them for up to an hour, and the already-notified marks come
back with them rather than re-announcing the same updates. The login rate
limiter is a table, so it cannot be cleared by getting the process to restart
and no longer multiplies by the worker count.

The constraint that shaped this: compose_service and update_service are shared
with the agent, which has no database. Neither may import one. So the lock is a
separate service the central app enforces at its own entry points, and update
persistence is an opt-in callback the central app registers in its lifespan —
the agent registers nothing and behaves exactly as before. A test asserts
update_service never imports the database, since that is the kind of thing a
later change breaks silently.

Both new nets were checked by reverting the fix: dropping the lock from
_lifecycle fails six tests, removing the stats cache fails the one that names
the behaviour.

Also wires up cache pruning in the same sweep — without it both the dict and
the table grew one entry per image tag ever run, for the life of the install.

31 new tests (729 total).

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Dk43rmEeRfYi5wsLDbmfyG
2026-08-31 13:43:39 +02:00

207 lines
6.8 KiB
Python

"""One compose operation per stack (F7), and the lock surviving a restart (F11).
``docker compose`` does no locking of its own. Before 0.47.0 nothing stopped two
``update`` calls landing on the same project at once — two browser tabs, or the
auto-update pass picking up a stack somebody had just clicked — and both would
run ``pull`` then ``up -d`` and fight over recreating the same containers.
There was a busy flag, but it only fed the status column: no handler consulted
it before acting. The lock is a table now, so it also holds across workers and
across a restart.
"""
from __future__ import annotations
from datetime import datetime, timedelta, timezone
import pytest
from sqlmodel import Session
@pytest.fixture
def lock_session(db):
from database import engine
with Session(engine) as session:
yield session
@pytest.fixture(autouse=True)
def clean_locks(db):
"""Locks are global state; don't let one test leak into the next."""
from database import engine
from models.runtime_state import StackLock
from sqlmodel import delete
with Session(engine) as session:
session.exec(delete(StackLock))
session.commit()
yield
@pytest.fixture
def svc():
from services import stack_lock_service
return stack_lock_service
# --------------------------------------------------------------------------- #
# The lock itself
# --------------------------------------------------------------------------- #
def test_a_second_caller_is_refused(svc, lock_session):
svc.acquire(lock_session, "demo", "update", "alice")
with pytest.raises(svc.StackBusy) as excinfo:
svc.acquire(lock_session, "demo", "start", "bob")
assert excinfo.value.action == "update", "the error names the operation in flight"
def test_releasing_frees_it(svc, lock_session):
svc.acquire(lock_session, "demo", "update")
svc.release(lock_session, "demo")
svc.acquire(lock_session, "demo", "start") # must not raise
def test_releasing_a_lock_nobody_holds_is_harmless(svc, lock_session):
svc.release(lock_session, "never-locked")
def test_different_stacks_do_not_block_each_other(svc, lock_session):
svc.acquire(lock_session, "one", "update")
svc.acquire(lock_session, "two", "update")
def test_hold_releases_even_when_the_operation_fails(svc, lock_session):
"""A failed deploy must not leave the stack locked."""
with pytest.raises(RuntimeError):
with svc.hold(lock_session, "demo", "update"):
raise RuntimeError("compose blew up")
assert not svc.is_busy(lock_session, "demo")
def test_an_expired_lock_is_taken_over(svc, lock_session):
"""The recovery path for a worker killed mid-deploy.
Without it the stack would stay locked forever and the only fix would be
editing the database by hand.
"""
from models.runtime_state import StackLock
past = datetime.now(timezone.utc) - timedelta(minutes=5)
lock_session.add(
StackLock(
stack_id="orphaned",
action="update",
owner="a worker that died",
acquired_at=past - timedelta(minutes=30),
expires_at=past,
)
)
lock_session.commit()
assert not svc.is_busy(lock_session, "orphaned")
svc.acquire(lock_session, "orphaned", "start") # must not raise
def test_active_lists_current_locks_and_skips_expired(svc, lock_session):
from models.runtime_state import StackLock
svc.acquire(lock_session, "live", "update")
lock_session.add(
StackLock(
stack_id="dead",
action="start",
expires_at=datetime.now(timezone.utc) - timedelta(seconds=1),
)
)
lock_session.commit()
assert svc.active(lock_session) == {"live": "update"}
def test_prune_removes_only_expired_locks(svc, lock_session):
from models.runtime_state import StackLock
svc.acquire(lock_session, "live", "update")
lock_session.add(
StackLock(
stack_id="dead",
action="start",
expires_at=datetime.now(timezone.utc) - timedelta(seconds=1),
)
)
lock_session.commit()
assert svc.prune_expired(lock_session) == 1
assert svc.active(lock_session) == {"live": "update"}
def test_the_lock_outlives_the_session_that_took_it(svc, db):
"""It is a row, not a set in one worker's memory — that is the point."""
from database import engine
with Session(engine) as first:
svc.acquire(first, "persisted", "update")
with Session(engine) as second:
assert svc.is_busy(second, "persisted")
with pytest.raises(svc.StackBusy):
svc.acquire(second, "persisted", "start")
# --------------------------------------------------------------------------- #
# Enforcement at the HTTP entry point
# --------------------------------------------------------------------------- #
@pytest.fixture
def locked_stack(db):
"""A registered stack that is already mid-operation."""
from database import engine
from models.stack import Stack
from services import compose_service, stack_lock_service
stack_id = "lock-fixture"
compose_service.write_compose(stack_id, "services:\n a:\n image: alpine\n")
with Session(engine) as session:
if not session.get(Stack, stack_id):
session.add(Stack(id=stack_id, name="lock fixture"))
session.commit()
stack_lock_service.acquire(session, stack_id, "update", "someone-else")
return stack_id
@pytest.mark.parametrize("action", ["start", "stop", "restart", "pull", "update", "down"])
def test_lifecycle_calls_are_refused_while_a_stack_is_busy(as_admin, locked_stack, action):
"""409, and crucially *without* reaching Docker — the guard is in front."""
response = as_admin.post(f"/api/stacks/{locked_stack}/{action}")
assert response.status_code == 409
assert "busy" in response.json()["detail"].lower()
assert "update in progress" in response.json()["detail"]
def test_the_stacks_list_shows_a_busy_stack_as_updating(as_admin, locked_stack):
rows = {row["id"]: row for row in as_admin.get("/api/stacks").json()}
assert rows[locked_stack]["status"] == "updating"
def test_an_unlocked_stack_is_not_refused(as_admin, db):
"""The guard must not block ordinary use.
Without a Docker daemon the call fails further in — anything but 409 means
it got past the lock, which is what this asserts.
"""
from database import engine
from models.stack import Stack
from services import compose_service
stack_id = "unlocked-fixture"
compose_service.write_compose(stack_id, "services:\n a:\n image: alpine\n")
with Session(engine) as session:
if not session.get(Stack, stack_id):
session.add(Stack(id=stack_id, name="unlocked fixture"))
session.commit()
assert as_admin.post(f"/api/stacks/{stack_id}/start").status_code != 409