mirror of
https://scm.tikali.ai/tikali/applications/monky/monky-deployd.git
synced 2026-09-18 05:36:15 +00:00
mdella
4ff2e29fbc
dpkg calls the OLD package's prerm on an UPGRADE as well as on a removal (rpm passes a remaining-instance count), and preremove.sh ran `systemctl disable --now monky-deployd.timer` unconditionally. Upgrading env-dev-01 and env-dev-08 to 0.1.8 today stopped and disabled both agents. The failure is silent, which is the dangerous part: the box stays reachable, the containers keep running, and nothing reports that check-ins have ceased — the backend just stops converging. A fleet upgrade would have taken every agent offline at once and looked like a success. preremove.sh now returns early for every upgrade shape (upgrade, failed-upgrade, deconfigure, rpm's 1) and only disables on a real removal. postinstall.sh try-restarts the long-lived proxy unit so it picks up the new code; the timer needs nothing, since each tick is a fresh process. Tests drive the script with a fake systemctl on PATH and assert an upgrade touches no units. OPERATIONS.md warns that a box coming FROM 0.1.8 or earlier still needs its timer re-enabled by hand, because the old prerm has already run by then. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01KLB7jieMNRkTsJ2epr4Ds1
47 lines
1.8 KiB
Python
47 lines
1.8 KiB
Python
"""The maintainer scripts must not stop the agent on an upgrade.
|
|
|
|
dpkg calls the OLD package's prerm on an upgrade as well as on a removal, and rpm calls it with
|
|
an install count. `systemctl disable --now` there stopped the agent on every upgrade and left it
|
|
disabled — silently, because the box stays reachable and nothing else notices that check-ins have
|
|
ceased (env-dev-01 and env-dev-08, 2026-09-09).
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import shutil
|
|
import subprocess
|
|
from pathlib import Path
|
|
|
|
import pytest
|
|
|
|
PREREMOVE = Path(__file__).resolve().parents[1] / "packaging" / "scripts" / "preremove.sh"
|
|
|
|
|
|
def _run(arg: str, tmp_path: Path) -> list[str]:
|
|
"""Run preremove with a fake `systemctl` on PATH and report the calls it made."""
|
|
calls = tmp_path / "systemctl.log"
|
|
fake = tmp_path / "bin"
|
|
fake.mkdir(exist_ok=True)
|
|
(fake / "systemctl").write_text(f'#!/bin/sh\necho "$@" >> {calls}\nexit 0\n')
|
|
(fake / "systemctl").chmod(0o755)
|
|
env = {"PATH": f"{fake}:/usr/bin:/bin"}
|
|
r = subprocess.run(["sh", str(PREREMOVE), arg], env=env, capture_output=True, text=True)
|
|
assert r.returncode == 0, r.stderr
|
|
return calls.read_text().splitlines() if calls.exists() else []
|
|
|
|
|
|
@pytest.mark.skipif(not Path("/run/systemd/system").is_dir(), reason="needs a systemd host to reach the disable branch")
|
|
@pytest.mark.parametrize("arg", ["remove", "0"])
|
|
def test_a_real_removal_disables_the_units(arg, tmp_path):
|
|
assert any("disable" in c for c in _run(arg, tmp_path))
|
|
|
|
|
|
@pytest.mark.parametrize("arg", ["upgrade", "failed-upgrade", "deconfigure", "1"])
|
|
def test_an_upgrade_leaves_the_units_alone(arg, tmp_path):
|
|
assert _run(arg, tmp_path) == []
|
|
|
|
|
|
def test_the_script_is_shell_clean():
|
|
assert shutil.which("sh")
|
|
subprocess.run(["sh", "-n", str(PREREMOVE)], check=True)
|