fix(recovery): ignore stale docker cpu attribution
Some checks failed
CD Pipeline / workflow-shape (push) Successful in 0s
CD Pipeline / cancel-stale-cd (push) Has been skipped
CD Pipeline / tests (push) Failing after 33s
AWOOOI Harbor 110 Local Repair / workflow-shape (push) Successful in 0s
CD Pipeline / build-and-deploy (push) Has been skipped
AWOOOI Harbor 110 Local Repair / harbor-110-local-repair (push) Failing after 1m41s
CD Pipeline / post-deploy-checks (push) Has been skipped

This commit is contained in:
Your Name
2026-07-01 14:06:51 +08:00
parent e580954e82
commit 1ac8808607
7 changed files with 318 additions and 4 deletions

View File

@@ -425,6 +425,60 @@ def test_sustained_load_controller_routes_gitea_backlog_from_docker_metrics(tmp_
assert "host-sustained-load-evidence.py" in payload["commands"]["dry_run"]
def test_sustained_load_controller_ignores_stale_docker_stats_attribution(tmp_path: Path) -> None:
metrics_file = tmp_path / "host.prom"
metrics_file.write_text(
"\n".join(
[
'awoooi_host_runaway_process_monitor_up{host="110",mode="read_only"} 1',
'awoooi_host_load5_per_core{host="110"} 2.5',
'awoooi_host_swap_used_ratio{host="110"} 0.1',
'awoooi_host_runaway_process_remediation_authorized{host="110"} 0',
'awoooi_host_gitea_actions_active_container_count{host="110"} 0',
'awoooi_host_gitea_actions_active_process_group_count{host="110"} 0',
'awoooi_host_runaway_browser_orphan_group_count{host="110",rule="stockplatform_headless_smoke",min_age_seconds="1800",min_cpu_percent="50"} 0',
'node_textfile_mtime_seconds{file="/host/home/wooo/node_exporter_textfiles/docker_stats.prom"} 1000',
'node_time_seconds 5000',
]
),
encoding="utf-8",
)
docker_file = tmp_path / "docker.prom"
docker_file.write_text(
"\n".join(
[
'docker_container_cpu_cores{host="110",container_name="gitea"} 3.4',
'docker_container_cpu_cores{host="110",container_name="redis"} 0.2',
]
),
encoding="utf-8",
)
result = subprocess.run(
[
sys.executable,
str(CONTROLLER_PATH),
"--host",
"110",
"--metrics-file",
str(metrics_file),
"--docker-stats-file",
str(docker_file),
"--json",
],
capture_output=True,
text=True,
)
assert result.returncode == 75
payload = json.loads(result.stdout)
assert payload["classification"] == "blocked_unknown_sustained_load_requires_source_specific_playbook"
assert payload["readback"]["docker_stats"]["fresh"] is False
assert payload["readback"]["top_container_cpu"] is None
assert payload["readback"]["top_container_cpu_untrusted"]["container_name"] == "gitea"
assert payload["controlled_apply_allowed"] is False
def test_sustained_load_controller_routes_unknown_load_to_sanitized_evidence(tmp_path: Path) -> None:
metrics_file = tmp_path / "host.prom"
metrics_file.write_text(
@@ -506,6 +560,55 @@ def test_sustained_load_evidence_emits_sanitized_gitea_recommendation(tmp_path:
assert "/home/wooo" not in result.stdout
def test_sustained_load_evidence_keeps_stale_container_samples_untrusted(tmp_path: Path) -> None:
metrics_file = tmp_path / "host.prom"
metrics_file.write_text(
"\n".join(
[
'node_textfile_mtime_seconds{file="/host/home/wooo/node_exporter_textfiles/docker_stats.prom"} 1000',
'node_time_seconds 5000',
]
),
encoding="utf-8",
)
docker_file = tmp_path / "docker.prom"
docker_file.write_text(
'docker_container_cpu_cores{host="110",container_name="gitea"} 3.4\n',
encoding="utf-8",
)
ps_file = tmp_path / "ps.txt"
ps_file.write_text(
"100 1 100 120 5.0 1.0 python python monitor.py\n",
encoding="utf-8",
)
result = subprocess.run(
[
sys.executable,
str(EVIDENCE_PATH),
"--host",
"110",
"--metrics-file",
str(metrics_file),
"--ps-file",
str(ps_file),
"--docker-stats-file",
str(docker_file),
"--json",
],
check=True,
capture_output=True,
text=True,
)
payload = json.loads(result.stdout)
assert payload["recommendation"] != "gitea_queue_or_hook_backlog_playbook"
assert payload["readback"]["docker_stats"]["fresh"] is False
assert payload["top_containers"] == []
assert payload["top_containers_untrusted"][0]["container_name"] == "gitea"
assert payload["operation_boundaries"]["host_write_performed"] is False
def test_sustained_load_controller_routes_unknown_load_to_sanitized_evidence(tmp_path: Path) -> None:
metrics_file = tmp_path / "host.prom"
metrics_file.write_text(