jessey
07bc722209
check_pcie_links() warns when an NVMe drive negotiates fewer lanes than it supports — almost always motherboard lane-sharing (a GPU/second card or another M.2 stealing lanes), the case the user asked about — and reports speed-only reductions as info (slower slot / idle ASPM). GPU is excluded: NVIDIA drops its PCIe gen+width at idle, so a snapshot would false-alarm. Reuses inventory read_link/nvme_controllers (refactored to public). Wired into run_health_checks; +tests. Folded into the 0.38.0 PCIe work. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
86 lines
3.3 KiB
Python
86 lines
3.3 KiB
Python
"""Tests for the M4 health report's log scanner (synthetic input)."""
|
||
|
||
import unittest
|
||
from pathlib import Path
|
||
from unittest import mock
|
||
|
||
from rigdoctor.core import health
|
||
from rigdoctor.core.health import (
|
||
CRITICAL,
|
||
INFO,
|
||
WARNING,
|
||
check_pcie_links,
|
||
run_health_checks,
|
||
scan_journal_text,
|
||
)
|
||
|
||
|
||
class HealthScanTests(unittest.TestCase):
|
||
def test_xid_79_is_critical(self):
|
||
text = "NVRM: Xid (PCI:0000:01:00): 79, pid=1234, GPU has fallen off the bus."
|
||
findings = scan_journal_text(text)
|
||
gpu = [f for f in findings if f.category == "GPU"]
|
||
self.assertEqual(len(gpu), 1)
|
||
self.assertIn("79", gpu[0].title)
|
||
self.assertEqual(gpu[0].severity, CRITICAL)
|
||
|
||
def test_xid_count_aggregates(self):
|
||
text = "\n".join(["NVRM: Xid (PCI:0000:01:00): 79, foo"] * 3)
|
||
gpu = [f for f in scan_journal_text(text) if f.category == "GPU"][0]
|
||
self.assertIn("×3", gpu.title)
|
||
|
||
def test_oom_and_panic_detected(self):
|
||
text = "Out of memory: Killed process 999 (game)\nKernel panic - not syncing: x"
|
||
cats = {f.category for f in scan_journal_text(text)}
|
||
self.assertIn("Memory", cats)
|
||
self.assertIn("Kernel", cats)
|
||
|
||
def test_mce_critical(self):
|
||
findings = scan_journal_text("mce: [Hardware Error]: Machine check events logged")
|
||
self.assertTrue(any(f.severity == CRITICAL and f.category == "Hardware" for f in findings))
|
||
|
||
def test_clean_text_yields_no_findings(self):
|
||
self.assertEqual(scan_journal_text("usb 1-1: new high-speed USB device\nbluetooth: ok"), [])
|
||
|
||
def test_run_health_checks_returns_findings(self):
|
||
# Runs against the real system; just assert it returns a sorted list of Findings.
|
||
findings = run_health_checks()
|
||
self.assertIsInstance(findings, list)
|
||
severities = [f.severity for f in findings]
|
||
order = {"critical": 0, "warning": 1, "info": 2, "ok": 3}
|
||
ranks = [order.get(s, 9) for s in severities]
|
||
self.assertEqual(ranks, sorted(ranks))
|
||
|
||
|
||
class PcieLinkCheckTests(unittest.TestCase):
|
||
def _with_link(self, cur_g, cur_w, max_g, max_w):
|
||
# one fake NVMe controller returning the given link tuple
|
||
return (mock.patch("rigdoctor.core.inventory.nvme_controllers",
|
||
return_value=[("nvme0", Path("/x"))]),
|
||
mock.patch("rigdoctor.core.inventory.read_link",
|
||
return_value=(cur_g, cur_w, max_g, max_w)))
|
||
|
||
def test_reduced_width_is_a_warning_about_lane_sharing(self):
|
||
ctrls, link = self._with_link(4, "2", 4, "4") # Gen4 x2 but supports x4
|
||
with ctrls, link:
|
||
findings = check_pcie_links()
|
||
self.assertEqual(len(findings), 1)
|
||
self.assertEqual(findings[0].severity, WARNING)
|
||
self.assertIn("lane-sharing", findings[0].detail)
|
||
|
||
def test_reduced_speed_only_is_info(self):
|
||
ctrls, link = self._with_link(3, "4", 4, "4") # Gen3 x4 but supports Gen4
|
||
with ctrls, link:
|
||
findings = check_pcie_links()
|
||
self.assertEqual(len(findings), 1)
|
||
self.assertEqual(findings[0].severity, INFO)
|
||
|
||
def test_full_speed_no_finding(self):
|
||
ctrls, link = self._with_link(4, "4", 4, "4")
|
||
with ctrls, link:
|
||
self.assertEqual(check_pcie_links(), [])
|
||
|
||
|
||
if __name__ == "__main__":
|
||
unittest.main()
|