Merge pull request 'feat(health): flag NVMe PCIe links below capability (lane-sharing) — 0.38.0' (#41) from feat/inventory-pcie into main

Reviewed-on: #41

CHANGELOG.md

@@ -12,6 +12,11 @@ release tag (so the auto-updater, D18, can compare versions).
   (`current/max_link_speed` + width). If a drive negotiates below its capability (a slower M.2
   slot, lane-sharing, or a downtrain) it's flagged: `PCIe Gen3 x4 (capable of Gen4 x4)`. So you
   can confirm a Gen4 SSD is actually in a Gen4 slot. (SATA disks show no PCIe link.)
+- **System Health flags downtrained NVMe links.** A new check warns when an NVMe drive negotiates
+  fewer PCIe lanes than it supports (almost always motherboard **lane-sharing** — a GPU/second
+  card or another M.2 stealing lanes) and notes speed-only reductions as info (a slower slot or
+  idle ASPM). The GPU is deliberately excluded — NVIDIA drops its PCIe gen/width at idle, so a
+  snapshot would false-alarm.
 
 ## [0.37.1] - 2026-05-22
 ### Fixed

src/rigdoctor/core/health.py

@@ -251,6 +251,38 @@ def check_live_temps() -> list[Finding]:
     )]
 
 
+def check_pcie_links() -> list[Finding]:
+    """Flag NVMe drives linked below their PCIe capability — a slower slot or, most often,
+    motherboard lane-sharing where a GPU/second card or another M.2 steals lanes from the slot.
+
+    Width reductions are reliable (reported as warnings); speed-only reductions are info (they can
+    also be normal link power management at idle). The GPU is intentionally not checked here:
+    NVIDIA drops its PCIe gen *and* width at idle, so a point-in-time snapshot is misleading.
+    """
+    from . import inventory
+
+    findings: list[Finding] = []
+    for name, dev in inventory.nvme_controllers():
+        cur_g, cur_w, max_g, max_w = inventory.read_link(dev)
+        if not cur_g or not max_g:
+            continue
+        if max_w and cur_w and cur_w != max_w:  # fewer lanes → almost always lane-sharing
+            findings.append(Finding(
+                WARNING, "PCIe", f"{name} linked at x{cur_w} (supports x{max_w})",
+                f"{name} negotiated PCIe Gen{cur_g} x{cur_w}, but the drive supports "
+                f"Gen{max_g} x{max_w}. Fewer lanes is usually motherboard lane-sharing — a GPU or a "
+                "second card in a PCIe slot, or another populated M.2, can steal lanes from this slot.",
+                "Check your board manual's lane-sharing table; move the drive to a full-x4 "
+                "(often CPU-attached) M.2 slot."))
+        elif cur_g < max_g:  # full width but a lower generation → slower slot or idle ASPM
+            findings.append(Finding(
+                INFO, "PCIe", f"{name} linked at Gen{cur_g} (supports Gen{max_g})",
+                f"{name} negotiated PCIe Gen{cur_g} but supports Gen{max_g}. This can be a slower "
+                "(chipset or older) M.2 slot, or normal link power management (ASPM) at idle.",
+                "If you expect full speed, check the slot and the BIOS PCIe/ASPM settings."))
+    return findings
+
+
 def run_health_checks(include_journal: bool = True) -> list[Finding]:
     """Run all checks and return findings sorted by severity (worst first).
 
@@ -273,5 +305,6 @@ def run_health_checks(include_journal: bool = True) -> list[Finding]:
     else:
         findings += check_smart()
     findings += check_live_temps()
+    findings += check_pcie_links()
     findings.sort(key=lambda f: _ORDER.get(f.severity, 9))
     return findings

src/rigdoctor/core/inventory.py

@@ -134,11 +134,10 @@ def _gen(speed: str) -> int | None:
     return _PCIE_GEN.get(tok)
 
 
-def _link_desc(dev: Path) -> str:
-    """Describe a PCI device's negotiated PCIe link, noting if it's below its max.
+def read_link(dev: Path) -> tuple[int | None, str, int | None, str]:
+    """Negotiated/max PCIe link for a PCI device dir: (cur_gen, cur_width, max_gen, max_width).
 
-    e.g. 'PCIe Gen4 x4', or 'PCIe Gen3 x4 (capable of Gen4 x4)' when downtrained / in a
-    slower slot.
+    Widths are the raw sysfs strings (e.g. '4'); gens are ints (4) or None when unreadable.
     """
     def rd(name: str) -> str:
         try:
@@ -146,8 +145,17 @@ def _link_desc(dev: Path) -> str:
         except OSError:
             return ""
 
-    cur_g, cur_w = _gen(rd("current_link_speed")), rd("current_link_width")
-    max_g, max_w = _gen(rd("max_link_speed")), rd("max_link_width")
+    return (_gen(rd("current_link_speed")), rd("current_link_width"),
+            _gen(rd("max_link_speed")), rd("max_link_width"))
+
+
+def _link_desc(dev: Path) -> str:
+    """Describe a PCI device's negotiated PCIe link, noting if it's below its max.
+
+    e.g. 'PCIe Gen4 x4', or 'PCIe Gen3 x4 (capable of Gen4 x4)' when downtrained / in a
+    slower slot.
+    """
+    cur_g, cur_w, max_g, max_w = read_link(dev)
     if not cur_g or not cur_w:
         return ""
     desc = f"PCIe Gen{cur_g} x{cur_w}"
@@ -156,6 +164,16 @@ def _link_desc(dev: Path) -> str:
     return desc
 
 
+def nvme_controllers() -> list[tuple[str, Path]]:
+    """Each NVMe controller as (name, pci-device-dir), e.g. ('nvme0', /sys/.../device)."""
+    base = Path("/sys/class/nvme")
+    try:
+        entries = [p for p in base.iterdir() if re.fullmatch(r"nvme\d+", p.name)]
+    except OSError:
+        return []
+    return sorted((p.name, p / "device") for p in entries)
+
+
 def _nvme_link(block_name: str) -> str:
     """PCIe link for an NVMe block device (nvme0n1 → controller nvme0); '' for non-NVMe."""
     m = re.match(r"(nvme\d+)", block_name)

tests/test_health.py

@@ -1,8 +1,18 @@
 """Tests for the M4 health report's log scanner (synthetic input)."""
 
 import unittest
+from pathlib import Path
+from unittest import mock
 
-from rigdoctor.core.health import CRITICAL, WARNING, run_health_checks, scan_journal_text
+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):
@@ -42,5 +52,34 @@ class HealthScanTests(unittest.TestCase):
         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()