pn51: document stress test pass and TSC runtime test failure

Both units survived 1h stress test at 80-85C. TSC clocksource
is genuinely unstable at runtime (not just boot), HPET is the
correct fallback for this platform.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

docs/plans/pn51-stability.md

@@ -54,6 +54,23 @@ Two ASUS PN51-E1 mini PCs (Ryzen 7 5700U) purchased years ago but shelved due to
 - The kernel handles TSC instability gracefully (falls back to HPET), and PSP LOAD_TA is non-fatal
 - Neither issue is likely the cause of the hard freezes — the fTPM bug remains the primary suspect
 
+### 2026-02-22: Stress Test (1 hour)
+
+- Ran `stress-ng --cpu 16 --vm 2 --vm-bytes 8G --timeout 1h` on both units
+- CPU temps peaked at ~85°C, settled to ~80°C sustained (throttle limit is 105°C)
+- Both survived the full hour with no freezes, no MCE errors, no kernel issues
+- No concerning log entries during or after the test
+
+### 2026-02-22: TSC Runtime Switch Test
+
+- Attempted to switch clocksource back to TSC at runtime on pn01:
+  ```
+  echo tsc > /sys/devices/system/clocksource/clocksource0/current_clocksource
+  ```
+- Kernel watchdog immediately reverted to HPET — TSC skew is ongoing, not just a boot-time issue
+- **Conclusion**: TSC is genuinely unstable on the PN51-E1 platform. HPET is the correct clocksource.
+- For virtualization (Incus), this means guest VMs will use HPET-backed timing. Performance impact is minimal for typical server workloads (DNS, monitoring, light services) but would matter for latency-sensitive applications.
+
 ## Benign Kernel Errors (Both Units)
 
 These appear on both units and can be ignored:
@@ -62,19 +79,13 @@ These appear on both units and can be ignored:
 - `pcie_mp2_amd: amd_sfh_hid_client_init failed err -95` — AMD Sensor Fusion Hub, no sensors connected
 - `Bluetooth: hci0: Reading supported features failed` — Bluetooth init quirk
 - `Serial bus multi instantiate pseudo device driver INT3515:00: error -ENXIO` — unused serial bus device
+- `snd_hda_intel: no codecs found` — no audio device connected, headless server
 - `ata2.00: supports DRM functions and may not be fully accessible` — Samsung SSD DRM quirk (pn02 only)
 
 ## Next Steps
 
-- Monitor both units for stability (fTPM disabled on both, BIOS updated on pn02)
+- Monitor both units for stability over the next few days
-- **Test TSC stability after boot**: The TSC skew may only occur during early boot (power state transitions, frequency scaling) and stabilize later. Test by switching clocksource back to TSC at runtime:
-  ```bash
-  # Check current clocksource
-  cat /sys/devices/system/clocksource/clocksource0/current_clocksource
-  # Switch back to TSC (kernel watchdog will revert if skew persists)
-  echo tsc > /sys/devices/system/clocksource/clocksource0/current_clocksource
-  ```
-  If TSC stays stable after boot, this is just an early-boot calibration issue. This matters for virtualization performance — HPET is 50-100x slower than TSC per timing call, and KVM guests rely on the host clocksource.
 - If either freezes again, try disabling unused hardware in BIOS (GPU, WiFi, Bluetooth, audio)
 - If still freezing, may be a hardware defect
 - Once stable: add second RAM stick back to pn02, reinstall with NVMe
+- Evaluate for Incus hypervisor use (see `nixos-hypervisor.md`)