drjones/gpu-program-swapper
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Detect fan-mode drift; document health checks, VRAM accounting and tests

Browse Source 
The reconciler only compared the power limit, so a profile whose fan setting never
applied stayed wrong indefinitely. The headless X server that owns the GPU can be
starting when this unit does; in-process retries cover a short delay, but if X
arrives later nothing noticed that the fan mode had never been set. profile_drift()
now compares fan mode too, gated on fan control having worked at least once so the
check does not fire forever on a machine without it.

README documents the self-check endpoint, the ollama/comfy/desktop/unmanaged
bucketing and why unreclaimable VRAM is reported separately, the SSE trimming, and
a tests section listing the measured constants the suite pins.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
This commit is contained in:
drjones
2026-09-05 19:17:16 -07:00
parent fb104ac9c0
commit 2948b0b440
2 changed files with 77 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files

40
overclock_manager.py
View File

@@ -308,9 +308,11 @@ def apply_profile(name: str, overrides: Optional[Dict[str, Any]] = None) -> Dict
logger.warning(f"Profile '{name}' could not set fans: "
f"{result['fan'].get('detail')}")
global _APPLIED_ONCE
global _APPLIED_ONCE, _FAN_AVAILABLE
if result["verified"]["power_limit_ok"]:
_APPLIED_ONCE = True
if result["verified"]["fan_ok"]:
_FAN_AVAILABLE = True
ACTIVE_PROFILE = name
_LAST_RESULT = result
logger.info(f"Overclock profile applied: {name} -> {json.dumps(result, default=str)}")
@@ -475,6 +477,9 @@ def restore_safe(reason: str = "shutdown") -> Dict[str, Any]:
_APPLIED_ONCE = False
# Set once fan control has worked at least once, so drift checks do not fire forever on
# a machine that simply has no fan control available.
_FAN_AVAILABLE = False
def profile_drift() -> Dict[str, Any]:
@@ -490,17 +495,38 @@ def profile_drift() -> Dict[str, Any]:
state = get_gpu_state()
intended = int(cfg.get("power_limit_w", 0) or 0)
actual = state.get("power_limit_w")
drifted = bool(intended and actual is not None
and abs(float(actual) - intended) >= 1.0)
power_drift = bool(intended and actual is not None
and abs(float(actual) - intended) >= 1.0)
# Fan mode is checked too. The headless X server that owns the GPU can still be
# starting when this unit does, and the fan assignment then fails; the in-process
# retries cover a short delay, but if X arrives later nothing else would ever notice
# that the profile's fan setting was never applied.
fan_intended = cfg.get("fan_mode", "auto")
fan_actual = None
fan_drift = False
if _FAN_AVAILABLE:
fan_actual = get_fan_status().get("mode")
fan_drift = bool(fan_actual and fan_actual != fan_intended)
drifted = power_drift or fan_drift or not _APPLIED_ONCE
reasons = []
if not _APPLIED_ONCE:
reasons.append("no profile has been successfully applied since startup")
if power_drift:
reasons.append(f"card reports {actual}W, profile asks {intended}W")
if fan_drift:
reasons.append(f"fans are {fan_actual}, profile asks {fan_intended}")
return {
"profile": ACTIVE_PROFILE,
"applied_since_start": _APPLIED_ONCE,
"power_limit_intended_w": intended,
"power_limit_actual_w": actual,
"drifted": drifted or not _APPLIED_ONCE,
"reason": ("no profile has been successfully applied since startup"
if not _APPLIED_ONCE else
f"card reports {actual}W, profile asks {intended}W" if drifted else None),
"fan_mode_intended": fan_intended,
"fan_mode_actual": fan_actual,
"fan_available": _FAN_AVAILABLE,
"drifted": drifted,
"reason": "; ".join(reasons) or None,
}