PUBLIC/gpu-turnstile
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 19 Wiki Activity

Add GPU_FOREIGN_UTIL_PCT: game detection via per-process GPU 3D-engine usage

Browse Source 
Reads the same PDH counters as Task Manager (\GPU Engine(*)\Utilization
Percentage, locale-independent via PdhAddEnglishCounterW), which cover
graphics work under WDDM — games are caught without an exe list and the
offender is named. Windows-only; a missing or failing counter disables
the path with one log line. dwm (the desktop compositor) joins the
default ignore list.
This commit is contained in:
mram
2026-09-22 10:53:29 +02:00
parent 8fccd333aa
commit d259b2e96c
11 changed files with 387 additions and 72 deletions
Download Patch File Download Diff File Expand all files Collapse all files
internal/config/sample.go
+2 -1
View File
@@ -34,7 +34,8 @@ func sampleEntries(logFile string) []sampleEntry {
{"COMFY_START_TIMEOUT", "2m", "How long a request waits for the managed ComfyUI to come up", false},
{"GAME_PROCS", "cyberpunk2077.exe,hl2.exe", "While a listed process runs, the GPU counts as held by it: requests wait, Ollama unloads, managed ComfyUI stops (default: empty = disabled)", false},
{"GPU_FOREIGN_VRAM_MB", "1024", "Also treat the GPU as held when a process not in GPU_IGNORE_PROCS uses more VRAM than this (needs nvidia-smi; 0/empty = disabled)", false},
{"GPU_IGNORE_PROCS", "ollama,ollama app,ollama_llama_server,python,pythonw", "Process names never counted as foreign GPU users (ComfyUI runs under python)", false},
{"GPU_FOREIGN_UTIL_PCT", "30", "Also treat the GPU as held when a process not in GPU_IGNORE_PROCS uses more than this percent of the GPU 3D engine (Windows Task-Manager counters; catches games without an exe list; 0/empty = disabled)", false},
{"GPU_IGNORE_PROCS", "ollama,ollama app,ollama_llama_server,python,pythonw,dwm", "Process names never counted as foreign GPU users (ComfyUI runs under python; dwm is the desktop compositor)", false},
{"GAME_POLL_INTERVAL", "15s", "How often game/VRAM detection runs (nvidia-smi polls keep the GPU awake; don't go below ~10s)", false},
{"UNLOAD_TIMEOUT", "60s", "How long to wait for Ollama to unload a model", false},
{"JOB_TIMEOUT", "15m", "Maximum time to wait for a ComfyUI job", false},