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

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
+19 -8
View File
@@ -70,12 +70,15 @@ type Config struct {
// them runs, the GPU is treated as held by a foreign process. The
// nvidia-smi path (GPUForeignVRAMMB, GPU_FOREIGN_VRAM_MB) does the same
// when a process not in GPUIgnoreProcs (GPU_IGNORE_PROCS) holds more than
// that many MiB of VRAM. GamePollInterval (GAME_POLL_INTERVAL) is how
// often both checks run.
GameProcs []string `env:"GAME_PROCS"`
GPUForeignVRAMMB int `env:"GPU_FOREIGN_VRAM_MB"`
GPUIgnoreProcs []string `env:"GPU_IGNORE_PROCS"`
GamePollInterval time.Duration `env:"GAME_POLL_INTERVAL"`
// that many MiB of VRAM, and the PDH path (GPUForeignUtilPct,
// GPU_FOREIGN_UTIL_PCT) when such a process uses more than that many
// percent of the GPU 3D engine (Windows only). GamePollInterval
// (GAME_POLL_INTERVAL) is how often all checks run.
GameProcs []string `env:"GAME_PROCS"`
GPUForeignVRAMMB int `env:"GPU_FOREIGN_VRAM_MB"`
GPUForeignUtilPct int `env:"GPU_FOREIGN_UTIL_PCT"`
GPUIgnoreProcs []string `env:"GPU_IGNORE_PROCS"`
GamePollInterval time.Duration `env:"GAME_POLL_INTERVAL"`
WarmModel string `env:"WARM_MODEL"`
LogLevel slog.Level `env:"LOGLEVEL"`
@@ -119,8 +122,9 @@ func Defaults() Config {
ComfyStartTimeout: 2 * time.Minute,
// ComfyUI runs under python; excluding it (and Ollama) by name keeps
// our own consumers from tripping the foreign-VRAM check.
GPUIgnoreProcs: []string{"ollama", "ollama app", "ollama_llama_server", "python", "pythonw"},
// our own consumers from tripping the foreign-VRAM check. dwm is the
// desktop compositor — it always shows some 3D-engine usage.
GPUIgnoreProcs: []string{"ollama", "ollama app", "ollama_llama_server", "python", "pythonw", "dwm"},
GamePollInterval: 15 * time.Second,
LogLevel: slog.LevelWarn,
@@ -243,6 +247,13 @@ func Load(getenv func(string) string) (Config, error) {
}
cfg.GPUForeignVRAMMB = n
}
if v := getenv("GPU_FOREIGN_UTIL_PCT"); v != "" {
n, err := strconv.Atoi(v)
if err != nil || n < 0 || n > 100 {
return cfg, fmt.Errorf("GPU_FOREIGN_UTIL_PCT: must be an integer in 0-100 (percent of the GPU 3D engine, 0 = disabled)")
}
cfg.GPUForeignUtilPct = n
}
if v := getenv("PROMPT_CAPTURE_LIMIT"); v != "" {
n, err := strconv.ParseInt(v, 10, 64)
if err != nil || n < 0 {
+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},