Game detection: foreign GPU holders take an external lock hold (GAME_PROCS, GPU_FOREIGN_VRAM_MB)

internal/game/game.go

@@ -0,0 +1,159 @@
+// Package game detects processes outside gpu-turnstile's control that hold
+// the GPU — typically a game — so the proxy can block new GPU work and free
+// VRAM while they run. Two detection paths: an explicit process watch list
+// (GAME_PROCS) and a foreign-VRAM threshold via nvidia-smi
+// (GPU_FOREIGN_VRAM_MB) that catches anything not on the ignore list.
+package game
+
+import (
+	"context"
+	"errors"
+	"fmt"
+	"log/slog"
+	"os/exec"
+	"strconv"
+	"strings"
+)
+
+// Process is one running OS process.
+type Process struct {
+	PID  int
+	Name string
+}
+
+// computeApp is one process holding GPU memory, as reported by nvidia-smi.
+type computeApp struct {
+	PID    int
+	UsedMB int
+}
+
+// Detector checks whether a foreign process holds the GPU. The zero value
+// (no watch list, no threshold) never detects anything; main only starts the
+// poll loop when at least one path is configured.
+type Detector struct {
+	procs    map[string]bool // normalized names from GAME_PROCS
+	vramMB   int             // foreign VRAM threshold; 0 = disabled
+	ignore   map[string]bool // normalized names never counted as foreign
+	log      *slog.Logger
+	noNvidia bool // nvidia-smi was not found; VRAM path disabled for good
+}
+
+// New builds a Detector from the configured watch list, VRAM threshold in
+// MiB (0 disables the nvidia-smi path) and ignore list. Names are matched
+// case-insensitively, with or without a trailing ".exe".
+func New(procs []string, vramMB int, ignore []string, log *slog.Logger) *Detector {
+	if log == nil {
+		log = slog.Default()
+	}
+	return &Detector{
+		procs:  nameSet(procs),
+		vramMB: vramMB,
+		ignore: nameSet(ignore),
+		log:    log,
+	}
+}
+
+// normName lowercases a process name and strips a trailing ".exe" so the
+// watch and ignore lists match on Windows and Linux spellings alike.
+func normName(s string) string {
+	return strings.TrimSuffix(strings.ToLower(strings.TrimSpace(s)), ".exe")
+}
+
+func nameSet(names []string) map[string]bool {
+	set := make(map[string]bool, len(names))
+	for _, n := range names {
+		if n = normName(n); n != "" {
+			set[n] = true
+		}
+	}
+	return set
+}
+
+// Check looks once for foreign GPU holders and returns a human-readable
+// description of each (empty when the GPU is free for gpu-turnstile's
+// consumers). A failing nvidia-smi call is returned as an error only when
+// the process list found nothing; a missing nvidia-smi binary disables the
+// VRAM path permanently (logged once).
+func (d *Detector) Check(ctx context.Context) ([]string, error) {
+	ps, psErr := processes()
+	if d.vramMB <= 0 || d.noNvidia {
+		return d.detect(ps, nil), psErr
+	}
+	apps, err := queryComputeApps(ctx)
+	if errors.Is(err, exec.ErrNotFound) {
+		d.noNvidia = true
+		d.log.Warn("GPU_FOREIGN_VRAM_MB is set but nvidia-smi was not found; VRAM detection disabled")
+		return d.detect(ps, nil), nil
+	}
+	if err != nil {
+		return d.detect(ps, nil), err
+	}
+	return d.detect(ps, apps), nil
+}
+
+// detect is the pure core of Check: given the process table and (optionally)
+// the nvidia-smi compute-apps list, it returns the foreign holders.
+func (d *Detector) detect(ps []Process, apps []computeApp) []string {
+	var holders []string
+	for _, p := range ps {
+		if d.procs[normName(p.Name)] {
+			holders = append(holders, fmt.Sprintf("%s (pid %d)", p.Name, p.PID))
+		}
+	}
+	if d.vramMB > 0 && apps != nil {
+		names := make(map[int]string, len(ps))
+		for _, p := range ps {
+			names[p.PID] = p.Name
+		}
+		for _, a := range apps {
+			name := names[a.PID]
+			if d.ignore[normName(name)] || a.UsedMB < d.vramMB {
+				continue
+			}
+			if name == "" {
+				name = "unknown process"
+			}
+			holders = append(holders, fmt.Sprintf("%s (pid %d) using %d MiB VRAM", name, a.PID, a.UsedMB))
+		}
+	}
+	return holders
+}
+
+// queryComputeApps runs nvidia-smi and parses the per-process VRAM list.
+// Note: under Windows' WDDM driver, nvidia-smi only sees compute
+// allocations, so graphics-only games may not appear there — GAME_PROCS is
+// the reliable path on Windows; on Linux both work.
+func queryComputeApps(ctx context.Context) ([]computeApp, error) {
+	out, err := exec.CommandContext(ctx, "nvidia-smi",
+		"--query-compute-apps=pid,used_memory", "--format=csv,noheader,nounits").Output()
+	if err != nil {
+		return nil, err
+	}
+	return parseComputeApps(string(out))
+}
+
+// parseComputeApps parses "pid, used_memory" CSV lines (no header, MiB
+// units). Unsupported rows ("N/A" on WDDM) are skipped.
+func parseComputeApps(out string) ([]computeApp, error) {
+	var apps []computeApp
+	for _, line := range strings.Split(out, "\n") {
+		line = strings.TrimSpace(line)
+		if line == "" {
+			continue
+		}
+		pidStr, memStr, ok := strings.Cut(line, ",")
+		if !ok {
+			return nil, fmt.Errorf("nvidia-smi: unexpected line %q", line)
+		}
+		pid, err := strconv.Atoi(strings.TrimSpace(pidStr))
+		if err != nil {
+			return nil, fmt.Errorf("nvidia-smi: unexpected pid in %q", line)
+		}
+		mem, err := strconv.Atoi(strings.TrimSpace(memStr))
+		if err != nil {
+			continue // "N/A" and friends: unsupported under WDDM
+		}
+		apps = append(apps, computeApp{PID: pid, UsedMB: mem})
+	}
+	return apps, nil
+}