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

internal/lock/lock.go

@@ -1,6 +1,8 @@
 // Package lock implements the two-mode GPU arbitration lock: any number of
 // concurrent LLM requests ("readers") or exactly one image job ("writer"),
-// with image jobs taking priority over newly arriving LLM requests.
+// with image jobs taking priority over newly arriving LLM requests. An
+// external hold (SetExternal) blocks new grants of both kinds while a
+// foreign process — e.g. a game — holds the GPU; in-flight work drains.
 package lock
 
 import (
@@ -13,9 +15,10 @@ import (
 type State string
 
 const (
-	StateIdle  State = "idle"
-	StateLLM   State = "llm"
-	StateImage State = "image"
+	StateIdle     State = "idle"
+	StateLLM      State = "llm"
+	StateImage    State = "image"
+	StateExternal State = "external"
 )
 
 type imageWaiter struct{ id uint64 }
@@ -30,6 +33,7 @@ type Lock struct {
 	imageActive bool // an image job holds the GPU
 	imageQ      []imageWaiter
 	nextID      uint64
+	external    string // non-empty: a foreign process (e.g. a game) holds the GPU
 
 	log *slog.Logger
 }
@@ -52,12 +56,41 @@ func (l *Lock) logTransition(msg string, args ...any) {
 	}
 }
 
+// SetExternal records that a process outside gpu-turnstile's control (a
+// game, another ML job) holds the GPU: new LLM and image grants block until
+// ClearExternal. In-flight work is not preempted. holder describes the
+// process for logs and busy responses.
+func (l *Lock) SetExternal(holder string) {
+	l.mu.Lock()
+	l.external = holder
+	l.broadcast()
+	l.mu.Unlock()
+	l.logTransition("lock transition", "state", StateExternal, "holder", holder)
+}
+
+// ClearExternal lifts the external hold; waiting LLM and image requests
+// proceed.
+func (l *Lock) ClearExternal() {
+	l.mu.Lock()
+	l.external = ""
+	l.broadcast()
+	l.mu.Unlock()
+	l.logTransition("lock transition", "state", StateIdle)
+}
+
+// External returns the current external holder, or "" when none.
+func (l *Lock) External() string {
+	l.mu.Lock()
+	defer l.mu.Unlock()
+	return l.external
+}
+
 // AcquireLLM blocks until no image job is active or pending, then registers
 // one in-flight LLM request. Returns ctx.Err() if the context is cancelled
 // while waiting; no state is changed in that case.
 func (l *Lock) AcquireLLM(ctx context.Context) error {
 	l.mu.Lock()
-	for l.imageActive || len(l.imageQ) > 0 {
+	for l.imageActive || len(l.imageQ) > 0 || l.external != "" {
 		ch := l.change
 		l.mu.Unlock()
 		select {
@@ -76,10 +109,10 @@ func (l *Lock) AcquireLLM(ctx context.Context) error {
 
 // TryAcquireLLM acquires one in-flight LLM slot without waiting and
 // reports whether it succeeded. It fails when an image job is active or
-// pending.
+// pending or an external hold is set.
 func (l *Lock) TryAcquireLLM() bool {
 	l.mu.Lock()
-	if l.imageActive || len(l.imageQ) > 0 {
+	if l.imageActive || len(l.imageQ) > 0 || l.external != "" {
 		l.mu.Unlock()
 		return false
 	}
@@ -120,7 +153,7 @@ func (l *Lock) AcquireImage(ctx context.Context) error {
 
 	for {
 		l.mu.Lock()
-		if l.imageQ[0].id == w.id && l.n == 0 && !l.imageActive {
+		if l.imageQ[0].id == w.id && l.n == 0 && !l.imageActive && l.external == "" {
 			l.imageQ = l.imageQ[1:]
 			l.imageActive = true
 			l.mu.Unlock()
@@ -166,6 +199,8 @@ func (l *Lock) Snapshot() (state State, llmInflight int, imagePending bool) {
 		state = StateImage
 	case l.n > 0:
 		state = StateLLM
+	case l.external != "":
+		state = StateExternal
 	default:
 		state = StateIdle
 	}

internal/lock/lock_test.go

@@ -226,3 +226,70 @@ func TestRace(t *testing.T) {
 		t.Fatalf("leaked lock state: state=%s n=%d pending=%v", state, n, pending)
 	}
 }
+
+func TestExternalHoldBlocksBoth(t *testing.T) {
+	lk := New(nil)
+	ctx := context.Background()
+
+	lk.SetExternal("game.exe (pid 42)")
+	if lk.TryAcquireLLM() {
+		t.Fatal("TryAcquireLLM succeeded during external hold")
+	}
+	if got := lk.External(); got != "game.exe (pid 42)" {
+		t.Fatalf("External() = %q", got)
+	}
+	if state, _, _ := lk.Snapshot(); state != StateExternal {
+		t.Fatalf("state=%s, want external", state)
+	}
+
+	llmAcquired := make(chan struct{})
+	go func() {
+		if err := lk.AcquireLLM(ctx); err != nil {
+			t.Error(err)
+		}
+		close(llmAcquired)
+	}()
+	assertBlocked(t, llmAcquired, "LLM acquire during external hold")
+
+	imageAcquired := make(chan struct{})
+	go func() {
+		if err := lk.AcquireImage(ctx); err != nil {
+			t.Error(err)
+		}
+		close(imageAcquired)
+	}()
+	assertBlocked(t, imageAcquired, "image acquire during external hold")
+
+	lk.ClearExternal()
+	// The queued image job wins over the LLM waiter (image priority).
+	waitFor(t, imageAcquired, "image acquire after ClearExternal")
+	assertBlocked(t, llmAcquired, "LLM acquire while image active")
+	lk.ReleaseImage()
+	waitFor(t, llmAcquired, "LLM acquire after image release")
+	lk.ReleaseLLM()
+}
+
+func TestExternalHoldDoesNotPreempt(t *testing.T) {
+	lk := New(nil)
+	ctx := context.Background()
+	if err := lk.AcquireLLM(ctx); err != nil {
+		t.Fatal(err)
+	}
+
+	lk.SetExternal("game.exe")
+	// In-flight LLM work keeps the llm state; the hold blocks new grants.
+	if state, _, _ := lk.Snapshot(); state != StateLLM {
+		t.Fatalf("state=%s, want llm while work in flight", state)
+	}
+	if lk.TryAcquireLLM() {
+		t.Fatal("TryAcquireLLM succeeded during external hold")
+	}
+	lk.ReleaseLLM()
+	if state, _, _ := lk.Snapshot(); state != StateExternal {
+		t.Fatalf("state=%s, want external after drain", state)
+	}
+	lk.ClearExternal()
+	if state, _, _ := lk.Snapshot(); state != StateIdle {
+		t.Fatalf("state=%s, want idle", state)
+	}
+}