[serve] Replace uuid.uuid4() with getrandbits

python/ray/serve/_private/router.py

@@ -3,7 +3,6 @@
 import logging
 import threading
 import time
-import uuid
 from abc import ABC, abstractmethod
 from collections import defaultdict
 from contextlib import contextmanager
@@ -31,7 +30,7 @@
 from ray.serve._private.metrics_utils import InMemoryMetricsStore, MetricsPusher
 from ray.serve._private.replica_result import ReplicaResult
 from ray.serve._private.replica_scheduler import PendingRequest, ReplicaScheduler
-from ray.serve._private.utils import resolve_deployment_response
+from ray.serve._private.utils import generate_request_id, resolve_deployment_response
 from ray.serve.config import AutoscalingConfig
 from ray.serve.exceptions import BackPressureError
 from ray.util import metrics
@@ -564,7 +563,7 @@ async def assign_request(
     ) -> ReplicaResult:
         """Assign a request to a replica and return the resulting object_ref."""
 
-        response_id = uuid.uuid4()
+        response_id = generate_request_id()
         assign_request_task = asyncio.current_task()
         ray.serve.context._add_request_pending_assignment(
             request_meta.internal_request_id, response_id, assign_request_task

python/ray/serve/_private/utils.py

@@ -542,7 +542,11 @@ def get_capacity_adjusted_num_replicas(
 
 
 def generate_request_id() -> str:
-    return str(uuid.uuid4())
+    # NOTE(edoakes): we use random.getrandbits because it reduces CPU overhead
+    # significantly. This is less cryptographically secure but should be ok for
+    # request ID generation.
+    # See https://bugs.python.org/issue45556 for discussion.
+    return str(uuid.UUID(int=random.getrandbits(128), version=4))
 
 
 def inside_ray_client_context() -> bool:

python/ray/serve/tests/test_http_headers.py

@@ -11,6 +11,7 @@
 
 import ray
 from ray import serve
+from ray.serve._private.utils import generate_request_id
 
 
 def test_request_id_header_by_default(serve_instance):
@@ -154,10 +155,10 @@ async def main():
         """Sending 20 requests in parallel all with the same request id, but with
         different request body.
         """
-        bodies = [{"app_name": f"an_{uuid.uuid4()}"} for _ in range(20)]
+        bodies = [{"app_name": f"an_{generate_request_id()}"} for _ in range(20)]
         connector = TCPConnector(ssl=False)
         async with aiohttp.ClientSession(connector=connector) as session:
-            request_id = f"rid_{uuid.uuid4()}"
+            request_id = f"rid_{generate_request_id()}"
             tasks = [
                 send_request(session, body, request_id=request_id) for body in bodies
             ]

python/ray/serve/tests/unit/test_pow_2_replica_scheduler.py

@@ -4,7 +4,6 @@
 import random
 import sys
 import time
-import uuid
 from typing import Optional, Set
 
 import pytest
@@ -29,6 +28,7 @@
 )
 from ray.serve._private.replica_scheduler.pow_2_scheduler import ReplicaQueueLengthCache
 from ray.serve._private.test_utils import MockTimer
+from ray.serve._private.utils import generate_request_id
 
 TIMER = MockTimer()
 
@@ -184,8 +184,8 @@ def fake_pending_request(
             args=list(),
             kwargs=dict(),
             metadata=RequestMetadata(
-                request_id=str(uuid.uuid4()),
-                internal_request_id=str(uuid.uuid4()),
+                request_id=generate_request_id(),
+                internal_request_id=generate_request_id(),
                 multiplexed_model_id=model_id,
             ),
             created_at=created_at,
@@ -195,8 +195,8 @@ def fake_pending_request(
             args=list(),
             kwargs=dict(),
             metadata=RequestMetadata(
-                request_id=str(uuid.uuid4()),
-                internal_request_id=str(uuid.uuid4()),
+                request_id=generate_request_id(),
+                internal_request_id=generate_request_id(),
                 multiplexed_model_id=model_id,
             ),
         )