From aafbf1c1ec7705d5cdea2ef03ed6084a5748e296 Mon Sep 17 00:00:00 2001
From: chengguangran <chengguangran@pjlab.org.cn>
Date: Mon, 10 Aug 2026 16:25:02 +0800
Subject: [PATCH] [Fix] Isolate rollout pause control requests

---
 tests/rl/test_rollout_logic.py     | 34 +++++++++++++++++++++++++++++-
 xtuner/v1/rl/rollout/controller.py |  2 ++
 xtuner/v1/rl/rollout/worker.py     |  2 ++
 3 files changed, 37 insertions(+), 1 deletion(-)

diff --git a/tests/rl/test_rollout_logic.py b/tests/rl/test_rollout_logic.py
index 5b0aa5ad8..4dbdfbeff 100644
--- a/tests/rl/test_rollout_logic.py
+++ b/tests/rl/test_rollout_logic.py
@@ -21,6 +21,7 @@
 
 from xtuner.v1.data_proto.rl_data import RolloutState, SampleParams, Status
 from xtuner.v1.rl.agent_loop import AgentLoopConfig
+from xtuner.v1.rl.rollout.constants import ROLLOUT_RAY_GENERATE_MAX_CONCURRENCY
 from xtuner.v1.rl.rollout.controller import RolloutController
 from xtuner.v1.rl.rollout.health_manager import RolloutHealthManager
 from xtuner.v1.rl.rollout.lmdeploy import LMDeployWorker
@@ -33,7 +34,13 @@
 )
 from xtuner.v1.rl.rollout.sglang import SGLangWorker
 from xtuner.v1.rl.rollout.utils import PartialRolloutHandler, SessionRouter
-from xtuner.v1.rl.rollout.worker import RolloutWorker, RolloutWorkerInitResult
+from xtuner.v1.rl.rollout.worker import (
+    ROLLOUT_CONCURRENCY_GROUP_CONTROL,
+    ROLLOUT_CONCURRENCY_GROUP_GENERATE,
+    RolloutConfig,
+    RolloutWorker,
+    RolloutWorkerInitResult,
+)
 from xtuner.v1.rl.utils.misc import delete_from_routedapiproxy
 from xtuner.v1.rl.weight_update.data import RolloutWeightUpdateInfo
 from xtuner.v1.train.rl_trainer import BaseRLTrainer, _agent_loop_manager_requires_rollout_proxy
@@ -316,6 +323,31 @@ def test_sglang_tp16_cross_node_weight_update_targets_match_legacy_mesh_and_url_
 
 
 class TestRolloutController(unittest.IsolatedAsyncioTestCase):
+    def test_pause_generation_uses_dedicated_control_concurrency_group(self):
+        self.assertEqual(
+            getattr(RolloutController.pause_generation, "__ray_concurrency_group__", None),
+            ROLLOUT_CONCURRENCY_GROUP_CONTROL,
+        )
+
+    def test_rollout_config_build_registers_control_concurrency_group(self):
+        remote_actor_cls = MagicMock()
+        remote_actor_cls.options.return_value.remote.return_value = "rollout-controller"
+
+        with (
+            patch("xtuner.v1.rl.rollout.worker.register_cpu_resources"),
+            patch("xtuner.v1.rl.trace.get_trace_env_vars", return_value={}),
+            patch("ray.remote", return_value=lambda _: remote_actor_cls) as ray_remote,
+        ):
+            result = RolloutConfig.build(MagicMock(), placement_group=object())
+
+        self.assertEqual(result, "rollout-controller")
+        ray_remote.assert_called_once_with(
+            concurrency_groups={
+                ROLLOUT_CONCURRENCY_GROUP_GENERATE: ROLLOUT_RAY_GENERATE_MAX_CONCURRENCY,
+                ROLLOUT_CONCURRENCY_GROUP_CONTROL: 1,
+            },
+        )
+
     def _state(self, uid: int, session_id: int) -> RolloutState:
         return RolloutState(
             rollout_id=uid,
diff --git a/xtuner/v1/rl/rollout/controller.py b/xtuner/v1/rl/rollout/controller.py
index cee7d7c6e..e4484f21c 100644
--- a/xtuner/v1/rl/rollout/controller.py
+++ b/xtuner/v1/rl/rollout/controller.py
@@ -18,6 +18,7 @@
 from .rollout_topology import RolloutTopology
 from .utils import SessionRouter
 from .worker import (
+    ROLLOUT_CONCURRENCY_GROUP_CONTROL,
     ROLLOUT_CONCURRENCY_GROUP_GENERATE,
     RolloutConfig,
     get_rollout_worker_base_cls,
@@ -131,6 +132,7 @@ def set_enable_partial_rollout(self, enable: bool) -> None:
             ]
         )
 
+    @ray.method(concurrency_group=ROLLOUT_CONCURRENCY_GROUP_CONTROL)
     def pause_generation(self):
         self.health_manager.pause()
         active_workers = self.registry.active_workers()
diff --git a/xtuner/v1/rl/rollout/worker.py b/xtuner/v1/rl/rollout/worker.py
index 547fd31d9..98ba12bd3 100644
--- a/xtuner/v1/rl/rollout/worker.py
+++ b/xtuner/v1/rl/rollout/worker.py
@@ -54,6 +54,7 @@
 
 infer_group = Group("inference", help="Inference worker configuration.")
 ROLLOUT_CONCURRENCY_GROUP_GENERATE = "generate"
+ROLLOUT_CONCURRENCY_GROUP_CONTROL = "control"
 
 
 @dataclass(frozen=True)
@@ -500,6 +501,7 @@ def build(self, placement_group: "PlacementGroup"):
             ray.remote(
                 concurrency_groups={
                     ROLLOUT_CONCURRENCY_GROUP_GENERATE: ROLLOUT_RAY_GENERATE_MAX_CONCURRENCY,
+                    ROLLOUT_CONCURRENCY_GROUP_CONTROL: 1,
                 },
             )(RolloutController)
             .options(**actor_options)