From 8cfdb0466e1cb79f0b6dde504c9c781e9da5918e Mon Sep 17 00:00:00 2001
From: laoyao0822 <laoyao0822@qq.com>
Date: Thu, 11 Jun 2026 05:49:05 +0800
Subject: [PATCH] Reduce CP per-layer transfer success-log noise

Per-layer prefill-to-decode transfer now finishes per request/rank/chunk, so success-path INFO logs can dominate production logs and hide actual failures. Keep successful finish breakdown and completion messages at DEBUG while preserving nonzero finish status as WARNING.

Constraint: Per-layer transfer is a hot path under CP shared-KV and may produce many batch completions per request.

Rejected: Disable CP per-layer transfer logging entirely | failures still need visible warning-level evidence.

Confidence: high

Scope-risk: narrow

Directive: Do not promote successful per-request transfer completion logs back to INFO without rate limiting.

Tested: PYTHONPATH=python python -m pytest -q test/registered/unit/disaggregation/test_cp_per_layer_transfer.py::TestPerLayerTransferContext::test_successful_finish_does_not_emit_hot_path_info_log

Tested: python -m py_compile python/sglang/srt/disaggregation/cp_per_layer_transfer.py python/sglang/srt/disaggregation/mooncake/conn.py

Not-tested: Full local disaggregation suite blocked by missing local orjson dependency.

Co-authored-by: OmX <omx@oh-my-codex.dev>
---
 .../srt/disaggregation/cp_per_layer_transfer.py |  4 ++--
 .../sglang/srt/disaggregation/mooncake/conn.py  | 17 ++++++++++++-----
 .../test_cp_per_layer_transfer.py               | 16 ++++++++++++++++
 3 files changed, 30 insertions(+), 7 deletions(-)

diff --git a/python/sglang/srt/disaggregation/cp_per_layer_transfer.py b/python/sglang/srt/disaggregation/cp_per_layer_transfer.py
index 557384f80..9de1617cb 100644
--- a/python/sglang/srt/disaggregation/cp_per_layer_transfer.py
+++ b/python/sglang/srt/disaggregation/cp_per_layer_transfer.py
@@ -186,8 +186,8 @@ class PerLayerTransferContext:
             batch_ids = list(self._batch_ids)
         wait_status = self.engine.wait_batch_transfers(batch_ids)
         t3 = time.perf_counter()  # RDMA complete
-        if logger.isEnabledFor(logging.INFO):
-            logger.info(
+        if logger.isEnabledFor(logging.DEBUG):
+            logger.debug(
                 "[CP_PER_LAYER_TRANSFER] finish breakdown: target=%d submitted_at_entry=%d "
                 "missing=%d wait_workers=%.1fms fallback=%.1fms wait_rdma=%.1fms total=%.1fms",
                 target,
diff --git a/python/sglang/srt/disaggregation/mooncake/conn.py b/python/sglang/srt/disaggregation/mooncake/conn.py
index 9bfda8089..1564aeb42 100644
--- a/python/sglang/srt/disaggregation/mooncake/conn.py
+++ b/python/sglang/srt/disaggregation/mooncake/conn.py
@@ -1280,11 +1280,18 @@ class MooncakeKVManager(CommonKVManager):
                             # with the forward; wait those transfers here instead of the
                             # monolithic send (no double-send). aux/state below unchanged.
                             ret = per_layer_mgr.finish(kv_chunk.room)
-                            logger.info(
-                                "[CP_PER_LAYER_TRANSFER] finished room=%s ret=%s",
-                                kv_chunk.room,
-                                ret,
-                            )
+                            if ret != 0:
+                                logger.warning(
+                                    "[CP_PER_LAYER_TRANSFER] finished room=%s ret=%s",
+                                    kv_chunk.room,
+                                    ret,
+                                )
+                            else:
+                                logger.debug(
+                                    "[CP_PER_LAYER_TRANSFER] finished room=%s ret=%s",
+                                    kv_chunk.room,
+                                    ret,
+                                )
                         elif self.is_mla_backend or (
                             self.attn_tp_size
                             == target_rank_registration_info.dst_attn_tp_size
diff --git a/test/registered/unit/disaggregation/test_cp_per_layer_transfer.py b/test/registered/unit/disaggregation/test_cp_per_layer_transfer.py
index dd87e7879..78555008c 100644
--- a/test/registered/unit/disaggregation/test_cp_per_layer_transfer.py
+++ b/test/registered/unit/disaggregation/test_cp_per_layer_transfer.py
@@ -10,6 +10,7 @@ Key correctness properties:
 Engine and CUDA events are mocked — no GPU/RDMA.
 """
 import unittest
+from unittest import mock
 
 from sglang.srt.disaggregation.cp_per_layer_transfer import PerLayerTransferContext
 
@@ -128,6 +129,21 @@ class TestPerLayerTransferContext(unittest.TestCase):
         self.assertEqual(eng.waits[-1], [101, 102])
         self.assertEqual(eng.submits[1], ("sess", [1000, 2000], [6000, 7000], [64, 64]))
 
+    def test_successful_finish_does_not_emit_hot_path_info_log(self):
+        # Successful per-request transfer completion is hot-path and can fire once per
+        # request/rank/chunk. It must not emit INFO logs by default.
+        eng = _FakeEngine()
+        ctx = _ctx(eng, num_layers=1)
+        ctx.submit_layer(0, None)
+        with mock.patch(
+            "sglang.srt.disaggregation.cp_per_layer_transfer.logger.isEnabledFor",
+            return_value=True,
+        ), mock.patch(
+            "sglang.srt.disaggregation.cp_per_layer_transfer.logger.info"
+        ) as info:
+            self.assertEqual(ctx.finish(timeout=0.5), 0)
+        info.assert_not_called()
+
     def test_failed_submit_still_reported_after_fallback(self):
         # layer 2 submit fails during the overlap; finish reports -1 even though it
         # also runs the fallback for any unfired layers.