From 3701f34dabebb0e765e70721795a9e6d111adb47 Mon Sep 17 00:00:00 2001
From: fzyzcjy <5236035+fzyzcjy@users.noreply.github.com>
Date: Fri, 14 Nov 2025 17:34:22 +0800
Subject: [PATCH] Tiny add utility to parse server logs (#12605)

---
 python/sglang/srt/debug_utils/log_parser.py | 46 +++++++++++++++++++++
 test/srt/debug_utils/test_log_parser.py     | 28 +++++++++++++
 2 files changed, 74 insertions(+)
 create mode 100644 python/sglang/srt/debug_utils/log_parser.py
 create mode 100644 test/srt/debug_utils/test_log_parser.py

diff --git a/python/sglang/srt/debug_utils/log_parser.py b/python/sglang/srt/debug_utils/log_parser.py
new file mode 100644
index 000000000..2fac51269
--- /dev/null
+++ b/python/sglang/srt/debug_utils/log_parser.py
@@ -0,0 +1,46 @@
+_PATTERN_DECODE = (
+    r"(\(\w+ pid=(?P<pid>\d+)(?:,\s*ip=(?P<ip>[\d\.]+))?\))?\s*"
+    r"\[(?P<time>\d{4}-\d{2}-\d{2} \d{2}:\d{2}:\d{2})"
+    r"(?:\s+DP(?P<dp_rank>\d+))?"
+    r"(?:\s+TP(?P<tp_rank>\d+))?"
+    r"(?:\s+EP(?P<ep_rank>\d+))?"
+    r"(?:\s+PP(?P<pp_rank>\d+))?"
+    r"\]\s+"
+    r"Decode batch( \[\d+\])?,\s+"
+    r"#running-req:\s*(?P<num_running_req>\d+),\s+"
+    r"#token:\s*(?P<num_token>\d+),\s+"
+    r"token usage:\s*(?P<token_usage>[0-9.]+),\s+"
+    r".*?"
+    r"gen throughput \(token/s\):\s*(?P<gen_throughput>[0-9.]+),\s+"
+    r"#queue-req:\s*(?P<queue_req>\d+),"
+)
+
+
+def parse(lines):
+    import polars as pl
+
+    df = pl.DataFrame(dict(line=lines.splitlines()))
+    df = df.with_columns(info=pl.col("line").str.extract_groups(_PATTERN_DECODE))
+    df = df.unnest("info")
+    df = df.filter(pl.col("gen_throughput").is_not_null())
+
+    df = df.with_columns(
+        pl.col("time").str.strptime(pl.Datetime, "%Y-%m-%d %H:%M:%S"),
+        *[
+            pl.col(col).cast(dtype)
+            for col, dtype in [
+                ("pid", pl.Int64),
+                ("dp_rank", pl.Int64),
+                ("tp_rank", pl.Int64),
+                ("ep_rank", pl.Int64),
+                ("pp_rank", pl.Int64),
+                ("num_running_req", pl.Int64),
+                ("num_token", pl.Int64),
+                ("token_usage", pl.Float64),
+                ("gen_throughput", pl.Float64),
+                ("queue_req", pl.Int64),
+            ]
+            if col in df.columns
+        ],
+    )
+    return df
diff --git a/test/srt/debug_utils/test_log_parser.py b/test/srt/debug_utils/test_log_parser.py
new file mode 100644
index 000000000..af5e496d8
--- /dev/null
+++ b/test/srt/debug_utils/test_log_parser.py
@@ -0,0 +1,28 @@
+import json
+import unittest
+
+from sglang.srt.debug_utils import log_parser
+from sglang.test.test_utils import CustomTestCase
+
+
+class TestLogParser(CustomTestCase):
+    def test_log_parser(self):
+        lines = """
+(SGLangEngine pid=35555) [2025-10-31 03:45:20 TP0] Decode batch [51341], #running-req: 317, #token: 1094261, token usage: 0.67, cuda graph: True, gen throughput (token/s): 14806.57, #queue-req: 0,
+(SGLangEngine pid=111711, ip=10.15.36.1) [2025-10-31 03:45:20 TP0] Decode batch [39913], #running-req: 78, #token: 432100, token usage: 0.27, cuda graph: True, gen throughput (token/s): 7269.16, #queue-req: 0,
+[2025-11-03 14:31:10 DP6 TP6 EP6] Decode batch, #running-req: 251, #token: 2811200, token usage: 1.00, cuda graph: True, gen throughput (token/s): 2055.94, #queue-req: 655,
+"""
+        expect_rows = json.loads(
+            """[{"line":"(SGLangEngine pid=35555) [2025-10-31 03:45:20 TP0] Decode batch [51341], #running-req: 317, #token: 1094261, token usage: 0.67, cuda graph: True, gen throughput (token/s): 14806.57, #queue-req: 0,","1":"(SGLangEngine pid=35555)","pid":35555,"ip":null,"time":"2025-10-31 03:45:20","dp_rank":null,"tp_rank":0,"ep_rank":null,"pp_rank":null,"9":" [51341]","num_running_req":317,"num_token":1094261,"token_usage":0.67,"gen_throughput":14806.57,"queue_req":0},{"line":"(SGLangEngine pid=111711, ip=10.15.36.1) [2025-10-31 03:45:20 TP0] Decode batch [39913], #running-req: 78, #token: 432100, token usage: 0.27, cuda graph: True, gen throughput (token/s): 7269.16, #queue-req: 0,","1":"(SGLangEngine pid=111711, ip=10.15.36.1)","pid":111711,"ip":"10.15.36.1","time":"2025-10-31 03:45:20","dp_rank":null,"tp_rank":0,"ep_rank":null,"pp_rank":null,"9":" [39913]","num_running_req":78,"num_token":432100,"token_usage":0.27,"gen_throughput":7269.16,"queue_req":0},{"line":"[2025-11-03 14:31:10 DP6 TP6 EP6] Decode batch, #running-req: 251, #token: 2811200, token usage: 1.00, cuda graph: True, gen throughput (token/s): 2055.94, #queue-req: 655,","1":null,"pid":null,"ip":null,"time":"2025-11-03 14:31:10","dp_rank":6,"tp_rank":6,"ep_rank":6,"pp_rank":null,"9":null,"num_running_req":251,"num_token":2811200,"token_usage":1.0,"gen_throughput":2055.94,"queue_req":655}]""",
+        )
+
+        df = log_parser.parse(lines)
+        print(df)
+        print(df.write_json())
+
+        assert len(df) == len(lines.strip().splitlines()), f"{len(df)=}"
+        self.assertEqual(json.loads(df.write_json()), expect_rows)
+
+
+if __name__ == "__main__":
+    unittest.main()