sgl-project--sglang
94057c3d3e
PR Test (NPU) / check-changes (push) Has been cancelled
PR Test (NPU) / pr-gate (push) Has been cancelled
PR Test (NPU) / set-image-config (push) Has been cancelled
PR Test (NPU) / stage-b-test-1-npu-a2 (0) (push) Has been cancelled
PR Test (NPU) / stage-b-test-1-npu-a2 (1) (push) Has been cancelled
PR Test (NPU) / stage-b-test-2-npu-a2 (0) (push) Has been cancelled
PR Test (NPU) / stage-b-test-2-npu-a2 (1) (push) Has been cancelled
PR Test (NPU) / stage-b-test-4-npu-a3 (push) Has been cancelled
PR Test (NPU) / stage-b-test-16-npu-a3 (push) Has been cancelled
PR Test (NPU) / multimodal-gen-test-1-npu-a3 (push) Has been cancelled
PR Test (NPU) / multimodal-gen-test-2-npu-a3 (push) Has been cancelled
PR Test (Arm64) / pr-gate (push) Has been cancelled
PR Test (Arm64) / check-changes (push) Has been cancelled
PR Test (Arm64) / build-test (push) Has been cancelled
PR Test (sgl-router) / gate (push) Has been cancelled
PR Test (sgl-router) / tier-1 — lint (push) Has been cancelled
PR Test (sgl-router) / tier-2 — build + test (push) Has been cancelled
PR Test (sgl-router) / tier-3 — docker (placeholder) (push) Has been cancelled
PR Test (sgl-router) / tier-3 — k8s integration (push) Has been cancelled
PR Test (sgl-router) / tier-3 — e2e (push) Has been cancelled
PR Test (sgl-router) / finish (push) Has been cancelled
PR Test (NPU) / single-node-poc (map[name:qwen3_6_27b_w8a8_1p_in64k_out1k_50ms runner:linux-aarch64-a3-2 test_case:test/registered/ascend/performance/qwen3_6_27b/test_npu_qwen3_6_27b_w8a8_1p_in64k_out1k_50ms.py test_type:perf]) (push) Has been cancelled
PR Test (NPU) / pr-test-npu-finish (push) Has been cancelled
PR Test (Xeon) / pr-gate (push) Has been cancelled
PR Test (Xeon) / check-changes (push) Has been cancelled
PR Test (Xeon) / build-test (, xeon-gnr, base-b-test-cpu) (push) Has been cancelled
PR Test (XPU) / check-changes (push) Has been cancelled
PR Test (XPU) / pr-gate (push) Has been cancelled
PR Test (XPU) / stage-a-test-1-gpu-xpu (push) Has been cancelled
PR Test (XPU) / wait-for-stage-a (push) Has been cancelled
PR Test (XPU) / stage-b-test-1-gpu-xpu (push) Has been cancelled
PR Test (XPU) / finish (push) Has been cancelled
CI Model Inventory / build-inventory (push) Has been cancelled
Lint / lint (push) Has been cancelled
PR Benchmark (SMG Components) / Benchmark Compilation Check (push) Has been cancelled
PR Benchmark (SMG Components) / Benchmark - Manual Policy (push) Has been cancelled
PR Benchmark (SMG Components) / Benchmark - Request Processing (push) Has been cancelled
PR Benchmark (SMG Components) / Benchmark Summary (push) Has been cancelled
PR Test (SMG) / build-wheel (push) Has been cancelled
Release SGLang Model Gateway to PyPI / build on windows (x86_64 - auto) (push) Has been cancelled
Release SGLang Model Gateway to PyPI / build on macos (x86_64 - auto) (push) Has been cancelled
PR Test (SMG) / python-unit-tests (push) Has been cancelled
PR Test (SMG) / unit-tests (push) Has been cancelled
PR Test (SMG) / benchmarks (push) Has been cancelled
PR Test (SMG) / chat-completions (push) Has been cancelled
PR Test (SMG) / chat-completions-4gpu (push) Has been cancelled
PR Test (SMG) / e2e (push) Has been cancelled
PR Test (SMG) / docker-build-test (push) Has been cancelled
PR Test (SMG) / k8s-integration (push) Has been cancelled
PR Test (SMG) / finish (push) Has been cancelled
PR Test (SMG) / summarize-benchmarks (push) Has been cancelled
Release SGLang Model Gateway Docker Image / publish (push) Has been cancelled
Release SGLang Model Gateway to PyPI / build on macos (aarch64 - auto) (push) Has been cancelled
Release SGLang Model Gateway to PyPI / build on linux (aarch64 - auto) (push) Has been cancelled
Release SGLang Model Gateway to PyPI / build on linux (x86_64 - auto) (push) Has been cancelled
Release SGLang Model Gateway to PyPI / build on linux (aarch64 - musllinux_1_1) (push) Has been cancelled
Release SGLang Model Gateway to PyPI / build on linux (x86_64 - musllinux_1_1) (push) Has been cancelled
Release SGLang Model Gateway to PyPI / Build SDist (push) Has been cancelled
Release SGLang Model Gateway to PyPI / Upload to PyPI (push) Has been cancelled
Release SGLang Kernels / build-cu129-matrix (aarch64, 12.9, 3.10, arm-kernel-build-node) (push) Has been cancelled
Release SGLang Kernels / build-cu129-matrix (x86_64, 12.9, 3.10, x64-kernel-build-node) (push) Has been cancelled
Release SGLang Kernels / release-cu129 (push) Has been cancelled
Release SGLang Kernels / build-cu130-matrix (aarch64, 13.0, 3.10, arm-kernel-build-node) (push) Has been cancelled
Release SGLang Kernels / build-cu130-matrix (x86_64, 13.0, 3.10, x64-kernel-build-node) (push) Has been cancelled
Release SGLang Kernels / release-cu130 (push) Has been cancelled
Release SGLang Kernels / build-rocm-matrix (3.10, 700) (push) Has been cancelled
Release SGLang Kernels / build-rocm-matrix (3.10, 720) (push) Has been cancelled
Release SGLang Kernels / release-rocm700 (push) Has been cancelled
Release SGLang Kernels / release-rocm720 (push) Has been cancelled
Release SGLang Kernels / build-musa43 (43, 3.10) (push) Has been cancelled
Release SGLang Kernels / release-musa43 (push) Has been cancelled
102 行
3.6 KiB
Python
102 行
3.6 KiB
Python
import threading
|
|
import time
|
|
import unittest
|
|
from collections import namedtuple
|
|
from unittest.mock import MagicMock, patch
|
|
|
|
from sglang.test.ci.ci_register import register_cpu_ci
|
|
|
|
register_cpu_ci(est_time=60, suite="base-a-test-cpu", nightly=True)
|
|
register_cpu_ci(est_time=7, suite="base-c-test-cpu")
|
|
|
|
|
|
class TestCpuMonitor(unittest.TestCase):
|
|
def test_cpu_monitor(self):
|
|
from prometheus_client import REGISTRY
|
|
|
|
from sglang.srt.observability.cpu_monitor import start_cpu_monitor_thread
|
|
|
|
thread = start_cpu_monitor_thread("test", interval=0.1)
|
|
self.assertTrue(thread.is_alive())
|
|
self.assertTrue(thread.daemon)
|
|
|
|
end_time = time.monotonic() + 0.3
|
|
while time.monotonic() < end_time:
|
|
_ = sum(i * i for i in range(1000))
|
|
time.sleep(0.2)
|
|
|
|
value = None
|
|
for metric in REGISTRY.collect():
|
|
for sample in metric.samples:
|
|
if (
|
|
sample.name == "sglang:process_cpu_seconds_total"
|
|
and sample.labels.get("component") == "test"
|
|
):
|
|
value = sample.value
|
|
print(f"sglang:process_cpu_seconds_total = {value}")
|
|
self.assertIsNotNone(value)
|
|
self.assertGreater(value, 0)
|
|
|
|
|
|
class TestCpuMonitorMocked(unittest.TestCase):
|
|
"""Fast, deterministic tests for start_cpu_monitor_thread using mocks."""
|
|
|
|
@patch("prometheus_client.Counter")
|
|
@patch("sglang.srt.observability.cpu_monitor.psutil.Process")
|
|
@patch("sglang.srt.observability.cpu_monitor.time.sleep")
|
|
def test_delta_calculation_over_two_iterations(
|
|
self, mock_sleep, MockProcess, MockCounter
|
|
):
|
|
"""Verify delta=(user_diff+system_diff) and last_times update across iterations."""
|
|
from sglang.srt.observability.cpu_monitor import start_cpu_monitor_thread
|
|
|
|
CpuTimes = namedtuple("CpuTimes", ["user", "system"])
|
|
mock_process = MockProcess.return_value
|
|
mock_process.cpu_times.side_effect = [
|
|
CpuTimes(user=1.0, system=0.5), # initial (L18)
|
|
CpuTimes(user=2.5, system=1.0), # iteration 1 (L22)
|
|
CpuTimes(user=4.0, system=2.0), # iteration 2 (L22)
|
|
]
|
|
|
|
# Allow 2 loop iterations, then stop the thread.
|
|
# Override threading.excepthook to suppress the pytest warning from
|
|
# the intentional exception used to terminate the monitor loop.
|
|
remaining = [2]
|
|
orig_hook = threading.excepthook
|
|
|
|
def controlled_sleep(seconds):
|
|
if remaining[0] <= 0:
|
|
raise SystemExit
|
|
remaining[0] -= 1
|
|
|
|
mock_sleep.side_effect = controlled_sleep
|
|
threading.excepthook = lambda args: None
|
|
|
|
mock_labeled = MagicMock()
|
|
MockCounter.return_value.labels.return_value = mock_labeled
|
|
|
|
thread = start_cpu_monitor_thread("my_component", interval=3.0)
|
|
thread.join(timeout=1.0)
|
|
threading.excepthook = orig_hook
|
|
|
|
# Thread is daemon (L29)
|
|
self.assertTrue(thread.daemon)
|
|
|
|
# Sleep called with correct interval (L21)
|
|
mock_sleep.assert_called_with(3.0)
|
|
|
|
# Counter labeled with component (L26)
|
|
MockCounter.return_value.labels.assert_called_with(component="my_component")
|
|
|
|
# Delta calculation (L23-24) and counter increment (L26)
|
|
inc_calls = mock_labeled.inc.call_args_list
|
|
self.assertEqual(len(inc_calls), 2)
|
|
# Iteration 1: (2.5 - 1.0) + (1.0 - 0.5) = 2.0
|
|
self.assertAlmostEqual(inc_calls[0].args[0], 2.0)
|
|
# Iteration 2: (4.0 - 2.5) + (2.0 - 1.0) = 2.5 (proves last_times updated)
|
|
self.assertAlmostEqual(inc_calls[1].args[0], 2.5)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
unittest.main()
|