kali20gakki/msAgent / skills/host-cpu/msagent-perf-cpu-config-audit
msagent-perf-cpu-config-audit
Verified昇腾训练/推理主机的环境配置体检:对 NUMA 亲和、大页/THP、governor 频率、cgroup 限流、IRQ smp_affinity、环境变量等 8 个配置域做单点快照审计,输出分级 Finding 与可回滚修改建议,不改动运行状态。触发:检查环境、配置体检、新机器开箱、换容器、 大页没配、governor 不对、cgroup 限流、中断亲和配置、NUMA 配置检查、绑核没生效。 不用于:训练变慢/step 抖动/利用率低的根因归因(→ perf-cpu-perf-triage); 产出绑核方案(→ perf-cpu-bind-tune);运行期实际落核观测(→ perf-cpu-tracing)。
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 5.2 KB |
| references/check-items.md | markdown | 6.5 KB |
| references/process-roles.md | markdown | 1.7 KB |
| references/profiles/ascend910.json | config | 1.6 KB |
| references/profiles/kunpeng920-910b.json | config | 507 B |
| references/rules-locality.md | markdown | 2.3 KB |
| resources/report_template.html | other | 11.5 KB |
| scripts/audit.py | script | 19.6 KB |
| scripts/baseline.py | script | 4.4 KB |
| scripts/checker.py | script | 39.6 KB |
| scripts/classify.py | script | 2.7 KB |
| scripts/discover.py | script | 6.6 KB |
| scripts/npu_query.py | script | 15.0 KB |
| scripts/preflight.py | script | 3.3 KB |
| scripts/procfs.py | script | 9.0 KB |
| scripts/report.py | script | 6.4 KB |
| scripts/rules_locality.py | script | 8.7 KB |
| scripts/static_collect.py | script | 13.8 KB |
| scripts/topology.py | script | 9.4 KB |
| scripts/workspace.py | script | 2.1 KB |
scripts/baseline.py
View on GitHub# -------------------------------------------------------------------------
# This file is part of the MindStudio project.
# Copyright (c) 2026 Huawei Technologies Co.,Ltd.
#
# MindStudio is licensed under Mulan PSL v2.
# You can use this software according to the terms and conditions of the Mulan PSL v2.
# You may obtain a copy of Mulan PSL v2 at:
#
# http://license.coscl.org.cn/MulanPSL2
#
# THIS SOFTWARE IS PROVIDED ON AN "AS IS" BASIS, WITHOUT WARRANTIES OF ANY KIND,
# EITHER EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO NON-INFRINGEMENT,
# MERCHANTABILITY OR FIT FOR A PARTICULAR PURPOSE.
# See the Mulan PSL v2 for more details.
# -------------------------------------------------------------------------
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""baseline.py — hostcpu-baseline.json 归档与 diff 对比。
基线内容 = 8 域配置原始值(可回滚依据 + 复检对比)。只落 JSON,无 DB。
"""
from __future__ import annotations
import json
import os
from typing import Any, Dict, List
# 纳入基线的配置事实项(可回滚的配置项)
BASELINE_ITEMS = (
"numa_balancing", "zone_reclaim_mode", "swappiness", "overcommit_memory",
"thp_enabled", "thp_defrag", "hugepages_total", "hugepages_free",
"scaling_governor", "epp", "cstates", "cmdline_boot_params",
"cpuset_cpus_effective", "cpuset_mems_effective", "cpu_max",
"cpu_stat_throttled", "cgroup_version",
)
def build_baseline(facts: List[Dict[str, Any]]) -> Dict[str, Any]:
"""从 facts 提取配置原始值生成基线。"""
values: Dict[str, Any] = {}
for fact in facts:
if fact.get("item") in BASELINE_ITEMS:
values[fact["item"]] = fact.get("value")
return {
"type": "hostcpu-baseline",
"version": 1,
"values": values,
}
def save_baseline(baseline: Dict[str, Any], path: str) -> str:
"""基线落盘(路径由主入口生成的会话目录内,非用户任意路径)。"""
parent = os.path.dirname(path)
if parent:
os.makedirs(parent, exist_ok=True)
with open(path, "w", encoding="utf-8") as fh:
json.dump(baseline, fh, ensure_ascii=False, indent=2)
return path
def load_baseline(path: str) -> Dict[str, Any]:
if not path or not os.path.isfile(path):
return {}
try:
with open(path, "r", encoding="utf-8") as fh:
data = json.load(fh)
return data if isinstance(data, dict) else {}
except (OSError, ValueError):
return {}
# 每个配置项的优劣值域独立定义:同一取值在不同 key 下方向相反(如 numa_balancing
# 与 zone_reclaim_mode 的 0/1 语义相反),不能跨 key 共用一个值集合
_DIRECTION_RULES: Dict[str, tuple] = {
"scaling_governor": ({"performance", "balance_performance"}, {"powersave", "balance_power"}),
"thp_enabled": ({"madvise", "always"}, {"never"}),
"thp_defrag": ({"madvise", "defer", "defer+madvise"}, {"always"}),
"numa_balancing": ({"0"}, {"1"}),
"zone_reclaim_mode": ({"0"}, {"1"}),
}
def _direction_value(key: str, value: Any) -> str:
"""scaling_governor 记录为 {governor: count},取占比最高的 governor 作为方向依据。"""
if key == "scaling_governor" and isinstance(value, dict) and value:
return str(max(value.items(), key=lambda kv: kv[1])[0])
return str(value)
def _direction(key: str, old: Any, new: Any) -> str:
rule = _DIRECTION_RULES.get(key)
if rule is None:
return "changed"
good_values, bad_values = rule
old_value, new_value = _direction_value(key, old), _direction_value(key, new)
if new_value in good_values and old_value in bad_values:
return "improved"
if new_value in bad_values and old_value in good_values:
return "degraded"
return "changed"
def diff_baseline(current: Dict[str, Any], previous: Dict[str, Any]) -> List[Dict[str, Any]]:
"""与上轮基线对比:改善 / 恶化 / 变化。
判定规则:本轮值 vs 上轮值,按配置项自身的值域语义给方向。
"""
diffs: List[Dict[str, Any]] = []
prev_values = previous.get("values", {})
curr_values = current.get("values", {})
for key in sorted(set(prev_values) & set(curr_values)):
old, new = prev_values[key], curr_values[key]
if old == new:
continue
diffs.append({"item": key, "old": old, "new": new,
"direction": _direction(key, old, new)})
return diffs
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |