- Installs
- 63
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/chaterm/terminal-skills --skill benchmarking- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads benchmarking automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
性能基准测试
概述
压力测试、基准测试工具使用技能。
sysbench
安装
# Debian/Ubuntu
apt install sysbench
# CentOS/RHEL
yum install sysbench
CPU 测试
# 单线程
sysbench cpu run
# 多线程
sysbench cpu --threads=4 run
# 指定时间
sysbench cpu --threads=4 --time=60 run
内存测试
# 顺序读写
sysbench memory run
# 随机读写
sysbench memory --memory-access-mode=rnd run
# 指定大小
sysbench memory --memory-block-size=1M --memory-total-size=10G run
磁盘 IO 测试
# 准备测试文件
sysbench fileio --file-total-size=10G prepare
# 随机读写
sysbench fileio --file-total-size=10G --file-test-mode=rndrw run
# 顺序读
sysbench fileio --file-total-size=10G --file-test-mode=seqrd run
# 清理
sysbench fileio --file-total-size=10G cleanup
MySQL 测试
# 准备数据
sysbench oltp_read_write --mysql-host=localhost --mysql-user=root \
--mysql-password=pass --mysql-db=test --tables=10 --table-size=100000 prepare
# 运行测试
sysbench oltp_read_write --mysql-host=localhost --mysql-user=root \
--mysql-password=pass --mysql-db=test --tables=10 --table-size=100000 \
--threads=16 --time=60 run
# 清理
sysbench oltp_read_write --mysql-host=localhost --mysql-user=root \
--mysql-password=pass --mysql-db=test cleanup
fio 磁盘测试
基础测试
# 顺序读
fio --name=seqread --rw=read --bs=1M --size=1G --numjobs=1 --runtime=60
# 顺序写
fio --name=seqwrite --rw=write --bs=1M --size=1G --numjobs=1 --runtime=60
# 随机读
fio --name=randread --rw=randread --bs=4k --size=1G --numjobs=4 --runtime=60
# 随机写
fio --name=randwrite --rw=randwrite --bs=4k --size=1G --numjobs=4 --runtime=60
# 混合读写
fio --name=randrw --rw=randrw --bs=4k --size=1G --numjobs=4 --rwmixread=70 --runtime=60
配置文件
# test.fio
[global]
ioengine=libaio
direct=1
runtime=60
time_based
[seqread]
rw=read
bs=1M
size=1G
[randread]
rw=randread
bs=4k
size=1G
numjobs=4
fio test.fio
HTTP 压测
ab (Apache Bench)
# 基础测试
ab -n 1000 -c 100 http://localhost/
# 带 Keep-Alive
ab -n 1000 -c 100 -k http://localhost/
# POST 请求
ab -n 1000 -c 100 -p data.json -T application/json http://localhost/api
wrk
# 基础测试
wrk -t4 -c100 -d30s http://localhost/
# 带脚本
wrk -t4 -c100 -d30s -s post.lua http://localhost/api
hey
# 基础测试
hey -n 1000 -c 100 http://localhost/
# 指定时间
hey -z 30s -c 100 http://localhost/
# POST 请求
hey -n 1000 -c 100 -m POST -d '{"key":"value"}' http://localhost/api
网络测试
iperf3
# 服务端
iperf3 -s
# 客户端
iperf3 -c server_ip
# UDP 测试
iperf3 -c server_ip -u -b 1G
# 双向测试
iperf3 -c server_ip -d
# 多线程
iperf3 -c server_ip -P 4
netperf
# 服务端
netserver
# TCP 吞吐
netperf -H server_ip
# TCP 延迟
netperf -H server_ip -t TCP_RR
常见场景
场景 1：服务器基准测试
#!/bin/bash
echo "=== CPU 测试 ==="
sysbench cpu --threads=$(nproc) --time=30 run
echo "=== 内存测试 ==="
sysbench memory --threads=$(nproc) --time=30 run
echo "=== 磁盘测试 ==="
fio --name=test --rw=randrw --bs=4k --size=1G --runtime=30 --time_based
场景 2：数据库基准
#!/bin/bash
# MySQL OLTP 测试
sysbench oltp_read_write \
--mysql-host=localhost \
--mysql-user=root \
--mysql-password=pass \
--mysql-db=sbtest \
--tables=10 \
--table-size=100000 \
--threads=16 \
--time=300 \
--report-interval=10 \
run
结果解读
| 指标 | 说明 |
|---|---|
| TPS | 每秒事务数 |
| QPS | 每秒查询数 |
| IOPS | 每秒 IO 操作数 |
| 延迟 | 响应时间 |
| 吞吐量 | 数据传输速率 |
故障排查
# 检查系统负载
uptime
vmstat 1
# 检查 IO
iostat -x 1
# 检查网络
sar -n DEV 1
FAQ
What does the benchmarking skill do?
性能基准测试
How do I install benchmarking?
Run npx skills add https://github.com/chaterm/terminal-skills --skill benchmarking in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/benchmarking/ (personal) or .claude/skills/benchmarking/ (project).
Which AI agents can use benchmarking?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is benchmarking safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains benchmarking?
It is published by chaterm in chaterm/terminal-skills. It has 63 recorded installs.
More from chaterm/terminal-skills
system-admin
chaterm/terminal-skills
Linux system administration and monitoring
Popular other skills
hyperframes-cli
heygen-com/hyperframes
The HyperFrames CLI by job - scaffold, check, look at frames, edit the timeline, preview, render locally or in the cloud, publish, project history - plus reading its JSON and recovering from build or render failures.
triage
mattpocock/skills
Move issues and external PRs through a state machine of triage roles, categorise, verify, grill if needed, and write agent-ready briefs.
ask-matt
mattpocock/skills
Ask which skill or flow fits your situation. A router over the skills in this repo.
to-questionnaire
mattpocock/skills
Turn a decision you can't fully answer into a questionnaire for someone else to fill in.
loop-me
mattpocock/skills
Grill me about specs for the workflows I want to build, within this workspace.