使用sysbench进行压力测试
2024-08-25 00:04:34
sysbench是一款开源的多线程性能测试工具，可以执行CPU/内存/线程/IO/数据库等方面的性能测试。数据库目前支持MySQL/Oracle/PostgreSQL/Drizzle，它主要包括以下几种方式的测试：
- cpu性能
- 磁盘io性能
- 调度程序性能
- 内存分配及传输速度
- POSIX线程性能
- 数据库性能(OLTP基准测试)
机器配置
[root@localhost ~]# grep -iE 'MemTotal|MemFree' /proc/meminfo
MemTotal: 8058060 kB
MemFree: 2213240 kB
[root@localhost ~]# grep "processor" /proc/cpuinfo | wc -l
4
[root@localhost ~]# uname -a
Linux localhost 2.6.32-431.11.2.el6.x86_64 #1 SMP Tue Mar 25 19:59:55 UTC 2014 x86_64 x86_64 x86_64 GNU/Linux
[root@localhost ~]# cat /etc/redhat-release
CentOS release 6.7 (Final)
一、安装
官方地址：https://github.com/akopytov/sysbench
下载方法：git clone https://github.com/akopytov/sysbench.git
安装
./autogen.sh
./configure
make && make install
以上命令的编译SysBench默认需要Mysql库的支持，如果你机器已安装Mysql但没有指定位置（在PATH下找不到mysql_config），你必须在./configure得时候指定–with-mysql-includes和–with-mysql-libs
也可以使用–without-mysql命令，取消Mysql的支持
command命令的简单描述及作用
prepare:为测试执行准备工作，例如为fileis测试在磁盘上创建必要的文件，为OLTP测试准备测试数据
run: 执行完整的测试，必须指定–-test选项
cleanup: 在测试运行结束移除prepare准备的临时数据
help:显示不同测试（根据–-test选项）的帮助信息，你也可以使用sysbench help命令（而不用–-test）去显示帮助信息
一些参数的解释
--num-threads #创建测试线程的数目
--max-requests #请求的最大数目，0表示不限制
--max-time #最大执行时间，单位秒，0表示不限制
--thread-stack-size #每个线程的堆栈大小 32K
--init-rng #在测试开始之前指定是否需要初始化随机数发生器 off
--report-interval #隔多久打印一次统计信息，注意的是统计信息统计的是间隔时间而不是累计时间的数据。单位秒，0表示关闭该功能
--test #指定测试项目名称 Required
--debug #是否显示更多的调试信息 off
--validate #在可能的情况下是否进行验证检查 off
--help #帮助信息 off
--verbosity #详细级别，0-严重信息，5-调试信息
--percentile #表示设定采样比例，默认是 95%，即丢弃1%的长请求，在剩余的99%里取最大值
二、CPU的基准测试
CPU测试使用64位整数，测试计算质数直到某个最大值所需要的时间，cpu测试主要是进行素数的加法运算，在上面的例子中，指定了最大的素数为 20000，自己可以根据机器cpu的性能来适当调整数值，主要看total time所花费的时间
[root@localhost sysbench]# sysbench --test=cpu --cpu-max-prime=10000 run
sysbench 0.5: multi-threaded system evaluation benchmark Running the test with following options:
Number of threads: 1
Random number generator seed is 0 and will be ignored Primer numbers limit: 10000 Threads started! General statistics:
total time: 14.5690s
total number of events: 10000
total time taken by event execution: 14.5616s
response time:
min: 1.40ms
avg: 1.46ms
max: 10.59ms
approx. 95 percentile: 1.52ms Threads fairness:
events (avg/stddev): 10000.0000/0.00
execution time (avg/stddev): 14.5616/0.00
相关选项
sysbench –test=cpu help
--cpu-max-prime=N 最大质数发生器数量。默认是10000
三、线程基准测试
thread-locks小于线程数除以2，lock越少，处理时间越长
[root@localhost sysbench]# sysbench --test=threads --num-threads=800 --thread-yields=100 --thread-locks=10 run
sysbench 0.5: multi-threaded system evaluation benchmark Running the test with following options:
Number of threads: 800
Random number generator seed is 0 and will be ignored Threads started! General statistics:
total time: 0.4644s
total number of events: 10000
total time taken by event execution: 350.9839s
response time:
min: 0.04ms
avg: 35.10ms
max: 456.96ms
approx. 95 percentile: 144.17ms Threads fairness:
events (avg/stddev): 12.5000/6.45
execution time (avg/stddev): 0.4387/0.01
相关参数
sysbench --test=threads help
sysbench 0.5: multi-threaded system evaluation benchmark threads options:
--thread-yields=N 每个请求产生多少个线程。默认是1000
--thread-locks=N 每个线程的锁的数量。默认是8
四、文件IO基准测试
磁盘IO性能测试[主要看每秒请求数(request)和总体的吞吐量(total)
[root@localhost sysbench]# sysbench --test=fileio --num-threads=16 --file-total-size=2G --file-test-mode=rndrw prepare
sysbench 0.5: multi-threaded system evaluation benchmark 128 files, 16384Kb each, 2048Mb total
Creating files for the test...
Extra file open flags: 0
Creating file test_file.0
Creating file test_file.1
……
Creating file test_file.127
2147483648 bytes written in 67.56 seconds (30.32 MB/sec).
[root@localhost sysbench]# sysbench --test=fileio --num-threads=20 --file-total-size=2G --file-test-mode=rndrw run
sysbench 0.5: multi-threaded system evaluation benchmark Running the test with following options:
Number of threads: 20
Random number generator seed is 0 and will be ignored Extra file open flags: 0
128 files, 16Mb each
2Gb total file size
Block size 16Kb
Number of IO requests: 10000
Read/Write ratio for combined random IO test: 1.50
Periodic FSYNC enabled, calling fsync() each 100 requests.
Calling fsync() at the end of test, Enabled.
Using synchronous I/O mode
Doing random r/w test
Threads started! Operations performed: 5999 reads, 4001 writes, 12800 Other = 22800 Total
Read 93.734Mb Written 62.516Mb Total transferred 156.25Mb (19.3Mb/sec)
1235.21 Requests/sec executed General statistics:
total time: 8.0958s
total number of events: 10000
total time taken by event execution: 1.4557s
response time:
min: 0.00ms
avg: 0.15ms
max: 1319.03ms
approx. 95 percentile: 0.02ms Threads fairness:
events (avg/stddev): 500.0000/186.14
execution time (avg/stddev): 0.0728/0.29
相关参数
sysbench --test=fileio help
sysbench 0.5: multi-threaded system evaluation benchmark fileio options:
--file-num=N 创建测试文件的数量。默认是128
--file-block-size=N 测试时文件块的大小。默认是16384(16K)
--file-total-size=SIZE 测试文件的总大小。默认是2G
--file-test-mode=STRING 文件测试模式{seqwr(顺序写), seqrewr(顺序读写), seqrd(顺序读), rndrd(随机读), rndwr(随机写), rndrw(随机读写)}
--file-io-mode=STRING 文件操作模式{sync(同步),async(异步),fastmmap(快速map映射),slowmmap(慢map映射)}。默认是sync
--file-extra-flags=STRING 使用额外的标志来打开文件{sync,dsync,direct} 。默认为空
--file-fsync-freq=N 执行fsync()的频率。(0 – 不使用fsync())。默认是100
--file-fsync-all=[on|off] 每执行完一次写操作就执行一次fsync。默认是off
--file-fsync-end=[on|off] 在测试结束时才执行fsync。默认是on
--file-fsync-mode=STRING 使用哪种方法进行同步{fsync, fdatasync}。默认是fsync
--file-merged-requests=N 如果可以，合并最多的IO请求数(0 – 表示不合并)。默认是0
--file-rw-ratio=N 测试时的读写比例。默认是1.5
五、内存基准测试
测试了内存的连续读写性能
[root@localhost sysbench]# sysbench --test=memory --memory-block-size=8k --memory-total-size=1G run
sysbench 0.5: multi-threaded system evaluation benchmark Running the test with following options:
Number of threads: 1
Random number generator seed is 0 and will be ignored Threads started! Operations performed: 131072 (769179.70 ops/sec) 1024.00 MB transferred (6009.22 MB/sec) General statistics:
total time: 0.1704s
total number of events: 131072
total time taken by event execution: 0.1387s
response time:
min: 0.00ms
avg: 0.00ms
max: 2.12ms
approx. 95 percentile: 0.00ms Threads fairness:
events (avg/stddev): 131072.0000/0.00
execution time (avg/stddev): 0.1387/0.00
相关参数
sysbench --test=memory help
sysbench 0.5: multi-threaded system evaluation benchmark memory options:
--memory-block-size=SIZE 测试时内存块大小。默认是1K
--memory-total-size=SIZE 传输数据的总大小。默认是100G
--memory-scope=STRING 内存访问范围{global,local}。默认是global
--memory-hugetlb=[on|off] 从HugeTLB池内存分配。默认是off
--memory-oper=STRING 内存操作类型。{read, write, none} 默认是write
--memory-access-mode=STRING 存储器存取方式{seq,rnd} 默认是seq
六、互斥锁基准测试
[root@localhost sysbench]# sysbench --test=mutex --num-threads=100 --mutex-num=1000 --mutex-locks=100000 --mutex-loops=10000 run
sysbench 0.5: multi-threaded system evaluation benchmark Running the test with following options:
Number of threads: 100
Random number generator seed is 0 and will be ignored Threads started! General statistics:
total time: 4.9822s
total number of events: 100
total time taken by event execution: 474.6478s
response time:
min: 1601.28ms
avg: 4746.48ms
max: 4981.76ms
approx. 95 percentile: 4973.56ms Threads fairness:
events (avg/stddev): 1.0000/0.00
execution time (avg/stddev): 4.7465/0.40
相关参数
sysbench --test=mutex help
sysbench 0.5: multi-threaded system evaluation benchmark mutex options: --mutex-num=N 数组互斥的总大小。默认是4096
--mutex-locks=N 每个线程互斥锁的数量。默认是50000
--mutex-loops=N 内部互斥锁的空循环数量。默认是10000
七、OLTP基准测试
完整过程分为3个阶段：prepare->run->cleanup，即分别为准备数据，测试，清理测试数据
[root@localhost sysbench]# sysbench --mysql-socket=/var/lib/mysql/mysql.sock --oltp-table-size=100000 --test=sysbench/tests/db/oltp.lua --mysql-user=root --mysql-password=123456 --report-interval=5 --num-threads=100 --oltp_tables_count=10 --rand-type=uniform --percentile=99 run
sysbench 0.5: multi-threaded system evaluation benchmark Running the test with following options:
Number of threads: 100
Report intermediate results every 5 second(s)
Random number generator seed is 0 and will be ignored Threads started! [ 5s] threads: 100, tps: 894.57, reads/s: 12790.38, writes/s: 3646.48, response time: 340.91ms (99%)
[ 10s] threads: 100, tps: 973.20, reads/s: 13608.42, writes/s: 3860.61, response time: 238.96ms (99%)
OLTP test statistics:
queries performed:
read: 140000
write: 40000
other: 20000
total: 200000
transactions: 10000 (932.07 per sec.)
deadlocks: 0 (0.00 per sec.)
read/write requests: 180000 (16777.18 per sec.)
other operations: 20000 (1864.13 per sec.) General statistics:
total time: 10.7289s
total number of events: 10000
total time taken by event execution: 1067.3242s
response time:
min: 9.75ms
avg: 106.73ms
max: 450.30ms
approx. 99 percentile: 284.52ms Threads fairness:
events (avg/stddev): 100.0000/4.15
execution time (avg/stddev): 10.6732/0.05
相关参数
sysbench --test=oltp help
sysbench 0.5: multi-threaded system evaluation benchmark oltp options:
--oltp-test-mode=STRING 执行模式{simple,complex(advanced transactional),nontrx(non-transactional),sp}。默认是complex
--oltp-reconnect-mode=STRING 重新连接模式{session(不使用重新连接。每个线程断开只在测试结束),transaction(在每次事务结束后重新连接),query(在每个SQL语句执行完重新连接),random(对于每个事务随机选择以上重新连接模式)}。默认是session
--oltp-sp-name=STRING 存储过程的名称。默认为空
--oltp-read-only=[on|off] 只读模式。Update，delete，insert语句不可执行。默认是off
--oltp-skip-trx=[on|off] 省略begin/commit语句。默认是off
--oltp-range-size=N 查询范围。默认是100
--oltp-point-selects=N number of point selects [10]
--oltp-simple-ranges=N number of simple ranges [1]
--oltp-sum-ranges=N number of sum ranges [1]
--oltp-order-ranges=N number of ordered ranges [1]
--oltp-distinct-ranges=N number of distinct ranges [1]
--oltp-index-updates=N number of index update [1]
--oltp-non-index-updates=N number of non-index updates [1]
--oltp-nontrx-mode=STRING 查询类型对于非事务执行模式{select, update_key, update_nokey, insert, delete} [select]
--oltp-auto-inc=[on|off] AUTO_INCREMENT是否开启。默认是on
--oltp-connect-delay=N 在多少微秒后连接数据库。默认是10000
--oltp-user-delay-min=N 每个请求最短等待时间。单位是ms。默认是0
--oltp-user-delay-max=N 每个请求最长等待时间。单位是ms。默认是0
--oltp-table-name=STRING 测试时使用到的表名。默认是sbtest
--oltp-table-size=N 测试表的记录数。默认是10000
--oltp-dist-type=STRING 分布的随机数{uniform(均匀分布),Gaussian(高斯分布),special(空间分布)}。默认是special
--oltp-dist-iter=N 产生数的迭代次数。默认是12
--oltp-dist-pct=N 值的百分比被视为'special' (for special distribution)。默认是1
--oltp-dist-res=N ‘special’的百分比值。默认是75 General database options:
--db-driver=STRING 指定数据库驱动程序('help' to get list of available drivers)
--db-ps-mode=STRING 编制报表使用模式{auto, disable} [auto]
Compiled-in database drivers:
mysql - MySQL driver
mysql options:
--mysql-host=[LIST,...] 数据库地址
--mysql-port=N 端口号，默认3306
--mysql-user=STRING 用户名
--mysql-password=STRING 密码
--mysql-db=STRING 测试数据库名
--mysql-table-engine=STRING 数据库存储引擎，默认innodb{myisam,innodb,bdb,heap,ndbcluster,federated}
--mysql-socket=STRING socket文件的位置
--mysql-engine-trx=STRING 是否使用事务，与存储引擎选择有关，默认auto{yes,no,auto}
--mysql-ssl=[on|off] 在客户端是否使用SSL连接，默认off
--myisam-max-rows=N MyISAM表最大行数，默认1000000
--mysql-create-options=STRING additional options passed to CREATE TABLE []
参考地址
https://launchpad.net/sysbench
https://github.com/akopytov/sysbench
最新文章
- 用Fiddler模拟低速网络环境
- shell脚本一
- curl详解
- 基于HTML5的WebGL电信网管3D机房监控应用
- sqlserver 导出数据字典
- processor, memory, I/O
- iOS - OC NSUserDefaults 数据存储
- 机器学习相关——协同过滤
- 使用ajax技术无刷新动态调用股票信息
- Android微信SDK API 调用教程【转】
- ServiceStack.RabbitMQ在站点中使用时导致静态页面无法正常解析
- NSIS：卸载时选择组件
- leetcode第二题--Median of Two Sorted Arrays
- class 文件反编译器的 java 实现
- scala的map操作
- 第二章 Android系统与嵌入式开发
- 2018-2019-1 20189210 《Linux内核原理与分析》第三周作业
- .net core WebApi Monitor实现并发同步
- Pyhthon爬虫其之验证码识别
- 力扣（LeetCode）922. 按奇偶排序数组 II
热门文章
- 利用DropDownList实现下拉
- LeetCode - 41. First Missing Positive
- 重新想象 Windows 8 Store Apps (50) - 输入: 边缘手势, 手势操作, 手势识别
- CodeForces 149D Coloring Brackets
- SQL Server Merge语句的使用
- jQuery.Cookie.js用法
- ASP.NET获取请求的url信息汇总
- CSS3属性(二)
- Java中的守护线程和非守护线程（转载）
- Add a file to a Document Library and update metadata properties in a single method添加文档的方法