准备数据+随机读写测试
sysbench --num-threads=16 --test=fileio --file-total-size=3G --file-test-mode=rndrw prepare sysbench --num-threads=16 --test=fileio --file-total-size=3G --file-test-mode=rndrw run
输出结果：#后面的是解读注释
root@wuzhou:/home/meizu/sysbench/sysbench-0.4.12# sysbench --num-threads=16 --test=fileio --file-total-size=3G --file-test-mode=rndrw run sysbench 0.4.12: multi-threaded system evaluation benchmark Running the test with following options: Number of threads: 16 #16个线程进行读写 Extra file open flags: 0 128 files, 24Mb each #3G的文件分成了128个文件，每个24Mb 3Gb total file size Block size 16Kb #块大小16Kb Number of random requests for random IO: 10000 #随机IO请求数10000 Read/Write ratio for combined random IO test: 1.50 #随机读写比例1.5:1 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 #测试模式 Threads started! Done. Operations performed: 6010 Read, 3998 Write, 12806 Other = 22814 Total Read 93.906Mb Written 62.469Mb Total transferred 156.38Mb (122.03Mb/sec) #总的IO读写效率（122.03Mb/sec) 7810.19 Requests/sec executed #7810.19/s 这个就是IOPC。每次IO读写一个block, 每个block=16K,7810*16/1024=122.03Mb. IO测试结果关注点IOPS。 Test execution summary: total time: 1.2814s total number of events: 10008 total time taken by event execution: 15.8660 per-request statistics: min: 0.00ms avg: 1.59ms max: 14.04ms approx. 95 percentile: 6.04ms Threads fairness: events (avg/stddev): 625.5000/24.21 execution time (avg/stddev): 0.9916/0.01