共计 9209 个字符，预计需要花费 24 分钟才能阅读完成。
如何进行 sysbench 测试，很多新手对此不是很清楚，为了帮助大家解决这个难题，下面丸趣 TV 小编将为大家详细讲解，有这方面需求的人可以来学习下，希望你能有所收获。
sysbench 支持以下几种测试模式：
1、CPU 运算性能
2、磁盘 IO 性能
3、调度程序性能
4、内存分配及传输速度
5、POSIX 线程性能
6、数据库性能 (OLTP 基准测试)
sysbench 版本：
[root@127-0-0-1 sysbench]# /u01/opt/sysbench/bin/sysbench –version
sysbench 1.1.0
CPU 测试：
[root@127-0-0-1 sysbench]# /u01/opt/sysbench/bin/sysbench cpu –cpu-max-prime=10000 run
sysbench 1.1.0 (using bundled LuaJIT 2.1.0-beta3)
Running the test with following options:
Number of threads: 1
Initializing random number generator from current time
Prime numbers limit: 10000
Initializing worker threads…
Threads started!
CPU speed:
events per second: 658.31
Throughput:
events/s (eps): 658.3125
time elapsed: 10.0013s
total number of events: 6584
Latency (ms):
min: 1.44
avg: 1.52
max: 3.07
95th percentile: 1.52
sum: 9998.21
Threads fairness:
events (avg/stddev): 6584.0000/0.00
execution time (avg/stddev): 9.9982/0.00
线程测试：
[root@127-0-0-1 sysbench]# /u01/opt/sysbench/bin/sysbench threads help
sysbench 1.1.0 (using bundled LuaJIT 2.1.0-beta3)
threads options:
–thread-yields=N number of yields to do per request [1000] # 每个请求要执行的收益效率 [1000]
–thread-locks=N number of locks per thread [8] #每个线程的锁数 [8][root@127-0-0-1 sysbench]# /u01/opt/sysbench/bin/sysbench threads –thread-yields=1000 –thread-locks=2 run
sysbench 1.1.0 (using bundled LuaJIT 2.1.0-beta3)
Running the test with following options:
Number of threads: 1
Initializing random number generator from current time
Initializing worker threads…
Threads started!
Throughput:
events/s (eps): 1349.6979
time elapsed: 10.0008s
total number of events: 13498
Latency (ms):
min: 0.73
avg: 0.74
max: 1.50
95th percentile: 0.74
sum: 9996.37
Threads fairness:
events (avg/stddev): 13498.0000/0.00
execution time (avg/stddev): 9.9964/0.00
磁盘 IO 测试：
[root@127-0-0-1 sysbench]# /u01/opt/sysbench/bin/sysbench fileio help
sysbench 1.1.0 (using bundled LuaJIT 2.1.0-beta3)
fileio options:
–file-num=N number of files to create [128] #代表生成文件的数量 [128]
–file-block-size=N block size to use in all IO operations [16384] #在所有 IO 操作中使用的块大小 [16384]
–file-total-size=SIZE total size of files to create [2G] # 要创建的文件的总大小 [2G]
–file-test-mode=STRING test mode {seqwr, seqrewr, seqrd, rndrd, rndwr, rndrw} # 测试模式 {seqwr, seqrewr, seqrd, rndrd, rndwr, rndrw}
–file-io-mode=STRING file operations mode {sync,async,mmap} [sync] # 文件操作模式 {sync,async,mmap} [sync]
–file-async-backlog=N number of asynchronous operatons to queue per thread [128] # 每个线程要排队的异步操作数 [128]
–file-extra-flags=[LIST,…] list of additional flags to use to open files {sync,dsync,direct} [] #用于打开文件的附加标志列表 {sync,dsync,direct} []
–file-fsync-freq=N do fsync() after this number of requests (0 – don t use fsync()) [100] #执行 fsync() 函数的频率。fsync 主要是同步磁盘文件，因为可能有系统和磁盘缓冲的关系。0 代表不使用 fsync 函数。默认值为 100。
–file-fsync-all[=on|off] do fsync() after each write operation [off] # 每执行完一次写操作，就执行一次 fsync。默认为 off。
–file-fsync-end[=on|off] do fsync() at the end of test [on] # 在测试结束时执行 fsync 函数。默认为 on。
–file-fsync-mode=STRING which method to use for synchronization {fsync, fdatasync} [fsync] #文件同步函数的选择，同样是和 API 相关的参数，由于多个操作系统对于 fdatasync 支持不同，因此不建议使用 fdatasync。默认为 fsync。
–file-merged-requests=N merge at most this number of IO requests if possible (0 – don t merge) [0] # 大多情况下，合并可能的 IO 的请求数，默认为 0。
–file-rw-ratio=N reads/writes ratio for combined test [1.5] # 测试时的读写比例，默认时为 1.5，即可 3：2。
/u01/opt/sysbench/bin/sysbench fileio –threads=16 –file-total-size=2G –file-test-mode=rndrw prepare #准备
/u01/opt/sysbench/bin/sysbench fileio –threads=16 –file-total-size=2G –file-fsync-freq=0 –file-test-mode=rndrw run # 运行
/u01/opt/sysbench/bin/sysbench fileio –threads=16 –file-total-size=2G –file-test-mode=rndrw cleanup #清理
[root@127-0-0-1 yoon]# /u01/opt/sysbench/bin/sysbench fileio –threads=16 –file-total-size=2G –file-fsync-freq=0 –file-test-mode=rndrw run
sysbench 1.1.0 (using bundled LuaJIT 2.1.0-beta3)
Running the test with following options:
Number of threads: 16
Initializing random number generator from current time
Extra file open flags: (none)
128 files, 16MiB each
2GiB total file size
Block size 16KiB
Number of IO requests: 0
Read/Write ratio for combined random IO test: 1.50
Calling fsync() at the end of test, Enabled.
Using synchronous I/O mode
Doing random r/w test
Initializing worker threads…
Threads started!
Throughput:
read: IOPS=383594.04 5993.66 MiB/s (6284.80 MB/s)
write: IOPS=255729.12 3995.77 MiB/s (4189.87 MB/s)
fsync: IOPS=122.71
Latency (ms):
min: 0.00
avg: 0.01
max: 1.73
95th percentile: 0.03
sum: 144444.71
内存测试：
[root@127-0-0-1 yoon]# /u01/opt/sysbench/bin/sysbench memory help
sysbench 1.1.0 (using bundled LuaJIT 2.1.0-beta3)
memory options:
–memory-block-size=SIZE size of memory block for test [1K] # 测试内存块的大小 [1K]
–memory-total-size=SIZE total size of data to transfer [100G] #要传输的数据的总大小 100G]
–memory-scope=STRING memory access scope {global,local} [global] #内存访问范围 {global,local} [global]
–memory-hugetlb[=on|off] allocate memory from HugeTLB pool [off] #从内存池中分配内存 [off]
–memory-oper=STRING type of memory operations {read, write, none} [write] #存储操作类型 {read, write, none} [write]
–memory-access-mode=STRING memory access mode {seq,rnd} [seq] #存储器存取方式 {seq,rnd} [seq][root@127-0-0-1 yoon]# /u01/opt/sysbench/bin/sysbench memory –memory-total-size=10G –memory-block-size=8K run
sysbench 1.1.0 (using bundled LuaJIT 2.1.0-beta3)
Running the test with following options:
Number of threads: 1
Initializing random number generator from current time
Running memory speed test with the following options:
block size: 8KiB
total size: 10240MiB
operation: write
scope: global
Initializing worker threads…
Threads started!
Total operations: 1310720 (1077326.35 per second)
10240.00 MiB transferred (8416.61 MiB/sec)
Throughput:
events/s (eps): 1077326.3489
time elapsed: 1.2166s
total number of events: 1310720
Latency (ms):
min: 0.00
avg: 0.00
max: 0.02
95th percentile: 0.00
sum: 893.01
Threads fairness:
events (avg/stddev): 1310720.0000/0.00
execution time (avg/stddev): 0.8930/0.00
OLTP 测试：
[root@127-0-0-1 sysbench]# ls
bulk_insert.lua oltp_delete.lua oltp_point_select.lua oltp_read_write.lua oltp_update_non_index.lua prepare.log select_random_ranges.lua
oltp_common.lua oltp_insert.lua oltp_read_only.lua oltp_update_index.lua oltp_write_only.lua select_random_points.lua tests
/u01/opt/sysbench/bin/sysbench /u01/opt/sysbench/share/sysbench/oltp_common.lua –mysql-host=127.0.0.1 –mysql-port=3306 –mysql-user=root –mysql-password= root@01.com –mysql-db=sbtest –table-size=5000000 –threads=10 –report-interval=10 prepare
[root@127-0-0-1 sysbench]# /u01/opt/sysbench/bin/sysbench /u01/opt/sysbench/share/sysbench/oltp_read_write.lua –mysql-host=127.0.0.1 –mysql-port=3306 –mysql-user=root –mysql-password= root@01.com –mysql-db=sbtest –table-size=5000000 –threads=10 –report-interval=10 –time=120 run
sysbench 1.1.0 (using bundled LuaJIT 2.1.0-beta3)
Running the test with following options:
Number of threads: 10
Report intermediate results every 10 second(s)
Initializing random number generator from current time
Initializing worker threads…
Threads started!
[10s] thds: 10 tps: 824.26 qps: 16498.17 (r/w/o: 11550.29/3298.36/1649.53) lat (ms,95%): 16.71 err/s: 0.00 reconn/s: 0.00
[20s] thds: 10 tps: 938.90 qps: 18778.84 (r/w/o: 13146.36/3754.69/1877.79) lat (ms,95%): 13.95 err/s: 0.00 reconn/s: 0.00
[30s] thds: 10 tps: 969.19 qps: 19383.22 (r/w/o: 13568.10/3876.74/1938.37) lat (ms,95%): 13.70 err/s: 0.00 reconn/s: 0.00
[40s] thds: 10 tps: 1003.32 qps: 20061.71 (r/w/o: 14042.19/4012.88/2006.64) lat (ms,95%): 13.22 err/s: 0.00 reconn/s: 0.00
[50s] thds: 10 tps: 1011.57 qps: 20236.34 (r/w/o: 14166.91/4046.29/2023.14) lat (ms,95%): 13.22 err/s: 0.00 reconn/s: 0.00
[60s] thds: 10 tps: 1115.50 qps: 22309.32 (r/w/o: 15615.94/4462.38/2230.99) lat (ms,95%): 11.87 err/s: 0.00 reconn/s: 0.00
[70s] thds: 10 tps: 1064.13 qps: 21283.06 (r/w/o: 14898.46/4256.33/2128.27) lat (ms,95%): 12.30 err/s: 0.00 reconn/s: 0.00
[80s] thds: 10 tps: 1030.00 qps: 20599.45 (r/w/o: 14419.27/4120.19/2060.00) lat (ms,95%): 12.52 err/s: 0.00 reconn/s: 0.00
[90s] thds: 10 tps: 1056.32 qps: 21127.75 (r/w/o: 14790.22/4224.89/2112.65) lat (ms,95%): 12.30 err/s: 0.00 reconn/s: 0.00
[100s] thds: 10 tps: 1097.38 qps: 21946.72 (r/w/o: 15362.43/4389.52/2194.76) lat (ms,95%): 12.30 err/s: 0.00 reconn/s: 0.00
[110s] thds: 10 tps: 1147.39 qps: 22948.97 (r/w/o: 16063.71/4590.47/2294.79) lat (ms,95%): 11.87 err/s: 0.00 reconn/s: 0.00
[120s] thds: 10 tps: 1110.00 qps: 22200.00 (r/w/o: 15540.00/4440.00/2220.00) lat (ms,95%): 12.08 err/s: 0.00 reconn/s: 0.00
SQL statistics:
queries performed:
read: 1731702
write: 494772
other: 247386
total: 2473860
transactions: 123693 (1030.70 per sec.)
queries: 2473860 (20614.02 per sec.)
ignored errors: 0 (0.00 per sec.)
reconnects: 0 (0.00 per sec.)
Throughput:
events/s (eps): 1030.7010
time elapsed: 120.0086s
total number of events: 123693
Latency (ms):
min: 4.32
avg: 9.70
max: 185.38
95th percentile: 13.22
sum: 1199649.68
Threads fairness:
events (avg/stddev): 12369.3000/304.67
execution time (avg/stddev): 119.9650/0.00
看完上述内容是否对您有帮助呢？如果还想对相关知识有进一步的了解或阅读更多相关文章，请关注丸趣 TV 行业资讯频道，感谢您对丸趣 TV 的支持。
