Test sysbench supports the following modes:
. 1, the CPU computing performance
2, IO performance disk
3, the performance of the scheduler
4, memory allocation and transmission speed
5, POSIX threads performance
6, database performance (OLTP benchmark)
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)
Options Threads:
--thread-N = Number of Yields Yields per Request to do [1000] # efficiency gains for each request to be performed [1000]
--thread = N-Locks Locks per Number of Thread [. 8] # each lock number [8] thread
[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
Disk IO test:
[root@127-0-0-1 sysbench]# /u01/opt/sysbench/bin/sysbench fileio help
sysbench 1.1.0 (using bundled LuaJIT 2.1.0-beta3)
Options FileIO:
--file NUM-N = Number of Files to Create [128] # represents the number of files generated [128]
--file-Block-size N = Block size to use in the IO All Operations [16384] All # IO block size used in the operation [16384]
--file-size-total = total size sIZE of files to Create [2G] # file to create the total size of [2G]
--file-Test Test MODE-MODE = STRING {seqwr, seqrewr, seqrd, rndrd , rndwr, rndrw} # test mode seqwr {, seqrewr, seqrd, rndrd, rndwr, rndrw}
--file-IO-STRING File Operations mODE mODE = {Sync, the async, the mmap} [Sync ] # file Sync mode of operation {, the async, the mmap} [Sync]
--file the async-backlog-N = number of per asynchronous operatons to queue thread [128] # for each thread to be queued asynchronous operand [128]
- file-extra-flags = [lIST , ...] list of additional flags to use to open files {sync, dsync, direct} [] # notation for opening a file list {sync, dsync, direct} [ ]
--file-fsync-freq = N do fsync () after this number of requests (0 - do not use fsync ()) [100] # perform fsync () function of frequency. fsync mainly synchronous disk file, because there may be a relationship between the system and the disk cache. 0 means do not use fsync function. The default value is 100.
--file-fsync-all [= on | off] do fsync () after each write operation [off] # every time executing the write operation is executed once fsync. The default is off.
--file-fsync-end [= on | off] do fsync () of test [on] # fsync function is performed at the end of the test at the end. The default is on.
--file-fsync-mode = STRING which method to use for synchronization {fsync, fdatasync} select [fsync] # file synchronization function, and also parameters related API, since a plurality of different operating systems support for fdatasync, which is not recommended fdatasync. The default is fsync.
--file-merged-requests = N merge at most number of IO requests if possible this - at [0] # most cases (0 do not merge), the combined number of possible IO request, the default is 0.
--file-rw-ratio = N reads / writes ratio for combined test write ratio when [1.5] # test, the default is 1.5 to 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)
Options Memory:
--memory-Block-size = SIZE for size of Memory Block Test [1K] size test memory block # [1K]
--memory-SIZE Total = Total-size to size of Data Transfer [100G] to # the total size of the data transmitted 100G]
--memory-access memory scope STRING = {Global scope, local} [Global] # Global memory access range {,} local [Global]
--memory-the hugetlb [= ON | OFF] the allocate memory from HugeTLB pool [off] # from the memory pool allocated [OFF]
--memory-Oper memory operations of type STRING = {read, write, none} [Write] # storage operation type {read, write, none} [ Write]
--memory-access-memory access STRING mODE mODE = {seq, rnd} [seq] # mode memory access {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='[email protected]' --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='[email protected]' --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