[root@master sysbench]# ls

bulk_insert.lua  oltp_delete.lua  oltp_point_select.lua  oltp_read_write.lua    oltp_update_non_index.lua  select_random_points.lua  tests oltp_common.lua  oltp_insert.lua  oltp_read_only.lua     oltp_update_index.lua  oltp_write_only.lua        select_random_ranges.lua

使用其中的oltp_read_write.lua进行读写压力测试：

第1步：构建数据

sysbench oltp_read_write.lua --mysql-socket=/tmp/mysql3306.sock --mysql-host=192.168.88.8 --mysql-port=3306 --mysql-db=lbgtest --mysql-user=root --mysql-password=root --table_size=50000 --tables=10 --threads=20 --time=60 --report-interval=10 prepare

第2步：压测

sysbench oltp_read_write.lua --mysql-socket=/tmp/mysql3306.sock --mysql-host=192.168.88.8 --mysql-port=3306 --mysql-db=lbgtest --mysql-user=root --mysql-password=root --table_size=50000 --tables=10 --threads=20 --time=60 --report-interval=10 run

选项说明：

--mysql-db=lbgtest   --用来测试的库，需先创建好。

--table-size=100000 表示每个测试表数据量为 100000

--tables=10     测试的表的个数（会自动创建）。

--threads=20    20个并发链接进行测试。

time=60  表示测试总时长为 60秒

--report-interval=10 表示每10秒输出一次测试进度报告

注明：上面的oltp_read_write.lua可写成绝对路径，将prepare改为run即可进行测试。

mysql> create database lbgtest;

创建测试数据:

[root@master sysbench]# sysbench oltp_read_write.lua --mysql-socket=/tmp/mysql3306.sock --mysql-host=192.168.88.8 --mysql-port=3306 --mysql-db=lbgtest --mysql-user=root --mysql-password=root --table_size=50000 --tables=10 --threads=20 --time=60 --report-interval=10 prepare

sysbench 1.1.0 (using bundled LuaJIT 2.1.0-beta3)

Initializing worker threads...

Creating table 'sbtest7'...

Creating table 'sbtest10'...

Creating table 'sbtest8'...

Creating table 'sbtest3'...

Creating table 'sbtest1'...

Creating table 'sbtest2'...

Creating table 'sbtest6'...

Creating table 'sbtest5'...

Creating table 'sbtest4'...

Creating table 'sbtest9'...

Inserting 50000 records into 'sbtest3'

Inserting 50000 records into 'sbtest5'

Inserting 50000 records into 'sbtest1'

Inserting 50000 records into 'sbtest6'

Inserting 50000 records into 'sbtest9'

Inserting 50000 records into 'sbtest2'

Inserting 50000 records into 'sbtest4'

Inserting 50000 records into 'sbtest8'

Inserting 50000 records into 'sbtest10'

Inserting 50000 records into 'sbtest7'

Creating a secondary index on 'sbtest5'...

Creating a secondary index on 'sbtest6'...

Creating a secondary index on 'sbtest4'...

Creating a secondary index on 'sbtest7'...

Creating a secondary index on 'sbtest1'...

Creating a secondary index on 'sbtest9'...

Creating a secondary index on 'sbtest3'...

Creating a secondary index on 'sbtest2'...

Creating a secondary index on 'sbtest10'...

Creating a secondary index on 'sbtest8'...

完成后查看测试数据：

可以在测试库里看到数据：

mysql> use lbgtest;

mysql> show tables;

+-------------------+

| Tables_in_lbgtest |

+-------------------+

| sbtest1           |

| sbtest10          |

| sbtest2           |

| sbtest3           |

| sbtest4           |

| sbtest5           |

| sbtest6           |

| sbtest7           |

| sbtest8           |

| sbtest9           |

+-------------------+

mysql> select count(1) from sbtest1;

+----------+

| count(1) |

+----------+

|    50000 |

+----------+

1 row in set (0.02 sec)

测试：

[root@master sysbench]# sysbench oltp_read_write.lua --mysql-socket=/tmp/mysql3306.sock --mysql-host=192.168.88.8 --mysql-port=3306 --mysql-db=lbgtest --mysql-user=root --mysql-password=root --table_size=50000 --tables=10 --threads=20 --time=60 --report-interval=10 run

sysbench 1.1.0 (using bundled LuaJIT 2.1.0-beta3)

Running the test with following options:

Number of threads: 20

Report intermediate results every 10 second(s)

Initializing random number generator from current time

Initializing worker threads...

Threads started!

[ 10s ] thds: 20 tps: 112.24 qps: 2281.24 (r/w/o: 1598.45/456.37/226.42) lat (ms,95%): 303.33 err/s: 0.00 reconn/s: 0.00

[ 20s ] thds: 20 tps: 141.68 qps: 2829.12 (r/w/o: 1983.33/562.42/283.36) lat (ms,95%): 244.38 err/s: 0.00 reconn/s: 0.00

[ 30s ] thds: 20 tps: 160.33 qps: 3198.39 (r/w/o: 2239.41/638.32/320.66) lat (ms,95%): 219.36 err/s: 0.00 reconn/s: 0.00

[ 40s ] thds: 20 tps: 161.93 qps: 3248.02 (r/w/o: 2272.64/651.52/323.86) lat (ms,95%): 207.82 err/s: 0.00 reconn/s: 0.00

[ 50s ] thds: 20 tps: 153.09 qps: 3055.18 (r/w/o: 2140.95/608.16/306.08) lat (ms,95%): 227.40 err/s: 0.00 reconn/s: 0.00

[ 60s ] thds: 20 tps: 167.67 qps: 3354.30 (r/w/o: 2347.85/671.10/335.35) lat (ms,95%): 223.34 err/s: 0.00 reconn/s: 0.00

SQL statistics:

queries performed:

read:                            125762

write:                           35932

other:                           17966

total:                           179660

transactions:                        8983   (149.56 per sec.)

queries:                             179660 (2991.27 per sec.)

ignored errors:                      0      (0.00 per sec.)

reconnects:                          0      (0.00 per sec.)

Throughput:

events/s (eps):                      149.5636

time elapsed:                        60.0614s

total number of events:              8983

Latency (ms):

min:                                 18.81

avg:                                133.67

max:                                922.85

95th percentile:                    240.02

sum:                            1200750.85

Threads fairness:

events (avg/stddev):           449.1500/6.83

execution time (avg/stddev):   60.0375/0.04

read:                125762   //读总数

write:                35932    //写⼊总数

other:               17966     //其他操作

total:                179660   //总操作数

    transactions:       8983   (149.56 per sec.)   //TPS每秒事务数

    queries:           179660 (2991.27 per sec.)   //QPS 每秒的读写请求数

ignored errors:      0      (0.00 per sec.)

reconnects:        0      (0.00 per sec.)

Throughput:

events/s (eps):                   149.5636

time elapsed:                    60.0614s   //总时间

total number of events:            8983     //总事务数

其中主要看：

transactions:       8983   (149.56 per sec.)   //TPS每秒事务数

queries:           179660 (2991.27 per sec.)   //QPS 每秒的读写请求数