MySQLはbrewで入れてTiDBはtiupで立ち上げた直後にsysbenchを実行してみた結果。Mac上でDBを上げてMac上でsysbenchも実行するという本番ではまあ無いような構成でやっています。結果としてはMySQLの方が倍近いQPSを出していました。TiDBのスケールアップも試してみたが大きく数値は変わらず。あまり有用なデータは取れませんでした。なんでだろ。
| DB | QPS |
|---|---|
| MySQL | 5811.14 |
| TiDB | 2063.65 |
MySQL
sysbench oltp_read_write --table-size=1000000 --mysql-db=test --mysql-user=root --mysql-host=127.0.0.1 --mysql-port=3306 run
sysbench 1.0.20 (using system 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!
SQL statistics:
queries performed:
read: 40698
write: 11628
other: 5814
total: 58140
transactions: 2907 (290.56 per sec.)
queries: 58140 (5811.14 per sec.)
ignored errors: 0 (0.00 per sec.)
reconnects: 0 (0.00 per sec.)
General statistics:
total time: 10.0037s
total number of events: 2907
Latency (ms):
min: 2.04
avg: 3.44
max: 63.05
95th percentile: 3.55
sum: 9997.75
Threads fairness:
events (avg/stddev): 2907.0000/0.00
execution time (avg/stddev): 9.9977/0.00
TiDB
sysbench oltp_read_write --table-size=1000000 --mysql-db=test --mysql-user=root --mysql-host=127.0.0.1 --mysql-port=4000 run
sysbench 1.0.20 (using system 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!
SQL statistics:
queries performed:
read: 14448
write: 4124
other: 2068
total: 20640
transactions: 1032 (103.18 per sec.)
queries: 20640 (2063.65 per sec.)
ignored errors: 0 (0.00 per sec.)
reconnects: 0 (0.00 per sec.)
General statistics:
total time: 10.0007s
total number of events: 1032
Latency (ms):
min: 7.20
avg: 9.69
max: 55.58
95th percentile: 23.95
sum: 9997.03
Threads fairness:
events (avg/stddev): 1032.0000/0.00
execution time (avg/stddev): 9.9970/0.00
