11. 【实战】对项目的主从redis架构进行QPS压测&&水平扩容支撑更高QPS

对刚刚搭建好的redis做一个基准的压测，测一下redis的性能和QPS（query per second）

redis-benchmark

redis自己提供的redis-benchmark压测工具，是最快捷最方便的，当然啦，这个工具比较简单，用一些简单的操作和场景去压测。

1. 对redis读写分离架构进行压测，单实例写QPS+单实例读QPS

cd /usr/local/redis-3.2.8/src
./redis-benchmark -h 192.168.0.106

-c <clients客户端> Number of parallel connections (default 50)
-n <requests请求> Total number of requests (default 100000)
-d <size数据大小> Data size of SET/GET value in bytes (default 2)

2. 根据你自己的高峰期的访问量，在高峰期，瞬时最大用户量会达到10万

3. 各种基准测试，直接出来：1核1G，虚拟机

默认测试参数： -c 100000，-n 10000000，-d 50

[root@eshop-cache01 src]# ./redis-benchmark -h 192.168.0.106
====== PING_INLINE ======
  100000 requests completed in 0.83 seconds
  50 parallel clients
  3 bytes payload
  keep alive: 1

99.96% <= 4 milliseconds
100.00% <= 5 milliseconds
100.00% <= 5 milliseconds
120918.98 requests per second

====== PING_BULK ======
  100000 requests completed in 0.88 seconds
  50 parallel clients
  3 bytes payload
  keep alive: 1

99.98% <= 2 milliseconds
100.00% <= 2 milliseconds
114025.09 requests per second

====== SET ======
  100000 requests completed in 1.66 seconds
  50 parallel clients
  3 bytes payload
  keep alive: 1

98.55% <= 1 milliseconds
99.55% <= 2 milliseconds
99.60% <= 4 milliseconds
99.64% <= 5 milliseconds
99.80% <= 6 milliseconds
99.83% <= 7 milliseconds
99.95% <= 8 milliseconds
99.95% <= 10 milliseconds
100.00% <= 10 milliseconds
60277.28 requests per second

====== GET ======
  100000 requests completed in 0.88 seconds
  50 parallel clients
  3 bytes payload
  keep alive: 1

99.79% <= 2 milliseconds
99.83% <= 3 milliseconds
99.89% <= 4 milliseconds
99.95% <= 10 milliseconds
99.97% <= 11 milliseconds
100.00% <= 11 milliseconds