redis自带一个很好的基准测试工具，记录一下测试效果，欢迎拍砖。我发现一个奇怪的情况，一些关于开源工具的博客，很少描述当时主机的一些情况，没有主机部分数据的记录，是有些不太完整的。
环境介绍
1.redis服务器（虚拟机，IP:192.168.163.156）
1M内存
20G硬盘
Linux操作系统
2.redis 客户端（虚拟机，IP:192.168.163.146）
1M内存
20G硬盘
3.监控 zabbix (虚拟机，IP:192.168.163.146）
1M内存
20G硬盘
测试了2次
测试记录
1.请求两1w，并发数为4
# /usr/local/redis/bin/redis-benchmark -h 192.168.163.156 -p 6379 -c 4 -n 10000
====== PING_INLINE ======
10000 requests completed in 0.46 seconds
4 parallel clients
3 bytes payload
keep alive: 1
99.77% <= 1 milliseconds
99.98% <= 2 milliseconds
100.00% <= 2 milliseconds
21598.27 requests per second
====== PING_BULK ======
10000 requests completed in 0.42 seconds
4 parallel clients
3 bytes payload
keep alive: 1
100.00% <= 0 milliseconds
23696.68 requests per second
====== SET ======
10000 requests completed in 0.43 seconds
4 parallel clients
3 bytes payload
keep alive: 1
100.00% <= 0 milliseconds
23364.49 requests per second
====== GET ======
10000 requests completed in 0.44 seconds
4 parallel clients
3 bytes payload
keep alive: 1
99.95% <= 1 milliseconds
100.00% <= 1 milliseconds
22935.78 requests per second
====== INCR ======
10000 requests completed in 0.43 seconds
4 parallel clients
3 bytes payload
keep alive: 1
100.00% <= 0 milliseconds
23201.86 requests per second
====== LPUSH ======
10000 requests completed in 0.42 seconds
4 parallel clients
3 bytes payload
keep alive: 1
100.00% <= 0 milliseconds
23923.45 requests per second
====== RPUSH ======
10000 requests completed in 0.43 seconds
4 parallel clients
3 bytes payload
keep alive: 1
100.00% <= 0 milliseconds
23148.15 requests per second
====== LPOP ======
10000 requests completed in 0.44 seconds
4 parallel clients
3 bytes payload
keep alive: 1
100.00% <= 1 milliseconds
22883.29 requests per second
====== RPOP ======
10000 requests completed in 0.44 seconds
4 parallel clients
3 bytes payload
keep alive: 1
100.00% <= 0 milliseconds
22883.29 requests per second
====== SADD ======
10000 requests completed in 0.43 seconds
4 parallel clients
3 bytes payload
keep alive: 1
99.97% <= 1 milliseconds
100.00% <= 1 milliseconds
23148.15 requests per second
====== SPOP ======
10000 requests completed in 0.43 seconds
4 parallel clients
3 bytes payload
keep alive: 1
100.00% <= 0 milliseconds
23474.18 requests per second
====== LPUSH (needed to benchmark LRANGE) ======
10000 requests completed in 0.42 seconds
4 parallel clients
3 bytes payload
keep alive: 1
100.00% <= 0 milliseconds
23640.66 requests per second
====== LRANGE_100 (first 100 elements) ======
10000 requests completed in 0.60 seconds
4 parallel clients
3 bytes payload
keep alive: 1
99.85% <= 2 milliseconds
99.91% <= 3 milliseconds
100.00% <= 3 milliseconds
16666.67 requests per second
====== LRANGE_300 (first 300 elements) ======
10000 requests completed in 1.07 seconds
4 parallel clients
3 bytes payload
keep alive: 1
100.00% <= 1 milliseconds
9337.07 requests per second
====== LRANGE_500 (first 450 elements) ======
10000 requests completed in 1.27 seconds
4 parallel clients
3 bytes payload
keep alive: 1
99.88% <= 1 milliseconds
99.97% <= 2 milliseconds
100.00% <= 2 milliseconds
7849.29 requests per second
====== LRANGE_600 (first 600 elements) ======
10000 requests completed in 1.64 seconds
4 parallel clients
3 bytes payload
keep alive: 1
99.72% <= 1 milliseconds
100.00% <= 1 milliseconds
6101.28 requests per second
====== MSET (10 keys) ======
10000 requests completed in 0.46 seconds
4 parallel clients
3 bytes payload
keep alive: 1
100.00% <= 0 milliseconds
21978.02 requests per second
LRANGE_600 (first 600 elements) 性能最差，6101.28 requests per second
2.请求两10w，并发数为4
[root@hadoop1 zabbix]# /usr/local/redis/bin/redis-benchmark -h 192.168.163.156 -p 6379 -c 4 -n 100000
====== PING_INLINE ======
100000 requests completed in 4.40 seconds
4 parallel clients
3 bytes payload
keep alive: 1
99.94% <= 1 milliseconds
99.98% <= 2 milliseconds
99.99% <= 3 milliseconds
100.00% <= 3 milliseconds
22742.78 requests per second
====== PING_BULK ======
100000 requests completed in 4.29 seconds
4 parallel clients
3 bytes payload
keep alive: 1
100.00% <= 1 milliseconds
100.00% <= 1 milliseconds
23288.31 requests per second
====== SET ======
100000 requests completed in 4.38 seconds
4 parallel clients
3 bytes payload
keep alive: 1
100.00% <= 0 milliseconds
22857.14 requests per second
====== GET ======
100000 requests completed in 4.41 seconds
4 parallel clients
3 bytes payload
keep alive: 1
99.99% <= 1 milliseconds
99.99% <= 2 milliseconds
100.00% <= 3 milliseconds
100.00% <= 3 milliseconds
22665.46 requests per second
====== INCR ======
100000 requests completed in 4.67 seconds
4 parallel clients
3 bytes payload
keep alive: 1
99.95% <= 1 milliseconds
99.98% <= 2 milliseconds
99.99% <= 3 milliseconds
100.00% <= 3 milliseconds
21422.45 requests per second
====== LPUSH ======
100000 requests completed in 4.30 seconds
4 parallel clients
3 bytes payload
keep alive: 1
99.99% <= 1 milliseconds
100.00% <= 2 milliseconds
100.00% <= 3 milliseconds
100.00% <= 3 milliseconds
23239.60 requests per second
====== RPUSH ======
100000 requests completed in 4.33 seconds
4 parallel clients
3 bytes payload
keep alive: 1
99.99% <= 1 milliseconds
100.00% <= 4 milliseconds
100.00% <= 4 milliseconds
23105.36 requests per second
====== LPOP ======
100000 requests completed in 4.35 seconds
4 parallel clients
3 bytes payload
keep alive: 1
99.99% <= 1 milliseconds
100.00% <= 2 milliseconds
100.00% <= 6 milliseconds
100.00% <= 6 milliseconds
22993.79 requests per second
====== RPOP ======
100000 requests completed in 4.38 seconds
4 parallel clients
3 bytes payload
keep alive: 1
99.99% <= 1 milliseconds
100.00% <= 1 milliseconds
22836.26 requests per second
====== SADD ======
100000 requests completed in 4.45 seconds
4 parallel clients
3 bytes payload
keep alive: 1
99.99% <= 1 milliseconds
99.99% <= 2 milliseconds
100.00% <= 2 milliseconds
22461.81 requests per second
====== SPOP ======
100000 requests completed in 4.39 seconds
4 parallel clients
3 bytes payload
keep alive: 1
100.00% <= 1 milliseconds
100.00% <= 1 milliseconds
22773.86 requests per second
====== LPUSH (needed to benchmark LRANGE) ======
100000 requests completed in 4.53 seconds
4 parallel clients
3 bytes payload
keep alive: 1
99.99% <= 1 milliseconds
99.99% <= 2 milliseconds
100.00% <= 2 milliseconds
22094.56 requests per second
====== LRANGE_100 (first 100 elements) ======
100000 requests completed in 5.63 seconds
4 parallel clients
3 bytes payload
keep alive: 1
99.98% <= 1 milliseconds
99.99% <= 2 milliseconds
99.99% <= 3 milliseconds
100.00% <= 3 milliseconds
17761.99 requests per second
====== LRANGE_300 (first 300 elements) ======
100000 requests completed in 11.27 seconds
4 parallel clients
3 bytes payload
keep alive: 1
99.48% <= 1 milliseconds
99.69% <= 2 milliseconds
99.87% <= 3 milliseconds
99.98% <= 4 milliseconds
100.00% <= 5 milliseconds
100.00% <= 6 milliseconds
100.00% <= 6 milliseconds
8876.26 requests per second
====== LRANGE_500 (first 450 elements) ======
100000 requests completed in 13.19 seconds
4 parallel clients
3 bytes payload
keep alive: 1
98.89% <= 1 milliseconds
99.44% <= 2 milliseconds
99.66% <= 3 milliseconds
99.90% <= 4 milliseconds
99.97% <= 5 milliseconds
100.00% <= 7 milliseconds
100.00% <= 7 milliseconds
7583.23 requests per second
====== LRANGE_600 (first 600 elements) ======
100000 requests completed in 17.35 seconds
4 parallel clients
3 bytes payload
keep alive: 1
99.67% <= 1 milliseconds
99.97% <= 2 milliseconds
99.98% <= 3 milliseconds
100.00% <= 4 milliseconds
5764.69 requests per second
====== MSET (10 keys) ======
100000 requests completed in 4.56 seconds
4 parallel clients
3 bytes payload
keep alive: 1
100.00% <= 3 milliseconds
100.00% <= 3 milliseconds
21939.45 requests per second
最差的是LRANGE_600 ，5764.69 requests per second
主机监控
另外，CPU load和Memory usage基本上没什么变化。
结论：
redis set,get等类操作，能到到2w吞吐量。
不同的操作类型，对CPU的影响也不同。
奇怪，redis对内存需求较稳定。