Calculate the Qps/tps of Redis processing actual production request

Qps/tpsbenchmark tool for measuring REDIS processing actual production requests

The Redis release version comes with the Redis-benchmark Performance test tool;

Example:
With 50 concurrent connections, 100,000 requests are made, and the data for each request is 2kb.
Test host for Redis server performance with 127.0.0.1 Port 6379:

./redis-benchmark -h 127.0.0.1 -p 6379 -c 50 -n 100000 -d 2...====== SADD ======  100000 requests completed in 2.27 seconds  500 parallel clients  3 bytes payload  keep alive: 14.66% <= 1 milliseconds14.15% <= 2 milliseconds23.87% <= 3 milliseconds33.59% <= 4 milliseconds43.13% <= 5 milliseconds52.69% <= 6 milliseconds62.08% <= 7 milliseconds71.43% <= 8 milliseconds80.66% <= 9 milliseconds89.10% <= 10 milliseconds95.23% <= 11 milliseconds98.76% <= 12 milliseconds99.59% <= 13 milliseconds99.78% <= 14 milliseconds99.87% <= 15 milliseconds99.95% <= 16 milliseconds99.99% <= 17 milliseconds100.00% <= 17 milliseconds44150.11 requests per second

We focus on the final line of results: 44150.11 requests per second, both QPS4.4 million;
But the data here is only the test data, measured by the QPS can not represent the actual production capacity of processing;

Calculate the Qps/tps of Redis processing actual production request

In the actual production, we need to care about this indicator, in our application scenario,
What is the largest (QPS/TPS) that Redis can handle?

There are two ways to measure Redis QPS:

1. Estimate the size of the produced message, using the benchmark tool to specify the-D data block size to simulate;

2. Calculates the difference using the info statistic in REDIS-CLI;
   One of the REDIS-CLI's info commands total_commands_processed says: The total number of commands from start up to now, you can calculate the QPS by counting the difference between the two info commands:

//返回redis-cli info中total_commands_processed的结果 long getCmdProcessNum(redisContext *c){    string strVal;    getInfo(c,strVal);    map<string,string> mpVal;    parserInfo(strVal,mpVal);    map<string,string>::iterator  iter = mpVal.find("total_commands_processed");    if(iter != mpVal.end())    {        return atol(iter->second.c_str());    }    cout << "[err] not found total_commands_processed" << endl;    return 0;}

The program implementation is very simple, not all posted here, the complete code is described in GitHub:
Https://github.com/me115/cppset/tree/master/redisTPS

In actual production, run this program to count the actual QPS.
To run the example:

/opt/app/redisTPS#./redisTPS Time:  1  Process:40962  TPS:40839.48Time:  1  Process:43741  TPS:43610.17Time:  1  Process:38935  TPS:38779.88Time:  1  Process:31724  TPS:31597.61Time:  1  Process:32169  TPS:32008.96Time:  1  Process:31634  TPS:31476.62Time:  1  Process:46007  TPS:45823.71Time:  1  Process:50460  TPS:50258.96Time:  1  Process:47309  TPS:47167.50Time:  1  Process:50511  TPS:50359.92...

Posted by: Big CC | 14mar,2015
Blog: blog.me115.com [Subscribe]
Weibo: Sina Weibo

Calculate the Qps/tps of Redis processing actual production request