How to identify the maximum TCP request limit
I’m running the redis-benchmark tool to send N requests from server A to B.
This tool generates a TCP request and receives a response.
Some how to stop when the number request reaches 51000 and does not exceed the value.
I tried the same approach with different machines and processed almost 100,000 requests per second.
What factors limit the number of these requests?
Solution
A major factor is the number of open file descriptors that a process is allowed to create. This is true for both the server side and the client side.
<a href=”http://redis.io/topics/clients” rel=”noreferrer noopener nofollow”>http://redis.io/topics/clients and http://redis.io/topics/benchmarks both have information you should deal with to determine what exactly your problem is. Without your setup details, it’s unlikely that we’ll provide more specific information.
Check your ulimits and your server configuration to make sure that you have configured your respective systems to the limits you intend to benchmark and that you will be able to get more data available.