Testifying that somaxconn change can make a difference

Posted by petermolnar on Server Fault See other posts from Server Fault or by petermolnar
Published on 2013-06-26T21:17:43Z Indexed on 2013/06/26 22:23 UTC
Read the original article Hit count: 158

Filed under:
|
|

I got into an argument on the net.core.somaxconn parameter: I was told that it will not make any difference if we change the default 128.

I believed this might be enough proof:

"If the backlog argument is greater than the value in /proc/sys/net/core/somaxconn, then it is silently truncated to that value" http://linux.die.net/man/2/listen

but it's not.

So does anyone know a method to testify this with two machines, one running, for example MySQL or LVS and the other is hammering it in a GBit network?

I'm opened to any solution, scripts are slightly more welcome.

© Server Fault or respective owner

Related posts about networking

Related posts about tcp