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
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