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.
Does anyone know a method to testify this with two machines, sitting on a Gbit network? The best would be against MySQL, LVS, apache2 ( 2.2 ), memcached.