On Thu, 4 Jun 2009 06:32:53 am Eric Dumazet wrote:

Rusty Russell a écrit :

quoted

On Sat, 30 May 2009 12:41:00 am Eric Dumazet wrote:

quoted

For TCP, I agree your patch is a huge benefit, since its paced by remote
ACKS and window control

I doubt that.  There'll be some cache friendliness, but I'm not sure
it'll be measurable, let alone "huge".

...

We can see sock_wfree() being number 2 on the profile, because it touches
three cache lines per socket and transmited packet in TX completion
handler.

Interesting, I take it back: got some "after" stats as well?

Also, taking a reference on socket for each xmit packet in flight is very
expensive, since it slows down receiver in __udp4_lib_lookup(). Several
cpus are fighting for sk->refcnt cache line.

Now we have decent dynamic per-cpu, we can finally implement bigrefs.  More 
obvious for device counts than sockets, but perhaps applicable here as well?

Rusty.