Theoretical connections/second limit using Varnish

[Nick Loman]

Poul-Henning Kamp wrote:
> In message <49F9BF57.4020909 at loman.net>, Nick Loman writes:
> 
>> Precisely, we only have perhaps 50 PHP children serving requests, so if 
>> these are kept open to serve idle keep-alive connections, that severely 
>> limits the numbers of dynamic page requests we can serve.
> 
> The difference between letting them say open 10msec and 0msec is very
> significant when it comes to performance.

Hi Poul-Henning,

Which way round do you mean?

Apache specifies Keep-Alive in seconds, and my sites will certainly die 
if I set it to even 1 second.

I've no problem with Varnish performance right now, it works really well 
for me. And solves the problem nicely of how to give Keep-Alive 
connections to my users whilst maintaining only a small pool of PHP 
FastCGI processes.

But I would like to eliminate my thousands of TIME_WAIT sockets if at 
all possible, as this represents a scaleability ceiling right now. Of 
course I could just throw more webservers at the problem - if necessary.

Cheers!

Nick.