Re: an idea about dual cpus

I know someone who runs squid on dual PIII500, they use single squid
compiled with async-io, machine has 1024M RAM and about 150GB SCSI HD
space. It goes up to 6Mil objects in cache and serves about 3000-4000
requests per minute. AFAIK load average on that machine never goes higher
than 1. Thing started to work better when they started to run squid with
async-io enabled. f you need more info you can contact me in person.

On Mon, 15 Nov 1999, Dustin Byford wrote:

|Our setup is currently consuming 80% of the cpu (average) with regular
|peaks to 100%. The machine is not io or network bound. So in an effort
|to fix the situation I was thinking about using smp. What does everyone
|think about this.
|
|Run 2 squid processes under different config files/log files/etc. Let
|them use icp to talk to each other through loopback. Give each process
|2 of the 4 disks. This way each squid process will get scheduled on 1
|cpu. Of course the overhead of icp may be to inefficient. What do you
|think?
|
|
| --Dustin
|

Leonid Igolnik aka LiM
Received on Mon Nov 15 1999 - 19:21:00 MST