Hi,
That is on a production server, not a Polygraph test. At busiest time: above 140 reqs/sec, using 8Mbit/s, average fds in use is between 3k-4k (50% is user-side and 50% server-side), and CPU usage is about 12% on a P4 2.8Ghz, RAM=2GB (cache_mem 400MB), and 95GB of cache_dir. cache_dir is ufs.
On the same server, squid with select/poll did starve CPU, and the number of open fds never bot bigger than 1600. When I started using epoll, the traffic and the number of concurrent connections did increase. I recommend epoll (at leas on Linux).
Regards,
G
On Wed, 3 Nov 2004 08:46:54 +0530
"Muthukumar" <kmuthu_gct@hotmail.com> wrote:
>
> Hai Gonzalo,
>
> > I've been using squid3 with epoll support for a couple of months.
> > In my case, squid with poll/select did consume up to 100% CPU. With epoll, CPU usage dropped to less than 10%.
>
> It seems to be great. How many requests are being generated per second?
>
> Are you using squid-3.0-pre3+latest patch for epoll().
> I am on analysis of squid-3.0pre3 + epoll() requests satisfaction / second there.
>
> Compilation:
> ./configure --prefix=/home/muthu/squidepoll --enable-epoll --with-aufs-threads=32 --with-descriptors=32768 --with-pthreads
> --enable-storeio=null,ufs,aufs --disable-poll --disable-select --disable-kqueue
>
> Configuration:
>
> cache_mem 90 MB ( 200 MB RAM )
> cache_dir null /dev/null
> cache_access_log none
> cache_store_log none
>
> > Long term average & max CPU usage:
> > http://webs.uolsinectis.com.ar/garana/x/cpu.4.png
> >
> > With epoll, CPU usage over the last 24 hours:
> > http://webs.uolsinectis.com.ar/garana/x/cpu.png
>
> Thanks for informations.
>
> Regards
> --Muthu
>
>
>
> ---
> =============== It is a "Virus Free Mail" ===============
> Checked by AVG anti-virus system (http://www.grisoft.com).
> Version: 6.0.786 / Virus Database: 532 - Release Date: 10/29/2004
>
>
Received on Wed Nov 03 2004 - 06:25:53 MST
This archive was generated by hypermail pre-2.1.9 : Wed Dec 01 2004 - 12:00:01 MST