RE: [squid-users] Proxy Benchmarks

> -----Original Message-----
> From: Ow Mun Heng [mailto:Ow.Mun.Heng@wdc.com]
> Sent: Monday, November 29, 2004 6:02 PM
> To: Squid-List
> Subject: RE: [squid-users] Proxy Benchmarks
>
>
> On Tue, 2004-11-30 at 03:10, Chris Robertson wrote:
>> For my own experience with Squid benchmarking, I used polygraph.
>
> That was the program I was seeing on the net. The squid box does not
> even have GCC installed!
>
>> I could
>> not get it to compile on RedHat FC1, so I imaged a couple of boxes with
>> RedHat 9.
> So, it will compile on RH9? Do you have a spec file?? hehe..

Sadly I don't. I don't think I even have the source locally any more.
That's the problem with test boxes. They are constantly being re-purposed.
>
>>
>> I was just looking for a simple load test (I was trouble shooting a CPU
>> usage issue), so I used the conf file from
>> http://www.squid-cache.org/Benchmarking/Surrogate07/.
>
> Thanks for tips

You are welcome for what help I can offer. It's not much.
>
>> There's no better benchmark than real users.
>
> I understand, but better not to risk it not_being_able to withstand the
> grunt.

I hear you there.
>
> Do you have any experience with load_balance??

I have some. I have somewhere between 150 and 200 remote sites each with
their own squid server that all have to pass traffic by a collection point
at the central office. At the CO we have three Squid servers. Two are
acting as load balancing peers (each running one squid process) and the
third is a parent for the two (running two Squid processes on a dual proc
box) to give the world a single IP address that our traffic comes from. If
the parent dies, the two load balancers will surf direct. It's not the most
graceful solution, but it has been working for several months.

Currently traffic is peaking about 100 requests/sec and 1.5MB/sec, with CPU
usage under 50% on all processors (Intel Xeon 3.0GHz, 2GB RAM on the peers
4GB on the parent).

Chris
Received on Tue Nov 30 2004 - 11:18:01 MST