[squid-users] aufs threads relationship to request rate

Guys

I'm currently benchmarking Squid, using Web Polygraph, and was wondering at
what value to pitch the number of aufs threads. I'm benchmarking at various
levels in the 200-500 requests/sec area. I'm using 4 x 8G caches and 2G
memory (which I feel should be increased). I upped the default aufs threads
to 128 for a 180 user benchmark, with good results. But a 300 user test
started giving lots of queue congestion warnings. I increased to 256 and
things look better, but still with some congestion warnings.

I understand that going too high with this parameter brings it's own
problems. So how do we judge an appropriate number of aufs threads to run
with?

TIA

Jeff

--
Jeff Richards
Technical Consultant
Unix Enterprise Services
jeff.richards@centrelink.gov.au
Tel: +61 2 6219 8125
Important:  This e-mail is intended for the use of the addressee and may contain information that is confidential, commercially valuable or subject to legal or parliamentary privilege.  If you are not the intended recipient you are notified that any review, re-transmission, disclosure, use or dissemination of this communication is strictly prohibited by several Commonwealth Acts of Parliament.  If you have received this communication in error please notify the sender immediately and delete all copies of this transmission together with any attachments.