On 22.07 07:57, Scott Phalen wrote: > I have searched the archives and can't seem to find a solution to my issue. > My server sits at 92% or higher for CPU utilization 24 hours a day. During > my peek hours it is at 99% with a load of about 35 requests per second. My > plan is to convert this to reiserfs in the next month and spread the cache > over both disks instead of using RAID0.
good idea and should help much. However, if it is squid who eats 99% of CPU, it is probably due to slow machine (...) or badly configured squid... > I am using a Dell PowerEdge 650 P4 3.0Ghz processor > 2 - 145Gig 15K RPM hard disks - striped > 2 Gig RAM > Linux 2.1AS > Squid-2.5STABLE6 > Below is my squid.conf minus the ACLs and cachemgr info: > cache_mem 128 MB I'd increase this probably to 1GB... > maximum_object_size 128 MB this is imho too much for 13GB storage... it would probably be OK with heap replacement policies like LFUDA (i'd use that one) > ipcache_size 0 > fqdncache_size 0 I am not sure if 0 in these cases means unlimited - check it... -- Matus UHLAR - fantomas, [EMAIL PROTECTED] ; http://www.fantomas.sk/ Warning: I wish NOT to receive e-mail advertising to this address. Varovanie: na tuto adresu chcem NEDOSTAVAT akukolvek reklamnu postu. Depression is merely anger without enthusiasm.
