Thanks everyone for your response. For the record, I'm using a forwarding caching setup. Meaning this is for our internet traffic. (we are one of the largest k12's in the US) I'm running redhat5 for OS and I'm stuck with running 2.5/2.6 do to I'm required to filter my internet traffic. My vendor (netsweeper) requires their redir prcoess to run on 2.5 or 2.6. My netsweeper deployment consists of 5 policy server that talk to 1 database that phones home. This is why is say this is a massive deployment. Basically I have 26 servers and a single load balancer... We also have 10g pipes everywhere else, so the network and other transport layers aren't the issue. The reason I suspect the load balancer is because when I point directly to one of the proxies and bypass the lb. The traffic is smooth and not sluggish. I was going to open a support ticket with foundry this morning and see where I get. Ultimately I would like to do some benchmarks and some performance tuning and will ultimately post back for all your professional help. I would like to get the proxy count down if possible. Also another reason I suspect the lb is we recently starting outsourcing our email solution from in house exchange to gmail and have 24k users now on gmail. The problems have started surfacing since the we finished the migration. I know I need to re-optomize squid since our recent gmail change. Amos Jeffries-2 wrote: > >> >> Hello people, I'm having some bottlenecks on our squid deployement and I >> was >> wondering if anyone had any recommendations because I'm near out of >> ideas. >> Would someone change my architecture or does anyone have any experience >> with >> a squid deployment of this size? Basically we are pushing 600mb at >> 240,000k >> connections. When we reach speeds on our around that that number, we >> start >> seeing slow performance and getting alot of page timeouts. We are running >> 20 >> squid 2.6 boxes running dsr behind a single foundry gte load balancer. I >> recently had 18 squid boxes and thought we had a squid bottleneck but no >> change. I was kinda leaning in the direction of splitting it in half and >> doing multiple load balancers. Does anyone have any experience pushing >> this >> much traffic? > > I'd go to 2.7 if it was squid being slow. It has a number of small > performance boosters missing in 2.6. > > But, it does sound like a load balancer bottleneck if you had zero change > from adding two more Squid. The Yahoo and Wikimedia guys are the poster > installs for these types of Squid deployment and they use CARP meshing. > > PS: We are very interested in getting some real-world benchmarks from > high-load systems like yours. Can you grab the data needed for > http://wiki.squid-cache.org/KnowledgeBase/Benchmarks ? > > Amos > > > > > -- View this message in context: http://www.nabble.com/Massive-Squid-Deployment-tp22805247p22826365.html Sent from the Squid - Users mailing list archive at Nabble.com.
