Hi, I'm planning to change the hardware of our internet proxies (we're using a two level proxy architecture) and benefits of this operation to also change the OS and squid version ; new Linux (FC 3), new kernel (2.6.10) and concerning the hardware : Bi-Xeon 3 Ghz + 6*.36.5 Go Ultra 320 + 2 GB RAM + gigabit network card. Each proxy having to handle about 80 req/s during peak times, and about 10000 users (up to 16000 according to the cachemgr.cgi). So I have a few questions concerning the new configuration : - I plan to set up three RAID 1 logical disks, 1 for the OS, and two for the cache dir. Do you think that's ok? What would be the recommandation for such a hardware configuration? - How many cache dir do you recommend to use? If several, each one on a hard drive? - What file system should I use for the cache dir : ext2, ext3 or reiserfs? With diskd, aufs? - I were using lfuda till now, do you think I should change of policy replacement? - Is there a link beetween the size of the cache_dir and cache_mem settings and the size of the swap partition? If anybody as any more "tips" or links on how to get the maximum performance of a squid box, I would be very interested. Thanx in advance. Pierre-E
