On 31.01.10 23:19, Mr. Issa(*) wrote: > We have an Intel SSR212MMC2 system with 32GB of rams , 12 SATA HD;s > (each 2 are made raid0) raid0 as stripes or raid1 as mirrors? > port 80 traffic is routed from a mikrotik to the squid 2.7 stable7 box > (running on debian lenny) > > cache_dir aufs /cache1 1200000 16 256 > cache_dir aufs /cache2 1200000 16 256 > cache_dir aufs /cache3 1200000 16 256 > cache_dir aufs /cache4 1200000 16 256 > > fdisk -l > /dev/sdc1 1.8T 72G 1.7T 5% /cache1 > /dev/sdd1 1.8T 72G 1.7T 5% /cache2 > /dev/sde1 1.8T 72G 1.7T 5% /cache3 > /dev/sdf1 1.8T 72G 1.7T 5% /cache4 > > we noticed that when cache is nearly about 280GB (70GB on each > cache_dir), squid closes all sessions every 1 hour for 30 seconds, > then it works back normally... is there anything in cache_log ? -- Matus UHLAR - fantomas, uhlar@xxxxxxxxxxx ; 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. Fighting for peace is like fucking for virginity...
