Just a little word about aufs, just for information, to avoid squidaio_queue_request: WARNING - Queue congestion squidaio_queue_request: WARNING - Queue congestion squidaio_queue_request: WARNING - Queue congestion squidaio_queue_request: WARNING - Queue congestion I had increase this value (sorry I can't remember the exact number) --with-aufs-threads=xxx But the "load average" - top counter - was very important and I should back to diskd So only diskd could works good (rock store was worst than aufs ...), with my load and my usage, but perhaps I should test with a more recent version Tested on Debian _______________________________________________ squid-users mailing list squid-users@xxxxxxxxxxxxxxxxxxxxx http://lists.squid-cache.org/listinfo/squid-users