Your are right fred,
It is is a difficult deal for us too...
aufs -> good speed but more troubles ( assertion failed, "empty()", HTTP
reply without date.... unstable rock system ) and must deal with squid
crashes ( watchdog)
diskd -> more stable but slower...
Le 15/07/2015 12:46, FredB a écrit :
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
_______________________________________________
squid-users mailing list
squid-users@xxxxxxxxxxxxxxxxxxxxx
http://lists.squid-cache.org/listinfo/squid-users