On 15/07/2015 11:41 p.m., Stakres wrote: > Hi Amos, > > Sorry but the Rock mode is totaly bugged, the worst mode to use here. > We did tons of tests, small, medium and big rock cache, all crash process > after process. We have definitively abandonned the Rock mode while it'll be > the same results. This seems to be specific to some use, but not others. Rock is young yet so not all use-cases are stabilized. (Particularly if you're talking about the Squid-3.4 in Debian's.) Specifics about those issues would help a lot if you are able to assist tracking that down. > > So, it seems we'll have to switch all boxes from diskd to aufs, but I think > we could survive > Anyway, we liked the diskd because we see good stability, but the HITed > objects are really too slow, all my clients are complaining, that's why we > did many tests yesterday and we found these times... Thanks for that. The AUFS results bear out what I know of it. But I am quite surprised you got diskd going that fast at all. What physical disk backend are you using? Amos _______________________________________________ squid-users mailing list squid-users@xxxxxxxxxxxxxxxxxxxxx http://lists.squid-cache.org/listinfo/squid-users
