Sent to a Squid developer I just had a discussion with on IRC...-------- Original Message --------Subject: Squid: Conversion of disk cache reads into cache misses when disk bandwidth is saturatedDate: Sun, 30 Apr 2006 14:07:29 +0200From: Mark Bergsma <mark@...>Hi. As discussed on IRC, a summary:We are having some problems efficiently using disk caches in ourWikimedia Squid cache cluster. When the disk cache is too big, diskcache reads can easily saturate all of the available disk bandwidth onall disks. This makes Squid very slow as it keeps queuing up therequests. Therefore we deploy many Squids without disk caches and havethem memory only, which results in much faster Squids (lower requesttimes with much shorter distribution tails), but the total hit rate suffers.It would be neat if Squid could decide to convert a disk cache read to acache miss when the relevant cache_dir is overloaded. That would makeSquid more load-tolerant reduces the need for administrators to tune andreadjust disk caches for each server over time.As Squid already does this for cache *writes*, this should be fairlyeasy to implement for reads too. Let me know when you have something,I'll be happy to test patches on a test server in our cluster. I'llstick around on IRC too...Thanks,-- Markmark(a)nedworks.org