On Wed, Apr 04, 2007, Zak Thompson wrote: > The Iops off the san is the current bottleneck, actually I believe it's the > iops/disk command queue that's getting backed up as well. This is why I'm > looking to deploy squid/frontend caching services to ease the pain. That makes sense for the small to medium sized objects. Not so much for the large ones. > So this is the question, RAM or fast disk drives? Maybe multiple squids, > try to force images into memory, and the large content to disk? For the image squids: plenty of RAM for the small objects. For the medium sized objects: plenty of RAM and local disk. > Unfortunately this isn't a home proxy setup or my life would be much much > easier. > > Its clear that the more disk cache you have the longer it takes to access > etc, even running diskd but say 16,24 or 32gb of memory acting as a ramdisk? Diskd/Aufs are fine for large objects (say, more than a megabyte) but suffer for smaller loads. Thankfully COSS is mostly stable in Squid-2.6 and it shines when serving small content (under half a megabyte.) Adrian
