Dave Caroline wrote:
The delays in the wikiserver system are caused by waiting for I/O- the time taken for mechanical devices to seek a particular block of data. If the data is being served from a squid cache rather than from a cache on the wiki server, how will this reduce the overall I/O blocking problem?
Agreed
I think you're both wrong about this. This is not where the bottleneck is, when Geoffrin is running. It *is* where the bottleneck is right now, because we're limping along on broken hardware.
--Jimbo