Just to add a bit of "untheoretical" info - we have quite often observed situation when cache is saturated (i.e. percent of dirty blocks is higher than certain threshold). In this situation the box starts delivering very poor service (if any) until it flushes enough to disk. 2005/11/18, Mark Brinsmead <mark.brinsmead@xxxxxxx>: > P.S. These comments are based on "theory" (or maybe even speculation). > It's been years since I have done any serious I/O benchmarks. I do, > however, still know how to read a datasheet and compute (estimate) "Random > IOs per Second" for a disk. If anybody has solid benchmark results > (particularly measuring Random IOs per Second over a long period of time) I > would be quite interested in seeing them... > > -- Best regards, Alex Gorbachev -- //www.freelists.org/webpage/oracle-l