From: William L. I. I. <wl...@ho...> - 2002-08-06 20:05:47
|
On Mon, Aug 05, 2002 at 06:26:49PM -0700, Craig Thomas wrote: >>> The question is, what is causing the database to slow down when >>> the load of users is increased? Are there elements in the kernel >>> that should be monitored to determine any bottlenecks? What would >>> be an interesting thing to look for when we run this test again? >>> This is a relatively small database with a small load of users when >>> compared to an enterprise database model. It is our intent to find >>> the bottlenecks so that Linux can scale to handle larger database loads. On Mon, Aug 05, 2002 William Lee Irwin III wrote: >> Look for pagetable space consumption. BTW, what kernel version? On Tue, Aug 06, 2002 at 09:20:44AM -0700, Cliff White wrote: > What is the best way to measure pagetable space? /proc/meminfo? > The kernel version for these runs is stock 2.4.18. We have run > some other kernels, there is a rough table of results with links to > details at http://www.osdl.org/projects/dbt1prfrns/results/ > cliffw Sorry about that, I should have mentioned 2 things: (1) this is not the only issue, this is one of the things I'm particularly concerned about and know is an issue arising with databases (2) it'll take some backporting from 2.5.x to get the pagetable accounting into 2.4.x kernels. I can help with (2) in a day or two. Cheers, Bill |