>-----Original Message----- >From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf >Of [EMAIL PROTECTED] >Sent: Monday, 4 August 2003 10:04 PM >To: [EMAIL PROTECTED] >Subject: RE: [SLUG] Benefits of source distro (Gentoo) somewhat elusive :-)
>[EMAIL PROTECTED] wrote on 04/08/2003 09:34:45 PM: --snip-- >> What specific tests should I run? I would like to test, for things other >> than just opening a spread sheet? How about >> >> Hitting a db? >> X rendering? >> File access? >> Compiling a kernel? >> >> >> >> Any other thoughts? >> >For the desktop: >I would like to see if there is any speed difference in OpenGL Games. >I'm not sure how many Linux gamers there are, but that would convince me >which distro is the best for my use. >Quake 3 Arena & Unreal Tournament 2003 would be good choices. I can do q3a but I will only be able to get the demo for UT. Should I run with or with out sound? I guess I will do both. >For the Server: >Perhaps things like 10 users retriving email then up the number to >100-150, 10 hits on a webpage then up the numbers again etc. >Making an enourmous encryption key (would this be considered accurate >since it gets it from /dev/random??). >Multiple hits on an sql database from the webpage? >I think the best benchmarking tests are real life tests and stressing >them. (If those numbers would be considered stressing??) >If I am going it install a high load email server, every little speed >optimisation counts. It is not easy to simulate tasks Like this, I guess I could script some thing up to hit it and then include the scripts as part of the test. Its easier to test simple things. -- SLUG - Sydney Linux User's Group - http://slug.org.au/ More Info: http://lists.slug.org.au/listinfo/slug