On 29-May 10:58, James Kahn wrote: > On Wed, 2002-05-29 at 22:16, Andrew Suffield wrote: > > On Wed, May 29, 2002 at 09:48:33AM +0200, Ulrich Eckhardt wrote: > > > Hmmm, everyone can do so on their own machines easily .... how are the > > > results on yours ? :) > > > > > > I'll give it a more systematic try with a linux-kernel sourcetree instead of > > > my cvsroot, but that's later today. > > > > That is not a deterministic test. It doesn't provide a particularly > > useful benchmark; it involves a semi-random pattern of disk access > > which is hopelessly skewed by environmental factors. > > Far from being a "deterministic" test, it's not a test of CPU at all. > The CPU will be mostly idle waiting for data from the hard disk and bus. =) I want your box. Even on my Athlon box with lots of ram, a kernel compile is definately cpu bound. I'll give you that disk access adds too much "noise" for benchmarking. A "find . -exec cat {} >/dev/null \;" in the build tree speeds things greatly, but then I have 512M ram. Building a test framework around a kernel untar then build isn't that hard. (Even I can do it...that's saying something.) That said, this tread seems to be heading now where fast. Wouldn't it just be nice of woody+1 could be rebuilt using tools? Software shouldn't need hand holding. Thomas [snip]
Attachment:
pgpbnbzLHbDxH.pgp
Description: PGP signature