On Wed, 22 Nov 2006, Stefan Tibus wrote:
> I wonder what the comparison would look like, if the system
> was working with some standard load (on CPU and fs) while running
> the actual fs-benchmark.

Hm, I'd have to create a *constant* workload for all tests, so that all 
filesystems are tested under the same conditions

> Especially regarding the huge (90%+)
> CPU-load imposed by ext3 when deleting files...

Yes, the CPU load is indeed high, but the results are much highr too: in 
theory(!), if ext3 would only use 20% as the rest, it'd still come out 
with 6000 deletes/s, still higher than the rest.

Do you/anybody know a better benchmark/procedure to test things like 
this?

Thanks,
Christian.
-- 
BOFH excuse #182:

endothermal recalibration

-------------------------------------------------------------------------
Take Surveys. Earn Cash. Influence the Future of IT
Join SourceForge.net's Techsay panel and you'll get the chance to share your
opinions on IT & business topics through brief surveys - and earn cash
http://www.techsay.com/default.php?page=join.php&p=sourceforge&CID=DEVDEV
_______________________________________________
Jfs-discussion mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/jfs-discussion

Reply via email to