On 05/10/2011 12:09 AM, Bob Evans wrote:
> I am using 2.6.35.11-83.fc14.x86_64 (stock from Fedora Core 14).
>
> Did anything else change? How exactly do you do the file writes? What
> block size do you use? Is there a lot of create / delete churn?
>
> I ask because I believe both write block size and the degree of free
> space fragmentation matter. Larger block sizes and systems with more
> free space fragmentation may mitigate the issue.

Right.  I'd suspect fragmentation in an older volume would reduce the 
likelihood that you'd have very large extents.

> Can you try a simple dd test? Copy from /dev/zero with (default) 512
> byte blocksize and watch the jfsCommit CPU usage as the file gets
> larger. The hard part is that it matters how exactly JFS allocates
> blocks so you might have to repeat this test a few times to see it
> happening.

You may want to compare the results of doing this on an existing volume, 
and a newly formatted one.  I suspect the problem is a lot worse on the 
new one.

------------------------------------------------------------------------------
Achieve unprecedented app performance and reliability
What every C/C++ and Fortran developer should know.
Learn how Intel has extended the reach of its next-generation tools
to help boost performance applications - inlcuding clusters.
http://p.sf.net/sfu/intel-dev2devmay
_______________________________________________
Jfs-discussion mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/jfs-discussion

Reply via email to