xfs
[Top] [All Lists]

Re: [reiserfs-list] Re: Benchmarking ReiserFS, ext2, XFS

To: Steve Lord <lord@xxxxxxx>, Federico Sevilla III <jijo@xxxxxxxxxxxxxxx>
Subject: Re: [reiserfs-list] Re: Benchmarking ReiserFS, ext2, XFS
From: Chris Mason <mason@xxxxxxxx>
Date: Wed, 16 May 2001 11:18:04 -0400
Cc: Linux XFS Mailing List <linux-xfs@xxxxxxxxxxx>, reiserfs-list@xxxxxxxxxxx
In-reply-to: <200105161451.f4GEpcj17003@jen.americas.sgi.com>
Sender: owner-linux-xfs@xxxxxxxxxxx
On Wednesday, May 16, 2001 09:51:38 AM -0500 Steve Lord <lord@xxxxxxx>
wrote:

> 
> Thanks for the info, I just took a look at the reiserfs archive,
> and subscribed to the list. Interesting that no one on the xfs
> list was contacted about this with questions such as how to configure
> xfs etc (I could say mindcraft here but that might be inflamatory ;-).

I hope everyone on the reiserfs lists realizes how informal these
benchmarks are.  If you want a real idea of how <foofs> performs, you've
got to talk with someone who knows a lot about foofs to make sure things
are fair.

> It would certainly be interesting to see which config options were
> used in the filesystem part of the kernel compile. The RPMs were
> shipped with all features turned on which will impact performance,
> turning off quotas and acls would be a good thing.

reiserfs acls are so fast, its like they aren't even there ;-)

> 
> Anyway, I am not surprised reiserfs wins on small file
> tests, someone independent might want to ask what happens if you
> pull the power in the middle of the test. I suspect the answer on
> reiserfs is that almost nothing is on the disk after reboot, the file
> creation/removal part of bonnie++ (30000 files created and removed
> twice) can complete without disk I/O on reiserfs.
> 

In 2.4.4, the metadata flush time is the same as the bdflush metadata
interval (5 secs by default).  Our bonnie++ numbers should be a little
worse  for the file creation tests now.

-chris


<Prev in Thread] Current Thread [Next in Thread>