[Btrfs-devel] btrfs stability

[Rekrutacja119]

2.6.24 kernel, also i see other people start to notice xfs problems too:
http://www.t2-project.org/zine/1/ ( i also saw other benchmarks)

it is second day that only thing i do is test different fs ( i need to
choose which one to use quickly ), and when it comes to small files, reading
them , listing large number of subdirs, xfs seems to have TRAGIC
performance. i mean it can be like 100 times slower in some cases. ( you can
see performance results of the other person in a link i pasted )

i will try 2.6.25-rc but i doubt it will bring back xfs to normal
performance state. something is really wrong with xfs, and i just see it on
my server for some time. how it is possible that my raid 0 made from 3 disks
was slow, most processes were in 'wait' state (top showing a lot of
processes waiting for hdd access) under heavy load, but... when i change
from this array of 3 disk in raid 0 on xfs, to just ONE disk (should be 3
times slower) but on reiser4 with compression, everything is working like it
was! i mean, reiser4 on hardware 3 times slower  was doing the same in real
life as xfs on better hardware. that's on server with more than 100 hits per
second.

reiser4 is working third week without problems (but it is just a temporary
solution, i had my own problems with reiser4 and i don't trust it enough to
use it longtime)

anyways, i hoped btrfs will help me with this, but if there are going to be
on-disk changes without backward compatbility, i think i will pass.


2008/3/8, Christoph Hellwig <hch at lst.de>:
>
> On Sat, Mar 08, 2008 at 07:50:02PM +0100, Rekrutacja119 wrote:
> > same for xfs is:
>
> which version of xfs did you test?  2.6.25-rc has some changes in this
> area that should improve metadata intensive workloads dramatically.
>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://oss.oracle.com/pipermail/btrfs-devel/attachments/20080308/80457a9b/attachment.html