Re: raid5 resync aborted under heavy XFS use

[Chris Bednar <cjb@xxxxxxxxxxxxxxxxxxxxxxxxx>]

    Sorry for the followup followup...

> there are some slight problems with xfs over software raid5 that have just 
> been fixed in the CVS tree. There were also IO stall problems with this 

    The only fix I saw for this was to linux/fs/pagebuf/page_buf.c,
mentioned in <http://oss.sgi.com/projects/xfs/mail_archive/0107/msg01102.html>
and of course the code has changed quite a bit between the 1.0.1 release
and this patch, but it looked for all the World to me like the thing
this was undoing wasn't being done in 1.0.1, so I'm not convinced this
is the same bug, fixed tho it may be elsewhere.


----
Chris J. Bednar   <http://optics.tamu.edu/~bednar/>
Director, Distributed Computing Product Group
http://AdvancedDataSolutions.com/