MD1000-PERC5/E Performance issues

[Matthias Saou]

Mike McGrath wrote :

> On Sun, 28 Dec 2008, Mike McGrath wrote:
> 
> > I've read up on:
> > http://thias.marmotte.net/archives/2008/01/05/Dell-PERC5E-and-MD1000-performance-tweaks.html
> >
> > Which seems to have helped but I really don't think I'm seeing the
> > performance data I should be.  Take the attached sar data.  I started by
> > doing a recursive cp of some files from the filesystem to some other
> > drives, then started the sar dump.
> >
> > At marker 12:12:55, I started to do a cat /dev/sde > /dev/null.  (/dev/sde
> > is the array).
> >
> > Why was there such a significant jump there?  Also, why does sar think the
> > array was 100% utilized basically the whole time even though there's such
> > a difference in sec reads/s?
> >
> > Other issues.  /dev/sde is the underlying physical device (raid5).
> > However, it is divided up using lvm.  The copy mentioned above was from
> > a logical volume.  While I expected some overhead and performance hit, I
> > didn't expect it to be so huge and sporadic.  I've seen reads as low as
> > 3MB/s during a copy.
> >
> > Thoughts?
> >
> 
> Ok, upon further testing I don't think the majority of my issue is related
> to the MD1000 or the raid controller.  I'm seeing decent read speeds from
> large files.  So I'll get back to debugging unless someone has a tip.  I
> suspect another list would be better.

Do post back your findings here, though, as you're far from being the
first to face performance issues with the MD1000... ;-)

Matthias

-- 
Clean custom Red Hat Linux rpm packages : http://freshrpms.net/
Fedora release 10 (Cambridge) - Linux kernel 2.6.27.9-159.fc10.x86_64
Load : 6.88 6.56 5.68