Megaraid with brakes on?

Dan Pritts danno at internet2.edu
Thu Jan 4 08:59:07 CST 2007


On Wed, Jan 03, 2007 at 11:08:55PM -0300, Martin Sarsale wrote:
> Dan,
> 
> >I'm not sure how good the ext3 file system is with loads like that;
> >you might also see improvement with another filesystem.  This is worthy
> >of  investigation.  Also, depending on how random your workload really
> >is you may see improvement by tuning the kernel's metadata buffering
> >(inode & directory caches; i'm not sure exactly what is available).
> 
> can you give me more info about meta data buffering? some keywords
> would be great.

look for inode cache & directory cache.  

This article is on topic but for a 2.4 kernel; might be a good
starting point though:

  http://kerneltrap.org/node/4462 


> 
> We're changing servers (not related to this issue) and we'll build a
> RAID10 in the new ones. What do you think it's better, assuming we
> want to have all the disks in a RAID?
> Hardware RAID0 and Software RAID1
> Software RAID0 and Hardware RAID1
> or Hardware RAID10 ?
> 

as i originally wrote, what i think would be best would be hardware RAID1
with software concatenation (which you can do with the linux "md" package; 
i think they call it "linear").

This is no less reliable than using RAID0 and my guess is it will work
better than RAID0 for your workload.

danno
--
Dan Pritts, System Administrator
Internet2
office: +1-734-352-4953 | mobile: +1-734-834-7224



More information about the Linux-PowerEdge mailing list