[Linux-cluster] which is better gfs2 and ocfs2?

yvette hirth yvette at dbtgroup.com
Sat Mar 12 23:00:41 UTC 2011


Alan Brown wrote:

> Those users are paying for GFS installations.

oh?  i've got the full cluster suite running here, from CentOS.  i don't 
remember receiving a bill...

> In addition the same problem appears every time a backup is run - even 
> incrementals need to stat each file in order to find out what's changed. 
> Having a 2million file filesystem take 28 hours to run an incremental vs 
> 10 minutes for the same thing on ext3/4 doesn't go down at all well.

if you have 2million files on one filesystem, methinks that GFS et al 
are doing the best that they can.  perhaps GFS is not the real issue...

we had issues with GFS; we flattened the big directories, and now things 
run much smoother.  slower than extX, and much slower than XFS, but 
since we can backup two machines to the same filesystem concurrently, 
we're not complaining...

> What you've said is right, but also comes across to the average academic 
> as condescending - which is a fast way of further alienating them.

"There is no offense where none is taken."
--old Vulcan sayinig

> As far as most users are concerned, a computer is a black box. You put 
> files in, you get files out. If it's shockingly slow it's _not_ their 
> problem, it's the problem of whoever installed it - and it doesn't help 
> that GFS has been sold as production-ready when it's only useful in a 
> limited range of filesystem activities.

while we have found that GFS is indeed production ready, one doesn't use 
a moving van to participate in the Indy 500.  caveat emptor.

yvette




More information about the Linux-cluster mailing list