[Linux-cluster] Starter Cluster / GFS

[Steven Whitehouse]

Hi,

On Fri, 2010-11-19 at 14:17 +0000, Gordan Bobic wrote:
> Nicolas Ross wrote:
> >> Is this the storage you are sharing between the nodes? If so, how 
> >> exactly are you doing it?
> > 
> > Yes, that if for the shared gfs between the node. What we've decided to 
> > use is 2 raid-1 sets of 1 tb (2 disk each), added to a single vg of 2 
> > tb. Other raid sets will be mounted on a per-node and per service basis.
> 
> I see. In that case, I dare say that the writes hitting one disk at a 
> time is normal. It's a volume group, not RAID1 per se.
> 
> >> What version of RHEL are you using? Early versions of RHEL5 had GFS2 
> >> lock-up issues like you're describing. IIRC, GFS2 was only considered 
> >> stable from around RHEL 5.5 (technology-preview-only in earlier 
> >> versions of RHEL). Try with GFS1, it's a lot more mature.
> > 
GFS2 has been fully supported since RHEL 5.3

> > I am currently using RHEL6 beta, while waiting for centos 6 to be out in 
> > a couple of weeks. I dont' think gfs1 is included with rhel6.
> 
> Interesting. If that really is the same GFS2 bug you're tripping that I 
> bumped into 3 years ago and you're on RHEL6b, that is quite concerning. 
> Doubly so if GFS1 support has been completely removed.
> 
> Gordan
> 
There is no GFS1 for RHEL6 and above, since the purpose of GFS2 is to
provide an upstream, improved version of GFS1. If you've run into any
issues with the RHEL6 version we are very interested to know about it.
Please file a bugzilla so that we can collect all the info and look into
it,

Steve.