[Linux-cluster] Starter Cluster / GFS

[Gordan Bobic]

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.
> 
> 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