Re: OCFS2 Filesystem inconsistency across nodes

[Claudio Martins]

On Wednesday 15 February 2006 17:50, Nohez wrote:
>
> Now started bonnie++ on one node while the same volume on the other node
> is mounted and is in quiescent stage. Its been more than 5 hours now
> and both the nodes are up & running. Seeing some very high load of >8 at
> times on the node running bonnie++. Test node has 4GB RAM and bonnie++
> is creating files of 8GB to test IO performance. Will start bonnie++
> on both the nodes concurrently later.
>

 Nice. It'll be interesting when you start concurrent tests. I think the last 
fixes from -mm made it better, but I'm still getting DLM errors and processes 
hung in D state when using tar concurrently reading kernel trees on 3 nodes. 
I'd like to know if you'll get the same or not.
 I'll be sending kernel messages and a more complete report later this 
evening. 

Regards

Claudio

-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/