[Ocfs2-users] Cluster setup

[Ryan Ordway]

On 10/11/07 3:28 PM, "Sunil Mushran" <Sunil.Mushran at oracle.com> spake:

> How is this a fs problem?
> 
> Ulf Zimmermann wrote:
>> We don't and when we were investigating why we had on the ProCurve
>> 4108gl reassembly problems, we were specific asked if we are doing
>> bonding or VLAN tagging (neither we were doing). Just looks like the
>> ProCurve are loosing packets without telling so. We switched in Cisco
>> 2960G-48 with Jumbo Frames now and haven't had any reassembly timeouts
>> since then. Global Cache timeout has gone down significant. Each
>> Interconnect for Oracle 10G has its own Cisco 2960G-48 now.

I'd say if the cluster is otherwise healthy but the FS dies, that is a FS
problem. A single point of failure is a single point of failure.


-- 
Ryan Ordway                          E-mail:   rordway at oregonstate.edu
Unix Systems Administrator             rordway at library.oregonstate.edu
OSU Libraries, Corvallis, OR 97370        Office: Valley Library #4657