[Ocfs2-users] has anyone experienced problems with ocfs2 1.2.5-1 using Emulex LP10000 HBA cards and EMC CX700 SAN's?

[Mike McCoy]

Thanks for the response.  No, not fencing.  The instability is (was - we've
already resolved it) related to general I/O - any I/O on the OCFS2 partition
would cause both the local and remote node to hang, i.e. the o2cb services
on both nodes would go into state 'D'.  So any subsequent calls to the OCFS2
partition would hang or timeout, or eventually respond after a serious
delay.  For example, running an "ls" command from either the local or remote
nodes would take 30 seconds or so to respond, if it responded at all.

It turns out the resolution was simple - the problem was the cabling to the
SAN switch.  Once the fiber cables were moved to different ports on the
fiber switch, and once the SAN people had finished re-configuring those
ports, all of OCFS2 stability problems disappeared.  So it was not as server
side issue to begin with.

Regardless, I appreciate the response.

-M


On 4/27/07, Sunil Mushran <sunil.mushran at oracle.com> wrote:
>
> We have LP10000 in our test machines.
>
> Is the instability in your system related to fencing?
>
> If so, update to OCFS2 1.2.5 and use more relaxed timeouts as
> listed in the FAQ.
>
> On Fri, 2007-04-27 at 14:50 -0400, Mike McCoy wrote:
> > Does anyone have any experience with Emulex HBA cards (LP10000) using
> > OCFS2, Linux AS4 U4 x86_64 AMD?  I'm trying to find out whether this
> > is a verified combination, if anyone has successfully used it.  I have
> > that hardware/sofware combination, and am experiencing
> > stability/performance/panic/hang issues with OCFS2.
> > _______________________________________________
> > Ocfs2-users mailing list
> > Ocfs2-users at oss.oracle.com
> > http://oss.oracle.com/mailman/listinfo/ocfs2-users
>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://oss.oracle.com/pipermail/ocfs2-users/attachments/20070427/c48fa09a/attachment.html