RE: {bb} Monitoring Power5 LPARs on RS/6Ks

["Fay, Michael" <Michael.Fay@pepperdine.edu>]

You load a client on each LPAR. It doesn't present any specific oddities
relating to things like load averages, but we do have problems with
monitoring virtualized disk on occasion. The big problem with monitoring of
virtualized function on LPARs is that you can't put a client on VIO servers,
so anything that is truly virtualized cannot be truly monitored. You just
have to pay clear attention to what you are doing on the VIO servers. 

The main area you might have problems with is network. VIO network response
from other machines can be spotty if the VIO server is not set up properly. 
-----Original Message-----
From: owner-bb@bb4.com [mailto:owner-bb@bb4.com] On Behalf Of Philip Clark
Sent: Friday, May 26, 2006 2:25 PM
To: bb@bb4.com
Subject: Re: {bb} Monitoring Power5 LPARs on RS/6Ks

On Fri, 2006-05-26 at 02:16, Richard Beals wrote:
> All,
> 
> A client is considering the migration to virtualized systems on Power5
> architecture... LPARs, and all that.
> 
> I anticipate they will find some occasional oddities, particularly
> around such things as reporting of load averages.
> 
> Does anyone have experiences, tips, or "lessons learned" they'd like to
> share?

First the disclaimer. I have no idea what I'm talking about here.
I apologise if it is irrelevant and/or just plain wrong.

I imagine that the optimum solution would be to install a BB client
under the native OS and then add extension scripts to gather information
about the virtual instances.

If the native OS on the machine is AIX, then you may be able to use this
to monitor the LPARs:

  http://www.deadcat.net/viewfile.php?fileid=670

If, OTOH, it runs something more esoteric, there are alternative clients
for things like z/OS and z/VM:

  http://www.deadcat.net/viewfile.php?fileid=797

  http://www.deadcat.net/viewfile.php?fileid=820


Cheers, Phil.



-- 
But in our enthusiasm, we could not resist a radical overhaul
of the system, in which all of its major weaknesses have been
exposed, analyzed, and replaced with new weaknesses.
(Bruce Leverett, "Register Allocation in Optimizing Compilers")

--
=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-==-=-=-=-=-=-=-=-=-=-=-=
To unsubscribe from this list, or to subscribe to the bb-digest list
send e-mail to mailto:majordomo@bb4.com with unsubscribe bb -and/or-
subscribe bb-digest in the BODY of the message.
--
=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-==-=-=-=-=-=-=-=-=-=-=-=
To unsubscribe from this list, or to subscribe to the bb-digest list
send e-mail to mailto:majordomo@bb4.com with unsubscribe bb -and/or-
subscribe bb-digest in the BODY of the message.