Those are good if you want to know more about _why_ your utilization metric is high, but looking at them on their own is only part of the story.  Nothing you see by looking at the domains is going to help you _more_ than just monitoring utilization, because utilization _includes_ the only domain that could cause you pain by being over utilized. 

PF

From: Scott Eno <s.eno@me.com>
Date: Thursday, April 21, 2016 at 12:13 PM
To: Paul Flores <Paul.Flores@netapp.com>
Cc: "NGC-steve.klise-wwt.com" <steve.klise@wwt.com>, Toasters <toasters@teaparty.net>
Subject: Re: OnCommand CPU report question for 2.x OPM

Don’t know if we’re allowed to attach images, but I’ll try.  If you can see the attached image, you see that marrying OCPM -> NetApp Harvest -> Grafana you get a really nice breakdown of these processes.

Sadly no alerting, just monitoring.




On Apr 21, 2016, at 1:07 PM, Flores, Paul <Paul.Flores@netapp.com> wrote:

utilization is supposed to include CPU load, kahuna load and disk busy %
as factors in it¹s value.

In theory, it should make a better metric for node utilization than just
CPU cores by themselves.  While I recognize that is not really helpful if
you are trying to do a deep dive into Œwhy¹ things are happening on a
given node, OPM is supposed to make it easy for you to alarm on
Œperformance of node is going¹, without having to do if cpu > x and kahuna
y and disk busy > z then page me that the controller is melting.


Paul Flores
Professional Services Consultant 3
Americas Performance Assessments Team
NetApp
281-857-6981 Direct Phone
713-446-5219 Mobile Phone
paul.flores@netapp.com

http://www.netapp.com/us/media/ds-3444.pdf
<http://www.netapp.com/us/solutions/professional/assessment.html>




On 4/21/16, 10:33 AM, "toasters-bounces@teaparty.net on behalf of Scott
Eno" <toasters-bounces@teaparty.net on behalf of s.eno@me.com> wrote:

Hi Steve,

I ended up having to follow NetApp¹s instructions on sending OCPM data to
Graphite (and later Grafana via the NetApp harvest toolbox tool), then
graphing the individual CPU counters.  OCPM just tracks ³utilization² of
the node, which is just not helpful.



On Apr 21, 2016, at 11:28 AM, Klise, Steve <Steve.Klise@wwt.com> wrote:

In former versions of DFM or whatever it was called now, I was able to
chart individual CPU¹s in Performance Manager.  Now, I only see an
average across all processors w/ 2.x OnCommand Performance Manager.  I
know I can drop down to the console, and run a sysstat -whatever... but
was wondering if I was missing something for OnCommand Performance
Manager to see, or graph individual CPUs.  Is this an option, or how
would I enable, setup?  I am running the LOD, and can't see how this
can be done... If its not available, that was of value to some of my
customers.  

Steve



_______________________________________________
Toasters mailing list
Toasters@teaparty.net
http://www.teaparty.net/mailman/listinfo/toasters


_______________________________________________
Toasters mailing list
Toasters@teaparty.net
http://www.teaparty.net/mailman/listinfo/toasters