| |
|
RSS Feed - WebSphere MQ Support
|
RSS Feed - Message Broker Support
|
  |
|
| WMQI on OS/390 compared to AIX |
« View previous topic :: View next topic » |
| Author |
Message
|
| zpat |
 Posted: Mon May 12, 2003 11:55 pm Post subject: WMQI on OS/390 compared to AIX |
 |
|
Jedi Council
Joined: 19 May 2001
Posts: 5866
Location: UK
|
I would be interested to hear from anyone who has chosen to use WMQI on OS/390 as opposed to on UNIX (AIX) and in particular the cost comparison case that they used to choose the mainframe.
Any data on the number of MIPS consumed would be of interest as I am trying to work out (short of installing it) whether a migration to OS/390 would be a good idea or not in cost terms.
At present I can't even persuade IBM to tell me the license cost for WMQI on OS/390 which suggests that it is expensive. |
|
| Back to top |
|
 |
| bolek |
| Posted: Tue May 13, 2003 2:26 am Post subject: Re: WMQI on OS/390 compared to AIX |
|
|
Apprentice
Joined: 25 Jul 2002
Posts: 35
Location: Germany
|
|
| Back to top |
|
|
| migstr |
| Posted: Wed May 14, 2003 6:13 am Post subject: |
|
|
Apprentice
Joined: 05 Jun 2002
Posts: 34
Location: New York
|
Hi,
Have you tried using the WMQI AIX and zOS performance white papers? There are some estimates for cpu ms/message for different nodes and types of messages. If you could get a guesstimate on number of messages,sizes, types (persistent/non-persistent) per year along with cost per cpu sec for peak, non-peak processing; you might be able to come up with a cost comparison.
_________________
Thanks, Margaret
-------------------------------------------------------
IBM Certified Specialist - MQSeries, Websphere MQ Integrator
IBM Certified Solutions Expert - MQSeries, Websphere MQ Integrator
IBM Certified Developer - MQSeries |
|
| Back to top |
|
|
| zpat |
| Posted: Thu May 22, 2003 6:48 am Post subject: |
|
|
Jedi Council
Joined: 19 May 2001
Posts: 5866
Location: UK
|
Yes, I did see that, but the problem is that different MQSI applications are entirely different in performance. Without running my apps on the same platforms that Tim Dunn used, the figures don't relate to mine much.
To extrapolate the differences means knowing how to compare Intel or RISC performance to S/390.
IBM refuse to publish SpecINT or TPC/C figures for the S/390 platform so it's almost impossible to get a factor between platforms.
However I have had an idea, if I compare our applications to Tim Dunn's on Intel using SpecINTs, and then use his relative performance to S/390 - along with the appropriate S/390 relative performance (MSU) for our mainframe, I might get an answer. |
|
| Back to top |
|
|
|
|
|
| |
|
Page 1 of 1 |
|
You cannot post new topics in this forum
You cannot reply to topics in this forum
You cannot edit your posts in this forum
You cannot delete your posts in this forum
You cannot vote in polls in this forum
|
|
|
|
