I realize I'm late to this discussion, but if you're on the fence, why not
set yourself up so you can do both? You now readily can do so with
the z10s.
I take it you're waffling between a G04 and (perhaps) an L02. From
my chart, an L02 is very slightly more capacity than a G02. So
I'm just curious. What does that do for your software bill for the month? Do
they bill you at the highest level you use, or does that use the highest
rolling 4 hour average, or what? If you adjusted it 5 times in one working
day, you never got a 4 hour period at the same capacity level.
--
@bama.ua.edu
cc
Scott Chapman sachap...@aep.com
Subject
Re: 2 versus 4 processors
I'm just curious. What does that do for your software bill for the month?
Do they bill you at the highest level you use, or does that use the
highest rolling 4 hour average, or what? If you adjusted it 5 times
Do they bill you at the highest level you use, or does that use the highest
rolling 4 hour average, or what?
For variable usage products, it's easy and SCRT can handle it.
If you adjusted it 5 times in one working day, you never got a 4 hour period
at the same capacity level.
I believe for
snip
I think black magic is more of a science than guessing the future for a
configuration.
---unsnip
Not strictly true, but all too often very close. :-)
Rick
Hi Rick
In addition to all valuable replies about this item , the following notes
maybe helpful for you to double check more ...
1- I strongly recommend you to use zPCR for both options and don't think about
MIPs or PCI first. Checking throughput from zPCR will be the first step .The
Crispin,
From what I read of your email you are trying to choose between two
sub-capacity z10 models, one with two CP and one with four, that have
roughly the same total MIPS as your current z9 which has two CP. If I have
that part correct, then the sub-capacity uniprocessor MIPS speed of the z10
-MAIN@bama.ua.edu
Subject: Re: 2 versus 4 processors
Crispin,
From what I read of your email you are trying to choose between two
sub-capacity z10 models, one with two CP and one with four, that have
roughly the same total MIPS as your current z9 which has two CP. If I
have
that part correct
Crispin,
I always thought that workload that changes day to day is really no
different than workload that changes minute by minute.
Perhaps some time spent looking at WLM will be better than going the
sub-capacity route. Why slow something down all the time, when you can slow
it down equitably
Crispin Hugo wrote:
Hi,
We are hopefully going from a z9 to z10 processor.
I would like to have 4 CP's instead of our current 2 CP's so our
configuration is more flexible. We are not worried about licensing costs
of multiple processors. The overall MIPage would be the same, whether we
have 2 or
As Steve Samson would say, this sounds like a techno-political decision.
Translation: How do I get more power for me and make it look good to
others
For an objective view, check the IN/READY queue in the RMF CPU report.
If work is queuing, you need more engines.
If little or no queuing is
In a message dated 7/16/2010 4:28:45 A.M. Central Daylight Time,
crispin.h...@macro4.com writes:
We are not worried about licensing costs
of multiple processors. The overall MIPage would be the same, whether we
have 2 or 4 CP's
Depends on what your workload is. If you've got long
On Fri, 2010-07-16 at 08:49 -0400, Staller, Allan wrote:
In the old days (circa 197x) the overhead was about 30%. I.E. going from
one processor to two gave an increase in capacity from 1 to 1.7, not 2.
Now days, the overhead is more like 90%
Do MSU ratings take this dispatching overhead into
Crispin,
From what you describe your z10 CPs will be kneecapped to 50% of your
current z9 CP speed. That means that any compute bound task that runs at
close to 100% of one CP is going to take twice as long to complete.
Ron
-Original Message-
From: IBM Mainframe Discussion List
Now days, the overhead is more like 90%, but there is still a point of
diminishing returns.
The last time I studied it, the reduction was non-linear, but the percentage,
after two, was.
This was the 990, and was based on LSPR published figures.
But, 17 and upwards figures made no sense.
At
Depends on what your workload is.
If you've got long running batch they'll run in twice the time!
NOT, if they're I/O-Bound.
Again, it depends.
You have to know your workload, as stated, and do the analysis.
We had an IMS/FP, CICS, DB2 environment, on a 9021.
When we went to a 9672, Amdahl was
I imagine that if MSUs are derived from some standard workload test, then the
answer is yes.
Representative benchmarks are an oxymoron.
IBM runs LSPR, but NOT for all models in a processor family.
Unless things have changed, both above, and the fact that they user linear
relationships to
---snip---
Hi,
We are hopefully going from a z9 to z10 processor.
I would like to have 4 CP's instead of our current 2 CP's so our
configuration is more flexible. We are not worried about licensing costs
of multiple processors. The
@bama.ua.edu
Subject: Re: 2 versus 4 processors
---snip---
Hi,
We are hopefully going from a z9 to z10 processor.
I would like to have 4 CP's instead of our current 2 CP's so our
configuration is more flexible. We are not worried about
and is intended only for
the
-Original Message-
From: IBM Mainframe Discussion List [mailto:ibm-m...@bama.ua.edu] On
Behalf Of Ron Hawkins
Sent: 16 July 2010 16:11
To: IBM-MAIN@bama.ua.edu
Subject: Re: 2 versus 4 processors
Crispin,
From what you describe your z10 CPs will be kneecapped to 50
--snip
I am sorry but I don't understand what you mean.
We are a software development company so our work has no standard at
all. It changes from day to day depending on what the developers are
doing. We have a 2096 n02
-Original Message-
From: Rick Fochtman rfocht...@ync.net
Sender: IBM Mainframe Discussion List IBM-MAIN@bama.ua.edu
Date: Fri, 16 Jul 2010 14:23:48
To: IBM-MAIN@bama.ua.edu
Reply-To: IBM Mainframe Discussion List IBM-MAIN@bama.ua.edu
Subject: Re: 2 versus 4 processors
as a solicitation, offer or
acceptance of any offer.
-Original Message-
From: IBM Mainframe Discussion List [mailto:ibm-m...@bama.ua.edu] On
Behalf Of Rick Fochtman
Sent: 16 July 2010 20:24
To: IBM-MAIN@bama.ua.edu
Subject: Re: 2 versus 4 processors
--snip
To: IBM-MAIN@bama.ua.edu
Subject: Re: 2 versus 4 processors
Under VM does have another layer, true. But not so different. Especially
on System z and current version of z/VM. Rather than type long winded
messages, I can set up a call. Or we can chat at Share in a couple of
weeks.
nor...@desertwiz.biz
The bottom line on your question can be answered possibly like this:
Do you have any single (thread/tcb) workload (batch or online) that
drives a current CP at more than 50% capacity for any significant time?
If so, then that workload will take approximately twice as long on the
newer
-Original Message-
From: IBM Mainframe Discussion List [mailto:ibm-m...@bama.ua.edu] On
Behalf Of Crispin Hugo
Sent: Friday, July 16, 2010 1:21 PM
To: IBM-MAIN@bama.ua.edu
Subject: Re: 2 versus 4 processors
Hi Ron,
I am sorry but I don't understand what you mean.
We are a software
IBM-MAIN@bama.ua.edu
Date: Fri, 16 Jul 2010 14:23:48
To: IBM-MAIN@bama.ua.edu
Reply-To: IBM Mainframe Discussion List IBM-MAIN@bama.ua.edu
Subject: Re: 2 versus 4 processors
--snip
I am sorry but I don't understand
27 matches
Mail list logo