In 5273c6a0.6020...@us.ibm.com, on 11/01/2013
at 11:20 AM, John Eells ee...@us.ibm.com said:
I am reliably told that there are in fact *two* MP effect curves.
There is indeed a machine-level curve that reduces the capacity of
the overall machine when an engine is added (or activated) to a
Shmuel Metz (Seymour J.) wrote:
Yes, if every CP is dedicated. But isn't there a third MP effect when you
share a processor across LPAR's?
Yes, there is a 3th MP effect for such sharing. When workload is heavy, this is
unavoidable.
Think about giving icecreams to kiddies. No problem if you
Of course software, networking, data centers, storage, output (e.g.
printing), and staffing are always and everywhere free, so let's just spend
countless hours talking about the acquisition price of server hardware, and
even then neither considering how much actual work a processor performs nor
On Thu, 31 Oct 2013 15:32:20 +, Pommier, Rex wrote:
According to this IBM web site, the IFL runs at full speed.
http://www-03.ibm.com/systems/z/os/linux/solutions/ifl.html
Full functionality of a System z processor and operating on full capacity
FSVO full capacity.
You don't get the real
Shane Ginnane wrote:
On Thu, 31 Oct 2013 15:32:20 +, Pommier, Rex wrote:
According to this IBM web site, the IFL runs at full speed.
http://www-03.ibm.com/systems/z/os/linux/solutions/ifl.html
Full functionality of a System z processor and operating on full capacity
FSVO full capacity.
John Eells wrote:
There is indeed a machine-level curve that reduces the capacity of the
overall machine when an engine is added (or activated) to a CEC.
Oops; I should have written:
There is indeed a machine-level curve that reduces the capacity of
*other processors within* the overall
I think IFLs run about 10% of a full speed CP processor. So it
doesn't take too much to make them cost effective.
On Wed, Oct 30, 2013 at 10:02 PM, adarsh khanna adarshkha...@yahoo.com wrote:
Thanks Timothy.I get it.
IFL costing across models is more to do with marketing and product
On 28 October 2013 22:24, adarsh khanna adarshkha...@yahoo.com wrote:
Does the cost of adding an IFL different on different machines e.g. 2817
compared to 2098. If yes why? as it is just characterization of a core.
You can just as well say that the difference between a CP and an IFL
is just
On Thu, 2013-10-31 at 11:38 -0400, Tony Harminc wrote:
He said I think IFLs run about 10% of a full speed CP processor. So
it doesn't take too much to make them cost effective.
I think he meant 10% of the price, not the speed.
There's a maintenance charge for that IFL too.
--
David
On 10/31/2013 7:42 AM, Mike Schwab wrote:
I think IFLs run about 10% of a full speed CP processor. So it
doesn't take too much to make them cost effective.
Specialty engines always run at full speed. THAT's what makes them cost
effective...
--
Edward E Jaffe
Phoenix Software International,
On 10/31/2013 10:31 PM, Ed Jaffe wrote:
On 10/31/2013 7:42 AM, Mike Schwab wrote:
I think IFLs run about 10% of a full speed CP processor. So it
doesn't take too much to make them cost effective.
Specialty engines always run at full speed. THAT's what makes them
cost effective...
Oops.
Thanks Timothy.I get it.
IFL costing across models is more to do with marketing and product positioning.
On Tuesday, 29 October 2013 2:45 PM, Timothy Sipples sipp...@sg.ibm.com wrote:
Bob Shannon writes:
Each book has to have at least one configured PU, so
the minimum configured PUs for the
Bob Shannon writes:
Each book has to have at least one configured PU, so
the minimum configured PUs for the CEC would be four.
Is that true uniquely for the 2827-HA1? It's not true for, say, the
2827-H43 as far as I know. Single engine 2827-H43 machines are reasonably
common. Could you be
A related question:
Does the cost of adding an IFL different on different machines e.g. 2817
compared to 2098. If yes why? as it is just characterization of a core.
On Monday, 28 October 2013 8:03 AM, Timothy Sipples sipp...@sg.ibm.com wrote:
Radoslaw Skorupka writes:
You cannot pay for
Radoslaw Skorupka writes:
You cannot pay for more spares
You can, though not at core-level granularity. That's because all
uncharacterized cores are spares. Among current mainframe models the
zEnterprise zEC12 always leaves the factory with a minimum of 2 spare
cores, but you can have up to
15 matches
Mail list logo
