One thing to be aware of is that once you turn on zAAP on zIIP you no
longer get the zAAP information in the SMF records (i.e. zAAP elligible,
etc.). It is now all considered zIIP work and shows up in those
buckets.
Tom Kelman
Enterprise Capacity Planner
Commerce Bank of Kansas City
(816) 760
-
From: IBM Mainframe Discussion List [mailto:ibm-m...@bama.ua.edu] On Behalf Of
George Henke
Sent: Friday, February 19, 2010 6:37 PM
To: IBM-MAIN@bama.ua.edu
Subject: Re: zAAp on zIIP Question
BTW: There are 2 great program products out there, Shadow and Neon, that
will do some TCB SRB
-about-neon-enterprise-softwares-zprime-product.html
-Original Message-
From: IBM Mainframe Discussion List [mailto:ibm-m...@bama.ua.edu] On
Behalf Of George Henke
Sent: Friday, February 19, 2010 6:37 PM
To: IBM-MAIN@bama.ua.edu
Subject: Re: zAAp on zIIP Question
BTW: There are 2 great
-
From: IBM Mainframe Discussion List [mailto:ibm-m...@bama.ua.edu] On Behalf Of
George Henke
Sent: Monday, February 22, 2010 3:57 PM
To: IBM-MAIN@bama.ua.edu
Subject: Re: zAAp on zIIP Question
Thank you very much, Gregg, for the enlightenment.
My current client is seriously considering your
Greetings All,
I'm wondering if anyone here has any experience with the ZAAPZIIP feature of
z/OS 1.11 yet.
We know not all zIIP-eligible work is dispatched to a zIIP engine (about 50% of
DB2 9 DDF work if what I've read is correct). If one has only zIIP engines and
uses the ZAAPZIIP option
Actually, it will be interesting to see what IBM will let you do. Once you
have a zAAP
installed, I don't believe IBM will let you convert it to a zIIP. But,
strangely, you
can easily convert a zIIP to a zAAP. Since you already have a zAAP on a z9
and have
paid for it, you can (logically) move
setting the percentage below 100%. In our products, we
always set the percentage to 100%.
zAAP on zIIP does not use this instrumentation. No enclaves; no SRBs.
The feature simply allows all work that would have been queued to the
WUQ for zAAPs (if there were any) to be queued to the WUQ
has
extended the life of their 2 GPP's enormously with no ill effects.
IBM has started some litigation over this, so it is probably a very good
tool. :-) And time is of the essence before they start metering and
throttling Ziip/Zaap processors.
On Fri, Feb 19, 2010 at 6:25 PM, Edward Jaffe
edja
Subject: Re: Detecting z Speciality Engines (zAAP or zIIP)
Arye Shemer wrote:
I Need to have a function to detect (in a program) the type of the
installed engines (CP, zAAP, zIIP, IFL).
DIAG 204.
--
Edward E Jaffe
OUCH! Is DIAG 204 GUPI? grin.
I had a thought (and it's lonely
Hello dear forumers,
I Need to have a function to detect (in a program) the type of the
installed engines (CP, zAAP, zIIP, IFL).
Any suggestions?
Arye Shemer.
--
For IBM-MAIN subscribe / signoff / archive access instructions
You can check field PCCAATTR in the PCCA, bits PCCA_BYLPAR_zIIP and
PCCA_BYLPAR_zAAP.
On Wed, 28 Oct 2009 14:10:36 +0200, Arye Shemer aryeshe...@gmail.com wrote:
Hello dear forumers,
I Need to have a function to detect (in a program) the type of the
installed engines (CP, zAAP, zIIP, IFL).
Any
-Original Message-
From: IBM Mainframe Discussion List
[mailto:ibm-m...@bama.ua.edu] On Behalf Of Arye Shemer
Sent: Wednesday, October 28, 2009 7:11 AM
To: IBM-MAIN@bama.ua.edu
Subject: Detecting z Speciality Engines (zAAP or zIIP)
Hello dear forumers,
I Need to have
Speciality Engines (zAAP or zIIP)
You can check field PCCAATTR in the PCCA, bits PCCA_BYLPAR_zIIP and
PCCA_BYLPAR_zAAP.
On Wed, 28 Oct 2009 14:10:36 +0200, Arye Shemer aryeshe...@gmail.com
wrote:
Hello dear forumers,
I Need to have a function to detect (in a program) the type of the
installed engines (CP
Arye Shemer wrote:
I Need to have a function to detect (in a program) the type of the
installed engines (CP, zAAP, zIIP, IFL).
DIAG 204.
--
Edward E Jaffe
Phoenix Software International, Inc
5200 W Century Blvd, Suite 800
Los Angeles, CA 90045
310-338-0400 x318
edja...@phoenixsoftware.com
-Original Message-
From: IBM Mainframe Discussion List
[mailto:ibm-m...@bama.ua.edu] On Behalf Of Edward Jaffe
Sent: Wednesday, October 28, 2009 9:06 AM
To: IBM-MAIN@bama.ua.edu
Subject: Re: Detecting z Speciality Engines (zAAP or zIIP)
Arye Shemer wrote:
I Need to have
...@homedepot.com
512-977-2615 direct
512-977-2930 fax
210-859-9887 cell phone
-Original Message-
From: IBM Mainframe Discussion List [mailto:ibm-m...@bama.ua.edu] On
Behalf Of Knutson, Sam
Sent: Thursday, September 24, 2009 9:04 PM
To: IBM-MAIN@bama.ua.edu
Subject: Re: zAAP on zIIP
http
http://www-01.ibm.com/support/docview.wss?uid=isg1OA27495
http://tinyurl.com/ya3ofrg
The zAAP on zIIP enhancement OA27495 NEW FUNCTION - ZAAP ON ZIPP
ENHANCEMENT closed with PTFs available yesterday for z/OS 1.9 and z/OS
1.10. It is included as a base function in z/OS 1.11.
We installed
The zAAP on zIIP support should not be construed to imply that zAAPs are
going away.
It was intended primarily for customers with small enough amounts of zAAP
and zIIP offload that it might not make sense to purchase both a zAAP and a
zIIP.
The support is not limited, however, only to that small
On Thu, 20 Aug 2009 07:35:45 -0400, Peter Relson rel...@us.ibm.com wrote:
The zAAP on zIIP support should not be construed to imply that zAAPs are
going away.
It was intended primarily for customers with small enough amounts of zAAP
and zIIP offload that it might not make sense to purchase both
On Thu, 20 Aug 2009 07:35:45 -0400, Peter Relson rel...@us.ibm.com wrote:
It was intended primarily for customers with small enough amounts of zAAP
and zIIP offload that it might not make sense to purchase both a zAAP and a
zIIP.
What about the opposite? Any plans to allow zIIP on zAAP
-Original Message-
From: IBM Mainframe Discussion List
[mailto:ibm-m...@bama.ua.edu] On Behalf Of Peter Relson
Sent: Thursday, August 20, 2009 6:36 AM
To: IBM-MAIN@bama.ua.edu
Subject: Re: zAAP on zIIP
The zAAP on zIIP support should not be construed to imply
that zAAPs
: Re: zAAP on zIIP
-Original Message-
From: IBM Mainframe Discussion List
[mailto:ibm-m...@bama.ua.edu] On Behalf Of Peter Relson
Sent: Thursday, August 20, 2009 6:36 AM
To: IBM-MAIN@bama.ua.edu
Subject: Re: zAAP on zIIP
The zAAP on zIIP support should not be construed to imply
However, by doing this, IBM has implicitly revealed that there cannot be
much, if any, difference between an zAAP and a zIIP, hardware-wise.
IBM has never hidden this fact. It has been discussed numerous times on this
list. A PU is a PU. Period. How else could they dynamically configure PUs
-Original Message-
From: IBM Mainframe Discussion List
[mailto:ibm-m...@bama.ua.edu] On Behalf Of Horne, Jim - James S
Sent: Thursday, August 20, 2009 8:17 AM
To: IBM-MAIN@bama.ua.edu
Subject: Re: zAAP on zIIP
John,
I don't think you understand zIIPs and zAAPs
Bob Shannon pisze:
However, by doing this, IBM has implicitly revealed that there cannot be much,
if any, difference between an zAAP and a zIIP, hardware-wise.
IBM has never hidden this fact. It has been discussed numerous times on this
list. A PU is a PU. Period. How else could
IBM always hide it on every presentation addressed to non-technical people
(read: mamangement).It causes a lot of effort for techies to clarify the
things our managers.
I'm not sure the technical implementation of specialty engines is something
that IBM should discuss with management. Did
And it appears that Neon Enterprise Software is exploiting that
similarity by somehow marking work, other than the standard IBM
work, to be dispatched to a zIIP or a zAAP via their new zPrime product.
Tom Kelman
Enterprise Capacity Planner
Commerce Bank of Kansas City
(816) 760-7632
On Thu, 20 Aug 2009 08:26:45 -0500, McKown, John wrote:
Thanks. I was under the impression that the microcode load in a
zAAP and a zIIP was different from the microcode load in a CP. I
guess that I was thinking that because there definately is a
difference (minor) in the microcode load
-Original Message-
From: IBM Mainframe Discussion List
[mailto:ibm-m...@bama.ua.edu] On Behalf Of Bob Shannon
Sent: Thursday, August 20, 2009 8:25 AM
To: IBM-MAIN@bama.ua.edu
Subject: Re: zAAP on zIIP
However, by doing this, IBM has implicitly revealed that
there cannot be much
that is not supported on the specialty engine. If
that's true, then NIP is a special case.
zIIPs and zAAPs support the full range of instructions. The decision to route
to zIIP or zAAP is made by the dispatcher. The dispatcher can't examine the
work to see what instructions will be run, and the pathlength to run
I was once told that one cannot IPL off an ICF (or maybe it was an IFL)
because NIP issues an instruction that is not supported on the specialty
engine. If that's true, then NIP is a special case.
ICFs load CFCC -- is that an IPL/NIP implementation?
IFLs allow the initialisation of z/VM --
Bob Shannon wrote:
I was once told that one cannot IPL off an ICF (or maybe it was an IFL) because
NIP issues an instruction that is not supported on the specialty engine. If
that's true, then NIP is a special case.
As I understand it, ONE useless IPL-time instruction program checks on
-Original Message-
From: IBM Mainframe Discussion List
[mailto:ibm-m...@bama.ua.edu] On Behalf Of Bob Shannon
Sent: Thursday, August 20, 2009 12:56 PM
To: IBM-MAIN@bama.ua.edu
Subject: Re: zAAP on zIIP
But the millicode in an IFL is different from that in a CP
is different from
On Thu, 20 Aug 2009 13:57:43 -0500, McKown, John jmck...@healthmarkets.com
wrote:
snip
But there must be some way for the dispatcher to somehow know that CPU#n is
a zIIP or a zAAP as opposed to a general CP. Otherwise how would the
dispatcher know not to dispatch general work onto that CPU? I
McKown, John wrote:
But there must be some way for the dispatcher to somehow know that CPU#n is a zIIP or a zAAP as opposed to a
general CP. Otherwise how would the dispatcher know not to dispatch general work onto that CPU? I would guess
that there is something in the PCCA(?) that says
On Thu, Aug 20, 2009 at 1:18 PM, Edward
Jaffeedja...@phoenixsoftware.com wrote:
As I understand it, ONE useless IPL-time instruction program checks on an
IFL (and possibly other specialty engines). This conveniently prevents z/OS
from IPLing on a specialty engine.
I know one ISV that wanted
Not quite. The zAAP on zIIP feature in z/OS 1.11 applies
only if there are no zAAPs in the configuration.
zAAP on zIIP woke me up. I just got aware of this.
From the announcement letter:
z/OS V1.11 is enhanced with a new function that can enable
System z Application Assist Processor (zAAP
Mainframe Discussion List [mailto:ibm-m...@bama.ua.edu] On
Behalf Of Hunkeler Peter (KIUP 4)
Sent: Wednesday, August 19, 2009 4:19 AM
To: IBM-MAIN@bama.ua.edu
Subject: Re: zAAP on zIIP
Not quite. The zAAP on zIIP feature in z/OS 1.11 applies
only if there are no zAAPs in the configuration.
zAAP
David Andrews wrote:
I hadn't looked at the V1.11 announcement before this, and just noticed
the zAAP on zIIP support. Is there any reason to buy a zAAP now?
There is a limit on the number of zIIPs you can have in a configuration.
--
Edward E Jaffe
Phoenix Software International, Inc
5200
-Original Message-
From: IBM Mainframe Discussion List
[mailto:ibm-m...@bama.ua.edu] On Behalf Of Edward Jaffe
Sent: Tuesday, August 18, 2009 12:45 PM
To: IBM-MAIN@bama.ua.edu
Subject: zAAP on zIIP
David Andrews wrote:
I hadn't looked at the V1.11 announcement before
John,
You are allowed to have as many zIIPs and zAAPs as CPs, so 2+2+2 is a
legitimate combination.
David,
You might still want to purchase a zAAP if your JAVA workload is large
enough to consume more than your zIIP's unused cycles. Plus the JVM
won't have to compete for cycles with other
?
For each CP, you may have up to one zIIP and one zAAP. So, if you have
two CPs, you can have two zIIPs and two zAAPs.
--
Edward E Jaffe
Phoenix Software International, Inc
5200 W Century Blvd, Suite 800
Los Angeles, CA 90045
310-338-0400 x318
edja...@phoenixsoftware.com
http
specialty engine to CP advantage for JAVA workloads
Not quite. The zAAP on zIIP feature in z/OS 1.11 applies only if there
are no zAAPs in the configuration.
--
Edward E Jaffe
Phoenix Software International, Inc
5200 W Century Blvd, Suite 800
Los Angeles, CA 90045
310-338-0400 x318
edja
-Original Message-
From: IBM Mainframe Discussion List
[mailto:ibm-m...@bama.ua.edu] On Behalf Of Jim Phoenix
Sent: Tuesday, August 18, 2009 1:04 PM
To: IBM-MAIN@bama.ua.edu
Subject: Re: zAAP on zIIP
John,
You are allowed to have as many zIIPs and zAAPs as CPs, so 2+2+2
You are allowed to have as many zIIPs and zAAPs as CPs, so 2+2+2 is a
legitimate combination.
Only IFL's don't require you to match with general CPs.
-
Too busy driving to stop for gas!
--
For IBM-MAIN subscribe / signoff /
Ted MacNEIL pisze:
You are allowed to have as many zIIPs and zAAPs as CPs, so 2+2+2 is a
legitimate combination.
Only IFL's don't require you to match with general CPs.
And ICF's as well.
BTW:
There are also SAP's, but:
1. I never observed them as busy (usually it is approcx 3%)
2. You can
I know that the characterization of a CP as a general purpose or IFL
or CFL or zAAP or zIIP is simply a matter of which microcode is loaded
into it. Is is possible to non disruptively add a zAAP or zIIP to a
z9BC? I.e. does the machine need to be down or a POR done? What about
the LPAR that I want
that the characterization of a CP as a general purpose or IFL
or CFL or zAAP or zIIP is simply a matter of which microcode is loaded
into it. Is is possible to non disruptively add a zAAP or zIIP to a
z9BC? I.e. does the machine need to be down or a POR done? What about
the LPAR that I want
we have a standard that any CP field that allows
reservation we will reserve at least 2 for dynamic activation.
We had a standard, recommended by IBM, that the sum of active and reserved add
up to the maximum configurable.
It doesn't cost anything, and makes life a lot easier.
-
Too busy
On Thu, 17 May 2007 09:41:08 -0500, McKown, John
[EMAIL PROTECTED] wrote:
Related: what about a totally new crypto card? Does it require a
hardware outage or it is hot installable? If it is hot installable, can
I then just start using it, or does the LPAR defination need to be
messed with?
50 matches
Mail list logo