Since it doesn't appear to have been mentioned, IBMs zCP3000 tool is useful
for analyzing if a benefit would derive from using a ZIIP engine.
I ran one for a customer and for a DB2 z/OS workload,the benefit was
apparent on a cost benefit basis.
I believe that CA-Datacom will utilise a zIIP if
David Crayford writes:
Do you have any real world experience with open source and
porting to z/OS?
Yes, some.
Tony Harminc opines:
Sure, if all your application does is crunch numbers or manipulate
bytes. But if it has any interaction with the operating system such as
calling its services...
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
Does SHOWMVS run under z/OS 2.1? I haven't heard from Roland S. in a
while.
Regards,
John K
--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO
I would expect PROJECTCPU to be pretty accurate as I would expect it to
work off when the task is marked zIIP-eligible.
For non-z/OS core code, there is no such thing as a task marked
zIIP-eligible (ignoring the zAAP on zIIP functionality).
So for products that dual-path if zIIP available then
On Fri, 2013-11-01 at 17:00 +1100, Wayne Bickerdike wrote:
I believe that CA-Datacom will utilise a zIIP if present.
As will IDMS. (We're seeing approximately 50% offload of so-called
system mode time in CV.)
--
David Andrews
A. Duda Sons, Inc.
david.andr...@duda.com
It does not seem to work, and there is a note in the PDS that indicates that it
is not yet working under z/OS 2.1.
On Fri, 1 Nov 2013 05:16:16 -0500, John P Kalinich jkali...@csc.com wrote:
Does SHOWMVS run under z/OS 2.1? I haven't heard from Roland S. in a
while.
Regards,
John K
Mike,
Thanks for the link, but actually it references error 8282 as tape drive needs
cleaning in the answer instead of the B282. My CE pointed me to the correct
portion of the manual. B282 is actually hidden inside error 04 44 00 b2 82 in
the manual and it says Top I/O station get failure,
Peter X. DeFabritus wrote:
It does not seem to work,
What part(s)?
... and there is a note in the PDS that indicates that it is not yet working
under z/OS 2.1.
Fully or partly? just curious of course, please.
Groete / Greetings
Elardus Engelbrecht
When I execute the SHOWMVS command under ISPF I get continuous 0C4 ABENDs.
Here is the note from over a year ago:
Since it should be over a year before the problem might be
encountered in z/OS, I am releasing the current SHOWzOS version
7.21 now, with this caveat. Don't use it on z/OS
Works for me:
BROWSEGSF Utilities - SHOWzOS R721
Command ===
*** Top of Data
SHOWMVS
You got me - maybe I'm assembling it incorrectly.
--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
I'm running SPF/Pro 5.0 on Windows 8.1 without any problems. For several years
now when I upgrade Windows or switch machines I simply copy the SPFPro
directory over to the new version/machine. Then I create a shortcut for
SPFPROW.EXE on my desktop.
You do need to open the shortcuts
I will go on record as being another zIIP-enabled vendor (like those who have
already opined) for which PROJECTCPU is worthless. When CICS starts and our
product initializes, we look to see if a zIIPs are available. If not, we don't
worry about marking the enclave SRB as zIIP elidgeble. If
Does the exit require APF authorization? If so you're going to have
trouble with TEST. You may need TESTAUTH.
If the exit is reentrant and you LOAD it with TEST(AUTH) first, Syncsort
should find it and use it if it plays by the rules. If the exit runs
APF-authorized it's good practice to
I link it serially reusable it will pick up the copy loaded via the TEST task
Thanks
Sent from my iPhone
On Nov 1, 2013, at 9:47 AM, Jim Blalock ca...@clemson.edu wrote:
Does the exit require APF authorization? If so you're going to have trouble
with TEST. You may need TESTAUTH.
If
After reading this thread, I understand the need for zIIP processors for heavy
CPU processes, but what about resigning and rewriting these applications ? For
us, who learned assembler or BAL ...we had less to use , cycle wise and
storage, but still managed to develop good code.
Scott ford
I know of at least one of our vendors whose product does not generate the srb's
that would get dispatched on the zIIP, if it's not there. However, they will,
if you ask, take some of the smf data for the sorts and run their analysis of
those records, and come back with projections based on
z/OS 1.13, I am getting the following error when I issue an OGET with the
output data set being new.
OGET '/work/shopzseries' 'LDARP1.SHOPZ.ZOS'
IKJ56893I DATA SET LDARP1.SHOPZ.ZOS NOT ALLOCATED+
IGD17351I SPACE REQUESTED IS TOO LARGE.
Sorry, some tips that I should have mentioned:
- don't search for NewFunction, search for New Function. That works.
- the backlog file (and also the instruction file) don't seem to have a name
on them from the overview page. Not sure how it got formatting into the
Techdoc. You should see
http://pic.dhe.ibm.com/infocenter/zos/v1r13/index.jsp?topic=%2Fcom.ibm.zos.r13.idak100%2Fsmsr13.htm
2. Allowing larger data set sizes: In z/OS V1R13, SMS expands the size
limit for data sets it supports. The new size limit is X'7FFF'
megabytes or higher, which is greater than 2500 million
Based on the output data set name, the allocaton will be extended format with a
dynamic volume count of 15.
I manually allocated the data set with that name and got the extended format
with dynamic volume count.
Since I don't know what DCB attributes OGET might generate, I don't think using
a
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.
Your code may be the best design possible but it still uses CPU. Redesigning
and rewriting code to be more efficient is not the point of zIIP processors.
They are simply an IBM sales tool to make the price if z hardware more price
competitive. Running code in zIIP is less efficient (code must
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
On 1 November 2013 02:47, Timothy Sipples sipp...@sg.ibm.com wrote:
Tony Harminc opines:
[with respect to the need to use EBCDIC]
Sure, if all your application does is crunch numbers or manipulate
bytes. But if it has any interaction with the operating system such as
calling its services...
Peter is correct.
SRB's are standard. Enclaves are standard. So workload that will run on zIIP
will also run on a GCP without any change. There is not a requirement to
execute the code in a TCB. It's up to the vendor.
For customers without zIIP, the SRB/enclave overhead will make the product
As long as the program accepts the data as valid and doesn't check it
for valid ASCII characters, it should work for any character set. Let
the operating system determine if it is a valid data set name, path,
etc.
On Fri, Nov 1, 2013 at 10:51 AM, Tony Harminc t...@harminc.net wrote:
On 1
On 11/1/2013 at 11:44 AM, Jon Perryman jperr...@pacbell.net wrote:
4. For IFL (Linux processors), IBM disabled some instructions that are
critical to z/OS, zVSE and zVM but never used by zLinux.
To be precise, IBM disabled a single instruction that they ensured z/OS, z/VSE
and z/TPF use.
On 10/22/2013 01:45 PM, Pommier, Rex wrote:
Hi list,
I just dug thru the Advanced Copy Redbook and the Advanced Copy Services
regular document, as well as looking thru the archives to no avail.
Here's my question. I have a large VSAM dataset that I am backing up with
DFDSS COPY
Edit version and modification level are used as you see fit. In the old days
before source comparison and source maint (e.g. SCLM Endeavour), we would use
these fields to identify changes and levels. VERSION sets version which is
manually maintained. MODLVL automatically increments but you may
Since zVM supports zLinux, it makes sense that it allows IFL. Is there a userid
option that allows the usage of IFL processors? Or do they use some other
method?
Does CMS also use that instruction to ensure it runs on a CP?
Jon Perryman.
From: Mark Post
Jon,
CMS and z/VM are fully supported on IFL's. This is required in order to
run Linux on System z under z/VM, since originally you could not define an
LPAR that had both GCP's and IFL's defined to it.
==
Wayne Driscoll
OMEGAMON DB2 L3
Have you considered whether any of the PLO functions would do the trick? More
expensive than CDS, but perhaps they would help?
HTH
Peter
-Original Message-
From: IBM Mainframe Discussion List [mailto:IBM-MAIN@LISTSERV.UA.EDU] On Behalf
Of Donald Likens
Sent: Friday, November 01, 2013
PLO with the CSDST function (compare swap and double store)
Sent from my iPhone
On 1 Nov 2013, at 20:22, Donald Likens dlik...@infosecinc.com wrote:
My code must be able to run in SRB mode and with locks held. I have a
situation where I need to serialize processing and cannot use CDS
Timothy is right - as long as your program doesn't call services that
require EBCDIC names, you don't need EBCDIC.
What's the open source equivalent of IEFBR14, the Unix true command?
Kirk Wolf
Dovetailed Technologies
http://dovetail.com
On Fri, Nov 1, 2013 at 11:18 AM, Mike Schwab
On 1 November 2013 16:22, Donald Likens dlik...@infosecinc.com wrote:
I have a situation where I need to serialize processing and cannot use CDS
because the two addresses being updated cannot
be next to each other (because I use CDS with these two addresses with other
addresses).
CDSG,
On 1 Nov 2013 08:44:42 -0700, in bit.listserv.ibm-main you wrote:
Your code may be the best design possible but it still uses CPU. Redesigning
and rewriting code to be more efficient is not the point of zIIP processors.
They are simply an IBM sales tool to make the price if z hardware more
Dave,
I actually looked up jdbc after your post. .. and was somewhat surprised. I
had assumed that jdbc was just java database connector ... Instead it is
just for relational using sql. I personally think that this was a huge
assumption by the original authors. It should have been jrdbc.
As far as Perl and EBCDIC goes the biggest objection was the lack of any
system that the Perl guys can use to validate the code with. I had put out
a question to the list a while back... Looking to run Tomcat and Jspwiki on
a z/os system ... And offer up some system time to the Perl guys for
I think zAAP are somehow for Java but I'm not sure. I don't know how they
restrict their usage. I doubt it is thru an SRB.
zIIP is supposed to run vendor software. Most are APF authorized anyways so the
exposure is not any greater. My point was if a customer discovered how to do
this, they
On 11/1/2013 at 03:37 PM, Jon Perryman jperr...@pacbell.net wrote:
Since zVM supports zLinux, it makes sense that it allows IFL. Is there a
userid option that allows the usage of IFL processors? Or do they use some
other method?
That option only applies to so-called VM Mode LPARs, where
I realized it was a REXX exec. Using a clist variable was a subtle way of
asking the poster to post a legitimate example without making it a big deal. I
personally think it's better to talk to people rather than down to them.
Gilmartins method of commenting makes those who feel they are less
44 matches
Mail list logo