Re: MIPS Calculation formula
On 12/1/2016 2:56 AM, Elardus Engelbrecht wrote: "meaningless"! Hahaha! Are there alternatives to MIPS? Service Units? Dispatch speed? Other measurement methods? For software contracts based on processor capacity, the only "meaningful" value is MSU (millions of service units per hour). -- Edward E Jaffe Phoenix Software International, Inc 831 Parkview Drive North El Segundo, CA 90245 http://www.phoenixsoftware.com/ -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
Re: MIPS Calculation formula
Itschak Mugzach wrote: >THere used to be a rexx that calculates mips and msus. Try this link at the >bottom >http://bit.listserv.tsorexx.narkive.com/KXbgme2w/res-tso-rexx-rexx-to-calculate-mips-and-msu Yes, thanks! There is a nice REXX program there. If you are refering to Mark Zelden's site which contains IPLINFO, look at http://mzelden.com/mvsutil.html It seemed to me http://home.flash.net/~mzelden/mvsutil.html is not working? Groete / Greetings Elardus Engelbrecht -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
Re: MIPS Calculation formula
THere used to be a rexx that calculates mips and msus. Try this link at the
bottom
http://bit.listserv.tsorexx.narkive.com/KXbgme2w/res-tso-rexx-rexx-to-calculate-mips-and-msu
Best,
ITschak
ITschak Mugzach
Z/OS, ISV Products and Application Security & Risk Assessments Professional
On Thu, Dec 1, 2016 at 1:49 PM, Elardus Engelbrecht <
elardus.engelbre...@sita.co.za> wrote:
> Radoslaw Skorupka wrote:
>
> >That's why I used quotation marks for "meaningless".
> >MIPS definitions is weak, there's another measure: MSU.
>
> Yup. I'm familiar with MSU.
>
> >MSU is good, because it's known for public with no fee.
> >MSU is good, because there no multiple different MSU tables, there's one
> source of information.
>
> And Sub Capacity Report is using MSU. So no disputes.
>
> >MSU is bad, because of IBM tricks ("marketing" MSU vs "technical" MSU)
> since z990 GA.
>
> Sigh, I still don't get all those pricing schemes, but then I'm not a
> manager...
>
> ;-D
>
> Groete / Greetings
> Elardus Engelbrecht
>
> --
> For IBM-MAIN subscribe / signoff / archive access instructions,
> send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
>
--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
Re: MIPS Calculation formula
Radoslaw Skorupka wrote:
>That's why I used quotation marks for "meaningless".
>MIPS definitions is weak, there's another measure: MSU.
Yup. I'm familiar with MSU.
>MSU is good, because it's known for public with no fee.
>MSU is good, because there no multiple different MSU tables, there's one
>source of information.
And Sub Capacity Report is using MSU. So no disputes.
>MSU is bad, because of IBM tricks ("marketing" MSU vs "technical" MSU) since
>z990 GA.
Sigh, I still don't get all those pricing schemes, but then I'm not a manager...
;-D
Groete / Greetings
Elardus Engelbrecht
--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
Re: MIPS Calculation formula
W dniu 2016-12-01 o 11:56, Elardus Engelbrecht pisze:
Radoslaw Skorupka wrote:
Note: every MIPS table can differ slightly due to "meaningless" value of MIPS.
"meaningless"! Hahaha!
Are there alternatives to MIPS? Service Units? Dispatch speed? Other
measurement methods?
Also, what mixture of instructions [on what hardware type!] are used to
calculate that MIPS?
For me, MIPS is 'useful', but with the usual disclaimers, cautions, pinch of
salt, etc. With that value, you can estimate in a way how that machine can
handle a specific workload mix, or for the OP, how many x records (SMF, SYSLOG,
etc) it can process in wallclock time hh:mm:ss.
Using IBM, Cheryl Watson, Gartner, etc. MIPS tables are somewhat useful for
comparing machine X with machine Y and justify your costs and overhead.
I am still curious about the OP's goal.
That's why I used quotation marks for "meaningless".
MIPS definitions is weak, there's another measure: MSU.
MSU is good, because it's known for public with no fee.
MSU is good, because there no multiple different MSU tables, there's one
source of information.
MSU is bad, because of IBM tricks ("marketing" MSU vs "technical" MSU)
since z990 GA.
--
Radoslaw Skorupka
Lodz, Poland
---
Treść tej wiadomości może zawierać informacje prawnie chronione Banku
przeznaczone wyłącznie do użytku służbowego adresata. Odbiorcą może być jedynie
jej adresat z wyłączeniem dostępu osób trzecich. Jeżeli nie jesteś adresatem
niniejszej wiadomości lub pracownikiem upoważnionym do jej przekazania
adresatowi, informujemy, że jej rozpowszechnianie, kopiowanie, rozprowadzanie
lub inne działanie o podobnym charakterze jest prawnie zabronione i może być
karalne. Jeżeli otrzymałeś tę wiadomość omyłkowo, prosimy niezwłocznie
zawiadomić nadawcę wysyłając odpowiedź oraz trwale usunąć tę wiadomość
włączając w to wszelkie jej kopie wydrukowane lub zapisane na dysku.
This e-mail may contain legally privileged information of the Bank and is
intended solely for business use of the addressee. This e-mail may only be
received by the addressee and may not be disclosed to any third parties. If you
are not the intended addressee of this e-mail or the employee authorized to
forward it to the addressee, be advised that any dissemination, copying,
distribution or any other similar activity is legally prohibited and may be
punishable. If you received this e-mail by mistake please advise the sender
immediately by using the reply facility in your e-mail software and delete
permanently this e-mail including any copies of it either printed or saved to
hard drive.
mBank S.A. z siedzibą w Warszawie, ul. Senatorska 18, 00-950 Warszawa,
www.mBank.pl, e-mail: kont...@mbank.pl
Sąd Rejonowy dla m. st. Warszawy XII Wydział Gospodarczy Krajowego Rejestru
Sądowego, nr rejestru przedsiębiorców KRS 025237, NIP: 526-021-50-88.
Według stanu na dzień 01.01.2016 r. kapitał zakładowy mBanku S.A. (w całości
wpłacony) wynosi 168.955.696 złotych.
--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
Re: MIPS Calculation formula
Radoslaw Skorupka wrote: >Note: every MIPS table can differ slightly due to "meaningless" value of MIPS. "meaningless"! Hahaha! Are there alternatives to MIPS? Service Units? Dispatch speed? Other measurement methods? Also, what mixture of instructions [on what hardware type!] are used to calculate that MIPS? For me, MIPS is 'useful', but with the usual disclaimers, cautions, pinch of salt, etc. With that value, you can estimate in a way how that machine can handle a specific workload mix, or for the OP, how many x records (SMF, SYSLOG, etc) it can process in wallclock time hh:mm:ss. Using IBM, Cheryl Watson, Gartner, etc. MIPS tables are somewhat useful for comparing machine X with machine Y and justify your costs and overhead. I am still curious about the OP's goal. Groete / Greetings Elardus Engelbrecht -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
Re: MIPS Calculation formula
IMHO the best way to obtain MIPS for given machine: 1. Find out the machine model and capacity marker. D M=CPU in z/OS or right click on CPC icon on HMC, or ...or some people working on it simply should know it. 2. Go to IBM site called LSPR and read "PCI index" which is MIPS value. Note: every MIPS table can differ slightly due to "meaningless" value of MIPS. However is it really important whether your machine has 4624 or 4622 MIPS??? Why? I know one reason: software contracts. BTDT. Whenever I informed about HW upgrade (to get invoice) they corrected my MIPS value, because I took the value from IBM and they took it from Gartner report which is quite expensive. Of course the difference was worth a pack o peanuts, but the paperwork was bothering. my €0.02 -- Radoslaw Skorupka Lodz, Poland --- Tre tej wiadomoci moe zawiera informacje prawnie chronione Banku przeznaczone wycznie do uytku subowego adresata. Odbiorc moe by jedynie jej adresat z wyczeniem dostpu osób trzecich. Jeeli nie jeste adresatem niniejszej wiadomoci lub pracownikiem upowanionym do jej przekazania adresatowi, informujemy, e jej rozpowszechnianie, kopiowanie, rozprowadzanie lub inne dziaanie o podobnym charakterze jest prawnie zabronione i moe by karalne. Jeeli otrzymae t wiadomo omykowo, prosimy niezwocznie zawiadomi nadawc wysyajc odpowied oraz trwale usun t wiadomo wczajc w to wszelkie jej kopie wydrukowane lub zapisane na dysku. This e-mail may contain legally privileged information of the Bank and is intended solely for business use of the addressee. This e-mail may only be received by the addressee and may not be disclosed to any third parties. If you are not the intended addressee of this e-mail or the employee authorized to forward it to the addressee, be advised that any dissemination, copying, distribution or any other similar activity is legally prohibited and may be punishable. If you received this e-mail by mistake please advise the sender immediately by using the reply facility in your e-mail software and delete permanently this e-mail including any copies of it either printed or saved to hard drive. mBank S.A. z siedzib w Warszawie, ul. Senatorska 18, 00-950 Warszawa, www.mBank.pl, e-mail: kont...@mbank.pl Sd Rejonowy dla m. st. Warszawy XII Wydzia Gospodarczy Krajowego Rejestru Sdowego, nr rejestru przedsibiorców KRS 025237, NIP: 526-021-50-88. Wedug stanu na dzie 01.01.2016 r. kapita zakadowy mBanku S.A. (w caoci wpacony) wynosi 168.955.696 zotych. -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
Re: MIPS Calculation formula
There are several good references. watsonwalker.com, SHARE, CMG and Performance Associates. I've always enjoyed Dr. H Pat's observations. http://researchr.org/alias/h.-pat-artis The IBM LSPR numbers are a good starting point if you have an idea of where you're going. You need to be cognizant of the Z13 design for thruput. Harv Emery points out in his SHARE presentations of the dual pathing and other improvements for the Z13. Tuning and Capacity planning are a life's endeavor. If you need help your local branch can provide assistance or will do planning recommendations. Depending on how much you need, they'll start to charge after a point based on your current licensing agreement. In a message dated 11/30/2016 11:57:12 P.M. Central Standard Time, elardus.engelbre...@sita.co.za writes: What are you trying to solve? Rather consider Service Units. You got good replies about calculation methods and cautions about what MIPS is really. -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
Re: MIPS Calculation formula
Carlos Cordero wrote: >Is there some formula to calculate a MIPS usage from the next kind of >data-source and volumes estimation: What are you trying to solve? Rather consider Service Units. You got good replies about calculation methods and cautions about what MIPS is really. Just one fact to remember: Volume has NOTHING to do with MIPS, unless some software compression and/or record manipulation is used. >Data Type: SMF >Records procesed: X million >Avg CPU per record: .0xy seconds By whom? SMF dump? Report generation? Resource usage billing? The same goes for SYSLOG and SYSOUT. Who or what is generating it? JES2? Programs in Jobs themselves or some Abend routine spewing out dumps? As Lizette said, you can use IEBGENER to copy SYSLOG on whatever CEC. Or you can use ICEGENER or other utility to do that. But then there is also overhead to take in account like startup overhead, preparing for possible abends, paging, etc. Groete / Greetings Elardus Engelbrecht -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
Re: MIPS Calculation formula
On Wed, Nov 30, 2016 at 3:54 PM, John McKown wrote: > -- > Heisenberg may have been here. > > Unicode: http://xkcd.com/1726/ > > Maranatha! <>< > John McKown > Donna the Deer Lady https://www.youtube.com/watch?v=n5edIVgiTU4 -- Mike A Schwab, Springfield IL USA Where do Forest Rangers go to get away from it all? -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
Re: MIPS Calculation formula
On Wed, Nov 30, 2016 at 3:49 PM, Jesse 1 Robinson wrote: > The insatiable hunger for MIPS comes mainly from the non-mainframe world. > IBM uses MSU ratings for mainframes of all sizes, but folks who want to > compare other hardware can only speak MIPS. So there are various charts > available from various sources to make sense of apples and oranges. You get > to pick your source and run with it. ;-( > IMO, there are only two really useful questions which can be asked: "How long until I get my answer?" and "How much will it cost me?". But those are way too difficult to answer in a generic sense. > > . > . > J.O.Skip Robinson > Southern California Edison Company > Electric Dragon Team Paddler > SHARE MVS Program Co-Manager > 323-715-0595 Mobile > 626-302-7535 Office > robin...@sce.com > > -- Heisenberg may have been here. Unicode: http://xkcd.com/1726/ Maranatha! <>< John McKown -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
Re: MIPS Calculation formula
Most MIPS charts are expensive spreadsheets that simply duplicate what is already available from the IBM LSPR. Unless the provider of such a chart is running their own benchmarks, they are largely nonsense. Adam -Original Message- From: IBM Mainframe Discussion List [mailto:IBM-MAIN@LISTSERV.UA.EDU] On Behalf Of Lizette Koehler Sent: Wednesday, November 30, 2016 12:09 PM To: IBM-MAIN@LISTSERV.UA.EDU Subject: Re: MIPS Calculation formula Along those lines, here are a couple of links I found using an internet for IBM Calculating MIPs and Service Units It would also help to understand what you are trying to do with MIPS. https://groups.google.com/forum/#!topic/bit.listserv.ibm-main/5ZIiozkVWZs http://ibmmainframes.com/about42940.html You may want to look more at Service Units or normalized reporting. I can run an IEBGENER to Print a SYSLOG file with 10,000,000 lines. My MIPS or SUs may vary across each iterating. If I change the CEC, it may change again, if I have more CPs or less, it may change again. It can be difficult to get a repeatable report of MIPs. http://www.ibmmainframeforum.com/all-other-tools/topic1988.html Postby Bill Dennis > Mon Jun 15, 2009 6:19 am The MIPS rating is based on processor type and Operating System. Performance guru Cheryl Watson offers several charts at http://www.watsonwalker.com/chart.html I'm not sure why you care about CPU MIPS rating because chargeback is usually by CPU time or Service Units used. Your job will run in less time on a faster CPU but the chargeback per second is usually more. Likewise, fewer Service Units are used on a faster CPU. So, knowing what you are trying to report would be helpful. Also, this may help. This is a specific product, but the terms and concepts may help (or not) http://www.ibm.com/support/knowledgecenter/SS8CCV_7.5.1/com.ibm.mams.doc/adm inis tering_tamit/c_capacity_units.html Lizette > -Original Message- > From: IBM Mainframe Discussion List [mailto:IBM-MAIN@LISTSERV.UA.EDU] > On Behalf Of Greg Dyck > Sent: Wednesday, November 30, 2016 12:54 PM > To: IBM-MAIN@LISTSERV.UA.EDU > Subject: Re: MIPS Calculation formula > > > Is there some formula to calculate a MIPS usage from the next kind > > of data- > source and volumes estimation: > > Keep in mind that MIPS stands for "Meaningless Indicator of Processor > Speed"... long used, usually misunderstood, and often abused. On a > current processor I can write one program that executes x million > instructions in a second, and another that executes 5x million instructions in a second. > > Regards, > Greg > -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
Re: MIPS Calculation formula
The insatiable hunger for MIPS comes mainly from the non-mainframe world. IBM uses MSU ratings for mainframes of all sizes, but folks who want to compare other hardware can only speak MIPS. So there are various charts available from various sources to make sense of apples and oranges. You get to pick your source and run with it. ;-( . . J.O.Skip Robinson Southern California Edison Company Electric Dragon Team Paddler SHARE MVS Program Co-Manager 323-715-0595 Mobile 626-302-7535 Office robin...@sce.com -Original Message- From: IBM Mainframe Discussion List [mailto:IBM-MAIN@LISTSERV.UA.EDU] On Behalf Of Lizette Koehler Sent: Wednesday, November 30, 2016 12:09 PM To: IBM-MAIN@LISTSERV.UA.EDU Subject: (External):Re: MIPS Calculation formula Along those lines, here are a couple of links I found using an internet for IBM Calculating MIPs and Service Units It would also help to understand what you are trying to do with MIPS. https://groups.google.com/forum/#!topic/bit.listserv.ibm-main/5ZIiozkVWZs http://ibmmainframes.com/about42940.html You may want to look more at Service Units or normalized reporting. I can run an IEBGENER to Print a SYSLOG file with 10,000,000 lines. My MIPS or SUs may vary across each iterating. If I change the CEC, it may change again, if I have more CPs or less, it may change again. It can be difficult to get a repeatable report of MIPs. http://www.ibmmainframeforum.com/all-other-tools/topic1988.html Postby Bill Dennis > Mon Jun 15, 2009 6:19 am The MIPS rating is based on processor type and Operating System. Performance guru Cheryl Watson offers several charts at http://www.watsonwalker.com/chart.html I'm not sure why you care about CPU MIPS rating because chargeback is usually by CPU time or Service Units used. Your job will run in less time on a faster CPU but the chargeback per second is usually more. Likewise, fewer Service Units are used on a faster CPU. So, knowing what you are trying to report would be helpful. Also, this may help. This is a specific product, but the terms and concepts may help (or not) http://www.ibm.com/support/knowledgecenter/SS8CCV_7.5.1/com.ibm.mams.doc/adminis tering_tamit/c_capacity_units.html Lizette > -Original Message- > From: IBM Mainframe Discussion List [mailto:IBM-MAIN@LISTSERV.UA.EDU] > On Behalf Of Greg Dyck > Sent: Wednesday, November 30, 2016 12:54 PM > To: IBM-MAIN@LISTSERV.UA.EDU > Subject: Re: MIPS Calculation formula > > > Is there some formula to calculate a MIPS usage from the next kind > > of data- > source and volumes estimation: > > Keep in mind that MIPS stands for "Meaningless Indicator of Processor > Speed"... long used, usually misunderstood, and often abused. On a > current processor I can write one program that executes x million > instructions in a second, and another that executes 5x million instructions > in a second. > > Regards, > Greg -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
Re: MIPS Calculation formula
Along those lines, here are a couple of links I found using an internet for IBM Calculating MIPs and Service Units It would also help to understand what you are trying to do with MIPS. https://groups.google.com/forum/#!topic/bit.listserv.ibm-main/5ZIiozkVWZs http://ibmmainframes.com/about42940.html You may want to look more at Service Units or normalized reporting. I can run an IEBGENER to Print a SYSLOG file with 10,000,000 lines. My MIPS or SUs may vary across each iterating. If I change the CEC, it may change again, if I have more CPs or less, it may change again. It can be difficult to get a repeatable report of MIPs. http://www.ibmmainframeforum.com/all-other-tools/topic1988.html Postby Bill Dennis > Mon Jun 15, 2009 6:19 am The MIPS rating is based on processor type and Operating System. Performance guru Cheryl Watson offers several charts at http://www.watsonwalker.com/chart.html I'm not sure why you care about CPU MIPS rating because chargeback is usually by CPU time or Service Units used. Your job will run in less time on a faster CPU but the chargeback per second is usually more. Likewise, fewer Service Units are used on a faster CPU. So, knowing what you are trying to report would be helpful. Also, this may help. This is a specific product, but the terms and concepts may help (or not) http://www.ibm.com/support/knowledgecenter/SS8CCV_7.5.1/com.ibm.mams.doc/adminis tering_tamit/c_capacity_units.html Lizette > -Original Message- > From: IBM Mainframe Discussion List [mailto:IBM-MAIN@LISTSERV.UA.EDU] On > Behalf Of Greg Dyck > Sent: Wednesday, November 30, 2016 12:54 PM > To: IBM-MAIN@LISTSERV.UA.EDU > Subject: Re: MIPS Calculation formula > > > Is there some formula to calculate a MIPS usage from the next kind of data- > source and volumes estimation: > > Keep in mind that MIPS stands for "Meaningless Indicator of Processor > Speed"... long used, usually misunderstood, and often abused. On a current > processor I can write one program that executes x million instructions in a > second, and another that executes 5x million instructions in a second. > > Regards, > Greg > -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
Re: MIPS Calculation formula
Is there some formula to calculate a MIPS usage from the next kind of data-source and volumes estimation: Keep in mind that MIPS stands for "Meaningless Indicator of Processor Speed"... long used, usually misunderstood, and often abused. On a current processor I can write one program that executes x million instructions in a second, and another that executes 5x million instructions in a second. Regards, Greg -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
Re: MIPS Calculation formula
What problem are you trying to solve? Or what type of report are you trying to produce? Do you have SAS/MXG or SAS/MICS or SAS? Have you tried searching www.ibm.com for this information? Or any performance manuals/books? Lizette > -Original Message- > From: IBM Mainframe Discussion List [mailto:IBM-MAIN@LISTSERV.UA.EDU] On > Behalf Of Carlos Cordero > Sent: Wednesday, November 30, 2016 12:33 PM > To: IBM-MAIN@LISTSERV.UA.EDU > Subject: MIPS Calculation formula > > Hi all, > > > Is there some formula to calculate a MIPS usage from the next kind of data- > source and volumes estimation: > > > Data Type: SMF > > Records procesed: X million > > Data Volume: Y GB > > Total CP CPU utilization: Z seconds > > Approx zIIP utilization: 1344 seconds > > Avg CPU per record: .0xy seconds > > > Data Type: SYSLOG > > Records processed X million > > Data volume: Y GB > > Total CP CPU utilization: z seconds > > Avg CPU per record: .xy seconds > > > Data Type: SYSOUT > > Records processed X million > > Data volume: Y GB > > Total CP CPU utilization: z seconds > > Avg CPU per record: .xy seconds > > > > Thanks in advance. > > > -- > For IBM-MAIN subscribe / signoff / archive access instructions, send email to > lists...@listserv.ua.edu with the message: INFO IBM-MAIN -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
MIPS Calculation formula
Hi all, Is there some formula to calculate a MIPS usage from the next kind of data-source and volumes estimation: Data Type: SMF Records procesed: X million Data Volume: Y GB Total CP CPU utilization: Z seconds Approx zIIP utilization: 1344 seconds Avg CPU per record: .0xy seconds Data Type: SYSLOG Records processed X million Data volume: Y GB Total CP CPU utilization: z seconds Avg CPU per record: .xy seconds Data Type: SYSOUT Records processed X million Data volume: Y GB Total CP CPU utilization: z seconds Avg CPU per record: .xy seconds Thanks in advance. -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
