R: R: R: Differences between CPU values from SMF30 and DB2 stats
Just click the @ symbol in the last column close to the white paper you want and put your details in the pop-up window ... + + Fabio Massimo Ottaviani + EPV Technologies Technical Director + Skype: fabio.massimo.ottaviani + Mobile: +393406168088 + + IT Cost under Control + www.epvtech.com + Please consider the environment - do you really need to print this email? -Messaggio originale- Da: IBM Mainframe Discussion List [mailto:IBM-MAIN@LISTSERV.UA.EDU] Per conto di efinnell15 Inviato: venerdì 9 agosto 2013 09:05 A: IBM-MAIN@LISTSERV.UA.EDU Oggetto: Re: R: R: Differences between CPU values from SMF30 and DB2 stats Looking at the three page Newsletter .pdf says reply to this eMail with Analyzing DB2 in Sub but doesn't give a hint as to the email? In a message dated 8/9/2013 1:43:36 AM Central Daylight Time, fabio.ottavi...@epvtech.com writes: Newsletter 4 and 5 2010. -- 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: R: R: Differences between CPU values from SMF30 and DB2 stats
Looking at the three page Newsletter .pdf says reply to this eMail with Analyzing DB2 in Sub but doesn't give a hint as to the email? In a message dated 8/9/2013 1:43:36 AM Central Daylight Time, fabio.ottavi...@epvtech.com writes: Newsletter 4 and 5 2010. -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
R: R: Differences between CPU values from SMF30 and DB2 stats
You can request the "Analyzing DB2 overhead" white paper at: http://www.epvtech.com/resources/newsletter.html Newsletter 4 and 5 2010. Best regards Fabio + + Fabio Massimo Ottaviani + EPV Technologies Technical Director + Skype: fabio.massimo.ottaviani + Mobile: +393406168088 + + IT Cost under Control + www.epvtech.com + Please consider the environment - do you really need to print this email? -Messaggio originale- Da: IBM Mainframe Discussion List [mailto:IBM-MAIN@LISTSERV.UA.EDU] Per conto di efinnell15 Inviato: giovedì 8 agosto 2013 23:00 A: IBM-MAIN@LISTSERV.UA.EDU Oggetto: Re: R: Differences between CPU values from SMF30 and DB2 stats Guess you could post a link or tinyurl where the paper could be found? In a message dated 08/08/13 12:39:40 Central Daylight Time, fabio.ottavi...@epvtech.com writes: Unfortunately I could not attach the graph because of List rules but results using SMF 100 are just a little bit lower than using SMF 30 OR 72. -- 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: R: Differences between CPU values from SMF30 and DB2 stats
Guess you could post a link or tinyurl where the paper could be found? In a message dated 08/08/13 12:39:40 Central Daylight Time, fabio.ottavi...@epvtech.com writes: Unfortunately I could not attach the graph because of List rules but results using SMF 100 are just a little bit lower than using SMF 30 OR 72. -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
R: Differences between CPU values from SMF30 and DB2 stats
Hi all This is a snapshot of a paper I wrote a couple of years ago. May be it can help ... Unfortunately I could not attach the graph because of List rules but results using SMF 100 are just a little bit lower than using SMF 30 OR 72. Best regards Fabio DB2 overhead for MSTR, DBM1 and IRLM can be easily evaluated using SMF 30, 100 or 72 records. a) Using SMF 30 interval records (subtype 2 and 3); you have to select the records belonging to MSTR, DBM1 and IRLM address spaces and sum the CPU time provided in the SMF30ICS, SMF30ICU, SMF30HPT, SMF30IIP, SMF30RCT, SMF30CPS, SMF30CPT fields; b) Using SMF 100; you have to use the QWSAEJST and QWSASRBT fields. A section for each DB2 system address space is provided, so to get MSTR, DBM1 and IRLM overhead you have to sum the values corresponding to all of them2. Remember that these counters have been accumulated since DB2 was last started. So a de-accumulation step is required to get the numbers relative to the analyzed period of time. c) Using SMF 72 records requires a preliminary assignment of DB2 system address spaces to specific WLM service or report class. Then you have to: 1. select the records belonging to these classes; 2. normalize zAAP and zIIP service units, provided in the R723CIFA and R723CSUP fields, to standard CPUs speed multiplying respectively by the R723NFFI and R723NFFS coefficient (they normally have the same value) and dividing by 256; 3. subtract normalized zAAP and zIIP service units from the service units provided in the R723CCPU field; 4. convert TCB and SRB service units values in R723CCPU and R723CSRB to CPU seconds multiplying by the system service units per second value and dividing by the TCB and SRB coefficients (provided in the R723MCPU and R723MSRB fields); 5. sum the values obtained in the previous step to the values provided in the R723CIIT, R723CHST and R723CRCT fields. We applied all the methods described above and we calculated the DB2 System Address Spaces overhead using the following variables: • AS100OVH, based on SMF 100 records; • AS072OVH, based on SMF 72 records; • AS030OVH, based on SMF 30 interval records. The graph in Figure 1 allows us to compare the results we obtained. Only the “prime shift” hours, from 8am to 5pm, are presented. + + Fabio Massimo Ottaviani + EPV Technologies Technical Director + Skype: fabio.massimo.ottaviani + Mobile: +393406168088 + + IT Cost under Control + www.epvtech.com + Please consider the environment - do you really need to print this email? -Messaggio originale- Da: IBM Mainframe Discussion List [mailto:IBM-MAIN@LISTSERV.UA.EDU] Per conto di Barry Merrill Inviato: giovedì 8 agosto 2013 19:27 A: IBM-MAIN@LISTSERV.UA.EDU Oggetto: Re: Differences between CPU values from SMF30 and DB2 stats In general, there will be very little CPU time recorded in the DB2 Address Spaces, except for the DDR address space, because CPU time consumed in DB2 is recorded in the address space OF THE CALLER, i.e., the Batch Job or the CICS region that called DB2, so the SMF 101 (DB2ACCT) data is the only safe source of who is consuming DB2 CPU time. Barry Herbert W. "Barry" Merrill, PhD President-Programmer MXG Software Merrill Consultants 10717 Cromwell Drive Dallas, TX 75229 <mailto:ba...@mxg.com> ba...@mxg.com <http://www.mxg.com> http://www.mxg.com - FAQ has Most Answers <mailto:ad...@mxg.com> ad...@mxg.com - invoices/PO/Payment <mailto:supp...@mxg.com> supp...@mxg.com- technical tel: 214 351 1966 - expect slow reply, use email fax: 214 350 3694 - prefer email, still works -Original Message- From: IBM Mainframe Discussion List [ <mailto:IBM-MAIN@LISTSERV.UA.EDU> mailto:IBM-MAIN@LISTSERV.UA.EDU] On Behalf Of Mike Bell Sent: Thursday, August 08, 2013 12:21 PM To: <mailto:IBM-MAIN@LISTSERV.UA.EDU> IBM-MAIN@LISTSERV.UA.EDU Subject: Re: Differences between CPU values from SMF30 and DB2 stats There is a basic issue with DB2 statistics for CPU - they start with the first SQL statement. Everything that happens before that is not recorded in the DB2 cpu times. This is WAD. There used to be some presentations on what was included in DB2 cpu and why. I haven't looked for them in a long time. Maybe someone on DB2 listserv has a better memory or keeps better notes. Mike On Thu, Aug 8, 2013 at 8:39 AM, Charles Mills < <mailto:charl...@mcn.org> charl...@mcn.org> wrote: > Do you know that there is a DB2-specific mailing list where lots of > serious DB2 performance heavyweights hang out? > > I believe the enrollment process is to go to <http://www.idug.org> > ww
Re: Differences between CPU values from SMF30 and DB2 stats
In general, there will be very little CPU time recorded in the DB2 Address Spaces, except for the DDR address space, because CPU time consumed in DB2 is recorded in the address space OF THE CALLER, i.e., the Batch Job or the CICS region that called DB2, so the SMF 101 (DB2ACCT) data is the only safe source of who is consuming DB2 CPU time. Barry Herbert W. "Barry" Merrill, PhD President-Programmer MXG Software Merrill Consultants 10717 Cromwell Drive Dallas, TX 75229 ba...@mxg.com http://www.mxg.com - FAQ has Most Answers ad...@mxg.com - invoices/PO/Payment supp...@mxg.com- technical tel: 214 351 1966 - expect slow reply, use email fax: 214 350 3694 - prefer email, still works -Original Message- From: IBM Mainframe Discussion List [mailto:IBM-MAIN@LISTSERV.UA.EDU] On Behalf Of Mike Bell Sent: Thursday, August 08, 2013 12:21 PM To: IBM-MAIN@LISTSERV.UA.EDU Subject: Re: Differences between CPU values from SMF30 and DB2 stats There is a basic issue with DB2 statistics for CPU - they start with the first SQL statement. Everything that happens before that is not recorded in the DB2 cpu times. This is WAD. There used to be some presentations on what was included in DB2 cpu and why. I haven't looked for them in a long time. Maybe someone on DB2 listserv has a better memory or keeps better notes. Mike On Thu, Aug 8, 2013 at 8:39 AM, Charles Mills wrote: > Do you know that there is a DB2-specific mailing list where lots of > serious DB2 performance heavyweights hang out? > > I believe the enrollment process is to go to www.idug.org and "join" IDUG. > > Charles > > -Original Message- > From: IBM Mainframe Discussion List [mailto:IBM-MAIN@LISTSERV.UA.EDU] > On Behalf Of Nguyen Duc > Sent: Thursday, August 08, 2013 3:45 AM > To: IBM-MAIN@LISTSERV.UA.EDU > Subject: Differences between CPU values from SMF30 and DB2 stats > > Dear all, > > I am a DB2 specialist , doing some measurements i just noticed that > there is a noticeable difference between DB2 CPU times i got from > SMF30, and the times i got from the DB2 statistics records (SMF100) > about the CPU consumption of DB2 address spaces. I submitted the > question to various performance specialists at IBM (authors of > presentations at CMG ...) but none of them noticed this before. > This is the second MVS site that i notice the differences , so i don't > think that there is a bug behind that. > > -- > For IBM-MAIN subscribe / signoff / archive access instructions, send > email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN > -- Mike -- 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: Differences between CPU values from SMF30 and DB2 stats
There is a basic issue with DB2 statistics for CPU - they start with the first SQL statement. Everything that happens before that is not recorded in the DB2 cpu times. This is WAD. There used to be some presentations on what was included in DB2 cpu and why. I haven't looked for them in a long time. Maybe someone on DB2 listserv has a better memory or keeps better notes. Mike On Thu, Aug 8, 2013 at 8:39 AM, Charles Mills wrote: > Do you know that there is a DB2-specific mailing list where lots of > serious DB2 performance heavyweights hang out? > > I believe the enrollment process is to go to www.idug.org and "join" IDUG. > > Charles > > -Original Message- > From: IBM Mainframe Discussion List [mailto:IBM-MAIN@LISTSERV.UA.EDU] On > Behalf Of Nguyen Duc > Sent: Thursday, August 08, 2013 3:45 AM > To: IBM-MAIN@LISTSERV.UA.EDU > Subject: Differences between CPU values from SMF30 and DB2 stats > > Dear all, > > I am a DB2 specialist , doing some measurements i just noticed that there > is a noticeable difference between DB2 CPU times i got from SMF30, and the > times i got from the DB2 statistics records (SMF100) about the CPU > consumption of DB2 address spaces. I submitted the question to various > performance specialists at IBM (authors of presentations at CMG ...) but > none of them noticed this before. > This is the second MVS site that i notice the differences , so i don't > think that there is a bug behind that. > > -- > For IBM-MAIN subscribe / signoff / archive access instructions, > send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN > -- Mike -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
Re: Differences between CPU values from SMF30 and DB2 stats
Do you know that there is a DB2-specific mailing list where lots of serious DB2 performance heavyweights hang out? I believe the enrollment process is to go to www.idug.org and "join" IDUG. Charles -Original Message- From: IBM Mainframe Discussion List [mailto:IBM-MAIN@LISTSERV.UA.EDU] On Behalf Of Nguyen Duc Sent: Thursday, August 08, 2013 3:45 AM To: IBM-MAIN@LISTSERV.UA.EDU Subject: Differences between CPU values from SMF30 and DB2 stats Dear all, I am a DB2 specialist , doing some measurements i just noticed that there is a noticeable difference between DB2 CPU times i got from SMF30, and the times i got from the DB2 statistics records (SMF100) about the CPU consumption of DB2 address spaces. I submitted the question to various performance specialists at IBM (authors of presentations at CMG ...) but none of them noticed this before. This is the second MVS site that i notice the differences , so i don't think that there is a bug behind that. -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
Re: Differences between CPU values from SMF30 and DB2 stats
Nguyen Duc wrote: >...doing some measurements i just noticed that there is a noticeable >difference between DB2 CPU times i got from SMF30, and the times i got from >the DB2 statistics records (SMF100) about the CPU consumption of DB2 address >spaces. >With excel , the 2 graphs are parallel , so i guess that there is something >that is not accounted with the SMF100 figures. My MVS colleague just noticed >that there is only 2% difference in the total consumption of the day, and >think that it may come from the way values are consolidated (SMF interval vs. >DB2 stats interval) Hmmm, I would say 'overhead', but I will rather STFU! :-D (because I'm not a DB2 expert/specialist/guru! I do however some measurements for performance purposes.) Questions so other experts may help you: What versions of DB2 and z/OS do you have? Do your DB2 work with CICS for example? What subtypes of SMF 30 records are you using? What are your intervals from SMF, RMF and DB2? Can you drill down to see if you can see any patterns of transactions and type of transactions or who is issuing those transactions? Just curious about your transaction mix... Are those CPU values from batch jobs or interactive? Could you see any patterns from RMF as additional help? Perhaps you can post your questions on DB2-L. 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
Differences between CPU values from SMF30 and DB2 stats
Dear all, I am a DB2 specialist , doing some measurements i just noticed that there is a noticeable difference between DB2 CPU times i got from SMF30, and the times i got from the DB2 statistics records (SMF100) about the CPU consumption of DB2 address spaces. I submitted the question to various performance specialists at IBM (authors of presentations at CMG ...) but none of them noticed this before. This is the second MVS site that i notice the differences , so i don't think that there is a bug behind that. These are the figures from DB2 stats (best viewed with Courrier font) DATE HOUR DBM1ETCB DBM1ESRB DBM1PSRB DBM1PSRB_ZIIP 03/06/2013 0 31.540178 140.2765 136.523835 333.401916 03/06/2013 1 14.870935 44.852774 43.859088 173.988302 03/06/2013 2 17.546114 18.196564 15.523842 207.300039 03/06/2013 3 17.325454 66.000236 61.649473 1456.999747 03/06/2013 4 16.751931 95.419908 92.829793 1206.804921 03/06/2013 5 24.213324 51.655342 46.506701 132.162745 03/06/2013 6 35.022954 22.884382 19.369356 173.514822 03/06/2013 7 42.324382 96.183217 88.467227 187.030505 03/06/2013 8 73.084055 66.288087 61.371691 290.603597 03/06/2013 9 69.850307 167.798167 161.188929 425.060097 03/06/2013 1067.665205 120.498136 113.186459 373.526041 03/06/2013 1170.706745 153.536732 147.812193 407.075726 03/06/2013 1260.539283 134.528962 129.393636 624.809478 03/06/2013 1373.153567 235.42081 221.661694 670.183583 03/06/2013 1463.761872 142.927346 136.625667 391.160465 03/06/2013 1582.927862 182.976444 176.288609 514.387042 03/06/2013 1684.381478 354.307218 343.988406 603.116344 03/06/2013 17144.88751 122.065313 112.093727 331.427855 03/06/2013 1866.494011 101.608153 94.651068 254.72 03/06/2013 1972.725397 181.765654 175.388629 704.725331 03/06/2013 2052.064067 244.641995 241.672743 648.582962 03/06/2013 2145.376909 150.177911 147.636724 830.518694 03/06/2013 2240.749379 185.008524 179.965654 583.106242 03/06/2013 2345.786124 522.132983 517.471089 978.145563 SMF30 HOURJOB CPTM___S ZIETM__SZIPTM__S 0 DB2ADBM178.7320.19 139.09 1 DB2ADBM152.730.2864.3 2 DB2ADBM142.480.4 199.27 3 DB2ADBM1118.01 0.12 526.86 4 DB2ADBM190.574 552.08 5 DB2ADBM183.270.0894.97 6 DB2ADBM172.950.54166.88 7 DB2ADBM1157.11 0.62 175.67 8 DB2ADBM1155.57 1.89 203.73 9 DB2ADBM1205.16.81365.48 10DB2ADBM1 204.05 8.15 346.49 11DB2ADBM1 213.57 10.93 351.76 12DB2ADBM1 203.95 21.67 453 13DB2ADBM1 278.48 12.72 413.49 14DB2ADBM1 191.55 3.86 327.08 15DB2ADBM1 235.35 17.87 382.24 16DB2ADBM1 355.58 28.18 516.72 17DB2ADBM1 294.43 4.75 310.23 18DB2ADBM1 178.44 2.58 174.93 19DB2ADBM1 164.93 13.89 420.33 20DB2ADBM1 152.48 34.16 276.46 21DB2ADBM1 166.14 40.72 517.69 22DB2ADBM1 173.13 35.89 383.63 23DB2ADBM1 283.16 138.37 563.8 Then when i compare 2 columns (DB2 stats Total without ziip = TCB+ SRB) DB2 stats Total SFM30 CPTM 72.1704978.73 16.707969 52.73 61.614529 42.48 41.264081 118.01 31.475179 90.57 66.229403 83.27 57.053882 72.95 125.252103 157.11 88.60907155.57 134.621029 205.1 169.553904 204.05 135.398974 213.57 127.345858 203.95 212.304083 278.48 130.535859 191.55 147.950007 235.35 171.674095 355.58 209.463009 294.43 120.344867 178.44 105.649649 164.93 50.374971 152.48 75.285076 166.14 147.288304 173.13 114.881095 283.16 With excel , the 2 graphs are para