Technology

7 opportunities to reduce wlc costs - por Danilo

Categories
Published
of 73
All materials on our website are shared by users. If you have any questions about copyright issues, please report us to resolve them. We are always happy to assist you.
Related Documents
Share
Description
1. 7 opportunities to reduce WLC costs May 2015 Proibida cópia ou divulgação sem permissão escrita do CMG Brasil. 1 2. Disclaimer, copyright & trademarks…
Transcript
  • 1. 7 opportunities to reduce WLC costs May 2015 Proibida cópia ou divulgação sem permissão escrita do CMG Brasil. 1
  • 2. Disclaimer, copyright & trademarks Disclaimer: THE INFORMATION CONTAINED IN THIS PRESENTATION HAS NOT BEEN SUBMITTED TO ANY FORMAL REVIEW AND IS DISTRIBUTED ON AN “AS IS” BASIS WITHOUT ANY WARRANTY EITHER EXPRESS OR IMPLIED. THE USE OF THIS INFORMATION OR THE IMPLEMENTATION OF ANY OF THESE TECHNIQUES IS A USER RESPONSIBILITY AND DEPENDS ON THE USER’S ABILITY TO EVALUATE AND INTEGRATE THEM INTO THE USER’S OPERATIONAL ENVIRONMENT. WHILE EACH ITEM MAY HAVE BEEN REVIEWED FOR ACCURACY IN A SPECIFIC SITUATION, THERE IS NO GUARANTEE THAT THE SAME OR SIMILAR RESULTS WILL BE OBTAINED ELSEWHERE. USERS ATTEMPTING TO ADAPT THESE TECHNIQUES TO THEIR OWN ENVIRONMENTS DO SO AT THEIR OWN RISK. Copyright Notice: © EPV Technologies. All rights reserved. Trademarks: All the trademarks mentioned here belong to their respective companies. 2 Proibida cópia ou divulgação sem permissão escrita do CMG Brasil.
  • 3. In all figures and reports, numbers are in European format; we use comma for decimals and point for thousands 3 Proibida cópia ou divulgação sem permissão escrita do CMG Brasil.
  • 4. Introduction • Saving money on the mainframe is still one of the most important goals of companies running z/OS applications • There are many ways to achieve this: some require a deep technical analysis whilst others can involve complex organizational issues 4 Proibida cópia ou divulgação sem permissão escrita do CMG Brasil.
  • 5. Introduction • Most of the z/OS software products are priced with the WLC policy where license fees are determined by the monthly peak of the 4-hour rolling average value of the MSU used • In WLC there is something simple and very important that you can do to keep the software products bill under control and hopefully reduce it: a daily WLC check 5 Proibida cópia ou divulgação sem permissão escrita do CMG Brasil.
  • 6. Introduction • You need effective reporting to perform a WLC check daily, to make sure that the money needed for software products is minimised • While ex-post controls can normally only reduce future costs, in WLC it may also be possible to reduce the current month bill • We will discuss these checks in the first part of this presentation 6 Proibida cópia ou divulgação sem permissão escrita do CMG Brasil.
  • 7. Introduction • In addition you should explore WLC cost reduction possibility offered by new hardware and software technologies and pricing options • In the second part of this presentation we will discuss IDAA and Mobile Workload Pricing 7 Proibida cópia ou divulgação sem permissão escrita do CMG Brasil.
  • 8. Agenda 1. Not a “beautiful” day ? 2. (un)Happy Hour 3. The system you don’t expect 4. The importance of “importance” 5. Could we save more money with zIIP ? 6. IDAA 7. MWP 8 Proibida cópia ou divulgação sem permissão escrita do CMG Brasil.
  • 9. Not a “beautiful” day ? 9 Proibida cópia ou divulgação sem permissão escrita do CMG Brasil.
  • 10. Not a “beautiful” day ? • The first thing to control is on which day the MSU monthly peak has occurred • You would expect this to happen on a working day and probably on a business- critical day (e.g. month-end or the start of the month) • A simple report such as the one in the next figure can allow a very easy and quick check 10 Proibida cópia ou divulgação sem permissão escrita do CMG Brasil.
  • 11. Not a “beautiful” day ? 11 • Machine is a 2097-717 valued 1,329 MSUs • Report refers to February 2012 • 4-hour rolling average monthly peak is 1,309 MSUs • It happened on Sunday • Note the big difference with the second peak value (354 MSUs) Proibida cópia ou divulgação sem permissão escrita do CMG Brasil.
  • 12. Not a “beautiful” day ? Bad news – At this customer site Saturday and Sunday are not business days so a such high value on Sunday has to be considered abnormal – In this case it was caused by a long, resource heavy recovery activity needed to fix a data corruption issue following the migration to new storage processors which happened on the previous day 12 Proibida cópia ou divulgação sem permissão escrita do CMG Brasil.
  • 13. Not a “beautiful” day ? Good news ? Customers have the primary responsibility for preventing uncontrolled loops, operator errors, or unwanted utilization spikes. However, IBM understands that, occasionally, situations that could not be prevented (especially situations related to disaster recovery) might cause exceptional utilization values. In these situations, IBM does not normally expect customers to pay for the increased utilization associated with the unusual situation. Use your best judgement to determine if an unusual situation has occurred. IBM does not publish a list of unusual situations because, by their nature, they will be unpredictable. From the “Using the Sub-Capacity Reporting Tool” manual. 13 Proibida cópia ou divulgação sem permissão escrita do CMG Brasil.
  • 14. Not a “beautiful” day ? – WLC rules foresee the possibility to manage “unusual situations” by excluding some hours or days from bill calculation – This is the reason why being able to intercept and document situations like that is very important – Talk with IBM … 14 Proibida cópia ou divulgação sem permissão escrita do CMG Brasil.
  • 15. (un)Happy Hour 15 Proibida cópia ou divulgação sem permissão escrita do CMG Brasil.
  • 16. (un)Happy Hour • Very often the monthly peak occurs on a business-critical day. In this case a next step in the WLC check should be done to verify in which hours of the day the peak occurred • What triggered customer attention in the next report is the difference between the first peak day and all the other days 16 Proibida cópia ou divulgação sem permissão escrita do CMG Brasil.
  • 17. • Machine is a 2827-711 valued 1.593 MSUs • Report refers to December 2014 • 4-hour rolling average monthly peak is 1.017 MSUs • It happened on Friday • The difference with the second peak value is 97 MSUs (un)Happy Hour 17 DATE DAY TYPE MODEL MSU USED 19/12/2014 Fri 2827 711 1.593 1.017 03/12/2014 Wed 2827 711 1.593 914 04/12/2014 Thu 2827 711 1.593 866 15/12/2014 Mon 2827 711 1.593 836 30/12/2014 Tue 2827 711 1.593 827 29/12/2014 Mon 2827 711 1.593 824 16/12/2014 Tue 2827 711 1.593 824 18/12/2014 Thu 2827 711 1.593 823 23/12/2014 Tue 2827 711 1.593 809 17/12/2014 Wed 2827 711 1.593 782 24/12/2014 Wed 2827 711 1.593 774 02/12/2014 Tue 2827 711 1.593 738 22/12/2014 Mon 2827 711 1.593 728 05/12/2014 Fri 2827 711 1.593 722 31/12/2014 Wed 2827 711 1.593 702 19/12/2014 Fri 2827 711 1.593 621 01/01/2015 Thu 2827 711 1.593 584 06/12/2014 Sat 2827 711 1.593 574 20/12/2014 Sat 2827 711 1.593 572 25/12/2014 Thu 2827 711 1.593 532 13/12/2014 Sat 2827 711 1.593 261 22/12/2014 Mon 2827 711 1.593 257 28/12/2014 Sun 2827 711 1.593 218 21/12/2014 Sun 2827 711 1.593 213 Proibida cópia ou divulgação sem permissão escrita do CMG Brasil.
  • 18. (un)Happy Hour • By analysing the peak day at the hour level, our customer realized that something strange had occurred. They normally have the workload peak in the morning so they expect to have the peak of the MSU used in the 4-hour rolling average just after noon • In fact a high value (907) was reported at 14 (between 14:00:00 and 14:59:59) but in the late afternoon the MSU utilization climbed up to a much higher value (1.017) 18 Proibida cópia ou divulgação sem permissão escrita do CMG Brasil.
  • 19.  Looking at the different systems’ contributions, it appeared clear that the peak was due to something running inside the SYS2 system  Our customer asked the technical team for a deeper analysis (un)Happy Hour 19 SYSTEM 12 13 14 15 16 17 18 19 20 21 22 23 SYS1 96 103 120 130 130 125 106 87 75 69 56 21 SYS2 699 720 746 538 549 594 736 878 898 867 746 580 SYS3 4 4 3 4 5 3 4 4 4 4 3 3 SYS4 44 43 38 35 38 43 49 48 40 39 30 23 TOTAL 843 870 907 707 722 765 895 1017 1017 979 835 627 Proibida cópia ou divulgação sem permissão escrita do CMG Brasil.
  • 20.  The late afternoon peak was caused by a TSO user running into a loop  As you can see in the above report, TSO001 used about all the MSUs of 1 CP continuously for about 5 hours (un)Happy Hour 20 WKL ADDRESS SPACE SRVCLASS MEAN 12 13 14 15 16 17 18 19 20 21 22 23 TSO TSO001 TSO 71 97 138 143 142 141 142 47 JOB BATCH001 BATCHHI 31 4,8 56,3 JOB BATCH002 BATCHHI 25 27,3 49,2 8,6 14,5 JOB BATCH005 BATCHHI 24 31,3 38,8 0,5 JOB BATCH006 BATCHHI 23 29,9 38,8 0,5 JOB BATCH008 BATCHHI 22 8,3 18,8 28,2 49,4 29 19,1 22,7 1,3 DB2 DB2DIST DDFDB2 22 29,5 22,7 33,4 52,4 63 30,7 6,6 5,6 3,3 8,7 3,8 1,2 Proibida cópia ou divulgação sem permissão escrita do CMG Brasil.
  • 21. (un)Happy Hour Good news ? Customers have the primary responsibility for preventing uncontrolled loops, operator errors, or unwanted utilization spikes. However, IBM understands that, occasionally, situations that could not be prevented (especially situations related to disaster recovery) might cause exceptional utilization values. In these situations, IBM does not normally expect customers to pay for the increased utilization associated with the unusual situation. Use your best judgement to determine if an unusual situation has occurred. IBM does not publish a list of unusual situations because, by their nature, they will be unpredictable. From the “Using the Sub-Capacity Reporting Tool” manual. 21 Proibida cópia ou divulgação sem permissão escrita do CMG Brasil.
  • 22. The system you don’t expect 22 Proibida cópia ou divulgação sem permissão escrita do CMG Brasil.
  • 23. The system you don’t expect • Every site runs systems dedicated to different workloads and activities such as production, application development, application test, system test, etc. • In a normal situation you expect the WLC monthly bill to be mostly related to the amount of MSUs used by production systems • A report showing the contribution of each system to the MSU monthly peak can be very useful 23 Proibida cópia ou divulgação sem permissão escrita do CMG Brasil.
  • 24. • Machine is a 2097-714 valued 1,139 MSUs • Report refers to 1 year (Nov 2010-Oct 2011) • 4-hour rolling average monthly peak is 1,092 in October 2011 • ZNET system consumption doubled in this month The system you don’t expect 24 DATE TYPE MODEL MSU PROD TST1 TST2 ZNET TOTAL 2011-10 2097 714 1.139 988 10 8 86 1092 2011-09 2097 714 1.139 975 10 9 45 1039 2011-08 2097 714 1.139 913 9 9 40 971 2011-07 2097 714 1.139 873 7 7 39 926 2011-06 2097 714 1.139 965 10 10 44 1029 2011-05 2097 714 1.139 943 10 10 45 1008 2011-04 2097 714 1.139 967 9 9 42 1027 2011-03 2097 714 1.139 961 10 10 44 1025 2011-02 2097 714 1.139 956 10 10 45 1021 2011-01 2097 714 1.139 940 9 9 41 999 2010-12 2097 714 1.139 944 8 8 43 1003 2010-11 2097 714 1.139 923 10 10 44 987 Proibida cópia ou divulgação sem permissão escrita do CMG Brasil.
  • 25. • ZNET workload used to be very stable • something happened on October 24th • It was Monday ! • First idea was to check for maintenance activities performed in the week end The system you don’t expect 25 DATE DAY MSU SYSA TST1 TST2 ZNET TOT 16/10/2011 Sun 1.139 395 5 5 18 423 17/10/2011 Mon 1.139 886 7 7 43 942 18/10/2011 Tue 1.139 896 8 7 43 954 19/10/2011 Wed 1.139 869 9 8 43 928 20/10/2011 Thu 1.139 851 8 7 45 910 21/10/2011 Fri 1.139 796 7 7 41 850 22/10/2011 Sat 1.139 684 5 5 24 718 23/10/2011 Sun 1.139 376 5 5 16 402 24/10/2011 Mon 1.139 863 7 7 79 955 25/10/2011 Tue 1.139 891 9 7 78 985 26/10/2011 Wed 1.139 900 10 8 78 996 27/10/2011 Thu 1.139 892 8 8 79 987 28/10/2011 Fri 1.139 842 7 7 75 931 29/10/2011 Sat 1.139 698 5 5 40 748 30/10/2011 Sun 1.139 385 5 5 38 433 31/10/2011 Mon 1.139 979 7 7 84 1077 01/11/2011 Tue 1.139 988 10 8 86 1092 Proibida cópia ou divulgação sem permissão escrita do CMG Brasil.
  • 26. The system you don’t expect • A more detailed ZNET workload analysis showed a correspondent CPU increase of the session manager address space • The new version of the session manager caused such a big increase (about 40 MSUs). • In this case most of these MSUs were recovered thanks to some PTFs • Being able to measure and report this issue gave the customer the possibility of discussing the October and November monthly bills with IBM in order to reduce them 26 Proibida cópia ou divulgação sem permissão escrita do CMG Brasil.
  • 27. The importance of “importance” 27 Proibida cópia ou divulgação sem permissão escrita do CMG Brasil.
  • 28. The importance of “importance” • Once you verified that WLC monthly peaks occur on business-critical days, in business-critical hours and they are due to business-critical systems, the next check you have to perform is about the “business importance” of the workloads which used most of the MSUs and determined the monthly software bill • It is not by chance that WLM, decides which workload can use the system resources (CPU, memory, etc) based on a parameter called “importance” 28 Proibida cópia ou divulgação sem permissão escrita do CMG Brasil.
  • 29. The importance of “importance” • There are five levels of importance for user workloads; they range from 1 (highest) to 5 (lowest). In addition there are system related workloads (more important and referred as importance 0 workloads) and discretionary workloads (less important than any other workload and referred as importance 6) • WLM “importance” has to be carefully matched to the “business importance” of the workload in order to provide the appropriate support to the company business 29 Proibida cópia ou divulgação sem permissão escrita do CMG Brasil.
  • 30. The importance of “importance” 30 DATE IMP 0-6 IMP 0-5 IMP 0-4 IMP 0-3 IMP 0-2 IMP 0-1 IMP 0 2015-01 1.087 920 713 628 440 387 140 2014-12 1.167 1.017 590 513 373 323 143 2014-11 1.163 1.013 655 565 351 301 146 2014-10 1.028 847 485 426 291 223 117 2014-09 1.004 841 512 461 302 251 124 2014-08 1.006 833 498 459 314 257 133 2014-07 1.044 862 410 359 283 224 129 2014-06 1.090 924 499 414 295 239 136 2014-05 1.114 952 603 523 323 260 123 2014-04 1.117 946 554 513 299 249 150 2014-03 1.128 970 548 465 302 245 182 2014-02 1.071 900 486 392 292 232 149 2014-01 1.095 899 569 525 293 234 133 IBM 2827 Model 709 - 1.350 MSU Proibida cópia ou divulgação sem permissão escrita do CMG Brasil.
  • 31. The importance of “importance” 31 DATE IMP 0-6 IMP 0-5 IMP 0-4 IMP 0-3 IMP 0-2 IMP 0-1 IMP 0 2015-01 1.087 920 713 628 440 387 140 2014-12 1.167 1.017 590 513 373 323 143 2014-11 1.163 1.013 655 565 351 301 146 2014-10 1.028 847 485 426 291 223 117 2014-09 1.004 841 512 461 302 251 124 2014-08 1.006 833 498 459 314 257 133 2014-07 1.044 862 410 359 283 224 129 2014-06 1.090 924 499 414 295 239 136 2014-05 1.114 952 603 523 323 260 123 2014-04 1.117 946 554 513 299 249 150 2014-03 1.128 970 548 465 302 245 182 2014-02 1.071 900 486 392 292 232 149 2014-01 1.095 899 569 525 293 234 133 IBM 2827 Model 709 - 1.350 MSU • In this report each IMP 0-n column shows the MSUs used in the 4-hour rolling average by all the workloads having an importance less than or equal to n Proibida cópia ou divulgação sem permissão escrita do CMG Brasil.
  • 32. The importance of “importance” 32 DATE IMP 0-6 IMP 0-5 IMP 0-4 IMP 0-3 IMP 0-2 IMP 0-1 IMP 0 2015-01 1.087 920 713 628 440 387 140 2014-12 1.167 1.017 590 513 373 323 143 2014-11 1.163 1.013 655 565 351 301 146 2014-10 1.028 847 485 426 291 223 117 2014-09 1.004 841 512 461 302 251 124 2014-08 1.006 833 498 459 314 257 133 2014-07 1.044 862 410 359 283 224 129 2014-06 1.090 924 499 414 295 239 136 2014-05 1.114 952 603 523 323 260 123 2014-04 1.117 946 554 513 299 249 150 2014-03 1.128 970 548 465 302 245 182 2014-02 1.071 900 486 392 292 232 149 2014-01 1.095 899 569 525 293 234 133 IBM 2827 Model 709 - 1.350 MSU • IMP 0-6 accumulates the MSUs used by all the workloads while IMP 0-5 accumulates the MSUs used by all the workloads excluding importance 6 workloads (running with a discretionary goal) Proibida cópia ou divulgação sem permissão escrita do CMG Brasil.
  • 33. DATE IMP 0-6 IMP 0-5 IMP 0-4 IMP 0-3 IMP 0-2 IMP 0-1 IMP 0 2015-01 1.087 920 713 628 440 387 140 2014-12 1.167 1.017 590 513 373 323 143 2014-11 1.163 1.013 655 565 351 301 146 2014-10 1.028 847 485 426 291 223 117 2014-09 1.004 841 512 461 302 251 124 2014-08 1.006 833 498 459 314 257 133 2014-07 1.044 862 410 359 283 224 129 2014-06 1.090 924 499 414 295 239 136 2014-05 1.114 952 603 523 323 260 123 2014-04 1.117 946 554 513 299 249 150 2014-03 1.128 970 548 465 302 245 182 2014-02 1.071 900 486 392 292 232 149 2014-01 1.095 899 569 525 293 234 133 IBM 2827 Model 709 - 1.350 MSU The importance of “importance” 33 • The difference between these two columns is the contribution of discretionary workloads to the software bill • At this customer site, this difference was very high in every month Proibida cópia ou divulgação sem permissão escrita do CMG Brasil.
  • 34. The importance of “importance” 34 Proibida cópia ou divulgação sem permissão escrita do CMG Brasil.
  • 35. The importance of “importance” • In January 2015 the difference was 167 MSUs (You have to consider the highest values of IMP 0-6 and IMP 0-5 in the month even if occurring on different days) • This means that a lot of money could have been saved if these discretionary workloads (batch jobs in this case) were scheduled in non-peak hours 35 Proibida cópia ou divulgação sem permissão escrita do CMG Brasil.
  • 36. The importance of “importance” • These numbers are estimates based on SMF 72. The following steps are needed:  transform the CPU and SRB service units, provided in the SMF 72 records, into MSU used values  increment the CPU usage accounted to WLM service class periods in order to account for the uncaptured CPU  sum MSU by WLM importance  calculate the MSU 4-hour rolling average based on WLM importance 36 Proibida cópia ou divulgação sem permissão escrita do CMG Brasil.
  • 37. Could we save more money with zIIP ? 37 Proibida cópia ou divulgação sem permissão escrita do CMG Brasil.
  • 38. Could we save more money with zIIP ? • Moving as much work as possible to zIIP is a key point in the strategy of any customer who really wants to reduce hardware and software costs • Because of the complexity of the current systems it is not uncommon to find customers having consistent zIIP eligible work running on standard CPUs so increasing the monthly software bill 38 Proibida cópia ou divulgação sem permissão escrita do CMG Brasil.
  • 39. Could we save more money with zIIP ? • The most common reasons for this undesired result are : wrong PRSM and system parameters missing PTFs loops not enough zIIP available due wrong estimates in the Capacity Planning process 39 Proibida cópia ou divulgação sem permissão escrita do CMG Brasil.
  • 40. DATE CURR NO IIPCP 2014-10 1267 1156 2014-09 1218 1092 2014-08 1182 1076 2014-07 1206 1146 2014-06 1200 1140 2014-05 1194 1134 2014-04 1188 1129 2014-03 1152 1094 2014-02 1134 1077 2014-01 1128 1128 2013-12 1140 1140 2013-11 1110 1110 2013-10 1120 1120 • The CURR column shows the MSUs used in the 4-hour rolling average • NO IIPCP is an estimate of what the CURR value would be if enough zIIP was available Could we save more money with zIIP ? 40 Proibida cópia ou divulgação sem permissão escrita do CMG Brasil.
  • 41. • IIPCP was always substantially less than CURR • In October 2014 peak hour the difference is 111 MSUs Could we save more money with zIIP ? 41 DATE CURR NO IIPCP 2014-10 1267 1156 2014-09 1218 1092 2014-08 1182 1076 2014-07 1206 1146 2014-06 1200 1140 2014-05 1194 1134 2014-04 1188 1129 2014-03 1152 1094 2014-02 1134 1077 2014-01 1128 1128 2013-12 1140 1140 2013-11 1110 1110 2013-10 1120 1120 Proibid
  • Books

    Jul 23, 2017
    Search
    Related Search
    We Need Your Support
    Thank you for visiting our website and your interest in our free products and services. We are nonprofit website to share and download documents. To the running of this website, we need your help to support us.

    Thanks to everyone for your continued support.

    No, Thanks