Re: Calculating SIIS% as MSUs or MIPS
Dump 70,72,113 from every system on the z server Run the following build: MYIN is FB 80 %LET MACKEEP= MACRO _XLA113 _XLA113F % ; %UTILBLDP(BUILDPDB=NO,USERADD=7072 113, OUTFILE=MYIN, WANTSMF=70.1 113.1, INCLAFTR=ASUM70PR ASUM113); %INCLUDE MYIN; RUN; set dagje.ASUM113 (obs=100); For a z15 the following calc when listing z15 E164 / B2 * 100% I Writes sourced with L3 intervention / I Writes siis = (extnd164 / basic02) / 100 ; SMF70CIN gives you CP or IIP CECSER for the CEC if you have more than one SMF70CPA the SU-SEC (see I like MSU) MIPSEXEC for the executed MIPS (only if you are old like me) Barry makes it all very easy for us. PS if SAS / MXG is not running on your clients system but on your own system then please check for SW license issues 1st. -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
Re: Calculating SIIS% as MSUs or MIPS
Using type 30's is not my 1st choice. Need to calculate capture ratio's, preferably by workload type. Cannot remember if DB2 type enclaves are captured here or it is all lumped into DB AS. I think that Shivang wants a total view. The document from John Burg spells it out quite clearly. eg page 4: z16 E170 / B2 * 100% I Writes sourced with L2 intervention / I Write I would take type 70's, match the intervals with the 113's and calculate the percentage. Never use MIPS, use HW or SW MSU (clearly state which one you are using). Why MSU? All contracts / pricing are based on this. MSU is also very easy to match to type 72's. Type 72's makes reporting easy peasy. Shivang, what tooling are you going to use to do this? Andreas von Imhof Capacity & Performance z/OS - zCAP -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
Re: DFSORT / ICETOOL SPLICE function
Hi Sri, It works! Thank you so much! You made the statements very simple (eazy peazy). Any fool (just like me) can use it. The saving: 2.09 million input records REXX - 9 minutes clock time, 6 minutes CPU (IBM Z15 8561-723) DFSORT - 9 seconds clock time, 0.78 seconds CPU Unbelievable! Kind regards, Andreas -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
Re: DFSORT / ICETOOL SPLICE function
Hi Sri This is great! Thank you! it's almost there. It only processes the 1st occurrence of "CURRENT PLAN OPERATION", and outputs 1 record correctly. There are many occurrences of "CURRENT PLAN OPERATION", and I need a record for each. Could you please help with the last bit? Kind regards, Andreas -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
Re: DFSORT / ICETOOL SPLICE function
Hi Max This was my miserable attempt (with various variations). Just keep getting the very 1st and very last record merged in both //SPLCE and //OUT1 datasets. * Top of Data ** +1+2+3+4+5+6+7+8 REC RD VERSI N NUMBER CURRENT PLAN OPERATION 0001 Bottom of Data //S1EXEC PGM=ICETOOL //TOOLMSG DD SYSOUT=* //DFSMSG DD SYSOUT=* //IN1 DD DISP=SHR,DSN=IMHOFAV.B.SRT3 //OUT1 DD DISP=(NEW,CATLG),DSN=IMHOFAV.B.SRT3.FORMAT, //SPACE=(CYL,(10,10),RLSE), //DCB=(RECFM=FB,LRECL=80,BLKSIZE=27920) //SPLCEDD DISP=(NEW,CATLG),DSN=IMHOFAV.B.SRT3.SPLICE, //SPACE=(CYL,(10,10),RLSE), //DCB=(RECFM=FB,LRECL=80,BLKSIZE=27920) //TOOLIN DD* * REFORMAT THE IN1 RECORDS FOR SPLICING COPY FROM(IN1) TO(SPLCE) USING(CTL1) SPLICE FROM(SPLCE) TO(OUT1) ON(72,8,ZD) KEEPNODUPS WITHANY - WITH(1,8) WITH(10,8) WITH(19,8) USING(CTL1) /* //CTL1CNTL DD * OPTION COPY INREC IFOUTLEN=80, IFTHEN=(WHEN=GROUP,BEGIN=(33,22,CH,EQ,C'CURRENT PLAN OPERATION'), RECORDS=3,PUSH=(73:ID=8)), IFTHEN=(WHEN=(6,14,CH,EQ,C'APPLICATION ID'), BUILD=(1:8,8)), IFTHEN=(WHEN=(6,14,CH,EQ,C'JOB NAME '), BUILD=(10:17,8)), IFTHEN=(WHEN=(6,17,CH,EQ,C'APPLIED RUN CYCLE'), BUILD=(19:25,8)) OUTFIL FNAMES=SPLCE,BUILD=(1,80) /* -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
DFSORT / ICETOOL SPLICE function
Hi I am trying to create 1 output record from multiple input records. Also the output record will be reformatted. I have been trying to get the ICETOOL SPLICE function to work, but alas to no avail. Please can someone help? Reason for wanting to use SORT/ICETOOL is to reduce CPU consumption (current REXX runs several times per day against input files with millions of records). Also the REXX is difficult to maintain. IF SORT can do this then it will be easy for the users to maintain. From the input record I want to scan for "CURRENT PLAN OPERATION" and select the 1st occurrence of APPLICATION ID / JOB NAME / WORKSTATION NAME. The rest of the records are discarded till the next occurrence of "CURRENT PLAN OPERATION". Input data (output from TWS (old OPC): Copy and paste into a dataset (lrecl 80) will restore the alignment) +1+2+3+4+5+6+7+8 1 CURRENT PLAN OPERATION ___ APPLICATION ID :ASC4D99A INPUT ARRIVAL DATE :220926 INPUT ARRIVAL TIME :0645 OPERATION NUMBER : 10 AUTHORITY GROUP :TEST DESCRIPTIVE TEXT :Unl tablespacestats DBTZ JOB NAME :C4D9910S JOB ID :JOB27971 WORKSTATION NAME :SONS FORM NUMBER : PLANNED START DATE :220926 PLANNED START TIME :00064501 PLANNED END DATE :220926 PLANNED END TIME :00064502 OPERATION INPUT ARRIVAL DATE : OPERATION INPUT ARRIVAL TIME : OPERATION DEADLINE DATE/TIME :2209270644 Desired output data: Built from APPLICATION ID / JOB NAME / WORKSTATION NAME ASC4D99A C4D9910S SONS If needed I can upload a larger version of the input file to Google drive (not sure I can add an attachment here). Thanks in advance and kind regards Andreas (aka the now useless z performance specialist) -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
Re: R: zEDC compression on z14 and z15 by using ADRDSSU
Despite the fact that we have thousands of volumes we don't take full volume dumps anywhere, so I cannot give our comparison. We also don't have TAPE anymore. :-) Perhaps open a ticket with IBM and let us know what IBM says? -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
Re: zEDC compression on z14 and z15 by using ADRDSSU
Have you looked at the amount of compression that you are getting when comparing the z14 to the z15? In our shop SMF data went from about 6:1 compression (z14) to 10:1. This is a massive improvement. I do not have the CPU stats, and I also really could not care. Dumps run at night when we have a massive amount of spare MSU available. You wrote that you have 4000 volumes. Most of this is surely DB2 data (or another DBMS)? Don't you use image copies and let the applications determine when and where the copy should be made? Depending on the nature of the data, legal requirements may force you to manage the backups different data differently. -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
Re: TADz and SMF
Turning it off in SMFPRMxx is like putting your head in the sand. Turn it off in the application, just take a look at the install manual. These kind of "new" applications from IBM can burn a lot of CPU in generating those SMF records. For example we have IBM's Information Broker. Someone turned on SMF logging for that on our dev LPAR's (they call it tracing). SMF data was only 30GB per day but CPU overhead was a massive 350 MSU per hour! As far as the record type 131 goes, I think that that is what your colleague assigned in the install. -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
Re: WLM Guidance/Suggestions ! ! !
What Kees has written is correct. My rule of thumb is the faster the CP the lower the velocity. With CPU upgrades I typically revise the velocity down. It would help us if you would post a snapshot of the SUM report in RMF III, then we have all the info and not just a tiny bit and we can help you more accuately. -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN