Hi Jason, Thanks. I've been running with 10000 in my sandbox LPARs for a few years. Even though we are z/OS 1.6 in production, I am sending off a note to the capacity team about the flash and to see if they noticed a change when we migrated to the z9s late last year.
Regards, Mark -- Mark Zelden Sr. Software and Systems Architect - z/OS Team Lead Zurich North America / Farmers Insurance Group - GITO mailto:[EMAIL PROTECTED] z/OS and OS390 expert at http://searchDataCenter.com/ateExperts/ Mark's MVS Utilities: http://home.flash.net/~mzelden/mvsutil.html On Tue, 24 Oct 2006 08:16:34 +1000, Jason Gately <[EMAIL PROTECTED]> wrote: >We are z/OS 1.7 > >The story we heard was that a couple of digits had been accidentally >transposed in the SRM interval 'table' for z9s...hence the issue. But that >it had brought to light that maybe the SRM intervals haven't been adjusted >appropriately in recent times to take into account processor speeds on the >new boxes, hence our understanding that this is of benefit on both z990's & >z9's, and at various levels of z/OS...but that it should be done with care >due to possible impacts to WLM etc. > >At our site, we believe that a figure of 5000 is probably going to be >appropriate. In Production, we initially set it to 2000, went to 3500 >yesterday, and all going well, will go to 5000 next week. On our Test/Dev >systems we initially set it to 5000, and went to 10,000 yesterday. Our >performance team are still analysing the results. > > >Jason. > > >On Mon, 23 Oct 2006 08:52:43 +1000, Jason Gately <[EMAIL PROTECTED]> >wrote: > >>Yes....we set it to 2000 last week, and saw a reduction in Uncaptured. >> >>(in fact, this APAR was created in part due to some excellent work by our >>capacity & performance guy's, who saw a marked increase in Uncaptured when >>we recently went to z9's, and wouldn't accept IBM's answer that it was >>WAD). >> > >What z/OS version? > >The APAR specifically mentions z/OS 1.7: > "When running z/OS 1.7 on a System z9 D/T2094 the SRM invocation > interval is incorrect, resulting in more timer interrupts than > intended. This can lead to an increase in uncaptured time." > >(wonder why not R8 also?) but the flash says: > > "This circumvention should be applied to all versions of z/OS." > >So does it make a difference in R6 and below? Or is it really >only apparent on R7 (and above?)? > >We're still at z/OS R6 and have been running z9s for about year. I >don't look at capture ratio on a regular basis but our crack >performance team <grin> does. I think they would have noticed a >big change. Of course the flash does say YMMV. > >Mark > ---------------------------------------------------------------------- For IBM-MAIN subscribe / signoff / archive access instructions, send email to [EMAIL PROTECTED] with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html
