On Fri, 2007-08-10 at 17:31 -0400, Gerhard Adam wrote: > >…our little z800 V1R4 was running along with >overhead numbers of > >11-17 percent and RMPTTOM at 15K… > > >…Tuesday our overhead number went to 24 and RMPTTOM at > 5K > >…Wednesday overhead was 24 and 15K; set >RMPTTOM to 10K > >…Thursday overhead was 27 percent with 10K > > First of all, this is exactly what would be expected when you increase > the number of SRM sampling intervals by reducing RMPTTOM. So no > surprises there.
???? - define overhead. I don't know how Barry (MXG) defines it, but I would expect to see the uncaptured ratio change as RMPTTOM is fiddled with. >From some testing I did, capped partitions add significantly to uncaptured if the workload is bouncing into the ceiling and being enforced at the cap for long periods. Shane ... ---------------------------------------------------------------------- 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
