When I worked with RMF LPAR reports over a decade ago, there was a maximum number of physical processors for each LPAR, and a weighting factor, especially for CFs, to limit them to a small part of a whole processor.
On Wed, Mar 1, 2017 at 12:50 PM, zMan <[email protected]> wrote: > My understanding is that when a system is using dynamic LPAR allocation, a > maximum defined capacity for a given LPAR can be set, something less than > the CEC capacity. Anyone know where that's defined (what control block)? > That is, given three LPARs on a 1000 MSU box, each might be allowed a > maximum of 800 MSUs. RCTLACS, RCTIMGW, and friends in IRARCT don't seem to > show the maximum: I've seen RCTLACS vary when examined five minutes apart. > > > SMF70MSU in ERBSMF70 is defined as: > Defined capacity limit (in millions of service units) that a logical > partition may consume per unit time on average > > ...so it's out there somewhere! > > I've spent some time searching for MSUs, "defined capacity", "workload > units", and even "millions", and I don't see it. I know about SYSEVENT > REQLPDAT, but am trying to make this simple for a user -- "run this Rexx > snippet and tell me the current, max, and CEC capacity". > > zMan -- "I've got a mainframe and I'm not afraid to use it" > > ---------------------------------------------------------------------- > For IBM-MAIN subscribe / signoff / archive access instructions, > send email to [email protected] with the message: INFO IBM-MAIN -- Mike A Schwab, Springfield IL USA Where do Forest Rangers go to get away from it all? ---------------------------------------------------------------------- For IBM-MAIN subscribe / signoff / archive access instructions, send email to [email protected] with the message: INFO IBM-MAIN
