Shmuel, If all of PLPA page-in occurs from the one cylinder PLPA dataset then I totally agree with you.
However, with PLPA overflowing into Common the majority of PLPA page-ins will come from the Common Page Dataset, not PLPA. You will have contention for the two exposures when concurrent page-in requests for PLPA happen at the same time as Common Page-in/out activity using the same two exposures. At the same time the PLPA dataset will be relatively inactive. A dedicated PLPA means there are "always" two exposures for PLPA Page-ins, and "always" two exposures for Common page-in and page-out. As for normal activity on the PLPA dataset, well have you considered that the activity on a one Cylinder PLPA dataset does not represent the page-in rate for PLPA pages. That is because most of the PLPA page-ins are coming from Common? Assuming that an overflowed PLPA Dataset's activity equals PLPA page-in activity is invalid. It does not. So tell me, if I am building a new system and allocating new PLPA, Common, and Locals, why wouldn't I simply allocate a larger PLPA without overflow this time around (with PAV). That would be two JCL changes: one to deduct CYLS from the Common and two; add them to the PLPA. Net result is improved throughput in the event of heavy Page-in activity for PLPA and Common pages, and no change if there is never any PLPA/Common activity. Change it or not is a pointless debate, as YMMV. Which configuration should be used to provide the maximum potential page-in rate is what I am discussing. Ron > -----Original Message----- > From: IBM Mainframe Discussion List [mailto:[EMAIL PROTECTED] On > Behalf Of Shmuel Metz (Seymour J.) > Sent: Tuesday, 26 July 2005 7:24 PM > To: [email protected] > Subject: Re: ILR005E PLPA PAGE DATA SET FULL > > In <[EMAIL PROTECTED]>, on 07/26/2005 > at 10:00 AM, Ron and Jenny Hawkins <[EMAIL PROTECTED]> said: > > > >you are restricting the number of paging paths, not increasing. > > He's doing neither. The limit is still 2 exposures per paging data > set. If you're concerned with active I/O rather than suspended, the > normal activity level on PLPA is so low as to make the issue more > political or theological than technical. > > >The logic in that defeats me. > > Because your assumptions are all wrong. > > >The number of paths to auxiliary is firstly the number of page > >datasets defined, and secondly the number of paths that they share. > >Your logic doesn't seem to work for this case. > > His logic works fine; it's your non sequitor that doesn't work. What > he is doing saves him effort and has no impact on performance. > > -- > Shmuel (Seymour J.) Metz, SysProg and JOAT > ISO position; see <http://patriot.net/~shmuel/resume/brief.html> > We don't care. We don't have to care, we're Congress. > (S877: The Shut up and Eat Your spam act of 2003) > ---------------------------------------------------------------------- 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
