"Jim Mulder" <[EMAIL PROTECTED]> wrote in message news:<[EMAIL PROTECTED]>... > IBM Mainframe Discussion List <[email protected]> wrote on 02/09/2006 > > 11:52:03 AM: > > > > > > > And does this mean another hoary old ROT - don't assign non-page > datasets > > > on page volumes - can be assigned to the dustbin of history ???. > > On PAV-capable disks, that ROT was already trashed. ASM forces the > > assignment of n aliases to a volume with n page datasets, so that it > > could have n-suspended ASM paging I/Os (one per page ds) and one > > exposure left for I/O to non-page datasets.
This is not correct, ASM requests 2n-1 aliasses on a volume with page datasets, where n is the number of pagedatasets. Together with the base exposure, ASM will have 2 paths to each page dataset. This already implies that one should not interfere with this presumption by ASM by placing other datasets with (heavy) load on the same volume. ASM assumes 2 private paths and if WLM does not assign more aliasses, the non-paging I/O will influence the paging I/O negatively. > > > > Even with suspended I/Os eliminated for ASM, I presume it will still > > assign the aliases so that it can usually have an idle exposures to do > > > > its paging I/O. > > That is correct. For PAV DASD, ASM builds an environment to allow it > to have up to 2 concurrently active channel programs for each data set. > When a single page read is required to satisfy a page fault and ASM > already > has an active channel program to the data set, ASM starts another channel > program to do the single page read instead of tacking the request on to > the > running channel program, so that resolution of the page fault is not > delayed by adding it to the end of a long string of writes (for steal > or swapout) or a long string of reads (for swap-in). > > Jim Mulder z/OS System Test IBM Corp. Poughkeepsie, NY This still indicates not to hinder ASM's channelprograms by occupying its "reserved" paths. When we talk about PAV devices, we talk about modern, large storage subsystems and I suppose it will not be a problem to created dedicated paging volumes. You won't need them very often, but when you need them, you will be happy to give ASM all the bandwith to its page datasets. When we converted to ESS, I dedicated 3390-09's to paging, each with 1 Plpa, 1 Common and 2 Locals. I also went back from the 1-cyl-Plpa strategy I kept for the last 25 years to a full Plpa and Common, because they now both get their 2 private ASM paths and separating Plpa and Common paging I/O makes sense again. Kees. ********************************************************************** For information, services and offers, please visit our web site: http://www.klm.com. This e-mail and any attachment may contain confidential and privileged material intended for the addressee only. If you are not the addressee, you are notified that no part of the e-mail or any attachment may be disclosed, copied or distributed, and that any other action related to this e-mail or attachment is strictly prohibited, and may be unlawful. If you have received this e-mail by error, please notify the sender immediately by return e-mail, and delete this message. Koninklijke Luchtvaart Maatschappij NV (KLM), its subsidiaries and/or its employees shall not be liable for the incorrect or incomplete transmission of this e-mail or any attachments, nor responsible for any delay in receipt. ********************************************************************** ---------------------------------------------------------------------- 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
