page data sets and HiperPAV (was: Large Page Datasets APAR OA20749)
Kees, >I am not sure who Hiperpavs react on ASM I/O, but currently ASM >*reserves* PAV exposures with WLM, so ASM will never be bothered by PAV >management issues, which could result in undesired bad ASM performance. My recollection of HiperPAV presentations is fuzzy, but as far as I remember, it is done completely in hardware, and the 'alias' is assigned for exactly one I/O operation, in hardware. So there is no 'reservation' of aliases needed anymore, they get shifted around in hardware depending on load to a volume. I have forgotten if several UCBs are needed in MVS, but I don't think so. I remember HiperPAV being presented as the best thing since sliced bread! :-) Regards, Barbara -- Psst! Geheimtipp: Online Games kostenlos spielen bei den GMX Free Games! http://games.entertainment.web.de/de/entertainment/games/free -- 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
Re: page data sets and HiperPAV (was: Large Page Datasets APAR OA20749)
"Barbara Nitz" <[EMAIL PROTECTED]> wrote in message news:<[EMAIL PROTECTED]>... > Kees, > > >I am not sure who Hiperpavs react on ASM I/O, but currently ASM > >*reserves* PAV exposures with WLM, so ASM will never be bothered by PAV > >management issues, which could result in undesired bad ASM performance. > > My recollection of HiperPAV presentations is fuzzy, but as far as I remember, it is done completely in hardware, and the 'alias' is assigned for exactly one I/O operation, in hardware. So there is no 'reservation' of aliases needed anymore, they get shifted around in hardware depending on load to a volume. I have forgotten if several UCBs are needed in MVS, but I don't think so. I remember HiperPAV being presented as the best thing since sliced bread! :-) > > Regards, Barbara Yes, as I understood too, it is fully managed by the hardware, not by WLM. So this means that ASM may have to compete for exposures. Possibly/hopefully ASM's I/O priority will give it the needed advantage. Otherwise Shane's remark about SECP may be not the joke it seemed at first glance. 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. Koninklijke Luchtvaart Maatschappij N.V. (also known as KLM Royal Dutch Airlines) is registered in Amstelveen, The Netherlands, with registered number 33014286 ** -- 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
Re: page data sets and HiperPAV (was: Large Page Datasets APAR OA20749)
On Tue, 4 Mar 2008 12:31:01 +0100, Vernooy, C.P. - SPLXM wrote: <- snip -> >Yes, as I understood too, it is fully managed by the hardware, not by >WLM. So this means that ASM may have to compete for exposures. >Possibly/hopefully ASM's I/O priority will give it the needed advantage. >Otherwise Shane's remark about SECP may be not the joke it seemed at >first glance. <- snip -> Last information I have found about status of ASM and HyperPAV was in the thread "PLPA and COMMON PAGESPACE Size", mail from 13 Sep 2007: <- snip -> > But note that ASM only supports starting 2 I/Os to a page data set > when there are dynamic PAVs (as opposed to static PAVs). Unless > something has changed since z/OS 1.3 when this support was introduced. That is a very good point, especially because I was going to say "Dynamic PAV and of course HyperPAV", but thought I had better check the code first. It turns out that the ASM code which decides whether to create two sets of I/O control blocks for a page data set was not updated for HyperPAV (an oversight on our part). It checks to see if you specified WLM PAV when you defined the device in HCD. Since WLM doesn't need to manage PAVs when the control unit has been told to use HyperPAV mode, our intention was that the specification of WLM PAV in HCD would be irrelevant for HyperPAV devices. But for now, it looks like you would want to specify WLM PAV for HyperPAV paging devices, until we can update the ASM code (probably via an APAR) to automatically recognize HyperPAV paging devices. <- snip -> Zaromil -- 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