Re: How many LPARs in a ring ?
Ted MacNEIL pisze: We have a z10 BC K03. GRS star, which means CF, which means Parallel Sysplex, is not an option. Response gets exponential with GRS ring as you add systems to the ring. No. There is an option called ACCELSYS, which relieves the pain for multi-member GRSplex. I haven't done RING with more than 4 systems, and we had to convert to STAR because of response issues. Admittedly, this was before FICON, so I don't know what the benefit from the faster channels would be, if any. FICON is not an option for cross-sysplex GRSplex. Explanation: GRS does use BCTC devices, but FICON CTC does not allow such emulation. So, FICON CTC is only applicable to GRS-over-XCF transport, which require scope of sysplex. -- Radoslaw Skorupka Lodz, Poland -- BRE Bank SA ul. Senatorska 18 00-950 Warszawa www.brebank.pl Sąd Rejonowy dla m. st. Warszawy XII Wydział Gospodarczy Krajowego Rejestru Sądowego, nr rejestru przedsiębiorców KRS 025237 NIP: 526-021-50-88 Według stanu na dzień 01.01.2009 r. kapitał zakładowy BRE Banku SA (w całości wpłacony) wynosi 118.763.528 złotych. W związku z realizacją warunkowego podwyższenia kapitału zakładowego, na podstawie uchwały XXI WZ z dnia 16 marca 2008r., oraz uchwały XVI NWZ z dnia 27 października 2008r., może ulec podwyższeniu do kwoty 123.763.528 zł. Akcje w podwyższonym kapitale zakładowym BRE Banku SA będą w całości opłacone. -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html
How many LPARs in a ring ?
I've been asked to add a 5th LPAR to an existing 4 LPAR Hello readers, I've been asked to add a 5th LPAR to an existing 4 LPARs basic Sysplex, with GRS ring. My concern is the message traffic within the ring, which might have negative impact for the entire plex. Also the higher number of logical CPs is a concern. Is there a ROT which apply here ? Is there anyone out there running a basic Sysplex in a ring configuration with more than 4 LPARs who can share his/her view ? We have a z10 BC K03. GRS star, which means CF, which means Parallel Sysplex, is not an option. TIA Walter Marguccio z/OS Systems Programmer BELENUS LOB Informatic GmbH Munich - Germany -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html
Re: How many LPARs in a ring ?
Within the one CEC, adding one more is probably no big deal. We ran across two sites (~10km) - and DB2 starts were awful. Especially more than one system coming up together after a PoR. TSO logon procs with large DD lists is also a no-no - see Toms dynamic stuff to help there. Shared catalogs on HCD defined SHARED volumes generated enormous traffic. But you're probably already suffering all that - or not, in which case you won't care. Maybe run the GRS monitor for a while - before and after. Will at least give you some ammo. I found running a CF LPAR just for GRS STAR was beneficial. Anyone with a real CF will laugh at the numbers you get, but in our case they were significantly better than the ring. Shane ... -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html
Re: How many LPARs in a ring ?
TSO logon procs with large DD lists is also a no-no - see Toms dynamic stuff to help there. Luckily we have a handful of TSO users here, and Toms dynamic stuff ia already in place. Shared catalogs on HCD defined SHARED volumes generated enormous traffic. But you're probably already suffering all that - or not, in which case you won't care. Exactly. All our catalogs are shared. I need to keep an eye on this, so far I didn't notice anything bad. Thanks for the tips. Walter Marguccio z/OS Systems Programmer BELENUS LOB Informatic GmbH Munich - Germany -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html
Re: How many LPARs in a ring ?
On Tue, 25 May 2010 03:54:53 -0700, Walter Marguccio walter_marguc...@yahoo.com wrote: TSO logon procs with large DD lists is also a no-no - see Toms dynamic stuff to help there. Luckily we have a handful of TSO users here, and Toms dynamic stuff ia already in place. Shared catalogs on HCD defined SHARED volumes generated enormous traffic. But you're probably already suffering all that - or not, in which case you won't care. Exactly. All our catalogs are shared. I need to keep an eye on this, so far I didn't notice anything bad. Thanks for the tips. Walter Marguccio z/OS Systems Programmer BELENUS LOB Informatic GmbH Munich - Germany I really have no idea how expensive CA-MIM is, but if performance is not acceptable, you may want to consider it. It always ran circles around GRS Ring (although GRS ring via XCF is probably better than GRS owning the CTCs).My client runs an 8 system MIMplex across 2 sysplexes and gets very good performance. Not as good as the 9 system GRS Star sysplex, but that is comparing apples and oranges. MIM can run in a CF also if the scope is sysplex. With 4 systems in your ring, you are probably already pushing the limits. I recall (years ago, before XCF) a client of mine adding a 3rd system to a GRS ring and the CA-1 scratch runs doubled in wall clock time due to catalog performance. Mark -- Mark Zelden - Zelden Consulting Services - z/OS, OS/390 and MVS mailto:mzel...@flash.net Mark's MVS Utilities: http://home.flash.net/~mzelden/mvsutil.html Systems Programming expert at http://expertanswercenter.techtarget.com/ -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html
Re: How many LPARs in a ring ?
Shane Ginnane ibm-m...@tpg.com.au wrote in message news:1274781293.4bfb9e6da6...@postoffice.tpg.com.au... Within the one CEC, adding one more is probably no big deal. We ran across two sites (~10km) - and DB2 starts were awful. Especially more than one system coming up together after a PoR. TSO logon procs with large DD lists is also a no-no - see Toms dynamic stuff to help there. Shared catalogs on HCD defined SHARED volumes generated enormous traffic. But you're probably already suffering all that - or not, in which case you won't care. Maybe run the GRS monitor for a while - before and after. Will at least give you some ammo. I found running a CF LPAR just for GRS STAR was beneficial. Anyone with a real CF will laugh at the numbers you get, but in our case they were significantly better than the ring. If you go to such a (CF on Shared CPs LPAR) configuration and you already have Ficon CTC connections for XCF Signalling communication paths, keep them because they perform better than XCF communication through the list structure. Kees. Shane ... -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html 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 lists...@bama.ua.edu with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html
Re: How many LPARs in a ring ?
I really have no idea how expensive CA-MIM is, but if performance is not acceptable, you may want to consider it. No, MIM is not an option. With 4 systems in your ring, you are probably already pushing the limits. That was my fear. I recall (years ago, before XCF) a client of mine adding a 3rd system to a GRS ring and the CA-1 scratch runs doubled in wall clock time due to catalog performance. We have GRS via XCF. Catalogs traffic is what I fear the most. I'll see what the GRS says, before and after. Thanks! Walter Marguccio z/OS Systems Programmer BELENUS LOB Informatic GmbH Munich - Germany -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html
Re: How many LPARs in a ring ?
On Tue, 25 May 2010 06:29:36 -0700, Walter Marguccio walter_marguc...@yahoo.com wrote: I really have no idea how expensive CA-MIM is, but if performance is not acceptable, you may want to consider it. No, MIM is not an option. I understand. It's hard to beat free. With 4 systems in your ring, you are probably already pushing the limits. That was my fear. I recall (years ago, before XCF) a client of mine adding a 3rd system to a GRS ring and the CA-1 scratch runs doubled in wall clock time due to catalog performance. We have GRS via XCF. Catalogs traffic is what I fear the most. I'll see what the GRS says, before and after. Normal catalog traffic may not be much different than you have today with 4 systems. Things that hit the catalog hard like the CA-1 scratch utility are the things that will suffer (a little more than they already do today). Depending on how your batch runs and how many data sets are allocated / deleted compared to actual step run times, you could see some differences there as well. Online response time shouldn't really be affected (but start up times could be). As usual, YMMV. Mark -- Mark Zelden - Zelden Consulting Services - z/OS, OS/390 and MVS mailto:mzel...@flash.net Mark's MVS Utilities: http://home.flash.net/~mzelden/mvsutil.html Systems Programming expert at http://expertanswercenter.techtarget.com/ -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html
Re: How many LPARs in a ring ?
We have a z10 BC K03. GRS star, which means CF, which means Parallel Sysplex, is not an option. Response gets exponential with GRS ring as you add systems to the ring. I haven't done RING with more than 4 systems, and we had to convert to STAR because of response issues. Admittedly, this was before FICON, so I don't know what the benefit from the faster channels would be, if any. - Too busy driving to stop for gas! -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html
Re: How many LPARs in a ring ?
I have to agree with Shane here. You're pain shouldn't increase too greatly going from 4 to 5, as long as you are using ACCELSYS(sp?) and other options properly, but you really should consider creating a shared CF to make to move to STAR. As long as you are using it only for GRS (and maybe JES2 CKPT, ECS, HSM recall queue), you will be better off than your current configuration. Leave your XCF communications going through your CTCs (as someone else suggested), and stay away from any heavy users of the CF. Shane Ginnane ibm-m...@tpg.com.au 5/25/2010 5:54 AM Within the one CEC, adding one more is probably no big deal. We ran across two sites (~10km) - and DB2 starts were awful. Especially more than one system coming up together after a PoR. TSO logon procs with large DD lists is also a no-no - see Toms dynamic stuff to help there. Shared catalogs on HCD defined SHARED volumes generated enormous traffic. But you're probably already suffering all that - or not, in which case you won't care. Maybe run the GRS monitor for a while - before and after. Will at least give you some ammo. I found running a CF LPAR just for GRS STAR was beneficial. Anyone with a real CF will laugh at the numbers you get, but in our case they were significantly better than the ring. Shane ... -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html CONFIDENTIALITY/EMAIL NOTICE: The material in this transmission contains confidential and privileged information intended only for the addressee. If you are not the intended recipient, please be advised that you have received this material in error and that any forwarding, copying, printing, distribution, use or disclosure of the material is strictly prohibited. If you have received this material in error, please (i) do not read it, (ii) reply to the sender that you received the message in error, and (iii) erase or destroy the material. Emails are not secure and can be intercepted, amended, lost or destroyed, or contain viruses. You are deemed to have accepted these risks if you communicate with us by email. Thank you. -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html