We've used ICF on pretty much every model of hardware since z10. We're currently on z14 and z13s. We use internal coupling links with external links to another CEC.
We do have--and always have--CF engines shared among non-prod LPARs using thin interrupt protocol. I would hesitate to suggest buying CFs just for GRS star, but if you already have them, star so far outperforms ring that there should be no hesitation in moving there. I also would not consider using regular CPs. They would work, but poorly. . . J.O.Skip Robinson Southern California Edison Company Electric Dragon Team Paddler SHARE MVS Program Co-Manager 323-715-0595 Mobile 626-543-6132 Office ⇐=== NEW robin...@sce.com -----Original Message----- From: IBM Mainframe Discussion List [mailto:IBM-MAIN@LISTSERV.UA.EDU] On Behalf Of Dana Mitchell Sent: Tuesday, January 29, 2019 9:28 AM To: IBM-MAIN@LISTSERV.UA.EDU Subject: (External):Re: Internal Coupling Channel on z13 Brian, We've actually been thinking about this too, as we evaluate moving to z14's. We currently have a 5 member GRS ring that could really benefit moving to GRS Star, but nobody want's to spend any $ for an ICF. As of BC12 generation IBM was still recommending against using GPs for CF processors: According to an IBM paper titled: Coupling Thin Interrupts and CF Performance in Shared Processor Environments While it is possible to use general purpose processors, CPs, as CF processors and share the CPs with z/OS and other similarly defined CFs, this is not a recommended configuration. Using CPs as CF processors creates interaction between z/OS and the CF in terms of cache reuse and other factors that may impact performance. Dana On Tue, 29 Jan 2019 00:23:56 -0600, Brian Westerman <brian_wester...@syzygyinc.com> wrote: >Hi, > >Has anyone had any experience with using the internal coupling channels on a >z13. "supposedly" IBM has removed the active wait problems (where the CF lpar >would try to use 100% of whatever it gets from PR/SM), but I was wondering if >it's ready for prime time yet. I have a z13s (single CPU) with 3 LPARs on it, >they are fairly low use, but I think it'a about time the started to use GRS >since they share DASD (it was small, but now more and more as time goes on). >They have been lucky so far, but I would rather not rely on luck. They don't >have the cash to add a specialty processor, and if IBM has really reduced the >overhead of ICF, then it might be a good fit for them. ---------------------------------------------------------------------- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
