On Fri, 27 Apr 2018 12:40:52 +0800, David Crayford <dcrayf...@gmail.com> wrote:
>On 27/04/2018 1:38 AM, Tom Marchant wrote: >> On Thu, 26 Apr 2018 16:14:49 +0100, Styles, Andy (ITS zPlatform Services) >> wrote: >> >>> Can't shutdown and IPL in 315 seconds.. (well, we can't). >> No, but you can move the work to another LPAR in the Sysplex before >> the IPL, minimizing the application down time. > >That can be done on Windows/Linux systems using virtualization >technologies like VMWare and HyperV live migration. Coupled with >fail-over clustering you can build >reasonably robust systems. The monitoring infrastructure is excellent. >Our distributed sysadmin was showing my HyperV and I was very impressed. >It's not as good as >a full parallel sysplex but good enough for a lot of companies WRT SLAs. On the way home from Boston Share, I dropped in to VMWorld in Frisco. One of the sessions was a live migration of an active representative workload from mainland USA to India. In front of a live audience, with monitors running. Bloody impressive. And this was Aug/Sept 2013. Even z/VM couldn't handle things like that, let alone a 'plex. Just ask google/facebook/amazon what can be done on non-proprietary commodity hardware to keep systems up and running. Shane ... ---------------------------------------------------------------------- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
