home *** CD-ROM | disk | FTP | other *** search
- Comments: Gated by NETNEWS@AUVM.AMERICAN.EDU
- Path: sparky!uunet!paladin.american.edu!auvm!UCLAMVS.BITNET!CSYSMAS
- Message-ID: <IBM-MAIN%92122400293355@RICEVM1.RICE.EDU>
- Newsgroups: bit.listserv.ibm-main
- Date: Wed, 23 Dec 1992 22:28:00 PST
- Sender: IBM Mainframe Discussion list <IBM-MAIN@RICEVM1.BITNET>
- From: Michael Stein <CSYSMAS@UCLAMVS.BITNET>
- Subject: Re: Logical Partitions/Physical Partitions
- Lines: 74
-
- > > - support of new hardware
- > > VM tends to have later support for new hardware, thus
- > > restricting you from installing new hardware (and selling the
- > > old while it's still worth something).
- >
- > I've never had trouble defining new whiz-bang devices to VM as
- > unsupported devices. Yes, VM can't use them, but if the object is
- > to supply them to a guest MVS, who cares? Let MVS deal with them
- > -- 3390 and 3490 support started this way, and it's been
- > succesful in our environment with non-blue gear.
-
- Try IPLing your virtual machine from the "whiz-bang" device.
-
- Try having VM translate the CLAW never ending channel programs
- without the right support in VM.
-
- Over the years, it always seems that VM needs updating for new
- devices and it's always after MVS -- unsupported definitions
- don't in general allow full function - even for a guest machine.
-
- > > - complexity
- > > VM is much more complex than LPAR. Besides taking system
- > > programmer time to support/maintain it, there are more things
- > > which can go wrong (I/O support, CMS which is at least needed
- > > to maintain VM).
- >
- > I'm not sure I buy this at all. By the time you keep track of the
- > microcode in the redundant controllers you need for good LPAR
- > support and tune the LPAR configuration to get the right CPU caps
- > and allocations, you've spent about as much time as you would
- > have installing VM once and been done with it. If you are using
- > VM for nothing but running guest MVS machines, you don't have to
- > do diddly to VM -- you set up really big V=R/V=F areas and VM
- > pretty much stays out of the way and lets MVS do it's thing.
-
- VM doesn't *really truely* support multiple CPUs.
-
- - VM runs asymmetric multiprocessing, using a master CPU. So
- much of VM processing has to run on the master.
-
- - VM doesn't have lock recovery code (as does MVS). If you
- get a failure in the right place you just spin...
-
- - VM doesn't simulate guest multi-processing correctly.
- Everytime the guest enters "console function mode" it stops all
- your virtual machines CPUs. The real hardware doesn't work
- this way (to say nothing of getting stuck here...)
-
- > There's also a pretty considerable hardware expense involved in
- > LPAR operations -- duplicate controllers & devices aren't cheap.
-
- With ESCON and multipath controllers for DASD, at least the DASD
- paths for test systems (low usage), aren't all that expensive
- (use 1 of 4 paths for test, leaving 3 for production).
-
- > The cost of a used 3880/3380K on the used market is small and
- > VM runs OK in 1 3380 box, compared to duplicating a complete
- > system configuration for each LPAR to maintain separation of
- > devices.
-
- > > It's easy to say that VM and LPAR should have the same
- > > overhead, however it may not be. It's probably easy to start
- > > using some VM services which have a large impact on the
- > > performance. And if you can't use the VM services why pay for
- > > VM? (reliability, $, maintenance, support etc).
- >
- > LPARs are a lot easier to tune, I'll admit. I dearly wish for an
- > absolute CPU cap in VM. Most MVS-intensive shops with VM that I know of
- > use VM to replace real CTCA or 3088 hardware and not much else.
- > The maintenance on one real CTCA makes up a significant portion of
- > the cost of VM, especially for academic sites eligible for the
- > HESC discounts.
-
- ESCON removes that need...
-