Virtualisation is not a novelty. It's actually one of the last pieces of the design of 1960s computers to trickle down to the PC – and only by understanding where it came from and how it was and is used can you begin to see the shape of its future in its PC incarnation. As described in our first article in this series, current …

COMMENTS

House rules Send corrections

This topic is closed for new posts.

Page:

Friday 15th July 2011 22:37 GMT Wile E. Veteran

MTS Rocked!

I had the good fortune (and I really mean that) to be a user of MTS at Wayne State U. in the little town of Detroit, a few miles from the center of the Earth located in Ann Arbor). I was also the first president of Wayne's MTS Users' Group which provided feedback to Michigan for bugs (very few) and system improvements (very many).

Under MTS, the 360/67 supported hundreds of simultaneous users, giving each the illusion of having the complete mainframe to themselves. That's what mainframes are good at. Individual workstations, even PC's can beat them soundly on a MIPS vs MIPS basis, but what they CAN'T do is deliver those MIPS to hundreds (or thousands on newer iron) simultaneously.

0 0
1. Wednesday 20th July 2011 15:20 GMT lynn
  
  MTS & LLMPS
  
  Lincoln Labs did LLMPS ... a stand-alone monitor that ran some number of applications (in pure 360 mode). Lincoln Labs got a duplex 360/67 (originally for running tss/360) ... but was then the 1st place (outside of science center) to install cp67 (univ. I was at, was 2nd place outside of science center to install cp67).
  
  Folklore is that MTS started out being built off LLMPS at its core.
  
  0 0
Friday 15th July 2011 22:37 GMT Stephen Channell

Punch me when you're done!

Ah VM’s virtual punch was ground breaking for providing inter-process messaging that they build a very good email system (profs) on top of it.. it was cool punching a daemon with work and getting punched when it finished.

Has VMWare, Xen & Hyper-V emulated CP/CMS.. not quite yet, even 20 years ago when I last used it VM could:

• Emulate older devices that we’re manufactured any more (handy for DOS/VME)

• Emulate new kit on older boxes (VM/SP could emulate XA on older machines)

• Emulate a vector facility on a box without one

• Lash several mainframes together as one (when using the punch for IPC)

• Operate a reverse proxy with VTAM.

But sadly it was also the host for the first global email virus & denial of service.. when somebody wrote a REXX script that displayed a Christmas tree and punched itself to everyone in you profs address book.. took down the whole VNET.

0 0
1. Monday 18th July 2011 08:12 GMT ps2os2
  
  Christmas tree
  
  I do not believe it was a REXX exec that brought down the system(s) rather it was an VM exec that was the villian.
  
  REXX didn't come out got maybe 10 or so years after the culprit had been identified. I suppose the valid question was the exec a worm or virus or malware. If push came to shove I would call it malware.
  
  0 0
  1. Monday 18th July 2011 19:19 GMT lynn
    
    xmas tree
    
    vmshare reference 10dec87 to xmas exec on bitnet
    
    http://vm.marist.edu/~vmshare/browse?fn=CHRISTMA&ft=PROB
    
    risk digest reference (21dec87)
    
    http://catless.ncl.ac.uk/Risks/5.81.html#subj1
    
    misc. past posts mentioning bitnet (used technology similar to internal network)
    
    http://www.garlic.com/~lynn/subnetwork.html#bitnet
    
    this is old post where I try and reproduce the effects of a 1981 rexx xmas tree that used FSX for 3279
    
    http://www.garlic.com/~lynn/2007v.html#54
    
    note that the bitnet 1987 xmas exec was almost exactly a year before the morris worm on the internet.
    
    0 0
Friday 15th July 2011 22:38 GMT bumpy

Semi-virtual

I remember working on a VM/370 system. I was testing an MVS/370 virtual machine during business hours and used an VM command in the wrong way - the production VM just froze- much rumbling was heard from the console room. I quietly quiesced my test system and all was well. Good times. Nice to be able to test your new sysres volume during the day (when done correctly!)

0 0
1. Sunday 17th July 2011 00:10 GMT lynn
  
  virtual paging under virtual paging
  
  VM370 supported the memory of the virtual machine with demand paged virtual memory managed by an approximation to global LRU. MVS/370 running in a virtual machine, managed its virtual pages (in what it thot was "real memory") with an LRU approximation.
  
  LRU or least recently used ... assumed that a page that hasn't been used for the longest time is the least likely page to be used in the future. It can be paged out and the real storage allocated for some other use.
  
  It was possible for MVS/370 with its LRU paging to get in pathological situation when running under vm370 (with its LRU paging). VM370 will select an MVS/370 virtual machine virtual page to be replaced (paged out) because it hasn't been used for a long time (aka least recently used). However, if MVS/370 is also paging (using LRU page replacement), that same page is also the one that MVS/370 will decide to use next (i.e. invalidating the assumptions behind vm370's least-recently-used page replacement)
  
  0 0
Saturday 16th July 2011 19:15 GMT lynn

vm history

lots of history in Melinda's history document, i recently provided her with a single file PDF version

http://web.me.com/melinda.varian/Site/Melinda_Varians_Home_Page_files/neuvm.pdf

and kindle version

http://web.me.com/melinda.varian/Site/Melinda_Varians_Home_Page_files/neuvm.azw

built from her multi-file postscript version

Science center first did cp/40 having added virtual memory hardware to 360/40. cp/40 morphed into CP/67 when they were able to obtain 360/67 that came standard with virtual memory hardware. Later cp/67 morphed into vm370 when virtual memory became standard on 370s. lots of past posts mentioning science center

http://www.garlic.com/~lynn/subtopic.html#545tech

TSS/360 was the "official" software for 360/67 ... but they had numerous difficulties. Running same exact simulated application script for fortran edit, compile and execute ... I got better throughput and responses for 35 simulated CP67/CMS users than the IBM SE got with 4 simulated TSS/360 users (running on same identical 360/67 hardware).

In the 70s, the massive (failed) Future System effort (was going to completely replace 370) heavily used the single-level-store from TSS/360.

0 0
Sunday 17th July 2011 18:36 GMT david 12

Multics/unix/toy operating systems

And it seems ironic now, that unix was widely seen as a toy operating system, not just because it couldn't virtualise, but also because (after the multi was stripped out of MULTICS), security was so broken.

0 0
1. Sunday 17th July 2011 21:26 GMT Peter Gathercole
  
  @david 12
  
  It is quite clear that the security model for UNIX is one of the weakest remnants of the original UNIX development.
  
  In a lot of cases it is actually much *weaker* than that provided by Windows NT and beyond.
  
  But the difference is that it is actually used properly, and has been almost everywhere UNIX has been deployed. It was fundamental to the original multi-user model, and you always had the concept of ordinary users and a super-user.
  
  Multics, VAX/VMS, and possibly several other contemporary OS's had better security models, but the UNIX model was adequate for what it had to do, and was well understood. In fact, the group model on UNIX, with non-root group administrators has so far fallen from use that it is practically absent in modern UNIXes (ever wondered why the /etc/group file has space for a password? Well this was it)
  
  When it comes to virtual address spaces (programs running in their own private address space mapped onto real memory by address translation hardware), UNIX has this from the time it was ported to the PDP/11. Virtualized memory (i.e. the ability to use more memory than the box physically has), first appeared on UNIX on the Interdata 8/32, with the 3BSD additions to UNIX/32V, and then in BSD releases on the VAX.
  
  The first AT&T release that supported demand paging was SVR3.2, although there were internal version of R&D UNIX 3.2.5 which supported this.
  
  1 0
  1. Monday 18th July 2011 08:16 GMT Peter Gathercole
    
    Oopsie
    
    The R&D version of UNIX was 5.2.5, not 3.2.5. This equated to SVR2 with some AT&T internal developments, including demand paging, enhanced networking (STREAMS [which could have Wollongong TCP/IP modules loaded], RFS), an enhanced multiplexed filesystem (not that I remember exactly what that gave us) and many more I can't remember.
    
    0 0
  2. Monday 18th July 2011 12:17 GMT Paul Crawford
    
    @Peter Gathercole
    
    "the UNIX model was adequate for what it had to do, and was well understood."
    
    I think that nails it on the head. Unix has a simple model of file (and thus essentially everything) permissions. Groups allow a more complex take on that, but most users glaze over when you get beyond the you/others can read/write/execute point of an explanation.
    
    Windows NT+ on NTFS has ACLs that potentially offer much finer grained control, but is a bugger to understand/follow the consequences, so is rarely used effectively. A lot of legacy windows programs just breaks if you try to implement a properly secure system, so it becomes rather useless to the end user :(
    
    So in reality, and most certainly for home users, Windows in basically broken and Linux is fine. Not by capability, but by complexity and working defaults.
    
    0 0
Wednesday 20th July 2011 19:01 GMT pizzafritte

zVM - Mainframe VM today

Hi..i enjoy reading your posts about VM history. If you want to learn about today's VM, z/VM, feel free to visit http://www.vm.ibm.com

You might be interested reading about the currently available z/VM V6.1 and the statements of direction for SSL and Live Guest Relocation.

http://www.vm.ibm.com/zvm610/zvm61sum.html (2009)

See also, (2010)

http://www-01.ibm.com/common/ssi/cgi-bin/ssialias?infotype=an&subtype=ca&appname=GPA&htmlfid=897/ENUS210-234

Regards, Pam C (VM-retired)

0 0
1. Thursday 21st July 2011 22:23 GMT lynn
  
  From Annals Of Release No Software Before Its time
  
  posts from two years ago ... after new feature presentation at hilltopics meeting
  
  http://www.garlic.com/~lynn/2009p.html#43
  
  http://www.garlic.com/~lynn/2009p.html#46
  
  in the later half of the 70s ... the internal, virtual-machine based HONE system (provided online world-wide sales & marketing support) implemented loosely-coupled single-system-image support ... with front-end load-balancing and recovery (but not live migration/relocation). In the early 80s this was extended when the US HONE datacenter had a 2nd and 3rd replicated datacenter at geographic distances.
  
  however, in the late 60s, there was two cp67 commercial online timesharing service bureaus startups (sort of precursor to modern day cloud computing). By the mid-70s, at least one had migrated to VM370 based and had made numerous enhancements ... including single-system-image, front-end load balancing and live guest migration (be able to transparently vary offline a processor complex offline for service/maintenance with all the virtual guests migrated to other processors in the complex).
  
  0 0
Thursday 21st July 2011 00:56 GMT pizzafritte

Gather at the July VM Workshop 2011 - technical and affordable

If you would like to gather with other z/VM and Linux on System z enthusiasts, consider attending the upcoming VM Workshop 2011. A very affordable $100 (yes one hundred) registration fee for 2 and1/2 days of presentations, roundtables, and peer interaction.

July 28-30, 2011 at Ohio State Univ. in Columbus, Ohio.

http://www.vmworkshop.org

if you are interested in other events, or you have mainframe VM events to be posted, send a vm web feedback form (click contact- vm on vm web page) so that events can be included on the events calendar.

http://www.vm.ibm.com/events/

Regards,Pam C

0 0
1. Sunday 24th July 2011 20:29 GMT Grey Dave
  
  VM Workshop - Looks like fun
  
  Still working for a living, I can't jump on the nostalgia opportunity. It's been 45 years since my first interactive computing on M44/44X, almost 43 since I first logged on to CP-67/CMS. I shipped the first three releases of VM/370, explained shadow tables to the microcode people, and ran a couple of the Future Systems task forces. Enjoy.
  
  0 0
Friday 22nd July 2011 23:05 GMT dlc.usa

Epilog

Dang. Seriously late to the party again. 65 comments and here I am.

Great article, especially if you didn't know any of this before reading it.

This is mostly about history. Today you can order a z114 for less than a hundred USD grand (but a working environment is at least one order of magnitude more). What will you get for that vis-a-vis other platforms? In short, your money's worth.

z/VM can virtualize itself, as could VM/370.

Those z cores can run 24/7 at 100% and PR/SM and CP enable that (yes, I'm ignoring spin cycles).

My point? If you are in a position to check this out for the benefit of your employer and you choose not to because some college professor told you the mainframe is dead, you are not doing your job very well at all. That's it, plain and simple.

0 0
Sunday 24th July 2011 20:29 GMT Anonymous Coward

retired

I spent two years at IBM Mohansic labs youktown, working on the 360/67 duplex system. IBM was its own worst enemy, work began on TSS coding a duplex system. Months went by before all coding was scrapped and coding for a simplex system could be in a somewhat working state.

IBM was able to deliver to customers a small number of working systems. By that time hardware was reaching the point of having a computer on your desk, and the need for a monster system like the 360/67 was dead.

The computer room we worked in was approx 100' by 75' for just one system with memory and i/o devices. The TSS project was run 24 hours per day 7 days a week, with Christmas day and new years day off. It was not unusual to see a program walk in at 2am in pajamas for her one our slot on the machine.

A little more involved then writing an apk for android. How time has changed my world. I still think a computer is not a computer unless you can stand inside it.

Ken

0 0
1. Tuesday 26th July 2011 07:36 GMT lynn
  
  TSS/360 duplex
  
  somebody recently quoted a soviet press article about a us/soviet track meet .... where the soviets came in 2nd and US came in next to last.
  
  In the early 70s there was TSS/360 duplex benchmark showing it ran 3.8 times faster than same TSS/360 on single process. Somebody wrote it up as TSS/360 having far superior multiprocessor support (much superior than any other operating system in handling multiprocessors ... i.e. any other system would at most get twice the thruput).
  
  It turns out that the both TSS/360 benchmarks actually had much inferior thruput compared to cp67. The scenario was that single processor 360/67 had 1mbyte storage and TSS/360 kernel was so bloated that only small amount was left for application execution (and single process benchmark was page thrashing). The two-processor 360/67 had 2mbytes storage .... which was enough to have more efficient application (after what was taken by the bloated tss/360 kernel) ... getting nearly four times the thruput.
  
  0 0