re: http://www.garlic.com/~lynn/2009r.html#18 "Portable" data centers
the modifications for vm370 release 6 to be service processor started well before 3090 came out. it was a copy of standard vm370 release 6 (predates vm/sp) and then "frozen" (with respect to the standard product) and then various enhancements added ... like interfaces to all the diagnostic hardware that was going to be in the 3090. i provided some number of tools and other stuff, supporting the effort. Some of the stuff was things I had done for the disk engineering & product test labs ... to eliminate large class of failures (they had been running stand-alone with trivial monitor ... after having tried to use MVS and experienced 15min MTBF with a single "testcell"): http://www.garlic.com/~lynn/subtopic.html#disk At the time they had started the effort ... they gathered up as much stuff as they could ... anticipating that vm370 release 6 ... would not be current thru the lifetime of the 3090; TROUT ... some past posts with other old email from TROUT period: http://www.garlic.com/~lynn/2006j.html#27 virtual memory http://www.garlic.com/~lynn/2006j.html#31 virtual memory i was blamed for online computer conferencing on the internal network in the late 70s and early 80s. The POK engineering manager that headed up the 3090 service processor ... had observed all the issues with the 3081 service processor ... having to write everything from scratch and was a big proponent of using as much as possible readily available tools (i.e. 3090 service processor screens were actually CMS IOS3270). In any case, the guy heading up the effort also became somewhat active in some of the computer conferencing and took some amount of hits for the activity (although not nearly as much as I did). He also took hits on scope-creep in the effort and growing demand for people and resources. DOS Emulator feature had base/bound (significantly simpler than all the segment and page table stuff; just check the address against the "bound" ... and then add in the "base") ... not for paging but for address translation ... like some LPAR implementations ... still required a contiguous amount of real-memory. I was undergraduate in the 60s ... but still doing a lot of work on both os/360 (responsible for academic and administrative system at the univ. ... including doing highly customized os/360 system for careful placement of datasets and PDS members to optimize arm seek & getting approx three times thruput improvement for student jobs). I was also allowed to do a lot of cp67 ... rewritting lots of the kernel code. Anycase, recent posts about Boeing trying to move all of their dataprocessing into BCS (fledging BCS started out in boeing corporate hdqtrs administrative ... which had single 360/30 for payroll): http://www.garlic.com/~lynn/2009r.html#43 Boeings New Dreamliner Ready For Maiden Voyage http://www.garlic.com/~lynn/2009r.html#44 Boeings New Dreamliner Ready For Maiden Voyage http://www.garlic.com/~lynn/2009r.html#45 Boeings New Dreamliner Ready For Maiden Voyage and I got dragged into it. I was con'ed into giving one week class (during spring break, '69) to the fledging BCS technical staff (and the ibm technical support team). I was then brought in as full-time BCS employee for the summer of '69. Part of responsibility was installing cp67 operation in corporate hdqtrs machine room (which until then just had a 360/30 for payroll). Part of BCS was to take over the renton datacenter (a little corporate internal politics) ... which was the largest operation I had seen ... summer of '69 there were always pieces for 2-3 360/65s staged around in the hallways ... because 360/65s were arriving faster than they could be installed. In any case, after 370s were available ... but not yet with virtual memory support ... one of the IBM SEs on the boeing account did a "hacked" version of cp67 to use 370 DOS Emulator (aka address base+bound, contiguous real storage) ... again much more like LPAR support. He did do complete swap of a virtual machine address space (i.e. virtual machine size had to match the base+bound contiguous area) ... so could run more virtual machines that there was total real storage available. As mentioned in the above ... summer of '69 ... Boeing also moved the 360/67 multiprocessor from Huntsville to Seattle (this was separate from the 360/67 uniprocessor installed in corporate hdqtrs). Huntsville had been using it to run a highly modified version of MVT release 13. Problem was that MVT had significant problem with storage fragmentation with long running jobs. Huntsville had a large collection of 2250s with long running graphics application. Hack to MVT was to use the 360/67 address translation hardware to re-arrange real storage to appear "contiguous" (no paging) ... this was different than the early 370 hack to cp67 to use the base+bound (instead of full address translation) and real contiguous storage for primitive virtual machine swapping. Before virtual memory was announced, 370/145s weren't shipped with the microcode-load to support virtual memory ... however, the front panel "rollers" for the PSW ... had a "xlate" label for one of the bit/lights. for other topic drift, recent post about science center working with endicott on support 370 virtual memory architecture ... before hardware was even available: http://www.garlic.com/~lynn/2009r.html#38 While watching Biography about Bill Gates on CNBC last Night http://www.garlic.com/~lynn/2009r.html#39 While watching Biography about Bill Gates on CNBC last Night http://www.garlic.com/~lynn/2009r.html#40 While watching Biography about Bill Gates on CNBC last Night science center worked with endicott to modify cp67 (running on 360/67) to provide support for 370 virtual machines. This required having a "370" option ... and then simulating new instructions and misc. other stuff for "370" virtual machinesl Then a "different" cp67 was modified to run in those "370" virtual machines (rather than on 360/67, this "CP67I" was regularly running in 370 virtual machine a year before hardware became available). This 370'ized cp67 was used by endicott for testing ... when they had an engineering 370/145 with first virtual memory hardware working. other lore ... unbundling announcement was 23jun69 ... misc. past posts http://www.garlic.com/~lynn/submain.html#unbundle and they started charging for application software, SE services, other stuff ... but managed to make the case that kernel software was still free. one of the things I did as undergraduate at the univ. was add tty/ascii support to cp67. Part of that was trying to make the 2702 do something that it couldn't really do. Somewhat as a result, the univ. started a clone controller effort ... where the channel interface was reverse engineered and channel interface board built for an Interdata/3. The Interdata/3 was then programmed to simulate 2702 (but with the additional stuff I wanted to do). This got written up, blaming four of us for clone controller business http://www.garlic.com/~lynn/subtopic.html#360pcm Clone controller business has been cited as major motivation for the "future system" effort ... which was going to completely 360/370 ... and as different from 360/370 as 360 had been from prior generations. some past posts http://www.garlic.com/~lynn/submain.html#futuresys Eventually FS effort was killed ... but during the effort ... the 370 product pipeline was allowed to dry up (since it was going to be completely replace) ... and when it was killed there was mad rush to get stuff back into (hardware & software) 370 product pipeline. The lack of products was also credited with allowing clone processors to gain a foothold in the market. I had done a lot of stuff for cp67 as undergraudate ... that was picked up and shipped in the product. For the morph from cp67->vm370 much of that was dropped as "simplification". Now, all during the future system effort, I continued to do 370 stuff (and ridiculed pieces of the FS activity ... which wasn't exactly a career enhancing thing to do, since the senior executives were still senior executives after the dust cleared). Misc. old email about 370 stuff: http://www.garlic.com/~lynn/2006v.html#email731212 http://www.garlic.com/~lynn/2006w.html#email750102 http://www.garlic.com/~lynn/2006w.html#email750430 so the mad rush to get stuff back into the product pipeline, included picking up some stuff that I had continued to do (a lot that had been dropped in the morph from cp67->vm370). Some of it was incorporate in standard product releases ... however a portion was selected to be release as a separate "resource manager" component. And then, somewhat motivated by the clone processors foothold in the market ... it was decided to start transition to charging for kernel software ... and my "resource manager" was selected to be the guinea pig. As a result I had to spend some amount of time with lawyers and busines people about kernel software charging policies. vm370 release 6 "product" then was towards the end of this transition ... the base product was free ... but there was BSEPP (entry & mid-range, aka endicott machines) & SEPP (high-end, pok machines) chared-for "add-ons". In any case, There was no vm370 release 7 ... the next release was all "charged for" and called VM/SP release 1 (no separate kernel free and non-free, it was all non-free). Then the next stage was the OCO-wars ... not only charged-for ... but no longer shipping full source ... and providing full source maintenance on monthly PLC service tapes. Another result of the unbundling announcement ... was major blow to SE education ... basically apprentice type operation as parge of SE team at customer account (couldn't figure out how to justify charges for this activity ... but required to). This was original motiviation for HONE ... misc. past posts http://www.garlic.com/~lynn/subtopic.html#hone ... allow SEs in the branch office to play with operating systems in cp67 virtual machines. After initial 370 announcement ... the non-virtual memory 370 "changes" (few new instructions, other stuff) was incorporated into the HONE cp67 systems (allowing ipl of 370 operating systems gen'ed to use the new instructions). -- 40+yrs virtualization experience (since Jan68), online at home since Mar1970
