Re: Before the PC: IBM invents virtualisation (Cambridge skunkworks)
On 07/14/11 23:16, Boyes wrote: http://www.theregister.co.uk/2011/07/14/brief_history_of_virtualisation_par= t_2/ Somebody who actually gets it that there was a world before the PC. Few minor nits, but overall an actually decent article on the role VM played in prefiguring virtualization before VMWare. Recommended reading for the glossy magazine set. there is forum/blog for the article: http://forums.theregister.co.uk/forum/1/2011/07/14/brief_history_of_virtualisation_part_2/ I've added several ... also archived here: http://www.garlic.com/~lynn/2011i.html#63 -- virtualization experience starting Jan1968, online at home since Mar1970
HILLGANG (history) Presentation
Earlier this week I converted an old OCT86 SEAS (european share) presentation on VM History Performance from foildoc to powerpoint ... with a couple additions ... and presented it at 16Mar HILLGANG meeting. Exported PDF copy here: http://www.garlic.com/~lynn/hill0316g.pdf a little discussion of the foildoc (presentation) in this recent a.f.c. post http://www.garlic.com/~lynn/2011e.html#20 some of the period also discussed in this (linkedin) MainframeZone group discussion: http://lnkd.in/ku-thX -- virtualization experience starting Jan1968, online at home since Mar1970
Re: Central vs. expanded storage
Kris Buelens wrote: There is handshaking between Linux and VM, and even more than one flavor The fact that z/VM still likes to have some expanded storage is that the management of central and expanded are different: For expanded, CP has a time stamp and know exactly how old each page is. For central storage there only is the reference bit, thus CP can only know if the page was referenced since the last scan. re: http://www.garlic.com/~lynn/2010n.html#39 Central vs. expanded storage least-recently-used approximation replacement (whether used in the last scan or not) ... is based on assumption that it is predictor of probability that the page will be needed in the near future. as things age past a certain point ... differences in their age (since last used) becomes less reliable differentiator (as to higher or lower probability of being used in the near future) ... and some sort of psuedo-random can actually outperform strict ordering (some of these are scenarios where LRU devolves to FIFO ... and random performs better than straight FIFO). in the 70s, there were a number of places that looked at multiple bits ... effectively one per scan, possibly one hardware bits and one or more software bits, where RRB becomes more like logical shift instruction. One of the issues is if it takes too long to do a complete scan ... then there is little differentiation being made between pages. Splitting memory into storage and extended storage ... makes regular storage smaller and therefor the scan goes faster. Having multiple bits (more history) also tends to scan going faster ... since the additional history tends to require scan to look at more pages each time. Again from the early 70s, another approach is to offset the testing of the reference bit from resetting the reference bit ... say by 1/2 or 1/4 the number of pages. This gave the name to clock in the early 80s i.e. two hands rotating around storage pages ... one resetting and the other testing ... rather than a single hand resetting and testing simultaneously; while I had done something similar in the late 60s and early 70s ... clock was a stanford phd in the early 80s. At the time of the stanford phd ... there was some academic opposition to giving a degree in that specific area ... and I was asked to provide some of my supporting studies from more than a decade earlier. An old post http://www.garlic.com/~lynn/2006w.html#46 with copy of communication from the time: http://www.garlic.com/~lynn/2006w.html#email821019 Besides doing VM, GML, bunch of online conversational stuff, the science center had done a lot of work on performance monitoring, workload configuration profiling, and stuff that would turn into capacity planning. This included various kinds of system simulators and analytical modeling. One of the system simulators included using instruction/storage traces for simulating variety of page replacement algorithms ... including exact LRU (aka maintaining exact LRU ordering of *every* page based on each every reference). In the early 70s, I had come up with a variation on clock which would always beat exact LRU (coming closer to Belady's OPT ... given fore knowledge of program execution, it would always choose the page for replacement that resulted in the fewest total page faults).
Re: Central vs. expanded storage
On Thu, Sep 23, 2010 at 2:14 AM, O'Brien, Dennis L dennis.l.o'br...@bankofamerica.com wrote: I heard from a couple of performance people at SHARE that we should have 20% to 25% of the total storage in an LPAR configured as expanded storage. Naturally, that's a guideline and the proper amount varies by workload. What should I look at to determine if we have enough expanded storage? We use Velocity's ESALPS suite. The systems that I'm most concerned about have a Linux guest workload. One of them is all WAS, and the other is a mix of WAS, Oracle, and some other things. I've heard that WAS isn't the best choice for System z, but that's not the focus of my concern. We have the workload that we have, and I just want to make it run as well as it can. expanded store was originally done for 3090 because of physical packaging problems ... it was not possible to locate all the memory they needed for configuration within the latency of the standard memory bus ... so they created the expanded store bus that was wider longer ... and used software control to move 4k pages backforth between regular storage and expanded store. a synchronous instruction was provided for moving the data backforth. the expanded store bus was also used to attach HIPPI (100mbyte/sec) channel/devices ... since the standard 3090 i/o interface couldn't handle the data-rate. However, since bus didn't support channel programs ... there was a peculiar (pc-liked) peek/poke convention used (i.e. i/o control was done by moving 4k blocks to/from special reserved addresses on the bus). moving forward (after physical packaging was no longer an issue) ... expanded store paradigm has been preserved because of software storage management /or storage addressing deficiencies. effectively, expanded store paradigm is used to partition real storage into different classes however, going back at least 40yrs ... there is large body of data that shows that single large store is more efficient than partitioning the same amount of storage (assuming that there aren't other storage management issues/shortcomings). the simple scenario is 1 storage pages and 1 expanded storage pages ... all occupied; when there is requirement for page that is in expanded storage, it is swapped with a page in regular storage (incurring some software overhead). The alternative is one large block of 2 pages ... all directly executable ... and doesn't require swapping any pages between expanded store and regular store. One of the efficiencies is dealing with application and/or operating systems that perform their own caching/paging algorithm using some sort of LRU mechanism (i.e. replacing their own pages/records using some approximation to least-recently-used). This is characteristic of large DBMS infrastructures that manage records in their own cache as well as operating systems that support virtual memory. Their is a pathological scenario if the virtual operation doesn't have all its own dedicated storage (like in LPARs); VM will be managing virtual pages using an LRU methodology (least-recently-used pages are the ones selected for replacement) ... at the same time the virtual guest/DBMS is also managing (what it thinks is real storage) with an LRU methodology. If both are operating simultaneously ... it is possible for VM to replace what it thinks is the least-recently-used page (the virtual page least likely to be used) ... at the same time the virtual guest/DBMS has decided that same page is exactly the next page it wants to use. Executing LRU replacement algorithms in a virtual guest/DBMS ... where its storage is also being managed via an LRU replacement algorithm, ... can invalidate the assumption underlying LRU replacement algorithms ... that the least-recently-used page is the least likely to be used (a virtual guest/DBMS ... doing is own LRU algorithm is likely to select the least-recently-used page as the next page most likely to be used). misc. past posts mentioning expanded store http://www.garlic.com/~lynn/2000c.html#61 TF-1 http://www.garlic.com/~lynn/2001k.html#73 Expanded Storage? http://www.garlic.com/~lynn/2001k.html#74 Expanded Storage? http://www.garlic.com/~lynn/2002e.html#8 What are some impressive page rates? http://www.garlic.com/~lynn/2004e.html#2 Expanded Storage http://www.garlic.com/~lynn/2004e.html#3 Expanded Storage http://www.garlic.com/~lynn/2004e.html#4 Expanded Storage http://www.garlic.com/~lynn/2006.html#13 VM maclib reference http://www.garlic.com/~lynn/2006.html#38 Is VIO mandatory? http://www.garlic.com/~lynn/2006b.html#14 Expanded Storage http://www.garlic.com/~lynn/2006b.html#15 {SPAM?} Re: Expanded Storage http://www.garlic.com/~lynn/2006b.html#16 {SPAM?} Re: Expanded Storage http://www.garlic.com/~lynn/2006b.html#17 {SPAM?} Re: Expanded Storage http://www.garlic.com/~lynn/2006b.html#18 {SPAM?} Re: Expanded Storage http://www.garlic.com/~lynn/2006b.html#34 Multiple address spaces
3090 service processor 370 virtual memory (long winded x-over from ibm-main)
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
Re: spool file data
Another application by the VMSG author was parasite/story. It used the PVM logical device/3270 facility and had a HLLAPI type scripting language (before the advent of ibm/pc) ... it was after REX was available internally. Another remarkable thing was that the executable was small enough to fit in the CMS transient area. some old storys ... including automatic logging into RETAIN and retrieving PUT buckets: http://www.garlic.com/~lynn/2001k.html#35 Newbie TOPS-10 7.03 question http://www.garlic.com/~lynn/2001k.html#36 Newbie TOPS-10 7.03 question for other topic drift ... in the early 80s I did a re-implementation of the spool file system written in vs/pascal running in virtual machine. a problem was that HSDT project was putting in multiple T1 (and higher speed links) ... with aggregate thruput requirements of megabyte/sec or more. This was effectively impossible with RSCS and the existing spool file system. The spool file interface was synchronous transfer of 4k block at a time. On a system with competing transfers, a RSCS transfer might be stuffed in queue with 3-4 other operations ... giving RSCS possibly 4-5 4kbyte transfers/sec; I needed possibly 200-300 4kbyte transfers/sec for RSCS. I had my page-mapped filesystem for CMS with things like contiguous allocation, efficient multiple block transfers and while CMS might view the interface as synchronous ... but playing games with page table entries allowed for asynchronous transfers (a CMS application with moderate filesystem use had something like three times the thruput using page-mapped filesystem compared to normal CMS filesystem running on exact same hardware), i could leverage that interface for the virtual machine spool file implementation ... but I was taking spool file assembler kernel implementation, redo it in virtual machine pascal implementation and get at least 100 times increased thruput. The additional challenge was that since RSCS transferred the whole 4k spool file block ... all of the high-thruput changes modifications had to be done so that they were transparent and interoperated with RSCS running on unmodified vm370 systems. old posts on the subject in this mailing list http://www.garlic.com/~lynn/2000b.html#43 Migrating pages from a paging device (was Re: removal of paging device) http://www.garlic.com/~lynn/2003k.html#63 SPXTAPE status from REXX other posts on the subject: http://www.garlic.com/~lynn/94.html#22 CP spooling programming technology http://www.garlic.com/~lynn/94.html#29 CP spooling programming technology http://www.garlic.com/~lynn/2003b.html#33 dasd full cylinder transfer (long post warning) misc. past HSDT posts http://www.garlic.com/~lynn/subnetwork.html#hsdt -- 40+yrs virtualization experience (since Jan68), online at home since Mar1970
Re: CMS IPL ( other misc)
On 07/14/2009 01:00 AM, IBMVM automatic digest system wrote: Version 3 was the first CMS that could not be IPLled on the iron, I think. Someone should ask Lynn Wheeler. re: http://www.garlic.com/~lynn/2009j.html#67 DCSS http://www.garlic.com/~lynn/2009j.html#68 DCSS addenda CMS started out with 256kbyte (virtual) machine operation (on real 360/40). original virtual machine system (at science center) was cp/40 done on a (256kbyte) 360/40 that had special hardware modification to support virtual memory. while cp/40 was being developed ... cms was also being developed ... running on the bare 360/40 in non-virtual memory mode. when the science center replaced the 360/40 with 360/67 (standard product, basically 360/65 with hardware modifications to support virtual memory) ... cp40 morphed into cp67 when 3 people from the science center came out to install cp67 at the univ the last week of jan68 ... all source was kept on cards on loaded into os/360 and assembled under os/360 producing physical text decks ... which were combined together in a card tray with a modified BPS loader in the front. The physical cp67 deck was loaded into 2540 card reader and ipl. after BPS loader got the CP67 txT decks into memory ... it would transfer to the last program ... CPINIT (in vm370 DMKCPI) ... which would write the core image to specified disk location and write the IPL CCW sequence to the IPL disk. Distribution was os/360tapes. CMS would run in a 256kbyte virtual machine or on the bare hardware. Part of the issue was both CP40 (and then CP67) and CMS were being developed in parallel ... with the original source compile, etc ... all being done on os/360. Sometime by summer 68, science center had moved to having source as CMS files and assembling on CMS to produce TXT decks. Physical TXT were still being kept in card tray and physically IPL to build new IPL'able kernel. By that summer, I had done a lot of kernel CP67 pathlength work ... especially targeted for OS/360 in CP67 virtual machine. Old post with part of presentation I gave at the Aug68 SHARE meeting (held in Boston) ... lots of changes were picked up by the science center for standard cp67 and shipped http://.garlic.com/~lynn/94.html# CP/67 OS MFT14 I was also doing very carefully crafted OS/360 stage2 sysgens. I originally would get the stage2 card deck output from the OS/360 stage1 assemble ... and reorder all the statements to achieve carefully order of resulting generated system file on disk (to optimize arm seek operation). Later in 68, I looked at doing some pathlength enhancements for CMS environment (as well as starting on dynamic adaptive resource management, new page replacement algorithms, new scheduling algorithms and other stuff). Lots of CMS operation was simplified (compared to OS/360) ... so major (cp67) pathlength overhead was in CMS disk I/O channel program translation (CCW). I originally defined a new CCW op-code that in single CCW specified all the parameters for seek/search/tic/read/write operation ... drastically reducing the channel program translation overhead. I also noticed that CMS didn't do any multitasking ... just did serialized wait for the disk i/o to complete. So I gave this new CCW op-code serialized semantics (i.e. it actually returned to virtual SIO after the I/O had completed, with CC=1 CSW stored). I got a lot of push back from the science center about having violated virtual machine architecture (a CCW that wasn't defined in any hardware manual). They explained that the appropriate way to violate the 360 principles of operation was with the diagnose instruction ... which was defined as being model dependent implementation. The fiction was then to define a virtual machine hardware model ... where the operation of the diagnose instruction were according to virtual machine (model) specification. CMS was modified to use a diagnose instruction at startup to determine whether it was running in virtual machine or (instruction failed) on real machine. If running in virtual machine, it would be setup to use diagnose instruction for diak i/o (semantics about the same as my special CCW) or SIO ( interrupts) for disk I/O. In the initial translation to VM370 (release 1), CMS (cambridge monitor system) was renamed to CMS (conversational monitor system) and the test for running in virtual machine was removed as well as the code to use SIO ( interrupts) for disk I/O ... eliminating CMS's ability to run on bare hardware. In cp67 there was a facility for saving named virtual memory pages and ipl-by-name virtual memory pages. The NAME specifications were part of a kernel module (renamed DMKSNT for VM370). In cp67, the named tables specified the range of virtual pages to be saved (and the disk location where they were to be saved). The ipl-by-name would modify virtual memory tables to point to the specified disk location (with RECOMP bit ... that the disk location was R/O to the page replacement algorithm ...
Re: IBMVM Digest - 12 Jul 2009 to 13 Jul 2009 (#2009-188)
Jeff wrote: I'm definitely no substitute for Sir Lynn, but I remember DCSS and DMKSNT in VM/370 Release 3 PLC 8, which is where I started with VM. In fact, I used CMSAMS and CMSVSAM then for Unnatural Practices, or at least not for the purposes for which they were created. I was porting the CP/67 port of LISP/MTS to VM/370, and needed something to replace the named segment used under CP/67 for LISP's pushdown stack. Instead of checking the stack pointer for the end of the stack, it would just push onto the stack and take the program check when it ran off the end. I simulated that by using DIAG x'64' to attach CMSAMS and CMSVSAM, and then set the protect key to user key for all but the last 2K (remember 2K pages?) page. A LISP interpreter written entirely in BAL, with self-modifying code and almost out of base register addressibility... that was quite an interesting piece of code. re: http://www.garlic.com/~lynn/2009j.html#67 http://www.garlic.com/~lynn/2009j.html#68 http://www.garlic.com/~lynn/2009j.html#76 and post in similar thread that I started in linkedin mainframe discussion http://www.garlic.com/~lynn/2009j.html#73 I mentioned that Cambridge had done port of apl\360 to (cp67) cms for cms\apl. This then became one of the main vehicles for deliverying sales marketing support on (virtual machine based) HONE (first cp67 and then moved to vm370 ... eventually with HONE clones all over the world) ... some past HONE clones http://www.garlic.com/~lynn/subtopic.html#hone a quick named version was done by getting APL started and then getting it at a certain point and doing a named system ... that was not only CMS but also APL. Then when IPL'ed ... the machine was placed immediately at a point in APL (special place chosen so it would do some last minute housekeeping and setup). One of the univ. did something similar for ipl-by-named version of os/360. for vm370 ... palo alto science center did a lot of additional stuff for apl\cms (including the apl microcode assist on the 370/145). For early vanilla vm370, HONE started out with ipl-by-name apl\cms ... with the addition that the cms shared segment was defined as well as most of the APL executable module and even some APL workspace. A early problem had some non-APL applications and had issue with trying to explain to salesman (which were mostly hardly computer literate users) how to IPL CMS ... to execute non-APL applications and then IPL APL ... to get back into the normal (APL-based) sales marketing environment. When I started distributing CSC/VM with the enhancements, HONE was one of the major internal clients (they even con'ed me into doing several of the early clone installations around the world). With the paged-mapped filesystem and the enhanced changes ... most salesmarketing could IPL normal CMS and have their profile setup to immediately execute APL (cms executable from S or Y disk that happened to be paged mapped format) ... and all the page mapping and shared segment was done as part of normal CMS program loading. Then it was possible to have APL processes that would invoke and execute non-APL applications ... even placing the user in the non-APL application environment w/o having to explain to the user about the IPL command or some of the other non-APL (there was a large salesmarketing APL application called SEQUOIA that actually hid nearly all APL CMS characteristics from the sales marketing people ... it was even possible that many sales marketing people never realized that they were using APL /or CMS). I've several times told the story that between middle 70s until at least middle 80s .. every couple yrs there would be a promotion of some sales/marketing person to the head of the dataprocessing business unit that included HONE. They would be startled to find that HONE was VM370/CMS based on figure that they could make their career by forcing HONE to be ported to MVS. This would consume the HONE organization for possibly 12 months until it was extremely evident that it was practical. Then things would almost return to normal until the next person was promoted into the position. As I've mentioned ... a small subset of the (shared/named) capabilities was shipped in vm370 release 3 as DCSS. It was then possible for (normal) customers to define APL as a named system w/o requiring the paged mapped filesystem support. One of the early issues with port of APL\360 for CMS\APL ... there was a big performance issue with how APL did storage allocation and (periodic) garbage collection. The problem wasn't noticed in a real workspace environment of APL\360 where the whole workspace was swapped as single unit. CMS/APL opened workspace up to nearly the full virtual machine size (which might be 16mbytes) ... and the garbage collection performed terribly in virtual memory paged environment ... and had to be significantly redone. the port to CMS\APL also added APL functions that could access CMS system services ... including ability to read
Re: More named/shared systems
Jeff wrote: I'm definitely no substitute for Sir Lynn, but I remember DCSS and DMKSNT in VM/370 Release 3 PLC 8, which is where I started with VM. In fact, I used CMSAMS and CMSVSAM then for Unnatural Practices, or at least not for the purposes for which they were created. I was porting the CP/67 port of LISP/MTS to VM/370, and needed something to replace the named segment used under CP/67 for LISP's pushdown stack. Instead of checking the stack pointer for the end of the stack, it would just push onto the stack and take the program check when it ran off the end. I simulated that by using DIAG x'64' to attach CMSAMS and CMSVSAM, and then set the protect key to user key for all but the last 2K (remember 2K pages?) page. A LISP interpreter written entirely in BAL, with self-modifying code and almost out of base register addressibility... that was quite an interesting piece of code. re: http://www.garlic.com/~lynn/2009j.html#67 http://www.garlic.com/~lynn/2009j.html#68 http://www.garlic.com/~lynn/2009j.html#76 and post in similar thread that I started in linkedin mainframe discussion http://www.garlic.com/~lynn/2009j.html#73 I mentioned that Cambridge had done port of apl\360 to (cp67) cms for cms\apl. This then became one of the main vehicles for deliverying sales marketing support on (virtual machine based) HONE (first cp67 and then moved to vm370 ... eventually with HONE clones all over the world) ... some past HONE clones http://www.garlic.com/~lynn/subtopic.html#hone a quick named version was done by getting APL started and then getting it at a certain point and doing a named system ... that was not only CMS but also APL. Then when IPL'ed ... the machine was placed immediately at a point in APL (special place chosen so it would do some last minute housekeeping and setup). One of the univ. did something similar for ipl-by-named version of os/360. for vm370 ... palo alto science center did a lot of additional stuff for apl\cms (including the apl microcode assist on the 370/145). For early vanilla vm370, HONE started out with ipl-by-name apl\cms ... with the addition that the cms shared segment was defined as well as most of the APL executable module and even some APL workspace. A early problem had some non-APL applications and had issue with trying to explain to salesman (which were mostly hardly computer literate users) how to IPL CMS ... to execute non-APL applications and then IPL APL ... to get back into the normal (APL-based) sales marketing environment. When I started distributing CSC/VM with the enhancements, HONE was one of the major internal clients (they even con'ed me into doing several of the early clone installations around the world). With the paged-mapped filesystem and the enhanced changes ... most salesmarketing could IPL normal CMS and have their profile setup to immediately execute APL (cms executable from S or Y disk that happened to be paged mapped format) ... and all the page mapping and shared segment was done as part of normal CMS program loading. Then it was possible to have APL processes that would invoke and execute non-APL applications ... even placing the user in the non-APL application environment w/o having to explain to the user about the IPL command or some of the other non-APL (there was a large salesmarketing APL application called SEQUOIA that actually hid nearly all APL CMS characteristics from the sales marketing people ... it was even possible that many sales marketing people never realized that they were using APL /or CMS). I've several times told the story that between middle 70s until at least middle 80s .. every couple yrs there would be a promotion of some sales/marketing person to the head of the dataprocessing business unit that included HONE. They would be startled to find that HONE was VM370/CMS based on figure that they could make their career by forcing HONE to be ported to MVS. This would consume the HONE organization for possibly 12 months until it was extremely evident that it was practical. Then things would almost return to normal until the next person was promoted into the position. As I've mentioned ... a small subset of the (shared/named) capabilities was shipped in vm370 release 3 as DCSS. It was then possible for (normal) customers to define APL as a named system w/o requiring the paged mapped filesystem support. One of the early issues with port of APL\360 for CMS\APL ... there was a big performance issue with how APL did storage allocation and (periodic) garbage collection. The problem wasn't noticed in a real workspace environment of APL\360 where the whole workspace was swapped as single unit. CMS/APL opened workspace up to nearly the full virtual machine size (which might be 16mbytes) ... and the garbage collection performed terribly in virtual memory paged environment (LISP had something similar) ... and had to be significantly redone. the port to CMS\APL also added APL functions that could access CMS system services
Timeline: The evolution of online communities
A history related post copied from a.f.c. ng: Timeline: The evolution of online communities http://www.computerworld.com/s/article/9135308/Timeline_The_evolution_of_online_communities from above: E-mail discussion lists, chat rooms, BBSs, Usenet groups and more all played a role in the development of online communities as we know them today. ... snip ... cp67 vm370 had real time messages on the same real system and then supported by rscs/vnet that would forward such messages between remote systems ... internal network was larger than arpanet/internet from just about the beginning until sometime late '85 or early '86. http://www.garlic.com/~lynn/subnetwork.html#internalnet Tymshare supported online conferencing early 70s ... and made the facility free to SHARE VM group in Aug76: http://vm.marist.edu/~vmshare/ in the late 70s and early 80s I got blamed for online computer conferencing on the internal network doing semi-automated mailing list operation ... recent reference in this n.g. http://www.garlic.com/~lynn/2009e.html#26 Microminiaturized Modules the above some major motivation behind official effort that resulted in the internal TOOLSRUN ... which could simultaneously operate somewhat similar to USENET and mailing list (i.e. somebody could subscribe as mailing list ... or setup TOOLSRUN client that would subscribe and maintain local repository of posts). Listserv on BITNET, misc. past posts http://www.garlic.com/~lynn/subnetwork.html#bitnet was somewhat to duplicate at least part of the TOOLSRUN function discussed here (starting Paris, 1985 ... i.e. the EARN part of BITNET) http://www.lsoft.com/products/listserv-history.asp related email (from Paris) regarding setting up EARN http://www.garlic.com/~lynn/2001h.html#email840320 in this post http://www.garlic.com/~lynn/2001h.html#65 and looking for network-oriented applications for the educational institution users. There is also esample of the distributed evolution of the REX language implementation in the late 70s and early 80s (leveraging the internal network) ... some discussion here: http://www-01.ibm.com/software/awdtools/rexx/library/rexxhist.html and here: http://web.archive.org/web/20020506063424/http://computinghistorymuseum.org/ieee/af_forum/read.cfm?forum=10id=21thread=7 the author of rexx ... had also done a multi-user space war game for cms (on 3270s) that used the rscs/vnet forwarding interface to extend the game into distributed environment across multiple machines in the network. somewhat as the result for getting blamed for online computer conferencing on the internal network in the late 70s and early 80s ... there was a researcher that was paid to sit in the back of my office for nine months and take notes on how I communicated (as well go with me to meetings). They also got copies of all my incoming and outgoing email as well as logs of all my instant messages. The result was an internal corporate report ... but also Stanford Phd thesis (joint between language and computer AI) as well as some number of papers and books ... misc. past posts mentioning computer mediated conversation http://www.garlic.com/~lynn/subnetwork.html#cmc -- 40+yrs virtualization experience (since Jan68), online at home since Mar1970
Re: DCSS
Chip Davis wrote: ... when shared segments were implemented in VM. It seems to me that it predated the VM/370 SEPP/BSEPP days when I started, but there's been many a synapse lost since then. Google, Wikipedia, ibm.com, and even Melinda's wonderful work have not been revealing, so I thought perhaps might be an old gray-beard like myself (with a better memory) still reading this list. Any help? CP67 had named systems ... basically page image was saved to reserved location and the IPL command would map the saved portion of virtual memory to those saved pages on disk. Used originally for CMS. 360/67 segment (sharing) only offered 1mbyte segments ... and CMS was much smaller than 1mbyte ... in fact standard CMS virtual machines were 256kbytes and CMS kernel (low core address) was something like the first 18 pages. So something as a result ... CMS had 3 shared pages ... that were locked into real storage ... every virtual memory page table (for named CMS) had same 3 virtual page table entries pointing to the same (locked) real pages. To provide read-only protection of those three pages, CP67 played special games with the 360 storage protect keys. Moving to 370, original 370 virtual memory architecture (defined in the 370 red book ... the red book was cms script file with command line options would print the full architecture book ... or just the principles of operation subset) had 64kbyte segment options and 1mbyte segment options. For 370, CMS was restructured to have the 1st 64k non-shared data, and the 2nd 64k shared ... using the 370 64kbyte shared segment facility. The original 370 virtual memory architecture also had R/O segment protect facility ... bit defined in each virtual memory segment table which would provide R/O segment protection. vm370 was initially implemented to use this facility for protecting shared pages. The mechanism was still the defined named systems and invoked/used via the ipl-by-name facility. the retrofit of virtual memory hardware to 370/165 ran into delays and at one point there was suggestion to drop a lot of the 370 virtual memory features in order to buy back six months in the scheduled (and not slip the 370 virtual memory announcement by six months). One of the features that got dropped was segment protect. As a result, all the other hardware implementations had to go back and remove all the features dropped by the 165 implementation ... and vm370 had to return to the (kludge) r/o page protection mechanism using the 360 key protect mechanism (from cp67) ... but for whole segments. I was at the science center ... past posts mentioning science center http://www.garlic.com/~lynn/subtopic.html#545tech and we were still running with 360/67 and doing lots of enhancements to cp67. One of the features was a page-mapped filesystem faciilty for cms. This eliminated a whole lot of I/O simulation overhead and pathlength (even compared to diagnose I/O ... a form of which I had originally done as undergraduate) and opened up the ability to do a whole lot more interesting things using virtual memory (basically allowing page mapped views of anything done as part of standard cms file operations ... not just restricted to ipl-by-name). Misc. past posts mentioning page-mapped work for cms filesystem http://www.garlic.com/~lynn/subtopic.html#mmap Eventually, science center was slated for getting at 370/155 and I had to look at moving lots of my cp67 work to vm370 ... old memo on the subject http://www.garlic.com/~lynn/lhwemail.html#email731212 and a couple describing having done the work (and what was in the csc/vm distribution system) http://www.garlic.com/~lynn/2006w.html#email750102 http://www.garlic.com/~lynn/2006w.html#email750430 one of my hobbies had been providing highly modified cp67 systems to internal locations (sort of my own product distribution). that dropped off as some number of internal locations moved from cp67 to vm370 ... but really took off when I had moved from cp67 to vm370. One of my major hobby/customers was the HONE system ... lots of past posts http://www.garlic.com/~lynn/subtopic.html#hone HONE had been created after the 23jun69 unbundling announcement ... originally cp67 virtual machine systems originally targeted at giving branch office SEs hands-on to operating systems running in virtual machines. The HONE system even got special CP67 modifications that simulated the initial new instructions in 370 ... allowing running/testing of 370 operating systems that used the new instructions (i.e. allowing them to run in virtual machine under cp67 on 360/67. The science center had also ported apl\360 to cp67 cms for cms\apl. A lot of sales marketing support applications were developed in APL and started to be offered to sales marketing. Eventually that use came to dominate HONE activity and the virtual machine experience for branch office SEs evaporated. APL had been restructured to shared memory operations and originally HONE had a special
Re: DCSS addenda
re: http://www.garlic.com/~lynn/2009j.html#67 DCSS Some of the other stuff in CSC/VM was released in my resource manager (which appeared with vm370 release 3 plc9) the 23jun69 unbundling announcement started charging for (application) software and se services (but they managed to make the case that kernel software should still be free). some posts mentioning unbundling http://www.garlic.com/~lynn/submain.html#unbundle When I was undergraduate ... I had added tty/ascii terminal support to cp67 ... and tried to make the 2702 do something it couldn't quite do. that somewhat was motivation behind the univ. starting a project for a clone controller using interdata/3 ... discussed some in this recent post http://www.garlic.com/~lynn/2009j.html#60 A Complete History Of Mainframe Computing four of us got written up being responsible for clone controller business. some posts mentioning clone controller http://www.garlic.com/~lynn/subtopic.html#360pcm The clone controller business has been attributed as the motivation for the FS project. http://www.ecole.org/Crisis_and_change_1995_1.htm quote from above: IBM tried to react by launching a major project called the 'Future System' (FS) in the early 1970's. The idea was to get so far ahead that the competition would never be able to keep up, and to have such a high level of integration that it would be impossible for competitors to follow a compatible niche strategy. However, the project failed because the objectives were too ambitious for the available technology. Many of the ideas that were developed were nevertheless adapted for later generations. Once IBM had acknowledged this failure, it launched its 'box strategy', which called for competitiveness with all the different types of compatible sub-systems. But this proved to be difficult because of IBM's cost structure and its RD spending, and the strategy only resulted in a partial narrowing of the price gap between IBM and its rivals. ... snip ... old post with somebody taking FS quotes from FergusMorris book on IBM http://www.garlic.com/~lynn/2001f.html#33 IBM's VM for the PC c.1984?? Now allowing 370 product pipelines dry up is claimed to have given the clone processors foothold in the market ... and success of the clone processors is major motivation to decide to start (also) charging for kernel software. My resource manager got chosen to be the guinea pig for kernel software charging ... and as a result ... I had to spend some amount of time with the business people lawyers on policies regarding software charging. another mad rush to get products back into the 370 product pipeline was the 303x stuff ... recent discussion http://www.garlic.com/~lynn/2009j.html#59 A Complete History Of Mainframe Computing basically after FS was killed, work on 3081 was started but that was going to take 6-7 yrs ... and they needed something on much shorter cycle ... so 3031 was repackaged 370/158, 3032 was repackaged 370/168, and 3033 started out as 168 wiring diagram remapped to newer chips that were 20% faster. Now one of the things that were in the page-mapped filesystem stuff was location independence support. Carefully crafted executable code could be loaded at any virtual location in any virtual address space. The same shared object could appear at different virtual addresses in different virtual address spaces. Operating systems that had been designed for paged-mapped operations had support for this as a matter of course ... including IBM's TSS/360. CMS inherited a lot of its structure, compilers and other features from os/360 ... which had a real-storage orientation. OS/360 Relocatable address constants ... were relocated at load time ... and while executing were tied to a specific address. This nominally prevented having the same shared object appearing simultaneously in multiple virtual address spaces at different addresses. The 370 issue was that with only 256 64kbyte segments (in 16mbyte virtual address space) ... there would be great difficulty in finding unique locations for every application that might be available at a large location. Any single user wouldn't necessarily require more than 16mbytes ... but might require an arbitrary combination of applications available at the installation. To support shared fixed address applications which might be used in arbitrary combination... a unique location had to be chosen for ever application ... but the total possible aggregate size of all available applications exceeded 16mbytes. Lots of past posts mentioning difficulty of modifying code so it would be location independent while executing (in addition to having to modify it for executing in a R/O protected shared segment) http://www.garlic.com/~lynn/submain.html#adcon
20 Years Ago Today: Birth of the Dot-Com Era
20 Years Ago Today: Birth of the Dot-Com Era http://www.pcworld.com/businesscenter/article/166302/20_years_ago_today_birth_of_the_dotcom_era.html from above: In those days, the Internet consisted of regional networks, who were mostly non-profit cooperatives, and the government funded 'NSFNet' backbone which linked them up, writes Templeton, a friend of many years' standing. ... snip misc. past posts mentioning NSFNet: http://www.garlic.com/~lynn/subnetwork.html#nsfnet and some old NSFNet related email http://www.garlic.com/~lynn/lhwemail.html#nsfnet for other drift ... SLAC (slac vm370 system) first webserver outside cern/europe http://www.slac.stanford.edu/history/earlyweb/history.shtml GML had been invented at the science center in 1969 and then standardized as SGML in the late 70s ... misc. past posts mentioning GML, SGML, etc http://www.garlic.com/~lynn/submail.html#sgml CMS script command did document formatting using dot commands ... somewhat from similar/earlier CTSS command. After, GML was invented, support for GML tag processing was added to script. Waterloo had done a clone of the cms command ... webpage tracking evolution from SGML into HTML at CERN: http://infomesh.net/html/history/early/ above includes references to Waterloo SCRIPT GML User's Guide.
Re: radar interfering with computer gear
Walter wrote: When examined after each failure, the core (yes, real core) memory was always wiped clean. That computer (and its tech) was housed in a metal box (IIRC, about 6'x10', 8' high) which was transportable on the back of a 2 1/2 ton (6-by) truck, or by helicopter It was located about 15 feet from another similar box with all the radar gear inside, and large radar dish on the top. After a few days of random core wipes, someone noticed that the core wipe only happened when the door to the computer hut was momentarily opened as the radar dish swept past. While aimed much higher, there was enough residual power from the dish to wipe the computer's core memory clean. Memory was reloaded (back on track now) from dependable paper tape. old thread about Mt. Umunhum interfering with (stanford) SAIL computer: http://www.garlic.com/~lynn/aadsm25.htm#25 the referenced URL has gone 404 http://www-db.stanford.edu/pub/voy/museum/pictures/AIlab/SailFarewell.html but is here: http://infolab.stanford.edu/pub/voy/museum/pictures/AIlab/SailFarewell.html from above: I got proper air conditioning a short time later, but unfortunately developed a bad case of hiccups that struck regularly at 12 second intervals. My assistants spent a number of days trying to find the cause of this mysterious malady without success. As luck would have it, somebody brought a portable radio into my room one day and noticed that it was emitting a Bzz at regular intervals -- in fact, at the same moment that I hicced. Further investigation revealed that the high-powered air defense radar atop Mt. Umunhum, about 20 miles away, was causing some of my transistors to act as radio receivers. We solved this problem by improving my grounding. ... snip ... for other drift ... later posts in the previously mentioned ibm-main thread http://www.garlic.com/~lynn/2009h.html#42 Book on Poughkeepsie http://www.garlic.com/~lynn/2009h.html#44 Book on Poughkeepsie http://www.garlic.com/~lynn/2009h.html#47 Book on Poughkeepsie http://www.garlic.com/~lynn/2009h.html#48 Book on Poughkeepsie http://www.garlic.com/~lynn/2009h.html#55 Book on Poughkeepsie http://www.garlic.com/~lynn/2009h.html#56 Punched Card Combinations http://www.garlic.com/~lynn/2009h.html#61 Punched Card Combinations http://www.garlic.com/~lynn/2009h.html#62 Book on Poughkeepsie and a recent, separate virtual machine thread in a.f.c: http://www.garlic.com/~lynn/2009h.html#59 Operating Systems for Virtual Machines http://www.garlic.com/~lynn/2009h.html#63 Operating Systems for Virtual Machines http://www.garlic.com/~lynn/2009h.html#64 Operating Systems for Virtual Machines http://www.garlic.com/~lynn/2009h.html#65 Operating Systems for Virtual Machines -- 40+yrs virtualization experience (since Jan68), online at home since Mar1970
Re: IBM 1401
rschuh wrote: The smaller systems, the 360-20 and 360-30 had a 1401 emulator mode. It was= a h/w or mc based feature. I don't know whether larger machines had it. Th= ere was also a 1410 emulator mode on the -40. I do not know of any 1401 sup= port that ran under DOS, but my DOS experience is miniscule.=20 360/30 had 1401 microcode emulation ... actually 360/30 front panel switch that selected 360 microcode emulation (since 360 was implemented as microcode on 360/30) and 1401 microcode emulation recent stories in ibm-main mailing list about univ. getting 360/30 to replace 1401 (in staged processs of replacing 709/1401 combo with 360/67 which was suppose to run with tss/360). http://www.garlic.com/~lynn/2009h.html#12 IBM Mainframe: 50 Years of Big Iron Innovation http://www.garlic.com/~lynn/2009h.html#41 Book on Poughkeepsie 709 ran ibsys, tape-tape, a lot of fortran student jobs. 1401 was front-end spooling handling card reader- tape tape-printer/punch for the 709 ... with tapes being manually moved from 1401 tapes and 709 tapes. Even tho the 1401 MPIO program ran perfectly fine on 360/30 in 1401 emulation mode (switch to emulation mode and boot MPIO from 2504 reader, effectively same as if running real 1401) ... I got a student job to re-implement it in 360 ... I got to design my own monitor, interrupt handling, device drivers, storage management, console interface, etc. Eventually was 2000 card program with assembler directive that would either generate a stand-alone program or version that ran under os/360. Stand-alone version took approx. 30 minutes to assemble ... version that would run under os/360 took nearly an hour to assemble since it took approx. five minutes elapsed time per DCB macro. The univ. eventually got a 360/67 ... but since tss/360 wasn't ready, it spent nearly all its time running os/360 as 360/65. 360/65 (and 360/67) had 709x microcode emulation support (as opposed to 1401 emulation available on lower-end 360s). Last week of January 1968, three people from the science center ... some past posts http://www.garlic.com/~lynn/subtopic.html#545tech came out to the univ. to install (virtual machine) cp67. at the time, cp67 wasn't really up to the univ. os/360 production workload ... but I got to play with it quite a bit on weekends. some discussion detailed in these posts: http://www.garlic.com/~lynn/2009h.html#47 Book on Poughkeepsie http://www.garlic.com/~lynn/2009h.html#48 Book on Poughkeepsie misc. other recent related posts in ibm-main mailing list thread http://www.garlic.com/~lynn/2009h.html#14 IBM Mainframe: 50 Years of Big Iron Innovation http://www.garlic.com/~lynn/2009h.html#42 Book on Poughkeepsie http://www.garlic.com/~lynn/2009h.html#44 Book on Poughkeepsie 360/30 functional characteristics has reference to 1401/1440/1460 compatibiilty feature (GA24-3255) http://www.bitsavers.org/pdf/ibm/360/funcChar/GA24-3231-7_360-30_funcChar.pdf 1401 simulator for os/360 contributed program: http://www.bitsavers.org/pdf/ibm/360/360D-11.1.019_1401simCorr_Sep69.pdf it might not have been all the difficult to port above to CMS??? 1401/1440/1460 Emulator Programs (under dos/360) http://www.bitsavers.org/pdf/ibm/360/GC27-6940-4_360_1401emul.pdf 360/65 functional characteristics http://www.bitsavers.org/pdf/ibm/360/funcChar/A22-6884-3_360-65_funcChar.pdf 360/67 functional characteristics http://www.bitsavers.org/pdf/ibm/360/funcChar/A27-2719-0_360-67_funcChar.pdf lists optional feature: 709/7040/7044/7090/7094/7094II Compatibility single processor 360/67 was nearly identical to single processor 360/65 except with addition to virtual address translation hardware. -- 40+yrs virtualization experience (since Jan68), online at home since Mar1970
Re: remembering PGP
On 03/04/2009 01:02 AM, IBMVM automatic digest system wrote: Long ago, in a galaxy close to where I am this week, there was a PGP MODULE. It was built by a kind person at MIT (which is NOT close to where I am this week) and worked exactly as one would expect it to work. Maybe some day we will have a PGP for CMS again. Dunno. Recently, PGP got interesting again (to me). Actually, GPG is what I use instead (for better or worse). So it occured to me that when there is a face-to-face opportunity, such as that enjoyed by those fortunate souls who made the trek to Central Texas, the subject of key signing should be kept in mind. Therefore, if you happen to be in Austin this week and have a GPG key and want a signature, let me know. At least, let SOMEONE know. (My signature may not be what you need, and I am okay with that. But ... get yer keys signed!) some old email discussing pgp-like implementation for the internal network http://www.garlic.com/~lynn/2006w.html#email810505 in this post http://www.garlic.com/~lynn/2006w.html#12 more secure communication over the network and http://www.garlic.com/~lynn/2007d.html#email810506 in this post http://www.garlic.com/~lynn/2007d.html#49 certificate distribution misc. old public key /or crypto email http://www.garlic.com/~lynn/lhwemail.html#crypto misc. past posts mentioning the internal network ... which was larger than the arpanet/internet from just about the beginning, until sometime late '85 or possibly early '86 http://www.garlic.com/~lynn/subnetwork.html#internalnet -- 40+yrs virtualization experience (since Jan68), online at home since Mar70
Re: Seeking (former) Adventurers
following are a couple of emails from '78 regarding getting a copy of adventure for vm370/cms http://www.garlic.com/~lynn/2006y.html#email780405 http://www.garlic.com/~lynn/2006y.html#email780405b in this post http://www.garlic.com/~lynn/2006y.html#18 The History of Computer Role-Playing Games additional followup in this post http://www.garlic.com/~lynn/2006y.html#19 The History of Computer Role-Playing Games another old adventure email reference http://www.garlic.com/~lynn/2007o.html#email790912 in this post http://www.garlic.com/~lynn/2007o.html#15 Atuan - Colossal Cave in APL? In the above, there was some amount of trouble caused by my making adventure (executable) available internally (via the internal network). I had an offer that anybody finishing the game (getting the points), i would send them a copy of the (fortran) source. At least one of the people at the STL lab converted the fortran source to PLI and added a bunch of additional rooms/pts.
whitehouse email
you might find this news article interesting Whitehouse Emails Were Lost Due to Upgrade http://news.slashdot.org/news/08/04/30/1359209.shtml and The case of the missing e-mail http://arstechnica.com/articles/culture/bush-lost-e-mails.ars and for some more whitehouse email from 25yrs or so ago (that weren't lost) http://www.cnn.com/SPECIALS/cold.war/episodes/18/archive/ from nearly the start in the 70s, I had been quite rabid about backups and backups of backups and backups of backups of the backups. There has been speculation that orientation carried over to PROFS deployments. In any case, that supposedly was major factor in the above reference. somebody told me in the early 90s that similar email systems had been deployed at numerous gov. agencies. during the period I was getting to play disk engineer http://www.garlic.com/~lynn/subtopic.html#disk and working on system/r (original relational/sql implementation): http://www.garlic.com/~lynn/subtopic.html#systemr and doing an internal sjr/vm distribution ... a recent refs: http://www.garlic.com/~lynn/2006u.html#26 Assembler question with this old email: http://www.garlic.com/~lynn/2006u.html#email800501 I had also implemented what I called CMSBACK ... some old email refs http://www.garlic.com/~lynn/lhwemail.html#cmsback and http://www.garlic.com/~lynn/2006t.html#email791025 http://www.garlic.com/~lynn/2006w.html#email801211 which was deployed internally at several internal locations ... including the internal (vm370-based) HONE systems that provided world-wide sales marketing support http://www.garlic.com/~lynn/subtopic.html#hone misc. past posts mentioning backup and/or archive http://www.garlic.com/~lynn/subtopic.html#backup CMSBACK went thru several internal releases and then a morph for a customer release under the product name workstation datasave facility. The product name then morphed into ADSM ... and then the name morphed again and is currently sold as TSM (tivoli storage manager). current Tivoli storage manager reference: http://www-306.ibm.com/software/tivoli/products/storage-mgr/ reference to virtual machine use in the gov. even much earlier: http://www.nsa.gov/selinux/list-archive/0409/8362.cfm as an undergraduate in the 60s, i did a lot of system enhancements that were picked up and shipped in the product. i even got requests from ibm for some specific changes. many years later ... having learned about some of the customers, i interpreted some of the change requests as of a security nature and possibly have originated from some such gov. agency.
Re: VTAM R.I.P. -- SNATAM anyone?
Jim Bohnsack wrote: I remember the SNATAM name now. There was an Englishman, Graham Pursey, who used to attend the VNET Project Team meetings that were held once or twice a year. It seems to me that he was involved in some kind of VM based VTAM project. Was that it or was there something else? It seems to me that there was something besides SNATAM. Getting old and memory is the second thing to go. Don't remember what the first was. from the 26-28feb80 VMITE schedule: Graham Pursey - SNATAM. This system is being perfected in Hursley to operate SNA devices from a CMS based system. The current direction is to make this into a product. 45 minutes to 1 hr ... snip ... there were constant battles with the communication group ... I got into all sort of problems with hsdt (high speed data transport) project ... http://www.garlic.com/~lynn/subnetwork.html#hsdt to place things in better perspective ... SNA wasn't networking ... it was dumb terminal communication. example of gap between the communication group and hsdt project: and also working with various parties associated with getting NSFNET going. http://www.garlic.com/~lynn/subnetwork.html#nsfnet recent retelling http://www.garlic.com/~lynn/2008e.html#45 of an announcement (one friday) by the communication group for a new internal conference. included in the announcement were these definitions (to be used for the conference): low-speed: 9.6kbits medium-speed: 19.2kbits high-speed 56kbits very high-speed 1.6mbits the next monday on a business trip to the far east, definition on the conference room wall low-speed 20mbits medium-speed 100mbits high-speed200-300mbits very high-speed 600mbits eventually we weren't allowed to bid on nsfnet backbone ... even tho a nsf audit of the high-speed backbone claimed that what we already had running (internally) was at least five years ahead of all NSFNET bid submissions. some related old email from the period http://www.garlic.com/~lynn/lhwemail.html#nsfnet including some stuff forwarded to us about communication group spreading FUD that sna vtam could be used for NSFNET. http://www.garlic.com/~lynn/2006w.html#email870109 for other topic drift, the internal network http://www.garlic.com/~lynn/subnetwork.html#internalnet (which wasn't SNA until the late 80s) was technology from the science center http://www.garlic.com/~lynn/subtopic.html#545tech and was larger than the arpanet/internet from just about the beginning until sometime mid-85. this was about the time that serious efforts were made to try and get the internal network converted over to sna (and also contributed to the internet exceeding the internal network). in this period there was a big explosion in internet nodes from workstations and PCs. SNA was still treating internal network as something that was purely (mainframe) host-to-host ... and the exploding numbers of PCs were to continue to be served by terminal emulation. some past posts http://www.garlic.com/~lynn/subnetwork.html#emulation
cp67 announced 40 yrs ago at spring 68 share in houston
CP67 was announced 40yrs ago at spring 68 share in houston. I was invited to attend. I was undergraduate at univ where the last week of jan68, three people from the science center http://www.garlic.com/~lynn/subtopic.html#545tech had come out to install cp67.
40 yrs of cp67 and cms
The following message is a courtesy copy of an article that has been posted to bit.listserv.vmesa-l,alt.folklore.computers as well. 40 yrs of cp67 and cms ... not quite for the announce, since that happened at the spring '68 share meeting in houston. however, three people had come out from the cambridge science center the last week of jan68 to install cp67 at the univ.
vm folklore, new, 40+ yr old technology
some recent posts in other venues on the new, 40+ yr old technology https://financialcryptography.com/mt/archives/000988.htm http://www.garlic.com/~lynn/aadsm27.htm#66 2007: year in review http://www.garlic.com/~lynn/aadsm28.htm#0 2007: year in review i've only started won on the technology slightly less than 40yrs ago; last week in jan68, three people from the science center had come out and installed cp67 at the univ. for other recent folklore thread ... this is series of posts of the precursor to DCSS work; that was converted from cp67 to vm370 ... but only a small subset was released (as part of DCSS) ... many of the features being eliminated (from DCSS product release), including location independent code (shared segments). some related old email http://www.garlic.com/~lynn/2006v.html#email731212 http://www.garlic.com/~lynn/2006w.html#email750102 http://www.garlic.com/~lynn/2007u.html#81 IBM mainframe history, was Floating-point myths http://www.garlic.com/~lynn/2007v.html#49 IBM mainframe history, was Floating-point myths http://www.garlic.com/~lynn/2007v.html#50 IBM mainframe history, was Floating-point myths http://www.garlic.com/~lynn/2007v.html#51 Education ranking
Re: ongoing rush to the new, 40+ yr old virtual machine technology
The following message is a courtesy copy of an article that has been posted to alt.folklore.computers as well. re: http://www.garlic.com/~lynn/2007s.html#40 ongoing rush to the new, 40+ yr old virtual machine technology IBM Ships 10,000th Storage Virtualization Engine http://www.marketwire.com/mw/release.do?id=793928 from above: IBM has been delivering virtualization capabilities for more than 40 years and today we unveil a milestone in the area of data storage virtualization with the shipment of 10,000 storage virtualization engines -- a fact no other storage company in the world can claim, said Kelly Beavers, Director, Storage Software, IBM. By working across multiple platforms, IBM's storage virtualization helps to lower energy costs and unlocks the proprietary hold that other storage vendors have had on customers for years -- which IBM believes makes storage virtualization the killer application in the storage industry over the next decade. ... snip ... in 1967, the science center: http://www.garlic.com/~lynn/subtopic.html#545tech had moved cp40 to 360/67 for cp67 and also had it installed out at lincoln labs. it wasn't installed at univ. where i was undergraduate (3rd installation) until last week in jan68 ... and it wasn't officially announced until spring share in houston, 1st week mar68. minor reference mentioning 35th anniv of cp67 announce http://www.garlic.com/~lynn/2003d.html#72 cp/67 35th anniversary other recent posts http://www.garlic.com/~lynn/2007s.html#33 Age of IBM VM http://www.garlic.com/~lynn/2007s.html#41 Age of IBM VM other recent news articles: Future Threats to Virtualization Security: Fact vs. Fiction http://www.networkworld.com/news/2007/111407-future-threats-to-virtualization-security.html Virtualization hot; ITIL, IPv6 not, survey says http://www.arnnet.com.au/index.php/id;1522739452;fp;16;fpid;1 A Virtual Conversation http://www.serverwatch.com/trends/article.php/3711431 Oracle's Ellison: Virtualization, Applications, We Got It All http://www.informationweek.com/news/showArticle.jhtml?articleID=203100432 Sun Commits $2 Billion to Virtualization http://news.yahoo.com/s/nf/20071115/bs_nf/56757 Sun Commits $2 Billion to Virtualization http://www.sci-tech-today.com/news/Sun-Commits--2-Billion-to-Virtualization/story.xhtml?story_id=033003ONF579 Sun Introduces Its New Virtualization Offering in San Francisco http://opensource.sys-con.com/read/462102.htm Sun Launches Virtual Assault http://www.byteandswitch.com/document.asp?doc_id=139308WT.svl=news2_1 Sun enters a suddenly crowded virtualization market http://www.betanews.com/article/Sun_enters_a_suddenly_crowded_virtualization_market/1195147886 Push Toward Virtualization Continues, with Two-thirds of Large Organizations Considering It Business-Critical, According to New Research from TheInfoPro http://home.businesswire.com/portal/site/google/index.jsp?ndmViewId=news_viewnewsId=20071115006066newsLang=en VMware refutes Oracle VM performance claims http://searchservervirtualization.techtarget.com/originalContent/0,289142,sid94_gci1282150,00.html Oracle VM Launched http://www.ddj.com/linux-open-source/203100799 VMware Updates Server Software http://www.ddj.com/hpc-high-performance-computing/202805757 Sun's New Virtualization Manager Supports Windows, Linux http://www.eweek.com/article2/0,1895,2217917,00.asp Desktop Virtualization - What's the Best Approach? http://linux.sys-con.com/read/462343.htm Red Hat strategy spans virtualized appliance deployments http://www.moneycontrol.com/india/news/pressnews/red-hat-strategy-spans-virtualizedappliance-deployments/13/25/313286 Sun Commits $2 Billion to Virtualization http://www.sci-tech-today.com/news/Sun-Commits--2-Billion-to-Virtualization/story.xhtml?story_id=1B5YYZEC Microsoft Windows Virtualization Explained - Video with Microsoft's Distinguished Engineer Eric Traut http://www.dabcc.com/article.aspx?id=6404 Sun Introduces Its New Virtualization Offering in San Francisco http://xml.sys-con.com/read/462102.htm Microsoft Wants a Bigger Slice of VMware's Pie http://www.eweek.com/article2/0,1895,2218057,00.asp
Age of IBM VM
The following message is a courtesy copy of an article that has been posted to alt.folklore.computers as well. Marty Zimelis wrote: Bob, Right name, but I believe the wrong derivation. The 67 in CP-67 comes form the fact that it ran on the S/360 model 67, the only production model of the S/360 line that implemented Dynamic Address Translation (DAT) -- virtual storage. Some would argue that was the first version of VM. Others would argue that the line starts with VM/370, the first generally available version of VM, which was first released in August of 1972. (FWIW, SHARE has been celebrating VM's birthdays using the VM/370 release date as the origin. Hence the 35th birthday was celebrated at SHARE 109 in San Diego last Summer.) CP40 predated CP67. Cambridge Science Center had cp67 up and running and had also installed it out at Lincoln Labs. The last week in Jan68, three people came out to install it at the university where I was an undergraduate. I was then invited to attend the spring 68 SHARE meeting in Houston where cp67 was officially announced. In that sense, the univ. was early beta test for cp67. For other topic drift, the univ was also best test site for original CICS ... and I got tasked to support/debug also ... misc. past posts mentioning CICS http://www.garlic.com/~lynn/subtopic.html#bdam I had been doing various work on os360, including a lot of workload throughput optimization. When CP67 was installed, I also started doing some work on it ... and then made a presentation on some of the work at the Aug68 SHARE meeting in Boston. Old post with part of that presentation http://www.garlic.com/~lynn/94.html#18 CP/67 OS MFT14 part of this post I made earlier this yr, has been repeated in this thread http://www.garlic.com/~lynn/2007b.html#21 history question some more recent posts mentioning cp40 (and early virtual machine work) http://www.garlic.com/~lynn/2007p.html#19 zH/OS (z/OS on Hercules for personal use only) http://www.garlic.com/~lynn/2007p.html#69 GETMAIN/FREEMAIN and virtual storage backing up http://www.garlic.com/~lynn/2007q.html#3 Virtualization: Don't Ask, Don't Tell http://www.garlic.com/~lynn/2007r.html#51 Translation of IBM Basic Assembler to C? http://www.garlic.com/~lynn/2007r.html#64 CSA 'above the bar' http://www.garlic.com/~lynn/2007s.html#29 Intel Ships Power-Efficient Penryn CPUs http://www.garlic.com/~lynn/2007s.html#30 Intel Ships Power-Efficient Penryn CPUs The cp67 group split off from the science center and took over the (IBM) Boston Programming Group on the 3rd flr of 545 tech sq; science center was on the 4th flr, science center machine room was on the 2nd flr. http://www.garlic.com/~lynn/subtopic.html#545tech For other trivia, multics was on the 5th flr ... a couple recent refs http://www.garlic.com/~lynn/2007s.html#24 multics source is now open http://www.garlic.com/~lynn/2007s.html#31 multics source is now open In the morph from cp67 to vm370, the group continued to expand, eventually outgrowing the 3rd flr and moved out to the old SBC bldg in Burlington Mall. During this period the company (and some amount of the vm group) got distracted by the Future System effort http://www.garlic.com/~lynn/subtopic.html#futuresys However, I continued to work on various 360 370 things (and also made some less than flattering references about FS). Old email referencing some of that work http://www.garlic.com/~lynn/lhwemail.html#1973 http://www.garlic.com/~lynn/lhwemail.html#1975 When FS was finally killed, there was a mad scramble to get things back into the 370 hardware and software product pipeline. Possibly somewhat as a result, the development group picked up quite a bit of stuff that I had been doing and shipped it in vm370 release 3. Then there was also a decision to release other stuff that I had been doing as the resource manager. Misc. posts http://www.garlic.com/subtopic.html#fairshare It was also in this time-frame that the internal scramble was on to get going on MVS/XA. POK finally convinced the company that it was necessary to kill the vm370 product, shutdown the burlington mall location and transfer all the people to POK as part of being able to meet the MVS/XA delivery schedule. Eventually, Endicott was able to salvage the vm370 product mission ... but effectively had to rebuild an organization nearly from scratch. Somebody from ibm forwarded me this photo from the vm370 b'day event at SHARE 99 http://www.garlic.com/~lynn/LynnWheeler023.jpg 40th anniv. of when I first got acquainted with cp67 is coming up in two months ... and the 40th anniv of cp67 announcement is later next spring. For other drift, 23jan69, the company announced unbundling ... somewhat as the result of various litigation going on. However, the case was made that unbundling and starting to charge separately for software only applied to application software; kernel software still needed to be bundled with the machine (and free). A big part of the
Re: Oracle Introduces Oracle VM As It Leaps Into Virtualization
The following message is a courtesy copy of an article that has been posted to alt.folklore.computers as well. [EMAIL PROTECTED] writes: Could you translate into layman's terms? What exactly is server virtualization software? The concept of virtual storage, as I understand it, is making an application program think it had more core ('RAM') memory than it had by using disk storage for parts of a program not being used at that moment. It's power was limited as trying to compress too much of a program slowed it down significantly. To me, today the concept is almost obsolete since RAM memory is damn cheap, measured in many hundreds of meagabytes. Virtual was developed when memory was still in kilobytes or at best a few megabytes. Anyway, I don't see how the above definition applies today to something like Oracle. How does this new product make it easier and more efficient for data processing centers? Thanks. re: http://www.garlic.com/~lynn/2007s.html#26 Oracle Introduces Oracle VM As It Leaps Into Virtualization http://www.garlic.com/~lynn/2007s.html#27 Oracle Introduces Oracle VM As It Leaps Into Virtualization http://www.garlic.com/~lynn/2007s.html#35 Oracle Introduces Oracle VM As It Leaps Into Virtualization for some topic drift and x-over with this thread http://www.garlic.com/~lynn/2007s.html#33 Age of IBM VM Endicott was working on the follow-on to 135/145 ... virgil/tully ... which had spare room for microcode. There was starting to be mid-range clone processor competition (primarily outside the US) and was looking for new added value features ... in addition to simply better price/performance. They had done a VS1 (kernel) microcode assist and approached the VM group out in burlington about doing a VM370 microcode assist. The VM group turned them down, saying that they were too busy doing other stuff. As a result, they eventually showed up on my doorstep. Old post with some results into initial investigation into selecting portions of vm kernel to drop into mcode: http://www.garlic.com/~lynn/94.html#21 370 ECPS VM microcode assist In addition to the other stuff I was doing in the same timeframe, not only did i get roped into working on design for ECPS VM microcode assist ... Endicott then wanted me to run around the world with them to explain what it all met to the business and forcasting people in different countries around the world. unlike domestic/US, world trade countries would forcast sales for the upcoming year ... which then turned into build orders at manufacturing plants ... which were then bought/delivered to the countries ... which in turn had to be sold to customers (by contrast, domestic forcasts were not directly tied to actual sales volume ... so manufacturing plant sites had to do significant amount of investigation regarding US forcasts since the plant sites would have to eat any inaccuracies). It turns out that 138/148 (virgil/tully) was just on the leading edge of shift from hardware costs dominating customer budgets to change-over to people costs starting to dominate (and skill availability representing bottleneck to customer installs). As a result, Endicott pushed hard for having VM370 preinstalled and transparently integrated into every 138/148 shipped from the factory (slightly akin to LPARS in the current generation of mainframes). The problem was that large portions of the corporation viewed vm370 as competitive with other operating system offerings and for one reason or another were out to kill the product. Having vm370 preinstalled and transparently integrated into every 138/148 shipped ran counter to this other political forces (for instance POK was in the process of making the case for killing off vm370 and having all the people in the burlington mall group transferred to pok as part of helping mvs/xa schedules). In any case, the vm370 preinstall and transparently integrated for every 138/148 was shot down. As i've posted before, the mid-range product sales really accelerated with the 138/148 followin ... 43xx machines (as well as vax machines). past posts mentioning the departmental server phenonama for 43xx (and vax) machines (43xx had some edge over vax with some large commercial customers placing 43xx machine orders in multiples of hundreds). a few recent posts http://www.garlic.com/~lynn/2007b.html#51 Special characters in passwords was Re: RACF - Password rules http://www.garlic.com/~lynn/2007j.html#7 Newbie question on table design http://www.garlic.com/~lynn/2007m.html#72 The Development of the Vital IBM PC in Spite of the Corporate Culture of IBM http://www.garlic.com/~lynn/2007n.html#18 The Development of the Vital IBM PC in Spite of the Corporate Culture of IBM http://www.garlic.com/~lynn/2007n.html#20 The Development of the Vital IBM PC in Spite of the Corporate Culture of IBM http://www.garlic.com/~lynn/2007n.html#21 The Development of the Vital IBM PC in Spite of the Corporate Culture of IBM
Re: Age of IBM VM
The following message is a courtesy copy of an article that has been posted to alt.folklore.computers as well. re: http://www.garlic.com/~lynn/2007s.html#33 Age of IBM VM http://www.garlic.com/~lynn/2007s.html#36 Oracle Introduces Oracle VM As It Leaps Into Virtualization one could claim that the relationship of cp67 to vm370 is somewhat like the relationship of HASP to JES2. misc past posts mentioning HASP, JES2, and/or JES2/HASP networking support http://www.garlic.com/~lynn/subtopic.html#hasp other cp67 heritage ... in the transition from MVT to os/vs2 (i.e. os/360 with virtual memory support) ... basically MVT was laid out in single virtual address space ... thus the reference to OS/VS2 SVS (single virtual storage) to distinquish from later OS/VS2 release MVS (multiple virtual storage). One might claim that there was little difference between OS/VS2 SVS and MVT with VM handshaking laid out in 16mbyte virtual address space. The biggest difference was needed to have channel program translation built into MVT. The initial prototypes of OS/VS2 SVS was built with minimal virtual address space support and a copy of CP67 CCWTRANS (and a couple other CP67 routines associated with channel program translation) hacked into the side. misc. recent posts discussing channel program translation and specifically getting os/vs2 to support it http://www.garlic.com/~lynn/2007e.html#19 Cycles per ASM instruction http://www.garlic.com/~lynn/2007e.html#27 IBM S/360 series operating systems history http://www.garlic.com/~lynn/2007e.html#46 FBA rant http://www.garlic.com/~lynn/2007f.html#0 FBA rant http://www.garlic.com/~lynn/2007f.html#6 IBM S/360 series operating systems history http://www.garlic.com/~lynn/2007f.html#33 Historical curiosity question http://www.garlic.com/~lynn/2007f.html#34 Historical curiosity question http://www.garlic.com/~lynn/2007k.html#26 user level TCP implementation http://www.garlic.com/~lynn/2007n.html#35 IBM obsoleting mainframe hardware http://www.garlic.com/~lynn/2007o.html#37 Each CPU usage http://www.garlic.com/~lynn/2007o.html#41 Virtual Storage implementation http://www.garlic.com/~lynn/2007p.html#69 GETMAIN/FREEMAIN and virtual storage backing up http://www.garlic.com/~lynn/2007p.html#70 GETMAIN/FREEMAIN and virtual storage backing up http://www.garlic.com/~lynn/2007p.html#72 A question for the Wheelers - Diagnose instruction http://www.garlic.com/~lynn/2007q.html#8 GETMAIN/FREEMAIN and virtual storage backing up http://www.garlic.com/~lynn/2007r.html#56 CSA 'above the bar' http://www.garlic.com/~lynn/2007s.html#2 Real storage usage - a quick question http://www.garlic.com/~lynn/2007s.html#9 Poster of computer hardware events? there was other technology from the science center http://www.garlic.com/~lynn/subtopic.html#545tech used in lots of transition to operating in virtual memory environment for 370. the science center had a number of efforts going on in the area of system and performance monitoring, modeling, and simulation (some of it being the runup to capacity planning). one of the projects involved tracing instruction and data storage references and then doing semi-automated program reorganization to optimize for operation in virtual memory environment. This was used for several yrs internally before being turned into product and released to customers as VS/REPACK (two moments before my vm370 resource manager was first released). An early version of the technology was used to help in the morph of apl\360 to cms\apl (originally on cp67/cms) ... which required completely redoing the apl storage allocation and garbage collection implementation for operation in virtual memory environment. vs/repack was also used by a number of product groups ... not only for helping with transition from real storage to virtual memory environment ... but also for things like application hot spot identification (i.e. where program is spending a lot of its time). For instance it was used in STL by the IMS development group for extensive studies of IMS operation and performance. misc. recent posts mentioning VS/REPACK http://www.garlic.com/~lynn/2007g.html#31 Wylbur and Paging http://www.garlic.com/~lynn/2007m.html#55 Capacity and Relational Database http://www.garlic.com/~lynn/2007o.html#53 Virtual Storage implementation http://www.garlic.com/~lynn/2007o.html#57 ACP/TPF another tool was an system performance analytical model implemented in APL which was eventually made available as sales and marketing support tool on (internal cms-based timesharing service) HONE http://www.garlic.com/~lynn/subtopic.html#hone as the performance predictor. branch people could input customer configuration and workload details and ask what-if questions about what would happen if there were configuration and/or workload changes. misc. past posts mentioning performance predictor http://www.garlic.com/~lynn/2001i.html#46 Withdrawal Announcement 901-218 - No More 'small machines'
Oracle Introduces Oracle VM As It Leaps Into Virtualization
for something a little different ... also posted here http://www.garlic.com/~lynn/2007s.html#26 latest in the new, 40+ yr old technology Oracle Introduces Oracle VM As It Leaps Into Virtualization http://www.informationweek.com/news/showArticle.jhtml?articleID=202805289 couple items from above: Oracle jumped into the virtualization market Monday, announcing Oracle VM, or server virtualization software to run Oracle databases and applications. ... Oracle will supply preconfigured images -- or virtualized files that combine the Oracle database with a preconfigured version of Linux -- for ease of installation and deployment. The move is Oracle's way of picking up on the use of virtualized appliances, software preconfigured with an operating system to run in a virtual machine. ... snip ... possibly another take on commodization (leaving more on the table for the product vendor?) mentioned here http://www.garlic.com/~lynn/2007s.html#20 Ellison Looks Back As Oracle Turns 30 ... effectively another kind of virtual appliance or what we started out calling server virtual machine ... misc. past posts http://www.garlic.com/~lynn/2007i.html#36 John W. Backus, 82, Fortran developer, dies http://www.garlic.com/~lynn/2007k.html#26 user level TCP implementation http://www.garlic.com/~lynn/2007k.html#48 John W. Backus, 82, Fortran developer, dies http://www.garlic.com/~lynn/2007m.html#67 Operating systems are old and busted http://www.garlic.com/~lynn/2007m.html#70 Is Parallel Programming Just Too Hard? http://www.garlic.com/~lynn/2007o.html#3 Hypervisors May Replace Operating Systems As King Of The Data Center http://www.garlic.com/~lynn/2007q.html#25 VMware: New King Of The Data Center? http://www.garlic.com/~lynn/2007s.html#4 Why do we think virtualization is new?
Re: Combining VM list threads
Gabe Goldberg wrote: There's SET SHARE RELATIVE and VM's 35 Birthday Celebration and 2007 Knights of VM and SHARE: Final chairbears needed (ribbon wearer time!!) in which phsiii said So bring your family...I am! I guess he's SET SHARE RELATIVE. So should anyone using family vacation as excuse to not be there to chair sessions, hmmm? post w/mention of 35th anniv. of cp67 announce (houston, spring '68 share meeting) http://www.garlic.com/~lynn/2003d.html#72 some people from CSC had come out the last week of jan68 to install cp67 at the univ. where i was undergraduate. i was then invited to attend the cp67 announce at the spring '68 houston share meeting. next spring will be 40th. and photo from vm370 30th b'day party at share 99 http://www.garlic.com/~lynn/LynnWheeler023.jpg
Re: z/VM usability
Alan Altmark wrote: Well, it's been nigh on 40 years that CMS has been around. Seems like a committment to me. CMS is here to stay. If all the people with z/OS get z/VM and [re]discover CMS, who knows what might happen? Never say die! re: http://www.garlic.com/~lynn/2007j.html#41 z/VM usability well, cms (as in cambridge monitor system) started on cp40 (cambridge had gotten a 360/40 and did the hardware modifications to implement virtual memory ... pending getting 360/67) ... cambridge then got 360/67 and morphed cp40 into cp67 ... so it has been 40yrs (in part, CMS work could even start on real 360/40 before cp40 was operational) from Melinda's history http://www.princeton.edu/~melinda/ By September of 1965, file system commands and macros already looked much like those we are familiar with today: ``RDBUF'', ``WRBUF'', ``FINIS'', ``STATE'', etc ... snip ... cambridge installed cp67 out at lincoln labs in 1967 and then last week in jan68 came out to install cp67 at the univ where i was undergraduate. Note, that in jan68, the cp67 people were still apprehensive about CMS filesystem ... with cp67 source, assemble, and build still being done on os/360 (keeping cp67 kernel build TXT files in card tray and modify/assemble routine, punch new TXT file, update that file in the card tray and rebuild kernel by doing IPL of real cards). in the morph of cp67 to vm370 ... they changed the cms name to conversational monitor system. major change in cms from cp67 to vm370 was a little re-arranging of cms kernel in anticipation of 370 (r/o) segment protection. However, in doing the virtual memory hardware retrofit to 370/165 ... they ran into problem with schedule slipping. In order to regain six months in the schedule for 370/165 virtual memory, they dropped r/o segment protect and some number of other features from the original 370 virtual memory architecture (and to have compatibility across the 370 product line ... the same features had to also be removed from other 370 models that already had implemented the full 370 virtual memory architecture). With 370 hardware r/o segment protect dropped ... vm370 had to revert to the page protect hack used by cp67 that involved fiddling the 360 storage protect keys. Then during the future system period ... much of the corporation was distracted and a lot of 370 product activity fell by the way side. Misc. past posts about future system: http://www.garlic.com/~lynn/subtopic.html#futuresys I had made some unflattering comments about practicallity of future system stuff and continued to do both cp67 and cms enhancements ... and then ported them from cp67 to vm370 ... some old email http://www.garlic.com/~lynn/2006v.html#email731212 http://www.garlic.com/~lynn/2006w.html#email750102 http://www.garlic.com/~lynn/2006w.html#email750430 after FS was canceled, there was rush to get stuff back into 370 product pipeline. Part of this was reason that small subset of the virtual memory management enhancements ... a lot of shared segment stuff http://www.garlic.com/~lynn/subtopic.html#adcon that had been integrated with the paged mapped filesystem stuff http://www.garlic.com/~lynn/subtopic.html#mmap was released as DCSS in vm370 release 3. Canceling FS contributed to enabling me to also release the resource manager (that included a lot of changes that were in cp67 that i had done ... which were dropped in the morph from cp67 to vm370) http://www.garlic.com/~lynn/subtopic.html#fairshare http://www.garlic.com/~lynn/subtopic.html#wsclock It was also in the aftermath of killing FS that POK convinced the corporation to kill the vm370 product, shutdown the vm370 product group and move all the people to POK to help accelerate the mvs/xa development schedule (again attempting to make up lost time in 370 product pipeline resulting from the FS distraction). Eventually Endicott was able to salvage the vm370 product mission.
Does anyone know of a documented case of VM being penetrated by hackers?
The following message is a courtesy copy of an article that has been posted to bit.listserv.vmesa-l,alt.folklore.computers as well. George Haddad wrote: The last major hole I can recall was in the late 80s or early 90s IIRC, where it was discovered that when sending an SMSG to an SVM (I think it was RSCS) which included a CP command, the the SVM would blindly execute multiple CP commands if they were chained with CP Newline character. If the SVM had any special privs ...well you get the idea. It was patched very quickly. re: http://www.garlic.com/~lynn/2007i.html#20 Does anyone know of a documented case of VM being penetrated by hackers? http://www.garlic.com/~lynn/2007i.html#29 Does anyone know of a documented case of VM being penetrated by hackers? should have been mid-70s ... not late 80s ... at least on the internal network http://www.garlic.com/~lynn/subnetwork.html#internalnet from long ago and far away ... To: wheeler Date: 80/12/16 10:52:11 I never came back last night, but I did speak to XX about that file. He points out that RSCS probably translates a pound sign to a question mark for display (to eliminate problems with embedded commands in messages, which caused some difficulty a few years ago). So the file is probably ok; perhaps you can check with X and find out. By the way, what I did last night was to tune my oil burner. I don't know how you people out there heat (on the 3 days a year when the temperature gets below 68), but if you have an oil burner (even just for hot water), you ought to look into doing a tune-up on it. The lab here has a kit we can borrow for the purpose, and in less than an hour I got the efficiency from 60% to about 74%. ... snip ... and now for some networking thing completely different from the late 80s To: wheeler From: somebody in corporate hdqtrs Date: 7 May 1987, 19:35:58 EDT Subject: Large Files... Lynn: We are getting requests to handle 500MB files.. EC releases, Chip Designs, software, and documentation... (one group has a 3BB file requirement!!).. Altho' the 500MB req't is coming within the next few months... Have you done any thinking during your HSDT work.. on what the limits might be on large files.. compared to our networking software and communication link capacity...??? I'm thinking that there must be a limit... or a knee on the curve which says.. use a courier service.. rather than the network... Have you been able to develop any attributes, characteristics, etc.. on 'large files'...that could be helpful to planning and operating with these large files...?? ... snip ... i.e. HSDT (high-speed data transport) was working with handling large files ... recent post referencing helping contribute to bringing in the RIOS chipset a year early http://www.garlic.com/~lynn/2007f.html#73 Is computer history taught now? http://www.garlic.com/~lynn/2007h.html#61 Fast and Safe C Strings: User friendly C macros to Declare and use C Strings misc. posts mentioning HSDT activities ... dating back to 1980 time-frame http://www.garlic.com/~lynn/subnetwork.html#hsdt as well as some activity working with various people at univ. and NSF ... old email: http://www.garlic.com/~lynn/lhwemail.html#nsfnet and misc. postings mentioning BITNET and/or EARN http:/www.garlic.com/~lynn/subnetwork.html#bitnet
Re: Does anyone know of a documented case of VM being penetrated by hackers?
The following message is a courtesy copy of an article that has been posted to bit.listserv.vmesa-l,alt.folklore.computers as well. re: http://www.garlic.com/~lynn/2007i.html#20 Does anyone know of a documented case of VM being penetrated by hackers? for a little topic drift ... a little about virtual machine assurance in recent post to ibm-main http://www.garlic.com/~lynn/2007i.html#26 Latest Principles of Operation
Re: Historical curiosity question
Rob van der Heij wrote The mini disk is an imperfect (but cheap) implementation of a low level abstraction. The main defect is the number of cylinders, but for many purposes the virtualization is good enough because the guest can live with that. But at considerable additional cost, VM could have been designed to span a mini disk over multiple volumes. With such support, you could give out more perfect 3390's (i.e. not being restricted by the actual models on the hardware). And VM could have played tricks not to allocate real disk space for unused tracks. This is exactly what was done in the RAMAC Virtual Array. re: http://www.garlic.com/~lynn/2007f.html#20 Historical curiosity question some long winded topic drift ... as undergraduate i had done a lot of modifications to the cp67 kernel ... a lot oriented towards significantly improving pathlength for os360 guest virtual machines, new resource management algorithms, and dynamic adaptive resource control. I had also looked at doing some stuff for CMS ... one of the things I realized that CMS was simulating the operation of doing syncronous disk transfers with overhead of sio/lpsw-wait/interrupt paradigm. so i defined a new CCW opcode that would do syncronous disk transfers ... and the virtual machine would get back CC=1, csw stored on the SIO operation ... indicating the operation had already completed. This i got somewhat slammed on by the people at the science center as having violated 360 machine architecture and principles of operation. Eventually it was explained that it would be possible to use the 360 DIAGNOSE instruction to implement such violations ... since the principles of operation defined the DIAGNOSE instruction implementation as model dependent. Define an abstract 360/virtual machine model and the way that the DIAGNOSE instruction work for that model. However, the pathlength improvement for the change was pretty significant ... so the syncronous disk transfer operation was eventually re-implemented with DIAGNOSE instruction. Later when I joined the science center ... one of the things that i did for cp67/cms (that never shipped in the product) was the cp67 and cms changes to support page-mapped filesystem operation. This was combined in general set of stuff that I referred to as virtual memory management. Later it was some of the stuff that was ported to vm370 ... old communication with reference http://www.garlic.com/~lynn/2006v.html#email731212 a small subset of the virtual memory management stuff made it out in vm370 as DCSS (but not the page mapped filesystem stuff or a lot of other stuff) ... recent post http://www.garlic.com/~lynn/2007f.html#14 more shared segment archeology Note that even with the DIAGNOSE operation there was still a lot of overhead related to emulated channel programs that require real addresses for execution (shadows of the virtual channel program created with real addresses of the virtual pages which have been pinned in real storage). This is not only true for virtual machine emulation ... but anything that has applications building channel programs in a virtual address space. For reference, posts about originaly prototype OS/360 to VS2 virtual memory operation by hacking a copy of cp67's CCWTRANS into the side of MVT (to create translated, shadow channel programs with real address and pinned virtual pages) http://www.garlic.com/~lynn/2007e.html#19 Cycles per ASM instruction http://www.garlic.com/~lynn/2007e.html#27 IBM S/360 series operating systems history http://www.garlic.com/~lynn/2007e.html#46 FBA rant http://www.garlic.com/~lynn/2007f.html#0 FBA rant http://www.garlic.com/~lynn/2007f.html#6 IBM S/360 series operating systems history so the page mapped filesystem support, changes to both cp67 to provide the DIAGNOSE instruction API) and changes to low-level CMS filesystem function to use the cp67 API (pretty much leaving the high-level CMS filesystem interfaces as-is) ... eliminated most of the rest of this channel program translation overhead gorp. It also moved the CMS disk paradigm interface even beyond the simplifications possible with FBA disks. Having drastically simplified the disk paradigm interface ... the implementation of a lot of other features became significantly easier. For instance, it was possible to dynamically adjust how requested page transfers were actually performed being able to dynamically do either syncronous transfers and/or even asyncronous transfers (transparent to the syncronous CMS virtual machine paradigm by fiddling the page invalid bits). The simple, original implementation just mapped a set of contiguous page records ... to contiguous cylinders supported leveraging existing minidisk definitions. However, it also become extremely straight-forward to do other types of enhancements (having removed the binding for the cms virtual machine to explicit ckd disk hardware characteristics), like having multiple sequentially chained blocks of pages ... at
Re: Historical curiosity question
McKown, John wrote: This is not important, but I just have to ask this. Does anybody know why the original designers of VM did not do something for minidisks akin to a OS/360 VTOC? Actually, it would be more akin to a partition table on a PC disk. It just seems that it would be easier to maintain if there was something on the physical disk which contained information about the minidisks on it. Perhaps with information such as: start cylinder, end cylinder, owning guest, read password, etc. CP owned volumes have an allocation map, this seems to me to be an extention of that concept. CP67 had a global directory ... that was indexed and paged ... so it didn't need individual volume index. it also avoided the horrendous overhead of multi-track search that os/360 used to search the volume VTOC on every open. lots of past posts mentioning multi-tract paradigm for VTOC PDS directory was io/memory trade-off ... os/360 target in the mid-60s was to burn enormous i/o capacity to save having in-memory index. http://www.garlic.com/~lynn/subtopic.html#dasd that resource trade-off had changed by at least the mid-70s ... and it wasn't ever true for the machine configurations that cp67 ran on. the other characteristic was that both cp67 and cms treated disks as fixed-block architecture ... even if they were CKD ... CKD disks would be formated into fixed-blocks ... and then treated as fixed-block devices ... and avoid the horrible i/o performance penalty of ever doing multi-track searches for looking up location and/or other information on disk. recent thread in bit.listserv.ibm-main http://www.garlic.com/~lynn/2007e.html#35 FBA rant http://www.garlic.com/~lynn/2007e.html#38 FBA rant http://www.garlic.com/~lynn/2007e.html#39 FBA rant http://www.garlic.com/~lynn/2007e.html#40 FBA rant http://www.garlic.com/~lynn/2007e.html#42 FBA rant http://www.garlic.com/~lynn/2007e.html#43 FBA rant http://www.garlic.com/~lynn/2007e.html#46 FBA rant http://www.garlic.com/~lynn/2007e.html#51 FBA rant http://www.garlic.com/~lynn/2007e.html#59 FBA rant http://www.garlic.com/~lynn/2007e.html#60 FBA rant http://www.garlic.com/~lynn/2007e.html#63 FBA rant http://www.garlic.com/~lynn/2007e.html#64 FBA rant http://www.garlic.com/~lynn/2007f.html#0 FBA rant http://www.garlic.com/~lynn/2007f.html#2 FBA rant http://www.garlic.com/~lynn/2007f.html#3 FBA rant http://www.garlic.com/~lynn/2007f.html#5 FBA rant http://www.garlic.com/~lynn/2007f.html#12 FBA rant the one possible exception was loosely-coupled single-system-image support done for HONE system. HONE mini-disk volumes had an in-use bitmap directory on each volume ... that was used to manage LINK consistency across all machines in the cluster. it basically used a channel program with search operation to implement i/o logical equivalent to the atomic compareswap instruction ... avoiding having to do reserve/release with intervening i/o operations. I have some recollection talking to the JES2 people about them trying a similar strategy for multi-system JES2 spool allocation. post from above mentioning HONE compareswap channel program for multi-system cluster operation http://www.garlic.com/~lynn/2007e.html#38 FBA rant HONE was vm-based online interactive for world-wide sales, marketing, and field people. It originally started in the early 70s with a clone of the science center's cp67 system http://www.garlic.com/~lynn/subtopic.html#545tech and eventually propogated to several regional US datacenters ... and also started to propogate overseas. I provided highly modified cp67 and then later vm370 systems for HONE operation for something like 15 yrs. I also handled some of the overseas clones ... like when EMEA hdqtrs moved from the states to just outside paris in the early 70s. In the mid-70s, the US HONE datacenters were consolidated in northern cal. ... and single-system-image software support quickly emerge ... running multiple attached processors in cluster operation. HONE applications were heavily APL ... so it was quite compute intensive. With four-channel controllers and string-switch ... you could get eight system paths to every disk. Going with attached processors ... effectively two processors made use of a single set of channels ... so you could get 16 processors in single-system-image ... with load-balancing and failure-fallover-recovery. Later in the early 80s, the northern cal. HONE datacenter was replicated first in Dallas and then a third center in Boulder ... for triple redundancy, load-balancing and fall-over (in part concern about natural disasters like earthquakes). lots of past posts mentioning HONE http://www.garlic.com/~lynn/subtopic.html#hone At one point in SJR after the 370/195 machine ... recent reference http://www.garlic.com/~lynn/2007f.html#10 Beyond multicore http://www.garlic.com/~lynn/2007f.html#11 Is computer history taught now? http://www.garlic.com/~lynn/2007f.html#12 FBA rant was replaced with mvs/168 system ... and vm was running on
more shared segment archeology
One of the reasons the vm development group picked up so much from the science center http://www.garlic.com/~lynn/subtopic.html#545tech to ship in the (vm370 product) release 3/4 time-frame was a lot of the resources had been diverted to FS ... similar to the reference in this post http://www.garlic.com/~lynn/2007f.html#10 Beyond multicore in this old email http://www.garlic.com/~lynn/2007f.html#email800117 and some followup to the above http://www.garlic.com/~lynn/2007f.html#11 Is computer history taught now? http://www.garlic.com/~lynn/2007f.html#12 FBA rant and lots of past posts mentioning future system project http://www.garlic.com/~lynn/subtopic.html#futuresys and then there was a relatively short window between the demise of FS (and return of the diverted resources) and when POK convinced corporate to completely shutdown VM and move all the people to POK to support MVS/XA development ... as part of trying to get MVS/XA out the door (everybody was scrambling to make up for lost time because of FS). The reference in this post to POK convincing corporate about VM shutdown and all the people diverted to MVS/XA (and Endicott salvaging some of the VM mission) ... glosses over the period with lots of resources diverted to work on FS http://www.garlic.com/~lynn/2007f.html#7 IBM S/360 series operating systems history In addition to development group having to play catch-up (by picking up stuff from the science center for product ship; because of period when a lot of resources were diverted to FS), there were also some amount of stuff that had been dropped in the morph from cp67 to vm370. I continued to work on cp67 during this period and then when the science center got a 370/155-II ... ported a bunch of stuff to vm370. Old communication from 1973 about porting/enhancing a bunch of science center stuff from cp67 to vm370 http://www.garlic.com/~lynn/2006v.html#email731212 in this post http://www.garlic.com/~lynn/2006v.html#36 Why these original FORTRAN quirks? and related email from 1975 ... creating an enhanced vm rel2 system for shipment to internal accounts: http://www.garlic.com/~lynn/2006w.html#email750102 in this post http://www.garlic.com/~lynn/2006w.html#7 Why these original FORTRAN quirks? and http://www.garlic.com/~lynn/2006w.html#email750430 in this post http://www.garlic.com/~lynn/2006w.html#8 Why these original FORTRAN quirks? One of the items was whole restructuring for what I called virtual memory management ... which included a bunch of bells and whistles related to virtual memory segments as well as being integrated with page mapped filesystem changes for CMS. Much of the internal restructuring for handling virtual memory segments was picked up as part of release 3 DCSS ... however only a small subset of the function that utilized that restructuring was actually shipped as part of release 3 DCSS. I had also gotten roped into doing a lot of the ECPS work for Endicott, old reference here http://www.garlic.com/~lynn/94.html#21 370 ECPS VM microcode assist http://www.garlic.com/~lynn/94.html#27 370 ECPS VM microcode assist http://www.garlic.com/~lynn/94.html#28 370 ECPS VM microcode assist and at the same time various SMP work ... old VAMPS email from 1975 http://www.garlic.com/~lynn/2006w.html#email750827 in this post http://www.garlic.com/~lynn/2006w.html#10 long ago and far away, vm370 from early/mid 70s lots of other posts mentioning VAMPS (5-way SMP project) http://www.garlic.com/~lynn/subtopic.html#bounce and lots of posts making general mention of SMP and/or compareswap instruction http://www.garlic.com/~lynn/subtopic.html#smp Another shared segment feature was a line item called DWSS that was part of system/r technology transfer from SJR to Encidott for SQL/DS product ... which allowed for shared segments that were writable (i.e. not r/o protected). A big issue with DWSS was what to do about ECPS microcode already in the field that supported r/o protection games for all segments identified as shared. This was another downstream fall-outs of letting the 165 hardware engineers gain six months in the vritual memory hardware change schedule for 165-ii ... by letting them drop various features from the 370 virtual memory architecture. recent references http://www.garlic.com/~lynn/2007f.html#6 IBM S/360 series operating systems history One of the features dropped was the hardware segment table protection bit ... which allowed specification of hardware r/o protection for virtual memory segments on a virtual address space basis (i.e. some address spaces could be allowed r/w segment storage operation while other address spaces were not allowed to change the same shared segment). This also caused a big retrofit hit to vm370 since cpcms had already been re-organized to take advantage of the feature ... when it was dropped ... a real cludge was created ... also referenced here http://www.garlic.com/~lynn/2007d.html#32 Running OS/390 on z9 BC effectively the original basis
I/O in Emulated Mainframes
oft repeated story about mainframe emulation and I/O with regard to 370/158 and integrated channels; most recent telling http://www.garlic.com/~lynn/2007d.html#62 Cycles per ASM instruction basically the 158 microcode engine had both microcode for emulating 370 and also for emulating channels. in the transition to 303x machines ... the (158) integrated channel microcode was split-off into a dedicated box called the channel director. A 3031 was basically two 158 microcode engines, one with a dedicated engine for running integrated channel microcode and the other engine dedicated to running the 370 emulation microcode (potentially could be considered a two-processor SMP ... which would make a 3031 SMP ... actually four processor system ... since each emulated 370 engine had its corresponding channel director). A 3032 was a repackaged 370/168 with one or more (158 microcode engine integrated channel) channel directors. A 3033 was 168 wiring diagram mapped to fast chip technology ... along with one or more (158 microcode engine integrated channel) channel directors ... i.e. 158 integrated channels supported 6 channels ... to get a 16 channel configuration, you needed three channel directors. A two processor 3033 SMP ... was actually typically an eight processor system ... two 3033 processor with each processor (typically) having three channel directors. note that splitting off the integrated channel microcode into dedicated processor made the 3031 benchmarks better than 370/158 (even tho the microprocessor engines were the same) ... with 3031 benchmarking almost as fast as 4341 ... the above URL reference also contains results of RAIN benchmark on 158, 3031 and early 4341 engineering machine (ran about 10-15 percent slower than production machines shipped to customers). similarly, 370 115/125 had a memory bus that provided 9 slots for up to nine processors. A 115 had a microcode engine running dedicated 370 microcode emulation ... and up to eight other (identical) processors running other microcode loads (communication controller microcode load, disk controller microcode load, etc). A 125 was identical to 115 except the processor engine running 370 microcode emulation was 50percent faster than the other processor engines. recent posts with discussion of 370 115/125 http://www.garlic.com/~lynn/2007d.html#71 Cycles per ASM instruction http://www.garlic.com/~lynn/2007d.html#72 IBM S/360 series operating systems history lots of past posts referring to 303x channel director being dedicated 158 microcode engine with integrated channel microcode from 370/158 http://www.garlic.com/~lynn/97.html#20 Why Mainframes? http://www.garlic.com/~lynn/98.html#23 Fear of Multiprocessing? http://www.garlic.com/~lynn/99.html#7 IBM S/360 http://www.garlic.com/~lynn/99.html#176 S/360 history http://www.garlic.com/~lynn/99.html#187 Merced Processor Support at it again http://www.garlic.com/~lynn/2000.html#78 Mainframe operating systems http://www.garlic.com/~lynn/2000c.html#69 Does the word mainframe still have a meaning? http://www.garlic.com/~lynn/2000d.html#7 4341 was Is a VAX a mainframe? http://www.garlic.com/~lynn/2000d.html#11 4341 was Is a VAX a mainframe? http://www.garlic.com/~lynn/2000d.html#12 4341 was Is a VAX a mainframe? http://www.garlic.com/~lynn/2000d.html#21 S/360 development burnout? http://www.garlic.com/~lynn/2000g.html#11 360/370 instruction cycle time http://www.garlic.com/~lynn/2001b.html#83 Z/90, S/390, 370/ESA (slightly off topic) http://www.garlic.com/~lynn/2001c.html#3 Z/90, S/390, 370/ESA (slightly off topic) http://www.garlic.com/~lynn/2001c.html#6 OS/360 (was LINUS for S/390) http://www.garlic.com/~lynn/2001i.html#34 IBM OS Timeline? http://www.garlic.com/~lynn/2001j.html#3 YKYGOW... http://www.garlic.com/~lynn/2001j.html#14 Parity - why even or odd (was Re: Load Locked (was: IA64 running out of steam)) http://www.garlic.com/~lynn/2001l.html#24 mainframe question http://www.garlic.com/~lynn/2001l.html#32 mainframe question http://www.garlic.com/~lynn/2002.html#36 a.f.c history checkup... (was What specifications will the standard year 2001 PC have?) http://www.garlic.com/~lynn/2002.html#48 Microcode? http://www.garlic.com/~lynn/2002d.html#7 IBM Mainframe at home http://www.garlic.com/~lynn/2002f.html#8 Is AMD doing an Intel? http://www.garlic.com/~lynn/2002i.html#19 CDC6600 - just how powerful a machine was it? http://www.garlic.com/~lynn/2002i.html#21 CDC6600 - just how powerful a machine was it? http://www.garlic.com/~lynn/2002i.html#23 CDC6600 - just how powerful a machine was it? http://www.garlic.com/~lynn/2002n.html#58 IBM S/370-168, 195, and 3033 http://www.garlic.com/~lynn/2002p.html#59 AMP vs SMP http://www.garlic.com/~lynn/2003.html#39 Flex Question http://www.garlic.com/~lynn/2003g.html#22 303x, idals, dat, disk head settle, and other rambling folklore http://www.garlic.com/~lynn/2003g.html#32 One Processor is bad? http://www.garlic.com/~lynn/2003m.html#31 SR
Re: The Future of CPUs: What's After Multi-Core?
Brian Inglis [EMAIL PROTECTED] writes: IME the IBM VM guys had very good ideas for interaction using the corporate products and facilities, even though it has never been funded adequately and often nearly terminated. They were much better than the batch guys at letting the users fully use all the machines' capabilities, providing nearly 100% capacity and keeping terminal response averages close to 0.1s; the batch guys were better at using up all the machines' capabilities, and the users considered themselves lucky to have 70% capacity available and get 1s terminal response times. The really cool thing about VM systems is that you can do anything with the software under timesharing: develop a new OS, test a changed OS, trace the execution of an OS. Once found a bug crashing a DB product only after tracing about a million instructions, a few times over to get it exactly right, with very selective output, sufficient to pinpoint the faulty code: try doing that on a real front panel or console! for some total drift ... a different reference to tracing in support of semi-automated program reorganization to optimize execution for virtual memory environment http://www.garlic.com/~lynn/2006x.html#1 IBM sues make of Intel-based Mainframe clones as an undergraduate in the 60s, i had done dynamic adaptive resource management ... it was sometimes referred to as fair share scheduling since the default resource management policy was fair share. this was shipped as part cp67 for 360/67. in the morph from cp67 to vm370 ... much of it was dropped. charlie's cp67 multiprocessor support also didn't make it into vm370. i had done a lot of pathlength optimization and fastpath stuff for cp67 which was also dropped in the morph to vm370 ... i helped put a small amount of that back into vm370 release1 plc9 ... a couple past posts mentioning some of the cp67 pathlength stuff http://www.garlic.com/~lynn/93.html#1 360/67, was Re: IBM's Project F/S ? http://www.garlic.com/~lynn/94.html#18 CP/67 OS MFT14 http://www.garlic.com/~lynn/94.html#20 CP/67 OS MFT14 i then got to work on porting a bunch of stuff that i had done for cp67 to vm370 ... some recent posts (includes old email from the early and mid 70s) http://www.garlic.com/~lynn/2006v.html#36 Why these original FORTRAN quirks? http://www.garlic.com/~lynn/2006w.html#7 Why these original FORTRAN quirks? http://www.garlic.com/~lynn/2006w.html#8 Why these original FORTRAN quirks? http://www.garlic.com/~lynn/2006w.html#10 long ago and far away, vm370 from early/mid 70s and of course mentioned in the above referenced email ... a small amount of the virtual memory management stuff showed up in vm370 release 3 as DCSS. there was eventually a decision to release some amount of the features as the vm370 resource manager. some collected posts on scheduling http://www.garlic.com/~lynn/subtopic.html#fairshare and other posts on page management http://www.garlic.com/~lynn/subtopic.html#wsclock and for something really different old communication (from 1982) about work i had done as undergraduate in the 60s (also in this thread): http://www.garlic.com/~lynn/2006w.html#46 The Future of CPUs: What's after Multi-Core? in any case, some resources manager issues/features * by continually doing real time dynamical monitoring and adjusting operations, I was able to operate at much higher resource utilization and still provide decent level of service. prior to resource manager ship, somebody from corporate stated that the current state of the art for resource managers were large number of static tuning parameters and that the resource manager couldn't be considered really advanced unless it had some number of static tuning parameters (installation system tuning expert would look at daily, weekly and monthly activity ... and would select some set of static tuning values that seemed to be suited to that installation). it did absolutely no good explaining that real-time dynamic monitoring and adapting was much more advanced that static tuning parameters. so, in order to get final corporate release approval ... i had to implement some number of static tuning parameters. I fully documented the implementation and formulas and the source code was readily available. Nobody seemed to realize that it was a joke ... somewhat from operations research ... it had to do with degrees of freedom ... aka the static tuning parameters had much less degrees of freedom than the dynamic adaptive features. i had always thot that real-time dynamic adaptive control was preferable to static parameters ... but it took another couple decades for a lot of the rest of the operating systems to catch up. it is now fairly evident ... even showing up in all sorts of embedded processors for real-time control and optimization. for some slight boyd dynamic adaptive drift http://www.garlic.com/~lynn/94.html#8 scheduling dynamic adaptive and collected posts mentioning boyd
intersection between autolog command and cmsback (more history)
Another CMSBACK status, a year later than the email referenced here http://www.garlic.com/~lynn/2006t.html#24 CMSBACK i.e. i had done the original CMSBACK implementation and deployment in the late 70s on sjr systems and hone ... the following refers to there additional systems where it was installed: To: distribution Date: 12/11/80 15:21:31 CMSBACK is now installed in: Los Gatos (2, CPUs), GPD SNJ (3), GPD STL (1) Austin (1) Note: Austin has (re)installed CMSBACK in other locations. It is also being installed in Yorktown. ... snip ... other recent CMSBACK references: http://www.garlic.com/~lynn/2006t.html#20 Why these original FORTRAN quirks?; Now : Programming practices http://www.garlic.com/~lynn/2006t.html#33 threads versus task http://www.garlic.com/~lynn/2006u.html#19 Why so little parallelism? http://www.garlic.com/~lynn/2006u.html#26 Assembler question http://www.garlic.com/~lynn/2006u.html#30 Why so little parallelism? http://www.garlic.com/~lynn/2006v.html#24 Z/Os Storage Mgmt products all of this preceeding the work mentioned in Melinda's history paper by a couple years (even preceeding the hiring of the people that Melinda's history paper mentions as having done the original work). now as to automated operator /or automated operations ... the *autolog* command ... mentioned here http://www.garlic.com/~lynn/2006w.html#8 Why these original FORTRAN quirks? helped significantly with the automation of service virtual machines ... some recent references here: http://www.garlic.com/~lynn/2006p.html#10 What part of z/OS is the OS? http://www.garlic.com/~lynn/2006t.html#45 To RISC or not to RISC http://www.garlic.com/~lynn/2006t.html#46 To RISC or not to RISC http://www.garlic.com/~lynn/2006v.html#22 vmshare CMSBACK would be one example of service virtual machine ... another would be VNET ... another would be the facility developed for automated benchmarking. I had originally created the *autolog* command (and the automated flavor that was done at kernel boot) in support of automated benchmarking http://www.garlic.com/~lynn/subtopic.html#bench aka, i needed automatically (and unattended) to stop a current benchmark, generate a new kernel with various modifications, reboot to the new kernel, and start the next set of benchmarks. this could be repeated a couple times an hour for extended period straight (say 6-10 8hr shifts). now some rudimentary stuff could be done for automated operations using combination of service virtual machines (*autolog* command being one of the enablers) and special message facility ... which allowed application to capture all text (messages, cp command responses, etc) that normally would be written to the terminal/screen. a couple recent posts mentioning spm http://www.garlic.com/~lynn/2006k.html#51 other cp/cms history http://www.garlic.com/~lynn/2006t.html#47 To RISC or not to RISC http://www.garlic.com/~lynn/2006w.html#8 Why these original FORTRAN quirks? another service virtual machine would be CJNTEL using special message ... mentioned here http://www.garlic.com/~lynn/2006w.html#12 more secure communication over the network some drift ... the above post also includes a mention from 1981 for public key infrastructure kind of operation. however, simple text/message processing was lacking sophisticated parsing ... like found in parasite/story ... misc. references http://www.garlic.com/~lynn/2001k.html#35 Newbie TOPS-10 7.03 question http://www.garlic.com/~lynn/2003i.html#73 Computer resources, past, present, and future http://www.garlic.com/~lynn/2003j.html#24 Red Phosphor Terminal? http://www.garlic.com/~lynn/2004e.html#14 were dumb terminals actually so dumb??? http://www.garlic.com/~lynn/2005r.html#12 Intel strikes back with a parallel x86 design http://www.garlic.com/~lynn/2006.html#3 PVM protocol documentation found http://www.garlic.com/~lynn/2006c.html#14 Program execution speed http://www.garlic.com/~lynn/2006f.html#37 Over my head in a JES exit http://www.garlic.com/~lynn/2006m.html#35 Draft Command Script Processing Manual http://www.garlic.com/~lynn/2006n.html#23 sorting was: The System/360 Model 20 Wasn't As Bad As All That http://www.garlic.com/~lynn/2006p.html#31 25th Anniversary of the Personal Computer or later hllapi-like implementations. also missing was sophisticated rule infrastructures (allowing specification about what should be done in different kinds of circumstances). for other references, part of an old SPMS application document SPMS: CMS/SPM Interface Program 1 1.0 INTRODUCTION SPMS is a transient CMS command that can be called by an EXEC or by a program running in a virtual machine. It enables the user to use the CP Special Message Facility to intercept messages from CP or from other users and process them within a CMS program or EXEC. A CP command may be passed to SPMS to cause the response to that command to be returned to the caller, or SPMS can be used
Re: long ago and far away, vm370 from early/mid 70s
ref: http://www.garlic.com/~lynn/2006w.html#10 long ago and far away, vm370 from early/mid 70s while only a small subset of the virtual memory management stuff was released as DCSS vm370 ... and none of the cms paged mapped filesystem stuff ... a little more of the virtual memory management stuff was used for the original relational/sql implementation in system/r . which provided r/w (unprotected) shared segments between semi-privileged processes (different system/r database tasks running in different virtual addresss spaces). misc. past posts mentioning system/r work http://www.garlic.comm/~lynn/subtopic.html#systemr It was also part of the technology transfer of system/r to endicott for what was to become sql/ds. This addition feature took on the name DWSS (or dynamic writeable shared segments) ... and there was lots of issues on whether or not it impacted ECPS and microcode on existing customer machines. recent posts mentioning system/r and DWSS http://www.garlic.com/~lynn/2006t.html#16 Is the teaching of non-reentrant HLASM coding practices ever defensible? http://www.garlic.com/~lynn/2006t.html#39 Why these original FORTRAN quirks? recent posts on early virtual memory management stuff (a small subset which was going to be released as DCSS in vm370 release 3) http://www.garlic.com/~lynn/2006v.html#36 Why these original FORTRAN quirks? http://www.garlic.com/~lynn/2006w.html#7 Why these original FORTRAN quirks? http://www.garlic.com/~lynn/2006w.html#8 Why these original FORTRAN quirks? http://www.garlic.com/~lynn/2006w.html#9 dcss and page mapped file system i also worked on a semantic network related activity about the same time as the system/r stuff which used more of the virtual memory management and page mapped technology ... recent reference http://www.garlic.com/~lynn/2006v.html#48 Why so little parallelism?
more secure communication over the network
In the following, CJNTEL was an online corporate directory that I had initially put up on SJRLVM1 that could be queried by anybody on the internal network. The following has a suggestion for registering a person's public key with CJNTEL and making (effecitvely publishing) it available for retrieval by anybody with access to the internal network. following is some 15 years or so before being brought in to do some consulting with a small client/server startup that wanted to do payment transactions on their server http://www.garlic.com/~lynn/aadsm5.htm#asrn2 http://www.garlic.com/~lynn/aadsm5.htm#asrn3 To: wheeler Date: 05/15/81 13:41:12 re: more secure communication over the network One of the obvious concerns that will surely surface from the CJN work will be the problem of confidential information being exchanged over the network. I have a package from ** called CRYPT that may be a solution. The package implements a public key encryption system proposed by Diffie and Hellman (see recent vm newsletter). The problem we have with using CIPHER is that we must know an agreed upon key and we have to exchange the key in a secure manner prior to communication. The public key system works as follows: I publish a key which anyone can look up. They use that key to CRYPT the file. That key can only lock the safe. In order to DECRYPT the file (unlock the safe) I have a private key which no-one knows. Only the private key can unlock the safe. As an implementation I suggest we update out CJNTEL entry to include a public key for each of us. The package includes a procedure for generating keys. In this way I can look up your key in CJNTEL and send you ENCRYPTED confidential data. Cheap and simple. ... snip ... effectively certificateless public key operation ... misc. past posts mentioning certicateless public key operation http://www.garlic.com/~lynn/subpubkey.html#certless and somewhat similar to the discussion about publishing public keys in the domain name infrastructure ... a few posts this year discussing the subject: http://www.garlic.com/~lynn/2006b.html#37 X.509 and ssh http://www.garlic.com/~lynn/2006c.html#10 X.509 and ssh http://www.garlic.com/~lynn/2006c.html#34 X.509 and ssh http://www.garlic.com/~lynn/2006c.html#35 X.509 and ssh http://www.garlic.com/~lynn/2006c.html#38 X.509 and ssh http://www.garlic.com/~lynn/2006d.html#29 Caller ID spoofing http://www.garlic.com/~lynn/2006f.html#16 trusted repositories and trusted transactions http://www.garlic.com/~lynn/2006f.html#32 X.509 and ssh http://www.garlic.com/~lynn/2006f.html#33 X.509 and ssh http://www.garlic.com/~lynn/2006f.html#34 X.509 and ssh http://www.garlic.com/~lynn/2006h.html#27 confidence in CA http://www.garlic.com/~lynn/2006p.html#7 SSL, Apache 2 and RSA key sizes http://www.garlic.com/~lynn/2006t.html#8 Root CA CRLs http://www.garlic.com/~lynn/2006v.html#49 Patent buster for a method that increases password security as well as the whole account authority digital signature stuff http://www.garlic.com/~lynn/x959.html#aads ... CJNTEL is different that the internal online telephone book recently mentioned here http://www.garlic.com/~lynn/2006v.html#32 Effi[ci]ency of branch table vs individual compare branch the internal online telephone book capture the original source from various corporate locations (that were used to generate the printed copy), converted the source to desired format and made them available for distribution. this normally was loaded on local systems that allowed users to do online lookups on their local machine. CJNTEL could be accessed remotely over the internal network using special message ... misc. past posts about the internal network ... which was larger than the arpanet/internet from just about the beginning until sometime mid-85. http://www.garlic.com/~lynn/subnetwork.html#internalnet note that the above reference is in addition to the requirement that all links leaving corporate facilities required link encryptors ... at one point there was the claim that the internal network had move than half of all link encryptors in the world. misc. recent posts mentioning special message http://www.garlic.com/~lynn/2006k.html#51 other cp/cms history http://www.garlic.com/~lynn/2006t.html#47 To RISC or not to RISC http://www.garlic.com/~lynn/2006w.html#8 Why these original FORTRAN quirks? We did do a modification to CJNTEL so that in addition to doing various operations on its corporate directory, it was also possible (for remote network user) to request CJNTEL to execute the telephone directory command on SJRLVM1 ... returning the results over the network. for some topic drift ... some references to the hsdt (high speed data transport) project http://www.garlic.com/~lynn/subnetwork.html#hsdt and some recent posts about various interactions with NSF: http://www.garlic.com/~lynn/2006s.html#50 Ranking of non-IBM mainframe builders? http://www.garlic.com/~lynn/2006t.html#6 Ranking of non-IBM mainframe
long ago and far away, vm370 from early/mid 70s
Concurrent with the benchmarking, shared segment, page mapped filesystem, resource manager, and other misc. stuff referred to in these posts http://www.garlic.com/~lynn/2006v.html#36 Why these original FORTRAN quirks? http://www.garlic.com/~lynn/2006w.html#7 Why these original FORTRAN quirks? http://www.garlic.com/~lynn/2006w.html#8 Why these original FORTRAN quirks? http://www.garlic.com/~lynn/2006w.html#9 dcss and page mapped filesystem I was also at the same time doing a lot of the work on VIRGIL/TULLY (138/148) and ECPS http://www.garlic.com/~lynn/94.html#21 370 ECPS VM microcode assist http://www.garlic.com/~lynn/94.html#27 370 ECPS VM microcode assist http://www.garlic.com/~lynn/94.html#28 370 ECPS VM microcode assist and at the same time doing system and microcode design for VAMPS, a five-way multiprocessor effort ... collected past posts mentiong VAMPS http://www.garlic.com/~lynn/subtopic.html#bounce For some reason, the product people responsible for both VIRGIL/TULLY and VAMPS somewhat viewed the other as competing products; even though i was doing much of the design for both products. There were some corporate product escalation meetings where I was expected to sit on both sides of the table simultaneously and argue it out with myself. VIRGIL/TULLY shipped, but VAMPS was canceled. Memo to: Endicott cc: wheeler Date: August 27, 1975 Subject: Simplifying Technical Considerations for VAMPS References: 1) Technical Review of VAMPS Proposal by KK and W dated 8/5/75 2) Update of above dated 8/21/75 As you pointed out last week during the Boeblingen Technical Review sessions, the VAMPS schedule is a critical PSE factor. During these sessions it became evident that the technical considerations of the original VAMPS proposal had not been fully adjusted to account for a marketing strategy similar to that for the VIRGIL/TULLY VM proposal. As described in the Attachment, this revised marketing strategy for VAMPS provides a number of technical simplifications. These simplifications are being proposed for resource and schedule reasons and not for reasons of technical feasibility. While the possible tradeoffs that these simplifications could allow in the major redesign MSC and dispatcher areas are not clear, the significant reduction in the total number of changes should not only alleviate the resources required, but also possibly the schedule due to the reduction in dependencies and testing. If the VAMPS forecast look promising early in September, a more detail technical design review of the MSC and dispatcher areas should be immediately arranged in Boeblingen after which more accurate resource and schedule estimates can be derived. ... snip ...
CMSBACK
The following message is a courtesy copy of an article that has been posted to alt.folklore.computers,bit.listserv.vmesa-l as well. Anne Lynn Wheeler [EMAIL PROTECTED] writes: search engine even turns up one of my old pasts mentioning VOL1 and HDR1: http://www.garlic.com/~lynn/2004q.html#20 Systems software versus applications software definitions which discusses an old backup/archive system that i had written for internal use ... which then went thru several iterations and eventually released as workstation datasave facility, morphed into adsm and is now known as tsm http://www.garlic.com/~lynn/subtopic.html#backup re: http://www.garlic.com/~lynn/2006t.html#20 Why these original FORTRAN quirks?; Now : Programming practices old email from the other person working on CMSBACK version 2. this is on enhancing the pattern matching capability in the user interface file retrieval process (from the backup/archive repository). as noted in the above reference, Melinda's history starts with what would be CMSBACK version 3 (or possibly 4 ... depending on how you classify all the work done between the initial CMSBACK deployment and assignment of the people mentioned in Medlinda's history). To: wheeler Date; 10/25/79 02:11:58 I had to make one change to OSPATM to make it work. The macro SREGS is a bit too much for me tonite so I replaced the one to set up addressability to the work area using R5 with the L R5,8(,R1) and USING PATSPC,R5. AND.. it works like a super star Try issuing the CMSBACK exec, ask for a report, and enter whatever patterns you like.. Disk load the returned RPT file and see what you get.. I've been playing with it now for a while and it really works great. (I will make the matching available on date and time tommorrow.. why stop with just the filename and filetype). ... snip ... for the original low-level CMSBACK interface to tape, I used a highly modified version of VMFPLC (mentioned in the old email below) that I had renamed VMXPLC. Not mentioned in the below ... but it was also enhanced to provide optimal processing for the paged mapped filesystem implementation that I had done http://www.garlic.com/~lynn/subtopic.html#mmap start of buffers were page aligned ... and 15 800 byte data blocks could be three 4096 byte blocks. For small files, the minimum size data block on tape could be 800 bytes. With separate FST record and data block, a tape with a lot of small files would have half (or more) of the length could be taken up with interrecord gaps. Merging the FST record and the first data record into the same physical tape record, would cut the tape devoted to interrecord gaps in half (when lots of small files was involved). From: wheeler Date: 03/21/80 13:41:39 To: somebody in endicott The original VMFPLC was an update to release 2 DMSTPE. The code took the FST record which is placed in a trailing 800 byte record following the file dumped and placed it in a 59 byte record in front of the file dumped. It also blocked up to 5 800 byte data blocks per physical tape block. I captured the update early and maintained it (I heard that the development lost it and didn't have a copy) against the current release plc level. I also enhanced the update to block up to 15 800 byte data blocks, to merge the FST record into the 1st physical data block dumped and to avoid rewriting the MFD after each file loaded. VMFPLC2 appears to have several new features which would indicate that it is not a modification of the original VMFPLC (since as far as I know, I'm the only one with the source) but it still maintains the original tape format. I must confess that I've not looked at the new release 6/bsepp tape source (although I've heard that it has grown substantially and has been split into several files). ... snip ... and for an even earlier CMSBACK related email. standard CMS could share various filesystem areas across multiple virtual machines. However, the filesystem status information would be duplicated in every virtual address space. A hack was done to place a copy of some shared CMS filesystem information in shared (r/o protected) memory ... so there only need to be a single physical copy of the filesystem metadata (shared across everybody). The problem for DMSDSK, DMSTPE, VMFPLC and VMXPLC was that there was a hack where they temporarily modified the file metadata that forced the logical record size to match the physical disk record ... and then restore it when they were done. This hack would fail if the file metadata information was located in shared (r/o protected) memory. From: wheeler Date: 04/02/79 19:22:35 Yorktown has done an update for DMSDSK (DISK DUMP) to handle the problem of dumping from a disk with FST in shared memory (DMSDSK YK187DMS). Can you merge with what you have been doing to DMSTPE for TAPE, VMFPLC, VMXPLC?? ... snip ...
Re: real core
Tom Duerbush wrote: So I guess the question I'm wondering... How many others have shipped dumps, online, back before high speed Internet connections? re: http://www.garlic.com/~lynn/2006s.html#16 memory, 360 lcs, 3090 extended store, etc http://www.garlic.com/~lynn/2006s.html#17 bandwidth of a swallow (was: real core) we had done hsdt (high speed data transport) project http://www.garlic.com/~lynn/subnetwork.html#hsdt in the 80s ... with high-speed backbone connected to the internal network. http://www.garlic.com/~lynn/subnetwork.html#internalnet in the late 80s, they used to ship chip designs to high-speed hardware logic simulator/checker in the late 80s. this was claimed to contributed to helping bring in rios/power chip a year early. we were also interested in participating in nsfnet-1 backbone (which could be considered the operational precurser to the modern internet). we weren't allowed to bid ... but did get an technical review, one of the conclusions was what we had running and operational was at least five years ahead of all the nsfnet-1 bids (RFP responses) to build something new. slightly related http://www.garlic.com/~lynn/internet.htm#0 and http://www.garlic.com/~lynn/2002k.html#12 nsfnet program announcement http://www.garlic.com/~lynn/2000e.html#10 nsfnet award announcement for other drift, in the early days of rex (rexx), i wanted to demonstrate that rex wasn't just another batch command processor (exec, exec2) but could be used to implement very complex application. I chose the vm problem/dump analyzer ... which was a fairly large application written in assembler. i wanted to demonstrate that in 3 months working half-time, i could implement in rex something that had ten times the function and ten times the performance of the existing assembler implementation. the result was dumprx http://www.garlic.com/~lynn/subtopic.html#dumprx which could be used to analyze a dump interactively ... even over the internal network w/pvm (terminal emulation) ... w/o having to actually ship the dump. part of dumprx was library of automated analysis scripts ... the results could be saved and restored; aka you could run the automated analysis scripts ... that batched the most common sequence of manual analysis processes. the library of batched analysis routines effectively automated most of the most common (manual) analysis procedures (examined storage for a broad range of failure signatures).
Re: bandwidth of a swallow (was: Real core)
Paul B. Nieman wrote: In the early 1990's we consolidated a data center from Sydney into Philadelphia. We used SYBACK to do a full dump of specific (most) minidisks to tape and shipped the tapes. We then performed daily incrementals to disk, and sent the incrementals via RSCS, via a 9600 baud line at most. I think we had a 9600 baud line that was shared for RSCS and VTAM traffic, but the telecom part wasn't mine to worry over. Each minidisk intended to move was a separate file and sent via SENDFILE. There were service machines written to send and receive them. I think the first incrementals arrived before the tapes. In any case, we kept track of different day's incrementals for a whole week and applied them as they finished arriving. The line was kept very busy and watched closely, but it was easy to restart if it dropped. Our actual cutover the following weekend went fairly quickly and met whatever target we had, which I certainly think wasn't enough to allow for backing up, shipping, and applying the tapes. in the later part of the mid-70s, one of the vm370 based commercial time-sharing services had datacenter on the east coast and put in datacenter on the west coast connected via 56kbit link. the had enhanced vm370 to support process migration between loosely-coupled machines in the same datacenter cluster ... i.e. for one thing, as they moved to 7x24 worldwide service ... there was no window left for doing preventive maintenance. process migration allowed them to move everything off a complex (that needed to be taken down for maint). the claim was that they could even do process migration over the 56kbit link ... modulo most of the file stuff having been replicated (so that there wasn't a lot needing movement in real time). misc. past posts mentioning vm time-sharing service http://www.garlic.com/~lynn/subtopic.html#timeshare they had also implemented page mapped filesystem capability with lots of advanced bells and whistles ... similar to the cms page mapped filesystem stuff that i had originally done in the early 70s for cp67. http://www.garlic.com/~lynn/subtopic.html#mmap which also included a superset of the memory segment stuff ... a small subset was later released as DCSS http://www.garlic.com/~lynn/subtopic.html#adcon for other drift ... as mentioned before ... the internal network was larger than the arpanet/internet from just about the beginning until around sometime mid-85. misc. posts mentioning internal network http://www.garlic.com/~lynn/subnetwork.html#internalnet one of the issues was what to do about JES2 nodes on the internal network. one of the issues was that relatively trivial changes in JES2 headers between releases would precipitate JES2 ( MVS) system crashes. for that reason (and quite a few others), JES2 nodes were pretty well limited to a few boundary nodes. A library of vnet/rscs line drivers grew up for JES2 that supported a cannonical JES2 header format ... and the nearest VNET/RSCS node would have the specific line-driver started that would make sure that all JES2 headers sent to the JES2 system ... met the requirements of that specific JES2 version/release. Sporadically, there were still some (infamous) cases where JES2 systems on one side of the world would precipitate JES2 systems on the other side of the world to crash (one particular well known case was JES2 systems in san jose causing JES2/MVS systems in hursley to crash). misc. past posts mentioning hasp /or jes2 http://www.garlic.com/~lynn/subtopic.html#hasp Another scenario was there was some work to do load-balancing offload between STL/bld90 and Hursley around 1980 (since they were offset by a full shift). the test was between two jes2 systems (carefully checked to be at compatible release/version) ... over a double-hop 56kbit satellite link (i.e. up from west coast to satellite over the us, down to the east coast, up to satellite over the atlantic, down to UK). JES2 couldn't make connection ... but all error indicators were clean. So finally it was suggested to try the link between two vnet systems. The link came up and ran with no problem. The person overseeing the operations was extremely sna/vtam indoctrinated. So the first reaction was what ever caused the problem went away. So it was time to switch it back between JES2 ... it didn't work. Several more switches were made ... always ran between VNET, never ran between JES2. The person overseeing the operation finally declared that the link actually had severe error problems but the primitive VNET drivers weren't seeing them ... and only the advanced VTAM error analysis was realizing there was lots of errors. it turned out the problem was with the double-hop satellite roundtrip (four hops, 44k miles per hop, 22k-up, 22k-down) propogation delay ... which VNET tolerated and vtam/jes2 didn't (not only was the majority of the internal network not jes2 ... it was also not sna/vtam)
memory, 360 lcs, 3090 extended store, etc
Schuh, Richard wrote: Yeah, but 3090 memory was not ferrite core, was it? IIRC, it was much cheaper and more reliable. I wasn't privy to the bean-counting specifics, but the rumored cost of the LCS storage on our 360 class machines was in the neighborhood or $2.5-3M per 2MB unit. And they were real core - you could look through the glass panels and see the individual planes of wires and doughnuts. The stuff was not reliable, so we had 3 boxes in order to always have 1 available for the production ACP system. There was usually 1 in use, 1 being repaired, and 1 just out of repair that was on standby. The care and feeding of those animals was a career. small spill-over from bit.listserv.ibm-main mentioning extended store, 3090 memory, 360 memory, 360 LCS and a couple other memory related topics http://www.garlic.com/~lynn/2006r.html#34 REAL memory column in SDSF http://www.garlic.com/~lynn/2006r.html#35 REAL memory column in SDSF http://www.garlic.com/~lynn/2006r.html#36 REAL memory column in SDSF http://www.garlic.com/~lynn/2006r.html#37 REAL memory column in SDSF http://www.garlic.com/~lynn/2006r.html#39 REAL memory column in SDSF http://www.garlic.com/~lynn/2006r.html#40 REAL memory column in SDSF http://www.garlic.com/~lynn/2006r.html#42 REAL memory column in SDSF http://www.garlic.com/~lynn/2006r.html#43 REAL memory column in SDSF
Re: The Fate of VM - was: Re: Baby MVS???
re: http://www.garlic.com/~lynn/2006o.html#49 The Fate of VM - was: Re: Baby MVS??? http://www.garlic.com/~lynn/2006o.html#51 The Fate of VM - was: Re: Baby MVS??? http://www.garlic.com/~lynn/2006o.html#52 The Fate of VM - was: Re: Baby MVS??? email from long ago and far away X-To: wheeler Subject: GENDMOD module Could I ask you to get an assembly listing of the GENMOD module so I can study it to determine what changes I have to make to VS APL. If we make this change, it could have a tremendous impact on the HONE system, above what their SEQUOIA system is giving them. There are several very large APL applications on there particularly the configurators. If users are sharing that code as well, we could get some big savings ... not to mention the time savings in just loading the workspaces. snip ... shared variables was eventually created as an alternative paradigm (to that originally implemented in cms\apl) for accessing system api/functions. apl\cms and apl\sv eventaully evolved into vs apl. the (cms) apl interpreter had been structured into code that could be shared across all the virtual address spaces. however, HONE apl operations had another couple hundred kbytes of commonly used apl applications that appeared in nearly all workspaces http://www.garlic.com/~lynn/subtopic.html#hone i had originally done paged mapped filesystem for cms in the early 70s along with a mechanism that allowed loading of objects from cms paged mapped filesystem as memory objects shared across multiple virtual address spaces. http://www.garlic.com/~lynn/subtopic.html#mmap one of the internal datacenters this was installed on was at HONE. HONE used it to create a shared executable image of the APL interpretor (under cms). I had modified the standard CMS executable creation command (GENMOD) and executable load command (LOADMOD) to add support for the shared executable object option. A small subset of the cp cms memory mapped feature/function was released in vm/370 release 3 called DCSS. However, the full function was in use at a number of internal datacenters, like HONE. The issue in this particular email ... was that there were several large APL applications (like the HONE mega-application mentioned in the previous post, SEQUOIA). These programs were mostly static data that was interpreted by the APL interpreter (and executable in the 370 sense). The idea here was to modify the APL workspace loader to play some of the same games that I had done in CMS GENMOD/LOADMOD ... so that static APL workspace applications could be loaded as shared memory objects (allowing a single common image to be used across all virtual address spaces). This could significantly cut both the aggregate HONE application real-storage requirements ... as well as I/Os involved in retrieving unique copies off disk for every HONE user.
hardware virtualization slower than software?
Hardware virtualization slower than software? http://developers.slashdot.org/developers/06/08/12/2028223.shtml ... from above: One example given is compilation of a Linux kernel under a virtualized Linux OS. Native wall-clock time: 265 seconds. Software-assisted virtualization: 393 seconds. Hardware-assisted virtualization: 484 seconds. Ouch. It sounds to me like a hybrid approach may be the best answer to the virtualization problem. ... snip ... similar, but different posting made here not too long ago http://www.garlic.com/~lynn/2006j.html#27 virtual memory the above has a discussion about hardware/software virtualization trade-off in 3081 vis-a-vis 3090. note that this was pre-PR/SM (which has since evolved into LPARS) ... where the microcode support can create virtual machines ... w/o requiring separate hypervisor monitor running (i.e. dropping everything into hardware was no longer a performance trade-off issue). for other drift, the performance characterization in the article is reminisent of presentation i made at boston share meeting in aug68. three people had came out from the science center http://www.garlic.com/~lynn/subtopic.html#545tech the last week in jan68 to install cp67 at the university. during the spring and summer of 68, i rewrote significant poritions of the kernel, some cases descreasing pathlengths by factor of 10 to 100 times. past posting of parts of that presentation http://www.garlic.com/~lynn/94.html#18 CP/67 and OS MFT14 which has a bare-machine (native wall clock) time of 322 sec. original virtualization elapsed time 856 sec. virtualization elapsed time (after rewrites of the spring and summer) 435 secs (virtualization processing was reduced from 534 cpu secs. to 113 cpu secs.).
Re: oops
Phil Smith III wrote: Gabe reminds me that the 360 didn't run VM; I did use it, but it was the 370/158 with 2MB that I used to use VM on. 360/67 was the only (standard) 360 with virtual memory support. it had both 24-bit and 32-bit virtual addressing options (you didn't see more than 24-bit again until 370-xa with 3081). 360/67 multiprocessor also had channel director ... which supported all processors accessing all channels (standard 360 370 multiprocessors only provided for common memory addressing ... the rest of the infrastructure, including channels, were partitioned, specific to processors). cp67 was developed by the science center http://www.garlic.com/~lynn/subtopic.html#545tech ... supporting virtual machines and virtual memory. cp67 was released to customers. there had been an earlier cp40 developed on a custom modified 360/40 with virtual memory ... pending availability of a 360/67. there was joint project between cambridge and endicott to add a lot of 370 stuff to cp67 kernel ... this was discussed recently in the series of posts on sequence numbers and cms multi-level source maintenance ... which mostly evolved out of the cp67 cambridge/endicott 370 effort (*CMS* originally stood for the cambridge monitor system, but morphed to conversational monitor system for vm370) modified version of cp67 ran internally extensively on 370s ... pending availability of vm370. also CCWTRANS (supporting virtual memory ccws translated to shadow real CCWs) was used in initial prototype of os/vs2 (i.e. mvt hacked to directly support 370 virtual memory). gobs of posts just this year mentioning cp/67 http://www.garlic.com/~lynn/2006.html#5 Page fault question (zero-filling) http://www.garlic.com/~lynn/2006.html#7 EREP , sense ... manual http://www.garlic.com/~lynn/2006.html#10 How to restore VMFPLC dumped files on z/VM V5.1 http://www.garlic.com/~lynn/2006.html#13 VM maclib reference http://www.garlic.com/~lynn/2006.html#17 {SPAM?} DCSS as SWAP disk for z/Linux http://www.garlic.com/~lynn/2006.html#19 DCSS as SWAP disk for z/Linux http://www.garlic.com/~lynn/2006.html#25 DCSS as SWAP disk for z/Linux http://www.garlic.com/~lynn/2006.html#38 Is VIO mandatory? http://www.garlic.com/~lynn/2006.html#40 All Good Things http://www.garlic.com/~lynn/2006b.html#7 Mount a tape http://www.garlic.com/~lynn/2006b.html#8 Free to good home: IBM RT UNIX http://www.garlic.com/~lynn/2006b.html#15 {SPAM?} Re: Expanded Storage http://www.garlic.com/~lynn/2006b.html#16 {SPAM?} Re: Expanded Storage http://www.garlic.com/~lynn/2006b.html#23 Seeking Info on XDS Sigma 7 APL http://www.garlic.com/~lynn/2006b.html#25 Multiple address spaces http://www.garlic.com/~lynn/2006b.html#32 Multiple address spaces http://www.garlic.com/~lynn/2006b.html#39 another blast from the past http://www.garlic.com/~lynn/2006b.html#40 another blast from the past ... VAMPS http://www.garlic.com/~lynn/2006c.html#2 Multiple address spaces http://www.garlic.com/~lynn/2006c.html#18 Change in computers as a hobbiest http://www.garlic.com/~lynn/2006c.html#21 Military Time? http://www.garlic.com/~lynn/2006c.html#22 Military Time? http://www.garlic.com/~lynn/2006c.html#28 Mount DASD as read-only http://www.garlic.com/~lynn/2006c.html#45 IBM 610 workstation computer http://www.garlic.com/~lynn/2006d.html#0 IBM 610 workstation computer http://www.garlic.com/~lynn/2006d.html#18 IBM 610 workstation computer http://www.garlic.com/~lynn/2006d.html#21 IBM 610 workstation computer http://www.garlic.com/~lynn/2006d.html#35 Fw: Tax chooses dead language - Austalia http://www.garlic.com/~lynn/2006e.html#7 About TLB in lower-level caches http://www.garlic.com/~lynn/2006e.html#28 MCTS http://www.garlic.com/~lynn/2006e.html#40 transputers again was: The demise of Commodore http://www.garlic.com/~lynn/2006e.html#45 using 3390 mod-9s http://www.garlic.com/~lynn/2006f.html#0 using 3390 mod-9s http://www.garlic.com/~lynn/2006f.html#1 using 3390 mod-9s http://www.garlic.com/~lynn/2006f.html#5 3380-3390 Conversion - DISAPPOINTMENT http://www.garlic.com/~lynn/2006f.html#21 Over my head in a JES exit http://www.garlic.com/~lynn/2006g.html#1 The Pankian Metaphor http://www.garlic.com/~lynn/2006g.html#3 The Pankian Metaphor http://www.garlic.com/~lynn/2006g.html#18 TOD Clock the same as the BIOS clock in PCs? http://www.garlic.com/~lynn/2006g.html#58 REP cards http://www.garlic.com/~lynn/2006h.html#7 The Pankian Metaphor http://www.garlic.com/~lynn/2006h.html#20 Binder REP Cards (Was: What's the linkage editor really wants?) http://www.garlic.com/~lynn/2006h.html#22 The Pankian Metaphor http://www.garlic.com/~lynn/2006h.html#30 The Pankian Metaphor http://www.garlic.com/~lynn/2006h.html#55 History of first use of all-computerized typesetting? http://www.garlic.com/~lynn/2006h.html#57 PDS Directory Question http://www.garlic.com/~lynn/2006i.html#4 Mainframe vs. xSeries http://www.garlic.com/~lynn/2006i.html#9 Hadware Support for Protection Bits: what does it really mean?
Re: the more things change, the more things stay the same
re: http://www.garlic.com/~lynn/2006n.html#52 the more things change, the more things stay the same http://www.garlic.com/~lynn/2006n.html#53 the more things change, the more things stay the same the following article: How Secure Is That Device? As device software joins the larger world, security becomes ever more vital http://dso.com/news/showArticle.jhtml?articleID=191501076 Has statements that are almost exact quotes of some statements about virtualization made in the late 60s, nearly 40 years ago. the article is also related to the thread raised in this crypto topic drift http://www.garlic.com/~lynn/2006n.html#56 The very first text editor started with this article http://www.eetimes.com/news/latest/showArticle.jhtml?articleID=190900759 the most recent in that thread http://www.garlic.com/~lynn/aadsm24.htm#52 Crypt to defend chip IP: snake oil or good idea? and even more thread drift related to the subject http://www.garlic.com/~lynn/aadsm24.htm#53
Re: SEQUENCE NUMBERS
R.S. wrote: Even some mainframe programs interpret it as data, with funny effects somtimes. For example SYSIN DD * for FTP program cannot contain the numbers. AFAIK some TCPIP config files as well. AFAIK the sequence numbers are completely useless nowadays. It was used for punched card sorter. Is there any other application ? they were also used for a long time as part of the cp67/cms multilevel source update infrastructure (later vm370/cms). since it was the pervasive internal platform for a long time ... even some number of mvs components would be start life with cms multilevel source update and then have to morph to smp for external release (there were some folktales of mvs components having periodic difficulty converting their cms source development and maintained environment to smp as part of customer ship). in vm/cms ... before the oco-wars, not only did source ship as standard, but maint. was done by shipping the source changes. recent thread that started out discussing card sorting but drifted into description of cms multi-level source update: http://www.garlic.com/~lynn/2006n.html#45 sorting
Re: Source maintenance was Re: SEQUENCE NUMBERS
Shmuel Metz , Seymour J. wrote: I'm not sure when it came along, but by VM/SE there was a somewhat more sophisticated UPDATE facility[1] with aux files, control files and update files. I'd love to see a similar facility integrated with ISPF. [1] Not only could the XEDIT editor process them, but it could generate update files to reproduce the effects of an edit session. That's one of the CMS facilities I miss the most. re: http://www.garlic.com/~lynn/2006o.html#19 Source maintenance was Re: SEQUENCE NUMBERS the aux files, control files, update files scheme was what was created for the effort for building 370 virtual machine support into a cp67 kernel (running on 360/67). however, it was implemented all in EXEC with EXEC processing figuring out the control aux files and making interative calls to UPDATE command. this was picked up as part of the original vm370 release and update command was enhanced to directly process control, aux, and update files (in one pass) and spitting out the (temporary, working) source file for compile/assemble. a little later, editors were enhanced to directly support the control, aux, and update files as part of loading a source file for editing ... with option that all changes made in the edit session resulted in an update file (as opposed to a new complete source). this recent posting, in a different thread, has more detailed description of some of the operations ... as well as URLs to current CMS documentation (including an example update from an internal editor that predated xedit). http://www.garlic.com/~lynn/2006n.html#45 sorting a few other recent postings that happen to also mention xedit: http://www.garlic.com/~lynn/2006n.html#34 Not Your Dad's Mainframe: Little Iron http://www.garlic.com/~lynn/2006n.html#43 MTS, Emacs, and... WYLBUR? http://www.garlic.com/~lynn/2006n.html#55 The very first text editor
Re: the more things change, the more things stay the same
[EMAIL PROTECTED] (John Savard) writes: Not surprising: the NSA's Security-Enhanced Linux includes, as its unique security feature, something called mandatory security. A file can be flagged as having restrictions on it, and then any program which accesses this file, and writes on other files, causes the restrictions to propagate. This, of course, was one of the features of Multics, which indeed dates from about 40 years ago. re: http://www.garlic.com/~lynn/2006n.html#52 the more things change, the more things stay the same they were on the 5th floor of 545 tech sq ... while we were on the 4th floor http://www.garlic.com/~lynn/subtopic.html#545tech
Re: Any resources on VLIW?
Brian Inglis [EMAIL PROTECTED] writes: Might be relevant if Lynn Wheeler could expand on the unreleased VAMPS microcode to speed up 370 SMP, and also provided logical processors with similarities to those on current zSeries LPARs, although that may just have dropped parts of 370 sequential code down into microcode. so presumably this recent post vis-a-vis vamps and the later i432 http://www.garlic.com/~lynn/2006n.html#42 Why is zSeries so CPU poor? misc. collected past vamps postings http://www.garlic.com/~lynn/subtopic.html#bounce early microcode effort was VMA original for 370/158 that helped virtual machine performance. for subset of supervisor state instructions, microcode was added to execute the instruction using virtual machine rules (to avoid interrupting into the virtual machine hypervisor where the instruction was simulated). concurrent with VAMPS effort was ECPS for 370 138148. ECPS did some more stuff like VMA on the 158 (direct supervisor state instruction execution) ... but it also identified parts of the hypervisor kernel and moved that kernel code into microcode. the issue on 138148 machines was that there was an avg. of 10:1 microcode instructions executed for every 370 instruction. Much of the kernel code moved to microcode on straigh 1:1 basis resulting in ten times performance speed up. old posting identifying specific kernel code segments for migrating into microcode. http://www.garlic.com/~lynn/94.html#21 370 ECPS VM microcode assist the VMA-related efforts eventually evolved into SIE ... where nearly all supervisor state instructions had microcode enhancement for directly executing with regard to virtual machine rules (avoiding a lot of interruption into virtual machine hypervisor to simulate supervisor state instructions). SIE was a state change instruction that gathered up all the fields needed by various supervisor state instructions to execute according to virtual machine rules. post of old SIE discussion about implementation issue differences between 3081 and trout (3090) http://www.garlic.com/~lynn/2006j.html#27 virtual memory there were still things like page faults for the virtual machine that resulted in interruptions into the hypervisor kernel for handling. a special case was defined involving things like dedicated real storage for a virtual machine ... eliminating need to interrupt into the hypervisor kernel. This resulted in being able to operate a virtual machine subset directly supported by hardware ... w/o the need for a virtual machine kernel. This was called PR/SM ... and PR/SM capability eventually evolved into the current LPARs (logical partitions). a reference discussing some current LPAR and PR/SM http://researchweb.watson.ibm.com/journal/rd/483/siegel.html current machines can have a configurable limited number of LPARs ... and it is possible to run a virtual machine hypervisor in an LPAR, which in turns supports a much larger number of virtual machines. The has been an evoluation of the SIE support. Initially, SIE was not virtualized but LPARs make use of SIE for support. That met that a virtual machine hypervisor running in an LPAR wouldn't have performance assist of SIE for running its virtual machines (all virtual machine supervisor instructions would interrupt into the hypervisor for simulation). Enhancements were required to virtualize SIE for at least one level (so it could be used both by LPAR function and also by hypervisor running in an LPAR). Since I was doing both VAMPS and ECPS ... I borrowed a lot of stuff done for ECPS for doing VAMPS. However, for VAMPS, I wanted it extended in a much more architected way ... rather than simply doing a 1-fo-1 movement of existing kernel 370 code into microcode. VAMPS was to have up to five processors ... and I defined a microcode hardware queued work interface where the hypervisor put units of work on the queued work interface (and the microcode took the queued work and executed on whatever available processor there were). The hardeware microcode also placed queued work for the hypervisor to handle ... like things that were i/o interrupts in traditional 370 or page fault interrupts (from executing virtual machines), etc. The VAMPS abstraction of queued work for multiprocessor environment was somewhat akin to the later defintion found later in i432. Some of the VAMPS abstraction for i/o work queueing was somewhat akin to what showed up later for 370-xa i/o operations. After VAMPS was killed, I adapted the multiprocessing microcode queued processing to an software implementation. A lot of the SMP kernel implementations used a single, global kernel SPIN lock to serialize all kernel execution. This drastically minimized the amount of code changes to adapt a single-processor operating system to support a multiprocessor operation. In adapting the VAMPs multiprocessing microcode support to software, I took the equivalent kernel software functions (that had been moved to microcode in VAMPS) and made
Re: Any resources on VLIW?
re: http://www.garlic.com/~lynn/2006n.html#44 Any resources on VLIW? http://www.garlic.com/~lynn/2006n.html#47 Any resources on VLIW? as an aside ... some number of the relatively recent 370 emulators written for intel platforms have quoted avg. instruction ratio numbers around 10:1 also (have to play some real tricks to get it much below 10:1).
Re: Not Your Dad's Mainframe: Little Iron
Jim wrote: DUMPRX was one of the slickest tools available for VM sysprogs in the '80s. With the overall level of code quality at that time, it was really needed. I have always thought that the only reason it wasn't included in the product was the NIH mentality that was common in IBM at that time in Endicott and Kingston. re: http://www.garlic.com/~lynn/2006n.html#11 Not Your Dad's Mainframe: Little Iron i may have alienated endicott ... which had a whole group supporting dumpscan (which was a large program written all in assembler). I had made a comment that i would implement dumprx in less 3 months elapsed time only working half time on it. It would have ten times the function of dumpscan as well as ten times the performance. also since this was the leading edge of the OCO-wars ... i pointed out that it would be implemented all in REXX (except for possibly a hundred assembler instructions) so that the source would have to be shipped. I got all the basic stuff done early ... and since i had been building up a knowledge base of failure scenarios ... i started a library of dumprx/rexx routines that searched for particular classes of failure signatures/characteristics. it could be run either as cms terminal line-mode ... or as a xedit rexx macro ... and then have full xedit capability for the dumprx session since they wouldn't ship it, i eventually got approval to give a detailed implementation dumprx talk at SHARE ... in case anybody else wanted to implement their own. re: http://www.garlic.com/~lynn/subtopic.html#dumprx
Re: dumprx
Jim wrote: DUMPRX was one of the slickest tools available for VM sysprogs in the '80s. With the overall level of code quality at that time, it was really needed. I have always thought that the only reason it wasn't included in the product was the NIH mentality that was common in IBM at that time in Endicott and Kingston. re: http://www.garlic.com/~lynn/2006n.html#11 Not Your Dad's Mainframe: Little Iron i may have alienated endicott ... which had a whole group supporting dumpscan (which was a large program written all in assembler). I had made a comment that i would implement dumprx in less 3 months working half time and it would have ten times the function of dumpscan as well as ten times the performance. also since this was the leading edge of the OCO-wars ... i pointed out that it would be implemented all in REXX (except for possibly a hundred assembler instructions) so that the source would have to be shipped. I got all the basic stuff done early ... and since i had been building up a knowledge base of failure scenarios ... i started a library of dumprx/rexx routines that searched for particular classes of failure signatures/characteristics. since they wouldn't ship it, i eventually got approval to give a detailed implementation dumprx talk at SHARE ... in case anybody else wanted to implement their own. re: http://www.garlic.com/~lynn/subtopic.html#dumprx
Re: Old IBM protocol IBM 1006
Charles Mills wrote: Here's a good start: http://listserv.uark.edu/scripts/wa.exe?A2=ind0509L=ibmvmP=8109 note in the above referenced archive ... it mentions transmission as reverse inverted • ALC is transmitted reverse inverted. For example, capital A is 0x31, but it's transmitted as 0x73. This makes it a major PITA to read off the wire. my off-repeated story of doing our own mainframe terminal controller at the univ. http://www.garlic.com/~lynn/subtopic.html#360pcm and somebody writing an article blaiming four of us for the mainframe pcm controller business. the ibm mainframe channel interface had been reverse engineered and a channel interface controller card built for an interdata/3 the second or third bug we encountered was passing ascii from the interdata/3 (programmed to emulate 2702 over the channel interface to the mainframe) ... showed data was coming in all garbage. it took some time to realize that the linescanner on the interdata/3 was taking the leading bit off the line and storing it it in the high order bit position of the byte ... while the linescanner in the 2702 was taking the leading bit off the line and storing it in the low order bit position of the byte. as a result ascii arriving in the mainframe memory from a 2702 (linescanner) was bit-reversed ... and the ibm translate tables were taking that into account.
Re: Not Your Dad's Mainframe: Little Iron
Rostyslaw J. Lewyckyj [EMAIL PROTECTED] writes: Well I had exposure, access, to an IBM MVT product called TESTTRAN which was sort of available on our system with assembler F and , if I remember correctly, Fortran G, both in batch and TSO. One had to compile/assemble with the TEST option, which produced and kept a variables symbol table and a statement location table. One could then set breakpoints, examine program values etc. etc. But it was very awkward to use, badly documented, and buggy. When I asked I was told that it wasn't developed because it wasn't used. Which I considered to be a very much a chicken and egg kind of argument. I had a little exposure to TEST under our CMS systems. But as we didn't really support VM/CMS too well at TUCCUNC I can't comment much except that I didn't find out much about what it was capable of. huge amount of OS/360 TESTRAN was outputing all the (12-2-9) SYM cards as part of assemble/compile ... so that you effectively could support symbolic debugging. I don't know anybody that actually used it ... I remember having a TESTRAN manual at one point and running with option to generate SYM cards (just to see what they looked like) ... but never actually using it. old post that has mention of SYM cards (as well as formats of most of the other 12-2-9 cards): http://www.garlic.com/~lynn/2001.html#14 IBM Model Numbers PER and TRACE command were initially machine level stuff ... hex addresses, hex locations ... etc .. not real symbolic stuff. I wrote a debug tool in REX(X) called DUMPRX that eventually was used extensively internally and at one point by nearly all the (vm/cms) field support people http://www.garlic.com/~lynn/subtopic.html#dumprx that had some amount of symbolic capability this has comment about locate command and symbolics (and testran) ... from 2001: http://listserv.uark.edu/scripts/wa.exe?A2=ind0103L=vmesa-lD=0P=39641 I had originally done pageable CP kernel function for cp67 3.1 the summer I did a stint with BCS in Seattle (i was still undergraduate) ... which didn't get released in product until vm370. Part of the thing that I did as part of the pageable CP kernel function was to capture the loader table symbolics (all the external entries) and write it out as part of the kernel image. this feature including the complete loader table symbolics as part of the (pageable) kernel image wasn't included in the pageable kernel that went out in vm370 release 1. As a result, there were periodic games played with a compiled module frequently called DMKSYM ... that had symbolics for some amount of kernel external entries. however, when i got around to doing dumprx, i recreated the capture of the complete loader table symbolics as part of saving the kernel image. Then the locate command was changed to use all the complete loader table entries saved out in the pageable kernel (instead of DMKSYM) ... and other things were enhanced to utilize the actual loader table entries. vm/cms postmortem kernel dump processing had facility of importing an image of the loader printed output. I modified the kernel dump process to initialize the dump image with a copy of the complete loader table image (from saving the original kernel image) as part of system startup. this has title of A Survey of current debugging concepts http://ntrs.nasa.gov/archive/nasa/casi.ntrs.nasa.gov/19690026235_1969026235.pdf it looks somewhat like a cms/script document printed on 1403 with TN train (some of the rendering looks wavy ... which might be scanning the original, it not, then it isn't likely to have been 1403 output). It is dated August, 1969 ... and it has section 3-34 TESTRAN, for IBM System/360 I now some number of gov. installations had cp67 (and cms, and script, etc) in 69 ... but I don't know if Goddard had one(?). The above does list TESTRAN reference as: IBM Corporation. IBM System/360 Operating System TESTRAN. Systems Reference Library. Form C28-6648-0 File Number S360-37. February 1967
Re: DCSS
Jim Bohnsack wrote: I had an XT/370 PC sometime in the mid-late 80's. It used PAM as it's native or default CMS file system if I remember correctly. Jim re: http://www.garlic.com/~lynn/2006m.html#53 DCSS http://www.garlic.com/~lynn/2006m.html#54 DCSS part of the issue was that even tho xt/370 hard disk was single user, it used the xt hard disk which had 110ms access with block at a time ... (plus the latency communicating backforth between the 370 processor and cp/88 running on the pc processor). The combination of the significantly slower disk (vis-a-vis mainframe) and CMS being quite a bit more disk intensive (vis-a-vis applications developed for the PC environment) ... there was noticeable perception about poor performance. PAM offers a much better matchup between filesystem operations and virtual memory paradigm ... resulting in significant efficiencies (most ibm mainframe operating systems inherited filesystems that had a significant real memory and real i/o paradigm orientation). http://www.garlic.com/~lynn/subtopic.html#mmap CMS filesystem operations had diagnose I/O for pathlength reduction but continued to retain channel program (a real memory) orientation. I had done the precursor to CMS diagnose I/O as an undergraduate ... demonstrating significant pathlength reduction for CMS I/O intensive operation (which was sort of continuation of a lot of cp67 kernel pathlength operations I was already doing). The other place that PAM helped was minimizing real storage requirements for filesystem operations ... especially evident in environments with limited real storage configurations. Actually the CP kernel PAM infrastructure could dynamically adapt filesystem operations to the level of real storage contention and/or amount of real storage available. In one high-end (real mainframe) filesystem intensive benchmark, PAM demonstrated something like 300percent increased efficiency in filesystem operations (compared to highly optimized standard CMS EDF filesystem). XT/370 was significantly real memory contrained for lots of cms operations. I had done various performance analysis on pre-announce XT/370 washington boxes and found significant page thrashing. When the information was distributed, I got blaimed for delay in XT/370 announce and ship while they retrofitted the hardware with larger real storage. However, XT/370, being a single user system, saw no benefit from the extensive segment/page sharing capability available via PAM (especially compared to the limited capability offered thru the namesys/dcss method). http://www.garlic.com/~lynn/subtopic.html#adcon misc. past washington, xt/at/370 postings: http://www.garlic.com/~lynn/94.html#42 bloat http://www.garlic.com/~lynn/96.html#23 Old IBM's http://www.garlic.com/~lynn/2000.html#5 IBM XT/370 and AT/370 (was Re: Computer of the century) http://www.garlic.com/~lynn/2000.html#29 Operating systems, guest and actual http://www.garlic.com/~lynn/2000e.html#52 Why not an IBM zSeries workstation? http://www.garlic.com/~lynn/2000e.html#55 Why not an IBM zSeries workstation? http://www.garlic.com/~lynn/2001c.html#89 database (or b-tree) page sizes http://www.garlic.com/~lynn/2001f.html#28 IBM's VM for the PC c.1984?? http://www.garlic.com/~lynn/2001i.html#19 Very CISC Instuctions (Was: why the machine word size ...) http://www.garlic.com/~lynn/2001i.html#20 Very CISC Instuctions (Was: why the machine word size ...) http://www.garlic.com/~lynn/2001k.html#24 HP Compaq merger, here we go again. http://www.garlic.com/~lynn/2002b.html#43 IBM 5100 [Was: First DESKTOP Unix Box?] http://www.garlic.com/~lynn/2002b.html#45 IBM 5100 [Was: First DESKTOP Unix Box?] http://www.garlic.com/~lynn/2002d.html#4 IBM Mainframe at home http://www.garlic.com/~lynn/2002i.html#76 HONE was .. Hercules and System/390 - do we need it? http://www.garlic.com/~lynn/2003f.html#8 Alpha performance, why? http://www.garlic.com/~lynn/2003h.html#40 IBM system 370 http://www.garlic.com/~lynn/2004h.html#29 BLKSIZE question http://www.garlic.com/~lynn/2004m.html#7 Whatever happened to IBM's VM PC software? http://www.garlic.com/~lynn/2004m.html#10 Whatever happened to IBM's VM PC software? http://www.garlic.com/~lynn/2004m.html#11 Whatever happened to IBM's VM PC software? http://www.garlic.com/~lynn/2004m.html#13 Whatever happened to IBM's VM PC software? http://www.garlic.com/~lynn/2005f.html#6 Where should the type information be: in tags and descriptors http://www.garlic.com/~lynn/2005f.html#10 Where should the type information be: in tags and descriptors http://www.garlic.com/~lynn/2006.html#10 How to restore VMFPLC dumped files on z/VM V5.1 http://www.garlic.com/~lynn/2006f.html#2 using 3390 mod-9s http://www.garlic.com/~lynn/2006j.html#36 The Pankian Metaphor
amadeus
jim bohnsack wrote: Colin--I was thinking about Amadeus last week anyway. I am still shaking my head in disbelief that last week, 4 years ago, I was sitting there with job offers from Amadeus, MIT, and Cornell. I have always said that in 20 years I hope that I'm not sitting in a rocking chair in my nursing home saying that I should have taken the Amadeus job. Anne had done stint as chief architect on Amadeus long ago (still have hard copy of specification, 24apr87) ... however she backed going with x.25 ... contrary to a lot of SNA forces ... which got her replaced. However, Amadeus went with x.25 anyway. misc. past posts mentioning amadeus http://www.garlic.com/~lynn/2001g.html#49 Did ATT offer Unix to Digital Equipment in the 70s? http://www.garlic.com/~lynn/2001g.html#50 Did ATT offer Unix to Digital Equipment in the 70s? http://www.garlic.com/~lynn/2001h.html#76 Other oddball IBM System 360's ? http://www.garlic.com/~lynn/2003d.html#67 unix http://www.garlic.com/~lynn/2003n.html#47 What makes a mainframe a mainframe? http://www.garlic.com/~lynn/2004b.html#6 Mainframe not a good architecture for interactive workloads http://www.garlic.com/~lynn/2004b.html#7 Mainframe not a good architecture for interactive workloads http://www.garlic.com/~lynn/2004m.html#27 Shipwrecks http://www.garlic.com/~lynn/2004o.html#23 Demo: Things in Hierarchies (w/o RM/SQL) http://www.garlic.com/~lynn/2004o.html#29 Integer types for 128-bit addressing http://www.garlic.com/~lynn/2005f.html#22 System/360; Hardwired vs. Microcoded http://www.garlic.com/~lynn/2005p.html#8 EBCDIC to 6-bit and back
Re: virtual memory
[EMAIL PROTECTED] [EMAIL PROTECTED] writes: Was there an acronym/initialism for this COMMON area? My memory of doing junior-level systems work on MVS systems is telling me that there was one, but not what. ? common segment ... having started out as a 1mbyte shared segment in every address space. the hardware table look-aside buffers (TLBs) were STO (virtual address space) associative. the result was that there were unique entries for the same common segment entries from different virtual address spaces. in the early 80s, some of the high-end hardware started adding special TLB treatment for the MVS common segment ... so that there would only be one set of TLB entries for MVS common segment areas across all MVS address spaces. However, this references a bug when MVS was running as a virtual guest ... and a temporary fix ... pending availability of MVS APAR. Date: 18 February 1983, 12:30:13 EST From: Hi - the 'official' fix to the STBVR 0Cx abend problem is MVS APAR/ PTF OZ67587. I don't know if it's available yet. In the meantime, the zap works just fine. I'll send the zap following this note. //x JOB (6007,X003),,MSGLEVEL=1,MSGCLASS=O,CLASS=B, // REGION=1024K,NOTIFY=PREISM //ZAP EXEC PGM=AMASPZAP //SYSPRINT DD SYSOUT=* //SYSLIB DD DSN=SYS1.NUCLEUS,DISP=SHR,UNIT=3330,VOL=SER=D00126 ** ** FOR VM MVS GUEST, STBVR, TURN OFF USE OF COMMON SEGMENTS ** NAME IEAVNPX1 IEAVNPX1 VER 0DA2 96026003OI SGTCB=1 REP 0DA2 4700NOP VER 0DCE 96026003OI SGTCB=1 REP 0DCE 4700NOP // -- Anne Lynn Wheeler | http://www.garlic.com/~lynn/
Re: Code density and performance?
Peter Flass [EMAIL PROTECTED] writes: Don't know about HP, bit it's also IBM: http://www.research.ibm.com/journal/rd/483/heller.html re: http://www.garlic.com/~lynn/2006j.html#32 Code density and performance? the above journal artcile reference mentions 1997 for millicode. it mentions millicode being needed for (at least) sie and pr/sm. pr/sm was done about a decade earlier on 3090 (and was significantly more difficult in native microcode). this is a recent posting including email from jun81 mentioning sie effort for 3090 http://www.garlic.com/~lynn/2006j.html#27 virtual memory this mention of macrocode http://www.garlic.com/~lynn/2006b.html#38 blast from the past ... macrocode has piece of email from mar81 that mentions the (then) announced amdhal 5880 with macrocode (and used for hypervisor implementation). i had first started running into references regarding amdahl's work on macrocode the previous year (mar80). -- Anne Lynn Wheeler | http://www.garlic.com/~lynn/
Re: virtual memory
memory to 370/165 said that shared segment protect and a couple other features would cause an extra six month delay). a few past posts mentioning virtual memory retrofit to 370/165: http://www.garlic.com/~lynn/2006i.html#4 Mainframe vs. xSeries http://www.garlic.com/~lynn/2006i.html#9 Hadware Support for Protection Bits: what does it really mean? http://www.garlic.com/~lynn/2006i.html#23 Virtual memory implementation in S/370 as a result, the shared page protection had to redone as a hack to utilize the storage protect keys that had been carried over from 360. this required behind the scenes fiddling of the virtual machine architecture ... which prevented running cms with the virtual machine assist microcode activated (hardware directly implemented virtual machine execution of privilege instructions). later, in order to run cms virtual machines with the VMA microcode assist, protection was turned off. instead a scan of all shared pages was substituted that occured on every task switch. an application running in virtual address space could modify shared pages ... but the effect would be caught and discarded before task switch occured (so any modification wouldn't be apparent in other address spaces). this sort of worked running single processor configurations ... but got much worse in multi-processor configurations. now you had to have a unique set of shared pages specific to each real processor. past post mentioning the changed protection hack for cms http://www.garlic.com/~lynn/2006i.html#9 Hadware Support for Protection Bits: what does it really mean? http://www.garlic.com/~lynn/2006i.html#23 Virtual memory implementation in S/370 past posts mention pageable kernel work: http://www.garlic.com/~lynn/2001b.html#23 Linux IA-64 interrupts [was Re: Itanium benchmarks ...] http://www.garlic.com/~lynn/2001l.html#32 mainframe question http://www.garlic.com/~lynn/2002b.html#44 PDP-10 Archive migration plan http://www.garlic.com/~lynn/2002n.html#71 bps loader, was PLX http://www.garlic.com/~lynn/2002p.html#56 cost of crossing kernel/user boundary http://www.garlic.com/~lynn/2002p.html#64 cost of crossing kernel/user boundary http://www.garlic.com/~lynn/2003f.html#12 Alpha performance, why? http://www.garlic.com/~lynn/2003f.html#14 Alpha performance, why? http://www.garlic.com/~lynn/2003f.html#20 Alpha performance, why? http://www.garlic.com/~lynn/2003f.html#23 Alpha performance, why? http://www.garlic.com/~lynn/2003f.html#26 Alpha performance, why? http://www.garlic.com/~lynn/2003f.html#30 Alpha performance, why? http://www.garlic.com/~lynn/2003n.html#45 hung/zombie users ... long boring, wandering story http://www.garlic.com/~lynn/2004b.html#26 determining memory size http://www.garlic.com/~lynn/2004g.html#45 command line switches [Re: [REALLY OT!] Overuse of symbolic constants] http://www.garlic.com/~lynn/2004o.html#9 Integer types for 128-bit addressing http://www.garlic.com/~lynn/2005f.html#10 Where should the type information be: in tags and descriptors http://www.garlic.com/~lynn/2005f.html#16 Where should the type information be: in tags and descriptors http://www.garlic.com/~lynn/2006.html#35 Charging Time http://www.garlic.com/~lynn/2006.html#40 All Good Things -- Anne Lynn Wheeler | http://www.garlic.com/~lynn/
Re: virtual memory
now were in separate address space) to directly access the calling application's parameters in the application's virtual address space. The initial solution was something called a COMMON segment, a (again initially) 1mbyte area of every virtual address space where applications could stuff parameter values that they needed to be accessed by called subsystems, resident in other address spaces. Over time, as customer installations added a large variety of subsystems, it was unusual to find the COMMON segment taking up five megabytes. While these were MVS systems, with a unique 16mbyte virtual address space for every application, the kernel image was taking 8mbytes out of every virtual address space, and with a five megabyte COMMON area, that would leave a maximum of 3mbytes for application use (out of a 16mbyte virtual address space). Dual-address space mode was introduced in the late 70s with 3033 processor (to start to alleviate this problem caused by the extensive use of pointer passing paradigm). This provided virtual address space modes ... a subsystem (in its own virtual address space) could be called with a pointer to parameters in the application address space. The subsystem had facilities that allowed it to reach into other virtual address spaces. A call to one of these subsystems still required passing through the kernel to swap virtual address space pointers ... and some other gorp. recent mention of some connection between dual-address space and itanium http://www.garlic.com/~lynn/2006.html#39 What happens if CR's are directly changed? http://www.garlic.com/~lynn/2006b.html#28 Multiple address spaces Along the way there was a desire to move more of the operating system library stuff that resided as part of the application code. So dual-address space was generalized to multiple address space and a new hardware facility was created called program call. It was attempting to achieve the efficiency of branch-and-link instruction calling some library code with the structured protection mechanisms required to switch virtual address spaces by passing through priviledge kernel code. the privilege program call hardware table had a bunch of permission specification controls ... including which collection of virtual address space pointers could be moved into the various access registers. 31-bit virtual addressing was also introduced. today there are all sorts of combinations of 24-bit virtual addressing, 31-bit virtual addressing, 64-bit virtual addressing ... as well as possibly several such virtual address spaces be able to be accessed concurrently. 3.8 Address spaces ... some overview including discussion about multiple virtual address spaces: http://publibz.boulder.ibm.com/cgi-bin/bookmgr_OS390/BOOKS/DZ9AR004/3.8?SHELF=E Z2HW125DT=19970613131822 2.3.5 Access Registers ... discussion of access registers 1-15 can dissignate any address space http://publibz.boulder.ibm.com/cgi-bin/bookmgr_OS390/BOOKS/DZ9AR004/2.3.5?SHELF =EZ2HW125DT=19970613131822 10.26 Program Call http://publibz.boulder.ibm.com/cgi-bin/bookmgr_OS390/BOOKS/DZ9AR004/10.26?SHELF =EZ2HW125DT=19970613131822 10.27 Program Return http://publibz.boulder.ibm.com/cgi-bin/bookmgr_OS390/BOOKS/DZ9AR004/10.27?SHELF =EZ2HW125DT=19970613131822 10.28 Program Transfer http://publibz.boulder.ibm.com/cgi-bin/bookmgr_OS390/BOOKS/DZ9AR004/10.28?SHELF =EZ2HW125DT=19970613131822 -- Anne Lynn Wheeler | http://www.garlic.com/~lynn/
11may76, 30 years, (re-)release of resource manager
30 years since (re-)release of resource manager; some amount of the stuff i had done as an undergraduate in the 60s for cp67 ... but was dropped in the morph from cp67 to vm370. collected past posts mentioning the scheduler http://www.garlic.com/~lynn/subtopic.html#fairshare and page replacement http://www.garlic.com/~lynn/subtopic.html#wsclock misc. past posts mentioning the date for resource manager: http://www.garlic.com/~lynn/2001e.html#45 VM/370 Resource Manager http://www.garlic.com/~lynn/2001f.html#56 any 70's era supercomputers that ran as slow as today's supercomputers? http://www.garlic.com/~lynn/2006d.html#27 IBM 610 workstation computer http://www.garlic.com/~lynn/2006g.html#1 The Pankian Metaphor http://www.garlic.com/~lynn/2006h.html#7 The Pankian Metaphor http://www.garlic.com/~lynn/2006h.html#22 The Pankian Metaphor http://www.garlic.com/~lynn/2006h.html#25 The Pankian Metaphor http://www.garlic.com/~lynn/2006i.html#24 Virtual memory implementation in S/370 -- Anne Lynn Wheeler | http://www.garlic.com/~lynn/
Re: virtual memory
it unmanned http://www.garlic.com/~lynn/2004n.html#22 Shipwrecks http://www.garlic.com/~lynn/2004p.html#39 100% CPU is not always bad http://www.garlic.com/~lynn/2005h.html#13 Today's mainframe--anything to new? http://www.garlic.com/~lynn/2005k.html#53 Performance and Capacity Planning http://www.garlic.com/~lynn/2005n.html#29 Data communications over telegraph circuits -- Anne Lynn Wheeler | http://www.garlic.com/~lynn/
Virtual memory implementation in S/370 (a.f.c x-post)
http://www.garlic.com/~lynn/2004p.html#8 vm/370 smp support and shared segment protection hack http://www.garlic.com/~lynn/2004q.html#72 IUCV in VM/CMS http://www.garlic.com/~lynn/2005b.html#8 Relocating application architecture and compiler support http://www.garlic.com/~lynn/2005e.html#53 System/360; Hardwired vs. Microcoded http://www.garlic.com/~lynn/2005f.html#45 Moving assembler programs above the line http://www.garlic.com/~lynn/2005g.html#30 Moving assembler programs above the line http://www.garlic.com/~lynn/2005j.html#54 Q ALLOC PAGE vs. CP Q ALLOC vs ESAMAP http://www.garlic.com/~lynn/2005t.html#39 FULIST http://www.garlic.com/~lynn/2006.html#10 How to restore VMFPLC dumped files on z/VM V5.1 http://www.garlic.com/~lynn/2006.html#13 VM maclib reference http://www.garlic.com/~lynn/2006.html#17 {SPAM?} DCSS as SWAP disk for z/Linux http://www.garlic.com/~lynn/2006.html#18 DCSS as SWAP disk for z/Linux http://www.garlic.com/~lynn/2006.html#19 DCSS as SWAP disk for z/Linux http://www.garlic.com/~lynn/2006.html#25 DCSS as SWAP disk for z/Linux http://www.garlic.com/~lynn/2006.html#28 DCSS as SWAP disk for z/Linux http://www.garlic.com/~lynn/2006.html#31 Is VIO mandatory? http://www.garlic.com/~lynn/2006.html#35 Charging Time http://www.garlic.com/~lynn/2006b.html#4 IBM 610 workstation computer http://www.garlic.com/~lynn/2006b.html#7 Mount a tape http://www.garlic.com/~lynn/2006f.html#2 using 3390 mod-9s -- Anne Lynn Wheeler | http://www.garlic.com/~lynn/
Virtual memory implementation in S/370 (a.f.c x-post)
Marten Kemp [EMAIL PROTECTED] writes: The recent thread about virtual memory sparked a (kind of) idle question: why did the implementation in the S/370 have a two-level scheme (segment and page)? My original thought was that it facilitated definition of discontiguous parts of an address space. re: http://www.garlic.com/~lynn/2006i.html#22 virtual memory http://www.garlic.com/~lynn/2006i.html#23 Virtual memory implementation in S/370 i had also done page migration as well as table migration ... which were released in my resource manager product ... the blue letter product announcement gives product release as 11may76 ... 30 years ago tomorrow. partial reproduction of the resource manager blue letter: http://www.garlic.com/~lynn/2001e.html#45 VM/370 Resource Manager page migration would look make judgements about different speed paging devices ... and if it found high speed paging devices filling up, it would start looking for idle virtual pages (resident on high speed devices), that it could migrate to slower speed devices. when real storage started getting constrained ... it would also look for idle portions of virtual address spaces. each 64kbyte virtual segment consumed ten bytes of real storage, 2bytes for the page table entry and 8bytes of adminstrative stuff (shadow storage protect keys, and location on paging device for the virtual page). for idle segments, it would turn on the invalid bit in the segment table entry, write the administrative stuff to special disk locations, and then discard the real memory for the page table and administrative stuff ... typically picking up 160bytes of real storage per 64kbyte of idle virtual address space or 2560bytes of real storage per 1mbyte of idle virtual address space ... little over 4kbytes of real storage per 2mbytes of idle virtual address space. the defined virtual address space might or not be contiguous ... but the segment table could have large gaps in the pointers to page tables ... potentially because the space wasn't defined in the particular virtual address space ... or because the virtual address space area was deamed to be idle at the moment and the associated tables had been removed from real storage. the administrative table containing the disk backing store address for virtual pages (and the shadow storage protect keys) was called a SWAPTABLE ... so the feature allowing the SWAPTABLE to be removed from real storage was called SWAPTABLE migration or paging SWAPTABLEs. a few other posts mentioning SWAPTABLE migration: http://www.garlic.com/~lynn/2006.html#19 DCSS as SWAP disk for z/Linux http://www.garlic.com/~lynn/2006.html#25 DCSS as SWAP disk for z/Linux http://www.garlic.com/~lynn/2006.html#35 Charging Time http://www.garlic.com/~lynn/2006.html#36 Charging Time ... and a few posts mentioning shadowing process: http://www.garlic.com/~lynn/2005h.html#17 Exceptions at basic block boundaries http://www.garlic.com/~lynn/2005h.html#18 Exceptions at basic block boundaries http://www.garlic.com/~lynn/2006i.html#10 Hadware Support for Protection Bits: what does it really mean? -- Anne Lynn Wheeler | http://www.garlic.com/~lynn/