The following message is a courtesy copy of an article that has been posted to bit.listserv.ibm-main,alt.folklore.computers as well.
[EMAIL PROTECTED] writes: > When? I never considered IBM world and its batch environment > timesharing. Timesharing does not do large data processing tasks > well; and it's not supposed to. there were somewhat distinct, different environments ... one was commercial dataprocessing and the other was interactive computing and timesharing. the commercial, batch, production environment was oriented towards business dataprocessing ... it wasn't computing done on behalf of some specific person ... it was computing done on behalf of some business operation ... like the organizations payroll and printing checks. the requirement was that the business dataprocessing be done ... frequently on very determined scheduled ... independent of any specific person. over time, there was lots of batch technology evolved to guarentee that specific operations could be done reliably, predictably, and deterministicly independent of any human involvement. much of the interactive and virtual machine paradigm evolved totally independently at the science center ... first with cp40/cms, morphing into cp67/cms, followed by vm370/cms (even tho during the 70s, the batch infrastructure and the timesharing infastructure shared a common 370 hardware platform): http://www.garlic.com/~lynn/subtopic.html#545tech both multics (on the 5th flr) and science center (on the 4th flr) could trace common heritage back to ctss (and unix traces some heritage back to multics). even tho there was a relatively large timesharing install base (in most cases larger than any other vendor's timesharing install base that might be more commonly associated with timesharing) ... in the period, it was dwarfed by the commerical batch install base. I've joked before that at one period, the installed commercial customer install base was much larger than the timesharing customer install base, and the timesharing customer install base was much larger than the timesharing internal install base, and the timesharing internal install base was much larger than the internal installations that I directly supported (built, distributed, fixed bugs, on highly customized/modified kernel and services). However, at one point the number of internal installations that I directly supported was as large as the total number of Multics installations that ever existed. lots of past posts mentioning the timesharing environment http://www.garlic.com/~lynn/subtopic.html#timeshare much of that timesharing install base was cms personal computing ... while other was mixed-mode operation with cms personal computing and other kinds of operating systems in virtual machines ... aka the same timesharing infrastructure supporting both interactive cms personal computing as well as production (frequently batch) guest operating systems. this required a timesharing dispatching/scheduling policy infrastructure that could support a broad range of requirements. for a little topic drift, slightly related recent post: http://www.garlic.com/~lynn/2007m.html#46 Rate Monotonic scheduling (RMS) vs. OS Scheduling also coming out of the science center in the period (besides virtual machines, a lot of timesharing and interactive/personal computer) ... somewhat reflecting the timesharing and personal computing orientation was much of the internal networking technology http://www.garlic.com/~lynn/subnetwork.html#internalnet as well as things like the invention of GML, precusor to SGML, HTML, XML, etc http://www.garlic.com/~lynn/subtopic.html#sgml with the advent of PCs ... a lot of the cms personal computing migrated to PCs ... although the (mainframe) virtual machine operating system continues to survive ... and even had seen some resurgent in the early part of this decade supporting large numbers of virtual machines running linux ... somewhat in the "server consolidation" market segment recently, "server consolidation" has become something of a more widely recognized buzzword ... pushing a combination of virtual machine capability migrated to PC hardware platforms possibly in combination with large BLADE form-factors farms ... where a business with hundreds, thousands, or even tens of thousands of servers are consolidating into much smaller space. Microsoft Looks to Stop Internal Server Sprawl http://www.computerworld.com/action/article.do?command=viewArticleBasic&articleId=296360 from above: The profile of Microsoft Corp.’s in-house server farm is similar to those of many other companies: one application per server, with less than 20% peak server utilization on average. But Devin Murray, Microsoft’s group manager of utility services, is working to change that. Murray’s team manages about 17,000 servers that support 40,000 of Microsoft’s end users worldwide. ... snip ... ---------------------------------------------------------------------- For IBM-MAIN subscribe / signoff / archive access instructions, send email to [EMAIL PROTECTED] with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html
