List of Archived Posts

2012 Newsgroup Postings (08/18 - 09/10)

Quelle Surprise! SEC Plans to Make the World Safer for Fraudsters, Push Through JOBS Act Con-Artist-Friendly Solicitation Rules
Time to choose the Knights of 2012
Cultural attitudes towards failure
Did Bill Gates Steal the Heart of DOS?
Auditors Don't Know Squat!
Cultural attitudes towards failure
Some fun with IBM acronyms and jargon (was Re: Auditors Don't Know Squat!)
More Evidence Wall Street is Overpaid
"execs" or "scripts"
"execs" or "scripts"
Cultural attitudes towards failure
This Award Winning British Speed Boat May Be Iran's Fiercest Weapon Against The US Navy
First Battle: Operation Starlite and the Beginning of the Blood Debt in Vietnam
Cultural attitudes towards failure
The growing openness of an organization's infrastructure has greatly impacted security landscape
"execs" or "scripts"
X86 server
Cultural attitudes towards failure
X86 server
X86 server
X86 server
"execs" or "scripts"
"execs" or "scripts"
PDP-10 system calls, was 1132 printer history
"execs" or "scripts"
X86 server
PDP-10 system calls, was 1132 printer history
PDP-10 system calls, was 1132 printer history
X86 server
X86 server
X86 server
X86 server
Use another browser - Kaspersky follows suit
Interesting News Article
X86 server
PDP-10 system calls, was 1132 printer history
PDP-10 system calls, was 1132 printer history
S/360 architecture, was PDP-10 system calls
S/360 architecture, was PDP-10 system calls
The IBM zEnterprise EC12 announcment
PDP-10 system calls, was 1132 printer history
The IBM zEnterprise EC12 announcment
I.B.M. Mainframe Evolves to Serve the Digital World
Judge dismisses BancorpSouth defense in online theft suit
Preparing for War with China
Introducing John Boyd
Boyd and the U.S. Navy's Return to History
I.B.M. Mainframe Evolves to Serve the Digital World
The Payoff: Why Wall Street Always Wins
Too true to be funny - 51% of the surveyed Americans think that stormy we
Arming for the Navy's Return to History
Turn Off Another Light - Univ. of Tennessee
I.B.M. Mainframe Evolves to Serve the Digital World
CALCULATORS
Singer Cartons of Punch Cards
CALCULATORS
Blades versus z was Re: Turn Off Another Light - Univ. of Tennessee
Blades versus z was Re: Turn Off Another Light - Univ. of Tennessee
Singer Cartons of Punch Cards
Blades versus z was Re: Turn Off Another Light - Univ. of Tennessee
Singer Cartons of Punch Cards
Singer Cartons of Punch Cards
Singer Cartons of Punch Cards
Singer Cartons of Punch Cards
Singer Cartons of Punch Cards
Singer Cartons of Punch Cards
Singer Cartons of Punch Cards
Strings (hijacked from: The IBM zEnterprise EC12 announcment)
Singer Cartons of Punch Cards
Cultural attitudes towards failure
Blades versus z was Re: Turn Off Another Light - Univ. of Tennessee
Strings (hijacked from: The IBM zEnterprise EC12 announcment)
zEC12, and previous generations, "why?" type question - GPU computing
PDP-10 system calls, was 1132 printer history
zEC12, and previous generations, "why?" type question - GPU computing
PDP-10 system calls, was 1132 printer history
PDP-10 system calls, was 1132 printer history
zEC12, and previous generations, "why?" type question - GPU computing
PDP-10 system calls, was 1132 printer history
zEC12, and previous generations, "why?" type question - GPU computing
PDP-10 system calls, was 1132 printer history
Blades versus z was Re: Turn Off Another Light - Univ. of Tennessee
zEC12, and previous generations, "why?" type question - GPU computing
IBM's z12 mainframe engine makes each clock count
72 column cards
Singer Cartons of Punch Cards
Etymology of APAR
Blades versus z was Re: Turn Off Another Light - Univ. of Tennessee
Blades versus z was Re: Turn Off Another Light - Univ. of Tennessee
PDP-10 system calls, was 1132 printer history
Blades versus z was Re: Turn Off Another Light - Univ. of Tennessee
Difference between fingerspitzengefuhl and Coup d'oeil?
What if practices rather than ideas are the main sources of innovation?
PDP-10 system calls, was 1132 printer history
PDP-10 system calls, was 1132 printer history
PDP-10 system calls, was 1132 printer history
PDP-10 system calls, was 1132 printer history
What a Caveman Can Teach You About Strategy
PDP-10 system calls, was 1132 printer history
PDP-10 system calls, was 1132 printer history
Blades versus z was Re: Turn Off Another Light - Univ. of Tennessee

Quelle Surprise! SEC Plans to Make the World Safer for Fraudsters, Push Through JOBS Act Con-Artist-Friendly Solicitation Rules

Refed: **, - **, - **, - **
From: lynn@garlic.com (Lynn Wheeler)
Date: 18 Aug, 2012
Subject: Quelle Surprise! SEC Plans to Make the World Safer for Fraudsters, Push Through JOBS Act Con-Artist-Friendly Solicitation Rules
Blog: Financial Crime Risk, Fraud and Security
Quelle Surprise! SEC Plans to Make the World Safer for Fraudsters, Push Through JOBS Act Con-Artist-Friendly Solicitation Rules
http://www.nakedcapitalism.com/2012/08/quelle-surprise-sec-plans-to-make-the-world-safer-for-fraudsters-push-through-jobs-act-con-artist-friendly-solicitation-rules.html

mentions SEC not using Sarbanes-Oxley. note ... apparently even GAO didn't believe SEC was doing anything and started doing reports of public company fraudulent financial filings (even showing uptic after SOX). In theory, under SOX, all the executives would be doing jail time.
http://www.gao.gov/products/GAO-03-395R .
http://www.gao.gov/products/GAO-06-678 .
https://www.gao.gov/products/gao-06-1079sp

Note Sarbanes-Oxley was passed in the wake of ENRON & Worldcom ... claims that it would prevent something similar from ever happening again. However, there were jokes at the time that the only effect would be increased business for auditors and wouldn't actual (since it required action on the part of SEC). More recently seen on the internet
ENRON was dry run and worked so well that it has become institutionalized

There were also comments at the time that possibly the only part of SOX was the stuff supporting whistle-blowers ... but that would also require SEC to do something. In the congressional hearings into Madoff ... the person that had tried unsuccessful for a decade to get SEC to do something about Madoff (SEC was finally forced to do something when he turned himself in), testified that tips (whistle-blowers) turn up 13 times more fraud than audits. Also that SEC has no "tip" line but has a 1-800 number for corporations to complain about audits.

... and then there is this (from year ago): SEC Whistleblower: Feds Destroyed Evidence Of Thousands Of Wall Streets' Worst Crimes
http://blog.alexanderhiggins.com/2011/08/17/sec-whistleblower-feds-destroyed-evidence-thousands-wall-streets-worst-crimes-60321/

Time to choose the Knights of 2012

Refed: **, - **, - **, - **, - **, - **
From: lynn@garlic.com (Lynn Wheeler)
Date: 18 Aug, 2012
Subject: Time to choose the Knights of 2012
Blog: Order of Knights of VM
The precursor was TOOLSRUN on the ibm internal network starting in the early 80s. It could operate in both usenet news-like mode as well in mailing list mode. I had been blamed for online computer conferencing on the internal network (larger than arpanet/internet from just about the beginning until late '85 or early '86). Folklore is that when the executive committee was told about computer conferencing (and the internal network), 5of6 wanted to fire me. I had been doing semi-automated stuff ... but then the corporation launched investigations into the activity. One of the results was TOOLSRUN and officially sanctioned newsgroups/discussion (with moderation).

Reference from IBM Jargon:
Tandem Memos - n. Something constructive but hard to control; a fresh of breath air (sic). That's another Tandem Memos. A phrase to worry middle management. It refers to the computer-based conference (widely distributed in 1981) in which many technical personnel expressed dissatisfaction with the tools available to them at that time, and also constructively criticized the way products were [are] developed. The memos are required reading for anyone with a serious interest in quality products. If you have not seen the memos, try reading the November 1981 Datamation summary.

... snip ...

BITNET (& EARN in europe) was univ. network using technology similar to that used for the internal network. misc. past posts mentioning internal network
https://www.garlic.com/~lynn/subnetwork.html#internalnet
misc. past posts mentioning bitnet (&/or EARN)
https://www.garlic.com/~lynn/subnetwork.html#bitnet

old email from person that got tasked with setting up EARN in europe:
https://www.garlic.com/~lynn/2001h.html#email840320

somewhere along the way, after the investigations into computer conferencing ... TOOLSRUN was pressed into service for the officially sanctioned and moderated news/discussion groups.

I was then doing HSDT internally (T1 & faster links) ... and working on speeding operations. T1 full-duplex was 300kbyte/sec sustained ... and I figured I needed ten times that throughput. misc. past posts mentioning hsdt
https://www.garlic.com/~lynn/subnetwork.html#hsdt

One of the things to get that throughput (for vnet/rscs) was rewrite vm370 spool in vs/pascal running in a virtual machine (some slight of hand to make it faster than assembler that ran supervisor in the vm370 kernel) ... supported contiguous allocation, multiblock read/writes ... and a psuedo asynchronous interface. Normal spool was 4k block serialized synchronous and under loaded system vnet/rscs might be lucky to get 4-8 4k blocks per second (maybe 30kbytes/sec instead of 3mbytes/sec).

Somewhere along the way somebody had introduced bug in vnet/rscs driver in the compression code that eliminated S&F no-op records. For high-speed links, compression was less thruput than no-compression... so I turned that off also ... and all of a sudden S&F no-op records re-appeared.

That got me into something of a *war* with the internal *owner* of TOOSLRUN at the time ... since TOOLSRUN started rejecting traffic that had the re-appeared S&F no-op records. I provided the fixes to TOOLSRUN to correctly handle the re-appeared, multiple S&F no-op records ... but there was a lot of resistance since initially nearly all the internal VNET/RSCS drivers had the *bug*.

I tried to get lots of the changes ... at least into the official internal network *backbone* machines ... but by that time, the communication group was starting to do heavy misinformation/lobbying to get the internal network converted SNA/VTAM. some old email on the issue:
https://www.garlic.com/~lynn/2006x.html#email870302 .
https://www.garlic.com/~lynn/2011.html#email870306 .

It was somewhat easier fixing the vm370 TCP/IP stack ... initially it had approx. 44kbytes/sec using nearly whole 3090 processor. I did the enhancements for RFC1044 support and in some testing at Cray research got 4341 channel speed between 4341 & Cray machine ... using only modest amount of 4341 processor.

whether or not you used the diagnose or CCWs ... the operations translated into a serialized synchronous 4k spool operation (effectively using path into the side of the paging system). large number of CCWs could cut down on processor overhead but couldn't get around the serialized synchronized 4k at a time (number of 4k byte spool records per second).

for rewrite running in virtual machine ... I provided up/down calls between the cp kernel into the spool virtual machine. for rscs/vnet driver provided a new fastpath going for 3mbyte/sec sustained thruput (for one thing, I couldn't have the rscs/vnet virtual machine disabled/non-executable while waiting for each 4k spool read/write.).

One of the things with RSCS was it layered the infrastructure ... and had lots of drivers to different infrastructures ... distinctly different than JES2/NJI. NJI had so jumbled its implementation that different releases of JES2 exchanging traffic would result in failure and bringing down the associated MVS system. As a result internally, a large library of NJI drivers evolved that were responsible for converting to canonical NJI format ... and then the specific RSCS NJI driver was started that corresponded to JES2 release it was directly talking to (and responsible for converting NJI header to format expected by that specific JES2). By the mid-80s, they had stopped shipping native RSCS drivers to customers and customers only got the NJI drivers (although native RSCS drivers continued to be used internally because they were more efficient and had higher throughput).

There was the infamous internal network incident where San Jose JES2 system resulted in MVS system in Hursley crashing. They eventually blamed it on the RSCS system in Hursley failing to start the specific NJI driver that would have reformated the NJI header for the Hursley JES2 system (and prevented MVS from crashing) ... nobody thought to blame JES2 for having a bad design.

--
virtualization experience starting Jan1968, online at home since Mar1970

Cultural attitudes towards failure

Refed: **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **
From: lynn@garlic.com (Lynn Wheeler)
Date: 18 Aug, 2012
Subject: Cultural attitudes towards failure.
Blog: Boyd Strategy
re:
http://lnkd.in/9q5Zvq
and
https://www.garlic.com/~lynn/2012k.html#87 Cultural attitudes towards failure

First have to assume that the agenda of those at the top and the interests of the organization are aligned. In the current corporate culture ... there are enormous instances where it is mis-aligned. A frequent theme is that the "C" executives are there for only short period and looking to soak the organization for as much as they can. A frequent & typical scenario was a decade ago a large manufacturing corporation had majority of the bottom line coming from financial services unit. The CFO was scheduled to depart and orchestrated the sale of the financial unit just before leaving. This represented long-term downside for the corporation bottom line ... but the CFO got a percent of the sale.

Note that article is by someone that worked closely with boyd over number of years
http://chuckspinney.blogspot.com/p/domestic-roots-of-perpetual-war.html

a similar article from long ago and far away (behind paywall but mostly lives free at wayback machine ... except for pg8?)
https://web.archive.org/web/20070320170523/http://www.time.com/time/magazine/article/0,9171,953733,00.html
also
https://content.time.com/time/magazine/article/0,9171,953733,00.html

Boyd would tell stories how SECDEF blamed Boyd for the article (and tried to have him banned from the pentagon).

similar comments (much later, if anything, things had gotten a lot worse) in preamble to tribute to Boyd
http://radio-weblogs.com/0107127/stories/2002/12/23/genghisJohnChuckSpinneysBioOfJohnBoyd.html

one of his Boyd quotes:
Pentagon say the Pentagon does not have a strategy. They are wrong. The Pentagon does have a strategy; it is: "Don't interrupt the money flow, add to it."

mistype, one of his Boyd quotes:
People say the Pentagon does not have a strategy. They are wrong. The Pentagon does have a strategy; it is: "Don't interrupt the money flow, add to it."

The reference
http://chuckspinney.blogspot.com/p/domestic-roots-of-perpetual-war.html

continues here and starts out with the above Boyd quote:
http://www.challengemagazine.com/extra/054_069.pdf

There are two different Boyd issues/warnings here:

• ww2 military officers were indoctrinated in rigid, top-down, command&control structure ... after ww2 lots of those officers returned to civilian life and carried with them a culture of rigid, top-down, command&control ... starting to contaminate all aspects of US culture (not just military and corporations doing business with military ... but also corporations having nothing to do with the military ... as well as many other organizations). That represents a general cultural contamination

• US military has had a 2nd generation warfare that heavily relies on strategy of overwhelming resources along with enormous industrial operation supporting the military. Once created, this represents a very large and very hungry beast that wants to be continuously feed ... even during periods when it is not needed. Eisenhower warned about it ... it never wants to reduce the amount that it is taking in ... it prefers to have it always increased ... even if it has to fabricate justifications for the funding. This is Boyd's quote regarding Pentagon strategy ... funding is always the number one thing.

The rigid, top-down, command&control contamination leaking out into all aspects of American culture ... is separate from the creation of the MICC beast that has a primary strategy of ever increasing amounts of funding.

Boyd's comments about the contamination spreading into American culture predates the modern internet (early 80s). The spinney(/boyd) time 1983 article on ill-considered spending and Eisenhower's warning about MICC predate the modern internet.

The culture of rigid, top-down, command&control was bringing down US competitiveness ... and the every hungry MICC (military, industrial, congressional complex ... references Eisenhower was originally going to say but shortened it at the last minute) had an aligned strategy to never stop the flow of funds ... even fabricating reasons while it always needed to be increased.

tcp/ip is the technology basis for the modern internet, NSFNET backbone was the operational basis for the modern internet and CIX was the business basis for the modern internet. arpanet converted to internetworking protocol on 1jan1983 ... at that time arpanet had reach approx. 100 IMP network nodes and around 250 connected hosts (by comparison the internal network ... which had been larger than the arpanet from just about the beginning, was rapidly approaching 1000).

NSFNET backbone started out as part of congressional NSF funding for supercomputing centers ... to maintain US competitive position ... with high-speed network connecting all the NSF supercomputers (and providing interconnection for the TCP/IP infrastructure in the regions around the centers). Started out the director of NSF was going to give me $20M to build the network. Congress then cut the budget before I got the money ... along with internal corporate politics kicked in ... that wanted to take it over. The director of NSF wrote the company a letter 3Apr1986, NSF Director to IBM Chief Scientist and IBM Senior VP and director of Research, copying IBM CEO),, but that just made the internal politics worse (comments like what I already had running internally being at least five years ahead of all submitted proposals, also made internal politics worse).

--
virtualization experience starting Jan1968, online at home since Mar1970

Did Bill Gates Steal the Heart of DOS?

From: lynn@garlic.com (Lynn Wheeler)
Date: 19 Aug, 2012
Subject: Did Bill Gates Steal the Heart of DOS?
Blog: Old Geeks
re:
http://lnkd.in/f5VFnb
and
https://www.garlic.com/~lynn/2012k.html#84 Did Bill Gates Steal the Heart of DOS?
https://www.garlic.com/~lynn/2012k.html#94 Did Bill Gates Steal the Heart of DOS?

Originally 8in floppy invented (by Shugart) for use to load software for the 3830 disk controller ... was also used for loading microcode for the 370. Consumers weren't exposed to it ... was purely inside the machine dealt with by maintenance engineers. Then found its way into other products
https://en.wikipedia.org/wiki/History_of_the_floppy_disk

Lots of engineers hired away from san Jose starting at the end of the 60s.
https://en.wikipedia.org/wiki/Alan_Shugart

I transferred from the cambridge science center to san jose research in '77. They would let me wander around the plant site and play disk engineer in bldgs. 14&15. Increasingly I would get con'ed into doing stuff ... including being requested to be on conference calls with the POK channel engineers. One of the explanations was that lots of the san jose institutional knowledge about channels was with the senior engineers that had been hired away by the mid-70s.

Early 80s, my brother was regional marketing rep for Apple (largest physical area in conus). I would get to attend business dinners with him when he was in town. I remember arguing design of MAC with the engineers at dinner (before MAC was announced).

--
virtualization experience starting Jan1968, online at home since Mar1970

Auditors Don't Know Squat!

From: lynn@GARLIC.COM (Anne & Lynn Wheeler)
Subject: Re: Auditors Don't Know Squat!
Newsgroups: bit.listserv.ibm-main
Date: 19 Aug 2012 12:08:28 -0700
shmuel+gen@PATRIOT.NET (Shmuel Metz , Seymour J.) writes:
Why didn't they preserve what they needed for their own use and deliver the stuff they would have otherwise thrown out to the DOJ?

re:
https://www.garlic.com/~lynn/2012k.html#89 Auditors Don't Know Squat!
https://www.garlic.com/~lynn/2012k.html#90 Auditors Don't Know Squat!

old post here from 2010
https://www.garlic.com/~lynn/2010e.html#7 Need tool to zap core

after they filled basement and storage ... pok was consuming offices at rate of something like five/week for document retention

... then scheduling freight trains with loaded boxcars filled with paper for DOJ.

earlier post on the subject
https://www.garlic.com/~lynn/2009m.html#1 Does this count as 'computer' folklore?

--
virtualization experience starting Jan1968, online at home since Mar1970

Cultural attitudes towards failure

Refed: **, - **, - **, - **, - **, - **, - **, - **, - **, - **
From: lynn@garlic.com (Lynn Wheeler)
Date: 20 Aug, 2012
Subject: Cultural attitudes towards failure.
Blog: Boyd Strategy
re:
http://lnkd.in/9q5Zvq
and
https://www.garlic.com/~lynn/2012k.html#87 Cultural attitudes towards failure
https://www.garlic.com/~lynn/2012l.html#2 Cultural attitudes towards failure

so the traditional is "not to be afraid of failure"; aka, "if you have never failed, you have never attempted anything new"

large parts of MICC perpetuates "risk adverse" because they don't want blemishes on their record and "perpetual war" as means of keeping funds flowing ("risk adverse" and failing to adapt helps with "perpetual war"); Success Of Failure culture is at the organizational level as part of keeping the funds flowing ... avoiding actually holding accountable those responsible

part of Boyd's "people first" can be ascribed to the extensive list of MICC high-priced failed technology efforts, frequently obfuscated behind "there are always failures, when attempting something new" (skimming enormous profits off of technology efforts has been institutionalized in MICC).

couldn't resist

How Drones Can Reinforce Failure (also by Spinney)
http://nation.time.com/2012/08/20/how-drones-reinforce-failure/

from above:
This disconnects the entire decision process from reality, because Orientation is the analytic/synthetic activity in the mind that makes sense out of the Observations, including the feedback on a strike's effectiveness. The disconnect of Observations from Reality allows preconceptions and belief systems to hijack the synthetic function of Orientation.

... snip ...

--
virtualization experience starting Jan1968, online at home since Mar1970

Some fun with IBM acronyms and jargon (was Re: Auditors Don't Know Squat!)

Refed: **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **
From: lynn@GARLIC.COM (Anne & Lynn Wheeler)
Subject: Re: Some fun with IBM acronyms and jargon (was Re: Auditors Don't Know Squat!)
Newsgroups: bit.listserv.ibm-main
Date: 20 Aug 2012 09:33:08 -0700
rreynolds@CIX.CO.UK (Rupert Reynolds) writes:
Does anyone have a copy of the old JARGON FILE that buzzed around the IBM VM network in the '90s when i was working in Portsmouth North Harbour? I'd love to see it again. I think it included discussion of Bubblegum vs. Boeblingen.

i have few different versions done over the years ... but there are also a few on the web.

1st url using search engine
http://www.comlay.net/ibmjarg.pdf

mentioned here
https://en.wikipedia.org/wiki/Mike_Cowlishaw

in the early 80s, we modified the vm/rscs 6670 print driver (ibm copier3 with computer interface, distributed around departmental areas) to randomly select "sayings" to help fill up the blanks on the separator page (i.e. alternate paper drawer filled with colored paper). One of the files of "sayings" was the ibmjargon file

Ran into problem with security auditors one year. I (and others) had introduced a number of "demo" programs (aka *games* by any other name, I brought in *adventure* inside ibm) and were maintaining growing large library of demos. Corporate was having For Business Purposes Only added to the vm370 logon screen ... and the security auditors claimed that the demo programs had to all be removed since they weren't for *business purposes*. It turns out we had gotten local change so that the logon screen had For Management Approved Uses Only and had gotten signoff on demo programs.

The security auditors were starting to feel like there was open conflict with what they had been instructed from corporate. One evening as they were doing after hours sweeps looking for unsecured classified material ... including classified prints-out left on 6670 departmental printers ... they came across print-out that had the following on the separator page.
[Business Maxims:] Signs, real and imagined, which belong on the walls of the nation's offices:
1) Never Try to Teach a Pig to Sing; It Wastes Your Time and It Annoys the Pig.
2) Sometimes the Crowd IS Right.
3) Auditors Are the People Who Go in After the War Is Lost and Bayonet the Wounded.
4) To Err Is Human -- To Forgive Is Not Company Policy.


... and they attempted to escalate to top executives that we did it on purpose ... attempting to ridicule them.

this is also about the time that I had first sponsored Col Boyd's briefings at IBM. I first attempted to do it employee education and they initially agreed. However, as I provided more information, they changed their mind, suggesting I restrict the audience to just senior members of competitive analysis departments. They explained that the corporation spends a large amount of money training managers on how to deal with employees, and they were afraid that exposing general employees to Boyd would be counter productive.

in the mid-80s, doing the vm tcpip interface ... i also converted the 6670 files into "zippy" format ... i.e. randomly select sayings for email signature line.

--
virtualization experience starting Jan1968, online at home since Mar1970

More Evidence Wall Street is Overpaid

Refed: **, - **, - **
From: lynn@garlic.com (Lynn Wheeler)
Date: 22 Aug, 2012
Subject: More Evidence Wall Street is Overpaid
Blog: Google+
re:
https://plus.google.com/u/0/102794881687002297268/posts/ChprA7sxRnS

More Evidence Wall Street is Overpaid
http://www.rollingstone.com/politics/blogs/taibblog/more-evidence-wall-street-is-overpaid-20120821

aka not pursuit of better pie but getting bigger piece of existing pie ...

The Price of Inequality: How Today's Divided Society Endangers Our Future (Joseph E. Stiglitz) pg35/loc1169-73
In business school we teach students how to recognize, and create, barriers to competition -- including barriers to entry -- that help ensure that profits won't be eroded. Indeed, as we shall shortly see, some of the most important innovations in business in the last three decades have centered not on making the economy more efficient but on how better to ensure monopoly power or how better to circumvent government regulations intended to align social returns and private rewards.

Freefall: America, Free Markets, and the Sinking of the World Economy (Joseph E. Stiglitz) pg271/loc5101-4
Standard economic theory (the neoclassical model discussed earlier in this chapter) has had little to say about innovation, even though most of the increases in U.S. standards of living in the past hundred years have come from technical progress.56 As I noted earlier, just as "information" was outside the old models, so too was innovation

--
virtualization experience starting Jan1968, online at home since Mar1970

"execs" or "scripts"

Refed: **, - **, - **, - **, - **, - **
From: Anne & Lynn Wheeler <lynn@garlic.com>
Subject: Re: "execs" or "scripts"
Newsgroups: comp.lang.rexx
Date: Tue, 21 Aug 2012 13:10:44 -0400
Jennifer Murphy <JenMurphy@jm.invalid> writes:
I notice that most people call the Rexx routines "scripts". I come from an old VM/CMS and MVS/TSO world where they were called "execs". I have to admit that "scripts" kinda grates on my ears (eyes?) a bit.

Is "script" the generally accepted terminology?


EXEC was command, EXEC was the filetype for command files in CMS. was RUNCOM on ctss
https://en.wikipedia.org/wiki/Compatible_Time-Sharing_System

open systems and terminal emulators have had command scripts and terminal scripts.

some of the ctss people went to the science center on the 4th flr and did virtual machines, cp67/cms (which later morphs into vm370/cms) and bunch of other stuff ... other ctss people went to project mac on the 5th floor for multics.

mid-60s, the ctss "runoff" document formater was ported to CMS at the science center and called script. then GML is invented at the science center in 1969, support for GML tag processing was added to the script command. the use of "script" for document formating then created conflict later when script came into use for command & terminal scripting.
https://en.wikipedia.org/wiki/SCRIPT_%28markup%29

as in above references ... CTSS inspired much in cp67/cms (and later vm370/cms) as well as inspired much in MULTICS ... which then inspired unix.

this has person that wrote EXEC for cp/cms (in 1966) ... is also the person that did cp/cms "script" (RUNOFF) document formater.
https://en.wikipedia.org/wiki/Scripting_language

between EXEC for CMS (from 1966) and REX for CMS (later changed to REXX for product release) in 1979 ... there was also EXEC2.
https://en.wikipedia.org/wiki/REXX

other trivia, a decade after GML was invented at the science center, it morphs into international standard SGML. After another decade, it morphs into HTML (at cern);
http://infomesh.net/html/history/early/

--
virtualization experience starting Jan1968, online at home since Mar1970

"execs" or "scripts"

Refed: **, - **, - **, - **, - **, - **, - **
From: Anne & Lynn Wheeler <lynn@garlic.com>
Subject: Re: "execs" or "scripts"
Newsgroups: comp.lang.rexx
Date: Tue, 21 Aug 2012 13:17:10 -0400
LesK <5mre20@tampabay.rr.com> writes:
I agree with both of you. My background was VM/CMS also. Trouble is that 'execs' comes from the CMS filetype EXEC, but Windows has a .exe which is entirely different, being what we would think of as a MODULE, so their can be some confusion.

I don't much like the use of 'script' when referring to Rexx code. To me it implies a simplicity that isn't appropriate to Rexx ("The HelpDesk person was following a script."). I simply call my code a program' and leave it at that.


re:
https://www.garlic.com/~lynn/2012l.html#8 "execs" or "scripts"

before windows there was ms-dos
https://en.wikipedia.org/wiki/MS-DOS
before ms-dos there was seattle computer
https://en.wikipedia.org/wiki/Seattle_Computer_Products
before seattle computer there was cp/m
https://en.wikipedia.org/wiki/CP/M

and before cp/m, kildall worked on cp/67 (cms) at npg (gone 404, but lives on at the wayback machine)
https://web.archive.org/web/20071011100440/http://www.khet.net/gmc/docs/museum/en_cpmName.html

discussed some more in this recent (linkedin) "Old Geeks" discussion
https://www.garlic.com/~lynn/2012k.html#84 Did Bill Gates Steal the Heart of DOS?
https://www.garlic.com/~lynn/2012k.html#94 Did Bill Gates Steal the Heart of DOS?
https://www.garlic.com/~lynn/2012l.html#3 Did Bill Gates Steal the Heart of DOS?

--
virtualization experience starting Jan1968, online at home since Mar1970

Cultural attitudes towards failure

Refed: **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **
From: lynn@garlic.com (Lynn Wheeler)
Date: 21 Aug, 2012
Subject: Cultural attitudes towards failure.
Blog: Boyd Strategy
re:
http://lnkd.in/9q5Zvq
and
https://www.garlic.com/~lynn/2012k.html#87 Cultural attitudes towards failure
https://www.garlic.com/~lynn/2012l.html#2 Cultural attitudes towards failure
https://www.garlic.com/~lynn/2012l.html#5 Cultural attitudes towards failure

more on Boyd's military corruption of corporate America

The Price of Inequality: How Today's Divided Society Endangers Our Future (Joseph E. Stiglitz) pg35/loc1169-73
In business school we teach students how to recognize, and create, barriers to competition -- including barriers to entry -- that help ensure that profits won't be eroded. Indeed, as we shall shortly see, some of the most important innovations in business in the last three decades have centered not on making the economy more efficient but on how better to ensure monopoly power or how better to circumvent government regulations intended to align social returns and private rewards.

...

recent item on Google+ on corporate protect/hide ... although possibly not quite what you think
https://plus.google.com/u/0/102794881687002297268/posts/YmgKgwa7R8Q

U.S. Boardrooms Wake Up to Data Security; Corporate America says data security is now the main concern in the boardroom when it comes to legal considerations.
http://www.cio.com/article/714292/U.S._Boardrooms_Wake_Up_to_Data_Security

we were tangentially involved in cal. state data breach notification law. in depth consumer surveys that #1 issue was identity theft, in large part fraudulent transactions as result of data breaches. nothing seemed to be done about it and it was hoped that publicity from notifications might motivate corrective actions. Major issue is normally security measures are done for self-protection. the breaches weren't a threat to the institutions but to their customers ... so there was no motivation.

IBM had a competitive data protection circa 1980. It was suing a company (that made compatible computer products) for several billion over theft of proprietary information (next generation disk design). Judge used the "swimming pool" attractive nuisance analogy; nobody could be expected not to steal proprietary information that was just sitting around; IBM had to demonstrate security proportional to claimed value of the information (corporations had been using legal system in lieu of security). The several billion dollar information/documentation had to be available to large number of people working on next generation disks ... but at the same time have security equivalent to Fort Knox with nearly nobody allowed access.

"Competitive" came up when I was first scheduling Boyd's briefing at IBM and tried to do it through the employee education department. Initially they agreed, but as I provided more information, they changed their mind and suggested that I limit the briefing to only senior members of competitive analysis departments (those divining what the competition is doing). Their explanation was that the company spends a large amount of money on training managers in how to handle employees and exposing general employees to Boyd's briefings could be counter productive.

--
virtualization experience starting Jan1968, online at home since Mar1970

This Award Winning British Speed Boat May Be Iran's Fiercest Weapon Against The US Navy

From: lynn@garlic.com (Lynn Wheeler)
Date: 22 Aug, 2012
Subject: This Award Winning British Speed Boat May Be Iran's Fiercest Weapon Against The US Navy
Blog: Facebook
This Award Winning British Speed Boat May Be Iran's Fiercest Weapon Against The US Navy
http://www.businessinsider.com/this-award-winning-british-speed-boat-may-be-irans-fiercest-weapon-against-the-us-navy-2012-8

ibm mainframe/killer micro analogy ... hundreds of hellfires and then thousands. plan for autonomous swams ... maybe kickstarted with commercial networked driverless car software. f35 talking about new software 20 times that of f22 ... complexity and faults tend to increase non-linear with size

mainframes have also tried a number of approaches to match agility of killer micros to track technology but still lag sometimes multiple generations

recent ref mentioning F35 software:
https://www.garlic.com/~lynn/2012i.html#50 Is there a connection between your strategic and tactical assertions?

--
virtualization experience starting Jan1968, online at home since Mar1970

First Battle: Operation Starlite and the Beginning of the Blood Debt in Vietnam

Refed: **, - **, - **, - **, - **
From: lynn@garlic.com (Lynn Wheeler)
Date: 22 Aug, 2012
Subject: First Battle: Operation Starlite and the Beginning of the Blood Debt in Vietnam
Blog: Facebook
First Battle: Operation Starlite and the Beginning of the Blood Debt in Vietnam
https://www.amazon.com/The-First-Battle-Operation-ebook/dp/B00BBPWBHI

good recommendation ... finished it Sunday ... managed to quote it here:
http://lnkd.in/nFRhH3

Saw this in US auto industry C4 taskforce meetings 1990 ... they could clearly articulate the issues with foreign competition and changes needed to respond ... and they weren't able to do it. Nearly decade earlier, there was call for 100% unearned profit tax on US auto industry. Foreign import quotas were to reduce competition and significantly increase profit which was to be used to completely remake the industry. Instead they pocketed it and continued status quo. Recent reports are they continue to find it difficult to change status quo.

I saw something similar in IBM hdqtrs locations in 1991 (just before going into the red in 1992), executives could clearly articulate changes that were needed ... but go back a couple months later and no changes. There were major disconnects between what they could say and actually being able to change; vested interests, head-in-sand, etc

recent posts mentioning 100% unearned profit tax &/or C4
https://www.garlic.com/~lynn/2012.html#22 Who originated the phrase "user-friendly"?
https://www.garlic.com/~lynn/2012.html#25 You may ask yourself, well, how did I get here?
https://www.garlic.com/~lynn/2012.html#31 Who originated the phrase "user-friendly"?
https://www.garlic.com/~lynn/2012c.html#26 Why Can't America Catch UP?
https://www.garlic.com/~lynn/2012c.html#32 US real-estate has lost $7T in value
https://www.garlic.com/~lynn/2012c.html#40 Where are all the old tech workers?
https://www.garlic.com/~lynn/2012c.html#62 Why Is Finance So Big?
https://www.garlic.com/~lynn/2012d.html#54 IBM cuts more than 1,000 U.S. Workers
https://www.garlic.com/~lynn/2012e.html#78 Time to Think ... and to Listen
https://www.garlic.com/~lynn/2012f.html#48 Explination of S0C4 reason code 4 and related data areas
https://www.garlic.com/~lynn/2012f.html#77 Vampire Squid
https://www.garlic.com/~lynn/2012f.html#88 Defense acquisitions are broken and no one cares
https://www.garlic.com/~lynn/2012g.html#70 Monopoly/ Cartons of Punch Cards
https://www.garlic.com/~lynn/2012h.html#31 How do you feel about the fact that today India has more IBM employees than US?
https://www.garlic.com/~lynn/2012i.html#86 Should the IBM approach be given a chance to fix the health care system?
https://www.garlic.com/~lynn/2012j.html#24 Why Asian companies struggle to manage global workers
https://www.garlic.com/~lynn/2012j.html#28 Why Asian companies struggle to manage global workers
https://www.garlic.com/~lynn/2012k.html#19 SnOODAn: Boyd, Snowden, and Resilience
https://www.garlic.com/~lynn/2012k.html#21 Is there a connection between your strategic and tactical assertions?
https://www.garlic.com/~lynn/2012k.html#36 Race Against the Machine

recent posts mentioning resurrection of IBM:
https://www.garlic.com/~lynn/2012.html#92 Has anyone successfully migrated off mainframes?
https://www.garlic.com/~lynn/2012.html#104 Can a business be democratic? Tom Watson Sr. thought so
https://www.garlic.com/~lynn/2012b.html#59 Original Thinking Is Hard, Where Good Ideas Come From
https://www.garlic.com/~lynn/2012b.html#74 IBM Doing Some Restructuring?
https://www.garlic.com/~lynn/2012d.html#23 IBM cuts more than 1,000 U.S. Workers
https://www.garlic.com/~lynn/2012d.html#35 Layer 8: NASA unplugs last mainframe
https://www.garlic.com/~lynn/2012f.html#84 How do you feel about the fact that India has more employees than US?
https://www.garlic.com/~lynn/2012g.html#4 Hard drives: A bit of progress
https://www.garlic.com/~lynn/2012g.html#34 Co-existance of z/OS and z/VM on same DASD farm
https://www.garlic.com/~lynn/2012g.html#72 Monopoly/ Cartons of Punch Cards
https://www.garlic.com/~lynn/2012g.html#74 Why So Many Formerly Successful Companies Are Failing
https://www.garlic.com/~lynn/2012g.html#82 How do you feel about the fact that today India has more IBM employees than US?
https://www.garlic.com/~lynn/2012g.html#87 Monopoly/ Cartons of Punch Cards
https://www.garlic.com/~lynn/2012h.html#4 Think You Know The Mainframe?
https://www.garlic.com/~lynn/2012h.html#16 Hierarchy
https://www.garlic.com/~lynn/2012h.html#35 Monopoly/ Cartons of Punch Cards
https://www.garlic.com/~lynn/2012h.html#54 How will mainframers retiring be different from Y2K?
https://www.garlic.com/~lynn/2012k.html#21 Is there a connection between your strategic and tactical assertions?
https://www.garlic.com/~lynn/2012k.html#31 History--punched card transmission over telegraph lines
https://www.garlic.com/~lynn/2012k.html#49 1132 printer history

--
virtualization experience starting Jan1968, online at home since Mar1970

Cultural attitudes towards failure

Refed: **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **
From: lynn@garlic.com (Lynn Wheeler)
Date: 23 Aug, 2012
Subject: Cultural attitudes towards failure.
Blog: Boyd Strategy
re:
http://lnkd.in/9q5Zvq
and
https://www.garlic.com/~lynn/2012k.html#87 Cultural attitudes towards failure
https://www.garlic.com/~lynn/2012l.html#2 Cultural attitudes towards failure
https://www.garlic.com/~lynn/2012l.html#5 Cultural attitudes towards failure
https://www.garlic.com/~lynn/2012l.html#10 Cultural attitudes towards failure

There are various references that once contamination became established in corporate america ... that the institutions became extremely resistance to change. This showing change dating from when Boyd was including references in his briefings:
http://globalguerrillas.typepad.com/globalguerrillas/2011/10/journal-why-the-us-middle-class-is-broken.html
from here:
http://www.nytimes.com/imagepages/2011/09/04/opinion/04reich-graphic.html
part of this article
http://www.nytimes.com/2011/09/04/opinion/sunday/jobs-will-follow-a-strengthening-of-the-middle-class.html

it also corresponds to the "three decades" mentioned in Stiglitz reference about business schools (teaching processes to eliminate change and freeze the status quo beginning to dominate). Other cultural influences during the period interacting .... drop in SAT and other scores for generations after baby-boomers ... references of the rise of "cult of personality" (at the expense of character) ... rise of MBAs and focus on quarterly nos. It is like once specific changes occurred ... that it acted as incubator (or at least eliminated counter force against potential that always existed) for a whole series of other aspects of culture.

One could make a case that rigid, top-down, command&control has analogies in potential for corruption under strong dictatorships versus much more egalitarian culture (it can be more efficient for specific short-term, point, familiar objectives but fails as long-term viable paradigm under changing conditions). A number of books regarding nation survive/fail corresponding to eqalitarian/non-eqalitarian characteristics. Fiske (history lectures from 1880s, my wife's father was awarded set for some distinction at west point) makes a point that our current form of gov. was heavily influenced by the Scottish settlers in the mid-atlantic states and would have been quite different if the English settlers had prevailed.

recent posts mentioning NYTimes/GlobalGuerrilla reference:
https://www.garlic.com/~lynn/2012.html#1 The war on terabytes
https://www.garlic.com/~lynn/2012.html#3 We are on the brink of a historic decision [referring to defence cuts]
https://www.garlic.com/~lynn/2012.html#30 Age of Greed: The Triumph of Finance and the Decline of America, 1970 to the Present
https://www.garlic.com/~lynn/2012.html#45 You may ask yourself, well, how did I get here?
https://www.garlic.com/~lynn/2012.html#87 The PC industry is heading for collapse
https://www.garlic.com/~lynn/2012d.html#48 IBM cuts more than 1,000 U.S. workers
https://www.garlic.com/~lynn/2012e.html#70 Disruptive Thinkers: Defining the Problem
https://www.garlic.com/~lynn/2012f.html#35 Inequality and Investment Bubbles: A Clearer Link Is Established
https://www.garlic.com/~lynn/2012g.html#80 Monopoly/ Cartons of Punch Cards
https://www.garlic.com/~lynn/2012h.html#3 Monopoly/ Cartons of Punch Cards
https://www.garlic.com/~lynn/2012h.html#18 How do you feel about the fact that India has more employees than US?
https://www.garlic.com/~lynn/2012h.html#27 Monopoly/ Cartons of Punch Cards
https://www.garlic.com/~lynn/2012h.html#32 Monopoly/ Cartons of Punch Cards
https://www.garlic.com/~lynn/2012h.html#38 Other Than In Computers, Civilization Basically Stopped Progressing In The 1960s
https://www.garlic.com/~lynn/2012h.html#44 Monopoly/ Cartons of Punch Cards
https://www.garlic.com/~lynn/2012h.html#46 How do you feel about the fact that today India has more IBM employees than US?
https://www.garlic.com/~lynn/2012i.html#1 Monopoly/ Cartons of Punch Cards
https://www.garlic.com/~lynn/2012i.html#10 Monopoly/ Cartons of Punch Cards
https://www.garlic.com/~lynn/2012i.html#48 Thousands Of IBM Employees Got A Nasty Surprise Yesterday: Here's The Email They Saw
https://www.garlic.com/~lynn/2012k.html#7 Is there a connection between your strategic and tactical assertions?
https://www.garlic.com/~lynn/2012k.html#40 Core characteristics of resilience

--
virtualization experience starting Jan1968, online at home since Mar1970

The growing openness of an organization's infrastructure has greatly impacted security landscape

Refed: **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **
From: lynn@garlic.com (Lynn Wheeler)
Date: 23 Aug, 2012
Subject: The growing openness of an organization's infrastructure has greatly impacted security landscape
Blog: Financial Crime Risk, Fraud and Security
Risk management now driven by 'fear', not strategic enough
http://www.zdnet.com/risk-management-now-driven-by-fear-not-strategic-enough-7000002081/

Some amount of misdirection in the article ... possibly has to do with what leaks into the popular press. We were tangentially involved in the Cal. state data breach notification act (having been brought in to help wordsmith electronic signature act and lots of the participants were heavily involved in privacy issues). There were indepth customer surveys that found #1 issue was identity theft, primarily kind involving fraudulent financial transactions as result of data breaches. Nothing was being done about the breaches (except lots of efforts to keep them out of the press) and it was hoped that data breach notifications would motivate corrective actions and countermeasures. Part of the issue was that majority motivation for security measures normally is self-protection. The institutions with the breaches weren't at risk of the fraudulent transactions ... it was their customers & clients (so they had little motivation).

I had worked with Jim Gray at research on the original relational DBMS and other things. More recently (before he disappeared), he con'ed me into interviewing for chief security architect in redmond. The interview went on over a period of several weeks, but we were unable to come to meeting of the minds. One of the things I pointed out was that desktop computing had arose in the 80s with totally isolated, unconnected box. Later, safe, local, small, business LAN connectivity was added ... and a paradigm of including automatically executable scripts in application data evolved. At the '96 spring MDC held at Moscone, all the banners were about supporting the internet ... but the theme in every session was about "protecting your investment" (aka preserving the automatic scripting paradigm). I've periodically drawn the analogy of just remapping the small, safe, local business LAN support to the wild, anarchy of the internet ... to shoving somebody out an airlock in open space w/o a spacesuit. A lot of the security design of original desktop computing and what is needed for an internet appliance are diametrically opposed.

Also, Sarbanes-Oxley was supposedly passed to prevent future Enrons & Worldcoms (supposedly strengthening authority that SEC already had to take action) ... but there were jokes at the time that it was just full employment for auditors. To actually be effective it required SEC to do something. Possibly because even GAO didn't believe SEC was doing anything ... it started doing reports of public company fraudulent financial filings ... even showing uptic after SOX:
http://www.gao.gov/products/GAO-03-395R
http://www.gao.gov/products/GAO-06-678
https://www.gao.gov/products/gao-06-1079sp

in theory under SOX ... the executives (and their auditors) would be doing jail time. More recently seen on the internet ENRON was dry run and worked so well that it has become institutionalized.

If one believed all the rhetoric about SOX a decade ago, they would be expecting thousands of executives and auditors currently doing jail time.

Another indication that during last decade, SEC was playing three monkeys (see no evil, hear no evil, speak no evil) came up in the Madoff congressional hearings. They had the person that had tried unsuccessfully for a decade to get SEC to do something about Madoff ... references was that SEC was finally forced to do something when Madoff turned himself in (some conjecture that he was looking for gov. protection for him and his family from some of the entities that were defrauded). Part of his testimony was that tips (whistle-blowers) turn up 13 times more fraud than audits ... and that SEC had no tip hotline ... but did have a 1-800 number for corporations to complain about audits.

Other decade old rhetoric regarding SOX was that possibly only the SOX whistle-blower section would actually make any difference (not expecting any benefit from audits) ... but that would have also required that SEC actually do something.

recent posts mentioning data breach notification act &/or '96 MDC
https://www.garlic.com/~lynn/2012.html#35 Israel vows to hit back after credit cards hacked
https://www.garlic.com/~lynn/2012.html#93 Where are all the old tech workers?
https://www.garlic.com/~lynn/2012d.html#49 Do you know where all your sensitive data is located?
https://www.garlic.com/~lynn/2012e.html#17 Data theft: Hacktivists 'steal more than criminals'
https://www.garlic.com/~lynn/2012e.html#29 Visa, MasterCard warn of 'massive' security breach
https://www.garlic.com/~lynn/2012e.html#79 What's the takeaway on Audit?
https://www.garlic.com/~lynn/2012e.html#82 Fighting Cyber Crime with Transparency
https://www.garlic.com/~lynn/2012i.html#80 Firms told to own up to cybercrime attacks

--
virtualization experience starting Jan1968, online at home since Mar1970

"execs" or "scripts"

Refed: **, - **, - **, - **
From: Anne & Lynn Wheeler <lynn@garlic.com>
Subject: Re: "execs" or "scripts"
Newsgroups: comp.lang.rexx
Date: Thu, 23 Aug 2012 11:39:21 -0400
Jeremy Nicoll - news posts <jn.nntp.scrap007@wingsandbeaks.org.uk> writes:
No. Script was the underlying language processor with the ability to parse free format text and fundamental commands (the dot commands like .br) and it allowed one to write macros (eg .this) combining multiple dot commands and using logic to examine attributes of arguments to the macros.

GML was a start-set of macros written in the Script language, using its builtin parser to associate a supplied set of macros with a supplied set of tag names. So eg the script initialisation parms told the parser how in general it should parse the user's text and in particular for each of the supplied tag/macro combinations whether to apply simple or more complicated parsing of tags and attributes.


re:
https://www.garlic.com/~lynn/2012l.html#8 "execs" or "scripts"
https://www.garlic.com/~lynn/2012l.html#9 "execs" or "scripts"

Madnick doing runoff port from ctss to cms, as script in 1966 (at the science center) ... predates the invention of GML (at the science center) in 1969 (Madnick also having done the original CMS *exec* processor).

support for GML *syntax* was original implemented as script macros ... in fact, it was possible to intermix "dot" (aka original script/runoff) controls in same file with GML *tags*.

roots of sgml
https://web.archive.org/web/20231001185033/http://www.sgmlsource.com/history/roots.htm

note that "GML" are the first letters of the last names of the three inventors.

science center only had 30-35 people (offices occupied part of the 4th floor, 545tech sq, computer machine room on the 2nd floor)

misc. past posts mentioning science center
https://www.garlic.com/~lynn/subtopic.html#545tech

misc. past posts mentioning gml/sgml
https://www.garlic.com/~lynn/submain.html#sgml

--
virtualization experience starting Jan1968, online at home since Mar1970

X86 server

Refed: **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **
From: lynn@GARLIC.COM (Anne & Lynn Wheeler)
Subject: Re: X86 server
Newsgroups: bit.listserv.ibm-main
Date: 23 Aug 2012 09:11:40 -0700
John.McKown@HEALTHMARKETS.COM (McKown, John) writes:
X64 hardware, as much as it has improved, is still not as reliable or have the I/O capacity of the z hardware. E.g.: We had a TCM fail once. A spare picked up the work, automatically restarting the instruction stream, with no outage of any sort and no software involvement. X86, from what I'm told, would at least require the OS to do the equivalent of a checkpoint restart. Also had an OSA fail. The other OSA did an ARP takeover and no IP sessions were lost. TCPIP was informed, but all it did was put out a message and not start any new sessions on the failing OSA. Our "open" people called me a liar when I told them that.

big cloud operators do hundreds of thousands of blades in megadatacenter with lots of failure/recovery infrastructure to handle individual blade failures (usually with lots of power, telco, provisioning provisioning).

Gray had been studying mix of failures issues (both at IBM and later at Tandem) and by '84 published report that hardware failures had become minority of failure modes (hardware reliability had increased so other kinds of failures were starting to dominating). scan of '84 presentation
https://www.garlic.com/~lynn/grayft84.pdf

several of the big cloud operators have published detailed studies of different component availability as part of building their own blades ... given optimal service life per dollar.

Cluster & take-over were increasingly being used to mask all kinds of outages ... even able to handle geographic operations and handling disasters taking out whole datacenter.

when we were doing ha/cmp ... we did a lot of failure mode study ... and part of our marketing was against hardware fault-tolerant systems. We showed availability of ha/cmp clusters was higher than the fault-tolerant systems. In competitive situation involving 1-800 number server (i.e. maps 1-800 number to "real" number) ... it required five-nines availability. hardware fault-tolerant system still required scheduled system outage to do software upgrade ... which would blow several decades of downtime budget. With cluster operation, we showed at least as good hardware availability (with redundant systems) along with capability of doing rolling software upgrades with no system outage.

the hardware fault tolerant vendor eventually came back with suggestion that they could come out with redundant, cluster system operation ... to handle the software upgrade issue. However, given reliability of the underlying hardware operating in redundant, cluster system mode ... there was no longer any justification for hardware fault tolerance.

part of ha/cmp was ip-address take-over ... which according to all the standards should time-out mac/ip-address in arp caches. at the time, most vendors were using BSD 4.3 tahoe or reno software for their tcp/ip stacks. In 1989, we found a bug in the BSD4.3 tahoe/reno IP/ARP lookup software. The ARP cache management was correctly timing out the ARP cache entries (so if there was ip-address take-over, it would discover the new MAC mapping). However, the BSD4.3 IP code had a performance optimization where it saved the last ip/mac lookup results ... which would only get reset if the client communicated with a different ip-address (otherwise that saved ip/mac mapping would exist forever). Since the "bug" existed in nearly every vendors implementation (all using same BSD4.3 tahoe/reno software), we had to come up with a work-around for the saved ip/mac bug. Any time there was ip-address take-over, we would quickly saturate the local LAN with dummy traffic from a different ip-address ... forcing all the machines on that LAN to perform a real ARP cache lookup (resetting the "saved" value). Then the next activity from the taken-over ip-address would force the clients to do a real ARP cache lookup.

misc. past posts mentioning ha/cmp
https://www.garlic.com/~lynn/subtopic.html#hacmp

--
virtualization experience starting Jan1968, online at home since Mar1970

Cultural attitudes towards failure

Refed: **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **
From: lynn@garlic.com (Lynn Wheeler)
Date: 23 Aug, 2012
Subject: Cultural attitudes towards failure.
Blog: Boyd Strategy
re:
http://lnkd.in/9q5Zvq
and
https://www.garlic.com/~lynn/2012k.html#87 Cultural attitudes towards failure
https://www.garlic.com/~lynn/2012l.html#2 Cultural attitudes towards failure
https://www.garlic.com/~lynn/2012l.html#5 Cultural attitudes towards failure
https://www.garlic.com/~lynn/2012l.html#10 Cultural attitudes towards failure
https://www.garlic.com/~lynn/2012l.html#13 Cultural attitudes towards failure

Why Nations Fail: The Origins of Power, Prosperity, and Poverty
https://www.amazon.com/Why-Nations-Fail-Prosperity-ebook/dp/B0058Z4NR8

discusses Spanish conquest of the new world which was plunder and enslave the local population (and keeping them at subsistance level). This is compared with the English originally attempting to emulate a similar strategy for Jamestown, almost starving the first two years because they originally sent over skills oriented to plundering and enslaving the local population ... then changed the strategy to sending over enslaved English that had no rights, the "leet-men", pg27:
The clauses of the Fundamental Constitutions laid out a rigid social structure. At the bottom were the "leet-men," with clause 23 noting, "All the children of leet-men shall be leet-men, and so to all generations."

... snip ...

Boyd talks about this some in Organic Design For Command and Control ... one of his examples when he was command at spook base (NKP) and his use of "legal eagle" and comptroller for independent communication paths. Ends with leadership & appreciation (instead of command&control) ... along with trust; odcc pg7:
Balck (1980)

Emphasis upon creation of implicit connections or bonds based upon trust, not mistrust, that permit wide freedom for subordinates to exercise imagination and initiative -- yet, harmonize within intent of superior commanders. Benefit: internal simplicity that permits rapid adaptability.


... snip ...

He would spend some time talking about Guderian's verbal orders only during the blitzkrieg ... part of Guderian trust and subordinates were encouraged to do the best possible at the time and not worry about need for paper CYA afterwards.

... and warn about how US military rigid, top-down, command&control was contaminating US corporate culture.

recent posts mentioning "Why Nations Fail":
https://www.garlic.com/~lynn/2012e.html#31 PC industry is heading for more change
https://www.garlic.com/~lynn/2012e.html#34 The never-ending SCO lawsuit
https://www.garlic.com/~lynn/2012e.html#35 The Dallas Fed Is Calling For The Immediate Breakup Of Large Banks
https://www.garlic.com/~lynn/2012e.html#36 The never-ending SCO lawsuit
https://www.garlic.com/~lynn/2012e.html#60 Candid Communications & Tweaking Curiosity, Tools to Consider
https://www.garlic.com/~lynn/2012e.html#70 Disruptive Thinkers: Defining the Problem
https://www.garlic.com/~lynn/2012f.html#2 Did they apply Boyd's concepts?
https://www.garlic.com/~lynn/2012f.html#32 Back to the future: convict labor returns to America
https://www.garlic.com/~lynn/2012f.html#70 The Army and Special Forces: The Fantasy Continues
https://www.garlic.com/~lynn/2012h.html#10 Monopoly/ Cartons of Punch Cards
https://www.garlic.com/~lynn/2012i.html#85 Naked emperors, holy cows and Libor
https://www.garlic.com/~lynn/2012j.html#81 GBP13tn: hoard hidden from taxman by global elite
https://www.garlic.com/~lynn/2012k.html#7 Is there a connection between your strategic and tactical assertions?
https://www.garlic.com/~lynn/2012k.html#42 The IBM "Open Door" policy
https://www.garlic.com/~lynn/2012k.html#45 If all of the American earned dollars hidden in off shore accounts were uncovered and taxed do you think we would be able to close the deficit gap?

--
virtualization experience starting Jan1968, online at home since Mar1970

X86 server

Refed: **, - **, - **, - **, - **, - **, - **
From: lynn@GARLIC.COM (Anne & Lynn Wheeler)
Subject: Re: X86 server
Newsgroups: bit.listserv.ibm-main
Date: 23 Aug 2012 13:50:59 -0700
John.McKown@HEALTHMARKETS.COM (McKown, John) writes:
"has always been" -> "had always been". As you indicated, at first software was written in order to sell the hardware. It was basically "overhead". However, when PCMs such as Amdahl came along and simply started redistributing IBM software (which they got for free since they owned IBM hardware), IBM had to have some other way to recoup their costs. Also, they started unbundling when the courts found them guilty of a monopoly which included their refusal to distribute software to non-IBM customers. At least, as best as I can recall after lo these many years.

re:
https://www.garlic.com/~lynn/2012l.html#16 X86 server

23jun69 unbundling announcement was result of various litigation, required starting to charge for application software, SE services, hardware maint., etc. Company managed to make the case that kernel software should still be free. misc. past unbundling posts
https://www.garlic.com/~lynn/submain.html#unbundle

FS effort in the early 70s was motivated by competition clone controllers (it was going to have been radically different from 370), The rise and fall of IBM
https://www.ecole.org/en/session/49-the-rise-and-fall-of-ibm
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 R&D spending, and the strategy only resulted in a partial narrowing of the price gap between IBM and its rivals.

... snip ...

misc. other Future System refs:
http://www.jfsowa.com/computer/memo125.htm
https://people.computing.clemson.edu/~mark/fs.html
https://en.wikipedia.org/wiki/IBM_Future_Systems_project
http://gdrean.perso.sfr.fr/papers/promises.html

during Future System period, internal politics killed off and/or suspended 370 acitivty ... also I continued to work on 360/370 stuff ... and periodically ridiculed FS (which possibly wasn't the greatest career enhancing activity). The lack of 370 products was credited with allowing clone processors to gain market foothold.

and misc. past posts mentioning Future System
https://www.garlic.com/~lynn/submain.html#futuresys

In the wake of the FS failure, there was mad rush to get stuff back into the 370 product pipelines ... this contributed to decisions to release various pieces of stuff that I was doing all during the FS period ... old email mentioning 360/370 stuff during FS period (one of my hobbies was providing production operating systems for internal datacenters):
https://www.garlic.com/~lynn/2006v.html#email731212
https://www.garlic.com/~lynn/2006w.html#email750102
https://www.garlic.com/~lynn/2006w.html#email750430

With the rise of the clone processors (made possible by the lack of products during the FS period) and with effort to get stuff back into the 370 product pipelines ... there was also a change in the decision to start charging for kernel software. This was going to be a staged conversion ... with new kernel add-ons being charged ... leaving base software free ... at least during transition period. One of my pieces selected to go out was my resource manager ... and it was selected as the guinea pig for starting to charge for kernel software (initially add-on pieces) and I got to spend some amount of time with business people about kernel charging policies. misc. past posts mentioning my resource manager and/or scheduling
https://www.garlic.com/~lynn/subtopic.html#fairshare

--
virtualization experience starting Jan1968, online at home since Mar1970

X86 server

Refed: **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **
From: lynn@GARLIC.COM (Anne & Lynn Wheeler)
Subject: Re: X86 server
Newsgroups: bit.listserv.ibm-main
Date: 23 Aug 2012 16:05:15 -0700
uriel.carrasquilla@MAIL.MCGILL.CA (Uriel Carrasquilla) writes:
When I used to work for the stock exchange (in Vancouver), it was always the question about MF versus Tandem/Stratus fault-tolerant equipment. Yes, most of the problems were not hardware related. But one time we were hit by a massive failure in the primary and backup components that brought trading down. It is black swan but can happen and the consequences can be nasty. When it comes to our mission critical applications, we are still a long way from going to the clouds. But for those systems that we can afford the risk, yes, we will go to the cloud.

re:
https://www.garlic.com/~lynn/2012l.html#16 X86 server
https://www.garlic.com/~lynn/2012l.html#18 X86 server

in ha/cmp we spent some amount of time with siac ... ran dataprocessing for exchange ... they had a carefully selected datacenter in a building that had lots of diverse routing ... two different water mains on different sides of the building, different electrical mains on different sides of the building to different substations, and four different telco feeds on four sides of the building into four different central exchanges (this besides UPS and power backup). past posts mentioning ha/cmp
https://www.garlic.com/~lynn/subtopic.html#hacmp

one of their outages was when the transformers in the basement blew-up contaminanting the building with PCB ... and the building had to be evacuated. misc. past posts mentioning SIAC
https://www.garlic.com/~lynn/2005i.html#0 More Phishing scams, still no SSL being used
https://www.garlic.com/~lynn/2007e.html#16 Attractive Alternatives to Mainframes
https://www.garlic.com/~lynn/2007k.html#41 DEC and news groups
https://www.garlic.com/~lynn/2007n.html#31 IBM obsoleting mainframe hardware
https://www.garlic.com/~lynn/2008b.html#36 windows time service
https://www.garlic.com/~lynn/2009g.html#2 Just posted third article about toxic assets in a series on the current financial crisis
https://www.garlic.com/~lynn/2009i.html#23 Why are z/OS people reluctant to use z/OS UNIX? (Are settlements a good argument for overnight batch COBOL ?)
https://www.garlic.com/~lynn/2009p.html#57 MasPar compiler and simulator
https://www.garlic.com/~lynn/2010q.html#37 Programmer Charged with thieft (maybe off topic)

I was out doing geographic separation and had coined the terms disaster survivability and geographic survivability (to differentiate from disaster recovery) ... some past posts
https://www.garlic.com/~lynn/submain.html#available

I was then asked to write a section for the corporate continuous availability strategy document ... but when both rochester and POK complained that they couldn't meet the requirements ... my section got pulled.

I was also doing cluster scale-up ... mentioned in this early jan92 meeting in ellison's conference room
https://www.garlic.com/~lynn/95.html#13

and mainframe DB2 compalined if I was allowed to go ahead ... I would be years ahead of them.

--
virtualization experience starting Jan1968, online at home since Mar1970

X86 server

Refed: **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **
From: lynn@GARLIC.COM (Anne & Lynn Wheeler)
Subject: Re: X86 server
Newsgroups: bit.listserv.ibm-main
Date: 23 Aug 2012 19:13:59 -0700
mward@SSFCU.ORG (Ward, Mike S) writes:
IBM has always been a hardware company. In the 60's they wrote operating systems and gave them away as long as you purchased the hardware from them to run it on.

re:
https://www.garlic.com/~lynn/2012l.html#16 X86 server
https://www.garlic.com/~lynn/2012l.html#18 X86 server
https://www.garlic.com/~lynn/2012l.html#19 X86 server

became much less so after Gerstner resurrected ibm.

recent revenue was 83% software and services with everything else ... including all hardware, 17%. mainframe, x86, and power hardware were approx. $5B each

max configured z196 with 80 processors is rated for 50BIPS and goes for $28M (about $560,000/BIPS) and at $28M, $5B represents approx. 180 max. configured z196 (180*50 or aggregate of 9TIPS processing)

ibm has base price of $1815 for e5-2600 blade ... which have ratings at 527BIPS (about $3.44/BIPS), at $1815, $5B represents approx. 2,754,800 e5-2600 blades (2754800*527 or aggregate of 1,452,000TIPS). Even if you inflate the base blade price by a factor of ten times, that reduces the number of blades (you could get for $5B) to 275,480 with aggregate processing power of 145,000TIPS

On the other hand the major cloud operators have claimed that they manufacturer blades with optimal components for 1/3rd the cost of brand name blades ... with a cloud megadatacenter typically containing several hundred thousand blades.

a couple recent ibm-main references to Gerstner's resurrect of ibm:
https://www.garlic.com/~lynn/2012b.html#74 IBM Doing Some Restructuring?
https://www.garlic.com/~lynn/2012g.html#34 Co-existance of z/OS and z/VM on same DASD farm

--
virtualization experience starting Jan1968, online at home since Mar1970

"execs" or "scripts"

From: Anne & Lynn Wheeler <lynn@garlic.com>
Subject: Re: "execs" or "scripts"
Newsgroups: comp.lang.rexx
Date: Fri, 24 Aug 2012 10:36:42 -0400
Bob Martin <bob.martin@excite.com> writes:
Where did ISIL fit into this?

re:
https://www.garlic.com/~lynn/2012l.html#8 "execs" or "scripts"
https://www.garlic.com/~lynn/2012l.html#9 "execs" or "scripts"
https://www.garlic.com/~lynn/2012l.html#15 "execs" or "scripts"

gml wiki
https://en.wikipedia.org/wiki/IBM_Generalized_Markup_Language

from above:

In the early 1980s, IBM developed a dedicated publishing tool called Information Structure Identification Language (ISIL) based on GML. ISIL was used to generate much of IBM documentation for the IBM PC and other products at this time. In the late 1980s, a commercial product called BookMaster was developed, based mostly on ISIL.

During the early 1980s, Don Williams at IBM developed DWScript to use the SCRIPT/VS on the IBM PC.[2] In 1986, he developed a PC version of ISIL called DWISIL. These products were only used internally at IBM.

... snip ...

--
virtualization experience starting Jan1968, online at home since Mar1970

"execs" or "scripts"

From: Anne & Lynn Wheeler <lynn@garlic.com>
Subject: Re: "execs" or "scripts"
Newsgroups: comp.lang.rexx
Date: Fri, 24 Aug 2012 11:09:18 -0400
re:
https://www.garlic.com/~lynn/2012l.html#8 "execs" or "scripts"
https://www.garlic.com/~lynn/2012l.html#9 "execs" or "scripts"
https://www.garlic.com/~lynn/2012l.html#15 "execs" or "scripts"
https://www.garlic.com/~lynn/2012l.html#21 "execs" or "scripts"

other trivia ... vm/cms "SE" on financial services accounts in LA branch office, did re-implementation of script for trs-80, past reference:
https://www.garlic.com/~lynn/2004l.html#74 Specifying all biz rules in relational data
https://www.garlic.com/~lynn/2011n.html#58 "Geek" t-shirts

--
virtualization experience starting Jan1968, online at home since Mar1970

PDP-10 system calls, was 1132 printer history

Refed: **, - **, - **, - **, - **, - **, - **, - **, - **, - **
From: Anne & Lynn Wheeler <lynn@garlic.com>
Subject: Re: PDP-10 system calls, was 1132 printer history
Newsgroups: alt.folklore.computers
Date: Fri, 24 Aug 2012 15:36:58 -0400
Morten Reistad <first@last.name> writes:
Yes, there are hardware reference manuals for the KA,KI,KS,KL etc, just as Prime made for the 550,750,850 etc; but nothing like the "50-series architecture guide" or the "360 Principles of Operations.". With the former in hand you could make assemblies of components that never were Prime products, but were still fully supported. Like a "650", with two 550's connected to do MP just like two 750's made an 850. Or hang a second I/O cage on a 2550, making it a low-profile 9350.

And so on. On the IBM side the relevance was first on what weird combinations of software and channel/cpu configurations you could run.


by at least 1970 ... the architecture group moved the principles of operation to cms script file ... it was actually the architecture "red book" for the red 3-ring binder it was distributed it. the architecture entries were bracketed and intermixed with the corresponding principles of operation information. the architecture entries gave things like justification, alternatives, engineering implementation notes, unannounced items, etc. cms script command line option controlled whether the full architecture redbook was formated or just the principles of operation subset. at the start, the full redbook was about twice the size of the POO/POP subset.

in the 370 case, it was giving all the different plant sites a common objective to work to ... 115/125 in boeblingen, 135/145 in endicott, 155 in kingston, 165 in POK, etc

--
virtualization experience starting Jan1968, online at home since Mar1970

"execs" or "scripts"

Refed: **, - **, - **, - **, - **
From: Anne & Lynn Wheeler <lynn@garlic.com>
Subject: Re: "execs" or "scripts"
Newsgroups: comp.lang.rexx
Date: Fri, 24 Aug 2012 15:48:21 -0400
LesK <5mre20@tampabay.rr.com> writes:
Back then I had a commercial version of SCRIPT for the TRS-80 and it was great! My (then) wife used it for her home typing business. My vague memory says Alan Tannenbaum was the author.

re:
https://www.garlic.com/~lynn/2012l.html#8 "execs" or "scripts"
https://www.garlic.com/~lynn/2012l.html#9 "execs" or "scripts"
https://www.garlic.com/~lynn/2012l.html#15 "execs" or "scripts"
https://www.garlic.com/~lynn/2012l.html#21 "execs" or "scripts"
https://www.garlic.com/~lynn/2012l.html#22 "execs" or "scripts"

past post
https://www.garlic.com/~lynn/2004l.html#74
https://www.garlic.com/~lynn/2011n.html#58

chuck tesler (and son glen) ... see these mentioned references
http://www.atarimagazines.com/creative/v9n6/70_GEAP_tricks.php
http://www.wsfa.org/journal/j82/b/

also see Allwrite! and NewScript entries here:
https://web.archive.org/web/20061130230530/http://www.trs-80.com/trs80-sw.htm

*script* 370 topic drift from a.f.c. post
https://www.garlic.com/~lynn/2012l.html#23

by at least 1970 ... the architecture group moved the principles of operation to cms script file ... it was actually the architecture "red book" for the red 3-ring binder it was distributed it. the architecture entries were bracketed and intermixed with the corresponding principles of operation information. the architecture entries gave things like justification, alternatives, engineering implementation notes, unannounced items, etc. cms script command line option controlled whether the full architecture redbook was formated or just the principles of operation subset. at the start, the full redbook was about twice the size of the POO/POP subset.

in the 370 case, it was giving all the different plant sites a common objective to work to ... 115/125 in boeblingen, 135/145 in endicott, 155 in kingston, 165 in POK, etc

--
virtualization experience starting Jan1968, online at home since Mar1970

X86 server

Refed: **, - **, - **, - **, - **, - **, - **, - **, - **
From: lynn@GARLIC.COM (Anne & Lynn Wheeler)
Subject: Re: X86 server
Newsgroups: bit.listserv.ibm-main
Date: 24 Aug 2012 13:13:50 -0700
scott_j_ford@YAHOO.COM (Scott Ford) writes:
Just for my 2 cents worth, ran P390s in one environment attached to two T1s. Attached to them we're 3800 laser printers and some 3274s we couldnt replace. The mainframes were an hour plus away in NJ, and our printed output queued up to the P390s. Everything worked like a champ. I am now on Z/Pdt z/os1.12 on a intel i7', everything s good, but are also only doing development.

Scott ford www.identityforge.com


re:
https://www.garlic.com/~lynn/2012l.html#16 X86 server
https://www.garlic.com/~lynn/2012l.html#18 X86 server
https://www.garlic.com/~lynn/2012l.html#19 X86 server
https://www.garlic.com/~lynn/2012l.html#20 X86 server

1980 STL is bursting at the seams and they are moving 300 people from IMS group to off-site bldg. the group tries remote 3270 support and find it intolerable. I get con'ed into writing HYPERchannel support for use as channel extender ... allowing them to put local channel-attached 3270 controllers at the remote site. Runs over T1 channel on the *campus* collins digital radio T3 microwave. They don't notice any change from cms local 3270 controllers in STL (maintaining their subsecond response ... back when mvs/tso people were claiming noody needed subsecond response). System thruput actually improves ... issue is the HYPERchannel A220s sitting on real channel have significantly lower channel busy (for the same operation) than 3270 controllers ... total system throughput improves 10-15% (the 3270 controller channel busy is masked at the remote site).

I try to get approval to release the software to customers ... which a group in POK manages to block. That group was playing with some fiber stuff (that eventually gets out as ESCON), and they are afraid if my HYPERchannel support is released to customers ... it would interfer with someday being able to get their fiber stuff out. As a result NSC has to re-do my implementation from scratch.

Roll forward several years, the 3090 product administrator tracks me down. the 3090 channels were designed to have 3-5 channel checks annually aggregate across the whole customer base. the industry service that collects erep data shows that there have been an aggregate of 20 channel checks the first year.

Turns out they are at customers running 3800 over HYERPChannel channel extender. In my original implementation ... if I had an unrecoverable transmission error ... I would simulate channel check in the CSW ... for the host software to go through its retry operation ... and the NSC faithfully reproduced that in their implementation. After some amount of toiling through error recovery code ... i determined that simulating IFCC would have effectively the same result as channel check and got NSC to update their implementation.

as an aside, long ago and far away somebody in Boulder does build a hardware channel emulator for ibm/pc which is used for 3800 testing.

--
virtualization experience starting Jan1968, online at home since Mar1970

PDP-10 system calls, was 1132 printer history

Refed: **, - **, - **, - **, - **, - **, - **
From: Anne & Lynn Wheeler <lynn@garlic.com>
Subject: Re: PDP-10 system calls, was 1132 printer history
Newsgroups: comp.lang.pl1, alt.folklore.computers
Date: Fri, 24 Aug 2012 19:29:36 -0400
"Joe Morris" <j.c.morris@verizon.net> writes:
Under VM/370 and its descendants, all program execution in a vm is performed in problem mode (including execution in virtual supervisor mode), so executing the DIAGNOSE opcode results in a privileged instruction trap; VM uses this for its API between the virtual machine and the hypervisor. A program designed to run both under VM and on a real machine could determine if it is running in a VM by using an unprivileged instruction that returns, among other things, the model number of the CPU: VM returned x'FF', which meant that DIAGNOSE could be safely used.

re
https://www.garlic.com/~lynn/2012l.html#23 PDP-10 system calls, was 1132 printer history

after cp67 was installed at the univ., I started redoing large sections ... in large part oriented to general operation and running os/360 virtually. This is part of performance presentation that I made at fall 1968 SHARE meeting about some of the changes:
https://www.garlic.com/~lynn/94.html#18

then i did some changes to cut (cp67) cms file i/o simulation pathlength ... doing it through standard SIO instruction ... but with a "special" CCW op-code. I demonstrated significant cut in cp67 pathlenth for cms file i/o. However, science center (Bob Adair) said that I had violated principles of operation (i.e. 360/67 architecture ... since there was no provision for doing such an implementation).

The suggestion was to implement such functions with the DIAGNOSE instruction ... the principles of operation defines DIAGNOSE instruction as having "model dependent" implementation. The fiction used was to define a DIAGNOSE implementation that was for a virtual machine model.

the changes were shipped with cp67/cms ... with cms testing whether it was running on real machine (and used standard SIO) or in virtual machine (under cp67). for cms morph from cp67 to vm370, its name was changed from "cambridge monitor system" to "converversational monitor system" and the code for running stand-alone (and real hardware with SIO) was removed.

after graduating and joining science center I then did cp67 interface to support page-mapped filesystem. at the univ., the ibm people were still periodically testing tss/360 ... and saw a lot of stuff "done wrong" in its implementations ... and setout to avoid making the same mistakes. This not only had more than the pathlength efficiencies that were done for i/o simulation using diagnose ... but got a whole lot of efficiencies because it aligned the cms filesystem operation with the cp67 virtual memory and demand paged infrastructure (real I/O simulation could still have a lot of stuff that worked at cross-purposes with the paging infrastructure). misc. past posts mentioning memory mapped filesystem
https://www.garlic.com/~lynn/submain.html#mmap

in the mean time, the future system effort took up "single-level-store" ... picking up a lot of stuff having been done in tss/360. it was one area where I would ridicule what they were doing (believing what I already had running was better than what they were blue skying about). misc. past posts mentioning future system
https://www.garlic.com/~lynn/submain.html#futuresys

--
virtualization experience starting Jan1968, online at home since Mar1970

PDP-10 system calls, was 1132 printer history

Refed: **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **
From: Anne & Lynn Wheeler <lynn@garlic.com>
Subject: Re: PDP-10 system calls, was 1132 printer history
Newsgroups: comp.lang.pl1, alt.folklore.computers
Date: Sun, 26 Aug 2012 10:29:25 -0400
Peter Flass <Peter_Flass@Yahoo.com> writes:
IBM had to do that because the different models were designed by different groups in the US, UK, and Europe. The POP was necessary to keep everyone on the same page.

re:
https://www.garlic.com/~lynn/2012l.html#23 PDP-10 system calls, was 1132 printer history
https://www.garlic.com/~lynn/2012l.html#26 PDP-10 system calls, was 1132 printer history

folklore/story, early 70s from somebody that relative at the gov. antitrust litigation ... top executive from one of the 7 dwarfs testified that in the late 50s every computer vendor realized that the single most important customer issue was compatible product line (computer uptake was starting to accelerate and computer upgrades was becoming more common) ... and IBM executives (watson) were the only ones that managed to enforce strict compatibility (aka individual product managers wanting to optimize for their technology).

the corollary was being the only company getting the single most important market/customer requirement *right* ... it was possible for IBM to get many other things wrong ... and still come to dominate the market (even if sometimes, the level of compatibility at application level was just market perception).

then early 1971, IBM started future system effort ... that was going to completely replace 360/370 ... and be as incompatible with 360/370 as 360 had been from prior generations. Major motivation for "future system" was countermeasure to clone controllers. However, during future system period, 370 efforts were abandoned and/or killed off ... the lack of 370 products during this period is credited with giving the clone processors a market foothold. misc. past posts mentioning future system
https://www.garlic.com/~lynn/submain.html#futuresys
a few other future system refs:
http://www.jfsowa.com/computer/memo125.htm
https://people.computing.clemson.edu/~mark/fs.html
https://www.ecole.org/en/session/49-the-rise-and-fall-of-ibm
https://en.wikipedia.org/wiki/IBM_Future_Systems_project
http://gdrean.perso.sfr.fr/papers/promises.html

Amdahl had left and was starting is own "clone" computer company. In this period, he gave a talk in large MIT auditorium; during the talk a student in the audience asked what justification did he use getting investment. he said that even if IBM were to completely walk away from 370 (might be considered a vieled reference to FS), there already was enormous customer investment in 370 application software development that would keep him in business at least through the end of the century (which has since come and gone).

the gov. litigation also motivated the 23jun1969 "unbundling" announcement, starting to charge for application software, SE services, hardware maintenance (howevere, the company managed to make the case that kernel software should still be free). misc. past posts mentioning unbundling
https://www.garlic.com/~lynn/submain.html#unbundle

Roll forward to the failure of the FS effort ... and there was mad rush to get products back into the 370 pipelines (motivating decision to release some of the 370 stuff that I had continued to do all thru the FS period, I would also periodically ridicule what they were doing). With the market foothold by the clone processors ... there was also a decision to start charging for kernel software. One of the things I had been doing (my resource manager) that was chosen for release, was selected to be guinea pig for starting to charge for kernel software. I got to spend a lot of time with business people disucssing pricing politices for kernel software. misc. past posts mentioning my resource manager
https://www.garlic.com/~lynn/subtopic.html#fairshare

recently in ibm-main mailing list ... there has been discussion of mainframe software emulators that ran on other hardware (getting close to the 10:1 simulation overhead that was typical of the low & mid-range 370 microcode ratios). There has been lots of effort to stamp out the emulators not provided directly by the corporation and carefully control the one that the corporation provides (Z/PDT)
https://www.garlic.com/~lynn/2012l.html#16 X86 server
https://www.garlic.com/~lynn/2012l.html#18 X86 server
https://www.garlic.com/~lynn/2012l.html#19 X86 server
https://www.garlic.com/~lynn/2012l.html#20 X86 server
https://www.garlic.com/~lynn/2012l.html#25 X86 server

I mention that latest max configured z/196 with 80 processors is rated at 50BIPS and goes for $28M ($560,000/BIPS). Also after Gerstner's resurrection of IBM it shifted to services ... recently getting 83% revenue from software&services ... and 17% from everything else (including all hardware) ... hardware working out to about $5B each for mainframe, i86, and power. At $28M, $5B total works out to equivalent of 180 max. configured z196 (or aggregate processing power of 180*50 = 9TIPS)

IBM has base price of $1815 for 35-2600 blade which have ratings of 527BIPS (about $3.44/BIPS), at $1815, $5B would represent 2,754,800 e5-2600 blades ... or aggregate processing power 1,452,000TIPS. Even if you inflate the base blade price by a factor of ten times, that is still 275,480 blades and aggregate processing power of 145,000TIPS.

--
virtualization experience starting Jan1968, online at home since Mar1970

X86 server

Refed: **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **
From: lynn@GARLIC.COM (Anne & Lynn Wheeler)
Subject: Re: X86 server
Newsgroups: bit.listserv.ibm-main
Date: 26 Aug 2012 07:59:31 -0700
PaulGBoulder@AIM.COM (Paul Gilmartin) writes:
What's impressive here is that they don't buy off-the-shelf hardware systems; they design their own.

at hundreds of thousands blades in a megadatacenter and multiple megadatacenters spread around the world ... they claim that they can build their own for 1/3rd the price of brand name blades. they also have done quite a bit of research into reliability of different commodity components and buy in quantity for total cost of ownship. They also tend to have some leverage over vendors that sell into the megadatacenter server market.

with the enormous reduction in cost of hardware that they've been able to achieve (if IBM has base price of $1815 for e5-2600 blade or approx. $3.44/BIPS ... and megadatacenter may be able to achieve 1/3rd that ... compared to $560,000/BIPS for z196) ... other costs start to play an increasing role. The megadatacenters have also pioneered much of the green datacenter efforts ... radically reducing power and cooling costs ... establishing power&cooling cost measures per unit of computing ... somewhat analogous to the TPC council ... total cost per transaction (gives results sorted by performance, price/performance and watts/performance). A few recent posts mentioning mainframes and TPC benchmarks:
https://www.garlic.com/~lynn/2012.html#23 21st Century Migrates Mainframe with Clerity
https://www.garlic.com/~lynn/2012h.html#20 Mainframes Warming Up to the Cloud
https://www.garlic.com/~lynn/2012i.html#16 Think You Know The Mainframe?
https://www.garlic.com/~lynn/2012i.html#89 Can anybody give me a clear idea about Cloud Computing in MAINFRAME ?
https://www.garlic.com/~lynn/2012j.html#1 Can anybody give me a clear idea about Cloud Computing in MAINFRAME ?

One of the issues is they have done significant excess provisioning for "on-demand" requirements and so have pressured vendors for implementations that drastically cut power use when idle ... but able to instantaneously come up to full-speed.

They've also openly published their findings ... hoping to encourage the component vendors to compete & improve their products. However, their findings have also tended to influence blade component selection and assembly by others.

recent posts in this thread
https://www.garlic.com/~lynn/2012l.html#16 X86 server
https://www.garlic.com/~lynn/2012l.html#18 X86 server
https://www.garlic.com/~lynn/2012l.html#19 X86 server
https://www.garlic.com/~lynn/2012l.html#20 X86 server
https://www.garlic.com/~lynn/2012l.html#25 X86 server

--
virtualization experience starting Jan1968, online at home since Mar1970

X86 server

Refed: **, - **, - **, - **, - **, - **, - **, - **, - **, - **
From: lynn@GARLIC.COM (Anne & Lynn Wheeler)
Subject: Re: X86 server
Newsgroups: bit.listserv.ibm-main
Date: 26 Aug 2012 11:23:26 -0700
shmuel+gen@PATRIOT.NET (Shmuel Metz , Seymour J.) writes:
Only if you're talking about the same instruction mix. When one system has instructions like MVCL and the other doesn't, MIPS truly means "meaningless indication of processor speed". A comparison of FLOPS ratings might be more meaningful, since the spread between the slowest and the fastest operation isn't as large.

note that x86 BIPS ratings are number of iterations executing dhrystone benchmark compared to vax 780 assumed to be 1mip ... have no idea *real* instruction execution rate. past discussion in this thread
https://www.garlic.com/~lynn/2012d.html#41 Layer 8: NASA unplugs last mainframe

above also mentions i7-3960x is single socket/chip with approx. four times the BIPS rating of 80processor z196

max. configured 64processor z10 was claimed to be 30BIPS ... and that increased by 2/3rds to 50BIPS for 80processor z196.

increase in processors from 64 to 80 can account for increase of 25%. tech articles claim the introduction of out-of-order execution for z196 accounts for another 20-25%. other misc. would then account for the remainder of the increase.

note that out-of-order execution, branch prediction, speculative execution, etc have all been part of risc technology for decades. the recent generations of i86 processors have negated much of the risc performance advantage by moving to risc processors with hardware layer that translates i86 instructions to risc micro-ops.

part of the issue is that cache miss delays (aka access to memory) counted in processor cycles are now comparable to 360-era disk access delays. multiprogramming/multitasking was introduced to give processors something to do while waiting for disk access. out-of-order execution and hyperthreading are comparable for modern technologies (keeping the processor units busy while waiting for stalled instruction access to memory).

370/195 allowed out-of-order execution with pipeline ... but stalled at conditional branch (having to wait to determine execution path that branch would take). normal codes ran about half peak rate on 370/195 (because of branch stalls) and there was proposal to do simulated multiprocessor (similar to modern hyperthread); two instruction streams, pair of PSWs, two sets of registers ... etc. ... trying to maintain to keep 370/195 running at peak processing rate.

modern branch prediction and speculative execution ... will do out-of-order execution along one path (before branch condition is determined). If the branch prediction is wrong, the incorrectly executed instructions are undone ... and processing resumes along the correct path.

recent post in this thread:
https://www.garlic.com/~lynn/2012l.html#28 X86 server

there was reference to older mainframe TPC benchmark ... there was some published work for z10 which was then prorated by 50/30 to give estimate for z196 ... as a means of making other thruput comparisons.

--
virtualization experience starting Jan1968, online at home since Mar1970

X86 server

Refed: **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **
From: lynn@GARLIC.COM (Anne & Lynn Wheeler)
Subject: Re: X86 server
Newsgroups: bit.listserv.ibm-main
Date: 26 Aug 2012 12:19:58 -0700
cfmpublic@NS.SYMPATICO.CA (Clark Morris) writes:
Are there any benchmarks available comparing a z series against a blade configuration doing the same work and comparing the cost per benchmark unit? Given the complexity of instruction sets for both Intel and the z series and the different nature of them, I agree with others that straight instruction speed comparisons may be meaningless. For example how much of the work for an i-o is done by the main processor on a blade versus on the z series? What is the MP effect on the blades versus the z series?

re:
https://www.garlic.com/~lynn/2012l.html#28 X86 server
https://www.garlic.com/~lynn/2012l.html#29 X86 server

both refer to TPC benchmarks ... which have benchmarks that are RDBMS transaction oriented with heavy disk i/o (as mentioned looking at number of transactions/thruput, cost of transactions/thruput, and power consumption of transactions/thruput)

Note that the e5-2600 blade is two socket-chip multiprocessor ... eight cores (or processors) per chip for total of 16 processors (simulating 32 processor with hyperthreading) ... benchmark at 527BIPS (compared to 50BIPS for 80processor z196). e5-4600 blade are out there (four sockets-chip multiprocessor, aggregate 32 processors, simulating 64 processors with hyperthreading) ... but having seen the dhrystone/bips benchmarks ... but expecting over 1TIP for e5-4600. This post mentions that mainframe sales of $5B last years translates into 180 $28m max. configured z196 ... which at 50BIPS represents aggregate of 9TIPS.
https://www.garlic.com/~lynn/2012l.html#20 X86 server

this has some e5-4600 benchmarks
http://www.intel.com/content/www/us/en/benchmarks/server/xeon-e5-4600.html

this has SPEC benchmarks for 64chip, 512 core-processor (no hyperthread)
http://www.sgi.com/company_info/newsroom/press_releases/2012/may/intel.html

Another part of the issue is that mainframe CKD disks haven't been manufactured for decades ... CKD being an extra layer of simulation (delay and overhead) on top of the same disks all the other platforms are using.

these recent posts reference the appearance of Harrier (morphs into SSA) and fiber-channel (mainframe ficon is built on fibre channel standard) in the late 80s and early 90s that were packetized serial technology (other variations on serial i/o technology would come along later).
https://www.garlic.com/~lynn/2012i.html#47 IBM, Lawrence Livermore aim to meld supercomputing, industries
https://www.garlic.com/~lynn/2012i.html#54 IBM, Lawrence Livermore aim to meld supercomputing, industries
https://www.garlic.com/~lynn/2012i.html#95 Can anybody give me a clear idea about Cloud Computing in MAINFRAME ?
https://www.garlic.com/~lynn/2012j.html#13 Can anybody give me a clear idea about Cloud Computing in MAINFRAME ?
https://www.garlic.com/~lynn/2012k.html#69 ESCON
https://www.garlic.com/~lynn/2012k.html#77 ESCON
https://www.garlic.com/~lynn/2012k.html#80 360/20, was 1132 printer history

a growing bottleneck for mainframe was the half-duplex channel architecture requiring synchronized end-to-end operation on every channel command and data transfer. the serialized i/o architecture that started to appear in the late 80s had dedicated outbound and inbound serial i/o data paths. The equivalent of a channel program was packaged as data and transmitted down the outbound channel. This would be followed by data-being written (on the same outbound channel as well as other packetized channel programs) and asynchronously with data being read flowing on the (dedicated) inbound channel.

Harrier was dual serial copper (out of Hursley from early 90s) ... that packetized SCSI commands and operated at 80mbits/sec concurrent in both directions. I mention here that I tried to evolved Harrier into interoperate with fibre-channel ... old post discussing meeting in Ellison's conference room early Jan1992
https://www.garlic.com/~lynn/95.html#13

However, instead it involved into proprietary SSA operating at 160mits/sec concurrent in both directions, fibre channel wiki
https://en.wikipedia.org/wiki/Fibre_Channel

from above:
When Fibre Channel started to compete for the mass storage market its primary competitor was IBM's proprietary Serial Storage Architecture (SSA) interface. Eventually the market chose Fibre Channel over SSA, depriving IBM of control over the next generation of mid- to high-end storage technology.

... snip ...

There were lots of discussion on the fibre channel standards mailing list about pok/mainframe channel engineers trying to do unnatural acts layering ficon ontop of the base fibre channel standard

The current fibre channel standard web site:
http://www.fibrechannel.org/

fiber channel standard wiki page ... lists earliest standard from 1994
https://en.wikipedia.org/wiki/List_of_Fibre_Channel_standards

I had been working off&on with LLNL on a number of things ... fibre channel standard work comes from 1988 time-frame with LLNL looking to standardized a serial technology they were using that had a non-blocking switch for interconnect. This old email mentions doing benchmark on 4341 for national lab looking at getting 70 machines based on the benchmark.
https://www.garlic.com/~lynn/2006y.html#email790220

customers looking at buying clusters of 4341 was a threat to POK mainframes (somewhat the current situation of blade clusters and POK mainframes) ... clusters of 4341 with greater aggregate processing and thruput was much cheaper and had much smaller footprint of equivalent POK mainframes. folklore is at one point, head of POK managed to have allocation of a critical 4341 manufacturing component cut in half. misc. old 43xx posts
https://www.garlic.com/~lynn/lhwemail.html#43xx

A big part of the myth around high mainframe i/o thruput comes from the big increase in the number channels needed for 3090. The issue was that from 3330 to 3380 disks, the transfer rate increased by factor of ten ... but the change from 3830 disk controller to 3880 disk controller radically increased the channel busy time for operations (other than pure transfer). The problem was that they went from 3830 fast horizontal microprocessor to a 3880 slow vertical microprocessor. When the 3090 engineers found out how bad the 3880 channel busy was going to be they realized they would have to drastically increase the number of channels ... in order to offset the drastically increased channel busy and to achieve the desired throughput (which increased the number of TCMs, which increased 3090 manufacturing costs; there were jokes that 3090 was going to charge the 3880 group for the cost increase in 3090 manufacturing).

Note that the technology used in server blades can be significantly more robust than what might be found in a desktop for a couple hundred dollars (there periodic equating i/o capability of server blades with what is typically found on entry desktop machines).

--
virtualization experience starting Jan1968, online at home since Mar1970

X86 server

Refed: **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **
From: lynn@GARLIC.COM (Anne & Lynn Wheeler)
Subject: Re: X86 server
Newsgroups: bit.listserv.ibm-main
Date: 26 Aug 2012 12:49:14 -0700
scott_j_ford@YAHOO.COM (Scott Ford) writes:
I saw the same exercise in a pharm. company trying to go from MVS, multiple Lpars to unix. Several millions of $$$ and it was a bust....some applications were difficult to convert

in the 90s, one of the biggest efforts was by the financial industry (large concentration in manhatten) to move from overnight batch window to straight-through processing ... using large numbers of "killer micros" ... where several billions were dumped down the drain. These efforts contributed to the "mainframe is dead" stories from the period.

"real-time" transactions had been added to traditional batch ... but the actual processing was still being down in the overnight batch window. With globalization, there was combination of more work as well as decreasing window size ... that was putting enormous pressure on the paradigm.

billions were spent on parallized implementation using large numbers "killer micros" implementing straight-through processing ... eliminated most of the work in the overnight batch window. They used some parallelization technology with roll-your-own implementations that looked good in the toy demos. However, they failed to do the speeds&feeds and when it came to production rollout ... the whole thing imploded horribly. The parallelization technology being used introduced an increase in overhead of 100 times (compared to cobol batch) ... totally swamping any anticipated throughput increase from large number of "killer micros"

I had done some simple speeds&feeds and pointed out the issue before deployments but was ignored. I also got to work on improving performance of cobol batch that ran everynight batch window on more than 40 maxed out mainframes (40+ needed to handle workload, datacenter took pride in saying no mainframe was older than 18months).

At least by the last half of the last decade, most of the major non-mainframe RDBMS vendors (including IBM) had made significant strides in non-mainframe RDBMS cluster-scale-up. I participated in demonstration of straight-through processing implementations that involved translating operations into fine-grain SQL operations that would could be easily parallelized by latest generation of non-mainframe RDBMS cluster implementations (more like factor of 3-5 times compared to cobol batch rather than 100 times). The financial industry standards organizations were interested but there were lots of comments there was still enormous resistance and risk aversion because of the lingering effects of the 90s disastrous failures.

these large financial institutions continue to be major mainframe customer market.

misc. past posts mentioning overnight batch window and/or straight-through processing
https://www.garlic.com/~lynn/2012.html#49 No internet in 1984
https://www.garlic.com/~lynn/2012c.html#13 Study links ultrafast machine trading with risk of crash
https://www.garlic.com/~lynn/2012c.html#25 Goldman Sachs P.R. Chief's Accidental Exit Interview
https://www.garlic.com/~lynn/2012e.html#49 US payments system failing to meet the needs of the digital economy
https://www.garlic.com/~lynn/2012f.html#0 Burroughs B5000, B5500, B6500 videos
https://www.garlic.com/~lynn/2012f.html#24 Time to competency for new software language?
https://www.garlic.com/~lynn/2012f.html#36 Time to competency for new software language?
https://www.garlic.com/~lynn/2012j.html#69 Monopoly/ Cartons of Punch Cards
https://www.garlic.com/~lynn/2012j.html#77 Monopoly/ Cartons of Punch Cards
https://www.garlic.com/~lynn/2012l.html#19 X86 server

--
virtualization experience starting Jan1968, online at home since Mar1970

Use another browser - Kaspersky follows suit

Refed: **, - **, - **, - **, - **, - **, - **, - **, - **, - **
From: lynn@garlic.com (Lynn Wheeler)
Date: 26 Aug, 2012
Subject: Use another browser - Kaspersky follows suit
Blog: Financial Cryptography
Use another browser - Kaspersky follows suit
https://financialcryptography.com/mt/archives/001384.html

Kaspersky Lab upgrades for online payments security
http://www.finextra.com/news/announcement.aspx?pressreleaseid=45995

95/96 time-frame, consumer dailup online banking were making presentations at industry conferences that they were moving to internet ... a major motivation was consumer support costs associated with serial-port dial-up modems (major support costs would effectively be offloaded to ISPs). At the same time the commercial/cash-management dialup online banking were saying they would *NEVER* move to the internet (because of a long list of security reasons ... which have since come to pass since they began moving to the internet).

Within the past couple years, the feds have been recommending that businesses have a dedicated PC that is *NEVER* used for anything else than online banking (as a partial return to the days of online banking). This could be considered similar to the recommendation of having a different browser that is dedicated to only being used for online banking.

In the late 90s, there was lots of work being done on consumer smartcards for authentication as countermeasure to stealing credentials ... as well as the EU "FINREAD" standard as countermeasure to compromised PCs. Then there was a large project in the early part of this century with consumer smartcards and give-away of serial-port cardreaders. The disastrous consumer support problems in the wake of the give-away resulted in rapidly spreading opinion in the industry that smartcards weren't practical in the consumer market (when the problem was actually the give-way of serial-port readers; demonstrating that all the institutional knowledge about serial-port consumer support problems had evaporated in the span of a couple years; note that serial-port issues were major motivation for development of USB ... and the serial-port give-away cardreaders were likely gotten in firesale on obsolete technology).

This resulted significant retrenching from any card oriented solution in the consumer market (including the EU "FINREAD" countermeasure for both skimmed credentials and compromised machine). misc. past posts mentioning FINREAD
https://www.garlic.com/~lynn/subintegrity.html#finread

Within a year or two, there were some non-card "SAFE" payment products developed (not as good as hardware tokens but better than what we have now) which saw high acceptance between the e-merchants (accounting for approx. 70% of online transactions of the period). However, merchants had been indoctrinated for decades that interchange rate was proportional to fraud rates ... and they were expecting order of magnitude interchange rate reduction from the *SAFE* products. Then the cognitive dissonance and the whole thing cratered when they were told that instead of major reduction in interchange rates (for the *SAFE* products), it would instead effectively be a surcharge on the highest rate they were already paying.

--
virtualization experience starting Jan1968, online at home since Mar1970

Interesting News Article

From: Anne & Lynn Wheeler <lynn@garlic.com>
Subject: Re: Interesting News Article
Newsgroups: rec.arts.sf.written, alt.folklore.computers
Date: Sun, 26 Aug 2012 21:39:02 -0400
"John F. Eldredge" <john@jfeldredge.com> writes:
That reminds me of living in a college dormitory. If anyone flushed a toilet, the shower water would immediately become much hotter. The custom was for anyone about to flush a toilet to call out a warning. However, if the person flushing the toilet was on a different floor than the person showering, you didn't get any warning.

berkeley folklore about cdc 6600 having thermal shutdown some time every week ... loss of cooling in the machine room. eventually they determined that it was morning class break at the same time lawn sprinklers were going ... combination of all the toilets flushing and the sprinklers dropped water pressure to datacenter cooling.

misc. past posts mentioning 6600 thermal shutdown
https://www.garlic.com/~lynn/2002d.html#6 IBM Mainframe at home
https://www.garlic.com/~lynn/2008i.html#57 Microsoft versus Digital Equipment Corporation
https://www.garlic.com/~lynn/2008i.html#96 A Blast from the Past
https://www.garlic.com/~lynn/2009c.html#14 Assembler Question
https://www.garlic.com/~lynn/2009j.html#72 A Complete History Of Mainframe Computing

--
virtualization experience starting Jan1968, online at home since Mar1970

X86 server

Refed: **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **
From: lynn@GARLIC.COM (Anne & Lynn Wheeler)
Subject: Re: X86 server
Newsgroups: bit.listserv.ibm-main
Date: 27 Aug 2012 07:59:04 -0700
John.McKown@HEALTHMARKETS.COM (McKown, John) writes:
CA-7 has a similar function to run "cross platform" work. It requires a "daemon" be running on the remote side. <WARNING type="plug">I like Co:Z Launcher from Dovetailed Technologies to do this. It only requires a standard SSH server on the remote end. And I can afford it (it is zero cost.) </WARNING>

part of the issue is the MVS evolved from a paradigm where people submitted card decks and the actual execution occurred at much later period ... with at most an operator present ... the responsible person was no where around. the unix & desktop platforms evolved from the exact opposite paradigm ... the computer was directly interacting with the person executing the application. those platforms have had to do quite a bit of evolution to handle server&unattended operation.

however, there has some interesting evolution on their server side ... the megadatacenters with hundreds of thousands of blades (and millions of processors) with provisioning for on-demand use is quite remarkable ... I doubt if anybody is claiming current mainframe operating systems are prepared to run several hundred thousand blades in a megadatacenter ... including allowing an entity to do on-demand, dynamically provision 17,000 cores for 240TFLOPs (for a "batch" supercomputer) @ $1,2479/hr. recent posts mentioning somebody doing just that with Amazon cloud:
https://www.garlic.com/~lynn/2012.html#78 Has anyone successfully migrated off mainframes?
https://www.garlic.com/~lynn/2012.html#80 Article on IBM's z196 Mainframe Architecture
https://www.garlic.com/~lynn/2012.html#82 Has anyone successfully migrated off mainframes?
https://www.garlic.com/~lynn/2012b.html#28 New IBM mainframe instructions
https://www.garlic.com/~lynn/2012b.html#30 New IBM mainframe instructions

for one thing, a single mega-datacenter is estimated to be more processing power than the aggregate of all mainframes in the world today.

This article from last year
http://news.cnet.com/8301-13846_3-57349321-62/amazon-takes-supercomputing-to-the-cloud/

The dynamic, on-demand amazon cloud "supercomputer" is compared to the Fujitsu K Computer ... that operates at 10 petaflops (10,000tflops), has 864 racks, 88,128 interconnected processors and estimated total provisioned cost of $20M (less than maxed out 80 processor z196 @ $28M, rated at 50BIPS); $23,148/rack, $227/processor, $2000/TFLOP, $2/BFLOP, 113BFLOP/processor, 11,576TFLOP/rack ... 102processors/rack

By comparison, 80 processor z196 @28M and 50BIPS works out to $350,000/processor, $560,000/BIPS, and 625MIPS/processor.

more recent article about on-demand, dynamic, amazon supercomputer
http://arstechnica.com/business/2012/04/4829-per-hour-supercomputer-built-on-amazon-cloud-to-fuel-cancer-research/

from above:
It ran for three hours on the night of March 30, at a cost of $4,828.85 per hour. Getting up to 51,132 cores required spinning up 6,742 Amazon EC2 instances running CentOS Linux. This virtual supercomputer spanned the globe, tapping data centers in four continents and every available Amazon region, from Tokyo, Singapore, and Sao Paolo, to Ireland, Virginia, Oregon, and California. As impressive as it sounds, such a cluster can be spun up by anyone with the proper expertise, without talking to a single employee of Amazon.

... snip ...

Not sure what an EC2 instance is made of for this (&/or if they are all the same), an e5-2600 would have 16 cores and 6742 instances would be aggregate of 107,872 cores (aka processors).

past posts in thread:
https://www.garlic.com/~lynn/2012l.html#16 X86 server
https://www.garlic.com/~lynn/2012l.html#18 X86 server
https://www.garlic.com/~lynn/2012l.html#19 X86 server
https://www.garlic.com/~lynn/2012l.html#20 X86 server
https://www.garlic.com/~lynn/2012l.html#25 X86 server
https://www.garlic.com/~lynn/2012l.html#28 X86 server
https://www.garlic.com/~lynn/2012l.html#29 X86 server
https://www.garlic.com/~lynn/2012l.html#30 X86 server
https://www.garlic.com/~lynn/2012l.html#31 X86 server

--
virtualization experience starting Jan1968, online at home since Mar1970

PDP-10 system calls, was 1132 printer history

Refed: **, - **, - **, - **
From: Anne & Lynn Wheeler <lynn@garlic.com>
Subject: Re: PDP-10 system calls, was 1132 printer history
Newsgroups: comp.lang.pl1, alt.folklore.computers
Date: Mon, 27 Aug 2012 13:41:02 -0400
John Levine <johnl@iecc.com> writes:
So I gather you'd say that the S/370 and S/390 weren't compatible with the S/360, since the latter two included new larger address schemes?

The various models of the PDP-10 were similar enough that you could move application software from an older model to a newer one without having to rewrite it. That's what mattered.


modulo 370-xa added 31-bit virtual addressing ... but 24-bit addressing mode continued to be supported for legacy software.

z with 64-bit addressing still supports 24-bit and 31-bit addressing modes for legacy software
http://publibz.boulder.ibm.com/cgi-bin/bookmgr_OS390/BOOKS/dz9zr003/3.1?SHELF=&DT=20040504121320&CASE=
and
http://publibz.boulder.ibm.com/cgi-bin/bookmgr_OS390/BOOKS/dz9zr003/3.2.2?DT=20040504121320#HDR03AH20

from above:
The size of effective addresses is controlled by bits 31 and 32 of the PSW, the extended-addressing-mode bit and the basic-addressing-mode bit, respectively. When bits 31 and 32 are both zero, the CPU is in the 24-bit addressing mode, and 24-bit operand and instruction effective addresses are specified. When bit 31 is zero and bit 32 is one, the CPU is in the 31-bit addressing mode, and 31-bit operand and instruction effective addresses are specified. When bits 31 and 32 are both one, the CPU is in the 64-bit addressing mode, and 64-bit operand and instruction effective addresses are specified (see "Address Generation" in topic 5.2).

... snip ...

as an aside, 360/67 supported 24-bit and 32-bit addressing modes.

--
virtualization experience starting Jan1968, online at home since Mar1970

PDP-10 system calls, was 1132 printer history

Refed: **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **
From: Anne & Lynn Wheeler <lynn@garlic.com>
Subject: Re: PDP-10 system calls, was 1132 printer history
Newsgroups: comp.lang.pl1, alt.folklore.computers
Date: Mon, 27 Aug 2012 17:10:43 -0400
glen herrmannsfeldt <gah@ugcs.caltech.edu> writes:
It can only be set in supervisor mode, and no systems were known to set it. Not by IBM, or other known to IBM.

It would have been much different if it could be set in problem state. (Such as the usual SPM mask bits.)

Besides, it was designed for an ASCII-8 code that never appeared. (The low seven bits aren't ASCII-7.)


the biggest computer goof ever (ascii support)
https://web.archive.org/web/20180513184025/http://www.bobbemer.com/P-BIT.HTM
more ascii
https://web.archive.org/web/20180513184025/http://www.bobbemer.com/ASCII.HTM

recent posts in this thread:
https://www.garlic.com/~lynn/2012l.html#23 PDP-10 system calls, was 1132 printer history
https://www.garlic.com/~lynn/2012l.html#26 PDP-10 system calls, was 1132 printer history
https://www.garlic.com/~lynn/2012l.html#27 PDP-10 system calls, was 1132 printer history
https://www.garlic.com/~lynn/2012l.html#35 PDP-10 system calls, was 1132 printer history

--
virtualization experience starting Jan1968, online at home since Mar1970

S/360 architecture, was PDP-10 system calls

Refed: **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **
From: Anne & Lynn Wheeler <lynn@garlic.com>
Subject: Re: S/360 architecture, was PDP-10 system calls
Newsgroups: comp.lang.pl1, alt.folklore.computers
Date: Tue, 28 Aug 2012 16:25:32 -0400
Findlay William <yaldnif.w@blueyonder.co.uk> writes:
They bought the paging patents that originated with the Ferranti Atlas, from the UK NRDC to which they had been assigned (IIRC). The 370 VM (not VM/370) ads did not actually claim that IBM invented paging, but they strongly implied it. They were the cause of much hilarity in the UK.

{NRDC = National Research Development Corporation, a quango}


there was ibm system journel article stating something to that effect, one of the co-workers from the science center wrote a letter to the system journel editor pointing out all the mis-statements ... citing sources (and suggesting that they should print correction). he got back a letter from the editor effectively saying that it wasn't in the best interest of the company to print a correction.

one the other hand ... melinda's vm370 history cites in mid-60s, some of the early science center people saying that atlas paging had problems and nobody in the company knew why ... aka this was leading up to science center wanting the official corporate virtual memory charter ... and it went to tss/360 instead (and nobody at tss/360 knew what were the problems with atlas paging).

from melinda's history (from past discussions problems may have been related to lack of page thrashing controls):
What was most significant was that the commitment to virtual memory was backed with no successful experience. A system of that period that had implemented virtual memory was the Ferranti Atlas computer, and that was known not to be working well. What was frightening is that nobody who was setting this virtual memory direction at IBM knew why Atlas didn't work.

... snip ...

this was before the ACM paper in '68 about working set dispatcher that included page thrashing controls ... based on "local" LRU page replacement. As an undergraduate in '68 I had done a form of page thrashing controls with a clock-like global LRU replacement for cp67 (which I believed much more efficient than the ACM '68 working set dispatcher)

roll forward to early '80s, somebody (co-worker of Jim Gray at Tandem) was working on stanford PHD on "clock" and global LRU replacement ... and the awarding of the PHD was being strongly opposed/fought by the "local LRU" replacement forces. Jim was aware of the work I had done as undergraduate and at SIGOPS (asilomor 14-16dec81) asks me to weigh in on the argument ... past post
https://www.garlic.com/~lynn/2006w.html#46

The Grenoble science center in the early 70s had modified their cp/67 to correspond with the '68 ACM working set dispatcher, published results in CACM ... and had also shared a lot of raw data with me. Basically, the Grenoble cp67 working set dispatcher with 1mbyte 360/67 (155 4k pages after fixed storage requirements) and 35 users got approx. same level of performance as the Cambridge wheeler cp67 with 768k 360/67 (104 4k pages after fixed storage requirements) and 75-80users (my stuff on machine with 1/3rd less paging space and twice the users could perform as well as grenoble working set dispatcher).

unfortunately it took me nearly year to get company approval to send a response ... hopefully it was because they thought they were punishing me for one thing or another (and not because research was trying to weigh in on the other side of the "academic" dispute):
https://www.garlic.com/~lynn/2006w.html#email821019

misc. past posts/discussing mentioning Altas paging problem quote:
https://www.garlic.com/~lynn/2000f.html#78 TSS ancient history, was X86 ultimate CISC? designs)
https://www.garlic.com/~lynn/2001h.html#10 VM: checking some myths.
https://www.garlic.com/~lynn/2002.html#42 a.f.c history checkup... (was What specifications will the standard year 2001 PC have?)
https://www.garlic.com/~lynn/2003b.html#1 Disk drives as commodities. Was Re: Yamhill
https://www.garlic.com/~lynn/2005o.html#4 Robert Creasy, RIP
https://www.garlic.com/~lynn/2006i.html#30 virtual memory
https://www.garlic.com/~lynn/2007e.html#1 Designing database tables for performance?
https://www.garlic.com/~lynn/2007r.html#51 Translation of IBM Basic Assembler to C?
https://www.garlic.com/~lynn/2007r.html#64 CSA 'above the bar'
https://www.garlic.com/~lynn/2007t.html#54 new 40+ yr old, disruptive technology
https://www.garlic.com/~lynn/2007u.html#77 IBM Floating-point myths
https://www.garlic.com/~lynn/2007u.html#79 IBM Floating-point myths
https://www.garlic.com/~lynn/2011d.html#81 Multiple Virtual Memory

misc. past posts mentioning the academic dispute &/or grenoble cp67 "working set" dispatcher compared to cambridge cp67 system:
https://www.garlic.com/~lynn/94.html#1 Multitasking question
https://www.garlic.com/~lynn/99.html#18 Old Computers
https://www.garlic.com/~lynn/2002c.html#49 Swapper was Re: History of Login Names
https://www.garlic.com/~lynn/2002o.html#30 Computer History Exhibition, Grenoble France
https://www.garlic.com/~lynn/2004.html#25 40th anniversary of IBM System/360 on 7 Apr 2004
https://www.garlic.com/~lynn/2004c.html#59 real multi-tasking, multi-programming
https://www.garlic.com/~lynn/2004g.html#13 Infiniband - practicalities for small clusters
https://www.garlic.com/~lynn/2004i.html#0 Hard disk architecture: are outer cylinders still faster than
https://www.garlic.com/~lynn/2004q.html#73 Athlon cache question
https://www.garlic.com/~lynn/2005d.html#37 Thou shalt have no other gods before the ANSI C standard
https://www.garlic.com/~lynn/2005d.html#48 Secure design
https://www.garlic.com/~lynn/2005f.html#47 Moving assembler programs above the line
https://www.garlic.com/~lynn/2005h.html#15 Exceptions at basic block boundaries
https://www.garlic.com/~lynn/2005m.html#28 IBM's mini computers--lack thereof
https://www.garlic.com/~lynn/2005n.html#23 Code density and performance?
https://www.garlic.com/~lynn/2006f.html#0 using 3390 mod-9s
https://www.garlic.com/~lynn/2006i.html#31 virtual memory
https://www.garlic.com/~lynn/2006i.html#36 virtual memory
https://www.garlic.com/~lynn/2006i.html#42 virtual memory
https://www.garlic.com/~lynn/2006j.html#17 virtual memory
https://www.garlic.com/~lynn/2006l.html#14 virtual memory
https://www.garlic.com/~lynn/2006q.html#19 virtual memory
https://www.garlic.com/~lynn/2006q.html#21 virtual memory
https://www.garlic.com/~lynn/2006r.html#34 REAL memory column in SDSF
https://www.garlic.com/~lynn/2006w.html#46 The Future of CPUs: What's After Multi-Core?
https://www.garlic.com/~lynn/2007c.html#56 SVCs
https://www.garlic.com/~lynn/2007s.html#5 Poster of computer hardware events?
https://www.garlic.com/~lynn/2007u.html#79 IBM Floating-point myths
https://www.garlic.com/~lynn/2008c.html#65 No Glory for the PDP-15
https://www.garlic.com/~lynn/2008e.html#16 Kernels
https://www.garlic.com/~lynn/2008h.html#79 Microsoft versus Digital Equipment Corporation
https://www.garlic.com/~lynn/2008m.html#7 Future architectures
https://www.garlic.com/~lynn/2010f.html#85 16:32 far pointers in OpenWatcom C/C++
https://www.garlic.com/~lynn/2010f.html#89 16:32 far pointers in OpenWatcom C/C++
https://www.garlic.com/~lynn/2011.html#70 Speed of Old Hard Disks
https://www.garlic.com/~lynn/2011c.html#8 The first personal computer (PC)
https://www.garlic.com/~lynn/2011d.html#82 Multiple Virtual Memory
https://www.garlic.com/~lynn/2011f.html#73 Wylbur, Orvyl, Milton, CRBE/CRJE were all used (and sometimes liked) in the past
https://www.garlic.com/~lynn/2011l.html#6 segments and sharing, was 68000 assembly language programming
https://www.garlic.com/~lynn/2011p.html#53 Odd variant on clock replacement algorithm
https://www.garlic.com/~lynn/2012g.html#21 Closure in Disappearance of Computer Scientist
https://www.garlic.com/~lynn/2012g.html#25 VM370 40yr anniv, CP67 44yr anniv

--
virtualization experience starting Jan1968, online at home since Mar1970

S/360 architecture, was PDP-10 system calls

Refed: **, - **, - **
From: Anne & Lynn Wheeler <lynn@garlic.com>
Subject: Re: S/360 architecture, was PDP-10 system calls
Newsgroups: comp.lang.pl1, alt.folklore.computers
Date: Tue, 28 Aug 2012 20:03:47 -0400
William Findlay <yaldnif.w@blueyonder.co.uk> writes:

http://sounds.bl.uk/Oral-history/Eminent-scientists/021M-C1379X0011XX-0008V0

Professor Dai Edwards (one of the designers of the Atlas) talks about the paging ("one-level store") patents. He says nothing whatever to suggest that paging on Atlas "did not work", or "had problems".

I have a slight suspicion that this may be a self-aggrandizing IBM myth.


re:
https://www.garlic.com/~lynn/2012l.html#37 S/360 architecture, was PDP-10 system calls

Melinda's Atlas quote was from Comeau's CP/40 presentation at 1982 SEAS meeting in Europe (aka SEAS is european share) ... scan here
https://www.garlic.com/~lynn/cp40seas1982.txt

discussion from last year ... it wasn't a page thrashing control issue and/or global/lru issue since there was no concurrent execution ... atlas completely swapped address space pages on task switch
https://www.garlic.com/~lynn/2011e.html#2 Multiple Virtual Memory

from above post:
http://www.ics.uci.edu/~bic/courses/JaverOS/ch8.pdf

from above:
Paging can be credited to the designers of the ATLAS computer, who employed an associative memory for the address mapping [Kilburn, et al., 1962]. For the ATLAS computer, |w| = 9 (resulting in 512 words per page), |p| = 11 (resulting in 2024 pages), and f = 5 (resulting in 32 page frames). Thus a 220-word virtual memory was provided for a 214- word machine. But the original ATLAS operating system employed paging solely as a means of implementing a large virtual memory; multiprogramming of user processes was not attempted initially, and thus no process id's had to be recorded in the associative memory. The search for a match was performed only on the page number p.

... snip ...

The science center initial CP40 implementation was adding associative virtual memory hardware to 360/40. A difference between the Atlas hardware implementation and the implementation for 360/40 was that the 360/40 implementation included a process identifier.

The implication from above could be that ATLAS totally swapped all virtual pages anytime it switched users/virtual-address space ... not attempting concurrent users/tasks. Such a implementation would also not need dynamic limit on concurrent executing tasks as page thrashing control (aka some form of working set control). If it did LRU replacement, there would be no difference between local & global.

--
virtualization experience starting Jan1968, online at home since Mar1970

The IBM zEnterprise EC12 announcment

Refed: **, - **, - **, - **, - **, - **, - **, - **
From: lynn@GARLIC.COM (Anne & Lynn Wheeler)
Subject: Re: The IBM zEnterprise EC12 announcment
Newsgroups: bit.listserv.ibm-main
Date: 29 Aug 2012 06:40:55 -0700
John.McKown@HEALTHMARKETS.COM (McKown, John) writes:
Why am I getting a vision of Medusa? Or perhaps a sea anemone? Tentacles reaching out to entrap prey. Pity the small servers in the room, getting lashed with FICON cables. <GRIN>

IBM 1991 (power) cluster scale-up with fiber-channel (FICON is layered on top of base fiber-channel standard) was in fact code-named MEDUSA ... old email (fiber-channel was common use in non-mainframe long before FICON):
https://www.garlic.com/~lynn/lhwemail.html#medusa

the cluster scale-up for commercial (128 systems), also referenced here regarding early jan1992 meeting in ellison's conference room
https://www.garlic.com/~lynn/95.html#13

as part of IBM's ha/cmp product ... old posts
https://www.garlic.com/~lynn/subtopic.html#hacmp

mainframe DB2 were complaining that if I was allowed to continue, it would be a minimum of five years (if not decades) ahead of them. the issue was this predated IBM's non-mainframe DB2 products, so had to go to other vendors to get RDBMS on IBM's non-mainframes. These vendors tended to have relatively common source base for both their vax-cluster and unix platforms ... so the issue was to adapt their vax-cluster support to unix platform and scale it up.

possibly within hrs of the last MEDUSA email end of jan92, the cluster-scale-up was transferred and we were told that we couldn't work on anything with more than four processors. A couple weeks later, it was announced as supercomputer for numerical intensive only ... press from 17Feb1992 for scientific and technical only
https://www.garlic.com/~lynn/2001n.html#6000clusters1
another press item from 11May1992
https://www.garlic.com/~lynn/2001n.html#6000clusters2

nearly 20yrs later ... "From the Annals of Release No Software Before Its Time" (Power DB2 with cluster of 100 systems)
https://www.garlic.com/~lynn/2009p.html#43

rebranded pureScale ...
http://www-03.ibm.com/press/us/en/pressrelease/28593.wss

current tpc-c (rdbms) results/rankings
http://www.tpc.org/tpcc/results/tpcc_perf_results.asp

--
virtualization experience starting Jan1968, online at home since Mar1970

PDP-10 system calls, was 1132 printer history

Refed: **, - **, - **, - **
From: Anne & Lynn Wheeler <lynn@garlic.com>
Subject: Re: PDP-10 system calls, was 1132 printer history
Newsgroups: comp.lang.pl1, alt.folklore.computers
Date: Wed, 29 Aug 2012 10:11:19 -0400
glen herrmannsfeldt <gah@ugcs.caltech.edu> writes:
I believe the 370/165 was another. Well, that is a 370 not a 360, but still. (And a 370 without virtual storage.)

all 370s were retrofitted virtual memory ... extra cost item for 370/155 and 370/165. there was major problems with retrofitting virtual memory hardware to 370/165 ... which was going to result in (at least) six month schedule slip in the announce of 370 virtual memory. Eventually it was escalated and the decision was to drop a bunch of 370 virtual memory stuff (that 165 was having trouble with) to keep things on schedule. the problem became that all the other 370 models had to go back and remove the dropped features from their implementations ... also any software already written to use the drop features had to be reworked.

vm370/cms biggest hit was the dropping of 370 virtual memory segment r/o protect. morph from cp67/cms to vm370/cms was to reorg cms so that it could have shared read-only 370 "64k-byte segments" ... and use r/o segment protect to prevent changes propagating across virtual address spaces. vm370 then had to fall-back to a really ugly hack manipulating storage protect keys and protect key in the psw.

--
virtualization experience starting Jan1968, online at home since Mar1970

The IBM zEnterprise EC12 announcment

Refed: **, - **, - **, - **, - **
From: lynn@GARLIC.COM (Anne & Lynn Wheeler)
Subject: Re: The IBM zEnterprise EC12 announcment
Newsgroups: bit.listserv.ibm-main
Date: 29 Aug 2012 10:02:37 -0700
lynn@GARLIC.COM (Anne & Lynn Wheeler) writes:
nearly 20yrs later ... "From the Annals of Release No Software Before Its Time" (Power DB2 with cluster of 100 systems)
https://www.garlic.com/~lynn/2009p.html#43

rebranded pureScale ...
http://www-03.ibm.com/press/us/en/pressrelease/28593.wss

current tpc-c (rdbms) results/rankings
http://www.tpc.org/tpcc/results/tpcc_perf_results.asp


re:
https://www.garlic.com/~lynn/2012l.html#39 The IBM zEnterprise EC12 announcment

EC12 announcement estimates it has 30% increase in DBMS thruput (compared to z196)

old report estimated 5m tpmC for max configured z10 which could give a guestimate of 7.5m tpmC for max configured z196 ... and at 30% increase would give guestimate of 9.74m tpmC for max configured EC12. that could put EC12 just below number two in the current tpmC rankings ... but presumably an enormous way off in terms of price/tpmC.

--
virtualization experience starting Jan1968, online at home since Mar1970

I.B.M. Mainframe Evolves to Serve the Digital World

Refed: **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **
From: lynn@garlic.com (Lynn Wheeler)
Date: 30 Aug, 2012
Subject: I.B.M. Mainframe Evolves to Serve the Digital World
Blog: Greater IBM
I.B.M. Mainframe Evolves to Serve the Digital World
http://www.nytimes.com/2012/08/28/technology/ibm-mainframe-evolves-to-serve-the-digital-world.html

x-over from (linkedin) "Old Geek" IBM mainframe evolves to Serve the Digital World
http://lnkd.in/JR_DNM

which has extended discussion of mainframe/non-mainframe comparison

in addition to this referenced thread in ibm-main (mainframe) mailing list
https://groups.google.com/forum/?fromgroups=#!topic/bit.listserv.ibm-main/a0YcLe6F8JY

there is this more recent discussion in ibm-main mailing list
https://groups.google.com/forum/?fromgroups=#!topic/bit.listserv.ibm-main/PBmWoIysFa0

the big cloud operators are doing mega-datacenters ... with extensive RAS involving millions of processor ... and an individual mega-datacenter has more computing power than the aggregate of all mainframes in the world today with something like 100,000 times better price/performance

With hundreds of thousands of blades and millions of processors ... the large cloud operators have been pioneers in all sorts of things ... they pioneered evaluation of optimal price/performance, reliability commodity components and openly publish results with claims that they assemble their own blades at 1/3rd the cost of brand name blades. With radical reduction in cost of dataprocessing components they've pioneered people/computing power/computing, cooling/computing, green datacenter techniques ... again openly publishing the results (aka with radical reduction in the cost of the dataprocessing components, other aspects become larger part of total cost of ownership).

They've done a lot of work on optimally selecting locations for building new megadatacenters ... sometimes in remote locations ... selecting for power availability, water/cooling availability, year-round temperature & humidity (for cooling costs), etc. Public announcements of deals with local governments for new megadatacenters usually mention well under 1000 jobs (aka people-staff) for all aspects of operating, maintaining, running such a megadatacenter (for operation with more dataprocessing power than the aggregate of all mainframes in the world today).

Part of the large cloud operations are large-scale, instantaneous, on-demand ... and so they have done a lot of work with component vendors on dropping power (& cooling) to zero when component is idle ... but able to come online nearly instantaneously.

Part of openly publishing the findings and evaluations is to encourage the component vendors to improve their products (even if it may provide competitive advantage to other large cloud vendors). The megadatacenters have evaluations for total cost of operation (including optimal "green") ... similar to what TPC & SPEC council do for individual types of benchmarking (where in addition to having rankings based on aggregate throughput, they also have rankings based on cost/operation and power/operation).
http://www.tpc.org/ .
http://www.spec.org/

article on subject:
http://www.businessweek.com/the_thread/techbeat/archives/2005/12/vmware_goes_mai.html

co-location datacenter evaluations
http://www.colocationamerica.com/data-center/tier-standards-overview.htm

PEU metric
http://www.greenbiz.com/blog/2009/01/20/its-time-know-green-its-best-metric-pue
PEU of 1.15 for facebook datacenter
http://www.greenbiz.com/news/2010/01/26/facebook-status-update-were-opening-green-data-center
other discussion
http://www.greenbiz.com/blog/2011/11/21/facebook-yahoo-qts-data-centers-land-leed-ratings

article on cloud on-demand scale-up ... how much dataprocessing at charge/hr (mentions better rates are available for prescheduled)
http://news.cnet.com/8301-13846_3-57349321-62/amazon-takes-supercomputing-to-the-cloud/

more recent on-demand scale-up
http://arstechnica.com/business/2012/04/4829-per-hour-supercomputer-built-on-amazon-cloud-to-fuel-cancer-research

max. configured z196 with 80 processors is rated at 50BIPs and goes for $28M ($350,000/processor, $560,000/BIPS, 625MIPS/processor)

IBM has base list price of $1815 for e5-2600 blade. There are various processor configurations for e5-2600 (two socket-chip, 8processors/socket-chip, 16processors) ... but some are benchmarked at 527BIPS ... using IBM base price, $113.44/processor, $3.44/BIPS, 33BIPS/processor. Large cloud operator claims of being able to assemble blades at 1/3rd cost of brand name blades potentially has it down to $1.14/BIPS.

The dynamic, on-demand amazon cloud "supercomputer" is compared to the Fujitsu K Computer ... that operates at 10 petaflops (10,000tflops), has 864 racks, 88,128 interconnected processors and estimated total provisioned cost of $20M (less than maxed out 80 processor z196 @ $28M, rated at 50BIPS); $23,148/rack, $227/processor, $2000/TFLOP, $2/BFLOP, 113BFLOP/processor, 11,576TFLOP/rack ... 102processors/rack

the z196 prices and the e5-2600 prices are equivalent from ibm. does ibm publish any additional numbers for its z196 and its e5-2600 blades?

one of the quotes from this article regarding the amazon on-demand supercomputer ... 51,132 cores (aka processors) @$4829/hr
http://arstechnica.com/business/2012/04/4829-per-hour-supercomputer-built-on-amazon-cloud-to-fuel-cancer-research

from above:
As impressive as it sounds, such a cluster can be spun up by anyone with the proper expertise, without talking to a single employee of Amazon.

... snip ...

Note assume the EC2 instances "spun" up are all e5-2600 ... then that would be an aggregate of 1,687,356 BIPS or the equivalent of 2,704,096 (z196) processors (at 625MIPS/processor) ... or approx. 33,801 (max. configured) 80 processor z196 machines ... at price of $28M each ... would come out to approx. trillion dollars. IBM statements are that it has been doing approx. $5B/year in mainframe business ... that would translate into approx. 180 (max. configured 80 processor) z196 per year. 33,801 z196 machines at a rate of 180/year would represent approx. 188yrs of z196 sales ... just for the equivalent of the example on-demand supercomputer (carved from an available subset of the amazon cloud).

--
virtualization experience starting Jan1968, online at home since Mar1970

Judge dismisses BancorpSouth defense in online theft suit

From: lynn@garlic.com (Lynn Wheeler)
Date: 30 Aug, 2012
Subject: Judge dismisses BancorpSouth defense in online theft suit
Blog: Financial Crime Risk, Fraud and Security
Judge dismisses BancorpSouth defense in online theft suit
http://www.computerworld.com/s/article/9230730/Judge_dismisses_BancorpSouth_defense_in_online_theft_suit

financial blog discussion of the ruling

Four Planks to support the next evolution in secure browsing
http://financialcryptography.com/mt/archives/001385.html

related to this previous blog discussion on use of browser for online banking:

Use another browser - Kaspersky follows suit
http://financialcryptography.com/mt/archives/001384.html

--
virtualization experience starting Jan1968, online at home since Mar1970

Preparing for War with China

From: lynn@garlic.com (Lynn Wheeler)
Date: 30 Aug, 2012
Subject: Preparing for War with China
Blog: Boyd Strategy
An intersting read...with a brief mention of Boyd.
http://lnkd.in/nFRhH3

Preparing for War with China
http://nationalinterest.org/commentary/preparing-war-china-7352

so much of AirSea is still 2nd generation.

First Battle: Operation Starlite and the Beginning of the Blood Debt in Vietnam (Otto Lehrack) pg165|loc2900-2904
Perhaps the most important reason for the so-so result was that the Viet Cong had gained an enormous appreciation of the Marines' ability to project power from the sea as a result of Starlite. Never again in the course of the war did they permit their units to tarry on the coastal plain. When they had a job to do near the water, they came in and did it, and then they fled inland again. Although they developed good antiaircraft techniques and weaponry during the war they had neither the ordnance nor the expertise to thwart an amphibious landing force.

... snip ...

so one of the lessons for the Chinese is countermeasures for amphibious operation. Another point in the book was Westermoreland Army background regarding large 2nd generation encounters (tank slug-fests in Europe) pg167/loc2924-27:
Ironically, Starlite, a Marine victory, reinforced General Westmoreland's notion that carrying the fight to main force enemy units was the key to success in Vietnam. This belief helped keep pacification, the Marines' focal point, in a secondary role.

... snip ...

Some common sense on S. China Sea dispute, where US China hawks are losing all perspective
http://thomaspmbarnett.com/globlogization/2012/8/20/some-common-sense-on-s-china-sea-dispute-where-us-china-hawk.html

Top 5 Obstacles to AirSea Battle
http://thediplomat.com/the-naval-diplomat/2012/08/20/top-5-obstacles-to-airsea-battle/

The South China Sea's Gathering Storm
http://online.wsj.com/article/SB10000872396390444184704577587483914661256.html

--
virtualization experience starting Jan1968, online at home since Mar1970

Introducing John Boyd

Refed: **, - **, - **, - **
From: lynn@garlic.com (Lynn Wheeler)
Date: 30 Aug, 2012
Subject: Introducing John Boyd
Blog: The Naval Diplomat
Introducing John Boyd
http://thediplomat.com/the-naval-diplomat/2012/08/26/introducing-john-boyd/

Time article behind paywall, but mostly lives free at the wayback machine (except pg.8; SECDEF blamed Boyd for the article and tried to have him banned from the pentagon for life)
https://web.archive.org/web/20070320170523/http://www.time.com/time/magazine/article/0,9171,953733,00.html
also
https://content.time.com/time/magazine/article/0,9171,953733,00.html

tribute to Boyd (from USNI proceedings) ... also comments that things hadn't improved since the Time article
http://radio-weblogs.com/0107127/stories/2002/12/23/genghisJohnChuckSpinneysBioOfJohnBoyd.html

One of Boyd's biographies mentioned he did tour commanding spook base; his Organic Design for Command and Control makes an oblique reference to NKP (pg.28: My use of "legal eagle" and comptroller at NKP). He would claim that early on he said it wouldn't work so the assignment may have been punishment. NKP description (gone 404, but lives on at wayback machine):
https://web.archive.org/web/20030212092342/http://home.att.net/~c.jeppeson/igloo_white.html

biography also mentions spook base as a $2.5B windfall for IBM (some $17+B inflation adjusted). Its been nearly 30yrs since the Time article and little seems to have changed, recent item in Spinney's blog:
http://chuckspinney.blogspot.com/p/domestic-roots-of-perpetual-war.html

--
virtualization experience starting Jan1968, online at home since Mar1970

Boyd and the U.S. Navy's Return to History

From: lynn@garlic.com (Lynn Wheeler)
Date: 30 Aug, 2012
Subject: Boyd and the U.S. Navy's Return to History
Blog: The Naval Diplomat
Boyd and the U.S. Navy's Return to History
http://thediplomat.com/the-naval-diplomat/2012/08/28/boyd-and-the-u-s-navys-return-to-history/

Boyd in his briefings would describe how the US military resorted to a rigid, top-down, command&control for WW2 in order to deploy huge numbers with little or no experience and leverage the few skilled resources available (assuming that only those at the very top knew what they were doing). He would contrast US military with 11% officers (growing to 20% needed to maintain rigid, top-down, command&control) with German 3% officers He would then describe that by the early 80s, that many of those officers had returned to civilian life and were starting to contaminate US corporate culture with similar rigid, top-down, command&control infrastructure. The downside was it made organizations much less agile and adaptable and created barriers to being able to use skills that existed at other levels of the organization (with the implied assumption that only those at very top knew what they were doing).

--
virtualization experience starting Jan1968, online at home since Mar1970

I.B.M. Mainframe Evolves to Serve the Digital World

Refed: **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **
From: lynn@garlic.com (Lynn Wheeler)
Date: 31 Aug, 2012
Subject: I.B.M. Mainframe Evolves to Serve the Digital World
Blog: Greater IBM
re:
https://www.garlic.com/~lynn/2012l.html#42 I.B.M. Mainframe Evolves to Serve the Digital World

as per previous referenced articles
http://news.cnet.com/8301-13846_3-57349321-62/amazon-takes-supercomputing-to-the-cloud/
and
http://arstechnica.com/business/2012/04/4829-per-hour-supercomputer-built-on-amazon-cloud-to-fuel-cancer-research

both articles cite what amazon charges for on-demand use of the instances ... including what it is required to make a profit, cover all costs, cover the costs of having significant excess provisioning with idle capacity to meet instantaneous on-demand. While I mentioned those additional cost for the amazon operations ... I didn't bother to go into additional details since there are no equivalent total-cost-of-ownership for an equivalent mainframe-based cloud. The articles also say that the price for prescheduled, planned is lower ... since it significantly reduces the cost of providing for idle provisioning that allows for instantaneous on-demand.

as repeated for above, $4829/hr for 51,132 cores ... which works out to $42,302,040/yr (24*365) to cover *ALL* amazon costs plus profit including having lots of idle computing laying around for "on-demand" requirements. That $42m/yr is for the equivalent processing power of 33,801 maxed out z196 computing systems at nearly $1T ... for less than the price of two Z196 ($56M).

On-demand provision for the equivalent of having 33,801 idle z196 (@$28M) sitting around as part of large cloud service ... possibly requires operation with 100,000 total aggregate z196. Is there a total-cost-of-ownship for 100,000 z196 machines plus purchase price (probably closer to 500,000 z196 machines) ... plus profit margin to provide an equivalent level of on-demand service (where the base purchase price is already going to be several trillion dollars). What is the physical planning, power requirements and cooling for 100,000 z196 machines?

I remember getting into lots of fights with the communication group over token-ring versus ethernet. They had published a report comparing 16mbit token-ring with ethernet. They only way that the numbers made sense was if they had used the original experimental, prototype, 3mbit ethernet that predated listen-before-transmit instead of product 10mbit ethernet (aka the comparison was enormously skewed and biased). Almaden research had just been built and provisioned with lots of CAT4 for 16mbit token ring ... but they quickly moved to CAT4 ethernet because it provided actual higher lan thruput capacity and lower latency than 16mbit token-ring (example of how skewed the numbers can be).

Original virtual machines was done at the science center in the 60s with cp67 (actual first one with cp40 on specially modified 360/40 with virtual memory hardware) . Several online commercial service bureaus sprung up in the 60s offering online ("on-demand") service. Several enhancements to cp67 had to be done to get its use for 24*7 service bureau operation. Initially off-shift use was very light but to develop 24*7 use ... the systems had to be left up all the time. In order to afford leaving the systems up all the time, the off-shift costs had to be enormously reduced (because of initially little or no 7x24 use).

At the time, IBM leased machines and charges were based on the "system meter" that ran whenever the processor and/or channels were busy. A hack had to be done to cp67 to allow the system meter to stop when nothing was going on ... but still leave active channel programs that would accept incoming connections/characters from dialed-in users. The system meter also would only come to a stop when both processor and all channels had been idle for 400ms. Note that at least well into the late 70s (long after switch-over from lease to sales, and for all I know continues today) MVS had a special system function that would wakeup every 400ms (to make sure that the system meter never stopped).

To reduce the operational costs of cp67 (especially 7x24, off-shift, when load was nearly non-existent) lots of enhancements were required for dark-room, operator-less operations. One of the things was after a system crash, it would automatically re-ipl and restart to operational state w/o manual/operator intervention.

Also in the 60s, service bureaus enhanced cp67 for loosely-coupled, single-system-image operation. Part of the issue is that hardware maintenance in the 60s required taking systems down/offline. To make this transparent to the users ... transparent process migration was added ... that it was transparent to users which systems they ran on ... and running users could be transparently moved between systems w/o interruption ... allowing systems to be taken offline for (both hardware & software) maintenance and service.

For various reasons, many of these features from the 60s commercial virtual machine operation never made it into the cp67 products &/or subsequent vm products. Last I looked, the z/VM cluster support still didn't provide for transparent process migration between systems in cluster operation.

One of the largest virtual machine single-system image, cluster operations was the internal HONE system providing world-wide sales&marketing support (thru the 70s & much of the 80s). While it had transparent system operation in the cluster, connect load-balancing, and automatic re-connect ... it never did do the transparent process migration that originated in the 60s with some of the virtual machine service bureaus.

Just seen on the internet: "IBM mainframe computer sales are 4% of IBM's revenue; with software, services, and storage it's 25%". This implies for every million in mainframe hardware sales, IBM charges $5.25m in software, services and storage ... i.e. a trillion dollars in z196 sales (for the 33,801 z196 machines), total cost from IBM would be closer $6.25trillion (which doesn't include building, cooling, staff, power, etc).

As to business continuity ... when I was doing HA/CMP ... I was asked to do a section of the corporate continuous availability strategy document ... however it got pulled because both Rochester and POK complained that they couldn't meet the requirements.
https://www.garlic.com/~lynn/submain.html#available

As to PCI-DSS there are various references it was an industry specification to help support federal legislation to eliminate data breach notification (aka the definition of PCI-DSS certification is never having a data breach, PCI-DSS certified institutions that have a breach, have their PCI-DSS certification revoked). 1995, I was asked to participate in the financial industry standard x9a10 working group that had been given the requirement to preserve the integrity of the financial industry for *ALL* retail payments. As part of that effort, we did extensive, detailed, end-to-end threat and vulnerability studies of the major kinds of retail payments. PCI-DSS only has very small coverage of the threats and vulnerabilities. We were then involved with the entities doing the cal. state data breach notification legislation (original in the country). Note X9 is chair for the (international) ISO financial standards group ... so X9 standards tend to proceed to ISO standardization. I was also the co-author of the financial industry privacy standard, X9.99 that then became ISO standard.

In the 90s, the financial industry spent billions of dollars to move mainframe overnight batch to large number of parallel killer micros (the efforts were behind lots of the comments about death of the mainframe). the issue was that while online, real-time transactions had been added to mainframe financial applications ... the transaction didn't go to settle until the overnight batch. The issue in the 90s was that globalization was increasing the workload needed to be done and also decreasing the size of the overnight batch window. The objective was to re-implement the whole infrastructure as straight-through processing on large numbers of parallel killer micros. The problem was that they were using some parallelizing technology and never did the speeds&feeds ... things looked great in toy demos ... but the technology introduced factor of 100times overhead ... totally swamping any improved thruput benefits of the killer micros (compared to cobol batch). The resulting disasters when moved into production created enormous fear and risk aversion in the industry. I had done the speeds&lfeeds beforehand ... but nobody wanted to listen. I then got brought in to do 14% improvement on overnight cobol batch application that ran every night on over 40 maxed out mainframes.

Since then most of the non-mainframe RDBMS vendors (including IBM) have done an enormous amount of throughput and performance work for (non-mainframe) RDBMS cluster scale-up. A couple years ago, I was involved in taking a straight-through implementation based on non-mainframe parallel RDBMS ... that met all of the financial industry objectives (enormous increase in performance thruput headroom, enormously lower cost, ACID properties, RAS, continuous operation) to industry associations. The technologists were highly favorable ... but eventually the people running the associations said that at the executive level, there was still lingering effects and risk aversion from the 90s disasters ... and things would have to wait for new generation.

It is at $48M/annum that has everything ... including building, staff, taxes, profit, cooling, power ... compared to $6.25T that doesn't including building, staff, taxes, profit, cooling, power, etc.

I would assert that anything deemed deficient in the $48M/annum could be added for less than the cost of the missing equivalent mainframe items (building, staff, taxes, profit, cooling, power, etc) ... still leaving a $6.25T gap (also 6.25T/48M = 130,208).

It would be possible to replicate the $48M/annum ... 100 times ... and still not make a noticeable dent in the $6.25T required for equivalent mainframe.

this has 1.8kW for z196 MCM
http://www.elektor.com/news/ibm-z196-microprocessor-boasts-5-2-ghz-clock-rate.1521411.lynkx
.. with 4 MCMs in fully configured or 7.2kW ... just for the MCMs. Fully loaded z196 is 31.7kW
http://www-ti.informatik.uni-tuebingen.de/~spruth/edumirror/xx095.pdf

33,801 z196 @31.7kW is then 1,071,491kw or 1,071MW not counting power for cooling, disks and other peripherals. This has 18.7kW for DS8800
http://www-03.ibm.com/systems/at/resources/systems_at_webkonferenzen_ibm_ds8800.pdf

at one DS8800 per z196, that would bring it up to 50.4kW and for 33,801 systems would be 1703570kW or 1704MW.

Even at 5cents per kwh, just electrical bill would be $85,179/hr compared to $4829/hr for fully loaded price for on-demand supercomputer subset of Amazon cloud.

--
virtualization experience starting Jan1968, online at home since Mar1970

The Payoff: Why Wall Street Always Wins

Refed: **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **
From: lynn@garlic.com (Lynn Wheeler)
Date: 31 Aug, 2012
Subject: The Payoff: Why Wall Street Always Wins
Blog: Google+
re:
https://plus.google.com/u/0/102794881687002297268/posts/3YiUCzRG8j3

The Payoff: Why Wall Street Always Wins
https://www.amazon.com/Payoff-Wall-Street-Always-ebook/dp/B008Y4TY92

Recent from the democratic side in congress ... implies that efforts stretched out for much longer that they actually seemed to. loc860-65:
At the December 2009 hearing, the three witnesses -- Breuer, Khuzami, and Perkins -- said all the right things. Don't worry. We're on the case. These are complex financial frauds committed by sophisticated actors. It takes time and patience to develop these cases. We're reviewing the facts and the evidence. We'll bring criminal or civil actions where the facts take us. Stay tuned. At the time, we believed them. Unraveling sophisticated financial fraud is an enormously complicated and resource-intensive undertaking, because of the nature of both the conduct and the perpetrators.

... snip ...

Note: Jan. 2009 I was asked to HTML'ize the Pecora hearings (30s senate hearings into '29 crash, had been scanned at boston public library fall of 2008) with lots of internal xrefs and lots URLs between what happened this time and what happened then (some anticipation that new congress would have appitite to do something). I worked on it for some time, but well before summer of 2009, I got a call that it wouldn't be needed after all (references to enormous piles of wallstreet money being spread around capital hill).

And similar recent work from the republican side: The Party Is Over: How Republicans Went Crazy, Democrats Became Useless, and the Middle Class Got Shafted
https://www.amazon.com/The-Party-Over-Republicans-ebook/dp/B007V65OLG

and earlier work: Confidence Men: Wall Street, Washington, and the Education of a President
https://www.amazon.com/Confidence-Men-Washington-Education-ebook/dp/B0089LOKKS/

characterizes that it was actually over before it ever started, that the economic A-team helped get the president elected but they were going to choose the "swedish" solution (over the lingering "japan" solution) and hold those responsible on wallstreet accountable. Instead the president appoints the B-team, people that were involved in creating the economic mess and not likely to hold anybody accountable.

a rolling stone reference complimenting above:

How Wall Street Killed Financial Reform; It's bad enough that the banks strangled the Dodd-Frank law. Even worse is the way they did it - with a big assist from Congress and the White House.
http://www.rollingstone.com/politics/news/how-wall-street-killed-financial-reform-20120510

more holding nobody accountable (some claims they became viewed as just "very small" cost of doing business ... aka as percent of total amounts involved): Revisiting Statements Around the Mortgage Settlement
http://www.nakedcapitalism.com/2012/08/revisiting-statements-around-the-mortgage-settlement.html

Big Banks Are Hazardous to U.S. Financial Health
http://www.bloomberg.com/news/2012-09-02/big-banks-are-hazardous-to-u-s-financial-health.html

from above:
In 1995, the Big Six -- JPMorgan, Bank of America Corp., Citigroup Inc., Wells Fargo & Co., Goldman Sachs Group Inc. and Morgan Stanley -- had assets worth only 17 percent of U.S. gross domestic product. As recently as 2005, their collective balance sheets were valued at less than 50 percent of GDP.

Today, the Big Six are much bigger, with combined assets of 60 percent of GDP.


"Confidence Men"
https://www.amazon.com/Confidence-Men-Washington-Education-ebook/dp/B0089LOKKS/
and "Bailout"
https://www.amazon.com/Bailout-ebook/dp/B00818J57W
pretty much have everything a bankster give-away from the beginning. The congressional staffers "How Republicans Went Crazy"
https://www.amazon.com/The-Party-Over-Republicans-ebook/dp/B007V65OLG
and "The Payoff" describe efforts that appear to try and help the public, just were never successful.

Bailout pg157/loc3106-9:
HAMP was not separate from the bank bailouts; it was an essential part of them. From that perspective, it didn't matter if the modifications failed after a year or so of trial payments or if struggling borrowers placed into doomed trial modifications ended up far worse off, as long as the banks were able to stretch out their pain until their profits returned.

... snip ...

Mortgage Settlement Monitor Hires Firm that Has Worked on Countrywide Matters
http://www.nakedcapitalism.com/2012/09/mortgage-settlement-monitor-hires-firm-that-has-worked-on-countrywide-matters.html

past posts mentioning "Confidence Men" &/or "The Party Is Over"
https://www.garlic.com/~lynn/2011p.html#67 The men who crashed the world
https://www.garlic.com/~lynn/2011p.html#70 No One Telling Who Took $586B in Fed Swaps
https://www.garlic.com/~lynn/2011p.html#73 A question for the readership
https://www.garlic.com/~lynn/2011p.html#74 Derivatives and free trade
https://www.garlic.com/~lynn/2011p.html#79 Financial Crimes Bedevil Prosecutors
https://www.garlic.com/~lynn/2011p.html#83 Heading For World War III | Gerald Celente Trends Blog
https://www.garlic.com/~lynn/2011p.html#88 Fed Report Finds Speculators Played Big Role in Housing Collapse
https://www.garlic.com/~lynn/2011p.html#91 Has anyone successfully migrated off mainframes?
https://www.garlic.com/~lynn/2011p.html#109 Zombie Banks
https://www.garlic.com/~lynn/2011p.html#110 Loan Originators
https://www.garlic.com/~lynn/2011p.html#111 Matt Taibbi with Xmas Message from the Rich
https://www.garlic.com/~lynn/2011p.html#132 Yes Virginia, Electronic Signatures Are Legal
https://www.garlic.com/~lynn/2012.html#17 What's your favorite quote on "accountability"?
https://www.garlic.com/~lynn/2012.html#21 Zombie Banks
https://www.garlic.com/~lynn/2012.html#44 Who originated the phrase "user-friendly"?
https://www.garlic.com/~lynn/2012.html#47 Avoiding a lost decade
https://www.garlic.com/~lynn/2012.html#48 Fed's image tarnished by newly released documents
https://www.garlic.com/~lynn/2012.html#72 Chris Dodd's SOPA crusading
https://www.garlic.com/~lynn/2012b.html#43 Where are all the old tech workers?
https://www.garlic.com/~lynn/2012c.html#2 Occupy the SEC (Securities & Exchange Commission)
https://www.garlic.com/~lynn/2012c.html#5 Too big not to fail
https://www.garlic.com/~lynn/2012c.html#19 Occupy the SEC Pitches An Extreme Makeover of Wall Street
https://www.garlic.com/~lynn/2012c.html#63 The Economist's Take on Financial Innovation
https://www.garlic.com/~lynn/2012f.html#13 The White House and Mortgage Fraud: So Far It's All Talk, No Action
https://www.garlic.com/~lynn/2012f.html#66 Predator GE: We Bring Bad Things to Life
https://www.garlic.com/~lynn/2012f.html#67 Cartons of Punch Cards
https://www.garlic.com/~lynn/2012f.html#83 Why Can't Obama Bring Wall Street to Justice?
https://www.garlic.com/~lynn/2012g.html#9 JPM LOSES $2 BILLION USD!
https://www.garlic.com/~lynn/2012g.html#16 Psychology Of Fraud: Why Good People Do Bad Things
https://www.garlic.com/~lynn/2012g.html#30 24/7/365 appropriateness was Re: IBMLink outages in 2012
https://www.garlic.com/~lynn/2012g.html#48 Owl: China Swamps US Across the Board -- Made in China Computer Chips Have Back Doors, 45 Other "Ways & Means" Sucking Blood from US
https://www.garlic.com/~lynn/2012g.html#56 Why Hasn't The Government Prosecuted Anyone For The 2008 Financial recession?
https://www.garlic.com/~lynn/2012h.html#25 US economic update. Everything that follows is a result of what you see here
https://www.garlic.com/~lynn/2012h.html#31 How do you feel about the fact that today India has more IBM employees than US?
https://www.garlic.com/~lynn/2012h.html#36 Monopoly/ Cartons of Punch Cards
https://www.garlic.com/~lynn/2012h.html#37 Monopoly/ Cartons of Punch Cards
https://www.garlic.com/~lynn/2012h.html#64 Monopoly/ Cartons of Punch Cards
https://www.garlic.com/~lynn/2012h.html#77 Interesting News Article
https://www.garlic.com/~lynn/2012i.html#1 Monopoly/ Cartons of Punch Cards
https://www.garlic.com/~lynn/2012i.html#6 Good article. Friday discussion type
https://www.garlic.com/~lynn/2012j.html#86 Study: One in Five Firms Misrepresent Earnings
https://www.garlic.com/~lynn/2012k.html#36 Race Against the Machine
https://www.garlic.com/~lynn/2012k.html#40 Core characteristics of resilience
https://www.garlic.com/~lynn/2012k.html#79 Romney and Ryan's Phony Deficit-Reduction Plan

--
virtualization experience starting Jan1968, online at home since Mar1970

Too true to be funny - 51% of the surveyed Americans think that stormy we

From: lynn@GARLIC.COM (Anne & Lynn Wheeler)
Subject: Re: Too true to be funny - 51% of the surveyed Americans think that stormy we...
Newsgroups: bit.listserv.ibm-main
Date: 31 Aug 2012 17:15:29 -0700
Efinnell15@AOL.COM (Ed Finnell) writes:
There was a 'dark comedy' film in the sixties, maybe Marcel Marceau where the Inmates were running the town at the end of WWII-dodging the various military factions, keeping the peace, and providing for the general welfare. The comedy I suppose is they were doing a better job than the previous administration.

It was cult film still playing non-stop down at central square (theater at the fork/junction of main & mass av) ... somewhat characterized as inmates being in charge of the institution.

i was at the science center at tech sq (couple blocks down main st) and continued to work on 360/370 ... all during the Future System period ... which was going to completely replace 370 with something totally different ... and internal politics was killing/suspending 370 stuff. I would periodically ridicule the FS activity ... including drawing analogies with the cult film (inmates being in charge of the institution) ... not the most career enhancing comments. misc. past posts mentioning science center at 545 tech sq
https://www.garlic.com/~lynn/subtopic.html#545tech

the lack of 370 products during the FS period is credited with giving the clone processors market foothold.

misc. past references to FS
https://www.garlic.com/~lynn/submain.html#futuresys

as per past references, when FS effort imploded ... there was mad rush to get products back into the 370 hardware&software pipelines.

--
virtualization experience starting Jan1968, online at home since Mar1970

Arming for the Navy's Return to History

Refed: **, - **, - **, - **
From: lynn@garlic.com (Lynn Wheeler)
Date: 31 Aug, 2012
Subject: Arming for the Navy's Return to History
Blog: Boyd Strategy
re:
http://lnkd.in/Gbf7u3

Arming for the Navy's Return to History
http://thediplomat.com/the-naval-diplomat/2012/08/29/arming-for-the-navys-return-to-history/

part of Boyd multi-part at Naval Diplomat

So much of US military is still focused on 2nd generation warfare ... and the enormous industrial base dedicated to supporting it ... or the enormous industrial base becomes an end-in-itself, with excuse of continuous conflict &/or "perpetual war" as justification
http://chuckspinney.blogspot.com/p/domestic-roots-of-perpetual-war.html

The "Art of War" would raise the possibility that China wouldn't need a "2nd generation" response ... although our 2nd generation industrial base would continue to interpret it that way.

I'm inclined to characterize this recasting of "The Art of War" as something of the flavor of Asimov's Foundation.

The School of Sun Tzu: Winning Empires Without War by David G. Jones
https://www.amazon.com/The-School-Sun-Tzu-ebook/dp/B007ZBYZDK

which should increase consideration that there isn't going to be a 2nd generation warfare response.

One scenario with the US dependent on so many imports from China (by sea, and MICC industrial base looking for any excuse), then they let the US police the lanes.

first two parts

Introducing John Boyd
http://thediplomat.com/the-naval-diplomat/2012/08/26/introducing-john-boyd/

Boyd and the U.S. Navy's Return to History
http://thediplomat.com/the-naval-diplomat/2012/08/28/boyd-and-the-u-s-navys-return-to-history/

For the fun of it ... "School of Sun Tzu" citing Chet; loc.3073-79:
Dr. Chester W. Richards developed a war "paradigm" that blends the mental and the physical. He thanks the late US Air Force colonel, John Boyd, "of the Sun Tzu school, and by far the most influential strategist of our generation," for his help in establishing a "modern paradigm for winning in armed conflict by destroying morale with quick and painless tactics." The paradigm he calls "rapid OODA speed" was applied with success, he says, in the Gulf War. Richards summarizes Ping-fa as "an uncompromised indictment of generals whose only ideas of strategy are frontal assaults and battles of attrition."

... snip ...

An Anti-Access Approximation; The PLA's Active Strategic Counterattacks on Exterior Lines
http://www.chinasecurity.us/index.php?option=com_content&view=article&id=487&Itemid=8

Positions A2/AD as defensive ... somewhat semantics, MICC tends to not describe our own defensive measures as "threats" ... but will describe others' defensive measures as "threats".

other discussions of A2/AD

The Birth of Chinese A2/AD
http://cdrsalamander.blogspot.com/2012/05/birth-of-chinese-a2ad.html
An Anti-Access History Lesson
http://thediplomat.com/flashpoints-blog/2012/05/25/an-anti-access-history-lesson/
Gaps in China's area-denial strategy
http://www.atimes.com/atimes/China/NE08Ad02.html
Challenges to American Access: The Joint Operational Access Concept and Future Military Risk
http://csis.org/publication/challenges-american-access-joint-operational-access-concept-and-future-military-risk
The dragon's new teeth
http://www.economist.com/node/21552193

--
virtualization experience starting Jan1968, online at home since Mar1970

Turn Off Another Light - Univ. of Tennessee

Refed: **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **
From: lynn@GARLIC.COM (Anne & Lynn Wheeler)
Subject: Re: Turn Off Another Light - Univ. of Tennessee
Newsgroups: bit.listserv.ibm-main
Date: 1 Sep 2012 08:04:00 -0700
R.Skorupka@BREMULTIBANK.COM.PL (R.S.) writes:
No, with *one* blade cabinet of Dell+Windows. HW cost comparable to spare HMC and two OSA cards.

as mentioned before:

max. configured z196 with 80 processors is rated at 50BIPs and goes for $28M ($350,000/processor, $560,000/BIPS, 625MIPS/processor)

IBM has base list price of $1815 for e5-2600 blade. There are various processor configurations for e5-2600 (two socket-chip, 8processors/socket-chip, 16processors) ... but some are benchmarked at 527BIPS ... using IBM base price, $113.44/processor, $3.44/BIPS, 33BIPS/processor. Large cloud operator claims of being able to assemble blades at 1/3rd cost of brand name blades potentially has it down to $1.14/BIPS.

and from recent thread in "Greater IBM" ... discussion of some of the scale-up/cost issues
https://www.garlic.com/~lynn/2012l.html#47 I.B.M. Mainframe Evolves to Serve the Digital World

comparing this on-demand supercomputer subset carved out of amazon cloud $4829/hr for 51,132 cores
http://arstechnica.com/business/2012/04/4829-per-hour-supercomputer-built-on-amazon-cloud-to-fuel-cancer-research

with number of z196s for equivalent BIPS aka 33,801 z196 80 processor machines. the $4829/hr works out to $48M/annum ... less than the $56M cost of two z196s. The cost of 33,801 z196 comes out to around trillion dollars. From yesterday, analysis that IBM sells $5.25M in mainframe software, services and storage for every million in mainframe sales ... making cost of 33,801 z196 closer to $6.25trillion (with software, services, and storage) ... doesn't include building, staff, power, cooling, taxes, etc (which would be included in an amazon cloud costs).

this has 1.8kW for z196 MCM
http://www.elektor.com/news/ibm-z196-microprocessor-boasts-5-2-ghz-clock-rate.1521411.lynkx
.. with 4 MCMs in fully configured or 7.2kW ... just for the MCMs. Fully loaded z196 is 31.7kW
http://www-ti.informatik.uni-tuebingen.de/~spruth/edumirror/xx095.pdf

33,801 z196 @31.7kW is then 1,071,491kw or 1,071MW not counting power for cooling, disks and other peripherals. This has 18.7kW for DS8800
http://www-03.ibm.com/systems/at/resources/systems_at_webkonferenzen_ibm_ds8800.pdf

at one DS8800 per z196, that would bring it up to 50.4kW and for 33,801 systems would be 1703570kW or 1704MW.

Even at 5cents per kwh, just electrical bill would be $85,179/hr compared to $4829/hr for fully loaded price for the on-demand supercomputer subset of Amazon cloud.

--
virtualization experience starting Jan1968, online at home since Mar1970

I.B.M. Mainframe Evolves to Serve the Digital World

Refed: **, - **, - **, - **
From: lynn@garlic.com (Lynn Wheeler)
Date: 1 Sep, 2012
Subject: I.B.M. Mainframe Evolves to Serve the Digital World
Blog: Greater IBM
re:
https://www.garlic.com/~lynn/2012l.html#42 I.B.M. Mainframe Evolves to Serve the Digital World
https://www.garlic.com/~lynn/2012l.html#47 I.B.M. Mainframe Evolves to Serve the Digital World

The question upthread wasn't about putting PII into the cloud ... but the total costs of open systems (one source being cloud prices for their open systems) compared to total mainframe costs. What a cloud operator charges for their open system use should be approx. of actual total costs (plus some uplift for profit operation). The analysis from yesterday for total mainframe price was that IBM charges over six times the hardware cost for total mainframe (i.e. earns total of $6.25million from every $1million of mainframe hardware) ... but doesn't include total cost to customer including building, power, cooling, staff, etc.

possibly more than anybody wants to know ... but two recent (financial) blog entries about "cloud" security issues (actually not just the traditional open system cloud servers but all dataprocessing operations with financial information)
http://financialcryptography.com/mt/archives/001385.html
and
http://financialcryptography.com/mt/archives/001384.html

this is old post with reference to cluster scale-up meeting in Ellison's conference room.
https://www.garlic.com/~lynn/95.html#13

Two of the people mentioned, later leave and show up at small client/server startup. We then get brought in as consultants because they want to do payment transactions on their server; the startup had also invented this technology call "SSL" they want to use, the result is now frequently called "electronic commerce".

As part of the effort, we do analysis of SSL, browser, and digital certificate operations and come up with several requirements for secure operation. After deployment, many of the requirements are almost immediately violated and we start referring to it as "comfort" security (only provides comfort with the appearance of security).

We document that business processes in payment infrastructure are severely mis-aligned ... independent of whether it is open system, mainframe, cloud, etc. For one; the typical profit a merchant receives from electronic transaction can be a few dollars (and a few cents for a transaction processor). In contrast, the value of the same transaction information to the crooks is the account credit limit or balance. As a result, crooks can frequent afford to spend 100 times attacking the infrastructure as the merchant/processor can spend to defend from attacks. For another; the information needed to be kept hidden from crooks (so they can't use it for fraudulent transactions) is the same information that is needed in dozens of business processes at millions of locations around the planet. We've claimed that even if the planet is buried in miles of information hiding encryption, it wouldn't be able to stop information leakage.

Most of these general security issues are unrelated to whether mainframes or open systems are involved. Also, the cloud specific security issues are unrelated to whether mainframes or open systems would be involved.

--
virtualization experience starting Jan1968, online at home since Mar1970

CALCULATORS

Refed: **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **
From: Anne & Lynn Wheeler <lynn@garlic.com>
Subject: Re: CALCULATORS
Newsgroups: alt.folklore.computers
Date: Sat, 01 Sep 2012 12:26:05 -0400
Walter Banks <walter@bytecraft.com> writes:
Unlike the real estate bubble the student debt has real consequences.

The real estate bubble was about middle class capital loss and great opportunity for affluent folks.

The student debt "pop" has more profound impact on future generations and will last far longer than the current fiscal bump the US is dealing with.

Without real education the earning power of future generations will be lost making a very steep downward spiral that the US will take several generations to recover if it is possible. The GOP have consistently targeted education costs for spending cuts yet most of the best GOP politicians are well educated.

The impact will be everywhere, loss of resources to create needed infrastructure needed to support jobs. Loss of the organizational and technical skills needed for innovation.


recent article (about Bankruptcy Abuse Prevention and Consumer Protection Act of 2005):

GOP Majority 109th Congress Caused Student Loan Crisis, With a Little Help from Some Dems
http://www.dailykos.com/story/2012/05/28/1095356/-GOP-Majority-109th-Congress-Caused-Student-Loan-Crisis-With-a-Little-Help-from-Some-Dems

picture of last 30years:
http://johnhively.wordpress.com/2012/08/31/3107/
and
http://globalguerrillas.typepad.com/globalguerrillas/2011/10/journal-why-the-us-middle-class-is-broken.html
from here:
http://www.nytimes.com/imagepages/2011/09/04/opinion/04reich-graphic.html
part of this article
http://www.nytimes.com/2011/09/04/opinion/sunday/jobs-will-follow-a-strengthening-of-the-middle-class.html

a little x-over from google+
https://plus.google.com/u/0/102794881687002297268/posts/3YiUCzRG8j3
and
https://www.garlic.com/~lynn/2012l.html#48 The Payoff: Why Wall Street Always Wins

The Payoff: Why Wall Street Always Wins
https://www.amazon.com/Payoff-Wall-Street-Always-ebook/dp/B008Y4TY92

Recent from the democratic side in congress ... implies that efforts stretched out for much longer that they actually seemed to. loc860-65:
At the December 2009 hearing, the three witnesses -- Breuer, Khuzami, and Perkins -- said all the right things. Don't worry. We're on the case. These are complex financial frauds committed by sophisticated actors. It takes time and patience to develop these cases. We're reviewing the facts and the evidence. We'll bring criminal or civil actions where the facts take us. Stay tuned. At the time, we believed them. Unraveling sophisticated financial fraud is an enormously complicated and resource-intensive undertaking, because of the nature of both the conduct and the perpetrators.

... snip ...

Note: Jan. 2009 I was asked to HTML'ize the Pecora hearings (30s senate hearings into '29 crash, had been scanned at boston public library fall of 2008) with lots of internal xrefs and lots of URLs between what happened this time and what happened then (some anticipation that new congress would have appitite to do something). I worked on it for some time, but well before summer of 2009, I got a call that it wouldn't be needed after all (references to enormous piles of wallstreet money being spread around capital hill).

And similar recent work from the republican side: The Party Is Over: How Republicans Went Crazy, Democrats Became Useless, and the Middle Class Got Shafted
https://www.amazon.com/The-Party-Over-Republicans-ebook/dp/B007V65OLG

and earlier work: Confidence Men: Wall Street, Washington, and the Education of a President
https://www.amazon.com/Confidence-Men-Washington-Education-ebook/dp/B0089LOKKS/

characterizes that it was actually over before it ever started, that the economic A-team helped get the president elected but they were going to choose the "swedish" solution (over the lingering "japan" solution) and hold those responsible on wallstreet accountable. Instead the president appoints the B-team, people that were involved in creating the economic mess and not likely to hold anybody accountable.

....

and another google+
https://plus.google.com/u/0/102794881687002297268/posts/ChprA7sxRnS
and
https://www.garlic.com/~lynn/2012l.html#7 More Evidence Wall Street is Overpaid

More Evidence Wall Street is Overpaid
http://www.rollingstone.com/politics/blogs/taibblog/more-evidence-wall-street-is-overpaid-20120821

aka not pursuit of better pie but getting bigger piece of existing pie ...

The Price of Inequality: How Today's Divided Society Endangers Our Future (Joseph E. Stiglitz) pg35/loc1169-73:
In business school we teach students how to recognize, and create, barriers to competition -- including barriers to entry -- that help ensure that profits won't be eroded. Indeed, as we shall shortly see, some of the most important innovations in business in the last three decades have centered not on making the economy more efficient but on how better to ensure monopoly power or how better to circumvent government regulations intended to align social returns and private rewards.

... snip ...

Freefall: America, Free Markets, and the Sinking of the World Economy (Joseph E. Stiglitz) pg271/loc5101-4
Standard economic theory (the neoclassical model discussed earlier in this chapter) has had little to say about innovation, even though most of the increases in U.S. standards of living in the past hundred years have come from technical progress.56 As I noted earlier, just as "information" was outside the old models, so too was innovation

... snip ...

...

another "The Payoff: Why Wall Street Always Wins", (referencing top business schools) loc555-56:
Everyone wanted to be a banker or a management consultant; the dream employers were Goldman Sachs, Salomon Brothers, and McKinsey. The consensus among students was that only losers took jobs at companies that actually made things, like IBM or Proctor & Gamble.

... snip ...

recent posts mentioning pecora:
https://www.garlic.com/~lynn/2012b.html#5 The round wheels industry is heading for collapse
https://www.garlic.com/~lynn/2012b.html#56 What's the most interesting thing you do in your non-work life?
https://www.garlic.com/~lynn/2012c.html#37 US real-estate has lost $7T in value
https://www.garlic.com/~lynn/2012c.html#52 PC industry is heading for more change
https://www.garlic.com/~lynn/2012d.html#32 PC industry is heading for more change
https://www.garlic.com/~lynn/2012g.html#7 Adult Supervision
https://www.garlic.com/~lynn/2012g.html#28 REPEAL OF GLASS-STEAGALL DID NOT CAUSE THE FINANCIAL CRISIS - WHAT DO YOU THINK?
https://www.garlic.com/~lynn/2012g.html#56 Why Hasn't The Government Prosecuted Anyone For The 2008 Financial recession?
https://www.garlic.com/~lynn/2012g.html#64 Monopoly/ Cartons of Punch Cards
https://www.garlic.com/~lynn/2012g.html#67 Monopoly/ Cartons of Punch Cards
https://www.garlic.com/~lynn/2012h.html#36 Monopoly/ Cartons of Punch Cards
https://www.garlic.com/~lynn/2012h.html#53 Monopoly/ Cartons of Punch Cards
https://www.garlic.com/~lynn/2012h.html#75 Interesting News Article
https://www.garlic.com/~lynn/2012i.html#63 Monopoly/ Cartons of Punch Cards
https://www.garlic.com/~lynn/2012i.html#81 Should the IBM approach be given a chance to fix the health care system?
https://www.garlic.com/~lynn/2012k.html#9 Sandy Weill's About-Face on Big Banks
https://www.garlic.com/~lynn/2012k.html#12 The Secret Consensus Among Economists
https://www.garlic.com/~lynn/2012k.html#13 Is there a connection between your strategic and tactical assertions?
https://www.garlic.com/~lynn/2012k.html#75 What's the bigger risk, retiring too soon, or too late?

--
virtualization experience starting Jan1968, online at home since Mar1970

Singer Cartons of Punch Cards

Refed: **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **
From: Anne & Lynn Wheeler <lynn@garlic.com>
Subject: Re: Singer Cartons of Punch Cards
Newsgroups: alt.folklore.computers
Date: Sun, 02 Sep 2012 12:05:26 -0400
Patrick Scheible <kkt@zipcon.net> writes:
Don't forget the war with Iran. It'll be just like old times under W.

recent afghan & iraq disucssion
http://fabiusmaximus.com/2012/09/01/42869/

Boyd is credited with battle plan for desert storm ... but the final action was terminated ... leaving it to be done again a decade later. past posts and other refs to Boyd
https://www.garlic.com/~lynn/subboyd.html

and cross-over from
https://www.garlic.com/~lynn/2012h.html#21 The Age of Unsatisfying Wars
https://www.garlic.com/~lynn/2012i.html#2 Interesting News Article
https://www.garlic.com/~lynn/2012i.html#8 Interesting News Article

my son-in-law did 2004-2005 tour in fallujah (constant firefights) and then 2nd tour was bugabah ... he says that this is fairly accurate

Battle for Baqubah: Killing Our Way Out
https://www.amazon.com/Battle-Baqubah-Killing-Our-ebook/dp/B007VBBS9I

past references:
https://www.garlic.com/~lynn/2012h.html#21 The Age of Unsatisfying Wars
https://www.garlic.com/~lynn/2012i.html#2 Interesting News Article
https://www.garlic.com/~lynn/2012i.html#64 Early use of the word "computer"

for other military topic drift

How Bush's grandfather helped Hitler's rise to power; Rumours of a link between the US first family and the Nazi war machine have circulated for decades. Now the Guardian can reveal how repercussions of events that culminated in action under the Trading with the Enemy Act are still being felt by today's president
http://www.guardian.co.uk/world/2004/sep/25/usa.secondworldwar

past post mentioning Thyssen ...
https://www.garlic.com/~lynn/2010i.html#82 Favourite computer history books?

snippet from 1154th engineering combat group status report from National Archives (my wife's father commanded 1154th, frequently out in front making repairs so armor and infrantry can move up):

On 28 Apr we were put in D/S of the 13th Armd and 80th Inf Divs and G/S Corps Opns. The night of the 28-29 April we cross the DANUBE River and the next day we set-up our OP in SCHLOSS PUCHHOF (vic PUCHOFF); an extensive structure remarkable for the depth of its carpets, the height of its rooms, the profusion of its game, the superiority of its plumbing and the fact that it had been owned by the original financial backer of the NAZIS, Fritz Thyssen. Herr Thyssen was not at home.

Forward from the DANUBE the enemy had been very active, and an intact bridge was never seen except by air reconnaissance. Maintenance of roads and bypasses went on and 29 April we began constructing 835' of M-2 Tdwy Br, plus a plank road approach over the ISAR River at PLATTLING. Construction was completed at 1900 on the 30th. For the month of April we had suffered no casualties of any kind and Die Gotterdamerung was falling, the last days of the once mighty WEHRMACHT.


... snip ...

also mentions Thyssen
https://en.wikipedia.org/wiki/Prescott_Bush

father-in-law and business partner
https://en.wikipedia.org/wiki/George_Herbert_Walker

prescott brother-in-law, george w. uncle
https://en.wikipedia.org/wiki/George_Herbert_Walker,_Jr.

--
virtualization experience starting Jan1968, online at home since Mar1970

CALCULATORS

Refed: **, - **, - **, - **, - **, - **, - **, - **
From: Anne & Lynn Wheeler <lynn@garlic.com>
Subject: Re: CALCULATORS
Newsgroups: alt.folklore.computers
Date: Sun, 02 Sep 2012 14:16:41 -0400
Shmuel (Seymour J.) Metz <spamtrap@library.lspace.org.invalid> writes:
Nonsense; the doubling of the rates was a "sunset" provision of the law reducing rhem.

congress has hit on the idea that they get more money from sharply partisian bills ... and ongoing money if instead of making them permanent ... have them periodically expire and the process can be repeated again and again. part of the motivation for references to congress as Kabuki theater
https://en.wikipedia.org/wiki/Kabuki

and/or the most corrupt institution on earth.

CBO has during '0x decade that tax revenue was reduced by $6T and spending increased by $6T (compared to baseline) for $12T budget gap (compared to baseline that had all federal debt retired by 2010). much of this occurring after congress let the fiscal responsibility act expire in 2002 (required that spending had to be matched by tax revenue) ... only $2T of the $6T spending increase (over baseline) last decade was for the wars ... recent war reference:
https://www.garlic.com/~lynn/2012l.html#54 Singer Cartons of Punch Cards

the established tax shortfall and size of govenment increase (from last decade) has on-going effects into this decade.

current partisian battle is over proposed *enormous* decreases in Pentagon budget ... which only takes it back down to the 2006 spending level. there was article that major military contractors are havesting much more now from DOD than they were in 2006 ... but have fewer employees than 2006 (the increase in revenue and having fewer employees showing up in executive compensation). "threats" about proposed spending reduction will result in loss of jobs ... fails to reference that there has already been significant/greater loss of jobs as part of increasing executive compensation (suggestion that returning to 2006 spending levels should actually result in return to 2006 employment levels and 2006 executive compensation).

misc. past posts mentioning creation of $12T budget gap last decade:
https://www.garlic.com/~lynn/2012c.html#50 They're Trying to Block Military Cuts
https://www.garlic.com/~lynn/2012c.html#52 PC industry is heading for more change
https://www.garlic.com/~lynn/2012c.html#53 PC industry is heading for more change
https://www.garlic.com/~lynn/2012d.html#42 China's J-20 Stealth Fighter Is Already Doing A Whole Lot More Than Anyone Expected
https://www.garlic.com/~lynn/2012d.html#46 Is Washington So Bad at Strategy?
https://www.garlic.com/~lynn/2012d.html#53 "Scoring" The Romney Tax Plan: Trillions Of Dollars Of Deficits As Far As The Eye Can See
https://www.garlic.com/~lynn/2012d.html#60 Memory versus processor speed
https://www.garlic.com/~lynn/2012e.html#25 We are on the brink of historic decision [referring to defence cuts]
https://www.garlic.com/~lynn/2012e.html#40 Who Increased the Debt?
https://www.garlic.com/~lynn/2012e.html#58 Word Length
https://www.garlic.com/~lynn/2012f.html#31 Rome speaks to us. Their example can inspire us to avoid their fate
https://www.garlic.com/~lynn/2012f.html#61 Zakaria: by itself, Buffett rule is good
https://www.garlic.com/~lynn/2012f.html#68 'Gutting' Our Military
https://www.garlic.com/~lynn/2012f.html#81 The Pentagon's New Defense Clandestine Service
https://www.garlic.com/~lynn/2012f.html#88 Defense acquisitions are broken and no one cares
https://www.garlic.com/~lynn/2012g.html#6 Adult Supervision
https://www.garlic.com/~lynn/2012g.html#45 Fareed Zakaria
https://www.garlic.com/~lynn/2012h.html#5 Monopoly/ Cartons of Punch Cards
https://www.garlic.com/~lynn/2012h.html#6 Monopoly/ Cartons of Punch Cards
https://www.garlic.com/~lynn/2012h.html#25 US economic update. Everything that follows is a result of what you see here
https://www.garlic.com/~lynn/2012h.html#26 US economic update. Everything that follows is a result of what you see here
https://www.garlic.com/~lynn/2012h.html#27 Monopoly/ Cartons of Punch Cards
https://www.garlic.com/~lynn/2012h.html#30 Monopoly/ Cartons of Punch Cards
https://www.garlic.com/~lynn/2012h.html#33 Monopoly/ Cartons of Punch Cards
https://www.garlic.com/~lynn/2012h.html#50 Monopoly/ Cartons of Punch Cards
https://www.garlic.com/~lynn/2012h.html#61 Monopoly/ Cartons of Punch Cards
https://www.garlic.com/~lynn/2012h.html#68 Interesting News Article
https://www.garlic.com/~lynn/2012i.html#0 Interesting News Article
https://www.garlic.com/~lynn/2012i.html#41 Lawmakers reworked financial portfolios after talks with Fed, Treasury officials
https://www.garlic.com/~lynn/2012i.html#81 Should the IBM approach be given a chance to fix the health care system?
https://www.garlic.com/~lynn/2012j.html#39 Monopoly/ Cartons of Punch Cards
https://www.garlic.com/~lynn/2012k.html#37 If all of the American earned dollars hidden in off shore accounts were uncovered and taxed do you think we would be able to close the deficit gap?
https://www.garlic.com/~lynn/2012k.html#74 Unthinkable, Predictable Disasters
https://www.garlic.com/~lynn/2012k.html#79 Romney and Ryan's Phony Deficit-Reduction Plan

--
virtualization experience starting Jan1968, online at home since Mar1970

Blades versus z was Re: Turn Off Another Light - Univ. of Tennessee

Refed: **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **
From: lynn@GARLIC.COM (Anne & Lynn Wheeler)
Subject: Re: Blades versus z was Re: Turn Off Another Light - Univ. of Tennessee
Newsgroups: bit.listserv.ibm-main
Date: 2 Sep 2012 13:26:31 -0700
mike.a.schwab@GMAIL.COM (Mike Schwab) writes:
Put a Hercules emulator and z/OS on that blade, 50 z/OS MIPS per hyperthread, so 100 MIPS per core, 1600 MIPS per blade (per TurboHercules). Perhaps $5,000 per blade? Some blades do have 4 sockets.

re:
https://www.garlic.com/~lynn/2012l.html#51 Turn Off Another Light - Univ. of Tennessee

This mentions 3.2BIPS with 8-way Nehalem (compared to z10 30BIPS with 64 processors at z196 50BIPS with 80 processors)
https://en.wikipedia.org/wiki/Hercules_%28emulator%29

there has big thruput difference between i86 and risc ... risc having out-or-order execution, branch prediction, speculative execution, etc for a couple decades. last couple i86 chip generations have moved to risc with hardware layer that translates i86 instructions to risc micro-ops ... mitigating much of the thruput difference. Hyperthreading (two simulated processors per core) is also used to further increase instructions per second (by feeding execution units from two independent instruction streams). Hyperthreading was worked on back in early 70s for 370/195 ... but never shipped to customers. The 370/195 was out-of-order and pipelined but didn't have branch-prediction or speculative instructions. Peak thruput was 10MIPS ... but most codes ran at 5MIPS because of branch stalls. It was planned that two independent instruction streams ... each running at 5MIPS effective thruput would obtain aggregate of 10MIPS.

even z196 claims the introduction of out-of-order execution was big part of thruput improvement from z10 to z196 ... with further out-of-order enhancements coming with the newest generation. Announcements claim 50% thruput increase for max EC12 over 80 processor z196 .. which would put it about 75BIPS.

traditional 370 simulation has claimed 10:1 (with further improvements in some of the commerical simuators with just-in-time "compilation" ... aka dynamic translation of repeatedly executive 370 snippets to native for direct execution). e5-2600 is two socket (chip) with 8 cores (processors) per chip for total of 16 processors benchmarked at aggregate of 527BIPS ... which might yield as much as mainframe 53BIPS (at 10:1) ... or approx. same as 80-processor z196. IBM has base price for e5-2600 blade at $1815 ... compared to $28M for 80-processor z196.

Note analysis from couple days ago claims IBM sells $5.25M in mainframe software, services and storage for every $1M in mainframe hardware. That would imply customers spend closer to $175M for 80-processor z196 ($28M + $147M).

If the Amazon "supercomputer" at $4829/hr, 51,132 cores, $48M/annum were running mainframe simulation (at 10:1) ... that would still be the equivalent of 3,380 z196 80 processor machines or $625B (one-tenth of the $6.25trillion from the previous post). The problem is would it require the equivalent amount of IBM mainframe software (at the cost of several hundred billion)?

Four socket e5-4600 blades are arriving ... which theoretically will be 1000BIPS machines ... but I haven't seen any published benchmarks yet ... four sockets (chips), 32 cores (processors), 64 hyperthreads ... which theoretically could give mainframe 100BIPS per blade.

Way back when, when I was involved in doing ECPS (initially for 138/148) ... there was factor 10 times increase in thruput dropping segments of vm370 kernel code into native "microcode". We were given that machines had 6kbytes of space available for ECPS native microcode and were to choose the 6kbytes of highest used vm370 kernel pathlengths. Old post given the result of kernel pathlength timings ... ordered by percent of total kernel time. 6kbyte cut-off accounted for 79.55% of vm370 kernel execution time ... dropping it into m'code resulted in ten times speedup (aka about 8% ... eliminating 72% of vm370 kernel time) ... aka low & mid-range 370s use to all be 370 simulator with software runnong on some native engine at approx. 10:1 overhead:
https://www.garlic.com/~lynn/94.html#21 370 ECPS VM microcode assist

as aside ... this mentions doing HA/CMP for unix platforms along with cluster scale-up.
https://www.garlic.com/~lynn/95.html#13

at the time, mainframe DB2 complained that if I was allowed to continue it would be a minimum of 5yrs ahead of them ... in both scale-up and availability. misc. past posts mentioning HA/CMP product
https://www.garlic.com/~lynn/subtopic.html#hacmp

also at the time, out doing marketing pitches, I coined the terms disaster survivability and geographic survivability ... and was also asked to write a section for the corporate continuous availability strategy document ... but the section got pulled when both Rochester and POK complained that they couldn't meet the requirements ... misc. past posts mentioning continuous availability
https://www.garlic.com/~lynn/submain.html#available

post from 2009 mentioning from (IBM) Annals of Release No Software Before Its Time:
https://www.garlic.com/~lynn/2009p.html#43 From The Annals of Release No Software Before Its Time

--
virtualization experience starting Jan1968, online at home since Mar1970

Blades versus z was Re: Turn Off Another Light - Univ. of Tennessee

Refed: **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **
From: lynn@GARLIC.COM (Anne & Lynn Wheeler)
Subject: Re: Blades versus z was Re: Turn Off Another Light - Univ. of Tennessee
Newsgroups: bit.listserv.ibm-main
Date: 2 Sep 2012 13:51:06 -0700
cfmpublic@NS.SYMPATICO.CA (Clark Morris) writes:
How much work can that z196 do compared with the 4829/hr Amazon cloud you mentioned? Given the great disparity between costs per instruction execution, on reading these posts it would seem that getting to a secure, fault tolerant operating system on blade clusters would be highly cost effective and that all new work should be moved to that environment.

re:
https://www.garlic.com/~lynn/2012l.html#51 Turn Off Another Light - Univ. of Tennessee
https://www.garlic.com/~lynn/2012l.html#56 Turn Off Another Light - Univ. of Tennessee

this is long-winded discussion in (linkedin) Greater IBM regarding financial industry spending several billions on attempting to move business critical applications off mainframes to "killer micros" in the 90s (contributed to lots of the press about mainframe death). The efforts failed disastrously for some specific reasons. More than a decade later ... when all of the reasons for the earlier failures had been addressed ... there was still significant resistance and risk adversion lingering because of the earlier failures.
https://www.garlic.com/~lynn/2012l.html#47 I.B.M. Mainframe Evolves to Serve the Digital World
also repeated in this ibm-main thread
https://www.garlic.com/~lynn/2012l.html#31 X86 server

for something totally different ... in the 70s, one of the online virtual machine based commercial service bureaus (claims that these virtual machine based services were the cloud of the 60s&70s and into the 80s) ... developed a "capability-based" operating system for ibm mainframe called gnosis. It was benchmarked doing ACP/TPF like transaction at higher-throughput than ACP/TPF (on the same hardware) ... part of the explanation was the higher integrity, higher abstraction ... allowed things that couldn't be done with the low-level ACP/TPF implementation. When M/D bought the business in the 80s, the capability-based operating system was spun-off into its own company (disclaimer: I was brought in to audit the implementation as part of the spin-off).

this has original background and history
http://cap-lore.com/CapTheory/upenn/Gnosis/Gnosis.html
it was spun-off as keykos
http://cap-lore.com/CapTheory/upenn/

more recently gnosis/keykos work has been the basis for non-mainframe capability based system
http://www.capros.org/

but there is significant difficulty getting market penetration and commercial acceptance.

--
virtualization experience starting Jan1968, online at home since Mar1970

Singer Cartons of Punch Cards

Refed: **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **
From: Anne & Lynn Wheeler <lynn@garlic.com>
Subject: Re: Singer Cartons of Punch Cards
Newsgroups: alt.folklore.computers
Date: Sun, 02 Sep 2012 18:14:02 -0400
sidd@situ.com (sidd) writes:
The speech is at

http://www.ratical.org/ratville/CAH/warracket.txt

The full text of his book "War is a Racket" may be found at

http://www.ratical.org/ratville/CAH/warisaracket.html


re:
https://www.garlic.com/~lynn/2012l.html#54 Singer Cartons of Punch Cards

Smedley Butler
https://en.wikipedia.org/wiki/Smedley_Butler
War Is a Racket
https://en.wikipedia.org/wiki/War_Is_a_Racket

"War Is a Racket" wiki includes reference to:

Perpetual war
https://en.wikipedia.org/wiki/Perpetual_war

above also includes references to Spinney, et. al efforts. Spinney worked closely with Boyd for many years ... Spinney's tribute to Boyd (that appeared in USNI Proceedings):
http://radio-weblogs.com/0107127/stories/2002/12/23/genghisJohnChuckSpinneysBioOfJohnBoyd.html

USNI:
http://www.usni.org/

misc. past posts & web references to boyd
https://www.garlic.com/~lynn/subboyd.html

--
virtualization experience starting Jan1968, online at home since Mar1970

Blades versus z was Re: Turn Off Another Light - Univ. of Tennessee

Refed: **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **
From: lynn@GARLIC.COM (Anne & Lynn Wheeler)
Subject: Re: Blades versus z was Re: Turn Off Another Light - Univ. of Tennessee
Newsgroups: bit.listserv.ibm-main
Date: 2 Sep 2012 15:33:57 -0700
mpost@SUSE.COM (Mark Post) writes:
Not particularly. From the work that Barton Robinson et. al. of Velocity Software has done, pretty much "A GHz is a GHz."

re:
https://www.garlic.com/~lynn/2012l.html#51 Turn Off Another Light - Univ. of Tennessee
https://www.garlic.com/~lynn/2012l.html#56 Turn Off Another Light - Univ. of Tennessee
https://www.garlic.com/~lynn/2012l.html#57 Turn Off Another Light - Univ. of Tennessee

current day ratio of memory access to processor cycle is similar to 60s ratio of disk access to processor cycle ... modern day cache misses are comparable to 60s disk i/o latency (measured in terms of processor cycles) ... giving rise to out-of-order execution, branch prediction, speculative execution, hyperthreading ... as means of providing overlapped execution during cache misses and memory access delays ... techniques that risc have been working with for decades ... and introduction of out-of-order execution is credited with major part of recent mainframe thruput increases.

Instructions per second
https://en.wikipedia.org/wiki/Million_instructions_per_second

Has Intel Core i7 Extreme Edition at (Dhrystone) 178BIPS

e5-2690 (two socket, 8cores/chip) review
http://www.istorya.net/forums/computer-hardware-21/485176-intel-xeon-e5-2690-and-e5-2660-8-core-sandy-bridge-ep-review.html

from above:
(Dhrystone)
E5-2690 @2.9GHZ 527.55BIPS
E5-2660 @2.2GHZ 428.15BIPS
X5690 @3.45GHZ 307.49BIPS
i7-3690 @4.78GHZ 288BIPS
AMD 6274 @2.4GHZ 272.73BIPS

(Whetstone)
e5.2690 @2.9GHZ 315GFLOPS
E5-2660 @2.2GHZ 263.7GFLOPS
X5690 @3.4GHZ 227GFLOPS
i7-3690 @4.78GHZ 176GFLOPS
AMD 6274 @2.4GHZ 168.11GFLOPS


--
virtualization experience starting Jan1968, online at home since Mar1970

Singer Cartons of Punch Cards

Refed: **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **
From: Anne & Lynn Wheeler <lynn@garlic.com>
Subject: Re: Singer Cartons of Punch Cards
Newsgroups: alt.folklore.computers
Date: Mon, 03 Sep 2012 00:59:16 -0400
Andrew Swallow <am.swallow@btinternet.com> writes:
The banker just persuaded the politicians that the companies were too big to be allowed to fail, particularly in an election year. The rest of us just got the bill. There was no reason why the resignation of all the company directors could not form part of the conditions of the loans.

re:
https://www.garlic.com/~lynn/2012g.html#60 Singer Cartons of Punch Cards
https://www.garlic.com/~lynn/2012l.html#54 Singer Cartons of Punch Cards

refs to Google+ discussion regarding "The Payoff: Why Wall Street Always Wins"
https://www.garlic.com/~lynn/2012l.html#53 CALCULATORS

"The Payoff" loc2694-98:
And Greenspan had admitted that Fed research "had been unable to find economies of scale in banking beyond a modest-sized institution." A decade ago, Greespan had continued, "I noted that 'megabanks being formed by growth and consolidation are increasingly complex entities that create the potential for unusually large systemic risks in the national and international economy should they fail.' Regrettably, we did little to address the problem."

... snip ...

Seems to be somewhat gratuitous, since Greespan was heavily involved in deregulation ... including giving Weill an exemption for takeover of Citi while Congress was being lobbied to repeal Glass-Steagall.

in the google+ discussion, somebody noted that the 5yr statute of limitation has been allowed to expire for much of what went on.

I've mentioned before about over a decade ago reviewing industry publication that gave average of top regional institutions compared to the average of the national institutions for several thousand measures. The data showed the regional institutions slightly more profitable than national instituations.

past posts mentioning comparing national & regional measures:
https://www.garlic.com/~lynn/2007e.html#65 Securing financial transactions a high priority for 2007
https://www.garlic.com/~lynn/2008p.html#25 How do group members think the US payments business will evolve over the next 3 years?
https://www.garlic.com/~lynn/2009g.html#59 We Can't Subsidize the Banks Forever
https://www.garlic.com/~lynn/2010f.html#51 The 2010 Census
https://www.garlic.com/~lynn/2010h.html#52 Our Pecora Moment
https://www.garlic.com/~lynn/2010i.html#16 Fake debate: The Senate will not vote on big banks
https://www.garlic.com/~lynn/2010i.html#21 Fake debate: The Senate will not vote on big banks
https://www.garlic.com/~lynn/2010k.html#43 Snow White and the Seven Dwarfs
https://www.garlic.com/~lynn/2010m.html#67 Idiotic programming style edicts
https://www.garlic.com/~lynn/2010p.html#7 What banking is. (Essential for predicting the end of finance as we know it.)
https://www.garlic.com/~lynn/2011d.html#28 The first personal computer (PC)
https://www.garlic.com/~lynn/2011j.html#14 Innovation and iconoclasm
https://www.garlic.com/~lynn/2011k.html#22 Slouching toward Weimar
https://www.garlic.com/~lynn/2011l.html#39 Kabuki Theater 1603-1629
https://www.garlic.com/~lynn/2011l.html#67 computer bootlaces
https://www.garlic.com/~lynn/2011o.html#7 John R. Opel, RIP
https://www.garlic.com/~lynn/2011o.html#83 The banking sector grew seven times faster than gross domestic product since the beginning of the financial crisis and too-big-to-fail: Banks Get Bigger After Dodd-Frank
https://www.garlic.com/~lynn/2012.html#25 You may ask yourself, well, how did I get here?
https://www.garlic.com/~lynn/2012e.html#1 The Dallas Fed Is Calling For The Immediate Breakup Of Large Banks
https://www.garlic.com/~lynn/2012g.html#9 JPM LOSES $2 BILLION USD!
https://www.garlic.com/~lynn/2012g.html#84 Monopoly/ Cartons of Punch Cards

past posts mentioning Greenspan & Weill
https://www.garlic.com/~lynn/2012.html#48 Fed's image tarnished by newly released documents
https://www.garlic.com/~lynn/2012b.html#67 How Economists Contributed to the Financial Crisis
https://www.garlic.com/~lynn/2012c.html#31 US real-estate has lost $7T in value
https://www.garlic.com/~lynn/2012c.html#44 New Citigroup Looks Too Much Like the Old One
https://www.garlic.com/~lynn/2012d.html#5 PC industry is heading for more change
https://www.garlic.com/~lynn/2012e.html#57 speculation
https://www.garlic.com/~lynn/2012f.html#31 Rome speaks to us. Their example can inspire us to avoid their fate
https://www.garlic.com/~lynn/2012g.html#16 Psychology Of Fraud: Why Good People Do Bad Things
https://www.garlic.com/~lynn/2012g.html#22 Psychology Of Fraud: Why Good People Do Bad Things
https://www.garlic.com/~lynn/2012g.html#59 Why Hasn't The Government Prosecuted Anyone For The 2008 Financial recession?
https://www.garlic.com/~lynn/2012g.html#77 Monopoly/ Cartons of Punch Cards
https://www.garlic.com/~lynn/2012g.html#82 How do you feel about the fact that today India has more IBM employees than US?
https://www.garlic.com/~lynn/2012g.html#87 Monopoly/ Cartons of Punch Cards
https://www.garlic.com/~lynn/2012h.html#45 Monopoly/ Cartons of Punch Cards
https://www.garlic.com/~lynn/2012i.html#17 Monopoly/ Cartons of Punch Cards
https://www.garlic.com/~lynn/2012i.html#25 Can anybody give me a clear idea about Cloud Computing in MAINFRAME ?
https://www.garlic.com/~lynn/2012i.html#94 Naked emperors, holy cows and Libor
https://www.garlic.com/~lynn/2012k.html#31 History--punched card transmission over telegraph lines
https://www.garlic.com/~lynn/2012k.html#38 Four Signs Your Awesome Investment May Actually Be A Ponzi Scheme
https://www.garlic.com/~lynn/2012k.html#64 Is there a connection between your strategic and tactical assertions?

--
virtualization experience starting Jan1968, online at home since Mar1970

Singer Cartons of Punch Cards

Refed: **, - **, - **, - **, - **
From: Anne & Lynn Wheeler <lynn@garlic.com>
Subject: Re: Singer Cartons of Punch Cards
Newsgroups: alt.folklore.computers
Date: Mon, 03 Sep 2012 01:25:16 -0400
Dave Garland <dave.garland@wizinfo.com> writes:
The near-collapse of the Detroit/Flint auto industry was the culmination of a 50-year process.

early 80s, there was article (washington post) calling for 100% unearned profit tax on us auto industry. The scenario was that the foreign auto import quotas was to reduce competition ... giving us auto industry significantly increased profits to completely remake themselves (into something more competitive). Instead they just pocketed the money and continued the status quo and business as usual.

1990, the industry had C4 taskforce to look at remaking themselves, plans were to heavily leverage technology and they invented participation from technology vendors. during the meetings they could clearly articulate the competitive issues, foreign competition and what needed to be done. however it is evident that they still weren't able to change the status quo.

recent posts mentioning C4 taskforce:
https://www.garlic.com/~lynn/2012.html#22 Who originated the phrase "user-friendly"?
https://www.garlic.com/~lynn/2012.html#31 Who originated the phrase "user-friendly"?
https://www.garlic.com/~lynn/2012c.html#26 Why Can't America Catch UP?
https://www.garlic.com/~lynn/2012d.html#54 IBM cuts more than 1,000 U.S. Workers
https://www.garlic.com/~lynn/2012h.html#31 How do you feel about the fact that today India has more IBM employees than US?
https://www.garlic.com/~lynn/2012i.html#86 Should the IBM approach be given a chance to fix the health care system?
https://www.garlic.com/~lynn/2012j.html#24 Why Asian companies struggle to manage global workers
https://www.garlic.com/~lynn/2012j.html#28 Why Asian companies struggle to manage global workers
https://www.garlic.com/~lynn/2012k.html#21 Is there a connection between your strategic and tactical assertions?
https://www.garlic.com/~lynn/2012l.html#12 First Battle: Operation Starlite and the Beginning of the Blood Debt in Vietnam

--
virtualization experience starting Jan1968, online at home since Mar1970

Singer Cartons of Punch Cards

Refed: **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **
From: Anne & Lynn Wheeler <lynn@garlic.com>
Subject: Re: Singer Cartons of Punch Cards
Newsgroups: alt.folklore.computers
Date: Mon, 03 Sep 2012 08:44:46 -0400
sidd@situ.com (sidd) writes:
The speech is at

http://www.ratical.org/ratville/CAH/warracket.txt

The full text of his book "War is a Racket" may be found at

http://www.ratical.org/ratville/CAH/warisaracket.html


re:
https://www.garlic.com/~lynn/2012l.html#58 Singer Cartons of Punch Cards
https://www.garlic.com/~lynn/2012l.html#60 Singer Cartons of Punch Cards
https://www.garlic.com/~lynn/2012l.html#61 Singer Cartons of Punch Cards

as an aside ... many of the same names & entities that show up in Prescott&Walker history and show up in the Smedly Butler references, also show up playing major roles in the Pecora hearings (senate hearings into '29 crash resulted in Glass-Steagall ... and some prosecutions).

I've mentioned several times that Jan2009, I was asked to HTML'ize the Pecora hearings (had been scanned fall of 2008 at Boston public library) with lots of internal cross-references as well as URLs between what happened this time and what happened then (some anticipation that the new congress had some appetite to do somehting). After working on it for some time, I got a call that it wouldn't be needed after all (references to enormous piles of wallstreet money being spread around capital hill).

recent reference
https://www.garlic.com/~lynn/2012l.html#48 The Payoff: Why Wall Street Always Wins
https://www.garlic.com/~lynn/2012l.html#53 CALCULATORS

--
virtualization experience starting Jan1968, online at home since Mar1970

Singer Cartons of Punch Cards

Refed: **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **
From: Anne & Lynn Wheeler <lynn@garlic.com>
Subject: Re: Singer Cartons of Punch Cards
Newsgroups: alt.folklore.computers
Date: Mon, 03 Sep 2012 09:04:33 -0400
Peter Flass <Peter_Flass@Yahoo.com> writes:
Probably the difference in the CEO's pay. The worst thing a corporation can do is locate its headquarters in a large city. In a smaller city a bank president, for example, would be the biggest fish in a small pond. In a large city I think they compete with one another in extravagant lifestyles. Of course with globalization they're now probably competing with people in Berne of Shanghai.

re:
https://www.garlic.com/~lynn/2012l.html#60 Singer Cartons of Punch Cards

I've periodically (*also*) commented in the past the only apparent motivation for too-big-to-fail was executive pay proportional to corporation size ... since the size seem to serve no other useful purpose.

there have been various references that egos were major factor behind the latest mess (not just the money).

past posts mentioning loosing to Gerstner to be heir apparent at AMEX ... leaving (with his protege Jamie Dimon) and nearly starting from scratch to create empire larger than AMEX. Eventually acquires insurance company and then take-over of citibank (forming citi group) ... which is in violation of Glass-Steagall. Greenspan gives gives him an exemption while he lobbies congress for repeal of Glass-Steagall ... that opens the door for too-big-to-fail
https://www.garlic.com/~lynn/2012g.html#9 JPM LOSES $2 BILLION USD!
https://www.garlic.com/~lynn/2012g.html#16 Psychology Of Fraud: Why Good People Do Bad Things
https://www.garlic.com/~lynn/2012g.html#61 Why Hasn't The Government Prosecuted Anyone For The 2008 Financial recession?
https://www.garlic.com/~lynn/2012g.html#82 How do you feel about the fact that today India has more IBM employees than US?
https://www.garlic.com/~lynn/2012g.html#87 Monopoly/ Cartons of Punch Cards
https://www.garlic.com/~lynn/2012h.html#45 Monopoly/ Cartons of Punch Cards
https://www.garlic.com/~lynn/2012h.html#79 Monopoly/ Cartons of Punch Cards
https://www.garlic.com/~lynn/2012i.html#25 Can anybody give me a clear idea about Cloud Computing in MAINFRAME ?
https://www.garlic.com/~lynn/2012k.html#31 History--punched card transmission over telegraph lines

wandering a bit back to computers:

AMEX had also been in bidding war with KKR (large private equity firm) for the reverse-IPO of RJR and KKR wins. KKR then runs into problem with RJR and hires Gerstner away from AMEX to turn-around RJR. IBM board then hires Gerstner to resurrect IBM ... afterwards he goes on to be head up Carlyle (another large private equity firm).

Along the way, AMEX in '92 does ipo/spin-off of major dataprocessing unit as First Data (largest IPO up until that time). More recently KKR does reverse-IPO of First Data (taking it private again, disclaimer I do a stint as chief scientist at first data). recent references to first data

gerstner posts
https://www.garlic.com/~lynn/submisc.html#gerstner
private equity posts
https://www.garlic.com/~lynn/submisc.html#private.equity

posts
https://www.garlic.com/~lynn/2012.html#57 The Myth of Work-Life Balance
https://www.garlic.com/~lynn/2012b.html#70 Four Sources of Trust, Crypto Not Scaling
https://www.garlic.com/~lynn/2012d.html#21 Inventor of e-mail honored by Smithsonian
https://www.garlic.com/~lynn/2012f.html#19 Can Mainframes Be Part Of Cloud Computing?
https://www.garlic.com/~lynn/2012g.html#82 How do you feel about the fact that today India has more IBM employees than US?
https://www.garlic.com/~lynn/2012g.html#87 Monopoly/ Cartons of Punch Cards
https://www.garlic.com/~lynn/2012h.html#55 The Invention of Email
https://www.garlic.com/~lynn/2012j.html#9 Can anybody give me a clear idea about Cloud Computing in MAINFRAME ?
https://www.garlic.com/~lynn/2012k.html#34 History--punched card transmission over telegraph lines

and recent posts mentioning too-big-to-fail
https://www.garlic.com/~lynn/2012.html#0 Revolution Through Banking?
https://www.garlic.com/~lynn/2012.html#25 You may ask yourself, well, how did I get here?
https://www.garlic.com/~lynn/2012b.html#35 Entropy and #SocialMedia
https://www.garlic.com/~lynn/2012c.html#31 US real-estate has lost $7T in value
https://www.garlic.com/~lynn/2012c.html#32 US real-estate has lost $7T in value
https://www.garlic.com/~lynn/2012c.html#45 Fannie, Freddie Charge Taxpayers For Legal Bills
https://www.garlic.com/~lynn/2012c.html#46 PC industry is heading for more change
https://www.garlic.com/~lynn/2012c.html#52 PC industry is heading for more change
https://www.garlic.com/~lynn/2012c.html#54 PC industry is heading for more change
https://www.garlic.com/~lynn/2012c.html#55 PC industry is heading for more change
https://www.garlic.com/~lynn/2012d.html#5 PC industry is heading for more change
https://www.garlic.com/~lynn/2012d.html#45 Banks Repaid Fed Bailout With Other Fed Money: Government Report
https://www.garlic.com/~lynn/2012d.html#48 IBM cuts more than 1,000 U.S. workers
https://www.garlic.com/~lynn/2012e.html#1 The Dallas Fed Is Calling For The Immediate Breakup Of Large Banks
https://www.garlic.com/~lynn/2012e.html#31 PC industry is heading for more change
https://www.garlic.com/~lynn/2012e.html#33 PC industry is heading for more change
https://www.garlic.com/~lynn/2012e.html#35 The Dallas Fed Is Calling For The Immediate Breakup Of Large Banks
https://www.garlic.com/~lynn/2012e.html#37 The $30 billion Social Security hack
https://www.garlic.com/~lynn/2012e.html#40 Who Increased the Debt?
https://www.garlic.com/~lynn/2012e.html#42 Who Increased the Debt?
https://www.garlic.com/~lynn/2012e.html#86 CISPA legislation seen by many as SOPA 2.0
https://www.garlic.com/~lynn/2012f.html#14 Free $10 Million Loans For All! and Other Wall Street Notes
https://www.garlic.com/~lynn/2012f.html#69 Freefall: America, Free Markets, and the Sinking of the World Economy
https://www.garlic.com/~lynn/2012f.html#75 Fed Report: Mortgage Mess NOT an Inside Job
https://www.garlic.com/~lynn/2012f.html#88 Defense acquisitions are broken and no one cares
https://www.garlic.com/~lynn/2012g.html#6 Adult Supervision
https://www.garlic.com/~lynn/2012g.html#9 JPM LOSES $2 BILLION USD!
https://www.garlic.com/~lynn/2012g.html#12 JPM LOSES $2 BILLION USD!
https://www.garlic.com/~lynn/2012g.html#20 Psychology Of Fraud: Why Good People Do Bad Things
https://www.garlic.com/~lynn/2012g.html#22 Psychology Of Fraud: Why Good People Do Bad Things
https://www.garlic.com/~lynn/2012g.html#28 REPEAL OF GLASS-STEAGALL DID NOT CAUSE THE FINANCIAL CRISIS - WHAT DO YOU THINK?
https://www.garlic.com/~lynn/2012g.html#70 Monopoly/ Cartons of Punch Cards
https://www.garlic.com/~lynn/2012g.html#83 Monopoly/ Cartons of Punch Cards
https://www.garlic.com/~lynn/2012g.html#84 Monopoly/ Cartons of Punch Cards
https://www.garlic.com/~lynn/2012h.html#21 The Age of Unsatisfying Wars
https://www.garlic.com/~lynn/2012h.html#25 US economic update. Everything that follows is a result of what you see here
https://www.garlic.com/~lynn/2012h.html#26 US economic update. Everything that follows is a result of what you see here
https://www.garlic.com/~lynn/2012h.html#41 Monopoly/ Cartons of Punch Cards
https://www.garlic.com/~lynn/2012h.html#45 Monopoly/ Cartons of Punch Cards
https://www.garlic.com/~lynn/2012h.html#47 Monopoly/ Cartons of Punch Cards
https://www.garlic.com/~lynn/2012h.html#53 Monopoly/ Cartons of Punch Cards
https://www.garlic.com/~lynn/2012h.html#55 The Invention of Email
https://www.garlic.com/~lynn/2012h.html#58 Monopoly/ Cartons of Punch Cards
https://www.garlic.com/~lynn/2012h.html#82 Interesting News Article
https://www.garlic.com/~lynn/2012i.html#14 Monopoly/ Cartons of Punch Cards
https://www.garlic.com/~lynn/2012i.html#25 Can anybody give me a clear idea about Cloud Computing in MAINFRAME ?
https://www.garlic.com/~lynn/2012i.html#29 Monopoly/ Cartons of Punch Cards
https://www.garlic.com/~lynn/2012i.html#60 Monopoly/ Cartons of Punch Cards
https://www.garlic.com/~lynn/2012i.html#86 Should the IBM approach be given a chance to fix the health care system?
https://www.garlic.com/~lynn/2012i.html#90 Operating System, what is it?
https://www.garlic.com/~lynn/2012j.html#25 This Is The Wall Street Scandal Of All Scandals
https://www.garlic.com/~lynn/2012j.html#28 Why Asian companies struggle to manage global workers
https://www.garlic.com/~lynn/2012j.html#65 Monopoly/ Cartons of Punch Cards
https://www.garlic.com/~lynn/2012k.html#7 Is there a connection between your strategic and tactical assertions?
https://www.garlic.com/~lynn/2012k.html#9 Sandy Weill's About-Face on Big Banks
https://www.garlic.com/~lynn/2012k.html#31 History--punched card transmission over telegraph lines
https://www.garlic.com/~lynn/2012k.html#37 If all of the American earned dollars hidden in off shore accounts were uncovered and taxed do you think we would be able to close the deficit gap?
https://www.garlic.com/~lynn/2012k.html#75 What's the bigger risk, retiring too soon, or too late?

--
virtualization experience starting Jan1968, online at home since Mar1970

Singer Cartons of Punch Cards

Refed: **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **
From: Anne & Lynn Wheeler <lynn@garlic.com>
Subject: Re: Singer Cartons of Punch Cards
Newsgroups: alt.folklore.computers
Date: Mon, 03 Sep 2012 09:34:12 -0400
Anne & Lynn Wheeler <lynn@garlic.com> writes:
"The Payoff" loc2694-98:

And Greenspan had admitted that Fed research "had been unable to find economies of scale in banking beyond a modest-sized institution." A decade ago, Greespan had continued, "I noted that 'megabanks being formed by growth and consolidation are increasingly complex entities that create the potential for unusually large systemic risks in the national and international economy should they fail.' Regrettably, we did little to address the problem."

... snip ...


re:
https://www.garlic.com/~lynn/2012l.html#60 Singer Cartons of Punch Cards

from yesterday

Forget Bernanke: A Paper At Jackson Hole May Have Changed The Future Of Economics
http://www.businessinsider.com/michael-woodford-endorses-ngdp-targeting-2012-9

from above:
Since the crisis hit, the Federal Reserve has attempted to juice the economy through a program that's called Quantitative Easing, which is buying long-dated government bonds and mortgage backed securities It's the same scheme that the Bank of Japan has tried in its long battle against saggy growth and deflation.

... snip ...

but in Confidence Men: Wall Street, Washington, and the Education of a President
https://www.amazon.com/Confidence-Men-Washington-Education-ebook/dp/B0089LOKKS/

mentions that economic A-team helped get the president elected but they were going to choose the "swedish" solution (over the lingering "japan" solution) and hold those responsible on wallstreet accountable. Instead the president appoints the B-team, people that were involved in creating the economic mess and not likely to hold anybody accountable.

also from "Forget Bernanke" article
Specifically he cited the "portfolio balance channel", which means that QE would work by reducing the supply of super-safe Treasuries and Mortgage Backed Securities, and instead push investors into other areas (like corporate bonds), thus depressing yields and borrowing costs in the private sector. Think of it this way: During the crisis, everyone sought refuge in the safety of Treasuries. Bernanke was now seeking to deprive them of this safety valve, and force their cash into areas where it might do some good in the economy.

... snip ...

In FED documents (that were released under FOIA after year of litigation) ... FED provides upwards of $30T in loans to too-big-to-fail ... in theory for them to use the money to loan to mainstreet. Instead the institutions use it to buy treasuries making huge profit off the spread between nearly zero percent loans from FED and what treasuries were paying (large amounts then used to pay bonuses for their executives). Bernanke then is asked about it and says he has no way of forcing the too-big-to-fail to use FED money for loans to mainstreet.

Documents also have FED buying huge amounts of toxic CDOs from too-big-to-fail for 98cents on the dollar (presumably the "super-safe" in the article *only* applies to Treasuries and is not met to infer anything about Mortgage Backed Securities).

$700B in TARP was originally appropriated to buy toxic assets being held off-balance. However, just the four largest too-big-to-fail were carrying $5.2T in triple-A rated toxic CDOs off-balance at the end of 2008.
Bank's Hidden Junk Menaces $1 Trillion Purge
http://www.bloomberg.com/apps/news?pid=newsarchive&sid=akv_p6LBNIdw&refer=home

earlier in the fall of 2008, several tens of billions of the triple-A rated toxic CDOs had gone for 22cents on the dollar ... with only $700B appropriated ... there was no way that it could address a problem of that magnitude. Obviously buying off-balance toxic CDOs at 98cents on the dollar was another gratuitous gift for the too-big-to-fail (if the too-big-to-fail had been forced to big the triple-A rated toxic CDOs back on to the balance sheet, they would have been declared insolvent and forced to be liquidated)

in total there was an estimated $27T in triple-A rated toxic CDOs done during the bubble
http://www.bloomberg.com/apps/news?pid=newsarchive&refer=home&sid=a0jln3.CSS6

misc. past posts mentioning FED being forced to release the documents about what was going on:
https://www.garlic.com/~lynn/2010p.html#17 What banking is. (Essential for predicting the end of finance as we know it.)
https://www.garlic.com/~lynn/2010p.html#23 They always think we don't understand
https://www.garlic.com/~lynn/2010p.html#46 TCM's Moguls documentary series
https://www.garlic.com/~lynn/2010q.html#58 Programmer Charged with thieft (maybe off topic)
https://www.garlic.com/~lynn/2010q.html#66 Ernst & Young sued for fraud over Lehman
https://www.garlic.com/~lynn/2011.html#48 What do you think about fraud prevention in the governments?
https://www.garlic.com/~lynn/2011b.html#45 Productivity And Bubbles
https://www.garlic.com/~lynn/2011j.html#3 Greed, Excess and America's Gaping Class Divide
https://www.garlic.com/~lynn/2011j.html#11 Innovation and iconoclasm
https://www.garlic.com/~lynn/2011j.html#39 Advice from Richard P. Feynman
https://www.garlic.com/~lynn/2011k.html#4 Geithner, Bernanke have little in arsenal to fight new crisis
https://www.garlic.com/~lynn/2011k.html#23 Wall Street Aristocracy Got $1.2 Trillion in Fed's Secret Loans
https://www.garlic.com/~lynn/2011l.html#73 computer bootlaces
https://www.garlic.com/~lynn/2011n.html#49 The men who crashed the world
https://www.garlic.com/~lynn/2011n.html#57 The Mortgage Crisis---Some Inside Views
https://www.garlic.com/~lynn/2011o.html#37 Civilization, doomed?
https://www.garlic.com/~lynn/2011o.html#74 The Wall Street Pentagon Papers: Biggest Scam In World History Exposed: Are The Federal Reserve's Crimes Too Big To Comprehend?
https://www.garlic.com/~lynn/2011o.html#93 The men who crashed the world
https://www.garlic.com/~lynn/2011p.html#3 The Obama Spending Non-surge
https://www.garlic.com/~lynn/2011p.html#7 FDR explains one dimension of our problem: bankers own the government
https://www.garlic.com/~lynn/2011p.html#30 21st Century Management approach?
https://www.garlic.com/~lynn/2011p.html#63 21st Century Management approach?
https://www.garlic.com/~lynn/2012c.html#32 US real-estate has lost $7T in value
https://www.garlic.com/~lynn/2012c.html#45 Fannie, Freddie Charge Taxpayers For Legal Bills
https://www.garlic.com/~lynn/2012c.html#46 PC industry is heading for more change
https://www.garlic.com/~lynn/2012c.html#55 PC industry is heading for more change
https://www.garlic.com/~lynn/2012d.html#45 Banks Repaid Fed Bailout With Other Fed Money: Government Report
https://www.garlic.com/~lynn/2012h.html#26 US economic update. Everything that follows is a result of what you see here
https://www.garlic.com/~lynn/2012i.html#14 Monopoly/ Cartons of Punch Cards
https://www.garlic.com/~lynn/2012j.html#65 Monopoly/ Cartons of Punch Cards

--
virtualization experience starting Jan1968, online at home since Mar1970

Singer Cartons of Punch Cards

Refed: **, - **, - **, - **, - **, - **, - **
From: Anne & Lynn Wheeler <lynn@garlic.com>
Subject: Re: Singer Cartons of Punch Cards
Newsgroups: alt.folklore.computers
Date: Mon, 03 Sep 2012 18:17:27 -0400
Anne & Lynn Wheeler <lynn@garlic.com> writes:
In FED documents (that were released under FOIA after year of litigation) ... FED provides upwards of $30T in loans to too-big-to-fail ... in theory for them to use the money to loan to mainstreet. Instead the institutions use it to buy treasuries making huge profit off the spread between nearly zero percent loans from FED and what treasuries were paying (large amounts then used to pay bonuses for their executives). Bernanke then is asked about it and says he has no way of forcing the too-big-to-fail to use FED money for loans to mainstreet.

re:
https://www.garlic.com/~lynn/2012l.html#64 Singer Cartons of Punch Cards

Bailout
https://www.amazon.com/Bailout-ebook/dp/B00818J57W

Barofsky is brought in as inspector general for TARP program ... which had been appropriated initial $350B with another $350B available for purchase of toxic assets from the too-big-to-fail. Apparently treasury (under Paulson) from possibly the beginning, hadn't intended to buy/purchase toxic assets. "Bailout" has Paulson telling congress that he was making loans to TBTF instead so that they could turn around and lend to mainstreet. Much of this had already happened by the time Barofsky came on board and those loans had no strings attached .. Barofsky uses congressional leverage for subsequent loans to at least require the borrowers to report what they were using it for (apparently none for lending to main street).

Supposedly treasury had also told congress (besides the TBTF would use the money to make loans to mainstreet), that the loans would only be to solvent TBTF that weren't on the verge of failure (but other reports was that they knew that the TBTF getting the loans would have failed w/o them, aka ... and that they weren't going to be using the money to make loans to mainstreet) ... several iterations of believing TBTF would make loans to mainstreet.

and ... Bailout, pg85/loc1743-47:
The mortgage-backed securities were a huge boon for the banks. At every stage of their creation and sale, the Wall Street institutions offering them raked in large fees, and every firm that participated in the transactions (from loan origination through the final sale of the bonds) enjoyed huge profits. With high credit ratings in hand, the AAA subprime bonds became wildly attractive to investors and other financial institutions because they paid a higher interest rate than other AAA-rated bonds, such as those issued by the U.S. government, and because regulators began giving such highly rated bonds favorable treatment.

... snip ... Bailout, pg85/loc1756-59:
For their part, the banks buying the mortgages weren't terribly concerned about the obvious problems with the mortgages being thrown into those pools. The profits from the securitization mill were too high, and the losses would not be borne by them but by the investors buying the bonds. Later investigations would demonstrate that several of the largest banks had been on full notice that the mortgages they were packaging were littered with fraud but continued to sell and package them.

... snip ...

The individual compensation was so huge that it easily offset any concerns that there might have been about the consequences to their institution, the economy, and/or the country.

--
virtualization experience starting Jan1968, online at home since Mar1970

Singer Cartons of Punch Cards

Refed: **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **
From: Anne & Lynn Wheeler <lynn@garlic.com>
Subject: Re: Singer Cartons of Punch Cards
Newsgroups: alt.folklore.computers
Date: Tue, 04 Sep 2012 11:29:38 -0400
jmfbahciv <See.above@aol.com> writes:
The muni market has dried up. One of those economic boosting deals gave the option of government entities to issue a 5% bond but pay <3% (according to my broker and I still don't understand this one). The bond interest paid out is taxable so I'm assuming the 2% difference is getting covered by the Fed? Whatever is being done, it sounds squirrely and you can't find a muni bond for income.

re:
https://www.garlic.com/~lynn/2012l.html#64 Singer Cartons of Punch Cards

as it dawned on investers that it was possible to buy triple-A ratings from the rating agencies ... they started to worry whether any of the rating agencies' ratings could be trusted ... and the muni-market completely froze. Buffett then stepped in with muni insurance to unfreeze the muni-market.

the muni-market has longer term structural problems ... 1) there has been some number of legal actions against wallstreet about outright fraud in bond offerings 2) some number of municipalities have become collaterial damage in the economic mess. During the height of the boom, there was big overbuilding in the real estate market, many municipalities had to build-out their infrastructures for the new developments ... issuing bonds to cover the cost ... assuming the debt service would be covered by taxes from all the new houses. When the crash happened ... lots of municipalities weren't getting the tax revenue to cover debt service fro the new bonds, 3) general collatoral damage with crash of the housing market there has been corresponding crash in the real-estate taxes that fund the municipalities (and used to service bond debt).

the part of both treasury and fed giving TBTF nearly free money because the TBTF would (of course) turn around and lend to mainstreet ... seems to have been total farce (just facade told to congress and the public ... pure Kabuki theater ... since TBTF were given several different opportunities and didn't do it).

re:
https://www.garlic.com/~lynn/2012l.html#65 Singer Cartons of Punch Cards

"Bailout" has Barofsky dumb-founded that treasury was giving all the TARP money to TBTF in the closing days of 2008 ... and that no strings were actually attached to the funds ... just claims that they expected that TBTF would feel compelled to use the TARP-funds to lend to mainstreet .... and seemed to be totally surprised when they didn't. these are a bunch of former Goldman-Sachs wiz-kids (joke during the last decade that US Treasury was Goldman-Sachs branch offine in washington dc). The story-line was then repeated with the enormous funds from FED for TBTF (and still no lending to mainstreet).

You have some of the top wallstreet financial wizards (at treasury having run one of the most "successful" TBTF) effectively claiming they have no idea how TBTF operates (not able to predict what TBTF will do when given enormous piles of money with no strings attached).

The current line is to periodic have FED buy up much of US Treasuries ... so investors are forced out of the US Treasury market and hopefully actually invest in mainstreet.

misc. past posts mentioning Buffett unfreezing the muni-bond market as the economy was crashing (big part being loss of trust in the rating agencies):
https://www.garlic.com/~lynn/2008o.html#52 Why is sub-prime crisis of America called the sub-prime crisis?
https://www.garlic.com/~lynn/2009b.html#78 How to defeat new telemarketing tactic
https://www.garlic.com/~lynn/2009c.html#29 How to defeat new telemarketing tactic
https://www.garlic.com/~lynn/2009d.html#77 Who first mentioned Credit Crunch?
https://www.garlic.com/~lynn/2009e.html#8 The background reasons of Credit Crunch
https://www.garlic.com/~lynn/2010f.html#81 The 2010 Census
https://www.garlic.com/~lynn/2010l.html#53 Who is Really to Blame for the Financial Crisis?
https://www.garlic.com/~lynn/2010p.html#17 What banking is. (Essential for predicting the end of finance as we know it.)
https://www.garlic.com/~lynn/2011b.html#43 Productivity And Bubbles
https://www.garlic.com/~lynn/2011c.html#46 If IBM Hadn't Bet the Company
https://www.garlic.com/~lynn/2011d.html#30 The first personal computer (PC)
https://www.garlic.com/~lynn/2011e.html#60 In your opinon, what is the highest risk of financial fraud for a corporation ?
https://www.garlic.com/~lynn/2011i.html#2 'Megalomania, Insanity' Fueled Bubble: Munger
https://www.garlic.com/~lynn/2011j.html#44 S&P Downgrades USA; Time to Downgrade S&P?
https://www.garlic.com/~lynn/2011l.html#69 computer bootlaces
https://www.garlic.com/~lynn/2012.html#92 Has anyone successfully migrated off mainframes?
https://www.garlic.com/~lynn/2012c.html#54 PC industry is heading for more change

--
virtualization experience starting Jan1968, online at home since Mar1970

Strings (hijacked from: The IBM zEnterprise EC12 announcment)

Refed: **, - **, - **, - **
From: lynn@GARLIC.COM (Anne & Lynn Wheeler)
Subject: Re: Strings (hijacked from: The IBM zEnterprise EC12 announcment)
Newsgroups: bit.listserv.ibm-main
Date: 4 Sep 2012 09:35:28 -0700
PaulGBoulder@AIM.COM (Paul Gilmartin) writes:
And here, I find myself in rare agreement with John G.'s view (if I understand correctly). A char[] containing no \0 is a perfectly valid array of char. It is not a string, by C's convention, and there is no requirement that a char[] represent a string.

in the 90s, C-language string related buffer exploits were top of internet attacks. I've been on campaign about this for long time. lots of past posts
https://www.garlic.com/~lynn/subintegrity.html#overflow

the mainframe TCP/IP stack from the 80s was done in vs/pascal and had none of the C-language buffer length related problems. The implementation had a few other performance issues ... getting 44kbytes/sec thruput using nearly whole 3090 processor. I did the changes for RFC1044 support and in some performance tests at cray research got channel media thruput between 4341 and cray using only modest amount of 4341 processor
https://www.garlic.com/~lynn/subnetwork.html#1044

also, air force performance evaluation of Multics (implemented in PLI) noted that it had no buffer length related problems. Old post about IBM Research update of the Air Force Multics study
https://www.garlic.com/~lynn/2002l.html#42 Thirty Years Later: Lessons from the Multics Security Evaluation

This is post about analysis I did of the Mitre CVE exploit database ... looking for ways to improve my merged security taxonomy & glossary (and how you do you structure thinking about security)
https://www.garlic.com/~lynn/2004e.html#43 security taxonomy and CVE

I suggested to mitre that they start requiring reports to have a little more structured information since they were quite free-form at the time. Their response was that they were lucky to get reports in any form at all ... adding structure form requirements afraid some people would just not do the report (although they have since started advising about more structure in the reports). Later , NIST came out with analysis that exploits were approx. nearly 1/3rd buffer related, 1/3rd automated script execution, and 1/3rd social engineering (with various other misc.).

I periodically mention this meeting in ellison's conference room
https://www.garlic.com/~lynn/95.html#13

a couple weeks later cluster scale-up is transferred and we are told we couldn't work on anything with more than four processors ... motivating us to leave. A couple of the other people mentioned in the meeting, later leave and show up at small client/server startup responsible for something called "commerce server". We get brought in as consultants because they want to do payment transactions on the server, the startup had also invented this technology called "SLL" they want to use, the result is now frequently called "electronic commerce".

Part of the deployment for "electronic commerce" was developing something called a "payment gateway" ... sits on the internet and handles transactions between webservers and the payment networks (we periodically refer to it as the original SOA). misc. past posts mentioning payment gateway
https://www.garlic.com/~lynn/subnetwork.html#gateway

Part of protection for the payment gateways there are multiple layers of firewalls and other kinds of filters. A common internet attack is long strings ... attempting to leverage buffer-overflow vulnerabilities found in about anything implemented in C-language ... so part of the intermediate security layers are checks for excessive long strings.

We also have to do audits/reviews of SSL, digital certificates, certificate issuing authorities, etc ... and come up with some requirements about how things are deployed. Almost immediately the requirements are violated and we start referring to it as "comfort security" (aka security that provides feeling of comfort to all the users). misc. past posts mentioning SSL, certs, CAs, etc
https://www.garlic.com/~lynn/subpubkey.html#sslcert

--
virtualization experience starting Jan1968, online at home since Mar1970

Singer Cartons of Punch Cards

Refed: **, - **, - **, - **, - **, - **, - **, - **, - **, - **
From: Anne & Lynn Wheeler <lynn@garlic.com>
Subject: Re: Singer Cartons of Punch Cards
Newsgroups: alt.folklore.computers
Date: Tue, 04 Sep 2012 17:58:40 -0400
re:
https://www.garlic.com/~lynn/2012l.html#54 Singer Cartons of Punch Cards
https://www.garlic.com/~lynn/2012l.html#58 Singer Cartons of Punch Cards
https://www.garlic.com/~lynn/2012l.html#60 Singer Cartons of Punch Cards
https://www.garlic.com/~lynn/2012l.html#61 Singer Cartons of Punch Cards
https://www.garlic.com/~lynn/2012l.html#62 Singer Cartons of Punch Cards
https://www.garlic.com/~lynn/2012l.html#63 Singer Cartons of Punch Cards
https://www.garlic.com/~lynn/2012l.html#64 Singer Cartons of Punch Cards
https://www.garlic.com/~lynn/2012l.html#65 Singer Cartons of Punch Cards
https://www.garlic.com/~lynn/2012l.html#66 Singer Cartons of Punch Cards

Bailout pg157/loc3106-9
HAMP was not separate from the bank bailouts; it was an essential part of them. From that perspective, it didn't matter if the modifications failed after a year or so of trial payments or if struggling borrowers placed into doomed trial modifications ended up far worse off, as long as the banks were able to stretch out their pain until their profits returned.

pg163/loc3206-8
In the short executive summary that Issa cited in his release we didn't give the details about what the $23.7 trillion figure really represented, instead stating that "the total potential Federal Government support could reach up to $23.7 trillion"

... snip ...

i.e. none of the programs from the government were for the public, they were all for the banksters ... everything else was pure fabrication.

"Confidence Men" and "Bailout" pretty much have everything a bankster give-away from the beginning. The congressional staffers "How Republicans Went Crazy" and "The Payoff" describe efforts that appear to try and help the public, just were never successful.

recent posts
https://www.garlic.com/~lynn/2012d.html#10 PC industry is heading for more change
https://www.garlic.com/~lynn/2012d.html#11 PC industry is heading for more change

one of snippets on the subject:

Ask the mineshaft: what's gone wrong with America? The decay spreads faster than I imagined possible.
http://fabiusmaximus.wordpress.com/2012/03/02/36115/

from above:
The mortgage settlement by State attorneys general marks a new low for America. A massive criminal conspiracy -- the Mortgage Electronic Registration Systems (MERs, see Wikipedia), plus large-scale perjury ("robo-signing" foreclosure papers) and fraud before our courts. All settled with a slap on the wrist to the banks. It teaches large corporations thay they lie beyond the law, a large step beyond the traditional lax enforcement of laws against big businesses.

... snip ...

a few past posts mentioning banksters
https://www.garlic.com/~lynn/2009h.html#23 Consumer Credit Crunch and Banking Writeoffs
https://www.garlic.com/~lynn/2009h.html#25 The Paradox of Economic Recovery
https://www.garlic.com/~lynn/2009h.html#36 Analysing risk, especially credit risk in Banks, which was a major reason for the current crisis
https://www.garlic.com/~lynn/2009i.html#52 Credit cards
https://www.garlic.com/~lynn/2010m.html#24 Little-Noted, Prepaid Rules Would Cover Non-Banks As Wells As Banks
https://www.garlic.com/~lynn/2011.html#50 What do you think about fraud prevention in the governments?
https://www.garlic.com/~lynn/2011f.html#52 Are Americans serious about dealing with money laundering and the drug cartels?
https://www.garlic.com/~lynn/2011p.html#88 Fed Report Finds Speculators Played Big Role in Housing Collapse

--
virtualization experience starting Jan1968, online at home since Mar1970

Cultural attitudes towards failure

Refed: **, - **, - **, - **, - **, - **, - **
From: lynn@garlic.com (Lynn Wheeler)
Date: 04 Sep, 2012
Subject: Cultural attitudes towards failure.
Blog: Boyd Strategy
re:
http://lnkd.in/9q5Zvq
and
https://www.garlic.com/~lynn/2012k.html#87 Cultural attitudes towards failure
https://www.garlic.com/~lynn/2012l.html#2 Cultural attitudes towards failure
https://www.garlic.com/~lynn/2012l.html#5 Cultural attitudes towards failure
https://www.garlic.com/~lynn/2012l.html#10 Cultural attitudes towards failure
https://www.garlic.com/~lynn/2012l.html#13 Cultural attitudes towards failure
https://www.garlic.com/~lynn/2012l.html#17 Cultural attitudes towards failure

Long ago and far away, I was blogging (before it was called blogging) about large bureaucracies turning into blackholes where nothing can escape. The issue was an analogy where change could occur ... about that time there was paper on blackholes evaporate. previously mentioned here in "UAV vis-a-vis F35"
http://lnkd.in/Q3hJ5G
and
https://www.garlic.com/~lynn/2011l.html#63 UAV vis-a-vis F35
https://www.garlic.com/~lynn/2011m.html#4 UAV vis-a-vis F35
https://www.garlic.com/~lynn/2011n.html#20 UAV vis-a-vis F35
https://www.garlic.com/~lynn/2011o.html#10 UAV vis-a-vis F35

originally posted after attending navy history conference last year ... the theme was on 100th anniv. of navy aviation ... but there was lots of discussion about UAVs including asking the academy students how many were planning on being naval aviators.

The bigger the bureaucracy, the more there are those with vested interests in the status quo, and the more resistance to change. One agent of change is major failure .... saw that with IBM ... and board bringing in Gerstner to resurrect the company.

recent posts mentioning Guerster resurrect ibm:
https://www.garlic.com/~lynn/2012g.html#82 How do you feel about the fact that today India has more IBM employees than US?
https://www.garlic.com/~lynn/2012g.html#87 Monopoly/ Cartons of Punch Cards
https://www.garlic.com/~lynn/2012h.html#54 How will mainframers retiring be different from Y2K?
https://www.garlic.com/~lynn/2012h.html#55 The Invention of Email
https://www.garlic.com/~lynn/2012k.html#70 END OF FILE
https://www.garlic.com/~lynn/2012l.html#20 X86 server
https://www.garlic.com/~lynn/2012l.html#63 Singer Cartons of Punch Cards

--
virtualization experience starting Jan1968, online at home since Mar1970

Blades versus z was Re: Turn Off Another Light - Univ. of Tennessee

Refed: **, - **, - **, - **
From: lynn@GARLIC.COM (Anne & Lynn Wheeler)
Subject: Re: Blades versus z was Re: Turn Off Another Light - Univ. of Tennessee
Newsgroups: bit.listserv.ibm-main
Date: 5 Sep 2012 06:16:58 -0700
re:
https://www.garlic.com/~lynn/2012l.html#56 Blades versus z was Re: Turn Off Another Light - Univ. of Tennessee
https://www.garlic.com/~lynn/2012l.html#57 Blades versus z was Re: Turn Off Another Light - Univ. of Tennessee
https://www.garlic.com/~lynn/2012l.html#59 Blades versus z was Re: Turn Off Another Light - Univ. of Tennessee

and at hotchips last week ... ibm decribes being able to plug two power7+ chips into a single socket ... there were references to software licensing gimicks (for licenses based on number of sockets)
http://www.theregister.co.uk/2012/08/31/ibm_power7_plus_processors/

from above:
Anyway, with a double-stuffed machine, you can in theory get 512 cores into a single system image, but it is not clear if AIX and Linux will be able to see more than 1,024 threads as they currently do; the IBM i operating system tops out at 128 threads in a single image at this point, with a special patch to boost it to 256 threads, and is woefully overdue for the same loving that AIX and Linux have gotten since 2010 to at least see 1,024 threads.

... snip ...

i.e. with four hyperthreads per core and 512 cores in a single multiprocessor would yield 2048 hyperthreads (aka the appearance of 2048 processors)

--
virtualization experience starting Jan1968, online at home since Mar1970

Strings (hijacked from: The IBM zEnterprise EC12 announcment)

Refed: **, - **, - **, - **
From: lynn@GARLIC.COM (Anne & Lynn Wheeler)
Subject: Re: Strings (hijacked from: The IBM zEnterprise EC12 announcment)
Newsgroups: bit.listserv.ibm-main
Date: 5 Sep 2012 08:10:22 -0700
PaulGBoulder@AIM.COM (Paul Gilmartin) writes:
You, Lynn, and John G. are correct to distrust null-terminated strings.

re:
https://www.garlic.com/~lynn/2012l.html#67 Strings (hijacked from: The IBM zEnterprise EC12 announcment)

in lots of discussions about C language string&buffer conventions being one the primary sources of programming errors ... there were analogous with careful drivers never having accidents and therefor there are no need for bumpers, safety glass, crash zones, seatbelts, padded dashboards, airbags, etc.

the more straight-forward analysis is that buffer length management is left to the programmer ... always having to manually manage whether the implicit length (of null terminated string) fits within target storage area. I've compared it to assembler language programming where a major manual effort on the programmer was managing register contents ... and mis-managed register contents has been major assembler programming error ... especially in complex programs with large number of code paths ... and at any particular point in execution ... did all possible execution paths correctly initialize registers.

It turns out that one of the benefits attributed for moving to C-programming ... is it allows system level programming while alleviating manual effort of the programmer managing the register contents. However, it has trade-off the elimination of the manual register content management effort with the buffer length manual management effort.

Long ago and far away (in the very earliest days of rexx before released to customers)... I wanted to demonstrate the power of REXX ... and selected IPCS ... which was a large, assembler implemented application. Objective was to completely re-implemented IPCS in REXX ... working half-time over 3month period ... with the new implementation having ten times the function and with ten times the performance (some coding slight of hand to make an application in REXX run ten times faster than corresponding application in assembler). I finished early ... so I started doing analysis of kinds of failures and their failure signatures ... developing an augmented library of IPCS procedures that could be automated to look for the various kinds of failure scenarios. Misc. past posts mentioning DUMPRX
https://www.garlic.com/~lynn/submain.html#dumprx

I had assumed that it would be released to customers as IPCS replacement ... which never happened for whatever reason ... although it eventually came to be used by all internal datacenters and nearly all customer support PSRs. I eventually managed to get approval for making presentation at user group meetings about how it was implemented ... and within a couple of months, similar implementations started to appear from other vendors.

Two of the most common (failure modes) were 1) anomolous code path failure to establish register contents (required at later point) and 2) dangling buffer pointers (aka asynchronous operation using pointer to storage area that was no longer active ... the particular storage area no longer active and/or re-allocated for some other purpose).

Most higher-level languages eliminate manual programmer effort in managing register contents. One of the characteristics claimed for languages like Java & LISP is having eliminated programmer manual managed storage ... not only doesn't have C-language buffer length like problems ... but also has eliminated dangling pointer problems.

--
virtualization experience starting Jan1968, online at home since Mar1970

zEC12, and previous generations, "why?" type question - GPU computing

Refed: **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **
From: lynn@GARLIC.COM (Anne & Lynn Wheeler)
Subject: Re: zEC12, and previous generations, "why?" type question - GPU computing.
Newsgroups: bit.listserv.ibm-main
Date: 5 Sep 2012 16:03:04 -0700
tony@HARMINC.NET (Tony Harminc) writes:
There *was* a single-chip 370 produced by someone in the late 70s - a "168i". I think it was a university or research institute, but not IBM. I'm not finding anything on Google with a casual search, but things like this are easily overwhelmed.

SLAC did 168E ... basically could run problem state fortran at 168 speed ... for data collection/reduction along the accelerator line ... long ways from single chip.

168 had been four circuits per chip, 3033 initially was 168 logic initially layed out on something like 40circuits per chip ... but just using 4 circuits in each chip ... getting 20% chip improvement. during development there was some rework of part of the 168 logic to make better use of higher chip density ... get 3033 up to 50% faster than 168.
http://www.jfsowa.com/computer/memo125.htm

i've frequently claimed that John Cocke's 801/risc was reaction to horrible complexity of (failed) FS effort ... initially simplified (aka reduced instruction set) for single chip implementation ... and then later simplified instructions that were all single machine cycle. misc. past posts mentioning future system
https://www.garlic.com/~lynn/submain.html#futuresys

360s, 370s, etc ... have been microcode implemented on variety of other kinds of engines. circa 1980 there was an effort to replace the wide variety of internet microprocessors used for controllers, low&mid range 370s, the planned as/400 replacement for s/38, etc ... all with 801/risc Iliad chips. For various reasons the efforts floundered and they went back to doing custom processor implementations.

It took another couple decades ... but lots of stuff is now risc in one way or another (as previously mentioned the past couple generations of i86 are risc processors with hardware layer translating i86 to risc micro-ops).

In the mid-80s, there was a 3-chip 370 that ran at 168 speed from Boeblingen called ROMAN. I had a project/proposal to pack arbitrary mix of large numbers of ROMAN and Iliad chips in the same rack ... with large number of racks (sort of precursor to latest rack announcement). a couple old email refs:
https://www.garlic.com/~lynn/2011b.html#email850314
https://www.garlic.com/~lynn/2007d.html#email850315

I had also been working with NSF on what was to become NSFNET backbone (i.e. tcp/ip is the technology basis for the modern internet, NSFNET backbone was the operational basis for the modern internet, and CIX was business basis for the modern internet). Above refs. that I had to find standin for me doing presentation to head of NSF ... because of rack cluster effort meeting. misc. past posts mentioning NSFNET
https://www.garlic.com/~lynn/subnetwork.html#nsfnet

Lots of low & mid-range clone 370 vendors were starting to spring up all over the place. Somebody in Nixdorf Germany had somehow acquired a proprietary ROMAN document ... and was trying to get it returned to IBM with all fingerprints removed. He sent it to somebody at Amdahl in silicon valley ... who arranged to hand it over to me.

Other trivia ... SLAC had hosted the monthly IBM user group meetings (BAYBUNCH) and was also the first webserver outside of europe.
http://www.slac.stanford.edu/history/earlyweb/history.shtml

and from long ago and far away ... mentions slac/cern 168E ... having become 3081E (3mips to 14mips).
Date: Fri, 7 Jul 89 10:52:39 CDT
From: wheeler
Subject: requirements task force

Note that both DEC and Apollo (along with hp) are heavily into distributed environment, heterogeneous network/system/enterprise management, and networks. Note that heterogenous means more than OSI, TCP/IP, UNIX, etc ... it means interoperability between all of them along with DECNET, VMS, XNS, etc.

Apollo's FDDI group is heavily involved in XTP and the former manager of the Apollo FDDI group (they've been active for some time and spending lot of time optimizing performance of high thruput adapters) left Apollo and formed synernetics (he was involved with XTP at Apollo and synernetics is a XTP/TAB member). They are working on initial cut of FDDI station management (SMT ... and have been out talking to a number of groups, including IBM ... I also believe he has even had contacts with <aaaaaa>).

Distributed 370s have a hard time keeping up. Way back in history (someplace), I spent a lot of time up at SLAC (there is tight coupling between SLAC and CERN). At that time SLAC was doing the 168E, a bit-slice processor that would run standard 370 Fortran programs. They technology has been improved and now CERN & SLAC are calling it a 3081E (i.e. the processing power of 3081). The design was to have one of these processors at each of the (large number of) data collection points.

Something that will be competing with this will be the 370 simulator that <xxxxxx> has done for the SUN4. He currently has VM/370 running at about 168 thruput on the old SUN4 (big register memory are super for large integrated applications but state switch overhead can be heavy/horrible ... something that we are currently grappling with ... some possibilities exist for pipelining/overlapping state switch like <yyyyyy> is doing with Vector Buffer architecture). I've known <xxxxxx> for a long time and he is experienced at what he does (he was lead development programming at Amdahl, then chief architect at 2pi, did DOS port for Olivetti, did 370 software ports/stuff for Nixdorf and most recently was contract to Boca West doing the OSI implementation for CPD). 168 thruput means he is effectively getting about 4:1 ratio of Sparc instructions to 370 instructions (implying that he could get 12.5 370 mips on the recently announced 50mip Sparc chip).


... snip ... top of post, old email index

--
virtualization experience starting Jan1968, online at home since Mar1970

PDP-10 system calls, was 1132 printer history

Refed: **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **
From: Anne & Lynn Wheeler <lynn@garlic.com>
Subject: Re: PDP-10 system calls, was 1132 printer history
Newsgroups: comp.lang.pl1, alt.folklore.computers
Date: Thu, 06 Sep 2012 11:01:17 -0400
glen herrmannsfeldt <gah@ugcs.caltech.edu> writes:
OK, I was stretching it a little. Some versions of S/360 were designed to test out different ideas. The 360/85 was the first with cache. IBM did much study on locality before doing it, but it still had to be actually built. (And them ended up almost as fast as the 360/91 for many programs.)

The 360/67 was the S/360 try at virtual storage, as I understand it more for timesharing than for larger addressing space for batch jobs. (Stanford ran ORVYL on their 360/67 using it.)

I agree it wasn't planned in advance as a test for S/370 paging, and in fact there were some changes in the paging hardware between the 67 and S/370. Even so, it did allow people (and IBM) to get to understand paging enough to add it to S/370.

Yes, the 155 and 165 didn't originally come with virtual addressing, and I don't remember by now exactly when they planned it as an add-on (and expensive) option.


370 batch larger address space ... was SVS (&VS1,DOS/VS) ... basically single virtual address space ... basically MVT laid out in single 16mbyte virtual address space (something analogous to what some univ. had done running MVT in 16mbyte virtual machine ... with some handshaking between VM and MVT). There was a little bit of hack on the side of MVT to setup the virtual tables and handle page fault. The major code hit was to i/o supervisor (aka EXCP processing).

MVT (os/360) convention were library code running as part of application built I/O channel programs. Pointer to the (user address space) channel programs were passed to the kernel/supervisor with an EXCP supervisor calle. Hardware executed the I/O channel programs with real addresses. In the move to SVS ... all the passed channel programs were built by the application using virtual addresses. Before the channel programs could be turned over to the hardware ... EXCP processing now had to convert all the virtual address to real addresses. The routine that performed this in CP67 (for virtual machine simulation) was CCWTRANS. Ludlow did early build of SVS running on 360/67 by hacking copy of cp67 ccwtrans into the MVT EXCP code. past post discussiong Ludlow doing the CP67 CCWTRANS hack for MVT and also discussing justifying virtual memory for all 370s:
https://www.garlic.com/~lynn/2011d.html#73 Multiple Virtual Memory

above references study that showed standard MVT application programs tended to only use 1/4th the memory in a partition ... resulting in "ability to run 16 initiators simulaneously on a 1 megabyte system". The issue was systems tended to be extremely I/O throughput limited ... processor idle while applications waited for I/O operations. To improve processor utilization (and usefulness) required being able to run multiple things simultaneously (having work waiting when something stalled waiting for i/o operations). As mentioned in the above, the cp67 experience had no input in the decision ... and tss/360 (the other system for 360/67) had little input ... it was more of a theoritical calculation.

In typical customer MVT environments, running 16 initiators simultaneously had potential of greatly increasing processor throughput ... w/o drastically increasing amount of real memory (real memory still a high-expense limited resource at the time). recent post in ibm-main drawing analogy with out-of-order execution and hyperthreading with MVT multitasking (for overlapped execution) ... i.e. cache misses and memory stall delays ... measured in number of processor cycles are comparable to 1960s 360 processors and disk i/o.
https://www.garlic.com/~lynn/2012l.html#29 X86 server
https://www.garlic.com/~lynn/2012l.html#59 Blades versus z

The tss/360 experience was more directly involved in the single-leve-store memory mapped design for the (failed) future system effort (that was going to completely 360/370 with something radically different). misc. past posts mentioning (failed) FS
https://www.garlic.com/~lynn/submain.html#futuresys

The 370 architecture book (called "red book" for its distribution in red 3-ring binder) specified the full 370 virtual memory architecture. The retrofit of adding virtual memory to 370/165 was major effort and the schedule was slipping. In order to make up time, there was decision to drop various pieces that 165 was having trouble with. That resulted in the other models going back on removing the dropped features ... as well as rewriting software that had already been developed using the dropped features ... including a major hit to vm370/cms.

As an aside, the "red book" was one of the early mainstream corporate documents moved to cp67/cms "script" (been ported from CTSS runoff) document formating. There were conditional variables and script command line option would select whether the principles of operation subset would be formated or the full "red book" would be formated. The "red book" contained unannounced hardware features, unannounced instructions, lots of engineering, implementation, and trade-off notes for various features (each instruction tended to have a lot of notes about why it was justified and engineering considerations on diferent models, etc).

recent virtual memory, paging, &/or single-level-store posts
https://www.garlic.com/~lynn/2012.html#7 Can any one tell about what is APL language
https://www.garlic.com/~lynn/2012.html#91 Has anyone successfully migrated off mainframes?
https://www.garlic.com/~lynn/2012c.html#16 5 Byte Device Addresses?
https://www.garlic.com/~lynn/2012c.html#23 M68k add to memory is not a mistake any more
https://www.garlic.com/~lynn/2012c.html#33 5 Byte Device Addresses?
https://www.garlic.com/~lynn/2012c.html#47 nested LRU schemes
https://www.garlic.com/~lynn/2012d.html#33 TINC?
https://www.garlic.com/~lynn/2012d.html#70 Mainframe System 370
https://www.garlic.com/~lynn/2012d.html#73 Execution Velocity
https://www.garlic.com/~lynn/2012e.html#103 Hard Disk Drive Construction
https://www.garlic.com/~lynn/2012e.html#106 Hard Disk Drive Construction
https://www.garlic.com/~lynn/2012f.html#10 Layer 8: NASA unplugs last mainframe
https://www.garlic.com/~lynn/2012f.html#11 Word Length
https://www.garlic.com/~lynn/2012f.html#29 which one came first
https://www.garlic.com/~lynn/2012f.html#60 Hard Disk Drive Construction
https://www.garlic.com/~lynn/2012g.html#24 Co-existance of z/OS and z/VM on same DASD farm
https://www.garlic.com/~lynn/2012i.html#55 Operating System, what is it?
https://www.garlic.com/~lynn/2012k.html#55 Simulated PDP-11 Blinkenlight front panel for SimH
https://www.garlic.com/~lynn/2012k.html#57 1132 printer history
https://www.garlic.com/~lynn/2012l.html#1 Time to choose the Knights of 2012
https://www.garlic.com/~lynn/2012l.html#26 PDP-10 system calls, was 1132 printer history
https://www.garlic.com/~lynn/2012l.html#37 S/360 architecture, was PDP-10 system calls
https://www.garlic.com/~lynn/2012l.html#38 S/360 architecture, was PDP-10 system calls

--
virtualization experience starting Jan1968, online at home since Mar1970

zEC12, and previous generations, "why?" type question - GPU computing

Refed: **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **
From: lynn@GARLIC.COM (Anne & Lynn Wheeler)
Subject: Re: zEC12, and previous generations, "why?" type question - GPU computing.
Newsgroups: bit.listserv.ibm-main
Date: 6 Sep 2012 09:07:25 -0700
gahenke@GMAIL.COM (George Henke) writes:
I believe IBM produced a pc with a 370 to run VM on a PC. Merrill Lynch had one. Somewhere in the late 80's I believe.

re:
https://www.garlic.com/~lynn/2012l.html#72 zEC12, and previous generations, "why?" type question - GPU computing

1984, xt/370 ... later same board was made available on at as at/370.

basically a couple M68k executing subset of vm370 ... code-named washington. it didn't support i/o ... so vm370 was modified to communicate with a monitor running under dos on the 8088 for all i/o functions. it provided approx. 100kip 370 with 384kbytes of memory ... little bit faster than 370/115. however, since all disk i/o (paging, cms file, etc) was being done on 100ms (per block) dos hard disk. By that time, vm370 and cms had gotten quite a bit bloated ... much larger than cp67/cms that would run on 256kbyte 360/67. Also any kind of disk i/o (paging, file activity) could become extremely painful ... compared to what one was use to with real mainframe disks.

I got con'ed into doing some work on it ... first thing simple paging tests showed almost any cms application would page thrash in the pageable pages available left over after vm370 kernel fixed storage size (from 384kbytes) ... exhaserbated by the paging on dos xt disk. I got blamed for several month schedule ship in the product while they upgraded the memory from 384kbytes to 512kbytes ... to cut down on severe paging problems. However, cms applications that tended to be much more file intensive than (and fared poorly in comparison with) equivalent applications developed for the DOS/XT resource limited environment.

I had tried to start a project to implement a super lean and fast vm370 replacement kernel in pascal. As a demo I had re-implemented the vm370 kernel spooling function in pascal running in virtual address space. My objective was to enormously increase the throughput and performance compared to the kernel assembler implemented equivalent.

I had another agenda ... I was also doing high-speed data transport project ... and for vm370 vnet ... which was dependent on vm370 spool ... I needed multi-megabyte sustained thruput to drive the links I had. misc. past posts mentioning hsdt
https://www.garlic.com/~lynn/subnetwork.html#hsdt

I indirectly referenced it in previous post regarding work with NSF on what was to become NSFNET backbone ... also original mainframe tcp/ip product was done for vm370 in pascal ... and I did the rfc1044 enhancements that got sustained channel thruput (between 4341 and cray machine using only modest amount of 4341 processor, about 500 times improvement in bytes moved per instruction executed). misc. past posts mentioning NSFNET backbone
https://www.garlic.com/~lynn/subnetwork.html#nsfnet

--
virtualization experience starting Jan1968, online at home since Mar1970

PDP-10 system calls, was 1132 printer history

Refed: **, - **, - **, - **, - **, - **, - **, - **, - **, - **
From: Anne & Lynn Wheeler <lynn@garlic.com>
Subject: Re: PDP-10 system calls, was 1132 printer history
Newsgroups: comp.lang.pl1, alt.folklore.computers
Date: Thu, 06 Sep 2012 12:42:11 -0400
glen herrmannsfeldt <gah@ugcs.caltech.edu> writes:
But a large address space doesn't help much if you don't have backing store for it. For the 360/67 that would have been 2314s at about 29MB or maybe 2301 drums.

The 2305, popular paging device for S/370, has a S/360 series 23xx number. Maybe they could also attach to the 360/67.

I suppose you could then argue that the 360/67 was practice for XA.


re:
https://www.garlic.com/~lynn/2012l.html#37 S/360 architecture, was PDP-10 system calls
https://www.garlic.com/~lynn/2012l.html#38 S/360 architecture, was PDP-10 system calls
https://www.garlic.com/~lynn/2012l.html#73 S/360 architecture, was PDP-10 system calls

tss/360 used (32-bit) large virtual address space for single-level-store ... i.e. files were memory-mapped into the virtual address space ... and file access basically performed as storage references.

370 didn't have virtual address space for file access ... and neither did xa.

there are also some real throughput gatchas about doing memory-mapped filesystem ... which contributed to tss/360 throughput issues. As undergraduate I did simulated user synthetic benchmarks (fortran compile, bind/link, execute) for cp67/cms on 768kbyte 360/67 for 30 users. The IBM/SE was doing a lot of work with tss/360 and did equivalent script. The tss/360 benchmark for 4 users had much worse response, throughput, etc ... than the equivalent script on cp67/cms with 30 users.

The failed Future System effort was adapting pretty much the same tss/360 single-level-store model and would have suffered similar extreme performance issues (but it had much more severe problems that it never even got that far). I was at the science center and figured I could do paged-mapped filesystem for CP67/CMS that avoided many of the pitfalls in the tss/360 implementation ... and contributed to my periodically ridiculing FS activities (and thinking what I already had running was significantly better than anything they planned). misc. past posts mentioning memory mapped operation:
https://www.garlic.com/~lynn/submain.html#mmap

much of move to 31-bit in XA was primarily an MVS problem ... unrelated to memory-mapping files. In initial move from MVT to SVS everything was in single virtual address space ... and os/360 over the years had extensively made use of pointer passing API paradigm. In the move from SVS to MVS ... each application got its own 16mbyte virtual address sapce ... but because of the pointer-passing API ... an 8mbyte image of the MVS kernel was included in every application virtual address space.

MVT&SVS had some number of "subsystems" (system function) that sat outside the kernel. In the move to MVS, these subsystems were given their own virtual address space. The problem was subsystems no longer had addressing to the pointer-passed parameters in the application address space. To address this the "COMMON SEGMENT" was created ... a part of every virtual address space ... for which dedicated storage could be obtain for passing parameters & data back&forth between applications and subsystems. This area started rapidly growing for large installations ... basically having to be proportional to combination of number of subsystems and number of concurrent applications. By the late 70s, many large installations had 4-5mbyte CSA (common segment renamed common system area) and were threatening to increase to 5-6mbytes ... i.e. large installations were under threat of the CSA increasing to 8mbytes ... so that the kernel was 8mbyte of every 16mbyte virtual address space and CSA was the other 8mbyte ... and there was nothing left to run applications.

There was internal MVS fanatic installation at the chip plant in Burlington that was being threatened with having to move to VM370. They had a large fortran chip design application that ran on a carefuly constructed MVS systems that had a one mbyte CSA ... just barefly fitting in the remaining 7mbytes. They were constantly have to do significantly design and programming just to maintain fitting in 7mbytes. They were offered vm370/cms that allowed nearly the whole 16mbytes ... beside thruput being slightly better ... even for computation intensive fortran application.

misc. recent references to common segment/CSA
https://www.garlic.com/~lynn/2012c.html#42 Where are all the old tech workers?
https://www.garlic.com/~lynn/2012e.html#80 Word Length
https://www.garlic.com/~lynn/2012i.html#53 Operating System, what is it?

--
virtualization experience starting Jan1968, online at home since Mar1970

PDP-10 system calls, was 1132 printer history

Refed: **, - **, - **, - **
From: Anne & Lynn Wheeler <lynn@garlic.com>
Subject: Re: PDP-10 system calls, was 1132 printer history
Newsgroups: comp.lang.pl1, alt.folklore.computers
Date: Thu, 06 Sep 2012 12:49:18 -0400
glen herrmannsfeldt <gah@ugcs.caltech.edu> writes:
Did the decision to do VS for S/370 come from the ability to do large address space batch processing? That is what it looks like. But also it made timesharing much easier.

re:
https://www.garlic.com/~lynn/2012l.html#37 S/360 architecture, was PDP-10 system calls
https://www.garlic.com/~lynn/2012l.html#38 S/360 architecture, was PDP-10 system calls
https://www.garlic.com/~lynn/2012l.html#73 S/360 architecture, was PDP-10 system calls
https://www.garlic.com/~lynn/2012l.html#75 S/360 architecture, was PDP-10 system calls

see email (extracts) in this previously mentioned post
https://www.garlic.com/~lynn/2011d.html#73 Multiple Virtual Memory

it is description from somebody was there with the executive that made the virtual memory decision for 370. The original question had originated from Shmuel.

--
virtualization experience starting Jan1968, online at home since Mar1970

zEC12, and previous generations, "why?" type question - GPU computing

Refed: **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **
From: lynn@GARLIC.COM (Anne & Lynn Wheeler)
Subject: Re: zEC12, and previous generations, "why?" type question - GPU computing.
Newsgroups: bit.listserv.ibm-main
Date: 6 Sep 2012 10:17:26 -0700
XT/370 and AT/370 used a 68000 with custom microcode and a second 68000 with standard microcode. The software for it was VM/PC. Note that the later P/370 and R/370 cards implemented the full architecture and ran stock operating systems.

re:
https://www.garlic.com/~lynn/2012l.html#72 zEC12, and previous generations, "why?" type question - GPU computing
https://www.garlic.com/~lynn/2012l.html#74 zEC12, and previous generations, "why?" type question - GPU computing

between xt/at/370 and p370/p390 was a74 (7437) done in POK by the same group that had done the 3277GA (i.e. large tektronics graphics tube that plugged into side of 3277 terminal) ... "a74" was their POK dept.

I got con'ed into making the vm370 modifications for them ... including a74 only supported 4k storage key. this is long-winded post ... with bunch of old a74 press at the bottom
https://www.garlic.com/~lynn/2002d.html#4 IBM Mainframe at home
post with some of the discussion of the vm370 changes I did for a74
https://www.garlic.com/~lynn/2003f.html#56 ECPS:VM DISPx instructions

old internal A74 email on the announcement of a74
https://www.garlic.com/~lynn/2000e.html#email880622
in this post
https://www.garlic.com/~lynn/2000e.html#56 Why not an IBM zSeries workstation?

a74 was 350kips (370, compared to 100kips for xt/at/370)

and the ROMAN chip set was 168/3mips ... mentioned in previous post.

--
virtualization experience starting Jan1968, online at home since Mar1970

PDP-10 system calls, was 1132 printer history

Refed: **, - **, - **, - **
From: Anne & Lynn Wheeler <lynn@garlic.com>
Subject: Re: PDP-10 system calls, was 1132 printer history
Newsgroups: comp.lang.pl1, alt.folklore.computers
Date: Thu, 06 Sep 2012 13:04:32 -0400
glen herrmannsfeldt <gah@ugcs.caltech.edu> writes:
I know it is two sets of microcode for the P/370.

It seems that the 3081 and 4381 also have the ability to run as either S/370 or XA/370.

"The Models D, G and K offer the option of operating with either System/370 architecture or the new System/370 Extended Architecture."

The description makes it sound like you get one or the other, but doesn't say how you switch.

http://www-03.ibm.com/ibm/history/exhibits/mainframe/mainframe_PP3081.html

http://www-03.ibm.com/ibm/history/exhibits/mainframe/mainframe_PP4381.html


re:
https://www.garlic.com/~lynn/2012l.html#23 PDP-10 system calls, was 1132 printer history
https://www.garlic.com/~lynn/2012l.html#26 PDP-10 system calls, was 1132 printer history
https://www.garlic.com/~lynn/2012l.html#27 PDP-10 system calls, was 1132 printer history
https://www.garlic.com/~lynn/2012l.html#35 PDP-10 system calls, was 1132 printer history
https://www.garlic.com/~lynn/2012l.html#36 PDP-10 system calls, was 1132 printer history
https://www.garlic.com/~lynn/2012l.html#40 PDP-10 system calls, was 1132 printer history
https://www.garlic.com/~lynn/2012l.html#73 PDP-10 system calls, was 1132 printer history
https://www.garlic.com/~lynn/2012l.html#75 PDP-10 system calls, was 1132 printer history
https://www.garlic.com/~lynn/2012l.html#76 PDP-10 system calls, was 1132 printer history

the 4300s saw huge uptake with large corporate orders (hundreds at a time) ... being placed out in departmental areas ... sort of the leading edge of the distributed computing tsunami. MVS lost out on this for a long list of reasons ... including requiring significant support staff for each MVS system. The other part was very low environmental footprint ... which included FBA disks. MVS only supported CKD (and still doesn't even after it has been decades since they stopped making real CKD disks) ... and the only (new) CKD was 3380 ... which had a high environmental footprint. The only mid-range disk was 3370 ... which was FBA only.

Since the 3033, MVS also had a set of pecular microcode enhancements (even before xa) which weren't available on 4300s. A large corporate customer did come in and say he would order 800 4341s if it ran MVS. As a result, some really ugly, gorping MVS specific microcode had to be retrofitted to 4341 ... and there was 3375 disk ... which was CKD simulation on 3370 FBA (it didn't address the enormous support staffing required to support MVS).

The follow-on to 4331/4341 were the 4361/4381 ... but as I've mentioned they never saw the huge explosive growth of the 4331/4341 ... the distributed computing market was starting its move workstations and large PCs.

--
virtualization experience starting Jan1968, online at home since Mar1970

zEC12, and previous generations, "why?" type question - GPU computing

Refed: **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **
From: lynn@GARLIC.COM (Anne & Lynn Wheeler)
Subject: Re: zEC12, and previous generations, "why?" type question - GPU computing.
Newsgroups: bit.listserv.ibm-main
Date: 6 Sep 2012 10:43:51 -0700
sipples@SG.IBM.COM (Timothy Sipples1) writes:
Keep in mind that for 1975 this was absolutely amazing technology, but amazing technology required some expense. Being early is pricey. If the 5100 debuted in, say, 1977 or 1978, it would have still been well timed but could have dramatically reduced the chip and board count. I also think the small built-in monitor could have been sacrified (at least as an option) in favor of a display port of some kind -- ideally RF for TV hookup. And IBM might have gone with a diskette drive for storage -- the 5100 was too early for the 5.25 inch drive, which debuted in 1976. Finally, if IBM had provided a little more guidance on the 370 subset instruction set they implemented, software developers could have taken over from there.

So I think the 5100 could have been a nice 5110 by tweaking the recipe a bit. But history didn't happen that way.


re:
https://www.garlic.com/~lynn/2012l.html#72 zEC12, and previous generations, "why?" type question - GPU computing
https://www.garlic.com/~lynn/2012l.html#74 zEC12, and previous generations, "why?" type question - GPU computing
https://www.garlic.com/~lynn/2012l.html#77 zEC12, and previous generations, "why?" type question - GPU

put all logic in microcode
https://en.wikipedia.org/wiki/IBM_PALM_processor

5100 had enuf 360 microcode emulation to run apl/360
https://en.wikipedia.org/wiki/IBM_5100

from above:
The 5100 was based on IBM's innovative concept that, using an emulator written in microcode, a small and relatively cheap computer could run programs already written for much larger, and much more expensive, existing computers, without the time and expense of writing and debugging new programs.

Two such programs were included: a slightly modified version of APL.SV, IBM's APL interpreter for its System/370 mainframes, and the BASIC interpreter used on IBM's System/3 minicomputer. Consequently, the 5100's microcode was written to emulate most of the functionality of both a System/370 and a System/3.

IBM later used the same approach for its 1983 introduction of the XT/370 model of the IBM PC, which was a standard IBM PC XT with the addition of a System/370 emulator card.


... snip ...

part of the issue was apl code was fairly dense ... and apl\360 workspaces were typically 16kbytes (some systems offered 32kbytes).

cambridge science center had taken apl\360 ... stripped out all the multitasking and swapping stuff and got it to run under cms workspace as large as virtual memory ... for cp67 cms\apl. some amount of work had to be done on how apl\360 storage since it tended to use all available workspace ... which resulted in page thrashing in virtual memory environment. there was also an cms\apl API to access system services (including file i/o). The combination of large workspace and file i/o allowed doing a lot of real-world applications (that couldn't be done with apl\360). The business planners in Armonk loaded the holiest of holy data (detailed customer profiles) on the cambridge system for business modeling in cms\apl. This also created something of security issue since cambridge also allowed non-employee access from various institutions in the cambridge area (students, staff, faculty).

palo alto science center then did the enhancements to make vm370 apl\cms ... they also did the 370/145 apl microcode assist and the 5100.

the person that did 370/145 apl microcode assist was also instrumental in many of the fortan hx performance enhancmenets.

--
virtualization experience starting Jan1968, online at home since Mar1970

PDP-10 system calls, was 1132 printer history

From: Anne & Lynn Wheeler <lynn@garlic.com>
Subject: Re: PDP-10 system calls, was 1132 printer history
Newsgroups: comp.lang.pl1, alt.folklore.computers
Date: Thu, 06 Sep 2012 13:54:17 -0400
hancock4 writes:
My old employer with the S/360-40 replaced it with a 43xx and DOS/ VSE. I think they used ADR's VOLLIE as an on-line editor. Perhaps around 1980?

announce 30Jan1979
https://web.archive.org/web/20190105032753/https://www.ibm.com/ibm/history/exhibits/mainframe/mainframe_PP4341.html

old 43xx email
https://www.garlic.com/~lynn/lhwemail.html#43xx

comment about the distributed computing tsunami
https://www.garlic.com/~lynn/2001m.html#15 departmental servers
with old email about 20 4341s for AFDS turning into 210
https://www.garlic.com/~lynn/2001m.html#email790404b

also doing benchmarks on engineering 4341 (before product release) originally for national lab looking for 70 4341s
https://www.garlic.com/~lynn/2002i.html#19 CDC6600 - just how powerful a machine was it?

past posts in this thread:
https://www.garlic.com/~lynn/2012l.html#23 PDP-10 system calls, was 1132 printer history
https://www.garlic.com/~lynn/2012l.html#26 PDP-10 system calls, was 1132 printer history
https://www.garlic.com/~lynn/2012l.html#27 PDP-10 system calls, was 1132 printer history
https://www.garlic.com/~lynn/2012l.html#35 PDP-10 system calls, was 1132 printer history
https://www.garlic.com/~lynn/2012l.html#36 PDP-10 system calls, was 1132 printer history
https://www.garlic.com/~lynn/2012l.html#40 PDP-10 system calls, was 1132 printer history
https://www.garlic.com/~lynn/2012l.html#73 PDP-10 system calls, was 1132 printer history
https://www.garlic.com/~lynn/2012l.html#75 PDP-10 system calls, was 1132 printer history
https://www.garlic.com/~lynn/2012l.html#76 PDP-10 system calls, was 1132 printer history
https://www.garlic.com/~lynn/2012l.html#78 PDP-10 system calls, was 1132 printer history

--
virtualization experience starting Jan1968, online at home since Mar1970

Blades versus z was Re: Turn Off Another Light - Univ. of Tennessee

Refed: **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **
From: lynn@GARLIC.COM (Anne & Lynn Wheeler)
Subject: Re: Blades versus z was Re: Turn Off Another Light - Univ. of Tennessee
Newsgroups: bit.listserv.ibm-main
Date: 6 Sep 2012 16:03:43 -0700
R.Skorupka@BREMULTIBANK.COM.PL (R.S.) writes:
WRONG! I meant it's hard to justfiy the choice: to buy IFL (plus rest of mainframe) or x64 servers. I meant Linux on IFL is *much* more expensive than on x64 servers. Things like power, cooling, floor space, staffing won't change it, but the software licenses could do it. BTW: I did not mention RAS, but not everyone will pay for good RollRoyce, some of us choose Toyota.

re:
https://www.garlic.com/~lynn/2012l.html#56 Blades versus z was Re: Turn Off Another Light - Univ. of Tennessee
https://www.garlic.com/~lynn/2012l.html#57 Blades versus z was Re: Turn Off Another Light - Univ. of Tennessee
https://www.garlic.com/~lynn/2012l.html#59 Blades versus z was Re: Turn Off Another Light - Univ. of Tennessee
https://www.garlic.com/~lynn/2012l.html#70 Blades versus z was Re: Turn Off Another Light - Univ. of Tennessee

z196 with 80 processors is rated at 50BIPS (besides increase from 64 to 80 processors over z10 at 30BIPS ... was the introduction of out-of-order execution ... something that had been used in risc for decades ... and the more recent I86 ... especially after they moved to risc cores with hardware layer that translated i86 to risc micro-ops for execution).

At $28M ... z196 at 50BIPS is 625MIPS/processor, $560,000/BIPS and $350,000/processor. z196 80 processor is also 31.7kW ... or 634watts/BIPS. So far ec12 is 101 processors and 1.5times processing of z196 (say 75BIPS) with 26% increase in number of processors. ec12 processors are running 6percent faster than z196 processors ... so much of the rest of the performance improvement may be the statements about improvements to out-of-order execution ... guestimate 75BIPS/101 ... aka 743MIPS/processor (compared to 625MIPS/processor for z196)

Analysis from last week is that IBM earns roughly $5.25M in mainframe services, software, and storage for every million in mainframe processor ... so a $28M z196 would represent total of $175M.

IBM has base list price of $1815 for e5-2600 blade. High-end e5-2600 is benchmarked at 527BIPS for two chip, 8processors/chip, 16 processors. (aka single e5-2600 has the processor power equivalent of more than ten max. configured 80processor z196), 33BIPS/processor, $3.44/BIPS, and $113/processor (compared to 625MIPS, $560,000, and $350,000 respectively for z196 ... based on $28M ... not fully loaded $175M ... aka factor 6.25 times).

Assumption that disk technology is effectively the same ... except for any additional overhead of CKD layer simulation on regular disks for mainframe (aka CKD disks haven't been manufactured for decades, being simulated on top of industry standard disks).

Motherhood that e5-2600 is 50% more energy efficient than previous generation (and "no-brainer when you can replace roughtly 20 old servers with one new E5 2600")
http://www.techspot.com/news/48000-xeon-e5-2600-interview-with-intel-its-ajay-chandramouly.html

Power consumption and efficiency (e5-2600 at 421watts):
http://www.tomshardware.com/reviews/xeon-e5-2687w-benchmark-review,3149-11.html

works out to around .8watts/BIPS (compared to 634watts/BIPS for z196).

anybody seen published z196 dhrystone and whestone benchmarks comparable to these:
http://www.istorya.net/forums/computer-hardware-21/485176-intel-xeon-e5-2690-and-e5-2660-8-core-sandy-bridge-ep-review.html

this mentions kilowatt for ("overclocked" 3.5ghz) e5-4600 (four sockets, 32 processors compared to two sockets, 16 processor for e5-2600)
http://www.istorya.net/forums/computer-hardware/459258-turbo-overclocking-high-tdp-cpus-8-core-intel-sandy-bridge-ep-example.html

and
http://www.istorya.net/forums/computer-hardware/518021-intel-announces-xeon-phi-co-processors.html

from above:
The Intel Xeon processor E5-2600 product family reached a new supercomputing milestone as the fastest adopted new processing technology to power 44 systems, including 3 Petascale-class supercomputers on the 39th edition of the Top500 list announced today.

... snip ...

--
virtualization experience starting Jan1968, online at home since Mar1970

zEC12, and previous generations, "why?" type question - GPU computing

Refed: **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **
From: lynn@GARLIC.COM (Anne & Lynn Wheeler)
Subject: Re: zEC12, and previous generations, "why?" type question - GPU computing.
Newsgroups: bit.listserv.ibm-main
Date: 6 Sep 2012 18:43:36 -0700
wdonzelli@GMAIL.COM (William Donzelli) writes:
Was this effort in some way related, or in competition with, the UC series of controllers? Quite a lot of machines used those internally, and they even popped out with the 8100 series (the mainframes that have fallen into the memory hole).

re:
https://www.garlic.com/~lynn/2012l.html#72 zEC12, and previous generations, "why?" type question - GPU computing
https://www.garlic.com/~lynn/2012l.html#74 zEC12, and previous generations, "why?" type question - GPU computing
https://www.garlic.com/~lynn/2012l.html#77 zEC12, and previous generations, "why?" type question - GPU computing
https://www.garlic.com/~lynn/2012l.html#79 zEC12, and previous generations, "why?" type question - GPU computing

uc controllers were much simpler, earlier (and underpowered) processors, 3705, 8100, service processor for 3081, etc. early on before 3705 was announced there was a strong effort at the science center to get cpd to use peachtree for 3705 (instead of uc) ... peachtree was much more powerful processor and was used in series/1.

UCs would have been part of the internal microprocessors replaced by 801, the 801 replacement effort was circa 1980 ... but for various reasons the efforts floundered (the as/400 quickly did a cisc chip to replace the planned 801 ... but in the 90s eventually migrated to 801/risc power/pc). The follow-on to 4331/4341 (aka 4361/4381) were suppose to be iliad (801/risc) ... but there was a white paper (that I contributed to) that shot down that effort (even tho I was working on 801/risc for other things). In the wake of the failure of those efforts in the earlier 80s, some number of 801/risc chip engineers left and showup working on risc efforts at other vendors (I've posted various old email from people worried that I might be following in their footsteps).

Bob Evans had asked my wife to audit 8100 and shortly later it was effectively canceled (although continued to linger on for quite some time) ... has some amount about UC also:
https://en.wikipedia.org/wiki/IBM_8100

old email referencing mit lisp machine group asking ibm for 801 processor ... and Bob Evans offering 8100 instead:
https://www.garlic.com/~lynn/2006o.html#email790711

later one of the baby bells did a NCP & VTAM (both) emulation on series/1 ... and outboard of mainframe ... carried sna traffic over real networking infrastructure (mainframe vtams were told all resources were cross-domain ... which was actually simulated outboard in redundant infrastructure). I did a deal with the baby bell to turn it out as an IBM product ... as well as concurrently porting from series/1 to rios (801/risc processor used in rs/6000). Because I knew that communication group would be out for my head ... I cut a deal with another baby bell to underwrite all of my development costs ... with no strings attached (their business case was that they would totally recover all my costs within the first year just replacing 37x5/NCP with new product). The internal politics that then happened could only be described as truth is stranger than fiction.

part of presentation that I did at sna architecture review board meeting in raleigh, fall of 1986:
https://www.garlic.com/~lynn/99.html#67 System/1 ?
part of presentation by baby bell at series/1 common meeting
https://www.garlic.com/~lynn/99.html#70 Series/1 as NCP

past posts mentioning 801/risc, iliad, romp, rios, fort knox, power, power/pc, etc
https://www.garlic.com/~lynn/subtopic.html#801

In the previous reference about using large number of 370 3mip roman (three) chip sets in racks ... the 801 chip was blue iliad ... which was first 32bit 801 chip ... and design for 20mips ... although it was never put into production (and it was a very large "hot" chip). Biggest design problem & bottleneck was increasing problem with getting all the heat out of the rack as ever increasing numbers of chips were packed into the rack. old post
https://www.garlic.com/~lynn/2004m.html#17 mainframe and microprocessors

mentioning series of documents that I did on the roman/iliad rack cluster design
RMN.DD.001, Jan 22, 1985
RMN.DD.002, Mar 5, 1985
RMN.DD.003, Mar 8, 1985
RMN.DD.004, Apr 16, 1985

old email discussing 801, risc, romp, rios
https://www.garlic.com/~lynn/lhwemail.html#801

there was huge amount of communication group FUD about my 3725 numbers used in comparison/presentation ... which I pulled directly from HONE 3725 "configurator" ... HONE configurations (world-wide virtual machine based online sales&marketing) were used by IBM sales&marketing for configuring hardware. In the case of 3725 configurator ... performance modeling had official communication group sanction. misc. past posts mentioning HONE
https://www.garlic.com/~lynn/subtopic.html#hone

one of my hobbies was enhanced production operating systems for internal datacenters ... HONE was (also) one of my long time customers since cp67/cms days in the early 70s. that hone was actually virtual machine based was obfuscated from most field people. There would periodically be branch manager promoted into hdqtr executive position ... that included HONE ... and would be horrified to find out that it was all virtual machine based and not MVS. They would figure that they could make their career & repudiation in the company by migrating HONE to MVS. All the resources of HONE would be dedicated for several months on a MVS migration until it was evident that it wouldn't work. Things would be quietly covered up until the next branch manager promoted into the executive position (and an attempt at another disasterous port was made). Finally they took to threatening HONE with they had to stop using my enhanced operating systems ... because what would happen if I was hit by a bus.

--
virtualization experience starting Jan1968, online at home since Mar1970

IBM's z12 mainframe engine makes each clock count

From: lynn@GARLIC.COM (Anne & Lynn Wheeler)
Subject: Re: IBM's z12 mainframe engine makes each clock count
Newsgroups: bit.listserv.ibm-main
Date: 6 Sep 2012 21:45:37 -0700
edgould1948@COMCAST.NET (Ed Gould) writes:

http://www.theregister.co.uk/2012/09/05/ibm_z12_mainframe_engine/


z12 is aggregate 75BIPS (for 101 processors, 50% more than 80processor z196 at 50BIPS). A z12 processor is 25% more powerful (than z196 engine) at 1,600MIPS (1.6BIPS).

75BIPS/101processors is 743MIPS/processor (less than half of the 1,600MIPS/processor mentioned in article) ... compared to 50BIPS/80processors or 625MIPS/processor for z196

cross-over from recent threads:
https://www.garlic.com/~lynn/2012l.html#34 X86 server
https://www.garlic.com/~lynn/2012l.html#42 I.B.M. Mainframe Evolves to Serve the Digital World
https://www.garlic.com/~lynn/2012l.html#51 Turn Off Another Light - Univ. of Tennessee
https://www.garlic.com/~lynn/2012l.html#81 Blades versus z was Re: Turn Off Another Light - Univ. of Tennessee

--
virtualization experience starting Jan1968, online at home since Mar1970

72 column cards

Refed: **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **
From: Anne & Lynn Wheeler <lynn@garlic.com>
Subject: 72 column cards
Newsgroups: alt.folklore.computers
Date: Fri, 07 Sep 2012 09:06:29 -0400
recent thread in another fora about ancient times was discussion why ibm 36bit computers with column binary was 72 columns ... that 72 columns was plug-board limit ... which was almost always the first 72 ... leaving the last 8 for sequence numbers for when you dropped the deck.

related discussion here:
http://cap-lore.com/Hardware/701-IO.html

may also influenced teletype & 72-character line lengths.

the leveraging of tab equipment then contributed to this about 360 turning out to be ebcdic rather than ascii (learson made the biggest computer goof ever):
https://web.archive.org/web/20180513184025/http://www.bobbemer.com/P-BIT.HTM

--
virtualization experience starting Jan1968, online at home since Mar1970

Singer Cartons of Punch Cards

Refed: **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **
From: Anne & Lynn Wheeler <lynn@garlic.com>
Subject: Re: Singer Cartons of Punch Cards
Newsgroups: alt.folklore.computers
Date: Fri, 07 Sep 2012 11:04:23 -0400
jmfbahciv <See.above@aol.com> writes:
The how did we get stuck with Obamacare? How did the banks and auto makers get trillions of dollars with not many strings attached? How did a close to a trillion get disbursed for "so-called" infrastructure improvements?

30yr senior republican congressional staffer:

The Party Is Over: How Republicans Went Crazy, Democrats Became Useless, and the Middle Class Got Shafted
https://www.amazon.com/The-Party-Over-Republicans-ebook/dp/B007V65OLG

which is pretty much the same as this from senior democratic congressional staffer:

The Payoff: Why Wall Street Always Wins
https://www.amazon.com/Payoff-Wall-Street-Always-ebook/dp/B008Y4TY92

it had started earlier in 2002 when congress let the fiscal responsibility act expire (spending had to be matched by tax revenue). CBO had report that last decade, tax revenue was reduced by $6T and spending increased by $6T for $12T budget gap (compared to baseline which had all federal debt retired by 2010). in the middle of last decade, congressional budget craziness was so bad that comptroller general would make references in speeches that nobody in congress was capable of middle school arithmetic. the tax cuts and large increase in size of gov. last decade have a momentum that carries forward ... like getting oil super-tanker to change direction.

dwarfing health care act (which CBO has overall positive effect) was medicare part-d ... first major legislation after fiscal responsibility act was allowed to expire. comptroller general characterizes it as long-term $40T unfunded mandate that comes to dwarf all other items. cbs 60mins did expose ... characterizing as trillions of dollars gift to the drug industry. 18 staffers and members of congress (from party in power) were responsible for shepherding bill thru ... at last minute they insert sentence prohibiting competitive bidding and prevent CBO from distributed report as to the effect of that sentence, until after the vote. After the legislation passes, all 18 resign and are on drug industry payrolls. 60mins shows table of identical drugs from Veterns administration (which has competitive bidding) and medicare part-d ... with the drugs under part-d three times the price of the same drugs from VA.

there have been recent news items on both "how 'clinton' balanced budget was bad for the country" and "how drug competitive bidding is bad for the country". somewhat brings to mind all the fraudulent news reports and testimony before congress (paid for by the tobacco industry) about how smoking cigarettes wasn't bad for the country. this morning there was item on science article recently picked up by several news operations about how there was no statistical difference between organic and non-organic food. the item this morning is that the author of the science article is funded by the large agricultural corporations and that the author was also one of the tobacco industry paid experts testifying before congress about how there was no statiscal evidence that smoking cigarettes was bad for people.

this has the problems much more systemic and long-term (reference ny times article from last sept.).

Key Facts About the US Economic Policies of the Last Thirty-Two Years
http://johnhively.wordpress.com/2012/08/31/3107/

why the us middle class is broken
http://globalguerrillas.typepad.com/globalguerrillas/2011/10/journal-why-the-us-middle-class-is-broken.html

using these graphics
http://www.nytimes.com/imagepages/2011/09/04/opinion/04reich-graphic.html
from this article
http://www.nytimes.com/2011/09/04/opinion/sunday/jobs-will-follow-a-strengthening-of-the-middle-class.html

also somewhat from banksters side:

Big Banks Are Hazardous to U.S. Financial Health
http://www.bloomberg.com/news/2012-09-02/big-banks-are-hazardous-to-u-s-financial-health.html

from above:

In 1995, the Big Six -- JPMorgan, Bank of America Corp., Citigroup Inc., Wells Fargo & Co., Goldman Sachs Group Inc. and Morgan Stanley -- had assets worth only 17 percent of U.S. gross domestic product. As recently as 2005, their collective balance sheets were valued at less than 50 percent of GDP.

Today, the Big Six are much bigger, with combined assets of 60 percent of GDP.

... snip ...

... however there was article yesterday that just the big five (w/o morgan stanley) are 56% of GDP.

as referenced earlier in this post
https://www.garlic.com/~lynn/2012l.html#60 Singer Cartons of Punch Cards

past relatively modest-size there is to benefit to the economy, society, and/or country of larger sized institutions ... and the TBTF were large part responsible for the economic mess of the last decade (not only taking down the economy, nearly taking down the country and the world) and continue to represent enormous systemic risk.

other recent posts in thread:
https://www.garlic.com/~lynn/2012l.html#54 Singer Cartons of Punch Cards
https://www.garlic.com/~lynn/2012l.html#58 Singer Cartons of Punch Cards
https://www.garlic.com/~lynn/2012l.html#60 Singer Cartons of Punch Cards
https://www.garlic.com/~lynn/2012l.html#61 Singer Cartons of Punch Cards
https://www.garlic.com/~lynn/2012l.html#62 Singer Cartons of Punch Cards
https://www.garlic.com/~lynn/2012l.html#63 Singer Cartons of Punch Cards
https://www.garlic.com/~lynn/2012l.html#64 Singer Cartons of Punch Cards
https://www.garlic.com/~lynn/2012l.html#65 Singer Cartons of Punch Cards
https://www.garlic.com/~lynn/2012l.html#66 Singer Cartons of Punch Cards
https://www.garlic.com/~lynn/2012l.html#68 Singer Cartons of Punch Cards

--
virtualization experience starting Jan1968, online at home since Mar1970

Etymology of APAR

From: lynn@GARLIC.COM (Anne & Lynn Wheeler)
Subject: Re: Etymology of APAR
Newsgroups: bit.listserv.ibm-main
Date: 7 Sep 2012 08:18:29 -0700
jwglists@GMAIL.COM (John Gilmore) writes:
Did the phrase come first, followed by its acronym? Or did the acronym come first, followed by the construction of a more or, often, very much less felicitous phrase to serve as its imputed its origin?

aka some claims that spool comes from spool/reel of tape which came from spools in looms ... which then generates phrase (unit-record front-end done by manually moving tapes between the backend processor and the front-end handling unit record).

from science center ... GML were the initials of the three people that invented GML at the science center in 1969 ... then needed to come up with the phrase generalized markup language.

also from science center ... charlie invented compare&swap while working on fine grain locking on cp67 multiprocessor. CAS are his initials which then resultetd in compare&swap. initial attempt to get compare&swap added to 370 was rebuffed, the 370 architecture owners saying that the POK favorite son operating system people claimed that (360) test&set was sufficient. the challenge from the 370 architecture owners was to come up with a non-multiprocessor specific use for compare&swap. thus was born the examples (that still appear in principles of operation) for using compare&swap in multithreaded/multiprogramming applications (independent of whether running on single processor or multiple processors). compare&swap was so useful that in the 80s it shows up on many other processor architecture and used by just about all large, high-thruput, DBMS implementations.

--
virtualization experience starting Jan1968, online at home since Mar1970

Blades versus z was Re: Turn Off Another Light - Univ. of Tennessee

Refed: **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **
From: lynn@GARLIC.COM (Anne & Lynn Wheeler)
Subject: Re: Blades versus z was Re: Turn Off Another Light - Univ. of Tennessee
Newsgroups: bit.listserv.ibm-main
Date: 7 Sep 2012 09:27:12 -0700
R.Skorupka@BREMULTIBANK.COM.PL (R.S.) writes:
1. 300? Only 300? Why not 30000? I can buy good memory for 6,6 $ per GB, IBM wanted recently 8k$ per GB. 1000+ times more. Now it's cheaper - "only" 1500 $/GB. I can also buy CPU for 150$, while IFL costs approx 150 k$.

re:
https://www.garlic.com/~lynn/2012l.html#81 Blades versus z was Re: Turn Off Another Light - Univ. of Tennessee

note part of the enormous growth in servers was that they were viewed as nearly zero cost item ... so people costs to manage multiple applications was greater than just having server per application. some operations then found that they might have grown to hundreds of thousands of servers ... and that the provisioning became a single large budget item (but still less than traditional people costs of manage multiple applications per server). Note that this is different than the cloud mega-datacenters with hundreds of thousands of servers ... which developed their own RAS, management & adminstsrative strategy ... and actual have processor use that justifies the hundreds of thousands of servers (and millions of processors).

vmware (and others) move into the market using virtual machines to drastically reduce the cost of managing multiple applications per server ... they were claiming 10:1 server consolidation for the previous generation over the generation before that.

newest e5-2600 with 527BIPS, 315GBLOPS, 421watts, and claiming 20:1 server consolidation over the previous generation ... at IBM base list price of $1815 for e5-2600 blade.

this is compared to 80 processor z196 with 50BIPS, ??GFLOPS, 31.7Kw at $28M (and IBM claiming it effectively earns roughly $5.25M in mainframe services, software, and storage for every $1M in mainframe sold) ... bringing 80 processor z196 to $175M

--
virtualization experience starting Jan1968, online at home since Mar1970

Blades versus z was Re: Turn Off Another Light - Univ. of Tennessee

Refed: **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **
From: lynn@GARLIC.COM (Anne & Lynn Wheeler)
Subject: Re: Blades versus z was Re: Turn Off Another Light - Univ. of Tennessee
Newsgroups: bit.listserv.ibm-main
Date: 7 Sep 2012 19:27:17 -0700
re:
https://www.garlic.com/~lynn/2012l.html#81 Blades versus z was Re: Turn Off Another Light - Univ. of Tennessee
https://www.garlic.com/~lynn/2012l.html#87 Blades versus z was Re: Turn Off Another Light - Univ. of Tennessee

BladeCenter blade servers
http://www-03.ibm.com/systems/bladecenter/hardware/servers/

at the current moment, following appears to incorrectly copy the description of HS23E for e5-2400 which is single chip-socket ... the HS23 is e5-2600 with dual chip-socket with 8processor per chip, for 16processors and 32 hyperthreads.

IBM BladeCenter HS23
http://www-03.ibm.com/systems/bladecenter/hardware/servers/hs23/index.html

this does better at describing HS23 with two sockets.

IBM BladeCenter HS23
http://www.research.ibm.com/about/top_innovations_history.shtml

BC-H 14 bay chassis allows 14 HS23 @$1815 is $25,410 (plus cost of the chassis) and at 527BIPS would be aggregate of 7.4TIPS (the equivalent of 147 50MIP 80-processor z196 and @$28M would be $4B).

BladeCenter H Chassis
http://www-03.ibm.com/systems/bladecenter/hardware/chassis/bladeh/

BladeCenter H (8852)
http://www-03.ibm.com/systems/xbc/cog/bc_h_8852/bc_h_8852aag.html

bladecenter H chassis is 9U ... for standard 42U rack,
https://en.wikipedia.org/wiki/19-inch_rack

that could allow four bladecenter h chassis (36U) per 42U rack or 56 HS23 blades, @$1815 is $101,640 (plus cost of rack and four bladecenter H chassis) and at 527BIPS would be aggregate of 30TIPS (or equivalent of 590 50MIP 80-processor z196 and @$28M would be $16.5B, IBM uplift for mainframe for services, software, and storage would be over $100B ).

--
virtualization experience starting Jan1968, online at home since Mar1970

PDP-10 system calls, was 1132 printer history

From: Anne & Lynn Wheeler <lynn@garlic.com>
Subject: Re: PDP-10 system calls, was 1132 printer history
Newsgroups: comp.lang.pl1, alt.folklore.computers
Date: Sat, 08 Sep 2012 08:37:54 -0400
Peter Flass <Peter_Flass@Yahoo.com> writes:
I remember for the /30 you had to IPL a special deck. I thought it was a microcode load, but IBM calls it an "Initialization Deck" and doesn't give any more information.

this previous thread discusses whether the 1401 microcode emulation was switch on the front panel or a diagnose instruction ... which would have required some 360 software to execute the diagnose instruction ... a small number of instruction on cards would have executed the instruction (and front panel system reset button would have brought things back to "normal" operation).
https://www.garlic.com/~lynn/2011h.html#15 Is the magic and romance killed by Windows (and Linux)?
https://www.garlic.com/~lynn/2011h.html#16 Is the magic and romance killed by Windows (and Linux)?
https://www.garlic.com/~lynn/2011h.html#18 Is the magic and romance killed by Windows (and Linux)?

--
virtualization experience starting Jan1968, online at home since Mar1970

Blades versus z was Re: Turn Off Another Light - Univ. of Tennessee

Refed: **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **
From: Anne & Lynn Wheeler <lynn@garlic.com>
Subject: Re: Blades versus z was Re: Turn Off Another Light - Univ. of Tennessee
Newsgroups: bit.listserv.ibm-main
Date: Sat, 08 Sep 2012 09:36:08 -0400
mike.a.schwab@GMAIL.COM (Mike Schwab) writes:
10 or 20 Linux servers consolidated onto 1 x86-64 blade server. 300 Linux servers consolidated onto 1 zIFL.

Now that looks reasonable. A full speed z processor is still 15 to 30 times faster than Virtual x86-64.


re:
https://www.garlic.com/~lynn/2012l.html#81 Blades versus z was Re: Turn Off Another Light - Univ. of Tennessee
https://www.garlic.com/~lynn/2012l.html#87 Blades versus z was Re: Turn Off Another Light - Univ. of Tennessee
https://www.garlic.com/~lynn/2012l.html#88 Blades versus z was Re: Turn Off Another Light - Univ. of Tennessee

there were two different scenarios ... the large proliferation of i86 servers with very low processor utilization being able to leverage virtual machines to consolidate 10:1 ... even using the same hardware (i.e. being able to consolidate ten 10% utilized systems into a single system ... w/o changing hardware). In the middle of last decade Marines were talking about 10:1 consolidation of datacenters (each datacenter with approx. same number of servers ... using virtual machines to eliminate 90% of the datacenters ... with their servers typically avg. 10% cpu utilization).

then there is the comment about the e5-2600 with 527BIPS being able to consolidate at 20:1, prior generation servers. 1/20th of 527BIPS is 26BIPS ...
https://en.wikipedia.org/wiki/Million_instructions_per_second

from above, Intel core2 dual-core as recently as 2006 was 27BIPS. e5-2600 (@527BIPS) would be able to consolidate 20 such systems all avg. nearly 100% processor utilization (potentially even w/o virtualization ... if originally replicated running same application).

the 2006 core2 dual-core was 13BIPS/core ... compared to e6-2600 @527BIPS and 16cores is 33BIPS/core. 2.5 times per core performance increase over approx. five years but also four times the cores/chip gives factor of aggregate ten times increase per chip in five years ... and then two chips to give the 20:1. as per previous posts, e5-2600 @527BIPS is equivalent of 10.5 maxed out, 80-processor, 50BIP z196 or seven maxed out, 101-processor 75BIPS zEC12 (z196 core is 50/80 or 624MIPS and zEC12 core is 75/101 or 743MIPS).

moore's law doubling every 18months hit single processor thruput increase limits sometime ago ... this old thread quotes intels svp pat gelsinger having to explain the realities to the CEO of microsoft and need to adopt parallel programming in order to take avantage of further thruput increases:
https://www.garlic.com/~lynn/2008f.html#42 Panic in Multicore Land

IBM had somewhat similar moment with 3081 ... which originally wasn't going to have a single processor version ... but there was issue with ACP/TPF not having (tightly-coupled) multiprocessor support (ACP/TPF had loosely-coupled support from early days in 60s) and the major clone vendor still offering faster single processor machine (potential that all the ACP/TPF customers would migrate to clone vendor). Initially there were all sorts of unnatural acts to try and make 3081 attractive to ACP/TPF customers ... but finally a 3083 had to be offered by removing one of the processor from 3081 (there were some physical issues since 3081 processor0 was at the top of the box ... and it would have been more of a no brainer to remove processor1 in the middle of the box ... but that would have left the box dangerously top-heavy).

of course the 3081 also had lots of other issues ... one of the quick&dirty efforts launched after failure of future system (FS internal politics actively killing off all the 370 efforts ... lack of 370 products also allowed the clone processor vendors to gain market foothold). misc. past posts mentioning Future System
https://www.garlic.com/~lynn/submain.html#futuresys

recent old email post discussing some of the clone & emulation competition
https://www.garlic.com/~lynn/2012l.html#email890707
in this post/thread
https://www.garlic.com/~lynn/2012l.html#72 zEC12, and previous generations, "why?" type question - GPU computing.

discusses 3081 technology being some warmed over FS stuff, but compares very poorly with clone vendors
http://www.jfsowa.com/computer/memo125.htm

--
virtualization experience starting Jan1968, online at home since Mar1970

Difference between fingerspitzengefuhl and Coup d'oeil?

Refed: **, - **, - **, - **, - **, - **
From: lynn@garlic.com (Lynn Wheeler)
Date: 8 Sep, 2012
Subject: Difference between fingerspitzengefuhl and Coup d'oeil?
Blog: Boyd Strategy
re:
http://lnkd.in/9g2Ggz
and
https://www.garlic.com/~lynn/2012h.html#48 Difference between fingerspitzengefuhl and Coup d'oeil?
https://www.garlic.com/~lynn/2012j.html#63 Difference between fingerspitzengefuhl and Coup d'oeil?

and a little recent on fast/slow

Brain connections power automatic and conscious behaviour
http://medicalxpress.com/news/2012-09-brain-power-automatic-conscious-behaviour.html

from above:
What determines whether you deal with new situations in a flexible manner or simply act out of habit? A team of psychologists have discovered that this is predicted by the strength of specific connections in the brain. It can therefore be seen in your brain whether you act consciously or on automatic pilot. An understanding of this is relevant for the treatment of drug addicts and compulsive patients, for example.

... snip ...

There has got to be lots of levels related to serial/parallel. Boyd's dog fights have lots of visual parallel ... and he objected to original heads-up display in f16 which had scrolling digital numbers .... claiming the mental effort to translate digital number into useful information took away from efficiently flying. The other part is great difficulty for those predisposed to automatic have a great deal of trouble unlearning the behavior when it is no longer useful (and/or even detrimental).

Parallel for computer programming has been holy grail for long time ... increasingly with transition to multiple core chips. Traditional programming tools are serial/sequential one step at a time ... there is corresponding issue that the brain world view becomes conditioned by the tools it has available; aka serial/sequential digital tools tends to reinforce serial/sequential thinking. old post about Intel SVP having to explain to Microsoft CEO that they would have to start adopting parallel programming paradigm
https://www.garlic.com/~lynn/2008f.html#2 Panic in Multicore Land

and for the fun of it: Revenge of the Lizard Brain
http://blogs.scientificamerican.com/guest-blog/2012/09/07/revenge-of-the-lizard-brain/

--
virtualization experience starting Jan1968, online at home since Mar1970

What if practices rather than ideas are the main sources of innovation?

From: lynn@garlic.com (Lynn Wheeler)
Date: 8 Sep, 2012
Subject: What if practices rather than ideas are the main sources of innovation?
Blog: Boyd Strategy
re:
http://lnkd.in/sWKbzv

The Idea Idea
http://cs.gmu.edu/cne/pjd/PUBS/CACMcols/cacmMar12.pdf

There is whether there is established status quo and vested interests or not.

We were brought in as consultants to small client/server startup that wanted to do payment transactions on their server ... the startup had also invented some technology they called "SSL" they wanted to use ... the result is now frequently called "electronic commerce". Since that time, there has been dozens of things created that address serious deficiencies in SSL ... but none of them have managed to displace the incumbent (disclaimer: we have a couple dozen patents in the area). Fast uptake of SSL mode of electronic commerce was because there wasn't established incumbent ... but once something is established ... it is much harder to replace.

Note: about same time peter published his CACM working set paper in 1968 ... I was doing something similar but different. Didn't try to make it an academic issue ... but just got it incorporated in commercial products. In the early 80s there was somebody had done his PHD at Stanford on something similar to what I had done as undergraduate in the 60s ... which was in many ways directly contradicted Peter's work. Peter was lobbying hard to prevent Stanford from awarding the PHD (which contradicted his work from the 60s). I got dragged into the dustup since I had apples-to-apples comparison between the two different kinds of implementations on identical software & hardware. recent discussion here:
https://www.garlic.com/~lynn/2012l.html#37

There is all sorts of pressures and vested interests related to maintaining the incumbent, status-quo, etc.

another aspect ... whether something new is viewed as a cost or a profit:

Amazon Loses Money On Tablets. It's All Going According To Plan
http://www.fastcompany.com/3001110/amazon-loses-money-tablets-its-all-going-according-plan

If you are in the business selling works ... then the equipment to read the works can represent cost item ... and higher cost represents barrier to selling works (the old "give away the razor to sell razor blades"). I once got into dustup with GSA over the chips being used in CAC-card ... vendors of existing chips viewing it as profit item ... and I was looking at designing chip from standpoint of it being a cost item (optimizing design to reduce costs as opposed to designing to maximize profit, i even showed how design to reduce costs improved security ... since design to maximize profit was overly complex)

--
virtualization experience starting Jan1968, online at home since Mar1970

PDP-10 system calls, was 1132 printer history

Refed: **, - **, - **, - **, - **
From: Anne & Lynn Wheeler <lynn@garlic.com>
Subject: Re: PDP-10 system calls, was 1132 printer history
Newsgroups: comp.lang.pl1, alt.folklore.computers
Date: Sat, 08 Sep 2012 15:17:32 -0400
Quadibloc <jsavard@ecn.ab.ca> writes:
All the early IBM 360 computers featured, in one corner of the front panel, three knobs with hex digits on them with a pattern of buttons above and below.

That was one of the few parts of the front panel that was for the use of machine operators instead of IBM service personnel. You turned the three knobs to choose the boot device, and then you pressed the IPL (Initial Program Load) to start the computer - you might boot it from cards, or tape, or disk. It didn't try scanning through them in an order set from the console screen, the way a modern PC does, but it did have a boot program of sorts in ROM, so that never had to be toggled in from the front panel.


aka the IPL button would invoke a "02" channel command read for 24 bytes into location zero ... and assumed that the first 16 bytes (at location) zero were additional channel i/o commands and do a channel program transfer/tic to location zero. when the channel program ended, it would do a load psw from location 16 (the 3rd double word read).

a three card loader program was first card with 24 bytes that had two read ccws of 80bytes each (160 bytes) followed by a psw that started executing at the first byte of the card image read. the 160 bytes was enough for 40 4byte instructions which were a program to read additional information.

a more complex disk ipl would be have the first ccw (loaded at location zero) a read from the disk of additional channel program and the 2nd ccw a transfer/tic to the channel I/O commands just read ... which could read a much large program from disk before finishing ... leading to the LPSW at location 16 ... starting the program.

--
virtualization experience starting Jan1968, online at home since Mar1970

PDP-10 system calls, was 1132 printer history

Refed: **, - **, - **, - **
From: Anne & Lynn Wheeler <lynn@garlic.com>
Subject: Re: PDP-10 system calls, was 1132 printer history
Newsgroups: comp.lang.pl1, alt.folklore.computers
Date: Sat, 08 Sep 2012 17:16:40 -0400
glen herrmannsfeldt <gah@ugcs.caltech.edu> writes:
Since I just posted something different, I had to look it up to be sure.

The CCWs are from locations 8 and 16, and the PSW in location 0.

The description is "as if" the IPL CCW doing the 24 byte read was in location zero, though as far as I know, no machines actually do that. If one did, it would naturally go to location 8 for the next CCW, after the read overwrites the CCW in location zero.

Somehow it always seemed more natural to me that the PSW came from location zero.


re:
https://www.garlic.com/~lynn/2012l.html#93 PDP-10 system calls, was 1132 printer history

you right, I was mis-remembering

from cms low core definition:
0000 0 Dbl-Word 8 IPLPSW Initial program loading PSW 0008 8 Dbl-Word 8 IPLCCW1 Initial program loading CCW1 0010 16 Dbl-Word 8 IPLCCW2 Initial program loading CCW2

--
virtualization experience starting Jan1968, online at home since Mar1970

PDP-10 system calls, was 1132 printer history

Refed: **, - **, - **
From: Anne & Lynn Wheeler <lynn@garlic.com>
Subject: Re: PDP-10 system calls, was 1132 printer history
Newsgroups: comp.lang.pl1, alt.folklore.computers
Date: Sat, 08 Sep 2012 17:32:23 -0400
re:
https://www.garlic.com/~lynn/2012l.html#93 PDP-10 system calls, was 1132 printer history
https://www.garlic.com/~lynn/2012l.html#94 PDP-10 system calls, was 1132 printer history

real brain check

got the order correct at least twice before:
https://www.garlic.com/~lynn/2000d.html#66 standard BASIC (was: S/360 development burnout?)
https://www.garlic.com/~lynn/2001c.html#87 "Bootstrap"

note more low stoarge description
https://www.garlic.com/~lynn/gcard.html#4

there was also "restart" button on front panel. if something was going wrong in the system ... it was possible to hit the restart button ... and it would store the current psw at location 8 and load the new psw from location zero (in much the same way that IPL would load new psw from location zero after initial i/o)

--
virtualization experience starting Jan1968, online at home since Mar1970

PDP-10 system calls, was 1132 printer history

From: Anne & Lynn Wheeler <lynn@garlic.com>
Subject: Re: PDP-10 system calls, was 1132 printer history
Newsgroups: comp.lang.pl1, alt.folklore.computers
Date: Sat, 08 Sep 2012 19:58:14 -0400
Ibmekon writes:
Was there was also a STOP button ?

I shudder to recall a time when operating an IBM 370, with an exitable supervisor of Italian extraction - in London, England.

A trick that could on occasion be useful, was to hit STOP. Maybe to clear some device problem - without the CPU spitting out console errors. Or use the switches to change the system clock - etc. And them hit RESTART.

One day I pressed STOP to show this to a fellow operator. The supervisor, from outside the ops room, saw all the lights had frozen and came running in a panicked state. So I just pressed RESTART. If looks could kill, you would not have read this.


re:
https://www.garlic.com/~lynn/2012l.html#93 PDP-10 system calls, was 1132 printer history
https://www.garlic.com/~lynn/2012l.html#94 PDP-10 system calls, was 1132 printer history
https://www.garlic.com/~lynn/2012l.html#95 PDP-10 system calls, was 1132 printer history

stop & start button ... as well as rotory switch that could select single-cycle ... rather than start button resuming execution would just execute single instruction.

here is front panel
http://upload.wikimedia.org/wikipedia/commons/6/6a/IBM360-65-1.corestore.jpg

with relatively good resolution ... that allows for image blowup ... but there is reflective glare, dirt and worn lettering.

The start button is below the "rate" rotary switch at the bottom middle.

--
virtualization experience starting Jan1968, online at home since Mar1970

What a Caveman Can Teach You About Strategy

Refed: **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **
From: lynn@garlic.com (Lynn Wheeler)
Date: 9 Sep, 2012
Subject: What a Caveman Can Teach You About Strategy
Blog: Boyd Strategy
re:
http://lnkd.in/TYahQ9

What a Caveman Can Teach You About Strategy
http://www.forbes.com/sites/silberzahnjones/2012/09/04/what-a-caveman-can-teach-you-about-strategy/

One of the scenarios was that the west was suppose to exhaust itself in the retaliation efforts. Instead of quick reaction attack on those responsible ... there was marshaling of massive forces that allows time for Al Qaeda to melt way ... long before any strike was made. MICC takes advantage of the situation to turn it into several trillion dollar campaign against Iraq and Taliban. Does it repeat Vietnam because MICC can never learn ... or does it repeat Vietnam because MICC is preoccupied with having continuous conflict and perpetual war.

There was the farce a few months in when there were eyes on the target and they couldn't get approval to take the shot.

The long-term war bill will supposedly exceed $5T with long-term health benefits taken into account. However one analysis was that last decade, DOD got an extra $2T over baseline ... $1T appropriations for the wars and not able to demonstrate what DOD got for the other trillion. CBO has last decade there being a $6T reduction in tax revenue and $6T increase in spending (compared to baseline) for $12T budget gap. Unknown what part of the other $4T increase in spending (over baseline) disappeared into non-DOD MICC related activities (including things like the $16B in shrink wrapped $100 bills sent over on pallets that apparently disappeared in Iraq). Is this failure to learn and/or "perpetual war" strategy?

Different viewpoints of (effectively same) Marine history
https://en.wikipedia.org/wiki/Small_Wars_Manual
and
https://en.wikipedia.org/wiki/War_Is_a_Racket

War is a Racket references:
https://en.wikipedia.org/wiki/Perpetual_war
which references Sprey, Spinney, et all. ... also referenced here:
http://chuckspinney.blogspot.com/p/domestic-roots-of-perpetual-war.html
total cost reference here: (from year ago)
http://www.phibetaiota.net/2011/09/chuck-spinney-bin-laden-perpetual-war-total-cost/

from above:
Osama bin Laden repeatedly said that his strategy for defeating the US and driving it out of the Middle East was to bankrupt the US by suckering it into a string expensive of never ending small wars. Osama may be dead, but the US remains locked in a state of perpetual wars abroad and shrinking civil liberties at home.

.... snip ...

misc. past posts mentioning "war is a racket" and/or "perpetual war"
https://www.garlic.com/~lynn/2011.html#93 America's Defense Meltdown
https://www.garlic.com/~lynn/2011d.html#83 End of an era
https://www.garlic.com/~lynn/2011e.html#18 End of an era
https://www.garlic.com/~lynn/2011e.html#33 The real cost of outsourcing (and offshoring)
https://www.garlic.com/~lynn/2011e.html#65 End of an era
https://www.garlic.com/~lynn/2011f.html#28 US military spending has increased 81% since 2001
https://www.garlic.com/~lynn/2011h.html#43 Happy 100th Birthday, IBM!
https://www.garlic.com/~lynn/2011i.html#32 Happy 100th Birthday, IBM!
https://www.garlic.com/~lynn/2011k.html#42 Senator urges DoD: Do better job defending F-35
https://www.garlic.com/~lynn/2011k.html#49 50th anniversary of BASIC, COBOL?
https://www.garlic.com/~lynn/2011k.html#88 Justifying application of Boyd to a project manager
https://www.garlic.com/~lynn/2011l.html#0 Justifying application of Boyd to a project manager
https://www.garlic.com/~lynn/2011l.html#8 The True Cost of 9/11 -- Includes 18 Veteran Suicides a Day
https://www.garlic.com/~lynn/2011l.html#17 Washington's Cult of Continuous Failure
https://www.garlic.com/~lynn/2011l.html#34 Scotland, was Re: Solving the Floating-Point Goldilocks Problem!
https://www.garlic.com/~lynn/2011p.html#34 21st Century Management approach?
https://www.garlic.com/~lynn/2011p.html#142 We are on the brink of a historic decision [referring to defence cuts]
https://www.garlic.com/~lynn/2012b.html#75 The Winds of Reform
https://www.garlic.com/~lynn/2012e.html#25 We are on the brink of historic decision [referring to defence cuts]
https://www.garlic.com/~lynn/2012e.html#70 Disruptive Thinkers: Defining the Problem
https://www.garlic.com/~lynn/2012e.html#71 Disruptive Thinkers: Defining the Problem
https://www.garlic.com/~lynn/2012e.html#78 Time to Think ... and to Listen
https://www.garlic.com/~lynn/2012e.html#104 Time to Think ... and to Listen
https://www.garlic.com/~lynn/2012f.html#88 Defense acquisitions are broken and no one cares
https://www.garlic.com/~lynn/2012h.html#21 The Age of Unsatisfying Wars
https://www.garlic.com/~lynn/2012h.html#63 Is this Boyd's fundamental postulate, 'to improve our capacity for independent action'?
https://www.garlic.com/~lynn/2012h.html#68 Interesting News Article
https://www.garlic.com/~lynn/2012i.html#0 Interesting News Article
https://www.garlic.com/~lynn/2012i.html#24 Interesting News Article
https://www.garlic.com/~lynn/2012i.html#51 Is this Boyd's fundamental postulate, 'to improve our capacity for independent action'? thoughts please
https://www.garlic.com/~lynn/2012k.html#87 Cultural attitudes towards failure
https://www.garlic.com/~lynn/2012l.html#2 Cultural attitudes towards failure
https://www.garlic.com/~lynn/2012l.html#5 Cultural attitudes towards failure
https://www.garlic.com/~lynn/2012l.html#45 Introducing John Boyd
https://www.garlic.com/~lynn/2012l.html#50 Arming for the Navy's Return to History
https://www.garlic.com/~lynn/2012l.html#58 Singer Cartons of Punch Cards
https://www.garlic.com/~lynn/2012l.html#62 Singer Cartons of Punch Cards

--
virtualization experience starting Jan1968, online at home since Mar1970

PDP-10 system calls, was 1132 printer history

Refed: **, - **, - **, - **, - **, - **
From: Anne & Lynn Wheeler <lynn@garlic.com>
Subject: Re: PDP-10 system calls, was 1132 printer history
Newsgroups: comp.lang.pl1, alt.folklore.computers
Date: Sun, 09 Sep 2012 17:28:31 -0400
hancock4 writes:
I understand on 1401's it was common for a customer programmer to take control of a machine and step through his program logic using the console lights and switches. But the 1401 instruction set was relatively simple and there was no supervisor or operating system to get in the way.

Was it common for a typical customer programmer to operate S/360 from the console, step-by-step? I assume that would've been more tricky due to the complexity of the S/360 instruction set and the need to work with the supervisor for I/O calls and interrupts.


re:
https://www.garlic.com/~lynn/2012l.html#93 PDP-10 system calls, was 1132 printer history
https://www.garlic.com/~lynn/2012l.html#94 PDP-10 system calls, was 1132 printer history
https://www.garlic.com/~lynn/2012l.html#95 PDP-10 system calls, was 1132 printer history
https://www.garlic.com/~lynn/2012l.html#96 PDP-10 system calls, was 1132 printer history

univ had 709 with 1401 front-end handling unit record (operator moved tapes between 709 and 1401). then they were to get 360/67 running tss/360 to replace everything. as part of transition they got 360/30 to replace 1401 ... it would run unit record front-end MPIO natively ... but I got a student job to write a 360 native replacement (performing all the 1401 MPIO unit record).

They normally shutdown on the weekends ... and let me have the datacenter from 8am Saturday until 8am Monday. My MPIO replacement eventually grew to box (2000) of cards. It had assembler conditional that would either generate a stand-alone monitor (had my own interrupt handler, device drivers, error recovery, storage management, dispatcher, etc) or run under os/360 (open/close, get/put, dcb macros). Stand-alone version would assemble in under 30 minutes (circa os/360 pcp release 6 on 360/30). os/360 version took approx. an hour to assemble ... could watch it take approx. 5-6 minutes each for DCB macro.

Debugging program on weekends, I spent a lot of time with switches. You could set address in switches and set rotary switch for address-compare-stop ... and then single step the machine, one instruction at a time. Toggles could be used to display values in storage or registers. It was also possible to use toggles to modify values.

The output of the stand-alone version ... would slap the BCP stand-alone loader on the front and boot from the card reader (similar to 1401 MPIO boot).

Later the 709 and 360/30 was replaced with 360/67 but tss/360 never got very mature. I was then hired for supporting os/360 ... and would still usually get the datacenter for the weekend (I've mentioned before that being up for 48hrs made monday morning classes a challenge).

Three people from science center ... some past posts
https://www.garlic.com/~lynn/subtopic.html#545tech

came out last week jan, 1969 to install cp67. I then got to play with cp67 and os/360 on weekends ... however, cp67 never quite got to the place that univ. did regular production during the week.

the installed cp67 had image restore to 2314 (with cp67 boot and cms and other file areas) and cp67 source files assembled under os/360 (just before they moved cp67 source maintenance to cms). Output of all cp67 source assemblies fit in card tray (i.e. less than 3000 cards but more than 2000 card box). Each module deck would have magic marker diagonal stripe with abbreviated name of module across top of deck ... making it easy to replace individual module executable deck. At the front of the CP67 load deck tray was the BPS stand-alone loader.

To build a new CP67 required doing stand-alone load of the card deck, which would load an image of the CP67 into kernel ... and transfer to entry point in "CPINIT" routine. CPINIT would write a memory image of the kernel to indicated disk position and update disk IPL information ... to load CPINIT. Standard system IPL from disk would bring in CPINIT ... which would reverse the process of writing the memory image to disk ... substituting read for write.

After CP67 source maintenance was moved to CMS ... there was also change to virtual machine operation ... "punching" the executable kernel cards to the virtual punch device ... which was "transferred" transferred to the virtual card reader device and a virtual IPL performance. Would have a virtual disk definition that mapped to the production real disk ... so the CPINIT kernel memory image write ... would overlay the real bootable kernel.

recent posts mentioning (1401) MPIO
https://www.garlic.com/~lynn/2012.html#33 Who originated the phrase "user-friendly"?
https://www.garlic.com/~lynn/2012.html#56 IBM researchers make 12-atom magnetic memory bit
https://www.garlic.com/~lynn/2012d.html#7 PCP - memory lane
https://www.garlic.com/~lynn/2012d.html#31 Can SSL Certificate Checking System Be Saved?
https://www.garlic.com/~lynn/2012e.html#38 A bit of IBM System 360 nostalgia
https://www.garlic.com/~lynn/2012e.html#98 Burroughs B5000, B5500, B6500 videos
https://www.garlic.com/~lynn/2012i.html#21 IEBPTPCH questions

--
virtualization experience starting Jan1968, online at home since Mar1970

PDP-10 system calls, was 1132 printer history

Refed: **, - **, - **, - **, - **, - **, - **, - **, - **
From: Anne & Lynn Wheeler <lynn@garlic.com>
Subject: Re: PDP-10 system calls, was 1132 printer history
Newsgroups: comp.lang.pl1, alt.folklore.computers
Date: Sun, 09 Sep 2012 18:14:18 -0400
Shmuel (Seymour J.) Metz <spamtrap@library.lspace.org.invalid> writes:
There is no "the IBM 370 control panel"; each model had its own. In particular, some older models had rollers and some newer models droped them in favor of other techniques.

transition from front panel to keyboard/display-screen.

before announce of virtual memory for 370, a copy of virtual memory hardcopy document showed up at some industry publication. there was then a "pentagon paper" witchhunt for the leak. best they could do was suspect the leak came from somebody in the vm370 development group (was still on 3rd flr of 545 tech sq after having taken over the ibm boston programming center). in the aftermath of the witchhunt, all corporate copy machines were retrofitted with unique serial number under the glass ... that would appear on all copied pages. more than decade later can be seen in this copy made on copy macine in IBM San Jose Research
https://www.garlic.com/~lynn/grayft84.pdf

For the FS effort ... the VM370 group had done a super-secure vm370 used for reading softcopy future system document (with facilities inhibited for any spool-file/print capability ... or doing anything but softcopy reading). By this time, they had moved out to the former (vacated) SBC bldg in Burlington Mall (SBC gone to CDC as part of some legal action).
https://www.garlic.com/~lynn/submain.html#futuresys

I had some machine time on 370/145 in their machine room over the weekend ... in support of this ECPS activity that I had been con'ed into doing:
https://www.garlic.com/~lynn/94.html#21 370 ECPS VM microcode assist

I stopped by late Friday afternoon, as part of setting up for weekend machine use, they showed me their 370/155 with all the FS enhancements and said that even I (aka lynn) couldn't break the security. I guess I succumbed to temptation and said that it would take less than five minutes. Most of the time was taken disabling all external access to the 370/155 and then I used the front panel to patch a byte in storage ... which change branch on condition instruction ... so that everything/whatever typed in was taken as valid password. I pointed out that for somebody with physical access they needed either a method for securing front panel and/or encryption for the data.

Later machines allowed for "logon" password for using the machine functions ... like display/alter storage.

machine keyboard/display got more complex with 3081 and the service processor ... uc processor mentioned in this recent post
https://www.garlic.com/~lynn/2012l.html#82 zEC12, and previous generations, "why?" type question - GPU computing.

field service had procedure requiring to bootstrap machine starting with scope. TCMs introduced with 3081 were totally enclosed and didn't allow for scoping. for field service, a bootstrap process was introduced with service processor that could be scoped/diagnosed ... and then using the service processor that had all sorts of diagnostic instrumentation into the TCMs. The service processor then also supported all the other machine functions. The problem was that uc processor was primitive and a whole monitor and infrastructure had to be developed for scratch for the machine.

This was going to be changed for the 3090 follow-on ... where vm370/cms running on 4331 would be used instead as a base for building service processor. This was eventually changed to instead have a pair of redundant 4361s ... but still running vm370/cms ... with service processor functions implemented with cms ios3270.

recent posts mentioning 3090 service processor:
https://www.garlic.com/~lynn/2012b.html#58 Why can't the track format be changed?
https://www.garlic.com/~lynn/2012c.html#23 M68k add to memory is not a mistake any more
https://www.garlic.com/~lynn/2012e.html#38 A bit of IBM System 360 nostalgia
https://www.garlic.com/~lynn/2012e.html#63 Typeface (font) and city identity
https://www.garlic.com/~lynn/2012f.html#53 Image if someone built a general-menu-system
https://www.garlic.com/~lynn/2012f.html#76 Time to competency for new software language?
https://www.garlic.com/~lynn/2012g.html#23 VM Workshop 2012
https://www.garlic.com/~lynn/2012i.html#83 How smart do you need to be to be really good with Assembler?

past posts in this thread
https://www.garlic.com/~lynn/2012l.html#23 PDP-10 system calls, was 1132 printer history
https://www.garlic.com/~lynn/2012l.html#26 PDP-10 system calls, was 1132 printer history
https://www.garlic.com/~lynn/2012l.html#27 PDP-10 system calls, was 1132 printer history
https://www.garlic.com/~lynn/2012l.html#35 PDP-10 system calls, was 1132 printer history
https://www.garlic.com/~lynn/2012l.html#36 PDP-10 system calls, was 1132 printer history
https://www.garlic.com/~lynn/2012l.html#40 PDP-10 system calls, was 1132 printer history
https://www.garlic.com/~lynn/2012l.html#73 PDP-10 system calls, was 1132 printer history
https://www.garlic.com/~lynn/2012l.html#75 PDP-10 system calls, was 1132 printer history
https://www.garlic.com/~lynn/2012l.html#76 PDP-10 system calls, was 1132 printer history
https://www.garlic.com/~lynn/2012l.html#78 PDP-10 system calls, was 1132 printer history
https://www.garlic.com/~lynn/2012l.html#80 PDP-10 system calls, was 1132 printer history
https://www.garlic.com/~lynn/2012l.html#89 PDP-10 system calls, was 1132 printer history
https://www.garlic.com/~lynn/2012l.html#93 PDP-10 system calls, was 1132 printer history
https://www.garlic.com/~lynn/2012l.html#94 PDP-10 system calls, was 1132 printer history
https://www.garlic.com/~lynn/2012l.html#95 PDP-10 system calls, was 1132 printer history
https://www.garlic.com/~lynn/2012l.html#96 PDP-10 system calls, was 1132 printer history
https://www.garlic.com/~lynn/2012l.html#98 PDP-10 system calls, was 1132 printer history

--
virtualization experience starting Jan1968, online at home since Mar1970

Blades versus z was Re: Turn Off Another Light - Univ. of Tennessee

Refed: **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **, - **
From: lynn@GARLIC.COM (Anne & Lynn Wheeler)
Subject: Re: Blades versus z was Re: Turn Off Another Light - Univ. of Tennessee
Newsgroups: bit.listserv.ibm-main
Date: 9 Sep 2012 21:33:56 -0700
Clark Morris <cfmpublic@ns.sympatico.ca> writes:
I see what you have posted and what Lynn Wheeler has posted and am confused. Assuming that VMware on Intel and similar solutions for the p series have gotten much better since 2007 (not unrealistic), I'm looking at the relative CPU power and asking is the server utilization in a well run Intel (Windows and Linux) or IBM p series shop still so low that z can beat them on a total dollars out the door. Is the main difference the I-O handling?

Is IBM mainframe traditional software (CICS, IMS, COBOL) subsidizing IBM mainframe new world software (Websphere, Java, C/C++)?


re:
https://www.garlic.com/~lynn/2012l.html#87 Blades versus z was Re: Turn Off Another Light - Univ. of Tennessee
https://www.garlic.com/~lynn/2012l.html#88 Blades versus z was Re: Turn Off Another Light - Univ. of Tennessee
https://www.garlic.com/~lynn/2012l.html#90 Blades versus z was Re: Turn Off Another Light - Univ. of Tennessee

There is TPC-C ... transaction benchmark for comparison
http://www.tpc.org/tpcc/results/tpcc_perf_results.asp

least expensive ($$/tpm) in the top 10 is ibm i86, most expensive is ibm risc.

IBM: "Converge your data center on your terms"
http://www-03.ibm.com/systems/info/x86servers/blades/servers/index.html

above fumbled a little bit, e5-2600 is two chip, 8-core/chip, 16 core.

IBM has a whole slew of e5-2600 benchmarks here
https://www.trustedcomputinggroup.org/home

can anybody find similar numbers for z196 and/or EC12??

ibm has e5-2600 in number of server products
http://www-03.ibm.com/systems/x/news/20120306_announce/index.html

not just hs23.

This claims the highest density per rack footprint
http://www-03.ibm.com/systems/x/hardware/rack/dx360m4/index.html

not e5-2600 ... but more ibm i86 benchmarks (from aug&sep 2011)
http://benchmarkingblog.wordpress.com/category/x3850/

note that disks will be the same across the three technologies, however i86 and risc will frequently have an edge over mainframe w/o the overhead of the additional layer to simulate CKD (ckd disks haven't been manufactured for decades, being emulated on industry standard disks).

some recent server-class disk i/o

5Gbyte/second, 724K IOPS (i/o operations per second)
http://www.servethehome.com/lsi-9202-16/

6.6Gbyte/second, 450K IOPS
http://www.marketwatch.com/story/adaptec-by-pmc-transforms-data-center-storage-architectures-with-industrys-highest-port-count-pcie-gen3-raid-adapters-2012-09-05

e5-2600 based servers ... lsi
http://www.scsita.org/library/2012/03/lsi-sas-technology-powers-over-200-new-server-models-based-on-the-intel-xeon-processor-e5-2600-produ.html

more e5-2600 ... adaptec
http://www.scsita.org/library/2012/03/adaptec-doubles-server-storage-performance-and-bandwidth-in-cebit-demo-featuring-pcie-30-on-the-inte.html

--
virtualization experience starting Jan1968, online at home since Mar1970




previous, next, index - home