First | Previous | Next | Last
|
IBM 610 workstation computer 3432
It is a poor man's fault tolerance. SMP makes a system able to withstand faults. Why do you think I'm fighting...
IBM 610 workstation computer 3433
On Thu, 02 Mar 06 13:09:27 GMT No it's not. The most common way of providing delivery of non stop continuous computing services these days is mbuttive redundancy at...
IBM 610 workstation computer 3434
when were were doing ha-cmp ... we talked to the 1-800 people. they had five-nines requirement (5...
IBM 610 workstation computer 3435
when we started project for ha-cmp product ... i created a cluster taxonomy around * mode1 ... 1+1 fail-over (2nd processor...
IBM 610 workstation computer 3436
You miss out on the sheer number of servers in use in commercial installations. A 4-way SMP (non-redundant cpu-wise, but with everything else...
IBM 610 workstation computer 3437
YES, I have been trying to step back and thinking about "component" fixtures. I consider an...
IBM 610 workstation computer 3438
I don't recall that on a printer (doesn't mean, of course, that it didn't happen), but there was a similar issue with the IBM 407 Accounting Machines. The boxes (hideously expensive) were available in several...
IBM 610 workstation computer 3439
Joe Morris I don't recall that on a printer (doesn't mean, of course, that it didn't happen), but there was...
IBM 610 workstation computer 3440
On Sat, 04 Mar 06 14:32:22 GMT It wasn't a problem with the setup I first did it on - which was basically a data...
IBM 610 workstation computer 3441
part of the issue is fault isolation. also, i think jim gray, after he left sjr for tandem ... published a paper in the...
IBM 610 workstation computer 3442
the or virtual so a stop (until That's how the SMP biz got started but this is no longer true. Take a second look at what you two are arguing about...
IBM 610 workstation computer 3443
As long as we agree on the definitions, I'm not too interested in what it's called. ;-) The L2 caches are available to all CPU ports, that's exactly my point. I haven't...
IBM 610 workstation computer 3444
are memory cache board. main is a Sure. But we are viewing the system from differently shaded glbuttes :-). That's where we get...
IBM 610 workstation computer 3445
snip In most (but not all) systems less than 10% of the memory contains writeable global data. The application software knows the name of these areas and gains...
IBM 610 workstation computer 3446
On Sun, 26 Feb 2006 13:37:25 +0000, jmfbahciv Call L2's memory then. If an L2 contains dirty data it will respond in place of (or before) main memory...
IBM 610 workstation computer 3447
Who is the I in this last sentence? I am stating that the I is the OS. It cannot be hardware. It is only the OS who knows...
IBM 610 workstation computer 3448
Sigh! Who is the it in that sentence? This question is the most important section of this post. My observations of hardware types is that they...
IBM 610 workstation computer 3449
two-way 370 processor adds cache overhead such that a two-way 370 is considered to be at best...
IBM 610 workstation computer 3450
ref: the problem was that with one cpu ... the cache ran at full-speed. with two cpus, the cache ran...
IBM 610 workstation computer 3451
there was a separate issue-paper involving TSS-360 on 360-67 which claimed over three times the thruput on two-processor 360-67...
IBM 610 workstation computer 3452
Using any approach requiring a global system lock seems to prevent any system from scaling to...
IBM 610 workstation computer 3453
this is somewhat dependent on the traditional spin-lock approach to global system lock. this was almost totally eliminated with the VAMPS bounce lock approach (reducing the cost of...
IBM 610 workstation computer 3454
KR Williams I will describe a machine I was programming in 1993. The main processor was an Intel 8080 which...
IBM 610 workstation computer 3455
On Sat, 25 Feb 2006 02:24:30 +0000, Andrew Swallow They work when you have more than one CPU too. This is a point that both you anBAH are completely missing. Huh? Wow! You can't write...
IBM 610 workstation computer 3456
Keith The point that you are missing is that *I have seen them fail.* BAH may have too...
IBM 610 workstation computer 3457
Andrew Swallow Its interesting how things change over time. If you read the early history of...
IBM 610 workstation computer 3458
I've seen lightlbulbs fail too. So *what*! Does that mean we don't use light bulbs? Good luck with that...
IBM 610 workstation computer 3459
You have fallen behind the times. Hardware is extremely more caused by other systematic failures like bane overheat; power supply failures etc. To the "newbies" around these newsgroups, I remember making a log...
IBM 610 workstation computer 3460
I've got boxes with over 480 days of uptime on old RedHat linux. The apps have been upgraded. Software maintenance rarely requires a reboot, sometimes services (apps) need a restart...
IBM 610 workstation computer 3461
Yea, I shouldn't have written it that way; I meant the only way to do this...
IBM 610 workstation computer 3462
Once upon a time, when I was the fierce guard of all TOPS-10's specs in the...
IBM 610 workstation computer 3463
they were also common on ibm tapes ... especially the ptf tapes ... small gray plastic ... barely bigger than the space for...
IBM 610 workstation computer 3464
On Thu, 02 Mar 06 13:21:28 GMT in alt.folklore.computers, ISTM he's talking about the processor chips nowadays. Some other devices are still not too different from RH20s...
IBM 610 workstation computer 3465
Only up to a hundred thousand processors, or so. ;-) Seriously, PowerPC (Power4-5 etc.) does 8-way SMP as a basic building block. Intel x86 is at...
IBM 610 workstation computer 3466
You may be tunnel visioning; memory isn't the only wire that has to be going to all CPUs; you also have to think about...
IBM 610 workstation computer 3467
I've oft claimed that the non-cache coherency for 801 (from the mid-70s) between the I and D caches...
IBM 610 workstation computer 3468
RJ On the contrary, it is about Fortran. It's about the deficiency of languages that follow the design of the von Neumann-style computer, of...
Mainframe near history IBM 3380 and 3880 docs
As often as not for us, it was more like whirl, kerchunk, clatter-tick-tick-clatter, kerchunck, whirl, kerchunk, clatter-tick-tick-clatter, kerCRUNCH with lots of red lights. The way...
Looking for Johnson's pcc DG Nova and Eclipse 3471
tcc looks a little too 32BITish and a little too X86ish for my taste, after a very quick look. The reason I would start with a Small-C Compiler is that...
Looking for Johnson's pcc DG Nova and Eclipse 3472
I can probably remember it. If I ever get that far. Besides that it's long dead :-) Multi...
Looking for Johnson's pcc DG Nova and Eclipse 3473
For the moment, I am just going to look at the routines to see how feasible such a hack...
History of Programming Languages III was AFC Book Listing, Big Update 3474
Eric Smith Actually looking at Dennis Ritchie's HOPL-II presentation I think the best interpretation is his conclusion on...
History of Programming Languages III was AFC Book Listing, Big Update 3475
Eric Smith That's precisely the reason I find it interesting. Well, I would argue that there was no planning to begin with...
AFC Book Listing, Big Update
On Sun, 14 May 2006 02:26:33 -0400 in alt.folklore.computers, Charles useful for refs, a lot of clbuttic papers and articles were published in Software--Practice and...
Arpa address 3477
slight nit ... arpa had funded arpanet and development of packet-switching protocol. this was relatively homogeneous environment requiring fairly expensive interface "IMPs" to be part of the...
Arpa address 3478
On Wed, 17 May 2006, in the Usenet newsgroup alt.computer.security, in article Minor simplification - I didn't think it important. "the internal network"... meaning? 404 compliant. 0836 Who talks TCP...
Arpa address 3479
On Thu, 18 May 2006, in the Usenet newsgroup alt.computer.security, in article Well, yeah - you have to look at what capabilities we had. RIP...
Arpa address 3480
The decade of the ARPAnet was nothing short of amazing. IMPs meant a lot. They were coveted. After 6-7 years, UCSB administration...
Arpa address 3481
from CSNET (Computer Science NETwork) is funded by NSF, and is an attempt to connect all computer science research insbreastutions...
Arpa address 3482
I thot we were taling about events leading up to 1983 and the size of the...
Arpa address 3483
cpremote was approximately 1970 between machines at the science center. approx. 1971 vnet was used between science center and endicott for distributed development project enhancing cp67...
Arpa address 3484
some number of homogeneous operations also tend to have lots of stories about scheduled shutdown of the service while all components...
Arpa address 3485
Anne & Lynn Wheeler from CSNET (Computer Science NETwork) is funded by NSF, and is an attempt to connect all computer science research insbreastutions in the U.S. It does not have a physical...
Arpa address 3486
Anne & Lynn Wheeler If a node is an IMP, then 100 nodes is not inconsistent with 250 hosts. Remember the mapping of IP addresses on...
Arpa address 3487
re: so a location might have an IMP node for the network, a mainframe ... considered a HOST, another IMP working as a terminal server ... also...
Arpa address 3488
re: if there were as few as *100 mainframe hosts*(?) connected to the arpanet on then 1jan83 cut-over to internetworking ... then the internal network would have had...
Arpa address 3489
actually there are two, somewhat separate heterogeneous capability provided by gateways ... one is somewhat the...