![](/i/fill.gif) |
![](/i/fill.gif) |
|
![](/i/fill.gif) |
|
![](/i/fill.gif) |
| ![](/i/fill.gif) |
| ![](/i/fill.gif) |
|
![](/i/fill.gif) |
|
![](/i/fill.gif) |
| ![](/i/fill.gif) |
| ![](/i/fill.gif) |
|
![](/i/fill.gif) |
>> How about drum memory? Or the various delay lines?
>
> Don't know, was before my time.
OK. So care is newer than either of those.
> I don't know very much about the actual electronics.
OK.
> Most really large files were on tape, you just read the data serially.
> For highly accessed files, or files that needed random access were kept on disk.
So the concept of a filesystem storing named files already existed at
this time?
> The file system for IBM mainframes are record oriented, not stream.
> Files are created with a defined record format and record length.
Interesting. So the system actually "knows" where each field of a record
is then?
>> What sort of access speeds do you get for reading or writing punched
>> card or tape?
>
> As I recall about 60 characters per second. The tape was paper, was 8 holes
> wide, and easily broken or scrunched.
Mmm, that's fairly fast for an optical system.
> On some of the older machines I worked with:
> 360/50 128KB
> 370/158 1MB
> 370/168 3MB
> 3033U 4MB
> 3081Q 8MB
> On the latest machine:
> z/9 BC S03 - 16GB
I should probably go plot that on a graph against date or something... ;-)
>> Nice consistent naming scheme. Heh. :-/
>
> You can always depend on IBM to be consistent.
Consistently inconsisten. ;-)
Still, some things never change:
nVidia GeForce 8xxx
nVidia GeForce 9xxx
nVidia GeForce 2xx <- WTH?
>> Now if I could figure out what a typical MIPS rating for a normal PC
>> today is, I'd have something dissimilar to compare it to. :-}
>
> It is rather difficult to compare since they have such different architectures.
Yes, that's what I meant by "dissimilar comparison". It all rather
depends on how many registers you have, how wide the various data busses
are, what operations you can perform in hardware (e.g., is
multiplication a hardware or software operation?), and so forth.
> I doubt that the internal processor speed is that much different than current
> PCs, but the i/o bandwidth is much higher in the mainframe.
Really? I didn't think anybody had mainframes any more... just big
server farms.
> For example our two machines, which are on the small side for mainframes, are
> connected to a disk storage unit containing 15TB of data. There are 4 high
> speed fiber optic channels from each processor to this unit. We can easily
> sustain i/o rates of over 10000 i/o operations per second, with peaks in the
> 20000 to 40000 range.
Sounds expensive.
> It is very rare for any single job to saturate the cpu.
> By running many jobs concurrently we make full use of the machine.
The *original* purpose of multitasking operating systems. ;-)
> If I could
> port POVRAY to our mainframe, I'm sure it would be slower than most current PCs.
> But cpu intensive work is not what the mainframe does best.
Out of curiosity, what *do* you use it for?
Post a reply to this message
|
![](/i/fill.gif) |
| ![](/i/fill.gif) |
| ![](/i/fill.gif) |
|
![](/i/fill.gif) |
|
![](/i/fill.gif) |
| ![](/i/fill.gif) |
| ![](/i/fill.gif) |
|
![](/i/fill.gif) |
> So the concept of a filesystem storing named files already existed at
> this time?
Yes, its been around long before I got into this business.
>
> Sounds expensive.
>
Its not cheap. But for the volume of data we process, its not that much more
expensive than a server farm
>
> Out of curiosity, what *do* you use it for?
All company information is kept on mainframe disks and maintained by mainframe
programs. All customer information, product information, personnel information,
sales information etc. This company started in the early 1900s selling its
merchandise from a store. Then expanding sales to mail order catalog, then via
telemarketing, and now by internet. The web front-end is handled by a small
server farm, but all back-end work is done on our mainframe.
Isaac
Post a reply to this message
|
![](/i/fill.gif) |
| ![](/i/fill.gif) |
| ![](/i/fill.gif) |
|
![](/i/fill.gif) |
|
![](/i/fill.gif) |
| ![](/i/fill.gif) |
| ![](/i/fill.gif) |
|
![](/i/fill.gif) |
Invisible wrote:
> Does anybody know approximately when this time was?
1970's. By about 1980 most of those machines were likely retired.
> For that matter, does anybody have a broad timeline of when various
> technologies were in use? What are the dates for things like core
> memory, drum memory, punch cards, magnetic tape, relays, vacuum tubes,
> transistors, ICs, etc?
Yes. Google.
> Was there ever a time when programs were entered into memory via
> switches rather than some other medium?
Yes.
http://en.wikipedia.org/wiki/Front_panel
The first personal computers worked that way.
http://en.wikipedia.org/wiki/Altair_8800
> Was there ever a "punched tape" medium similar to punch cards?
Yes. That's why DEL is up at 127. Think about it.
> Similarly, you hear people talk about the VAX, the PDP, the varouis IBM
> mainframes and Cray supercomputers. Does anybody know the timeline for
> these, the technologies used and the basic design and performance details?
http://en.wikipedia.org/wiki/Computer_history
> (Sure, you can look up individual questions on Wikipedia, but the
> articles tend to contain huge amounts of minute detail about specific
> things. I'm trying to get a general overview of an entire era.)
So you want someone else to read the 10 pages and summarize it into 10 lines
for you? You need a job in management.
--
Darren New, San Diego CA, USA (PST)
Ada - the programming language trying to avoid
you literally shooting yourself in the foot.
Post a reply to this message
|
![](/i/fill.gif) |
| ![](/i/fill.gif) |
| ![](/i/fill.gif) |
|
![](/i/fill.gif) |
|
![](/i/fill.gif) |
| ![](/i/fill.gif) |
| ![](/i/fill.gif) |
|
![](/i/fill.gif) |
scott wrote:
>>> We added 1MB of memory to an IBM 370/168 in the mid 70s. Price? $50000.
>>
>> Ouch! o_O
>>
>> It still somewhat blows my mind that you could do anything useful with
>> so little memory.
>
> You could do useful stuff with *far* less.
We ran an entire school district on 32K of RAM and 16M of online disk.
Core memory, so cycle time close to a milisecond, let alone nanosecond.
--
Darren New, San Diego CA, USA (PST)
Ada - the programming language trying to avoid
you literally shooting yourself in the foot.
Post a reply to this message
|
![](/i/fill.gif) |
| ![](/i/fill.gif) |
| ![](/i/fill.gif) |
|
![](/i/fill.gif) |
|
![](/i/fill.gif) |
| ![](/i/fill.gif) |
| ![](/i/fill.gif) |
|
![](/i/fill.gif) |
Invisible <voi### [at] dev null> wrote:
> Warp wrote:
> > Orchid XP v8 <voi### [at] dev null> wrote:
> >> Many hundred billion years ago, there existed a bizzare world that most
> >> of us have only read about in books. Plastics did not yet exist, so
> >> small children's toys were made of wood or metal, because there was
> >> literally nothing cheaper.
> >
> > There were no children many hundred billion years ago.
> I was waiting for that one... *sigh*
It's a so-called mathematician's answer.
--
- Warp
Post a reply to this message
|
![](/i/fill.gif) |
| ![](/i/fill.gif) |
| ![](/i/fill.gif) |
|
![](/i/fill.gif) |
|
![](/i/fill.gif) |
| ![](/i/fill.gif) |
| ![](/i/fill.gif) |
|
![](/i/fill.gif) |
Invisible wrote:
> So the concept of a filesystem storing named files already existed at
> this time?
Generally, yes. But you usually wound up pre-allocating files, and they were
contiguous on disk.
> Interesting. So the system actually "knows" where each field of a record
> is then?
Records were fixed size, so it was trivial to calculate.
>> I doubt that the internal processor speed is that much different than
>> current
>> PCs, but the i/o bandwidth is much higher in the mainframe.
>
> Really? I didn't think anybody had mainframes any more... just big
> server farms.
The people who want to do lots of I/O have machines where instead of GPUs
they have IOPs. A 800,000 line phone switch, for example, is pretty much
all IOP, with something like a 68000 running the actual switching part.
Of course, what one might call a "PC" nowadays has a terabyte of RAM and 96
quad-core processor chips, so the lines blur.
--
Darren New, San Diego CA, USA (PST)
Ada - the programming language trying to avoid
you literally shooting yourself in the foot.
Post a reply to this message
|
![](/i/fill.gif) |
| ![](/i/fill.gif) |
| ![](/i/fill.gif) |
|
![](/i/fill.gif) |
|
![](/i/fill.gif) |
| ![](/i/fill.gif) |
| ![](/i/fill.gif) |
|
![](/i/fill.gif) |
Invisible wrote:
> http://www.columbia.edu/acis/history/fisk.pdf
>
> Hmm, interesting. Some of the guys I went to uni with learned COBOL. All
> they could tell me about it is "if you miss out a dot, you get an error
> message 300 lines later". Sounds delightful...
It's more fun to spell the first word wrong. "Idnetification Division." Then
you get at least two error lines on each input line, or three if it's
actually a top-level statement.
--
Darren New, San Diego CA, USA (PST)
Ada - the programming language trying to avoid
you literally shooting yourself in the foot.
Post a reply to this message
|
![](/i/fill.gif) |
| ![](/i/fill.gif) |
| ![](/i/fill.gif) |
|
![](/i/fill.gif) |
|
![](/i/fill.gif) |
| ![](/i/fill.gif) |
| ![](/i/fill.gif) |
|
![](/i/fill.gif) |
Invisible escreveu:
>> The first computer I ever saw was in 1997 at Glasgow University. It
>> was an analogue machine that used valves.
>
> 1997? o_O
just in time for the first version of GHC... :-)
--
a game sig: http://tinyurl.com/d3rxz9
Post a reply to this message
|
![](/i/fill.gif) |
| ![](/i/fill.gif) |
| ![](/i/fill.gif) |
|
![](/i/fill.gif) |
|
![](/i/fill.gif) |
| ![](/i/fill.gif) |
| ![](/i/fill.gif) |
|
![](/i/fill.gif) |
Invisible escreveu:
>> We added 1MB of memory to an IBM 370/168 in the mid 70s. Price? $50000.
>
> Ouch! o_O
>
> It still somewhat blows my mind that you could do anything useful with
> so little memory. Presumably for processing large datasets, most of the
> data at any one time would be in secondary storage?
Large datasets then were also very tiny compared to large datasets of
today. :)
>> When I was at university in the mid to late 60s, I took a FORTRAN
>> programming
>> course. Punch program into cards, place in card tray, come back 4 to
>> 6 hours
>> later and pick up your card deck and output listing. Fix your typos
>> and bugs
>> and repeat the above process until the program works.
see the revolution that were programs like ed (and its successor vi) in
bringing flexible terminal text editing rather than wasting tons of
paper... :)
--
a game sig: http://tinyurl.com/d3rxz9
Post a reply to this message
|
![](/i/fill.gif) |
| ![](/i/fill.gif) |
| ![](/i/fill.gif) |
|
![](/i/fill.gif) |
|
![](/i/fill.gif) |
| ![](/i/fill.gif) |
| ![](/i/fill.gif) |
|
![](/i/fill.gif) |
Clarence1898 escreveu:
> All company information is kept on mainframe disks and maintained by mainframe
> programs. All customer information, product information, personnel information,
> sales information etc. This company started in the early 1900s selling its
> merchandise from a store. Then expanding sales to mail order catalog, then via
> telemarketing, and now by internet. The web front-end is handled by a small
> server farm, but all back-end work is done on our mainframe.
in other words: mainframes were never supercomputers. They were
commerce-oriented machines rather than scientific number-crunchers.
--
a game sig: http://tinyurl.com/d3rxz9
Post a reply to this message
|
![](/i/fill.gif) |
| ![](/i/fill.gif) |
| ![](/i/fill.gif) |
|
![](/i/fill.gif) |
|
![](/i/fill.gif) |
| ![](/i/fill.gif) |
|
![](/i/fill.gif) |