>> The only problem with that, of course, is that paging is controlled by
>> the operating system, not by a user-level application program.
>
> Yes, of course. That's also why virtual machines are mind-bogglingly
> slow and/or rely on specially patched OSes. Rrrright.
>
> Andy, wake up.

You say that, but last time I tried to do virtualisation on Linux, it 
/did/ actually require loading a special kernel module. (Which is 
presumably why it didn't work when I tried it...)

No idea how it works in Windows.

Post a reply to this message

On 8/12/2012 13:35, Orchid Win7 v1 wrote:
> The only problem with that, of course, is that paging is controlled by the
> operating system, not by a user-level application program.

Not in this system. I believe Linux now has a hack in it that lets you get 
first dibs on page faults.

> And you're claiming you had 100x more than that IN RAM? Somehow, I doubt it.

Yep. And the room the box was in was full of mainframes, including three 
tape carousels that held 2.5TB each. You've just never worked for a company 
with enough money to buy stuff.

-- 
Darren New, San Diego CA, USA (PST)
   "Oh no! We're out of code juice!"
   "Don't panic. There's beans and filters
    in the cabinet."

Post a reply to this message

On 13/08/2012 03:54 PM, Darren New wrote:
> On 8/12/2012 13:35, Orchid Win7 v1 wrote:
>> The only problem with that, of course, is that paging is controlled by
>> the
>> operating system, not by a user-level application program.
>
> Not in this system. I believe Linux now has a hack in it that lets you
> get first dibs on page faults.

Hmm, OK.

>> And you're claiming you had 100x more than that IN RAM? Somehow, I
>> doubt it.
>
> Yep. And the room the box was in was full of mainframes, including three
> tape carousels that held 2.5TB each. You've just never worked for a
> company with enough money to buy stuff.

So you're saying that the fact that British Telecom plc could only 
afford 25.2GB of spinning disk for a mission-critical system means that 
they're "not big enough" to play with the Big Boys? :-P

Post a reply to this message

Am 13.08.2012 18:09, schrieb Orchid Win7 v1:

> So you're saying that the fact that British Telecom plc could only
> afford 25.2GB of spinning disk for a mission-critical system means that
> they're "not big enough" to play with the Big Boys? :-P

Heck, maybe they didn't need more.

Post a reply to this message

On 8/13/2012 9:09, Orchid Win7 v1 wrote:
> So you're saying that the fact that British Telecom plc could only afford
> 25.2GB of spinning disk for a mission-critical system means that they're
> "not big enough" to play with the Big Boys? :-P

I don't know. AT&T had five major databases (and bunches of minor ones) the 
smallest of which was 300TB.

EDS (the mainframe room I'm talking about) processes pretty much every 
credit card in the USA and many internationally. So, yes.

How many power companies did BT get their power from? Was it 
mission-critical enough that if one of the power plants exploded, they'd 
still be online?

-- 
Darren New, San Diego CA, USA (PST)
   "Oh no! We're out of code juice!"
   "Don't panic. There's beans and filters
    in the cabinet."

Post a reply to this message

>> So you're saying that the fact that British Telecom plc could only afford
>> 25.2GB of spinning disk for a mission-critical system means that they're
>> "not big enough" to play with the Big Boys? :-P

> How many power companies did BT get their power from? Was it
> mission-critical enough that if one of the power plants exploded, they'd
> still be online?

It wasn't /that/ mission-critical. It was only their fault-reporting 
database, not one of the actual call routine systems or anything like that.

Still, if it's as trivial as you claim to have multiple TB of RAM back 
in 1995, why didn't they do that?

Post a reply to this message

Am 14.08.2012 10:35, schrieb Invisible:
>>> So you're saying that the fact that British Telecom plc could only
>>> afford
>>> 25.2GB of spinning disk for a mission-critical system means that they're
>>> "not big enough" to play with the Big Boys? :-P
>
>> How many power companies did BT get their power from? Was it
>> mission-critical enough that if one of the power plants exploded, they'd
>> still be online?
>
> It wasn't /that/ mission-critical. It was only their fault-reporting
> database, not one of the actual call routine systems or anything like that.
>
> Still, if it's as trivial as you claim to have multiple TB of RAM back
> in 1995, why didn't they do that?

The claim was about hundreds of GB, not TB. It sure as hell wasn't 
available for a dollar and a dime. But it was /possible/ and could be 
obtained... for money.

Why on earth would a company (or government-funded institution for that 
matter) spend even a single /penny/ to pimp their equipment beyond what 
they actually /need/?

Post a reply to this message

Le 2012-08-14 04:35, Invisible a écrit :
>>> So you're saying that the fact that British Telecom plc could only
>>> afford
>>> 25.2GB of spinning disk for a mission-critical system means that they're
>>> "not big enough" to play with the Big Boys? :-P
>
>> How many power companies did BT get their power from? Was it
>> mission-critical enough that if one of the power plants exploded, they'd
>> still be online?
>
> It wasn't /that/ mission-critical. It was only their fault-reporting
> database, not one of the actual call routine systems or anything like that.
>
> Still, if it's as trivial as you claim to have multiple TB of RAM back
> in 1995, why didn't they do that?

Because they didn't need to.

If their fault reporting system was able to run just fine on a system 
using 1 raid array of 4GB disks, there was no need to have it run on a 
more powerful system. (Side note:  the PC I bought in 99 had a 20GB HD, 
so those 4.2GB disks were probably already a few years old.)

Also, 128GB is not multiple TB.

-- 
/*Francois Labreque*/#local a=x+y;#local b=x+a;#local c=a+b;#macro P(F//
/*    flabreque    */L)polygon{5,F,F+z,L+z,L,F pigment{rgb 9}}#end union
/*        @        */{P(0,a)P(a,b)P(b,c)P(2*a,2*b)P(2*b,b+c)P(b+c,<2,3>)
/*   gmail.com     */}camera{orthographic location<6,1.25,-6>look_at a }

Post a reply to this message

On Tue, 14 Aug 2012 09:35:48 +0100, Invisible wrote:

> Still, if it's as trivial as you claim to have multiple TB of RAM back
> in 1995, why didn't they do that?

I don't think anyone said it was "trivial" - just "possible".

Neither of those implies "cheap" or "desirable in all circumstances" 
either.

Jim

Post a reply to this message

>> Still, if it's as trivial as you claim to have multiple TB of RAM back
>> in 1995, why didn't they do that?
>
> I don't think anyone said it was "trivial" - just "possible".
>
> Neither of those implies "cheap" or "desirable in all circumstances"
> either.

I said "why would you want a 140GB heap when it's impossible to have 
that much RAM?"

And everyone was like "OMG, are you kidding? Of COURSE you can have 
hundreds of GB of RAM. EVERYBODY does this ALL THE TIME for EVERYTHING! 
If your company doesn't do this then they're just being cheap."

Post a reply to this message