Re: CONUNDRUM.

Richard B. Johnson (root@analogic.com)
Wed, 12 Feb 1997 16:30:34 -0500 (EST)


On Wed, 12 Feb 1997, A.N.Kuznetsov wrote:

> Hello!
>
> I'd like to propose a funny conundrum.
>
> History.
[SNIPPED for brevity]
> Alexey Kuznetsov.
>
You just answered your own question! You are using the Pentium Cycle timer.
This counts everything, including the kernel's context-switches, updating
the jiffies timer, time-clock, etc., plus dumping ethernet broadcast
messages out onto the floor, etc, etc. There is a lot of activity going
on when a program is being run on a multi-tasker.

A bare-bones MS-DOS machine will have very little overhead. Only the
BIOS timer gets bumped 18.206 times per second and there's very little
interrupt code to do that! You get to use nearly 100% of the CPU under
MS-DOS.

Windows-95 certainly has more activity than MS-DOS. I question whether
a MS-DOS application gets nearly as much CPU time under windows as
a user application gets under Linux.

Cheers,
Dick Johnson
-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-
Richard B. Johnson
Project Engineer
Analogic Corporation
Voice : (508) 977-3000 ext. 3754
Fax : (508) 532-6097
Modem : (508) 977-6870
Ftp : ftp@boneserver.analogic.com
Email : rjohnson@analogic.com, johnson@analogic.com
Penguin : Linux version 2.1.26 on an i586 machine (66.15 BogoMips).
Warning : It's hard to remain at the trailing edge of technology.
-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-