Path: utzoo!attcan!uunet!know!news.cs.indiana.edu!iuvax!bomgard
From: bomgard@iuvax.cs.indiana.edu (Tim Bomgardner)
Newsgroups: comp.os.msdos.programmer
Subject: Re: Increasing #task switches per second (> 18.2), help
Message-ID: <78060@iuvax.cs.indiana.edu>
Date: 13 Dec 90 19:25:10 GMT
References: <4348@dnlunx.pttrnl.nl> <31600011@hpcvra.cv.hp.com.CV.HP.COM>
Organization: Indiana University, Bloomington
Lines: 35

In article <31600011@hpcvra.cv.hp.com.CV.HP.COM> everett@hpcvra.cv.hp.com.CV.HP.COM (Everett Kaser) writes:
}/ levericw@cheetah.ece.clarkson.edu (Walden Leverich) writes...
} > bomgard@iuvax.cs.indiana.edu (Tim Bomgardner) writes:
}>Tim> filetp@dnlunx.pttrnl.nl (Peter Filet) writes:
}>Tim> >I am developing an Operating System, in the Protected Mode of the i286
}>Tim> >processor.
}>Tim> > (wants a faster system clock)
}
}>Tim> want, say, a 4X clock rate (72.8/sec), you call the original handler every
}>Tim> fourth tick.  The rest of the OS has no idea anything has
}>Tim> changed.....
}
}>Very interesting. But wrong.  Considering that your interrupt timer
}>will be called once every 1/18.2 seconds. Now if your pass that tick
}>onto the OS every fouth time, then the OS gets 1/4 of the clock *NOT*
}>4X the clock.
}
}It WILL work,  what was left out of the explanation is this:  after you take
}over the interrupt vector, you have to reprogram the timer to interrupt
}4 times as often.  THEN, you only pass every fourth one on to the regular
}interrupt service routine, maintaining the original frequency for the original
}interrupt service routine, but quadrupling the frequency for yourself.
}
My apologies for leaving out this critical bit of information.  The 8254
counter is easily programmed for the desired clock rate, 72.8/sec in this
example.

}>Tim> Academic types can usually tell you why you can't do something.
}>Tim> Commercial software developers can usually tell you how to do it
}>Tim> anyway :)
}
}>Academic types in the CompEng field will explain why it is impossible.
}

Like I said...  :)