Subject: Re: Floating point in the kernel
To: Jason Thorpe <thorpej@nas.nasa.gov>
From: Curt Sampson <cjs@portal.ca>
List: tech-kern
Date: 09/18/1998 15:38:30
On Fri, 18 Sep 1998, Jason Thorpe wrote:
> > It sounds to me as if we're going the wrong direction for this,
> > and what we really want is some way to give the userland process
> > enough priority that it's going to get the time it needs even on
> > a heavily loaded system.
>
> You mean, like POSIX real-time scheduling?
I don't know, because I don't know enough about real-time scheduling.
What I envisioned is something fairly simple that would be easy to
implement. This probably means no sophisticated negotiation of
priorities or guarantees of access to the CPU. We'd need some sort
of basic protection to keep a process from eating up so much of
the CPU that you can never get on to the machine to kill it, though.
cjs
--
Curt Sampson <cjs@portal.ca> 604-257-9400 De gustibus, aut bene aut nihil.
Any opinions expressed are mine and mine alone.
The most widely ported operating system in the world: http://www.netbsd.org