Re: What I suspect

Linus Torvalds (torvalds@transmeta.com)
Wed, 8 Dec 1999 09:12:05 -0800 (PST)


On Wed, 8 Dec 1999, Rogier Wolff wrote:
>
> There would be two different pages mapped: One with process-centered
> info. pid, ppid, ruid, euid, fsuid, rgid, egid, pgid?, pgrp?, rlimit?
> rusage, sid?, priority_max, times. Some of these are not static, and
> the "rest of the kernel" will have to be modified to maintain these
> parameters "in place" on the page that the program has read-access to.

No. This is what many UNIXes have done, and it sucks raw eggs through a
straw.

The problem is threads. Many of the above things are thread-specific, and
you MUST NOT have different pages mapped in different threads, because
that messes up the whole idea of threads (suddenly you cannot share
the same page tables in an SMP environment etc)

> The other would be one with system info: hostname, domainname, time
> etc etc (I'm too lazy right now to run through the whole list of
> syscalls again.)

gettimeofday() is a great example of global state that really =is=
timing-critical. But very little else is (nobody _really_ cares whether it
takes 50 cycles or 2 microseconds to get the hostname)

Linus

-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/