Subject: Re: Considering port to new processor
To: Erik E. Fair <email@example.com>
From: Jonathan Stone <jonathan@DSG.Stanford.EDU>
Date: 03/30/2001 16:14:18
In message <firstname.lastname@example.org>"Erik E. Fair" writes:
>There was a time when UNIX did not page - it swapped. Processes were
>either all the way in RAM, or not there at all - no "pages" at all.
>On that sort of system, there is no need to support restartable
>instructions for page faults.
Yep. But these days "Unix" includes forget mmap(), copy-on-write
semantics, and other address-space-sharing mechanisms which, in
general, are not implementable using swapping.
(c.f. Minix on the 8086, or Mini-Unix on PDP-11/10s.)