Path: utzoo!utgpu!news-server.csri.toronto.edu!mailrus!uwm.edu!zaphod.mps.ohio-state.edu!sdd.hp.com!hplabs!hpda!hpcuhb!hpcllla!hpclisp!hpcljms!brians
From: brians@hpcljms.HP.COM (Brian Sullivan)
Newsgroups: comp.lang.misc
Subject: Re: UNIX semantics do permit full support for asynchronous I/O
Message-ID: <960022@hpcljms.HP.COM>
Date: 30 Aug 90 22:54:31 GMT
References: <27619@nuchat.UUCP>
Organization: Hewlett-Packard Calif. Language Lab
Lines: 21

> Have read(2) and write(2) calls map the pages containing the buffers
> out of the user address space and return immediately.  Once the
> data have been copied (DMAed?) to/from the buffers, map the pages back in.

  Well,  I suspect that this solution will not work with most C programs.
Why, because most of the time read(2) and write(2) are called with a
buffer that is an auto-variable or stack allocated.  Telling the MMU to
unmap a page in the users stack will have very dire consequences.  Maybe
a better idea would be a new memory allocation, combined with new read(2)
and write(2) calls.  Using this method the need to copy the users data
would be solved.

   kalloc :  allocate pages in kernal memory
   kwrite :  perform write without copying memory into kernal data area
   kread  :  perform read without copying memory into kernal data area


  You might want to investigate the POSIX working group P1003.4 which
deals with real-time issues.  They are creating the next generation
UNIX standard that will support threads, async_io, real-time scheduling
and other real-time issues.