Path: utzoo!utgpu!cunews!bnrgate!brtph3!brchh104!brchs1!bnr.ca!rice.edu!sun-spots-request
From: jeffv@bisco.kodak.com (Jeff Van Epps)
Newsgroups: comp.sys.sun
Subject: Memory-mapped gettimeofday(2)?
Keywords: Miscellaneous
Message-ID: <1639@brchh104.bnr.ca>
Date: 13 Feb 91 22:03:00 GMT
Sender: news@brchh104.bnr.ca
Organization: Sun-Spots
Lines: 12
Approved: Sun-Spots@rice.edu
X-Original-Date: Thu, 7 Feb 91 15:29:01 GMT
X-Sun-Spots-Digest: Volume 10, Issue 39, message 5
X-Note: Submissions: sun-spots@rice.edu, Admin: sun-spots-request@rice.edu

It seems to me that Sun has been emphasizing memory mapping as a way to
solve problems lately, so I got to wondering whether certain system calls
had been or could be implemented as accesses in a page of memory which
every process can read but only the kernel can write.  So that something
like gettimeofday() would be only a fetch from memory vs.  the normal
trap/syscall overhead (and possibly blocking??).  I confess to not having
any numbers, so perhaps someone else can tell me that this is a non-issue?

Just a dreamy break from my more mundane Sun questions ;-)

    Jeff Van Epps          jeffv@bisco.kodak.com
                           rochester!kodak!bisco!jeffv