From owner-freebsd-arch Sun Oct 8 15:30:49 2000 Delivered-To: freebsd-arch@freebsd.org Received: from citusc17.usc.edu (citusc17.usc.edu [128.125.38.177]) by hub.freebsd.org (Postfix) with ESMTP id 307F937B503; Sun, 8 Oct 2000 15:30:48 -0700 (PDT) Received: (from kris@localhost) by citusc17.usc.edu (8.9.3/8.9.3) id PAA35913; Sun, 8 Oct 2000 15:30:57 -0700 (PDT) Date: Sun, 8 Oct 2000 15:30:57 -0700 From: Kris Kennaway To: Matt Dillon Cc: Terry Lambert , Bruce Evans , Peter Wemm , Chuck Paterson , Alfred Perlstein , John Baldwin , arch@FreeBSD.ORG, John Polstra , Daniel Eischen , Greg Lehey Subject: Re: Mutexes and semaphores Message-ID: <20001008153057.A35887@citusc17.usc.edu> References: <200010050458.VAA07440@usr07.primenet.com> <200010050722.e957MbF33401@earth.backplane.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline User-Agent: Mutt/1.2.5i In-Reply-To: <200010050722.e957MbF33401@earth.backplane.com>; from dillon@earth.backplane.com on Thu, Oct 05, 2000 at 12:22:37AM -0700 Sender: owner-freebsd-arch@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.ORG On Thu, Oct 05, 2000 at 12:22:37AM -0700, Matt Dillon wrote: > Who gives a fart about getpid() ... now time() is a function that > would benefit greatly from a globally shared userland read-only page! Unfortunately it's fairly often used in benchmarks against "that penguin thing" as a "null" syscall. I've even seen one benchmark which used getpid() to claim zero scaling of syscall latency with increasing process load under Linux compared to a more physically possible linear scaling under FreeBSD. Older versions used to cache the pid in userland, I think, but they removed that when they added their kernel threads stuff. I don't know if it's treated specially in the SMP case, but it sounds like the kind of thing they would do to try and win benchmarks. Kris To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-arch" in the body of the message