Date: Sun, 8 Oct 2000 15:30:57 -0700 From: Kris Kennaway <kris@citusc.usc.edu> To: Matt Dillon <dillon@earth.backplane.com> Cc: Terry Lambert <tlambert@primenet.com>, Bruce Evans <bde@zeta.org.au>, Peter Wemm <peter@netplex.com.au>, Chuck Paterson <cp@bsdi.com>, Alfred Perlstein <bright@wintelcom.net>, John Baldwin <jhb@FreeBSD.ORG>, arch@FreeBSD.ORG, John Polstra <jdp@polstra.com>, Daniel Eischen <eischen@vigrid.com>, Greg Lehey <grog@lemis.com> Subject: Re: Mutexes and semaphores Message-ID: <20001008153057.A35887@citusc17.usc.edu> In-Reply-To: <200010050722.e957MbF33401@earth.backplane.com>; from dillon@earth.backplane.com on Thu, Oct 05, 2000 at 12:22:37AM -0700 References: <200010050458.VAA07440@usr07.primenet.com> <200010050722.e957MbF33401@earth.backplane.com>
next in thread | previous in thread | raw e-mail | index | archive | help
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
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20001008153057.A35887>