Re: Is MTX_CONTESTED evil?

From: Kris Kennaway (kris_at_obsecurity.org)
Date: 03/27/04

  • Next message: Albert Cahalan: "Re: posix ps (was Re: Adding `pgrep' and `pkill' to /usr/bin)" 
    Date: Fri, 26 Mar 2004 15:16:35 -0800
To: John Baldwin <jhb@freebsd.org>

    On Fri, Mar 26, 2004 at 02:04:57PM -0500, John Baldwin wrote:
    > On Friday 26 March 2004 01:37 pm, M. Warner Losh wrote:
    > > In message: <xzpekrgf103.fsf@dwp.des.no>
    > >
    > > des@des.no (Dag-Erling Sm?rgrav) writes:
    > > : "Brian F. Feldman" <green@FreeBSD.org> writes:
    > > : > Well, that certainly explains the blitz of crashes I had to fix
    > > : > recently! Since INVARIANTS and WITNESS are on by default, it would
    > > : > make sense to make ADAPTIVE_MUTEX default to catch more bugs.
    > > :
    > > : Making ADAPTIVE_MUTEXES default will not catch more bugs, it will just
    > > : piss off users.
    > >
    > > I think that if we don't fix the class of bugs that AM points out,
    > > we'll ruin our reputation as a quality system in the long run. Maybe
    > > they are so pervasive that we don't want to turn it on by default just
    > > yet, but there will come a time we turn it on, just like we turned on
    > > WITNESS and INVARIANTS to get better coverage on our testing.
    >
    > Right, let's not just gratuitously break everyone right yet. It's actually an
    > option largely b/c I want us to be able to benchmark it once our locking is
    > farther along to see if it helps more than it hurts.

    FYI, I'm going to run with this on the bento cluster for a bit to dig
    out some of these bugs.

    Kris

  • Next message: Albert Cahalan: "Re: posix ps (was Re: Adding `pgrep' and `pkill' to /usr/bin)"