Date: Wed, 12 Aug 2009 14:47:19 +0100 (BST) From: Robert Watson <rwatson@FreeBSD.org> To: Mike Tancsa <mike@sentex.net> Cc: current@freebsd.org Subject: Re: Call for regression and performance testing - 8.0 Message-ID: <alpine.BSF.2.00.0908121444030.17186@fledge.watson.org> In-Reply-To: <200908121335.n7CDZZcg047419@lava.sentex.ca> References: <alpine.BSF.2.00.0908121329130.66335@fledge.watson.org> <200908121335.n7CDZZcg047419@lava.sentex.ca>
next in thread | previous in thread | raw e-mail | index | archive | help
On Wed, 12 Aug 2009, Mike Tancsa wrote:
>> As we're approaching 8.0 BETA3, now would be a really good time to start
>> identifying functional and performance regressions from the 7.x series.
>> We've done a mixed job at this in the past, but when it comes to "I'll do
>> better some day", there's no time like the present :-). Some notes:
>
> Other than the removal of whats below from the kernel, what other
> adjustments should be made to make more accurate comparisons ?
The main thing I'm aware of is malloc debugging in userspace -- the best way
to do this is to uncomment MALLOC_PRODUCTION in src/lib/libc/stdlib/malloc.c:
/*
* MALLOC_PRODUCTION disables assertions and statistics gathering. It also
* defaults the A and J runtime options to off. These settings are appropriate
* for production systems.
*/
/* #define MALLOC_PRODUCTION */
You can also manually disable many of the debugging features in malloc(3)
using malloc.conf -- however, it looks to me like some things, such as magic
number checking, etc, are basically a compile time-only configuration option,
so I'd encourage using MALLOC_PRODUCTION instead.
Robert N M Watson
Computer Laboratory
University of Cambridge
>
> # Debugging for use in -current
> options KDB # Enable kernel debugger support.
> options DDB # Support DDB.
> options GDB # Support remote GDB.
> options INVARIANTS # Enable calls of extra sanity
> checking
> options INVARIANT_SUPPORT # Extra sanity checks of internal
> structures, required by INVARIANTS
> options WITNESS # Enable checks to detect deadlocks
> and cycles
> options WITNESS_SKIPSPIN # Don't run witness on spinlocks for
> speed
>
> ---Mike
>
>
>
> --------------------------------------------------------------------
> Mike Tancsa, tel +1 519 651 3400
> Sentex Communications, mike@sentex.net
> Providing Internet since 1994 www.sentex.net
> Cambridge, Ontario Canada www.sentex.net/mike
>
>
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?alpine.BSF.2.00.0908121444030.17186>