This is the mail archive of the
libc-alpha@sourceware.org
mailing list for the glibc project.
Re: [PATCH] Fix dwarf2 unwinding through futex functions
- From: Andi Kleen <andi at firstfloor dot org>
- To: Roland McGrath <roland at hack dot frob dot com>
- Cc: libc-alpha at sourceware dot org
- Date: Sat, 19 Oct 2013 16:36:09 -0700
- Subject: Re: [PATCH] Fix dwarf2 unwinding through futex functions
- Authentication-results: sourceware.org; auth=none
- References: <1378770227-13849-1-git-send-email-andi at firstfloor dot org> <20131007225741 dot GF3363 at tassilo dot jf dot intel dot com> <20131007232243 dot 713F32C067 at topped-with-meat dot com> <20131007234407 dot GG3363 at tassilo dot jf dot intel dot com> <20131008002827 dot GN6882 at two dot firstfloor dot org>
Andi Kleen <andi@firstfloor.org> writes:
> So I ran some benchmarks: just doing an empty lock with:
>
> no icache pollution
> artificial icache pollution
> articicial icache and branch prediction pollution
>
> comparing the new locks with the old locks.
>
> No difference outside run-to-run variability in either case.
Just as a reminder, these patches are still awaiting review.
If you are not interested in supporting unwinding in pthread
please let me know.
-Andi
--
ak@linux.intel.com -- Speaking for myself only