[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20060930204900.GA576@elte.hu>
Date: Sat, 30 Sep 2006 22:49:00 +0200
From: Ingo Molnar <mingo@...e.hu>
To: Linus Torvalds <torvalds@...l.org>
Cc: Andi Kleen <ak@...e.de>, Eric Rannaud <eric.rannaud@...il.com>,
Linux Kernel Mailing List <linux-kernel@...r.kernel.org>,
Andrew Morton <akpm@...l.org>, nagar@...son.ibm.com,
Chandra Seetharaman <sekharan@...ibm.com>,
Jan Beulich <jbeulich@...ell.com>
Subject: Re: BUG-lockdep and freeze (was: Arrr! Linux 2.6.18)
* Linus Torvalds <torvalds@...l.org> wrote:
> I mean, really: Andi, point me to anything that was a real problem
> when we had no unwinder at all?
personally, i like perfect stacktraces, alot. x86_64 was a huge pain for
me without the unwinder. I got so used to perfect backtraces on i686
(when using %ebp frames) during the years, and i had to look at _many_
backtraces with lockdep. On x86_64 it was just constant brain-drain to
think away bogus stack entries. Yes, i can do it no problem when i have
to look at only a few stacktraces per day, but if it's hundreds per day
it's _alot_ of brainpower wasted.
(i'd have been happy with an %rbp based unwinder for x86_64, in fact i
implemented it for lockdep and used it for some time on x86_64, but Andi
wanted a dwarf-based, lower-overhead one. Andi also nicely integrated it
into stacktrace.c.)
Ingo
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists