From mboxrd@z Thu Jan 1 00:00:00 1970 Path: news.gmane.org!not-for-mail From: Stefan Monnier Newsgroups: gmane.emacs.devel Subject: Re: indirect threading for bytecode interpreter Date: Mon, 21 Sep 2009 10:46:09 -0400 Message-ID: References: <200909181915.n8IJFfw7006915@godzilla.ics.uci.edu> <200909210158.n8L1wr55000349@godzilla.ics.uci.edu> <87vdjcv3fe.fsf@lola.goethe.zz> NNTP-Posting-Host: lo.gmane.org Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii X-Trace: ger.gmane.org 1253544395 23849 80.91.229.12 (21 Sep 2009 14:46:35 GMT) X-Complaints-To: usenet@ger.gmane.org NNTP-Posting-Date: Mon, 21 Sep 2009 14:46:35 +0000 (UTC) Cc: emacs-devel@gnu.org To: David Kastrup Original-X-From: emacs-devel-bounces+ged-emacs-devel=m.gmane.org@gnu.org Mon Sep 21 16:46:28 2009 Return-path: Envelope-to: ged-emacs-devel@m.gmane.org Original-Received: from lists.gnu.org ([199.232.76.165]) by lo.gmane.org with esmtp (Exim 4.50) id 1Mpk9q-0002lD-9z for ged-emacs-devel@m.gmane.org; Mon, 21 Sep 2009 16:46:26 +0200 Original-Received: from localhost ([127.0.0.1]:57833 helo=lists.gnu.org) by lists.gnu.org with esmtp (Exim 4.43) id 1Mpk9o-0005mF-QH for ged-emacs-devel@m.gmane.org; Mon, 21 Sep 2009 10:46:24 -0400 Original-Received: from mailman by lists.gnu.org with tmda-scanned (Exim 4.43) id 1Mpk9i-0005lw-UK for emacs-devel@gnu.org; Mon, 21 Sep 2009 10:46:18 -0400 Original-Received: from exim by lists.gnu.org with spam-scanned (Exim 4.43) id 1Mpk9e-0005lU-2R for emacs-devel@gnu.org; Mon, 21 Sep 2009 10:46:18 -0400 Original-Received: from [199.232.76.173] (port=48516 helo=monty-python.gnu.org) by lists.gnu.org with esmtp (Exim 4.43) id 1Mpk9d-0005lR-V6 for emacs-devel@gnu.org; Mon, 21 Sep 2009 10:46:13 -0400 Original-Received: from ironport2-out.teksavvy.com ([206.248.154.183]:34979 helo=ironport2-out.pppoe.ca) by monty-python.gnu.org with esmtp (Exim 4.60) (envelope-from ) id 1Mpk9a-0007UU-U3; Mon, 21 Sep 2009 10:46:11 -0400 X-IronPort-Anti-Spam-Filtered: true X-IronPort-Anti-Spam-Result: AgUFAA4ut0pFxKcP/2dsb2JhbACBU9EBhBsFh34 X-IronPort-AV: E=Sophos;i="4.44,424,1249272000"; d="scan'208";a="46199508" Original-Received: from 69-196-167-15.dsl.teksavvy.com (HELO pastel.home) ([69.196.167.15]) by ironport2-out.pppoe.ca with ESMTP; 21 Sep 2009 10:46:09 -0400 Original-Received: by pastel.home (Postfix, from userid 20848) id 51FED8079; Mon, 21 Sep 2009 10:46:09 -0400 (EDT) In-Reply-To: <87vdjcv3fe.fsf@lola.goethe.zz> (David Kastrup's message of "Mon, 21 Sep 2009 15:21:41 +0200") User-Agent: Gnus/5.13 (Gnus v5.13) Emacs/23.1.50 (gnu/linux) X-detected-operating-system: by monty-python.gnu.org: Genre and OS details not recognized. X-BeenThere: emacs-devel@gnu.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: "Emacs development discussions." List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Original-Sender: emacs-devel-bounces+ged-emacs-devel=m.gmane.org@gnu.org Errors-To: emacs-devel-bounces+ged-emacs-devel=m.gmane.org@gnu.org Xref: news.gmane.org gmane.emacs.devel:115496 Archived-At: >>> I've profiled (using oprofile) Emacs running this a few times; >>> typical results show mark_object at 10-12% of runtime. It is >>> probably pretty easy to reproduce this with a variety of elisp >>> programs. >> So no matter how hard we try, we won't gain more than about 10% >> speed-up trying to optimize the GC. Doesn't sound like a great >> motivator. > The 10% occur in bursts of unresponsiveness. If such a burst is halved > in size, the total runtime improvement will not be impressive, but the > responsiveness gets quite better. That is true. To help solve this, we should aim to move towards a concurrent GC (i.e. a GC that's actually likely to be slower, but won't cause unresponsiveness). Stefan