From mboxrd@z Thu Jan 1 00:00:00 1970 Path: news.gmane.org!not-for-mail From: Tom Tromey Newsgroups: gmane.emacs.devel Subject: Re: indirect threading for bytecode interpreter Date: Sun, 20 Sep 2009 21:17:10 -0600 Message-ID: References: <200909181915.n8IJFfw7006915@godzilla.ics.uci.edu> <200909210158.n8L1wr55000349@godzilla.ics.uci.edu> Reply-To: Tom Tromey NNTP-Posting-Host: lo.gmane.org Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii X-Trace: ger.gmane.org 1253503053 6608 80.91.229.12 (21 Sep 2009 03:17:33 GMT) X-Complaints-To: usenet@ger.gmane.org NNTP-Posting-Date: Mon, 21 Sep 2009 03:17:33 +0000 (UTC) Cc: Emacs development discussions To: Dan Nicolaescu Original-X-From: emacs-devel-bounces+ged-emacs-devel=m.gmane.org@gnu.org Mon Sep 21 05:17:26 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 1MpZP3-0003Dt-8m for ged-emacs-devel@m.gmane.org; Mon, 21 Sep 2009 05:17:25 +0200 Original-Received: from localhost ([127.0.0.1]:47747 helo=lists.gnu.org) by lists.gnu.org with esmtp (Exim 4.43) id 1MpZP2-0008HY-LB for ged-emacs-devel@m.gmane.org; Sun, 20 Sep 2009 23:17:24 -0400 Original-Received: from mailman by lists.gnu.org with tmda-scanned (Exim 4.43) id 1MpZOx-0008HT-L4 for emacs-devel@gnu.org; Sun, 20 Sep 2009 23:17:19 -0400 Original-Received: from exim by lists.gnu.org with spam-scanned (Exim 4.43) id 1MpZOs-0008HH-NR for emacs-devel@gnu.org; Sun, 20 Sep 2009 23:17:18 -0400 Original-Received: from [199.232.76.173] (port=52559 helo=monty-python.gnu.org) by lists.gnu.org with esmtp (Exim 4.43) id 1MpZOs-0008HE-Jm for emacs-devel@gnu.org; Sun, 20 Sep 2009 23:17:14 -0400 Original-Received: from mx1.redhat.com ([209.132.183.28]:64113) by monty-python.gnu.org with esmtp (Exim 4.60) (envelope-from ) id 1MpZOs-0008Eq-6b for emacs-devel@gnu.org; Sun, 20 Sep 2009 23:17:14 -0400 Original-Received: from int-mx02.intmail.prod.int.phx2.redhat.com (int-mx02.intmail.prod.int.phx2.redhat.com [10.5.11.12]) by mx1.redhat.com (8.13.8/8.13.8) with ESMTP id n8L3HDLf029312; Sun, 20 Sep 2009 23:17:13 -0400 Original-Received: from ns3.rdu.redhat.com (ns3.rdu.redhat.com [10.11.255.199]) by int-mx02.intmail.prod.int.phx2.redhat.com (8.13.8/8.13.8) with ESMTP id n8L3HC6p024403; Sun, 20 Sep 2009 23:17:12 -0400 Original-Received: from opsy.redhat.com (ovpn01.gateway.prod.ext.phx2.redhat.com [10.5.9.1]) by ns3.rdu.redhat.com (8.13.8/8.13.8) with ESMTP id n8L3HBWR026582; Sun, 20 Sep 2009 23:17:11 -0400 Original-Received: by opsy.redhat.com (Postfix, from userid 500) id CBEBA3782A4; Sun, 20 Sep 2009 21:17:10 -0600 (MDT) X-Attribution: Tom In-Reply-To: <200909210158.n8L1wr55000349@godzilla.ics.uci.edu> (Dan Nicolaescu's message of "Sun, 20 Sep 2009 18:58:53 -0700 (PDT)") User-Agent: Gnus/5.13 (Gnus v5.13) Emacs/23.1 (gnu/linux) X-Scanned-By: MIMEDefang 2.67 on 10.5.11.12 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:115489 Archived-At: >>>>> "Dan" == Dan Nicolaescu writes: Dan> Making the GC generational might help. The first GC after startup does Dan> 200K mark_object calls, so if most of those don't need to be scanned for Dan> each GC, then that might help. Yeah. Whatever happened to the Boehm GC branch? That seems like the simplest way to implement this feature. Dan> If you have a testcase that shows GC problems, maybe posting the test Dan> case would enticemore people look into it... Here's a script I've been running on the GDB sources: http://sourceware.org/ml/gdb-patches/2009-08/msg00390.html 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. Tom