From owner-freebsd-current@FreeBSD.ORG Wed Apr 5 00:34:05 2006 Return-Path: X-Original-To: current@freebsd.org Delivered-To: freebsd-current@FreeBSD.ORG Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 473D416A41F for ; Wed, 5 Apr 2006 00:34:05 +0000 (UTC) (envelope-from flag@longino.wired.org) Received: from mail.oltrelinux.com (krisma.oltrelinux.com [194.242.226.43]) by mx1.FreeBSD.org (Postfix) with ESMTP id 34CC743D53 for ; Wed, 5 Apr 2006 00:34:03 +0000 (GMT) (envelope-from flag@longino.wired.org) Received: from longino.wired.org (ip-114-46.sn1.eutelia.it [62.94.114.46]) (using TLSv1 with cipher DHE-RSA-AES256-SHA (256/256 bits)) (No client certificate requested) by mail.oltrelinux.com (Postfix) with ESMTP id C6E9B11B1FC; Wed, 5 Apr 2006 02:34:05 +0200 (CEST) Received: from longino.wired.org (localhost [127.0.0.1]) by longino.wired.org (8.13.4/8.13.4) with ESMTP id k350Y0xO083689; Wed, 5 Apr 2006 02:34:00 +0200 (CEST) (envelope-from flag@longino.wired.org) Received: (from flag@localhost) by longino.wired.org (8.13.4/8.13.4/Submit) id k350Xx8F083688; Wed, 5 Apr 2006 02:33:59 +0200 (CEST) (envelope-from flag) Date: Wed, 5 Apr 2006 02:33:58 +0200 From: Paolo Pisati To: current@freebsd.org Message-ID: <20060405003358.GA83600@tin.it> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline User-Agent: Mutt/1.4.2.1i X-Virus-Scanned: by amavisd-new-20030616-p10 (Debian) at krisma.oltrelinux.com Cc: Luigi Rizzo Subject: Interesting data on network interrupt - part II X-BeenThere: freebsd-current@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Discussions about the use of FreeBSD-current List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 05 Apr 2006 00:34:05 -0000 Hi, i updated my work on interrupt profiling with sone new experiments. In total we have now: -FreeBSD 4 PIC (no asm part) -FreeBSD 7 APIC -FreeBSD 7 PIC -FreeBSD 7 PREE APIC -FreeBSD 7 APIC JHB Some quick comments: -PIC is much slower in masking interrupt (7k in PIC vs 3k in APIC) -PREE let new thread save less than 500 ticks of 'queue' while preempted threads are often resumed after a lot -JHB patch shaved 2.5k ticks in interrupt masking op For graphs, data and more comments: http://mercurio.sm.dsi.unimi.it/~pisati/interrupt/ bye -- Paolo "le influenze esterne sono troppe, il mondo reale non e' mica quello fatato dei komunisti :-p" - Anonymous Lumbard