From owner-freebsd-current@FreeBSD.ORG Sat Mar 12 08:05:15 2005 Return-Path: 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 EFFF016A4DA for ; Sat, 12 Mar 2005 08:05:06 +0000 (GMT) Received: from salmon.maths.tcd.ie (salmon.maths.tcd.ie [134.226.81.11]) by mx1.FreeBSD.org (Postfix) with SMTP id 92D3F43D5F for ; Sat, 12 Mar 2005 08:05:05 +0000 (GMT) (envelope-from dwmalone@maths.tcd.ie) Date: Sat, 12 Mar 2005 08:05:03 +0000 From: David Malone To: Daniel Eriksson Message-ID: <20050312080503.GA99089@salmon.maths.tcd.ie> References: Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: User-Agent: Mutt/1.5.6i Sender: dwmalone@maths.tcd.ie cc: 'FreeBSD Current' Subject: Re: Higher interrupt rate after recent SMP/APIC timer changes? X-BeenThere: freebsd-current@freebsd.org X-Mailman-Version: 2.1.1 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: Sat, 12 Mar 2005 08:05:16 -0000 On Fri, Mar 11, 2005 at 11:51:40PM +0100, Daniel Eriksson wrote: > This is an SMP box (dual AMD AthlonMP) running with HZ=2000 and POLLING > enabled. Should I worry about the 4k intr/sec reported for lapic0 and > lapic1, or is this the way things should be? I believe this is what you should expect. The when using the lapic for timers, the lapic is programmed to interrupt at HZ*2 and then other timers are generated. See the commit messages for version 1.14 and 1.13 at: http://www.freebsd.org/cgi/cvsweb.cgi/src/sys/i386/i386/local_apic.c for more details. (There is also one lapic per processor - previously one timer interrupt would happen and then the processer that handeled that interrupt would have to forward it to other processors.) David.