From owner-freebsd-current@FreeBSD.ORG Fri Mar 12 11:12:44 2004 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 8C41716A4CE for ; Fri, 12 Mar 2004 11:12:44 -0800 (PST) Received: from mailhub1.midco.net (mailhub1.midco.net [24.220.0.32]) by mx1.FreeBSD.org (Postfix) with ESMTP id 2505543D1D for ; Fri, 12 Mar 2004 11:12:44 -0800 (PST) (envelope-from pmes@bis.midco.net) Received: (qmail 1995 invoked by uid 0); 12 Mar 2004 19:12:43 -0000 Received: from host-195-219-220-24.midco.net (HELO bis.midco.net) ([24.220.219.195]) (envelope-sender ) by lvs-pop.midco.net (qmail-ldap-1.03) with SMTP for ; 12 Mar 2004 19:12:43 -0000 Message-ID: <40520BA9.4080502@bis.midco.net> Date: Fri, 12 Mar 2004 13:12:41 -0600 From: Peter Schultz User-Agent: Mozilla/5.0 (X11; U; FreeBSD i386; en-US; rv:1.7a) Gecko/20040308 X-Accept-Language: en-us, en MIME-Version: 1.0 To: Taku YAMAMOTO References: <4050BBCB.50302@cinci.rr.com> <20040312092348.18be60e0.taku@cent.saitama-u.ac.jp> In-Reply-To: <20040312092348.18be60e0.taku@cent.saitama-u.ac.jp> Content-Type: text/plain; charset=us-ascii; format=flowed Content-Transfer-Encoding: 7bit cc: freebsd-current@freebsd.org Subject: Re: [PATCH] for SCHED_ULE & libpthread issue (was Re: I like SCHED_4BSD) 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: Fri, 12 Mar 2004 19:12:44 -0000 Taku YAMAMOTO wrote: > Unfortunately, due to over-optimization in sched_switch(), SCHED_ULE doesn't > give reasonable CPU time to the threads which are using scheduler activation. > > Detailed analisis is described in my previous message posted to current@: > "SCHED_ULE sometimes puts P_SA processes into ksq_next unnecessarily" > <20040213063139.71298ea9.taku@cent.saitama-u.ac.jp> > or > http://docs.freebsd.org/cgi/mid.cgi?20040213063139.71298ea9.taku > , which didn't get broader audience :( > > Until the problem is fully addressed, I will propose following patch > to be applied. (the least intrusive one attached in the former message) > This patch improves interactivity under heavy load very much. Thanks, Pete...