From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S965673AbXCBVdw (ORCPT ); Fri, 2 Mar 2007 16:33:52 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1030177AbXCBVdw (ORCPT ); Fri, 2 Mar 2007 16:33:52 -0500 Received: from mga05.intel.com ([192.55.52.89]:22766 "EHLO fmsmga101.fm.intel.com" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S965673AbXCBVdv (ORCPT ); Fri, 2 Mar 2007 16:33:51 -0500 X-ExtLoop1: 1 X-IronPort-AV: i="4.14,244,1170662400"; d="scan'208"; a="206099001:sNHT29230131" Date: Fri, 2 Mar 2007 12:57:29 -0800 From: "Siddha, Suresh B" To: Laurent Riffard Cc: "Siddha, Suresh B" , Andrew Morton , linux-kernel@vger.kernel.org, Nick Piggin Subject: Re: 2.6.21-rc2-mm1: what about CONFIG_NO_HZ and !CONFIG_SMP ? Message-ID: <20070302125729.A27368@unix-os.sc.intel.com> References: <20070302030026.5eef0c92.akpm@linux-foundation.org> <45E89339.1050504@free.fr> Mime-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 Content-Disposition: inline Content-Transfer-Encoding: 8bit User-Agent: Mutt/1.2.5.1i In-Reply-To: <45E89339.1050504@free.fr>; from laurent.riffard@free.fr on Fri, Mar 02, 2007 at 10:12:25PM +0100 Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org On Fri, Mar 02, 2007 at 10:12:25PM +0100, Laurent Riffard wrote: > Le 02.03.2007 12:00, Andrew Morton a écrit : > > Temporarily at > > > > http://userweb.kernel.org/~akpm/2.6.21-rc2-mm1/ > > > > Will appear later at > > > > ftp://ftp.kernel.org/pub/linux/kernel/people/akpm/patches/2.6/2.6.21-rc2/2.6.21-rc2-mm1/ > > Got this when CONFIG_NO_HZ=y and CONFIG_SMP=n: > > CC kernel/sched.o > kernel/sched.c: In function 'trigger_load_balance': > kernel/sched.c:3384: error: 'struct rq' has no member named 'in_nohz_recently' > kernel/sched.c:3384: error: 'struct rq' has no member named 'idle_at_tick' > kernel/sched.c:3385: error: 'struct rq' has no member named 'in_nohz_recently' > kernel/sched.c:3387: error: 'nohz' undeclared (first use in this function) > kernel/sched.c:3387: error: (Each undeclared identifier is reported only once > kernel/sched.c:3387: error: for each function it appears in.) > kernel/sched.c:3404: warning: implicit declaration of function 'resched_cpu' > kernel/sched.c:3412: error: 'struct rq' has no member named 'idle_at_tick' > kernel/sched.c:3422: error: 'struct rq' has no member named 'idle_at_tick' > make[1]: *** [kernel/sched.o] Error 1 > make: *** [kernel] Error 2 > > Looking at kernel/sched.c, it seems CONFIG_NO_HZ should depend on CONFIG_SMP... No. There is no such dependency. Can you please check if the below patch fixes the compilation issue. Thanks. --- Move trigger_load_balance() under ifdef CONFIG_SMP. Signed-off-by: Suresh Siddha --- diff -pNru linux-2.6.21-rc2/kernel/sched.c linux-mm/kernel/sched.c --- linux-2.6.21-rc2/kernel/sched.c 2007-03-02 13:23:46.000000000 -0800 +++ linux-mm/kernel/sched.c 2007-03-02 13:26:38.000000000 -0800 @@ -3156,6 +3156,68 @@ static void run_rebalance_domains(struct } #endif } + +/* + * Trigger the SCHED_SOFTIRQ if it is time to do periodic load balancing. + * + * In case of CONFIG_NO_HZ, this is the place where we nominate a new + * idle load balancing owner or decide to stop the periodic load balancing, + * if the whole system is idle. + */ +static inline void trigger_load_balance(int cpu) +{ + struct rq *rq = cpu_rq(cpu); +#ifdef CONFIG_NO_HZ + /* + * If we were in the nohz mode recently and busy at the current + * scheduler tick, then check if we need to nominate new idle + * load balancer. + */ + if (rq->in_nohz_recently && !rq->idle_at_tick) { + rq->in_nohz_recently = 0; + + if (atomic_read(&nohz.load_balancer) == cpu) { + cpu_clear(cpu, nohz.cpu_mask); + atomic_set(&nohz.load_balancer, -1); + } + + if (atomic_read(&nohz.load_balancer) == -1) { + /* + * simple selection for now: Nominate the + * first cpu in the nohz list to be the next + * ilb owner. + * + * TBD: Traverse the sched domains and nominate + * the nearest cpu in the nohz.cpu_mask. + */ + int ilb = first_cpu(nohz.cpu_mask); + + if (ilb != NR_CPUS) + resched_cpu(ilb); + } + } + + /* + * If this cpu is idle and doing idle load balancing for all the + * cpus with ticks stopped, is it time for that to stop? + */ + if (rq->idle_at_tick && atomic_read(&nohz.load_balancer) == cpu && + cpus_weight(nohz.cpu_mask) == num_online_cpus()) { + resched_cpu(cpu); + return; + } + + /* + * If this cpu is idle and the idle load balancing is done by + * someone else, then no need raise the SCHED_SOFTIRQ + */ + if (rq->idle_at_tick && atomic_read(&nohz.load_balancer) != cpu && + cpu_isset(cpu, nohz.cpu_mask)) + return; +#endif + if (time_after_eq(jiffies, rq->next_balance)) + raise_softirq(SCHED_SOFTIRQ); +} #else /* * on UP we do not need to balance between CPUs: @@ -3366,68 +3428,6 @@ out_unlock: } /* - * Trigger the SCHED_SOFTIRQ if it is time to do periodic load balancing. - * - * In case of CONFIG_NO_HZ, this is the place where we nominate a new - * idle load balancing owner or decide to stop the periodic load balancing, - * if the whole system is idle. - */ -static inline void trigger_load_balance(int cpu) -{ - struct rq *rq = cpu_rq(cpu); -#ifdef CONFIG_NO_HZ - /* - * If we were in the nohz mode recently and busy at the current - * scheduler tick, then check if we need to nominate new idle - * load balancer. - */ - if (rq->in_nohz_recently && !rq->idle_at_tick) { - rq->in_nohz_recently = 0; - - if (atomic_read(&nohz.load_balancer) == cpu) { - cpu_clear(cpu, nohz.cpu_mask); - atomic_set(&nohz.load_balancer, -1); - } - - if (atomic_read(&nohz.load_balancer) == -1) { - /* - * simple selection for now: Nominate the - * first cpu in the nohz list to be the next - * ilb owner. - * - * TBD: Traverse the sched domains and nominate - * the nearest cpu in the nohz.cpu_mask. - */ - int ilb = first_cpu(nohz.cpu_mask); - - if (ilb != NR_CPUS) - resched_cpu(ilb); - } - } - - /* - * If this cpu is idle and doing idle load balancing for all the - * cpus with ticks stopped, is it time for that to stop? - */ - if (rq->idle_at_tick && atomic_read(&nohz.load_balancer) == cpu && - cpus_weight(nohz.cpu_mask) == num_online_cpus()) { - resched_cpu(cpu); - return; - } - - /* - * If this cpu is idle and the idle load balancing is done by - * someone else, then no need raise the SCHED_SOFTIRQ - */ - if (rq->idle_at_tick && atomic_read(&nohz.load_balancer) != cpu && - cpu_isset(cpu, nohz.cpu_mask)) - return; -#endif - if (time_after_eq(jiffies, rq->next_balance)) - raise_softirq(SCHED_SOFTIRQ); -} - -/* * This function gets called by the timer code, with HZ frequency. * We call it with interrupts disabled. *