From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1755987AbXLDVNr (ORCPT ); Tue, 4 Dec 2007 16:13:47 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1754640AbXLDVH5 (ORCPT ); Tue, 4 Dec 2007 16:07:57 -0500 Received: from 75-130-111-13.dhcp.oxfr.ma.charter.com ([75.130.111.13]:53496 "EHLO novell1.haskins.net" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1755306AbXLDVH4 (ORCPT ); Tue, 4 Dec 2007 16:07:56 -0500 From: Gregory Haskins Subject: [PATCH 18/23] Subject: SCHED - Optimize cpu search with hamming weight To: mingo@elte.hu Cc: rostedt@goodmis.org, ghaskins@novell.com, linux-rt-users@vger.kernel.org, linux-kernel@vger.kernel.org Date: Tue, 04 Dec 2007 15:45:56 -0500 Message-ID: <20071204204556.3567.19342.stgit@novell1.haskins.net> In-Reply-To: <20071204204236.3567.65491.stgit@novell1.haskins.net> References: <20071204204236.3567.65491.stgit@novell1.haskins.net> User-Agent: StGIT/0.12.1 MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org We can cheaply track the number of bits set in the cpumask for the lowest priority CPUs. Therefore, compute the mask's weight and use it to skip the optimal domain search logic when there is only one CPU available. Signed-off-by: Gregory Haskins --- kernel/sched_rt.c | 25 ++++++++++++++++++------- 1 files changed, 18 insertions(+), 7 deletions(-) diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c index fe0b43f..0514b27 100644 --- a/kernel/sched_rt.c +++ b/kernel/sched_rt.c @@ -301,7 +301,7 @@ static int find_lowest_cpus(struct task_struct *task, cpumask_t *lowest_mask) int cpu; cpumask_t *valid_mask = &__get_cpu_var(valid_cpu_mask); int lowest_prio = -1; - int ret = 0; + int count = 0; cpus_clear(*lowest_mask); cpus_and(*valid_mask, cpu_online_map, task->cpus_allowed); @@ -314,7 +314,7 @@ static int find_lowest_cpus(struct task_struct *task, cpumask_t *lowest_mask) /* We look for lowest RT prio or non-rt CPU */ if (rq->rt.highest_prio >= MAX_RT_PRIO) { - if (ret) + if (count) cpus_clear(*lowest_mask); cpu_set(rq->cpu, *lowest_mask); return 1; @@ -326,14 +326,17 @@ static int find_lowest_cpus(struct task_struct *task, cpumask_t *lowest_mask) if (rq->rt.highest_prio > lowest_prio) { /* new low - clear old data */ lowest_prio = rq->rt.highest_prio; - cpus_clear(*lowest_mask); + if (count) { + cpus_clear(*lowest_mask); + count = 0; + } } cpu_set(rq->cpu, *lowest_mask); - ret = 1; + count++; } } - return ret; + return count; } static inline int pick_optimal_cpu(int this_cpu, cpumask_t *mask) @@ -357,9 +360,17 @@ static int find_lowest_rq(struct task_struct *task) cpumask_t *lowest_mask = &__get_cpu_var(local_cpu_mask); int this_cpu = smp_processor_id(); int cpu = task_cpu(task); + int count = find_lowest_cpus(task, lowest_mask); - if (!find_lowest_cpus(task, lowest_mask)) - return -1; + if (!count) + return -1; /* No targets found */ + + /* + * There is no sense in performing an optimal search if only one + * target is found. + */ + if (count == 1) + return first_cpu(*lowest_mask); /* * At this point we have built a mask of cpus representing the