From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1751514AbaGVFBI (ORCPT ); Tue, 22 Jul 2014 01:01:08 -0400 Received: from cn.fujitsu.com ([59.151.112.132]:19244 "EHLO heian.cn.fujitsu.com" rhost-flags-OK-FAIL-OK-FAIL) by vger.kernel.org with ESMTP id S1750940AbaGVFBH (ORCPT ); Tue, 22 Jul 2014 01:01:07 -0400 X-IronPort-AV: E=Sophos;i="5.00,931,1396972800"; d="scan'208";a="33612895" From: Lai Jiangshan To: CC: Tejun Heo , Lai Jiangshan Subject: [PATCH 1/2 V2] workqueue: remove unneeded test before wake up next worker Date: Tue, 22 Jul 2014 13:01:59 +0800 Message-ID: <1406005330-11864-1-git-send-email-laijs@cn.fujitsu.com> X-Mailer: git-send-email 1.7.4.4 In-Reply-To: <20140718225317.GC5739@htj.dyndns.org> References: <20140718225317.GC5739@htj.dyndns.org> MIME-Version: 1.0 Content-Type: text/plain X-Originating-IP: [10.167.226.103] Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org In this code: if ((worker->flags & WORKER_UNBOUND) && need_more_worker(pool)) wake_up_worker(pool); the first test is unneeded. Even the first test is removed, it doesn't affect the wake-up logic when WORKER_UNBOUND. And it will not introduce any useless wake-up when !WORKER_UNBOUND since the nr_running >= 1 except only one case. It will introduce useless/redundant wake-up when cpu_intensive, but this case is rare and next patch will also remove this redundant wake-up. Signed-off-by: Lai Jiangshan --- kernel/workqueue.c | 9 ++++++--- 1 files changed, 6 insertions(+), 3 deletions(-) diff --git a/kernel/workqueue.c b/kernel/workqueue.c index a791a8c..cd75689 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -2048,10 +2048,13 @@ __acquires(&pool->lock) worker_set_flags(worker, WORKER_CPU_INTENSIVE, true); /* - * Unbound pool isn't concurrency managed and work items should be - * executed ASAP. Wake up another worker if necessary. + * Wake up another worker if necessary. It is a no-op + * when the current worker is concurrency managed since + * pool->nr_running >= 1. But it is required for non-concurrency + * managed workers, mainly for unbound pool which requries + * chain execution of currently pending work items ASAP. */ - if ((worker->flags & WORKER_UNBOUND) && need_more_worker(pool)) + if (need_more_worker(pool)) wake_up_worker(pool); /* -- 1.7.4.4