From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754919AbbAGCTg (ORCPT ); Tue, 6 Jan 2015 21:19:36 -0500 Received: from e37.co.us.ibm.com ([32.97.110.158]:49609 "EHLO e37.co.us.ibm.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754922AbbAGCTc (ORCPT ); Tue, 6 Jan 2015 21:19:32 -0500 Date: Tue, 6 Jan 2015 18:19:26 -0800 From: "Paul E. McKenney" To: Calvin Owens Cc: Thomas Gleixner , Andrew Morton , Joe Perches , Peter Zijlstra , linux-kernel@vger.kernel.org, kernel-team@fb.com Subject: Re: [PATCH v2] ksoftirqd: Enable IRQs and call cond_resched() before poking RCU Message-ID: <20150107021926.GT5280@linux.vnet.ibm.com> Reply-To: paulmck@linux.vnet.ibm.com References: <1420594659-16996-1-git-send-email-calvinowens@fb.com> <20150107014906.GA27996@mail.thefacebook.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20150107014906.GA27996@mail.thefacebook.com> User-Agent: Mutt/1.5.21 (2010-09-15) X-TM-AS-MML: disable X-Content-Scanned: Fidelis XPS MAILER x-cbid: 15010702-0025-0000-0000-0000078CF496 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Tue, Jan 06, 2015 at 05:49:06PM -0800, Calvin Owens wrote: > While debugging an issue with excessive softirq usage, I encountered the > following note in commit 3e339b5dae24a706 ("softirq: Use hotplug thread > infrastructure"): > > [ paulmck: Call rcu_note_context_switch() with interrupts enabled. ] > > ...but despite this note, the patch still calls RCU with IRQs disabled. > > This seemingly innocuous change caused a significant regression in softirq > CPU usage on the sending side of a large TCP transfer (~1 GB/s): when > introducing 0.01% packet loss, the softirq usage would jump to around 25%, > spiking as high as 50%. Before the change, the usage would never exceed 5%. > > Moving the call to rcu_note_context_switch() after the cond_sched() call, > as it was originally before the hotplug patch, completely eliminated this > problem. > > Signed-off-by: Calvin Owens > --- > Changes since v1: > I mixed up the kernel versions I was patching against, sorry! > > kernel/softirq.c | 6 +++++- > 1 file changed, 5 insertions(+), 1 deletion(-) > > diff --git a/kernel/softirq.c b/kernel/softirq.c > index 501baa9..9e787d8 100644 > --- a/kernel/softirq.c > +++ b/kernel/softirq.c > @@ -656,9 +656,13 @@ static void run_ksoftirqd(unsigned int cpu) > * in the task stack here. > */ > __do_softirq(); > - rcu_note_context_switch(); > local_irq_enable(); > cond_resched(); If this is for 3.20, we can just replace cond_resched() with cond_resched_rcu_qs(), and get rid of the direct call to rcu_note_context_switch(). This has the benefit of avoiding needless rcu_note_context_switch() overhead if cond_resched() actually did a reschedule. But don't try it in 3.19 or earlier. ;-) Thanx, Paul > + > + preempt_disable(); > + rcu_note_context_switch(); > + preempt_enable(); > + > return; > } > local_irq_enable(); > -- > 2.1.1 >