mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Thomas Gleixner <tglx@linutronix.de>
To: Calvin Owens <calvinowens@fb.com>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>,
	Andrew Morton <akpm@linux-foundation.org>,
	Joe Perches <joe@perches.com>,
	Peter Zijlstra <peterz@infradead.org>,
	linux-kernel@vger.kernel.org, kernel-team@fb.com
Subject: Re: [PATCH] ksoftirqd: Enable IRQs and call cond_resched() before poking RCU
Date: Tue, 20 Jan 2015 14:21:51 +0100 (CET)	[thread overview]
Message-ID: <alpine.DEB.2.11.1501201419550.5526@nanos> (raw)
In-Reply-To: <20150113211618.GA21498@mail.thefacebook.com>

On Tue, 13 Jan 2015, 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 <calvinowens@fb.com>
> Cc: stable@vger.kernel.org
> ---
> This version includes the "cpu" argument to rcu_note_context_switch() in
> order to apply cleanly to stable kernels. It will need to be removed to
> apply to 3.18+ and 3.19 (upstream commit 38200cf2 removed the argument).
> 
>  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(cpu);
>  		local_irq_enable();
>  		cond_resched();
> +
> +		preempt_disable();
> +		rcu_note_context_switch(cpu);
> +		preempt_enable();
> +

The whole rcu_note_context_switch() in run_ksoftirqd() is silly.

    cond_resched()
	__preempt_count_add(PREEMPT_ACTIVE);

	__schedule();
	     preempt_disable();
	     rcu_note_context_switch();
	     ....

	__preempt_count_sub(PREEMPT_ACTIVE);

Thanks,

	tglx

  parent reply	other threads:[~2015-01-20 13:22 UTC|newest]

Thread overview: 19+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2015-01-07  1:37 Calvin Owens
2015-01-07  1:49 ` [PATCH v2] " Calvin Owens
2015-01-07  2:19   ` Paul E. McKenney
2015-01-07 16:52     ` Paul E. McKenney
2015-01-08  4:33       ` Calvin Owens
2015-01-08  4:53         ` Paul E. McKenney
2015-01-08 21:46           ` Calvin Owens
2015-01-13 11:17             ` Thomas Gleixner
2015-01-13 18:43               ` Paul E. McKenney
2015-01-13 21:16                 ` [PATCH] " Calvin Owens
2015-01-14 22:12                   ` Paul E. McKenney
2015-01-20 13:21                   ` Thomas Gleixner [this message]
2015-01-20 20:30                     ` Paul E. McKenney
2015-01-21  3:40                       ` Mike Galbraith
2015-01-21  5:10                         ` Paul E. McKenney
2015-01-21  6:29                           ` Mike Galbraith
2015-01-21  9:30                       ` Thomas Gleixner
2015-01-21 10:27                         ` Paul E. McKenney
2015-01-22 10:39                           ` Thomas Gleixner

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=alpine.DEB.2.11.1501201419550.5526@nanos \
    --to=tglx@linutronix.de \
    --cc=akpm@linux-foundation.org \
    --cc=calvinowens@fb.com \
    --cc=joe@perches.com \
    --cc=kernel-team@fb.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=paulmck@linux.vnet.ibm.com \
    --cc=peterz@infradead.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox

all inboxes | Powered by JetHome®