From: Oleg Nesterov <oleg@redhat.com>
To: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Chris Mason <chris.mason@oracle.com>,
Frank Rowand <frank.rowand@am.sony.com>,
Ingo Molnar <mingo@elte.hu>, Thomas Gleixner <tglx@linutronix.de>,
Mike Galbraith <efault@gmx.de>, Paul Turner <pjt@google.com>,
Jens Axboe <axboe@kernel.dk>, Yong Zhang <yong.zhang0@gmail.com>,
linux-kernel@vger.kernel.org
Subject: Re: [RFC][PATCH 18/18] sched: Sort hotplug vs ttwu queueing
Date: Wed, 5 Jan 2011 21:47:00 +0100 [thread overview]
Message-ID: <20110105204700.GA1313@redhat.com> (raw)
In-Reply-To: <20110104150103.214765376@chello.nl>
On 01/04, Peter Zijlstra wrote:
>
> +#ifdef CONFIG_HOTPLUG_CPU
> +static void ttwu_queue_unplug(struct rq *rq)
> +{
> + struct task_struct *p, *list = xchg(&rq->wake_list, NULL);
> + unsigned long flags;
> + int cpu;
> +
> + if (!list)
> + return;
> +
> + while (list) {
> + p = list;
> + list = list->wake_entry;
> +
> + raw_spin_lock_irqsave(&p->pi_lock, flags);
> + cpu = select_task_rq(p, SD_BALANCE_WAKE, 0);
> + set_task_cpu(p, cpu);
> + ttwu_queue(p, cpu);
> + raw_spin_unlock_irqrestore(&p->pi_lock, flags);
> + }
> +}
> +#endif
> +
> /**
> * try_to_wake_up - wake up a thread
> * @p: the thread to be awakened
> @@ -6151,6 +6174,11 @@ migration_call(struct notifier_block *nf
> migrate_nr_uninterruptible(rq);
> calc_global_load_remove(rq);
> break;
> +
> + case CPU_DEAD:
> + ttwu_queue_unplug(cpu_rq(cpu));
I think this is not strictly needed...
Afaics, take_cpu_down() can simply call sched_ttwu_pending() at the
start. This will activate the pending tasks on the (almost) dead
cpu but we don't care, they will be migrated later.
When __stop_machine(take_cpu_down) returns nobody can use this CPU
as a target, iow rq->wake_list can't be used again.
Oleg.
next prev parent reply other threads:[~2011-01-05 20:54 UTC|newest]
Thread overview: 44+ messages / expand[flat|nested] mbox.gz Atom feed top
2011-01-04 14:59 [RFC][PATCH 00/18] sched: Reduce runqueue lock contention -v4 Peter Zijlstra
2011-01-04 14:59 ` [RFC][PATCH 01/18] sched: Always provide p->on_cpu Peter Zijlstra
2011-01-04 14:59 ` [RFC][PATCH 02/18] mutex: Use p->on_cpu for the adaptive spin Peter Zijlstra
2011-01-04 14:59 ` [RFC][PATCH 03/18] sched: Change the ttwu success details Peter Zijlstra
2011-01-04 14:59 ` [RFC][PATCH 04/18] sched: Clean up ttwu stats Peter Zijlstra
2011-01-04 14:59 ` [RFC][PATCH 05/18] sched: Provide p->on_rq Peter Zijlstra
2011-01-05 8:13 ` Yong Zhang
2011-01-05 9:53 ` Peter Zijlstra
2011-01-29 0:10 ` Frank Rowand
2011-01-04 14:59 ` [RFC][PATCH 06/18] sched: Serialize p->cpus_allowed and ttwu() using p->pi_lock Peter Zijlstra
2011-01-04 14:59 ` [RFC][PATCH 07/18] sched: Drop the rq argument to sched_class::select_task_rq() Peter Zijlstra
2011-01-06 13:57 ` Peter Zijlstra
2011-01-06 14:23 ` Peter Zijlstra
2011-01-04 14:59 ` [RFC][PATCH 08/18] sched: Remove rq argument to sched_class::task_waking() Peter Zijlstra
2011-01-04 14:59 ` [RFC][PATCH 09/18] sched: Delay task_contributes_to_load() Peter Zijlstra
2011-01-04 14:59 ` [RFC][PATCH 10/18] sched: Also serialize ttwu_local() with p->pi_lock Peter Zijlstra
2011-01-04 14:59 ` [RFC][PATCH 11/18] sched: Add p->pi_lock to task_rq_lock() Peter Zijlstra
2011-01-05 18:46 ` Oleg Nesterov
2011-01-05 19:33 ` Peter Zijlstra
2011-01-29 0:21 ` Frank Rowand
2011-02-03 17:16 ` Peter Zijlstra
2011-02-03 17:49 ` Frank Rowand
2011-01-04 14:59 ` [RFC][PATCH 12/18] sched: Drop rq->lock from first part of wake_up_new_task() Peter Zijlstra
2011-01-04 14:59 ` [RFC][PATCH 13/18] sched: Drop rq->lock from sched_exec() Peter Zijlstra
2011-01-04 14:59 ` [RFC][PATCH 14/18] sched: Remove rq->lock from the first half of ttwu() Peter Zijlstra
2011-01-06 16:29 ` Peter Zijlstra
2011-01-29 1:05 ` Frank Rowand
2011-02-03 17:16 ` Peter Zijlstra
2011-01-04 14:59 ` [RFC][PATCH 15/18] sched: Remove rq argument from ttwu_stat() Peter Zijlstra
2011-01-04 14:59 ` [RFC][PATCH 16/18] sched: Rename ttwu_post_activation Peter Zijlstra
2011-01-29 1:08 ` Frank Rowand
2011-01-04 14:59 ` [RFC][PATCH 17/18] sched: Move the second half of ttwu() to the remote cpu Peter Zijlstra
2011-01-05 21:07 ` Oleg Nesterov
2011-01-06 15:09 ` Peter Zijlstra
2011-01-07 15:22 ` Oleg Nesterov
2011-01-18 16:38 ` Peter Zijlstra
2011-01-19 19:37 ` Oleg Nesterov
2011-01-29 0:04 ` Frank Rowand
2011-02-03 17:16 ` Peter Zijlstra
2011-01-04 14:59 ` [RFC][PATCH 18/18] sched: Sort hotplug vs ttwu queueing Peter Zijlstra
2011-01-05 20:47 ` Oleg Nesterov [this message]
2011-01-06 10:56 ` Peter Zijlstra
2011-01-04 15:16 ` [RFC][PATCH 00/18] sched: Reduce runqueue lock contention -v4 Ingo Molnar
2011-01-29 1:20 ` Frank Rowand
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=20110105204700.GA1313@redhat.com \
--to=oleg@redhat.com \
--cc=a.p.zijlstra@chello.nl \
--cc=axboe@kernel.dk \
--cc=chris.mason@oracle.com \
--cc=efault@gmx.de \
--cc=frank.rowand@am.sony.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@elte.hu \
--cc=pjt@google.com \
--cc=tglx@linutronix.de \
--cc=yong.zhang0@gmail.com \
/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