From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
To: Peter Zijlstra <peterz@infradead.org>
Cc: Lai Jiangshan <laijs@cn.fujitsu.com>,
Steven Rostedt <rostedt@goodmis.org>,
linux-kernel@vger.kernel.org,
Dipankar Sarma <dipankar@in.ibm.com>
Subject: Re: [PATCH 5/8] rcu: eliminate deadlock for rcu read site
Date: Mon, 12 Aug 2013 08:16:18 -0700 [thread overview]
Message-ID: <20130812151618.GR29406@linux.vnet.ibm.com> (raw)
In-Reply-To: <20130812135544.GG27162@twins.programming.kicks-ass.net>
On Mon, Aug 12, 2013 at 03:55:44PM +0200, Peter Zijlstra wrote:
> On Fri, Aug 09, 2013 at 05:31:27PM +0800, Lai Jiangshan wrote:
> > On 08/09/2013 04:40 AM, Paul E. McKenney wrote:
> > > One problem here -- it may take quite some time for a set_need_resched()
> > > to take effect. This is especially a problem for RCU priority boosting,
> > > but can also needlessly delay preemptible-RCU grace periods because
> > > local_irq_restore() and friends don't check the TIF_NEED_RESCHED bit.
> >
> >
> > The final effect of deboosting(rt_mutex_unlock()) is also accomplished
> > via set_need_resched()/set_tsk_need_resched().
> > set_need_resched() is enough for RCU priority boosting issue here.
>
> But there's a huge difference between the boosting and deboosting side
> of things. rcu_read_unlock_special() starts the boost, the deboosting
> only matters if/when you reschedule.
Or if there is a pre-existing runnable task whose priority is such that
deboosting makes it the highest-priority task.
Thanx, Paul
next prev parent reply other threads:[~2013-08-12 15:17 UTC|newest]
Thread overview: 49+ messages / expand[flat|nested] mbox.gz Atom feed top
2013-08-07 10:24 [PATCH 0/8] rcu: Ensure rcu read site is deadlock-immunity Lai Jiangshan
2013-08-07 10:24 ` [PATCH 1/8] rcu: add a warn to rcu_preempt_note_context_switch() Lai Jiangshan
2013-10-30 11:02 ` Paul E. McKenney
2013-08-07 10:24 ` [PATCH 2/8] rcu: remove irq/softirq context check in rcu_read_unlock_special() Lai Jiangshan
2013-10-30 11:18 ` Paul E. McKenney
2013-08-07 10:24 ` [PATCH 3/8] rcu: keep irqs disabled " Lai Jiangshan
2013-08-07 10:25 ` [PATCH 4/8] rcu: delay task rcu state cleanup in exit_rcu() Lai Jiangshan
2013-08-07 10:25 ` [PATCH 5/8] rcu: eliminate deadlock for rcu read site Lai Jiangshan
2013-08-08 20:40 ` Paul E. McKenney
2013-08-09 9:31 ` Lai Jiangshan
2013-08-09 17:58 ` Paul E. McKenney
2013-08-12 13:55 ` Peter Zijlstra
2013-08-12 15:16 ` Paul E. McKenney [this message]
2013-08-12 16:21 ` Peter Zijlstra
2013-08-12 16:44 ` Paul E. McKenney
2013-08-10 3:43 ` Lai Jiangshan
2013-08-10 15:07 ` Paul E. McKenney
2013-08-10 15:08 ` Paul E. McKenney
2013-08-21 3:17 ` Paul E. McKenney
2013-08-21 3:25 ` Lai Jiangshan
2013-08-21 13:42 ` Paul E. McKenney
2013-08-12 13:53 ` Peter Zijlstra
2013-08-12 14:10 ` Steven Rostedt
2013-08-12 14:14 ` Peter Zijlstra
[not found] ` <CACvQF51-oAGkdxwku+orKSQ=SZd1A4saXzkrgcRGi+KnZUZYxQ@mail.gmail.com>
2013-08-22 14:34 ` Steven Rostedt
2013-08-22 14:41 ` Steven Rostedt
2013-08-23 6:26 ` Lai Jiangshan
[not found] ` <CACvQF51kcLrJsa=zBKhLkJfFBh109TW+Zrepm+tRxmEp0gALbQ@mail.gmail.com>
2013-08-25 17:43 ` Paul E. McKenney
2013-08-26 2:39 ` Lai Jiangshan
2013-08-30 2:05 ` Paul E. McKenney
2013-09-05 15:22 ` Steven Rostedt
2013-08-07 10:25 ` [PATCH 6/8] rcu: call rcu_read_unlock_special() in rcu_preempt_check_callbacks() Lai Jiangshan
2013-08-07 10:25 ` [PATCH 7/8] rcu: add # of deferred _special() statistics Lai Jiangshan
2013-08-07 16:42 ` Paul E. McKenney
2013-08-07 10:25 ` [PATCH 8/8] rcu: remove irq work for rsp_wakeup() Lai Jiangshan
2013-08-07 12:38 ` [PATCH 0/8] rcu: Ensure rcu read site is deadlock-immunity Paul E. McKenney
2013-08-07 19:29 ` Carsten Emde
2013-08-07 19:52 ` Paul E. McKenney
2013-08-08 1:17 ` Lai Jiangshan
2013-08-08 0:36 ` Paul E. McKenney
2013-08-08 1:47 ` Lai Jiangshan
2013-08-08 2:12 ` Steven Rostedt
2013-08-08 2:33 ` Lai Jiangshan
2013-08-08 2:33 ` Paul E. McKenney
2013-08-08 3:10 ` Lai Jiangshan
2013-08-08 4:18 ` Paul E. McKenney
2013-08-08 5:27 ` Lai Jiangshan
2013-08-08 7:05 ` Paul E. McKenney
2013-08-08 2:45 ` Lai Jiangshan
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=20130812151618.GR29406@linux.vnet.ibm.com \
--to=paulmck@linux.vnet.ibm.com \
--cc=dipankar@in.ibm.com \
--cc=laijs@cn.fujitsu.com \
--cc=linux-kernel@vger.kernel.org \
--cc=peterz@infradead.org \
--cc=rostedt@goodmis.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;
as well as URLs for NNTP newsgroup(s).