From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
To: Peter Zijlstra <peterz@infradead.org>
Cc: Julian Anastasov <ja@ssi.bg>, Simon Horman <horms@verge.net.au>,
Eric Dumazet <eric.dumazet@gmail.com>,
Ingo Molnar <mingo@redhat.com>,
lvs-devel@vger.kernel.org, netdev@vger.kernel.org,
netfilter-devel@vger.kernel.org, linux-kernel@vger.kernel.org,
Pablo Neira Ayuso <pablo@netfilter.org>,
Dipankar Sarma <dipankar@in.ibm.com>
Subject: Re: [PATCH v2 1/2] sched: Add cond_resched_rcu_lock() helper
Date: Fri, 3 May 2013 10:34:44 -0700 [thread overview]
Message-ID: <20130503173444.GH3780@linux.vnet.ibm.com> (raw)
In-Reply-To: <20130503170447.GB30733@dyad.programming.kicks-ass.net>
On Fri, May 03, 2013 at 07:04:47PM +0200, Peter Zijlstra wrote:
> > The key point is that I don't understand why we cannot get the effect
> > we are looking for with the following in sched.h (or wherever):
> >
> > static inline int cond_resched_rcu(void)
> > {
> > #if defined(CONFIG_DEBUG_ATOMIC_SLEEP) || !defined(CONFIG_PREEMPT_RCU)
> > rcu_read_unlock();
> > cond_resched();
> > rcu_read_lock();
> > #endif
> > }
> >
> > This adds absolutely no overhead in non-debug builds of CONFIG_PREEMPT_RCU,
> > does the checking in debug builds, and allows voluntary preemption in
> > !CONFIG_PREEMPT_RCU builds. CONFIG_PROVE_RCU builds will check for an
> > (illegal) outer rcu_read_lock() in CONFIG_PREEMPT_RCU builds, and you
> > will get "scheduling while atomic" in response to an outer rcu_read_lock()
> > in !CONFIG_PREEMPT_RCU builds.
> >
> > It also seems to me a lot simpler.
> >
> > Does this work, or am I still missing something?
>
> It can do quite a number of superfluous rcu_read_unlock()/lock() pairs for
> voluntary preemption kernels?
This happens in only two cases:
1. CONFIG_PREEMPT_RCU=n kernels. But in this case, rcu_read_unlock()
and rcu_read_lock() are free, at least for CONFIG_PROVE_LOCKING=n
kernels. And if you have CONFIG_PROVE_LOCKING=y, any contribution
from rcu_read_unlock() and rcu_read_lock() will be in the noise.
2. CONFIG_DEBUG_ATOMIC_SLEEP=y kernels -- but in this case, you
-want- the debugging.
So either the overhead is non-existent, or you explicitly asked for the
resulting debugging.
In particular, CONFIG_PREEMPT_RCU=y kernels have an empty static inline
function, which is free -- unless CONFIG_DEBUG_ATOMIC_SLEEP=y, in which
case you again explicitly asked for the debugging.
So I do not believe that the extra rcu_read_unlock()/lock() pairs are a
problem in any of the possible combinations of configurations.
Thanx, Paul
next prev parent reply other threads:[~2013-05-03 17:34 UTC|newest]
Thread overview: 37+ messages / expand[flat|nested] mbox.gz Atom feed top
2013-04-30 2:52 [PATCH v2 0/2] sched: Add cond_resched_rcu_lock() helper Simon Horman
2013-04-30 2:52 ` [PATCH v2 1/2] " Simon Horman
2013-04-30 7:12 ` Julian Anastasov
2013-04-30 7:29 ` Simon Horman
2013-04-30 7:52 ` Julian Anastasov
2013-05-01 9:10 ` Peter Zijlstra
2013-05-01 12:46 ` Paul E. McKenney
2013-05-01 14:32 ` Paul E. McKenney
2013-05-02 7:27 ` Peter Zijlstra
2013-05-01 15:17 ` Peter Zijlstra
2013-05-01 15:29 ` Eric Dumazet
2013-05-01 15:59 ` Peter Zijlstra
2013-05-01 16:02 ` Paul E. McKenney
2013-05-01 16:57 ` Peter Zijlstra
2013-05-01 17:30 ` Paul E. McKenney
2013-05-01 14:22 ` Julian Anastasov
2013-05-01 15:55 ` Peter Zijlstra
2013-05-01 18:22 ` Julian Anastasov
2013-05-01 19:04 ` Paul E. McKenney
2013-05-02 7:26 ` Peter Zijlstra
2013-05-02 10:06 ` Julian Anastasov
2013-05-02 15:54 ` Julian Anastasov
2013-05-02 17:32 ` Paul E. McKenney
2013-05-02 18:55 ` Julian Anastasov
2013-05-02 19:24 ` Julian Anastasov
2013-05-02 19:34 ` Paul E. McKenney
2013-05-02 20:19 ` Julian Anastasov
2013-05-02 22:31 ` Paul E. McKenney
2013-05-03 7:52 ` Julian Anastasov
2013-05-03 16:30 ` Paul E. McKenney
2013-05-03 17:04 ` Peter Zijlstra
2013-05-03 17:34 ` Paul E. McKenney [this message]
2013-05-03 18:09 ` Peter Zijlstra
2013-05-03 17:47 ` Julian Anastasov
2013-05-04 7:23 ` Julian Anastasov
2013-05-04 18:03 ` Paul E. McKenney
2013-04-30 2:52 ` [PATCH v2 2/2] ipvs: Use cond_resched_rcu_lock() helper when dumping connections Simon Horman
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=20130503173444.GH3780@linux.vnet.ibm.com \
--to=paulmck@linux.vnet.ibm.com \
--cc=dipankar@in.ibm.com \
--cc=eric.dumazet@gmail.com \
--cc=horms@verge.net.au \
--cc=ja@ssi.bg \
--cc=linux-kernel@vger.kernel.org \
--cc=lvs-devel@vger.kernel.org \
--cc=mingo@redhat.com \
--cc=netdev@vger.kernel.org \
--cc=netfilter-devel@vger.kernel.org \
--cc=pablo@netfilter.org \
--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;
as well as URLs for NNTP newsgroup(s).