Re: [tip:sched/core] sched/core: Avoid _cond_resched() for PREEMPT=y

From	Peter Zijlstra <peterz@infradead.org>
Newsgroups	linux.kernel
Subject	Re: [tip:sched/core] sched/core: Avoid _cond_resched() for PREEMPT=y
Date	2016-09-23 10:50 +0200
Message-ID	<skulc-1p5-3@gated-at.bofh.it> (permalink)
References	<skgUV-1qI-13@gated-at.bofh.it> <skgUV-1qI-11@gated-at.bofh.it> <skhei-1xN-35@gated-at.bofh.it> <skiN3-2zX-23@gated-at.bofh.it>
Organization	linux.* mail to news gateway

Show all headers | View raw

On Thu, Sep 22, 2016 at 01:28:17PM -0700, Paul E. McKenney wrote:
> On Thu, Sep 22, 2016 at 08:42:28PM +0200, Peter Zijlstra wrote:
> > On Thu, Sep 22, 2016 at 02:25:01PM -0400, Mikulas Patocka wrote:
> > > I've found a document that says that cond_resched() is needed on
> > > preemptible kernels to mark RCU quiescent states:
> > > 
> > > https://lwn.net/Articles/603252/
> > > 
> > > Paul, is cond_resched() still needed on current RCU implementation? Or not?
> > 
> > No, we ripped that out. See 4a81e8328d37 ("rcu: Reduce overhead of
> > cond_resched() checks for RCU")
> 
> I would instead say that we changed the algorithm to reduce the overhead
> in the common case, but yes, this commit did change things quite a bit.

Sure, but critical point (for this discussion) is that cond_resched() no
longer implies anything RCU, it really only is a voluntary reschedule
point.

Thread

Re: [tip:sched/core] sched/core: Avoid _cond_resched() for  PREEMPT=y Mikulas Patocka <mpatocka@redhat.com> - 2016-09-22 20:30 +0200
  Re: [tip:sched/core] sched/core: Avoid _cond_resched() for PREEMPT=y "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> - 2016-09-22 20:40 +0200
  Re: [tip:sched/core] sched/core: Avoid _cond_resched() for PREEMPT=y Peter Zijlstra <peterz@infradead.org> - 2016-09-22 20:50 +0200
    Re: [tip:sched/core] sched/core: Avoid _cond_resched() for PREEMPT=y "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> - 2016-09-22 22:30 +0200
      Re: [tip:sched/core] sched/core: Avoid _cond_resched() for PREEMPT=y Peter Zijlstra <peterz@infradead.org> - 2016-09-23 10:50 +0200
        Re: [tip:sched/core] sched/core: Avoid _cond_resched() for PREEMPT=y "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> - 2016-09-23 16:50 +0200

csiph-web