[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <20180423154707.GP26088@linux.vnet.ibm.com>
Date: Mon, 23 Apr 2018 08:47:07 -0700
From: "Paul E. McKenney" <paulmck@...ux.vnet.ibm.com>
To: Steven Rostedt <rostedt@...dmis.org>
Cc: Peter Zijlstra <peterz@...radead.org>,
linux-kernel@...r.kernel.org, mingo@...nel.org,
jiangshanlai@...il.com, dipankar@...ibm.com,
akpm@...ux-foundation.org, mathieu.desnoyers@...icios.com,
josh@...htriplett.org, tglx@...utronix.de, dhowells@...hat.com,
edumazet@...gle.com, fweisbec@...il.com, oleg@...hat.com,
joel.opensrc@...il.com
Subject: Re: [PATCH tip/core/rcu 01/22] sched: Make non-production PREEMPT
cond_resched() help Tasks RCU
On Mon, Apr 23, 2018 at 10:35:29AM -0400, Steven Rostedt wrote:
> On Mon, 23 Apr 2018 16:10:38 +0200
> Peter Zijlstra <peterz@...radead.org> wrote:
>
> > > http://lkml.kernel.org/r/20180227153646.GD3777@linux.vnet.ibm.com
> >
> > That thread using cond_resched_task_rcu_qs() seems like a _lot_ better
> > than having cond_resched() semantics change depending on random
> > !scheduler config parameters.
>
> Yeah, I agree. Not sure why Paul didn't push it. Maybe because I never
> replied to that final email and he forgot?
>
> Paul?
Yeah, I have been a bit event-driven of late. So the thought is to keep
cond_resched() as-is and use cond_resched_task_rcu_qs(), that is after
the rename, for the stress tests instead of the current cond_resched().
Or did I lose the thread?
Thanx, paul
Powered by blists - more mailing lists