On Mon, Jul 09, 2018 at 01:47:14PM +0100, David Woodhouse wrote: > On Mon, 2018-07-09 at 05:34 -0700, Paul E. McKenney wrote: > > The reason that David's latencies went from 100ms to one second is > > because I made this code less aggressive about invoking resched_cpu(). > > Ten seconds. We saw synchronize_sched() take ten seconds in 4.15. We > wouldn't have been happy with one second, but ten seconds was > considered particularly suboptimal.
Yes, ten seconds. Please accept my apologies for my early morning confusion. Thanx, Paul > > The reason I did that was to allow cond_resched_rcu_qs() to be used less > > without performance regressions. And just plain cond_resched() on > > !PREEMPT is intended to handle the faster checks. But KVM defeats > > this by checking need_resched() before invoking cond_resched(). > > It isn't just KVM. It's a relatively common construct to use > need_resched(), then drop any local locks around cond_resched(). > > A bare cond_resched() will call rcu_all_qs() unconditionally, and it is > kind of inconsistent that need_resched() doesn't include the > corresponding condition.