On Thu, Oct 18, 2018 at 08:58:44PM -0700, Joel Fernandes wrote: > On Thu, Oct 18, 2018 at 10:52:23PM -0400, Steven Rostedt wrote: > > On Thu, 18 Oct 2018 19:25:29 -0700 > > Joel Fernandes <joel@xxxxxxxxxxxxxxxxx> wrote: > > > > > On Thu, Oct 18, 2018 at 09:50:35PM -0400, Steven Rostedt wrote: > > > > On Thu, 18 Oct 2018 18:26:45 -0700 > > > > Joel Fernandes <joel@xxxxxxxxxxxxxxxxx> wrote: > > > > > > > > > Yes, local_irq_restore is light weight, and does not check for reschedules. > > > > > > > > > > I was thinking of case where ksoftirqd is woken up, but does not run unless > > > > > we set the NEED_RESCHED flag. But that should get set anyway since probably > > > > > ksoftirqd is of high enough priority than the currently running task.. > > > > > > > > > > Roughly speaking the scenario could be something like: > > > > > > > > > > rcu_read_lock(); > > > > > <-- IPI comes in for the expedited GP, sets exp_hint > > > > > local_irq_disable(); > > > > > // do a bunch of stuff > > > > > rcu_read_unlock(); <-- This calls the rcu_read_unlock_special which raises > > > > > the soft irq, and wakesup softirqd. > > > > > > > > If softirqd is of higher priority than the current running task, then > > > > the try_to_wake_up() will set NEED_RESCHED of the current task here. > > > > > > > > > > Yes, only *if*. On my system, ksoftirqd is CFS nice 0. I thought expedited > > > grace periods are quite important and they should complete quickly which is > > > the whole reason for interrupting rcu read sections with an IPI and stuff. > > > IMO there should be no harm in setting NEED_RESCHED unconditionally anyway > > > for possible benefit of systems where the ksoftirqd is not of higher priority > > > than the currently running task, and we need to run it soon on the CPU. But > > > I'm Ok with whatever Paul and you want to do here. > > > > > > Setting NEED_RESCHED unconditionally wont help. Because even if we call > > schedule() ksoftirqd will not be scheduled! If it's CFS nice 0, and the > > current task still has quota to run, if you call schedule, you'll just > > waste time calculating that the current task should still be running. > > It's equivalent to calling yield() (which is why we removed all yield() > > users in the kernel, because *all* of them were buggy!). This is *why* > > it only calls schedule *if* softirqd is of higher priority. > > Yes, ok. you are right the TTWU path should handle setting the NEED_RESCHED > flag or not and unconditionally setting it does not get us anything. I had to > go through the code a bit since it has been a while since I explored it. > > So Paul, I'm Ok with your latest patch for the issue we discussed and don't > think much more can be done barring raising of ksofitrqd priorities :-) So I > guess the synchronize_rcu_expedited will just cope with the deal between > local_irq_enable and the next scheduling point.. :-) Thank you both! Indeed, real-time systems need to be configured carefully, especially if you are crazy enough to run them under high load. I interpreted "Ok with your latest patch" as an Acked-by, but please let me know if that is a misinterpretation. Thanx, Paul
