Yes, that's why blacklisting workqueues from critical cpus should be on the jitter elimination check list. They can be affinitized just like irqs
On Fri, 26 May 2017, 11:10 Sarunas Vancevicius, <vsaru...@gmail.com> wrote: > > > On Monday, 22 May 2017 16:03:53 UTC+3, Wojciech Kudla wrote: >> >> There's lots of work being scheduled on even isolated cpus. If you are >> not running a tickless kernel, you should see around 1000 local timer >> interrupts per second (by default). You will also see soft irqs (if you >> haven't affinitized them with some housekeeping cpu), non maskable >> interrupts/machine check errors, work queue tasks, etc. >> As for rcu, even with offloading you will see the isolated cores >> performing work required to schedule the callbacks on the offloaded cpus. >> You can solve that by switching to rcu callback polling, but my point here >> is, there's a number of different types of tasks that will run on isolated >> cpus. >> > > Kernel can run work queue tasks on isolated cores quiet often, can observe > them via: > > # perf record -C 1 -e workqueue:workqueue_execute_start -e > workqueue:workqueue_execute_end -o wrk_start_$(date "+%Y-%m-%d_%H%M") -- > sleep 300 > > Sometimes things like cursor blink or EDAC can be avoided/reduced. > > -- > You received this message because you are subscribed to the Google Groups > "mechanical-sympathy" group. > To unsubscribe from this group and stop receiving emails from it, send an > email to mechanical-sympathy+unsubscr...@googlegroups.com. > For more options, visit https://groups.google.com/d/optout. > -- You received this message because you are subscribed to the Google Groups "mechanical-sympathy" group. To unsubscribe from this group and stop receiving emails from it, send an email to mechanical-sympathy+unsubscr...@googlegroups.com. For more options, visit https://groups.google.com/d/optout.
