On Thu 2022-02-17 13:57 +0100, Frederic Weisbecker wrote: > Hmm, but does it matter? The issue seem to be that we can enter in idle loop without > flushing vmstat. Or am I missing something else? Frederic, Yes, this is indeed the concern. So, the idea I had was to invoke quiet_vmstat() regardless if the tick was stopped or not. If I understand correctly, this should resolve the issue. Furthermore, folding of all outstanding differentials will only occur when required. Thus performance should be negligible. Kind regards, -- Aaron Tomlin
