Re: [PATCH 6/7] Cpuidle: Deal with timer expiring in the past
From: Len Brown <lenb@kernel.org>
Date: 2014-03-21 23:10:27
Also in:
lkml
From: Len Brown <lenb@kernel.org>
Date: 2014-03-21 23:10:27
Also in:
lkml
Tuukka, I've reproduced this negative on a 48 thread 2-socket Xeon during boot (seen it only once, so far). expected_us gets calculated to be -1, which is truthful, since the next timer return value was about 500ns in the past and our math truncates. This, in turn, confuses the heck out of menu's prediction of the next event to be over 500 sec in the future. I suspect more breakage is lurking, so I'll poke some more... Len Brown, Intel Open Source Technology Center