Messages in this thread | | | Date | Wed, 27 May 2015 16:09:36 -0700 | Subject | Re: Leap Second, nohz, and ABSOLUTE timers problem | From | John Stultz <> |
| |
On Wed, May 27, 2015 at 7:55 AM, Prarit Bhargava <prarit@redhat.com> wrote: > John, > > We've identified an issue with ABSOLUTE timers and the leap second that > effects, AFAICT, all kernels. > > This is the scenario. Suppose you have a userspace program that has an > ABSOLUTE timer that will expire @ midnight (00:00:00) UTC. The timer expiry > should occur at the end of the leap second event but it does not always occur > at the end. In fact it may occur during the leap second event and effectively > one second too early. > > In the NOHZ kernel, timers are not necessarily aligned to the ticks the > following does happen in userspace:
Hrm.. Thanks for the report! Looks like this could happen on !NOHZ as well, and is an artifact of the fact the leapsecond is being applied by a timer.
I'm working on a patch and will send it out shortly.
thanks -john
| |