Messages in this thread | | | Date | Fri, 5 Jun 2015 10:28:54 -0700 | Subject | Re: [RFC][PATCH 4/4] time: Do leapsecond adjustment in gettime fastpaths | From | John Stultz <> |
| |
On Fri, Jun 5, 2015 at 7:12 AM, Richard Cochran <richardcochran@gmail.com> wrote: > On Fri, Jun 05, 2015 at 11:10:08AM +0200, Peter Zijlstra wrote: >> Firstly I would strongly suggest such applications not use UTC because >> of this, I think TAI was invented for just this reason. > > So I wonder whether the bug in the original post affects TAI timers as > well...
No, I don't believe so. The TAI timeline doesn't have a discontinuity(ie: each second is properly represented over a leapsecond), so it wouldn't have the same issue with the specifics of when that discontinuity is applied. Our TAI adjustment is done atomically with the leap adjustment, so late or not it shouldn't have problematic behavior.
thanks -john
| |