Messages in this thread |  | | Date | Tue, 2 Jun 2015 07:09:46 -0700 | Subject | Re: [RFC][PATCH 4/4] time: Do leapsecond adjustment in gettime fastpaths | From | John Stultz <> |
| |
On Tue, Jun 2, 2015 at 2:21 AM, Peter Zijlstra <peterz@infradead.org> wrote: > On Tue, Jun 02, 2015 at 11:01:54AM +0200, Ingo Molnar wrote: >> > Currently, leapsecond adjustments are done at tick time. >> > >> > As a result, the leapsecond was applied at the first timer >> > tick *after* the leapsecond (~1-10ms late depending on HZ), >> > rather then exactly on the second edge. > > So why not program a hrtimer to expire at the exact right time? Then > even the VDSO gets its time 'right' and you avoid touching all the > fast paths.
Well, the hrtimer won't always expire at the exact right time (due to irq latency, possible clockevent drift/error, etc) , so that would close the window a bit, but wouldn't eliminate the issue.
thanks -john
|  |