Neal McBurnett wrote on 2005-12-31 07:35 UTC: > On Mon, Dec 19, 2005 at 11:31:22PM +0000, Markus Kuhn wrote: > > I suspect, the basic exercise will be running a little test routines on > > various NTP-synchronized hosts, that log the progression of > > clock_gettime(), gettimeofday(), etc. against whatever hardware counter > > register is available, just to see what actually happens these days at > > the API during a leap second with the very latest kernel versions. > > Anyone have software to watch this stuff which they want to share?
Try something along the lines of http://www.cl.cam.ac.uk/~mgk25/time/leap/timelog.c This records the BSD API, the POSIX API, and on Pentium CPUs also the Pentium timestamp counter. Command-line options allow you specify start time and duration of the recording. This is meant to be portable POSIX code, but has only been tested under Linux so far. Markus -- Markus Kuhn, Computer Laboratory, University of Cambridge http://www.cl.cam.ac.uk/~mgk25/ || CB3 0FD, Great Britain
