Setting noselect for all sources seems to have no impact on standard deviation.
Disabling all forms of dynamic tic (CONFIG_HZ_PERIODIC=y) seems to have some
effect in reducing the number of “D H”, but does not appear to have much of an
impact on the standard deviation. I am returning CONFIG_NO_HZ_IDLE=y.
> On Nov 14, 2016, at 05:35, Miroslav Lichvar <mlich...@redhat.com> wrote:
> Another experiment would be to try
> configuring all sources with the noselect option and see how much
> stddev improves. If it does improve significantly, it would suggest a
> problem with the synchronization of the clock. Maybe the kernel is too
> slow (the nohz=off option might help) or there is a problem in the
> chrony's loop.