[ntp:questions] kernel precision on Linux

Nicholas Garfield Nicholas.Garfield at cern.ch
Thu Jan 29 15:26:54 UTC 2004


I am running RedHat 7.2 with all updates.  Following the instructions of FAQ
Section 6.4 I have established that the kernel is most likely not running a
nanokernel, nor the pps kit (looking in timex.h).
This agrees with when I run ntptime and check the status  (0x1 (PLL)) and
also ntpdc.  kerninfo reports precision at 1microsec, sysinfo reports
precision at -17 and "system flags:         auth monitor ntp kernel stats".

The FAQ also states:

" Are the individual kernel models compatible?

The most recent version known as nanokernel has different semantics for the
time_constant. When used with the old version 3 daemon, the PLL has a
tendency to oscillate, because the damping is too low.

When the old kernel implementation is used with the new version 4 daemon,
the PLL is too stiff, causing a slow adjustment to frequency changes.

When the new version 4 daemon has set the STA_NANO bit, the old version 3
daemon gets completely confused by nanoseconds which are believed to be
microseconds. As it seems, the daemon does not clear STA_NANO during
startup, so the only solution is to reboot or clear that flag by other

Professor David L. Mills wrote:

The old and new kernel code does use different time constant ranges. The
current ntpd and API do understand and adjust accordingly. The old xntpd
will probably be off by a factor of 16 in the time constant. That is
absolutely certain to cause unstable operation.

If you have an even older implementation, you probably can't compile the
daemon, or the daemon will not use the kernel PLL."

The FAQ then continues to talk about linux differences........ How much can
these differences affect the precision of a stock redhat box when running
ntpd v4.

So I guess I am running the old kernel implmentation with the new daemon
ntp4.2.  Does anybody know by how much this will affect time precision?

Also, anyone patched the RedHat kernel with the nanokernel mods?  I would
love to have a recipe of how to do it :D



More information about the questions mailing list