[ntp:questions] IEEE 1588 (PTP) at the nanosecond level?
joegwinn at comcast.net
Thu Mar 20 13:38:22 UTC 2014
In article <yvqdnQukc7QJB7fOnZ2dnUVZ_vudnZ2d at megapath.net>, Hal Murray
<hal-usenet at ip-64-139-1-69.sjc.megapath.net> wrote:
> In article <190320142025178186%joegwinn at comcast.net>,
> Joe Gwinn <joegwinn at comcast.net> writes:
> >The original issue was to be able to drop IRIG support in honor of PTP
> >via the ethernet infrastructure we always need.
> How stable is your local clock?
These systems are tied to GPS with Rubidium local oscillators. The end
nodes have crystal oscillators, some temperature compensated, and very
few being oven stabilized.
> What sort of accuracy to you need?
Varies. In some systems, it's a hard limit -- absolute error cannot
exceed one microsecond. In others, it's that we are trying to
synchronize independent subsystems to a fraction of a microsecond with
great reliability, which leads us to focus on the probability
distribution of errors - the distribution tails matter.
> How much traffic will be on the ethernet you want to use?
Varies as well. The timing-related traffic is negligible. The
application traffic is significant, is a mix of big (1.5 Kbyte) and
small (64 byte) packets, but still a gigabit enet link is loafing.
The big issue is as always timing-related packets being buffeted by the
application traffic, because we care about outliers, not just means and
medians. In many cases, this is solved by having a dedicated LAN for
timing-related traffic, but this isn't always possible.
More information about the questions