Re: [net-next 5/6] ixgbe: add hardware timestamping support

On Mon, Oct 17, 2011 at 9:44 AM, Richard Cochran
[off-list ref] wrote:

On Mon, Oct 17, 2011 at 05:21:01AM -0700, Jeff Kirsher wrote:

quoted

The cyclecounter has the potential to miss a wrap-around of the
systim register (this should occur no more often than every 35
seconds) unless some activity regarding the cycle counter occurs at
least once within this time. This version adds a cycle counter read
every time the watchdog task is run, which should occur at least once
within this timeframe. Any packets being timestamped will also count
as a read due to the call to timecompare_update.

So, is this wrap around due to the fact that you are tied to the
system time via time_compare? Or, putting it another way, can't you
program the hardware time stamping unit so that the registers have
some reasonable resolution (like 64 bits worth of nanoseconds) and
just offer RAW timestamps?

The wrap around is due to hardware limitations. The ixgbe devices
cannot support 64bits worth of nanoseconds and still have the ability
to adjust the frequency in parts per billion. A larger increment
increases the resolution available for frequency adjustments, but
decreases the time it takes for the cycle counter to wrap around.

I would really like to move away from the timecompare hacks and
towards a proper PHC->SYS PPS solution.

I agree that this is the correct approach. The timecompare
functionality does have issues.

quoted

This version fixes an issue regarding timecompare not updating
detected skew after the clock offset is changed due to ptpd or outside
influence from the OS. Now the skew detection is forced just before we
hand a timestamp up to the kernel stack

Again, doing the update thing on every packet won't work for real
world PTP scenarios.

Which is why the PHC solution is better. Work on implementing this
support is in progress. Out of curiosity, what is the sync rate for
the scenario that breaks this? I would like to try that rate out on my
setup.

Thanks,
Richard
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html