netdev - Re: [PATCH net-next 0/3] PHC frequency fine tuning

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite for Android: free password hash cracker in your pocket

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <1478642213.7545.36.camel@intel.com>
Date:   Tue, 8 Nov 2016 21:56:54 +0000
From:   "Keller, Jacob E" <jacob.e.keller@...el.com>
To:     "netdev@...r.kernel.org" <netdev@...r.kernel.org>,
        "richardcochran@...il.com" <richardcochran@...il.com>
CC:     "tglx@...utronix.de" <tglx@...utronix.de>,
        "Manfred.Rudigier@...cron.at" <Manfred.Rudigier@...cron.at>,
        "ulrik.debie-os@...ig.org" <ulrik.debie-os@...ig.org>,
        "stefan.sorensen@...ctralink.com" <stefan.sorensen@...ctralink.com>,
        "davem@...emloft.net" <davem@...emloft.net>,
        "Kirsher, Jeffrey T" <jeffrey.t.kirsher@...el.com>,
        "john.stultz@...aro.org" <john.stultz@...aro.org>,
        "intel-wired-lan@...ts.osuosl.org" <intel-wired-lan@...ts.osuosl.org>
Subject: Re: [PATCH net-next 0/3] PHC frequency fine tuning

On Tue, 2016-11-08 at 22:49 +0100, Richard Cochran wrote:
> This series expands the PTP Hardware Clock subsystem by adding a
> method that passes the frequency tuning word to the the drivers
> without dropping the low order bits.  Keeping those bits is useful
> for
> drivers whose frequency resolution is higher than 1 ppb.
> 

Makes sense.

> The appended script (below) runs a simple demonstration of the
> improvement.  This test needs two Intel i210 PCIe cards installed in
> the same PC, with their SDP0 pins connected by copper
> wire.  Measuring
> the estimated offset (from the ptp4l servo) and the true offset (from
> the PPS) over one hour yields the following statistics.
> 
> > 
> >        |   Est. Before |    Est. After |   True Before |    True
> > After |
> > --------+---------------+---------------+---------------+--------
> > -------|
> > min    | -5.200000e+01 | -1.600000e+01 | -3.100000e+01 |
> > -1.000000e+00 |
> > max    | +5.700000e+01 | +2.500000e+01 | +8.500000e+01 |
> > +4.000000e+01 |
> > pk-pk: | +1.090000e+02 | +4.100000e+01 | +1.160000e+02 |
> > +4.100000e+01 |
> > mean   | +6.472222e-02 | +1.277778e-02 | +2.422083e+01 |
> > +1.826083e+01 |
> > stddev | +1.158006e+01 | +4.581982e+00 | +1.207708e+01 |
> > +4.981435e+00 |
> 
> Here the numbers in units of nanoseconds, and the ~20 nanosecond PPS
> offset is due to input/output delays on the i210's external interface
> logic.
> 
> With the series applied, both the peak to peak error and the standard
> deviation improve by a factor of more than two.  These two graphs
> show
> the improvement nicely.
> 
>   http://linuxptp.sourceforge.net/fine-tuning/fine-est.png
> 
>   http://linuxptp.sourceforge.net/fine-tuning/fine-tru.png
> 

Wow, nice! I'll take a look at the actual patches in a few minutes, but
this is a really nice improvement!

Thanks,
Jake

> 
> Thanks,
> Richard
> 
> Richard Cochran (3):
>   ptp: Introduce a high resolution frequency adjustment method.
>   ptp: igb: Use the high resolution frequency method.
>   ptp: dp83640: Use the high resolution frequency method.
> 
>  drivers/net/ethernet/intel/igb/igb_ptp.c | 16 ++++++++--------
>  drivers/net/phy/dp83640.c                | 14 +++++++-------
>  drivers/ptp/ptp_clock.c                  |  5 ++++-
>  include/linux/ptp_clock_kernel.h         |  8 ++++++++
>  4 files changed, 27 insertions(+), 16 deletions(-)
>