[Linuxptp-users] High frequency

[Collins, Cris L.]

We have a dozen very similar RHEL 7.2 systems configured with Linuxptp 1.6 and the same NIC driver version on each. Some of them look great, some show a frequency of "-100000000" and an offset of ~ -2333333 and some say Clockcheck: clock jumped forward or running faster than expected. Everyone is on the same switch.

I can't see a program like chronyd ot NTP that would be adjusting the time. Is there a way to see what programs are adjusting the clock?

What are some things we can do to debug the problem machines?

Thank you for any direction that you may be able to provide.

[Richard Cochran]

Post by Collins, Cris L.
We have a dozen very similar RHEL 7.2 systems configured with Linuxptp 1.6 and the same NIC driver version on each. Some of them look great, some show a frequency of "-100000000" and an offset of ~ -2333333 and some say Clockcheck: clock jumped forward or running faster than expected. Everyone is on the same switch.

Sounds like a HW bug.

Post by Collins, Cris L.
What are some things we can do to debug the problem machines?

Which HW are you using?

Thanks,
Richard

[Collins, Cris L.]

Another strange bit is without PTP or any other time protocol running, on many of the systems the system clock is drifting rapidly after syncing it to hardware clock manually. Within twenty minutes the system clock is 7 minutes ahead of the hardware clock. Is there way to see what is affecting the system clock? There are about 8 machines acting this way, another 3 with seemingly the same hardware, OS, and software on the same switch that are not exhibiting the behavior.

The following is 24 hours after syncing the System clock to the hardware clock manually
date;hwclock
Thu Apr 20 18:58:01 CDT 2017
Thu 20 Apr 2017 04:38:20 PM CDT -0.310003 seconds

ethtool -i ens2
driver: mlx4_en
version: 3.1-1.0.4 (30 Sep 2015)
firmware-version: 2.35.5100
bus-info: 0000:83:00.0
supports-statistics: yes
supports-test: yes
supports-eeprom-access: no
supports-register-dump: no
supports-priv-flags: yes


ethtool -T ens2
Time stamping parameters for ens2:
Capabilities:
hardware-transmit (SOF_TIMESTAMPING_TX_HARDWARE)
software-transmit (SOF_TIMESTAMPING_TX_SOFTWARE)
hardware-receive (SOF_TIMESTAMPING_RX_HARDWARE)
software-receive (SOF_TIMESTAMPING_RX_SOFTWARE)
software-system-clock (SOF_TIMESTAMPING_SOFTWARE)
hardware-raw-clock (SOF_TIMESTAMPING_RAW_HARDWARE)
PTP Hardware Clock: 2
Hardware Transmit Timestamp Modes:
off (HWTSTAMP_TX_OFF)
on (HWTSTAMP_TX_ON)
Hardware Receive Filter Modes:
none (HWTSTAMP_FILTER_NONE)
all (HWTSTAMP_FILTER_ALL)



-----Original Message-----
From: Richard Cochran [mailto:***@gmail.com]
Sent: Thursday, April 20, 2017 5:23 PM
To: Collins, Cris L.
Cc: linuxptp-***@lists.sourceforge.net
Subject: Re: [Linuxptp-users] High frequency

Post by Collins, Cris L.
We have a dozen very similar RHEL 7.2 systems configured with Linuxptp 1.6 and the same NIC driver version on each. Some of them look great, some show a frequency of "-100000000" and an offset of ~ -2333333 and some say Clockcheck: clock jumped forward or running faster than expected. Everyone is on the same switch.

Sounds like a HW bug.

Post by Collins, Cris L.
What are some things we can do to debug the problem machines?

Which HW are you using?

Thanks,
Richard