Clock skew problems between nodes on an IBM x3850 M2 system

Solution Unverified - Updated -

Issue

  • Kernel picks the TSC as a clock source on two-node x3850 M2 system causing a noticeable clock skew.
  • Following messages from ntp are seen in the logs :
June  8 17:51:42 hostname ntpd[5658]: frequency error 776 PPM exceeds tolerance 500 PPM
June  8 17:52:32 hostname ntpd[5658]: synchronized to 10.94.59.92, stratum 1
June  8 17:52:32 hostname ntpd[5658]: frequency error 776 PPM exceeds tolerance 500 PPM
June  8 17:53:01 hostname ntpd[5658]: no servers reachable
June  8 17:53:38 hostname ntpd[5658]: synchronized to 10.94.59.91, stratum 1
June  8 17:53:38 hostname ntpd[5658]: frequency error 777 PPM exceeds tolerance 500 PPM
June  8 17:53:39 hostname ntpd[5658]: frequency error 638 PPM exceeds tolerance 500 PPM
June  8 17:55:35 hostname ntpd[5658]: frequency error 517 PPM exceeds tolerance 500 PPM
June  8 17:55:52 hostname ntpd[5658]: no servers reachable
June  8 17:57:14 hostname ntpd[5658]: synchronized to 10.94.59.91, stratum 1
June  8 17:57:14 hostname ntpd[5658]: frequency error 777 PPM exceeds tolerance 500 PPM
June  8 17:57:15 hostname ntpd[5658]: frequency error 569 PPM exceeds tolerance 500 PPM

Environment

  • Red Hat Enterprise Linux 5.6, 5.7
  • IBM x3850 M2

Subscriber exclusive content

A Red Hat subscription provides unlimited access to our knowledgebase, tools, and much more.

Current Customers and Partners

Log in for full access

Log In

New to Red Hat?

Learn more about Red Hat subscriptions

Using a Red Hat product through a public cloud?

How to access this content