Network is unstable between overcloud nodes and ovs-vswitchd consume much CPU after a deployment, update or upgrade

Solution Unverified - Updated -

Issue

  • After or while running openstack overcloud deploy, openstack overcloud update run or openstack overcloud upgrade run, network connectivity is randomly broken between overcloud nodes
    Ping between overcloud nodes doesn't work. Ping to some overcloud nodes works well, but ping to some other nodes doesn't work at all.
  • ovs-vswitchd process consumes CPU extremely

    # pidstat -p ALL -rudvwsRU --human -h
      Time          USER       PID    %usr    %system  %guest   %wait    %CPU   CPU ...
    21:21:50    openvswitch    339639 3045.4%    1.7%    0.0%    0.0% 3047.1%    53 ...
                                      ^^^^^^^                         ^^^^^^^
    
  • The issue is solved for a few minutes by restarting openvswitch.
    However, the issue recurs a few minutes later.

Environment

  • Red Hat OpenStack Platform 17.1

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