overcloud global response times are slower when 1 controller is offline

Solution In Progress - Updated -

Issue

  • We have just re-installed our overcloud with RHOSP13 Z8.

  • Whenever we take one controller node offline we see a jump in the amount of time it takes to run openstack commands.

  • Whenever we take one controller in the cluster offline using following commands:

# pcs cluster stop
# shutdown now -P
  • The following table explains the situation quite eloquently:
    Action execution time with all controllers online execution time with one controller down
    Volume Create x 1 real 0m2.911s user 0m1.488s sys 0m0.316s real 0m2.214s user 0m1.401s sys 0m0.336s
    Volume List real 0m2.732s user 0m1.581s sys 0m0.380s real 0m2.393s user 0m1.530s sys 0m0.354s
    Instance Create x 1 real 0m2.794s user 0m1.396s sys 0m0.249s real 0m33.635s user 0m1.467s sys 0m0.313s

Environment

  • Red Hat OpenStack Platform 13.0 (RHOSP)

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