overcloud global response times are slower when 1 controller is offline
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.