Performance load test issues on OSP 8 with DPDK environment

Solution In Progress - Updated -

Issue

During performance load test with RTP calls and after PIM board takeover. It is possible to find dpdk_watchdog2 BLOCK in ovs-vswitchd.log in the compute node. This ends with restarting the openvswitch on the host:

2016-06-14T08:48:56.900Z|01564|ovs_rcu(vhost_thread1)|WARN|blocked 64000 ms waiting for dpdk_watchdog2 to quiesce
2016-06-14T08:48:56.900Z|00010|ovs_rcu(urcu3)|WARN|blocked 64000 ms waiting for dpdk_watchdog2 to quiesce
2016-06-14T08:48:57.051Z|00879|ovs_rcu|WARN|blocked 64000 ms waiting for dpdk_watchdog2 to quiesce
2016-06-14T08:50:00.900Z|00011|ovs_rcu(urcu3)|WARN|blocked 128000 ms waiting for dpdk_watchdog2 to quiesce
2016-06-14T08:50:00.900Z|01565|ovs_rcu(vhost_thread1)|WARN|blocked 128000 ms waiting for dpdk_watchdog2 to quiesce
2016-06-14T08:50:01.051Z|00880|ovs_rcu|WARN|blocked 128000 ms waiting for dpdk_watchdog2 to quiesce

Environment

Red Hat OpenStack Platform 8

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