OpenStack Neutron with ML2 OVS has always been a challenging component in terms of performance and scalability. However, in recent releases, several enhancements and bug-fixes have resulted in significant improvements in overall reliability, performance and scalability of Neutron. In this talk, we will share the results of our testing (both control-plane and data-plane) at large scale and provide a detailed data-driven analysis that explores the true scale limits and bottlenecks of Neutron. We also discuss better ways to tune Neutron configuration parameters for large scale. Moving forward, we expect further improvements based on planned optimizations.
With these changes, is Neutron ready for large-scale production deployments? If customers are planning to deploy vanilla Neutron in their production deployments, what can they expect? How does the reference implementation stack up against other commercial alternatives? These are some of the questions the presentation tries to address.
The attendees should expect to learn the following from this session based on the analysis of results from our large scale testing focused on Neutron.
- How does OpenStack Neutron perform? How well does it scale?
- What enhancements and bug-fixes have resulted in improvements to Neutron?
- What are the key reasons for the observed limitations and bottlenecks?
- What tools and techniques are useful to run scalability and performance testing?
- What plans exist for further improvements?
- With all these changes, what can be expected from Neutron in the near future?
- Is Neutron ready for large scale production deployments?