The Red Hat OpenStack® Platform scheduler is optimized to run as many virtual machines on a single host as possible. However, with modern x86 servers, the default behavior can lead to non-optimal performance of individual virtual machines. CPU pinning and OpenStack Nova filters can make the Red Hat OpenStack Platform scheduler aware of NUMA in order to achieve better performance for specific virtual machines.
In this session, Razique Mahroua will demonstrate how to optimize performance when deploying large Red Hat OpenStack Platform environments. We'll cover:
- How to optimize distributed virtual routing and performance tuning, including the NUMA architecture, CPU pinning, host aggregates, hugepages, and compute scheduler filters.
- The details of how to configure and use of DVR, the routing traffic direction flows, nodes components, and the management of DVR routers.
The session is perfect for network engineers, network operators, cloud operators, and cloud administrators who need to manage and tune networking performance in Red Hat OpenStack Platform.
The OpenStack® Word Mark and OpenStack Logo are either registered trademarks / service marks or trademarks / service marks of the OpenStack Foundation, in the United States and other countries and are used with the OpenStack Foundation's permission. We are not affiliated with, endorsed or sponsored by the OpenStack Foundation or the OpenStack community.