Vancouver, BC
May 21-24, 2018

Event Details


Painless Cache allocation in Cloud

As more and more workloads move off dedicated hardware into the cloud as virtual appliances, it is critical to ensure predictable performance and guarantee the quality of service. Contention for hardware resource such as cache, memory and network bandwidth affects performance in the same vein as resources such as CPU and RAM,especially for latency and jitter sensitive Network Virtual Functions (NFV) workload. We introduce Resource Management Daemon (RMD), a system daemon running on generic Linux platforms, to provide cache allocation capability to the resource control arsenal.

In this talk we discuss the Resource Management Daemon (RMD) architecture, components, and the design of monitor component that will track and fine tune allocations to meet service level agreements. We then show how RMD significantly benefits the NFV use case. Last but not least we share how RMD can be leveraged by cloud and container orchestration engines to effectively introduce cache allocation capabilities.


What can I expect to learn?

In this talk we discuss the Resource Management Daemon (RMD) architecture, components, security, RESTful API, and the design of monitor component that will track the host level resource allocations and fine tune allocations to meet service level agreements. We then show how RMD significantly benefits the NFV use case. Last but not least we share how RMD can be leveraged by cloud and container orchestration engines to effectively introduce cache allocation capabilities without having to expose all its complexities to high level orchestration systems.

Wednesday, May 23, 1:50pm-2:00pm
Difficulty Level: Beginner
Intel
Lin Yang is a senior engineer of OTC (open source technology center) in Intel. He has proven experiences on CI/CD(continuous integration/continuous delivery) area and DevOps methodology. After worked on OTC, Lin has been technical leader and core developer for Developer Platform Team and was responsible for the design, development and operations of automation... FULL PROFILE
OpenStack-PDX Meetup Group, Organizer
Sunku Ranganath is a Network Software Engineer at Intel specializing in platform service assurance and active contributor to OPNFV Barometer & VSPERF projects. As the orgainzer of OpenStack & OpenInfra PDX meetup group, Sunku is passionate about reaching out to OpenStack & open source community for greater collaboration. Sunku's work has been lot of fun integrating and... FULL PROFILE