QCon New York June 15-19, 2020 | | Containers at Web Scale Panel

Abstract

Containers and container management platforms are becoming a standard part of many infrastructures. At Facebook, Google, Netflix, and Uber container technologies have been a large part of their infrastructures for many years. By leveraging these technologies, each company has seen improvements in developer productivity, overall systems reliability and improvements in compute efficiency. Come to this session to hear how these improvements have been delivered, what lessons were learned during implementation and operations, and what the future looks like in the container management space.

Speaker: Kenny Yu

Software Engineer @Facebook

Kenny Yu is a software engineer at Facebook. For the past four years, Kenny has worked on Tupperware, Facebook’s cluster manager and container platform, with a large focus on container scheduling and orchestration. In that time, he has also improved the testing and developer experience for engineers at Facebook, working on things such as debugging tools and concurrency bug-finders.

Find Kenny Yu at

Speaker page

Speaker: Victor Marmol

Staff Software Engineer @Google

Victor is a Staff Software Engineer at Google and is one of the leaders of the Borg team. Borg is the cluster management system which runs all of Google’s compute jobs across the world; starting over 2 billion containers per week. He's worked on open sourcing some of Google’s containers infrastructure technology through lmctfy and cAdvisor. He also spent some time as a maintainer of Kubernetes and Docker's libcontainer. His current work around containers in Google is centered around automatic performance management and container migration.

Find Victor Marmol at

Speaker page

Speaker: Andrew Leung

Senior Software Engineer @Netflix

Andrew Leung (@anwleung) is a senior software engineer at Netflix, where he helps design, build, and operate Titus. Prior to Netflix, he worked at NetApp, EMC, and several startups on distributed file and storage systems. He received his Ph.D. from the University of California, Santa Cruz in 2009.

Find Andrew Leung at

Speaker page

https://www.linkedin.com/in/anwleung

Speaker: Xiaojian Huang

Engineer Manager @Uber

Xiaojian is the first engineer starting the container effort in Uber 3 years ago, and later transit into management role with a team that build container infrastructure. Right now, they are running the largest clusters in Uber which carry majority of Uber critical workloads. They are leveraging Mesos, Docker, Aurora, as well as building systems to provide container management as a service to all the Uber engineers.

This year, they took an new initiative and looked into more convergence and better efficiency by introducing an unified scheduler to run batch and stateful workloads together with stateless services.

Prior to Uber, Xiaojian worked on HDFS / Datacenter automation @Facebook and Middleware @Oracle

Find Xiaojian Huang at

Speaker page

Speaker: Wendy Dembowski

Staff Software Engineer @Google

Wendy is a Staff Software Engineer at Google. She works on Software Supply Chain Management for Google Cloud. Wendy founded and continues to lead Greafeas, an open source, structured metadata API.