Presentation: Alibaba Container Platform Infrastructure - a Kubernetes Approach

Track: Software Defined Infrastructure: Kubernetes, Service Meshes, & Beyond

Location: Majestic Complex, 6th fl.

Duration: 10:35am - 11:25am

Day of week: Wednesday

Share this on:

Abstract

As one of the biggest data companies in the world, Alibaba provides thousands of on-line/off-line services to various customers to support their business. Most of those services are fully containerized and run against Alibaba container platform built on top of huge amount of clustered physical machines. A typical Alibaba container cluster consists of tens of thousands nodes and manages more than ten thousand heterogeneous applications.

With the rapid increase of popularity and flourish development activities in the community, Kuberenetes has become the standard for new application deployment and life cycle management. To adopt this emerging technology, we decided to fully integrate upstream Kubernetes into existing Alibaba container management system. We will present how we extend, scale Kubernetes to make this integration succeed in this talk.

Overall, we’d like to deliver the following key takeaways from this talk.

  • Architectural wise, Kubernetes is scalable. It can manage large scale cluster(more than 10K nodes) with minimal modification.
  • Kubernetes can support complicated business application deployments with its strong extendability. We built a set of new CRDs to satisfy the application requirements.
  • The scheduler plug-in mode make it possible to overcome the default scheduling limitation by developing a new scheduler as a replacement. We will share the design of our in-house Pod scheduler which scales extremely well.
  • It is important to keep the Kubernetes APIs unchanged during the integration in order to keep them as standard for different PAAS client.  We will share some of our integration tips for this rule.a

Speaker: Fei Guo

Senior Staff Engineer in Alibaba Container Platform Group

Fei Guo is currently a senior staff engineer in Alibaba Container Platform Group. He has more than 10 years of experience in compute resource management and performance optimization for virtualized and containerized environments. Before joining Alibaba, Fei worked in VMware and was the tech leader for vSphere DRS (distributed resource scheduler). He has authored/co-authored a few white papers and academic papers in these technical areas.

Find Fei Guo at

Similar Talks

Psychologically Safe Process Evolution in a Flat Structure

Director of Software Development @Hunter_Ind

Chris Lucian

Let's talk locks!

Software Engineer @Samsara

Kavya Joshi

Graceful Degradation as a Feature

Director of Product @GremlinInc

Lorne Kligerman

Scaling Infrastructure Engineering at Slack

Senior Director of Infrastructure Engineering @Slack

Julia Grace

Liberating Structures at Capital One

Agile Coach, Engineering @CapitalOne

Greg Myers

Making 'npm install' Safe

Software Engineer @agoric

Kate Sills

Tracks

Monday, 24 June

Tuesday, 25 June

Wednesday, 26 June