Building and maintaining complex distributed systems
June 19–20, 2017: Training
June 20–22, 2017: Tutorials & Conference
San Jose, CA

Scheduling deep dive for orchestration systems

Dharmesh Kakadia (Microsoft)
1:15pm–1:55pm Wednesday, June 21, 2017
Level: Intermediate
Average rating: ***..
(3.00, 4 ratings)

Who is this presentation for?

  • Developers and technology decision makers

Prerequisite knowledge

  • A basic understanding of orchestration

What you'll learn

  • Understand how scheduling works in Mesos, Kubernetes, and Docker Swarm and how this influences the strengths and limitations of these systems


Orchestration systems are central to modern infrastructure. Many options exist, such as Mesos, Kubernetes, and Docker Swarm, and it’s often difficult to choose the right one. Orchestration systems all have different design trade-offs. Despite best efforts, these choices are not always clear to developers using these systems.

One key difference between various orchestration systems is their treatment of scheduling. The choice of scheduling directly or indirectly affects many crucial aspects of business, including the availability of critical components, resource utilization, and response times. Dharmesh Kakadia describes the fundamentals of scheduling and explores the scheduling algorithms implemented by various orchestration systems, highlighting similarities, differences, and the consequences of the design choices for the users.

Photo of Dharmesh Kakadia

Dharmesh Kakadia


Dharmesh Kakadia is a developer and a researcher at Microsoft, where he works on distributed systems. Dharmesh is the author Apache Mesos Essentials. He is passionate about open source and likes to work at the intersection of data and cloud. He enjoys reading in his free time.