Scaling a Distributed Stateful System: A LinkedIn Case Study

Website Maintenance Alert

Due to scheduled maintenance, the USENIX website may not be available on Monday, March 17, from 10:00 am–6:00 pm Pacific Daylight Time (UTC -7). We apologize for the inconvenience and thank you for your patience.

If you would like to register for NSDI '25, SREcon25 Americas, or PEPR '25, please complete your registration before or after this time period.

Friday, June 08, 2018 - 10:00 am10:55 am

Sai Kiran Kanuri, LinkedIn

Abstract: 

A system is called scalable if it manages to take additional users and requests without losing any noticeable performance. Scaling a data system involves significant movement and replication of data within a cluster. This can put considerable load on a system that is already running hot, affecting the service experience.

Some of the topics that I would touch upon include:

  • Replication
  • Data distribution
  • Load balancing
  • Cluster management
  • Client Data
  • Capacity Management
  • Tuning

Open Access Media

USENIX is committed to Open Access to the research presented at our events. Papers and proceedings are freely available to everyone once the event begins. Any video, audio, and/or slides that are posted after the event are also free and open to everyone. Support USENIX and our commitment to Open Access.

BibTeX

Presentation Video 

Presentation Audio