The Tail at Scale - Ideas behind building large scale latency tolerant distributed systems.

Papers We Love Meetup

Software techniques that tolerate latency variability are vital to building responsive large-scale web services. Systems that respond to user actions quickly, within 100ms, feel more fluid and natural to users than those that take longer. Improvements in Internet connectivity and the rise of warehouse-scale computing systems have enabled web services that provide fluid responsiveness while consulting multi-terabyte datasets spanning thousands of servers. For example, the Google search system updates query results interactively as the user types, predicting the most likely query based on the prefix typed so far, performing the search and showing the results within a few tens of milliseconds.

This is a “Papers We Love” meetup. We will discuss the paper - The Tail at Scale - by Jeff Dean and Luiz André Barroso.

Discussant: Piyush Goel will present the paper. Piyush is Vice President of Engineering at Capillary Technologies. He has vast experience with building systems from ground up. Piyush is also an active member of various communities, and is passionate about sharing insights from his work.

If you’d like to respond to the discussion, nominate yourself by leaving a comment here -

- It is recommended that everyone comes to the session having read the paper.
- The speaker will present the paper and keep the session interactive with the audience.
- We will discuss the paper and ancillary topics around it and how they are used in other systems.

Participation: Registered members will receive the Zoom link. Or, you can watch the livestream of the discussion via this page.

Slides -