Lessons learned from building a globally distributed database service from the ground up
Dharma Shukla explores Azure Cosmos DB, discussing the internals of the system design and the various design trade-offs Azure had to make while building the service. Dharma also shares his experience and lessons learned operating a globally distributed database service worldwide while maintaining comprehensive service level agreements.
Talk Title | Lessons learned from building a globally distributed database service from the ground up |
Speakers | Dharma Shukla (Microsoft) |
Conference | O’Reilly Velocity Conference |
Conf Tag | Build Resilient Distributed Systems |
Location | San Jose, California |
Date | June 20-22, 2017 |
URL | Talk Page |
Slides | |
Video | Talk Video |
Dharma Shukla explores Azure Cosmos DB—a massively scalable, multitenant, globally distributed database service that he and his team have spent the last seven years building. Cosmos DB is currently operating across more than 34 geographical regions, managing hundreds of petabytes of indexed data and serving 100s of trillions of requests every day from thousands of customers worldwide. The database system allows developers to elastically scale both throughput and storage across any number of geographical regions on a single table; offers guaranteed single-digit millisecond low latency at the 99th percentile, 99.99% high availability, predictable throughput, and multiple well-defined consistency models; and offers comprehensive SLAs for latency, availability, throughput, and consistency. Azure Cosmos DB is used extensively within Microsoft and has been available to external Azure customers since 2015. Dharma discusses the internals of the system design and the various design trade-offs Azure had to make while building the service. Dharma also shares his experience and lessons learned operating a globally distributed database service worldwide while maintaining comprehensive service level agreements (SLAs).