DataLayer: High throughput, low latency at scale - Boost the performance of your distributed database

Learn how distributed DBs (Cassandra, MongoDB, RethinkDB, etc) solve the problem of scaling persistent storage, but introduce latency as data size increases and become I/O bound. In single server DBs, latency is solved by introducing caching. In this talk, Akbar Ahmed shows you how to improve the performance of distributed DBs by using a distributed cache to move the data layer performance limitation from I/O bound to network bound.

Akbar is the CEO and founder of DynomiteDB, a framework for turning single server data stores into linearly scalable, distributed databases. He is an Apache Cassandra certified developer and a Cassandra MVP, enjoys the expressiveness of both SQL and alternative query languages, and evaluates the entire database ecosystem every 6 months and has an MBA in Information Systems.

If you have any feedback about this or any other Compose article, drop the Compose Articles team a line at We're happy to hear from you.