Quantitative Cluster Sizing

How many shards should I have? How many nodes should I have? What about replicas? Do these questions sound familiar? The answer is often ‘it depends’. This talk will outline the factors that affect sizing and walk you through a quantitative approach to estimating the configuration and size of your cluster.

Christian Dahlqvist

Christian is part of the Solutions Architecture team at Elastic, helping users build solutions using the most innovative and advanced open source distributed search engine. He previously worked at Basho Technologies in a variety of client facing roles, assisting customers in developing applications on top of the NoSQL database Riak. Previous to this he spent many years working with the design and integration of highly available real-time changing and policy systems within the telecommunications sector across the world.

Ryan Schneider

Ryan Schneider has worked as a backend and distributed system engineer since 2004 and worked in companies both large and small. Ryan has a BS in CS, an MS in Software Development and Management, and a passion for architecture and building great systems. At night he also taught as an adjunct professor for the RIT Software Engineering department. Ryan is excited to now be able to blend his love for teaching, elasticsearch, and building great software into his role as a Technical Trainer for Elastic where he enjoys helping enable other engineers to build amazing products using Elasticsearch, Kibana, and Logstash.