Aerospike : High Performance NoSQL store with flash optimization
High Performance databases are need of most widely used real-time internet services. Low latency and high throughput has always been of utmost importance in bringing traffic to the site. Aerospike is one such noSql store designed to maintain under 1 millisecond response time even under peak load with billions of records spanning over tera bytes in size. Optimized for flash storage, aerospike can be scaled by adding new nodes and provides high operational efficiency due to minmal manual involvement. In this talk I am going to introduce Aerospike, talk about it’s architecture and show how easy it is to start with Aerospike and expand as per need.
NoSQL space is very vast and consists of various stores designed for specific use cases. Aerospike, which belongs to key-value store category, is specifically designed with scalability at it’s root. Scaling Aerospike is as easy as adding a node to already running cluster, and aerospike will take of re-distributing it’s data and balance the nodes. Zero maintainence being one of the primary goals of Aerospike, it requires almost negligible manual involvment to keep it long running with high efficiency. Aerospike has been battle tested to maintain under 1 millisecond response time with over 1 million requests and billions of records.
In this session I am going to talk about Aerospike’s architecture which is built using Paxos like algorithm for peer to peer communication. Will further discuss it’s data model and walk through a demo to show Aerospike in action. I will be discussing some real world use cases where Aerospike can be used and makes most sense. This session will also introduce aerospike’s UDF and Aggregation framework with which one can extend Aerospike’s built-in capabilities and also run analytic queries to get deep insight of the data. I will also compare with other NoSQL stores and describe the use cases that Aerospike has been specifically designed for.
Gagan Agarwal is a Sr. Principal Engineer at Snapdeal and is currently heading Personalization and Recommendation team at Snapdeal. He has close to 10 years of experience in Software industry and have worked in domains like e-commerce, digital advertising, e-Governance, Document and Content Management, Customer Communication Management, Media Buy Management etc. Gagan has worked and developed challenging softwares ranging from multi-tiered Web Applications with millions of users to batch processing of multi tera byte data. Apart from expertise in Java/JEE technologies, Gagan has been working with Big Data technologies like Hadoop, Spark, Cascading, Pig, Hive, Sqoop, Oozie, Kafka etc. and nosql stores like Hbase, Cassandra, Aerospike, Mongo, Neo4j etc for past several years. Gagan is a seasoned speaker and has spoken on several technology conferences on topics ranging from Big Data Processing, No SQL Stores (key-value, graph based, column oriented stores) to functional programming languages.