Performance comparison of differentNoSQL structure orientations

Abstract: This study proposes a performance comparison between the different structures of NoSQL databases; document, key-value, column and graph. A second study is also conducted, when looking at performance comparison between three different NoSQL databases, all of the same structure; document based, the databases that are tested here are; MongoDB, OrientDB and Couchbase. Performance tests are conducted using a benchmarking tool YCSB (Yahoo! Cloud Serving Benchmark), and by looking at time to execute and throughput (operations/ second). Beside benchmarking literature reviews are conducted to be able to understand the different NoSQL structures, and to elaborate our benchmarking results. Every NoSQL structure and database in our benchmark is tested in the same way, a loading phase of 1k, 10k and 100k entries, and a running phase with a workload of approximately 50% reads and 50% updates with 1k, 10k and 100k operations. The finding of this study is that there are differences in performance, both between different structures and between same structured NoSQL databases. Document based OrientDB was the highest performing database at high volumes of data, and key-value store database Redis performed best at low volumes of data. Reasons for performance differences are both linked to specific trademarks of the structural orientation, the usage of the specific attributes of CAP theorem, storage type and development language.