Fast Compaction Algorithms for NoSQL Databases
Mainak Ghosh, Indranil Sen Gupta, Shalmoli Gupta, Nirman Kumar · 2015
Compaction plays a crucial role in NoSQL systems to ensure a high overall read throughput. In this work, we formally define compaction as an optimization problem that attempts to minimize disk I/O. We prove this problem to be NP-Hard. We then propose a set of algorithms and mathematically analyze upper bounds on worst-case cost. We evaluate the proposed algorithms on real-life workloads. Our results show that our algorithms incur low I/O costs and that a compaction approach using a balanced tree is most preferable.