Handling multi-dimensional complex queries in key-value data stores

作者：

Highlights：

• We propose SP-Index, a two-level indexing scheme, to support efficient complex queries of large scale multi-dimensional datasets.

• We implement SPIKE with SP-Index and have applied itto Cassandra to achieve a key-value store that supports multi-dimensional complex queries.

• Our experimental results show that SPIKE can achieve dozens of times better performance than comparing methods.

• We discuss the application scenarios that SPIKE is suited for, and the limitations of the proposed approach.

摘要

•We propose SP-Index, a two-level indexing scheme, to support efficient complex queries of large scale multi-dimensional datasets.•We implement SPIKE with SP-Index and have applied itto Cassandra to achieve a key-value store that supports multi-dimensional complex queries.•Our experimental results show that SPIKE can achieve dozens of times better performance than comparing methods.•We discuss the application scenarios that SPIKE is suited for, and the limitations of the proposed approach.

论文关键词：Big data,Key-value store,NoSQL,Range query,kNN query,Multi-attribute query,Index,Multi-dimensional dataset

论文评审过程：Received 17 July 2014, Revised 19 December 2016, Accepted 3 February 2017, Available online 4 February 2017, Version of Record 24 February 2017.

论文官网地址：https://doi.org/10.1016/j.is.2017.02.001