Access-Aware In-memory Data Cache Middleware for Relational Databases

Data systems are typically categorized into source-of-truth systems that serve as primary stores for the user-generated writes, reads and other complex queries. In recent years, scientists regularly encounter limitations due to large data sets in many areas, especially for the query of big data. In this paper, we construct Access-aware In-memory Data Cache Middleware (AIDCM) for relational databases, which is an integral part of RDBMS and in-memory cache. On one hand, AIDCM provides low latency while supporting log-based trigger in the presence of updates to maintain data consistency. On the other hand, AIDCM translate the frequently accessed data to column-oriented in-memory cache by the column access frequency to ensure heavy hitter queries. We also present the experimental results to describe our middleware supporting a wide range of applications with big data.