Adaptive compressed caching: Design and implementation

In this paper, we reevaluate the use of adaptive com-pressed caching to improve system performance through the reduction of accesses to the backing stores. We pro-pose a new adaptability policy that adjusts the compressed cache size on-the-fly, and evaluate a compressed caching system with this policy through an implementation in a widely used operating system, Linux. We also redesign compressed caching in order to provide performance im-provements for all the tested workloads and we believe it addresses the problems faced in previous works and im-plementations. Among these fundamental modifications, our compressed cache is the first one to also compress file cache pages and to adaptively disable compression of clean pages when necessary. We tested a system with our adaptive compressed cache under many applications and benchmarks, each one with different memory pressures. The results showed perfor-mance improvements (up to 171.4%) in all of them if under memory pressure, and minimal overhead (up to 0.39%) when there is very light memory pressure. We be-lieve this work shows that this adaptive compressed cache design should be actually considered as an effective mech-anism for improvement in system performance.