用于二级缓存的一种改进的自适应缓存管理算法

在机群系统或数据库服务器等应用环境下，由于本地内存资源限制，某些大内存应用与磁盘交互过多，会严重损害其性能.在高速网络支持下，把其他节点内存或采用专门的内存服务器作为系统的二级缓存，可减少对磁盘访问并提高应用性能.在二级缓存应用模式下，基于LIRS算法并对其存在的缺点进行改进，提出了一种自适应缓存管理算法LIRS-A. LIRS-A可根据应用访问特征自适应调整，避免了LIRS不适应某些具有时间局部性模式的情况.在TPC-H应用中，LIRS-A比LIRS最多有7.2%的性能提升；在网络流分析数据库的典型Groupby查询中，LIRS-A比LIRS的命中率最多可提高31.2%.

An Improved Adaptive Buffer Replacement Algorithm Used for Second Level Buffer

In a cluster or a database server system, the performance of some data intensive applications will be degraded much because of the limited local memory and large amount of interactions with slow disk. In high speed network, utilizing remote memory of other nodes or customized memory server to be as second level buffer can decrease access numbers to disks and benefit application performance. With second level buffer mode, this paper made some improvements for a recently proposed buffer cache replacement algorithm-LIRS, and brings forward an adaptive algorithm-LIRS-A. LIRS-A can adaptively adjust itself according to application characteristic, thus the problem of not suiting for time locality of LIRS is avoided. In TPC-H benchmarks, LIRS-A could improve hit rate over LIRS by 7.2 % at most. In a Groupby query with network stream analyzing database, LIRS-A could improve hit rate over LIRS by 31.2% at most. When compared with other algorithms, LIRS-A also show similar or better performance.