Considering block popularity in disk cache replacement for enhancing hit ratio with solid state drive

The Solid State Drive (SSD) is now becoming a main stream in storage systems. It is widely deployed as cache for hard disk drive (HDD) to speed up the execution of data intensive applications. In this paper we propose a novel block replacement algorithm for flash-based disk cache, named Block Replacement based on Popularity(BRP). Using the frequency and recency of block access, it calculates the block popularity to select the block which will be evicted from SSD. This avoids cache pollution and keeps popular blocks in SSD cache, leading to high hit ratio. Meanwhile, the proposed scheme reduces block replacements, and thus incurs less write operations to SSD. As a result, BRP enhances the performance of storage and the lifetime of SSD. Computer simulation demonstrates that the proposed scheme consistently outperforms five existing cache replacement algorithms with two different kinds of traces.

[1]  Sang Lyul Min,et al.  LRFU: A Spectrum of Policies that Subsumes the Least Recently Used and Least Frequently Used Policies , 2001, IEEE Trans. Computers.

[2]  Yannis Smaragdakis,et al.  EELRU: simple and effective adaptive page replacement , 1999, SIGMETRICS '99.

[3]  Xiao Qin,et al.  WEC: Improving Durability of SSD Cache Drives by Caching Write-Efficient Data , 2015, IEEE Transactions on Computers.

[4]  Nimrod Megiddo,et al.  ARC: A Self-Tuning, Low Overhead Replacement Cache , 2003, FAST.

[5]  Jun Yang,et al.  CBM: A cooperative buffer management for SSD , 2014, 2014 30th Symposium on Mass Storage Systems and Technologies (MSST).

[6]  David Hung-Chang Du,et al.  Large Block CLOCK (LB-CLOCK): A write caching algorithm for solid state disks , 2009, 2009 IEEE International Symposium on Modeling, Analysis & Simulation of Computer and Telecommunication Systems.

[7]  Antony I. T. Rowstron,et al.  Migrating server storage to SSDs: analysis of tradeoffs , 2009, EuroSys '09.

[8]  Binny S. Gill.  On Multi-level Exclusive Caching: Offline Optimality and Why Promotions Are Better Than Demotions , 2008, FAST.

[9]  Dan Feng,et al.  Improving flash-based disk cache with Lazy Adaptive Replacement , 2013, 2013 IEEE 29th Symposium on Mass Storage Systems and Technologies (MSST).

[10]  Lingfang Zeng,et al.  A popularity-aware buffer management to improve buffer hit ratio and sequentiality for Solid State Drive , 2012, 2012 Digest APMRC.

[11]  Jianhua Li,et al.  ExLRU: A unified write buffer cache management for flash memory , 2011, 2011 Proceedings of the Ninth ACM International Conference on Embedded Software (EMSOFT).

[12]  Goetz Graefe,et al.  The five-minute rule twenty years later, and how flash memory changes the rules , 2007, DaMoN '07.

[13]  John Wilkes,et al.  My Cache or Yours? Making Storage More Exclusive , 2002, USENIX Annual Technical Conference, General Track.

[14]  Lingfang Zeng,et al.  A Popularity-Aware Buffer Management to Improve Buffer Hit Ratio and Write Sequentiality for Solid-State Drive , 2013, IEEE Transactions on Magnetics.

[15]  Yuanyuan Zhou,et al.  The Multi-Queue Replacement Algorithm for Second Level Buffer Caches , 2001, USENIX Annual Technical Conference, General Track.