PRMS: Page Reallocation Method for SSDs

Solid-State Disks (SSDs) have been currently considered as a promising candidate to replace hard disks, due to their significantly short access time, low power consumption, and shock resistance. SSDs, however, have drawbacks such that their write throughput and life span are decreased by random-writes, nearly regardless of SSDs controller designs. Previous studies have mostly focused on better designs of SSDs controller and reducing the number of write operations to SSDs. We suggest another method that reallocates data pages that tend to be simultaneously written to contiguous blocks. Our method gathers write operations during a period of time and generates write traces. After transforming each trace to a set of transactions, our method mines frequent itemsets from the transactions and reallocates the pages of the frequent itemsets. In addition, we introduce an algorithm that reallocates the pages of the frequent itemsets with moderate time complexity. Experiments using TPC-C workload demonstrated that our method successfully reduce 6% of total logical block access.

[1]  Johannes Gehrke,et al.  MAFIA: a maximal frequent itemset algorithm for transactional databases , 2001, Proceedings 17th International Conference on Data Engineering.

[2]  Tomasz Imielinski,et al.  Mining association rules between sets of items in large databases , 1993, SIGMOD Conference.

[3]  Li Xiong,et al.  Frequent pattern mining for kernel trace data , 2008, SAC '08.

[4]  Sang Lyul Min,et al.  A space-efficient flash translation layer for CompactFlash systems , 2002, IEEE Trans. Consumer Electron..

[5]  T. Lane,et al.  Sequence Matching and Learning in Anomaly Detection for Computer Security , 1997 .

[6]  Ramakrishnan Srikant,et al.  Fast algorithms for mining association rules , 1998, VLDB 1998.

[7]  Sang-Won Lee,et al.  A log buffer-based flash translation layer using fully-associative sector translation , 2007, TECS.

[8]  Jim Griffioen,et al.  Reducing File System Latency using a Predictive Approach , 1994, USENIX Summer.

[9]  Jian Pei,et al.  CLOSET: An Efficient Algorithm for Mining Frequent Closed Itemsets , 2000, ACM SIGMOD Workshop on Research Issues in Data Mining and Knowledge Discovery.

[10]  Li-Pin Chang,et al.  On efficient wear leveling for large-scale flash-memory storage systems , 2007, SAC '07.

[11]  Jian Pei,et al.  Mining frequent patterns without candidate generation , 2000, SIGMOD '00.

[12]  Xiaodong Zhang,et al.  Understanding intrinsic characteristics and system implications of flash memory based solid state drives , 2009, SIGMETRICS '09.

[13]  Chris Clifton,et al.  Developing custom intrusion detection filters using data mining , 2000, MILCOM 2000 Proceedings. 21st Century Military Communications. Architectures and Technologies for Information Superiority (Cat. No.00CH37155).

[14]  Erez Zadok,et al.  Amino : Extending ACID Semantics to the File System , 2006 .

[15]  Yuanyuan Zhou,et al.  Mining block correlations to improve storage performance , 2005, TOS.

[16]  Erez Zadok,et al.  Extending ACID semantics to the file system , 2007, TOS.