期刊名称：Bulletin of the Technical Committee on Data Engineering
出版年度：2014
卷号：37
期号：2
出版社：IEEE Computer Society
摘要：With the development of flash memory technology, flash-based solid state drives (SSDs) are graduallyused in more and more devices and applications. In addition to characteristics of flash memory itself,a unique characteristic of SSDs, namely internal parallelism, should also be considered to improveperformance of SSDs-based DBMSs, especially query processing. In this paper, we first describe theinternal architecture of SSDs and the resulting internal parallelism of SSDs. In the second part, wepresent a parallel table scan operator, ParaScan, that exploits the internal parallelism of SSDs. Basedon ParaScan, we then propose a parallel hash join operator, ParaHashJoin, and a parallel aggregationmodel, ParaAggr. Experimental results show that ParaScan, ParaHashJoin and ParaAggr on SSDssignificantly outperform traditional table scan, hash join and aggregation. Furthermore, sort, as animportant basic operator for other complex operators, can also be redesigned based on ParaScan. Wedesign a parallel sort algorithm, ParaSort and then present a parallel ParaSort operator in the thirdpart. Looking forward, database query processing by exploiting internal parallelism of SSDs, can begeneralized to other kinds of SSDs with similar internal parallel characteristics.
