并行处理中多路连接的偏斜处理
Handling Skew in Multiway Joins in Parallel Processing
摘要:
处理偏斜是查询处理中的主要挑战之一。在诸如MapReduce的分布式计算环境中,不期望数据到服务器的不均匀分布。我们希望在分布式环境中优化的主要措施之一是通信成本。在MapReduce作业中,这是从映射器传输到归约器的数据量。在本文中,我们将介绍一种新的技术来处理偏斜,当我们想在一个MapReduce回合中以最小的通信成本计算多路连接时。这种技术实际上是股份算法的适应[Afrati et.等人,TKDE 2011]。
英文摘要:
Handling skew is one of the major challenges in query processing. In distributed computational environments such as MapReduce, uneven distribution of the data to the servers is not desired. One of the dominant measures that we want to optimize in distributed environments is communication cost. In a MapReduce job this is the amount of data that is transferred from the mappers to the reducers. In this paper we will introduce a novel technique for handling skew when we want to compute a multiway join in one MapReduce round with minimum communication cost. This technique is actually an adaptation of the Shares algorithm [Afrati et. al, TKDE 2011].
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。