Efficient outer join data skew handling in parallel

  • Slides: 23
Download presentation

目录 遇到的问题 论文:Efficient outer join data skew handling in parallel DBMS 其他论文

目录 遇到的问题 论文:Efficient outer join data skew handling in parallel DBMS 其他论文

Part 1 论文:Efficient outer join data skew handling in parallel DBMS

Part 1 论文:Efficient outer join data skew handling in parallel DBMS

Outer join 实例 Ø 考虑如下Outer join实例 R(x, a) S(y, b) T(z, d)

Outer join 实例 Ø 考虑如下Outer join实例 R(x, a) S(y, b) T(z, d)

Outer join 实例 Ø 假设先进行 R left outer join S,再进行left outer join T

Outer join 实例 Ø 假设先进行 R left outer join S,再进行left outer join T

Outer join 实例 Ø 假设先进行 R left outer join S,再进行left outer join T

Outer join 实例 Ø 假设先进行 R left outer join S,再进行left outer join T

Outer join 实例

Outer join 实例

Implementation and Analysis of Join Algorithms to handle skew for the Hadoop Map/Reduce Framework

Implementation and Analysis of Join Algorithms to handle skew for the Hadoop Map/Reduce Framework Ø 主要内容 学位论文,较为详细的介绍了Hadoop中Join算法的实现和分析。 Ø 创新点 提出了Hybrid Join:结合Map-side join和Reduce-side join。

Implementation and Analysis of Join Algorithms to handle skew for the Hadoop Map/Reduce Framewor

Implementation and Analysis of Join Algorithms to handle skew for the Hadoop Map/Reduce Framewor Ø 主要内容 学位论文,较为详细的介绍了Hadoop中Join算法的实现和分析。 Ø 创新点 提出了Hybrid Join:结合Map-side join和Reduce-side join。

Implementation and Analysis of Join Algorithms to handle skew for the Hadoop Map/Reduce Framewor

Implementation and Analysis of Join Algorithms to handle skew for the Hadoop Map/Reduce Framewor Ø 主要内容 学位论文,较为详细的介绍了Hadoop中Join算法的实现和分析。 Ø 创新点 提出了Hybrid Join:结合Map-side join和Reduce-side join。

Implementation and Analysis of Join Algorithms to handle skew for the Hadoop Map/Reduce Framewor

Implementation and Analysis of Join Algorithms to handle skew for the Hadoop Map/Reduce Framewor Ø 主要内容 学位论文,较为详细的介绍了Hadoop中Join算法的实现和分析。 Ø 创新点 提出了Hybrid Join:结合Map-side join和Reduce-side join。 Ø 处理数据倾斜: • 简单范围分区算法 • 虚拟范围分区算法