The End of Slow Networks: It's Time for a Redesign

被引：94

作者：

Binnig, Carsten ^{[1
]}

Crotty, Andrew ^{[1
]}

Galakatos, Alex ^{[1
]}

Kraska, Tim ^{[1
]}

Zamanian, Erfan ^{[1
]}

机构：

[1] Brown Univ, Dept Comp Sci, Providence, RI 02912 USA

来源：

PROCEEDINGS OF THE VLDB ENDOWMENT | 2016年 / 9卷 / 07期

基金：

美国国家科学基金会;

关键词：

D O I：

10.14778/2904483.2904485

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

The next generation of high-performance networks with remote direct memory access (RDMA) capabilities requires a fundamental rethinking of the design of distributed in memory DRNISs. These systems are commonly built, under the assumption that the network is the primary bottleneck and should be avoided at all costs, but this assumption no longer holds For instance, with InfiniBand FDI3 4x, the bandwidth available to transfer data across the network is in the same ballpark as the bandwidth of one memory channel. Moreover, RLTh/IA transfer latencies continue to rapidly improve as well. In this paper, we first argue that traditional distributed DBMS architectures cannot lake full advantage of high-performance networks and suggest a new architecture to address this problem. Then, we discuss initial results from a prototype implementation of our proposed architecture for OLTP and OLAF, showing remarkable performance improvements over existing designs.

引用

页码：528 / 539

页数：12