A Novel Software-based Multi-path RDMA Solutionfor Data Center Networks

09/01/2020
by   Feng Tian, et al.
0

In this paper we propose Virtuoso, a purely software-based multi-path RDMA solution for data center networks (DCNs) to effectively utilize the rich multi-path topology for load balancing and reliability. As a "middleware" library operating at the user space, Virtuoso employs three innovative mechanisms to achieve its goal. In contrast to existing hardware-based MP-RDMA solution, Virtuoso can be readily deployed in DCNs with existing RDMA NICs. It also decouples path selection and load balancing mechanisms from hardware features, allowing DCN operators and applications to make flexible decisions by employing the best mechanisms (as "plug-in" software library modules) as needed. Our experiments show that Virtuoso is capable of fully utilizing multiple paths with negligible CPU overheads

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

page 2

page 3

page 4

10/08/2019

FlowDyn: Towards a Dynamic Flowlet Gap Detection using Programmable Data Planes

Data center networks offer multiple disjoint paths between Top-of-Rack (...
10/01/2020

CAFT: Congestion-Aware Fault-Tolerant Load Balancing for Three-Tier Clos Data Centers

Production data centers operate under various workload sizes ranging fro...
01/16/2020

A New Software Framework for Traffic Engineering: Path Cardinality and the Effect of Multipath on Residual Capacity

In this paper, we present a new traffic engineering (TE) software framew...
10/27/2021

Charon: Load-Aware Load-Balancing in P4

Load-Balancers play an important role in data centers as they distribute...
11/01/2017

Dynamic Load Balancing Strategies for Graph Applications on GPUs

Acceleration of graph applications on GPUs has found large interest due ...
01/15/2021

Boosting performance for software defined networks from traffic engineering perspective

Paths selection algorithms and rate adaptation objective functions are u...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.