Abstract

The multi-tenancy concept in cloud data center (DC) networks paves the way towards advancements and innovation in the underlying infrastructure such as network virtualization. Multicast routing is essential in leveraging multi-tenancy to its full potential. However, traditional IP multicast routing is not suitable for DC networks due to the need to support a massive amount of multicast groups and hosts. State-of-the-art DC multicast routing approaches aim to overcome these scalability issues by, for instance, taking advantage of the symmetry of DC topologies and the programmability of DC switches to compactly encode multicast group information inside packets, thereby reducing the overhead resulting from the need to store the states of flows at the network switches. Although these approaches scale well with the number of multicast groups, they do not perform well with group sizes and, as a result, yield substantial traffic control overhead and network congestion. In this article, we present Bert, a scalable source-initiated DC multicast routing approach that scales well with both the number and size of multicast groups through the clustering of multicast group members where each cluster employs its own forwarding rules. Compared to the state-of-the-art approach, Bert yields much less traffic control overhead by significantly reducing packet header sizes and eliminating switch memory usage across the switches.

Highlights

  • Modern data center infrastructures have shifted from traditional on-premise physical servers to virtual networks where data and services exist and are connected across pools of data centers, both on-premises and in the cloud

  • We study a critical requirement of data center (DC) topologies, i.e., multicast scalability

  • To overcome Elmo’s aforementioned limitations, we propose in this article Bert, a source-initiated multicast routing for DCs

Read more

Summary

INTRODUCTION

Modern data center infrastructures have shifted from traditional on-premise physical servers to virtual networks where data and services exist and are connected across pools of data centers, both on-premises and in the cloud. Traditional IP multicast routing is primarily designed for arbitrary network topologies and Internet traffic, with a focus on reducing CPU and network bandwidth overheads, and is not suitable for DCs due to the need for supporting large numbers of groups in commodity switches with limited memory capability. Elmo [12], a recently proposed source-initiated multicast routing approach for DCs, overcomes the scalability issue and is shown to support millions of multicast groups with reasonable overhead in terms of switch state and network. To overcome Elmo’s aforementioned limitations, we propose in this article Bert, a source-initiated multicast routing for DCs. Unlike Elmo, Bert scales well with both the number and the size of multicast groups, and does so through clustering, by dividing the members of the multicast group into a set of clusters with each cluster employing its own forwarding rules.

RELATED WORK
CLUSTERED MULTICAST SOURCE ROUTING
MULTICAST GROUP CLUSTERING
POD-BASED VERSUS LEAF-BASED CLUSTERING
PERFORMANCE EVALUATION
Findings
CONCLUSION AND FUTURE DIRECTIONS
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call