Opposites Attract: Virtual Cluster Embedding for Profit

TL;DR

This paper introduces Tetris, an online algorithm for efficient virtual cluster embedding, and DSP, a demand-specific pricing model that enhances profit and fairness in cloud network resource allocation.

Contribution

It proposes a novel online embedding algorithm and a demand-specific pricing model for virtual clusters, improving resource multiplexing and fairness.

Findings

Tetris increases the number of virtual clusters multiplexed over physical infrastructure.

DSP pricing model ensures customers pay only for their requested resources.

The combined approach improves provider profit and maintains fairness.

Abstract

It is well-known that cloud application performance critically depends on the network. Accordingly, new abstractions for cloud applications are proposed which extend the performance isolation guarantees to the network. The most common abstraction is the Virtual Cluster V C(n, b): the n virtual machines of a customer are connected to a virtual switch at bandwidth b. However, today, not much is known about how to efficiently embed and price virtual clusters. This paper makes two contributions. (1) We present an algorithm called Tetris that efficiently embeds virtual clusters arriving in an online fashion, by jointly optimizing the node and link resources. We show that this algorithm allows to multiplex more virtual clusters over the same physical infrastructure compared to existing algorithms, hence improving the provider profit. (2) We present the first demand-specific pricing model called DSP for virtual clusters. Our pricing model is fair in the sense that a customer only needs to pay for what he or she asked. Moreover, it features other desirable properties, such as price independence from mapping locations.