Empirical Evaluation of Content-based Pub/Sub Systems over Cloud Infrastructure

Abstract

Pub/Sub systems permit users to submit subscriptions and notify interested users of the events detected in a distributed way. Moving a Pub/Sub system to a cloud infrastructure is for high performance and scalability. This paper describes how to migrate two Pub/Sub systems i.e. PADRES and OncePubSub to Xen Cloud Platform, especially proposes black-box method, grey-box method and white-box method so as to take full advantage of cloud mechanisms. This paper then conducts a series of experiments on the Pub/Sub systems in the cloud to evaluate benefits and costs. The experimental results indicate that the black-box method does not always take effect although it can be implemented easily, the grey-box method is more appropriate to a Pub/Sub system if its workload features and brokers' roles are known in advance. Further, the experimental results show the white-box method, combined the load balance mechanism both in the cloud and in a Pub/Sub system, can achieve satisfying performance and scalability especially facing the workload with unidentified distribution.

Mobile Publish/Subscribe System for Intelligent Transport Systems over a Cloud Environment

“…Results are presented in Figs. [12][13][14], which indicate that memory usage, total number of packets and packet rate, increases with increase in the number of publishers and subscribers. To test the performance of the real-time event matching capacity we perform a series of experiments by setting different numbers of rules for the subscriptions.…”

“…Zhang B. et al [12] provide the idea of moving two Pub/Sub systems -PADRES and OncePubSub over a cloud infrastructure -Xen platform for high performance and scalability. This paper suggests three methods for mapping a Pub/Sub system into a cloud infrastructure -Black-box method, Grey-box method, and White-box method.…”

Design and evaluation of a Pub/Sub service in the cloud

“…To evaluate the performance and scalability of OPS4Cloud in comparison with Pub/Sub systems in [5], we design and conduct experiments similar to the ones in [5] in accordance with the experimental methodology proposed in [5]. To verify the load balance capability of OPS4Cloud, we also conduct a region splitting experiment and a region expansion experiment.…”

“…As stated in [5], we choose four metrics: CPU utilization rate per VM, memory consumed per VM, system throughput, and average event response time. System throughput denotes the total number of events processed in a unit time.…”

“…[5] presents three kinds of methods for migrating existing systems to cloud infrastructure, and carries out the migration of two existing Pub/Sub systems (OncePubSub and Padres) to XenServer.…”