Resource Bundles: Using Aggregation for Statistical Large-Scale Resource Discovery and Management

Abstract

Resource discovery is an important process for finding suitable nodes that satisfy application requirements in large loosely-coupled distributed systems. Besides inter-node heterogeneity, many of these systems also show a high degree of intra-node dynamism, so that selecting nodes based only on their recently observed resource capacities can lead to poor deployment decisions resulting in application failures or migration overheads. However, most existing resource discovery mechanisms rely mainly on recent observations to achieve scalability in large systems. In this paper, we propose the notion of a resource bundle -a representative resource usage distribution for a group of nodes with similar resource usage patterns -that employs two complementary techniques to overcome the limitations of existing techniques: resource usage histograms to provide statistical guarantees for resource capacities, and clustering-based resource aggregation to achieve scalability. Using trace-driven simulations and data analysis of a month-long PlanetLab trace, we show that resource bundles are able to provide high accuracy for statistical resource discovery, while achieving high scalability. We also show that resource bundles are ideally suited for identifying group-level characteristics (e.g. hot spots, total group capacity).To automatically parameterize the bundling algorithm, we present an adaptive algorithm that can detect online fluctuations in resource heterogeneity.

Trade-off among timeliness, messages and accuracy for large-Ssale information management

“…The main drawback of this work is that it only considers numeric parameters (such as effective bandwidth or number of processes) to perform the resource discovery. [CC10] propose a clustering technique that is based on the aggregation of resource bundles for the resource discovery in Grid systems. Their clustering technique is important to ensure a large scalability and the robustness against failures.…”

“…Moreover, different market mechanisms lead to different peaks and distributions of the allocations. Cardosa and Chandra [CC10] analyze statistical aggregation for the resource allocation. The information retrieval aggregates historical data, which builds the basis for the prediction mechanisms.…”