Security-Aware Orchestration of Linear Workflows on Distributed Resources

Abstract

In hybrid and multi-tier distributed architectures, where data may have different security requirements and typically require processing in a pipeline fashion, resource allocation has become particularly challenging. In such environments, it is crucial to use security-aware and effective resource allocation techniques, in order to ensure the secure processing of the workload and achieve a satisfactory Quality of Service (QoS). Towards this direction, in this paper we examine the performance of security-aware resource allocation strategies for linear workflow (LW) jobs in an environment of distributed resources. Only a subset of the resources is considered secure and thus suitable for processing high risk LW jobs. Low risk LW jobs may be executed on either secure or non-secure resources. Two commonly used routing techniques are adapted in order to incorporate security awareness. Their performance is evaluated through simulation. Several scenarios are investigated, with different subset sizes of the secure resources, as well as different probabilities for a LW job to be considered high risk. The simulation results provide useful insights into how the percentage of high risk LW jobs affects the performance in each of the examined cases of secure resources.