|International Journal of Computer Applications
|Foundation of Computer Science (FCS), NY, USA
|Volume 79 - Number 15
|Year of Publication: 2013
|Authors: B. Arunkumar, T. Ravichandran
B. Arunkumar, T. Ravichandran . De-De Dodging Algorithm for Scheduling Multiple Workflows in Hybrid Cloud. International Journal of Computer Applications. 79, 15 ( October 2013), 5-9. DOI=10.5120/13815-1808
Workflow-based applications usually consist of multiple instances depending on a single workflow, which are jobs with control or data dependencies to provide a well-defined scientific computation task, with each instances acting on its own input data. Due to the raise in convention of many applications currently, there is necessitating for high processing and storage capacity along with the consideration of cost and instance use and also without any deadlocks between those instances. To improve the performance of the entire system a high degree of concurrency is obtained by running multiple instances at the same time. On the other hand, since the amount of storage is limited on most systems, deadlock due to numerous storage requests would-be a problem. In this paper we have proposed a new dependency and deadlock avoidance (De-De algorithm) algorithm along with the consideration of both instance and value. The TCHC algorithm that comes to the decision of desiring which resource should be chartered from public providers is now combined with the newly proposed De-De algorithm considering that each instance of both single and multiple workflows should work without any deadlocks. To address this problem, we have combined two new concepts with the traditional problem of deadlock avoidance by proposing a single algorithm that can maximize active (not just allocated) resource utilization and minimize makespan. Our approach is based on the well-known banker's algorithm, but our algorithms make the important distinction between active and passive resources, which is not a part of previous approaches. Through simulation-based studies, we show how our proposed algorithms are better than the classic banker's algorithm.