Availability-Aware Scheduling Method for Parallel Task in Cloud Environment

Cloud computing is a newly emerging computing paradigm that advocates supplying users everything as a service. Cloud computing becomes more and more popular in large scale computing and data store recently due to it enables the sharing of computing resources that are distributed all over the world. Nowdays, cloud computing is a hot research area in IT industries and in academic institutes. Particularly, the problem of resource availability cannot be ignored in cloud environment. High availability is a key requirement in the design and development of cloud computing systems where processors operate at different speeds and are not continuously available for computation. This paper addresses the main factors of availability requirement for parallel tasks and the influencing factors of availability support for computational resources based on the graph structure of parallel task and tree cloud platform. We present the formulas to quantify the availability. Through being aware of availability, we realize the availability matching between availability requirement and availability support, and develop two availability-aware scheduling algorithms, that are Afsa and Agsa. The simulation experimental results show that such algorithms can effectively enhance the resource availability and reliability in cloud environment. It is significant to improve the success rate of parallel task scheduling in practice.