Equality Workloads with Priority Based Association in the Cloud

The complex applications are attracted by cloud computing is increased in day to day manner to run in remote data centers. Many applications needs parallel processing capabilities. The nature of parallel application is decrease the utilization of CPU resources as parallelism grows, because of the communication and synchronization between parallel processes. It challenging task but important for the data centers to reach a certain level of utilization of its nodes at the time of maintaining the level of responsiveness of parallel jobs. The existing parallel scheduling mechanisms take irresponsibleness as the top important and need nontrivial effort to make them work for the data centers in the cloud era. In this we introduced a parallel priority based technique to consolidate parallel workload in the cloud. We influence virtualization technology to partition the computing capacity of every node into two tiers, the fore virtual machine (VM) tier (with high CPU priority) and the background VM tier (with low CPU priority). They provided scheduling algorithms for parallel jobs to make effective utilization of the two tier VMs to improve the responsiveness of these jobs. Our wide range experiments display that our parallel scheduling algorithm expressively outperforms commonly used algorithms such as extensible Argonne scheduling system in a data center setting. This technique is practically and experimentally effective for consolidating parallel workload in data centers. Keywords— cloud computing, consolidation, scheduling technique, parallel priority.