Nitin Dhawas

Large scale data processing is increasingly common in Cloud Computing systems like Hadoop, Mapreduce etc. In these systems, files are split into many small blocks and all blocks are replicated over several servers. To process files efficiently, each job is divided into many tasks and each task is allocated to a server to deal with a file block. Because network bandwidth is a scarce resource in these systems. Enhancing task data locality (placing tasks on servers that contain their input blocks) is crucial for the job completion time. Although there have been many approaches on improving data locality, most of them either are greedy and ignore global optimization, or suffer from high computation complexity. To address these problems, we propose a heuristic task scheduling algorithm in which an initial task allocation will be produced at first, and then the job completion time can be reduced gradually by tuning the initial task allocation. By taking a global view, the algorithm can ad...

1,2,3Student, Dept. IT Engineering, PCET’s NMIET Pune, Maharashtra, India 4 Professor, Dept. IT Engineering, PCET’s NMIET Pune, Maharashtra, India ---------------------------------------------------------------------***--------------------------------------------------------------------Abstract Fine grained access management could be a demand for knowledge stored in untrusted servers like clouds. Due to the massive volume of data, redistributed key management schemes square measure most popular over centralized ones. Usually coding and cryptography square measure quite expensive and not sensible once user’s access knowledge from resource constrained devices. We tend to propose a redistributed attribute primarily based encryption (ABE) method with quick coding, outsourced cryptography and user revocation. Our scheme is incredibly specific to the context of mobile cloud because the storage of encrypted knowledge and therefore the partial decryption of cipher text square measure keen a...