Identifier

etd-07012013-211426

Degree

Doctor of Philosophy (PhD)

Department

Computer Science

Document Type

Dissertation

Abstract

Developing platforms for large scale data processing has been a great interest to scientists. Hadoop is a widely used computational platform which is a fault-tolerant distributed system for data storage due to HDFS (Hadoop Distributed File System) and performs fault-tolerant distributed data processing in parallel due to MapReduce framework. It is quite often that actual computations require multiple MapReduce cycles, which needs chained MapReduce jobs. However, Design by Hadoop is poor in addressing problems with iterative structures. In many iterative problems, some invariant data is required by every MapReduce cycle. The same data is uploaded to Hadoop file system in every MapReduce cycle, causing repeated data delivering and unnecessary time cost in transferring this data. In addition, although Hadoop can process data in parallel, it does not support MPI in computing. In any Map/Reduce task, the computation must be serial. This results in inefficient scientific computations wrapped in Map/Reduce tasks because the computation can not be distributed over a Hadoop cluster, especially a Hadoop cluster on a traditional high performance computing cluster. Computational technologies have been extensively investigated to be applied into many application domains. Since the presence of Hadoop, scientists have applied the MapReduce framework to biological sciences, chemistry, medical sciences, and other areas to efficiently process huge data sets. In our research, we proposed a hybrid framework of iterative MapReduce and MPI for molecular dynamics applications. We carried out molecular dynamics simulations with the implemented hybrid framework. We improved the capability and performance of Hadoop by adding a MPI module to Hadoop. The MPI module enables Hadoop to monitor and manage the resources of Hadoop cluster so that computations incurred in Map/Reduce tasks can be performed in a parallel manner. We also applied the local caching mechanism to avoid data delivery redundancy to make the computing more efficient. Our hybrid framework inherits features of Hadoop and improves computing efficiency of Hadoop. The targeting application domain of our research is molecular dynamics simulation. However, the potential use of our iterative MapReduce framework with MPI is broad. It can be used by any applications which contain single or multiple MapReduce iterations, invoke serial or parallel (MPI) computations in Map phase or Reduce phase of Hadoop.

Date

2013

Document Availability at the Time of Submission

Release the entire work immediately for access worldwide.

Committee Chair

Park, Seung-Jong

Share

COinS