H2Hadoop: Improving Hadoop Performance using the Metadata of Related Jobs
Author(s):
C. PRASANTH, S. MUNI KUMAR
Keywords:
H2Hadoop, MapReduce, Hadoop Performance, Data Mining
Abstract
Cloud Computing leverages Hadoop framework for process BigData in parallel. Hadoop has bound limitations that could be exploited to execute the work with efficiency. These limitations are largely as a result of knowledge vicinity within the cluster, jobs and tasks scheduling, and resource allocations in Hadoop. economical resource allocation remains a challenge in Cloud Computing MapReduce platforms. we propose H2Hadoop, that is an increased Hadoop design that reduces the computation price related to BigData analysis. The proposed architecture additionally addresses the difficulty of resource allocation in native Hadoop. H2Hadoop provides a better resolution for text data, like finding DNA sequence and also the motif of a DNA sequence. Also, H2Hadoop provides associate economical Data Mining approach for Cloud Computing environments. H2Hadoop design leverages on NameNode’s ability to assign jobs to the TaskTrakers (DataNodes) among the cluster. By adding management options to the NameNode, H2Hadoop will showing intelligence direct and assign tasks to the DataNodes that contain the desired knowledge while not causing the work to the complete cluster. Examination with native Hadoop, H2Hadoop reduces central processing unit time, range of browse operations, and another Hadoop factors.
Article Details
Unique Paper ID: 145489
Publication Volume & Issue: Volume 4, Issue 10
Page(s): 533 - 537
Article Preview & Download
Share This Article
Join our RMS
Conference Alert
NCSEM 2024
National Conference on Sustainable Engineering and Management - 2024