Development of Comprehensive Parallel I/O Benchmarking Tool for HPC Cluster File Systems

Abstract

High Performance Computing Clusters uses parallel file systems such as Lustre, GlusterFS for better I/O throughput with multiple clients. These file systems are implemented over high speed interconnects like 10G, Quadrics, Myinet and Infiniband. Parallel scientific applications require high performance I/O support from underlying file systems. The objective of this work is to evaluate and analyze performance of parallel file systems in HPC cluster with different configuration parameters with development of a comprehensive bench-marking tool. The developed tool measures the performance of different data I/O and meta-data operations under various workloads. This paper briefly describes various cluster file systems, parallel I/O approaches and different Message Passing Interface (MPI) implementations supporting MPI-IO and throughput results for different I/O scenarios.

Authors and Affiliations

M Swarnalatha , P. Durgadevi, T. Chindrella Priyadharshini, M. Hemalatha

Keywords

Related Articles

Novel Approach to Crosstalk Avoidance in RLC Modelled Interconnects Using Bus Encoder

In this paper, we have proposed efficient bus encoder for crosstalk avoidance in RLC modelled interconnects. In past years many encoding methods have been proposed which dealt with only RC modelled VLSI inter-connects.D...

Multi Core Processor Arrays Cores Optimization in AES Engines

In the present scenario protecting the sensitive information is done by several encryption standards. AES encryption is modern technique which is based on the principle of substitution-permutation network. Advanced encr...

Design of High Pass Fir Filter Using Rectangular, Hanning and Kaiser Window Techniques

Digital filter are widely used in the world of communication and computation .On the other hand to design a Digital Finite Impulse Response (FIR) filter that satisfies all the required condition is challenging one. In t...

Diabetic Retinopathy Screening

using fundus camera, we capture the images of eye and find out the disorders in retina. These images are to be processed for better diagnosis and planning of treatment. Retinal image segmentation is greatly required to...

Fault phase selection and fault Identification in weak-infeed side

Traditional low voltage phase selector and sequence current based fault phase selector will not operate satisfactory under weak infeed condition. The study proposes a new method of fault phase selection for transmission...

Download PDF file
  • EP ID EP20359
  • DOI -
  • Views 267
  • Downloads 3

How To Cite

M Swarnalatha, P. Durgadevi, T. Chindrella Priyadharshini, M. Hemalatha (2015). Development of Comprehensive Parallel I/O Benchmarking Tool for HPC Cluster File Systems. International Journal for Research in Applied Science and Engineering Technology (IJRASET), 3(5), -. https://www.europub.co.uk/articles/-A-20359