System-Call Based Problem Diagnosis for PVFS

Abstract

We present a syscall-based approach to automatically diagnose performance problems, server-to-client propagated errors, and server crash/hang problems in PVFS. Our approach compares the statistical and semantic attributes of syscalls across PVFS servers in order to diagnose the culprit server, under these problems, for different file-system benchmarks-dd, PostMark and IOzone-in a PVFS cluster.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jun 01, 2009
Accession Number
ADA512852

Entities

People

  • Eugene E. Marinelli Iii
  • Jiaqi Tan
  • Keith A. Bare
  • Michael P. Kasick
  • Priya Narasimhan
  • Rajeev Gandhi

Organizations

  • Carnegie Mellon University

Tags

Communities of Interest

  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Abstracts
  • Algorithms
  • Computer Programs
  • Computers
  • Data Science
  • Debugging
  • Engineering
  • Failure Mode And Effect Analysis
  • High Performance Computing
  • Networks
  • Packet Loss
  • Predictive Modeling
  • Statistical Algorithms
  • Statistical Analysis
  • Statistical Data
  • Training
  • Workload

Fields of Study

  • Computer science

Readers

  • Distributed Systems and Data Platform Development
  • Fault Tolerant Diagnosis of Black and White Balloon Isolation Tests Using ¥.
  • Parallel and Distributed Computing.