And Eat It Too: High Read Performance in Write-Optimized HPC I/O Middleware File Formats

Abstract

The two I/O middleware layer examined in this paper are the Adaptable IO System (ADIOS), a library-based approach developed at Oak Ridge National Laboratory to provide a high-level IO API that can be used in place of netCDF or HDF5 to do much more aggressive write-behind and efficient reordering of data locations within the file; and the Parallel Log-structured Filesystem (PLFS), a stackable FUSE filesystem approach developed at Los Alamos National Laboratory that decouples concurrent writes to improve the speed of checkpoints. We observe that not only can write-optimized I/O middleware be built to not penalize read speeds, but for important workloads, techniques that improve write performance can, perhaps counterintuitively, improve read speeds over reading from a contiguously organized file format. In the remainder of this paper, we investigate this further through case studies of PLFS and ADIOS on simulation checkpoint restarts.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Nov 15, 2009
Accession Number
ADA512866

Entities

People

  • Garth Gibson
  • Jay Lofstead
  • John Bent
  • Karsten Schwan
  • Manish Parashar
  • Matthew T Wolf
  • Meghan Wingate
  • Milo Polte
  • Norbert Podhorszki
  • Qing Liu
  • Scott A. Klasky

Organizations

  • Carnegie Mellon University

Tags

Communities of Interest

  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Abstracts
  • Application Software
  • Bandwidth
  • Case Studies
  • Computer Programs
  • Contracts
  • Data Analysis
  • Department Of Defense
  • Digital Information
  • Fault Tolerance
  • Hard Copy
  • Information Operations
  • Middleware
  • Standards
  • Storage
  • Three Dimensional
  • Workload

Fields of Study

  • Computer science

Readers

  • Parallel and Distributed Computing.