Skip to main content
OSTI.GOVU.S. Department of Energy Office of Scientific and Technical Information
U.S. Department of Energy
Office of Scientific and Technical Information
 

Performance measurement of a parallel Input/Output system for the Intel iPSC/2 Hypercube

Conference · · Performance Evaluation Review
 [1];  [1];  [1]
  1. Univ. of Virginia, Charlottesville, VA (United States)
+ Show Author Affiliations
The Intel Concurrent File System (CFS) for the iPSC/2 hypercube is one of the first production file systems to utilize the declustering of large files across numbers of disks to improve I/O performance. The CFS also makes use of dedicated I/O nodes, operating asynchronously, which provide file caching and prefetching. Processing of I/O requests is distributed between the compute node that initiates the request and the I/O nodes that service the request. The effects of the various design decisions in the Intel CFS are difficult to determine without measurements of an actual system. We present performance measurements of the CFS for a hypercube with 32 compute nodes and four I/0 nodes (four disks). Measurement of read/write rates for one compute node to one I/O node, one compute node to multiple I/O nodes, and multiple compute nodes to multiple I/O nodes form the basis for the study. Additional measurements show the effects of different buffer sizes, caching, prefetching, and file preallocation on system performance.
Research Organization:
Virginia Univ., Charlottesville, VA (USA). Inst. for Parallel Computation
Sponsoring Organization:
USDOE; Jet Propulsion Laboratory (JPL)
DOE Contract Number:
FG05-88ER25063
OSTI ID:
7820020
Report Number(s):
IPC-TR--91-002; CONF-9105215--1; ON: DE91014219
Conference Information:
Journal Name: Performance Evaluation Review Journal Issue: 1 Journal Volume: 19
Country of Publication:
United States
Language:
English

References (9)

A case for redundant arrays of inexpensive disks (RAID)
  • Patterson, David A.; Gibson, Garth; Katz, Randy H.
  • Proceedings of the 1988 ACM SIGMOD international conference on Management of data - SIGMOD '88 https://doi.org/10.1145/50202.50214
conference January 1988
Benchmarking the iPSC/2 hypercube multiprocessor journal September 1989
Prefetching in file systems for MIMD multiprocessors journal April 1990
Design, analysis, and simulation of I/O architectures for hypercube multiprocessors journal April 1990
Synchronized Disk Interleaving journal November 1986
The NX/2 operating system
  • Pierce, P.
  • Proceedings of the third conference on Hypercube concurrent computers and applications Architecture, software, computer systems, and general issues - https://doi.org/10.1145/62297.62341
conference January 1988
File concepts for parallel I/O conference January 1989
An evaluation of multiple-disk I/O systems journal January 1989
Multi-disk management algorithms
  • Livny, Miron; Khoshafian, Setrag; Boral, Haran
  • Proceedings of the 1987 ACM SIGMETRICS conference on Measurement and modeling of computer systems https://doi.org/10.1145/29903.29914
conference May 1987

Similar Records

Performance of the Intel iPSC/860 hypercube
Technical Report · Fri Jun 01 00:00:00 EDT 1990 · OSTI ID:6745398
Performance of the Intel iPSC/860 and Ncube 6400 hypercubes
Journal Article · Tue Jul 12 20:00:00 EDT 2005 · Parallel Computing · OSTI ID:5710182
Performance of three hypercubes. [Ametek S14, Intel iPSC, Ncube]
Technical Report · Fri May 01 00:00:00 EDT 1987 · OSTI ID:6595499

Related Subjects

97 MATHEMATICS AND COMPUTING
990200* -- Mathematics & Computers
COMPUTER ARCHITECTURE
COMPUTER OUTPUT DEVICES
COMPUTERS
HYPERCUBE COMPUTERS
PARALLEL PROCESSING
PERFORMANCE
PROGRAMMING