Traffic characteristics of a distributed memory system

Jonathan M. Smith, David Farber

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

We believe that many distributed computing systems of the future will use distributed shared memory as a technique for interprocess communication. Thus, traffic generated by memory requests will be a major component of the traffic for any networks which connect nodes in such a system. In this paper, we study memory reference strings gathered with a tracing program we devised. We study several models. First, we look at raw reference data, as would be seen if the network were a backplane. Second, we examine references in units of "blocks", first using a one-block cache model and then with an infinite cache. Finally, we study the effect of predictive prepaging of these "blocks" on the traffic. We provide a novel representation of memory reference data which can used to calculate interarrival distributions directly. Integrating communication with computation can be used to control both traffic and performance.

Original languageEnglish
Pages (from-to)143-154
Number of pages12
JournalComputer Networks and ISDN Systems
Volume22
Issue number2
DOIs
Publication statusPublished - 1991 Jan 1
Externally publishedYes

Fingerprint

Computer systems
Data storage equipment
Communication
Traffic control
Distributed computer systems

Keywords

  • computer networks
  • distributed computation
  • distributed memory
  • networking
  • traffic characteristics

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Traffic characteristics of a distributed memory system. / Smith, Jonathan M.; Farber, David.

In: Computer Networks and ISDN Systems, Vol. 22, No. 2, 01.01.1991, p. 143-154.

Research output: Contribution to journalArticle

Smith, Jonathan M. ; Farber, David. / Traffic characteristics of a distributed memory system. In: Computer Networks and ISDN Systems. 1991 ; Vol. 22, No. 2. pp. 143-154.
@article{212e32fa2fa246778a9f93ead0a1c512,
title = "Traffic characteristics of a distributed memory system",
abstract = "We believe that many distributed computing systems of the future will use distributed shared memory as a technique for interprocess communication. Thus, traffic generated by memory requests will be a major component of the traffic for any networks which connect nodes in such a system. In this paper, we study memory reference strings gathered with a tracing program we devised. We study several models. First, we look at raw reference data, as would be seen if the network were a backplane. Second, we examine references in units of {"}blocks{"}, first using a one-block cache model and then with an infinite cache. Finally, we study the effect of predictive prepaging of these {"}blocks{"} on the traffic. We provide a novel representation of memory reference data which can used to calculate interarrival distributions directly. Integrating communication with computation can be used to control both traffic and performance.",
keywords = "computer networks, distributed computation, distributed memory, networking, traffic characteristics",
author = "Smith, {Jonathan M.} and David Farber",
year = "1991",
month = "1",
day = "1",
doi = "10.1016/0169-7552(91)90006-X",
language = "English",
volume = "22",
pages = "143--154",
journal = "Computer Networks",
issn = "1389-1286",
publisher = "Elsevier",
number = "2",

}

TY - JOUR

T1 - Traffic characteristics of a distributed memory system

AU - Smith, Jonathan M.

AU - Farber, David

PY - 1991/1/1

Y1 - 1991/1/1

N2 - We believe that many distributed computing systems of the future will use distributed shared memory as a technique for interprocess communication. Thus, traffic generated by memory requests will be a major component of the traffic for any networks which connect nodes in such a system. In this paper, we study memory reference strings gathered with a tracing program we devised. We study several models. First, we look at raw reference data, as would be seen if the network were a backplane. Second, we examine references in units of "blocks", first using a one-block cache model and then with an infinite cache. Finally, we study the effect of predictive prepaging of these "blocks" on the traffic. We provide a novel representation of memory reference data which can used to calculate interarrival distributions directly. Integrating communication with computation can be used to control both traffic and performance.

AB - We believe that many distributed computing systems of the future will use distributed shared memory as a technique for interprocess communication. Thus, traffic generated by memory requests will be a major component of the traffic for any networks which connect nodes in such a system. In this paper, we study memory reference strings gathered with a tracing program we devised. We study several models. First, we look at raw reference data, as would be seen if the network were a backplane. Second, we examine references in units of "blocks", first using a one-block cache model and then with an infinite cache. Finally, we study the effect of predictive prepaging of these "blocks" on the traffic. We provide a novel representation of memory reference data which can used to calculate interarrival distributions directly. Integrating communication with computation can be used to control both traffic and performance.

KW - computer networks

KW - distributed computation

KW - distributed memory

KW - networking

KW - traffic characteristics

UR - http://www.scopus.com/inward/record.url?scp=0026221302&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0026221302&partnerID=8YFLogxK

U2 - 10.1016/0169-7552(91)90006-X

DO - 10.1016/0169-7552(91)90006-X

M3 - Article

VL - 22

SP - 143

EP - 154

JO - Computer Networks

JF - Computer Networks

SN - 1389-1286

IS - 2

ER -