🚀 go-pugleaf

RetroBBS NetNews Server

Inspired by RockSolid Light RIP Retro Guy

Article View: capdist.seminars
Article #474

SUNYA C. S. Dept. Colloquium

#474
From: Pat Keller
Date: Tue, 16 Aug 1994 13:49
42 lines
2786 bytes
                                     COLLOQUIUM

                University at Albany - State University of New York

                            Computer Science Department

                Distributed Diagnosis and Monitoring Algorithms for

                            Arbitrary Network Topologies

                                 Sampath Rangarajan

                 Department of Electrical and Computer Engineering
                              Northeastern University

                  Wednesday, August 17, 1994 at 3:00 PM, in LI-98

                                      ABSTRACT

                 In large distributed systems where hundreds of  proces-
            sors  are  connected  through a communication network, it is
            essential to provide mechanisms for detecting and diagnosing
            faulty  processors  at the system level and also disseminate
            this information to other processors on the network.  It  is
            also  useful to provide mechanisms for monitoring other pro-
            cessor status information (e.g. processor load) and  dissem-
            inate this information on the network. In this talk, we will
            present distributed algorithms that provide such mechanisms.
            In  these  algorithms,  fault-free processors perform simple
            periodic tests on one another; when a fault is detected or a
            newly  repaired processor joins the network, this new infor-
            mation is disseminated in parallel throughout  the  network.
            The  goal  is  to decrease the information latency, which is
            the time required for all of the  fault-free  processors  in
            the  network to learn of a new fault-event. We identify some
            distributed system services that can  be  built  on  top  of
            these monitoring mechanisms.

                 Further, we discuss how these algorithms can be used as
            the  basis for designing efficient protocols for maintaining
            location directories in mobile networks.
Technical Details
Message-ID: <199408161349.JAA01011@von.cs.albany.edu>
Path: arc1-ca.pugleaf.net!bga.com!news.sprintlink.net!uunet!psinntp!rebecca!sarah\!newsgate

Show Full Headers
Complete Article Headers
X-Google-Language: ENGLISH,ASCII-7-bit
X-Google-Thread: 1463ce,8814b7eab5051232,start
X-Google-Attributes: gid1463ce,public
X-Google-Thread: f61a9,8814b7eab5051232,start
X-Google-Attributes: gidf61a9,public
X-Google-ArrivalTime: 1994-08-19 07:26:17 PST
Path: arc1-ca.pugleaf.net!bga.com!news.sprintlink.net!uunet!psinntp!rebecca!sarah\!newsgate
From: Pat Keller <pat>
Newsgroups: capdist.seminars,sunya.cs.general
Subject: SUNYA C. S. Dept. Colloquium
Date: Tue, 16 Aug 1994 09:49:51 -0400
Organization: The University at Albany
Lines: 43
Message-ID: <199408161349.JAA01011@von.cs.albany.edu>
NNTP-Posting-Host: cs.albany.edu
To: bboard
Originator: daemon@cs.albany.edu