loading...
 This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
28th Hawaii International Conference on System Sciences (HICSS'95)
Hawaii, USA
January 04-January 07
ISBN: 0-8186-6930-6
ASCII Text
x 
 
M. Aldred, I. Gertner, S. McKellar, "A distributed lock manager on fault tolerant MPP," Hawaii International Conference on System Sciences, pp. 134, 28th Hawaii International Conference on System Sciences (HICSS'95), 1995.
 
 
BibTex
x
 
@article{ 10.1109/HICSS.1995.375401,
author = {M. Aldred and I. Gertner and S. McKellar},
title = {A distributed lock manager on fault tolerant MPP},
journal ={Hawaii International Conference on System Sciences},
volume = {0},
year = {1995},
issn = {1060-3425},
pages = {134},
doi = {http://doi.ieeecomputersociety.org/10.1109/HICSS.1995.375401},
publisher = {IEEE Computer Society},
address = {Los Alamitos, CA, USA},
}
 
 
RefWorks Procite/RefMan/Endnote
x 
 
TY - CONF
JO - Hawaii International Conference on System Sciences
TI - A distributed lock manager on fault tolerant MPP
SN - 1060-3425
SP
EP
A1 - M. Aldred,
A1 - I. Gertner,
A1 - S. McKellar,
PY - 1995
KW - software fault tolerance; fault tolerant computing; reliability; parallel programming; shared memory systems; Unix; operating systems (computers); message passing; distributed lock manager; fault tolerant MPP; Oracle Parallel Server; MPP UNIX system; resource locks; distributed message passing; global memory; reflective memory; Encore Infinity 90 architecture; shared memory style DLM; DLM recovery; Oracle session; node repair; MPP Unix
VL - 0
JA - Hawaii International Conference on System Sciences
ER -
 
M. Aldred, Encore Comput. Corp., Marlborough, MA, USA
I. Gertner, Encore Comput. Corp., Marlborough, MA, USA
S. McKellar, Encore Comput. Corp., Marlborough, MA, USA
The Distributed Lock Manager (DLM) is the cornerstone of running the Oracle Parallel Server on a MPP Unix system. The DLM grants resource locks in NULL, READ, WRITE, and other levels. The DLM is typically implemented either with distributed message passing or in global memory, depending on the architecture. Reflective memory on the Encore Infinity 90 architecture permits a shared memory style DLM. Each node runs a separate copy of Unix so failure of one node is isolated and DLM recovery can cleanup state. A node can later rejoin the Oracle session after node repair.
Index Terms:
software fault tolerance; fault tolerant computing; reliability; parallel programming; shared memory systems; Unix; operating systems (computers); message passing; distributed lock manager; fault tolerant MPP; Oracle Parallel Server; MPP UNIX system; resource locks; distributed message passing; global memory; reflective memory; Encore Infinity 90 architecture; shared memory style DLM; DLM recovery; Oracle session; node repair; MPP Unix
Citation:
M. Aldred, I. Gertner, S. McKellar, "A distributed lock manager on fault tolerant MPP," hicss, pp.134, 28th Hawaii International Conference on System Sciences (HICSS'95), 1995
Usage of this product signifies your acceptance of the Terms of Use.