Summary: Using k­Exclusion to Implement Resilient, Scalable
Shared Objects \Lambda
(Extended Abstract)
James H. Anderson and Mark Moir
Department of Computer Science
The University of North Carolina at Chapel Hill
Chapel Hill, North Carolina 27599­3175, USA
Abstract
We present a methodology for the implementation of
resilient shared objects that allows the desired level of
resiliency to be selected based on performance concerns.
This methodology is based on the k­exclusion and re­
naming problems. To make this methodology practi­
cal, we present a number of fast k­exclusion algorithms
that employ ``local spin'' techniques to minimize the im­
pact of the processor­to­memory bottleneck. We also
present a new ``long­lived'' renaming algorithm. Our k­
exclusion algorithms are based on commonly­available
synchronization primitives, are fast in the absence of
contention, and have scalable performance when con­

Source: Anderson, James - Department of Computer Science, University of North Carolina at Chapel Hill
Moir, Mark - Sun Microsystems

Collections: Computer Technologies and Information Sciences