By Topic

Copying garbage collection for distributed object stores

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$31 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

3 Author(s)
Mancini, L.V. ; Dipartimento di Inf., Pisa Univ., Italy ; Rotella, V. ; Venosa, S.

The authors describe a garbage collection scheme for managing a distributed object store in which accessible objects survive system failures. The scheme is based on copying garbage collection and has the following advantages: it is tolerant to node failures, a fail-stop behavior of the node is assumed; it is partial, a given execution of the distributed garbage collection does not need to involve all the nodes, that is, the garbage collector can collect garbage on a subset of the entire system nodes; it minimizes disk accesses; it can collect any kind of cycles both within a node and among different nodes; it uses the depth-first-search to increase locality; it is iterative and it does not assume any particular primitives of the operating system of a node. In addition this distributed garbage collector can be extended to be asynchronous, that is, every node can decide to begin the collection at any time independently of the others

Published in:

Reliable Distributed Systems, 1991. Proceedings., Tenth Symposium on

Date of Conference:

30 Sep-2 Oct 1991