|
|
Sloppy Management of Structured P2P Services
Authors: Paolo Costa,
Guillaume Pierre,
Alexander Reinefeld,
Thorsten Schütt,
and Maarten van Steen.
Source: Third Workshop
on Hot Topics in Autonomic Computing, Chicago, IL, USA, June 2008.
Abstract
|
The traditional way to manage distributed systems software is to list
all possible error conditions such as churn and partial node or
network failures, and come up with repair algorithms that take care of
maintaining the desired structure despite adversary conditions.
However, implementing repair algorithms is cumbersome, and any error
can potentially lead to complex liveness bugs. In this context, our
position is that explicit repair algorithms can and should be avoided
in the implementation of structured peer-to-peer services. Instead, we
should use continuous lazy background algorithms to handle
non-functional management tasks such as routing table maintenance,
while relying on the original structured algorithms for the functional
tasks such as routing messages through a DHT.
|
Download
Bibtex Entry
@Unpublished{costa2008a,
author = {Paolo Costa and Guillaume Pierre and
Alexander Reinefeld and Thorsten Sch\"utt
and Maarten van Steen},
title = {Sloppy Management of Structured P2P Services},
month = jun,
year = {2008},
note = {\url{http://www.globule.org/publi/SMSPS_hotac2008.html}},
annote = {The HotAC workshop does not publish proceedings}
}
|
gpierre@cs.vu.nl
|
|
|
