[P2PSIP] New draft defining a topology plug-in for RELOAD

[Jouni Mäenpää <[e-mail]>]

Hi folks,

We have just submitted a draft that proposes a new topology plug-in for
RELOAD. This draft is a merge of two earlier drafts, "A Self-tuning DHT
for RELOAD" (draft-maenpaa-p2psip-self-tuning-00) and "A Load Balancing
Mechanism for RELOAD" (draft-saumitra-p2psip-loadbalance-00).

The draft defines a new topology plug-in for RELOAD that is more
appropriate for real world large scale overlays. This topology plug-in
implements three important functionalities that allow RELOAD to operate
under real world constraints. First, it includes a load balancing
algorithm that specifies efficient allocation of load to different nodes
in the network. Second, the document describes robust techniques for
stabilization of fingers and successors and specifies self tuning
mechanisms that allow dynamic and automatic adjustment of parameters
needed for these advanced techniques in the topology plug-in. Finally,
it specifies a locality aware finger selection algorithm that reduces
average lookup latency.

A URL for this Internet-Draft is:

http://www.ietf.org/internet-drafts/draft-maenpaa-p2psip-topologyplugin-00.txt

Comments are welcome!

Best regards,
Jouni Mäenpää


-------8<-------

A new version of I-D, draft-maenpaa-p2psip-topologyplugin-00.txt has
been successfuly submitted by Jouni Maenpaa and posted to the IETF
repository.

Filename:	 draft-maenpaa-p2psip-topologyplugin
Revision:	 00
Title:		 A Topology Plug-in for REsource LOcation And Discovery
Creation_date:	 2009-07-06
WG ID:		 Independent Submission
Number_of_pages: 43

Abstract:
REsource LOcation And Discovery (RELOAD) is a peer-to-peer signaling
protocol that can be used to maintain an overlay network, and to
store data in and retrieve data from the overlay.  This document
defines a new topology plug-in for RELOAD that is more appropriate
for real world large scale overlays.  This topology plug-in
implements three important functionalities that allow RELOAD to
operate under real world constraints.  First, it includes a load
balancing algorithm that specifies efficient allocation of load to
different nodes in the network.  Second, the document describes
robust techniques for stabilization of fingers and successors and
specifies self tuning mechanisms that allow dynamic and automatic
adjustment of parameters needed for these advanced techniques in the
topology plug-in.  Finally, it specifies a locality aware finger
selection algorithm that reduces average lookup latency.


------->8-------