<DIV id=RTEContent>sepending on how many are behind firewalls compared to those that are not.<BR><BR><B><I>Daniel Stutzbach <agthorr@cs.uoregon.edu></I></B> wrote: <BLOCKQUOTE class=replbq style="PADDING-LEFT: 5px; MARGIN-LEFT: 5px; BORDER-LEFT: #1010ff 2px solid">On Wed, Jan 04, 2006 at 03:03:07PM +0100, Wolfgang M?ller wrote:<BR>> How often does it happen in existing P2P netowrks that significant parts of <BR>> the network are really unreachable?<BR><BR>One could argue that unreachable peers are not actually part of the<BR>network, and therefore this happens 0% of the time. ;-)<BR><BR>I know what you mean, though: how often are a significant fraction of<BR>peers which are running the P2P software unreachable from the largest<BR>connected component?<BR><BR>I'm not aware of any measurement studies on this topic (perhaps partly<BR>because it's difficult to measure). Are you thinking of DHT<BR>applications or "unstructured" P2P systems such as Gnutella? In the<BR>later
case, significant fragmentation is very unlikely due to the high<BR>out-degree of most peers.<BR><BR>> How high is the percentage of requests that fail (in the sense that they <BR>> return a faulty result) in existing fielded DHT applications?<BR><BR>I do not think this question (as stated) is sufficiently<BR>well-defined. What would you consider a faulty result, and (for the<BR>purposes of designing a measurement study) how would you can you tell<BR>if a result is faulty?<BR><BR>Which fielded DHT applications are you thinking of?<BR><BR>-- <BR>Daniel Stutzbach Computer Science Ph.D Student<BR>http://www.barsoom.org/~agthorr University of Oregon<BR>_______________________________________________<BR>p2p-hackers mailing list<BR>p2p-hackers@zgp.org<BR>http://zgp.org/mailman/listinfo/p2p-hackers<BR>_______________________________________________<BR>Here is a web page listing P2P
Conferences:<BR>http://www.neurogrid.net/twiki/bin/view/Main/PeerToPeerConferences<BR></BLOCKQUOTE><BR></DIV><BR><BR>You don't get no juice unless you squeeze<br>Lemon Obrien, the Third.