<html><head></head><body style="word-wrap: break-word; -webkit-nbsp-mode: space; -webkit-line-break: after-white-space; "><br><div><div>On 25 Jan 2012, at 12:06, Bela Ban wrote:</div><br class="Apple-interchange-newline"><blockquote type="cite"><div><br><br>On 1/25/12 12:58 PM, Mircea Markus wrote:<br><blockquote type="cite"><br></blockquote><blockquote type="cite">On 25 Jan 2012, at 09:42, Bela Ban wrote:<br></blockquote><blockquote type="cite"><br></blockquote><blockquote type="cite"><blockquote type="cite"><br></blockquote></blockquote><blockquote type="cite"><blockquote type="cite"><br></blockquote></blockquote><blockquote type="cite"><blockquote type="cite">On 1/25/12 9:51 AM, Dan Berindei wrote:<br></blockquote></blockquote><blockquote type="cite"><blockquote type="cite"><br></blockquote></blockquote><blockquote type="cite"><blockquote type="cite"><blockquote type="cite">Slightly related, I wonder if Manik's comment is still true:<br></blockquote></blockquote></blockquote><blockquote type="cite"><blockquote type="cite"><blockquote type="cite"><br></blockquote></blockquote></blockquote><blockquote type="cite"><blockquote type="cite"><blockquote type="cite"> if at all possible, try not to use JGroups' ANYCAST for now.<br></blockquote></blockquote></blockquote><blockquote type="cite"><blockquote type="cite"><blockquote type="cite">Multiple (parallel) UNICASTs are much faster.)<br></blockquote></blockquote></blockquote><blockquote type="cite"><blockquote type="cite"><blockquote type="cite"><br></blockquote></blockquote></blockquote><blockquote type="cite"><blockquote type="cite"><blockquote type="cite">Intuitively it shouldn't be true, unicasts+FutureCollator do basically<br></blockquote></blockquote></blockquote><blockquote type="cite"><blockquote type="cite"><blockquote type="cite">the same thing as anycast+GroupRequest.<br></blockquote></blockquote></blockquote><blockquote type="cite"><blockquote type="cite"><br></blockquote></blockquote><blockquote type="cite"><blockquote type="cite"><br></blockquote></blockquote><blockquote type="cite"><blockquote type="cite">No, parallel unicasts will be faster, as an anycast to A,B,C sends the<br></blockquote></blockquote><blockquote type="cite"><blockquote type="cite">unicasts sequentially<br></blockquote></blockquote><blockquote type="cite">Thanks, very good to know that.<br></blockquote><blockquote type="cite"><br></blockquote><blockquote type="cite">I'm a a bit confused by the jgroups terminology though :-)<br></blockquote><blockquote type="cite">My understanding of the term ANYCAST is that the message is sent to *one* of the A,B,C. But from what I read here it is sent to A, B and C - that's what I know as MULTICAST.<br></blockquote><br><br>No, here's the definition:<br>* anycast: message sent to a subset S of members N. The message is sent <br>to all members in S as sequential unicasts. S <= N<br>* multicast: cluster-wide message, sent to all members N of a cluster. <br>This can be done via UDP (IP multicast) or TCP<br>* IP multicast: the network level datagram packet with a class D address <br>as destination<br>* broadcast: IP packet sent to all hosts on a given range same host, <br>subnet or higher)<br></div></blockquote>Thanks for the clarification Bela. I've been using wikipedia[1] as a reference and the terms have a slightly different meaning there.</div><div><br></div><div>[1] <a href="http://en.wikipedia.org/wiki/Anycast#Addressing_methodologies">http://en.wikipedia.org/wiki/Anycast#Addressing_methodologies</a></div></body></html>