There are some papers about how to do this sort of thing on <a href="http://www.dsn.jhu.edu/publications.html">http://www.dsn.jhu.edu/publications.html</a>.<br>Maybe <a href="http://www.cnds.jhu.edu/pub/papers/AT02_icdcs.pdf">
http://www.cnds.jhu.edu/pub/papers/AT02_icdcs.pdf</a> would be a good one to start with, but it may be that Yair has a different suggestion.<br><br>Cheers,<br>Ryan<br><br><div><span class="gmail_quote">On 4/18/07, <b class="gmail_sendername">
Nick Johnson</b> <<a href="mailto:arachnid@notdot.net">arachnid@notdot.net</a>> wrote:</span><blockquote class="gmail_quote" style="border-left: 1px solid rgb(204, 204, 204); margin: 0pt 0pt 0pt 0.8ex; padding-left: 1ex;">
I have a simple event server that keeps a list of all events sent to a<br>particular event queue, and allows clients to ask for ranges. I'm<br>wanting to implement replication for load-balancing and reliability<br>using Spread. In order for clients to be able to know that they have
<br>every event, the order of events on each replicated server needs to be<br>identical. The basic replication using Spread is easy. What I'm unsure<br>about is how to handle splits/joins.<br><br>Has anyone had to deal with this issue? How do you ensure that if a
<br>split occurs, the individual servers won't become out of sync and each<br>accept events that cannot be merged when a join occurs, without<br>relying on a single authoritative server (which is hence vulnerable to<br>
failure)?<br><br>-Nick Johnson<br><br>_______________________________________________<br>Spread-users mailing list<br><a href="mailto:Spread-users@lists.spread.org">Spread-users@lists.spread.org</a><br><a href="http://lists.spread.org/mailman/listinfo/spread-users">
http://lists.spread.org/mailman/listinfo/spread-users</a><br></blockquote></div><br>