On nodes imaged after the initial cluster setup this value is present in several places in /etc/gmond.conf
mcast_join = 239.2.11.71 On the "original" ones (and the head node) it has this mcast_join = 239.2.11.70 So the newly nodes are broadcasting on a different multicast channel than the old ones and don't show up on the ganglia page. Not sure if this is intended behavior or not, but it does mean the new nodes don't show up on the ganglia page. This seems like a bug to me, since it seems like if you reimage the cluster there is no pressing reason why it should suddenly use a different multicast channel. I am not super familiar with multicast, so I am not sure if this is a problem with ganglia itself, multicast, or the OSCAR package. Also, the ganglia page loads painfully slowly off campus, no idea why. Less important, but also odd. ------------------------------------------------------------------------- This SF.net email is sponsored by: Splunk Inc. Still grepping through log files to find problems? Stop. Now Search log events and configuration files using AJAX and a browser. Download your FREE copy of Splunk now >> http://get.splunk.com/ _______________________________________________ Oscar-devel mailing list [email protected] https://lists.sourceforge.net/lists/listinfo/oscar-devel
