Sweet to hear you are running Ganglia on the G5 cluster. Strange about the TN figure, looks like a signed-unsigned int issue. I'll have a look at the code when I get back from my holiday vacation.
Definately send the patches when you get them in order. -Federico > Greetings from Virginia Tech. > > I'm working on getting Ganglia on our 1100 node G5 cluster, and have > had some pretty good success. > > I do have an issue, and I wonder if it's related to scaling, or the > Darwin platform. First, let me describe how I've set everything up so > far. > > All 1100 nodes are running gmond deaf. I have a couple of systems > running gmond muted for monitoring. One of them is running gmetad with > the webfrontend. Gmetad is polling every 600 seconds, in this example. > > For some reason, the webfrontend will occasionally list a few (though > I've seen 60) hosts down. gstat reports the hosts are up, and after > the gmetad polls again, the hosts down will change, or go away. > > So, I did some tracking of the data. First, I had gmetad print out tn, > tmax, and xmldata->host_alive at line 447 in gmetad/process_xml.c. > Everytime it reports a host as down, the value of tn=-1. > > So, I dumped the output of telnet localhost 8651, and checked some of > the hosts there, and for the same hosts received: > <HOST NAME="n0731.tcf-int.vt.edu" IP="10.1.4.63" REPORTED="1072728955" > TN="4294967295" TMAX="20" DMAX="0" LOCATION="unspecified" > GMOND_STARTED="1072723722"> > > This could be a coincidence, but I do > > Anyone have any idea why this is happening? It's messing up my pretty > graphs. Also, I have some patches for machines/darwin.c in the works. > I've been adding some metric data to it, and fixing some of the > existing ones. I'll post those as soon as I'm done adding them in. > > Thanks alot! > - Josh > > > > ------------------------------------------------------- > This SF.net email is sponsored by: IBM Linux Tutorials. > Become an expert in LINUX or just sharpen your skills. Sign up for IBM's > Free Linux Tutorials. Learn everything from the bash shell to sys admin. > Click now! http://ads.osdn.com/?ad_id=1278&alloc_id=3371&op=click > _______________________________________________ > Ganglia-developers mailing list > Ganglia-developers@lists.sourceforge.net > https://lists.sourceforge.net/lists/listinfo/ganglia-developers >
