Thank you kindly Ian. I want to summarize the final solution just in case someone else has the same confusion that I had.
The front-end node has gmeta running with the following configuration: % more /etc/gmetad.conf data_source "Servers" 60 localhost:8650 data_source "Athlons" 60 hsd404:8655 hsd420:8655 data_source "Opterons" 60 hsd550:8656 hsd602:8656 gridname "Galaxy" Each node has the monitor running. The only changes from the default settings in /etc/gmond.conf were: 1. setting the appropriate cluster name (Servers, Athlons or Opterons in my case) 2. udp_send mcast_join port changed to match designations above (i.e. 8650 or 8655 or 8656 depending on node type) 3. tcp_accept_channel port changed to match designations above 4. the udp_recv_channel block was removed from nodes that just report data (not a requirement to work). udp_recv_channel port was changed to match designations above for nodes that run gmetad (hsd404,420,550,602). The nodes hsd404 & hsd420 run gmetad and report data to the ganglia front end via port 8655. The nodes hsd550 and hsd602 run gmetad and report data to the front end via port 8656. > > From: Ian Cunningham <[EMAIL PROTECTED]> > Date: 2006/02/10 Fri AM 11:04:58 PST > To: "Stoia, Mike" <[EMAIL PROTECTED]> > CC: [EMAIL PROTECTED], [email protected] > Subject: Re: [Ganglia-general] config file confusion > > Mike, > > I apologize, I left out that you need to change the receive port. You > should not need to change the IP address. > > FYI, after you change the configs, don't forget to kill and start all > the gmonds. > > Ian > > Stoia, Mike wrote: > > >Thanks for the help. This is definitely the right track, but something > >is still amiss. Let me provide a few more specifics and really let my > >ignorance shine. I get no data on the Ganglia page with the > >configuration below. I suspect that the default IP for > >mcast_join/receive might need changing. > > > >Ganglia front-end: > >Hostname = luna2 (IP# is not 239.2.11.71) > > > >Ganglia client nodes (sampling): > >Athlon hostnames = hsd357, hsd358, ..., hsd428 > >Opteron hostnames = hsd502, hsd 503, ..., hsd660 > > > >Here is my gmetad.conf (on luna2): > >data_source "Servers" 60 localhost:8650 > >data_source "Athlons" 60 hsd404:8655 hsd420:8655 > >Gridname "Galaxy" > > > >Here is my gmetad.conf (on hsd404 & hsd420) > >data_source "Athlons" 60 localhost:8655 > > > >Here is my gmond.conf for each data source: > >SERVERS > >cluster { > > name = "Servers" > >} > >udp_send_channel { > > mcast_join = 239.2.11.71 > > port = 8650 > >} > > > > > udp_recv_channel { > mcast_join = 239.2.11.71 > bind = 239.2.11.71 > port = 8650 > } > > >ATHLONS > >cluster { > > name = "Athlons" > >} > >udp_send_channel { > > mcast_join = 239.2.11.71 > > port = 8655 > >} > > > > > udp_recv_channel { > mcast_join = 239.2.11.71 > bind = 239.2.11.71 > port = 8655 > } > > > > >-----Original Message----- > >From: [EMAIL PROTECTED] > >[mailto:[EMAIL PROTECTED] On Behalf Of Ian > >Cunningham > >Sent: Thursday, February 09, 2006 10:13 AM > >To: [EMAIL PROTECTED] > >Cc: [email protected] > >Subject: Re: [Ganglia-general] config file confusion > > > >To expand on what Jason wrote, the name doesn't actually decide which > >cluster the node's data gets included in. If you are using multicast as > >it appears you are (my guess), You will need to take an additional step > >of segregating each cluster by using different ports. With your example: > > > >gmetad.conf > >data_source "Servers" 60 localhost:8649 > >data_source "Opterons" 60 hsd380:8655 hsd400:8655 > >data_source "Athlons" 60 hsd250:8656 hsd258:8656 > > > >Opterons gmond.conf > >udp_send_channel { > >mcast_join = 239.2.11.71 > >port = 8655 > >} > > > >etcetera > > > >Ian > > > >[EMAIL PROTECTED] wrote: > > > > > > > >>Ganglia developers, > >> > >>I am trying to implement Ganglia on a 500+ node cluster. My goal is to > >> > >> > >use the grid functionality to have the data split up into several > >groupings (by architecture -- it is a non-homogeneous cluster). The > >issue I am having is that every one of my nodes is showing up for all > >"data_source" definitions. In other words, the metrics from all ~500 > >nodes shows up under each data_source heading even though I have defined > >distinct "cluster names" in the /etc/gmond.conf files. > > > > > >>My config files are provided below for reference. > >> > >>Thanks for any advice you can provide, > >>Mike > >> > >>GANGLIA FRONT-END CONFIGS (web front-end / gmetad / gmond) > >>/etc/gmetad.conf # data_source "my cluster" 10 localhost > >>my.machine.edu:8649 1.2.3.5:8655 # data_source "my grid" 50 > >>1.3.4.7:8655 grid.org:8651 grid-backup.org:8651 # data_source "another > >>source" 1.3.4.7:8655 1.3.4.8 data_source "Servers" 60 localhost > >>data_source "Opterons" 60 hsd380 hsd400 data_source "Athlons" 60 hsd250 > >> > >> > > > > > > > >>hsd258 # > >> > >>/etc/gmond.conf > >>} > >> > >>/* If a cluster attribute is specified, then all gmond hosts are > >>wrapped inside > >>* of a <CLUSTER> tag. If you do not specify a cluster tag, then all > >><HOSTS> will > >>* NOT be wrapped inside of a <CLUSTER> tag. */ cluster { > >> name = "Servers" > >>} > >> > >> > >>GANGLIA NODE CONFIGS > >>/etc/gmond.conf (on Opteron nodes) > >>} > >> > >>/* If a cluster attribute is specified, then all gmond hosts are > >>wrapped inside > >>* of a <CLUSTER> tag. If you do not specify a cluster tag, then all > >><HOSTS> will > >>* NOT be wrapped inside of a <CLUSTER> tag. */ cluster { > >> name = "Opterons" > >>} > >> > >> > >>/etc/gmond.conf (on Athlon nodes) > >>} > >> > >>/* If a cluster attribute is specified, then all gmond hosts are > >>wrapped inside > >>* of a <CLUSTER> tag. If you do not specify a cluster tag, then all > >><HOSTS> will > >>* NOT be wrapped inside of a <CLUSTER> tag. */ cluster { > >> name = "Athlons" > >>} > >> > >> > >> > >>------------------------------------------------------- > >>This SF.net email is sponsored by: Splunk Inc. Do you grep through log > >>files for problems? Stop! Download the new AJAX search engine that > >>makes searching your log files as easy as surfing the web. DOWNLOAD > >> > >> > >SPLUNK! > > > > > >>http://sel.as-us.falkag.net/sel?cmd=lnk&kid=103432&bid=230486&dat=12164 > >>2 _______________________________________________ > >>Ganglia-general mailing list > >>[email protected] > >>https://lists.sourceforge.net/lists/listinfo/ganglia-general > >> > >> > >> > >> > >> > > > > > > > >------------------------------------------------------- > >This SF.net email is sponsored by: Splunk Inc. Do you grep through log > >files for problems? Stop! Download the new AJAX search engine that > >makes searching your log files as easy as surfing the web. DOWNLOAD > >SPLUNK! > >http://sel.as-us.falkag.net/sel?cmd=k&kid3432&bid#0486&dat1642 > >_______________________________________________ > >Ganglia-general mailing list > >[email protected] > >https://lists.sourceforge.net/lists/listinfo/ganglia-general > > > > > > > > > >
