Server Fault Stack Exchange
Server Fault Stack Exchange

Questions tagged [ganglia]

Ganglia is a scalable distributed monitoring system for high-performance computing systems such as clusters and grids.

Ganglia is a scalable distributed monitoring system for high-performance computing systems such as clusters and grids.

Ganglia is based on a hierarchical design targeted at federations of clusters. It leverages widely used technologies such as XML for data representation, XDR for compact, portable data transport, and RRDtool for data storage and visualization. It uses carefully engineered data structures and algorithms to achieve very low per-node overheads and high concurrency. The implementation is robust, has been ported to an extensive set of operating systems and processor architectures, and is currently in use on thousands of clusters around the world. It has been used to link clusters across university campuses and around the world and can scale to handle clusters with 2000 nodes.

The ganglia system comprises two unique daemons, a PHP-based web front-end, and a few other small utility programs.

47 questions
0
votes
3 answers

Collectl Disk IO and Ganglia

I'm trying to push disk io statistics from collectl V3.3.5-4 (with the multicast and socket Perl modules installed) through to a Ganglia version 3.0.7 instance. Configured and followed the instructions…
Jon
  • 365
  • 1
  • 4
  • 10
0
votes
1 answer

Ganglia Running but Not Showing CPUs or Hosts

So I just set up ganglia on a single debian node. It followed a pretty simple process of 1 - installed from stable repo using apt-get install ganglia-monitor gmetad apt-get install ganglia-webfrontend 2 - configured using using:…
clifgray
  • 155
  • 1
  • 2
  • 10
0
votes
1 answer

How to know which script or executable is linked with a metric in ganglia?

I have just started to explore ganglia and my question is "How to know which script or executable is linked with a metric in ganglia?" The fact is that I don't know much about ganglia. I have good experience in zabbix and I want to link a graph in…
Rohit
  • 101
  • 4
0
votes
1 answer

Setting up multiple grids in Ganglia

Has anyone set up multiple grids to show on a single UI with Ganglia? I know how to set up multiple clusters but would love to show Grids on one interface. Here's an example. http://ganglia.g.gsic.titech.ac.jp/ganglia/
sdot257
  • 3,039
  • 5
  • 29
  • 38
0
votes
1 answer

Ganglia multicast with clustering

Let's say I have two hosts. One acts as the server where gmetad and a local gmond resides. It also has the web interface. I then have a client that only has gmond configure as follows. Anyways, everything works fine if i remove the mcast_join line…
sdot257
  • 3,039
  • 5
  • 29
  • 38
0
votes
1 answer

Access Internal Website from Public Internet

I have the current setup: laptop -> gatekeeper -> master_server -> my_machine There are 3 SSH's that I need to do to get to my_machine and I found a solution to do it in one step by editing SSH's config file and using ProxyCommand. I want to access…
mchangun
  • 103
  • 2
0
votes
1 answer

What is the use of gmond collection group in unicast Ganglia setup?

There is a Ganglia aggregator running: gmond gmetad And three Ganglia agents working in unicast mode, to publish data to the aggregator. From one of the Ganglia agents, I manually push new metrics using gmetric CLI utility, and I see it plotted on…
Howard
  • 273
  • 2
  • 4
  • 10
0
votes
1 answer

What tool to retain and compare detailed previous ganglia data?

The loss of resolution in Ganglia makes it difficult for my product team to compare periods of load and test performance changes. We have bursty periods, separated by days or weeks. What tools are available for saving detailed (e.g. hour-level) data…
burkemw3
  • 133
  • 1
  • 4
0
votes
1 answer

gmetric data submitted doesn't follow dmax value

I have a custom script that is querying a metric port for an application that I'm running and submitting parsed values to ganglia via gmetric. The script runs every minute, so I submit the data to ganglia using the following gmetric…
580farm
  • 241
  • 2
  • 4
  • 12
0
votes
1 answer

Ganglia web generating "error collecting ganglia data (:): fsockopen error"

Now, I'm trying to install a new ganglia-web interface to replace an older one. Google searching on the error got me a lot, but none of it helps. One large distinction I note is that Google usually returns "There was an error collecting ganglia data…
dafydd
  • 395
  • 2
  • 3
  • 10
0
votes
1 answer

How to bring up an hourly graph for a specified period (rather than only "Last Hour") in Ganglia

Sorry if this is a silly question but I can't find a way to make Ganglia display an hourly graph of a specified time. How do I do this? The version of my Ganglia Web Frontend is 3.1.7
Enno Shioji
  • 117
  • 4
0
votes
2 answers

Graphite Integration breaks ganglia/gmetad?

I'm trying to forward metrics from gmetad to graphite/carbon. After configuring carbon_server and ganglia_prefix in gmetad.conf gmetad starts losing metrics. gmetad Version is 3.3.5, carbon/whisper/graphite-web is 0.9.8. There is no I/O bottleneck…
Falk Stern
  • 141
  • 5
0
votes
2 answers

ganglia graphs like munin for cpu, etc?

I'm coming from munin and a CPU graph contains data for system, user, nice, etc ALL on one graph. I just installed ganglia and setup the basic monitoring. It appears that each type of cpu data is a separate graph! WTF is this and can I change the…
CarpeNoctem
  • 2,397
  • 4
  • 23
  • 32
0
votes
1 answer

having trouble setting up ganglia on three machines

I am running ubuntu 11.10 I have one machine with gmetad, gmond and ganglia-webinterface. When I browse the web interface this machine picks up the local gmond output. I then added another machine, running only gmond. I didn't really change anything…
Pieter Breed
  • 101
  • 4
0
votes
2 answers

Setting up Ganglia for multiple clusters

Say I have a bunch of clients with ONE master host that houses the gmetad and web interface. If I define one cluster (i.e. 'Cluster'), it works, but let's say I want a second set of cluster, how does that work? I can't point all my client nodes to…
sdot257
  • 3,039
  • 5
  • 29
  • 38
1 2
3
4