Copyright © 2002 by University of California, Berkeley
The latest version of this document can be found on the ganglia documentation page.
Ganglia grew out of UC Berkeley Computer Science clustering research: The Millennium Cluster Project in collaboration with the NPACI Rocks Cluster Group.
Ganglia provides a complete real-time monitoring and execution environment that is in use by hundreds of universities, private and government laboratories and commercial cluster implementors around the world. Whether you want to monitor hundreds of computers in real-time across a university campus or around the world, ganglia is for you.
| Component | Description | Author | Version |
|---|---|---|---|
| Ganglia Monitor Daemon (gmond) | This daemon must be running on all nodes you want to monitor. it multicasts its present for other gmonds, collects host metrics, multicasts the state of the host on the multicast channel and exports the data for itself and other nodes via XML | Matt Massie, Preston Smith (FreeBSD and AIX port), Steve Wagner (Solaris and Tru64 port), Federico Sacerdoti, Matt Rice (Windows port) | 2.5.0 |
| Ganglia Meta Daemon (gmetad) | The Ganglia Meta Daemon merges and data from multiple gmond sources over the wide area, stores the volatile numerical data in local round-robin databases, concatenates and presents a single XML image of all clusters which are being monitored. | Matt Massie | 2.5.0 |
| Ganglia Metad Web Interface | The Ganglia Meta Daemon Web Interface uses a PHP-enabled web server to present the data collected by gmetad to a web browser. For an example of the output, visit http://ganglia.sourceforge.net/demo/ | Federico Sacerdoti and Matt Massie | 2.5.0 |
| Python Class and Client | a Python class for sorting and classifying large clusters using the monitoring core | Mason Katz and Greg Bruno | 2.0 |
| Next | ||
| Introduction |