Skip to content
Switch branches/tags
Go to file
Cannot retrieve contributors at this time

Monitoring Infrastructure

© Atos Spain S.A. 2016

License: GPL v3

The Monitoring Infrastructure is a component of the European Project TANGO ( ).



Component architecture

Installation Guide

Usage Guide

Relation to other TANGO components


The responsibility of this component is twofold. On one side it must provide running applications with metrics of the status of different devices, such as CPU, GPUs, FPGAs, etc. This information should be both energy consumption and performance status. On the other side it should also provide historical statistics for device metrics for latter analysis of upper components of the TANGO architecture.

TANGO architecture

This component relies on Collectd, which will be used together with some custom plugins done specifically for TANGO, in order to get and store energy consumption and performance values from the applications running in the different environments.

Available collection of probes to measure energy in heterogeneous hardware for the TANGO project:

  1. NVIDIA collectd plugin

    • power
    • temperature
    • memory used
    • usage
    • processes running
  2. Xeon Phi collectd plugin

    • power
    • temperature
    • memory used
    • usage
  3. IPMI plugin from collectd

    • power

Component architecture


The monitoring Infrastructure is composed by the following components:

Collectd & plugins

Collectd is a daemon which collects system and application performance metrics periodically and provides mechanisms to store the values in a variety of ways. The TANGO Collectd plugins provide metrics from specific devices like the NVIDIA GPUs and the XEON PHI processors. The metrics gathered from this component are stored in the InfluxDB instance.


InfluxDB is used as a data store for the metrics gathered from Collectd. The REST API and the Graphana applications connect to this tool in order to present the processed information.


Graphana is a data visualization and monitoring tool with support for Graphite, InfluxDB and many more databases. This component is used as the GUI of the monitoring component.


The main purpose of the REST API application is to offer to other TANGO components the information they need from the metrics gathered from Collectd.

View REST API specification to see the available methods.


Component architecture

Installation Guide (ubuntu, 64-bit systems)

1. Requirements
  • ubuntu 64-bit system
  • Java 8
  • Leiningen 2.0.0 or above installed.
2. Install Collectd
sudo apt-get update
sudo apt-get install collectd collectd-utils
2.1. Install plugins

View Collectd - Readme file to see how to compile and install the plugins.

3. Install InfluxDB
sudo dpkg -i influxdb_0.13.0_amd64.deb
sudo service influxdb start
sudo service influxdb statu
4. Install Grafana
sudo apt-get install -y adduser libfontconfig
sudo dpkg -i grafana_3.0.4-1464167696_amd64.deb
5. Collectd & InfluxDB & Grafana setup

See Monitoring with Collectd, InfluxDB & Grafana for more information about how to setup the three components.

6. Install and configure the REST API component

View rest-api - Readme file to see how to install and configure the REST API component.

Usage Guide

Relation to other TANGO components

The other TANGO components connect to the monitoring Infrastructure through the REST API application:

  • Programming model

  • heterogeneous parallel device clusters

  • Energy modeller

  • Self-Adaptation Manager


The Monitoring Infrastructure project is licensed under a GNU General Public License, version 3.

The rest-api component depends on a set of libraries and plugins licensed under the Eclipse Public License v1 and the Eclipse Public License v2. These libraries are used and imported through leiningen or maven, and they don't belong to the distribution of this project. This means that the original source code of these libraries was not modified. These libraries are the following:

Library Version Project URL
ring-cors/ring-cors 0.1.10
compojure 1.5.1
org.clojure/tools.logging 0.3.1
org.clojure/data.json 0.2.6
lein-ring 0.12.0
lein-uberwar 0.2.0