CERN Stores + Analyzes Mountains of Data to Answer Science’s Biggest Questions

The European Organization for Nuclear Research, known as CERN, operates the largest particle physics laboratory in the world, including the Large Hadron Collider (LHC). They use Puppet to process gigantic data sets and support the expansive infrastructure CERN relies on to learn more about the nature of matter, uncover the origin of being, and test the limits of human knowledge. 

Benefits of Using Puppet:

Automate building + retirement

of resources to enable ‘blue-sky research’ without boundaries. 

Increased the rate of managed services

per DevOps personnel as IT footprint expanded. 

Reduced support ticket volume

dramatically with minimal service disruption. 

Challenge: Big Questions, Bigger Data + Thousands of Users 

Among other experiments, CERN records 40 million instances of particle collision and decay every second in the LHC to better understand the nature of matter and the known universe. Their impressive IT infrastructure deals with tens of thousands of users and about a million gigabytes every day.

Additionally, an expanded data center footprint in 2013 meant more capacity but no more human resources to manage it. As CERN Operating System and Infrastructure Manager Tim Bell said, “We’ve got twice as many machines to manage and the same number of guys.”

CERN needed a way to store and analyze data, monitor daily operations, and identify problems in real time – without adding more personnel. 

Results: Automated Provisioning, Readable Configuration + Greater Focus 

“Our performance is much better. We have time … to dedicate to actual things that are important.”

David Moreno García, DevOps Engineer Officer, CERN

With Puppet, the CERN IT team now automates the provisioning, decommissioning, and management of tens of thousands nodes with hundreds of virtual servers. 

CERN uses a monitoring system for infrastructure that combines Puppet agents, Puppet servers, and PuppetDB in workflows collecting data in two source pipelines using data processing pipelines (Kafka, Logstash), analytics software (Elasticsearch), data storage (InfluxDB, HDFS), and frontend components (Grafana, Kibana, and Jupyter).

Automation enables CERN to continuously introduce service changes while minimizing service disruption. That gives them time to develop better software to serve the physics community while building more resources for researchers. 

Discover the Potential of Your Infrastructure with Puppet

If Puppet can support the infrastructure handling the mountains of data that hold the secrets of the natural world, it can handle your infrastructure needs. Whatever they are, we'll show you how Puppet can be used to tackle them in a personalized demo session with our team.