The Worldwide LHC Computing Grid (WLCG), is a distributed computing infrastructure arranged in tiers – giving a community of over 12,000 physicists near real-time access to LHC data. Data pours out of the LHC detectors at a blistering rate. Even after filtering out 99% of it, in 2018 we gathered 88 petabytes of data. That's 88 million gigabytes, the equivalent to around 22 million high-definition (HD) movies.

The scale and complexity of data from the LHC is unprecedented. This data needs to be stored, easily retrieved and analysed by physicists all over the world. This requires massive storage facilities, global networking, immense computing power, and, of course, funding.

CERN does not have the computing or financial resources to crunch all of the data on site, so in 2002 it turned to grid computing to share the burden with computer centres around the world. The WLCG builds on the ideas of grid technology initially proposed in 1999 by Ian Foster and Carl Kesselman.

Using the Grid

With more than 12,000 LHC physicists across the four main experiments – ALICEATLASCMS and LHCb – actively accessing and analysing data in near real-time, the computing system designed to handle the data has to be very flexible.

WLCG provides seamless access to computing resources which include data storage capacity, processing power, sensors, visualization tools and more. Users make job requests from one of the many entry points into the system. A job will entail the processing of a requested set of data, using software provided by the experiments

The computing Grid establishes the identity of the user, checks their credentials, and searches for available sites that can provide the resources requested. Users do not have to worry about where the computing resources are coming from – they can tap into the Grid's computing power and access storage on demand.

LHC Run 2 (2014-2018)

The LHC completed its four-year long "Run 2" at the end of 2018, and was running at an energy frontier of 13 teraelectonvolts (TeV) - nearly double the energy of collisions in the LHC's first three-year run. These collisions, which occured up to a billion times a second, sent showers of particles through the detectors.

With every second of run-time, gigabytes of data came pouring into the Tier0 - CERN Data Centre - to be stored, sorted and shared with physicists worldwide. During Run 1 (2009 – 2013), CERN was storing 1 gigabyte-per-second (Gb/s), with the occasional peak of 6 gigabytes-per-second. For Run 2, CERN was storing around 8 Gb/s (see the EOS storage dashboard), while seeing global transfer rates of over 60 Gb/s.

This of course translates into masses amounts more of data sent out across the Worlwide LHC Computing Grid, to be made available to physicists across the globe. The computing requirements of ALICE, ATLAS, CMS and LHCb are evolving and increasing in conjunction with the experiments’ physics programmes and the improved precision of the detectors’ measurements. 

LHC Run 3 (2021-2023) and LHC Run 4 (HL-LHC 2026-2029)

The next LHC Run is scheduled for 2021-2023. This looks to be even more challenging than the previous runs; data archiving is expected to be double what it was for LHC Run 2, and Run 4 - in HL-LHC operation - is even expected to be fives times that. 

The requirements for data and computing will grow dramatically during this time, with rates of 500 PB/year expected for the HL-LHC. The needs for processing are expected to increase more than 10 times over and above what technology evolution will provide. As a consequence, partnerships such as those with CERN openlab and other programmes of R&D are essential to investigate how the computing models could evolve to address these needs. They will focus on applying more intelligence into filtering and selecting data as early as possible. Investigating the distributed infrastructure itself (the grid) and how one can best make use of available technologies and opportunistic resources (grid, cloud, HPC, volunteer, etc), improving software performance to optimise the overall system.