FAQ

A place to run real particle-physics analysis in your browser, on CERN infrastructure, next to the data and software you need to do it. It is built as part of the EOSC Federation, the European effort to connect national and institutional research infrastructure into one federated system.

Researchers can sign in through federated login, so you do not need a CERN staff or computing account to get started. Exactly which identity providers are accepted is still being finalised ahead of general availability; the Get Started page has the current login path.

Head to Get Started, which lays out three paths depending on what you want to do: run a ready-made analysis with one click, bring your own notebook and work against Open Data, or package a pipeline as a reproducible REANA workflow. All three sign you in through the same federated login.

Yes, using the Node costs nothing. The honest catch: it is shared public infrastructure with finite capacity, not an unlimited commercial cloud, so it runs under fair-use limits and is aimed at research and teaching rather than production hosting.

A working session is comparable to 2 CPU and 8 GB of RAM, the setup the performance numbers on this page were measured on. The exact quota offered at general availability, and whether it differs between the CERN VRE and REANA, is still being finalised.

Not yet finalised. For comparison, Google Colab's free tier disconnects after about 90 minutes of inactivity and 12 hours total, and MyBinder culls a session after just 10 minutes idle; the Node's own idle and maximum-session limits will be published here once they are set.

Capacity is shared and is being scaled up through the phased rollout toward the Node's production milestone in October. There is no published concurrency figure yet; the aim is a fair share per user, not unlimited simultaneous load.

Not for now: the Node offers CPU and memory, no GPU. That may be revisited later depending on demand, but every timing on this page, including the ones below, was measured on CPU alone.

One 10,000-event Open Data file runs through Rivet in about 4 minutes on a single core, roughly 39 events per second. A typical 100,000-event study is about 20 minutes on two cores, around 0.7 CPU-hours in total. Scaling is roughly linear, so you can estimate your own job by counting events: ten times the events takes roughly ten times as long.

Different tool for a different job. Colab gives you more memory (about 13 GB) and MyBinder gives you less (1 to 2 GB), but on both you start from an empty machine: you install the physics software yourself and download every data file across the network, every time you connect. MyBinder's disk and idle limits mean it cannot even hold a single 2.1 GB Open Data file for the length of one event loop.

On the Node the data is already mounted (EOS) and the software is already there (CVMFS), so the same analysis starts immediately and reads data locally instead of over the network.

CERN Open Data: real and simulated collision data released for public use, including the ATLAS and CMS datasets in the Analysis Catalogue and the 13.6 TeV event-generation release used in the timing numbers above. Browse it directly, or launch straight into a ready-made analysis.

This is the main practical difference from a commercial free tier. Open Data volumes are mounted directly on the Node (EOS), so a 2.1 GB file is read in place with no download and no egress fees. On a commercial cloud you pay for that transfer in time, and sometimes in money, on every single run.

Yes: bring your own notebook to the CERN VRE and work against Open Data with your own code. For larger private datasets, Rucio is the tool for managing them across sites; upload limits and the exact policy for external users' private data are still being worked out.

Interactive work in the CERN VRE is backed by CERNBox, so your notebooks and files persist between sessions. Scratch space used by REANA workflow runs is temporary and not meant for long-term storage; exactly how long scratch is kept is still being finalised.

The CERN and LHC analysis stack, delivered through CVMFS: ROOT, Rivet, atlasopenmagic, and the usual Python scientific stack. On Colab or MyBinder none of this is preinstalled, and CVMFS is not available there at all, so you install and build the stack yourself, every time.

Yes, pip install works normally inside your session. It installs into your own user environment, not the shared service, so it does not affect other users or the base stack everyone else relies on.

Yes, and this is a real advantage over an ad-hoc notebook on a commercial free tier: package your pipeline as a containerised REANA workflow, and anyone can re-run it and get the same result, with the environment captured alongside the code.

Interactive sessions run in a network segment kept isolated from the rest of CERN's infrastructure, so an incident in one session cannot spread to other services or users. Access itself requires authentication through your federated login; there is no anonymous access to compute.

Good for: interactive analysis of Open Data, prototyping, teaching, and reproducible workflows built on the tools above. Not for: unlimited compute, long-running production services, or as a general-purpose replacement for a commercial cloud account; this is a production-minimum research node, not a hyperscaler.

Yes: training and workshop use is a supported use case, planned for at the scale of a few hundred participants. Contact the Node ahead of your session so the team can prepare, rather than finding out on the day.

The Contact page is the way to reach the team directly, and Get Started has guided paths if you are not sure where to begin. Dedicated support channels are still being set up ahead of general availability.

Capacity and features are being expanded in phases toward the Node's production milestone in October. Specifics will be published here as they are confirmed, rather than promised in advance.