All work
Project · Research computing

A future-proof network for sciCORE

Many networks have grown over the years without an overall plan behind them. A structured design makes such a network future-proof. It carries the performance of the coming years and keeps the complexity manageable.

Customer
sciCORE, University of Basel
Sector
Scientific computing
Engagement
Future-proof network design
Validated in
A network lab, before rollout

The challenge

sciCORE is the University of Basel's centre for scientific computing. Workloads like that put sustained, heavy demand on the network. A network that has grown over time is then often only extended in individual places.

Performance bought with complexity becomes a liability. Every exception, every one-off link and every undocumented path is something that has to be understood again the next time the network is touched. The goal was a design that delivers the performance, and stays manageable while doing it.

The approach

We created a new design and tested it before it went into production.

  1. Design for the structure, not the symptoms

    Rather than extend the grown topology, we designed a clean, scalable structure: a spine-leaf fabric where capacity is added by adding leaves, and where the path between any two points is predictable.

  2. Validate it in the lab

    The design was built and tested in a network lab first: a 100G spine-leaf fabric with MLAG, modelled end to end so its behaviour was known before a single production device was reconfigured.

The sciCORE network design modelled in a lab — a 100G spine-leaf fabric with MLAG
The design, modelled end to end in the lab: a 100G spine-leaf fabric with MLAG between the spines, tested before rollout

The result

sciCORE now has a network with a clear structure and headroom for future performance demands. The topology is clear enough to operate and extend safely.

Has your network grown past its design?
Talk to us