NCI operates multiple high-speed, low-latency global parallel filesystems to support the most data-intensive research workloads

A long row of storage arrays with grey front faces stacked together.

We run the fastest filesystems in the Southern Hemisphere, linking high-performance computing (HPC) with high-performance data (HPD) via 100-gigabit network links.

Our fastest filesystem, /scratch, provides data storage for active IO taking place on Gadi.

Technical Specifications /scratch

  • 7,200 4-Terabyte hard disks in 120 NetApp disk arrays
  • 20 Petabytes total useable capacity
  • 980 Gigabytes per second maximum performance

NCI’s filesystems contain around 50 Petabytes of research data stored in five separate global Lustre filesystems, reaching a peak IO performance of around 350 GB/second. NCI also runs a special IO Intensive Platform, a dedicated filesystem using 576 2-Terabyte NVMe drives for a cumulative performance around 960 Gigabytes per second. On top of this, NCI also stores 50 Petabytes of archival project data in state of the art magnetic tape libraries.

In total NCI runs more than 15,000 hard drives from vendors including NetApp, DDN and HPE.

Overview of NCI storage filesystems
Filesystem Capacity (Petabytes) Purpose Availability Performance (maximum)
/scratch 20 PB Large and fast IO Gadi only 980 GB/s
/g/data1-4 47 PB Storage of large data files Global 350 GB/s
Massdata 50 PB Archiving data files External 8 TB/hour