Storage Hardware

The storage at OSC consists of servers, data storage subsystems, and networks providing a number of storage services to OSC HPC systems. The current configuration consists of:

  • A NetApp WAFL service providing 900 TB of storage and 10 GB/s bandwidth for home directories
  • An IBM Elastic Storage service providing 3,400 TB of storage and 40 to 50 GB/s bandwidth for project storage
  • An IBM Elastic Storage service providing 1,000 TB of storage and 100 GB/s bandwidth for global scratch
  • local disk storage on each compute node
  • One IBM 3584 tape robot:
    • 16 LTO tape drives
    • 5,500 TB (raw capacity) of LTO tapes

 

Service: 

Overview of File Systems

This page provides an overview of file systems at OSC. Each file system is configured differently to serve a different purpose:

  Home Directory Project Local Disk Scratch (global) Tape
Path /users/project/userID /fs/project /tmp /fs/scratch N/A
Environment Variable $HOME or ~ N/A $TMPDIR $PFSDIR N/A
Space Purpose Permanent storage Long-term storage Temporary Temporary Archive
Backed Up? Daily Daily No No Yes
Flushed No No End of job when $TMPDIR    is used End of job when $PFSDIR is used No
Visibility Login and compute nodes Login and compute nodes Compute node Login and compute nodes N/A
Quota/Allocation 500  GB  of storage and 1,000,000 files Typically 1-5  TB  of storage and 1,000,000 files Varies. Depending on node No quota N/A
Total Size 900  TB 3,400  TB Varies. Depending on system 1,000  TB 5,500  TB
Bandwidth 10  GB/S 40 to 50  GB/S Varies. Depending on system 100  GB/S 3.5  GB/S
Type NetApp  WAFL  service GPFS Varies. Depending on system GPFS LTO  tape
Supercomputer: 
Service: