NERSC's global home and project file systems are available on Franklin. Additionally, Franklin has over 400 TB of locally attached high-performance /scratch disk space For information on the NERSC file systems, see the link at right.
Scratch File Systems
||Aggregate Peak Performance||# IO Servers||Interconnect||File System Software||Disk Array Vendor|
|$SCRATCH||209 TB||17 GB/sec
|$SCRATCH2||209 TB||17 GB/sec||24||Lustre||DDN|
SCRATCH and SCRATCH2
There are two Lustre file systems on the Franklin system mounted as /scratch and /scratch2. They both have the same configuration.
- 12 DDN S2A9550 disk controllers per file system
- Each disk controller is served by 2 I/O servers called OSSs (Object Storage Servers)
- Each OSS host 2 OSTs (Object Storage Target) which a user can think of as a software abstraction of a physical disk
In total each /scratch file system has 48 OSTs which is the lowest layer with which users need to interact. When a file is created in /scratch it is "striped" or split across two different OSTs, which is the default. Lustre file systems at other computing centers may set a different default based on their workload. Striping is a technique to increase I/O performance. Instead of writing to a single disk, striping to two disks allows the user to potentially double read and write bandwidth.