All user home directories are kept in DFS, and each user has a default storage limit of 500 MB. In addition to the ``yesterday'' backup described below, home directories in DFS are copied to tape backup four times a week. Each home directory has a default set of subdirectories:
| public | This directory is world readable. Use it to make files available to other users of the SP. |
| private | This directory is only accessible by the user. |
| yesterday | This directory contains a read-only copy of all the rest of the home directory, including other subdirectories, as of the day before. The copy is generated at 4 AM each morning. If you accidentally delete any of your DFS files, you can simply copy versions from the day before out of ``yesterday''. |
| bin | This directory is a default location for user-generated executables. It is not in your ``PATH'' by default, however. You can add it or one if its subdirectories to your ``PATH'' in your ``.profile'' or ``.cshrc'' file. |
| www | In the future, we plan to make all documents kept in this directory available over the World-Wide Web. |
For more information on DCE and DFS, see the online documentation from IBM, available at the following URL.
http://www-4.ibm.com/software/network/dce/library/publications/dceaix.html
The General Parallel File System (GPFS) is a large temporary-storage area with shared access from all SP nodes. For large files, GPFS is the highest-performance file system available on the SP. The GPFS servers are nodes of the SP, and data transfer goes exclusively over the SP Switch.
GPFS is intended as work space for SP applications. GPFS is not backed up, so you need to copy any important output from GPFS to one of the other file systems for permanent storage. To emphasize the fact that GPFS is not permanent, GPFS storage is mounted under directories of the form ``/tmp/gpfs*''. The storage is divided into various pieces, and the name of each directory indicates the size of its piece. For example, ``/tmp/gpfs200a'' is about 200 GB. The character after the size differentiates multiple partitions of the same size.
The directory ``/tmp/gpfs200a'' has a subdirectory for each user. We recommend that you use this subdirectory unless you have extreme storage requirements. The larger directories are intended for applications with such requirements.
GPFS does not yet support memory-mapped files. This limitation affects the compilation of Fortran files. For details, see our online documentation for XL Fortran, available at the following URL.
http://www.csm.ornl.gov/ccs/xlf.html#gpfs
For more information about GPFS, see the online documentation from IBM, available at the following URL.
http://www.rs6000.ibm.com/resource/aix_resource/sp_books/gpfs/
The High-Performance Storage System (HPSS) provides archival storage. It is ``high performance'' relative to other archival systems, not relative to native file systems like GPFS. Large permanent files should be moved directly from GPFS, presumably where they were created, to HPSS.
You access HPSS through the ``hsi'' interface, which is available on all SP nodes. Because it uses DCE authentication, ``hsi'' requires no password and can thus be used within batch scripts.
For more information on HPSS and ``hsi'', type ``hsi help'' on one of the login nodes or see the online documentation kept at SDSC, available at the following URL.
http://www.sdsc.edu/Storage/hsi/
Though the ``/tmp/gpfs*'' directories are shared across the SP, ``/tmp'' and all its other subdirectories are local to each node. The local storage on each node is very limited, and each uses a single pair of mirrored disks. GPFS, however, is served from striped arrays of disks. Therefore, for large files, GPFS is faster than local ``/tmp''. For these reasons, we recommend the use of ``/tmp/gpfs*'' instead of ``/tmp''.