Upd:SuperMUC: User operation suspended
LRZ aktuell
publish at lrz.de
Mi Mär 13 17:16:00 CET 2013
Changes to this message: User operation suspended again
Status update (March 13, 17:00) Unfortunately the data corruption
problem has recurred. We have again suspended user operation. Status
update (March 13, 16:15) IBM in collaboration with DDN and Mellanox has
isolated and repaired two technical issues. One of these issues was
located in the I/O subsystem and has caused data corruption which was
noticed by GPFS but could not be automatically repaired, leading to
unavailability of the file system. It is believed that the scope of
this data corruption was limited to a single file, which was identified
and removed from the GPFS file system. After successful internal test
runs the system has been returned to regular user operation.
-----------------------------------------------------------------------
Dear users of SuperMUC,
Due to a problem with the GPFS services access to the file systems WORK
and SCRATCH is presently disrupted. IBM is attending to the problem,
and we'll keep you up to date on the status via this document.
Apologies for any delays in job processing.
This information is also available on our web server
http://www.lrz-muenchen.de/services/compute/supermuc/aktuell/ali4543/
Reinhold Bader
Mehr Informationen über die Mailingliste aktuell