Due to various problems, the reservation last night was cancelled. We are
rescheduling for this evening, 7pm to 11pm. Last night there were jobs
still running at the time the reservation was supposed to start. It would
be good if everyone could make sure their jobs were finished or killed by
7pm tonight (or let me know that it is ok to kill them).
Thanks,
Susan.
On Sat, 5 Feb 2005, Susan Coghlan wrote:
Start Date: 10pm, Sunday 2/6/2005
End Date: 2am, Monday 2/7/2005
Summary: 1024 nodes reserved (full rack)
Details:
The full rack, 1024 nodes, of the BGL machine will be used for scaling
runs tomorrow night (2/6/05) from 10pm to 2am. All 32 node partitions will
be freed around 10pm. Unless there is a strong need, I won't reallocate
the 32 node partitions until the morning. You should be able to use the
32node partitions after 2am, but mpirun will be allocating and freeing
them during each job. This means a slight delay of around 3mins at the
start of each job. Dinesh Kaushik will send email to
discuss@xxxxxxxxxxxxxxx when the scaling runs are finished and the rack is
again available to everyone.
Susan Coghlan
BGL Systems Team
- ----------------------------------------------------------------------
To add or remove yourself from this mailing list, use the 'notifyme'
command on any BGL machine. To remove: notifyme -n, to add: notifyme -y.