BCX jobs problems - temporary workaround

[HPC-News]

Dear All

Some users have noticed their jobs are exiting prematurely with errors like the following:

/bcx/userfranc/user00/.lsbatch/1206952887.828833: line 8: cannot create temp file for here document: No space left on device
/cineca/sysprod/lsf/7.0/linux2.6-glibc2.3-x86_64/bin/post_exec_cleanup: line 104: echo: write error: No space left on device
....

The reason for this is that due to some tests that are being done on the filesystems, the /tmp areas on some compute nodes are being filled up.

We are working to resolve this issue but in the meantime you can avoid getting this error by adding the following line to your batch scripts:

#BSUB -R "span[ptile=4] select[tmp>10] order[ch]"

our apologies for the inconvenience but this should be only a temporary problem

best wishes
CINECA support

Sent by: Andrew Emerson