This shows you the differences between two versions of the page.
Last revision Both sides next revision | |||
cluster:129 [2014/06/18 09:57] hmeij created |
cluster:129 [2014/06/18 10:03] hmeij |
||
---|---|---|---|
Line 7: | Line 7: | ||
When you have one or more jobs running that rely on Gaussian internal checkpoint mechanism, heavy read/write operations may result. | When you have one or more jobs running that rely on Gaussian internal checkpoint mechanism, heavy read/write operations may result. | ||
- | So we've been trying to figure out how to control, or throttle, the IO traffic. Usually the application itself will provide option for this, like rsync' | + | So we've been trying to figure out how to control, or throttle, the IO traffic. Usually the application itself will provide option for this, like rsync' |
So for those that rely on the generation of large Gaussian checkpoint file, please add the following lines to the very top of your submission script: | So for those that rely on the generation of large Gaussian checkpoint file, please add the following lines to the very top of your submission script: | ||
Line 18: | Line 18: | ||
</ | </ | ||
- | This instructs the compute node to schedule the IO traffic with "best effort" | + | This instructs the compute node to schedule the IO traffic with "best effort" |
- | Example using the /sanscratch area, you must stage your data in the temporary work directory and save results back to your home directory before the job finishes. The scheduler will automatically remove and delete that work directory. | + | Example using the /sanscratch area; you must stage your data in the temporary work directory and save results back to your home directory before the job finishes. The scheduler will automatically remove and delete that work directory. |
< | < |