I/O on a cluster
Asked by
Sean Wu
I've recently been talking with administrator of our cluster and he says there is an issue with the way our cluster is set up and the way I'm running MadGraph. Specifically he says that it does lots of tiny read and writes during the run and this is a problem for where it is that I am running. He says that this can be avoided if I do my runs in a /tmp folder and then transfer the files to the location I store them. Currently, I am just running out of a folder generated by madgraph using the ./generate_events command. Is there a simple way to redirect this run into another directory?
Question information
- Language:
- English Edit question
- Status:
- Answered
- Assignee:
- No assignee Edit question
- Last query:
- Last reply:
Can you help with this problem?
Provide an answer of your own, or ask Sean Wu for more information if necessary.
To post a message you must log in.