How to submit your program and dispatch it to the cluster
Step 1. Create a new file called myjob.lsf, and please use the following example as your job submission script
Note: This job script assumes you have only one program to run, and this program will only allocate one CPU from the cluster.
#!/bin/bash
# enable your environment, which will use .bashrc configuration in your home directory
#BSUB -L /bin/bash
# the name of your job showing on the queue system
#BSUB -J gethosts
# the queue that you will use, the example here use the queue called "normal"
# please use bqueus command to check the available queues
#BSUB -q normal
# the system output and error message output, %J will show as your jobID
#BSUB -o %J.out
#BSUB -e %J.err
#the computing core number that you will collect (Attention: each node has multiple computing cores)
#BSUB -n 1
# the following -x means the system will try to allocate the entire computing node for your job.
# It means that even if you only use one computing core, no other people can access this node once your job start running
# You only need to use this when your requires a large amount of memory
# However, it might take longer to get your job dispatched because there are always some
# other people's job in the node already, the system has to wait until the whole node is "empty".
# this example here does not use this feature by adding another "#" in front of #BSUB
##BSUB -x
#when job finish that you will get email notification
#BSUB -u YourID@partners.org
#BSUB -N
#enter your working directory
cd /shr/home/$USER/working_dir
# Finally, Start the program
./gethostname
You can download the example source code of gethostname.c
Step 2. Submit your job
[testy@n137 ~] bsub < myjob.lsf
Step 3. Check your results
After the job finishes, you will see two files created in your working directory, one is JOB_ID.out (JOB_ID is a real number associated with your job ID assigned by the system) and JOB_ID.err. You will also receive an email when the job finishes.
|