Skip to content
Snippets Groups Projects
Commit 06a74d02 authored by Moe Jette's avatar Moe Jette
Browse files

describe the need to explicitly transfer executable and data files

parent 4d9c8978
No related branches found
No related tags found
No related merge requests found
...@@ -305,22 +305,31 @@ The <span class="commandline">salloc</span> command is would be used ...@@ -305,22 +305,31 @@ The <span class="commandline">salloc</span> command is would be used
to create a resource allocation and typically start a shell within to create a resource allocation and typically start a shell within
that allocation. that allocation.
One or more job steps would typically be executed within that allocation One or more job steps would typically be executed within that allocation
using the srun command to launch the tasks. using the <span class="commandline">srun</span> command to launch the tasks
Finally the shell created by salloc would be terminated using the (depending upon the type of MPI being used, the launch mechanism may
<i>exit</i> command. differ, see <a href="#mpi">MPI</a> details below).
In this example we will also use the <span class="commandline">sbcast</span> Finally the shell created by <span class="commandline">salloc</span> would
command to transfer the executable program to local storage, /tmp/joe.a.out, be terminated using the <i>exit</i> command.
on the allocated nodes (1024 nodes in this example). SLURM does not automatically migrate executable or data files
to the nodes allocated to a job.
Either the files must exists on local disk or in some global file system
(e.g. NFS or Lustre).
We provide the tool <span class="commandline">sbcast</span> to transfer
files to local storage on allocated nodes using SLURM's hierarchical
communications.
In this example we use <span class="commandline">sbcast</span> to transfer
the executable program <i>a.out</i> to <i>/tmp/joe.a.out</i> on local storage
of the allocated nodes.
After executing the program, we delete it from local storage</p> After executing the program, we delete it from local storage</p>
<pre> <pre>
tux0: salloc -N1024 bash tux0: salloc -N1024 bash
$ sbcast a.out /tmp/joe.a.out $ sbcast a.out /tmp/joe.a.out
Granted job allocation 471 Granted job allocation 471
$ srun /tmp/joe.a.out $ srun /tmp/joe.a.out
Result is 471 Result is 3.14159
$ srun rm /tmp/joe.a.out $ srun rm /tmp/joe.a.out
$ exit $ exit
salloc: Relinquishing job allocation 1234 salloc: Relinquishing job allocation 471
</pre> </pre>
<p>In this example, we submit a batch job, get its status, and cancel it. </p> <p>In this example, we submit a batch job, get its status, and cancel it. </p>
...@@ -568,6 +577,6 @@ sbatch: Submitted batch job 1234 ...@@ -568,6 +577,6 @@ sbatch: Submitted batch job 1234
tasks. These tasks are not managed by SLURM since they are launched tasks. These tasks are not managed by SLURM since they are launched
outside of its control.</p> outside of its control.</p>
<p style="text-align:center;">Last modified 2 June 2008</p> <p style="text-align:center;">Last modified 16 July 2008</p>
<!--#include virtual="footer.txt"--> <!--#include virtual="footer.txt"-->
0% Loading or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment