DokuWiki

User Tools

Site Tools

Trace:
cluster:103

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
Next revision Both sides next revision
cluster:103 [2011/12/21 19:39]
hmeij [Submit] 		cluster:103 [2011/12/21 19:41]
hmeij [Submit 2]
Line 132: Line 132:
 ==== Submit 2 ==== ==== Submit 2 ====
  
-On the back end compute nodes, unless specified, the job runs inside your home directory.  That job competes with other activities inside /home.  Compute nodes have two other areas where the jobs could be submitted: /localscratch and /sanscratch.  The former is a local filesystem for each node and should be used if file locking essential. The later is a filesystem from greentails disarray of 5 TB served vi IPoIB (that is NFS traffic over fast interconnects switches, the performance should be much better than gigabit ethernet switches).  It is comprised of disks and spindles that are not impacted by happens on /home.  So we're going to use that.+On the back end compute nodes, unless specified, the job runs inside your home directory.  That job competes with other activities inside /home.  Compute nodes have two other areas where the jobs could be submitted: /localscratch and /sanscratch.  The former is a local filesystem for each node and should be used if file locking is essential. The later is a filesystem from greentails diskarray (5 TB) served vi IPoIB (that is NFS traffic over fast interconnects switches, the performance should be much better than gigabit ethernet switches).  It is comprised of disks and spindles that are not impacted by what happens on /home.  So we're going to use that.
  
   * new submission file with edits   * new submission file with edits
-  * -n implies reserve job slots (cpu cores) for job (not necesssary, SAS jobs will always be one)+  * -n implies reserve job slots (cpu cores) for job (not necesssary, SAS jobs will always use only one)
   * -R reserves memory, for example, reserve 200 MB of memory on target compute node   * -R reserves memory, for example, reserve 200 MB of memory on target compute node
-  * scheduler creates unique dirs in scratch by JOBPID for you, so we'll satge the job there+  * scheduler creates unique dirs in scratch by JOBPID for you, so we'll stage the job there 
 +  * but now we must copy relevant to scratch dir and results back to home dir
  
 <code> <code>
Line 163: Line 164:
  
   * you can monitor the progress of your jobs from greentail while it runs   * you can monitor the progress of your jobs from greentail while it runs
 +
 <code> <code>
 [hmeij@greentail sas]$ ll /sanscratch/492667/ [hmeij@greentail sas]$ ll /sanscratch/492667/
Line 172: Line 174:
 </code> </code>
  
 +==== Best Practices ====
  
  
 \\ \\
 **[[cluster:0|Back]]** **[[cluster:0|Back]]**
cluster/103.txt · Last modified: 2011/12/22 19:34 by hmeij

Page Tools

Except where otherwise noted, content on this wiki is licensed under the following license: CC Attribution-Share Alike 4.0 International
CC Attribution-Share Alike 4.0 International Donate Powered by PHP Valid HTML5 Valid CSS Driven by DokuWiki