Changeset 1179 for trunk/src/cluster_command.m

Timestamp:

Mar 23, 2025, 11:13:38 AM (4 weeks ago)

Author:

sommeria

Message:

a few bug repairs and cleaning

File:

• trunk/src/cluster_command.m (modified) (2 diffs)

trunk/src/cluster_command.m

@@ -1 @@
-%'cluster_command': creates the command string for launching jobs in the cluster
-%------------------------------------------------------------------------
+%'cluster_command': creates the command string for launching jobs in the cluster system 'oar'
+% other cluster options 'pbs' and 'psmn' are available in cluster_command_pbs and
+% cluster_command_psmn. The choice is made in the xml file for parameters: series.xml
+%-- ----------------------------------------------------------------------
 % function cmd=cluster_command(ListProcess,ActionFullName,DirLog,NbProcess, NbCore,CPUTimeProcess)
 %
@@ -19 +21 @@
 filename_log=fullfile(DirLog,'job_list.stdout'); % file for output messages of the master oar process
 filename_errors=fullfile(DirLog,'job_list.stderr'); % file for error messages of the master oar process
-        if NbProcess>=6
-            bigiojob_string=['+{type = ' char(39) 'bigiojob' char(39) '}/licence=1'];% char(39) is quote - bigiojob limit UVmat parallel launch on cluster to avoid saturation of disk access to data
-        else
-            bigiojob_string='';
-        end 
+if NbProcess>=6
+    bigiojob_string=['+{type = ' char(39) 'bigiojob' char(39) '}/licence=1'];% char(39) is quote - bigiojob limit UVmat parallel launch on cluster to avoid saturation of disk access to data
+else
+    bigiojob_string='';
+end
 
 WallTimeMax=23;% absolute limit on computation time (in hours)
-WallTimeTotal=min(WallTimeMax,4*CPUTimeProcess/60);% chosen limit on computation time (in hours),possibly smaller than the absolute limit to favor job priority in the system.  
-WallTimeOneProcess=min(4*CPUTimeProcess+10,WallTimeTotal*60/2); % estimated max time of an individual process, used for checkpoint: 
-                                                                %if less than this time remains before walltime, the job is stopped and a new one can be launched ( by the option 'idempotent')
+WallTimeTotal=min(WallTimeMax,4*CPUTimeProcess/60);% chosen limit on computation time (in hours),possibly smaller than the absolute limit to favor job priority in the system.
+WallTimeOneProcess=min(4*CPUTimeProcess+10,WallTimeTotal*60/2); % estimated max time of an individual process, used for checkpoint:
+%if less than this time remains before walltime, the job is stopped and a new one can be launched ( by the option 'idempotent')
 
-      if NbCore==1
-          corestring='cpu=1/core=4'; %increases the allowed memory in case of single core job
-      else
-         % corestring=['/core=' num2str(NbCore)]; 
-         corestring=['{cluster=''calcul8''}/core=' num2str(NbCore)]; 
-      end
-                                                                cmd=['oarsub -n UVmat_' ActionFullName ' '...
-            '-t idempotent --checkpoint ' num2str(WallTimeOneProcess*60) ' '...
-            '-l "' corestring bigiojob_string... % char(39) is quote - bigiojob limit UVmat parallel launch on cluster
-            ',walltime=' datestr(WallTimeTotal/24,13) '" '...
-            '-E ' filename_errors ' '...
-            '-O ' filename_log ' '...
-            '"oar-parexec -s -f ' ListProcessFile ' '...
-            '-l ' ListProcessFile '.log"'];
+% if NbCore==1
+%     corestring='cpu=1/core=4'; %increases the allowed memory in case of single core job
+% else
+    corestring=['{cluster=''calcul8''}/core=' num2str(max(NbCore,4))];
+% end
+cmd=['oarsub -n UVmat_' ActionFullName ' '...
+    '-t idempotent --checkpoint ' num2str(WallTimeOneProcess*60) ' '...
+    '-l "' corestring bigiojob_string... % char(39) is quote - bigiojob limit UVmat parallel launch on cluster
+    ',walltime=' datestr(WallTimeTotal/24,13) '" '...
+    '-E ' filename_errors ' '...
+    '-O ' filename_log ' '...
+    '"oar-parexec -s -f ' ListProcessFile ' '...
+    '-l ' ListProcessFile '.log"'];