[Swift-devel] Dynamic profiles and count

[David Kelly]

Hello,

I have been working on a namd scaling test using Swift. I am using the plain PBS provider at the moment (no coasters). The swift script sets a minimum number of nodes, a maximum number of nodes, iterates through those values, then uses dynamic profiles to change the value of 'count' to modify the number of nodes to request. Here is the script:

---
type file;

app (file out, file err) namd_wrapper (int numnodes, file psf_file, file pdb_file, file coord_restart_file, 
                                       file velocity_restart_file, file system_restart_file)
{
   profile "count" = numnodes;
   namd_wrapper @psf_file @pdb_file @coord_restart_file @velocity_restart_file @system_restart_file stdout=@out stderr=@err; 
}

# Range of nodes to test on
int minNodes=1;
int maxNodes=2;
int delta=1;

# Files
file psf <"h0_solvion.psf">;
file pdb <"h0_solvion.pdb">;
file coord_restart <"h0_eq.0.restart.coor">;
file velocity_restart <"h0_eq.0.restart.vel">;
file system_restart <"h0_eq.0.restart.xsc">;

foreach nodes in [minNodes:maxNodes:delta] {
   file output <single_file_mapper; file=@strcat("logs/scaling-", nodes, ".out.txt")>;
   file error <single_file_mapper; file=@strcat("logs/scaling-", nodes, ".err.txt")>;
   (output, error) = namd_wrapper(nodes, psf, pdb, coord_restart, velocity_restart, system_restart);
}
---

In sites.xml, I also set the jobtype to "single" so it doesn't start a worker on each node (namd uses MPI).

The problem that I'm running into is that, as is, dynamic profiles do not seem to allow you to modify the value for count. I have a workaround for this which involves removing references to "count" in GridExec.java, Execute.java, and TCProfile.java. This works for me in terms of this script, and it works with a few other simple catsn type scripts I've tested. I just wanted to double check to make sure this wouldn't cause any other issues before committing. Here are the changes:

Index: modules/karajan/src/org/globus/cog/karajan/workflow/nodes/grid/GridExec.java
===================================================================
--- modules/karajan/src/org/globus/cog/karajan/workflow/nodes/grid/GridExec.java        (revision 3472)
+++ modules/karajan/src/org/globus/cog/karajan/workflow/nodes/grid/GridExec.java        (working copy)
@@ -56,7 +56,7 @@
         public static final Arg A_STDIN = new Arg.Optional("stdin");
         public static final Arg A_PROVIDER = new Arg.Optional("provider");
         public static final Arg A_SECURITY_CONTEXT = new Arg.Optional("securitycontext");
-        public static final Arg A_COUNT = new Arg.Optional("count");
+        // public static final Arg A_COUNT = new Arg.Optional("count");
         public static final Arg A_HOST_COUNT = new Arg.Optional("hostcount");
         public static final Arg A_JOBTYPE = new Arg.Optional("jobtype");
         public static final Arg A_MAXTIME = new Arg.Optional("maxtime");
@@ -86,7 +86,8 @@
         static {
                 setArguments(GridExec.class, new Arg[] { A_EXECUTABLE, A_ARGS, A_ARGUMENTS, A_HOST,
                                 A_STDOUT, A_STDERR, A_STDOUTLOCATION, A_STDERRLOCATION, A_STDIN, A_PROVIDER,
-                                A_COUNT, A_HOST_COUNT, A_JOBTYPE, A_MAXTIME, A_MAXWALLTIME, A_MAXCPUTIME,
+                                // A_COUNT,
+                                A_HOST_COUNT, A_JOBTYPE, A_MAXTIME, A_MAXWALLTIME, A_MAXCPUTIME,
                                 A_ENVIRONMENT, A_QUEUE, A_PROJECT, A_MINMEMORY, A_MAXMEMORY, A_REDIRECT,
                                 A_SECURITY_CONTEXT, A_DIRECTORY, A_NATIVESPEC, A_DELEGATION, A_ATTRIBUTES,
                                 C_ENVIRONMENT, A_FAIL_ON_JOB_ERROR, A_BATCH, C_STAGEIN, C_STAGEOUT, C_CLEANUP,
@@ -346,7 +347,7 @@
                 }
         }
 
-        protected final static Arg[] MISC_ATTRS = new Arg[] { A_COUNT, A_HOST_COUNT, A_JOBTYPE,
+        protected final static Arg[] MISC_ATTRS = new Arg[] { A_HOST_COUNT, A_JOBTYPE,
                         A_MAXTIME, A_MAXWALLTIME, A_MAXCPUTIME, A_QUEUE, A_PROJECT, A_MINMEMORY, A_MAXMEMORY };
 
         protected void setMiscAttributes(JobSpecification js, VariableStack stack)

Index: src/org/griphyn/vdl/karajan/lib/TCProfile.java
===================================================================
--- src/org/griphyn/vdl/karajan/lib/TCProfile.java        (revision 5930)
+++ src/org/griphyn/vdl/karajan/lib/TCProfile.java        (working copy)
@@ -63,7 +63,6 @@
 
         static {
                 PROFILE_T = new HashMap<String, Arg>();
-                PROFILE_T.put("count", GridExec.A_COUNT);
                 PROFILE_T.put("jobtype", GridExec.A_JOBTYPE);
                 PROFILE_T.put("maxcputime", GridExec.A_MAXCPUTIME);
                 PROFILE_T.put("maxmemory", GridExec.A_MAXMEMORY);

Index: src/org/griphyn/vdl/karajan/lib/Execute.java
===================================================================
--- src/org/griphyn/vdl/karajan/lib/Execute.java        (revision 5930)
+++ src/org/griphyn/vdl/karajan/lib/Execute.java        (working copy)
@@ -47,7 +47,7 @@
         static {
                 setArguments(Execute.class, new Arg[] { A_EXECUTABLE, A_ARGS, A_ARGUMENTS, A_HOST,
                                 A_STDOUT, A_STDERR, A_STDOUTLOCATION, A_STDERRLOCATION, A_STDIN, A_PROVIDER,
-                                A_COUNT, A_HOST_COUNT, A_JOBTYPE, A_MAXTIME, A_MAXWALLTIME, A_MAXCPUTIME,
+                                A_HOST_COUNT, A_JOBTYPE, A_MAXTIME, A_MAXWALLTIME, A_MAXCPUTIME,
                                 A_ENVIRONMENT, A_QUEUE, A_PROJECT, A_MINMEMORY, A_MAXMEMORY, A_REDIRECT,
                                 A_SECURITY_CONTEXT, A_DIRECTORY, A_NATIVESPEC, A_DELEGATION, A_ATTRIBUTES,
                                 C_ENVIRONMENT, A_FAIL_ON_JOB_ERROR, A_BATCH, A_REPLICATION_GROUP,