[padb] r407 committed - Add a "launch_mode" to control how the backend processes are launched....

[padb at googlecode.com]

Revision: 407
Author: apittman at gmail.com
Date: Fri Nov  5 17:03:08 2010
Log: Add a "launch_mode" to control how the backend processes are launched.

The four options are local,ssh,pdsh and rmgr and are set as a comma  
seperated
list which is walked until one that is able to launch the job is found.

local: launch the inner process locally.  Only works for single node jobs  
on the local host.
ssh: launch the inner process using ssh.  Only works for single node jobs.
pdsh: launch using pdsh.
rmgr: launch using the selected resource manager.

The old behaviour was equilivent to a setting of "rmgr,local,pdsh", the new
default it "local,rmgr,ssh,pdsh".

http://code.google.com/p/padb/source/detail?r=407

Modified:
  /trunk/src/padb

=======================================
--- /trunk/src/padb	Sun Oct 31 14:00:13 2010
+++ /trunk/src/padb	Fri Nov  5 17:03:08 2010
@@ -575,6 +575,8 @@

  $conf{tree_width} = '4';

+$conf{launch_mode} = 'local,rmgr,ssh,pdsh';
+
  # Config options which take boolean values.
  my @conf_bool = qw(watch_clears_screen inner_callback);

@@ -3711,30 +3713,66 @@
      # Otherwise call the more flexible setup_job function.
      my %pcmd = $rmgr{ $conf{rmgr} }{setup_job}($job);

-    # If the resource manager interface is able to give a hostlist but
-    # not able or willing to launch a shadow job natively then use
-    # pdsh to launch the inner processes.  This allows us to be less
-    # dependant on the resource manager and work in a wider variety of
-    # cases.  Using pdsh like this limits us to 32 hosts (More if we
-    # set the FANOUT pdsh environment variable) so perhaps a better
-    # way can be found in the future.
-    if ( defined $pcmd{host_list} and not defined $pcmd{command} ) {
-
-        my @hosts = @{ $pcmd{host_list} };
-        if ( $hosts[0] ne hostname() or @hosts > 1 ) {
-
-            if ( not find_exe('pdsh') ) {
-                print
-"$conf{rmgr} resource manager on multiple or remote hosts requires pdsh to  
be installed\n";
-                return;
-            }
+# Now we have a either a command capable of launching using the selected  
resource
+# manager, a list of hosts or both.  At this point we can pick the best  
way to
+# launch the job by walkin the list given in the configuration until we  
find one
+# that works.  Note this allows users to prevent the use of the resource  
manager
+# to launch shadow jobs and also to force the use of pdsh.
+
+    my $mode_list = $conf{launch_mode};
+
+# The other three launchers require a host list so in the absence of one  
force it
+# to use rmgr.
+    if ( not defined $pcmd{host_list} ) {
+        $mode_list = 'rmgr';
+    }
+
+    my @modes = split $COMMA, $mode_list;
+
+    my @hosts = @{ $pcmd{host_list} };
+
+    my $have_pdsh = find_exe('pdsh');
+
+    foreach my $mode (@modes) {
+        if ( $mode eq 'local' ) {
+            my $hc = @hosts;
+            my $h  = hostname();
+            if ( @hosts == 1 and $hosts[0] eq hostname() ) {
+                $pcmd{command} = '';
+                return %pcmd;
+            }
+        } elsif ( $mode eq 'rmgr' ) {
+            return %pcmd;
+        } elsif ( $mode eq 'ssh' ) {
+            if ( @hosts == 1 ) {
+                $pcmd{command} = "ssh $hosts[0]";
+                return %pcmd;
+            }
+        } elsif ( $mode eq 'pdsh' and $have_pdsh ) {

              $pcmd{require_inner_callback} = 1;
              my $hlist = join q{,}, @hosts;
              $pcmd{command} = "pdsh -w $hlist";
+
+            if ( @hosts > 20 ) {
+                my $fanout = @hosts + 5;
+                $ENV{FANOUT} = $fanout;
+
+                if ( @hosts > 128 ) {
+                    print "Pdsh backend not recommended for such large  
jobs\n";
+                }
+            }
+
+            return %pcmd;
+
+        } else {
+            print "Backend invalid: $mode\n";
          }
      }
-    return %pcmd;
+
+    print "No suitable backend found (perhaps try installing pdsh?)!\n";
+    return;
+
  }

   
###############################################################################