[padb] r423 committed - Handle ompi-ps output when it's compiled with support for checkpoint-r...

[padb at googlecode.com]

Revision: 423
Author: apittman at gmail.com
Date: Mon Dec  6 13:22:27 2010
Log: Handle ompi-ps output when it's compiled with support for  
checkpoint-restart.
This adds extra output to the ompi-ps command which was causing the pattern
matching to fail so be more careful in what we check for to ensure we match
both the case when it's enabled and also the case where it isn't.

http://code.google.com/p/padb/source/detail?r=423

Modified:
  /trunk/src/padb

=======================================
--- /trunk/src/padb	Fri Dec  3 10:04:09 2010
+++ /trunk/src/padb	Mon Dec  6 13:22:27 2010
@@ -635,16 +635,19 @@
      printf {*STDERR} "Time value \"%s\" not recognised, aborting.\n", $str;
      exit 1;
  }
+
+sub is_digit {
+    my ($str) = @_;
+
+    return $str =~ m{\A     # Start of line
+		   \d+    # A number
+		   \z}x
+}

  sub check_int {
      my ($str) = @_;

-    return
-      if (
-        $str =~ m{\A     # Start of line
-                  \d+    # A number
-                  \z}x
-      );
+    return if ( is_digit($str) );

      printf {*STDERR} "Integer value \"%s\" not recognised, aborting.\n",  
$str;
      exit 1;
@@ -3248,26 +3251,36 @@
          next if ( $l eq $EMPTY_STRING );

          my @elems = split qr{\s*\|\s*}, $l;
-
-        if ( @elems == 4 ) {
+        next unless @elems >= 4;
+
+# We used to check for the number of elements here and then match the  
jobid seperatly but that doesn't
+# work for all cases as sometimes Open-Mpi has extra checkpoint-restart  
related data on the end
+# of each line changing the element count and hence the test to fail.  Now  
we check the element count
+# is at least as long as we expect, we check that all fields that should  
be integers are actually integers
+# and I've moved the regexp for matching the job ID into the line test.
+# For performance reasons I've put the per-rank test before the per-job  
test as it triggers more often.
+        if (    @elems >= 6
+            and ( $elems[1] =~ m{\A\[\[(\d+)\,(\d+)\]\,(\d+)\]}x )
+            and is_digit( $elems[2] )
+            and is_digit( $elems[3] ) )
+        {
+            my $job  = $1;
+            my $step = $2;
+            my $rank = $3;
+            my $pid  = $elems[3];
+            my $host = $elems[4];
+            $open_jobs{$job}{$step}{hosts}{$host}++;
+            $open_jobs{$job}{$step}{ranks}{$host}{$rank} = $pid;
+
+        } elsif ( @elems >= 4
+            and ( $elems[0] =~ m{\A\[(\d+)\,(\d+)]\z}x )
+            and is_digit( $elems[2] )
+            and is_digit( $elems[3] ) )
+        {
              my $nprocs = $elems[3];
-            my $name   = $elems[0];
-            if ( $name =~ m{\A\[(\d+)\,(\d+)]\z}x ) {
-                my $job  = $1;
-                my $step = $2;
-                $open_jobs{$job}{$step}{nprocs} = $nprocs;
-            }
-        } elsif ( @elems == 6 ) {
-            my $name = $elems[1];
-            if ( $name =~ m{\A\[\[(\d+)\,(\d+)\]\,(\d+)\]}x ) {
-                my $job  = $1;
-                my $step = $2;
-                my $rank = $3;
-                my $pid  = $elems[3];
-                my $host = $elems[4];
-                $open_jobs{$job}{$step}{hosts}{$host}++;
-                $open_jobs{$job}{$step}{ranks}{$host}{$rank} = $pid;
-            }
+            my $job    = $1;
+            my $step   = $2;
+            $open_jobs{$job}{$step}{nprocs} = $nprocs;
          }
      }
      return;