[padb-devel] [padb] r197 committed - re-check that a given process exists when walking through /proc in a n...

[codesite-noreply at google.com]

Revision: 197
Author: apittman
Date: Mon Sep  7 01:36:34 2009
Log: re-check that a given process exists when walking through /proc in a  
number of places.

http://code.google.com/p/padb/source/detail?r=197

Modified:
  /branches/cleanup/src/padb

=======================================
--- /branches/cleanup/src/padb	Sun Sep  6 14:30:15 2009
+++ /branches/cleanup/src/padb	Mon Sep  7 01:36:34 2009
@@ -656,6 +656,11 @@
      foreach my $pid (@pids) {
          next unless ( $pid =~ m{\A\d+\z}xms );
          my ( undef, undef, undef, undef, $owner ) = stat("/proc/$pid");
+
+        # Check the stat worked, it's possible for processes to dissapear
+        # Take care to check for defined rather than true as root has a
+        # uid of zero.
+        next unless defined $owner;
          next unless $owner == $uid;
          push @userpids, $pid;
      }
@@ -6570,7 +6575,7 @@
  sub is_resmgr_process {
      my $pid  = shift;
      my $name = find_from_status( $pid, 'Name' );
-    my $mgrs = { 'rmsloader' => 1, 'slurmd' => 1, 'slurmstepd' => 1 };
+    my $mgrs = { rmsloader => 1, slurmd => 1, slurmstepd => 1 };
      return 1 if ( defined $mgrs->{$name} );
      return;
  }
@@ -6891,11 +6896,16 @@
              $newpid = $ppids[0];
          }

-        push @apids,
-          {
-            pid => $newpid,
-            vp  => $ip->{rank}
-          };
+        # The process might have died and we simply didn't find anything,
+        # if this is the case then just skip it, the outer will notice
+        # the missing signon and report an approtiate error.
+        if ( defined $newpid ) {
+            push @apids,
+              {
+                pid => $newpid,
+                vp  => $ip->{rank}
+              };
+        }
      }

      # Sort local pids by order of increasing rank.