[padb] r409 committed - Add a timeout to the inner loop to allow the code to exit silently ...

[padb at googlecode.com]

Revision: 409
Author: apittman at gmail.com
Date: Sat Nov  6 16:16:23 2010
Log: Add a timeout to the inner loop to allow the code to exit silently
if the outer process is killed for any reason.  Pass through "interval"
from the outer process to the inner processes so they can set
an appropiate value for this timeout, do this on the command line
so it can be set once at startup rather than at signon.

http://code.google.com/p/padb/source/detail?r=409

Modified:
  /trunk/src/padb

=======================================
--- /trunk/src/padb	Sat Nov  6 14:16:22 2010
+++ /trunk/src/padb	Sat Nov  6 16:16:23 2010
@@ -373,9 +373,9 @@
  my @inner_conf =
    qw(edb edbopt rmgr scripts slurm_job_step pbs_server lsf_mode  
lsfmpi_server lsfmpi_mpirpid lsfmpi_port);

-# More config options the inner knows about, these are forwarded on the
+# More options the inner knows about, these are forwarded on the
  # command line rather than over the sockets.
-my @inner_conf_cmd = qw(port_range outer);
+my @inner_conf_cmd = qw(port_range outer interval);

   
###############################################################################
  #
@@ -5697,11 +5697,11 @@
      }

      foreach my $co (@conf_bool) {
-        $conf{$co} = check_and_convert_bool( $conf{$co} );
+        config_set_internal( $co, check_and_convert_bool( $conf{$co} ) );
      }

      foreach my $co (@conf_time) {
-        $conf{$co} = check_and_convert_time( $conf{$co} );
+        config_set_internal( $co, check_and_convert_time( $conf{$co} ) );
      }

      foreach my $co (@conf_int) {
@@ -9984,6 +9984,8 @@
      my $hostname = $inner_conf{hostname};
      my $key      = rand;

+    my $outer_timeout = $inner_conf{interval} * 2;
+
      if ( defined $outerloc ) {
          my ( $ohost, $oport ) = split $COLON, $outerloc;
          my $os = IO::Socket::INET->new(
@@ -10019,8 +10021,14 @@

      my $stime = time;

+    # "Last seen time" of another process.  This is the time we last had  
any
+    # communication from the outer, if it becomes too far in the past then
+    # we should probably exit.
+    my $ltime = $stime;
+
      while ( $sel->count() > 0 ) {
          while ( my @data = $sel->can_read(5) ) {
+            $ltime = time;
              foreach my $s (@data) {
                  if ( $s == $server ) {
                      my $new = $server->accept() or confess('Failed  
accept');
@@ -10071,6 +10079,16 @@
          if ( ( $sel->count() == 1 ) and ( ( $time - $stime ) > 30 ) ) {
              exit 0;
          }
+
+        # If we are (were) connected but haven't heard anything for a  
while then
+        # the outer process has likely died so we should also exit cleanly.
+        # There doesn't seem to be another way to detect this so just abort
+        # if we haven't heard anything for a while.  This value needs to be
+        # greater than the maximum reasonable value for 'interval' in the
+        # outer process.
+        if ( ( $time - $ltime ) > $outer_timeout ) {
+            exit 0;
+        }
      }
      my $count = $sel->count();
      print "Thats not supposed to happen count=($count)\n";