Right. Fix the real problem in the child, or just add a timeout:

# wait to reap all children
for my $pid (@child_pids)
{
    local $SIG{__DIE__};
    local $@ = "";
                                                                   
    eval {
        local $SIG{ALRM} = sub { die("alarm\n") };
        alarm(3600);

        # potentially long operation
        waitpid $pid, 0;

        alarm(0);
        1;
    } or do {
        die($@) unless $@ eq "alarm\n";
                                                                   
        # timed out
        warn("Waited too long for child $pid. Skipping it.\n");
    }
}
[download]