Run with: ./fetch.py --user iupui_ndt --nodelist ../plsync/good.ndt.txt --threadcount=40 --timeout 300 --script kill_ndt

kill_ndt.sh

(
parent=$( pstree -a -A -p | grep ndtd | grep -v grep | head -1 | tr ',' ' ' | awk '{print $2}' )
ps ax -opid,args \
  | grep ndtd \
  | grep -v grep \
  | awk 'BEGIN {
            start_time_index = 22 ;
            utime_index = 14 ;
            stime_index = 15 ;

            # All older processes will have an earlier (smaller) start_time.
            "cat /proc/self/stat" |& getline result ; split(result, proc) ;
            awk_start = proc[start_time_index] ;
        }
        {
            # Read the start_time of each NDT process.
            sprintf("cat /proc/%d/stat", $1) |& getline result ; split(result, proc) ;
            cpu_time = proc[utime_index] + proc[stime_index] ;
            t_diff = awk_start - proc[start_time_index] ;

            # NDT should not last longer than 5 minutes (300 sec, 30000 ticks).
            if ('$parent' != $1) {
               if (t_diff > 30000 ) {
                  print "killed_child_of", '$parent', "cpu", cpu_time, "tdiff", t_diff, result ;
                  system(sprintf("sudo kill %d", $1)) ;
               }
            }
        }'
)