[PATCH] in /etc/init.d/pcp, if TERM doesnt work, try KILL

[Michael Newton <kimbrr@xxxxxxx>]

I wrote:
>in the current form of /etc/init.d/pcp, it is again possible without too
>much extra fuss to fall back to SIGKILL when TERM doesnt work.
>Heres a patch

..except that if I do that I'd better reinstate _killpmdas() as well..

BTW i chose this in preference to tackling the disentanglement of
testing the -KILL fallback in qa/041 from that of IPC failure

--- a/mgmt/pcp/src/pmcd/rc_pcp  2007-07-25 18:03:33.000000000 +1000
+++ b/mgmt/pcp/src/pmcd/rc_pcp  2007-07-25 18:01:15.005906760 +1000
@@ -4,7 +4,7 @@
 #
 # Start or Stop the Performance Co-Pilot Daemon(s)
 #
-# $Id: rc_pcp,v 1.44 2007/07/17 02:52:06 kimbrr Exp $
+# $Id: rc_pcp,v 1.43 2007/07/12 01:30:21 kimbrr Exp $
 #
 # The following is for chkconfig on RedHat based systems
 # chkconfig: 2345 95 05
@@ -370,6 +370,46 @@
     $RC_STATUS -v
 }

+# Use $PCP_PMCDCONF_PATH to find and kill pipe/socket PMDAs created by PMCD.
+# (First join up continued lines in config file)
+#
+_killpmdas()
+{
+    if [ ! -f $PCP_PMCDCONF_PATH ]
+    then
+       echo "$prog:"'
+Warning: PMCD control file '"$PCP_PMCDCONF_PATH"' is missing, cannot identify 
PMDAs
+         to be terminated.'
+       return
+    fi
+    # Give each PMDA 2 seconds after a SIGTERM to die, then SIGKILL
+    for pmda in `$PCP_AWK_PROG <$PCP_PMCDCONF_PATH '
+/\\\\$/                { printf "%s ", substr($0, 0, length($0) - 1); next }
+               { print }' \
+| $PCP_AWK_PROG '
+$1 ~ /^#/                              { next }
+tolower($3) == "pipe" && NF > 4                { print $5; next }
+tolower($3) == "socket" && NF > 5      { print $6; next }' \
+| sort -u`
+    do
+       $PCP_KILLALL_PROG -TERM `basename $pmda` > /dev/null 2>&1 &
+    done
+    sleep 2
+    for pmda in `$PCP_AWK_PROG <$PCP_PMCDCONF_PATH '
+/\\\\$/                { printf "%s ", substr($0, 0, length($0) - 1); next }
+               { print }' \
+| $PCP_AWK_PROG '
+$1 ~ /^#/                              { next }
+tolower($3) == "pipe" && NF > 4                { print $5; next }
+tolower($3) == "socket" && NF > 5      { print $6; next }' \
+| sort -u`
+    do
+       $PCP_KILLALL_PROG -KILL `basename $pmda` > /dev/null 2>&1 &
+    done
+
+    wait
+}
+
 _shutdown()
 {
     # Is pmcd running?
@@ -397,18 +437,12 @@
          Assuming an uninstall from a chroot: PMCD not killed.
          If this is incorrect, kill -TERM can be applied to the above PID."
         exit
-
-    # Send pmcd a SIGTERM, which is noted as a pending shutdown.
-    # When finished the currently active request, pmcd will close any
-    # connections, wait for any agents, and then exit.
-    #
     elif [ -f $PCP_RUN_DIR/pmcd.pid ]
     then
        TOKILL=`cat $PCP_RUN_DIR/pmcd.pid`
        if grep "^$TOKILL$" $tmp.tmp >/dev/null
        then
-           kill -TERM $TOKILL >/dev/null 2>&1
-           rm -f $PCP_RUN_DIR/pmcd.pid
+           :
        else
            echo "Process ..."
            cat $tmp.tmp
@@ -419,26 +453,54 @@
            exit
        fi
     else
-       $PCP_KILLALL_PROG -TERM pmcd > /dev/null 2>&1
+       TOKILL=
     fi
+
+    # Send pmcd a SIGTERM, which is noted as a pending shutdown.
+    # When finished the currently active request, pmcd will close any
+    # connections, wait for any agents, and then exit.
+    # On failure, resort to SIGKILL.
+    #
     $ECHO $PCP_ECHO_N "Waiting for PMCD to terminate ...""$PCP_ECHO_C"
-    delay=200  # tenths of a second
-    while [ $delay -gt 0 ]
+    delay=80   # tenths of a second
+    for SIG in TERM KILL
     do
-       _get_pids_by_name pmcd >$tmp.tmp
-       [ ! -s $tmp.tmp ] && break
-       pmsleep 0.1
-       delay=`expr $delay - 1`
-       [ `expr $delay % 10` -ne 0 ] || $ECHO $PCP_ECHO_N ".""$PCP_ECHO_C"
-    done
-    if [ $delay -eq 0 ]        # It just WON'T DIE, give up.
-    then
+       if [ "x$TOKILL" == "x" ]
+       then
+           $PCP_KILLALL_PROG -$SIG pmcd > /dev/null 2>&1
+       else
+           kill -$SIG $TOKILL >/dev/null 2>&1
+           rm -f $PCP_RUN_DIR/pmcd.pid
+       fi
+       while [ $delay -gt 0 ]
+       do
+           _get_pids_by_name pmcd >$tmp.tmp
+           [ ! -s $tmp.tmp ] && break 2
+           pmsleep 0.1
+           delay=`expr $delay - 1`
+           [ "$SIG" == "TERM" ] && [ `expr $delay % 10` -eq 0 ] \
+               && $ECHO $PCP_ECHO_N ".""$PCP_ECHO_C"
+       done
+       echo
        echo "Process ..."
-       cat $tmp.tmp
-       echo "$prog: Warning: PMCD won't die!"
-       exit
-    fi
-     $RC_STATUS -v
+       if [ "$SIG" == "TERM" ]
+       then
+           ps $PCP_PS_ALL_FLAGS >$tmp.ps
+           sed 1q $tmp.ps
+           for pid in `cat $tmp.tmp`
+           do
+               $PCP_AWK_PROG <$tmp.ps "\$2 == $pid { print }"
+           done
+           echo "$prog: Warning: Forcing PMCD to terminate!"
+           delay=20
+       else
+           cat $tmp.tmp
+           echo "$prog: Warning: PMCD won't die!"
+           exit
+       fi
+    done
+    _killpmdas
+    $RC_STATUS -v
     pmpost "stop pmcd from $PCP_RC_DIR/pcp"
 }


Dr.Michael("Kimba")Newton  kimbrr@xxxxxxx