help from Nelson Kawumi on 2002-08-01 (tru64-unix-managers)

From: Nelson Kawumi <kawumin_at_mtn.co.ug>
Date: Wed, 31 Jul 2002 16:46:02 +0300

>I'm running a script that does continuous ftp of files to a given ftp
>server. When started manually, it runs fine. When started using CAA, it
>gives the following error,
>
>
>
>EVM alert [sauga01.mtn.co.ug]: CAAD[524900]: `streamserve` on `sauga01` went
>OFFLINE unexpectedly
>
>in the CAA script I run the following to stop the application
>
>kill `ps -e | grep streamserve.sh | grep -v "grep" | cut -d " " -f 1`
>
>I need help on this error
>
>Attached are my profile and script
>
>Profile
>
>NAME=streamserve
>
>TYPE=application
>
>ACTION_SCRIPT=streamserve.scr
>
>ACTIVE_PLACEMENT=0
>
>AUTO_START=1
>
>CHECK_INTERVAL=60
>
>DESCRIPTION=streamserve
>
>FAILOVER_DELAY=0
>
>FAILURE_INTERVAL=40
>
>FAILURE_THRESHOLD=3
>
>HOSTING_MEMBERS=sauga02 sauga01
>
>OPTIONAL_RESOURCES=
>
>PLACEMENT=restricted
>
>REQUIRED_RESOURCES=
>
>RESTART_ATTEMPTS=1
>
>SCRIPT_TIMEOUT=60
>
>Script
>
>
>
>SERVICE_NAME="streamserve"
>
>PROBE_PROCS="/usr/scripts/streamserve.sh"
>
>START_APPCMD="/usr/scripts/streamserve.sh"
>
>STOP_APPCMD="/usr/scripts/streamservestop.sh"
>
>APPDIR="/usr/scripts"
>
>export SERVICE_NAME START_APPCMD START_APPCMD2
>
>export APPDIR PROBE_PROCS STOP_APPCMD STOP_APPCMD2
>
>DEBUG_PRIORITY=100
>
>INFO_PRIORITY=200
>
>ERROR_PRIORITY=500
>
>SCRIPT=$0
>
>ACTION=$1 # Action (start, stop or check)
>
>EVMPOST="/usr/bin/evmpost" # EVM command to post events
>
>DEBUG=0
>
>if [[ "$CAA_SCRIPT_DEBUG" != "" ]]; then
>
>DEBUG=1
>
>EVMPOST="/usr/bin/evmpost -r | /usr/bin/evmshow -d"
>
>fi
>
>export EVMPOST ACTION SCRIPT
>
>etpid () {
>
>if [ -n "$1" ]; then
>
>GETMYPID=$1
>
>shift
>
>/bin/ps -e -o pid,command $* | while read mypid command args
>
>do
>
>if [ "$command" = "$GETMYPID" ]; then
>
>echo "$mypid"
>
>fi
>
>done
>
>fi
>
>
>
>zapdaemon () {
>
>typeset ret=0
>
>for i in ${1}
>
>do
>
>checkdaemon ${i}
>
>if [ $? -ne 0 ]; then
>
>kill `getpid ${i}`
>
>checkdaemon ${i}
>
>if [ $? -ne 0 ]; then
>
>kill -9 `getpid ${i}`
>
>checkdaemon ${i}
>
>if [ $? -ne 0 ]; then
>
>postevent $ERROR_PRIORITY "${i}: stuck - could not kill -KIL
>
>L"
>
>ret=1
>
>else
>
>postevent $ERROR_PRIORITY "${i}: killed with -KILL"
>
>fi
>
>else
>
>postevent "" "${i}: killed"
>
>fi
>
>fi
>
>done
>
>return $ret
>
>
>
>probeapp () {
>
>checkdaemon $1
>
>if [ $? -ne 0 ]; then
>
>postevent $DEBUG_PRIORITY "$1 check OK"
>
>return 0
>
>else
>
>postevent $DEBUG_PRIORITY "$1 check failed"
>
>return 1
>
>fi
>
>
>
>case $1 in
>
>'start')
>
>postevent $DEBUG_PRIORITY "trying to start"
>
>cd $APPDIR
>
>if [ "$START_APPCMD" != "" ]; then
>
>$START_APPCMD &
>
>if [ $? -ne 0 ]; then
>
>postevent $ERROR_PRIORITY "start: $out"
>
>exit 1
>
>fi
>
>fi
>
>
>
>'stop')
>
>postevent $DEBUG_PRIORITY "trying to stop"
>
>cd $APPDIR
>
>if [ "$STOP_APPCMD" != "" ]; then
>
>$STOP_APPCMD &
>
>if [ $? -ne 0 ]; then
>
>postevent $ERROR_PRIORITY "stop: $out"
>
>exit 1
>
>fi
>
>fi
>
>if [ $STOP_APPCMD2 != "" ]; then
>
>$STOP_APPCMD2 &
>
>if [ $? -ne 0 ]; then
>
>postevent $ERROR_PRIORITY "stop 2: $out"
>
>exit 1
>
>fi
>
>fi
>
>if [ "$START_APPCMD2" != "" ]; then
>
>$START_APPCMD2 &
>
>if [ $? -ne 0 ]; then
>
>postevent $ERROR_PRIORITY "start 2: $out"
>
>exit 1
>
>fi
>
>fi
>
>;;
>
>for i in ${PROBE_PROCS}; do
>
>zapdaemon ${i}
>
>done
>
>;;
>
>'check')
>
>for i in ${PROBE_PROCS}; do
>
>postevent $DEBUG_PRIORITY "trying to check $i"
>
>probeapp $i
>
>if [ $? -ne 0 ]; then
>
>postevent "" "check failed for $i"
>
>exit 1
>
>fi
>
>done
>
>;;
>
>*)
>
>postevent $ERROR_PRIORITY "usage: $0 {start|stop|check}"
>
>exit 1
>
>;;
>
>esac
>
>postevent "" success
>
>exit 0
>
>
>
><!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 3.2//EN">
><HTML>
><HEAD>
><TITLE></TITLE>
></HEAD>
><BODY>
>
>
>I'm running a script that does continuous ftp of files to a
given ftp 
>server. When started manually, it runs fine. When started using CAA, it 
>gives the following error, 
> 
> 
> 
>EVM alert [sauga01.mtn.co.ug]: CAAD[524900]: `streamserve` on `sauga01`
went 
>OFFLINE unexpectedly 
> 
>in the CAA script I run the following to stop the application 
> 
>kill `ps -e | grep streamserve.sh | grep -v "grep" | cut -d "
" -f 1` 
> 
>I need help on this error 
> 
>Attached are my profile and script 
> 
>Profile 
> 
>NAME=streamserve 
> 
>TYPE=application 
> 
>ACTION_SCRIPT=streamserve.scr 
> 
>ACTIVE_PLACEMENT=0 
> 
>AUTO_START=1 
> 
>CHECK_INTERVAL=60 
> 
>DESCRIPTION=streamserve 
> 
>FAILOVER_DELAY=0 
> 
>FAILURE_INTERVAL=40 
> 
>FAILURE_THRESHOLD=3 
> 
>HOSTING_MEMBERS=sauga02 sauga01 
> 
>OPTIONAL_RESOURCES= 
> 
>PLACEMENT=restricted 
> 
>REQUIRED_RESOURCES= 
> 
>RESTART_ATTEMPTS=1 
> 
>SCRIPT_TIMEOUT=60 
> 
>Script 
> 
> 
> 
>SERVICE_NAME="streamserve" 
> 
>PROBE_PROCS="/usr/scripts/streamserve.sh" 
> 
>START_APPCMD="/usr/scripts/streamserve.sh" 
> 
>STOP_APPCMD="/usr/scripts/streamservestop.sh" 
> 
>APPDIR="/usr/scripts" 
> 
>export SERVICE_NAME START_APPCMD START_APPCMD2 
> 
>export APPDIR PROBE_PROCS STOP_APPCMD STOP_APPCMD2 
> 
>DEBUG_PRIORITY=100 
> 
>INFO_PRIORITY=200 
> 
>ERROR_PRIORITY=500 
> 
>SCRIPT=$0 
> 
>ACTION=$1 # Action (start, stop or check) 
> 
>EVMPOST="/usr/bin/evmpost" # EVM command to post events 
> 
>DEBUG=0 
> 
>if [[ "$CAA_SCRIPT_DEBUG" != "" ]]; then 
> 
>DEBUG=1 
> 
>EVMPOST="/usr/bin/evmpost -r | /usr/bin/evmshow -d" 
> 
>fi 
> 
>export EVMPOST ACTION SCRIPT 
> 
>etpid () { 
> 
>if [ -n "$1" ]; then 
> 
>GETMYPID=$1 
> 
>shift 
> 
>/bin/ps -e -o pid,command $* | while read mypid command args 
> 
>do 
> 
>if [ "$command" = "$GETMYPID" ]; then 
> 
>echo "$mypid" 
> 
>fi 
> 
>done 
> 
>fi 
> 
>} 
> 
>zapdaemon () { 
> 
>typeset ret=0 
> 
>for i in ${1} 
> 
>do 
> 
>checkdaemon ${i} 
> 
>if [ $? -ne 0 ]; then 
> 
>kill `getpid ${i}` 
> 
>checkdaemon ${i} 
> 
>if [ $? -ne 0 ]; then 
> 
>kill -9 `getpid ${i}` 
> 
>checkdaemon ${i} 
> 
>if [ $? -ne 0 ]; then 
> 
>postevent $ERROR_PRIORITY "${i}: stuck - could not kill -KIL 
> 
>L" 
> 
>ret=1 
> 
>else 
> 
>postevent $ERROR_PRIORITY "${i}: killed with -KILL" 
> 
>fi 
> 
>else 
> 
>postevent "" "${i}: killed" 
> 
>fi 
> 
>fi 
> 
>done 
> 
>return $ret 
> 
>} 
> 
>probeapp () { 
> 
>checkdaemon $1 
> 
>if [ $? -ne 0 ]; then 
> 
>postevent $DEBUG_PRIORITY "$1 check OK" 
> 
>return 0 
> 
>else 
> 
>postevent $DEBUG_PRIORITY "$1 check failed" 
> 
>return 1 
> 
>fi 
> 
>} 
> 
>case $1 in 
> 
>'start') 
> 
>postevent $DEBUG_PRIORITY "trying to start" 
> 
>cd $APPDIR 
> 
>if [ "$START_APPCMD" != "" ]; then 
> 
>$START_APPCMD & 
> 
>if [ $? -ne 0 ]; then 
> 
>postevent $ERROR_PRIORITY "start: $out" 
> 
>exit 1 
> 
>fi 
> 
>fi 
> 
> 
> 
>'stop') 
> 
>postevent $DEBUG_PRIORITY "trying to stop" 
> 
>cd $APPDIR 
> 
>if [ "$STOP_APPCMD" != "" ]; then 
> 
>$STOP_APPCMD & 
> 
>if [ $? -ne 0 ]; then 
> 
>postevent $ERROR_PRIORITY "stop: $out" 
> 
>exit 1 
> 
>fi 
> 
>fi 
> 
>if [ $STOP_APPCMD2 != "" ]; then 
> 
>$STOP_APPCMD2 & 
> 
>if [ $? -ne 0 ]; then 
> 
>postevent $ERROR_PRIORITY "stop 2: $out" 
> 
>exit 1 
> 
>fi 
> 
>fi 
> 
>if [ "$START_APPCMD2" != "" ]; then 
> 
>$START_APPCMD2 & 
> 
>if [ $? -ne 0 ]; then 
> 
>postevent $ERROR_PRIORITY "start 2: $out" 
> 
>exit 1 
> 
>fi 
> 
>fi 
> 
>;; 
> 
>for i in ${PROBE_PROCS}; do 
> 
>zapdaemon ${i} 
> 
>done 
> 
>;; 
> 
>'check') 
> 
>for i in ${PROBE_PROCS}; do 
> 
>postevent $DEBUG_PRIORITY "trying to check $i" 
> 
>probeapp $i 
> 
>if [ $? -ne 0 ]; then 
> 
>postevent "" "check failed for $i" 
> 
>exit 1 
> 
>fi 
> 
>done 
> 
>;; 
> 
>*) 
> 
>postevent $ERROR_PRIORITY "usage: $0 {start|stop|check}" 
> 
>exit 1 
> 
>;; 
> 
>esac 
> 
>postevent "" success 
> 
>exit 0 
> 
> 
>
>
>
></BODY>
></HTML>
Received on Wed Jul 31 2002 - 13:44:56 NZST

This archive was generated by hypermail 2.4.0 : Wed Nov 08 2023 - 11:53:43 NZDT