Process monitoring in UNIX shell scripting

 Top
 Gets you a list of processes that are consuming the CPU
 htop
 Near real time list of running processes by CPU, includes
scrolling, and mouse support
 vmstat
 Provides information about processes, memory, paging, I/O,
traps and CPU
 w/who/finger
 Provides information about users that are consuming
resources on the computer
 ps (ps –ef )
 Lists all the currently running processes on a Linux computer

 pgrep/pkill
 pgrep <process name> lists the PID of the process based on
name
 pkill <process name> sends a specific kill signal (default
sigterm or shutdown) to a matching process
 free
 Shows the current memory usage of the system. Shows
physical and swap memory
 mpstat
 mpstat 2 5 - shows five set of data of global statistics among
all processors at two second intervals.
 mpstat –P ALL 2 5 - shows 5 sets of statistics for all processors
at two second intervals.

 iostat
 reports CPU statists for devices and partitions
(including NFS Samba partitions)
 pmap
 This command reports memory map of a process. This
can be used to find memory usage of the process.

 Set the debug mode for this, you will want it,
remember what each debug mode switch does
1. # set -n : Uncomment to check script syntax, without
execution.
2. # Note: Do not forget to put the comment back in
or
3. # the shell script will not execute!
4. # set -x : Uncomment to debug this shell script

 PROC_MON=`basename $0` # Defines the script_name variable as the
file name of this script
LOGFILE="/home/ganesh/procmon.log" # Shows log file and where
located
[[ ! -s $LOGFILE ]] && touch $LOGFILE # This checks to see if the file exists
# if not it creates one.
TTY=$(tty) # Current tty or pty
PROCESS="ssh" # This will define which process to monitor
SLEEP_TIME="1" # This is the sleep time in second between
monitoring

txtred=$(tput setaf 1) # Red: will indicate a failed process and the information
txtgrn=$(tput setaf 2) # Green: this is successful process information
txtylw=$(tput setaf 3) # Yellow: this is used to show cautionary information
txtrst=$(tput sgr0) # resets text

 function exit_trap # this is the behavior of the trap
signal
{
# Log an ending time for process monitoring
DATE=$(date +%D)
TIME=$(date +%T) # Get a new timestamp...
echo "$DATE @ $TIME: Monitoring for $PROCESS
terminated" >> $LOGFILE & # this will create an entry in
the logfile
echo "$DATE @ $TIME: ${txtred}Monitoring for
$PROCESS terminated${txtrst}"
#kill all functions
kill -9 $(jobs -p) 2>/dev/null

 Set the trap to see if the process exits
 trap 'exit_trap; exit 0' 1 2 3 15

# this will see if process is running if not will start it

ps aux | grep "$PROCESS" | grep -v "grep $PROCESS"
| grep -v $PROC_MON >/dev/null

 if (( $? != 0 ))
then
DATE=$(date +%D)
TIME=$(date +%T)
echo
echo "$DATE @ $TIME: $PROCESS is NOT active...starting $PROCESS.." >> $LOGFILE & #
creates
# an entry in the logfile
echo "$DATE @ $TIME: ${txtylw}$PROCESS is NOT active...starting $PROCESS..${txtrst}"
echo
sleep 1
service $PROCESS start &
echo "$DATE @ $TIME: $PROCESS has been started..." >> $LOGFILE & #puts an enrty in logfile
else # this will say what to do if process is already running
echo -e "n" # a blank line
DATE=$(date +%D)
TIME=$(date +%T)
echo "$DATE @ $TIME: $PROCESS is currnetly RUNNING..." >> $LOGFILE & # puts entry in logfile
echo "$DATE @ $TIME: ${txtgrn}$PROCESS is currently RUNNING...${txtrst}"
fi

 while (( RC == 0 )) # this will loop until the return code is not zero
do
ps aux | grep $PROCESS | grep -v "grep $PROCESS"
| grep -v $PROC_MON >/dev/null 2>&1
if (( $? != 0 )) # check the return code
then
echo
DATE=$(date +%D)
TIME=$(date +%T)
echo "$DATE @ $TIME: $PROCESS has STOPPED..." >> $LOGFILE & # entry
in logfile
echo "$DATE @ $TIME: ${txtred}$PROCESS has STOPPED...${txtrst}"
echo
service $PROCESS start &
echo "$DATE @ $TIME: $PROCESS has RESTARTED..." >> $LOGFILE & #
ENTRY IN LOGFILE
echo "$DATE @ $TIME: ${txtgrn}$PROCESS has RESTARTED...${txtrst}"
sleep 1

 ps aux | grep $PROCESS | grep -v "grep $PROCESS"
| grep -v $PROC_MON >/dev/null 2>&1
if (( $? != 0 )) # This will check the return code
then
echo
DATE=$(date +%D) # New time stamp
TIME=$(date +%T)
echo "$DATE @ $TIME: $PROCESS failed to restart..." >> $LOGFILE
& #entry in logfile
echo "$DATE @ $TIME: ${txtred}$PROCESS failed to
restart...${txtrst}"
exit 0
fi
fi
sleep $SLEEP_TIME # This is needed to reduce CPU Load!!!
done

 Process is hard coded in the script
 # Process to be monitored
target="ssh"

 wait_time="10“
 This is in seconds

 # Monitor process and restart if necessary
for attempt in 1 2 3
do
ps aux | grep "$target" | grep -v "grep $target"
| grep -v $script_name >/dev/null
if [ $? != 0 ]
then
log_time=$(date)
echo
echo "$(tput setaf 3)$target is not running. Attempt will be made to restart. This is attempt
$attempt of 3.$(tput sgr0)"
echo >>$log_file
echo "$log_time: $target is not running. Restarting. Attempt $attempt of 3.">>$log_file
echo
service $target start &
sleep 2 # Pause to prevent false positives from restart attempt.
else
attempt="3"
fi
done
sleep 2 # Pause to prevent false positives from restart attempt.
}

 detect_failure()
{
ps aux | grep "$target" | grep -v "grep $target"
| grep -v $script_name >/dev/null
if [ $? != 0 ]
then
log_time=$(date)
echo
echo "$(tput setaf 1)$target is not running after 3 attempts. Process has failed and
cannot be restarted. $(tput sgr0)" # Report failure to user
echo "This script will now close."
echo "">>$log_file
echo "$log_time: $target cannot be restarted.">>$log_file # Log failure
script_failure="1" # Set failure flag
else
log_time=$(date)
echo
echo "$log_time : $target is running."
echo "$log_time : $target is running." >> $log_file
fi
}

 program_closing()
{
# Report and log script shutdown
log_time=$(date)
echo
echo "Closing ProcMon script. No further monitoring of $target will be
performed." #Reports closing of ProcMon to user
echo
echo "$(tput setaf 1)$log_time: Monitoring for $target terminated. $(tput sgr0)"
echo
echo "$log_time: Monitoring for $target terminated.">>$log_file # Logs closing
of ProcMon to log_file
echo >> $log_file
echo "***************" >> $log_file
echo >> $log_file
# Ensure this script is properly killed
kill -9 > /dev/null
}

 # Trap shutdown attempts to enable logging of shutdown
trap 'program_closing; exit 0' 1 2 3 15
# Inform user of purpose of script
clear
echo
echo "This script will monitor $target to ensure that it is running,"
echo "and attempt to restart it if it is not. If it is unable to"
echo "restart after 3 attempts, it will report failure and close."
sleep 2
#Perform monitoring
while [ $script_failure != "1" ]
do
process_monitoring # Monitors process and attempts 3 restarts if it fails.
detect_failure # Reports failure in the event that the process does not restart.
if [ $script_failure != "1" ]
then
sleep $wait_time
fi
done
sleep 2
program_closing # Logs script closure
exit 0

Process monitoring in UNIX shell scripting

Process monitoring in UNIX shell scripting

Recommended

More Related Content

What's hot (20)

Viewers also liked (20)

Similar to Process monitoring in UNIX shell scripting (20)

More from Dan Morrill (16)

Recently uploaded (20)

Process monitoring in UNIX shell scripting