script to check server process

#!/bin/bash
export PATH=$PATH:/grid/app/bin/

SUBJECT=”Server Process failed for – Server `hostname` on `date ‘+%m/%d/%y %X %A ‘`”
REPSUBJECT=”Server `hostname` health check report at `date +%H:%M` hours on `date +%d-%m-%Y`”
ERRLOG=$MONITOR_DIR/logs/server_process_check.log
REPORT=$MONITOR_DIR/logs/server_process_report.txt
BODY=$MONITOR_DIR/server_process_report_email_body.txt
## Delete the errorlog file if found
/usr/bin/find  $ERRLOG -type f -exec rm {} \; 2>&1 > /dev/null

##Report recipients
MAILID=’gangai.nathan@doyensys.com’
chour=`date +%H“date +%M`

if [ `grep -i “TEST01  HEALTH CHECK FOR” $REPORT | wc -l` -eq 0 ]; then
echo “—————————-TEST01 HEALTH CHECK FOR `date +%m_%d_%Y`———————————” > $REPORT
fi

echo ” ” >> $REPORT

echo “—————————-CRS process status `date +%m_%d_%Y_%H:%M`—————————-” >> $REPORT
crsctl check crs | while read outputline
do
if test `echo $outputline | grep ‘online’ | wc -l` -eq 0 ## This will check if the CRS process is online or not
then
echo “Date        : “`date ‘+%m/%d/%y %X %A ‘` >> $ERRLOG
echo “Details     :”`crsctl check  crs` >> $ERRLOG
echo ”  ” >> $ERRLOG
echo ” Details     :”`crsctl check  crs` >> $REPORT
echo ” ” >> $REPORT
echo ” Skiiping other tests ” >> $REPORT
echo ”  ” >> $ERRLOG
##mutt -s “$SUBJECT” $MAILTO < $ERRLOG
/bin/mail -s “$SUBJECT” “$MAILID”
exit
else
echo ” Details     :”`crsctl check  crs` >> $REPORT
echo ” ” >> $REPORT
fi
done

echo “—————————-PMON process Status count on `date +%m_%d_%Y_%H:%M`—————————-” >> $REPORT
if test `ps -ef|grep pmon|grep -v grep |wc -l` -ne 2 ## This will check the no of pmon process for each of the server
then
echo “Date        : “`date ‘+%m/%d/%y %X %A ‘` >> $ERRLOG
echo “Details     :”`ps -ef|grep pmon|grep -v ‘grep’ |wc -l` >> $ERRLOG
echo ” ” >> $ERRLOG
echo ” PMON process not found. Oracle Instance on `hostname` may be down . Require immediate attention” >> $ERRLOG
echo ” ” >> $REPORT
echo ” Skiiping other tests ” >> $REPORT
echo ”  ” >> $ERRLOG
/bin/mail -s “$SUBJECT” “$MAILID”
exit
else
echo ” Details     :”`crsctl check  crs` >> $REPORT
echo ” ” >> $REPORT
fi

echo “—————————-Listener Status on `date +%m_%d_%Y_%H:%M`—————————-” >> $REPORT

##Check whether listener is running. Output should be 1
if test `ps -ef|grep tnslsnr | grep -v “grep” |wc -l` -ne 1 ##Check the no of listener running.
then
echo “Date        : “`date ‘+%m/%d/%y %X %A ‘` >> $ERRLOG
echo “Details     :”`ps -ef|grep tnslsnr |grep -v ‘grep’ |wc -l` >> $ERRLOG
echo ” ” >> $ERRLOG
echo ” Listener on `hostname` may be down . Require immediate attention” >> $ERRLOG
echo ” ” >> $REPORT
echo ”  ” >> $ERRLOG
/bin/mail -s “$SUBJECT” “$MAILID”
else
echo ” Details     :”`crsctl check  crs` >> $REPORT
echo ” ” >> $REPORT
fi

echo “—————————-Checking number of oracle processes `date +%m_%d_%Y_%H:%M`—————————-” >> $REPORT

##Check Process count of “oracle” user. Output should be less than or equal to 1500
if test `ps -ef|grep -i oracle |wc -l` -ge 1000
then
echo “Date        : “`date ‘+%m/%d/%y %X %A ‘` >> $ERRLOG
echo “Details     : “`ps -ef|grep -i oracle|wc -l` >> $ERRLOG
echo ”  ”
echo ” Count of processes exceeded 1000. Require immediate attention” >>  $ERRLOG
echo ”  ” >> $ERRLOG
echo ”  ” >> $ERRLOG
/bin/mail -s “$SUBJECT” “$MAILID”
else
echo “Number of oracle processes: ” `ps -ef|grep -i oracle |wc -l` >> $REPORT
echo ” ” >> $REPORT
fi

##Send the report at particular times (e.g 1500 hours or 2300 hours)
if [ $chour -ge 1500 -a $chour -lt 1502 ]; then
mutt  -s “$REPSUBJECT” -a $REPORT $MAILID < $BODY
if [ $? -eq 0 ]; then
cp $REPORT $MONITOR_DIR/logs/server_process_report_`date +%d-%m-%Y`.txt
> $REPORT
fi
fi

if [ $chour -ge 2350 -a $chour -lt 2355 ]; then
mutt -s “$REPSUBJECT” -a $REPORT $MAILID < $BODY
if [ $? -eq 0 ]; then
cp $REPORT $MONITOR_DIR/logs/server_process_report_`date +%d-%m-%Y`.txt
> $REPORT
fi
fi

exit