Differences

This shows you the differences between two versions of the page.

--- aix:scripts_category:nagios_aix_check [2021/01/18 13:51]
manu
+++ aix:scripts_category:nagios_aix_check [2025/02/24 15:34] (current)
manu [Check path disks]
@@ Line 1: / Line 1: @@
-**check_mailq_aix**
+===== Scripts for AIX monitoring with Nagios =====
+==== Monitor filesystems ====
+=== script 1 ===
+This script with an exception list will check the percent usage of each filesystem, and you can also use wildcards.
+<cli prompt='>'>
+root@aixserver - /opt/freeware/lib/nagios/plugins > cat MY_checkfs.cfg
+#fs_name:pct_warning:pct_critical
+# You can add exception in this file, else the default is used
+#Example:
+#/db*:98:100   , 98 and 100 whill be used for all filesystems /db*
+#default:90:95
+/tmp:80:95
+/usr:96:98
+/opt:95:98
+/cdrom:100:100
+/mnt:100:100
+</cli>
+<cli prompt='>'>
+root@aixserver - /opt/freeware/lib/nagios/plugins > cat MY_checkfs.sh
+</cli>
+<code>
+#!/usr/bin/ksh93
+#set -x
+##################################################
+#@(#) send an alert if filesystems usage is higher than threshold
+##################################################
+# associate file is checkfs.cfg (exceptions)
+# please do not modify this script use checkfs.cfg
+# checkfs.cfg format:
+# fs_name:pctwarning_threshold:pctcritical_threshold
+# version: 1.1 10-02-2014 Manu
+##################################################
+dir=`dirname $0`
+#. $dir/.env
+sn=`basename $0 | cut -d. -f1`
+configfile=/opt/freeware/lib/nagios/plugins/$sn.cfg
+logpath=/tmp
+logname=$logpath/$sn.log
+tmpcfg=$logpath/$sn.txt
+tmpscript=$logpath/$sn.scr
+nb_file=25
+nb_dir=15
+DATE=$(date +"%Y-%m-%d %H:%M")
+STATE_OK=0
+STATE_WARNING=1
+STATE_CRITICAL=2
+STATE_UNKNOWN=3
+STATE_DEPENDENT=4
+#echo "$sn: $DATE" > $logname
+#------------------------------------------------
+# generate_case_file ()
+#------------------------------------------------
+generate_case_file()
+{
+pctwarn_def=$(grep "^#default" $configfile | cut -d":" -f2)
+pctcrit_def=$(grep "^#default" $configfile | cut -d":" -f3)
+cat $configfile | grep -v "^ *#" | sed '/^$/d' > $tmpcfg
+cat $tmpcfg | awk -F':' '{print $1") pctwarn="$2" pctcrit="$3}' | sed '/^$/d;$G' | sed '$s/^/\*\)\ pctwarn=pctwarn_def\ pctcrit=pctcrit_def /' | sed "s/pctwarn_def/$pctwarn_def/" | sed "s/pctcrit_def/$pctcrit_def/" | sed '2,$s/^/\\n/' | sed 's/$/;;/' > $tmpcfg
+}
+#------------------------------------------------
+# check_fs ()
+#------------------------------------------------
+check_fs()
+{
+EXIT_CODE=0
+MSG_WARN=""
+MSG_CRIT=""
+OUTPUT="All filesystems OK"
+clauses=$(cat $tmpcfg)
+for i in $(df -k | egrep -v "Filesystem|:|/proc" | grep -v ":" | grep "/dev/" | awk '{print $4 $7}')
+do
+  fs=`echo $i | cut -f 2 -d%`
+  pct_fs=`echo $i | cut -f 1 -d%`
+  mail=""
+  cmd="case $fs in \n $clauses                      \n esac"
+  echo $cmd > $tmpscript
+  . $tmpscript > /dev/null
+  if [ $pct_fs -gt $pctwarn ]
+  then
+    if [ $pct_fs -gt $pctcrit ]
+    then
+      MSG_CRIT="$MSG_CRIT $fs used $pct_fs"
+      EXIT_CODE=$(echo $STATE_CRITICAL)
+    else
+      MSG_WARN="$MSG_WARN $fs used $pct_fs"
+      if [ $STATE_WARNING -gt $EXIT_CODE ]
+      then
+        EXIT_CODE=$(echo $STATE_WARNING)
+      fi
+    fi
+    #info_fs >> $logname 2>&1 &
+  fi
+done
+if [ "$MSG_CRIT" != "" ]
+then
+  OUTPUT="DISK CRITICAL - $MSG_CRIT"
+fi
+if [ "$MSG_WARN" != "" ]
+then
+  if [ "$MSG_CRIT" != "" ]
+  then
+    OUTPUT="$OUTPUT -- DISK WARNING - $MSG_WARN"
+  else
+    OUTPUT="DISK WARNING - $MSG_WARN"
+  fi
+fi
+rm $tmpcfg $tmpscript > /dev/null 2>&1
+}
+#------------------------------------------------
+# info_fs ()
+#------------------------------------------------
+info_fs()
+{
+echo "####### Here are the $nb_file biggest files from filesystem $fs"
+find $fs  -xdev -type f -ls | sort +6nr | head -$nb_file
+echo "\n####### Here are the $nb_dir biggest directories from filesystem $fs"
+du -ms $fs/* | sort -nr | head -$nb_dir
+}
+generate_case_file #>> $logname 2>&1
+check_fs #>> $logname 2>&1
+echo $OUTPUT
+exit $EXIT_CODE
+</code>
+=== script 2 ===
+<cli prompt='>'>
+root@aixserver - /opt/freeware/lib/nagios/plugins > cat check_fs.cfg
+#filesystem_name:alert_w(%):alert_c(%)
+/tmp:80:95
+/usr:96:98
+/cdrom:100:100
+/mnt:100:100
+/export/aix6100-09:99:100
+/export/aix7100-03:99:100
+/export/aix7200-02:99:100
+/export/mksysb:95:99
+/export/vios226:99:100
+/export/vios310:99:100
+/export/software:99:100
+</cli>
+<cli prompt='>'>
+root@aixserver - /opt/freeware/lib/nagios/plugins > cat check_fs.sh
+</cli>
+<code>
+#!/bin/sh
+#set -x
+##################################################
+#@(#) check filesystems usage is higher than threshold
+##################################################
+# associate file is check_fs.cfg (exceptions)
+# please do not modify this script use check_fs.cfg
+# check_fs.cfg format:
+# fs_name:pct_warn:pct_crit
+# check also GPFS quotas if used
+# version: 1.0 10-2020 Manu
+##################################################
+STATUS=0
+STATE_OK=0
+STATE_WARNING=1
+STATE_CRITICAL=2
+STATE_UNKNOWN=3
+MSG=""
+configfile=/usr/local/nagios/libexec/check_fs.cfg
+os=$(uname -a | awk '{print $1}')
+defaultwarn=92
+defaultcrit=98
+#------------------------------------------------
+# check_gpfs ()
+#------------------------------------------------
+check_gpfs()
+{
+# test gpfs quota if applicable
+lsfs -a | sed '1d' | awk '{print $4}' | grep "mmfs" > /dev/null 2>&1
+if [ $? -eq 0 ]
+then
+   quotaalert=2000000
+   for i in sybase kplus
+   do
+        used=$(mmlsquota -u $i |grep clkpfs|awk '{print $3}')
+        max=$(mmlsquota -u $i |grep clkpfs|awk '{print $4}')
+        diff=$(expr $max - $used)
+        if [ $diff -lt $quotaalert ]
+                then
+                echo "***** GPFS Quota-WARNING *****" >> $logname
+                echo " User $i has ounly $diff KB free quota " >> $logname
+                echo " Reduce used space or use mmedquota -u $i to modifie quota" >> $logname
+        fi
+   done
+fi
+}
+#------------------------------------------------
+# check_aix_fs ()
+#------------------------------------------------
+check_aix_fs()
+{
+df -k | egrep -v "Filesystem|:|/proc" | grep -v ":" | grep "/dev/" | awk '{print $4,$7}' | sed 's/\%//' | while read pct fs
+do
+  if [ -e $configfile ]
+  then
+    line=$(grep "^$fs:" $configfile)
+    if [ "$line" != "" ]
+    then
+      warn=$(echo $line |cut -d':' -f2)
+      crit=$(echo $line |cut -d':' -f3)
+    else
+      warn=$defaultwarn
+      crit=$defaultcrit
+    fi
+  else
+    warn=$defaultwarn
+    crit=$defaultcrit
+  fi
+  if [ "$pct" -gt "$crit" ]
+  then
+    MSG=$(echo "$MSG $fs:${pct}%")
+    STATE=${STATE_CRITICAL}
+  else
+    if [ "$pct" -gt "$warn" ]
+    then
+      MSG=$(echo "$MSG $fs:${pct}%")
+      STATE=${STATE_WARNING}
+    fi
+  fi
+  if [ "$STATUS" -lt "$STATE" ]
+  then
+    STATUS=$STATE
+  fi
+done
+}
+#------------------------------------------------
+# check_lnx_fs ()
+#------------------------------------------------
+check_lnx_fs()
+{
+df -k | egrep -v "Filesystem|:|/proc" | grep -v ":" | grep "/dev/" | rev | awk '{print $1,$2}' | rev | sed 's/\%//' | while read pct fs
+do
+  if [ -e $configfile ]
+  then
+    line=$(grep "^$fs:" $configfile)
+    if [ "$line" != "" ]
+    then
+      warn=$(echo $line |cut -d':' -f2)
+      crit=$(echo $line |cut -d':' -f3)
+    else
+      warn=$defaultwarn
+      crit=$defaultcrit
+    fi
+  else
+    warn=$defaultwarn
+    crit=$defaultcrit
+  fi
+  if [ "$pct" -gt "$crit" ]
+  then
+    MSG=$(echo "$MSG $fs:${pct}%")
+    STATE=${STATE_CRITICAL}
+  else
+    if [ "$pct" -gt "$warn" ]
+    then
+      MSG=$(echo "$MSG $fs:${pct}%")
+      STATE=${STATE_WARNING}
+    fi
+  fi
+  if [ "$STATUS" -lt "$STATE" ]
+  then
+    STATUS=$STATE
+  fi
+done
+}
+###########################################
+if [ "$os" = "Linux" ]
+then
+  check_lnx_fs
+else
+  if [ "$os" = "AIX" ]
+  then
+    check_aix_fs
+  else
+    echo "########## Unknown OS"
+        STATUS=$STATE_UNKNOWN
+  fi
+fi
+#check_gpfs
+case "$STATUS" in
+    "$STATE_OK")          MSG=$(echo "OK") ;;
+    "$STATE_WARNING")     MSG=$(echo "WARNING: $MSG") ;;
+    "$STATE_CRITICAL")    MSG=$(echo "CRITICAL: $MSG") ;;
+esac
+echo $MSG
+exit $STATUS
+</code>
+==== check_ntp_aix.sh (as nagios user) ====
+<code>
+#!/bin/ksh93
+#
+# AIX check NTP for Nagios v1.0 06/2023
+#  EIF
+#
+STATE_OK=0
+STATE_WARNING=1
+STATE_CRITICAL=2
+STATE_UNKNOWN=3
+STATE_DEPENDENT=4
+MAXSEC=30 # max delay allowed in seconds
+OUTPUT=$(ntpq -p 2>&1 | sed 's/$/;/g')
+if [ $(echo $OUTPUT | grep refused >/dev/null 2>&1; echo $?) -eq 0 ]
+then
+  EXIT_CODE=$STATE_CRITICAL
+  OUTPUT="Process: xntpd not running"
+else
+  if [[ $(echo $OUTPUT | tr ';' '\n' | sed '/^$/d' | sed 's/^\ //g' | tail +3) == "" ]]
+  then
+    EXIT_CODE=$STATE_CRITICAL
+    OUTPUT="Process: xntpd not running"
+  else
+    OFFSET=$(echo $OUTPUT | tr ';' '\n' | sed '/^$/d' | sed 's/^\ //g' | tail +3 | rev | awk '{print $2}' | rev | cut -d'.' -f1 | sed 's/+//' | sed 's/-//' | sort -u | tail -1)
+    if [ $(echo $OUTPUT | tr ';' '\n' | sed '/^$/d' | sed 's/^\ //g' | tail +3 | grep -q '^\*'; echo $?) -eq 0 ]
+    then
+      EXIT_CODE=$STATE_OK
+      OUTPUT="Process: xntpd offset ${OFFSET}s synchronized OK"
+    else
+      if [ $(echo $OFFSET) -lt "$MAXSEC" ]
+      then
+        EXIT_CODE=$STATE_OK
+        OUTPUT="Process: xntpd offset ${OFFSET}s synchronized OK"
+      else
+        EXIT_CODE=$STATE_WARNING
+        OUTPUT="Process: xntpd offset ${OFFSET}s Not synchronized"
+      fi
+    fi
+  fi
+fi
+echo $OUTPUT | tr ';' '\n' | sed '/^$/d' | sed 's/^\ //g' | tail +3 | rev | awk '{print $2}' | rev | cut -d'.' -f1 | sed 's/-//'
+echo $OUTPUT
+exit $EXIT_CODE
+</code>
+As root:
+<code>
+#!/bin/ksh93
+#
+# AIX check NTP for Nagios v1.0 06/2023
+#
+STATE_OK=0
+STATE_WARNING=1
+STATE_CRITICAL=2
+STATE_UNKNOWN=3
+STATE_DEPENDENT=4
+STATE=$(/usr/bin/lssrc -ls xntpd > /dev/null 2>&1; echo $?)
+if [ "$STATE" -ne 0 ]
+then
+  EXIT_CODE=$STATE_CRITICAL
+  OUTPUT="Process: xntpd not running"
+else
+  CODE=$(/usr/bin/lssrc -ls xntpd | tr -s ' ' |  tr ' ' ';' | grep -i 'Leap;indicator:' | cut -d':' -f2- | cut -d'(' -f1 | sed 's/;//g')
+  if [ "$CODE" == "00" ]
+  then
+    EXIT_CODE=$STATE_OK
+    OUTPUT="Process: xntpd synchronized OK"
+  else
+    EXIT_CODE=$STATE_CRITICAL
+    OUTPUT="Process: xntpd Not synchronized"
+  fi
+fi
+echo $OUTPUT
+exit $EXIT_CODE
+</code>
+==== check_mailq_aix ====
 <code>
 #!/usr/bin/ksh
@@ Line 69: / Line 479: @@
-**check_aix_cpu.sh**
+==== check_aix_cpu.sh ====
 <code>
@@ Line 148: / Line 558: @@
   exit $STATE_OK
 fi
+</code>
+==== Check path disks ====
+<cli prompt='#'>
+# cat check_paths.sh
+</cli>
+<code>
+#!/bin/sh
+#@(#) v1.0 Count number of paths per disk
+# v1.1 add sudo linux
+# v1.2 change for VSCSI
+# v1.3 add verbose (-v), improvements linux
+# On linux, add into /etc/sudoers the following lines for linux:
+#      nagios ALL=(ALL) NOPASSWD: /usr/sbin/multipath
+#      nrpe ALL=(ALL) NOPASSWD: /usr/sbin/multipath
+# number of path per type of disk
+pathviosfc=4
+pathviosscsi=2
+pathviossas=1
+pathlparfc=8
+pathlparscsi=2
+pathlparsas=1
+STATUS=0
+STATE_OK=0
+STATE_WARNING=1
+STATE_CRITICAL=2
+STATE_UNKNOWN=3
+MSG=""
+verbose=""
+# specified value for nb paths
+if [ "$npath" == "" ]
+then
+  nbpath=$pathlparfc
+fi
+os=$(uname -a | awk '{print $1}')
+grepp() { [ $# -eq 1 ] && perl -00ne "print if /$1/i" || perl -00ne "print if /$1/i" < "$2";}
+#---------------------
+count_linux_path()
+{
+tempfile=/tmp/multipath.txt
+if [ ! -x /usr/sbin/multipath ] || [ $(lsscsi -s | grep -q VMware; echo $?) -eq 0 ]
+then
+  MSG="OK: no multipathing"
+  verbose="$MSG"
+  STATUS=$STATE_OK
+else
+  if [ $(timeout 30  sudo /usr/sbin/multipath -ll | grep -v "policy=" | grep -v "size=" | tr -s ' ' | sed 's/\ /;/g' | sed '/^mpath/i \\n' > $tempfile ; echo $?) -ne "0" ]
+  then
+    MSG="$MSG Maybe error on sudo config"
+    verbose="$MSG"
+    STATUS=$STATE_UNKNOWN
+  else
+    for i in $(cat $tempfile | grep '^mpath' | awk -F';' '{print $1}')
+    do
+      pathok=$(cat $tempfile | grepp "^$i;" | grep -v "policy=" | grep -v "size=" | grep -v '^mpath' | grep active | wc -l | awk '{print $1}')
+      pathok_pct=$(echo "scale=1;100*$pathok/$nbpath" | bc | cut -d '.' -f1)
+      verbose="$verbose $i;$pathok/$nbpath" # verbose message
+      if [ "$pathok_pct" -lt "50" ]
+      then
+        MSG="$MSG $i;$pathok/$nbpath"
+        if [ $STATUS -lt $STATE_CRITICAL ]
+        then
+          STATUS=$STATE_CRITICAL
+        fi
+      else
+        if [ "$pathok_pct" -ne "100" ]
+        then
+          MSG="$MSG $i;$pathok/$nbpath"
+          if [ $STATUS -lt $STATE_CRITICAL ]
+          then
+            STATUS=$STATE_WARNING
+          fi
+        fi
+      fi
+    done
+  fi
+fi
+rm -f $tempfile 2>/dev/null
+}
+#---------------------
+count_aix_path()
+{
+# check not available disks
+nbdisknok=$(lsdev -Cc disk | grep -v Available | wc -l | awk '{print $1}')
+if [ "$nbdisknok" -ne "0" ]
+then
+  MSG="$MSG WARNING: $nbdisknok disks defined"
+  verbose="$MSG"
+  STATUS=$STATE_WARNING
+else
+  STATUS=$STATE_OK
+fi
+for line in $(lsdev -Cc disk | tr -s ' ' | sed 's/\ /:/' | sed 's/\ /:/' | sed 's/\ /,/g')
+do
+  hdisk=$(echo $line | awk -F':' '{print $1}')
+  if [ "$(echo $line | cut -d':' -f3- | tr 'A-Z' 'a-z' | grep -q mpio; echo $?)" -eq "0" ]
+  then
+    if [ ! -e /usr/ios/cli/ioscli ]
+        then
+          # type LPAR FC
+          nbpath=$pathlparfc
+    else
+          # type VIOS FC
+          nbpath=$pathviosfc
+    fi
+  else
+    if [ "$(echo $line | cut -d':' -f3- | tr 'A-Z' 'a-z' | grep -q scsi; echo $?)" -eq "0" ]
+    then
+      if [ ! -e /usr/ios/cli/ioscli ]
+          then
+            # type LPAR SCSI
+            nbpath=$pathlparscsi
+      else
+            # type VIOS SCSI
+            nbpath=$pathviosscsi
+      fi
+    else
+      if [ "$(echo $line | cut -d':' -f3- | tr 'A-Z' 'a-z' | grep -q sas; echo $?)" -eq "0" ]
+      then
+        if [ ! -e /usr/ios/cli/ioscli ]
+            then
+              # type LPAR SAS
+              nbpath=$pathlparsas
+        else
+              # type VIOS SAS
+              nbpath=$pathviossas
+        fi
+          fi
+        fi
+  fi
+  pathok=$(lspath -l $hdisk | grep Enabled | wc -l | awk '{print $1}')
+  pathok_pct=$(echo "scale=1;100*$pathok/$nbpath" | bc | cut -d '.' -f1)
+  verbose="$verbose $hdisk;$pathok/$nbpath"
+  if [ "$pathok_pct" -lt "50" ]
+  then
+    MSG="$MSG $hdisk;$pathok/$nbpath"
+    if [ $STATUS -lt $STATE_CRITICAL ]
+    then
+      STATUS=$STATE_CRITICAL
+    fi
+  else
+    if [ "$pathok_pct" -ne "100" ]
+    then
+      MSG="$MSG $hdisk;$pathok/$nbpath"
+      if [ $STATUS -lt $STATE_CRITICAL ]
+      then
+        STATUS=$STATE_WARNING
+      fi
+    fi
+  fi
+done
+}
+######################
+if [ "$os" = "Linux" ]
+then
+  count_linux_path
+else
+  if [ "$os" = "AIX" ]
+  then
+    count_aix_path
+  else
+    echo "########## Unknown OS"
+        STATUS=$STATE_UNKNOWN
+  fi
+fi
+if [ $STATUS -eq $STATE_OK ]
+then
+  echo "OK"
+else
+  echo "$MSG"
+fi
+# For debug
+if [ "$1" = "-v" ]
+then
+  echo "$verbose" | tr ' ' '\n'
+fi
+exit $STATUS
 </code>
+==== Check SEA status ====
+Check Shared Ethernet Adapter status on VIOS
+<cli prompt='#'>
+# cat check_sea.sh
+</cli>
+<code>
+#!/bin/ksh
+# v1.1 eif check LACP
+#
+# Add sudoers:
+#nagios ALL=(ALL) NOPASSWD: /usr/bin/entstat
+#nrpe ALL=(ALL) NOPASSWD: /usr/bin/entstat
+#valeurs retour Nagios
+STATE_OK=0
+STATE_WARNING=1
+STATE_CRITICAL=2
+STATE_UNKNOWN=3
+STATE_DEPENDENT=4
+EXITSTATUS=$STATE_UNKNOWN # Default Exit Code as UNKNOWN.
+#Recuperation variable
+hostname=$(hostname)
+SEA=$(lsdev -Cc adapter | grep Shared|grep -v Defined | wc -l | awk '{print $1}')
+#Initialisation
+if [ $SEA = "0" ]
+then
+  MSG="No SEA available on $hostname"
+  EXITSTATUS=2 #Exit status critical
+else
+  #Verification ensemble des cartes si disponible
+  for ent in $(lsdev -Cc adapter | grep Shared | awk '{print $1}')
+  do
+    # check physical ports / links
+    count_all=$(sudo /usr/bin/entstat -d $ent 2>&1 | grep -i status | grep "Physical Port Link Status" | wc -l | awk '{print $1}')
+    count_up=$(sudo /usr/bin/entstat -d $ent 2>&1 | grep -i status | grep "Physical Port Link Status" | grep Up |wc -l | awk '{print $1}')
+    if [ $count_up -ne $count_all ]
+    then
+      MSG="One or more Ethernet port down"
+      EXITSTATUS=1 #Exit status Warning
+    else
+      MSG="No ethernet port issue"
+      EXITSTATUS=0 #Exit status OK
+    fi
+    # check physical ports Speed, must be the same on all ports
+    nb_speed=$(sudo /usr/bin/entstat -d $ent 2>&1 | grep "Physical Port Speed" | sort -u | wc -l | awk '{print $1}')
+    if [ $nb_speed != "1" ]
+    then
+      MSG="Ethernet Ports bad speed"
+      EXITSTATUS=1 #Exit status Warning
+    fi
+    # check LACP
+    count_all=$(sudo /usr/bin/entstat -d $ent 2>&1 | grep "Synchronization" | wc -l | awk '{print $1}')
+    count_up=$(sudo /usr/bin/entstat -d $ent 2>&1 | grep "Synchronization" | grep 'IN_SYNC' | wc -l | awk '{print $1}')
+    echo "count_all=$count_all count_up=$count_up" >> /tmp/aaa
+    if [ $count_up -ne $count_all ]
+    then
+      MSG="LACP not synced"
+      EXITSTATUS=1 #Exit status Warning
+    fi
+  done
+fi
+echo $MSG
+exit $EXITSTATUS
+</code>

wiki

User Tools

Site Tools

Differences

Page Tools