check_on_cluster

#! /usr/bin/env bash

###############################################################################
# Monitor DB2 with Nagios
# Copyright 2013,2014,2015 Andres Gomez Casanova
# https://github.com/angoca/monitor-db2-with-nagios
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
###############################################################################

# Wraps the execution of a check when using an active-passive cluster. When the
# execution is on the passive cluster, it returns OK. In order to identify the
# active or passive cluster it checks if a file system (directory) is present.
# The wrapped command is called normally, with all parameters.
#
# In order to be used in Nagios, you have to configure the following.
# (Example with check_instance_up)
#
# # 'check_instance_up' command definition
# define command {
#         command_name    check_connection_qty
#         command_line    $USER1$/check_by_ssh -H $HOSTADDRESS$ -l nagios -C "scripts/check_on_cluster -f /data/db2 scripts/check_instance_up -i /home/db2inst1"
# }
# define service{
#         host_name               db2server
#         service_description     Quantity of current connections
#         check_command           check_instance_up
#         use                     generic-service
# }
#
# When using NRPE (Example with check_instance_up):
#
# In the database server:
#
# command[check_instance_up]=/home/nagios/scripts/check_on_cluste -d /data/db2 check_instance_up -i /home/db2inst1
#
# Parameters:
# -d : Directory presented only in the active node.
# Followed by the set of parameters and the command to execute.
#
# The exit codes are the standard for Nagios.
#
# 0 The plugin was able to check the service and it appeared to be functioning
#   properly.
# 1 The plugin was able to check the service, but it appeared to be above some
#   "warning" threshold or did not appear to be working properly.
# 2 The plugin detected that either the service was not running or it was above
#   some "critical" threshold.
# 3 Invalid command line arguments were supplied to the plugin or low-level
#   failures internal to the plugin (such as unable to fork, or open a tcp
#   socket) that prevent it from performing the specified operation.
#   Higher-level errors (such as name resolution errors, socket timeouts, etc)
#   are outside of the control of plugins and should generally NOT be reported
#   as UNKNOWN states.
#
# Author: Andres Gomez Casanova
# Version: v1.0 2015-12-15

# Flag for debugging.
#set -xv

# Locale to print messages in English. Prevent language problems.
export LANG=en_US

# Version of this script.
function print_revision {
  echo Andres Gomez Casanova - AngocA
  echo v1.0 2015-12-15
}
# Function to show the help
function print_usage {
  /bin/cat <<__EOT
Usage: ${1} { -d directory commandWithParameters }
__EOT
}

function print_help {
  print_revision
  print_usage ${1}
  # Max 80 chars width.
  /bin/cat <<__EOT
-------------------------------------------------------------------------------
Wraps the execution of a command, useful when using an active-passive node.
-d
   Directory to check if the current node is the active (if present) or the
   passive (not present).

Followed by the command name and set of parameters to execute as the active
node.
__EOT
}

# Variable to control the flow execution. Prevent Spaghetti code.
CONTINUE=true

# Nagios return codes
OK=0
WARNING=1
CRITICAL=2
UNKNOWN=3
# This is the returned code.
RETURN=${UNKNOWN}

# Nagios output
OUTPUT=

APPL_NAME=$(basename ${0})

echo "$(date +"%Y-%m-%d-%H.%M.%S") $$ Started ${APPL_NAME} $@" >> /tmp/${APPL_NAME}.log

# Checks the lock file does not exist.
# The lock file is the way the command was called with its parameters
# without spaces.
COPY_ARGS=("${@}")
PARAMS=("${@}")
LOCK_FILE=
for VALUE in "${COPY_ARGS[@]}" ; do
  LOCK_FILE="${LOCK_FILE}${VALUE}"
done
LOCK_FILE=${LOCK_FILE//\//}
LOCK_FILE=${LOCK_FILE//\\/}
LOCK_FILE=${LOCK_FILE//\:/}
LOCK_FILE=${LOCK_FILE//\*/}
LOCK_FILE=${LOCK_FILE//\|/}
LOCK_FILE="/tmp/${APPL_NAME}${LOCK_FILE}.lock"
if [[ ! -r ${LOCK_FILE} ]] ; then
  echo $$ > ${LOCK_FILE}
  LOCKED=true
else
  # If it exist, then check if the process is running.
  EXIST=$(ps -ef | grep $(cat ${LOCK_FILE}) | grep ${APPL_NAME})
  # If process is not running, delete it.
  if [[ ${EXIST} == "" ]] ; then
    rm ${LOCK_FILE}
    if [[ ! -r ${LOCK_FILE} ]] ; then
      echo $$ > ${LOCK_FILE}
      LOCKED=true
    else
      OUTPUT="The lock file cannot be replaced: ${LOCK_FILE}"
      CONTINUE=false
      RETURN=${UNKNOWN}
    fi
  else
    OUTPUT="An instance of the script with the same parameters is already running."
    CONTINUE=false
    RETURN=${UNKNOWN}
  fi
fi

if [[ ${#} -eq 0 ]] ; then
  print_help ${APPL_NAME}
  RETURN=${UNKNOWN}
  CONTINUE=false
fi

#set -xv
if [[ "${1}" = "-d" ]] ; then
  DIRECTORY=$2
  COMMAND=${@:3}
else
  echo "The first parameter should be -d followed by the directory"
  print_usage ${APPL_NAME}
  RETURN=${UNKNOWN}
  CONTINUE=false
fi

if [[ ${CONTINUE} == true ]] ; then
  if [[ -d ${DIRECTORY} ]] ; then
    OUTPUT=$(${COMMAND})
    RETURN=${?}
  else
    RETURN=${OK}
    OUTPUT="Ok, el nodo es pasivo"
  fi
fi

# Prints the output.
if [[ ${OUTPUT} == "" ]] ; then
  OUTPUT="Note: The test was not executed."
fi
# Builds the output.
echo "${OUTPUT}"

if [[ ${LOCKED} == true && -r ${LOCK_FILE} ]] ; then
  rm ${LOCK_FILE}
fi

echo "$(date +"%Y-%m-%d-%H.%M.%S") $$ Ended ${APPL_NAME} ${COPY_ARGS[@]}" >> /tmp/${APPL_NAME}.log

exit ${RETURN}