continuent-monitors-nagios 0.0.3 → 0.5.0

data/bin/check_tungsten_backups

@@ -1,70 +0,0 @@
-#!/usr/bin/env ruby
-#
-# The script should be run as the tungsten user to ensure the
-# environment is set correctly.  Export the environment variables before
-# calling the script to modify behavior
-#
-
-require "#{File.dirname(__FILE__)}/../lib/ruby/tungsten"
-
-class CheckTungstenBackups
-  include TungstenScript
-  
-  def main
-    status = TI.status()
-    unless status.coordinator() == TI.hostname()
-      nagios_ok("Not running check because this node is not the coordinator")
-    end
-    seconds_since_epoch = TU.cmd_result("date +%s").to_i()
-    most_recent_backup = nil
-    
-    status.datasources().each{
-      |ds|
-      begin
-        TU.ssh_result("stat -c\"%n %Y\" #{TI.trepctl_property(status.name(), 'replicator.storage.agent.fs.directory')}/store*.properties 2>/dev/null", ds, TI.user()).split("\n").each{
-          |line|
-          stored_backup=line.split(" ")
-          stored_backup[1] = stored_backup[1].to_i()
-          
-          if most_recent_backup == nil || stored_backup[1] > most_recent_backup[:seconds]
-            most_recent_backup = {
-              :hostname => ds,
-              :filename => stored_backup[0],
-              :seconds => stored_backup[1]
-            }
-          end
-        }
-      rescue CommandError
-      end
-    }
-    
-    if most_recent_backup == nil
-      nagios_critical("Unable to find a backup on any datasource")
-    end
-    
-    age = seconds_since_epoch-most_recent_backup[:seconds]
-    if age > @options[:max_backup_age]
-      nagios_critical("#{most_recent_backup[:hostname]}:#{most_recent_backup[:filename]} [#{age}s] is older than #{@options[:max_backup_age]}s")
-    else
-      nagios_ok("The most recent backup is #{most_recent_backup[:hostname]}:#{most_recent_backup[:filename]} [#{age}s]")
-    end
-  end
-  
-  def configure
-    super()
-    
-    description("Check all local datasources to make sure one of them has a backup younger than the max allowed age")
-    add_option(:max_backup_age, {
-      :on => "--max-backup-age String",
-      :help => "Maximum allowed age in seconds of a backup on any machine",
-      :parse => method(:parse_integer_option),
-      :default => 86400
-    })
-  end
-  
-  def script_name
-    "check_tungsten_backups"
-  end
-  
-  self.new().run()
-end

data/bin/check_tungsten_latency

@@ -1,172 +0,0 @@
-#!/bin/bash
-#
-# Simple Bash Script To Check Tungsten Latency
-# Nagios Plugin For NRPE
-#
-# This script accepts two arguments, {{-w}} and {{-c}}.  The {{-w}} flag is 
-# the level at which a warning should be returned.  {{-c}} sets the level for 
-# a critical return value.  The script uses the maximum latency of any slave 
-# to determine the return value.
-#
-OK_STATE=0
-WARNING_STATE=1
-CRITICAL_STATE=2
-THOME=`dirname $0`
-
-function display_help()
-{
-  echo "Usage: ./check_tungsten_latency -w warning_level -c critical_level [-h]"
-  echo " -w                     Throw a warning alert if the maximum latency"
-  echo "                          is above this level"
-  echo " -c                     Throw a critical alert if the maximum latency"
-  echo "                          is above this level"
-  echo " --perfdata             Display performance data of the latency"
-  echo " --perslave-perfdata    Show performance latency values of each slave."
-  echo "                          If this is not set the maximum latency will be"
-  echo "                          displayed in the performace data"
-  echo " -h                     Display this message"
-  exit 0
-}
-
-# We will use this to make some floating point comparisons
-function float_cond()
-{
-    local cond=0
-    if [[ $# -gt 0 ]]; then
-        cond=$(echo "$*" | bc -q 2>&1)
-        if [[ $? -ne 0 ]]; then
-            echo "Error: $cond"
-            exit 1
-        fi
-        if [[ -z "$cond" ]]; then cond=0; fi
-        if [[ "$cond" != 0  &&  "$cond" != 1 ]]; then cond=0; fi
-    fi
-    local stat=$((cond == 0))
-    return $stat
-}
-
-warning_level=0
-critical_level=0
-perfdata="false"
-performance_data_default_glue=""
-performance_data_suffix=""
-perfdata_allslaves=""
-
-for arg
-do
-  delim=""
-  case "$arg" in
-  #translate --gnu-long-options to -g (short options)
-    --perfdata) args="${args}-p ";;
-    --perslave-perfdata) args="${args}-s ";;
-    #pass through anything else
-    *) [[ "${arg:0:1}" == "-" ]] || delim="\""
-      args="${args}${delim}${arg}${delim} ";;
-  esac
-done
- 
-#Reset the positional parameters to the short options
-eval set -- $args
-
-while getopts "w:c:h:nps" Option
-do
-  case $Option in
-    w	)
-  	warning_level=$OPTARG
-  	;;
-  	c )
-  	critical_level=$OPTARG
-    ;;
-    h )
-    display_help
-    ;;
-    p )
-    perfdata="true"
-    ;;
-    s   )
-    perfdata_allslaves="true"
-    ;;
-  esac
-done
-if float_cond "$warning_level == 0"; then
-  echo "Error: warning_level has not been set"
-  echo ""
-  display_help
-fi
-
-if float_cond "$critical_level == 0"; then
-  echo "Error: critical_level has not been set"
-  echo ""
-  display_help
-fi
-
-if [ "$perfdata" == "true" ]; then
-  performance_data_default_glue=" "
-  performance_data_suffix=";$warning_level;$critical_level;;"
-fi
-
-error_message=""
-error_messaage_glue=""
-performance_data_glue=""
-performance_data="| "
-max_latency=0
-
-manager_running=`${THOME}/../../tungsten-manager/bin/manager status | grep "PID" | wc -l`
-# Check the manager status
-if [ $manager_running -eq 0 ]; then
-  echo "CRITICAL: Manager is not running"
-  exit $CRITICAL_STATE
-fi
-
-latency_values=`echo "ls -l" | ${THOME}/../../tungsten-manager/bin/cctrl | grep -E "REPLICATOR\(role=[relay|slave]|appliedLatency" | tr -d "| "`
-
-current_slave=""
-for line in $latency_values
-do
-  if [[ $current_slave == "" ]]
-  then
-    current_slave=`echo $line | grep "REPLICATOR" | cut -f 1 -d ":"`
-  else
-    applied_latency=`echo $line | grep "appliedLatency" | cut -f 2 -d ":"`
-    
-    if float_cond "$applied_latency > $max_latency"; then
-      max_latency=$applied_latency
-    fi
-    
-    if float_cond "$applied_latency > $warning_level"; then
-      error_message="$error_message$error_message_glue$current_slave=$applied_latency""s"
-      error_message_glue=", "
-    fi
-    
-    if float_cond "$applied_latency == -1"; then
-      error_message="$error_message$error_message_glue$current_slave is missing latency information"
-      error_message_glue=", "
-    fi
-
-    performance_data="$performance_data$performance_data_glue$current_slave=$applied_latency$performance_data_suffix"
-    performance_data_glue="$performance_data_default_glue"
-    current_slave=""
-  fi
-done
-
-if [ "$perfdata_allslaves" != "true" ]; then
-	 performance_data="|  max_latency=${max_latency}$performance_data_suffix"
-fi
-
-if [ "$perfdata" == "false" ]; then
-  performance_data=""
-fi
-
-if float_cond "$max_latency > $critical_level"; then
-  echo "CRITICAL: $error_message $performance_data" 
-  exit $CRITICAL_STATE
-fi
-
-if [[ $error_message != "" ]]; then
-  echo "WARNING: $error_message  $performance_data" 
-  exit $WARNING_STATE
-fi
-
-  echo "OK: All slaves are running normally (max_latency=${max_latency}) $performance_data " 
-
-exit $OK_STATE

data/bin/check_tungsten_online

@@ -1,105 +0,0 @@
-#!/bin/bash
-# Copyright (C) 2014 Continuent, Inc.
-#
-# 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.
-#
-# Initial developer(s): Jeff Mace
-# Contributor(s):
-#
-# Simple Bash Script To Check Tungsten Services
-# Nagios Plugin For NRPE
-#
-# This script does not accept any arguments.  It will return a warning if any 
-# of Tungsten resources is not in an {{ONLINE}} state.  It uses the output of 
-# the {{ls resources}} command to determine the current state.
-#
-OK_STATE=0
-WARNING_STATE=1
-CRITICAL_STATE=2
-THOME=`dirname $0`
-
-error_message=""
-error_messaage_glue=""
-offline_count=0
-dataservice=""
-skip_shun=0
-
-function display_help()
-{
-  echo "Usage: ./check_tungsten_online -s dataservice [-h]"
-  echo " -s                     The data service you would like to check"
-  echo " -h                     Display this message"
-  echo " -n                     Skip Shunned Services"
-  exit 0
-}
-
-while getopts "s:h:n" Option
-do
-  case $Option in
-    h )
-    display_help
-    ;;
-    s   )
-    dataservice=$OPTARG
-    ;;
-    n   )
-    skip_shun=1
-    ;;
-  esac
-done
-
-manager_running=`${THOME}/../../tungsten-manager/bin/manager status | grep "PID" | wc -l`
-# Check the manager status
-if [ $manager_running -eq 0 ]; then
-  echo "CRITICAL: Manager is not running"
-  exit $CRITICAL_STATE
-fi
-
-if [ "$dataservice" == "" ]; then
-    offline_services=`echo "ls resources" | ${THOME}/../../tungsten-manager/bin/cctrl | grep \| | grep : | grep -v ONLINE | tr -d "| " | cut -f 1,2 -d ":"`
-else
-    offline_services=`echo "use $dataservice; ls" | ${THOME}/../../tungsten-manager/bin/cctrl -multi | grep "(\(composite \)\?master\|(\(composite \)\?slave\|(relay" | grep -v ONLINE | tr -d "|" | cut -f 1 -d "("`
-fi
-
-for offline_service in $offline_services
-do
-  offline_count=$(($offline_count+1))
-  error_message="$error_message$error_message_glue$offline_service"
-  error_message_glue=", "
-done
-
-if [ $offline_count -gt 0 ]
-then
-  echo "CRITICAL: $error_message are not ONLINE"
-  exit $CRITICAL_STATE
-fi
-
-
-if [ $skip_shun -eq 0 ]
-then
-    if [ "$dataservice" == "" ]; then
-        shunned=`echo "ls" | ${THOME}/../../tungsten-manager/bin/cctrl | grep 'SHUNNED' | wc -l`
-    else
-        shunned=`echo "use $dataservice; ls" | ${THOME}/../../tungsten-manager/bin/cctrl -multi  | grep 'SHUNNED' | wc -l`
-    fi
-
-    if [ $shunned -gt 0 ]
-    then
-      echo "CRITICAL: Dataservices are shunned"
-      exit $CRITICAL_STATE
-    fi
-fi
-
-
-echo "OK: All services are online"
-exit $OK_STATE

data/bin/check_tungsten_policy

@@ -1,61 +0,0 @@
-#!/bin/bash
-#
-# Simple Bash Script To Check Tungsten Policy
-# Nagios Plugin For NRPE
-#
-# This script does not accept any arguments.  It will return error if the
-# cluster is in maintenance mode
-#
-OK_STATE=0
-WARNING_STATE=1
-CRITICAL_STATE=2
-THOME=`dirname $0`
-
-error_message=""
-error_messaage_glue=""
-offline_count=0
-dataservice=""
-
-function display_help()
-{
-  echo "Usage: ./check_tungsten_policy -s dataservice [-h]"
-  echo " -s                     The data service you would like to check"
-  echo " -h                     Display this message"
-  exit 0
-}
-
-while getopts "s:h" Option
-do
-  case $Option in
-    h )
-    display_help
-    ;;
-    s   )
-    dataservice=$OPTARG
-    ;;
-  esac
-done
-
-manager_running=`${THOME}/../../tungsten-manager/bin/manager status | grep "PID" | wc -l`
-# Check the manager status
-if [ $manager_running -eq 0 ]; then
-  echo "CRITICAL: Manager is not running"
-  exit $CRITICAL_STATE
-fi
-
-if [ "$dataservice" == "" ]; then
-    maint_mode=`echo "ls " | ${THOME}/../../tungsten-manager/bin/cctrl | grep MAINTENANCE | wc -l`
-else
-    maint_mode=`echo "use $dataservice; ls " | ${THOME}/../../tungsten-manager/bin/cctrl | grep MAINTENANCE | wc -l`
-fi
-
-
-if [ $maint_mode -gt 0 ]
-then
-  echo "CRITICAL: Cluster is in Maintenance mode"
-  exit $CRITICAL_STATE
-fi
-
-
-echo "OK: Cluster is in Automatic Mode"
-exit $OK_STATE

data/bin/check_tungsten_progress

@@ -1,81 +0,0 @@
-#!/bin/bash
-#
-# Simple Bash Script To Check Tungsten Progress
-# Nagios Plugin For NRPE
-#
-# This script accepts three arguments, {{-w}}, {{-c}} and {{-t}}.  The {{-w}} flag 
-# is the level at which a warning should be returned.  {{-c}} sets the level for 
-# a critical return value.  The {{-t}} flag sets the amount of time used to wait 
-# between monitoring the progress of the cluster.  The script uses the difference 
-# between the values to determine if a warning or critical alert should be 
-# issued
-#
-OK_STATE=0
-WARNING_STATE=1
-CRITICAL_STATE=2
-THOME=`dirname $0`
-
-function display_help()
-{
-  echo "Usage: ./check_tungsten_progress -t time [-h]"
-  echo " -t     The number of seconds to wait when monitoring progress"
-  echo " -h     Display this message"
-  exit 0
-}
-
-# We will use this to make some floating point comparisons
-function float_cond()
-{
-    local cond=0
-    if [[ $# -gt 0 ]]; then
-        cond=$(echo "$*" | bc -q 2>&1)
-        if [[ $? -ne 0 ]]; then
-            echo "Error: $cond"
-            exit 1
-        fi
-        if [[ -z "$cond" ]]; then cond=0; fi
-        if [[ "$cond" != 0  &&  "$cond" != 1 ]]; then cond=0; fi
-    fi
-    local stat=$((cond == 0))
-    return $stat
-}
-
-time_period=1
-while getopts "t:h" Option
-do
-  case $Option in
-    t)
-    time_period=$OPTARG
-    ;;
-    h )
-    display_help
-    ;;
-  esac
-done
-
-if float_cond "$time_period == 0"; then
-  echo "Error: time_period has not been set"
-  echo ""
-  display_help
-fi
-
-is_online=`${THOME}/../../tungsten-replicator/bin/trepctl status | grep "state" | grep "ONLINE" | wc -l`
-if float_cond "$is_online == 0"; then
-  echo "CRITICAL: Replicator is not ONLINE"
-  exit $CRITICAL_STATE
-fi
-
-pre_progress_number=`${THOME}/../../tungsten-replicator/bin/trepctl status | grep "appliedLastSeqno" | tr -d "| " | awk -F":" '{print $2}'`
-echo "cluster heartbeat" | ${THOME}/../../tungsten-manager/bin/cctrl > /dev/null
-sleep $time_period
-post_progress_number=`${THOME}/../../tungsten-replicator/bin/trepctl status | grep "appliedLastSeqno" | tr -d "| " | awk -F":" '{print $2}'`
-
-progress_number=`echo "$post_progress_number - $pre_progress_number" | bc -q 2>/dev/null`
-
-if float_cond "$progress_number < 1"; then
-  echo "WARNING: Replicator did not show progress"
-  exit $WARNING_STATE
-fi
-
-echo "OK: Replicator is making progress"
-exit $OK_STATE