插件地址:https://www.claudiokuenzler.com/monitoring-plugins/check_es_system.php
#!/bin/bash
################################################################################
# Script: check_es_system.sh #
# Author: Claudio Kuenzler www.claudiokuenzler.com #
# Purpose: Monitor ElasticSearch Store (Disk) Usage #
# Official doc: www.claudiokuenzler.com/monitoring-plugins/check_es_system.php #
# License: GPLv2 #
# GNU General Public Licence (GPL) http://www.gnu.org/ #
# This program is free software; you can redistribute it and/or #
# modify it under the terms of the GNU General Public License #
# as published by the Free Software Foundation; either version 2 #
# of the License, or (at your option) any later version. #
# #
# This program is distributed in the hope that it will be useful, #
# but WITHOUT ANY WARRANTY; without even the implied warranty of #
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the #
# GNU General Public License for more details. #
# #
# You should have received a copy of the GNU General Public License #
# along with this program; if not, see <https://www.gnu.org/licenses/>. #
# #
# Copyright 2016,2018-2020 Claudio Kuenzler #
# Copyright 2018 Tomas Barton #
# Copyright 2020 NotAProfessionalDeveloper #
# #
# History: #
# 20160429: Started programming plugin #
# 20160601: Continued programming. Working now as it should =) #
# 20160906: Added memory usage check, check types option (-t) #
# 20160906: Renamed plugin from check_es_store to check_es_system #
# 20160907: Change internal referenced variable name for available size #
# 20160907: Output now contains both used and available sizes #
# 20161017: Add missing -t in usage output #
# 20180105: Fix if statement for authentication (@deric) #
# 20180105: Fix authentication when wrong credentials were used #
# 20180313: Configure max_time for Elastic to respond (@deric) #
# 20190219: Fix alternative subject name in ssl (issue 4), direct to auth #
# 20190220: Added status check type #
# 20190403: Check for mandatory parameter checktype, adjust help #
# 20190403: Catch connection refused error #
# 20190426: Catch unauthorized (403) error #
# 20190626: Added readonly check type #
# 20190905: Catch empty cluster health status (issue #13) #
# 20190909: Added jthreads and tps (thread pool stats) check types #
# 20190909: Handle correct curl return codes #
# 20190924: Missing 'than' in tps output #
# 20191104: Added master check type #
# 20200401: Fix/handle 503 errors with curl exit code 0 (issue #20) #
# 20200409: Fix 503 error lookup (issue #22) #
# 20200430: Support both jshon and jq as json parsers (issue #18) #
# 20200609: Fix readonly check on ALL indices (issue #26) #
################################################################################
#Variables and defaults
STATE_OK=0 # define the exit code if status is OK
STATE_WARNING=1 # define the exit code if status is Warning
STATE_CRITICAL=2 # define the exit code if status is Critical
STATE_UNKNOWN=3 # define the exit code if status is Unknown
export PATH=$PATH:/usr/local/bin:/usr/bin:/bin # Set path
version=1.8.1
port=9200
httpscheme=http
unit=G
indexes='_all'
max_time=30
parsers=(jshon jq)
################################################################################
#Functions
help () {
echo -e "$0 $version (c) 2016-$(date +%Y) Claudio Kuenzler and contributors (open source rulez!)
Usage: ./check_es_system.sh -H ESNode [-P port] [-S] [-u user] [-p pass] -t checktype [-d int] [-o unit] [-w int] [-c int] [-m int] [-X parser]
Options:
* -H Hostname or ip address of ElasticSearch Node
-P Port (defaults to 9200)
-S Use https
-u Username if authentication is required
-p Password if authentication is required
* -t Type of check (disk, mem, status, readonly, jthreads, tps, master)
+ -d Available size of disk or memory (ex. 20)
-o Disk space unit (K|M|G) (defaults to G)
-i Space separated list of indexes to be checked for readonly (default: '_all')
-w Warning threshold (see usage notes below)
-c Critical threshold (see usage notes below)
-m Maximum time in seconds to wait for response (default: 30)
-e Expect master node (used with 'master' check)
-X The json parser to be used jshon or jq (default: jshon)
-h Help!
*mandatory options
+mandatory option for types disk,mem
Threshold format for 'disk' and 'mem': int (for percent), defaults to 80 (warn) and 95 (crit)
Threshold format for 'tps': int,int,int (active, queued, rejected), no defaults
Threshold format for all other check types': int, no defaults
Requirements: curl, expr and one of $(IFS=,; echo "${parsers[*]}")"
exit $STATE_UNKNOWN;
}
authlogic () {
if [[ -z $user ]] && [[ -z $pass ]]; then echo "ES SYSTEM UNKNOWN - Authentication required but missing username and password"; exit $STATE_UNKNOWN
elif [[ -n $user ]] && [[ -z $pass ]]; then echo "ES SYSTEM UNKNOWN - Authentication required but missing password"; exit $STATE_UNKNOWN
elif [[ -n $pass ]] && [[ -z $user ]]; then echo "ES SYSTEM UNKNOWN - Missing username"; exit $STATE_UNKNOWN
fi
}
unitcalc() {
# ES presents the currently used disk space in Bytes
if [[ -n $unit ]]; then
case $unit in
K) availsize=$(expr $available * 1024); outputsize=$(expr ${size} / 1024);;
M) availsize=$(expr $available * 1024 * 1024); outputsize=$(expr ${size} / 1024 / 1024);;
G) availsize=$(expr $available * 1024 * 1024 * 1024); outputsize=$(expr ${size} / 1024 / 1024 / 1024);;
esac
if [[ -n $warning ]] ; then
warningsize=$(expr $warning * ${availsize} / 100)
fi
if [[ -n $critical ]] ; then
criticalsize=$(expr $critical * ${availsize} / 100)
fi
usedpercent=$(expr $size * 100 / $availsize)
else echo "UNKNOWN - Shouldnt exit here. No units given"; exit $STATE_UNKNOWN
fi
}
availrequired() {
if [ -z ${available} ]; then echo "UNKNOWN - Missing parameter '-d'"; exit $STATE_UNKNOWN; fi
}
thresholdlogic () {
if [ -n $warning ] && [ -z $critical ]; then echo "UNKNOWN - Define both warning and critical thresholds"; exit $STATE_UNKNOWN; fi
if [ -n $critical ] && [ -z $warning ]; then echo "UNKNOWN - Define both warning and critical thresholds"; exit $STATE_UNKNOWN; fi
}
default_percentage_thresholds() {
if [ -z $warning ] || [ "${warning}" = "" ]; then warning=80; fi
if [ -z $critical ] || [ "${critical}" = "" ]; then critical=95; fi
}
json_parse() {
json_parse_usage() { echo "$0: [-r] [-q] [-c] [-a] -x arg1 -x arg2 ..." 1>&2; exit; }
local OPTIND opt r q c a x
while getopts ":rqcax:" opt
do
case "${opt}" in
r) raw=1;;
q) quiet=1;; # only required for jshon
c) continue=1;; # only required for jshon
a) across=1;;
x) args+=("$OPTARG");;
*) json_parse_usage;;
esac
done
case ${parser} in
jshon)
cmd=()
for arg in "${args[@]}"; do
cmd+=(-e $arg)
done
jshon ${quiet:+-Q} ${continue:+-C} ${across:+-a} "${cmd[@]}" ${raw:+-u}
;;
jq)
cmd=()
for arg in "${args[@]}"; do
cmd+=(.$arg)
done
jq ${raw:+-r} $(IFS=; echo ${across:+.[]}"${cmd[*]}")
;;
esac
}
################################################################################
# Check for people who need help - aren't we all nice ;-)
if [ "${1}" = "--help" -o "${#}" = "0" ]; then help; exit $STATE_UNKNOWN; fi
################################################################################
# Get user-given variables
while getopts "H:P:Su:p:d:o:i:w:c:t:m:e:X:" Input
do
case ${Input} in
H) host=${OPTARG};;
P) port=${OPTARG};;
S) httpscheme=https;;
u) user=${OPTARG};;
p) pass=${OPTARG};;
d) available=${OPTARG};;
o) unit=${OPTARG};;
i) indexes=${OPTARG};;
w) warning=${OPTARG};;
c) critical=${OPTARG};;
t) checktype=${OPTARG};;
m) max_time=${OPTARG};;
e) expect_master=${OPTARG};;
X) parser=${OPTARG:=jshon};;
*) help;;
esac
done
# Check for mandatory opts
if [ -z ${host} ]; then help; exit $STATE_UNKNOWN; fi
if [ -z ${checktype} ]; then help; exit $STATE_UNKNOWN; fi
################################################################################
# Check requirements
for cmd in curl expr ${parser}; do
if ! `which ${cmd} >/dev/null 2>&1`; then
echo "UNKNOWN: ${cmd} does not exist, please check if command exists and PATH is correct"
exit ${STATE_UNKNOWN}
fi
done
# Find parser
if [ -z ${parser} ]; then
for cmd in ${parsers[@]}; do
if `which ${cmd} >/dev/null 2>&1`; then
parser=${cmd}
break
fi
done
if [ -z "${parser}" ]; then
echo "UNKNOWN: No JSON parser found. Either one of the following is required: $(IFS=,; echo "${parsers[*]}")"
exit ${STATE_UNKNOWN}
fi
fi
################################################################################
# Retrieve information from Elasticsearch
getstatus() {
esurl="${httpscheme}://${host}:${port}/_cluster/stats"
eshealthurl="${httpscheme}://${host}:${port}/_cluster/health"
if [[ -z $user ]]; then
# Without authentication
esstatus=$(curl -k -s --max-time ${max_time} $esurl)
esstatusrc=$?
if [[ $esstatusrc -eq 7 ]]; then
echo "ES SYSTEM CRITICAL - Failed to connect to ${host} port ${port}: Connection refused"
exit $STATE_CRITICAL
elif [[ $esstatusrc -eq 28 ]]; then
echo "ES SYSTEM CRITICAL - server did not respond within ${max_time} seconds"
exit $STATE_CRITICAL
elif [[ $esstatus =~ "503 Service Unavailable" ]]; then
echo "ES SYSTEM CRITICAL - Elasticsearch not available: ${host}:${port} return error 503"
exit $STATE_CRITICAL
fi
# Additionally get cluster health infos
if [ $checktype = status ]; then
eshealth=$(curl -k -s --max-time ${max_time} $eshealthurl)
if [[ -z $eshealth ]]; then
echo "ES SYSTEM CRITICAL - unable to get cluster health information"
exit $STATE_CRITICAL
fi
fi
fi
if [[ -n $user ]] || [[ -n $(echo $esstatus | grep -i authentication) ]] ; then
# Authentication required
authlogic
esstatus=$(curl -k -s --max-time ${max_time} --basic -u ${user}:${pass} $esurl)
esstatusrc=$?
if [[ $esstatusrc -eq 7 ]]; then
echo "ES SYSTEM CRITICAL - Failed to connect to ${host} port ${port}: Connection refused"
exit $STATE_CRITICAL
elif [[ $esstatusrc -eq 28 ]]; then
echo "ES SYSTEM CRITICAL - server did not respond within ${max_time} seconds"
exit $STATE_CRITICAL
elif [[ $esstatus =~ "503 Service Unavailable" ]]; then
echo "ES SYSTEM CRITICAL - Elasticsearch not available: ${host}:${port} return error 503"
exit $STATE_CRITICAL
elif [[ -n $(echo $esstatus | grep -i "unable to authenticate") ]]; then
echo "ES SYSTEM CRITICAL - Unable to authenticate user $user for REST request"
exit $STATE_CRITICAL
elif [[ -n $(echo $esstatus | grep -i "unauthorized") ]]; then
echo "ES SYSTEM CRITICAL - User $user is unauthorized"
exit $STATE_CRITICAL
fi
# Additionally get cluster health infos
if [[ $checktype = status ]]; then
eshealth=$(curl -k -s --max-time ${max_time} --basic -u ${user}:${pass} $eshealthurl)
if [[ -z $eshealth ]]; then
echo "ES SYSTEM CRITICAL - unable to get cluster health information"
exit $STATE_CRITICAL
fi
fi
fi
# Catch empty reply from server (typically happens when ssl port used with http connection)
if [[ -z $esstatus ]] || [[ $esstatus = '' ]]; then
echo "ES SYSTEM UNKNOWN - Empty reply from server (verify ssl settings)"
exit $STATE_UNKNOWN
fi
}
################################################################################
# Do the checks
case $checktype in
disk) # Check disk usage
availrequired
default_percentage_thresholds
getstatus
size=$(echo $esstatus | json_parse -x indices -x store -x "size_in_bytes")
unitcalc
if [ -n "${warning}" ] || [ -n "${critical}" ]; then
# Handle tresholds
thresholdlogic
if [ $size -ge $criticalsize ]; then
echo "ES SYSTEM CRITICAL - Disk usage is at ${usedpercent}% ($outputsize $unit from $available $unit)|es_disk=${size}B;${warningsize};${criticalsize};;"
exit $STATE_CRITICAL
elif [ $size -ge $warningsize ]; then
echo "ES SYSTEM WARNING - Disk usage is at ${usedpercent}% ($outputsize $unit from $available $unit)|es_disk=${size}B;${warningsize};${criticalsize};;"
exit $STATE_WARNING
else
echo "ES SYSTEM OK - Disk usage is at ${usedpercent}% ($outputsize $unit from $available $unit)|es_disk=${size}B;${warningsize};${criticalsize};;"
exit $STATE_OK
fi
else
# No thresholds
echo "ES SYSTEM OK - Disk usage is at ${usedpercent}% ($outputsize $unit from $available $unit)|es_disk=${size}B;;;;"
exit $STATE_OK
fi
;;
mem) # Check memory usage
availrequired
default_percentage_thresholds
getstatus
size=$(echo $esstatus | json_parse -x nodes -x jvm -x mem -x "heap_used_in_bytes")
unitcalc
if [ -n "${warning}" ] || [ -n "${critical}" ]; then
# Handle tresholds
thresholdlogic
if [ $size -ge $criticalsize ]; then
echo "ES SYSTEM CRITICAL - Memory usage is at ${usedpercent}% ($outputsize $unit) from $available $unit|es_memory=${size}B;${warningsize};${criticalsize};;"
exit $STATE_CRITICAL
elif [ $size -ge $warningsize ]; then
echo "ES SYSTEM WARNING - Memory usage is at ${usedpercent}% ($outputsize $unit from $available $unit)|es_memory=${size}B;${warningsize};${criticalsize};;"
exit $STATE_WARNING
else
echo "ES SYSTEM OK - Memory usage is at ${usedpercent}% ($outputsize $unit from $available $unit)|es_memory=${size}B;${warningsize};${criticalsize};;"
exit $STATE_OK
fi
else
# No thresholds
echo "ES SYSTEM OK - Memory usage is at ${usedpercent}% ($outputsize $unit from $available $unit)|es_memory=${size}B;;;;"
exit $STATE_OK
fi
;;
status) # Check Elasticsearch status
getstatus
status=$(echo $esstatus | json_parse -r -x status)
shards=$(echo $esstatus | json_parse -r -x indices -x shards -x total)
docs=$(echo $esstatus | json_parse -r -x indices -x docs -x count)
nodest=$(echo $esstatus | json_parse -r -x nodes -x count -x total)
nodesd=$(echo $esstatus | json_parse -r -x nodes -x count -x data)
relocating=$(echo $eshealth | json_parse -r -x relocating_shards)
init=$(echo $eshealth | json_parse -r -x initializing_shards)
unass=$(echo $eshealth | json_parse -r -x unassigned_shards)
if [ "$status" = "green" ]; then
echo "ES SYSTEM OK - Elasticsearch Cluster is green (${nodest} nodes, ${nodesd} data nodes, ${shards} shards, ${docs} docs)|total_nodes=${nodest};;;; data_nodes=${nodesd};;;; total_shards=${shards};;;; relocating_shards=${relocating};;;; initializing_shards=${init};;;; unassigned_shards=${unass};;;; docs=${docs};;;;"
exit $STATE_OK
elif [ "$status" = "yellow" ]; then
echo "ES SYSTEM WARNING - Elasticsearch Cluster is yellow (${nodest} nodes, ${nodesd} data nodes, ${shards} shards, ${relocating} relocating shards, ${init} initializing shards, ${unass} unassigned shards, ${docs} docs)|total_nodes=${nodest};;;; data_nodes=${nodesd};;;; total_shards=${shards};;;; relocating_shards=${relocating};;;; initializing_shards=${init};;;; unassigned_shards=${unass};;;; docs=${docs};;;;"
exit $STATE_WARNING
elif [ "$status" = "red" ]; then
echo "ES SYSTEM CRITICAL - Elasticsearch Cluster is red (${nodest} nodes, ${nodesd} data nodes, ${shards} shards, ${relocating} relocating shards, ${init} initializing shards, ${unass} unassigned shards, ${docs} docs)|total_nodes=${nodest};;;; data_nodes=${nodesd};;;; total_shards=${shards};;;; relocating_shards=${relocating};;;; initializing_shards=${init};;;; unassigned_shards=${unass};;;; docs=${docs};;;;"
exit $STATE_CRITICAL
fi
;;
readonly) # Check Readonly status on given indexes
icount=0
for index in $indexes; do
if [[ -z $user ]]; then
# Without authentication
settings=$(curl -k -s --max-time ${max_time} ${httpscheme}://${host}:${port}/$index/_settings)
if [[ $? -eq 7 ]]; then
echo "ES SYSTEM CRITICAL - Failed to connect to ${host} port ${port}: Connection refused"
exit $STATE_CRITICAL
elif [[ $? -eq 28 ]]; then
echo "ES SYSTEM CRITICAL - server did not respond within ${max_time} seconds"
exit $STATE_CRITICAL
fi
rocount=$(echo $settings | json_parse -r -q -c -a -x settings -x index -x blocks -x read_only | grep -c true)
roadcount=$(echo $settings | json_parse -r -q -c -a -x settings -x index -x blocks -x read_only_allow_delete | grep -c true)
if [[ $rocount -gt 0 ]]; then
output[${icount}]=" $index is read-only -"
roerror=true
fi
if [[ $roadcount -gt 0 ]]; then
output[${icount}]+=" $index is read-only (allow delete) -"
roerror=true
fi
fi
if [[ -n $user ]] || [[ -n $(echo $esstatus | grep -i authentication) ]] ; then
# Authentication required
authlogic
settings=$(curl -k -s --max-time ${max_time} --basic -u ${user}:${pass} ${httpscheme}://${host}:${port}/$index/_settings)
settingsrc=$?
if [[ $settingsrc -eq 7 ]]; then
echo "ES SYSTEM CRITICAL - Failed to connect to ${host} port ${port}: Connection refused"
exit $STATE_CRITICAL
elif [[ $settingsrc -eq 28 ]]; then
echo "ES SYSTEM CRITICAL - server did not respond within ${max_time} seconds"
exit $STATE_CRITICAL
elif [[ -n $(echo $esstatus | grep -i "unable to authenticate") ]]; then
echo "ES SYSTEM CRITICAL - Unable to authenticate user $user for REST request"
exit $STATE_CRITICAL
elif [[ -n $(echo $esstatus | grep -i "unauthorized") ]]; then
echo "ES SYSTEM CRITICAL - User $user is unauthorized"
exit $STATE_CRITICAL
fi
rocount=$(echo $settings | json_parse -r -q -c -a -x settings -x index -x blocks -x read_only | grep -c true)
roadcount=$(echo $settings | json_parse -r -q -c -a -x settings -x index -x blocks -x read_only_allow_delete | grep -c true)
if [[ $rocount -gt 0 ]]; then
if [[ "$index" = "_all" ]]; then
output[${icount}]=" $rocount index(es) found read-only -"
else output[${icount}]=" $index is read-only -"
fi
roerror=true
fi
if [[ $roadcount -gt 0 ]]; then
if [[ "$index" = "_all" ]]; then
output[${icount}]+=" $rocount index(es) found read-only (allow delete) -"
else output[${icount}]+=" $index is read-only (allow delete) -"
fi
roerror=true
fi
fi
let icount++
done
if [[ $roerror ]]; then
echo "ES SYSTEM CRITICAL - ${output[*]}"
exit $STATE_CRITICAL
else
echo "ES SYSTEM OK - Elasticsearch Indexes ($indexes) are writeable"
exit $STATE_OK
fi
;;
jthreads) # Check JVM threads
getstatus
threads=$(echo $esstatus | json_parse -r -x nodes -x jvm -x "threads")
if [ -n "${warning}" ] || [ -n "${critical}" ]; then
# Handle tresholds
thresholdlogic
if [[ $threads -ge $criticalsize ]]; then
echo "ES SYSTEM CRITICAL - Number of JVM threads is ${threads}|es_jvm_threads=${threads};${warning};${critical};;"
exit $STATE_CRITICAL
elif [[ $threads -ge $warningsize ]]; then
echo "ES SYSTEM WARNING - Number of JVM threads is ${threads}|es_jvm_threads=${threads};${warning};${critical};;"
exit $STATE_WARNING
else
echo "ES SYSTEM OK - Number of JVM threads is ${threads}|es_jvm_threads=${threads};${warning};${critical};;"
exit $STATE_OK
fi
else
# No thresholds
echo "ES SYSTEM OK - Number of JVM threads is ${threads}|es_jvm_threads=${threads};${warning};${critical};;"
exit $STATE_OK
fi
;;
tps) # Check Thread Pool Statistics
if [[ -z $user ]]; then
# Without authentication
threadpools=$(curl -k -s --max-time ${max_time} ${httpscheme}://${host}:${port}/_cat/thread_pool)
threadpoolrc=$?
if [[ $threadpoolrc -eq 7 ]]; then
echo "ES SYSTEM CRITICAL - Failed to connect to ${host} port ${port}: Connection refused"
exit $STATE_CRITICAL
elif [[ $threadpoolrc -eq 28 ]]; then
echo "ES SYSTEM CRITICAL - server did not respond within ${max_time} seconds"
exit $STATE_CRITICAL
fi
fi
if [[ -n $user ]] || [[ -n $(echo $esstatus | grep -i authentication) ]] ; then
# Authentication required
authlogic
threadpools=$(curl -k -s --max-time ${max_time} --basic -u ${user}:${pass} ${httpscheme}://${host}:${port}/_cat/thread_pool)
threadpoolrc=$?
if [[ $threadpoolrc -eq 7 ]]; then
echo "ES SYSTEM CRITICAL - Failed to connect to ${host} port ${port}: Connection refused"
exit $STATE_CRITICAL
elif [[ $threadpoolrc -eq 28 ]]; then
echo "ES SYSTEM CRITICAL - server did not respond within ${max_time} seconds"
exit $STATE_CRITICAL
elif [[ -n $(echo $esstatus | grep -i "unable to authenticate") ]]; then
echo "ES SYSTEM CRITICAL - Unable to authenticate user $user for REST request"
exit $STATE_CRITICAL
elif [[ -n $(echo $esstatus | grep -i "unauthorized") ]]; then
echo "ES SYSTEM CRITICAL - User $user is unauthorized"
exit $STATE_CRITICAL
fi
fi
tpname=($(echo "$threadpools" | awk '{print $1"-"$2}' | sed "s/
//g"))
tpactive=($(echo "$threadpools" | awk '{print $3}' | sed "s/
//g"))
tpqueue=($(echo "$threadpools" | awk '{print $4}' | sed "s/
//g"))
tprejected=($(echo "$threadpools" | awk '{print $5}' | sed "s/
//g"))
if [ -n "${warning}" ] || [ -n "${critical}" ]; then
# Handle thresholds. They have to come in a special format: n,n,n (active, queue, rejected)
thresholdlogic
wactive=$(echo ${warning} | awk -F',' '{print $1}')
wqueue=$(echo ${warning} | awk -F',' '{print $2}')
wrejected=$(echo ${warning} | awk -F',' '{print $3}')
cactive=$(echo ${critical} | awk -F',' '{print $1}')
cqueue=$(echo ${critical} | awk -F',' '{print $2}')
crejected=$(echo ${critical} | awk -F',' '{print $3}')
i=0; for tp in ${tpname[*]}; do
perfdata[$i]="tp_${tp}_active=${tpactive[$i]};${wactive};${cactive};; tp_${tp}_queue=${tpqueue[$i]};${wqueue};${cqueue};; tp_${tp}_rejected=${tprejected[$i]};${wrejected};${crejected};; "
let i++
done
i=0
for tpa in $(echo ${tpactive[*]}); do
if [[ $tpa -ge $cactive ]]; then
echo "Thread Pool ${tpname[$i]} is critical: Active ($tpa) is equal or higher than threshold ($cactive)|${perfdata[*]}"
exit $STATE_CRITICAL
elif [[ $tpa -ge $wactive ]]; then
echo "Thread Pool ${tpname[$i]} is warning: Active ($tpa) is equal or higher than threshold ($wactive)|${perfdata[*]}"
exit $STATE_WARNING
fi
let i++
done
i=0
for tpq in $(echo ${tpqueue[*]}); do
if [[ $tpq -ge $cqueue ]]; then
echo "Thread Pool ${tpname[$i]} is critical: Queue ($tpq) is equal or higher than threshold ($cqueue)|${perfdata[*]}"
exit $STATE_CRITICAL
elif [[ $tpq -ge $wqueue ]]; then
echo "Thread Pool ${tpname[$i]} is warning: Queue ($tpq) is equal or higher than threshold ($wqueue)|${perfdata[*]}"
exit $STATE_WARNING
fi
let i++
done
i=0
for tpr in $(echo ${tprejected[*]}); do
if [[ $tpr -ge $crejected ]]; then
echo "Thread Pool ${tpname[$i]} is critical: Rejected ($tpr) is equal or higher than threshold ($crejected)|${perfdata[*]}"
exit $STATE_CRITICAL
elif [[ $tpr -ge $wrejected ]]; then
echo "Thread Pool ${tpname[$i]} is warning: Rejected ($tpr) is equal or higher than threshold ($wrejected)|${perfdata[*]}"
exit $STATE_WARNING
fi
let i++
done
echo "ES SYSTEM OK - Found ${#tpname[*]} thread pools in cluster|${perfdata[*]}"
exit $STATE_OK
fi
# No Thresholds
i=0; for tp in ${tpname[*]}; do
perfdata[$i]="tp_${tp}_active=${tpactive[$i]};;;; tp_${tp}_queue=${tpqueue[$i]};;;; tp_${tp}_rejected=${tprejected[$i]};;;; "
let i++
done
echo "ES SYSTEM OK - Found ${#tpname[*]} thread pools in cluster|${perfdata[*]}"
exit $STATE_OK
;;
master) # Check Cluster Master
if [[ -z $user ]]; then
# Without authentication
master=$(curl -k -s --max-time ${max_time} ${httpscheme}://${host}:${port}/_cat/master)
masterrc=$?
if [[ $masterrc -eq 7 ]]; then
echo "ES SYSTEM CRITICAL - Failed to connect to ${host} port ${port}: Connection refused"
exit $STATE_CRITICAL
elif [[ $masterrc -eq 28 ]]; then
echo "ES SYSTEM CRITICAL - server did not respond within ${max_time} seconds"
exit $STATE_CRITICAL
fi
fi
if [[ -n $user ]] || [[ -n $(echo $esstatus | grep -i authentication) ]] ; then
# Authentication required
authlogic
master=$(curl -k -s --max-time ${max_time} --basic -u ${user}:${pass} ${httpscheme}://${host}:${port}/_cat/master)
masterrc=$?
if [[ $threadpoolrc -eq 7 ]]; then
echo "ES SYSTEM CRITICAL - Failed to connect to ${host} port ${port}: Connection refused"
exit $STATE_CRITICAL
elif [[ $threadpoolrc -eq 28 ]]; then
echo "ES SYSTEM CRITICAL - server did not respond within ${max_time} seconds"
exit $STATE_CRITICAL
elif [[ -n $(echo $esstatus | grep -i "unable to authenticate") ]]; then
echo "ES SYSTEM CRITICAL - Unable to authenticate user $user for REST request"
exit $STATE_CRITICAL
elif [[ -n $(echo $esstatus | grep -i "unauthorized") ]]; then
echo "ES SYSTEM CRITICAL - User $user is unauthorized"
exit $STATE_CRITICAL
fi
fi
masternode=$(echo "$master" | awk '{print $NF}')
if [[ -n ${expect_master} ]]; then
if [[ "${expect_master}" = "${masternode}" ]]; then
echo "ES SYSTEM OK - Master node is $masternode"
exit $STATE_OK
else
echo "ES SYSTEM WARNING - Master node is $masternode but expected ${expect_master}"
exit $STATE_WARNING
fi
else
echo "ES SYSTEM OK - Master node is $masternode"
exit $STATE_OK
fi
;;
*) help
esac
要求
-
curl(SUSE:curl中的zypper,Debian / Ubuntu:apt-get install curl,CentOS / RHEL:yum install curl)
-
json解析器,其中之一:
-
- jshon(SUSE:搜索jshon,Debian / Ubuntu:apt-get install jshon)
-
- jq命令(SUSE:jq中的zypper,Debian / Ubuntu:apt-get install jq)
-
Bash内部命令/功能(插件检查其存在性)
参数定义
参数 | 描述 |
---|---|
-H* | ElasticSearch节点的主机名或IP地址 |
-P | 端口(默认为9200) |
-S | 使用安全的HTTP(https) |
-u | 用户名(如果需要身份验证) |
-p | 密码(如果需要验证) |
-t * | 要运行的检查类型(磁盘|内存|状态) |
-d + | 可用磁盘或内存大小(例如20) |
-o | 大小单位(K | M | G)(默认为G) |
-一世 | 要检查的只读索引的空格分隔列表(默认值:“ _ all”) |
-w | 警告阈 值“磁盘”和“内存”的阈值格式:整数(以百分比表示),默认为80(警告)和95(暴击)。 阈值格式为“ tps”:整数,整数,整数(活动,排队,已拒绝),没有默认 值所有其他检查类型的阈值格式:int,没有默认值 |
-C | “磁盘”和“内存”的临界阈值格式:int(百分比),默认为80(警告)和95(临界) tps的阈值格式:int,int,int(活动,已排队,已拒绝),没有默认 值所有其他检查类型的阈值格式:int,没有默认值 |
-米 | 等待Elasticsearch服务器响应的最长时间(以秒为单位)(默认值:30) |
-e | 给定的节点应该是Elasticsearch集群的主节点(仅影响“主”检查) |
-X | 要使用的json解析器,可以是jshon或jq(默认值:jshon) |
-H | 帮帮我! |
*必填参数
+对于磁盘和内存检查类型是必需的
检查类型的定义
类型 | 描述 |
---|---|
状态 | 检查集群的当前状态(绿色,黄色,红色)。除此之外,还显示其他信息(节点,分片,文档)。当状态为黄色或红色时,将显示相关的分片信息(例如,初始化或未分配)。 |
记忆 | 检查当前内存使用情况,并将其与-d参数定义的可用内存进行比较。阈值可能。 |
磁碟 | 检查当前磁盘使用情况,并将其与使用-d参数定义的可用磁盘容量进行比较。阈值可能。 |
只读 | 检查所有-i参数列出的(默认值:_all)或索引是否为只读标志。 |
线程 | 监视跨ES集群的Java线程数。阈值可能。 |
点 | 监视跨ES群集的线程池统计信息。对于每个线程池,都会检查“活动”,“排队”和“拒绝”队列。某些队列的数量不断增加,这可能表明您的Elasticsearch集群出现问题。阈值可能。 |
主 | 监视ES群集的当前主节点。参数-e可用于检查某个节点是否为主节点,如果不是这种情况,则发出警报。 |
用法/在命令行上运行插件
用法:
./check_es_system.sh -H主机名[-P端口] [-S] [-u用户] [-p密码] -t checktype [-d容量] [-o单位] [-i索引] [- w警告] [-c严重] [-m时间]
示例1:经典状态检查。此处,Elasticsearch群集在escluster.example.com上运行,并使用HTTPS(使用-S启用https)在端口9243上使用基本身份验证凭据用户和密码进行访问。输出显示集群状态(绿色)和一些其他信息。
作为性能数据,使用了节点号,分片信息和文档总数。
注意:当状态变为黄色(=警告)或红色(=严重)时,输出还将包含重定位,初始化和未分配的分片的信息。性能数据保持不变,不会混淆图形数据库。
./check_es_system.sh -H escluster.example.com -P 9243 -S -u用户-p password -t状态
ES系统正常-Elasticsearch集群为绿色(3个节点,2个数据节点,114个分片,8426885个文档)| total_nodes = 3 ;;;; data_nodes = 2 ;;; total_shards = 114 ;;; relocating_shards = 0 ;;;; initializing_shards = 0 ;;;; unassigned_shards = 0 ;;;; docs = 8426885 ;;;
示例2:磁盘使用情况检查。访问与之前相同的Elasticsearch集群。由于此ES在云中运行,因此我们没有主机监控可用(意味着:我们无法进行文件系统监控)。但是我们知道,我们有128GB的可用磁盘空间。我们告诉插件,我们的容量为128GB(-d 128)。让插件完成其余工作:
./check_es_system.sh -H escluster.example.com -P 9243 -S -u用户-p密码-t磁盘-d 128
ES系统正常-磁盘使用率为14%(128 G中为18 G)| es_disk = 19637018938B ; 109951162777; 130567005798 ;;
示例3:内存使用情况检查。与以前一样,ES在云中运行,我们无法在主机本身上进行内存监视。但是我们已经预订了24GB RAM /内存的Elasticsearch服务。
./check_es_system.sh -H escluster.example.com -P 9243 -S -u用户-p密码-t mem -d 24
ES系统正常-内存使用率为58%(24 G中为14 G)| es_memory = 15107616304B ; 20615843020; 24481313587 ;;
示例4:只读索引检查。插件使用-i参数检查提到的索引是否为只读标志。如果未使用-i参数,则将检查所有索引。
./check_es_system.sh -H escluster.example.com -P 9243 -S -u用户-p密码-t只读-i“ filebeat- * logstash- *”严重-Elasticsearch
Index filebeat- *是只读的(找到53索引设置为只读)Elasticsearch索引logstash- *为只读(找到的125个索引设置为只读)
示例5:JVM线程检查。该插件检查整个集群中的JVM线程数。该插件应在200个或更多线程正在运行时发出警告,在300个或更多线程处于运行状态时会发出警告。
./check_es_system.sh -H escluster.example.com -P 9243 -S -u用户-p密码-t jthreads -w 200 -c 300
ES系统关键-JVM线程数为319 | es_jvm_threads = 319; 200; 300 ;;
示例6:TPS(线程池统计信息)。该插件将遍历所有检测到的集群线程池。没有阈值,该插件仅输出检测到的线程池的数量并添加性能数据。使用阈值(请注意特殊格式!),插件将警告线程池之一是否等于或大于阈值。
./check_es_system.sh -H escluster.example.com -P 9243 -S -u用户-p密码-t tps -w 200 -c 300
ES系统正常-在cluster | tp_es02-analyze_active = 0; 10; 50 ;;中找到46个线程池 tp_es02-analyze_queue = 0; 50; 200 ;; tp_es02-analyze_rejected = 0; 1000; 2000 ;; tp_es02-ccr_active = 0; 10; 50 ;; tp_es02-ccr_queue = 0; 50; 200 ;; tp_es02-ccr_rejected = 0; 1000; 2000 ;; tp_es02-fetch_shard_started_active = 0; 10; 50 ;; tp_es02-fetch_shard_started_queue = 0; 50; 200 ;; tp_es02-fetch_shard_started_rejected = 0; 1000; 2000 ;; tp_es02-fetch_shard_store_active = 0; 10; 50 ;; tp_es02-fetch_shard_store_queue = 0; 50; 200 ;; tp_es02-fetch_shard_store_rejected = 0; 1000; 2000 ;; tp_es02-flush_active = 0; 10; 50 ;; tp_es02-flush_queue = 0; 50; 200 ;; tp_es02-flush_rejected = 0; 1000; 2000 ;; tp_es02-force_merge_active = 0; 10; 50 ;; tp_es02-force_merge_queue = 0; 50; 200 ;; tp_es02-force_merge_rejected = 0; 1000; 2000 ;; tp_es02-generic_active = 0; 10; 50 ;; tp_es02-generic_queue = 0; 50; 200 ;; tp_es02-generic_rejected = 0; 1000; 2000 ;; tp_es02-get_active = 0; 10; 50 ;; tp_es02-get_queue = 0; 50; 200 ;; tp_es02-get_rejected = 0; 1000; 2000 ;; tp_es02-index_active = 0; 10; 50 ;; tp_es02-index_queue = 0; 50; 200 ;; tp_es02-index_rejected = 0; 1000; 2000 ;; tp_es02-listener_active = 0; 10; 50 ;; tp_es02-listener_queue = 0; 50; 200 ;; tp_es02-listener_rejected = 0; 1000; 2000 ;; tp_es02-management_active = 1; 10; 50 ;; tp_es02-management_queue = 0; 50; 200 ;; tp_es02-management_rejected = 0; 1000; 2000 ;; tp_es02-ml_autodetect_active = 0; 10; 50 ;; tp_es02-ml_autodetect_queue = 0; 50; 200 ;; tp_es02-ml_autodetect_rejected = 0; 1000; 2000 ;; tp_es02-ml_datafeed_active = 0; 10; 50 ;; tp_es02-ml_datafeed_queue = 0; 50; 200 ;; tp_es02-ml_datafeed_rejected = 0; 1000; 2000 ;; tp_es02-ml_utility_active = 0; 10; 50 ;; tp_es02-ml_utility_queue = 0; 50; 200 ;; tp_es02-ml_utility_rejected = 0; 1000; 2000 ;; tp_es02-refresh_active = 1; 10; 50 ;; tp_es02-refresh_queue = 0; 50; 200 ;; tp_es02-refresh_rejected = 0; 1000; 2000 ;; tp_es02-rollup_indexing_active = 0; 10; 50 ;; tp_es02-rollup_indexing_queue = 0; 50; 200 ;; tp_es02-rollup_indexing_rejected = 0; 1000; 2000 ;; tp_es02-search_active = 0; 10; 50 ;; tp_es02-search_queue = 0; 50; 200 ;; tp_es02-search_rejected = 0; 1000; 2000 ;; tp_es02-search_throttled_active = 0; 10; 50 ;; tp_es02-search_throttled_queue = 0; 50; 200 ;; tp_es02-search_throttled_rejected = 0; 1000; 2000 ;; tp_es02-security-token-key_active = 0; 10; 50 ;; tp_es02-security-token-key_queue = 0; 50; 200 ;; tp_es02-security-token-key_rejected = 0; 1000; 2000 ;; tp_es02-snapshot_active = 0; 10; 50 ;; tp_es02-snapshot_queue = 0; 50; 200 ;; tp_es02-snapshot_rejected = 0; 1000; 2000 ;; tp_es02-warmer_active = 0; 10; 50 ;; tp_es02-warmer_queue = 0; 50; 200 ;; tp_es02-warmer_rejected = 0; 1000; 2000 ;; tp_es02-watcher_active = 0; 10; 50 ;; tp_es02-watcher_queue = 0; 50; 200 ;; tp_es02-watcher_rejected = 0; 1000; 2000 ;; tp_es02-write_active = 8; 10; 50 ;; tp_es02-write_queue = 10; 50; 200 ;; tp_es02-write_rejected = 0; 1000; 2000 ;; tp_es01-analyze_active = 0; 10; 50 ;; tp_es01-analyze_queue = 0; 50; 200 ;; tp_es01-analyze_rejected = 0; 1000; 2000 ;; tp_es01-ccr_active = 0; 10; 50 ;; tp_es01-ccr_queue = 0; 50; 200 ;; tp_es01-ccr_rejected = 0; 1000; 2000 ;; tp_es01-fetch_shard_started_active = 0; 10; 50 ;; tp_es01-fetch_shard_started_queue = 0; 50; 200 ;; tp_es01-fetch_shard_started_rejected = 0; 1000; 2000 ;; tp_es01-fetch_shard_store_active = 0; 10; 50 ;; tp_es01-fetch_shard_store_queue = 0; 50; 200 ;; tp_es01-fetch_shard_store_rejected = 0; 1000; 2000 ;; tp_es01-flush_active = 0; 10; 50 ;; tp_es01-flush_queue = 0; 50; 200 ;; tp_es01-flush_rejected = 0; 1000; 2000 ;; tp_es01-force_merge_active = 0; 10; 50 ;; tp_es01-force_merge_queue = 0; 50; 200 ;; tp_es01-force_merge_rejected = 0; 1000; 2000 ;; tp_es01-generic_active = 0; 10; 50 ;; tp_es01-generic_queue = 0; 50; 200 ;; tp_es01-generic_rejected = 0; 1000; 2000 ;; tp_es01-get_active = 0; 10; 50 ;; tp_es01-get_queue = 0; 50; 200 ;; tp_es01-get_rejected = 0; 1000; 2000 ;; tp_es01-index_active = 0; 10; 50 ;; tp_es01-index_queue = 0; 50; 200 ;; tp_es01-index_rejected = 0; 1000; 2000 ;; tp_es01-listener_active = 0; 10; 50 ;; tp_es01-listener_queue = 0; 50; 200 ;; tp_es01-listener_rejected = 0; 1000; 2000 ;; tp_es01-management_active = 1; 10; 50 ;; tp_es01-management_queue = 0; 50; 200 ;; tp_es01-management_rejected = 0; 1000; 2000 ;; tp_es01-ml_autodetect_active = 0; 10; 50 ;; tp_es01-ml_autodetect_queue = 0; 50; 200 ;; tp_es01-ml_autodetect_rejected = 0; 1000; 2000 ;; tp_es01-ml_datafeed_active = 0; 10; 50 ;; tp_es01-ml_datafeed_queue = 0; 50; 200 ;; tp_es01-ml_datafeed_rejected = 0; 1000; 2000 ;; tp_es01-ml_utility_active = 0; 10; 50 ;; tp_es01-ml_utility_queue = 0; 50; 200 ;; tp_es01-ml_utility_rejected = 0; 1000; 2000 ;; tp_es01-refresh_active = 0; 10; 50 ;; tp_es01-refresh_queue = 0; 50; 200 ;; tp_es01-refresh_rejected = 0; 1000; 2000 ;; tp_es01-rollup_indexing_active = 0; 10; 50 ;; tp_es01-rollup_indexing_queue = 0; 50; 200 ;; tp_es01-rollup_indexing_rejected = 0; 1000; 2000 ;; tp_es01-search_active = 0; 10; 50 ;; tp_es01-search_queue = 0; 50; 200 ;; tp_es01-search_rejected = 78; 1000; 2000 ;; tp_es01-search_throttled_active = 0; 10; 50 ;; tp_es01-search_throttled_queue = 0; 50; 200 ;; tp_es01-search_throttled_rejected = 0; 1000; 2000 ;; tp_es01-security-token-key_active = 0; 10; 50 ;; tp_es01-security-token-key_queue = 0; 50; 200 ;; tp_es01-security-token-key_rejected = 0; 1000; 2000 ;; tp_es01-snapshot_active = 0; 10; 50 ;; tp_es01-snapshot_queue = 0; 50; 200 ;; tp_es01-snapshot_rejected = 0; 1000; 2000 ;; tp_es01-warmer_active = 0; 10; 50 ;; tp_es01-warmer_queue = 0; 50; 200 ;; tp_es01-warmer_rejected = 0; 1000; 2000 ;; tp_es01-watcher_active = 0; 10; 50 ;; tp_es01-watcher_queue = 0; 50; 200 ;; tp_es01-watcher_rejected = 0; 1000; 2000 ;; tp_es01-write_active = 8; 10; 50 ;; tp_es01-write_queue = 20; 50; 200 ;; tp_es01-write_rejected = 0; 1000; 2000 ;;
示例7:主检查。插件检查给定Elasticsearch集群的哪个节点是当前主节点。使用可选参数-e(期望主服务器),可以指定节点名称。如果给定的节点名称和群集的当前主节点不同,则插件将发出警告。
./check_es_system.sh -H escluster.example.com -P 9243 -S -u用户-p密码-t master -e node1
ES系统警告-主节点为node2但预期为node1
命令定义
Nagios,Icinga 1.x,Shinken,Naemon中的命令定义
以下命令定义允许在ARG4中全部定义可选参数。
#'check_es_system'命令定义
定义命令{
command_name check_es_system
command_line $ USER1 $ / check_es_system.sh -H $ ARG1 $ -t $ ARG3 $ $ ARG4 $
}
Icinga 2.x中的命令定义
对象CheckCommand“ check_es_system” {
导入“ plugin-check-command”
命令= [PluginContribDir +“ /check_es_system.sh”]
参数= {
“ -H” = {
值=“ $ es_address $”
描述=“主机名或IP地址ElasticSearch节点“
}
” -P“ = {
值=” $ es_port $“
描述=”端口号(默认值:9200)“
}
” -S“ = {
set_if =” $ es_ssl $“
description =”使用https“
}
” -u“= {
值=“ $ es_user $”
描述=“如果需要验证,则为用户名”
}
“ -p” = {
value =“ $ es_password $”
description =“如果需要身份验证,则需要输入密码”
}
“ -d” = {
value =“ $ es_available $”
description =“定义ES的可用磁盘或内存大小cluster“
}
” -t“ = {
value =” $ es_checktype $“
description =”定义检查类型(磁盘|内存|状态)“
}
” -o“ = {
value =” $ es_unit $“
description =”选择大小单位(K | M | G)-千兆字节默认为G“
}
“ -i” = {
value =“ $ es_index $”
description =“要检查的只读索引的空格分隔列表(默认:'_all')”
}
“ -w” = {
value =“ $ es_warn $”
description =“警告阈值”
}
“ -c“ = {
值=” $ es_crit $“
描述=”关键阈值“
}
” -m“ = {
值=” $ es_max_time $“
描述=”以秒为单位的最大时间(超时),Elasticsearch响应(默认值:30 )“
}
” -e“= {
value =“ $ es_expect_master $”
description =“给定的节点名称应该是Elasticsearch集群的主节点。”
}
}
vars.es_address =“ $ address $”
vars.es_ssl = false
}
服务定义
Nagios,Icinga 1.x,Shinken,Naemon中的服务定义
在此示例中,磁盘检查在myexcluster.in.the.cloud上进行,并假定有50GB的可用磁盘空间。访问集群统计信息需要身份验证,因此此处的登录使用用户“ read”和密码“ only”进行。
#检查ElasticSearch磁盘使用情况
定义服务{
使用通用服务
host_name myesnode
service_description ElasticSearch磁盘使用情况
check_command check_es_system!myescluster.in.the.cloud!disk!-d 50 -u只读-p
}
在下一个示例中,在myexcluster.in.the.cloud中检查Elasticsearch集群的状态:
#检查ElasticSearch状态
定义服务{
使用通用服务
host_name myesnode
service_description ElasticSearch状态
check_command check_es_system!myescluster.in.the.cloud!status
}
服务对象定义Icinga 2.x
在此示例中,磁盘检查在myexcluster.in.the.cloud上进行,并假定有50GB的可用磁盘空间。访问集群统计信息需要身份验证,因此此处的登录使用用户“ read”和密码“ only”进行。
#检查Elasticsearch磁盘使用情况
对象服务“ ElasticSearch磁盘使用情况” {
import“ generic-service”
host_name =“ myesnode”
check_command =“ check_es_system”
vars.es_address =“ myescluster.in.the.cloud”
vars.es_user =“读取”
vars .es_password =“仅”
vars.es_checktype =“磁盘”
vars.es_available =“ 50”
}
在此示例中,将检查在myexcluster.in.the.cloud上运行的Elasticsearch的状态。访问集群统计信息需要身份验证,因此此处的登录使用用户“ read”和密码“ only”进行。
#检查Elasticsearch Status
对象服务“ ElasticSearch Status” {
import“通用服务”
host_name =“ myesnode”
check_command =“ check_es_system”
vars.es_address =“ myescluster.in.the.cloud”
vars.es_user =“已读”
vars.es_password =“仅”
vars.es_checktype =“状态”
}
在此示例中,将检查在myexcluster.in.the.cloud上运行的Elasticsearch的线程池统计信息。如果任何线程池状态(活动,已排队,已拒绝)触发阈值,则插件将以警告或严重状态退出。
#检查Elasticsearch Status
对象服务“ ElasticSearch Status” {
import“通用服务”
host_name =“ myesnode”
check_command =“ check_es_system”
vars.es_address =“ myescluster.in.the.cloud”
vars.es_user =“已读”
vars.es_password =“仅”
vars.es_checktype =“ tps”
vars.es_warn =“ 50,170,1000”
vars.es_crit =“ 100,200,5000”
}