Monitoring framework for minute-by-minute service testing, including live dashboard

2025-12-06 07:48:26 +01:00 · 2025-11-27 21:12:30 +01:00
parent 97e8a90b26
commit f383bcec2b
17 changed files with 986 additions and 0 deletions
--- a/script/monitor/README.md
+++ b/script/monitor/README.md
@@ -0,0 +1,33 @@
+
+Monitoring - How it works
+=========================
+
+Basics
+------
+
+You have to set up the monitoring host first. That host will monitor your other machines.
+Execute `/cis/script/monitor/setupMonitoringHost.sh` to start the process.
+
+As usual you can configure this feature via definitions.
+```
+# Path of this feature's scripts       : '/cis/script                 /monitor'
+# Path of the corresponding definitions: '/cis/definitions/YOUR.DOMAIN/monitor'
+ls -lha '/cis/script/monitor'
+ls -lha '/cis/definitions/YOUR.DOMAIN/monitor'
+```
+
+You can modify the appearance and place your own `check.css` or `logo.png` into the definitions folder:
+
+ - /cis/definitions/YOUR.DOMAIN/monitor/check.css
+ - /cis/definitions/YOUR.DOMAIN/monitor/logo.png
+
+After the change, you have to call `/cis/script/monitor/setupMonitoringHost.sh` again,  
+because it creates links in '/var/www/html/' and gives the definitions priority over the script.  
+Additional you need to configure a webserver to publish the site. 
+
+
+
+Dashboard
+---------
+
+You can set up an dashboard following this manual [SETUP_DASHBOARD.md](SETUP_DASHBOARD.md)
--- a/script/monitor/SETUP_DASHBOARD.md
+++ b/script/monitor/SETUP_DASHBOARD.md
@@ -0,0 +1,126 @@
+
+How to setup a monitoring dashboard
+===================================
+
+Inspired by: https://pimylifeup.com/ubuntu-chromium-kiosk/
+
+Steps
+-----
+
+
+
+### 1.) Install Ubuntu Server (no desktop) on your computer than set hostname and timezone.
+
+```sh
+hostnamectl set-hostname check.local
+timedatectl set-timezone Europe/Berlin
+```
+
+
+
+### 2.) Install minimal GUI and Tools.
+
+```sh
+apt install ubuntu-desktop-minimal
+apt install language-pack-gnome-de
+apt install xdotool
+apt install dbus-x11
+```
+
+
+
+### 3.) Create a kiosk user with home-directory.
+
+```sh
+useradd -m kiosk
+```
+
+and disable Welocme-Screen
+```sh
+echo "yes" > /home/kiosk/.config/gnome-initial-setup-done
+```
+
+
+
+### 4.) Edit following file `nano /etc/gdm3/custom.conf` to turn of wayland and turn on autologin for user 'kiosk'.
+
+```
+[daemon]
+# Uncomment the line below to force the login screen to use Xorg
+#WaylandEnable=false
+
+WaylandEnable=false
+
+# Enabling automatic login
+#  AutomaticLoginEnable = true
+#  AutomaticLogin = user1
+
+AutomaticLoginEnable = true
+AutomaticLogin = kiosk
+```
+
+
+
+### 5.) Configure GUI of user kiosk to prevent monitor from sleeping
+
+```sh
+#gsettings list-recursively
+
+# Does not work
+#sudo -u kiosk gsettings set org.gnome.desktop.session idle-delay 0
+
+# Set idle-delay from "uint32 300" to "uint32 0", needs 'apt install dbus-x11'
+# You can check the value in "GUI-Session of kiosk -> Settings -> Power"
+sudo -u kiosk dbus-launch dconf write /org/gnome/desktop/session/idle-delay "uint32 0"
+```
+
+
+
+### 6.) Create custom service to start firefox loading the page.
+
+Therefore create a file `/etc/systemd/system/kiosk.service` with this content:
+
+```
+[Unit]
+Description=Firefox Kiosk
+Wants=graphical.target
+After=graphical.target
+
+[Service]
+Environment=DISPLAY=:0
+# Set firefox language, needs 'apt install language-pack-gnome-de' 
+Environment=LANG=de_DE.UTF-8
+Type=simple
+# Always a fresh firefox ('-' allow error if common does not exist)
+ExecStartPre=-/usr/bin/rm -r /home/kiosk/snap/firefox/common
+# Move Mouse (should also work on small screens), needs 'apt install dbus-x11'
+ExecStartPre=/usr/bin/xdotool mousemove 4096 2160
+# See: https://wiki.mozilla.org/Firefox/CommandLineOptions (just -kiosk URL => Start-Assistant, so use -url too)
+ExecStart=/usr/bin/firefox -fullscreen -kiosk -url http://monitor.example.net/check.html
+Restart=always
+RestartSec=30
+User=kiosk
+Group=kiosk
+
+[Install]
+WantedBy=graphical.target
+```
+
+
+
+### 7.) Enable the service and reboot
+
+```sh
+systemctl enable kiosk
+reboot
+```
+
+
+
+Troubleshouting
+---------------
+
+```
+systemctl disable pd-mapper.service
+apt purge cloud-init -y && apt autoremove --purge -y
+```
--- a/script/monitor/check.css
+++ b/script/monitor/check.css
@@ -0,0 +1,77 @@
+html, body {
+    --background-theme-color: #001EA0;
+    --cell-space: 20px;
+    --logo-height: 50px;
+
+    background-color: #cccccc;
+    font-family: Verdana;
+    font-size: 14pt;
+    color: #ffffff;
+    height: 100%;
+    margin: 0;
+}
+@media screen and (orientation: portrait) {
+    body {
+        zoom: 200%
+    }
+}
+#header {
+    background-color: var(--background-theme-color); 
+    position: sticky;
+    top: 0;
+    height: calc(var(--logo-height) + (2 * var(--cell-space)));
+    width: 100%;
+}
+#header img {
+    height: var(--logo-height);
+    margin: var(--cell-space);
+    vertical-align: middle;
+}
+#header h1 {
+    display: inline;
+    font-weight: normal;
+    vertical-align: middle;
+}
+#content {
+    min-height: 100%;
+}
+#footer {
+    background-color: var(--background-theme-color);
+    position: sticky;
+    bottom: 0px;
+    padding: var(--cell-space);
+    text-align: center;
+    vertical-align: middle;
+    font-size: 22pt;
+}
+#checks {
+    display: grid;
+    grid-template-columns: repeat(auto-fit, minmax(350px, 1fr));
+    padding: var(--cell-space);
+    grid-gap: var(--cell-space);
+}
+#checks > div {
+    border: 1px solid black;
+    border-radius: 10px;
+    padding: 10px;
+    text-align: center;
+    box-shadow: 0 2px 5px 0 rgba(0, 0, 0, 0.3), 0 2px 10px 0 rgba(0, 0, 0, 0.2);
+}
+#checks > div.ok {
+    background-color: #66aa22;
+    color: #222222;	
+}
+#checks > div.info {
+    background-color: #88cc44;
+    color: #222222;	
+}
+#checks > div.warn {
+    background-color: #ffdd00;
+    color: #222222;	
+}
+#checks > div.fail {
+    background-color: #ff0000;
+}
+#checks > div.timeout {
+    background-color: var(--background-theme-color);
+}
--- a/script/monitor/check.html
+++ b/script/monitor/check.html
@@ -0,0 +1,122 @@
+<html>
+<head>
+    <meta charset="utf-8">
+    <title>Monitoring Dashboard</title>
+    <link rel="stylesheet" href="check.css">
+</head>
+<body>
+    <div id="header">
+        <img src="logo.png"></img>
+        <h1>Monitoring</h1>
+    </div>
+    <div id="content">
+        <div id="checks">
+            <div class="check warn">Loading...</div>
+        </div>
+    </div>
+    <div id="footer">
+        Köln, <span id="datetime"></span>
+    </div>
+
+    <script>
+        var connectionAlive = true;
+
+        function downloadCheckFile(callback) {
+            var xmlHttp = new XMLHttpRequest();
+            xmlHttp.open('GET', "check.txt", false);
+            xmlHttp.onreadystatechange=function() {
+                if(xmlHttp.readyState==4) {
+                    callback(xmlHttp.responseText);
+                }
+            }
+            try {
+                xmlHttp.send(null);
+                if (xmlHttp.status >= 200 && xmlHttp.status < 304) {
+                    return true;
+                } else {
+                    return false;
+                }
+            } catch (e) {
+                return false;
+            }
+        }
+        function convertToHtml(checkText) {
+            if (!connectionAlive) {
+                return '<div class="fail">CONNECTION FAILED</div>';
+            }
+
+            var html = "";
+            var lines = checkText.split(/\n/);
+
+            for(var lineNo = 2; lineNo < lines.length; lineNo++) {
+                var line = lines[lineNo];
+
+                var parts = line.split('?');
+                if (parts.length > 1) {
+
+                    var name = parts[0].trim().split("_").join(" ");
+                    var resultParts = parts[1].trim().split('#');
+                    var result = resultParts[0];
+                    var message = resultParts[1];
+
+                    if(name == 'MISSED') {
+                        var fileTimeParts = message.split('-');
+                        var fileTime = new Date();
+                        fileTime.setHours(parseInt(fileTimeParts[0]));
+                        fileTime.setMinutes(parseInt(fileTimeParts[1]));
+                        fileTime.setSeconds(parseInt(fileTimeParts[2]));
+
+                        var scriptTime = new Date();
+                        scriptTime.setMinutes(scriptTime.getMinutes() - 2);
+                        if (scriptTime.getTime() < fileTime.getTime()){
+                            if (result == "0") {
+                                html += '<div class="ok">EVERYTHING OK<br/>' + fileTime.toLocaleTimeString() + '</div>';
+                            } else {
+                                html += '<div class="fail">FAILED: ' + result + '<br/>' + fileTime.toLocaleTimeString() + '</div>';
+                            }
+                        } else {
+                            html += '<div class="check fail">CHECKS TOO OLD<br/>' + fileTime.toLocaleTimeString() + '</div>';
+                        }
+                    } else {
+                        if(result.indexOf('OK') >= 0) {
+                            html += '<div class="ok">'+ name;
+                        } else if(result.indexOf('INFO') >= 0) {
+                            html += '<div class="info">'+ name;
+                        } else if(result.indexOf('TIMEOUT') >= 0) {
+                            html += '<div class="timeout">'+ name;
+                        } else if(result.indexOf('WARN') >= 0) {
+                            html += '<div class="warn">'+ name;
+                        } else {
+                            html += '<div class="fail">' + name;
+                        }
+                        if(message) {
+                            html += '<br/>' + message.trim();
+                        }
+                        html += '</div>';
+                    }
+                }
+            }
+            return html;
+        }
+        function exchangeChecks(text) {
+            document.getElementById("checks").innerHTML = convertToHtml(text);
+        }
+        function refreshTime() {
+            document.getElementById("datetime").innerHTML = new Date().toLocaleString("de-DE", {timeZone: "Europe/Berlin"});
+        }
+        function refreshChecks() {
+            connectionAlive = downloadCheckFile(exchangeChecks);
+        }
+        function reloadIfAlive() {
+            if (connectionAlive) {
+                location.reload();
+            }
+        }
+        setInterval(refreshTime, 1000);
+        setInterval(refreshChecks, 5000);
+        setInterval(reloadIfAlive, 300000);
+        refreshTime();
+        refreshChecks();
+    </script>
+</body>
+</html>
--- a/script/monitor/check.sh
+++ b/script/monitor/check.sh
@@ -0,0 +1,88 @@
+#!/bin/bash
+
+# Folders always ends with an tailing '/'
+_SCRIPT="$(readlink -f "${0}" 2> /dev/null)"
+_CIS_ROOT="${_SCRIPT%%/script/monitor/*}/"               #Removes longest  matching pattern '/script/monitor/*' from the end
+_CORE_SCRIPTS="${_CIS_ROOT:?"Missing CIS_ROOT"}core/"
+_CURRENT_DOMAIN="$("${_CORE_SCRIPTS:?"Missing CORE_SCRIPTS"}printOwnDomain.sh")"
+_DEFINITIONS="${_CIS_ROOT:?"Missing CIS_ROOT"}definitions/${_CURRENT_DOMAIN:?"Missing CURRENT_DOMAIN"}/"
+
+# Checks for the entire domain
+_DOMAIN_CHECKS="${_DEFINITIONS:?"Missing DEFINITIONS"}monitor/checks/"
+
+
+
+function doChecks(){
+    local readonly _TMPDIR="${1:?"doChecks(): Missing parameter TMPDIR:"}"
+
+    local _DATETIME=$(date +%H-%M-%S)
+
+    mkdir -p ${_TMPDIR}
+    rm ${_TMPDIR}/* > /dev/null 2>&1
+
+    for check in ${_DOMAIN_CHECKS}*.on
+    do
+        local _CHECK_FILENAME="${check##*/}"
+        echo -n "${_CHECK_FILENAME%%.on}?" > "${_TMPDIR}/${_CHECK_FILENAME}"
+        timeout -k 10s 20s bash ${check} >> "${_TMPDIR}/${_CHECK_FILENAME}" 2> /dev/null || echo "TIMEOUT#Timeout" >> "${_TMPDIR}/${_CHECK_FILENAME}" &
+    done
+    wait
+
+    local _FAILED=0
+    echo "CHECK?RESULT[#MESSAGE]:"
+    echo "-----------------------"
+    for resultFile in ${_TMPDIR}/*
+    do
+        cat "${resultFile}"
+        grep -q "FAIL" ${resultFile} && _FAILED=$(expr ${_FAILED} + 1)
+    done
+    echo "MISSED?${_FAILED}#${_DATETIME}"
+
+    rm -r ${_TMPDIR} > /dev/null 2>&1
+    return 0
+}
+
+function usage(){
+    printf "\nUsage: /monitoring/check.sh <command> <options>"
+    echo
+    echo "possible commands:"
+    echo
+    echo "- all"
+    echo "    Executes all checks."
+    echo "- auto <out_file>"
+    echo "    Executes quiet all checks and saves the result in the given out_file."
+    echo "      (e.g. add the following line to crontab: '* * * * * /cis/script/monitor/check.sh auto /var/www/html/check.txt'"
+    echo "       to update the file '/var/www/html/check.txt' every minute as 'check.html' needs it.)"
+    return 0
+}
+
+main(){
+    case "${1:-""}" in
+        all)
+            echo "Checks werden ausgeführt..." \
+                && echo \
+                && doChecks "/tmp/checks" color \
+                && echo \
+                && echo "Success" \
+                && return 0
+            ;;
+        auto)
+            # If just a filename is given it is created in /tmp, because of 'cd /tmp' 
+            cd /tmp \
+                && doChecks "/tmp/checks$(date +%N)" > "$2.new" \
+                && mv -f "$2.new" "$2" \
+                && return 0
+            return 1
+            ;;
+		*)
+            [ "${1:+isset}" == "isset" ] \
+                && echo "Parameter '${1}' ist kein gültiger Befehl."
+            usage
+            return 0
+            ;;
+    esac
+
+    return 1
+}
+
+main "$@" || exit 1
--- a/script/monitor/checks/EXAMPLE_CHECK.off
+++ b/script/monitor/checks/EXAMPLE_CHECK.off
@@ -0,0 +1,9 @@
+#!/bin/bash
+
+_CHECK="$(readlink -f "${0}" 2> /dev/null)"
+
+# Folders always ends with an tailing '/'
+_CIS_ROOT="${_CHECK%%/definitions/*}/"             #Removes longest  matching pattern '/definitions/*' from the end
+_GENERIC_CHECKS="${_CIS_ROOT:?"Missing CIS_ROOT"}script/monitor/generic/"
+
+${_GENERIC_CHECKS:?"Missing GENERIC_CHECKS"}OVERRIDDEN_DOMAIN_CHECK.sh "your-host.your-domain.net"
--- a/script/monitor/generic/CIS_OWN_DOMAIN_CHECK.sh
+++ b/script/monitor/generic/CIS_OWN_DOMAIN_CHECK.sh
@@ -0,0 +1,45 @@
+#!/bin/bash
+
+_REMOTE_HOST="${1:?"FQDN of server missing: e.g. host.example.net[:port]"}"
+_REMOTE_HOSTNAME_FQDN="${_REMOTE_HOST%%:*}"            #Removes longest  matching pattern ':*' from the end
+_REMOTE_HOSTNAME_SHORT="${_REMOTE_HOSTNAME_FQDN%%.*}"  #Removes longest  matching pattern '.*' from the end
+_REMOTE_PORT="${_REMOTE_HOST}:"
+_REMOTE_PORT="${_REMOTE_PORT#*:}"                      #Removes shortest matching pattern '*:' from the begin
+_REMOTE_PORT="${_REMOTE_PORT%%:*}"                     #Removes longest  matching pattern ':*' from the end
+_REMOTE_PORT="${_REMOTE_PORT:-"22"}"
+_REMOTE_USER="monitoring"
+_SOCKET='~/.ssh/%r@%h:%p'
+
+
+
+function checkOrStartSSHMaster() {
+    timeout --preserve-status 1 ssh -O check -S ${_SOCKET} -p ${_REMOTE_PORT} ${_REMOTE_USER}@${_REMOTE_HOSTNAME_FQDN} 2>&1 | grep -q -F 'Master running' \
+        && return 0
+
+    ssh -O stop -S ${_SOCKET} -p ${_REMOTE_PORT} ${_REMOTE_USER}@${_REMOTE_HOSTNAME_FQDN} &> /dev/null
+    ssh -o ControlMaster=auto \
+        -o ControlPath=${_SOCKET} \
+        -o ControlPersist=65 \
+        -p ${_REMOTE_PORT} \
+        -f ${_REMOTE_USER}@${_REMOTE_HOSTNAME_FQDN} exit &> /dev/null \
+        && return 0
+
+    echo "FAIL#SSH connection (setup ok?)"
+    return 1
+}
+
+function testDomain(){
+    checkOrStartSSHMaster \
+        || return 1
+
+    local _RESULT="$(ssh -S ${_SOCKET} -p ${_REMOTE_PORT} ${_REMOTE_USER}@${_REMOTE_HOSTNAME_FQDN} 'bash /cis/core/printOwnDomain.sh' 2>&1 1>/dev/null)"
+
+    [ -z "${_RESULT}" ] \
+        && echo "OK" \
+        && return 0
+
+    echo "WARNING#Check hosts '/cis/core/printOwnDomain'"
+    return 0
+}
+
+testDomain && exit 0
--- a/script/monitor/generic/NGINX_CHECK.sh
+++ b/script/monitor/generic/NGINX_CHECK.sh
@@ -0,0 +1,67 @@
+#!/bin/bash
+
+_REMOTE_HOST="${1:?"FQDN of server missing: e.g. host.example.net[:port]"}"
+_REMOTE_HOSTNAME_FQDN="${_REMOTE_HOST%%:*}"            #Removes longest  matching pattern ':*' from the end
+_REMOTE_HOSTNAME_SHORT="${_REMOTE_HOSTNAME_FQDN%%.*}"  #Removes longest  matching pattern '.*' from the end
+_REMOTE_PORT="${_REMOTE_HOST}:"
+_REMOTE_PORT="${_REMOTE_PORT#*:}"                      #Removes shortest matching pattern '*:' from the begin
+_REMOTE_PORT="${_REMOTE_PORT%%:*}"                     #Removes longest  matching pattern ':*' from the end
+_REMOTE_PORT="${_REMOTE_PORT:-"22"}"
+_REMOTE_USER="monitoring"
+_SOCKET='~/.ssh/%r@%h:%p'
+
+
+
+function checkOrStartSSHMaster() {
+    timeout --preserve-status 1 ssh -O check -S ${_SOCKET} -p ${_REMOTE_PORT} ${_REMOTE_USER}@${_REMOTE_HOSTNAME_FQDN} 2>&1 | grep -q -F 'Master running' \
+        && return 0
+
+    ssh -O stop -S ${_SOCKET} -p ${_REMOTE_PORT} ${_REMOTE_USER}@${_REMOTE_HOSTNAME_FQDN} &> /dev/null
+    ssh -o ControlMaster=auto \
+        -o ControlPath=${_SOCKET} \
+        -o ControlPersist=65 \
+        -p ${_REMOTE_PORT} \
+        -f ${_REMOTE_USER}@${_REMOTE_HOSTNAME_FQDN} exit &> /dev/null \
+        && return 0
+
+    echo "FAIL#SSH connection (setup ok?)"
+    return 1
+}
+
+function checkViaHTTP() {
+    _STATUS="$(curl -I http://${_REMOTE_HOSTNAME_FQDN} 2>/dev/null | head -n 1 | cut -d$' ' -f2)"
+    [ "${_STATUS}" == "200" ] \
+        && echo "OK" \
+        && return 0
+
+    return 1
+}
+
+function checkViaHTTPS() {
+    _STATUS="$(curl -k -I https://${_REMOTE_HOSTNAME_FQDN} 2>/dev/null | head -n 1 | cut -d$' ' -f2)"
+    [ "${_STATUS}" == "200" ] \
+        && echo "OK" \
+        && return 0
+
+    return 1
+}
+
+#grep:
+# -E                         Use regexp, '.*' => any chars between 'Active:' and '(running)', the round brackets are escaped.
+
+#cut:
+# -d                         Delimiter, marker where to cut (here ;)
+# -f                         Index of column to show (One based, so there is no -f0)
+function checkViaSSH() {
+    checkOrStartSSHMaster \
+        || return 1
+
+    _RESULT=$(ssh -S ${_SOCKET} -p ${_REMOTE_PORT} ${_REMOTE_USER}@${_REMOTE_HOSTNAME_FQDN} 'systemctl status nginx.service' | grep -E 'Active:.*\(running\)' | cut -d';' -f2)
+    ! [ -z "${_RESULT}" ] && echo "OK#UPTIME:${_RESULT}" || echo "FAIL"
+}
+
+#checkViaHTTP && exit 0
+#checkViaHTTPS && exit 0
+checkViaSSH && exit 0
+
+exit 1
--- a/script/monitor/generic/PING_CHECK.sh
+++ b/script/monitor/generic/PING_CHECK.sh
@@ -0,0 +1,9 @@
+#!/bin/bash
+
+_SERVER="${1:?"FQDN of server missing"}"
+
+# -4                         Use IPv4
+# -W            SECONDS      Wait seconds for an answer
+# -c            COUNT_VALUE  Count of pings being executed
+_RESULT="$(ping -4 -W 1 -c 1 "${_SERVER}" | grep "time=" | cut -d'=' -f4)"
+! [ -z "${_RESULT}" ] && echo "OK#RTT: ${_RESULT}" || echo "FAIL#PLEASE USE FALLBACK!"
--- a/script/monitor/generic/POSTGRES_CERTIFICATE_CHECK.sh
+++ b/script/monitor/generic/POSTGRES_CERTIFICATE_CHECK.sh
@@ -0,0 +1,37 @@
+#!/bin/bash
+
+function checkPostgresSSLCertificate() {
+    local _SERVER
+    _SERVER="${1:?"FQDN of server missing"}"
+    readonly _SERVER
+
+    local _RESULT
+    _RESULT="$(echo | openssl s_client -starttls postgres -connect "${_SERVER}":5432 -servername "${_SERVER}" 2> /dev/null | openssl x509 -noout -enddate | grep -F 'notAfter=' | cut -d'=' -f2)"
+    readonly _RESULT
+
+    [ -z "${_RESULT}" ] \
+        && echo "FAIL#Unable to get cert's end date from ${_SERVER}:5432" \
+        && return 1
+
+    local _ENDDATE
+    _ENDDATE="$(date --date="${_RESULT}" --utc +%s)"
+    readonly _ENDDATE
+
+    ! echo "${_ENDDATE}" | grep -q -E "^[0-9]*$" \
+        && echo "FAIL#Unable to parse end date of certificate" \
+        && return 1
+
+    local _NOW _REMAINING_DAYS
+    _NOW="$(date --date now +%s)"
+    _REMAINING_DAYS="$(( (_ENDDATE - _NOW) / 86400 ))"
+    readonly _NOW _REMAINING_DAYS
+
+    [ -z "${_REMAINING_DAYS}" ] \
+        && echo "WARN#Only ${_REMAINING_DAYS} days left" \
+        && return 1
+
+    echo "OK#${_REMAINING_DAYS} days remaining"
+    return 0
+}
+
+checkPostgresSSLCertificate "${@}" && exit 0 || exit 1
--- a/script/monitor/generic/URL_CHECK.sh
+++ b/script/monitor/generic/URL_CHECK.sh
@@ -0,0 +1,62 @@
+#!/bin/bash
+
+#curl:
+# --connect-timeout SECONDS  Maximum time allowed for connection
+# -k                         Allow connections to SSL sites without certs (H)
+# -L                         Follow redirects (H)
+# --max-time        SECONDS  Maximum time allowed for the transfer
+# -s                         Silent mode. Don't output anything
+# --head                     Show head information only
+# --no-progress-meter        Clean output for grep
+
+#grep:
+# -q                         Quite, no output just status codes
+# -F                         Interpret search term as plain text
+function checkUrl() {
+    local _URL _SEARCH_STRING
+    _URL="${1:?"URL of site missing"}"
+    _SEARCH_STRING="${2}"
+    readonly _URL _SEARCH_STRING
+
+    local _RESULT
+    if [ -z "${_SEARCH_STRING}" ]; then
+        _RESULT="$(curl --connect-timeout 10 --max-time 10 --no-progress-meter --verbose "${_URL}" 2>&1 | grep -o -E "(expire.*|HTTP.*200 OK)")"
+    else
+        _RESULT="$(curl --connect-timeout 10 --max-time 10 --no-progress-meter --verbose "${_URL}" 2>&1 | grep -o -E "(expire.*|HTTP.*200 OK|${_SEARCH_STRING})")"
+    fi
+    readonly _RESULT
+
+    ! echo "${_RESULT}" | grep -q -F '200 OK' \
+        && echo "FAIL#Status code 200 not found" \
+        && return 1
+
+    ! [ -z "${_SEARCH_STRING}" ] \
+        && ! echo "${_RESULT}" | grep -q -F "${_SEARCH_STRING}" \
+        && echo "FAIL#Search string not found" \
+        && return 1
+
+    local _ENDDATE
+    _ENDDATE="$(echo "${_RESULT}" | grep -F 'expire' | cut -d':' -f2-)"
+    _ENDDATE="$(date --date="${_ENDDATE}" --utc +%s)"
+    readonly _ENDDATE
+
+    ! echo "${_ENDDATE}" | grep -q -E "^[0-9]*$" \
+        && echo "FAIL#Unable to parse end date of certificate" \
+        && return 1
+
+    local _NOW _REMAINING_DAYS
+    _NOW="$(date --date now +%s)"
+    _REMAINING_DAYS="$(( (_ENDDATE - _NOW) / 86400 ))"
+    readonly _NOW _REMAINING_DAYS
+
+    # less than 30 days remaining => should be warned
+    [ "${_REMAINING_DAYS}" -le "30" ] \
+        && echo "WARN#Certificate: only ${_REMAINING_DAYS} days left" \
+        && return 1
+
+    echo "OK#Certificate: ${_REMAINING_DAYS} days remaining"
+    return 0
+}
+
+#((curl --connect-timeout 10 --max-time 10 -k -s --head --no-progress-meter "${_URL}" | grep -qF '200 OK') && echo OK) || echo FAIL
+checkUrl "${1}" "${2}" && exit 0 || exit 1
--- a/script/monitor/generic/ZFS_POOL_CHECK.sh
+++ b/script/monitor/generic/ZFS_POOL_CHECK.sh
@@ -0,0 +1,50 @@
+#!/bin/bash
+
+_REMOTE_HOST="${1:?"FQDN of server missing: e.g. host.example.net[:port]"}"
+_ZFS_POOL="${2:?"Name of zfs pool missing: e.g. zpool1"}"
+_REMOTE_HOSTNAME_FQDN="${_REMOTE_HOST%%:*}"            #Removes longest  matching pattern ':*' from the end
+_REMOTE_HOSTNAME_SHORT="${_REMOTE_HOSTNAME_FQDN%%.*}"  #Removes longest  matching pattern '.*' from the end
+_REMOTE_PORT="${_REMOTE_HOST}:"
+_REMOTE_PORT="${_REMOTE_PORT#*:}"                      #Removes shortest matching pattern '*:' from the begin
+_REMOTE_PORT="${_REMOTE_PORT%%:*}"                     #Removes longest  matching pattern ':*' from the end
+_REMOTE_PORT="${_REMOTE_PORT:-"22"}"
+_REMOTE_USER="monitoring"
+_SOCKET='~/.ssh/%r@%h:%p'
+
+
+
+function checkOrStartSSHMaster() {
+    timeout --preserve-status 1 ssh -O check -S ${_SOCKET} -p ${_REMOTE_PORT} ${_REMOTE_USER}@${_REMOTE_HOSTNAME_FQDN} 2>&1 | grep -q -F 'Master running' \
+        && return 0
+
+    ssh -O stop -S ${_SOCKET} -p ${_REMOTE_PORT} ${_REMOTE_USER}@${_REMOTE_HOSTNAME_FQDN} &> /dev/null
+    ssh -o ControlMaster=auto \
+        -o ControlPath=${_SOCKET} \
+        -o ControlPersist=65 \
+        -p ${_REMOTE_PORT} \
+        -f ${_REMOTE_USER}@${_REMOTE_HOSTNAME_FQDN} exit &> /dev/null \
+        && return 0
+
+    echo "FAIL#SSH connection (setup ok?)"
+    return 1
+}
+
+function testPool(){
+    checkOrStartSSHMaster \
+        || return 1
+
+    local _RESPONSE="$(ssh -S ${_SOCKET} -p ${_REMOTE_PORT} ${_REMOTE_USER}@${_REMOTE_HOSTNAME_FQDN} 'zpool status ${_ZFS_POOL} | grep -F scrub')"
+    local _RESULT=$(echo "${_RESPONSE}" | grep -F 'scrub repaired 0B' | grep -F '0 errors')
+    _RESULT="${_RESULT#*on}"  #Removes shortest matching pattern '*on' from the begin
+
+    [ -z "${_RESULT}" ] \
+        && echo "FAIL#CHECK POOL: ${_ZFS_POOL}" \
+        && return 0
+
+    echo "OK#Scrubbed on ${_RESULT}."
+    return 0
+}
+
+testPool && exit 0
+
+exit 1
--- a/script/monitor/generic/ZFS_SYNC_CHECK.sh
+++ b/script/monitor/generic/ZFS_SYNC_CHECK.sh
@@ -0,0 +1,106 @@
+#!/bin/bash
+
+_SCRIPT="$(readlink -f "${0}" 2> /dev/null)"
+
+# Folders always ends with an tailing '/'
+_CIS_ROOT="${_SCRIPT%%/script/monitor/*}/"             #Removes longest  matching pattern '/script/monitor/*' from the end
+_DOMAIN="$("${_CIS_ROOT:?"Missing CIS_ROOT"}core/printOwnDomain.sh")"
+_COMPOSITIONS="${_CIS_ROOT:?"Missing CIS_ROOT"}definitions/${_DOMAIN:?"Missing DOMAIN"}/compositions/"
+
+_REMOTE_HOST="${1:?"FQDN of server missing: e.g. host.example.net[:port]"}"
+_REMOTE_HOSTNAME_FQDN="${_REMOTE_HOST%%:*}"            #Removes longest  matching pattern ':*' from the end
+_REMOTE_HOSTNAME_SHORT="${_REMOTE_HOSTNAME_FQDN%%.*}"  #Removes longest  matching pattern '.*' from the end
+_REMOTE_PORT="${_REMOTE_HOST}:"
+_REMOTE_PORT="${_REMOTE_PORT#*:}"                      #Removes shortest matching pattern '*:' from the begin
+_REMOTE_PORT="${_REMOTE_PORT%%:*}"                     #Removes longest  matching pattern ':*' from the end
+_REMOTE_PORT="${_REMOTE_PORT:-"22"}"
+_REMOTE_USER="monitoring"
+_SOCKET='~/.ssh/%r@%h:%p'
+
+# This is crucial:
+#  - default value for the filter part is extracted from the first parameter (FQDN)
+#  - but you can override this part to to adapt the test during a change of the domain.
+#    (e.g. the short hostname can be an option - or even a better default in the future)
+_ZFS_SNAPSHOT_FILTER="@SYNC_${2:-"${_REMOTE_HOSTNAME_FQDN:?"Missing REMOTE_HOSTNAME_FQDN"}"}"
+
+_MODE="${3:-"normal"}"
+_NOW_UTC_UNIXTIME=$(date -u +%s)
+_DEBUG_PATH="/tmp/monitor/"
+
+
+
+function checkOrStartSSHMaster() {
+    timeout --preserve-status 1 ssh -O check -S ${_SOCKET} -p ${_REMOTE_PORT} ${_REMOTE_USER}@${_REMOTE_HOSTNAME_FQDN} 2>&1 | grep -q -F 'Master running' \
+        && return 0
+
+    ssh -O stop -S ${_SOCKET} -p ${_REMOTE_PORT} ${_REMOTE_USER}@${_REMOTE_HOSTNAME_FQDN} &> /dev/null
+    ssh -o ControlMaster=auto \
+        -o ControlPath=${_SOCKET} \
+        -o ControlPersist=65 \
+        -p ${_REMOTE_PORT} \
+        -f ${_REMOTE_USER}@${_REMOTE_HOSTNAME_FQDN} exit &> /dev/null \
+        && return 0
+
+    echo "FAIL#SSH connection (setup ok?)"
+    return 1
+}
+
+function checkSync() {
+    checkOrStartSSHMaster \
+        || return 1
+
+    [ "${_MODE}" == "debug" ] \
+        && mkdir -p "${_DEBUG_PATH}" > /dev/null \
+        && echo "Now: ${_NOW_UTC_UNIXTIME}" > ${_DEBUG_PATH}SECONDS_BEHIND_${_REMOTE_HOSTNAME_FQDN}.txt
+
+    ! [ -d "${_COMPOSITIONS:?"Missing COMPOSITIONS"}" ] \
+        && echo "WARN#no compositions" \
+        && return 0
+
+    [ "${_MODE}" == "debug" ] \
+        && echo "Snapshot filter: ${_ZFS_SNAPSHOT_FILTER}" >> ${_DEBUG_PATH}SECONDS_BEHIND_${_REMOTE_HOSTNAME_FQDN}.txt
+
+    # This retrieves the list of the interesting snapshots including creation timestamp
+    _SNAPSHOTS="$(ssh -S ${_SOCKET} -p ${_REMOTE_PORT} ${_REMOTE_USER}@${_REMOTE_HOSTNAME_FQDN} zfs list -po creation,name -r -t snapshot zpool1/persistent | grep -F ${_ZFS_SNAPSHOT_FILTER})"
+    [ "${_MODE}" == "debug" ] \
+        && echo "${_SNAPSHOTS}" > ${_DEBUG_PATH}SNAPSHOTS_${_REMOTE_HOSTNAME_FQDN}.txt
+
+    [ -z "${_SNAPSHOTS}" ] \
+        && echo "FAIL#no snapshots" \
+        && return 1
+
+    echo "OK#Checks running"
+
+    for _COMPOSITION_PATH in ${_COMPOSITIONS}*; do
+
+        # If remote host is found than it is responsible for this container-composition, otherwise skip
+        #   (grep -E "^[[:blank:]]*something" means. Line has to start with "something", leading blank chars are ok.)
+        grep -E "^[[:blank:]]*${_REMOTE_HOSTNAME_SHORT}" "${_COMPOSITION_PATH}/zfssync-hosts" &> /dev/null \
+            || continue;
+
+        _COMPOSITION_NAME="${_COMPOSITION_PATH##*/}"   #Removes longest  matching pattern '*/' from the begin
+        _LAST_SNAPSHOT_UNIXTIME="$(echo "${_SNAPSHOTS}" | grep ${_COMPOSITION_NAME} | tail -n 1 | cut -d' ' -f1)"
+        _SECONDS_BEHIND=$[ ${_NOW_UTC_UNIXTIME} - ${_LAST_SNAPSHOT_UNIXTIME} ]
+
+        [ "${_MODE}" == "debug" ] \
+            && echo "${_LAST_SNAPSHOT_UNIXTIME} ${_COMPOSITION_NAME} on ${_REMOTE_HOSTNAME_FQDN} behind: ${_SECONDS_BEHIND}s" >> ${_DEBUG_PATH}SECONDS_BEHIND_${_REMOTE_HOSTNAME_FQDN}.txt
+
+        [ "${_SECONDS_BEHIND}" -lt 40 ] \
+            && continue
+
+        [ "${_SECONDS_BEHIND}" -lt 60 ] \
+            && echo "ZFSSYNC_of_${_REMOTE_HOSTNAME_SHORT}_LAGGING?WARN#${_COMPOSITION_NAME} ${_SECONDS_BEHIND}s" \
+            && continue
+
+        echo "ZFSSYNC_of_${_REMOTE_HOSTNAME_SHORT}_LAGGING?FAIL#${_COMPOSITION_NAME} ${_SECONDS_BEHIND}s"
+    done
+}
+
+
+
+RESULTS="$(checkSync)"
+
+[ "${_MODE}" == "debug" ] \
+    && echo "$RESULTS" > ${_DEBUG_PATH}RESULTS_${_REMOTE_HOSTNAME_FQDN}.txt
+
+echo "$RESULTS"
--- a/script/monitor/generic/ZFS_USAGE_CHECK.sh
+++ b/script/monitor/generic/ZFS_USAGE_CHECK.sh
@@ -0,0 +1,57 @@
+#!/bin/bash
+
+_REMOTE_HOST="${1:?"FQDN of server missing: e.g. host.example.net[:port]"}"
+_REMOTE_HOSTNAME_FQDN="${_REMOTE_HOST%%:*}"            #Removes longest  matching pattern ':*' from the end
+_REMOTE_HOSTNAME_SHORT="${_REMOTE_HOSTNAME_FQDN%%.*}"  #Removes longest  matching pattern '.*' from the end
+_REMOTE_PORT="${_REMOTE_HOST}:"
+_REMOTE_PORT="${_REMOTE_PORT#*:}"                      #Removes shortest matching pattern '*:' from the begin
+_REMOTE_PORT="${_REMOTE_PORT%%:*}"                     #Removes longest  matching pattern ':*' from the end
+_REMOTE_PORT="${_REMOTE_PORT:-"22"}"
+_REMOTE_USER="monitoring"
+_SOCKET='~/.ssh/%r@%h:%p'
+
+
+
+function checkOrStartSSHMaster() {
+    timeout --preserve-status 1 ssh -O check -S ${_SOCKET} -p ${_REMOTE_PORT} ${_REMOTE_USER}@${_REMOTE_HOSTNAME_FQDN} 2>&1 | grep -q -F 'Master running' \
+        && return 0
+
+    ssh -O stop -S ${_SOCKET} -p ${_REMOTE_PORT} ${_REMOTE_USER}@${_REMOTE_HOSTNAME_FQDN} &> /dev/null
+    ssh -o ControlMaster=auto \
+        -o ControlPath=${_SOCKET} \
+        -o ControlPersist=65 \
+        -p ${_REMOTE_PORT} \
+        -f ${_REMOTE_USER}@${_REMOTE_HOSTNAME_FQDN} exit &> /dev/null \
+        && return 0
+
+    echo "FAIL#SSH connection (setup ok?)"
+    return 1
+}
+
+function testSpace(){
+    checkOrStartSSHMaster \
+        || return 1
+
+    local _RESULT="$(ssh -S ${_SOCKET} -p ${_REMOTE_PORT} ${_REMOTE_USER}@${_REMOTE_HOSTNAME_FQDN} 'zpool list -H -o capacity,name')"
+    local _SPACE_USED=$(echo "${_RESULT}" | /usr/bin/tail -n 1 | /usr/bin/cut -f1)
+    local _POOL=$(echo "${_RESULT}" | /usr/bin/tail -n 1 | /usr/bin/cut -f2)
+
+    [ -z "${_SPACE_USED}" ] \
+        && echo "FAIL#NO value" \
+        && return 0
+
+    [ "${1:?"Missing OK_THRESHOLD"}" -ge "${_SPACE_USED%\%*}" ] \
+        && echo "OK#${_SPACE_USED} used ${_POOL}." \
+        && return 0
+
+    [ "${2:?"Missing INFO_THRESHOLD"}" -ge "${_SPACE_USED%\%*}" ] \
+        && echo "INFO#${_SPACE_USED} already used ${_POOL}." \
+        && return 0
+
+    echo "FAIL#${_SPACE_USED} used ${_POOL}!"
+    return 0
+}
+
+testSpace 80 90 && exit 0
+
+exit 1
--- a/script/monitor/logo.png
+++ b/script/monitor/logo.png
--- a/script/monitor/setupMonitoringHost.sh
+++ b/script/monitor/setupMonitoringHost.sh
@@ -0,0 +1,73 @@
+#!/bin/bash
+
+[ "$(id -u)" != "0" ] \
+    && sudo "${0}" \
+    && exit 0
+
+
+
+_SETUP="$(readlink -f "${0}" 2> /dev/null)"
+
+# Folders always ends with an tailing '/'
+_CIS_ROOT="${_SETUP%%/script/monitor/*}/"             #Removes longest  matching pattern '/script/monitor/*' from the end
+_DOMAIN="$("${_CIS_ROOT:?"Missing CIS_ROOT"}core/printOwnDomain.sh")"
+_DEFINITIONS="${_CIS_ROOT:?"Missing CIS_ROOT"}definitions/${_DOMAIN:?"Missing DOMAIN"}/"
+
+
+
+function checkPreconditions() {
+    [ -d "${_DEFINITIONS:?"Missing DEFINITIONS"}monitor/checks" ] \
+        && return 0
+
+    echo "No folder for your defined checks found: ${_DEFINITIONS:?"Missing DEFINITIONS"}monitor/checks"
+    echo "Please create it and add all your custom monitoring checks there, following this convention: 'NAME_OF_THE_CHECK.on'"
+    echo "A check has to be switched 'on' to be executed, so you can rename a check to 'NAME_OF_THE_CHECK.off' and it will be ignored."
+    echo
+    echo "You can copy the file '/cis/script/monitor/checks/EXAMPLE_CHECK.off' to your check definitions folder and modify it."
+    return 1
+}
+
+
+
+function printSelectedDefinition() {
+    local _FILE_DEFINED_DOMAIN _FILE_DEFINED_DEFAULT
+    _FILE_DEFINED_DOMAIN="${_DEFINITIONS:?"Missing DEFINITIONS"}monitor/${1:?"Missing CURRENT_FULLFILE"}"
+    _FILE_DEFINED_DEFAULT="${_CIS_ROOT:?"Missing CIS_ROOT"}script/monitor/${1:?"Missing CURRENT_FULLFILE"}"
+    readonly _FILE_DEFINED_DOMAIN _FILE_DEFINED_DEFAULT
+
+    [ -s "${_FILE_DEFINED_DOMAIN}" ] \
+        && echo "${_FILE_DEFINED_DOMAIN}" \
+        && return 0
+
+    [ -s "${_FILE_DEFINED_DEFAULT}" ] \
+        && echo "${_FILE_DEFINED_DEFAULT}" \
+        && return 0
+
+    return 1
+}
+
+function setupPublicFile() {
+    ! [ -d "/var/www/html" ] \
+        && echo "Missing folder '/var/www/html'. Is a webserver installed?" \
+        && return 1
+
+    [ -L "/var/www/html/${1:?"Missing filename"}" ] \
+        && [ "$(readlink -f /var/www/html/${1:?"Missing filename"})" == "$(printSelectedDefinition ${1:?"Missing filename"})" ] \
+        && echo "Link '/var/www/html/${1:?"Missing filename"}' already exists pointing to the expected file:" \
+        && echo "  - '$(readlink -f /var/www/html/${1:?"Missing filename"})'" \
+        && return 0
+
+    ln -f -s "$(printSelectedDefinition ${1:?"Missing filename"})" "/var/www/html/${1:?"Missing filename"}" \
+        && echo "Link '/var/www/html/${1:?"Missing filename"}' created successfully:" \
+        && echo "  - '$(readlink -f /var/www/html/${1:?"Missing filename"})'" \
+        && return 0
+}
+
+echo "Setup the monitoring host that monitors the others ... " \
+    && checkPreconditions \
+    && setupPublicFile "check.html" \
+    && setupPublicFile "check.css" \
+    && setupPublicFile "logo.png" \
+    && exit 0
+
+exit 1
--- a/script/monitor/setupServiceProvidingHost.sh
+++ b/script/monitor/setupServiceProvidingHost.sh
@@ -0,0 +1,25 @@
+#!/bin/bash
+
+[ "$(id -u)" != "0" ] \
+    && sudo "${0}" \
+    && exit 0
+
+
+
+_SETUP="$(readlink -f "${0}" 2> /dev/null)"
+
+# Folders always ends with an tailing '/'
+_CIS_ROOT="${_SETUP%%/script/monitor/*}/"             #Removes longest  matching pattern '/script/monitor/*' from the end
+_CORE_SCRIPTS="${_CIS_ROOT:?"Missing CIS_ROOT"}core/"
+_DOMAIN="$("${_CIS_ROOT:?"Missing CIS_ROOT"}core/printOwnDomain.sh")"
+_DEFINITIONS="${_CIS_ROOT:?"Missing CIS_ROOT"}definitions/${_DOMAIN:?"Missing DOMAIN"}/"
+
+
+
+echo "Setup the user and permission to enable the monitoring this host ... " \
+    && "${_CORE_SCRIPTS:?"Missing CORE_SCRIPTS"}addNormalUser.sh" monitoring \
+    && echo \
+    && "${_CORE_SCRIPTS:?"Missing CORE_SCRIPTS"}defineAuthorizedKeysOfUser.sh" "${_DEFINITIONS}" monitoring \
+    && exit 0
+
+exit 1