X-Git-Url: https://arthur.barton.de/cgi-bin/gitweb.cgi?a=blobdiff_plain;f=plugins.d%2Falarm-notify.sh;h=d0188fe3b11b5361810b62a791ece461f43d6d49;hb=HEAD;hp=88ac8723e040b9d15fe1f1062435df890299cf18;hpb=4764d3115f34718a2c219b4070b26a3a70b2c574;p=netdata.git diff --git a/plugins.d/alarm-notify.sh b/plugins.d/alarm-notify.sh index 88ac8723..d0188fe3 100755 --- a/plugins.d/alarm-notify.sh +++ b/plugins.d/alarm-notify.sh @@ -1,22 +1,117 @@ #!/usr/bin/env bash -# (C) Costa Tsaousis -# pushover support by Jan Arnold +# netdata +# real-time performance and health monitoring, done right! +# (C) 2016 Costa Tsaousis +# GPL v3+ +# +# Script to send alarm notifications for netdata +# +# Features: +# - multiple notification methods +# - multiple roles per alarm +# - multiple recipients per role +# - severity filtering per recipient +# +# Supported notification methods: +# - emails by @ktsaou +# - slack.com notifications by @ktsaou +# - discordapp.com notifications by @lowfive +# - pushover.net notifications by @ktsaou +# - pushbullet.com push notifications by Tiago Peralta @tperalta82 PR #1070 +# - telegram.org notifications by @hashworks PR #1002 +# - twilio.com notifications by Levi Blaney @shadycuz PR #1211 +# - kafka notifications by @ktsaou #1342 +# - pagerduty.com notifications by Jim Cooley @jimcooley PR #1373 +# - messagebird.com notifications by @tech_no_logical #1453 +# - hipchat notifications by @ktsaou #1561 -me="${0}" +# ----------------------------------------------------------------------------- +# testing notifications -if [ $(( ${BASH_VERSINFO[0]} )) -lt 4 ] +if [ \( "${1}" = "test" -o "${2}" = "test" \) -a "${#}" -le 2 ] then - echo >&2 - echo >&2 "$me: ERROR" - echo >&2 "BASH version 4 or later is required." - echo >&2 "You are running version: ${BASH_VERSION}" - echo >&2 "Please upgrade." - echo >&2 + if [ "${2}" = "test" ] + then + recipient="${1}" + else + recipient="${2}" + fi + + [ -z "${recipient}" ] && recipient="sysadmin" + + id=1 + last="CLEAR" + for x in "CRITICAL" "WARNING" "CLEAR" + do + echo >&2 + echo >&2 "# SENDING TEST ${x} ALARM TO ROLE: ${recipient}" + + "${0}" "${recipient}" "$(hostname)" 1 1 "${id}" "$(date +%s)" "test_alarm" "test.chart" "test.family" "${x}" "${last}" 100 90 "${0}" 1 $((0 + id)) "units" "this is a test alarm to verify notifications work" "new value" "old value" + if [ $? -ne 0 ] + then + echo >&2 "# FAILED" + else + echo >&2 "# OK" + fi + + last="${x}" + id=$((id + 1)) + done + exit 1 fi +export PATH="${PATH}:/sbin:/usr/sbin:/usr/local/sbin" +export LC_ALL=C + +# ----------------------------------------------------------------------------- + +PROGRAM_NAME="$(basename "${0}")" + +logdate() { + date "+%Y-%m-%d %H:%M:%S" +} + +log() { + local status="${1}" + shift + + echo >&2 "$(logdate): ${PROGRAM_NAME}: ${status}: ${*}" + +} + +warning() { + log WARNING "${@}" +} + +error() { + log ERROR "${@}" +} + +info() { + log INFO "${@}" +} + +fatal() { + log FATAL "${@}" + exit 1 +} + +debug=0 +debug() { + [ ${debug} -eq 1 ] && log DEBUG "${@}" +} + +# ----------------------------------------------------------------------------- + +# check for BASH v4+ (required for associative arrays) +[ $(( ${BASH_VERSINFO[0]} )) -lt 4 ] && \ + fatal "BASH version 4 or later is required (this is ${BASH_VERSION})." + +# ----------------------------------------------------------------------------- # defaults to allow running this script by hand + NETDATA_CONFIG_DIR="${NETDATA_CONFIG_DIR-/etc/netdata}" NETDATA_CACHE_DIR="${NETDATA_CACHE_DIR-/var/cache/netdata}" [ -z "${NETDATA_REGISTRY_URL}" ] && NETDATA_REGISTRY_URL="https://registry.my-netdata.io" @@ -26,24 +121,33 @@ NETDATA_CACHE_DIR="${NETDATA_CACHE_DIR-/var/cache/netdata}" # ----------------------------------------------------------------------------- # parse command line parameters -recipient="${1}" # the recepient of the email -host="${2}" # the host this event refers to +roles="${1}" # the roles that should be notified for this event +host="${2}" # the host generated this event unique_id="${3}" # the unique id of this event alarm_id="${4}" # the unique id of the alarm that generated this event -event_id="${5}" # the incremental id of the event, for this alarm -when="${6}" # the timestamp this event occured +event_id="${5}" # the incremental id of the event, for this alarm id +when="${6}" # the timestamp this event occurred name="${7}" # the name of the alarm, as given in netdata health.d entries chart="${8}" # the name of the chart (type.id) family="${9}" # the family of the chart status="${10}" # the current status : REMOVED, UNITIALIZED, UNDEFINED, CLEAR, WARNING, CRITICAL old_status="${11}" # the previous status: REMOVED, UNITIALIZED, UNDEFINED, CLEAR, WARNING, CRITICAL -value="${12}" # the current value -old_value="${13}" # the previous value +value="${12}" # the current value of the alarm +old_value="${13}" # the previous value of the alarm src="${14}" # the line number and file the alarm has been configured -duration="${15}" # the duration in seconds the previous state took -non_clear_duration="${16}" # the total duration in seconds this is non-clear +duration="${15}" # the duration in seconds of the previous alarm state +non_clear_duration="${16}" # the total duration in seconds this is/was non-clear units="${17}" # the units of the value info="${18}" # a short description of the alarm +value_string="${19}" # friendly value (with units) +old_value_string="${20}" # friendly old value (with units) + +# ----------------------------------------------------------------------------- +# find a suitable hostname to use, if netdata did not supply a hostname + +[ -z "${host}" ] && host="${NETDATA_HOSTNAME}" +[ -z "${host}" ] && host="${NETDATA_REGISTRY_HOSTNAME}" +[ -z "${host}" ] && host="$(hostname 2>/dev/null)" # ----------------------------------------------------------------------------- # screen statuses we don't need to send a notification @@ -51,23 +155,24 @@ info="${18}" # a short description of the alarm # don't do anything if this is not WARNING, CRITICAL or CLEAR if [ "${status}" != "WARNING" -a "${status}" != "CRITICAL" -a "${status}" != "CLEAR" ] then - echo >&2 "${me}: not sending notification for ${status} on '${chart}.${name}'" + info "not sending notification for ${status} of '${host}.${chart}.${name}'" exit 1 fi # don't do anything if this is CLEAR, but it was not WARNING or CRITICAL if [ "${old_status}" != "WARNING" -a "${old_status}" != "CRITICAL" -a "${status}" = "CLEAR" ] then - echo >&2 "${me}: not sending notification for ${status} on '${chart}.${name}' (last status was ${old_status})" + info "not sending notification for ${status} of '${host}.${chart}.${name}' (last status was ${old_status})" exit 1 fi # ----------------------------------------------------------------------------- # load configuration -# this is defined here so that private registries -# can setup their own -# images_base_url="${NETDATA_REGISTRY_URL}" +# By default fetch images from the global public registry. +# This is required by default, since all notification methods need to download +# images via the Internet, and private registries might not be reachable. +# This can be overwritten at the configuration file. images_base_url="https://registry.my-netdata.io" # needed commands @@ -77,25 +182,69 @@ sendmail= # enable / disable features SEND_SLACK="YES" +SEND_DISCORD="YES" SEND_PUSHOVER="YES" +SEND_TWILIO="YES" +SEND_HIPCHAT="YES" +SEND_MESSAGEBIRD="YES" SEND_TELEGRAM="YES" SEND_EMAIL="YES" +SEND_PUSHBULLET="YES" +SEND_KAFKA="YES" +SEND_PD="YES" # slack configs SLACK_WEBHOOK_URL= DEFAULT_RECIPIENT_SLACK= declare -A role_recipients_slack=() +# discord configs +DISCORD_WEBHOOK_URL= +DEFAULT_RECIPIENT_DISCORD= +declare -A role_recipients_discord=() + # pushover configs PUSHOVER_APP_TOKEN= DEFAULT_RECIPIENT_PUSHOVER= declare -A role_recipients_pushover=() +# pushbullet configs +PUSHBULLET_ACCESS_TOKEN= +DEFAULT_RECIPIENT_PUSHBULLET= +declare -A role_recipients_pushbullet=() + +# twilio configs +TWILIO_ACCOUNT_SID= +TWILIO_ACCOUNT_TOKEN= +TWILIO_NUMBER= +DEFAULT_RECIPIENT_TWILIO= +declare -A role_recipients_twilio=() + +# hipchat configs +HIPCHAT_SERVER= +HIPCHAT_AUTH_TOKEN= +DEFAULT_RECIPIENT_HIPCHAT= +declare -A role_recipients_hipchat=() + +# messagebird configs +MESSAGEBIRD_ACCESS_KEY= +MESSAGEBIRD_NUMBER= +DEFAULT_RECIPIENT_MESSAGEBIRD= +declare -A role_recipients_messagebird=() + # telegram configs TELEGRAM_BOT_TOKEN= DEFAULT_RECIPIENT_TELEGRAM= declare -A role_recipients_telegram=() +# kafka configs +KAFKA_URL= +KAFKA_SENDER_IP= + +# pagerduty.com configs +PD_SERVICE_KEY= +declare -A role_recipients_pd=() + # email configs DEFAULT_RECIPIENT_EMAIL="root" declare -A role_recipients_email=() @@ -108,14 +257,14 @@ if [ -f "${NETDATA_CONFIG_DIR}/health_alarm_notify.conf" ] fi # ----------------------------------------------------------------------------- -# filter recipients based on the criticality of each +# filter a recipient based on alarm event severity filter_recipient_by_criticality() { local method="${1}" x="${2}" r s shift - r="${x/|*/}" - s="${x/*|/}" + r="${x/|*/}" # the recipient + s="${x/*|/}" # the severity required for notifying this recipient # no severity filtering for this person [ "${r}" = "${s}" ] && return 0 @@ -148,22 +297,28 @@ filter_recipient_by_criticality() { } # ----------------------------------------------------------------------------- -# find the recipient's addresses per method +# find the recipients' addresses per method declare -A arr_slack=() +declare -A arr_discord=() declare -A arr_pushover=() +declare -A arr_pushbullet=() +declare -A arr_twilio=() +declare -A arr_hipchat=() declare -A arr_telegram=() +declare -A arr_pd=() declare -A arr_email=() -# netdata may call us with multiple recipients -# so, here we find the unique ones -for x in ${recipient//,/ } +# netdata may call us with multiple roles, and roles may have multiple but +# overlapping recipients - so, here we find the unique recipients. +for x in ${roles//,/ } do - # the recipient 'silent' means, don't send a notification for this event - [ "${x}" = "silent" ] && continue + # the roles 'silent' and 'disabled' mean: + # don't send a notification for this role + [ "${x}" = "silent" -o "${x}" = "disabled" ] && continue # email - a="${role_recipients_email[${recipient}]}" + a="${role_recipients_email[${x}]}" [ -z "${a}" ] && a="${DEFAULT_RECIPIENT_EMAIL}" for r in ${a//,/ } do @@ -171,15 +326,47 @@ do done # pushover - a="${role_recipients_pushover[${recipient}]}" + a="${role_recipients_pushover[${x}]}" [ -z "${a}" ] && a="${DEFAULT_RECIPIENT_PUSHOVER}" for r in ${a//,/ } do [ "${r}" != "disabled" ] && filter_recipient_by_criticality pushover "${r}" && arr_pushover[${r/|*/}]="1" done + # pushbullet + a="${role_recipients_pushbullet[${x}]}" + [ -z "${a}" ] && a="${DEFAULT_RECIPIENT_PUSHBULLET}" + for r in ${a//,/ } + do + [ "${r}" != "disabled" ] && filter_recipient_by_criticality pushbullet "${r}" && arr_pushbullet[${r/|*/}]="1" + done + + # twilio + a="${role_recipients_twilio[${x}]}" + [ -z "${a}" ] && a="${DEFAULT_RECIPIENT_TWILIO}" + for r in ${a//,/ } + do + [ "${r}" != "disabled" ] && filter_recipient_by_criticality twilio "${r}" && arr_twilio[${r/|*/}]="1" + done + + # hipchat + a="${role_recipients_hipchat[${x}]}" + [ -z "${a}" ] && a="${DEFAULT_RECIPIENT_HIPCHAT}" + for r in ${a//,/ } + do + [ "${r}" != "disabled" ] && filter_recipient_by_criticality hipchat "${r}" && arr_hipchat[${r/|*/}]="1" + done + + # messagebird + a="${role_recipients_messagebird[${x}]}" + [ -z "${a}" ] && a="${DEFAULT_RECIPIENT_MESSAGEBIRD}" + for r in ${a//,/ } + do + [ "${r}" != "disabled" ] && filter_recipient_by_criticality messagebird "${r}" && arr_messagebird[${r/|*/}]="1" + done + # telegram - a="${role_recipients_telegram[${recipient}]}" + a="${role_recipients_telegram[${x}]}" [ -z "${a}" ] && a="${DEFAULT_RECIPIENT_TELEGRAM}" for r in ${a//,/ } do @@ -187,26 +374,66 @@ do done # slack - a="${role_recipients_slack[${recipient}]}" + a="${role_recipients_slack[${x}]}" [ -z "${a}" ] && a="${DEFAULT_RECIPIENT_SLACK}" for r in ${a//,/ } do [ "${r}" != "disabled" ] && filter_recipient_by_criticality slack "${r}" && arr_slack[${r/|*/}]="1" done + + # discord + a="${role_recipients_discord[${x}]}" + [ -z "${a}" ] && a="${DEFAULT_RECIPIENT_DISCORD}" + for r in ${a//,/ } + do + [ "${r}" != "disabled" ] && filter_recipient_by_criticality discord "${r}" && arr_discord[${r/|*/}]="1" + done + + # pagerduty.com + a="${role_recipients_pd[${x}]}" + [ -z "${a}" ] && a="${DEFAULT_RECIPIENT_PD}" + for r in ${a//,/ } + do + [ "${r}" != "disabled" ] && filter_recipient_by_criticality pd "${r}" && arr_pd[${r/|*/}]="1" + done done # build the list of slack recipients (channels) to_slack="${!arr_slack[*]}" [ -z "${to_slack}" ] && SEND_SLACK="NO" +# build the list of discord recipients (channels) +to_discord="${!arr_discord[*]}" +[ -z "${to_discord}" ] && SEND_DISCORD="NO" + # build the list of pushover recipients (user tokens) to_pushover="${!arr_pushover[*]}" [ -z "${to_pushover}" ] && SEND_PUSHOVER="NO" +# build the list of pushbulet recipients (user tokens) +to_pushbullet="${!arr_pushbullet[*]}" +[ -z "${to_pushbullet}" ] && SEND_PUSHBULLET="NO" + +# build the list of twilio recipients (phone numbers) +to_twilio="${!arr_twilio[*]}" +[ -z "${to_twilio}" ] && SEND_TWILIO="NO" + +# build the list of hipchat recipients (rooms) +to_hipchat="${!arr_hipchat[*]}" +[ -z "${to_hipchat}" ] && SEND_HIPCHAT="NO" + +# build the list of messagebird recipients (phone numbers) +to_messagebird="${!arr_messagebird[*]}" +[ -z "${to_messagebird}" ] && SEND_MESSAGEBIRD="NO" + # check array of telegram recipients (chat ids) to_telegram="${!arr_telegram[*]}" [ -z "${to_telegram}" ] && SEND_TELEGRAM="NO" +# build the list of pagerduty recipients (service keys) +to_pd="${!arr_pd[*]}" +[ -z "${to_pd}" ] && SEND_PD="NO" + # build the list of email recipients (email addresses) to_email= for x in "${!arr_email[@]}" @@ -223,23 +450,75 @@ done # check slack [ -z "${SLACK_WEBHOOK_URL}" ] && SEND_SLACK="NO" +# check discord +[ -z "${DISCORD_WEBHOOK_URL}" ] && SEND_DISCORD="NO" + # check pushover [ -z "${PUSHOVER_APP_TOKEN}" ] && SEND_PUSHOVER="NO" +# check pushbullet +[ -z "${PUSHBULLET_ACCESS_TOKEN}" ] && SEND_PUSHBULLET="NO" + +# check twilio +[ -z "${TWILIO_ACCOUNT_TOKEN}" -o -z "${TWILIO_ACCOUNT_SID}" -o -z "${TWILIO_NUMBER}" ] && SEND_TWILIO="NO" + +# check hipchat +[ -z "${HIPCHAT_AUTH_TOKEN}" ] && SEND_HIPCHAT="NO" + +# check messagebird +[ -z "${MESSAGEBIRD_ACCESS_KEY}" -o -z "${MESSAGEBIRD_NUMBER}" ] && SEND_MESSAGEBIRD="NO" + # check telegram [ -z "${TELEGRAM_BOT_TOKEN}" ] && SEND_TELEGRAM="NO" -if [ \( "${SEND_PUSHOVER}" = "YES" -o "${SEND_SLACK}" = "YES" -o "${SEND_TELEGRAM}" = "YES" \) -a -z "${curl}" ] +# check kafka +[ -z "${KAFKA_URL}" -o -z "${KAFKA_SENDER_IP}" ] && SEND_KAFKA="NO" + +# check pagerduty.com +# if we need pd-send, check for the pd-send command +# https://www.pagerduty.com/docs/guides/agent-install-guide/ +if [ "${SEND_PD}" = "YES" ] + then + pd_send="$(which pd-send 2>/dev/null || command -v pd-send 2>/dev/null)" + if [ -z "${pd_send}" ] + then + # no pd-send available + # disable pagerduty.com + SEND_PD="NO" + fi +fi + +# if we need curl, check for the curl command +if [ \( \ + "${SEND_PUSHOVER}" = "YES" \ + -o "${SEND_SLACK}" = "YES" \ + -o "${SEND_DISCORD}" = "YES" \ + -o "${SEND_HIPCHAT}" = "YES" \ + -o "${SEND_TWILIO}" = "YES" \ + -o "${SEND_MESSAGEBIRD}" = "YES" \ + -o "${SEND_TELEGRAM}" = "YES" \ + -o "${SEND_PUSHBULLET}" = "YES" \ + -o "${SEND_KAFKA}" = "YES" \ + \) -a -z "${curl}" ] then curl="$(which curl 2>/dev/null || command -v curl 2>/dev/null)" if [ -z "${curl}" ] then + # no curl available + # disable all curl based methods SEND_PUSHOVER="NO" + SEND_PUSHBULLET="NO" SEND_TELEGRAM="NO" SEND_SLACK="NO" + SEND_DISCORD="NO" + SEND_TWILIO="NO" + SEND_HIPCHAT="NO" + SEND_MESSAGEBIRD="NO" + SEND_KAFKA="NO" fi fi +# if we need sendmail, check for the sendmail command if [ "${SEND_EMAIL}" = "YES" -a -z "${sendmail}" ] then sendmail="$(which sendmail 2>/dev/null || command -v sendmail 2>/dev/null)" @@ -247,19 +526,22 @@ if [ "${SEND_EMAIL}" = "YES" -a -z "${sendmail}" ] fi # check that we have at least a method enabled -if [ "${SEND_EMAIL}" != "YES" -a "${SEND_PUSHOVER}" != "YES" -a "${SEND_TELEGRAM}" != "YES" -a "${SEND_SLACK}" != "YES" ] +if [ "${SEND_EMAIL}" != "YES" \ + -a "${SEND_PUSHOVER}" != "YES" \ + -a "${SEND_TELEGRAM}" != "YES" \ + -a "${SEND_SLACK}" != "YES" \ + -a "${SEND_DISCORD}" != "YES" \ + -a "${SEND_TWILIO}" != "YES" \ + -a "${SEND_HIPCHAT}" != "YES" \ + -a "${SEND_MESSAGEBIRD}" != "YES" \ + -a "${SEND_PUSHBULLET}" != "YES" \ + -a "${SEND_KAFKA}" != "YES" \ + -a "${SEND_PD}" != "YES" \ + ] then - echo >&2 "All notification methods are disabled. Not sending a notification." - exit 1 + fatal "All notification methods are disabled. Not sending notification for host '${host}', chart '${chart}' to '${roles}' for '${name}' = '${value}' for status '${status}'." fi -# ----------------------------------------------------------------------------- -# get the system hostname - -[ -z "${host}" ] && host="${NETDATA_HOSTNAME}" -[ -z "${host}" ] && host="${NETDATA_REGISTRY_HOSTNAME}" -[ -z "${host}" ] && host="$(hostname 2>/dev/null)" - # ----------------------------------------------------------------------------- # get the date the alarm happened @@ -267,7 +549,7 @@ date="$(date --date=@${when} 2>/dev/null)" [ -z "${date}" ] && date="$(date 2>/dev/null)" # ----------------------------------------------------------------------------- -# URL encode a string +# function to URL encode a string urlencode() { local string="${1}" strlen encoded pos c o @@ -275,14 +557,14 @@ urlencode() { strlen=${#string} for (( pos=0 ; pos&2 "${me}: Sent email notification for: ${host} ${chart}.${name} is ${status} to '${to_email}'" + info "sent email notification for: ${host} ${chart}.${name} is ${status} to '${to_email}'" return 0 else - echo >&2 "${me}: Failed to send email notification for: ${host} ${chart}.${name} is ${status} to '${to_email}' with error code ${ret}." + error "failed to send email notification for: ${host} ${chart}.${name} is ${status} to '${to_email}' with error code ${ret}." return 1 fi fi @@ -404,10 +686,46 @@ send_pushover() { if [ "${httpcode}" == "200" ] then - echo >&2 "${me}: Sent pushover notification for: ${host} ${chart}.${name} is ${status} to '${user}'" + info "sent pushover notification for: ${host} ${chart}.${name} is ${status} to '${user}'" + sent=$((sent + 1)) + else + error "failed to send pushover notification for: ${host} ${chart}.${name} is ${status} to '${user}' with HTTP error code ${httpcode}." + fi + done + + [ ${sent} -gt 0 ] && return 0 + fi + + return 1 +} + +# ----------------------------------------------------------------------------- +# pushbullet sender + +send_pushbullet() { + local userapikey="${1}" recipients="${2}" title="${3}" message="${4}" httpcode sent=0 user + if [ "${SEND_PUSHBULLET}" = "YES" -a ! -z "${userapikey}" -a ! -z "${recipients}" -a ! -z "${message}" -a ! -z "${title}" ] + then + #https://docs.pushbullet.com/#create-push + for user in ${recipients} + do + httpcode=$(${curl} --write-out %{http_code} --silent --output /dev/null \ + --header 'Access-Token: '${userapikey}'' \ + --header 'Content-Type: application/json' \ + --data-binary @<(cat <&2 "${me}: Failed to send pushover notification for: ${host} ${chart}.${name} is ${status} to '${user}' with HTTP error code ${httpcode}." + error "failed to send pushbullet notification for: ${host} ${chart}.${name} is ${status} to '${user}' with HTTP error code ${httpcode}." fi done @@ -417,6 +735,205 @@ send_pushover() { return 1 } +# ----------------------------------------------------------------------------- +# kafka sender + +send_kafka() { + local httpcode sent=0 + if [ "${SEND_KAFKA}" = "YES" ] + then + httpcode=$(${curl} -X POST --write-out %{http_code} --silent --output /dev/null \ + --data "{host_ip:\"${KAFKA_SENDER_IP}\",when:${when},name:\"${name}\",chart:\"${chart}\",family:\"${family}\",status:\"${status}\",old_status:\"${old_status}\",value:${value},old_value:${old_value},duration:${duration},non_clear_duration:${non_clear_duration},units:\"${units}\",info:\"${info}\"}" \ + "${KAFKA_URL}") + + if [ "${httpcode}" == "204" ] + then + info "sent kafka data for: ${host} ${chart}.${name} is ${status} and ip '${KAFKA_SENDER_IP}'" + sent=$((sent + 1)) + else + error "failed to send kafka data for: ${host} ${chart}.${name} is ${status} and ip '${KAFKA_SENDER_IP}' with HTTP error code ${httpcode}." + fi + + [ ${sent} -gt 0 ] && return 0 + fi + + return 1 +} + +# ----------------------------------------------------------------------------- +# pagerduty.com sender + +send_pd() { + local recipients="${1}" sent=0 + unset t + case ${status} in + CLEAR) t='resolve';; + WARNING) t='trigger';; + CRITICAL) t='trigger';; + esac + + if [ ${SEND_PD} = "YES" -a ! -z "${t}" ] + then + for PD_SERVICE_KEY in ${recipients} + do + d="${status} ${name} = ${value_string} - ${host}, ${family}" + ${pd_send} -k ${PD_SERVICE_KEY} \ + -t ${t} \ + -d "${d}" \ + -i ${alarm_id} \ + -f 'info'="${info}" \ + -f 'value_w_units'="${value_string}" \ + -f 'when'="${when}" \ + -f 'duration'="${duration}" \ + -f 'roles'="${roles}" \ + -f 'host'="${host}" \ + -f 'unique_id'="${unique_id}" \ + -f 'alarm_id'="${alarm_id}" \ + -f 'event_id'="${event_id}" \ + -f 'name'="${name}" \ + -f 'chart'="${chart}" \ + -f 'family'="${family}" \ + -f 'status'="${status}" \ + -f 'old_status'="${old_status}" \ + -f 'value'="${value}" \ + -f 'old_value'="${old_value}" \ + -f 'src'="${src}" \ + -f 'non_clear_duration'="${non_clear_duration}" \ + -f 'units'="${units}" + retval=$? + if [ ${retval} -eq 0 ] + then + info "sent pagerduty.com notification for host ${host} ${chart}.${name} using service key ${PD_SERVICE_KEY::-26}....: ${d}" + sent=$((sent + 1)) + else + error "failed to send pagerduty.com notification for ${host} ${chart}.${name} using service key ${PD_SERVICE_KEY::-26}.... (error code ${retval}): ${d}" + fi + done + + [ ${sent} -gt 0 ] && return 0 + fi + + return 1 +} + +# ----------------------------------------------------------------------------- +# twilio sender + +send_twilio() { + local accountsid="${1}" accounttoken="${2}" twilionumber="${3}" recipients="${4}" title="${5}" message="${6}" httpcode sent=0 user + if [ "${SEND_TWILIO}" = "YES" -a ! -z "${accountsid}" -a ! -z "${accounttoken}" -a ! -z "${twilionumber}" -a ! -z "${recipients}" -a ! -z "${message}" -a ! -z "${title}" ] + then + #https://www.twilio.com/packages/labs/code/bash/twilio-sms + for user in ${recipients} + do + httpcode=$(${curl} -X POST --write-out %{http_code} --silent --output /dev/null \ + --data-urlencode "From=${twilionumber}" \ + --data-urlencode "To=${user}" \ + --data-urlencode "Body=${title} ${message}" \ + -u "${accountsid}:${accounttoken}" \ + "https://api.twilio.com/2010-04-01/Accounts/${accountsid}/Messages.json") + + if [ "${httpcode}" == "201" ] + then + info "sent Twilio SMS for: ${host} ${chart}.${name} is ${status} to '${user}'" + sent=$((sent + 1)) + else + error "failed to send Twilio SMS for: ${host} ${chart}.${name} is ${status} to '${user}' with HTTP error code ${httpcode}." + fi + done + + [ ${sent} -gt 0 ] && return 0 + fi + + return 1 +} + + +# ----------------------------------------------------------------------------- +# hipchat sender + +send_hipchat() { + local authtoken="${1}" recipients="${2}" message="${3}" httpcode sent=0 room color sender msg_format notify + + if [ "${SEND_HIPCHAT}" = "YES" -a ! -z "${HIPCHAT_SERVER}" -a ! -z "${authtoken}" -a ! -z "${recipients}" -a ! -z "${message}" ] + then + # A label to be shown in addition to the sender's name + # Valid length range: 0 - 64. + sender="netdata" + + # Valid values: html, text. + # Defaults to 'html'. + msg_format="html" + + # Background color for message. Valid values: yellow, green, red, purple, gray, random. Defaults to 'yellow'. + case "${status}" in + WARNING) color="yellow" ;; + CRITICAL) color="red" ;; + CLEAR) color="green" ;; + *) color="gray" ;; + esac + + # Whether this message should trigger a user notification (change the tab color, play a sound, notify mobile phones, etc). + # Each recipient's notification preferences are taken into account. + # Defaults to false. + notify="true" + + for room in ${recipients} + do + httpcode=$(${curl} -X POST --write-out %{http_code} --silent --output /dev/null \ + -H "Content-type: application/json" \ + -H "Authorization: Bearer ${authtoken}" \ + -d "{\"color\": \"${color}\", \"from\": \"${netdata}\", \"message_format\": \"${msg_format}\", \"message\": \"${message}\", \"notify\": \"${notify}\"}" \ + "https://${HIPCHAT_SERVER}/v2/room/${room}/notification") + + if [ "${httpcode}" == "204" ] + then + info "sent HipChat notification for: ${host} ${chart}.${name} is ${status} to '${room}'" + sent=$((sent + 1)) + else + error "failed to send HipChat notification for: ${host} ${chart}.${name} is ${status} to '${room}' with HTTP error code ${httpcode}." + fi + done + + [ ${sent} -gt 0 ] && return 0 + fi + + return 1 +} + + +# ----------------------------------------------------------------------------- +# messagebird sender + +send_messagebird() { + local accesskey="${1}" messagebirdnumber="${2}" recipients="${3}" title="${4}" message="${5}" httpcode sent=0 user + if [ "${SEND_MESSAGEBIRD}" = "YES" -a ! -z "${accesskey}" -a ! -z "${messagebirdnumber}" -a ! -z "${recipients}" -a ! -z "${message}" -a ! -z "${title}" ] + then + #https://developers.messagebird.com/docs/messaging + for user in ${recipients} + do + httpcode=$(${curl} -X POST --write-out %{http_code} --silent --output /dev/null \ + --data-urlencode "originator=${messagebirdnumber}" \ + --data-urlencode "recipients=${user}" \ + --data-urlencode "body=${title} ${message}" \ + --data-urlencode "datacoding=auto" \ + -H "Authorization: AccessKey ${accesskey}" \ + "https://rest.messagebird.com/messages") + + if [ "${httpcode}" == "201" ] + then + info "sent Messagebird SMS for: ${host} ${chart}.${name} is ${status} to '${user}'" + sent=$((sent + 1)) + else + error "failed to send Messagebird SMS for: ${host} ${chart}.${name} is ${status} to '${user}' with HTTP error code ${httpcode}." + fi + done + + [ ${sent} -gt 0 ] && return 0 + fi + + return 1 +} # ----------------------------------------------------------------------------- # telegram sender @@ -434,18 +951,18 @@ send_telegram() { httpcode=$(${curl} --write-out %{http_code} --silent --output /dev/null ${disableNotification} \ --data-urlencode "parse_mode=HTML" \ --data-urlencode "disable_web_page_preview=true" \ - --data-urlencode "text=$message" \ - "https://api.telegram.org/bot${bottoken}/sendMessage?chat_id=$chatid") + --data-urlencode "text=${message}" \ + "https://api.telegram.org/bot${bottoken}/sendMessage?chat_id=${chatid}") if [ "${httpcode}" == "200" ] then - echo >&2 "${me}: Sent telegram notification for: ${host} ${chart}.${name} is ${status} to '${chatid}'" + info "sent telegram notification for: ${host} ${chart}.${name} is ${status} to '${chatid}'" sent=$((sent + 1)) elif [ "${httpcode}" == "401" ] then - echo >&2 "${me}: Failed to send telegram notification for: ${host} ${chart}.${name} is ${status} to '${chatid}': Wrong bot token." + error "failed to send telegram notification for: ${host} ${chart}.${name} is ${status} to '${chatid}': Wrong bot token." else - echo >&2 "${me}: Failed to send telegram notification for: ${host} ${chart}.${name} is ${status} to '${chatid}' with HTTP error code ${httpcode}." + error "failed to send telegram notification for: ${host} ${chart}.${name} is ${status} to '${chatid}' with HTTP error code ${httpcode}." fi done @@ -464,10 +981,10 @@ send_slack() { [ "${SEND_SLACK}" != "YES" ] && return 1 case "${status}" in - WARNING) color="warning" ;; + WARNING) color="warning" ;; CRITICAL) color="danger" ;; - CLEAR) color="good" ;; - *) color="#777777" ;; + CLEAR) color="good" ;; + *) color="#777777" ;; esac for channel in ${channels} @@ -507,10 +1024,70 @@ EOF httpcode=$(${curl} --write-out %{http_code} --silent --output /dev/null -X POST --data-urlencode "payload=${payload}" "${webhook}") if [ "${httpcode}" == "200" ] then - echo >&2 "${me}: Sent slack notification for: ${host} ${chart}.${name} is ${status} to '${channel}'" + info "sent slack notification for: ${host} ${chart}.${name} is ${status} to '${channel}'" + sent=$((sent + 1)) + else + error "failed to send slack notification for: ${host} ${chart}.${name} is ${status} to '${channel}', with HTTP error code ${httpcode}." + fi + done + + [ ${sent} -gt 0 ] && return 0 + + return 1 +} + +# ----------------------------------------------------------------------------- +# discord sender + +send_discord() { + local webhook="${1}/slack" channels="${2}" httpcode sent=0 channel color payload + + [ "${SEND_DISCORD}" != "YES" ] && return 1 + + case "${status}" in + WARNING) color="warning" ;; + CRITICAL) color="danger" ;; + CLEAR) color="good" ;; + *) color="#777777" ;; + esac + + for channel in ${channels} + do + payload="$(cat <&2 "${me}: Failed to send slack notification for: ${host} ${chart}.${name} is ${status} to '${channel}', with HTTP error code ${httpcode}." + error "failed to send discord notification for: ${host} ${chart}.${name} is ${status} to '${channel}', with HTTP error code ${httpcode}." fi done @@ -545,7 +1122,7 @@ status_message="status unknown" color="grey" # the alarm value -alarm="${name//_/ } = ${value} ${units}" +alarm="${name//_/ } = ${value_string}" # the image of the alarm image="${images_base_url}/images/seo-performance-128.png" @@ -568,25 +1145,25 @@ case "${status}" in image="${images_base_url}/images/check-mark-2-128-green.png" status_message="recovered" color="#77ca6d" - - # don't show the value when the status is CLEAR - # for certain alarms, this value might not have any meaning - alarm="${name//_/ } ${raised_for}" ;; esac if [ "${status}" = "CLEAR" ] then severity="Recovered from ${old_status}" - if [ $non_clear_duration -gt $duration ] + if [ ${non_clear_duration} -gt ${duration} ] then raised_for="(alarm was raised for ${non_clear_duration_txt})" fi + # don't show the value when the status is CLEAR + # for certain alarms, this value might not have any meaning + alarm="${name//_/ } ${raised_for}" + elif [ "${old_status}" = "WARNING" -a "${status}" = "CRITICAL" ] then severity="Escalated to ${status}" - if [ $non_clear_duration -gt $duration ] + if [ ${non_clear_duration} -gt ${duration} ] then raised_for="(alarm is raised for ${non_clear_duration_txt})" fi @@ -594,7 +1171,7 @@ then elif [ "${old_status}" = "CRITICAL" -a "${status}" = "WARNING" ] then severity="Demoted to ${status}" - if [ $non_clear_duration -gt $duration ] + if [ ${non_clear_duration} -gt ${duration} ] then raised_for="(alarm is raised for ${non_clear_duration_txt})" fi @@ -619,6 +1196,15 @@ raised_for_html= send_slack "${SLACK_WEBHOOK_URL}" "${to_slack}" SENT_SLACK=$? +# ----------------------------------------------------------------------------- +# send the discord notification + +# discord aggregates posts from the same username +# so we use "${host} ${status}" as the bot username, to make them diff + +send_discord "${DISCORD_WEBHOOK_URL}" "${to_discord}" +SENT_DISCORD=$? + # ----------------------------------------------------------------------------- # send the pushover notification @@ -634,21 +1220,81 @@ send_pushover "${PUSHOVER_APP_TOKEN}" "${to_pushover}" "${when}" "${goto_url}" " SENT_PUSHOVER=$? +# ----------------------------------------------------------------------------- +# send the pushbullet notification + +send_pushbullet "${PUSHBULLET_ACCESS_TOKEN}" "${to_pushbullet}" "${host} ${status_message} - ${name//_/ } - ${chart}" "${alarm}\n +Severity: ${severity}\n +Chart: ${chart}\n +Family: ${family}\n +To View Netdata go to: ${goto_url}\n +The source of this alarm is line ${src}" + +SENT_PUSHBULLET=$? + +# ----------------------------------------------------------------------------- +# send the twilio SMS + +send_twilio "${TWILIO_ACCOUNT_SID}" "${TWILIO_ACCOUNT_TOKEN}" "${TWILIO_NUMBER}" "${to_twilio}" "${host} ${status_message} - ${name//_/ } - ${chart}" "${alarm} +Severity: ${severity} +Chart: ${chart} +Family: ${family} +${info}" + +SENT_TWILIO=$? + +# ----------------------------------------------------------------------------- +# send the messagebird SMS + +send_messagebird "${MESSAGEBIRD_ACCESS_KEY}" "${MESSAGEBIRD_NUMBER}" "${to_messagebird}" "${host} ${status_message} - ${name//_/ } - ${chart}" "${alarm} +Severity: ${severity} +Chart: ${chart} +Family: ${family} +${info}" + +SENT_MESSAGEBIRD=$? + + # ----------------------------------------------------------------------------- # send the telegram.org message # https://core.telegram.org/bots/api#formatting-options -telegram_message="${severity}" -[ "${status_message}" != "recovered" ] && telegram_message="${telegram_message}, ${status_message}" -telegram_message="${telegram_message} -${chart} (${family}) +send_telegram "${TELEGRAM_BOT_TOKEN}" "${to_telegram}" "${host} ${status_message} - ${name//_/ } +${chart} (${family}) ${alarm} ${info}" -send_telegram "${TELEGRAM_BOT_TOKEN}" "${to_telegram}" "${telegram_message}" - SENT_TELEGRAM=$? + +# ----------------------------------------------------------------------------- +# send the kafka message + +send_kafka +SENT_KAFKA=$? + + +# ----------------------------------------------------------------------------- +# send the pagerduty.com message + +send_pd "${to_pd}" +SENT_PD=$? + + +# ----------------------------------------------------------------------------- +# send hipchat message + +send_hipchat "${HIPCHAT_AUTH_TOKEN}" "${to_hipchat}" " \ +${host} ${status_message}
\ +${alarm} ${info_html}
\ +${chart} (family ${family})
\ +${date}${raised_for_html}
\ +View netdata dashboard \ +(source of alarm ${src}) \ +" + +SENT_HIPCHAT=$? + # ----------------------------------------------------------------------------- # send the email @@ -747,8 +1393,23 @@ SENT_EMAIL=$? # ----------------------------------------------------------------------------- # let netdata know -# we did send somehting -[ ${SENT_EMAIL} -eq 0 -o ${SENT_PUSHOVER} -eq 0 -o ${SENT_TELEGRAM} -eq 0 -o ${SENT_SLACK} -eq 0 ] && exit 0 +if [ ${SENT_EMAIL} -eq 0 \ + -o ${SENT_PUSHOVER} -eq 0 \ + -o ${SENT_TELEGRAM} -eq 0 \ + -o ${SENT_SLACK} -eq 0 \ + -o ${SENT_DISCORD} -eq 0 \ + -o ${SENT_TWILIO} -eq 0 \ + -o ${SENT_HIPCHAT} -eq 0 \ + -o ${SENT_MESSAGEBIRD} -eq 0 \ + -o ${SENT_PUSHBULLET} -eq 0 \ + -o ${SENT_KAFKA} -eq 0 \ + -o ${SENT_PD} -eq 0 \ + ] + then + # we did send something + exit 0 +fi # we did not send anything exit 1 +