X-Git-Url: https://arthur.barton.de/gitweb/?a=blobdiff_plain;f=plugins.d%2Falarm-notify.sh;h=d0188fe3b11b5361810b62a791ece461f43d6d49;hb=8679670bdbe3c5928ec2e266d9c72e1a758fdf37;hp=17b009c965a0c7ad46d0b9993a96d7307786dd67;hpb=170a18bcc85dbd5437ab9d3e009617ce0ded65ce;p=netdata.git diff --git a/plugins.d/alarm-notify.sh b/plugins.d/alarm-notify.sh index 17b009c9..d0188fe3 100755 --- a/plugins.d/alarm-notify.sh +++ b/plugins.d/alarm-notify.sh @@ -14,13 +14,17 @@ # - severity filtering per recipient # # Supported notification methods: -# - emails -# - slack.com notifications -# - pushover.net notifications +# - 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 +# - 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 # ----------------------------------------------------------------------------- # testing notifications @@ -43,7 +47,7 @@ then 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 $((0 + id)) "units" "this is a test alarm to verify notifications work" + "${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 [ $? -ne 0 ] then echo >&2 "# FAILED" @@ -135,6 +139,15 @@ duration="${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="$(hostname 2>/dev/null)" # ----------------------------------------------------------------------------- # screen statuses we don't need to send a notification @@ -142,14 +155,14 @@ info="${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 - info "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 - info "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 ${old_status})" exit 1 fi @@ -169,18 +182,27 @@ sendmail= # enable / disable features SEND_SLACK="YES" +SEND_DISCORD="YES" SEND_PUSHOVER="YES" SEND_TWILIO="YES" +SEND_HIPCHAT="YES" +SEND_MESSAGEBIRD="YES" SEND_TELEGRAM="YES" SEND_EMAIL="YES" SEND_PUSHBULLET="YES" SEND_KAFKA="YES" +SEND_PD="YES" # slack configs SLACK_WEBHOOK_URL= DEFAULT_RECIPIENT_SLACK= declare -A role_recipients_slack=() +# discord configs +DISCORD_WEBHOOK_URL= +DEFAULT_RECIPIENT_DISCORD= +declare -A role_recipients_discord=() + # pushover configs PUSHOVER_APP_TOKEN= DEFAULT_RECIPIENT_PUSHOVER= @@ -198,6 +220,18 @@ TWILIO_NUMBER= DEFAULT_RECIPIENT_TWILIO= declare -A role_recipients_twilio=() +# hipchat configs +HIPCHAT_SERVER= +HIPCHAT_AUTH_TOKEN= +DEFAULT_RECIPIENT_HIPCHAT= +declare -A role_recipients_hipchat=() + +# messagebird configs +MESSAGEBIRD_ACCESS_KEY= +MESSAGEBIRD_NUMBER= +DEFAULT_RECIPIENT_MESSAGEBIRD= +declare -A role_recipients_messagebird=() + # telegram configs TELEGRAM_BOT_TOKEN= DEFAULT_RECIPIENT_TELEGRAM= @@ -207,6 +241,10 @@ declare -A role_recipients_telegram=() KAFKA_URL= KAFKA_SENDER_IP= +# pagerduty.com configs +PD_SERVICE_KEY= +declare -A role_recipients_pd=() + # email configs DEFAULT_RECIPIENT_EMAIL="root" declare -A role_recipients_email=() @@ -262,10 +300,13 @@ filter_recipient_by_criticality() { # find the recipients' addresses per method declare -A arr_slack=() +declare -A arr_discord=() declare -A arr_pushover=() declare -A arr_pushbullet=() declare -A arr_twilio=() +declare -A arr_hipchat=() declare -A arr_telegram=() +declare -A arr_pd=() declare -A arr_email=() # netdata may call us with multiple roles, and roles may have multiple but @@ -308,6 +349,22 @@ do [ "${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="${role_recipients_telegram[${x}]}" [ -z "${a}" ] && a="${DEFAULT_RECIPIENT_TELEGRAM}" @@ -323,12 +380,32 @@ do 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" @@ -341,10 +418,22 @@ to_pushbullet="${!arr_pushbullet[*]}" to_twilio="${!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[@]}" @@ -361,6 +450,9 @@ done # check slack [ -z "${SLACK_WEBHOOK_URL}" ] && SEND_SLACK="NO" +# check discord +[ -z "${DISCORD_WEBHOOK_URL}" ] && SEND_DISCORD="NO" + # check pushover [ -z "${PUSHOVER_APP_TOKEN}" ] && SEND_PUSHOVER="NO" @@ -370,14 +462,44 @@ done # check twilio [ -z "${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" # 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 [ \( "${SEND_PUSHOVER}" = "YES" -o "${SEND_SLACK}" = "YES" -o "${SEND_TWILIO}" = "YES" -o "${SEND_TELEGRAM}" = "YES" -o "${SEND_PUSHBULLET}" = "YES" -o "${SEND_KAFKA}" = "YES" \) -a -z "${curl}" ] +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}" ] @@ -388,7 +510,10 @@ if [ \( "${SEND_PUSHOVER}" = "YES" -o "${SEND_SLACK}" = "YES" -o "${SEND_TWILIO} SEND_PUSHBULLET="NO" SEND_TELEGRAM="NO" SEND_SLACK="NO" + SEND_DISCORD="NO" SEND_TWILIO="NO" + SEND_HIPCHAT="NO" + SEND_MESSAGEBIRD="NO" SEND_KAFKA="NO" fi fi @@ -401,25 +526,22 @@ if [ "${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 "${SEND_SLACK}" != "YES" \ - -a "${SEND_TWILIO}" != "YES" \ - -a "${SEND_PUSHBULLET}" != "YES" \ - -a "${SEND_KAFKA}" != "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 "${SEND_PD}" != "YES" \ ] then - fatal "All notification methods are disabled. Not sending notification to '${role}' for '${name}' = '${value}' of chart '${chart}' for status '${status}'." + fatal "All notification methods are disabled. Not sending notification for host '${host}', chart '${chart}' to '${roles}' for '${name}' = '${value}' for status '${status}'." fi -# ----------------------------------------------------------------------------- -# 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)" - # ----------------------------------------------------------------------------- # get the date the alarm happened @@ -638,6 +760,62 @@ send_kafka() { 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 + + [ ${sent} -gt 0 ] && return 0 + fi + + return 1 +} + # ----------------------------------------------------------------------------- # twilio sender @@ -670,6 +848,93 @@ send_twilio() { return 1 } + +# ----------------------------------------------------------------------------- +# hipchat sender + +send_hipchat() { + local authtoken="${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 + + [ ${sent} -gt 0 ] && return 0 + fi + + return 1 +} + # ----------------------------------------------------------------------------- # telegram sender @@ -771,6 +1036,66 @@ EOF return 1 } +# ----------------------------------------------------------------------------- +# discord sender + +send_discord() { + local webhook="${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 < \ +${alarm} ${info_html}
\ +${chart} (family ${family})
\ +${date}${raised_for_html}
\ +View netdata dashboard \ +(source of alarm ${src}) \ +" + +SENT_HIPCHAT=$? + # ----------------------------------------------------------------------------- # send the email @@ -1026,13 +1393,17 @@ SENT_EMAIL=$? # ----------------------------------------------------------------------------- # let netdata know -if [ ${SENT_EMAIL} -eq 0 \ - -o ${SENT_PUSHOVER} -eq 0 \ - -o ${SENT_TELEGRAM} -eq 0 \ - -o ${SENT_SLACK} -eq 0 \ - -o ${SENT_TWILIO} -eq 0 \ - -o ${SENT_PUSHBULLET} -eq 0 \ - -o ${SENT_KAFKA} -eq 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 @@ -1041,3 +1412,4 @@ fi # we did not send anything exit 1 +