40 lines
1.4 KiB
Text
40 lines
1.4 KiB
Text
|
#!/bin/bash
|
||
|
|
# phoenixd health check — managed by Ansible (roles/phoenixd)
|
||
|
|
#
|
||
|
|
# Asks the node whether it is healthy and records the answer in the exit code,
|
||
|
|
# which systemd keeps:
|
||
|
|
# systemctl is-failed {{ phoenixd_healthcheck_service_name }}.service
|
||
|
|
# That is a complete answer on its own. Reporting anywhere else is optional.
|
||
|
|
PUSH_URL="${HEALTHCHECK_PUSH_URL:-}"
|
||
|
|
export PHOENIX_DATADIR="{{ phoenixd_data_dir }}"
|
||
|
|
|
||
|
|
check_phoenixd() {
|
||
|
|
# Service must be active and the node must answer getinfo.
|
||
|
|
# phoenix-cli reads the api password from $PHOENIX_DATADIR/phoenix.conf,
|
||
|
|
# but not the bind address, so pass it explicitly.
|
||
|
|
systemctl is-active --quiet phoenixd && \
|
||
|
|
{{ phoenixd_bin_dir }}/phoenix-cli \
|
||
|
|
--http-bind-ip {{ phoenixd_http_bind_ip }} \
|
||
|
|
--http-bind-port {{ phoenixd_http_bind_port }} \
|
||
|
|
getinfo 2>/dev/null | grep -q '"nodeId"'
|
||
|
|
}
|
||
|
|
|
||
|
|
report() {
|
||
|
|
local status=$1 msg=$2
|
||
|
|
# No push URL configured is NORMAL, not an error: the exit code below still
|
||
|
|
# answers the question. The previous version logged ERROR here on every
|
||
|
|
# single fire, once a minute, which is noise that trains you to ignore it.
|
||
|
|
[ -n "$PUSH_URL" ] || return 0
|
||
|
|
curl -s --max-time 10 --retry 2 -o /dev/null \
|
||
|
|
"${PUSH_URL}?status=${status}&msg=${msg// /%20}&ping=" || true
|
||
|
|
}
|
||
|
|
|
||
|
|
if check_phoenixd; then
|
||
|
|
report "up" "OK"
|
||
|
|
exit 0
|
||
|
|
else
|
||
|
|
echo "phoenixd is not responding"
|
||
|
|
report "down" "phoenixd not responding"
|
||
|
|
exit 1
|
||
|
|
fi
|