ansible/roles/nagios_client/files/scripts/check_systemd_units

49 lines
1.1 KiB
Text
Raw Normal View History

2021-03-12 01:38:33 +01:00
#!/usr/bin/env bash
# Description : script to check the status of systemd units
# if they failed, try to restart the service once !!
# Author : Seddik Alaoui Ismaili
# Version : 1.0
# Exits code
warning_exit="1"
ok_exit="0"
# Unit list
unit_list=(pagure_ci
pagure_ev
pagure_fast_worker
pagure_loadjson
pagure_logcom
pagure_medium_worker
pagure_milter
pagure_mirror
pagure_slow_worker
pagure_webhook
pagure_worker
pagure_mirror_project_in.timer)
#Element's arrays
failed_array=()
active_array=()
# Check units's status
echo -e "here the lenght of array : ${#active_array[@]}"
for element in ${unit_list[@]}; do
status=$(systemctl status ${element} |grep -E "Active:" | awk '{ print $2 }')
if [ $status == failed ]; then
systemctl restart ${element} && active_array+=($element) || failed_array+=($element)
fi
done
# check the lenght of array and print result/exit code for nagios
if [ ${#failed_array[@]} -ne "0" ]; then
echo -e "WARNING - Failed systemd units after restart : ${failed_array[@]}"
exit ${warning_exit}
elif [ ${#failed_array[@]} -eq "0" ]; then
echo -e "OK - Systemd units are active"
exit ${ok_exit}
fi