- id: "41x0aldpro000101" name: '[ALD-Pro] Непредвиденная остановка сервиса {{index .Labels "name"}} на контроллере {{.Host}}' description: '[ALD-Pro] Непредвиденная остановка сервиса {{index .Labels "name"}} на контроллере {{.Host}}' query: 'share_eq_over_time(systemd_unit_state_id{name=~"chrony.service|aldpro-mp-services.service|rabbitmq-server.service|celery.service|salt-master.service|krb5-kdc.service|ipa-custodia.service|apache2.service|dirsrv@.*|bind9.*.service|krb5-admin.*.service|ipa-dnskeysyncd.service", product="ald-pro", component="controller"}[5m], 1) * 100' object_tag: "hostname" labels: integration: aldpro aggregator: sum group_by: - "hostname" step: 5m rate: 60s metric_ttl: 168h no_data_mode: "No data" rules: - id: "42x0aldpro000101" labels_required: labels_absent: type: "threshold_1level_asym" parameters: alert: "85" recovery: "100" reverse: "true" critical: "true" priority: 1 - id: "41x0aldpro000201" name: '[ALD-Pro] Непредвиденная остановка сокета {{index .Labels "name"}} на контроллере {{.Host}}' description: '[ALD-Pro] Непредвиденная остановка сокета {{index .Labels "name"}} на контроллере {{.Host}}' query: 'share_eq_over_time(systemd_unit_state_id{name=~"ipa-otpd.socket", product="ald-pro", component="controller"}[5m], 8) * 100' object_tag: "hostname" labels: integration: aldpro aggregator: sum group_by: - "hostname" step: 5m rate: 60s metric_ttl: 168h no_data_mode: "No data" rules: - id: "42x0aldpro000201" labels_required: labels_absent: type: "threshold_1level_asym" parameters: alert: "85" critical: "true" recovery: "100" reverse: "true" priority: 1 - id: "41x0aldpro000301" name: '[ALD-Pro] Через 30 дней истечет ldap сертификат на контроллере {{.Host}}' description: '[ALD-Pro] Через 30 дней истечет ldap сертификат на контроллере {{.Host}}' query: 'ald_ldap_cert_exp_check{product="ald-pro", component="controller"} - now()' object_tag: "hostname" labels: integration: aldpro aggregator: sum group_by: - "hostname" step: 5m rate: 60s metric_ttl: 168h no_data_mode: "No data" rules: - id: "42x0aldpro000301" labels_required: labels_absent: type: "threshold_1level_sym" parameters: level: "2592000" critical: "false" reverse: "true" priority: 1 - id: "41x0aldpro000401" name: '[ALD-Pro] Через 10 дней истечет ldap сертификат на контроллере {{.Host}}' description: '[ALD-Pro] Через 10 дней истечет ldap сертификат на контроллере {{.Host}}' query: 'ald_ldap_cert_exp_check{product="ald-pro", component="controller"} - now()' object_tag: "hostname" labels: integration: aldpro aggregator: sum group_by: - "hostname" step: 5m rate: 60s metric_ttl: 168h no_data_mode: "No data" rules: - id: "42x0aldpro000401" labels_required: labels_absent: type: "threshold_1level_sym" parameters: level: "864000" critical: "false" reverse: "true" priority: 1 - id: "41x0aldpro000501" name: '[ALD-Pro] Истек срок действия ldap сертификата на контроллере {{.Host}} ' description: '[ALD-Pro] Истек срок действия ldap сертификата на контроллере {{.Host}}' query: 'ald_ldap_cert_exp_check{product="ald-pro", component="controller"} - now()' object_tag: "hostname" labels: integration: aldpro aggregator: sum group_by: - "hostname" step: 5m rate: 60s metric_ttl: 168h no_data_mode: "No data" rules: - id: "42x0aldpro000501" labels_required: labels_absent: type: "threshold_1level_sym" parameters: level: "0" critical: "true" reverse: "true" priority: 1 - id: "41x0aldpro000601" name: '[ALD-Pro] Через 30 дней истечет web сертификат на контроллере {{.Host}}' description: '[ALD-Pro] Через 30 дней истечет web сертификат на контроллере {{.Host}}' query: 'ald_web_cert_exp_check{product="ald-pro", component="controller"} - now()' object_tag: "hostname" labels: integration: aldpro aggregator: sum group_by: - "hostname" step: 5m rate: 60s metric_ttl: 168h no_data_mode: "No data" rules: - id: "42x0aldpro000601" labels_required: labels_absent: type: "threshold_1level_sym" parameters: level: "2592000" critical: "false" reverse: "true" priority: 1 - id: "41x0aldpro000701" name: '[ALD-Pro] Через 10 дней истечет web сертификат на контроллере {{.Host}}' description: '[ALD-Pro] Через 10 дней истечет web сертификат на контроллере {{.Host}}' query: 'ald_web_cert_exp_check{product="ald-pro", component="controller"} - now()' object_tag: "hostname" labels: integration: aldpro aggregator: sum group_by: - "hostname" step: 5m rate: 60s metric_ttl: 168h no_data_mode: "No data" rules: - id: "42x0aldpro000701" labels_required: labels_absent: type: "threshold_1level_sym" parameters: level: "864000" critical: "false" reverse: "true" priority: 1 - id: "41x0aldpro000801" name: '[ALD-Pro] Истек срок действия web сертификата на контроллере {{.Host}} ' description: '[ALD-Pro] Истек срок действия web сертификата на контроллере {{.Host}}' query: 'ald_web_cert_exp_check{product="ald-pro", component="controller"} - now()' object_tag: "hostname" group_by: - "hostname" step: 5m rate: 60s metric_ttl: 168h no_data_mode: "No data" rules: - id: "42x0aldpro000801" labels_required: labels_absent: type: "threshold_1level_sym" parameters: level: "0" critical: "true" reverse: "true" priority: 1 - id: "41x0aldpro000901" name: '[ALD-Pro] Непредвиденная остановка сервиса {{index .Labels "name"}} на DHCP сервере {{.Host}}' description: '[ALD-Pro] Непредвиденная остановка сервиса {{index .Labels "name"}} на DHCP сервере {{.Host}}' query: 'share_eq_over_time(systemd_unit_state_id{name=~"isc-dhcp-server.service", product="ald-pro", component="dhcp"}[5m], 1) * 100' object_tag: "hostname" group_by: - "hostname" step: 5m rate: 60s metric_ttl: 168h no_data_mode: "No data" rules: - id: "42x0aldpro000901" labels_required: labels_absent: type: "threshold_1level_asym" parameters: alert: "85" recovery: "100" reverse: "true" critical: "true" priority: 1 - id: "41x0aldpro001001" name: '[ALD-Pro] Непредвиденная остановка сервиса {{index .Labels "name"}} на Filesharing сервере {{.Host}}' description: '[ALD-Pro] Непредвиденная остановка сервиса {{index .Labels "name"}} на Filesharing сервере {{.Host}}' query: 'share_eq_over_time(systemd_unit_state_id{name=~"smbd.service", product="ald-pro", component="filesharing"}[5m], 1) * 100' object_tag: "hostname" group_by: - "hostname" step: 5m rate: 60s metric_ttl: 168h no_data_mode: "No data" rules: - id: "42x0aldpro001001" labels_required: labels_absent: type: "threshold_1level_asym" parameters: alert: "85" recovery: "100" reverse: "true" critical: "true" priority: 1 - id: "41x0aldpro001101" name: '[ALD-Pro] Непредвиденная остановка сервиса {{index .Labels "name"}} на OS installing сервере {{.Host}}' description: '[ALD-Pro] Непредвиденная остановка сервиса {{index .Labels "name"}} на OS installing сервере {{.Host}}' query: 'share_eq_over_time(systemd_unit_state_id{name=~"apache2.service|rabbitmq-server.service|postgresql@.*.service", product="ald-pro", component="osinstalling"}[5m], 1) * 100' object_tag: "hostname" group_by: - "hostname" step: 5m rate: 60s metric_ttl: 168h no_data_mode: "No data" rules: - id: "42x0aldpro001101" labels_required: labels_absent: type: "threshold_1level_asym" parameters: alert: "85" recovery: "100" reverse: "true" critical: "true" priority: 1 - id: "41x0aldpro001201" name: '[ALD-Pro] Не корректный ответ от web портала с контроллера {{.Host}}' description: '[ALD-Pro] Не корректный ответ от web портала с контроллера {{.Host}}' query: 'share_eq_over_time(ald_portal_check{product="ald-pro", component="controller"}[5m], 200) * 100' object_tag: "hostname" group_by: - "hostname" step: 5m rate: 60s metric_ttl: 168h no_data_mode: "No data" rules: - id: "42x0aldpro001201" labels_required: labels_absent: type: "threshold_1level_asym" parameters: alert: "85" recovery: "100" reverse: "true" critical: "true" priority: 1 - id: "41x0aldpro001301" name: '[ALD-Pro] Непредвиденная остановка сервиса {{index .Labels "name"}} на сервере мониторинга {{.Host}}' description: '[ALD-Pro] Непредвиденная остановка сервиса {{index .Labels "name"}} на сервере мониторинга {{.Host}}' query: 'share_eq_over_time(systemd_unit_state_id{name=~"apache2.service|zabbix-agent.service|postgresql@.*.service|zabbix-server.service", product="ald-pro", component="monitoring"}[5m], 1) * 100' object_tag: "hostname" group_by: - "hostname" step: 5m rate: 60s metric_ttl: 168h no_data_mode: "No data" rules: - id: "42x0aldpro001301" labels_required: labels_absent: type: "threshold_1level_asym" parameters: alert: "85" recovery: "100" reverse: "true" critical: "true" priority: 1 - id: "41x0aldpro001401" name: '[ALD-Pro] Ошибка локальной DNS проверки на контроллере {{.Host}}' description: '[ALD-Pro] Ошибка локальной DNS проверки на контроллере {{.Host}}' query: 'share_eq_over_time(dns_localhost_check{product="ald-pro", component="controller"}[5m], 1) * 100' object_tag: "hostname" group_by: - "hostname" step: 5m rate: 60s metric_ttl: 168h no_data_mode: "No data" rules: - id: "42x0aldpro001401" labels_required: labels_absent: type: "threshold_1level_asym" parameters: alert: "85" recovery: "100" reverse: "true" critical: "true" priority: 1 - id: "41x0aldpro001501" name: '[ALD-Pro] Ошибка DNS проверки через удаленный DNS сервер на контроллере {{.Host}}' description: '[ALD-Pro] Ошибка DNS проверки через удаленный DNS сервер на контроллере {{.Host}}' query: 'share_eq_over_time(dns_specific_server{product="ald-pro", component="controller"}[5m], 1) * 100' object_tag: "hostname" group_by: - "hostname" step: 5m rate: 60s metric_ttl: 168h no_data_mode: "No data" rules: - id: "42x0aldpro001501" labels_required: labels_absent: type: "threshold_1level_asym" parameters: alert: "85" recovery: "100" reverse: "true" critical: "true" priority: 1 - id: "41x0aldpro001601" name: '[ALD-Pro] Непредвиденная остановка сервиса {{index .Labels "name"}} на сервере печати {{.Host}}' description: '[ALD-Pro] Непредвиденная остановка сервиса {{index .Labels "name"}} на сервере печати {{.Host}}' query: 'share_eq_over_time(systemd_unit_state_id{name=~"cups.service", product="ald-pro", component="printing"}[5m], 1) * 100' object_tag: "hostname" group_by: - "hostname" step: 5m rate: 60s metric_ttl: 168h no_data_mode: "No data" rules: - id: "42x0aldpro001601" labels_required: labels_absent: type: "threshold_1level_asym" parameters: alert: "85" recovery: "100" reverse: "true" critical: "true" priority: 1 - id: "41x0aldpro001701" name: '[ALD-Pro] Непредвиденная остановка сервиса {{index .Labels "name"}} на сервере репозиториев {{.Host}}' description: '[ALD-Pro] Непредвиденная остановка сервиса {{index .Labels "name"}} на сервере репозиториев {{.Host}}' query: 'share_eq_over_time(systemd_unit_state_id{name=~"apache2.service|rabbitmq-server.service|postgresql@.*.service", product="ald-pro", component="repositoring"}[5m], 1) * 100' object_tag: "hostname" group_by: - "hostname" step: 5m rate: 60s metric_ttl: 168h no_data_mode: "No data" rules: - id: "42x0aldpro001701" labels_required: labels_absent: type: "threshold_1level_asym" parameters: alert: "85" recovery: "100" reverse: "true" critical: "true" priority: 1 - id: "41x0aldpro001801" name: '[ALD-Pro] Непредвиденная ошибка подключения пользователя freeipa-exporter на контроллере {{.Host}}' description: '[ALD-Pro] Непредвиденная ошибка подключения пользователя freeipa-exporter на контроллере {{.Host}}' query: 'share_eq_over_time(ipa_user_connect{product="ald-pro", component="controller"}[5m], 1) * 100' object_tag: "hostname" group_by: - "hostname" step: 5m rate: 60s metric_ttl: 168h no_data_mode: "No data" rules: - id: "42x0aldpro001801" labels_required: labels_absent: type: "threshold_1level_asym" parameters: alert: "85" recovery: "100" critical: "true" reverse: "true" priority: 1 - id: "41x0aldpro001901" name: '[ALD-Pro] Время подключения подключения пользователя freeipa-exporter на контроллере {{.Host}} очень большое' description: '[ALD-Pro] Время подключения подключения пользователя freeipa-exporter на контроллере {{.Host}} очень большое' query: 'ipa_time_for_connect{product="ald-pro", component="controller"}' object_tag: "hostname" group_by: - "hostname" step: 5m rate: 60s metric_ttl: 168h no_data_mode: "No data" rules: - id: "42x0aldpro001901" labels_required: labels_absent: type: "threshold_1level_sym" parameters: level: "2000" # 2 seconds critical: "false" reverse: "false" priority: 1 - id: "41x0aldpro002001" name: '[ALD-Pro] Непредвиденная ошибка репликации на контроллере {{.Host}}' description: '[ALD-Pro] Непредвиденная ошибка репликации на контроллере {{.Host}}' query: 'share_eq_over_time(ipa_ldap_replication_status{product="ald-pro", component="controller"}[5m], 1) * 100' object_tag: "hostname" group_by: - "hostname" step: 5m rate: 60s metric_ttl: 168h no_data_mode: "No data" rules: - id: "42x0aldpro002001" labels_required: labels_absent: type: "threshold_1level_asym" parameters: alert: "85" recovery: "100" reverse: "true" critical: "true" priority: 1 - id: "41x0aldpro002101" name: '[ALD-Pro] Непредвиденная ошибка синхронизации времени на контроллере {{.Host}}' description: '[ALD-Pro] Непредвиденная ошибка синхронизации времени на контроллере {{.Host}}' query: 'share_eq_over_time(ipa_ntp_check{product="ald-pro", component="controller"}[5m], 0) * 100' object_tag: "hostname" group_by: - "hostname" step: 5m rate: 60s metric_ttl: 168h no_data_mode: "No data" rules: - id: "42x0aldpro002101" labels_required: labels_absent: type: "threshold_1level_asym" parameters: alert: "85" recovery: "100" reverse: "true" critical: "true" priority: 1 - id: "41x0aldpro002201" name: '[ALD-Pro] Через 7 дней пароль пользователя {{index .Labels "username"}} будет недействителен на контроллере {{.Host}}' description: '[ALD-Pro] Через 7 дней пароль пользователя {{index .Labels "username"}} будет недействителен на контроллере {{.Host}}' query: '(ald_expiration_user_password{} - time()) / 3600 / 24' object_tag: "hostname" group_by: - "hostname" step: 5m rate: 60s metric_ttl: 168h no_data_mode: "No data" rules: - id: "42x0aldpro002201" labels_required: labels_absent: type: "threshold_1level_sym" parameters: level: "8" # 8 days critical: "false" reverse: "true" priority: 1