From 6a611f53facf22f220181e7ff95d87700e9a7a33 Mon Sep 17 00:00:00 2001 From: Matt Thompson Date: Thu, 4 Sep 2014 14:40:24 +0100 Subject: [PATCH] Add more local checks to maas_local.yml This change adds the missing checks which rely on the X_service_check.py plugins. --- .../playbooks/monitoring/maas_local.yml | 120 ++++++++++++++++++ 1 file changed, 120 insertions(+) diff --git a/rpc_deployment/playbooks/monitoring/maas_local.yml b/rpc_deployment/playbooks/monitoring/maas_local.yml index b94295cccb..1283d56fad 100644 --- a/rpc_deployment/playbooks/monitoring/maas_local.yml +++ b/rpc_deployment/playbooks/monitoring/maas_local.yml @@ -25,6 +25,30 @@ roles: - maas_local +- hosts: cinder_scheduler + vars: + check_name: cinder_scheduler_check + check_details: file=cinder_service_check.py,args=--host,args={{ ansible_hostname }},args={{ internal_vip_address }} + check_period: "{{ maas_check_period }}" + check_timeout: "{{ maas_check_timeout }}" + alarms: + - { 'name': 'cinder_scheduler_status', 'criteria': ':set consecutiveCount={{ maas_alarm_local_consecutive_count }} if (metric["cinder-scheduler_status"] != 1) { return new AlarmStatus(CRITICAL, "cinder-scheduler down"); }' } + user: root + roles: + - maas_local + +- hosts: cinder_volume + vars: + check_name: cinder_volume_check + check_details: file=cinder_service_check.py,args=--host,args={{ ansible_hostname }},args={{ internal_vip_address }} + check_period: "{{ maas_check_period }}" + check_timeout: "{{ maas_check_timeout }}" + alarms: + - { 'name': 'cinder_volume_status', 'criteria': ':set consecutiveCount={{ maas_alarm_local_consecutive_count }} if (metric["cinder-volume_status"] != 1) { return new AlarmStatus(CRITICAL, "cinder-volume down"); }' } + user: root + roles: + - maas_local + - hosts: glance_api vars: check_name: glance_api_local_check @@ -109,6 +133,54 @@ roles: - maas_local +- hosts: neutron_dhcp_agent + vars: + check_name: neutron_dhcp_agent_check + check_details: file=neutron_service_check.py,args=--host,args={{ ansible_hostname }},args={{ internal_vip_address }} + check_period: "{{ maas_check_period }}" + check_timeout: "{{ maas_check_timeout }}" + alarms: + - { 'name': 'neutron_dhcp_agent_status', 'criteria': ':set consecutiveCount={{ maas_alarm_local_consecutive_count }} if (metric["neutron-dhcp-agent_status"] != 1) { return new AlarmStatus(CRITICAL, "neutron-dhcp-agent down"); }' } + user: root + roles: + - maas_local + +- hosts: neutron_l3_agent + vars: + check_name: neutron_l3_agent_check + check_details: file=neutron_service_check.py,args=--host,args={{ ansible_hostname }},args={{ internal_vip_address }} + check_period: "{{ maas_check_period }}" + check_timeout: "{{ maas_check_timeout }}" + alarms: + - { 'name': 'neutron_l3_agent_status', 'criteria': ':set consecutiveCount={{ maas_alarm_local_consecutive_count }} if (metric["neutron-l3-agent_status"] != 1) { return new AlarmStatus(CRITICAL, "neutron-l3-agent down"); }' } + user: root + roles: + - maas_local + +- hosts: neutron_linuxbridge_agent + vars: + check_name: neutron_linuxbridge_agent_check + check_details: file=neutron_service_check.py,args=--host,args={{ ansible_hostname }},args={{ internal_vip_address }} + check_period: "{{ maas_check_period }}" + check_timeout: "{{ maas_check_timeout }}" + alarms: + - { 'name': 'neutron_linuxbridge_agent_status', 'criteria': ':set consecutiveCount={{ maas_alarm_local_consecutive_count }} if (metric["neutron-linuxbridge-agent_status"] != 1) { return new AlarmStatus(CRITICAL, "neutron-linuxbridge-agent down"); }' } + user: root + roles: + - maas_local + +- hosts: neutron_metadata_agent + vars: + check_name: neutron_metadata_agent_check + check_details: file=neutron_service_check.py,args=--host,args={{ ansible_hostname }},args={{ internal_vip_address }} + check_period: "{{ maas_check_period }}" + check_timeout: "{{ maas_check_timeout }}" + alarms: + - { 'name': 'neutron_metadata_agent_status', 'criteria': ':set consecutiveCount={{ maas_alarm_local_consecutive_count }} if (metric["neutron-metadata-agent_status"] != 1) { return new AlarmStatus(CRITICAL, "neutron-metadata-agent down"); }' } + user: root + roles: + - maas_local + - hosts: nova_api_os_compute vars: check_name: nova_api_local_check @@ -121,6 +193,54 @@ roles: - maas_local +- hosts: nova_compute + vars: + check_name: nova_compute_check + check_details: file=nova_service_check.py,args=--host,args={{ ansible_hostname }},args={{ internal_vip_address }} + check_period: "{{ maas_check_period }}" + check_timeout: "{{ maas_check_timeout }}" + alarms: + - { 'name': 'nova_compute_status', 'criteria': ':set consecutiveCount={{ maas_alarm_local_consecutive_count }} if (metric["nova-compute_status"] != 1) { return new AlarmStatus(CRITICAL, "nova-compute down"); }' } + user: root + roles: + - maas_local + +- hosts: nova_conductor + vars: + check_name: nova_conductor_check + check_details: file=nova_service_check.py,args=--host,args={{ ansible_hostname }},args={{ internal_vip_address }} + check_period: "{{ maas_check_period }}" + check_timeout: "{{ maas_check_timeout }}" + alarms: + - { 'name': 'nova_conductor_status', 'criteria': ':set consecutiveCount={{ maas_alarm_local_consecutive_count }} if (metric["nova-conductor_status"] != 1) { return new AlarmStatus(CRITICAL, "nova-conductor down"); }' } + user: root + roles: + - maas_local + +- hosts: nova_scheduler + vars: + check_name: nova_scheduler_check + check_details: file=nova_service_check.py,args=--host,args={{ ansible_hostname }},args={{ internal_vip_address }} + check_period: "{{ maas_check_period }}" + check_timeout: "{{ maas_check_timeout }}" + alarms: + - { 'name': 'nova_scheduler_status', 'criteria': ':set consecutiveCount={{ maas_alarm_local_consecutive_count }} if (metric["nova-scheduler_status"] != 1) { return new AlarmStatus(CRITICAL, "nova-scheduler down"); }' } + user: root + roles: + - maas_local + +- hosts: nova_spice_console + vars: + check_name: nova_consoleauth_check + check_details: file=nova_service_check.py,args=--host,args={{ ansible_hostname }},args={{ internal_vip_address }} + check_period: "{{ maas_check_period }}" + check_timeout: "{{ maas_check_timeout }}" + alarms: + - { 'name': 'nova_consoleauth_status', 'criteria': ':set consecutiveCount={{ maas_alarm_local_consecutive_count }} if (metric["nova-consoleauth_status"] != 1) { return new AlarmStatus(CRITICAL, "nova-consoleauth down"); }' } + user: root + roles: + - maas_local + - hosts: nova_spice_console vars: check_name: nova_spice_console_check