Create trigger for nova/neutron/cinder services goes offline

Add item to monitor number of neutron services in offline
state

Change-Id: I1afa6c11156b17b9205fe805ea1134e7b0bccc4d
Closes-bug: #1446257
This commit is contained in:
Bartosz Kupidura
2015-07-27 14:39:23 +02:00
parent a662a49fe8
commit 77e08b8045
4 changed files with 94 additions and 1 deletions

View File

@@ -1,7 +1,7 @@
<?xml version="1.0" encoding="UTF-8"?>
<zabbix_export>
<version>2.0</version>
<date>2014-12-10T10:37:28Z</date>
<date>2015-07-27T12:25:30Z</date>
<groups>
<group>
<name>Templates</name>
@@ -11,6 +11,7 @@
<template>
<template>Template OpenStack Cluster</template>
<name>Template OpenStack Cluster</name>
<description/>
<groups>
<group>
<name>Templates</name>
@@ -506,6 +507,48 @@
</applications>
<valuemap/>
</item>
<item>
<name>Number of Neutron services in offline state</name>
<type>0</type>
<snmp_community/>
<multiplier>0</multiplier>
<snmp_oid/>
<key>db.services.offline.neutron.query</key>
<delay>30</delay>
<history>90</history>
<trends>365</trends>
<status>0</status>
<value_type>3</value_type>
<allowed_hosts/>
<units/>
<delta>0</delta>
<snmpv3_contextname/>
<snmpv3_securityname/>
<snmpv3_securitylevel>0</snmpv3_securitylevel>
<snmpv3_authprotocol>0</snmpv3_authprotocol>
<snmpv3_authpassphrase/>
<snmpv3_privprotocol>0</snmpv3_privprotocol>
<snmpv3_privpassphrase/>
<formula>1</formula>
<delay_flex/>
<params/>
<ipmi_sensor/>
<data_type>0</data_type>
<authtype>0</authtype>
<username/>
<password/>
<publickey/>
<privatekey/>
<port/>
<description/>
<inventory_link>0</inventory_link>
<applications>
<application>
<name>Capacity data</name>
</application>
</applications>
<valuemap/>
</item>
<item>
<name>Number of Nova services in offline state</name>
<type>0</type>
@@ -724,6 +767,36 @@
</template>
</templates>
<triggers>
<trigger>
<expression>{Template OpenStack Cluster:db.services.offline.nova.query.last(0)}>0</expression>
<name>Nova service status offline test failed</name>
<url/>
<status>0</status>
<priority>3</priority>
<description/>
<type>0</type>
<dependencies/>
</trigger>
<trigger>
<expression>{Template OpenStack Cluster:db.services.offline.cinder.query.last(0)}>0</expression>
<name>Cinder service status offline test failed</name>
<url/>
<status>0</status>
<priority>3</priority>
<description/>
<type>0</type>
<dependencies/>
</trigger>
<trigger>
<expression>{Template OpenStack Cluster:db.services.offline.neutron.query.last(0)}>0</expression>
<name>Neutron service status offline test failed</name>
<url/>
<status>0</status>
<priority>3</priority>
<description/>
<type>0</type>
<dependencies/>
</trigger>
<trigger>
<expression>{Template OpenStack Cluster:vip.cinder.api.status.last(0)}=0</expression>
<name>Cinder VIP API test failed</name>
@@ -962,6 +1035,18 @@
<key>db.services.offline.nova.query</key>
</item>
</graph_item>
<graph_item>
<sortorder>2</sortorder>
<drawtype>0</drawtype>
<color>0000C8</color>
<yaxisside>0</yaxisside>
<calc_fnc>2</calc_fnc>
<type>0</type>
<item>
<host>Template OpenStack Cluster</host>
<key>db.services.offline.neutron.query</key>
</item>
</graph_item>
</graph_items>
</graph>
<graph>

View File

@@ -25,6 +25,8 @@ class plugin_zabbix::monitoring::openstack_virtual_mon {
command => '/etc/zabbix/scripts/query_db.py instance_error';
'db.services.offline.nova.query':
command => '/etc/zabbix/scripts/query_db.py services_offline_nova';
'db.services.offline.neutron.query':
command => '/etc/zabbix/scripts/query_db.py services_offline_neutron';
'db.instance.count.query':
command => '/etc/zabbix/scripts/query_db.py instance_count';
'db.cpu.total.query':

View File

@@ -27,6 +27,7 @@ class plugin_zabbix::params::openstack {
$access_hash = hiera('access')
$keystone_hash = hiera('keystone')
$nova_hash = hiera('nova')
$neutron_hash = hiera('neutron_config')
$cinder_hash = hiera('cinder')
$rabbit_hash = hiera('rabbit')
@@ -35,6 +36,7 @@ class plugin_zabbix::params::openstack {
$access_tenant = $access_hash['tenant']
$keystone_db_password = $keystone_hash['db_password']
$nova_db_password = $nova_hash['db_password']
$neutron_db_password = $neutron_hash['database']['passwd']
$cinder_db_password = $cinder_hash['db_password']
$rabbit_password = $rabbit_hash['password']
$rabbitmq_service_name = 'rabbitmq-server'

View File

@@ -35,3 +35,7 @@ ram_used_query=select ifnull(sum(memory_mb), 0) from instances where deleted=0 a
#Count offline services - cinder
services_offline_cinder_connection=mysql://cinder:<%= scope.lookupvar('plugin_zabbix::params::openstack::cinder_db_password') %>@<%= scope.lookupvar('plugin_zabbix::params::openstack::db_vip') %>/cinder
services_offline_cinder_query=select count(*) from services where disabled=0 and deleted=0 and timestampdiff(SECOND,updated_at,utc_timestamp())>60
#Count offline services - neutron
services_offline_neutron_connection=mysql://neutron:<%= scope.lookupvar('plugin_zabbix::params::openstack::neutron_db_password') %>@<%= scope.lookupvar('plugin_zabbix::params::openstack::db_vip') %>/neutron
services_offline_neutron_query=select count(*) from agents where admin_state_up=1 and timestampdiff(SECOND,heartbeat_timestamp,utc_timestamp())>60