summaryrefslogtreecommitdiffstats
path: root/roles
diff options
context:
space:
mode:
Diffstat (limited to 'roles')
-rw-r--r--roles/openshift_common/tasks/main.yml1
-rwxr-xr-xroles/openshift_facts/library/openshift_facts.py12
-rw-r--r--roles/openshift_manageiq/tasks/main.yaml50
-rw-r--r--roles/openshift_manageiq/vars/main.yml24
-rw-r--r--roles/openshift_master/tasks/main.yml8
-rw-r--r--roles/openshift_node/tasks/main.yml7
-rw-r--r--roles/openshift_node/templates/node.yaml.v1.j26
-rw-r--r--roles/os_zabbix/vars/template_openshift_master.yml93
-rw-r--r--roles/os_zabbix/vars/template_os_linux.yml34
9 files changed, 169 insertions, 66 deletions
diff --git a/roles/openshift_common/tasks/main.yml b/roles/openshift_common/tasks/main.yml
index 55065b3de..c0982290d 100644
--- a/roles/openshift_common/tasks/main.yml
+++ b/roles/openshift_common/tasks/main.yml
@@ -22,6 +22,7 @@
deployment_type: "{{ openshift_deployment_type }}"
use_fluentd: "{{ openshift_use_fluentd | default(None) }}"
use_flannel: "{{ openshift_use_flannel | default(None) }}"
+ use_manageiq: "{{ openshift_use_manageiq | default(None) }}"
# For enterprise versions < 3.1 and origin versions < 1.1 we want to set the
# hostname by default.
diff --git a/roles/openshift_facts/library/openshift_facts.py b/roles/openshift_facts/library/openshift_facts.py
index b60e42c71..8b3402729 100755
--- a/roles/openshift_facts/library/openshift_facts.py
+++ b/roles/openshift_facts/library/openshift_facts.py
@@ -528,9 +528,9 @@ def set_aggregate_facts(facts):
internal_hostnames.add(facts['common']['hostname'])
internal_hostnames.add(facts['common']['ip'])
+ cluster_domain = facts['common']['dns_domain']
+
if 'master' in facts:
- # FIXME: not sure why but facts['dns']['domain'] fails
- cluster_domain = 'cluster.local'
if 'cluster_hostname' in facts['master']:
all_hostnames.add(facts['master']['cluster_hostname'])
if 'cluster_public_hostname' in facts['master']:
@@ -623,7 +623,7 @@ def set_deployment_facts_if_unset(facts):
service_type = 'atomic-openshift'
if deployment_type == 'origin':
service_type = 'origin'
- elif deployment_type in ['enterprise', 'online']:
+ elif deployment_type in ['enterprise']:
service_type = 'openshift'
facts['common']['service_type'] = service_type
if 'config_base' not in facts['common']:
@@ -985,7 +985,7 @@ class OpenShiftFacts(object):
Raises:
OpenShiftFactsUnsupportedRoleError:
"""
- known_roles = ['common', 'master', 'node', 'master_sdn', 'node_sdn', 'dns', 'etcd']
+ known_roles = ['common', 'master', 'node', 'master_sdn', 'node_sdn', 'etcd']
def __init__(self, role, filename, local_facts, additive_facts_to_overwrite=False):
self.changed = False
@@ -1053,9 +1053,10 @@ class OpenShiftFacts(object):
common = dict(use_openshift_sdn=True, ip=ip_addr, public_ip=ip_addr,
deployment_type='origin', hostname=hostname,
- public_hostname=hostname)
+ public_hostname=hostname, use_manageiq=False)
common['client_binary'] = 'oc' if os.path.isfile('/usr/bin/oc') else 'osc'
common['admin_binary'] = 'oadm' if os.path.isfile('/usr/bin/oadm') else 'osadm'
+ common['dns_domain'] = 'cluster.local'
defaults['common'] = common
if 'master' in roles:
@@ -1076,7 +1077,6 @@ class OpenShiftFacts(object):
node = dict(labels={}, annotations={}, portal_net='172.30.0.0/16',
iptables_sync_period='5s', set_node_ip=False)
defaults['node'] = node
-
return defaults
def guess_host_provider(self):
diff --git a/roles/openshift_manageiq/tasks/main.yaml b/roles/openshift_manageiq/tasks/main.yaml
new file mode 100644
index 000000000..2d3187e21
--- /dev/null
+++ b/roles/openshift_manageiq/tasks/main.yaml
@@ -0,0 +1,50 @@
+---
+- name: Copy Configuration to temporary conf
+ command: >
+ cp {{ openshift.common.config_base }}/master/admin.kubeconfig {{manage_iq_tmp_conf}}
+ changed_when: false
+
+- name: Add Managment Infrastructure project
+ command: >
+ {{ openshift.common.admin_binary }} new-project
+ management-infra
+ --description="Management Infrastructure"
+ --config={{manage_iq_tmp_conf}}
+ register: osmiq_create_mi_project
+ failed_when: "'already exists' not in osmiq_create_mi_project.stderr and osmiq_create_mi_project.rc != 0"
+ changed_when: osmiq_create_mi_project.rc == 0
+
+- name: Create Service Account
+ shell: >
+ echo {{ manageiq_service_account | to_json | quote }} |
+ {{ openshift.common.client_binary }} create
+ -n management-infra
+ --config={{manage_iq_tmp_conf}}
+ -f -
+ register: osmiq_create_service_account
+ failed_when: "'already exists' not in osmiq_create_service_account.stderr and osmiq_create_service_account.rc != 0"
+ changed_when: osmiq_create_service_account.rc == 0
+
+- name: Create Cluster Role
+ shell: >
+ echo {{ manageiq_cluster_role | to_json | quote }} |
+ {{ openshift.common.client_binary }} create
+ --config={{manage_iq_tmp_conf}}
+ -f -
+ register: osmiq_create_cluster_role
+ failed_when: "'already exists' not in osmiq_create_cluster_role.stderr and osmiq_create_cluster_role.rc != 0"
+ changed_when: osmiq_create_cluster_role.rc == 0
+
+- name: Configure role/user permissions
+ command: >
+ {{ openshift.common.admin_binary }} {{item}}
+ --config={{manage_iq_tmp_conf}}
+ with_items: "{{manage_iq_tasks}}"
+ register: osmiq_perm_task
+ failed_when: "'already exists' not in osmiq_perm_task.stderr and osmiq_perm_task.rc != 0"
+ changed_when: osmiq_perm_task.rc == 0
+
+- name: Clean temporary configuration file
+ command: >
+ rm -f {{manage_iq_tmp_conf}}
+ changed_when: false
diff --git a/roles/openshift_manageiq/vars/main.yml b/roles/openshift_manageiq/vars/main.yml
new file mode 100644
index 000000000..77e1c304b
--- /dev/null
+++ b/roles/openshift_manageiq/vars/main.yml
@@ -0,0 +1,24 @@
+manageiq_cluster_role:
+ apiVersion: v1
+ kind: ClusterRole
+ metadata:
+ name: management-infra-admin
+ rules:
+ - resources:
+ - pods/proxy
+ verbs:
+ - '*'
+
+manageiq_service_account:
+ apiVersion: v1
+ kind: ServiceAccount
+ metadata:
+ name: management-admin
+
+manage_iq_tmp_conf: /tmp/manageiq_admin.kubeconfig
+
+manage_iq_tasks:
+ - policy add-role-to-user -n management-infra admin -z management-admin
+ - policy add-role-to-user -n management-infra management-infra-admin -z management-admin
+ - policy add-cluster-role-to-user cluster-reader system:serviceaccount:management-infra:management-admin
+ - policy add-scc-to-user privileged system:serviceaccount:management-infra:management-admin
diff --git a/roles/openshift_master/tasks/main.yml b/roles/openshift_master/tasks/main.yml
index 9d7880041..8a78f8f2a 100644
--- a/roles/openshift_master/tasks/main.yml
+++ b/roles/openshift_master/tasks/main.yml
@@ -87,14 +87,8 @@
when: ansible_pkg_mgr == "dnf"
register: install_result
-# TODO: These values need to be configurable
-- name: Set dns facts
+- name: Re-gather package dependent master facts
openshift_facts:
- role: dns
- local_facts:
- ip: "{{ openshift_master_cluster_vip | default(openshift.common.ip, true) | default(None) }}"
- domain: cluster.local
- when: openshift.master.embedded_dns
- name: Create config parent directory if it does not exist
file:
diff --git a/roles/openshift_node/tasks/main.yml b/roles/openshift_node/tasks/main.yml
index 36bcc1a90..29e7eb532 100644
--- a/roles/openshift_node/tasks/main.yml
+++ b/roles/openshift_node/tasks/main.yml
@@ -1,12 +1,6 @@
---
# TODO: allow for overriding default ports where possible
- fail:
- msg: This role requres that osn_cluster_dns_domain is set
- when: osn_cluster_dns_domain is not defined or not osn_cluster_dns_domain
-- fail:
- msg: This role requres that osn_cluster_dns_ip is set
- when: osn_cluster_dns_ip is not defined or not osn_cluster_dns_ip
-- fail:
msg: "SELinux is disabled, This deployment type requires that SELinux is enabled."
when: (not ansible_selinux or ansible_selinux.status != 'enabled') and deployment_type in ['enterprise', 'online', 'atomic-enterprise', 'openshift-enterprise']
@@ -20,6 +14,7 @@
hostname: "{{ openshift_hostname | default(none) }}"
public_hostname: "{{ openshift_public_hostname | default(none) }}"
deployment_type: "{{ openshift_deployment_type }}"
+ dns_ip: "{{ openshift_dns_ip | default(openshift_master_cluster_vip | default(None, true), true) }}"
- role: node
local_facts:
annotations: "{{ openshift_node_annotations | default(none) }}"
diff --git a/roles/openshift_node/templates/node.yaml.v1.j2 b/roles/openshift_node/templates/node.yaml.v1.j2
index 41a303dee..23bd81f91 100644
--- a/roles/openshift_node/templates/node.yaml.v1.j2
+++ b/roles/openshift_node/templates/node.yaml.v1.j2
@@ -1,7 +1,9 @@
allowDisabledDocker: false
apiVersion: v1
-dnsDomain: {{ osn_cluster_dns_domain }}
-dnsIP: {{ osn_cluster_dns_ip }}
+dnsDomain: {{ openshift.common.dns_domain }}
+{% if 'dns_ip' in openshift.common %}
+dnsIP: {{ openshift.common.dns_ip }}
+{% endif %}
dockerConfig:
execHandlerName: ""
iptablesSyncPeriod: "{{ openshift.node.iptables_sync_period }}"
diff --git a/roles/os_zabbix/vars/template_openshift_master.yml b/roles/os_zabbix/vars/template_openshift_master.yml
index 6972ac877..514d6fd24 100644
--- a/roles/os_zabbix/vars/template_openshift_master.yml
+++ b/roles/os_zabbix/vars/template_openshift_master.yml
@@ -68,6 +68,36 @@ g_template_openshift_master:
applications:
- Openshift Master
+ - key: openshift.master.pv.total.count
+ description: Total number of Persistent Volumes in the Openshift Cluster
+ type: int
+ applications:
+ - Openshift Master
+
+ - key: openshift.master.pv.available.count
+ description: Total number of Available Persistent Volumes in the Openshift Cluster
+ type: int
+ applications:
+ - Openshift Master
+
+ - key: openshift.master.pv.released.count
+ description: Total number of Released Persistent Volumes in the Openshift Cluster
+ type: int
+ applications:
+ - Openshift Master
+
+ - key: openshift.master.pv.bound.count
+ description: Total number of Bound Persistent Volumes in the Openshift Cluster
+ type: int
+ applications:
+ - Openshift Master
+
+ - key: openshift.master.pv.failed.count
+ description: Total number of Failed Persistent Volumes in the Openshift Cluster
+ type: int
+ applications:
+ - Openshift Master
+
- key: openshift.master.etcd.create.success
description: Show number of successful create actions
type: int
@@ -201,26 +231,6 @@ g_template_openshift_master:
- Openshift Master Metrics
ztriggers:
- - name: 'Application creation has failed on {HOST.NAME}'
- expression: '{Template Openshift Master:create_app.last(#1)}=1 and {Template Openshift Master:create_app.last(#2)}=1'
- url: 'https://github.com/openshift/ops-sop/blob/master/V3/Alerts/check_create_app.asciidoc'
- priority: avg
-
- - name: 'Openshift Master API health check is failing on {HOST.NAME}'
- expression: '{Template Openshift Master:openshift.master.api.healthz.max(#3)}<1'
- url: 'https://github.com/openshift/ops-sop/blob/master/V3/Alerts/openshift_master.asciidoc'
- priority: high
-
- - name: 'Openshift Master API PING check is failing on {HOST.NAME}'
- expression: '{Template Openshift Master:openshift.master.api.ping.max(#3)}<1'
- url: 'https://github.com/openshift/ops-sop/blob/master/V3/Alerts/openshift_master.asciidoc'
- priority: high
-
- - name: 'Openshift Master metric PING check is failing on {HOST.NAME}'
- expression: '{Template Openshift Master:openshift.master.metric.ping.max(#3)}<1'
- url: 'https://github.com/openshift/ops-sop/blob/master/V3/Alerts/openshift_master.asciidoc'
- priority: avg
-
- name: 'Openshift Master process not running on {HOST.NAME}'
expression: '{Template Openshift Master:openshift.master.process.count.max(#3)}<1'
url: 'https://github.com/openshift/ops-sop/blob/master/V3/Alerts/openshift_master.asciidoc'
@@ -231,6 +241,16 @@ g_template_openshift_master:
url: 'https://github.com/openshift/ops-sop/blob/master/V3/Alerts/openshift_master.asciidoc'
priority: high
+ - name: 'Low number of etcd watchers on {HOST.NAME}'
+ expression: '{Template Openshift Master:openshift.master.etcd.watchers.last(#1)}<10 and {Template Openshift Master:openshift.master.etcd.watchers.last(#2)}<10'
+ url: 'https://github.com/openshift/ops-sop/blob/master/V3/Alerts/check_etcd.asciidoc'
+ priority: avg
+
+ - name: 'Etcd ping failed on {HOST.NAME}'
+ expression: '{Template Openshift Master:openshift.master.etcd.ping.last(#1)}=0 and {Template Openshift Master:openshift.master.etcd.ping.last(#2)}=0'
+ url: 'https://github.com/openshift/ops-sop/blob/master/V3/Alerts/check_etcd.asciidoc'
+ priority: high
+
- name: 'Number of users for Openshift Master on {HOST.NAME}'
expression: '{Template Openshift Master:openshift.master.user.count.last()}=0'
url: 'https://github.com/openshift/ops-sop/blob/master/V3/Alerts/openshift_master.asciidoc'
@@ -241,19 +261,40 @@ g_template_openshift_master:
url: 'https://github.com/openshift/ops-sop/blob/master/V3/Alerts/openshift_master.asciidoc'
priority: info
- - name: 'Low number of etcd watchers on {HOST.NAME}'
- expression: '{Template Openshift Master:openshift.master.etcd.watchers.last(#1)}<10 and {Template Openshift Master:openshift.master.etcd.watchers.last(#2)}<10'
- url: 'https://github.com/openshift/ops-sop/blob/master/V3/Alerts/check_etcd.asciidoc'
+ # Put triggers that depend on other triggers here (deps must be created first)
+ - name: 'Application creation has failed on {HOST.NAME}'
+ expression: '{Template Openshift Master:create_app.last(#1)}=1 and {Template Openshift Master:create_app.last(#2)}=1'
+ url: 'https://github.com/openshift/ops-sop/blob/master/V3/Alerts/check_create_app.asciidoc'
+ dependencies:
+ - 'Openshift Master process not running on {HOST.NAME}'
priority: avg
- - name: 'Etcd ping failed on {HOST.NAME}'
- expression: '{Template Openshift Master:openshift.master.etcd.ping.last(#1)}=0 and {Template Openshift Master:openshift.master.etcd.ping.last(#2)}=0'
- url: 'https://github.com/openshift/ops-sop/blob/master/V3/Alerts/check_etcd.asciidoc'
+ - name: 'Openshift Master API health check is failing on {HOST.NAME}'
+ expression: '{Template Openshift Master:openshift.master.api.healthz.max(#3)}<1'
+ url: 'https://github.com/openshift/ops-sop/blob/master/V3/Alerts/openshift_master.asciidoc'
+ dependencies:
+ - 'Openshift Master process not running on {HOST.NAME}'
+ priority: high
+
+ - name: 'Openshift Master API PING check is failing on {HOST.NAME}'
+ expression: '{Template Openshift Master:openshift.master.api.ping.max(#3)}<1'
+ url: 'https://github.com/openshift/ops-sop/blob/master/V3/Alerts/openshift_master.asciidoc'
+ dependencies:
+ - 'Openshift Master process not running on {HOST.NAME}'
priority: high
+ - name: 'Openshift Master metric PING check is failing on {HOST.NAME}'
+ expression: '{Template Openshift Master:openshift.master.metric.ping.max(#3)}<1'
+ url: 'https://github.com/openshift/ops-sop/blob/master/V3/Alerts/openshift_master.asciidoc'
+ dependencies:
+ - 'Openshift Master process not running on {HOST.NAME}'
+ priority: avg
+
- name: 'Docker Registry check failed on {HOST.NAME}'
expression: '{Template Openshift Master:openshift.master.registry.healthz.max(#2)}<1'
url: 'https://github.com/openshift/ops-sop/blob/master/V3/Alerts/openshift_master.asciidoc'
+ dependencies:
+ - 'Openshift Master process not running on {HOST.NAME}'
priority: high
zgraphs:
diff --git a/roles/os_zabbix/vars/template_os_linux.yml b/roles/os_zabbix/vars/template_os_linux.yml
index 79d52ef9b..c6e557f12 100644
--- a/roles/os_zabbix/vars/template_os_linux.yml
+++ b/roles/os_zabbix/vars/template_os_linux.yml
@@ -258,26 +258,34 @@ g_template_os_linux:
- Network
ztriggerprototypes:
- - name: 'Filesystem: {#OSO_FILESYS} has less than 15% free disk space on {HOST.NAME}'
- expression: '{Template OS Linux:disc.filesys.full[{#OSO_FILESYS}].last()}>85'
- url: 'https://github.com/openshift/ops-sop/blob/master/V3/Alerts/check_filesys_full.asciidoc'
- priority: warn
-
- name: 'Filesystem: {#OSO_FILESYS} has less than 10% free disk space on {HOST.NAME}'
expression: '{Template OS Linux:disc.filesys.full[{#OSO_FILESYS}].last()}>90'
url: 'https://github.com/openshift/ops-sop/blob/master/V3/Alerts/check_filesys_full.asciidoc'
priority: high
- - name: 'Filesystem: {#OSO_FILESYS} has less than 10% free inodes on {HOST.NAME}'
- expression: '{Template OS Linux:disc.filesys.inodes.pused[{#OSO_FILESYS}].last()}>90'
+ # This has a dependency on the previous trigger
+ # Trigger Prototypes do not work in 2.4. They will work in Zabbix 3.0
+ - name: 'Filesystem: {#OSO_FILESYS} has less than 15% free disk space on {HOST.NAME}'
+ expression: '{Template OS Linux:disc.filesys.full[{#OSO_FILESYS}].last()}>85'
url: 'https://github.com/openshift/ops-sop/blob/master/V3/Alerts/check_filesys_full.asciidoc'
priority: warn
+ dependencies:
+ - 'Filesystem: {#OSO_FILESYS} has less than 10% free disk space on {HOST.NAME}'
- name: 'Filesystem: {#OSO_FILESYS} has less than 5% free inodes on {HOST.NAME}'
expression: '{Template OS Linux:disc.filesys.inodes.pused[{#OSO_FILESYS}].last()}>95'
url: 'https://github.com/openshift/ops-sop/blob/master/V3/Alerts/check_filesys_full.asciidoc'
priority: high
+ # This has a dependency on the previous trigger
+ # Trigger Prototypes do not work in 2.4. They will work in Zabbix 3.0
+ - name: 'Filesystem: {#OSO_FILESYS} has less than 10% free inodes on {HOST.NAME}'
+ expression: '{Template OS Linux:disc.filesys.inodes.pused[{#OSO_FILESYS}].last()}>90'
+ url: 'https://github.com/openshift/ops-sop/blob/master/V3/Alerts/check_filesys_full.asciidoc'
+ priority: warn
+ dependencies:
+ - 'Filesystem: {#OSO_FILESYS} has less than 5% free inodes on {HOST.NAME}'
+
ztriggers:
- name: 'Too many TOTAL processes on {HOST.NAME}'
expression: '{Template OS Linux:proc.nprocs.last()}>5000'
@@ -304,15 +312,3 @@ g_template_os_linux:
description: 'CPU is less than 10% idle'
dependencies:
- 'CPU idle less than 5% on {HOST.NAME}'
-
- zgraphprototypes:
- - name: Network Interface Usage
- width: 1000
- height: 400
- graph_items:
- - item_name: "Bytes per second IN on network interface {#OSO_NET_INTERFACE}"
- item_type: prototype
- color: red
- - item_name: "Bytes per second OUT on network interface {#OSO_NET_INTERFACE}"
- item_type: prototype
- color: blue
generated by cgit v1.2.3 (git 2.25.1) at 2024-11-24 14:54:05 +0000