diff options
24 files changed, 146 insertions, 107 deletions
diff --git a/playbooks/common/openshift-cluster/upgrades/v3_0_to_v3_1/upgrade.yml b/playbooks/common/openshift-cluster/upgrades/v3_0_to_v3_1/upgrade.yml index 55c36810f..342a12810 100644 --- a/playbooks/common/openshift-cluster/upgrades/v3_0_to_v3_1/upgrade.yml +++ b/playbooks/common/openshift-cluster/upgrades/v3_0_to_v3_1/upgrade.yml @@ -258,7 +258,7 @@ openshift_master_certs_no_etcd: - admin.crt - master.kubelet-client.crt - - "{{ 'master.proxy-client.crt' if openshift.common.version_greater_than_3_1_or_1_1 else omit }}" + - "{{ 'master.proxy-client.crt' if openshift.common.version_gte_3_1_or_1_1 else omit }}" - master.server.crt - openshift-master.crt - openshift-registry.crt diff --git a/playbooks/common/openshift-master/config.yml b/playbooks/common/openshift-master/config.yml index 540c6a148..bba53151a 100644 --- a/playbooks/common/openshift-master/config.yml +++ b/playbooks/common/openshift-master/config.yml @@ -150,7 +150,7 @@ openshift_master_certs_no_etcd: - admin.crt - master.kubelet-client.crt - - "{{ 'master.proxy-client.crt' if openshift.common.version_greater_than_3_1_or_1_1 else omit }}" + - "{{ 'master.proxy-client.crt' if openshift.common.version_gte_3_1_or_1_1 else omit }}" - master.server.crt - openshift-master.crt - openshift-registry.crt @@ -174,10 +174,10 @@ master_cert_subdir: master-{{ openshift.common.hostname }} master_cert_config_dir: "{{ openshift.common.config_base }}/master" - set_fact: - openshift_infra_nodes: "{{ hostvars | oo_select_keys(groups['nodes']) + openshift_infra_nodes: "{{ hostvars | oo_select_keys(groups['oo_nodes_to_config']) | oo_nodes_with_label('region', 'infra') | oo_collect('inventory_hostname') }}" - when: openshift_infra_nodes is not defined + when: openshift_infra_nodes is not defined and groups.oo_nodes_to_config | default([]) | length > 0 - name: Configure master certificates hosts: oo_first_master @@ -364,6 +364,8 @@ - name: Additional master configuration hosts: oo_first_master vars: + cockpit_plugins: "{{ osm_cockpit_plugins | default(['cockpit-kubernetes']) }}" + etcd_urls: "{{ openshift.master.etcd_urls }}" openshift_master_ha: "{{ groups.oo_masters_to_config | length > 1 }}" omc_cluster_hosts: "{{ groups.oo_masters_to_config | join(' ')}}" roles: @@ -375,30 +377,16 @@ when: openshift.common.use_cluster_metrics | bool - role: openshift_manageiq when: openshift.common.use_manageiq | bool - -- name: Enable cockpit - hosts: oo_first_master - vars: - cockpit_plugins: "{{ osm_cockpit_plugins | default(['cockpit-kubernetes']) }}" - roles: - role: cockpit when: not openshift.common.is_atomic and ( deployment_type in ['atomic-enterprise','openshift-enterprise'] ) and (osm_use_cockpit | bool or osm_use_cockpit is undefined ) - -- name: Configure flannel - hosts: oo_first_master - vars: - etcd_urls: "{{ openshift.master.etcd_urls }}" - roles: - role: flannel_register when: openshift.common.use_flannel | bool + - role: pods + when: openshift.common.deployment_type == 'online' + - role: os_env_extras + when: openshift.common.deployment_type == 'online' -# Additional instance config for online deployments -- name: Additional instance config - hosts: oo_masters_deployment_type_online - roles: - - pods - - os_env_extras - name: Delete temporary directory on localhost hosts: localhost @@ -409,22 +397,25 @@ - file: name={{ g_master_mktemp.stdout }} state=absent changed_when: False -- name: Configure service accounts - hosts: oo_first_master - vars: - accounts: ["router", "registry"] - roles: - - openshift_serviceaccounts - -- name: Create persistent volumes and services +- name: Create persistent volumes and create hosted services hosts: oo_first_master vars: + attach_registry_volume: "{{ openshift.hosted.registry.storage.kind != None }}" + deploy_infra: "{{ openshift.master.infra_nodes | default([]) | length > 0 }}" persistent_volumes: "{{ hostvars[groups.oo_first_master.0] | oo_persistent_volumes(groups) }}" persistent_volume_claims: "{{ hostvars[groups.oo_first_master.0] | oo_persistent_volume_claims }}" roles: - role: openshift_persistent_volumes when: persistent_volumes | length > 0 or persistent_volume_claims | length > 0 + - role: openshift_serviceaccounts + openshift_serviceaccounts_names: + - router + - registry + openshift_serviceaccounts_namespace: default + openshift_serviceaccounts_sccs: + - privileged - role: openshift_router - when: openshift.master.infra_nodes is defined + when: deploy_infra | bool - role: openshift_registry - when: openshift.master.infra_nodes is defined and openshift.hosted.registry.storage.kind != None + when: deploy_infra | bool and attach_registry_volume | bool + diff --git a/playbooks/common/openshift-node/config.yml b/playbooks/common/openshift-node/config.yml index e07de0e99..01e637f7a 100644 --- a/playbooks/common/openshift-node/config.yml +++ b/playbooks/common/openshift-node/config.yml @@ -176,6 +176,7 @@ - name: Evaluate node groups hosts: localhost become: no + connection: local tasks: - name: Evaluate oo_containerized_master_nodes add_host: diff --git a/roles/fluentd_master/meta/main.yml b/roles/fluentd_master/meta/main.yml new file mode 100644 index 000000000..148bc377e --- /dev/null +++ b/roles/fluentd_master/meta/main.yml @@ -0,0 +1,15 @@ +--- +galaxy_info: + author: OpenShift Red Hat + description: Fluentd Master + company: Red Hat, Inc. + license: Apache License, Version 2.0 + min_ansible_version: 1.9 + platforms: + - name: EL + versions: + - 7 + categories: + - monitoring + dependencies: + - openshift_facts diff --git a/roles/lib_dyn/library/dyn_record.py b/roles/lib_dyn/library/dyn_record.py index 5e088a674..f2796ccf2 100644 --- a/roles/lib_dyn/library/dyn_record.py +++ b/roles/lib_dyn/library/dyn_record.py @@ -224,11 +224,13 @@ def main(): # First get a list of existing records for the node values = get_record_values(dyn_node_records) value_key = get_record_key(module.params['record_type']) + param_value = module.params['record_value'] # Check to see if the record is already in place before doing anything. if (dyn_node_records and dyn_node_records[value_key][0].ttl == module.params['record_ttl'] and - module.params['record_value'] in values[value_key]): + (param_value in values[value_key] or + param_value + '.' in values[value_key])): module.exit_json(changed=False) diff --git a/roles/lib_dyn/tasks/main.yml b/roles/lib_dyn/tasks/main.yml index 9b3b1b0b9..965962928 100644 --- a/roles/lib_dyn/tasks/main.yml +++ b/roles/lib_dyn/tasks/main.yml @@ -3,3 +3,5 @@ - name: Make sure python-dyn is installed yum: name=python-dyn state=present + tags: + - lib_dyn diff --git a/roles/openshift_common/tasks/main.yml b/roles/openshift_common/tasks/main.yml index 98b0b11ea..06e2c0878 100644 --- a/roles/openshift_common/tasks/main.yml +++ b/roles/openshift_common/tasks/main.yml @@ -8,7 +8,7 @@ when: openshift_use_openshift_sdn | default(false) | bool and openshift_use_nuage | default(false) | bool - fail: - msg: Nuage sdn can not be used with flannel + msg: Nuage sdn can not be used with flannel when: openshift_use_flannel | default(false) | bool and openshift_use_nuage | default(false) | bool - fail: @@ -49,7 +49,7 @@ # For enterprise versions < 3.1 and origin versions < 1.1 we want to set the # hostname by default. - set_fact: - set_hostname_default: "{{ not openshift.common.version_greater_than_3_1_or_1_1 }}" + set_hostname_default: "{{ not openshift.common.version_gte_3_1_or_1_1 }}" - name: Set hostname command: > diff --git a/roles/openshift_examples/defaults/main.yml b/roles/openshift_examples/defaults/main.yml index 6b9964aec..5e955590e 100644 --- a/roles/openshift_examples/defaults/main.yml +++ b/roles/openshift_examples/defaults/main.yml @@ -6,7 +6,7 @@ openshift_examples_load_db_templates: true openshift_examples_load_xpaas: "{{ openshift_deployment_type != 'origin' }}" openshift_examples_load_quickstarts: true -content_version: "{{ 'v1.1' if openshift.common.version_greater_than_3_1_or_1_1 else 'v1.0' }}" +content_version: "{{ 'v1.1' if openshift.common.version_gte_3_1_or_1_1 else 'v1.0' }}" examples_base: "{{ openshift.common.config_base if openshift.common.is_containerized else '/usr/share/openshift' }}/examples" image_streams_base: "{{ examples_base }}/image-streams" diff --git a/roles/openshift_facts/library/openshift_facts.py b/roles/openshift_facts/library/openshift_facts.py index 01329d008..5f5c5c788 100755 --- a/roles/openshift_facts/library/openshift_facts.py +++ b/roles/openshift_facts/library/openshift_facts.py @@ -720,7 +720,7 @@ def set_deployment_facts_if_unset(facts): def set_version_facts_if_unset(facts): """ Set version facts. This currently includes common.version and - common.version_greater_than_3_1_or_1_1. + common.version_gte_3_1_or_1_1. Args: facts (dict): existing facts @@ -732,16 +732,20 @@ def set_version_facts_if_unset(facts): facts['common']['version'] = version = get_openshift_version() if version is not None: if deployment_type == 'origin': - version_gt_3_1_or_1_1 = LooseVersion(version) > LooseVersion('1.0.6') - version_gt_3_1_1_or_1_1_1 = LooseVersion(version) > LooseVersion('1.1.1') + version_gte_3_1_or_1_1 = LooseVersion(version) >= LooseVersion('1.1.0') + version_gte_3_1_1_or_1_1_1 = LooseVersion(version) >= LooseVersion('1.1.1') + version_gte_3_2_or_1_2 = LooseVersion(version) >= LooseVersion('1.1.2') else: - version_gt_3_1_or_1_1 = LooseVersion(version) > LooseVersion('3.0.2.900') - version_gt_3_1_1_or_1_1_1 = LooseVersion(version) > LooseVersion('3.1.1') + version_gte_3_1_or_1_1 = LooseVersion(version) >= LooseVersion('3.1.0') + version_gte_3_1_1_or_1_1_1 = LooseVersion(version) >= LooseVersion('3.1.1') + version_gte_3_2_or_1_2 = LooseVersion(version) >= LooseVersion('3.2.0') else: - version_gt_3_1_or_1_1 = True - version_gt_3_1_1_or_1_1_1 = True - facts['common']['version_greater_than_3_1_or_1_1'] = version_gt_3_1_or_1_1 - facts['common']['version_greater_than_3_1_1_or_1_1_1'] = version_gt_3_1_1_or_1_1_1 + version_gte_3_1_or_1_1 = True + version_gte_3_1_1_or_1_1_1 = True + version_gte_3_2_or_1_2 = True + facts['common']['version_gte_3_1_or_1_1'] = version_gte_3_1_or_1_1 + facts['common']['version_gte_3_1_1_or_1_1_1'] = version_gte_3_1_1_or_1_1_1 + facts['common']['version_gte_3_2_or_1_2'] = version_gte_3_2_or_1_2 return facts @@ -756,12 +760,12 @@ def set_manageiq_facts_if_unset(facts): OpenShiftFactsInternalError: """ if 'common' not in facts: - if 'version_greater_than_3_1_or_1_1' not in facts['common']: + if 'version_gte_3_1_or_1_1' not in facts['common']: raise OpenShiftFactsInternalError( "Invalid invocation: The required facts are not set" ) if 'use_manageiq' not in facts['common']: - facts['common']['use_manageiq'] = facts['common']['version_greater_than_3_1_or_1_1'] + facts['common']['use_manageiq'] = facts['common']['version_gte_3_1_or_1_1'] return facts diff --git a/roles/openshift_manageiq/tasks/main.yaml b/roles/openshift_manageiq/tasks/main.yaml index 0357fc85a..d2ff1b4b7 100644 --- a/roles/openshift_manageiq/tasks/main.yaml +++ b/roles/openshift_manageiq/tasks/main.yaml @@ -1,7 +1,7 @@ --- - fail: msg: "The openshift_manageiq role requires OpenShift Enterprise 3.1 or Origin 1.1." - when: not openshift.common.version_greater_than_3_1_or_1_1 | bool + when: not openshift.common.version_gte_3_1_or_1_1 | bool - name: Copy Configuration to temporary conf command: > @@ -9,7 +9,7 @@ changed_when: false - name: Add Managment Infrastructure project - command: > + command: > {{ openshift.common.admin_binary }} new-project management-infra --description="Management Infrastructure" @@ -20,9 +20,9 @@ - name: Create Service Account shell: > - echo {{ manageiq_service_account | to_json | quote }} | - {{ openshift.common.client_binary }} create - -n management-infra + 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 @@ -32,7 +32,7 @@ - name: Create Cluster Role shell: > echo {{ manageiq_cluster_role | to_json | quote }} | - {{ openshift.common.client_binary }} create + {{ openshift.common.client_binary }} create --config={{manage_iq_tmp_conf}} -f - register: osmiq_create_cluster_role diff --git a/roles/openshift_master/tasks/main.yml b/roles/openshift_master/tasks/main.yml index 83f6f7542..3613808b6 100644 --- a/roles/openshift_master/tasks/main.yml +++ b/roles/openshift_master/tasks/main.yml @@ -15,7 +15,7 @@ when: openshift_master_ha | bool and ((openshift_master_cluster_method is not defined) or (openshift_master_cluster_method is defined and openshift_master_cluster_method not in ["native", "pacemaker"])) - fail: msg: "'native' high availability is not supported for the requested OpenShift version" - when: openshift_master_ha | bool and openshift_master_cluster_method == "native" and not openshift.common.version_greater_than_3_1_or_1_1 | bool + when: openshift_master_ha | bool and openshift_master_cluster_method == "native" and not openshift.common.version_gte_3_1_or_1_1 | bool - fail: msg: "openshift_master_cluster_password must be set for multi-master installations" when: openshift_master_ha | bool and openshift_master_cluster_method == "pacemaker" and (openshift_master_cluster_password is not defined or not openshift_master_cluster_password) @@ -287,7 +287,7 @@ - name: Mask master service command: systemctl mask {{ openshift.common.service_type }}-master - when: openshift_master_ha | bool and openshift.master.cluster_method == 'native' + when: openshift_master_ha | bool and openshift.master.cluster_method == 'native' and not openshift.common.is_atomic | bool - name: Start and enable master api service: name={{ openshift.common.service_type }}-master-api enabled=yes state=started diff --git a/roles/openshift_master/templates/master.yaml.v1.j2 b/roles/openshift_master/templates/master.yaml.v1.j2 index 1eeab46fe..813a58d60 100644 --- a/roles/openshift_master/templates/master.yaml.v1.j2 +++ b/roles/openshift_master/templates/master.yaml.v1.j2 @@ -1,5 +1,5 @@ apiLevels: -{% if not openshift.common.version_greater_than_3_1_or_1_1 | bool %} +{% if not openshift.common.version_gte_3_1_or_1_1 | bool %} - v1beta3 {% endif %} - v1 @@ -91,7 +91,7 @@ kubeletClientInfo: port: 10250 {% if openshift.master.embedded_kube | bool %} kubernetesMasterConfig: -{% if not openshift.common.version_greater_than_3_1_or_1_1 | bool %} +{% if not openshift.common.version_gte_3_1_or_1_1 | bool %} apiLevels: - v1beta3 - v1 diff --git a/roles/openshift_master/templates/native-cluster/atomic-openshift-master-controllers.service.j2 b/roles/openshift_master/templates/native-cluster/atomic-openshift-master-controllers.service.j2 index e6e97b24f..b393bb9ff 100644 --- a/roles/openshift_master/templates/native-cluster/atomic-openshift-master-controllers.service.j2 +++ b/roles/openshift_master/templates/native-cluster/atomic-openshift-master-controllers.service.j2 @@ -7,7 +7,7 @@ Before={{ openshift.common.service_type }}-node.service Requires=network.target [Service] -{% if openshift.common.version_greater_than_3_1_1_or_1_1_1 | bool %} +{% if openshift.common.version_gte_3_1_1_or_1_1_1 | bool %} Type=notify {% else %} Type=simple diff --git a/roles/openshift_master_certificates/tasks/main.yml b/roles/openshift_master_certificates/tasks/main.yml index 36d953111..7c58e943a 100644 --- a/roles/openshift_master_certificates/tasks/main.yml +++ b/roles/openshift_master_certificates/tasks/main.yml @@ -39,7 +39,7 @@ state: hard with_nested: - masters_needing_certs - - "{{ master_certificates | union(master_31_certificates) if openshift.common.version_greater_than_3_1_or_1_1 | bool else master_certificates }}" + - "{{ master_certificates | union(master_31_certificates) if openshift.common.version_gte_3_1_or_1_1 | bool else master_certificates }}" - name: Create the master certificates if they do not already exist command: > diff --git a/roles/openshift_node/tasks/main.yml b/roles/openshift_node/tasks/main.yml index 9035248f9..1df81ca00 100644 --- a/roles/openshift_node/tasks/main.yml +++ b/roles/openshift_node/tasks/main.yml @@ -17,7 +17,7 @@ # TODO: Replace this with a lookup or filter plugin. dns_ip: "{{ openshift_dns_ip | default(openshift_master_cluster_vip - | default(None if openshift.common.version_greater_than_3_1_or_1_1 | bool else openshift_node_first_master_ip | default(None, true), true), true) }}" + | default(None if openshift.common.version_gte_3_1_or_1_1 | bool else openshift_node_first_master_ip | default(None, true), true), true) }}" - role: node local_facts: annotations: "{{ openshift_node_annotations | default(none) }}" diff --git a/roles/openshift_registry/README.md b/roles/openshift_registry/README.md index 8e66c483b..247272668 100644 --- a/roles/openshift_registry/README.md +++ b/roles/openshift_registry/README.md @@ -17,12 +17,6 @@ From this role: |--------------------|-------------------------------------------------------|---------------------| | | | | -From openshift_common: - -| Name | Default value | | -|-----------------------|---------------|--------------------------------------| -| openshift_debug_level | 2 | Global openshift debug log verbosity | - Dependencies ------------ diff --git a/roles/openshift_registry/meta/main.yml b/roles/openshift_registry/meta/main.yml index 93b6797d1..b220a020e 100644 --- a/roles/openshift_registry/meta/main.yml +++ b/roles/openshift_registry/meta/main.yml @@ -4,10 +4,12 @@ galaxy_info: description: OpenShift Embedded Docker Registry company: Red Hat, Inc. license: Apache License, Version 2.0 - min_ansible_version: 1.7 + min_ansible_version: 1.9 platforms: - name: EL versions: - 7 categories: - cloud + dependencies: + - openshift_facts diff --git a/roles/openshift_router/README.md b/roles/openshift_router/README.md index 836efc443..d490e1038 100644 --- a/roles/openshift_router/README.md +++ b/roles/openshift_router/README.md @@ -16,11 +16,6 @@ From this role: |--------------------|-------------------------------------------------------|---------------------| | | | | -From openshift_common: -| Name | Default value | | -|-----------------------|---------------|--------------------------------------| -| openshift_debug_level | 2 | Global openshift debug log verbosity | - Dependencies ------------ diff --git a/roles/openshift_router/meta/main.yml b/roles/openshift_router/meta/main.yml index 0471e5e14..c2b0777b5 100644 --- a/roles/openshift_router/meta/main.yml +++ b/roles/openshift_router/meta/main.yml @@ -4,10 +4,12 @@ galaxy_info: description: OpenShift Embedded Router company: Red Hat, Inc. license: Apache License, Version 2.0 - min_ansible_version: 1.7 + min_ansible_version: 1.9 platforms: - name: EL versions: - 7 categories: - cloud + dependencies: + - openshift_facts diff --git a/roles/openshift_serviceaccounts/meta/main.yml b/roles/openshift_serviceaccounts/meta/main.yml new file mode 100644 index 000000000..a2c9fee70 --- /dev/null +++ b/roles/openshift_serviceaccounts/meta/main.yml @@ -0,0 +1,15 @@ +--- +galaxy_info: + author: OpenShift Operations + description: OpenShift Service Accounts + company: Red Hat, Inc. + license: Apache License, Version 2.0 + min_ansible_version: 1.9 + platforms: + - name: EL + versions: + - 7 + categories: + - cloud +dependencies: +- { role: openshift_facts } diff --git a/roles/openshift_serviceaccounts/tasks/main.yml b/roles/openshift_serviceaccounts/tasks/main.yml index 4c7faa6fe..5fe7d28f3 100644 --- a/roles/openshift_serviceaccounts/tasks/main.yml +++ b/roles/openshift_serviceaccounts/tasks/main.yml @@ -1,36 +1,33 @@ -- name: tmp dir for openshift - file: - path: /tmp/openshift - state: directory - owner: root - mode: 700 - -- name: Create service account configs - template: - src: serviceaccount.j2 - dest: "/tmp/openshift/{{ item }}-serviceaccount.yaml" - with_items: accounts - -- name: Create {{ item }} service account +- name: test if service accounts exists command: > - {{ openshift.common.client_binary }} create -f "/tmp/openshift/{{ item }}-serviceaccount.yaml" - with_items: accounts - register: _sa_result - failed_when: "'serviceaccounts \"{{ item }}\" already exists' not in _sa_result.stderr and _sa_result.rc != 0" - changed_when: "'serviceaccounts \"{{ item }}\" already exists' not in _sa_result.stderr and _sa_result.rc == 0" + {{ openshift.common.client_binary }} get sa {{ item }} -n {{ openshift_serviceaccounts_namespace }} + with_items: openshift_serviceaccounts_names + failed_when: false + changed_when: false + register: account_test -- name: Get current security context constraints +- name: create the service account shell: > - {{ openshift.common.client_binary }} get scc privileged -o yaml - --output-version=v1 > /tmp/openshift/scc.yaml - changed_when: false + echo {{ lookup('template', '../templates/serviceaccount.j2') + | from_yaml | to_json | quote }} | {{ openshift.common.client_binary }} create -f - + when: item.1.rc != 0 + with_together: + - openshift_serviceaccounts_names + - account_test.results -- name: Add security context constraint for {{ item }} - lineinfile: - dest: /tmp/openshift/scc.yaml - line: "- system:serviceaccount:default:{{ item }}" - insertafter: "^users:$" - with_items: accounts +- name: test if scc needs to be updated + command: > + {{ openshift.common.client_binary }} get scc {{ item }} -o yaml + changed_when: false + failed_when: false + register: scc_test + with_items: openshift_serviceaccounts_sccs -- name: Apply new scc rules for service accounts - command: "{{ openshift.common.client_binary }} update -f /tmp/openshift/scc.yaml --api-version=v1" +- name: Grant the user access to the privileged scc + command: > + {{ openshift.common.admin_binary }} policy add-scc-to-user + privileged system:serviceaccount:{{ openshift_serviceaccounts_namespace }}:{{ item.0 }} + when: "item.1.rc == 0 and 'system:serviceaccount:{{ openshift_serviceaccounts_namespace }}:{{ item.0 }}' not in {{ (item.1.stdout | from_yaml).users }}" + with_nested: + - openshift_serviceaccounts_names + - scc_test.results diff --git a/roles/openshift_serviceaccounts/templates/serviceaccount.j2 b/roles/openshift_serviceaccounts/templates/serviceaccount.j2 index 931e249f9..c5f12421f 100644 --- a/roles/openshift_serviceaccounts/templates/serviceaccount.j2 +++ b/roles/openshift_serviceaccounts/templates/serviceaccount.j2 @@ -1,4 +1,4 @@ apiVersion: v1 kind: ServiceAccount metadata: - name: {{ item }} + name: {{ item.0 }} diff --git a/roles/os_zabbix/vars/template_openshift_master.yml b/roles/os_zabbix/vars/template_openshift_master.yml index 5aae2496a..1824d7881 100644 --- a/roles/os_zabbix/vars/template_openshift_master.yml +++ b/roles/os_zabbix/vars/template_openshift_master.yml @@ -201,6 +201,18 @@ g_template_openshift_master: applications: - Openshift Master Metrics + - key: openshift.master.nodesnotready.count + description: "This check shows how many nodes in a cluster are in NotReady state." + type: int + applications: + - Openshift Master + + - key: openshift.master.nodesnotschedulable.count + description: "This check shows how many nodes in a cluster are not schedulable." + type: int + applications: + - Openshift Master + - key: openshift.master.apiserver.latency.summary.pods.quantile.list.5 description: "Value from https://master/metrics. This is the time, in miliseconds, that 50% of the pod operations have taken to completed." type: int @@ -361,6 +373,13 @@ g_template_openshift_master: - 'Openshift Master API health check is failing on {HOST.NAME}' priority: high + - name: 'Hosts not ready according to {HOST.NAME}' + expression: '{Template Openshift Master:openshift.master.nodesnotready.count.last(#2)}>0' + url: 'https://github.com/openshift/ops-sop/blob/master/V3/Alerts/openshift_node.asciidoc' + dependencies: + - 'Openshift Master process not running on {HOST.NAME}' + priority: high + zgraphs: - name: Openshift Master API Server Latency Pods LIST Quantiles width: 900 diff --git a/roles/os_zabbix/vars/template_openshift_node.yml b/roles/os_zabbix/vars/template_openshift_node.yml index ff65ef158..b0488656d 100644 --- a/roles/os_zabbix/vars/template_openshift_node.yml +++ b/roles/os_zabbix/vars/template_openshift_node.yml @@ -37,8 +37,8 @@ g_template_openshift_node: url: 'https://github.com/openshift/ops-sop/blob/node/V3/Alerts/openshift_node.asciidoc' priority: high - - name: 'OVS may not be running on {HOST.NAME}' - expression: '{Template Openshift Node:openshift.node.ovs.pids.count.last()}<>4' + - name: '[HEAL] OVS may not be running on {HOST.NAME}' + expression: '{Template Openshift Node:openshift.node.ovs.pids.count.last(#1)}<>4 and {Template Openshift Node:openshift.node.ovs.pids.count.last(#2)}<>4' url: 'https://github.com/openshift/ops-sop/blob/node/V3/Alerts/openshift_node.asciidoc' priority: high |