diff options
Diffstat (limited to 'roles')
113 files changed, 7571 insertions, 419 deletions
diff --git a/roles/ansible_service_broker/tasks/install.yml b/roles/ansible_service_broker/tasks/install.yml index ba2f7293b..f869b5fae 100644 --- a/roles/ansible_service_broker/tasks/install.yml +++ b/roles/ansible_service_broker/tasks/install.yml @@ -72,6 +72,15 @@ - apiGroups: ["image.openshift.io", ""] resources: ["images"] verbs: ["get", "list"] + - apiGroups: ["network.openshift.io"] + resources: ["clusternetworks", "netnamespaces"] + verbs: ["get"] + - apiGroups: ["network.openshift.io"] + resources: ["netnamespaces"] + verbs: ["update"] + - apiGroups: ["networking.k8s.io"] + resources: ["networkpolicies"] + verbs: ["create", "delete"] - name: Create asb-access cluster role oc_clusterrole: @@ -366,6 +375,11 @@ secret: secretName: etcd-auth-secret +- name: set auth name and type facts if needed + set_fact: + ansible_service_broker_registry_auth_type: "secret" + ansible_service_broker_registry_auth_name: "asb-registry-auth" + when: ansible_service_broker_registry_user != "" and ansible_service_broker_registry_password != "" # TODO: saw a oc_configmap in the library, but didn't understand how to get it to do the following: - name: Create config map for ansible-service-broker @@ -393,6 +407,8 @@ org: {{ ansible_service_broker_registry_organization }} tag: {{ ansible_service_broker_registry_tag }} white_list: {{ ansible_service_broker_registry_whitelist | to_yaml }} + auth_type: "{{ ansible_service_broker_registry_auth_type | default("") }}" + auth_name: "{{ ansible_service_broker_registry_auth_name | default("") }}" - type: local_openshift name: localregistry namespaces: ['openshift'] @@ -438,6 +454,7 @@ data: "{{ ansible_service_broker_registry_user }}" - path: password data: "{{ ansible_service_broker_registry_password }}" + when: ansible_service_broker_registry_user != "" and ansible_service_broker_registry_password != "" - name: Create the Broker resource in the catalog oc_obj: diff --git a/roles/calico_master/tasks/main.yml b/roles/calico_master/tasks/main.yml index 05415a4d6..834ebba64 100644 --- a/roles/calico_master/tasks/main.yml +++ b/roles/calico_master/tasks/main.yml @@ -23,7 +23,7 @@ -f {{ mktemp.stdout }}/calico-policy-controller.yml --config={{ openshift.common.config_base }}/master/admin.kubeconfig register: calico_create_output - failed_when: ('already exists' not in calico_create_output.stderr) and ('created' not in calico_create_output.stdout) + failed_when: "('already exists' not in calico_create_output.stderr) and ('created' not in calico_create_output.stdout) and calico_create_output.rc != 0" changed_when: ('created' in calico_create_output.stdout) - name: Calico Master | Delete temp directory diff --git a/roles/container_runtime/defaults/main.yml b/roles/container_runtime/defaults/main.yml index d0e37e2f4..8203d15f5 100644 --- a/roles/container_runtime/defaults/main.yml +++ b/roles/container_runtime/defaults/main.yml @@ -101,45 +101,34 @@ l_crt_crio_image_tag_dict: openshift-enterprise: "{{ l_openshift_image_tag }}" origin: "{{ openshift_crio_image_tag | default(openshift_crio_image_tag_default) }}" -l_crt_crio_image_prepend_dict: - openshift-enterprise: "registry.access.redhat.com/openshift3" - origin: "docker.io/gscrivano" - l_crt_crio_image_dict: - Fedora: - crio_image_name: "cri-o-fedora" - crio_image_tag: "latest" - CentOS: - crio_image_name: "cri-o-centos" - crio_image_tag: "latest" - RedHat: - crio_image_name: "cri-o" - crio_image_tag: "{{ openshift_crio_image_tag | default(l_crt_crio_image_tag_dict[openshift_deployment_type]) }}" - -l_crio_image_prepend: "{{ l_crt_crio_image_prepend_dict[openshift_deployment_type] }}" -l_crio_image_name: "{{ l_crt_crio_image_dict[ansible_distribution]['crio_image_name'] }}" -l_crio_image_tag: "{{ l_crt_crio_image_dict[ansible_distribution] }}" - -l_crio_image_default: "{{ l_crio_image_prepend }}/{{ l_crio_image_name }}:{{ l_crio_image_tag }}" + Fedora: "registry.fedoraproject.org/latest/cri-o" + CentOS: "registry.centos.org/projectatomic/cri-o" + RedHat: "registry.access.redhat.com/openshift3/cri-o" + +l_crio_image_name: "{{ l_crt_crio_image_dict[ansible_distribution] }}" +l_crio_image_tag: "{{ l_crt_crio_image_tag_dict[openshift_deployment_type] }}" + +l_crio_image_default: "{{ l_crio_image_name }}:{{ l_crio_image_tag }}" l_crio_image: "{{ openshift_crio_systemcontainer_image_override | default(l_crio_image_default) }}" # ----------------------- # # systemcontainers_docker # # ----------------------- # -l_crt_docker_image_prepend_dict: - Fedora: "registry.fedoraproject.org/latest" - Centos: "docker.io/gscrivano" - RedHat: "registry.access.redhat.com/openshift3" +l_crt_docker_image_dict: + Fedora: "registry.fedoraproject.org/latest/docker" + Centos: "registry.centos.org/projectatomic/docker" + RedHat: "registry.access.redhat.com/openshift3/container-engine" openshift_docker_image_tag_default: "latest" l_crt_docker_image_tag_dict: openshift-enterprise: "{{ l_openshift_image_tag }}" origin: "{{ openshift_docker_image_tag | default(openshift_docker_image_tag_default) }}" -l_docker_image_prepend: "{{ l_crt_docker_image_prepend_dict[ansible_distribution] }}" +l_docker_image_prepend: "{{ l_crt_docker_image_dict[ansible_distribution] }}" l_docker_image_tag: "{{ l_crt_docker_image_tag_dict[openshift_deployment_type] }}" -l_docker_image_default: "{{ l_docker_image_prepend }}/{{ openshift_docker_service_name }}:{{ l_docker_image_tag }}" +l_docker_image_default: "{{ l_docker_image_prepend }}:{{ l_docker_image_tag }}" l_docker_image: "{{ openshift_docker_systemcontainer_image_override | default(l_docker_image_default) }}" l_is_node_system_container: "{{ (openshift_use_node_system_container | default(openshift_use_system_containers | default(false)) | bool) }}" diff --git a/roles/container_runtime/tasks/package_docker.yml b/roles/container_runtime/tasks/package_docker.yml index d6e7e7fed..ed9a2709b 100644 --- a/roles/container_runtime/tasks/package_docker.yml +++ b/roles/container_runtime/tasks/package_docker.yml @@ -1,6 +1,17 @@ --- - include_tasks: common/pre.yml +# In some cases, some services may be run as containers and docker may still +# be installed via rpm. +- include_tasks: common/atomic_proxy.yml + when: + - > + (openshift_use_system_containers | default(False)) | bool + or (openshift_use_etcd_system_container | default(False)) | bool + or (openshift_use_openvswitch_system_container | default(False)) | bool + or (openshift_use_node_system_container | default(False)) | bool + or (openshift_use_master_system_container | default(False)) | bool + - name: Get current installed Docker version command: "{{ repoquery_installed }} --qf '%{version}' docker" when: not openshift_is_atomic | bool diff --git a/roles/etcd/tasks/auxiliary/drop_etcdctl.yml b/roles/etcd/tasks/auxiliary/drop_etcdctl.yml index 881a8c270..cab835e20 100644 --- a/roles/etcd/tasks/auxiliary/drop_etcdctl.yml +++ b/roles/etcd/tasks/auxiliary/drop_etcdctl.yml @@ -1,7 +1,7 @@ --- - name: Install etcd for etcdctl package: name=etcd{{ '-' + etcd_version if etcd_version is defined else '' }} state=present - when: not openshift_is_atomic | bool + when: not openshift_is_containerized | bool register: result until: result is succeeded diff --git a/roles/flannel/meta/main.yml b/roles/flannel/meta/main.yml index 7634b8192..38d2f748b 100644 --- a/roles/flannel/meta/main.yml +++ b/roles/flannel/meta/main.yml @@ -14,3 +14,4 @@ galaxy_info: - system dependencies: - role: lib_utils +- role: openshift_facts diff --git a/roles/kuryr/tasks/node.yaml b/roles/kuryr/tasks/node.yaml index 08f2d5adc..41d0ead20 100644 --- a/roles/kuryr/tasks/node.yaml +++ b/roles/kuryr/tasks/node.yaml @@ -40,7 +40,7 @@ regexp: '^OPTIONS="?(.*?)"?$' backrefs: yes backup: yes - line: 'OPTIONS="\1 --disable dns,proxy,plugins"' + line: 'OPTIONS="\1 --disable proxy"' - name: force node restart to disable the proxy service: diff --git a/roles/kuryr/templates/cni-daemonset.yaml.j2 b/roles/kuryr/templates/cni-daemonset.yaml.j2 index 39348ae90..09f4c7dfe 100644 --- a/roles/kuryr/templates/cni-daemonset.yaml.j2 +++ b/roles/kuryr/templates/cni-daemonset.yaml.j2 @@ -26,6 +26,13 @@ spec: image: kuryr/cni:latest imagePullPolicy: IfNotPresent command: [ "cni_ds_init" ] + env: + - name: CNI_DAEMON + value: "True" + - name: KUBERNETES_NODE_NAME + valueFrom: + fieldRef: + fieldPath: spec.nodeName securityContext: privileged: true volumeMounts: @@ -38,6 +45,10 @@ spec: subPath: kuryr-cni.conf - name: etc mountPath: /etc + - name: proc + mountPath: /host_proc + - name: openvswitch + mountPath: /var/run/openvswitch volumes: - name: bin hostPath: @@ -50,4 +61,10 @@ spec: name: kuryr-config - name: etc hostPath: - path: /etc
\ No newline at end of file + path: /etc + - name: proc + hostPath: + path: /proc + - name: openvswitch + hostPath: + path: /var/run/openvswitch diff --git a/roles/kuryr/templates/configmap.yaml.j2 b/roles/kuryr/templates/configmap.yaml.j2 index 96c215f00..4bf1dbddf 100644 --- a/roles/kuryr/templates/configmap.yaml.j2 +++ b/roles/kuryr/templates/configmap.yaml.j2 @@ -16,17 +16,17 @@ data: # Directory for Kuryr vif binding executables. (string value) #bindir = /usr/libexec/kuryr + # Neutron subnetpool name will be prefixed by this. (string value) + #subnetpool_name_prefix = kuryrPool + + # baremetal or nested-containers are the supported values. (string value) + #deployment_type = baremetal + # If set to true, the logging level will be set to DEBUG instead of the default # INFO level. (boolean value) # Note: This option can be changed without restarting. #debug = false - # DEPRECATED: If set to false, the logging level will be set to WARNING instead - # of the default INFO level. (boolean value) - # This option is deprecated for removal. - # Its value may be silently ignored in the future. - #verbose = true - # The name of a logging configuration file. This file is appended to any # existing logging configuration files. For details about logging configuration # files, see the Python logging module documentation. Note that when logging @@ -46,7 +46,7 @@ data: # logging will go to stderr as defined by use_stderr. This option is ignored if # log_config_append is set. (string value) # Deprecated group/name - [DEFAULT]/logfile - #log_file = /var/log/kuryr/kuryr-controller.log + #log_file = <None> # (Optional) The base directory used for relative log_file paths. This option # is ignored if log_config_append is set. (string value) @@ -65,13 +65,19 @@ data: # is set. (boolean value) #use_syslog = false + # Enable journald for logging. If running in a systemd environment you may wish + # to enable journal support. Doing so will use the journal native protocol + # which includes structured metadata in addition to log messages.This option is + # ignored if log_config_append is set. (boolean value) + #use_journal = false + # Syslog facility to receive log lines. This option is ignored if # log_config_append is set. (string value) #syslog_log_facility = LOG_USER # Log output to standard error. This option is ignored if log_config_append is # set. (boolean value) - #use_stderr = true + #use_stderr = false # Format string to use for log messages with context. (string value) #logging_context_format_string = %(asctime)s.%(msecs)03d %(process)d %(levelname)s %(name)s [%(request_id)s %(user_identity)s] %(instance)s%(message)s @@ -93,7 +99,7 @@ data: # List of package logging levels in logger=LEVEL pairs. This option is ignored # if log_config_append is set. (list value) - #default_log_levels = amqp=WARN,amqplib=WARN,boto=WARN,qpid=WARN,sqlalchemy=WARN,suds=INFO,oslo.messaging=INFO,iso8601=WARN,requests.packages.urllib3.connectionpool=WARN,urllib3.connectionpool=WARN,websocket=WARN,requests.packages.urllib3.util.retry=WARN,urllib3.util.retry=WARN,keystonemiddleware=WARN,routes.middleware=WARN,stevedore=WARN,taskflow=WARN,keystoneauth=WARN,oslo.cache=INFO,dogpile.core.dogpile=INFO + #default_log_levels = amqp=WARN,amqplib=WARN,boto=WARN,qpid=WARN,sqlalchemy=WARN,suds=INFO,oslo.messaging=INFO,oslo_messaging=INFO,iso8601=WARN,requests.packages.urllib3.connectionpool=WARN,urllib3.connectionpool=WARN,websocket=WARN,requests.packages.urllib3.util.retry=WARN,urllib3.util.retry=WARN,keystonemiddleware=WARN,routes.middleware=WARN,stevedore=WARN,taskflow=WARN,keystoneauth=WARN,oslo.cache=INFO,dogpile.core.dogpile=INFO # Enables or disables publication of error events. (boolean value) #publish_errors = false @@ -106,15 +112,86 @@ data: # value) #instance_uuid_format = "[instance: %(uuid)s] " + # Interval, number of seconds, of log rate limiting. (integer value) + #rate_limit_interval = 0 + + # Maximum number of logged messages per rate_limit_interval. (integer value) + #rate_limit_burst = 0 + + # Log level name used by rate limiting: CRITICAL, ERROR, INFO, WARNING, DEBUG + # or empty string. Logs with level greater or equal to rate_limit_except_level + # are not filtered. An empty string means that all levels are filtered. (string + # value) + #rate_limit_except_level = CRITICAL + # Enables or disables fatal status of deprecations. (boolean value) #fatal_deprecations = false [binding] + # Configuration options for container interface binding. - driver = kuryr.lib.binding.drivers.vlan + # + # From kuryr_kubernetes + # + + # The name prefix of the veth endpoint put inside the container. (string value) + #veth_dst_prefix = eth + + # Driver to use for binding and unbinding ports. (string value) + # Deprecated group/name - [binding]/driver + #default_driver = kuryr.lib.binding.drivers.veth + + # Drivers to use for binding and unbinding ports. (list value) + #enabled_drivers = kuryr.lib.binding.drivers.veth + + # Specifies the name of the Nova instance interface to link the virtual devices + # to (only applicable to some binding drivers. (string value) link_iface = eth0 + driver = kuryr.lib.binding.drivers.vlan + + + [cni_daemon] + + # + # From kuryr_kubernetes + # + + # Enable CNI Daemon configuration. (boolean value) + daemon_enabled = true + + # Bind address for CNI daemon HTTP server. It is recommened to allow only local + # connections. (string value) + bind_address = 127.0.0.1:50036 + + # Maximum number of processes that will be spawned to process requests from CNI + # driver. (integer value) + #worker_num = 30 + + # Time (in seconds) the CNI daemon will wait for VIF annotation to appear in + # pod metadata before failing the CNI request. (integer value) + #vif_annotation_timeout = 120 + + # Kuryr uses pyroute2 library to manipulate networking interfaces. When + # processing a high number of Kuryr requests in parallel, it may take kernel + # more time to process all networking stack changes. This option allows to tune + # internal pyroute2 timeout. (integer value) + #pyroute2_timeout = 30 + + # Set to True when you are running kuryr-daemon inside a Docker container on + # Kubernetes host. E.g. as DaemonSet on Kubernetes cluster Kuryr is supposed to + # provide networking for. This mainly means thatkuryr-daemon will look for + # network namespaces in $netns_proc_dir instead of /proc. (boolean value) + docker_mode = true + + # When docker_mode is set to True, this config option should be set to where + # host's /proc directory is mounted. Please note that mounting it is necessary + # to allow Kuryr-Kubernetes to move host interfaces between host network + # namespaces, which is essential for Kuryr to work. (string value) + netns_proc_dir = /host_proc + + [kubernetes] # @@ -164,11 +241,6 @@ data: # The driver that manages VIFs pools for Kubernetes Pods (string value) vif_pool_driver = {{ kuryr_openstack_enable_pools | default(False) | ternary('nested', 'noop') }} - [vif_pool] - ports_pool_max = {{ kuryr_openstack_pool_max | default(0) }} - ports_pool_min = {{ kuryr_openstack_pool_min | default(1) }} - ports_pool_batch = {{ kuryr_openstack_pool_batch | default(5) }} - ports_pool_update_frequency = {{ kuryr_openstack_pool_update_frequency | default(20) }} [neutron] # Configuration options for OpenStack Neutron @@ -232,13 +304,55 @@ data: external_svc_subnet = {{ kuryr_openstack_external_svc_subnet_id }} [pod_vif_nested] + worker_nodes_subnet = {{ kuryr_openstack_worker_nodes_subnet_id }} + + + [pool_manager] + + # + # From kuryr_kubernetes + # + + # Absolute path to socket file that will be used for communication with the + # Pool Manager daemon (string value) + #sock_file = /run/kuryr/kuryr_manage.sock + + + [vif_pool] + + # + # From kuryr_kubernetes + # + + # Set a maximun amount of ports per pool. 0 to disable (integer value) + ports_pool_max = {{ kuryr_openstack_pool_max | default(0) }} + + # Set a target minimum size of the pool of ports (integer value) + ports_pool_min = {{ kuryr_openstack_pool_min | default(1) }} + + # Number of ports to be created in a bulk request (integer value) + ports_pool_batch = {{ kuryr_openstack_pool_batch | default(5) }} + + # Minimun interval (in seconds) between pool updates (integer value) + ports_pool_update_frequency = {{ kuryr_openstack_pool_update_frequency | default(20) }} + kuryr-cni.conf: |+ [DEFAULT] # # From kuryr_kubernetes # + + # Directory for Kuryr vif binding executables. (string value) + #bindir = /usr/libexec/kuryr + + # Neutron subnetpool name will be prefixed by this. (string value) + #subnetpool_name_prefix = kuryrPool + + # baremetal or nested-containers are the supported values. (string value) + #deployment_type = baremetal + # If set to true, the logging level will be set to DEBUG instead of the default # INFO level. (boolean value) # Note: This option can be changed without restarting. @@ -263,7 +377,7 @@ data: # logging will go to stderr as defined by use_stderr. This option is ignored if # log_config_append is set. (string value) # Deprecated group/name - [DEFAULT]/logfile - #log_file = /var/log/kuryr/cni.log + #log_file = <None> # (Optional) The base directory used for relative log_file paths. This option # is ignored if log_config_append is set. (string value) @@ -282,6 +396,12 @@ data: # is set. (boolean value) #use_syslog = false + # Enable journald for logging. If running in a systemd environment you may wish + # to enable journal support. Doing so will use the journal native protocol + # which includes structured metadata in addition to log messages.This option is + # ignored if log_config_append is set. (boolean value) + #use_journal = false + # Syslog facility to receive log lines. This option is ignored if # log_config_append is set. (string value) #syslog_log_facility = LOG_USER @@ -310,7 +430,7 @@ data: # List of package logging levels in logger=LEVEL pairs. This option is ignored # if log_config_append is set. (list value) - #default_log_levels = amqp=WARN,amqplib=WARN,boto=WARN,qpid=WARN,sqlalchemy=WARN,suds=INFO,oslo.messaging=INFO,iso8601=WARN,requests.packages.urllib3.connectionpool=WARN,urllib3.connectionpool=WARN,websocket=WARN,requests.packages.urllib3.util.retry=WARN,urllib3.util.retry=WARN,keystonemiddleware=WARN,routes.middleware=WARN,stevedore=WARN,taskflow=WARN,keystoneauth=WARN,oslo.cache=INFO,dogpile.core.dogpile=INFO + #default_log_levels = amqp=WARN,amqplib=WARN,boto=WARN,qpid=WARN,sqlalchemy=WARN,suds=INFO,oslo.messaging=INFO,oslo_messaging=INFO,iso8601=WARN,requests.packages.urllib3.connectionpool=WARN,urllib3.connectionpool=WARN,websocket=WARN,requests.packages.urllib3.util.retry=WARN,urllib3.util.retry=WARN,keystonemiddleware=WARN,routes.middleware=WARN,stevedore=WARN,taskflow=WARN,keystoneauth=WARN,oslo.cache=INFO,dogpile.core.dogpile=INFO # Enables or disables publication of error events. (boolean value) #publish_errors = false @@ -323,14 +443,85 @@ data: # value) #instance_uuid_format = "[instance: %(uuid)s] " + # Interval, number of seconds, of log rate limiting. (integer value) + #rate_limit_interval = 0 + + # Maximum number of logged messages per rate_limit_interval. (integer value) + #rate_limit_burst = 0 + + # Log level name used by rate limiting: CRITICAL, ERROR, INFO, WARNING, DEBUG + # or empty string. Logs with level greater or equal to rate_limit_except_level + # are not filtered. An empty string means that all levels are filtered. (string + # value) + #rate_limit_except_level = CRITICAL + # Enables or disables fatal status of deprecations. (boolean value) #fatal_deprecations = false [binding] + # Configuration options for container interface binding. + + # + # From kuryr_kubernetes + # + + # The name prefix of the veth endpoint put inside the container. (string value) + #veth_dst_prefix = eth + + # Driver to use for binding and unbinding ports. (string value) + # Deprecated group/name - [binding]/driver + #default_driver = kuryr.lib.binding.drivers.veth + + # Drivers to use for binding and unbinding ports. (list value) + #enabled_drivers = kuryr.lib.binding.drivers.veth + + # Specifies the name of the Nova instance interface to link the virtual devices + # to (only applicable to some binding drivers. (string value) + link_iface = eth0 driver = kuryr.lib.binding.drivers.vlan - link_iface = {{ kuryr_cni_link_interface }} + + + [cni_daemon] + + # + # From kuryr_kubernetes + # + + # Enable CNI Daemon configuration. (boolean value) + daemon_enabled = true + + # Bind address for CNI daemon HTTP server. It is recommened to allow only local + # connections. (string value) + bind_address = 127.0.0.1:50036 + + # Maximum number of processes that will be spawned to process requests from CNI + # driver. (integer value) + #worker_num = 30 + + # Time (in seconds) the CNI daemon will wait for VIF annotation to appear in + # pod metadata before failing the CNI request. (integer value) + #vif_annotation_timeout = 120 + + # Kuryr uses pyroute2 library to manipulate networking interfaces. When + # processing a high number of Kuryr requests in parallel, it may take kernel + # more time to process all networking stack changes. This option allows to tune + # internal pyroute2 timeout. (integer value) + #pyroute2_timeout = 30 + + # Set to True when you are running kuryr-daemon inside a Docker container on + # Kubernetes host. E.g. as DaemonSet on Kubernetes cluster Kuryr is supposed to + # provide networking for. This mainly means thatkuryr-daemon will look for + # network namespaces in $netns_proc_dir instead of /proc. (boolean value) + docker_mode = true + + # When docker_mode is set to True, this config option should be set to where + # host's /proc directory is mounted. Please note that mounting it is necessary + # to allow Kuryr-Kubernetes to move host interfaces between host network + # namespaces, which is essential for Kuryr to work. (string value) + netns_proc_dir = /host_proc + [kubernetes] @@ -341,12 +532,136 @@ data: # The root URL of the Kubernetes API (string value) api_root = {{ openshift.master.api_url }} - # The token to talk to the k8s API - token_file = /etc/kuryr/token + # Absolute path to client cert to connect to HTTPS K8S_API (string value) + # ssl_client_crt_file = /etc/kuryr/controller.crt + + # Absolute path client key file to connect to HTTPS K8S_API (string value) + # ssl_client_key_file = /etc/kuryr/controller.key # Absolute path to ca cert file to connect to HTTPS K8S_API (string value) - ssl_ca_crt_file = /etc/kuryr/ca.crt + ssl_ca_crt_file = /var/run/secrets/kubernetes.io/serviceaccount/ca.crt + + # The token to talk to the k8s API + token_file = /var/run/secrets/kubernetes.io/serviceaccount/token # HTTPS K8S_API server identity verification (boolean value) # TODO (apuimedo): Make configurable ssl_verify_server_crt = True + + # The driver to determine OpenStack project for pod ports (string value) + pod_project_driver = default + + # The driver to determine OpenStack project for services (string value) + service_project_driver = default + + # The driver to determine Neutron subnets for pod ports (string value) + pod_subnets_driver = default + + # The driver to determine Neutron subnets for services (string value) + service_subnets_driver = default + + # The driver to determine Neutron security groups for pods (string value) + pod_security_groups_driver = default + + # The driver to determine Neutron security groups for services (string value) + service_security_groups_driver = default + + # The driver that provides VIFs for Kubernetes Pods. (string value) + pod_vif_driver = nested-vlan + + # The driver that manages VIFs pools for Kubernetes Pods (string value) + vif_pool_driver = {{ kuryr_openstack_enable_pools | default(False) | ternary('nested', 'noop') }} + + [neutron] + # Configuration options for OpenStack Neutron + + # + # From kuryr_kubernetes + # + + # Authentication URL (string value) + auth_url = {{ kuryr_openstack_auth_url }} + + # Authentication type to load (string value) + # Deprecated group/name - [neutron]/auth_plugin + auth_type = password + + # Domain ID to scope to (string value) + user_domain_name = {{ kuryr_openstack_user_domain_name }} + + # User's password (string value) + password = {{ kuryr_openstack_password }} + + # Domain name containing project (string value) + project_domain_name = {{ kuryr_openstack_project_domain_name }} + + # Project ID to scope to (string value) + # Deprecated group/name - [neutron]/tenant-id + project_id = {{ kuryr_openstack_project_id }} + + # Token (string value) + #token = <None> + + # Trust ID (string value) + #trust_id = <None> + + # User's domain id (string value) + #user_domain_id = <None> + + # User id (string value) + #user_id = <None> + + # Username (string value) + # Deprecated group/name - [neutron]/user-name + username = {{kuryr_openstack_username }} + + # Whether a plugging operation is failed if the port to plug does not become + # active (boolean value) + #vif_plugging_is_fatal = false + + # Seconds to wait for port to become active (integer value) + #vif_plugging_timeout = 0 + + [neutron_defaults] + + pod_security_groups = {{ kuryr_openstack_pod_sg_id }} + pod_subnet = {{ kuryr_openstack_pod_subnet_id }} + service_subnet = {{ kuryr_openstack_service_subnet_id }} + project = {{ kuryr_openstack_pod_project_id }} + # TODO (apuimedo): Remove the duplicated line just after this one once the + # RDO packaging contains the upstream patch + worker_nodes_subnet = {{ kuryr_openstack_worker_nodes_subnet_id }} + + [pod_vif_nested] + + worker_nodes_subnet = {{ kuryr_openstack_worker_nodes_subnet_id }} + + + [pool_manager] + + # + # From kuryr_kubernetes + # + + # Absolute path to socket file that will be used for communication with the + # Pool Manager daemon (string value) + #sock_file = /run/kuryr/kuryr_manage.sock + + + [vif_pool] + + # + # From kuryr_kubernetes + # + + # Set a maximun amount of ports per pool. 0 to disable (integer value) + ports_pool_max = {{ kuryr_openstack_pool_max | default(0) }} + + # Set a target minimum size of the pool of ports (integer value) + ports_pool_min = {{ kuryr_openstack_pool_min | default(1) }} + + # Number of ports to be created in a bulk request (integer value) + ports_pool_batch = {{ kuryr_openstack_pool_batch | default(5) }} + + # Minimun interval (in seconds) between pool updates (integer value) + ports_pool_update_frequency = {{ kuryr_openstack_pool_update_frequency | default(20) }} diff --git a/roles/lib_utils/filter_plugins/oo_filters.py b/roles/lib_utils/filter_plugins/oo_filters.py index fc14b5633..ef996fefe 100644 --- a/roles/lib_utils/filter_plugins/oo_filters.py +++ b/roles/lib_utils/filter_plugins/oo_filters.py @@ -4,6 +4,7 @@ """ Custom filters for use in openshift-ansible """ +import json import os import pdb import random @@ -21,13 +22,10 @@ import yaml from ansible import errors from ansible.parsing.yaml.dumper import AnsibleDumper -# ansible.compat.six goes away with Ansible 2.4 -try: - from ansible.compat.six import string_types, u - from ansible.compat.six.moves.urllib.parse import urlparse -except ImportError: - from ansible.module_utils.six import string_types, u - from ansible.module_utils.six.moves.urllib.parse import urlparse +# pylint: disable=import-error,no-name-in-module +from ansible.module_utils.six import string_types, u +# pylint: disable=import-error,no-name-in-module +from ansible.module_utils.six.moves.urllib.parse import urlparse HAS_OPENSSL = False try: @@ -589,6 +587,18 @@ that result to this filter plugin. return secret_name +def lib_utils_oo_l_of_d_to_csv(input_list): + """Map a list of dictionaries, input_list, into a csv string + of json values. + + Example input: + [{'var1': 'val1', 'var2': 'val2'}, {'var1': 'val3', 'var2': 'val4'}] + Example output: + u'{"var1": "val1", "var2": "val2"},{"var1": "val3", "var2": "val4"}' + """ + return ','.join(json.dumps(x) for x in input_list) + + def map_from_pairs(source, delim="="): ''' Returns a dict given the source and delim delimited ''' if source == '': @@ -626,5 +636,6 @@ class FilterModule(object): "lib_utils_oo_contains_rule": lib_utils_oo_contains_rule, "lib_utils_oo_selector_to_string_list": lib_utils_oo_selector_to_string_list, "lib_utils_oo_filter_sa_secrets": lib_utils_oo_filter_sa_secrets, + "lib_utils_oo_l_of_d_to_csv": lib_utils_oo_l_of_d_to_csv, "map_from_pairs": map_from_pairs } diff --git a/roles/lib_utils/filter_plugins/openshift_master.py b/roles/lib_utils/filter_plugins/openshift_master.py index ff15f693b..e67b19c28 100644 --- a/roles/lib_utils/filter_plugins/openshift_master.py +++ b/roles/lib_utils/filter_plugins/openshift_master.py @@ -10,11 +10,7 @@ from ansible import errors from ansible.parsing.yaml.dumper import AnsibleDumper from ansible.plugins.filter.core import to_bool as ansible_bool -# ansible.compat.six goes away with Ansible 2.4 -try: - from ansible.compat.six import string_types, u -except ImportError: - from ansible.module_utils.six import string_types, u +from ansible.module_utils.six import string_types, u import yaml diff --git a/roles/lib_utils/library/docker_creds.py b/roles/lib_utils/library/docker_creds.py index d4674845e..b94c0b779 100644 --- a/roles/lib_utils/library/docker_creds.py +++ b/roles/lib_utils/library/docker_creds.py @@ -135,7 +135,7 @@ def update_config(docker_config, registry, username, password): docker_config['auths'][registry] = {} # base64 encode our username:password string - encoded_data = base64.b64encode('{}:{}'.format(username, password)) + encoded_data = base64.b64encode('{}:{}'.format(username, password).encode()) # check if the same value is already present for idempotency. if 'auth' in docker_config['auths'][registry]: @@ -151,7 +151,7 @@ def write_config(module, docker_config, dest): conf_file_path = os.path.join(dest, 'config.json') try: with open(conf_file_path, 'w') as conf_file: - json.dump(docker_config, conf_file, indent=8) + json.dump(docker_config.decode(), conf_file, indent=8) except IOError as ioerror: result = {'failed': True, 'changed': False, diff --git a/roles/openshift_aws/defaults/main.yml b/roles/openshift_aws/defaults/main.yml index 8c8227b5e..a729e8dbd 100644 --- a/roles/openshift_aws/defaults/main.yml +++ b/roles/openshift_aws/defaults/main.yml @@ -98,12 +98,20 @@ openshift_aws_elb_dict: proxy_protocol: True openshift_aws_node_group_config_master_volumes: +- device_name: /dev/sda1 + volume_size: 100 + device_type: gp2 + delete_on_termination: False - device_name: /dev/sdb volume_size: 100 device_type: gp2 delete_on_termination: False openshift_aws_node_group_config_node_volumes: +- device_name: /dev/sda1 + volume_size: 100 + device_type: gp2 + delete_on_termination: True - device_name: /dev/sdb volume_size: 100 device_type: gp2 @@ -293,3 +301,7 @@ openshift_aws_node_user_data: '' openshift_aws_node_config_namespace: openshift-node openshift_aws_masters_groups: masters,etcd,nodes + +# By default, don't delete things like the shared IAM instance +# profile and uploaded ssh keys +openshift_aws_enable_uninstall_shared_objects: False diff --git a/roles/openshift_aws/tasks/accept_nodes.yml b/roles/openshift_aws/tasks/accept_nodes.yml index c2a2cea30..db30fe5c9 100644 --- a/roles/openshift_aws/tasks/accept_nodes.yml +++ b/roles/openshift_aws/tasks/accept_nodes.yml @@ -1,4 +1,6 @@ --- +- include_tasks: setup_master_group.yml + - name: fetch masters ec2_instance_facts: region: "{{ openshift_aws_region | default('us-east-1') }}" @@ -36,4 +38,4 @@ nodes: "{{ instancesout.instances|map(attribute='private_dns_name') | list }}" timeout: 60 register: nodeout - delegate_to: "{{ mastersout.instances[0].public_ip_address }}" + delegate_to: "{{ groups.masters.0 }}" diff --git a/roles/openshift_aws/tasks/provision.yml b/roles/openshift_aws/tasks/provision.yml index 786a2e4cf..2b5f317d8 100644 --- a/roles/openshift_aws/tasks/provision.yml +++ b/roles/openshift_aws/tasks/provision.yml @@ -1,23 +1,6 @@ --- -- when: openshift_aws_create_iam_cert | bool - name: create the iam_cert for elb certificate - include_tasks: iam_cert.yml - -- when: openshift_aws_create_s3 | bool - name: create s3 bucket for registry - include_tasks: s3.yml - - include_tasks: vpc_and_subnet_id.yml -- name: create elbs - include_tasks: elb.yml - with_dict: "{{ openshift_aws_elb_dict }}" - vars: - l_elb_security_groups: "{{ openshift_aws_elb_security_groups }}" - l_openshift_aws_elb_name_dict: "{{ openshift_aws_elb_name_dict }}" - loop_control: - loop_var: l_elb_dict_item - - name: include scale group creation for master include_tasks: build_node_group.yml with_items: "{{ openshift_aws_master_group }}" diff --git a/roles/openshift_aws/tasks/provision_elb.yml b/roles/openshift_aws/tasks/provision_elb.yml new file mode 100644 index 000000000..a52f63bd5 --- /dev/null +++ b/roles/openshift_aws/tasks/provision_elb.yml @@ -0,0 +1,15 @@ +--- +- when: openshift_aws_create_iam_cert | bool + name: create the iam_cert for elb certificate + include_tasks: iam_cert.yml + +- include_tasks: vpc_and_subnet_id.yml + +- name: create elbs + include_tasks: elb.yml + with_dict: "{{ openshift_aws_elb_dict }}" + vars: + l_elb_security_groups: "{{ openshift_aws_elb_security_groups }}" + l_openshift_aws_elb_name_dict: "{{ openshift_aws_elb_name_dict }}" + loop_control: + loop_var: l_elb_dict_item diff --git a/roles/openshift_aws/tasks/provision_nodes.yml b/roles/openshift_aws/tasks/provision_nodes.yml index d82f18574..9105b5b4c 100644 --- a/roles/openshift_aws/tasks/provision_nodes.yml +++ b/roles/openshift_aws/tasks/provision_nodes.yml @@ -2,25 +2,12 @@ # Get bootstrap config token # bootstrap should be created on first master # need to fetch it and shove it into cloud data -- name: fetch master instances - ec2_instance_facts: - region: "{{ openshift_aws_region }}" - filters: - "tag:clusterid": "{{ openshift_aws_clusterid }}" - "tag:host-type": master - instance-state-name: running - register: instancesout - retries: 20 - delay: 3 - until: - - "'instances' in instancesout" - - instancesout.instances|length > 0 +- include_tasks: setup_master_group.yml - name: slurp down the bootstrap.kubeconfig slurp: src: /etc/origin/master/bootstrap.kubeconfig - delegate_to: "{{ instancesout.instances[0].public_ip_address }}" - remote_user: root + delegate_to: "{{ groups.masters.0 }}" register: bootstrap - name: set_fact for kubeconfig token diff --git a/roles/openshift_aws/tasks/uninstall_security_group.yml b/roles/openshift_aws/tasks/uninstall_security_group.yml new file mode 100644 index 000000000..55d40e8ec --- /dev/null +++ b/roles/openshift_aws/tasks/uninstall_security_group.yml @@ -0,0 +1,14 @@ +--- +- name: delete the node group sgs + oo_ec2_group: + state: absent + name: "{{ item.value.name}}" + region: "{{ openshift_aws_region }}" + with_dict: "{{ openshift_aws_node_security_groups }}" + +- name: delete the k8s sgs for the node group + oo_ec2_group: + state: absent + name: "{{ item.value.name }}_k8s" + region: "{{ openshift_aws_region }}" + with_dict: "{{ openshift_aws_node_security_groups }}" diff --git a/roles/openshift_aws/tasks/uninstall_ssh_keys.yml b/roles/openshift_aws/tasks/uninstall_ssh_keys.yml new file mode 100644 index 000000000..27e42da53 --- /dev/null +++ b/roles/openshift_aws/tasks/uninstall_ssh_keys.yml @@ -0,0 +1,9 @@ +--- +- name: Remove the public keys for the user(s) + ec2_key: + state: absent + name: "{{ item.key_name }}" + region: "{{ openshift_aws_region }}" + with_items: "{{ openshift_aws_users }}" + no_log: True + when: openshift_aws_enable_uninstall_shared_objects | bool diff --git a/roles/openshift_aws/tasks/uninstall_vpc.yml b/roles/openshift_aws/tasks/uninstall_vpc.yml new file mode 100644 index 000000000..ecf39f694 --- /dev/null +++ b/roles/openshift_aws/tasks/uninstall_vpc.yml @@ -0,0 +1,36 @@ +--- +- name: Fetch the VPC for the vpc.id + ec2_vpc_net_facts: + region: "{{ openshift_aws_region }}" + filters: + "tag:Name": "{{ openshift_aws_clusterid }}" + register: vpcout +- debug: + var: vpcout + verbosity: 1 + +- when: vpcout.vpcs | length > 0 + block: + - name: delete the vpc igw + ec2_vpc_igw: + state: absent + region: "{{ openshift_aws_region }}" + vpc_id: "{{ vpcout.vpcs[0].id }}" + register: igw + + - name: delete the vpc subnets + ec2_vpc_subnet: + state: absent + region: "{{ openshift_aws_region }}" + vpc_id: "{{ vpcout.vpcs[0].id }}" + cidr: "{{ item.cidr }}" + az: "{{ item.az }}" + with_items: "{{ openshift_aws_vpc.subnets[openshift_aws_region] }}" + + - name: Delete AWS VPC + ec2_vpc_net: + state: absent + region: "{{ openshift_aws_region }}" + name: "{{ openshift_aws_clusterid }}" + cidr_block: "{{ openshift_aws_vpc.cidr }}" + register: vpc diff --git a/roles/openshift_bootstrap_autoapprover/files/openshift-bootstrap-controller-policy.yaml b/roles/openshift_bootstrap_autoapprover/files/openshift-bootstrap-controller-policy.yaml new file mode 100644 index 000000000..90ee40943 --- /dev/null +++ b/roles/openshift_bootstrap_autoapprover/files/openshift-bootstrap-controller-policy.yaml @@ -0,0 +1,10 @@ +kind: ClusterRoleBinding +apiVersion: rbac.authorization.k8s.io/v1beta1 +metadata: + name: bootstrap-autoapprover +roleRef: + kind: ClusterRole + name: system:node-bootstrap-autoapprover +subjects: +- kind: User + name: system:serviceaccount:openshift-infra:bootstrap-autoapprover diff --git a/roles/openshift_bootstrap_autoapprover/files/openshift-bootstrap-controller-role.yaml b/roles/openshift_bootstrap_autoapprover/files/openshift-bootstrap-controller-role.yaml new file mode 100644 index 000000000..d8143d047 --- /dev/null +++ b/roles/openshift_bootstrap_autoapprover/files/openshift-bootstrap-controller-role.yaml @@ -0,0 +1,21 @@ +apiVersion: rbac.authorization.k8s.io/v1beta1 +kind: ClusterRole +metadata: + name: system:node-bootstrap-autoapprover +rules: +- apiGroups: + - certificates.k8s.io + resources: + - certificatesigningrequests + verbs: + - delete + - get + - list + - watch +- apiGroups: + - certificates.k8s.io + resources: + - certificatesigningrequests/approval + verbs: + - create + - update diff --git a/roles/openshift_bootstrap_autoapprover/files/openshift-bootstrap-controller-serviceaccount.yaml b/roles/openshift_bootstrap_autoapprover/files/openshift-bootstrap-controller-serviceaccount.yaml new file mode 100644 index 000000000..e22ce6f34 --- /dev/null +++ b/roles/openshift_bootstrap_autoapprover/files/openshift-bootstrap-controller-serviceaccount.yaml @@ -0,0 +1,5 @@ +kind: ServiceAccount +apiVersion: v1 +metadata: + name: bootstrap-autoapprover + namespace: openshift-infra diff --git a/roles/openshift_bootstrap_autoapprover/files/openshift-bootstrap-controller.yaml b/roles/openshift_bootstrap_autoapprover/files/openshift-bootstrap-controller.yaml new file mode 100644 index 000000000..dbcedb407 --- /dev/null +++ b/roles/openshift_bootstrap_autoapprover/files/openshift-bootstrap-controller.yaml @@ -0,0 +1,68 @@ +kind: StatefulSet +apiVersion: apps/v1beta1 +metadata: + name: bootstrap-autoapprover + namespace: openshift-infra +spec: + updateStrategy: + type: RollingUpdate + template: + metadata: + labels: + app: bootstrap-autoapprover + spec: + serviceAccountName: bootstrap-autoapprover + terminationGracePeriodSeconds: 1 + containers: + - name: signer + image: openshift/node:v3.7.0-rc.0 + command: + - /bin/bash + - -c + args: + - | + #!/bin/bash + set -o errexit + set -o nounset + set -o pipefail + + unset KUBECONFIG + cat <<SCRIPT > /tmp/signer + #!/bin/bash + # + # It will approve any CSR that is not approved yet, and delete any CSR that expired more than 60 seconds + # ago. + # + + set -o errexit + set -o nounset + set -o pipefail + + name=\${1} + condition=\${2} + certificate=\${3} + username=\${4} + + # auto approve + if [[ -z "\${condition}" && ("\${username}" == "system:serviceaccount:openshift-infra:node-bootstrapper" || "\${username}" == "system:node:"* ) ]]; then + oc adm certificate approve "\${name}" + exit 0 + fi + + # check certificate age + if [[ -n "\${certificate}" ]]; then + text="\$( echo "\${certificate}" | base64 -d - )" + if ! echo "\${text}" | openssl x509 -noout; then + echo "error: Unable to parse certificate" 2>&1 + exit 1 + fi + if ! echo "\${text}" | openssl x509 -checkend -60 > /dev/null; then + echo "Certificate is expired, deleting" + oc delete csr "\${name}" + fi + exit 0 + fi + SCRIPT + chmod u+x /tmp/signer + + exec oc observe csr --maximum-errors=1 --resync-period=10m -a '{.status.conditions[*].type}' -a '{.status.certificate}' -a '{.spec.username}' -- /tmp/signer diff --git a/roles/openshift_bootstrap_autoapprover/tasks/main.yml b/roles/openshift_bootstrap_autoapprover/tasks/main.yml new file mode 100644 index 000000000..88e9d08e7 --- /dev/null +++ b/roles/openshift_bootstrap_autoapprover/tasks/main.yml @@ -0,0 +1,28 @@ +--- +- name: Copy auto-approver config to host + run_once: true + copy: + src: "{{ item }}" + dest: /tmp/openshift-approver/ + owner: root + mode: 0400 + with_fileglob: + - "*.yaml" + +- name: Set auto-approver nodeSelector + run_once: true + yedit: + src: "/tmp/openshift-approver/openshift-bootstrap-controller.yaml" + key: spec.template.spec.nodeSelector + value: "{{ openshift_master_bootstrap_auto_approver_node_selector | default({}) }}" + value_type: list + +- name: Create auto-approver on cluster + run_once: true + command: oc apply -f /tmp/openshift-approver/ + +- name: Remove auto-approver config + run_once: true + file: + path: /tmp/openshift-approver/ + state: absent diff --git a/roles/openshift_ca/tasks/main.yml b/roles/openshift_ca/tasks/main.yml index b94cd9fba..9c8534c74 100644 --- a/roles/openshift_ca/tasks/main.yml +++ b/roles/openshift_ca/tasks/main.yml @@ -19,7 +19,8 @@ - name: Reload generated facts openshift_facts: - when: hostvars[openshift_ca_host].install_result is changed + when: + - hostvars[openshift_ca_host].install_result | default({'changed':false}) is changed - name: Create openshift_ca_config_dir if it does not exist file: diff --git a/roles/openshift_cloud_provider/tasks/gce.yml b/roles/openshift_cloud_provider/tasks/gce.yml index ee4048911..395bd304c 100644 --- a/roles/openshift_cloud_provider/tasks/gce.yml +++ b/roles/openshift_cloud_provider/tasks/gce.yml @@ -13,5 +13,11 @@ ini_file: dest: "{{ openshift.common.config_base }}/cloudprovider/gce.conf" section: Global - option: multizone - value: "true" + option: "{{ item.key }}" + value: "{{ item.value }}" + with_items: + - { key: 'project-id', value: '{{ openshift_gcp_project }}' } + - { key: 'network-name', value: '{{ openshift_gcp_network_name }}' } + - { key: 'node-tags', value: '{{ openshift_gcp_prefix }}ocp' } + - { key: 'node-instance-prefix', value: '{{ openshift_gcp_prefix }}' } + - { key: 'multizone', value: 'false' } diff --git a/roles/openshift_examples/meta/main.yml b/roles/openshift_examples/meta/main.yml index 1a34c85fc..9f46a4683 100644 --- a/roles/openshift_examples/meta/main.yml +++ b/roles/openshift_examples/meta/main.yml @@ -13,3 +13,4 @@ galaxy_info: - cloud dependencies: - role: lib_utils +- role: openshift_facts diff --git a/roles/openshift_excluder/tasks/verify_excluder.yml b/roles/openshift_excluder/tasks/verify_excluder.yml index 4f5277fa2..22a3fcd3b 100644 --- a/roles/openshift_excluder/tasks/verify_excluder.yml +++ b/roles/openshift_excluder/tasks/verify_excluder.yml @@ -3,7 +3,7 @@ # - excluder - name: Get available excluder version repoquery: - name: "{{ excluder }}" + name: "{{ excluder }}{{ '-' ~ r_openshift_excluder_upgrade_target.split('.')[0:2] | join('.') ~ '*' if r_openshift_excluder_upgrade_target is defined else '' }}" ignore_excluders: true register: repoquery_out diff --git a/roles/openshift_expand_partition/tasks/main.yml b/roles/openshift_expand_partition/tasks/main.yml index 5ae863871..b38ebdfb4 100644 --- a/roles/openshift_expand_partition/tasks/main.yml +++ b/roles/openshift_expand_partition/tasks/main.yml @@ -8,7 +8,7 @@ - name: Determine if growpart is installed command: "rpm -q cloud-utils-growpart" register: has_growpart - failed_when: has_growpart.cr != 0 and 'package cloud-utils-growpart is not installed' not in has_growpart.stdout + failed_when: has_growpart.rc != 0 and 'package cloud-utils-growpart is not installed' not in has_growpart.stdout changed_when: false when: openshift_is_containerized | bool diff --git a/roles/openshift_facts/library/openshift_facts.py b/roles/openshift_facts/library/openshift_facts.py index d7c358a2f..26f0525e9 100755 --- a/roles/openshift_facts/library/openshift_facts.py +++ b/roles/openshift_facts/library/openshift_facts.py @@ -1465,6 +1465,11 @@ class OpenShiftFacts(object): if metadata: metadata['project']['attributes'].pop('sshKeys', None) metadata['instance'].pop('serviceAccounts', None) + elif bios_vendor == 'Amazon EC2': + # Adds support for Amazon EC2 C5 instance types + provider = 'aws' + metadata_url = 'http://169.254.169.254/latest/meta-data/' + metadata = get_provider_metadata(metadata_url) elif virt_type == 'xen' and virt_role == 'guest' and re.match(r'.*\.amazon$', product_version): provider = 'aws' metadata_url = 'http://169.254.169.254/latest/meta-data/' diff --git a/roles/openshift_gcp/files/bootstrap-script.sh b/roles/openshift_gcp/files/bootstrap-script.sh new file mode 100644 index 000000000..0c3f1999b --- /dev/null +++ b/roles/openshift_gcp/files/bootstrap-script.sh @@ -0,0 +1,42 @@ +#!/bin/bash +# +# This script is a startup script for bootstrapping a GCP node +# from a config stored in the project metadata. It loops until +# it finds the script and then starts the origin-node service. +# TODO: generalize + +set -o errexit +set -o nounset +set -o pipefail + +if [[ "$( curl "http://metadata.google.internal/computeMetadata/v1/instance/attributes/bootstrap" -H "Metadata-Flavor: Google" )" != "true" ]]; then + echo "info: Bootstrap is not enabled for this instance, skipping" 1>&2 + exit 0 +fi + +if ! id=$( curl "http://metadata.google.internal/computeMetadata/v1/instance/attributes/cluster-id" -H "Metadata-Flavor: Google" ); then + echo "error: Unable to get cluster-id for instance from cluster metadata" 1>&2 + exit 1 +fi + +if ! node_group=$( curl "http://metadata.google.internal/computeMetadata/v1/instance/attributes/node-group" -H "Metadata-Flavor: Google" ); then + echo "error: Unable to get node-group for instance from cluster metadata" 1>&2 + exit 1 +fi + +if ! config=$( curl -f "http://metadata.google.internal/computeMetadata/v1/instance/attributes/bootstrap-config" -H "Metadata-Flavor: Google" 2>/dev/null ); then + while true; do + if config=$( curl -f "http://metadata.google.internal/computeMetadata/v1/project/attributes/${id}-bootstrap-config" -H "Metadata-Flavor: Google" 2>/dev/null ); then + break + fi + echo "info: waiting for ${id}-bootstrap-config to become available in cluster metadata ..." 1>&2 + sleep 5 + done +fi + +echo "Got bootstrap config from metadata" +mkdir -p /etc/origin/node +echo -n "${config}" > /etc/origin/node/bootstrap.kubeconfig +echo "BOOTSTRAP_CONFIG_NAME=node-config-${node_group}" >> /etc/sysconfig/origin-node +systemctl enable origin-node +systemctl start origin-node diff --git a/roles/openshift_gcp/files/openshift-bootstrap-update.service b/roles/openshift_gcp/files/openshift-bootstrap-update.service new file mode 100644 index 000000000..c65b1b34e --- /dev/null +++ b/roles/openshift_gcp/files/openshift-bootstrap-update.service @@ -0,0 +1,7 @@ +[Unit] +Description=Update the OpenShift node bootstrap configuration + +[Service] +Type=oneshot +ExecStart=/usr/bin/openshift-bootstrap-update +User=root diff --git a/roles/openshift_gcp/files/openshift-bootstrap-update.timer b/roles/openshift_gcp/files/openshift-bootstrap-update.timer new file mode 100644 index 000000000..1a517b33e --- /dev/null +++ b/roles/openshift_gcp/files/openshift-bootstrap-update.timer @@ -0,0 +1,10 @@ +[Unit] +Description=Update the OpenShift node bootstrap credentials hourly + +[Timer] +OnBootSec=30s +OnCalendar=hourly +Persistent=true + +[Install] +WantedBy=timers.target
\ No newline at end of file diff --git a/roles/openshift_gcp_image_prep/files/partition.conf b/roles/openshift_gcp/files/partition.conf index b87e5e0b6..76e65ab9c 100644 --- a/roles/openshift_gcp_image_prep/files/partition.conf +++ b/roles/openshift_gcp/files/partition.conf @@ -1,3 +1,3 @@ [Service] ExecStartPost=-/usr/bin/growpart /dev/sda 1 -ExecStartPost=-/sbin/xfs_growfs / +ExecStartPost=-/sbin/xfs_growfs /
\ No newline at end of file diff --git a/roles/openshift_gcp/meta/main.yml b/roles/openshift_gcp/meta/main.yml new file mode 100644 index 000000000..5e428f8de --- /dev/null +++ b/roles/openshift_gcp/meta/main.yml @@ -0,0 +1,17 @@ +--- +galaxy_info: + author: Clayton Coleman + description: + company: Red Hat, Inc. + license: Apache License, Version 2.0 + min_ansible_version: 1.8 + platforms: + - name: EL + versions: + - 7 + categories: + - cloud + - system +dependencies: +- role: lib_utils +- role: lib_openshift diff --git a/roles/openshift_gcp/tasks/add_custom_repositories.yml b/roles/openshift_gcp/tasks/add_custom_repositories.yml new file mode 100644 index 000000000..04718f78e --- /dev/null +++ b/roles/openshift_gcp/tasks/add_custom_repositories.yml @@ -0,0 +1,20 @@ +--- +- name: Copy custom repository secrets + copy: + src: "{{ files_dir }}/{{ item.1.sslclientcert }}" + dest: /var/lib/yum/custom_secret_{{ item.0 }}_cert + when: item.1.sslclientcert | default(false) + with_indexed_items: "{{ provision_custom_repositories }}" +- name: Copy custom repository secrets + copy: + src: "{{ files_dir }}/{{ item.1.sslclientkey }}" + dest: /var/lib/yum/custom_secret_{{ item.0 }}_key + when: item.1.sslclientkey | default(false) + with_indexed_items: "{{ provision_custom_repositories }}" + +- name: Create any custom repos that are defined + template: + src: yum_repo.j2 + dest: /etc/yum.repos.d/provision_custom_repositories.repo + when: provision_custom_repositories | length > 0 + notify: refresh cache diff --git a/roles/openshift_gcp_image_prep/tasks/main.yaml b/roles/openshift_gcp/tasks/configure_gcp_base_image.yml index fee5ab618..2c6e2790a 100644 --- a/roles/openshift_gcp_image_prep/tasks/main.yaml +++ b/roles/openshift_gcp/tasks/configure_gcp_base_image.yml @@ -1,18 +1,10 @@ ---- # GCE instances are starting with xfs AND barrier=1, which is only for extfs. +--- - name: Remove barrier=1 from XFS fstab entries - lineinfile: - path: /etc/fstab - regexp: '^(.+)xfs(.+?),?barrier=1,?(.*?)$' - line: '\1xfs\2 \4' - backrefs: yes + command: sed -i -e 's/xfs\(.*\)barrier=1/xfs\1/g; s/, / /g' /etc/fstab - name: Ensure the root filesystem has XFS group quota turned on - lineinfile: - path: /boot/grub2/grub.cfg - regexp: '^(.*)linux16 (.*)$' - line: '\1linux16 \2 rootflags=gquota' - backrefs: yes + command: sed -i -e 's/linux16 \(.*\)$/linux16 \1 rootflags=gquota/g' /boot/grub2/grub.cfg - name: Ensure the root partition grows on startup copy: src=partition.conf dest=/etc/systemd/system/google-instance-setup.service.d/ diff --git a/roles/openshift_gcp/tasks/configure_master_bootstrap.yml b/roles/openshift_gcp/tasks/configure_master_bootstrap.yml new file mode 100644 index 000000000..591cb593c --- /dev/null +++ b/roles/openshift_gcp/tasks/configure_master_bootstrap.yml @@ -0,0 +1,36 @@ +# +# These tasks configure the instance to periodically update the project metadata with the +# latest bootstrap kubeconfig from the project metadata. This keeps the project metadata +# in sync with the cluster's configuration. We then invoke a CSR approve on any nodes that +# are waiting to join the cluster. +# +--- +- name: Copy unit service + copy: + src: openshift-bootstrap-update.timer + dest: /etc/systemd/system/openshift-bootstrap-update.timer + owner: root + group: root + mode: 0664 + +- name: Copy unit timer + copy: + src: openshift-bootstrap-update.service + dest: /etc/systemd/system/openshift-bootstrap-update.service + owner: root + group: root + mode: 0664 + +- name: Create bootstrap update script + template: src=openshift-bootstrap-update.j2 dest=/usr/bin/openshift-bootstrap-update mode=u+rx + +- name: Start bootstrap update timer + systemd: + name: "openshift-bootstrap-update.timer" + state: started + +- name: Bootstrap all nodes that were identified with bootstrap metadata + run_once: true + oc_adm_csr: + nodes: "{{ groups['all'] | map('extract', hostvars) | selectattr('gce_metadata.bootstrap', 'match', 'true') | map(attribute='gce_name') | list }}" + timeout: 60 diff --git a/roles/openshift_gcp/tasks/configure_master_healthcheck.yml b/roles/openshift_gcp/tasks/configure_master_healthcheck.yml new file mode 100644 index 000000000..aa9655977 --- /dev/null +++ b/roles/openshift_gcp/tasks/configure_master_healthcheck.yml @@ -0,0 +1,19 @@ +--- +- name: refresh yum cache + command: yum clean all + args: + warn: no + when: ansible_os_family == "RedHat" + +- name: install haproxy + package: name=haproxy state=present + register: result + until: '"failed" not in result' + retries: 10 + delay: 10 + +- name: configure haproxy + template: src=master_healthcheck.j2 dest=/etc/haproxy/haproxy.cfg + +- name: start and enable haproxy service + service: name=haproxy state=started enabled=yes diff --git a/roles/openshift_gcp/tasks/dynamic_inventory.yml b/roles/openshift_gcp/tasks/dynamic_inventory.yml new file mode 100644 index 000000000..1637da945 --- /dev/null +++ b/roles/openshift_gcp/tasks/dynamic_inventory.yml @@ -0,0 +1,5 @@ +--- +- name: Extract PEM from service account file + copy: content="{{ (lookup('file', openshift_gcp_iam_service_account_keyfile ) | from_json ).private_key }}" dest=/tmp/gce.pem mode=0600 +- name: Templatize environment script + template: src=inventory.j2.sh dest=/tmp/inventory.sh mode=u+rx diff --git a/roles/openshift_gcp/tasks/frequent_log_rotation.yml b/roles/openshift_gcp/tasks/frequent_log_rotation.yml new file mode 100644 index 000000000..0b4b27f84 --- /dev/null +++ b/roles/openshift_gcp/tasks/frequent_log_rotation.yml @@ -0,0 +1,18 @@ +--- +- name: Rotate logs daily + replace: + dest: /etc/logrotate.conf + regexp: '^weekly|monthly|yearly$' + replace: daily +- name: Rotate at a smaller size of log + lineinfile: + dest: /etc/logrotate.conf + state: present + regexp: '^size' + line: size 10M +- name: Limit total size of log files + lineinfile: + dest: /etc/logrotate.conf + state: present + regexp: '^maxsize' + line: maxsize 20M diff --git a/roles/openshift_gcp/tasks/main.yaml b/roles/openshift_gcp/tasks/main.yml index ad205ba33..fb147bc78 100644 --- a/roles/openshift_gcp/tasks/main.yaml +++ b/roles/openshift_gcp/tasks/main.yml @@ -17,7 +17,7 @@ - name: Provision GCP DNS domain command: /tmp/openshift_gcp_provision_dns.sh args: - chdir: "{{ playbook_dir }}/files" + chdir: "{{ files_dir }}" register: dns_provision when: - state | default('present') == 'present' @@ -33,7 +33,7 @@ - name: Provision GCP resources command: /tmp/openshift_gcp_provision.sh args: - chdir: "{{ playbook_dir }}/files" + chdir: "{{ files_dir }}" when: - state | default('present') == 'present' diff --git a/roles/openshift_gcp/tasks/node_cloud_config.yml b/roles/openshift_gcp/tasks/node_cloud_config.yml new file mode 100644 index 000000000..4e982f497 --- /dev/null +++ b/roles/openshift_gcp/tasks/node_cloud_config.yml @@ -0,0 +1,12 @@ +--- +- name: ensure the /etc/origin folder exists + file: name=/etc/origin state=directory + +- name: configure gce cloud config options + ini_file: dest=/etc/origin/cloudprovider/gce.conf section=Global option={{ item.key }} value={{ item.value }} state=present create=yes + with_items: + - { key: 'project-id', value: '{{ openshift_gcp_project }}' } + - { key: 'network-name', value: '{{ openshift_gcp_network_name }}' } + - { key: 'node-tags', value: '{{ openshift_gcp_prefix }}ocp' } + - { key: 'node-instance-prefix', value: '{{ openshift_gcp_prefix }}' } + - { key: 'multizone', value: 'false' } diff --git a/roles/openshift_gcp/tasks/publish_image.yml b/roles/openshift_gcp/tasks/publish_image.yml new file mode 100644 index 000000000..db8a7ca69 --- /dev/null +++ b/roles/openshift_gcp/tasks/publish_image.yml @@ -0,0 +1,32 @@ +--- +- name: Require openshift_gcp_image + fail: + msg: "A source image name or family is required for image publishing. Please ensure `openshift_gcp_image` is defined." + when: openshift_gcp_image is undefined + +- name: Require openshift_gcp_target_image + fail: + msg: "A target image name or family is required for image publishing. Please ensure `openshift_gcp_target_image` is defined." + when: openshift_gcp_target_image is undefined + +- block: + - name: Retrieve images in the {{ openshift_gcp_target_image }} family + command: > + gcloud --project "{{ openshift_gcp_project }}" compute images list + "--filter=family={{ openshift_gcp_target_image }}" + --format=json --sort-by ~creationTimestamp + register: images + - name: Prune oldest images + command: > + gcloud --project "{{ openshift_gcp_project }}" compute images delete "{{ item['name'] }}" + with_items: "{{ (images.stdout | default('[]') | from_json )[( openshift_gcp_keep_images | int ):] }}" + when: openshift_gcp_keep_images is defined + +- name: Copy the latest image in the family {{ openshift_gcp_image }} to {{ openshift_gcp_target_image }} + command: > + gcloud --project "{{ openshift_gcp_target_project | default(openshift_gcp_project) }}" + beta compute images create + "{{ openshift_gcp_target_image_name | default(openshift_gcp_target_image + '-' + lookup('pipe','date +%Y%m%d-%H%M%S')) }}" + --family "{{ openshift_gcp_target_image }}" + --source-image-family "{{ openshift_gcp_image }}" + --source-image-project "{{ openshift_gcp_project }}" diff --git a/roles/openshift_gcp/tasks/setup_scale_group_facts.yml b/roles/openshift_gcp/tasks/setup_scale_group_facts.yml new file mode 100644 index 000000000..0fda43123 --- /dev/null +++ b/roles/openshift_gcp/tasks/setup_scale_group_facts.yml @@ -0,0 +1,44 @@ +--- +- name: Add masters to requisite groups + add_host: + name: "{{ hostvars[item].gce_name }}" + groups: masters, etcd + with_items: "{{ groups['tag_ocp-master'] }}" + +- name: Add a master to the primary masters group + add_host: + name: "{{ hostvars[item].gce_name }}" + groups: primary_master + with_items: "{{ groups['tag_ocp-master'].0 }}" + +- name: Add non-bootstrapping master node instances to node group + add_host: + name: "{{ hostvars[item].gce_name }}" + groups: nodes + openshift_node_labels: + role: infra + with_items: "{{ groups['tag_ocp-master'] | default([]) | difference(groups['tag_ocp-bootstrap'] | default([])) }}" + +- name: Add infra node instances to node group + add_host: + name: "{{ hostvars[item].gce_name }}" + groups: nodes + openshift_node_labels: + role: infra + with_items: "{{ groups['tag_ocp-infra-node'] | default([]) | difference(groups['tag_ocp-bootstrap'] | default([])) }}" + +- name: Add node instances to node group + add_host: + name: "{{ hostvars[item].gce_name }}" + groups: nodes + openshift_node_labels: + role: app + with_items: "{{ groups['tag_ocp-node'] | default([]) | difference(groups['tag_ocp-bootstrap'] | default([])) }}" + +- name: Add bootstrap node instances + add_host: + name: "{{ hostvars[item].gce_name }}" + groups: bootstrap_nodes + openshift_node_bootstrap: True + with_items: "{{ groups['tag_ocp-node'] | default([]) | intersect(groups['tag_ocp-bootstrap'] | default([])) }}" + when: not (openshift_node_bootstrap | default(False)) diff --git a/roles/openshift_gcp/templates/inventory.j2.sh b/roles/openshift_gcp/templates/inventory.j2.sh new file mode 100644 index 000000000..dcaffb578 --- /dev/null +++ b/roles/openshift_gcp/templates/inventory.j2.sh @@ -0,0 +1,8 @@ +#!/bin/sh + +export GCE_PROJECT="{{ openshift_gcp_project }}" +export GCE_ZONE="{{ openshift_gcp_zone }}" +export GCE_EMAIL="{{ (lookup('file', openshift_gcp_iam_service_account_keyfile ) | from_json ).client_email }}" +export GCE_PEM_FILE_PATH="/tmp/gce.pem" +export INVENTORY_IP_TYPE="{{ inventory_ip_type }}" +export GCE_TAGGED_INSTANCES="{{ openshift_gcp_prefix }}ocp"
\ No newline at end of file diff --git a/roles/openshift_gcp/templates/master_healthcheck.j2 b/roles/openshift_gcp/templates/master_healthcheck.j2 new file mode 100644 index 000000000..189e578c5 --- /dev/null +++ b/roles/openshift_gcp/templates/master_healthcheck.j2 @@ -0,0 +1,68 @@ +#--------------------------------------------------------------------- +# Example configuration for a possible web application. See the +# full configuration options online. +# +# http://haproxy.1wt.eu/download/1.4/doc/configuration.txt +# +#--------------------------------------------------------------------- + +#--------------------------------------------------------------------- +# Global settings +#--------------------------------------------------------------------- +global + # to have these messages end up in /var/log/haproxy.log you will + # need to: + # + # 1) configure syslog to accept network log events. This is done + # by adding the '-r' option to the SYSLOGD_OPTIONS in + # /etc/sysconfig/syslog + # + # 2) configure local2 events to go to the /var/log/haproxy.log + # file. A line like the following can be added to + # /etc/sysconfig/syslog + # + # local2.* /var/log/haproxy.log + # + log 127.0.0.1 local2 + + chroot /var/lib/haproxy + pidfile /var/run/haproxy.pid + maxconn 4000 + user haproxy + group haproxy + daemon + + # turn on stats unix socket + stats socket /var/lib/haproxy/stats + +#--------------------------------------------------------------------- +# common defaults that all the 'listen' and 'backend' sections will +# use if not designated in their block +#--------------------------------------------------------------------- +defaults + mode http + log global + option httplog + option dontlognull + option http-server-close + option forwardfor except 127.0.0.0/8 + option redispatch + retries 3 + timeout http-request 10s + timeout queue 1m + timeout connect 10s + timeout client 1m + timeout server 1m + timeout http-keep-alive 10s + timeout check 10s + maxconn 3000 + +#--------------------------------------------------------------------- +# main frontend which proxys to the backends +#--------------------------------------------------------------------- +frontend http-proxy *:8080 + acl url_healthz path_beg -i /healthz + use_backend ocp if url_healthz + +backend ocp + server ocp localhost:{{ internal_console_port }} ssl verify none diff --git a/roles/openshift_gcp/templates/openshift-bootstrap-update.j2 b/roles/openshift_gcp/templates/openshift-bootstrap-update.j2 new file mode 100644 index 000000000..5b0563724 --- /dev/null +++ b/roles/openshift_gcp/templates/openshift-bootstrap-update.j2 @@ -0,0 +1,7 @@ +#!/bin/bash + +set -euo pipefail + +oc serviceaccounts create-kubeconfig -n openshift-infra node-bootstrapper > /root/bootstrap.kubeconfig +gcloud compute project-info --project '{{ openshift_gcp_project }}' add-metadata --metadata-from-file '{{ openshift_gcp_prefix + openshift_gcp_clusterid | default("default") }}-bootstrap-config=/root/bootstrap.kubeconfig' +rm -f /root/bootstrap.kubeconfig diff --git a/roles/openshift_gcp/templates/provision.j2.sh b/roles/openshift_gcp/templates/provision.j2.sh index 4d150bc74..794985322 100644 --- a/roles/openshift_gcp/templates/provision.j2.sh +++ b/roles/openshift_gcp/templates/provision.j2.sh @@ -9,15 +9,26 @@ if [[ -n "{{ openshift_gcp_ssh_private_key }}" ]]; then ssh-add "{{ openshift_gcp_ssh_private_key }}" || true fi - # Check if the ~/.ssh/google_compute_engine.pub key is in the project metadata, and if not, add it there - pub_key=$(cut -d ' ' -f 2 < "{{ openshift_gcp_ssh_private_key }}.pub") + # Check if the public key is in the project metadata, and if not, add it there + if [ -f "{{ openshift_gcp_ssh_private_key }}.pub" ]; then + pub_file="{{ openshift_gcp_ssh_private_key }}.pub" + pub_key=$(cut -d ' ' -f 2 < "{{ openshift_gcp_ssh_private_key }}.pub") + else + keyfile="${HOME}/.ssh/google_compute_engine" + pub_file="${keyfile}.pub" + mkdir -p "${HOME}/.ssh" + cp "{{ openshift_gcp_ssh_private_key }}" "${keyfile}" + chmod 0600 "${keyfile}" + ssh-keygen -y -f "${keyfile}" > "${pub_file}" + pub_key=$(cut -d ' ' -f 2 < "${pub_file}") + fi key_tmp_file='/tmp/ocp-gce-keys' if ! gcloud --project "{{ openshift_gcp_project }}" compute project-info describe | grep -q "$pub_key"; then if gcloud --project "{{ openshift_gcp_project }}" compute project-info describe | grep -q ssh-rsa; then gcloud --project "{{ openshift_gcp_project }}" compute project-info describe | grep ssh-rsa | sed -e 's/^[[:space:]]*//' -e 's/[[:space:]]*$//' -e 's/value: //' > "$key_tmp_file" fi echo -n 'cloud-user:' >> "$key_tmp_file" - cat "{{ openshift_gcp_ssh_private_key }}.pub" >> "$key_tmp_file" + cat "${pub_file}" >> "$key_tmp_file" gcloud --project "{{ openshift_gcp_project }}" compute project-info add-metadata --metadata-from-file "sshKeys=${key_tmp_file}" rm -f "$key_tmp_file" fi diff --git a/roles/openshift_gcp/templates/yum_repo.j2 b/roles/openshift_gcp/templates/yum_repo.j2 new file mode 100644 index 000000000..77919ea75 --- /dev/null +++ b/roles/openshift_gcp/templates/yum_repo.j2 @@ -0,0 +1,20 @@ +{% for repo in provision_custom_repositories %} +[{{ repo.id | default(repo.name) }}] +name={{ repo.name | default(repo.id) }} +baseurl={{ repo.baseurl }} +{% set enable_repo = repo.enabled | default(1) %} +enabled={{ 1 if ( enable_repo == 1 or enable_repo == True ) else 0 }} +{% set enable_gpg_check = repo.gpgcheck | default(1) %} +gpgcheck={{ 1 if ( enable_gpg_check == 1 or enable_gpg_check == True ) else 0 }} +{% if 'sslclientcert' in repo %} +sslclientcert={{ "/var/lib/yum/custom_secret_" + (loop.index-1)|string + "_cert" if repo.sslclientcert }} +{% endif %} +{% if 'sslclientkey' in repo %} +sslclientkey={{ "/var/lib/yum/custom_secret_" + (loop.index-1)|string + "_key" if repo.sslclientkey }} +{% endif %} +{% for key, value in repo.iteritems() %} +{% if key not in ['id', 'name', 'baseurl', 'enabled', 'gpgcheck', 'sslclientkey', 'sslclientcert'] and value is defined %} +{{ key }}={{ value }} +{% endif %} +{% endfor %} +{% endfor %} diff --git a/roles/openshift_grafana/defaults/main.yml b/roles/openshift_grafana/defaults/main.yml new file mode 100644 index 000000000..7fd7a085d --- /dev/null +++ b/roles/openshift_grafana/defaults/main.yml @@ -0,0 +1,12 @@ +--- +gf_body_tmp: + name: grafana_name + type: prometheus + typeLogoUrl: '' + access: proxy + url: prometheus_url + basicAuth: false + withCredentials: false + jsonData: + tlsSkipVerify: true + token: satoken diff --git a/roles/openshift_grafana/files/grafana-ocp-oauth.yml b/roles/openshift_grafana/files/grafana-ocp-oauth.yml new file mode 100644 index 000000000..82fa89004 --- /dev/null +++ b/roles/openshift_grafana/files/grafana-ocp-oauth.yml @@ -0,0 +1,661 @@ +--- +kind: Template +apiVersion: v1 +metadata: + name: grafana-ocp + annotations: + "openshift.io/display-name": Grafana ocp + description: | + Grafana server with patched Prometheus datasource. + iconClass: icon-cogs + tags: "metrics,monitoring,grafana,prometheus" +parameters: +- description: The location of the proxy image + name: IMAGE_GF + value: mrsiano/grafana-ocp:latest +- description: The location of the proxy image + name: IMAGE_PROXY + value: openshift/oauth-proxy:v1.0.0 +- description: External URL for the grafana route + name: ROUTE_URL + value: "" +- description: The namespace to instantiate heapster under. Defaults to 'grafana'. + name: NAMESPACE + value: grafana +- description: The session secret for the proxy + name: SESSION_SECRET + generate: expression + from: "[a-zA-Z0-9]{43}" +objects: +- apiVersion: v1 + kind: ServiceAccount + metadata: + name: grafana-ocp + namespace: "${NAMESPACE}" + annotations: + serviceaccounts.openshift.io/oauth-redirectreference.primary: '{"kind":"OAuthRedirectReference","apiVersion":"v1","reference":{"kind":"Route","name":"grafana-ocp"}}' +- apiVersion: authorization.openshift.io/v1 + kind: ClusterRoleBinding + metadata: + name: gf-cluster-reader + roleRef: + name: cluster-reader + subjects: + - kind: ServiceAccount + name: grafana-ocp + namespace: "${NAMESPACE}" +- apiVersion: route.openshift.io/v1 + kind: Route + metadata: + name: grafana-ocp + namespace: "${NAMESPACE}" + spec: + host: "${ROUTE_URL}" + to: + name: grafana-ocp + tls: + termination: Reencrypt +- apiVersion: v1 + kind: Service + metadata: + name: grafana-ocp + annotations: + prometheus.io/scrape: "true" + prometheus.io/scheme: https + service.alpha.openshift.io/serving-cert-secret-name: gf-tls + namespace: "${NAMESPACE}" + labels: + metrics-infra: grafana-ocp + name: grafana-ocp + spec: + ports: + - name: grafana-ocp + port: 443 + protocol: TCP + targetPort: 8443 + selector: + app: grafana-ocp +- apiVersion: v1 + kind: Secret + metadata: + name: gf-proxy + namespace: "${NAMESPACE}" + stringData: + session_secret: "${SESSION_SECRET}=" +# Deploy Prometheus behind an oauth proxy +- apiVersion: extensions/v1beta1 + kind: Deployment + metadata: + labels: + app: grafana-ocp + name: grafana-ocp + namespace: "${NAMESPACE}" + spec: + replicas: 1 + selector: + matchLabels: + app: grafana-ocp + template: + metadata: + labels: + app: grafana-ocp + name: grafana-ocp-app + spec: + serviceAccountName: grafana-ocp + containers: + - name: oauth-proxy + image: ${IMAGE_PROXY} + imagePullPolicy: IfNotPresent + ports: + - containerPort: 8443 + name: web + args: + - -https-address=:8443 + - -http-address= + - -email-domain=* + - -client-id=system:serviceaccount:${NAMESPACE}:grafana-ocp + - -upstream=http://localhost:3000 + - -provider=openshift +# - '-openshift-delegate-urls={"/api/datasources": {"resource": "namespace", "verb": "get", "resourceName": "grafana-ocp", "namespace": "${NAMESPACE}"}}' + - '-openshift-sar={"namespace": "${NAMESPACE}", "verb": "list", "resource": "services"}' + - -tls-cert=/etc/tls/private/tls.crt + - -tls-key=/etc/tls/private/tls.key + - -client-secret-file=/var/run/secrets/kubernetes.io/serviceaccount/token + - -cookie-secret-file=/etc/proxy/secrets/session_secret + - -skip-auth-regex=^/metrics,/api/datasources,/api/dashboards + volumeMounts: + - mountPath: /etc/tls/private + name: gf-tls + - mountPath: /etc/proxy/secrets + name: secrets + + - name: grafana-ocp + image: ${IMAGE_GF} + ports: + - name: grafana-http + containerPort: 3000 + volumeMounts: + - mountPath: "/root/go/src/github.com/grafana/grafana/data" + name: gf-data + - mountPath: "/root/go/src/github.com/grafana/grafana/conf" + name: gfconfig + - mountPath: /etc/tls/private + name: gf-tls + - mountPath: /etc/proxy/secrets + name: secrets + command: + - "./bin/grafana-server" + + volumes: + - name: gfconfig + configMap: + name: gf-config + - name: secrets + secret: + secretName: gf-proxy + - name: gf-tls + secret: + secretName: gf-tls + - emptyDir: {} + name: gf-data +- apiVersion: v1 + kind: ConfigMap + metadata: + name: gf-config + namespace: "${NAMESPACE}" + data: + defaults.ini: |- + ##################### Grafana Configuration Defaults ##################### + # + # Do not modify this file in grafana installs + # + + # possible values : production, development + app_mode = production + + # instance name, defaults to HOSTNAME environment variable value or hostname if HOSTNAME var is empty + instance_name = ${HOSTNAME} + + #################################### Paths ############################### + [paths] + # Path to where grafana can store temp files, sessions, and the sqlite3 db (if that is used) + # + data = data + # + # Directory where grafana can store logs + # + logs = data/log + # + # Directory where grafana will automatically scan and look for plugins + # + plugins = data/plugins + + #################################### Server ############################## + [server] + # Protocol (http, https, socket) + protocol = http + + # The ip address to bind to, empty will bind to all interfaces + http_addr = + + # The http port to use + http_port = 3000 + + # The public facing domain name used to access grafana from a browser + domain = localhost + + # Redirect to correct domain if host header does not match domain + # Prevents DNS rebinding attacks + enforce_domain = false + + # The full public facing url + root_url = %(protocol)s://%(domain)s:%(http_port)s/ + + # Log web requests + router_logging = false + + # the path relative working path + static_root_path = public + + # enable gzip + enable_gzip = false + + # https certs & key file + cert_file = /etc/tls/private/tls.crt + cert_key = /etc/tls/private/tls.key + + # Unix socket path + socket = /tmp/grafana.sock + + #################################### Database ############################ + [database] + # You can configure the database connection by specifying type, host, name, user and password + # as separate properties or as on string using the url property. + + # Either "mysql", "postgres" or "sqlite3", it's your choice + type = sqlite3 + host = 127.0.0.1:3306 + name = grafana + user = root + # If the password contains # or ; you have to wrap it with triple quotes. Ex """#password;""" + password = + # Use either URL or the previous fields to configure the database + # Example: mysql://user:secret@host:port/database + url = + + # Max idle conn setting default is 2 + max_idle_conn = 2 + + # Max conn setting default is 0 (mean not set) + max_open_conn = + + # For "postgres", use either "disable", "require" or "verify-full" + # For "mysql", use either "true", "false", or "skip-verify". + ssl_mode = disable + + ca_cert_path = + client_key_path = + client_cert_path = + server_cert_name = + + # For "sqlite3" only, path relative to data_path setting + path = grafana.db + + #################################### Session ############################# + [session] + # Either "memory", "file", "redis", "mysql", "postgres", "memcache", default is "file" + provider = file + + # Provider config options + # memory: not have any config yet + # file: session dir path, is relative to grafana data_path + # redis: config like redis server e.g. `addr=127.0.0.1:6379,pool_size=100,db=grafana` + # postgres: user=a password=b host=localhost port=5432 dbname=c sslmode=disable + # mysql: go-sql-driver/mysql dsn config string, examples: + # `user:password@tcp(127.0.0.1:3306)/database_name` + # `user:password@unix(/var/run/mysqld/mysqld.sock)/database_name` + # memcache: 127.0.0.1:11211 + + + provider_config = sessions + + # Session cookie name + cookie_name = grafana_sess + + # If you use session in https only, default is false + cookie_secure = false + + # Session life time, default is 86400 + session_life_time = 86400 + gc_interval_time = 86400 + + #################################### Data proxy ########################### + [dataproxy] + + # This enables data proxy logging, default is false + logging = false + + #################################### Analytics ########################### + [analytics] + # Server reporting, sends usage counters to stats.grafana.org every 24 hours. + # No ip addresses are being tracked, only simple counters to track + # running instances, dashboard and error counts. It is very helpful to us. + # Change this option to false to disable reporting. + reporting_enabled = true + + # Set to false to disable all checks to https://grafana.com + # for new versions (grafana itself and plugins), check is used + # in some UI views to notify that grafana or plugin update exists + # This option does not cause any auto updates, nor send any information + # only a GET request to https://grafana.com to get latest versions + check_for_updates = true + + # Google Analytics universal tracking code, only enabled if you specify an id here + google_analytics_ua_id = + + # Google Tag Manager ID, only enabled if you specify an id here + google_tag_manager_id = + + #################################### Security ############################ + [security] + # default admin user, created on startup + admin_user = admin + + # default admin password, can be changed before first start of grafana, or in profile settings + admin_password = admin + + # used for signing + secret_key = SW2YcwTIb9zpOOhoPsMm + + # Auto-login remember days + login_remember_days = 7 + cookie_username = grafana_user + cookie_remember_name = grafana_remember + + # disable gravatar profile images + disable_gravatar = false + + # data source proxy whitelist (ip_or_domain:port separated by spaces) + data_source_proxy_whitelist = + + [snapshots] + # snapshot sharing options + external_enabled = true + external_snapshot_url = https://snapshots-origin.raintank.io + external_snapshot_name = Publish to snapshot.raintank.io + + # remove expired snapshot + snapshot_remove_expired = true + + # remove snapshots after 90 days + snapshot_TTL_days = 90 + + #################################### Users #################################### + [users] + # disable user signup / registration + allow_sign_up = true + + # Allow non admin users to create organizations + allow_org_create = true + + # Set to true to automatically assign new users to the default organization (id 1) + auto_assign_org = true + + # Default role new users will be automatically assigned (if auto_assign_org above is set to true) + auto_assign_org_role = Admin + + # Require email validation before sign up completes + verify_email_enabled = false + + # Background text for the user field on the login page + login_hint = email or username + + # Default UI theme ("dark" or "light") + default_theme = dark + + # External user management + external_manage_link_url = + external_manage_link_name = + external_manage_info = + + [auth] + # Set to true to disable (hide) the login form, useful if you use OAuth + disable_login_form = true + + # Set to true to disable the signout link in the side menu. useful if you use auth.proxy + disable_signout_menu = true + + #################################### Anonymous Auth ###################### + [auth.anonymous] + # enable anonymous access + enabled = true + + # specify organization name that should be used for unauthenticated users + org_name = Main Org. + + # specify role for unauthenticated users + org_role = Admin + + #################################### Github Auth ######################### + [auth.github] + enabled = false + allow_sign_up = true + client_id = some_id + client_secret = some_secret + scopes = user:email + auth_url = https://github.com/login/oauth/authorize + token_url = https://github.com/login/oauth/access_token + api_url = https://api.github.com/user + team_ids = + allowed_organizations = + + #################################### Google Auth ######################### + [auth.google] + enabled = false + allow_sign_up = true + client_id = some_client_id + client_secret = some_client_secret + scopes = https://www.googleapis.com/auth/userinfo.profile https://www.googleapis.com/auth/userinfo.email + auth_url = https://accounts.google.com/o/oauth2/auth + token_url = https://accounts.google.com/o/oauth2/token + api_url = https://www.googleapis.com/oauth2/v1/userinfo + allowed_domains = + hosted_domain = + + #################################### Grafana.com Auth #################### + # legacy key names (so they work in env variables) + [auth.grafananet] + enabled = false + allow_sign_up = true + client_id = some_id + client_secret = some_secret + scopes = user:email + allowed_organizations = + + [auth.grafana_com] + enabled = false + allow_sign_up = true + client_id = some_id + client_secret = some_secret + scopes = user:email + allowed_organizations = + + #################################### Generic OAuth ####################### + [auth.generic_oauth] + name = OAuth + enabled = false + allow_sign_up = true + client_id = some_id + client_secret = some_secret + scopes = user:email + auth_url = + token_url = + api_url = + team_ids = + allowed_organizations = + + #################################### Basic Auth ########################## + [auth.basic] + enabled = false + + #################################### Auth Proxy ########################## + [auth.proxy] + enabled = true + header_name = X-WEBAUTH-USER + header_property = username + auto_sign_up = true + ldap_sync_ttl = 60 + whitelist = + + #################################### Auth LDAP ########################### + [auth.ldap] + enabled = false + config_file = /etc/grafana/ldap.toml + allow_sign_up = true + + #################################### SMTP / Emailing ##################### + [smtp] + enabled = false + host = localhost:25 + user = + # If the password contains # or ; you have to wrap it with trippel quotes. Ex """#password;""" + password = + cert_file = + key_file = + skip_verify = false + from_address = admin@grafana.localhost + from_name = Grafana + ehlo_identity = + + [emails] + welcome_email_on_sign_up = false + templates_pattern = emails/*.html + + #################################### Logging ########################## + [log] + # Either "console", "file", "syslog". Default is console and file + # Use space to separate multiple modes, e.g. "console file" + mode = console file + + # Either "debug", "info", "warn", "error", "critical", default is "info" + level = error + + # optional settings to set different levels for specific loggers. Ex filters = sqlstore:debug + filters = + + # For "console" mode only + [log.console] + level = + + # log line format, valid options are text, console and json + format = console + + # For "file" mode only + [log.file] + level = + + # log line format, valid options are text, console and json + format = text + + # This enables automated log rotate(switch of following options), default is true + log_rotate = true + + # Max line number of single file, default is 1000000 + max_lines = 1000000 + + # Max size shift of single file, default is 28 means 1 << 28, 256MB + max_size_shift = 28 + + # Segment log daily, default is true + daily_rotate = true + + # Expired days of log file(delete after max days), default is 7 + max_days = 7 + + [log.syslog] + level = + + # log line format, valid options are text, console and json + format = text + + # Syslog network type and address. This can be udp, tcp, or unix. If left blank, the default unix endpoints will be used. + network = + address = + + # Syslog facility. user, daemon and local0 through local7 are valid. + facility = + + # Syslog tag. By default, the process' argv[0] is used. + tag = + + + #################################### AMQP Event Publisher ################ + [event_publisher] + enabled = false + rabbitmq_url = amqp://localhost/ + exchange = grafana_events + + #################################### Dashboard JSON files ################ + [dashboards.json] + enabled = false + path = /var/lib/grafana/dashboards + + #################################### Usage Quotas ######################## + [quota] + enabled = false + + #### set quotas to -1 to make unlimited. #### + # limit number of users per Org. + org_user = 10 + + # limit number of dashboards per Org. + org_dashboard = 100 + + # limit number of data_sources per Org. + org_data_source = 10 + + # limit number of api_keys per Org. + org_api_key = 10 + + # limit number of orgs a user can create. + user_org = 10 + + # Global limit of users. + global_user = -1 + + # global limit of orgs. + global_org = -1 + + # global limit of dashboards + global_dashboard = -1 + + # global limit of api_keys + global_api_key = -1 + + # global limit on number of logged in users. + global_session = -1 + + #################################### Alerting ############################ + [alerting] + # Disable alerting engine & UI features + enabled = true + # Makes it possible to turn off alert rule execution but alerting UI is visible + execute_alerts = true + + #################################### Internal Grafana Metrics ############ + # Metrics available at HTTP API Url /api/metrics + [metrics] + enabled = true + interval_seconds = 10 + + # Send internal Grafana metrics to graphite + [metrics.graphite] + # Enable by setting the address setting (ex localhost:2003) + address = + prefix = prod.grafana.%(instance_name)s. + + [grafana_net] + url = https://grafana.com + + [grafana_com] + url = https://grafana.com + + #################################### Distributed tracing ############ + [tracing.jaeger] + # jaeger destination (ex localhost:6831) + address = + # tag that will always be included in when creating new spans. ex (tag1:value1,tag2:value2) + always_included_tag = + # Type specifies the type of the sampler: const, probabilistic, rateLimiting, or remote + sampler_type = const + # jaeger samplerconfig param + # for "const" sampler, 0 or 1 for always false/true respectively + # for "probabilistic" sampler, a probability between 0 and 1 + # for "rateLimiting" sampler, the number of spans per second + # for "remote" sampler, param is the same as for "probabilistic" + # and indicates the initial sampling rate before the actual one + # is received from the mothership + sampler_param = 1 + + #################################### External Image Storage ############## + [external_image_storage] + # You can choose between (s3, webdav, gcs) + provider = + + [external_image_storage.s3] + bucket_url = + bucket = + region = + path = + access_key = + secret_key = + + [external_image_storage.webdav] + url = + username = + password = + public_url = + + [external_image_storage.gcs] + key_file = + bucket = diff --git a/roles/openshift_grafana/files/grafana-ocp.yml b/roles/openshift_grafana/files/grafana-ocp.yml new file mode 100644 index 000000000..bc7b4b286 --- /dev/null +++ b/roles/openshift_grafana/files/grafana-ocp.yml @@ -0,0 +1,76 @@ +--- +kind: Template +apiVersion: v1 +metadata: + name: grafana-ocp + annotations: + "openshift.io/display-name": Grafana ocp + description: | + Grafana server with patched Prometheus datasource. + iconClass: icon-cogs + tags: "metrics,monitoring,grafana,prometheus" +parameters: +- description: External URL for the grafana route + name: ROUTE_URL + value: "" +- description: The namespace to instantiate heapster under. Defaults to 'grafana'. + name: NAMESPACE + value: grafana +objects: +- apiVersion: route.openshift.io/v1 + kind: Route + metadata: + name: grafana-ocp + namespace: "${NAMESPACE}" + spec: + host: "${ROUTE_URL}" + to: + name: grafana-ocp +- apiVersion: v1 + kind: Service + metadata: + name: grafana-ocp + namespace: "${NAMESPACE}" + labels: + metrics-infra: grafana-ocp + name: grafana-ocp + spec: + selector: + name: grafana-ocp + ports: + - port: 8082 + protocol: TCP + targetPort: grafana-http +- apiVersion: v1 + kind: ReplicationController + metadata: + name: grafana-ocp + namespace: "${NAMESPACE}" + labels: + metrics-infra: grafana-ocp + name: grafana-ocp + spec: + selector: + name: grafana-ocp + replicas: 1 + template: + version: v1 + metadata: + labels: + metrics-infra: grafana-ocp + name: grafana-ocp + spec: + volumes: + - name: data + emptyDir: {} + containers: + - image: "mrsiano/grafana-ocp:latest" + name: grafana-ocp + ports: + - name: grafana-http + containerPort: 3000 + volumeMounts: + - name: data + mountPath: "/root/go/src/github.com/grafana/grafana/data" + command: + - "./bin/grafana-server" diff --git a/roles/openshift_grafana/files/openshift-cluster-monitoring.json b/roles/openshift_grafana/files/openshift-cluster-monitoring.json new file mode 100644 index 000000000..f59ca997f --- /dev/null +++ b/roles/openshift_grafana/files/openshift-cluster-monitoring.json @@ -0,0 +1,5138 @@ +{ + "dashboard": { + "description": "Monitors Openshift cluster using Prometheus. Shows overall cluster CPU / Memory / Filesystem usage as well as individual pod, containers, systemd services statistics. Uses cAdvisor metrics only.", + "editable": true, + "gnetId": 315, + "graphTooltip": 0, + "hideControls": false, + "id": null, + "links": [], + "rows": [ + { + "collapse": false, + "height": "200px", + "panels": [ + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PR}", + "decimals": 2, + "editable": true, + "error": false, + "fill": 1, + "grid": {}, + "height": "200px", + "id": 32, + "legend": { + "alignAsTable": false, + "avg": true, + "current": true, + "max": false, + "min": false, + "rightSide": false, + "show": false, + "sideWidth": 200, + "sort": "current", + "sortDesc": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 2, + "links": [], + "nullPointMode": "connected", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum (irate (container_network_receive_bytes_total{kubernetes_io_hostname=~\"^$Node$\"}[2m]))", + "format": "time_series", + "instant": false, + "interval": "1s", + "intervalFactor": 1, + "legendFormat": "Received", + "metric": "network", + "refId": "A", + "step": 1 + }, + { + "expr": "- sum (irate (container_network_transmit_bytes_total{kubernetes_io_hostname=~\"^$Node$\"}[2m]))", + "format": "time_series", + "interval": "1s", + "intervalFactor": 1, + "legendFormat": "Sent", + "metric": "network", + "refId": "B", + "step": 1 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "Network I/O pressure", + "tooltip": { + "msResolution": false, + "shared": true, + "sort": 0, + "value_type": "cumulative" + }, + "transparent": false, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Network I/O pressure", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": true, + "colors": [ + "rgba(50, 172, 45, 0.97)", + "rgba(237, 129, 40, 0.89)", + "rgba(245, 54, 54, 0.9)" + ], + "datasource": "${DS_PR}", + "editable": true, + "error": false, + "format": "percent", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": true, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "height": "180px", + "id": 4, + "interval": null, + "links": [], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "span": 4, + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "sum (container_memory_working_set_bytes{id=\"/\",kubernetes_io_hostname=~\"^$Node$\"}) / sum (machine_memory_bytes{kubernetes_io_hostname=~\"^$Node$\"}) * 100", + "format": "time_series", + "interval": "", + "intervalFactor": 1, + "refId": "A", + "step": 20 + } + ], + "thresholds": "", + "title": "Cluster memory usage", + "transparent": false, + "type": "singlestat", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "current" + }, + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": true, + "colors": [ + "rgba(50, 172, 45, 0.97)", + "rgba(237, 129, 40, 0.89)", + "rgba(245, 54, 54, 0.9)" + ], + "datasource": "${DS_PR}", + "decimals": 2, + "editable": true, + "error": false, + "format": "percent", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": true, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "height": "180px", + "id": 6, + "interval": null, + "links": [], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "span": 4, + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "sum (irate (container_cpu_usage_seconds_total{id=\"/\",kubernetes_io_hostname=~\"^$Node$\"}[2m])) / sum (machine_cpu_cores{kubernetes_io_hostname=~\"^$Node$\"}) * 100", + "format": "time_series", + "interval": "", + "intervalFactor": 1, + "refId": "A", + "step": 20 + } + ], + "thresholds": "", + "title": "Cluster CPU usage ", + "type": "singlestat", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "current" + }, + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": true, + "colors": [ + "rgba(50, 172, 45, 0.97)", + "rgba(237, 129, 40, 0.89)", + "rgba(245, 54, 54, 0.9)" + ], + "datasource": "${DS_PR}", + "decimals": 2, + "editable": true, + "error": false, + "format": "percent", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": true, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "height": "180px", + "id": 7, + "interval": null, + "links": [], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "span": 4, + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "sum (container_fs_usage_bytes{device=~\"^/dev/mapper/docker_.*\",id=\"/\",kubernetes_io_hostname=~\"^$Node$\"}) / sum (container_fs_limit_bytes{device=~\"^/dev/mapper/docker_.*\",id=\"/\",kubernetes_io_hostname=~\"^$Node$\"}) * 100", + "format": "time_series", + "hide": false, + "interval": "", + "intervalFactor": 1, + "legendFormat": "", + "metric": "", + "refId": "A", + "step": 20 + } + ], + "thresholds": "", + "title": "Cluster filesystem usage", + "type": "singlestat", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "current" + }, + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "rgba(50, 172, 45, 0.97)", + "rgba(237, 129, 40, 0.89)", + "rgba(245, 54, 54, 0.9)" + ], + "datasource": "${DS_PR}", + "decimals": 2, + "editable": true, + "error": false, + "format": "bytes", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "height": "1px", + "id": 9, + "interval": null, + "links": [], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "postfix": "", + "postfixFontSize": "20%", + "prefix": "", + "prefixFontSize": "20%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "span": 2, + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "sum (container_memory_working_set_bytes{id=\"/\",kubernetes_io_hostname=~\"^$Node$\"})", + "format": "time_series", + "interval": "", + "intervalFactor": 1, + "refId": "A", + "step": 20 + } + ], + "thresholds": "", + "title": "Used", + "type": "singlestat", + "valueFontSize": "50%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "current" + }, + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "rgba(50, 172, 45, 0.97)", + "rgba(237, 129, 40, 0.89)", + "rgba(245, 54, 54, 0.9)" + ], + "datasource": "${DS_PR}", + "decimals": 2, + "editable": true, + "error": false, + "format": "bytes", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "height": "1px", + "id": 10, + "interval": null, + "links": [], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "span": 2, + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "sum (machine_memory_bytes{kubernetes_io_hostname=~\"^$Node$\"})", + "format": "time_series", + "interval": "", + "intervalFactor": 1, + "refId": "A", + "step": 20 + } + ], + "thresholds": "", + "title": "Total", + "type": "singlestat", + "valueFontSize": "50%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "current" + }, + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "rgba(50, 172, 45, 0.97)", + "rgba(237, 129, 40, 0.89)", + "rgba(245, 54, 54, 0.9)" + ], + "datasource": "${DS_PR}", + "decimals": 2, + "editable": true, + "error": false, + "format": "none", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "height": "1px", + "id": 11, + "interval": null, + "links": [], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "postfix": " cores", + "postfixFontSize": "30%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "span": 2, + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "sum (irate (container_cpu_usage_seconds_total{id=\"/\",kubernetes_io_hostname=~\"^$Node$\"}[2m]))", + "format": "time_series", + "interval": "", + "intervalFactor": 1, + "refId": "A", + "step": 20 + } + ], + "thresholds": "", + "title": "Used", + "type": "singlestat", + "valueFontSize": "50%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "current" + }, + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "rgba(50, 172, 45, 0.97)", + "rgba(237, 129, 40, 0.89)", + "rgba(245, 54, 54, 0.9)" + ], + "datasource": "${DS_PR}", + "decimals": 2, + "editable": true, + "error": false, + "format": "none", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "height": "1px", + "id": 12, + "interval": null, + "links": [], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "postfix": " cores", + "postfixFontSize": "30%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "span": 2, + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "sum (machine_cpu_cores{kubernetes_io_hostname=~\"^$Node$\"})", + "format": "time_series", + "interval": "", + "intervalFactor": 1, + "refId": "A", + "step": 20 + } + ], + "thresholds": "", + "title": "Total", + "type": "singlestat", + "valueFontSize": "50%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "current" + }, + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "rgba(50, 172, 45, 0.97)", + "rgba(237, 129, 40, 0.89)", + "rgba(245, 54, 54, 0.9)" + ], + "datasource": "${DS_PR}", + "decimals": 2, + "editable": true, + "error": false, + "format": "bytes", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "height": "1px", + "id": 13, + "interval": null, + "links": [], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "span": 2, + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "sum (container_fs_usage_bytes{device=~\"^/dev/mapper/docker_.*$\",id=\"/\",kubernetes_io_hostname=~\"^$Node$\"})", + "format": "time_series", + "interval": "", + "intervalFactor": 1, + "refId": "A", + "step": 20 + } + ], + "thresholds": "", + "title": "Used", + "type": "singlestat", + "valueFontSize": "50%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "current" + }, + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "rgba(50, 172, 45, 0.97)", + "rgba(237, 129, 40, 0.89)", + "rgba(245, 54, 54, 0.9)" + ], + "datasource": "${DS_PR}", + "decimals": 2, + "editable": true, + "error": false, + "format": "bytes", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "height": "1px", + "id": 14, + "interval": null, + "links": [], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "span": 2, + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "sum (container_fs_limit_bytes{device=~\"^/dev/mapper/docker_.*$\",id=\"/\",kubernetes_io_hostname=~\"^$Node$\"})", + "format": "time_series", + "hide": false, + "interval": "", + "intervalFactor": 1, + "refId": "A", + "step": 20 + } + ], + "thresholds": "", + "title": "Total", + "type": "singlestat", + "valueFontSize": "50%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "current" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Total usage", + "titleSize": "h6" + }, + { + "collapse": true, + "height": 250, + "panels": [ + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PR}", + "fill": 1, + "id": 33, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum (irate (container_cpu_usage_seconds_total{id=\"/\",kubernetes_io_hostname=~\"^$Node$\"}[2m])) / sum (machine_cpu_cores{kubernetes_io_hostname=~\"^$Node$\"}) ", + "format": "time_series", + "hide": false, + "interval": "1s", + "intervalFactor": 1, + "legendFormat": "overall cpu usage", + "refId": "A", + "step": 1 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "Cluster CPU Usage", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "percent", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Dashboard Row", + "titleSize": "h6" + }, + { + "collapse": true, + "height": "250px", + "panels": [ + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PR}", + "decimals": 3, + "editable": true, + "error": false, + "fill": 0, + "grid": {}, + "height": "", + "id": 17, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sort": "current", + "sortDesc": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "connected", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": true, + "targets": [ + { + "expr": "sum (irate (container_cpu_usage_seconds_total{image!=\"\",name=~\"^k8s_.*\",kubernetes_io_hostname=~\"^$Node$\"}[2m])) by (pod_name) * 100", + "format": "time_series", + "hide": false, + "interval": "", + "intervalFactor": 1, + "legendFormat": "{{ pod_name }}", + "metric": "container_cpu", + "refId": "A", + "step": 2 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "Pods CPU usage ", + "tooltip": { + "msResolution": true, + "shared": true, + "sort": 2, + "value_type": "cumulative" + }, + "transparent": false, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "percent", + "label": "% Usage", + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Pods CPU usage", + "titleSize": "h6" + }, + { + "collapse": true, + "height": "250px", + "panels": [ + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PR}", + "decimals": 3, + "editable": true, + "error": false, + "fill": 0, + "grid": {}, + "height": "", + "id": 24, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "hideEmpty": false, + "hideZero": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "sort": "current", + "sortDesc": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 2, + "links": [], + "nullPointMode": "connected", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": true, + "targets": [ + { + "expr": "sum (irate (container_cpu_usage_seconds_total{image!=\"\",name=~\"^k8s_.*\",container_name!=\"POD\",kubernetes_io_hostname=~\"^$Node$\"}[2m])) by (container_name, pod_name)", + "format": "time_series", + "hide": false, + "interval": "1s", + "intervalFactor": 1, + "legendFormat": "pod: {{ pod_name }} | {{ container_name }}", + "metric": "container_cpu", + "refId": "A", + "step": 2 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "Containers Cores Usage", + "tooltip": { + "msResolution": true, + "shared": true, + "sort": 2, + "value_type": "cumulative" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "none", + "label": "cores", + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Containers CPU usage", + "titleSize": "h6" + }, + { + "collapse": true, + "height": "250px", + "panels": [ + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PR}", + "decimals": 3, + "editable": true, + "error": false, + "fill": 0, + "grid": {}, + "height": "", + "id": 23, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sort": "current", + "sortDesc": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 2, + "links": [], + "nullPointMode": "connected", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": true, + "targets": [ + { + "expr": "sum (irate (container_cpu_usage_seconds_total{id!=\"/\",kubernetes_io_hostname=~\"^$Node$\"}[2m])) by (id)", + "format": "time_series", + "hide": false, + "interval": "1s", + "intervalFactor": 1, + "legendFormat": "{{ id }}", + "metric": "container_cpu", + "refId": "A", + "step": 2 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "System services CPU usage ", + "tooltip": { + "msResolution": true, + "shared": true, + "sort": 2, + "value_type": "cumulative" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "none", + "label": "cores", + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "System services CPU usage", + "titleSize": "h6" + }, + { + "collapse": true, + "height": 411, + "panels": [ + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PR}", + "decimals": 3, + "editable": true, + "error": false, + "fill": 0, + "grid": {}, + "id": 34, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sort": "current", + "sortDesc": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 2, + "links": [], + "nullPointMode": "connected", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": true, + "targets": [ + { + "expr": "sum (irate (container_memory_usage_bytes{id!=\"/\",kubernetes_io_hostname=~\"^$Node$\"}[2m])) by (id)", + "format": "time_series", + "hide": false, + "interval": "1s", + "intervalFactor": 1, + "legendFormat": "{{ id }}", + "metric": "container_cpu", + "refId": "A", + "step": 2 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "All processes Memory usage ", + "tooltip": { + "msResolution": true, + "shared": true, + "sort": 2, + "value_type": "cumulative" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "bytes", + "label": "cores", + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "All processes CPU usage", + "titleSize": "h6" + }, + { + "collapse": true, + "height": "250px", + "panels": [ + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PR}", + "decimals": 2, + "editable": true, + "error": false, + "fill": 0, + "grid": {}, + "id": 25, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": 200, + "sort": "current", + "sortDesc": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 2, + "links": [], + "nullPointMode": "connected", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": true, + "targets": [ + { + "expr": "sum (container_memory_working_set_bytes{image!=\"\",name=~\"^k8s_.*\",kubernetes_io_hostname=~\"^$Node$\"}) by (pod_name)", + "format": "time_series", + "interval": "1s", + "intervalFactor": 1, + "legendFormat": "{{ pod_name }}", + "metric": "container_memory_usage:sort_desc", + "refId": "A", + "step": 10 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "Pods memory usage", + "tooltip": { + "msResolution": false, + "shared": true, + "sort": 2, + "value_type": "cumulative" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Pods memory usage", + "titleSize": "h6" + }, + { + "collapse": true, + "height": "250px", + "panels": [ + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PR}", + "decimals": 2, + "editable": true, + "error": false, + "fill": 0, + "grid": {}, + "id": 26, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": 200, + "sort": "current", + "sortDesc": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 2, + "links": [], + "nullPointMode": "connected", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": true, + "targets": [ + { + "expr": "sum (container_memory_rss{systemd_service_name=\"\",kubernetes_io_hostname=~\"^$Node$\"}) by (systemd_service_name)", + "format": "time_series", + "hide": false, + "interval": "1s", + "intervalFactor": 1, + "legendFormat": "{{ systemd_service_name }}", + "metric": "container_memory_usage:sort_desc", + "refId": "B", + "step": 2 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "System services memory usage", + "tooltip": { + "msResolution": false, + "shared": true, + "sort": 2, + "value_type": "cumulative" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "System services memory usage", + "titleSize": "h6" + }, + { + "collapse": true, + "height": "250px", + "panels": [ + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PR}", + "decimals": 2, + "editable": true, + "error": false, + "fill": 0, + "grid": {}, + "id": 27, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": 200, + "sort": "current", + "sortDesc": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 2, + "links": [], + "nullPointMode": "connected", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": true, + "targets": [ + { + "expr": "sum (container_memory_working_set_bytes{image!=\"\",name=~\"^k8s_.*\",container_name!=\"POD\",kubernetes_io_hostname=~\"^$Node$\"}) by (container_name, pod_name)", + "format": "time_series", + "interval": "1s", + "intervalFactor": 1, + "legendFormat": "pod: {{ pod_name }} | {{ container_name }}", + "metric": "container_memory_usage:sort_desc", + "refId": "A", + "step": 10 + }, + { + "expr": "sum (container_memory_working_set_bytes{image!=\"\",name!~\"^k8s_.*\",kubernetes_io_hostname=~\"^$Node$\"}) by (kubernetes_io_hostname, name, image)", + "format": "time_series", + "hide": false, + "interval": "1s", + "intervalFactor": 1, + "legendFormat": "docker: {{ kubernetes_io_hostname }} | {{ image }} ({{ name }})", + "metric": "container_memory_usage:sort_desc", + "refId": "B", + "step": 10 + }, + { + "expr": "sum (container_memory_working_set_bytes{rkt_container_name!=\"\",kubernetes_io_hostname=~\"^$Node$\"}) by (kubernetes_io_hostname, rkt_container_name)", + "format": "time_series", + "hide": false, + "interval": "1s", + "intervalFactor": 1, + "legendFormat": "rkt: {{ kubernetes_io_hostname }} | {{ rkt_container_name }}", + "metric": "container_memory_usage:sort_desc", + "refId": "C", + "step": 10 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "Containers memory usage", + "tooltip": { + "msResolution": false, + "shared": true, + "sort": 2, + "value_type": "cumulative" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Containers memory usage", + "titleSize": "h6" + }, + { + "collapse": true, + "height": "500px", + "panels": [ + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PR}", + "decimals": 2, + "editable": true, + "error": false, + "fill": 0, + "grid": {}, + "id": 28, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": 200, + "sort": "current", + "sortDesc": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 2, + "links": [], + "nullPointMode": "connected", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": true, + "targets": [ + { + "expr": "sum (container_memory_working_set_bytes{id!=\"/\",kubernetes_io_hostname=~\"^$Node$\"}) by (id)", + "interval": "1s", + "intervalFactor": 1, + "legendFormat": "{{ id }}", + "metric": "container_memory_usage:sort_desc", + "refId": "A", + "step": 1 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "All processes memory usage", + "tooltip": { + "msResolution": false, + "shared": true, + "sort": 2, + "value_type": "cumulative" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "All processes memory usage", + "titleSize": "h6" + }, + { + "collapse": true, + "height": "250px", + "panels": [ + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PR}", + "decimals": 2, + "editable": true, + "error": false, + "fill": 1, + "grid": {}, + "id": 30, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": 200, + "sort": "current", + "sortDesc": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 2, + "links": [], + "nullPointMode": "connected", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum (irate (container_network_receive_bytes_total{image!=\"\",name=~\"^k8s_.*\",kubernetes_io_hostname=~\"^$Node$\"}[2m])) by (container_name, pod_name)", + "format": "time_series", + "hide": false, + "interval": "1s", + "intervalFactor": 1, + "legendFormat": "-> pod: {{ pod_name }} | {{ container_name }}", + "metric": "network", + "refId": "B", + "step": 1 + }, + { + "expr": "- sum (irate (container_network_transmit_bytes_total{image!=\"\",name=~\"^k8s_.*\",kubernetes_io_hostname=~\"^$Node$\"}[2m])) by (container_name, pod_name)", + "format": "time_series", + "hide": false, + "interval": "1s", + "intervalFactor": 1, + "legendFormat": "<- pod: {{ pod_name }} | {{ container_name }}", + "metric": "network", + "refId": "D", + "step": 1 + }, + { + "expr": "sum (irate (container_network_receive_bytes_total{image!=\"\",name!~\"^k8s_.*\",kubernetes_io_hostname=~\"^$Node$\"}[2m])) by (kubernetes_io_hostname, name, image)", + "format": "time_series", + "hide": false, + "interval": "1s", + "intervalFactor": 1, + "legendFormat": "-> docker: {{ kubernetes_io_hostname }} | {{ image }} ({{ name }})", + "metric": "network", + "refId": "A", + "step": 1 + }, + { + "expr": "- sum (irate (container_network_transmit_bytes_total{image!=\"\",name!~\"^k8s_.*\",kubernetes_io_hostname=~\"^$Node$\"}[2m])) by (kubernetes_io_hostname, name, image)", + "format": "time_series", + "hide": false, + "interval": "1s", + "intervalFactor": 1, + "legendFormat": "<- docker: {{ kubernetes_io_hostname }} | {{ image }} ({{ name }})", + "metric": "network", + "refId": "C", + "step": 1 + }, + { + "expr": "sum (irate (container_network_transmit_bytes_total{rkt_container_name!=\"\",kubernetes_io_hostname=~\"^$Node$\"}[2m])) by (kubernetes_io_hostname, rkt_container_name)", + "format": "time_series", + "hide": false, + "interval": "1s", + "intervalFactor": 1, + "legendFormat": "-> rkt: {{ kubernetes_io_hostname }} | {{ rkt_container_name }}", + "metric": "network", + "refId": "E", + "step": 1 + }, + { + "expr": "- sum (irate (container_network_transmit_bytes_total{rkt_container_name!=\"\",kubernetes_io_hostname=~\"^$Node$\"}[2m])) by (kubernetes_io_hostname, rkt_container_name)", + "format": "time_series", + "hide": false, + "interval": "1s", + "intervalFactor": 1, + "legendFormat": "<- rkt: {{ kubernetes_io_hostname }} | {{ rkt_container_name }}", + "metric": "network", + "refId": "F", + "step": 1 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "Containers network I/O ", + "tooltip": { + "msResolution": false, + "shared": true, + "sort": 2, + "value_type": "cumulative" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Containers network I/O", + "titleSize": "h6" + }, + { + "collapse": true, + "height": 277, + "panels": [ + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PR}", + "decimals": 2, + "editable": true, + "error": false, + "fill": 1, + "grid": {}, + "id": 16, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": 200, + "sort": "current", + "sortDesc": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 2, + "links": [], + "nullPointMode": "connected", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum (irate (container_network_receive_bytes_total{image!=\"\",name=~\"^k8s_.*\",kubernetes_io_hostname=~\"^$Node$\"}[2m])) by (pod_name)", + "format": "time_series", + "interval": "1s", + "intervalFactor": 1, + "legendFormat": "-> {{ pod_name }}", + "metric": "network", + "refId": "A", + "step": 1 + }, + { + "expr": "- sum (irate (container_network_transmit_bytes_total{image!=\"\",name=~\"^k8s_.*\",kubernetes_io_hostname=~\"^$Node$\"}[2m])) by (pod_name)", + "format": "time_series", + "interval": "1s", + "intervalFactor": 1, + "legendFormat": "<- {{ pod_name }}", + "metric": "network", + "refId": "B", + "step": 1 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "Pods network I/O ", + "tooltip": { + "msResolution": false, + "shared": true, + "sort": 2, + "value_type": "cumulative" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Pods network I/O", + "titleSize": "h6" + }, + { + "collapse": true, + "height": "500px", + "panels": [ + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PR}", + "decimals": 2, + "editable": true, + "error": false, + "fill": 1, + "grid": {}, + "id": 29, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": 200, + "sort": "current", + "sortDesc": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 2, + "links": [], + "nullPointMode": "connected", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum (irate (container_network_receive_bytes_total{id!=\"/\",kubernetes_io_hostname=~\"^$Node$\"}[2m])) by (id)", + "format": "time_series", + "instant": true, + "interval": "1s", + "intervalFactor": 1, + "legendFormat": "-> {{ id }}", + "metric": "network", + "refId": "A", + "step": 1 + }, + { + "expr": "- sum (irate (container_network_transmit_bytes_total{id!=\"/\",kubernetes_io_hostname=~\"^$Node$\"}[2m])) by (id)", + "format": "time_series", + "interval": "1s", + "intervalFactor": 1, + "legendFormat": "<- {{ id }}", + "metric": "network", + "refId": "B", + "step": 1 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "All processes network I/O ", + "tooltip": { + "msResolution": false, + "shared": true, + "sort": 2, + "value_type": "cumulative" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "All processes network I/O", + "titleSize": "h6" + }, + { + "collapse": true, + "height": 250, + "panels": [ + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PR}", + "fill": 1, + "id": 35, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sort": "avg", + "sortDesc": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(openshift_build_total) by (phase,reason)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{ phase }} | {{ reason }}", + "refId": "A", + "step": 1 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "openshift_build_total", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PR}", + "fill": 1, + "id": 54, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": false, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "count(openshift_build_active_time_seconds{phase=\"running\"} offset 10m)", + "format": "time_series", + "intervalFactor": 2, + "refId": "A", + "step": 2 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "Returns the number of builds that have been running for more than 10 minutes (600 seconds).", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PR}", + "fill": 1, + "id": 55, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": false, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "count(openshift_build_active_time_seconds{phase=\"pending\"} offset 10m)", + "format": "time_series", + "intervalFactor": 2, + "refId": "A", + "step": 2 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "Returns the number of build that have been waiting at least 10 minutes (600 seconds) to start.", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PR}", + "fill": 1, + "id": 56, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": false, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(openshift_build_total{phase=\"Failed\"})", + "format": "time_series", + "intervalFactor": 2, + "refId": "A", + "step": 2 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "Returns the number of failed builds, regardless of the failure reason.", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PR}", + "fill": 1, + "id": 57, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "openshift_build_total{phase=\"Failed\",reason=\"FetchSourceFailed\"}", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{ instance }}", + "refId": "A", + "step": 1 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "Returns the number of failed builds because of problems retrieving source from the associated Git repository.", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": {}, + "bars": true, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PR}", + "fill": 1, + "id": 58, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": false, + "total": false, + "values": false + }, + "lines": false, + "linewidth": 1, + "links": [], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(openshift_build_total{phase=\"Complete\"})", + "format": "time_series", + "intervalFactor": 2, + "refId": "A", + "step": 2 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "Returns the number of successfully completed builds.", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PR}", + "fill": 0, + "id": 59, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sort": "avg", + "sortDesc": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "percentage": false, + "pointradius": 1, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "openshift_build_total{phase=\"Failed\"} offset 5m", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{ reason }}", + "refId": "A", + "step": 2 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "Returns the failed builds totals, per failure reason, from 5 minutes ago.", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "OpenShift Builds", + "titleSize": "h6" + }, + { + "collapse": true, + "height": 250, + "panels": [ + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PR}", + "fill": 1, + "id": 36, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": false, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(openshift_sdn_pod_setup_latency_sum)", + "format": "time_series", + "intervalFactor": 2, + "refId": "A", + "step": 1 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "openshift_sdn_pod_setup_latency_sum", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PR}", + "fill": 1, + "id": 41, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": false, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(openshift_sdn_pod_teardown_latency{quantile=\"0.9\"}) by (instance)", + "format": "time_series", + "intervalFactor": 2, + "refId": "A", + "step": 1 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "openshift_sdn_pod_teardown_latency", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PR}", + "fill": 1, + "id": 50, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sort": "avg", + "sortDesc": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "topk(10, (sum by (pod_name) (irate(container_network_receive_bytes_total{pod_name!=\"\"}[5m]))))", + "format": "time_series", + "interval": "", + "intervalFactor": 1, + "legendFormat": "{{ pod_name }}", + "refId": "A", + "step": 1 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "Top 10 pods doing the most receive network traffic", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "decbytes", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PR}", + "fill": 1, + "id": 37, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sort": "avg", + "sortDesc": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "openshift_sdn_pod_ips", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{ instance }} | {{ role }}", + "refId": "A", + "step": 1 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "openshift_sdn_pod_ips", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PR}", + "fill": 1, + "id": 39, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": false, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "garbage_collector_monitoring_route:openshift:io_v1_rate_limiter_use", + "format": "time_series", + "intervalFactor": 2, + "refId": "A", + "step": 1 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "garbage_collector_monitoring_route:openshift:io_v1_rate_limiter_use", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PR}", + "fill": 1, + "id": 42, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sort": "avg", + "sortDesc": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "openshift_sdn_arp_cache_entries", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{ role }} | {{ instance }}", + "refId": "A", + "step": 1 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "openshift_sdn_arp_cache_entries", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PR}", + "fill": 1, + "id": 40, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": false, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "openshift_sdn_arp_cache_entries", + "format": "time_series", + "intervalFactor": 2, + "refId": "A", + "step": 1 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "openshift_sdn_arp_cache_entries", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "OpenShift SDN", + "titleSize": "h6" + }, + { + "collapse": true, + "height": 250, + "panels": [ + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PR}", + "fill": 1, + "id": 44, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sort": "avg", + "sortDesc": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "irate(kubelet_pleg_relist_latency_microseconds{kubernetes_io_hostname=~\"$Node\",quantile=\"0.9\"}[2m])", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{ role }} | {{ instance }}", + "refId": "A", + "step": 4 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "kubelet_pleg_relist", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "µs", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PR}", + "fill": 1, + "id": 51, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sort": "avg", + "sortDesc": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "irate(kubelet_docker_operations_latency_microseconds{quantile=\"0.9\"}[2m])", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{ operation_type }}", + "refId": "A", + "step": 4 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "kubelet_docker_operations_latency_microseconds{quantile=\"0.9\"}", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "µs", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PR}", + "fill": 1, + "id": 52, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sort": "avg", + "sortDesc": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "kubelet_docker_operations_timeout", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{ operation_type }}", + "refId": "A", + "step": 4 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "Returns a running count (not a rate) of docker operations that have timed out since the kubelet was started.", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "none", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PR}", + "fill": 1, + "id": 53, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sort": "avg", + "sortDesc": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "kubelet_docker_operations_errors", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{ operation_type }}", + "refId": "A", + "step": 2 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "Returns a running count (not a rate) of docker operations that have failed since the kubelet was started.", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "none", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Kubelet", + "titleSize": "h6" + }, + { + "collapse": true, + "height": 250, + "panels": [ + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PR}", + "fill": 1, + "id": 46, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sort": "avg", + "sortDesc": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "irate(scrape_samples_scraped[2m])", + "format": "time_series", + "hide": false, + "intervalFactor": 2, + "legendFormat": "{{ kubernetes_name }} | {{ instance }} ", + "refId": "A", + "step": 4 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "scrape_samples_scraped", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "none", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PR}", + "fill": 1, + "id": 68, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": false, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sort_desc(sum without (cpu) (irate(container_cpu_usage_seconds_total{container_name=\"prometheus\"}[5m])))", + "format": "time_series", + "interval": "1s", + "intervalFactor": 1, + "refId": "A", + "step": 2 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "CPU per instance of Prometheus container.", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "none", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Prometheus", + "titleSize": "h6" + }, + { + "collapse": true, + "height": 250, + "panels": [ + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PR}", + "fill": 1, + "id": 48, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sort": "avg", + "sortDesc": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sort_desc(sum without (instance,type,client,contentType) (irate(apiserver_request_count{verb!~\"GET|LIST|WATCH\"}[2m]))) > 0", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{ resource }} || {{ verb }}", + "refId": "A", + "step": 4 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "Number of mutating API requests being made to the control plane.", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "none", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PR}", + "fill": 1, + "id": 49, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sort": "avg", + "sortDesc": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sort_desc(sum without (instance,type,client,contentType) (irate(apiserver_request_count{verb=~\"GET|LIST|WATCH\"}[2m]))) > 0", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{ resource }} || {{ pod }}", + "refId": "A", + "step": 4 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "Number of non-mutating API requests being made to the control plane.", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "none", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PR}", + "fill": 1, + "id": 74, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "endpoint_queue_latency", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": " quantile {{ quantile }}", + "refId": "A", + "step": 4 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "endpoint_queue_latency", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "API Server", + "titleSize": "h6" + }, + { + "collapse": true, + "height": 250, + "panels": [ + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PR}", + "fill": 1, + "id": 61, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": false, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "etcd_disk_wal_fsync_duration_seconds_count", + "format": "time_series", + "intervalFactor": 2, + "refId": "A", + "step": 10 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "etcd_disk_wal_fsync_duration_seconds_count", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "none", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "etcd", + "titleSize": "h6" + }, + { + "collapse": true, + "height": 250, + "panels": [ + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PR}", + "fill": 1, + "id": 62, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": false, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(changes(container_start_time_seconds[10m]))", + "format": "time_series", + "intervalFactor": 2, + "refId": "A", + "step": 2 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "The number of containers that start or restart over the last ten minutes.", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "none", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Changes in your cluster", + "titleSize": "h6" + }, + { + "collapse": true, + "height": 250, + "panels": [ + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PR}", + "fill": 1, + "id": 63, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": false, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(machine_cpu_cores)", + "format": "time_series", + "intervalFactor": 2, + "refId": "A", + "step": 4 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "Total number of cores in the cluster.", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "none", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PR}", + "fill": 1, + "id": 64, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": false, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(sort_desc(irate(container_cpu_usage_seconds_total{id=\"/\"}[5m])))", + "format": "time_series", + "intervalFactor": 2, + "refId": "A", + "step": 4 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "Total number of consumed cores.", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "none", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PR}", + "fill": 1, + "id": 65, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": false, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sort_desc(sum by (kubernetes_io_hostname,type) (irate(container_cpu_usage_seconds_total{id=\"/\"}[5m])))", + "format": "time_series", + "intervalFactor": 2, + "refId": "A", + "step": 4 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "CPU consumed per node in the cluster.", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "none", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PR}", + "fill": 1, + "id": 66, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": false, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sort_desc(sum by (cpu,id,pod_name,container_name) (irate(container_cpu_usage_seconds_total{role=\"infra\"}[5m])))", + "format": "time_series", + "hide": false, + "intervalFactor": 2, + "refId": "A", + "step": 4 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "CPU consumption per system service or container on the infrastructure nodes.", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "none", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PR}", + "fill": 1, + "id": 67, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": false, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sort_desc(sum by (namespace) (irate(container_cpu_usage_seconds_total[5m])))", + "format": "time_series", + "intervalFactor": 2, + "refId": "A", + "step": 4 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "CPU consumed per namespace on the cluster.", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "none", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PR}", + "fill": 1, + "id": 47, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": false, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(irate(container_cpu_usage_seconds_total{id=\"/\"}[3m])) / sum(machine_cpu_cores)", + "format": "time_series", + "intervalFactor": 2, + "refId": "A", + "step": 4 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "Percentage of total cluster CPU in use", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "percent", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PR}", + "fill": 1, + "id": 69, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": false, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(container_memory_rss) / sum(machine_memory_bytes)", + "format": "time_series", + "intervalFactor": 2, + "refId": "A", + "step": 4 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "Percentage of total cluster memory in use", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "percent", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PR}", + "fill": 1, + "id": 70, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": false, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum by (kubernetes_io_hostname) (irate(container_cpu_usage_seconds_total{id=~\"/system.slice/(docker|etcd).service\"}[5m]))", + "format": "time_series", + "intervalFactor": 2, + "refId": "A", + "step": 4 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "Aggregate CPU usage (seconds total) of etcd+docker", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "none", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "System and container CPU", + "titleSize": "h6" + }, + { + "collapse": true, + "height": 250, + "panels": [ + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PR}", + "fill": 1, + "id": 71, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": false, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + { + "title": "Kubernetes Storage Metrics via Prometheus", + "type": "absolute", + "url": "https://docs.google.com/document/d/1Fh0T60T_y888LsRwC51CQHO75b2IZ3A34ZQS71s_F0g" + } + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "volumes_queue_latency", + "format": "time_series", + "intervalFactor": 2, + "refId": "A", + "step": 4 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "volumes_queue_latency", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "none", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PR}", + "fill": 1, + "id": 72, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sort": "avg", + "sortDesc": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [ + { + "title": "Kubernetes Storage Metrics via Prometheus", + "type": "absolute", + "url": "https://docs.google.com/document/d/1Fh0T60T_y888LsRwC51CQHO75b2IZ3A34ZQS71s_F0g" + } + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "irate(cloudprovider_gce_api_request_duration_seconds_count[2m])", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{ request }}", + "refId": "A", + "step": 4 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "cloudprovider_aws_api_request_duration_seconds_count", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "none", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PR}", + "fill": 1, + "id": 73, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sort": "avg", + "sortDesc": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [ + { + "title": "Kubernetes Storage Metrics via Prometheus", + "type": "absolute", + "url": "https://docs.google.com/document/d/1Fh0T60T_y888LsRwC51CQHO75b2IZ3A34ZQS71s_F0g" + } + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum (irate(storage_operation_duration_seconds_sum{kubernetes_io_hostname=~\"$Node\"}[2m])) by (operation_name,kubernetes_io_hostname)", + "format": "time_series", + "interval": "1s", + "intervalFactor": 1, + "legendFormat": "{{ operation_name }} || {{ kubernetes_io_hostname }}", + "refId": "A", + "step": 2 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "storage_operation_duration_seconds_sum", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "OpenShift Volumes", + "titleSize": "h6" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "kubernetes", + "openshift" + ], + "templating": { + "list": [ + { + "allValue": ".*", + "current": {}, + "datasource": "${DS_PR}", + "hide": 0, + "includeAll": true, + "label": null, + "multi": false, + "name": "Node", + "options": [], + "query": "label_values(kubernetes_io_hostname)", + "refresh": 1, + "regex": "", + "sort": 0, + "tagValuesQuery": "", + "tags": [], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-30m", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "1s", + "2m", + "20s", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "browser", + "title": "openshift cluster monitoring", + "version": 6 + } +} diff --git a/roles/openshift_grafana/meta/main.yml b/roles/openshift_grafana/meta/main.yml new file mode 100644 index 000000000..8dea6f197 --- /dev/null +++ b/roles/openshift_grafana/meta/main.yml @@ -0,0 +1,13 @@ +--- +galaxy_info: + author: Eldad Marciano + description: Setup grafana pod + company: Red Hat, Inc. + license: Apache License, Version 2.0 + min_ansible_version: 2.3 + platforms: + - name: EL + versions: + - 7 + categories: + - metrics diff --git a/roles/openshift_grafana/tasks/gf-permissions.yml b/roles/openshift_grafana/tasks/gf-permissions.yml new file mode 100644 index 000000000..9d3c741ee --- /dev/null +++ b/roles/openshift_grafana/tasks/gf-permissions.yml @@ -0,0 +1,12 @@ +--- +- name: Create gf user on htpasswd + command: htpasswd -c /etc/origin/master/htpasswd gfadmin + +- name: Make sure master config use HTPasswdPasswordIdentityProvider + command: "sed -ie 's|AllowAllPasswordIdentityProvider|HTPasswdPasswordIdentityProvider\n file: /etc/origin/master/htpasswd|' /etc/origin/master/master-config.yaml" + +- name: Grant permission for gfuser + command: oc adm policy add-cluster-role-to-user cluster-reader gfadmin + +- name: Restart mater api + command: systemctl restart atomic-openshift-master-api.service diff --git a/roles/openshift_grafana/tasks/main.yml b/roles/openshift_grafana/tasks/main.yml new file mode 100644 index 000000000..6a06d40a9 --- /dev/null +++ b/roles/openshift_grafana/tasks/main.yml @@ -0,0 +1,122 @@ +--- +- name: Create grafana namespace + oc_project: + state: present + name: grafana + +- name: Configure Grafana Permissions + include_tasks: tasks/gf-permissions.yml + when: gf_oauth | default(false) | bool == true + +# TODO: we should grab this yaml file from openshift/origin +- name: Templatize grafana yaml + template: src=grafana-ocp.yaml dest=/tmp/grafana-ocp.yaml + register: + cl_file: /tmp/grafana-ocp.yaml + when: gf_oauth | default(false) | bool == false + +# TODO: we should grab this yaml file from openshift/origin +- name: Templatize grafana yaml + template: src=grafana-ocp-oauth.yaml dest=/tmp/grafana-ocp-oauth.yaml + register: + cl_file: /tmp/grafana-ocp-oauth.yaml + when: gf_oauth | default(false) | bool == true + +- name: Process the grafana file + oc_process: + namespace: grafana + template_name: "{{ cl_file }}" + create: True + when: gf_oauth | default(false) | bool == true + +- name: Wait to grafana be running + command: oc rollout status deployment/grafana-ocp + +- name: oc adm policy add-role-to-user view -z grafana-ocp -n {{ gf_prometheus_namespace }} + oc_adm_policy_user: + user: grafana-ocp + resource_kind: cluster-role + resource_name: view + state: present + role_namespace: "{{ gf_prometheus_namespace }}" + +- name: Get grafana route + oc_obj: + kind: route + name: grafana + namespace: grafana + register: route + +- name: Get prometheus route + oc_obj: + kind: route + name: prometheus + namespace: "{{ gf_prometheus_namespace }}" + register: route + +- name: Get the prometheus SA + oc_serviceaccount_secret: + state: list + service_account: prometheus + namespace: "{{ gf_prometheus_namespace }}" + register: sa + +- name: Get the management SA bearer token + set_fact: + management_token: "{{ sa.results | oo_filter_sa_secrets }}" + +- name: Ensure the SA bearer token value is read + oc_secret: + state: list + name: "{{ management_token }}" + namespace: "{{ gf_prometheus_namespace }}" + no_log: True + register: sa_secret + +- name: Get the SA bearer token for prometheus + set_fact: + token: "{{ sa_secret.results.encoded.token }}" + +- name: Convert to json + var: + ds_json: "{{ gf_body_tmp }} | to_json }}" + +- name: Set protocol type + var: + protocol: "{{ 'https' if {{ gf_oauth }} == true else 'http' }}" + +- name: Add gf datasrouce + uri: + url: "{{ protocol }}://{{ route }}/api/datasources" + user: admin + password: admin + method: POST + body: "{{ ds_json | regex_replace('grafana_name', {{ gf_datasource_name }}) | regex_replace('prometheus_url', 'https://'{{ prometheus }} ) | regex_replace('satoken', {{ token }}) }}" + headers: + Content-Type: "Content-Type: application/json" + register: add_ds + +- name: Regex setup ds name + replace: + path: "{{ lookup('file', 'openshift-cluster-monitoring.json') }}" + regexp: '${DS_PR}' + replace: '{{ gf_datasource_name }}' + backup: yes + +- name: Add new dashboard + uri: + url: "{{ protocol }}://{{ route }}/api/dashboards/db" + user: admin + password: admin + method: POST + body: "{{ lookup('file', 'openshift-cluster-monitoring.json') }}" + headers: + Content-Type: "Content-Type: application/json" + register: add_ds + +- name: Regex json tear down + replace: + path: "{{ lookup('file', 'openshift-cluster-monitoring.json') }}" + regexp: '${DS_PR}' + replace: '{{ gf_datasource_name }}' + backup: yes diff --git a/roles/openshift_health_checker/openshift_checks/__init__.py b/roles/openshift_health_checker/openshift_checks/__init__.py index 83e551b5d..b9c41d1b4 100644 --- a/roles/openshift_health_checker/openshift_checks/__init__.py +++ b/roles/openshift_health_checker/openshift_checks/__init__.py @@ -5,6 +5,7 @@ Health checks for OpenShift clusters. import json import operator import os +import re import time import collections @@ -309,28 +310,38 @@ class OpenShiftCheck(object): name_list = name_list.split(',') return [name.strip() for name in name_list if name.strip()] - @staticmethod - def get_major_minor_version(openshift_image_tag): + def get_major_minor_version(self, openshift_image_tag=None): """Parse and return the deployed version of OpenShift as a tuple.""" - if openshift_image_tag and openshift_image_tag[0] == 'v': - openshift_image_tag = openshift_image_tag[1:] - # map major release versions across releases - # to a common major version - openshift_major_release_version = { - "1": "3", - } + version = openshift_image_tag or self.get_var("openshift_image_tag") + components = [int(component) for component in re.findall(r'\d+', version)] - components = openshift_image_tag.split(".") - if not components or len(components) < 2: + if len(components) < 2: msg = "An invalid version of OpenShift was found for this host: {}" - raise OpenShiftCheckException(msg.format(openshift_image_tag)) + raise OpenShiftCheckException(msg.format(version)) + + # map major release version across releases to OCP major version + components[0] = {1: 3}.get(components[0], components[0]) + + return tuple(int(x) for x in components[:2]) + + def get_required_version(self, name, version_map): + """Return the correct required version(s) for the current (or nearest) OpenShift version.""" + openshift_version = self.get_major_minor_version() + + earliest = min(version_map) + latest = max(version_map) + if openshift_version < earliest: + return version_map[earliest] + if openshift_version > latest: + return version_map[latest] - if components[0] in openshift_major_release_version: - components[0] = openshift_major_release_version[components[0]] + required_version = version_map.get(openshift_version) + if not required_version: + msg = "There is no recommended version of {} for the current version of OpenShift ({})" + raise OpenShiftCheckException(msg.format(name, ".".join(str(comp) for comp in openshift_version))) - components = tuple(int(x) for x in components[:2]) - return components + return required_version def find_ansible_mount(self, path): """Return the mount point for path from ansible_mounts.""" diff --git a/roles/openshift_health_checker/openshift_checks/docker_image_availability.py b/roles/openshift_health_checker/openshift_checks/docker_image_availability.py index 7afb8f730..d298fbab2 100644 --- a/roles/openshift_health_checker/openshift_checks/docker_image_availability.py +++ b/roles/openshift_health_checker/openshift_checks/docker_image_availability.py @@ -40,7 +40,7 @@ class DockerImageAvailability(DockerHostMixin, OpenShiftCheck): # to look for images available remotely without waiting to pull them. dependencies = ["python-docker-py", "skopeo"] # command for checking if remote registries have an image, without docker pull - skopeo_command = "timeout 10 skopeo inspect --tls-verify={tls} {creds} docker://{registry}/{image}" + skopeo_command = "{proxyvars} timeout 10 skopeo inspect --tls-verify={tls} {creds} docker://{registry}/{image}" skopeo_example_command = "skopeo inspect [--tls-verify=false] [--creds=<user>:<pass>] docker://<registry>/<image>" def __init__(self, *args, **kwargs): @@ -56,7 +56,7 @@ class DockerImageAvailability(DockerHostMixin, OpenShiftCheck): # ordered list of registries (according to inventory vars) that docker will try for unscoped images regs = self.ensure_list("openshift_docker_additional_registries") # currently one of these registries is added whether the user wants it or not. - deployment_type = self.get_var("openshift_deployment_type") + deployment_type = self.get_var("openshift_deployment_type", default="") if deployment_type == "origin" and "docker.io" not in regs: regs.append("docker.io") elif deployment_type == 'openshift-enterprise' and "registry.access.redhat.com" not in regs: @@ -76,11 +76,20 @@ class DockerImageAvailability(DockerHostMixin, OpenShiftCheck): if oreg_auth_user != '' and oreg_auth_password != '': oreg_auth_user = self.template_var(oreg_auth_user) oreg_auth_password = self.template_var(oreg_auth_password) - self.skopeo_command_creds = "--creds={}:{}".format(quote(oreg_auth_user), quote(oreg_auth_password)) + self.skopeo_command_creds = quote("--creds={}:{}".format(oreg_auth_user, oreg_auth_password)) # record whether we could reach a registry or not (and remember results) self.reachable_registries = {} + # take note of any proxy settings needed + proxies = [] + for var in ['http_proxy', 'https_proxy', 'no_proxy']: + # ansible vars are openshift_http_proxy, openshift_https_proxy, openshift_no_proxy + value = self.get_var("openshift_" + var, default=None) + if value: + proxies.append(var.upper() + "=" + quote(self.template_var(value))) + self.skopeo_proxy_vars = " ".join(proxies) + def is_active(self): """Skip hosts with unsupported deployment types.""" deployment_type = self.get_var("openshift_deployment_type") @@ -249,11 +258,18 @@ class DockerImageAvailability(DockerHostMixin, OpenShiftCheck): if not self.reachable_registries[registry]: continue # do not keep trying unreachable registries - args = dict(registry=registry, image=image) - args["tls"] = "false" if registry in self.registries["insecure"] else "true" - args["creds"] = self.skopeo_command_creds if registry == self.registries["oreg"] else "" + args = dict( + proxyvars=self.skopeo_proxy_vars, + tls="false" if registry in self.registries["insecure"] else "true", + creds=self.skopeo_command_creds if registry == self.registries["oreg"] else "", + registry=quote(registry), + image=quote(image), + ) - result = self.execute_module_with_retries("command", {"_raw_params": self.skopeo_command.format(**args)}) + result = self.execute_module_with_retries("command", { + "_uses_shell": True, + "_raw_params": self.skopeo_command.format(**args), + }) if result.get("rc", 0) == 0 and not result.get("failed"): return True if result.get("rc") == 124: # RC 124 == timed out; mark unreachable @@ -263,6 +279,10 @@ class DockerImageAvailability(DockerHostMixin, OpenShiftCheck): def connect_to_registry(self, registry): """Use ansible wait_for module to test connectivity from host to registry. Returns bool.""" + if self.skopeo_proxy_vars != "": + # assume we can't connect directly; just waive the test + return True + # test a simple TCP connection host, _, port = registry.partition(":") port = port or 443 diff --git a/roles/openshift_health_checker/openshift_checks/logging/elasticsearch.py b/roles/openshift_health_checker/openshift_checks/logging/elasticsearch.py index 986a01f38..7f8c6ebdc 100644 --- a/roles/openshift_health_checker/openshift_checks/logging/elasticsearch.py +++ b/roles/openshift_health_checker/openshift_checks/logging/elasticsearch.py @@ -170,7 +170,7 @@ class Elasticsearch(LoggingCheck): """ errors = [] for pod_name in pods_by_name.keys(): - df_cmd = 'exec {} -- df --output=ipcent,pcent /elasticsearch/persistent'.format(pod_name) + df_cmd = '-c elasticsearch exec {} -- df --output=ipcent,pcent /elasticsearch/persistent'.format(pod_name) disk_output = self.exec_oc(df_cmd, [], save_as_name='get_pv_diskspace.json') lines = disk_output.splitlines() # expecting one header looking like 'IUse% Use%' and one body line diff --git a/roles/openshift_health_checker/openshift_checks/logging/kibana.py b/roles/openshift_health_checker/openshift_checks/logging/kibana.py index 3b1cf8baa..16ec3a7f6 100644 --- a/roles/openshift_health_checker/openshift_checks/logging/kibana.py +++ b/roles/openshift_health_checker/openshift_checks/logging/kibana.py @@ -5,12 +5,11 @@ Module for performing checks on a Kibana logging deployment import json import ssl -try: - from urllib2 import HTTPError, URLError - import urllib2 -except ImportError: - from urllib.error import HTTPError, URLError - import urllib.request as urllib2 +# pylint can't find the package when its installed in virtualenv +# pylint: disable=import-error,no-name-in-module +from ansible.module_utils.six.moves.urllib import request +# pylint: disable=import-error,no-name-in-module +from ansible.module_utils.six.moves.urllib.error import HTTPError, URLError from openshift_checks.logging.logging import LoggingCheck, OpenShiftCheckException @@ -65,7 +64,7 @@ class Kibana(LoggingCheck): # Verify that the url is returning a valid response try: # We only care if the url connects and responds - return_code = urllib2.urlopen(url, context=ctx).getcode() + return_code = request.urlopen(url, context=ctx).getcode() except HTTPError as httperr: return httperr.reason except URLError as urlerr: diff --git a/roles/openshift_health_checker/openshift_checks/ovs_version.py b/roles/openshift_health_checker/openshift_checks/ovs_version.py index 0cad19842..58a2692bd 100644 --- a/roles/openshift_health_checker/openshift_checks/ovs_version.py +++ b/roles/openshift_health_checker/openshift_checks/ovs_version.py @@ -3,7 +3,7 @@ Ansible module for determining if an installed version of Open vSwitch is incomp currently installed version of OpenShift. """ -from openshift_checks import OpenShiftCheck, OpenShiftCheckException +from openshift_checks import OpenShiftCheck from openshift_checks.mixins import NotContainerizedMixin @@ -16,10 +16,12 @@ class OvsVersion(NotContainerizedMixin, OpenShiftCheck): tags = ["health"] openshift_to_ovs_version = { - "3.7": ["2.6", "2.7", "2.8"], - "3.6": ["2.6", "2.7", "2.8"], - "3.5": ["2.6", "2.7"], - "3.4": "2.4", + (3, 4): "2.4", + (3, 5): ["2.6", "2.7"], + (3, 6): ["2.6", "2.7", "2.8"], + (3, 7): ["2.6", "2.7", "2.8"], + (3, 8): ["2.6", "2.7", "2.8"], + (3, 9): ["2.6", "2.7", "2.8"], } def is_active(self): @@ -40,16 +42,5 @@ class OvsVersion(NotContainerizedMixin, OpenShiftCheck): return self.execute_module("rpm_version", args) def get_required_ovs_version(self): - """Return the correct Open vSwitch version for the current OpenShift version""" - openshift_version_tuple = self.get_major_minor_version(self.get_var("openshift_image_tag")) - - if openshift_version_tuple < (3, 5): - return self.openshift_to_ovs_version["3.4"] - - openshift_version = ".".join(str(x) for x in openshift_version_tuple) - ovs_version = self.openshift_to_ovs_version.get(openshift_version) - if ovs_version: - return self.openshift_to_ovs_version[openshift_version] - - msg = "There is no recommended version of Open vSwitch for the current version of OpenShift: {}" - raise OpenShiftCheckException(msg.format(openshift_version)) + """Return the correct Open vSwitch version(s) for the current OpenShift version.""" + return self.get_required_version("Open vSwitch", self.openshift_to_ovs_version) diff --git a/roles/openshift_health_checker/openshift_checks/package_version.py b/roles/openshift_health_checker/openshift_checks/package_version.py index f3a628e28..28aee8b35 100644 --- a/roles/openshift_health_checker/openshift_checks/package_version.py +++ b/roles/openshift_health_checker/openshift_checks/package_version.py @@ -1,8 +1,6 @@ """Check that available RPM packages match the required versions.""" -import re - -from openshift_checks import OpenShiftCheck, OpenShiftCheckException +from openshift_checks import OpenShiftCheck from openshift_checks.mixins import NotContainerizedMixin @@ -18,6 +16,8 @@ class PackageVersion(NotContainerizedMixin, OpenShiftCheck): (3, 5): ["2.6", "2.7"], (3, 6): ["2.6", "2.7", "2.8"], (3, 7): ["2.6", "2.7", "2.8"], + (3, 8): ["2.6", "2.7", "2.8"], + (3, 9): ["2.6", "2.7", "2.8"], } openshift_to_docker_version = { @@ -27,11 +27,9 @@ class PackageVersion(NotContainerizedMixin, OpenShiftCheck): (3, 4): "1.12", (3, 5): "1.12", (3, 6): "1.12", - } - - # map major OpenShift release versions across releases to a common major version - map_major_release_version = { - 1: 3, + (3, 7): "1.12", + (3, 8): "1.12", + (3, 9): ["1.12", "1.13"], } def is_active(self): @@ -83,48 +81,8 @@ class PackageVersion(NotContainerizedMixin, OpenShiftCheck): def get_required_ovs_version(self): """Return the correct Open vSwitch version(s) for the current OpenShift version.""" - openshift_version = self.get_openshift_version_tuple() - - earliest = min(self.openshift_to_ovs_version) - latest = max(self.openshift_to_ovs_version) - if openshift_version < earliest: - return self.openshift_to_ovs_version[earliest] - if openshift_version > latest: - return self.openshift_to_ovs_version[latest] - - ovs_version = self.openshift_to_ovs_version.get(openshift_version) - if not ovs_version: - msg = "There is no recommended version of Open vSwitch for the current version of OpenShift: {}" - raise OpenShiftCheckException(msg.format(".".join(str(comp) for comp in openshift_version))) - - return ovs_version + return self.get_required_version("Open vSwitch", self.openshift_to_ovs_version) def get_required_docker_version(self): """Return the correct Docker version(s) for the current OpenShift version.""" - openshift_version = self.get_openshift_version_tuple() - - earliest = min(self.openshift_to_docker_version) - latest = max(self.openshift_to_docker_version) - if openshift_version < earliest: - return self.openshift_to_docker_version[earliest] - if openshift_version > latest: - return self.openshift_to_docker_version[latest] - - docker_version = self.openshift_to_docker_version.get(openshift_version) - if not docker_version: - msg = "There is no recommended version of Docker for the current version of OpenShift: {}" - raise OpenShiftCheckException(msg.format(".".join(str(comp) for comp in openshift_version))) - - return docker_version - - def get_openshift_version_tuple(self): - """Return received image tag as a normalized (X, Y) minor version tuple.""" - version = self.get_var("openshift_image_tag") - comps = [int(component) for component in re.findall(r'\d+', version)] - - if len(comps) < 2: - msg = "An invalid version of OpenShift was found for this host: {}" - raise OpenShiftCheckException(msg.format(version)) - - comps[0] = self.map_major_release_version.get(comps[0], comps[0]) - return tuple(comps[0:2]) + return self.get_required_version("Docker", self.openshift_to_docker_version) diff --git a/roles/openshift_health_checker/test/kibana_test.py b/roles/openshift_health_checker/test/kibana_test.py index 04a5e89c4..750d4b9e9 100644 --- a/roles/openshift_health_checker/test/kibana_test.py +++ b/roles/openshift_health_checker/test/kibana_test.py @@ -1,12 +1,10 @@ import pytest import json -try: - import urllib2 - from urllib2 import HTTPError, URLError -except ImportError: - from urllib.error import HTTPError, URLError - import urllib.request as urllib2 +# pylint can't find the package when its installed in virtualenv +from ansible.module_utils.six.moves.urllib import request # pylint: disable=import-error +# pylint: disable=import-error +from ansible.module_utils.six.moves.urllib.error import HTTPError, URLError from openshift_checks.logging.kibana import Kibana, OpenShiftCheckException @@ -202,7 +200,7 @@ def test_verify_url_external_failure(lib_result, expect, monkeypatch): if type(lib_result) is int: return _http_return(lib_result) raise lib_result - monkeypatch.setattr(urllib2, 'urlopen', urlopen) + monkeypatch.setattr(request, 'urlopen', urlopen) check = Kibana() check._get_kibana_url = lambda: 'url' diff --git a/roles/openshift_health_checker/test/ovs_version_test.py b/roles/openshift_health_checker/test/ovs_version_test.py index 0238f49d5..80c7a0541 100644 --- a/roles/openshift_health_checker/test/ovs_version_test.py +++ b/roles/openshift_health_checker/test/ovs_version_test.py @@ -1,26 +1,7 @@ import pytest -from openshift_checks.ovs_version import OvsVersion, OpenShiftCheckException - - -def test_openshift_version_not_supported(): - def execute_module(*_): - return {} - - openshift_release = '111.7.0' - - task_vars = dict( - openshift=dict(common=dict()), - openshift_release=openshift_release, - openshift_image_tag='v' + openshift_release, - openshift_deployment_type='origin', - openshift_service_type='origin' - ) - - with pytest.raises(OpenShiftCheckException) as excinfo: - OvsVersion(execute_module, task_vars).run() - - assert "no recommended version of Open vSwitch" in str(excinfo.value) +from openshift_checks.ovs_version import OvsVersion +from openshift_checks import OpenShiftCheckException def test_invalid_openshift_release_format(): diff --git a/roles/openshift_health_checker/test/package_version_test.py b/roles/openshift_health_checker/test/package_version_test.py index d2916f617..868b4bd12 100644 --- a/roles/openshift_health_checker/test/package_version_test.py +++ b/roles/openshift_health_checker/test/package_version_test.py @@ -1,6 +1,7 @@ import pytest -from openshift_checks.package_version import PackageVersion, OpenShiftCheckException +from openshift_checks.package_version import PackageVersion +from openshift_checks import OpenShiftCheckException def task_vars_for(openshift_release, deployment_type): @@ -18,7 +19,7 @@ def task_vars_for(openshift_release, deployment_type): def test_openshift_version_not_supported(): check = PackageVersion(None, task_vars_for("1.2.3", 'origin')) - check.get_openshift_version_tuple = lambda: (3, 4, 1) # won't be in the dict + check.get_major_minor_version = lambda: (3, 4, 1) # won't be in the dict with pytest.raises(OpenShiftCheckException) as excinfo: check.get_required_ovs_version() diff --git a/roles/openshift_hosted/tasks/storage/glusterfs_endpoints.yml b/roles/openshift_hosted/tasks/storage/glusterfs_endpoints.yml index 77f020357..fef945d51 100644 --- a/roles/openshift_hosted/tasks/storage/glusterfs_endpoints.yml +++ b/roles/openshift_hosted/tasks/storage/glusterfs_endpoints.yml @@ -1,4 +1,10 @@ --- +- name: Create temp directory for doing work in + command: mktemp -d /tmp/openshift-hosted-ansible-XXXXXX + register: mktempHosted + changed_when: False + check_mode: no + - name: Generate GlusterFS registry endpoints template: src: "{{ openshift.common.examples_content_version }}/glusterfs-registry-endpoints.yml.j2" @@ -14,3 +20,10 @@ with_items: - "{{ mktempHosted.stdout }}/glusterfs-registry-service.yml" - "{{ mktempHosted.stdout }}/glusterfs-registry-endpoints.yml" + +- name: Delete temp directory + file: + name: "{{ mktempHosted.stdout }}" + state: absent + changed_when: False + check_mode: no diff --git a/roles/openshift_hosted_templates/files/v3.6/enterprise/registry-console.yaml b/roles/openshift_hosted_templates/files/v3.6/enterprise/registry-console.yaml index cc3159a32..0786e2d2f 100644 --- a/roles/openshift_hosted_templates/files/v3.6/enterprise/registry-console.yaml +++ b/roles/openshift_hosted_templates/files/v3.6/enterprise/registry-console.yaml @@ -102,7 +102,7 @@ objects: parameters: - description: 'Specify "registry/repository" prefix for container image; e.g. for "registry.access.redhat.com/openshift3/registry-console:latest", set prefix "registry.access.redhat.com/openshift3/"' name: IMAGE_PREFIX - value: "openshift3/" + value: "registry.access.redhat.com/openshift3/" - description: 'Specify component name for container image; e.g. for "registry.access.redhat.com/openshift3/registry-console:latest", use base name "registry-console"' name: IMAGE_BASENAME value: "registry-console" diff --git a/roles/openshift_hosted_templates/files/v3.7/enterprise/registry-console.yaml b/roles/openshift_hosted_templates/files/v3.7/enterprise/registry-console.yaml index 9f2e6125d..ccea54aaf 100644 --- a/roles/openshift_hosted_templates/files/v3.7/enterprise/registry-console.yaml +++ b/roles/openshift_hosted_templates/files/v3.7/enterprise/registry-console.yaml @@ -102,7 +102,7 @@ objects: parameters: - description: 'Specify "registry/repository" prefix for container image; e.g. for "registry.access.redhat.com/openshift3/registry-console:latest", set prefix "registry.access.redhat.com/openshift3/"' name: IMAGE_PREFIX - value: "openshift3/" + value: "registry.access.redhat.com/openshift3/" - description: 'Specify component name for container image; e.g. for "registry.access.redhat.com/openshift3/registry-console:latest", use base name "registry-console"' name: IMAGE_BASENAME value: "registry-console" diff --git a/roles/openshift_hosted_templates/files/v3.8/enterprise/registry-console.yaml b/roles/openshift_hosted_templates/files/v3.8/enterprise/registry-console.yaml index f04ce06d3..15ad4e9af 100644 --- a/roles/openshift_hosted_templates/files/v3.8/enterprise/registry-console.yaml +++ b/roles/openshift_hosted_templates/files/v3.8/enterprise/registry-console.yaml @@ -102,7 +102,7 @@ objects: parameters: - description: 'Specify "registry/repository" prefix for container image; e.g. for "registry.access.redhat.com/openshift3/registry-console:latest", set prefix "registry.access.redhat.com/openshift3/"' name: IMAGE_PREFIX - value: "openshift3/" + value: "registry.access.redhat.com/openshift3/" - description: 'Specify component name for container image; e.g. for "registry.access.redhat.com/openshift3/registry-console:latest", use base name "registry-console"' name: IMAGE_BASENAME value: "registry-console" diff --git a/roles/openshift_hosted_templates/files/v3.9/enterprise/registry-console.yaml b/roles/openshift_hosted_templates/files/v3.9/enterprise/registry-console.yaml index c178cf432..7acefa0f0 100644 --- a/roles/openshift_hosted_templates/files/v3.9/enterprise/registry-console.yaml +++ b/roles/openshift_hosted_templates/files/v3.9/enterprise/registry-console.yaml @@ -102,7 +102,7 @@ objects: parameters: - description: 'Specify "registry/repository" prefix for container image; e.g. for "registry.access.redhat.com/openshift3/registry-console:latest", set prefix "registry.access.redhat.com/openshift3/"' name: IMAGE_PREFIX - value: "openshift3/" + value: "registry.access.redhat.com/openshift3/" - description: 'Specify component name for container image; e.g. for "registry.access.redhat.com/openshift3/registry-console:latest", use base name "registry-console"' name: IMAGE_BASENAME value: "registry-console" diff --git a/roles/openshift_logging/tasks/annotate_ops_projects.yaml b/roles/openshift_logging/tasks/annotate_ops_projects.yaml index 4a2ee64f0..6fdba6580 100644 --- a/roles/openshift_logging/tasks/annotate_ops_projects.yaml +++ b/roles/openshift_logging/tasks/annotate_ops_projects.yaml @@ -12,6 +12,7 @@ separator: '#' content: metadata#annotations#openshift.io/logging.ui.hostname: "{{ openshift_logging_kibana_ops_hostname }}" + metadata#annotations#openshift.io/logging.data.prefix: ".operations" with_items: "{{ __logging_ops_projects.stdout.split(' ') }}" loop_control: loop_var: project diff --git a/roles/openshift_logging/tasks/delete_logging.yaml b/roles/openshift_logging/tasks/delete_logging.yaml index fbc3e3fd1..ced7397b5 100644 --- a/roles/openshift_logging/tasks/delete_logging.yaml +++ b/roles/openshift_logging/tasks/delete_logging.yaml @@ -131,13 +131,13 @@ when: not openshift_logging_install_eventrouter | default(false) | bool -# Update asset config in openshift-web-console namespace -- name: Remove Kibana route information from web console asset config +# Update console config in openshift-web-console namespace +- name: Remove Kibana route information from the web console config include_role: name: openshift_web_console - tasks_from: update_asset_config.yml + tasks_from: update_console_config.yml vars: - asset_config_edits: - - key: loggingPublicURL + console_config_edits: + - key: clusterInfo#loggingPublicURL value: "" when: openshift_web_console_install | default(true) | bool diff --git a/roles/openshift_logging/tasks/generate_certs.yaml b/roles/openshift_logging/tasks/generate_certs.yaml index 0d7f8c056..a40449bf6 100644 --- a/roles/openshift_logging/tasks/generate_certs.yaml +++ b/roles/openshift_logging/tasks/generate_certs.yaml @@ -19,7 +19,7 @@ command: > {{ openshift_client_binary }} adm --config={{ mktemp.stdout }}/admin.kubeconfig ca create-signer-cert --key={{generated_certs_dir}}/ca.key --cert={{generated_certs_dir}}/ca.crt - --serial={{generated_certs_dir}}/ca.serial.txt --name=logging-signer-test + --serial={{generated_certs_dir}}/ca.serial.txt --name=logging-signer-test --overwrite=false check_mode: no when: - not ca_key_file.stat.exists diff --git a/roles/openshift_logging/tasks/install_logging.yaml b/roles/openshift_logging/tasks/install_logging.yaml index ebd2d747b..3afd8680f 100644 --- a/roles/openshift_logging/tasks/install_logging.yaml +++ b/roles/openshift_logging/tasks/install_logging.yaml @@ -87,7 +87,7 @@ openshift_logging_elasticsearch_storage_type: "{{ elasticsearch_storage_type }}" openshift_logging_elasticsearch_pvc_pv_selector: "{{ openshift_logging_es_pv_selector }}" - openshift_logging_elasticsearch_pvc_storage_class_name: "{{ openshift_logging_es_pvc_storage_class_name }}" + openshift_logging_elasticsearch_pvc_storage_class_name: "{{ openshift_logging_es_pvc_storage_class_name | default() }}" openshift_logging_elasticsearch_nodeselector: "{{ openshift_logging_es_nodeselector if outer_item.0.nodeSelector | default(None) is none else outer_item.0.nodeSelector }}" openshift_logging_elasticsearch_storage_group: "{{ [openshift_logging_es_storage_group] if outer_item.0.storageGroups | default([]) | length == 0 else outer_item.0.storageGroups }}" _es_containers: "{{ outer_item.0.containers}}" @@ -114,7 +114,7 @@ openshift_logging_elasticsearch_storage_type: "{{ elasticsearch_storage_type }}" openshift_logging_elasticsearch_pvc_pv_selector: "{{ openshift_logging_es_pv_selector }}" - openshift_logging_elasticsearch_pvc_storage_class_name: "{{ openshift_logging_es_pvc_storage_class_name }}" + openshift_logging_elasticsearch_pvc_storage_class_name: "{{ openshift_logging_es_pvc_storage_class_name | default() }}" with_sequence: count={{ openshift_logging_es_cluster_size | int - openshift_logging_facts.elasticsearch.deploymentconfigs.keys() | count }} loop_control: @@ -151,7 +151,7 @@ openshift_logging_elasticsearch_pvc_size: "{{ openshift_logging_es_ops_pvc_size }}" openshift_logging_elasticsearch_pvc_dynamic: "{{ openshift_logging_es_ops_pvc_dynamic }}" openshift_logging_elasticsearch_pvc_pv_selector: "{{ openshift_logging_es_ops_pv_selector }}" - openshift_logging_elasticsearch_pvc_storage_class_name: "{{ openshift_logging_es_ops_pvc_storage_class_name }}" + openshift_logging_elasticsearch_pvc_storage_class_name: "{{ openshift_logging_es_ops_pvc_storage_class_name | default() }}" openshift_logging_elasticsearch_memory_limit: "{{ openshift_logging_es_ops_memory_limit }}" openshift_logging_elasticsearch_cpu_limit: "{{ openshift_logging_es_ops_cpu_limit }}" openshift_logging_elasticsearch_cpu_request: "{{ openshift_logging_es_ops_cpu_request }}" @@ -193,7 +193,7 @@ openshift_logging_elasticsearch_pvc_size: "{{ openshift_logging_es_ops_pvc_size }}" openshift_logging_elasticsearch_pvc_dynamic: "{{ openshift_logging_es_ops_pvc_dynamic }}" openshift_logging_elasticsearch_pvc_pv_selector: "{{ openshift_logging_es_ops_pv_selector }}" - openshift_logging_elasticsearch_pvc_storage_class_name: "{{ openshift_logging_es_ops_pvc_storage_class_name }}" + openshift_logging_elasticsearch_pvc_storage_class_name: "{{ openshift_logging_es_ops_pvc_storage_class_name | default() }}" openshift_logging_elasticsearch_memory_limit: "{{ openshift_logging_es_ops_memory_limit }}" openshift_logging_elasticsearch_cpu_limit: "{{ openshift_logging_es_ops_cpu_limit }}" openshift_logging_elasticsearch_cpu_request: "{{ openshift_logging_es_ops_cpu_request }}" @@ -321,9 +321,9 @@ - name: Add Kibana route information to web console asset config include_role: name: openshift_web_console - tasks_from: update_asset_config.yml + tasks_from: update_console_config.yml vars: - asset_config_edits: - - key: loggingPublicURL + console_config_edits: + - key: clusterInfo#loggingPublicURL value: "https://{{ openshift_logging_kibana_hostname }}" when: openshift_web_console_install | default(true) | bool diff --git a/roles/openshift_logging/tasks/procure_server_certs.yaml b/roles/openshift_logging/tasks/procure_server_certs.yaml index bc817075d..d28d1d160 100644 --- a/roles/openshift_logging/tasks/procure_server_certs.yaml +++ b/roles/openshift_logging/tasks/procure_server_certs.yaml @@ -30,7 +30,7 @@ {{ openshift_client_binary }} adm --config={{ mktemp.stdout }}/admin.kubeconfig ca create-server-cert --key={{generated_certs_dir}}/{{cert_info.procure_component}}.key --cert={{generated_certs_dir}}/{{cert_info.procure_component}}.crt --hostnames={{cert_info.hostnames|quote}} --signer-cert={{generated_certs_dir}}/ca.crt --signer-key={{generated_certs_dir}}/ca.key - --signer-serial={{generated_certs_dir}}/ca.serial.txt + --signer-serial={{generated_certs_dir}}/ca.serial.txt --overwrite=false check_mode: no when: - cert_info.hostnames is defined diff --git a/roles/openshift_logging_elasticsearch/tasks/get_es_version.yml b/roles/openshift_logging_elasticsearch/tasks/get_es_version.yml index 9182bddb2..16de6f252 100644 --- a/roles/openshift_logging_elasticsearch/tasks/get_es_version.yml +++ b/roles/openshift_logging_elasticsearch/tasks/get_es_version.yml @@ -1,6 +1,6 @@ --- - command: > - oc get pod -l component=es,provider=openshift -n {{ openshift_logging_elasticsearch_namespace }} -o jsonpath={.items[*].metadata.name} + oc get pod -l component=es,provider=openshift -n {{ openshift_logging_elasticsearch_namespace }} -o jsonpath={.items[?(@.status.phase==\"Running\")].metadata.name} register: _cluster_pods - name: "Getting ES version for logging-es cluster" @@ -10,7 +10,7 @@ when: _cluster_pods.stdout_lines | count > 0 - command: > - oc get pod -l component=es-ops,provider=openshift -n {{ openshift_logging_elasticsearch_namespace }} -o jsonpath={.items[*].metadata.name} + oc get pod -l component=es-ops,provider=openshift -n {{ openshift_logging_elasticsearch_namespace }} -o jsonpath={.items[?(@.status.phase==\"Running\")].metadata.name} register: _ops_cluster_pods - name: "Getting ES version for logging-es-ops cluster" diff --git a/roles/openshift_logging_elasticsearch/tasks/restart_cluster.yml b/roles/openshift_logging_elasticsearch/tasks/restart_cluster.yml index d55beec86..6bce13d1d 100644 --- a/roles/openshift_logging_elasticsearch/tasks/restart_cluster.yml +++ b/roles/openshift_logging_elasticsearch/tasks/restart_cluster.yml @@ -19,7 +19,7 @@ ## get all pods for the cluster - command: > - oc get pod -l component={{ _cluster_component }},provider=openshift -n {{ openshift_logging_elasticsearch_namespace }} -o jsonpath={.items[*].metadata.name} + oc get pod -l component={{ _cluster_component }},provider=openshift -n {{ openshift_logging_elasticsearch_namespace }} -o jsonpath={.items[?(@.status.phase==\"Running\")].metadata.name} register: _cluster_pods - name: "Disable shard balancing for logging-{{ _cluster_component }} cluster" @@ -64,7 +64,7 @@ ## we may need a new first pod to run against -- fetch them all again - command: > - oc get pod -l component={{ _cluster_component }},provider=openshift -n {{ openshift_logging_elasticsearch_namespace }} -o jsonpath={.items[*].metadata.name} + oc get pod -l component={{ _cluster_component }},provider=openshift -n {{ openshift_logging_elasticsearch_namespace }} -o jsonpath={.items[?(@.status.phase==\"Running\")].metadata.name} register: _cluster_pods - name: "Enable shard balancing for logging-{{ _cluster_component }} cluster" diff --git a/roles/openshift_master/tasks/upgrade/rpm_upgrade.yml b/roles/openshift_master/tasks/upgrade/rpm_upgrade.yml index 7870f43e2..4564f33dd 100644 --- a/roles/openshift_master/tasks/upgrade/rpm_upgrade.yml +++ b/roles/openshift_master/tasks/upgrade/rpm_upgrade.yml @@ -8,8 +8,10 @@ # TODO: If the sdn package isn't already installed this will install it, we # should fix that -- name: Upgrade master packages - package: name={{ master_pkgs | join(',') }} state=present +- name: Upgrade master packages - yum + command: + yum install -y {{ master_pkgs | join(' ') }} \ + {{ ' --exclude *' ~ openshift_service_type ~ '*3.9*' if openshift_release | version_compare('3.9','<') else '' }} vars: master_pkgs: - "{{ openshift_service_type }}{{ openshift_pkg_version | default('') }}" @@ -17,6 +19,21 @@ - "{{ openshift_service_type }}-node{{ openshift_pkg_version | default('') }}" - "{{ openshift_service_type }}-sdn-ovs{{ openshift_pkg_version | default('') }}" - "{{ openshift_service_type }}-clients{{ openshift_pkg_version | default('') }}" - - "tuned-profiles-{{ openshift_service_type }}-node{{ openshift_pkg_version | default('') }}" register: result until: result is succeeded + when: ansible_pkg_mgr == 'yum' + +- name: Upgrade master packages - dnf + dnf: + name: "{{ master_pkgs | join(',') }}" + state: present + vars: + master_pkgs: + - "{{ openshift_service_type }}{{ openshift_pkg_version }}" + - "{{ openshift_service_type }}-master{{ openshift_pkg_version }}" + - "{{ openshift_service_type }}-node{{ openshift_pkg_version }}" + - "{{ openshift_service_type }}-sdn-ovs{{ openshift_pkg_version }}" + - "{{ openshift_service_type }}-clients{{ openshift_pkg_version }}" + register: result + until: result is succeeded + when: ansible_pkg_mgr == 'dnf' diff --git a/roles/openshift_metrics/tasks/install_metrics.yaml b/roles/openshift_metrics/tasks/install_metrics.yaml index 0866fe0d2..0dd5d1621 100644 --- a/roles/openshift_metrics/tasks/install_metrics.yaml +++ b/roles/openshift_metrics/tasks/install_metrics.yaml @@ -74,10 +74,10 @@ - name: Add metrics route information to web console asset config include_role: name: openshift_web_console - tasks_from: update_asset_config.yml + tasks_from: update_console_config.yml vars: - asset_config_edits: - - key: metricsPublicURL + console_config_edits: + - key: clusterInfo#metricsPublicURL value: "https://{{ openshift_metrics_hawkular_hostname}}/hawkular/metrics" when: openshift_web_console_install | default(true) | bool diff --git a/roles/openshift_metrics/tasks/oc_apply.yaml b/roles/openshift_metrics/tasks/oc_apply.yaml index 8ccfb7192..057963c1a 100644 --- a/roles/openshift_metrics/tasks/oc_apply.yaml +++ b/roles/openshift_metrics/tasks/oc_apply.yaml @@ -16,7 +16,9 @@ apply -f {{ file_name }} -n {{namespace}} register: generation_apply - failed_when: "'error' in generation_apply.stderr" + failed_when: + - "'error' in generation_apply.stderr" + - "generation_apply.rc != 0" changed_when: no - name: Determine change status of {{file_content.kind}} {{file_content.metadata.name}} @@ -28,5 +30,7 @@ register: version_changed vars: init_version: "{{ (generation_init is defined) | ternary(generation_init.stdout, '0') }}" - failed_when: "'error' in version_changed.stderr" + failed_when: + - "'error' in version_changed.stderr" + - "version_changed.rc != 0" changed_when: version_changed.stdout | int > init_version | int diff --git a/roles/openshift_metrics/tasks/uninstall_metrics.yaml b/roles/openshift_metrics/tasks/uninstall_metrics.yaml index 610c7b4e5..1664e9975 100644 --- a/roles/openshift_metrics/tasks/uninstall_metrics.yaml +++ b/roles/openshift_metrics/tasks/uninstall_metrics.yaml @@ -19,13 +19,13 @@ clusterrolebinding/hawkular-metrics changed_when: delete_metrics.stdout != 'No resources found' -# Update asset config in openshift-web-console namespace -- name: Remove metrics route information from web console asset config +# Update the web config in openshift-web-console namespace +- name: Remove metrics route information from the web console config include_role: name: openshift_web_console - tasks_from: update_asset_config.yml + tasks_from: update_console_config.yml vars: - asset_config_edits: - - key: metricsPublicURL + console_config_edits: + - key: clusterInfo#metricsPublicURL value: "" when: openshift_web_console_install | default(true) | bool diff --git a/roles/openshift_node/defaults/main.yml b/roles/openshift_node/defaults/main.yml index c1fab4382..5864d3c03 100644 --- a/roles/openshift_node/defaults/main.yml +++ b/roles/openshift_node/defaults/main.yml @@ -48,6 +48,12 @@ openshift_node_kubelet_args_dict: cloud-config: - "{{ openshift_config_base ~ '/cloudprovider/gce.conf' }}" node-labels: "{{ l_node_kubelet_node_labels }}" + azure: + cloud-provider: + - azure + cloud-config: + - "{{ openshift_config_base ~ '/cloudprovider/azure.conf' }}" + node-labels: "{{ l_node_kubelet_node_labels }}" undefined: node-labels: "{{ l_node_kubelet_node_labels }}" @@ -71,6 +77,18 @@ r_openshift_node_use_firewalld: "{{ os_firewall_use_firewalld | default(False) } l_is_node_system_container: "{{ (openshift_use_node_system_container | default(openshift_use_system_containers | default(false)) | bool) }}" +openshift_node_syscon_auth_mounts_l: +- type: bind + source: "{{ oreg_auth_credentials_path }}" + destination: "/root/.docker" + options: + - ro + +# If we need to add new mounts in the future, or the user wants to mount data. +# This should be in the same format as auth_mounts_l above. +openshift_node_syscon_add_mounts_l: [] + + openshift_deployment_type: "{{ openshift_deployment_type | default('origin') }}" openshift_node_image_dict: diff --git a/roles/openshift_node/tasks/node_system_container.yml b/roles/openshift_node/tasks/node_system_container.yml index 06b879050..008f209d7 100644 --- a/roles/openshift_node/tasks/node_system_container.yml +++ b/roles/openshift_node/tasks/node_system_container.yml @@ -14,4 +14,23 @@ - "DNS_DOMAIN={{ openshift.common.dns_domain }}" - "DOCKER_SERVICE={{ openshift_docker_service_name }}.service" - "MASTER_SERVICE={{ openshift_service_type }}.service" + - 'ADDTL_MOUNTS={{ l_node_syscon_add_mounts2 }}' state: latest + vars: + # We need to evaluate some variables here to ensure + # l_bind_docker_reg_auth is evaluated after registry_auth.yml has been + # processed. + + # Determine if we want to include auth credentials mount. + l_node_syscon_auth_mounts_l: "{{ l_bind_docker_reg_auth | ternary(openshift_node_syscon_auth_mounts_l,[]) }}" + + # Join any user-provided mounts and auth_mounts into a combined list. + l_node_syscon_add_mounts_l: "{{ openshift_node_syscon_add_mounts_l | union(l_node_syscon_auth_mounts_l) }}" + + # We must prepend a ',' here to ensure the value is inserted properly into an + # existing json list in the container's config.json + # lib_utils_oo_l_of_d_to_csv is a custom filter plugin in roles/lib_utils/oo_filters.py + l_node_syscon_add_mounts: ",{{ l_node_syscon_add_mounts_l | lib_utils_oo_l_of_d_to_csv }}" + # if we have just a ',' then both mount lists were empty, we don't want to add + # anything to config.json + l_node_syscon_add_mounts2: "{{ (l_node_syscon_add_mounts != ',') | bool | ternary(l_node_syscon_add_mounts,'') }}" diff --git a/roles/openshift_node/tasks/upgrade/config_changes.yml b/roles/openshift_node/tasks/upgrade/config_changes.yml index 721656117..dd9183382 100644 --- a/roles/openshift_node/tasks/upgrade/config_changes.yml +++ b/roles/openshift_node/tasks/upgrade/config_changes.yml @@ -21,6 +21,12 @@ path: "/var/lib/dockershim/sandbox/" state: absent +# https://bugzilla.redhat.com/show_bug.cgi?id=1518912 +- name: Clean up IPAM data + file: + path: "/var/lib/cni/networks/openshift-sdn/" + state: absent + # Disable Swap Block (pre) - block: - name: Remove swap entries from /etc/fstab diff --git a/roles/openshift_node/templates/node.yaml.v1.j2 b/roles/openshift_node/templates/node.yaml.v1.j2 index 5f2a94ea2..7d817463c 100644 --- a/roles/openshift_node/templates/node.yaml.v1.j2 +++ b/roles/openshift_node/templates/node.yaml.v1.j2 @@ -32,7 +32,7 @@ masterClientConnectionOverrides: contentType: application/vnd.kubernetes.protobuf burst: 200 qps: 100 -masterKubeConfig: system:node:{{ openshift.common.hostname }}.kubeconfig +masterKubeConfig: system:node:{{ openshift.common.hostname | lower }}.kubeconfig {% if openshift_node_use_openshift_sdn | bool %} networkPluginName: {{ openshift_node_sdn_network_plugin_name }} {% endif %} diff --git a/roles/openshift_node_certificates/tasks/main.yml b/roles/openshift_node_certificates/tasks/main.yml index 5f73f3bdc..13d9fd718 100644 --- a/roles/openshift_node_certificates/tasks/main.yml +++ b/roles/openshift_node_certificates/tasks/main.yml @@ -18,9 +18,9 @@ stat: path: "{{ openshift.common.config_base }}/node/{{ item }}" with_items: - - "system:node:{{ openshift.common.hostname }}.crt" - - "system:node:{{ openshift.common.hostname }}.key" - - "system:node:{{ openshift.common.hostname }}.kubeconfig" + - "system:node:{{ openshift.common.hostname | lower }}.crt" + - "system:node:{{ openshift.common.hostname | lower }}.key" + - "system:node:{{ openshift.common.hostname | lower }}.kubeconfig" - ca.crt - server.key - server.crt @@ -59,16 +59,16 @@ --certificate-authority {{ legacy_ca_certificate }} {% endfor %} --certificate-authority={{ openshift_ca_cert }} - --client-dir={{ openshift_generated_configs_dir }}/node-{{ hostvars[item].openshift.common.hostname }} + --client-dir={{ openshift_generated_configs_dir }}/node-{{ hostvars[item].openshift.common.hostname | lower }} --groups=system:nodes --master={{ hostvars[openshift_ca_host].openshift.master.api_url }} --signer-cert={{ openshift_ca_cert }} --signer-key={{ openshift_ca_key }} --signer-serial={{ openshift_ca_serial }} - --user=system:node:{{ hostvars[item].openshift.common.hostname }} + --user=system:node:{{ hostvars[item].openshift.common.hostname | lower }} --expire-days={{ openshift_node_cert_expire_days }} args: - creates: "{{ openshift_generated_configs_dir }}/node-{{ hostvars[item].openshift.common.hostname }}" + creates: "{{ openshift_generated_configs_dir }}/node-{{ hostvars[item].openshift.common.hostname | lower }}" with_items: "{{ hostvars | lib_utils_oo_select_keys(groups['oo_nodes_to_config']) | lib_utils_oo_collect(attribute='inventory_hostname', filters={'node_certs_missing':True}) }}" @@ -78,16 +78,16 @@ - name: Generate the node server certificate command: > {{ hostvars[openshift_ca_host]['first_master_client_binary'] }} adm ca create-server-cert - --cert={{ openshift_generated_configs_dir }}/node-{{ hostvars[item].openshift.common.hostname }}/server.crt - --key={{ openshift_generated_configs_dir }}/node-{{ hostvars[item].openshift.common.hostname }}/server.key + --cert={{ openshift_generated_configs_dir }}/node-{{ hostvars[item].openshift.common.hostname | lower }}/server.crt + --key={{ openshift_generated_configs_dir }}/node-{{ hostvars[item].openshift.common.hostname | lower }}/server.key --expire-days={{ openshift_node_cert_expire_days }} --overwrite=true - --hostnames={{ hostvars[item].openshift.common.hostname }},{{ hostvars[item].openshift.common.public_hostname }},{{ hostvars[item].openshift.common.ip }},{{ hostvars[item].openshift.common.public_ip }} + --hostnames={{ hostvars[item].openshift.common.hostname }},{{ hostvars[item].openshift.common.hostname | lower }},{{ hostvars[item].openshift.common.public_hostname }},{{ hostvars[item].openshift.common.public_hostname | lower }},{{ hostvars[item].openshift.common.ip }},{{ hostvars[item].openshift.common.public_ip }} --signer-cert={{ openshift_ca_cert }} --signer-key={{ openshift_ca_key }} --signer-serial={{ openshift_ca_serial }} args: - creates: "{{ openshift_generated_configs_dir }}/node-{{ hostvars[item].openshift.common.hostname }}/server.crt" + creates: "{{ openshift_generated_configs_dir }}/node-{{ hostvars[item].openshift.common.hostname | lower }}/server.crt" with_items: "{{ hostvars | lib_utils_oo_select_keys(groups['oo_nodes_to_config']) | lib_utils_oo_collect(attribute='inventory_hostname', filters={'node_certs_missing':True}) }}" diff --git a/roles/openshift_node_certificates/vars/main.yml b/roles/openshift_node_certificates/vars/main.yml index 17ad8106d..12a6d3f94 100644 --- a/roles/openshift_node_certificates/vars/main.yml +++ b/roles/openshift_node_certificates/vars/main.yml @@ -1,7 +1,7 @@ --- openshift_generated_configs_dir: "{{ openshift.common.config_base }}/generated-configs" openshift_node_cert_dir: "{{ openshift.common.config_base }}/node" -openshift_node_cert_subdir: "node-{{ openshift.common.hostname }}" +openshift_node_cert_subdir: "node-{{ openshift.common.hostname | lower }}" openshift_node_config_dir: "{{ openshift.common.config_base }}/node" openshift_node_generated_config_dir: "{{ openshift_generated_configs_dir }}/{{ openshift_node_cert_subdir }}" diff --git a/roles/openshift_openstack/templates/heat_stack.yaml.j2 b/roles/openshift_openstack/templates/heat_stack.yaml.j2 index 1be5d3a62..8e7c6288a 100644 --- a/roles/openshift_openstack/templates/heat_stack.yaml.j2 +++ b/roles/openshift_openstack/templates/heat_stack.yaml.j2 @@ -523,7 +523,7 @@ resources: floating_network: if: - no_floating - - null + - '' - {{ openshift_openstack_external_network_name }} {% if openshift_openstack_provider_network_name %} attach_float_net: false @@ -589,8 +589,13 @@ resources: secgrp: - { get_resource: lb-secgrp } - { get_resource: common-secgrp } -{% if not openshift_openstack_provider_network_name %} - floating_network: {{ openshift_openstack_external_network_name }} + floating_network: + if: + - no_floating + - '' + - {{ openshift_openstack_external_network_name }} +{% if openshift_openstack_provider_network_name %} + attach_float_net: false {% endif %} volume_size: {{ openshift_openstack_lb_volume_size }} {% if not openshift_openstack_provider_network_name %} @@ -655,7 +660,7 @@ resources: floating_network: if: - no_floating - - null + - '' - {{ openshift_openstack_external_network_name }} {% if openshift_openstack_provider_network_name %} attach_float_net: false @@ -725,7 +730,7 @@ resources: floating_network: if: - no_floating - - null + - '' - {{ openshift_openstack_external_network_name }} {% if openshift_openstack_provider_network_name %} attach_float_net: false @@ -792,8 +797,13 @@ resources: {% endif %} - { get_resource: infra-secgrp } - { get_resource: common-secgrp } -{% if not openshift_openstack_provider_network_name %} - floating_network: {{ openshift_openstack_external_network_name }} + floating_network: + if: + - no_floating + - '' + - {{ openshift_openstack_external_network_name }} +{% if openshift_openstack_provider_network_name %} + attach_float_net: false {% endif %} volume_size: {{ openshift_openstack_infra_volume_size }} {% if openshift_openstack_infra_server_group_policies|length > 0 %} diff --git a/roles/openshift_openstack/templates/heat_stack_server.yaml.j2 b/roles/openshift_openstack/templates/heat_stack_server.yaml.j2 index 1e73c9e1c..29b09f3c9 100644 --- a/roles/openshift_openstack/templates/heat_stack_server.yaml.j2 +++ b/roles/openshift_openstack/templates/heat_stack_server.yaml.j2 @@ -102,13 +102,11 @@ parameters: label: Attach-float-net description: A switch for floating network port connection -{% if not openshift_openstack_provider_network_name %} floating_network: type: string default: '' label: Floating network description: Network to allocate floating IP from -{% endif %} availability_zone: type: string diff --git a/roles/openshift_persistent_volumes/tasks/pv.yml b/roles/openshift_persistent_volumes/tasks/pv.yml index ef9ab7f5f..865269b7a 100644 --- a/roles/openshift_persistent_volumes/tasks/pv.yml +++ b/roles/openshift_persistent_volumes/tasks/pv.yml @@ -13,5 +13,5 @@ --config={{ mktemp.stdout }}/admin.kubeconfig register: pv_create_output when: persistent_volumes | length > 0 - failed_when: ('already exists' not in pv_create_output.stderr) and ('created' not in pv_create_output.stdout) + failed_when: "('already exists' not in pv_create_output.stderr) and ('created' not in pv_create_output.stdout) and pv_create_output.rc != 0" changed_when: ('created' in pv_create_output.stdout) diff --git a/roles/openshift_persistent_volumes/tasks/pvc.yml b/roles/openshift_persistent_volumes/tasks/pvc.yml index 2c5519192..6c12d128c 100644 --- a/roles/openshift_persistent_volumes/tasks/pvc.yml +++ b/roles/openshift_persistent_volumes/tasks/pvc.yml @@ -13,5 +13,5 @@ --config={{ mktemp.stdout }}/admin.kubeconfig register: pvc_create_output when: persistent_volume_claims | length > 0 - failed_when: ('already exists' not in pvc_create_output.stderr) and ('created' not in pvc_create_output.stdout) + failed_when: "('already exists' not in pvc_create_output.stderr) and ('created' not in pvc_create_output.stdout) and pvc_create_output.rc != 0" changed_when: ('created' in pvc_create_output.stdout) diff --git a/roles/openshift_provisioners/tasks/oc_apply.yaml b/roles/openshift_provisioners/tasks/oc_apply.yaml index a4ce53eae..239e1f1cc 100644 --- a/roles/openshift_provisioners/tasks/oc_apply.yaml +++ b/roles/openshift_provisioners/tasks/oc_apply.yaml @@ -15,7 +15,9 @@ apply -f {{ file_name }} -n {{ namespace }} register: generation_apply - failed_when: "'error' in generation_apply.stderr" + failed_when: + - "'error' in generation_apply.stderr" + - "generation_apply.rc != 0" changed_when: no - name: Determine change status of {{file_content.kind}} {{file_content.metadata.name}} @@ -36,7 +38,9 @@ delete -f {{ file_name }} -n {{ namespace }} register: generation_delete - failed_when: "'error' in generation_delete.stderr" + failed_when: + - "'error' in generation_delete.stderr" + - "generation_delete.rc != 0" changed_when: generation_delete.rc == 0 when: generation_apply.rc != 0 @@ -46,6 +50,8 @@ apply -f {{ file_name }} -n {{ namespace }} register: generation_apply - failed_when: "'error' in generation_apply.stderr" + failed_when: + - "'error' in generation_apply.stderr" + - "generation_apply.rc != 0" changed_when: generation_apply.rc == 0 when: generation_apply.rc != 0 diff --git a/roles/openshift_version/tasks/check_available_rpms.yml b/roles/openshift_version/tasks/check_available_rpms.yml index bdbc63d27..fea0daf77 100644 --- a/roles/openshift_version/tasks/check_available_rpms.yml +++ b/roles/openshift_version/tasks/check_available_rpms.yml @@ -1,7 +1,7 @@ --- - name: Get available {{ openshift_service_type}} version repoquery: - name: "{{ openshift_service_type}}" + name: "{{ openshift_service_type}}{{ '-' ~ openshift_release ~ '*' if openshift_release is defined else '' }}" ignore_excluders: true register: rpm_results diff --git a/roles/openshift_version/tasks/first_master_containerized_version.yml b/roles/openshift_version/tasks/first_master_containerized_version.yml index e02a75eab..3ed1d2cfe 100644 --- a/roles/openshift_version/tasks/first_master_containerized_version.yml +++ b/roles/openshift_version/tasks/first_master_containerized_version.yml @@ -7,6 +7,7 @@ when: - openshift_image_tag is defined - openshift_version is not defined + - not (openshift_version_reinit | default(false)) - name: Set containerized version to configure if openshift_release specified set_fact: @@ -20,7 +21,7 @@ docker run --rm {{ openshift_cli_image }}:latest version register: cli_image_version when: - - openshift_version is not defined + - openshift_version is not defined or openshift_version_reinit | default(false) - not openshift_use_crio_only # Origin latest = pre-release version (i.e. v1.3.0-alpha.1-321-gb095e3a) @@ -34,7 +35,7 @@ - set_fact: openshift_version: "{{ cli_image_version.stdout_lines[0].split(' ')[1].split('-')[0][1:] }}" - when: openshift_version is not defined + when: openshift_version is not defined or openshift_version_reinit | default(false) # If we got an openshift_version like "3.2", lookup the latest 3.2 container version # and use that value instead. diff --git a/roles/openshift_version/tasks/first_master_rpm_version.yml b/roles/openshift_version/tasks/first_master_rpm_version.yml index 264baca65..5d92f90c6 100644 --- a/roles/openshift_version/tasks/first_master_rpm_version.yml +++ b/roles/openshift_version/tasks/first_master_rpm_version.yml @@ -6,6 +6,7 @@ when: - openshift_pkg_version is defined - openshift_version is not defined + - not (openshift_version_reinit | default(false)) # These tasks should only be run against masters and nodes - name: Set openshift_version for rpm installation @@ -13,4 +14,7 @@ - set_fact: openshift_version: "{{ rpm_results.results.versions.available_versions.0 }}" - when: openshift_version is not defined + when: openshift_version is not defined or ( openshift_version_reinit | default(false) ) +- set_fact: + openshift_pkg_version: "-{{ rpm_results.results.versions.available_versions.0 }}" + when: openshift_version_reinit | default(false) diff --git a/roles/openshift_version/tasks/masters_and_nodes.yml b/roles/openshift_version/tasks/masters_and_nodes.yml index fbeb22d8b..eddd5ff42 100644 --- a/roles/openshift_version/tasks/masters_and_nodes.yml +++ b/roles/openshift_version/tasks/masters_and_nodes.yml @@ -6,9 +6,12 @@ include_tasks: check_available_rpms.yml - name: Fail if rpm version and docker image version are different fail: - msg: "OCP rpm version {{ openshift_rpm_version }} is different from OCP image version {{ openshift_version }}" + msg: "OCP rpm version {{ rpm_results.results.versions.available_versions.0 }} is different from OCP image version {{ openshift_version }}" # Both versions have the same string representation - when: rpm_results.results.versions.available_versions.0 != openshift_version + when: + - openshift_version not in rpm_results.results.versions.available_versions.0 + - openshift_version_reinit | default(false) + # block when when: not openshift_is_atomic | bool diff --git a/roles/openshift_web_console/defaults/main.yml b/roles/openshift_web_console/defaults/main.yml index 4f395398c..c747f73a8 100644 --- a/roles/openshift_web_console/defaults/main.yml +++ b/roles/openshift_web_console/defaults/main.yml @@ -1,3 +1,2 @@ --- -# TODO: This is temporary and will be updated to use taints and tolerations so that the console runs on the masters -openshift_web_console_nodeselector: {"region":"infra"} +openshift_web_console_nodeselector: "{{ openshift_hosted_infra_selector | default('region=infra') | map_from_pairs }}" diff --git a/roles/openshift_web_console/tasks/install.yml b/roles/openshift_web_console/tasks/install.yml index 12916961b..cc5eef47d 100644 --- a/roles/openshift_web_console/tasks/install.yml +++ b/roles/openshift_web_console/tasks/install.yml @@ -21,43 +21,123 @@ node_selector: - "" -- name: Make temp directory for asset config files +- name: Make temp directory for web console templates command: mktemp -d /tmp/console-ansible-XXXXXX register: mktemp changed_when: False -- name: Copy asset config template to temp directory +- name: Copy admin client config + command: > + cp {{ openshift.common.config_base }}/master//admin.kubeconfig {{ mktemp.stdout }}/admin.kubeconfig + changed_when: false + +- name: Copy web console templates to temp directory copy: src: "{{ __console_files_location }}/{{ item }}" dest: "{{ mktemp.stdout }}/{{ item }}" with_items: - "{{ __console_template_file }}" + - "{{ __console_rbac_file }}" - "{{ __console_config_file }}" -- name: Update asset config properties - yedit: - src: "{{ mktemp.stdout }}/{{ __console_config_file }}" - edits: - - key: logoutURL - value: "{{ openshift.master.logout_url | default('') }}" - - key: publicURL - # Must have a trailing slash - value: "{{ openshift.master.public_console_url }}/" - - key: masterPublicURL - value: "{{ openshift.master.public_api_url }}" +# Check if an existing webconsole-config config map exists. If so, use those +# contents so we don't overwrite changes. +- name: Read the existing web console config map + oc_configmap: + namespace: openshift-web-console + name: webconsole-config + state: list + register: webconsole_config_map + +- set_fact: + existing_config_map_data: "{{ webconsole_config_map.results.results[0].data | default({}) }}" + +- name: Copy the existing web console config to temp directory + copy: + content: "{{ existing_config_map_data['webconsole-config.yaml'] }}" + dest: "{{ mktemp.stdout }}/{{ __console_config_file }}" + when: existing_config_map_data['webconsole-config.yaml'] is defined + +# Generate a new config when a config map is not defined. +- when: existing_config_map_data['webconsole-config.yaml'] is not defined + block: + # Migrate the previous master-config.yaml asset config if it exists into the new + # web console config config map. + - name: Read existing assetConfig in master-config.yaml + slurp: + src: "{{ openshift.common.config_base }}/master/master-config.yaml" + register: master_config_output + + - set_fact: + config_to_migrate: "{{ master_config_output.content | b64decode | from_yaml }}" + + # Update properties in the config template based on inventory vars when the + # asset config does not exist. + - name: Set web console config properties from inventory variables + yedit: + src: "{{ mktemp.stdout }}/{{ __console_config_file }}" + edits: + - key: clusterInfo#consolePublicURL + # Must have a trailing slash + value: "{{ openshift.master.public_console_url }}/" + - key: clusterInfo#masterPublicURL + value: "{{ openshift.master.public_api_url }}" + - key: clusterInfo#logoutPublicURL + value: "{{ openshift.master.logout_url | default('') }}" + - key: features#inactivityTimeoutMinutes + value: "{{ openshift_web_console_inactivity_timeout_minutes | default(0) }}" + - key: features#clusterResourceOverridesEnabled + value: "{{ openshift_web_console_cluster_resource_overrides_enabled | default(false) }}" + - key: extensions#scriptURLs + value: "{{ openshift_web_console_extension_script_urls | default([]) }}" + - key: extensions#stylesheetURLs + value: "{{ openshift_web_console_extension_stylesheet_urls | default([]) }}" + - key: extensions#properties + value: "{{ openshift_web_console_extension_properties | default({}) }}" + separator: '#' + state: present + when: config_to_migrate.assetConfig is not defined + + - name: Migrate assetConfig from master-config.yaml + yedit: + src: "{{ mktemp.stdout }}/{{ __console_config_file }}" + edits: + - key: clusterInfo#consolePublicURL + value: "{{ config_to_migrate.assetConfig.publicURL }}" + - key: clusterInfo#masterPublicURL + value: "{{ config_to_migrate.assetConfig.masterPublicURL }}" + - key: clusterInfo#logoutPublicURL + value: "{{ config_to_migrate.assetConfig.logoutURL | default('') }}" + - key: clusterInfo#metricsPublicURL + value: "{{ config_to_migrate.assetConfig.metricsPublicURL | default('') }}" + - key: clusterInfo#loggingPublicURL + value: "{{ config_to_migrate.assetConfig.loggingPublicURL | default('') }}" + - key: servingInfo#maxRequestsInFlight + value: "{{ config_to_migrate.assetConfig.servingInfo.maxRequestsInFlight | default(0) }}" + - key: servingInfo#requestTimeoutSeconds + value: "{{ config_to_migrate.assetConfig.servingInfo.requestTimeoutSeconds | default(0) }}" + separator: '#' + state: present + when: config_to_migrate.assetConfig is defined - slurp: src: "{{ mktemp.stdout }}/{{ __console_config_file }}" - register: config + register: updated_console_config + +- name: Reconcile with the web console RBAC file + shell: > + {{ openshift_client_binary }} process -f "{{ mktemp.stdout }}/{{ __console_rbac_file }}" --config={{ mktemp.stdout }}/admin.kubeconfig + | {{ openshift_client_binary }} auth reconcile --config={{ mktemp.stdout }}/admin.kubeconfig -f - -- name: Apply template file +- name: Apply the web console template file shell: > {{ openshift_client_binary }} process -f "{{ mktemp.stdout }}/{{ __console_template_file }}" - --param API_SERVER_CONFIG="{{ config['content'] | b64decode }}" + --param API_SERVER_CONFIG="{{ updated_console_config['content'] | b64decode }}" --param IMAGE="{{ openshift_web_console_prefix }}{{ openshift_web_console_image_name }}:{{ openshift_web_console_version }}" --param NODE_SELECTOR={{ openshift_web_console_nodeselector | to_json | quote }} --param REPLICA_COUNT="{{ openshift_web_console_replica_count }}" - | {{ openshift_client_binary }} apply -f - + --config={{ mktemp.stdout }}/admin.kubeconfig + | {{ openshift_client_binary }} apply --config={{ mktemp.stdout }}/admin.kubeconfig -f - - name: Verify that the web console is running command: > diff --git a/roles/openshift_web_console/tasks/rollout_console.yml b/roles/openshift_web_console/tasks/rollout_console.yml new file mode 100644 index 000000000..75682ba1d --- /dev/null +++ b/roles/openshift_web_console/tasks/rollout_console.yml @@ -0,0 +1,20 @@ +--- +- name: Check if console deployment exists + oc_obj: + kind: deployments + name: webconsole + namespace: openshift-web-console + state: list + register: console_deployment + +# There's currently no command to trigger a rollout for a k8s deployment +# without changing the pod spec. Add an annotation to force a rollout. +- name: Rollout updated web console deployment + oc_edit: + kind: deployments + name: webconsole + namespace: openshift-web-console + separator: '#' + content: + spec#template#metadata#annotations#installer-triggered-rollout: "{{ ansible_date_time.iso8601_micro }}" + when: console_deployment.results.results.0 | length > 0 diff --git a/roles/openshift_web_console/tasks/update_asset_config.yml b/roles/openshift_web_console/tasks/update_asset_config.yml deleted file mode 100644 index 0992b32e1..000000000 --- a/roles/openshift_web_console/tasks/update_asset_config.yml +++ /dev/null @@ -1,68 +0,0 @@ ---- -# This task updates asset config values in the webconsole-config config map in -# the openshift-web-console namespace. The values to set are pased in the -# variable `asset_config_edits`, which is an array of objects with `key` and -# `value` properties in the same format as `yedit` module `edits`. Only -# properties passed are updated. -# -# Note that this triggers a redeployment on the console and a brief downtime -# since it uses a `Recreate` strategy. -# -# Example usage: -# -# - include_role: -# name: openshift_web_console -# tasks_from: update_asset_config.yml -# vars: -# asset_config_edits: -# - key: loggingPublicURL -# value: "https://{{ openshift_logging_kibana_hostname }}" -# when: openshift_web_console_install | default(true) | bool - -- name: Read web console config map - oc_configmap: - namespace: openshift-web-console - name: webconsole-config - state: list - register: webconsole_config - -- name: Make temp directory - command: mktemp -d /tmp/console-ansible-XXXXXX - register: mktemp - changed_when: False - -- name: Copy asset config to temp file - copy: - content: "{{webconsole_config.results.results[0].data['webconsole-config.yaml']}}" - dest: "{{ mktemp.stdout }}/webconsole-config.yaml" - -- name: Change asset config properties - yedit: - src: "{{ mktemp.stdout }}/webconsole-config.yaml" - edits: "{{asset_config_edits}}" - -- name: Update web console config map - oc_configmap: - namespace: openshift-web-console - name: webconsole-config - state: present - from_file: - webconsole-config.yaml: "{{ mktemp.stdout }}/webconsole-config.yaml" - -- name: Remove temp directory - file: - state: absent - name: "{{ mktemp.stdout }}" - changed_when: False - -# There's currently no command to trigger a rollout for a k8s deployment -# without changing the pod spec. Add an annotation to force a rollout after -# the config map has been edited. -- name: Rollout updated web console deployment - oc_edit: - kind: deployments - name: webconsole - namespace: openshift-web-console - separator: '#' - content: - spec#template#metadata#annotations#installer-triggered-rollout: "{{ ansible_date_time.iso8601_micro }}" diff --git a/roles/openshift_web_console/tasks/update_console_config.yml b/roles/openshift_web_console/tasks/update_console_config.yml new file mode 100644 index 000000000..967222ea4 --- /dev/null +++ b/roles/openshift_web_console/tasks/update_console_config.yml @@ -0,0 +1,67 @@ +--- +# This task updates asset config values in the webconsole-config config map in +# the openshift-web-console namespace. The values to set are pased in the +# variable `console_config_edits`, which is an array of objects with `key` and +# `value` properties in the same format as `yedit` module `edits`. Only +# properties passed are updated. The separator for nested properties is `#`. +# +# Note that this triggers a redeployment on the console and a brief downtime +# since it uses a `Recreate` strategy. +# +# Example usage: +# +# - include_role: +# name: openshift_web_console +# tasks_from: update_console_config.yml +# vars: +# console_config_edits: +# - key: clusterInfo#loggingPublicURL +# value: "https://{{ openshift_logging_kibana_hostname }}" +# when: openshift_web_console_install | default(true) | bool + +- name: Read the existing web console config map + oc_configmap: + namespace: openshift-web-console + name: webconsole-config + state: list + register: webconsole_config_map + +- set_fact: + existing_config_map_data: "{{ webconsole_config_map.results.results[0].data | default({}) }}" + +- when: existing_config_map_data['webconsole-config.yaml'] is defined + block: + - name: Make temp directory + command: mktemp -d /tmp/console-ansible-XXXXXX + register: mktemp_console + changed_when: False + + - name: Copy the existing web console config to temp directory + copy: + content: "{{ existing_config_map_data['webconsole-config.yaml'] }}" + dest: "{{ mktemp_console.stdout }}/webconsole-config.yaml" + + - name: Change web console config properties + yedit: + src: "{{ mktemp_console.stdout }}/webconsole-config.yaml" + edits: "{{console_config_edits}}" + separator: '#' + state: present + + - name: Update web console config map + oc_configmap: + namespace: openshift-web-console + name: webconsole-config + state: present + from_file: + webconsole-config.yaml: "{{ mktemp_console.stdout }}/webconsole-config.yaml" + register: update_console_config_map + + - name: Remove temp directory + file: + state: absent + name: "{{ mktemp_console.stdout }}" + changed_when: False + + - include_tasks: rollout_console.yml + when: update_console_config_map.changed | bool diff --git a/roles/openshift_web_console/vars/default_images.yml b/roles/openshift_web_console/vars/default_images.yml index 7adb8a0d0..42d331ac5 100644 --- a/roles/openshift_web_console/vars/default_images.yml +++ b/roles/openshift_web_console/vars/default_images.yml @@ -1,4 +1,4 @@ --- -__openshift_web_console_prefix: "docker.io/openshift/" +__openshift_web_console_prefix: "docker.io/openshift/origin-" __openshift_web_console_version: "latest" -__openshift_web_console_image_name: "origin-web-console" +__openshift_web_console_image_name: "web-console" diff --git a/roles/openshift_web_console/vars/main.yml b/roles/openshift_web_console/vars/main.yml index 80bc56a17..e91048e38 100644 --- a/roles/openshift_web_console/vars/main.yml +++ b/roles/openshift_web_console/vars/main.yml @@ -2,4 +2,5 @@ __console_files_location: "../../../files/origin-components/" __console_template_file: "console-template.yaml" +__console_rbac_file: "console-rbac-template.yaml" __console_config_file: "console-config.yaml" diff --git a/roles/openshift_web_console/vars/openshift-enterprise.yml b/roles/openshift_web_console/vars/openshift-enterprise.yml index 721ac1d27..375c22067 100644 --- a/roles/openshift_web_console/vars/openshift-enterprise.yml +++ b/roles/openshift_web_console/vars/openshift-enterprise.yml @@ -1,4 +1,4 @@ --- -__openshift_web_console_prefix: "registry.access.redhat.com/openshift3/" +__openshift_web_console_prefix: "registry.access.redhat.com/openshift3/ose-" __openshift_web_console_version: "v3.9" -__openshift_web_console_image_name: "ose-web-console" +__openshift_web_console_image_name: "web-console" diff --git a/roles/os_firewall/tasks/firewalld.yml b/roles/os_firewall/tasks/firewalld.yml index 4eae31596..fa933da51 100644 --- a/roles/os_firewall/tasks/firewalld.yml +++ b/roles/os_firewall/tasks/firewalld.yml @@ -2,7 +2,9 @@ - name: Fail - Firewalld is not supported on Atomic Host fail: msg: "Firewalld is not supported on Atomic Host" - when: r_os_firewall_is_atomic | bool + when: + - r_os_firewall_is_atomic | bool + - not openshift_enable_unsupported_configurations | default(false) - name: Install firewalld packages package: @@ -10,6 +12,7 @@ state: present register: result until: result is succeeded + when: not r_os_firewall_is_atomic | bool - name: Ensure iptables services are not enabled systemd: diff --git a/roles/template_service_broker/defaults/main.yml b/roles/template_service_broker/defaults/main.yml index c32872d24..3465832cc 100644 --- a/roles/template_service_broker/defaults/main.yml +++ b/roles/template_service_broker/defaults/main.yml @@ -3,4 +3,4 @@ template_service_broker_remove: False template_service_broker_install: True openshift_template_service_broker_namespaces: ['openshift'] -template_service_broker_selector: { "region": "infra" } +template_service_broker_selector: "{{ openshift_hosted_infra_selector | default('region=infra') | map_from_pairs }}" diff --git a/roles/template_service_broker/tasks/install.yml b/roles/template_service_broker/tasks/install.yml index 604e94602..4e6ad2ae5 100644 --- a/roles/template_service_broker/tasks/install.yml +++ b/roles/template_service_broker/tasks/install.yml @@ -22,6 +22,11 @@ register: mktemp changed_when: False +- name: Copy admin client config + command: > + cp {{ openshift.common.config_base }}/master//admin.kubeconfig {{ mktemp.stdout }}/admin.kubeconfig + changed_when: false + - copy: src: "{{ __tsb_files_location }}/{{ item }}" dest: "{{ mktemp.stdout }}/{{ item }}" @@ -43,16 +48,18 @@ - name: Apply template file shell: > - {{ openshift_client_binary }} process -f "{{ mktemp.stdout }}/{{ __tsb_template_file }}" + {{ openshift_client_binary }} process --config={{ mktemp.stdout }}/admin.kubeconfig + -f "{{ mktemp.stdout }}/{{ __tsb_template_file }}" --param API_SERVER_CONFIG="{{ config['content'] | b64decode }}" --param IMAGE="{{ template_service_broker_prefix }}{{ template_service_broker_image_name }}:{{ template_service_broker_version }}" --param NODE_SELECTOR={{ template_service_broker_selector | to_json | quote }} - | {{ openshift_client_binary }} apply -f - + | {{ openshift_client_binary }} apply --config={{ mktemp.stdout }}/admin.kubeconfig -f - # reconcile with rbac - name: Reconcile with RBAC file shell: > - {{ openshift_client_binary }} process -f "{{ mktemp.stdout }}/{{ __tsb_rbac_file }}" | {{ openshift_client_binary }} auth reconcile -f - + {{ openshift_client_binary }} process --config={{ mktemp.stdout }}/admin.kubeconfig -f "{{ mktemp.stdout }}/{{ __tsb_rbac_file }}" + | {{ openshift_client_binary }} auth reconcile --config={{ mktemp.stdout }}/admin.kubeconfig -f - # Check that the TSB is running - name: Verify that TSB is running @@ -79,9 +86,15 @@ # Register with broker - name: Register TSB with broker shell: > - {{ openshift_client_binary }} process -f "{{ mktemp.stdout }}/{{ __tsb_broker_file }}" --param CA_BUNDLE="{{ __ca_bundle.content }}" | {{ openshift_client_binary }} apply -f - + {{ openshift_client_binary }} process --config={{ mktemp.stdout }}/admin.kubeconfig -f "{{ mktemp.stdout }}/{{ __tsb_broker_file }}" --param CA_BUNDLE="{{ __ca_bundle.content }}" | {{ openshift_client_binary }} apply --config={{ mktemp.stdout }}/admin.kubeconfig -f - - file: state: absent name: "{{ mktemp.stdout }}" changed_when: False + +- name: Rollout console so it discovers the template service broker is installed + include_role: + name: openshift_web_console + tasks_from: rollout_console.yml + when: openshift_web_console_install | default(true) | bool diff --git a/roles/template_service_broker/tasks/remove.yml b/roles/template_service_broker/tasks/remove.yml index db1b558e4..48dc1327e 100644 --- a/roles/template_service_broker/tasks/remove.yml +++ b/roles/template_service_broker/tasks/remove.yml @@ -3,6 +3,11 @@ register: mktemp changed_when: False +- name: Copy admin client config + command: > + cp {{ openshift.common.config_base }}/master//admin.kubeconfig {{ mktemp.stdout }}/admin.kubeconfig + changed_when: false + - copy: src: "{{ __tsb_files_location }}/{{ item }}" dest: "{{ mktemp.stdout }}/{{ item }}" @@ -12,11 +17,11 @@ - name: Delete TSB broker shell: > - {{ openshift_client_binary }} process -f "{{ mktemp.stdout }}/{{ __tsb_broker_file }}" | {{ openshift_client_binary }} delete --ignore-not-found -f - + {{ openshift_client_binary }} process --config={{ mktemp.stdout }}/admin.kubeconfig -f "{{ mktemp.stdout }}/{{ __tsb_broker_file }}" | {{ openshift_client_binary }} delete --config={{ mktemp.stdout }}/admin.kubeconfig --ignore-not-found -f - - name: Delete TSB objects shell: > - {{ openshift_client_binary }} process -f "{{ mktemp.stdout }}/{{ __tsb_template_file }}" | {{ openshift_client_binary }} delete --ignore-not-found -f - + {{ openshift_client_binary }} process --config={{ mktemp.stdout }}/admin.kubeconfig -f "{{ mktemp.stdout }}/{{ __tsb_template_file }}" | {{ openshift_client_binary }} delete --config={{ mktemp.stdout }}/admin.kubeconfig --ignore-not-found -f - - name: empty out tech preview extension file for service console UI copy: @@ -31,3 +36,9 @@ state: absent name: "{{ mktemp.stdout }}" changed_when: False + +- name: Rollout console so it discovers the template service broker is removed + include_role: + name: openshift_web_console + tasks_from: rollout_console.yml + when: openshift_web_console_install | default(true) | bool diff --git a/roles/template_service_broker/vars/default_images.yml b/roles/template_service_broker/vars/default_images.yml index 662d65d9f..dc164a4db 100644 --- a/roles/template_service_broker/vars/default_images.yml +++ b/roles/template_service_broker/vars/default_images.yml @@ -1,4 +1,4 @@ --- -__template_service_broker_prefix: "docker.io/openshift/" +__template_service_broker_prefix: "docker.io/openshift/origin-" __template_service_broker_version: "latest" -__template_service_broker_image_name: "origin-template-service-broker" +__template_service_broker_image_name: "template-service-broker" diff --git a/roles/template_service_broker/vars/openshift-enterprise.yml b/roles/template_service_broker/vars/openshift-enterprise.yml index 16a08e72f..b65b97691 100644 --- a/roles/template_service_broker/vars/openshift-enterprise.yml +++ b/roles/template_service_broker/vars/openshift-enterprise.yml @@ -1,4 +1,4 @@ --- -__template_service_broker_prefix: "registry.access.redhat.com/openshift3/" +__template_service_broker_prefix: "registry.access.redhat.com/openshift3/ose-" __template_service_broker_version: "v3.7" -__template_service_broker_image_name: "ose-template-service-broker" +__template_service_broker_image_name: "template-service-broker" diff --git a/roles/tuned/tasks/main.yml b/roles/tuned/tasks/main.yml index 4a28d47b2..5129f4471 100644 --- a/roles/tuned/tasks/main.yml +++ b/roles/tuned/tasks/main.yml @@ -28,7 +28,12 @@ when: item.state == 'file' - name: Make tuned use the recommended tuned profile on restart - file: path=/etc/tuned/active_profile state=absent + file: + path: '{{ item }}' + state: absent + with_items: + - /etc/tuned/active_profile + - /etc/tuned/profile_mode - name: Restart tuned service systemd: |