openstack-k8s-operators · jistr · Jul 29, 2024 · Jul 4, 2024
diff --git a/docs_user/modules/proc_adopting-autoscaling.adoc b/docs_user/modules/proc_adopting-autoscaling.adoc
@@ -1,6 +1,6 @@
 [id="adopting-autoscaling_{context}"]
 
-= Adopting autoscaling
+= Adopting Autoscaling services
 
 Adopting autoscaling means that an existing `OpenStackControlPlane` custom resource (CR), where Aodh services are supposed to be disabled, should be patched to start the service with the configuration parameters provided by the source environment.
 
@@ -20,87 +20,65 @@ should be already adopted.
 . Patch the `OpenStackControlPlane` CR to deploy autoscaling services:
 +
 ----
-cat << EOF > aodh_patch.yaml
+oc patch openstackcontrolplane openstack --type=merge --patch '
 spec:
-  autoscaling:
+  telemetry:
     enabled: true
-    prometheus:
-      deployPrometheus: false
-    aodh:
-      customServiceConfig: |
-        [DEFAULT]
-        debug=true
-      secret: osp-secret
-ifeval::["{build}" != "downstream"]
-      apiImage: "quay.io/podified-antelope-centos9/openstack-aodh-api:current-podified"
-      evaluatorImage: "quay.io/podified-antelope-centos9/openstack-aodh-evaluator:current-podified"
-      notifierImage: "quay.io/podified-antelope-centos9/openstack-aodh-notifier:current-podified"
-      listenerImage: "quay.io/podified-antelope-centos9/openstack-aodh-listener:current-podified"
-endif::[]
-ifeval::["{build}" == "downstream"]
-      apiImage: "registry.redhat.io/rhosp-dev-preview/openstack-aodh-api-rhel9:18.0"
-      evaluatorImage: "registry.redhat.io/rhosp-dev-preview/openstack-aodh-evaluator-rhel9:18.0"
-      notifierImage: "registry.redhat.io/rhosp-dev-preview/openstack-aodh-notifier-rhel9:18.0"
-      listenerImage: "registry.redhat.io/rhosp-dev-preview/openstack-aodh-listener-rhel9:18.0"
-endif::[]
-      passwordSelectors:
-      databaseAccount: aodh
-      databaseInstance: openstack
-      memcachedInstance: memcached
-EOF
-----
-
-. Optional: If you have previously backed up your {OpenStackShort} services configuration file from the old environment, you can use os-diff to compare and make sure the configuration is correct. This will producre the difference between both ini configuration files:
-+
-----
-os-diff diff /tmp/collect_tripleo_configs/aodh/etc/aodh/aodh.conf aodh_patch.yaml --crd
-----
-+
-For more information, see xref:reviewing-the-openstack-control-plane-configuration_{context}[Reviewing the {rhos_prev_long} control plane configuration].
-
-. Patch the `OpenStackControlPlane` CR to deploy Aodh services:
-+
-----
-oc patch openstackcontrolplane openstack --type=merge --patch-file aodh_patch.yaml
+    template:
+      autoscaling:
+        enabled: true
+        aodh:
+          passwordSelector:
+            aodhService: AodhPassword
+          databaseAccount: aodh
+          databaseInstance: openstack
+          secret: osp-secret
+          serviceUser: aodh
+        heatInstance: heat
+'
 ----
 
 .Verification
 
 . If autoscaling services are enabled, inspect Aodh pods:
 +
 ----
-AODH_POD=`oc get pods -l service=aodh | tail -n 1 | cut -f 1 -d' '`
+AODH_POD=`oc get pods -l service=aodh -n openstack | tail -n 1 | cut -f 1 -d' '`
 oc exec -t $AODH_POD -c aodh-api -- cat /etc/aodh/aodh.conf
 ----
 
 . Check whether Aodh API service is registered in {identity_service}:
 +
 ----
 openstack endpoint list | grep aodh
-| 6a805bd6c9f54658ad2f24e5a0ae0ab6 | regionOne | aodh      | network      | True    | public    | http://aodh-public-openstack.apps-crc.testing  |
-| b943243e596847a9a317c8ce1800fa98 | regionOne | aodh      | network      | True    | internal  | http://aodh-internal.openstack.svc:9696        |
-| f97f2b8f7559476bb7a5eafe3d33cee7 | regionOne | aodh      | network      | True    | admin     | http://192.168.122.99:9696                     |
+| d05d120153cd4f9b8310ac396b572926 | regionOne | aodh  | alarming  | True    | internal  | http://aodh-internal.openstack.svc:8042  |
+| d6daee0183494d7a9a5faee681c79046 | regionOne | aodh  | alarming  | True    | public    | http://aodh-public.openstack.svc:8042    |
 ----
 
-. Create sample resources. You can test whether you can create alarms:
+.Autoscaling template adoption
+
+* `PrometheusAlarm` alarm type must be used instead of `GnocchiAggregationByResourcesAlarm`
+
+* Create Aodh alarms of type prometheus
 +
 ----
-openstack alarm create \
---name low_alarm \
---type gnocchi_resources_threshold \
---metric cpu \
---resource-id b7ac84e4-b5ca-4f9e-a15c-ece7aaf68987 \
---threshold 35000000000 \
---comparison-operator lt \
---aggregation-method rate:mean \
---granularity 300 \
+openstack alarm create --name high_cpu_alarm \
+--type prometheus \
+--query "(rate(ceilometer_cpu{resource_name=~'cirros'})) * 100" \
+--alarm-action 'log://' \
+--granularity 15 \
 --evaluation-periods 3 \
---alarm-action 'log:\\' \
---ok-action 'log:\\' \
---resource-type instance
+--comparison-operator gt \
+--threshold 7000000000
 ----
 
-//=== (TODO)
-
-//* Include adopted autoscaling heat templates
-//* Include adopted Aodh alarm create commands of type prometheus
+* Verify the state of alarm
++
+----
+openstack alarm list
++--------------------------------------+------------+------------------+-------------------+----------+
+| alarm_id                             | type       | name             | state  | severity | enabled  |
++--------------------------------------+------------+------------------+-------------------+----------+
+| 209dc2e9-f9d6-40e5-aecc-e767ce50e9c0 | prometheus | prometheus_alarm |   ok   |    low   |   True   |
++--------------------------------------+------------+------------------+-------------------+----------+
+----
diff --git a/docs_user/modules/proc_adopting-compute-services-to-the-data-plane.adoc b/docs_user/modules/proc_adopting-compute-services-to-the-data-plane.adoc
@@ -261,6 +261,7 @@ spec:
     - nova
     - ovn
     - neutron-metadata
+    - telemetry
   env:
     - name: ANSIBLE_CALLBACKS_ENABLED
       value: "profile_tasks"
@@ -426,6 +427,7 @@ spec:
     - nova
     - ovn
     - neutron-metadata
+    - telemetry
   nodeTemplate:
     extraMounts:
     - extraVolType: Ceph

diff --git a/docs_user/modules/proc_adopting-telemetry-services.adoc b/docs_user/modules/proc_adopting-telemetry-services.adoc
@@ -14,93 +14,130 @@ This guide also assumes that:
 * Previous Adoption steps completed. MariaDB, the {identity_service_first_ref} and the data plane should be already adopted.
 //kgilliga:Should this procedure be moved after the "Adopting the data plane" chapter?
 
-.Procedure
-
-. Patch the `OpenStackControlPlane` CR to deploy Ceilometer services:
-// TODO(jistr): There are still some quay.io images in the downstream build.
+* Patch the `OpenStackControlPlane` CR to deploy `cluster-observability-operator`:
 +
 ----
-cat << EOF > ceilometer_patch.yaml
+oc create -f - <<EOF
+apiVersion: operators.coreos.com/v1alpha1
+kind: Subscription
+metadata:
+  name: cluster-observability-operator
+  namespace: openshift-operators
 spec:
-  ceilometer:
-    enabled: true
-    template:
-ifeval::["{build}" != "downstream"]
-      centralImage: quay.io/podified-antelope-centos9/openstack-ceilometer-central:current-podified
-      computeImage: quay.io/podified-antelope-centos9/openstack-ceilometer-compute:current-podified
-      customServiceConfig: |
-        [DEFAULT]
-        debug=true
-      ipmiImage: quay.io/podified-antelope-centos9/openstack-ceilometer-ipmi:current-podified
-      nodeExporterImage: quay.io/prometheus/node-exporter:v1.5.0
-      notificationImage: quay.io/podified-antelope-centos9/openstack-ceilometer-notification:current-podified
-      secret: osp-secret
-      sgCoreImage: quay.io/infrawatch/sg-core:v5.1.1
-endif::[]
-ifeval::["{build}" == "downstream"]
-      centralImage: registry.redhat.io/rhosp-dev-preview/openstack-ceilometer-central-rhel9:18.0
-      computeImage: registry.redhat.io/rhosp-dev-preview/openstack-ceilometer-compute-rhel9:18.0
-      customServiceConfig: |
-        [DEFAULT]
-        debug=true
-      ipmiImage: registry.redhat.io/rhosp-dev-preview/openstack-ceilometer-ipmi-rhel9:18.0
-      nodeExporterImage: quay.io/prometheus/node-exporter:v1.5.0
-      notificationImage: registry.redhat.io/rhosp-dev-preview/openstack-ceilometer-notification-rhel9:18.0
-      secret: osp-secret
-      sgCoreImage: quay.io/infrawatch/sg-core:v5.1.1
-endif::[]
+  channel: development
+  installPlanApproval: Automatic
+  name: cluster-observability-operator
+  source: redhat-operators
+  sourceNamespace: openshift-marketplace
 EOF
 ----
 
-. Optional: If you previously backed up your {OpenStackShort} services configuration file from the old environment, you can use os-diff to compare and make sure the configuration is correct. This will produce the difference between both ini configuration files:
+* Wait for the installation to succeed
 +
 ----
-os-diff diff /tmp/collect_tripleo_configs/ceilometer/etc/ceilometer/ceilometer.conf ceilometer_patch.yaml --crd
+oc wait --for jsonpath="{.status.phase}"=Succeeded csv --namespace=openshift-operators -l operators.coreos.com/cluster-observability-operator.openshift-operators
 ----
+
+* Enable metrics storage backend
 +
-For more information, see xref:reviewing-the-openstack-control-plane-configuration_{context}[Reviewing the {rhos_prev_long} control plane configuration].
+----
+oc patch openstackcontrolplane openstack --type=merge --patch '
+spec:
+  telemetry:
+    template:
+      metricStorage:
+        enabled: true
+        monitoringStack:
+          alertingEnabled: true
+          scrapeInterval: 30s
+          storage:
+            strategy: persistent
+            retention: 24h
+            persistent:
+              pvcStorageRequest: 20G
+'
+----
+
+* Verify that `alertmanager` and `prometheus` pods are available
++
+----
+oc get pods -l alertmanager=metric-storage -n openstack
+NAME                            READY   STATUS    RESTARTS   AGE
+alertmanager-metric-storage-0   2/2     Running   0          46s
+alertmanager-metric-storage-1   2/2     Running   0          46s
+
+oc get pods -l prometheus=metric-storage -n openstack
+NAME                          READY   STATUS    RESTARTS   AGE
+prometheus-metric-storage-0   3/3     Running   0          46s
+----
 
-. Patch the `OpenStackControlPlane` CR to deploy Ceilometer services:
+.Procedure
+
+* Patch the `OpenStackControlPlane` CR to deploy Ceilometer services:
 +
 ----
-oc patch openstackcontrolplane openstack --type=merge --patch-file ceilometer_patch.yaml
+oc patch openstackcontrolplane openstack --type=merge --patch '
+spec:
+  telemetry:
+    enabled: true
+    template:
+      ceilometer:
+        passwordSelector:
+          ceilometerService: CeilometerPassword
+        enabled: true
+        secret: osp-secret
+        serviceUser: ceilometer
+'
 ----
 
 .Verification
 
 . Inspect the resulting Ceilometer pods:
 +
 ----
-CEILOMETETR_POD=`oc get pods -l service=ceilometer | tail -n 1 | cut -f 1 -d' '`
+CEILOMETETR_POD=`oc get pods -l service=ceilometer -n openstack | tail -n 1 | cut -f 1 -d' '`
 oc exec -t $CEILOMETETR_POD -c ceilometer-central-agent -- cat /etc/ceilometer/ceilometer.conf
 ----
 
-. Inspect the resulting Ceilometer IPMI agent pod on data plane nodes:
+. Inspect enabled pollsters:
 +
 ----
-podman ps | grep ceilometer-ipmi
+oc get secret ceilometer-config-data -o jsonpath="{.data['polling\.yaml\.j2']}"  | base64 -d
 ----
 
-. Inspect enabled pollsters:
+. Optional: Override default pollsters according to requirements:
 +
 ----
-oc get secret ceilometer-config-data -o jsonpath="{.data['polling\.yaml']}"  | base64 -d
+oc patch openstackcontrolplane controlplane --type=merge --patch '
+spec:
+  telemetry:
+    template:
+      ceilometer:
+          defaultConfigOverwrite:
+            polling.yaml.j2: |
+              ---
+              sources:
+                - name: pollsters
+                  interval: 100
+                  meters:
+                    - volume.*
+                    - image.size
+          enabled: true
+          secret: osp-secret
+'
 ----
 
-. Enable pollsters according to requirements:
+* Patch the `OpenStackControlPlane` CR to include `logging`
 +
 ----
-cat << EOF > polling.yaml
----
-sources:
-    - name: pollsters
-      interval: 300
-      meters:
-        - volume.size
-        - image.size
-        - cpu
-        - memory
-EOF
-
-oc patch secret ceilometer-config-data  --patch="{\"data\": { \"polling.yaml\": \"$(base64 -w0 polling.yaml)\"}}"
+oc patch openstackcontrolplane openstack --type=merge --patch '
+spec:
+  telemetry:
+    template:
+      logging:
+      enabled: false
+      ipaddr: 172.17.0.80
+      port: 10514
+      cloNamespace: openshift-logging
+'
 ----
diff --git a/docs_user/modules/proc_deploying-backend-services.adoc b/docs_user/modules/proc_deploying-backend-services.adoc
@@ -53,7 +53,6 @@ For example, in developer environments with {OpenStackPreviousInstaller} Standal
 ----
 AODH_PASSWORD=$(cat ~/tripleo-standalone-passwords.yaml | grep ' AodhPassword:' | awk -F ': ' '{ print $2; }')
 BARBICAN_PASSWORD=$(cat ~/tripleo-standalone-passwords.yaml | grep ' BarbicanPassword:' | awk -F ': ' '{ print $2; }')
-CEILOMETER_METERING_SECRET=$(cat ~/tripleo-standalone-passwords.yaml | grep ' CeilometerMeteringSecret:' | awk -F ': ' '{ print $2; }')
 CEILOMETER_PASSWORD=$(cat ~/tripleo-standalone-passwords.yaml | grep ' CeilometerPassword:' | awk -F ': ' '{ print $2; }')
 CINDER_PASSWORD=$(cat ~/tripleo-standalone-passwords.yaml | grep ' CinderPassword:' | awk -F ': ' '{ print $2; }')
 GLANCE_PASSWORD=$(cat ~/tripleo-standalone-passwords.yaml | grep ' GlancePassword:' | awk -F ': ' '{ print $2; }')
@@ -105,7 +104,6 @@ account passwords from the original deployment:
 ----
 $ oc set data secret/osp-secret "AodhPassword=$AODH_PASSWORD"
 $ oc set data secret/osp-secret "BarbicanPassword=$BARBICAN_PASSWORD"
-$ oc set data secret/osp-secret "CeilometerMeteringSecret=$CEILOMETER_METERING_SECRET"
 $ oc set data secret/osp-secret "CeilometerPassword=$CEILOMETER_PASSWORD"
 $ oc set data secret/osp-secret "CinderPassword=$CINDER_PASSWORD"
 $ oc set data secret/osp-secret "GlancePassword=$GLANCE_PASSWORD"

diff --git a/docs_user/modules/proc_stopping-openstack-services.adoc b/docs_user/modules/proc_stopping-openstack-services.adoc
@@ -57,7 +57,14 @@ sudo pcs constraint remove order-ceph-nfs-openstack-manila-share-Optional
 +
 ----
 # Update the services list to be stopped
-ServicesToStop=("tripleo_horizon.service"
+ServicesToStop=("tripleo_aodh_api.service"
+                "tripleo_aodh_api_cron.service"
+                "tripleo_aodh_evaluator.service"
+                "tripleo_aodh_listener.service"
+                "tripleo_aodh_notifier.service"
+                "tripleo_ceilometer_agent_central.service"
+                "tripleo_ceilometer_agent_notification.service"
+                "tripleo_horizon.service"
                 "tripleo_keystone.service"
                 "tripleo_barbican_api.service"
                 "tripleo_barbican_worker.service"
@@ -67,7 +74,11 @@ ServicesToStop=("tripleo_horizon.service"
                 "tripleo_cinder_scheduler.service"
                 "tripleo_cinder_volume.service"
                 "tripleo_cinder_backup.service"
+                "tripleo_collectd.service"
                 "tripleo_glance_api.service"
+                "tripleo_gnocchi_api.service"
+                "tripleo_gnocchi_metricd.service"
+                "tripleo_gnocchi_statsd.service"
                 "tripleo_manila_api.service"
                 "tripleo_manila_api_cron.service"
                 "tripleo_manila_scheduler.service"

diff --git a/tests/playbooks/test_minimal.yaml b/tests/playbooks/test_minimal.yaml
@@ -61,6 +61,12 @@
     - role: heat_adoption
       tags:
         - heat_adoption
+    - role: telemetry_adoption
+      tags:
+        - telemetry_adoption
+    - role: autoscaling_adoption
+      tags:
+        - autoscaling_adoption
     - role: stop_remaining_services
       tags:
         - stop_remaining_services