Update telemetry adoption guide

openstack-k8s-operators · Mar 27, 2024 · 7b4482f · 7b4482f
1 parent 949ddcf
commit 7b4482f
Show file tree

Hide file tree

Showing 17 changed files with 244 additions and 92 deletions.
diff --git a/docs_user/modules/openstack-autoscaling_adoption.adoc b/docs_user/modules/openstack-autoscaling_adoption.adoc
@@ -20,12 +20,12 @@ should be already adopted.
 
 == Procedure - Autoscaling adoption
 
-Patch OpenStackControlPlane to deploy autoscaling services:
+=== Patch OpenStackControlPlane to deploy autoscaling services:
 
 ----
-cat << EOF > aodh_patch.yaml
+oc patch openstackcontrolplane openstack --type=merge --patch '
 spec:
-  autoscaling:
+  telemetry:
     enabled: true
     prometheus:
       deployPrometheus: false
@@ -53,29 +53,45 @@ endif::[]
 EOF
 ----
 
-
-____
-If you have previously backed up your OpenStack services configuration file from the old environment, you can use os-diff to compare and make sure the configuration is correct. For more information, see xref:pulling-the-openstack-configuration_{context}[Pulling the OpenStack configuration].
-____
+=== Install cluster-observability-operator
 
 ----
-pushd os-diff
-./os-diff cdiff --service aodh -c /tmp/collect_tripleo_configs/aodh/etc/aodh/aodh.conf -o aodh_patch.yaml
+oc create -f - <<EOF
+apiVersion: operators.coreos.com/v1alpha1
+kind: Subscription
+metadata:
+  name: cluster-observability-operator
+  namespace: openshift-operators
+spec:
+  channel: development
+  installPlanApproval: Automatic
+  name: cluster-observability-operator
+  source: redhat-operators
+  sourceNamespace: openshift-marketplace
+EOF
 ----
 
-____
-This will producre the difference between both ini configuration files.
-____
+=== Wait for the installation to succeed
 
-Patch OpenStackControlPlane to deploy Aodh services:
+----
+oc wait --for jsonpath="{.status.phase}"=Succeeded csv --namespace=openshift-operators -l operators.coreos.com/cluster-observability-operator.openshift-operators
+----
 
+=== Enable metrics storage backend
 ----
-oc patch openstackcontrolplane openstack --type=merge --patch-file aodh_patch.yaml
+oc patch openstackcontrolplane openstack --type=merge --patch '
+spec:
+  telemetry:
+    enabled: true
+    template:
+      metricStorage:
+        enabled: true
+'
 ----
 
 == Post-checks
 
-=== If autoscaling services are enabled inspect Aodh pods
+=== Verify Aodh pods and service endpoints
 
 ----
 AODH_POD=`oc get pods -l service=aodh | tail -n 1 | cut -f 1 -d' '`
@@ -86,29 +102,21 @@ oc exec -t $AODH_POD -c aodh-api -- cat /etc/aodh/aodh.conf
 
 ----
 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.
+=== Verify metric storage pods are deployed
 
 ----
-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 \
---evaluation-periods 3 \
---alarm-action 'log:\\' \
---ok-action 'log:\\' \
---resource-type instance
+oc get pods -l alertmanager=metric-storage
+NAME                            READY   STATUS    RESTARTS   AGE
+alertmanager-metric-storage-0   2/2     Running   0          17h
+alertmanager-metric-storage-1   2/2     Running   0          17h
+
+oc get pods -l prometheus=metric-storage
+NAME                          READY   STATUS    RESTARTS   AGE
+prometheus-metric-storage-0   3/3     Running   0          17h
 ----
 
 //=== (TODO)

diff --git a/docs_user/modules/openstack-backend_services_deployment.adoc b/docs_user/modules/openstack-backend_services_deployment.adoc
@@ -279,14 +279,24 @@ spec:
                 metallb.universe.tf/loadBalancerIPs: 172.17.0.86
             spec:
               type: LoadBalancer
-
-  ceilometer:
+  telemtry:
     enabled: false
-    template: {}
+    template:
+      ceilometer:
+        enabled: false
+        template: {}
 
-  autoscaling:
-    enabled: false
-    template: {}
+      autoscaling:
+        enabled: false
+        template: {}
+
+      metricStorage:
+        enabled: false
+        template: {}
+
+      logging:
+        enabled: false
+        template: {}
 EOF
 ----
 

diff --git a/docs_user/modules/openstack-edpm_adoption.adoc b/docs_user/modules/openstack-edpm_adoption.adoc
@@ -277,6 +277,7 @@ spec:
     - nova-compute-extraconfig
     - ovn
     - neutron-metadata
+    - telemetry
   env:
     - name: ANSIBLE_CALLBACKS_ENABLED
       value: "profile_tasks"

diff --git a/docs_user/modules/openstack-heat_adoption.adoc b/docs_user/modules/openstack-heat_adoption.adoc
@@ -78,6 +78,8 @@ spec:
         authEncryptionKey: HeatAuthEncryptionKey
         database: HeatDatabasePassword
         service: HeatPassword
+      rabbitMqClusterName: rabbitmq
+      serviceUser: heat
 '
 ----
 

diff --git a/docs_user/modules/openstack-stop_openstack_services.adoc b/docs_user/modules/openstack-stop_openstack_services.adoc
@@ -98,7 +98,14 @@ environmental variables and function:
 ----
 
 # 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"
@@ -108,7 +115,11 @@ 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/docs_user/modules/openstack-stop_remaining_services.adoc b/docs_user/modules/openstack-stop_remaining_services.adoc
@@ -64,7 +64,10 @@ ComputeServicesToStop=(
                 "tripleo_nova_virtproxyd.service"
                 "tripleo_nova_virtqemud.service"
                 "tripleo_nova_virtsecretd.service"
-                "tripleo_nova_virtstoraged.service")
+                "tripleo_nova_virtstoraged.service"
+                "tripleo_ceilometer_agent_compute.service"
+                "tripleo_ceilometer_agent_ipmi.service"
+                "tripleo_collectd.service")
 
 PacemakerResourcesToStop=(
                 "galera-bundle"

diff --git a/docs_user/modules/openstack-telemetry_adoption.adoc b/docs_user/modules/openstack-telemetry_adoption.adoc
@@ -19,61 +19,44 @@ This guide also assumes that:
 
 == Procedure - Telemetry adoption
 
-Patch OpenStackControlPlane to deploy Ceilometer services:
+Create  OpenStackControlPlane to deploy Ceilometer services:
 
 // TODO(jistr): There are still some quay.io images in the downstream build.
 
 ----
-cat << EOF > ceilometer_patch.yaml
+oc patch openstackcontrolplane openstack --type=merge --patch '
 spec:
-  ceilometer:
+  telemetry:
     enabled: true
     template:
+      ceilometer:
 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
+        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
+        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::[]
 EOF
 ----
 
-____
-If you have previously backed up your OpenStack services configuration file from the old environment, you can use os-diff to compare and make sure the configuration is correct. For more information, see xref:pulling-the-openstack-configuration_{context}[Pulling the OpenStack configuration].
-____
-
-----
-pushd os-diff
-./os-diff cdiff --service ceilometer -c /tmp/collect_tripleo_configs/ceilometer/etc/ceilometer/ceilometer.conf -o ceilometer_patch.yaml
-----
-
-____
-This will produce the difference between both ini configuration files.
-____
-
-Patch OpenStackControlPlane to deploy Ceilometer services:
-
-----
-oc patch openstackcontrolplane openstack --type=merge --patch-file ceilometer_patch.yaml
-----
 
 == Post-checks
 
@@ -84,19 +67,13 @@ CEILOMETETR_POD=`oc get pods -l service=ceilometer | 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
-
-----
-podman ps | grep ceilometer-ipmi
-----
-
 === Inspecting enabled pollsters
 
 ----
 oc get secret ceilometer-config-data -o jsonpath="{.data['polling\.yaml']}"  | base64 -d
 ----
 
-=== Enabling pollsters according to requirements
+=== Create polling.yaml with required pollsters
 
 ----
 cat << EOF > polling.yaml
@@ -108,8 +85,11 @@ sources:
         - volume.size
         - image.size
         - cpu
-        - memory
+        - memory.usage
 EOF
+----
 
+=== Update ceilometer configuration with new pollsters
+----
 oc patch secret ceilometer-config-data  --patch="{\"data\": { \"polling.yaml\": \"$(base64 -w0 polling.yaml)\"}}"
 ----
diff --git a/tests/roles/autoscaling_adoption/meta/main.yaml b/tests/roles/autoscaling_adoption/meta/main.yaml
@@ -0,0 +1,2 @@
+dependencies:
+  - role: common_defaults