Monitoring
Installing kube-prometheus-stack in the same Kubernetes cluster that hosts the Seldon Enterprise Platform.
kube-prometheus
, also known as Prometheus Operator, is a popular open-source project that provides complete monitoring and alerting solutions for Kubernetes clusters. It combines tools and components to create a monitoring stack for Kubernetes environments.
The Seldon Enterprise Platform, along with any deployed models, automatically exposes metrics to Prometheus. By default, certain alerting rules are pre-configured, and an alertmanager instance is included.
You can install kube-prometheus
to monitor Seldon components, and ensure that the appropriate ServiceMonitors
are in place for Seldon deployments. The analytics component is configured with the Prometheus integration. The monitoring for Seldon Enterprise Platform is based on the Prometheus Operator and the related PodMonitor
and PrometheusRule
resources.
Monitoring the model deployments in Seldon Enterprise Platform involves:
Prerequisites
Install Seldon Enterprise Platform.
Install Ingress Controller.
Install Docker
Installing kube-prometheus
Download the
seldon-deploy-install.tar
file that contains required installation resources. For example, to download the installation resources for version2.4.0
of Seldon Enterprise Platform run the following:TAG=2.4.0 && \ docker create --name=tmp-sd-container seldonio/seldon-deploy-server:2.4.0 && \ docker cp tmp-sd-container:/seldon-deploy-dist/seldon-deploy-install.tar.gz . && \ docker rm -v tmp-sd-container
Extract the contents of the
seldon-deploy-install.tar
file.tar -xzf seldon-deploy-install.tar.gz
Create a namespace for the monitoring components of Seldon Enterprise Platform.
kubectl create ns seldon-monitoring || echo "Namespace seldon-monitoring already exists"
Create a YAML file to specify the initial configuration. For example, create the
prometheus-values.yaml
file. Use your preferred text editor to create and save the file with the following content:fullnameOverride: seldon-monitoring kube-state-metrics: extraArgs: metric-labels-allowlist: pods=[*]
Note: Make sure to include
metric-labels-allowlist: pods=[*]
in the Helm values file. If you are using your own Prometheus Operator installation, ensure that the pods labels, particularlyapp.kubernetes.io/managed-by=seldon-core
, are part of the collected metrics. These labels are essential for calculating deployment usage rules.Change to the directory that contains the
prometheus-values
file and run the following command to install version9.5.12
ofkube-prometheus
.helm upgrade --install prometheus kube-prometheus \ --version 9.5.12 \ --namespace seldon-monitoring \ --values prometheus-values.yaml \ --repo https://charts.bitnami.com/bitnami
When the installation is complete, you should see this:
WARNING: There are "resources" sections in the chart not set. Using "resourcesPreset" is not recommended for production. For production installations, please set the following values according to your workload needs: - alertmanager.resources - blackboxExporter.resources - operator.resources - prometheus.resources - prometheus.thanos.resources +info https://kubernetes.io/docs/concepts/configuration/manage-resources-containers/
Check the status of the installation.
kubectl rollout status -n seldon-monitoring deployment/seldon-monitoring-operator
When the installation is complete, you should see this:
Waiting for deployment "seldon-monitoring-operator" rollout to finish: 0 of 1 updated replicas are available... deployment "seldon-monitoring-operator" successfully rolled out
Configuring monitoring for Seldon Enterprise Platform
To configure monitoring create a dedicated
PodMonitor
andPrometheusRule
resources. Copy the installation resource files from theseldon-deploy-install/reference-configuration/metrics/
directory to the current directory.cp seldon-deploy-install/reference-configuration/metrics/seldon-monitor.yaml seldon-monitor.yaml cp seldon-deploy-install/reference-configuration/metrics/drift-monitor.yaml drift-monitor.yaml cp seldon-deploy-install/reference-configuration/metrics/deploy-monitor.yaml deploy-monitor.yaml cp seldon-deploy-install/reference-configuration/metrics/metrics-server-monitor.yaml metrics-server-monitor.yaml cp seldon-deploy-install/reference-configuration/metrics/deployment-usage-rules.yaml deployment-usage-rules.yaml
Apply the configurations to the Kubernetes cluster that is running the Seldon Enterprise Platform.
kubectl apply -n seldon-monitoring -f seldon-monitor.yaml kubectl apply -n seldon-monitoring -f drift-monitor.yaml kubectl apply -n seldon-monitoring -f deploy-monitor.yaml kubectl apply -n seldon-monitoring -f metrics-server-monitor.yaml kubectl apply -f deployment-usage-rules.yaml -n seldon-monitoring
When the configuration is complete, you should see this:
podmonitor.monitoring.coreos.com/seldon-core created podmonitor.monitoring.coreos.com/seldon-drift-detector created podmonitor.monitoring.coreos.com/seldon-deploy created podmonitor.monitoring.coreos.com/metrics-server created prometheusrule.monitoring.coreos.com/seldon-deployment-usage-rules created
You can access Prometheus from outside the cluster by running the following commands:
echo "Prometheus URL: http://127.0.0.1:9090/" kubectl port-forward --namespace seldon-monitoring svc/seldon-monitoring-prometheus 9090:9090
You can access Alertmanager from outside the cluster by running the following commands:
echo "Alertmanager URL: http://127.0.0.1:9093/" kubectl port-forward --namespace seldon-monitoring svc/seldon-monitoring-alertmanager 9093:9093
Add the following to your
install-values.yaml
file.prometheus: seldon: namespaceMetricName: namespace activeModelsNamespaceMetricName: exported_namespace serviceMetricName: service url: http://seldon-monitoring-prometheus.seldon-monitoring:9090/api/v1/ env: ALERTMANAGER_URL: http://seldon-monitoring-alertmanager.seldon-monitoring:9093/api/v1/alerts
Configure metrics collection by creating the following
PodMonitor
resources.PODMONITOR_RESOURCE_LOCATION=https://raw.githubusercontent.com/SeldonIO/seldon-core/v2.8.5/prometheus/monitors kubectl apply -f ${PODMONITOR_RESOURCE_LOCATION}/agent-podmonitor.yaml kubectl apply -f ${PODMONITOR_RESOURCE_LOCATION}/envoy-servicemonitor.yaml kubectl apply -f ${PODMONITOR_RESOURCE_LOCATION}/pipelinegateway-podmonitor.yaml kubectl apply -f ${PODMONITOR_RESOURCE_LOCATION}/server-podmonitor.yaml
When the resources are created, you should see this:
podmonitor.monitoring.coreos.com/agent created servicemonitor.monitoring.coreos.com/envoy created podmonitor.monitoring.coreos.com/pipelinegateway created podmonitor.monitoring.coreos.com/server created
Change to the directory that contains the
install-values.yaml
file and then upgrade the Seldon Enterprise Platform installation in the namespaceseldon-system
.helm upgrade seldon-enterprise seldon-charts/seldon-deploy --namespace seldon-system -f install-values.yaml --version 2.4.0 --install
Check the status of the installation seldon-enterprise-seldon-deploy.
kubectl rollout status deployment/seldon-enterprise-seldon-deploy -n seldon-system
When the installation is complete you should see this:
deployment "seldon-enterprise-seldon-deploy" successfully rolled out
Access Seldon Enterprise Platform.
Get the Pod that is running Seldon Enterprise Platform in the cluster and save it as
$POD_NAME.
export POD_NAME=$(kubectl get pods --namespace seldon-system -l "app.kubernetes.io/name=seldon-deploy,app.kubernetes.io/instance=seldon-enterprise" -o jsonpath="{.items[0].metadata.name}")
You can use port-forwarding to access your application locally.
kubectl port-forward $POD_NAME 8000:8000 --namespace seldon-system
Open your browser and navigate to
http://127.0.0.1:8000/seldon-deploy/
to access Seldon Enterprise Platform.
Next
You may now be able to check the status of Seldon components in Prometheus:
Open your browser and navigate to
http://127.0.0.1:9090/
to access Prometheus UI from outside the cluster.Go to Status and select Targets.
The status of all the endpoints and the scrape details are displayed.
Last updated
Was this helpful?