diff --git a/helm-charts/common/embedding-usvc/README.md b/helm-charts/common/embedding-usvc/README.md index 9dc5877eb..6cef0c1af 100644 --- a/helm-charts/common/embedding-usvc/README.md +++ b/helm-charts/common/embedding-usvc/README.md @@ -43,16 +43,17 @@ https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-promet ### Gotchas Why HPA is opt-in: -* Enabling chart `horizontalPodAutoscaler` option will _overwrite_ cluster's current + +- Enabling chart `horizontalPodAutoscaler` option will _overwrite_ cluster's current `PrometheusAdapter` configuration with its own custom metrics configuration. Take copy of the existing one before install, if that matters: `kubectl -n monitoring get cm/adapter-config -o yaml > adapter-config.yaml` -* `PrometheusAdapter` needs to be restarted after install, for it to read the new configuration: +- `PrometheusAdapter` needs to be restarted after install, for it to read the new configuration: `ns=monitoring; kubectl -n $ns delete $(kubectl -n $ns get pod --selector app.kubernetes.io/name=prometheus-adapter -o name)` -* By default Prometheus adds [k8s RBAC rules](https://github.com/prometheus-operator/kube-prometheus/blob/main/manifests/prometheus-roleBindingSpecificNamespaces.yaml) - for accessing metrics from `default`, `kube-system` and `monitoring` namespaces. If Helm is +- By default Prometheus adds [k8s RBAC rules](https://github.com/prometheus-operator/kube-prometheus/blob/main/manifests/prometheus-roleBindingSpecificNamespaces.yaml) + for accessing metrics from `default`, `kube-system` and `monitoring` namespaces. If Helm is asked to install OPEA services to some other namespace, those rules need to be updated accordingly -* Provided HPA rules are examples for Xeon, for efficient scaling they need to be fine-tune for given setup +- Provided HPA rules are examples for Xeon, for efficient scaling they need to be fine-tune for given setup (underlying HW, used models, OPEA version etc) ## Verify diff --git a/helm-charts/common/embedding-usvc/templates/servicemonitor.yaml b/helm-charts/common/embedding-usvc/templates/servicemonitor.yaml index 0d5e6e776..f540509ca 100644 --- a/helm-charts/common/embedding-usvc/templates/servicemonitor.yaml +++ b/helm-charts/common/embedding-usvc/templates/servicemonitor.yaml @@ -14,4 +14,4 @@ spec: - interval: 4s port: service scheme: http -{{- end }} \ No newline at end of file +{{- end }} diff --git a/helm-charts/common/teirerank/README.md b/helm-charts/common/teirerank/README.md index 5a1e3ef46..20207a1dc 100644 --- a/helm-charts/common/teirerank/README.md +++ b/helm-charts/common/teirerank/README.md @@ -37,16 +37,17 @@ https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-promet ### Gotchas Why HPA is opt-in: -* Enabling chart `horizontalPodAutoscaler` option will _overwrite_ cluster's current + +- Enabling chart `horizontalPodAutoscaler` option will _overwrite_ cluster's current `PrometheusAdapter` configuration with its own custom metrics configuration. Take copy of the existing one before install, if that matters: `kubectl -n monitoring get cm/adapter-config -o yaml > adapter-config.yaml` -* `PrometheusAdapter` needs to be restarted after install, for it to read the new configuration: +- `PrometheusAdapter` needs to be restarted after install, for it to read the new configuration: `ns=monitoring; kubectl -n $ns delete $(kubectl -n $ns get pod --selector app.kubernetes.io/name=prometheus-adapter -o name)` -* By default Prometheus adds [k8s RBAC rules](https://github.com/prometheus-operator/kube-prometheus/blob/main/manifests/prometheus-roleBindingSpecificNamespaces.yaml) - for accessing metrics from `default`, `kube-system` and `monitoring` namespaces. If Helm is +- By default Prometheus adds [k8s RBAC rules](https://github.com/prometheus-operator/kube-prometheus/blob/main/manifests/prometheus-roleBindingSpecificNamespaces.yaml) + for accessing metrics from `default`, `kube-system` and `monitoring` namespaces. If Helm is asked to install OPEA services to some other namespace, those rules need to be updated accordingly -* Provided HPA rules are examples for Xeon, for efficient scaling they need to be fine-tune for given setup +- Provided HPA rules are examples for Xeon, for efficient scaling they need to be fine-tune for given setup (underlying HW, used models, OPEA version etc) ## Verify diff --git a/helm-charts/common/teirerank/templates/servicemonitor.yaml b/helm-charts/common/teirerank/templates/servicemonitor.yaml index 5f2ef6f46..83666b6b2 100644 --- a/helm-charts/common/teirerank/templates/servicemonitor.yaml +++ b/helm-charts/common/teirerank/templates/servicemonitor.yaml @@ -14,4 +14,4 @@ spec: - interval: 4s port: service scheme: http -{{- end }} \ No newline at end of file +{{- end }} diff --git a/helm-charts/common/tgi/README.md b/helm-charts/common/tgi/README.md index abacd8505..79e9756d0 100644 --- a/helm-charts/common/tgi/README.md +++ b/helm-charts/common/tgi/README.md @@ -40,16 +40,17 @@ https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-promet ### Gotchas Why HPA is opt-in: -* Enabling chart `horizontalPodAutoscaler` option will _overwrite_ cluster's current + +- Enabling chart `horizontalPodAutoscaler` option will _overwrite_ cluster's current `PrometheusAdapter` configuration with its own custom metrics configuration. Take copy of the existing one before install, if that matters: `kubectl -n monitoring get cm/adapter-config -o yaml > adapter-config.yaml` -* `PrometheusAdapter` needs to be restarted after install, for it to read the new configuration: +- `PrometheusAdapter` needs to be restarted after install, for it to read the new configuration: `ns=monitoring; kubectl -n $ns delete $(kubectl -n $ns get pod --selector app.kubernetes.io/name=prometheus-adapter -o name)` -* By default Prometheus adds [k8s RBAC rules](https://github.com/prometheus-operator/kube-prometheus/blob/main/manifests/prometheus-roleBindingSpecificNamespaces.yaml) - for accessing metrics from `default`, `kube-system` and `monitoring` namespaces. If Helm is +- By default Prometheus adds [k8s RBAC rules](https://github.com/prometheus-operator/kube-prometheus/blob/main/manifests/prometheus-roleBindingSpecificNamespaces.yaml) + for accessing metrics from `default`, `kube-system` and `monitoring` namespaces. If Helm is asked to install OPEA services to some other namespace, those rules need to be updated accordingly -* Provided HPA rules are examples for Xeon, for efficient scaling they need to be fine-tune for given setup +- Provided HPA rules are examples for Xeon, for efficient scaling they need to be fine-tune for given setup (underlying HW, used models, OPEA version etc) ## Verify diff --git a/helm-charts/common/tgi/servicemonitor.yaml b/helm-charts/common/tgi/servicemonitor.yaml index 6f96aff89..6a2bc391d 100644 --- a/helm-charts/common/tgi/servicemonitor.yaml +++ b/helm-charts/common/tgi/servicemonitor.yaml @@ -19,4 +19,4 @@ spec: - interval: 4s port: service scheme: http -{{- end }} \ No newline at end of file +{{- end }}