chore: unmanaged fixes (microsoft#56)

Signed-off-by: Evan Baker <rbtr@users.noreply.github.com> Co-authored-by: Evan Baker <rbtr@users.noreply.github.com>
rbtr · Mar 15, 2024 · 7866733 · 7866733
1 parent 7dd6cb3
commit 7866733
Show file tree

Hide file tree

Showing 4 changed files with 66 additions and 40 deletions.
diff --git a/Makefile b/Makefile
@@ -405,7 +405,7 @@ helm-install: manifests
 		--set logLevel=info \
 		--set os.windows=true \
 		--set operator.enabled=false \
-		--set enabledPlugin_linux="[\"dropreason\"\,\"packetforward\"\,\"linuxutil\"\,\"dns\"]"
+		--set enabledPlugin_linux="\[dropreason\,packetforward\,linuxutil\,dns\]"
 
 # advanced/pod-level mode with scale limitations, where metrics are aggregated by source and destination Pod
 helm-install-advanced-remote-context: manifests
@@ -420,7 +420,7 @@ helm-install-advanced-remote-context: manifests
 		--set operator.enableRetinaEndpoint=true \
 		--set operator.repository=$(IMAGE_REGISTRY)/$(RETINA_OPERATOR_IMAGE) \
 		--skip-crds \
-		--set enabledPlugin_linux="[\"dropreason\",\"packetforward\",\"linuxutil\",\"dns\",\"packetparser\"\]" \
+		--set enabledPlugin_linux="\[dropreason\,packetforward\,linuxutil\,dns\,packetparser\]" \
 		--set enablePodLevel=true \
 		--set remoteContext=true
 
@@ -437,7 +437,7 @@ helm-install-advanced-local-context: manifests
 		--set operator.enableRetinaEndpoint=true \
 		--set operator.repository=$(IMAGE_REGISTRY)/$(RETINA_OPERATOR_IMAGE) \
 		--skip-crds \
-		--set enabledPlugin_linux="[\"dropreason\",\"packetforward\",\"linuxutil\",\"dns\",\"packetparser\"]" \
+		--set enabledPlugin_linux="\[dropreason\,packetforward\,linuxutil\,dns\,packetparser\]" \
 		--set enablePodLevel=true \
 		--set enableAnnotations=true \
 		--set bypassLookupIPOfInterest=false

diff --git a/deploy/prometheus/values.yaml b/deploy/prometheus/values.yaml
@@ -1,5 +1,50 @@
+windowsMonitoring:
+  enabled: true
+
+prometheusOperator:
+  affinity:
+    nodeAffinity:
+      requiredDuringSchedulingIgnoredDuringExecution:
+        nodeSelectorTerms:
+          - matchExpressions:
+              - key: kubernetes.io/os
+                operator: In
+                values:
+                  - linux
+
+  admissionWebhooks:
+    deployment:
+      affinity:
+        nodeAffinity:
+          requiredDuringSchedulingIgnoredDuringExecution:
+            nodeSelectorTerms:
+              - matchExpressions:
+                  - key: kubernetes.io/os
+                    operator: In
+                    values:
+                      - linux
+    patch:
+      affinity:
+        nodeAffinity:
+          requiredDuringSchedulingIgnoredDuringExecution:
+            nodeSelectorTerms:
+              - matchExpressions:
+                  - key: kubernetes.io/os
+                    operator: In
+                    values:
+                      - linux
+
 prometheus:
   prometheusSpec:
+    affinity:
+      nodeAffinity:
+        requiredDuringSchedulingIgnoredDuringExecution:
+          nodeSelectorTerms:
+            - matchExpressions:
+                - key: kubernetes.io/os
+                  operator: In
+                  values:
+                    - linux
     additionalScrapeConfigs: |
       - job_name: "retina-pods"
         kubernetes_sd_configs:

diff --git a/docs/installation/img/grafana-dashboard-metrics.png b/docs/installation/img/grafana-dashboard-metrics.png
diff --git a/docs/installation/prometheus-unmanaged.md b/docs/installation/prometheus-unmanaged.md
@@ -15,52 +15,21 @@
   helm repo update
   ```
 
-2. Install the Prometheus chart
+2. Save **[these Prometheus values](https://github.com/microsoft/retina/blob/main/deploy/prometheus/values.yaml)** below to `deploy/prometheus/values.yaml`
+
+3. Install the Prometheus chart
 
   ```shell
   helm install prometheus -n kube-system -f deploy/prometheus/values.yaml prometheus-community/kube-prometheus-stack
   ```
 
-3. Save the Prometheus values below to `deploy/prometheus/values.yaml`
-
-  ```yaml
-  prometheus:
-    prometheusSpec:
-      additionalScrapeConfigs: |
-        - job_name: "retina-pods"
-          kubernetes_sd_configs:
-            - role: pod
-          relabel_configs:
-            - source_labels: [__meta_kubernetes_pod_container_name]
-              action: keep
-              regex: retina(.*)
-            - source_labels:
-                [__address__, __meta_kubernetes_pod_annotation_prometheus_io_port]
-              separator: ":"
-              regex: ([^:]+)(?::\d+)?
-              target_label: __address__
-              replacement: ${1}:${2}
-              action: replace
-            - source_labels: [__meta_kubernetes_pod_node_name]
-              action: replace
-              target_label: instance
-          metric_relabel_configs:
-            - source_labels: [__name__]
-              action: keep
-              regex: (.*)
-  ```
-
-4. Upgrade deployment with
+Or if you already have the chart installed, upgrade how you see fit, providing the new job name as an additional scrape config, ex:
 
   ```shell
   helm upgrade prometheus -n kube-system -f deploy/prometheus/values.yaml prometheus-community/kube-prometheus-stack
   ```
 
-5. Install Retina
-
-  ```shell
-  helm install retina ./deploy/manifests/controller/helm/retina/ --namespace kube-system --dependency-update
-  ```
+Node: Grafana and kube-state metrics may schedule on Windows nodes, the current chart doesn't have node affinity for those components. Some manual intervention may be required.
 
 6. Verify that the Retina Pods are being scraped by port-forwarding the Prometheus server:
 
@@ -74,4 +43,16 @@
 
 ## Configuring Grafana
 
-Create a Grafana instance at [grafana.com](https://www.grafana.com) and follow [Configuring Grafana](./grafana.md).
+Create a Grafana instance at [grafana.com](https://www.grafana.com) and follow [Configuring Grafana](./grafana.md), or use the one installed from above.
+
+8. Get the Grafana password:
+
+```shell
+kubectl get secret -n kube-system prometheus-grafana -o jsonpath="{.data.admin-password}" | base64 --decode ; echo
+```
+
+9. Import the new dashboard from **[here](https://grafana.com/grafana/dashboards/18814/)**.
+
+10. Metrics should be visible:
+
+![alt text](img/grafana-dashboard-metrics.png)