Fix: Align exporter labels, image tags, and build process (#25)

- Helm Chart:
  - Added `app.kubernetes.io/component: exporter` to the exporter pod
    labels via `values.yaml` to match the service selector.
  - Updated image tag defaulting in `exporter-controller.yaml` to use
    `Chart.appVersion` directly (e.g., "0.1.0" instead of "v0.1.0").

- Build Process (`.github/workflows/release.yml`):
  - Configured `docker/metadata-action` to ensure image tags are generated
    without a 'v' prefix (e.g., "0.1.0" from Git tag "v0.1.0").
    This aligns the published image tags with the Helm chart's
    updated image tag references.

- Repository:
  - Added `rendered-manifests.yaml` and `rendered-manifests-updated.yaml`
    to `.gitignore`.

Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com>

.github/workflows/ci.yaml

@@ -19,7 +19,16 @@ jobs:
       - name: Set up Helm
         uses: azure/setup-helm@v3
         with:
-          version: v3.10.0
+          version: v3.10.0 # Using a specific version, can be updated
+
+      - name: Add Helm repositories
+        run: |
+          helm repo add bjw-s https://bjw-s-labs.github.io/helm-charts/ --force-update
+          helm repo add prometheus-community https://prometheus-community.github.io/helm-charts --force-update
+          helm repo update
+
+      - name: Build Helm chart dependencies
+        run: helm dependency build ./charts/iperf3-monitor
 
       - name: Helm Lint
         run: helm lint ./charts/iperf3-monitor
@@ -27,23 +36,49 @@ jobs:
   build:
     name: Build Docker Image
     runs-on: ubuntu-latest
+    permissions:
+      contents: read # Needed to checkout the repository
+      packages: write # Needed to push Docker images to GHCR
     steps:
       - name: Check out code
         uses: actions/checkout@v3
 
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: Set up QEMU
+        uses: docker/setup-qemu-action@v2
+
       - name: Extract metadata (tags, labels) for Docker
         id: meta
         uses: docker/metadata-action@v4
         with:
           images: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}
+          tags: |
+            # Tag with the PR number if it's a pull request event
+            type=match,pattern=pull_request,value=pr-{{number}}
+            # Tag with the git SHA
+            type=sha,prefix=
+            # Tag with 'latest' if on the main branch (though this workflow only runs on PRs to main)
+            type=ref,event=branch,pattern=main,value=latest
+
+      - name: Log in to GitHub Container Registry
+        uses: docker/login-action@v3
+        with:
+          registry: ${{ env.REGISTRY }}
+          username: ${{ github.actor }}
+          password: ${{ secrets.GITHUB_TOKEN }}
 
       - name: Build Docker image
         uses: docker/build-push-action@v4
         with:
           context: ./exporter
-          push: false # Do not push on PRs
+          # Push the image if the event is a pull request.
+          # The workflow currently only triggers on pull_request events.
+          push: ${{ github.event_name == 'pull_request' }}
           tags: ${{ steps.meta.outputs.tags }}
           labels: ${{ steps.meta.outputs.labels }}
+          platforms: linux/amd64,linux/arm64
 
   test:
     name: Run Tests

.github/workflows/release.yml

@@ -22,6 +22,15 @@ jobs:
         with:
           version: v3.10.0
 
+      - name: Add Helm repositories
+        run: |
+          helm repo add bjw-s https://bjw-s-labs.github.io/helm-charts/ --force-update
+          helm repo add prometheus-community https://prometheus-community.github.io/helm-charts --force-update
+          helm repo update
+
+      - name: Build Helm chart dependencies
+        run: helm dependency build ./charts/iperf3-monitor
+
       - name: Helm Lint
         run: helm lint ./charts/iperf3-monitor
 
@@ -36,6 +45,12 @@ jobs:
       - name: Check out code
         uses: actions/checkout@v3
 
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: Set up QEMU
+        uses: docker/setup-qemu-action@v2
+
       - name: Log in to GitHub Container Registry
         uses: docker/login-action@v2
         with:
@@ -48,6 +63,11 @@ jobs:
         uses: docker/metadata-action@v4
         with:
           images: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}
+          tags: |
+            type=semver,pattern={{version}}
+            # This ensures that for a git tag like "v0.1.0",
+            # an image tag "0.1.0" is generated.
+            # It will also generate "latest" for the most recent semver tag.
 
       - name: Build and push Docker image
         uses: docker/build-push-action@v4
@@ -56,6 +76,7 @@ jobs:
           push: true
           tags: ${{ steps.meta.outputs.tags }}
           labels: ${{ steps.meta.outputs.labels }}
+          platforms: linux/amd64,linux/arm64
 
   package-and-publish-chart:
     name: Package and Publish Helm Chart
@@ -79,11 +100,20 @@ jobs:
           sudo wget https://github.com/mikefarah/yq/releases/latest/download/yq_linux_amd64 -O /usr/bin/yq &&\
           sudo chmod +x /usr/bin/yq
 
+      - name: Add Helm repositories
+        run: |
+          helm repo add bjw-s https://bjw-s-labs.github.io/helm-charts/ --force-update
+          helm repo add prometheus-community https://prometheus-community.github.io/helm-charts --force-update
+          helm repo update
+
+      - name: Build Helm chart dependencies
+        run: helm dependency build ./charts/iperf3-monitor
+
       - name: Set Chart Version from Tag
         run: |
           VERSION=$(echo "${{ github.ref_name }}" | sed 's/^v//')
-          yq e -i '.version = strenv(VERSION)' ./charts/iperf3-monitor/Chart.yaml
+          VERSION=$VERSION yq e -i '.version = strenv(VERSION)' ./charts/iperf3-monitor/Chart.yaml
-          yq e -i '.appVersion = strenv(VERSION)' ./charts/iperf3-monitor/Chart.yaml
+          VERSION=$VERSION yq e -i '.appVersion = strenv(VERSION)' ./charts/iperf3-monitor/Chart.yaml
           cat ./charts/iperf3-monitor/Chart.yaml # Optional: print updated Chart.yaml
 
       - name: Publish Helm chart

.gitignore

@@ -36,4 +36,8 @@ Thumbs.db
 
 # Helm
 !charts/iperf3-monitor/.helmignore
-charts/*.tgz # Ignore packaged chart files
+charts/iperf3-monitor/charts/
+
+# Rendered Kubernetes manifests (for local testing)
+rendered-manifests.yaml
+rendered-manifests-updated.yaml

README.md

@@ -74,37 +74,123 @@ nameOverride: ""
 # -- Override the fully qualified app name.
 fullnameOverride: ""
 
+# Exporter Configuration (`controllers.exporter`)
+# The iperf3 exporter is managed under the `controllers.exporter` section,
+# leveraging the `bjw-s/common-library` for robust workload management.
+controllers:
   exporter:
-  # -- Configuration for the exporter container image.
+    # -- Enable the exporter controller.
-  image:
+    enabled: true
-    # -- The container image repository for the exporter.
+    # -- Set the controller type for the exporter.
-    repository: ghcr.io/malarinv/iperf3-monitor
+    # Valid options are "deployment" or "daemonset".
-    # -- The container image tag for the exporter. If not set, the chart's appVersion is used.
+    # Use "daemonset" for N-to-N node monitoring where an exporter runs on each node (or selected nodes).
-    tag: ""
+    # Use "deployment" for a centralized exporter (typically with replicaCount: 1).
-    # -- The image pull policy for the exporter container.
+    # @default -- "deployment"
-    pullPolicy: IfNotPresent
+    type: deployment
-
+    # -- Number of desired exporter pods. Only used if type is "deployment".
-  # -- Number of exporter pod replicas. Typically 1 is sufficient.
+    # @default -- 1
-  replicaCount: 1
+    replicas: 1
 
+    # -- Application-specific configuration for the iperf3 exporter.
+    # These values are used to populate environment variables for the exporter container.
+    appConfig:
       # -- Interval in seconds between complete test cycles (i.e., testing all server nodes).
       testInterval: 300
-
+      # -- Log level for the iperf3 exporter (e.g., DEBUG, INFO, WARNING, ERROR, CRITICAL).
+      logLevel: INFO
       # -- Timeout in seconds for a single iperf3 test run.
       testTimeout: 10
-
       # -- Protocol to use for testing (tcp or udp).
       testProtocol: tcp
+      # -- iperf3 server port to connect to. Should match the server's listening port.
+      serverPort: "5201"
+      # -- Label selector to find iperf3 server pods.
+      # This is templated. Default: 'app.kubernetes.io/name=<chart-name>,app.kubernetes.io/instance=<release-name>,app.kubernetes.io/component=server'
+      serverLabelSelector: 'app.kubernetes.io/name={{ include "iperf3-monitor.name" . }},app.kubernetes.io/instance={{ .Release.Name }},app.kubernetes.io/component=server'
 
-  # -- CPU and memory resource requests and limits for the exporter pod.
+    # -- Pod-level configurations for the exporter.
-  # @default -- A small default is provided if commented out.
+    pod:
-  resources: {}
+      # -- Annotations for the exporter pod.
+      annotations: {}
+      # -- Labels for the exporter pod (the common library adds its own defaults too).
+      labels: {}
+      # -- Node selector for scheduling exporter pods. Useful for DaemonSet or specific scheduling with Deployments.
+      # Example:
+      # nodeSelector:
+      #   kubernetes.io/os: linux
+      nodeSelector: {}
+      # -- Tolerations for scheduling exporter pods.
+      # Example:
+      # tolerations:
+      # - key: "node-role.kubernetes.io/control-plane"
+      #   operator: "Exists"
+      #   effect: "NoSchedule"
+      tolerations: []
+      # -- Affinity rules for scheduling exporter pods.
+      # Example:
+      # affinity:
+      #   nodeAffinity:
+      #     requiredDuringSchedulingIgnoredDuringExecution:
+      #       nodeSelectorTerms:
+      #       - matchExpressions:
+      #         - key: "kubernetes.io/arch"
+      #           operator: In
+      #           values:
+      #           - amd64
+      affinity: {}
+      # -- Security context for the exporter pod.
+      # securityContext:
+      #   fsGroup: 65534
+      #   runAsUser: 65534
+      #   runAsGroup: 65534
+      #   runAsNonRoot: true
+      securityContext: {}
+      # -- Automount service account token for the pod.
+      automountServiceAccountToken: true
+
+    # -- Container-level configurations for the main exporter container.
+    containers:
+      exporter: # Name of the primary container
+        image:
+          repository: ghcr.io/malarinv/iperf3-monitor
+          tag: "" # Defaults to .Chart.AppVersion
+          pullPolicy: IfNotPresent
+        # -- Custom environment variables for the exporter container.
+        # These are merged with the ones generated from appConfig.
+        # env:
+        #   MY_CUSTOM_VAR: "my_value"
+        env: {}
+        # -- Ports for the exporter container.
+        ports:
+          metrics: # Name of the port
+            port: 9876 # Container port for metrics
+            protocol: TCP
+            enabled: true
+        # -- CPU and memory resource requests and limits.
+        # resources:
         #   requests:
         #     cpu: "100m"
         #     memory: "128Mi"
         #   limits:
         #     cpu: "500m"
         #     memory: "256Mi"
+        resources: {}
+        # -- Probes configuration for the exporter container.
+        # probes:
+        #   liveness:
+        #     enabled: true # Example: enable liveness probe
+        #     spec: # Customize probe spec if needed
+        #       initialDelaySeconds: 30
+        #       periodSeconds: 15
+        #       timeoutSeconds: 5
+        #       failureThreshold: 3
+        probes:
+          liveness:
+            enabled: false
+          readiness:
+            enabled: false
+          startup:
+            enabled: false
 
 server:
   # -- Configuration for the iperf3 server container image (DaemonSet).

charts/iperf3-monitor/Chart.lock

@@ -1,6 +1,12 @@
 dependencies:
 - name: kube-prometheus-stack
   repository: https://prometheus-community.github.io/helm-charts
-  version: 75.3.6
+  version: 75.7.0
-digest: sha256:d15acd48bfc0b842654ae025e1bd1969e636a66508020312d555db84f381c379
+- name: prometheus-operator
-generated: "2025-06-19T20:40:53.415529365Z"
+  repository: oci://tccr.io/truecharts
+  version: 11.5.1
+- name: common
+  repository: https://bjw-s-labs.github.io/helm-charts/
+  version: 4.1.2
+digest: sha256:68485b4e158a6a405073e9c59966d251b62971846cdc9871e41fde46f19aabfe
+generated: "2025-07-01T20:32:00.061995907Z"

charts/iperf3-monitor/Chart.yaml

@@ -27,4 +27,11 @@ dependencies:
   - name: kube-prometheus-stack # Example dependency if you package the whole stack
     version: ">=30.0.0" # Specify a compatible version range
     repository: https://prometheus-community.github.io/helm-charts
-    condition: serviceMonitor.enabled # Only include if ServiceMonitor is enabled (assuming Prometheus Operator)
+    condition: "dependencies.install, serviceMonitor.enabled, !dependencies.useTrueChartsPrometheusOperator"
+  - name: prometheus-operator
+    version: ">=8.11.1"
+    repository: "oci://tccr.io/truecharts"
+    condition: "dependencies.install, serviceMonitor.enabled, dependencies.useTrueChartsPrometheusOperator"
+  - name: common
+    version: "4.1.2"
+    repository: "https://bjw-s-labs.github.io/helm-charts/"

charts/iperf3-monitor/grafana/iperf3-dashboard.json

@@ -0,0 +1,194 @@
+{
+"__inputs": [],
+"__requires": [
+{
+"type": "grafana",
+"id": "grafana",
+"name": "Grafana",
+"version": "8.0.0"
+},
+{
+"type": "datasource",
+"id": "prometheus",
+"name": "Prometheus",
+"version": "1.0.0"
+}
+],
+"annotations": {
+"list": [
+{
+"builtIn": 1,
+"datasource": {
+"type": "grafana",
+"uid": "-- Grafana --"
+},
+"enable": true,
+"hide": true,
+"iconColor": "rgba(0, 211, 255, 1)",
+"name": "Annotations & Alerts",
+"type": "dashboard"
+}
+]
+},
+"editable": true,
+"fiscalYearStartMonth": 0,
+"gnetId": null,
+"graphTooltip": 0,
+"id": null,
+"links": [],
+"panels": [
+{
+"datasource": {
+"type": "prometheus",
+"uid": "prometheus"
+},
+"gridPos": {
+"h": 9,
+"w": 24,
+"x": 0,
+"y": 0
+},
+"id": 2,
+"targets": [
+{
+"expr": "avg(iperf_network_bandwidth_mbps) by (source_node, destination_node)",
+"format": "heatmap",
+"legendFormat": "{{source_node}} -> {{destination_node}}",
+"refId": "A"
+}
+],
+"cards": { "cardPadding": null, "cardRound": null },
+"color": {
+"mode": "spectrum",
+"scheme": "red-yellow-green",
+"exponent": 0.5,
+"reverse": false
+},
+"dataFormat": "tsbuckets",
+"yAxis": { "show": true, "format": "short" },
+"xAxis": { "show": true }
+},
+{
+"title": "Bandwidth Over Time (Source: $source_node, Dest: $destination_node)",
+"type": "timeseries",
+"datasource": {
+"type": "prometheus",
+"uid": "prometheus"
+},
+"gridPos": {
+"h": 8,
+"w": 12,
+"x": 0,
+"y": 9
+},
+"targets": [
+{
+"expr": "iperf_network_bandwidth_mbps{source_node=~\"^$source_node$\", destination_node=~\"^$destination_node$\", protocol=~\"^$protocol$\"}",
+"legendFormat": "Bandwidth",
+"refId": "A"
+}
+],
+"fieldConfig": {
+"defaults": {
+"unit": "mbps"
+}
+}
+},
+{
+"title": "Jitter Over Time (Source: $source_node, Dest: $destination_node)",
+"type": "timeseries",
+"datasource": {
+"type": "prometheus",
+"uid": "prometheus"
+},
+"gridPos": {
+"h": 8,
+"w": 12,
+"x": 12,
+"y": 9
+},
+"targets": [
+{
+"expr": "iperf_network_jitter_ms{source_node=~\"^$source_node$\", destination_node=~\"^$destination_node$\", protocol=\"udp\"}",
+"legendFormat": "Jitter",
+"refId": "A"
+}
+],
+"fieldConfig": {
+"defaults": {
+"unit": "ms"
+}
+}
+}
+],
+"refresh": "30s",
+"schemaVersion": 36,
+"style": "dark",
+"tags": ["iperf3", "network", "kubernetes"],
+"templating": {
+"list": [
+{
+"current": {},
+"datasource": {
+"type": "prometheus",
+"uid": "prometheus"
+},
+"definition": "label_values(iperf_network_bandwidth_mbps, source_node)",
+"hide": 0,
+"includeAll": false,
+"multi": false,
+"name": "source_node",
+"options": [],
+"query": "label_values(iperf_network_bandwidth_mbps, source_node)",
+"refresh": 1,
+"regex": "",
+"skipUrlSync": false,
+"sort": 1,
+"type": "query"
+},
+{
+"current": {},
+"datasource": {
+"type": "prometheus",
+"uid": "prometheus"
+},
+"definition": "label_values(iperf_network_bandwidth_mbps{source_node=~\"^$source_node$\"}, destination_node)",
+"hide": 0,
+"includeAll": false,
+"multi": false,
+"name": "destination_node",
+"options": [],
+"query": "label_values(iperf_network_bandwidth_mbps{source_node=~\"^$source_node$\"}, destination_node)",
+"refresh": 1,
+"regex": "",
+"skipUrlSync": false,
+"sort": 1,
+"type": "query"
+},
+{
+"current": { "selected": true, "text": "tcp", "value": "tcp" },
+"hide": 0,
+"includeAll": false,
+"multi": false,
+"name": "protocol",
+"options": [
+{ "selected": true, "text": "tcp", "value": "tcp" },
+{ "selected": false, "text": "udp", "value": "udp" }
+],
+"query": "tcp,udp",
+"skipUrlSync": false,
+"type": "custom"
+}
+]
+},
+"time": {
+"from": "now-1h",
+"to": "now"
+},
+"timepicker": {},
+"timezone": "browser",
+"title": "Kubernetes iperf3 Network Performance",
+"uid": "k8s-iperf3-dashboard",
+"version": 1,
+"weekStart": ""
+}

charts/iperf3-monitor/templates/_helpers.tpl

@@ -47,7 +47,7 @@ app.kubernetes.io/instance: {{ .Release.Name }}
 Create the name of the service account to use
 */}}
 {{- define "iperf3-monitor.serviceAccountName" -}}
-{{- if .Values.serviceAccount.create -}}
+{{- if .Values.rbac.create -}}
     {{- default (include "iperf3-monitor.fullname" .) .Values.serviceAccount.name -}}
 {{- else -}}
     {{- default "default" .Values.serviceAccount.name -}}

charts/iperf3-monitor/templates/exporter-controller.yaml

@@ -0,0 +1,140 @@
+{{- /*
+This template is responsible for rendering the 'exporter' controller (Deployment or DaemonSet)
+by calling the bjw-s common library.
+
+The primary values for the exporter are expected under .Values.controllers.exporter.
+Modifications to environment variables and service account are handled here before
+passing the configuration to the common library.
+*/}}
+
+{{- /*
+Prepare a local, modifiable copy of the .Values. This allows us to adjust the
+exporter controller's configuration (like env vars and SA) specifically for this chart's needs
+before the common library processes it.
+Convert to map[string]interface{} via toYaml/fromYaml to ensure compatibility with 'dig'.
+*/}}
+{{- $localValues := .Values | toYaml | fromYaml | deepCopy -}}
+{{- $chart := .Chart -}}
+{{- $release := .Release -}}
+{{- $appName := include "iperf3-monitor.name" . -}}
+{{- $fullName := include "iperf3-monitor.fullname" . -}}
+
+{{- /*
+Define the key for the exporter controller, typically "exporter" as per our values.yaml.
+*/}}
+{{- $exporterControllerKey := "exporter" -}}
+
+{{- /*
+Attempt to get the exporter controller's configuration block.
+Proceed with modifications only if the exporter controller is defined.
+*/}}
+{{- $exporterControllerConfig := get $localValues.controllers $exporterControllerKey -}}
+{{- if $exporterControllerConfig -}}
+
+  {{- /*
+  Construct the base set of environment variables required by the iperf3-exporter application.
+  These are derived from the 'appConfig' section of the exporter's controller configuration.
+  */}}
+  {{- $baseExporterEnv := dict -}}
+  {{- if $exporterControllerConfig.appConfig -}}
+    {{- $_ := set $baseExporterEnv "SOURCE_NODE_NAME" (dict "valueFrom" (dict "fieldRef" (dict "fieldPath" "spec.nodeName"))) -}}
+    {{- $_ := set $baseExporterEnv "IPERF_TEST_INTERVAL" ($exporterControllerConfig.appConfig.testInterval | default "300" | toString) -}}
+    {{- $_ := set $baseExporterEnv "IPERF_TEST_PROTOCOL" ($exporterControllerConfig.appConfig.testProtocol | default "tcp") -}}
+    {{- $_ := set $baseExporterEnv "LOG_LEVEL" ($exporterControllerConfig.appConfig.logLevel | default "INFO") -}}
+    {{- $_ := set $baseExporterEnv "IPERF_SERVER_PORT" ($exporterControllerConfig.appConfig.serverPort | default "5201" | toString) -}}
+    {{- $_ := set $baseExporterEnv "IPERF_SERVER_NAMESPACE" (dict "valueFrom" (dict "fieldRef" (dict "fieldPath" "metadata.namespace"))) -}}
+    {{- $_ := set $baseExporterEnv "IPERF_TEST_TIMEOUT" ($exporterControllerConfig.appConfig.testTimeout | default "10" | toString) -}}
+    {{- $serverLabelSelectorDefault := printf "app.kubernetes.io/name=%s,app.kubernetes.io/instance=%s,app.kubernetes.io/component=server" $appName $release.Name -}}
+    {{- $serverLabelSelector := tpl ($exporterControllerConfig.appConfig.serverLabelSelector | default $serverLabelSelectorDefault) . -}}
+    {{- $_ := set $baseExporterEnv "IPERF_SERVER_LABEL_SELECTOR" $serverLabelSelector -}}
+  {{- end -}}
+
+  {{- /*
+  Merge the base environment variables with any user-defined environment variables.
+  User-defined variables (from .Values.controllers.exporter.containers.exporter.env)
+  will take precedence in case of conflicting keys.
+  */}}
+  {{- $userExporterEnv := $exporterControllerConfig.containers.exporter.env | default dict -}}
+  {{- $finalExporterEnv := mergeOverwrite $baseExporterEnv $userExporterEnv -}}
+
+  {{- /*
+  Ensure the container structure exists and update its 'env' field with the final set.
+  The common library expects this under controllers.<key>.containers.<containerName>.env
+  */}}
+  {{- if not $exporterControllerConfig.containers -}}
+    {{- $_ := set $exporterControllerConfig "containers" dict -}}
+  {{- end -}}
+  {{- if not $exporterControllerConfig.containers.exporter -}}
+    {{- $_ := set $exporterControllerConfig.containers "exporter" dict -}}
+  {{- end -}}
+  {{- $_ := set $exporterControllerConfig.containers.exporter "env" $finalExporterEnv -}}
+
+  {{- /*
+  Ensure the container image tag is set, defaulting to Chart.AppVersion if empty,
+  as the common library validation requires it during 'helm template'.
+
+  NOTE: BJW-S common library typically handles defaulting image.tag to Chart.appVersion
+  if image.tag is empty or null in values. The custom logic below prepending "v"
+  is specific to this chart and might be redundant if the common library's default
+  is preferred. For now, we keep it as it was the reason for previous errors if tag was not set.
+  However, if common library handles it, this block could be removed and image.tag in values.yaml set to "" or null.
+  Forcing the tag to be set (even if to chart.appVersion) ensures the common library doesn't complain.
+  The issue encountered during `helm template` earlier (empty output) was resolved by
+  explicitly setting the tag (e.g. via --set or by ensuring values.yaml has it).
+  The common library's internal validation likely needs *a* tag to be present in the values passed to it,
+  even if that tag is derived from AppVersion. This block ensures that.
+  */}}
+  {{- $exporterContainerCfg := get $exporterControllerConfig.containers "exporter" -}}
+  {{- if $exporterContainerCfg -}}
+    {{- if not $exporterContainerCfg.image.tag -}}
+      {{- if $chart.AppVersion -}}
+        {{- $_ := set $exporterContainerCfg.image "tag" (printf "%s" $chart.AppVersion) -}} # Removed "v" prefix
+      {{- else -}}
+        {{- fail (printf "Error: Container image tag is not specified for controller '%s', container '%s', and Chart.AppVersion is also empty." $exporterControllerKey "exporter") -}}
+      {{- end -}}
+    {{- end -}}
+  {{- end -}}
+
+  {{- /*
+  Configure the Service Account for the exporter controller.
+  This ensures the controller pod uses the ServiceAccount that is intended by this chart's
+  RBAC configuration (.Values.rbac.create and .Values.serviceAccount.name).
+  */}}
+  {{- $serviceAccountNameFromValues := $localValues.serviceAccount.name | default (printf "%s-exporter" $fullName) -}}
+  {{- if not $exporterControllerConfig.serviceAccount -}}
+    {{- $_ := set $exporterControllerConfig "serviceAccount" dict -}}
+  {{- end -}}
+  {{- $_ := set $exporterControllerConfig.serviceAccount "name" $serviceAccountNameFromValues -}}
+  {{- $_ := set $exporterControllerConfig.serviceAccount "create" $localValues.rbac.create -}}
+  {{- $_ := set $exporterControllerConfig.serviceAccount "automountServiceAccountToken" ($exporterControllerConfig.pod.automountServiceAccountToken | default true) -}}
+
+  {{- /*
+  Replace the original exporter controller config in our $localValues copy
+  with the modified version (that now includes the correct env and SA settings).
+  */}}
+  {{- $_ := set $localValues.controllers $exporterControllerKey $exporterControllerConfig -}}
+{{- end -}}
+
+{{- /*
+Ensure .Values.global exists and is a map, as the common library expects it.
+*/}}
+{{- if not (get $localValues "global") -}}
+  {{- $_ := set $localValues "global" dict -}}
+{{- else if not (kindIs "map" (get $localValues "global")) -}}
+  {{- $_ := set $localValues "global" dict -}}
+{{- end -}}
+
+{{- /*
+Ensure defaultPodOptionsStrategy exists, as common lib expects it at the root of Values.
+*/}}
+{{- if not (get $localValues "defaultPodOptionsStrategy") -}}
+  {{- $_ := set $localValues "defaultPodOptionsStrategy" "overwrite" -}}
+{{- end -}}
+
+{{- /*
+Call the common library's main render function for controllers.
+This function iterates through all controllers defined under $localValues.controllers
+(in our case, just "exporter") and renders them using their specified type and configuration.
+The context passed must mirror the global Helm context, including 'Values', 'Chart', 'Release', 'Capabilities', and 'Template'.
+*/}}
+{{- include "bjw-s.common.render.controllers" (dict "Values" $localValues "Chart" $chart "Release" $release "Capabilities" .Capabilities "Template" .Template) | nindent 0 -}}

charts/iperf3-monitor/templates/exporter-deployment.yaml

@@ -1,48 +0,0 @@
-apiVersion: apps/v1
-kind: Deployment
-metadata:
-  name: {{ include "iperf3-monitor.fullname" . }}-exporter
-  labels:
-    {{- include "iperf3-monitor.labels" . | nindent 4 }}
-    app.kubernetes.io/component: exporter
-spec:
-  replicas: {{ .Values.exporter.replicaCount }}
-  selector:
-    matchLabels:
-      {{- include "iperf3-monitor.selectorLabels" . | nindent 6 }}
-      app.kubernetes.io/component: exporter
-  template:
-    metadata:
-      labels:
-        {{- include "iperf3-monitor.selectorLabels" . | nindent 8 }}
-        app.kubernetes.io/component: exporter
-    spec:
-      serviceAccountName: {{ include "iperf3-monitor.serviceAccountName" . }}
-      containers:
-      - name: iperf3-exporter
-        image: "{{ .Values.exporter.image.repository }}:{{ .Values.exporter.image.tag | default .Chart.AppVersion }}"
-        imagePullPolicy: {{ .Values.exporter.image.pullPolicy }}
-        ports:
-        - containerPort: {{ .Values.service.targetPort }}
-          name: metrics
-        env:
-        - name: SOURCE_NODE_NAME
-          valueFrom:
-            fieldRef:
-              fieldPath: spec.nodeName
-        - name: IPERF_TEST_INTERVAL
-          value: "{{ .Values.exporter.testInterval }}"
-        - name: IPERF_TEST_PROTOCOL
-          value: "{{ .Values.exporter.testProtocol }}"
-        - name: IPERF_SERVER_PORT
-          value: "5201" # Hardcoded as per server DaemonSet
-        - name: IPERF_SERVER_NAMESPACE
-          valueFrom:
-            fieldRef:
-              fieldPath: metadata.namespace
-        - name: IPERF_SERVER_LABEL_SELECTOR
-          value: 'app.kubernetes.io/name={{ include "iperf3-monitor.name" . }},app.kubernetes.io/instance={{ .Release.Name }},app.kubernetes.io/component=server'
-        {{- with .Values.exporter.resources }}
-        resources:
-          {{- toYaml . | nindent 10 }}
-        {{- end }}

charts/iperf3-monitor/templates/grafana-dashboard-configmap.yaml

@@ -0,0 +1,13 @@
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: {{ .Release.Name }}-grafana-dashboard
+  labels:
+    grafana_dashboard: "1"
+    app.kubernetes.io/name: {{ include "iperf3-monitor.name" . }}
+    helm.sh/chart: {{ .Chart.Name }}-{{ .Chart.Version | replace "+" "_" }}
+    app.kubernetes.io/instance: {{ .Release.Name }}
+    app.kubernetes.io/managed-by: {{ .Release.Service }}
+data:
+  iperf3-dashboard.json: |
+    {{ .Files.Get "grafana/iperf3-dashboard.json" | nindent 4 }}

charts/iperf3-monitor/templates/rbac.yaml

@@ -7,9 +7,10 @@ metadata:
     {{- include "iperf3-monitor.labels" . | nindent 4 }}
 ---
 apiVersion: rbac.authorization.k8s.io/v1
-kind: ClusterRole
+kind: Role
 metadata:
   name: {{ include "iperf3-monitor.fullname" . }}-role
+  namespace: {{ .Release.Namespace }}
   labels:
     {{- include "iperf3-monitor.labels" . | nindent 4 }}
 rules:
@@ -18,9 +19,10 @@ rules:
     verbs: ["get", "list", "watch"]
 ---
 apiVersion: rbac.authorization.k8s.io/v1
-kind: ClusterRoleBinding
+kind: RoleBinding
 metadata:
   name: {{ include "iperf3-monitor.fullname" . }}-rb
+  namespace: {{ .Release.Namespace }}
   labels:
     {{- include "iperf3-monitor.labels" . | nindent 4 }}
 subjects:
@@ -28,7 +30,7 @@ subjects:
     name: {{ include "iperf3-monitor.serviceAccountName" . }}
     namespace: {{ .Release.Namespace }}
 roleRef:
-  kind: ClusterRole
+  kind: Role # Changed from ClusterRole
   name: {{ include "iperf3-monitor.fullname" . }}-role
   apiGroup: rbac.authorization.k8s.io
 {{- end -}}

charts/iperf3-monitor/templates/service.yaml

@@ -11,7 +11,7 @@ spec:
     {{- include "iperf3-monitor.selectorLabels" . | nindent 4 }}
     app.kubernetes.io/component: exporter
   ports:
-    - name: metrics
+    - name: metrics # Assuming 'metrics' is the intended name, aligns with values structure
-      port: {{ .Values.service.port }}
+      port: {{ .Values.service.main.ports.metrics.port }}
-      targetPort: {{ .Values.service.targetPort }}
+      targetPort: {{ .Values.service.main.ports.metrics.targetPort }}
-      protocol: TCP
+      protocol: {{ .Values.service.main.ports.metrics.protocol | default "TCP" }}

charts/iperf3-monitor/values.yaml

@@ -8,30 +8,96 @@ nameOverride: ""
 # -- Override the fully qualified app name.
 fullnameOverride: ""
 
+controllers:
   exporter:
-  # -- Configuration for the exporter container image.
+    # -- Enable the exporter controller.
+    enabled: true
+    # -- Set the controller type for the exporter.
+    # Valid options are "deployment" or "daemonset".
+    # @default -- "deployment"
+    type: deployment
+    # -- Number of desired exporter pods. Only used if type is "deployment".
+    # @default -- 1
+    replicas: 1
+
+    # -- Application-specific configuration for the iperf3 exporter.
+    # These values are used to populate environment variables for the exporter container.
+    appConfig:
+      # -- Interval in seconds between complete test cycles (i.e., testing all server nodes).
+      testInterval: 300
+      # -- Log level for the iperf3 exporter (e.g., DEBUG, INFO, WARNING, ERROR, CRITICAL).
+      logLevel: INFO
+      # -- Timeout in seconds for a single iperf3 test run.
+      testTimeout: 10
+      # -- Protocol to use for testing (tcp or udp).
+      testProtocol: tcp
+      # -- iperf3 server port to connect to. Should match the server's listening port.
+      # @default -- "5201" (hardcoded in the original chart for server daemonset)
+      serverPort: "5201"
+      # -- Label selector to find iperf3 server pods.
+      # This will be templated in the actual deployment.
+      # Example default (if not overridden by template logic): 'app.kubernetes.io/component=server'
+      serverLabelSelector: 'app.kubernetes.io/name={{ include "iperf3-monitor.name" . }},app.kubernetes.io/instance={{ .Release.Name }},app.kubernetes.io/component=server'
+
+
+    # -- Pod-level configurations for the exporter, leveraging bjw-s common library structure.
+    pod:
+      # -- Annotations for the exporter pod.
+      annotations: {}
+      # -- Labels for the exporter pod.
+      labels:
+        app.kubernetes.io/component: exporter # Ensure pods get the component label for service selection
+      # -- Node selector for scheduling exporter pods.
+      nodeSelector: {}
+      # -- Tolerations for scheduling exporter pods.
+      tolerations: []
+      # -- Affinity rules for scheduling exporter pods.
+      affinity: {}
+      # -- Security context for the exporter pod.
+      securityContext: {}
+        # fsGroup: 65534
+        # runAsUser: 65534
+        # runAsGroup: 65534
+        # runAsNonRoot: true
+      # -- Automount service account token for the pod.
+      automountServiceAccountToken: true # Default from common lib
+
+    # -- Container-level configurations for the main exporter container.
+    containers:
+      exporter: # This is the primary container, name it 'exporter'
         image:
           # -- The container image repository for the exporter.
           repository: ghcr.io/malarinv/iperf3-monitor
           # -- The container image tag for the exporter. If not set, the chart's appVersion is used.
-    tag: ""
+          tag: "" # Defaults to .Chart.AppVersion via common library
           # -- The image pull policy for the exporter container.
           pullPolicy: IfNotPresent
 
-  # -- Number of exporter pod replicas. Typically 1 is sufficient.
+        # -- Environment variables for the exporter container.
-  replicaCount: 1
+        # The actual env map will be constructed in the main chart template
+        # and passed to the common library. This section is for user overrides
+        # if they want to directly set other env vars using common lib's env schema.
+        env: {}
+          # Example:
+          # MY_CUSTOM_VAR: "my_value"
+          # ANOTHER_VAR:
+          #   valueFrom:
+          #     secretKeyRef:
+          #       name: mysecret
+          #       key: mykey
 
-  # -- Interval in seconds between complete test cycles (i.e., testing all server nodes).
+        # -- Ports for the exporter container.
-  testInterval: 300
+        # Expected by Kubernetes and bjw-s common library as a list of objects.
+        ports:
+          - name: metrics # Name of the port, referenced by Service's targetPort
+            # -- Port number for the metrics endpoint on the container.
+            containerPort: 9876
+            # -- Protocol for the metrics port.
+            protocol: TCP
+            # -- Whether this port definition is enabled. Specific to bjw-s common library.
+            enabled: true
 
-  # -- Timeout in seconds for a single iperf3 test run.
+        # -- CPU and memory resource requests and limits for the exporter container.
-  testTimeout: 10
-
-  # -- Protocol to use for testing (tcp or udp).
-  testProtocol: tcp
-
-  # -- CPU and memory resource requests and limits for the exporter pod.
-  # @default -- A small default is provided if commented out.
         resources:
           {}
           # requests:
@@ -41,6 +107,16 @@ exporter:
           #   cpu: "500m"
           #   memory: "256Mi"
 
+        # -- Probes configuration for the exporter container.
+        probes:
+          liveness:
+            enabled: false
+          readiness:
+            enabled: false
+          startup:
+            enabled: false
+
+# Server configuration (iperf3 server daemonset)
 server:
   # -- Configuration for the iperf3 server container image (DaemonSet).
   image:
@@ -50,8 +126,6 @@ server:
     tag: latest
 
   # -- CPU and memory resource requests and limits for the iperf3 server pods (DaemonSet).
-  # These should be very low as the server is mostly idle.
-  # @default -- A small default is provided if commented out.
   resources:
     {}
     # requests:
@@ -62,13 +136,9 @@ server:
     #   memory: "128Mi"
 
   # -- Node selector for scheduling iperf3 server pods.
-  # Use this to restrict the DaemonSet to a subset of nodes.
-  # @default -- {} (schedule on all nodes)
   nodeSelector: {}
 
-  # -- Tolerations for scheduling iperf3 server pods on tainted nodes (e.g., control-plane nodes).
+  # -- Tolerations for scheduling iperf3 server pods on tainted nodes.
-  # This is often necessary to include master nodes in the test mesh.
-  # @default -- Tolerates control-plane and master taints.
   tolerations:
     - key: "node-role.kubernetes.io/control-plane"
       operator: "Exists"
@@ -77,44 +147,62 @@ server:
       operator: "Exists"
       effect: "NoSchedule"
 
+# RBAC and ServiceAccount settings
+# These are for the exporter. The exporter deployment (managed by common library)
+# will need to use the ServiceAccount specified here or one created by the library.
 rbac:
   # -- If true, create ServiceAccount, ClusterRole, and ClusterRoleBinding for the exporter.
-  # Set to false if you manage RBAC externally.
   create: true
 
 serviceAccount:
-  # -- The name of the ServiceAccount to use for the exporter pod.
+  # -- The name of the ServiceAccount to use/create for the exporter pod.
-  # Only used if rbac.create is false. If not set, it defaults to the chart's fullname.
+  # If rbac.create is true, this SA is created. The exporter pod must use this SA.
-  name: ""
+  name: "iperf3-monitor"
 
+# Service Monitor configuration for Prometheus
 serviceMonitor:
-  # -- If true, create a ServiceMonitor resource for integration with Prometheus Operator.
+  # -- If true, create a ServiceMonitor resource.
-  # Requires a running Prometheus Operator in the cluster.
   enabled: true
-
+  # -- Scrape interval for the ServiceMonitor.
-  # -- Scrape interval for the ServiceMonitor. How often Prometheus scrapes the exporter metrics.
   interval: 60s
-
+  # -- Scrape timeout for the ServiceMonitor.
-  # -- Scrape timeout for the ServiceMonitor. How long Prometheus waits for metrics response.
   scrapeTimeout: 30s
 
-# -- Configuration for the exporter Service.
+# Service configuration for the exporter
+# This defines how the exporter is exposed.
+# The common library can also manage services, or we can use our own template.
+# This structure is compatible with bjw-s common library's service management if we choose to use it.
 service:
-  # -- Service type. ClusterIP is typically sufficient.
+  main: # A key for the service, 'main' is a common convention.
-  type: ClusterIP
+    # -- Enable the exporter service.
-  # -- Port on which the exporter service is exposed.
+    enabled: true
+    # -- Service type.
+    type: ClusterIP # ClusterIP is typical for internal services scraped by Prometheus.
+    # -- Ports configuration for the service.
+    ports:
+      metrics: # Name of the service port, should align with a container port name.
+        # -- Port number on which the service is exposed.
         port: 9876
-  # -- Target port on the exporter pod.
+        # -- Target port on the exporter pod. Can be a number or name.
-  targetPort: 9876
+        # Refers to the 'metrics' port defined in controllers.exporter.containers.exporter.ports.
+        targetPort: metrics
+        protocol: TCP
 
-# -- Optional configuration for a network policy to allow traffic to the iperf3 server DaemonSet.
+# Network Policy (optional)
-# This is often necessary if you are using a network policy controller.
 networkPolicy:
   # -- If true, create a NetworkPolicy resource.
   enabled: false
-  # -- Specify source selectors if needed (e.g., pods in a specific namespace).
+  # -- Source selectors for ingress rules.
   from: []
-  # -- Specify namespace selectors if needed.
+  # -- Namespace selectors for ingress rules.
   namespaceSelector: {}
-  # -- Specify pod selectors if needed.
+  # -- Pod selectors for ingress rules.
   podSelector: {}
+
+# Dependency Configuration (for Prometheus Operator)
+dependencies:
+  # -- Set to false by default. Set to true to install a Prometheus operator dependency (used if serviceMonitor.enabled=true).
+  # -- If false (default), and serviceMonitor.enabled is true, you must have a compatible Prometheus Operator already running in your cluster.
+  install: false
+  # -- If true, use TrueCharts Prometheus Operator instead of kube-prometheus-stack (used if dependencies.install is true).
+  useTrueChartsPrometheusOperator: false

exporter/Dockerfile

@@ -1,11 +1,15 @@
 # Stage 1: Build stage with dependencies
 FROM python:3.9-slim as builder
 
+# Declare TARGETARCH for use in this stage
+ARG TARGETARCH
 WORKDIR /app
 
-# Install iperf3 and build dependencies
+# Minimal dependencies for builder stage if any Python packages had C extensions.
+# Assuming requirements.txt does not need gcc or other build tools for now.
+# If pip install fails later, add necessary build tools (e.g., gcc, python3-dev) here.
 RUN apt-get update && \
-    apt-get install -y --no-install-recommends gcc iperf3 libiperf-dev && \
+    # apt-get install -y --no-install-recommends gcc python3-dev # Example if needed
     rm -rf /var/lib/apt/lists/*
 
 # Install Python dependencies
@@ -17,9 +21,11 @@ FROM python:3.9-slim
 
 WORKDIR /app
 
-# Copy iperf3 binary and library from the builder stage
+# Install iperf3 and its runtime dependency libsctp1 directly in the final stage.
-COPY --from=builder /usr/bin/iperf3 /usr/bin/iperf3
+# This simplifies the Dockerfile by removing the need to copy iperf3 components from the builder.
-COPY --from=builder /usr/lib/x86_64-linux-gnu/libiperf.so.0 /usr/lib/x86_64-linux-gnu/libiperf.so.0
+RUN apt-get update && \
+    apt-get install -y --no-install-recommends iperf3 libsctp1 && \
+    rm -rf /var/lib/apt/lists/*
 
 # Copy installed Python packages from the builder stage
 COPY --from=builder /usr/local/lib/python3.9/site-packages /usr/local/lib/python3.9/site-packages

exporter/exporter.py

@@ -1,28 +1,60 @@
+"""
+Prometheus exporter for iperf3 network performance monitoring.
+
+This script runs iperf3 tests between the node it's running on (source) and
+other iperf3 server pods discovered in a Kubernetes cluster. It then exposes
+these metrics for Prometheus consumption.
+
+Configuration is primarily through environment variables and command-line arguments
+for log level.
+"""
 import os
 import time
 import logging
+import argparse
+import sys
 from kubernetes import client, config
 from prometheus_client import start_http_server, Gauge
 import iperf3
 
-# --- Configuration ---
+# --- Global Configuration & Setup ---
-# Configure logging
+
-logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')
+# Argument parsing for log level configuration
+# The command-line --log-level argument takes precedence over the LOG_LEVEL env var.
+# Defaults to INFO if neither is set.
+parser = argparse.ArgumentParser(description="iperf3 Prometheus exporter.")
+parser.add_argument(
+    '--log-level',
+    default=os.environ.get('LOG_LEVEL', 'INFO').upper(),
+    choices=['DEBUG', 'INFO', 'WARNING', 'ERROR', 'CRITICAL'],
+    help='Set the logging level. Overrides LOG_LEVEL environment variable. (Default: INFO)'
+)
+args = parser.parse_args()
+log_level_str = args.log_level
+
+# Convert log level string (e.g., 'INFO') to its numeric representation (e.g., logging.INFO)
+numeric_level = getattr(logging, log_level_str.upper(), None)
+if not isinstance(numeric_level, int):
+    # This case should ideally not be reached if choices in argparse are respected.
+    logging.error(f"Invalid log level: {log_level_str}. Defaulting to INFO.")
+    numeric_level = logging.INFO
+logging.basicConfig(level=numeric_level, format='%(asctime)s - %(levelname)s - %(message)s')
 
 # --- Prometheus Metrics Definition ---
+# These gauges will be used to expose iperf3 test results.
 IPERF_BANDWIDTH_MBPS = Gauge(
     'iperf_network_bandwidth_mbps',
-    'Network bandwidth measured by iperf3 in Megabits per second',
+    'Network bandwidth measured by iperf3 in Megabits per second (Mbps)',
     ['source_node', 'destination_node', 'protocol']
 )
 IPERF_JITTER_MS = Gauge(
     'iperf_network_jitter_ms',
-    'Network jitter measured by iperf3 in milliseconds',
+    'Network jitter measured by iperf3 in milliseconds (ms) for UDP tests',
     ['source_node', 'destination_node', 'protocol']
 )
 IPERF_PACKETS_TOTAL = Gauge(
     'iperf_network_packets_total',
-    'Total packets transmitted or received during the iperf3 test',
+    'Total packets transmitted/received during the iperf3 UDP test',
     ['source_node', 'destination_node', 'protocol']
 )
 IPERF_LOST_PACKETS = Gauge(
@@ -38,12 +70,21 @@ IPERF_TEST_SUCCESS = Gauge(
 
 def discover_iperf_servers():
     """
-    Discover iperf3 server pods in the cluster using the Kubernetes API.
+    Discovers iperf3 server pods within a Kubernetes cluster.
+
+    It uses the in-cluster Kubernetes configuration to connect to the API.
+    The target namespace and label selector for iperf3 server pods are configured
+    via environment variables:
+    - IPERF_SERVER_NAMESPACE (default: 'default')
+    - IPERF_SERVER_LABEL_SELECTOR (default: 'app=iperf3-server')
+
+    Returns:
+        list: A list of dictionaries, where each dictionary contains the 'ip'
+              and 'node_name' of a discovered iperf3 server pod. Returns an
+              empty list if discovery fails or no servers are found.
     """
     try:
-        # Load in-cluster configuration
+        config.load_incluster_config() # Assumes running inside a Kubernetes pod
-        # Assumes the exporter runs in a pod with a service account having permissions
-        config.load_incluster_config()
         v1 = client.CoreV1Api()
 
         namespace = os.getenv('IPERF_SERVER_NAMESPACE', 'default')
@@ -51,110 +92,208 @@ def discover_iperf_servers():
 
         logging.info(f"Discovering iperf3 servers with label '{label_selector}' in namespace '{namespace}'")
 
-        # List pods across all namespaces with the specified label selector
+        # Use list_namespaced_pod to query only the specified namespace
-        # Note: list_pod_for_all_namespaces requires cluster-wide permissions
+        ret = v1.list_namespaced_pod(namespace=namespace, label_selector=label_selector, watch=False)
-        ret = v1.list_pod_for_all_namespaces(label_selector=label_selector, watch=False)
 
         servers = []
-        for i in ret.items:
+        for item in ret.items:
-            # Ensure pod has an IP and is running
+            # No need to filter by namespace here as the API call is already namespaced
-            if i.status.pod_ip and i.status.phase == 'Running':
+            if item.status.pod_ip and item.status.phase == 'Running':
                 servers.append({
-                    'ip': i.status.pod_ip,
+                    'ip': item.status.pod_ip,
-                    'node_name': i.spec.node_name
+                    'node_name': item.spec.node_name # Node where the iperf server pod is running
                 })
-        logging.info(f"Discovered {len(servers)} iperf3 server pods.")
+        logging.info(f"Discovered {len(servers)} iperf3 server pods in namespace '{namespace}'.")
         return servers
+    except config.ConfigException as e:
+        logging.error(f"Kubernetes config error: {e}. Is the exporter running in a cluster with RBAC permissions?")
+        return []
     except Exception as e:
         logging.error(f"Error discovering iperf servers: {e}")
-        return [] # Return empty list on error to avoid crashing the loop
+        return [] # Return empty list on error to avoid crashing the main loop
 
-def run_iperf_test(server_ip, server_port, protocol, source_node, dest_node):
+def run_iperf_test(server_ip, server_port, protocol, source_node_name, dest_node_name):
     """
-    Runs a single iperf3 test and updates Prometheus metrics.
+    Runs a single iperf3 test against a specified server and publishes metrics.
+
+    Args:
+        server_ip (str): The IP address of the iperf3 server.
+        server_port (int): The port number of the iperf3 server.
+        protocol (str): The protocol to use ('tcp' or 'udp').
+        source_node_name (str): The name of the source node (where this exporter is running).
+        dest_node_name (str): The name of the destination node (where the server is running).
+
+    The test duration is controlled by the IPERF_TEST_DURATION environment variable
+    (default: 5 seconds).
     """
-    logging.info(f"Running iperf3 test from {source_node} to {dest_node} ({server_ip}:{server_port}) using {protocol.upper()}")
+    logging.info(f"Running iperf3 {protocol.upper()} test from {source_node_name} to {dest_node_name} ({server_ip}:{server_port})")
 
-    client = iperf3.Client()
+    iperf_client = iperf3.Client()
-    client.server_hostname = server_ip
+    iperf_client.server_hostname = server_ip
-    client.port = server_port
+    iperf_client.port = server_port
-    client.protocol = protocol
+    iperf_client.protocol = protocol
-    # Duration of the test (seconds)
+    iperf_client.duration = int(os.getenv('IPERF_TEST_DURATION', 5)) # Test duration in seconds
-    client.duration = int(os.getenv('IPERF_TEST_DURATION', 5))
+    iperf_client.json_output = True # Enables easy parsing of results
-    # Output results as JSON for easy parsing
-    client.json_output = True
 
-    result = client.run()
+    try:
+        result = iperf_client.run()
+        parse_and_publish_metrics(result, source_node_name, dest_node_name, protocol)
+    except Exception as e:
+        # Catch unexpected errors during client.run() or parsing
+        logging.error(f"Exception during iperf3 test or metric parsing for {dest_node_name}: {e}")
+        labels = {'source_node': source_node_name, 'destination_node': dest_node_name, 'protocol': protocol}
+        IPERF_TEST_SUCCESS.labels(**labels).set(0)
+        try:
+            IPERF_BANDWIDTH_MBPS.labels(**labels).set(0)
+            IPERF_JITTER_MS.labels(**labels).set(0)
+            IPERF_PACKETS_TOTAL.labels(**labels).set(0)
+            IPERF_LOST_PACKETS.labels(**labels).set(0)
+        except KeyError:
+            logging.debug(f"KeyError setting failure metrics for {labels} after client.run() exception.")
 
-    # Parse results and update metrics
-    parse_and_publish_metrics(result, source_node, dest_node, protocol)
 
 def parse_and_publish_metrics(result, source_node, dest_node, protocol):
     """
-    Parses the iperf3 result and updates Prometheus gauges.
+    Parses the iperf3 test result and updates Prometheus gauges.
-    Handles both successful and failed tests.
+
+    Args:
+        result (iperf3.TestResult): The result object from the iperf3 client.
+        source_node (str): Name of the source node.
+        dest_node (str): Name of the destination node.
+        protocol (str): Protocol used for the test ('tcp' or 'udp').
     """
     labels = {'source_node': source_node, 'destination_node': dest_node, 'protocol': protocol}
 
-    if result and result.error:
+    # Handle failed tests (e.g., server unreachable) or missing result object
-        logging.error(f"Test from {source_node} to {dest_node} failed: {result.error}")
+    if not result or result.error:
+        error_message = result.error if result and result.error else "No result object from iperf3 client"
+        logging.warning(f"Test from {source_node} to {dest_node} ({protocol.upper()}) failed: {error_message}")
         IPERF_TEST_SUCCESS.labels(**labels).set(0)
-        # Set metrics to 0 on failure
+        # Set all relevant metrics to 0 on failure to clear stale values from previous successes
         try:
             IPERF_BANDWIDTH_MBPS.labels(**labels).set(0)
-            IPERF_JITTER_MS.labels(**labels).set(0)
+            IPERF_JITTER_MS.labels(**labels).set(0) # Applicable for UDP, zeroed for TCP later
-            IPERF_PACKETS_TOTAL.labels(**labels).set(0)
+            IPERF_PACKETS_TOTAL.labels(**labels).set(0) # Applicable for UDP, zeroed for TCP later
-            IPERF_LOST_PACKETS.labels(**labels).set(0)
+            IPERF_LOST_PACKETS.labels(**labels).set(0) # Applicable for UDP, zeroed for TCP later
         except KeyError:
-             # Labels might not be registered yet if this is the first failure
+            # This can happen if labels were never registered due to continuous failures
-             pass
+            logging.debug(f"KeyError when setting failure metrics for {labels}. Gauges might not be initialized.")
         return
 
-    if not result:
+    # If we reach here, the test itself was successful in execution
-         logging.error(f"Test from {source_node} to {dest_node} failed to return a result object.")
-         IPERF_TEST_SUCCESS.labels(**labels).set(0)
-         try:
-            IPERF_BANDWIDTH_MBPS.labels(**labels).set(0)
-            IPERF_JITTER_MS.labels(**labels).set(0)
-            IPERF_PACKETS_TOTAL.labels(**labels).set(0)
-            IPERF_LOST_PACKETS.labels(**labels).set(0)
-         except KeyError:
-             pass
-         return
-
-
     IPERF_TEST_SUCCESS.labels(**labels).set(1)
 
-    # The summary data is typically in result.json['end']['sum_sent'] or result.json['end']['sum_received']
+    # Determine bandwidth:
-    # The iperf3-python client often exposes this directly as attributes like sent_Mbps or received_Mbps
+    # Order of preference: received_Mbps, sent_Mbps, Mbps, then JSON fallbacks.
-    # For TCP, we usually care about the received bandwidth on the client side (which is the exporter)
+    # received_Mbps is often most relevant for TCP client perspective.
-    # For UDP, the client report contains jitter, lost packets, etc.
+    # sent_Mbps can be relevant for UDP or as a TCP fallback.
     bandwidth_mbps = 0
     if hasattr(result, 'received_Mbps') and result.received_Mbps is not None:
         bandwidth_mbps = result.received_Mbps
     elif hasattr(result, 'sent_Mbps') and result.sent_Mbps is not None:
-        # Fallback, though received_Mbps is usually more relevant for TCP client
         bandwidth_mbps = result.sent_Mbps
-    # Add a check for the raw JSON output structure as a fallback
+    elif hasattr(result, 'Mbps') and result.Mbps is not None: # General attribute from iperf3 library
-    elif result.json and 'end' in result.json and 'sum_received' in result.json['end'] and result.json['end']['sum_received']['bits_per_second'] is not None:
+        bandwidth_mbps = result.Mbps
-         bandwidth_mbps = result.json['end']['sum_received']['bits_per_second'] / 1000000
+    # Fallback to raw JSON if direct attributes are None or missing
-    elif result.json and 'end' in result.json and 'sum_sent' in result.json['end'] and result.json['end']['sum_sent']['bits_per_second'] is not None:
+    elif result.json:
-         bandwidth_mbps = result.json['end']['sum_sent']['bits_per_second'] / 1000000
+        # Prefer received sum, then sent sum from the JSON output's 'end' summary
-
+        if 'end' in result.json and 'sum_received' in result.json['end'] and \
+           result.json['end']['sum_received'].get('bits_per_second') is not None:
+            bandwidth_mbps = result.json['end']['sum_received']['bits_per_second'] / 1000000.0
+        elif 'end' in result.json and 'sum_sent' in result.json['end'] and \
+             result.json['end']['sum_sent'].get('bits_per_second') is not None:
+            bandwidth_mbps = result.json['end']['sum_sent']['bits_per_second'] / 1000000.0
 
     IPERF_BANDWIDTH_MBPS.labels(**labels).set(bandwidth_mbps)
 
     # UDP specific metrics
     if protocol == 'udp':
-        # iperf3-python exposes UDP results directly
+        # These attributes are specific to UDP tests in iperf3
-        IPERF_JITTER_MS.labels(**labels).set(result.jitter_ms if hasattr(result, 'jitter_ms') and result.jitter_ms is not None else 0)
+        IPERF_JITTER_MS.labels(**labels).set(getattr(result, 'jitter_ms', 0) if result.jitter_ms is not None else 0)
-        IPERF_PACKETS_TOTAL.labels(**labels).set(result.packets if hasattr(result, 'packets') and result.packets is not None else 0)
+        IPERF_PACKETS_TOTAL.labels(**labels).set(getattr(result, 'packets', 0) if result.packets is not None else 0)
-        IPERF_LOST_PACKETS.labels(**labels).set(result.lost_packets if hasattr(result, 'lost_packets') and result.lost_packets is not None else 0)
+        IPERF_LOST_PACKETS.labels(**labels).set(getattr(result, 'lost_packets', 0) if result.lost_packets is not None else 0)
     else:
-        # Ensure UDP metrics are zeroed or absent for TCP tests
+        # For TCP tests, ensure UDP-specific metrics are set to 0
         try:
              IPERF_JITTER_MS.labels(**labels).set(0)
              IPERF_PACKETS_TOTAL.labels(**labels).set(0)
              IPERF_LOST_PACKETS.labels(**labels).set(0)
         except KeyError:
+            # Can occur if labels not yet registered (e.g. first test is TCP)
+            logging.debug(f"KeyError for {labels} when zeroing UDP metrics for TCP test.")
             pass
+
+def main_loop():
+    """
+    Main operational loop of the iperf3 exporter.
+
+    This loop periodically:
+    1. Fetches configuration from environment variables:
+       - IPERF_TEST_INTERVAL (default: 300s): Time between test cycles.
+       - IPERF_SERVER_PORT (default: 5201): Port for iperf3 servers.
+       - IPERF_TEST_PROTOCOL (default: 'tcp'): 'tcp' or 'udp'.
+       - SOURCE_NODE_NAME (critical): Name of the node this exporter runs on.
+    2. Discovers iperf3 server pods in the Kubernetes cluster.
+    3. Runs iperf3 tests against each discovered server (unless it's on the same node).
+    4. Sleeps for the configured test interval.
+
+    If SOURCE_NODE_NAME is not set, the script will log an error and exit.
+    """
+    # Fetch operational configuration from environment variables
+    test_interval = int(os.getenv('IPERF_TEST_INTERVAL', 300))
+    server_port = int(os.getenv('IPERF_SERVER_PORT', 5201))
+    protocol = os.getenv('IPERF_TEST_PROTOCOL', 'tcp').lower() # Ensure lowercase
+    source_node_name = os.getenv('SOURCE_NODE_NAME')
+
+    # SOURCE_NODE_NAME is crucial for labeling metrics correctly.
+    if not source_node_name:
+        logging.error("CRITICAL: SOURCE_NODE_NAME environment variable not set. This is required. Exiting.")
+        sys.exit(1)
+
+    logging.info(
+        f"Exporter configured. Source Node: {source_node_name}, "
+        f"Test Interval: {test_interval}s, Server Port: {server_port}, Protocol: {protocol.upper()}"
+    )
+
+    while True:
+        logging.info("Starting new iperf test cycle...")
+        servers = discover_iperf_servers()
+
+        if not servers:
+            logging.warning("No iperf servers discovered in this cycle. Check K8s setup and RBAC permissions.")
+        else:
+            for server in servers:
+                dest_node_name = server.get('node_name', 'unknown_destination_node') # Default if key missing
+                server_ip = server.get('ip')
+
+                if not server_ip:
+                    logging.warning(f"Discovered server entry missing an IP: {server}. Skipping.")
+                    continue
+
+                # Avoid testing a node against itself
+                if dest_node_name == source_node_name:
+                    logging.info(f"Skipping test to self: {source_node_name} to {server_ip} (on same node: {dest_node_name}).")
+                    continue
+
+                run_iperf_test(server_ip, server_port, protocol, source_node_name, dest_node_name)
+
+        logging.info(f"Test cycle completed. Sleeping for {test_interval} seconds.")
+        time.sleep(test_interval)
+
+if __name__ == '__main__':
+    # Initial logging (like log level) is configured globally at the start of the script.
+
+    # Fetch Prometheus exporter listen port from environment variable
+    listen_port = int(os.getenv('LISTEN_PORT', 9876))
+
+    try:
+        # Start the Prometheus HTTP server to expose metrics.
+        start_http_server(listen_port)
+        logging.info(f"Prometheus exporter listening on port {listen_port}")
+    except Exception as e:
+        logging.error(f"Failed to start Prometheus HTTP server on port {listen_port}: {e}")
+        sys.exit(1) # Exit if the metrics server cannot start
+
+    # Enter the main operational loop.
+    # main_loop() contains its own critical checks (e.g., SOURCE_NODE_NAME) and will exit if necessary.
+    main_loop()