fix: Correct Helm chart label in Grafana dashboard ConfigMap

Updates the `helm.sh/chart` label in the Grafana dashboard ConfigMap
to use `{{ .Chart.Name }}-{{ .Chart.Version | replace "+" "_" }}`.
This resolves a Helm linting error caused by an incorrect template reference.

The previous commit added the Grafana dashboard as a ConfigMap:
feat: Add Grafana dashboard as ConfigMap

Adds the Grafana dashboard for iperf3-monitor as a ConfigMap to the Helm chart.

The dashboard is sourced from the project's README and stored in
`charts/iperf3-monitor/grafana/iperf3-dashboard.json`.

A new template `charts/iperf3-monitor/templates/grafana-dashboard-configmap.yaml`
creates the ConfigMap, loading the dashboard JSON and labeling it with
`grafana_dashboard: "1"` to enable auto-discovery by Grafana.

.github/workflows/ci.yaml

@@ -0,0 +1,83 @@
+name: CI
+
+on:
+  pull_request:
+    branches: ["main"] # Or your main development branch
+
+env:
+  REGISTRY: ghcr.io
+  IMAGE_NAME: ${{ github.repository }}
+
+jobs:
+  validate-chart:
+    name: Validate Helm Chart
+    runs-on: ubuntu-latest
+    steps:
+      - name: Check out code
+        uses: actions/checkout@v3
+
+      - name: Set up Helm
+        uses: azure/setup-helm@v3
+        with:
+          version: v3.10.0
+
+      - name: Helm Lint
+        run: helm lint ./charts/iperf3-monitor
+
+  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 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
+    runs-on: ubuntu-latest
+    steps:
+      - name: Check out code
+        uses: actions/checkout@v3
+
+      # Replace this step with your actual test command(s)
+      - name: Placeholder Test Step
+        run: echo "No tests configured yet. Add your test commands here."

.github/workflows/release.yml

@@ -36,6 +36,12 @@ 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:
@@ -56,6 +62,7 @@ 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
@@ -82,8 +89,8 @@ jobs:
       - 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
-          yq e -i '.appVersion = strenv(VERSION)' ./charts/iperf3-monitor/Chart.yaml
+          VERSION=$VERSION yq e -i '.version = strenv(VERSION)' ./charts/iperf3-monitor/Chart.yaml
+          VERSION=$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 +36,4 @@ Thumbs.db
 
 # Helm
 !charts/iperf3-monitor/.helmignore
-charts/*.tgz # Ignore packaged chart files
+charts/iperf3-monitor/charts/

README.md

@@ -37,7 +37,7 @@ This separation of concerns ensures scalability, resilience, and aligns with Kub
 1.  Add the Helm chart repository (replace with your actual repo URL once published):
 
     ```/dev/null/helm-install.sh#L1-1
-    helm repo add iperf3-monitor https://your-github-org.github.io/iperf3-monitor/
+    helm repo add iperf3-monitor https://malarinv.github.io/iperf3-monitor/
     ```
 
 2.  Update your Helm repositories:
@@ -78,7 +78,7 @@ exporter:
   # -- Configuration for the exporter container image.
   image:
     # -- The container image repository for the exporter.
-    repository: ghcr.io/my-org/iperf3-prometheus-exporter # Replace with your repo URL
+    repository: ghcr.io/malarinv/iperf3-monitor
     # -- The container image tag for the exporter. If not set, the chart's appVersion is used.
     tag: ""
     # -- The image pull policy for the exporter container.
@@ -430,8 +430,4 @@ The project includes a GitHub Actions workflow (`.github/workflows/release.yml`)
 
 ## License
 
-This project is licensed under the terms defined in the `LICENSE` file.
-
-```iperf3-monitor/LICENSE
-This project is currently unlicensed. Please see the project's documentation or repository for licensing information when it becomes available.
-```
+This project is licensed under the GNU Affero General Public License v3. See the `LICENSE` file for details.

charts/iperf3-monitor/Chart.lock

@@ -0,0 +1,9 @@
+dependencies:
+- name: kube-prometheus-stack
+  repository: https://prometheus-community.github.io/helm-charts
+  version: 75.3.6
+- name: prometheus-operator
+  repository: oci://tccr.io/truecharts
+  version: 11.5.1
+digest: sha256:3000e63445f8ba8df601cb483f4f77d14c5c4662bff2d16ffcf5cf1f7def314b
+generated: "2025-06-20T17:25:44.538372209+05:30"

charts/iperf3-monitor/Chart.yaml

@@ -12,19 +12,23 @@ keywords:
   - kubernetes
   - prometheus
   - grafana
-home: https://github.com/malarinv/iperf3-monitor # Replace with your repo URL
+home: https://github.com/malarinv/iperf3-monitor
 sources:
-  - https://github.com/malarinv/iperf3-monitor # Replace with your repo URL
+  - https://github.com/malarinv/iperf3-monitor
 maintainers:
-  - name: Malar Invention # Replace with your name
-    email: malarkannan.invention@gmail.com # Replace with your email
+  - name: Malar Invention
+    email: malarkannan.invention@gmail.com
 icon: https://raw.githubusercontent.com/malarinv/iperf3-monitor/main/icon.png # Optional icon URL
 annotations:
   artifacthub.io/changes: |
     - Add initial Helm chart structure.
   artifacthub.io/category: networking
 dependencies:
-  - name: prometheus-community/kube-prometheus-stack # Example dependency if you package the whole stack
+  - 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"

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

@@ -29,9 +29,9 @@ Create chart's labels
 {{- define "iperf3-monitor.labels" -}}
 helm.sh/chart: {{ include "iperf3-monitor.name" . }}-{{ .Chart.Version | replace "+" "_" }}
 {{ include "iperf3-monitor.selectorLabels" . }}
-{{- if .Chart.AppVersion -}}
+{{ if .Chart.AppVersion }}
 app.kubernetes.io/version: {{ .Chart.AppVersion | quote }}
-{{- end -}}
+{{ end }}
 app.kubernetes.io/managed-by: {{ .Release.Service }}
 {{- end -}}
 
@@ -41,13 +41,13 @@ Selector labels
 {{- define "iperf3-monitor.selectorLabels" -}}
 app.kubernetes.io/name: {{ include "iperf3-monitor.name" . }}
 app.kubernetes.io/instance: {{ .Release.Name }}
-{{- end -}}
+{{ end }}
 
 {{/*
 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-deployment.yaml

@@ -34,6 +34,8 @@ spec:
           value: "{{ .Values.exporter.testInterval }}"
         - name: IPERF_TEST_PROTOCOL
           value: "{{ .Values.exporter.testProtocol }}"
+        - name: LOG_LEVEL
+          value: "{{ .Values.exporter.logLevel }}"
         - name: IPERF_SERVER_PORT
           value: "5201" # Hardcoded as per server DaemonSet
         - name: IPERF_SERVER_NAMESPACE
@@ -41,7 +43,7 @@ spec:
             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"
+          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 }}

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/values.yaml

@@ -12,7 +12,7 @@ exporter:
   # -- Configuration for the exporter container image.
   image:
     # -- The container image repository for the exporter.
-    repository: ghcr.io/malarinv/iperf3-prometheus-exporter # Replace with your repo URL
+    repository: ghcr.io/malarinv/iperf3-monitor
     # -- The container image tag for the exporter. If not set, the chart's appVersion is used.
     tag: ""
     # -- The image pull policy for the exporter container.
@@ -24,6 +24,9 @@ exporter:
   # -- 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
 
@@ -85,7 +88,7 @@ rbac:
 serviceAccount:
   # -- The name of the ServiceAccount to use for the exporter pod.
   # Only used if rbac.create is false. If not set, it defaults to the chart's fullname.
-  name: ""
+  name: "iperf3-monitor"
 
 serviceMonitor:
   # -- If true, create a ServiceMonitor resource for integration with Prometheus Operator.
@@ -118,3 +121,19 @@ networkPolicy:
   namespaceSelector: {}
   # -- Specify pod selectors if needed.
   podSelector: {}
+
+# -----------------------------------------------------------------------------
+# Dependency Configuration
+# -----------------------------------------------------------------------------
+dependencies:
+  # -- Set to true to install Prometheus operator dependency if serviceMonitor.enabled is also true.
+  # -- Set to false to disable the installation of Prometheus operator dependency,
+  # -- regardless of serviceMonitor.enabled. This is useful if you have Prometheus
+  # -- Operator installed and managed separately in your cluster.
+  install: true
+
+  # -- Set to true to use the TrueCharts Prometheus Operator instead of kube-prometheus-stack.
+  # This chart's ServiceMonitor resources require a Prometheus Operator to be functional.
+  # If serviceMonitor.enabled is true and dependencies.install is true,
+  # one of these two dependencies will be pulled based on this flag.
+  useTrueChartsPrometheusOperator: false

devbox.json

@@ -0,0 +1,14 @@
+{
+  "$schema":  "https://raw.githubusercontent.com/jetify-com/devbox/0.13.7/.schema/devbox.schema.json",
+  "packages": [],
+  "shell": {
+    "init_hook": [
+      "echo 'Welcome to devbox!' > /dev/null"
+    ],
+    "scripts": {
+      "test": [
+        "echo \"Error: no test specified\" && exit 1"
+      ]
+    }
+  }
+}

devbox.lock

@@ -0,0 +1,4 @@
+{
+  "lockfile_version": "1",
+  "packages": {}
+}

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
-COPY --from=builder /usr/bin/iperf3 /usr/bin/iperf3
-COPY --from=builder /usr/lib/x86_64-linux-gnu/libiperf.so.0 /usr/lib/x86_64-linux-gnu/libiperf.so.0
+# Install iperf3 and its runtime dependency libsctp1 directly in the final stage.
+# This simplifies the Dockerfile by removing the need to copy iperf3 components from the builder.
+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 ---
-# Configure logging
-logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')
+# --- Global Configuration & Setup ---
+
+# 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
-        # Assumes the exporter runs in a pod with a service account having permissions
-        config.load_incluster_config()
+        config.load_incluster_config() # Assumes running inside a Kubernetes pod
         v1 = client.CoreV1Api()
 
         namespace = os.getenv('IPERF_SERVER_NAMESPACE', 'default')
@@ -51,110 +92,206 @@ 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
-        # Note: list_pod_for_all_namespaces requires cluster-wide permissions
         ret = v1.list_pod_for_all_namespaces(label_selector=label_selector, watch=False)
 
         servers = []
-        for i in ret.items:
-            # Ensure pod has an IP and is running
-            if i.status.pod_ip and i.status.phase == 'Running':
+        for item in ret.items:
+            if item.status.pod_ip and item.status.phase == 'Running':
                 servers.append({
-                    'ip': i.status.pod_ip,
-                    'node_name': i.spec.node_name
+                    'ip': item.status.pod_ip,
+                    'node_name': item.spec.node_name # Node where the iperf server pod is running
                 })
         logging.info(f"Discovered {len(servers)} iperf3 server pods.")
         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()
-    client.server_hostname = server_ip
-    client.port = server_port
-    client.protocol = protocol
-    # Duration of the test (seconds)
-    client.duration = int(os.getenv('IPERF_TEST_DURATION', 5))
-    # Output results as JSON for easy parsing
-    client.json_output = True
+    iperf_client = iperf3.Client()
+    iperf_client.server_hostname = server_ip
+    iperf_client.port = server_port
+    iperf_client.protocol = protocol
+    iperf_client.duration = int(os.getenv('IPERF_TEST_DURATION', 5)) # Test duration in seconds
+    iperf_client.json_output = True # Enables easy parsing of results
 
-    result = client.run()
-
-    # 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.
-    Handles both successful and failed tests.
-    """
-    labels = {'source_node': source_node, 'destination_node': dest_node, 'protocol': protocol}
-
-    if result and result.error:
-        logging.error(f"Test from {source_node} to {dest_node} failed: {result.error}")
+    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)
-        # Set metrics to 0 on failure
         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:
-             # Labels might not be registered yet if this is the first failure
-             pass
+            logging.debug(f"KeyError setting failure metrics for {labels} after client.run() exception.")
+
+
+def parse_and_publish_metrics(result, source_node, dest_node, protocol):
+    """
+    Parses the iperf3 test result and updates Prometheus gauges.
+
+    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}
+
+    # Handle failed tests (e.g., server unreachable) or missing result object
+    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 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) # Applicable for UDP, zeroed for TCP later
+            IPERF_PACKETS_TOTAL.labels(**labels).set(0) # Applicable for UDP, zeroed for TCP later
+            IPERF_LOST_PACKETS.labels(**labels).set(0) # Applicable for UDP, zeroed for TCP later
+        except KeyError:
+            # This can happen if labels were never registered due to continuous failures
+            logging.debug(f"KeyError when setting failure metrics for {labels}. Gauges might not be initialized.")
         return
 
-    if not result:
-         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
-
-
+    # If we reach here, the test itself was successful in execution
     IPERF_TEST_SUCCESS.labels(**labels).set(1)
 
-    # The summary data is typically in result.json['end']['sum_sent'] or result.json['end']['sum_received']
-    # The iperf3-python client often exposes this directly as attributes like sent_Mbps or received_Mbps
-    # For TCP, we usually care about the received bandwidth on the client side (which is the exporter)
-    # For UDP, the client report contains jitter, lost packets, etc.
+    # Determine bandwidth:
+    # Order of preference: received_Mbps, sent_Mbps, Mbps, then JSON fallbacks.
+    # received_Mbps is often most relevant for TCP client perspective.
+    # 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 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.json['end']['sum_received']['bits_per_second'] / 1000000
-    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:
-         bandwidth_mbps = result.json['end']['sum_sent']['bits_per_second'] / 1000000
-
+    elif hasattr(result, 'Mbps') and result.Mbps is not None: # General attribute from iperf3 library
+        bandwidth_mbps = result.Mbps
+    # Fallback to raw JSON if direct attributes are None or missing
+    elif result.json:
+        # 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
-        IPERF_JITTER_MS.labels(**labels).set(result.jitter_ms if hasattr(result, 'jitter_ms') and 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_LOST_PACKETS.labels(**labels).set(result.lost_packets if hasattr(result, 'lost_packets') and result.lost_packets is not None else 0)
+        # These attributes are specific to UDP tests in iperf3
+        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(getattr(result, 'packets', 0) if result.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()