k8s-monitoring 2.0 alpha

.configs/certificates.yaml

@@ -0,0 +1,35 @@
+---
+apiVersion: v1
+kind: Namespace
+metadata:
+ name: prometheus
+---
+apiVersion: secretgen.k14s.io/v1alpha1
+kind: Certificate
+metadata:
+ name: ca-cert
+ namespace: prometheus
+spec:
+ isCA: true
+---
+apiVersion: secretgen.k14s.io/v1alpha1
+kind: Certificate
+metadata:
+ name: prometheus-ssl
+ namespace: prometheus
+spec:
+ alternativeNames:
+ - prometheus-server.prometheus.svc.cluster.local
+ caRef:
+ name: ca-cert
+---
+apiVersion: secretgen.k14s.io/v1alpha1
+kind: Certificate
+metadata:
+ name: prometheus-workload-ssl
+ namespace: prometheus
+spec:
+ alternativeNames:
+ - prometheus-workload-server.prometheus.svc.cluster.local
+ caRef:
+ name: ca-cert

.configs/loki.yaml

@@ -0,0 +1,93 @@
+---
+loki:
+ commonConfig:
+ replication_factor: 1
+ schemaConfig:
+ configs:
+ - from: 2024-04-01
+ store: tsdb
+ object_store: s3
+ schema: v13
+ index:
+ prefix: loki_index_
+ period: 24h
+ ingester:
+ chunk_encoding: snappy
+ querier:
+ # Default is 4, if you have enough memory and CPU you can increase, reduce if OOMing
+ max_concurrent: 2
+
+test:
+ enabled: false
+
+lokiCanary:
+ enabled: false
+
+gateway:
+ basicAuth:
+ enabled: true
+ username: loki
+ password: lokipassword
+ service:
+ port: 8080
+
+deploymentMode: SingleBinary
+singleBinary:
+ replicas: 1
+# resources:
+# limits:
+# cpu: 3
+# memory: 4Gi
+# requests:
+# cpu: 2
+# memory: 2Gi
+# extraEnv:
+# # Keep a little bit lower than memory limits
+# - name: GOMEMLIMIT
+# value: 3750MiB
+
+# Enable minio for storage
+minio:
+ enabled: true
+
+# Zero out replica counts of other deployment modes
+backend:
+ replicas: 0
+read:
+ replicas: 0
+write:
+ replicas: 0
+
+ingester:
+ replicas: 0
+querier:
+ replicas: 0
+queryFrontend:
+ replicas: 0
+queryScheduler:
+ replicas: 0
+distributor:
+ replicas: 0
+compactor:
+ replicas: 0
+indexGateway:
+ replicas: 0
+bloomCompactor:
+ replicas: 0
+bloomGateway:
+ replicas: 0
+resultsCache:
+ enabled: false
+chunksCache:
+ enabled: false
+
+monitoring:
+ selfMonitoring:
+ enabled: false
+ grafanaAgent:
+ installOperator: false
+ serviceMonitor:
+ enabled: true
+ # This actually isn't recommended by Loki, the default is 15s for a reason, but we don't want to upset
+ # our DPM test calculations.
+ interval: 1m

.configs/prometheus.yaml

@@ -0,0 +1,49 @@
+---
+server:
+ extraFlags:
+ - enable-feature=otlp-write-receiver
+ - enable-feature=remote-write-receiver
+ - web.config.file=/etc/config/web.yml
+
+ extraSecretMounts:
+ - name: prometheus-ssl
+ mountPath: /etc/prometheus-ssl
+ secretName: prometheus-ssl
+ readOnly: true
+
+ persistentVolume:
+ enabled: false
+
+ probeHeaders:
+ - name: "Authorization"
+ value: "Basic cHJvbXVzZXI6cHJvbWV0aGV1c3Bhc3N3b3Jk"
+ probeScheme: HTTPS
+
+ service:
+ servicePort: 9090
+
+serverFiles:
+ prometheus.yml:
+ scrape_configs: []
+ web.yml:
+ basic_auth_users:
+ promuser: $2a$12$1UJsAG4QnhjjDzqcSVkZmeDxxjgIFOAmzfuVTybTuhhDnYgfuAbAq # "prometheuspassword"
+ tls_server_config:
+ cert_file: /etc/prometheus-ssl/crt.pem
+ key_file: /etc/prometheus-ssl/key.pem
+
+configmapReload:
+ prometheus:
+ enabled: false
+
+alertmanager:
+ enabled: false
+
+kube-state-metrics:
+ enabled: false
+
+prometheus-node-exporter:
+ enabled: false
+
+prometheus-pushgateway:
+ enabled: false

.github/CODEOWNERS

@@ -0,0 +1,16 @@
+# This file is used to define the owners of the code in this repository.
+# https://help.github.com/articles/about-codeowners/
+
+# Global owners
+* @petewall
+
+# Chart owners
+charts/feature-annotation-autodiscovery @grafana/k8s-monitoring-dev
+charts/feature-application-observability @rlankfo
+charts/feature-cluster-events @grafana/k8s-monitoring-dev
+charts/feature-cluster-metrics @grafana/k8s-monitoring-dev
+charts/feature-frontend-observability @rlankfo
+charts/feature-pod-logs @grafana/k8s-monitoring-dev
+charts/feature-profiling @simonswine
+charts/feature-prometheus-operator-objects @grafana/k8s-monitoring-dev
+charts/k8s-monitoring-v1 @grafana/k8s-monitoring-dev

.github/workflows/helm-test.yml

@@ -15,7 +15,7 @@ on:
 
 env:
  CT_CONFIGFILE: "${{ github.workspace }}/.github/configs/ct.yaml"
- LINT_CONFIGFILE: "${{ github.workspace }}/.github/configs/lintconf.yaml"
+ LINT_CONFIGFILE: "${{ github.workspace }}/.configs/lintconf.yaml"
  GRAFANA_ALLOY_VALUES: "${{ github.workspace }}/.github/configs/alloy-config.yaml"
  GRAFANA_ALLOY_LOKI_OTLP_VALUES: "${{ github.workspace }}/.github/configs/alloy-config-loki-otlp.yaml"
  GRAFANA_ALLOY_RECEIVER_SERVICE: "${{ github.workspace }}/.github/configs/receiver-service.yaml"
@@ -212,4 +212,4 @@ jobs:
  if: (steps.list-changed.outputs.changed == 'true') || (contains(github.event.pull_request.labels.*.name, 'full_test_required'))
  run: |
  latestRelease=$(git describe --abbrev=0 --tags)
- ct install --all --config "${CT_CONFIGFILE}" --since "${latestRelease}" --helm-extra-args "--timeout 10m"
+ ct install --config "${CT_CONFIGFILE}" --since "${latestRelease}" --helm-extra-args "--timeout 10m" --charts charts/k8s-monitoring-v1

.github/workflows/integration-test.yml

@@ -0,0 +1,56 @@
+---
+name: Integration Test
+# yamllint disable-line rule:truthy
+on:
+ push:
+ branches: ["main"]
+ paths:
+ - 'charts/**'
+ - '!charts/k8s-monitoring-v1/**'
+ pull_request:
+ paths:
+ - 'charts/**'
+ - '!charts/k8s-monitoring-v1/**'
+
+ # Allows you to run this workflow manually from the Actions tab
+ workflow_dispatch:
+
+jobs:
+ list-tests:
+ name: List tests
+ runs-on: ubuntu-latest
+ outputs:
+ tests: ${{ steps.list_tests.outputs.tests }}
+ steps:
+ - name: Checkout code
+ uses: actions/checkout@v4
+
+ - name: List tests
+ id: list_tests
+ run: |
+ tests=$(ls charts/k8s-monitoring/tests/integration)
+ echo "Tests: ${tests}"
+ echo "tests=$(echo "${tests}" | jq --raw-input --slurp --compact-output 'split("\n") | map(select(. != ""))')" >> "${GITHUB_OUTPUT}"
+
+ run-tests:
+ name: Integration Test
+ needs: list-tests
+ runs-on: ubuntu-latest
+ strategy:
+ matrix:
+ test: ${{ fromJson(needs.list-tests.outputs.tests) }}
+ fail-fast: false
+ steps:
+ - name: Checkout code
+ uses: actions/checkout@v4
+
+ - name: Set up Helm
+ uses: azure/setup-helm@v4
+
+ - name: Create kind cluster
+ uses: helm/kind-action@v1
+
+ - name: Run test
+ run: |
+ echo "Testing ${{ matrix.test }}"
+ CREATE_CLUSTER=false ./scripts/integration-test.sh "charts/k8s-monitoring/tests/integration/${{ matrix.test }}"

.github/workflows/reviewdog.yml

@@ -2,9 +2,13 @@
 name: ReviewDog
 # yamllint disable-line rule:truthy
 on:
- pull_request:
+ push:
  branches: ["main"]
 
+ pull_request:
+
+ workflow_dispatch:
+
 jobs:
  markdownlint:
  name: runner / markdownlint
@@ -137,7 +141,7 @@ jobs:
  - env:
  REVIEWDOG_GITHUB_API_TOKEN: ${{ secrets.GITHUB_TOKEN }}
  run: |
- npx textlint --format checkstyle --config ./.textlintrc --ignore-path ./.textlintignore $(find . -type f -name "*.md" -not \( -path "./node_modules/*" -o -path "./data-alloy/*" \)) | \
+ npx textlint --format checkstyle --config ./.textlintrc --ignore-path ./.textlintignore "$(find . -type f -name "*.md" -not \( -path "./node_modules/*" -o -path "./data-alloy/*" \))" | \
  reviewdog -f=checkstyle -name="textlint" -reporter=github-check -level=info
 
  alloy: