Add ci steps

.github/workflows/helm-ci.yml

@@ -0,0 +1,101 @@
+---
+name: helm-ci
+on:
+  pull_request:
+    paths:
+      - "charts/meta-monitoring/**"
+
+env:
+  CT_CONFIGFILE: charts/meta-monitoring/ct.yaml
+
+jobs:
+  call-lint:
+    name: Lint Helm Chart
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout Code
+        uses: actions/checkout@v3
+
+      # - name: Check Docs
+      #   run: |
+      #     docker run --rm --volume "$(pwd):/helm-docs" -u "$(id -u)" jnorwood/helm-docs:v1.11.0
+      #     if ! git diff --exit-code; then
+      #         echo "Documentation not up to date. Please run helm-docs and commit changes!" >&2
+      #         exit 1
+      #     fi
+
+      - name: Lint Yaml
+        run: make helm-lint
+
+      # - name: Lint Code Base
+      #   uses: docker://github/super-linter:v3.12.0
+      #   env:
+      #     FILTER_REGEX_EXCLUDE: .*(README\.md|Chart\.yaml|NOTES.txt).*
+      #     FILTER_REGEX_INCLUDE: .*charts/meta-monitoring/.*
+      #     VALIDATE_ALL_CODEBASE: false
+      #     VALIDATE_KUBERNETES_KUBEVAL: false
+      #     VALIDATE_YAML: false
+      #     VALIDATE_GO: false
+      #     DEFAULT_BRANCH: main
+      #     GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+  call-test:
+    name: Test Helm Chart
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v3
+        with:
+          fetch-depth: 0
+
+      - name: Set up Helm
+        uses: azure/setup-helm@v3
+        with:
+          version: v3.8.2
+
+      # Python is required because `ct lint` runs Yamale (https://github.com/23andMe/Yamale) and
+      # yamllint (https://github.com/adrienverge/yamllint) which require Python
+      - name: Set up Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: 3.7
+
+      - name: Set up chart-testing
+        uses: helm/chart-testing-action@v2.4.0
+
+      - name: Run chart-testing (list-changed)
+        id: list-changed
+        run: |
+          changed=$(ct list-changed --config "${CT_CONFIGFILE}")
+          if [[ -n "$changed" ]]; then
+            echo "changed=true" >> $GITHUB_OUTPUT
+          fi
+
+      - name: Run chart-testing (lint)
+        run: ct lint --config "${CT_CONFIGFILE}" --check-version-increment=false
+
+      - name: Create kind cluster
+        uses: helm/kind-action@v1.8.0
+        if: steps.list-changed.outputs.changed == 'true'
+
+      # - name: Install prometheus operator
+      #   id: install-prometheus
+      #   if: steps.list-changed.outputs.changed == 'true'
+      #   run: |
+      #     kubectl create namespace prometheus
+
+      #     helm install prometheus prometheus-community/kube-prometheus-stack \
+      #       --namespace prometheus \
+      #       --set grafana.enabled=false \
+      #       --set prometheus.prometheusSpec.serviceMonitorSelector.matchLabels.release=prometheus
+
+      #     kubectl --namespace prometheus get pods -l "release=prometheus"
+      #     kubectl --namespace prometheus get services -l "release=prometheus"
+
+      - name: Run chart-testing (install)
+        run: |
+          changed=$(ct list-changed --config "${CT_CONFIGFILE}")
+          if [[ "$changed" == "charts/enterprise-metrics" ]]; then
+            # Do not run `ct install` for enterprise-metrics
+            exit 0
+          fi
+          ct install --config "${CT_CONFIGFILE}"

Makefile

@@ -0,0 +1,10 @@
+# Adapted from https://www.thapaliya.com/en/writings/well-documented-makefiles/
+.PHONY: help
+help: ## Display this help and any documented user-facing targets. Other undocumented targets may be present in the Makefile.
+help:
+	@awk 'BEGIN {FS = ":.*##"; printf "\nUsage:\n  make <target>\n\nTargets:\n"} /^[a-zA-Z_-]+:.*?##/ { printf "  %-45s %s\n", $$1, $$2 }' $(MAKEFILE_LIST)
+
+.PHONY: helm-lint
+
+helm-lint: ## run helm linter
+	$(MAKE) -BC charts/meta-monitoring lint

charts/meta-monitoring/Chart.lock

@@ -14,5 +14,5 @@ dependencies:
 - name: minio
   repository: https://charts.min.io
   version: 5.0.11
-digest: sha256:4b04084e6fe821c4d481017b2430f7c8cd782a5d60830dd3a24eb8f10a9ece09
-generated: "2023-06-29T14:25:07.247853+01:00"
+digest: sha256:da0e744b5046eb7972e0bf82d1d0ba4786e9600af63b65f35b16118105248074
+generated: "2023-08-16T16:08:36.406791+01:00"

charts/meta-monitoring/Chart.yaml

@@ -25,21 +25,21 @@ appVersion: "0.0.1"
 
 dependencies:
 - name: loki
-  repository:  https://grafana.github.io/helm-charts
+  repository: https://grafana.github.io/helm-charts
   version: "5.8.0"
   condition: local.logs.enabled
 - name: grafana-agent
-  repository:  https://grafana.github.io/helm-charts
+  repository: https://grafana.github.io/helm-charts
   version: "0.15.0"
 - name: mimir-distributed
-  repository:  https://grafana.github.io/helm-charts
+  repository: https://grafana.github.io/helm-charts
   version: "4.4.1"
   condition: local.metrics.enabled
 - name: tempo-distributed
-  repository:  https://grafana.github.io/helm-charts
+  repository: https://grafana.github.io/helm-charts
   version: "1.4.7"
   condition: local.traces.enabled
 - name: minio
   repository: https://charts.min.io
   version: "5.0.11"
-  condition: local.minio.enabled
+  condition: local.minio.enabled

charts/meta-monitoring/Makefile

@@ -0,0 +1,7 @@
+.DEFAULT_GOAL := all
+.PHONY: lint lint-yaml
+
+lint: lint-yaml
+
+lint-yaml:
+	yamllint -c $(CURDIR)/src/.yamllint.yaml $(CURDIR)/src

charts/meta-monitoring/ct.yaml

@@ -0,0 +1,11 @@
+---
+remote: origin
+target-branch: main
+chart-dirs:
+  - charts
+chart-repos:
+  - grafana=https://grafana.github.io/helm-charts
+  - minio=https://charts.min.io
+helm-extra-args: --timeout 1200s
+check-version-increment: false
+validate-maintainers: false

charts/meta-monitoring/src/.yamllint.yaml

@@ -0,0 +1,4 @@
+---
+rules:
+  quoted-strings:
+    required: true

charts/meta-monitoring/src/rules/loki-rules.yaml

@@ -1,53 +1,53 @@
 groups:
-- name: loki_rules
+- name: "loki_rules"
   rules:
-  - expr: histogram_quantile(0.99, sum(rate(loki_request_duration_seconds_bucket[1m]))
-      by (le, cluster, job))
-    record: cluster_job:loki_request_duration_seconds:99quantile
-  - expr: histogram_quantile(0.50, sum(rate(loki_request_duration_seconds_bucket[1m]))
-      by (le, cluster, job))
-    record: cluster_job:loki_request_duration_seconds:50quantile
-  - expr: sum(rate(loki_request_duration_seconds_sum[1m])) by (cluster, job) / sum(rate(loki_request_duration_seconds_count[1m]))
-      by (cluster, job)
-    record: cluster_job:loki_request_duration_seconds:avg
-  - expr: sum(rate(loki_request_duration_seconds_bucket[1m])) by (le, cluster, job)
-    record: cluster_job:loki_request_duration_seconds_bucket:sum_rate
-  - expr: sum(rate(loki_request_duration_seconds_sum[1m])) by (cluster, job)
-    record: cluster_job:loki_request_duration_seconds_sum:sum_rate
-  - expr: sum(rate(loki_request_duration_seconds_count[1m])) by (cluster, job)
-    record: cluster_job:loki_request_duration_seconds_count:sum_rate
-  - expr: histogram_quantile(0.99, sum(rate(loki_request_duration_seconds_bucket[1m]))
-      by (le, cluster, job, route))
-    record: cluster_job_route:loki_request_duration_seconds:99quantile
-  - expr: histogram_quantile(0.50, sum(rate(loki_request_duration_seconds_bucket[1m]))
-      by (le, cluster, job, route))
-    record: cluster_job_route:loki_request_duration_seconds:50quantile
-  - expr: sum(rate(loki_request_duration_seconds_sum[1m])) by (cluster, job, route)
-      / sum(rate(loki_request_duration_seconds_count[1m])) by (cluster, job, route)
-    record: cluster_job_route:loki_request_duration_seconds:avg
-  - expr: sum(rate(loki_request_duration_seconds_bucket[1m])) by (le, cluster, job,
-      route)
-    record: cluster_job_route:loki_request_duration_seconds_bucket:sum_rate
-  - expr: sum(rate(loki_request_duration_seconds_sum[1m])) by (cluster, job, route)
-    record: cluster_job_route:loki_request_duration_seconds_sum:sum_rate
-  - expr: sum(rate(loki_request_duration_seconds_count[1m])) by (cluster, job, route)
-    record: cluster_job_route:loki_request_duration_seconds_count:sum_rate
-  - expr: histogram_quantile(0.99, sum(rate(loki_request_duration_seconds_bucket[1m]))
-      by (le, cluster, namespace, job, route))
-    record: cluster_namespace_job_route:loki_request_duration_seconds:99quantile
-  - expr: histogram_quantile(0.50, sum(rate(loki_request_duration_seconds_bucket[1m]))
-      by (le, cluster, namespace, job, route))
-    record: cluster_namespace_job_route:loki_request_duration_seconds:50quantile
-  - expr: sum(rate(loki_request_duration_seconds_sum[1m])) by (cluster, namespace,
+  - expr: "histogram_quantile(0.99, sum(rate(loki_request_duration_seconds_bucket[1m]))
+      by (le, cluster, job))"
+    record: "cluster_job:loki_request_duration_seconds:99quantile"
+  - expr: "histogram_quantile(0.50, sum(rate(loki_request_duration_seconds_bucket[1m]))
+      by (le, cluster, job))"
+    record: "cluster_job:loki_request_duration_seconds:50quantile"
+  - expr: "sum(rate(loki_request_duration_seconds_sum[1m])) by (cluster, job) / sum(rate(loki_request_duration_seconds_count[1m]))
+      by (cluster, job)"
+    record: "cluster_job:loki_request_duration_seconds:avg"
+  - expr: "sum(rate(loki_request_duration_seconds_bucket[1m])) by (le, cluster, job)"
+    record: "cluster_job:loki_request_duration_seconds_bucket:sum_rate"
+  - expr: "sum(rate(loki_request_duration_seconds_sum[1m])) by (cluster, job)"
+    record: "cluster_job:loki_request_duration_seconds_sum:sum_rate"
+  - expr: "sum(rate(loki_request_duration_seconds_count[1m])) by (cluster, job)"
+    record: "cluster_job:loki_request_duration_seconds_count:sum_rate"
+  - expr: "histogram_quantile(0.99, sum(rate(loki_request_duration_seconds_bucket[1m]))
+      by (le, cluster, job, route))"
+    record: "cluster_job_route:loki_request_duration_seconds:99quantile"
+  - expr: "histogram_quantile(0.50, sum(rate(loki_request_duration_seconds_bucket[1m]))
+      by (le, cluster, job, route))"
+    record: "cluster_job_route:loki_request_duration_seconds:50quantile"
+  - expr: "sum(rate(loki_request_duration_seconds_sum[1m])) by (cluster, job, route)
+      / sum(rate(loki_request_duration_seconds_count[1m])) by (cluster, job, route)"
+    record: "cluster_job_route:loki_request_duration_seconds:avg"
+  - expr: "sum(rate(loki_request_duration_seconds_bucket[1m])) by (le, cluster, job,
+      route)"
+    record: "cluster_job_route:loki_request_duration_seconds_bucket:sum_rate"
+  - expr: "sum(rate(loki_request_duration_seconds_sum[1m])) by (cluster, job, route)"
+    record: "cluster_job_route:loki_request_duration_seconds_sum:sum_rate"
+  - expr: "sum(rate(loki_request_duration_seconds_count[1m])) by (cluster, job, route)"
+    record: "cluster_job_route:loki_request_duration_seconds_count:sum_rate"
+  - expr: "histogram_quantile(0.99, sum(rate(loki_request_duration_seconds_bucket[1m]))
+      by (le, cluster, namespace, job, route))"
+    record: "cluster_namespace_job_route:loki_request_duration_seconds:99quantile"
+  - expr: "histogram_quantile(0.50, sum(rate(loki_request_duration_seconds_bucket[1m]))
+      by (le, cluster, namespace, job, route))"
+    record: "cluster_namespace_job_route:loki_request_duration_seconds:50quantile"
+  - expr: "sum(rate(loki_request_duration_seconds_sum[1m])) by (cluster, namespace,
       job, route) / sum(rate(loki_request_duration_seconds_count[1m])) by (cluster,
-      namespace, job, route)
-    record: cluster_namespace_job_route:loki_request_duration_seconds:avg
-  - expr: sum(rate(loki_request_duration_seconds_bucket[1m])) by (le, cluster, namespace,
-      job, route)
-    record: cluster_namespace_job_route:loki_request_duration_seconds_bucket:sum_rate
-  - expr: sum(rate(loki_request_duration_seconds_sum[1m])) by (cluster, namespace,
-      job, route)
-    record: cluster_namespace_job_route:loki_request_duration_seconds_sum:sum_rate
-  - expr: sum(rate(loki_request_duration_seconds_count[1m])) by (cluster, namespace,
-      job, route)
-    record: cluster_namespace_job_route:loki_request_duration_seconds_count:sum_rate
+      namespace, job, route)"
+    record: "cluster_namespace_job_route:loki_request_duration_seconds:avg"
+  - expr: "sum(rate(loki_request_duration_seconds_bucket[1m])) by (le, cluster, namespace,
+      job, route)"
+    record: "cluster_namespace_job_route:loki_request_duration_seconds_bucket:sum_rate"
+  - expr: "sum(rate(loki_request_duration_seconds_sum[1m])) by (cluster, namespace,
+      job, route)"
+    record: "cluster_namespace_job_route:loki_request_duration_seconds_sum:sum_rate"
+  - expr: "sum(rate(loki_request_duration_seconds_count[1m])) by (cluster, namespace,
+      job, route)"
+    record: "cluster_namespace_job_route:loki_request_duration_seconds_count:sum_rate"