Add more docs, examples, and tests. (#765)

* Add details to the test chart Signed-off-by: Pete Wall <pete.wall@grafana.com> * Fix profiling feature and add an integration test for it. Signed-off-by: Pete Wall <pete.wall@grafana.com> * Allow tenantids to be numbers Signed-off-by: Pete Wall <pete.wall@grafana.com> * Fix profiling and update cluster config to use custom clusters Signed-off-by: Pete Wall <pete.wall@grafana.com> * Fix test chart to actually check the result Signed-off-by: Pete Wall <pete.wall@grafana.com> * More test fixes Signed-off-by: Pete Wall <pete.wall@grafana.com> * Remove settings that actually make it harder Signed-off-by: Pete Wall <pete.wall@grafana.com> * Fix cluster name Signed-off-by: Pete Wall <pete.wall@grafana.com> * More test fixing Signed-off-by: Pete Wall <pete.wall@grafana.com> * Fixing tests Signed-off-by: Pete Wall <pete.wall@grafana.com> * simplify the loki deployment to speed up tests Signed-off-by: Pete Wall <pete.wall@grafana.com> * More work on loki chart Signed-off-by: Pete Wall <pete.wall@grafana.com> * Working on docuemntation and examples Signed-off-by: Pete Wall <pete.wall@grafana.com> * Get int tests working Signed-off-by: Pete Wall <pete.wall@grafana.com> * Massive docs and tests update Signed-off-by: Pete Wall <pete.wall@grafana.com> * Add helm repos Signed-off-by: Pete Wall <pete.wall@grafana.com> * Use GITHUB_OUTPUT instead of env Signed-off-by: Pete Wall <pete.wall@grafana.com> * Making linters even happier Signed-off-by: Pete Wall <pete.wall@grafana.com> --------- Signed-off-by: Pete Wall <pete.wall@grafana.com>
grafana · Oct 5, 2024 · 0e8dce2 · 0e8dce2
1 parent d26e124
commit 0e8dce2
Show file tree

Hide file tree

Showing 147 changed files with 7,966 additions and 269 deletions.
diff --git a/.configs/loki.yaml b/.configs/loki.yaml
@@ -1,93 +1,41 @@
 ---
+deploymentMode: SingleBinary
 loki:
   commonConfig:
     replication_factor: 1
+  storage:
+    type: 'filesystem'
   schemaConfig:
     configs:
-      - from: 2024-04-01
+      - from: "2024-01-01"
         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
+        object_store: filesystem  # we're storing on filesystem so there's no real persistence here.
+        schema: v13
 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
+backend:
+  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
+chunksCache:
+  enabled: false
 resultsCache:
   enabled: false
-chunksCache:
+lokiCanary:
+  enabled: false
+test:
   enabled: false
 
-monitoring:
-  selfMonitoring:
-    enabled: false
-    grafanaAgent:
-      installOperator: false
-  serviceMonitor:
+gateway:
+  basicAuth:
     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
+    username: loki
+    password: lokipassword
+  service:
+    port: 8080
diff --git a/.github/workflows/integration-test.yml b/.github/workflows/integration-test.yml
@@ -47,10 +47,29 @@ jobs:
       - name: Set up Helm
         uses: azure/setup-helm@v4
 
+      - name: Check for cluster config
+        id: check-cluster-config
+        run: |
+          if [ -f "charts/k8s-monitoring/tests/integration/${{ matrix.test }}/cluster.yaml" ]; then
+            echo "has-cluster-config=true" >> "${GITHUB_OUTPUT}"
+          else
+            echo "has-cluster-config=false" >> "${GITHUB_OUTPUT}"
+          fi
+
       - name: Create kind cluster
+        if: ${{ steps.check-cluster-config.outputs.has-cluster-config == 'false' }}
+        uses: helm/kind-action@v1
+
+      - name: Create kind cluster with special config
+        if: ${{ steps.check-cluster-config.outputs.has-cluster-config == 'true' }}
         uses: helm/kind-action@v1
+        with:
+          config: charts/k8s-monitoring/tests/integration/${{ matrix.test }}/cluster.yaml
 
       - name: Run test
+        env:
+          CREATE_CLUSTER: "false"
+          DEPLOY_GRAFANA: "false"
         run: |
           echo "Testing ${{ matrix.test }}"
-          CREATE_CLUSTER=false ./scripts/integration-test.sh "charts/k8s-monitoring/tests/integration/${{ matrix.test }}"
+          ./scripts/integration-test.sh "charts/k8s-monitoring/tests/integration/${{ matrix.test }}"
diff --git a/Makefile b/Makefile
@@ -13,6 +13,7 @@ build:
 
 .PHONY: test
 test: build
+	helm repo update
 	set -e && \
 	for chart in $(FEATURE_CHARTS); do \
 		make -C charts/$$chart test; \

diff --git a/charts/feature-annotation-autodiscovery/Chart.yaml b/charts/feature-annotation-autodiscovery/Chart.yaml
@@ -3,6 +3,8 @@ apiVersion: v2
 name: k8s-monitoring-feature-annotation-autodiscovery
 description: Gathers metrics automatically based on Kubernetes Pod and Service annotations
 icon: https://raw.githubusercontent.com/grafana/grafana/main/public/img/grafana_icon.svg
+sources:
+  - https://github.com/grafana/k8s-monitoring-helm/tree/main/charts/feature-annotation-autodiscovery
 version: 1.0.0
 appVersion: 1.0.0
 maintainers:

diff --git a/charts/feature-annotation-autodiscovery/Makefile b/charts/feature-annotation-autodiscovery/Makefile
@@ -26,7 +26,7 @@ build: README.md Chart.lock values.schema.json
 .PHONY: test
 test: build
 	helm lint .
-	ct lint --lint-conf ../../.configs/lintconf.yaml --check-version-increment=false --charts .
+	ct lint --lint-conf ../../.configs/lintconf.yaml --check-version-increment=false --helm-dependency-extra-args=--skip-refresh --charts .
 ifdef HAS_HELM_UNITTEST
 	helm unittest .
 else

diff --git a/charts/feature-annotation-autodiscovery/README.md b/charts/feature-annotation-autodiscovery/README.md
@@ -1,14 +1,38 @@
+<!--
+(NOTE: Do not edit README.md directly. It is a generated file!)
+(      To make changes, please modify README.md.gotmpl and run `helm-docs`)
+-->
+
 # k8s-monitoring-feature-annotation-autodiscovery
 
 ![Version: 1.0.0](https://img.shields.io/badge/Version-1.0.0-informational?style=flat-square) ![AppVersion: 1.0.0](https://img.shields.io/badge/AppVersion-1.0.0-informational?style=flat-square)
-
 Gathers metrics automatically based on Kubernetes Pod and Service annotations
 
+The annotation-based autodiscovery feature makes it very simple to add scrape targets. With this feature enabled, any
+Kubernetes Pods or Services with the `k8s.grafana.com/scrape` annotation set to `true` will be automatically discovered
+and scraped by the collector. There are several other annotations that can be used to customize the behavior of the
+scrape configuration, such as:
+
+*   `k8s.grafana.com/job`: The value to use for the `job` label.
+*   `k8s.grafana.com/instance`: The value to use for the `instance` label.
+*   `k8s.grafana.com/metrics.path`: The path to scrape for metrics. Defaults to `/metrics`.
+*   `k8s.grafana.com/metrics.portNumber`: The port on the Pod or Service to scrape for metrics. This is used to target a specific port by its number, rather than all ports.
+*   `k8s.grafana.com/metrics.portName`: The named port on the Pod or Service to scrape for metrics. This is used to target a specific port by its name, rather than all ports.
+*   `k8s.grafana.com/metrics.scheme`: The scheme to use when scraping metrics. Defaults to `http`.
+*   `k8s.grafana.com/metrics.scrapeInterval`: The scrape interval to use when scraping metrics. Defaults to `60s`.
+
 ## Maintainers
 
 | Name | Email | Url |
 | ---- | ------ | --- |
 | petewall | <pete.wall@grafana.com> |  |
+<!-- markdownlint-disable no-bare-urls -->
+<!-- markdownlint-disable list-marker-space -->
+## Source Code
+
+* <https://github.com/grafana/k8s-monitoring-helm/tree/main/charts/feature-annotation-autodiscovery>
+<!-- markdownlint-enable list-marker-space -->
+<!-- markdownlint-enable no-bare-urls -->
 
 ## Values
 
@@ -60,6 +84,3 @@ Gathers metrics automatically based on Kubernetes Pod and Service annotations
 |-----|------|---------|-------------|
 | global.maxCacheSize | int | `100000` | Sets the max_cache_size for every prometheus.relabel component. ([docs](https://grafana.com/docs/alloy/latest/reference/components/prometheus.relabel/#arguments)) This should be at least 2x-5x your largest scrape target or samples appended rate. |
 | global.scrapeInterval | string | `"60s"` | How frequently to scrape metrics. |
-
-----------------------------------------------
-Autogenerated from chart metadata using [helm-docs v1.14.2](https://github.com/norwoodj/helm-docs/releases/v1.14.2)
diff --git a/charts/feature-annotation-autodiscovery/README.md.gotmpl b/charts/feature-annotation-autodiscovery/README.md.gotmpl
@@ -0,0 +1,32 @@
+<!--
+(NOTE: Do not edit README.md directly. It is a generated file!)
+(      To make changes, please modify README.md.gotmpl and run `helm-docs`)
+-->
+
+{{ template "chart.header" . }}
+{{ template "chart.deprecationWarning" . }}
+{{ template "chart.badgesSection" . }}
+{{ template "chart.description" . }}
+{{ template "chart.homepageLine" . }}
+
+The annotation-based autodiscovery feature makes it very simple to add scrape targets. With this feature enabled, any
+Kubernetes Pods or Services with the `k8s.grafana.com/scrape` annotation set to `true` will be automatically discovered
+and scraped by the collector. There are several other annotations that can be used to customize the behavior of the
+scrape configuration, such as:
+
+*   `k8s.grafana.com/job`: The value to use for the `job` label.
+*   `k8s.grafana.com/instance`: The value to use for the `instance` label.
+*   `k8s.grafana.com/metrics.path`: The path to scrape for metrics. Defaults to `/metrics`.
+*   `k8s.grafana.com/metrics.portNumber`: The port on the Pod or Service to scrape for metrics. This is used to target a specific port by its number, rather than all ports.
+*   `k8s.grafana.com/metrics.portName`: The named port on the Pod or Service to scrape for metrics. This is used to target a specific port by its name, rather than all ports.
+*   `k8s.grafana.com/metrics.scheme`: The scheme to use when scraping metrics. Defaults to `http`.
+*   `k8s.grafana.com/metrics.scrapeInterval`: The scrape interval to use when scraping metrics. Defaults to `60s`.
+
+{{ template "chart.maintainersSection" . }}
+<!-- markdownlint-disable no-bare-urls -->
+<!-- markdownlint-disable list-marker-space -->
+{{ template "chart.sourcesSection" . }}
+<!-- markdownlint-enable list-marker-space -->
+<!-- markdownlint-enable no-bare-urls -->
+{{ template "chart.requirementsSection" . }}
+{{ template "chart.valuesSection" . }}
diff --git a/charts/feature-application-observability/Chart.yaml b/charts/feature-application-observability/Chart.yaml
@@ -3,6 +3,8 @@ apiVersion: v2
 name: k8s-monitoring-feature-application-observability
 description: Gathers application data
 icon: https://raw.githubusercontent.com/grafana/grafana/main/public/img/grafana_icon.svg
+sources:
+  - https://github.com/grafana/k8s-monitoring-helm/tree/main/charts/feature-application-observability
 version: 1.0.0
 appVersion: 1.0.0
 maintainers:

diff --git a/charts/feature-application-observability/Makefile b/charts/feature-application-observability/Makefile
@@ -26,7 +26,7 @@ build: README.md Chart.lock values.schema.json
 .PHONY: test
 test: build
 	helm lint .
-	ct lint --lint-conf ../../.configs/lintconf.yaml --check-version-increment=false --charts .
+	ct lint --lint-conf ../../.configs/lintconf.yaml --check-version-increment=false --helm-dependency-extra-args=--skip-refresh --charts .
 ifdef HAS_HELM_UNITTEST
 	helm unittest .
 else

diff --git a/charts/feature-application-observability/README.md b/charts/feature-application-observability/README.md
@@ -1,14 +1,28 @@
+<!--
+(NOTE: Do not edit README.md directly. It is a generated file!)
+(      To make changes, please modify README.md.gotmpl and run `helm-docs`)
+-->
+
 # k8s-monitoring-feature-application-observability
 
 ![Version: 1.0.0](https://img.shields.io/badge/Version-1.0.0-informational?style=flat-square) ![AppVersion: 1.0.0](https://img.shields.io/badge/AppVersion-1.0.0-informational?style=flat-square)
-
 Gathers application data
 
+The Application Observability feature enables the collection of application telemetry data. Enabling this feature
+requires enabling one or more receivers where data will be sent from the application.
+
 ## Maintainers
 
 | Name | Email | Url |
 | ---- | ------ | --- |
 | petewall | <pete.wall@grafana.com> |  |
+<!-- markdownlint-disable no-bare-urls -->
+<!-- markdownlint-disable list-marker-space -->
+## Source Code
+
+* <https://github.com/grafana/k8s-monitoring-helm/tree/main/charts/feature-application-observability>
+<!-- markdownlint-enable list-marker-space -->
+<!-- markdownlint-enable no-bare-urls -->
 
 ## Values
 
@@ -74,6 +88,3 @@ Gathers application data
 | traces.enabled | bool | `true` |  |
 | traces.filters | object | `{"span":[],"spanevent":[]}` | Apply a filter to traces received via the OTLP or OTLP HTTP receivers. ([docs](https://grafana.com/docs/alloy/latest/reference/components/otelcol.processor.filter/)) |
 | traces.transforms | object | `{"resource":[],"span":[],"spanevent":[]}` | Apply a transformation to traces received via the OTLP or OTLP HTTP receivers. ([docs](https://grafana.com/docs/alloy/latest/reference/components/otelcol.processor.transform/)) |
-
-----------------------------------------------
-Autogenerated from chart metadata using [helm-docs v1.14.2](https://github.com/norwoodj/helm-docs/releases/v1.14.2)
diff --git a/charts/feature-application-observability/README.md.gotmpl b/charts/feature-application-observability/README.md.gotmpl
@@ -0,0 +1,22 @@
+<!--
+(NOTE: Do not edit README.md directly. It is a generated file!)
+(      To make changes, please modify README.md.gotmpl and run `helm-docs`)
+-->
+
+{{ template "chart.header" . }}
+{{ template "chart.deprecationWarning" . }}
+{{ template "chart.badgesSection" . }}
+{{ template "chart.description" . }}
+{{ template "chart.homepageLine" . }}
+
+The Application Observability feature enables the collection of application telemetry data. Enabling this feature
+requires enabling one or more receivers where data will be sent from the application.
+
+{{ template "chart.maintainersSection" . }}
+<!-- markdownlint-disable no-bare-urls -->
+<!-- markdownlint-disable list-marker-space -->
+{{ template "chart.sourcesSection" . }}
+<!-- markdownlint-enable list-marker-space -->
+<!-- markdownlint-enable no-bare-urls -->
+{{ template "chart.requirementsSection" . }}
+{{ template "chart.valuesSection" . }}
diff --git a/charts/feature-application-observability/templates/_validation.tpl b/charts/feature-application-observability/templates/_validation.tpl
@@ -7,7 +7,7 @@
   {{- $msg = append $msg "  receivers:" }}
   {{- $msg = append $msg "    grpc:" }}
   {{- $msg = append $msg "      enabled: true" }}
-  {{- $msg = append $msg "See https://github.com/grafana/k8s-monitoring-helm/blob/main/charts/feature-application-observability for more details." }}
+  {{- $msg = append $msg "See https://github.com/grafana/k8s-monitoring-helm/tree/main/charts/feature-application-observability for more details." }}
   {{- fail (join "\n" $msg) }}
 {{- end }}
 {{- end }}
diff --git a/charts/feature-application-observability/tests/validation_test.yaml b/charts/feature-application-observability/tests/validation_test.yaml
@@ -16,4 +16,4 @@ tests:
               receivers:
                 grpc:
                   enabled: true
-            See https://github.com/grafana/k8s-monitoring-helm/blob/main/charts/feature-application-observability for more details.
+            See https://github.com/grafana/k8s-monitoring-helm/tree/main/charts/feature-application-observability for more details.
diff --git a/charts/feature-cluster-events/Chart.yaml b/charts/feature-cluster-events/Chart.yaml
@@ -3,6 +3,8 @@ apiVersion: v2
 name: k8s-monitoring-feature-cluster-events
 description: Gathers Kubernetes Events
 icon: https://raw.githubusercontent.com/grafana/grafana/main/public/img/grafana_icon.svg
+sources:
+  - https://github.com/grafana/k8s-monitoring-helm/tree/main/charts/feature-cluster-events
 version: 1.0.0
 appVersion: 1.0.0
 maintainers:

diff --git a/charts/feature-cluster-events/Makefile b/charts/feature-cluster-events/Makefile
@@ -26,7 +26,7 @@ build: README.md Chart.lock values.schema.json
 .PHONY: test
 test: build
 	helm lint .
-	ct lint --lint-conf ../../.configs/lintconf.yaml --check-version-increment=false --charts .
+	ct lint --lint-conf ../../.configs/lintconf.yaml --check-version-increment=false --helm-dependency-extra-args=--skip-refresh --charts .
 ifdef HAS_HELM_UNITTEST
 	helm unittest .
 else

diff --git a/charts/feature-cluster-events/README.md b/charts/feature-cluster-events/README.md
@@ -1,14 +1,28 @@
+<!--
+(NOTE: Do not edit README.md directly. It is a generated file!)
+(      To make changes, please modify README.md.gotmpl and run `helm-docs`)
+-->
+
 # k8s-monitoring-feature-cluster-events
 
 ![Version: 1.0.0](https://img.shields.io/badge/Version-1.0.0-informational?style=flat-square) ![AppVersion: 1.0.0](https://img.shields.io/badge/AppVersion-1.0.0-informational?style=flat-square)
-
 Gathers Kubernetes Events
 
+The Cluster Events feature enables the collection of Kubernetes events from the cluster. Events are captured as logs and
+are annotated with additional metadata to make them easier to search and filter.
+
 ## Maintainers
 
 | Name | Email | Url |
 | ---- | ------ | --- |
 | petewall | <pete.wall@grafana.com> |  |
+<!-- markdownlint-disable no-bare-urls -->
+<!-- markdownlint-disable list-marker-space -->
+## Source Code
+
+* <https://github.com/grafana/k8s-monitoring-helm/tree/main/charts/feature-cluster-events>
+<!-- markdownlint-enable list-marker-space -->
+<!-- markdownlint-enable no-bare-urls -->
 
 ## Values
 
@@ -31,6 +45,3 @@ Gathers Kubernetes Events
 |-----|------|---------|-------------|
 | logFormat | string | `"logfmt"` | Log format used to forward cluster events. Allowed values: `logfmt` (default), `json`. |
 | namespaces | list | `[]` | List of namespaces to watch for events (`[]` means all namespaces) |
-
-----------------------------------------------
-Autogenerated from chart metadata using [helm-docs v1.14.2](https://github.com/norwoodj/helm-docs/releases/v1.14.2)