Split up Grafana yaml

Signed-off-by: Michel Hollands <michel.hollands@gmail.com>

.github/configs/cr.yaml

@@ -0,0 +1,3 @@
+owner: grafana
+git-repo: helm-charts
+skip-existing: true

.github/configs/ct.yaml

@@ -0,0 +1,15 @@
+## Reference: https://github.com/helm/chart-testing/blob/master/doc/ct_lint-and-install.md
+remote: origin
+target-branch: main
+chart-dirs:
+- charts
+chart-repos:
+  - grafana=https://grafana.github.io/helm-charts
+  - minio=https://charts.min.io
+validate-chart-schema: true
+validate-maintainers: true
+validate-yaml: true
+exclude-deprecated: true
+excluded-charts: []
+namespace: meta-monitoring # Need to set the namespace because we create the secret there
+release-label: app.kubernetes.io/instance

.github/configs/updatecli.d/alloy.yaml

@@ -0,0 +1,30 @@
+name: Bump dependency "alloy" for Helm chart "meta-monitoring"
+sources:
+    alloy:
+        name: Get latest "alloy" Helm chart version
+        kind: helmchart
+        spec:
+            name: alloy
+            url: https://grafana.github.io/helm-charts
+            versionfilter:
+                kind: semver
+                pattern: '*'
+conditions:
+    alloy:
+        name: Ensure Helm chart dependency "alloy" is specified
+        kind: yaml
+        spec:
+            file: charts/meta-monitoring/Chart.yaml
+            key: $.dependencies[1].name
+            value: alloy
+        disablesourceinput: true
+targets:
+    alloy:
+        name: Bump Helm chart dependency "alloy" for Helm chart "meta-monitoring"
+        kind: helmchart
+        spec:
+            file: Chart.yaml
+            key: $.dependencies[1].version
+            name: charts/meta-monitoring
+            versionincrement: none
+        sourceid: alloy

.github/configs/updatecli.d/grafana.yaml

@@ -0,0 +1,30 @@
+name: Bump grafana version specified in the values.yaml
+sources:
+    latestGrafanaRelease:
+        name: Get latest grafana release on Github
+        kind: githubrelease
+        spec:
+            owner: grafana
+            repository: grafana
+            token: '{{ requiredEnv "UPDATECLI_GITHUB_TOKEN" }}'
+            versionfilter:
+                kind: latest
+        transformers:
+          - trimprefix: "v"
+conditions:
+    grafanaImagePublished:
+        name: Ensure the latest Grafana is published on DockerHub
+        kind: dockerimage
+        source-id: latestGrafanaRelease
+        spec:
+            image: "grafana/grafana"
+targets:
+    grafana:
+        name: Update Grafana version in values.yaml
+        kind: helmchart
+        spec:
+            file: values.yaml
+            key: $.grafana.version
+            name: charts/meta-monitoring
+            versionincrement: none
+        sourceid: latestGrafanaRelease

.github/configs/updatecli.d/loki.yaml

@@ -0,0 +1,30 @@
+name: Bump dependency "loki" for Helm chart "meta-monitoring"
+sources:
+    loki:
+        name: Get latest "loki" Helm chart version
+        kind: helmchart
+        spec:
+            name: loki
+            url: https://grafana.github.io/helm-charts
+            versionfilter:
+                kind: semver
+                pattern: '*'
+conditions:
+    loki:
+        name: Ensure Helm chart dependency "loki" is specified
+        kind: yaml
+        spec:
+            file: charts/meta-monitoring/Chart.yaml
+            key: $.dependencies[0].name
+            value: loki
+        disablesourceinput: true
+targets:
+    loki:
+        name: Bump Helm chart dependency "loki" for Helm chart "meta-monitoring"
+        kind: helmchart
+        spec:
+            file: Chart.yaml
+            key: $.dependencies[0].version
+            name: charts/meta-monitoring
+            versionincrement: none
+        sourceid: loki

.github/configs/updatecli.d/mimir-distributed.yaml

@@ -0,0 +1,30 @@
+name: Bump dependency "mimir-distributed" for Helm chart "meta-monitoring"
+sources:
+    mimir-distributed:
+        name: Get latest "mimir-distributed" Helm chart version
+        kind: helmchart
+        spec:
+            name: mimir-distributed
+            url: https://grafana.github.io/helm-charts
+            versionfilter:
+                kind: semver
+                pattern: '*'
+conditions:
+    mimir-distributed:
+        name: Ensure Helm chart dependency "mimir-distributed" is specified
+        kind: yaml
+        spec:
+            file: charts/meta-monitoring/Chart.yaml
+            key: $.dependencies[2].name
+            value: mimir-distributed
+        disablesourceinput: true
+targets:
+    mimir-distributed:
+        name: Bump Helm chart dependency "mimir-distributed" for Helm chart "meta-monitoring"
+        kind: helmchart
+        spec:
+            file: Chart.yaml
+            key: $.dependencies[2].version
+            name: charts/meta-monitoring
+            versionincrement: none
+        sourceid: mimir-distributed

.github/configs/updatecli.d/minio.yaml

@@ -0,0 +1,30 @@
+name: Bump dependency "minio" for Helm chart "meta-monitoring"
+sources:
+    minio:
+        name: Get latest "minio" Helm chart version
+        kind: helmchart
+        spec:
+            name: minio
+            url: https://charts.min.io
+            versionfilter:
+                kind: semver
+                pattern: '*'
+conditions:
+    minio:
+        name: Ensure Helm chart dependency "minio" is specified
+        kind: yaml
+        spec:
+            file: charts/meta-monitoring/Chart.yaml
+            key: $.dependencies[4].name
+            value: minio
+        disablesourceinput: true
+targets:
+    minio:
+        name: Bump Helm chart dependency "minio" for Helm chart "meta-monitoring"
+        kind: helmchart
+        spec:
+            file: Chart.yaml
+            key: $.dependencies[4].version
+            name: charts/meta-monitoring
+            versionincrement: none
+        sourceid: minio

.github/configs/updatecli.d/tempo-distributed.yaml

@@ -0,0 +1,30 @@
+name: Bump dependency "tempo-distributed" for Helm chart "meta-monitoring"
+sources:
+    tempo-distributed:
+        name: Get latest "tempo-distributed" Helm chart version
+        kind: helmchart
+        spec:
+            name: tempo-distributed
+            url: https://grafana.github.io/helm-charts
+            versionfilter:
+                kind: semver
+                pattern: '*'
+conditions:
+    tempo-distributed:
+        name: Ensure Helm chart dependency "tempo-distributed" is specified
+        kind: yaml
+        spec:
+            file: charts/meta-monitoring/Chart.yaml
+            key: $.dependencies[3].name
+            value: tempo-distributed
+        disablesourceinput: true
+targets:
+    tempo-distributed:
+        name: Bump Helm chart dependency "tempo-distributed" for Helm chart "meta-monitoring"
+        kind: helmchart
+        spec:
+            file: Chart.yaml
+            key: $.dependencies[3].version
+            name: charts/meta-monitoring
+            versionincrement: none
+        sourceid: tempo-distributed

.github/workflows/check-for-dependency-updates.yaml

@@ -0,0 +1,113 @@
+---
+name: Check for dependency updates
+
+on:
+    workflow_dispatch:
+    schedule:
+      # Run once a day
+      - cron: '0 7 * * *'
+
+permissions:
+    contents: "write"
+    pull-requests: "write"
+
+env:
+    UPDATECLI_CONFIG_DIR: "${{ github.workspace }}/.github/configs/updatecli.d"
+    UPDATECLI_GITHUB_TOKEN: "${{ secrets.GITHUB_TOKEN }}"
+
+jobs:
+    updateVersions:
+        name: Update the subcharts
+        runs-on: "ubuntu-latest"
+        steps:
+            - name: Checkout
+              uses: actions/checkout@v2
+
+            - name: Install Updatecli
+              uses: updatecli/updatecli-action@v2
+
+            - name: Run Updatecli for Loki
+              id: update-loki
+              run: |
+                updatecli apply --config ${UPDATECLI_CONFIG_DIR}/loki.yaml
+                if ! git diff --exit-code > /dev/null; then
+                  echo "changed=true" >> "${GITHUB_OUTPUT}"
+                fi
+
+            - name: Run Updatecli for Alloy
+              id: update-grafana-alloy
+              run: |
+                updatecli apply --config ${UPDATECLI_CONFIG_DIR}/alloy.yaml
+                if ! git diff --exit-code > /dev/null; then
+                  echo "changed=true" >> "${GITHUB_OUTPUT}"
+                fi
+
+            - name: Run Updatecli for Mimir
+              id: update-mimir-distributed
+              run: |
+                updatecli apply --config ${UPDATECLI_CONFIG_DIR}/mimir-distributed.yaml
+                if ! git diff --exit-code > /dev/null; then
+                  echo "changed=true" >> "${GITHUB_OUTPUT}"
+                fi
+
+            - name: Run Updatecli for Tempo
+              id: update-tempo-distributed
+              run: |
+                updatecli apply --config ${UPDATECLI_CONFIG_DIR}/tempo-distributed.yaml
+                if ! git diff --exit-code > /dev/null; then
+                  echo "changed=true" >> "${GITHUB_OUTPUT}"
+                fi
+
+            - name: Run Updatecli for Minio
+              id: update-minio
+              run: |
+                updatecli apply --config ${UPDATECLI_CONFIG_DIR}/minio.yaml
+                if ! git diff --exit-code > /dev/null; then
+                  echo "changed=true" >> "${GITHUB_OUTPUT}"
+                fi
+
+            - name: Create pull request
+              if: steps.update-loki.outputs.changed == 'true' || steps.update-grafana-alloy.outputs.changed == 'true' || steps.update-mimir-distributed.outputs.changed == 'true' || steps.update-tempo-distributed.outputs.changed == 'true' || steps.update-minio.outputs.changed == 'true'
+              uses: peter-evans/create-pull-request@v5
+              with:
+                title: "[dependency] Update the subcharts"
+                body: "Updates the subcharts"
+                base: main
+                author: "${{ github.actor }} <${{ github.actor }}@users.noreply.github.com>"
+                committer: "GitHub <noreply@github.com>"
+                commit-message: Update dependencies
+                labels: dependencies
+                branch: chore/update-dependencies
+                delete-branch: true
+
+    updateGrafana:
+        name: Update the Grafana version
+        runs-on: "ubuntu-latest"
+        steps:
+            - name: Checkout
+              uses: actions/checkout@v2
+
+            - name: Install Updatecli
+              uses: updatecli/updatecli-action@v2
+
+            - name: Run Updatecli
+              id: update-grafana
+              run: |
+                updatecli apply --config ${UPDATECLI_CONFIG_DIR}/grafana.yaml
+                if ! git diff --exit-code > /dev/null; then
+                  echo "changed=true" >> "${GITHUB_OUTPUT}"
+                fi
+
+            - name: Create pull request
+              if: steps.update-grafana.outputs.changed == 'true'
+              uses: peter-evans/create-pull-request@v5
+              with:
+                title: "[dependency] Update the Grafana version"
+                body: "Updates the Grafana version"
+                base: main
+                author: "${{ github.actor }} <${{ github.actor }}@users.noreply.github.com>"
+                committer: "GitHub <noreply@github.com>"
+                commit-message: Update Grafana version
+                labels: dependencies
+                branch: chore/update-minio
+                delete-branch: true

.github/workflows/helm-ci.yml

@@ -0,0 +1,66 @@
+---
+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: Lint Yaml
+        run: make helm-lint
+
+  # 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'
+  #       with:
+  #         config: tools/kind.config
+
+  #     - name: Run chart-testing (install)
+  #       run: |
+  #         changed=$(ct list-changed --config "${CT_CONFIGFILE}")
+  #         ct install --config "${CT_CONFIGFILE}"

.github/workflows/helm-release.yml

@@ -0,0 +1,175 @@
+name: Release Helm chart
+on:
+  workflow_dispatch:
+env:
+  CR_CONFIGFILE: "${{ github.workspace }}/source/.github/configs/cr.yaml"
+  CT_CONFIGFILE: "${{ github.workspace }}/source/.github/configs/ct.yaml"
+  CR_INDEX_PATH: "${{ github.workspace }}/.cr-index"
+  CR_PACKAGE_PATH: "${{ github.workspace }}/.cr-release-packages"
+  CR_TOOL_PATH: "${{ github.workspace }}/.cr-tool"
+  CR_VERSION: "1.5.0"
+jobs:
+  setup:
+    runs-on: ubuntu-latest
+    outputs:
+      changed: ${{ steps.list-changed.outputs.changed }}
+      chartpath: ${{ steps.list-changed.outputs.chartpath }}
+    steps:
+    - name: Checkout
+      uses: actions/checkout@v4
+      with:
+        fetch-depth: 0
+        path: source
+
+    - name: Install chart-testing
+      uses: helm/chart-testing-action@v2
+
+    - name: List changed charts
+      id: list-changed
+      run: |
+        cd source
+
+        latest_tag=$( if ! git describe --tags --abbrev=0 --match='helm-chart/*' 2> /dev/null ; then git rev-list --max-parents=0 --first-parent HEAD; fi )
+
+        echo "Running: ct list-changed --config ${CT_CONFIGFILE} --since ${latest_tag} --target-branch ${{ github.ref_name }}"
+        changed=$(ct list-changed --config "${CT_CONFIGFILE}" --since "${latest_tag}" --target-branch "${{ github.ref_name }}")
+        echo "${changed}"
+
+        num_changed=$(wc -l <<< ${changed})
+        if [[ "${num_changed}" -gt "1" ]] ; then
+          echo "More than one chart changed, exiting"
+          exit 1
+        fi
+        if [[ -n "${changed}" ]]; then
+          name=$(yq ".name" < ${changed}/Chart.yaml)
+          version=$(yq ".version" < ${changed}/Chart.yaml)
+          tagname="v${version}"
+
+          if [ $(git tag -l "${tagname}") ]; then
+            echo "Tag ${tagname} already exists, skipping release"
+            echo "changed=false" >> $GITHUB_OUTPUT
+          else
+            echo "Releasing ${changed}"
+            echo "changed=true" >> $GITHUB_OUTPUT
+            echo "chartpath=${changed}" >> $GITHUB_OUTPUT
+          fi
+        else
+          echo "No charts have changed, skipping release"
+          echo "changed=false" >> $GITHUB_OUTPUT
+        fi
+
+  release:
+    needs: [setup]
+    runs-on: ubuntu-latest
+    if: needs.setup.outputs.changed == 'true'
+    permissions:
+      contents: write
+      id-token: write
+    steps:
+    - id: get-secrets
+      uses: grafana/shared-workflows/actions/get-vault-secrets@main
+      with:
+        # Secrets placed in the ci/repo/grafana/<repo>/<path> path in Vault
+        repo_secrets: |
+          APP_ID=github-app:app-id
+          PRIVATE_KEY=github-app:private-key
+    - uses: actions/create-github-app-token@v1
+      id: app-token
+      with:
+        app-id: ${{ env.APP_ID }}
+        private-key: ${{ env.PRIVATE_KEY }}
+        owner: ${{ github.repository_owner }}
+    - name: Checkout
+      uses: actions/checkout@v4
+      with:
+        fetch-depth: 0
+        path: source
+
+    - name: Configure Git
+      run: |
+        cd source
+        git config user.name "$GITHUB_ACTOR"
+        git config user.email "$GITHUB_ACTOR@users.noreply.github.com"
+
+    - name: Checkout helm-charts
+      uses: actions/checkout@v4
+      with:
+        fetch-depth: 0
+        repository: grafana/helm-charts
+        path: helm-charts
+        token: "${{ steps.app-token.outputs.token }}"
+
+    - name: Configure Git for helm-charts
+      run: |
+        cd helm-charts
+        git config user.name "$GITHUB_ACTOR"
+        git config user.email "$GITHUB_ACTOR@users.noreply.github.com"
+
+    - name: Set up Helm
+      uses: azure/setup-helm@v4
+
+    - name: Parse Chart.yaml
+      id: parse-chart
+      run: |
+        cd source
+        changed="${{ needs.setup.outputs.chartpath }}"
+        description=$(yq ".description" < ${changed}/Chart.yaml)
+        name=$(yq ".name" < ${changed}/Chart.yaml)
+        version=$(yq ".version" < ${changed}/Chart.yaml)
+
+        echo "chartpath=${changed}" >> $GITHUB_OUTPUT
+        echo "desc=${description}" >> $GITHUB_OUTPUT
+        echo "tagname=v${version}" >> $GITHUB_OUTPUT
+        echo "packagename=${name}-${version}" >> $GITHUB_OUTPUT
+
+    - name: Install CR tool
+      run: |
+        mkdir "${CR_TOOL_PATH}"
+        mkdir "${CR_PACKAGE_PATH}"
+        mkdir "${CR_INDEX_PATH}"
+        curl -sSLo cr.tar.gz "https://github.com/helm/chart-releaser/releases/download/v${CR_VERSION}/chart-releaser_${CR_VERSION}_linux_amd64.tar.gz"
+        tar -xzf cr.tar.gz -C "${CR_TOOL_PATH}"
+        rm -f cr.tar.gz
+
+    - name: Create Helm package
+      run: |
+        cd source
+        helm repo add grafana https://grafana.github.io/helm-charts
+        helm repo add minio https://charts.min.io
+
+        "${CR_TOOL_PATH}/cr" package "${{ steps.parse-chart.outputs.chartpath }}" --config "${CR_CONFIGFILE}" --package-path "${CR_PACKAGE_PATH}"
+
+    - name: Make a release on this repo
+      uses: softprops/action-gh-release@v2
+      with:
+        name: ${{ steps.parse-chart.outputs.tagname }}
+        repository: grafana/meta-monitoring-chart
+        tag_name: ${{ steps.parse-chart.outputs.tagname }}
+        token: ${{ steps.app-token.outputs.token }}
+        generate_release_notes: true
+        files: |
+          ${{ env.CR_PACKAGE_PATH }}/${{ steps.parse-chart.outputs.packagename }}.tgz
+
+    # Note that this creates a release in grafana/helm-charts with a new tag.
+    # The tag name in grafana/helm-charts is <package>-<version>, while the
+    # tag name for grafana/meta-monitoring-chart is <version>.
+    - name: Make release on Helm Charts
+      uses: softprops/action-gh-release@v2
+      with:
+        name: ${{ steps.parse-chart.outputs.packagename }}
+        repository: grafana/helm-charts
+        tag_name: ${{ steps.parse-chart.outputs.packagename }}
+        token: ${{ steps.app-token.outputs.token }}
+        body: |
+          ${{ steps.parse-chart.outputs.desc }}
+
+          Source commit: https://github.com/${{ github.repository }}/commit/${{ github.sha }}
+
+          Tag on source: https://github.com/${{ github.repository }}/releases/tag/${{ steps.parse-chart.outputs.tagname }}
+        files: |
+          ${{ env.CR_PACKAGE_PATH }}/${{ steps.parse-chart.outputs.packagename }}.tgz
+
+    - name: Update helm-charts index.yaml
+      run: |
+        cd helm-charts
+        "${CR_TOOL_PATH}/cr" index --config "${CR_CONFIGFILE}" --token "${{ steps.app-token.outputs.token }}" --index-path "${CR_INDEX_PATH}" --package-path "${CR_PACKAGE_PATH}" --push

.gitignore

@@ -0,0 +1 @@
+.DS_Store

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

README.md

@@ -1,43 +1,50 @@
 # meta-monitoring-chart
 
-This is a meta-monitoring chart for GEL, GEM and GET. It should be installed in a
+This is a meta-monitoring chart for Loki.
-separate namespace next to GEM, GEL or GET installations.
 
-## Preparation
+Note that this is pre-production software at the moment.
-
-Create a values.yaml file based on the [default one](../charts/meta-monitoring/values.yaml).
-
-1. Add or remove the namespaces to monitor in the `namespacesToMonitor` setting
-
-1. Set the cluster name in the `clusterName` setting. This will be added as a label to all logs, metrics and traces.
-
-1. Create a `meta` namespace.
 
 ## Local and cloud modes
 
-The chart has 2 modes: local and cloud. In the local mode logs, metrics and traces are sent
+The chart has 2 modes: local and cloud. In the local mode logs, metrics and/or traces are sent
 to small Loki, Mimir and Tempo installations running in the meta-monitoring namespace.
 
 ![local mode](docs/images/Meta%20monitoring%20local.png)
 
-To enable local mode set `local.enabled` to true.
+To enable local mode set `local.<logs|metrics|traces>.enabled` to true.
 
-In the cloud mode the logs, metrics and traces are sent to
+In the cloud mode the logs, metrics and/or traces are sent to Grafana Cloud.
 
 ![cloud mode](docs/images/Meta%20monitoring%20cloud.png)
 
-To enable cloud mode set `cloud.enabled` to true. The `endpoint`, `username` and `password` settings for your Grafana Cloud logs, metrics and traces instances have to be filled in as well.
+To enable cloud mode set `cloud.<logs|metrics|traces>.enabled` to true. The `endpoint`, `username` and `password` settings for your Grafana Cloud logs, metrics and traces instances have to be filled in as well.
 
-Both modes can be enabled at the same time.
+Both modes can be enabled at the same time. Cloud mode is preferred.
 
 ## Installation
 
-```
-helm install -n meta -f values.yaml meta ./charts/meta-monitoring
-```
-
 For more instructions including how to update the chart go to the [installation](docs/installation.md) page.
 
+## Supported features
+
+- Specify which namespaces are monitored
+- Specify if logs, metrics or traces should be enabled for cloud or local
+- Specify the cluster name used for the logs, metrics and traces
+- Specify PII regexes that are applied to logs before they are sent to Loki (cloud or local). The capture group in the regex is replaced with *****.
+- a Grafana instance is installed (when local mode is used) with the relevant datasources installed. The following dashboards are installed:
+  - logs dashboards
+  - agent dashboards
+- Retention is set to 24 hours
+
+Most of these features are enabled by default. See the values.yaml file for how to enable/disable them.
+
+## Caveats
+
+- This has not been tested on Openshift yet.
+- The underlying Loki, Mimir and Tempo are at the default size installed by the Helm chart. This might need changing when monitoring bigger Loki, Mimir or Tempo installations.
+- MinIO is used as storage at the moment with a limited retention. At the moment this chart cannot be used for monitoring over longer periods.
+- Agent self monitoring is not done at the moment.
+
 ## Developer help topics
 
-- [update dependencies](docs/dev_update_dependencies.md)
+- [update dependencies](docs/dev_update_dependencies.md)

charts/meta-monitoring/Chart.lock

@@ -1,18 +1,18 @@
 dependencies:
 - name: loki
   repository: https://grafana.github.io/helm-charts
-  version: 5.8.0
+  version: 6.5.0
-- name: grafana-agent
+- name: alloy
   repository: https://grafana.github.io/helm-charts
-  version: 0.15.0
+  version: 0.1.1
 - name: mimir-distributed
   repository: https://grafana.github.io/helm-charts
-  version: 4.4.1
+  version: 5.3.0
 - name: tempo-distributed
   repository: https://grafana.github.io/helm-charts
-  version: 1.4.7
+  version: 1.9.9
 - name: minio
   repository: https://charts.min.io
-  version: 5.0.11
+  version: 5.2.0
-digest: sha256:4b04084e6fe821c4d481017b2430f7c8cd782a5d60830dd3a24eb8f10a9ece09
+digest: sha256:5328702b5f6b0487aba8f7bc77d6abfcd5e094569e9205cd725971e3e31255dd
-generated: "2023-06-29T14:25:07.247853+01:00"
+generated: "2024-05-08T07:03:21.797461955Z"

charts/meta-monitoring/Chart.yaml

@@ -1,7 +1,6 @@
 apiVersion: v2
 name: meta-monitoring
 description: A Helm chart for meta monitoring Grafana Loki, Mimir and Tempo
-
 # A chart can be either an 'application' or a 'library' chart.
 #
 # Application charts are a collection of templates that can be packaged into versioned archives
@@ -11,35 +10,32 @@ description: A Helm chart for meta monitoring Grafana Loki, Mimir and Tempo
 # a dependency of application charts to inject those utilities and functions into the rendering
 # pipeline. Library charts do not define any templates and therefore cannot be deployed.
 type: application
-
 # This is the chart version. This version number should be incremented each time you make changes
 # to the chart and its templates, including the app version.
 # Versions are expected to follow Semantic Versioning (https://semver.org/)
-version: 0.0.1
+version: 0.0.2
-
 # This is the version number of the application being deployed. This version number should be
 # incremented each time you make changes to the application. Versions are not expected to
 # follow Semantic Versioning. They should reflect the version the application is using.
 # It is recommended to use it with quotes.
 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"
+  version: 6.5.0
   condition: local.logs.enabled
-- name: grafana-agent
+- name: alloy
-  repository:  https://grafana.github.io/helm-charts
+  repository: https://grafana.github.io/helm-charts
-  version: "0.15.0"
+  version: 0.1.1
 - name: mimir-distributed
-  repository:  https://grafana.github.io/helm-charts
+  repository: https://grafana.github.io/helm-charts
-  version: "4.4.1"
+  version: 5.3.0
   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"
+  version: 1.9.9
   condition: local.traces.enabled
 - name: minio
   repository: https://charts.min.io
-  version: "5.0.11"
+  version: 5.2.0
-  condition: local.minio.enabled
+  condition: local.minio.enabled

charts/meta-monitoring/Makefile

@@ -0,0 +1,7 @@
+.DEFAULT_GOAL := lint
+.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/dashboards/agent.json

@@ -0,0 +1,786 @@
+{
+   "annotations": {
+      "list": [ ]
+   },
+   "editable": true,
+   "gnetId": null,
+   "graphTooltip": 0,
+   "hideControls": false,
+   "links": [ ],
+   "refresh": "30s",
+   "rows": [
+      {
+         "collapse": false,
+         "height": "250px",
+         "panels": [
+            {
+               "aliasColors": { },
+               "bars": false,
+               "dashLength": 10,
+               "dashes": false,
+               "datasource": "$datasource",
+               "fill": 1,
+               "id": 1,
+               "legend": {
+                  "avg": false,
+                  "current": false,
+                  "max": false,
+                  "min": false,
+                  "show": true,
+                  "total": false,
+                  "values": false
+               },
+               "lines": true,
+               "linewidth": 1,
+               "links": [ ],
+               "nullPointMode": "null as zero",
+               "percentage": false,
+               "pointradius": 5,
+               "points": false,
+               "renderer": "flot",
+               "seriesOverrides": [ ],
+               "spaceLength": 10,
+               "span": 12,
+               "stack": false,
+               "steppedLine": false,
+               "styles": [
+                  {
+                     "alias": "Time",
+                     "dateFormat": "YYYY-MM-DD HH:mm:ss",
+                     "pattern": "Time",
+                     "type": "hidden"
+                  },
+                  {
+                     "alias": "Count",
+                     "colorMode": null,
+                     "colors": [ ],
+                     "dateFormat": "YYYY-MM-DD HH:mm:ss",
+                     "decimals": 2,
+                     "link": false,
+                     "linkTargetBlank": false,
+                     "linkTooltip": "Drill down",
+                     "linkUrl": "",
+                     "pattern": "Value #A",
+                     "thresholds": [ ],
+                     "type": "hidden",
+                     "unit": "short"
+                  },
+                  {
+                     "alias": "Uptime",
+                     "colorMode": null,
+                     "colors": [ ],
+                     "dateFormat": "YYYY-MM-DD HH:mm:ss",
+                     "decimals": 2,
+                     "link": false,
+                     "linkTargetBlank": false,
+                     "linkTooltip": "Drill down",
+                     "linkUrl": "",
+                     "pattern": "Value #B",
+                     "thresholds": [ ],
+                     "type": "number",
+                     "unit": "short"
+                  },
+                  {
+                     "alias": "Container",
+                     "colorMode": null,
+                     "colors": [ ],
+                     "dateFormat": "YYYY-MM-DD HH:mm:ss",
+                     "decimals": 2,
+                     "link": false,
+                     "linkTargetBlank": false,
+                     "linkTooltip": "Drill down",
+                     "linkUrl": "",
+                     "pattern": "container",
+                     "thresholds": [ ],
+                     "type": "number",
+                     "unit": "short"
+                  },
+                  {
+                     "alias": "Pod",
+                     "colorMode": null,
+                     "colors": [ ],
+                     "dateFormat": "YYYY-MM-DD HH:mm:ss",
+                     "decimals": 2,
+                     "link": false,
+                     "linkTargetBlank": false,
+                     "linkTooltip": "Drill down",
+                     "linkUrl": "",
+                     "pattern": "pod",
+                     "thresholds": [ ],
+                     "type": "number",
+                     "unit": "short"
+                  },
+                  {
+                     "alias": "Version",
+                     "colorMode": null,
+                     "colors": [ ],
+                     "dateFormat": "YYYY-MM-DD HH:mm:ss",
+                     "decimals": 2,
+                     "link": false,
+                     "linkTargetBlank": false,
+                     "linkTooltip": "Drill down",
+                     "linkUrl": "",
+                     "pattern": "version",
+                     "thresholds": [ ],
+                     "type": "number",
+                     "unit": "short"
+                  },
+                  {
+                     "alias": "",
+                     "colorMode": null,
+                     "colors": [ ],
+                     "dateFormat": "YYYY-MM-DD HH:mm:ss",
+                     "decimals": 2,
+                     "pattern": "/.*/",
+                     "thresholds": [ ],
+                     "type": "string",
+                     "unit": "short"
+                  }
+               ],
+               "targets": [
+                  {
+                     "expr": "count by (pod, container, version) (agent_build_info{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"$container\"})",
+                     "format": "table",
+                     "instant": true,
+                     "intervalFactor": 2,
+                     "legendFormat": "",
+                     "refId": "A",
+                     "step": 10
+                  },
+                  {
+                     "expr": "max by (pod, container) (time() - process_start_time_seconds{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"$container\"})",
+                     "format": "table",
+                     "instant": true,
+                     "intervalFactor": 2,
+                     "legendFormat": "",
+                     "refId": "B",
+                     "step": 10
+                  }
+               ],
+               "thresholds": [ ],
+               "timeFrom": null,
+               "timeShift": null,
+               "title": "Agent Stats",
+               "tooltip": {
+                  "shared": true,
+                  "sort": 2,
+                  "value_type": "individual"
+               },
+               "transform": "table",
+               "type": "table",
+               "xaxis": {
+                  "buckets": null,
+                  "mode": "time",
+                  "name": null,
+                  "show": true,
+                  "values": [ ]
+               },
+               "yaxes": [
+                  {
+                     "format": "short",
+                     "label": null,
+                     "logBase": 1,
+                     "max": null,
+                     "min": 0,
+                     "show": true
+                  },
+                  {
+                     "format": "short",
+                     "label": null,
+                     "logBase": 1,
+                     "max": null,
+                     "min": null,
+                     "show": false
+                  }
+               ]
+            }
+         ],
+         "repeat": null,
+         "repeatIteration": null,
+         "repeatRowId": null,
+         "showTitle": true,
+         "title": "Agent Stats",
+         "titleSize": "h6"
+      },
+      {
+         "collapse": false,
+         "height": "250px",
+         "panels": [
+            {
+               "aliasColors": { },
+               "bars": false,
+               "dashLength": 10,
+               "dashes": false,
+               "datasource": "$datasource",
+               "fill": 1,
+               "id": 2,
+               "legend": {
+                  "avg": false,
+                  "current": false,
+                  "max": false,
+                  "min": false,
+                  "show": true,
+                  "total": false,
+                  "values": false
+               },
+               "lines": true,
+               "linewidth": 1,
+               "links": [ ],
+               "nullPointMode": "null as zero",
+               "percentage": false,
+               "pointradius": 5,
+               "points": false,
+               "renderer": "flot",
+               "seriesOverrides": [ ],
+               "spaceLength": 10,
+               "span": 6,
+               "stack": false,
+               "steppedLine": false,
+               "targets": [
+                  {
+                     "expr": "sum(rate(prometheus_target_sync_length_seconds_sum{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"$container\"}[5m])) by (pod, scrape_job) * 1e3",
+                     "format": "time_series",
+                     "intervalFactor": 2,
+                     "legendFormat": "{{pod}}/{{scrape_job}}",
+                     "legendLink": null,
+                     "step": 10
+                  }
+               ],
+               "thresholds": [ ],
+               "timeFrom": null,
+               "timeShift": null,
+               "title": "Target Sync",
+               "tooltip": {
+                  "shared": true,
+                  "sort": 2,
+                  "value_type": "individual"
+               },
+               "type": "graph",
+               "xaxis": {
+                  "buckets": null,
+                  "mode": "time",
+                  "name": null,
+                  "show": true,
+                  "values": [ ]
+               },
+               "yaxes": [
+                  {
+                     "format": "ms",
+                     "label": null,
+                     "logBase": 1,
+                     "max": null,
+                     "min": 0,
+                     "show": true
+                  },
+                  {
+                     "format": "short",
+                     "label": null,
+                     "logBase": 1,
+                     "max": null,
+                     "min": null,
+                     "show": false
+                  }
+               ]
+            },
+            {
+               "aliasColors": { },
+               "bars": false,
+               "dashLength": 10,
+               "dashes": false,
+               "datasource": "$datasource",
+               "fill": 10,
+               "id": 3,
+               "legend": {
+                  "avg": false,
+                  "current": false,
+                  "max": false,
+                  "min": false,
+                  "show": true,
+                  "total": false,
+                  "values": false
+               },
+               "lines": true,
+               "linewidth": 0,
+               "links": [ ],
+               "nullPointMode": "null as zero",
+               "percentage": false,
+               "pointradius": 5,
+               "points": false,
+               "renderer": "flot",
+               "seriesOverrides": [ ],
+               "spaceLength": 10,
+               "span": 6,
+               "stack": true,
+               "steppedLine": false,
+               "targets": [
+                  {
+                     "expr": "sum by (pod) (prometheus_sd_discovered_targets{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"$container\"})",
+                     "format": "time_series",
+                     "intervalFactor": 2,
+                     "legendFormat": "{{pod}}",
+                     "legendLink": null,
+                     "step": 10
+                  }
+               ],
+               "thresholds": [ ],
+               "timeFrom": null,
+               "timeShift": null,
+               "title": "Targets",
+               "tooltip": {
+                  "shared": true,
+                  "sort": 2,
+                  "value_type": "individual"
+               },
+               "type": "graph",
+               "xaxis": {
+                  "buckets": null,
+                  "mode": "time",
+                  "name": null,
+                  "show": true,
+                  "values": [ ]
+               },
+               "yaxes": [
+                  {
+                     "format": "short",
+                     "label": null,
+                     "logBase": 1,
+                     "max": null,
+                     "min": 0,
+                     "show": true
+                  },
+                  {
+                     "format": "short",
+                     "label": null,
+                     "logBase": 1,
+                     "max": null,
+                     "min": null,
+                     "show": false
+                  }
+               ]
+            }
+         ],
+         "repeat": null,
+         "repeatIteration": null,
+         "repeatRowId": null,
+         "showTitle": true,
+         "title": "Prometheus Discovery",
+         "titleSize": "h6"
+      },
+      {
+         "collapse": false,
+         "height": "250px",
+         "panels": [
+            {
+               "aliasColors": { },
+               "bars": false,
+               "dashLength": 10,
+               "dashes": false,
+               "datasource": "$datasource",
+               "fill": 1,
+               "id": 4,
+               "legend": {
+                  "avg": false,
+                  "current": false,
+                  "max": false,
+                  "min": false,
+                  "show": true,
+                  "total": false,
+                  "values": false
+               },
+               "lines": true,
+               "linewidth": 1,
+               "links": [ ],
+               "nullPointMode": "null as zero",
+               "percentage": false,
+               "pointradius": 5,
+               "points": false,
+               "renderer": "flot",
+               "seriesOverrides": [ ],
+               "spaceLength": 10,
+               "span": 4,
+               "stack": false,
+               "steppedLine": false,
+               "targets": [
+                  {
+                     "expr": "rate(prometheus_target_interval_length_seconds_sum{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"$container\"}[5m])\n/\nrate(prometheus_target_interval_length_seconds_count{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"$container\"}[5m])\n* 1e3\n",
+                     "format": "time_series",
+                     "intervalFactor": 2,
+                     "legendFormat": "{{pod}} {{interval}} configured",
+                     "legendLink": null,
+                     "step": 10
+                  }
+               ],
+               "thresholds": [ ],
+               "timeFrom": null,
+               "timeShift": null,
+               "title": "Average Scrape Interval Duration",
+               "tooltip": {
+                  "shared": true,
+                  "sort": 2,
+                  "value_type": "individual"
+               },
+               "type": "graph",
+               "xaxis": {
+                  "buckets": null,
+                  "mode": "time",
+                  "name": null,
+                  "show": true,
+                  "values": [ ]
+               },
+               "yaxes": [
+                  {
+                     "format": "ms",
+                     "label": null,
+                     "logBase": 1,
+                     "max": null,
+                     "min": 0,
+                     "show": true
+                  },
+                  {
+                     "format": "short",
+                     "label": null,
+                     "logBase": 1,
+                     "max": null,
+                     "min": null,
+                     "show": false
+                  }
+               ]
+            },
+            {
+               "aliasColors": { },
+               "bars": false,
+               "dashLength": 10,
+               "dashes": false,
+               "datasource": "$datasource",
+               "fill": 10,
+               "id": 5,
+               "legend": {
+                  "avg": false,
+                  "current": false,
+                  "max": false,
+                  "min": false,
+                  "show": true,
+                  "total": false,
+                  "values": false
+               },
+               "lines": true,
+               "linewidth": 0,
+               "links": [ ],
+               "nullPointMode": "null as zero",
+               "percentage": false,
+               "pointradius": 5,
+               "points": false,
+               "renderer": "flot",
+               "seriesOverrides": [ ],
+               "spaceLength": 10,
+               "span": 4,
+               "stack": true,
+               "steppedLine": false,
+               "targets": [
+                  {
+                     "expr": "sum by (job) (rate(prometheus_target_scrapes_exceeded_sample_limit_total{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"$container\"}[1m]))",
+                     "format": "time_series",
+                     "intervalFactor": 2,
+                     "legendFormat": "exceeded sample limit: {{job}}",
+                     "legendLink": null,
+                     "step": 10
+                  },
+                  {
+                     "expr": "sum by (job) (rate(prometheus_target_scrapes_sample_duplicate_timestamp_total{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"$container\"}[1m]))",
+                     "format": "time_series",
+                     "intervalFactor": 2,
+                     "legendFormat": "duplicate timestamp: {{job}}",
+                     "legendLink": null,
+                     "step": 10
+                  },
+                  {
+                     "expr": "sum by (job) (rate(prometheus_target_scrapes_sample_out_of_bounds_total{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"$container\"}[1m]))",
+                     "format": "time_series",
+                     "intervalFactor": 2,
+                     "legendFormat": "out of bounds: {{job}}",
+                     "legendLink": null,
+                     "step": 10
+                  },
+                  {
+                     "expr": "sum by (job) (rate(prometheus_target_scrapes_sample_out_of_order_total{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"$container\"}[1m]))",
+                     "format": "time_series",
+                     "intervalFactor": 2,
+                     "legendFormat": "out of order: {{job}}",
+                     "legendLink": null,
+                     "step": 10
+                  }
+               ],
+               "thresholds": [ ],
+               "timeFrom": null,
+               "timeShift": null,
+               "title": "Scrape failures",
+               "tooltip": {
+                  "shared": true,
+                  "sort": 2,
+                  "value_type": "individual"
+               },
+               "type": "graph",
+               "xaxis": {
+                  "buckets": null,
+                  "mode": "time",
+                  "name": null,
+                  "show": true,
+                  "values": [ ]
+               },
+               "yaxes": [
+                  {
+                     "format": "short",
+                     "label": null,
+                     "logBase": 1,
+                     "max": null,
+                     "min": 0,
+                     "show": true
+                  },
+                  {
+                     "format": "short",
+                     "label": null,
+                     "logBase": 1,
+                     "max": null,
+                     "min": null,
+                     "show": false
+                  }
+               ]
+            },
+            {
+               "aliasColors": { },
+               "bars": false,
+               "dashLength": 10,
+               "dashes": false,
+               "datasource": "$datasource",
+               "fill": 10,
+               "id": 6,
+               "legend": {
+                  "avg": false,
+                  "current": false,
+                  "max": false,
+                  "min": false,
+                  "show": true,
+                  "total": false,
+                  "values": false
+               },
+               "lines": true,
+               "linewidth": 0,
+               "links": [ ],
+               "nullPointMode": "null as zero",
+               "percentage": false,
+               "pointradius": 5,
+               "points": false,
+               "renderer": "flot",
+               "seriesOverrides": [ ],
+               "spaceLength": 10,
+               "span": 4,
+               "stack": true,
+               "steppedLine": false,
+               "targets": [
+                  {
+                     "expr": "sum by (job, instance_group_name) (rate(agent_wal_samples_appended_total{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"$container\"}[5m]))",
+                     "format": "time_series",
+                     "intervalFactor": 2,
+                     "legendFormat": "{{job}} {{instance_group_name}}",
+                     "legendLink": null,
+                     "step": 10
+                  }
+               ],
+               "thresholds": [ ],
+               "timeFrom": null,
+               "timeShift": null,
+               "title": "Appended Samples",
+               "tooltip": {
+                  "shared": true,
+                  "sort": 2,
+                  "value_type": "individual"
+               },
+               "type": "graph",
+               "xaxis": {
+                  "buckets": null,
+                  "mode": "time",
+                  "name": null,
+                  "show": true,
+                  "values": [ ]
+               },
+               "yaxes": [
+                  {
+                     "format": "short",
+                     "label": null,
+                     "logBase": 1,
+                     "max": null,
+                     "min": 0,
+                     "show": true
+                  },
+                  {
+                     "format": "short",
+                     "label": null,
+                     "logBase": 1,
+                     "max": null,
+                     "min": null,
+                     "show": false
+                  }
+               ]
+            }
+         ],
+         "repeat": null,
+         "repeatIteration": null,
+         "repeatRowId": null,
+         "showTitle": true,
+         "title": "Prometheus Retrieval",
+         "titleSize": "h6"
+      }
+   ],
+   "schemaVersion": 14,
+   "style": "dark",
+   "tags": [
+      "grafana-agent-mixin"
+   ],
+   "templating": {
+      "list": [
+         {
+            "current": {
+               "text": "default",
+               "value": "default"
+            },
+            "hide": 0,
+            "label": "Data Source",
+            "name": "datasource",
+            "options": [ ],
+            "query": "prometheus",
+            "refresh": 1,
+            "regex": "",
+            "type": "datasource"
+         },
+         {
+            "allValue": ".+",
+            "current": {
+               "selected": true,
+               "text": "All",
+               "value": "$__all"
+            },
+            "datasource": "$datasource",
+            "hide": 0,
+            "includeAll": true,
+            "label": "cluster",
+            "multi": true,
+            "name": "cluster",
+            "options": [ ],
+            "query": "label_values(agent_build_info, cluster)",
+            "refresh": 1,
+            "regex": "",
+            "sort": 2,
+            "tagValuesQuery": "",
+            "tags": [ ],
+            "tagsQuery": "",
+            "type": "query",
+            "useTags": false
+         },
+         {
+            "allValue": ".+",
+            "current": {
+               "selected": true,
+               "text": "All",
+               "value": "$__all"
+            },
+            "datasource": "$datasource",
+            "hide": 0,
+            "includeAll": true,
+            "label": "namespace",
+            "multi": true,
+            "name": "namespace",
+            "options": [ ],
+            "query": "label_values(agent_build_info, namespace)",
+            "refresh": 1,
+            "regex": "",
+            "sort": 2,
+            "tagValuesQuery": "",
+            "tags": [ ],
+            "tagsQuery": "",
+            "type": "query",
+            "useTags": false
+         },
+         {
+            "allValue": ".+",
+            "current": {
+               "selected": true,
+               "text": "All",
+               "value": "$__all"
+            },
+            "datasource": "$datasource",
+            "hide": 0,
+            "includeAll": true,
+            "label": "container",
+            "multi": true,
+            "name": "container",
+            "options": [ ],
+            "query": "label_values(agent_build_info, container)",
+            "refresh": 1,
+            "regex": "",
+            "sort": 2,
+            "tagValuesQuery": "",
+            "tags": [ ],
+            "tagsQuery": "",
+            "type": "query",
+            "useTags": false
+         },
+         {
+            "allValue": "grafana-agent-.*",
+            "current": {
+               "selected": true,
+               "text": "All",
+               "value": "$__all"
+            },
+            "datasource": "$datasource",
+            "hide": 0,
+            "includeAll": true,
+            "label": "pod",
+            "multi": true,
+            "name": "pod",
+            "options": [ ],
+            "query": "label_values(agent_build_info{container=~\"$container\"}, pod)",
+            "refresh": 1,
+            "regex": "",
+            "sort": 2,
+            "tagValuesQuery": "",
+            "tags": [ ],
+            "tagsQuery": "",
+            "type": "query",
+            "useTags": false
+         }
+      ]
+   },
+   "time": {
+      "from": "now-1h",
+      "to": "now"
+   },
+   "timepicker": {
+      "refresh_intervals": [
+         "5s",
+         "10s",
+         "30s",
+         "1m",
+         "5m",
+         "15m",
+         "30m",
+         "1h",
+         "2h",
+         "1d"
+      ],
+      "time_options": [
+         "5m",
+         "15m",
+         "1h",
+         "6h",
+         "12h",
+         "24h",
+         "2d",
+         "7d",
+         "30d"
+      ]
+   },
+   "timezone": "",
+   "title": "Agent",
+   "uid": "",
+   "version": 0
+}

charts/meta-monitoring/src/dashboards/loki-deletion.json

@@ -35,6 +35,7 @@
                   "fill": 1,
                   "format": "none",
                   "id": 1,
+                  "interval": "1m",
                   "legend": {
                      "avg": false,
                      "current": false,
@@ -62,7 +63,6 @@
                         "expr": "sum(loki_compactor_pending_delete_requests_count{cluster=~\"$cluster\", namespace=~\"$namespace\"})",
                         "format": "time_series",
                         "instant": true,
-                        "intervalFactor": 2,
                         "refId": "A"
                      }
                   ],
@@ -111,6 +111,7 @@
                   "fill": 1,
                   "format": "dtdurations",
                   "id": 2,
+                  "interval": "1m",
                   "legend": {
                      "avg": false,
                      "current": false,
@@ -138,7 +139,6 @@
                         "expr": "max(loki_compactor_oldest_pending_delete_request_age_seconds{cluster=~\"$cluster\", namespace=~\"$namespace\"})",
                         "format": "time_series",
                         "instant": true,
-                        "intervalFactor": 2,
                         "refId": "A"
                      }
                   ],
@@ -191,156 +191,148 @@
             "height": "250px",
             "panels": [
                {
-                  "aliasColors": { },
-                  "bars": false,
-                  "dashLength": 10,
-                  "dashes": false,
                   "datasource": "$datasource",
-                  "fill": 1,
+                  "fieldConfig": {
-                  "id": 3,
+                     "defaults": {
-                  "legend": {
+                        "custom": {
-                     "avg": false,
+                           "drawStyle": "line",
-                     "current": false,
+                           "fillOpacity": 10,
-                     "max": false,
+                           "lineWidth": 1,
-                     "min": false,
+                           "pointSize": 5,
-                     "show": true,
+                           "showPoints": "never",
-                     "total": false,
+                           "spanNulls": false,
-                     "values": false
+                           "stacking": {
+                              "group": "A",
+                              "mode": "none"
+                           }
+                        },
+                        "thresholds": {
+                           "mode": "absolute",
+                           "steps": [ ]
+                        },
+                        "unit": "short"
+                     },
+                     "overrides": [ ]
                   },
-                  "lines": true,
+                  "id": 3,
-                  "linewidth": 1,
+                  "interval": "1m",
                   "links": [ ],
-                  "nullPointMode": "null as zero",
+                  "options": {
-                  "percentage": false,
+                     "legend": {
-                  "pointradius": 5,
+                        "showLegend": true
-                  "points": false,
+                     },
-                  "renderer": "flot",
+                     "tooltip": {
-                  "seriesOverrides": [ ],
+                        "mode": "single",
-                  "spaceLength": 10,
+                        "sort": "none"
-                  "span": 6,
+                     }
-                  "stack": false,
+                  },
-                  "steppedLine": false,
+                  "span": 4,
+                  "targets": [
+                     {
+                        "expr": "(loki_compactor_delete_requests_received_total{cluster=~\"$cluster\", namespace=~\"$namespace\"} or on() vector(0)) - on () (loki_compactor_delete_requests_processed_total{cluster=~\"$cluster\", namespace=~\"$namespace\"} or on () vector(0))",
+                        "format": "time_series",
+                        "legendFormat": "in progress",
+                        "legendLink": null
+                     }
+                  ],
+                  "title": "# of Delete Requests (received - processed) ",
+                  "type": "timeseries"
+               },
+               {
+                  "datasource": "$datasource",
+                  "fieldConfig": {
+                     "defaults": {
+                        "custom": {
+                           "drawStyle": "line",
+                           "fillOpacity": 10,
+                           "lineWidth": 1,
+                           "pointSize": 5,
+                           "showPoints": "never",
+                           "spanNulls": false,
+                           "stacking": {
+                              "group": "A",
+                              "mode": "none"
+                           }
+                        },
+                        "thresholds": {
+                           "mode": "absolute",
+                           "steps": [ ]
+                        },
+                        "unit": "short"
+                     },
+                     "overrides": [ ]
+                  },
+                  "id": 4,
+                  "interval": "1m",
+                  "links": [ ],
+                  "options": {
+                     "legend": {
+                        "showLegend": true
+                     },
+                     "tooltip": {
+                        "mode": "single",
+                        "sort": "none"
+                     }
+                  },
+                  "span": 4,
                   "targets": [
                      {
                         "expr": "sum(increase(loki_compactor_delete_requests_received_total{cluster=~\"$cluster\", namespace=~\"$namespace\"}[1d]))",
                         "format": "time_series",
-                        "intervalFactor": 2,
                         "legendFormat": "received",
-                        "legendLink": null,
+                        "legendLink": null
-                        "step": 10
                      }
                   ],
-                  "thresholds": [ ],
-                  "timeFrom": null,
-                  "timeShift": null,
                   "title": "Delete Requests Received / Day",
-                  "tooltip": {
+                  "type": "timeseries"
-                     "shared": true,
-                     "sort": 2,
-                     "value_type": "individual"
-                  },
-                  "type": "graph",
-                  "xaxis": {
-                     "buckets": null,
-                     "mode": "time",
-                     "name": null,
-                     "show": true,
-                     "values": [ ]
-                  },
-                  "yaxes": [
-                     {
-                        "format": "short",
-                        "label": null,
-                        "logBase": 1,
-                        "max": null,
-                        "min": 0,
-                        "show": true
-                     },
-                     {
-                        "format": "short",
-                        "label": null,
-                        "logBase": 1,
-                        "max": null,
-                        "min": null,
-                        "show": false
-                     }
-                  ]
                },
                {
-                  "aliasColors": { },
-                  "bars": false,
-                  "dashLength": 10,
-                  "dashes": false,
                   "datasource": "$datasource",
-                  "fill": 1,
+                  "fieldConfig": {
-                  "id": 4,
+                     "defaults": {
-                  "legend": {
+                        "custom": {
-                     "avg": false,
+                           "drawStyle": "line",
-                     "current": false,
+                           "fillOpacity": 10,
-                     "max": false,
+                           "lineWidth": 1,
-                     "min": false,
+                           "pointSize": 5,
-                     "show": true,
+                           "showPoints": "never",
-                     "total": false,
+                           "spanNulls": false,
-                     "values": false
+                           "stacking": {
+                              "group": "A",
+                              "mode": "none"
+                           }
+                        },
+                        "thresholds": {
+                           "mode": "absolute",
+                           "steps": [ ]
+                        },
+                        "unit": "short"
+                     },
+                     "overrides": [ ]
                   },
-                  "lines": true,
+                  "id": 5,
-                  "linewidth": 1,
+                  "interval": "1m",
                   "links": [ ],
-                  "nullPointMode": "null as zero",
+                  "options": {
-                  "percentage": false,
+                     "legend": {
-                  "pointradius": 5,
+                        "showLegend": true
-                  "points": false,
+                     },
-                  "renderer": "flot",
+                     "tooltip": {
-                  "seriesOverrides": [ ],
+                        "mode": "single",
-                  "spaceLength": 10,
+                        "sort": "none"
-                  "span": 6,
+                     }
-                  "stack": false,
+                  },
-                  "steppedLine": false,
+                  "span": 4,
                   "targets": [
                      {
                         "expr": "sum(increase(loki_compactor_delete_requests_processed_total{cluster=~\"$cluster\", namespace=~\"$namespace\"}[1d]))",
                         "format": "time_series",
-                        "intervalFactor": 2,
                         "legendFormat": "processed",
-                        "legendLink": null,
+                        "legendLink": null
-                        "step": 10
                      }
                   ],
-                  "thresholds": [ ],
-                  "timeFrom": null,
-                  "timeShift": null,
                   "title": "Delete Requests Processed / Day",
-                  "tooltip": {
+                  "type": "timeseries"
-                     "shared": true,
-                     "sort": 2,
-                     "value_type": "individual"
-                  },
-                  "type": "graph",
-                  "xaxis": {
-                     "buckets": null,
-                     "mode": "time",
-                     "name": null,
-                     "show": true,
-                     "values": [ ]
-                  },
-                  "yaxes": [
-                     {
-                        "format": "short",
-                        "label": null,
-                        "logBase": 1,
-                        "max": null,
-                        "min": 0,
-                        "show": true
-                     },
-                     {
-                        "format": "short",
-                        "label": null,
-                        "logBase": 1,
-                        "max": null,
-                        "min": null,
-                        "show": false
-                     }
-                  ]
                }
             ],
             "repeat": null,
@@ -355,87 +347,155 @@
             "height": "250px",
             "panels": [
                {
-                  "aliasColors": { },
-                  "bars": false,
-                  "dashLength": 10,
-                  "dashes": false,
                   "datasource": "$datasource",
-                  "fill": 1,
+                  "fieldConfig": {
-                  "id": 5,
+                     "defaults": {
-                  "legend": {
+                        "custom": {
-                     "avg": false,
+                           "drawStyle": "line",
-                     "current": false,
+                           "fillOpacity": 10,
-                     "max": false,
+                           "lineWidth": 1,
-                     "min": false,
+                           "pointSize": 5,
-                     "show": true,
+                           "showPoints": "never",
-                     "total": false,
+                           "spanNulls": false,
-                     "values": false
+                           "stacking": {
+                              "group": "A",
+                              "mode": "none"
+                           }
+                        },
+                        "thresholds": {
+                           "mode": "absolute",
+                           "steps": [ ]
+                        },
+                        "unit": "short"
+                     },
+                     "overrides": [ ]
                   },
-                  "lines": true,
+                  "id": 6,
-                  "linewidth": 1,
+                  "interval": "1m",
                   "links": [ ],
-                  "nullPointMode": "null as zero",
+                  "options": {
-                  "percentage": false,
+                     "legend": {
-                  "pointradius": 5,
+                        "showLegend": true
-                  "points": false,
+                     },
-                  "renderer": "flot",
+                     "tooltip": {
-                  "seriesOverrides": [ ],
+                        "mode": "single",
-                  "spaceLength": 10,
+                        "sort": "none"
-                  "span": 12,
+                     }
-                  "stack": false,
+                  },
-                  "steppedLine": false,
+                  "span": 4,
                   "targets": [
                      {
-                        "expr": "sum(increase(loki_compactor_load_pending_requests_attempts_total{status=\"fail\", cluster=~\"$cluster\", namespace=~\"$namespace\"}[1h]))",
+                        "expr": "node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=~\"$cluster\", namespace=~\"$namespace\", container=\"compactor\"}",
                         "format": "time_series",
-                        "intervalFactor": 2,
+                        "legendFormat": "{{pod}}",
-                        "legendFormat": "failures",
+                        "legendLink": null
-                        "legendLink": null,
-                        "step": 10
                      }
                   ],
-                  "thresholds": [ ],
+                  "title": "Compactor CPU usage",
-                  "timeFrom": null,
+                  "type": "timeseries"
-                  "timeShift": null,
+               },
-                  "title": "Failures in Loading Delete Requests / Hour",
+               {
-                  "tooltip": {
+                  "datasource": "$datasource",
-                     "shared": true,
+                  "fieldConfig": {
-                     "sort": 2,
+                     "defaults": {
-                     "value_type": "individual"
+                        "custom": {
-                  },
+                           "drawStyle": "line",
-                  "type": "graph",
+                           "fillOpacity": 10,
-                  "xaxis": {
+                           "lineWidth": 1,
-                     "buckets": null,
+                           "pointSize": 5,
-                     "mode": "time",
+                           "showPoints": "never",
-                     "name": null,
+                           "spanNulls": false,
-                     "show": true,
+                           "stacking": {
-                     "values": [ ]
+                              "group": "A",
-                  },
+                              "mode": "none"
-                  "yaxes": [
+                           }
-                     {
+                        },
-                        "format": "short",
+                        "thresholds": {
-                        "label": null,
+                           "mode": "absolute",
-                        "logBase": 1,
+                           "steps": [ ]
-                        "max": null,
+                        },
-                        "min": 0,
+                        "unit": "short"
-                        "show": true
                      },
-                     {
+                     "overrides": [ ]
-                        "format": "short",
+                  },
-                        "label": null,
+                  "id": 7,
-                        "logBase": 1,
+                  "interval": "1m",
-                        "max": null,
+                  "links": [ ],
-                        "min": null,
+                  "options": {
-                        "show": false
+                     "legend": {
+                        "showLegend": true
+                     },
+                     "tooltip": {
+                        "mode": "single",
+                        "sort": "none"
                      }
-                  ]
+                  },
+                  "span": 4,
+                  "targets": [
+                     {
+                        "expr": "go_memstats_heap_inuse_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\", container=\"compactor\"} / 1024 / 1024 ",
+                        "format": "time_series",
+                        "legendFormat": " {{pod}} ",
+                        "legendLink": null
+                     }
+                  ],
+                  "title": "Compactor memory usage (MiB)",
+                  "type": "timeseries"
+               },
+               {
+                  "datasource": "$datasource",
+                  "fieldConfig": {
+                     "defaults": {
+                        "custom": {
+                           "drawStyle": "line",
+                           "fillOpacity": 10,
+                           "lineWidth": 1,
+                           "pointSize": 5,
+                           "showPoints": "never",
+                           "spanNulls": false,
+                           "stacking": {
+                              "group": "A",
+                              "mode": "none"
+                           }
+                        },
+                        "thresholds": {
+                           "mode": "absolute",
+                           "steps": [ ]
+                        },
+                        "unit": "short"
+                     },
+                     "overrides": [ ]
+                  },
+                  "id": 8,
+                  "interval": "1m",
+                  "links": [ ],
+                  "options": {
+                     "legend": {
+                        "showLegend": true
+                     },
+                     "tooltip": {
+                        "mode": "single",
+                        "sort": "none"
+                     }
+                  },
+                  "span": 4,
+                  "targets": [
+                     {
+                        "expr": "loki_boltdb_shipper_compact_tables_operation_duration_seconds{cluster=~\"$cluster\", namespace=~\"$namespace\"}",
+                        "format": "time_series",
+                        "legendFormat": "{{pod}}",
+                        "legendLink": null
+                     }
+                  ],
+                  "title": "Compaction run duration (seconds)",
+                  "type": "timeseries"
                }
             ],
             "repeat": null,
             "repeatIteration": null,
             "repeatRowId": null,
             "showTitle": true,
-            "title": "Failures",
+            "title": "Compactor",
             "titleSize": "h6"
          },
          {
@@ -443,87 +503,147 @@
             "height": "250px",
             "panels": [
                {
-                  "aliasColors": { },
-                  "bars": false,
-                  "dashLength": 10,
-                  "dashes": false,
                   "datasource": "$datasource",
-                  "fill": 1,
+                  "fieldConfig": {
-                  "id": 6,
+                     "defaults": {
-                  "legend": {
+                        "custom": {
-                     "avg": false,
+                           "drawStyle": "line",
-                     "current": false,
+                           "fillOpacity": 10,
-                     "max": false,
+                           "lineWidth": 1,
-                     "min": false,
+                           "pointSize": 5,
-                     "show": true,
+                           "showPoints": "never",
-                     "total": false,
+                           "spanNulls": false,
-                     "values": false
+                           "stacking": {
+                              "group": "A",
+                              "mode": "none"
+                           }
+                        },
+                        "thresholds": {
+                           "mode": "absolute",
+                           "steps": [ ]
+                        },
+                        "unit": "short"
+                     },
+                     "overrides": [ ]
                   },
-                  "lines": true,
+                  "id": 9,
-                  "linewidth": 1,
+                  "interval": "1m",
                   "links": [ ],
-                  "nullPointMode": "null as zero",
+                  "options": {
-                  "percentage": false,
+                     "legend": {
-                  "pointradius": 5,
+                        "showLegend": true
-                  "points": false,
+                     },
-                  "renderer": "flot",
+                     "tooltip": {
-                  "seriesOverrides": [ ],
+                        "mode": "single",
-                  "spaceLength": 10,
+                        "sort": "none"
-                  "span": 12,
+                     }
-                  "stack": false,
+                  },
-                  "steppedLine": false,
+                  "span": 6,
                   "targets": [
                      {
-                        "expr": "sum(rate(loki_compactor_deleted_lines{cluster=~\"$cluster\",job=~\"$namespace/(loki|enterprise-logs)-read\"}[$__rate_interval])) by (user)",
+                        "expr": "sum(increase(loki_compactor_load_pending_requests_attempts_total{status=\"fail\", cluster=~\"$cluster\", namespace=~\"$namespace\"}[1h]))",
                         "format": "time_series",
-                        "intervalFactor": 2,
+                        "legendFormat": "failures",
-                        "legendFormat": "{{user}}",
+                        "legendLink": null
-                        "legendLink": null,
-                        "step": 10
                      }
                   ],
-                  "thresholds": [ ],
+                  "title": "Failures in Loading Delete Requests / Hour",
-                  "timeFrom": null,
+                  "type": "timeseries"
-                  "timeShift": null,
+               },
-                  "title": "Lines Deleted / Sec",
+               {
-                  "tooltip": {
+                  "datasource": "$datasource",
-                     "shared": true,
+                  "fieldConfig": {
-                     "sort": 2,
+                     "defaults": {
-                     "value_type": "individual"
+                        "custom": {
-                  },
+                           "drawStyle": "line",
-                  "type": "graph",
+                           "fillOpacity": 10,
-                  "xaxis": {
+                           "lineWidth": 1,
-                     "buckets": null,
+                           "pointSize": 5,
-                     "mode": "time",
+                           "showPoints": "never",
-                     "name": null,
+                           "spanNulls": false,
-                     "show": true,
+                           "stacking": {
-                     "values": [ ]
+                              "group": "A",
-                  },
+                              "mode": "none"
-                  "yaxes": [
+                           }
-                     {
+                        },
-                        "format": "short",
+                        "thresholds": {
-                        "label": null,
+                           "mode": "absolute",
-                        "logBase": 1,
+                           "steps": [ ]
-                        "max": null,
+                        },
-                        "min": 0,
+                        "unit": "short"
-                        "show": true
                      },
-                     {
+                     "overrides": [ ]
-                        "format": "short",
+                  },
-                        "label": null,
+                  "id": 10,
-                        "logBase": 1,
+                  "interval": "1m",
-                        "max": null,
+                  "links": [ ],
-                        "min": null,
+                  "options": {
-                        "show": false
+                     "legend": {
+                        "showLegend": true
+                     },
+                     "tooltip": {
+                        "mode": "single",
+                        "sort": "none"
                      }
-                  ]
+                  },
+                  "span": 6,
+                  "targets": [
+                     {
+                        "expr": "sum(rate(loki_compactor_deleted_lines{cluster=~\"$cluster\", namespace=~\"$namespace\", pod=~\"(.*/compactor|(loki|enterprise-logs)-backend.*|loki-single-binary)\"}[$__rate_interval])) by (user)",
+                        "format": "time_series",
+                        "legendFormat": "{{user}}",
+                        "legendLink": null
+                     }
+                  ],
+                  "title": "Lines Deleted / Sec",
+                  "type": "timeseries"
                }
             ],
             "repeat": null,
             "repeatIteration": null,
             "repeatRowId": null,
             "showTitle": true,
-            "title": "Deleted lines",
+            "title": "Deletion metrics",
+            "titleSize": "h6"
+         },
+         {
+            "collapse": false,
+            "height": "250px",
+            "panels": [
+               {
+                  "datasource": "$loki_datasource",
+                  "id": 11,
+                  "interval": "1m",
+                  "span": 6,
+                  "targets": [
+                     {
+                        "expr": "{cluster=~\"$cluster\", namespace=~\"$namespace\", pod=~\"(.*/compactor|(loki|enterprise-logs)-backend.*|loki-single-binary)\"} |~ \"Started processing delete request|delete request for user marked as processed\" | logfmt | line_format \"{{.ts}} user={{.user}} delete_request_id={{.delete_request_id}} msg={{.msg}}\" ",
+                        "refId": "A"
+                     }
+                  ],
+                  "title": "In progress/finished",
+                  "type": "logs"
+               },
+               {
+                  "datasource": "$loki_datasource",
+                  "id": 12,
+                  "interval": "1m",
+                  "span": 6,
+                  "targets": [
+                     {
+                        "expr": "{cluster=~\"$cluster\", namespace=~\"$namespace\", pod=~\"(.*/compactor|(loki|enterprise-logs)-backend.*|loki-single-binary)\"} |~ \"delete request for user added\" | logfmt | line_format \"{{.ts}} user={{.user}} query='{{.query}}'\"",
+                        "refId": "A"
+                     }
+                  ],
+                  "title": "Requests",
+                  "type": "logs"
+               }
+            ],
+            "repeat": null,
+            "repeatIteration": null,
+            "repeatRowId": null,
+            "showTitle": true,
+            "title": "List of deletion requests",
             "titleSize": "h6"
          }
       ],
@@ -540,7 +660,7 @@
                   "value": "default"
                },
                "hide": 0,
-               "label": "Data Source",
+               "label": "Data source",
                "name": "datasource",
                "options": [ ],
                "query": "prometheus",
@@ -593,6 +713,16 @@
                "tagsQuery": "",
                "type": "query",
                "useTags": false
+            },
+            {
+               "hide": 0,
+               "label": null,
+               "name": "loki_datasource",
+               "options": [ ],
+               "query": "loki",
+               "refresh": 1,
+               "regex": "",
+               "type": "datasource"
             }
          ]
       },

charts/meta-monitoring/src/dashboards/loki-logs.json

@@ -6,7 +6,6 @@
       "gnetId": null,
       "graphTooltip": 0,
       "hideControls": false,
-      "id": 8,
       "iteration": 1583185057230,
       "links": [
          {
@@ -39,6 +38,7 @@
             },
             "hiddenSeries": false,
             "id": 35,
+            "interval": "1m",
             "legend": {
                "avg": false,
                "current": false,
@@ -78,7 +78,7 @@
                "sort": 0,
                "value_type": "individual"
             },
-            "type": "graph",
+            "type": "timeseries",
             "xaxis": {
                "buckets": null,
                "mode": "time",
@@ -115,6 +115,11 @@
             "dashLength": 10,
             "dashes": false,
             "datasource": "$datasource",
+            "fieldConfig": {
+               "defaults": {
+                  "unit": "s"
+               }
+            },
             "fill": 1,
             "fillGradient": 0,
             "gridPos": {
@@ -125,6 +130,7 @@
             },
             "hiddenSeries": false,
             "id": 41,
+            "interval": "1m",
             "legend": {
                "avg": false,
                "current": false,
@@ -165,7 +171,7 @@
                "sort": 0,
                "value_type": "individual"
             },
-            "type": "graph",
+            "type": "timeseries",
             "xaxis": {
                "buckets": null,
                "mode": "time",
@@ -212,6 +218,7 @@
             },
             "hiddenSeries": false,
             "id": 36,
+            "interval": "1m",
             "legend": {
                "avg": false,
                "current": false,
@@ -237,7 +244,7 @@
             "steppedLine": false,
             "targets": [
                {
-                  "expr": "sum(rate(container_cpu_usage_seconds_total{cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"$deployment.*\", pod=~\"$pod\", container=~\"$container\"}[5m]))",
+                  "expr": "sum(rate(container_cpu_usage_seconds_total{cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"$deployment.*\", pod=~\"$pod\", container=~\"$container\"}[$__rate_interval]))",
                   "refId": "A"
                }
             ],
@@ -251,7 +258,7 @@
                "sort": 0,
                "value_type": "individual"
             },
-            "type": "graph",
+            "type": "timeseries",
             "xaxis": {
                "buckets": null,
                "mode": "time",
@@ -288,6 +295,11 @@
             "dashLength": 10,
             "dashes": false,
             "datasource": "$datasource",
+            "fieldConfig": {
+               "defaults": {
+                  "unit": "bytes"
+               }
+            },
             "fill": 1,
             "fillGradient": 0,
             "gridPos": {
@@ -298,6 +310,7 @@
             },
             "hiddenSeries": false,
             "id": 40,
+            "interval": "1m",
             "legend": {
                "avg": false,
                "current": false,
@@ -337,7 +350,7 @@
                "sort": 0,
                "value_type": "individual"
             },
-            "type": "graph",
+            "type": "timeseries",
             "xaxis": {
                "buckets": null,
                "mode": "time",
@@ -374,6 +387,11 @@
             "dashLength": 10,
             "dashes": false,
             "datasource": "$datasource",
+            "fieldConfig": {
+               "defaults": {
+                  "unit": "binBps"
+               }
+            },
             "fill": 1,
             "fillGradient": 0,
             "gridPos": {
@@ -384,6 +402,7 @@
             },
             "hiddenSeries": false,
             "id": 38,
+            "interval": "1m",
             "legend": {
                "avg": false,
                "current": false,
@@ -409,7 +428,7 @@
             "steppedLine": false,
             "targets": [
                {
-                  "expr": "sum(rate(container_network_transmit_bytes_total{cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"$deployment.*\", pod=~\"$pod\"}[5m]))",
+                  "expr": "sum(rate(container_network_transmit_bytes_total{cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"$deployment.*\", pod=~\"$pod\"}[$__rate_interval]))",
                   "refId": "A"
                }
             ],
@@ -423,7 +442,7 @@
                "sort": 0,
                "value_type": "individual"
             },
-            "type": "graph",
+            "type": "timeseries",
             "xaxis": {
                "buckets": null,
                "mode": "time",
@@ -460,6 +479,11 @@
             "dashLength": 10,
             "dashes": false,
             "datasource": "$datasource",
+            "fieldConfig": {
+               "defaults": {
+                  "unit": "binBps"
+               }
+            },
             "fill": 1,
             "fillGradient": 0,
             "gridPos": {
@@ -470,6 +494,7 @@
             },
             "hiddenSeries": false,
             "id": 39,
+            "interval": "1m",
             "legend": {
                "avg": false,
                "current": false,
@@ -495,7 +520,7 @@
             "steppedLine": false,
             "targets": [
                {
-                  "expr": "sum(rate(container_network_receive_bytes_total{cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"$deployment.*\", pod=~\"$pod\"}[5m]))",
+                  "expr": "sum(rate(container_network_receive_bytes_total{cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"$deployment.*\", pod=~\"$pod\"}[$__rate_interval]))",
                   "refId": "A"
                }
             ],
@@ -509,7 +534,7 @@
                "sort": 0,
                "value_type": "individual"
             },
-            "type": "graph",
+            "type": "timeseries",
             "xaxis": {
                "buckets": null,
                "mode": "time",
@@ -556,6 +581,7 @@
             },
             "hiddenSeries": false,
             "id": 37,
+            "interval": "1m",
             "legend": {
                "avg": false,
                "current": false,
@@ -596,7 +622,7 @@
                "sort": 0,
                "value_type": "individual"
             },
-            "type": "graph",
+            "type": "timeseries",
             "xaxis": {
                "buckets": null,
                "mode": "time",
@@ -633,6 +659,11 @@
             "dashLength": 10,
             "dashes": false,
             "datasource": "$datasource",
+            "fieldConfig": {
+               "defaults": {
+                  "unit": "ops"
+               }
+            },
             "fill": 1,
             "fillGradient": 0,
             "gridPos": {
@@ -643,6 +674,7 @@
             },
             "hiddenSeries": false,
             "id": 42,
+            "interval": "1m",
             "legend": {
                "avg": false,
                "current": false,
@@ -668,7 +700,7 @@
             "steppedLine": false,
             "targets": [
                {
-                  "expr": "sum(rate(promtail_custom_bad_words_total{cluster=\"$cluster\", exported_namespace=\"$namespace\", exported_pod=~\"$deployment.*\", exported_pod=~\"$pod\", container=~\"$container\"}[5m])) by (level)",
+                  "expr": "sum(rate(promtail_custom_bad_words_total{cluster=\"$cluster\", exported_namespace=\"$namespace\", exported_pod=~\"$deployment.*\", exported_pod=~\"$pod\", container=~\"$container\"}[$__rate_interval])) by (level)",
                   "legendFormat": "{{level}}",
                   "refId": "A"
                }
@@ -683,7 +715,7 @@
                "sort": 0,
                "value_type": "individual"
             },
-            "type": "graph",
+            "type": "timeseries",
             "xaxis": {
                "buckets": null,
                "mode": "time",
@@ -719,7 +751,12 @@
             "bars": false,
             "dashLength": 10,
             "dashes": false,
-            "datasource": "$logs",
+            "datasource": "$loki_datasource",
+            "fieldConfig": {
+               "defaults": {
+                  "unit": "ops"
+               }
+            },
             "fill": 1,
             "fillGradient": 0,
             "gridPos": {
@@ -730,6 +767,7 @@
             },
             "hiddenSeries": false,
             "id": 31,
+            "interval": "1m",
             "legend": {
                "avg": false,
                "current": false,
@@ -772,7 +810,7 @@
             "steppedLine": false,
             "targets": [
                {
-                  "expr": "sum(rate({cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"$deployment.*\", pod=~\"$pod\", container=~\"$container\" } |logfmt| level=\"$level\" |= \"$filter\" [5m])) by (level)",
+                  "expr": "sum(rate({cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"$deployment.*\", pod=~\"$pod\", container=~\"$container\" } |logfmt| level=\"$level\" |= \"$filter\" | __error__=\"\" [$__interval])) by (level)",
                   "intervalFactor": 3,
                   "legendFormat": "{{level}}",
                   "refId": "A"
@@ -788,7 +826,7 @@
                "sort": 2,
                "value_type": "individual"
             },
-            "type": "graph",
+            "type": "timeseries",
             "xaxis": {
                "buckets": null,
                "mode": "time",
@@ -820,7 +858,7 @@
             }
          },
          {
-            "datasource": "$logs",
+            "datasource": "$loki_datasource",
             "gridPos": {
                "h": 19,
                "w": 24,
@@ -828,6 +866,7 @@
                "y": 6
             },
             "id": 29,
+            "interval": "1m",
             "maxDataPoints": "",
             "options": {
                "showLabels": false,
@@ -862,7 +901,7 @@
                   "value": "default"
                },
                "hide": 0,
-               "label": "Data Source",
+               "label": "Data source",
                "name": "datasource",
                "options": [ ],
                "query": "prometheus",
@@ -919,7 +958,7 @@
             {
                "hide": 0,
                "label": null,
-               "name": "logs",
+               "name": "loki_datasource",
                "options": [ ],
                "query": "loki",
                "refresh": 1,

charts/meta-monitoring/src/dashboards/loki-mixin-recording-rules.json

@@ -1,657 +0,0 @@
-{
-      "annotations": {
-         "list": [
-            {
-               "builtIn": 1,
-               "datasource": "-- Grafana --",
-               "enable": true,
-               "hide": true,
-               "iconColor": "rgba(0, 211, 255, 1)",
-               "name": "Annotations & Alerts",
-               "target": {
-                  "limit": 100,
-                  "matchAny": false,
-                  "tags": [ ],
-                  "type": "dashboard"
-               },
-               "type": "dashboard"
-            },
-            {
-               "datasource": "${datasource}",
-               "enable": false,
-               "expr": "sum by (tenant) (changes(loki_ruler_wal_prometheus_tsdb_wal_truncations_total{tenant=~\"${tenant}\"}[$__rate_interval]))",
-               "iconColor": "red",
-               "name": "WAL Truncations",
-               "target": {
-                  "queryType": "Azure Monitor",
-                  "refId": "Anno"
-               },
-               "titleFormat": "{{tenant}}"
-            }
-         ]
-      },
-      "editable": true,
-      "fiscalYearStartMonth": 0,
-      "gnetId": null,
-      "graphTooltip": 0,
-      "iteration": 1635347545534,
-      "links": [ ],
-      "liveNow": false,
-      "panels": [
-         {
-            "datasource": "${datasource}",
-            "fieldConfig": {
-               "defaults": {
-                  "color": {
-                     "mode": "thresholds"
-                  },
-                  "mappings": [ ],
-                  "noValue": "0",
-                  "thresholds": {
-                     "mode": "absolute",
-                     "steps": [
-                        {
-                           "color": "green",
-                           "value": null
-                        },
-                        {
-                           "color": "red",
-                           "value": 1
-                        }
-                     ]
-                  }
-               },
-               "overrides": [ ]
-            },
-            "gridPos": {
-               "h": 10,
-               "w": 2,
-               "x": 0,
-               "y": 0
-            },
-            "id": 2,
-            "options": {
-               "colorMode": "value",
-               "graphMode": "area",
-               "justifyMode": "auto",
-               "orientation": "auto",
-               "reduceOptions": {
-                  "calcs": [
-                     "lastNotNull"
-                  ],
-                  "fields": "",
-                  "values": false
-               },
-               "textMode": "auto"
-            },
-            "pluginVersion": "8.3.0-38205pre",
-            "targets": [
-               {
-                  "datasource": "${datasource}",
-                  "exemplar": false,
-                  "expr": "sum(loki_ruler_wal_appender_ready) by (pod, tenant) == 0",
-                  "instant": true,
-                  "interval": "",
-                  "legendFormat": "",
-                  "refId": "A"
-               }
-            ],
-            "title": "Appenders Not Ready",
-            "type": "stat"
-         },
-         {
-            "datasource": "${datasource}",
-            "description": "",
-            "fieldConfig": {
-               "defaults": {
-                  "color": {
-                     "mode": "palette-classic"
-                  },
-                  "custom": {
-                     "axisLabel": "",
-                     "axisPlacement": "auto",
-                     "barAlignment": 0,
-                     "drawStyle": "line",
-                     "fillOpacity": 0,
-                     "gradientMode": "none",
-                     "hideFrom": {
-                        "legend": false,
-                        "tooltip": false,
-                        "viz": false
-                     },
-                     "lineInterpolation": "linear",
-                     "lineWidth": 1,
-                     "pointSize": 5,
-                     "scaleDistribution": {
-                        "type": "linear"
-                     },
-                     "showPoints": "auto",
-                     "spanNulls": false,
-                     "stacking": {
-                        "group": "A",
-                        "mode": "none"
-                     },
-                     "thresholdsStyle": {
-                        "mode": "off"
-                     }
-                  },
-                  "mappings": [ ],
-                  "thresholds": {
-                     "mode": "absolute",
-                     "steps": [
-                        {
-                           "color": "green",
-                           "value": null
-                        },
-                        {
-                           "color": "red",
-                           "value": 80
-                        }
-                     ]
-                  }
-               },
-               "overrides": [ ]
-            },
-            "gridPos": {
-               "h": 10,
-               "w": 11,
-               "x": 2,
-               "y": 0
-            },
-            "id": 4,
-            "options": {
-               "legend": {
-                  "calcs": [ ],
-                  "displayMode": "list",
-                  "placement": "bottom"
-               },
-               "tooltip": {
-                  "mode": "single"
-               }
-            },
-            "targets": [
-               {
-                  "datasource": "${datasource}",
-                  "exemplar": true,
-                  "expr": "sum(rate(loki_ruler_wal_samples_appended_total{tenant=~\"${tenant}\"}[$__rate_interval])) by (tenant) > 0",
-                  "interval": "",
-                  "legendFormat": "{{tenant}}",
-                  "refId": "A"
-               }
-            ],
-            "title": "Samples Appended to WAL per Second",
-            "type": "timeseries"
-         },
-         {
-            "datasource": "${datasource}",
-            "description": "Series are unique combinations of labels",
-            "fieldConfig": {
-               "defaults": {
-                  "color": {
-                     "mode": "palette-classic"
-                  },
-                  "custom": {
-                     "axisLabel": "",
-                     "axisPlacement": "auto",
-                     "barAlignment": 0,
-                     "drawStyle": "line",
-                     "fillOpacity": 0,
-                     "gradientMode": "none",
-                     "hideFrom": {
-                        "legend": false,
-                        "tooltip": false,
-                        "viz": false
-                     },
-                     "lineInterpolation": "linear",
-                     "lineWidth": 1,
-                     "pointSize": 5,
-                     "scaleDistribution": {
-                        "type": "linear"
-                     },
-                     "showPoints": "auto",
-                     "spanNulls": false,
-                     "stacking": {
-                        "group": "A",
-                        "mode": "none"
-                     },
-                     "thresholdsStyle": {
-                        "mode": "off"
-                     }
-                  },
-                  "mappings": [ ],
-                  "thresholds": {
-                     "mode": "absolute",
-                     "steps": [
-                        {
-                           "color": "green",
-                           "value": null
-                        },
-                        {
-                           "color": "red",
-                           "value": 80
-                        }
-                     ]
-                  }
-               },
-               "overrides": [ ]
-            },
-            "gridPos": {
-               "h": 10,
-               "w": 11,
-               "x": 13,
-               "y": 0
-            },
-            "id": 5,
-            "options": {
-               "legend": {
-                  "calcs": [ ],
-                  "displayMode": "list",
-                  "placement": "bottom"
-               },
-               "tooltip": {
-                  "mode": "single"
-               }
-            },
-            "targets": [
-               {
-                  "datasource": "${datasource}",
-                  "exemplar": true,
-                  "expr": "sum(rate(loki_ruler_wal_storage_created_series_total{tenant=~\"${tenant}\"}[$__rate_interval])) by (tenant) > 0",
-                  "interval": "",
-                  "legendFormat": "{{tenant}}",
-                  "refId": "A"
-               }
-            ],
-            "title": "Series Created per Second",
-            "type": "timeseries"
-         },
-         {
-            "datasource": "${datasource}",
-            "description": "Difference between highest timestamp appended to WAL and highest timestamp successfully written to remote storage",
-            "fieldConfig": {
-               "defaults": {
-                  "color": {
-                     "mode": "palette-classic"
-                  },
-                  "custom": {
-                     "axisLabel": "",
-                     "axisPlacement": "auto",
-                     "barAlignment": 0,
-                     "drawStyle": "line",
-                     "fillOpacity": 0,
-                     "gradientMode": "none",
-                     "hideFrom": {
-                        "legend": false,
-                        "tooltip": false,
-                        "viz": false
-                     },
-                     "lineInterpolation": "linear",
-                     "lineWidth": 1,
-                     "pointSize": 5,
-                     "scaleDistribution": {
-                        "type": "linear"
-                     },
-                     "showPoints": "auto",
-                     "spanNulls": false,
-                     "stacking": {
-                        "group": "A",
-                        "mode": "none"
-                     },
-                     "thresholdsStyle": {
-                        "mode": "off"
-                     }
-                  },
-                  "mappings": [ ],
-                  "thresholds": {
-                     "mode": "absolute",
-                     "steps": [
-                        {
-                           "color": "green",
-                           "value": null
-                        },
-                        {
-                           "color": "red",
-                           "value": 80
-                        }
-                     ]
-                  }
-               },
-               "overrides": [ ]
-            },
-            "gridPos": {
-               "h": 10,
-               "w": 12,
-               "x": 0,
-               "y": 10
-            },
-            "id": 6,
-            "options": {
-               "legend": {
-                  "calcs": [ ],
-                  "displayMode": "list",
-                  "placement": "bottom"
-               },
-               "tooltip": {
-                  "mode": "single"
-               }
-            },
-            "targets": [
-               {
-                  "datasource": "${datasource}",
-                  "exemplar": true,
-                  "expr": "loki_ruler_wal_prometheus_remote_storage_highest_timestamp_in_seconds{tenant=~\"${tenant}\"}\n- on (tenant)\n  (\n    loki_ruler_wal_prometheus_remote_storage_queue_highest_sent_timestamp_seconds{tenant=~\"${tenant}\"}\n    or vector(0)\n  )",
-                  "interval": "",
-                  "legendFormat": "{{tenant}}",
-                  "refId": "A"
-               }
-            ],
-            "title": "Write Behind",
-            "type": "timeseries"
-         },
-         {
-            "datasource": "${datasource}",
-            "description": "",
-            "fieldConfig": {
-               "defaults": {
-                  "color": {
-                     "mode": "palette-classic"
-                  },
-                  "custom": {
-                     "axisLabel": "",
-                     "axisPlacement": "auto",
-                     "barAlignment": 0,
-                     "drawStyle": "line",
-                     "fillOpacity": 0,
-                     "gradientMode": "none",
-                     "hideFrom": {
-                        "legend": false,
-                        "tooltip": false,
-                        "viz": false
-                     },
-                     "lineInterpolation": "linear",
-                     "lineWidth": 1,
-                     "pointSize": 5,
-                     "scaleDistribution": {
-                        "type": "linear"
-                     },
-                     "showPoints": "auto",
-                     "spanNulls": false,
-                     "stacking": {
-                        "group": "A",
-                        "mode": "none"
-                     },
-                     "thresholdsStyle": {
-                        "mode": "off"
-                     }
-                  },
-                  "mappings": [ ],
-                  "thresholds": {
-                     "mode": "absolute",
-                     "steps": [
-                        {
-                           "color": "green",
-                           "value": null
-                        },
-                        {
-                           "color": "red",
-                           "value": 80
-                        }
-                     ]
-                  }
-               },
-               "overrides": [ ]
-            },
-            "gridPos": {
-               "h": 10,
-               "w": 12,
-               "x": 12,
-               "y": 10
-            },
-            "id": 7,
-            "options": {
-               "legend": {
-                  "calcs": [ ],
-                  "displayMode": "list",
-                  "placement": "bottom"
-               },
-               "tooltip": {
-                  "mode": "single"
-               }
-            },
-            "targets": [
-               {
-                  "datasource": "${datasource}",
-                  "exemplar": true,
-                  "expr": "sum(rate(loki_ruler_wal_prometheus_remote_storage_samples_total{tenant=~\"${tenant}\"}[$__rate_interval])) by (tenant) > 0",
-                  "interval": "",
-                  "legendFormat": "{{tenant}}",
-                  "refId": "A"
-               }
-            ],
-            "title": "Samples Sent per Second",
-            "type": "timeseries"
-         },
-         {
-            "datasource": "${datasource}",
-            "description": "\n",
-            "fieldConfig": {
-               "defaults": {
-                  "color": {
-                     "mode": "palette-classic"
-                  },
-                  "custom": {
-                     "axisLabel": "",
-                     "axisPlacement": "auto",
-                     "barAlignment": 0,
-                     "drawStyle": "line",
-                     "fillOpacity": 0,
-                     "gradientMode": "none",
-                     "hideFrom": {
-                        "legend": false,
-                        "tooltip": false,
-                        "viz": false
-                     },
-                     "lineInterpolation": "linear",
-                     "lineWidth": 1,
-                     "pointSize": 5,
-                     "scaleDistribution": {
-                        "type": "linear"
-                     },
-                     "showPoints": "auto",
-                     "spanNulls": false,
-                     "stacking": {
-                        "group": "A",
-                        "mode": "none"
-                     },
-                     "thresholdsStyle": {
-                        "mode": "off"
-                     }
-                  },
-                  "mappings": [ ],
-                  "thresholds": {
-                     "mode": "absolute",
-                     "steps": [
-                        {
-                           "color": "green",
-                           "value": null
-                        },
-                        {
-                           "color": "red",
-                           "value": 80
-                        }
-                     ]
-                  },
-                  "unit": "bytes"
-               },
-               "overrides": [ ]
-            },
-            "gridPos": {
-               "h": 10,
-               "w": 12,
-               "x": 0,
-               "y": 20
-            },
-            "id": 8,
-            "options": {
-               "legend": {
-                  "calcs": [ ],
-                  "displayMode": "list",
-                  "placement": "bottom"
-               },
-               "tooltip": {
-                  "mode": "single"
-               }
-            },
-            "targets": [
-               {
-                  "datasource": "${datasource}",
-                  "exemplar": true,
-                  "expr": "sum by (tenant) (loki_ruler_wal_disk_size{tenant=~\"${tenant}\"})",
-                  "interval": "",
-                  "legendFormat": "{{tenant}}",
-                  "refId": "A"
-               }
-            ],
-            "title": "WAL Disk Size",
-            "type": "timeseries"
-         },
-         {
-            "datasource": "${datasource}",
-            "description": "Some number of pending samples is expected, but if remote-write is failing this value will remain high",
-            "fieldConfig": {
-               "defaults": {
-                  "color": {
-                     "mode": "palette-classic"
-                  },
-                  "custom": {
-                     "axisLabel": "",
-                     "axisPlacement": "auto",
-                     "barAlignment": 0,
-                     "drawStyle": "line",
-                     "fillOpacity": 0,
-                     "gradientMode": "none",
-                     "hideFrom": {
-                        "legend": false,
-                        "tooltip": false,
-                        "viz": false
-                     },
-                     "lineInterpolation": "linear",
-                     "lineWidth": 1,
-                     "pointSize": 5,
-                     "scaleDistribution": {
-                        "type": "linear"
-                     },
-                     "showPoints": "auto",
-                     "spanNulls": false,
-                     "stacking": {
-                        "group": "A",
-                        "mode": "none"
-                     },
-                     "thresholdsStyle": {
-                        "mode": "off"
-                     }
-                  },
-                  "mappings": [ ],
-                  "thresholds": {
-                     "mode": "absolute",
-                     "steps": [
-                        {
-                           "color": "green",
-                           "value": null
-                        },
-                        {
-                           "color": "red",
-                           "value": 80
-                        }
-                     ]
-                  }
-               },
-               "overrides": [ ]
-            },
-            "gridPos": {
-               "h": 10,
-               "w": 12,
-               "x": 12,
-               "y": 20
-            },
-            "id": 9,
-            "options": {
-               "legend": {
-                  "calcs": [ ],
-                  "displayMode": "list",
-                  "placement": "bottom"
-               },
-               "tooltip": {
-                  "mode": "single"
-               }
-            },
-            "targets": [
-               {
-                  "datasource": "${datasource}",
-                  "exemplar": true,
-                  "expr": "max(loki_ruler_wal_prometheus_remote_storage_samples_pending{tenant=~\"${tenant}\"}) by (tenant,pod) > 0",
-                  "interval": "",
-                  "legendFormat": "{{tenant}}",
-                  "refId": "A"
-               }
-            ],
-            "title": "Pending Samples",
-            "type": "timeseries"
-         }
-      ],
-      "schemaVersion": 31,
-      "style": "dark",
-      "tags": [ ],
-      "templating": {
-         "list": [
-            {
-               "description": null,
-               "error": null,
-               "hide": 0,
-               "includeAll": false,
-               "label": "Datasource",
-               "multi": false,
-               "name": "datasource",
-               "options": [ ],
-               "query": "prometheus",
-               "queryValue": "",
-               "refresh": 1,
-               "regex": "",
-               "skipUrlSync": false,
-               "type": "datasource"
-            },
-            {
-               "allValue": null,
-               "datasource": "${datasource}",
-               "definition": "label_values(loki_ruler_wal_samples_appended_total, tenant)",
-               "description": null,
-               "error": null,
-               "hide": 0,
-               "includeAll": true,
-               "label": "Tenant",
-               "multi": true,
-               "name": "tenant",
-               "options": [ ],
-               "query": {
-                  "query": "label_values(loki_ruler_wal_samples_appended_total, tenant)",
-                  "refId": "StandardVariableQuery"
-               },
-               "refresh": 2,
-               "regex": "",
-               "skipUrlSync": false,
-               "sort": 0,
-               "type": "query"
-            }
-         ]
-      },
-      "time": {
-         "from": "now-6h",
-         "to": "now"
-      },
-      "timepicker": { },
-      "timezone": "",
-      "title": "Recording Rules",
-      "uid": "2xKA_ZK7k",
-      "version": 9,
-      "weekStart": ""
-   }

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

@@ -0,0 +1,52 @@
+- name: "loki_rules"
+  rules:
+  - expr: "histogram_quantile(0.99, sum(rate(loki_request_duration_seconds_bucket[5m]))
+      by (le, cluster, job))"
+    record: "cluster_job:loki_request_duration_seconds:99quantile"
+  - expr: "histogram_quantile(0.50, sum(rate(loki_request_duration_seconds_bucket[5m]))
+      by (le, cluster, job))"
+    record: "cluster_job:loki_request_duration_seconds:50quantile"
+  - expr: "sum(rate(loki_request_duration_seconds_sum[5m])) by (cluster, job) / sum(rate(loki_request_duration_seconds_count[5m]))
+      by (cluster, job)"
+    record: "cluster_job:loki_request_duration_seconds:avg"
+  - expr: "sum(rate(loki_request_duration_seconds_bucket[5m])) by (le, cluster, job)"
+    record: "cluster_job:loki_request_duration_seconds_bucket:sum_rate"
+  - expr: "sum(rate(loki_request_duration_seconds_sum[5m])) by (cluster, job)"
+    record: "cluster_job:loki_request_duration_seconds_sum:sum_rate"
+  - expr: "sum(rate(loki_request_duration_seconds_count[5m])) 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[5m]))
+      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[5m]))
+      by (le, cluster, job, route))"
+    record: "cluster_job_route:loki_request_duration_seconds:50quantile"
+  - expr: "sum(rate(loki_request_duration_seconds_sum[5m])) by (cluster, job, route)
+      / sum(rate(loki_request_duration_seconds_count[5m])) by (cluster, job, route)"
+    record: "cluster_job_route:loki_request_duration_seconds:avg"
+  - expr: "sum(rate(loki_request_duration_seconds_bucket[5m])) by (le, cluster, job,
+      route)"
+    record: "cluster_job_route:loki_request_duration_seconds_bucket:sum_rate"
+  - expr: "sum(rate(loki_request_duration_seconds_sum[5m])) by (cluster, job, route)"
+    record: "cluster_job_route:loki_request_duration_seconds_sum:sum_rate"
+  - expr: "sum(rate(loki_request_duration_seconds_count[5m])) 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[5m]))
+      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[5m]))
+      by (le, cluster, namespace, job, route))"
+    record: "cluster_namespace_job_route:loki_request_duration_seconds:50quantile"
+  - expr: "sum(rate(loki_request_duration_seconds_sum[5m])) by (cluster, namespace,
+      job, route) / sum(rate(loki_request_duration_seconds_count[5m])) by (cluster,
+      namespace, job, route)"
+    record: "cluster_namespace_job_route:loki_request_duration_seconds:avg"
+  - expr: "sum(rate(loki_request_duration_seconds_bucket[5m])) 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[5m])) 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[5m])) by (cluster, namespace,
+      job, route)"
+    record: "cluster_namespace_job_route:loki_request_duration_seconds_count:sum_rate"

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

@@ -0,0 +1,555 @@
+groups:
+- name: "mimir_api_1"
+  rules:
+  - expr: "histogram_quantile(0.99, sum(rate(cortex_request_duration_seconds_bucket[5m]))
+      by (le, cluster, job))"
+    record: "cluster_job:cortex_request_duration_seconds:99quantile"
+  - expr: "histogram_quantile(0.50, sum(rate(cortex_request_duration_seconds_bucket[5m]))
+      by (le, cluster, job))"
+    record: "cluster_job:cortex_request_duration_seconds:50quantile"
+  - expr: "sum(rate(cortex_request_duration_seconds_sum[5m])) by (cluster, job) / sum(rate(cortex_request_duration_seconds_count[5m]))
+      by (cluster, job)"
+    record: "cluster_job:cortex_request_duration_seconds:avg"
+  - expr: "sum(rate(cortex_request_duration_seconds_bucket[5m])) by (le, cluster, job)"
+    record: "cluster_job:cortex_request_duration_seconds_bucket:sum_rate"
+  - expr: "sum(rate(cortex_request_duration_seconds_sum[5m])) by (cluster, job)"
+    record: "cluster_job:cortex_request_duration_seconds_sum:sum_rate"
+  - expr: "sum(rate(cortex_request_duration_seconds_count[5m])) by (cluster, job)"
+    record: "cluster_job:cortex_request_duration_seconds_count:sum_rate"
+- name: "mimir_api_2"
+  rules:
+  - expr: "histogram_quantile(0.99, sum(rate(cortex_request_duration_seconds_bucket[5m]))
+      by (le, cluster, job, route))"
+    record: "cluster_job_route:cortex_request_duration_seconds:99quantile"
+  - expr: "histogram_quantile(0.50, sum(rate(cortex_request_duration_seconds_bucket[5m]))
+      by (le, cluster, job, route))"
+    record: "cluster_job_route:cortex_request_duration_seconds:50quantile"
+  - expr: "sum(rate(cortex_request_duration_seconds_sum[5m])) by (cluster, job, route)
+      / sum(rate(cortex_request_duration_seconds_count[5m])) by (cluster, job, route)"
+    record: "cluster_job_route:cortex_request_duration_seconds:avg"
+  - expr: "sum(rate(cortex_request_duration_seconds_bucket[5m])) by (le, cluster, job,
+      route)"
+    record: "cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate"
+  - expr: "sum(rate(cortex_request_duration_seconds_sum[5m])) by (cluster, job, route)"
+    record: "cluster_job_route:cortex_request_duration_seconds_sum:sum_rate"
+  - expr: "sum(rate(cortex_request_duration_seconds_count[5m])) by (cluster, job, route)"
+    record: "cluster_job_route:cortex_request_duration_seconds_count:sum_rate"
+- name: "mimir_api_3"
+  rules:
+  - expr: "histogram_quantile(0.99, sum(rate(cortex_request_duration_seconds_bucket[5m]))
+      by (le, cluster, namespace, job, route))"
+    record: "cluster_namespace_job_route:cortex_request_duration_seconds:99quantile"
+  - expr: "histogram_quantile(0.50, sum(rate(cortex_request_duration_seconds_bucket[5m]))
+      by (le, cluster, namespace, job, route))"
+    record: "cluster_namespace_job_route:cortex_request_duration_seconds:50quantile"
+  - expr: "sum(rate(cortex_request_duration_seconds_sum[5m])) by (cluster, namespace,
+      job, route) / sum(rate(cortex_request_duration_seconds_count[5m])) by (cluster,
+      namespace, job, route)"
+    record: "cluster_namespace_job_route:cortex_request_duration_seconds:avg"
+  - expr: "sum(rate(cortex_request_duration_seconds_bucket[5m])) by (le, cluster, namespace,
+      job, route)"
+    record: "cluster_namespace_job_route:cortex_request_duration_seconds_bucket:sum_rate"
+  - expr: "sum(rate(cortex_request_duration_seconds_sum[5m])) by (cluster, namespace,
+      job, route)"
+    record: "cluster_namespace_job_route:cortex_request_duration_seconds_sum:sum_rate"
+  - expr: "sum(rate(cortex_request_duration_seconds_count[5m])) by (cluster, namespace,
+      job, route)"
+    record: "cluster_namespace_job_route:cortex_request_duration_seconds_count:sum_rate"
+- name: "mimir_querier_api"
+  rules:
+  - expr: "histogram_quantile(0.99, sum(rate(cortex_querier_request_duration_seconds_bucket[5m]))
+      by (le, cluster, job))"
+    record: "cluster_job:cortex_querier_request_duration_seconds:99quantile"
+  - expr: "histogram_quantile(0.50, sum(rate(cortex_querier_request_duration_seconds_bucket[5m]))
+      by (le, cluster, job))"
+    record: "cluster_job:cortex_querier_request_duration_seconds:50quantile"
+  - expr: "sum(rate(cortex_querier_request_duration_seconds_sum[5m])) by (cluster,
+      job) / sum(rate(cortex_querier_request_duration_seconds_count[5m])) by (cluster,
+      job)"
+    record: "cluster_job:cortex_querier_request_duration_seconds:avg"
+  - expr: "sum(rate(cortex_querier_request_duration_seconds_bucket[5m])) by (le, cluster,
+      job)"
+    record: "cluster_job:cortex_querier_request_duration_seconds_bucket:sum_rate"
+  - expr: "sum(rate(cortex_querier_request_duration_seconds_sum[5m])) by (cluster,
+      job)"
+    record: "cluster_job:cortex_querier_request_duration_seconds_sum:sum_rate"
+  - expr: "sum(rate(cortex_querier_request_duration_seconds_count[5m])) by (cluster,
+      job)"
+    record: "cluster_job:cortex_querier_request_duration_seconds_count:sum_rate"
+  - expr: "histogram_quantile(0.99, sum(rate(cortex_querier_request_duration_seconds_bucket[5m]))
+      by (le, cluster, job, route))"
+    record: "cluster_job_route:cortex_querier_request_duration_seconds:99quantile"
+  - expr: "histogram_quantile(0.50, sum(rate(cortex_querier_request_duration_seconds_bucket[5m]))
+      by (le, cluster, job, route))"
+    record: "cluster_job_route:cortex_querier_request_duration_seconds:50quantile"
+  - expr: "sum(rate(cortex_querier_request_duration_seconds_sum[5m])) by (cluster,
+      job, route) / sum(rate(cortex_querier_request_duration_seconds_count[5m])) by
+      (cluster, job, route)"
+    record: "cluster_job_route:cortex_querier_request_duration_seconds:avg"
+  - expr: "sum(rate(cortex_querier_request_duration_seconds_bucket[5m])) by (le, cluster,
+      job, route)"
+    record: "cluster_job_route:cortex_querier_request_duration_seconds_bucket:sum_rate"
+  - expr: "sum(rate(cortex_querier_request_duration_seconds_sum[5m])) by (cluster,
+      job, route)"
+    record: "cluster_job_route:cortex_querier_request_duration_seconds_sum:sum_rate"
+  - expr: "sum(rate(cortex_querier_request_duration_seconds_count[5m])) by (cluster,
+      job, route)"
+    record: "cluster_job_route:cortex_querier_request_duration_seconds_count:sum_rate"
+  - expr: "histogram_quantile(0.99, sum(rate(cortex_querier_request_duration_seconds_bucket[5m]))
+      by (le, cluster, namespace, job, route))"
+    record: "cluster_namespace_job_route:cortex_querier_request_duration_seconds:99quantile"
+  - expr: "histogram_quantile(0.50, sum(rate(cortex_querier_request_duration_seconds_bucket[5m]))
+      by (le, cluster, namespace, job, route))"
+    record: "cluster_namespace_job_route:cortex_querier_request_duration_seconds:50quantile"
+  - expr: "sum(rate(cortex_querier_request_duration_seconds_sum[5m])) by (cluster,
+      namespace, job, route) / sum(rate(cortex_querier_request_duration_seconds_count[5m]))
+      by (cluster, namespace, job, route)"
+    record: "cluster_namespace_job_route:cortex_querier_request_duration_seconds:avg"
+  - expr: "sum(rate(cortex_querier_request_duration_seconds_bucket[5m])) by (le, cluster,
+      namespace, job, route)"
+    record: "cluster_namespace_job_route:cortex_querier_request_duration_seconds_bucket:sum_rate"
+  - expr: "sum(rate(cortex_querier_request_duration_seconds_sum[5m])) by (cluster,
+      namespace, job, route)"
+    record: "cluster_namespace_job_route:cortex_querier_request_duration_seconds_sum:sum_rate"
+  - expr: "sum(rate(cortex_querier_request_duration_seconds_count[5m])) by (cluster,
+      namespace, job, route)"
+    record: "cluster_namespace_job_route:cortex_querier_request_duration_seconds_count:sum_rate"
+- name: "mimir_cache"
+  rules:
+  - expr: "histogram_quantile(0.99, sum(rate(cortex_memcache_request_duration_seconds_bucket[5m]))
+      by (le, cluster, job, method))"
+    record: "cluster_job_method:cortex_memcache_request_duration_seconds:99quantile"
+  - expr: "histogram_quantile(0.50, sum(rate(cortex_memcache_request_duration_seconds_bucket[5m]))
+      by (le, cluster, job, method))"
+    record: "cluster_job_method:cortex_memcache_request_duration_seconds:50quantile"
+  - expr: "sum(rate(cortex_memcache_request_duration_seconds_sum[5m])) by (cluster,
+      job, method) / sum(rate(cortex_memcache_request_duration_seconds_count[5m]))
+      by (cluster, job, method)"
+    record: "cluster_job_method:cortex_memcache_request_duration_seconds:avg"
+  - expr: "sum(rate(cortex_memcache_request_duration_seconds_bucket[5m])) by (le, cluster,
+      job, method)"
+    record: "cluster_job_method:cortex_memcache_request_duration_seconds_bucket:sum_rate"
+  - expr: "sum(rate(cortex_memcache_request_duration_seconds_sum[5m])) by (cluster,
+      job, method)"
+    record: "cluster_job_method:cortex_memcache_request_duration_seconds_sum:sum_rate"
+  - expr: "sum(rate(cortex_memcache_request_duration_seconds_count[5m])) by (cluster,
+      job, method)"
+    record: "cluster_job_method:cortex_memcache_request_duration_seconds_count:sum_rate"
+  - expr: "histogram_quantile(0.99, sum(rate(cortex_cache_request_duration_seconds_bucket[5m]))
+      by (le, cluster, job))"
+    record: "cluster_job:cortex_cache_request_duration_seconds:99quantile"
+  - expr: "histogram_quantile(0.50, sum(rate(cortex_cache_request_duration_seconds_bucket[5m]))
+      by (le, cluster, job))"
+    record: "cluster_job:cortex_cache_request_duration_seconds:50quantile"
+  - expr: "sum(rate(cortex_cache_request_duration_seconds_sum[5m])) by (cluster, job)
+      / sum(rate(cortex_cache_request_duration_seconds_count[5m])) by (cluster, job)"
+    record: "cluster_job:cortex_cache_request_duration_seconds:avg"
+  - expr: "sum(rate(cortex_cache_request_duration_seconds_bucket[5m])) by (le, cluster,
+      job)"
+    record: "cluster_job:cortex_cache_request_duration_seconds_bucket:sum_rate"
+  - expr: "sum(rate(cortex_cache_request_duration_seconds_sum[5m])) by (cluster, job)"
+    record: "cluster_job:cortex_cache_request_duration_seconds_sum:sum_rate"
+  - expr: "sum(rate(cortex_cache_request_duration_seconds_count[5m])) by (cluster,
+      job)"
+    record: "cluster_job:cortex_cache_request_duration_seconds_count:sum_rate"
+  - expr: "histogram_quantile(0.99, sum(rate(cortex_cache_request_duration_seconds_bucket[5m]))
+      by (le, cluster, job, method))"
+    record: "cluster_job_method:cortex_cache_request_duration_seconds:99quantile"
+  - expr: "histogram_quantile(0.50, sum(rate(cortex_cache_request_duration_seconds_bucket[5m]))
+      by (le, cluster, job, method))"
+    record: "cluster_job_method:cortex_cache_request_duration_seconds:50quantile"
+  - expr: "sum(rate(cortex_cache_request_duration_seconds_sum[5m])) by (cluster, job,
+      method) / sum(rate(cortex_cache_request_duration_seconds_count[5m])) by (cluster,
+      job, method)"
+    record: "cluster_job_method:cortex_cache_request_duration_seconds:avg"
+  - expr: "sum(rate(cortex_cache_request_duration_seconds_bucket[5m])) by (le, cluster,
+      job, method)"
+    record: "cluster_job_method:cortex_cache_request_duration_seconds_bucket:sum_rate"
+  - expr: "sum(rate(cortex_cache_request_duration_seconds_sum[5m])) by (cluster, job,
+      method)"
+    record: "cluster_job_method:cortex_cache_request_duration_seconds_sum:sum_rate"
+  - expr: "sum(rate(cortex_cache_request_duration_seconds_count[5m])) by (cluster,
+      job, method)"
+    record: "cluster_job_method:cortex_cache_request_duration_seconds_count:sum_rate"
+- name: "mimir_storage"
+  rules:
+  - expr: "histogram_quantile(0.99, sum(rate(cortex_kv_request_duration_seconds_bucket[5m]))
+      by (le, cluster, job))"
+    record: "cluster_job:cortex_kv_request_duration_seconds:99quantile"
+  - expr: "histogram_quantile(0.50, sum(rate(cortex_kv_request_duration_seconds_bucket[5m]))
+      by (le, cluster, job))"
+    record: "cluster_job:cortex_kv_request_duration_seconds:50quantile"
+  - expr: "sum(rate(cortex_kv_request_duration_seconds_sum[5m])) by (cluster, job)
+      / sum(rate(cortex_kv_request_duration_seconds_count[5m])) by (cluster, job)"
+    record: "cluster_job:cortex_kv_request_duration_seconds:avg"
+  - expr: "sum(rate(cortex_kv_request_duration_seconds_bucket[5m])) by (le, cluster,
+      job)"
+    record: "cluster_job:cortex_kv_request_duration_seconds_bucket:sum_rate"
+  - expr: "sum(rate(cortex_kv_request_duration_seconds_sum[5m])) by (cluster, job)"
+    record: "cluster_job:cortex_kv_request_duration_seconds_sum:sum_rate"
+  - expr: "sum(rate(cortex_kv_request_duration_seconds_count[5m])) by (cluster, job)"
+    record: "cluster_job:cortex_kv_request_duration_seconds_count:sum_rate"
+- name: "mimir_queries"
+  rules:
+  - expr: "histogram_quantile(0.99, sum(rate(cortex_query_frontend_retries_bucket[5m]))
+      by (le, cluster, job))"
+    record: "cluster_job:cortex_query_frontend_retries:99quantile"
+  - expr: "histogram_quantile(0.50, sum(rate(cortex_query_frontend_retries_bucket[5m]))
+      by (le, cluster, job))"
+    record: "cluster_job:cortex_query_frontend_retries:50quantile"
+  - expr: "sum(rate(cortex_query_frontend_retries_sum[5m])) by (cluster, job) / sum(rate(cortex_query_frontend_retries_count[5m]))
+      by (cluster, job)"
+    record: "cluster_job:cortex_query_frontend_retries:avg"
+  - expr: "sum(rate(cortex_query_frontend_retries_bucket[5m])) by (le, cluster, job)"
+    record: "cluster_job:cortex_query_frontend_retries_bucket:sum_rate"
+  - expr: "sum(rate(cortex_query_frontend_retries_sum[5m])) by (cluster, job)"
+    record: "cluster_job:cortex_query_frontend_retries_sum:sum_rate"
+  - expr: "sum(rate(cortex_query_frontend_retries_count[5m])) by (cluster, job)"
+    record: "cluster_job:cortex_query_frontend_retries_count:sum_rate"
+  - expr: "histogram_quantile(0.99, sum(rate(cortex_query_frontend_queue_duration_seconds_bucket[5m]))
+      by (le, cluster, job))"
+    record: "cluster_job:cortex_query_frontend_queue_duration_seconds:99quantile"
+  - expr: "histogram_quantile(0.50, sum(rate(cortex_query_frontend_queue_duration_seconds_bucket[5m]))
+      by (le, cluster, job))"
+    record: "cluster_job:cortex_query_frontend_queue_duration_seconds:50quantile"
+  - expr: "sum(rate(cortex_query_frontend_queue_duration_seconds_sum[5m])) by (cluster,
+      job) / sum(rate(cortex_query_frontend_queue_duration_seconds_count[5m])) by
+      (cluster, job)"
+    record: "cluster_job:cortex_query_frontend_queue_duration_seconds:avg"
+  - expr: "sum(rate(cortex_query_frontend_queue_duration_seconds_bucket[5m])) by (le,
+      cluster, job)"
+    record: "cluster_job:cortex_query_frontend_queue_duration_seconds_bucket:sum_rate"
+  - expr: "sum(rate(cortex_query_frontend_queue_duration_seconds_sum[5m])) by (cluster,
+      job)"
+    record: "cluster_job:cortex_query_frontend_queue_duration_seconds_sum:sum_rate"
+  - expr: "sum(rate(cortex_query_frontend_queue_duration_seconds_count[5m])) by (cluster,
+      job)"
+    record: "cluster_job:cortex_query_frontend_queue_duration_seconds_count:sum_rate"
+- name: "mimir_ingester_queries"
+  rules:
+  - expr: "histogram_quantile(0.99, sum(rate(cortex_ingester_queried_series_bucket[5m]))
+      by (le, cluster, job))"
+    record: "cluster_job:cortex_ingester_queried_series:99quantile"
+  - expr: "histogram_quantile(0.50, sum(rate(cortex_ingester_queried_series_bucket[5m]))
+      by (le, cluster, job))"
+    record: "cluster_job:cortex_ingester_queried_series:50quantile"
+  - expr: "sum(rate(cortex_ingester_queried_series_sum[5m])) by (cluster, job) / sum(rate(cortex_ingester_queried_series_count[5m]))
+      by (cluster, job)"
+    record: "cluster_job:cortex_ingester_queried_series:avg"
+  - expr: "sum(rate(cortex_ingester_queried_series_bucket[5m])) by (le, cluster, job)"
+    record: "cluster_job:cortex_ingester_queried_series_bucket:sum_rate"
+  - expr: "sum(rate(cortex_ingester_queried_series_sum[5m])) by (cluster, job)"
+    record: "cluster_job:cortex_ingester_queried_series_sum:sum_rate"
+  - expr: "sum(rate(cortex_ingester_queried_series_count[5m])) by (cluster, job)"
+    record: "cluster_job:cortex_ingester_queried_series_count:sum_rate"
+  - expr: "histogram_quantile(0.99, sum(rate(cortex_ingester_queried_samples_bucket[5m]))
+      by (le, cluster, job))"
+    record: "cluster_job:cortex_ingester_queried_samples:99quantile"
+  - expr: "histogram_quantile(0.50, sum(rate(cortex_ingester_queried_samples_bucket[5m]))
+      by (le, cluster, job))"
+    record: "cluster_job:cortex_ingester_queried_samples:50quantile"
+  - expr: "sum(rate(cortex_ingester_queried_samples_sum[5m])) by (cluster, job) / sum(rate(cortex_ingester_queried_samples_count[5m]))
+      by (cluster, job)"
+    record: "cluster_job:cortex_ingester_queried_samples:avg"
+  - expr: "sum(rate(cortex_ingester_queried_samples_bucket[5m])) by (le, cluster, job)"
+    record: "cluster_job:cortex_ingester_queried_samples_bucket:sum_rate"
+  - expr: "sum(rate(cortex_ingester_queried_samples_sum[5m])) by (cluster, job)"
+    record: "cluster_job:cortex_ingester_queried_samples_sum:sum_rate"
+  - expr: "sum(rate(cortex_ingester_queried_samples_count[5m])) by (cluster, job)"
+    record: "cluster_job:cortex_ingester_queried_samples_count:sum_rate"
+  - expr: "histogram_quantile(0.99, sum(rate(cortex_ingester_queried_exemplars_bucket[5m]))
+      by (le, cluster, job))"
+    record: "cluster_job:cortex_ingester_queried_exemplars:99quantile"
+  - expr: "histogram_quantile(0.50, sum(rate(cortex_ingester_queried_exemplars_bucket[5m]))
+      by (le, cluster, job))"
+    record: "cluster_job:cortex_ingester_queried_exemplars:50quantile"
+  - expr: "sum(rate(cortex_ingester_queried_exemplars_sum[5m])) by (cluster, job) /
+      sum(rate(cortex_ingester_queried_exemplars_count[5m])) by (cluster, job)"
+    record: "cluster_job:cortex_ingester_queried_exemplars:avg"
+  - expr: "sum(rate(cortex_ingester_queried_exemplars_bucket[5m])) by (le, cluster,
+      job)"
+    record: "cluster_job:cortex_ingester_queried_exemplars_bucket:sum_rate"
+  - expr: "sum(rate(cortex_ingester_queried_exemplars_sum[5m])) by (cluster, job)"
+    record: "cluster_job:cortex_ingester_queried_exemplars_sum:sum_rate"
+  - expr: "sum(rate(cortex_ingester_queried_exemplars_count[5m])) by (cluster, job)"
+    record: "cluster_job:cortex_ingester_queried_exemplars_count:sum_rate"
+- name: "mimir_received_samples"
+  rules:
+  - expr: "sum by (cluster, namespace, job) (rate(cortex_distributor_received_samples_total[5m]))"
+    record: "cluster_namespace_job:cortex_distributor_received_samples:rate5m"
+- name: "mimir_exemplars_in"
+  rules:
+  - expr: "sum by (cluster, namespace, job) (rate(cortex_distributor_exemplars_in_total[5m]))"
+    record: "cluster_namespace_job:cortex_distributor_exemplars_in:rate5m"
+- name: "mimir_received_exemplars"
+  rules:
+  - expr: "sum by (cluster, namespace, job) (rate(cortex_distributor_received_exemplars_total[5m]))"
+    record: "cluster_namespace_job:cortex_distributor_received_exemplars:rate5m"
+- name: "mimir_exemplars_ingested"
+  rules:
+  - expr: "sum by (cluster, namespace, job) (rate(cortex_ingester_ingested_exemplars_total[5m]))"
+    record: "cluster_namespace_job:cortex_ingester_ingested_exemplars:rate5m"
+- name: "mimir_exemplars_appended"
+  rules:
+  - expr: "sum by (cluster, namespace, job) (rate(cortex_ingester_tsdb_exemplar_exemplars_appended_total[5m]))"
+    record: "cluster_namespace_job:cortex_ingester_tsdb_exemplar_exemplars_appended:rate5m"
+- name: "mimir_scaling_rules"
+  rules:
+  - expr: |
+      # Convenience rule to get the number of replicas for both a deployment and a statefulset.
+      # Multi-zone deployments are grouped together removing the "zone-X" suffix.
+      sum by (cluster, namespace, deployment) (
+        label_replace(
+          kube_deployment_spec_replicas,
+          # The question mark in "(.*?)" is used to make it non-greedy, otherwise it
+          # always matches everything and the (optional) zone is not removed.
+          "deployment", "$1", "deployment", "(.*?)(?:-zone-[a-z])?"
+        )
+      )
+      or
+      sum by (cluster, namespace, deployment) (
+        label_replace(kube_statefulset_replicas, "deployment", "$1", "statefulset", "(.*?)(?:-zone-[a-z])?")
+      )
+    record: "cluster_namespace_deployment:actual_replicas:count"
+  - expr: |
+      ceil(
+        quantile_over_time(0.99,
+          sum by (cluster, namespace) (
+            cluster_namespace_job:cortex_distributor_received_samples:rate5m
+          )[24h:]
+        )
+        / 240000
+      )
+    labels:
+      deployment: "distributor"
+      reason: "sample_rate"
+    record: "cluster_namespace_deployment_reason:required_replicas:count"
+  - expr: |
+      ceil(
+        sum by (cluster, namespace) (cortex_limits_overrides{limit_name="ingestion_rate"})
+        * 0.59999999999999998 / 240000
+      )
+    labels:
+      deployment: "distributor"
+      reason: "sample_rate_limits"
+    record: "cluster_namespace_deployment_reason:required_replicas:count"
+  - expr: |
+      ceil(
+        quantile_over_time(0.99,
+          sum by (cluster, namespace) (
+            cluster_namespace_job:cortex_distributor_received_samples:rate5m
+          )[24h:]
+        )
+        * 3 / 80000
+      )
+    labels:
+      deployment: "ingester"
+      reason: "sample_rate"
+    record: "cluster_namespace_deployment_reason:required_replicas:count"
+  - expr: |
+      ceil(
+        quantile_over_time(0.99,
+          sum by(cluster, namespace) (
+            cortex_ingester_memory_series
+          )[24h:]
+        )
+        / 1500000
+      )
+    labels:
+      deployment: "ingester"
+      reason: "active_series"
+    record: "cluster_namespace_deployment_reason:required_replicas:count"
+  - expr: |
+      ceil(
+        sum by (cluster, namespace) (cortex_limits_overrides{limit_name="max_global_series_per_user"})
+        * 3 * 0.59999999999999998 / 1500000
+      )
+    labels:
+      deployment: "ingester"
+      reason: "active_series_limits"
+    record: "cluster_namespace_deployment_reason:required_replicas:count"
+  - expr: |
+      ceil(
+        sum by (cluster, namespace) (cortex_limits_overrides{limit_name="ingestion_rate"})
+        * 0.59999999999999998 / 80000
+      )
+    labels:
+      deployment: "ingester"
+      reason: "sample_rate_limits"
+    record: "cluster_namespace_deployment_reason:required_replicas:count"
+  - expr: |
+      ceil(
+        (sum by (cluster, namespace) (
+          cortex_ingester_tsdb_storage_blocks_bytes{job=~".+/ingester.*"}
+        ) / 4)
+          /
+        avg by (cluster, namespace) (
+          memcached_limit_bytes{job=~".+/memcached"}
+        )
+      )
+    labels:
+      deployment: "memcached"
+      reason: "active_series"
+    record: "cluster_namespace_deployment_reason:required_replicas:count"
+  - expr: |
+      sum by (cluster, namespace, deployment) (
+        label_replace(
+          label_replace(
+            sum by (cluster, namespace, pod)(rate(container_cpu_usage_seconds_total[5m])),
+            "deployment", "$1", "pod", "(.*)-(?:([0-9]+)|([a-z0-9]+)-([a-z0-9]+))"
+          ),
+          # The question mark in "(.*?)" is used to make it non-greedy, otherwise it
+          # always matches everything and the (optional) zone is not removed.
+          "deployment", "$1", "deployment", "(.*?)(?:-zone-[a-z])?"
+        )
+      )
+    record: "cluster_namespace_deployment:container_cpu_usage_seconds_total:sum_rate"
+  - expr: |
+      # Convenience rule to get the CPU request for both a deployment and a statefulset.
+      # Multi-zone deployments are grouped together removing the "zone-X" suffix.
+      # This recording rule is made compatible with the breaking changes introduced in kube-state-metrics v2
+      # that remove resource metrics, ref:
+      # - https://github.com/kubernetes/kube-state-metrics/blob/master/CHANGELOG.md#v200-alpha--2020-09-16
+      # - https://github.com/kubernetes/kube-state-metrics/pull/1004
+      #
+      # This is the old expression, compatible with kube-state-metrics < v2.0.0,
+      # where kube_pod_container_resource_requests_cpu_cores was removed:
+      (
+        sum by (cluster, namespace, deployment) (
+          label_replace(
+            label_replace(
+              kube_pod_container_resource_requests_cpu_cores,
+              "deployment", "$1", "pod", "(.*)-(?:([0-9]+)|([a-z0-9]+)-([a-z0-9]+))"
+            ),
+            # The question mark in "(.*?)" is used to make it non-greedy, otherwise it
+            # always matches everything and the (optional) zone is not removed.
+            "deployment", "$1", "deployment", "(.*?)(?:-zone-[a-z])?"
+          )
+        )
+      )
+      or
+      # This expression is compatible with kube-state-metrics >= v1.4.0,
+      # where kube_pod_container_resource_requests was introduced.
+      (
+        sum by (cluster, namespace, deployment) (
+          label_replace(
+            label_replace(
+              kube_pod_container_resource_requests{resource="cpu"},
+              "deployment", "$1", "pod", "(.*)-(?:([0-9]+)|([a-z0-9]+)-([a-z0-9]+))"
+            ),
+            # The question mark in "(.*?)" is used to make it non-greedy, otherwise it
+            # always matches everything and the (optional) zone is not removed.
+            "deployment", "$1", "deployment", "(.*?)(?:-zone-[a-z])?"
+          )
+        )
+      )
+    record: "cluster_namespace_deployment:kube_pod_container_resource_requests_cpu_cores:sum"
+  - expr: |
+      # Jobs should be sized to their CPU usage.
+      # We do this by comparing 99th percentile usage over the last 24hrs to
+      # their current provisioned #replicas and resource requests.
+      ceil(
+        cluster_namespace_deployment:actual_replicas:count
+          *
+        quantile_over_time(0.99, cluster_namespace_deployment:container_cpu_usage_seconds_total:sum_rate[24h])
+          /
+        cluster_namespace_deployment:kube_pod_container_resource_requests_cpu_cores:sum
+      )
+    labels:
+      reason: "cpu_usage"
+    record: "cluster_namespace_deployment_reason:required_replicas:count"
+  - expr: |
+      # Convenience rule to get the Memory utilization for both a deployment and a statefulset.
+      # Multi-zone deployments are grouped together removing the "zone-X" suffix.
+      sum by (cluster, namespace, deployment) (
+        label_replace(
+          label_replace(
+            container_memory_usage_bytes{image!=""},
+            "deployment", "$1", "pod", "(.*)-(?:([0-9]+)|([a-z0-9]+)-([a-z0-9]+))"
+          ),
+          # The question mark in "(.*?)" is used to make it non-greedy, otherwise it
+          # always matches everything and the (optional) zone is not removed.
+          "deployment", "$1", "deployment", "(.*?)(?:-zone-[a-z])?"
+        )
+      )
+    record: "cluster_namespace_deployment:container_memory_usage_bytes:sum"
+  - expr: |
+      # Convenience rule to get the Memory request for both a deployment and a statefulset.
+      # Multi-zone deployments are grouped together removing the "zone-X" suffix.
+      # This recording rule is made compatible with the breaking changes introduced in kube-state-metrics v2
+      # that remove resource metrics, ref:
+      # - https://github.com/kubernetes/kube-state-metrics/blob/master/CHANGELOG.md#v200-alpha--2020-09-16
+      # - https://github.com/kubernetes/kube-state-metrics/pull/1004
+      #
+      # This is the old expression, compatible with kube-state-metrics < v2.0.0,
+      # where kube_pod_container_resource_requests_memory_bytes was removed:
+      (
+        sum by (cluster, namespace, deployment) (
+          label_replace(
+            label_replace(
+              kube_pod_container_resource_requests_memory_bytes,
+              "deployment", "$1", "pod", "(.*)-(?:([0-9]+)|([a-z0-9]+)-([a-z0-9]+))"
+            ),
+            # The question mark in "(.*?)" is used to make it non-greedy, otherwise it
+            # always matches everything and the (optional) zone is not removed.
+            "deployment", "$1", "deployment", "(.*?)(?:-zone-[a-z])?"
+          )
+        )
+      )
+      or
+      # This expression is compatible with kube-state-metrics >= v1.4.0,
+      # where kube_pod_container_resource_requests was introduced.
+      (
+        sum by (cluster, namespace, deployment) (
+          label_replace(
+            label_replace(
+              kube_pod_container_resource_requests{resource="memory"},
+              "deployment", "$1", "pod", "(.*)-(?:([0-9]+)|([a-z0-9]+)-([a-z0-9]+))"
+            ),
+            # The question mark in "(.*?)" is used to make it non-greedy, otherwise it
+            # always matches everything and the (optional) zone is not removed.
+            "deployment", "$1", "deployment", "(.*?)(?:-zone-[a-z])?"
+          )
+        )
+      )
+    record: "cluster_namespace_deployment:kube_pod_container_resource_requests_memory_bytes:sum"
+  - expr: |
+      # Jobs should be sized to their Memory usage.
+      # We do this by comparing 99th percentile usage over the last 24hrs to
+      # their current provisioned #replicas and resource requests.
+      ceil(
+        cluster_namespace_deployment:actual_replicas:count
+          *
+        quantile_over_time(0.99, cluster_namespace_deployment:container_memory_usage_bytes:sum[24h])
+          /
+        cluster_namespace_deployment:kube_pod_container_resource_requests_memory_bytes:sum
+      )
+    labels:
+      reason: "memory_usage"
+    record: "cluster_namespace_deployment_reason:required_replicas:count"
+- name: "mimir_alertmanager_rules"
+  rules:
+  - expr: "sum by (cluster, job, pod) (cortex_alertmanager_alerts)"
+    record: "cluster_job_pod:cortex_alertmanager_alerts:sum"
+  - expr: "sum by (cluster, job, pod) (cortex_alertmanager_silences)"
+    record: "cluster_job_pod:cortex_alertmanager_silences:sum"
+  - expr: "sum by (cluster, job) (rate(cortex_alertmanager_alerts_received_total[5m]))"
+    record: "cluster_job:cortex_alertmanager_alerts_received_total:rate5m"
+  - expr: "sum by (cluster, job) (rate(cortex_alertmanager_alerts_invalid_total[5m]))"
+    record: "cluster_job:cortex_alertmanager_alerts_invalid_total:rate5m"
+  - expr: "sum by (cluster, job, integration) (rate(cortex_alertmanager_notifications_total[5m]))"
+    record: "cluster_job_integration:cortex_alertmanager_notifications_total:rate5m"
+  - expr: "sum by (cluster, job, integration) (rate(cortex_alertmanager_notifications_failed_total[5m]))"
+    record: "cluster_job_integration:cortex_alertmanager_notifications_failed_total:rate5m"
+  - expr: "sum by (cluster, job) (rate(cortex_alertmanager_state_replication_total[5m]))"
+    record: "cluster_job:cortex_alertmanager_state_replication_total:rate5m"
+  - expr: "sum by (cluster, job) (rate(cortex_alertmanager_state_replication_failed_total[5m]))"
+    record: "cluster_job:cortex_alertmanager_state_replication_failed_total:rate5m"
+  - expr: "sum by (cluster, job) (rate(cortex_alertmanager_partial_state_merges_total[5m]))"
+    record: "cluster_job:cortex_alertmanager_partial_state_merges_total:rate5m"
+  - expr: "sum by (cluster, job) (rate(cortex_alertmanager_partial_state_merges_failed_total[5m]))"
+    record: "cluster_job:cortex_alertmanager_partial_state_merges_failed_total:rate5m"
+- name: "mimir_ingester_rules"
+  rules:
+  - expr: "sum by(cluster, namespace, pod) (rate(cortex_ingester_ingested_samples_total[5m]))"
+    record: "cluster_namespace_pod:cortex_ingester_ingested_samples_total:rate1m"

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

@@ -0,0 +1,15 @@
+groups:
+- name: "tempo_rules"
+  rules:
+  - expr: "histogram_quantile(0.99, sum(rate(tempo_request_duration_seconds_bucket[5m])) by (le, cluster, namespace, job, route))"
+    record: "cluster_namespace_job_route:tempo_request_duration_seconds:99quantile"
+  - expr: "histogram_quantile(0.50, sum(rate(tempo_request_duration_seconds_bucket[5m])) by (le, cluster, namespace, job, route))"
+    record: "cluster_namespace_job_route:tempo_request_duration_seconds:50quantile"
+  - expr: "sum(rate(tempo_request_duration_seconds_sum[5m])) by (cluster, namespace, job, route) / sum(rate(tempo_request_duration_seconds_count[5m])) by (cluster, namespace, job, route)"
+    record: "cluster_namespace_job_route:tempo_request_duration_seconds:avg"
+  - expr: "sum(rate(tempo_request_duration_seconds_bucket[5m])) by (le, cluster, namespace, job, route)"
+    record: "cluster_namespace_job_route:tempo_request_duration_seconds_bucket:sum_rate"
+  - expr: "sum(rate(tempo_request_duration_seconds_sum[5m])) by (cluster, namespace, job, route)"
+    record: "cluster_namespace_job_route:tempo_request_duration_seconds_sum:sum_rate"
+  - expr: "sum(rate(tempo_request_duration_seconds_count[5m])) by (cluster, namespace, job, route)"
+    record: "cluster_namespace_job_route:tempo_request_duration_seconds_count:sum_rate"

charts/meta-monitoring/templates/_helpers.tpl

@@ -0,0 +1,33 @@
+{{/*
+Return the appropriate apiVersion for ingress.
+*/}}
+{{- define "ingress.apiVersion" -}}
+  {{- if and (.Capabilities.APIVersions.Has "networking.k8s.io/v1") (semverCompare ">= 1.19-0" .Capabilities.KubeVersion.Version) -}}
+      {{- print "networking.k8s.io/v1" -}}
+  {{- else if .Capabilities.APIVersions.Has "networking.k8s.io/v1beta1" -}}
+    {{- print "networking.k8s.io/v1beta1" -}}
+  {{- else -}}
+    {{- print "extensions/v1beta1" -}}
+  {{- end -}}
+{{- end -}}
+
+{{/*
+Return if ingress is stable.
+*/}}
+{{- define "ingress.isStable" -}}
+  {{- eq (include "ingress.apiVersion" .) "networking.k8s.io/v1" -}}
+{{- end -}}
+
+{{/*
+Return if ingress supports ingressClassName.
+*/}}
+{{- define "ingress.supportsIngressClassName" -}}
+  {{- or (eq (include "ingress.isStable" .) "true") (and (eq (include "ingress.apiVersion" .) "networking.k8s.io/v1beta1") (semverCompare ">= 1.18-0" .Capabilities.KubeVersion.Version)) -}}
+{{- end -}}
+
+{{/*
+Return if ingress supports pathType.
+*/}}
+{{- define "ingress.supportsPathType" -}}
+  {{- or (eq (include "ingress.isStable" .) "true") (and (eq (include "ingress.apiVersion" .) "networking.k8s.io/v1beta1") (semverCompare ">= 1.18-0" .Capabilities.KubeVersion.Version)) -}}
+{{- end -}}

charts/meta-monitoring/templates/agent/_helpers-agent.tpl

@@ -6,6 +6,15 @@
 {{- join ", " $list }}
 {{- end }}
 
+{{- define "agent.all_namespaces" -}}
+{{- $list := list }}
+{{- range .Values.namespacesToMonitor }}
+{{- $list = append $list (printf "%s" .) }}
+{{- end }}
+{{- $list = append $list .Release.Namespace }}
+{{- join "|" $list }}
+{{- end }}
+
 {{- define "agent.loki_write_targets" -}}
 {{- $list := list }}
 {{- if .Values.local.logs.enabled }}
@@ -17,6 +26,14 @@
 {{- join ", " $list }}
 {{- end }}
 
+{{- define "agent.loki_process_targets" -}}
+{{- if and (empty .Values.logs.piiRegexes) (empty .Values.logs.retain) }}
+{{- include "agent.loki_write_targets" . }}
+{{- else }}
+{{- printf "loki.process.filter.receiver" }}
+{{- end }}
+{{- end }}
+
 {{- define "agent.prometheus_write_targets" -}}
 {{- $list := list }}
 {{- if .Values.local.metrics.enabled }}
@@ -31,10 +48,32 @@
 {{- define "agent.tempo_write_targets" -}}
 {{- $list := list }}
 {{- if .Values.local.traces.enabled }}
-{{- $list = append $list ("otelcol.exporter.otlp.local.input") }}
+{{- $list = append $list ("otelcol.exporter.otlphttp.local.input") }}
 {{- end }}
 {{- if .Values.cloud.traces.enabled }}
-{{- $list = append $list ("otelcol.exporter.otlp.cloud.input") }}
+{{- $list = append $list ("otelcol.exporter.otlphttp.cloud.input") }}
 {{- end }}
 {{- join ", " $list }}
+{{- end }}
+
+{{- define "agent.all_logs" -}}
+{{- $list := list }}
+{{- range .Values.logs.retain }}
+{{- $list = append $list . }}
+{{- end }}
+{{- range .Values.logs.extraLogs }}
+{{- $list = append $list . }}
+{{- end }}
+{{- join "|" $list }}
+{{- end }}
+
+{{- define "agent.all_metrics" -}}
+{{- $list := list }}
+{{- range .Values.metrics.retain }}
+{{- $list = append $list . }}
+{{- end }}
+{{- range .Values.metrics.extraMetrics }}
+{{- $list = append $list . }}
+{{- end }}
+{{- join "|" $list }}
 {{- end }}

charts/meta-monitoring/templates/agent/config.yaml

@@ -8,7 +8,7 @@ data:
     discovery.kubernetes "pods" {
       role = "pod"
       namespaces {
-        own_namespace = false
+        own_namespace = true
         names = [ {{ include "agent.namespaces" . }} ]
       }
     }
@@ -33,38 +33,283 @@ data:
       }
       rule {
         target_label = "cluster"
-        replacement = "{{- .Values.clusterName -}}"
+        replacement = "{{- .Values.clusterLabelValue -}}"
       }
     }
 
     {{- if or .Values.local.logs.enabled .Values.cloud.logs.enabled }}
-    loki.source.kubernetes "pods" {
+    // Logs
-      targets    = discovery.relabel.rename_meta_labels.output
+
-      forward_to = [ {{ include "agent.loki_write_targets" . }} ]
+    {{- if .Values.cloud.logs.enabled }}
+    remote.kubernetes.secret "logs_credentials" {
+      namespace = "{{- $.Release.Namespace -}}"
+      name = "{{- .Values.cloud.logs.secret -}}"
     }
     {{- end }}
 
-    {{- if or .Values.local.metrics.enabled .Values.cloud.metrics.enabled }}
+    loki.source.kubernetes "pods" {
-    prometheus.scrape "pods" {
+      clustering {
+        enabled = true
+      }
       targets    = discovery.relabel.rename_meta_labels.output
+      forward_to = [ {{ include "agent.loki_process_targets" . }} ]
+    }
+
+    {{- if or (not (empty .Values.logs.retain)) (not (empty .Values.logs.piiRegexes)) }}
+    loki.process "filter" {
+      forward_to = [ {{ include "agent.loki_write_targets" . }} ]
+
+      {{- if or (not (empty .Values.logs.retain)) (not (empty .Values.logs.extraLogs)) }}
+      stage.match {
+        selector = "{cluster=\"{{- .Values.clusterLabelValue -}}\", namespace=~\"{{- join "|" .Values.namespacesToMonitor -}}|{{- $.Release.Namespace -}}\", pod=~\"loki.*\"} !~ \"{{ include "agent.all_logs" . }}\""
+        action   = "drop"
+      }
+      {{- end }}
+
+      {{- if not (empty .Values.logs.piiRegexes) }}
+      {{- range .Values.logs.piiRegexes }}
+      stage.replace {
+        expression = "{{ .expression }}"
+        source = "{{ .source }}"
+        replace = "{{ .replace }}"
+      }
+      {{- end }}
+      {{- end }}
+    }
+    {{- end }}
+    {{- end }}
+
+    {{- if or .Values.local.metrics.enabled .Values.cloud.metrics.enabled }}
+    // Metrics
+
+    {{- if .Values.cloud.metrics.enabled }}
+    remote.kubernetes.secret "metrics_credentials" {
+      namespace = "{{- $.Release.Namespace -}}"
+      name = "{{- .Values.cloud.metrics.secret -}}"
+    }
+    {{- end }}
+
+    discovery.kubernetes "metric_pods" {
+      role = "pod"
+      namespaces {
+        own_namespace = true
+        names = [ {{ include "agent.namespaces" . }} ]
+      }
+    }
+
+    discovery.relabel "only_http_metrics" {
+      targets = discovery.kubernetes.metric_pods.targets
+
+      rule {
+        source_labels = ["__meta_kubernetes_namespace"]
+        target_label  = "namespace"
+      }
+      rule {
+        source_labels = ["__meta_kubernetes_pod_name"]
+        target_label  = "pod"
+      }
+      rule {
+        source_labels = ["__meta_kubernetes_namespace", "__meta_kubernetes_pod_label_app_kubernetes_io_name", "__meta_kubernetes_pod_label_app_kubernetes_io_component"]
+        separator = "/"
+        regex = "(.*)/(.*)/(.*)"
+        replacement = "${1}/${2}-${3}"
+        target_label = "job"
+      }
+      rule {
+        target_label = "cluster"
+        replacement = "{{- .Values.clusterLabelValue -}}"
+      }
+      rule {
+        source_labels = ["__meta_kubernetes_pod_container_port_number"]
+        action = "drop"
+        regex = "9095"
+      }
+    }
+
+    prometheus.scrape "pods" {
+      clustering {
+        enabled = true
+      }
+      targets    = discovery.relabel.only_http_metrics.output
+      forward_to = [ prometheus.relabel.filter.receiver ]
+    }
+
+    prometheus.relabel "filter" {
+      rule {
+        source_labels = ["__name__"]
+        regex = "({{ include "agent.all_metrics" . }})"
+        action = "keep"
+      }
+
+      rule {
+        source_labels = ["namespace"]
+        regex = "{{ include "agent.all_namespaces" . }}"
+
+        action = "keep"
+      }
+
       forward_to = [ {{ include "agent.prometheus_write_targets" . }} ]
     }
+    {{- if .Values.kubeStateMetrics.enabled }}
+
+    prometheus.scrape "kubeStateMetrics" {
+      clustering {
+        enabled = true
+      }
+      targets    = [ { "__address__" = "{{ .Values.kubeStateMetrics.endpoint }}" } ]
+      forward_to = [ prometheus.relabel.filter.receiver ]
+    }
+    {{- end }}
+
+    // cAdvisor and Kubelet metrics
+    // Based on https://github.com/Chewie/loutretelecom-manifests/blob/main/manifests/addons/monitoring/config.river
+    discovery.kubernetes "all_nodes" {
+      role = "node"
+      namespaces {
+        own_namespace = true
+        names = [ {{ include "agent.namespaces" . }} ]
+      }
+    }
+
+    discovery.relabel "all_nodes" {
+      targets = discovery.kubernetes.all_nodes.targets
+      rule {
+        source_labels = ["__meta_kubernetes_node_name"]
+        target_label = "node"
+      }
+      rule {
+        source_labels = ["__meta_kubernetes_namespace"]
+        target_label  = "namespace"
+      }
+      rule {
+        source_labels = ["__meta_kubernetes_pod_name"]
+        target_label  = "pod"
+      }
+      rule {
+        source_labels = ["__meta_kubernetes_namespace", "__meta_kubernetes_pod_label_app_kubernetes_io_name", "__meta_kubernetes_pod_label_app_kubernetes_io_component"]
+        separator = "/"
+        regex = "(.*)/(.*)/(.*)"
+        replacement = "${1}/${2}-${3}"
+        target_label = "job"
+      }
+      rule {
+        target_label = "cluster"
+        replacement = "{{- .Values.clusterLabelValue -}}"
+      }
+    }
+
+    prometheus.scrape "cadvisor" {
+      clustering {
+        enabled = true
+      }
+      targets    = discovery.relabel.all_nodes.output
+      forward_to = [ prometheus.relabel.filter.receiver ]
+
+      metrics_path = "/metrics/cadvisor"
+      scheme = "https"
+
+      bearer_token_file = "/var/run/secrets/kubernetes.io/serviceaccount/token"
+      tls_config {
+        ca_file = "/var/run/secrets/kubernetes.io/serviceaccount/ca.crt"
+      }
+    }
+
+    prometheus.scrape "kubelet" {
+      clustering {
+        enabled = true
+      }
+      targets    = discovery.relabel.all_nodes.output
+      forward_to = [ prometheus.relabel.filter.receiver ]
+
+      metrics_path = "/metrics"
+      scheme = "https"
+
+      bearer_token_file = "/var/run/secrets/kubernetes.io/serviceaccount/token"
+      tls_config {
+        ca_file = "/var/run/secrets/kubernetes.io/serviceaccount/ca.crt"
+      }
+    }
+
+    prometheus.exporter.unix "promexporter" {}
+
+    prometheus.scrape "node_exporter" {
+      clustering {
+        enabled = true
+      }
+      targets = prometheus.exporter.unix.promexporter.targets
+      forward_to = [prometheus.relabel.node_exporter.receiver]
+
+      job_name = "node-exporter"
+    }
+
+    prometheus.relabel "node_exporter" {
+      forward_to = [ prometheus.relabel.filter.receiver ]
+
+      rule {
+        replacement = env("HOSTNAME")
+        target_label = "nodename"
+      }
+      rule {
+        replacement = "node-exporter"
+        target_label = "job"
+      }
+      rule {
+        source_labels = ["__meta_kubernetes_node_name"]
+        target_label = "node"
+      }
+      rule {
+        source_labels = ["__meta_kubernetes_namespace"]
+        target_label  = "namespace"
+      }
+      rule {
+        source_labels = ["__meta_kubernetes_pod_name"]
+        target_label  = "pod"
+      }
+      rule {
+        source_labels = ["__meta_kubernetes_namespace", "__meta_kubernetes_pod_label_app_kubernetes_io_name", "__meta_kubernetes_pod_label_app_kubernetes_io_component"]
+        separator = "/"
+        regex = "(.*)/(.*)/(.*)"
+        replacement = "${1}/${2}-${3}"
+        target_label = "job"
+      }
+      rule {
+        target_label = "cluster"
+        replacement = "{{- .Values.clusterLabelValue -}}"
+      }
+    }
     {{- end }}
 
     {{- if or .Values.local.traces.enabled .Values.cloud.traces.enabled }}
+    // Traces
+
+    {{- if .Values.cloud.traces.enabled }}
+    remote.kubernetes.secret "traces_credentials" {
+      namespace = "{{- $.Release.Namespace -}}"
+      name = "{{- .Values.cloud.traces.secret -}}"
+    }
+    {{- end }}
+
     // Shamelessly copied from https://github.com/grafana/intro-to-mlt/blob/main/agent/config.river
     otelcol.receiver.otlp "otlp_receiver" {
       // We don't technically need this, but it shows how to change listen address and incoming port.
       // In this case, the Agent is listening on all available bindable addresses on port 4317 (which is the
       // default OTLP gRPC port) for the OTLP protocol.
-      grpc {
+      grpc {}
-          endpoint = "0.0.0.0:4317"
-      }
 
       // We define where to send the output of all ingested traces. In this case, to the OpenTelemetry batch processor
       // named 'default'.
       output {
-          traces = [otelcol.processor.batch.default.input]
+        traces = [otelcol.processor.batch.default.input]
+      }
+    }
+
+    otelcol.receiver.jaeger "jaeger" {
+      protocols {
+        thrift_http {}
+      }
+
+      output {
+        traces = [otelcol.processor.batch.default.input]
       }
     }
 
@@ -85,7 +330,7 @@ data:
     {{- if .Values.local.logs.enabled }}
     loki.write "local" {
       endpoint {
-        url = "http://loki-gateway.{{- .Release.Namespace -}}.svc.cluster.local:80/loki/api/v1/push"
+        url = "http://{{- .Release.Namespace -}}-loki-gateway.{{- .Release.Namespace -}}.svc.cluster.local:80/loki/api/v1/push"
       }
     }
     {{- end }}
@@ -98,21 +343,10 @@ data:
     }
     {{- end }}
 
-    {{- if or .Values.local.traces.enabled .Values.cloud.traces.enabled }}
+    {{- if .Values.local.traces.enabled }}
-    // The OpenTelemetry exporter exports processed trace spans to another target that is listening for OTLP format traces.
+    otelcol.exporter.otlphttp "local" {
-    // A unique label, 'local', is added to uniquely identify this exporter.
-    otelcol.exporter.otlp "local" {
-        // Define the client for exporting.
         client {
-            // Send to the locally running Tempo instance, on port 4317 (OTLP gRPC).
+            endpoint = "http://{{- .Release.Name -}}-tempo-distributor.svc:4318"
-            endpoint = "meta-tempo-distributor:4317"
-            // Configure TLS settings for communicating with the endpoint.
-            tls {
-                // The connection is insecure.
-                insecure = true
-                // Do not verify TLS certificates when connecting.
-                insecure_skip_verify = true
-            }
         }
     }
     {{- end }}
@@ -120,11 +354,10 @@ data:
     {{- if .Values.cloud.logs.enabled }}
     loki.write "cloud" {
       endpoint {
-        url = "{{- .Values.cloud.logs.endpoint -}}/loki/api/v1/push"
+        url = nonsensitive(remote.kubernetes.secret.logs_credentials.data["endpoint"])
-
         basic_auth {
-          username = "{{- .Values.cloud.logs.username -}}"
+          username = nonsensitive(remote.kubernetes.secret.logs_credentials.data["username"])
-          password = "{{- .Values.cloud.logs.password -}}"
+          password = remote.kubernetes.secret.logs_credentials.data["password"]
         }
       }
     }
@@ -133,26 +366,25 @@ data:
     {{- if .Values.cloud.metrics.enabled }}
     prometheus.remote_write "cloud" {
       endpoint {
-        url = "{{- .Values.cloud.metrics.endpoint -}}/api/prom/push"
+        url = nonsensitive(remote.kubernetes.secret.metrics_credentials.data["endpoint"])
-
         basic_auth {
-          username = "{{- .Values.cloud.metrics.username -}}"
+          username = nonsensitive(remote.kubernetes.secret.metrics_credentials.data["username"])
-          password = "{{- .Values.cloud.metrics.password -}}"
+          password = remote.kubernetes.secret.metrics_credentials.data["password"]
         }
       }
     }
     {{- end }}
 
     {{- if .Values.cloud.traces.enabled }}
-    otelcol.exporter.otlp "cloud" {
+    otelcol.exporter.otlphttp "cloud" {
         client {
-            endpoint = "{{- .Values.cloud.traces.endpoint -}}"
+            endpoint = nonsensitive(remote.kubernetes.secret.traces_credentials.data["endpoint"])
             auth = otelcol.auth.basic.creds.handler
         }
     }
 
     otelcol.auth.basic "creds" {
-      username = "{{- .Values.cloud.traces.username -}}"
+      username = nonsensitive(remote.kubernetes.secret.traces_credentials.data["username"])
-      password = "{{- .Values.cloud.traces.password -}}"
+      password = remote.kubernetes.secret.traces_credentials.data["password"]
     }
     {{- end }}

charts/meta-monitoring/templates/grafana/agent-dashboards-1.yaml

@@ -0,0 +1,19 @@
+{{- if and .Values.local.grafana.enabled .Values.dashboards.logs.enabled }}
+---
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: agent-dashboards-1
+  namespace: {{ $.Release.Namespace }}
+data:
+  "agent-logs-pipeline.json": |
+    {{ $.Files.Get "src/dashboards/agent-logs-pipeline.json" | fromJson | toJson }}
+  "agent-operational.json": |
+    {{ $.Files.Get "src/dashboards/agent-operational.json" | fromJson | toJson }}
+  "agent-remote-write.json": |
+    {{ $.Files.Get "src/dashboards/agent-remote-write.json" | fromJson | toJson }}
+  "agent-tracing-pipeline.json": |
+    {{ $.Files.Get "src/dashboards/agent-tracing-pipeline.json" | fromJson | toJson }}
+  "agent.json": |
+    {{ $.Files.Get "src/dashboards/agent.json" | fromJson | toJson }}
+{{- end }}

charts/meta-monitoring/templates/grafana/dashboard.yaml

@@ -1,15 +1,16 @@
-{{- if .Values.local.logs.enabled }}
+{{- if and .Values.local.grafana.enabled .Values.dashboards.logs.enabled }}
 ---
 apiVersion: v1
 kind: ConfigMap
 metadata:
-  name: loki-dashboards-provisioning
+  name: dashboards-provisioning
   namespace: {{ $.Release.Namespace }}
 data:
   dashboards.yaml: |
     ---
     apiVersion: 1
     providers:
+{{- if .Values.dashboards.logs.enabled }}
       - disableDeletion: true
         editable: false
         folder: Loki
@@ -26,4 +27,13 @@ data:
           path: /var/lib/grafana/dashboards/loki-2
         orgId: 1
         type: file
+{{- end }}
+      - disableDeletion: true
+        editable: false
+        folder: Agent
+        name: agent-1
+        options:
+          path: /var/lib/grafana/dashboards/agent-1
+        orgId: 1
+        type: file
 {{- end }}

charts/meta-monitoring/templates/grafana/datasources.yaml

@@ -1,9 +1,9 @@
-{{- if or (or .Values.local.logs.enabled .Values.local.metrics.enabled) .Values.local.traces.enabled }}
+{{- if .Values.local.grafana.enabled }}
 ---
 apiVersion: v1
 kind: ConfigMap
 metadata:
-  name: loki-datasources-provisioning
+  name: datasources-provisioning
   namespace: {{ $.Release.Namespace }}
 data:
   datasources.yaml: |
@@ -12,7 +12,7 @@ data:
 
     # List of data sources to delete from the database.
     deleteDatasources:
-      - name: Loki 
+      - name: Loki
         orgId: 1
 
     # List of data sources to insert/update depending on what's
@@ -32,7 +32,7 @@ data:
         uid: loki_ds
         # <string> Sets the data source's URL, including the
         # port.
-        url: http://loki-gateway.{{- $.Release.Namespace -}}.svc.cluster.local
+        url: http://{{- $.Release.Namespace -}}-loki-gateway.{{- $.Release.Namespace -}}.svc.cluster.local
         # <bool> Toggles whether the data source is pre-selected
         # for new panels. You can set only one default
         # data source per organization.
@@ -61,6 +61,10 @@ data:
         # <bool> Allows users to edit data sources from the
         # Grafana UI.
         editable: true
+        # Extra config.
+        jsonData:
+          # Scrape interval
+          timeInterval: 1m
       {{- end }}
       {{- if .Values.local.traces.enabled }}
       - name: Tempo

charts/meta-monitoring/templates/grafana/grafana-deployment.yaml

@@ -1,16 +1,4 @@
-{{- if or (or .Values.local.logs.enabled .Values.local.metrics.enabled) .Values.local.traces.enabled }}
+{{- if .Values.local.grafana.enabled }}
----
-apiVersion: v1
-kind: PersistentVolumeClaim
-metadata:
-  name: grafana-pvc
-spec:
-  accessModes:
-    - ReadWriteOnce
-  resources:
-    requests:
-      storage: 1Gi
----
 apiVersion: apps/v1
 kind: Deployment
 metadata:
@@ -32,7 +20,7 @@ spec:
           - 0
       containers:
         - name: grafana
-          image: grafana/grafana:10.0.0
+          image: grafana/grafana:{{- .Values.grafana.version }}
           imagePullPolicy: IfNotPresent
           ports:
             - containerPort: 3000
@@ -64,26 +52,30 @@ spec:
             - mountPath: /var/lib/grafana
               name: grafana-pv
             - mountPath: /etc/grafana/provisioning/datasources
-              name: loki-datasources-provisioning
+              name: datasources-provisioning
-            {{- if .Values.local.logs.enabled }}
+            {{- if .Values.dashboards.logs.enabled }}
             - mountPath: /etc/grafana/provisioning/dashboards
-              name: loki-dashboards-provisioning
+              name: dashboards-provisioning
+            {{- end }}
+            {{- if .Values.dashboards.logs.enabled }}
             - mountPath: /var/lib/grafana/dashboards/loki-1
               name: loki-dashboards-1
             - mountPath: /var/lib/grafana/dashboards/loki-2
               name: loki-dashboards-2
             {{- end }}
+            - mountPath: /var/lib/grafana/dashboards/agent-1
+              name: agent-dashboards-1
       volumes:
         - name: grafana-pv
           persistentVolumeClaim:
             claimName: grafana-pvc
-        - name: loki-datasources-provisioning
+        - name: datasources-provisioning
           configMap:
-            name: loki-datasources-provisioning
+            name: datasources-provisioning
-        {{- if .Values.local.logs.enabled }}
+        - name: dashboards-provisioning
-        - name: loki-dashboards-provisioning
           configMap:
-            name: loki-dashboards-provisioning
+            name: dashboards-provisioning
+        {{- if .Values.dashboards.logs.enabled }}
         - name: loki-dashboards-1
           configMap:
             name: loki-dashboards-1
@@ -91,19 +83,7 @@ spec:
           configMap:
             name: loki-dashboards-2
         {{- end }}
-
+        - name: agent-dashboards-1
----
+          configMap:
-apiVersion: v1
+            name: agent-dashboards-1
-kind: Service
+{{- end }}
-metadata:
-  name: grafana
-spec:
-  ports:
-    - port: 3000
-      protocol: TCP
-      targetPort: http-grafana
-  selector:
-    app: grafana
-  sessionAffinity: None
-  type: ClusterIP  # Make this configurable
-{{- end }}

charts/meta-monitoring/templates/grafana/grafana-ingress.yaml

@@ -0,0 +1,57 @@
+{{- if and .Values.local.grafana.enabled .Values.grafana.ingress.enabled -}}
+{{- $ingressApiIsStable := eq (include "ingress.isStable" .) "true" -}}
+{{- $ingressSupportsIngressClassName := eq (include "ingress.supportsIngressClassName" .) "true" -}}
+{{- $ingressSupportsPathType := eq (include "ingress.supportsPathType" .) "true" -}}
+apiVersion: {{ include "ingress.apiVersion" . }}
+kind: Ingress
+metadata:
+  name: grafana
+  namespace: {{ $.Release.Namespace }}
+  labels:
+    app: grafana
+    {{- range $labelKey, $labelValue := .Values.grafana.ingress.labels }}
+    {{ $labelKey }}: {{ $labelValue | toYaml }}
+    {{- end }}
+  {{- with .Values.grafana.ingress.annotations }}
+  annotations:
+    {{- toYaml . | nindent 4 }}
+  {{- end }}
+spec:
+  {{- if and $ingressSupportsIngressClassName .Values.grafana.ingress.ingressClassName }}
+  ingressClassName: {{ .Values.grafana.ingress.ingressClassName }}
+  {{- end -}}
+  {{- if .Values.grafana.ingress.tls }}
+  tls:
+    {{- range .Values.grafana.ingress.tls }}
+    - hosts:
+        {{- range .hosts }}
+        - {{ tpl . $ | quote }}
+        {{- end }}
+      {{- with .secretName }}
+      secretName: {{ . }}
+      {{- end }}
+    {{- end }}
+  {{- end }}
+  rules:
+    {{- range .Values.grafana.ingress.hosts }}
+    - host: {{ tpl .host $ | quote }}
+      http:
+        paths:
+          {{- range .paths }}
+          - path: {{ .path }}
+            {{- if $ingressSupportsPathType }}
+            pathType: {{ .pathType }}
+            {{- end }}
+            backend:
+              {{- if $ingressApiIsStable }}
+              service:
+                name: grafana
+                port:
+                  number: 3000
+              {{- else }}
+              serviceName: grafana
+              servicePort: 3000
+              {{- end }}
+          {{- end }}
+    {{- end }}
+{{- end }}

charts/meta-monitoring/templates/grafana/grafana-pvc.yaml

@@ -0,0 +1,12 @@
+{{- if .Values.local.grafana.enabled }}
+apiVersion: v1
+kind: PersistentVolumeClaim
+metadata:
+  name: grafana-pvc
+spec:
+  accessModes:
+    - ReadWriteOnce
+  resources:
+    requests:
+      storage: 1Gi
+{{- end }}

charts/meta-monitoring/templates/grafana/grafana-service.yaml

@@ -0,0 +1,15 @@
+{{- if .Values.local.grafana.enabled }}
+apiVersion: v1
+kind: Service
+metadata:
+  name: grafana
+spec:
+  ports:
+    - port: 3000
+      protocol: TCP
+      targetPort: http-grafana
+  selector:
+    app: grafana
+  sessionAffinity: None
+  type: ClusterIP  # Make this configurable
+{{- end }}

charts/meta-monitoring/templates/grafana/loki-dashboards-1.yaml

@@ -1,4 +1,4 @@
-{{- if .Values.local.logs.enabled }}
+{{- if and .Values.local.grafana.enabled .Values.dashboards.logs.enabled }}
 ---
 apiVersion: v1
 kind: ConfigMap

charts/meta-monitoring/templates/grafana/loki-dashboards-2.yaml

@@ -1,4 +1,4 @@
-{{- if .Values.local.logs.enabled }}
+{{- if and .Values.local.grafana.enabled .Values.dashboards.logs.enabled }}
 ---
 apiVersion: v1
 kind: ConfigMap

charts/meta-monitoring/templates/ruler/ruler.yaml

@@ -0,0 +1,129 @@
+{{- if .Values.local.grafana.enabled }}
+{{- if and .Values.local.grafana.enabled .Values.dashboards.logs.enabled }}
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: {{ $.Release.Namespace }}-mimir-ruler-for-dashboards
+  namespace: {{ $.Release.Namespace }}
+spec:
+  progressDeadlineSeconds: 600
+  replicas: 1
+  revisionHistoryLimit: 10
+  selector:
+    matchLabels:
+      app.kubernetes.io/component: ruler-for-dashboards
+      app.kubernetes.io/instance: meta
+      app.kubernetes.io/name: mimir
+  strategy:
+    rollingUpdate:
+      maxSurge: 50%
+      maxUnavailable: 0
+    type: RollingUpdate
+  template:
+    metadata:
+      labels:
+        app.kubernetes.io/component: ruler-for-dashboards
+        app.kubernetes.io/instance: meta
+        app.kubernetes.io/name: mimir
+      namespace: {{ $.Release.Namespace }}
+    spec:
+      containers:
+        - args:
+            - -target=ruler
+            - -log.level=debug
+            - -ruler-storage.backend=local
+            - -ruler-storage.local.directory=/etc/rules
+            - -ruler.ring.prefix=dashboards/
+            - -config.expand-env=true
+            - -config.file=/etc/mimir/mimir.yaml
+          image: grafana/mimir:2.8.0
+          imagePullPolicy: IfNotPresent
+          name: ruler
+          ports:
+            - containerPort: 8080
+              name: http-metrics
+              protocol: TCP
+            - containerPort: 9095
+              name: grpc
+              protocol: TCP
+            - containerPort: 7946
+              name: memberlist
+              protocol: TCP
+          envFrom:
+          - secretRef:
+             name: minio
+          readinessProbe:
+            failureThreshold: 3
+            httpGet:
+              path: /ready
+              port: http-metrics
+              scheme: HTTP
+            initialDelaySeconds: 45
+            periodSeconds: 10
+            successThreshold: 1
+            timeoutSeconds: 1
+          resources:
+            requests:
+              cpu: 100m
+              memory: 128Mi
+          securityContext:
+            allowPrivilegeEscalation: false
+            capabilities:
+              drop:
+                - ALL
+            readOnlyRootFilesystem: true
+          terminationMessagePath: /dev/termination-log
+          terminationMessagePolicy: File
+          volumeMounts:
+            - mountPath: /etc/mimir
+              name: config
+            - mountPath: /var/mimir
+              name: runtime-config
+            - mountPath: /data
+              name: storage
+            - mountPath: /active-query-tracker
+              name: active-queries
+            - mountPath: /etc/rules/anonymous
+              name: rules
+      dnsPolicy: ClusterFirst
+      restartPolicy: Always
+      schedulerName: default-scheduler
+      securityContext:
+        fsGroup: 10001
+        runAsGroup: 10001
+        runAsNonRoot: true
+        runAsUser: 10001
+        seccompProfile:
+          type: RuntimeDefault
+      terminationGracePeriodSeconds: 180
+      topologySpreadConstraints:
+        - labelSelector:
+            matchLabels:
+              app.kubernetes.io/component: ruler
+              app.kubernetes.io/instance: meta
+              app.kubernetes.io/name: mimir
+          maxSkew: 1
+          topologyKey: kubernetes.io/hostname
+          whenUnsatisfiable: ScheduleAnyway
+      volumes:
+        - configMap:
+            defaultMode: 420
+            items:
+              - key: mimir.yaml
+                path: mimir.yaml
+            name: {{ $.Release.Namespace }}-mimir-config
+          name: config
+        - configMap:
+            defaultMode: 420
+            name: {{ $.Release.Namespace }}-mimir-runtime
+          name: runtime-config
+        - emptyDir: {}
+          name: storage
+        - emptyDir: {}
+          name: active-queries
+        - configMap:
+            defaultMode: 420
+            name: rules
+          name: rules
+{{- end }}
+{{- end }}

charts/meta-monitoring/templates/ruler/rules-configmap.yaml

@@ -0,0 +1,14 @@
+{{- if .Values.local.metrics.enabled }}
+{{- if and .Values.local.grafana.enabled .Values.dashboards.logs.enabled }}
+---
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: rules
+  namespace: {{ $.Release.Namespace }}
+data:
+{{- if .Values.dashboards.logs.enabled }}
+{{ ($.Files.Glob "src/rules/loki-rules.yaml").AsConfig | indent 2 }}
+{{- end }}
+{{- end }}
+{{- end }}

charts/meta-monitoring/templates/validate.yaml

@@ -3,20 +3,20 @@
 {{- end -}}
 
 {{- if eq .Values.cloud.logs.enabled true -}}
-  {{- if or (empty .Values.cloud.logs.endpoint) (or (empty .Values.cloud.logs.username) (empty .Values.cloud.logs.password)) -}}
+  {{- if empty .Values.cloud.logs.secret -}}
-    {{- fail "if cloud.logs is enabled then the endpoint, username and password have to be filled in" -}}
+    {{- fail "if cloud.logs is enabled then the secret has to be filled in" -}}
   {{- end -}}
 {{- end -}}
 
 {{- if eq .Values.cloud.metrics.enabled true -}}
-  {{- if or (empty .Values.cloud.metrics.endpoint) (or (empty .Values.cloud.metrics.username) (empty .Values.cloud.metrics.password)) -}}
+  {{- if empty .Values.cloud.metrics.secret -}}
-    {{- fail "if cloud.metrics is enabled then the endpoint, username and password have to be filled in" -}}
+    {{- fail "if cloud.metrics is enabled then the secret has to be filled in" -}}
   {{- end -}}
 {{- end -}}
 
 {{- if eq .Values.cloud.traces.enabled true -}}
-  {{- if or (empty .Values.cloud.traces.endpoint) (or (empty .Values.cloud.traces.username) (empty .Values.cloud.traces.password)) -}}
+  {{- if empty .Values.cloud.traces.secret -}}
-    {{- fail "if cloud.traces is enabled then the endpoint, username and password have to be filled in" -}}
+    {{- fail "if cloud.traces is enabled then the secret has to be filled in" -}}
   {{- end -}}
 {{- end -}}
 
@@ -37,3 +37,7 @@
 {{- if empty .Values.namespacesToMonitor -}}
   {{- fail "No namespaces have been specified in namespacesToMonitor" -}}
 {{- end -}}
+
+{{- if empty .Values.metrics.retain -}}
+  {{- fail "All metrics will be collected, please specify some in metrics.retain" -}}
+{{- end -}}

charts/meta-monitoring/values.yaml

@@ -1,58 +1,226 @@
+# Specify the namespaces to monitor here
 namespacesToMonitor:
 - loki
-- mimir
+# The name of the cluster where this will be installed
-- tempo
+clusterLabelValue: "meta-monitoring"
-clusterName: "meta-monitoring"  # TODO check if this can be derived
+# Set to true to write logs, metrics or traces to Grafana Cloud
-
+# The secrets have to be created first
-local:
-  logs:
-    enabled: false
-  metrics:
-    enabled: false
-  traces:
-    enabled: false
-  minio:
-    enabled: false  # This should be set to true if any of the previous is enabled
-
-
 cloud:
   logs:
     enabled: true
-    endpoint:
+    secret: "logs"
-    username:
-    password:
   metrics:
     enabled: true
-    endpoint:
+    secret: "metrics"
-    username:
-    password:
   traces:
     enabled: true
-    endpoint:
+    secret: "traces"
-    username:
+# Set to true for a local version of logs, metrics or traces
-    password:
+local:
-
+  grafana:
-global:
+    enabled: false
+  logs:
+    enabled: false
+  metrics:
+    enabled: false
+  traces:
+    enabled: false
   minio:
-    rootUser: "rootuser"
+    enabled: false # This should be set to true if any of the previous is enabled
-    rootPassword: "rootpassword"
+grafana:
-
+  version: 10.4.2
+  # Gateway ingress configuration
+  ingress:
+    # -- Specifies whether an ingress for the gateway should be created
+    enabled: true
+    # -- Ingress Class Name. MAY be required for Kubernetes versions >= 1.18
+    ingressClassName: ""
+    # -- Annotations for the gateway ingress
+    annotations: {}
+    # -- Labels for the gateway ingress
+    labels: {}
+    # -- Hosts configuration for the gateway ingress, passed through the `tpl` function to allow templating
+    hosts:
+      - host: monitoring.example.com
+        paths:
+          - path: /
+            # -- pathType (e.g. ImplementationSpecific, Prefix, .. etc.) might also be required by some Ingress Controllers
+            # pathType: Prefix
+    # -- TLS configuration for the gateway ingress. Hosts passed through the `tpl` function to allow templating
+    #tls:
+    #  - secretName: grafana-tls
+    #    hosts:
+    #      - monitoring.example.com
+logs:
+  # Adding regexes here will add a stage.replace block for logs. For more information see
+  # https://grafana.com/docs/agent/latest/flow/reference/components/loki.process/#stagereplace-block
+  piiRegexes: null # This example replaces the word after password with *****
+# - expression: "password (\\\\S+)"
+#   source: ""         # Empty uses the log message
+#   replace: "*****""
+# The lines matching these will be kept in Loki
+  retain:
+  # This shows the queries
+  - caller=metrics.go
+  # This shows any errors
+  - level=error
+  # Log lines for delete requests
+  - delete request for user added
+  - Started processing delete request
+  - delete request for user marked as processed
+  # This shows the ingest requests and is very noisy. Uncomment to include.
+  # - caller=push.go
+  # Additional log lines to retain
+  extraLogs: []
+metrics:
+  # The list of metrics to retain for logging dashboards
+  retain:
+  - agent_config_last_load_success_timestamp_seconds
+  - agent_config_last_load_successful
+  - agent_config_load_failures_total
+  - container_cpu_usage_seconds_total
+  - container_fs_writes_bytes_total
+  - container_memory_working_set_bytes
+  - container_network_receive_bytes_total
+  - container_network_transmit_bytes_total
+  - container_spec_cpu_period
+  - container_spec_cpu_quota
+  - container_spec_memory_limit_bytes
+  - cortex_ingester_flush_queue_length
+  - cortex_prometheus_rule_group_iterations_total
+  - cortex_prometheus_rule_evaluation_failures_total
+  - cortex_prometheus_rule_group_rules
+  - cortex_prometheus_rule_group_last_duration_seconds
+  - cortex_prometheus_rule_group_last_evaluation_timestamp_seconds
+  - cortex_prometheus_rule_group_iterations_missed_total
+  - go_gc_duration_seconds
+  - go_goroutines
+  - go_memstats_heap_inuse_bytes
+  - kubelet_volume_stats_used_bytes
+  - kubelet_volume_stats_capacity_bytes
+  - kube_deployment_created
+  - kube_persistentvolumeclaim_labels
+  - kube_pod_container_info
+  - kube_pod_container_resource_requests
+  - kube_pod_container_status_last_terminated_reason
+  - kube_pod_container_status_restarts_total
+  - loki_boltdb_shipper_compact_tables_operation_duration_seconds
+  - loki_boltdb_shipper_compact_tables_operation_last_successful_run_timestamp_seconds
+  - loki_boltdb_shipper_retention_marker_count_total
+  - loki_boltdb_shipper_retention_marker_table_processed_duration_seconds_bucket
+  - loki_boltdb_shipper_retention_marker_table_processed_duration_seconds_count
+  - loki_boltdb_shipper_retention_marker_table_processed_duration_seconds_sum
+  - loki_boltdb_shipper_retention_marker_table_processed_total
+  - loki_boltdb_shipper_request_duration_seconds_bucket
+  - loki_boltdb_shipper_request_duration_seconds_count
+  - loki_boltdb_shipper_request_duration_seconds_sum
+  - loki_boltdb_shipper_retention_sweeper_chunk_deleted_duration_seconds_bucket
+  - loki_boltdb_shipper_retention_sweeper_chunk_deleted_duration_seconds_count
+  - loki_boltdb_shipper_retention_sweeper_chunk_deleted_duration_seconds_sum
+  - loki_boltdb_shipper_retention_sweeper_marker_files_current
+  - loki_boltdb_shipper_retention_sweeper_marker_file_processing_current_time
+  - loki_build_info
+  - loki_chunk_store_deduped_chunks_total
+  - loki_chunk_store_index_entries_per_chunk_bucket
+  - loki_chunk_store_index_entries_per_chunk_count
+  - loki_chunk_store_index_entries_per_chunk_sum
+  - loki_compactor_delete_requests_processed_total
+  - loki_compactor_delete_requests_received_total
+  - loki_compactor_deleted_lines
+  - loki_compactor_oldest_pending_delete_request_age_seconds
+  - loki_compactor_pending_delete_requests_count
+  - loki_discarded_samples_total
+  - loki_distributor_bytes_received_total
+  - loki_distributor_lines_received_total
+  - loki_distributor_structured_metadata_bytes_received_total
+  - loki_index_request_duration_seconds_count
+  - loki_ingester_chunk_age_seconds_bucket
+  - loki_ingester_chunk_age_seconds_count
+  - loki_ingester_chunk_age_seconds_sum
+  - loki_ingester_chunk_bounds_hours_bucket
+  - loki_ingester_chunk_bounds_hours_count
+  - loki_ingester_chunk_bounds_hours_sum
+  - loki_ingester_chunk_entries_bucket
+  - loki_ingester_chunk_entries_count
+  - loki_ingester_chunk_entries_sum
+  - loki_ingester_chunk_size_bytes_bucket
+  - loki_ingester_chunk_utilization_bucket
+  - loki_ingester_chunk_utilization_sum
+  - loki_ingester_chunks_flushed_total
+  - loki_ingester_flush_queue_length
+  - loki_ingester_memory_chunks
+  - loki_ingester_memory_streams
+  - loki_ingester_streams_created_total
+  - loki_request_duration_seconds_bucket
+  - loki_request_duration_seconds_count
+  - loki_request_duration_seconds_sum
+  - loki_ruler_wal_appender_ready
+  - loki_ruler_wal_disk_size
+  - loki_ruler_wal_prometheus_remote_storage_highest_timestamp_in_seconds
+  - loki_ruler_wal_prometheus_remote_storage_queue_highest_sent_timestamp_seconds
+  - loki_ruler_wal_prometheus_remote_storage_samples_pending
+  - loki_ruler_wal_prometheus_remote_storage_samples_total
+  - loki_ruler_wal_samples_appended_total
+  - loki_ruler_wal_storage_created_series_total
+  - loki_write_batch_retries_total
+  - loki_write_dropped_bytes_total
+  - loki_write_dropped_entries_total
+  - loki_write_sent_bytes_total
+  - loki_write_sent_entries_total
+  - node_disk_read_bytes_total
+  - node_disk_written_bytes_total
+  - promtail_custom_bad_words_total
+  # Additional metrics to retain
+  extraMetrics: []
+# Set enabled = true to add the default logs dashboards to the local Grafana
+dashboards:
+  logs:
+    enabled: true
+kubeStateMetrics:
+  # Scrape https://github.com/kubernetes/kube-state-metrics by default
+  enabled: true
+  # This endpoint is created when the helm chart from
+  # https://artifacthub.io/packages/helm/prometheus-community/kube-state-metrics/
+  # is used. Change this if kube-state-metrics is installed somewhere else.
+  endpoint: kube-state-metrics.kube-state-metrics.svc.cluster.local:8080
 # The following are configuration for the dependencies.
-# These should not be changed.
+# These should usually not be changed.
-
 loki:
   loki:
     auth_enabled: false
+    schemaConfig:
+      configs:
+        - from: 2024-03-29
+          store: tsdb
+          object_store: s3
+          schema: v13
+          index:
+            prefix: index_
+            period: 24h
     storage:
       type: "s3"
       s3:
-        endpoint: "meta-minio.meta.svc:9000"
-        access_key_id: rootuser
-        secret_access_key: rootpassword
         insecure: true
+        s3ForcePathStyle: true
       bucketNames:
         chunks: loki-chunks
         ruler: loki-ruler
+    structuredConfig:
+      common:
+        storage:
+          s3:
+            access_key_id: "${rootUser}"
+            endpoint: "{{ .Release.Name }}-minio.{{ .Release.Namespace }}.svc:9000"
+            secret_access_key: "${rootPassword}"
+      compactor:
+        retention_enabled: true
+        delete_request_store: s3
+      limits_config:
+        retention_period: 30d
+  lokiCanary:
+    enabled: false
+  test:
+    enabled: false
   monitoring:
     dashboards:
       enabled: false
@@ -66,44 +234,85 @@ loki:
         installOperator: false
     lokiCanary:
       enabled: false
-  test:
+  write:
-    enabled: false
+    extraArgs:
-
+    - "-config.expand-env=true"
-grafana-agent:
+    extraEnvFrom:
-  agent:
+    - secretRef:
+        name: "minio"
+  read:
+    extraArgs:
+    - "-config.expand-env=true"
+    extraEnvFrom:
+    - secretRef:
+        name: "minio"
+  backend:
+    extraArgs:
+    - "-config.expand-env=true"
+    extraEnvFrom:
+    - secretRef:
+        name: "minio"
+alloy:
+  alloy:
+    clustering:
+      enabled: true
     configMap:
       create: false
       name: "agent-configmap"
       key: 'config.river'
-
+    resources:
+      requests:
+        cpu: '1000m'
+        memory: '600Mi'
+      limits:
+        memory: '4Gi'
+    extraPorts:
+    - name: "otel"
+      port: 4317
+      targetPort: 4317
+      protocol: "TCP"
+    - name: "thrifthttp"
+      port: 14268
+      targetPort: 14268
+      protocol: "TCP"
+  controller:
+    type: "statefulset"
+    autoscaling:
+      enabled: true
+      minReplicas: 3
+      maxReplicas: 30
+      targetMemoryUtilizationPercentage: 90
+      targetCPUUtilizationPercentage: 90
 mimir-distributed:
   minio:
     enabled: false
+  global:
+    extraEnvFrom:
+    - secretRef:
+        name: "minio"
   mimir:
     structuredConfig:
       alertmanager_storage:
         s3:
           bucket_name: mimir-ruler
-          access_key_id: "{{ .Values.global.minio.rootUser }}"
-          endpoint: "{{ .Release.Name }}-minio.{{ .Release.Namespace }}.svc:9000"
-          secret_access_key: "{{ .Values.global.minio.rootPassword }}"
-          insecure: true
       blocks_storage:
         backend: s3
         s3:
           bucket_name: mimir-tsdb
-          access_key_id: "{{ .Values.global.minio.rootUser }}"
-          endpoint: "{{ .Release.Name }}-minio.{{ .Release.Namespace }}.svc:9000"
-          secret_access_key: "{{ .Values.global.minio.rootPassword }}"
-          insecure: true
       ruler_storage:
         s3:
           bucket_name: mimir-ruler
-          access_key_id: "{{ .Values.global.minio.rootUser }}"
+      common:
-          endpoint: "{{ .Release.Name }}-minio.{{ .Release.Namespace }}.svc:9000"
+        storage:
-          secret_access_key: "{{ .Values.global.minio.rootPassword }}"
+          backend: s3
-          insecure: true
+          s3:
-
+            bucket_name: mimir-ruler
+            access_key_id: "${rootUser}"
+            endpoint: "{{ .Release.Name }}-minio.{{ .Release.Namespace }}.svc:9000"
+            secret_access_key: "${rootPassword}"
+            insecure: true
+      limits:
+        compactor_blocks_retention_period: 30d
 tempo-distributed:
   tempo:
     structuredConfig:
@@ -113,19 +322,47 @@ tempo-distributed:
           s3:
             bucket: tempo
             endpoint: "{{ .Release.Name }}-minio.{{ .Release.Namespace }}.svc:9000"
-            access_key: "{{ .Values.global.minio.rootUser }}"
+            access_key: "${rootUser}"
-            secret_key: "{{ .Values.global.minio.rootPassword }}"
+            secret_key: "${rootPassword}"
             insecure: true
+  distributor:
+    extraArgs:
+    - "-config.expand-env=true"
+    extraEnvFrom:
+    - secretRef:
+        name: "minio"
+  ingester:
+    extraArgs:
+    - "-config.expand-env=true"
+    extraEnvFrom:
+    - secretRef:
+        name: "minio"
+  compactor:
+    extraArgs:
+    - "-config.expand-env=true"
+    extraEnvFrom:
+    - secretRef:
+        name: "minio"
+  querier:
+    extraArgs:
+    - "-config.expand-env=true"
+    extraEnvFrom:
+    - secretRef:
+        name: "minio"
+  queryFrontend:
+    extraArgs:
+    - "-config.expand-env=true"
+    extraEnvFrom:
+    - secretRef:
+        name: "minio"
   traces:
     otlp:
       http:
         enabled: true
       grpc:
         enabled: true
-
 minio:
-  rootUser: rootuser
+  existingSecret: "minio"
-  rootPassword: rootpassword
   buckets:
     - name: loki-chunks
       policy: none
@@ -150,4 +387,4 @@ minio:
       cpu: 100m
       memory: 128Mi
   # Changed the mc config path to '/tmp' from '/etc' as '/etc' is only writable by root and OpenShift will not permit this.
-  configPathmc: "/tmp/minio/mc/"
+  configPathmc: "/tmp/minio/mc/"

docs/create_new_release.md

@@ -0,0 +1,10 @@
+# Create a new release
+
+1. Update the version field in charts/meta-monitoring/Chart.yaml in a new PR. Merge this PR if approved.
+
+2. On the [Actions tab](https://github.com/grafana/meta-monitoring-chart/actions):
+   - Select `Release Helm chart` in the workflows on the left
+   - Click the `Run workflow` button
+   - Leave the `main` branch as is
+   - Click the green `Run workflow` button
+

docs/installation.md

@@ -1,27 +1,193 @@
 # Install this chart
 
+## Preparation for Cloud mode (preferred)
+
+1. Use an existing Grafana Cloud account or setup a new one. Then create an access token:
+
+   1. In Grafana go to Administration -> Users and Access -> Cloud access policies.
+
+   1. Click `Create access policy`.
+
+   1. Fill in the `Display name` field and check the `Write` check box for metrics, logs and traces. Then click `Create`.
+
+   1. On the newly created access policy click `Add token`.
+
+   1. Fill in the `Token name` field and click `Create`. Make a copy of the token as it will be used later on.
+
 1. Create the meta namespace
 
    ```
    kubectl create namespace meta
    ```
 
-1. Create a values.yaml file based on the [default one](../charts/meta-monitoring/values.yaml).
+1. Create secrets with credentials and the endpoint when sending logs, metrics or traces to Grafana Cloud.
+
+   ```
+   kubectl create secret generic logs -n meta \
+    --from-literal=username=<logs username> \
+    --from-literal=password=<token> \
+    --from-literal=endpoint='https://logs-prod-us-central1.grafana.net/loki/api/v1/push'
+
+   kubectl create secret generic metrics -n meta \
+    --from-literal=username=<metrics username> \
+    --from-literal=password=<token> \
+    --from-literal=endpoint='https://prometheus-us-central1.grafana.net/api/prom/push'
+
+   kubectl create secret generic traces -n meta \
+    --from-literal=username=<OTLP instance ID> \
+    --from-literal=password=<token> \
+    --from-literal=endpoint='https://otlp-gateway-prod-us-east-0.grafana.net/otlp'
+   ```
+
+   The logs, metrics and traces usernames are the `User / Username / Instance IDs` of the Loki, Prometheus/Mimir and OpenTelemetry instances in Grafana Cloud. From `Home` in Grafana click on `Stacks`. Then go to the `Details` pages of Loki and Prometheus/Mimir. For OpenTelemetry go to the `Configure` page.
+
+1. Create a values.yaml file based on the [default one](../charts/meta-monitoring/values.yaml). Fill in the names of the secrets created above as needed. An example minimal values.yaml looks like this:
+
+   ```
+   namespacesToMonitor:
+   - loki
+
+   cloud:
+     logs:
+       enabled: true
+       secret: "logs"
+     metrics:
+       enabled: true
+       secret: "metrics"
+     traces:
+       enabled: true
+       secret: "traces"
+   ```
+
+## Preparation for Local mode
+
+1. Create the meta namespace
+
+   ```
+   kubectl create namespace meta
+   ```
+
+1. Create a secret named `minio` with the user and password for the local Minio:
+
+   ```
+   kubectl create secret generic minio -n meta \
+    --from-literal=rootPassword=<password> \
+    --from-literal=rootUser=<user>
+   ```
+
+1. Create a values.yaml file based on the [default one](../charts/meta-monitoring/values.yaml). An example minimal values.yaml looks like this:
+
+   ```
+   namespacesToMonitor:
+   - loki
+
+   cloud:
+     logs:
+       enabled: false
+     metrics:
+       enabled: false
+     traces:
+       enabled: false
+
+   local:
+     grafana:
+       enabled:true
+     logs:
+       enabled: true
+     metrics:
+       enabled: true
+     traces:
+       enabled: true
+     minio:
+       enabled: true
+   ```
+
+## Installing the chart
+
+1. Add the repo
+
+   ```
+   helm repo add grafana https://grafana.github.io/helm-charts
+   ```
+
+1. Fetch the latest charts from the grafana repo
+
+   ```
+   helm repo update grafana
+   ```
+
 
 1. Install this helm chart
 
    ```
-   helm install -n meta -f values.yaml meta ./charts/meta-monitoring
+   helm install -n meta -f values.yaml meta grafana/meta-monitoring
    ```
 
 1. Upgrade
 
    ```
-   helm upgrade --install -f values.yaml -n meta meta ./charts/meta-monitoring
+   helm upgrade --install -f values.yaml -n meta meta grafana/meta-monitoring
    ```
 
 1. Delete this chart:
 
    ```
    helm delete -n meta meta
-   ```
+   ```
+
+## Installing the dashboards and rules on Grafana Cloud
+
+## Installing the dashboards on Grafana Cloud
+
+Only the files for the application monitored have to be copied. When monitoring Loki import dashboard files starting with 'loki-'.
+
+For each of the dashboard files in charts/meta-monitoring/src/dashboards folder do the following:
+
+1. Click on 'Dashboards' in Grafana
+
+1. Click on the 'New` button and select 'Import'
+
+1. Drop the dashboard file to the 'Upload dashboard JSON file' drop area
+
+1. Click 'Import'
+
+## Installing the rules on Grafana Cloud
+
+1. Select the rules files in charts/meta-monitoring/src/rules for the application to monitor. When monitoring Loki use loki-rules.yaml.
+
+1. Install mimirtool as per the [instructions](https://grafana.com/docs/mimir/latest/manage/tools/mimirtool/)
+
+1. Create an access policy with Read and Write permission for Rules. Also create a token and record the token.
+
+1. Get your cloud Prometheus endpoint and Instance ID from the `Prometheus` page in `Stacks`.
+
+1. Use them to load the rules using mimirtool as follows:
+
+  ```
+  mimirtool rules load --address=<your_cloud_prometheus_endpoint> --id=<your_instance_id> --key=<your_cloud_access_policy_token> *.yaml
+  ```
+
+1. To check the rules you have uploaded run:
+
+  ```
+  mimirtool rules print --address=<your_cloud_prometheus_endpoint> --id=<your_instance_id> --key=<your_cloud_access_policy_token>
+  ```
+
+## Configure Loki to send traces
+
+1. In the Loki config enable tracing:
+
+   ```
+   loki:
+     tracing:
+       enabled: true
+   ```
+
+1. Add the following environment variables to your Loki binaries. When using the Loki Helm chart these can be added using the `extraEnv` setting for the Loki components.
+
+   1. JAEGER_ENDPOINT: http address of the mmc-alloy service installed by the meta-monitoring chart, for example "http://mmc-alloy:14268/api/traces"
+   1. JAEGER_AGENT_TAGS: extra tags you would like to add to the spans, for example  'cluster="abc",namespace="def"'
+   1. JAEGER_SAMPLER_TYPE: the sampling strategy, for example to sample all use 'const' with a value of 1 for the next environment variable
+   1. JAEGER_SAMPLER_PARAM: 1
+
+1. If Loki is installed in a different namespace you can create an [ExternalName service](https://kubernetes.io/docs/concepts/services-networking/service/#externalname) in Kubernetes to point to the mmc-alloy service in the meta monitoring namespace

scripts/clone_loki_mixin.sh

@@ -0,0 +1,20 @@
+#!/usr/bin/env bash
+
+clean_up() {
+  test -d "$tmp_dir" && rm -fr "$tmp_dir"
+}
+
+here=${PWD}
+
+tmp_dir=$( mktemp -d -t my-script )
+cd $tmp_dir
+
+echo "Cloning Loki"
+git clone --filter=blob:none  --no-checkout "https://github.com/grafana/loki"
+cd loki
+git sparse-checkout init --cone
+git checkout main
+git sparse-checkout set production/loki-mixin
+
+echo "Copying production/loki-mixin to ${here}"
+cp -r production ${here}

scripts/mixin-meta-monitoring.libsonnet

@@ -0,0 +1,18 @@
+(import 'dashboards.libsonnet') +
+(import 'alerts.libsonnet') +
+(import 'recording_rules.libsonnet') + {
+  grafanaDashboardFolder: 'Loki Meta Monitoring',
+
+  _config+:: {
+    internal_components: false,
+
+    // The Meta Monitoring helm chart uses Grafana Alloy instead of promtail
+    promtail+: {
+      enabled: false,
+    },
+
+    meta_monitoring+: {
+      enabled: true,
+    },
+  },
+}

tools/kind.config

@@ -0,0 +1,9 @@
+kind: Cluster
+apiVersion: kind.x-k8s.io/v1alpha4
+name: meta
+nodes:
+- role: control-plane
+- role: worker
+- role: worker
+- role: worker
+