Reformat loki-rules

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/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 +1,177 @@
+---
+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:
+    updateLoki:
+        name: Update the Loki subchart
+        runs-on: "ubuntu-latest"
+        steps:
+            - name: Checkout
+              uses: actions/checkout@v2
+
+            - name: Install Updatecli
+              uses: updatecli/updatecli-action@v2
+
+            - name: Run Updatecli
+              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: Create pull request
+              if: steps.update-loki.outputs.changed == 'true'
+              uses: peter-evans/create-pull-request@v5
+              with:
+                title: "[dependency] Update the Loki subchart"
+                body: "Updates the Loki subchart"
+                base: main
+                author: "${{ github.actor }} <${{ github.actor }}@users.noreply.github.com>"
+                committer: "GitHub <noreply@github.com>"
+                commit-message: Update loki
+                labels: dependencies
+                branch: chore/update-loki
+                delete-branch: true
+
+    updateGrafanaAlloy:
+        name: Update the Grafana Alloy subchart
+        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-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: Create pull request
+              if: steps.update-grafana-alloy.outputs.changed == 'true'
+              uses: peter-evans/create-pull-request@v5
+              with:
+                title: "[dependency] Update the Grafana Alloy subchart"
+                body: "Updates the Grafana Alloy subchart"
+                base: main
+                author: "${{ github.actor }} <${{ github.actor }}@users.noreply.github.com>"
+                committer: "GitHub <noreply@github.com>"
+                commit-message: Update Grafana Alloy
+                labels: dependencies
+                branch: chore/update-grafana-alloy
+                delete-branch: true
+
+    updateMimirDistributed:
+        name: Update the Mimir Distributed subchart
+        runs-on: "ubuntu-latest"
+        steps:
+            - name: Checkout
+              uses: actions/checkout@v2
+
+            - name: Install Updatecli
+              uses: updatecli/updatecli-action@v2
+
+            - name: Run Updatecli
+              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: Create pull request
+              if: steps.update-mimir-distributed.outputs.changed == 'true'
+              uses: peter-evans/create-pull-request@v5
+              with:
+                title: "[dependency] Update the Mimir Distributed subchart"
+                body: "Updates the Mimir Distributed subchart"
+                base: main
+                author: "${{ github.actor }} <${{ github.actor }}@users.noreply.github.com>"
+                committer: "GitHub <noreply@github.com>"
+                commit-message: Update Mimir Distributed
+                labels: dependencies
+                branch: chore/update-mimir-distributed
+                delete-branch: true
+
+    updateTempoDistributed:
+        name: Update the Tempo Distributed subchart
+        runs-on: "ubuntu-latest"
+        steps:
+            - name: Checkout
+              uses: actions/checkout@v2
+
+            - name: Install Updatecli
+              uses: updatecli/updatecli-action@v2
+
+            - name: Run Updatecli
+              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: Create pull request
+              if: steps.update-tempo-distributed.outputs.changed == 'true'
+              uses: peter-evans/create-pull-request@v5
+              with:
+                title: "[dependency] Update the Tempo Distributed subchart"
+                body: "Updates the tempo Distributed subchart"
+                base: main
+                author: "${{ github.actor }} <${{ github.actor }}@users.noreply.github.com>"
+                committer: "GitHub <noreply@github.com>"
+                commit-message: Update Tempo Distributed
+                labels: dependencies
+                branch: chore/update-tempo-distributed
+                delete-branch: true
+
+    updateMinio:
+        name: Update the Minio subchart
+        runs-on: "ubuntu-latest"
+        steps:
+            - name: Checkout
+              uses: actions/checkout@v2
+
+            - name: Install Updatecli
+              uses: updatecli/updatecli-action@v2
+
+            - name: Run Updatecli
+              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-minio.outputs.changed == 'true'
+              uses: peter-evans/create-pull-request@v5
+              with:
+                title: "[dependency] Update the Minio subchart"
+                body: "Updates the Minio subchart"
+                base: main
+                author: "${{ github.actor }} <${{ github.actor }}@users.noreply.github.com>"
+                committer: "GitHub <noreply@github.com>"
+                commit-message: Update minio
+                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 @@
+production/

Makefile

@@ -0,0 +1,22 @@
+# 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
+
+MIXIN_PATH := production/loki-mixin
+MIXIN_OUT_PATH_META_MONITORING := production/loki-mixin-compiled-meta-monitoring
+
+mixin: ## Create our version of the mixin
+	@rm -rf $(MIXIN_PATH)
+	./scripts/clone_loki_mixin.sh
+	@rm -rf $(MIXIN_OUT_PATH_META_MONITORING) && mkdir $(MIXIN_OUT_PATH_META_MONITORING)
+	@cd $(MIXIN_PATH) && jb install
+	@mixtool generate all --output-alerts $(MIXIN_OUT_PATH_META_MONITORING)/alerts.yaml --output-rules $(MIXIN_OUT_PATH_META_MONITORING)/rules.yaml --directory $(MIXIN_OUT_PATH_META_MONITORING)/dashboards ${MIXIN_PATH}/mixin-meta-monitoring.libsonnet
+	@cp $(MIXIN_OUT_PATH_META_MONITORING)/dashboards/* charts/meta-monitoring/src/dashboards
+	@cp $(MIXIN_OUT_PATH_META_MONITORING)/rules.yaml charts/meta-monitoring/src/rules/loki-rules.yaml

README.md

@@ -1,20 +1,9 @@
 # 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.
 
 Note that this is pre-production software at the moment.
 
-## Preparation
-
-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/or traces are sent
@@ -34,12 +23,6 @@ Both modes can be enabled at the same time.
 
 ## Installation
 
-```
-helm install -n meta --skip-crds -f values.yaml meta ./charts/meta-monitoring
-```
-
-If the platform supports CRDs the `--skip-crds` option can be removed. However the CRDs are not used by this chart.
-
 For more instructions including how to update the chart go to the [installation](docs/installation.md) page.
 
 ## Supported features
@@ -59,7 +42,6 @@ Most of these features are enabled by default. See the values.yaml file for how
 
 ## Caveats
 
-- The [loki.source.kubernetes](https://grafana.com/docs/agent/latest/flow/reference/components/loki.source.kubernetes/) component of the Grafana Agent is used to scrape Kubernetes log files. This component is marked experimental at the moment.
 - 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.

charts/meta-monitoring/Chart.lock

@@ -1,18 +1,18 @@
 dependencies:
 - name: loki
   repository: https://grafana.github.io/helm-charts
-  version: 5.8.0
+  version: 6.3.4
-- 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: 1.9.4
 - name: minio
   repository: https://charts.min.io
-  version: 5.0.11
+  version: 5.1.0
-digest: sha256:4b04084e6fe821c4d481017b2430f7c8cd782a5d60830dd3a24eb8f10a9ece09
+digest: sha256:4bb2a4f62c9ebddcd64c28a94126ab3f07d319b028ea7c17ffbdf28d86b3be61
-generated: "2023-06-29T14:25:07.247853+01:00"
+generated: "2024-04-25T07:02:28.663945601Z"

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
-
 # 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: 6.3.4
   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: 1.9.4
   condition: local.traces.enabled
 - name: minio
   repository: https://charts.min.io
-  version: "5.0.11"
+  version: 5.1.0
-  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/loki-deletion.json

@@ -62,7 +62,6 @@
                         "expr": "sum(loki_compactor_pending_delete_requests_count{cluster=~\"$cluster\", namespace=~\"$namespace\"})",
                         "format": "time_series",
                         "instant": true,
-                        "intervalFactor": 2,
                         "refId": "A"
                      }
                   ],
@@ -138,7 +137,6 @@
                         "expr": "max(loki_compactor_oldest_pending_delete_request_age_seconds{cluster=~\"$cluster\", namespace=~\"$namespace\"})",
                         "format": "time_series",
                         "instant": true,
-                        "intervalFactor": 2,
                         "refId": "A"
                      }
                   ],
@@ -191,232 +189,145 @@
             "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,
                   "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": 4,
-                  "stack": false,
-                  "steppedLine": false,
                   "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=~\"$namespace\"} or on () vector(0))",
                         "format": "time_series",
-                        "intervalFactor": 2,
                         "legendFormat": "in progress",
-                        "legendLink": null,
+                        "legendLink": null
-                        "step": 10
                      }
                   ],
-                  "thresholds": [ ],
-                  "timeFrom": null,
-                  "timeShift": null,
                   "title": "# of Delete Requests (received - processed) ",
-                  "tooltip": {
+                  "type": "timeseries"
-                     "shared": true,
-                     "sort": 2,
-                     "value_type": "individual"
-                  },
-                  "type": "graph",
-                  "xaxis": {
-                     "buckets": null,
-                     "mode": "time",
-                     "name": null,
-                     "show": true,
-                     "values": [ ]
-                  },
-                  "yaxes": [
-                     {
-                        "format": "short",
-                        "label": null,
-                        "logBase": 1,
-                        "max": null,
-                        "min": 0,
-                        "show": true
-                     },
-                     {
-                        "format": "short",
-                        "label": null,
-                        "logBase": 1,
-                        "max": null,
-                        "min": null,
-                        "show": false
-                     }
-                  ]
                },
                {
-                  "aliasColors": { },
-                  "bars": false,
-                  "dashLength": 10,
-                  "dashes": false,
                   "datasource": "$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": 4,
-                  "linewidth": 1,
                   "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": 4,
-                  "stack": false,
-                  "steppedLine": false,
                   "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": 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": 5,
-                  "linewidth": 1,
                   "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": 4,
-                  "stack": false,
-                  "steppedLine": false,
                   "targets": [
                      {
                         "expr": "sum(increase(loki_compactor_delete_requests_processed_total{cluster=~\"$cluster\", namespace=~\"$namespace\"}[1d]))",
                         "format": "time_series",
-                        "intervalFactor": 2,
                         "legendFormat": "processed",
-                        "legendLink": null,
+                        "legendLink": null
-                        "step": 10
                      }
                   ],
-                  "thresholds": [ ],
-                  "timeFrom": null,
-                  "timeShift": null,
                   "title": "Delete Requests Processed / Day",
-                  "tooltip": {
+                  "type": "timeseries"
-                     "shared": true,
-                     "sort": 2,
-                     "value_type": "individual"
-                  },
-                  "type": "graph",
-                  "xaxis": {
-                     "buckets": null,
-                     "mode": "time",
-                     "name": null,
-                     "show": true,
-                     "values": [ ]
-                  },
-                  "yaxes": [
-                     {
-                        "format": "short",
-                        "label": null,
-                        "logBase": 1,
-                        "max": null,
-                        "min": 0,
-                        "show": true
-                     },
-                     {
-                        "format": "short",
-                        "label": null,
-                        "logBase": 1,
-                        "max": null,
-                        "min": null,
-                        "show": false
-                     }
-                  ]
                }
             ],
             "repeat": null,
@@ -431,232 +342,145 @@
             "height": "250px",
             "panels": [
                {
-                  "aliasColors": { },
-                  "bars": false,
-                  "dashLength": 10,
-                  "dashes": false,
                   "datasource": "$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": 6,
-                  "linewidth": 1,
                   "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": 4,
-                  "stack": false,
-                  "steppedLine": false,
                   "targets": [
                      {
                         "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}}",
-                        "legendLink": null,
+                        "legendLink": null
-                        "step": 10
                      }
                   ],
-                  "thresholds": [ ],
-                  "timeFrom": null,
-                  "timeShift": null,
                   "title": "Compactor CPU usage",
-                  "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": 7,
+                     "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": 7,
-                  "linewidth": 1,
                   "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": 4,
-                  "stack": false,
-                  "steppedLine": false,
                   "targets": [
                      {
                         "expr": "go_memstats_heap_inuse_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\", container=\"compactor\"} / 1024 / 1024 ",
                         "format": "time_series",
-                        "intervalFactor": 2,
                         "legendFormat": " {{pod}} ",
-                        "legendLink": null,
+                        "legendLink": null
-                        "step": 10
                      }
                   ],
-                  "thresholds": [ ],
-                  "timeFrom": null,
-                  "timeShift": null,
                   "title": "Compactor memory usage (MiB)",
-                  "tooltip": {
+                  "type": "timeseries"
-                     "shared": true,
-                     "sort": 2,
-                     "value_type": "individual"
-                  },
-                  "type": "graph",
-                  "xaxis": {
-                     "buckets": null,
-                     "mode": "time",
-                     "name": null,
-                     "show": true,
-                     "values": [ ]
-                  },
-                  "yaxes": [
-                     {
-                        "format": "short",
-                        "label": null,
-                        "logBase": 1,
-                        "max": null,
-                        "min": 0,
-                        "show": true
-                     },
-                     {
-                        "format": "short",
-                        "label": null,
-                        "logBase": 1,
-                        "max": null,
-                        "min": null,
-                        "show": false
-                     }
-                  ]
                },
                {
-                  "aliasColors": { },
-                  "bars": false,
-                  "dashLength": 10,
-                  "dashes": false,
                   "datasource": "$datasource",
-                  "fill": 1,
+                  "fieldConfig": {
-                  "id": 8,
+                     "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": 8,
-                  "linewidth": 1,
                   "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": 4,
-                  "stack": false,
-                  "steppedLine": false,
                   "targets": [
                      {
                         "expr": "loki_boltdb_shipper_compact_tables_operation_duration_seconds{cluster=~\"$cluster\", namespace=~\"$namespace\"}",
                         "format": "time_series",
-                        "intervalFactor": 2,
                         "legendFormat": "{{pod}}",
-                        "legendLink": null,
+                        "legendLink": null
-                        "step": 10
                      }
                   ],
-                  "thresholds": [ ],
-                  "timeFrom": null,
-                  "timeShift": null,
                   "title": "Compaction run duration (seconds)",
-                  "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,
@@ -671,156 +495,98 @@
             "height": "250px",
             "panels": [
                {
-                  "aliasColors": { },
-                  "bars": false,
-                  "dashLength": 10,
-                  "dashes": false,
                   "datasource": "$datasource",
-                  "fill": 1,
+                  "fieldConfig": {
-                  "id": 9,
+                     "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,
                   "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,
                   "targets": [
                      {
                         "expr": "sum(increase(loki_compactor_load_pending_requests_attempts_total{status=\"fail\", cluster=~\"$cluster\", namespace=~\"$namespace\"}[1h]))",
                         "format": "time_series",
-                        "intervalFactor": 2,
                         "legendFormat": "failures",
-                        "legendLink": null,
+                        "legendLink": null
-                        "step": 10
                      }
                   ],
-                  "thresholds": [ ],
-                  "timeFrom": null,
-                  "timeShift": null,
                   "title": "Failures in Loading Delete Requests / Hour",
-                  "tooltip": {
+                  "type": "timeseries"
-                     "shared": true,
-                     "sort": 2,
-                     "value_type": "individual"
-                  },
-                  "type": "graph",
-                  "xaxis": {
-                     "buckets": null,
-                     "mode": "time",
-                     "name": null,
-                     "show": true,
-                     "values": [ ]
-                  },
-                  "yaxes": [
-                     {
-                        "format": "short",
-                        "label": null,
-                        "logBase": 1,
-                        "max": null,
-                        "min": 0,
-                        "show": true
-                     },
-                     {
-                        "format": "short",
-                        "label": null,
-                        "logBase": 1,
-                        "max": null,
-                        "min": null,
-                        "show": false
-                     }
-                  ]
                },
                {
-                  "aliasColors": { },
-                  "bars": false,
-                  "dashLength": 10,
-                  "dashes": false,
                   "datasource": "$datasource",
-                  "fill": 1,
+                  "fieldConfig": {
-                  "id": 10,
+                     "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": 10,
-                  "linewidth": 1,
                   "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,
                   "targets": [
                      {
-                        "expr": "sum(rate(loki_compactor_deleted_lines{cluster=~\"$cluster\",job=~\"$namespace/(loki|enterprise-logs)-read\"}[$__rate_interval])) by (user)",
+                        "expr": "sum(rate(loki_compactor_deleted_lines{cluster=~\"$cluster\", namespace=~\"$namespace\", pod=~\"(compactor|(loki|enterprise-logs)-backend.*|loki-single-binary)\"}[$__rate_interval])) by (user)",
                         "format": "time_series",
-                        "intervalFactor": 2,
                         "legendFormat": "{{user}}",
-                        "legendLink": null,
+                        "legendLink": null
-                        "step": 10
                      }
                   ],
-                  "thresholds": [ ],
-                  "timeFrom": null,
-                  "timeShift": null,
                   "title": "Lines Deleted / Sec",
-                  "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,
@@ -840,7 +606,7 @@
                   "span": 6,
                   "targets": [
                      {
-                        "expr": "{cluster=~\"$cluster\", namespace=~\"$namespace\", container=\"compactor\"} |~ \"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}}\" ",
+                        "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"
                      }
                   ],
@@ -853,7 +619,7 @@
                   "span": 6,
                   "targets": [
                      {
-                        "expr": "{cluster=~\"$cluster\", namespace=~\"$namespace\", container=\"compactor\"} |~ \"delete request for user added\" | logfmt | line_format \"{{.ts}} user={{.user}} query='{{.query}}'\"",
+                        "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"
                      }
                   ],
@@ -882,7 +648,7 @@
                   "value": "default"
                },
                "hide": 0,
-               "label": "Data Source",
+               "label": "Data source",
                "name": "datasource",
                "options": [ ],
                "query": "prometheus",

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

@@ -77,7 +77,7 @@
                "sort": 0,
                "value_type": "individual"
             },
-            "type": "graph",
+            "type": "timeseries",
             "xaxis": {
                "buckets": null,
                "mode": "time",
@@ -114,6 +114,11 @@
             "dashLength": 10,
             "dashes": false,
             "datasource": "$datasource",
+            "fieldConfig": {
+               "defaults": {
+                  "unit": "s"
+               }
+            },
             "fill": 1,
             "fillGradient": 0,
             "gridPos": {
@@ -164,7 +169,7 @@
                "sort": 0,
                "value_type": "individual"
             },
-            "type": "graph",
+            "type": "timeseries",
             "xaxis": {
                "buckets": null,
                "mode": "time",
@@ -236,7 +241,7 @@
             "steppedLine": false,
             "targets": [
                {
-                  "expr": "sum(rate(container_cpu_usage_seconds_total{cluster=\"$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"
                }
             ],
@@ -250,7 +255,7 @@
                "sort": 0,
                "value_type": "individual"
             },
-            "type": "graph",
+            "type": "timeseries",
             "xaxis": {
                "buckets": null,
                "mode": "time",
@@ -287,6 +292,11 @@
             "dashLength": 10,
             "dashes": false,
             "datasource": "$datasource",
+            "fieldConfig": {
+               "defaults": {
+                  "unit": "bytes"
+               }
+            },
             "fill": 1,
             "fillGradient": 0,
             "gridPos": {
@@ -336,7 +346,7 @@
                "sort": 0,
                "value_type": "individual"
             },
-            "type": "graph",
+            "type": "timeseries",
             "xaxis": {
                "buckets": null,
                "mode": "time",
@@ -373,6 +383,11 @@
             "dashLength": 10,
             "dashes": false,
             "datasource": "$datasource",
+            "fieldConfig": {
+               "defaults": {
+                  "unit": "binBps"
+               }
+            },
             "fill": 1,
             "fillGradient": 0,
             "gridPos": {
@@ -408,7 +423,7 @@
             "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\"}[$__rate_interval]))",
                   "refId": "A"
                }
             ],
@@ -422,7 +437,7 @@
                "sort": 0,
                "value_type": "individual"
             },
-            "type": "graph",
+            "type": "timeseries",
             "xaxis": {
                "buckets": null,
                "mode": "time",
@@ -459,6 +474,11 @@
             "dashLength": 10,
             "dashes": false,
             "datasource": "$datasource",
+            "fieldConfig": {
+               "defaults": {
+                  "unit": "binBps"
+               }
+            },
             "fill": 1,
             "fillGradient": 0,
             "gridPos": {
@@ -494,7 +514,7 @@
             "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\"}[$__rate_interval]))",
                   "refId": "A"
                }
             ],
@@ -508,7 +528,7 @@
                "sort": 0,
                "value_type": "individual"
             },
-            "type": "graph",
+            "type": "timeseries",
             "xaxis": {
                "buckets": null,
                "mode": "time",
@@ -595,7 +615,7 @@
                "sort": 0,
                "value_type": "individual"
             },
-            "type": "graph",
+            "type": "timeseries",
             "xaxis": {
                "buckets": null,
                "mode": "time",
@@ -632,6 +652,11 @@
             "dashLength": 10,
             "dashes": false,
             "datasource": "$datasource",
+            "fieldConfig": {
+               "defaults": {
+                  "unit": "ops"
+               }
+            },
             "fill": 1,
             "fillGradient": 0,
             "gridPos": {
@@ -667,7 +692,7 @@
             "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\"}[$__rate_interval])) by (level)",
                   "legendFormat": "{{level}}",
                   "refId": "A"
                }
@@ -682,7 +707,7 @@
                "sort": 0,
                "value_type": "individual"
             },
-            "type": "graph",
+            "type": "timeseries",
             "xaxis": {
                "buckets": null,
                "mode": "time",
@@ -718,7 +743,12 @@
             "bars": false,
             "dashLength": 10,
             "dashes": false,
-            "datasource": "$logs",
+            "datasource": "$loki_datasource",
+            "fieldConfig": {
+               "defaults": {
+                  "unit": "ops"
+               }
+            },
             "fill": 1,
             "fillGradient": 0,
             "gridPos": {
@@ -771,7 +801,7 @@
             "steppedLine": false,
             "targets": [
                {
-                  "expr": "sum(rate({cluster=\"$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\" |= \"$filter\" | __error__=\"\" [$__auto])) by (level)",
                   "intervalFactor": 3,
                   "legendFormat": "{{level}}",
                   "refId": "A"
@@ -787,7 +817,7 @@
                "sort": 2,
                "value_type": "individual"
             },
-            "type": "graph",
+            "type": "timeseries",
             "xaxis": {
                "buckets": null,
                "mode": "time",
@@ -819,7 +849,7 @@
             }
          },
          {
-            "datasource": "$logs",
+            "datasource": "$loki_datasource",
             "gridPos": {
                "h": 19,
                "w": 24,
@@ -861,7 +891,7 @@
                   "value": "default"
                },
                "hide": 0,
-               "label": "Data Source",
+               "label": "Data source",
                "name": "datasource",
                "options": [ ],
                "query": "prometheus",
@@ -918,7 +948,7 @@
             {
                "hide": 0,
                "label": null,
-               "name": "logs",
+               "name": "loki_datasource",
                "options": [ ],
                "query": "loki",
                "refresh": 1,
@@ -1069,4 +1099,4 @@
       "title": "Loki / Logs",
       "uid": "logs",
       "version": 0
-   }
+   }

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

@@ -300,7 +300,8 @@
                            "value": 80
                         }
                      ]
-                  }
+                  },
+                  "unit": "s"
                },
                "overrides": [ ]
             },
@@ -600,7 +601,7 @@
                   "value": "default"
                },
                "hide": 0,
-               "label": "Data Source",
+               "label": "Data source",
                "name": "datasource",
                "options": [ ],
                "query": "prometheus",

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

@@ -1,53 +1,52 @@
-groups:
+- name: "loki_rules"
-- name: loki_rules
   rules:
-  - expr: histogram_quantile(0.99, sum(rate(loki_request_duration_seconds_bucket[1m]))
+  - expr: "histogram_quantile(0.99, sum(rate(loki_request_duration_seconds_bucket[5m]))
-      by (le, cluster, job))
+      by (le, cluster, job))"
-    record: cluster_job:loki_request_duration_seconds:99quantile
+    record: "cluster_job:loki_request_duration_seconds:99quantile"
-  - expr: histogram_quantile(0.50, sum(rate(loki_request_duration_seconds_bucket[1m]))
+  - expr: "histogram_quantile(0.50, sum(rate(loki_request_duration_seconds_bucket[5m]))
-      by (le, cluster, job))
+      by (le, cluster, job))"
-    record: cluster_job:loki_request_duration_seconds:50quantile
+    record: "cluster_job:loki_request_duration_seconds:50quantile"
-  - expr: sum(rate(loki_request_duration_seconds_sum[1m])) by (cluster, job) / sum(rate(loki_request_duration_seconds_count[1m]))
+  - expr: "sum(rate(loki_request_duration_seconds_sum[5m])) by (cluster, job) / sum(rate(loki_request_duration_seconds_count[5m]))
-      by (cluster, job)
+      by (cluster, job)"
-    record: cluster_job:loki_request_duration_seconds:avg
+    record: "cluster_job:loki_request_duration_seconds:avg"
-  - expr: sum(rate(loki_request_duration_seconds_bucket[1m])) by (le, cluster, job)
+  - expr: "sum(rate(loki_request_duration_seconds_bucket[5m])) by (le, cluster, job)"
-    record: cluster_job:loki_request_duration_seconds_bucket:sum_rate
+    record: "cluster_job:loki_request_duration_seconds_bucket:sum_rate"
-  - expr: sum(rate(loki_request_duration_seconds_sum[1m])) by (cluster, job)
+  - expr: "sum(rate(loki_request_duration_seconds_sum[5m])) by (cluster, job)"
-    record: cluster_job:loki_request_duration_seconds_sum:sum_rate
+    record: "cluster_job:loki_request_duration_seconds_sum:sum_rate"
-  - expr: sum(rate(loki_request_duration_seconds_count[1m])) by (cluster, job)
+  - expr: "sum(rate(loki_request_duration_seconds_count[5m])) by (cluster, job)"
-    record: cluster_job:loki_request_duration_seconds_count:sum_rate
+    record: "cluster_job:loki_request_duration_seconds_count:sum_rate"
-  - expr: histogram_quantile(0.99, sum(rate(loki_request_duration_seconds_bucket[1m]))
+  - expr: "histogram_quantile(0.99, sum(rate(loki_request_duration_seconds_bucket[5m]))
-      by (le, cluster, job, route))
+      by (le, cluster, job, route))"
-    record: cluster_job_route:loki_request_duration_seconds:99quantile
+    record: "cluster_job_route:loki_request_duration_seconds:99quantile"
-  - expr: histogram_quantile(0.50, sum(rate(loki_request_duration_seconds_bucket[1m]))
+  - expr: "histogram_quantile(0.50, sum(rate(loki_request_duration_seconds_bucket[5m]))
-      by (le, cluster, job, route))
+      by (le, cluster, job, route))"
-    record: cluster_job_route:loki_request_duration_seconds:50quantile
+    record: "cluster_job_route:loki_request_duration_seconds:50quantile"
-  - expr: sum(rate(loki_request_duration_seconds_sum[1m])) by (cluster, job, route)
+  - expr: "sum(rate(loki_request_duration_seconds_sum[5m])) by (cluster, job, route)
-      / sum(rate(loki_request_duration_seconds_count[1m])) 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
+    record: "cluster_job_route:loki_request_duration_seconds:avg"
-  - expr: sum(rate(loki_request_duration_seconds_bucket[1m])) by (le, cluster, job,
+  - expr: "sum(rate(loki_request_duration_seconds_bucket[5m])) by (le, cluster, job,
-      route)
+      route)"
-    record: cluster_job_route:loki_request_duration_seconds_bucket:sum_rate
+    record: "cluster_job_route:loki_request_duration_seconds_bucket:sum_rate"
-  - expr: sum(rate(loki_request_duration_seconds_sum[1m])) by (cluster, job, route)
+  - expr: "sum(rate(loki_request_duration_seconds_sum[5m])) by (cluster, job, route)"
-    record: cluster_job_route:loki_request_duration_seconds_sum:sum_rate
+    record: "cluster_job_route:loki_request_duration_seconds_sum:sum_rate"
-  - expr: sum(rate(loki_request_duration_seconds_count[1m])) by (cluster, job, route)
+  - expr: "sum(rate(loki_request_duration_seconds_count[5m])) by (cluster, job, route)"
-    record: cluster_job_route:loki_request_duration_seconds_count:sum_rate
+    record: "cluster_job_route:loki_request_duration_seconds_count:sum_rate"
-  - expr: histogram_quantile(0.99, sum(rate(loki_request_duration_seconds_bucket[1m]))
+  - expr: "histogram_quantile(0.99, sum(rate(loki_request_duration_seconds_bucket[5m]))
-      by (le, cluster, namespace, job, route))
+      by (le, cluster, namespace, job, route))"
-    record: cluster_namespace_job_route:loki_request_duration_seconds:99quantile
+    record: "cluster_namespace_job_route:loki_request_duration_seconds:99quantile"
-  - expr: histogram_quantile(0.50, sum(rate(loki_request_duration_seconds_bucket[1m]))
+  - expr: "histogram_quantile(0.50, sum(rate(loki_request_duration_seconds_bucket[5m]))
-      by (le, cluster, namespace, job, route))
+      by (le, cluster, namespace, job, route))"
-    record: cluster_namespace_job_route:loki_request_duration_seconds:50quantile
+    record: "cluster_namespace_job_route:loki_request_duration_seconds:50quantile"
-  - expr: sum(rate(loki_request_duration_seconds_sum[1m])) by (cluster, namespace,
+  - expr: "sum(rate(loki_request_duration_seconds_sum[5m])) by (cluster, namespace,
-      job, route) / sum(rate(loki_request_duration_seconds_count[1m])) by (cluster,
+      job, route) / sum(rate(loki_request_duration_seconds_count[5m])) by (cluster,
-      namespace, job, route)
+      namespace, job, route)"
-    record: cluster_namespace_job_route:loki_request_duration_seconds:avg
+    record: "cluster_namespace_job_route:loki_request_duration_seconds:avg"
-  - expr: sum(rate(loki_request_duration_seconds_bucket[1m])) by (le, cluster, namespace,
+  - expr: "sum(rate(loki_request_duration_seconds_bucket[5m])) by (le, cluster, namespace,
-      job, route)
+      job, route)"
-    record: cluster_namespace_job_route:loki_request_duration_seconds_bucket:sum_rate
+    record: "cluster_namespace_job_route:loki_request_duration_seconds_bucket:sum_rate"
-  - expr: sum(rate(loki_request_duration_seconds_sum[1m])) by (cluster, namespace,
+  - expr: "sum(rate(loki_request_duration_seconds_sum[5m])) by (cluster, namespace,
-      job, route)
+      job, route)"
-    record: cluster_namespace_job_route:loki_request_duration_seconds_sum:sum_rate
+    record: "cluster_namespace_job_route:loki_request_duration_seconds_sum:sum_rate"
-  - expr: sum(rate(loki_request_duration_seconds_count[1m])) by (cluster, namespace,
+  - expr: "sum(rate(loki_request_duration_seconds_count[5m])) by (cluster, namespace,
-      job, route)
+      job, route)"
-    record: cluster_namespace_job_route:loki_request_duration_seconds_count:sum_rate
+    record: "cluster_namespace_job_route:loki_request_duration_seconds_count:sum_rate"

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

@@ -1,304 +1,299 @@
 groups:
-- name: mimir_api_1
+- name: "mimir_api_1"
   rules:
-  - expr: histogram_quantile(0.99, sum(rate(cortex_request_duration_seconds_bucket[1m]))
+  - expr: "histogram_quantile(0.99, sum(rate(cortex_request_duration_seconds_bucket[5m]))
-      by (le, cluster, job))
+      by (le, cluster, job))"
-    record: cluster_job:cortex_request_duration_seconds:99quantile
+    record: "cluster_job:cortex_request_duration_seconds:99quantile"
-  - expr: histogram_quantile(0.50, sum(rate(cortex_request_duration_seconds_bucket[1m]))
+  - expr: "histogram_quantile(0.50, sum(rate(cortex_request_duration_seconds_bucket[5m]))
-      by (le, cluster, job))
+      by (le, cluster, job))"
-    record: cluster_job:cortex_request_duration_seconds:50quantile
+    record: "cluster_job:cortex_request_duration_seconds:50quantile"
-  - expr: sum(rate(cortex_request_duration_seconds_sum[1m])) by (cluster, job) / sum(rate(cortex_request_duration_seconds_count[1m]))
+  - expr: "sum(rate(cortex_request_duration_seconds_sum[5m])) by (cluster, job) / sum(rate(cortex_request_duration_seconds_count[5m]))
-      by (cluster, job)
+      by (cluster, job)"
-    record: cluster_job:cortex_request_duration_seconds:avg
+    record: "cluster_job:cortex_request_duration_seconds:avg"
-  - expr: sum(rate(cortex_request_duration_seconds_bucket[1m])) by (le, cluster, job)
+  - expr: "sum(rate(cortex_request_duration_seconds_bucket[5m])) by (le, cluster, job)"
-    record: cluster_job:cortex_request_duration_seconds_bucket:sum_rate
+    record: "cluster_job:cortex_request_duration_seconds_bucket:sum_rate"
-  - expr: sum(rate(cortex_request_duration_seconds_sum[1m])) by (cluster, job)
+  - expr: "sum(rate(cortex_request_duration_seconds_sum[5m])) by (cluster, job)"
-    record: cluster_job:cortex_request_duration_seconds_sum:sum_rate
+    record: "cluster_job:cortex_request_duration_seconds_sum:sum_rate"
-  - expr: sum(rate(cortex_request_duration_seconds_count[1m])) by (cluster, job)
+  - expr: "sum(rate(cortex_request_duration_seconds_count[5m])) by (cluster, job)"
-    record: cluster_job:cortex_request_duration_seconds_count:sum_rate
+    record: "cluster_job:cortex_request_duration_seconds_count:sum_rate"
-- name: mimir_api_2
+- name: "mimir_api_2"
   rules:
-  - expr: histogram_quantile(0.99, sum(rate(cortex_request_duration_seconds_bucket[1m]))
+  - expr: "histogram_quantile(0.99, sum(rate(cortex_request_duration_seconds_bucket[5m]))
-      by (le, cluster, job, route))
+      by (le, cluster, job, route))"
-    record: cluster_job_route:cortex_request_duration_seconds:99quantile
+    record: "cluster_job_route:cortex_request_duration_seconds:99quantile"
-  - expr: histogram_quantile(0.50, sum(rate(cortex_request_duration_seconds_bucket[1m]))
+  - expr: "histogram_quantile(0.50, sum(rate(cortex_request_duration_seconds_bucket[5m]))
-      by (le, cluster, job, route))
+      by (le, cluster, job, route))"
-    record: cluster_job_route:cortex_request_duration_seconds:50quantile
+    record: "cluster_job_route:cortex_request_duration_seconds:50quantile"
-  - expr: sum(rate(cortex_request_duration_seconds_sum[1m])) by (cluster, job, route)
+  - expr: "sum(rate(cortex_request_duration_seconds_sum[5m])) by (cluster, job, route)
-      / sum(rate(cortex_request_duration_seconds_count[1m])) 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
+    record: "cluster_job_route:cortex_request_duration_seconds:avg"
-  - expr: sum(rate(cortex_request_duration_seconds_bucket[1m])) by (le, cluster, job,
+  - expr: "sum(rate(cortex_request_duration_seconds_bucket[5m])) by (le, cluster, job,
-      route)
+      route)"
-    record: cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate
+    record: "cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate"
-  - expr: sum(rate(cortex_request_duration_seconds_sum[1m])) by (cluster, job, route)
+  - expr: "sum(rate(cortex_request_duration_seconds_sum[5m])) by (cluster, job, route)"
-    record: cluster_job_route:cortex_request_duration_seconds_sum:sum_rate
+    record: "cluster_job_route:cortex_request_duration_seconds_sum:sum_rate"
-  - expr: sum(rate(cortex_request_duration_seconds_count[1m])) by (cluster, job, route)
+  - expr: "sum(rate(cortex_request_duration_seconds_count[5m])) by (cluster, job, route)"
-    record: cluster_job_route:cortex_request_duration_seconds_count:sum_rate
+    record: "cluster_job_route:cortex_request_duration_seconds_count:sum_rate"
-- name: mimir_api_3
+- name: "mimir_api_3"
   rules:
-  - expr: histogram_quantile(0.99, sum(rate(cortex_request_duration_seconds_bucket[1m]))
+  - expr: "histogram_quantile(0.99, sum(rate(cortex_request_duration_seconds_bucket[5m]))
-      by (le, cluster, namespace, job, route))
+      by (le, cluster, namespace, job, route))"
-    record: cluster_namespace_job_route:cortex_request_duration_seconds:99quantile
+    record: "cluster_namespace_job_route:cortex_request_duration_seconds:99quantile"
-  - expr: histogram_quantile(0.50, sum(rate(cortex_request_duration_seconds_bucket[1m]))
+  - expr: "histogram_quantile(0.50, sum(rate(cortex_request_duration_seconds_bucket[5m]))
-      by (le, cluster, namespace, job, route))
+      by (le, cluster, namespace, job, route))"
-    record: cluster_namespace_job_route:cortex_request_duration_seconds:50quantile
+    record: "cluster_namespace_job_route:cortex_request_duration_seconds:50quantile"
-  - expr: sum(rate(cortex_request_duration_seconds_sum[1m])) by (cluster, namespace,
+  - expr: "sum(rate(cortex_request_duration_seconds_sum[5m])) by (cluster, namespace,
-      job, route) / sum(rate(cortex_request_duration_seconds_count[1m])) by (cluster,
+      job, route) / sum(rate(cortex_request_duration_seconds_count[5m])) by (cluster,
-      namespace, job, route)
+      namespace, job, route)"
-    record: cluster_namespace_job_route:cortex_request_duration_seconds:avg
+    record: "cluster_namespace_job_route:cortex_request_duration_seconds:avg"
-  - expr: sum(rate(cortex_request_duration_seconds_bucket[1m])) by (le, cluster, namespace,
+  - expr: "sum(rate(cortex_request_duration_seconds_bucket[5m])) by (le, cluster, namespace,
-      job, route)
+      job, route)"
-    record: cluster_namespace_job_route:cortex_request_duration_seconds_bucket:sum_rate
+    record: "cluster_namespace_job_route:cortex_request_duration_seconds_bucket:sum_rate"
-  - expr: sum(rate(cortex_request_duration_seconds_sum[1m])) by (cluster, namespace,
+  - expr: "sum(rate(cortex_request_duration_seconds_sum[5m])) by (cluster, namespace,
-      job, route)
+      job, route)"
-    record: cluster_namespace_job_route:cortex_request_duration_seconds_sum:sum_rate
+    record: "cluster_namespace_job_route:cortex_request_duration_seconds_sum:sum_rate"
-  - expr: sum(rate(cortex_request_duration_seconds_count[1m])) by (cluster, namespace,
+  - expr: "sum(rate(cortex_request_duration_seconds_count[5m])) by (cluster, namespace,
-      job, route)
+      job, route)"
-    record: cluster_namespace_job_route:cortex_request_duration_seconds_count:sum_rate
+    record: "cluster_namespace_job_route:cortex_request_duration_seconds_count:sum_rate"
-- name: mimir_querier_api
+- name: "mimir_querier_api"
   rules:
-  - expr: histogram_quantile(0.99, sum(rate(cortex_querier_request_duration_seconds_bucket[1m]))
+  - expr: "histogram_quantile(0.99, sum(rate(cortex_querier_request_duration_seconds_bucket[5m]))
-      by (le, cluster, job))
+      by (le, cluster, job))"
-    record: cluster_job:cortex_querier_request_duration_seconds:99quantile
+    record: "cluster_job:cortex_querier_request_duration_seconds:99quantile"
-  - expr: histogram_quantile(0.50, sum(rate(cortex_querier_request_duration_seconds_bucket[1m]))
+  - expr: "histogram_quantile(0.50, sum(rate(cortex_querier_request_duration_seconds_bucket[5m]))
-      by (le, cluster, job))
+      by (le, cluster, job))"
-    record: cluster_job:cortex_querier_request_duration_seconds:50quantile
+    record: "cluster_job:cortex_querier_request_duration_seconds:50quantile"
-  - expr: sum(rate(cortex_querier_request_duration_seconds_sum[1m])) by (cluster,
+  - expr: "sum(rate(cortex_querier_request_duration_seconds_sum[5m])) by (cluster,
-      job) / sum(rate(cortex_querier_request_duration_seconds_count[1m])) by (cluster,
+      job) / sum(rate(cortex_querier_request_duration_seconds_count[5m])) by (cluster,
-      job)
+      job)"
-    record: cluster_job:cortex_querier_request_duration_seconds:avg
+    record: "cluster_job:cortex_querier_request_duration_seconds:avg"
-  - expr: sum(rate(cortex_querier_request_duration_seconds_bucket[1m])) by (le, cluster,
+  - expr: "sum(rate(cortex_querier_request_duration_seconds_bucket[5m])) by (le, cluster,
-      job)
+      job)"
-    record: cluster_job:cortex_querier_request_duration_seconds_bucket:sum_rate
+    record: "cluster_job:cortex_querier_request_duration_seconds_bucket:sum_rate"
-  - expr: sum(rate(cortex_querier_request_duration_seconds_sum[1m])) by (cluster,
+  - expr: "sum(rate(cortex_querier_request_duration_seconds_sum[5m])) by (cluster,
-      job)
+      job)"
-    record: cluster_job:cortex_querier_request_duration_seconds_sum:sum_rate
+    record: "cluster_job:cortex_querier_request_duration_seconds_sum:sum_rate"
-  - expr: sum(rate(cortex_querier_request_duration_seconds_count[1m])) by (cluster,
+  - expr: "sum(rate(cortex_querier_request_duration_seconds_count[5m])) by (cluster,
-      job)
+      job)"
-    record: cluster_job:cortex_querier_request_duration_seconds_count:sum_rate
+    record: "cluster_job:cortex_querier_request_duration_seconds_count:sum_rate"
-  - expr: histogram_quantile(0.99, sum(rate(cortex_querier_request_duration_seconds_bucket[1m]))
+  - expr: "histogram_quantile(0.99, sum(rate(cortex_querier_request_duration_seconds_bucket[5m]))
-      by (le, cluster, job, route))
+      by (le, cluster, job, route))"
-    record: cluster_job_route:cortex_querier_request_duration_seconds:99quantile
+    record: "cluster_job_route:cortex_querier_request_duration_seconds:99quantile"
-  - expr: histogram_quantile(0.50, sum(rate(cortex_querier_request_duration_seconds_bucket[1m]))
+  - expr: "histogram_quantile(0.50, sum(rate(cortex_querier_request_duration_seconds_bucket[5m]))
-      by (le, cluster, job, route))
+      by (le, cluster, job, route))"
-    record: cluster_job_route:cortex_querier_request_duration_seconds:50quantile
+    record: "cluster_job_route:cortex_querier_request_duration_seconds:50quantile"
-  - expr: sum(rate(cortex_querier_request_duration_seconds_sum[1m])) by (cluster,
+  - expr: "sum(rate(cortex_querier_request_duration_seconds_sum[5m])) by (cluster,
-      job, route) / sum(rate(cortex_querier_request_duration_seconds_count[1m])) by
+      job, route) / sum(rate(cortex_querier_request_duration_seconds_count[5m])) by
-      (cluster, job, route)
+      (cluster, job, route)"
-    record: cluster_job_route:cortex_querier_request_duration_seconds:avg
+    record: "cluster_job_route:cortex_querier_request_duration_seconds:avg"
-  - expr: sum(rate(cortex_querier_request_duration_seconds_bucket[1m])) by (le, cluster,
+  - expr: "sum(rate(cortex_querier_request_duration_seconds_bucket[5m])) by (le, cluster,
-      job, route)
+      job, route)"
-    record: cluster_job_route:cortex_querier_request_duration_seconds_bucket:sum_rate
+    record: "cluster_job_route:cortex_querier_request_duration_seconds_bucket:sum_rate"
-  - expr: sum(rate(cortex_querier_request_duration_seconds_sum[1m])) by (cluster,
+  - expr: "sum(rate(cortex_querier_request_duration_seconds_sum[5m])) by (cluster,
-      job, route)
+      job, route)"
-    record: cluster_job_route:cortex_querier_request_duration_seconds_sum:sum_rate
+    record: "cluster_job_route:cortex_querier_request_duration_seconds_sum:sum_rate"
-  - expr: sum(rate(cortex_querier_request_duration_seconds_count[1m])) by (cluster,
+  - expr: "sum(rate(cortex_querier_request_duration_seconds_count[5m])) by (cluster,
-      job, route)
+      job, route)"
-    record: cluster_job_route:cortex_querier_request_duration_seconds_count:sum_rate
+    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[1m]))
+  - expr: "histogram_quantile(0.99, sum(rate(cortex_querier_request_duration_seconds_bucket[5m]))
-      by (le, cluster, namespace, job, route))
+      by (le, cluster, namespace, job, route))"
-    record: cluster_namespace_job_route:cortex_querier_request_duration_seconds:99quantile
+    record: "cluster_namespace_job_route:cortex_querier_request_duration_seconds:99quantile"
-  - expr: histogram_quantile(0.50, sum(rate(cortex_querier_request_duration_seconds_bucket[1m]))
+  - expr: "histogram_quantile(0.50, sum(rate(cortex_querier_request_duration_seconds_bucket[5m]))
-      by (le, cluster, namespace, job, route))
+      by (le, cluster, namespace, job, route))"
-    record: cluster_namespace_job_route:cortex_querier_request_duration_seconds:50quantile
+    record: "cluster_namespace_job_route:cortex_querier_request_duration_seconds:50quantile"
-  - expr: sum(rate(cortex_querier_request_duration_seconds_sum[1m])) by (cluster,
+  - expr: "sum(rate(cortex_querier_request_duration_seconds_sum[5m])) by (cluster,
-      namespace, job, route) / sum(rate(cortex_querier_request_duration_seconds_count[1m]))
+      namespace, job, route) / sum(rate(cortex_querier_request_duration_seconds_count[5m]))
-      by (cluster, namespace, job, route)
+      by (cluster, namespace, job, route)"
-    record: cluster_namespace_job_route:cortex_querier_request_duration_seconds:avg
+    record: "cluster_namespace_job_route:cortex_querier_request_duration_seconds:avg"
-  - expr: sum(rate(cortex_querier_request_duration_seconds_bucket[1m])) by (le, cluster,
+  - expr: "sum(rate(cortex_querier_request_duration_seconds_bucket[5m])) by (le, cluster,
-      namespace, job, route)
+      namespace, job, route)"
-    record: cluster_namespace_job_route:cortex_querier_request_duration_seconds_bucket:sum_rate
+    record: "cluster_namespace_job_route:cortex_querier_request_duration_seconds_bucket:sum_rate"
-  - expr: sum(rate(cortex_querier_request_duration_seconds_sum[1m])) by (cluster,
+  - expr: "sum(rate(cortex_querier_request_duration_seconds_sum[5m])) by (cluster,
-      namespace, job, route)
+      namespace, job, route)"
-    record: cluster_namespace_job_route:cortex_querier_request_duration_seconds_sum:sum_rate
+    record: "cluster_namespace_job_route:cortex_querier_request_duration_seconds_sum:sum_rate"
-  - expr: sum(rate(cortex_querier_request_duration_seconds_count[1m])) by (cluster,
+  - expr: "sum(rate(cortex_querier_request_duration_seconds_count[5m])) by (cluster,
-      namespace, job, route)
+      namespace, job, route)"
-    record: cluster_namespace_job_route:cortex_querier_request_duration_seconds_count:sum_rate
+    record: "cluster_namespace_job_route:cortex_querier_request_duration_seconds_count:sum_rate"
-- name: mimir_cache
+- name: "mimir_cache"
   rules:
-  - expr: histogram_quantile(0.99, sum(rate(cortex_memcache_request_duration_seconds_bucket[1m]))
+  - expr: "histogram_quantile(0.99, sum(rate(cortex_memcache_request_duration_seconds_bucket[5m]))
-      by (le, cluster, job, method))
+      by (le, cluster, job, method))"
-    record: cluster_job_method:cortex_memcache_request_duration_seconds:99quantile
+    record: "cluster_job_method:cortex_memcache_request_duration_seconds:99quantile"
-  - expr: histogram_quantile(0.50, sum(rate(cortex_memcache_request_duration_seconds_bucket[1m]))
+  - expr: "histogram_quantile(0.50, sum(rate(cortex_memcache_request_duration_seconds_bucket[5m]))
-      by (le, cluster, job, method))
+      by (le, cluster, job, method))"
-    record: cluster_job_method:cortex_memcache_request_duration_seconds:50quantile
+    record: "cluster_job_method:cortex_memcache_request_duration_seconds:50quantile"
-  - expr: sum(rate(cortex_memcache_request_duration_seconds_sum[1m])) by (cluster,
+  - expr: "sum(rate(cortex_memcache_request_duration_seconds_sum[5m])) by (cluster,
-      job, method) / sum(rate(cortex_memcache_request_duration_seconds_count[1m]))
+      job, method) / sum(rate(cortex_memcache_request_duration_seconds_count[5m]))
-      by (cluster, job, method)
+      by (cluster, job, method)"
-    record: cluster_job_method:cortex_memcache_request_duration_seconds:avg
+    record: "cluster_job_method:cortex_memcache_request_duration_seconds:avg"
-  - expr: sum(rate(cortex_memcache_request_duration_seconds_bucket[1m])) by (le, cluster,
+  - expr: "sum(rate(cortex_memcache_request_duration_seconds_bucket[5m])) by (le, cluster,
-      job, method)
+      job, method)"
-    record: cluster_job_method:cortex_memcache_request_duration_seconds_bucket:sum_rate
+    record: "cluster_job_method:cortex_memcache_request_duration_seconds_bucket:sum_rate"
-  - expr: sum(rate(cortex_memcache_request_duration_seconds_sum[1m])) by (cluster,
+  - expr: "sum(rate(cortex_memcache_request_duration_seconds_sum[5m])) by (cluster,
-      job, method)
+      job, method)"
-    record: cluster_job_method:cortex_memcache_request_duration_seconds_sum:sum_rate
+    record: "cluster_job_method:cortex_memcache_request_duration_seconds_sum:sum_rate"
-  - expr: sum(rate(cortex_memcache_request_duration_seconds_count[1m])) by (cluster,
+  - expr: "sum(rate(cortex_memcache_request_duration_seconds_count[5m])) by (cluster,
-      job, method)
+      job, method)"
-    record: cluster_job_method:cortex_memcache_request_duration_seconds_count:sum_rate
+    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[1m]))
+  - expr: "histogram_quantile(0.99, sum(rate(cortex_cache_request_duration_seconds_bucket[5m]))
-      by (le, cluster, job))
+      by (le, cluster, job))"
-    record: cluster_job:cortex_cache_request_duration_seconds:99quantile
+    record: "cluster_job:cortex_cache_request_duration_seconds:99quantile"
-  - expr: histogram_quantile(0.50, sum(rate(cortex_cache_request_duration_seconds_bucket[1m]))
+  - expr: "histogram_quantile(0.50, sum(rate(cortex_cache_request_duration_seconds_bucket[5m]))
-      by (le, cluster, job))
+      by (le, cluster, job))"
-    record: cluster_job:cortex_cache_request_duration_seconds:50quantile
+    record: "cluster_job:cortex_cache_request_duration_seconds:50quantile"
-  - expr: sum(rate(cortex_cache_request_duration_seconds_sum[1m])) by (cluster, job)
+  - expr: "sum(rate(cortex_cache_request_duration_seconds_sum[5m])) by (cluster, job)
-      / sum(rate(cortex_cache_request_duration_seconds_count[1m])) by (cluster, job)
+      / sum(rate(cortex_cache_request_duration_seconds_count[5m])) by (cluster, job)"
-    record: cluster_job:cortex_cache_request_duration_seconds:avg
+    record: "cluster_job:cortex_cache_request_duration_seconds:avg"
-  - expr: sum(rate(cortex_cache_request_duration_seconds_bucket[1m])) by (le, cluster,
+  - expr: "sum(rate(cortex_cache_request_duration_seconds_bucket[5m])) by (le, cluster,
-      job)
+      job)"
-    record: cluster_job:cortex_cache_request_duration_seconds_bucket:sum_rate
+    record: "cluster_job:cortex_cache_request_duration_seconds_bucket:sum_rate"
-  - expr: sum(rate(cortex_cache_request_duration_seconds_sum[1m])) by (cluster, job)
+  - expr: "sum(rate(cortex_cache_request_duration_seconds_sum[5m])) by (cluster, job)"
-    record: cluster_job:cortex_cache_request_duration_seconds_sum:sum_rate
+    record: "cluster_job:cortex_cache_request_duration_seconds_sum:sum_rate"
-  - expr: sum(rate(cortex_cache_request_duration_seconds_count[1m])) by (cluster,
+  - expr: "sum(rate(cortex_cache_request_duration_seconds_count[5m])) by (cluster,
-      job)
+      job)"
-    record: cluster_job:cortex_cache_request_duration_seconds_count:sum_rate
+    record: "cluster_job:cortex_cache_request_duration_seconds_count:sum_rate"
-  - expr: histogram_quantile(0.99, sum(rate(cortex_cache_request_duration_seconds_bucket[1m]))
+  - expr: "histogram_quantile(0.99, sum(rate(cortex_cache_request_duration_seconds_bucket[5m]))
-      by (le, cluster, job, method))
+      by (le, cluster, job, method))"
-    record: cluster_job_method:cortex_cache_request_duration_seconds:99quantile
+    record: "cluster_job_method:cortex_cache_request_duration_seconds:99quantile"
-  - expr: histogram_quantile(0.50, sum(rate(cortex_cache_request_duration_seconds_bucket[1m]))
+  - expr: "histogram_quantile(0.50, sum(rate(cortex_cache_request_duration_seconds_bucket[5m]))
-      by (le, cluster, job, method))
+      by (le, cluster, job, method))"
-    record: cluster_job_method:cortex_cache_request_duration_seconds:50quantile
+    record: "cluster_job_method:cortex_cache_request_duration_seconds:50quantile"
-  - expr: sum(rate(cortex_cache_request_duration_seconds_sum[1m])) by (cluster, job,
+  - expr: "sum(rate(cortex_cache_request_duration_seconds_sum[5m])) by (cluster, job,
-      method) / sum(rate(cortex_cache_request_duration_seconds_count[1m])) by (cluster,
+      method) / sum(rate(cortex_cache_request_duration_seconds_count[5m])) by (cluster,
-      job, method)
+      job, method)"
-    record: cluster_job_method:cortex_cache_request_duration_seconds:avg
+    record: "cluster_job_method:cortex_cache_request_duration_seconds:avg"
-  - expr: sum(rate(cortex_cache_request_duration_seconds_bucket[1m])) by (le, cluster,
+  - expr: "sum(rate(cortex_cache_request_duration_seconds_bucket[5m])) by (le, cluster,
-      job, method)
+      job, method)"
-    record: cluster_job_method:cortex_cache_request_duration_seconds_bucket:sum_rate
+    record: "cluster_job_method:cortex_cache_request_duration_seconds_bucket:sum_rate"
-  - expr: sum(rate(cortex_cache_request_duration_seconds_sum[1m])) by (cluster, job,
+  - expr: "sum(rate(cortex_cache_request_duration_seconds_sum[5m])) by (cluster, job,
-      method)
+      method)"
-    record: cluster_job_method:cortex_cache_request_duration_seconds_sum:sum_rate
+    record: "cluster_job_method:cortex_cache_request_duration_seconds_sum:sum_rate"
-  - expr: sum(rate(cortex_cache_request_duration_seconds_count[1m])) by (cluster,
+  - expr: "sum(rate(cortex_cache_request_duration_seconds_count[5m])) by (cluster,
-      job, method)
+      job, method)"
-    record: cluster_job_method:cortex_cache_request_duration_seconds_count:sum_rate
+    record: "cluster_job_method:cortex_cache_request_duration_seconds_count:sum_rate"
-- name: mimir_storage
+- name: "mimir_storage"
   rules:
-  - expr: histogram_quantile(0.99, sum(rate(cortex_kv_request_duration_seconds_bucket[1m]))
+  - expr: "histogram_quantile(0.99, sum(rate(cortex_kv_request_duration_seconds_bucket[5m]))
-      by (le, cluster, job))
+      by (le, cluster, job))"
-    record: cluster_job:cortex_kv_request_duration_seconds:99quantile
+    record: "cluster_job:cortex_kv_request_duration_seconds:99quantile"
-  - expr: histogram_quantile(0.50, sum(rate(cortex_kv_request_duration_seconds_bucket[1m]))
+  - expr: "histogram_quantile(0.50, sum(rate(cortex_kv_request_duration_seconds_bucket[5m]))
-      by (le, cluster, job))
+      by (le, cluster, job))"
-    record: cluster_job:cortex_kv_request_duration_seconds:50quantile
+    record: "cluster_job:cortex_kv_request_duration_seconds:50quantile"
-  - expr: sum(rate(cortex_kv_request_duration_seconds_sum[1m])) by (cluster, job)
+  - expr: "sum(rate(cortex_kv_request_duration_seconds_sum[5m])) by (cluster, job)
-      / sum(rate(cortex_kv_request_duration_seconds_count[1m])) by (cluster, job)
+      / sum(rate(cortex_kv_request_duration_seconds_count[5m])) by (cluster, job)"
-    record: cluster_job:cortex_kv_request_duration_seconds:avg
+    record: "cluster_job:cortex_kv_request_duration_seconds:avg"
-  - expr: sum(rate(cortex_kv_request_duration_seconds_bucket[1m])) by (le, cluster,
+  - expr: "sum(rate(cortex_kv_request_duration_seconds_bucket[5m])) by (le, cluster,
-      job)
+      job)"
-    record: cluster_job:cortex_kv_request_duration_seconds_bucket:sum_rate
+    record: "cluster_job:cortex_kv_request_duration_seconds_bucket:sum_rate"
-  - expr: sum(rate(cortex_kv_request_duration_seconds_sum[1m])) by (cluster, job)
+  - expr: "sum(rate(cortex_kv_request_duration_seconds_sum[5m])) by (cluster, job)"
-    record: cluster_job:cortex_kv_request_duration_seconds_sum:sum_rate
+    record: "cluster_job:cortex_kv_request_duration_seconds_sum:sum_rate"
-  - expr: sum(rate(cortex_kv_request_duration_seconds_count[1m])) by (cluster, job)
+  - expr: "sum(rate(cortex_kv_request_duration_seconds_count[5m])) by (cluster, job)"
-    record: cluster_job:cortex_kv_request_duration_seconds_count:sum_rate
+    record: "cluster_job:cortex_kv_request_duration_seconds_count:sum_rate"
-- name: mimir_queries
+- name: "mimir_queries"
   rules:
-  - expr: histogram_quantile(0.99, sum(rate(cortex_query_frontend_retries_bucket[1m]))
+  - expr: "histogram_quantile(0.99, sum(rate(cortex_query_frontend_retries_bucket[5m]))
-      by (le, cluster, job))
+      by (le, cluster, job))"
-    record: cluster_job:cortex_query_frontend_retries:99quantile
+    record: "cluster_job:cortex_query_frontend_retries:99quantile"
-  - expr: histogram_quantile(0.50, sum(rate(cortex_query_frontend_retries_bucket[1m]))
+  - expr: "histogram_quantile(0.50, sum(rate(cortex_query_frontend_retries_bucket[5m]))
-      by (le, cluster, job))
+      by (le, cluster, job))"
-    record: cluster_job:cortex_query_frontend_retries:50quantile
+    record: "cluster_job:cortex_query_frontend_retries:50quantile"
-  - expr: sum(rate(cortex_query_frontend_retries_sum[1m])) by (cluster, job) / sum(rate(cortex_query_frontend_retries_count[1m]))
+  - expr: "sum(rate(cortex_query_frontend_retries_sum[5m])) by (cluster, job) / sum(rate(cortex_query_frontend_retries_count[5m]))
-      by (cluster, job)
+      by (cluster, job)"
-    record: cluster_job:cortex_query_frontend_retries:avg
+    record: "cluster_job:cortex_query_frontend_retries:avg"
-  - expr: sum(rate(cortex_query_frontend_retries_bucket[1m])) by (le, cluster, job)
+  - expr: "sum(rate(cortex_query_frontend_retries_bucket[5m])) by (le, cluster, job)"
-    record: cluster_job:cortex_query_frontend_retries_bucket:sum_rate
+    record: "cluster_job:cortex_query_frontend_retries_bucket:sum_rate"
-  - expr: sum(rate(cortex_query_frontend_retries_sum[1m])) by (cluster, job)
+  - expr: "sum(rate(cortex_query_frontend_retries_sum[5m])) by (cluster, job)"
-    record: cluster_job:cortex_query_frontend_retries_sum:sum_rate
+    record: "cluster_job:cortex_query_frontend_retries_sum:sum_rate"
-  - expr: sum(rate(cortex_query_frontend_retries_count[1m])) by (cluster, job)
+  - expr: "sum(rate(cortex_query_frontend_retries_count[5m])) by (cluster, job)"
-    record: cluster_job:cortex_query_frontend_retries_count:sum_rate
+    record: "cluster_job:cortex_query_frontend_retries_count:sum_rate"
-  - expr: histogram_quantile(0.99, sum(rate(cortex_query_frontend_queue_duration_seconds_bucket[1m]))
+  - expr: "histogram_quantile(0.99, sum(rate(cortex_query_frontend_queue_duration_seconds_bucket[5m]))
-      by (le, cluster, job))
+      by (le, cluster, job))"
-    record: cluster_job:cortex_query_frontend_queue_duration_seconds:99quantile
+    record: "cluster_job:cortex_query_frontend_queue_duration_seconds:99quantile"
-  - expr: histogram_quantile(0.50, sum(rate(cortex_query_frontend_queue_duration_seconds_bucket[1m]))
+  - expr: "histogram_quantile(0.50, sum(rate(cortex_query_frontend_queue_duration_seconds_bucket[5m]))
-      by (le, cluster, job))
+      by (le, cluster, job))"
-    record: cluster_job:cortex_query_frontend_queue_duration_seconds:50quantile
+    record: "cluster_job:cortex_query_frontend_queue_duration_seconds:50quantile"
-  - expr: sum(rate(cortex_query_frontend_queue_duration_seconds_sum[1m])) by (cluster,
+  - expr: "sum(rate(cortex_query_frontend_queue_duration_seconds_sum[5m])) by (cluster,
-      job) / sum(rate(cortex_query_frontend_queue_duration_seconds_count[1m])) by
+      job) / sum(rate(cortex_query_frontend_queue_duration_seconds_count[5m])) by
-      (cluster, job)
+      (cluster, job)"
-    record: cluster_job:cortex_query_frontend_queue_duration_seconds:avg
+    record: "cluster_job:cortex_query_frontend_queue_duration_seconds:avg"
-  - expr: sum(rate(cortex_query_frontend_queue_duration_seconds_bucket[1m])) by (le,
+  - expr: "sum(rate(cortex_query_frontend_queue_duration_seconds_bucket[5m])) by (le,
-      cluster, job)
+      cluster, job)"
-    record: cluster_job:cortex_query_frontend_queue_duration_seconds_bucket:sum_rate
+    record: "cluster_job:cortex_query_frontend_queue_duration_seconds_bucket:sum_rate"
-  - expr: sum(rate(cortex_query_frontend_queue_duration_seconds_sum[1m])) by (cluster,
+  - expr: "sum(rate(cortex_query_frontend_queue_duration_seconds_sum[5m])) by (cluster,
-      job)
+      job)"
-    record: cluster_job:cortex_query_frontend_queue_duration_seconds_sum:sum_rate
+    record: "cluster_job:cortex_query_frontend_queue_duration_seconds_sum:sum_rate"
-  - expr: sum(rate(cortex_query_frontend_queue_duration_seconds_count[1m])) by (cluster,
+  - expr: "sum(rate(cortex_query_frontend_queue_duration_seconds_count[5m])) by (cluster,
-      job)
+      job)"
-    record: cluster_job:cortex_query_frontend_queue_duration_seconds_count:sum_rate
+    record: "cluster_job:cortex_query_frontend_queue_duration_seconds_count:sum_rate"
-- name: mimir_ingester_queries
+- name: "mimir_ingester_queries"
   rules:
-  - expr: histogram_quantile(0.99, sum(rate(cortex_ingester_queried_series_bucket[1m]))
+  - expr: "histogram_quantile(0.99, sum(rate(cortex_ingester_queried_series_bucket[5m]))
-      by (le, cluster, job))
+      by (le, cluster, job))"
-    record: cluster_job:cortex_ingester_queried_series:99quantile
+    record: "cluster_job:cortex_ingester_queried_series:99quantile"
-  - expr: histogram_quantile(0.50, sum(rate(cortex_ingester_queried_series_bucket[1m]))
+  - expr: "histogram_quantile(0.50, sum(rate(cortex_ingester_queried_series_bucket[5m]))
-      by (le, cluster, job))
+      by (le, cluster, job))"
-    record: cluster_job:cortex_ingester_queried_series:50quantile
+    record: "cluster_job:cortex_ingester_queried_series:50quantile"
-  - expr: sum(rate(cortex_ingester_queried_series_sum[1m])) by (cluster, job) / sum(rate(cortex_ingester_queried_series_count[1m]))
+  - expr: "sum(rate(cortex_ingester_queried_series_sum[5m])) by (cluster, job) / sum(rate(cortex_ingester_queried_series_count[5m]))
-      by (cluster, job)
+      by (cluster, job)"
-    record: cluster_job:cortex_ingester_queried_series:avg
+    record: "cluster_job:cortex_ingester_queried_series:avg"
-  - expr: sum(rate(cortex_ingester_queried_series_bucket[1m])) by (le, cluster, job)
+  - expr: "sum(rate(cortex_ingester_queried_series_bucket[5m])) by (le, cluster, job)"
-    record: cluster_job:cortex_ingester_queried_series_bucket:sum_rate
+    record: "cluster_job:cortex_ingester_queried_series_bucket:sum_rate"
-  - expr: sum(rate(cortex_ingester_queried_series_sum[1m])) by (cluster, job)
+  - expr: "sum(rate(cortex_ingester_queried_series_sum[5m])) by (cluster, job)"
-    record: cluster_job:cortex_ingester_queried_series_sum:sum_rate
+    record: "cluster_job:cortex_ingester_queried_series_sum:sum_rate"
-  - expr: sum(rate(cortex_ingester_queried_series_count[1m])) by (cluster, job)
+  - expr: "sum(rate(cortex_ingester_queried_series_count[5m])) by (cluster, job)"
-    record: cluster_job:cortex_ingester_queried_series_count:sum_rate
+    record: "cluster_job:cortex_ingester_queried_series_count:sum_rate"
-  - expr: histogram_quantile(0.99, sum(rate(cortex_ingester_queried_samples_bucket[1m]))
+  - expr: "histogram_quantile(0.99, sum(rate(cortex_ingester_queried_samples_bucket[5m]))
-      by (le, cluster, job))
+      by (le, cluster, job))"
-    record: cluster_job:cortex_ingester_queried_samples:99quantile
+    record: "cluster_job:cortex_ingester_queried_samples:99quantile"
-  - expr: histogram_quantile(0.50, sum(rate(cortex_ingester_queried_samples_bucket[1m]))
+  - expr: "histogram_quantile(0.50, sum(rate(cortex_ingester_queried_samples_bucket[5m]))
-      by (le, cluster, job))
+      by (le, cluster, job))"
-    record: cluster_job:cortex_ingester_queried_samples:50quantile
+    record: "cluster_job:cortex_ingester_queried_samples:50quantile"
-  - expr: sum(rate(cortex_ingester_queried_samples_sum[1m])) by (cluster, job) / sum(rate(cortex_ingester_queried_samples_count[1m]))
+  - expr: "sum(rate(cortex_ingester_queried_samples_sum[5m])) by (cluster, job) / sum(rate(cortex_ingester_queried_samples_count[5m]))
-      by (cluster, job)
+      by (cluster, job)"
-    record: cluster_job:cortex_ingester_queried_samples:avg
+    record: "cluster_job:cortex_ingester_queried_samples:avg"
-  - expr: sum(rate(cortex_ingester_queried_samples_bucket[1m])) by (le, cluster, job)
+  - expr: "sum(rate(cortex_ingester_queried_samples_bucket[5m])) by (le, cluster, job)"
-    record: cluster_job:cortex_ingester_queried_samples_bucket:sum_rate
+    record: "cluster_job:cortex_ingester_queried_samples_bucket:sum_rate"
-  - expr: sum(rate(cortex_ingester_queried_samples_sum[1m])) by (cluster, job)
+  - expr: "sum(rate(cortex_ingester_queried_samples_sum[5m])) by (cluster, job)"
-    record: cluster_job:cortex_ingester_queried_samples_sum:sum_rate
+    record: "cluster_job:cortex_ingester_queried_samples_sum:sum_rate"
-  - expr: sum(rate(cortex_ingester_queried_samples_count[1m])) by (cluster, job)
+  - expr: "sum(rate(cortex_ingester_queried_samples_count[5m])) by (cluster, job)"
-    record: cluster_job:cortex_ingester_queried_samples_count:sum_rate
+    record: "cluster_job:cortex_ingester_queried_samples_count:sum_rate"
-  - expr: histogram_quantile(0.99, sum(rate(cortex_ingester_queried_exemplars_bucket[1m]))
+  - expr: "histogram_quantile(0.99, sum(rate(cortex_ingester_queried_exemplars_bucket[5m]))
-      by (le, cluster, job))
+      by (le, cluster, job))"
-    record: cluster_job:cortex_ingester_queried_exemplars:99quantile
+    record: "cluster_job:cortex_ingester_queried_exemplars:99quantile"
-  - expr: histogram_quantile(0.50, sum(rate(cortex_ingester_queried_exemplars_bucket[1m]))
+  - expr: "histogram_quantile(0.50, sum(rate(cortex_ingester_queried_exemplars_bucket[5m]))
-      by (le, cluster, job))
+      by (le, cluster, job))"
-    record: cluster_job:cortex_ingester_queried_exemplars:50quantile
+    record: "cluster_job:cortex_ingester_queried_exemplars:50quantile"
-  - expr: sum(rate(cortex_ingester_queried_exemplars_sum[1m])) by (cluster, job) /
+  - expr: "sum(rate(cortex_ingester_queried_exemplars_sum[5m])) by (cluster, job) /
-      sum(rate(cortex_ingester_queried_exemplars_count[1m])) by (cluster, job)
+      sum(rate(cortex_ingester_queried_exemplars_count[5m])) by (cluster, job)"
-    record: cluster_job:cortex_ingester_queried_exemplars:avg
+    record: "cluster_job:cortex_ingester_queried_exemplars:avg"
-  - expr: sum(rate(cortex_ingester_queried_exemplars_bucket[1m])) by (le, cluster,
+  - expr: "sum(rate(cortex_ingester_queried_exemplars_bucket[5m])) by (le, cluster,
-      job)
+      job)"
-    record: cluster_job:cortex_ingester_queried_exemplars_bucket:sum_rate
+    record: "cluster_job:cortex_ingester_queried_exemplars_bucket:sum_rate"
-  - expr: sum(rate(cortex_ingester_queried_exemplars_sum[1m])) by (cluster, job)
+  - expr: "sum(rate(cortex_ingester_queried_exemplars_sum[5m])) by (cluster, job)"
-    record: cluster_job:cortex_ingester_queried_exemplars_sum:sum_rate
+    record: "cluster_job:cortex_ingester_queried_exemplars_sum:sum_rate"
-  - expr: sum(rate(cortex_ingester_queried_exemplars_count[1m])) by (cluster, job)
+  - expr: "sum(rate(cortex_ingester_queried_exemplars_count[5m])) by (cluster, job)"
-    record: cluster_job:cortex_ingester_queried_exemplars_count:sum_rate
+    record: "cluster_job:cortex_ingester_queried_exemplars_count:sum_rate"
-- name: mimir_received_samples
+- name: "mimir_received_samples"
   rules:
-  - expr: |
+  - expr: "sum by (cluster, namespace, job) (rate(cortex_distributor_received_samples_total[5m]))"
-      sum by (cluster, namespace, job) (rate(cortex_distributor_received_samples_total[5m]))
+    record: "cluster_namespace_job:cortex_distributor_received_samples:rate5m"
-    record: cluster_namespace_job:cortex_distributor_received_samples:rate5m
+- name: "mimir_exemplars_in"
-- name: mimir_exemplars_in
   rules:
-  - expr: |
+  - expr: "sum by (cluster, namespace, job) (rate(cortex_distributor_exemplars_in_total[5m]))"
-      sum by (cluster, namespace, job) (rate(cortex_distributor_exemplars_in_total[5m]))
+    record: "cluster_namespace_job:cortex_distributor_exemplars_in:rate5m"
-    record: cluster_namespace_job:cortex_distributor_exemplars_in:rate5m
+- name: "mimir_received_exemplars"
-- name: mimir_received_exemplars
   rules:
-  - expr: |
+  - expr: "sum by (cluster, namespace, job) (rate(cortex_distributor_received_exemplars_total[5m]))"
-      sum by (cluster, namespace, job) (rate(cortex_distributor_received_exemplars_total[5m]))
+    record: "cluster_namespace_job:cortex_distributor_received_exemplars:rate5m"
-    record: cluster_namespace_job:cortex_distributor_received_exemplars:rate5m
+- name: "mimir_exemplars_ingested"
-- name: mimir_exemplars_ingested
   rules:
-  - expr: |
+  - expr: "sum by (cluster, namespace, job) (rate(cortex_ingester_ingested_exemplars_total[5m]))"
-      sum by (cluster, namespace, job) (rate(cortex_ingester_ingested_exemplars_total[5m]))
+    record: "cluster_namespace_job:cortex_ingester_ingested_exemplars:rate5m"
-    record: cluster_namespace_job:cortex_ingester_ingested_exemplars:rate5m
+- name: "mimir_exemplars_appended"
-- name: mimir_exemplars_appended
   rules:
-  - expr: |
+  - expr: "sum by (cluster, namespace, job) (rate(cortex_ingester_tsdb_exemplar_exemplars_appended_total[5m]))"
-      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"
-    record: cluster_namespace_job:cortex_ingester_tsdb_exemplar_exemplars_appended:rate5m
+- name: "mimir_scaling_rules"
-- name: mimir_scaling_rules
   rules:
   - expr: |
       # Convenience rule to get the number of replicas for both a deployment and a statefulset.
@@ -315,7 +310,7 @@ groups:
       sum by (cluster, namespace, deployment) (
         label_replace(kube_statefulset_replicas, "deployment", "$1", "statefulset", "(.*?)(?:-zone-[a-z])?")
       )
-    record: cluster_namespace_deployment:actual_replicas:count
+    record: "cluster_namespace_deployment:actual_replicas:count"
   - expr: |
       ceil(
         quantile_over_time(0.99,
@@ -326,18 +321,18 @@ groups:
         / 240000
       )
     labels:
-      deployment: distributor
+      deployment: "distributor"
-      reason: sample_rate
+      reason: "sample_rate"
-    record: cluster_namespace_deployment_reason:required_replicas:count
+    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
+      deployment: "distributor"
-      reason: sample_rate_limits
+      reason: "sample_rate_limits"
-    record: cluster_namespace_deployment_reason:required_replicas:count
+    record: "cluster_namespace_deployment_reason:required_replicas:count"
   - expr: |
       ceil(
         quantile_over_time(0.99,
@@ -348,9 +343,9 @@ groups:
         * 3 / 80000
       )
     labels:
-      deployment: ingester
+      deployment: "ingester"
-      reason: sample_rate
+      reason: "sample_rate"
-    record: cluster_namespace_deployment_reason:required_replicas:count
+    record: "cluster_namespace_deployment_reason:required_replicas:count"
   - expr: |
       ceil(
         quantile_over_time(0.99,
@@ -361,27 +356,27 @@ groups:
         / 1500000
       )
     labels:
-      deployment: ingester
+      deployment: "ingester"
-      reason: active_series
+      reason: "active_series"
-    record: cluster_namespace_deployment_reason:required_replicas:count
+    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
+      deployment: "ingester"
-      reason: active_series_limits
+      reason: "active_series_limits"
-    record: cluster_namespace_deployment_reason:required_replicas:count
+    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
+      deployment: "ingester"
-      reason: sample_rate_limits
+      reason: "sample_rate_limits"
-    record: cluster_namespace_deployment_reason:required_replicas:count
+    record: "cluster_namespace_deployment_reason:required_replicas:count"
   - expr: |
       ceil(
         (sum by (cluster, namespace) (
@@ -393,14 +388,14 @@ groups:
         )
       )
     labels:
-      deployment: memcached
+      deployment: "memcached"
-      reason: active_series
+      reason: "active_series"
-    record: cluster_namespace_deployment_reason:required_replicas:count
+    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[1m])),
+            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
@@ -408,7 +403,7 @@ groups:
           "deployment", "$1", "deployment", "(.*?)(?:-zone-[a-z])?"
         )
       )
-    record: cluster_namespace_deployment:container_cpu_usage_seconds_total:sum_rate
+    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.
@@ -448,7 +443,7 @@ groups:
           )
         )
       )
-    record: cluster_namespace_deployment:kube_pod_container_resource_requests_cpu_cores:sum
+    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
@@ -461,8 +456,8 @@ groups:
         cluster_namespace_deployment:kube_pod_container_resource_requests_cpu_cores:sum
       )
     labels:
-      reason: cpu_usage
+      reason: "cpu_usage"
-    record: cluster_namespace_deployment_reason:required_replicas:count
+    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.
@@ -477,7 +472,7 @@ groups:
           "deployment", "$1", "deployment", "(.*?)(?:-zone-[a-z])?"
         )
       )
-    record: cluster_namespace_deployment:container_memory_usage_bytes:sum
+    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.
@@ -517,7 +512,7 @@ groups:
           )
         )
       )
-    record: cluster_namespace_deployment:kube_pod_container_resource_requests_memory_bytes:sum
+    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
@@ -530,42 +525,31 @@ groups:
         cluster_namespace_deployment:kube_pod_container_resource_requests_memory_bytes:sum
       )
     labels:
-      reason: memory_usage
+      reason: "memory_usage"
-    record: cluster_namespace_deployment_reason:required_replicas:count
+    record: "cluster_namespace_deployment_reason:required_replicas:count"
-- name: mimir_alertmanager_rules
+- name: "mimir_alertmanager_rules"
   rules:
-  - expr: |
+  - expr: "sum by (cluster, job, pod) (cortex_alertmanager_alerts)"
-      sum by (cluster, job, pod) (cortex_alertmanager_alerts)
+    record: "cluster_job_pod:cortex_alertmanager_alerts:sum"
-    record: cluster_job_pod:cortex_alertmanager_alerts:sum
+  - expr: "sum by (cluster, job, pod) (cortex_alertmanager_silences)"
-  - expr: |
+    record: "cluster_job_pod:cortex_alertmanager_silences:sum"
-      sum by (cluster, job, pod) (cortex_alertmanager_silences)
+  - expr: "sum by (cluster, job) (rate(cortex_alertmanager_alerts_received_total[5m]))"
-    record: cluster_job_pod:cortex_alertmanager_silences:sum
+    record: "cluster_job:cortex_alertmanager_alerts_received_total:rate5m"
-  - expr: |
+  - expr: "sum by (cluster, job) (rate(cortex_alertmanager_alerts_invalid_total[5m]))"
-      sum by (cluster, job) (rate(cortex_alertmanager_alerts_received_total[5m]))
+    record: "cluster_job:cortex_alertmanager_alerts_invalid_total:rate5m"
-    record: cluster_job:cortex_alertmanager_alerts_received_total:rate5m
+  - expr: "sum by (cluster, job, integration) (rate(cortex_alertmanager_notifications_total[5m]))"
-  - expr: |
+    record: "cluster_job_integration:cortex_alertmanager_notifications_total:rate5m"
-      sum by (cluster, job) (rate(cortex_alertmanager_alerts_invalid_total[5m]))
+  - expr: "sum by (cluster, job, integration) (rate(cortex_alertmanager_notifications_failed_total[5m]))"
-    record: cluster_job:cortex_alertmanager_alerts_invalid_total:rate5m
+    record: "cluster_job_integration:cortex_alertmanager_notifications_failed_total:rate5m"
-  - expr: |
+  - expr: "sum by (cluster, job) (rate(cortex_alertmanager_state_replication_total[5m]))"
-      sum by (cluster, job, integration) (rate(cortex_alertmanager_notifications_total[5m]))
+    record: "cluster_job:cortex_alertmanager_state_replication_total:rate5m"
-    record: cluster_job_integration:cortex_alertmanager_notifications_total:rate5m
+  - expr: "sum by (cluster, job) (rate(cortex_alertmanager_state_replication_failed_total[5m]))"
-  - expr: |
+    record: "cluster_job:cortex_alertmanager_state_replication_failed_total:rate5m"
-      sum by (cluster, job, integration) (rate(cortex_alertmanager_notifications_failed_total[5m]))
+  - expr: "sum by (cluster, job) (rate(cortex_alertmanager_partial_state_merges_total[5m]))"
-    record: cluster_job_integration:cortex_alertmanager_notifications_failed_total:rate5m
+    record: "cluster_job:cortex_alertmanager_partial_state_merges_total:rate5m"
-  - expr: |
+  - expr: "sum by (cluster, job) (rate(cortex_alertmanager_partial_state_merges_failed_total[5m]))"
-      sum by (cluster, job) (rate(cortex_alertmanager_state_replication_total[5m]))
+    record: "cluster_job:cortex_alertmanager_partial_state_merges_failed_total:rate5m"
-    record: cluster_job:cortex_alertmanager_state_replication_total:rate5m
+- name: "mimir_ingester_rules"
-  - 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: |
+  - expr: "sum by(cluster, namespace, pod) (rate(cortex_ingester_ingested_samples_total[5m]))"
-      sum by(cluster, namespace, pod) (rate(cortex_ingester_ingested_samples_total[1m]))
+    record: "cluster_namespace_pod:cortex_ingester_ingested_samples_total:rate1m"
-    record: cluster_namespace_pod:cortex_ingester_ingested_samples_total:rate1m

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

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

@@ -18,10 +18,10 @@
 {{- end }}
 
 {{- define "agent.loki_process_targets" -}}
-{{- if empty .Values.logs.piiRegexes }}
+{{- if and (empty .Values.logs.piiRegexes) (empty .Values.logs.retain) }}
 {{- include "agent.loki_write_targets" . }}
 {{- else }}
-{{- printf "loki.process.PII.receiver" }}
+{{- printf "loki.process.filter.receiver" }}
 {{- end }}
 {{- 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" . }} ]
       }
     }
@@ -33,22 +33,38 @@ data:
       }
       rule {
         target_label = "cluster"
-        replacement = "{{- .Values.clusterName -}}"
+        replacement = "{{- .Values.clusterLabelValue -}}"
       }
     }
 
+    {{- if or .Values.local.logs.enabled .Values.cloud.logs.enabled }}
     // Logs
 
-    {{- if or .Values.local.logs.enabled .Values.cloud.logs.enabled }}
+    remote.kubernetes.secret "logs_credentials" {
+      namespace = "{{- $.Release.Namespace -}}"
+      name = "{{- .Values.cloud.logs.secret -}}"
+    }
+
     loki.source.kubernetes "pods" {
+      clustering {
+        enabled = true
+      }
       targets    = discovery.relabel.rename_meta_labels.output
       forward_to = [ {{ include "agent.loki_process_targets" . }} ]
     }
 
-    {{- if not (empty .Values.logs.piiRegexes) }}
+    {{- if or (not (empty .Values.logs.retain)) (not (empty .Values.logs.piiRegexes)) }}
-    loki.process "PII" {
+    loki.process "filter" {
       forward_to = [ {{ include "agent.loki_write_targets" . }} ]
 
+      {{- if not (empty .Values.logs.retain) }}
+      stage.match {
+        selector = "{cluster=\"{{- .Values.clusterLabelValue -}}\", namespace=~\"{{- join "|" .Values.namespacesToMonitor -}}|{{- $.Release.Namespace -}}\", pod=~\"loki.*\"} !~ \"{{ join "|" .Values.logs.retain }}\""
+        action   = "drop"
+      }
+      {{- end }}
+
+      {{- if not (empty .Values.logs.piiRegexes) }}
       {{- range .Values.logs.piiRegexes }}
       stage.replace {
         expression = "{{ .expression }}"
@@ -56,26 +72,85 @@ data:
         replace = "{{ .replace }}"
       }
       {{- end }}
+      {{- end }}
     }
     {{- end }}
     {{- end }}
 
+    {{- if or .Values.local.metrics.enabled .Values.cloud.metrics.enabled }}
     // Metrics
 
-    {{- if or .Values.local.metrics.enabled .Values.cloud.metrics.enabled }}
+    remote.kubernetes.secret "metrics_credentials" {
+      namespace = "{{- $.Release.Namespace -}}"
+      name = "{{- .Values.cloud.metrics.secret -}}"
+    }
+
+    discovery.kubernetes "metric_pods" {
+      role = "pod"
+      namespaces {
+        own_namespace = true
+        names = [ {{ include "agent.namespaces" . }} ]
+      }
+    }
+
+    discovery.relabel "only_http_metrics" {
+      targets = discovery.kubernetes.metric_pods.targets
+
+      rule {
+        source_labels = ["__meta_kubernetes_namespace"]
+        target_label  = "namespace"
+      }
+      rule {
+        source_labels = ["__meta_kubernetes_pod_name"]
+        target_label  = "pod"
+      }
+      rule {
+        source_labels = ["__meta_kubernetes_namespace", "__meta_kubernetes_pod_label_app_kubernetes_io_name", "__meta_kubernetes_pod_label_app_kubernetes_io_component"]
+        separator = "/"
+        regex = "(.*)/(.*)/(.*)"
+        replacement = "${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" {
-      targets    = discovery.relabel.rename_meta_labels.output
+      clustering {
+        enabled = true
+      }
+      targets    = discovery.relabel.only_http_metrics.output
+      forward_to = [ prometheus.relabel.filter.receiver ]
+    }
+
+    prometheus.relabel "filter" {
+      rule {
+        source_labels = ["__name__"]
+        regex = "({{ join "|" .Values.metrics.retain }})"
+        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 = [ {{ include "agent.prometheus_write_targets" . }} ]
+      forward_to = [ prometheus.relabel.filter.receiver ]
     }
     {{- end }}
 
-    // cAdvisor and Kubelete metrics
+    // 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"
@@ -104,15 +179,17 @@ data:
       }
       rule {
         target_label = "cluster"
-        replacement = "{{- .Values.clusterName -}}"
+        replacement = "{{- .Values.clusterLabelValue -}}"
       }
     }
 
     prometheus.scrape "cadvisor" {
+      clustering {
+        enabled = true
+      }
       targets    = discovery.relabel.all_nodes.output
-      forward_to = [ {{ include "agent.prometheus_write_targets" . }} ]
+      forward_to = [ prometheus.relabel.filter.receiver ]
 
-      scrape_interval = "15s"
       metrics_path = "/metrics/cadvisor"
       scheme = "https"
 
@@ -123,10 +200,12 @@ data:
     }
 
     prometheus.scrape "kubelet" {
+      clustering {
+        enabled = true
+      }
       targets    = discovery.relabel.all_nodes.output
-      forward_to = [ {{ include "agent.prometheus_write_targets" . }} ]
+      forward_to = [ prometheus.relabel.filter.receiver ]
 
-      scrape_interval = "15s"
       metrics_path = "/metrics"
       scheme = "https"
 
@@ -136,18 +215,20 @@ data:
       }
     }
 
-    prometheus.exporter.unix {}
+    prometheus.exporter.unix "promexporter" {}
 
     prometheus.scrape "node_exporter" {
-      targets = prometheus.exporter.unix.targets
+      clustering {
+        enabled = true
+      }
+      targets = prometheus.exporter.unix.promexporter.targets
       forward_to = [prometheus.relabel.node_exporter.receiver]
 
       job_name = "node-exporter"
-      scrape_interval = "15s"
     }
 
     prometheus.relabel "node_exporter" {
-      forward_to = [ {{ include "agent.prometheus_write_targets" . }} ]
+      forward_to = [ prometheus.relabel.filter.receiver ]
 
       rule {
         replacement = env("HOSTNAME")
@@ -178,14 +259,19 @@ data:
       }
       rule {
         target_label = "cluster"
-        replacement = "{{- .Values.clusterName -}}"
+        replacement = "{{- .Values.clusterLabelValue -}}"
       }
     }
     {{- end }}
 
+    {{- if or .Values.local.traces.enabled .Values.cloud.traces.enabled }}
     // Traces
 
-    {{- if or .Values.local.traces.enabled .Values.cloud.traces.enabled }}
+    remote.kubernetes.secret "traces_credentials" {
+      namespace = "{{- $.Release.Namespace -}}"
+      name = "{{- .Values.cloud.traces.secret -}}"
+    }
+
     // 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.
@@ -254,11 +340,10 @@ 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"]
         }
       }
     }
@@ -267,11 +352,10 @@ 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"]
         }
       }
     }
@@ -280,13 +364,13 @@ data:
     {{- if .Values.cloud.traces.enabled }}
     otelcol.exporter.otlp "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

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

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

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

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

@@ -1,4 +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: ConfigMap

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.yaml

@@ -1,4 +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

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

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

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

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

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

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

charts/meta-monitoring/templates/grafana/mimir-dashboards-3.yaml

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

charts/meta-monitoring/templates/grafana/mimir-dashboards-4.yaml

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

charts/meta-monitoring/templates/grafana/mimir-dashboards-5.yaml

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

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

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

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

@@ -1,9 +1,10 @@
-{{- if or (or .Values.dashboards.logs.enabled .Values.dashboards.metrics.enabled) .Values.dashboards.traces.enabled }}
+{{- if .Values.local.grafana.enabled }}
+{{- if and .Values.local.grafana.enabled (or .Values.dashboards.logs.enabled .Values.dashboards.metrics.enabled .Values.dashboards.traces.enabled) }}
 apiVersion: apps/v1
 kind: Deployment
 metadata:
-  name: meta-mimir-ruler-for-dashboards
+  name: {{ $.Release.Namespace }}-mimir-ruler-for-dashboards
-  namespace: meta
+  namespace: {{ $.Release.Namespace }}
 spec:
   progressDeadlineSeconds: 600
   replicas: 1
@@ -24,7 +25,7 @@ spec:
         app.kubernetes.io/component: ruler-for-dashboards
         app.kubernetes.io/instance: meta
         app.kubernetes.io/name: mimir
-      namespace: meta
+      namespace: {{ $.Release.Namespace }}
     spec:
       containers:
         - args:
@@ -91,8 +92,6 @@ spec:
         runAsUser: 10001
         seccompProfile:
           type: RuntimeDefault
-      serviceAccount: meta-mimir
-      serviceAccountName: meta-mimir
       terminationGracePeriodSeconds: 180
       topologySpreadConstraints:
         - labelSelector:
@@ -109,11 +108,11 @@ spec:
             items:
               - key: mimir.yaml
                 path: mimir.yaml
-            name: meta-mimir-config
+            name: {{ $.Release.Namespace }}-mimir-config
           name: config
         - configMap:
             defaultMode: 420
-            name: meta-mimir-runtime
+            name: {{ $.Release.Namespace }}-mimir-runtime
           name: runtime-config
         - emptyDir: {}
           name: storage
@@ -124,3 +123,4 @@ spec:
             name: rules
           name: rules
 {{- end }}
+{{- end }}

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

@@ -1,4 +1,5 @@
-{{- if or (or .Values.dashboards.logs.enabled .Values.dashboards.metrics.enabled) .Values.dashboards.traces.enabled }}
+{{- if .Values.local.metrics.enabled }}
+{{- if and .Values.local.grafana.enabled (or .Values.dashboards.logs.enabled .Values.dashboards.metrics.enabled .Values.dashboards.traces.enabled) }}
 ---
 apiVersion: v1
 kind: ConfigMap
@@ -16,3 +17,4 @@ data:
 {{ ($.Files.Glob "src/rules/tempo-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

@@ -1,13 +1,26 @@
 # Specify the namespaces to monitor here
 namespacesToMonitor:
 - loki
-- mimir
-- tempo
 # The name of the cluster where this will be installed
-clusterName: "meta-monitoring"
+clusterLabelValue: "meta-monitoring"
+
+# Set to true to write logs, metrics or traces to Grafana Cloud
+# The secrets have to be created first
+cloud:
+  logs:
+    enabled: true
+    secret: "logs"
+  metrics:
+    enabled: true
+    secret: "metrics"
+  traces:
+    enabled: true
+    secret: "traces"
 
 # Set to true for a local version of logs, metrics or traces
 local:
+  grafana:
+    enabled: false
   logs:
     enabled: false
   metrics:
@@ -17,33 +30,149 @@ local:
   minio:
     enabled: false  # This should be set to true if any of the previous is enabled
 
-# Set to true to write logs, metrics or traces to Grafana Cloud
+grafana:
-cloud:
+  # Gateway ingress configuration
-  logs:
+  ingress:
+    # -- Specifies whether an ingress for the gateway should be created
     enabled: true
-    endpoint:
+    # -- Ingress Class Name. MAY be required for Kubernetes versions >= 1.18
-    username:
+    ingressClassName: ""
-    password:
+    # -- Annotations for the gateway ingress
-  metrics:
+    annotations: { }
-    enabled: true
+    # -- Labels for the gateway ingress
-    endpoint:
+    labels: { }
-    username:
+    # -- Hosts configuration for the gateway ingress, passed through the `tpl` function to allow templating
-    password:
+    hosts:
-  traces:
+      - host: monitoring.example.com
-    enabled: true
+        paths:
-    endpoint:
+          - path: /
-    username:
+            # -- pathType (e.g. ImplementationSpecific, Prefix, .. etc.) might also be required by some Ingress Controllers
-    password:
+            # 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
+
 
-# 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
 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:
   # 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
+  # This shows the ingest requests and is very noisy. Uncomment to include.
+  # - caller=push.go
+  # Log lines for delete requests
+  - delete request for user added
+  - Started processing delete request
+  - delete request for user marked as processed
+
+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_persistentvolumeclaim_labels
+  - 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_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
+
 # Set enabled = true to add the default logs/metrics/traces dashboards to the local Grafana
 dashboards:
   logs:
@@ -72,6 +201,15 @@ kubeStateMetrics:
 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:
@@ -89,8 +227,13 @@ loki:
             secret_access_key: "{{ .Values.global.minio.rootPassword }}"
       compactor:
         retention_enabled: true
+        delete_request_store: s3
       limits_config:
-        retention_period: 24h
+        retention_period: 30d
+  lokiCanary:
+    enabled: false
+  test:
+    enabled: false
   monitoring:
     dashboards:
       enabled: false
@@ -107,12 +250,28 @@ loki:
   test:
     enabled: false
 
-grafana-agent:
+alloy:
-  agent:
+  alloy:
+    clustering:
+      enabled: true
     configMap:
       create: false
       name: "agent-configmap"
       key: 'config.river'
+    resources:
+      requests:
+        cpu: '1000m'
+        memory: '600Mi'
+      limits:
+        memory: '4Gi'
+  controller:
+    type: "statefulset"
+    autoscaling:
+      enabled: true
+      minReplicas: 3
+      maxReplicas: 30
+      targetMemoryUtilizationPercentage: 90
+      targetCPUUtilizationPercentage: 90
 
 mimir-distributed:
   minio:
@@ -142,7 +301,7 @@ mimir-distributed:
           secret_access_key: "{{ .Values.global.minio.rootPassword }}"
           insecure: true
       limits:
-        compactor_blocks_retention_period: 24h
+        compactor_blocks_retention_period: 30d
 
 tempo-distributed:
   tempo:
@@ -158,7 +317,7 @@ tempo-distributed:
             insecure: true
       compactor:
         compaction:
-          block_retention: 24h
+          block_retention: 30d
   traces:
     otlp:
       http:
@@ -193,4 +352,4 @@ 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 +1,166 @@
 # 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=<traces username> \
+    --from-literal=password=<token>
+    --from-literal=endpoint='https://tempo-us-central1.grafana.net/tempo'
+   ```
+
+   The logs, metrics and traces usernames are the `User / Username / Instance IDs` of the Loki, Prometheus/Mimir and Tempo instances in Grafana Cloud. From `Home` in Grafana click on `Stacks`. Then go to the `Details` pages of Loki, Prometheus/Mimir and Tempo.
+
+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 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>
+  ```

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
+