Rename agent dashboard file

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

.github/workflows/helm-ci.yml

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

Makefile

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

charts/meta-monitoring/Chart.lock

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

charts/meta-monitoring/Chart.yaml

@@ -25,18 +25,18 @@ appVersion: "0.0.1"
 
 dependencies:
 - name: loki
-  repository:  https://grafana.github.io/helm-charts
+  repository: https://grafana.github.io/helm-charts
   version: "5.8.0"
   condition: local.logs.enabled
 - name: grafana-agent
-  repository:  https://grafana.github.io/helm-charts
+  repository: https://grafana.github.io/helm-charts
   version: "0.15.0"
 - name: mimir-distributed
-  repository:  https://grafana.github.io/helm-charts
+  repository: https://grafana.github.io/helm-charts
   version: "4.4.1"
   condition: local.metrics.enabled
 - name: tempo-distributed
-  repository:  https://grafana.github.io/helm-charts
+  repository: https://grafana.github.io/helm-charts
   version: "1.4.7"
   condition: local.traces.enabled
 - name: minio

charts/meta-monitoring/Makefile

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

charts/meta-monitoring/ct.yaml

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

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

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

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

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

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

@@ -1,322 +1,322 @@
 groups:
-- name: mimir_api_1
+- name: "mimir_api_1"
   rules:
-  - expr: histogram_quantile(0.99, sum(rate(cortex_request_duration_seconds_bucket[1m]))
-      by (le, cluster, job))
-    record: cluster_job:cortex_request_duration_seconds:99quantile
-  - expr: histogram_quantile(0.50, sum(rate(cortex_request_duration_seconds_bucket[1m]))
-      by (le, cluster, job))
-    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]))
-      by (cluster, job)
-    record: cluster_job:cortex_request_duration_seconds:avg
-  - expr: sum(rate(cortex_request_duration_seconds_bucket[1m])) by (le, cluster, job)
-    record: cluster_job:cortex_request_duration_seconds_bucket:sum_rate
-  - expr: sum(rate(cortex_request_duration_seconds_sum[1m])) by (cluster, job)
-    record: cluster_job:cortex_request_duration_seconds_sum:sum_rate
-  - expr: sum(rate(cortex_request_duration_seconds_count[1m])) by (cluster, job)
-    record: cluster_job:cortex_request_duration_seconds_count:sum_rate
-- name: mimir_api_2
+  - expr: "histogram_quantile(0.99, sum(rate(cortex_request_duration_seconds_bucket[1m]))
+      by (le, cluster, job))"
+    record: "cluster_job:cortex_request_duration_seconds:99quantile"
+  - expr: "histogram_quantile(0.50, sum(rate(cortex_request_duration_seconds_bucket[1m]))
+      by (le, cluster, job))"
+    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]))
+      by (cluster, job)"
+    record: "cluster_job:cortex_request_duration_seconds:avg"
+  - expr: "sum(rate(cortex_request_duration_seconds_bucket[1m])) by (le, cluster, job)"
+    record: "cluster_job:cortex_request_duration_seconds_bucket:sum_rate"
+  - expr: "sum(rate(cortex_request_duration_seconds_sum[1m])) by (cluster, job)"
+    record: "cluster_job:cortex_request_duration_seconds_sum:sum_rate"
+  - expr: "sum(rate(cortex_request_duration_seconds_count[1m])) by (cluster, job)"
+    record: "cluster_job:cortex_request_duration_seconds_count:sum_rate"
+- name: "mimir_api_2"
   rules:
-  - expr: histogram_quantile(0.99, sum(rate(cortex_request_duration_seconds_bucket[1m]))
-      by (le, cluster, job, route))
-    record: cluster_job_route:cortex_request_duration_seconds:99quantile
-  - expr: histogram_quantile(0.50, sum(rate(cortex_request_duration_seconds_bucket[1m]))
-      by (le, cluster, job, route))
-    record: cluster_job_route:cortex_request_duration_seconds:50quantile
-  - expr: sum(rate(cortex_request_duration_seconds_sum[1m])) by (cluster, job, route)
-      / sum(rate(cortex_request_duration_seconds_count[1m])) by (cluster, job, route)
-    record: cluster_job_route:cortex_request_duration_seconds:avg
-  - expr: sum(rate(cortex_request_duration_seconds_bucket[1m])) by (le, cluster, job,
-      route)
-    record: cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate
-  - expr: sum(rate(cortex_request_duration_seconds_sum[1m])) by (cluster, job, route)
-    record: cluster_job_route:cortex_request_duration_seconds_sum:sum_rate
-  - expr: sum(rate(cortex_request_duration_seconds_count[1m])) by (cluster, job, route)
-    record: cluster_job_route:cortex_request_duration_seconds_count:sum_rate
-- name: mimir_api_3
+  - expr: "histogram_quantile(0.99, sum(rate(cortex_request_duration_seconds_bucket[1m]))
+      by (le, cluster, job, route))"
+    record: "cluster_job_route:cortex_request_duration_seconds:99quantile"
+  - expr: "histogram_quantile(0.50, sum(rate(cortex_request_duration_seconds_bucket[1m]))
+      by (le, cluster, job, route))"
+    record: "cluster_job_route:cortex_request_duration_seconds:50quantile"
+  - expr: "sum(rate(cortex_request_duration_seconds_sum[1m])) by (cluster, job, route)
+      / sum(rate(cortex_request_duration_seconds_count[1m])) by (cluster, job, route)"
+    record: "cluster_job_route:cortex_request_duration_seconds:avg"
+  - expr: "sum(rate(cortex_request_duration_seconds_bucket[1m])) by (le, cluster, job,
+      route)"
+    record: "cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate"
+  - expr: "sum(rate(cortex_request_duration_seconds_sum[1m])) by (cluster, job, route)"
+    record: "cluster_job_route:cortex_request_duration_seconds_sum:sum_rate"
+  - expr: "sum(rate(cortex_request_duration_seconds_count[1m])) by (cluster, job, route)"
+    record: "cluster_job_route:cortex_request_duration_seconds_count:sum_rate"
+- name: "mimir_api_3"
   rules:
-  - expr: histogram_quantile(0.99, sum(rate(cortex_request_duration_seconds_bucket[1m]))
-      by (le, cluster, namespace, job, route))
-    record: cluster_namespace_job_route:cortex_request_duration_seconds:99quantile
-  - expr: histogram_quantile(0.50, sum(rate(cortex_request_duration_seconds_bucket[1m]))
-      by (le, cluster, namespace, job, route))
-    record: cluster_namespace_job_route:cortex_request_duration_seconds:50quantile
-  - expr: sum(rate(cortex_request_duration_seconds_sum[1m])) by (cluster, namespace,
+  - expr: "histogram_quantile(0.99, sum(rate(cortex_request_duration_seconds_bucket[1m]))
+      by (le, cluster, namespace, job, route))"
+    record: "cluster_namespace_job_route:cortex_request_duration_seconds:99quantile"
+  - expr: "histogram_quantile(0.50, sum(rate(cortex_request_duration_seconds_bucket[1m]))
+      by (le, cluster, namespace, job, route))"
+    record: "cluster_namespace_job_route:cortex_request_duration_seconds:50quantile"
+  - expr: "sum(rate(cortex_request_duration_seconds_sum[1m])) by (cluster, namespace,
       job, route) / sum(rate(cortex_request_duration_seconds_count[1m])) by (cluster,
-      namespace, job, route)
-    record: cluster_namespace_job_route:cortex_request_duration_seconds:avg
-  - expr: sum(rate(cortex_request_duration_seconds_bucket[1m])) by (le, cluster, namespace,
-      job, route)
-    record: cluster_namespace_job_route:cortex_request_duration_seconds_bucket:sum_rate
-  - expr: sum(rate(cortex_request_duration_seconds_sum[1m])) by (cluster, namespace,
-      job, route)
-    record: cluster_namespace_job_route:cortex_request_duration_seconds_sum:sum_rate
-  - expr: sum(rate(cortex_request_duration_seconds_count[1m])) by (cluster, namespace,
-      job, route)
-    record: cluster_namespace_job_route:cortex_request_duration_seconds_count:sum_rate
-- name: mimir_querier_api
+      namespace, job, route)"
+    record: "cluster_namespace_job_route:cortex_request_duration_seconds:avg"
+  - expr: "sum(rate(cortex_request_duration_seconds_bucket[1m])) by (le, cluster, namespace,
+      job, route)"
+    record: "cluster_namespace_job_route:cortex_request_duration_seconds_bucket:sum_rate"
+  - expr: "sum(rate(cortex_request_duration_seconds_sum[1m])) by (cluster, namespace,
+      job, route)"
+    record: "cluster_namespace_job_route:cortex_request_duration_seconds_sum:sum_rate"
+  - expr: "sum(rate(cortex_request_duration_seconds_count[1m])) by (cluster, namespace,
+      job, route)"
+    record: "cluster_namespace_job_route:cortex_request_duration_seconds_count:sum_rate"
+- name: "mimir_querier_api"
   rules:
-  - expr: histogram_quantile(0.99, sum(rate(cortex_querier_request_duration_seconds_bucket[1m]))
-      by (le, cluster, job))
-    record: cluster_job:cortex_querier_request_duration_seconds:99quantile
-  - expr: histogram_quantile(0.50, sum(rate(cortex_querier_request_duration_seconds_bucket[1m]))
-      by (le, cluster, job))
-    record: cluster_job:cortex_querier_request_duration_seconds:50quantile
-  - expr: sum(rate(cortex_querier_request_duration_seconds_sum[1m])) by (cluster,
+  - expr: "histogram_quantile(0.99, sum(rate(cortex_querier_request_duration_seconds_bucket[1m]))
+      by (le, cluster, job))"
+    record: "cluster_job:cortex_querier_request_duration_seconds:99quantile"
+  - expr: "histogram_quantile(0.50, sum(rate(cortex_querier_request_duration_seconds_bucket[1m]))
+      by (le, cluster, job))"
+    record: "cluster_job:cortex_querier_request_duration_seconds:50quantile"
+  - expr: "sum(rate(cortex_querier_request_duration_seconds_sum[1m])) by (cluster,
       job) / sum(rate(cortex_querier_request_duration_seconds_count[1m])) by (cluster,
-      job)
-    record: cluster_job:cortex_querier_request_duration_seconds:avg
-  - expr: sum(rate(cortex_querier_request_duration_seconds_bucket[1m])) by (le, cluster,
-      job)
-    record: cluster_job:cortex_querier_request_duration_seconds_bucket:sum_rate
-  - expr: sum(rate(cortex_querier_request_duration_seconds_sum[1m])) by (cluster,
-      job)
-    record: cluster_job:cortex_querier_request_duration_seconds_sum:sum_rate
-  - expr: sum(rate(cortex_querier_request_duration_seconds_count[1m])) by (cluster,
-      job)
-    record: cluster_job:cortex_querier_request_duration_seconds_count:sum_rate
-  - expr: histogram_quantile(0.99, sum(rate(cortex_querier_request_duration_seconds_bucket[1m]))
-      by (le, cluster, job, route))
-    record: cluster_job_route:cortex_querier_request_duration_seconds:99quantile
-  - expr: histogram_quantile(0.50, sum(rate(cortex_querier_request_duration_seconds_bucket[1m]))
-      by (le, cluster, job, route))
-    record: cluster_job_route:cortex_querier_request_duration_seconds:50quantile
-  - expr: sum(rate(cortex_querier_request_duration_seconds_sum[1m])) by (cluster,
+      job)"
+    record: "cluster_job:cortex_querier_request_duration_seconds:avg"
+  - expr: "sum(rate(cortex_querier_request_duration_seconds_bucket[1m])) by (le, cluster,
+      job)"
+    record: "cluster_job:cortex_querier_request_duration_seconds_bucket:sum_rate"
+  - expr: "sum(rate(cortex_querier_request_duration_seconds_sum[1m])) by (cluster,
+      job)"
+    record: "cluster_job:cortex_querier_request_duration_seconds_sum:sum_rate"
+  - expr: "sum(rate(cortex_querier_request_duration_seconds_count[1m])) by (cluster,
+      job)"
+    record: "cluster_job:cortex_querier_request_duration_seconds_count:sum_rate"
+  - expr: "histogram_quantile(0.99, sum(rate(cortex_querier_request_duration_seconds_bucket[1m]))
+      by (le, cluster, job, route))"
+    record: "cluster_job_route:cortex_querier_request_duration_seconds:99quantile"
+  - expr: "histogram_quantile(0.50, sum(rate(cortex_querier_request_duration_seconds_bucket[1m]))
+      by (le, cluster, job, route))"
+    record: "cluster_job_route:cortex_querier_request_duration_seconds:50quantile"
+  - expr: "sum(rate(cortex_querier_request_duration_seconds_sum[1m])) by (cluster,
       job, route) / sum(rate(cortex_querier_request_duration_seconds_count[1m])) by
-      (cluster, job, route)
-    record: cluster_job_route:cortex_querier_request_duration_seconds:avg
-  - expr: sum(rate(cortex_querier_request_duration_seconds_bucket[1m])) by (le, cluster,
-      job, route)
-    record: cluster_job_route:cortex_querier_request_duration_seconds_bucket:sum_rate
-  - expr: sum(rate(cortex_querier_request_duration_seconds_sum[1m])) by (cluster,
-      job, route)
-    record: cluster_job_route:cortex_querier_request_duration_seconds_sum:sum_rate
-  - expr: sum(rate(cortex_querier_request_duration_seconds_count[1m])) by (cluster,
-      job, route)
-    record: cluster_job_route:cortex_querier_request_duration_seconds_count:sum_rate
-  - expr: histogram_quantile(0.99, sum(rate(cortex_querier_request_duration_seconds_bucket[1m]))
-      by (le, cluster, namespace, job, route))
-    record: cluster_namespace_job_route:cortex_querier_request_duration_seconds:99quantile
-  - expr: histogram_quantile(0.50, sum(rate(cortex_querier_request_duration_seconds_bucket[1m]))
-      by (le, cluster, namespace, job, route))
-    record: cluster_namespace_job_route:cortex_querier_request_duration_seconds:50quantile
-  - expr: sum(rate(cortex_querier_request_duration_seconds_sum[1m])) by (cluster,
+      (cluster, job, route)"
+    record: "cluster_job_route:cortex_querier_request_duration_seconds:avg"
+  - expr: "sum(rate(cortex_querier_request_duration_seconds_bucket[1m])) by (le, cluster,
+      job, route)"
+    record: "cluster_job_route:cortex_querier_request_duration_seconds_bucket:sum_rate"
+  - expr: "sum(rate(cortex_querier_request_duration_seconds_sum[1m])) by (cluster,
+      job, route)"
+    record: "cluster_job_route:cortex_querier_request_duration_seconds_sum:sum_rate"
+  - expr: "sum(rate(cortex_querier_request_duration_seconds_count[1m])) by (cluster,
+      job, route)"
+    record: "cluster_job_route:cortex_querier_request_duration_seconds_count:sum_rate"
+  - expr: "histogram_quantile(0.99, sum(rate(cortex_querier_request_duration_seconds_bucket[1m]))
+      by (le, cluster, namespace, job, route))"
+    record: "cluster_namespace_job_route:cortex_querier_request_duration_seconds:99quantile"
+  - expr: "histogram_quantile(0.50, sum(rate(cortex_querier_request_duration_seconds_bucket[1m]))
+      by (le, cluster, namespace, job, route))"
+    record: "cluster_namespace_job_route:cortex_querier_request_duration_seconds:50quantile"
+  - expr: "sum(rate(cortex_querier_request_duration_seconds_sum[1m])) by (cluster,
       namespace, job, route) / sum(rate(cortex_querier_request_duration_seconds_count[1m]))
-      by (cluster, namespace, job, route)
-    record: cluster_namespace_job_route:cortex_querier_request_duration_seconds:avg
-  - expr: sum(rate(cortex_querier_request_duration_seconds_bucket[1m])) by (le, cluster,
-      namespace, job, route)
-    record: cluster_namespace_job_route:cortex_querier_request_duration_seconds_bucket:sum_rate
-  - expr: sum(rate(cortex_querier_request_duration_seconds_sum[1m])) by (cluster,
-      namespace, job, route)
-    record: cluster_namespace_job_route:cortex_querier_request_duration_seconds_sum:sum_rate
-  - expr: sum(rate(cortex_querier_request_duration_seconds_count[1m])) by (cluster,
-      namespace, job, route)
-    record: cluster_namespace_job_route:cortex_querier_request_duration_seconds_count:sum_rate
-- name: mimir_cache
+      by (cluster, namespace, job, route)"
+    record: "cluster_namespace_job_route:cortex_querier_request_duration_seconds:avg"
+  - expr: "sum(rate(cortex_querier_request_duration_seconds_bucket[1m])) by (le, cluster,
+      namespace, job, route)"
+    record: "cluster_namespace_job_route:cortex_querier_request_duration_seconds_bucket:sum_rate"
+  - expr: "sum(rate(cortex_querier_request_duration_seconds_sum[1m])) by (cluster,
+      namespace, job, route)"
+    record: "cluster_namespace_job_route:cortex_querier_request_duration_seconds_sum:sum_rate"
+  - expr: "sum(rate(cortex_querier_request_duration_seconds_count[1m])) by (cluster,
+      namespace, job, route)"
+    record: "cluster_namespace_job_route:cortex_querier_request_duration_seconds_count:sum_rate"
+- name: "mimir_cache"
   rules:
-  - expr: histogram_quantile(0.99, sum(rate(cortex_memcache_request_duration_seconds_bucket[1m]))
-      by (le, cluster, job, method))
-    record: cluster_job_method:cortex_memcache_request_duration_seconds:99quantile
-  - expr: histogram_quantile(0.50, sum(rate(cortex_memcache_request_duration_seconds_bucket[1m]))
-      by (le, cluster, job, method))
-    record: cluster_job_method:cortex_memcache_request_duration_seconds:50quantile
-  - expr: sum(rate(cortex_memcache_request_duration_seconds_sum[1m])) by (cluster,
+  - expr: "histogram_quantile(0.99, sum(rate(cortex_memcache_request_duration_seconds_bucket[1m]))
+      by (le, cluster, job, method))"
+    record: "cluster_job_method:cortex_memcache_request_duration_seconds:99quantile"
+  - expr: "histogram_quantile(0.50, sum(rate(cortex_memcache_request_duration_seconds_bucket[1m]))
+      by (le, cluster, job, method))"
+    record: "cluster_job_method:cortex_memcache_request_duration_seconds:50quantile"
+  - expr: "sum(rate(cortex_memcache_request_duration_seconds_sum[1m])) by (cluster,
       job, method) / sum(rate(cortex_memcache_request_duration_seconds_count[1m]))
-      by (cluster, job, method)
-    record: cluster_job_method:cortex_memcache_request_duration_seconds:avg
-  - expr: sum(rate(cortex_memcache_request_duration_seconds_bucket[1m])) by (le, cluster,
-      job, method)
-    record: cluster_job_method:cortex_memcache_request_duration_seconds_bucket:sum_rate
-  - expr: sum(rate(cortex_memcache_request_duration_seconds_sum[1m])) by (cluster,
-      job, method)
-    record: cluster_job_method:cortex_memcache_request_duration_seconds_sum:sum_rate
-  - expr: sum(rate(cortex_memcache_request_duration_seconds_count[1m])) by (cluster,
-      job, method)
-    record: cluster_job_method:cortex_memcache_request_duration_seconds_count:sum_rate
-  - expr: histogram_quantile(0.99, sum(rate(cortex_cache_request_duration_seconds_bucket[1m]))
-      by (le, cluster, job))
-    record: cluster_job:cortex_cache_request_duration_seconds:99quantile
-  - expr: histogram_quantile(0.50, sum(rate(cortex_cache_request_duration_seconds_bucket[1m]))
-      by (le, cluster, job))
-    record: cluster_job:cortex_cache_request_duration_seconds:50quantile
-  - expr: sum(rate(cortex_cache_request_duration_seconds_sum[1m])) by (cluster, job)
-      / sum(rate(cortex_cache_request_duration_seconds_count[1m])) by (cluster, job)
-    record: cluster_job:cortex_cache_request_duration_seconds:avg
-  - expr: sum(rate(cortex_cache_request_duration_seconds_bucket[1m])) by (le, cluster,
-      job)
-    record: cluster_job:cortex_cache_request_duration_seconds_bucket:sum_rate
-  - expr: sum(rate(cortex_cache_request_duration_seconds_sum[1m])) by (cluster, job)
-    record: cluster_job:cortex_cache_request_duration_seconds_sum:sum_rate
-  - expr: sum(rate(cortex_cache_request_duration_seconds_count[1m])) by (cluster,
-      job)
-    record: cluster_job:cortex_cache_request_duration_seconds_count:sum_rate
-  - expr: histogram_quantile(0.99, sum(rate(cortex_cache_request_duration_seconds_bucket[1m]))
-      by (le, cluster, job, method))
-    record: cluster_job_method:cortex_cache_request_duration_seconds:99quantile
-  - expr: histogram_quantile(0.50, sum(rate(cortex_cache_request_duration_seconds_bucket[1m]))
-      by (le, cluster, job, method))
-    record: cluster_job_method:cortex_cache_request_duration_seconds:50quantile
-  - expr: sum(rate(cortex_cache_request_duration_seconds_sum[1m])) by (cluster, job,
+      by (cluster, job, method)"
+    record: "cluster_job_method:cortex_memcache_request_duration_seconds:avg"
+  - expr: "sum(rate(cortex_memcache_request_duration_seconds_bucket[1m])) by (le, cluster,
+      job, method)"
+    record: "cluster_job_method:cortex_memcache_request_duration_seconds_bucket:sum_rate"
+  - expr: "sum(rate(cortex_memcache_request_duration_seconds_sum[1m])) by (cluster,
+      job, method)"
+    record: "cluster_job_method:cortex_memcache_request_duration_seconds_sum:sum_rate"
+  - expr: "sum(rate(cortex_memcache_request_duration_seconds_count[1m])) by (cluster,
+      job, method)"
+    record: "cluster_job_method:cortex_memcache_request_duration_seconds_count:sum_rate"
+  - expr: "histogram_quantile(0.99, sum(rate(cortex_cache_request_duration_seconds_bucket[1m]))
+      by (le, cluster, job))"
+    record: "cluster_job:cortex_cache_request_duration_seconds:99quantile"
+  - expr: "histogram_quantile(0.50, sum(rate(cortex_cache_request_duration_seconds_bucket[1m]))
+      by (le, cluster, job))"
+    record: "cluster_job:cortex_cache_request_duration_seconds:50quantile"
+  - expr: "sum(rate(cortex_cache_request_duration_seconds_sum[1m])) by (cluster, job)
+      / sum(rate(cortex_cache_request_duration_seconds_count[1m])) by (cluster, job)"
+    record: "cluster_job:cortex_cache_request_duration_seconds:avg"
+  - expr: "sum(rate(cortex_cache_request_duration_seconds_bucket[1m])) by (le, cluster,
+      job)"
+    record: "cluster_job:cortex_cache_request_duration_seconds_bucket:sum_rate"
+  - expr: "sum(rate(cortex_cache_request_duration_seconds_sum[1m])) by (cluster, job)"
+    record: "cluster_job:cortex_cache_request_duration_seconds_sum:sum_rate"
+  - expr: "sum(rate(cortex_cache_request_duration_seconds_count[1m])) by (cluster,
+      job)"
+    record: "cluster_job:cortex_cache_request_duration_seconds_count:sum_rate"
+  - expr: "histogram_quantile(0.99, sum(rate(cortex_cache_request_duration_seconds_bucket[1m]))
+      by (le, cluster, job, method))"
+    record: "cluster_job_method:cortex_cache_request_duration_seconds:99quantile"
+  - expr: "histogram_quantile(0.50, sum(rate(cortex_cache_request_duration_seconds_bucket[1m]))
+      by (le, cluster, job, method))"
+    record: "cluster_job_method:cortex_cache_request_duration_seconds:50quantile"
+  - expr: "sum(rate(cortex_cache_request_duration_seconds_sum[1m])) by (cluster, job,
       method) / sum(rate(cortex_cache_request_duration_seconds_count[1m])) by (cluster,
-      job, method)
-    record: cluster_job_method:cortex_cache_request_duration_seconds:avg
-  - expr: sum(rate(cortex_cache_request_duration_seconds_bucket[1m])) by (le, cluster,
-      job, method)
-    record: cluster_job_method:cortex_cache_request_duration_seconds_bucket:sum_rate
-  - expr: sum(rate(cortex_cache_request_duration_seconds_sum[1m])) by (cluster, job,
-      method)
-    record: cluster_job_method:cortex_cache_request_duration_seconds_sum:sum_rate
-  - expr: sum(rate(cortex_cache_request_duration_seconds_count[1m])) by (cluster,
-      job, method)
-    record: cluster_job_method:cortex_cache_request_duration_seconds_count:sum_rate
-- name: mimir_storage
+      job, method)"
+    record: "cluster_job_method:cortex_cache_request_duration_seconds:avg"
+  - expr: "sum(rate(cortex_cache_request_duration_seconds_bucket[1m])) by (le, cluster,
+      job, method)"
+    record: "cluster_job_method:cortex_cache_request_duration_seconds_bucket:sum_rate"
+  - expr: "sum(rate(cortex_cache_request_duration_seconds_sum[1m])) by (cluster, job,
+      method)"
+    record: "cluster_job_method:cortex_cache_request_duration_seconds_sum:sum_rate"
+  - expr: "sum(rate(cortex_cache_request_duration_seconds_count[1m])) by (cluster,
+      job, method)"
+    record: "cluster_job_method:cortex_cache_request_duration_seconds_count:sum_rate"
+- name: "mimir_storage"
   rules:
-  - expr: histogram_quantile(0.99, sum(rate(cortex_kv_request_duration_seconds_bucket[1m]))
-      by (le, cluster, job))
-    record: cluster_job:cortex_kv_request_duration_seconds:99quantile
-  - expr: histogram_quantile(0.50, sum(rate(cortex_kv_request_duration_seconds_bucket[1m]))
-      by (le, cluster, job))
-    record: cluster_job:cortex_kv_request_duration_seconds:50quantile
-  - expr: sum(rate(cortex_kv_request_duration_seconds_sum[1m])) by (cluster, job)
-      / sum(rate(cortex_kv_request_duration_seconds_count[1m])) by (cluster, job)
-    record: cluster_job:cortex_kv_request_duration_seconds:avg
-  - expr: sum(rate(cortex_kv_request_duration_seconds_bucket[1m])) by (le, cluster,
-      job)
-    record: cluster_job:cortex_kv_request_duration_seconds_bucket:sum_rate
-  - expr: sum(rate(cortex_kv_request_duration_seconds_sum[1m])) by (cluster, job)
-    record: cluster_job:cortex_kv_request_duration_seconds_sum:sum_rate
-  - expr: sum(rate(cortex_kv_request_duration_seconds_count[1m])) by (cluster, job)
-    record: cluster_job:cortex_kv_request_duration_seconds_count:sum_rate
-- name: mimir_queries
+  - expr: "histogram_quantile(0.99, sum(rate(cortex_kv_request_duration_seconds_bucket[1m]))
+      by (le, cluster, job))"
+    record: "cluster_job:cortex_kv_request_duration_seconds:99quantile"
+  - expr: "histogram_quantile(0.50, sum(rate(cortex_kv_request_duration_seconds_bucket[1m]))
+      by (le, cluster, job))"
+    record: "cluster_job:cortex_kv_request_duration_seconds:50quantile"
+  - expr: "sum(rate(cortex_kv_request_duration_seconds_sum[1m])) by (cluster, job)
+      / sum(rate(cortex_kv_request_duration_seconds_count[1m])) by (cluster, job)"
+    record: "cluster_job:cortex_kv_request_duration_seconds:avg"
+  - expr: "sum(rate(cortex_kv_request_duration_seconds_bucket[1m])) by (le, cluster,
+      job)"
+    record: "cluster_job:cortex_kv_request_duration_seconds_bucket:sum_rate"
+  - expr: "sum(rate(cortex_kv_request_duration_seconds_sum[1m])) by (cluster, job)"
+    record: "cluster_job:cortex_kv_request_duration_seconds_sum:sum_rate"
+  - expr: "sum(rate(cortex_kv_request_duration_seconds_count[1m])) by (cluster, job)"
+    record: "cluster_job:cortex_kv_request_duration_seconds_count:sum_rate"
+- name: "mimir_queries"
   rules:
-  - expr: histogram_quantile(0.99, sum(rate(cortex_query_frontend_retries_bucket[1m]))
-      by (le, cluster, job))
-    record: cluster_job:cortex_query_frontend_retries:99quantile
-  - expr: histogram_quantile(0.50, sum(rate(cortex_query_frontend_retries_bucket[1m]))
-      by (le, cluster, job))
-    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]))
-      by (cluster, job)
-    record: cluster_job:cortex_query_frontend_retries:avg
-  - expr: sum(rate(cortex_query_frontend_retries_bucket[1m])) by (le, cluster, job)
-    record: cluster_job:cortex_query_frontend_retries_bucket:sum_rate
-  - expr: sum(rate(cortex_query_frontend_retries_sum[1m])) by (cluster, job)
-    record: cluster_job:cortex_query_frontend_retries_sum:sum_rate
-  - expr: sum(rate(cortex_query_frontend_retries_count[1m])) by (cluster, job)
-    record: cluster_job:cortex_query_frontend_retries_count:sum_rate
-  - expr: histogram_quantile(0.99, sum(rate(cortex_query_frontend_queue_duration_seconds_bucket[1m]))
-      by (le, cluster, job))
-    record: cluster_job:cortex_query_frontend_queue_duration_seconds:99quantile
-  - expr: histogram_quantile(0.50, sum(rate(cortex_query_frontend_queue_duration_seconds_bucket[1m]))
-      by (le, cluster, job))
-    record: cluster_job:cortex_query_frontend_queue_duration_seconds:50quantile
-  - expr: sum(rate(cortex_query_frontend_queue_duration_seconds_sum[1m])) by (cluster,
+  - expr: "histogram_quantile(0.99, sum(rate(cortex_query_frontend_retries_bucket[1m]))
+      by (le, cluster, job))"
+    record: "cluster_job:cortex_query_frontend_retries:99quantile"
+  - expr: "histogram_quantile(0.50, sum(rate(cortex_query_frontend_retries_bucket[1m]))
+      by (le, cluster, job))"
+    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]))
+      by (cluster, job)"
+    record: "cluster_job:cortex_query_frontend_retries:avg"
+  - expr: "sum(rate(cortex_query_frontend_retries_bucket[1m])) by (le, cluster, job)"
+    record: "cluster_job:cortex_query_frontend_retries_bucket:sum_rate"
+  - expr: "sum(rate(cortex_query_frontend_retries_sum[1m])) by (cluster, job)"
+    record: "cluster_job:cortex_query_frontend_retries_sum:sum_rate"
+  - expr: "sum(rate(cortex_query_frontend_retries_count[1m])) by (cluster, job)"
+    record: "cluster_job:cortex_query_frontend_retries_count:sum_rate"
+  - expr: "histogram_quantile(0.99, sum(rate(cortex_query_frontend_queue_duration_seconds_bucket[1m]))
+      by (le, cluster, job))"
+    record: "cluster_job:cortex_query_frontend_queue_duration_seconds:99quantile"
+  - expr: "histogram_quantile(0.50, sum(rate(cortex_query_frontend_queue_duration_seconds_bucket[1m]))
+      by (le, cluster, job))"
+    record: "cluster_job:cortex_query_frontend_queue_duration_seconds:50quantile"
+  - expr: "sum(rate(cortex_query_frontend_queue_duration_seconds_sum[1m])) by (cluster,
       job) / sum(rate(cortex_query_frontend_queue_duration_seconds_count[1m])) by
-      (cluster, job)
-    record: cluster_job:cortex_query_frontend_queue_duration_seconds:avg
-  - expr: sum(rate(cortex_query_frontend_queue_duration_seconds_bucket[1m])) by (le,
-      cluster, job)
-    record: cluster_job:cortex_query_frontend_queue_duration_seconds_bucket:sum_rate
-  - expr: sum(rate(cortex_query_frontend_queue_duration_seconds_sum[1m])) by (cluster,
-      job)
-    record: cluster_job:cortex_query_frontend_queue_duration_seconds_sum:sum_rate
-  - expr: sum(rate(cortex_query_frontend_queue_duration_seconds_count[1m])) by (cluster,
-      job)
-    record: cluster_job:cortex_query_frontend_queue_duration_seconds_count:sum_rate
-- name: mimir_ingester_queries
+      (cluster, job)"
+    record: "cluster_job:cortex_query_frontend_queue_duration_seconds:avg"
+  - expr: "sum(rate(cortex_query_frontend_queue_duration_seconds_bucket[1m])) by (le,
+      cluster, job)"
+    record: "cluster_job:cortex_query_frontend_queue_duration_seconds_bucket:sum_rate"
+  - expr: "sum(rate(cortex_query_frontend_queue_duration_seconds_sum[1m])) by (cluster,
+      job)"
+    record: "cluster_job:cortex_query_frontend_queue_duration_seconds_sum:sum_rate"
+  - expr: "sum(rate(cortex_query_frontend_queue_duration_seconds_count[1m])) by (cluster,
+      job)"
+    record: "cluster_job:cortex_query_frontend_queue_duration_seconds_count:sum_rate"
+- name: "mimir_ingester_queries"
   rules:
-  - expr: histogram_quantile(0.99, sum(rate(cortex_ingester_queried_series_bucket[1m]))
-      by (le, cluster, job))
-    record: cluster_job:cortex_ingester_queried_series:99quantile
-  - expr: histogram_quantile(0.50, sum(rate(cortex_ingester_queried_series_bucket[1m]))
-      by (le, cluster, job))
-    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]))
-      by (cluster, job)
-    record: cluster_job:cortex_ingester_queried_series:avg
-  - expr: sum(rate(cortex_ingester_queried_series_bucket[1m])) by (le, cluster, job)
-    record: cluster_job:cortex_ingester_queried_series_bucket:sum_rate
-  - expr: sum(rate(cortex_ingester_queried_series_sum[1m])) by (cluster, job)
-    record: cluster_job:cortex_ingester_queried_series_sum:sum_rate
-  - expr: sum(rate(cortex_ingester_queried_series_count[1m])) by (cluster, job)
-    record: cluster_job:cortex_ingester_queried_series_count:sum_rate
-  - expr: histogram_quantile(0.99, sum(rate(cortex_ingester_queried_samples_bucket[1m]))
-      by (le, cluster, job))
-    record: cluster_job:cortex_ingester_queried_samples:99quantile
-  - expr: histogram_quantile(0.50, sum(rate(cortex_ingester_queried_samples_bucket[1m]))
-      by (le, cluster, job))
-    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]))
-      by (cluster, job)
-    record: cluster_job:cortex_ingester_queried_samples:avg
-  - expr: sum(rate(cortex_ingester_queried_samples_bucket[1m])) by (le, cluster, job)
-    record: cluster_job:cortex_ingester_queried_samples_bucket:sum_rate
-  - expr: sum(rate(cortex_ingester_queried_samples_sum[1m])) by (cluster, job)
-    record: cluster_job:cortex_ingester_queried_samples_sum:sum_rate
-  - expr: sum(rate(cortex_ingester_queried_samples_count[1m])) by (cluster, job)
-    record: cluster_job:cortex_ingester_queried_samples_count:sum_rate
-  - expr: histogram_quantile(0.99, sum(rate(cortex_ingester_queried_exemplars_bucket[1m]))
-      by (le, cluster, job))
-    record: cluster_job:cortex_ingester_queried_exemplars:99quantile
-  - expr: histogram_quantile(0.50, sum(rate(cortex_ingester_queried_exemplars_bucket[1m]))
-      by (le, cluster, job))
-    record: cluster_job:cortex_ingester_queried_exemplars:50quantile
-  - expr: sum(rate(cortex_ingester_queried_exemplars_sum[1m])) by (cluster, job) /
-      sum(rate(cortex_ingester_queried_exemplars_count[1m])) by (cluster, job)
-    record: cluster_job:cortex_ingester_queried_exemplars:avg
-  - expr: sum(rate(cortex_ingester_queried_exemplars_bucket[1m])) by (le, cluster,
-      job)
-    record: cluster_job:cortex_ingester_queried_exemplars_bucket:sum_rate
-  - expr: sum(rate(cortex_ingester_queried_exemplars_sum[1m])) by (cluster, job)
-    record: cluster_job:cortex_ingester_queried_exemplars_sum:sum_rate
-  - expr: sum(rate(cortex_ingester_queried_exemplars_count[1m])) by (cluster, job)
-    record: cluster_job:cortex_ingester_queried_exemplars_count:sum_rate
-- name: mimir_received_samples
+  - expr: "histogram_quantile(0.99, sum(rate(cortex_ingester_queried_series_bucket[1m]))
+      by (le, cluster, job))"
+    record: "cluster_job:cortex_ingester_queried_series:99quantile"
+  - expr: "histogram_quantile(0.50, sum(rate(cortex_ingester_queried_series_bucket[1m]))
+      by (le, cluster, job))"
+    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]))
+      by (cluster, job)"
+    record: "cluster_job:cortex_ingester_queried_series:avg"
+  - expr: "sum(rate(cortex_ingester_queried_series_bucket[1m])) by (le, cluster, job)"
+    record: "cluster_job:cortex_ingester_queried_series_bucket:sum_rate"
+  - expr: "sum(rate(cortex_ingester_queried_series_sum[1m])) by (cluster, job)"
+    record: "cluster_job:cortex_ingester_queried_series_sum:sum_rate"
+  - expr: "sum(rate(cortex_ingester_queried_series_count[1m])) by (cluster, job)"
+    record: "cluster_job:cortex_ingester_queried_series_count:sum_rate"
+  - expr: "histogram_quantile(0.99, sum(rate(cortex_ingester_queried_samples_bucket[1m]))
+      by (le, cluster, job))"
+    record: "cluster_job:cortex_ingester_queried_samples:99quantile"
+  - expr: "histogram_quantile(0.50, sum(rate(cortex_ingester_queried_samples_bucket[1m]))
+      by (le, cluster, job))"
+    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]))
+      by (cluster, job)"
+    record: "cluster_job:cortex_ingester_queried_samples:avg"
+  - expr: "sum(rate(cortex_ingester_queried_samples_bucket[1m])) by (le, cluster, job)"
+    record: "cluster_job:cortex_ingester_queried_samples_bucket:sum_rate"
+  - expr: "sum(rate(cortex_ingester_queried_samples_sum[1m])) by (cluster, job)"
+    record: "cluster_job:cortex_ingester_queried_samples_sum:sum_rate"
+  - expr: "sum(rate(cortex_ingester_queried_samples_count[1m])) by (cluster, job)"
+    record: "cluster_job:cortex_ingester_queried_samples_count:sum_rate"
+  - expr: "histogram_quantile(0.99, sum(rate(cortex_ingester_queried_exemplars_bucket[1m]))
+      by (le, cluster, job))"
+    record: "cluster_job:cortex_ingester_queried_exemplars:99quantile"
+  - expr: "histogram_quantile(0.50, sum(rate(cortex_ingester_queried_exemplars_bucket[1m]))
+      by (le, cluster, job))"
+    record: "cluster_job:cortex_ingester_queried_exemplars:50quantile"
+  - expr: "sum(rate(cortex_ingester_queried_exemplars_sum[1m])) by (cluster, job) /
+      sum(rate(cortex_ingester_queried_exemplars_count[1m])) by (cluster, job)"
+    record: "cluster_job:cortex_ingester_queried_exemplars:avg"
+  - expr: "sum(rate(cortex_ingester_queried_exemplars_bucket[1m])) by (le, cluster,
+      job)"
+    record: "cluster_job:cortex_ingester_queried_exemplars_bucket:sum_rate"
+  - expr: "sum(rate(cortex_ingester_queried_exemplars_sum[1m])) by (cluster, job)"
+    record: "cluster_job:cortex_ingester_queried_exemplars_sum:sum_rate"
+  - expr: "sum(rate(cortex_ingester_queried_exemplars_count[1m])) by (cluster, job)"
+    record: "cluster_job:cortex_ingester_queried_exemplars_count:sum_rate"
+- name: "mimir_received_samples"
   rules:
-  - expr: |
-      sum by (cluster, namespace, job) (rate(cortex_distributor_received_samples_total[5m]))
-    record: cluster_namespace_job:cortex_distributor_received_samples:rate5m
-- name: mimir_exemplars_in
+  - expr: "|
+      sum by (cluster, namespace, job) (rate(cortex_distributor_received_samples_total[5m]))"
+    record: "cluster_namespace_job:cortex_distributor_received_samples:rate5m"
+- name: "mimir_exemplars_in"
   rules:
-  - expr: |
-      sum by (cluster, namespace, job) (rate(cortex_distributor_exemplars_in_total[5m]))
-    record: cluster_namespace_job:cortex_distributor_exemplars_in:rate5m
-- name: mimir_received_exemplars
+  - expr: "|
+      sum by (cluster, namespace, job) (rate(cortex_distributor_exemplars_in_total[5m]))"
+    record: "cluster_namespace_job:cortex_distributor_exemplars_in:rate5m"
+- name: "mimir_received_exemplars"
   rules:
-  - expr: |
-      sum by (cluster, namespace, job) (rate(cortex_distributor_received_exemplars_total[5m]))
-    record: cluster_namespace_job:cortex_distributor_received_exemplars:rate5m
-- name: mimir_exemplars_ingested
+  - expr: "|
+      sum by (cluster, namespace, job) (rate(cortex_distributor_received_exemplars_total[5m]))"
+    record: "cluster_namespace_job:cortex_distributor_received_exemplars:rate5m"
+- name: "mimir_exemplars_ingested"
   rules:
-  - expr: |
-      sum by (cluster, namespace, job) (rate(cortex_ingester_ingested_exemplars_total[5m]))
-    record: cluster_namespace_job:cortex_ingester_ingested_exemplars:rate5m
-- name: mimir_exemplars_appended
+  - expr: "|
+      sum by (cluster, namespace, job) (rate(cortex_ingester_ingested_exemplars_total[5m]))"
+    record: "cluster_namespace_job:cortex_ingester_ingested_exemplars:rate5m"
+- name: "mimir_exemplars_appended"
   rules:
-  - expr: |
-      sum by (cluster, namespace, job) (rate(cortex_ingester_tsdb_exemplar_exemplars_appended_total[5m]))
-    record: cluster_namespace_job:cortex_ingester_tsdb_exemplar_exemplars_appended:rate5m
-- name: mimir_scaling_rules
+  - expr: "|
+      sum by (cluster, namespace, job) (rate(cortex_ingester_tsdb_exemplar_exemplars_appended_total[5m]))"
+    record: "cluster_namespace_job:cortex_ingester_tsdb_exemplar_exemplars_appended:rate5m"
+- name: "mimir_scaling_rules"
   rules:
-  - expr: |
+  - expr: "|
       # Convenience rule to get the number of replicas for both a deployment and a statefulset.
-      # Multi-zone deployments are grouped together removing the "zone-X" suffix.
+      # Multi-zone deployments are grouped together removing the \"zone-X\" suffix.
       sum by (cluster, namespace, deployment) (
         label_replace(
           kube_deployment_spec_replicas,
-          # The question mark in "(.*?)" is used to make it non-greedy, otherwise it
+          # The question mark in \"(.*?)\" is used to make it non-greedy, otherwise it
           # always matches everything and the (optional) zone is not removed.
-          "deployment", "$1", "deployment", "(.*?)(?:-zone-[a-z])?"
+          \"deployment\", \"$1\", \"deployment\", \"(.*?)(?:-zone-[a-z])?\"
         )
       )
       or
       sum by (cluster, namespace, deployment) (
-        label_replace(kube_statefulset_replicas, "deployment", "$1", "statefulset", "(.*?)(?:-zone-[a-z])?")
-      )
-    record: cluster_namespace_deployment:actual_replicas:count
-  - expr: |
+        label_replace(kube_statefulset_replicas, \"deployment\", \"$1\", \"statefulset\", \"(.*?)(?:-zone-[a-z])?\")
+      )"
+    record: "cluster_namespace_deployment:actual_replicas:count"
+  - expr: "|
       ceil(
         quantile_over_time(0.99,
           sum by (cluster, namespace) (
@@ -324,21 +324,21 @@ groups:
           )[24h:]
         )
         / 240000
-      )
+      )"
     labels:
-      deployment: distributor
-      reason: sample_rate
-    record: cluster_namespace_deployment_reason:required_replicas:count
-  - expr: |
+      deployment: "distributor"
+      reason: "sample_rate"
+    record: "cluster_namespace_deployment_reason:required_replicas:count"
+  - expr: "|
       ceil(
-        sum by (cluster, namespace) (cortex_limits_overrides{limit_name="ingestion_rate"})
+        sum by (cluster, namespace) (cortex_limits_overrides{limit_name=\"ingestion_rate\"})
         * 0.59999999999999998 / 240000
-      )
+      )"
     labels:
-      deployment: distributor
-      reason: sample_rate_limits
-    record: cluster_namespace_deployment_reason:required_replicas:count
-  - expr: |
+      deployment: "distributor"
+      reason: "sample_rate_limits"
+    record: "cluster_namespace_deployment_reason:required_replicas:count"
+  - expr: "|
       ceil(
         quantile_over_time(0.99,
           sum by (cluster, namespace) (
@@ -346,12 +346,12 @@ groups:
           )[24h:]
         )
         * 3 / 80000
-      )
+      )"
     labels:
-      deployment: ingester
-      reason: sample_rate
-    record: cluster_namespace_deployment_reason:required_replicas:count
-  - expr: |
+      deployment: "ingester"
+      reason: "sample_rate"
+    record: "cluster_namespace_deployment_reason:required_replicas:count"
+  - expr: "|
       ceil(
         quantile_over_time(0.99,
           sum by(cluster, namespace) (
@@ -359,59 +359,59 @@ groups:
           )[24h:]
         )
         / 1500000
-      )
+      )"
     labels:
-      deployment: ingester
-      reason: active_series
-    record: cluster_namespace_deployment_reason:required_replicas:count
-  - expr: |
+      deployment: "ingester"
+      reason: "active_series"
+    record: "cluster_namespace_deployment_reason:required_replicas:count"
+  - expr: "|
       ceil(
-        sum by (cluster, namespace) (cortex_limits_overrides{limit_name="max_global_series_per_user"})
+        sum by (cluster, namespace) (cortex_limits_overrides{limit_name=\"max_global_series_per_user\"})
         * 3 * 0.59999999999999998 / 1500000
-      )
+      )"
     labels:
-      deployment: ingester
-      reason: active_series_limits
-    record: cluster_namespace_deployment_reason:required_replicas:count
-  - expr: |
+      deployment: "ingester"
+      reason: "active_series_limits"
+    record: "cluster_namespace_deployment_reason:required_replicas:count"
+  - expr: "|
       ceil(
-        sum by (cluster, namespace) (cortex_limits_overrides{limit_name="ingestion_rate"})
+        sum by (cluster, namespace) (cortex_limits_overrides{limit_name=\"ingestion_rate\"})
         * 0.59999999999999998 / 80000
-      )
+      )"
     labels:
-      deployment: ingester
-      reason: sample_rate_limits
-    record: cluster_namespace_deployment_reason:required_replicas:count
-  - expr: |
+      deployment: "ingester"
+      reason: "sample_rate_limits"
+    record: "cluster_namespace_deployment_reason:required_replicas:count"
+  - expr: "|
       ceil(
         (sum by (cluster, namespace) (
-          cortex_ingester_tsdb_storage_blocks_bytes{job=~".+/ingester.*"}
+          cortex_ingester_tsdb_storage_blocks_bytes{job=~\".+/ingester.*\"}
         ) / 4)
           /
         avg by (cluster, namespace) (
-          memcached_limit_bytes{job=~".+/memcached"}
+          memcached_limit_bytes{job=~\".+/memcached\"}
         )
-      )
+      )"
     labels:
-      deployment: memcached
-      reason: active_series
-    record: cluster_namespace_deployment_reason:required_replicas:count
-  - expr: |
+      deployment: "memcached"
+      reason: "active_series"
+    record: "cluster_namespace_deployment_reason:required_replicas:count"
+  - expr: "|
       sum by (cluster, namespace, deployment) (
         label_replace(
           label_replace(
             sum by (cluster, namespace, pod)(rate(container_cpu_usage_seconds_total[1m])),
-            "deployment", "$1", "pod", "(.*)-(?:([0-9]+)|([a-z0-9]+)-([a-z0-9]+))"
+            \"deployment\", \"$1\", \"pod\", \"(.*)-(?:([0-9]+)|([a-z0-9]+)-([a-z0-9]+))\"
           ),
-          # The question mark in "(.*?)" is used to make it non-greedy, otherwise it
+          # The question mark in \"(.*?)\" is used to make it non-greedy, otherwise it
           # always matches everything and the (optional) zone is not removed.
-          "deployment", "$1", "deployment", "(.*?)(?:-zone-[a-z])?"
+          \"deployment\", \"$1\", \"deployment\", \"(.*?)(?:-zone-[a-z])?\"
         )
-      )
-    record: cluster_namespace_deployment:container_cpu_usage_seconds_total:sum_rate
-  - expr: |
+      )"
+    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.
+      # Multi-zone deployments are grouped together removing the \"zone-X\" suffix.
       # This recording rule is made compatible with the breaking changes introduced in kube-state-metrics v2
       # that remove resource metrics, ref:
       # - https://github.com/kubernetes/kube-state-metrics/blob/master/CHANGELOG.md#v200-alpha--2020-09-16
@@ -424,11 +424,11 @@ groups:
           label_replace(
             label_replace(
               kube_pod_container_resource_requests_cpu_cores,
-              "deployment", "$1", "pod", "(.*)-(?:([0-9]+)|([a-z0-9]+)-([a-z0-9]+))"
+              \"deployment\", \"$1\", \"pod\", \"(.*)-(?:([0-9]+)|([a-z0-9]+)-([a-z0-9]+))\"
             ),
-            # The question mark in "(.*?)" is used to make it non-greedy, otherwise it
+            # The question mark in \"(.*?)\" is used to make it non-greedy, otherwise it
             # always matches everything and the (optional) zone is not removed.
-            "deployment", "$1", "deployment", "(.*?)(?:-zone-[a-z])?"
+            \"deployment\", \"$1\", \"deployment\", \"(.*?)(?:-zone-[a-z])?\"
           )
         )
       )
@@ -439,17 +439,17 @@ groups:
         sum by (cluster, namespace, deployment) (
           label_replace(
             label_replace(
-              kube_pod_container_resource_requests{resource="cpu"},
-              "deployment", "$1", "pod", "(.*)-(?:([0-9]+)|([a-z0-9]+)-([a-z0-9]+))"
+              kube_pod_container_resource_requests{resource=\"cpu\"},
+              \"deployment\", \"$1\", \"pod\", \"(.*)-(?:([0-9]+)|([a-z0-9]+)-([a-z0-9]+))\"
             ),
-            # The question mark in "(.*?)" is used to make it non-greedy, otherwise it
+            # The question mark in \"(.*?)\" is used to make it non-greedy, otherwise it
             # always matches everything and the (optional) zone is not removed.
-            "deployment", "$1", "deployment", "(.*?)(?:-zone-[a-z])?"
+            \"deployment\", \"$1\", \"deployment\", \"(.*?)(?:-zone-[a-z])?\"
           )
         )
-      )
-    record: cluster_namespace_deployment:kube_pod_container_resource_requests_cpu_cores:sum
-  - expr: |
+      )"
+    record: "cluster_namespace_deployment:kube_pod_container_resource_requests_cpu_cores:sum"
+  - expr: "|
       # Jobs should be sized to their CPU usage.
       # We do this by comparing 99th percentile usage over the last 24hrs to
       # their current provisioned #replicas and resource requests.
@@ -459,28 +459,28 @@ groups:
         quantile_over_time(0.99, cluster_namespace_deployment:container_cpu_usage_seconds_total:sum_rate[24h])
           /
         cluster_namespace_deployment:kube_pod_container_resource_requests_cpu_cores:sum
-      )
+      )"
     labels:
-      reason: cpu_usage
-    record: cluster_namespace_deployment_reason:required_replicas:count
-  - expr: |
+      reason: "cpu_usage"
+    record: "cluster_namespace_deployment_reason:required_replicas:count"
+  - expr: "|
       # Convenience rule to get the Memory utilization for both a deployment and a statefulset.
-      # Multi-zone deployments are grouped together removing the "zone-X" suffix.
+      # Multi-zone deployments are grouped together removing the \"zone-X\" suffix.
       sum by (cluster, namespace, deployment) (
         label_replace(
           label_replace(
-            container_memory_usage_bytes{image!=""},
-            "deployment", "$1", "pod", "(.*)-(?:([0-9]+)|([a-z0-9]+)-([a-z0-9]+))"
+            container_memory_usage_bytes{image!=\"\"},
+            \"deployment\", \"$1\", \"pod\", \"(.*)-(?:([0-9]+)|([a-z0-9]+)-([a-z0-9]+))\"
           ),
-          # The question mark in "(.*?)" is used to make it non-greedy, otherwise it
+          # The question mark in \"(.*?)\" is used to make it non-greedy, otherwise it
           # always matches everything and the (optional) zone is not removed.
-          "deployment", "$1", "deployment", "(.*?)(?:-zone-[a-z])?"
+          \"deployment\", \"$1\", \"deployment\", \"(.*?)(?:-zone-[a-z])?\"
         )
-      )
-    record: cluster_namespace_deployment:container_memory_usage_bytes:sum
-  - expr: |
+      )"
+    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.
+      # Multi-zone deployments are grouped together removing the \"zone-X\" suffix.
       # This recording rule is made compatible with the breaking changes introduced in kube-state-metrics v2
       # that remove resource metrics, ref:
       # - https://github.com/kubernetes/kube-state-metrics/blob/master/CHANGELOG.md#v200-alpha--2020-09-16
@@ -493,11 +493,11 @@ groups:
           label_replace(
             label_replace(
               kube_pod_container_resource_requests_memory_bytes,
-              "deployment", "$1", "pod", "(.*)-(?:([0-9]+)|([a-z0-9]+)-([a-z0-9]+))"
+              \"deployment\", \"$1\", \"pod\", \"(.*)-(?:([0-9]+)|([a-z0-9]+)-([a-z0-9]+))\"
             ),
-            # The question mark in "(.*?)" is used to make it non-greedy, otherwise it
+            # The question mark in \"(.*?)\" is used to make it non-greedy, otherwise it
             # always matches everything and the (optional) zone is not removed.
-            "deployment", "$1", "deployment", "(.*?)(?:-zone-[a-z])?"
+            \"deployment\", \"$1\", \"deployment\", \"(.*?)(?:-zone-[a-z])?\"
           )
         )
       )
@@ -508,17 +508,17 @@ groups:
         sum by (cluster, namespace, deployment) (
           label_replace(
             label_replace(
-              kube_pod_container_resource_requests{resource="memory"},
-              "deployment", "$1", "pod", "(.*)-(?:([0-9]+)|([a-z0-9]+)-([a-z0-9]+))"
+              kube_pod_container_resource_requests{resource=\"memory\"},
+              \"deployment\", \"$1\", \"pod\", \"(.*)-(?:([0-9]+)|([a-z0-9]+)-([a-z0-9]+))\"
             ),
-            # The question mark in "(.*?)" is used to make it non-greedy, otherwise it
+            # The question mark in \"(.*?)\" is used to make it non-greedy, otherwise it
             # always matches everything and the (optional) zone is not removed.
-            "deployment", "$1", "deployment", "(.*?)(?:-zone-[a-z])?"
+            \"deployment\", \"$1\", \"deployment\", \"(.*?)(?:-zone-[a-z])?\"
           )
         )
-      )
-    record: cluster_namespace_deployment:kube_pod_container_resource_requests_memory_bytes:sum
-  - expr: |
+      )"
+    record: "cluster_namespace_deployment:kube_pod_container_resource_requests_memory_bytes:sum"
+  - expr: "|
       # Jobs should be sized to their Memory usage.
       # We do this by comparing 99th percentile usage over the last 24hrs to
       # their current provisioned #replicas and resource requests.
@@ -528,44 +528,44 @@ groups:
         quantile_over_time(0.99, cluster_namespace_deployment:container_memory_usage_bytes:sum[24h])
           /
         cluster_namespace_deployment:kube_pod_container_resource_requests_memory_bytes:sum
-      )
+      )"
     labels:
-      reason: memory_usage
-    record: cluster_namespace_deployment_reason:required_replicas:count
-- name: mimir_alertmanager_rules
+      reason: "memory_usage"
+    record: "cluster_namespace_deployment_reason:required_replicas:count"
+- name: "mimir_alertmanager_rules"
   rules:
-  - expr: |
-      sum by (cluster, job, pod) (cortex_alertmanager_alerts)
-    record: cluster_job_pod:cortex_alertmanager_alerts:sum
-  - expr: |
-      sum by (cluster, job, pod) (cortex_alertmanager_silences)
-    record: cluster_job_pod:cortex_alertmanager_silences:sum
-  - expr: |
-      sum by (cluster, job) (rate(cortex_alertmanager_alerts_received_total[5m]))
-    record: cluster_job:cortex_alertmanager_alerts_received_total:rate5m
-  - expr: |
-      sum by (cluster, job) (rate(cortex_alertmanager_alerts_invalid_total[5m]))
-    record: cluster_job:cortex_alertmanager_alerts_invalid_total:rate5m
-  - expr: |
-      sum by (cluster, job, integration) (rate(cortex_alertmanager_notifications_total[5m]))
-    record: cluster_job_integration:cortex_alertmanager_notifications_total:rate5m
-  - expr: |
-      sum by (cluster, job, integration) (rate(cortex_alertmanager_notifications_failed_total[5m]))
-    record: cluster_job_integration:cortex_alertmanager_notifications_failed_total:rate5m
-  - expr: |
-      sum by (cluster, job) (rate(cortex_alertmanager_state_replication_total[5m]))
-    record: cluster_job:cortex_alertmanager_state_replication_total:rate5m
-  - expr: |
-      sum by (cluster, job) (rate(cortex_alertmanager_state_replication_failed_total[5m]))
-    record: cluster_job:cortex_alertmanager_state_replication_failed_total:rate5m
-  - expr: |
-      sum by (cluster, job) (rate(cortex_alertmanager_partial_state_merges_total[5m]))
-    record: cluster_job:cortex_alertmanager_partial_state_merges_total:rate5m
-  - expr: |
-      sum by (cluster, job) (rate(cortex_alertmanager_partial_state_merges_failed_total[5m]))
-    record: cluster_job:cortex_alertmanager_partial_state_merges_failed_total:rate5m
-- name: mimir_ingester_rules
+  - expr: "|
+      sum by (cluster, job, pod) (cortex_alertmanager_alerts)"
+    record: "cluster_job_pod:cortex_alertmanager_alerts:sum"
+  - expr: "|
+      sum by (cluster, job, pod) (cortex_alertmanager_silences)"
+    record: "cluster_job_pod:cortex_alertmanager_silences:sum"
+  - expr: "|
+      sum by (cluster, job) (rate(cortex_alertmanager_alerts_received_total[5m]))"
+    record: "cluster_job:cortex_alertmanager_alerts_received_total:rate5m"
+  - expr: "|
+      sum by (cluster, job) (rate(cortex_alertmanager_alerts_invalid_total[5m]))"
+    record: "cluster_job:cortex_alertmanager_alerts_invalid_total:rate5m"
+  - expr: "|
+      sum by (cluster, job, integration) (rate(cortex_alertmanager_notifications_total[5m]))"
+    record: "cluster_job_integration:cortex_alertmanager_notifications_total:rate5m"
+  - expr: "|
+      sum by (cluster, job, integration) (rate(cortex_alertmanager_notifications_failed_total[5m]))"
+    record: "cluster_job_integration:cortex_alertmanager_notifications_failed_total:rate5m"
+  - expr: "|
+      sum by (cluster, job) (rate(cortex_alertmanager_state_replication_total[5m]))"
+    record: "cluster_job:cortex_alertmanager_state_replication_total:rate5m"
+  - expr: "|
+      sum by (cluster, job) (rate(cortex_alertmanager_state_replication_failed_total[5m]))"
+    record: "cluster_job:cortex_alertmanager_state_replication_failed_total:rate5m"
+  - expr: "|
+      sum by (cluster, job) (rate(cortex_alertmanager_partial_state_merges_total[5m]))"
+    record: "cluster_job:cortex_alertmanager_partial_state_merges_total:rate5m"
+  - expr: "|
+      sum by (cluster, job) (rate(cortex_alertmanager_partial_state_merges_failed_total[5m]))"
+    record: "cluster_job:cortex_alertmanager_partial_state_merges_failed_total:rate5m"
+- name: "mimir_ingester_rules"
   rules:
-  - expr: |
-      sum by(cluster, namespace, pod) (rate(cortex_ingester_ingested_samples_total[1m]))
-    record: cluster_namespace_pod:cortex_ingester_ingested_samples_total:rate1m
+  - expr: "|
+      sum by(cluster, namespace, pod) (rate(cortex_ingester_ingested_samples_total[1m]))"
+    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))
-    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))
-    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)
-    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)
-    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)
-    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)
-    record: cluster_namespace_job_route:tempo_request_duration_seconds_count:sum_rate
+  - expr: "histogram_quantile(0.99, sum(rate(tempo_request_duration_seconds_bucket[1m])) by (le, cluster, namespace, job, route))"
+    record: "cluster_namespace_job_route:tempo_request_duration_seconds:99quantile"
+  - expr: "histogram_quantile(0.50, sum(rate(tempo_request_duration_seconds_bucket[1m])) by (le, cluster, namespace, job, route))"
+    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)"
+    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)"
+    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)"
+    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)"
+    record: "cluster_namespace_job_route:tempo_request_duration_seconds_count:sum_rate"

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

@@ -14,6 +14,6 @@ data:
     {{ $.Files.Get "src/dashboards/agent-remote-write.json" | fromJson | toJson }}
   "agent-tracing-pipeline.json": |
     {{ $.Files.Get "src/dashboards/agent-tracing-pipeline.json" | fromJson | toJson }}
-  "agent.json": |
+  "agent-overview.json": |
     {{ $.Files.Get "src/dashboards/agent.json" | fromJson | toJson }}
 {{- end }}

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

@@ -3,7 +3,7 @@ apiVersion: apps/v1
 kind: Deployment
 metadata:
   name: meta-mimir-ruler-for-dashboards
-  namespace: meta
+  namespace: {{ $.Release.Namespace }}
 spec:
   progressDeadlineSeconds: 600
   replicas: 1
@@ -24,7 +24,7 @@ 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:

charts/meta-monitoring/values.yaml

@@ -9,28 +9,28 @@ clusterName: "meta-monitoring"
 # Set to true for a local version of logs, metrics or traces
 local:
   logs:
-    enabled: false
+    enabled: true
   metrics:
-    enabled: false
+    enabled: true
   traces:
-    enabled: false
+    enabled: true
   minio:
-    enabled: false  # This should be set to true if any of the previous is enabled
+    enabled: true  # 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
 cloud:
   logs:
-    enabled: true
+    enabled: false
     endpoint:
     username:
     password:
   metrics:
-    enabled: true
+    enabled: false
     endpoint:
     username:
     password:
   traces:
-    enabled: true
+    enabled: false
     endpoint:
     username:
     password: