Remove unused ruler files

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

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

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

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

@@ -16,8 +16,8 @@ env:
     UPDATECLI_GITHUB_TOKEN: "${{ secrets.GITHUB_TOKEN }}"
 
 jobs:
-    updateLoki:
-        name: Update the Loki subchart
+    updateVersions:
+        name: Update the subcharts
         runs-on: "ubuntu-latest"
         steps:
             - name: Checkout
@@ -26,7 +26,7 @@ jobs:
             - name: Install Updatecli
               uses: updatecli/updatecli-action@v2
 
-            - name: Run Updatecli
+            - name: Run Updatecli for Loki
               id: update-loki
               run: |
                 updatecli apply --config ${UPDATECLI_CONFIG_DIR}/loki.yaml
@@ -34,31 +34,7 @@ jobs:
                   echo "changed=true" >> "${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
+            - name: Run Updatecli for Alloy
               id: update-grafana-alloy
               run: |
                 updatecli apply --config ${UPDATECLI_CONFIG_DIR}/alloy.yaml
@@ -66,31 +42,7 @@ jobs:
                   echo "changed=true" >> "${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
+            - name: Run Updatecli for Mimir
               id: update-mimir-distributed
               run: |
                 updatecli apply --config ${UPDATECLI_CONFIG_DIR}/mimir-distributed.yaml
@@ -98,31 +50,7 @@ jobs:
                   echo "changed=true" >> "${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
+            - name: Run Updatecli for Tempo
               id: update-tempo-distributed
               run: |
                 updatecli apply --config ${UPDATECLI_CONFIG_DIR}/tempo-distributed.yaml
@@ -130,31 +58,7 @@ jobs:
                   echo "changed=true" >> "${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
+            - name: Run Updatecli for Minio
               id: update-minio
               run: |
                 updatecli apply --config ${UPDATECLI_CONFIG_DIR}/minio.yaml
@@ -163,15 +67,47 @@ jobs:
                 fi
 
             - name: Create pull request
-              if: steps.update-minio.outputs.changed == 'true'
+              if: steps.update-loki.outputs.changed == 'true' || steps.update-grafana-alloy.outputs.changed == 'true' || steps.update-mimir-distributed.outputs.changed == 'true' || steps.update-tempo-distributed.outputs.changed == 'true' || steps.update-minio.outputs.changed == 'true'
               uses: peter-evans/create-pull-request@v5
               with:
-                title: "[dependency] Update the Minio subchart"
-                body: "Updates the Minio subchart"
+                title: "[dependency] Update the subcharts"
+                body: "Updates the subcharts"
                 base: main
                 author: "${{ github.actor }} <${{ github.actor }}@users.noreply.github.com>"
                 committer: "GitHub <noreply@github.com>"
-                commit-message: Update minio
+                commit-message: Update dependencies
+                labels: dependencies
+                branch: chore/update-dependencies
+                delete-branch: true
+
+    updateGrafana:
+        name: Update the Grafana version
+        runs-on: "ubuntu-latest"
+        steps:
+            - name: Checkout
+              uses: actions/checkout@v2
+
+            - name: Install Updatecli
+              uses: updatecli/updatecli-action@v2
+
+            - name: Run Updatecli
+              id: update-grafana
+              run: |
+                updatecli apply --config ${UPDATECLI_CONFIG_DIR}/grafana.yaml
+                if ! git diff --exit-code > /dev/null; then
+                  echo "changed=true" >> "${GITHUB_OUTPUT}"
+                fi
+
+            - name: Create pull request
+              if: steps.update-grafana.outputs.changed == 'true'
+              uses: peter-evans/create-pull-request@v5
+              with:
+                title: "[dependency] Update the Grafana version"
+                body: "Updates the Grafana version"
+                base: main
+                author: "${{ github.actor }} <${{ github.actor }}@users.noreply.github.com>"
+                committer: "GitHub <noreply@github.com>"
+                commit-message: Update Grafana version
                 labels: dependencies
                 branch: chore/update-minio
                 delete-branch: true

charts/meta-monitoring/Chart.lock

@@ -1,7 +1,7 @@
 dependencies:
 - name: loki
   repository: https://grafana.github.io/helm-charts
-  version: 6.4.2
+  version: 6.5.0
 - name: alloy
   repository: https://grafana.github.io/helm-charts
   version: 0.1.1
@@ -10,9 +10,9 @@ dependencies:
   version: 5.3.0
 - name: tempo-distributed
   repository: https://grafana.github.io/helm-charts
-  version: 1.9.5
+  version: 1.9.9
 - name: minio
   repository: https://charts.min.io
   version: 5.2.0
-digest: sha256:1b5cc2c89ce11b6f0f1c02d7459ac9202577ac4e56bae9cc7e54e253a27df265
-generated: "2024-05-03T07:02:27.762464734Z"
+digest: sha256:5328702b5f6b0487aba8f7bc77d6abfcd5e094569e9205cd725971e3e31255dd
+generated: "2024-05-08T07:03:21.797461955Z"

charts/meta-monitoring/Chart.yaml

@@ -22,7 +22,7 @@ appVersion: "0.0.1"
 dependencies:
 - name: loki
   repository: https://grafana.github.io/helm-charts
-  version: 6.4.2
+  version: 6.5.0
   condition: local.logs.enabled
 - name: alloy
   repository: https://grafana.github.io/helm-charts
@@ -33,7 +33,7 @@ dependencies:
   condition: local.metrics.enabled
 - name: tempo-distributed
   repository: https://grafana.github.io/helm-charts
-  version: 1.9.5
+  version: 1.9.9
   condition: local.traces.enabled
 - name: minio
   repository: https://charts.min.io

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

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

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

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

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

@@ -48,7 +48,7 @@
 {{- define "agent.tempo_write_targets" -}}
 {{- $list := list }}
 {{- if .Values.local.traces.enabled }}
-{{- $list = append $list ("otelcol.exporter.otlp.local.input") }}
+{{- $list = append $list ("otelcol.exporter.otlphttp.local.input") }}
 {{- end }}
 {{- if .Values.cloud.traces.enabled }}
 {{- $list = append $list ("otelcol.exporter.otlphttp.cloud.input") }}

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

@@ -294,9 +294,7 @@ data:
       // We don't technically need this, but it shows how to change listen address and incoming port.
       // In this case, the Agent is listening on all available bindable addresses on port 4317 (which is the
       // default OTLP gRPC port) for the OTLP protocol.
-      grpc {
-        endpoint = "0.0.0.0:4317"
-      }
+      grpc {}
 
       // We define where to send the output of all ingested traces. In this case, to the OpenTelemetry batch processor
       // named 'default'.
@@ -345,6 +343,14 @@ data:
     }
     {{- end }}
 
+    {{- if .Values.local.traces.enabled }}
+    otelcol.exporter.otlphttp "local" {
+        client {
+            endpoint = "http://{{- .Release.Name -}}-tempo-distributor.svc:4318"
+        }
+    }
+    {{- end }}
+
     {{- if .Values.cloud.logs.enabled }}
     loki.write "cloud" {
       endpoint {

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

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

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

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

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

@@ -1,16 +1,4 @@
 {{- if .Values.local.grafana.enabled }}
----
-apiVersion: v1
-kind: PersistentVolumeClaim
-metadata:
-  name: grafana-pvc
-spec:
-  accessModes:
-    - ReadWriteOnce
-  resources:
-    requests:
-      storage: 1Gi
----
 apiVersion: apps/v1
 kind: Deployment
 metadata:
@@ -32,7 +20,7 @@ spec:
           - 0
       containers:
         - name: grafana
-          image: grafana/grafana:10.0.0
+          image: grafana/grafana:{{- .Values.grafana.version }}
           imagePullPolicy: IfNotPresent
           ports:
             - containerPort: 3000
@@ -65,7 +53,7 @@ spec:
               name: grafana-pv
             - mountPath: /etc/grafana/provisioning/datasources
               name: datasources-provisioning
-            {{- if or (or .Values.dashboards.logs.enabled .Values.dashboards.metrics.enabled) .Values.dashboards.traces.enabled }}
+            {{- if .Values.dashboards.logs.enabled }}
             - mountPath: /etc/grafana/provisioning/dashboards
               name: dashboards-provisioning
             {{- end }}
@@ -98,19 +86,4 @@ spec:
         - name: agent-dashboards-1
           configMap:
             name: agent-dashboards-1
-
----
-apiVersion: v1
-kind: Service
-metadata:
-  name: grafana
-spec:
-  ports:
-    - port: 3000
-      protocol: TCP
-      targetPort: http-grafana
-  selector:
-    app: grafana
-  sessionAffinity: None
-  type: ClusterIP  # Make this configurable
 {{- end }}

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

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

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

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

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

@@ -1,5 +1,5 @@
 {{- if .Values.local.grafana.enabled }}
-{{- if and .Values.local.grafana.enabled (or .Values.dashboards.logs.enabled .Values.dashboards.metrics.enabled .Values.dashboards.traces.enabled) }}
+{{- if and .Values.local.grafana.enabled .Values.dashboards.logs.enabled }}
 apiVersion: apps/v1
 kind: Deployment
 metadata:
@@ -51,7 +51,7 @@ spec:
               protocol: TCP
           envFrom:
           - secretRef:
-             name: mmc-minio
+             name: minio
           readinessProbe:
             failureThreshold: 3
             httpGet:

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

@@ -1,5 +1,5 @@
 {{- if .Values.local.metrics.enabled }}
-{{- if and .Values.local.grafana.enabled (or .Values.dashboards.logs.enabled .Values.dashboards.metrics.enabled .Values.dashboards.traces.enabled) }}
+{{- if and .Values.local.grafana.enabled .Values.dashboards.logs.enabled }}
 ---
 apiVersion: v1
 kind: ConfigMap
@@ -10,11 +10,5 @@ data:
 {{- if .Values.dashboards.logs.enabled }}
 {{ ($.Files.Glob "src/rules/loki-rules.yaml").AsConfig | indent 2 }}
 {{- end }}
-{{- if .Values.dashboards.metrics.enabled }}
-{{ ($.Files.Glob "src/rules/mimir-rules.yaml").AsConfig | indent 2 }}
-{{- end }}
-{{- if .Values.dashboards.traces.enabled }}
-{{ ($.Files.Glob "src/rules/tempo-rules.yaml").AsConfig | indent 2 }}
-{{- end }}
 {{- end }}
 {{- end }}

charts/meta-monitoring/values.yaml

@@ -3,7 +3,6 @@ namespacesToMonitor:
 - loki
 # The name of the cluster where this will be installed
 clusterLabelValue: "meta-monitoring"
-
 # Set to true to write logs, metrics or traces to Grafana Cloud
 # The secrets have to be created first
 cloud:
@@ -16,7 +15,6 @@ cloud:
   traces:
     enabled: true
     secret: "traces"
-
 # Set to true for a local version of logs, metrics or traces
 local:
   grafana:
@@ -28,9 +26,9 @@ local:
   traces:
     enabled: false
   minio:
-    enabled: false  # This should be set to true if any of the previous is enabled
-
+    enabled: false # This should be set to true if any of the previous is enabled
 grafana:
+  version: 10.4.2
   # Gateway ingress configuration
   ingress:
     # -- Specifies whether an ingress for the gateway should be created
@@ -38,9 +36,9 @@ grafana:
     # -- Ingress Class Name. MAY be required for Kubernetes versions >= 1.18
     ingressClassName: ""
     # -- Annotations for the gateway ingress
-    annotations: { }
+    annotations: {}
     # -- Labels for the gateway ingress
-    labels: { }
+    labels: {}
     # -- Hosts configuration for the gateway ingress, passed through the `tpl` function to allow templating
     hosts:
       - host: monitoring.example.com
@@ -53,18 +51,14 @@ grafana:
     #  - secretName: grafana-tls
     #    hosts:
     #      - monitoring.example.com
-
-
 logs:
   # Adding regexes here will add a stage.replace block for logs. For more information see
   # https://grafana.com/docs/agent/latest/flow/reference/components/loki.process/#stagereplace-block
-  piiRegexes:
-  # 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
+  piiRegexes: null # This example replaces the word after password with *****
+# - expression: "password (\\\\S+)"
+#   source: ""         # Empty uses the log message
+#   replace: "*****""
+# The lines matching these will be kept in Loki
   retain:
   # This shows the queries
   - caller=metrics.go
@@ -78,7 +72,6 @@ logs:
   # - caller=push.go
   # Additional log lines to retain
   extraLogs: []
-
 metrics:
   # The list of metrics to retain for logging dashboards
   retain:
@@ -179,21 +172,10 @@ metrics:
   - promtail_custom_bad_words_total
   # Additional metrics to retain
   extraMetrics: []
-
-# Set enabled = true to add the default logs/metrics/traces dashboards to the local Grafana
+# Set enabled = true to add the default logs dashboards to the local Grafana
 dashboards:
   logs:
     enabled: true
-  metrics:
-    enabled: true
-  traces:
-    enabled: true
-
-global:
-  minio:
-    rootUser: "rootuser"
-    rootPassword: "rootpassword"
-
 kubeStateMetrics:
   # Scrape https://github.com/kubernetes/kube-state-metrics by default
   enabled: true
@@ -201,10 +183,8 @@ kubeStateMetrics:
   # https://artifacthub.io/packages/helm/prometheus-community/kube-state-metrics/
   # is used. Change this if kube-state-metrics is installed somewhere else.
   endpoint: kube-state-metrics.kube-state-metrics.svc.cluster.local:8080
-
 # The following are configuration for the dependencies.
 # These should usually not be changed.
-
 loki:
   loki:
     auth_enabled: false
@@ -259,20 +239,19 @@ loki:
     - "-config.expand-env=true"
     extraEnvFrom:
     - secretRef:
-        name: "mmc-minio"
+        name: "minio"
   read:
     extraArgs:
     - "-config.expand-env=true"
     extraEnvFrom:
     - secretRef:
-        name: "mmc-minio"
+        name: "minio"
   backend:
     extraArgs:
     - "-config.expand-env=true"
     extraEnvFrom:
     - secretRef:
-        name: "mmc-minio"
-
+        name: "minio"
 alloy:
   alloy:
     clustering:
@@ -304,14 +283,13 @@ alloy:
       maxReplicas: 30
       targetMemoryUtilizationPercentage: 90
       targetCPUUtilizationPercentage: 90
-
 mimir-distributed:
   minio:
     enabled: false
   global:
     extraEnvFrom:
     - secretRef:
-        name: "mmc-minio"
+        name: "minio"
   mimir:
     structuredConfig:
       alertmanager_storage:
@@ -335,7 +313,6 @@ mimir-distributed:
             insecure: true
       limits:
         compactor_blocks_retention_period: 30d
-
 tempo-distributed:
   tempo:
     structuredConfig:
@@ -353,38 +330,37 @@ tempo-distributed:
     - "-config.expand-env=true"
     extraEnvFrom:
     - secretRef:
-        name: "mmc-minio"
+        name: "minio"
   ingester:
     extraArgs:
     - "-config.expand-env=true"
     extraEnvFrom:
     - secretRef:
-        name: "mmc-minio"
+        name: "minio"
   compactor:
     extraArgs:
     - "-config.expand-env=true"
     extraEnvFrom:
     - secretRef:
-        name: "mmc-minio"
+        name: "minio"
   querier:
     extraArgs:
     - "-config.expand-env=true"
     extraEnvFrom:
     - secretRef:
-        name: "mmc-minio"
+        name: "minio"
   queryFrontend:
     extraArgs:
     - "-config.expand-env=true"
     extraEnvFrom:
     - secretRef:
-        name: "mmc-minio"
+        name: "minio"
   traces:
     otlp:
       http:
         enabled: true
       grpc:
         enabled: true
-
 minio:
   existingSecret: "minio"
   buckets:

docs/installation.md

@@ -67,7 +67,7 @@
    kubectl create namespace meta
    ```
 
-1. Create a secret with the user and password for the local Minio:
+1. Create a secret named `minio` with the user and password for the local Minio:
 
    ```
    kubectl create secret generic minio -n meta \