Merge pull request #186 from grafana/chore/update-dependencies

[dependency] Update the subcharts

.github/configs/cluster-config.yaml

@@ -0,0 +1,19 @@
+apiVersion: kind.x-k8s.io/v1alpha4
+kind: Cluster
+nodes:
+  - role: control-plane
+    kubeadmConfigPatches:
+      - |
+        kind: ClusterConfiguration
+        controllerManager:
+          extraArgs:
+            bind-address: 0.0.0.0
+            secure-port: "10257"
+        scheduler:
+          extraArgs:
+            bind-address: 0.0.0.0
+            secure-port: "10259"
+      - |
+        kind: KubeProxyConfiguration
+        metricsBindAddress: 0.0.0.0:10249
+  - role: worker

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

@@ -19,6 +19,9 @@ jobs:
     updateVersions:
         name: Update the subcharts
         runs-on: "ubuntu-latest"
+        permissions:
+          contents: write
+          id-token: write
         steps:
             - name: Checkout
               uses: actions/checkout@v2
@@ -66,6 +69,20 @@ jobs:
                   echo "changed=true" >> "${GITHUB_OUTPUT}"
                 fi
 
+            - id: get-secrets
+              uses: grafana/shared-workflows/actions/get-vault-secrets@main
+              with:
+                # Secrets placed in the ci/repo/grafana/<repo>/<path> path in Vault
+                repo_secrets: |
+                  APP_ID=github-app:app-id
+                  PRIVATE_KEY=github-app:private-key
+
+            - uses: actions/create-github-app-token@v1
+              id: app-token
+              with:
+                app-id: ${{ env.APP_ID }}
+                private-key: ${{ env.PRIVATE_KEY }}
+
             - name: Create pull request
               if: steps.update-loki.outputs.changed == 'true' || steps.update-grafana-alloy.outputs.changed == 'true' || steps.update-mimir-distributed.outputs.changed == 'true' || steps.update-tempo-distributed.outputs.changed == 'true' || steps.update-minio.outputs.changed == 'true'
               uses: peter-evans/create-pull-request@v5
@@ -79,10 +96,15 @@ jobs:
                 labels: dependencies
                 branch: chore/update-dependencies
                 delete-branch: true
+                team-reviewers: "@grafana/loki-squad"
+                token: ${{ steps.app-token.outputs.token }}
 
     updateGrafana:
         name: Update the Grafana version
         runs-on: "ubuntu-latest"
+        permissions:
+          contents: write
+          id-token: write
         steps:
             - name: Checkout
               uses: actions/checkout@v2
@@ -98,6 +120,20 @@ jobs:
                   echo "changed=true" >> "${GITHUB_OUTPUT}"
                 fi
 
+            - id: get-secrets
+              uses: grafana/shared-workflows/actions/get-vault-secrets@main
+              with:
+                # Secrets placed in the ci/repo/grafana/<repo>/<path> path in Vault
+                repo_secrets: |
+                  APP_ID=github-app:app-id
+                  PRIVATE_KEY=github-app:private-key
+
+            - uses: actions/create-github-app-token@v1
+              id: app-token
+              with:
+                app-id: ${{ env.APP_ID }}
+                private-key: ${{ env.PRIVATE_KEY }}
+
             - name: Create pull request
               if: steps.update-grafana.outputs.changed == 'true'
               uses: peter-evans/create-pull-request@v5
@@ -111,3 +147,5 @@ jobs:
                 labels: dependencies
                 branch: chore/update-minio
                 delete-branch: true
+                team-reviewers: "@grafana/loki-squad"
+                token: ${{ steps.app-token.outputs.token }}

.github/workflows/helm-ci.yml

@@ -1,6 +1,7 @@
 ---
 name: helm-ci
 on:
+  workflow_dispatch:
   pull_request:
     paths:
       - "charts/meta-monitoring/**"
@@ -24,7 +25,7 @@ jobs:
   #   runs-on: ubuntu-latest
   #   steps:
   #     - name: Checkout
-  #       uses: actions/checkout@v3
+  #       uses: actions/checkout@v4
   #       with:
   #         fetch-depth: 0
 
@@ -38,10 +39,10 @@ jobs:
   #     - name: Set up Python
   #       uses: actions/setup-python@v4
   #       with:
-  #         python-version: 3.7
+  #         python-version: 3.9
 
   #     - name: Set up chart-testing
-  #       uses: helm/chart-testing-action@v2.4.0
+  #       uses: helm/chart-testing-action@v2
 
   #     - name: Run chart-testing (list-changed)
   #       id: list-changed
@@ -55,10 +56,10 @@ jobs:
   #       run: ct lint --config "${CT_CONFIGFILE}" --check-version-increment=false
 
   #     - name: Create kind cluster
-  #       uses: helm/kind-action@v1.8.0
+  #       uses: helm/kind-action@v1
   #       if: steps.list-changed.outputs.changed == 'true'
   #       with:
-  #         config: tools/kind.config
+  #         config: "${{ github.workspace }}/.github/configs/cluster-config.yaml"
 
   #     - name: Run chart-testing (install)
   #       run: |

README.md

@@ -1,8 +1,6 @@
 # meta-monitoring-chart
 
-This is a meta-monitoring chart for Loki.
+This is a meta-monitoring chart for Loki, specifically Loki installed via the Loki helm chart.
-
-Note that this is pre-production software at the moment.
 
 ## Local and cloud modes
 
@@ -11,19 +9,15 @@ to small Loki, Mimir and Tempo installations running in the meta-monitoring name
 
 ![local mode](docs/images/Meta%20monitoring%20local.png)
 
-To enable local mode set `local.<logs|metrics|traces>.enabled` to true.
-
 In the cloud mode the logs, metrics and/or traces are sent to Grafana Cloud.
 
 ![cloud mode](docs/images/Meta%20monitoring%20cloud.png)
 
-To enable cloud mode set `cloud.<logs|metrics|traces>.enabled` to true. The `endpoint`, `username` and `password` settings for your Grafana Cloud logs, metrics and traces instances have to be filled in as well.
-
 Both modes can be enabled at the same time. Cloud mode is preferred.
 
 ## Installation
 
-For more instructions including how to update the chart go to the [installation](docs/installation.md) page.
+For more instructions including how to install the chart go to the [installation](docs/installation.md) page.
 
 ## Supported features
 
@@ -33,8 +27,7 @@ For more instructions including how to update the chart go to the [installation]
 - Specify PII regexes that are applied to logs before they are sent to Loki (cloud or local). The capture group in the regex is replaced with *****.
 - a Grafana instance is installed (when local mode is used) with the relevant datasources installed. The following dashboards are installed:
   - logs dashboards
-  - agent dashboards
+  - Alloy dashboards
-- Retention is set to 24 hours
 
 Most of these features are enabled by default. See the values.yaml file for how to enable/disable them.
 
@@ -42,8 +35,7 @@ Most of these features are enabled by default. See the values.yaml file for how
 
 - This has not been tested on Openshift yet.
 - The underlying Loki, Mimir and Tempo are at the default size installed by the Helm chart. This might need changing when monitoring bigger Loki, Mimir or Tempo installations.
-- MinIO is used as storage at the moment with a limited retention. At the moment this chart cannot be used for monitoring over longer periods.
+- MinIO is used as storage for the local mode at the moment with a limited retention. At the moment this chart cannot be used for monitoring over longer periods.
-- Agent self monitoring is not done at the moment.
 
 ## Developer help topics
 

charts/meta-monitoring/Chart.lock

@@ -1,18 +1,18 @@
 dependencies:
 - name: loki
   repository: https://grafana.github.io/helm-charts
-  version: 6.5.0
+  version: 6.29.0
 - name: alloy
   repository: https://grafana.github.io/helm-charts
-  version: 0.1.1
+  version: 0.12.5
 - name: mimir-distributed
   repository: https://grafana.github.io/helm-charts
-  version: 5.3.0
+  version: 5.6.0
 - name: tempo-distributed
   repository: https://grafana.github.io/helm-charts
-  version: 1.9.9
+  version: 1.33.0
 - name: minio
   repository: https://charts.min.io
-  version: 5.2.0
+  version: 5.4.0
-digest: sha256:5328702b5f6b0487aba8f7bc77d6abfcd5e094569e9205cd725971e3e31255dd
+digest: sha256:5225a03d9003384639f5d43b1971126371269347f16f221b7aed377ab85d71be
-generated: "2024-05-08T07:03:21.797461955Z"
+generated: "2025-03-27T07:03:11.17404081Z"

charts/meta-monitoring/Chart.yaml

@@ -13,7 +13,7 @@ type: application
 # This is the chart version. This version number should be incremented each time you make changes
 # to the chart and its templates, including the app version.
 # Versions are expected to follow Semantic Versioning (https://semver.org/)
-version: 0.0.2
+version: 1.3.0
 # This is the version number of the application being deployed. This version number should be
 # incremented each time you make changes to the application. Versions are not expected to
 # follow Semantic Versioning. They should reflect the version the application is using.
@@ -22,20 +22,20 @@ appVersion: "0.0.1"
 dependencies:
 - name: loki
   repository: https://grafana.github.io/helm-charts
-  version: 6.5.0
+  version: 6.29.0
   condition: local.logs.enabled
 - name: alloy
   repository: https://grafana.github.io/helm-charts
-  version: 0.1.1
+  version: 0.12.5
 - name: mimir-distributed
   repository: https://grafana.github.io/helm-charts
-  version: 5.3.0
+  version: 5.6.0
   condition: local.metrics.enabled
 - name: tempo-distributed
   repository: https://grafana.github.io/helm-charts
-  version: 1.9.9
+  version: 1.33.0
   condition: local.traces.enabled
 - name: minio
   repository: https://charts.min.io
-  version: 5.2.0
+  version: 5.4.0
   condition: local.minio.enabled

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

@@ -1824,7 +1824,7 @@
                   "steppedLine": false,
                   "targets": [
                      {
-                        "expr": "sum by(pod) (rate(container_cpu_usage_seconds_total{cluster=~\"$cluster\", namespace=~\"$namespace\", pod=~\"(.*distributor.*|(loki|enterprise-logs)-write)\"}[$__rate_interval]))",
+                        "expr": "sum by(pod) (rate(container_cpu_usage_seconds_total{cluster=~\"$cluster\", namespace=~\"$namespace\", pod=~\"(.*distributor.*|(loki|enterprise-logs)-write.*|$namespace-[0-9]+)\"}[$__rate_interval]))",
                         "intervalFactor": 3,
                         "legendFormat": "{{pod}}",
                         "refId": "A"
@@ -1921,7 +1921,7 @@
                   "steppedLine": false,
                   "targets": [
                      {
-                        "expr": "go_memstats_heap_inuse_bytes{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"(.*/distributor|(loki|enterprise-logs)-write|.*/loki)\"}",
+                        "expr": "go_memstats_heap_inuse_bytes{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"(.*/.*distributor|$namespace/(loki|enterprise-logs)-write|.*/loki|$namespace/loki-single-binary)\"}",
                         "instant": false,
                         "intervalFactor": 3,
                         "legendFormat": "{{pod}}",
@@ -2525,7 +2525,7 @@
                   "steppedLine": false,
                   "targets": [
                      {
-                        "expr": "sum by(pod) (rate(container_cpu_usage_seconds_total{cluster=~\"$cluster\", namespace=~\"$namespace\", pod=~\"(.*ingester.*|(loki|enterprise-logs)-write|loki-single-binary)\"}[$__rate_interval]))",
+                        "expr": "sum by(pod) (rate(container_cpu_usage_seconds_total{cluster=~\"$cluster\", namespace=~\"$namespace\", pod=~\"(.*ingester.*|(loki|enterprise-logs)-write.*|loki-single-binary|$namespace-[0-9]+)\"}[$__rate_interval]))",
                         "intervalFactor": 3,
                         "legendFormat": "{{pod}}",
                         "refId": "A"
@@ -2622,7 +2622,7 @@
                   "steppedLine": false,
                   "targets": [
                      {
-                        "expr": "go_memstats_heap_inuse_bytes{cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"(.*ingester.*|(loki|enterprise-logs)-write|loki-single-binary)\"}",
+                        "expr": "go_memstats_heap_inuse_bytes{cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"(.*ingester.*|(loki|enterprise-logs)-write.*|loki-single-binary|$namespace-[0-9]+)\"}",
                         "instant": false,
                         "intervalFactor": 3,
                         "legendFormat": "{{pod}}",
@@ -3308,7 +3308,7 @@
                   "steppedLine": false,
                   "targets": [
                      {
-                        "expr": "sum by(reason) (rate(loki_ingester_chunks_flushed_total{cluster=~\"$cluster\",job=~\"$namespace/.*ingester.*\", namespace=~\"$namespace\"}[$__rate_interval])) / ignoring(reason) group_left sum(rate(loki_ingester_chunks_flushed_total{cluster=~\"$cluster\",job=~\"$namespace/.*ingester.*\", namespace=~\"$namespace\"}[$__rate_interval]))",
+                        "expr": "sum by(reason) (rate(loki_ingester_chunks_flushed_total{cluster=~\"$cluster\",job=~\"($namespace)/(.*ingester.*|(loki|enterprise-logs)-write|loki-single-binary)\", namespace=~\"$namespace\"}[$__rate_interval])) / ignoring(reason) group_left sum(rate(loki_ingester_chunks_flushed_total{cluster=~\"$cluster\",job=~\"($namespace)/(.*ingester.*|(loki|enterprise-logs)-write|loki-single-binary)\", namespace=~\"$namespace\"}[$__rate_interval]))",
                         "interval": "",
                         "legendFormat": "{{ reason }}"
                      }
@@ -3388,7 +3388,7 @@
                   "reverseYBuckets": false,
                   "targets": [
                      {
-                        "expr": "sum by (le) (rate(loki_ingester_chunk_utilization_bucket{cluster=\"$cluster\", job=~\"($namespace)/(ingester|(loki|enterprise-logs)-write|loki-single-binary)\"}[$__rate_interval]))",
+                        "expr": "sum by (le) (rate(loki_ingester_chunk_utilization_bucket{cluster=\"$cluster\", job=~\"($namespace)/(.*ingester|(loki|enterprise-logs)-write|loki-single-binary)\"}[$__rate_interval]))",
                         "format": "heatmap",
                         "instant": false,
                         "interval": "",
@@ -3481,7 +3481,7 @@
                   "steppedLine": false,
                   "targets": [
                      {
-                        "expr": "sum by(pod) (rate(container_cpu_usage_seconds_total{cluster=~\"$cluster\", namespace=~\"$namespace\", pod=~\"(.*querier.*|(loki|enterprise-logs)-read|loki-single-binary)\"}[$__rate_interval]))",
+                        "expr": "sum by(pod) (rate(container_cpu_usage_seconds_total{cluster=~\"$cluster\", namespace=~\"$namespace\", pod=~\"(.*querier.*|(loki|enterprise-logs)-read.*|loki-single-binary|$namespace-[0-9]+)\"}[$__rate_interval]))",
                         "intervalFactor": 3,
                         "legendFormat": "{{pod}}",
                         "refId": "A"
@@ -3578,7 +3578,7 @@
                   "steppedLine": false,
                   "targets": [
                      {
-                        "expr": "go_memstats_heap_inuse_bytes{cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"(.*querier.*|(loki|enterprise-logs)-read|.*loki-single-binary)\"}",
+                        "expr": "go_memstats_heap_inuse_bytes{cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"(.*querier.*|(loki|enterprise-logs)-read.*|.*loki-single-binary|$namespace-[0-9]+)\"}",
                         "instant": false,
                         "intervalFactor": 3,
                         "legendFormat": "{{pod}}",

charts/meta-monitoring/src/dashboards/loki-reads-resources.json

@@ -104,19 +104,19 @@
                   "span": 4,
                   "targets": [
                      {
-                        "expr": "sum by(pod) (rate(container_cpu_usage_seconds_total{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"query-frontend\"}[$__rate_interval]))",
+                        "expr": "sum by(pod) (rate(container_cpu_usage_seconds_total{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"query-frontend|loki\", pod=~\"query-frontend|loki-read-.*|$namespace-[0-9]*\"}[$__rate_interval]))",
                         "format": "time_series",
                         "legendFormat": "{{pod}}",
                         "legendLink": null
                      },
                      {
-                        "expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"query-frontend\", resource=\"cpu\"} > 0)",
+                        "expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"query-frontend|loki\", pod=~\"query-frontend|loki-read-.*|$namespace-[0-9]*\", resource=\"cpu\"} > 0)",
                         "format": "time_series",
                         "legendFormat": "request",
                         "legendLink": null
                      },
                      {
-                        "expr": "min(container_spec_cpu_quota{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"query-frontend\"} / container_spec_cpu_period{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"query-frontend\"})",
+                        "expr": "min(container_spec_cpu_quota{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"query-frontend|loki\", pod=~\"query-frontend|loki-read-.*|$namespace-[0-9]*\"} / container_spec_cpu_period{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"query-frontend|loki\", pod=~\"query-frontend|loki-read-.*|$namespace-[0-9]*\"})",
                         "format": "time_series",
                         "legendFormat": "limit",
                         "legendLink": null
@@ -206,19 +206,19 @@
                   "span": 4,
                   "targets": [
                      {
-                        "expr": "max by(pod) (container_memory_working_set_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"query-frontend\"})",
+                        "expr": "max by(pod) (container_memory_working_set_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"query-frontend|loki\", pod=~\"query-frontend|loki-read-.*|$namespace-[0-9]*\"})",
                         "format": "time_series",
                         "legendFormat": "{{pod}}",
                         "legendLink": null
                      },
                      {
-                        "expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"query-frontend\", resource=\"memory\"} > 0)",
+                        "expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"query-frontend|loki\", pod=~\"query-frontend|loki-read-.*|$namespace-[0-9]*\", resource=\"memory\"} > 0)",
                         "format": "time_series",
                         "legendFormat": "request",
                         "legendLink": null
                      },
                      {
-                        "expr": "min(container_spec_memory_limit_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"query-frontend\"} > 0)",
+                        "expr": "min(container_spec_memory_limit_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"query-frontend|loki\", pod=~\"query-frontend|loki-read-.*|$namespace-[0-9]*\"} > 0)",
                         "format": "time_series",
                         "legendFormat": "limit",
                         "legendLink": null
@@ -269,7 +269,7 @@
                   "span": 4,
                   "targets": [
                      {
-                        "expr": "sum by(pod) (go_memstats_heap_inuse_bytes{cluster=~\"$cluster\", job=~\"($namespace)/.*query-frontend\"})",
+                        "expr": "sum by(pod) (go_memstats_heap_inuse_bytes{cluster=~\"$cluster\", job=~\"($namespace)/(.*query-frontend|loki-read|loki-single-binary)\"})",
                         "format": "time_series",
                         "legendFormat": "{{pod}}",
                         "legendLink": null
@@ -371,19 +371,19 @@
                   "span": 4,
                   "targets": [
                      {
-                        "expr": "sum by(pod) (rate(container_cpu_usage_seconds_total{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"query-scheduler\"}[$__rate_interval]))",
+                        "expr": "sum by(pod) (rate(container_cpu_usage_seconds_total{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"query-scheduler|loki\", pod=~\"query-scheduler|loki-read-.*|$namespace-[0-9]*\"}[$__rate_interval]))",
                         "format": "time_series",
                         "legendFormat": "{{pod}}",
                         "legendLink": null
                      },
                      {
-                        "expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"query-scheduler\", resource=\"cpu\"} > 0)",
+                        "expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"query-scheduler|loki\", pod=~\"query-scheduler|loki-read-.*|$namespace-[0-9]*\", resource=\"cpu\"} > 0)",
                         "format": "time_series",
                         "legendFormat": "request",
                         "legendLink": null
                      },
                      {
-                        "expr": "min(container_spec_cpu_quota{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"query-scheduler\"} / container_spec_cpu_period{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"query-scheduler\"})",
+                        "expr": "min(container_spec_cpu_quota{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"query-scheduler|loki\", pod=~\"query-scheduler|loki-read-.*|$namespace-[0-9]*\"} / container_spec_cpu_period{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"query-scheduler|loki\", pod=~\"query-scheduler|loki-read-.*|$namespace-[0-9]*\"})",
                         "format": "time_series",
                         "legendFormat": "limit",
                         "legendLink": null
@@ -473,19 +473,19 @@
                   "span": 4,
                   "targets": [
                      {
-                        "expr": "max by(pod) (container_memory_working_set_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"query-scheduler\"})",
+                        "expr": "max by(pod) (container_memory_working_set_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"query-scheduler|loki\", pod=~\"query-scheduler|loki-read-.*|$namespace-[0-9]*\"})",
                         "format": "time_series",
                         "legendFormat": "{{pod}}",
                         "legendLink": null
                      },
                      {
-                        "expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"query-scheduler\", resource=\"memory\"} > 0)",
+                        "expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"query-scheduler|loki\", pod=~\"query-scheduler|loki-read-.*|$namespace-[0-9]*\", resource=\"memory\"} > 0)",
                         "format": "time_series",
                         "legendFormat": "request",
                         "legendLink": null
                      },
                      {
-                        "expr": "min(container_spec_memory_limit_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"query-scheduler\"} > 0)",
+                        "expr": "min(container_spec_memory_limit_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"query-scheduler|loki\", pod=~\"query-scheduler|loki-read-.*|$namespace-[0-9]*\"} > 0)",
                         "format": "time_series",
                         "legendFormat": "limit",
                         "legendLink": null
@@ -536,7 +536,7 @@
                   "span": 4,
                   "targets": [
                      {
-                        "expr": "sum by(pod) (go_memstats_heap_inuse_bytes{cluster=~\"$cluster\", job=~\"($namespace)/.*query-scheduler\"})",
+                        "expr": "sum by(pod) (go_memstats_heap_inuse_bytes{cluster=~\"$cluster\", job=~\"($namespace)/(.*query-scheduler|loki-read|loki-single-binary)\"})",
                         "format": "time_series",
                         "legendFormat": "{{pod}}",
                         "legendLink": null
@@ -638,19 +638,19 @@
                   },
                   "targets": [
                      {
-                        "expr": "sum by(pod) (rate(container_cpu_usage_seconds_total{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"querier\"}[$__rate_interval]))",
+                        "expr": "sum by(pod) (rate(container_cpu_usage_seconds_total{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"querier|loki\", pod=~\"query-frontend|loki-read-.*|$namespace-[0-9]*\"}[$__rate_interval]))",
                         "format": "time_series",
                         "legendFormat": "{{pod}}",
                         "legendLink": null
                      },
                      {
-                        "expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"querier\", resource=\"cpu\"} > 0)",
+                        "expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"querier|loki\", pod=~\"query-frontend|loki-read-.*|$namespace-[0-9]*\", resource=\"cpu\"} > 0)",
                         "format": "time_series",
                         "legendFormat": "request",
                         "legendLink": null
                      },
                      {
-                        "expr": "min(container_spec_cpu_quota{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"querier\"} / container_spec_cpu_period{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"querier\"})",
+                        "expr": "min(container_spec_cpu_quota{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"querier|loki\", pod=~\"query-frontend|loki-read-.*|$namespace-[0-9]*\"} / container_spec_cpu_period{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"querier|loki\", pod=~\"query-frontend|loki-read-.*|$namespace-[0-9]*\"})",
                         "format": "time_series",
                         "legendFormat": "limit",
                         "legendLink": null
@@ -740,19 +740,19 @@
                   },
                   "targets": [
                      {
-                        "expr": "max by(pod) (container_memory_working_set_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"querier\"})",
+                        "expr": "max by(pod) (container_memory_working_set_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"querier|loki\", pod=~\"query-frontend|loki-read-.*|$namespace-[0-9]*\"})",
                         "format": "time_series",
                         "legendFormat": "{{pod}}",
                         "legendLink": null
                      },
                      {
-                        "expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"querier\", resource=\"memory\"} > 0)",
+                        "expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"querier|loki\", pod=~\"query-frontend|loki-read-.*|$namespace-[0-9]*\", resource=\"memory\"} > 0)",
                         "format": "time_series",
                         "legendFormat": "request",
                         "legendLink": null
                      },
                      {
-                        "expr": "min(container_spec_memory_limit_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"querier\"} > 0)",
+                        "expr": "min(container_spec_memory_limit_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"querier|loki\", pod=~\"query-frontend|loki-read-.*|$namespace-[0-9]*\"} > 0)",
                         "format": "time_series",
                         "legendFormat": "limit",
                         "legendLink": null
@@ -803,7 +803,7 @@
                   },
                   "targets": [
                      {
-                        "expr": "sum by(pod) (go_memstats_heap_inuse_bytes{cluster=~\"$cluster\", job=~\"($namespace)/.*querier\"})",
+                        "expr": "sum by(pod) (go_memstats_heap_inuse_bytes{cluster=~\"$cluster\", job=~\"($namespace)/(.*querier|loki-read|loki-single-binary)\"})",
                         "format": "time_series",
                         "legendFormat": "{{pod}}",
                         "legendLink": null
@@ -854,7 +854,7 @@
                   },
                   "targets": [
                      {
-                        "expr": "sum by(instance, pod, device) (rate(node_disk_written_bytes_total[$__rate_interval])) + ignoring(pod) group_right() (label_replace(count by(instance, pod, device) (container_fs_writes_bytes_total{cluster=~\"$cluster\", namespace=~\"$namespace\", container=\"querier\", device!~\".*sda.*\"}), \"device\", \"$1\", \"device\", \"/dev/(.*)\") * 0)\n",
+                        "expr": "sum by(instance, pod, device) (rate(node_disk_written_bytes_total[$__rate_interval])) + ignoring(pod) group_right() (label_replace(count by(instance, pod, device) (container_fs_writes_bytes_total{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"query-frontend|loki\", pod=~\"query-frontend|loki-read-.*|$namespace-[0-9]*\", device!~\".*sda.*\"}), \"device\", \"$1\", \"device\", \"/dev/(.*)\") * 0)\n",
                         "format": "time_series",
                         "legendFormat": "{{pod}} - {{device}}",
                         "legendLink": null
@@ -902,7 +902,7 @@
                   },
                   "targets": [
                      {
-                        "expr": "sum by(instance, pod, device) (rate(node_disk_read_bytes_total[$__rate_interval])) + ignoring(pod) group_right() (label_replace(count by(instance, pod, device) (container_fs_writes_bytes_total{cluster=~\"$cluster\", namespace=~\"$namespace\", container=\"querier\", device!~\".*sda.*\"}), \"device\", \"$1\", \"device\", \"/dev/(.*)\") * 0)\n",
+                        "expr": "sum by(instance, pod, device) (rate(node_disk_read_bytes_total[$__rate_interval])) + ignoring(pod) group_right() (label_replace(count by(instance, pod, device) (container_fs_writes_bytes_total{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"query-frontend|loki\", pod=~\"query-frontend|loki-read-.*|$namespace-[0-9]*\", device!~\".*sda.*\"}), \"device\", \"$1\", \"device\", \"/dev/(.*)\") * 0)\n",
                         "format": "time_series",
                         "legendFormat": "{{pod}} - {{device}}",
                         "legendLink": null
@@ -1462,19 +1462,19 @@
                   },
                   "targets": [
                      {
-                        "expr": "sum by(pod) (rate(container_cpu_usage_seconds_total{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"bloom-gateway\"}[$__rate_interval]))",
+                        "expr": "sum by(pod) (rate(container_cpu_usage_seconds_total{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"bloom-gateway|loki\", pod=~\"query-frontend|loki-read-.*|$namespace-[0-9]*\"}[$__rate_interval]))",
                         "format": "time_series",
                         "legendFormat": "{{pod}}",
                         "legendLink": null
                      },
                      {
-                        "expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"bloom-gateway\", resource=\"cpu\"} > 0)",
+                        "expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"bloom-gateway|loki\", pod=~\"query-frontend|loki-read-.*|$namespace-[0-9]*\", resource=\"cpu\"} > 0)",
                         "format": "time_series",
                         "legendFormat": "request",
                         "legendLink": null
                      },
                      {
-                        "expr": "min(container_spec_cpu_quota{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"bloom-gateway\"} / container_spec_cpu_period{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"bloom-gateway\"})",
+                        "expr": "min(container_spec_cpu_quota{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"bloom-gateway|loki\", pod=~\"query-frontend|loki-read-.*|$namespace-[0-9]*\"} / container_spec_cpu_period{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"bloom-gateway|loki\", pod=~\"query-frontend|loki-read-.*|$namespace-[0-9]*\"})",
                         "format": "time_series",
                         "legendFormat": "limit",
                         "legendLink": null
@@ -1564,19 +1564,19 @@
                   },
                   "targets": [
                      {
-                        "expr": "max by(pod) (container_memory_working_set_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"bloom-gateway\"})",
+                        "expr": "max by(pod) (container_memory_working_set_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"bloom-gateway|loki\", pod=~\"query-frontend|loki-read-.*|$namespace-[0-9]*\"})",
                         "format": "time_series",
                         "legendFormat": "{{pod}}",
                         "legendLink": null
                      },
                      {
-                        "expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"bloom-gateway\", resource=\"memory\"} > 0)",
+                        "expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"bloom-gateway|loki\", pod=~\"query-frontend|loki-read-.*|$namespace-[0-9]*\", resource=\"memory\"} > 0)",
                         "format": "time_series",
                         "legendFormat": "request",
                         "legendLink": null
                      },
                      {
-                        "expr": "min(container_spec_memory_limit_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"bloom-gateway\"} > 0)",
+                        "expr": "min(container_spec_memory_limit_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"bloom-gateway|loki\", pod=~\"query-frontend|loki-read-.*|$namespace-[0-9]*\"} > 0)",
                         "format": "time_series",
                         "legendFormat": "limit",
                         "legendLink": null
@@ -1627,7 +1627,7 @@
                   },
                   "targets": [
                      {
-                        "expr": "sum by(pod) (go_memstats_heap_inuse_bytes{cluster=~\"$cluster\", job=~\"($namespace)/.*bloom-gateway\"})",
+                        "expr": "sum by(pod) (go_memstats_heap_inuse_bytes{cluster=~\"$cluster\", job=~\"($namespace)/(.*bloom-gateway|loki-read|loki-single-binary)\"})",
                         "format": "time_series",
                         "legendFormat": "{{pod}}",
                         "legendLink": null
@@ -1678,7 +1678,7 @@
                   },
                   "targets": [
                      {
-                        "expr": "sum by(instance, pod, device) (rate(node_disk_written_bytes_total[$__rate_interval])) + ignoring(pod) group_right() (label_replace(count by(instance, pod, device) (container_fs_writes_bytes_total{cluster=~\"$cluster\", namespace=~\"$namespace\", container=\"bloom-gateway\", device!~\".*sda.*\"}), \"device\", \"$1\", \"device\", \"/dev/(.*)\") * 0)\n",
+                        "expr": "sum by(instance, pod, device) (rate(node_disk_written_bytes_total[$__rate_interval])) + ignoring(pod) group_right() (label_replace(count by(instance, pod, device) (container_fs_writes_bytes_total{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"bloom-gateway|loki\", pod=~\"query-frontend|loki-read-.*|$namespace-[0-9]*\", device!~\".*sda.*\"}), \"device\", \"$1\", \"device\", \"/dev/(.*)\") * 0)\n",
                         "format": "time_series",
                         "legendFormat": "{{pod}} - {{device}}",
                         "legendLink": null
@@ -1726,7 +1726,7 @@
                   },
                   "targets": [
                      {
-                        "expr": "sum by(instance, pod, device) (rate(node_disk_read_bytes_total[$__rate_interval])) + ignoring(pod) group_right() (label_replace(count by(instance, pod, device) (container_fs_writes_bytes_total{cluster=~\"$cluster\", namespace=~\"$namespace\", container=\"bloom-gateway\", device!~\".*sda.*\"}), \"device\", \"$1\", \"device\", \"/dev/(.*)\") * 0)\n",
+                        "expr": "sum by(instance, pod, device) (rate(node_disk_read_bytes_total[$__rate_interval])) + ignoring(pod) group_right() (label_replace(count by(instance, pod, device) (container_fs_writes_bytes_total{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"bloom-gateway|loki\", pod=~\"query-frontend|loki-read-.*|$namespace-[0-9]*\", device!~\".*sda.*\"}), \"device\", \"$1\", \"device\", \"/dev/(.*)\") * 0)\n",
                         "format": "time_series",
                         "legendFormat": "{{pod}} - {{device}}",
                         "legendLink": null
@@ -2189,19 +2189,19 @@
                   },
                   "targets": [
                      {
-                        "expr": "sum by(pod) (rate(container_cpu_usage_seconds_total{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"ruler\"}[$__rate_interval]))",
+                        "expr": "sum by(pod) (rate(container_cpu_usage_seconds_total{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"ruler|loki\", pod=~\"ruler|loki-backend-.*|$namespace-[0-9]*\"}[$__rate_interval]))",
                         "format": "time_series",
                         "legendFormat": "{{pod}}",
                         "legendLink": null
                      },
                      {
-                        "expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"ruler\", resource=\"cpu\"} > 0)",
+                        "expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"ruler|loki\", pod=~\"ruler|loki-backend-.*|$namespace-[0-9]*\", resource=\"cpu\"} > 0)",
                         "format": "time_series",
                         "legendFormat": "request",
                         "legendLink": null
                      },
                      {
-                        "expr": "min(container_spec_cpu_quota{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"ruler\"} / container_spec_cpu_period{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"ruler\"})",
+                        "expr": "min(container_spec_cpu_quota{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"ruler|loki\", pod=~\"ruler|loki-backend-.*|$namespace-[0-9]*\"} / container_spec_cpu_period{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"ruler|loki\", pod=~\"ruler|loki-backend-.*|$namespace-[0-9]*\"})",
                         "format": "time_series",
                         "legendFormat": "limit",
                         "legendLink": null
@@ -2291,19 +2291,19 @@
                   },
                   "targets": [
                      {
-                        "expr": "max by(pod) (container_memory_working_set_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"ruler\"})",
+                        "expr": "max by(pod) (container_memory_working_set_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"ruler|loki\", pod=~\"ruler|loki-backend-.*|$namespace-[0-9]*\"})",
                         "format": "time_series",
                         "legendFormat": "{{pod}}",
                         "legendLink": null
                      },
                      {
-                        "expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"ruler\", resource=\"memory\"} > 0)",
+                        "expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"ruler|loki\", pod=~\"ruler|loki-backend-.*|$namespace-[0-9]*\", resource=\"memory\"} > 0)",
                         "format": "time_series",
                         "legendFormat": "request",
                         "legendLink": null
                      },
                      {
-                        "expr": "min(container_spec_memory_limit_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"ruler\"} > 0)",
+                        "expr": "min(container_spec_memory_limit_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"ruler|loki\", pod=~\"ruler|loki-backend-.*|$namespace-[0-9]*\"} > 0)",
                         "format": "time_series",
                         "legendFormat": "limit",
                         "legendLink": null
@@ -2354,7 +2354,7 @@
                   },
                   "targets": [
                      {
-                        "expr": "sum by(pod) (go_memstats_heap_inuse_bytes{cluster=~\"$cluster\", job=~\"($namespace)/ruler\"})",
+                        "expr": "sum by(pod) (go_memstats_heap_inuse_bytes{cluster=~\"$cluster\", job=~\"($namespace)/(.*ruler|loki-backend|loki-single-binary)\"})",
                         "format": "time_series",
                         "legendFormat": "{{pod}}",
                         "legendLink": null

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

@@ -2449,7 +2449,7 @@
             "repeatIteration": null,
             "repeatRowId": null,
             "showTitle": true,
-            "title": "TSBD Index",
+            "title": "TSDB Index",
             "titleSize": "h6"
          },
          {
@@ -2897,4 +2897,4 @@
       "title": "Loki / Reads",
       "uid": "reads",
       "version": 0
-   }
+   }

charts/meta-monitoring/src/dashboards/loki-writes-resources.json

@@ -104,7 +104,7 @@
                   "span": 4,
                   "targets": [
                      {
-                        "expr": "sum by(pod) (rate(container_cpu_usage_seconds_total{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"distributor\"}[$__rate_interval]))",
+                        "expr": "sum by(pod) (rate(container_cpu_usage_seconds_total{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"distributor|loki\", pod=~\"distributor|loki-write-.*|$namespace-[0-9]*\"}[$__rate_interval]))",
                         "format": "time_series",
                         "legendFormat": "{{pod}}",
                         "legendLink": null
@@ -116,7 +116,7 @@
                         "legendLink": null
                      },
                      {
-                        "expr": "min(container_spec_cpu_quota{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"distributor\"} / container_spec_cpu_period{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"distributor\"})",
+                        "expr": "min(container_spec_cpu_quota{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"distributor|loki\", pod=~\"distributor|loki-write-.*|$namespace-[0-9]*\"} / container_spec_cpu_period{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"distributor|loki\", pod=~\"distributor|loki-write-.*|$namespace-[0-9]*\"})",
                         "format": "time_series",
                         "legendFormat": "limit",
                         "legendLink": null
@@ -206,7 +206,7 @@
                   "span": 4,
                   "targets": [
                      {
-                        "expr": "max by(pod) (container_memory_working_set_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"distributor\"})",
+                        "expr": "max by(pod) (container_memory_working_set_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"distributor|loki\", pod=~\"distributor|loki-write-.*|$namespace-[0-9]*\"})",
                         "format": "time_series",
                         "legendFormat": "{{pod}}",
                         "legendLink": null
@@ -218,7 +218,7 @@
                         "legendLink": null
                      },
                      {
-                        "expr": "min(container_spec_memory_limit_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"distributor\"} > 0)",
+                        "expr": "min(container_spec_memory_limit_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"distributor|loki\", pod=~\"distributor|loki-write-.*|$namespace-[0-9]*\"} > 0)",
                         "format": "time_series",
                         "legendFormat": "limit",
                         "legendLink": null
@@ -269,7 +269,7 @@
                   "span": 4,
                   "targets": [
                      {
-                        "expr": "sum by(pod) (go_memstats_heap_inuse_bytes{cluster=~\"$cluster\", job=~\"($namespace)/.*distributor\"})",
+                        "expr": "sum by(pod) (go_memstats_heap_inuse_bytes{cluster=~\"$cluster\", job=~\"($namespace)/(.*distributor|loki-write|loki-single-binary)\"})",
                         "format": "time_series",
                         "legendFormat": "{{pod}}",
                         "legendLink": null

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

@@ -120,9 +120,9 @@ data:
         replacement = "{{- .Values.clusterLabelValue -}}"
       }
       rule {
-        source_labels = ["__meta_kubernetes_pod_container_port_number"]
+        source_labels = ["__meta_kubernetes_pod_container_port_name"]
-        action = "drop"
+        action = "keep"
-        regex = "9095"
+        regex = ".*metrics.*"
       }
     }
 
@@ -135,6 +135,11 @@ data:
     }
 
     prometheus.relabel "filter" {
+      rule {
+        target_label = "cluster"
+        replacement = "{{- .Values.clusterLabelValue -}}"
+      }
+
       rule {
         source_labels = ["__name__"]
         regex = "({{ include "agent.all_metrics" . }})"
@@ -150,133 +155,7 @@ data:
 
       forward_to = [ {{ include "agent.prometheus_write_targets" . }} ]
     }
-    {{- if .Values.kubeStateMetrics.enabled }}
 
-    prometheus.scrape "kubeStateMetrics" {
-      clustering {
-        enabled = true
-      }
-      targets    = [ { "__address__" = "{{ .Values.kubeStateMetrics.endpoint }}" } ]
-      forward_to = [ prometheus.relabel.filter.receiver ]
-    }
-    {{- end }}
-
-    // cAdvisor and Kubelet metrics
-    // Based on https://github.com/Chewie/loutretelecom-manifests/blob/main/manifests/addons/monitoring/config.river
-    discovery.kubernetes "all_nodes" {
-      role = "node"
-      namespaces {
-        own_namespace = true
-        names = [ {{ include "agent.namespaces" . }} ]
-      }
-    }
-
-    discovery.relabel "all_nodes" {
-      targets = discovery.kubernetes.all_nodes.targets
-      rule {
-        source_labels = ["__meta_kubernetes_node_name"]
-        target_label = "node"
-      }
-      rule {
-        source_labels = ["__meta_kubernetes_namespace"]
-        target_label  = "namespace"
-      }
-      rule {
-        source_labels = ["__meta_kubernetes_pod_name"]
-        target_label  = "pod"
-      }
-      rule {
-        source_labels = ["__meta_kubernetes_namespace", "__meta_kubernetes_pod_label_app_kubernetes_io_name", "__meta_kubernetes_pod_label_app_kubernetes_io_component"]
-        separator = "/"
-        regex = "(.*)/(.*)/(.*)"
-        replacement = "${1}/${2}-${3}"
-        target_label = "job"
-      }
-      rule {
-        target_label = "cluster"
-        replacement = "{{- .Values.clusterLabelValue -}}"
-      }
-    }
-
-    prometheus.scrape "cadvisor" {
-      clustering {
-        enabled = true
-      }
-      targets    = discovery.relabel.all_nodes.output
-      forward_to = [ prometheus.relabel.filter.receiver ]
-
-      metrics_path = "/metrics/cadvisor"
-      scheme = "https"
-
-      bearer_token_file = "/var/run/secrets/kubernetes.io/serviceaccount/token"
-      tls_config {
-        ca_file = "/var/run/secrets/kubernetes.io/serviceaccount/ca.crt"
-      }
-    }
-
-    prometheus.scrape "kubelet" {
-      clustering {
-        enabled = true
-      }
-      targets    = discovery.relabel.all_nodes.output
-      forward_to = [ prometheus.relabel.filter.receiver ]
-
-      metrics_path = "/metrics"
-      scheme = "https"
-
-      bearer_token_file = "/var/run/secrets/kubernetes.io/serviceaccount/token"
-      tls_config {
-        ca_file = "/var/run/secrets/kubernetes.io/serviceaccount/ca.crt"
-      }
-    }
-
-    prometheus.exporter.unix "promexporter" {}
-
-    prometheus.scrape "node_exporter" {
-      clustering {
-        enabled = true
-      }
-      targets = prometheus.exporter.unix.promexporter.targets
-      forward_to = [prometheus.relabel.node_exporter.receiver]
-
-      job_name = "node-exporter"
-    }
-
-    prometheus.relabel "node_exporter" {
-      forward_to = [ prometheus.relabel.filter.receiver ]
-
-      rule {
-        replacement = env("HOSTNAME")
-        target_label = "nodename"
-      }
-      rule {
-        replacement = "node-exporter"
-        target_label = "job"
-      }
-      rule {
-        source_labels = ["__meta_kubernetes_node_name"]
-        target_label = "node"
-      }
-      rule {
-        source_labels = ["__meta_kubernetes_namespace"]
-        target_label  = "namespace"
-      }
-      rule {
-        source_labels = ["__meta_kubernetes_pod_name"]
-        target_label  = "pod"
-      }
-      rule {
-        source_labels = ["__meta_kubernetes_namespace", "__meta_kubernetes_pod_label_app_kubernetes_io_name", "__meta_kubernetes_pod_label_app_kubernetes_io_component"]
-        separator = "/"
-        regex = "(.*)/(.*)/(.*)"
-        replacement = "${1}/${2}-${3}"
-        target_label = "job"
-      }
-      rule {
-        target_label = "cluster"
-        replacement = "{{- .Values.clusterLabelValue -}}"
-      }
-    }
     {{- end }}
 
     {{- if or .Values.local.traces.enabled .Values.cloud.traces.enabled }}
@@ -330,7 +209,7 @@ data:
     {{- if .Values.local.logs.enabled }}
     loki.write "local" {
       endpoint {
-        url = "http://{{- .Release.Namespace -}}-loki-gateway.{{- .Release.Namespace -}}.svc.cluster.local:80/loki/api/v1/push"
+        url = "http://loki-write.{{- .Release.Namespace -}}.svc.cluster.local:3100/loki/api/v1/push"
       }
     }
     {{- end }}
@@ -346,7 +225,7 @@ data:
     {{- if .Values.local.traces.enabled }}
     otelcol.exporter.otlphttp "local" {
         client {
-            endpoint = "http://{{- .Release.Name -}}-tempo-distributor.svc:4318"
+            endpoint = "http://{{- .Release.Name -}}-tempo-distributor.{{- .Release.Namespace -}}.svc:4318"
         }
     }
     {{- end }}

charts/meta-monitoring/templates/validate.yaml

@@ -34,10 +34,6 @@
 {{- end -}}
 {{- end -}}
 
-{{- if empty .Values.namespacesToMonitor -}}
-  {{- fail "No namespaces have been specified in namespacesToMonitor" -}}
-{{- end -}}
-
 {{- if empty .Values.metrics.retain -}}
   {{- fail "All metrics will be collected, please specify some in metrics.retain" -}}
 {{- end -}}

charts/meta-monitoring/values.yaml

@@ -1,8 +1,9 @@
 # Specify the namespaces to monitor here
-namespacesToMonitor:
+# By default the chart will monitor the namespace it is installed in
-- loki
+# namespacesToMonitor:
+# - loki
 # The name of the cluster where this will be installed
-clusterLabelValue: "meta-monitoring"
+clusterLabelValue: "meta"
 # Set to true to write logs, metrics or traces to Grafana Cloud
 # The secrets have to be created first
 cloud:
@@ -28,7 +29,7 @@ local:
   minio:
     enabled: false # This should be set to true if any of the previous is enabled
 grafana:
-  version: 10.4.2
+  version: 11.4.3
   # Gateway ingress configuration
   ingress:
     # -- Specifies whether an ingress for the gateway should be created
@@ -45,7 +46,12 @@ grafana:
         paths:
           - path: /
             # -- pathType (e.g. ImplementationSpecific, Prefix, .. etc.) might also be required by some Ingress Controllers
-            # pathType: Prefix
+            pathType: Prefix
+            # backend:
+            #   service:
+            #     name: TODO
+            #     port:
+            #       number: TODO
     # -- TLS configuration for the gateway ingress. Hosts passed through the `tpl` function to allow templating
     #tls:
     #  - secretName: grafana-tls
@@ -55,15 +61,17 @@ logs:
   # Adding regexes here will add a stage.replace block for logs. For more information see
   # https://grafana.com/docs/agent/latest/flow/reference/components/loki.process/#stagereplace-block
   piiRegexes: null # This example replaces the word after password with *****
-# - expression: "password (\\\\S+)"
+  # - expression: "password (\\\\S+)"
-#   source: ""         # Empty uses the log message
+  #   source: ""         # Empty uses the log message
-#   replace: "*****""
+  #   replace: "*****""
-# The lines matching these will be kept in Loki
+  # The lines matching these will be kept in Loki
   retain:
   # This shows the queries
+  - executing query
   - caller=metrics.go
   # This shows any errors
   - level=error
+  - level=warn
   # Log lines for delete requests
   - delete request for user added
   - Started processing delete request
@@ -144,6 +152,7 @@ metrics:
   - kube_pod_container_resource_requests
   - kube_pod_container_status_last_terminated_reason
   - kube_pod_container_status_restarts_total
+  - loki_azure_blob_request_duration_seconds_bucket
   - loki_boltdb_shipper_compact_tables_operation_duration_seconds
   - loki_boltdb_shipper_compact_tables_operation_last_successful_run_timestamp_seconds
   - loki_boltdb_shipper_retention_marker_count_total
@@ -169,11 +178,15 @@ metrics:
   - loki_compactor_deleted_lines
   - loki_compactor_oldest_pending_delete_request_age_seconds
   - loki_compactor_pending_delete_requests_count
+  - loki_consul_request_duration_seconds_bucket
   - loki_discarded_samples_total
   - loki_discarded_bytes_total
   - loki_distributor_bytes_received_total
   - loki_distributor_lines_received_total
   - loki_distributor_structured_metadata_bytes_received_total
+  - loki_gcs_request_duration_seconds_bucket
+  - loki_gcs_request_duration_seconds_count
+  - loki_index_request_duration_seconds_bucket
   - loki_index_request_duration_seconds_count
   - loki_ingester_chunk_age_seconds_bucket
   - loki_ingester_chunk_age_seconds_count
@@ -186,6 +199,7 @@ metrics:
   - loki_ingester_chunk_entries_sum
   - loki_ingester_chunk_size_bytes_bucket
   - loki_ingester_chunk_utilization_bucket
+  - loki_ingester_chunk_utilization_count
   - loki_ingester_chunk_utilization_sum
   - loki_ingester_chunks_flushed_total
   - loki_ingester_flush_queue_length
@@ -203,6 +217,8 @@ metrics:
   - loki_ruler_wal_prometheus_remote_storage_samples_total
   - loki_ruler_wal_samples_appended_total
   - loki_ruler_wal_storage_created_series_total
+  - loki_s3_request_duration_seconds_bucket
+  - loki_s3_request_duration_seconds_count
   - loki_write_batch_retries_total
   - loki_write_dropped_bytes_total
   - loki_write_dropped_entries_total

docs/dev_update_dependencies.md

@@ -1,8 +1,12 @@
 # Update the dependencies
 
-The dependencies are the version of Loki, Mimir, Agent and so on that are included in this chart.
+The dependencies are the versions of Loki, Mimir, Agent and so on that are included in this chart.
 The current versions can be found in the [Chart.yaml](../charts/meta-monitoring/Chart.yaml) file.
 
+A Github action runs daily to see if updated versions are available. A PR will be created.
+
+The manual steps are as follows:
+
 Run this in the charts/meta-monitoring directory after updating a dependency:
 
 ```

docs/installation.md

@@ -4,7 +4,7 @@
 
 1. Use an existing Grafana Cloud account or setup a new one. Then create an access token:
 
-   1. In Grafana go to Administration -> Users and Access -> Cloud access policies.
+   1. In a Grafana instance on Grafana Cloud go to Administration -> Users and Access -> Cloud access policies.
 
    1. Click `Create access policy`.
 
@@ -39,7 +39,7 @@
     --from-literal=endpoint='https://otlp-gateway-prod-us-east-0.grafana.net/otlp'
    ```
 
-   The logs, metrics and traces usernames are the `User / Username / Instance IDs` of the Loki, Prometheus/Mimir and OpenTelemetry instances in Grafana Cloud. From `Home` in Grafana click on `Stacks`. Then go to the `Details` pages of Loki and Prometheus/Mimir. For OpenTelemetry go to the `Configure` page.
+   The logs, metrics and traces usernames are the `User / Username / Instance IDs` of the Loki, Prometheus/Mimir and OpenTelemetry instances in Grafana Cloud. From `Home` in Grafana click on `Stacks`. Then go to the `Details` pages of Loki and Prometheus/Mimir. For OpenTelemetry go to the `Configure` page. The endpoints will also have to be changed to match your settings.
 
 1. Create a values.yaml file based on the [default one](../charts/meta-monitoring/values.yaml). Fill in the names of the secrets created above as needed. An example minimal values.yaml looks like this:
 
@@ -91,7 +91,7 @@
 
    local:
      grafana:
-       enabled:true
+       enabled: true
      logs:
        enabled: true
      metrics:
@@ -102,7 +102,7 @@
        enabled: true
    ```
 
-## Installing the chart
+## Installing, updating and deleting the chart
 
 1. Add the repo
 
@@ -175,7 +175,7 @@ For each of the dashboard files in charts/meta-monitoring/src/dashboards folder
 
 ## Configure Loki to send traces
 
-1. In the Loki config enable tracing:
+1. In the Loki that is being monitored enable tracing in the config:
 
    ```
    loki:
@@ -187,7 +187,15 @@ For each of the dashboard files in charts/meta-monitoring/src/dashboards folder
 
    1. JAEGER_ENDPOINT: http address of the mmc-alloy service installed by the meta-monitoring chart, for example "http://mmc-alloy:14268/api/traces"
    1. JAEGER_AGENT_TAGS: extra tags you would like to add to the spans, for example  'cluster="abc",namespace="def"'
-   1. JAEGER_SAMPLER_TYPE: the sampling strategy, for example to sample all use 'const' with a value of 1 for the next environment variable
+   1. JAEGER_SAMPLER_TYPE: the sampling strategy, we suggest setting this to `ratelimiting` so at most 1 trace is accepted per second. See these [docs](https://www.jaegertracing.io/docs/1.57/sampling/) for more options.
-   1. JAEGER_SAMPLER_PARAM: 1
+   1. JAEGER_SAMPLER_PARAM: 1.0
 
 1. If Loki is installed in a different namespace you can create an [ExternalName service](https://kubernetes.io/docs/concepts/services-networking/service/#externalname) in Kubernetes to point to the mmc-alloy service in the meta monitoring namespace
+
+## Configure external access using an Ingress in local mode
+
+When using local mode by default a Kubernetes [Ingress](https://kubernetes.io/docs/concepts/services-networking/ingress/) object is created to access the Grafana instance. This will need to be adapted to your cloud provider by updating the `grafana.ingress` section of the `values.yaml` file provided to Helm. Check the documentation of your cloud provider for available options.
+
+## Kube-state-metrics
+
+Metrics about Kubernetes objects are scraped from [kube-state-metrics](https://github.com/kubernetes/kube-state-metrics). This needs to be installed in the cluster. The `kubeStateMetrics.endpoint` entry in values.yaml should be set to it's address (without the `/metrics` part in the URL).