.github/configs/cluster-config.yaml

@@ -1,19 +0,0 @@
-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

@@ -19,9 +19,6 @@ jobs:
     updateVersions:
         name: Update the subcharts
         runs-on: "ubuntu-latest"
-        permissions:
-          contents: write
-          id-token: write
         steps:
             - name: Checkout
               uses: actions/checkout@v2
@@ -69,20 +66,6 @@ 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
@@ -96,15 +79,10 @@ 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
@@ -120,20 +98,6 @@ 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
@@ -147,5 +111,3 @@ 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

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

README.md

@@ -1,6 +1,8 @@
 # meta-monitoring-chart
 
-This is a meta-monitoring chart for Loki, specifically Loki installed via the Loki helm chart.
+This is a meta-monitoring chart for Loki.
+
+Note that this is pre-production software at the moment.
 
 ## Local and cloud modes
 
@@ -9,15 +11,19 @@ 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 install the chart go to the [installation](docs/installation.md) page.
+For more instructions including how to update the chart go to the [installation](docs/installation.md) page.
 
 ## Supported features
 
@@ -27,7 +33,8 @@ For more instructions including how to install 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
-  - Alloy dashboards
+  - agent dashboards
+- Retention is set to 24 hours
 
 Most of these features are enabled by default. See the values.yaml file for how to enable/disable them.
 
@@ -35,7 +42,8 @@ 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 for the local mode 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 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: 6.29.0
+  version: 6.5.1
 - name: alloy
   repository: https://grafana.github.io/helm-charts
-  version: 0.12.5
+  version: 0.1.1
 - name: mimir-distributed
   repository: https://grafana.github.io/helm-charts
-  version: 5.6.0
+  version: 5.3.0
 - name: tempo-distributed
   repository: https://grafana.github.io/helm-charts
-  version: 1.33.0
+  version: 1.9.9
 - name: minio
   repository: https://charts.min.io
-  version: 5.4.0
-digest: sha256:5225a03d9003384639f5d43b1971126371269347f16f221b7aed377ab85d71be
-generated: "2025-03-27T07:03:11.17404081Z"
+  version: 5.2.0
+digest: sha256:e0c7af6d328fe35f4b9a3557235f458d92225b84b1366dbb77c4626d3cdb5be9
+generated: "2024-05-09T07:02:42.911579524Z"

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: 1.3.0
+version: 0.0.3
 # 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: 6.29.0
+  version: 6.5.1
   condition: local.logs.enabled
 - name: alloy
   repository: https://grafana.github.io/helm-charts
-  version: 0.12.5
+  version: 0.1.1
 - name: mimir-distributed
   repository: https://grafana.github.io/helm-charts
-  version: 5.6.0
+  version: 5.3.0
   condition: local.metrics.enabled
 - name: tempo-distributed
   repository: https://grafana.github.io/helm-charts
-  version: 1.33.0
+  version: 1.9.9
   condition: local.traces.enabled
 - name: minio
   repository: https://charts.min.io
-  version: 5.4.0
+  version: 5.2.0
   condition: local.minio.enabled

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

@@ -2449,7 +2449,7 @@
             "repeatIteration": null,
             "repeatRowId": null,
             "showTitle": true,
-            "title": "TSDB Index",
+            "title": "TSBD Index",
             "titleSize": "h6"
          },
          {

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

@@ -120,9 +120,9 @@ data:
         replacement = "{{- .Values.clusterLabelValue -}}"
       }
       rule {
-        source_labels = ["__meta_kubernetes_pod_container_port_name"]
-        action = "keep"
-        regex = ".*metrics.*"
+        source_labels = ["__meta_kubernetes_pod_container_port_number"]
+        action = "drop"
+        regex = "9095"
       }
     }
 
@@ -155,7 +155,133 @@ 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 }}

charts/meta-monitoring/templates/validate.yaml

@@ -34,6 +34,10 @@
 {{- 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

@@ -1,9 +1,8 @@
 # Specify the namespaces to monitor here
-# By default the chart will monitor the namespace it is installed in
-# namespacesToMonitor:
-# - loki
+namespacesToMonitor:
+- loki
 # The name of the cluster where this will be installed
-clusterLabelValue: "meta"
+clusterLabelValue: "meta-monitoring"
 # Set to true to write logs, metrics or traces to Grafana Cloud
 # The secrets have to be created first
 cloud:
@@ -29,7 +28,7 @@ local:
   minio:
     enabled: false # This should be set to true if any of the previous is enabled
 grafana:
-  version: 11.4.3
+  version: 10.4.2
   # Gateway ingress configuration
   ingress:
     # -- Specifies whether an ingress for the gateway should be created
@@ -67,11 +66,9 @@ logs:
 # 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

docs/dev_update_dependencies.md

@@ -1,12 +1,8 @@
 # Update the dependencies
 
-The dependencies are the versions of Loki, Mimir, Agent and so on that are included in this chart.
+The dependencies are the version 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 a Grafana instance on Grafana Cloud go to Administration -> Users and Access -> Cloud access policies.
+   1. In Grafana 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 endpoints will also have to be changed to match your settings.
+   The logs, metrics and traces usernames are the `User / Username / Instance IDs` of the Loki, Prometheus/Mimir and OpenTelemetry instances in Grafana Cloud. From `Home` in Grafana click on `Stacks`. Then go to the `Details` pages of Loki and Prometheus/Mimir. For OpenTelemetry go to the `Configure` page.
 
 1. Create a values.yaml file based on the [default one](../charts/meta-monitoring/values.yaml). Fill in the names of the secrets created above as needed. An example minimal values.yaml looks like this:
 
@@ -102,7 +102,7 @@
        enabled: true
    ```
 
-## Installing, updating and deleting the chart
+## Installing 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 that is being monitored enable tracing in the config:
+1. In the Loki config enable tracing:
 
    ```
    loki:
@@ -195,7 +195,3 @@ For each of the dashboard files in charts/meta-monitoring/src/dashboards folder
 ## 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).