Update Mimir Distributed

Add team-reviewers and fix text

.github/configs/updatecli.d/alloy.yaml

@@ -0,0 +1,30 @@
+name: Bump dependency "alloy" for Helm chart "meta-monitoring"
+sources:
+    alloy:
+        name: Get latest "alloy" Helm chart version
+        kind: helmchart
+        spec:
+            name: alloy
+            url: https://grafana.github.io/helm-charts
+            versionfilter:
+                kind: semver
+                pattern: '*'
+conditions:
+    alloy:
+        name: Ensure Helm chart dependency "alloy" is specified
+        kind: yaml
+        spec:
+            file: charts/meta-monitoring/Chart.yaml
+            key: $.dependencies[1].name
+            value: alloy
+        disablesourceinput: true
+targets:
+    alloy:
+        name: Bump Helm chart dependency "alloy" for Helm chart "meta-monitoring"
+        kind: helmchart
+        spec:
+            file: Chart.yaml
+            key: $.dependencies[1].version
+            name: charts/meta-monitoring
+            versionincrement: none
+        sourceid: alloy

.github/configs/updatecli.d/loki.yaml

@@ -0,0 +1,30 @@
+name: Bump dependency "loki" for Helm chart "meta-monitoring"
+sources:
+    loki:
+        name: Get latest "loki" Helm chart version
+        kind: helmchart
+        spec:
+            name: loki
+            url: https://grafana.github.io/helm-charts
+            versionfilter:
+                kind: semver
+                pattern: '*'
+conditions:
+    loki:
+        name: Ensure Helm chart dependency "loki" is specified
+        kind: yaml
+        spec:
+            file: charts/meta-monitoring/Chart.yaml
+            key: $.dependencies[0].name
+            value: loki
+        disablesourceinput: true
+targets:
+    loki:
+        name: Bump Helm chart dependency "loki" for Helm chart "meta-monitoring"
+        kind: helmchart
+        spec:
+            file: Chart.yaml
+            key: $.dependencies[0].version
+            name: charts/meta-monitoring
+            versionincrement: none
+        sourceid: loki

.github/configs/updatecli.d/mimir-distributed.yaml

@@ -0,0 +1,30 @@
+name: Bump dependency "mimir-distributed" for Helm chart "meta-monitoring"
+sources:
+    mimir-distributed:
+        name: Get latest "mimir-distributed" Helm chart version
+        kind: helmchart
+        spec:
+            name: mimir-distributed
+            url: https://grafana.github.io/helm-charts
+            versionfilter:
+                kind: semver
+                pattern: '*'
+conditions:
+    mimir-distributed:
+        name: Ensure Helm chart dependency "mimir-distributed" is specified
+        kind: yaml
+        spec:
+            file: charts/meta-monitoring/Chart.yaml
+            key: $.dependencies[2].name
+            value: mimir-distributed
+        disablesourceinput: true
+targets:
+    mimir-distributed:
+        name: Bump Helm chart dependency "mimir-distributed" for Helm chart "meta-monitoring"
+        kind: helmchart
+        spec:
+            file: Chart.yaml
+            key: $.dependencies[2].version
+            name: charts/meta-monitoring
+            versionincrement: none
+        sourceid: mimir-distributed

.github/configs/updatecli.d/minio.yaml

@@ -0,0 +1,30 @@
+name: Bump dependency "minio" for Helm chart "meta-monitoring"
+sources:
+    minio:
+        name: Get latest "minio" Helm chart version
+        kind: helmchart
+        spec:
+            name: minio
+            url: https://charts.min.io
+            versionfilter:
+                kind: semver
+                pattern: '*'
+conditions:
+    minio:
+        name: Ensure Helm chart dependency "minio" is specified
+        kind: yaml
+        spec:
+            file: charts/meta-monitoring/Chart.yaml
+            key: $.dependencies[4].name
+            value: minio
+        disablesourceinput: true
+targets:
+    minio:
+        name: Bump Helm chart dependency "minio" for Helm chart "meta-monitoring"
+        kind: helmchart
+        spec:
+            file: Chart.yaml
+            key: $.dependencies[4].version
+            name: charts/meta-monitoring
+            versionincrement: none
+        sourceid: minio

.github/configs/updatecli.d/tempo-distributed.yaml

@@ -0,0 +1,30 @@
+name: Bump dependency "tempo-distributed" for Helm chart "meta-monitoring"
+sources:
+    tempo-distributed:
+        name: Get latest "tempo-distributed" Helm chart version
+        kind: helmchart
+        spec:
+            name: tempo-distributed
+            url: https://grafana.github.io/helm-charts
+            versionfilter:
+                kind: semver
+                pattern: '*'
+conditions:
+    tempo-distributed:
+        name: Ensure Helm chart dependency "tempo-distributed" is specified
+        kind: yaml
+        spec:
+            file: charts/meta-monitoring/Chart.yaml
+            key: $.dependencies[3].name
+            value: tempo-distributed
+        disablesourceinput: true
+targets:
+    tempo-distributed:
+        name: Bump Helm chart dependency "tempo-distributed" for Helm chart "meta-monitoring"
+        kind: helmchart
+        spec:
+            file: Chart.yaml
+            key: $.dependencies[3].version
+            name: charts/meta-monitoring
+            versionincrement: none
+        sourceid: tempo-distributed

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

@@ -0,0 +1,182 @@
+---
+name: Check for dependency updates
+
+on:
+    workflow_dispatch:
+    schedule:
+      # Run once a day
+      - cron: '0 0 * * *'
+
+permissions:
+    contents: "write"
+    pull-requests: "write"
+
+env:
+    UPDATECLI_CONFIG_DIR: "${{ github.workspace }}/.github/configs/updatecli.d"
+    UPDATECLI_GITHUB_TOKEN: "${{ secrets.GITHUB_TOKEN }}"
+
+jobs:
+    updateLoki:
+        name: Update the Loki subchart
+        runs-on: "ubuntu-latest"
+        steps:
+            - name: Checkout
+              uses: actions/checkout@v2
+
+            - name: Install Updatecli
+              uses: updatecli/updatecli-action@v2
+
+            - name: Run Updatecli
+              id: update-loki
+              run: |
+                updatecli apply --config ${UPDATECLI_CONFIG_DIR}/loki.yaml
+                if ! git diff --exit-code > /dev/null; then
+                  echo "changed=true" >> "${GITHUB_OUTPUT}"
+                fi
+
+            - name: Create pull request
+              if: steps.update-loki.outputs.changed == 'true'
+              uses: peter-evans/create-pull-request@v5
+              with:
+                title: "[dependency] Update the Loki subchart"
+                body: "Updates the Loki subchart"
+                base: main
+                author: "${{ github.actor }} <${{ github.actor }}@users.noreply.github.com>"
+                committer: "GitHub <noreply@github.com>"
+                commit-message: Update loki
+                labels: dependencies
+                branch: chore/update-loki
+                delete-branch: true
+                team-reviewers: loki-team
+
+    updateGrafanaAlloy:
+        name: Update the Grafana Alloy subchart
+        runs-on: "ubuntu-latest"
+        steps:
+            - name: Checkout
+              uses: actions/checkout@v2
+
+            - name: Install Updatecli
+              uses: updatecli/updatecli-action@v2
+
+            - name: Run Updatecli
+              id: update-grafana-alloy
+              run: |
+                updatecli apply --config ${UPDATECLI_CONFIG_DIR}/alloy.yaml
+                if ! git diff --exit-code > /dev/null; then
+                  echo "changed=true" >> "${GITHUB_OUTPUT}"
+                fi
+
+            - name: Create pull request
+              if: steps.update-grafana-alloy.outputs.changed == 'true'
+              uses: peter-evans/create-pull-request@v5
+              with:
+                title: "[dependency] Update the Grafana Alloy subchart"
+                body: "Updates the Grafana Alloy subchart"
+                base: main
+                author: "${{ github.actor }} <${{ github.actor }}@users.noreply.github.com>"
+                committer: "GitHub <noreply@github.com>"
+                commit-message: Update Grafana Alloy
+                labels: dependencies
+                branch: chore/update-grafana-alloy
+                delete-branch: true
+                team-reviewers: loki-team
+
+    updateMimirDistributed:
+        name: Update the Mimir Distributed subchart
+        runs-on: "ubuntu-latest"
+        steps:
+            - name: Checkout
+              uses: actions/checkout@v2
+
+            - name: Install Updatecli
+              uses: updatecli/updatecli-action@v2
+
+            - name: Run Updatecli
+              id: update-mimir-distributed
+              run: |
+                updatecli apply --config ${UPDATECLI_CONFIG_DIR}/mimir-distributed.yaml
+                if ! git diff --exit-code > /dev/null; then
+                  echo "changed=true" >> "${GITHUB_OUTPUT}"
+                fi
+
+            - name: Create pull request
+              if: steps.update-mimir-distributed.outputs.changed == 'true'
+              uses: peter-evans/create-pull-request@v5
+              with:
+                title: "[dependency] Update the Mimir Distributed subchart"
+                body: "Updates the Mimir Distributed subchart"
+                base: main
+                author: "${{ github.actor }} <${{ github.actor }}@users.noreply.github.com>"
+                committer: "GitHub <noreply@github.com>"
+                commit-message: Update Mimir Distributed
+                labels: dependencies
+                branch: chore/update-mimir-distributed
+                delete-branch: true
+                team-reviewers: loki-team
+
+    updateTempoDistributed:
+        name: Update the Tempo Distributed subchart
+        runs-on: "ubuntu-latest"
+        steps:
+            - name: Checkout
+              uses: actions/checkout@v2
+
+            - name: Install Updatecli
+              uses: updatecli/updatecli-action@v2
+
+            - name: Run Updatecli
+              id: update-tempo-distributed
+              run: |
+                updatecli apply --config ${UPDATECLI_CONFIG_DIR}/tempo-distributed.yaml
+                if ! git diff --exit-code > /dev/null; then
+                  echo "changed=true" >> "${GITHUB_OUTPUT}"
+                fi
+
+            - name: Create pull request
+              if: steps.update-tempo-distributed.outputs.changed == 'true'
+              uses: peter-evans/create-pull-request@v5
+              with:
+                title: "[dependency] Update the Tempo Distributed subchart"
+                body: "Updates the tempo Distributed subchart"
+                base: main
+                author: "${{ github.actor }} <${{ github.actor }}@users.noreply.github.com>"
+                committer: "GitHub <noreply@github.com>"
+                commit-message: Update Tempo Distributed
+                labels: dependencies
+                branch: chore/update-tempo-distributed
+                delete-branch: true
+                team-reviewers: loki-team
+
+    updateMinio:
+        name: Update the Minio subchart
+        runs-on: "ubuntu-latest"
+        steps:
+            - name: Checkout
+              uses: actions/checkout@v2
+
+            - name: Install Updatecli
+              uses: updatecli/updatecli-action@v2
+
+            - name: Run Updatecli
+              id: update-minio
+              run: |
+                updatecli apply --config ${UPDATECLI_CONFIG_DIR}/minio.yaml
+                if ! git diff --exit-code > /dev/null; then
+                  echo "changed=true" >> "${GITHUB_OUTPUT}"
+                fi
+
+            - name: Create pull request
+              if: steps.update-minio.outputs.changed == 'true'
+              uses: peter-evans/create-pull-request@v5
+              with:
+                title: "[dependency] Update the Minio subchart"
+                body: "Updates the Minio subchart"
+                base: main
+                author: "${{ github.actor }} <${{ github.actor }}@users.noreply.github.com>"
+                committer: "GitHub <noreply@github.com>"
+                commit-message: Update minio
+                labels: dependencies
+                branch: chore/update-minio
+                delete-branch: true
+                team-reviewers: loki-team

.github/workflows/helm-ci.yml

@@ -0,0 +1,66 @@
+---
+name: helm-ci
+on:
+  pull_request:
+    paths:
+      - "charts/meta-monitoring/**"
+
+env:
+  CT_CONFIGFILE: charts/meta-monitoring/ct.yaml
+
+jobs:
+  call-lint:
+    name: Lint Helm Chart
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout Code
+        uses: actions/checkout@v3
+
+      - name: Lint Yaml
+        run: make helm-lint
+
+  # call-test:
+  #   name: Test Helm Chart
+  #   runs-on: ubuntu-latest
+  #   steps:
+  #     - name: Checkout
+  #       uses: actions/checkout@v3
+  #       with:
+  #         fetch-depth: 0
+
+  #     - name: Set up Helm
+  #       uses: azure/setup-helm@v3
+  #       with:
+  #         version: v3.8.2
+
+  #     # Python is required because `ct lint` runs Yamale (https://github.com/23andMe/Yamale) and
+  #     # yamllint (https://github.com/adrienverge/yamllint) which require Python
+  #     - name: Set up Python
+  #       uses: actions/setup-python@v4
+  #       with:
+  #         python-version: 3.7
+
+  #     - name: Set up chart-testing
+  #       uses: helm/chart-testing-action@v2.4.0
+
+  #     - name: Run chart-testing (list-changed)
+  #       id: list-changed
+  #       run: |
+  #         changed=$(ct list-changed --config "${CT_CONFIGFILE}")
+  #         if [[ -n "$changed" ]]; then
+  #           echo "changed=true" >> $GITHUB_OUTPUT
+  #         fi
+
+  #     - name: Run chart-testing (lint)
+  #       run: ct lint --config "${CT_CONFIGFILE}" --check-version-increment=false
+
+  #     - name: Create kind cluster
+  #       uses: helm/kind-action@v1.8.0
+  #       if: steps.list-changed.outputs.changed == 'true'
+  #       with:
+  #         config: tools/kind.config
+
+  #     - name: Run chart-testing (install)
+  #       run: |
+  #         changed=$(ct list-changed --config "${CT_CONFIGFILE}")
+  #         ct install --config "${CT_CONFIGFILE}"

Makefile

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

README.md

@@ -3,6 +3,8 @@
 This is a meta-monitoring chart for GEL, GEM and GET. It should be installed in a
 separate namespace next to GEM, GEL or GET installations.
 
+Note that this is pre-production software at the moment.
+
 ## Preparation
 
 Create a values.yaml file based on the [default one](../charts/meta-monitoring/values.yaml).
@@ -15,29 +17,54 @@ Create a values.yaml file based on the [default one](../charts/meta-monitoring/v
 
 ## Local and cloud modes
 
-The chart has 2 modes: local and cloud. In the local mode logs, metrics and traces are sent
+The chart has 2 modes: local and cloud. In the local mode logs, metrics and/or traces are sent
 to small Loki, Mimir and Tempo installations running in the meta-monitoring namespace.
 
 ![local mode](docs/images/Meta%20monitoring%20local.png)
 
-To enable local mode set `local.enabled` to true.
+To enable local mode set `local.<logs|metrics|traces>.enabled` to true.
 
-In the cloud mode the logs, metrics and traces are sent to
+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.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.
+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.
 
 ## Installation
 
 ```
-helm install -n meta -f values.yaml meta ./charts/meta-monitoring
+helm install -n meta --skip-crds -f values.yaml meta ./charts/meta-monitoring
 ```
 
+If the platform supports CRDs the `--skip-crds` option can be removed. However the CRDs are not used by this chart.
+
 For more instructions including how to update the chart go to the [installation](docs/installation.md) page.
 
+## Supported features
+
+- Specify which namespaces are monitored
+- Specify if logs, metrics or traces should be enabled for cloud or local
+- Specify the cluster name used for the logs, metrics and traces
+- 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
+  - metrics dashboards
+  - traces 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.
+
+## Caveats
+
+- The [loki.source.kubernetes](https://grafana.com/docs/agent/latest/flow/reference/components/loki.source.kubernetes/) component of the Grafana Agent is used to scrape Kubernetes log files. This component is marked experimental at the moment.
+- This has not been tested on Openshift yet.
+- The underlying Loki, Mimir and Tempo are at the default size installed by the Helm chart. This might need changing when monitoring bigger Loki, Mimir or Tempo installations.
+- MinIO is used as storage at the moment with a limited retention. At the moment this chart cannot be used for monitoring over longer periods.
+- Agent self monitoring is not done at the moment.
+
 ## Developer help topics
 
-- [update dependencies](docs/dev_update_dependencies.md)
+- [update dependencies](docs/dev_update_dependencies.md)

charts/meta-monitoring/Chart.lock

@@ -1,18 +1,18 @@
 dependencies:
 - name: loki
   repository: https://grafana.github.io/helm-charts
-  version: 5.8.0
-- name: grafana-agent
+  version: 5.47.2
+- name: alloy
   repository: https://grafana.github.io/helm-charts
-  version: 0.15.0
+  version: 0.1.1
 - name: mimir-distributed
   repository: https://grafana.github.io/helm-charts
-  version: 4.4.1
+  version: 5.3.0
 - name: tempo-distributed
   repository: https://grafana.github.io/helm-charts
-  version: 1.4.7
+  version: 1.9.2
 - name: minio
   repository: https://charts.min.io
-  version: 5.0.11
-digest: sha256:4b04084e6fe821c4d481017b2430f7c8cd782a5d60830dd3a24eb8f10a9ece09
-generated: "2023-06-29T14:25:07.247853+01:00"
+  version: 5.1.0
+digest: sha256:b9521eea011cdf82856ee909f3f42f98722393678799094de2307e89c92bc045
+generated: "2024-04-16T08:02:21.931525336Z"

charts/meta-monitoring/Chart.yaml

@@ -1,7 +1,6 @@
 apiVersion: v2
 name: meta-monitoring
 description: A Helm chart for meta monitoring Grafana Loki, Mimir and Tempo
-
 # A chart can be either an 'application' or a 'library' chart.
 #
 # Application charts are a collection of templates that can be packaged into versioned archives
@@ -11,38 +10,32 @@ description: A Helm chart for meta monitoring Grafana Loki, Mimir and Tempo
 # a dependency of application charts to inject those utilities and functions into the rendering
 # pipeline. Library charts do not define any templates and therefore cannot be deployed.
 type: application
-
 # This is the chart version. This version number should be incremented each time you make changes
 # to the chart and its templates, including the app version.
 # Versions are expected to follow Semantic Versioning (https://semver.org/)
 version: 0.0.1
-
 # This is the version number of the application being deployed. This version number should be
 # incremented each time you make changes to the application. Versions are not expected to
 # follow Semantic Versioning. They should reflect the version the application is using.
 # It is recommended to use it with quotes.
 appVersion: "0.0.1"
-
 dependencies:
 - name: loki
-  repository:  https://grafana.github.io/helm-charts
-  version: "5.8.0"
+  repository: https://grafana.github.io/helm-charts
+  version: "5.47.2"
   condition: local.logs.enabled
-- name: grafana-agent
-  repository:  https://grafana.github.io/helm-charts
-  version: "0.15.0"
+- name: alloy
+  repository: https://grafana.github.io/helm-charts
+  version: 0.1.1
 - name: mimir-distributed
-  repository:  https://grafana.github.io/helm-charts
-  version: "4.4.1"
+  repository: https://grafana.github.io/helm-charts
+  version: 5.3.0
   condition: local.metrics.enabled
 - name: tempo-distributed
-  repository:  https://grafana.github.io/helm-charts
-  version: "1.4.7"
+  repository: https://grafana.github.io/helm-charts
+  version: 1.9.2
   condition: local.traces.enabled
 - name: minio
   repository: https://charts.min.io
-  version: "5.0.11"
-  tags:
-  - local-logs
-  - local-metrics
-  - local-traces
+  version: 5.1.0
+  condition: local.minio.enabled

charts/meta-monitoring/Makefile

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

charts/meta-monitoring/ct.yaml

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

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

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

charts/meta-monitoring/src/dashboards/agent.json

@@ -0,0 +1,786 @@
+{
+   "annotations": {
+      "list": [ ]
+   },
+   "editable": true,
+   "gnetId": null,
+   "graphTooltip": 0,
+   "hideControls": false,
+   "links": [ ],
+   "refresh": "30s",
+   "rows": [
+      {
+         "collapse": false,
+         "height": "250px",
+         "panels": [
+            {
+               "aliasColors": { },
+               "bars": false,
+               "dashLength": 10,
+               "dashes": false,
+               "datasource": "$datasource",
+               "fill": 1,
+               "id": 1,
+               "legend": {
+                  "avg": false,
+                  "current": false,
+                  "max": false,
+                  "min": false,
+                  "show": true,
+                  "total": false,
+                  "values": false
+               },
+               "lines": true,
+               "linewidth": 1,
+               "links": [ ],
+               "nullPointMode": "null as zero",
+               "percentage": false,
+               "pointradius": 5,
+               "points": false,
+               "renderer": "flot",
+               "seriesOverrides": [ ],
+               "spaceLength": 10,
+               "span": 12,
+               "stack": false,
+               "steppedLine": false,
+               "styles": [
+                  {
+                     "alias": "Time",
+                     "dateFormat": "YYYY-MM-DD HH:mm:ss",
+                     "pattern": "Time",
+                     "type": "hidden"
+                  },
+                  {
+                     "alias": "Count",
+                     "colorMode": null,
+                     "colors": [ ],
+                     "dateFormat": "YYYY-MM-DD HH:mm:ss",
+                     "decimals": 2,
+                     "link": false,
+                     "linkTargetBlank": false,
+                     "linkTooltip": "Drill down",
+                     "linkUrl": "",
+                     "pattern": "Value #A",
+                     "thresholds": [ ],
+                     "type": "hidden",
+                     "unit": "short"
+                  },
+                  {
+                     "alias": "Uptime",
+                     "colorMode": null,
+                     "colors": [ ],
+                     "dateFormat": "YYYY-MM-DD HH:mm:ss",
+                     "decimals": 2,
+                     "link": false,
+                     "linkTargetBlank": false,
+                     "linkTooltip": "Drill down",
+                     "linkUrl": "",
+                     "pattern": "Value #B",
+                     "thresholds": [ ],
+                     "type": "number",
+                     "unit": "short"
+                  },
+                  {
+                     "alias": "Container",
+                     "colorMode": null,
+                     "colors": [ ],
+                     "dateFormat": "YYYY-MM-DD HH:mm:ss",
+                     "decimals": 2,
+                     "link": false,
+                     "linkTargetBlank": false,
+                     "linkTooltip": "Drill down",
+                     "linkUrl": "",
+                     "pattern": "container",
+                     "thresholds": [ ],
+                     "type": "number",
+                     "unit": "short"
+                  },
+                  {
+                     "alias": "Pod",
+                     "colorMode": null,
+                     "colors": [ ],
+                     "dateFormat": "YYYY-MM-DD HH:mm:ss",
+                     "decimals": 2,
+                     "link": false,
+                     "linkTargetBlank": false,
+                     "linkTooltip": "Drill down",
+                     "linkUrl": "",
+                     "pattern": "pod",
+                     "thresholds": [ ],
+                     "type": "number",
+                     "unit": "short"
+                  },
+                  {
+                     "alias": "Version",
+                     "colorMode": null,
+                     "colors": [ ],
+                     "dateFormat": "YYYY-MM-DD HH:mm:ss",
+                     "decimals": 2,
+                     "link": false,
+                     "linkTargetBlank": false,
+                     "linkTooltip": "Drill down",
+                     "linkUrl": "",
+                     "pattern": "version",
+                     "thresholds": [ ],
+                     "type": "number",
+                     "unit": "short"
+                  },
+                  {
+                     "alias": "",
+                     "colorMode": null,
+                     "colors": [ ],
+                     "dateFormat": "YYYY-MM-DD HH:mm:ss",
+                     "decimals": 2,
+                     "pattern": "/.*/",
+                     "thresholds": [ ],
+                     "type": "string",
+                     "unit": "short"
+                  }
+               ],
+               "targets": [
+                  {
+                     "expr": "count by (pod, container, version) (agent_build_info{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"$container\"})",
+                     "format": "table",
+                     "instant": true,
+                     "intervalFactor": 2,
+                     "legendFormat": "",
+                     "refId": "A",
+                     "step": 10
+                  },
+                  {
+                     "expr": "max by (pod, container) (time() - process_start_time_seconds{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"$container\"})",
+                     "format": "table",
+                     "instant": true,
+                     "intervalFactor": 2,
+                     "legendFormat": "",
+                     "refId": "B",
+                     "step": 10
+                  }
+               ],
+               "thresholds": [ ],
+               "timeFrom": null,
+               "timeShift": null,
+               "title": "Agent Stats",
+               "tooltip": {
+                  "shared": true,
+                  "sort": 2,
+                  "value_type": "individual"
+               },
+               "transform": "table",
+               "type": "table",
+               "xaxis": {
+                  "buckets": null,
+                  "mode": "time",
+                  "name": null,
+                  "show": true,
+                  "values": [ ]
+               },
+               "yaxes": [
+                  {
+                     "format": "short",
+                     "label": null,
+                     "logBase": 1,
+                     "max": null,
+                     "min": 0,
+                     "show": true
+                  },
+                  {
+                     "format": "short",
+                     "label": null,
+                     "logBase": 1,
+                     "max": null,
+                     "min": null,
+                     "show": false
+                  }
+               ]
+            }
+         ],
+         "repeat": null,
+         "repeatIteration": null,
+         "repeatRowId": null,
+         "showTitle": true,
+         "title": "Agent Stats",
+         "titleSize": "h6"
+      },
+      {
+         "collapse": false,
+         "height": "250px",
+         "panels": [
+            {
+               "aliasColors": { },
+               "bars": false,
+               "dashLength": 10,
+               "dashes": false,
+               "datasource": "$datasource",
+               "fill": 1,
+               "id": 2,
+               "legend": {
+                  "avg": false,
+                  "current": false,
+                  "max": false,
+                  "min": false,
+                  "show": true,
+                  "total": false,
+                  "values": false
+               },
+               "lines": true,
+               "linewidth": 1,
+               "links": [ ],
+               "nullPointMode": "null as zero",
+               "percentage": false,
+               "pointradius": 5,
+               "points": false,
+               "renderer": "flot",
+               "seriesOverrides": [ ],
+               "spaceLength": 10,
+               "span": 6,
+               "stack": false,
+               "steppedLine": false,
+               "targets": [
+                  {
+                     "expr": "sum(rate(prometheus_target_sync_length_seconds_sum{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"$container\"}[5m])) by (pod, scrape_job) * 1e3",
+                     "format": "time_series",
+                     "intervalFactor": 2,
+                     "legendFormat": "{{pod}}/{{scrape_job}}",
+                     "legendLink": null,
+                     "step": 10
+                  }
+               ],
+               "thresholds": [ ],
+               "timeFrom": null,
+               "timeShift": null,
+               "title": "Target Sync",
+               "tooltip": {
+                  "shared": true,
+                  "sort": 2,
+                  "value_type": "individual"
+               },
+               "type": "graph",
+               "xaxis": {
+                  "buckets": null,
+                  "mode": "time",
+                  "name": null,
+                  "show": true,
+                  "values": [ ]
+               },
+               "yaxes": [
+                  {
+                     "format": "ms",
+                     "label": null,
+                     "logBase": 1,
+                     "max": null,
+                     "min": 0,
+                     "show": true
+                  },
+                  {
+                     "format": "short",
+                     "label": null,
+                     "logBase": 1,
+                     "max": null,
+                     "min": null,
+                     "show": false
+                  }
+               ]
+            },
+            {
+               "aliasColors": { },
+               "bars": false,
+               "dashLength": 10,
+               "dashes": false,
+               "datasource": "$datasource",
+               "fill": 10,
+               "id": 3,
+               "legend": {
+                  "avg": false,
+                  "current": false,
+                  "max": false,
+                  "min": false,
+                  "show": true,
+                  "total": false,
+                  "values": false
+               },
+               "lines": true,
+               "linewidth": 0,
+               "links": [ ],
+               "nullPointMode": "null as zero",
+               "percentage": false,
+               "pointradius": 5,
+               "points": false,
+               "renderer": "flot",
+               "seriesOverrides": [ ],
+               "spaceLength": 10,
+               "span": 6,
+               "stack": true,
+               "steppedLine": false,
+               "targets": [
+                  {
+                     "expr": "sum by (pod) (prometheus_sd_discovered_targets{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"$container\"})",
+                     "format": "time_series",
+                     "intervalFactor": 2,
+                     "legendFormat": "{{pod}}",
+                     "legendLink": null,
+                     "step": 10
+                  }
+               ],
+               "thresholds": [ ],
+               "timeFrom": null,
+               "timeShift": null,
+               "title": "Targets",
+               "tooltip": {
+                  "shared": true,
+                  "sort": 2,
+                  "value_type": "individual"
+               },
+               "type": "graph",
+               "xaxis": {
+                  "buckets": null,
+                  "mode": "time",
+                  "name": null,
+                  "show": true,
+                  "values": [ ]
+               },
+               "yaxes": [
+                  {
+                     "format": "short",
+                     "label": null,
+                     "logBase": 1,
+                     "max": null,
+                     "min": 0,
+                     "show": true
+                  },
+                  {
+                     "format": "short",
+                     "label": null,
+                     "logBase": 1,
+                     "max": null,
+                     "min": null,
+                     "show": false
+                  }
+               ]
+            }
+         ],
+         "repeat": null,
+         "repeatIteration": null,
+         "repeatRowId": null,
+         "showTitle": true,
+         "title": "Prometheus Discovery",
+         "titleSize": "h6"
+      },
+      {
+         "collapse": false,
+         "height": "250px",
+         "panels": [
+            {
+               "aliasColors": { },
+               "bars": false,
+               "dashLength": 10,
+               "dashes": false,
+               "datasource": "$datasource",
+               "fill": 1,
+               "id": 4,
+               "legend": {
+                  "avg": false,
+                  "current": false,
+                  "max": false,
+                  "min": false,
+                  "show": true,
+                  "total": false,
+                  "values": false
+               },
+               "lines": true,
+               "linewidth": 1,
+               "links": [ ],
+               "nullPointMode": "null as zero",
+               "percentage": false,
+               "pointradius": 5,
+               "points": false,
+               "renderer": "flot",
+               "seriesOverrides": [ ],
+               "spaceLength": 10,
+               "span": 4,
+               "stack": false,
+               "steppedLine": false,
+               "targets": [
+                  {
+                     "expr": "rate(prometheus_target_interval_length_seconds_sum{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"$container\"}[5m])\n/\nrate(prometheus_target_interval_length_seconds_count{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"$container\"}[5m])\n* 1e3\n",
+                     "format": "time_series",
+                     "intervalFactor": 2,
+                     "legendFormat": "{{pod}} {{interval}} configured",
+                     "legendLink": null,
+                     "step": 10
+                  }
+               ],
+               "thresholds": [ ],
+               "timeFrom": null,
+               "timeShift": null,
+               "title": "Average Scrape Interval Duration",
+               "tooltip": {
+                  "shared": true,
+                  "sort": 2,
+                  "value_type": "individual"
+               },
+               "type": "graph",
+               "xaxis": {
+                  "buckets": null,
+                  "mode": "time",
+                  "name": null,
+                  "show": true,
+                  "values": [ ]
+               },
+               "yaxes": [
+                  {
+                     "format": "ms",
+                     "label": null,
+                     "logBase": 1,
+                     "max": null,
+                     "min": 0,
+                     "show": true
+                  },
+                  {
+                     "format": "short",
+                     "label": null,
+                     "logBase": 1,
+                     "max": null,
+                     "min": null,
+                     "show": false
+                  }
+               ]
+            },
+            {
+               "aliasColors": { },
+               "bars": false,
+               "dashLength": 10,
+               "dashes": false,
+               "datasource": "$datasource",
+               "fill": 10,
+               "id": 5,
+               "legend": {
+                  "avg": false,
+                  "current": false,
+                  "max": false,
+                  "min": false,
+                  "show": true,
+                  "total": false,
+                  "values": false
+               },
+               "lines": true,
+               "linewidth": 0,
+               "links": [ ],
+               "nullPointMode": "null as zero",
+               "percentage": false,
+               "pointradius": 5,
+               "points": false,
+               "renderer": "flot",
+               "seriesOverrides": [ ],
+               "spaceLength": 10,
+               "span": 4,
+               "stack": true,
+               "steppedLine": false,
+               "targets": [
+                  {
+                     "expr": "sum by (job) (rate(prometheus_target_scrapes_exceeded_sample_limit_total{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"$container\"}[1m]))",
+                     "format": "time_series",
+                     "intervalFactor": 2,
+                     "legendFormat": "exceeded sample limit: {{job}}",
+                     "legendLink": null,
+                     "step": 10
+                  },
+                  {
+                     "expr": "sum by (job) (rate(prometheus_target_scrapes_sample_duplicate_timestamp_total{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"$container\"}[1m]))",
+                     "format": "time_series",
+                     "intervalFactor": 2,
+                     "legendFormat": "duplicate timestamp: {{job}}",
+                     "legendLink": null,
+                     "step": 10
+                  },
+                  {
+                     "expr": "sum by (job) (rate(prometheus_target_scrapes_sample_out_of_bounds_total{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"$container\"}[1m]))",
+                     "format": "time_series",
+                     "intervalFactor": 2,
+                     "legendFormat": "out of bounds: {{job}}",
+                     "legendLink": null,
+                     "step": 10
+                  },
+                  {
+                     "expr": "sum by (job) (rate(prometheus_target_scrapes_sample_out_of_order_total{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"$container\"}[1m]))",
+                     "format": "time_series",
+                     "intervalFactor": 2,
+                     "legendFormat": "out of order: {{job}}",
+                     "legendLink": null,
+                     "step": 10
+                  }
+               ],
+               "thresholds": [ ],
+               "timeFrom": null,
+               "timeShift": null,
+               "title": "Scrape failures",
+               "tooltip": {
+                  "shared": true,
+                  "sort": 2,
+                  "value_type": "individual"
+               },
+               "type": "graph",
+               "xaxis": {
+                  "buckets": null,
+                  "mode": "time",
+                  "name": null,
+                  "show": true,
+                  "values": [ ]
+               },
+               "yaxes": [
+                  {
+                     "format": "short",
+                     "label": null,
+                     "logBase": 1,
+                     "max": null,
+                     "min": 0,
+                     "show": true
+                  },
+                  {
+                     "format": "short",
+                     "label": null,
+                     "logBase": 1,
+                     "max": null,
+                     "min": null,
+                     "show": false
+                  }
+               ]
+            },
+            {
+               "aliasColors": { },
+               "bars": false,
+               "dashLength": 10,
+               "dashes": false,
+               "datasource": "$datasource",
+               "fill": 10,
+               "id": 6,
+               "legend": {
+                  "avg": false,
+                  "current": false,
+                  "max": false,
+                  "min": false,
+                  "show": true,
+                  "total": false,
+                  "values": false
+               },
+               "lines": true,
+               "linewidth": 0,
+               "links": [ ],
+               "nullPointMode": "null as zero",
+               "percentage": false,
+               "pointradius": 5,
+               "points": false,
+               "renderer": "flot",
+               "seriesOverrides": [ ],
+               "spaceLength": 10,
+               "span": 4,
+               "stack": true,
+               "steppedLine": false,
+               "targets": [
+                  {
+                     "expr": "sum by (job, instance_group_name) (rate(agent_wal_samples_appended_total{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"$container\"}[5m]))",
+                     "format": "time_series",
+                     "intervalFactor": 2,
+                     "legendFormat": "{{job}} {{instance_group_name}}",
+                     "legendLink": null,
+                     "step": 10
+                  }
+               ],
+               "thresholds": [ ],
+               "timeFrom": null,
+               "timeShift": null,
+               "title": "Appended Samples",
+               "tooltip": {
+                  "shared": true,
+                  "sort": 2,
+                  "value_type": "individual"
+               },
+               "type": "graph",
+               "xaxis": {
+                  "buckets": null,
+                  "mode": "time",
+                  "name": null,
+                  "show": true,
+                  "values": [ ]
+               },
+               "yaxes": [
+                  {
+                     "format": "short",
+                     "label": null,
+                     "logBase": 1,
+                     "max": null,
+                     "min": 0,
+                     "show": true
+                  },
+                  {
+                     "format": "short",
+                     "label": null,
+                     "logBase": 1,
+                     "max": null,
+                     "min": null,
+                     "show": false
+                  }
+               ]
+            }
+         ],
+         "repeat": null,
+         "repeatIteration": null,
+         "repeatRowId": null,
+         "showTitle": true,
+         "title": "Prometheus Retrieval",
+         "titleSize": "h6"
+      }
+   ],
+   "schemaVersion": 14,
+   "style": "dark",
+   "tags": [
+      "grafana-agent-mixin"
+   ],
+   "templating": {
+      "list": [
+         {
+            "current": {
+               "text": "default",
+               "value": "default"
+            },
+            "hide": 0,
+            "label": "Data Source",
+            "name": "datasource",
+            "options": [ ],
+            "query": "prometheus",
+            "refresh": 1,
+            "regex": "",
+            "type": "datasource"
+         },
+         {
+            "allValue": ".+",
+            "current": {
+               "selected": true,
+               "text": "All",
+               "value": "$__all"
+            },
+            "datasource": "$datasource",
+            "hide": 0,
+            "includeAll": true,
+            "label": "cluster",
+            "multi": true,
+            "name": "cluster",
+            "options": [ ],
+            "query": "label_values(agent_build_info, cluster)",
+            "refresh": 1,
+            "regex": "",
+            "sort": 2,
+            "tagValuesQuery": "",
+            "tags": [ ],
+            "tagsQuery": "",
+            "type": "query",
+            "useTags": false
+         },
+         {
+            "allValue": ".+",
+            "current": {
+               "selected": true,
+               "text": "All",
+               "value": "$__all"
+            },
+            "datasource": "$datasource",
+            "hide": 0,
+            "includeAll": true,
+            "label": "namespace",
+            "multi": true,
+            "name": "namespace",
+            "options": [ ],
+            "query": "label_values(agent_build_info, namespace)",
+            "refresh": 1,
+            "regex": "",
+            "sort": 2,
+            "tagValuesQuery": "",
+            "tags": [ ],
+            "tagsQuery": "",
+            "type": "query",
+            "useTags": false
+         },
+         {
+            "allValue": ".+",
+            "current": {
+               "selected": true,
+               "text": "All",
+               "value": "$__all"
+            },
+            "datasource": "$datasource",
+            "hide": 0,
+            "includeAll": true,
+            "label": "container",
+            "multi": true,
+            "name": "container",
+            "options": [ ],
+            "query": "label_values(agent_build_info, container)",
+            "refresh": 1,
+            "regex": "",
+            "sort": 2,
+            "tagValuesQuery": "",
+            "tags": [ ],
+            "tagsQuery": "",
+            "type": "query",
+            "useTags": false
+         },
+         {
+            "allValue": "grafana-agent-.*",
+            "current": {
+               "selected": true,
+               "text": "All",
+               "value": "$__all"
+            },
+            "datasource": "$datasource",
+            "hide": 0,
+            "includeAll": true,
+            "label": "pod",
+            "multi": true,
+            "name": "pod",
+            "options": [ ],
+            "query": "label_values(agent_build_info{container=~\"$container\"}, pod)",
+            "refresh": 1,
+            "regex": "",
+            "sort": 2,
+            "tagValuesQuery": "",
+            "tags": [ ],
+            "tagsQuery": "",
+            "type": "query",
+            "useTags": false
+         }
+      ]
+   },
+   "time": {
+      "from": "now-1h",
+      "to": "now"
+   },
+   "timepicker": {
+      "refresh_intervals": [
+         "5s",
+         "10s",
+         "30s",
+         "1m",
+         "5m",
+         "15m",
+         "30m",
+         "1h",
+         "2h",
+         "1d"
+      ],
+      "time_options": [
+         "5m",
+         "15m",
+         "1h",
+         "6h",
+         "12h",
+         "24h",
+         "2d",
+         "7d",
+         "30d"
+      ]
+   },
+   "timezone": "",
+   "title": "Agent",
+   "uid": "",
+   "version": 0
+}

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

@@ -62,7 +62,6 @@
                         "expr": "sum(loki_compactor_pending_delete_requests_count{cluster=~\"$cluster\", namespace=~\"$namespace\"})",
                         "format": "time_series",
                         "instant": true,
-                        "intervalFactor": 2,
                         "refId": "A"
                      }
                   ],
@@ -138,7 +137,6 @@
                         "expr": "max(loki_compactor_oldest_pending_delete_request_age_seconds{cluster=~\"$cluster\", namespace=~\"$namespace\"})",
                         "format": "time_series",
                         "instant": true,
-                        "intervalFactor": 2,
                         "refId": "A"
                      }
                   ],
@@ -191,156 +189,145 @@
             "height": "250px",
             "panels": [
                {
-                  "aliasColors": { },
-                  "bars": false,
-                  "dashLength": 10,
-                  "dashes": false,
                   "datasource": "$datasource",
-                  "fill": 1,
-                  "id": 3,
-                  "legend": {
-                     "avg": false,
-                     "current": false,
-                     "max": false,
-                     "min": false,
-                     "show": true,
-                     "total": false,
-                     "values": false
+                  "fieldConfig": {
+                     "defaults": {
+                        "custom": {
+                           "drawStyle": "line",
+                           "fillOpacity": 10,
+                           "lineWidth": 1,
+                           "pointSize": 5,
+                           "showPoints": "never",
+                           "spanNulls": false,
+                           "stacking": {
+                              "group": "A",
+                              "mode": "none"
+                           }
+                        },
+                        "thresholds": {
+                           "mode": "absolute",
+                           "steps": [ ]
+                        },
+                        "unit": "short"
+                     },
+                     "overrides": [ ]
                   },
-                  "lines": true,
-                  "linewidth": 1,
+                  "id": 3,
                   "links": [ ],
-                  "nullPointMode": "null as zero",
-                  "percentage": false,
-                  "pointradius": 5,
-                  "points": false,
-                  "renderer": "flot",
-                  "seriesOverrides": [ ],
-                  "spaceLength": 10,
-                  "span": 6,
-                  "stack": false,
-                  "steppedLine": false,
+                  "options": {
+                     "legend": {
+                        "showLegend": true
+                     },
+                     "tooltip": {
+                        "mode": "single",
+                        "sort": "none"
+                     }
+                  },
+                  "span": 4,
+                  "targets": [
+                     {
+                        "expr": "(loki_compactor_delete_requests_received_total{cluster=~\"$cluster\", namespace=~\"$namespace\"} or on() vector(0)) - on () (loki_compactor_delete_requests_processed_total{cluster=~\"$cluster\", namespace=~\"$namespace\"} or on () vector(0))",
+                        "format": "time_series",
+                        "legendFormat": "in progress",
+                        "legendLink": null
+                     }
+                  ],
+                  "title": "# of Delete Requests (received - processed) ",
+                  "type": "timeseries"
+               },
+               {
+                  "datasource": "$datasource",
+                  "fieldConfig": {
+                     "defaults": {
+                        "custom": {
+                           "drawStyle": "line",
+                           "fillOpacity": 10,
+                           "lineWidth": 1,
+                           "pointSize": 5,
+                           "showPoints": "never",
+                           "spanNulls": false,
+                           "stacking": {
+                              "group": "A",
+                              "mode": "none"
+                           }
+                        },
+                        "thresholds": {
+                           "mode": "absolute",
+                           "steps": [ ]
+                        },
+                        "unit": "short"
+                     },
+                     "overrides": [ ]
+                  },
+                  "id": 4,
+                  "links": [ ],
+                  "options": {
+                     "legend": {
+                        "showLegend": true
+                     },
+                     "tooltip": {
+                        "mode": "single",
+                        "sort": "none"
+                     }
+                  },
+                  "span": 4,
                   "targets": [
                      {
                         "expr": "sum(increase(loki_compactor_delete_requests_received_total{cluster=~\"$cluster\", namespace=~\"$namespace\"}[1d]))",
                         "format": "time_series",
-                        "intervalFactor": 2,
                         "legendFormat": "received",
-                        "legendLink": null,
-                        "step": 10
+                        "legendLink": null
                      }
                   ],
-                  "thresholds": [ ],
-                  "timeFrom": null,
-                  "timeShift": null,
                   "title": "Delete Requests Received / Day",
-                  "tooltip": {
-                     "shared": true,
-                     "sort": 2,
-                     "value_type": "individual"
-                  },
-                  "type": "graph",
-                  "xaxis": {
-                     "buckets": null,
-                     "mode": "time",
-                     "name": null,
-                     "show": true,
-                     "values": [ ]
-                  },
-                  "yaxes": [
-                     {
-                        "format": "short",
-                        "label": null,
-                        "logBase": 1,
-                        "max": null,
-                        "min": 0,
-                        "show": true
-                     },
-                     {
-                        "format": "short",
-                        "label": null,
-                        "logBase": 1,
-                        "max": null,
-                        "min": null,
-                        "show": false
-                     }
-                  ]
+                  "type": "timeseries"
                },
                {
-                  "aliasColors": { },
-                  "bars": false,
-                  "dashLength": 10,
-                  "dashes": false,
                   "datasource": "$datasource",
-                  "fill": 1,
-                  "id": 4,
-                  "legend": {
-                     "avg": false,
-                     "current": false,
-                     "max": false,
-                     "min": false,
-                     "show": true,
-                     "total": false,
-                     "values": false
+                  "fieldConfig": {
+                     "defaults": {
+                        "custom": {
+                           "drawStyle": "line",
+                           "fillOpacity": 10,
+                           "lineWidth": 1,
+                           "pointSize": 5,
+                           "showPoints": "never",
+                           "spanNulls": false,
+                           "stacking": {
+                              "group": "A",
+                              "mode": "none"
+                           }
+                        },
+                        "thresholds": {
+                           "mode": "absolute",
+                           "steps": [ ]
+                        },
+                        "unit": "short"
+                     },
+                     "overrides": [ ]
                   },
-                  "lines": true,
-                  "linewidth": 1,
+                  "id": 5,
                   "links": [ ],
-                  "nullPointMode": "null as zero",
-                  "percentage": false,
-                  "pointradius": 5,
-                  "points": false,
-                  "renderer": "flot",
-                  "seriesOverrides": [ ],
-                  "spaceLength": 10,
-                  "span": 6,
-                  "stack": false,
-                  "steppedLine": false,
+                  "options": {
+                     "legend": {
+                        "showLegend": true
+                     },
+                     "tooltip": {
+                        "mode": "single",
+                        "sort": "none"
+                     }
+                  },
+                  "span": 4,
                   "targets": [
                      {
                         "expr": "sum(increase(loki_compactor_delete_requests_processed_total{cluster=~\"$cluster\", namespace=~\"$namespace\"}[1d]))",
                         "format": "time_series",
-                        "intervalFactor": 2,
                         "legendFormat": "processed",
-                        "legendLink": null,
-                        "step": 10
+                        "legendLink": null
                      }
                   ],
-                  "thresholds": [ ],
-                  "timeFrom": null,
-                  "timeShift": null,
                   "title": "Delete Requests Processed / Day",
-                  "tooltip": {
-                     "shared": true,
-                     "sort": 2,
-                     "value_type": "individual"
-                  },
-                  "type": "graph",
-                  "xaxis": {
-                     "buckets": null,
-                     "mode": "time",
-                     "name": null,
-                     "show": true,
-                     "values": [ ]
-                  },
-                  "yaxes": [
-                     {
-                        "format": "short",
-                        "label": null,
-                        "logBase": 1,
-                        "max": null,
-                        "min": 0,
-                        "show": true
-                     },
-                     {
-                        "format": "short",
-                        "label": null,
-                        "logBase": 1,
-                        "max": null,
-                        "min": null,
-                        "show": false
-                     }
-                  ]
+                  "type": "timeseries"
                }
             ],
             "repeat": null,
@@ -355,87 +342,152 @@
             "height": "250px",
             "panels": [
                {
-                  "aliasColors": { },
-                  "bars": false,
-                  "dashLength": 10,
-                  "dashes": false,
                   "datasource": "$datasource",
-                  "fill": 1,
-                  "id": 5,
-                  "legend": {
-                     "avg": false,
-                     "current": false,
-                     "max": false,
-                     "min": false,
-                     "show": true,
-                     "total": false,
-                     "values": false
+                  "fieldConfig": {
+                     "defaults": {
+                        "custom": {
+                           "drawStyle": "line",
+                           "fillOpacity": 10,
+                           "lineWidth": 1,
+                           "pointSize": 5,
+                           "showPoints": "never",
+                           "spanNulls": false,
+                           "stacking": {
+                              "group": "A",
+                              "mode": "none"
+                           }
+                        },
+                        "thresholds": {
+                           "mode": "absolute",
+                           "steps": [ ]
+                        },
+                        "unit": "short"
+                     },
+                     "overrides": [ ]
                   },
-                  "lines": true,
-                  "linewidth": 1,
+                  "id": 6,
                   "links": [ ],
-                  "nullPointMode": "null as zero",
-                  "percentage": false,
-                  "pointradius": 5,
-                  "points": false,
-                  "renderer": "flot",
-                  "seriesOverrides": [ ],
-                  "spaceLength": 10,
-                  "span": 12,
-                  "stack": false,
-                  "steppedLine": false,
+                  "options": {
+                     "legend": {
+                        "showLegend": true
+                     },
+                     "tooltip": {
+                        "mode": "single",
+                        "sort": "none"
+                     }
+                  },
+                  "span": 4,
                   "targets": [
                      {
-                        "expr": "sum(increase(loki_compactor_load_pending_requests_attempts_total{status=\"fail\", cluster=~\"$cluster\", namespace=~\"$namespace\"}[1h]))",
+                        "expr": "node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=~\"$cluster\", namespace=~\"$namespace\", container=\"compactor\"}",
                         "format": "time_series",
-                        "intervalFactor": 2,
-                        "legendFormat": "failures",
-                        "legendLink": null,
-                        "step": 10
+                        "legendFormat": "{{pod}}",
+                        "legendLink": null
                      }
                   ],
-                  "thresholds": [ ],
-                  "timeFrom": null,
-                  "timeShift": null,
-                  "title": "Failures in Loading Delete Requests / Hour",
-                  "tooltip": {
-                     "shared": true,
-                     "sort": 2,
-                     "value_type": "individual"
-                  },
-                  "type": "graph",
-                  "xaxis": {
-                     "buckets": null,
-                     "mode": "time",
-                     "name": null,
-                     "show": true,
-                     "values": [ ]
-                  },
-                  "yaxes": [
-                     {
-                        "format": "short",
-                        "label": null,
-                        "logBase": 1,
-                        "max": null,
-                        "min": 0,
-                        "show": true
+                  "title": "Compactor CPU usage",
+                  "type": "timeseries"
+               },
+               {
+                  "datasource": "$datasource",
+                  "fieldConfig": {
+                     "defaults": {
+                        "custom": {
+                           "drawStyle": "line",
+                           "fillOpacity": 10,
+                           "lineWidth": 1,
+                           "pointSize": 5,
+                           "showPoints": "never",
+                           "spanNulls": false,
+                           "stacking": {
+                              "group": "A",
+                              "mode": "none"
+                           }
+                        },
+                        "thresholds": {
+                           "mode": "absolute",
+                           "steps": [ ]
+                        },
+                        "unit": "short"
                      },
-                     {
-                        "format": "short",
-                        "label": null,
-                        "logBase": 1,
-                        "max": null,
-                        "min": null,
-                        "show": false
+                     "overrides": [ ]
+                  },
+                  "id": 7,
+                  "links": [ ],
+                  "options": {
+                     "legend": {
+                        "showLegend": true
+                     },
+                     "tooltip": {
+                        "mode": "single",
+                        "sort": "none"
                      }
-                  ]
+                  },
+                  "span": 4,
+                  "targets": [
+                     {
+                        "expr": "go_memstats_heap_inuse_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\", container=\"compactor\"} / 1024 / 1024 ",
+                        "format": "time_series",
+                        "legendFormat": " {{pod}} ",
+                        "legendLink": null
+                     }
+                  ],
+                  "title": "Compactor memory usage (MiB)",
+                  "type": "timeseries"
+               },
+               {
+                  "datasource": "$datasource",
+                  "fieldConfig": {
+                     "defaults": {
+                        "custom": {
+                           "drawStyle": "line",
+                           "fillOpacity": 10,
+                           "lineWidth": 1,
+                           "pointSize": 5,
+                           "showPoints": "never",
+                           "spanNulls": false,
+                           "stacking": {
+                              "group": "A",
+                              "mode": "none"
+                           }
+                        },
+                        "thresholds": {
+                           "mode": "absolute",
+                           "steps": [ ]
+                        },
+                        "unit": "short"
+                     },
+                     "overrides": [ ]
+                  },
+                  "id": 8,
+                  "links": [ ],
+                  "options": {
+                     "legend": {
+                        "showLegend": true
+                     },
+                     "tooltip": {
+                        "mode": "single",
+                        "sort": "none"
+                     }
+                  },
+                  "span": 4,
+                  "targets": [
+                     {
+                        "expr": "loki_boltdb_shipper_compact_tables_operation_duration_seconds{cluster=~\"$cluster\", namespace=~\"$namespace\"}",
+                        "format": "time_series",
+                        "legendFormat": "{{pod}}",
+                        "legendLink": null
+                     }
+                  ],
+                  "title": "Compaction run duration (seconds)",
+                  "type": "timeseries"
                }
             ],
             "repeat": null,
             "repeatIteration": null,
             "repeatRowId": null,
             "showTitle": true,
-            "title": "Failures",
+            "title": "Compactor",
             "titleSize": "h6"
          },
          {
@@ -443,87 +495,143 @@
             "height": "250px",
             "panels": [
                {
-                  "aliasColors": { },
-                  "bars": false,
-                  "dashLength": 10,
-                  "dashes": false,
                   "datasource": "$datasource",
-                  "fill": 1,
-                  "id": 6,
-                  "legend": {
-                     "avg": false,
-                     "current": false,
-                     "max": false,
-                     "min": false,
-                     "show": true,
-                     "total": false,
-                     "values": false
+                  "fieldConfig": {
+                     "defaults": {
+                        "custom": {
+                           "drawStyle": "line",
+                           "fillOpacity": 10,
+                           "lineWidth": 1,
+                           "pointSize": 5,
+                           "showPoints": "never",
+                           "spanNulls": false,
+                           "stacking": {
+                              "group": "A",
+                              "mode": "none"
+                           }
+                        },
+                        "thresholds": {
+                           "mode": "absolute",
+                           "steps": [ ]
+                        },
+                        "unit": "short"
+                     },
+                     "overrides": [ ]
                   },
-                  "lines": true,
-                  "linewidth": 1,
+                  "id": 9,
                   "links": [ ],
-                  "nullPointMode": "null as zero",
-                  "percentage": false,
-                  "pointradius": 5,
-                  "points": false,
-                  "renderer": "flot",
-                  "seriesOverrides": [ ],
-                  "spaceLength": 10,
-                  "span": 12,
-                  "stack": false,
-                  "steppedLine": false,
+                  "options": {
+                     "legend": {
+                        "showLegend": true
+                     },
+                     "tooltip": {
+                        "mode": "single",
+                        "sort": "none"
+                     }
+                  },
+                  "span": 6,
+                  "targets": [
+                     {
+                        "expr": "sum(increase(loki_compactor_load_pending_requests_attempts_total{status=\"fail\", cluster=~\"$cluster\", namespace=~\"$namespace\"}[1h]))",
+                        "format": "time_series",
+                        "legendFormat": "failures",
+                        "legendLink": null
+                     }
+                  ],
+                  "title": "Failures in Loading Delete Requests / Hour",
+                  "type": "timeseries"
+               },
+               {
+                  "datasource": "$datasource",
+                  "fieldConfig": {
+                     "defaults": {
+                        "custom": {
+                           "drawStyle": "line",
+                           "fillOpacity": 10,
+                           "lineWidth": 1,
+                           "pointSize": 5,
+                           "showPoints": "never",
+                           "spanNulls": false,
+                           "stacking": {
+                              "group": "A",
+                              "mode": "none"
+                           }
+                        },
+                        "thresholds": {
+                           "mode": "absolute",
+                           "steps": [ ]
+                        },
+                        "unit": "short"
+                     },
+                     "overrides": [ ]
+                  },
+                  "id": 10,
+                  "links": [ ],
+                  "options": {
+                     "legend": {
+                        "showLegend": true
+                     },
+                     "tooltip": {
+                        "mode": "single",
+                        "sort": "none"
+                     }
+                  },
+                  "span": 6,
                   "targets": [
                      {
                         "expr": "sum(rate(loki_compactor_deleted_lines{cluster=~\"$cluster\",job=~\"$namespace/(loki|enterprise-logs)-read\"}[$__rate_interval])) by (user)",
                         "format": "time_series",
-                        "intervalFactor": 2,
                         "legendFormat": "{{user}}",
-                        "legendLink": null,
-                        "step": 10
+                        "legendLink": null
                      }
                   ],
-                  "thresholds": [ ],
-                  "timeFrom": null,
-                  "timeShift": null,
                   "title": "Lines Deleted / Sec",
-                  "tooltip": {
-                     "shared": true,
-                     "sort": 2,
-                     "value_type": "individual"
-                  },
-                  "type": "graph",
-                  "xaxis": {
-                     "buckets": null,
-                     "mode": "time",
-                     "name": null,
-                     "show": true,
-                     "values": [ ]
-                  },
-                  "yaxes": [
-                     {
-                        "format": "short",
-                        "label": null,
-                        "logBase": 1,
-                        "max": null,
-                        "min": 0,
-                        "show": true
-                     },
-                     {
-                        "format": "short",
-                        "label": null,
-                        "logBase": 1,
-                        "max": null,
-                        "min": null,
-                        "show": false
-                     }
-                  ]
+                  "type": "timeseries"
                }
             ],
             "repeat": null,
             "repeatIteration": null,
             "repeatRowId": null,
             "showTitle": true,
-            "title": "Deleted lines",
+            "title": "Deletion metrics",
+            "titleSize": "h6"
+         },
+         {
+            "collapse": false,
+            "height": "250px",
+            "panels": [
+               {
+                  "datasource": "$loki_datasource",
+                  "id": 11,
+                  "span": 6,
+                  "targets": [
+                     {
+                        "expr": "{cluster=~\"$cluster\", namespace=~\"$namespace\", container=\"compactor\"} |~ \"Started processing delete request|delete request for user marked as processed\" | logfmt | line_format \"{{.ts}} user={{.user}} delete_request_id={{.delete_request_id}} msg={{.msg}}\" ",
+                        "refId": "A"
+                     }
+                  ],
+                  "title": "In progress/finished",
+                  "type": "logs"
+               },
+               {
+                  "datasource": "$loki_datasource",
+                  "id": 12,
+                  "span": 6,
+                  "targets": [
+                     {
+                        "expr": "{cluster=~\"$cluster\", namespace=~\"$namespace\", container=\"compactor\"} |~ \"delete request for user added\" | logfmt | line_format \"{{.ts}} user={{.user}} query='{{.query}}'\"",
+                        "refId": "A"
+                     }
+                  ],
+                  "title": "Requests",
+                  "type": "logs"
+               }
+            ],
+            "repeat": null,
+            "repeatIteration": null,
+            "repeatRowId": null,
+            "showTitle": true,
+            "title": "List of deletion requests",
             "titleSize": "h6"
          }
       ],
@@ -540,7 +648,7 @@
                   "value": "default"
                },
                "hide": 0,
-               "label": "Data Source",
+               "label": "Data source",
                "name": "datasource",
                "options": [ ],
                "query": "prometheus",

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

@@ -6,7 +6,6 @@
       "gnetId": null,
       "graphTooltip": 0,
       "hideControls": false,
-      "id": 8,
       "iteration": 1583185057230,
       "links": [
          {
@@ -78,7 +77,7 @@
                "sort": 0,
                "value_type": "individual"
             },
-            "type": "graph",
+            "type": "timeseries",
             "xaxis": {
                "buckets": null,
                "mode": "time",
@@ -165,7 +164,7 @@
                "sort": 0,
                "value_type": "individual"
             },
-            "type": "graph",
+            "type": "timeseries",
             "xaxis": {
                "buckets": null,
                "mode": "time",
@@ -251,7 +250,7 @@
                "sort": 0,
                "value_type": "individual"
             },
-            "type": "graph",
+            "type": "timeseries",
             "xaxis": {
                "buckets": null,
                "mode": "time",
@@ -337,7 +336,7 @@
                "sort": 0,
                "value_type": "individual"
             },
-            "type": "graph",
+            "type": "timeseries",
             "xaxis": {
                "buckets": null,
                "mode": "time",
@@ -423,7 +422,7 @@
                "sort": 0,
                "value_type": "individual"
             },
-            "type": "graph",
+            "type": "timeseries",
             "xaxis": {
                "buckets": null,
                "mode": "time",
@@ -509,7 +508,7 @@
                "sort": 0,
                "value_type": "individual"
             },
-            "type": "graph",
+            "type": "timeseries",
             "xaxis": {
                "buckets": null,
                "mode": "time",
@@ -596,7 +595,7 @@
                "sort": 0,
                "value_type": "individual"
             },
-            "type": "graph",
+            "type": "timeseries",
             "xaxis": {
                "buckets": null,
                "mode": "time",
@@ -683,7 +682,7 @@
                "sort": 0,
                "value_type": "individual"
             },
-            "type": "graph",
+            "type": "timeseries",
             "xaxis": {
                "buckets": null,
                "mode": "time",
@@ -719,7 +718,7 @@
             "bars": false,
             "dashLength": 10,
             "dashes": false,
-            "datasource": "$logs",
+            "datasource": "$loki_datasource",
             "fill": 1,
             "fillGradient": 0,
             "gridPos": {
@@ -788,7 +787,7 @@
                "sort": 2,
                "value_type": "individual"
             },
-            "type": "graph",
+            "type": "timeseries",
             "xaxis": {
                "buckets": null,
                "mode": "time",
@@ -820,7 +819,7 @@
             }
          },
          {
-            "datasource": "$logs",
+            "datasource": "$loki_datasource",
             "gridPos": {
                "h": 19,
                "w": 24,
@@ -862,7 +861,7 @@
                   "value": "default"
                },
                "hide": 0,
-               "label": "Data Source",
+               "label": "Data source",
                "name": "datasource",
                "options": [ ],
                "query": "prometheus",
@@ -919,7 +918,7 @@
             {
                "hide": 0,
                "label": null,
-               "name": "logs",
+               "name": "loki_datasource",
                "options": [ ],
                "query": "loki",
                "refresh": 1,

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

@@ -1,41 +1,27 @@
 {
       "annotations": {
-         "list": [
-            {
-               "builtIn": 1,
-               "datasource": "-- Grafana --",
-               "enable": true,
-               "hide": true,
-               "iconColor": "rgba(0, 211, 255, 1)",
-               "name": "Annotations & Alerts",
-               "target": {
-                  "limit": 100,
-                  "matchAny": false,
-                  "tags": [ ],
-                  "type": "dashboard"
-               },
-               "type": "dashboard"
-            },
-            {
-               "datasource": "${datasource}",
-               "enable": false,
-               "expr": "sum by (tenant) (changes(loki_ruler_wal_prometheus_tsdb_wal_truncations_total{tenant=~\"${tenant}\"}[$__rate_interval]))",
-               "iconColor": "red",
-               "name": "WAL Truncations",
-               "target": {
-                  "queryType": "Azure Monitor",
-                  "refId": "Anno"
-               },
-               "titleFormat": "{{tenant}}"
-            }
-         ]
+         "list": [ ]
       },
       "editable": true,
       "fiscalYearStartMonth": 0,
       "gnetId": null,
       "graphTooltip": 0,
+      "hideControls": false,
       "iteration": 1635347545534,
-      "links": [ ],
+      "links": [
+         {
+            "asDropdown": true,
+            "icon": "external link",
+            "includeVars": true,
+            "keepTime": true,
+            "tags": [
+               "loki"
+            ],
+            "targetBlank": false,
+            "title": "Loki Dashboards",
+            "type": "dashboards"
+         }
+      ],
       "liveNow": false,
       "panels": [
          {
@@ -599,59 +585,139 @@
             "type": "timeseries"
          }
       ],
-      "schemaVersion": 31,
+      "refresh": "10s",
+      "rows": [ ],
+      "schemaVersion": 14,
       "style": "dark",
-      "tags": [ ],
+      "tags": [
+         "loki"
+      ],
       "templating": {
          "list": [
             {
-               "description": null,
-               "error": null,
+               "current": {
+                  "text": "default",
+                  "value": "default"
+               },
                "hide": 0,
-               "includeAll": false,
-               "label": "Datasource",
-               "multi": false,
+               "label": "Data source",
                "name": "datasource",
                "options": [ ],
                "query": "prometheus",
-               "queryValue": "",
                "refresh": 1,
                "regex": "",
-               "skipUrlSync": false,
                "type": "datasource"
             },
             {
                "allValue": null,
-               "datasource": "${datasource}",
-               "definition": "label_values(loki_ruler_wal_samples_appended_total, tenant)",
-               "description": null,
-               "error": null,
+               "current": {
+                  "text": "prod",
+                  "value": "prod"
+               },
+               "datasource": "$datasource",
+               "hide": 0,
+               "includeAll": false,
+               "label": "cluster",
+               "multi": false,
+               "name": "cluster",
+               "options": [ ],
+               "query": "label_values(loki_build_info, cluster)",
+               "refresh": 1,
+               "regex": "",
+               "sort": 2,
+               "tagValuesQuery": "",
+               "tags": [ ],
+               "tagsQuery": "",
+               "type": "query",
+               "useTags": false
+            },
+            {
+               "allValue": null,
+               "current": {
+                  "text": "prod",
+                  "value": "prod"
+               },
+               "datasource": "$datasource",
+               "hide": 0,
+               "includeAll": false,
+               "label": "namespace",
+               "multi": false,
+               "name": "namespace",
+               "options": [ ],
+               "query": "label_values(loki_build_info{cluster=~\"$cluster\"}, namespace)",
+               "refresh": 1,
+               "regex": "",
+               "sort": 2,
+               "tagValuesQuery": "",
+               "tags": [ ],
+               "tagsQuery": "",
+               "type": "query",
+               "useTags": false
+            },
+            {
+               "hide": 0,
+               "label": null,
+               "name": "loki_datasource",
+               "options": [ ],
+               "query": "loki",
+               "refresh": 1,
+               "regex": "",
+               "type": "datasource"
+            },
+            {
+               "allValue": ".+",
+               "current": { },
+               "datasource": "$datasource",
                "hide": 0,
                "includeAll": true,
-               "label": "Tenant",
-               "multi": true,
+               "label": null,
+               "multi": false,
                "name": "tenant",
                "options": [ ],
-               "query": {
-                  "query": "label_values(loki_ruler_wal_samples_appended_total, tenant)",
-                  "refId": "StandardVariableQuery"
-               },
-               "refresh": 2,
-               "regex": "",
-               "skipUrlSync": false,
-               "sort": 0,
-               "type": "query"
+               "query": "query_result(sum by (id) (grafanacloud_logs_instance_info) and sum(label_replace(loki_tenant:active_streams{cluster=\"$cluster\",namespace=\"$namespace\"},\"id\",\"$1\",\"tenant\",\"(.*)\")) by(id))",
+               "refresh": 0,
+               "regex": "/\"([^\"]+)\"/",
+               "sort": 1,
+               "tagValuesQuery": "",
+               "tags": [ ],
+               "tagsQuery": "",
+               "type": "query",
+               "useTags": false
             }
          ]
       },
       "time": {
-         "from": "now-6h",
+         "from": "now-1h",
          "to": "now"
       },
-      "timepicker": { },
-      "timezone": "",
-      "title": "Recording Rules",
-      "uid": "2xKA_ZK7k",
-      "version": 9,
+      "timepicker": {
+         "refresh_intervals": [
+            "5s",
+            "10s",
+            "30s",
+            "1m",
+            "5m",
+            "15m",
+            "30m",
+            "1h",
+            "2h",
+            "1d"
+         ],
+         "time_options": [
+            "5m",
+            "15m",
+            "1h",
+            "6h",
+            "12h",
+            "24h",
+            "2d",
+            "7d",
+            "30d"
+         ]
+      },
+      "timezone": "utc",
+      "title": "Loki / Recording Rules",
+      "uid": "recording-rules",
+      "version": 0,
       "weekStart": ""
    }

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

@@ -6,7 +6,6 @@
       "gnetId": null,
       "graphTooltip": 0,
       "hideControls": false,
-      "id": 68,
       "iteration": 1588704280892,
       "links": [
          {
@@ -103,7 +102,7 @@
                "sort": 0,
                "value_type": "individual"
             },
-            "type": "graph",
+            "type": "timeseries",
             "xaxis": {
                "buckets": null,
                "mode": "time",
@@ -199,7 +198,7 @@
                "sort": 0,
                "value_type": "individual"
             },
-            "type": "graph",
+            "type": "timeseries",
             "xaxis": {
                "buckets": null,
                "mode": "time",
@@ -294,7 +293,7 @@
                "sort": 0,
                "value_type": "individual"
             },
-            "type": "graph",
+            "type": "timeseries",
             "xaxis": {
                "buckets": null,
                "mode": "time",
@@ -390,7 +389,7 @@
                "sort": 0,
                "value_type": "individual"
             },
-            "type": "graph",
+            "type": "timeseries",
             "xaxis": {
                "buckets": null,
                "mode": "time",
@@ -486,7 +485,7 @@
                "sort": 2,
                "value_type": "individual"
             },
-            "type": "graph",
+            "type": "timeseries",
             "xaxis": {
                "buckets": null,
                "mode": "time",
@@ -567,17 +566,17 @@
             "steppedLine": false,
             "targets": [
                {
-                  "expr": "histogram_quantile(0.99, sum by (le) (job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-write\", route=~\"api_prom_push|loki_api_v1_push\", cluster=~\"$cluster\"})) * 1e3",
+                  "expr": "histogram_quantile(0.99, sum by (le) (cluster_job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-write\", route=~\"api_prom_push|loki_api_v1_push\", cluster=~\"$cluster\"})) * 1e3",
                   "legendFormat": ".99",
                   "refId": "A"
                },
                {
-                  "expr": "histogram_quantile(0.75, sum by (le) (job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-write\", route=~\"api_prom_push|loki_api_v1_push\", cluster=~\"$cluster\"})) * 1e3",
+                  "expr": "histogram_quantile(0.75, sum by (le) (cluster_job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-write\", route=~\"api_prom_push|loki_api_v1_push\", cluster=~\"$cluster\"})) * 1e3",
                   "legendFormat": ".9",
                   "refId": "B"
                },
                {
-                  "expr": "histogram_quantile(0.5, sum by (le) (job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-write\", route=~\"api_prom_push|loki_api_v1_push\", cluster=~\"$cluster\"})) * 1e3",
+                  "expr": "histogram_quantile(0.5, sum by (le) (cluster_job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-write\", route=~\"api_prom_push|loki_api_v1_push\", cluster=~\"$cluster\"})) * 1e3",
                   "legendFormat": ".5",
                   "refId": "C"
                }
@@ -592,7 +591,7 @@
                "sort": 0,
                "value_type": "individual"
             },
-            "type": "graph",
+            "type": "timeseries",
             "xaxis": {
                "buckets": null,
                "mode": "time",
@@ -673,17 +672,17 @@
             "steppedLine": false,
             "targets": [
                {
-                  "expr": "histogram_quantile(0.99, sum by (le) (job:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-write\", cluster=~\"$cluster\"})) * 1e3",
+                  "expr": "histogram_quantile(0.99, sum by (le) (cluster_job:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-write\", cluster=~\"$cluster\"})) * 1e3",
                   "legendFormat": ".99",
                   "refId": "A"
                },
                {
-                  "expr": "histogram_quantile(0.9, sum by (le) (job:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-write\", cluster=~\"$cluster\"})) * 1e3",
+                  "expr": "histogram_quantile(0.9, sum by (le) (cluster_job:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-write\", cluster=~\"$cluster\"})) * 1e3",
                   "legendFormat": ".9",
                   "refId": "B"
                },
                {
-                  "expr": "histogram_quantile(0.5, sum by (le) (job:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-write\", cluster=~\"$cluster\"})) * 1e3",
+                  "expr": "histogram_quantile(0.5, sum by (le) (cluster_job:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-write\", cluster=~\"$cluster\"})) * 1e3",
                   "legendFormat": ".5",
                   "refId": "C"
                }
@@ -698,7 +697,7 @@
                "sort": 0,
                "value_type": "individual"
             },
-            "type": "graph",
+            "type": "timeseries",
             "xaxis": {
                "buckets": null,
                "mode": "time",
@@ -779,7 +778,7 @@
             "steppedLine": false,
             "targets": [
                {
-                  "expr": "sum(rate(loki_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(loki|enterprise-logs)-write\", status_code!~\"5[0-9]{2}\"}[5m])) by (route)\n/\nsum(rate(loki_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(loki|enterprise-logs)-write\"}[5m])) by (route)",
+                  "expr": "sum(rate(loki_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(loki|enterprise-logs)-write\", status_code!~\"5[0-9]{2}\"}[$__rate_interval])) by (route)\n/\nsum(rate(loki_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(loki|enterprise-logs)-write\"}[$__rate_interval])) by (route) > 0",
                   "interval": "",
                   "legendFormat": "{{route}}",
                   "refId": "A"
@@ -795,7 +794,7 @@
                "sort": 0,
                "value_type": "individual"
             },
-            "type": "graph",
+            "type": "timeseries",
             "xaxis": {
                "buckets": null,
                "mode": "time",
@@ -877,18 +876,18 @@
             "steppedLine": false,
             "targets": [
                {
-                  "expr": "histogram_quantile(0.99, sum by (le) (job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-write\", route=\"/logproto.Pusher/Push\", cluster=~\"$cluster\"})) * 1e3",
+                  "expr": "histogram_quantile(0.99, sum by (le) (cluster_job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-write\", route=\"/logproto.Pusher/Push\", cluster=~\"$cluster\"})) * 1e3",
                   "legendFormat": ".99",
                   "refId": "A"
                },
                {
-                  "expr": "histogram_quantile(0.9, sum by (le) (job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-write\", route=\"/logproto.Pusher/Push\", cluster=~\"$cluster\"})) * 1e3",
+                  "expr": "histogram_quantile(0.9, sum by (le) (cluster_job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-write\", route=\"/logproto.Pusher/Push\", cluster=~\"$cluster\"})) * 1e3",
                   "hide": false,
                   "legendFormat": ".9",
                   "refId": "B"
                },
                {
-                  "expr": "histogram_quantile(0.5, sum by (le) (job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-write\", route=\"/logproto.Pusher/Push\", cluster=~\"$cluster\"})) * 1e3",
+                  "expr": "histogram_quantile(0.5, sum by (le) (cluster_job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-write\", route=\"/logproto.Pusher/Push\", cluster=~\"$cluster\"})) * 1e3",
                   "hide": false,
                   "legendFormat": ".5",
                   "refId": "C"
@@ -904,7 +903,7 @@
                "sort": 0,
                "value_type": "individual"
             },
-            "type": "graph",
+            "type": "timeseries",
             "xaxis": {
                "buckets": null,
                "mode": "time",
@@ -985,7 +984,7 @@
             "steppedLine": false,
             "targets": [
                {
-                  "expr": "sum(rate(loki_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(loki|enterprise-logs)-write\", status_code!~\"5[0-9]{2}\", route=\"/logproto.Pusher/Push\"}[5m])) by (route)\n/\nsum(rate(loki_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(loki|enterprise-logs)-write\", route=\"/logproto.Pusher/Push\"}[5m])) by (route)",
+                  "expr": "sum(rate(loki_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(loki|enterprise-logs)-write\", status_code!~\"5[0-9]{2}\", route=\"/logproto.Pusher/Push\"}[$__rate_interval])) by (route)\n/\nsum(rate(loki_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(loki|enterprise-logs)-write\", route=\"/logproto.Pusher/Push\"}[$__rate_interval])) by (route) > 0",
                   "interval": "",
                   "legendFormat": "{{route}}",
                   "refId": "A"
@@ -1001,7 +1000,7 @@
                "sort": 0,
                "value_type": "individual"
             },
-            "type": "graph",
+            "type": "timeseries",
             "xaxis": {
                "buckets": null,
                "mode": "time",
@@ -1085,17 +1084,17 @@
             "steppedLine": false,
             "targets": [
                {
-                  "expr": "histogram_quantile(0.99, sum by (le,route) (job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-read\", route=~\"api_prom_query|api_prom_labels|api_prom_label_name_values|loki_api_v1_query|loki_api_v1_query_range|loki_api_v1_label|loki_api_v1_label_name_values\", cluster=\"$cluster\"}))",
+                  "expr": "histogram_quantile(0.99, sum by (le,route) (cluster_job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-read\", route=~\"api_prom_query|api_prom_labels|api_prom_label_name_values|loki_api_v1_query|loki_api_v1_query_range|loki_api_v1_label|loki_api_v1_label_name_values\", cluster=\"$cluster\"}))",
                   "legendFormat": "{{route}}-.99",
                   "refId": "A"
                },
                {
-                  "expr": "histogram_quantile(0.9, sum by (le,route) (job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-read\", route=~\"api_prom_query|api_prom_labels|api_prom_label_name_values|loki_api_v1_query|loki_api_v1_query_range|loki_api_v1_label|loki_api_v1_label_name_values\", cluster=\"$cluster\"}))",
+                  "expr": "histogram_quantile(0.9, sum by (le,route) (cluster_job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-read\", route=~\"api_prom_query|api_prom_labels|api_prom_label_name_values|loki_api_v1_query|loki_api_v1_query_range|loki_api_v1_label|loki_api_v1_label_name_values\", cluster=\"$cluster\"}))",
                   "legendFormat": "{{route}}-.9",
                   "refId": "B"
                },
                {
-                  "expr": "histogram_quantile(0.5, sum by (le,route) (job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-read\", route=~\"api_prom_query|api_prom_labels|api_prom_label_name_values|loki_api_v1_query|loki_api_v1_query_range|loki_api_v1_label|loki_api_v1_label_name_values\", cluster=\"$cluster\"}))",
+                  "expr": "histogram_quantile(0.5, sum by (le,route) (cluster_job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-read\", route=~\"api_prom_query|api_prom_labels|api_prom_label_name_values|loki_api_v1_query|loki_api_v1_query_range|loki_api_v1_label|loki_api_v1_label_name_values\", cluster=\"$cluster\"}))",
                   "legendFormat": "{{route}}-.5",
                   "refId": "C"
                }
@@ -1110,7 +1109,7 @@
                "sort": 0,
                "value_type": "individual"
             },
-            "type": "graph",
+            "type": "timeseries",
             "xaxis": {
                "buckets": null,
                "mode": "time",
@@ -1191,17 +1190,17 @@
             "steppedLine": false,
             "targets": [
                {
-                  "expr": "histogram_quantile(0.99, sum by (le,route) (job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-read\", route=~\"api_prom_query|api_prom_labels|api_prom_label_name_values|loki_api_v1_query|loki_api_v1_query_range|loki_api_v1_label|loki_api_v1_label_name_values\", cluster=\"$cluster\"})) * 1e3",
+                  "expr": "histogram_quantile(0.99, sum by (le,route) (cluster_job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-read\", route=~\"api_prom_query|api_prom_labels|api_prom_label_name_values|loki_api_v1_query|loki_api_v1_query_range|loki_api_v1_label|loki_api_v1_label_name_values\", cluster=\"$cluster\"})) * 1e3",
                   "legendFormat": ".99-{{route}}",
                   "refId": "A"
                },
                {
-                  "expr": "histogram_quantile(0.9, sum by (le,route) (job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-read\", route=~\"api_prom_query|api_prom_labels|api_prom_label_name_values|loki_api_v1_query|loki_api_v1_query_range|loki_api_v1_label|loki_api_v1_label_name_values\", cluster=\"$cluster\"})) * 1e3",
+                  "expr": "histogram_quantile(0.9, sum by (le,route) (cluster_job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-read\", route=~\"api_prom_query|api_prom_labels|api_prom_label_name_values|loki_api_v1_query|loki_api_v1_query_range|loki_api_v1_label|loki_api_v1_label_name_values\", cluster=\"$cluster\"})) * 1e3",
                   "legendFormat": ".9-{{route}}",
                   "refId": "B"
                },
                {
-                  "expr": "histogram_quantile(0.5, sum by (le,route) (job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-read\", route=~\"api_prom_query|api_prom_labels|api_prom_label_name_values|loki_api_v1_query|loki_api_v1_query_range|loki_api_v1_label|loki_api_v1_label_name_values\", cluster=\"$cluster\"})) * 1e3",
+                  "expr": "histogram_quantile(0.5, sum by (le,route) (cluster_job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-read\", route=~\"api_prom_query|api_prom_labels|api_prom_label_name_values|loki_api_v1_query|loki_api_v1_query_range|loki_api_v1_label|loki_api_v1_label_name_values\", cluster=\"$cluster\"})) * 1e3",
                   "legendFormat": ".5-{{route}}",
                   "refId": "C"
                }
@@ -1216,7 +1215,7 @@
                "sort": 0,
                "value_type": "individual"
             },
-            "type": "graph",
+            "type": "timeseries",
             "xaxis": {
                "buckets": null,
                "mode": "time",
@@ -1297,7 +1296,7 @@
             "steppedLine": false,
             "targets": [
                {
-                  "expr": "sum(rate(loki_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(loki|enterprise-logs)-read\", status_code!~\"5[0-9]{2}\"}[5m])) by (route)\n/\nsum(rate(loki_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(loki|enterprise-logs)-read\"}[5m])) by (route)",
+                  "expr": "sum(rate(loki_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(loki|enterprise-logs)-read\", status_code!~\"5[0-9]{2}\"}[$__rate_interval])) by (route)\n/\nsum(rate(loki_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(loki|enterprise-logs)-read\"}[$__rate_interval])) by (route) > 0",
                   "interval": "",
                   "legendFormat": "{{route}}",
                   "refId": "A"
@@ -1313,7 +1312,7 @@
                "sort": 0,
                "value_type": "individual"
             },
-            "type": "graph",
+            "type": "timeseries",
             "xaxis": {
                "buckets": null,
                "mode": "time",
@@ -1396,17 +1395,17 @@
             "steppedLine": false,
             "targets": [
                {
-                  "expr": "histogram_quantile(0.99, sum by (le,route) (job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-write\", route=~\"/logproto.Querier/Query|/logproto.Querier/Label|/logproto.Querier/Series|/logproto.Querier/QuerySample|/logproto.Querier/GetChunkIDs\", cluster=\"$cluster\"})) * 1e3",
+                  "expr": "histogram_quantile(0.99, sum by (le,route) (cluster_job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-write\", route=~\"/logproto.Querier/Query|/logproto.Querier/Label|/logproto.Querier/Series|/logproto.Querier/QuerySample|/logproto.Querier/GetChunkIDs\", cluster=\"$cluster\"})) * 1e3",
                   "legendFormat": ".99-{{route}}",
                   "refId": "A"
                },
                {
-                  "expr": "histogram_quantile(0.9, sum by (le,route) (job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-write\", route=~\"/logproto.Querier/Query|/logproto.Querier/Label|/logproto.Querier/Series|/logproto.Querier/QuerySample|/logproto.Querier/GetChunkIDs\", cluster=\"$cluster\"})) * 1e3",
+                  "expr": "histogram_quantile(0.9, sum by (le,route) (cluster_job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-write\", route=~\"/logproto.Querier/Query|/logproto.Querier/Label|/logproto.Querier/Series|/logproto.Querier/QuerySample|/logproto.Querier/GetChunkIDs\", cluster=\"$cluster\"})) * 1e3",
                   "legendFormat": ".9-{{route}}",
                   "refId": "B"
                },
                {
-                  "expr": "histogram_quantile(0.5, sum by (le,route) (job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-write\", route=~\"/logproto.Querier/Query|/logproto.Querier/Label|/logproto.Querier/Series|/logproto.Querier/QuerySample|/logproto.Querier/GetChunkIDs\", cluster=\"$cluster\"})) * 1e3",
+                  "expr": "histogram_quantile(0.5, sum by (le,route) (cluster_job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-write\", route=~\"/logproto.Querier/Query|/logproto.Querier/Label|/logproto.Querier/Series|/logproto.Querier/QuerySample|/logproto.Querier/GetChunkIDs\", cluster=\"$cluster\"})) * 1e3",
                   "legendFormat": ".5-{{route}}",
                   "refId": "C"
                }
@@ -1421,7 +1420,7 @@
                "sort": 0,
                "value_type": "individual"
             },
-            "type": "graph",
+            "type": "timeseries",
             "xaxis": {
                "buckets": null,
                "mode": "time",
@@ -1502,7 +1501,7 @@
             "steppedLine": false,
             "targets": [
                {
-                  "expr": "sum(rate(loki_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(loki|enterprise-logs)-write\", status_code!~\"5[0-9]{2}\", route=~\"/logproto.Querier/Query|/logproto.Querier/Label|/logproto.Querier/Series|/logproto.Querier/QuerySample|/logproto.Querier/GetChunkIDs\"}[5m])) by (route)\n/\nsum(rate(loki_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(loki|enterprise-logs)-write\", route=~\"/logproto.Querier/Query|/logproto.Querier/Label|/logproto.Querier/Series|/logproto.Querier/QuerySample|/logproto.Querier/GetChunkIDs\"}[5m])) by (route)",
+                  "expr": "sum(rate(loki_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(loki|enterprise-logs)-write\", status_code!~\"5[0-9]{2}\", route=~\"/logproto.Querier/Query|/logproto.Querier/Label|/logproto.Querier/Series|/logproto.Querier/QuerySample|/logproto.Querier/GetChunkIDs\"}[$__rate_interval])) by (route)\n/\nsum(rate(loki_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(loki|enterprise-logs)-write\", route=~\"/logproto.Querier/Query|/logproto.Querier/Label|/logproto.Querier/Series|/logproto.Querier/QuerySample|/logproto.Querier/GetChunkIDs\"}[$__rate_interval])) by (route) > 0",
                   "interval": "",
                   "legendFormat": "{{route}}",
                   "refId": "A"
@@ -1518,7 +1517,7 @@
                "sort": 0,
                "value_type": "individual"
             },
-            "type": "graph",
+            "type": "timeseries",
             "xaxis": {
                "buckets": null,
                "mode": "time",
@@ -1619,7 +1618,7 @@
                      "sort": 0,
                      "value_type": "individual"
                   },
-                  "type": "graph",
+                  "type": "timeseries",
                   "xaxis": {
                      "buckets": null,
                      "mode": "time",
@@ -1800,9 +1799,9 @@
                   "steppedLine": false,
                   "targets": [
                      {
-                        "expr": "node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"(loki|enterprise-logs)-write.*\"}",
+                        "expr": "sum by(pod) (rate(container_cpu_usage_seconds_total{cluster=~\"$cluster\", namespace=~\"$namespace\", pod=~\"(loki|enterprise-logs)-write.*\"}[$__rate_interval]))",
                         "intervalFactor": 3,
-                        "legendFormat": "{{pod}}-{{container}}",
+                        "legendFormat": "{{pod}}",
                         "refId": "A"
                      }
                   ],
@@ -1816,7 +1815,7 @@
                      "sort": 2,
                      "value_type": "individual"
                   },
-                  "type": "graph",
+                  "type": "timeseries",
                   "xaxis": {
                      "buckets": null,
                      "mode": "time",
@@ -1908,7 +1907,7 @@
                      "sort": 2,
                      "value_type": "individual"
                   },
-                  "type": "graph",
+                  "type": "timeseries",
                   "xaxis": {
                      "buckets": null,
                      "mode": "time",
@@ -1944,7 +1943,7 @@
                   "bars": true,
                   "dashLength": 10,
                   "dashes": false,
-                  "datasource": "$logs",
+                  "datasource": "$loki_datasource",
                   "fill": 1,
                   "fillGradient": 0,
                   "gridPos": {
@@ -2000,7 +1999,7 @@
                      "sort": 2,
                      "value_type": "individual"
                   },
-                  "type": "graph",
+                  "type": "timeseries",
                   "xaxis": {
                      "buckets": null,
                      "mode": "time",
@@ -2032,7 +2031,7 @@
                   }
                },
                {
-                  "datasource": "$logs",
+                  "datasource": "$loki_datasource",
                   "gridPos": {
                      "h": 18,
                      "w": 12,
@@ -2049,7 +2048,7 @@
                   "panels": [ ],
                   "targets": [
                      {
-                        "expr": "{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(loki|enterprise-logs)-write\"} | logfmt | level=\"error\"",
+                        "expr": "{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(loki|enterprise-logs)-write\"} |= \"level=error\"",
                         "refId": "A"
                      }
                   ],
@@ -2100,7 +2099,7 @@
                   "steppedLine": false,
                   "targets": [
                      {
-                        "expr": "sum(rate(loki_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(loki|enterprise-logs)-write\", status_code!~\"5[0-9]{2}\"}[5m])) by (route)\n/\nsum(rate(loki_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(loki|enterprise-logs)-write\"}[5m])) by (route)",
+                        "expr": "sum(rate(loki_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(loki|enterprise-logs)-write\", status_code!~\"5[0-9]{2}\"}[$__rate_interval])) by (route)\n/\nsum(rate(loki_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(loki|enterprise-logs)-write\"}[$__rate_interval])) by (route) > 0",
                         "interval": "",
                         "intervalFactor": 1,
                         "legendFormat": "{{route}}",
@@ -2117,7 +2116,7 @@
                      "sort": 2,
                      "value_type": "individual"
                   },
-                  "type": "graph",
+                  "type": "timeseries",
                   "xaxis": {
                      "buckets": null,
                      "mode": "time",
@@ -2190,9 +2189,9 @@
                   "steppedLine": false,
                   "targets": [
                      {
-                        "expr": "sum(rate(loki_distributor_ingester_append_failures_total{cluster=\"$cluster\", namespace=\"$namespace\"}[5m])) by (ingester)",
+                        "expr": "sum(rate(loki_distributor_ingester_append_failures_total{cluster=\"$cluster\", namespace=\"$namespace\"}[5m])) by (pod)",
                         "intervalFactor": 1,
-                        "legendFormat": "{{ingester}}",
+                        "legendFormat": "{{pod}}",
                         "refId": "A"
                      }
                   ],
@@ -2206,7 +2205,7 @@
                      "sort": 2,
                      "value_type": "individual"
                   },
-                  "type": "graph",
+                  "type": "timeseries",
                   "xaxis": {
                      "buckets": null,
                      "mode": "time",
@@ -2295,7 +2294,7 @@
                      "sort": 2,
                      "value_type": "individual"
                   },
-                  "type": "graph",
+                  "type": "timeseries",
                   "xaxis": {
                      "buckets": null,
                      "mode": "time",
@@ -2384,7 +2383,7 @@
                      "sort": 2,
                      "value_type": "individual"
                   },
-                  "type": "graph",
+                  "type": "timeseries",
                   "xaxis": {
                      "buckets": null,
                      "mode": "time",
@@ -2491,7 +2490,7 @@
                      "sort": 0,
                      "value_type": "individual"
                   },
-                  "type": "graph",
+                  "type": "timeseries",
                   "xaxis": {
                      "buckets": null,
                      "mode": "time",
@@ -2582,7 +2581,7 @@
                      "sort": 0,
                      "value_type": "individual"
                   },
-                  "type": "graph",
+                  "type": "timeseries",
                   "xaxis": {
                      "buckets": null,
                      "mode": "time",
@@ -2698,7 +2697,7 @@
                      "sort": 0,
                      "value_type": "individual"
                   },
-                  "type": "graph",
+                  "type": "timeseries",
                   "xaxis": {
                      "buckets": null,
                      "mode": "time",
@@ -2851,7 +2850,7 @@
                      "sort": 0,
                      "value_type": "individual"
                   },
-                  "type": "graph",
+                  "type": "timeseries",
                   "xaxis": {
                      "buckets": null,
                      "mode": "time",
@@ -3007,9 +3006,9 @@
                   "steppedLine": false,
                   "targets": [
                      {
-                        "expr": "node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"(loki|enterprise-logs)-read.*\"}",
+                        "expr": "sum by(pod) (rate(container_cpu_usage_seconds_total{cluster=~\"$cluster\", namespace=~\"$namespace\", pod=~\"(loki|enterprise-logs)-read.*\"}[$__rate_interval]))",
                         "intervalFactor": 3,
-                        "legendFormat": "{{pod}}-{{container}}",
+                        "legendFormat": "{{pod}}",
                         "refId": "A"
                      }
                   ],
@@ -3023,7 +3022,7 @@
                      "sort": 2,
                      "value_type": "individual"
                   },
-                  "type": "graph",
+                  "type": "timeseries",
                   "xaxis": {
                      "buckets": null,
                      "mode": "time",
@@ -3115,7 +3114,7 @@
                      "sort": 2,
                      "value_type": "individual"
                   },
-                  "type": "graph",
+                  "type": "timeseries",
                   "xaxis": {
                      "buckets": null,
                      "mode": "time",
@@ -3151,7 +3150,7 @@
                   "bars": true,
                   "dashLength": 10,
                   "dashes": false,
-                  "datasource": "$logs",
+                  "datasource": "$loki_datasource",
                   "fill": 1,
                   "fillGradient": 0,
                   "gridPos": {
@@ -3207,7 +3206,7 @@
                      "sort": 2,
                      "value_type": "individual"
                   },
-                  "type": "graph",
+                  "type": "timeseries",
                   "xaxis": {
                      "buckets": null,
                      "mode": "time",
@@ -3239,7 +3238,7 @@
                   }
                },
                {
-                  "datasource": "$logs",
+                  "datasource": "$loki_datasource",
                   "gridPos": {
                      "h": 18,
                      "w": 18,
@@ -3256,7 +3255,7 @@
                   "panels": [ ],
                   "targets": [
                      {
-                        "expr": "{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(loki|enterprise-logs)-read\"} | logfmt | level=\"error\"",
+                        "expr": "{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(loki|enterprise-logs)-read\"} |= \"level=error\"",
                         "refId": "A"
                      }
                   ],
@@ -3307,7 +3306,7 @@
                   "steppedLine": false,
                   "targets": [
                      {
-                        "expr": "sum(rate(loki_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(loki|enterprise-logs)-read\", status_code!~\"5[0-9]{2}\"}[1m])) by (route)\n/\nsum(rate(loki_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(loki|enterprise-logs)-read\"}[1m])) by (route)",
+                        "expr": "sum(rate(loki_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(loki|enterprise-logs)-read\", status_code!~\"5[0-9]{2}\"}[$__rate_interval])) by (route)\n/\nsum(rate(loki_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(loki|enterprise-logs)-read\"}[$__rate_interval])) by (route) > 0",
                         "interval": "",
                         "intervalFactor": 1,
                         "legendFormat": "{{route}}",
@@ -3324,7 +3323,7 @@
                      "sort": 2,
                      "value_type": "individual"
                   },
-                  "type": "graph",
+                  "type": "timeseries",
                   "xaxis": {
                      "buckets": null,
                      "mode": "time",
@@ -3444,7 +3443,7 @@
                      "sort": 2,
                      "value_type": "individual"
                   },
-                  "type": "graph",
+                  "type": "timeseries",
                   "xaxis": {
                      "buckets": null,
                      "mode": "time",
@@ -3536,7 +3535,7 @@
                      "sort": 2,
                      "value_type": "individual"
                   },
-                  "type": "graph",
+                  "type": "timeseries",
                   "xaxis": {
                      "buckets": null,
                      "mode": "time",
@@ -3656,7 +3655,7 @@
                      "sort": 2,
                      "value_type": "individual"
                   },
-                  "type": "graph",
+                  "type": "timeseries",
                   "xaxis": {
                      "buckets": null,
                      "mode": "time",
@@ -3748,7 +3747,7 @@
                      "sort": 2,
                      "value_type": "individual"
                   },
-                  "type": "graph",
+                  "type": "timeseries",
                   "xaxis": {
                      "buckets": null,
                      "mode": "time",
@@ -3862,7 +3861,7 @@
                      "sort": 2,
                      "value_type": "individual"
                   },
-                  "type": "graph",
+                  "type": "timeseries",
                   "xaxis": {
                      "buckets": null,
                      "mode": "time",
@@ -3965,7 +3964,7 @@
                      "sort": 2,
                      "value_type": "individual"
                   },
-                  "type": "graph",
+                  "type": "timeseries",
                   "xaxis": {
                      "buckets": null,
                      "mode": "time",
@@ -4068,7 +4067,7 @@
                      "sort": 2,
                      "value_type": "individual"
                   },
-                  "type": "graph",
+                  "type": "timeseries",
                   "xaxis": {
                      "buckets": null,
                      "mode": "time",
@@ -4166,7 +4165,7 @@
                      "sort": 2,
                      "value_type": "individual"
                   },
-                  "type": "graph",
+                  "type": "timeseries",
                   "xaxis": {
                      "buckets": null,
                      "mode": "time",
@@ -4256,7 +4255,7 @@
                      "sort": 2,
                      "value_type": "individual"
                   },
-                  "type": "graph",
+                  "type": "timeseries",
                   "xaxis": {
                      "buckets": null,
                      "mode": "time",
@@ -4346,7 +4345,7 @@
                      "sort": 2,
                      "value_type": "individual"
                   },
-                  "type": "graph",
+                  "type": "timeseries",
                   "xaxis": {
                      "buckets": null,
                      "mode": "time",
@@ -4436,7 +4435,7 @@
                      "sort": 2,
                      "value_type": "individual"
                   },
-                  "type": "graph",
+                  "type": "timeseries",
                   "xaxis": {
                      "buckets": null,
                      "mode": "time",
@@ -4526,7 +4525,7 @@
                      "sort": 2,
                      "value_type": "individual"
                   },
-                  "type": "graph",
+                  "type": "timeseries",
                   "xaxis": {
                      "buckets": null,
                      "mode": "time",
@@ -4646,7 +4645,7 @@
                      "sort": 2,
                      "value_type": "individual"
                   },
-                  "type": "graph",
+                  "type": "timeseries",
                   "xaxis": {
                      "buckets": null,
                      "mode": "time",
@@ -4738,7 +4737,7 @@
                      "sort": 2,
                      "value_type": "individual"
                   },
-                  "type": "graph",
+                  "type": "timeseries",
                   "xaxis": {
                      "buckets": null,
                      "mode": "time",
@@ -4826,7 +4825,7 @@
                   "steppedLine": false,
                   "targets": [
                      {
-                        "expr": "sum(rate(cortex_dynamo_failures_total{cluster=\"$cluster\", namespace=\"$namespace\"}[5m]))",
+                        "expr": "sum(rate(loki_dynamo_failures_total{cluster=\"$cluster\", namespace=\"$namespace\"}[5m]))",
                         "refId": "A"
                      }
                   ],
@@ -4840,7 +4839,7 @@
                      "sort": 0,
                      "value_type": "individual"
                   },
-                  "type": "graph",
+                  "type": "timeseries",
                   "xaxis": {
                      "buckets": null,
                      "mode": "time",
@@ -4912,7 +4911,7 @@
                   "steppedLine": false,
                   "targets": [
                      {
-                        "expr": "sum(rate(cortex_dynamo_consumed_capacity_total{cluster=\"$cluster\", namespace=\"$namespace\"}[5m]))",
+                        "expr": "sum(rate(loki_dynamo_consumed_capacity_total{cluster=\"$cluster\", namespace=\"$namespace\"}[5m]))",
                         "refId": "A"
                      }
                   ],
@@ -4926,7 +4925,7 @@
                      "sort": 0,
                      "value_type": "individual"
                   },
-                  "type": "graph",
+                  "type": "timeseries",
                   "xaxis": {
                      "buckets": null,
                      "mode": "time",
@@ -4998,7 +4997,7 @@
                   "steppedLine": false,
                   "targets": [
                      {
-                        "expr": "sum(rate(cortex_dynamo_throttled_total{cluster=\"$cluster\", namespace=\"$namespace\"}[5m]))",
+                        "expr": "sum(rate(loki_dynamo_throttled_total{cluster=\"$cluster\", namespace=\"$namespace\"}[5m]))",
                         "refId": "A"
                      }
                   ],
@@ -5012,7 +5011,7 @@
                      "sort": 0,
                      "value_type": "individual"
                   },
-                  "type": "graph",
+                  "type": "timeseries",
                   "xaxis": {
                      "buckets": null,
                      "mode": "time",
@@ -5084,7 +5083,7 @@
                   "steppedLine": false,
                   "targets": [
                      {
-                        "expr": "sum(rate(cortex_dynamo_dropped_requests_total{cluster=\"$cluster\", namespace=\"$namespace\"}[5m]))",
+                        "expr": "sum(rate(loki_dynamo_dropped_requests_total{cluster=\"$cluster\", namespace=\"$namespace\"}[5m]))",
                         "refId": "A"
                      }
                   ],
@@ -5098,7 +5097,7 @@
                      "sort": 0,
                      "value_type": "individual"
                   },
-                  "type": "graph",
+                  "type": "timeseries",
                   "xaxis": {
                      "buckets": null,
                      "mode": "time",
@@ -5170,17 +5169,17 @@
                   "steppedLine": false,
                   "targets": [
                      {
-                        "expr": "histogram_quantile(.99, sum(rate(cortex_dynamo_query_pages_count{cluster=\"$cluster\", namespace=\"$namespace\"}[5m])))",
+                        "expr": "histogram_quantile(.99, sum(rate(loki_dynamo_query_pages_count{cluster=\"$cluster\", namespace=\"$namespace\"}[5m])))",
                         "legendFormat": ".99",
                         "refId": "A"
                      },
                      {
-                        "expr": "histogram_quantile(.9, sum(rate(cortex_dynamo_query_pages_count{cluster=\"$cluster\", namespace=\"$namespace\"}[5m])))",
+                        "expr": "histogram_quantile(.9, sum(rate(loki_dynamo_query_pages_count{cluster=\"$cluster\", namespace=\"$namespace\"}[5m])))",
                         "legendFormat": ".9",
                         "refId": "B"
                      },
                      {
-                        "expr": "histogram_quantile(.5, sum(rate(cortex_dynamo_query_pages_count{cluster=\"$cluster\", namespace=\"$namespace\"}[5m])))",
+                        "expr": "histogram_quantile(.5, sum(rate(loki_dynamo_query_pages_count{cluster=\"$cluster\", namespace=\"$namespace\"}[5m])))",
                         "legendFormat": ".5",
                         "refId": "C"
                      }
@@ -5195,7 +5194,7 @@
                      "sort": 0,
                      "value_type": "individual"
                   },
-                  "type": "graph",
+                  "type": "timeseries",
                   "xaxis": {
                      "buckets": null,
                      "mode": "time",
@@ -5270,19 +5269,19 @@
                   "steppedLine": false,
                   "targets": [
                      {
-                        "expr": "histogram_quantile(.99, sum(rate(cortex_dynamo_request_duration_seconds_bucket{cluster=\"$cluster\", namespace=\"$namespace\"}[5m])) by (operation, le))",
+                        "expr": "histogram_quantile(.99, sum(rate(loki_dynamo_request_duration_seconds_bucket{cluster=\"$cluster\", namespace=\"$namespace\"}[5m])) by (operation, le))",
                         "intervalFactor": 1,
                         "legendFormat": ".99-{{operation}}",
                         "refId": "A"
                      },
                      {
-                        "expr": "histogram_quantile(.9, sum(rate(cortex_dynamo_request_duration_seconds_bucket{cluster=\"$cluster\", namespace=\"$namespace\"}[5m])) by (operation, le))",
+                        "expr": "histogram_quantile(.9, sum(rate(loki_dynamo_request_duration_seconds_bucket{cluster=\"$cluster\", namespace=\"$namespace\"}[5m])) by (operation, le))",
                         "hide": false,
                         "legendFormat": ".9-{{operation}}",
                         "refId": "B"
                      },
                      {
-                        "expr": "histogram_quantile(.5, sum(rate(cortex_dynamo_request_duration_seconds_bucket{cluster=\"$cluster\", namespace=\"$namespace\"}[5m])) by (operation, le))",
+                        "expr": "histogram_quantile(.5, sum(rate(loki_dynamo_request_duration_seconds_bucket{cluster=\"$cluster\", namespace=\"$namespace\"}[5m])) by (operation, le))",
                         "hide": false,
                         "legendFormat": ".5-{{operation}}",
                         "refId": "C"
@@ -5298,7 +5297,7 @@
                      "sort": 2,
                      "value_type": "individual"
                   },
-                  "type": "graph",
+                  "type": "timeseries",
                   "xaxis": {
                      "buckets": null,
                      "mode": "time",
@@ -5373,7 +5372,7 @@
                   "steppedLine": false,
                   "targets": [
                      {
-                        "expr": "sum(rate(cortex_dynamo_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\"}[5m])) by (status_code, operation)",
+                        "expr": "sum(rate(loki_dynamo_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\"}[5m])) by (status_code, operation)",
                         "intervalFactor": 1,
                         "legendFormat": "{{status_code}}-{{operation}}",
                         "refId": "A"
@@ -5389,7 +5388,7 @@
                      "sort": 2,
                      "value_type": "individual"
                   },
-                  "type": "graph",
+                  "type": "timeseries",
                   "xaxis": {
                      "buckets": null,
                      "mode": "time",
@@ -5508,7 +5507,7 @@
                      "sort": 2,
                      "value_type": "individual"
                   },
-                  "type": "graph",
+                  "type": "timeseries",
                   "xaxis": {
                      "buckets": null,
                      "mode": "time",
@@ -5599,7 +5598,7 @@
                      "sort": 2,
                      "value_type": "individual"
                   },
-                  "type": "graph",
+                  "type": "timeseries",
                   "xaxis": {
                      "buckets": null,
                      "mode": "time",
@@ -5718,7 +5717,7 @@
                      "sort": 2,
                      "value_type": "individual"
                   },
-                  "type": "graph",
+                  "type": "timeseries",
                   "xaxis": {
                      "buckets": null,
                      "mode": "time",
@@ -5809,7 +5808,7 @@
                      "sort": 2,
                      "value_type": "individual"
                   },
-                  "type": "graph",
+                  "type": "timeseries",
                   "xaxis": {
                      "buckets": null,
                      "mode": "time",
@@ -5928,7 +5927,7 @@
                      "sort": 2,
                      "value_type": "individual"
                   },
-                  "type": "graph",
+                  "type": "timeseries",
                   "xaxis": {
                      "buckets": null,
                      "mode": "time",
@@ -6019,7 +6018,7 @@
                      "sort": 2,
                      "value_type": "individual"
                   },
-                  "type": "graph",
+                  "type": "timeseries",
                   "xaxis": {
                      "buckets": null,
                      "mode": "time",
@@ -6071,7 +6070,7 @@
                   "value": "default"
                },
                "hide": 0,
-               "label": "Data Source",
+               "label": "Data source",
                "name": "datasource",
                "options": [ ],
                "query": "prometheus",
@@ -6082,7 +6081,7 @@
             {
                "hide": 0,
                "label": null,
-               "name": "logs",
+               "name": "loki_datasource",
                "options": [ ],
                "query": "loki",
                "refresh": 1,
@@ -6170,4 +6169,4 @@
       "title": "Loki / Operational",
       "uid": "operational",
       "version": 0
-   }
+   }

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

@@ -33,116 +33,237 @@
                      "3xx": "#6ED0E0",
                      "4xx": "#EF843C",
                      "5xx": "#E24D42",
+                     "OK": "#7EB26D",
+                     "cancel": "#A9A9A9",
                      "error": "#E24D42",
                      "success": "#7EB26D"
                   },
-                  "bars": false,
-                  "dashLength": 10,
-                  "dashes": false,
                   "datasource": "$datasource",
+                  "fieldConfig": {
+                     "defaults": {
+                        "custom": {
+                           "drawStyle": "line",
+                           "fillOpacity": 100,
+                           "lineWidth": 0,
+                           "pointSize": 5,
+                           "showPoints": "never",
+                           "spanNulls": false,
+                           "stacking": {
+                              "group": "A",
+                              "mode": "normal"
+                           }
+                        },
+                        "min": 0,
+                        "thresholds": {
+                           "mode": "absolute",
+                           "steps": [ ]
+                        },
+                        "unit": "short"
+                     },
+                     "overrides": [
+                        {
+                           "matcher": {
+                              "id": "byName",
+                              "options": "1xx"
+                           },
+                           "properties": [
+                              {
+                                 "id": "color",
+                                 "value": {
+                                    "fixedColor": "#EAB839",
+                                    "mode": "fixed"
+                                 }
+                              }
+                           ]
+                        },
+                        {
+                           "matcher": {
+                              "id": "byName",
+                              "options": "2xx"
+                           },
+                           "properties": [
+                              {
+                                 "id": "color",
+                                 "value": {
+                                    "fixedColor": "#7EB26D",
+                                    "mode": "fixed"
+                                 }
+                              }
+                           ]
+                        },
+                        {
+                           "matcher": {
+                              "id": "byName",
+                              "options": "3xx"
+                           },
+                           "properties": [
+                              {
+                                 "id": "color",
+                                 "value": {
+                                    "fixedColor": "#6ED0E0",
+                                    "mode": "fixed"
+                                 }
+                              }
+                           ]
+                        },
+                        {
+                           "matcher": {
+                              "id": "byName",
+                              "options": "4xx"
+                           },
+                           "properties": [
+                              {
+                                 "id": "color",
+                                 "value": {
+                                    "fixedColor": "#EF843C",
+                                    "mode": "fixed"
+                                 }
+                              }
+                           ]
+                        },
+                        {
+                           "matcher": {
+                              "id": "byName",
+                              "options": "5xx"
+                           },
+                           "properties": [
+                              {
+                                 "id": "color",
+                                 "value": {
+                                    "fixedColor": "#E24D42",
+                                    "mode": "fixed"
+                                 }
+                              }
+                           ]
+                        },
+                        {
+                           "matcher": {
+                              "id": "byName",
+                              "options": "OK"
+                           },
+                           "properties": [
+                              {
+                                 "id": "color",
+                                 "value": {
+                                    "fixedColor": "#7EB26D",
+                                    "mode": "fixed"
+                                 }
+                              }
+                           ]
+                        },
+                        {
+                           "matcher": {
+                              "id": "byName",
+                              "options": "cancel"
+                           },
+                           "properties": [
+                              {
+                                 "id": "color",
+                                 "value": {
+                                    "fixedColor": "#A9A9A9",
+                                    "mode": "fixed"
+                                 }
+                              }
+                           ]
+                        },
+                        {
+                           "matcher": {
+                              "id": "byName",
+                              "options": "error"
+                           },
+                           "properties": [
+                              {
+                                 "id": "color",
+                                 "value": {
+                                    "fixedColor": "#E24D42",
+                                    "mode": "fixed"
+                                 }
+                              }
+                           ]
+                        },
+                        {
+                           "matcher": {
+                              "id": "byName",
+                              "options": "success"
+                           },
+                           "properties": [
+                              {
+                                 "id": "color",
+                                 "value": {
+                                    "fixedColor": "#7EB26D",
+                                    "mode": "fixed"
+                                 }
+                              }
+                           ]
+                        }
+                     ]
+                  },
                   "fill": 10,
                   "id": 1,
-                  "legend": {
-                     "avg": false,
-                     "current": false,
-                     "max": false,
-                     "min": false,
-                     "show": true,
-                     "total": false,
-                     "values": false
-                  },
-                  "lines": true,
                   "linewidth": 0,
                   "links": [ ],
-                  "nullPointMode": "null as zero",
-                  "percentage": false,
-                  "pointradius": 5,
-                  "points": false,
-                  "renderer": "flot",
-                  "seriesOverrides": [ ],
-                  "spaceLength": 10,
-                  "span": 6,
+                  "options": {
+                     "legend": {
+                        "showLegend": true
+                     },
+                     "tooltip": {
+                        "mode": "single",
+                        "sort": "none"
+                     }
+                  },
+                  "span": 4,
                   "stack": true,
-                  "steppedLine": false,
                   "targets": [
                      {
-                        "expr": "sum by (status) (\n  label_replace(label_replace(rate(loki_request_duration_seconds_count{cluster=~\"$cluster\",job=~\"($namespace)/(loki|enterprise-logs)-read\", route=~\"loki_api_v1_series|api_prom_series|api_prom_query|api_prom_label|api_prom_label_name_values|loki_api_v1_query|loki_api_v1_query_range|loki_api_v1_labels|loki_api_v1_label_name_values\"}[$__rate_interval]),\n  \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n  \"status\", \"${1}\", \"status_code\", \"([a-z]+)\"))\n",
+                        "expr": "sum by (status) (\n  label_replace(label_replace(rate(loki_request_duration_seconds_count{cluster=~\"$cluster\",job=~\"($namespace)/(loki|enterprise-logs)-read\", route=~\"loki_api_v1_series|api_prom_series|api_prom_query|api_prom_label|api_prom_label_name_values|loki_api_v1_query|loki_api_v1_query_range|loki_api_v1_labels|loki_api_v1_label_name_values\"}[$__rate_interval]),\n  \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n  \"status\", \"${1}\", \"status_code\", \"([a-zA-Z]+)\"))\n",
                         "format": "time_series",
-                        "intervalFactor": 2,
                         "legendFormat": "{{status}}",
-                        "refId": "A",
-                        "step": 10
+                        "refId": "A"
                      }
                   ],
-                  "thresholds": [ ],
-                  "timeFrom": null,
-                  "timeShift": null,
                   "title": "QPS",
-                  "tooltip": {
-                     "shared": true,
-                     "sort": 2,
-                     "value_type": "individual"
-                  },
-                  "type": "graph",
-                  "xaxis": {
-                     "buckets": null,
-                     "mode": "time",
-                     "name": null,
-                     "show": true,
-                     "values": [ ]
-                  },
-                  "yaxes": [
-                     {
-                        "format": "short",
-                        "label": null,
-                        "logBase": 1,
-                        "max": null,
-                        "min": 0,
-                        "show": true
-                     },
-                     {
-                        "format": "short",
-                        "label": null,
-                        "logBase": 1,
-                        "max": null,
-                        "min": null,
-                        "show": false
-                     }
-                  ]
+                  "type": "timeseries"
                },
                {
-                  "aliasColors": { },
-                  "bars": false,
-                  "dashLength": 10,
-                  "dashes": false,
                   "datasource": "$datasource",
-                  "fill": 1,
-                  "id": 2,
-                  "legend": {
-                     "avg": false,
-                     "current": false,
-                     "max": false,
-                     "min": false,
-                     "show": true,
-                     "total": false,
-                     "values": false
+                  "fieldConfig": {
+                     "defaults": {
+                        "custom": {
+                           "drawStyle": "line",
+                           "fillOpacity": 10,
+                           "lineWidth": 1,
+                           "pointSize": 5,
+                           "showPoints": "never",
+                           "spanNulls": false,
+                           "stacking": {
+                              "group": "A",
+                              "mode": "none"
+                           }
+                        },
+                        "thresholds": {
+                           "mode": "absolute",
+                           "steps": [ ]
+                        },
+                        "unit": "ms"
+                     },
+                     "overrides": [ ]
                   },
-                  "lines": true,
-                  "linewidth": 1,
+                  "id": 2,
                   "links": [ ],
                   "nullPointMode": "null as zero",
-                  "percentage": false,
-                  "pointradius": 5,
-                  "points": false,
-                  "renderer": "flot",
-                  "seriesOverrides": [ ],
-                  "spaceLength": 10,
-                  "span": 6,
-                  "stack": false,
-                  "steppedLine": false,
+                  "options": {
+                     "legend": {
+                        "showLegend": true
+                     },
+                     "tooltip": {
+                        "mode": "single",
+                        "sort": "none"
+                     }
+                  },
+                  "span": 4,
                   "targets": [
                      {
-                        "expr": "histogram_quantile(0.99, sum by (le,route) (job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-read\", route=~\"loki_api_v1_series|api_prom_series|api_prom_query|api_prom_label|api_prom_label_name_values|loki_api_v1_query|loki_api_v1_query_range|loki_api_v1_labels|loki_api_v1_label_name_values\", cluster=~\"$cluster\"})) * 1e3",
+                        "expr": "histogram_quantile(0.99, sum by (le,route) (cluster_job_route:loki_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/(loki|enterprise-logs)-read\", route=~\"loki_api_v1_series|api_prom_series|api_prom_query|api_prom_label|api_prom_label_name_values|loki_api_v1_query|loki_api_v1_query_range|loki_api_v1_labels|loki_api_v1_label_name_values\"})) * 1e3",
                         "format": "time_series",
                         "intervalFactor": 2,
                         "legendFormat": "{{ route }} 99th Percentile",
@@ -150,7 +271,7 @@
                         "step": 10
                      },
                      {
-                        "expr": "histogram_quantile(0.50, sum by (le,route) (job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-read\", route=~\"loki_api_v1_series|api_prom_series|api_prom_query|api_prom_label|api_prom_label_name_values|loki_api_v1_query|loki_api_v1_query_range|loki_api_v1_labels|loki_api_v1_label_name_values\", cluster=~\"$cluster\"})) * 1e3",
+                        "expr": "histogram_quantile(0.50, sum by (le,route) (cluster_job_route:loki_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/(loki|enterprise-logs)-read\", route=~\"loki_api_v1_series|api_prom_series|api_prom_query|api_prom_label|api_prom_label_name_values|loki_api_v1_query|loki_api_v1_query_range|loki_api_v1_labels|loki_api_v1_label_name_values\"})) * 1e3",
                         "format": "time_series",
                         "intervalFactor": 2,
                         "legendFormat": "{{ route }} 50th Percentile",
@@ -158,7 +279,7 @@
                         "step": 10
                      },
                      {
-                        "expr": "1e3 * sum(job_route:loki_request_duration_seconds_sum:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-read\", route=~\"loki_api_v1_series|api_prom_series|api_prom_query|api_prom_label|api_prom_label_name_values|loki_api_v1_query|loki_api_v1_query_range|loki_api_v1_labels|loki_api_v1_label_name_values\", cluster=~\"$cluster\"}) by (route)  / sum(job_route:loki_request_duration_seconds_count:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-read\", route=~\"loki_api_v1_series|api_prom_series|api_prom_query|api_prom_label|api_prom_label_name_values|loki_api_v1_query|loki_api_v1_query_range|loki_api_v1_labels|loki_api_v1_label_name_values\", cluster=~\"$cluster\"}) by (route) ",
+                        "expr": "1e3 * sum(cluster_job_route:loki_request_duration_seconds_sum:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/(loki|enterprise-logs)-read\", route=~\"loki_api_v1_series|api_prom_series|api_prom_query|api_prom_label|api_prom_label_name_values|loki_api_v1_query|loki_api_v1_query_range|loki_api_v1_labels|loki_api_v1_label_name_values\"}) by (route)  / sum(cluster_job_route:loki_request_duration_seconds_count:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/(loki|enterprise-logs)-read\", route=~\"loki_api_v1_series|api_prom_series|api_prom_query|api_prom_label|api_prom_label_name_values|loki_api_v1_query|loki_api_v1_query_range|loki_api_v1_labels|loki_api_v1_label_name_values\"}) by (route) ",
                         "format": "time_series",
                         "intervalFactor": 2,
                         "legendFormat": "{{ route }} Average",
@@ -166,23 +287,8 @@
                         "step": 10
                      }
                   ],
-                  "thresholds": [ ],
-                  "timeFrom": null,
-                  "timeShift": null,
                   "title": "Latency",
-                  "tooltip": {
-                     "shared": true,
-                     "sort": 2,
-                     "value_type": "individual"
-                  },
-                  "type": "graph",
-                  "xaxis": {
-                     "buckets": null,
-                     "mode": "time",
-                     "name": null,
-                     "show": true,
-                     "values": [ ]
-                  },
+                  "type": "timeseries",
                   "yaxes": [
                      {
                         "format": "ms",
@@ -201,6 +307,57 @@
                         "show": false
                      }
                   ]
+               },
+               {
+                  "datasource": "$datasource",
+                  "fieldConfig": {
+                     "defaults": {
+                        "custom": {
+                           "drawStyle": "line",
+                           "fillOpacity": 10,
+                           "lineWidth": 1,
+                           "pointSize": 5,
+                           "showPoints": "never",
+                           "spanNulls": false,
+                           "stacking": {
+                              "group": "A",
+                              "mode": "none"
+                           }
+                        },
+                        "thresholds": {
+                           "mode": "absolute",
+                           "steps": [ ]
+                        },
+                        "unit": "ms"
+                     },
+                     "overrides": [ ]
+                  },
+                  "id": 3,
+                  "links": [ ],
+                  "nullPointMode": "null as zero",
+                  "options": {
+                     "legend": {
+                        "showLegend": true
+                     },
+                     "tooltip": {
+                        "mode": "single",
+                        "sort": "none"
+                     }
+                  },
+                  "span": 4,
+                  "targets": [
+                     {
+                        "expr": "histogram_quantile(0.99, sum(rate(loki_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/(loki|enterprise-logs)-read\", route=~\"loki_api_v1_series|api_prom_series|api_prom_query|api_prom_label|api_prom_label_name_values|loki_api_v1_query|loki_api_v1_query_range|loki_api_v1_labels|loki_api_v1_label_name_values\"}[$__rate_interval])) by (le,pod)) * 1e3",
+                        "format": "time_series",
+                        "interval": "1m",
+                        "intervalFactor": 2,
+                        "legendFormat": "__auto",
+                        "refId": "A",
+                        "step": 10
+                     }
+                  ],
+                  "title": "Per Pod Latency (p99)",
+                  "type": "timeseries"
                }
             ],
             "repeat": null,
@@ -221,156 +378,256 @@
                      "3xx": "#6ED0E0",
                      "4xx": "#EF843C",
                      "5xx": "#E24D42",
+                     "OK": "#7EB26D",
+                     "cancel": "#A9A9A9",
                      "error": "#E24D42",
                      "success": "#7EB26D"
                   },
-                  "bars": false,
-                  "dashLength": 10,
-                  "dashes": false,
                   "datasource": "$datasource",
-                  "fill": 10,
-                  "id": 3,
-                  "legend": {
-                     "avg": false,
-                     "current": false,
-                     "max": false,
-                     "min": false,
-                     "show": true,
-                     "total": false,
-                     "values": false
+                  "fieldConfig": {
+                     "defaults": {
+                        "custom": {
+                           "drawStyle": "line",
+                           "fillOpacity": 100,
+                           "lineWidth": 0,
+                           "pointSize": 5,
+                           "showPoints": "never",
+                           "spanNulls": false,
+                           "stacking": {
+                              "group": "A",
+                              "mode": "normal"
+                           }
+                        },
+                        "min": 0,
+                        "thresholds": {
+                           "mode": "absolute",
+                           "steps": [ ]
+                        },
+                        "unit": "short"
+                     },
+                     "overrides": [
+                        {
+                           "matcher": {
+                              "id": "byName",
+                              "options": "1xx"
+                           },
+                           "properties": [
+                              {
+                                 "id": "color",
+                                 "value": {
+                                    "fixedColor": "#EAB839",
+                                    "mode": "fixed"
+                                 }
+                              }
+                           ]
+                        },
+                        {
+                           "matcher": {
+                              "id": "byName",
+                              "options": "2xx"
+                           },
+                           "properties": [
+                              {
+                                 "id": "color",
+                                 "value": {
+                                    "fixedColor": "#7EB26D",
+                                    "mode": "fixed"
+                                 }
+                              }
+                           ]
+                        },
+                        {
+                           "matcher": {
+                              "id": "byName",
+                              "options": "3xx"
+                           },
+                           "properties": [
+                              {
+                                 "id": "color",
+                                 "value": {
+                                    "fixedColor": "#6ED0E0",
+                                    "mode": "fixed"
+                                 }
+                              }
+                           ]
+                        },
+                        {
+                           "matcher": {
+                              "id": "byName",
+                              "options": "4xx"
+                           },
+                           "properties": [
+                              {
+                                 "id": "color",
+                                 "value": {
+                                    "fixedColor": "#EF843C",
+                                    "mode": "fixed"
+                                 }
+                              }
+                           ]
+                        },
+                        {
+                           "matcher": {
+                              "id": "byName",
+                              "options": "5xx"
+                           },
+                           "properties": [
+                              {
+                                 "id": "color",
+                                 "value": {
+                                    "fixedColor": "#E24D42",
+                                    "mode": "fixed"
+                                 }
+                              }
+                           ]
+                        },
+                        {
+                           "matcher": {
+                              "id": "byName",
+                              "options": "OK"
+                           },
+                           "properties": [
+                              {
+                                 "id": "color",
+                                 "value": {
+                                    "fixedColor": "#7EB26D",
+                                    "mode": "fixed"
+                                 }
+                              }
+                           ]
+                        },
+                        {
+                           "matcher": {
+                              "id": "byName",
+                              "options": "cancel"
+                           },
+                           "properties": [
+                              {
+                                 "id": "color",
+                                 "value": {
+                                    "fixedColor": "#A9A9A9",
+                                    "mode": "fixed"
+                                 }
+                              }
+                           ]
+                        },
+                        {
+                           "matcher": {
+                              "id": "byName",
+                              "options": "error"
+                           },
+                           "properties": [
+                              {
+                                 "id": "color",
+                                 "value": {
+                                    "fixedColor": "#E24D42",
+                                    "mode": "fixed"
+                                 }
+                              }
+                           ]
+                        },
+                        {
+                           "matcher": {
+                              "id": "byName",
+                              "options": "success"
+                           },
+                           "properties": [
+                              {
+                                 "id": "color",
+                                 "value": {
+                                    "fixedColor": "#7EB26D",
+                                    "mode": "fixed"
+                                 }
+                              }
+                           ]
+                        }
+                     ]
                   },
-                  "lines": true,
+                  "fill": 10,
+                  "id": 4,
                   "linewidth": 0,
                   "links": [ ],
-                  "nullPointMode": "null as zero",
-                  "percentage": false,
-                  "pointradius": 5,
-                  "points": false,
-                  "renderer": "flot",
-                  "seriesOverrides": [ ],
-                  "spaceLength": 10,
-                  "span": 6,
+                  "options": {
+                     "legend": {
+                        "showLegend": true
+                     },
+                     "tooltip": {
+                        "mode": "single",
+                        "sort": "none"
+                     }
+                  },
+                  "span": 4,
                   "stack": true,
-                  "steppedLine": false,
                   "targets": [
                      {
-                        "expr": "sum by (status) (\n  label_replace(label_replace(rate(loki_boltdb_shipper_request_duration_seconds_count{cluster=~\"$cluster\",job=~\"($namespace)/(loki|enterprise-logs)-read\", operation=\"Shipper.Query\"}[$__rate_interval]),\n  \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n  \"status\", \"${1}\", \"status_code\", \"([a-z]+)\"))\n",
+                        "expr": "sum by (status) (\n  label_replace(label_replace(rate(loki_boltdb_shipper_request_duration_seconds_count{cluster=~\"$cluster\",job=~\"($namespace)/(loki|enterprise-logs)-read\", operation=\"Shipper.Query\"}[$__rate_interval]),\n  \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n  \"status\", \"${1}\", \"status_code\", \"([a-zA-Z]+)\"))\n",
                         "format": "time_series",
-                        "intervalFactor": 2,
                         "legendFormat": "{{status}}",
-                        "refId": "A",
-                        "step": 10
+                        "refId": "A"
                      }
                   ],
-                  "thresholds": [ ],
-                  "timeFrom": null,
-                  "timeShift": null,
                   "title": "QPS",
-                  "tooltip": {
-                     "shared": true,
-                     "sort": 2,
-                     "value_type": "individual"
-                  },
-                  "type": "graph",
-                  "xaxis": {
-                     "buckets": null,
-                     "mode": "time",
-                     "name": null,
-                     "show": true,
-                     "values": [ ]
-                  },
-                  "yaxes": [
-                     {
-                        "format": "short",
-                        "label": null,
-                        "logBase": 1,
-                        "max": null,
-                        "min": 0,
-                        "show": true
-                     },
-                     {
-                        "format": "short",
-                        "label": null,
-                        "logBase": 1,
-                        "max": null,
-                        "min": null,
-                        "show": false
-                     }
-                  ]
+                  "type": "timeseries"
                },
                {
-                  "aliasColors": { },
-                  "bars": false,
-                  "dashLength": 10,
-                  "dashes": false,
                   "datasource": "$datasource",
-                  "fill": 1,
-                  "id": 4,
-                  "legend": {
-                     "avg": false,
-                     "current": false,
-                     "max": false,
-                     "min": false,
-                     "show": true,
-                     "total": false,
-                     "values": false
+                  "fieldConfig": {
+                     "defaults": {
+                        "custom": {
+                           "drawStyle": "line",
+                           "fillOpacity": 10,
+                           "lineWidth": 1,
+                           "pointSize": 5,
+                           "showPoints": "never",
+                           "spanNulls": false,
+                           "stacking": {
+                              "group": "A",
+                              "mode": "none"
+                           }
+                        },
+                        "thresholds": {
+                           "mode": "absolute",
+                           "steps": [ ]
+                        },
+                        "unit": "ms"
+                     },
+                     "overrides": [ ]
                   },
-                  "lines": true,
-                  "linewidth": 1,
+                  "id": 5,
                   "links": [ ],
                   "nullPointMode": "null as zero",
-                  "percentage": false,
-                  "pointradius": 5,
-                  "points": false,
-                  "renderer": "flot",
-                  "seriesOverrides": [ ],
-                  "spaceLength": 10,
-                  "span": 6,
-                  "stack": false,
-                  "steppedLine": false,
+                  "options": {
+                     "legend": {
+                        "showLegend": true
+                     },
+                     "tooltip": {
+                        "mode": "single",
+                        "sort": "none"
+                     }
+                  },
+                  "span": 4,
                   "targets": [
                      {
                         "expr": "histogram_quantile(0.99, sum(rate(loki_boltdb_shipper_request_duration_seconds_bucket{cluster=~\"$cluster\",job=~\"($namespace)/(loki|enterprise-logs)-read\", operation=\"Shipper.Query\"}[$__rate_interval])) by (le)) * 1e3",
                         "format": "time_series",
-                        "intervalFactor": 2,
                         "legendFormat": "99th Percentile",
-                        "refId": "A",
-                        "step": 10
+                        "refId": "A"
                      },
                      {
                         "expr": "histogram_quantile(0.50, sum(rate(loki_boltdb_shipper_request_duration_seconds_bucket{cluster=~\"$cluster\",job=~\"($namespace)/(loki|enterprise-logs)-read\", operation=\"Shipper.Query\"}[$__rate_interval])) by (le)) * 1e3",
                         "format": "time_series",
-                        "intervalFactor": 2,
                         "legendFormat": "50th Percentile",
-                        "refId": "B",
-                        "step": 10
+                        "refId": "B"
                      },
                      {
                         "expr": "sum(rate(loki_boltdb_shipper_request_duration_seconds_sum{cluster=~\"$cluster\",job=~\"($namespace)/(loki|enterprise-logs)-read\", operation=\"Shipper.Query\"}[$__rate_interval])) * 1e3 / sum(rate(loki_boltdb_shipper_request_duration_seconds_count{cluster=~\"$cluster\",job=~\"($namespace)/(loki|enterprise-logs)-read\", operation=\"Shipper.Query\"}[$__rate_interval]))",
                         "format": "time_series",
-                        "intervalFactor": 2,
                         "legendFormat": "Average",
-                        "refId": "C",
-                        "step": 10
+                        "refId": "C"
                      }
                   ],
-                  "thresholds": [ ],
-                  "timeFrom": null,
-                  "timeShift": null,
                   "title": "Latency",
-                  "tooltip": {
-                     "shared": true,
-                     "sort": 2,
-                     "value_type": "individual"
-                  },
-                  "type": "graph",
-                  "xaxis": {
-                     "buckets": null,
-                     "mode": "time",
-                     "name": null,
-                     "show": true,
-                     "values": [ ]
-                  },
+                  "type": "timeseries",
                   "yaxes": [
                      {
                         "format": "ms",
@@ -389,6 +646,57 @@
                         "show": false
                      }
                   ]
+               },
+               {
+                  "datasource": "$datasource",
+                  "fieldConfig": {
+                     "defaults": {
+                        "custom": {
+                           "drawStyle": "line",
+                           "fillOpacity": 10,
+                           "lineWidth": 1,
+                           "pointSize": 5,
+                           "showPoints": "never",
+                           "spanNulls": false,
+                           "stacking": {
+                              "group": "A",
+                              "mode": "none"
+                           }
+                        },
+                        "thresholds": {
+                           "mode": "absolute",
+                           "steps": [ ]
+                        },
+                        "unit": "ms"
+                     },
+                     "overrides": [ ]
+                  },
+                  "id": 6,
+                  "links": [ ],
+                  "nullPointMode": "null as zero",
+                  "options": {
+                     "legend": {
+                        "showLegend": true
+                     },
+                     "tooltip": {
+                        "mode": "single",
+                        "sort": "none"
+                     }
+                  },
+                  "span": 4,
+                  "targets": [
+                     {
+                        "expr": "histogram_quantile(0.99, sum(rate(loki_boltdb_shipper_request_duration_seconds_bucket{cluster=~\"$cluster\",job=~\"($namespace)/(loki|enterprise-logs)-read\", operation=\"Shipper.Query\"}[$__rate_interval])) by (le,pod)) * 1e3",
+                        "format": "time_series",
+                        "interval": "1m",
+                        "intervalFactor": 2,
+                        "legendFormat": "__auto",
+                        "refId": "A",
+                        "step": 10
+                     }
+                  ],
+                  "title": "Per Pod Latency (p99)",
+                  "type": "timeseries"
                }
             ],
             "repeat": null,
@@ -412,7 +720,7 @@
                   "value": "default"
                },
                "hide": 0,
-               "label": "Data Source",
+               "label": "Data source",
                "name": "datasource",
                "options": [ ],
                "query": "prometheus",

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

@@ -27,563 +27,447 @@
             "collapsed": false,
             "panels": [
                {
-                  "aliasColors": { },
-                  "bars": false,
-                  "dashLength": 10,
-                  "dashes": false,
                   "datasource": "$datasource",
-                  "fill": 1,
+                  "fieldConfig": {
+                     "defaults": {
+                        "custom": {
+                           "drawStyle": "line",
+                           "fillOpacity": 10,
+                           "lineWidth": 1,
+                           "pointSize": 5,
+                           "showPoints": "never",
+                           "spanNulls": false,
+                           "stacking": {
+                              "group": "A",
+                              "mode": "none"
+                           }
+                        },
+                        "thresholds": {
+                           "mode": "absolute",
+                           "steps": [ ]
+                        },
+                        "unit": "short"
+                     },
+                     "overrides": [ ]
+                  },
                   "gridPos": { },
                   "id": 1,
-                  "legend": {
-                     "avg": false,
-                     "current": false,
-                     "max": false,
-                     "min": false,
-                     "show": true,
-                     "total": false,
-                     "values": false
-                  },
-                  "lines": true,
-                  "linewidth": 1,
                   "links": [ ],
-                  "nullPointMode": "null as zero",
-                  "percentage": false,
-                  "pointradius": 5,
-                  "points": false,
-                  "renderer": "flot",
-                  "seriesOverrides": [ ],
-                  "spaceLength": 10,
-                  "span": 6,
-                  "stack": false,
-                  "steppedLine": false,
+                  "options": {
+                     "legend": {
+                        "showLegend": true
+                     },
+                     "tooltip": {
+                        "mode": "single",
+                        "sort": "none"
+                     }
+                  },
                   "targets": [
                      {
                         "expr": "sum by(pod) (loki_ingester_memory_streams{cluster=~\"$cluster\", job=~\"($namespace)/(loki|enterprise-logs)-write\"})",
                         "format": "time_series",
-                        "intervalFactor": 2,
                         "legendFormat": "{{pod}}",
-                        "legendLink": null,
-                        "step": 10
+                        "legendLink": null
                      }
                   ],
-                  "thresholds": [ ],
-                  "timeFrom": null,
-                  "timeShift": null,
                   "title": "In-memory streams",
                   "tooltip": {
                      "sort": 2
                   },
-                  "type": "graph",
-                  "xaxis": {
-                     "buckets": null,
-                     "mode": "time",
-                     "name": null,
-                     "show": true,
-                     "values": [ ]
-                  },
-                  "yaxes": [
-                     {
-                        "format": "short",
-                        "label": null,
-                        "logBase": 1,
-                        "max": null,
-                        "min": 0,
-                        "show": true
-                     },
-                     {
-                        "format": "short",
-                        "label": null,
-                        "logBase": 1,
-                        "max": null,
-                        "min": null,
-                        "show": false
-                     }
-                  ]
+                  "type": "timeseries"
                },
                {
-                  "aliasColors": { },
-                  "bars": false,
-                  "dashLength": 10,
-                  "dashes": false,
                   "datasource": "$datasource",
-                  "fill": 1,
+                  "fieldConfig": {
+                     "defaults": {
+                        "custom": {
+                           "drawStyle": "line",
+                           "fillOpacity": 10,
+                           "lineWidth": 1,
+                           "pointSize": 5,
+                           "showPoints": "never",
+                           "spanNulls": false,
+                           "stacking": {
+                              "group": "A",
+                              "mode": "none"
+                           }
+                        },
+                        "thresholds": {
+                           "mode": "absolute",
+                           "steps": [ ]
+                        },
+                        "unit": "short"
+                     },
+                     "overrides": [
+                        {
+                           "matcher": {
+                              "id": "byName",
+                              "options": "request"
+                           },
+                           "properties": [
+                              {
+                                 "id": "color",
+                                 "value": {
+                                    "fixedColor": "#FFC000",
+                                    "mode": "fixed"
+                                 }
+                              },
+                              {
+                                 "id": "custom.fillOpacity",
+                                 "value": 0
+                              }
+                           ]
+                        },
+                        {
+                           "matcher": {
+                              "id": "byName",
+                              "options": "limit"
+                           },
+                           "properties": [
+                              {
+                                 "id": "color",
+                                 "value": {
+                                    "fixedColor": "#E02F44",
+                                    "mode": "fixed"
+                                 }
+                              },
+                              {
+                                 "id": "custom.fillOpacity",
+                                 "value": 0
+                              }
+                           ]
+                        }
+                     ]
+                  },
                   "gridPos": { },
                   "id": 2,
-                  "legend": {
-                     "avg": false,
-                     "current": false,
-                     "max": false,
-                     "min": false,
-                     "show": true,
-                     "total": false,
-                     "values": false
-                  },
-                  "lines": true,
-                  "linewidth": 1,
                   "links": [ ],
-                  "nullPointMode": "null as zero",
-                  "percentage": false,
-                  "pointradius": 5,
-                  "points": false,
-                  "renderer": "flot",
-                  "seriesOverrides": [
-                     {
-                        "alias": "limit",
-                        "color": "#E02F44",
-                        "fill": 0
+                  "options": {
+                     "legend": {
+                        "showLegend": true
+                     },
+                     "tooltip": {
+                        "mode": "single",
+                        "sort": "none"
                      }
-                  ],
-                  "spaceLength": 10,
-                  "span": 6,
-                  "stack": false,
-                  "steppedLine": false,
+                  },
                   "targets": [
                      {
                         "expr": "sum by(pod) (rate(container_cpu_usage_seconds_total{cluster=~\"$cluster\", namespace=~\"$namespace\", container=\"loki\", pod=~\"(loki|enterprise-logs)-write.*\"}[$__rate_interval]))",
                         "format": "time_series",
-                        "intervalFactor": 2,
                         "legendFormat": "{{pod}}",
-                        "legendLink": null,
-                        "step": 10
+                        "legendLink": null
+                     },
+                     {
+                        "expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\", container=\"loki\", pod=~\"(loki|enterprise-logs)-write.*\", resource=\"cpu\"} > 0)",
+                        "format": "time_series",
+                        "legendFormat": "request",
+                        "legendLink": null
                      },
                      {
                         "expr": "min(container_spec_cpu_quota{cluster=~\"$cluster\", namespace=~\"$namespace\", container=\"loki\", pod=~\"(loki|enterprise-logs)-write.*\"} / container_spec_cpu_period{cluster=~\"$cluster\", namespace=~\"$namespace\", container=\"loki\", pod=~\"(loki|enterprise-logs)-write.*\"})",
                         "format": "time_series",
-                        "intervalFactor": 2,
                         "legendFormat": "limit",
-                        "legendLink": null,
-                        "step": 10
+                        "legendLink": null
                      }
                   ],
-                  "thresholds": [ ],
-                  "timeFrom": null,
-                  "timeShift": null,
                   "title": "CPU",
                   "tooltip": {
                      "sort": 2
                   },
-                  "type": "graph",
-                  "xaxis": {
-                     "buckets": null,
-                     "mode": "time",
-                     "name": null,
-                     "show": true,
-                     "values": [ ]
-                  },
-                  "yaxes": [
-                     {
-                        "format": "short",
-                        "label": null,
-                        "logBase": 1,
-                        "max": null,
-                        "min": 0,
-                        "show": true
-                     },
-                     {
-                        "format": "short",
-                        "label": null,
-                        "logBase": 1,
-                        "max": null,
-                        "min": null,
-                        "show": false
-                     }
-                  ]
+                  "type": "timeseries"
                },
                {
-                  "aliasColors": { },
-                  "bars": false,
-                  "dashLength": 10,
-                  "dashes": false,
                   "datasource": "$datasource",
-                  "fill": 1,
+                  "fieldConfig": {
+                     "defaults": {
+                        "custom": {
+                           "drawStyle": "line",
+                           "fillOpacity": 10,
+                           "lineWidth": 1,
+                           "pointSize": 5,
+                           "showPoints": "never",
+                           "spanNulls": false,
+                           "stacking": {
+                              "group": "A",
+                              "mode": "none"
+                           }
+                        },
+                        "thresholds": {
+                           "mode": "absolute",
+                           "steps": [ ]
+                        },
+                        "unit": "bytes"
+                     },
+                     "overrides": [
+                        {
+                           "matcher": {
+                              "id": "byName",
+                              "options": "request"
+                           },
+                           "properties": [
+                              {
+                                 "id": "color",
+                                 "value": {
+                                    "fixedColor": "#FFC000",
+                                    "mode": "fixed"
+                                 }
+                              },
+                              {
+                                 "id": "custom.fillOpacity",
+                                 "value": 0
+                              }
+                           ]
+                        },
+                        {
+                           "matcher": {
+                              "id": "byName",
+                              "options": "limit"
+                           },
+                           "properties": [
+                              {
+                                 "id": "color",
+                                 "value": {
+                                    "fixedColor": "#E02F44",
+                                    "mode": "fixed"
+                                 }
+                              },
+                              {
+                                 "id": "custom.fillOpacity",
+                                 "value": 0
+                              }
+                           ]
+                        }
+                     ]
+                  },
                   "gridPos": { },
                   "id": 3,
-                  "legend": {
-                     "avg": false,
-                     "current": false,
-                     "max": false,
-                     "min": false,
-                     "show": true,
-                     "total": false,
-                     "values": false
-                  },
-                  "lines": true,
-                  "linewidth": 1,
                   "links": [ ],
-                  "nullPointMode": "null as zero",
-                  "percentage": false,
-                  "pointradius": 5,
-                  "points": false,
-                  "renderer": "flot",
-                  "seriesOverrides": [
-                     {
-                        "alias": "limit",
-                        "color": "#E02F44",
-                        "fill": 0
+                  "options": {
+                     "legend": {
+                        "showLegend": true
+                     },
+                     "tooltip": {
+                        "mode": "single",
+                        "sort": "none"
                      }
-                  ],
-                  "spaceLength": 10,
-                  "span": 6,
-                  "stack": false,
-                  "steppedLine": false,
+                  },
                   "targets": [
                      {
                         "expr": "max by(pod) (container_memory_working_set_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\", container=\"loki\", pod=~\"(loki|enterprise-logs)-write.*\"})",
                         "format": "time_series",
-                        "intervalFactor": 2,
                         "legendFormat": "{{pod}}",
-                        "legendLink": null,
-                        "step": 10
+                        "legendLink": null
+                     },
+                     {
+                        "expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\", container=\"loki\", pod=~\"(loki|enterprise-logs)-write.*\", resource=\"memory\"} > 0)",
+                        "format": "time_series",
+                        "legendFormat": "request",
+                        "legendLink": null
                      },
                      {
                         "expr": "min(container_spec_memory_limit_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\", container=\"loki\", pod=~\"(loki|enterprise-logs)-write.*\"} > 0)",
                         "format": "time_series",
-                        "intervalFactor": 2,
                         "legendFormat": "limit",
-                        "legendLink": null,
-                        "step": 10
+                        "legendLink": null
                      }
                   ],
-                  "thresholds": [ ],
-                  "timeFrom": null,
-                  "timeShift": null,
                   "title": "Memory (workingset)",
                   "tooltip": {
                      "sort": 2
                   },
-                  "type": "graph",
-                  "xaxis": {
-                     "buckets": null,
-                     "mode": "time",
-                     "name": null,
-                     "show": true,
-                     "values": [ ]
-                  },
-                  "yaxes": [
-                     {
-                        "format": "bytes",
-                        "label": null,
-                        "logBase": 1,
-                        "max": null,
-                        "min": 0,
-                        "show": true
-                     },
-                     {
-                        "format": "short",
-                        "label": null,
-                        "logBase": 1,
-                        "max": null,
-                        "min": null,
-                        "show": false
-                     }
-                  ]
+                  "type": "timeseries"
                },
                {
-                  "aliasColors": { },
-                  "bars": false,
-                  "dashLength": 10,
-                  "dashes": false,
                   "datasource": "$datasource",
-                  "fill": 1,
+                  "fieldConfig": {
+                     "defaults": {
+                        "custom": {
+                           "drawStyle": "line",
+                           "fillOpacity": 10,
+                           "lineWidth": 1,
+                           "pointSize": 5,
+                           "showPoints": "never",
+                           "spanNulls": false,
+                           "stacking": {
+                              "group": "A",
+                              "mode": "none"
+                           }
+                        },
+                        "thresholds": {
+                           "mode": "absolute",
+                           "steps": [ ]
+                        },
+                        "unit": "bytes"
+                     },
+                     "overrides": [ ]
+                  },
                   "gridPos": { },
                   "id": 4,
-                  "legend": {
-                     "avg": false,
-                     "current": false,
-                     "max": false,
-                     "min": false,
-                     "show": true,
-                     "total": false,
-                     "values": false
-                  },
-                  "lines": true,
-                  "linewidth": 1,
                   "links": [ ],
-                  "nullPointMode": "null as zero",
-                  "percentage": false,
-                  "pointradius": 5,
-                  "points": false,
-                  "renderer": "flot",
-                  "seriesOverrides": [ ],
-                  "spaceLength": 10,
-                  "span": 6,
-                  "stack": false,
-                  "steppedLine": false,
+                  "options": {
+                     "legend": {
+                        "showLegend": true
+                     },
+                     "tooltip": {
+                        "mode": "single",
+                        "sort": "none"
+                     }
+                  },
                   "targets": [
                      {
                         "expr": "sum by(pod) (go_memstats_heap_inuse_bytes{cluster=~\"$cluster\", job=~\"($namespace)/(loki|enterprise-logs)-write\"})",
                         "format": "time_series",
-                        "intervalFactor": 2,
                         "legendFormat": "{{pod}}",
-                        "legendLink": null,
-                        "step": 10
+                        "legendLink": null
                      }
                   ],
-                  "thresholds": [ ],
-                  "timeFrom": null,
-                  "timeShift": null,
                   "title": "Memory (go heap inuse)",
                   "tooltip": {
                      "sort": 2
                   },
-                  "type": "graph",
-                  "xaxis": {
-                     "buckets": null,
-                     "mode": "time",
-                     "name": null,
-                     "show": true,
-                     "values": [ ]
-                  },
-                  "yaxes": [
-                     {
-                        "format": "bytes",
-                        "label": null,
-                        "logBase": 1,
-                        "max": null,
-                        "min": 0,
-                        "show": true
-                     },
-                     {
-                        "format": "short",
-                        "label": null,
-                        "logBase": 1,
-                        "max": null,
-                        "min": null,
-                        "show": false
-                     }
-                  ]
+                  "type": "timeseries"
                },
                {
-                  "aliasColors": { },
-                  "bars": false,
-                  "dashLength": 10,
-                  "dashes": false,
                   "datasource": "$datasource",
-                  "fill": 10,
+                  "fieldConfig": {
+                     "defaults": {
+                        "custom": {
+                           "drawStyle": "line",
+                           "fillOpacity": 100,
+                           "lineWidth": 0,
+                           "pointSize": 5,
+                           "showPoints": "never",
+                           "spanNulls": false,
+                           "stacking": {
+                              "group": "A",
+                              "mode": "normal"
+                           }
+                        },
+                        "thresholds": {
+                           "mode": "absolute",
+                           "steps": [ ]
+                        },
+                        "unit": "Bps"
+                     },
+                     "overrides": [ ]
+                  },
                   "gridPos": { },
                   "id": 5,
-                  "legend": {
-                     "avg": false,
-                     "current": false,
-                     "max": false,
-                     "min": false,
-                     "show": true,
-                     "total": false,
-                     "values": false
-                  },
-                  "lines": true,
-                  "linewidth": 0,
                   "links": [ ],
-                  "nullPointMode": "null as zero",
-                  "percentage": false,
-                  "pointradius": 5,
-                  "points": false,
-                  "renderer": "flot",
-                  "seriesOverrides": [ ],
-                  "spaceLength": 10,
-                  "span": 6,
-                  "stack": true,
-                  "steppedLine": false,
+                  "options": {
+                     "legend": {
+                        "showLegend": true
+                     },
+                     "tooltip": {
+                        "mode": "single",
+                        "sort": "none"
+                     }
+                  },
                   "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=\"loki\", pod=~\"(loki|enterprise-logs)-write.*\", device!~\".*sda.*\"}), \"device\", \"$1\", \"device\", \"/dev/(.*)\") * 0)\n",
                         "format": "time_series",
-                        "intervalFactor": 2,
                         "legendFormat": "{{pod}} - {{device}}",
-                        "legendLink": null,
-                        "step": 10
+                        "legendLink": null
                      }
                   ],
-                  "thresholds": [ ],
-                  "timeFrom": null,
-                  "timeShift": null,
                   "title": "Disk Writes",
-                  "tooltip": {
-                     "shared": true,
-                     "sort": 2,
-                     "value_type": "individual"
-                  },
-                  "type": "graph",
-                  "xaxis": {
-                     "buckets": null,
-                     "mode": "time",
-                     "name": null,
-                     "show": true,
-                     "values": [ ]
-                  },
-                  "yaxes": [
-                     {
-                        "format": "Bps",
-                        "label": null,
-                        "logBase": 1,
-                        "max": null,
-                        "min": 0,
-                        "show": true
-                     },
-                     {
-                        "format": "short",
-                        "label": null,
-                        "logBase": 1,
-                        "max": null,
-                        "min": null,
-                        "show": false
-                     }
-                  ]
+                  "type": "timeseries"
                },
                {
-                  "aliasColors": { },
-                  "bars": false,
-                  "dashLength": 10,
-                  "dashes": false,
                   "datasource": "$datasource",
-                  "fill": 10,
+                  "fieldConfig": {
+                     "defaults": {
+                        "custom": {
+                           "drawStyle": "line",
+                           "fillOpacity": 100,
+                           "lineWidth": 0,
+                           "pointSize": 5,
+                           "showPoints": "never",
+                           "spanNulls": false,
+                           "stacking": {
+                              "group": "A",
+                              "mode": "normal"
+                           }
+                        },
+                        "thresholds": {
+                           "mode": "absolute",
+                           "steps": [ ]
+                        },
+                        "unit": "Bps"
+                     },
+                     "overrides": [ ]
+                  },
                   "gridPos": { },
                   "id": 6,
-                  "legend": {
-                     "avg": false,
-                     "current": false,
-                     "max": false,
-                     "min": false,
-                     "show": true,
-                     "total": false,
-                     "values": false
-                  },
-                  "lines": true,
-                  "linewidth": 0,
                   "links": [ ],
-                  "nullPointMode": "null as zero",
-                  "percentage": false,
-                  "pointradius": 5,
-                  "points": false,
-                  "renderer": "flot",
-                  "seriesOverrides": [ ],
-                  "spaceLength": 10,
-                  "span": 6,
-                  "stack": true,
-                  "steppedLine": false,
+                  "options": {
+                     "legend": {
+                        "showLegend": true
+                     },
+                     "tooltip": {
+                        "mode": "single",
+                        "sort": "none"
+                     }
+                  },
                   "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=\"loki\", pod=~\"(loki|enterprise-logs)-write.*\", device!~\".*sda.*\"}), \"device\", \"$1\", \"device\", \"/dev/(.*)\") * 0)\n",
                         "format": "time_series",
-                        "intervalFactor": 2,
                         "legendFormat": "{{pod}} - {{device}}",
-                        "legendLink": null,
-                        "step": 10
+                        "legendLink": null
                      }
                   ],
-                  "thresholds": [ ],
-                  "timeFrom": null,
-                  "timeShift": null,
                   "title": "Disk Reads",
-                  "tooltip": {
-                     "shared": true,
-                     "sort": 2,
-                     "value_type": "individual"
-                  },
-                  "type": "graph",
-                  "xaxis": {
-                     "buckets": null,
-                     "mode": "time",
-                     "name": null,
-                     "show": true,
-                     "values": [ ]
-                  },
-                  "yaxes": [
-                     {
-                        "format": "Bps",
-                        "label": null,
-                        "logBase": 1,
-                        "max": null,
-                        "min": 0,
-                        "show": true
-                     },
-                     {
-                        "format": "short",
-                        "label": null,
-                        "logBase": 1,
-                        "max": null,
-                        "min": null,
-                        "show": false
-                     }
-                  ]
+                  "type": "timeseries"
                },
                {
-                  "aliasColors": { },
-                  "bars": false,
-                  "dashLength": 10,
-                  "dashes": false,
                   "datasource": "$datasource",
-                  "fill": 1,
+                  "fieldConfig": {
+                     "defaults": {
+                        "custom": {
+                           "drawStyle": "line",
+                           "fillOpacity": 10,
+                           "lineWidth": 1,
+                           "pointSize": 5,
+                           "showPoints": "never",
+                           "spanNulls": false,
+                           "stacking": {
+                              "group": "A",
+                              "mode": "none"
+                           }
+                        },
+                        "thresholds": {
+                           "mode": "absolute",
+                           "steps": [ ]
+                        },
+                        "unit": "percentunit"
+                     },
+                     "overrides": [ ]
+                  },
                   "gridPos": { },
                   "id": 7,
-                  "legend": {
-                     "avg": false,
-                     "current": false,
-                     "max": false,
-                     "min": false,
-                     "show": true,
-                     "total": false,
-                     "values": false
-                  },
-                  "lines": true,
-                  "linewidth": 1,
                   "links": [ ],
-                  "nullPointMode": "null as zero",
-                  "percentage": false,
-                  "pointradius": 5,
-                  "points": false,
-                  "renderer": "flot",
-                  "seriesOverrides": [ ],
-                  "spaceLength": 10,
-                  "span": 6,
-                  "stack": false,
-                  "steppedLine": false,
+                  "options": {
+                     "legend": {
+                        "showLegend": true
+                     },
+                     "tooltip": {
+                        "mode": "single",
+                        "sort": "none"
+                     }
+                  },
                   "targets": [
                      {
                         "expr": "max by(persistentvolumeclaim) (kubelet_volume_stats_used_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\"} / kubelet_volume_stats_capacity_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\"}) and count by(persistentvolumeclaim) (kube_persistentvolumeclaim_labels{cluster=~\"$cluster\", namespace=~\"$namespace\",label_name=~\"(loki|enterprise-logs)-write.*\"})",
                         "format": "time_series",
-                        "intervalFactor": 2,
                         "legendFormat": "{{persistentvolumeclaim}}",
-                        "legendLink": null,
-                        "step": 10
+                        "legendLink": null
                      }
                   ],
-                  "thresholds": [ ],
-                  "timeFrom": null,
-                  "timeShift": null,
                   "title": "Disk Space Utilization",
-                  "tooltip": {
-                     "shared": true,
-                     "sort": 2,
-                     "value_type": "individual"
-                  },
-                  "type": "graph",
-                  "xaxis": {
-                     "buckets": null,
-                     "mode": "time",
-                     "name": null,
-                     "show": true,
-                     "values": [ ]
-                  },
-                  "yaxes": [
-                     {
-                        "format": "percentunit",
-                        "label": null,
-                        "logBase": 1,
-                        "max": null,
-                        "min": 0,
-                        "show": true
-                     },
-                     {
-                        "format": "short",
-                        "label": null,
-                        "logBase": 1,
-                        "max": null,
-                        "min": null,
-                        "show": false
-                     }
-                  ]
+                  "type": "timeseries"
                }
             ],
             "repeat": null,
@@ -608,7 +492,7 @@
                   "value": "default"
                },
                "hide": 0,
-               "label": "Data Source",
+               "label": "Data source",
                "name": "datasource",
                "options": [ ],
                "query": "prometheus",

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

@@ -33,116 +33,237 @@
                      "3xx": "#6ED0E0",
                      "4xx": "#EF843C",
                      "5xx": "#E24D42",
+                     "OK": "#7EB26D",
+                     "cancel": "#A9A9A9",
                      "error": "#E24D42",
                      "success": "#7EB26D"
                   },
-                  "bars": false,
-                  "dashLength": 10,
-                  "dashes": false,
                   "datasource": "$datasource",
+                  "fieldConfig": {
+                     "defaults": {
+                        "custom": {
+                           "drawStyle": "line",
+                           "fillOpacity": 100,
+                           "lineWidth": 0,
+                           "pointSize": 5,
+                           "showPoints": "never",
+                           "spanNulls": false,
+                           "stacking": {
+                              "group": "A",
+                              "mode": "normal"
+                           }
+                        },
+                        "min": 0,
+                        "thresholds": {
+                           "mode": "absolute",
+                           "steps": [ ]
+                        },
+                        "unit": "short"
+                     },
+                     "overrides": [
+                        {
+                           "matcher": {
+                              "id": "byName",
+                              "options": "1xx"
+                           },
+                           "properties": [
+                              {
+                                 "id": "color",
+                                 "value": {
+                                    "fixedColor": "#EAB839",
+                                    "mode": "fixed"
+                                 }
+                              }
+                           ]
+                        },
+                        {
+                           "matcher": {
+                              "id": "byName",
+                              "options": "2xx"
+                           },
+                           "properties": [
+                              {
+                                 "id": "color",
+                                 "value": {
+                                    "fixedColor": "#7EB26D",
+                                    "mode": "fixed"
+                                 }
+                              }
+                           ]
+                        },
+                        {
+                           "matcher": {
+                              "id": "byName",
+                              "options": "3xx"
+                           },
+                           "properties": [
+                              {
+                                 "id": "color",
+                                 "value": {
+                                    "fixedColor": "#6ED0E0",
+                                    "mode": "fixed"
+                                 }
+                              }
+                           ]
+                        },
+                        {
+                           "matcher": {
+                              "id": "byName",
+                              "options": "4xx"
+                           },
+                           "properties": [
+                              {
+                                 "id": "color",
+                                 "value": {
+                                    "fixedColor": "#EF843C",
+                                    "mode": "fixed"
+                                 }
+                              }
+                           ]
+                        },
+                        {
+                           "matcher": {
+                              "id": "byName",
+                              "options": "5xx"
+                           },
+                           "properties": [
+                              {
+                                 "id": "color",
+                                 "value": {
+                                    "fixedColor": "#E24D42",
+                                    "mode": "fixed"
+                                 }
+                              }
+                           ]
+                        },
+                        {
+                           "matcher": {
+                              "id": "byName",
+                              "options": "OK"
+                           },
+                           "properties": [
+                              {
+                                 "id": "color",
+                                 "value": {
+                                    "fixedColor": "#7EB26D",
+                                    "mode": "fixed"
+                                 }
+                              }
+                           ]
+                        },
+                        {
+                           "matcher": {
+                              "id": "byName",
+                              "options": "cancel"
+                           },
+                           "properties": [
+                              {
+                                 "id": "color",
+                                 "value": {
+                                    "fixedColor": "#A9A9A9",
+                                    "mode": "fixed"
+                                 }
+                              }
+                           ]
+                        },
+                        {
+                           "matcher": {
+                              "id": "byName",
+                              "options": "error"
+                           },
+                           "properties": [
+                              {
+                                 "id": "color",
+                                 "value": {
+                                    "fixedColor": "#E24D42",
+                                    "mode": "fixed"
+                                 }
+                              }
+                           ]
+                        },
+                        {
+                           "matcher": {
+                              "id": "byName",
+                              "options": "success"
+                           },
+                           "properties": [
+                              {
+                                 "id": "color",
+                                 "value": {
+                                    "fixedColor": "#7EB26D",
+                                    "mode": "fixed"
+                                 }
+                              }
+                           ]
+                        }
+                     ]
+                  },
                   "fill": 10,
                   "id": 1,
-                  "legend": {
-                     "avg": false,
-                     "current": false,
-                     "max": false,
-                     "min": false,
-                     "show": true,
-                     "total": false,
-                     "values": false
-                  },
-                  "lines": true,
                   "linewidth": 0,
                   "links": [ ],
-                  "nullPointMode": "null as zero",
-                  "percentage": false,
-                  "pointradius": 5,
-                  "points": false,
-                  "renderer": "flot",
-                  "seriesOverrides": [ ],
-                  "spaceLength": 10,
+                  "options": {
+                     "legend": {
+                        "showLegend": true
+                     },
+                     "tooltip": {
+                        "mode": "single",
+                        "sort": "none"
+                     }
+                  },
                   "span": 6,
                   "stack": true,
-                  "steppedLine": false,
                   "targets": [
                      {
-                        "expr": "sum by (status) (\n  label_replace(label_replace(rate(loki_request_duration_seconds_count{cluster=~\"$cluster\",job=~\"($namespace)/(loki|enterprise-logs)-write\", route=~\"api_prom_push|loki_api_v1_push|/httpgrpc.HTTP/Handle\"}[$__rate_interval]),\n  \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n  \"status\", \"${1}\", \"status_code\", \"([a-z]+)\"))\n",
+                        "expr": "sum by (status) (\n  label_replace(label_replace(rate(loki_request_duration_seconds_count{cluster=~\"$cluster\",job=~\"($namespace)/(loki|enterprise-logs)-write\", route=~\"api_prom_push|loki_api_v1_push|/httpgrpc.HTTP/Handle\"}[$__rate_interval]),\n  \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n  \"status\", \"${1}\", \"status_code\", \"([a-zA-Z]+)\"))\n",
                         "format": "time_series",
-                        "intervalFactor": 2,
                         "legendFormat": "{{status}}",
-                        "refId": "A",
-                        "step": 10
+                        "refId": "A"
                      }
                   ],
-                  "thresholds": [ ],
-                  "timeFrom": null,
-                  "timeShift": null,
                   "title": "QPS",
-                  "tooltip": {
-                     "shared": true,
-                     "sort": 2,
-                     "value_type": "individual"
-                  },
-                  "type": "graph",
-                  "xaxis": {
-                     "buckets": null,
-                     "mode": "time",
-                     "name": null,
-                     "show": true,
-                     "values": [ ]
-                  },
-                  "yaxes": [
-                     {
-                        "format": "short",
-                        "label": null,
-                        "logBase": 1,
-                        "max": null,
-                        "min": 0,
-                        "show": true
-                     },
-                     {
-                        "format": "short",
-                        "label": null,
-                        "logBase": 1,
-                        "max": null,
-                        "min": null,
-                        "show": false
-                     }
-                  ]
+                  "type": "timeseries"
                },
                {
-                  "aliasColors": { },
-                  "bars": false,
-                  "dashLength": 10,
-                  "dashes": false,
                   "datasource": "$datasource",
-                  "fill": 1,
-                  "id": 2,
-                  "legend": {
-                     "avg": false,
-                     "current": false,
-                     "max": false,
-                     "min": false,
-                     "show": true,
-                     "total": false,
-                     "values": false
+                  "fieldConfig": {
+                     "defaults": {
+                        "custom": {
+                           "drawStyle": "line",
+                           "fillOpacity": 10,
+                           "lineWidth": 1,
+                           "pointSize": 5,
+                           "showPoints": "never",
+                           "spanNulls": false,
+                           "stacking": {
+                              "group": "A",
+                              "mode": "none"
+                           }
+                        },
+                        "thresholds": {
+                           "mode": "absolute",
+                           "steps": [ ]
+                        },
+                        "unit": "ms"
+                     },
+                     "overrides": [ ]
                   },
-                  "lines": true,
-                  "linewidth": 1,
+                  "id": 2,
                   "links": [ ],
                   "nullPointMode": "null as zero",
-                  "percentage": false,
-                  "pointradius": 5,
-                  "points": false,
-                  "renderer": "flot",
-                  "seriesOverrides": [ ],
-                  "spaceLength": 10,
+                  "options": {
+                     "legend": {
+                        "showLegend": true
+                     },
+                     "tooltip": {
+                        "mode": "single",
+                        "sort": "none"
+                     }
+                  },
                   "span": 6,
-                  "stack": false,
-                  "steppedLine": false,
                   "targets": [
                      {
-                        "expr": "histogram_quantile(0.99, sum by (le) (job:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-write\", cluster=~\"$cluster\"})) * 1e3",
+                        "expr": "histogram_quantile(0.99, sum by (le) (cluster_job_route:loki_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/(loki|enterprise-logs)-write\", route=~\"api_prom_push|loki_api_v1_push|/httpgrpc.HTTP/Handle\"})) * 1e3",
                         "format": "time_series",
                         "intervalFactor": 2,
                         "legendFormat": "99th Percentile",
@@ -150,7 +271,7 @@
                         "step": 10
                      },
                      {
-                        "expr": "histogram_quantile(0.50, sum by (le) (job:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-write\", cluster=~\"$cluster\"})) * 1e3",
+                        "expr": "histogram_quantile(0.50, sum by (le) (cluster_job_route:loki_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/(loki|enterprise-logs)-write\", route=~\"api_prom_push|loki_api_v1_push|/httpgrpc.HTTP/Handle\"})) * 1e3",
                         "format": "time_series",
                         "intervalFactor": 2,
                         "legendFormat": "50th Percentile",
@@ -158,7 +279,7 @@
                         "step": 10
                      },
                      {
-                        "expr": "1e3 * sum(job:loki_request_duration_seconds_sum:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-write\", cluster=~\"$cluster\"}) / sum(job:loki_request_duration_seconds_count:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-write\", cluster=~\"$cluster\"})",
+                        "expr": "1e3 * sum(cluster_job_route:loki_request_duration_seconds_sum:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/(loki|enterprise-logs)-write\", route=~\"api_prom_push|loki_api_v1_push|/httpgrpc.HTTP/Handle\"}) / sum(cluster_job_route:loki_request_duration_seconds_count:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/(loki|enterprise-logs)-write\", route=~\"api_prom_push|loki_api_v1_push|/httpgrpc.HTTP/Handle\"})",
                         "format": "time_series",
                         "intervalFactor": 2,
                         "legendFormat": "Average",
@@ -166,23 +287,8 @@
                         "step": 10
                      }
                   ],
-                  "thresholds": [ ],
-                  "timeFrom": null,
-                  "timeShift": null,
                   "title": "Latency",
-                  "tooltip": {
-                     "shared": true,
-                     "sort": 2,
-                     "value_type": "individual"
-                  },
-                  "type": "graph",
-                  "xaxis": {
-                     "buckets": null,
-                     "mode": "time",
-                     "name": null,
-                     "show": true,
-                     "values": [ ]
-                  },
+                  "type": "timeseries",
                   "yaxes": [
                      {
                         "format": "ms",
@@ -215,76 +321,105 @@
             "height": "250px",
             "panels": [
                {
-                  "aliasColors": {
-                     "1xx": "#EAB839",
-                     "2xx": "#7EB26D",
-                     "3xx": "#6ED0E0",
-                     "4xx": "#EF843C",
-                     "5xx": "#E24D42",
-                     "error": "#E24D42",
-                     "success": "#7EB26D"
-                  },
-                  "bars": false,
-                  "dashLength": 10,
-                  "dashes": false,
                   "datasource": "$datasource",
-                  "fill": 10,
-                  "id": 3,
-                  "legend": {
-                     "avg": false,
-                     "current": false,
-                     "max": false,
-                     "min": false,
-                     "show": true,
-                     "total": false,
-                     "values": false
+                  "fieldConfig": {
+                     "defaults": {
+                        "custom": {
+                           "drawStyle": "line",
+                           "fillOpacity": 10,
+                           "lineWidth": 1,
+                           "pointSize": 5,
+                           "showPoints": "never",
+                           "spanNulls": false,
+                           "stacking": {
+                              "group": "A",
+                              "mode": "none"
+                           }
+                        },
+                        "thresholds": {
+                           "mode": "absolute",
+                           "steps": [ ]
+                        },
+                        "unit": "short"
+                     },
+                     "overrides": [ ]
                   },
-                  "lines": true,
-                  "linewidth": 0,
+                  "id": 3,
                   "links": [ ],
-                  "nullPointMode": "null as zero",
-                  "percentage": false,
-                  "pointradius": 5,
-                  "points": false,
-                  "renderer": "flot",
-                  "seriesOverrides": [ ],
-                  "spaceLength": 10,
+                  "options": {
+                     "legend": {
+                        "showLegend": true
+                     },
+                     "tooltip": {
+                        "mode": "single",
+                        "sort": "none"
+                     }
+                  },
                   "span": 6,
-                  "stack": true,
-                  "steppedLine": false,
                   "targets": [
                      {
-                        "expr": "sum by (status) (\n  label_replace(label_replace(rate(loki_boltdb_shipper_request_duration_seconds_count{cluster=~\"$cluster\",job=~\"($namespace)/(loki|enterprise-logs)-write\", operation=\"WRITE\"}[$__rate_interval]),\n  \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n  \"status\", \"${1}\", \"status_code\", \"([a-z]+)\"))\n",
+                        "expr": "sum (rate(loki_distributor_structured_metadata_bytes_received_total{cluster=~\"$cluster\",job=~\"($namespace)/(loki|enterprise-logs)-write\",}[$__rate_interval])) / sum(rate(loki_distributor_bytes_received_total{cluster=~\"$cluster\",job=~\"($namespace)/(loki|enterprise-logs)-write\",}[$__rate_interval]))",
                         "format": "time_series",
-                        "intervalFactor": 2,
-                        "legendFormat": "{{status}}",
-                        "refId": "A",
-                        "step": 10
+                        "legendFormat": "bytes",
+                        "legendLink": null
                      }
                   ],
-                  "thresholds": [ ],
-                  "timeFrom": null,
-                  "timeShift": null,
-                  "title": "QPS",
-                  "tooltip": {
-                     "shared": true,
-                     "sort": 2,
-                     "value_type": "individual"
+                  "title": "Per Total Received Bytes",
+                  "type": "timeseries"
+               },
+               {
+                  "datasource": "$datasource",
+                  "fieldConfig": {
+                     "defaults": {
+                        "custom": {
+                           "drawStyle": "line",
+                           "fillOpacity": 10,
+                           "lineWidth": 1,
+                           "pointSize": 5,
+                           "showPoints": "never",
+                           "spanNulls": false,
+                           "stacking": {
+                              "group": "A",
+                              "mode": "none"
+                           }
+                        },
+                        "thresholds": {
+                           "mode": "absolute",
+                           "steps": [ ]
+                        },
+                        "unit": "short"
+                     },
+                     "overrides": [ ]
                   },
-                  "type": "graph",
-                  "xaxis": {
-                     "buckets": null,
-                     "mode": "time",
-                     "name": null,
-                     "show": true,
-                     "values": [ ]
+                  "id": 4,
+                  "links": [ ],
+                  "options": {
+                     "legend": {
+                        "showLegend": true
+                     },
+                     "tooltip": {
+                        "mode": "single",
+                        "sort": "none"
+                     }
                   },
+                  "span": 6,
+                  "stack": true,
+                  "targets": [
+                     {
+                        "expr": "sum by (tenant) (rate(loki_distributor_structured_metadata_bytes_received_total{cluster=~\"$cluster\",job=~\"($namespace)/(loki|enterprise-logs)-write\",}[$__rate_interval])) / ignoring(tenant) group_left sum(rate(loki_distributor_structured_metadata_bytes_received_total{cluster=~\"$cluster\",job=~\"($namespace)/(loki|enterprise-logs)-write\",}[$__rate_interval]))",
+                        "format": "time_series",
+                        "legendFormat": "{{tenant}}",
+                        "legendLink": null
+                     }
+                  ],
+                  "title": "Per Tenant",
+                  "type": "timeseries",
                   "yaxes": [
                      {
                         "format": "short",
                         "label": null,
                         "logBase": 1,
-                        "max": null,
+                        "max": 1,
                         "min": 0,
                         "show": true
                      },
@@ -292,85 +427,281 @@
                         "format": "short",
                         "label": null,
                         "logBase": 1,
-                        "max": null,
+                        "max": 1,
                         "min": null,
                         "show": false
                      }
                   ]
+               }
+            ],
+            "repeat": null,
+            "repeatIteration": null,
+            "repeatRowId": null,
+            "showTitle": true,
+            "title": "Write Path",
+            "titleSize": "h6"
+         },
+         {
+            "collapse": false,
+            "height": "250px",
+            "panels": [
+               {
+                  "aliasColors": {
+                     "1xx": "#EAB839",
+                     "2xx": "#7EB26D",
+                     "3xx": "#6ED0E0",
+                     "4xx": "#EF843C",
+                     "5xx": "#E24D42",
+                     "OK": "#7EB26D",
+                     "cancel": "#A9A9A9",
+                     "error": "#E24D42",
+                     "success": "#7EB26D"
+                  },
+                  "datasource": "$datasource",
+                  "fieldConfig": {
+                     "defaults": {
+                        "custom": {
+                           "drawStyle": "line",
+                           "fillOpacity": 100,
+                           "lineWidth": 0,
+                           "pointSize": 5,
+                           "showPoints": "never",
+                           "spanNulls": false,
+                           "stacking": {
+                              "group": "A",
+                              "mode": "normal"
+                           }
+                        },
+                        "min": 0,
+                        "thresholds": {
+                           "mode": "absolute",
+                           "steps": [ ]
+                        },
+                        "unit": "short"
+                     },
+                     "overrides": [
+                        {
+                           "matcher": {
+                              "id": "byName",
+                              "options": "1xx"
+                           },
+                           "properties": [
+                              {
+                                 "id": "color",
+                                 "value": {
+                                    "fixedColor": "#EAB839",
+                                    "mode": "fixed"
+                                 }
+                              }
+                           ]
+                        },
+                        {
+                           "matcher": {
+                              "id": "byName",
+                              "options": "2xx"
+                           },
+                           "properties": [
+                              {
+                                 "id": "color",
+                                 "value": {
+                                    "fixedColor": "#7EB26D",
+                                    "mode": "fixed"
+                                 }
+                              }
+                           ]
+                        },
+                        {
+                           "matcher": {
+                              "id": "byName",
+                              "options": "3xx"
+                           },
+                           "properties": [
+                              {
+                                 "id": "color",
+                                 "value": {
+                                    "fixedColor": "#6ED0E0",
+                                    "mode": "fixed"
+                                 }
+                              }
+                           ]
+                        },
+                        {
+                           "matcher": {
+                              "id": "byName",
+                              "options": "4xx"
+                           },
+                           "properties": [
+                              {
+                                 "id": "color",
+                                 "value": {
+                                    "fixedColor": "#EF843C",
+                                    "mode": "fixed"
+                                 }
+                              }
+                           ]
+                        },
+                        {
+                           "matcher": {
+                              "id": "byName",
+                              "options": "5xx"
+                           },
+                           "properties": [
+                              {
+                                 "id": "color",
+                                 "value": {
+                                    "fixedColor": "#E24D42",
+                                    "mode": "fixed"
+                                 }
+                              }
+                           ]
+                        },
+                        {
+                           "matcher": {
+                              "id": "byName",
+                              "options": "OK"
+                           },
+                           "properties": [
+                              {
+                                 "id": "color",
+                                 "value": {
+                                    "fixedColor": "#7EB26D",
+                                    "mode": "fixed"
+                                 }
+                              }
+                           ]
+                        },
+                        {
+                           "matcher": {
+                              "id": "byName",
+                              "options": "cancel"
+                           },
+                           "properties": [
+                              {
+                                 "id": "color",
+                                 "value": {
+                                    "fixedColor": "#A9A9A9",
+                                    "mode": "fixed"
+                                 }
+                              }
+                           ]
+                        },
+                        {
+                           "matcher": {
+                              "id": "byName",
+                              "options": "error"
+                           },
+                           "properties": [
+                              {
+                                 "id": "color",
+                                 "value": {
+                                    "fixedColor": "#E24D42",
+                                    "mode": "fixed"
+                                 }
+                              }
+                           ]
+                        },
+                        {
+                           "matcher": {
+                              "id": "byName",
+                              "options": "success"
+                           },
+                           "properties": [
+                              {
+                                 "id": "color",
+                                 "value": {
+                                    "fixedColor": "#7EB26D",
+                                    "mode": "fixed"
+                                 }
+                              }
+                           ]
+                        }
+                     ]
+                  },
+                  "fill": 10,
+                  "id": 5,
+                  "linewidth": 0,
+                  "links": [ ],
+                  "options": {
+                     "legend": {
+                        "showLegend": true
+                     },
+                     "tooltip": {
+                        "mode": "single",
+                        "sort": "none"
+                     }
+                  },
+                  "span": 6,
+                  "stack": true,
+                  "targets": [
+                     {
+                        "expr": "sum by (status) (\n  label_replace(label_replace(rate(loki_boltdb_shipper_request_duration_seconds_count{cluster=~\"$cluster\",job=~\"($namespace)/(loki|enterprise-logs)-write\", operation=\"WRITE\"}[$__rate_interval]),\n  \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n  \"status\", \"${1}\", \"status_code\", \"([a-zA-Z]+)\"))\n",
+                        "format": "time_series",
+                        "legendFormat": "{{status}}",
+                        "refId": "A"
+                     }
+                  ],
+                  "title": "QPS",
+                  "type": "timeseries"
                },
                {
-                  "aliasColors": { },
-                  "bars": false,
-                  "dashLength": 10,
-                  "dashes": false,
                   "datasource": "$datasource",
-                  "fill": 1,
-                  "id": 4,
-                  "legend": {
-                     "avg": false,
-                     "current": false,
-                     "max": false,
-                     "min": false,
-                     "show": true,
-                     "total": false,
-                     "values": false
+                  "fieldConfig": {
+                     "defaults": {
+                        "custom": {
+                           "drawStyle": "line",
+                           "fillOpacity": 10,
+                           "lineWidth": 1,
+                           "pointSize": 5,
+                           "showPoints": "never",
+                           "spanNulls": false,
+                           "stacking": {
+                              "group": "A",
+                              "mode": "none"
+                           }
+                        },
+                        "thresholds": {
+                           "mode": "absolute",
+                           "steps": [ ]
+                        },
+                        "unit": "ms"
+                     },
+                     "overrides": [ ]
                   },
-                  "lines": true,
-                  "linewidth": 1,
+                  "id": 6,
                   "links": [ ],
                   "nullPointMode": "null as zero",
-                  "percentage": false,
-                  "pointradius": 5,
-                  "points": false,
-                  "renderer": "flot",
-                  "seriesOverrides": [ ],
-                  "spaceLength": 10,
+                  "options": {
+                     "legend": {
+                        "showLegend": true
+                     },
+                     "tooltip": {
+                        "mode": "single",
+                        "sort": "none"
+                     }
+                  },
                   "span": 6,
-                  "stack": false,
-                  "steppedLine": false,
                   "targets": [
                      {
                         "expr": "histogram_quantile(0.99, sum(rate(loki_boltdb_shipper_request_duration_seconds_bucket{cluster=~\"$cluster\",job=~\"($namespace)/(loki|enterprise-logs)-write\", operation=\"WRITE\"}[$__rate_interval])) by (le)) * 1e3",
                         "format": "time_series",
-                        "intervalFactor": 2,
                         "legendFormat": "99th Percentile",
-                        "refId": "A",
-                        "step": 10
+                        "refId": "A"
                      },
                      {
                         "expr": "histogram_quantile(0.50, sum(rate(loki_boltdb_shipper_request_duration_seconds_bucket{cluster=~\"$cluster\",job=~\"($namespace)/(loki|enterprise-logs)-write\", operation=\"WRITE\"}[$__rate_interval])) by (le)) * 1e3",
                         "format": "time_series",
-                        "intervalFactor": 2,
                         "legendFormat": "50th Percentile",
-                        "refId": "B",
-                        "step": 10
+                        "refId": "B"
                      },
                      {
                         "expr": "sum(rate(loki_boltdb_shipper_request_duration_seconds_sum{cluster=~\"$cluster\",job=~\"($namespace)/(loki|enterprise-logs)-write\", operation=\"WRITE\"}[$__rate_interval])) * 1e3 / sum(rate(loki_boltdb_shipper_request_duration_seconds_count{cluster=~\"$cluster\",job=~\"($namespace)/(loki|enterprise-logs)-write\", operation=\"WRITE\"}[$__rate_interval]))",
                         "format": "time_series",
-                        "intervalFactor": 2,
                         "legendFormat": "Average",
-                        "refId": "C",
-                        "step": 10
+                        "refId": "C"
                      }
                   ],
-                  "thresholds": [ ],
-                  "timeFrom": null,
-                  "timeShift": null,
                   "title": "Latency",
-                  "tooltip": {
-                     "shared": true,
-                     "sort": 2,
-                     "value_type": "individual"
-                  },
-                  "type": "graph",
-                  "xaxis": {
-                     "buckets": null,
-                     "mode": "time",
-                     "name": null,
-                     "show": true,
-                     "values": [ ]
-                  },
+                  "type": "timeseries",
                   "yaxes": [
                      {
                         "format": "ms",
@@ -412,7 +743,7 @@
                   "value": "default"
                },
                "hide": 0,
-               "label": "Data Source",
+               "label": "Data source",
                "name": "datasource",
                "options": [ ],
                "query": "prometheus",

charts/meta-monitoring/src/dashboards/mimir-alertmanager-resources.json

@@ -0,0 +1,836 @@
+{
+      "__requires": [
+         {
+            "id": "grafana",
+            "name": "Grafana",
+            "type": "grafana",
+            "version": "8.0.0"
+         }
+      ],
+      "annotations": {
+         "list": [ ]
+      },
+      "editable": true,
+      "gnetId": null,
+      "graphTooltip": 1,
+      "hideControls": false,
+      "links": [
+         {
+            "asDropdown": true,
+            "icon": "external link",
+            "includeVars": true,
+            "keepTime": true,
+            "tags": [
+               "mimir"
+            ],
+            "targetBlank": false,
+            "title": "Mimir dashboards",
+            "type": "dashboards"
+         }
+      ],
+      "refresh": "10s",
+      "rows": [
+         {
+            "collapse": false,
+            "height": "250px",
+            "panels": [
+               {
+                  "aliasColors": { },
+                  "bars": false,
+                  "dashLength": 10,
+                  "dashes": false,
+                  "datasource": "$datasource",
+                  "fill": 0,
+                  "id": 1,
+                  "legend": {
+                     "avg": false,
+                     "current": false,
+                     "max": false,
+                     "min": false,
+                     "show": true,
+                     "total": false,
+                     "values": false
+                  },
+                  "lines": true,
+                  "linewidth": 1,
+                  "links": [ ],
+                  "nullPointMode": "null as zero",
+                  "percentage": false,
+                  "pointradius": 5,
+                  "points": false,
+                  "renderer": "flot",
+                  "seriesOverrides": [
+                     {
+                        "alias": "request",
+                        "color": "#FFC000",
+                        "dashLength": 5,
+                        "dashes": true,
+                        "fill": 0
+                     },
+                     {
+                        "alias": "limit",
+                        "color": "#E02F44",
+                        "dashLength": 5,
+                        "dashes": true,
+                        "fill": 0
+                     }
+                  ],
+                  "spaceLength": 10,
+                  "span": 4,
+                  "stack": false,
+                  "steppedLine": false,
+                  "targets": [
+                     {
+                        "expr": "sum by(pod) (rate(container_cpu_usage_seconds_total{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"alertmanager\"}[$__rate_interval]))",
+                        "format": "time_series",
+                        "intervalFactor": 2,
+                        "legendFormat": "{{pod}}",
+                        "legendLink": null
+                     },
+                     {
+                        "expr": "min(container_spec_cpu_quota{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"alertmanager\"} / container_spec_cpu_period{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"alertmanager\"})",
+                        "format": "time_series",
+                        "intervalFactor": 2,
+                        "legendFormat": "limit",
+                        "legendLink": null
+                     },
+                     {
+                        "expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"alertmanager\",resource=\"cpu\"})",
+                        "format": "time_series",
+                        "intervalFactor": 2,
+                        "legendFormat": "request",
+                        "legendLink": null
+                     }
+                  ],
+                  "thresholds": [ ],
+                  "timeFrom": null,
+                  "timeShift": null,
+                  "title": "CPU",
+                  "tooltip": {
+                     "sort": 2
+                  },
+                  "type": "graph",
+                  "xaxis": {
+                     "buckets": null,
+                     "mode": "time",
+                     "name": null,
+                     "show": true,
+                     "values": [ ]
+                  },
+                  "yaxes": [
+                     {
+                        "format": "short",
+                        "label": null,
+                        "logBase": 1,
+                        "max": null,
+                        "min": 0,
+                        "show": true
+                     },
+                     {
+                        "format": "short",
+                        "label": null,
+                        "logBase": 1,
+                        "max": null,
+                        "min": null,
+                        "show": false
+                     }
+                  ]
+               },
+               {
+                  "aliasColors": { },
+                  "bars": false,
+                  "dashLength": 10,
+                  "dashes": false,
+                  "datasource": "$datasource",
+                  "fill": 0,
+                  "id": 2,
+                  "legend": {
+                     "avg": false,
+                     "current": false,
+                     "max": false,
+                     "min": false,
+                     "show": true,
+                     "total": false,
+                     "values": false
+                  },
+                  "lines": true,
+                  "linewidth": 1,
+                  "links": [ ],
+                  "nullPointMode": "null as zero",
+                  "percentage": false,
+                  "pointradius": 5,
+                  "points": false,
+                  "renderer": "flot",
+                  "seriesOverrides": [
+                     {
+                        "alias": "request",
+                        "color": "#FFC000",
+                        "dashLength": 5,
+                        "dashes": true,
+                        "fill": 0
+                     },
+                     {
+                        "alias": "limit",
+                        "color": "#E02F44",
+                        "dashLength": 5,
+                        "dashes": true,
+                        "fill": 0
+                     }
+                  ],
+                  "spaceLength": 10,
+                  "span": 4,
+                  "stack": false,
+                  "steppedLine": false,
+                  "targets": [
+                     {
+                        "expr": "max by(pod) (container_memory_working_set_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"alertmanager\"})",
+                        "format": "time_series",
+                        "intervalFactor": 2,
+                        "legendFormat": "{{pod}}",
+                        "legendLink": null
+                     },
+                     {
+                        "expr": "min(container_spec_memory_limit_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"alertmanager\"} > 0)",
+                        "format": "time_series",
+                        "intervalFactor": 2,
+                        "legendFormat": "limit",
+                        "legendLink": null
+                     },
+                     {
+                        "expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"alertmanager\",resource=\"memory\"})",
+                        "format": "time_series",
+                        "intervalFactor": 2,
+                        "legendFormat": "request",
+                        "legendLink": null
+                     }
+                  ],
+                  "thresholds": [ ],
+                  "timeFrom": null,
+                  "timeShift": null,
+                  "title": "Memory (workingset)",
+                  "tooltip": {
+                     "sort": 2
+                  },
+                  "type": "graph",
+                  "xaxis": {
+                     "buckets": null,
+                     "mode": "time",
+                     "name": null,
+                     "show": true,
+                     "values": [ ]
+                  },
+                  "yaxes": [
+                     {
+                        "format": "bytes",
+                        "label": null,
+                        "logBase": 1,
+                        "max": null,
+                        "min": 0,
+                        "show": true
+                     },
+                     {
+                        "format": "short",
+                        "label": null,
+                        "logBase": 1,
+                        "max": null,
+                        "min": null,
+                        "show": false
+                     }
+                  ]
+               },
+               {
+                  "aliasColors": { },
+                  "bars": false,
+                  "dashLength": 10,
+                  "dashes": false,
+                  "datasource": "$datasource",
+                  "fill": 0,
+                  "id": 3,
+                  "legend": {
+                     "avg": false,
+                     "current": false,
+                     "max": false,
+                     "min": false,
+                     "show": true,
+                     "total": false,
+                     "values": false
+                  },
+                  "lines": true,
+                  "linewidth": 1,
+                  "links": [ ],
+                  "nullPointMode": "null as zero",
+                  "percentage": false,
+                  "pointradius": 5,
+                  "points": false,
+                  "renderer": "flot",
+                  "seriesOverrides": [ ],
+                  "spaceLength": 10,
+                  "span": 4,
+                  "stack": false,
+                  "steppedLine": false,
+                  "targets": [
+                     {
+                        "expr": "sum by(pod) (go_memstats_heap_inuse_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"alertmanager\"})",
+                        "format": "time_series",
+                        "intervalFactor": 2,
+                        "legendFormat": "{{pod}}",
+                        "legendLink": null
+                     }
+                  ],
+                  "thresholds": [ ],
+                  "timeFrom": null,
+                  "timeShift": null,
+                  "title": "Memory (go heap inuse)",
+                  "tooltip": {
+                     "sort": 2
+                  },
+                  "type": "graph",
+                  "xaxis": {
+                     "buckets": null,
+                     "mode": "time",
+                     "name": null,
+                     "show": true,
+                     "values": [ ]
+                  },
+                  "yaxes": [
+                     {
+                        "format": "bytes",
+                        "label": null,
+                        "logBase": 1,
+                        "max": null,
+                        "min": 0,
+                        "show": true
+                     },
+                     {
+                        "format": "short",
+                        "label": null,
+                        "logBase": 1,
+                        "max": null,
+                        "min": null,
+                        "show": false
+                     }
+                  ]
+               }
+            ],
+            "repeat": null,
+            "repeatIteration": null,
+            "repeatRowId": null,
+            "showTitle": true,
+            "title": "Alertmanager",
+            "titleSize": "h6"
+         },
+         {
+            "collapse": false,
+            "height": "250px",
+            "panels": [
+               {
+                  "aliasColors": { },
+                  "bars": false,
+                  "dashLength": 10,
+                  "dashes": false,
+                  "datasource": "$datasource",
+                  "fill": 10,
+                  "id": 4,
+                  "legend": {
+                     "avg": false,
+                     "current": false,
+                     "max": false,
+                     "min": false,
+                     "show": true,
+                     "total": false,
+                     "values": false
+                  },
+                  "lines": true,
+                  "linewidth": 0,
+                  "links": [ ],
+                  "nullPointMode": "null as zero",
+                  "percentage": false,
+                  "pointradius": 5,
+                  "points": false,
+                  "renderer": "flot",
+                  "seriesOverrides": [ ],
+                  "spaceLength": 10,
+                  "span": 6,
+                  "stack": true,
+                  "steppedLine": false,
+                  "targets": [
+                     {
+                        "expr": "sum by(pod) (rate(container_network_receive_bytes_total{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?alertmanager.*\"}[$__rate_interval]))",
+                        "format": "time_series",
+                        "intervalFactor": 2,
+                        "legendFormat": "{{pod}}",
+                        "legendLink": null
+                     }
+                  ],
+                  "thresholds": [ ],
+                  "timeFrom": null,
+                  "timeShift": null,
+                  "title": "Receive bandwidth",
+                  "tooltip": {
+                     "shared": false,
+                     "sort": 0,
+                     "value_type": "individual"
+                  },
+                  "type": "graph",
+                  "xaxis": {
+                     "buckets": null,
+                     "mode": "time",
+                     "name": null,
+                     "show": true,
+                     "values": [ ]
+                  },
+                  "yaxes": [
+                     {
+                        "format": "Bps",
+                        "label": null,
+                        "logBase": 1,
+                        "max": null,
+                        "min": 0,
+                        "show": true
+                     },
+                     {
+                        "format": "short",
+                        "label": null,
+                        "logBase": 1,
+                        "max": null,
+                        "min": null,
+                        "show": false
+                     }
+                  ]
+               },
+               {
+                  "aliasColors": { },
+                  "bars": false,
+                  "dashLength": 10,
+                  "dashes": false,
+                  "datasource": "$datasource",
+                  "fill": 10,
+                  "id": 5,
+                  "legend": {
+                     "avg": false,
+                     "current": false,
+                     "max": false,
+                     "min": false,
+                     "show": true,
+                     "total": false,
+                     "values": false
+                  },
+                  "lines": true,
+                  "linewidth": 0,
+                  "links": [ ],
+                  "nullPointMode": "null as zero",
+                  "percentage": false,
+                  "pointradius": 5,
+                  "points": false,
+                  "renderer": "flot",
+                  "seriesOverrides": [ ],
+                  "spaceLength": 10,
+                  "span": 6,
+                  "stack": true,
+                  "steppedLine": false,
+                  "targets": [
+                     {
+                        "expr": "sum by(pod) (rate(container_network_transmit_bytes_total{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?alertmanager.*\"}[$__rate_interval]))",
+                        "format": "time_series",
+                        "intervalFactor": 2,
+                        "legendFormat": "{{pod}}",
+                        "legendLink": null
+                     }
+                  ],
+                  "thresholds": [ ],
+                  "timeFrom": null,
+                  "timeShift": null,
+                  "title": "Transmit bandwidth",
+                  "tooltip": {
+                     "shared": false,
+                     "sort": 0,
+                     "value_type": "individual"
+                  },
+                  "type": "graph",
+                  "xaxis": {
+                     "buckets": null,
+                     "mode": "time",
+                     "name": null,
+                     "show": true,
+                     "values": [ ]
+                  },
+                  "yaxes": [
+                     {
+                        "format": "Bps",
+                        "label": null,
+                        "logBase": 1,
+                        "max": null,
+                        "min": 0,
+                        "show": true
+                     },
+                     {
+                        "format": "short",
+                        "label": null,
+                        "logBase": 1,
+                        "max": null,
+                        "min": null,
+                        "show": false
+                     }
+                  ]
+               }
+            ],
+            "repeat": null,
+            "repeatIteration": null,
+            "repeatRowId": null,
+            "showTitle": true,
+            "title": "Network",
+            "titleSize": "h6"
+         },
+         {
+            "collapse": false,
+            "height": "250px",
+            "panels": [
+               {
+                  "aliasColors": { },
+                  "bars": false,
+                  "dashLength": 10,
+                  "dashes": false,
+                  "datasource": "$datasource",
+                  "fill": 10,
+                  "id": 6,
+                  "legend": {
+                     "avg": false,
+                     "current": false,
+                     "max": false,
+                     "min": false,
+                     "show": true,
+                     "total": false,
+                     "values": false
+                  },
+                  "lines": true,
+                  "linewidth": 0,
+                  "links": [ ],
+                  "nullPointMode": "null as zero",
+                  "percentage": false,
+                  "pointradius": 5,
+                  "points": false,
+                  "renderer": "flot",
+                  "seriesOverrides": [ ],
+                  "spaceLength": 10,
+                  "span": 6,
+                  "stack": true,
+                  "steppedLine": false,
+                  "targets": [
+                     {
+                        "expr": "sum by(instance, pod, device) (\n  rate(\n    node_disk_written_bytes_total[$__rate_interval]\n  )\n)\n+\nignoring(pod) group_right() (\n  label_replace(\n    count by(\n      instance,\n      pod,\n      device\n    )\n    (\n      container_fs_writes_bytes_total{\n        cluster=~\"$cluster\", namespace=~\"$namespace\",\n        container=~\"alertmanager\",\n        device!~\".*sda.*\"\n      }\n    ),\n    \"device\",\n    \"$1\",\n    \"device\",\n    \"/dev/(.*)\"\n  ) * 0\n)\n\n",
+                        "format": "time_series",
+                        "intervalFactor": 2,
+                        "legendFormat": "{{pod}} - {{device}}",
+                        "legendLink": null
+                     }
+                  ],
+                  "thresholds": [ ],
+                  "timeFrom": null,
+                  "timeShift": null,
+                  "title": "Disk writes",
+                  "tooltip": {
+                     "shared": false,
+                     "sort": 0,
+                     "value_type": "individual"
+                  },
+                  "type": "graph",
+                  "xaxis": {
+                     "buckets": null,
+                     "mode": "time",
+                     "name": null,
+                     "show": true,
+                     "values": [ ]
+                  },
+                  "yaxes": [
+                     {
+                        "format": "Bps",
+                        "label": null,
+                        "logBase": 1,
+                        "max": null,
+                        "min": 0,
+                        "show": true
+                     },
+                     {
+                        "format": "short",
+                        "label": null,
+                        "logBase": 1,
+                        "max": null,
+                        "min": null,
+                        "show": false
+                     }
+                  ]
+               },
+               {
+                  "aliasColors": { },
+                  "bars": false,
+                  "dashLength": 10,
+                  "dashes": false,
+                  "datasource": "$datasource",
+                  "fill": 10,
+                  "id": 7,
+                  "legend": {
+                     "avg": false,
+                     "current": false,
+                     "max": false,
+                     "min": false,
+                     "show": true,
+                     "total": false,
+                     "values": false
+                  },
+                  "lines": true,
+                  "linewidth": 0,
+                  "links": [ ],
+                  "nullPointMode": "null as zero",
+                  "percentage": false,
+                  "pointradius": 5,
+                  "points": false,
+                  "renderer": "flot",
+                  "seriesOverrides": [ ],
+                  "spaceLength": 10,
+                  "span": 6,
+                  "stack": true,
+                  "steppedLine": false,
+                  "targets": [
+                     {
+                        "expr": "sum by(instance, pod, device) (\n  rate(\n    node_disk_read_bytes_total[$__rate_interval]\n  )\n) + ignoring(pod) group_right() (\n  label_replace(\n    count by(\n      instance,\n      pod,\n      device\n    )\n    (\n      container_fs_writes_bytes_total{\n        cluster=~\"$cluster\", namespace=~\"$namespace\",\n        container=~\"alertmanager\",\n        device!~\".*sda.*\"\n      }\n    ),\n    \"device\",\n    \"$1\",\n    \"device\",\n    \"/dev/(.*)\"\n  ) * 0\n)\n\n",
+                        "format": "time_series",
+                        "intervalFactor": 2,
+                        "legendFormat": "{{pod}} - {{device}}",
+                        "legendLink": null
+                     }
+                  ],
+                  "thresholds": [ ],
+                  "timeFrom": null,
+                  "timeShift": null,
+                  "title": "Disk reads",
+                  "tooltip": {
+                     "shared": false,
+                     "sort": 0,
+                     "value_type": "individual"
+                  },
+                  "type": "graph",
+                  "xaxis": {
+                     "buckets": null,
+                     "mode": "time",
+                     "name": null,
+                     "show": true,
+                     "values": [ ]
+                  },
+                  "yaxes": [
+                     {
+                        "format": "Bps",
+                        "label": null,
+                        "logBase": 1,
+                        "max": null,
+                        "min": 0,
+                        "show": true
+                     },
+                     {
+                        "format": "short",
+                        "label": null,
+                        "logBase": 1,
+                        "max": null,
+                        "min": null,
+                        "show": false
+                     }
+                  ]
+               }
+            ],
+            "repeat": null,
+            "repeatIteration": null,
+            "repeatRowId": null,
+            "showTitle": true,
+            "title": "Disk",
+            "titleSize": "h6"
+         },
+         {
+            "collapse": false,
+            "height": "250px",
+            "panels": [
+               {
+                  "aliasColors": { },
+                  "bars": false,
+                  "dashLength": 10,
+                  "dashes": false,
+                  "datasource": "$datasource",
+                  "fill": 0,
+                  "id": 8,
+                  "legend": {
+                     "avg": false,
+                     "current": false,
+                     "max": false,
+                     "min": false,
+                     "show": true,
+                     "total": false,
+                     "values": false
+                  },
+                  "lines": true,
+                  "linewidth": 1,
+                  "links": [ ],
+                  "nullPointMode": "null as zero",
+                  "percentage": false,
+                  "pointradius": 5,
+                  "points": false,
+                  "renderer": "flot",
+                  "seriesOverrides": [ ],
+                  "spaceLength": 10,
+                  "span": 12,
+                  "stack": false,
+                  "steppedLine": false,
+                  "targets": [
+                     {
+                        "expr": "max by(persistentvolumeclaim) (\n  kubelet_volume_stats_used_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\"} /\n  kubelet_volume_stats_capacity_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\"}\n)\nand\ncount by(persistentvolumeclaim) (\n  kube_persistentvolumeclaim_labels{\n    cluster=~\"$cluster\", namespace=~\"$namespace\",\n    label_name=~\"(alertmanager).*\"\n  }\n)\n",
+                        "format": "time_series",
+                        "intervalFactor": 2,
+                        "legendFormat": "{{persistentvolumeclaim}}",
+                        "legendLink": null
+                     }
+                  ],
+                  "thresholds": [ ],
+                  "timeFrom": null,
+                  "timeShift": null,
+                  "title": "Disk space utilization",
+                  "tooltip": {
+                     "shared": false,
+                     "sort": 0,
+                     "value_type": "individual"
+                  },
+                  "type": "graph",
+                  "xaxis": {
+                     "buckets": null,
+                     "mode": "time",
+                     "name": null,
+                     "show": true,
+                     "values": [ ]
+                  },
+                  "yaxes": [
+                     {
+                        "format": "percentunit",
+                        "label": null,
+                        "logBase": 1,
+                        "max": null,
+                        "min": 0,
+                        "show": true
+                     },
+                     {
+                        "format": "short",
+                        "label": null,
+                        "logBase": 1,
+                        "max": null,
+                        "min": null,
+                        "show": false
+                     }
+                  ]
+               }
+            ],
+            "repeat": null,
+            "repeatIteration": null,
+            "repeatRowId": null,
+            "showTitle": true,
+            "title": "",
+            "titleSize": "h6"
+         }
+      ],
+      "schemaVersion": 14,
+      "style": "dark",
+      "tags": [
+         "mimir"
+      ],
+      "templating": {
+         "list": [
+            {
+               "current": {
+                  "text": "default",
+                  "value": "default"
+               },
+               "hide": 0,
+               "label": "Data Source",
+               "name": "datasource",
+               "options": [ ],
+               "query": "prometheus",
+               "refresh": 1,
+               "regex": "",
+               "type": "datasource"
+            },
+            {
+               "allValue": ".*",
+               "current": {
+                  "text": "prod",
+                  "value": "prod"
+               },
+               "datasource": "$datasource",
+               "hide": 0,
+               "includeAll": true,
+               "label": "cluster",
+               "multi": false,
+               "name": "cluster",
+               "options": [ ],
+               "query": "label_values(cortex_build_info, cluster)",
+               "refresh": 1,
+               "regex": "",
+               "sort": 1,
+               "tagValuesQuery": "",
+               "tags": [ ],
+               "tagsQuery": "",
+               "type": "query",
+               "useTags": false
+            },
+            {
+               "allValue": null,
+               "current": {
+                  "text": "prod",
+                  "value": "prod"
+               },
+               "datasource": "$datasource",
+               "hide": 0,
+               "includeAll": false,
+               "label": "namespace",
+               "multi": false,
+               "name": "namespace",
+               "options": [ ],
+               "query": "label_values(cortex_build_info{cluster=~\"$cluster\"}, namespace)",
+               "refresh": 1,
+               "regex": "",
+               "sort": 1,
+               "tagValuesQuery": "",
+               "tags": [ ],
+               "tagsQuery": "",
+               "type": "query",
+               "useTags": false
+            }
+         ]
+      },
+      "time": {
+         "from": "now-1h",
+         "to": "now"
+      },
+      "timepicker": {
+         "refresh_intervals": [
+            "5s",
+            "10s",
+            "30s",
+            "1m",
+            "5m",
+            "15m",
+            "30m",
+            "1h",
+            "2h",
+            "1d"
+         ],
+         "time_options": [
+            "5m",
+            "15m",
+            "1h",
+            "6h",
+            "12h",
+            "24h",
+            "2d",
+            "7d",
+            "30d"
+         ]
+      },
+      "timezone": "utc",
+      "title": "Mimir / Alertmanager resources",
+      "uid": "a6883fb22799ac74479c7db872451092",
+      "version": 0
+   }

charts/meta-monitoring/src/dashboards/mimir-compactor-resources.json

@@ -0,0 +1,940 @@
+{
+      "__requires": [
+         {
+            "id": "grafana",
+            "name": "Grafana",
+            "type": "grafana",
+            "version": "8.0.0"
+         }
+      ],
+      "annotations": {
+         "list": [ ]
+      },
+      "editable": true,
+      "gnetId": null,
+      "graphTooltip": 1,
+      "hideControls": false,
+      "links": [
+         {
+            "asDropdown": true,
+            "icon": "external link",
+            "includeVars": true,
+            "keepTime": true,
+            "tags": [
+               "mimir"
+            ],
+            "targetBlank": false,
+            "title": "Mimir dashboards",
+            "type": "dashboards"
+         }
+      ],
+      "refresh": "10s",
+      "rows": [
+         {
+            "collapse": false,
+            "height": "250px",
+            "panels": [
+               {
+                  "aliasColors": { },
+                  "bars": false,
+                  "dashLength": 10,
+                  "dashes": false,
+                  "datasource": "$datasource",
+                  "fill": 0,
+                  "id": 1,
+                  "legend": {
+                     "avg": false,
+                     "current": false,
+                     "max": false,
+                     "min": false,
+                     "show": true,
+                     "total": false,
+                     "values": false
+                  },
+                  "lines": true,
+                  "linewidth": 1,
+                  "links": [ ],
+                  "nullPointMode": "null as zero",
+                  "percentage": false,
+                  "pointradius": 5,
+                  "points": false,
+                  "renderer": "flot",
+                  "seriesOverrides": [
+                     {
+                        "alias": "request",
+                        "color": "#FFC000",
+                        "dashLength": 5,
+                        "dashes": true,
+                        "fill": 0
+                     },
+                     {
+                        "alias": "limit",
+                        "color": "#E02F44",
+                        "dashLength": 5,
+                        "dashes": true,
+                        "fill": 0
+                     }
+                  ],
+                  "spaceLength": 10,
+                  "span": 6,
+                  "stack": false,
+                  "steppedLine": false,
+                  "targets": [
+                     {
+                        "expr": "sum by(pod) (rate(container_cpu_usage_seconds_total{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"compactor\"}[$__rate_interval]))",
+                        "format": "time_series",
+                        "intervalFactor": 2,
+                        "legendFormat": "{{pod}}",
+                        "legendLink": null
+                     },
+                     {
+                        "expr": "min(container_spec_cpu_quota{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"compactor\"} / container_spec_cpu_period{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"compactor\"})",
+                        "format": "time_series",
+                        "intervalFactor": 2,
+                        "legendFormat": "limit",
+                        "legendLink": null
+                     },
+                     {
+                        "expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"compactor\",resource=\"cpu\"})",
+                        "format": "time_series",
+                        "intervalFactor": 2,
+                        "legendFormat": "request",
+                        "legendLink": null
+                     }
+                  ],
+                  "thresholds": [ ],
+                  "timeFrom": null,
+                  "timeShift": null,
+                  "title": "CPU",
+                  "tooltip": {
+                     "sort": 2
+                  },
+                  "type": "graph",
+                  "xaxis": {
+                     "buckets": null,
+                     "mode": "time",
+                     "name": null,
+                     "show": true,
+                     "values": [ ]
+                  },
+                  "yaxes": [
+                     {
+                        "format": "short",
+                        "label": null,
+                        "logBase": 1,
+                        "max": null,
+                        "min": 0,
+                        "show": true
+                     },
+                     {
+                        "format": "short",
+                        "label": null,
+                        "logBase": 1,
+                        "max": null,
+                        "min": null,
+                        "show": false
+                     }
+                  ]
+               },
+               {
+                  "aliasColors": { },
+                  "bars": false,
+                  "dashLength": 10,
+                  "dashes": false,
+                  "datasource": "$datasource",
+                  "fill": 0,
+                  "id": 2,
+                  "legend": {
+                     "avg": false,
+                     "current": false,
+                     "max": false,
+                     "min": false,
+                     "show": true,
+                     "total": false,
+                     "values": false
+                  },
+                  "lines": true,
+                  "linewidth": 1,
+                  "links": [ ],
+                  "nullPointMode": "null as zero",
+                  "percentage": false,
+                  "pointradius": 5,
+                  "points": false,
+                  "renderer": "flot",
+                  "seriesOverrides": [ ],
+                  "spaceLength": 10,
+                  "span": 6,
+                  "stack": false,
+                  "steppedLine": false,
+                  "targets": [
+                     {
+                        "expr": "sum by(pod) (go_memstats_heap_inuse_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"compactor\"})",
+                        "format": "time_series",
+                        "intervalFactor": 2,
+                        "legendFormat": "{{pod}}",
+                        "legendLink": null
+                     }
+                  ],
+                  "thresholds": [ ],
+                  "timeFrom": null,
+                  "timeShift": null,
+                  "title": "Memory (go heap inuse)",
+                  "tooltip": {
+                     "sort": 2
+                  },
+                  "type": "graph",
+                  "xaxis": {
+                     "buckets": null,
+                     "mode": "time",
+                     "name": null,
+                     "show": true,
+                     "values": [ ]
+                  },
+                  "yaxes": [
+                     {
+                        "format": "bytes",
+                        "label": null,
+                        "logBase": 1,
+                        "max": null,
+                        "min": 0,
+                        "show": true
+                     },
+                     {
+                        "format": "short",
+                        "label": null,
+                        "logBase": 1,
+                        "max": null,
+                        "min": null,
+                        "show": false
+                     }
+                  ]
+               }
+            ],
+            "repeat": null,
+            "repeatIteration": null,
+            "repeatRowId": null,
+            "showTitle": true,
+            "title": "CPU and memory",
+            "titleSize": "h6"
+         },
+         {
+            "collapse": false,
+            "height": "250px",
+            "panels": [
+               {
+                  "aliasColors": { },
+                  "bars": false,
+                  "dashLength": 10,
+                  "dashes": false,
+                  "datasource": "$datasource",
+                  "fill": 0,
+                  "id": 3,
+                  "legend": {
+                     "avg": false,
+                     "current": false,
+                     "max": false,
+                     "min": false,
+                     "show": true,
+                     "total": false,
+                     "values": false
+                  },
+                  "lines": true,
+                  "linewidth": 1,
+                  "links": [ ],
+                  "nullPointMode": "null as zero",
+                  "percentage": false,
+                  "pointradius": 5,
+                  "points": false,
+                  "renderer": "flot",
+                  "seriesOverrides": [
+                     {
+                        "alias": "request",
+                        "color": "#FFC000",
+                        "dashLength": 5,
+                        "dashes": true,
+                        "fill": 0
+                     },
+                     {
+                        "alias": "limit",
+                        "color": "#E02F44",
+                        "dashLength": 5,
+                        "dashes": true,
+                        "fill": 0
+                     }
+                  ],
+                  "spaceLength": 10,
+                  "span": 6,
+                  "stack": false,
+                  "steppedLine": false,
+                  "targets": [
+                     {
+                        "expr": "max by(pod) (container_memory_rss{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"compactor\"})",
+                        "format": "time_series",
+                        "intervalFactor": 2,
+                        "legendFormat": "{{pod}}",
+                        "legendLink": null
+                     },
+                     {
+                        "expr": "min(container_spec_memory_limit_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"compactor\"} > 0)",
+                        "format": "time_series",
+                        "intervalFactor": 2,
+                        "legendFormat": "limit",
+                        "legendLink": null
+                     },
+                     {
+                        "expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"compactor\",resource=\"memory\"})",
+                        "format": "time_series",
+                        "intervalFactor": 2,
+                        "legendFormat": "request",
+                        "legendLink": null
+                     }
+                  ],
+                  "thresholds": [ ],
+                  "timeFrom": null,
+                  "timeShift": null,
+                  "title": "Memory (RSS)",
+                  "tooltip": {
+                     "sort": 2
+                  },
+                  "type": "graph",
+                  "xaxis": {
+                     "buckets": null,
+                     "mode": "time",
+                     "name": null,
+                     "show": true,
+                     "values": [ ]
+                  },
+                  "yaxes": [
+                     {
+                        "format": "bytes",
+                        "label": null,
+                        "logBase": 1,
+                        "max": null,
+                        "min": 0,
+                        "show": true
+                     },
+                     {
+                        "format": "short",
+                        "label": null,
+                        "logBase": 1,
+                        "max": null,
+                        "min": null,
+                        "show": false
+                     }
+                  ]
+               },
+               {
+                  "aliasColors": { },
+                  "bars": false,
+                  "dashLength": 10,
+                  "dashes": false,
+                  "datasource": "$datasource",
+                  "fill": 0,
+                  "id": 4,
+                  "legend": {
+                     "avg": false,
+                     "current": false,
+                     "max": false,
+                     "min": false,
+                     "show": true,
+                     "total": false,
+                     "values": false
+                  },
+                  "lines": true,
+                  "linewidth": 1,
+                  "links": [ ],
+                  "nullPointMode": "null as zero",
+                  "percentage": false,
+                  "pointradius": 5,
+                  "points": false,
+                  "renderer": "flot",
+                  "seriesOverrides": [
+                     {
+                        "alias": "request",
+                        "color": "#FFC000",
+                        "dashLength": 5,
+                        "dashes": true,
+                        "fill": 0
+                     },
+                     {
+                        "alias": "limit",
+                        "color": "#E02F44",
+                        "dashLength": 5,
+                        "dashes": true,
+                        "fill": 0
+                     }
+                  ],
+                  "spaceLength": 10,
+                  "span": 6,
+                  "stack": false,
+                  "steppedLine": false,
+                  "targets": [
+                     {
+                        "expr": "max by(pod) (container_memory_working_set_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"compactor\"})",
+                        "format": "time_series",
+                        "intervalFactor": 2,
+                        "legendFormat": "{{pod}}",
+                        "legendLink": null
+                     },
+                     {
+                        "expr": "min(container_spec_memory_limit_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"compactor\"} > 0)",
+                        "format": "time_series",
+                        "intervalFactor": 2,
+                        "legendFormat": "limit",
+                        "legendLink": null
+                     },
+                     {
+                        "expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"compactor\",resource=\"memory\"})",
+                        "format": "time_series",
+                        "intervalFactor": 2,
+                        "legendFormat": "request",
+                        "legendLink": null
+                     }
+                  ],
+                  "thresholds": [ ],
+                  "timeFrom": null,
+                  "timeShift": null,
+                  "title": "Memory (workingset)",
+                  "tooltip": {
+                     "sort": 2
+                  },
+                  "type": "graph",
+                  "xaxis": {
+                     "buckets": null,
+                     "mode": "time",
+                     "name": null,
+                     "show": true,
+                     "values": [ ]
+                  },
+                  "yaxes": [
+                     {
+                        "format": "bytes",
+                        "label": null,
+                        "logBase": 1,
+                        "max": null,
+                        "min": 0,
+                        "show": true
+                     },
+                     {
+                        "format": "short",
+                        "label": null,
+                        "logBase": 1,
+                        "max": null,
+                        "min": null,
+                        "show": false
+                     }
+                  ]
+               }
+            ],
+            "repeat": null,
+            "repeatIteration": null,
+            "repeatRowId": null,
+            "showTitle": true,
+            "title": "",
+            "titleSize": "h6"
+         },
+         {
+            "collapse": false,
+            "height": "250px",
+            "panels": [
+               {
+                  "aliasColors": { },
+                  "bars": false,
+                  "dashLength": 10,
+                  "dashes": false,
+                  "datasource": "$datasource",
+                  "fill": 10,
+                  "id": 5,
+                  "legend": {
+                     "avg": false,
+                     "current": false,
+                     "max": false,
+                     "min": false,
+                     "show": true,
+                     "total": false,
+                     "values": false
+                  },
+                  "lines": true,
+                  "linewidth": 0,
+                  "links": [ ],
+                  "nullPointMode": "null as zero",
+                  "percentage": false,
+                  "pointradius": 5,
+                  "points": false,
+                  "renderer": "flot",
+                  "seriesOverrides": [ ],
+                  "spaceLength": 10,
+                  "span": 6,
+                  "stack": true,
+                  "steppedLine": false,
+                  "targets": [
+                     {
+                        "expr": "sum by(pod) (rate(container_network_receive_bytes_total{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?compactor.*\"}[$__rate_interval]))",
+                        "format": "time_series",
+                        "intervalFactor": 2,
+                        "legendFormat": "{{pod}}",
+                        "legendLink": null
+                     }
+                  ],
+                  "thresholds": [ ],
+                  "timeFrom": null,
+                  "timeShift": null,
+                  "title": "Receive bandwidth",
+                  "tooltip": {
+                     "shared": false,
+                     "sort": 0,
+                     "value_type": "individual"
+                  },
+                  "type": "graph",
+                  "xaxis": {
+                     "buckets": null,
+                     "mode": "time",
+                     "name": null,
+                     "show": true,
+                     "values": [ ]
+                  },
+                  "yaxes": [
+                     {
+                        "format": "Bps",
+                        "label": null,
+                        "logBase": 1,
+                        "max": null,
+                        "min": 0,
+                        "show": true
+                     },
+                     {
+                        "format": "short",
+                        "label": null,
+                        "logBase": 1,
+                        "max": null,
+                        "min": null,
+                        "show": false
+                     }
+                  ]
+               },
+               {
+                  "aliasColors": { },
+                  "bars": false,
+                  "dashLength": 10,
+                  "dashes": false,
+                  "datasource": "$datasource",
+                  "fill": 10,
+                  "id": 6,
+                  "legend": {
+                     "avg": false,
+                     "current": false,
+                     "max": false,
+                     "min": false,
+                     "show": true,
+                     "total": false,
+                     "values": false
+                  },
+                  "lines": true,
+                  "linewidth": 0,
+                  "links": [ ],
+                  "nullPointMode": "null as zero",
+                  "percentage": false,
+                  "pointradius": 5,
+                  "points": false,
+                  "renderer": "flot",
+                  "seriesOverrides": [ ],
+                  "spaceLength": 10,
+                  "span": 6,
+                  "stack": true,
+                  "steppedLine": false,
+                  "targets": [
+                     {
+                        "expr": "sum by(pod) (rate(container_network_transmit_bytes_total{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?compactor.*\"}[$__rate_interval]))",
+                        "format": "time_series",
+                        "intervalFactor": 2,
+                        "legendFormat": "{{pod}}",
+                        "legendLink": null
+                     }
+                  ],
+                  "thresholds": [ ],
+                  "timeFrom": null,
+                  "timeShift": null,
+                  "title": "Transmit bandwidth",
+                  "tooltip": {
+                     "shared": false,
+                     "sort": 0,
+                     "value_type": "individual"
+                  },
+                  "type": "graph",
+                  "xaxis": {
+                     "buckets": null,
+                     "mode": "time",
+                     "name": null,
+                     "show": true,
+                     "values": [ ]
+                  },
+                  "yaxes": [
+                     {
+                        "format": "Bps",
+                        "label": null,
+                        "logBase": 1,
+                        "max": null,
+                        "min": 0,
+                        "show": true
+                     },
+                     {
+                        "format": "short",
+                        "label": null,
+                        "logBase": 1,
+                        "max": null,
+                        "min": null,
+                        "show": false
+                     }
+                  ]
+               }
+            ],
+            "repeat": null,
+            "repeatIteration": null,
+            "repeatRowId": null,
+            "showTitle": true,
+            "title": "Network",
+            "titleSize": "h6"
+         },
+         {
+            "collapse": false,
+            "height": "250px",
+            "panels": [
+               {
+                  "aliasColors": { },
+                  "bars": false,
+                  "dashLength": 10,
+                  "dashes": false,
+                  "datasource": "$datasource",
+                  "fill": 10,
+                  "id": 7,
+                  "legend": {
+                     "avg": false,
+                     "current": false,
+                     "max": false,
+                     "min": false,
+                     "show": true,
+                     "total": false,
+                     "values": false
+                  },
+                  "lines": true,
+                  "linewidth": 0,
+                  "links": [ ],
+                  "nullPointMode": "null as zero",
+                  "percentage": false,
+                  "pointradius": 5,
+                  "points": false,
+                  "renderer": "flot",
+                  "seriesOverrides": [ ],
+                  "spaceLength": 10,
+                  "span": 4,
+                  "stack": true,
+                  "steppedLine": false,
+                  "targets": [
+                     {
+                        "expr": "sum by(instance, pod, device) (\n  rate(\n    node_disk_written_bytes_total[$__rate_interval]\n  )\n)\n+\nignoring(pod) group_right() (\n  label_replace(\n    count by(\n      instance,\n      pod,\n      device\n    )\n    (\n      container_fs_writes_bytes_total{\n        cluster=~\"$cluster\", namespace=~\"$namespace\",\n        container=~\"compactor\",\n        device!~\".*sda.*\"\n      }\n    ),\n    \"device\",\n    \"$1\",\n    \"device\",\n    \"/dev/(.*)\"\n  ) * 0\n)\n\n",
+                        "format": "time_series",
+                        "intervalFactor": 2,
+                        "legendFormat": "{{pod}} - {{device}}",
+                        "legendLink": null
+                     }
+                  ],
+                  "thresholds": [ ],
+                  "timeFrom": null,
+                  "timeShift": null,
+                  "title": "Disk writes",
+                  "tooltip": {
+                     "shared": false,
+                     "sort": 0,
+                     "value_type": "individual"
+                  },
+                  "type": "graph",
+                  "xaxis": {
+                     "buckets": null,
+                     "mode": "time",
+                     "name": null,
+                     "show": true,
+                     "values": [ ]
+                  },
+                  "yaxes": [
+                     {
+                        "format": "Bps",
+                        "label": null,
+                        "logBase": 1,
+                        "max": null,
+                        "min": 0,
+                        "show": true
+                     },
+                     {
+                        "format": "short",
+                        "label": null,
+                        "logBase": 1,
+                        "max": null,
+                        "min": null,
+                        "show": false
+                     }
+                  ]
+               },
+               {
+                  "aliasColors": { },
+                  "bars": false,
+                  "dashLength": 10,
+                  "dashes": false,
+                  "datasource": "$datasource",
+                  "fill": 10,
+                  "id": 8,
+                  "legend": {
+                     "avg": false,
+                     "current": false,
+                     "max": false,
+                     "min": false,
+                     "show": true,
+                     "total": false,
+                     "values": false
+                  },
+                  "lines": true,
+                  "linewidth": 0,
+                  "links": [ ],
+                  "nullPointMode": "null as zero",
+                  "percentage": false,
+                  "pointradius": 5,
+                  "points": false,
+                  "renderer": "flot",
+                  "seriesOverrides": [ ],
+                  "spaceLength": 10,
+                  "span": 4,
+                  "stack": true,
+                  "steppedLine": false,
+                  "targets": [
+                     {
+                        "expr": "sum by(instance, pod, device) (\n  rate(\n    node_disk_read_bytes_total[$__rate_interval]\n  )\n) + ignoring(pod) group_right() (\n  label_replace(\n    count by(\n      instance,\n      pod,\n      device\n    )\n    (\n      container_fs_writes_bytes_total{\n        cluster=~\"$cluster\", namespace=~\"$namespace\",\n        container=~\"compactor\",\n        device!~\".*sda.*\"\n      }\n    ),\n    \"device\",\n    \"$1\",\n    \"device\",\n    \"/dev/(.*)\"\n  ) * 0\n)\n\n",
+                        "format": "time_series",
+                        "intervalFactor": 2,
+                        "legendFormat": "{{pod}} - {{device}}",
+                        "legendLink": null
+                     }
+                  ],
+                  "thresholds": [ ],
+                  "timeFrom": null,
+                  "timeShift": null,
+                  "title": "Disk reads",
+                  "tooltip": {
+                     "shared": false,
+                     "sort": 0,
+                     "value_type": "individual"
+                  },
+                  "type": "graph",
+                  "xaxis": {
+                     "buckets": null,
+                     "mode": "time",
+                     "name": null,
+                     "show": true,
+                     "values": [ ]
+                  },
+                  "yaxes": [
+                     {
+                        "format": "Bps",
+                        "label": null,
+                        "logBase": 1,
+                        "max": null,
+                        "min": 0,
+                        "show": true
+                     },
+                     {
+                        "format": "short",
+                        "label": null,
+                        "logBase": 1,
+                        "max": null,
+                        "min": null,
+                        "show": false
+                     }
+                  ]
+               },
+               {
+                  "aliasColors": { },
+                  "bars": false,
+                  "dashLength": 10,
+                  "dashes": false,
+                  "datasource": "$datasource",
+                  "fill": 0,
+                  "id": 9,
+                  "legend": {
+                     "avg": false,
+                     "current": false,
+                     "max": false,
+                     "min": false,
+                     "show": true,
+                     "total": false,
+                     "values": false
+                  },
+                  "lines": true,
+                  "linewidth": 1,
+                  "links": [ ],
+                  "nullPointMode": "null as zero",
+                  "percentage": false,
+                  "pointradius": 5,
+                  "points": false,
+                  "renderer": "flot",
+                  "seriesOverrides": [ ],
+                  "spaceLength": 10,
+                  "span": 4,
+                  "stack": false,
+                  "steppedLine": false,
+                  "targets": [
+                     {
+                        "expr": "max by(persistentvolumeclaim) (\n  kubelet_volume_stats_used_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\"} /\n  kubelet_volume_stats_capacity_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\"}\n)\nand\ncount by(persistentvolumeclaim) (\n  kube_persistentvolumeclaim_labels{\n    cluster=~\"$cluster\", namespace=~\"$namespace\",\n    label_name=~\"(compactor).*\"\n  }\n)\n",
+                        "format": "time_series",
+                        "intervalFactor": 2,
+                        "legendFormat": "{{persistentvolumeclaim}}",
+                        "legendLink": null
+                     }
+                  ],
+                  "thresholds": [ ],
+                  "timeFrom": null,
+                  "timeShift": null,
+                  "title": "Disk space utilization",
+                  "tooltip": {
+                     "shared": false,
+                     "sort": 0,
+                     "value_type": "individual"
+                  },
+                  "type": "graph",
+                  "xaxis": {
+                     "buckets": null,
+                     "mode": "time",
+                     "name": null,
+                     "show": true,
+                     "values": [ ]
+                  },
+                  "yaxes": [
+                     {
+                        "format": "percentunit",
+                        "label": null,
+                        "logBase": 1,
+                        "max": null,
+                        "min": 0,
+                        "show": true
+                     },
+                     {
+                        "format": "short",
+                        "label": null,
+                        "logBase": 1,
+                        "max": null,
+                        "min": null,
+                        "show": false
+                     }
+                  ]
+               }
+            ],
+            "repeat": null,
+            "repeatIteration": null,
+            "repeatRowId": null,
+            "showTitle": true,
+            "title": "Disk",
+            "titleSize": "h6"
+         }
+      ],
+      "schemaVersion": 14,
+      "style": "dark",
+      "tags": [
+         "mimir"
+      ],
+      "templating": {
+         "list": [
+            {
+               "current": {
+                  "text": "default",
+                  "value": "default"
+               },
+               "hide": 0,
+               "label": "Data Source",
+               "name": "datasource",
+               "options": [ ],
+               "query": "prometheus",
+               "refresh": 1,
+               "regex": "",
+               "type": "datasource"
+            },
+            {
+               "allValue": ".+",
+               "current": {
+                  "selected": true,
+                  "text": "All",
+                  "value": "$__all"
+               },
+               "datasource": "$datasource",
+               "hide": 0,
+               "includeAll": true,
+               "label": "cluster",
+               "multi": true,
+               "name": "cluster",
+               "options": [ ],
+               "query": "label_values(cortex_build_info, cluster)",
+               "refresh": 1,
+               "regex": "",
+               "sort": 1,
+               "tagValuesQuery": "",
+               "tags": [ ],
+               "tagsQuery": "",
+               "type": "query",
+               "useTags": false
+            },
+            {
+               "allValue": ".+",
+               "current": {
+                  "selected": true,
+                  "text": "All",
+                  "value": "$__all"
+               },
+               "datasource": "$datasource",
+               "hide": 0,
+               "includeAll": false,
+               "label": "namespace",
+               "multi": true,
+               "name": "namespace",
+               "options": [ ],
+               "query": "label_values(cortex_build_info{cluster=~\"$cluster\"}, namespace)",
+               "refresh": 1,
+               "regex": "",
+               "sort": 1,
+               "tagValuesQuery": "",
+               "tags": [ ],
+               "tagsQuery": "",
+               "type": "query",
+               "useTags": false
+            }
+         ]
+      },
+      "time": {
+         "from": "now-1h",
+         "to": "now"
+      },
+      "timepicker": {
+         "refresh_intervals": [
+            "5s",
+            "10s",
+            "30s",
+            "1m",
+            "5m",
+            "15m",
+            "30m",
+            "1h",
+            "2h",
+            "1d"
+         ],
+         "time_options": [
+            "5m",
+            "15m",
+            "1h",
+            "6h",
+            "12h",
+            "24h",
+            "2d",
+            "7d",
+            "30d"
+         ]
+      },
+      "timezone": "utc",
+      "title": "Mimir / Compactor resources",
+      "uid": "09a5c49e9cdb2f2b24c6d184574a07fd",
+      "version": 0
+   }

charts/meta-monitoring/src/dashboards/mimir-config.json

@@ -0,0 +1,312 @@
+{
+      "__requires": [
+         {
+            "id": "grafana",
+            "name": "Grafana",
+            "type": "grafana",
+            "version": "8.0.0"
+         }
+      ],
+      "annotations": {
+         "list": [ ]
+      },
+      "editable": true,
+      "gnetId": null,
+      "graphTooltip": 1,
+      "hideControls": false,
+      "links": [
+         {
+            "asDropdown": true,
+            "icon": "external link",
+            "includeVars": true,
+            "keepTime": true,
+            "tags": [
+               "mimir"
+            ],
+            "targetBlank": false,
+            "title": "Mimir dashboards",
+            "type": "dashboards"
+         }
+      ],
+      "refresh": "10s",
+      "rows": [
+         {
+            "collapse": false,
+            "height": "250px",
+            "panels": [
+               {
+                  "aliasColors": { },
+                  "bars": false,
+                  "dashLength": 10,
+                  "dashes": false,
+                  "datasource": "$datasource",
+                  "fill": 10,
+                  "id": 1,
+                  "legend": {
+                     "avg": false,
+                     "current": false,
+                     "max": false,
+                     "min": false,
+                     "show": true,
+                     "total": false,
+                     "values": false
+                  },
+                  "lines": true,
+                  "linewidth": 0,
+                  "links": [ ],
+                  "nullPointMode": "null as zero",
+                  "percentage": false,
+                  "pointradius": 5,
+                  "points": false,
+                  "renderer": "flot",
+                  "seriesOverrides": [ ],
+                  "spaceLength": 10,
+                  "span": 12,
+                  "stack": true,
+                  "steppedLine": false,
+                  "targets": [
+                     {
+                        "expr": "count(cortex_config_hash{cluster=~\"$cluster\", namespace=~\"$namespace\"}) by (sha256)",
+                        "format": "time_series",
+                        "intervalFactor": 2,
+                        "legendFormat": "sha256:{{sha256}}",
+                        "legendLink": null
+                     }
+                  ],
+                  "thresholds": [ ],
+                  "timeFrom": null,
+                  "timeShift": null,
+                  "title": "Startup config file hashes",
+                  "tooltip": {
+                     "shared": false,
+                     "sort": 0,
+                     "value_type": "individual"
+                  },
+                  "type": "graph",
+                  "xaxis": {
+                     "buckets": null,
+                     "mode": "time",
+                     "name": null,
+                     "show": true,
+                     "values": [ ]
+                  },
+                  "yaxes": [
+                     {
+                        "format": "instances",
+                        "label": null,
+                        "logBase": 1,
+                        "max": null,
+                        "min": 0,
+                        "show": true
+                     },
+                     {
+                        "format": "short",
+                        "label": null,
+                        "logBase": 1,
+                        "max": null,
+                        "min": null,
+                        "show": false
+                     }
+                  ]
+               }
+            ],
+            "repeat": null,
+            "repeatIteration": null,
+            "repeatRowId": null,
+            "showTitle": true,
+            "title": "Startup config file",
+            "titleSize": "h6"
+         },
+         {
+            "collapse": false,
+            "height": "250px",
+            "panels": [
+               {
+                  "aliasColors": { },
+                  "bars": false,
+                  "dashLength": 10,
+                  "dashes": false,
+                  "datasource": "$datasource",
+                  "fill": 10,
+                  "id": 2,
+                  "legend": {
+                     "avg": false,
+                     "current": false,
+                     "max": false,
+                     "min": false,
+                     "show": true,
+                     "total": false,
+                     "values": false
+                  },
+                  "lines": true,
+                  "linewidth": 0,
+                  "links": [ ],
+                  "nullPointMode": "null as zero",
+                  "percentage": false,
+                  "pointradius": 5,
+                  "points": false,
+                  "renderer": "flot",
+                  "seriesOverrides": [ ],
+                  "spaceLength": 10,
+                  "span": 12,
+                  "stack": true,
+                  "steppedLine": false,
+                  "targets": [
+                     {
+                        "expr": "count(cortex_runtime_config_hash{cluster=~\"$cluster\", namespace=~\"$namespace\"}) by (sha256)",
+                        "format": "time_series",
+                        "intervalFactor": 2,
+                        "legendFormat": "sha256:{{sha256}}",
+                        "legendLink": null
+                     }
+                  ],
+                  "thresholds": [ ],
+                  "timeFrom": null,
+                  "timeShift": null,
+                  "title": "Runtime config file hashes",
+                  "tooltip": {
+                     "shared": false,
+                     "sort": 0,
+                     "value_type": "individual"
+                  },
+                  "type": "graph",
+                  "xaxis": {
+                     "buckets": null,
+                     "mode": "time",
+                     "name": null,
+                     "show": true,
+                     "values": [ ]
+                  },
+                  "yaxes": [
+                     {
+                        "format": "instances",
+                        "label": null,
+                        "logBase": 1,
+                        "max": null,
+                        "min": 0,
+                        "show": true
+                     },
+                     {
+                        "format": "short",
+                        "label": null,
+                        "logBase": 1,
+                        "max": null,
+                        "min": null,
+                        "show": false
+                     }
+                  ]
+               }
+            ],
+            "repeat": null,
+            "repeatIteration": null,
+            "repeatRowId": null,
+            "showTitle": true,
+            "title": "Runtime config file",
+            "titleSize": "h6"
+         }
+      ],
+      "schemaVersion": 14,
+      "style": "dark",
+      "tags": [
+         "mimir"
+      ],
+      "templating": {
+         "list": [
+            {
+               "current": {
+                  "text": "default",
+                  "value": "default"
+               },
+               "hide": 0,
+               "label": "Data Source",
+               "name": "datasource",
+               "options": [ ],
+               "query": "prometheus",
+               "refresh": 1,
+               "regex": "",
+               "type": "datasource"
+            },
+            {
+               "allValue": ".+",
+               "current": {
+                  "selected": true,
+                  "text": "All",
+                  "value": "$__all"
+               },
+               "datasource": "$datasource",
+               "hide": 0,
+               "includeAll": true,
+               "label": "cluster",
+               "multi": true,
+               "name": "cluster",
+               "options": [ ],
+               "query": "label_values(cortex_build_info, cluster)",
+               "refresh": 1,
+               "regex": "",
+               "sort": 1,
+               "tagValuesQuery": "",
+               "tags": [ ],
+               "tagsQuery": "",
+               "type": "query",
+               "useTags": false
+            },
+            {
+               "allValue": ".+",
+               "current": {
+                  "selected": true,
+                  "text": "All",
+                  "value": "$__all"
+               },
+               "datasource": "$datasource",
+               "hide": 0,
+               "includeAll": true,
+               "label": "namespace",
+               "multi": true,
+               "name": "namespace",
+               "options": [ ],
+               "query": "label_values(cortex_build_info{cluster=~\"$cluster\"}, namespace)",
+               "refresh": 1,
+               "regex": "",
+               "sort": 1,
+               "tagValuesQuery": "",
+               "tags": [ ],
+               "tagsQuery": "",
+               "type": "query",
+               "useTags": false
+            }
+         ]
+      },
+      "time": {
+         "from": "now-1h",
+         "to": "now"
+      },
+      "timepicker": {
+         "refresh_intervals": [
+            "5s",
+            "10s",
+            "30s",
+            "1m",
+            "5m",
+            "15m",
+            "30m",
+            "1h",
+            "2h",
+            "1d"
+         ],
+         "time_options": [
+            "5m",
+            "15m",
+            "1h",
+            "6h",
+            "12h",
+            "24h",
+            "2d",
+            "7d",
+            "30d"
+         ]
+      },
+      "timezone": "utc",
+      "title": "Mimir / Config",
+      "uid": "5d9d0b4724c0f80d68467088ec61e003",
+      "version": 0
+   }

charts/meta-monitoring/src/dashboards/mimir-object-store.json

@@ -0,0 +1,938 @@
+{
+      "__requires": [
+         {
+            "id": "grafana",
+            "name": "Grafana",
+            "type": "grafana",
+            "version": "8.0.0"
+         }
+      ],
+      "annotations": {
+         "list": [ ]
+      },
+      "editable": true,
+      "gnetId": null,
+      "graphTooltip": 1,
+      "hideControls": false,
+      "links": [
+         {
+            "asDropdown": true,
+            "icon": "external link",
+            "includeVars": true,
+            "keepTime": true,
+            "tags": [
+               "mimir"
+            ],
+            "targetBlank": false,
+            "title": "Mimir dashboards",
+            "type": "dashboards"
+         }
+      ],
+      "refresh": "10s",
+      "rows": [
+         {
+            "collapse": false,
+            "height": "250px",
+            "panels": [
+               {
+                  "aliasColors": { },
+                  "bars": false,
+                  "dashLength": 10,
+                  "dashes": false,
+                  "datasource": "$datasource",
+                  "fill": 10,
+                  "id": 1,
+                  "legend": {
+                     "avg": false,
+                     "current": false,
+                     "max": false,
+                     "min": false,
+                     "show": true,
+                     "total": false,
+                     "values": false
+                  },
+                  "lines": true,
+                  "linewidth": 0,
+                  "links": [ ],
+                  "nullPointMode": "null as zero",
+                  "percentage": false,
+                  "pointradius": 5,
+                  "points": false,
+                  "renderer": "flot",
+                  "seriesOverrides": [ ],
+                  "spaceLength": 10,
+                  "span": 6,
+                  "stack": true,
+                  "steppedLine": false,
+                  "targets": [
+                     {
+                        "expr": "sum by(component) (rate(thanos_objstore_bucket_operations_total{cluster=~\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval]))",
+                        "format": "time_series",
+                        "intervalFactor": 2,
+                        "legendFormat": "{{component}}",
+                        "legendLink": null
+                     }
+                  ],
+                  "thresholds": [ ],
+                  "timeFrom": null,
+                  "timeShift": null,
+                  "title": "RPS / component",
+                  "tooltip": {
+                     "shared": false,
+                     "sort": 0,
+                     "value_type": "individual"
+                  },
+                  "type": "graph",
+                  "xaxis": {
+                     "buckets": null,
+                     "mode": "time",
+                     "name": null,
+                     "show": true,
+                     "values": [ ]
+                  },
+                  "yaxes": [
+                     {
+                        "format": "reqps",
+                        "label": null,
+                        "logBase": 1,
+                        "max": null,
+                        "min": 0,
+                        "show": true
+                     },
+                     {
+                        "format": "short",
+                        "label": null,
+                        "logBase": 1,
+                        "max": null,
+                        "min": null,
+                        "show": false
+                     }
+                  ]
+               },
+               {
+                  "datasource": "$datasource",
+                  "fieldConfig": {
+                     "defaults": {
+                        "max": 1,
+                        "min": 0,
+                        "noValue": "0",
+                        "unit": "percentunit"
+                     }
+                  },
+                  "id": 2,
+                  "links": [ ],
+                  "options": {
+                     "legend": {
+                        "showLegend": true
+                     },
+                     "tooltip": {
+                        "mode": "single",
+                        "sort": "none"
+                     }
+                  },
+                  "span": 6,
+                  "targets": [
+                     {
+                        "expr": "sum by(component) (rate(thanos_objstore_bucket_operation_failures_total{cluster=~\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])) / sum by(component) (rate(thanos_objstore_bucket_operations_total{cluster=~\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])) >= 0",
+                        "format": "time_series",
+                        "intervalFactor": 2,
+                        "legendFormat": "{{component}}",
+                        "legendLink": null
+                     }
+                  ],
+                  "title": "Error rate / component",
+                  "type": "timeseries"
+               }
+            ],
+            "repeat": null,
+            "repeatIteration": null,
+            "repeatRowId": null,
+            "showTitle": true,
+            "title": "Components",
+            "titleSize": "h6"
+         },
+         {
+            "collapse": false,
+            "height": "250px",
+            "panels": [
+               {
+                  "aliasColors": { },
+                  "bars": false,
+                  "dashLength": 10,
+                  "dashes": false,
+                  "datasource": "$datasource",
+                  "fill": 10,
+                  "id": 3,
+                  "legend": {
+                     "avg": false,
+                     "current": false,
+                     "max": false,
+                     "min": false,
+                     "show": true,
+                     "total": false,
+                     "values": false
+                  },
+                  "lines": true,
+                  "linewidth": 0,
+                  "links": [ ],
+                  "nullPointMode": "null as zero",
+                  "percentage": false,
+                  "pointradius": 5,
+                  "points": false,
+                  "renderer": "flot",
+                  "seriesOverrides": [ ],
+                  "spaceLength": 10,
+                  "span": 6,
+                  "stack": true,
+                  "steppedLine": false,
+                  "targets": [
+                     {
+                        "expr": "sum by(operation) (rate(thanos_objstore_bucket_operations_total{cluster=~\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval]))",
+                        "format": "time_series",
+                        "intervalFactor": 2,
+                        "legendFormat": "{{operation}}",
+                        "legendLink": null
+                     }
+                  ],
+                  "thresholds": [ ],
+                  "timeFrom": null,
+                  "timeShift": null,
+                  "title": "RPS / operation",
+                  "tooltip": {
+                     "shared": false,
+                     "sort": 0,
+                     "value_type": "individual"
+                  },
+                  "type": "graph",
+                  "xaxis": {
+                     "buckets": null,
+                     "mode": "time",
+                     "name": null,
+                     "show": true,
+                     "values": [ ]
+                  },
+                  "yaxes": [
+                     {
+                        "format": "reqps",
+                        "label": null,
+                        "logBase": 1,
+                        "max": null,
+                        "min": 0,
+                        "show": true
+                     },
+                     {
+                        "format": "short",
+                        "label": null,
+                        "logBase": 1,
+                        "max": null,
+                        "min": null,
+                        "show": false
+                     }
+                  ]
+               },
+               {
+                  "datasource": "$datasource",
+                  "fieldConfig": {
+                     "defaults": {
+                        "max": 1,
+                        "min": 0,
+                        "noValue": "0",
+                        "unit": "percentunit"
+                     }
+                  },
+                  "id": 4,
+                  "links": [ ],
+                  "options": {
+                     "legend": {
+                        "showLegend": true
+                     },
+                     "tooltip": {
+                        "mode": "single",
+                        "sort": "none"
+                     }
+                  },
+                  "span": 6,
+                  "targets": [
+                     {
+                        "expr": "sum by(operation) (rate(thanos_objstore_bucket_operation_failures_total{cluster=~\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])) / sum by(operation) (rate(thanos_objstore_bucket_operations_total{cluster=~\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])) >= 0",
+                        "format": "time_series",
+                        "intervalFactor": 2,
+                        "legendFormat": "{{operation}}",
+                        "legendLink": null
+                     }
+                  ],
+                  "title": "Error rate / operation",
+                  "type": "timeseries"
+               }
+            ],
+            "repeat": null,
+            "repeatIteration": null,
+            "repeatRowId": null,
+            "showTitle": true,
+            "title": "Operations",
+            "titleSize": "h6"
+         },
+         {
+            "collapse": false,
+            "height": "250px",
+            "panels": [
+               {
+                  "aliasColors": { },
+                  "bars": false,
+                  "dashLength": 10,
+                  "dashes": false,
+                  "datasource": "$datasource",
+                  "fill": 1,
+                  "id": 5,
+                  "legend": {
+                     "avg": false,
+                     "current": false,
+                     "max": false,
+                     "min": false,
+                     "show": true,
+                     "total": false,
+                     "values": false
+                  },
+                  "lines": true,
+                  "linewidth": 1,
+                  "links": [ ],
+                  "nullPointMode": "null as zero",
+                  "percentage": false,
+                  "pointradius": 5,
+                  "points": false,
+                  "renderer": "flot",
+                  "seriesOverrides": [ ],
+                  "spaceLength": 10,
+                  "span": 4,
+                  "stack": false,
+                  "steppedLine": false,
+                  "targets": [
+                     {
+                        "expr": "histogram_quantile(0.99, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",operation=\"get\"}[$__rate_interval])) by (le)) * 1e3",
+                        "format": "time_series",
+                        "intervalFactor": 2,
+                        "legendFormat": "99th Percentile",
+                        "refId": "A"
+                     },
+                     {
+                        "expr": "histogram_quantile(0.50, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",operation=\"get\"}[$__rate_interval])) by (le)) * 1e3",
+                        "format": "time_series",
+                        "intervalFactor": 2,
+                        "legendFormat": "50th Percentile",
+                        "refId": "B"
+                     },
+                     {
+                        "expr": "sum(rate(thanos_objstore_bucket_operation_duration_seconds_sum{cluster=~\"$cluster\", namespace=~\"$namespace\",operation=\"get\"}[$__rate_interval])) * 1e3 / sum(rate(thanos_objstore_bucket_operation_duration_seconds_count{cluster=~\"$cluster\", namespace=~\"$namespace\",operation=\"get\"}[$__rate_interval]))",
+                        "format": "time_series",
+                        "intervalFactor": 2,
+                        "legendFormat": "Average",
+                        "refId": "C"
+                     }
+                  ],
+                  "thresholds": [ ],
+                  "timeFrom": null,
+                  "timeShift": null,
+                  "title": "Op: Get",
+                  "tooltip": {
+                     "shared": false,
+                     "sort": 0,
+                     "value_type": "individual"
+                  },
+                  "type": "graph",
+                  "xaxis": {
+                     "buckets": null,
+                     "mode": "time",
+                     "name": null,
+                     "show": true,
+                     "values": [ ]
+                  },
+                  "yaxes": [
+                     {
+                        "format": "ms",
+                        "label": null,
+                        "logBase": 1,
+                        "max": null,
+                        "min": 0,
+                        "show": true
+                     },
+                     {
+                        "format": "short",
+                        "label": null,
+                        "logBase": 1,
+                        "max": null,
+                        "min": null,
+                        "show": false
+                     }
+                  ]
+               },
+               {
+                  "aliasColors": { },
+                  "bars": false,
+                  "dashLength": 10,
+                  "dashes": false,
+                  "datasource": "$datasource",
+                  "fill": 1,
+                  "id": 6,
+                  "legend": {
+                     "avg": false,
+                     "current": false,
+                     "max": false,
+                     "min": false,
+                     "show": true,
+                     "total": false,
+                     "values": false
+                  },
+                  "lines": true,
+                  "linewidth": 1,
+                  "links": [ ],
+                  "nullPointMode": "null as zero",
+                  "percentage": false,
+                  "pointradius": 5,
+                  "points": false,
+                  "renderer": "flot",
+                  "seriesOverrides": [ ],
+                  "spaceLength": 10,
+                  "span": 4,
+                  "stack": false,
+                  "steppedLine": false,
+                  "targets": [
+                     {
+                        "expr": "histogram_quantile(0.99, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",operation=\"get_range\"}[$__rate_interval])) by (le)) * 1e3",
+                        "format": "time_series",
+                        "intervalFactor": 2,
+                        "legendFormat": "99th Percentile",
+                        "refId": "A"
+                     },
+                     {
+                        "expr": "histogram_quantile(0.50, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",operation=\"get_range\"}[$__rate_interval])) by (le)) * 1e3",
+                        "format": "time_series",
+                        "intervalFactor": 2,
+                        "legendFormat": "50th Percentile",
+                        "refId": "B"
+                     },
+                     {
+                        "expr": "sum(rate(thanos_objstore_bucket_operation_duration_seconds_sum{cluster=~\"$cluster\", namespace=~\"$namespace\",operation=\"get_range\"}[$__rate_interval])) * 1e3 / sum(rate(thanos_objstore_bucket_operation_duration_seconds_count{cluster=~\"$cluster\", namespace=~\"$namespace\",operation=\"get_range\"}[$__rate_interval]))",
+                        "format": "time_series",
+                        "intervalFactor": 2,
+                        "legendFormat": "Average",
+                        "refId": "C"
+                     }
+                  ],
+                  "thresholds": [ ],
+                  "timeFrom": null,
+                  "timeShift": null,
+                  "title": "Op: GetRange",
+                  "tooltip": {
+                     "shared": false,
+                     "sort": 0,
+                     "value_type": "individual"
+                  },
+                  "type": "graph",
+                  "xaxis": {
+                     "buckets": null,
+                     "mode": "time",
+                     "name": null,
+                     "show": true,
+                     "values": [ ]
+                  },
+                  "yaxes": [
+                     {
+                        "format": "ms",
+                        "label": null,
+                        "logBase": 1,
+                        "max": null,
+                        "min": 0,
+                        "show": true
+                     },
+                     {
+                        "format": "short",
+                        "label": null,
+                        "logBase": 1,
+                        "max": null,
+                        "min": null,
+                        "show": false
+                     }
+                  ]
+               },
+               {
+                  "aliasColors": { },
+                  "bars": false,
+                  "dashLength": 10,
+                  "dashes": false,
+                  "datasource": "$datasource",
+                  "fill": 1,
+                  "id": 7,
+                  "legend": {
+                     "avg": false,
+                     "current": false,
+                     "max": false,
+                     "min": false,
+                     "show": true,
+                     "total": false,
+                     "values": false
+                  },
+                  "lines": true,
+                  "linewidth": 1,
+                  "links": [ ],
+                  "nullPointMode": "null as zero",
+                  "percentage": false,
+                  "pointradius": 5,
+                  "points": false,
+                  "renderer": "flot",
+                  "seriesOverrides": [ ],
+                  "spaceLength": 10,
+                  "span": 4,
+                  "stack": false,
+                  "steppedLine": false,
+                  "targets": [
+                     {
+                        "expr": "histogram_quantile(0.99, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",operation=\"exists\"}[$__rate_interval])) by (le)) * 1e3",
+                        "format": "time_series",
+                        "intervalFactor": 2,
+                        "legendFormat": "99th Percentile",
+                        "refId": "A"
+                     },
+                     {
+                        "expr": "histogram_quantile(0.50, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",operation=\"exists\"}[$__rate_interval])) by (le)) * 1e3",
+                        "format": "time_series",
+                        "intervalFactor": 2,
+                        "legendFormat": "50th Percentile",
+                        "refId": "B"
+                     },
+                     {
+                        "expr": "sum(rate(thanos_objstore_bucket_operation_duration_seconds_sum{cluster=~\"$cluster\", namespace=~\"$namespace\",operation=\"exists\"}[$__rate_interval])) * 1e3 / sum(rate(thanos_objstore_bucket_operation_duration_seconds_count{cluster=~\"$cluster\", namespace=~\"$namespace\",operation=\"exists\"}[$__rate_interval]))",
+                        "format": "time_series",
+                        "intervalFactor": 2,
+                        "legendFormat": "Average",
+                        "refId": "C"
+                     }
+                  ],
+                  "thresholds": [ ],
+                  "timeFrom": null,
+                  "timeShift": null,
+                  "title": "Op: Exists",
+                  "tooltip": {
+                     "shared": false,
+                     "sort": 0,
+                     "value_type": "individual"
+                  },
+                  "type": "graph",
+                  "xaxis": {
+                     "buckets": null,
+                     "mode": "time",
+                     "name": null,
+                     "show": true,
+                     "values": [ ]
+                  },
+                  "yaxes": [
+                     {
+                        "format": "ms",
+                        "label": null,
+                        "logBase": 1,
+                        "max": null,
+                        "min": 0,
+                        "show": true
+                     },
+                     {
+                        "format": "short",
+                        "label": null,
+                        "logBase": 1,
+                        "max": null,
+                        "min": null,
+                        "show": false
+                     }
+                  ]
+               }
+            ],
+            "repeat": null,
+            "repeatIteration": null,
+            "repeatRowId": null,
+            "showTitle": true,
+            "title": "",
+            "titleSize": "h6"
+         },
+         {
+            "collapse": false,
+            "height": "250px",
+            "panels": [
+               {
+                  "aliasColors": { },
+                  "bars": false,
+                  "dashLength": 10,
+                  "dashes": false,
+                  "datasource": "$datasource",
+                  "fill": 1,
+                  "id": 8,
+                  "legend": {
+                     "avg": false,
+                     "current": false,
+                     "max": false,
+                     "min": false,
+                     "show": true,
+                     "total": false,
+                     "values": false
+                  },
+                  "lines": true,
+                  "linewidth": 1,
+                  "links": [ ],
+                  "nullPointMode": "null as zero",
+                  "percentage": false,
+                  "pointradius": 5,
+                  "points": false,
+                  "renderer": "flot",
+                  "seriesOverrides": [ ],
+                  "spaceLength": 10,
+                  "span": 4,
+                  "stack": false,
+                  "steppedLine": false,
+                  "targets": [
+                     {
+                        "expr": "histogram_quantile(0.99, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",operation=\"attributes\"}[$__rate_interval])) by (le)) * 1e3",
+                        "format": "time_series",
+                        "intervalFactor": 2,
+                        "legendFormat": "99th Percentile",
+                        "refId": "A"
+                     },
+                     {
+                        "expr": "histogram_quantile(0.50, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",operation=\"attributes\"}[$__rate_interval])) by (le)) * 1e3",
+                        "format": "time_series",
+                        "intervalFactor": 2,
+                        "legendFormat": "50th Percentile",
+                        "refId": "B"
+                     },
+                     {
+                        "expr": "sum(rate(thanos_objstore_bucket_operation_duration_seconds_sum{cluster=~\"$cluster\", namespace=~\"$namespace\",operation=\"attributes\"}[$__rate_interval])) * 1e3 / sum(rate(thanos_objstore_bucket_operation_duration_seconds_count{cluster=~\"$cluster\", namespace=~\"$namespace\",operation=\"attributes\"}[$__rate_interval]))",
+                        "format": "time_series",
+                        "intervalFactor": 2,
+                        "legendFormat": "Average",
+                        "refId": "C"
+                     }
+                  ],
+                  "thresholds": [ ],
+                  "timeFrom": null,
+                  "timeShift": null,
+                  "title": "Op: Attributes",
+                  "tooltip": {
+                     "shared": false,
+                     "sort": 0,
+                     "value_type": "individual"
+                  },
+                  "type": "graph",
+                  "xaxis": {
+                     "buckets": null,
+                     "mode": "time",
+                     "name": null,
+                     "show": true,
+                     "values": [ ]
+                  },
+                  "yaxes": [
+                     {
+                        "format": "ms",
+                        "label": null,
+                        "logBase": 1,
+                        "max": null,
+                        "min": 0,
+                        "show": true
+                     },
+                     {
+                        "format": "short",
+                        "label": null,
+                        "logBase": 1,
+                        "max": null,
+                        "min": null,
+                        "show": false
+                     }
+                  ]
+               },
+               {
+                  "aliasColors": { },
+                  "bars": false,
+                  "dashLength": 10,
+                  "dashes": false,
+                  "datasource": "$datasource",
+                  "fill": 1,
+                  "id": 9,
+                  "legend": {
+                     "avg": false,
+                     "current": false,
+                     "max": false,
+                     "min": false,
+                     "show": true,
+                     "total": false,
+                     "values": false
+                  },
+                  "lines": true,
+                  "linewidth": 1,
+                  "links": [ ],
+                  "nullPointMode": "null as zero",
+                  "percentage": false,
+                  "pointradius": 5,
+                  "points": false,
+                  "renderer": "flot",
+                  "seriesOverrides": [ ],
+                  "spaceLength": 10,
+                  "span": 4,
+                  "stack": false,
+                  "steppedLine": false,
+                  "targets": [
+                     {
+                        "expr": "histogram_quantile(0.99, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",operation=\"upload\"}[$__rate_interval])) by (le)) * 1e3",
+                        "format": "time_series",
+                        "intervalFactor": 2,
+                        "legendFormat": "99th Percentile",
+                        "refId": "A"
+                     },
+                     {
+                        "expr": "histogram_quantile(0.50, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",operation=\"upload\"}[$__rate_interval])) by (le)) * 1e3",
+                        "format": "time_series",
+                        "intervalFactor": 2,
+                        "legendFormat": "50th Percentile",
+                        "refId": "B"
+                     },
+                     {
+                        "expr": "sum(rate(thanos_objstore_bucket_operation_duration_seconds_sum{cluster=~\"$cluster\", namespace=~\"$namespace\",operation=\"upload\"}[$__rate_interval])) * 1e3 / sum(rate(thanos_objstore_bucket_operation_duration_seconds_count{cluster=~\"$cluster\", namespace=~\"$namespace\",operation=\"upload\"}[$__rate_interval]))",
+                        "format": "time_series",
+                        "intervalFactor": 2,
+                        "legendFormat": "Average",
+                        "refId": "C"
+                     }
+                  ],
+                  "thresholds": [ ],
+                  "timeFrom": null,
+                  "timeShift": null,
+                  "title": "Op: Upload",
+                  "tooltip": {
+                     "shared": false,
+                     "sort": 0,
+                     "value_type": "individual"
+                  },
+                  "type": "graph",
+                  "xaxis": {
+                     "buckets": null,
+                     "mode": "time",
+                     "name": null,
+                     "show": true,
+                     "values": [ ]
+                  },
+                  "yaxes": [
+                     {
+                        "format": "ms",
+                        "label": null,
+                        "logBase": 1,
+                        "max": null,
+                        "min": 0,
+                        "show": true
+                     },
+                     {
+                        "format": "short",
+                        "label": null,
+                        "logBase": 1,
+                        "max": null,
+                        "min": null,
+                        "show": false
+                     }
+                  ]
+               },
+               {
+                  "aliasColors": { },
+                  "bars": false,
+                  "dashLength": 10,
+                  "dashes": false,
+                  "datasource": "$datasource",
+                  "fill": 1,
+                  "id": 10,
+                  "legend": {
+                     "avg": false,
+                     "current": false,
+                     "max": false,
+                     "min": false,
+                     "show": true,
+                     "total": false,
+                     "values": false
+                  },
+                  "lines": true,
+                  "linewidth": 1,
+                  "links": [ ],
+                  "nullPointMode": "null as zero",
+                  "percentage": false,
+                  "pointradius": 5,
+                  "points": false,
+                  "renderer": "flot",
+                  "seriesOverrides": [ ],
+                  "spaceLength": 10,
+                  "span": 4,
+                  "stack": false,
+                  "steppedLine": false,
+                  "targets": [
+                     {
+                        "expr": "histogram_quantile(0.99, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",operation=\"delete\"}[$__rate_interval])) by (le)) * 1e3",
+                        "format": "time_series",
+                        "intervalFactor": 2,
+                        "legendFormat": "99th Percentile",
+                        "refId": "A"
+                     },
+                     {
+                        "expr": "histogram_quantile(0.50, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",operation=\"delete\"}[$__rate_interval])) by (le)) * 1e3",
+                        "format": "time_series",
+                        "intervalFactor": 2,
+                        "legendFormat": "50th Percentile",
+                        "refId": "B"
+                     },
+                     {
+                        "expr": "sum(rate(thanos_objstore_bucket_operation_duration_seconds_sum{cluster=~\"$cluster\", namespace=~\"$namespace\",operation=\"delete\"}[$__rate_interval])) * 1e3 / sum(rate(thanos_objstore_bucket_operation_duration_seconds_count{cluster=~\"$cluster\", namespace=~\"$namespace\",operation=\"delete\"}[$__rate_interval]))",
+                        "format": "time_series",
+                        "intervalFactor": 2,
+                        "legendFormat": "Average",
+                        "refId": "C"
+                     }
+                  ],
+                  "thresholds": [ ],
+                  "timeFrom": null,
+                  "timeShift": null,
+                  "title": "Op: Delete",
+                  "tooltip": {
+                     "shared": false,
+                     "sort": 0,
+                     "value_type": "individual"
+                  },
+                  "type": "graph",
+                  "xaxis": {
+                     "buckets": null,
+                     "mode": "time",
+                     "name": null,
+                     "show": true,
+                     "values": [ ]
+                  },
+                  "yaxes": [
+                     {
+                        "format": "ms",
+                        "label": null,
+                        "logBase": 1,
+                        "max": null,
+                        "min": 0,
+                        "show": true
+                     },
+                     {
+                        "format": "short",
+                        "label": null,
+                        "logBase": 1,
+                        "max": null,
+                        "min": null,
+                        "show": false
+                     }
+                  ]
+               }
+            ],
+            "repeat": null,
+            "repeatIteration": null,
+            "repeatRowId": null,
+            "showTitle": true,
+            "title": "",
+            "titleSize": "h6"
+         }
+      ],
+      "schemaVersion": 14,
+      "style": "dark",
+      "tags": [
+         "mimir"
+      ],
+      "templating": {
+         "list": [
+            {
+               "current": {
+                  "text": "default",
+                  "value": "default"
+               },
+               "hide": 0,
+               "label": "Data Source",
+               "name": "datasource",
+               "options": [ ],
+               "query": "prometheus",
+               "refresh": 1,
+               "regex": "",
+               "type": "datasource"
+            },
+            {
+               "allValue": ".+",
+               "current": {
+                  "selected": true,
+                  "text": "All",
+                  "value": "$__all"
+               },
+               "datasource": "$datasource",
+               "hide": 0,
+               "includeAll": true,
+               "label": "cluster",
+               "multi": true,
+               "name": "cluster",
+               "options": [ ],
+               "query": "label_values(cortex_build_info, cluster)",
+               "refresh": 1,
+               "regex": "",
+               "sort": 1,
+               "tagValuesQuery": "",
+               "tags": [ ],
+               "tagsQuery": "",
+               "type": "query",
+               "useTags": false
+            },
+            {
+               "allValue": ".+",
+               "current": {
+                  "selected": true,
+                  "text": "All",
+                  "value": "$__all"
+               },
+               "datasource": "$datasource",
+               "hide": 0,
+               "includeAll": true,
+               "label": "namespace",
+               "multi": true,
+               "name": "namespace",
+               "options": [ ],
+               "query": "label_values(cortex_build_info{cluster=~\"$cluster\"}, namespace)",
+               "refresh": 1,
+               "regex": "",
+               "sort": 1,
+               "tagValuesQuery": "",
+               "tags": [ ],
+               "tagsQuery": "",
+               "type": "query",
+               "useTags": false
+            }
+         ]
+      },
+      "time": {
+         "from": "now-1h",
+         "to": "now"
+      },
+      "timepicker": {
+         "refresh_intervals": [
+            "5s",
+            "10s",
+            "30s",
+            "1m",
+            "5m",
+            "15m",
+            "30m",
+            "1h",
+            "2h",
+            "1d"
+         ],
+         "time_options": [
+            "5m",
+            "15m",
+            "1h",
+            "6h",
+            "12h",
+            "24h",
+            "2d",
+            "7d",
+            "30d"
+         ]
+      },
+      "timezone": "utc",
+      "title": "Mimir / Object Store",
+      "uid": "e1324ee2a434f4158c00a9ee279d3292",
+      "version": 0
+   }

charts/meta-monitoring/src/dashboards/mimir-overrides.json

@@ -0,0 +1,266 @@
+{
+      "__requires": [
+         {
+            "id": "grafana",
+            "name": "Grafana",
+            "type": "grafana",
+            "version": "8.0.0"
+         }
+      ],
+      "annotations": {
+         "list": [ ]
+      },
+      "editable": true,
+      "gnetId": null,
+      "graphTooltip": 1,
+      "hideControls": false,
+      "links": [
+         {
+            "asDropdown": true,
+            "icon": "external link",
+            "includeVars": true,
+            "keepTime": true,
+            "tags": [
+               "mimir"
+            ],
+            "targetBlank": false,
+            "title": "Mimir dashboards",
+            "type": "dashboards"
+         }
+      ],
+      "refresh": "",
+      "rows": [
+         {
+            "collapse": false,
+            "height": "250px",
+            "panels": [
+               {
+                  "datasource": "${datasource}",
+                  "id": 1,
+                  "span": 12,
+                  "targets": [
+                     {
+                        "expr": "max by(limit_name) (cortex_limits_defaults{cluster=~\"$cluster\",namespace=~\"$namespace\"})",
+                        "instant": true,
+                        "legendFormat": "",
+                        "refId": "A"
+                     }
+                  ],
+                  "title": "Defaults",
+                  "transformations": [
+                     {
+                        "id": "labelsToFields",
+                        "options": { }
+                     },
+                     {
+                        "id": "merge",
+                        "options": { }
+                     },
+                     {
+                        "id": "organize",
+                        "options": {
+                           "excludeByName": {
+                              "Time": true
+                           },
+                           "indexByName": {
+                              "Value": 1,
+                              "limit_name": 0
+                           }
+                        }
+                     },
+                     {
+                        "id": "sortBy",
+                        "options": {
+                           "fields": { },
+                           "sort": [
+                              {
+                                 "field": "limit_name"
+                              }
+                           ]
+                        }
+                     }
+                  ],
+                  "type": "table"
+               }
+            ],
+            "repeat": null,
+            "repeatIteration": null,
+            "repeatRowId": null,
+            "showTitle": true,
+            "title": "",
+            "titleSize": "h6"
+         },
+         {
+            "collapse": false,
+            "height": "250px",
+            "panels": [
+               {
+                  "datasource": "${datasource}",
+                  "id": 2,
+                  "span": 12,
+                  "targets": [
+                     {
+                        "expr": "max by(user, limit_name) (cortex_limits_overrides{cluster=~\"$cluster\",namespace=~\"$namespace\",user=~\"${tenant_id}\"})",
+                        "instant": true,
+                        "legendFormat": "",
+                        "refId": "A"
+                     }
+                  ],
+                  "title": "Per-tenant overrides",
+                  "transformations": [
+                     {
+                        "id": "labelsToFields",
+                        "options": {
+                           "mode": "columns",
+                           "valueLabel": "limit_name"
+                        }
+                     },
+                     {
+                        "id": "merge",
+                        "options": { }
+                     },
+                     {
+                        "id": "organize",
+                        "options": {
+                           "excludeByName": {
+                              "Time": true
+                           },
+                           "indexByName": {
+                              "user": 0
+                           }
+                        }
+                     }
+                  ],
+                  "type": "table"
+               }
+            ],
+            "repeat": null,
+            "repeatIteration": null,
+            "repeatRowId": null,
+            "showTitle": true,
+            "title": "",
+            "titleSize": "h6"
+         }
+      ],
+      "schemaVersion": 14,
+      "style": "dark",
+      "tags": [
+         "mimir"
+      ],
+      "templating": {
+         "list": [
+            {
+               "current": {
+                  "text": "default",
+                  "value": "default"
+               },
+               "hide": 0,
+               "label": "Data Source",
+               "name": "datasource",
+               "options": [ ],
+               "query": "prometheus",
+               "refresh": 1,
+               "regex": "",
+               "type": "datasource"
+            },
+            {
+               "allValue": ".*",
+               "current": {
+                  "text": "prod",
+                  "value": "prod"
+               },
+               "datasource": "$datasource",
+               "hide": 0,
+               "includeAll": true,
+               "label": "cluster",
+               "multi": false,
+               "name": "cluster",
+               "options": [ ],
+               "query": "label_values(cortex_build_info, cluster)",
+               "refresh": 1,
+               "regex": "",
+               "sort": 1,
+               "tagValuesQuery": "",
+               "tags": [ ],
+               "tagsQuery": "",
+               "type": "query",
+               "useTags": false
+            },
+            {
+               "allValue": null,
+               "current": {
+                  "text": "prod",
+                  "value": "prod"
+               },
+               "datasource": "$datasource",
+               "hide": 0,
+               "includeAll": false,
+               "label": "namespace",
+               "multi": false,
+               "name": "namespace",
+               "options": [ ],
+               "query": "label_values(cortex_build_info{cluster=~\"$cluster\"}, namespace)",
+               "refresh": 1,
+               "regex": "",
+               "sort": 1,
+               "tagValuesQuery": "",
+               "tags": [ ],
+               "tagsQuery": "",
+               "type": "query",
+               "useTags": false
+            },
+            {
+               "current": {
+                  "selected": true,
+                  "text": ".*",
+                  "value": ".*"
+               },
+               "hide": 0,
+               "label": "Tenant ID",
+               "name": "tenant_id",
+               "options": [
+                  {
+                     "selected": true,
+                     "text": ".*",
+                     "value": ".*"
+                  }
+               ],
+               "query": ".*",
+               "type": "textbox"
+            }
+         ]
+      },
+      "time": {
+         "from": "now-1h",
+         "to": "now"
+      },
+      "timepicker": {
+         "refresh_intervals": [
+            "5s",
+            "10s",
+            "30s",
+            "1m",
+            "5m",
+            "15m",
+            "30m",
+            "1h",
+            "2h",
+            "1d"
+         ],
+         "time_options": [
+            "5m",
+            "15m",
+            "1h",
+            "6h",
+            "12h",
+            "24h",
+            "2d",
+            "7d",
+            "30d"
+         ]
+      },
+      "timezone": "utc",
+      "title": "Mimir / Overrides",
+      "uid": "1e2c358600ac53f09faea133f811b5bb",
+      "version": 0
+   }

charts/meta-monitoring/src/dashboards/mimir-scaling.json

@@ -0,0 +1,362 @@
+{
+      "__requires": [
+         {
+            "id": "grafana",
+            "name": "Grafana",
+            "type": "grafana",
+            "version": "8.0.0"
+         }
+      ],
+      "annotations": {
+         "list": [ ]
+      },
+      "editable": true,
+      "gnetId": null,
+      "graphTooltip": 1,
+      "hideControls": false,
+      "links": [
+         {
+            "asDropdown": true,
+            "icon": "external link",
+            "includeVars": true,
+            "keepTime": true,
+            "tags": [
+               "mimir"
+            ],
+            "targetBlank": false,
+            "title": "Mimir dashboards",
+            "type": "dashboards"
+         }
+      ],
+      "refresh": "10s",
+      "rows": [
+         {
+            "collapse": false,
+            "height": "200px",
+            "panels": [
+               {
+                  "id": 1,
+                  "options": {
+                     "content": "This dashboard identifies scaling-related issues by suggesting services that you might want to scale up.\nThe table that follows contains a suggested number of replicas and the reason why.\nIf the system is failing and depending on the reason, try scaling up to the specified number.\nThe specified numbers are intended as helpful guidelines when things go wrong, rather than prescriptive guidelines.\n\nReasons:\n- **sample_rate**: There are not enough replicas to handle the\n  sample rate.  Applies to distributor and ingesters.\n- **active_series**: There are not enough replicas\n  to handle the number of active series.  Applies to ingesters.\n- **cpu_usage**: There are not enough replicas\n  based on the CPU usage of the jobs vs the resource requests.\n  Applies to all jobs.\n- **memory_usage**: There are not enough replicas based on the memory\n  usage vs the resource requests.  Applies to all jobs.\n- **active_series_limits**: There are not enough replicas to hold 60% of the\n  sum of all the per tenant series limits.\n- **sample_rate_limits**: There are not enough replicas to handle 60% of the\n  sum of all the per tenant rate limits.\n",
+                     "mode": "markdown"
+                  },
+                  "span": 12,
+                  "title": "",
+                  "type": "text"
+               }
+            ],
+            "repeat": null,
+            "repeatIteration": null,
+            "repeatRowId": null,
+            "showTitle": true,
+            "title": "Service scaling",
+            "titleSize": "h6"
+         },
+         {
+            "collapse": false,
+            "height": "400px",
+            "panels": [
+               {
+                  "aliasColors": { },
+                  "bars": false,
+                  "dashLength": 10,
+                  "dashes": false,
+                  "datasource": "$datasource",
+                  "fill": 1,
+                  "id": 2,
+                  "legend": {
+                     "avg": false,
+                     "current": false,
+                     "max": false,
+                     "min": false,
+                     "show": true,
+                     "total": false,
+                     "values": false
+                  },
+                  "lines": true,
+                  "linewidth": 1,
+                  "links": [ ],
+                  "nullPointMode": "null as zero",
+                  "percentage": false,
+                  "pointradius": 5,
+                  "points": false,
+                  "renderer": "flot",
+                  "seriesOverrides": [ ],
+                  "sort": {
+                     "col": 0,
+                     "desc": false
+                  },
+                  "spaceLength": 10,
+                  "span": 12,
+                  "stack": false,
+                  "steppedLine": false,
+                  "styles": [
+                     {
+                        "alias": "Time",
+                        "dateFormat": "YYYY-MM-DD HH:mm:ss",
+                        "pattern": "Time",
+                        "type": "hidden"
+                     },
+                     {
+                        "alias": "Required Replicas",
+                        "colorMode": null,
+                        "colors": [ ],
+                        "dateFormat": "YYYY-MM-DD HH:mm:ss",
+                        "decimals": 0,
+                        "link": false,
+                        "linkTargetBlank": false,
+                        "linkTooltip": "Drill down",
+                        "linkUrl": "",
+                        "pattern": "Value",
+                        "thresholds": [ ],
+                        "type": "number",
+                        "unit": "short"
+                     },
+                     {
+                        "alias": "Cluster",
+                        "colorMode": null,
+                        "colors": [ ],
+                        "dateFormat": "YYYY-MM-DD HH:mm:ss",
+                        "decimals": 2,
+                        "link": false,
+                        "linkTargetBlank": false,
+                        "linkTooltip": "Drill down",
+                        "linkUrl": "",
+                        "pattern": "__name__",
+                        "thresholds": [ ],
+                        "type": "hidden",
+                        "unit": "short"
+                     },
+                     {
+                        "alias": "Cluster",
+                        "colorMode": null,
+                        "colors": [ ],
+                        "dateFormat": "YYYY-MM-DD HH:mm:ss",
+                        "decimals": 2,
+                        "link": false,
+                        "linkTargetBlank": false,
+                        "linkTooltip": "Drill down",
+                        "linkUrl": "",
+                        "pattern": "cluster",
+                        "thresholds": [ ],
+                        "type": "number",
+                        "unit": "short"
+                     },
+                     {
+                        "alias": "Service",
+                        "colorMode": null,
+                        "colors": [ ],
+                        "dateFormat": "YYYY-MM-DD HH:mm:ss",
+                        "decimals": 2,
+                        "link": false,
+                        "linkTargetBlank": false,
+                        "linkTooltip": "Drill down",
+                        "linkUrl": "",
+                        "pattern": "deployment",
+                        "thresholds": [ ],
+                        "type": "number",
+                        "unit": "short"
+                     },
+                     {
+                        "alias": "Namespace",
+                        "colorMode": null,
+                        "colors": [ ],
+                        "dateFormat": "YYYY-MM-DD HH:mm:ss",
+                        "decimals": 2,
+                        "link": false,
+                        "linkTargetBlank": false,
+                        "linkTooltip": "Drill down",
+                        "linkUrl": "",
+                        "pattern": "namespace",
+                        "thresholds": [ ],
+                        "type": "number",
+                        "unit": "short"
+                     },
+                     {
+                        "alias": "Reason",
+                        "colorMode": null,
+                        "colors": [ ],
+                        "dateFormat": "YYYY-MM-DD HH:mm:ss",
+                        "decimals": 2,
+                        "link": false,
+                        "linkTargetBlank": false,
+                        "linkTooltip": "Drill down",
+                        "linkUrl": "",
+                        "pattern": "reason",
+                        "thresholds": [ ],
+                        "type": "number",
+                        "unit": "short"
+                     },
+                     {
+                        "alias": "",
+                        "colorMode": null,
+                        "colors": [ ],
+                        "dateFormat": "YYYY-MM-DD HH:mm:ss",
+                        "decimals": 2,
+                        "pattern": "/.*/",
+                        "thresholds": [ ],
+                        "type": "string",
+                        "unit": "short"
+                     }
+                  ],
+                  "targets": [
+                     {
+                        "expr": "sort_desc(\n  cluster_namespace_deployment_reason:required_replicas:count{cluster=~\"$cluster\", namespace=~\"$namespace\"}\n    > ignoring(reason) group_left\n  cluster_namespace_deployment:actual_replicas:count{cluster=~\"$cluster\", namespace=~\"$namespace\"}\n)\n",
+                        "format": "table",
+                        "instant": true,
+                        "intervalFactor": 2,
+                        "legendFormat": "",
+                        "refId": "A"
+                     }
+                  ],
+                  "thresholds": [ ],
+                  "timeFrom": null,
+                  "timeShift": null,
+                  "title": "Workload-based scaling",
+                  "tooltip": {
+                     "shared": false,
+                     "sort": 0,
+                     "value_type": "individual"
+                  },
+                  "transform": "table",
+                  "type": "table",
+                  "xaxis": {
+                     "buckets": null,
+                     "mode": "time",
+                     "name": null,
+                     "show": true,
+                     "values": [ ]
+                  },
+                  "yaxes": [
+                     {
+                        "format": "short",
+                        "label": null,
+                        "logBase": 1,
+                        "max": null,
+                        "min": 0,
+                        "show": true
+                     },
+                     {
+                        "format": "short",
+                        "label": null,
+                        "logBase": 1,
+                        "max": null,
+                        "min": null,
+                        "show": false
+                     }
+                  ]
+               }
+            ],
+            "repeat": null,
+            "repeatIteration": null,
+            "repeatRowId": null,
+            "showTitle": true,
+            "title": "Scaling",
+            "titleSize": "h6"
+         }
+      ],
+      "schemaVersion": 14,
+      "style": "dark",
+      "tags": [
+         "mimir"
+      ],
+      "templating": {
+         "list": [
+            {
+               "current": {
+                  "text": "default",
+                  "value": "default"
+               },
+               "hide": 0,
+               "label": "Data Source",
+               "name": "datasource",
+               "options": [ ],
+               "query": "prometheus",
+               "refresh": 1,
+               "regex": "",
+               "type": "datasource"
+            },
+            {
+               "allValue": ".+",
+               "current": {
+                  "selected": true,
+                  "text": "All",
+                  "value": "$__all"
+               },
+               "datasource": "$datasource",
+               "hide": 0,
+               "includeAll": true,
+               "label": "cluster",
+               "multi": true,
+               "name": "cluster",
+               "options": [ ],
+               "query": "label_values(cortex_build_info, cluster)",
+               "refresh": 1,
+               "regex": "",
+               "sort": 1,
+               "tagValuesQuery": "",
+               "tags": [ ],
+               "tagsQuery": "",
+               "type": "query",
+               "useTags": false
+            },
+            {
+               "allValue": ".+",
+               "current": {
+                  "selected": true,
+                  "text": "All",
+                  "value": "$__all"
+               },
+               "datasource": "$datasource",
+               "hide": 0,
+               "includeAll": true,
+               "label": "namespace",
+               "multi": true,
+               "name": "namespace",
+               "options": [ ],
+               "query": "label_values(cortex_build_info{cluster=~\"$cluster\"}, namespace)",
+               "refresh": 1,
+               "regex": "",
+               "sort": 1,
+               "tagValuesQuery": "",
+               "tags": [ ],
+               "tagsQuery": "",
+               "type": "query",
+               "useTags": false
+            }
+         ]
+      },
+      "time": {
+         "from": "now-1h",
+         "to": "now"
+      },
+      "timepicker": {
+         "refresh_intervals": [
+            "5s",
+            "10s",
+            "30s",
+            "1m",
+            "5m",
+            "15m",
+            "30m",
+            "1h",
+            "2h",
+            "1d"
+         ],
+         "time_options": [
+            "5m",
+            "15m",
+            "1h",
+            "6h",
+            "12h",
+            "24h",
+            "2d",
+            "7d",
+            "30d"
+         ]
+      },
+      "timezone": "utc",
+      "title": "Mimir / Scaling",
+      "uid": "64bbad83507b7289b514725658e10352",
+      "version": 0
+   }

charts/meta-monitoring/src/dashboards/mimir-slow-queries.json

@@ -0,0 +1,323 @@
+{
+      "__requires": [
+         {
+            "id": "grafana",
+            "name": "Grafana",
+            "type": "grafana",
+            "version": "8.0.0"
+         }
+      ],
+      "annotations": {
+         "list": [ ]
+      },
+      "editable": true,
+      "gnetId": null,
+      "graphTooltip": 1,
+      "hideControls": false,
+      "links": [
+         {
+            "asDropdown": true,
+            "icon": "external link",
+            "includeVars": true,
+            "keepTime": true,
+            "tags": [
+               "mimir"
+            ],
+            "targetBlank": false,
+            "title": "Mimir dashboards",
+            "type": "dashboards"
+         }
+      ],
+      "refresh": "",
+      "rows": [
+         {
+            "collapse": false,
+            "height": "250px",
+            "panels": [
+               {
+                  "datasource": "${lokidatasource}",
+                  "fieldConfig": {
+                     "overrides": [
+                        {
+                           "matcher": {
+                              "id": "byName",
+                              "options": "Time range"
+                           },
+                           "properties": [
+                              {
+                                 "id": "mappings",
+                                 "value": [
+                                    {
+                                       "from": "",
+                                       "id": 1,
+                                       "text": "Instant query",
+                                       "to": "",
+                                       "type": 1,
+                                       "value": "0"
+                                    }
+                                 ]
+                              },
+                              {
+                                 "id": "unit",
+                                 "value": "s"
+                              }
+                           ]
+                        },
+                        {
+                           "matcher": {
+                              "id": "byName",
+                              "options": "Step"
+                           },
+                           "properties": [
+                              {
+                                 "id": "unit",
+                                 "value": "s"
+                              }
+                           ]
+                        }
+                     ]
+                  },
+                  "id": 1,
+                  "span": 12,
+                  "targets": [
+                     {
+                        "expr": "{cluster=~\"$cluster\",namespace=~\"$namespace\",name=~\"query-frontend.*\"} |= \"query stats\" != \"/api/v1/read\" | logfmt | user=~\"${tenant_id}\" | response_time > ${min_duration}",
+                        "instant": false,
+                        "legendFormat": "",
+                        "range": true,
+                        "refId": "A"
+                     }
+                  ],
+                  "title": "Slow queries",
+                  "transformations": [
+                     {
+                        "id": "extractFields",
+                        "options": {
+                           "source": "labels"
+                        }
+                     },
+                     {
+                        "id": "calculateField",
+                        "options": {
+                           "alias": "Time range",
+                           "binary": {
+                              "left": "param_end",
+                              "operator": "-",
+                              "reducer": "sum",
+                              "right": "param_start"
+                           },
+                           "mode": "binary",
+                           "reduce": {
+                              "reducer": "sum"
+                           },
+                           "replaceFields": false
+                        }
+                     },
+                     {
+                        "id": "organize",
+                        "options": {
+                           "excludeByName": {
+                              "Line": true,
+                              "Time": true,
+                              "caller": true,
+                              "cluster": true,
+                              "container": true,
+                              "host": true,
+                              "id": true,
+                              "job": true,
+                              "labels": true,
+                              "level": true,
+                              "line": true,
+                              "method": true,
+                              "msg": true,
+                              "name": true,
+                              "namespace": true,
+                              "param_end": true,
+                              "param_start": true,
+                              "param_time": true,
+                              "path": true,
+                              "pod": true,
+                              "pod_template_hash": true,
+                              "query_wall_time_seconds": true,
+                              "stream": true,
+                              "traceID": true,
+                              "tsNs": true
+                           },
+                           "indexByName": {
+                              "Time range": 3,
+                              "param_query": 2,
+                              "param_step": 4,
+                              "response_time": 5,
+                              "ts": 0,
+                              "user": 1
+                           },
+                           "renameByName": {
+                              "org_id": "Tenant ID",
+                              "param_query": "Query",
+                              "param_step": "Step",
+                              "response_time": "Duration"
+                           }
+                        }
+                     }
+                  ],
+                  "type": "table"
+               }
+            ],
+            "repeat": null,
+            "repeatIteration": null,
+            "repeatRowId": null,
+            "showTitle": true,
+            "title": "",
+            "titleSize": "h6"
+         }
+      ],
+      "schemaVersion": 14,
+      "style": "dark",
+      "tags": [
+         "mimir"
+      ],
+      "templating": {
+         "list": [
+            {
+               "current": {
+                  "text": "default",
+                  "value": "default"
+               },
+               "hide": 0,
+               "label": "Data Source",
+               "name": "datasource",
+               "options": [ ],
+               "query": "prometheus",
+               "refresh": 1,
+               "regex": "",
+               "type": "datasource"
+            },
+            {
+               "allValue": ".*",
+               "current": {
+                  "text": "prod",
+                  "value": "prod"
+               },
+               "datasource": "$datasource",
+               "hide": 0,
+               "includeAll": true,
+               "label": "cluster",
+               "multi": false,
+               "name": "cluster",
+               "options": [ ],
+               "query": "label_values(cortex_build_info, cluster)",
+               "refresh": 1,
+               "regex": "",
+               "sort": 1,
+               "tagValuesQuery": "",
+               "tags": [ ],
+               "tagsQuery": "",
+               "type": "query",
+               "useTags": false
+            },
+            {
+               "allValue": null,
+               "current": {
+                  "text": "prod",
+                  "value": "prod"
+               },
+               "datasource": "$datasource",
+               "hide": 0,
+               "includeAll": false,
+               "label": "namespace",
+               "multi": false,
+               "name": "namespace",
+               "options": [ ],
+               "query": "label_values(cortex_build_info{cluster=~\"$cluster\"}, namespace)",
+               "refresh": 1,
+               "regex": "",
+               "sort": 1,
+               "tagValuesQuery": "",
+               "tags": [ ],
+               "tagsQuery": "",
+               "type": "query",
+               "useTags": false
+            },
+            {
+               "hide": 0,
+               "includeAll": false,
+               "label": "Logs datasource",
+               "multi": false,
+               "name": "lokidatasource",
+               "query": "loki",
+               "type": "datasource"
+            },
+            {
+               "current": {
+                  "selected": true,
+                  "text": "5s",
+                  "value": "5s"
+               },
+               "hide": 0,
+               "label": "Min duration",
+               "name": "min_duration",
+               "options": [
+                  {
+                     "selected": true,
+                     "text": "5s",
+                     "value": "5s"
+                  }
+               ],
+               "query": "5s",
+               "type": "textbox"
+            },
+            {
+               "current": {
+                  "selected": true,
+                  "text": ".*",
+                  "value": ".*"
+               },
+               "hide": 0,
+               "label": "Tenant ID",
+               "name": "tenant_id",
+               "options": [
+                  {
+                     "selected": true,
+                     "text": ".*",
+                     "value": ".*"
+                  }
+               ],
+               "query": ".*",
+               "type": "textbox"
+            }
+         ]
+      },
+      "time": {
+         "from": "now-1h",
+         "to": "now"
+      },
+      "timepicker": {
+         "refresh_intervals": [
+            "5s",
+            "10s",
+            "30s",
+            "1m",
+            "5m",
+            "15m",
+            "30m",
+            "1h",
+            "2h",
+            "1d"
+         ],
+         "time_options": [
+            "5m",
+            "15m",
+            "1h",
+            "6h",
+            "12h",
+            "24h",
+            "2d",
+            "7d",
+            "30d"
+         ]
+      },
+      "timezone": "utc",
+      "title": "Mimir / Slow queries",
+      "uid": "6089e1ce1e678788f46312a0a1e647e6",
+      "version": 0
+   }

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

@@ -0,0 +1,53 @@
+groups:
+- name: "loki_rules"
+  rules:
+  - expr: "histogram_quantile(0.99, sum(rate(loki_request_duration_seconds_bucket[5m]))
+      by (le, cluster, job))"
+    record: "cluster_job:loki_request_duration_seconds:99quantile"
+  - expr: "histogram_quantile(0.50, sum(rate(loki_request_duration_seconds_bucket[5m]))
+      by (le, cluster, job))"
+    record: "cluster_job:loki_request_duration_seconds:50quantile"
+  - expr: "sum(rate(loki_request_duration_seconds_sum[5m])) by (cluster, job) / sum(rate(loki_request_duration_seconds_count[5m]))
+      by (cluster, job)"
+    record: "cluster_job:loki_request_duration_seconds:avg"
+  - expr: "sum(rate(loki_request_duration_seconds_bucket[5m])) by (le, cluster, job)"
+    record: "cluster_job:loki_request_duration_seconds_bucket:sum_rate"
+  - expr: "sum(rate(loki_request_duration_seconds_sum[5m])) by (cluster, job)"
+    record: "cluster_job:loki_request_duration_seconds_sum:sum_rate"
+  - expr: "sum(rate(loki_request_duration_seconds_count[5m])) by (cluster, job)"
+    record: "cluster_job:loki_request_duration_seconds_count:sum_rate"
+  - expr: "histogram_quantile(0.99, sum(rate(loki_request_duration_seconds_bucket[5m]))
+      by (le, cluster, job, route))"
+    record: "cluster_job_route:loki_request_duration_seconds:99quantile"
+  - expr: "histogram_quantile(0.50, sum(rate(loki_request_duration_seconds_bucket[5m]))
+      by (le, cluster, job, route))"
+    record: "cluster_job_route:loki_request_duration_seconds:50quantile"
+  - expr: "sum(rate(loki_request_duration_seconds_sum[5m])) by (cluster, job, route)
+      / sum(rate(loki_request_duration_seconds_count[5m])) by (cluster, job, route)"
+    record: "cluster_job_route:loki_request_duration_seconds:avg"
+  - expr: "sum(rate(loki_request_duration_seconds_bucket[5m])) by (le, cluster, job,
+      route)"
+    record: "cluster_job_route:loki_request_duration_seconds_bucket:sum_rate"
+  - expr: "sum(rate(loki_request_duration_seconds_sum[5m])) by (cluster, job, route)"
+    record: "cluster_job_route:loki_request_duration_seconds_sum:sum_rate"
+  - expr: "sum(rate(loki_request_duration_seconds_count[5m])) by (cluster, job, route)"
+    record: "cluster_job_route:loki_request_duration_seconds_count:sum_rate"
+  - expr: "histogram_quantile(0.99, sum(rate(loki_request_duration_seconds_bucket[5m]))
+      by (le, cluster, namespace, job, route))"
+    record: "cluster_namespace_job_route:loki_request_duration_seconds:99quantile"
+  - expr: "histogram_quantile(0.50, sum(rate(loki_request_duration_seconds_bucket[5m]))
+      by (le, cluster, namespace, job, route))"
+    record: "cluster_namespace_job_route:loki_request_duration_seconds:50quantile"
+  - expr: "sum(rate(loki_request_duration_seconds_sum[5m])) by (cluster, namespace,
+      job, route) / sum(rate(loki_request_duration_seconds_count[5m])) by (cluster,
+      namespace, job, route)"
+    record: "cluster_namespace_job_route:loki_request_duration_seconds:avg"
+  - expr: "sum(rate(loki_request_duration_seconds_bucket[5m])) by (le, cluster, namespace,
+      job, route)"
+    record: "cluster_namespace_job_route:loki_request_duration_seconds_bucket:sum_rate"
+  - expr: "sum(rate(loki_request_duration_seconds_sum[5m])) by (cluster, namespace,
+      job, route)"
+    record: "cluster_namespace_job_route:loki_request_duration_seconds_sum:sum_rate"
+  - expr: "sum(rate(loki_request_duration_seconds_count[5m])) by (cluster, namespace,
+      job, route)"
+    record: "cluster_namespace_job_route:loki_request_duration_seconds_count:sum_rate"

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

@@ -0,0 +1,555 @@
+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

@@ -0,0 +1,15 @@
+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/_helpers.tpl

@@ -0,0 +1,33 @@
+{{/*
+Return the appropriate apiVersion for ingress.
+*/}}
+{{- define "ingress.apiVersion" -}}
+  {{- if and (.Capabilities.APIVersions.Has "networking.k8s.io/v1") (semverCompare ">= 1.19-0" .Capabilities.KubeVersion.Version) -}}
+      {{- print "networking.k8s.io/v1" -}}
+  {{- else if .Capabilities.APIVersions.Has "networking.k8s.io/v1beta1" -}}
+    {{- print "networking.k8s.io/v1beta1" -}}
+  {{- else -}}
+    {{- print "extensions/v1beta1" -}}
+  {{- end -}}
+{{- end -}}
+
+{{/*
+Return if ingress is stable.
+*/}}
+{{- define "ingress.isStable" -}}
+  {{- eq (include "ingress.apiVersion" .) "networking.k8s.io/v1" -}}
+{{- end -}}
+
+{{/*
+Return if ingress supports ingressClassName.
+*/}}
+{{- define "ingress.supportsIngressClassName" -}}
+  {{- or (eq (include "ingress.isStable" .) "true") (and (eq (include "ingress.apiVersion" .) "networking.k8s.io/v1beta1") (semverCompare ">= 1.18-0" .Capabilities.KubeVersion.Version)) -}}
+{{- end -}}
+
+{{/*
+Return if ingress supports pathType.
+*/}}
+{{- define "ingress.supportsPathType" -}}
+  {{- or (eq (include "ingress.isStable" .) "true") (and (eq (include "ingress.apiVersion" .) "networking.k8s.io/v1beta1") (semverCompare ">= 1.18-0" .Capabilities.KubeVersion.Version)) -}}
+{{- end -}}

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

@@ -17,6 +17,14 @@
 {{- join ", " $list }}
 {{- end }}
 
+{{- define "agent.loki_process_targets" -}}
+{{- if and (empty .Values.logs.piiRegexes) (empty .Values.logs.retain) }}
+{{- include "agent.loki_write_targets" . }}
+{{- else }}
+{{- printf "loki.process.filter.receiver" }}
+{{- end }}
+{{- end }}
+
 {{- define "agent.prometheus_write_targets" -}}
 {{- $list := list }}
 {{- if .Values.local.metrics.enabled }}

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

@@ -8,7 +8,7 @@ data:
     discovery.kubernetes "pods" {
       role = "pod"
       namespaces {
-        own_namespace = false
+        own_namespace = true
         names = [ {{ include "agent.namespaces" . }} ]
       }
     }
@@ -33,25 +33,245 @@ data:
       }
       rule {
         target_label = "cluster"
-        replacement = "{{- .Values.clusterName -}}"
+        replacement = "{{- .Values.clusterLabelValue -}}"
       }
     }
 
     {{- if or .Values.local.logs.enabled .Values.cloud.logs.enabled }}
-    loki.source.kubernetes "pods" {
-      targets    = discovery.relabel.rename_meta_labels.output
-      forward_to = [ {{ include "agent.loki_write_targets" . }} ]
+    // Logs
+
+    remote.kubernetes.secret "logs_credentials" {
+      namespace = "{{- $.Release.Namespace -}}"
+      name = "{{- .Values.cloud.logs.secret -}}"
     }
+
+    loki.source.kubernetes "pods" {
+      clustering {
+        enabled = true
+      }
+      targets    = discovery.relabel.rename_meta_labels.output
+      forward_to = [ {{ include "agent.loki_process_targets" . }} ]
+    }
+
+    {{- if or (not (empty .Values.logs.retain)) (not (empty .Values.logs.piiRegexes)) }}
+    loki.process "filter" {
+      forward_to = [ {{ include "agent.loki_write_targets" . }} ]
+
+      {{- if not (empty .Values.logs.retain) }}
+      stage.match {
+        selector = "{cluster=\"{{- .Values.clusterLabelValue -}}\", namespace=~\"{{- join "|" .Values.namespacesToMonitor -}}|{{- $.Release.Namespace -}}\", pod=~\"loki.*\"} !~ \"{{ join "|" .Values.logs.retain }}\""
+        action   = "drop"
+      }
+      {{- end }}
+
+      {{- if not (empty .Values.logs.piiRegexes) }}
+      {{- range .Values.logs.piiRegexes }}
+      stage.replace {
+        expression = "{{ .expression }}"
+        source = "{{ .source }}"
+        replace = "{{ .replace }}"
+      }
+      {{- end }}
+      {{- end }}
+    }
+    {{- end }}
     {{- end }}
 
     {{- if or .Values.local.metrics.enabled .Values.cloud.metrics.enabled }}
+    // Metrics
+
+    remote.kubernetes.secret "metrics_credentials" {
+      namespace = "{{- $.Release.Namespace -}}"
+      name = "{{- .Values.cloud.metrics.secret -}}"
+    }
+
+    discovery.kubernetes "metric_pods" {
+      role = "pod"
+      namespaces {
+        own_namespace = true
+        names = [ {{ include "agent.namespaces" . }} ]
+      }
+    }
+
+    discovery.relabel "only_http_metrics" {
+      targets = discovery.kubernetes.metric_pods.targets
+
+      rule {
+        source_labels = ["__meta_kubernetes_namespace"]
+        target_label  = "namespace"
+      }
+      rule {
+        source_labels = ["__meta_kubernetes_pod_name"]
+        target_label  = "pod"
+      }
+      rule {
+        source_labels = ["__meta_kubernetes_namespace", "__meta_kubernetes_pod_label_app_kubernetes_io_name", "__meta_kubernetes_pod_label_app_kubernetes_io_component"]
+        separator = "/"
+        regex = "(.*)/(.*)/(.*)"
+        replacement = "${1}/${2}-${3}"
+        target_label = "job"
+      }
+      rule {
+        target_label = "cluster"
+        replacement = "{{- .Values.clusterLabelValue -}}"
+      }
+      rule {
+        source_labels = ["__meta_kubernetes_pod_container_port_number"]
+        action = "drop"
+        regex = "9095"
+      }
+    }
+
     prometheus.scrape "pods" {
-      targets    = discovery.relabel.rename_meta_labels.output
+      clustering {
+        enabled = true
+      }
+      targets    = discovery.relabel.only_http_metrics.output
+      forward_to = [ prometheus.relabel.filter.receiver ]
+    }
+
+    prometheus.relabel "filter" {
+      rule {
+        source_labels = ["__name__"]
+        regex = "({{ join "|" .Values.metrics.retain }})"
+        action = "keep"
+      }
+
       forward_to = [ {{ include "agent.prometheus_write_targets" . }} ]
     }
+    {{- if .Values.kubeStateMetrics.enabled }}
+
+    prometheus.scrape "kubeStateMetrics" {
+      clustering {
+        enabled = true
+      }
+      targets    = [ { "__address__" = "{{ .Values.kubeStateMetrics.endpoint }}" } ]
+      forward_to = [ 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"
+    }
+
+    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 }}
+    // Traces
+
+    remote.kubernetes.secret "traces_credentials" {
+      namespace = "{{- $.Release.Namespace -}}"
+      name = "{{- .Values.cloud.traces.secret -}}"
+    }
+
     // Shamelessly copied from https://github.com/grafana/intro-to-mlt/blob/main/agent/config.river
     otelcol.receiver.otlp "otlp_receiver" {
       // We don't technically need this, but it shows how to change listen address and incoming port.
@@ -120,11 +340,10 @@ data:
     {{- if .Values.cloud.logs.enabled }}
     loki.write "cloud" {
       endpoint {
-        url = "{{- .Values.cloud.logs.endpoint -}}/loki/api/v1/push"
-
+        url = nonsensitive(remote.kubernetes.secret.logs_credentials.data["endpoint"])
         basic_auth {
-          username = "{{- .Values.cloud.logs.username -}}"
-          password = "{{- .Values.cloud.logs.password -}}"
+          username = nonsensitive(remote.kubernetes.secret.logs_credentials.data["username"])
+          password = remote.kubernetes.secret.logs_credentials.data["password"]
         }
       }
     }
@@ -133,11 +352,10 @@ data:
     {{- if .Values.cloud.metrics.enabled }}
     prometheus.remote_write "cloud" {
       endpoint {
-        url = "{{- .Values.cloud.metrics.endpoint -}}/api/prom/push"
-
+        url = nonsensitive(remote.kubernetes.secret.metrics_credentials.data["endpoint"])
         basic_auth {
-          username = "{{- .Values.cloud.metrics.username -}}"
-          password = "{{- .Values.cloud.metrics.password -}}"
+          username = nonsensitive(remote.kubernetes.secret.metrics_credentials.data["username"])
+          password = remote.kubernetes.secret.metrics_credentials.data["password"]
         }
       }
     }
@@ -146,13 +364,13 @@ data:
     {{- if .Values.cloud.traces.enabled }}
     otelcol.exporter.otlp "cloud" {
         client {
-            endpoint = "{{- .Values.cloud.traces.endpoint -}}"
+            endpoint = nonsensitive(remote.kubernetes.secret.traces_credentials.data["endpoint"])
             auth = otelcol.auth.basic.creds.handler
         }
     }
 
     otelcol.auth.basic "creds" {
-      username = "{{- .Values.cloud.traces.username -}}"
-      password = "{{- .Values.cloud.traces.password -}}"
+      username = nonsensitive(remote.kubernetes.secret.traces_credentials.data["username"])
+      password = remote.kubernetes.secret.traces_credentials.data["password"]
     }
     {{- end }}

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

@@ -0,0 +1,19 @@
+{{- if and .Values.local.grafana.enabled (or .Values.dashboards.logs.enabled .Values.dashboards.metrics.enabled .Values.dashboards.traces.enabled) }}
+---
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: agent-dashboards-1
+  namespace: {{ $.Release.Namespace }}
+data:
+  "agent-logs-pipeline.json": |
+    {{ $.Files.Get "src/dashboards/agent-logs-pipeline.json" | fromJson | toJson }}
+  "agent-operational.json": |
+    {{ $.Files.Get "src/dashboards/agent-operational.json" | fromJson | toJson }}
+  "agent-remote-write.json": |
+    {{ $.Files.Get "src/dashboards/agent-remote-write.json" | fromJson | toJson }}
+  "agent-tracing-pipeline.json": |
+    {{ $.Files.Get "src/dashboards/agent-tracing-pipeline.json" | fromJson | toJson }}
+  "agent.json": |
+    {{ $.Files.Get "src/dashboards/agent.json" | fromJson | toJson }}
+{{- end }}

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

@@ -1,15 +1,16 @@
-{{- if .Values.local.logs.enabled }}
+{{- if and .Values.local.grafana.enabled (or .Values.dashboards.logs.enabled .Values.dashboards.metrics.enabled .Values.dashboards.traces.enabled) }}
 ---
 apiVersion: v1
 kind: ConfigMap
 metadata:
-  name: loki-dashboards-provisioning
+  name: dashboards-provisioning
   namespace: {{ $.Release.Namespace }}
 data:
   dashboards.yaml: |
     ---
     apiVersion: 1
     providers:
+{{- if .Values.dashboards.logs.enabled }}
       - disableDeletion: true
         editable: false
         folder: Loki
@@ -26,4 +27,65 @@ data:
           path: /var/lib/grafana/dashboards/loki-2
         orgId: 1
         type: file
+{{- end }}
+{{- if .Values.dashboards.metrics.enabled }}
+      - disableDeletion: true
+        editable: false
+        folder: Mimir
+        name: mimir-1
+        options:
+          path: /var/lib/grafana/dashboards/mimir-1
+        orgId: 1
+        type: file
+      - disableDeletion: true
+        editable: false
+        folder: Mimir
+        name: mimir-2
+        options:
+          path: /var/lib/grafana/dashboards/mimir-2
+        orgId: 1
+        type: file
+      - disableDeletion: true
+        editable: false
+        folder: Mimir
+        name: mimir-3
+        options:
+          path: /var/lib/grafana/dashboards/mimir-3
+        orgId: 1
+        type: file
+      - disableDeletion: true
+        editable: false
+        folder: Mimir
+        name: mimir-4
+        options:
+          path: /var/lib/grafana/dashboards/mimir-4
+        orgId: 1
+        type: file
+      - disableDeletion: true
+        editable: false
+        folder: Mimir
+        name: mimir-5
+        options:
+          path: /var/lib/grafana/dashboards/mimir-5
+        orgId: 1
+        type: file
+{{- end }}
+{{- if .Values.dashboards.traces.enabled }}
+      - disableDeletion: true
+        editable: false
+        folder: Tempo
+        name: tempo-1
+        options:
+          path: /var/lib/grafana/dashboards/tempo-1
+        orgId: 1
+        type: file
+{{- end }}
+      - disableDeletion: true
+        editable: false
+        folder: Agent
+        name: agent-1
+        options:
+          path: /var/lib/grafana/dashboards/agent-1
+        orgId: 1
+        type: file
 {{- end }}

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

@@ -1,9 +1,9 @@
-{{- if or (or .Values.local.logs.enabled .Values.local.metrics.enabled) .Values.local.traces.enabled }}
+{{- if .Values.local.grafana.enabled }}
 ---
 apiVersion: v1
 kind: ConfigMap
 metadata:
-  name: loki-datasources-provisioning
+  name: datasources-provisioning
   namespace: {{ $.Release.Namespace }}
 data:
   datasources.yaml: |

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

@@ -0,0 +1,57 @@
+{{- if and .Values.local.grafana.enabled .Values.grafana.ingress.enabled -}}
+{{- $ingressApiIsStable := eq (include "ingress.isStable" .) "true" -}}
+{{- $ingressSupportsIngressClassName := eq (include "ingress.supportsIngressClassName" .) "true" -}}
+{{- $ingressSupportsPathType := eq (include "ingress.supportsPathType" .) "true" -}}
+apiVersion: {{ include "ingress.apiVersion" . }}
+kind: Ingress
+metadata:
+  name: grafana
+  namespace: {{ $.Release.Namespace }}
+  labels:
+    app: grafana
+    {{- range $labelKey, $labelValue := .Values.grafana.ingress.labels }}
+    {{ $labelKey }}: {{ $labelValue | toYaml }}
+    {{- end }}
+  {{- with .Values.grafana.ingress.annotations }}
+  annotations:
+    {{- toYaml . | nindent 4 }}
+  {{- end }}
+spec:
+  {{- if and $ingressSupportsIngressClassName .Values.grafana.ingress.ingressClassName }}
+  ingressClassName: {{ .Values.grafana.ingress.ingressClassName }}
+  {{- end -}}
+  {{- if .Values.grafana.ingress.tls }}
+  tls:
+    {{- range .Values.grafana.ingress.tls }}
+    - hosts:
+        {{- range .hosts }}
+        - {{ tpl . $ | quote }}
+        {{- end }}
+      {{- with .secretName }}
+      secretName: {{ . }}
+      {{- end }}
+    {{- end }}
+  {{- end }}
+  rules:
+    {{- range .Values.grafana.ingress.hosts }}
+    - host: {{ tpl .host $ | quote }}
+      http:
+        paths:
+          {{- range .paths }}
+          - path: {{ .path }}
+            {{- if $ingressSupportsPathType }}
+            pathType: {{ .pathType }}
+            {{- end }}
+            backend:
+              {{- if $ingressApiIsStable }}
+              service:
+                name: grafana
+                port:
+                  number: 3000
+              {{- else }}
+              serviceName: grafana
+              servicePort: 3000
+              {{- end }}
+          {{- end }}
+    {{- end }}
+{{- end }}

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

@@ -1,4 +1,4 @@
-{{- if or (or .Values.local.logs.enabled .Values.local.metrics.enabled) .Values.local.traces.enabled }}
+{{- if .Values.local.grafana.enabled }}
 ---
 apiVersion: v1
 kind: PersistentVolumeClaim
@@ -64,26 +64,46 @@ spec:
             - mountPath: /var/lib/grafana
               name: grafana-pv
             - mountPath: /etc/grafana/provisioning/datasources
-              name: loki-datasources-provisioning
-            {{- if .Values.local.logs.enabled }}
+              name: datasources-provisioning
+            {{- if or (or .Values.dashboards.logs.enabled .Values.dashboards.metrics.enabled) .Values.dashboards.traces.enabled }}
             - mountPath: /etc/grafana/provisioning/dashboards
-              name: loki-dashboards-provisioning
+              name: dashboards-provisioning
+            {{- end }}
+            {{- if .Values.dashboards.logs.enabled }}
             - mountPath: /var/lib/grafana/dashboards/loki-1
               name: loki-dashboards-1
             - mountPath: /var/lib/grafana/dashboards/loki-2
               name: loki-dashboards-2
             {{- end }}
+            {{- if .Values.dashboards.metrics.enabled }}
+            - mountPath: /var/lib/grafana/dashboards/mimir-1
+              name: mimir-dashboards-1
+            - mountPath: /var/lib/grafana/dashboards/mimir-2
+              name: mimir-dashboards-2
+            - mountPath: /var/lib/grafana/dashboards/mimir-3
+              name: mimir-dashboards-3
+            - mountPath: /var/lib/grafana/dashboards/mimir-4
+              name: mimir-dashboards-4
+            - mountPath: /var/lib/grafana/dashboards/mimir-5
+              name: mimir-dashboards-5
+            {{- end }}
+            {{- if .Values.dashboards.traces.enabled }}
+            - mountPath: /var/lib/grafana/dashboards/tempo-1
+              name: tempo-dashboards-1
+            {{- end }}
+            - mountPath: /var/lib/grafana/dashboards/agent-1
+              name: agent-dashboards-1
       volumes:
         - name: grafana-pv
           persistentVolumeClaim:
             claimName: grafana-pvc
-        - name: loki-datasources-provisioning
+        - name: datasources-provisioning
           configMap:
-            name: loki-datasources-provisioning
-        {{- if .Values.local.logs.enabled }}
-        - name: loki-dashboards-provisioning
+            name: datasources-provisioning
+        - name: dashboards-provisioning
           configMap:
-            name: loki-dashboards-provisioning
+            name: dashboards-provisioning
+        {{- if .Values.dashboards.logs.enabled }}
         - name: loki-dashboards-1
           configMap:
             name: loki-dashboards-1
@@ -91,6 +111,31 @@ spec:
           configMap:
             name: loki-dashboards-2
         {{- end }}
+        {{- if .Values.dashboards.metrics.enabled }}
+        - name: mimir-dashboards-1
+          configMap:
+            name: mimir-dashboards-1
+        - name: mimir-dashboards-2
+          configMap:
+            name: mimir-dashboards-2
+        - name: mimir-dashboards-3
+          configMap:
+            name: mimir-dashboards-3
+        - name: mimir-dashboards-4
+          configMap:
+            name: mimir-dashboards-4
+        - name: mimir-dashboards-5
+          configMap:
+            name: mimir-dashboards-5
+        {{- end }}
+        {{- if .Values.dashboards.traces.enabled }}
+        - name: tempo-dashboards-1
+          configMap:
+            name: tempo-dashboards-1
+        {{- end }}
+        - name: agent-dashboards-1
+          configMap:
+            name: agent-dashboards-1
 
 ---
 apiVersion: v1
@@ -106,4 +151,4 @@ spec:
     app: grafana
   sessionAffinity: None
   type: ClusterIP  # Make this configurable
-{{- end }}
+{{- end }}

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

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

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

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

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

@@ -0,0 +1,19 @@
+{{- if and .Values.local.grafana.enabled .Values.dashboards.metrics.enabled }}
+---
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: mimir-dashboards-1
+  namespace: {{ $.Release.Namespace }}
+data:
+  "mimir-alertmanager-resources.json": |
+    {{ $.Files.Get "src/dashboards/mimir-alertmanager-resources.json" | fromJson | toJson }}
+  "mimir-alertmanager.json": |
+    {{ $.Files.Get "src/dashboards/mimir-alertmanager.json" | fromJson | toJson }}
+  "mimir-compactor-resources.json": |
+    {{ $.Files.Get "src/dashboards/mimir-compactor-resources.json" | fromJson | toJson }}
+  "mimir-compactor.json": |
+    {{ $.Files.Get "src/dashboards/mimir-compactor.json" | fromJson | toJson }}
+  "mimir-config.json": |
+    {{ $.Files.Get "src/dashboards/mimir-config.json" | fromJson | toJson }}
+{{- end }}

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

@@ -0,0 +1,19 @@
+{{- if and .Values.local.grafana.enabled .Values.dashboards.metrics.enabled }}
+---
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: mimir-dashboards-2
+  namespace: {{ $.Release.Namespace }}
+data:
+  "mimir-object-store.json": |
+    {{ $.Files.Get "src/dashboards/mimir-object-store.json" | fromJson | toJson }}
+  "mimir-overrides.json": |
+    {{ $.Files.Get "src/dashboards/mimir-overrides.json" | fromJson | toJson }}
+  "mimir-overview-networking.json": |
+    {{ $.Files.Get "src/dashboards/mimir-overview-networking.json" | fromJson | toJson }}
+  "mimir-overview-resources.json": |
+    {{ $.Files.Get "src/dashboards/mimir-overview-resources.json" | fromJson | toJson }}
+  "mimir-overview.json": |
+    {{ $.Files.Get "src/dashboards/mimir-overview.json" | fromJson | toJson }}
+{{- end }}

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

@@ -0,0 +1,19 @@
+{{- if and .Values.local.grafana.enabled .Values.dashboards.metrics.enabled }}
+---
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: mimir-dashboards-3
+  namespace: {{ $.Release.Namespace }}
+data:
+  "mimir-queries.json": |
+    {{ $.Files.Get "src/dashboards/mimir-queries.json" | fromJson | toJson }}
+  "mimir-reads-networking.json": |
+    {{ $.Files.Get "src/dashboards/mimir-reads-networking.json" | fromJson | toJson }}
+  "mimir-reads-resources.json": |
+    {{ $.Files.Get "src/dashboards/mimir-reads-resources.json" | fromJson | toJson }}
+  "mimir-reads.json": |
+    {{ $.Files.Get "src/dashboards/mimir-reads.json" | fromJson | toJson }}
+  "mimir-remote-ruler-reads-resources.json": |
+    {{ $.Files.Get "src/dashboards/mimir-remote-ruler-reads-resources.json" | fromJson | toJson }}
+{{- end }}

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

@@ -0,0 +1,19 @@
+{{- if and .Values.local.grafana.enabled .Values.dashboards.metrics.enabled }}
+---
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: mimir-dashboards-4
+  namespace: {{ $.Release.Namespace }}
+data:
+  "mimir-remote-ruler-reads.json": |
+    {{ $.Files.Get "src/dashboards/mimir-remote-ruler-reads.json" | fromJson | toJson }}
+  "mimir-rollout-progress.json": |
+    {{ $.Files.Get "src/dashboards/mimir-rollout-progress.json" | fromJson | toJson }}
+  "mimir-ruler.json": |
+    {{ $.Files.Get "src/dashboards/mimir-ruler.json" | fromJson | toJson }}
+  "mimir-scaling.json": |
+    {{ $.Files.Get "src/dashboards/mimir-scaling.json" | fromJson | toJson }}
+  "mimir-slow-queries.json": |
+    {{ $.Files.Get "src/dashboards/mimir-slow-queries.json" | fromJson | toJson }}
+{{- end }}

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

@@ -0,0 +1,19 @@
+{{- if and .Values.local.grafana.enabled .Values.dashboards.metrics.enabled }}
+---
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: mimir-dashboards-5
+  namespace: {{ $.Release.Namespace }}
+data:
+  "mimir-tenants.json": |
+    {{ $.Files.Get "src/dashboards/mimir-tenants.json" | fromJson | toJson }}
+  "mimir-top-tenants.json": |
+    {{ $.Files.Get "src/dashboards/mimir-top-tenants.json" | fromJson | toJson }}
+  "mimir-writes-networking.json": |
+    {{ $.Files.Get "src/dashboards/mimir-writes-networking.json" | fromJson | toJson }}
+  "mimir-writes-resources.json": |
+    {{ $.Files.Get "src/dashboards/mimir-writes-resources.json" | fromJson | toJson }}
+  "mimir-writes.json": |
+    {{ $.Files.Get "src/dashboards/mimir-writes.json" | fromJson | toJson }}
+{{- end }}

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

@@ -0,0 +1,21 @@
+{{- if and .Values.local.grafana.enabled .Values.dashboards.traces.enabled }}
+---
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: tempo-dashboards-1
+  namespace: {{ $.Release.Namespace }}
+data:
+  "tempo-operational.json": |
+    {{ $.Files.Get "src/dashboards/tempo-operational.json" | fromJson | toJson }}
+  "tempo-reads.json": |
+    {{ $.Files.Get "src/dashboards/tempo-reads.json" | fromJson | toJson }}
+  "tempo-resources.json": |
+    {{ $.Files.Get "src/dashboards/tempo-resources.json" | fromJson | toJson }}
+  "tempo-rollout-progress.json": |
+    {{ $.Files.Get "src/dashboards/tempo-rollout-progress.json" | fromJson | toJson }}
+  "tempo-tenants.json": |
+    {{ $.Files.Get "src/dashboards/tempo-tenants.json" | fromJson | toJson }}
+  "tempo-writes.json": |
+    {{ $.Files.Get "src/dashboards/tempo-writes.json" | fromJson | toJson }}
+{{- end }}

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

@@ -0,0 +1,126 @@
+{{- if .Values.local.grafana.enabled }}
+{{- if and .Values.local.grafana.enabled (or .Values.dashboards.logs.enabled .Values.dashboards.metrics.enabled .Values.dashboards.traces.enabled) }}
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: {{ $.Release.Namespace }}-mimir-ruler-for-dashboards
+  namespace: {{ $.Release.Namespace }}
+spec:
+  progressDeadlineSeconds: 600
+  replicas: 1
+  revisionHistoryLimit: 10
+  selector:
+    matchLabels:
+      app.kubernetes.io/component: ruler-for-dashboards
+      app.kubernetes.io/instance: meta
+      app.kubernetes.io/name: mimir
+  strategy:
+    rollingUpdate:
+      maxSurge: 50%
+      maxUnavailable: 0
+    type: RollingUpdate
+  template:
+    metadata:
+      labels:
+        app.kubernetes.io/component: ruler-for-dashboards
+        app.kubernetes.io/instance: meta
+        app.kubernetes.io/name: mimir
+      namespace: {{ $.Release.Namespace }}
+    spec:
+      containers:
+        - args:
+            - -target=ruler
+            - -log.level=debug
+            - -ruler-storage.backend=local
+            - -ruler-storage.local.directory=/etc/rules
+            - -ruler.ring.prefix=dashboards/
+            - -config.expand-env=true
+            - -config.file=/etc/mimir/mimir.yaml
+          image: grafana/mimir:2.8.0
+          imagePullPolicy: IfNotPresent
+          name: ruler
+          ports:
+            - containerPort: 8080
+              name: http-metrics
+              protocol: TCP
+            - containerPort: 9095
+              name: grpc
+              protocol: TCP
+            - containerPort: 7946
+              name: memberlist
+              protocol: TCP
+          readinessProbe:
+            failureThreshold: 3
+            httpGet:
+              path: /ready
+              port: http-metrics
+              scheme: HTTP
+            initialDelaySeconds: 45
+            periodSeconds: 10
+            successThreshold: 1
+            timeoutSeconds: 1
+          resources:
+            requests:
+              cpu: 100m
+              memory: 128Mi
+          securityContext:
+            allowPrivilegeEscalation: false
+            capabilities:
+              drop:
+                - ALL
+            readOnlyRootFilesystem: true
+          terminationMessagePath: /dev/termination-log
+          terminationMessagePolicy: File
+          volumeMounts:
+            - mountPath: /etc/mimir
+              name: config
+            - mountPath: /var/mimir
+              name: runtime-config
+            - mountPath: /data
+              name: storage
+            - mountPath: /active-query-tracker
+              name: active-queries
+            - mountPath: /etc/rules/anonymous
+              name: rules
+      dnsPolicy: ClusterFirst
+      restartPolicy: Always
+      schedulerName: default-scheduler
+      securityContext:
+        fsGroup: 10001
+        runAsGroup: 10001
+        runAsNonRoot: true
+        runAsUser: 10001
+        seccompProfile:
+          type: RuntimeDefault
+      terminationGracePeriodSeconds: 180
+      topologySpreadConstraints:
+        - labelSelector:
+            matchLabels:
+              app.kubernetes.io/component: ruler
+              app.kubernetes.io/instance: meta
+              app.kubernetes.io/name: mimir
+          maxSkew: 1
+          topologyKey: kubernetes.io/hostname
+          whenUnsatisfiable: ScheduleAnyway
+      volumes:
+        - configMap:
+            defaultMode: 420
+            items:
+              - key: mimir.yaml
+                path: mimir.yaml
+            name: {{ $.Release.Namespace }}-mimir-config
+          name: config
+        - configMap:
+            defaultMode: 420
+            name: {{ $.Release.Namespace }}-mimir-runtime
+          name: runtime-config
+        - emptyDir: {}
+          name: storage
+        - emptyDir: {}
+          name: active-queries
+        - configMap:
+            defaultMode: 420
+            name: rules
+          name: rules
+{{- end }}
+{{- end }}

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

@@ -0,0 +1,20 @@
+{{- if .Values.local.metrics.enabled }}
+{{- if and .Values.local.grafana.enabled (or .Values.dashboards.logs.enabled .Values.dashboards.metrics.enabled .Values.dashboards.traces.enabled) }}
+---
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: rules
+  namespace: {{ $.Release.Namespace }}
+data:
+{{- if .Values.dashboards.logs.enabled }}
+{{ ($.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/templates/validate.yaml

@@ -0,0 +1,43 @@
+{{- if not (eq .Values.local.minio.enabled (or .Values.local.traces.enabled (or .Values.local.logs.enabled .Values.local.metrics.enabled))) -}}
+  {{- fail "minio.enabled should be set to true if any of the the local databases is enabled " -}}
+{{- end -}}
+
+{{- if eq .Values.cloud.logs.enabled true -}}
+  {{- if empty .Values.cloud.logs.secret -}}
+    {{- fail "if cloud.logs is enabled then the secret has to be filled in" -}}
+  {{- end -}}
+{{- end -}}
+
+{{- if eq .Values.cloud.metrics.enabled true -}}
+  {{- if empty .Values.cloud.metrics.secret -}}
+    {{- fail "if cloud.metrics is enabled then the secret has to be filled in" -}}
+  {{- end -}}
+{{- end -}}
+
+{{- if eq .Values.cloud.traces.enabled true -}}
+  {{- if empty .Values.cloud.traces.secret -}}
+    {{- fail "if cloud.traces is enabled then the secret has to be filled in" -}}
+  {{- end -}}
+{{- end -}}
+
+{{- if eq .Values.cloud.traces.enabled false -}}
+{{- if eq .Values.cloud.metrics.enabled false -}}
+{{- if eq .Values.cloud.logs.enabled false -}}
+{{- if eq .Values.local.traces.enabled false -}}
+{{- if eq .Values.local.metrics.enabled false -}}
+{{- if eq .Values.local.logs.enabled false -}}
+    {{- fail "nothing has been enabled" -}}
+{{- end -}}
+{{- end -}}
+{{- end -}}
+{{- end -}}
+{{- 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

@@ -1,48 +1,203 @@
+# Specify the namespaces to monitor here
 namespacesToMonitor:
 - loki
 - mimir
 - tempo
-clusterName: "observability"  # TODO check if this can be derived
-
-# Turn on or off for local storing of metrics, logs or traces
-tags:
-  local-logs: true
-  local-metrics: true
-  local-traces: true
-
-# Unfortunately this is duplicate as Helm's tags and conditions fro dependencies are limited
-local:
-  logs:
-    enabled: false
-  metrics:
-    enabled: false
-  traces:
-    enabled: false
+# 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
 cloud:
   logs:
     enabled: true
-    endpoint:
-    username:
-    password:
+    secret: "logs"
+  metrics:
+    enabled: true
+    secret: "metrics"
+  traces:
+    enabled: true
+    secret: "traces"
+
+# Set to true for a local version of logs, metrics or traces
+local:
+  grafana:
+    enabled: false
+  logs:
+    enabled: false
+  metrics:
+    enabled: false
+  traces:
+    enabled: false
+  minio:
+    enabled: false  # This should be set to true if any of the previous is enabled
+
+grafana:
+  # Gateway ingress configuration
+  ingress:
+    # -- Specifies whether an ingress for the gateway should be created
+    enabled: true
+    # -- Ingress Class Name. MAY be required for Kubernetes versions >= 1.18
+    ingressClassName: ""
+    # -- Annotations for the gateway ingress
+    annotations: { }
+    # -- Labels for the gateway ingress
+    labels: { }
+    # -- Hosts configuration for the gateway ingress, passed through the `tpl` function to allow templating
+    hosts:
+      - host: monitoring.example.com
+        paths:
+          - path: /
+            # -- pathType (e.g. ImplementationSpecific, Prefix, .. etc.) might also be required by some Ingress Controllers
+            # pathType: Prefix
+    # -- TLS configuration for the gateway ingress. Hosts passed through the `tpl` function to allow templating
+    #tls:
+    #  - secretName: grafana-tls
+    #    hosts:
+    #      - monitoring.example.com
+
+
+logs:
+  # Adding regexes here will add a stage.replace block for logs. For more information see
+  # https://grafana.com/docs/agent/latest/flow/reference/components/loki.process/#stagereplace-block
+  piiRegexes:
+  # This example replaces the word after password with *****
+  # - expression: "password (\\\\S+)"
+  #   source: ""         # Empty uses the log message
+  #   replace: "*****""
+
+  # The lines matching these will be kept in Loki
+  retain:
+  # This shows the queries
+  - caller=metrics.go
+  # This shows any errors
+  - level=error
+  # This shows the ingest requests and is very noisy. Uncomment to include.
+  # - caller=push.go
+  # Log lines for delete requests
+  - delete request for user added
+  - Started processing delete request
+  - delete request for user marked as processed
+
+metrics:
+  # The list of metrics to retain for logging dashboards
+  retain:
+  - agent_config_last_load_success_timestamp_seconds
+  - agent_config_last_load_successful
+  - agent_config_load_failures_total
+  - container_cpu_usage_seconds_total
+  - container_fs_writes_bytes_total
+  - container_memory_working_set_bytes
+  - container_network_receive_bytes_total
+  - container_network_transmit_bytes_total
+  - container_spec_cpu_period
+  - container_spec_cpu_quota
+  - container_spec_memory_limit_bytes
+  - cortex_ingester_flush_queue_length
+  - cortex_prometheus_rule_group_iterations_total
+  - cortex_prometheus_rule_evaluation_failures_total
+  - cortex_prometheus_rule_group_rules
+  - cortex_prometheus_rule_group_last_duration_seconds
+  - cortex_prometheus_rule_group_last_evaluation_timestamp_seconds
+  - cortex_prometheus_rule_group_iterations_missed_total
+  - go_gc_duration_seconds
+  - go_goroutines
+  - go_memstats_heap_inuse_bytes
+  - kubelet_volume_stats_used_bytes
+  - kubelet_volume_stats_capacity_bytes
+  - kube_persistentvolumeclaim_labels
+  - kube_pod_container_resource_requests
+  - kube_pod_container_status_last_terminated_reason
+  - kube_pod_container_status_restarts_total
+  - loki_boltdb_shipper_compact_tables_operation_duration_seconds
+  - loki_boltdb_shipper_compact_tables_operation_last_successful_run_timestamp_seconds
+  - loki_boltdb_shipper_retention_marker_count_total
+  - loki_boltdb_shipper_retention_marker_table_processed_duration_seconds_bucket
+  - loki_boltdb_shipper_retention_marker_table_processed_duration_seconds_count
+  - loki_boltdb_shipper_retention_marker_table_processed_duration_seconds_sum
+  - loki_boltdb_shipper_retention_marker_table_processed_total
+  - loki_boltdb_shipper_request_duration_seconds_bucket
+  - loki_boltdb_shipper_request_duration_seconds_count
+  - loki_boltdb_shipper_request_duration_seconds_sum
+  - loki_boltdb_shipper_retention_sweeper_chunk_deleted_duration_seconds_bucket
+  - loki_boltdb_shipper_retention_sweeper_chunk_deleted_duration_seconds_count
+  - loki_boltdb_shipper_retention_sweeper_chunk_deleted_duration_seconds_sum
+  - loki_boltdb_shipper_retention_sweeper_marker_files_current
+  - loki_boltdb_shipper_retention_sweeper_marker_file_processing_current_time
+  - loki_build_info
+  - loki_chunk_store_deduped_chunks_total
+  - loki_chunk_store_index_entries_per_chunk_bucket
+  - loki_chunk_store_index_entries_per_chunk_count
+  - loki_chunk_store_index_entries_per_chunk_sum
+  - loki_compactor_delete_requests_processed_total
+  - loki_compactor_delete_requests_received_total
+  - loki_compactor_deleted_lines
+  - loki_compactor_oldest_pending_delete_request_age_seconds
+  - loki_compactor_pending_delete_requests_count
+  - loki_discarded_samples_total
+  - loki_distributor_bytes_received_total
+  - loki_distributor_lines_received_total
+  - loki_distributor_structured_metadata_bytes_received_total
+  - loki_ingester_chunk_age_seconds_bucket
+  - loki_ingester_chunk_age_seconds_count
+  - loki_ingester_chunk_age_seconds_sum
+  - loki_ingester_chunk_bounds_hours_bucket
+  - loki_ingester_chunk_bounds_hours_count
+  - loki_ingester_chunk_bounds_hours_sum
+  - loki_ingester_chunk_entries_bucket
+  - loki_ingester_chunk_entries_count
+  - loki_ingester_chunk_entries_sum
+  - loki_ingester_chunk_size_bytes_bucket
+  - loki_ingester_chunk_utilization_bucket
+  - loki_ingester_chunk_utilization_sum
+  - loki_ingester_chunks_flushed_total
+  - loki_ingester_flush_queue_length
+  - loki_ingester_memory_chunks
+  - loki_ingester_memory_streams
+  - loki_ingester_streams_created_total
+  - loki_request_duration_seconds_bucket
+  - loki_request_duration_seconds_count
+  - loki_request_duration_seconds_sum
+  - loki_ruler_wal_appender_ready
+  - loki_ruler_wal_disk_size
+  - loki_ruler_wal_prometheus_remote_storage_highest_timestamp_in_seconds
+  - loki_ruler_wal_prometheus_remote_storage_queue_highest_sent_timestamp_seconds
+  - loki_ruler_wal_prometheus_remote_storage_samples_pending
+  - loki_ruler_wal_prometheus_remote_storage_samples_total
+  - loki_ruler_wal_samples_appended_total
+  - loki_ruler_wal_storage_created_series_total
+  - loki_write_batch_retries_total
+  - loki_write_dropped_bytes_total
+  - loki_write_dropped_entries_total
+  - loki_write_sent_bytes_total
+  - loki_write_sent_entries_total
+  - node_disk_read_bytes_total
+  - node_disk_written_bytes_total
+  - promtail_custom_bad_words_total
+
+# Set enabled = true to add the default logs/metrics/traces dashboards to the local Grafana
+dashboards:
+  logs:
+    enabled: true
   metrics:
     enabled: true
-    endpoint:
-    username:
-    password:
   traces:
     enabled: true
-    endpoint:
-    username:
-    password:
 
 global:
   minio:
     rootUser: "rootuser"
     rootPassword: "rootpassword"
 
+kubeStateMetrics:
+  # Scrape https://github.com/kubernetes/kube-state-metrics by default
+  enabled: true
+  # This endpoint is created when the helm chart from
+  # 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 not be changed.
+# These should usually not be changed.
 
 loki:
   loki:
@@ -50,13 +205,22 @@ loki:
     storage:
       type: "s3"
       s3:
-        endpoint: "meta-minio.meta.svc:9000"
-        access_key_id: rootuser
-        secret_access_key: rootpassword
         insecure: true
+        s3ForcePathStyle: true
       bucketNames:
         chunks: loki-chunks
         ruler: loki-ruler
+    structuredConfig:
+      common:
+        storage:
+          s3:
+            access_key_id: "{{ .Values.global.minio.rootUser }}"
+            endpoint: "{{ .Release.Name }}-minio.{{ .Release.Namespace }}.svc:9000"
+            secret_access_key: "{{ .Values.global.minio.rootPassword }}"
+      compactor:
+        retention_enabled: true
+      limits_config:
+        retention_period: 30d
   monitoring:
     dashboards:
       enabled: false
@@ -73,12 +237,28 @@ loki:
   test:
     enabled: false
 
-grafana-agent:
-  agent:
+alloy:
+  alloy:
+    clustering:
+      enabled: true
     configMap:
       create: false
       name: "agent-configmap"
       key: 'config.river'
+    resources:
+      requests:
+        cpu: '1000m'
+        memory: '600Mi'
+      limits:
+        memory: '4Gi'
+  controller:
+    type: "statefulset"
+    autoscaling:
+      enabled: true
+      minReplicas: 3
+      maxReplicas: 30
+      targetMemoryUtilizationPercentage: 90
+      targetCPUUtilizationPercentage: 90
 
 mimir-distributed:
   minio:
@@ -107,6 +287,8 @@ mimir-distributed:
           endpoint: "{{ .Release.Name }}-minio.{{ .Release.Namespace }}.svc:9000"
           secret_access_key: "{{ .Values.global.minio.rootPassword }}"
           insecure: true
+      limits:
+        compactor_blocks_retention_period: 30d
 
 tempo-distributed:
   tempo:
@@ -120,6 +302,9 @@ tempo-distributed:
             access_key: "{{ .Values.global.minio.rootUser }}"
             secret_key: "{{ .Values.global.minio.rootPassword }}"
             insecure: true
+      compactor:
+        compaction:
+          block_retention: 30d
   traces:
     otlp:
       http:
@@ -154,4 +339,4 @@ minio:
       cpu: 100m
       memory: 128Mi
   # Changed the mc config path to '/tmp' from '/etc' as '/etc' is only writable by root and OpenShift will not permit this.
-  configPathmc: "/tmp/minio/mc/"
+  configPathmc: "/tmp/minio/mc/"

docs/installation.md

@@ -6,7 +6,26 @@
    kubectl create namespace meta
    ```
 
-1. Create a values.yaml file based on the [default one](../charts/meta-monitoring/values.yaml).
+1. Create secrets with credentials and the endpoint when sending logs, metrics or traces to Grafana Cloud.
+
+   ```
+   kubectl create secret generic logs -n meta \
+    --from-literal=username=<logs username> \
+    --from-literal=password=<logs password>
+    --from-literal=endpoint='https://logs-prod-us-central1.grafana.net/loki/api/v1/push'
+
+   kubectl create secret generic metrics -n meta \
+    --from-literal=username=<metrics username> \
+    --from-literal=password=<metrics password>
+    --from-literal=endpoint='https://prometheus-us-central1.grafana.net/api/prom/push'
+
+   kubectl create secret generic traces -n meta \
+    --from-literal=username=<traces username> \
+    --from-literal=password=<traces password>
+    --from-literal=endpoint='https://tempo-us-central1.grafana.net/tempo'
+   ```
+
+1. Create a values.yaml file based on the [default one](../charts/meta-monitoring/values.yaml). Fill in the names of the secrets created above as needed.
 
 1. Install this helm chart
 

tools/kind.config

@@ -0,0 +1,9 @@
+kind: Cluster
+apiVersion: kind.x-k8s.io/v1alpha4
+name: meta
+nodes:
+- role: control-plane
+- role: worker
+- role: worker
+- role: worker
+