Compare commits

..

16 Commits

Author SHA1 Message Date
Michel Hollands
c9295f51e2 Rename agent dashboard file
Signed-off-by: Michel Hollands <michel.hollands@gmail.com>
2023-08-17 09:40:25 +01:00
Michel Hollands
1eafbd4904 Fix linting issues
Signed-off-by: Michel Hollands <michel.hollands@gmail.com>
2023-08-16 17:19:09 +01:00
Michel Hollands
70312c135d Do local install
Signed-off-by: Michel Hollands <michel.hollands@gmail.com>
2023-08-16 17:14:44 +01:00
Michel Hollands
1b3b89df42 Increase timeout
Signed-off-by: Michel Hollands <michel.hollands@gmail.com>
2023-08-16 17:13:15 +01:00
Michel Hollands
419cdede3d Remove hardcoded meta namespace
Signed-off-by: Michel Hollands <michel.hollands@gmail.com>
2023-08-16 16:59:42 +01:00
Michel Hollands
a3d27c1c3a Add default values in values.yaml
Signed-off-by: Michel Hollands <michel.hollands@gmail.com>
2023-08-16 16:48:41 +01:00
Michel Hollands
4cf4d13955 Remove prometheus operator
Signed-off-by: Michel Hollands <michel.hollands@gmail.com>
2023-08-16 16:43:37 +01:00
Michel Hollands
3a59a6bc82 Fix linting issues again 2
Signed-off-by: Michel Hollands <michel.hollands@gmail.com>
2023-08-16 16:31:48 +01:00
Michel Hollands
e9b05c3856 Fix linting issues again
Signed-off-by: Michel Hollands <michel.hollands@gmail.com>
2023-08-16 16:29:38 +01:00
Michel Hollands
f9b6ae9b3e Fix linting issues
Signed-off-by: Michel Hollands <michel.hollands@gmail.com>
2023-08-16 16:15:00 +01:00
Michel Hollands
4534f3eb21 Update chart dependencies
Signed-off-by: Michel Hollands <michel.hollands@gmail.com>
2023-08-16 16:09:22 +01:00
Michel Hollands
b7dc7212e9 Update path for CI
Signed-off-by: Michel Hollands <michel.hollands@gmail.com>
2023-08-16 14:38:18 +01:00
Michel Hollands
ed6c6da4a0 Add ct.yaml file
Signed-off-by: Michel Hollands <michel.hollands@gmail.com>
2023-08-16 14:31:55 +01:00
Michel Hollands
9c67417c02 Fix path again
Signed-off-by: Michel Hollands <michel.hollands@gmail.com>
2023-08-16 14:11:09 +01:00
Michel Hollands
9e136cdc5e Fix paths
Signed-off-by: Michel Hollands <michel.hollands@gmail.com>
2023-08-16 14:08:11 +01:00
Michel Hollands
46dd6ffeb3 Add ci steps
Signed-off-by: Michel Hollands <michel.hollands@gmail.com>
2023-08-16 14:06:07 +01:00
96 changed files with 63770 additions and 10700 deletions

View File

@@ -1,3 +0,0 @@
owner: grafana
git-repo: helm-charts
skip-existing: true

View File

@@ -1,15 +0,0 @@
## Reference: https://github.com/helm/chart-testing/blob/master/doc/ct_lint-and-install.md
remote: origin
target-branch: main
chart-dirs:
- charts
chart-repos:
- grafana=https://grafana.github.io/helm-charts
- minio=https://charts.min.io
validate-chart-schema: true
validate-maintainers: true
validate-yaml: true
exclude-deprecated: true
excluded-charts: []
namespace: meta-monitoring # Need to set the namespace because we create the secret there
release-label: app.kubernetes.io/instance

View File

@@ -1,30 +0,0 @@
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

View File

@@ -1,30 +0,0 @@
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

View File

@@ -1,30 +0,0 @@
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

View File

@@ -1,30 +0,0 @@
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

View File

@@ -1,30 +0,0 @@
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

View File

@@ -1,177 +0,0 @@
---
name: Check for dependency updates
on:
workflow_dispatch:
schedule:
# Run once a day
- cron: '0 7 * * *'
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
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
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
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
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

View File

@@ -16,51 +16,86 @@ jobs:
- name: Checkout Code
uses: actions/checkout@v3
# - name: Check Docs
# run: |
# docker run --rm --volume "$(pwd):/helm-docs" -u "$(id -u)" jnorwood/helm-docs:v1.11.0
# if ! git diff --exit-code; then
# echo "Documentation not up to date. Please run helm-docs and commit changes!" >&2
# exit 1
# fi
- name: Lint Yaml
run: make helm-lint
# call-test:
# name: Test Helm Chart
# runs-on: ubuntu-latest
# steps:
# - name: Checkout
# uses: actions/checkout@v3
# with:
# fetch-depth: 0
# - name: Lint Code Base
# uses: docker://github/super-linter:v3.12.0
# env:
# FILTER_REGEX_EXCLUDE: .*(README\.md|Chart\.yaml|NOTES.txt).*
# FILTER_REGEX_INCLUDE: .*charts/meta-monitoring/.*
# VALIDATE_ALL_CODEBASE: false
# VALIDATE_KUBERNETES_KUBEVAL: false
# VALIDATE_YAML: false
# VALIDATE_GO: false
# DEFAULT_BRANCH: main
# GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
call-test:
name: Test Helm Chart
runs-on: ubuntu-latest
steps:
- name: Checkout
uses: actions/checkout@v3
with:
fetch-depth: 0
# - name: Set up Helm
# uses: azure/setup-helm@v3
# with:
# version: v3.8.2
- name: Set up Helm
uses: azure/setup-helm@v3
with:
version: v3.8.2
# # Python is required because `ct lint` runs Yamale (https://github.com/23andMe/Yamale) and
# # yamllint (https://github.com/adrienverge/yamllint) which require Python
# - name: Set up Python
# uses: actions/setup-python@v4
# with:
# python-version: 3.7
# Python is required because `ct lint` runs Yamale (https://github.com/23andMe/Yamale) and
# yamllint (https://github.com/adrienverge/yamllint) which require Python
- name: Set up Python
uses: actions/setup-python@v4
with:
python-version: 3.7
# - name: Set up chart-testing
# uses: helm/chart-testing-action@v2.4.0
- name: Set up chart-testing
uses: helm/chart-testing-action@v2.4.0
# - name: Run chart-testing (list-changed)
# id: list-changed
# run: |
# changed=$(ct list-changed --config "${CT_CONFIGFILE}")
# if [[ -n "$changed" ]]; then
# echo "changed=true" >> $GITHUB_OUTPUT
# fi
- name: Run chart-testing (list-changed)
id: list-changed
run: |
changed=$(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: Run chart-testing (lint)
run: ct lint --config "${CT_CONFIGFILE}" --check-version-increment=false
# - name: Create kind cluster
# uses: helm/kind-action@v1.8.0
# if: steps.list-changed.outputs.changed == 'true'
# with:
# config: tools/kind.config
- name: Create kind cluster
uses: helm/kind-action@v1.8.0
if: steps.list-changed.outputs.changed == 'true'
# - name: Run chart-testing (install)
# run: |
# changed=$(ct list-changed --config "${CT_CONFIGFILE}")
# ct install --config "${CT_CONFIGFILE}"
# - name: Install prometheus operator
# id: install-prometheus
# if: steps.list-changed.outputs.changed == 'true'
# run: |
# kubectl create namespace prometheus
# helm install prometheus prometheus-community/kube-prometheus-stack \
# --namespace prometheus \
# --set grafana.enabled=false \
# --set prometheus.prometheusSpec.serviceMonitorSelector.matchLabels.release=prometheus
# kubectl --namespace prometheus get pods -l "release=prometheus"
# kubectl --namespace prometheus get services -l "release=prometheus"
- name: Run chart-testing (install)
run: |
changed=$(ct list-changed --config "${CT_CONFIGFILE}")
if [[ "$changed" == "charts/enterprise-metrics" ]]; then
# Do not run `ct install` for enterprise-metrics
exit 0
fi
ct install --config "${CT_CONFIGFILE}"

View File

@@ -1,175 +0,0 @@
name: Release Helm chart
on:
workflow_dispatch:
env:
CR_CONFIGFILE: "${{ github.workspace }}/source/.github/configs/cr.yaml"
CT_CONFIGFILE: "${{ github.workspace }}/source/.github/configs/ct.yaml"
CR_INDEX_PATH: "${{ github.workspace }}/.cr-index"
CR_PACKAGE_PATH: "${{ github.workspace }}/.cr-release-packages"
CR_TOOL_PATH: "${{ github.workspace }}/.cr-tool"
CR_VERSION: "1.5.0"
jobs:
setup:
runs-on: ubuntu-latest
outputs:
changed: ${{ steps.list-changed.outputs.changed }}
chartpath: ${{ steps.list-changed.outputs.chartpath }}
steps:
- name: Checkout
uses: actions/checkout@v4
with:
fetch-depth: 0
path: source
- name: Install chart-testing
uses: helm/chart-testing-action@v2
- name: List changed charts
id: list-changed
run: |
cd source
latest_tag=$( if ! git describe --tags --abbrev=0 --match='helm-chart/*' 2> /dev/null ; then git rev-list --max-parents=0 --first-parent HEAD; fi )
echo "Running: ct list-changed --config ${CT_CONFIGFILE} --since ${latest_tag} --target-branch ${{ github.ref_name }}"
changed=$(ct list-changed --config "${CT_CONFIGFILE}" --since "${latest_tag}" --target-branch "${{ github.ref_name }}")
echo "${changed}"
num_changed=$(wc -l <<< ${changed})
if [[ "${num_changed}" -gt "1" ]] ; then
echo "More than one chart changed, exiting"
exit 1
fi
if [[ -n "${changed}" ]]; then
name=$(yq ".name" < ${changed}/Chart.yaml)
version=$(yq ".version" < ${changed}/Chart.yaml)
tagname="v${version}"
if [ $(git tag -l "${tagname}") ]; then
echo "Tag ${tagname} already exists, skipping release"
echo "changed=false" >> $GITHUB_OUTPUT
else
echo "Releasing ${changed}"
echo "changed=true" >> $GITHUB_OUTPUT
echo "chartpath=${changed}" >> $GITHUB_OUTPUT
fi
else
echo "No charts have changed, skipping release"
echo "changed=false" >> $GITHUB_OUTPUT
fi
release:
needs: [setup]
runs-on: ubuntu-latest
if: needs.setup.outputs.changed == 'true'
permissions:
contents: write
id-token: write
steps:
- id: get-secrets
uses: grafana/shared-workflows/actions/get-vault-secrets@main
with:
# Secrets placed in the ci/repo/grafana/<repo>/<path> path in Vault
repo_secrets: |
APP_ID=github-app:app-id
PRIVATE_KEY=github-app:private-key
- uses: actions/create-github-app-token@v1
id: app-token
with:
app-id: ${{ env.APP_ID }}
private-key: ${{ env.PRIVATE_KEY }}
owner: ${{ github.repository_owner }}
- name: Checkout
uses: actions/checkout@v4
with:
fetch-depth: 0
path: source
- name: Configure Git
run: |
cd source
git config user.name "$GITHUB_ACTOR"
git config user.email "$GITHUB_ACTOR@users.noreply.github.com"
- name: Checkout helm-charts
uses: actions/checkout@v4
with:
fetch-depth: 0
repository: grafana/helm-charts
path: helm-charts
token: "${{ steps.app-token.outputs.token }}"
- name: Configure Git for helm-charts
run: |
cd helm-charts
git config user.name "$GITHUB_ACTOR"
git config user.email "$GITHUB_ACTOR@users.noreply.github.com"
- name: Set up Helm
uses: azure/setup-helm@v4
- name: Parse Chart.yaml
id: parse-chart
run: |
cd source
changed="${{ needs.setup.outputs.chartpath }}"
description=$(yq ".description" < ${changed}/Chart.yaml)
name=$(yq ".name" < ${changed}/Chart.yaml)
version=$(yq ".version" < ${changed}/Chart.yaml)
echo "chartpath=${changed}" >> $GITHUB_OUTPUT
echo "desc=${description}" >> $GITHUB_OUTPUT
echo "tagname=v${version}" >> $GITHUB_OUTPUT
echo "packagename=${name}-${version}" >> $GITHUB_OUTPUT
- name: Install CR tool
run: |
mkdir "${CR_TOOL_PATH}"
mkdir "${CR_PACKAGE_PATH}"
mkdir "${CR_INDEX_PATH}"
curl -sSLo cr.tar.gz "https://github.com/helm/chart-releaser/releases/download/v${CR_VERSION}/chart-releaser_${CR_VERSION}_linux_amd64.tar.gz"
tar -xzf cr.tar.gz -C "${CR_TOOL_PATH}"
rm -f cr.tar.gz
- name: Create Helm package
run: |
cd source
helm repo add grafana https://grafana.github.io/helm-charts
helm repo add minio https://charts.min.io
"${CR_TOOL_PATH}/cr" package "${{ steps.parse-chart.outputs.chartpath }}" --config "${CR_CONFIGFILE}" --package-path "${CR_PACKAGE_PATH}"
- name: Make a release on this repo
uses: softprops/action-gh-release@v2
with:
name: ${{ steps.parse-chart.outputs.tagname }}
repository: grafana/meta-monitoring-chart
tag_name: ${{ steps.parse-chart.outputs.tagname }}
token: ${{ steps.app-token.outputs.token }}
generate_release_notes: true
files: |
${{ env.CR_PACKAGE_PATH }}/${{ steps.parse-chart.outputs.packagename }}.tgz
# Note that this creates a release in grafana/helm-charts with a new tag.
# The tag name in grafana/helm-charts is <package>-<version>, while the
# tag name for grafana/meta-monitoring-chart is <version>.
- name: Make release on Helm Charts
uses: softprops/action-gh-release@v2
with:
name: ${{ steps.parse-chart.outputs.packagename }}
repository: grafana/helm-charts
tag_name: ${{ steps.parse-chart.outputs.packagename }}
token: ${{ steps.app-token.outputs.token }}
body: |
${{ steps.parse-chart.outputs.desc }}
Source commit: https://github.com/${{ github.repository }}/commit/${{ github.sha }}
Tag on source: https://github.com/${{ github.repository }}/releases/tag/${{ steps.parse-chart.outputs.tagname }}
files: |
${{ env.CR_PACKAGE_PATH }}/${{ steps.parse-chart.outputs.packagename }}.tgz
- name: Update helm-charts index.yaml
run: |
cd helm-charts
"${CR_TOOL_PATH}/cr" index --config "${CR_CONFIGFILE}" --token "${{ steps.app-token.outputs.token }}" --index-path "${CR_INDEX_PATH}" --package-path "${CR_PACKAGE_PATH}" --push

1
.gitignore vendored
View File

@@ -1 +0,0 @@
.DS_Store

View File

@@ -6,5 +6,5 @@ help:
.PHONY: helm-lint
helm-lint: ## Run helm linter
helm-lint: ## run helm linter
$(MAKE) -BC charts/meta-monitoring lint

View File

@@ -1,9 +1,20 @@
# meta-monitoring-chart
This is a meta-monitoring chart for Loki.
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).
1. Add or remove the namespaces to monitor in the `namespacesToMonitor` setting
1. Set the cluster name in the `clusterName` setting. This will be added as a label to all logs, metrics and traces.
1. Create a `meta` namespace.
## Local and cloud modes
The chart has 2 modes: local and cloud. In the local mode logs, metrics and/or traces are sent
@@ -19,10 +30,16 @@ In the cloud mode the logs, metrics and/or traces are sent to Grafana Cloud.
To enable cloud mode set `cloud.<logs|metrics|traces>.enabled` to true. The `endpoint`, `username` and `password` settings for your Grafana Cloud logs, metrics and traces instances have to be filled in as well.
Both modes can be enabled at the same time. Cloud mode is preferred.
Both modes can be enabled at the same time.
## Installation
```
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
@@ -33,6 +50,8 @@ For more instructions including how to update the chart go to the [installation]
- Specify PII regexes that are applied to logs before they are sent to Loki (cloud or local). The capture group in the regex is replaced with *****.
- a Grafana instance is installed (when local mode is used) with the relevant datasources installed. The following dashboards are installed:
- logs dashboards
- metrics dashboards
- traces dashboards
- agent dashboards
- Retention is set to 24 hours
@@ -40,6 +59,7 @@ Most of these features are enabled by default. See the values.yaml file for how
## 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.

View File

@@ -1,18 +1,18 @@
dependencies:
- name: loki
repository: https://grafana.github.io/helm-charts
version: 6.4.2
- name: alloy
version: 5.8.0
- name: grafana-agent
repository: https://grafana.github.io/helm-charts
version: 0.1.1
version: 0.15.0
- name: mimir-distributed
repository: https://grafana.github.io/helm-charts
version: 5.3.0
version: 4.4.1
- name: tempo-distributed
repository: https://grafana.github.io/helm-charts
version: 1.9.4
version: 1.4.7
- name: minio
repository: https://charts.min.io
version: 5.2.0
digest: sha256:62e737c64e180822d737a94514acee68d3c58c2cfb3e741be2f707a5d3588004
generated: "2024-05-02T07:02:31.487968368Z"
version: 5.0.11
digest: sha256:da0e744b5046eb7972e0bf82d1d0ba4786e9600af63b65f35b16118105248074
generated: "2023-08-16T16:08:36.406791+01:00"

View File

@@ -1,6 +1,7 @@
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
@@ -10,32 +11,35 @@ 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: 0.0.2
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: 6.4.2
version: "5.8.0"
condition: local.logs.enabled
- name: alloy
- name: grafana-agent
repository: https://grafana.github.io/helm-charts
version: 0.1.1
version: "0.15.0"
- name: mimir-distributed
repository: https://grafana.github.io/helm-charts
version: 5.3.0
version: "4.4.1"
condition: local.metrics.enabled
- name: tempo-distributed
repository: https://grafana.github.io/helm-charts
version: 1.9.4
version: "1.4.7"
condition: local.traces.enabled
- name: minio
repository: https://charts.min.io
version: 5.2.0
version: "5.0.11"
condition: local.minio.enabled

View File

@@ -1,4 +1,4 @@
.DEFAULT_GOAL := lint
.DEFAULT_GOAL := all
.PHONY: lint lint-yaml
lint: lint-yaml

Binary file not shown.

Binary file not shown.

Binary file not shown.

View File

@@ -8,4 +8,4 @@ chart-repos:
- minio=https://charts.min.io
helm-extra-args: --timeout 1200s
check-version-increment: false
validate-maintainers: false
validate-maintainers: false

File diff suppressed because it is too large Load Diff

View File

@@ -62,6 +62,7 @@
"expr": "sum(loki_compactor_pending_delete_requests_count{cluster=~\"$cluster\", namespace=~\"$namespace\"})",
"format": "time_series",
"instant": true,
"intervalFactor": 2,
"refId": "A"
}
],
@@ -137,6 +138,7 @@
"expr": "max(loki_compactor_oldest_pending_delete_request_age_seconds{cluster=~\"$cluster\", namespace=~\"$namespace\"})",
"format": "time_series",
"instant": true,
"intervalFactor": 2,
"refId": "A"
}
],
@@ -189,145 +191,232 @@
"height": "250px",
"panels": [
{
"aliasColors": { },
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fieldConfig": {
"defaults": {
"custom": {
"drawStyle": "line",
"fillOpacity": 10,
"lineWidth": 1,
"pointSize": 5,
"showPoints": "never",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
}
},
"thresholds": {
"mode": "absolute",
"steps": [ ]
},
"unit": "short"
},
"overrides": [ ]
},
"fill": 1,
"id": 3,
"links": [ ],
"options": {
"legend": {
"showLegend": true
},
"tooltip": {
"mode": "single",
"sort": "none"
}
"legend": {
"avg": false,
"current": false,
"max": false,
"min": false,
"show": true,
"total": false,
"values": false
},
"lines": true,
"linewidth": 1,
"links": [ ],
"nullPointMode": "null as zero",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"seriesOverrides": [ ],
"spaceLength": 10,
"span": 4,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "(loki_compactor_delete_requests_received_total{cluster=~\"$cluster\", namespace=~\"$namespace\"} or on() vector(0)) - on () (loki_compactor_delete_requests_processed_total{cluster=~\"$cluster\", namespace=~\"$namespace\"} or on () vector(0))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "in progress",
"legendLink": null
"legendLink": null,
"step": 10
}
],
"thresholds": [ ],
"timeFrom": null,
"timeShift": null,
"title": "# of Delete Requests (received - processed) ",
"type": "timeseries"
"tooltip": {
"shared": true,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [ ]
},
"yaxes": [
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
},
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": false
}
]
},
{
"aliasColors": { },
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"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": [ ]
},
"fill": 1,
"id": 4,
"links": [ ],
"options": {
"legend": {
"showLegend": true
},
"tooltip": {
"mode": "single",
"sort": "none"
}
"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(increase(loki_compactor_delete_requests_received_total{cluster=~\"$cluster\", namespace=~\"$namespace\"}[1d]))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "received",
"legendLink": null
"legendLink": null,
"step": 10
}
],
"thresholds": [ ],
"timeFrom": null,
"timeShift": null,
"title": "Delete Requests Received / Day",
"type": "timeseries"
"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": "$datasource",
"fieldConfig": {
"defaults": {
"custom": {
"drawStyle": "line",
"fillOpacity": 10,
"lineWidth": 1,
"pointSize": 5,
"showPoints": "never",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
}
},
"thresholds": {
"mode": "absolute",
"steps": [ ]
},
"unit": "short"
},
"overrides": [ ]
},
"fill": 1,
"id": 5,
"links": [ ],
"options": {
"legend": {
"showLegend": true
},
"tooltip": {
"mode": "single",
"sort": "none"
}
"legend": {
"avg": false,
"current": false,
"max": false,
"min": false,
"show": true,
"total": false,
"values": false
},
"lines": true,
"linewidth": 1,
"links": [ ],
"nullPointMode": "null as zero",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"seriesOverrides": [ ],
"spaceLength": 10,
"span": 4,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "sum(increase(loki_compactor_delete_requests_processed_total{cluster=~\"$cluster\", namespace=~\"$namespace\"}[1d]))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "processed",
"legendLink": null
"legendLink": null,
"step": 10
}
],
"thresholds": [ ],
"timeFrom": null,
"timeShift": null,
"title": "Delete Requests Processed / Day",
"type": "timeseries"
"tooltip": {
"shared": true,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [ ]
},
"yaxes": [
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
},
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": false
}
]
}
],
"repeat": null,
@@ -342,145 +431,232 @@
"height": "250px",
"panels": [
{
"aliasColors": { },
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$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": "short"
},
"overrides": [ ]
},
"fill": 1,
"id": 6,
"links": [ ],
"options": {
"legend": {
"showLegend": true
},
"tooltip": {
"mode": "single",
"sort": "none"
}
"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": "node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=~\"$cluster\", namespace=~\"$namespace\", container=\"compactor\"}",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{pod}}",
"legendLink": null
"legendLink": null,
"step": 10
}
],
"thresholds": [ ],
"timeFrom": null,
"timeShift": null,
"title": "Compactor CPU usage",
"type": "timeseries"
"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": "$datasource",
"fieldConfig": {
"defaults": {
"custom": {
"drawStyle": "line",
"fillOpacity": 10,
"lineWidth": 1,
"pointSize": 5,
"showPoints": "never",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
}
},
"thresholds": {
"mode": "absolute",
"steps": [ ]
},
"unit": "short"
},
"overrides": [ ]
},
"fill": 1,
"id": 7,
"links": [ ],
"options": {
"legend": {
"showLegend": true
},
"tooltip": {
"mode": "single",
"sort": "none"
}
"legend": {
"avg": false,
"current": false,
"max": false,
"min": false,
"show": true,
"total": false,
"values": false
},
"lines": true,
"linewidth": 1,
"links": [ ],
"nullPointMode": "null as zero",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"seriesOverrides": [ ],
"spaceLength": 10,
"span": 4,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "go_memstats_heap_inuse_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\", container=\"compactor\"} / 1024 / 1024 ",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": " {{pod}} ",
"legendLink": null
"legendLink": null,
"step": 10
}
],
"thresholds": [ ],
"timeFrom": null,
"timeShift": null,
"title": "Compactor memory usage (MiB)",
"type": "timeseries"
"tooltip": {
"shared": true,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [ ]
},
"yaxes": [
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
},
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": false
}
]
},
{
"aliasColors": { },
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"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": [ ]
},
"fill": 1,
"id": 8,
"links": [ ],
"options": {
"legend": {
"showLegend": true
},
"tooltip": {
"mode": "single",
"sort": "none"
}
"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": "loki_boltdb_shipper_compact_tables_operation_duration_seconds{cluster=~\"$cluster\", namespace=~\"$namespace\"}",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{pod}}",
"legendLink": null
"legendLink": null,
"step": 10
}
],
"thresholds": [ ],
"timeFrom": null,
"timeShift": null,
"title": "Compaction run duration (seconds)",
"type": "timeseries"
"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,
@@ -495,98 +671,156 @@
"height": "250px",
"panels": [
{
"aliasColors": { },
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fieldConfig": {
"defaults": {
"custom": {
"drawStyle": "line",
"fillOpacity": 10,
"lineWidth": 1,
"pointSize": 5,
"showPoints": "never",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
}
},
"thresholds": {
"mode": "absolute",
"steps": [ ]
},
"unit": "short"
},
"overrides": [ ]
},
"fill": 1,
"id": 9,
"links": [ ],
"options": {
"legend": {
"showLegend": true
},
"tooltip": {
"mode": "single",
"sort": "none"
}
"legend": {
"avg": false,
"current": false,
"max": false,
"min": false,
"show": true,
"total": false,
"values": false
},
"lines": true,
"linewidth": 1,
"links": [ ],
"nullPointMode": "null as zero",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"seriesOverrides": [ ],
"spaceLength": 10,
"span": 6,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "sum(increase(loki_compactor_load_pending_requests_attempts_total{status=\"fail\", cluster=~\"$cluster\", namespace=~\"$namespace\"}[1h]))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "failures",
"legendLink": null
"legendLink": null,
"step": 10
}
],
"thresholds": [ ],
"timeFrom": null,
"timeShift": null,
"title": "Failures in Loading Delete Requests / Hour",
"type": "timeseries"
"tooltip": {
"shared": true,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [ ]
},
"yaxes": [
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
},
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": false
}
]
},
{
"aliasColors": { },
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"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": [ ]
},
"fill": 1,
"id": 10,
"links": [ ],
"options": {
"legend": {
"showLegend": true
},
"tooltip": {
"mode": "single",
"sort": "none"
}
"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(loki_compactor_deleted_lines{cluster=~\"$cluster\", namespace=~\"$namespace\", pod=~\"(.*/compactor|(loki|enterprise-logs)-backend.*|loki-single-binary)\"}[$__rate_interval])) by (user)",
"expr": "sum(rate(loki_compactor_deleted_lines{cluster=~\"$cluster\",job=~\"$namespace/(loki|enterprise-logs)-read\"}[$__rate_interval])) by (user)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{user}}",
"legendLink": null
"legendLink": null,
"step": 10
}
],
"thresholds": [ ],
"timeFrom": null,
"timeShift": null,
"title": "Lines Deleted / Sec",
"type": "timeseries"
"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,
@@ -606,7 +840,7 @@
"span": 6,
"targets": [
{
"expr": "{cluster=~\"$cluster\", namespace=~\"$namespace\", pod=~\"(.*/compactor|(loki|enterprise-logs)-backend.*|loki-single-binary)\"} |~ \"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}}\" ",
"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"
}
],
@@ -619,7 +853,7 @@
"span": 6,
"targets": [
{
"expr": "{cluster=~\"$cluster\", namespace=~\"$namespace\", pod=~\"(.*/compactor|(loki|enterprise-logs)-backend.*|loki-single-binary)\"} |~ \"delete request for user added\" | logfmt | line_format \"{{.ts}} user={{.user}} query='{{.query}}'\"",
"expr": "{cluster=~\"$cluster\", namespace=~\"$namespace\", container=\"compactor\"} |~ \"delete request for user added\" | logfmt | line_format \"{{.ts}} user={{.user}} query='{{.query}}'\"",
"refId": "A"
}
],
@@ -648,7 +882,7 @@
"value": "default"
},
"hide": 0,
"label": "Data source",
"label": "Data Source",
"name": "datasource",
"options": [ ],
"query": "prometheus",
@@ -701,16 +935,6 @@
"tagsQuery": "",
"type": "query",
"useTags": false
},
{
"hide": 0,
"label": null,
"name": "loki_datasource",
"options": [ ],
"query": "loki",
"refresh": 1,
"regex": "",
"type": "datasource"
}
]
},

View File

@@ -77,7 +77,7 @@
"sort": 0,
"value_type": "individual"
},
"type": "timeseries",
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
@@ -114,11 +114,6 @@
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fieldConfig": {
"defaults": {
"unit": "s"
}
},
"fill": 1,
"fillGradient": 0,
"gridPos": {
@@ -169,7 +164,7 @@
"sort": 0,
"value_type": "individual"
},
"type": "timeseries",
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
@@ -241,7 +236,7 @@
"steppedLine": false,
"targets": [
{
"expr": "sum(rate(container_cpu_usage_seconds_total{cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"$deployment.*\", pod=~\"$pod\", container=~\"$container\"}[$__rate_interval]))",
"expr": "sum(rate(container_cpu_usage_seconds_total{cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"$deployment.*\", pod=~\"$pod\", container=~\"$container\"}[5m]))",
"refId": "A"
}
],
@@ -255,7 +250,7 @@
"sort": 0,
"value_type": "individual"
},
"type": "timeseries",
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
@@ -292,11 +287,6 @@
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fieldConfig": {
"defaults": {
"unit": "bytes"
}
},
"fill": 1,
"fillGradient": 0,
"gridPos": {
@@ -346,7 +336,7 @@
"sort": 0,
"value_type": "individual"
},
"type": "timeseries",
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
@@ -383,11 +373,6 @@
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fieldConfig": {
"defaults": {
"unit": "binBps"
}
},
"fill": 1,
"fillGradient": 0,
"gridPos": {
@@ -423,7 +408,7 @@
"steppedLine": false,
"targets": [
{
"expr": "sum(rate(container_network_transmit_bytes_total{cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"$deployment.*\", pod=~\"$pod\"}[$__rate_interval]))",
"expr": "sum(rate(container_network_transmit_bytes_total{cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"$deployment.*\", pod=~\"$pod\"}[5m]))",
"refId": "A"
}
],
@@ -437,7 +422,7 @@
"sort": 0,
"value_type": "individual"
},
"type": "timeseries",
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
@@ -474,11 +459,6 @@
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fieldConfig": {
"defaults": {
"unit": "binBps"
}
},
"fill": 1,
"fillGradient": 0,
"gridPos": {
@@ -514,7 +494,7 @@
"steppedLine": false,
"targets": [
{
"expr": "sum(rate(container_network_receive_bytes_total{cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"$deployment.*\", pod=~\"$pod\"}[$__rate_interval]))",
"expr": "sum(rate(container_network_receive_bytes_total{cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"$deployment.*\", pod=~\"$pod\"}[5m]))",
"refId": "A"
}
],
@@ -528,7 +508,7 @@
"sort": 0,
"value_type": "individual"
},
"type": "timeseries",
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
@@ -615,7 +595,7 @@
"sort": 0,
"value_type": "individual"
},
"type": "timeseries",
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
@@ -652,11 +632,6 @@
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fieldConfig": {
"defaults": {
"unit": "ops"
}
},
"fill": 1,
"fillGradient": 0,
"gridPos": {
@@ -692,7 +667,7 @@
"steppedLine": false,
"targets": [
{
"expr": "sum(rate(promtail_custom_bad_words_total{cluster=\"$cluster\", exported_namespace=\"$namespace\", exported_pod=~\"$deployment.*\", exported_pod=~\"$pod\", container=~\"$container\"}[$__rate_interval])) by (level)",
"expr": "sum(rate(promtail_custom_bad_words_total{cluster=\"$cluster\", exported_namespace=\"$namespace\", exported_pod=~\"$deployment.*\", exported_pod=~\"$pod\", container=~\"$container\"}[5m])) by (level)",
"legendFormat": "{{level}}",
"refId": "A"
}
@@ -707,7 +682,7 @@
"sort": 0,
"value_type": "individual"
},
"type": "timeseries",
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
@@ -743,12 +718,7 @@
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$loki_datasource",
"fieldConfig": {
"defaults": {
"unit": "ops"
}
},
"datasource": "$logs",
"fill": 1,
"fillGradient": 0,
"gridPos": {
@@ -801,7 +771,7 @@
"steppedLine": false,
"targets": [
{
"expr": "sum(rate({cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"$deployment.*\", pod=~\"$pod\", container=~\"$container\" } |logfmt| level=\"$level\" |= \"$filter\" | __error__=\"\" [$__interval])) by (level)",
"expr": "sum(rate({cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"$deployment.*\", pod=~\"$pod\", container=~\"$container\" } |logfmt| level=\"$level\" |= \"$filter\" [5m])) by (level)",
"intervalFactor": 3,
"legendFormat": "{{level}}",
"refId": "A"
@@ -817,7 +787,7 @@
"sort": 2,
"value_type": "individual"
},
"type": "timeseries",
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
@@ -849,7 +819,7 @@
}
},
{
"datasource": "$loki_datasource",
"datasource": "$logs",
"gridPos": {
"h": 19,
"w": 24,
@@ -891,7 +861,7 @@
"value": "default"
},
"hide": 0,
"label": "Data source",
"label": "Data Source",
"name": "datasource",
"options": [ ],
"query": "prometheus",
@@ -948,7 +918,7 @@
{
"hide": 0,
"label": null,
"name": "loki_datasource",
"name": "logs",
"options": [ ],
"query": "loki",
"refresh": 1,
@@ -1099,4 +1069,4 @@
"title": "Loki / Logs",
"uid": "logs",
"version": 0
}
}

View File

@@ -0,0 +1,723 @@
{
"annotations": {
"list": [ ]
},
"editable": true,
"fiscalYearStartMonth": 0,
"gnetId": null,
"graphTooltip": 0,
"hideControls": false,
"iteration": 1635347545534,
"links": [
{
"asDropdown": true,
"icon": "external link",
"includeVars": true,
"keepTime": true,
"tags": [
"loki"
],
"targetBlank": false,
"title": "Loki Dashboards",
"type": "dashboards"
}
],
"liveNow": false,
"panels": [
{
"datasource": "${datasource}",
"fieldConfig": {
"defaults": {
"color": {
"mode": "thresholds"
},
"mappings": [ ],
"noValue": "0",
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "red",
"value": 1
}
]
}
},
"overrides": [ ]
},
"gridPos": {
"h": 10,
"w": 2,
"x": 0,
"y": 0
},
"id": 2,
"options": {
"colorMode": "value",
"graphMode": "area",
"justifyMode": "auto",
"orientation": "auto",
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"textMode": "auto"
},
"pluginVersion": "8.3.0-38205pre",
"targets": [
{
"datasource": "${datasource}",
"exemplar": false,
"expr": "sum(loki_ruler_wal_appender_ready) by (pod, tenant) == 0",
"instant": true,
"interval": "",
"legendFormat": "",
"refId": "A"
}
],
"title": "Appenders Not Ready",
"type": "stat"
},
{
"datasource": "${datasource}",
"description": "",
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"drawStyle": "line",
"fillOpacity": 0,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "auto",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [ ],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "red",
"value": 80
}
]
}
},
"overrides": [ ]
},
"gridPos": {
"h": 10,
"w": 11,
"x": 2,
"y": 0
},
"id": 4,
"options": {
"legend": {
"calcs": [ ],
"displayMode": "list",
"placement": "bottom"
},
"tooltip": {
"mode": "single"
}
},
"targets": [
{
"datasource": "${datasource}",
"exemplar": true,
"expr": "sum(rate(loki_ruler_wal_samples_appended_total{tenant=~\"${tenant}\"}[$__rate_interval])) by (tenant) > 0",
"interval": "",
"legendFormat": "{{tenant}}",
"refId": "A"
}
],
"title": "Samples Appended to WAL per Second",
"type": "timeseries"
},
{
"datasource": "${datasource}",
"description": "Series are unique combinations of labels",
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"drawStyle": "line",
"fillOpacity": 0,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "auto",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [ ],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "red",
"value": 80
}
]
}
},
"overrides": [ ]
},
"gridPos": {
"h": 10,
"w": 11,
"x": 13,
"y": 0
},
"id": 5,
"options": {
"legend": {
"calcs": [ ],
"displayMode": "list",
"placement": "bottom"
},
"tooltip": {
"mode": "single"
}
},
"targets": [
{
"datasource": "${datasource}",
"exemplar": true,
"expr": "sum(rate(loki_ruler_wal_storage_created_series_total{tenant=~\"${tenant}\"}[$__rate_interval])) by (tenant) > 0",
"interval": "",
"legendFormat": "{{tenant}}",
"refId": "A"
}
],
"title": "Series Created per Second",
"type": "timeseries"
},
{
"datasource": "${datasource}",
"description": "Difference between highest timestamp appended to WAL and highest timestamp successfully written to remote storage",
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"drawStyle": "line",
"fillOpacity": 0,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "auto",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [ ],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "red",
"value": 80
}
]
}
},
"overrides": [ ]
},
"gridPos": {
"h": 10,
"w": 12,
"x": 0,
"y": 10
},
"id": 6,
"options": {
"legend": {
"calcs": [ ],
"displayMode": "list",
"placement": "bottom"
},
"tooltip": {
"mode": "single"
}
},
"targets": [
{
"datasource": "${datasource}",
"exemplar": true,
"expr": "loki_ruler_wal_prometheus_remote_storage_highest_timestamp_in_seconds{tenant=~\"${tenant}\"}\n- on (tenant)\n (\n loki_ruler_wal_prometheus_remote_storage_queue_highest_sent_timestamp_seconds{tenant=~\"${tenant}\"}\n or vector(0)\n )",
"interval": "",
"legendFormat": "{{tenant}}",
"refId": "A"
}
],
"title": "Write Behind",
"type": "timeseries"
},
{
"datasource": "${datasource}",
"description": "",
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"drawStyle": "line",
"fillOpacity": 0,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "auto",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [ ],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "red",
"value": 80
}
]
}
},
"overrides": [ ]
},
"gridPos": {
"h": 10,
"w": 12,
"x": 12,
"y": 10
},
"id": 7,
"options": {
"legend": {
"calcs": [ ],
"displayMode": "list",
"placement": "bottom"
},
"tooltip": {
"mode": "single"
}
},
"targets": [
{
"datasource": "${datasource}",
"exemplar": true,
"expr": "sum(rate(loki_ruler_wal_prometheus_remote_storage_samples_total{tenant=~\"${tenant}\"}[$__rate_interval])) by (tenant) > 0",
"interval": "",
"legendFormat": "{{tenant}}",
"refId": "A"
}
],
"title": "Samples Sent per Second",
"type": "timeseries"
},
{
"datasource": "${datasource}",
"description": "\n",
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"drawStyle": "line",
"fillOpacity": 0,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "auto",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [ ],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "red",
"value": 80
}
]
},
"unit": "bytes"
},
"overrides": [ ]
},
"gridPos": {
"h": 10,
"w": 12,
"x": 0,
"y": 20
},
"id": 8,
"options": {
"legend": {
"calcs": [ ],
"displayMode": "list",
"placement": "bottom"
},
"tooltip": {
"mode": "single"
}
},
"targets": [
{
"datasource": "${datasource}",
"exemplar": true,
"expr": "sum by (tenant) (loki_ruler_wal_disk_size{tenant=~\"${tenant}\"})",
"interval": "",
"legendFormat": "{{tenant}}",
"refId": "A"
}
],
"title": "WAL Disk Size",
"type": "timeseries"
},
{
"datasource": "${datasource}",
"description": "Some number of pending samples is expected, but if remote-write is failing this value will remain high",
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"drawStyle": "line",
"fillOpacity": 0,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "auto",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [ ],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "red",
"value": 80
}
]
}
},
"overrides": [ ]
},
"gridPos": {
"h": 10,
"w": 12,
"x": 12,
"y": 20
},
"id": 9,
"options": {
"legend": {
"calcs": [ ],
"displayMode": "list",
"placement": "bottom"
},
"tooltip": {
"mode": "single"
}
},
"targets": [
{
"datasource": "${datasource}",
"exemplar": true,
"expr": "max(loki_ruler_wal_prometheus_remote_storage_samples_pending{tenant=~\"${tenant}\"}) by (tenant,pod) > 0",
"interval": "",
"legendFormat": "{{tenant}}",
"refId": "A"
}
],
"title": "Pending Samples",
"type": "timeseries"
}
],
"refresh": "10s",
"rows": [ ],
"schemaVersion": 14,
"style": "dark",
"tags": [
"loki"
],
"templating": {
"list": [
{
"current": {
"text": "default",
"value": "default"
},
"hide": 0,
"label": "Data Source",
"name": "datasource",
"options": [ ],
"query": "prometheus",
"refresh": 1,
"regex": "",
"type": "datasource"
},
{
"allValue": 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": null,
"multi": false,
"name": "tenant",
"options": [ ],
"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-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": "Loki / Recording Rules",
"uid": "recording-rules",
"version": 0,
"weekStart": ""
}

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

View File

@@ -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
}

File diff suppressed because it is too large Load Diff

View File

@@ -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
}

File diff suppressed because it is too large Load Diff

View File

@@ -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
}

View File

@@ -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
}

View File

@@ -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
}

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

View File

@@ -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
}

View File

@@ -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
}

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

View File

@@ -1,52 +1,53 @@
groups:
- name: "loki_rules"
rules:
- expr: "histogram_quantile(0.99, sum(rate(loki_request_duration_seconds_bucket[5m]))
- expr: "histogram_quantile(0.99, sum(rate(loki_request_duration_seconds_bucket[1m]))
by (le, cluster, job))"
record: "cluster_job:loki_request_duration_seconds:99quantile"
- expr: "histogram_quantile(0.50, sum(rate(loki_request_duration_seconds_bucket[5m]))
- expr: "histogram_quantile(0.50, sum(rate(loki_request_duration_seconds_bucket[1m]))
by (le, cluster, job))"
record: "cluster_job:loki_request_duration_seconds:50quantile"
- expr: "sum(rate(loki_request_duration_seconds_sum[5m])) by (cluster, job) / sum(rate(loki_request_duration_seconds_count[5m]))
- expr: "sum(rate(loki_request_duration_seconds_sum[1m])) by (cluster, job) / sum(rate(loki_request_duration_seconds_count[1m]))
by (cluster, job)"
record: "cluster_job:loki_request_duration_seconds:avg"
- expr: "sum(rate(loki_request_duration_seconds_bucket[5m])) by (le, cluster, job)"
- expr: "sum(rate(loki_request_duration_seconds_bucket[1m])) by (le, cluster, job)"
record: "cluster_job:loki_request_duration_seconds_bucket:sum_rate"
- expr: "sum(rate(loki_request_duration_seconds_sum[5m])) by (cluster, job)"
- expr: "sum(rate(loki_request_duration_seconds_sum[1m])) by (cluster, job)"
record: "cluster_job:loki_request_duration_seconds_sum:sum_rate"
- expr: "sum(rate(loki_request_duration_seconds_count[5m])) by (cluster, job)"
- expr: "sum(rate(loki_request_duration_seconds_count[1m])) by (cluster, job)"
record: "cluster_job:loki_request_duration_seconds_count:sum_rate"
- expr: "histogram_quantile(0.99, sum(rate(loki_request_duration_seconds_bucket[5m]))
- expr: "histogram_quantile(0.99, sum(rate(loki_request_duration_seconds_bucket[1m]))
by (le, cluster, job, route))"
record: "cluster_job_route:loki_request_duration_seconds:99quantile"
- expr: "histogram_quantile(0.50, sum(rate(loki_request_duration_seconds_bucket[5m]))
- expr: "histogram_quantile(0.50, sum(rate(loki_request_duration_seconds_bucket[1m]))
by (le, cluster, job, route))"
record: "cluster_job_route:loki_request_duration_seconds:50quantile"
- expr: "sum(rate(loki_request_duration_seconds_sum[5m])) by (cluster, job, route)
/ sum(rate(loki_request_duration_seconds_count[5m])) by (cluster, job, route)"
- expr: "sum(rate(loki_request_duration_seconds_sum[1m])) by (cluster, job, route)
/ sum(rate(loki_request_duration_seconds_count[1m])) by (cluster, job, route)"
record: "cluster_job_route:loki_request_duration_seconds:avg"
- expr: "sum(rate(loki_request_duration_seconds_bucket[5m])) by (le, cluster, job,
- expr: "sum(rate(loki_request_duration_seconds_bucket[1m])) by (le, cluster, job,
route)"
record: "cluster_job_route:loki_request_duration_seconds_bucket:sum_rate"
- expr: "sum(rate(loki_request_duration_seconds_sum[5m])) by (cluster, job, route)"
- expr: "sum(rate(loki_request_duration_seconds_sum[1m])) by (cluster, job, route)"
record: "cluster_job_route:loki_request_duration_seconds_sum:sum_rate"
- expr: "sum(rate(loki_request_duration_seconds_count[5m])) by (cluster, job, route)"
- expr: "sum(rate(loki_request_duration_seconds_count[1m])) by (cluster, job, route)"
record: "cluster_job_route:loki_request_duration_seconds_count:sum_rate"
- expr: "histogram_quantile(0.99, sum(rate(loki_request_duration_seconds_bucket[5m]))
- expr: "histogram_quantile(0.99, sum(rate(loki_request_duration_seconds_bucket[1m]))
by (le, cluster, namespace, job, route))"
record: "cluster_namespace_job_route:loki_request_duration_seconds:99quantile"
- expr: "histogram_quantile(0.50, sum(rate(loki_request_duration_seconds_bucket[5m]))
- expr: "histogram_quantile(0.50, sum(rate(loki_request_duration_seconds_bucket[1m]))
by (le, cluster, namespace, job, route))"
record: "cluster_namespace_job_route:loki_request_duration_seconds:50quantile"
- expr: "sum(rate(loki_request_duration_seconds_sum[5m])) by (cluster, namespace,
job, route) / sum(rate(loki_request_duration_seconds_count[5m])) by (cluster,
- expr: "sum(rate(loki_request_duration_seconds_sum[1m])) by (cluster, namespace,
job, route) / sum(rate(loki_request_duration_seconds_count[1m])) by (cluster,
namespace, job, route)"
record: "cluster_namespace_job_route:loki_request_duration_seconds:avg"
- expr: "sum(rate(loki_request_duration_seconds_bucket[5m])) by (le, cluster, namespace,
- expr: "sum(rate(loki_request_duration_seconds_bucket[1m])) by (le, cluster, namespace,
job, route)"
record: "cluster_namespace_job_route:loki_request_duration_seconds_bucket:sum_rate"
- expr: "sum(rate(loki_request_duration_seconds_sum[5m])) by (cluster, namespace,
- expr: "sum(rate(loki_request_duration_seconds_sum[1m])) by (cluster, namespace,
job, route)"
record: "cluster_namespace_job_route:loki_request_duration_seconds_sum:sum_rate"
- expr: "sum(rate(loki_request_duration_seconds_count[5m])) by (cluster, namespace,
- expr: "sum(rate(loki_request_duration_seconds_count[1m])) by (cluster, namespace,
job, route)"
record: "cluster_namespace_job_route:loki_request_duration_seconds_count:sum_rate"
record: "cluster_namespace_job_route:loki_request_duration_seconds_count:sum_rate"

View File

@@ -1,317 +1,322 @@
groups:
- name: "mimir_api_1"
rules:
- expr: "histogram_quantile(0.99, sum(rate(cortex_request_duration_seconds_bucket[5m]))
- expr: "histogram_quantile(0.99, sum(rate(cortex_request_duration_seconds_bucket[1m]))
by (le, cluster, job))"
record: "cluster_job:cortex_request_duration_seconds:99quantile"
- expr: "histogram_quantile(0.50, sum(rate(cortex_request_duration_seconds_bucket[5m]))
- expr: "histogram_quantile(0.50, sum(rate(cortex_request_duration_seconds_bucket[1m]))
by (le, cluster, job))"
record: "cluster_job:cortex_request_duration_seconds:50quantile"
- expr: "sum(rate(cortex_request_duration_seconds_sum[5m])) by (cluster, job) / sum(rate(cortex_request_duration_seconds_count[5m]))
- expr: "sum(rate(cortex_request_duration_seconds_sum[1m])) by (cluster, job) / sum(rate(cortex_request_duration_seconds_count[1m]))
by (cluster, job)"
record: "cluster_job:cortex_request_duration_seconds:avg"
- expr: "sum(rate(cortex_request_duration_seconds_bucket[5m])) by (le, cluster, job)"
- expr: "sum(rate(cortex_request_duration_seconds_bucket[1m])) by (le, cluster, job)"
record: "cluster_job:cortex_request_duration_seconds_bucket:sum_rate"
- expr: "sum(rate(cortex_request_duration_seconds_sum[5m])) by (cluster, job)"
- expr: "sum(rate(cortex_request_duration_seconds_sum[1m])) by (cluster, job)"
record: "cluster_job:cortex_request_duration_seconds_sum:sum_rate"
- expr: "sum(rate(cortex_request_duration_seconds_count[5m])) by (cluster, job)"
- expr: "sum(rate(cortex_request_duration_seconds_count[1m])) by (cluster, job)"
record: "cluster_job:cortex_request_duration_seconds_count:sum_rate"
- name: "mimir_api_2"
rules:
- expr: "histogram_quantile(0.99, sum(rate(cortex_request_duration_seconds_bucket[5m]))
- expr: "histogram_quantile(0.99, sum(rate(cortex_request_duration_seconds_bucket[1m]))
by (le, cluster, job, route))"
record: "cluster_job_route:cortex_request_duration_seconds:99quantile"
- expr: "histogram_quantile(0.50, sum(rate(cortex_request_duration_seconds_bucket[5m]))
- expr: "histogram_quantile(0.50, sum(rate(cortex_request_duration_seconds_bucket[1m]))
by (le, cluster, job, route))"
record: "cluster_job_route:cortex_request_duration_seconds:50quantile"
- expr: "sum(rate(cortex_request_duration_seconds_sum[5m])) by (cluster, job, route)
/ sum(rate(cortex_request_duration_seconds_count[5m])) by (cluster, job, route)"
- expr: "sum(rate(cortex_request_duration_seconds_sum[1m])) by (cluster, job, route)
/ sum(rate(cortex_request_duration_seconds_count[1m])) by (cluster, job, route)"
record: "cluster_job_route:cortex_request_duration_seconds:avg"
- expr: "sum(rate(cortex_request_duration_seconds_bucket[5m])) by (le, cluster, job,
- expr: "sum(rate(cortex_request_duration_seconds_bucket[1m])) by (le, cluster, job,
route)"
record: "cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate"
- expr: "sum(rate(cortex_request_duration_seconds_sum[5m])) by (cluster, job, route)"
- expr: "sum(rate(cortex_request_duration_seconds_sum[1m])) by (cluster, job, route)"
record: "cluster_job_route:cortex_request_duration_seconds_sum:sum_rate"
- expr: "sum(rate(cortex_request_duration_seconds_count[5m])) by (cluster, job, route)"
- expr: "sum(rate(cortex_request_duration_seconds_count[1m])) by (cluster, job, route)"
record: "cluster_job_route:cortex_request_duration_seconds_count:sum_rate"
- name: "mimir_api_3"
rules:
- expr: "histogram_quantile(0.99, sum(rate(cortex_request_duration_seconds_bucket[5m]))
- expr: "histogram_quantile(0.99, sum(rate(cortex_request_duration_seconds_bucket[1m]))
by (le, cluster, namespace, job, route))"
record: "cluster_namespace_job_route:cortex_request_duration_seconds:99quantile"
- expr: "histogram_quantile(0.50, sum(rate(cortex_request_duration_seconds_bucket[5m]))
- expr: "histogram_quantile(0.50, sum(rate(cortex_request_duration_seconds_bucket[1m]))
by (le, cluster, namespace, job, route))"
record: "cluster_namespace_job_route:cortex_request_duration_seconds:50quantile"
- expr: "sum(rate(cortex_request_duration_seconds_sum[5m])) by (cluster, namespace,
job, route) / sum(rate(cortex_request_duration_seconds_count[5m])) by (cluster,
- expr: "sum(rate(cortex_request_duration_seconds_sum[1m])) by (cluster, namespace,
job, route) / sum(rate(cortex_request_duration_seconds_count[1m])) by (cluster,
namespace, job, route)"
record: "cluster_namespace_job_route:cortex_request_duration_seconds:avg"
- expr: "sum(rate(cortex_request_duration_seconds_bucket[5m])) by (le, cluster, namespace,
- expr: "sum(rate(cortex_request_duration_seconds_bucket[1m])) by (le, cluster, namespace,
job, route)"
record: "cluster_namespace_job_route:cortex_request_duration_seconds_bucket:sum_rate"
- expr: "sum(rate(cortex_request_duration_seconds_sum[5m])) by (cluster, namespace,
- expr: "sum(rate(cortex_request_duration_seconds_sum[1m])) by (cluster, namespace,
job, route)"
record: "cluster_namespace_job_route:cortex_request_duration_seconds_sum:sum_rate"
- expr: "sum(rate(cortex_request_duration_seconds_count[5m])) by (cluster, namespace,
- expr: "sum(rate(cortex_request_duration_seconds_count[1m])) by (cluster, namespace,
job, route)"
record: "cluster_namespace_job_route:cortex_request_duration_seconds_count:sum_rate"
- name: "mimir_querier_api"
rules:
- expr: "histogram_quantile(0.99, sum(rate(cortex_querier_request_duration_seconds_bucket[5m]))
- expr: "histogram_quantile(0.99, sum(rate(cortex_querier_request_duration_seconds_bucket[1m]))
by (le, cluster, job))"
record: "cluster_job:cortex_querier_request_duration_seconds:99quantile"
- expr: "histogram_quantile(0.50, sum(rate(cortex_querier_request_duration_seconds_bucket[5m]))
- expr: "histogram_quantile(0.50, sum(rate(cortex_querier_request_duration_seconds_bucket[1m]))
by (le, cluster, job))"
record: "cluster_job:cortex_querier_request_duration_seconds:50quantile"
- expr: "sum(rate(cortex_querier_request_duration_seconds_sum[5m])) by (cluster,
job) / sum(rate(cortex_querier_request_duration_seconds_count[5m])) by (cluster,
- expr: "sum(rate(cortex_querier_request_duration_seconds_sum[1m])) by (cluster,
job) / sum(rate(cortex_querier_request_duration_seconds_count[1m])) by (cluster,
job)"
record: "cluster_job:cortex_querier_request_duration_seconds:avg"
- expr: "sum(rate(cortex_querier_request_duration_seconds_bucket[5m])) by (le, cluster,
- expr: "sum(rate(cortex_querier_request_duration_seconds_bucket[1m])) by (le, cluster,
job)"
record: "cluster_job:cortex_querier_request_duration_seconds_bucket:sum_rate"
- expr: "sum(rate(cortex_querier_request_duration_seconds_sum[5m])) by (cluster,
- expr: "sum(rate(cortex_querier_request_duration_seconds_sum[1m])) by (cluster,
job)"
record: "cluster_job:cortex_querier_request_duration_seconds_sum:sum_rate"
- expr: "sum(rate(cortex_querier_request_duration_seconds_count[5m])) by (cluster,
- expr: "sum(rate(cortex_querier_request_duration_seconds_count[1m])) by (cluster,
job)"
record: "cluster_job:cortex_querier_request_duration_seconds_count:sum_rate"
- expr: "histogram_quantile(0.99, sum(rate(cortex_querier_request_duration_seconds_bucket[5m]))
- expr: "histogram_quantile(0.99, sum(rate(cortex_querier_request_duration_seconds_bucket[1m]))
by (le, cluster, job, route))"
record: "cluster_job_route:cortex_querier_request_duration_seconds:99quantile"
- expr: "histogram_quantile(0.50, sum(rate(cortex_querier_request_duration_seconds_bucket[5m]))
- expr: "histogram_quantile(0.50, sum(rate(cortex_querier_request_duration_seconds_bucket[1m]))
by (le, cluster, job, route))"
record: "cluster_job_route:cortex_querier_request_duration_seconds:50quantile"
- expr: "sum(rate(cortex_querier_request_duration_seconds_sum[5m])) by (cluster,
job, route) / sum(rate(cortex_querier_request_duration_seconds_count[5m])) by
- expr: "sum(rate(cortex_querier_request_duration_seconds_sum[1m])) by (cluster,
job, route) / sum(rate(cortex_querier_request_duration_seconds_count[1m])) by
(cluster, job, route)"
record: "cluster_job_route:cortex_querier_request_duration_seconds:avg"
- expr: "sum(rate(cortex_querier_request_duration_seconds_bucket[5m])) by (le, cluster,
- expr: "sum(rate(cortex_querier_request_duration_seconds_bucket[1m])) by (le, cluster,
job, route)"
record: "cluster_job_route:cortex_querier_request_duration_seconds_bucket:sum_rate"
- expr: "sum(rate(cortex_querier_request_duration_seconds_sum[5m])) by (cluster,
- expr: "sum(rate(cortex_querier_request_duration_seconds_sum[1m])) by (cluster,
job, route)"
record: "cluster_job_route:cortex_querier_request_duration_seconds_sum:sum_rate"
- expr: "sum(rate(cortex_querier_request_duration_seconds_count[5m])) by (cluster,
- expr: "sum(rate(cortex_querier_request_duration_seconds_count[1m])) by (cluster,
job, route)"
record: "cluster_job_route:cortex_querier_request_duration_seconds_count:sum_rate"
- expr: "histogram_quantile(0.99, sum(rate(cortex_querier_request_duration_seconds_bucket[5m]))
- expr: "histogram_quantile(0.99, sum(rate(cortex_querier_request_duration_seconds_bucket[1m]))
by (le, cluster, namespace, job, route))"
record: "cluster_namespace_job_route:cortex_querier_request_duration_seconds:99quantile"
- expr: "histogram_quantile(0.50, sum(rate(cortex_querier_request_duration_seconds_bucket[5m]))
- expr: "histogram_quantile(0.50, sum(rate(cortex_querier_request_duration_seconds_bucket[1m]))
by (le, cluster, namespace, job, route))"
record: "cluster_namespace_job_route:cortex_querier_request_duration_seconds:50quantile"
- expr: "sum(rate(cortex_querier_request_duration_seconds_sum[5m])) by (cluster,
namespace, job, route) / sum(rate(cortex_querier_request_duration_seconds_count[5m]))
- expr: "sum(rate(cortex_querier_request_duration_seconds_sum[1m])) by (cluster,
namespace, job, route) / sum(rate(cortex_querier_request_duration_seconds_count[1m]))
by (cluster, namespace, job, route)"
record: "cluster_namespace_job_route:cortex_querier_request_duration_seconds:avg"
- expr: "sum(rate(cortex_querier_request_duration_seconds_bucket[5m])) by (le, cluster,
- expr: "sum(rate(cortex_querier_request_duration_seconds_bucket[1m])) by (le, cluster,
namespace, job, route)"
record: "cluster_namespace_job_route:cortex_querier_request_duration_seconds_bucket:sum_rate"
- expr: "sum(rate(cortex_querier_request_duration_seconds_sum[5m])) by (cluster,
- expr: "sum(rate(cortex_querier_request_duration_seconds_sum[1m])) by (cluster,
namespace, job, route)"
record: "cluster_namespace_job_route:cortex_querier_request_duration_seconds_sum:sum_rate"
- expr: "sum(rate(cortex_querier_request_duration_seconds_count[5m])) by (cluster,
- expr: "sum(rate(cortex_querier_request_duration_seconds_count[1m])) by (cluster,
namespace, job, route)"
record: "cluster_namespace_job_route:cortex_querier_request_duration_seconds_count:sum_rate"
- name: "mimir_cache"
rules:
- expr: "histogram_quantile(0.99, sum(rate(cortex_memcache_request_duration_seconds_bucket[5m]))
- expr: "histogram_quantile(0.99, sum(rate(cortex_memcache_request_duration_seconds_bucket[1m]))
by (le, cluster, job, method))"
record: "cluster_job_method:cortex_memcache_request_duration_seconds:99quantile"
- expr: "histogram_quantile(0.50, sum(rate(cortex_memcache_request_duration_seconds_bucket[5m]))
- expr: "histogram_quantile(0.50, sum(rate(cortex_memcache_request_duration_seconds_bucket[1m]))
by (le, cluster, job, method))"
record: "cluster_job_method:cortex_memcache_request_duration_seconds:50quantile"
- expr: "sum(rate(cortex_memcache_request_duration_seconds_sum[5m])) by (cluster,
job, method) / sum(rate(cortex_memcache_request_duration_seconds_count[5m]))
- expr: "sum(rate(cortex_memcache_request_duration_seconds_sum[1m])) by (cluster,
job, method) / sum(rate(cortex_memcache_request_duration_seconds_count[1m]))
by (cluster, job, method)"
record: "cluster_job_method:cortex_memcache_request_duration_seconds:avg"
- expr: "sum(rate(cortex_memcache_request_duration_seconds_bucket[5m])) by (le, cluster,
- expr: "sum(rate(cortex_memcache_request_duration_seconds_bucket[1m])) by (le, cluster,
job, method)"
record: "cluster_job_method:cortex_memcache_request_duration_seconds_bucket:sum_rate"
- expr: "sum(rate(cortex_memcache_request_duration_seconds_sum[5m])) by (cluster,
- expr: "sum(rate(cortex_memcache_request_duration_seconds_sum[1m])) by (cluster,
job, method)"
record: "cluster_job_method:cortex_memcache_request_duration_seconds_sum:sum_rate"
- expr: "sum(rate(cortex_memcache_request_duration_seconds_count[5m])) by (cluster,
- expr: "sum(rate(cortex_memcache_request_duration_seconds_count[1m])) by (cluster,
job, method)"
record: "cluster_job_method:cortex_memcache_request_duration_seconds_count:sum_rate"
- expr: "histogram_quantile(0.99, sum(rate(cortex_cache_request_duration_seconds_bucket[5m]))
- expr: "histogram_quantile(0.99, sum(rate(cortex_cache_request_duration_seconds_bucket[1m]))
by (le, cluster, job))"
record: "cluster_job:cortex_cache_request_duration_seconds:99quantile"
- expr: "histogram_quantile(0.50, sum(rate(cortex_cache_request_duration_seconds_bucket[5m]))
- expr: "histogram_quantile(0.50, sum(rate(cortex_cache_request_duration_seconds_bucket[1m]))
by (le, cluster, job))"
record: "cluster_job:cortex_cache_request_duration_seconds:50quantile"
- expr: "sum(rate(cortex_cache_request_duration_seconds_sum[5m])) by (cluster, job)
/ sum(rate(cortex_cache_request_duration_seconds_count[5m])) by (cluster, job)"
- expr: "sum(rate(cortex_cache_request_duration_seconds_sum[1m])) by (cluster, job)
/ sum(rate(cortex_cache_request_duration_seconds_count[1m])) by (cluster, job)"
record: "cluster_job:cortex_cache_request_duration_seconds:avg"
- expr: "sum(rate(cortex_cache_request_duration_seconds_bucket[5m])) by (le, cluster,
- expr: "sum(rate(cortex_cache_request_duration_seconds_bucket[1m])) by (le, cluster,
job)"
record: "cluster_job:cortex_cache_request_duration_seconds_bucket:sum_rate"
- expr: "sum(rate(cortex_cache_request_duration_seconds_sum[5m])) by (cluster, job)"
- expr: "sum(rate(cortex_cache_request_duration_seconds_sum[1m])) by (cluster, job)"
record: "cluster_job:cortex_cache_request_duration_seconds_sum:sum_rate"
- expr: "sum(rate(cortex_cache_request_duration_seconds_count[5m])) by (cluster,
- expr: "sum(rate(cortex_cache_request_duration_seconds_count[1m])) by (cluster,
job)"
record: "cluster_job:cortex_cache_request_duration_seconds_count:sum_rate"
- expr: "histogram_quantile(0.99, sum(rate(cortex_cache_request_duration_seconds_bucket[5m]))
- expr: "histogram_quantile(0.99, sum(rate(cortex_cache_request_duration_seconds_bucket[1m]))
by (le, cluster, job, method))"
record: "cluster_job_method:cortex_cache_request_duration_seconds:99quantile"
- expr: "histogram_quantile(0.50, sum(rate(cortex_cache_request_duration_seconds_bucket[5m]))
- expr: "histogram_quantile(0.50, sum(rate(cortex_cache_request_duration_seconds_bucket[1m]))
by (le, cluster, job, method))"
record: "cluster_job_method:cortex_cache_request_duration_seconds:50quantile"
- expr: "sum(rate(cortex_cache_request_duration_seconds_sum[5m])) by (cluster, job,
method) / sum(rate(cortex_cache_request_duration_seconds_count[5m])) by (cluster,
- expr: "sum(rate(cortex_cache_request_duration_seconds_sum[1m])) by (cluster, job,
method) / sum(rate(cortex_cache_request_duration_seconds_count[1m])) by (cluster,
job, method)"
record: "cluster_job_method:cortex_cache_request_duration_seconds:avg"
- expr: "sum(rate(cortex_cache_request_duration_seconds_bucket[5m])) by (le, cluster,
- expr: "sum(rate(cortex_cache_request_duration_seconds_bucket[1m])) by (le, cluster,
job, method)"
record: "cluster_job_method:cortex_cache_request_duration_seconds_bucket:sum_rate"
- expr: "sum(rate(cortex_cache_request_duration_seconds_sum[5m])) by (cluster, job,
- expr: "sum(rate(cortex_cache_request_duration_seconds_sum[1m])) by (cluster, job,
method)"
record: "cluster_job_method:cortex_cache_request_duration_seconds_sum:sum_rate"
- expr: "sum(rate(cortex_cache_request_duration_seconds_count[5m])) by (cluster,
- expr: "sum(rate(cortex_cache_request_duration_seconds_count[1m])) by (cluster,
job, method)"
record: "cluster_job_method:cortex_cache_request_duration_seconds_count:sum_rate"
- name: "mimir_storage"
rules:
- expr: "histogram_quantile(0.99, sum(rate(cortex_kv_request_duration_seconds_bucket[5m]))
- expr: "histogram_quantile(0.99, sum(rate(cortex_kv_request_duration_seconds_bucket[1m]))
by (le, cluster, job))"
record: "cluster_job:cortex_kv_request_duration_seconds:99quantile"
- expr: "histogram_quantile(0.50, sum(rate(cortex_kv_request_duration_seconds_bucket[5m]))
- expr: "histogram_quantile(0.50, sum(rate(cortex_kv_request_duration_seconds_bucket[1m]))
by (le, cluster, job))"
record: "cluster_job:cortex_kv_request_duration_seconds:50quantile"
- expr: "sum(rate(cortex_kv_request_duration_seconds_sum[5m])) by (cluster, job)
/ sum(rate(cortex_kv_request_duration_seconds_count[5m])) by (cluster, job)"
- expr: "sum(rate(cortex_kv_request_duration_seconds_sum[1m])) by (cluster, job)
/ sum(rate(cortex_kv_request_duration_seconds_count[1m])) by (cluster, job)"
record: "cluster_job:cortex_kv_request_duration_seconds:avg"
- expr: "sum(rate(cortex_kv_request_duration_seconds_bucket[5m])) by (le, cluster,
- expr: "sum(rate(cortex_kv_request_duration_seconds_bucket[1m])) by (le, cluster,
job)"
record: "cluster_job:cortex_kv_request_duration_seconds_bucket:sum_rate"
- expr: "sum(rate(cortex_kv_request_duration_seconds_sum[5m])) by (cluster, job)"
- expr: "sum(rate(cortex_kv_request_duration_seconds_sum[1m])) by (cluster, job)"
record: "cluster_job:cortex_kv_request_duration_seconds_sum:sum_rate"
- expr: "sum(rate(cortex_kv_request_duration_seconds_count[5m])) by (cluster, job)"
- expr: "sum(rate(cortex_kv_request_duration_seconds_count[1m])) by (cluster, job)"
record: "cluster_job:cortex_kv_request_duration_seconds_count:sum_rate"
- name: "mimir_queries"
rules:
- expr: "histogram_quantile(0.99, sum(rate(cortex_query_frontend_retries_bucket[5m]))
- expr: "histogram_quantile(0.99, sum(rate(cortex_query_frontend_retries_bucket[1m]))
by (le, cluster, job))"
record: "cluster_job:cortex_query_frontend_retries:99quantile"
- expr: "histogram_quantile(0.50, sum(rate(cortex_query_frontend_retries_bucket[5m]))
- expr: "histogram_quantile(0.50, sum(rate(cortex_query_frontend_retries_bucket[1m]))
by (le, cluster, job))"
record: "cluster_job:cortex_query_frontend_retries:50quantile"
- expr: "sum(rate(cortex_query_frontend_retries_sum[5m])) by (cluster, job) / sum(rate(cortex_query_frontend_retries_count[5m]))
- expr: "sum(rate(cortex_query_frontend_retries_sum[1m])) by (cluster, job) / sum(rate(cortex_query_frontend_retries_count[1m]))
by (cluster, job)"
record: "cluster_job:cortex_query_frontend_retries:avg"
- expr: "sum(rate(cortex_query_frontend_retries_bucket[5m])) by (le, cluster, job)"
- expr: "sum(rate(cortex_query_frontend_retries_bucket[1m])) by (le, cluster, job)"
record: "cluster_job:cortex_query_frontend_retries_bucket:sum_rate"
- expr: "sum(rate(cortex_query_frontend_retries_sum[5m])) by (cluster, job)"
- expr: "sum(rate(cortex_query_frontend_retries_sum[1m])) by (cluster, job)"
record: "cluster_job:cortex_query_frontend_retries_sum:sum_rate"
- expr: "sum(rate(cortex_query_frontend_retries_count[5m])) by (cluster, job)"
- expr: "sum(rate(cortex_query_frontend_retries_count[1m])) by (cluster, job)"
record: "cluster_job:cortex_query_frontend_retries_count:sum_rate"
- expr: "histogram_quantile(0.99, sum(rate(cortex_query_frontend_queue_duration_seconds_bucket[5m]))
- expr: "histogram_quantile(0.99, sum(rate(cortex_query_frontend_queue_duration_seconds_bucket[1m]))
by (le, cluster, job))"
record: "cluster_job:cortex_query_frontend_queue_duration_seconds:99quantile"
- expr: "histogram_quantile(0.50, sum(rate(cortex_query_frontend_queue_duration_seconds_bucket[5m]))
- expr: "histogram_quantile(0.50, sum(rate(cortex_query_frontend_queue_duration_seconds_bucket[1m]))
by (le, cluster, job))"
record: "cluster_job:cortex_query_frontend_queue_duration_seconds:50quantile"
- expr: "sum(rate(cortex_query_frontend_queue_duration_seconds_sum[5m])) by (cluster,
job) / sum(rate(cortex_query_frontend_queue_duration_seconds_count[5m])) by
- expr: "sum(rate(cortex_query_frontend_queue_duration_seconds_sum[1m])) by (cluster,
job) / sum(rate(cortex_query_frontend_queue_duration_seconds_count[1m])) by
(cluster, job)"
record: "cluster_job:cortex_query_frontend_queue_duration_seconds:avg"
- expr: "sum(rate(cortex_query_frontend_queue_duration_seconds_bucket[5m])) by (le,
- expr: "sum(rate(cortex_query_frontend_queue_duration_seconds_bucket[1m])) by (le,
cluster, job)"
record: "cluster_job:cortex_query_frontend_queue_duration_seconds_bucket:sum_rate"
- expr: "sum(rate(cortex_query_frontend_queue_duration_seconds_sum[5m])) by (cluster,
- expr: "sum(rate(cortex_query_frontend_queue_duration_seconds_sum[1m])) by (cluster,
job)"
record: "cluster_job:cortex_query_frontend_queue_duration_seconds_sum:sum_rate"
- expr: "sum(rate(cortex_query_frontend_queue_duration_seconds_count[5m])) by (cluster,
- expr: "sum(rate(cortex_query_frontend_queue_duration_seconds_count[1m])) by (cluster,
job)"
record: "cluster_job:cortex_query_frontend_queue_duration_seconds_count:sum_rate"
- name: "mimir_ingester_queries"
rules:
- expr: "histogram_quantile(0.99, sum(rate(cortex_ingester_queried_series_bucket[5m]))
- expr: "histogram_quantile(0.99, sum(rate(cortex_ingester_queried_series_bucket[1m]))
by (le, cluster, job))"
record: "cluster_job:cortex_ingester_queried_series:99quantile"
- expr: "histogram_quantile(0.50, sum(rate(cortex_ingester_queried_series_bucket[5m]))
- expr: "histogram_quantile(0.50, sum(rate(cortex_ingester_queried_series_bucket[1m]))
by (le, cluster, job))"
record: "cluster_job:cortex_ingester_queried_series:50quantile"
- expr: "sum(rate(cortex_ingester_queried_series_sum[5m])) by (cluster, job) / sum(rate(cortex_ingester_queried_series_count[5m]))
- expr: "sum(rate(cortex_ingester_queried_series_sum[1m])) by (cluster, job) / sum(rate(cortex_ingester_queried_series_count[1m]))
by (cluster, job)"
record: "cluster_job:cortex_ingester_queried_series:avg"
- expr: "sum(rate(cortex_ingester_queried_series_bucket[5m])) by (le, cluster, job)"
- expr: "sum(rate(cortex_ingester_queried_series_bucket[1m])) by (le, cluster, job)"
record: "cluster_job:cortex_ingester_queried_series_bucket:sum_rate"
- expr: "sum(rate(cortex_ingester_queried_series_sum[5m])) by (cluster, job)"
- expr: "sum(rate(cortex_ingester_queried_series_sum[1m])) by (cluster, job)"
record: "cluster_job:cortex_ingester_queried_series_sum:sum_rate"
- expr: "sum(rate(cortex_ingester_queried_series_count[5m])) by (cluster, job)"
- expr: "sum(rate(cortex_ingester_queried_series_count[1m])) by (cluster, job)"
record: "cluster_job:cortex_ingester_queried_series_count:sum_rate"
- expr: "histogram_quantile(0.99, sum(rate(cortex_ingester_queried_samples_bucket[5m]))
- expr: "histogram_quantile(0.99, sum(rate(cortex_ingester_queried_samples_bucket[1m]))
by (le, cluster, job))"
record: "cluster_job:cortex_ingester_queried_samples:99quantile"
- expr: "histogram_quantile(0.50, sum(rate(cortex_ingester_queried_samples_bucket[5m]))
- expr: "histogram_quantile(0.50, sum(rate(cortex_ingester_queried_samples_bucket[1m]))
by (le, cluster, job))"
record: "cluster_job:cortex_ingester_queried_samples:50quantile"
- expr: "sum(rate(cortex_ingester_queried_samples_sum[5m])) by (cluster, job) / sum(rate(cortex_ingester_queried_samples_count[5m]))
- expr: "sum(rate(cortex_ingester_queried_samples_sum[1m])) by (cluster, job) / sum(rate(cortex_ingester_queried_samples_count[1m]))
by (cluster, job)"
record: "cluster_job:cortex_ingester_queried_samples:avg"
- expr: "sum(rate(cortex_ingester_queried_samples_bucket[5m])) by (le, cluster, job)"
- expr: "sum(rate(cortex_ingester_queried_samples_bucket[1m])) by (le, cluster, job)"
record: "cluster_job:cortex_ingester_queried_samples_bucket:sum_rate"
- expr: "sum(rate(cortex_ingester_queried_samples_sum[5m])) by (cluster, job)"
- expr: "sum(rate(cortex_ingester_queried_samples_sum[1m])) by (cluster, job)"
record: "cluster_job:cortex_ingester_queried_samples_sum:sum_rate"
- expr: "sum(rate(cortex_ingester_queried_samples_count[5m])) by (cluster, job)"
- expr: "sum(rate(cortex_ingester_queried_samples_count[1m])) by (cluster, job)"
record: "cluster_job:cortex_ingester_queried_samples_count:sum_rate"
- expr: "histogram_quantile(0.99, sum(rate(cortex_ingester_queried_exemplars_bucket[5m]))
- expr: "histogram_quantile(0.99, sum(rate(cortex_ingester_queried_exemplars_bucket[1m]))
by (le, cluster, job))"
record: "cluster_job:cortex_ingester_queried_exemplars:99quantile"
- expr: "histogram_quantile(0.50, sum(rate(cortex_ingester_queried_exemplars_bucket[5m]))
- expr: "histogram_quantile(0.50, sum(rate(cortex_ingester_queried_exemplars_bucket[1m]))
by (le, cluster, job))"
record: "cluster_job:cortex_ingester_queried_exemplars:50quantile"
- expr: "sum(rate(cortex_ingester_queried_exemplars_sum[5m])) by (cluster, job) /
sum(rate(cortex_ingester_queried_exemplars_count[5m])) by (cluster, job)"
- expr: "sum(rate(cortex_ingester_queried_exemplars_sum[1m])) by (cluster, job) /
sum(rate(cortex_ingester_queried_exemplars_count[1m])) by (cluster, job)"
record: "cluster_job:cortex_ingester_queried_exemplars:avg"
- expr: "sum(rate(cortex_ingester_queried_exemplars_bucket[5m])) by (le, cluster,
- expr: "sum(rate(cortex_ingester_queried_exemplars_bucket[1m])) by (le, cluster,
job)"
record: "cluster_job:cortex_ingester_queried_exemplars_bucket:sum_rate"
- expr: "sum(rate(cortex_ingester_queried_exemplars_sum[5m])) by (cluster, job)"
- expr: "sum(rate(cortex_ingester_queried_exemplars_sum[1m])) by (cluster, job)"
record: "cluster_job:cortex_ingester_queried_exemplars_sum:sum_rate"
- expr: "sum(rate(cortex_ingester_queried_exemplars_count[5m])) by (cluster, job)"
- expr: "sum(rate(cortex_ingester_queried_exemplars_count[1m])) by (cluster, job)"
record: "cluster_job:cortex_ingester_queried_exemplars_count:sum_rate"
- name: "mimir_received_samples"
rules:
- expr: "sum by (cluster, namespace, job) (rate(cortex_distributor_received_samples_total[5m]))"
- 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]))"
- 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]))"
- 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]))"
- 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]))"
- expr: "|
sum by (cluster, namespace, job) (rate(cortex_ingester_tsdb_exemplar_exemplars_appended_total[5m]))"
record: "cluster_namespace_job:cortex_ingester_tsdb_exemplar_exemplars_appended:rate5m"
- name: "mimir_scaling_rules"
rules:
- expr: |
- expr: "|
# Convenience rule to get the number of replicas for both a deployment and a statefulset.
# Multi-zone deployments are grouped together removing the "zone-X" suffix.
# Multi-zone deployments are grouped together removing the \"zone-X\" suffix.
sum by (cluster, namespace, deployment) (
label_replace(
kube_deployment_spec_replicas,
# The question mark in "(.*?)" is used to make it non-greedy, otherwise it
# The question mark in \"(.*?)\" is used to make it non-greedy, otherwise it
# always matches everything and the (optional) zone is not removed.
"deployment", "$1", "deployment", "(.*?)(?:-zone-[a-z])?"
\"deployment\", \"$1\", \"deployment\", \"(.*?)(?:-zone-[a-z])?\"
)
)
or
sum by (cluster, namespace, deployment) (
label_replace(kube_statefulset_replicas, "deployment", "$1", "statefulset", "(.*?)(?:-zone-[a-z])?")
)
label_replace(kube_statefulset_replicas, \"deployment\", \"$1\", \"statefulset\", \"(.*?)(?:-zone-[a-z])?\")
)"
record: "cluster_namespace_deployment:actual_replicas:count"
- expr: |
- expr: "|
ceil(
quantile_over_time(0.99,
sum by (cluster, namespace) (
@@ -319,21 +324,21 @@ groups:
)[24h:]
)
/ 240000
)
)"
labels:
deployment: "distributor"
reason: "sample_rate"
record: "cluster_namespace_deployment_reason:required_replicas:count"
- expr: |
- expr: "|
ceil(
sum by (cluster, namespace) (cortex_limits_overrides{limit_name="ingestion_rate"})
sum by (cluster, namespace) (cortex_limits_overrides{limit_name=\"ingestion_rate\"})
* 0.59999999999999998 / 240000
)
)"
labels:
deployment: "distributor"
reason: "sample_rate_limits"
record: "cluster_namespace_deployment_reason:required_replicas:count"
- expr: |
- expr: "|
ceil(
quantile_over_time(0.99,
sum by (cluster, namespace) (
@@ -341,12 +346,12 @@ groups:
)[24h:]
)
* 3 / 80000
)
)"
labels:
deployment: "ingester"
reason: "sample_rate"
record: "cluster_namespace_deployment_reason:required_replicas:count"
- expr: |
- expr: "|
ceil(
quantile_over_time(0.99,
sum by(cluster, namespace) (
@@ -354,59 +359,59 @@ groups:
)[24h:]
)
/ 1500000
)
)"
labels:
deployment: "ingester"
reason: "active_series"
record: "cluster_namespace_deployment_reason:required_replicas:count"
- expr: |
- expr: "|
ceil(
sum by (cluster, namespace) (cortex_limits_overrides{limit_name="max_global_series_per_user"})
sum by (cluster, namespace) (cortex_limits_overrides{limit_name=\"max_global_series_per_user\"})
* 3 * 0.59999999999999998 / 1500000
)
)"
labels:
deployment: "ingester"
reason: "active_series_limits"
record: "cluster_namespace_deployment_reason:required_replicas:count"
- expr: |
- expr: "|
ceil(
sum by (cluster, namespace) (cortex_limits_overrides{limit_name="ingestion_rate"})
sum by (cluster, namespace) (cortex_limits_overrides{limit_name=\"ingestion_rate\"})
* 0.59999999999999998 / 80000
)
)"
labels:
deployment: "ingester"
reason: "sample_rate_limits"
record: "cluster_namespace_deployment_reason:required_replicas:count"
- expr: |
- expr: "|
ceil(
(sum by (cluster, namespace) (
cortex_ingester_tsdb_storage_blocks_bytes{job=~".+/ingester.*"}
cortex_ingester_tsdb_storage_blocks_bytes{job=~\".+/ingester.*\"}
) / 4)
/
avg by (cluster, namespace) (
memcached_limit_bytes{job=~".+/memcached"}
memcached_limit_bytes{job=~\".+/memcached\"}
)
)
)"
labels:
deployment: "memcached"
reason: "active_series"
record: "cluster_namespace_deployment_reason:required_replicas:count"
- expr: |
- 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]+))"
sum by (cluster, namespace, pod)(rate(container_cpu_usage_seconds_total[1m])),
\"deployment\", \"$1\", \"pod\", \"(.*)-(?:([0-9]+)|([a-z0-9]+)-([a-z0-9]+))\"
),
# The question mark in "(.*?)" is used to make it non-greedy, otherwise it
# The question mark in \"(.*?)\" is used to make it non-greedy, otherwise it
# always matches everything and the (optional) zone is not removed.
"deployment", "$1", "deployment", "(.*?)(?:-zone-[a-z])?"
\"deployment\", \"$1\", \"deployment\", \"(.*?)(?:-zone-[a-z])?\"
)
)
)"
record: "cluster_namespace_deployment:container_cpu_usage_seconds_total:sum_rate"
- expr: |
- expr: "|
# Convenience rule to get the CPU request for both a deployment and a statefulset.
# Multi-zone deployments are grouped together removing the "zone-X" suffix.
# Multi-zone deployments are grouped together removing the \"zone-X\" suffix.
# This recording rule is made compatible with the breaking changes introduced in kube-state-metrics v2
# that remove resource metrics, ref:
# - https://github.com/kubernetes/kube-state-metrics/blob/master/CHANGELOG.md#v200-alpha--2020-09-16
@@ -419,11 +424,11 @@ groups:
label_replace(
label_replace(
kube_pod_container_resource_requests_cpu_cores,
"deployment", "$1", "pod", "(.*)-(?:([0-9]+)|([a-z0-9]+)-([a-z0-9]+))"
\"deployment\", \"$1\", \"pod\", \"(.*)-(?:([0-9]+)|([a-z0-9]+)-([a-z0-9]+))\"
),
# The question mark in "(.*?)" is used to make it non-greedy, otherwise it
# The question mark in \"(.*?)\" is used to make it non-greedy, otherwise it
# always matches everything and the (optional) zone is not removed.
"deployment", "$1", "deployment", "(.*?)(?:-zone-[a-z])?"
\"deployment\", \"$1\", \"deployment\", \"(.*?)(?:-zone-[a-z])?\"
)
)
)
@@ -434,17 +439,17 @@ groups:
sum by (cluster, namespace, deployment) (
label_replace(
label_replace(
kube_pod_container_resource_requests{resource="cpu"},
"deployment", "$1", "pod", "(.*)-(?:([0-9]+)|([a-z0-9]+)-([a-z0-9]+))"
kube_pod_container_resource_requests{resource=\"cpu\"},
\"deployment\", \"$1\", \"pod\", \"(.*)-(?:([0-9]+)|([a-z0-9]+)-([a-z0-9]+))\"
),
# The question mark in "(.*?)" is used to make it non-greedy, otherwise it
# The question mark in \"(.*?)\" is used to make it non-greedy, otherwise it
# always matches everything and the (optional) zone is not removed.
"deployment", "$1", "deployment", "(.*?)(?:-zone-[a-z])?"
\"deployment\", \"$1\", \"deployment\", \"(.*?)(?:-zone-[a-z])?\"
)
)
)
)"
record: "cluster_namespace_deployment:kube_pod_container_resource_requests_cpu_cores:sum"
- expr: |
- 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.
@@ -454,28 +459,28 @@ groups:
quantile_over_time(0.99, cluster_namespace_deployment:container_cpu_usage_seconds_total:sum_rate[24h])
/
cluster_namespace_deployment:kube_pod_container_resource_requests_cpu_cores:sum
)
)"
labels:
reason: "cpu_usage"
record: "cluster_namespace_deployment_reason:required_replicas:count"
- expr: |
- expr: "|
# Convenience rule to get the Memory utilization for both a deployment and a statefulset.
# Multi-zone deployments are grouped together removing the "zone-X" suffix.
# Multi-zone deployments are grouped together removing the \"zone-X\" suffix.
sum by (cluster, namespace, deployment) (
label_replace(
label_replace(
container_memory_usage_bytes{image!=""},
"deployment", "$1", "pod", "(.*)-(?:([0-9]+)|([a-z0-9]+)-([a-z0-9]+))"
container_memory_usage_bytes{image!=\"\"},
\"deployment\", \"$1\", \"pod\", \"(.*)-(?:([0-9]+)|([a-z0-9]+)-([a-z0-9]+))\"
),
# The question mark in "(.*?)" is used to make it non-greedy, otherwise it
# The question mark in \"(.*?)\" is used to make it non-greedy, otherwise it
# always matches everything and the (optional) zone is not removed.
"deployment", "$1", "deployment", "(.*?)(?:-zone-[a-z])?"
\"deployment\", \"$1\", \"deployment\", \"(.*?)(?:-zone-[a-z])?\"
)
)
)"
record: "cluster_namespace_deployment:container_memory_usage_bytes:sum"
- expr: |
- expr: "|
# Convenience rule to get the Memory request for both a deployment and a statefulset.
# Multi-zone deployments are grouped together removing the "zone-X" suffix.
# Multi-zone deployments are grouped together removing the \"zone-X\" suffix.
# This recording rule is made compatible with the breaking changes introduced in kube-state-metrics v2
# that remove resource metrics, ref:
# - https://github.com/kubernetes/kube-state-metrics/blob/master/CHANGELOG.md#v200-alpha--2020-09-16
@@ -488,11 +493,11 @@ groups:
label_replace(
label_replace(
kube_pod_container_resource_requests_memory_bytes,
"deployment", "$1", "pod", "(.*)-(?:([0-9]+)|([a-z0-9]+)-([a-z0-9]+))"
\"deployment\", \"$1\", \"pod\", \"(.*)-(?:([0-9]+)|([a-z0-9]+)-([a-z0-9]+))\"
),
# The question mark in "(.*?)" is used to make it non-greedy, otherwise it
# The question mark in \"(.*?)\" is used to make it non-greedy, otherwise it
# always matches everything and the (optional) zone is not removed.
"deployment", "$1", "deployment", "(.*?)(?:-zone-[a-z])?"
\"deployment\", \"$1\", \"deployment\", \"(.*?)(?:-zone-[a-z])?\"
)
)
)
@@ -503,17 +508,17 @@ groups:
sum by (cluster, namespace, deployment) (
label_replace(
label_replace(
kube_pod_container_resource_requests{resource="memory"},
"deployment", "$1", "pod", "(.*)-(?:([0-9]+)|([a-z0-9]+)-([a-z0-9]+))"
kube_pod_container_resource_requests{resource=\"memory\"},
\"deployment\", \"$1\", \"pod\", \"(.*)-(?:([0-9]+)|([a-z0-9]+)-([a-z0-9]+))\"
),
# The question mark in "(.*?)" is used to make it non-greedy, otherwise it
# The question mark in \"(.*?)\" is used to make it non-greedy, otherwise it
# always matches everything and the (optional) zone is not removed.
"deployment", "$1", "deployment", "(.*?)(?:-zone-[a-z])?"
\"deployment\", \"$1\", \"deployment\", \"(.*?)(?:-zone-[a-z])?\"
)
)
)
)"
record: "cluster_namespace_deployment:kube_pod_container_resource_requests_memory_bytes:sum"
- expr: |
- 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.
@@ -523,33 +528,44 @@ groups:
quantile_over_time(0.99, cluster_namespace_deployment:container_memory_usage_bytes:sum[24h])
/
cluster_namespace_deployment:kube_pod_container_resource_requests_memory_bytes:sum
)
)"
labels:
reason: "memory_usage"
record: "cluster_namespace_deployment_reason:required_replicas:count"
- name: "mimir_alertmanager_rules"
rules:
- expr: "sum by (cluster, job, pod) (cortex_alertmanager_alerts)"
- 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)"
- 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]))"
- 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]))"
- 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]))"
- 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]))"
- 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]))"
- 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]))"
- 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]))"
- 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]))"
- 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]))"
- expr: "|
sum by(cluster, namespace, pod) (rate(cortex_ingester_ingested_samples_total[1m]))"
record: "cluster_namespace_pod:cortex_ingester_ingested_samples_total:rate1m"

View File

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

View File

@@ -1,33 +0,0 @@
{{/*
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 -}}

View File

@@ -6,15 +6,6 @@
{{- join ", " $list }}
{{- end }}
{{- define "agent.all_namespaces" -}}
{{- $list := list }}
{{- range .Values.namespacesToMonitor }}
{{- $list = append $list (printf "%s" .) }}
{{- end }}
{{- $list = append $list .Release.Namespace }}
{{- join "|" $list }}
{{- end }}
{{- define "agent.loki_write_targets" -}}
{{- $list := list }}
{{- if .Values.local.logs.enabled }}
@@ -27,10 +18,10 @@
{{- end }}
{{- define "agent.loki_process_targets" -}}
{{- if and (empty .Values.logs.piiRegexes) (empty .Values.logs.retain) }}
{{- if empty .Values.logs.piiRegexes }}
{{- include "agent.loki_write_targets" . }}
{{- else }}
{{- printf "loki.process.filter.receiver" }}
{{- printf "loki.process.PII.receiver" }}
{{- end }}
{{- end }}
@@ -51,7 +42,7 @@
{{- $list = append $list ("otelcol.exporter.otlp.local.input") }}
{{- end }}
{{- if .Values.cloud.traces.enabled }}
{{- $list = append $list ("otelcol.exporter.otlphttp.cloud.input") }}
{{- $list = append $list ("otelcol.exporter.otlp.cloud.input") }}
{{- end }}
{{- join ", " $list }}
{{- end }}

View File

@@ -8,7 +8,7 @@ data:
discovery.kubernetes "pods" {
role = "pod"
namespaces {
own_namespace = true
own_namespace = false
names = [ {{ include "agent.namespaces" . }} ]
}
}
@@ -33,40 +33,22 @@ data:
}
rule {
target_label = "cluster"
replacement = "{{- .Values.clusterLabelValue -}}"
replacement = "{{- .Values.clusterName -}}"
}
}
{{- if or .Values.local.logs.enabled .Values.cloud.logs.enabled }}
// Logs
{{- if .Values.cloud.logs.enabled }}
remote.kubernetes.secret "logs_credentials" {
namespace = "{{- $.Release.Namespace -}}"
name = "{{- .Values.cloud.logs.secret -}}"
}
{{- end }}
{{- if or .Values.local.logs.enabled .Values.cloud.logs.enabled }}
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" {
{{- if not (empty .Values.logs.piiRegexes) }}
loki.process "PII" {
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 }}"
@@ -74,101 +56,29 @@ data:
replace = "{{ .replace }}"
}
{{- end }}
{{- end }}
}
{{- end }}
{{- end }}
{{- if or .Values.local.metrics.enabled .Values.cloud.metrics.enabled }}
// Metrics
{{- if .Values.cloud.metrics.enabled }}
remote.kubernetes.secret "metrics_credentials" {
namespace = "{{- $.Release.Namespace -}}"
name = "{{- .Values.cloud.metrics.secret -}}"
}
{{- end }}
discovery.kubernetes "metric_pods" {
role = "pod"
namespaces {
own_namespace = true
names = [ {{ include "agent.namespaces" . }} ]
}
}
discovery.relabel "only_http_metrics" {
targets = discovery.kubernetes.metric_pods.targets
rule {
source_labels = ["__meta_kubernetes_namespace"]
target_label = "namespace"
}
rule {
source_labels = ["__meta_kubernetes_pod_name"]
target_label = "pod"
}
rule {
source_labels = ["__meta_kubernetes_namespace", "__meta_kubernetes_pod_label_app_kubernetes_io_name", "__meta_kubernetes_pod_label_app_kubernetes_io_component"]
separator = "/"
regex = "(.*)/(.*)/(.*)"
replacement = "${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"
}
}
{{- if or .Values.local.metrics.enabled .Values.cloud.metrics.enabled }}
prometheus.scrape "pods" {
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"
}
rule {
source_labels = ["namespace"]
regex = "{{ include "agent.all_namespaces" . }}"
action = "keep"
}
targets = discovery.relabel.rename_meta_labels.output
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 ]
forward_to = [ {{ include "agent.prometheus_write_targets" . }} ]
}
{{- end }}
// cAdvisor and Kubelet metrics
// cAdvisor and Kubelete metrics
// Based on https://github.com/Chewie/loutretelecom-manifests/blob/main/manifests/addons/monitoring/config.river
discovery.kubernetes "all_nodes" {
role = "node"
namespaces {
own_namespace = true
names = [ {{ include "agent.namespaces" . }} ]
}
}
discovery.relabel "all_nodes" {
@@ -194,17 +104,15 @@ data:
}
rule {
target_label = "cluster"
replacement = "{{- .Values.clusterLabelValue -}}"
replacement = "{{- .Values.clusterName -}}"
}
}
prometheus.scrape "cadvisor" {
clustering {
enabled = true
}
targets = discovery.relabel.all_nodes.output
forward_to = [ prometheus.relabel.filter.receiver ]
forward_to = [ {{ include "agent.prometheus_write_targets" . }} ]
scrape_interval = "15s"
metrics_path = "/metrics/cadvisor"
scheme = "https"
@@ -215,12 +123,10 @@ data:
}
prometheus.scrape "kubelet" {
clustering {
enabled = true
}
targets = discovery.relabel.all_nodes.output
forward_to = [ prometheus.relabel.filter.receiver ]
forward_to = [ {{ include "agent.prometheus_write_targets" . }} ]
scrape_interval = "15s"
metrics_path = "/metrics"
scheme = "https"
@@ -230,20 +136,18 @@ data:
}
}
prometheus.exporter.unix "promexporter" {}
prometheus.exporter.unix {}
prometheus.scrape "node_exporter" {
clustering {
enabled = true
}
targets = prometheus.exporter.unix.promexporter.targets
targets = prometheus.exporter.unix.targets
forward_to = [prometheus.relabel.node_exporter.receiver]
job_name = "node-exporter"
scrape_interval = "15s"
}
prometheus.relabel "node_exporter" {
forward_to = [ prometheus.relabel.filter.receiver ]
forward_to = [ {{ include "agent.prometheus_write_targets" . }} ]
rule {
replacement = env("HOSTNAME")
@@ -274,44 +178,27 @@ data:
}
rule {
target_label = "cluster"
replacement = "{{- .Values.clusterLabelValue -}}"
replacement = "{{- .Values.clusterName -}}"
}
}
{{- end }}
{{- if or .Values.local.traces.enabled .Values.cloud.traces.enabled }}
// Traces
{{- if .Values.cloud.traces.enabled }}
remote.kubernetes.secret "traces_credentials" {
namespace = "{{- $.Release.Namespace -}}"
name = "{{- .Values.cloud.traces.secret -}}"
}
{{- end }}
{{- if or .Values.local.traces.enabled .Values.cloud.traces.enabled }}
// 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.
// In this case, the Agent is listening on all available bindable addresses on port 4317 (which is the
// default OTLP gRPC port) for the OTLP protocol.
grpc {
endpoint = "0.0.0.0:4317"
endpoint = "0.0.0.0:4317"
}
// We define where to send the output of all ingested traces. In this case, to the OpenTelemetry batch processor
// named 'default'.
output {
traces = [otelcol.processor.batch.default.input]
}
}
otelcol.receiver.jaeger "jaeger" {
protocols {
thrift_http {}
}
output {
traces = [otelcol.processor.batch.default.input]
traces = [otelcol.processor.batch.default.input]
}
}
@@ -332,7 +219,7 @@ data:
{{- if .Values.local.logs.enabled }}
loki.write "local" {
endpoint {
url = "http://{{- .Release.Namespace -}}-loki-gateway.{{- .Release.Namespace -}}.svc.cluster.local:80/loki/api/v1/push"
url = "http://loki-gateway.{{- .Release.Namespace -}}.svc.cluster.local:80/loki/api/v1/push"
}
}
{{- end }}
@@ -345,13 +232,33 @@ data:
}
{{- end }}
{{- if or .Values.local.traces.enabled .Values.cloud.traces.enabled }}
// The OpenTelemetry exporter exports processed trace spans to another target that is listening for OTLP format traces.
// A unique label, 'local', is added to uniquely identify this exporter.
otelcol.exporter.otlp "local" {
// Define the client for exporting.
client {
// Send to the locally running Tempo instance, on port 4317 (OTLP gRPC).
endpoint = "meta-tempo-distributor:4317"
// Configure TLS settings for communicating with the endpoint.
tls {
// The connection is insecure.
insecure = true
// Do not verify TLS certificates when connecting.
insecure_skip_verify = true
}
}
}
{{- end }}
{{- if .Values.cloud.logs.enabled }}
loki.write "cloud" {
endpoint {
url = nonsensitive(remote.kubernetes.secret.logs_credentials.data["endpoint"])
url = "{{- .Values.cloud.logs.endpoint -}}/loki/api/v1/push"
basic_auth {
username = nonsensitive(remote.kubernetes.secret.logs_credentials.data["username"])
password = remote.kubernetes.secret.logs_credentials.data["password"]
username = "{{- .Values.cloud.logs.username -}}"
password = "{{- .Values.cloud.logs.password -}}"
}
}
}
@@ -360,25 +267,26 @@ data:
{{- if .Values.cloud.metrics.enabled }}
prometheus.remote_write "cloud" {
endpoint {
url = nonsensitive(remote.kubernetes.secret.metrics_credentials.data["endpoint"])
url = "{{- .Values.cloud.metrics.endpoint -}}/api/prom/push"
basic_auth {
username = nonsensitive(remote.kubernetes.secret.metrics_credentials.data["username"])
password = remote.kubernetes.secret.metrics_credentials.data["password"]
username = "{{- .Values.cloud.metrics.username -}}"
password = "{{- .Values.cloud.metrics.password -}}"
}
}
}
{{- end }}
{{- if .Values.cloud.traces.enabled }}
otelcol.exporter.otlphttp "cloud" {
otelcol.exporter.otlp "cloud" {
client {
endpoint = nonsensitive(remote.kubernetes.secret.traces_credentials.data["endpoint"])
endpoint = "{{- .Values.cloud.traces.endpoint -}}"
auth = otelcol.auth.basic.creds.handler
}
}
otelcol.auth.basic "creds" {
username = nonsensitive(remote.kubernetes.secret.traces_credentials.data["username"])
password = remote.kubernetes.secret.traces_credentials.data["password"]
username = "{{- .Values.cloud.traces.username -}}"
password = "{{- .Values.cloud.traces.password -}}"
}
{{- end }}

View File

@@ -1,4 +1,4 @@
{{- if and .Values.local.grafana.enabled (or .Values.dashboards.logs.enabled .Values.dashboards.metrics.enabled .Values.dashboards.traces.enabled) }}
{{- if .Values.dashboards.traces.enabled }}
---
apiVersion: v1
kind: ConfigMap
@@ -14,6 +14,6 @@ data:
{{ $.Files.Get "src/dashboards/agent-remote-write.json" | fromJson | toJson }}
"agent-tracing-pipeline.json": |
{{ $.Files.Get "src/dashboards/agent-tracing-pipeline.json" | fromJson | toJson }}
"agent.json": |
"agent-overview.json": |
{{ $.Files.Get "src/dashboards/agent.json" | fromJson | toJson }}
{{- end }}

View File

@@ -1,4 +1,4 @@
{{- if and .Values.local.grafana.enabled (or .Values.dashboards.logs.enabled .Values.dashboards.metrics.enabled .Values.dashboards.traces.enabled) }}
{{- if or (or .Values.dashboards.logs.enabled .Values.dashboards.metrics.enabled) .Values.dashboards.traces.enabled }}
---
apiVersion: v1
kind: ConfigMap
@@ -27,6 +27,58 @@ 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

View File

@@ -1,4 +1,4 @@
{{- if .Values.local.grafana.enabled }}
{{- if or (or .Values.local.logs.enabled .Values.local.metrics.enabled) .Values.local.traces.enabled }}
---
apiVersion: v1
kind: ConfigMap
@@ -12,7 +12,7 @@ data:
# List of data sources to delete from the database.
deleteDatasources:
- name: Loki
- name: Loki
orgId: 1
# List of data sources to insert/update depending on what's
@@ -32,7 +32,7 @@ data:
uid: loki_ds
# <string> Sets the data source's URL, including the
# port.
url: http://{{- $.Release.Namespace -}}-loki-gateway.{{- $.Release.Namespace -}}.svc.cluster.local
url: http://loki-gateway.{{- $.Release.Namespace -}}.svc.cluster.local
# <bool> Toggles whether the data source is pre-selected
# for new panels. You can set only one default
# data source per organization.
@@ -61,10 +61,6 @@ data:
# <bool> Allows users to edit data sources from the
# Grafana UI.
editable: true
# Extra config.
jsonData:
# Scrape interval
timeInterval: 1m
{{- end }}
{{- if .Values.local.traces.enabled }}
- name: Tempo

View File

@@ -1,57 +0,0 @@
{{- 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 }}

View File

@@ -1,4 +1,4 @@
{{- if .Values.local.grafana.enabled }}
{{- if or (or .Values.local.logs.enabled .Values.local.metrics.enabled) .Values.local.traces.enabled }}
---
apiVersion: v1
kind: PersistentVolumeClaim
@@ -75,6 +75,22 @@ spec:
- 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:
@@ -95,6 +111,28 @@ 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

View File

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

View File

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

View File

@@ -0,0 +1,19 @@
{{- if .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 }}

View File

@@ -0,0 +1,19 @@
{{- if .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 }}

View File

@@ -0,0 +1,19 @@
{{- if .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 }}

View File

@@ -0,0 +1,19 @@
{{- if .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 }}

View File

@@ -0,0 +1,19 @@
{{- if .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 }}

View File

@@ -0,0 +1,21 @@
{{- if .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 }}

View File

@@ -1,9 +1,8 @@
{{- if .Values.local.grafana.enabled }}
{{- if and .Values.local.grafana.enabled (or .Values.dashboards.logs.enabled .Values.dashboards.metrics.enabled .Values.dashboards.traces.enabled) }}
{{- if or (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
name: meta-mimir-ruler-for-dashboards
namespace: {{ $.Release.Namespace }}
spec:
progressDeadlineSeconds: 600
@@ -92,6 +91,8 @@ spec:
runAsUser: 10001
seccompProfile:
type: RuntimeDefault
serviceAccount: meta-mimir
serviceAccountName: meta-mimir
terminationGracePeriodSeconds: 180
topologySpreadConstraints:
- labelSelector:
@@ -108,11 +109,11 @@ spec:
items:
- key: mimir.yaml
path: mimir.yaml
name: {{ $.Release.Namespace }}-mimir-config
name: meta-mimir-config
name: config
- configMap:
defaultMode: 420
name: {{ $.Release.Namespace }}-mimir-runtime
name: meta-mimir-runtime
name: runtime-config
- emptyDir: {}
name: storage
@@ -123,4 +124,3 @@ spec:
name: rules
name: rules
{{- end }}
{{- end }}

View File

@@ -1,5 +1,4 @@
{{- if .Values.local.metrics.enabled }}
{{- if and .Values.local.grafana.enabled (or .Values.dashboards.logs.enabled .Values.dashboards.metrics.enabled .Values.dashboards.traces.enabled) }}
{{- if or (or .Values.dashboards.logs.enabled .Values.dashboards.metrics.enabled) .Values.dashboards.traces.enabled }}
---
apiVersion: v1
kind: ConfigMap
@@ -17,4 +16,3 @@ data:
{{ ($.Files.Glob "src/rules/tempo-rules.yaml").AsConfig | indent 2 }}
{{- end }}
{{- end }}
{{- end }}

View File

@@ -3,20 +3,20 @@
{{- 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" -}}
{{- if or (empty .Values.cloud.logs.endpoint) (or (empty .Values.cloud.logs.username) (empty .Values.cloud.logs.password)) -}}
{{- fail "if cloud.logs is enabled then the endpoint, username and password have 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" -}}
{{- if or (empty .Values.cloud.metrics.endpoint) (or (empty .Values.cloud.metrics.username) (empty .Values.cloud.metrics.password)) -}}
{{- fail "if cloud.metrics is enabled then the endpoint, username and password have 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" -}}
{{- if or (empty .Values.cloud.traces.endpoint) (or (empty .Values.cloud.traces.username) (empty .Values.cloud.traces.password)) -}}
{{- fail "if cloud.traces is enabled then the endpoint, username and password have to be filled in" -}}
{{- end -}}
{{- end -}}
@@ -37,7 +37,3 @@
{{- 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 -}}

View File

@@ -1,181 +1,49 @@
# Specify the namespaces to monitor here
namespacesToMonitor:
- loki
- mimir
- tempo
# The name of the cluster where this will be installed
clusterLabelValue: "meta-monitoring"
# Set to true to write logs, metrics or traces to Grafana Cloud
# The secrets have to be created first
cloud:
logs:
enabled: true
secret: "logs"
metrics:
enabled: true
secret: "metrics"
traces:
enabled: true
secret: "traces"
clusterName: "meta-monitoring"
# Set to true for a local version of logs, metrics or traces
local:
grafana:
enabled: false
logs:
enabled: true
metrics:
enabled: true
traces:
enabled: true
minio:
enabled: true # This should be set to true if any of the previous is enabled
# Set to true to write logs, metrics or traces to Grafana Cloud
cloud:
logs:
enabled: false
endpoint:
username:
password:
metrics:
enabled: false
endpoint:
username:
password:
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
endpoint:
username:
password:
# 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
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_deployment_created
- kube_persistentvolumeclaim_labels
- kube_pod_container_info
- 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_index_request_duration_seconds_count
- 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:
@@ -204,15 +72,6 @@ kubeStateMetrics:
loki:
loki:
auth_enabled: false
schemaConfig:
configs:
- from: 2024-03-29
store: tsdb
object_store: s3
schema: v13
index:
prefix: index_
period: 24h
storage:
type: "s3"
s3:
@@ -230,13 +89,8 @@ loki:
secret_access_key: "{{ .Values.global.minio.rootPassword }}"
compactor:
retention_enabled: true
delete_request_store: s3
limits_config:
retention_period: 30d
lokiCanary:
enabled: false
test:
enabled: false
retention_period: 24h
monitoring:
dashboards:
enabled: false
@@ -253,37 +107,12 @@ loki:
test:
enabled: false
alloy:
alloy:
clustering:
enabled: true
grafana-agent:
agent:
configMap:
create: false
name: "agent-configmap"
key: 'config.river'
resources:
requests:
cpu: '1000m'
memory: '600Mi'
limits:
memory: '4Gi'
extraPorts:
- name: "otel"
port: 4317
targetPort: 4317
protocol: "TCP"
- name: "thrifthttp"
port: 14268
targetPort: 14268
protocol: "TCP"
controller:
type: "statefulset"
autoscaling:
enabled: true
minReplicas: 3
maxReplicas: 30
targetMemoryUtilizationPercentage: 90
targetCPUUtilizationPercentage: 90
mimir-distributed:
minio:
@@ -313,7 +142,7 @@ mimir-distributed:
secret_access_key: "{{ .Values.global.minio.rootPassword }}"
insecure: true
limits:
compactor_blocks_retention_period: 30d
compactor_blocks_retention_period: 24h
tempo-distributed:
tempo:
@@ -329,7 +158,7 @@ tempo-distributed:
insecure: true
compactor:
compaction:
block_retention: 30d
block_retention: 24h
traces:
otlp:
http:

View File

@@ -1,10 +0,0 @@
# Create a new release
1. Update the version field in charts/meta-monitoring/Chart.yaml in a new PR. Merge this PR if approved.
2. On the [Actions tab](https://github.com/grafana/meta-monitoring-chart/actions):
- Select `Release Helm chart` in the workflows on the left
- Click the `Run workflow` button
- Leave the `main` branch as is
- Click the green `Run workflow` button

View File

@@ -1,185 +1,27 @@
# Install this chart
## Preparation for Cloud mode (preferred)
1. Use an existing Grafana Cloud account or setup a new one. Then create an access token:
1. In Grafana go to Administration -> Users and Access -> Cloud access policies.
1. Click `Create access policy`.
1. Fill in the `Display name` field and check the `Write` check box for metrics, logs and traces. Then click `Create`.
1. On the newly created access policy click `Add token`.
1. Fill in the `Token name` field and click `Create`. Make a copy of the token as it will be used later on.
1. Create the meta namespace
```
kubectl create namespace meta
```
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=<token>
--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=<token>
--from-literal=endpoint='https://prometheus-us-central1.grafana.net/api/prom/push'
kubectl create secret generic traces -n meta \
--from-literal=username=<OTLP instance ID> \
--from-literal=password=<token>
--from-literal=endpoint='https://otlp-gateway-prod-us-east-0.grafana.net/otlp'
```
The logs, metrics and traces usernames are the `User / Username / Instance IDs` of the Loki, Prometheus/Mimir and OpenTelemetry instances in Grafana Cloud. From `Home` in Grafana click on `Stacks`. Then go to the `Details` pages of Loki and Prometheus/Mimir. For OpenTelemetry go to the `Configure` page.
1. Create a values.yaml file based on the [default one](../charts/meta-monitoring/values.yaml). Fill in the names of the secrets created above as needed. An example minimal values.yaml looks like this:
```
namespacesToMonitor:
- loki
cloud:
logs:
enabled: true
secret: "logs"
metrics:
enabled: true
secret: "metrics"
traces:
enabled: true
secret: "traces"
```
## Preparation for Local mode
1. Create the meta namespace
```
kubectl create namespace meta
```
1. Create a values.yaml file based on the [default one](../charts/meta-monitoring/values.yaml). An example minimal values.yaml looks like this:
```
namespacesToMonitor:
- loki
cloud:
logs:
enabled: false
metrics:
enabled: false
traces:
enabled: false
local:
grafana:
enabled:true
logs:
enabled: true
metrics:
enabled: true
traces:
enabled: true
minio:
enabled: true
```
## Installing the chart
1. Add the repo
```
helm repo add grafana https://grafana.github.io/helm-charts
```
1. Fetch the latest charts from the grafana repo
```
helm repo update grafana
```
1. Create a values.yaml file based on the [default one](../charts/meta-monitoring/values.yaml).
1. Install this helm chart
```
helm install -n meta -f values.yaml meta grafana/meta-monitoring
helm install -n meta -f values.yaml meta ./charts/meta-monitoring
```
1. Upgrade
```
helm upgrade --install -f values.yaml -n meta meta grafana/meta-monitoring
helm upgrade --install -f values.yaml -n meta meta ./charts/meta-monitoring
```
1. Delete this chart:
```
helm delete -n meta meta
```
## Installing the dashboards and rules on Grafana Cloud
## Installing the dashboards on Grafana Cloud
Only the files for the application monitored have to be copied. When monitoring Loki import dashboard files starting with 'loki-'.
For each of the dashboard files in charts/meta-monitoring/src/dashboards folder do the following:
1. Click on 'Dashboards' in Grafana
1. Click on the 'New` button and select 'Import'
1. Drop the dashboard file to the 'Upload dashboard JSON file' drop area
1. Click 'Import'
## Installing the rules on Grafana Cloud
1. Select the rules files in charts/meta-monitoring/src/rules for the application to monitor. When monitoring Loki use loki-rules.yaml.
1. Install mimirtool as per the [instructions](https://grafana.com/docs/mimir/latest/manage/tools/mimirtool/)
1. Create an access policy with Read and Write permission for Rules. Also create a token and record the token.
1. Get your cloud Prometheus endpoint and Instance ID from the `Prometheus` page in `Stacks`.
1. Use them to load the rules using mimirtool as follows:
```
mimirtool rules load --address=<your_cloud_prometheus_endpoint> --id=<your_instance_id> --key=<your_cloud_access_policy_token> *.yaml
```
1. To check the rules you have uploaded run:
```
mimirtool rules print --address=<your_cloud_prometheus_endpoint> --id=<your_instance_id> --key=<your_cloud_access_policy_token>
```
## Configure Loki to send traces
1. In the Loki config enable tracing:
```
loki:
tracing:
enabled: true
```
1. Add the following environment variables to your Loki binaries. When using the Loki Helm chart these can be added using the `extraEnv` setting for the Loki components.
1. JAEGER_ENDPOINT: http address of the mmc-alloy service installed by the meta-monitoring chart, for example "http://mmc-alloy:14268/api/traces"
1. JAEGER_AGENT_TAGS: extra tags you would like to add to the spans, for example 'cluster="abc",namespace="def"'
1. JAEGER_SAMPLER_TYPE: the sampling strategy, for example to sample all use 'const' with a value of 1 for the next environment variable
1. JAEGER_SAMPLER_PARAM: 1
1. If Loki is installed in a different namespace you can create an [ExternalName service](https://kubernetes.io/docs/concepts/services-networking/service/#externalname) in Kubernetes to point to the mmc-alloy service in the meta monitoring namespace
```

View File

@@ -1,20 +0,0 @@
#!/usr/bin/env bash
clean_up() {
test -d "$tmp_dir" && rm -fr "$tmp_dir"
}
here=${PWD}
tmp_dir=$( mktemp -d -t my-script )
cd $tmp_dir
echo "Cloning Loki"
git clone --filter=blob:none --no-checkout "https://github.com/grafana/loki"
cd loki
git sparse-checkout init --cone
git checkout main
git sparse-checkout set production/loki-mixin
echo "Copying production/loki-mixin to ${here}"
cp -r production ${here}

View File

@@ -1,18 +0,0 @@
(import 'dashboards.libsonnet') +
(import 'alerts.libsonnet') +
(import 'recording_rules.libsonnet') + {
grafanaDashboardFolder: 'Loki Meta Monitoring',
_config+:: {
internal_components: false,
// The Meta Monitoring helm chart uses Grafana Alloy instead of promtail
promtail+: {
enabled: false,
},
meta_monitoring+: {
enabled: true,
},
},
}

View File

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