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
51 changed files with 4082 additions and 4376 deletions

View File

@@ -1,30 +0,0 @@
ame: 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

@@ -1,53 +0,0 @@
---
name: Check for dependency updates
on:
workflow_dispatch:
schedule:
# Run once a day
- cron: '0 0 * * *'
permissions:
contents: "write"
pull-requests: "write"
env:
UPDATECLI_CONFIG_DIR: "${{ github.workspace }}/.github/configs/updatecli.d"
UPDATECLI_GITHUB_TOKEN: "${{ secrets.GITHUB_TOKEN }}"
jobs:
updateGrafanaAlloy:
name: Update Grafana Alloy
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 ${UPDATECLI_CONFIG_DIR}/grafana-alloy.yaml
if ! git diff --exit-code > /dev/null; then
echo "changed=true" >> "${GITHUB_OUTPUT}"
fi
- name: Install Helm
if: steps.update-grafana-alloy.outputs.changed == 'true'
uses: azure/setup-helm@v3
- name: Create pull request
if: steps.update-grafana-alloy.outputs.changed == 'true'
uses: peter-evans/create-pull-request@v5
with:
title: "[dependency] Update Grafana Alloy"
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

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

@@ -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

@@ -1,18 +1,18 @@
dependencies:
- name: loki
repository: https://grafana.github.io/helm-charts
version: 5.47.2
- 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: 5.2.0
version: 4.4.1
- name: tempo-distributed
repository: https://grafana.github.io/helm-charts
version: 1.9.1
version: 1.4.7
- name: minio
repository: https://charts.min.io
version: 5.0.11
digest: sha256:14d19ff9b9d96f535a3f32b8d1f7050143209a004720c98903bc94d03af5cee0
generated: "2024-04-15T10:10:57.690716+01:00"
digest: sha256:da0e744b5046eb7972e0bf82d1d0ba4786e9600af63b65f35b16118105248074
generated: "2023-08-16T16:08:36.406791+01:00"

View File

@@ -26,18 +26,18 @@ appVersion: "0.0.1"
dependencies:
- name: loki
repository: https://grafana.github.io/helm-charts
version: "5.47.2"
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: "5.2.0"
version: "4.4.1"
condition: local.metrics.enabled
- name: tempo-distributed
repository: https://grafana.github.io/helm-charts
version: "1.9.1"
version: "1.4.7"
condition: local.traces.enabled
- name: minio
repository: https://charts.min.io

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.

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=~\"$cluster\",job=~\"$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,
@@ -648,7 +882,7 @@
"value": "default"
},
"hide": 0,
"label": "Data source",
"label": "Data Source",
"name": "datasource",
"options": [ ],
"query": "prometheus",

View File

@@ -77,7 +77,7 @@
"sort": 0,
"value_type": "individual"
},
"type": "timeseries",
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
@@ -164,7 +164,7 @@
"sort": 0,
"value_type": "individual"
},
"type": "timeseries",
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
@@ -250,7 +250,7 @@
"sort": 0,
"value_type": "individual"
},
"type": "timeseries",
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
@@ -336,7 +336,7 @@
"sort": 0,
"value_type": "individual"
},
"type": "timeseries",
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
@@ -422,7 +422,7 @@
"sort": 0,
"value_type": "individual"
},
"type": "timeseries",
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
@@ -508,7 +508,7 @@
"sort": 0,
"value_type": "individual"
},
"type": "timeseries",
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
@@ -595,7 +595,7 @@
"sort": 0,
"value_type": "individual"
},
"type": "timeseries",
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
@@ -682,7 +682,7 @@
"sort": 0,
"value_type": "individual"
},
"type": "timeseries",
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
@@ -718,7 +718,7 @@
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$loki_datasource",
"datasource": "$logs",
"fill": 1,
"fillGradient": 0,
"gridPos": {
@@ -787,7 +787,7 @@
"sort": 2,
"value_type": "individual"
},
"type": "timeseries",
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
@@ -819,7 +819,7 @@
}
},
{
"datasource": "$loki_datasource",
"datasource": "$logs",
"gridPos": {
"h": 19,
"w": 24,
@@ -861,7 +861,7 @@
"value": "default"
},
"hide": 0,
"label": "Data source",
"label": "Data Source",
"name": "datasource",
"options": [ ],
"query": "prometheus",
@@ -918,7 +918,7 @@
{
"hide": 0,
"label": null,
"name": "loki_datasource",
"name": "logs",
"options": [ ],
"query": "loki",
"refresh": 1,
@@ -1069,4 +1069,4 @@
"title": "Loki / Logs",
"uid": "logs",
"version": 0
}
}

View File

@@ -600,7 +600,7 @@
"value": "default"
},
"hide": 0,
"label": "Data source",
"label": "Data Source",
"name": "datasource",
"options": [ ],
"query": "prometheus",

View File

@@ -102,7 +102,7 @@
"sort": 0,
"value_type": "individual"
},
"type": "timeseries",
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
@@ -198,7 +198,7 @@
"sort": 0,
"value_type": "individual"
},
"type": "timeseries",
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
@@ -293,7 +293,7 @@
"sort": 0,
"value_type": "individual"
},
"type": "timeseries",
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
@@ -389,7 +389,7 @@
"sort": 0,
"value_type": "individual"
},
"type": "timeseries",
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
@@ -485,7 +485,7 @@
"sort": 2,
"value_type": "individual"
},
"type": "timeseries",
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
@@ -591,7 +591,7 @@
"sort": 0,
"value_type": "individual"
},
"type": "timeseries",
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
@@ -697,7 +697,7 @@
"sort": 0,
"value_type": "individual"
},
"type": "timeseries",
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
@@ -794,7 +794,7 @@
"sort": 0,
"value_type": "individual"
},
"type": "timeseries",
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
@@ -903,7 +903,7 @@
"sort": 0,
"value_type": "individual"
},
"type": "timeseries",
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
@@ -1000,7 +1000,7 @@
"sort": 0,
"value_type": "individual"
},
"type": "timeseries",
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
@@ -1109,7 +1109,7 @@
"sort": 0,
"value_type": "individual"
},
"type": "timeseries",
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
@@ -1215,7 +1215,7 @@
"sort": 0,
"value_type": "individual"
},
"type": "timeseries",
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
@@ -1312,7 +1312,7 @@
"sort": 0,
"value_type": "individual"
},
"type": "timeseries",
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
@@ -1420,7 +1420,7 @@
"sort": 0,
"value_type": "individual"
},
"type": "timeseries",
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
@@ -1517,7 +1517,7 @@
"sort": 0,
"value_type": "individual"
},
"type": "timeseries",
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
@@ -1618,7 +1618,7 @@
"sort": 0,
"value_type": "individual"
},
"type": "timeseries",
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
@@ -1799,9 +1799,9 @@
"steppedLine": false,
"targets": [
{
"expr": "sum by(pod) (rate(container_cpu_usage_seconds_total{cluster=~\"$cluster\", namespace=~\"$namespace\", pod=~\"(loki|enterprise-logs)-write.*\"}[$__rate_interval]))",
"expr": "node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"(loki|enterprise-logs)-write.*\"}",
"intervalFactor": 3,
"legendFormat": "{{pod}}",
"legendFormat": "{{pod}}-{{container}}",
"refId": "A"
}
],
@@ -1815,7 +1815,7 @@
"sort": 2,
"value_type": "individual"
},
"type": "timeseries",
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
@@ -1907,7 +1907,7 @@
"sort": 2,
"value_type": "individual"
},
"type": "timeseries",
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
@@ -1943,7 +1943,7 @@
"bars": true,
"dashLength": 10,
"dashes": false,
"datasource": "$loki_datasource",
"datasource": "$logs",
"fill": 1,
"fillGradient": 0,
"gridPos": {
@@ -1999,7 +1999,7 @@
"sort": 2,
"value_type": "individual"
},
"type": "timeseries",
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
@@ -2031,7 +2031,7 @@
}
},
{
"datasource": "$loki_datasource",
"datasource": "$logs",
"gridPos": {
"h": 18,
"w": 12,
@@ -2116,7 +2116,7 @@
"sort": 2,
"value_type": "individual"
},
"type": "timeseries",
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
@@ -2205,7 +2205,7 @@
"sort": 2,
"value_type": "individual"
},
"type": "timeseries",
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
@@ -2294,7 +2294,7 @@
"sort": 2,
"value_type": "individual"
},
"type": "timeseries",
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
@@ -2383,7 +2383,7 @@
"sort": 2,
"value_type": "individual"
},
"type": "timeseries",
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
@@ -2490,7 +2490,7 @@
"sort": 0,
"value_type": "individual"
},
"type": "timeseries",
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
@@ -2581,7 +2581,7 @@
"sort": 0,
"value_type": "individual"
},
"type": "timeseries",
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
@@ -2697,7 +2697,7 @@
"sort": 0,
"value_type": "individual"
},
"type": "timeseries",
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
@@ -2850,7 +2850,7 @@
"sort": 0,
"value_type": "individual"
},
"type": "timeseries",
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
@@ -3006,9 +3006,9 @@
"steppedLine": false,
"targets": [
{
"expr": "sum by(pod) (rate(container_cpu_usage_seconds_total{cluster=~\"$cluster\", namespace=~\"$namespace\", pod=~\"(loki|enterprise-logs)-read.*\"}[$__rate_interval]))",
"expr": "node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"(loki|enterprise-logs)-read.*\"}",
"intervalFactor": 3,
"legendFormat": "{{pod}}",
"legendFormat": "{{pod}}-{{container}}",
"refId": "A"
}
],
@@ -3022,7 +3022,7 @@
"sort": 2,
"value_type": "individual"
},
"type": "timeseries",
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
@@ -3114,7 +3114,7 @@
"sort": 2,
"value_type": "individual"
},
"type": "timeseries",
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
@@ -3150,7 +3150,7 @@
"bars": true,
"dashLength": 10,
"dashes": false,
"datasource": "$loki_datasource",
"datasource": "$logs",
"fill": 1,
"fillGradient": 0,
"gridPos": {
@@ -3206,7 +3206,7 @@
"sort": 2,
"value_type": "individual"
},
"type": "timeseries",
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
@@ -3238,7 +3238,7 @@
}
},
{
"datasource": "$loki_datasource",
"datasource": "$logs",
"gridPos": {
"h": 18,
"w": 18,
@@ -3323,7 +3323,7 @@
"sort": 2,
"value_type": "individual"
},
"type": "timeseries",
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
@@ -3443,7 +3443,7 @@
"sort": 2,
"value_type": "individual"
},
"type": "timeseries",
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
@@ -3535,7 +3535,7 @@
"sort": 2,
"value_type": "individual"
},
"type": "timeseries",
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
@@ -3655,7 +3655,7 @@
"sort": 2,
"value_type": "individual"
},
"type": "timeseries",
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
@@ -3747,7 +3747,7 @@
"sort": 2,
"value_type": "individual"
},
"type": "timeseries",
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
@@ -3861,7 +3861,7 @@
"sort": 2,
"value_type": "individual"
},
"type": "timeseries",
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
@@ -3964,7 +3964,7 @@
"sort": 2,
"value_type": "individual"
},
"type": "timeseries",
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
@@ -4067,7 +4067,7 @@
"sort": 2,
"value_type": "individual"
},
"type": "timeseries",
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
@@ -4165,7 +4165,7 @@
"sort": 2,
"value_type": "individual"
},
"type": "timeseries",
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
@@ -4255,7 +4255,7 @@
"sort": 2,
"value_type": "individual"
},
"type": "timeseries",
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
@@ -4345,7 +4345,7 @@
"sort": 2,
"value_type": "individual"
},
"type": "timeseries",
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
@@ -4435,7 +4435,7 @@
"sort": 2,
"value_type": "individual"
},
"type": "timeseries",
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
@@ -4525,7 +4525,7 @@
"sort": 2,
"value_type": "individual"
},
"type": "timeseries",
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
@@ -4645,7 +4645,7 @@
"sort": 2,
"value_type": "individual"
},
"type": "timeseries",
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
@@ -4737,7 +4737,7 @@
"sort": 2,
"value_type": "individual"
},
"type": "timeseries",
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
@@ -4825,7 +4825,7 @@
"steppedLine": false,
"targets": [
{
"expr": "sum(rate(loki_dynamo_failures_total{cluster=\"$cluster\", namespace=\"$namespace\"}[5m]))",
"expr": "sum(rate(cortex_dynamo_failures_total{cluster=\"$cluster\", namespace=\"$namespace\"}[5m]))",
"refId": "A"
}
],
@@ -4839,7 +4839,7 @@
"sort": 0,
"value_type": "individual"
},
"type": "timeseries",
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
@@ -4911,7 +4911,7 @@
"steppedLine": false,
"targets": [
{
"expr": "sum(rate(loki_dynamo_consumed_capacity_total{cluster=\"$cluster\", namespace=\"$namespace\"}[5m]))",
"expr": "sum(rate(cortex_dynamo_consumed_capacity_total{cluster=\"$cluster\", namespace=\"$namespace\"}[5m]))",
"refId": "A"
}
],
@@ -4925,7 +4925,7 @@
"sort": 0,
"value_type": "individual"
},
"type": "timeseries",
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
@@ -4997,7 +4997,7 @@
"steppedLine": false,
"targets": [
{
"expr": "sum(rate(loki_dynamo_throttled_total{cluster=\"$cluster\", namespace=\"$namespace\"}[5m]))",
"expr": "sum(rate(cortex_dynamo_throttled_total{cluster=\"$cluster\", namespace=\"$namespace\"}[5m]))",
"refId": "A"
}
],
@@ -5011,7 +5011,7 @@
"sort": 0,
"value_type": "individual"
},
"type": "timeseries",
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
@@ -5083,7 +5083,7 @@
"steppedLine": false,
"targets": [
{
"expr": "sum(rate(loki_dynamo_dropped_requests_total{cluster=\"$cluster\", namespace=\"$namespace\"}[5m]))",
"expr": "sum(rate(cortex_dynamo_dropped_requests_total{cluster=\"$cluster\", namespace=\"$namespace\"}[5m]))",
"refId": "A"
}
],
@@ -5097,7 +5097,7 @@
"sort": 0,
"value_type": "individual"
},
"type": "timeseries",
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
@@ -5169,17 +5169,17 @@
"steppedLine": false,
"targets": [
{
"expr": "histogram_quantile(.99, sum(rate(loki_dynamo_query_pages_count{cluster=\"$cluster\", namespace=\"$namespace\"}[5m])))",
"expr": "histogram_quantile(.99, sum(rate(cortex_dynamo_query_pages_count{cluster=\"$cluster\", namespace=\"$namespace\"}[5m])))",
"legendFormat": ".99",
"refId": "A"
},
{
"expr": "histogram_quantile(.9, sum(rate(loki_dynamo_query_pages_count{cluster=\"$cluster\", namespace=\"$namespace\"}[5m])))",
"expr": "histogram_quantile(.9, sum(rate(cortex_dynamo_query_pages_count{cluster=\"$cluster\", namespace=\"$namespace\"}[5m])))",
"legendFormat": ".9",
"refId": "B"
},
{
"expr": "histogram_quantile(.5, sum(rate(loki_dynamo_query_pages_count{cluster=\"$cluster\", namespace=\"$namespace\"}[5m])))",
"expr": "histogram_quantile(.5, sum(rate(cortex_dynamo_query_pages_count{cluster=\"$cluster\", namespace=\"$namespace\"}[5m])))",
"legendFormat": ".5",
"refId": "C"
}
@@ -5194,7 +5194,7 @@
"sort": 0,
"value_type": "individual"
},
"type": "timeseries",
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
@@ -5269,19 +5269,19 @@
"steppedLine": false,
"targets": [
{
"expr": "histogram_quantile(.99, sum(rate(loki_dynamo_request_duration_seconds_bucket{cluster=\"$cluster\", namespace=\"$namespace\"}[5m])) by (operation, le))",
"expr": "histogram_quantile(.99, sum(rate(cortex_dynamo_request_duration_seconds_bucket{cluster=\"$cluster\", namespace=\"$namespace\"}[5m])) by (operation, le))",
"intervalFactor": 1,
"legendFormat": ".99-{{operation}}",
"refId": "A"
},
{
"expr": "histogram_quantile(.9, sum(rate(loki_dynamo_request_duration_seconds_bucket{cluster=\"$cluster\", namespace=\"$namespace\"}[5m])) by (operation, le))",
"expr": "histogram_quantile(.9, sum(rate(cortex_dynamo_request_duration_seconds_bucket{cluster=\"$cluster\", namespace=\"$namespace\"}[5m])) by (operation, le))",
"hide": false,
"legendFormat": ".9-{{operation}}",
"refId": "B"
},
{
"expr": "histogram_quantile(.5, sum(rate(loki_dynamo_request_duration_seconds_bucket{cluster=\"$cluster\", namespace=\"$namespace\"}[5m])) by (operation, le))",
"expr": "histogram_quantile(.5, sum(rate(cortex_dynamo_request_duration_seconds_bucket{cluster=\"$cluster\", namespace=\"$namespace\"}[5m])) by (operation, le))",
"hide": false,
"legendFormat": ".5-{{operation}}",
"refId": "C"
@@ -5297,7 +5297,7 @@
"sort": 2,
"value_type": "individual"
},
"type": "timeseries",
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
@@ -5372,7 +5372,7 @@
"steppedLine": false,
"targets": [
{
"expr": "sum(rate(loki_dynamo_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\"}[5m])) by (status_code, operation)",
"expr": "sum(rate(cortex_dynamo_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\"}[5m])) by (status_code, operation)",
"intervalFactor": 1,
"legendFormat": "{{status_code}}-{{operation}}",
"refId": "A"
@@ -5388,7 +5388,7 @@
"sort": 2,
"value_type": "individual"
},
"type": "timeseries",
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
@@ -5507,7 +5507,7 @@
"sort": 2,
"value_type": "individual"
},
"type": "timeseries",
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
@@ -5598,7 +5598,7 @@
"sort": 2,
"value_type": "individual"
},
"type": "timeseries",
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
@@ -5717,7 +5717,7 @@
"sort": 2,
"value_type": "individual"
},
"type": "timeseries",
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
@@ -5808,7 +5808,7 @@
"sort": 2,
"value_type": "individual"
},
"type": "timeseries",
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
@@ -5927,7 +5927,7 @@
"sort": 2,
"value_type": "individual"
},
"type": "timeseries",
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
@@ -6018,7 +6018,7 @@
"sort": 2,
"value_type": "individual"
},
"type": "timeseries",
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
@@ -6070,7 +6070,7 @@
"value": "default"
},
"hide": 0,
"label": "Data source",
"label": "Data Source",
"name": "datasource",
"options": [ ],
"query": "prometheus",
@@ -6081,7 +6081,7 @@
{
"hide": 0,
"label": null,
"name": "loki_datasource",
"name": "logs",
"options": [ ],
"query": "loki",
"refresh": 1,
@@ -6169,4 +6169,4 @@
"title": "Loki / Operational",
"uid": "operational",
"version": 0
}
}

File diff suppressed because it is too large Load Diff

View File

@@ -33,234 +33,113 @@
"3xx": "#6ED0E0",
"4xx": "#EF843C",
"5xx": "#E24D42",
"OK": "#7EB26D",
"cancel": "#A9A9A9",
"error": "#E24D42",
"success": "#7EB26D"
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fieldConfig": {
"defaults": {
"custom": {
"drawStyle": "line",
"fillOpacity": 100,
"lineWidth": 0,
"pointSize": 5,
"showPoints": "never",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "normal"
}
},
"min": 0,
"thresholds": {
"mode": "absolute",
"steps": [ ]
},
"unit": "short"
},
"overrides": [
{
"matcher": {
"id": "byName",
"options": "1xx"
},
"properties": [
{
"id": "color",
"value": {
"fixedColor": "#EAB839",
"mode": "fixed"
}
}
]
},
{
"matcher": {
"id": "byName",
"options": "2xx"
},
"properties": [
{
"id": "color",
"value": {
"fixedColor": "#7EB26D",
"mode": "fixed"
}
}
]
},
{
"matcher": {
"id": "byName",
"options": "3xx"
},
"properties": [
{
"id": "color",
"value": {
"fixedColor": "#6ED0E0",
"mode": "fixed"
}
}
]
},
{
"matcher": {
"id": "byName",
"options": "4xx"
},
"properties": [
{
"id": "color",
"value": {
"fixedColor": "#EF843C",
"mode": "fixed"
}
}
]
},
{
"matcher": {
"id": "byName",
"options": "5xx"
},
"properties": [
{
"id": "color",
"value": {
"fixedColor": "#E24D42",
"mode": "fixed"
}
}
]
},
{
"matcher": {
"id": "byName",
"options": "OK"
},
"properties": [
{
"id": "color",
"value": {
"fixedColor": "#7EB26D",
"mode": "fixed"
}
}
]
},
{
"matcher": {
"id": "byName",
"options": "cancel"
},
"properties": [
{
"id": "color",
"value": {
"fixedColor": "#A9A9A9",
"mode": "fixed"
}
}
]
},
{
"matcher": {
"id": "byName",
"options": "error"
},
"properties": [
{
"id": "color",
"value": {
"fixedColor": "#E24D42",
"mode": "fixed"
}
}
]
},
{
"matcher": {
"id": "byName",
"options": "success"
},
"properties": [
{
"id": "color",
"value": {
"fixedColor": "#7EB26D",
"mode": "fixed"
}
}
]
}
]
},
"fill": 10,
"id": 1,
"legend": {
"avg": false,
"current": false,
"max": false,
"min": false,
"show": true,
"total": false,
"values": false
},
"lines": true,
"linewidth": 0,
"links": [ ],
"options": {
"legend": {
"showLegend": true
},
"tooltip": {
"mode": "single",
"sort": "none"
}
},
"span": 4,
"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 (status) (\n label_replace(label_replace(rate(loki_request_duration_seconds_count{cluster=~\"$cluster\",job=~\"($namespace)/(loki|enterprise-logs)-read\", route=~\"loki_api_v1_series|api_prom_series|api_prom_query|api_prom_label|api_prom_label_name_values|loki_api_v1_query|loki_api_v1_query_range|loki_api_v1_labels|loki_api_v1_label_name_values\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-zA-Z]+)\"))\n",
"expr": "sum by (status) (\n label_replace(label_replace(rate(loki_request_duration_seconds_count{cluster=~\"$cluster\",job=~\"($namespace)/(loki|enterprise-logs)-read\", route=~\"loki_api_v1_series|api_prom_series|api_prom_query|api_prom_label|api_prom_label_name_values|loki_api_v1_query|loki_api_v1_query_range|loki_api_v1_labels|loki_api_v1_label_name_values\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-z]+)\"))\n",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{status}}",
"refId": "A"
"refId": "A",
"step": 10
}
],
"thresholds": [ ],
"timeFrom": null,
"timeShift": null,
"title": "QPS",
"type": "timeseries"
"tooltip": {
"shared": true,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [ ]
},
"yaxes": [
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
},
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": false
}
]
},
{
"aliasColors": { },
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$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": "ms"
},
"overrides": [ ]
},
"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",
"options": {
"legend": {
"showLegend": true
},
"tooltip": {
"mode": "single",
"sort": "none"
}
},
"span": 4,
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"seriesOverrides": [ ],
"spaceLength": 10,
"span": 6,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "histogram_quantile(0.99, sum by (le,route) (cluster_job_route:loki_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/(loki|enterprise-logs)-read\", route=~\"loki_api_v1_series|api_prom_series|api_prom_query|api_prom_label|api_prom_label_name_values|loki_api_v1_query|loki_api_v1_query_range|loki_api_v1_labels|loki_api_v1_label_name_values\"})) * 1e3",
@@ -287,8 +166,23 @@
"step": 10
}
],
"thresholds": [ ],
"timeFrom": null,
"timeShift": null,
"title": "Latency",
"type": "timeseries",
"tooltip": {
"shared": true,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [ ]
},
"yaxes": [
{
"format": "ms",
@@ -307,57 +201,6 @@
"show": false
}
]
},
{
"datasource": "$datasource",
"fieldConfig": {
"defaults": {
"custom": {
"drawStyle": "line",
"fillOpacity": 10,
"lineWidth": 1,
"pointSize": 5,
"showPoints": "never",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
}
},
"thresholds": {
"mode": "absolute",
"steps": [ ]
},
"unit": "ms"
},
"overrides": [ ]
},
"id": 3,
"links": [ ],
"nullPointMode": "null as zero",
"options": {
"legend": {
"showLegend": true
},
"tooltip": {
"mode": "single",
"sort": "none"
}
},
"span": 4,
"targets": [
{
"expr": "histogram_quantile(0.99, sum(rate(loki_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/(loki|enterprise-logs)-read\", route=~\"loki_api_v1_series|api_prom_series|api_prom_query|api_prom_label|api_prom_label_name_values|loki_api_v1_query|loki_api_v1_query_range|loki_api_v1_labels|loki_api_v1_label_name_values\"}[$__rate_interval])) by (le,pod)) * 1e3",
"format": "time_series",
"interval": "1m",
"intervalFactor": 2,
"legendFormat": "__auto",
"refId": "A",
"step": 10
}
],
"title": "Per Pod Latency (p99)",
"type": "timeseries"
}
],
"repeat": null,
@@ -378,256 +221,156 @@
"3xx": "#6ED0E0",
"4xx": "#EF843C",
"5xx": "#E24D42",
"OK": "#7EB26D",
"cancel": "#A9A9A9",
"error": "#E24D42",
"success": "#7EB26D"
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fieldConfig": {
"defaults": {
"custom": {
"drawStyle": "line",
"fillOpacity": 100,
"lineWidth": 0,
"pointSize": 5,
"showPoints": "never",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "normal"
}
},
"min": 0,
"thresholds": {
"mode": "absolute",
"steps": [ ]
},
"unit": "short"
},
"overrides": [
{
"matcher": {
"id": "byName",
"options": "1xx"
},
"properties": [
{
"id": "color",
"value": {
"fixedColor": "#EAB839",
"mode": "fixed"
}
}
]
},
{
"matcher": {
"id": "byName",
"options": "2xx"
},
"properties": [
{
"id": "color",
"value": {
"fixedColor": "#7EB26D",
"mode": "fixed"
}
}
]
},
{
"matcher": {
"id": "byName",
"options": "3xx"
},
"properties": [
{
"id": "color",
"value": {
"fixedColor": "#6ED0E0",
"mode": "fixed"
}
}
]
},
{
"matcher": {
"id": "byName",
"options": "4xx"
},
"properties": [
{
"id": "color",
"value": {
"fixedColor": "#EF843C",
"mode": "fixed"
}
}
]
},
{
"matcher": {
"id": "byName",
"options": "5xx"
},
"properties": [
{
"id": "color",
"value": {
"fixedColor": "#E24D42",
"mode": "fixed"
}
}
]
},
{
"matcher": {
"id": "byName",
"options": "OK"
},
"properties": [
{
"id": "color",
"value": {
"fixedColor": "#7EB26D",
"mode": "fixed"
}
}
]
},
{
"matcher": {
"id": "byName",
"options": "cancel"
},
"properties": [
{
"id": "color",
"value": {
"fixedColor": "#A9A9A9",
"mode": "fixed"
}
}
]
},
{
"matcher": {
"id": "byName",
"options": "error"
},
"properties": [
{
"id": "color",
"value": {
"fixedColor": "#E24D42",
"mode": "fixed"
}
}
]
},
{
"matcher": {
"id": "byName",
"options": "success"
},
"properties": [
{
"id": "color",
"value": {
"fixedColor": "#7EB26D",
"mode": "fixed"
}
}
]
}
]
},
"fill": 10,
"id": 4,
"id": 3,
"legend": {
"avg": false,
"current": false,
"max": false,
"min": false,
"show": true,
"total": false,
"values": false
},
"lines": true,
"linewidth": 0,
"links": [ ],
"options": {
"legend": {
"showLegend": true
},
"tooltip": {
"mode": "single",
"sort": "none"
}
},
"span": 4,
"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 (status) (\n label_replace(label_replace(rate(loki_boltdb_shipper_request_duration_seconds_count{cluster=~\"$cluster\",job=~\"($namespace)/(loki|enterprise-logs)-read\", operation=\"Shipper.Query\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-zA-Z]+)\"))\n",
"expr": "sum by (status) (\n label_replace(label_replace(rate(loki_boltdb_shipper_request_duration_seconds_count{cluster=~\"$cluster\",job=~\"($namespace)/(loki|enterprise-logs)-read\", operation=\"Shipper.Query\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-z]+)\"))\n",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{status}}",
"refId": "A"
"refId": "A",
"step": 10
}
],
"thresholds": [ ],
"timeFrom": null,
"timeShift": null,
"title": "QPS",
"type": "timeseries"
"tooltip": {
"shared": true,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [ ]
},
"yaxes": [
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
},
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": false
}
]
},
{
"aliasColors": { },
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$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": "ms"
},
"overrides": [ ]
"fill": 1,
"id": 4,
"legend": {
"avg": false,
"current": false,
"max": false,
"min": false,
"show": true,
"total": false,
"values": false
},
"id": 5,
"lines": true,
"linewidth": 1,
"links": [ ],
"nullPointMode": "null as zero",
"options": {
"legend": {
"showLegend": true
},
"tooltip": {
"mode": "single",
"sort": "none"
}
},
"span": 4,
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"seriesOverrides": [ ],
"spaceLength": 10,
"span": 6,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "histogram_quantile(0.99, sum(rate(loki_boltdb_shipper_request_duration_seconds_bucket{cluster=~\"$cluster\",job=~\"($namespace)/(loki|enterprise-logs)-read\", operation=\"Shipper.Query\"}[$__rate_interval])) by (le)) * 1e3",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "99th Percentile",
"refId": "A"
"refId": "A",
"step": 10
},
{
"expr": "histogram_quantile(0.50, sum(rate(loki_boltdb_shipper_request_duration_seconds_bucket{cluster=~\"$cluster\",job=~\"($namespace)/(loki|enterprise-logs)-read\", operation=\"Shipper.Query\"}[$__rate_interval])) by (le)) * 1e3",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "50th Percentile",
"refId": "B"
"refId": "B",
"step": 10
},
{
"expr": "sum(rate(loki_boltdb_shipper_request_duration_seconds_sum{cluster=~\"$cluster\",job=~\"($namespace)/(loki|enterprise-logs)-read\", operation=\"Shipper.Query\"}[$__rate_interval])) * 1e3 / sum(rate(loki_boltdb_shipper_request_duration_seconds_count{cluster=~\"$cluster\",job=~\"($namespace)/(loki|enterprise-logs)-read\", operation=\"Shipper.Query\"}[$__rate_interval]))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "Average",
"refId": "C"
"refId": "C",
"step": 10
}
],
"thresholds": [ ],
"timeFrom": null,
"timeShift": null,
"title": "Latency",
"type": "timeseries",
"tooltip": {
"shared": true,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [ ]
},
"yaxes": [
{
"format": "ms",
@@ -646,57 +389,6 @@
"show": false
}
]
},
{
"datasource": "$datasource",
"fieldConfig": {
"defaults": {
"custom": {
"drawStyle": "line",
"fillOpacity": 10,
"lineWidth": 1,
"pointSize": 5,
"showPoints": "never",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
}
},
"thresholds": {
"mode": "absolute",
"steps": [ ]
},
"unit": "ms"
},
"overrides": [ ]
},
"id": 6,
"links": [ ],
"nullPointMode": "null as zero",
"options": {
"legend": {
"showLegend": true
},
"tooltip": {
"mode": "single",
"sort": "none"
}
},
"span": 4,
"targets": [
{
"expr": "histogram_quantile(0.99, sum(rate(loki_boltdb_shipper_request_duration_seconds_bucket{cluster=~\"$cluster\",job=~\"($namespace)/(loki|enterprise-logs)-read\", operation=\"Shipper.Query\"}[$__rate_interval])) by (le,pod)) * 1e3",
"format": "time_series",
"interval": "1m",
"intervalFactor": 2,
"legendFormat": "__auto",
"refId": "A",
"step": 10
}
],
"title": "Per Pod Latency (p99)",
"type": "timeseries"
}
],
"repeat": null,
@@ -720,7 +412,7 @@
"value": "default"
},
"hide": 0,
"label": "Data source",
"label": "Data Source",
"name": "datasource",
"options": [ ],
"query": "prometheus",

File diff suppressed because it is too large Load Diff

View File

@@ -27,447 +27,589 @@
"collapsed": false,
"panels": [
{
"aliasColors": { },
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fieldConfig": {
"defaults": {
"custom": {
"drawStyle": "line",
"fillOpacity": 10,
"lineWidth": 1,
"pointSize": 5,
"showPoints": "never",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
}
},
"thresholds": {
"mode": "absolute",
"steps": [ ]
},
"unit": "short"
},
"overrides": [ ]
},
"fill": 1,
"gridPos": { },
"id": 1,
"links": [ ],
"options": {
"legend": {
"showLegend": true
},
"tooltip": {
"mode": "single",
"sort": "none"
}
"legend": {
"avg": false,
"current": false,
"max": false,
"min": false,
"show": true,
"total": false,
"values": false
},
"lines": true,
"linewidth": 1,
"links": [ ],
"nullPointMode": "null as zero",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"seriesOverrides": [ ],
"spaceLength": 10,
"span": 6,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "sum by(pod) (loki_ingester_memory_streams{cluster=~\"$cluster\", job=~\"($namespace)/(loki|enterprise-logs)-write\"})",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{pod}}",
"legendLink": null
"legendLink": null,
"step": 10
}
],
"thresholds": [ ],
"timeFrom": null,
"timeShift": null,
"title": "In-memory streams",
"tooltip": {
"sort": 2
},
"type": "timeseries"
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [ ]
},
"yaxes": [
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
},
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": false
}
]
},
{
"aliasColors": { },
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$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": [
{
"matcher": {
"id": "byName",
"options": "request"
},
"properties": [
{
"id": "color",
"value": {
"fixedColor": "#FFC000",
"mode": "fixed"
}
},
{
"id": "custom.fillOpacity",
"value": 0
}
]
},
{
"matcher": {
"id": "byName",
"options": "limit"
},
"properties": [
{
"id": "color",
"value": {
"fixedColor": "#E02F44",
"mode": "fixed"
}
},
{
"id": "custom.fillOpacity",
"value": 0
}
]
}
]
},
"fill": 1,
"gridPos": { },
"id": 2,
"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": [
{
"alias": "request",
"color": "#FFC000",
"fill": 0
},
{
"alias": "limit",
"color": "#E02F44",
"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=\"loki\", pod=~\"(loki|enterprise-logs)-write.*\"}[$__rate_interval]))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{pod}}",
"legendLink": null
"legendLink": null,
"step": 10
},
{
"expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\", container=\"loki\", pod=~\"(loki|enterprise-logs)-write.*\", resource=\"cpu\"} > 0)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "request",
"legendLink": null
"legendLink": null,
"step": 10
},
{
"expr": "min(container_spec_cpu_quota{cluster=~\"$cluster\", namespace=~\"$namespace\", container=\"loki\", pod=~\"(loki|enterprise-logs)-write.*\"} / container_spec_cpu_period{cluster=~\"$cluster\", namespace=~\"$namespace\", container=\"loki\", pod=~\"(loki|enterprise-logs)-write.*\"})",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "limit",
"legendLink": null
"legendLink": null,
"step": 10
}
],
"thresholds": [ ],
"timeFrom": null,
"timeShift": null,
"title": "CPU",
"tooltip": {
"sort": 2
},
"type": "timeseries"
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [ ]
},
"yaxes": [
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
},
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": false
}
]
},
{
"aliasColors": { },
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$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": "bytes"
},
"overrides": [
{
"matcher": {
"id": "byName",
"options": "request"
},
"properties": [
{
"id": "color",
"value": {
"fixedColor": "#FFC000",
"mode": "fixed"
}
},
{
"id": "custom.fillOpacity",
"value": 0
}
]
},
{
"matcher": {
"id": "byName",
"options": "limit"
},
"properties": [
{
"id": "color",
"value": {
"fixedColor": "#E02F44",
"mode": "fixed"
}
},
{
"id": "custom.fillOpacity",
"value": 0
}
]
}
]
},
"fill": 1,
"gridPos": { },
"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": [
{
"alias": "request",
"color": "#FFC000",
"fill": 0
},
{
"alias": "limit",
"color": "#E02F44",
"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=\"loki\", pod=~\"(loki|enterprise-logs)-write.*\"})",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{pod}}",
"legendLink": null
"legendLink": null,
"step": 10
},
{
"expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\", container=\"loki\", pod=~\"(loki|enterprise-logs)-write.*\", resource=\"memory\"} > 0)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "request",
"legendLink": null
"legendLink": null,
"step": 10
},
{
"expr": "min(container_spec_memory_limit_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\", container=\"loki\", pod=~\"(loki|enterprise-logs)-write.*\"} > 0)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "limit",
"legendLink": null
"legendLink": null,
"step": 10
}
],
"thresholds": [ ],
"timeFrom": null,
"timeShift": null,
"title": "Memory (workingset)",
"tooltip": {
"sort": 2
},
"type": "timeseries"
"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": "$datasource",
"fieldConfig": {
"defaults": {
"custom": {
"drawStyle": "line",
"fillOpacity": 10,
"lineWidth": 1,
"pointSize": 5,
"showPoints": "never",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
}
},
"thresholds": {
"mode": "absolute",
"steps": [ ]
},
"unit": "bytes"
},
"overrides": [ ]
},
"fill": 1,
"gridPos": { },
"id": 4,
"links": [ ],
"options": {
"legend": {
"showLegend": true
},
"tooltip": {
"mode": "single",
"sort": "none"
}
"legend": {
"avg": false,
"current": false,
"max": false,
"min": false,
"show": true,
"total": false,
"values": false
},
"lines": true,
"linewidth": 1,
"links": [ ],
"nullPointMode": "null as zero",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"seriesOverrides": [ ],
"spaceLength": 10,
"span": 6,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "sum by(pod) (go_memstats_heap_inuse_bytes{cluster=~\"$cluster\", job=~\"($namespace)/(loki|enterprise-logs)-write\"})",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{pod}}",
"legendLink": null
"legendLink": null,
"step": 10
}
],
"thresholds": [ ],
"timeFrom": null,
"timeShift": null,
"title": "Memory (go heap inuse)",
"tooltip": {
"sort": 2
},
"type": "timeseries"
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [ ]
},
"yaxes": [
{
"format": "bytes",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
},
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": false
}
]
},
{
"aliasColors": { },
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fieldConfig": {
"defaults": {
"custom": {
"drawStyle": "line",
"fillOpacity": 100,
"lineWidth": 0,
"pointSize": 5,
"showPoints": "never",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "normal"
}
},
"thresholds": {
"mode": "absolute",
"steps": [ ]
},
"unit": "Bps"
},
"overrides": [ ]
},
"fill": 10,
"gridPos": { },
"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": 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) (rate(node_disk_written_bytes_total[$__rate_interval])) + ignoring(pod) group_right() (label_replace(count by(instance, pod, device) (container_fs_writes_bytes_total{cluster=~\"$cluster\", namespace=~\"$namespace\", container=\"loki\", pod=~\"(loki|enterprise-logs)-write.*\", device!~\".*sda.*\"}), \"device\", \"$1\", \"device\", \"/dev/(.*)\") * 0)\n",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{pod}} - {{device}}",
"legendLink": null
"legendLink": null,
"step": 10
}
],
"thresholds": [ ],
"timeFrom": null,
"timeShift": null,
"title": "Disk Writes",
"type": "timeseries"
"tooltip": {
"shared": true,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [ ]
},
"yaxes": [
{
"format": "Bps",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
},
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": false
}
]
},
{
"aliasColors": { },
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fieldConfig": {
"defaults": {
"custom": {
"drawStyle": "line",
"fillOpacity": 100,
"lineWidth": 0,
"pointSize": 5,
"showPoints": "never",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "normal"
}
},
"thresholds": {
"mode": "absolute",
"steps": [ ]
},
"unit": "Bps"
},
"overrides": [ ]
},
"fill": 10,
"gridPos": { },
"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": 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) (rate(node_disk_read_bytes_total[$__rate_interval])) + ignoring(pod) group_right() (label_replace(count by(instance, pod, device) (container_fs_writes_bytes_total{cluster=~\"$cluster\", namespace=~\"$namespace\", container=\"loki\", pod=~\"(loki|enterprise-logs)-write.*\", device!~\".*sda.*\"}), \"device\", \"$1\", \"device\", \"/dev/(.*)\") * 0)\n",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{pod}} - {{device}}",
"legendLink": null
"legendLink": null,
"step": 10
}
],
"thresholds": [ ],
"timeFrom": null,
"timeShift": null,
"title": "Disk Reads",
"type": "timeseries"
"tooltip": {
"shared": true,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [ ]
},
"yaxes": [
{
"format": "Bps",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
},
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": false
}
]
},
{
"aliasColors": { },
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$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": "percentunit"
},
"overrides": [ ]
},
"fill": 1,
"gridPos": { },
"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": 6,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "max by(persistentvolumeclaim) (kubelet_volume_stats_used_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\"} / kubelet_volume_stats_capacity_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\"}) and count by(persistentvolumeclaim) (kube_persistentvolumeclaim_labels{cluster=~\"$cluster\", namespace=~\"$namespace\",label_name=~\"(loki|enterprise-logs)-write.*\"})",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{persistentvolumeclaim}}",
"legendLink": null
"legendLink": null,
"step": 10
}
],
"thresholds": [ ],
"timeFrom": null,
"timeShift": null,
"title": "Disk Space Utilization",
"type": "timeseries"
"tooltip": {
"shared": true,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [ ]
},
"yaxes": [
{
"format": "percentunit",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
},
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": false
}
]
}
],
"repeat": null,
@@ -492,7 +634,7 @@
"value": "default"
},
"hide": 0,
"label": "Data source",
"label": "Data Source",
"name": "datasource",
"options": [ ],
"query": "prometheus",

View File

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

View File

@@ -1,53 +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"

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

@@ -18,10 +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 }}

View File

@@ -8,7 +8,7 @@ data:
discovery.kubernetes "pods" {
role = "pod"
namespaces {
own_namespace = true
own_namespace = false
names = [ {{ include "agent.namespaces" . }} ]
}
}
@@ -33,38 +33,22 @@ data:
}
rule {
target_label = "cluster"
replacement = "{{- .Values.clusterLabelValue -}}"
replacement = "{{- .Values.clusterName -}}"
}
}
{{- if or .Values.local.logs.enabled .Values.cloud.logs.enabled }}
// Logs
remote.kubernetes.secret "logs_credentials" {
namespace = "{{- $.Release.Namespace -}}"
name = "{{- .Values.cloud.logs.secret -}}"
}
{{- 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 }}"
@@ -72,85 +56,26 @@ data:
replace = "{{ .replace }}"
}
{{- end }}
{{- end }}
}
{{- end }}
{{- end }}
{{- if or .Values.local.metrics.enabled .Values.cloud.metrics.enabled }}
// Metrics
remote.kubernetes.secret "metrics_credentials" {
namespace = "{{- $.Release.Namespace -}}"
name = "{{- .Values.cloud.metrics.secret -}}"
}
discovery.kubernetes "metric_pods" {
role = "pod"
namespaces {
own_namespace = true
names = [ {{ include "agent.namespaces" . }} ]
}
}
discovery.relabel "only_http_metrics" {
targets = discovery.kubernetes.metric_pods.targets
rule {
source_labels = ["__meta_kubernetes_namespace"]
target_label = "namespace"
}
rule {
source_labels = ["__meta_kubernetes_pod_name"]
target_label = "pod"
}
rule {
source_labels = ["__meta_kubernetes_namespace", "__meta_kubernetes_pod_label_app_kubernetes_io_name", "__meta_kubernetes_pod_label_app_kubernetes_io_component"]
separator = "/"
regex = "(.*)/(.*)/(.*)"
replacement = "${1}/${2}-${3}"
target_label = "job"
}
rule {
target_label = "cluster"
replacement = "{{- .Values.clusterLabelValue -}}"
}
rule {
source_labels = ["__meta_kubernetes_pod_container_port_number"]
action = "drop"
regex = "9095"
}
}
{{- 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"
}
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"
@@ -179,17 +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"
@@ -200,12 +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"
@@ -215,20 +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")
@@ -259,19 +178,14 @@ data:
}
rule {
target_label = "cluster"
replacement = "{{- .Values.clusterLabelValue -}}"
replacement = "{{- .Values.clusterName -}}"
}
}
{{- end }}
{{- if or .Values.local.traces.enabled .Values.cloud.traces.enabled }}
// Traces
remote.kubernetes.secret "traces_credentials" {
namespace = "{{- $.Release.Namespace -}}"
name = "{{- .Values.cloud.traces.secret -}}"
}
{{- 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.
@@ -340,10 +254,11 @@ data:
{{- 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 -}}"
}
}
}
@@ -352,10 +267,11 @@ 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 -}}"
}
}
}
@@ -364,13 +280,13 @@ data:
{{- if .Values.cloud.traces.enabled }}
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

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

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

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

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

View File

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

View File

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

View File

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

View File

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

View File

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

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

@@ -4,176 +4,46 @@ namespacesToMonitor:
- mimir
- tempo
# The name of the cluster where this will be installed
clusterLabelValue: "meta-monitoring"
clusterName: "meta-monitoring"
# Set to true for a local version of logs, metrics or traces
local:
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: true
secret: "logs"
metrics:
enabled: true
secret: "metrics"
traces:
enabled: true
secret: "traces"
# Set to true for a local version of logs, metrics or traces
local:
grafana:
enabled: false
logs:
enabled: false
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_persistentvolumeclaim_labels
- kube_pod_container_resource_requests
- kube_pod_container_status_last_terminated_reason
- kube_pod_container_status_restarts_total
- loki_boltdb_shipper_compact_tables_operation_duration_seconds
- loki_boltdb_shipper_compact_tables_operation_last_successful_run_timestamp_seconds
- loki_boltdb_shipper_retention_marker_count_total
- loki_boltdb_shipper_retention_marker_table_processed_duration_seconds_bucket
- loki_boltdb_shipper_retention_marker_table_processed_duration_seconds_count
- loki_boltdb_shipper_retention_marker_table_processed_duration_seconds_sum
- loki_boltdb_shipper_retention_marker_table_processed_total
- loki_boltdb_shipper_request_duration_seconds_bucket
- loki_boltdb_shipper_request_duration_seconds_count
- loki_boltdb_shipper_request_duration_seconds_sum
- loki_boltdb_shipper_retention_sweeper_chunk_deleted_duration_seconds_bucket
- loki_boltdb_shipper_retention_sweeper_chunk_deleted_duration_seconds_count
- loki_boltdb_shipper_retention_sweeper_chunk_deleted_duration_seconds_sum
- loki_boltdb_shipper_retention_sweeper_marker_files_current
- loki_boltdb_shipper_retention_sweeper_marker_file_processing_current_time
- loki_build_info
- loki_chunk_store_deduped_chunks_total
- loki_chunk_store_index_entries_per_chunk_bucket
- loki_chunk_store_index_entries_per_chunk_count
- loki_chunk_store_index_entries_per_chunk_sum
- loki_compactor_delete_requests_processed_total
- loki_compactor_delete_requests_received_total
- loki_compactor_deleted_lines
- loki_compactor_oldest_pending_delete_request_age_seconds
- loki_compactor_pending_delete_requests_count
- loki_discarded_samples_total
- loki_distributor_bytes_received_total
- loki_distributor_lines_received_total
- loki_distributor_structured_metadata_bytes_received_total
- loki_ingester_chunk_age_seconds_bucket
- loki_ingester_chunk_age_seconds_count
- loki_ingester_chunk_age_seconds_sum
- loki_ingester_chunk_bounds_hours_bucket
- loki_ingester_chunk_bounds_hours_count
- loki_ingester_chunk_bounds_hours_sum
- loki_ingester_chunk_entries_bucket
- loki_ingester_chunk_entries_count
- loki_ingester_chunk_entries_sum
- loki_ingester_chunk_size_bytes_bucket
- loki_ingester_chunk_utilization_bucket
- loki_ingester_chunk_utilization_sum
- loki_ingester_chunks_flushed_total
- loki_ingester_flush_queue_length
- loki_ingester_memory_chunks
- loki_ingester_memory_streams
- loki_ingester_streams_created_total
- loki_request_duration_seconds_bucket
- loki_request_duration_seconds_count
- loki_request_duration_seconds_sum
- loki_ruler_wal_appender_ready
- loki_ruler_wal_disk_size
- loki_ruler_wal_prometheus_remote_storage_highest_timestamp_in_seconds
- loki_ruler_wal_prometheus_remote_storage_queue_highest_sent_timestamp_seconds
- loki_ruler_wal_prometheus_remote_storage_samples_pending
- loki_ruler_wal_prometheus_remote_storage_samples_total
- loki_ruler_wal_samples_appended_total
- loki_ruler_wal_storage_created_series_total
- loki_write_batch_retries_total
- loki_write_dropped_bytes_total
- loki_write_dropped_entries_total
- loki_write_sent_bytes_total
- loki_write_sent_entries_total
- node_disk_read_bytes_total
- node_disk_written_bytes_total
- promtail_custom_bad_words_total
# Set enabled = true to add the default logs/metrics/traces dashboards to the local Grafana
dashboards:
logs:
@@ -220,7 +90,7 @@ loki:
compactor:
retention_enabled: true
limits_config:
retention_period: 30d
retention_period: 24h
monitoring:
dashboards:
enabled: false
@@ -237,28 +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'
controller:
type: "statefulset"
autoscaling:
enabled: true
minReplicas: 3
maxReplicas: 30
targetMemoryUtilizationPercentage: 90
targetCPUUtilizationPercentage: 90
mimir-distributed:
minio:
@@ -288,7 +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:
@@ -304,7 +158,7 @@ tempo-distributed:
insecure: true
compactor:
compaction:
block_retention: 30d
block_retention: 24h
traces:
otlp:
http:

View File

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

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