forked from RemoteSync/grafana-meta-monitoring-chart
Compare commits
57 Commits
add_mimir_
...
remove_hel
| Author | SHA1 | Date | |
|---|---|---|---|
|
ef05e599e6 | ||
|
a586e753da | ||
|
|
76908c1e9e | ||
|
|
bc5cdadb9f | ||
|
|
687c77c0f6 | ||
|
|
2a0b14ee45 | ||
|
|
7e06d611a7 | ||
|
|
f4934d6007 | ||
|
|
427764278c | ||
|
|
1093e91741 | ||
|
|
1ed196299b | ||
|
|
faa0015c11 | ||
|
|
53416e042c | ||
|
|
d804da13f1 | ||
|
|
8c0b68fe02 | ||
|
|
99bb8f13c2 | ||
|
|
26ff679cbb | ||
|
|
fb3e3ece1b | ||
|
|
7a5358b322 | ||
|
|
9c92e18efe | ||
|
|
ffe220590d | ||
|
|
e3708ce3fe | ||
|
|
3149f4df9b | ||
|
|
86ec586917 | ||
|
|
6cd12bee01 | ||
|
|
b042b396a2 | ||
|
|
bcacb70e2d | ||
|
|
d9c3b60659 | ||
|
|
6d091d564e | ||
|
8671993962 | ||
|
|
f80c9d7c43 | ||
|
|
60853bc8b0 | ||
|
|
debdd67283 | ||
|
|
8bc465b2e6 | ||
|
|
18d24c39f7 | ||
|
|
23d14110a0 | ||
|
|
092423c2b3 | ||
|
|
dcbe85a37a | ||
|
|
db8558982c | ||
|
|
49034b9f6b | ||
|
|
15f96d9cc6 | ||
|
|
b9f22ba27e | ||
|
|
2f79e7ef14 | ||
|
|
aa988adb47 | ||
|
|
6fb22ae671 | ||
|
|
d3878e1516 | ||
|
|
8ae136e0c4 | ||
|
|
ac3e4462f9 | ||
|
|
e9aab491db | ||
|
|
c95c0e2ca9 | ||
|
|
c288a80bd4 | ||
|
|
93cac45b2e | ||
|
|
6ce4be70e2 | ||
|
|
176312167c | ||
|
|
07a336d9ed | ||
|
|
f4d5bcc018 | ||
|
|
18f0dc932a |
66
.github/workflows/helm-ci.yml
vendored
Normal file
66
.github/workflows/helm-ci.yml
vendored
Normal file
@@ -0,0 +1,66 @@
|
||||
---
|
||||
name: helm-ci
|
||||
on:
|
||||
pull_request:
|
||||
paths:
|
||||
- "charts/meta-monitoring/**"
|
||||
|
||||
env:
|
||||
CT_CONFIGFILE: charts/meta-monitoring/ct.yaml
|
||||
|
||||
jobs:
|
||||
call-lint:
|
||||
name: Lint Helm Chart
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- name: Checkout Code
|
||||
uses: actions/checkout@v3
|
||||
|
||||
- name: Lint Yaml
|
||||
run: make helm-lint
|
||||
|
||||
# call-test:
|
||||
# name: Test Helm Chart
|
||||
# runs-on: ubuntu-latest
|
||||
# steps:
|
||||
# - name: Checkout
|
||||
# uses: actions/checkout@v3
|
||||
# with:
|
||||
# fetch-depth: 0
|
||||
|
||||
# - name: Set up Helm
|
||||
# uses: azure/setup-helm@v3
|
||||
# with:
|
||||
# version: v3.8.2
|
||||
|
||||
# # Python is required because `ct lint` runs Yamale (https://github.com/23andMe/Yamale) and
|
||||
# # yamllint (https://github.com/adrienverge/yamllint) which require Python
|
||||
# - name: Set up Python
|
||||
# uses: actions/setup-python@v4
|
||||
# with:
|
||||
# python-version: 3.7
|
||||
|
||||
# - name: Set up chart-testing
|
||||
# uses: helm/chart-testing-action@v2.4.0
|
||||
|
||||
# - name: Run chart-testing (list-changed)
|
||||
# id: list-changed
|
||||
# run: |
|
||||
# changed=$(ct list-changed --config "${CT_CONFIGFILE}")
|
||||
# if [[ -n "$changed" ]]; then
|
||||
# echo "changed=true" >> $GITHUB_OUTPUT
|
||||
# fi
|
||||
|
||||
# - name: Run chart-testing (lint)
|
||||
# run: ct lint --config "${CT_CONFIGFILE}" --check-version-increment=false
|
||||
|
||||
# - name: Create kind cluster
|
||||
# uses: helm/kind-action@v1.8.0
|
||||
# if: steps.list-changed.outputs.changed == 'true'
|
||||
# with:
|
||||
# config: tools/kind.config
|
||||
|
||||
# - name: Run chart-testing (install)
|
||||
# run: |
|
||||
# changed=$(ct list-changed --config "${CT_CONFIGFILE}")
|
||||
# ct install --config "${CT_CONFIGFILE}"
|
||||
10
Makefile
Normal file
10
Makefile
Normal file
@@ -0,0 +1,10 @@
|
||||
# Adapted from https://www.thapaliya.com/en/writings/well-documented-makefiles/
|
||||
.PHONY: help
|
||||
help: ## Display this help and any documented user-facing targets. Other undocumented targets may be present in the Makefile.
|
||||
help:
|
||||
@awk 'BEGIN {FS = ":.*##"; printf "\nUsage:\n make <target>\n\nTargets:\n"} /^[a-zA-Z_-]+:.*?##/ { printf " %-45s %s\n", $$1, $$2 }' $(MAKEFILE_LIST)
|
||||
|
||||
.PHONY: helm-lint
|
||||
|
||||
helm-lint: ## Run helm linter
|
||||
$(MAKE) -BC charts/meta-monitoring lint
|
||||
39
README.md
39
README.md
@@ -3,6 +3,8 @@
|
||||
This is a meta-monitoring chart for GEL, GEM and GET. It should be installed in a
|
||||
separate namespace next to GEM, GEL or GET installations.
|
||||
|
||||
Note that this is pre-production software at the moment.
|
||||
|
||||
## Preparation
|
||||
|
||||
Create a values.yaml file based on the [default one](../charts/meta-monitoring/values.yaml).
|
||||
@@ -15,29 +17,54 @@ Create a values.yaml file based on the [default one](../charts/meta-monitoring/v
|
||||
|
||||
## Local and cloud modes
|
||||
|
||||
The chart has 2 modes: local and cloud. In the local mode logs, metrics and traces are sent
|
||||
The chart has 2 modes: local and cloud. In the local mode logs, metrics and/or traces are sent
|
||||
to small Loki, Mimir and Tempo installations running in the meta-monitoring namespace.
|
||||
|
||||
|
||||
|
||||
To enable local mode set `local.enabled` to true.
|
||||
To enable local mode set `local.<logs|metrics|traces>.enabled` to true.
|
||||
|
||||
In the cloud mode the logs, metrics and traces are sent to
|
||||
In the cloud mode the logs, metrics and/or traces are sent to Grafana Cloud.
|
||||
|
||||
|
||||
|
||||
To enable cloud mode set `cloud.enabled` to true. The `endpoint`, `username` and `password` settings for your Grafana Cloud logs, metrics and traces instances have to be filled in as well.
|
||||
To enable cloud mode set `cloud.<logs|metrics|traces>.enabled` to true. The `endpoint`, `username` and `password` settings for your Grafana Cloud logs, metrics and traces instances have to be filled in as well.
|
||||
|
||||
Both modes can be enabled at the same time.
|
||||
|
||||
## Installation
|
||||
|
||||
```
|
||||
helm install -n meta -f values.yaml meta ./charts/meta-monitoring
|
||||
helm install -n meta --skip-crds -f values.yaml meta ./charts/meta-monitoring
|
||||
```
|
||||
|
||||
If the platform supports CRDs the `--skip-crds` option can be removed. However the CRDs are not used by this chart.
|
||||
|
||||
For more instructions including how to update the chart go to the [installation](docs/installation.md) page.
|
||||
|
||||
## Supported features
|
||||
|
||||
- Specify which namespaces are monitored
|
||||
- Specify if logs, metrics or traces should be enabled for cloud or local
|
||||
- Specify the cluster name used for the logs, metrics and traces
|
||||
- Specify PII regexes that are applied to logs before they are sent to Loki (cloud or local). The capture group in the regex is replaced with *****.
|
||||
- a Grafana instance is installed (when local mode is used) with the relevant datasources installed. The following dashboards are installed:
|
||||
- logs dashboards
|
||||
- metrics dashboards
|
||||
- traces dashboards
|
||||
- agent dashboards
|
||||
- Retention is set to 24 hours
|
||||
|
||||
Most of these features are enabled by default. See the values.yaml file for how to enable/disable them.
|
||||
|
||||
## Caveats
|
||||
|
||||
- The [loki.source.kubernetes](https://grafana.com/docs/agent/latest/flow/reference/components/loki.source.kubernetes/) component of the Grafana Agent is used to scrape Kubernetes log files. This component is marked experimental at the moment.
|
||||
- This has not been tested on Openshift yet.
|
||||
- The underlying Loki, Mimir and Tempo are at the default size installed by the Helm chart. This might need changing when monitoring bigger Loki, Mimir or Tempo installations.
|
||||
- MinIO is used as storage at the moment with a limited retention. At the moment this chart cannot be used for monitoring over longer periods.
|
||||
- Agent self monitoring is not done at the moment.
|
||||
|
||||
## Developer help topics
|
||||
|
||||
- [update dependencies](docs/dev_update_dependencies.md)
|
||||
- [update dependencies](docs/dev_update_dependencies.md)
|
||||
@@ -14,5 +14,5 @@ dependencies:
|
||||
- name: minio
|
||||
repository: https://charts.min.io
|
||||
version: 5.0.11
|
||||
digest: sha256:4b04084e6fe821c4d481017b2430f7c8cd782a5d60830dd3a24eb8f10a9ece09
|
||||
generated: "2023-06-29T14:25:07.247853+01:00"
|
||||
digest: sha256:da0e744b5046eb7972e0bf82d1d0ba4786e9600af63b65f35b16118105248074
|
||||
generated: "2023-08-18T10:58:08.978123+01:00"
|
||||
|
||||
@@ -25,21 +25,21 @@ appVersion: "0.0.1"
|
||||
|
||||
dependencies:
|
||||
- name: loki
|
||||
repository: https://grafana.github.io/helm-charts
|
||||
repository: https://grafana.github.io/helm-charts
|
||||
version: "5.8.0"
|
||||
condition: local.logs.enabled
|
||||
- name: grafana-agent
|
||||
repository: https://grafana.github.io/helm-charts
|
||||
repository: https://grafana.github.io/helm-charts
|
||||
version: "0.15.0"
|
||||
- name: mimir-distributed
|
||||
repository: https://grafana.github.io/helm-charts
|
||||
repository: https://grafana.github.io/helm-charts
|
||||
version: "4.4.1"
|
||||
condition: local.metrics.enabled
|
||||
- name: tempo-distributed
|
||||
repository: https://grafana.github.io/helm-charts
|
||||
repository: https://grafana.github.io/helm-charts
|
||||
version: "1.4.7"
|
||||
condition: local.traces.enabled
|
||||
- name: minio
|
||||
repository: https://charts.min.io
|
||||
version: "5.0.11"
|
||||
condition: local.minio.enabled
|
||||
condition: local.minio.enabled
|
||||
|
||||
7
charts/meta-monitoring/Makefile
Normal file
7
charts/meta-monitoring/Makefile
Normal file
@@ -0,0 +1,7 @@
|
||||
.DEFAULT_GOAL := lint
|
||||
.PHONY: lint lint-yaml
|
||||
|
||||
lint: lint-yaml
|
||||
|
||||
lint-yaml:
|
||||
yamllint -c $(CURDIR)/src/.yamllint.yaml $(CURDIR)/src
|
||||
11
charts/meta-monitoring/ct.yaml
Normal file
11
charts/meta-monitoring/ct.yaml
Normal file
@@ -0,0 +1,11 @@
|
||||
---
|
||||
remote: origin
|
||||
target-branch: main
|
||||
chart-dirs:
|
||||
- charts
|
||||
chart-repos:
|
||||
- grafana=https://grafana.github.io/helm-charts
|
||||
- minio=https://charts.min.io
|
||||
helm-extra-args: --timeout 1200s
|
||||
check-version-increment: false
|
||||
validate-maintainers: false
|
||||
4
charts/meta-monitoring/src/.yamllint.yaml
Normal file
4
charts/meta-monitoring/src/.yamllint.yaml
Normal file
@@ -0,0 +1,4 @@
|
||||
---
|
||||
rules:
|
||||
quoted-strings:
|
||||
required: true
|
||||
1082
charts/meta-monitoring/src/dashboards/agent-logs-pipeline.json
Normal file
1082
charts/meta-monitoring/src/dashboards/agent-logs-pipeline.json
Normal file
File diff suppressed because it is too large
Load Diff
1189
charts/meta-monitoring/src/dashboards/agent-operational.json
Normal file
1189
charts/meta-monitoring/src/dashboards/agent-operational.json
Normal file
File diff suppressed because it is too large
Load Diff
1512
charts/meta-monitoring/src/dashboards/agent-remote-write.json
Normal file
1512
charts/meta-monitoring/src/dashboards/agent-remote-write.json
Normal file
File diff suppressed because it is too large
Load Diff
1065
charts/meta-monitoring/src/dashboards/agent-tracing-pipeline.json
Normal file
1065
charts/meta-monitoring/src/dashboards/agent-tracing-pipeline.json
Normal file
File diff suppressed because it is too large
Load Diff
786
charts/meta-monitoring/src/dashboards/agent.json
Normal file
786
charts/meta-monitoring/src/dashboards/agent.json
Normal file
@@ -0,0 +1,786 @@
|
||||
{
|
||||
"annotations": {
|
||||
"list": [ ]
|
||||
},
|
||||
"editable": true,
|
||||
"gnetId": null,
|
||||
"graphTooltip": 0,
|
||||
"hideControls": false,
|
||||
"links": [ ],
|
||||
"refresh": "30s",
|
||||
"rows": [
|
||||
{
|
||||
"collapse": false,
|
||||
"height": "250px",
|
||||
"panels": [
|
||||
{
|
||||
"aliasColors": { },
|
||||
"bars": false,
|
||||
"dashLength": 10,
|
||||
"dashes": false,
|
||||
"datasource": "$datasource",
|
||||
"fill": 1,
|
||||
"id": 1,
|
||||
"legend": {
|
||||
"avg": false,
|
||||
"current": false,
|
||||
"max": false,
|
||||
"min": false,
|
||||
"show": true,
|
||||
"total": false,
|
||||
"values": false
|
||||
},
|
||||
"lines": true,
|
||||
"linewidth": 1,
|
||||
"links": [ ],
|
||||
"nullPointMode": "null as zero",
|
||||
"percentage": false,
|
||||
"pointradius": 5,
|
||||
"points": false,
|
||||
"renderer": "flot",
|
||||
"seriesOverrides": [ ],
|
||||
"spaceLength": 10,
|
||||
"span": 12,
|
||||
"stack": false,
|
||||
"steppedLine": false,
|
||||
"styles": [
|
||||
{
|
||||
"alias": "Time",
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"pattern": "Time",
|
||||
"type": "hidden"
|
||||
},
|
||||
{
|
||||
"alias": "Count",
|
||||
"colorMode": null,
|
||||
"colors": [ ],
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "Value #A",
|
||||
"thresholds": [ ],
|
||||
"type": "hidden",
|
||||
"unit": "short"
|
||||
},
|
||||
{
|
||||
"alias": "Uptime",
|
||||
"colorMode": null,
|
||||
"colors": [ ],
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "Value #B",
|
||||
"thresholds": [ ],
|
||||
"type": "number",
|
||||
"unit": "short"
|
||||
},
|
||||
{
|
||||
"alias": "Container",
|
||||
"colorMode": null,
|
||||
"colors": [ ],
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "container",
|
||||
"thresholds": [ ],
|
||||
"type": "number",
|
||||
"unit": "short"
|
||||
},
|
||||
{
|
||||
"alias": "Pod",
|
||||
"colorMode": null,
|
||||
"colors": [ ],
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "pod",
|
||||
"thresholds": [ ],
|
||||
"type": "number",
|
||||
"unit": "short"
|
||||
},
|
||||
{
|
||||
"alias": "Version",
|
||||
"colorMode": null,
|
||||
"colors": [ ],
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "version",
|
||||
"thresholds": [ ],
|
||||
"type": "number",
|
||||
"unit": "short"
|
||||
},
|
||||
{
|
||||
"alias": "",
|
||||
"colorMode": null,
|
||||
"colors": [ ],
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"pattern": "/.*/",
|
||||
"thresholds": [ ],
|
||||
"type": "string",
|
||||
"unit": "short"
|
||||
}
|
||||
],
|
||||
"targets": [
|
||||
{
|
||||
"expr": "count by (pod, container, version) (agent_build_info{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"$container\"})",
|
||||
"format": "table",
|
||||
"instant": true,
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "",
|
||||
"refId": "A",
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"expr": "max by (pod, container) (time() - process_start_time_seconds{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"$container\"})",
|
||||
"format": "table",
|
||||
"instant": true,
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "",
|
||||
"refId": "B",
|
||||
"step": 10
|
||||
}
|
||||
],
|
||||
"thresholds": [ ],
|
||||
"timeFrom": null,
|
||||
"timeShift": null,
|
||||
"title": "Agent Stats",
|
||||
"tooltip": {
|
||||
"shared": true,
|
||||
"sort": 2,
|
||||
"value_type": "individual"
|
||||
},
|
||||
"transform": "table",
|
||||
"type": "table",
|
||||
"xaxis": {
|
||||
"buckets": null,
|
||||
"mode": "time",
|
||||
"name": null,
|
||||
"show": true,
|
||||
"values": [ ]
|
||||
},
|
||||
"yaxes": [
|
||||
{
|
||||
"format": "short",
|
||||
"label": null,
|
||||
"logBase": 1,
|
||||
"max": null,
|
||||
"min": 0,
|
||||
"show": true
|
||||
},
|
||||
{
|
||||
"format": "short",
|
||||
"label": null,
|
||||
"logBase": 1,
|
||||
"max": null,
|
||||
"min": null,
|
||||
"show": false
|
||||
}
|
||||
]
|
||||
}
|
||||
],
|
||||
"repeat": null,
|
||||
"repeatIteration": null,
|
||||
"repeatRowId": null,
|
||||
"showTitle": true,
|
||||
"title": "Agent Stats",
|
||||
"titleSize": "h6"
|
||||
},
|
||||
{
|
||||
"collapse": false,
|
||||
"height": "250px",
|
||||
"panels": [
|
||||
{
|
||||
"aliasColors": { },
|
||||
"bars": false,
|
||||
"dashLength": 10,
|
||||
"dashes": false,
|
||||
"datasource": "$datasource",
|
||||
"fill": 1,
|
||||
"id": 2,
|
||||
"legend": {
|
||||
"avg": false,
|
||||
"current": false,
|
||||
"max": false,
|
||||
"min": false,
|
||||
"show": true,
|
||||
"total": false,
|
||||
"values": false
|
||||
},
|
||||
"lines": true,
|
||||
"linewidth": 1,
|
||||
"links": [ ],
|
||||
"nullPointMode": "null as zero",
|
||||
"percentage": false,
|
||||
"pointradius": 5,
|
||||
"points": false,
|
||||
"renderer": "flot",
|
||||
"seriesOverrides": [ ],
|
||||
"spaceLength": 10,
|
||||
"span": 6,
|
||||
"stack": false,
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(rate(prometheus_target_sync_length_seconds_sum{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"$container\"}[5m])) by (pod, scrape_job) * 1e3",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{pod}}/{{scrape_job}}",
|
||||
"legendLink": null,
|
||||
"step": 10
|
||||
}
|
||||
],
|
||||
"thresholds": [ ],
|
||||
"timeFrom": null,
|
||||
"timeShift": null,
|
||||
"title": "Target Sync",
|
||||
"tooltip": {
|
||||
"shared": true,
|
||||
"sort": 2,
|
||||
"value_type": "individual"
|
||||
},
|
||||
"type": "graph",
|
||||
"xaxis": {
|
||||
"buckets": null,
|
||||
"mode": "time",
|
||||
"name": null,
|
||||
"show": true,
|
||||
"values": [ ]
|
||||
},
|
||||
"yaxes": [
|
||||
{
|
||||
"format": "ms",
|
||||
"label": null,
|
||||
"logBase": 1,
|
||||
"max": null,
|
||||
"min": 0,
|
||||
"show": true
|
||||
},
|
||||
{
|
||||
"format": "short",
|
||||
"label": null,
|
||||
"logBase": 1,
|
||||
"max": null,
|
||||
"min": null,
|
||||
"show": false
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"aliasColors": { },
|
||||
"bars": false,
|
||||
"dashLength": 10,
|
||||
"dashes": false,
|
||||
"datasource": "$datasource",
|
||||
"fill": 10,
|
||||
"id": 3,
|
||||
"legend": {
|
||||
"avg": false,
|
||||
"current": false,
|
||||
"max": false,
|
||||
"min": false,
|
||||
"show": true,
|
||||
"total": false,
|
||||
"values": false
|
||||
},
|
||||
"lines": true,
|
||||
"linewidth": 0,
|
||||
"links": [ ],
|
||||
"nullPointMode": "null as zero",
|
||||
"percentage": false,
|
||||
"pointradius": 5,
|
||||
"points": false,
|
||||
"renderer": "flot",
|
||||
"seriesOverrides": [ ],
|
||||
"spaceLength": 10,
|
||||
"span": 6,
|
||||
"stack": true,
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum by (pod) (prometheus_sd_discovered_targets{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"$container\"})",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{pod}}",
|
||||
"legendLink": null,
|
||||
"step": 10
|
||||
}
|
||||
],
|
||||
"thresholds": [ ],
|
||||
"timeFrom": null,
|
||||
"timeShift": null,
|
||||
"title": "Targets",
|
||||
"tooltip": {
|
||||
"shared": true,
|
||||
"sort": 2,
|
||||
"value_type": "individual"
|
||||
},
|
||||
"type": "graph",
|
||||
"xaxis": {
|
||||
"buckets": null,
|
||||
"mode": "time",
|
||||
"name": null,
|
||||
"show": true,
|
||||
"values": [ ]
|
||||
},
|
||||
"yaxes": [
|
||||
{
|
||||
"format": "short",
|
||||
"label": null,
|
||||
"logBase": 1,
|
||||
"max": null,
|
||||
"min": 0,
|
||||
"show": true
|
||||
},
|
||||
{
|
||||
"format": "short",
|
||||
"label": null,
|
||||
"logBase": 1,
|
||||
"max": null,
|
||||
"min": null,
|
||||
"show": false
|
||||
}
|
||||
]
|
||||
}
|
||||
],
|
||||
"repeat": null,
|
||||
"repeatIteration": null,
|
||||
"repeatRowId": null,
|
||||
"showTitle": true,
|
||||
"title": "Prometheus Discovery",
|
||||
"titleSize": "h6"
|
||||
},
|
||||
{
|
||||
"collapse": false,
|
||||
"height": "250px",
|
||||
"panels": [
|
||||
{
|
||||
"aliasColors": { },
|
||||
"bars": false,
|
||||
"dashLength": 10,
|
||||
"dashes": false,
|
||||
"datasource": "$datasource",
|
||||
"fill": 1,
|
||||
"id": 4,
|
||||
"legend": {
|
||||
"avg": false,
|
||||
"current": false,
|
||||
"max": false,
|
||||
"min": false,
|
||||
"show": true,
|
||||
"total": false,
|
||||
"values": false
|
||||
},
|
||||
"lines": true,
|
||||
"linewidth": 1,
|
||||
"links": [ ],
|
||||
"nullPointMode": "null as zero",
|
||||
"percentage": false,
|
||||
"pointradius": 5,
|
||||
"points": false,
|
||||
"renderer": "flot",
|
||||
"seriesOverrides": [ ],
|
||||
"spaceLength": 10,
|
||||
"span": 4,
|
||||
"stack": false,
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "rate(prometheus_target_interval_length_seconds_sum{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"$container\"}[5m])\n/\nrate(prometheus_target_interval_length_seconds_count{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"$container\"}[5m])\n* 1e3\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{pod}} {{interval}} configured",
|
||||
"legendLink": null,
|
||||
"step": 10
|
||||
}
|
||||
],
|
||||
"thresholds": [ ],
|
||||
"timeFrom": null,
|
||||
"timeShift": null,
|
||||
"title": "Average Scrape Interval Duration",
|
||||
"tooltip": {
|
||||
"shared": true,
|
||||
"sort": 2,
|
||||
"value_type": "individual"
|
||||
},
|
||||
"type": "graph",
|
||||
"xaxis": {
|
||||
"buckets": null,
|
||||
"mode": "time",
|
||||
"name": null,
|
||||
"show": true,
|
||||
"values": [ ]
|
||||
},
|
||||
"yaxes": [
|
||||
{
|
||||
"format": "ms",
|
||||
"label": null,
|
||||
"logBase": 1,
|
||||
"max": null,
|
||||
"min": 0,
|
||||
"show": true
|
||||
},
|
||||
{
|
||||
"format": "short",
|
||||
"label": null,
|
||||
"logBase": 1,
|
||||
"max": null,
|
||||
"min": null,
|
||||
"show": false
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"aliasColors": { },
|
||||
"bars": false,
|
||||
"dashLength": 10,
|
||||
"dashes": false,
|
||||
"datasource": "$datasource",
|
||||
"fill": 10,
|
||||
"id": 5,
|
||||
"legend": {
|
||||
"avg": false,
|
||||
"current": false,
|
||||
"max": false,
|
||||
"min": false,
|
||||
"show": true,
|
||||
"total": false,
|
||||
"values": false
|
||||
},
|
||||
"lines": true,
|
||||
"linewidth": 0,
|
||||
"links": [ ],
|
||||
"nullPointMode": "null as zero",
|
||||
"percentage": false,
|
||||
"pointradius": 5,
|
||||
"points": false,
|
||||
"renderer": "flot",
|
||||
"seriesOverrides": [ ],
|
||||
"spaceLength": 10,
|
||||
"span": 4,
|
||||
"stack": true,
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum by (job) (rate(prometheus_target_scrapes_exceeded_sample_limit_total{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"$container\"}[1m]))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "exceeded sample limit: {{job}}",
|
||||
"legendLink": null,
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"expr": "sum by (job) (rate(prometheus_target_scrapes_sample_duplicate_timestamp_total{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"$container\"}[1m]))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "duplicate timestamp: {{job}}",
|
||||
"legendLink": null,
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"expr": "sum by (job) (rate(prometheus_target_scrapes_sample_out_of_bounds_total{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"$container\"}[1m]))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "out of bounds: {{job}}",
|
||||
"legendLink": null,
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"expr": "sum by (job) (rate(prometheus_target_scrapes_sample_out_of_order_total{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"$container\"}[1m]))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "out of order: {{job}}",
|
||||
"legendLink": null,
|
||||
"step": 10
|
||||
}
|
||||
],
|
||||
"thresholds": [ ],
|
||||
"timeFrom": null,
|
||||
"timeShift": null,
|
||||
"title": "Scrape failures",
|
||||
"tooltip": {
|
||||
"shared": true,
|
||||
"sort": 2,
|
||||
"value_type": "individual"
|
||||
},
|
||||
"type": "graph",
|
||||
"xaxis": {
|
||||
"buckets": null,
|
||||
"mode": "time",
|
||||
"name": null,
|
||||
"show": true,
|
||||
"values": [ ]
|
||||
},
|
||||
"yaxes": [
|
||||
{
|
||||
"format": "short",
|
||||
"label": null,
|
||||
"logBase": 1,
|
||||
"max": null,
|
||||
"min": 0,
|
||||
"show": true
|
||||
},
|
||||
{
|
||||
"format": "short",
|
||||
"label": null,
|
||||
"logBase": 1,
|
||||
"max": null,
|
||||
"min": null,
|
||||
"show": false
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"aliasColors": { },
|
||||
"bars": false,
|
||||
"dashLength": 10,
|
||||
"dashes": false,
|
||||
"datasource": "$datasource",
|
||||
"fill": 10,
|
||||
"id": 6,
|
||||
"legend": {
|
||||
"avg": false,
|
||||
"current": false,
|
||||
"max": false,
|
||||
"min": false,
|
||||
"show": true,
|
||||
"total": false,
|
||||
"values": false
|
||||
},
|
||||
"lines": true,
|
||||
"linewidth": 0,
|
||||
"links": [ ],
|
||||
"nullPointMode": "null as zero",
|
||||
"percentage": false,
|
||||
"pointradius": 5,
|
||||
"points": false,
|
||||
"renderer": "flot",
|
||||
"seriesOverrides": [ ],
|
||||
"spaceLength": 10,
|
||||
"span": 4,
|
||||
"stack": true,
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum by (job, instance_group_name) (rate(agent_wal_samples_appended_total{cluster=~\"$cluster\", namespace=~\"$namespace\", container=~\"$container\"}[5m]))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{job}} {{instance_group_name}}",
|
||||
"legendLink": null,
|
||||
"step": 10
|
||||
}
|
||||
],
|
||||
"thresholds": [ ],
|
||||
"timeFrom": null,
|
||||
"timeShift": null,
|
||||
"title": "Appended Samples",
|
||||
"tooltip": {
|
||||
"shared": true,
|
||||
"sort": 2,
|
||||
"value_type": "individual"
|
||||
},
|
||||
"type": "graph",
|
||||
"xaxis": {
|
||||
"buckets": null,
|
||||
"mode": "time",
|
||||
"name": null,
|
||||
"show": true,
|
||||
"values": [ ]
|
||||
},
|
||||
"yaxes": [
|
||||
{
|
||||
"format": "short",
|
||||
"label": null,
|
||||
"logBase": 1,
|
||||
"max": null,
|
||||
"min": 0,
|
||||
"show": true
|
||||
},
|
||||
{
|
||||
"format": "short",
|
||||
"label": null,
|
||||
"logBase": 1,
|
||||
"max": null,
|
||||
"min": null,
|
||||
"show": false
|
||||
}
|
||||
]
|
||||
}
|
||||
],
|
||||
"repeat": null,
|
||||
"repeatIteration": null,
|
||||
"repeatRowId": null,
|
||||
"showTitle": true,
|
||||
"title": "Prometheus Retrieval",
|
||||
"titleSize": "h6"
|
||||
}
|
||||
],
|
||||
"schemaVersion": 14,
|
||||
"style": "dark",
|
||||
"tags": [
|
||||
"grafana-agent-mixin"
|
||||
],
|
||||
"templating": {
|
||||
"list": [
|
||||
{
|
||||
"current": {
|
||||
"text": "default",
|
||||
"value": "default"
|
||||
},
|
||||
"hide": 0,
|
||||
"label": "Data Source",
|
||||
"name": "datasource",
|
||||
"options": [ ],
|
||||
"query": "prometheus",
|
||||
"refresh": 1,
|
||||
"regex": "",
|
||||
"type": "datasource"
|
||||
},
|
||||
{
|
||||
"allValue": ".+",
|
||||
"current": {
|
||||
"selected": true,
|
||||
"text": "All",
|
||||
"value": "$__all"
|
||||
},
|
||||
"datasource": "$datasource",
|
||||
"hide": 0,
|
||||
"includeAll": true,
|
||||
"label": "cluster",
|
||||
"multi": true,
|
||||
"name": "cluster",
|
||||
"options": [ ],
|
||||
"query": "label_values(agent_build_info, cluster)",
|
||||
"refresh": 1,
|
||||
"regex": "",
|
||||
"sort": 2,
|
||||
"tagValuesQuery": "",
|
||||
"tags": [ ],
|
||||
"tagsQuery": "",
|
||||
"type": "query",
|
||||
"useTags": false
|
||||
},
|
||||
{
|
||||
"allValue": ".+",
|
||||
"current": {
|
||||
"selected": true,
|
||||
"text": "All",
|
||||
"value": "$__all"
|
||||
},
|
||||
"datasource": "$datasource",
|
||||
"hide": 0,
|
||||
"includeAll": true,
|
||||
"label": "namespace",
|
||||
"multi": true,
|
||||
"name": "namespace",
|
||||
"options": [ ],
|
||||
"query": "label_values(agent_build_info, namespace)",
|
||||
"refresh": 1,
|
||||
"regex": "",
|
||||
"sort": 2,
|
||||
"tagValuesQuery": "",
|
||||
"tags": [ ],
|
||||
"tagsQuery": "",
|
||||
"type": "query",
|
||||
"useTags": false
|
||||
},
|
||||
{
|
||||
"allValue": ".+",
|
||||
"current": {
|
||||
"selected": true,
|
||||
"text": "All",
|
||||
"value": "$__all"
|
||||
},
|
||||
"datasource": "$datasource",
|
||||
"hide": 0,
|
||||
"includeAll": true,
|
||||
"label": "container",
|
||||
"multi": true,
|
||||
"name": "container",
|
||||
"options": [ ],
|
||||
"query": "label_values(agent_build_info, container)",
|
||||
"refresh": 1,
|
||||
"regex": "",
|
||||
"sort": 2,
|
||||
"tagValuesQuery": "",
|
||||
"tags": [ ],
|
||||
"tagsQuery": "",
|
||||
"type": "query",
|
||||
"useTags": false
|
||||
},
|
||||
{
|
||||
"allValue": "grafana-agent-.*",
|
||||
"current": {
|
||||
"selected": true,
|
||||
"text": "All",
|
||||
"value": "$__all"
|
||||
},
|
||||
"datasource": "$datasource",
|
||||
"hide": 0,
|
||||
"includeAll": true,
|
||||
"label": "pod",
|
||||
"multi": true,
|
||||
"name": "pod",
|
||||
"options": [ ],
|
||||
"query": "label_values(agent_build_info{container=~\"$container\"}, pod)",
|
||||
"refresh": 1,
|
||||
"regex": "",
|
||||
"sort": 2,
|
||||
"tagValuesQuery": "",
|
||||
"tags": [ ],
|
||||
"tagsQuery": "",
|
||||
"type": "query",
|
||||
"useTags": false
|
||||
}
|
||||
]
|
||||
},
|
||||
"time": {
|
||||
"from": "now-1h",
|
||||
"to": "now"
|
||||
},
|
||||
"timepicker": {
|
||||
"refresh_intervals": [
|
||||
"5s",
|
||||
"10s",
|
||||
"30s",
|
||||
"1m",
|
||||
"5m",
|
||||
"15m",
|
||||
"30m",
|
||||
"1h",
|
||||
"2h",
|
||||
"1d"
|
||||
],
|
||||
"time_options": [
|
||||
"5m",
|
||||
"15m",
|
||||
"1h",
|
||||
"6h",
|
||||
"12h",
|
||||
"24h",
|
||||
"2d",
|
||||
"7d",
|
||||
"30d"
|
||||
]
|
||||
},
|
||||
"timezone": "",
|
||||
"title": "Agent",
|
||||
"uid": "",
|
||||
"version": 0
|
||||
}
|
||||
@@ -217,15 +217,15 @@
|
||||
"renderer": "flot",
|
||||
"seriesOverrides": [ ],
|
||||
"spaceLength": 10,
|
||||
"span": 6,
|
||||
"span": 4,
|
||||
"stack": false,
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(increase(loki_compactor_delete_requests_received_total{cluster=~\"$cluster\", namespace=~\"$namespace\"}[1d]))",
|
||||
"expr": "(loki_compactor_delete_requests_received_total{cluster=~\"$cluster\", namespace=~\"$namespace\"} or on() vector(0)) - on () (loki_compactor_delete_requests_processed_total{cluster=~\"$cluster\", namespace=~\"$namespace\"} or on () vector(0))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "received",
|
||||
"legendFormat": "in progress",
|
||||
"legendLink": null,
|
||||
"step": 10
|
||||
}
|
||||
@@ -233,7 +233,7 @@
|
||||
"thresholds": [ ],
|
||||
"timeFrom": null,
|
||||
"timeShift": null,
|
||||
"title": "Delete Requests Received / Day",
|
||||
"title": "# of Delete Requests (received - processed) ",
|
||||
"tooltip": {
|
||||
"shared": true,
|
||||
"sort": 2,
|
||||
@@ -293,7 +293,83 @@
|
||||
"renderer": "flot",
|
||||
"seriesOverrides": [ ],
|
||||
"spaceLength": 10,
|
||||
"span": 6,
|
||||
"span": 4,
|
||||
"stack": false,
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(increase(loki_compactor_delete_requests_received_total{cluster=~\"$cluster\", namespace=~\"$namespace\"}[1d]))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "received",
|
||||
"legendLink": null,
|
||||
"step": 10
|
||||
}
|
||||
],
|
||||
"thresholds": [ ],
|
||||
"timeFrom": null,
|
||||
"timeShift": null,
|
||||
"title": "Delete Requests Received / Day",
|
||||
"tooltip": {
|
||||
"shared": true,
|
||||
"sort": 2,
|
||||
"value_type": "individual"
|
||||
},
|
||||
"type": "graph",
|
||||
"xaxis": {
|
||||
"buckets": null,
|
||||
"mode": "time",
|
||||
"name": null,
|
||||
"show": true,
|
||||
"values": [ ]
|
||||
},
|
||||
"yaxes": [
|
||||
{
|
||||
"format": "short",
|
||||
"label": null,
|
||||
"logBase": 1,
|
||||
"max": null,
|
||||
"min": 0,
|
||||
"show": true
|
||||
},
|
||||
{
|
||||
"format": "short",
|
||||
"label": null,
|
||||
"logBase": 1,
|
||||
"max": null,
|
||||
"min": null,
|
||||
"show": false
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"aliasColors": { },
|
||||
"bars": false,
|
||||
"dashLength": 10,
|
||||
"dashes": false,
|
||||
"datasource": "$datasource",
|
||||
"fill": 1,
|
||||
"id": 5,
|
||||
"legend": {
|
||||
"avg": false,
|
||||
"current": false,
|
||||
"max": false,
|
||||
"min": false,
|
||||
"show": true,
|
||||
"total": false,
|
||||
"values": false
|
||||
},
|
||||
"lines": true,
|
||||
"linewidth": 1,
|
||||
"links": [ ],
|
||||
"nullPointMode": "null as zero",
|
||||
"percentage": false,
|
||||
"pointradius": 5,
|
||||
"points": false,
|
||||
"renderer": "flot",
|
||||
"seriesOverrides": [ ],
|
||||
"spaceLength": 10,
|
||||
"span": 4,
|
||||
"stack": false,
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
@@ -361,7 +437,7 @@
|
||||
"dashes": false,
|
||||
"datasource": "$datasource",
|
||||
"fill": 1,
|
||||
"id": 5,
|
||||
"id": 6,
|
||||
"legend": {
|
||||
"avg": false,
|
||||
"current": false,
|
||||
@@ -381,7 +457,247 @@
|
||||
"renderer": "flot",
|
||||
"seriesOverrides": [ ],
|
||||
"spaceLength": 10,
|
||||
"span": 12,
|
||||
"span": 4,
|
||||
"stack": false,
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=~\"$cluster\", namespace=~\"$namespace\", container=\"compactor\"}",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{pod}}",
|
||||
"legendLink": null,
|
||||
"step": 10
|
||||
}
|
||||
],
|
||||
"thresholds": [ ],
|
||||
"timeFrom": null,
|
||||
"timeShift": null,
|
||||
"title": "Compactor CPU usage",
|
||||
"tooltip": {
|
||||
"shared": true,
|
||||
"sort": 2,
|
||||
"value_type": "individual"
|
||||
},
|
||||
"type": "graph",
|
||||
"xaxis": {
|
||||
"buckets": null,
|
||||
"mode": "time",
|
||||
"name": null,
|
||||
"show": true,
|
||||
"values": [ ]
|
||||
},
|
||||
"yaxes": [
|
||||
{
|
||||
"format": "short",
|
||||
"label": null,
|
||||
"logBase": 1,
|
||||
"max": null,
|
||||
"min": 0,
|
||||
"show": true
|
||||
},
|
||||
{
|
||||
"format": "short",
|
||||
"label": null,
|
||||
"logBase": 1,
|
||||
"max": null,
|
||||
"min": null,
|
||||
"show": false
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"aliasColors": { },
|
||||
"bars": false,
|
||||
"dashLength": 10,
|
||||
"dashes": false,
|
||||
"datasource": "$datasource",
|
||||
"fill": 1,
|
||||
"id": 7,
|
||||
"legend": {
|
||||
"avg": false,
|
||||
"current": false,
|
||||
"max": false,
|
||||
"min": false,
|
||||
"show": true,
|
||||
"total": false,
|
||||
"values": false
|
||||
},
|
||||
"lines": true,
|
||||
"linewidth": 1,
|
||||
"links": [ ],
|
||||
"nullPointMode": "null as zero",
|
||||
"percentage": false,
|
||||
"pointradius": 5,
|
||||
"points": false,
|
||||
"renderer": "flot",
|
||||
"seriesOverrides": [ ],
|
||||
"spaceLength": 10,
|
||||
"span": 4,
|
||||
"stack": false,
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "go_memstats_heap_inuse_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\", container=\"compactor\"} / 1024 / 1024 ",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": " {{pod}} ",
|
||||
"legendLink": null,
|
||||
"step": 10
|
||||
}
|
||||
],
|
||||
"thresholds": [ ],
|
||||
"timeFrom": null,
|
||||
"timeShift": null,
|
||||
"title": "Compactor memory usage (MiB)",
|
||||
"tooltip": {
|
||||
"shared": true,
|
||||
"sort": 2,
|
||||
"value_type": "individual"
|
||||
},
|
||||
"type": "graph",
|
||||
"xaxis": {
|
||||
"buckets": null,
|
||||
"mode": "time",
|
||||
"name": null,
|
||||
"show": true,
|
||||
"values": [ ]
|
||||
},
|
||||
"yaxes": [
|
||||
{
|
||||
"format": "short",
|
||||
"label": null,
|
||||
"logBase": 1,
|
||||
"max": null,
|
||||
"min": 0,
|
||||
"show": true
|
||||
},
|
||||
{
|
||||
"format": "short",
|
||||
"label": null,
|
||||
"logBase": 1,
|
||||
"max": null,
|
||||
"min": null,
|
||||
"show": false
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"aliasColors": { },
|
||||
"bars": false,
|
||||
"dashLength": 10,
|
||||
"dashes": false,
|
||||
"datasource": "$datasource",
|
||||
"fill": 1,
|
||||
"id": 8,
|
||||
"legend": {
|
||||
"avg": false,
|
||||
"current": false,
|
||||
"max": false,
|
||||
"min": false,
|
||||
"show": true,
|
||||
"total": false,
|
||||
"values": false
|
||||
},
|
||||
"lines": true,
|
||||
"linewidth": 1,
|
||||
"links": [ ],
|
||||
"nullPointMode": "null as zero",
|
||||
"percentage": false,
|
||||
"pointradius": 5,
|
||||
"points": false,
|
||||
"renderer": "flot",
|
||||
"seriesOverrides": [ ],
|
||||
"spaceLength": 10,
|
||||
"span": 4,
|
||||
"stack": false,
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "loki_boltdb_shipper_compact_tables_operation_duration_seconds{cluster=~\"$cluster\", namespace=~\"$namespace\"}",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{pod}}",
|
||||
"legendLink": null,
|
||||
"step": 10
|
||||
}
|
||||
],
|
||||
"thresholds": [ ],
|
||||
"timeFrom": null,
|
||||
"timeShift": null,
|
||||
"title": "Compaction run duration (seconds)",
|
||||
"tooltip": {
|
||||
"shared": true,
|
||||
"sort": 2,
|
||||
"value_type": "individual"
|
||||
},
|
||||
"type": "graph",
|
||||
"xaxis": {
|
||||
"buckets": null,
|
||||
"mode": "time",
|
||||
"name": null,
|
||||
"show": true,
|
||||
"values": [ ]
|
||||
},
|
||||
"yaxes": [
|
||||
{
|
||||
"format": "short",
|
||||
"label": null,
|
||||
"logBase": 1,
|
||||
"max": null,
|
||||
"min": 0,
|
||||
"show": true
|
||||
},
|
||||
{
|
||||
"format": "short",
|
||||
"label": null,
|
||||
"logBase": 1,
|
||||
"max": null,
|
||||
"min": null,
|
||||
"show": false
|
||||
}
|
||||
]
|
||||
}
|
||||
],
|
||||
"repeat": null,
|
||||
"repeatIteration": null,
|
||||
"repeatRowId": null,
|
||||
"showTitle": true,
|
||||
"title": "Compactor",
|
||||
"titleSize": "h6"
|
||||
},
|
||||
{
|
||||
"collapse": false,
|
||||
"height": "250px",
|
||||
"panels": [
|
||||
{
|
||||
"aliasColors": { },
|
||||
"bars": false,
|
||||
"dashLength": 10,
|
||||
"dashes": false,
|
||||
"datasource": "$datasource",
|
||||
"fill": 1,
|
||||
"id": 9,
|
||||
"legend": {
|
||||
"avg": false,
|
||||
"current": false,
|
||||
"max": false,
|
||||
"min": false,
|
||||
"show": true,
|
||||
"total": false,
|
||||
"values": false
|
||||
},
|
||||
"lines": true,
|
||||
"linewidth": 1,
|
||||
"links": [ ],
|
||||
"nullPointMode": "null as zero",
|
||||
"percentage": false,
|
||||
"pointradius": 5,
|
||||
"points": false,
|
||||
"renderer": "flot",
|
||||
"seriesOverrides": [ ],
|
||||
"spaceLength": 10,
|
||||
"span": 6,
|
||||
"stack": false,
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
@@ -429,19 +745,7 @@
|
||||
"show": false
|
||||
}
|
||||
]
|
||||
}
|
||||
],
|
||||
"repeat": null,
|
||||
"repeatIteration": null,
|
||||
"repeatRowId": null,
|
||||
"showTitle": true,
|
||||
"title": "Failures",
|
||||
"titleSize": "h6"
|
||||
},
|
||||
{
|
||||
"collapse": false,
|
||||
"height": "250px",
|
||||
"panels": [
|
||||
},
|
||||
{
|
||||
"aliasColors": { },
|
||||
"bars": false,
|
||||
@@ -449,7 +753,7 @@
|
||||
"dashes": false,
|
||||
"datasource": "$datasource",
|
||||
"fill": 1,
|
||||
"id": 6,
|
||||
"id": 10,
|
||||
"legend": {
|
||||
"avg": false,
|
||||
"current": false,
|
||||
@@ -469,7 +773,7 @@
|
||||
"renderer": "flot",
|
||||
"seriesOverrides": [ ],
|
||||
"spaceLength": 10,
|
||||
"span": 12,
|
||||
"span": 6,
|
||||
"stack": false,
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
@@ -523,7 +827,45 @@
|
||||
"repeatIteration": null,
|
||||
"repeatRowId": null,
|
||||
"showTitle": true,
|
||||
"title": "Deleted lines",
|
||||
"title": "Deletion metrics",
|
||||
"titleSize": "h6"
|
||||
},
|
||||
{
|
||||
"collapse": false,
|
||||
"height": "250px",
|
||||
"panels": [
|
||||
{
|
||||
"datasource": "$loki_datasource",
|
||||
"id": 11,
|
||||
"span": 6,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "{cluster=~\"$cluster\", namespace=~\"$namespace\", container=\"compactor\"} |~ \"Started processing delete request|delete request for user marked as processed\" | logfmt | line_format \"{{.ts}} user={{.user}} delete_request_id={{.delete_request_id}} msg={{.msg}}\" ",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"title": "In progress/finished",
|
||||
"type": "logs"
|
||||
},
|
||||
{
|
||||
"datasource": "$loki_datasource",
|
||||
"id": 12,
|
||||
"span": 6,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "{cluster=~\"$cluster\", namespace=~\"$namespace\", container=\"compactor\"} |~ \"delete request for user added\" | logfmt | line_format \"{{.ts}} user={{.user}} query='{{.query}}'\"",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"title": "Requests",
|
||||
"type": "logs"
|
||||
}
|
||||
],
|
||||
"repeat": null,
|
||||
"repeatIteration": null,
|
||||
"repeatRowId": null,
|
||||
"showTitle": true,
|
||||
"title": "List of deletion requests",
|
||||
"titleSize": "h6"
|
||||
}
|
||||
],
|
||||
|
||||
@@ -6,7 +6,6 @@
|
||||
"gnetId": null,
|
||||
"graphTooltip": 0,
|
||||
"hideControls": false,
|
||||
"id": 8,
|
||||
"iteration": 1583185057230,
|
||||
"links": [
|
||||
{
|
||||
@@ -1070,4 +1069,4 @@
|
||||
"title": "Loki / Logs",
|
||||
"uid": "logs",
|
||||
"version": 0
|
||||
}
|
||||
}
|
||||
|
||||
@@ -1,41 +1,27 @@
|
||||
{
|
||||
"annotations": {
|
||||
"list": [
|
||||
{
|
||||
"builtIn": 1,
|
||||
"datasource": "-- Grafana --",
|
||||
"enable": true,
|
||||
"hide": true,
|
||||
"iconColor": "rgba(0, 211, 255, 1)",
|
||||
"name": "Annotations & Alerts",
|
||||
"target": {
|
||||
"limit": 100,
|
||||
"matchAny": false,
|
||||
"tags": [ ],
|
||||
"type": "dashboard"
|
||||
},
|
||||
"type": "dashboard"
|
||||
},
|
||||
{
|
||||
"datasource": "${datasource}",
|
||||
"enable": false,
|
||||
"expr": "sum by (tenant) (changes(loki_ruler_wal_prometheus_tsdb_wal_truncations_total{tenant=~\"${tenant}\"}[$__rate_interval]))",
|
||||
"iconColor": "red",
|
||||
"name": "WAL Truncations",
|
||||
"target": {
|
||||
"queryType": "Azure Monitor",
|
||||
"refId": "Anno"
|
||||
},
|
||||
"titleFormat": "{{tenant}}"
|
||||
}
|
||||
]
|
||||
"list": [ ]
|
||||
},
|
||||
"editable": true,
|
||||
"fiscalYearStartMonth": 0,
|
||||
"gnetId": null,
|
||||
"graphTooltip": 0,
|
||||
"hideControls": false,
|
||||
"iteration": 1635347545534,
|
||||
"links": [ ],
|
||||
"links": [
|
||||
{
|
||||
"asDropdown": true,
|
||||
"icon": "external link",
|
||||
"includeVars": true,
|
||||
"keepTime": true,
|
||||
"tags": [
|
||||
"loki"
|
||||
],
|
||||
"targetBlank": false,
|
||||
"title": "Loki Dashboards",
|
||||
"type": "dashboards"
|
||||
}
|
||||
],
|
||||
"liveNow": false,
|
||||
"panels": [
|
||||
{
|
||||
@@ -599,59 +585,139 @@
|
||||
"type": "timeseries"
|
||||
}
|
||||
],
|
||||
"schemaVersion": 31,
|
||||
"refresh": "10s",
|
||||
"rows": [ ],
|
||||
"schemaVersion": 14,
|
||||
"style": "dark",
|
||||
"tags": [ ],
|
||||
"tags": [
|
||||
"loki"
|
||||
],
|
||||
"templating": {
|
||||
"list": [
|
||||
{
|
||||
"description": null,
|
||||
"error": null,
|
||||
"current": {
|
||||
"text": "default",
|
||||
"value": "default"
|
||||
},
|
||||
"hide": 0,
|
||||
"includeAll": false,
|
||||
"label": "Datasource",
|
||||
"multi": false,
|
||||
"label": "Data Source",
|
||||
"name": "datasource",
|
||||
"options": [ ],
|
||||
"query": "prometheus",
|
||||
"queryValue": "",
|
||||
"refresh": 1,
|
||||
"regex": "",
|
||||
"skipUrlSync": false,
|
||||
"type": "datasource"
|
||||
},
|
||||
{
|
||||
"allValue": null,
|
||||
"datasource": "${datasource}",
|
||||
"definition": "label_values(loki_ruler_wal_samples_appended_total, tenant)",
|
||||
"description": null,
|
||||
"error": null,
|
||||
"current": {
|
||||
"text": "prod",
|
||||
"value": "prod"
|
||||
},
|
||||
"datasource": "$datasource",
|
||||
"hide": 0,
|
||||
"includeAll": false,
|
||||
"label": "cluster",
|
||||
"multi": false,
|
||||
"name": "cluster",
|
||||
"options": [ ],
|
||||
"query": "label_values(loki_build_info, cluster)",
|
||||
"refresh": 1,
|
||||
"regex": "",
|
||||
"sort": 2,
|
||||
"tagValuesQuery": "",
|
||||
"tags": [ ],
|
||||
"tagsQuery": "",
|
||||
"type": "query",
|
||||
"useTags": false
|
||||
},
|
||||
{
|
||||
"allValue": null,
|
||||
"current": {
|
||||
"text": "prod",
|
||||
"value": "prod"
|
||||
},
|
||||
"datasource": "$datasource",
|
||||
"hide": 0,
|
||||
"includeAll": false,
|
||||
"label": "namespace",
|
||||
"multi": false,
|
||||
"name": "namespace",
|
||||
"options": [ ],
|
||||
"query": "label_values(loki_build_info{cluster=~\"$cluster\"}, namespace)",
|
||||
"refresh": 1,
|
||||
"regex": "",
|
||||
"sort": 2,
|
||||
"tagValuesQuery": "",
|
||||
"tags": [ ],
|
||||
"tagsQuery": "",
|
||||
"type": "query",
|
||||
"useTags": false
|
||||
},
|
||||
{
|
||||
"hide": 0,
|
||||
"label": null,
|
||||
"name": "loki_datasource",
|
||||
"options": [ ],
|
||||
"query": "loki",
|
||||
"refresh": 1,
|
||||
"regex": "",
|
||||
"type": "datasource"
|
||||
},
|
||||
{
|
||||
"allValue": ".+",
|
||||
"current": { },
|
||||
"datasource": "$datasource",
|
||||
"hide": 0,
|
||||
"includeAll": true,
|
||||
"label": "Tenant",
|
||||
"multi": true,
|
||||
"label": null,
|
||||
"multi": false,
|
||||
"name": "tenant",
|
||||
"options": [ ],
|
||||
"query": {
|
||||
"query": "label_values(loki_ruler_wal_samples_appended_total, tenant)",
|
||||
"refId": "StandardVariableQuery"
|
||||
},
|
||||
"refresh": 2,
|
||||
"regex": "",
|
||||
"skipUrlSync": false,
|
||||
"sort": 0,
|
||||
"type": "query"
|
||||
"query": "query_result(sum by (id) (grafanacloud_logs_instance_info) and sum(label_replace(loki_tenant:active_streams{cluster=\"$cluster\",namespace=\"$namespace\"},\"id\",\"$1\",\"tenant\",\"(.*)\")) by(id))",
|
||||
"refresh": 0,
|
||||
"regex": "/\"([^\"]+)\"/",
|
||||
"sort": 1,
|
||||
"tagValuesQuery": "",
|
||||
"tags": [ ],
|
||||
"tagsQuery": "",
|
||||
"type": "query",
|
||||
"useTags": false
|
||||
}
|
||||
]
|
||||
},
|
||||
"time": {
|
||||
"from": "now-6h",
|
||||
"from": "now-1h",
|
||||
"to": "now"
|
||||
},
|
||||
"timepicker": { },
|
||||
"timezone": "",
|
||||
"title": "Recording Rules",
|
||||
"uid": "2xKA_ZK7k",
|
||||
"version": 9,
|
||||
"timepicker": {
|
||||
"refresh_intervals": [
|
||||
"5s",
|
||||
"10s",
|
||||
"30s",
|
||||
"1m",
|
||||
"5m",
|
||||
"15m",
|
||||
"30m",
|
||||
"1h",
|
||||
"2h",
|
||||
"1d"
|
||||
],
|
||||
"time_options": [
|
||||
"5m",
|
||||
"15m",
|
||||
"1h",
|
||||
"6h",
|
||||
"12h",
|
||||
"24h",
|
||||
"2d",
|
||||
"7d",
|
||||
"30d"
|
||||
]
|
||||
},
|
||||
"timezone": "utc",
|
||||
"title": "Loki / Recording Rules",
|
||||
"uid": "recording-rules",
|
||||
"version": 0,
|
||||
"weekStart": ""
|
||||
}
|
||||
@@ -6,7 +6,6 @@
|
||||
"gnetId": null,
|
||||
"graphTooltip": 0,
|
||||
"hideControls": false,
|
||||
"id": 68,
|
||||
"iteration": 1588704280892,
|
||||
"links": [
|
||||
{
|
||||
@@ -567,17 +566,17 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "histogram_quantile(0.99, sum by (le) (job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-write\", route=~\"api_prom_push|loki_api_v1_push\", cluster=~\"$cluster\"})) * 1e3",
|
||||
"expr": "histogram_quantile(0.99, sum by (le) (cluster_job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-write\", route=~\"api_prom_push|loki_api_v1_push\", cluster=~\"$cluster\"})) * 1e3",
|
||||
"legendFormat": ".99",
|
||||
"refId": "A"
|
||||
},
|
||||
{
|
||||
"expr": "histogram_quantile(0.75, sum by (le) (job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-write\", route=~\"api_prom_push|loki_api_v1_push\", cluster=~\"$cluster\"})) * 1e3",
|
||||
"expr": "histogram_quantile(0.75, sum by (le) (cluster_job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-write\", route=~\"api_prom_push|loki_api_v1_push\", cluster=~\"$cluster\"})) * 1e3",
|
||||
"legendFormat": ".9",
|
||||
"refId": "B"
|
||||
},
|
||||
{
|
||||
"expr": "histogram_quantile(0.5, sum by (le) (job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-write\", route=~\"api_prom_push|loki_api_v1_push\", cluster=~\"$cluster\"})) * 1e3",
|
||||
"expr": "histogram_quantile(0.5, sum by (le) (cluster_job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-write\", route=~\"api_prom_push|loki_api_v1_push\", cluster=~\"$cluster\"})) * 1e3",
|
||||
"legendFormat": ".5",
|
||||
"refId": "C"
|
||||
}
|
||||
@@ -673,17 +672,17 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "histogram_quantile(0.99, sum by (le) (job:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-write\", cluster=~\"$cluster\"})) * 1e3",
|
||||
"expr": "histogram_quantile(0.99, sum by (le) (cluster_job:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-write\", cluster=~\"$cluster\"})) * 1e3",
|
||||
"legendFormat": ".99",
|
||||
"refId": "A"
|
||||
},
|
||||
{
|
||||
"expr": "histogram_quantile(0.9, sum by (le) (job:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-write\", cluster=~\"$cluster\"})) * 1e3",
|
||||
"expr": "histogram_quantile(0.9, sum by (le) (cluster_job:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-write\", cluster=~\"$cluster\"})) * 1e3",
|
||||
"legendFormat": ".9",
|
||||
"refId": "B"
|
||||
},
|
||||
{
|
||||
"expr": "histogram_quantile(0.5, sum by (le) (job:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-write\", cluster=~\"$cluster\"})) * 1e3",
|
||||
"expr": "histogram_quantile(0.5, sum by (le) (cluster_job:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-write\", cluster=~\"$cluster\"})) * 1e3",
|
||||
"legendFormat": ".5",
|
||||
"refId": "C"
|
||||
}
|
||||
@@ -779,7 +778,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(rate(loki_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(loki|enterprise-logs)-write\", status_code!~\"5[0-9]{2}\"}[5m])) by (route)\n/\nsum(rate(loki_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(loki|enterprise-logs)-write\"}[5m])) by (route)",
|
||||
"expr": "sum(rate(loki_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(loki|enterprise-logs)-write\", status_code!~\"5[0-9]{2}\"}[$__rate_interval])) by (route)\n/\nsum(rate(loki_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(loki|enterprise-logs)-write\"}[$__rate_interval])) by (route) > 0",
|
||||
"interval": "",
|
||||
"legendFormat": "{{route}}",
|
||||
"refId": "A"
|
||||
@@ -877,18 +876,18 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "histogram_quantile(0.99, sum by (le) (job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-write\", route=\"/logproto.Pusher/Push\", cluster=~\"$cluster\"})) * 1e3",
|
||||
"expr": "histogram_quantile(0.99, sum by (le) (cluster_job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-write\", route=\"/logproto.Pusher/Push\", cluster=~\"$cluster\"})) * 1e3",
|
||||
"legendFormat": ".99",
|
||||
"refId": "A"
|
||||
},
|
||||
{
|
||||
"expr": "histogram_quantile(0.9, sum by (le) (job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-write\", route=\"/logproto.Pusher/Push\", cluster=~\"$cluster\"})) * 1e3",
|
||||
"expr": "histogram_quantile(0.9, sum by (le) (cluster_job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-write\", route=\"/logproto.Pusher/Push\", cluster=~\"$cluster\"})) * 1e3",
|
||||
"hide": false,
|
||||
"legendFormat": ".9",
|
||||
"refId": "B"
|
||||
},
|
||||
{
|
||||
"expr": "histogram_quantile(0.5, sum by (le) (job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-write\", route=\"/logproto.Pusher/Push\", cluster=~\"$cluster\"})) * 1e3",
|
||||
"expr": "histogram_quantile(0.5, sum by (le) (cluster_job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-write\", route=\"/logproto.Pusher/Push\", cluster=~\"$cluster\"})) * 1e3",
|
||||
"hide": false,
|
||||
"legendFormat": ".5",
|
||||
"refId": "C"
|
||||
@@ -985,7 +984,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(rate(loki_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(loki|enterprise-logs)-write\", status_code!~\"5[0-9]{2}\", route=\"/logproto.Pusher/Push\"}[5m])) by (route)\n/\nsum(rate(loki_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(loki|enterprise-logs)-write\", route=\"/logproto.Pusher/Push\"}[5m])) by (route)",
|
||||
"expr": "sum(rate(loki_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(loki|enterprise-logs)-write\", status_code!~\"5[0-9]{2}\", route=\"/logproto.Pusher/Push\"}[$__rate_interval])) by (route)\n/\nsum(rate(loki_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(loki|enterprise-logs)-write\", route=\"/logproto.Pusher/Push\"}[$__rate_interval])) by (route) > 0",
|
||||
"interval": "",
|
||||
"legendFormat": "{{route}}",
|
||||
"refId": "A"
|
||||
@@ -1085,17 +1084,17 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "histogram_quantile(0.99, sum by (le,route) (job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-read\", route=~\"api_prom_query|api_prom_labels|api_prom_label_name_values|loki_api_v1_query|loki_api_v1_query_range|loki_api_v1_label|loki_api_v1_label_name_values\", cluster=\"$cluster\"}))",
|
||||
"expr": "histogram_quantile(0.99, sum by (le,route) (cluster_job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-read\", route=~\"api_prom_query|api_prom_labels|api_prom_label_name_values|loki_api_v1_query|loki_api_v1_query_range|loki_api_v1_label|loki_api_v1_label_name_values\", cluster=\"$cluster\"}))",
|
||||
"legendFormat": "{{route}}-.99",
|
||||
"refId": "A"
|
||||
},
|
||||
{
|
||||
"expr": "histogram_quantile(0.9, sum by (le,route) (job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-read\", route=~\"api_prom_query|api_prom_labels|api_prom_label_name_values|loki_api_v1_query|loki_api_v1_query_range|loki_api_v1_label|loki_api_v1_label_name_values\", cluster=\"$cluster\"}))",
|
||||
"expr": "histogram_quantile(0.9, sum by (le,route) (cluster_job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-read\", route=~\"api_prom_query|api_prom_labels|api_prom_label_name_values|loki_api_v1_query|loki_api_v1_query_range|loki_api_v1_label|loki_api_v1_label_name_values\", cluster=\"$cluster\"}))",
|
||||
"legendFormat": "{{route}}-.9",
|
||||
"refId": "B"
|
||||
},
|
||||
{
|
||||
"expr": "histogram_quantile(0.5, sum by (le,route) (job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-read\", route=~\"api_prom_query|api_prom_labels|api_prom_label_name_values|loki_api_v1_query|loki_api_v1_query_range|loki_api_v1_label|loki_api_v1_label_name_values\", cluster=\"$cluster\"}))",
|
||||
"expr": "histogram_quantile(0.5, sum by (le,route) (cluster_job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-read\", route=~\"api_prom_query|api_prom_labels|api_prom_label_name_values|loki_api_v1_query|loki_api_v1_query_range|loki_api_v1_label|loki_api_v1_label_name_values\", cluster=\"$cluster\"}))",
|
||||
"legendFormat": "{{route}}-.5",
|
||||
"refId": "C"
|
||||
}
|
||||
@@ -1191,17 +1190,17 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "histogram_quantile(0.99, sum by (le,route) (job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-read\", route=~\"api_prom_query|api_prom_labels|api_prom_label_name_values|loki_api_v1_query|loki_api_v1_query_range|loki_api_v1_label|loki_api_v1_label_name_values\", cluster=\"$cluster\"})) * 1e3",
|
||||
"expr": "histogram_quantile(0.99, sum by (le,route) (cluster_job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-read\", route=~\"api_prom_query|api_prom_labels|api_prom_label_name_values|loki_api_v1_query|loki_api_v1_query_range|loki_api_v1_label|loki_api_v1_label_name_values\", cluster=\"$cluster\"})) * 1e3",
|
||||
"legendFormat": ".99-{{route}}",
|
||||
"refId": "A"
|
||||
},
|
||||
{
|
||||
"expr": "histogram_quantile(0.9, sum by (le,route) (job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-read\", route=~\"api_prom_query|api_prom_labels|api_prom_label_name_values|loki_api_v1_query|loki_api_v1_query_range|loki_api_v1_label|loki_api_v1_label_name_values\", cluster=\"$cluster\"})) * 1e3",
|
||||
"expr": "histogram_quantile(0.9, sum by (le,route) (cluster_job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-read\", route=~\"api_prom_query|api_prom_labels|api_prom_label_name_values|loki_api_v1_query|loki_api_v1_query_range|loki_api_v1_label|loki_api_v1_label_name_values\", cluster=\"$cluster\"})) * 1e3",
|
||||
"legendFormat": ".9-{{route}}",
|
||||
"refId": "B"
|
||||
},
|
||||
{
|
||||
"expr": "histogram_quantile(0.5, sum by (le,route) (job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-read\", route=~\"api_prom_query|api_prom_labels|api_prom_label_name_values|loki_api_v1_query|loki_api_v1_query_range|loki_api_v1_label|loki_api_v1_label_name_values\", cluster=\"$cluster\"})) * 1e3",
|
||||
"expr": "histogram_quantile(0.5, sum by (le,route) (cluster_job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-read\", route=~\"api_prom_query|api_prom_labels|api_prom_label_name_values|loki_api_v1_query|loki_api_v1_query_range|loki_api_v1_label|loki_api_v1_label_name_values\", cluster=\"$cluster\"})) * 1e3",
|
||||
"legendFormat": ".5-{{route}}",
|
||||
"refId": "C"
|
||||
}
|
||||
@@ -1297,7 +1296,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(rate(loki_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(loki|enterprise-logs)-read\", status_code!~\"5[0-9]{2}\"}[5m])) by (route)\n/\nsum(rate(loki_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(loki|enterprise-logs)-read\"}[5m])) by (route)",
|
||||
"expr": "sum(rate(loki_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(loki|enterprise-logs)-read\", status_code!~\"5[0-9]{2}\"}[$__rate_interval])) by (route)\n/\nsum(rate(loki_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(loki|enterprise-logs)-read\"}[$__rate_interval])) by (route) > 0",
|
||||
"interval": "",
|
||||
"legendFormat": "{{route}}",
|
||||
"refId": "A"
|
||||
@@ -1396,17 +1395,17 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "histogram_quantile(0.99, sum by (le,route) (job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-write\", route=~\"/logproto.Querier/Query|/logproto.Querier/Label|/logproto.Querier/Series|/logproto.Querier/QuerySample|/logproto.Querier/GetChunkIDs\", cluster=\"$cluster\"})) * 1e3",
|
||||
"expr": "histogram_quantile(0.99, sum by (le,route) (cluster_job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-write\", route=~\"/logproto.Querier/Query|/logproto.Querier/Label|/logproto.Querier/Series|/logproto.Querier/QuerySample|/logproto.Querier/GetChunkIDs\", cluster=\"$cluster\"})) * 1e3",
|
||||
"legendFormat": ".99-{{route}}",
|
||||
"refId": "A"
|
||||
},
|
||||
{
|
||||
"expr": "histogram_quantile(0.9, sum by (le,route) (job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-write\", route=~\"/logproto.Querier/Query|/logproto.Querier/Label|/logproto.Querier/Series|/logproto.Querier/QuerySample|/logproto.Querier/GetChunkIDs\", cluster=\"$cluster\"})) * 1e3",
|
||||
"expr": "histogram_quantile(0.9, sum by (le,route) (cluster_job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-write\", route=~\"/logproto.Querier/Query|/logproto.Querier/Label|/logproto.Querier/Series|/logproto.Querier/QuerySample|/logproto.Querier/GetChunkIDs\", cluster=\"$cluster\"})) * 1e3",
|
||||
"legendFormat": ".9-{{route}}",
|
||||
"refId": "B"
|
||||
},
|
||||
{
|
||||
"expr": "histogram_quantile(0.5, sum by (le,route) (job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-write\", route=~\"/logproto.Querier/Query|/logproto.Querier/Label|/logproto.Querier/Series|/logproto.Querier/QuerySample|/logproto.Querier/GetChunkIDs\", cluster=\"$cluster\"})) * 1e3",
|
||||
"expr": "histogram_quantile(0.5, sum by (le,route) (cluster_job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-write\", route=~\"/logproto.Querier/Query|/logproto.Querier/Label|/logproto.Querier/Series|/logproto.Querier/QuerySample|/logproto.Querier/GetChunkIDs\", cluster=\"$cluster\"})) * 1e3",
|
||||
"legendFormat": ".5-{{route}}",
|
||||
"refId": "C"
|
||||
}
|
||||
@@ -1502,7 +1501,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(rate(loki_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(loki|enterprise-logs)-write\", status_code!~\"5[0-9]{2}\", route=~\"/logproto.Querier/Query|/logproto.Querier/Label|/logproto.Querier/Series|/logproto.Querier/QuerySample|/logproto.Querier/GetChunkIDs\"}[5m])) by (route)\n/\nsum(rate(loki_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(loki|enterprise-logs)-write\", route=~\"/logproto.Querier/Query|/logproto.Querier/Label|/logproto.Querier/Series|/logproto.Querier/QuerySample|/logproto.Querier/GetChunkIDs\"}[5m])) by (route)",
|
||||
"expr": "sum(rate(loki_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(loki|enterprise-logs)-write\", status_code!~\"5[0-9]{2}\", route=~\"/logproto.Querier/Query|/logproto.Querier/Label|/logproto.Querier/Series|/logproto.Querier/QuerySample|/logproto.Querier/GetChunkIDs\"}[$__rate_interval])) by (route)\n/\nsum(rate(loki_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(loki|enterprise-logs)-write\", route=~\"/logproto.Querier/Query|/logproto.Querier/Label|/logproto.Querier/Series|/logproto.Querier/QuerySample|/logproto.Querier/GetChunkIDs\"}[$__rate_interval])) by (route) > 0",
|
||||
"interval": "",
|
||||
"legendFormat": "{{route}}",
|
||||
"refId": "A"
|
||||
@@ -2049,7 +2048,7 @@
|
||||
"panels": [ ],
|
||||
"targets": [
|
||||
{
|
||||
"expr": "{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(loki|enterprise-logs)-write\"} | logfmt | level=\"error\"",
|
||||
"expr": "{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(loki|enterprise-logs)-write\"} |= \"level=error\"",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
@@ -2100,7 +2099,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(rate(loki_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(loki|enterprise-logs)-write\", status_code!~\"5[0-9]{2}\"}[5m])) by (route)\n/\nsum(rate(loki_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(loki|enterprise-logs)-write\"}[5m])) by (route)",
|
||||
"expr": "sum(rate(loki_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(loki|enterprise-logs)-write\", status_code!~\"5[0-9]{2}\"}[$__rate_interval])) by (route)\n/\nsum(rate(loki_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(loki|enterprise-logs)-write\"}[$__rate_interval])) by (route) > 0",
|
||||
"interval": "",
|
||||
"intervalFactor": 1,
|
||||
"legendFormat": "{{route}}",
|
||||
@@ -2190,9 +2189,9 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(rate(loki_distributor_ingester_append_failures_total{cluster=\"$cluster\", namespace=\"$namespace\"}[5m])) by (ingester)",
|
||||
"expr": "sum(rate(loki_distributor_ingester_append_failures_total{cluster=\"$cluster\", namespace=\"$namespace\"}[5m])) by (pod)",
|
||||
"intervalFactor": 1,
|
||||
"legendFormat": "{{ingester}}",
|
||||
"legendFormat": "{{pod}}",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
@@ -3256,7 +3255,7 @@
|
||||
"panels": [ ],
|
||||
"targets": [
|
||||
{
|
||||
"expr": "{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(loki|enterprise-logs)-read\"} | logfmt | level=\"error\"",
|
||||
"expr": "{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(loki|enterprise-logs)-read\"} |= \"level=error\"",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
@@ -3307,7 +3306,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(rate(loki_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(loki|enterprise-logs)-read\", status_code!~\"5[0-9]{2}\"}[1m])) by (route)\n/\nsum(rate(loki_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(loki|enterprise-logs)-read\"}[1m])) by (route)",
|
||||
"expr": "sum(rate(loki_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(loki|enterprise-logs)-read\", status_code!~\"5[0-9]{2}\"}[$__rate_interval])) by (route)\n/\nsum(rate(loki_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(loki|enterprise-logs)-read\"}[$__rate_interval])) by (route) > 0",
|
||||
"interval": "",
|
||||
"intervalFactor": 1,
|
||||
"legendFormat": "{{route}}",
|
||||
|
||||
@@ -53,6 +53,11 @@
|
||||
"points": false,
|
||||
"renderer": "flot",
|
||||
"seriesOverrides": [
|
||||
{
|
||||
"alias": "request",
|
||||
"color": "#FFC000",
|
||||
"fill": 0
|
||||
},
|
||||
{
|
||||
"alias": "limit",
|
||||
"color": "#E02F44",
|
||||
@@ -72,6 +77,14 @@
|
||||
"legendLink": null,
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\", container=\"loki\", pod=~\"(loki|enterprise-logs)-read.*\", resource=\"cpu\"} > 0)",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "request",
|
||||
"legendLink": null,
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"expr": "min(container_spec_cpu_quota{cluster=~\"$cluster\", namespace=~\"$namespace\", container=\"loki\", pod=~\"(loki|enterprise-logs)-read.*\"} / container_spec_cpu_period{cluster=~\"$cluster\", namespace=~\"$namespace\", container=\"loki\", pod=~\"(loki|enterprise-logs)-read.*\"})",
|
||||
"format": "time_series",
|
||||
@@ -142,6 +155,11 @@
|
||||
"points": false,
|
||||
"renderer": "flot",
|
||||
"seriesOverrides": [
|
||||
{
|
||||
"alias": "request",
|
||||
"color": "#FFC000",
|
||||
"fill": 0
|
||||
},
|
||||
{
|
||||
"alias": "limit",
|
||||
"color": "#E02F44",
|
||||
@@ -161,6 +179,14 @@
|
||||
"legendLink": null,
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\", container=\"loki\", pod=~\"(loki|enterprise-logs)-read.*\", resource=\"memory\"} > 0)",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "request",
|
||||
"legendLink": null,
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"expr": "min(container_spec_memory_limit_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\", container=\"loki\", pod=~\"(loki|enterprise-logs)-read.*\"} > 0)",
|
||||
"format": "time_series",
|
||||
@@ -509,83 +535,6 @@
|
||||
"show": false
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"aliasColors": { },
|
||||
"bars": false,
|
||||
"dashLength": 10,
|
||||
"dashes": false,
|
||||
"datasource": "$datasource",
|
||||
"fill": 1,
|
||||
"gridPos": { },
|
||||
"id": 7,
|
||||
"legend": {
|
||||
"avg": false,
|
||||
"current": false,
|
||||
"max": false,
|
||||
"min": false,
|
||||
"show": true,
|
||||
"total": false,
|
||||
"values": false
|
||||
},
|
||||
"lines": true,
|
||||
"linewidth": 1,
|
||||
"links": [ ],
|
||||
"nullPointMode": "null as zero",
|
||||
"percentage": false,
|
||||
"pointradius": 5,
|
||||
"points": false,
|
||||
"renderer": "flot",
|
||||
"seriesOverrides": [ ],
|
||||
"spaceLength": 10,
|
||||
"span": 6,
|
||||
"stack": false,
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "loki_boltdb_shipper_query_readiness_duration_seconds{cluster=~\"$cluster\", namespace=~\"$namespace\"}",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "duration",
|
||||
"legendLink": null,
|
||||
"step": 10
|
||||
}
|
||||
],
|
||||
"thresholds": [ ],
|
||||
"timeFrom": null,
|
||||
"timeShift": null,
|
||||
"title": "Query Readiness Duration",
|
||||
"tooltip": {
|
||||
"shared": true,
|
||||
"sort": 2,
|
||||
"value_type": "individual"
|
||||
},
|
||||
"type": "graph",
|
||||
"xaxis": {
|
||||
"buckets": null,
|
||||
"mode": "time",
|
||||
"name": null,
|
||||
"show": true,
|
||||
"values": [ ]
|
||||
},
|
||||
"yaxes": [
|
||||
{
|
||||
"format": "s",
|
||||
"label": null,
|
||||
"logBase": 1,
|
||||
"max": null,
|
||||
"min": 0,
|
||||
"show": true
|
||||
},
|
||||
{
|
||||
"format": "short",
|
||||
"label": null,
|
||||
"logBase": 1,
|
||||
"max": null,
|
||||
"min": null,
|
||||
"show": false
|
||||
}
|
||||
]
|
||||
}
|
||||
],
|
||||
"repeat": null,
|
||||
@@ -607,7 +556,7 @@
|
||||
"dashes": false,
|
||||
"datasource": "$datasource",
|
||||
"fill": 1,
|
||||
"id": 8,
|
||||
"id": 7,
|
||||
"legend": {
|
||||
"avg": false,
|
||||
"current": false,
|
||||
@@ -626,6 +575,11 @@
|
||||
"points": false,
|
||||
"renderer": "flot",
|
||||
"seriesOverrides": [
|
||||
{
|
||||
"alias": "request",
|
||||
"color": "#FFC000",
|
||||
"fill": 0
|
||||
},
|
||||
{
|
||||
"alias": "limit",
|
||||
"color": "#E02F44",
|
||||
@@ -645,6 +599,14 @@
|
||||
"legendLink": null,
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\", container=\"loki\", pod=~\"(loki|enterprise-logs)-write.*\", resource=\"cpu\"} > 0)",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "request",
|
||||
"legendLink": null,
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"expr": "min(container_spec_cpu_quota{cluster=~\"$cluster\", namespace=~\"$namespace\", container=\"loki\", pod=~\"(loki|enterprise-logs)-write.*\"} / container_spec_cpu_period{cluster=~\"$cluster\", namespace=~\"$namespace\", container=\"loki\", pod=~\"(loki|enterprise-logs)-write.*\"})",
|
||||
"format": "time_series",
|
||||
@@ -695,7 +657,7 @@
|
||||
"dashes": false,
|
||||
"datasource": "$datasource",
|
||||
"fill": 1,
|
||||
"id": 9,
|
||||
"id": 8,
|
||||
"legend": {
|
||||
"avg": false,
|
||||
"current": false,
|
||||
@@ -714,6 +676,11 @@
|
||||
"points": false,
|
||||
"renderer": "flot",
|
||||
"seriesOverrides": [
|
||||
{
|
||||
"alias": "request",
|
||||
"color": "#FFC000",
|
||||
"fill": 0
|
||||
},
|
||||
{
|
||||
"alias": "limit",
|
||||
"color": "#E02F44",
|
||||
@@ -733,6 +700,14 @@
|
||||
"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,
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"expr": "min(container_spec_memory_limit_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\", container=\"loki\", pod=~\"(loki|enterprise-logs)-write.*\"} > 0)",
|
||||
"format": "time_series",
|
||||
@@ -783,7 +758,7 @@
|
||||
"dashes": false,
|
||||
"datasource": "$datasource",
|
||||
"fill": 1,
|
||||
"id": 10,
|
||||
"id": 9,
|
||||
"legend": {
|
||||
"avg": false,
|
||||
"current": false,
|
||||
|
||||
@@ -142,7 +142,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "histogram_quantile(0.99, sum by (le,route) (job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-read\", route=~\"loki_api_v1_series|api_prom_series|api_prom_query|api_prom_label|api_prom_label_name_values|loki_api_v1_query|loki_api_v1_query_range|loki_api_v1_labels|loki_api_v1_label_name_values\", cluster=~\"$cluster\"})) * 1e3",
|
||||
"expr": "histogram_quantile(0.99, sum by (le,route) (cluster_job_route:loki_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/(loki|enterprise-logs)-read\", route=~\"loki_api_v1_series|api_prom_series|api_prom_query|api_prom_label|api_prom_label_name_values|loki_api_v1_query|loki_api_v1_query_range|loki_api_v1_labels|loki_api_v1_label_name_values\"})) * 1e3",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{ route }} 99th Percentile",
|
||||
@@ -150,7 +150,7 @@
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"expr": "histogram_quantile(0.50, sum by (le,route) (job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-read\", route=~\"loki_api_v1_series|api_prom_series|api_prom_query|api_prom_label|api_prom_label_name_values|loki_api_v1_query|loki_api_v1_query_range|loki_api_v1_labels|loki_api_v1_label_name_values\", cluster=~\"$cluster\"})) * 1e3",
|
||||
"expr": "histogram_quantile(0.50, sum by (le,route) (cluster_job_route:loki_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/(loki|enterprise-logs)-read\", route=~\"loki_api_v1_series|api_prom_series|api_prom_query|api_prom_label|api_prom_label_name_values|loki_api_v1_query|loki_api_v1_query_range|loki_api_v1_labels|loki_api_v1_label_name_values\"})) * 1e3",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{ route }} 50th Percentile",
|
||||
@@ -158,7 +158,7 @@
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"expr": "1e3 * sum(job_route:loki_request_duration_seconds_sum:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-read\", route=~\"loki_api_v1_series|api_prom_series|api_prom_query|api_prom_label|api_prom_label_name_values|loki_api_v1_query|loki_api_v1_query_range|loki_api_v1_labels|loki_api_v1_label_name_values\", cluster=~\"$cluster\"}) by (route) / sum(job_route:loki_request_duration_seconds_count:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-read\", route=~\"loki_api_v1_series|api_prom_series|api_prom_query|api_prom_label|api_prom_label_name_values|loki_api_v1_query|loki_api_v1_query_range|loki_api_v1_labels|loki_api_v1_label_name_values\", cluster=~\"$cluster\"}) by (route) ",
|
||||
"expr": "1e3 * sum(cluster_job_route:loki_request_duration_seconds_sum:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/(loki|enterprise-logs)-read\", route=~\"loki_api_v1_series|api_prom_series|api_prom_query|api_prom_label|api_prom_label_name_values|loki_api_v1_query|loki_api_v1_query_range|loki_api_v1_labels|loki_api_v1_label_name_values\"}) by (route) / sum(cluster_job_route:loki_request_duration_seconds_count:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/(loki|enterprise-logs)-read\", route=~\"loki_api_v1_series|api_prom_series|api_prom_query|api_prom_label|api_prom_label_name_values|loki_api_v1_query|loki_api_v1_query_range|loki_api_v1_labels|loki_api_v1_label_name_values\"}) by (route) ",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{ route }} Average",
|
||||
|
||||
@@ -52,6 +52,11 @@
|
||||
"points": false,
|
||||
"renderer": "flot",
|
||||
"seriesOverrides": [
|
||||
{
|
||||
"alias": "request",
|
||||
"color": "#FFC000",
|
||||
"fill": 0
|
||||
},
|
||||
{
|
||||
"alias": "limit",
|
||||
"color": "#E02F44",
|
||||
@@ -71,6 +76,14 @@
|
||||
"legendLink": null,
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\", container=\"loki\", pod=~\"(loki|enterprise-logs)-read.*\", resource=\"cpu\"} > 0)",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "request",
|
||||
"legendLink": null,
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"expr": "min(container_spec_cpu_quota{cluster=~\"$cluster\", namespace=~\"$namespace\", container=\"loki\", pod=~\"(loki|enterprise-logs)-read.*\"} / container_spec_cpu_period{cluster=~\"$cluster\", namespace=~\"$namespace\", container=\"loki\", pod=~\"(loki|enterprise-logs)-read.*\"})",
|
||||
"format": "time_series",
|
||||
@@ -140,6 +153,11 @@
|
||||
"points": false,
|
||||
"renderer": "flot",
|
||||
"seriesOverrides": [
|
||||
{
|
||||
"alias": "request",
|
||||
"color": "#FFC000",
|
||||
"fill": 0
|
||||
},
|
||||
{
|
||||
"alias": "limit",
|
||||
"color": "#E02F44",
|
||||
@@ -159,6 +177,14 @@
|
||||
"legendLink": null,
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\", container=\"loki\", pod=~\"(loki|enterprise-logs)-read.*\", resource=\"memory\"} > 0)",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "request",
|
||||
"legendLink": null,
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"expr": "min(container_spec_memory_limit_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\", container=\"loki\", pod=~\"(loki|enterprise-logs)-read.*\"} > 0)",
|
||||
"format": "time_series",
|
||||
@@ -1534,4 +1560,4 @@
|
||||
"title": "Loki / Retention",
|
||||
"uid": "retention",
|
||||
"version": 0
|
||||
}
|
||||
}
|
||||
|
||||
@@ -128,6 +128,11 @@
|
||||
"points": false,
|
||||
"renderer": "flot",
|
||||
"seriesOverrides": [
|
||||
{
|
||||
"alias": "request",
|
||||
"color": "#FFC000",
|
||||
"fill": 0
|
||||
},
|
||||
{
|
||||
"alias": "limit",
|
||||
"color": "#E02F44",
|
||||
@@ -147,6 +152,14 @@
|
||||
"legendLink": null,
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\", container=\"loki\", pod=~\"(loki|enterprise-logs)-write.*\", resource=\"cpu\"} > 0)",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "request",
|
||||
"legendLink": null,
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"expr": "min(container_spec_cpu_quota{cluster=~\"$cluster\", namespace=~\"$namespace\", container=\"loki\", pod=~\"(loki|enterprise-logs)-write.*\"} / container_spec_cpu_period{cluster=~\"$cluster\", namespace=~\"$namespace\", container=\"loki\", pod=~\"(loki|enterprise-logs)-write.*\"})",
|
||||
"format": "time_series",
|
||||
@@ -217,6 +230,11 @@
|
||||
"points": false,
|
||||
"renderer": "flot",
|
||||
"seriesOverrides": [
|
||||
{
|
||||
"alias": "request",
|
||||
"color": "#FFC000",
|
||||
"fill": 0
|
||||
},
|
||||
{
|
||||
"alias": "limit",
|
||||
"color": "#E02F44",
|
||||
@@ -236,6 +254,14 @@
|
||||
"legendLink": null,
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\", container=\"loki\", pod=~\"(loki|enterprise-logs)-write.*\", resource=\"memory\"} > 0)",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "request",
|
||||
"legendLink": null,
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"expr": "min(container_spec_memory_limit_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\", container=\"loki\", pod=~\"(loki|enterprise-logs)-write.*\"} > 0)",
|
||||
"format": "time_series",
|
||||
|
||||
@@ -142,7 +142,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "histogram_quantile(0.99, sum by (le) (job:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-write\", cluster=~\"$cluster\"})) * 1e3",
|
||||
"expr": "histogram_quantile(0.99, sum by (le) (cluster_job:loki_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/(loki|enterprise-logs)-write\"})) * 1e3",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "99th Percentile",
|
||||
@@ -150,7 +150,7 @@
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"expr": "histogram_quantile(0.50, sum by (le) (job:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-write\", cluster=~\"$cluster\"})) * 1e3",
|
||||
"expr": "histogram_quantile(0.50, sum by (le) (cluster_job:loki_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/(loki|enterprise-logs)-write\"})) * 1e3",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "50th Percentile",
|
||||
@@ -158,7 +158,7 @@
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"expr": "1e3 * sum(job:loki_request_duration_seconds_sum:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-write\", cluster=~\"$cluster\"}) / sum(job:loki_request_duration_seconds_count:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-write\", cluster=~\"$cluster\"})",
|
||||
"expr": "1e3 * sum(cluster_job:loki_request_duration_seconds_sum:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/(loki|enterprise-logs)-write\"}) / sum(cluster_job:loki_request_duration_seconds_count:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/(loki|enterprise-logs)-write\"})",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "Average",
|
||||
|
||||
@@ -67,7 +67,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(cluster_job_pod:cortex_alertmanager_alerts:sum{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"})",
|
||||
"expr": "sum(cluster_job_pod:cortex_alertmanager_alerts:sum{cluster=~\"$cluster\", job=~\"($namespace)/((.*alertmanager|cortex|mimir|mimir-backend.*))\"})",
|
||||
"format": "time_series",
|
||||
"instant": true,
|
||||
"intervalFactor": 2,
|
||||
@@ -143,7 +143,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(cluster_job_pod:cortex_alertmanager_silences:sum{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"})",
|
||||
"expr": "sum(cluster_job_pod:cortex_alertmanager_silences:sum{cluster=~\"$cluster\", job=~\"($namespace)/((.*alertmanager|cortex|mimir|mimir-backend.*))\"})",
|
||||
"format": "time_series",
|
||||
"instant": true,
|
||||
"intervalFactor": 2,
|
||||
@@ -219,7 +219,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "max(cortex_alertmanager_tenants_discovered{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"})",
|
||||
"expr": "max(cortex_alertmanager_tenants_discovered{cluster=~\"$cluster\", job=~\"($namespace)/((.*alertmanager|cortex|mimir|mimir-backend.*))\"})",
|
||||
"format": "time_series",
|
||||
"instant": true,
|
||||
"intervalFactor": 2,
|
||||
@@ -315,7 +315,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\", route=~\"/alertmanagerpb.Alertmanager/HandleRequest\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-z]+)\"))\n",
|
||||
"expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*alertmanager|cortex|mimir|mimir-backend.*))\", route=~\"/alertmanagerpb.Alertmanager/HandleRequest\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-z]+)\"))\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{status}}",
|
||||
@@ -390,7 +390,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "histogram_quantile(0.99, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\", route=~\"/alertmanagerpb.Alertmanager/HandleRequest\"})) * 1e3",
|
||||
"expr": "histogram_quantile(0.99, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((.*alertmanager|cortex|mimir|mimir-backend.*))\", route=~\"/alertmanagerpb.Alertmanager/HandleRequest\"})) * 1e3",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "99th Percentile",
|
||||
@@ -398,7 +398,7 @@
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"expr": "histogram_quantile(0.50, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\", route=~\"/alertmanagerpb.Alertmanager/HandleRequest\"})) * 1e3",
|
||||
"expr": "histogram_quantile(0.50, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((.*alertmanager|cortex|mimir|mimir-backend.*))\", route=~\"/alertmanagerpb.Alertmanager/HandleRequest\"})) * 1e3",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "50th Percentile",
|
||||
@@ -406,7 +406,7 @@
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"expr": "1e3 * sum(cluster_job_route:cortex_request_duration_seconds_sum:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\", route=~\"/alertmanagerpb.Alertmanager/HandleRequest\"}) / sum(cluster_job_route:cortex_request_duration_seconds_count:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\", route=~\"/alertmanagerpb.Alertmanager/HandleRequest\"})",
|
||||
"expr": "1e3 * sum(cluster_job_route:cortex_request_duration_seconds_sum:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((.*alertmanager|cortex|mimir|mimir-backend.*))\", route=~\"/alertmanagerpb.Alertmanager/HandleRequest\"}) / sum(cluster_job_route:cortex_request_duration_seconds_count:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((.*alertmanager|cortex|mimir|mimir-backend.*))\", route=~\"/alertmanagerpb.Alertmanager/HandleRequest\"})",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "Average",
|
||||
@@ -497,14 +497,14 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(cluster_job:cortex_alertmanager_alerts_received_total:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"})\n-\nsum(cluster_job:cortex_alertmanager_alerts_invalid_total:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"})\n",
|
||||
"expr": "sum(cluster_job:cortex_alertmanager_alerts_received_total:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((.*alertmanager|cortex|mimir|mimir-backend.*))\"})\n-\nsum(cluster_job:cortex_alertmanager_alerts_invalid_total:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((.*alertmanager|cortex|mimir|mimir-backend.*))\"})\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "successful",
|
||||
"legendLink": null
|
||||
},
|
||||
{
|
||||
"expr": "sum(cluster_job:cortex_alertmanager_alerts_invalid_total:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"})",
|
||||
"expr": "sum(cluster_job:cortex_alertmanager_alerts_invalid_total:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((.*alertmanager|cortex|mimir|mimir-backend.*))\"})",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "failed",
|
||||
@@ -591,7 +591,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "cortex_alertmanager_dispatcher_aggregation_groups{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"}",
|
||||
"expr": "cortex_alertmanager_dispatcher_aggregation_groups{cluster=~\"$cluster\", job=~\"($namespace)/((.*alertmanager|cortex|mimir|mimir-backend.*))\"}",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{pod}}",
|
||||
@@ -681,14 +681,14 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(cluster_job_integration:cortex_alertmanager_notifications_total:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"})\n-\nsum(cluster_job_integration:cortex_alertmanager_notifications_failed_total:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"})\n",
|
||||
"expr": "sum(cluster_job_integration:cortex_alertmanager_notifications_total:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((.*alertmanager|cortex|mimir|mimir-backend.*))\"})\n-\nsum(cluster_job_integration:cortex_alertmanager_notifications_failed_total:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((.*alertmanager|cortex|mimir|mimir-backend.*))\"})\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "successful",
|
||||
"legendLink": null
|
||||
},
|
||||
{
|
||||
"expr": "sum(cluster_job_integration:cortex_alertmanager_notifications_failed_total:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"})\n",
|
||||
"expr": "sum(cluster_job_integration:cortex_alertmanager_notifications_failed_total:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((.*alertmanager|cortex|mimir|mimir-backend.*))\"})\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "failed",
|
||||
@@ -763,14 +763,14 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "(\nsum(cluster_job_integration:cortex_alertmanager_notifications_total:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"}) by(integration)\n-\nsum(cluster_job_integration:cortex_alertmanager_notifications_failed_total:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"}) by(integration)\n) > 0\nor on () vector(0)\n",
|
||||
"expr": "(\nsum(cluster_job_integration:cortex_alertmanager_notifications_total:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((.*alertmanager|cortex|mimir|mimir-backend.*))\"}) by(integration)\n-\nsum(cluster_job_integration:cortex_alertmanager_notifications_failed_total:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((.*alertmanager|cortex|mimir|mimir-backend.*))\"}) by(integration)\n) > 0\nor on () vector(0)\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "success - {{ integration }}",
|
||||
"legendLink": null
|
||||
},
|
||||
{
|
||||
"expr": "sum(cluster_job_integration:cortex_alertmanager_notifications_failed_total:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"}) by(integration)",
|
||||
"expr": "sum(cluster_job_integration:cortex_alertmanager_notifications_failed_total:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((.*alertmanager|cortex|mimir|mimir-backend.*))\"}) by(integration)",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "failed - {{ integration }}",
|
||||
@@ -845,21 +845,21 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "histogram_quantile(0.99, sum(rate(cortex_alertmanager_notification_latency_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) by (le)) * 1e3",
|
||||
"expr": "histogram_quantile(0.99, sum(rate(cortex_alertmanager_notification_latency_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) by (le)) * 1e3",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "99th Percentile",
|
||||
"refId": "A"
|
||||
},
|
||||
{
|
||||
"expr": "histogram_quantile(0.50, sum(rate(cortex_alertmanager_notification_latency_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) by (le)) * 1e3",
|
||||
"expr": "histogram_quantile(0.50, sum(rate(cortex_alertmanager_notification_latency_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) by (le)) * 1e3",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "50th Percentile",
|
||||
"refId": "B"
|
||||
},
|
||||
{
|
||||
"expr": "sum(rate(cortex_alertmanager_notification_latency_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) * 1e3 / sum(rate(cortex_alertmanager_notification_latency_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))",
|
||||
"expr": "sum(rate(cortex_alertmanager_notification_latency_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((.*alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) * 1e3 / sum(rate(cortex_alertmanager_notification_latency_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "Average",
|
||||
@@ -1613,7 +1613,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "max by(pod) (cortex_alertmanager_tenants_owned{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"})",
|
||||
"expr": "max by(pod) (cortex_alertmanager_tenants_owned{cluster=~\"$cluster\", job=~\"($namespace)/((.*alertmanager|cortex|mimir|mimir-backend.*))\"})",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{pod}}",
|
||||
@@ -1688,7 +1688,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum by(pod) (cluster_job_pod:cortex_alertmanager_alerts:sum{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"})",
|
||||
"expr": "sum by(pod) (cluster_job_pod:cortex_alertmanager_alerts:sum{cluster=~\"$cluster\", job=~\"($namespace)/((.*alertmanager|cortex|mimir|mimir-backend.*))\"})",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{pod}}",
|
||||
@@ -1763,7 +1763,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum by(pod) (cluster_job_pod:cortex_alertmanager_silences:sum{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"})",
|
||||
"expr": "sum by(pod) (cluster_job_pod:cortex_alertmanager_silences:sum{cluster=~\"$cluster\", job=~\"($namespace)/((.*alertmanager|cortex|mimir|mimir-backend.*))\"})",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{pod}}",
|
||||
@@ -1853,14 +1853,14 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(rate(cortex_alertmanager_sync_configs_total{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n-\nsum(rate(cortex_alertmanager_sync_configs_failed_total{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n",
|
||||
"expr": "sum(rate(cortex_alertmanager_sync_configs_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n-\nsum(rate(cortex_alertmanager_sync_configs_failed_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "successful",
|
||||
"legendLink": null
|
||||
},
|
||||
{
|
||||
"expr": "sum(rate(cortex_alertmanager_sync_configs_failed_total{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))",
|
||||
"expr": "sum(rate(cortex_alertmanager_sync_configs_failed_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "failed",
|
||||
@@ -1935,7 +1935,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum by(reason) (rate(cortex_alertmanager_sync_configs_total{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))",
|
||||
"expr": "sum by(reason) (rate(cortex_alertmanager_sync_configs_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{reason}}",
|
||||
@@ -2010,7 +2010,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum (rate(cortex_alertmanager_ring_check_errors_total{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))",
|
||||
"expr": "sum (rate(cortex_alertmanager_ring_check_errors_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "errors",
|
||||
@@ -2097,7 +2097,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum by(outcome) (rate(cortex_alertmanager_state_initial_sync_completed_total{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))",
|
||||
"expr": "sum by(outcome) (rate(cortex_alertmanager_state_initial_sync_completed_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))",
|
||||
"format": "time_series",
|
||||
"interval": "1m",
|
||||
"intervalFactor": 2,
|
||||
@@ -2173,7 +2173,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "histogram_quantile(0.99, sum(rate(cortex_alertmanager_state_initial_sync_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) by (le)) * 1e3",
|
||||
"expr": "histogram_quantile(0.99, sum(rate(cortex_alertmanager_state_initial_sync_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) by (le)) * 1e3",
|
||||
"format": "time_series",
|
||||
"interval": "1m",
|
||||
"intervalFactor": 2,
|
||||
@@ -2181,7 +2181,7 @@
|
||||
"refId": "A"
|
||||
},
|
||||
{
|
||||
"expr": "histogram_quantile(0.50, sum(rate(cortex_alertmanager_state_initial_sync_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) by (le)) * 1e3",
|
||||
"expr": "histogram_quantile(0.50, sum(rate(cortex_alertmanager_state_initial_sync_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) by (le)) * 1e3",
|
||||
"format": "time_series",
|
||||
"interval": "1m",
|
||||
"intervalFactor": 2,
|
||||
@@ -2189,7 +2189,7 @@
|
||||
"refId": "B"
|
||||
},
|
||||
{
|
||||
"expr": "sum(rate(cortex_alertmanager_state_initial_sync_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) * 1e3 / sum(rate(cortex_alertmanager_state_initial_sync_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))",
|
||||
"expr": "sum(rate(cortex_alertmanager_state_initial_sync_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((.*alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) * 1e3 / sum(rate(cortex_alertmanager_state_initial_sync_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))",
|
||||
"format": "time_series",
|
||||
"interval": "1m",
|
||||
"intervalFactor": 2,
|
||||
@@ -2268,7 +2268,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(rate(cortex_alertmanager_state_fetch_replica_state_total{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n-\nsum(rate(cortex_alertmanager_state_fetch_replica_state_failed_total{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n",
|
||||
"expr": "sum(rate(cortex_alertmanager_state_fetch_replica_state_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n-\nsum(rate(cortex_alertmanager_state_fetch_replica_state_failed_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n",
|
||||
"format": "time_series",
|
||||
"interval": "1m",
|
||||
"intervalFactor": 2,
|
||||
@@ -2276,7 +2276,7 @@
|
||||
"legendLink": null
|
||||
},
|
||||
{
|
||||
"expr": "sum(rate(cortex_alertmanager_state_fetch_replica_state_failed_total{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))",
|
||||
"expr": "sum(rate(cortex_alertmanager_state_fetch_replica_state_failed_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))",
|
||||
"format": "time_series",
|
||||
"interval": "1m",
|
||||
"intervalFactor": 2,
|
||||
@@ -2367,14 +2367,14 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(cluster_job:cortex_alertmanager_state_replication_total:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"})\n-\nsum(cluster_job:cortex_alertmanager_state_replication_failed_total:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"})\n",
|
||||
"expr": "sum(cluster_job:cortex_alertmanager_state_replication_total:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((.*alertmanager|cortex|mimir|mimir-backend.*))\"})\n-\nsum(cluster_job:cortex_alertmanager_state_replication_failed_total:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((.*alertmanager|cortex|mimir|mimir-backend.*))\"})\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "successful",
|
||||
"legendLink": null
|
||||
},
|
||||
{
|
||||
"expr": "sum(cluster_job:cortex_alertmanager_state_replication_failed_total:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"})",
|
||||
"expr": "sum(cluster_job:cortex_alertmanager_state_replication_failed_total:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((.*alertmanager|cortex|mimir|mimir-backend.*))\"})",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "failed",
|
||||
@@ -2452,14 +2452,14 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(cluster_job:cortex_alertmanager_partial_state_merges_total:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"})\n-\nsum(cluster_job:cortex_alertmanager_partial_state_merges_failed_total:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"})\n",
|
||||
"expr": "sum(cluster_job:cortex_alertmanager_partial_state_merges_total:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((.*alertmanager|cortex|mimir|mimir-backend.*))\"})\n-\nsum(cluster_job:cortex_alertmanager_partial_state_merges_failed_total:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((.*alertmanager|cortex|mimir|mimir-backend.*))\"})\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "successful",
|
||||
"legendLink": null
|
||||
},
|
||||
{
|
||||
"expr": "sum(cluster_job:cortex_alertmanager_partial_state_merges_failed_total:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"})",
|
||||
"expr": "sum(cluster_job:cortex_alertmanager_partial_state_merges_failed_total:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((.*alertmanager|cortex|mimir|mimir-backend.*))\"})",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "failed",
|
||||
@@ -2537,14 +2537,14 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(rate(cortex_alertmanager_state_persist_total{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n-\nsum(rate(cortex_alertmanager_state_persist_failed_total{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n",
|
||||
"expr": "sum(rate(cortex_alertmanager_state_persist_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n-\nsum(rate(cortex_alertmanager_state_persist_failed_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "successful",
|
||||
"legendLink": null
|
||||
},
|
||||
{
|
||||
"expr": "sum(rate(cortex_alertmanager_state_persist_failed_total{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))",
|
||||
"expr": "sum(rate(cortex_alertmanager_state_persist_failed_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "failed",
|
||||
|
||||
@@ -71,21 +71,21 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(rate(cortex_compactor_runs_started_total{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))",
|
||||
"expr": "sum(rate(cortex_compactor_runs_started_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "started",
|
||||
"legendLink": null
|
||||
},
|
||||
{
|
||||
"expr": "sum(rate(cortex_compactor_runs_completed_total{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))",
|
||||
"expr": "sum(rate(cortex_compactor_runs_completed_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "completed",
|
||||
"legendLink": null
|
||||
},
|
||||
{
|
||||
"expr": "sum(rate(cortex_compactor_runs_failed_total{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))",
|
||||
"expr": "sum(rate(cortex_compactor_runs_failed_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "failed",
|
||||
@@ -152,7 +152,7 @@
|
||||
"span": 3,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "(\n cortex_compactor_tenants_processing_succeeded{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"} +\n cortex_compactor_tenants_processing_failed{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"} +\n cortex_compactor_tenants_skipped{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"}\n)\n/\ncortex_compactor_tenants_discovered{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"} > 0\n",
|
||||
"expr": "(\n cortex_compactor_tenants_processing_succeeded{cluster=~\"$cluster\", job=~\"($namespace)/((.*compactor.*|cortex|mimir|mimir-backend.*))\"} +\n cortex_compactor_tenants_processing_failed{cluster=~\"$cluster\", job=~\"($namespace)/((.*compactor.*|cortex|mimir|mimir-backend.*))\"} +\n cortex_compactor_tenants_skipped{cluster=~\"$cluster\", job=~\"($namespace)/((.*compactor.*|cortex|mimir|mimir-backend.*))\"}\n)\n/\ncortex_compactor_tenants_discovered{cluster=~\"$cluster\", job=~\"($namespace)/((.*compactor.*|cortex|mimir|mimir-backend.*))\"} > 0\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{pod}}",
|
||||
@@ -279,7 +279,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "max by(pod)\n(\n (time() * (max_over_time(cortex_compactor_last_successful_run_timestamp_seconds{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"}[1h]) !=bool 0))\n -\n max_over_time(cortex_compactor_last_successful_run_timestamp_seconds{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"}[1h])\n)\n",
|
||||
"expr": "max by(pod)\n(\n (time() * (max_over_time(cortex_compactor_last_successful_run_timestamp_seconds{cluster=~\"$cluster\", job=~\"($namespace)/((.*compactor.*|cortex|mimir|mimir-backend.*))\"}[1h]) !=bool 0))\n -\n max_over_time(cortex_compactor_last_successful_run_timestamp_seconds{cluster=~\"$cluster\", job=~\"($namespace)/((.*compactor.*|cortex|mimir|mimir-backend.*))\"}[1h])\n)\n",
|
||||
"format": "table",
|
||||
"instant": true,
|
||||
"interval": "",
|
||||
@@ -505,7 +505,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "max by(pod)\n(\n (time() * (max_over_time(cortex_compactor_last_successful_run_timestamp_seconds{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"}[1h]) !=bool 0))\n -\n max_over_time(cortex_compactor_last_successful_run_timestamp_seconds{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"}[1h])\n)\n",
|
||||
"expr": "max by(pod)\n(\n (time() * (max_over_time(cortex_compactor_last_successful_run_timestamp_seconds{cluster=~\"$cluster\", job=~\"($namespace)/((.*compactor.*|cortex|mimir|mimir-backend.*))\"}[1h]) !=bool 0))\n -\n max_over_time(cortex_compactor_last_successful_run_timestamp_seconds{cluster=~\"$cluster\", job=~\"($namespace)/((.*compactor.*|cortex|mimir|mimir-backend.*))\"}[1h])\n)\n",
|
||||
"format": "table",
|
||||
"instant": true,
|
||||
"intervalFactor": 2,
|
||||
@@ -654,7 +654,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(rate(prometheus_tsdb_compactions_total{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))",
|
||||
"expr": "sum(rate(prometheus_tsdb_compactions_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "compactions",
|
||||
@@ -730,21 +730,21 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "histogram_quantile(0.99, sum(rate(prometheus_tsdb_compaction_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) by (le)) * 1e3",
|
||||
"expr": "histogram_quantile(0.99, sum(rate(prometheus_tsdb_compaction_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) by (le)) * 1e3",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "99th Percentile",
|
||||
"refId": "A"
|
||||
},
|
||||
{
|
||||
"expr": "histogram_quantile(0.50, sum(rate(prometheus_tsdb_compaction_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) by (le)) * 1e3",
|
||||
"expr": "histogram_quantile(0.50, sum(rate(prometheus_tsdb_compaction_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) by (le)) * 1e3",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "50th Percentile",
|
||||
"refId": "B"
|
||||
},
|
||||
{
|
||||
"expr": "sum(rate(prometheus_tsdb_compaction_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) * 1e3 / sum(rate(prometheus_tsdb_compaction_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))",
|
||||
"expr": "sum(rate(prometheus_tsdb_compaction_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((.*compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) * 1e3 / sum(rate(prometheus_tsdb_compaction_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "Average",
|
||||
@@ -831,7 +831,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "avg(max by(user) (cortex_bucket_blocks_count{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"}))",
|
||||
"expr": "avg(max by(user) (cortex_bucket_blocks_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*compactor.*|cortex|mimir|mimir-backend.*))\"}))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "avg",
|
||||
@@ -907,7 +907,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "topk(10, max by(user) (cortex_bucket_blocks_count{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"}))",
|
||||
"expr": "topk(10, max by(user) (cortex_bucket_blocks_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*compactor.*|cortex|mimir|mimir-backend.*))\"}))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{user}}",
|
||||
@@ -994,7 +994,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(rate(cortex_compactor_blocks_marked_for_deletion_total{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n",
|
||||
"expr": "sum(rate(cortex_compactor_blocks_marked_for_deletion_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "blocks",
|
||||
@@ -1072,14 +1072,14 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(rate(cortex_compactor_blocks_cleaned_total{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n",
|
||||
"expr": "sum(rate(cortex_compactor_blocks_cleaned_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "successful",
|
||||
"legendLink": null
|
||||
},
|
||||
{
|
||||
"expr": "sum(rate(cortex_compactor_block_cleanup_failures_total{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n",
|
||||
"expr": "sum(rate(cortex_compactor_block_cleanup_failures_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "failed",
|
||||
@@ -1169,14 +1169,14 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(rate(cortex_compactor_meta_syncs_total{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n-\nsum(rate(cortex_compactor_meta_sync_failures_total{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n",
|
||||
"expr": "sum(rate(cortex_compactor_meta_syncs_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n-\nsum(rate(cortex_compactor_meta_sync_failures_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "successful",
|
||||
"legendLink": null
|
||||
},
|
||||
{
|
||||
"expr": "sum(rate(cortex_compactor_meta_sync_failures_total{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n",
|
||||
"expr": "sum(rate(cortex_compactor_meta_sync_failures_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "failed",
|
||||
@@ -1251,21 +1251,21 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "histogram_quantile(0.99, sum(rate(cortex_compactor_meta_sync_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) by (le)) * 1e3",
|
||||
"expr": "histogram_quantile(0.99, sum(rate(cortex_compactor_meta_sync_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) by (le)) * 1e3",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "99th Percentile",
|
||||
"refId": "A"
|
||||
},
|
||||
{
|
||||
"expr": "histogram_quantile(0.50, sum(rate(cortex_compactor_meta_sync_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) by (le)) * 1e3",
|
||||
"expr": "histogram_quantile(0.50, sum(rate(cortex_compactor_meta_sync_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) by (le)) * 1e3",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "50th Percentile",
|
||||
"refId": "B"
|
||||
},
|
||||
{
|
||||
"expr": "sum(rate(cortex_compactor_meta_sync_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) * 1e3 / sum(rate(cortex_compactor_meta_sync_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))",
|
||||
"expr": "sum(rate(cortex_compactor_meta_sync_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((.*compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) * 1e3 / sum(rate(cortex_compactor_meta_sync_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "Average",
|
||||
@@ -2028,7 +2028,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_kv_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\", kv_name=~\".+\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-z]+)\"))\n",
|
||||
"expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_kv_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*compactor.*|cortex|mimir|mimir-backend.*))\", kv_name=~\".+\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-z]+)\"))\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{status}}",
|
||||
@@ -2103,21 +2103,21 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "histogram_quantile(0.99, sum(rate(cortex_kv_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\", kv_name=~\".+\"}[$__rate_interval])) by (le)) * 1e3",
|
||||
"expr": "histogram_quantile(0.99, sum(rate(cortex_kv_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*compactor.*|cortex|mimir|mimir-backend.*))\", kv_name=~\".+\"}[$__rate_interval])) by (le)) * 1e3",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "99th Percentile",
|
||||
"refId": "A"
|
||||
},
|
||||
{
|
||||
"expr": "histogram_quantile(0.50, sum(rate(cortex_kv_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\", kv_name=~\".+\"}[$__rate_interval])) by (le)) * 1e3",
|
||||
"expr": "histogram_quantile(0.50, sum(rate(cortex_kv_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*compactor.*|cortex|mimir|mimir-backend.*))\", kv_name=~\".+\"}[$__rate_interval])) by (le)) * 1e3",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "50th Percentile",
|
||||
"refId": "B"
|
||||
},
|
||||
{
|
||||
"expr": "sum(rate(cortex_kv_request_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\", kv_name=~\".+\"}[$__rate_interval])) * 1e3 / sum(rate(cortex_kv_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\", kv_name=~\".+\"}[$__rate_interval]))",
|
||||
"expr": "sum(rate(cortex_kv_request_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((.*compactor.*|cortex|mimir|mimir-backend.*))\", kv_name=~\".+\"}[$__rate_interval])) * 1e3 / sum(rate(cortex_kv_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*compactor.*|cortex|mimir|mimir-backend.*))\", kv_name=~\".+\"}[$__rate_interval]))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "Average",
|
||||
|
||||
@@ -81,7 +81,7 @@
|
||||
"uid": "$datasource"
|
||||
},
|
||||
"exemplar": false,
|
||||
"expr": "(\n # gRPC errors are not tracked as 5xx but \"error\".\n sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", route=~\"/distributor.Distributor/Push|/httpgrpc.*|api_(v1|prom)_push|otlp_v1_metrics\",status_code=~\"5.*|error\"}[$__rate_interval]))\n or\n # Handle the case no failure has been tracked yet.\n vector(0)\n)\n/\nsum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", route=~\"/distributor.Distributor/Push|/httpgrpc.*|api_(v1|prom)_push|otlp_v1_metrics\"}[$__rate_interval]))\n",
|
||||
"expr": "(\n # gRPC errors are not tracked as 5xx but \"error\".\n sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\", route=~\"/distributor.Distributor/Push|/httpgrpc.*|api_(v1|prom)_push|otlp_v1_metrics\",status_code=~\"5.*|error\"}[$__rate_interval]))\n or\n # Handle the case no failure has been tracked yet.\n vector(0)\n)\n/\nsum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\", route=~\"/distributor.Distributor/Push|/httpgrpc.*|api_(v1|prom)_push|otlp_v1_metrics\"}[$__rate_interval]))\n",
|
||||
"instant": false,
|
||||
"legendFormat": "Writes",
|
||||
"range": true
|
||||
@@ -91,7 +91,7 @@
|
||||
"uid": "$datasource"
|
||||
},
|
||||
"exemplar": false,
|
||||
"expr": "(\n sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\",status_code=~\"5.*\"}[$__rate_interval]))\n or\n # Handle the case no failure has been tracked yet.\n vector(0)\n)\n/\nsum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"}[$__rate_interval]))\n",
|
||||
"expr": "(\n sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\",status_code=~\"5.*\"}[$__rate_interval]))\n or\n # Handle the case no failure has been tracked yet.\n vector(0)\n)\n/\nsum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"}[$__rate_interval]))\n",
|
||||
"instant": false,
|
||||
"legendFormat": "Reads",
|
||||
"range": true
|
||||
@@ -101,7 +101,7 @@
|
||||
"uid": "$datasource"
|
||||
},
|
||||
"exemplar": false,
|
||||
"expr": "(\n (\n sum(rate(cortex_prometheus_rule_evaluation_failures_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n +\n # Consider missed evaluations as failures.\n sum(rate(cortex_prometheus_rule_group_iterations_missed_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n )\n or\n # Handle the case no failure has been tracked yet.\n vector(0)\n)\n/\nsum(rate(cortex_prometheus_rule_evaluations_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n",
|
||||
"expr": "(\n (\n sum(rate(cortex_prometheus_rule_evaluation_failures_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n +\n # Consider missed evaluations as failures.\n sum(rate(cortex_prometheus_rule_group_iterations_missed_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n )\n or\n # Handle the case no failure has been tracked yet.\n vector(0)\n)\n/\nsum(rate(cortex_prometheus_rule_evaluations_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n",
|
||||
"instant": false,
|
||||
"legendFormat": "Rule evaluations",
|
||||
"range": true
|
||||
@@ -111,7 +111,7 @@
|
||||
"uid": "$datasource"
|
||||
},
|
||||
"exemplar": false,
|
||||
"expr": "(\n # Failed notifications from ruler to Alertmanager (handling the case the ruler metrics are missing).\n ((sum(rate(cortex_prometheus_notifications_errors_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n) or vector(0))\n +\n # Failed notifications from Alertmanager to receivers (handling the case the alertmanager metrics are missing).\n ((sum(cluster_job_integration:cortex_alertmanager_notifications_failed_total:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"})\n) or vector(0))\n)\n/\n(\n # Total notifications from ruler to Alertmanager (handling the case the ruler metrics are missing).\n ((sum(rate(cortex_prometheus_notifications_sent_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n) or vector(0))\n +\n # Total notifications from Alertmanager to receivers (handling the case the alertmanager metrics are missing).\n ((sum(cluster_job_integration:cortex_alertmanager_notifications_total:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"})\n) or vector(0))\n)\n",
|
||||
"expr": "(\n # Failed notifications from ruler to Alertmanager (handling the case the ruler metrics are missing).\n ((sum(rate(cortex_prometheus_notifications_errors_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n) or vector(0))\n +\n # Failed notifications from Alertmanager to receivers (handling the case the alertmanager metrics are missing).\n ((sum(cluster_job_integration:cortex_alertmanager_notifications_failed_total:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((.*alertmanager|cortex|mimir|mimir-backend.*))\"})\n) or vector(0))\n)\n/\n(\n # Total notifications from ruler to Alertmanager (handling the case the ruler metrics are missing).\n ((sum(rate(cortex_prometheus_notifications_sent_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n) or vector(0))\n +\n # Total notifications from Alertmanager to receivers (handling the case the alertmanager metrics are missing).\n ((sum(cluster_job_integration:cortex_alertmanager_notifications_total:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((.*alertmanager|cortex|mimir|mimir-backend.*))\"})\n) or vector(0))\n)\n",
|
||||
"instant": false,
|
||||
"legendFormat": "Alerting notifications",
|
||||
"range": true
|
||||
@@ -214,7 +214,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", route=~\"/distributor.Distributor/Push|/httpgrpc.*|api_(v1|prom)_push|otlp_v1_metrics\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-z]+)\"))\n",
|
||||
"expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\", route=~\"/distributor.Distributor/Push|/httpgrpc.*|api_(v1|prom)_push|otlp_v1_metrics\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-z]+)\"))\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{status}}",
|
||||
@@ -289,7 +289,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "histogram_quantile(0.99, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", route=~\"/distributor.Distributor/Push|/httpgrpc.*|api_(v1|prom)_push|otlp_v1_metrics\"})) * 1e3",
|
||||
"expr": "histogram_quantile(0.99, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\", route=~\"/distributor.Distributor/Push|/httpgrpc.*|api_(v1|prom)_push|otlp_v1_metrics\"})) * 1e3",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "99th Percentile",
|
||||
@@ -297,7 +297,7 @@
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"expr": "histogram_quantile(0.50, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", route=~\"/distributor.Distributor/Push|/httpgrpc.*|api_(v1|prom)_push|otlp_v1_metrics\"})) * 1e3",
|
||||
"expr": "histogram_quantile(0.50, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\", route=~\"/distributor.Distributor/Push|/httpgrpc.*|api_(v1|prom)_push|otlp_v1_metrics\"})) * 1e3",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "50th Percentile",
|
||||
@@ -305,7 +305,7 @@
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"expr": "1e3 * sum(cluster_job_route:cortex_request_duration_seconds_sum:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", route=~\"/distributor.Distributor/Push|/httpgrpc.*|api_(v1|prom)_push|otlp_v1_metrics\"}) / sum(cluster_job_route:cortex_request_duration_seconds_count:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", route=~\"/distributor.Distributor/Push|/httpgrpc.*|api_(v1|prom)_push|otlp_v1_metrics\"})",
|
||||
"expr": "1e3 * sum(cluster_job_route:cortex_request_duration_seconds_sum:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\", route=~\"/distributor.Distributor/Push|/httpgrpc.*|api_(v1|prom)_push|otlp_v1_metrics\"}) / sum(cluster_job_route:cortex_request_duration_seconds_count:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\", route=~\"/distributor.Distributor/Push|/httpgrpc.*|api_(v1|prom)_push|otlp_v1_metrics\"})",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "Average",
|
||||
@@ -381,14 +381,14 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(cluster_namespace_job:cortex_distributor_received_samples:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\"})",
|
||||
"expr": "sum(cluster_namespace_job:cortex_distributor_received_samples:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\"})",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "samples / sec",
|
||||
"legendLink": null
|
||||
},
|
||||
{
|
||||
"expr": "sum(cluster_namespace_job:cortex_distributor_received_exemplars:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\"})",
|
||||
"expr": "sum(cluster_namespace_job:cortex_distributor_received_exemplars:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\"})",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "exemplars / sec",
|
||||
@@ -495,7 +495,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-z]+)\"))\n",
|
||||
"expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-z]+)\"))\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{status}}",
|
||||
@@ -570,7 +570,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "histogram_quantile(0.99, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"})) * 1e3",
|
||||
"expr": "histogram_quantile(0.99, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"})) * 1e3",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "99th Percentile",
|
||||
@@ -578,7 +578,7 @@
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"expr": "histogram_quantile(0.50, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"})) * 1e3",
|
||||
"expr": "histogram_quantile(0.50, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"})) * 1e3",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "50th Percentile",
|
||||
@@ -586,7 +586,7 @@
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"expr": "1e3 * sum(cluster_job_route:cortex_request_duration_seconds_sum:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"}) / sum(cluster_job_route:cortex_request_duration_seconds_count:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"})",
|
||||
"expr": "1e3 * sum(cluster_job_route:cortex_request_duration_seconds_sum:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"}) / sum(cluster_job_route:cortex_request_duration_seconds_count:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"})",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "Average",
|
||||
@@ -699,63 +699,63 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\",route=~\"(prometheus|api_prom)_api_v1_query\"}[$__rate_interval]))",
|
||||
"expr": "sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\",route=~\"(prometheus|api_prom)_api_v1_query\"}[$__rate_interval]))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "instant queries",
|
||||
"legendLink": null
|
||||
},
|
||||
{
|
||||
"expr": "sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\",route=~\"(prometheus|api_prom)_api_v1_query_range\"}[$__rate_interval]))",
|
||||
"expr": "sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\",route=~\"(prometheus|api_prom)_api_v1_query_range\"}[$__rate_interval]))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "range queries",
|
||||
"legendLink": null
|
||||
},
|
||||
{
|
||||
"expr": "sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\",route=~\"(prometheus|api_prom)_api_v1_labels\"}[$__rate_interval]))",
|
||||
"expr": "sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\",route=~\"(prometheus|api_prom)_api_v1_labels\"}[$__rate_interval]))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "\"label names\" queries",
|
||||
"legendLink": null
|
||||
},
|
||||
{
|
||||
"expr": "sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\",route=~\"(prometheus|api_prom)_api_v1_label_name_values\"}[$__rate_interval]))",
|
||||
"expr": "sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\",route=~\"(prometheus|api_prom)_api_v1_label_name_values\"}[$__rate_interval]))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "\"label values\" queries",
|
||||
"legendLink": null
|
||||
},
|
||||
{
|
||||
"expr": "sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\",route=~\"(prometheus|api_prom)_api_v1_series\"}[$__rate_interval]))",
|
||||
"expr": "sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\",route=~\"(prometheus|api_prom)_api_v1_series\"}[$__rate_interval]))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "series queries",
|
||||
"legendLink": null
|
||||
},
|
||||
{
|
||||
"expr": "sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\",route=~\"(prometheus|api_prom)_api_v1_read\"}[$__rate_interval]))",
|
||||
"expr": "sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\",route=~\"(prometheus|api_prom)_api_v1_read\"}[$__rate_interval]))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "remote read queries",
|
||||
"legendLink": null
|
||||
},
|
||||
{
|
||||
"expr": "sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\",route=~\"(prometheus|api_prom)_api_v1_metadata\"}[$__rate_interval]))",
|
||||
"expr": "sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\",route=~\"(prometheus|api_prom)_api_v1_metadata\"}[$__rate_interval]))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "metadata queries",
|
||||
"legendLink": null
|
||||
},
|
||||
{
|
||||
"expr": "sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\",route=~\"(prometheus|api_prom)_api_v1_query_exemplars\"}[$__rate_interval]))",
|
||||
"expr": "sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\",route=~\"(prometheus|api_prom)_api_v1_query_exemplars\"}[$__rate_interval]))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "exemplar queries",
|
||||
"legendLink": null
|
||||
},
|
||||
{
|
||||
"expr": "sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\",route=~\"(prometheus|api_prom)_api_v1_.*\",route!~\".*(query|query_range|label.*|series|read|metadata|query_exemplars)\"}[$__rate_interval]))",
|
||||
"expr": "sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\",route=~\"(prometheus|api_prom)_api_v1_.*\",route!~\".*(query|query_range|label.*|series|read|metadata|query_exemplars)\"}[$__rate_interval]))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "other",
|
||||
@@ -856,21 +856,21 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(rate(cortex_prometheus_rule_evaluations_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n-\nsum(rate(cortex_prometheus_rule_evaluation_failures_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n",
|
||||
"expr": "sum(rate(cortex_prometheus_rule_evaluations_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n-\nsum(rate(cortex_prometheus_rule_evaluation_failures_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "success",
|
||||
"legendLink": null
|
||||
},
|
||||
{
|
||||
"expr": "sum(rate(cortex_prometheus_rule_evaluation_failures_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))",
|
||||
"expr": "sum(rate(cortex_prometheus_rule_evaluation_failures_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "failed",
|
||||
"legendLink": null
|
||||
},
|
||||
{
|
||||
"expr": "sum(rate(cortex_prometheus_rule_group_iterations_missed_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))",
|
||||
"expr": "sum(rate(cortex_prometheus_rule_group_iterations_missed_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "missed",
|
||||
@@ -945,7 +945,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum (rate(cortex_prometheus_rule_evaluation_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n /\nsum (rate(cortex_prometheus_rule_evaluation_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n",
|
||||
"expr": "sum (rate(cortex_prometheus_rule_evaluation_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n /\nsum (rate(cortex_prometheus_rule_evaluation_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "average",
|
||||
@@ -1023,14 +1023,14 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(rate(cortex_prometheus_notifications_sent_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n -\nsum(rate(cortex_prometheus_notifications_errors_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n",
|
||||
"expr": "sum(rate(cortex_prometheus_notifications_sent_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n -\nsum(rate(cortex_prometheus_notifications_errors_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "successful",
|
||||
"legendLink": null
|
||||
},
|
||||
{
|
||||
"expr": "sum(rate(cortex_prometheus_notifications_errors_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n",
|
||||
"expr": "sum(rate(cortex_prometheus_notifications_errors_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "failed",
|
||||
@@ -1317,7 +1317,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(max by(user) (max_over_time(cortex_bucket_blocks_count{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"}[15m])))",
|
||||
"expr": "sum(max by(user) (max_over_time(cortex_bucket_blocks_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*compactor.*|cortex|mimir|mimir-backend.*))\"}[15m])))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "blocks",
|
||||
|
||||
@@ -66,21 +66,21 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "histogram_quantile(0.99, sum(rate(cortex_query_frontend_queue_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) by (le)) * 1e3",
|
||||
"expr": "histogram_quantile(0.99, sum(rate(cortex_query_frontend_queue_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) by (le)) * 1e3",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "99th Percentile",
|
||||
"refId": "A"
|
||||
},
|
||||
{
|
||||
"expr": "histogram_quantile(0.50, sum(rate(cortex_query_frontend_queue_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) by (le)) * 1e3",
|
||||
"expr": "histogram_quantile(0.50, sum(rate(cortex_query_frontend_queue_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) by (le)) * 1e3",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "50th Percentile",
|
||||
"refId": "B"
|
||||
},
|
||||
{
|
||||
"expr": "sum(rate(cortex_query_frontend_queue_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) * 1e3 / sum(rate(cortex_query_frontend_queue_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval]))",
|
||||
"expr": "sum(rate(cortex_query_frontend_queue_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) * 1e3 / sum(rate(cortex_query_frontend_queue_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval]))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "Average",
|
||||
@@ -155,21 +155,21 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "histogram_quantile(0.99, sum(rate(cortex_query_frontend_retries_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) by (le)) * 1",
|
||||
"expr": "histogram_quantile(0.99, sum(rate(cortex_query_frontend_retries_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) by (le)) * 1",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "99th Percentile",
|
||||
"refId": "A"
|
||||
},
|
||||
{
|
||||
"expr": "histogram_quantile(0.50, sum(rate(cortex_query_frontend_retries_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) by (le)) * 1",
|
||||
"expr": "histogram_quantile(0.50, sum(rate(cortex_query_frontend_retries_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) by (le)) * 1",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "50th Percentile",
|
||||
"refId": "B"
|
||||
},
|
||||
{
|
||||
"expr": "sum(rate(cortex_query_frontend_retries_sum{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) * 1 / sum(rate(cortex_query_frontend_retries_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval]))",
|
||||
"expr": "sum(rate(cortex_query_frontend_retries_sum{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) * 1 / sum(rate(cortex_query_frontend_retries_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval]))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "Average",
|
||||
@@ -244,7 +244,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum by(pod) (cortex_query_frontend_queue_length{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\"})",
|
||||
"expr": "sum by(pod) (cortex_query_frontend_queue_length{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\"})",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{pod}}",
|
||||
@@ -309,7 +309,7 @@
|
||||
"span": 3,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum by(user) (cortex_query_frontend_queue_length{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\"}) > 0",
|
||||
"expr": "sum by(user) (cortex_query_frontend_queue_length{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\"}) > 0",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{user}}",
|
||||
@@ -572,7 +572,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(rate(cortex_frontend_split_queries_total{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) / sum(rate(cortex_frontend_query_range_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", method=\"split_by_interval_and_results_cache\"}[$__rate_interval]))",
|
||||
"expr": "sum(rate(cortex_frontend_split_queries_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) / sum(rate(cortex_frontend_query_range_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\", method=\"split_by_interval_and_results_cache\"}[$__rate_interval]))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "splitting rate",
|
||||
@@ -647,7 +647,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "# Query the new metric introduced in Mimir 2.10.\n(\n sum by(request_type) (rate(cortex_frontend_query_result_cache_hits_total{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval]))\n /\n sum by(request_type) (rate(cortex_frontend_query_result_cache_requests_total{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval]))\n)\n# Otherwise fallback to the previous general-purpose metrics.\nor\n(\n label_replace(\n # Query metrics before and after migration to new memcached backend.\n sum (\n rate(cortex_cache_hits{name=~\"frontend.+\", cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])\n or\n rate(thanos_cache_memcached_hits_total{name=\"frontend-cache\", cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])\n )\n /\n sum (\n rate(cortex_cache_fetched_keys{name=~\"frontend.+\", cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])\n or\n rate(thanos_cache_memcached_requests_total{name=~\"frontend-cache\", cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])\n ),\n \"request_type\", \"query_range\", \"\", \"\")\n)\n",
|
||||
"expr": "# Query the new metric introduced in Mimir 2.10.\n(\n sum by(request_type) (rate(cortex_frontend_query_result_cache_hits_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval]))\n /\n sum by(request_type) (rate(cortex_frontend_query_result_cache_requests_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval]))\n)\n# Otherwise fallback to the previous general-purpose metrics.\nor\n(\n label_replace(\n # Query metrics before and after migration to new memcached backend.\n sum (\n rate(cortex_cache_hits{name=~\"frontend.+\", cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])\n or\n rate(thanos_cache_memcached_hits_total{name=\"frontend-cache\", cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])\n )\n /\n sum (\n rate(cortex_cache_fetched_keys{name=~\"frontend.+\", cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])\n or\n rate(thanos_cache_memcached_requests_total{name=~\"frontend-cache\", cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])\n ),\n \"request_type\", \"query_range\", \"\", \"\")\n)\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{request_type}}",
|
||||
@@ -723,7 +723,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(rate(cortex_frontend_query_result_cache_skipped_total{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) by (reason) /\nignoring (reason) group_left sum(rate(cortex_frontend_query_result_cache_attempted_total{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval]))\n",
|
||||
"expr": "sum(rate(cortex_frontend_query_result_cache_skipped_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) by (reason) /\nignoring (reason) group_left sum(rate(cortex_frontend_query_result_cache_attempted_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval]))\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{reason}}",
|
||||
@@ -811,7 +811,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(rate(cortex_frontend_query_sharding_rewrites_succeeded_total{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) /\nsum(rate(cortex_frontend_query_sharding_rewrites_attempted_total{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval]))\n",
|
||||
"expr": "sum(rate(cortex_frontend_query_sharding_rewrites_succeeded_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) /\nsum(rate(cortex_frontend_query_sharding_rewrites_attempted_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval]))\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "sharded queries ratio",
|
||||
@@ -887,21 +887,21 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "histogram_quantile(0.99, sum(rate(cortex_frontend_sharded_queries_per_query_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) by (le)) * 1",
|
||||
"expr": "histogram_quantile(0.99, sum(rate(cortex_frontend_sharded_queries_per_query_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) by (le)) * 1",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "99th Percentile",
|
||||
"refId": "A"
|
||||
},
|
||||
{
|
||||
"expr": "histogram_quantile(0.50, sum(rate(cortex_frontend_sharded_queries_per_query_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) by (le)) * 1",
|
||||
"expr": "histogram_quantile(0.50, sum(rate(cortex_frontend_sharded_queries_per_query_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) by (le)) * 1",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "50th Percentile",
|
||||
"refId": "B"
|
||||
},
|
||||
{
|
||||
"expr": "sum(rate(cortex_frontend_sharded_queries_per_query_sum{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) * 1 / sum(rate(cortex_frontend_sharded_queries_per_query_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval]))",
|
||||
"expr": "sum(rate(cortex_frontend_sharded_queries_per_query_sum{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) * 1 / sum(rate(cortex_frontend_sharded_queries_per_query_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval]))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "Average",
|
||||
@@ -988,7 +988,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "histogram_quantile(0.99, sum by (le) (cluster_job:cortex_ingester_queried_series_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"})) * 1",
|
||||
"expr": "histogram_quantile(0.99, sum by (le) (cluster_job:cortex_ingester_queried_series_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\"})) * 1",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "99th Percentile",
|
||||
@@ -996,7 +996,7 @@
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"expr": "histogram_quantile(0.50, sum by (le) (cluster_job:cortex_ingester_queried_series_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"})) * 1",
|
||||
"expr": "histogram_quantile(0.50, sum by (le) (cluster_job:cortex_ingester_queried_series_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\"})) * 1",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "50th Percentile",
|
||||
@@ -1004,7 +1004,7 @@
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"expr": "1 * sum(cluster_job:cortex_ingester_queried_series_sum:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}) / sum(cluster_job:cortex_ingester_queried_series_count:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"})",
|
||||
"expr": "1 * sum(cluster_job:cortex_ingester_queried_series_sum:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\"}) / sum(cluster_job:cortex_ingester_queried_series_count:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\"})",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "Average",
|
||||
@@ -1080,7 +1080,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "histogram_quantile(0.99, sum by (le) (cluster_job:cortex_ingester_queried_samples_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"})) * 1",
|
||||
"expr": "histogram_quantile(0.99, sum by (le) (cluster_job:cortex_ingester_queried_samples_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\"})) * 1",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "99th Percentile",
|
||||
@@ -1088,7 +1088,7 @@
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"expr": "histogram_quantile(0.50, sum by (le) (cluster_job:cortex_ingester_queried_samples_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"})) * 1",
|
||||
"expr": "histogram_quantile(0.50, sum by (le) (cluster_job:cortex_ingester_queried_samples_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\"})) * 1",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "50th Percentile",
|
||||
@@ -1096,7 +1096,7 @@
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"expr": "1 * sum(cluster_job:cortex_ingester_queried_samples_sum:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}) / sum(cluster_job:cortex_ingester_queried_samples_count:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"})",
|
||||
"expr": "1 * sum(cluster_job:cortex_ingester_queried_samples_sum:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\"}) / sum(cluster_job:cortex_ingester_queried_samples_count:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\"})",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "Average",
|
||||
@@ -1172,7 +1172,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "histogram_quantile(0.99, sum by (le) (cluster_job:cortex_ingester_queried_exemplars_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"})) * 1",
|
||||
"expr": "histogram_quantile(0.99, sum by (le) (cluster_job:cortex_ingester_queried_exemplars_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\"})) * 1",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "99th Percentile",
|
||||
@@ -1180,7 +1180,7 @@
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"expr": "histogram_quantile(0.50, sum by (le) (cluster_job:cortex_ingester_queried_exemplars_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"})) * 1",
|
||||
"expr": "histogram_quantile(0.50, sum by (le) (cluster_job:cortex_ingester_queried_exemplars_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\"})) * 1",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "50th Percentile",
|
||||
@@ -1188,7 +1188,7 @@
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"expr": "1 * sum(cluster_job:cortex_ingester_queried_exemplars_sum:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}) / sum(cluster_job:cortex_ingester_queried_exemplars_count:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"})",
|
||||
"expr": "1 * sum(cluster_job:cortex_ingester_queried_exemplars_sum:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\"}) / sum(cluster_job:cortex_ingester_queried_exemplars_count:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\"})",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "Average",
|
||||
@@ -1276,21 +1276,21 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "histogram_quantile(0.99, sum(rate(cortex_querier_storegateway_instances_hit_per_query_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) by (le)) * 1",
|
||||
"expr": "histogram_quantile(0.99, sum(rate(cortex_querier_storegateway_instances_hit_per_query_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*querier.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) by (le)) * 1",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "99th Percentile",
|
||||
"refId": "A"
|
||||
},
|
||||
{
|
||||
"expr": "histogram_quantile(0.50, sum(rate(cortex_querier_storegateway_instances_hit_per_query_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) by (le)) * 1",
|
||||
"expr": "histogram_quantile(0.50, sum(rate(cortex_querier_storegateway_instances_hit_per_query_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*querier.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) by (le)) * 1",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "50th Percentile",
|
||||
"refId": "B"
|
||||
},
|
||||
{
|
||||
"expr": "sum(rate(cortex_querier_storegateway_instances_hit_per_query_sum{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) * 1 / sum(rate(cortex_querier_storegateway_instances_hit_per_query_count{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval]))",
|
||||
"expr": "sum(rate(cortex_querier_storegateway_instances_hit_per_query_sum{cluster=~\"$cluster\", job=~\"($namespace)/((.*querier.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) * 1 / sum(rate(cortex_querier_storegateway_instances_hit_per_query_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*querier.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval]))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "Average",
|
||||
@@ -1365,21 +1365,21 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "histogram_quantile(0.99, sum(rate(cortex_querier_storegateway_refetches_per_query_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) by (le)) * 1",
|
||||
"expr": "histogram_quantile(0.99, sum(rate(cortex_querier_storegateway_refetches_per_query_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*querier.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) by (le)) * 1",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "99th Percentile",
|
||||
"refId": "A"
|
||||
},
|
||||
{
|
||||
"expr": "histogram_quantile(0.50, sum(rate(cortex_querier_storegateway_refetches_per_query_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) by (le)) * 1",
|
||||
"expr": "histogram_quantile(0.50, sum(rate(cortex_querier_storegateway_refetches_per_query_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*querier.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) by (le)) * 1",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "50th Percentile",
|
||||
"refId": "B"
|
||||
},
|
||||
{
|
||||
"expr": "sum(rate(cortex_querier_storegateway_refetches_per_query_sum{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) * 1 / sum(rate(cortex_querier_storegateway_refetches_per_query_count{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval]))",
|
||||
"expr": "sum(rate(cortex_querier_storegateway_refetches_per_query_sum{cluster=~\"$cluster\", job=~\"($namespace)/((.*querier.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) * 1 / sum(rate(cortex_querier_storegateway_refetches_per_query_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*querier.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval]))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "Average",
|
||||
@@ -1456,7 +1456,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(rate(cortex_querier_blocks_consistency_checks_failed_total{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) / sum(rate(cortex_querier_blocks_consistency_checks_total{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval]))",
|
||||
"expr": "sum(rate(cortex_querier_blocks_consistency_checks_failed_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*querier.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) / sum(rate(cortex_querier_blocks_consistency_checks_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*querier.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval]))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "Failure Rate",
|
||||
@@ -1532,7 +1532,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum by (reason) (rate(cortex_querier_queries_rejected_total{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) / ignoring (reason) group_left sum(rate(cortex_querier_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_query(_range)?\"}[$__rate_interval]))",
|
||||
"expr": "sum by (reason) (rate(cortex_querier_queries_rejected_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*querier.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) / ignoring (reason) group_left sum(rate(cortex_querier_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*querier.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_query(_range)?\"}[$__rate_interval]))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{reason}}",
|
||||
@@ -1619,21 +1619,21 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "max(cortex_bucket_index_loaded{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\"})",
|
||||
"expr": "max(cortex_bucket_index_loaded{cluster=~\"$cluster\", job=~\"($namespace)/((.*querier.*|cortex|mimir|mimir-read.*))\"})",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "Max",
|
||||
"legendLink": null
|
||||
},
|
||||
{
|
||||
"expr": "min(cortex_bucket_index_loaded{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\"})",
|
||||
"expr": "min(cortex_bucket_index_loaded{cluster=~\"$cluster\", job=~\"($namespace)/((.*querier.*|cortex|mimir|mimir-read.*))\"})",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "Min",
|
||||
"legendLink": null
|
||||
},
|
||||
{
|
||||
"expr": "avg(cortex_bucket_index_loaded{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\"})",
|
||||
"expr": "avg(cortex_bucket_index_loaded{cluster=~\"$cluster\", job=~\"($namespace)/((.*querier.*|cortex|mimir|mimir-read.*))\"})",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "Average",
|
||||
@@ -1711,14 +1711,14 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(rate(cortex_bucket_index_loads_total{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) - sum(rate(cortex_bucket_index_load_failures_total{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval]))",
|
||||
"expr": "sum(rate(cortex_bucket_index_loads_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*querier.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) - sum(rate(cortex_bucket_index_load_failures_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*querier.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval]))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "successful",
|
||||
"legendLink": null
|
||||
},
|
||||
{
|
||||
"expr": "sum(rate(cortex_bucket_index_load_failures_total{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval]))",
|
||||
"expr": "sum(rate(cortex_bucket_index_load_failures_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*querier.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval]))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "failed",
|
||||
@@ -1793,21 +1793,21 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "histogram_quantile(0.99, sum(rate(cortex_bucket_index_load_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) by (le)) * 1e3",
|
||||
"expr": "histogram_quantile(0.99, sum(rate(cortex_bucket_index_load_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*querier.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) by (le)) * 1e3",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "99th Percentile",
|
||||
"refId": "A"
|
||||
},
|
||||
{
|
||||
"expr": "histogram_quantile(0.50, sum(rate(cortex_bucket_index_load_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) by (le)) * 1e3",
|
||||
"expr": "histogram_quantile(0.50, sum(rate(cortex_bucket_index_load_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*querier.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) by (le)) * 1e3",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "50th Percentile",
|
||||
"refId": "B"
|
||||
},
|
||||
{
|
||||
"expr": "sum(rate(cortex_bucket_index_load_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) * 1e3 / sum(rate(cortex_bucket_index_load_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval]))",
|
||||
"expr": "sum(rate(cortex_bucket_index_load_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((.*querier.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) * 1e3 / sum(rate(cortex_bucket_index_load_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*querier.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval]))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "Average",
|
||||
@@ -1894,7 +1894,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(rate(cortex_bucket_store_series_blocks_queried_sum{component=\"store-gateway\",cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))",
|
||||
"expr": "sum(rate(cortex_bucket_store_series_blocks_queried_sum{component=\"store-gateway\",cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "blocks",
|
||||
@@ -1969,7 +1969,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum by(data_type) (\n # Exclude \"chunks refetched\".\n rate(cortex_bucket_store_series_data_size_fetched_bytes_sum{component=\"store-gateway\", stage!=\"refetched\", cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])\n)\n",
|
||||
"expr": "sum by(data_type) (\n # Exclude \"chunks refetched\".\n rate(cortex_bucket_store_series_data_size_fetched_bytes_sum{component=\"store-gateway\", stage!=\"refetched\", cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])\n)\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{data_type}}",
|
||||
@@ -2044,7 +2044,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum by(data_type) (\n # Exclude \"chunks processed\" to only count \"chunks returned\", other than postings and series.\n rate(cortex_bucket_store_series_data_size_touched_bytes_sum{component=\"store-gateway\", stage!=\"processed\",cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])\n)\n",
|
||||
"expr": "sum by(data_type) (\n # Exclude \"chunks processed\" to only count \"chunks returned\", other than postings and series.\n rate(cortex_bucket_store_series_data_size_touched_bytes_sum{component=\"store-gateway\", stage!=\"processed\",cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])\n)\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{data_type}}",
|
||||
@@ -2131,7 +2131,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum by(stage) (rate(cortex_bucket_store_series_request_stage_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n/\nsum by(stage) (rate(cortex_bucket_store_series_request_stage_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n",
|
||||
"expr": "sum by(stage) (rate(cortex_bucket_store_series_request_stage_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n/\nsum by(stage) (rate(cortex_bucket_store_series_request_stage_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{stage}}",
|
||||
@@ -2206,7 +2206,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "histogram_quantile(0.99, sum by(stage, le) (rate(cortex_bucket_store_series_request_stage_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])))\n",
|
||||
"expr": "histogram_quantile(0.99, sum by(stage, le) (rate(cortex_bucket_store_series_request_stage_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])))\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{stage}}",
|
||||
@@ -2282,7 +2282,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "# Clamping min to 0 because if preloading not useful at all, then the actual value we get is\n# slightly negative because of the small overhead introduced by preloading.\nclamp_min(1 - (\n sum(rate(cortex_bucket_store_series_batch_preloading_wait_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n /\n sum(rate(cortex_bucket_store_series_batch_preloading_load_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n), 0)\n",
|
||||
"expr": "# Clamping min to 0 because if preloading not useful at all, then the actual value we get is\n# slightly negative because of the small overhead introduced by preloading.\nclamp_min(1 - (\n sum(rate(cortex_bucket_store_series_batch_preloading_wait_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n /\n sum(rate(cortex_bucket_store_series_batch_preloading_load_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n), 0)\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "% of time reduced by preloading",
|
||||
@@ -2369,7 +2369,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "cortex_bucket_store_blocks_loaded{component=\"store-gateway\",cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"}",
|
||||
"expr": "cortex_bucket_store_blocks_loaded{component=\"store-gateway\",cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\"}",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{pod}}",
|
||||
@@ -2447,14 +2447,14 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(rate(cortex_bucket_store_block_loads_total{component=\"store-gateway\",cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) - sum(rate(cortex_bucket_store_block_load_failures_total{component=\"store-gateway\",cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))",
|
||||
"expr": "sum(rate(cortex_bucket_store_block_loads_total{component=\"store-gateway\",cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) - sum(rate(cortex_bucket_store_block_load_failures_total{component=\"store-gateway\",cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "successful",
|
||||
"legendLink": null
|
||||
},
|
||||
{
|
||||
"expr": "sum(rate(cortex_bucket_store_block_load_failures_total{component=\"store-gateway\",cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))",
|
||||
"expr": "sum(rate(cortex_bucket_store_block_load_failures_total{component=\"store-gateway\",cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "failed",
|
||||
@@ -2532,14 +2532,14 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(rate(cortex_bucket_store_block_drops_total{component=\"store-gateway\",cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) - sum(rate(cortex_bucket_store_block_drop_failures_total{component=\"store-gateway\",cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))",
|
||||
"expr": "sum(rate(cortex_bucket_store_block_drops_total{component=\"store-gateway\",cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) - sum(rate(cortex_bucket_store_block_drop_failures_total{component=\"store-gateway\",cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "successful",
|
||||
"legendLink": null
|
||||
},
|
||||
{
|
||||
"expr": "sum(rate(cortex_bucket_store_block_drop_failures_total{component=\"store-gateway\",cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))",
|
||||
"expr": "sum(rate(cortex_bucket_store_block_drop_failures_total{component=\"store-gateway\",cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "failed",
|
||||
@@ -2626,7 +2626,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "cortex_bucket_store_indexheader_lazy_load_total{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"} - cortex_bucket_store_indexheader_lazy_unload_total{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"}",
|
||||
"expr": "cortex_bucket_store_indexheader_lazy_load_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\"} - cortex_bucket_store_indexheader_lazy_unload_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\"}",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{pod}}",
|
||||
@@ -2701,21 +2701,21 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "histogram_quantile(0.99, sum(rate(cortex_bucket_store_indexheader_lazy_load_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) by (le)) * 1e3",
|
||||
"expr": "histogram_quantile(0.99, sum(rate(cortex_bucket_store_indexheader_lazy_load_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) by (le)) * 1e3",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "99th Percentile",
|
||||
"refId": "A"
|
||||
},
|
||||
{
|
||||
"expr": "histogram_quantile(0.50, sum(rate(cortex_bucket_store_indexheader_lazy_load_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) by (le)) * 1e3",
|
||||
"expr": "histogram_quantile(0.50, sum(rate(cortex_bucket_store_indexheader_lazy_load_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) by (le)) * 1e3",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "50th Percentile",
|
||||
"refId": "B"
|
||||
},
|
||||
{
|
||||
"expr": "sum(rate(cortex_bucket_store_indexheader_lazy_load_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) * 1e3 / sum(rate(cortex_bucket_store_indexheader_lazy_load_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))",
|
||||
"expr": "sum(rate(cortex_bucket_store_indexheader_lazy_load_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) * 1e3 / sum(rate(cortex_bucket_store_indexheader_lazy_load_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "Average",
|
||||
@@ -2791,21 +2791,21 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "histogram_quantile(0.99, sum(rate(cortex_bucket_stores_gate_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",gate=\"index_header\"}[$__rate_interval])) by (le)) * 1e3",
|
||||
"expr": "histogram_quantile(0.99, sum(rate(cortex_bucket_stores_gate_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\",gate=\"index_header\"}[$__rate_interval])) by (le)) * 1e3",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "99th Percentile",
|
||||
"refId": "A"
|
||||
},
|
||||
{
|
||||
"expr": "histogram_quantile(0.50, sum(rate(cortex_bucket_stores_gate_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",gate=\"index_header\"}[$__rate_interval])) by (le)) * 1e3",
|
||||
"expr": "histogram_quantile(0.50, sum(rate(cortex_bucket_stores_gate_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\",gate=\"index_header\"}[$__rate_interval])) by (le)) * 1e3",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "50th Percentile",
|
||||
"refId": "B"
|
||||
},
|
||||
{
|
||||
"expr": "sum(rate(cortex_bucket_stores_gate_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",gate=\"index_header\"}[$__rate_interval])) * 1e3 / sum(rate(cortex_bucket_stores_gate_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",gate=\"index_header\"}[$__rate_interval]))",
|
||||
"expr": "sum(rate(cortex_bucket_stores_gate_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\",gate=\"index_header\"}[$__rate_interval])) * 1e3 / sum(rate(cortex_bucket_stores_gate_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\",gate=\"index_header\"}[$__rate_interval]))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "Average",
|
||||
@@ -2892,7 +2892,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(rate(cortex_bucket_store_series_hash_cache_hits_total{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n/\nsum(rate(cortex_bucket_store_series_hash_cache_requests_total{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n",
|
||||
"expr": "sum(rate(cortex_bucket_store_series_hash_cache_hits_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n/\nsum(rate(cortex_bucket_store_series_hash_cache_requests_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "hit ratio",
|
||||
@@ -2967,7 +2967,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(rate(thanos_store_index_cache_hits_total{item_type=\"ExpandedPostings\",cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n/\nsum(rate(thanos_store_index_cache_requests_total{item_type=\"ExpandedPostings\",cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n",
|
||||
"expr": "sum(rate(thanos_store_index_cache_hits_total{item_type=\"ExpandedPostings\",cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n/\nsum(rate(thanos_store_index_cache_requests_total{item_type=\"ExpandedPostings\",cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "hit ratio",
|
||||
@@ -3042,7 +3042,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(rate(cortex_cache_memory_hits_total{name=\"chunks-attributes-cache\",cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n/\nsum(rate(cortex_cache_memory_requests_total{name=\"chunks-attributes-cache\",cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n",
|
||||
"expr": "sum(rate(cortex_cache_memory_hits_total{name=\"chunks-attributes-cache\",cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n/\nsum(rate(cortex_cache_memory_requests_total{name=\"chunks-attributes-cache\",cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "hit ratio",
|
||||
|
||||
@@ -1571,7 +1571,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum by(pod) (cortex_prometheus_rule_group_rules{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"})",
|
||||
"expr": "sum by(pod) (cortex_prometheus_rule_group_rules{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\"})",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{pod}}",
|
||||
|
||||
@@ -91,7 +91,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(\n rate(\n cortex_request_duration_seconds_count{\n cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\",\n route=~\"(prometheus|api_prom)_api_v1_query\"\n }[$__rate_interval]\n )\n or\n rate(\n cortex_prometheus_rule_evaluations_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"\n }[$__rate_interval]\n )\n)\n",
|
||||
"expr": "sum(\n rate(\n cortex_request_duration_seconds_count{\n cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\",\n route=~\"(prometheus|api_prom)_api_v1_query\"\n }[$__rate_interval]\n )\n or\n rate(\n cortex_prometheus_rule_evaluations_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\"\n }[$__rate_interval]\n )\n)\n",
|
||||
"format": "time_series",
|
||||
"instant": true,
|
||||
"intervalFactor": 2,
|
||||
@@ -168,7 +168,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\",route=~\"(prometheus|api_prom)_api_v1_query_range\"}[$__rate_interval]))",
|
||||
"expr": "sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\",route=~\"(prometheus|api_prom)_api_v1_query_range\"}[$__rate_interval]))",
|
||||
"format": "time_series",
|
||||
"instant": true,
|
||||
"intervalFactor": 2,
|
||||
@@ -245,7 +245,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\",route=~\"(prometheus|api_prom)_api_v1_labels\"}[$__rate_interval]))",
|
||||
"expr": "sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\",route=~\"(prometheus|api_prom)_api_v1_labels\"}[$__rate_interval]))",
|
||||
"format": "time_series",
|
||||
"instant": true,
|
||||
"intervalFactor": 2,
|
||||
@@ -322,7 +322,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\",route=~\"(prometheus|api_prom)_api_v1_label_name_values\"}[$__rate_interval]))",
|
||||
"expr": "sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\",route=~\"(prometheus|api_prom)_api_v1_label_name_values\"}[$__rate_interval]))",
|
||||
"format": "time_series",
|
||||
"instant": true,
|
||||
"intervalFactor": 2,
|
||||
@@ -399,7 +399,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\",route=~\"(prometheus|api_prom)_api_v1_series\"}[$__rate_interval]))",
|
||||
"expr": "sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\",route=~\"(prometheus|api_prom)_api_v1_series\"}[$__rate_interval]))",
|
||||
"format": "time_series",
|
||||
"instant": true,
|
||||
"intervalFactor": 2,
|
||||
@@ -495,7 +495,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-z]+)\"))\n",
|
||||
"expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-z]+)\"))\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{status}}",
|
||||
@@ -570,7 +570,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "histogram_quantile(0.99, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"})) * 1e3",
|
||||
"expr": "histogram_quantile(0.99, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"})) * 1e3",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "99th Percentile",
|
||||
@@ -578,7 +578,7 @@
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"expr": "histogram_quantile(0.50, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"})) * 1e3",
|
||||
"expr": "histogram_quantile(0.50, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"})) * 1e3",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "50th Percentile",
|
||||
@@ -586,7 +586,7 @@
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"expr": "1e3 * sum(cluster_job_route:cortex_request_duration_seconds_sum:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"}) / sum(cluster_job_route:cortex_request_duration_seconds_count:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"})",
|
||||
"expr": "1e3 * sum(cluster_job_route:cortex_request_duration_seconds_sum:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"}) / sum(cluster_job_route:cortex_request_duration_seconds_count:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"})",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "Average",
|
||||
@@ -670,7 +670,7 @@
|
||||
"targets": [
|
||||
{
|
||||
"exemplar": true,
|
||||
"expr": "histogram_quantile(0.99, sum by(le, pod) (rate(cortex_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"}[$__rate_interval])))",
|
||||
"expr": "histogram_quantile(0.99, sum by(le, pod) (rate(cortex_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"}[$__rate_interval])))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "",
|
||||
@@ -920,7 +920,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum (\n rate(thanos_memcached_operations_total{name=\"frontend-cache\", cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])\n or ignoring(backend)\n rate(thanos_cache_operations_total{name=\"frontend-cache\", cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])\n)\n",
|
||||
"expr": "sum (\n rate(thanos_memcached_operations_total{name=\"frontend-cache\", cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])\n or ignoring(backend)\n rate(thanos_cache_operations_total{name=\"frontend-cache\", cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])\n)\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "Requests/s",
|
||||
@@ -995,7 +995,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "histogram_quantile(0.99, sum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", name=\"frontend-cache\"}[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", name=\"frontend-cache\"}[$__rate_interval])\n) by (le)) * 1e3\n",
|
||||
"expr": "histogram_quantile(0.99, sum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\", name=\"frontend-cache\"}[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\", name=\"frontend-cache\"}[$__rate_interval])\n) by (le)) * 1e3\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "99th Percentile",
|
||||
@@ -1003,7 +1003,7 @@
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"expr": "histogram_quantile(0.50, sum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", name=\"frontend-cache\"}[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", name=\"frontend-cache\"}[$__rate_interval])\n) by (le)) * 1e3\n",
|
||||
"expr": "histogram_quantile(0.50, sum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\", name=\"frontend-cache\"}[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\", name=\"frontend-cache\"}[$__rate_interval])\n) by (le)) * 1e3\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "50th Percentile",
|
||||
@@ -1011,7 +1011,7 @@
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"expr": "sum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", name=\"frontend-cache\"}[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", name=\"frontend-cache\"}[$__rate_interval])\n) * 1e3\n/\nsum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", name=\"frontend-cache\"}[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", name=\"frontend-cache\"}[$__rate_interval])\n)\n",
|
||||
"expr": "sum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\", name=\"frontend-cache\"}[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\", name=\"frontend-cache\"}[$__rate_interval])\n) * 1e3\n/\nsum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\", name=\"frontend-cache\"}[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\", name=\"frontend-cache\"}[$__rate_interval])\n)\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "Average",
|
||||
@@ -1108,7 +1108,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_querier_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-z]+)\"))\n",
|
||||
"expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_querier_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*querier.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-z]+)\"))\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{status}}",
|
||||
@@ -1183,7 +1183,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "histogram_quantile(0.99, sum by (le) (cluster_job_route:cortex_querier_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"})) * 1e3",
|
||||
"expr": "histogram_quantile(0.99, sum by (le) (cluster_job_route:cortex_querier_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((.*querier.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"})) * 1e3",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "99th Percentile",
|
||||
@@ -1191,7 +1191,7 @@
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"expr": "histogram_quantile(0.50, sum by (le) (cluster_job_route:cortex_querier_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"})) * 1e3",
|
||||
"expr": "histogram_quantile(0.50, sum by (le) (cluster_job_route:cortex_querier_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((.*querier.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"})) * 1e3",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "50th Percentile",
|
||||
@@ -1199,7 +1199,7 @@
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"expr": "1e3 * sum(cluster_job_route:cortex_querier_request_duration_seconds_sum:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"}) / sum(cluster_job_route:cortex_querier_request_duration_seconds_count:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"})",
|
||||
"expr": "1e3 * sum(cluster_job_route:cortex_querier_request_duration_seconds_sum:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((.*querier.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"}) / sum(cluster_job_route:cortex_querier_request_duration_seconds_count:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((.*querier.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"})",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "Average",
|
||||
@@ -1283,7 +1283,7 @@
|
||||
"targets": [
|
||||
{
|
||||
"exemplar": true,
|
||||
"expr": "histogram_quantile(0.99, sum by(le, pod) (rate(cortex_querier_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"}[$__rate_interval])))",
|
||||
"expr": "histogram_quantile(0.99, sum by(le, pod) (rate(cortex_querier_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*querier.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"}[$__rate_interval])))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "",
|
||||
@@ -1346,7 +1346,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\",route=~\"/cortex.Ingester/Query(Stream)?|/cortex.Ingester/MetricsForLabelMatchers|/cortex.Ingester/LabelValues|/cortex.Ingester/MetricsMetadata\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-z]+)\"))\n",
|
||||
"expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\",route=~\"/cortex.Ingester/Query(Stream)?|/cortex.Ingester/MetricsForLabelMatchers|/cortex.Ingester/LabelValues|/cortex.Ingester/MetricsMetadata\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-z]+)\"))\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{status}}",
|
||||
@@ -1421,7 +1421,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "histogram_quantile(0.99, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", route=~\"/cortex.Ingester/Query(Stream)?|/cortex.Ingester/MetricsForLabelMatchers|/cortex.Ingester/LabelValues|/cortex.Ingester/MetricsMetadata\"})) * 1e3",
|
||||
"expr": "histogram_quantile(0.99, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\", route=~\"/cortex.Ingester/Query(Stream)?|/cortex.Ingester/MetricsForLabelMatchers|/cortex.Ingester/LabelValues|/cortex.Ingester/MetricsMetadata\"})) * 1e3",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "99th Percentile",
|
||||
@@ -1429,7 +1429,7 @@
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"expr": "histogram_quantile(0.50, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", route=~\"/cortex.Ingester/Query(Stream)?|/cortex.Ingester/MetricsForLabelMatchers|/cortex.Ingester/LabelValues|/cortex.Ingester/MetricsMetadata\"})) * 1e3",
|
||||
"expr": "histogram_quantile(0.50, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\", route=~\"/cortex.Ingester/Query(Stream)?|/cortex.Ingester/MetricsForLabelMatchers|/cortex.Ingester/LabelValues|/cortex.Ingester/MetricsMetadata\"})) * 1e3",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "50th Percentile",
|
||||
@@ -1437,7 +1437,7 @@
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"expr": "1e3 * sum(cluster_job_route:cortex_request_duration_seconds_sum:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", route=~\"/cortex.Ingester/Query(Stream)?|/cortex.Ingester/MetricsForLabelMatchers|/cortex.Ingester/LabelValues|/cortex.Ingester/MetricsMetadata\"}) / sum(cluster_job_route:cortex_request_duration_seconds_count:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", route=~\"/cortex.Ingester/Query(Stream)?|/cortex.Ingester/MetricsForLabelMatchers|/cortex.Ingester/LabelValues|/cortex.Ingester/MetricsMetadata\"})",
|
||||
"expr": "1e3 * sum(cluster_job_route:cortex_request_duration_seconds_sum:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\", route=~\"/cortex.Ingester/Query(Stream)?|/cortex.Ingester/MetricsForLabelMatchers|/cortex.Ingester/LabelValues|/cortex.Ingester/MetricsMetadata\"}) / sum(cluster_job_route:cortex_request_duration_seconds_count:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\", route=~\"/cortex.Ingester/Query(Stream)?|/cortex.Ingester/MetricsForLabelMatchers|/cortex.Ingester/LabelValues|/cortex.Ingester/MetricsMetadata\"})",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "Average",
|
||||
@@ -1521,7 +1521,7 @@
|
||||
"targets": [
|
||||
{
|
||||
"exemplar": true,
|
||||
"expr": "histogram_quantile(0.99, sum by(le, pod) (rate(cortex_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", route=~\"/cortex.Ingester/Query(Stream)?|/cortex.Ingester/MetricsForLabelMatchers|/cortex.Ingester/LabelValues|/cortex.Ingester/MetricsMetadata\"}[$__rate_interval])))",
|
||||
"expr": "histogram_quantile(0.99, sum by(le, pod) (rate(cortex_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\", route=~\"/cortex.Ingester/Query(Stream)?|/cortex.Ingester/MetricsForLabelMatchers|/cortex.Ingester/LabelValues|/cortex.Ingester/MetricsMetadata\"}[$__rate_interval])))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "",
|
||||
@@ -1584,7 +1584,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",route=~\"/gatewaypb.StoreGateway/.*\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-z]+)\"))\n",
|
||||
"expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\",route=~\"/gatewaypb.StoreGateway/.*\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-z]+)\"))\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{status}}",
|
||||
@@ -1659,7 +1659,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "histogram_quantile(0.99, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\", route=~\"/gatewaypb.StoreGateway/.*\"})) * 1e3",
|
||||
"expr": "histogram_quantile(0.99, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\", route=~\"/gatewaypb.StoreGateway/.*\"})) * 1e3",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "99th Percentile",
|
||||
@@ -1667,7 +1667,7 @@
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"expr": "histogram_quantile(0.50, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\", route=~\"/gatewaypb.StoreGateway/.*\"})) * 1e3",
|
||||
"expr": "histogram_quantile(0.50, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\", route=~\"/gatewaypb.StoreGateway/.*\"})) * 1e3",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "50th Percentile",
|
||||
@@ -1675,7 +1675,7 @@
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"expr": "1e3 * sum(cluster_job_route:cortex_request_duration_seconds_sum:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\", route=~\"/gatewaypb.StoreGateway/.*\"}) / sum(cluster_job_route:cortex_request_duration_seconds_count:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\", route=~\"/gatewaypb.StoreGateway/.*\"})",
|
||||
"expr": "1e3 * sum(cluster_job_route:cortex_request_duration_seconds_sum:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\", route=~\"/gatewaypb.StoreGateway/.*\"}) / sum(cluster_job_route:cortex_request_duration_seconds_count:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\", route=~\"/gatewaypb.StoreGateway/.*\"})",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "Average",
|
||||
@@ -1759,7 +1759,7 @@
|
||||
"targets": [
|
||||
{
|
||||
"exemplar": true,
|
||||
"expr": "histogram_quantile(0.99, sum by(le, pod) (rate(cortex_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\", route=~\"/gatewaypb.StoreGateway/.*\"}[$__rate_interval])))",
|
||||
"expr": "histogram_quantile(0.99, sum by(le, pod) (rate(cortex_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\", route=~\"/gatewaypb.StoreGateway/.*\"}[$__rate_interval])))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "",
|
||||
@@ -2084,7 +2084,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_kv_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\", kv_name=~\"store-gateway\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-z]+)\"))\n",
|
||||
"expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_kv_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\", kv_name=~\"store-gateway\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-z]+)\"))\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{status}}",
|
||||
@@ -2159,21 +2159,21 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "histogram_quantile(0.99, sum(rate(cortex_kv_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\", kv_name=~\"store-gateway\"}[$__rate_interval])) by (le)) * 1e3",
|
||||
"expr": "histogram_quantile(0.99, sum(rate(cortex_kv_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\", kv_name=~\"store-gateway\"}[$__rate_interval])) by (le)) * 1e3",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "99th Percentile",
|
||||
"refId": "A"
|
||||
},
|
||||
{
|
||||
"expr": "histogram_quantile(0.50, sum(rate(cortex_kv_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\", kv_name=~\"store-gateway\"}[$__rate_interval])) by (le)) * 1e3",
|
||||
"expr": "histogram_quantile(0.50, sum(rate(cortex_kv_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\", kv_name=~\"store-gateway\"}[$__rate_interval])) by (le)) * 1e3",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "50th Percentile",
|
||||
"refId": "B"
|
||||
},
|
||||
{
|
||||
"expr": "sum(rate(cortex_kv_request_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\", kv_name=~\"store-gateway\"}[$__rate_interval])) * 1e3 / sum(rate(cortex_kv_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\", kv_name=~\"store-gateway\"}[$__rate_interval]))",
|
||||
"expr": "sum(rate(cortex_kv_request_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\", kv_name=~\"store-gateway\"}[$__rate_interval])) * 1e3 / sum(rate(cortex_kv_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\", kv_name=~\"store-gateway\"}[$__rate_interval]))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "Average",
|
||||
@@ -2260,7 +2260,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum by(operation) (\n # Backwards compatibility\n rate(\n thanos_memcached_operations_total{\n component=\"store-gateway\",\n name=\"index-cache\",\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"\n }[$__rate_interval]\n )\n or ignoring(backend)\n rate(\n thanos_cache_operations_total{\n component=\"store-gateway\",\n name=\"index-cache\",\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"\n }[$__rate_interval]\n )\n)\n",
|
||||
"expr": "sum by(operation) (\n # Backwards compatibility\n rate(\n thanos_memcached_operations_total{\n component=\"store-gateway\",\n name=\"index-cache\",\n cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\"\n }[$__rate_interval]\n )\n or ignoring(backend)\n rate(\n thanos_cache_operations_total{\n component=\"store-gateway\",\n name=\"index-cache\",\n cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\"\n }[$__rate_interval]\n )\n)\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{operation}}",
|
||||
@@ -2335,7 +2335,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "histogram_quantile(0.99, sum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_bucket{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"index-cache\"\n}\n[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_bucket{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"index-cache\"\n}\n[$__rate_interval])\n) by (le)) * 1e3\n",
|
||||
"expr": "histogram_quantile(0.99, sum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_bucket{\n cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"index-cache\"\n}\n[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_bucket{\n cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"index-cache\"\n}\n[$__rate_interval])\n) by (le)) * 1e3\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "99th Percentile",
|
||||
@@ -2343,7 +2343,7 @@
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"expr": "histogram_quantile(0.50, sum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_bucket{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"index-cache\"\n}\n[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_bucket{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"index-cache\"\n}\n[$__rate_interval])\n) by (le)) * 1e3\n",
|
||||
"expr": "histogram_quantile(0.50, sum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_bucket{\n cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"index-cache\"\n}\n[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_bucket{\n cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"index-cache\"\n}\n[$__rate_interval])\n) by (le)) * 1e3\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "50th Percentile",
|
||||
@@ -2351,7 +2351,7 @@
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"expr": "sum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_sum{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"index-cache\"\n}\n[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_sum{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"index-cache\"\n}\n[$__rate_interval])\n) * 1e3\n/\nsum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_count{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"index-cache\"\n}\n[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_count{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"index-cache\"\n}\n[$__rate_interval])\n)\n",
|
||||
"expr": "sum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_sum{\n cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"index-cache\"\n}\n[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_sum{\n cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"index-cache\"\n}\n[$__rate_interval])\n) * 1e3\n/\nsum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_count{\n cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"index-cache\"\n}\n[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_count{\n cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"index-cache\"\n}\n[$__rate_interval])\n)\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "Average",
|
||||
@@ -2428,7 +2428,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum by(item_type) (\n rate(\n thanos_store_index_cache_hits_total{\n component=\"store-gateway\",\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"\n }[$__rate_interval]\n )\n)\n/\nsum by(item_type) (\n rate(\n thanos_store_index_cache_requests_total{\n component=\"store-gateway\",\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"\n }[$__rate_interval]\n )\n)\n",
|
||||
"expr": "sum by(item_type) (\n rate(\n thanos_store_index_cache_hits_total{\n component=\"store-gateway\",\n cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\"\n }[$__rate_interval]\n )\n)\n/\nsum by(item_type) (\n rate(\n thanos_store_index_cache_requests_total{\n component=\"store-gateway\",\n cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\"\n }[$__rate_interval]\n )\n)\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{item_type}}",
|
||||
@@ -2515,7 +2515,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum by(operation) (\n # Backwards compatibility\n rate(thanos_memcached_operations_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n component=\"store-gateway\",\n name=\"chunks-cache\"\n }[$__rate_interval])\n or ignoring(backend)\n rate(thanos_cache_operations_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n component=\"store-gateway\",\n name=\"chunks-cache\"\n }[$__rate_interval])\n)\n",
|
||||
"expr": "sum by(operation) (\n # Backwards compatibility\n rate(thanos_memcached_operations_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\",\n component=\"store-gateway\",\n name=\"chunks-cache\"\n }[$__rate_interval])\n or ignoring(backend)\n rate(thanos_cache_operations_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\",\n component=\"store-gateway\",\n name=\"chunks-cache\"\n }[$__rate_interval])\n)\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{operation}}",
|
||||
@@ -2590,7 +2590,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "histogram_quantile(0.99, sum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_bucket{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"chunks-cache\"\n}\n[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_bucket{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"chunks-cache\"\n}\n[$__rate_interval])\n) by (le)) * 1e3\n",
|
||||
"expr": "histogram_quantile(0.99, sum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_bucket{\n cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"chunks-cache\"\n}\n[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_bucket{\n cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"chunks-cache\"\n}\n[$__rate_interval])\n) by (le)) * 1e3\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "99th Percentile",
|
||||
@@ -2598,7 +2598,7 @@
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"expr": "histogram_quantile(0.50, sum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_bucket{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"chunks-cache\"\n}\n[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_bucket{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"chunks-cache\"\n}\n[$__rate_interval])\n) by (le)) * 1e3\n",
|
||||
"expr": "histogram_quantile(0.50, sum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_bucket{\n cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"chunks-cache\"\n}\n[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_bucket{\n cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"chunks-cache\"\n}\n[$__rate_interval])\n) by (le)) * 1e3\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "50th Percentile",
|
||||
@@ -2606,7 +2606,7 @@
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"expr": "sum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_sum{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"chunks-cache\"\n}\n[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_sum{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"chunks-cache\"\n}\n[$__rate_interval])\n) * 1e3\n/\nsum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_count{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"chunks-cache\"\n}\n[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_count{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"chunks-cache\"\n}\n[$__rate_interval])\n)\n",
|
||||
"expr": "sum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_sum{\n cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"chunks-cache\"\n}\n[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_sum{\n cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"chunks-cache\"\n}\n[$__rate_interval])\n) * 1e3\n/\nsum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_count{\n cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"chunks-cache\"\n}\n[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_count{\n cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"chunks-cache\"\n}\n[$__rate_interval])\n)\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "Average",
|
||||
@@ -2682,7 +2682,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(\n # Backwards compatibility\n rate(thanos_cache_memcached_hits_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n component=\"store-gateway\",\n name=\"chunks-cache\"\n }[$__rate_interval])\n or\n rate(thanos_cache_hits_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n component=\"store-gateway\",\n name=\"chunks-cache\"\n }[$__rate_interval])\n)\n/\nsum(\n # Backwards compatibility\n rate(thanos_cache_memcached_requests_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n component=\"store-gateway\",\n name=\"chunks-cache\"\n }[$__rate_interval])\n or\n rate(thanos_cache_requests_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n component=\"store-gateway\",\n name=\"chunks-cache\"\n }[$__rate_interval])\n)\n",
|
||||
"expr": "sum(\n # Backwards compatibility\n rate(thanos_cache_memcached_hits_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\",\n component=\"store-gateway\",\n name=\"chunks-cache\"\n }[$__rate_interval])\n or\n rate(thanos_cache_hits_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\",\n component=\"store-gateway\",\n name=\"chunks-cache\"\n }[$__rate_interval])\n)\n/\nsum(\n # Backwards compatibility\n rate(thanos_cache_memcached_requests_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\",\n component=\"store-gateway\",\n name=\"chunks-cache\"\n }[$__rate_interval])\n or\n rate(thanos_cache_requests_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\",\n component=\"store-gateway\",\n name=\"chunks-cache\"\n }[$__rate_interval])\n)\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "items",
|
||||
@@ -2769,7 +2769,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum by(operation) (\n # Backwards compatibility\n rate(thanos_memcached_operations_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n component=\"store-gateway\",\n name=\"metadata-cache\"\n }[$__rate_interval])\n or ignoring(backend)\n rate(thanos_cache_operations_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n component=\"store-gateway\",\n name=\"metadata-cache\"\n }[$__rate_interval])\n)\n",
|
||||
"expr": "sum by(operation) (\n # Backwards compatibility\n rate(thanos_memcached_operations_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\",\n component=\"store-gateway\",\n name=\"metadata-cache\"\n }[$__rate_interval])\n or ignoring(backend)\n rate(thanos_cache_operations_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\",\n component=\"store-gateway\",\n name=\"metadata-cache\"\n }[$__rate_interval])\n)\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{operation}}",
|
||||
@@ -2844,7 +2844,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "histogram_quantile(0.99, sum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_bucket{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"metadata-cache\"\n}\n[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_bucket{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"metadata-cache\"\n}\n[$__rate_interval])\n) by (le)) * 1e3\n",
|
||||
"expr": "histogram_quantile(0.99, sum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_bucket{\n cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"metadata-cache\"\n}\n[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_bucket{\n cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"metadata-cache\"\n}\n[$__rate_interval])\n) by (le)) * 1e3\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "99th Percentile",
|
||||
@@ -2852,7 +2852,7 @@
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"expr": "histogram_quantile(0.50, sum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_bucket{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"metadata-cache\"\n}\n[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_bucket{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"metadata-cache\"\n}\n[$__rate_interval])\n) by (le)) * 1e3\n",
|
||||
"expr": "histogram_quantile(0.50, sum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_bucket{\n cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"metadata-cache\"\n}\n[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_bucket{\n cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"metadata-cache\"\n}\n[$__rate_interval])\n) by (le)) * 1e3\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "50th Percentile",
|
||||
@@ -2860,7 +2860,7 @@
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"expr": "sum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_sum{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"metadata-cache\"\n}\n[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_sum{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"metadata-cache\"\n}\n[$__rate_interval])\n) * 1e3\n/\nsum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_count{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"metadata-cache\"\n}\n[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_count{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"metadata-cache\"\n}\n[$__rate_interval])\n)\n",
|
||||
"expr": "sum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_sum{\n cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"metadata-cache\"\n}\n[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_sum{\n cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"metadata-cache\"\n}\n[$__rate_interval])\n) * 1e3\n/\nsum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_count{\n cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"metadata-cache\"\n}\n[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_count{\n cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"metadata-cache\"\n}\n[$__rate_interval])\n)\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "Average",
|
||||
@@ -2936,7 +2936,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(\n # Backwards compatibility\n rate(thanos_cache_memcached_hits_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n component=\"store-gateway\",\n name=\"metadata-cache\"\n }[$__rate_interval])\n or\n rate(thanos_cache_hits_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n component=\"store-gateway\",\n name=\"metadata-cache\"\n }[$__rate_interval])\n)\n/\nsum(\n # Backwards compatibility\n rate(thanos_cache_memcached_requests_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n component=\"store-gateway\",\n name=\"metadata-cache\"\n }[$__rate_interval])\n or\n rate(thanos_cache_requests_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n component=\"store-gateway\",\n name=\"metadata-cache\"\n }[$__rate_interval])\n)\n",
|
||||
"expr": "sum(\n # Backwards compatibility\n rate(thanos_cache_memcached_hits_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\",\n component=\"store-gateway\",\n name=\"metadata-cache\"\n }[$__rate_interval])\n or\n rate(thanos_cache_hits_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\",\n component=\"store-gateway\",\n name=\"metadata-cache\"\n }[$__rate_interval])\n)\n/\nsum(\n # Backwards compatibility\n rate(thanos_cache_memcached_requests_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\",\n component=\"store-gateway\",\n name=\"metadata-cache\"\n }[$__rate_interval])\n or\n rate(thanos_cache_requests_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\",\n component=\"store-gateway\",\n name=\"metadata-cache\"\n }[$__rate_interval])\n)\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "items",
|
||||
@@ -3023,7 +3023,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum by(operation) (\n # Backwards compatibility\n rate(thanos_memcached_operations_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\",\n component=\"querier\",\n name=\"metadata-cache\"\n }[$__rate_interval])\n or ignoring(backend)\n rate(thanos_cache_operations_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\",\n component=\"querier\",\n name=\"metadata-cache\"\n }[$__rate_interval])\n)\n",
|
||||
"expr": "sum by(operation) (\n # Backwards compatibility\n rate(thanos_memcached_operations_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((.*querier.*|cortex|mimir|mimir-read.*))\",\n component=\"querier\",\n name=\"metadata-cache\"\n }[$__rate_interval])\n or ignoring(backend)\n rate(thanos_cache_operations_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((.*querier.*|cortex|mimir|mimir-read.*))\",\n component=\"querier\",\n name=\"metadata-cache\"\n }[$__rate_interval])\n)\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{operation}}",
|
||||
@@ -3098,7 +3098,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "histogram_quantile(0.99, sum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_bucket{\n cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\",\n operation=\"getmulti\",\n component=\"querier\",\n name=\"metadata-cache\"\n}\n[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_bucket{\n cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\",\n operation=\"getmulti\",\n component=\"querier\",\n name=\"metadata-cache\"\n}\n[$__rate_interval])\n) by (le)) * 1e3\n",
|
||||
"expr": "histogram_quantile(0.99, sum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_bucket{\n cluster=~\"$cluster\", job=~\"($namespace)/((.*querier.*|cortex|mimir|mimir-read.*))\",\n operation=\"getmulti\",\n component=\"querier\",\n name=\"metadata-cache\"\n}\n[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_bucket{\n cluster=~\"$cluster\", job=~\"($namespace)/((.*querier.*|cortex|mimir|mimir-read.*))\",\n operation=\"getmulti\",\n component=\"querier\",\n name=\"metadata-cache\"\n}\n[$__rate_interval])\n) by (le)) * 1e3\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "99th Percentile",
|
||||
@@ -3106,7 +3106,7 @@
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"expr": "histogram_quantile(0.50, sum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_bucket{\n cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\",\n operation=\"getmulti\",\n component=\"querier\",\n name=\"metadata-cache\"\n}\n[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_bucket{\n cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\",\n operation=\"getmulti\",\n component=\"querier\",\n name=\"metadata-cache\"\n}\n[$__rate_interval])\n) by (le)) * 1e3\n",
|
||||
"expr": "histogram_quantile(0.50, sum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_bucket{\n cluster=~\"$cluster\", job=~\"($namespace)/((.*querier.*|cortex|mimir|mimir-read.*))\",\n operation=\"getmulti\",\n component=\"querier\",\n name=\"metadata-cache\"\n}\n[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_bucket{\n cluster=~\"$cluster\", job=~\"($namespace)/((.*querier.*|cortex|mimir|mimir-read.*))\",\n operation=\"getmulti\",\n component=\"querier\",\n name=\"metadata-cache\"\n}\n[$__rate_interval])\n) by (le)) * 1e3\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "50th Percentile",
|
||||
@@ -3114,7 +3114,7 @@
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"expr": "sum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_sum{\n cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\",\n operation=\"getmulti\",\n component=\"querier\",\n name=\"metadata-cache\"\n}\n[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_sum{\n cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\",\n operation=\"getmulti\",\n component=\"querier\",\n name=\"metadata-cache\"\n}\n[$__rate_interval])\n) * 1e3\n/\nsum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_count{\n cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\",\n operation=\"getmulti\",\n component=\"querier\",\n name=\"metadata-cache\"\n}\n[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_count{\n cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\",\n operation=\"getmulti\",\n component=\"querier\",\n name=\"metadata-cache\"\n}\n[$__rate_interval])\n)\n",
|
||||
"expr": "sum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_sum{\n cluster=~\"$cluster\", job=~\"($namespace)/((.*querier.*|cortex|mimir|mimir-read.*))\",\n operation=\"getmulti\",\n component=\"querier\",\n name=\"metadata-cache\"\n}\n[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_sum{\n cluster=~\"$cluster\", job=~\"($namespace)/((.*querier.*|cortex|mimir|mimir-read.*))\",\n operation=\"getmulti\",\n component=\"querier\",\n name=\"metadata-cache\"\n}\n[$__rate_interval])\n) * 1e3\n/\nsum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_count{\n cluster=~\"$cluster\", job=~\"($namespace)/((.*querier.*|cortex|mimir|mimir-read.*))\",\n operation=\"getmulti\",\n component=\"querier\",\n name=\"metadata-cache\"\n}\n[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_count{\n cluster=~\"$cluster\", job=~\"($namespace)/((.*querier.*|cortex|mimir|mimir-read.*))\",\n operation=\"getmulti\",\n component=\"querier\",\n name=\"metadata-cache\"\n}\n[$__rate_interval])\n)\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "Average",
|
||||
@@ -3190,7 +3190,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(\n # Backwards compatibility\n rate(thanos_cache_memcached_hits_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\",\n component=\"querier\",\n name=\"metadata-cache\"\n }[$__rate_interval])\n or\n rate(thanos_cache_hits_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\",\n component=\"querier\",\n name=\"metadata-cache\"\n }[$__rate_interval])\n)\n/\nsum(\n # Backwards compatibility\n rate(thanos_cache_memcached_requests_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\",\n component=\"querier\",\n name=\"metadata-cache\"\n }[$__rate_interval])\n or\n rate(thanos_cache_requests_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\",\n component=\"querier\",\n name=\"metadata-cache\"\n }[$__rate_interval])\n)\n",
|
||||
"expr": "sum(\n # Backwards compatibility\n rate(thanos_cache_memcached_hits_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((.*querier.*|cortex|mimir|mimir-read.*))\",\n component=\"querier\",\n name=\"metadata-cache\"\n }[$__rate_interval])\n or\n rate(thanos_cache_hits_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((.*querier.*|cortex|mimir|mimir-read.*))\",\n component=\"querier\",\n name=\"metadata-cache\"\n }[$__rate_interval])\n)\n/\nsum(\n # Backwards compatibility\n rate(thanos_cache_memcached_requests_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((.*querier.*|cortex|mimir|mimir-read.*))\",\n component=\"querier\",\n name=\"metadata-cache\"\n }[$__rate_interval])\n or\n rate(thanos_cache_requests_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((.*querier.*|cortex|mimir|mimir-read.*))\",\n component=\"querier\",\n name=\"metadata-cache\"\n }[$__rate_interval])\n)\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "items",
|
||||
|
||||
@@ -242,7 +242,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", route=~\"api_(v1|prom)_push|otlp_v1_metrics\",status_code=~\"2.+\"}[$__rate_interval])) /\nsum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", route=~\"api_(v1|prom)_push|otlp_v1_metrics\"}[$__rate_interval]))\n",
|
||||
"expr": "sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\", route=~\"api_(v1|prom)_push|otlp_v1_metrics\",status_code=~\"2.+\"}[$__rate_interval])) /\nsum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\", route=~\"api_(v1|prom)_push|otlp_v1_metrics\"}[$__rate_interval]))\n",
|
||||
"format": null,
|
||||
"instant": false,
|
||||
"interval": "",
|
||||
@@ -354,7 +354,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", route=~\"api_(v1|prom)_push|otlp_v1_metrics\",status_code=~\"4.+\"}[$__rate_interval])) /\nsum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", route=~\"api_(v1|prom)_push|otlp_v1_metrics\"}[$__rate_interval]))\n",
|
||||
"expr": "sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\", route=~\"api_(v1|prom)_push|otlp_v1_metrics\",status_code=~\"4.+\"}[$__rate_interval])) /\nsum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\", route=~\"api_(v1|prom)_push|otlp_v1_metrics\"}[$__rate_interval]))\n",
|
||||
"format": null,
|
||||
"instant": false,
|
||||
"interval": "",
|
||||
@@ -462,7 +462,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", route=~\"api_(v1|prom)_push|otlp_v1_metrics\",status_code=~\"5.+\"}[$__rate_interval])) /\nsum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", route=~\"api_(v1|prom)_push|otlp_v1_metrics\"}[$__rate_interval]))\n",
|
||||
"expr": "sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\", route=~\"api_(v1|prom)_push|otlp_v1_metrics\",status_code=~\"5.+\"}[$__rate_interval])) /\nsum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\", route=~\"api_(v1|prom)_push|otlp_v1_metrics\"}[$__rate_interval]))\n",
|
||||
"format": null,
|
||||
"instant": false,
|
||||
"interval": "",
|
||||
@@ -574,7 +574,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "histogram_quantile(0.99, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", route=~\"api_(v1|prom)_push|otlp_v1_metrics\"}))\n",
|
||||
"expr": "histogram_quantile(0.99, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\", route=~\"api_(v1|prom)_push|otlp_v1_metrics\"}))\n",
|
||||
"format": null,
|
||||
"instant": false,
|
||||
"interval": "",
|
||||
@@ -678,7 +678,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\",status_code=~\"2.+\"}[$__rate_interval])) /\nsum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"}[$__rate_interval]))\n",
|
||||
"expr": "sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\",status_code=~\"2.+\"}[$__rate_interval])) /\nsum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"}[$__rate_interval]))\n",
|
||||
"format": null,
|
||||
"instant": false,
|
||||
"interval": "",
|
||||
@@ -790,7 +790,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\",status_code=~\"4.+\"}[$__rate_interval])) /\nsum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"}[$__rate_interval]))\n",
|
||||
"expr": "sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\",status_code=~\"4.+\"}[$__rate_interval])) /\nsum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"}[$__rate_interval]))\n",
|
||||
"format": null,
|
||||
"instant": false,
|
||||
"interval": "",
|
||||
@@ -898,7 +898,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\",status_code=~\"5.+\"}[$__rate_interval])) /\nsum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"}[$__rate_interval]))\n",
|
||||
"expr": "sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\",status_code=~\"5.+\"}[$__rate_interval])) /\nsum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"}[$__rate_interval]))\n",
|
||||
"format": null,
|
||||
"instant": false,
|
||||
"interval": "",
|
||||
@@ -1010,7 +1010,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "histogram_quantile(0.99, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"}))\n",
|
||||
"expr": "histogram_quantile(0.99, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"}))\n",
|
||||
"format": null,
|
||||
"instant": false,
|
||||
"interval": "",
|
||||
@@ -1290,14 +1290,14 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "1 - (\n avg_over_time(histogram_quantile(0.99, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", route=~\"api_(v1|prom)_push|otlp_v1_metrics\"} offset 24h))[1h:])\n /\n avg_over_time(histogram_quantile(0.99, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", route=~\"api_(v1|prom)_push|otlp_v1_metrics\"}))[1h:])\n)\n",
|
||||
"expr": "1 - (\n avg_over_time(histogram_quantile(0.99, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\", route=~\"api_(v1|prom)_push|otlp_v1_metrics\"} offset 24h))[1h:])\n /\n avg_over_time(histogram_quantile(0.99, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\", route=~\"api_(v1|prom)_push|otlp_v1_metrics\"}))[1h:])\n)\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "writes",
|
||||
"legendLink": null
|
||||
},
|
||||
{
|
||||
"expr": "1 - (\n avg_over_time(histogram_quantile(0.99, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"} offset 24h))[1h:])\n /\n avg_over_time(histogram_quantile(0.99, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"}))[1h:])\n)\n",
|
||||
"expr": "1 - (\n avg_over_time(histogram_quantile(0.99, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"} offset 24h))[1h:])\n /\n avg_over_time(histogram_quantile(0.99, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"}))[1h:])\n)\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "reads",
|
||||
|
||||
@@ -67,7 +67,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(cortex_ruler_managers_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"})",
|
||||
"expr": "sum(cortex_ruler_managers_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\"})",
|
||||
"format": "time_series",
|
||||
"instant": true,
|
||||
"intervalFactor": 2,
|
||||
@@ -143,7 +143,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(cortex_prometheus_rule_group_rules{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"})",
|
||||
"expr": "sum(cortex_prometheus_rule_group_rules{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\"})",
|
||||
"format": "time_series",
|
||||
"instant": true,
|
||||
"intervalFactor": 2,
|
||||
@@ -220,7 +220,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(rate(cortex_ingester_client_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*|ruler-querier.*))\", operation=\"/cortex.Ingester/QueryStream\"}[$__rate_interval]))",
|
||||
"expr": "sum(rate(cortex_ingester_client_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*|ruler-querier.*))\", operation=\"/cortex.Ingester/QueryStream\"}[$__rate_interval]))",
|
||||
"format": "time_series",
|
||||
"instant": true,
|
||||
"intervalFactor": 2,
|
||||
@@ -296,7 +296,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(rate(cortex_ingester_client_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\", operation=\"/cortex.Ingester/Push\"}[$__rate_interval]))",
|
||||
"expr": "sum(rate(cortex_ingester_client_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\", operation=\"/cortex.Ingester/Push\"}[$__rate_interval]))",
|
||||
"format": "time_series",
|
||||
"instant": true,
|
||||
"intervalFactor": 2,
|
||||
@@ -386,21 +386,21 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(rate(cortex_prometheus_rule_evaluations_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n-\nsum(rate(cortex_prometheus_rule_evaluation_failures_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n",
|
||||
"expr": "sum(rate(cortex_prometheus_rule_evaluations_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n-\nsum(rate(cortex_prometheus_rule_evaluation_failures_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "success",
|
||||
"legendLink": null
|
||||
},
|
||||
{
|
||||
"expr": "sum(rate(cortex_prometheus_rule_evaluation_failures_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))",
|
||||
"expr": "sum(rate(cortex_prometheus_rule_evaluation_failures_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "failed",
|
||||
"legendLink": null
|
||||
},
|
||||
{
|
||||
"expr": "sum(rate(cortex_prometheus_rule_group_iterations_missed_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))",
|
||||
"expr": "sum(rate(cortex_prometheus_rule_group_iterations_missed_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "missed",
|
||||
@@ -475,7 +475,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum (rate(cortex_prometheus_rule_evaluation_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n /\nsum (rate(cortex_prometheus_rule_evaluation_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n",
|
||||
"expr": "sum (rate(cortex_prometheus_rule_evaluation_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n /\nsum (rate(cortex_prometheus_rule_evaluation_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "average",
|
||||
@@ -571,7 +571,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_ingester_client_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\", operation=\"/cortex.Ingester/Push\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-z]+)\"))\n",
|
||||
"expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_ingester_client_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\", operation=\"/cortex.Ingester/Push\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-z]+)\"))\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{status}}",
|
||||
@@ -646,21 +646,21 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "histogram_quantile(0.99, sum(rate(cortex_ingester_client_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\", operation=\"/cortex.Ingester/Push\"}[$__rate_interval])) by (le)) * 1e3",
|
||||
"expr": "histogram_quantile(0.99, sum(rate(cortex_ingester_client_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\", operation=\"/cortex.Ingester/Push\"}[$__rate_interval])) by (le)) * 1e3",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "99th Percentile",
|
||||
"refId": "A"
|
||||
},
|
||||
{
|
||||
"expr": "histogram_quantile(0.50, sum(rate(cortex_ingester_client_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\", operation=\"/cortex.Ingester/Push\"}[$__rate_interval])) by (le)) * 1e3",
|
||||
"expr": "histogram_quantile(0.50, sum(rate(cortex_ingester_client_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\", operation=\"/cortex.Ingester/Push\"}[$__rate_interval])) by (le)) * 1e3",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "50th Percentile",
|
||||
"refId": "B"
|
||||
},
|
||||
{
|
||||
"expr": "sum(rate(cortex_ingester_client_request_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\", operation=\"/cortex.Ingester/Push\"}[$__rate_interval])) * 1e3 / sum(rate(cortex_ingester_client_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\", operation=\"/cortex.Ingester/Push\"}[$__rate_interval]))",
|
||||
"expr": "sum(rate(cortex_ingester_client_request_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\", operation=\"/cortex.Ingester/Push\"}[$__rate_interval])) * 1e3 / sum(rate(cortex_ingester_client_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\", operation=\"/cortex.Ingester/Push\"}[$__rate_interval]))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "Average",
|
||||
@@ -756,7 +756,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_ingester_client_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*|ruler-querier.*))\", operation=\"/cortex.Ingester/QueryStream\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-z]+)\"))\n",
|
||||
"expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_ingester_client_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*|ruler-querier.*))\", operation=\"/cortex.Ingester/QueryStream\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-z]+)\"))\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{status}}",
|
||||
@@ -831,21 +831,21 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "histogram_quantile(0.99, sum(rate(cortex_ingester_client_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*|ruler-querier.*))\", operation=\"/cortex.Ingester/QueryStream\"}[$__rate_interval])) by (le)) * 1e3",
|
||||
"expr": "histogram_quantile(0.99, sum(rate(cortex_ingester_client_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*|ruler-querier.*))\", operation=\"/cortex.Ingester/QueryStream\"}[$__rate_interval])) by (le)) * 1e3",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "99th Percentile",
|
||||
"refId": "A"
|
||||
},
|
||||
{
|
||||
"expr": "histogram_quantile(0.50, sum(rate(cortex_ingester_client_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*|ruler-querier.*))\", operation=\"/cortex.Ingester/QueryStream\"}[$__rate_interval])) by (le)) * 1e3",
|
||||
"expr": "histogram_quantile(0.50, sum(rate(cortex_ingester_client_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*|ruler-querier.*))\", operation=\"/cortex.Ingester/QueryStream\"}[$__rate_interval])) by (le)) * 1e3",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "50th Percentile",
|
||||
"refId": "B"
|
||||
},
|
||||
{
|
||||
"expr": "sum(rate(cortex_ingester_client_request_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*|ruler-querier.*))\", operation=\"/cortex.Ingester/QueryStream\"}[$__rate_interval])) * 1e3 / sum(rate(cortex_ingester_client_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*|ruler-querier.*))\", operation=\"/cortex.Ingester/QueryStream\"}[$__rate_interval]))",
|
||||
"expr": "sum(rate(cortex_ingester_client_request_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*|ruler-querier.*))\", operation=\"/cortex.Ingester/QueryStream\"}[$__rate_interval])) * 1e3 / sum(rate(cortex_ingester_client_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*|ruler-querier.*))\", operation=\"/cortex.Ingester/QueryStream\"}[$__rate_interval]))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "Average",
|
||||
@@ -941,7 +941,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_kv_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\", kv_name=~\"ruler\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-z]+)\"))\n",
|
||||
"expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_kv_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\", kv_name=~\"ruler\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-z]+)\"))\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{status}}",
|
||||
@@ -1016,21 +1016,21 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "histogram_quantile(0.99, sum(rate(cortex_kv_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\", kv_name=~\"ruler\"}[$__rate_interval])) by (le)) * 1e3",
|
||||
"expr": "histogram_quantile(0.99, sum(rate(cortex_kv_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\", kv_name=~\"ruler\"}[$__rate_interval])) by (le)) * 1e3",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "99th Percentile",
|
||||
"refId": "A"
|
||||
},
|
||||
{
|
||||
"expr": "histogram_quantile(0.50, sum(rate(cortex_kv_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\", kv_name=~\"ruler\"}[$__rate_interval])) by (le)) * 1e3",
|
||||
"expr": "histogram_quantile(0.50, sum(rate(cortex_kv_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\", kv_name=~\"ruler\"}[$__rate_interval])) by (le)) * 1e3",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "50th Percentile",
|
||||
"refId": "B"
|
||||
},
|
||||
{
|
||||
"expr": "sum(rate(cortex_kv_request_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\", kv_name=~\"ruler\"}[$__rate_interval])) * 1e3 / sum(rate(cortex_kv_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\", kv_name=~\"ruler\"}[$__rate_interval]))",
|
||||
"expr": "sum(rate(cortex_kv_request_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\", kv_name=~\"ruler\"}[$__rate_interval])) * 1e3 / sum(rate(cortex_kv_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\", kv_name=~\"ruler\"}[$__rate_interval]))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "Average",
|
||||
@@ -1117,21 +1117,21 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "histogram_quantile(0.99, sum(rate(cortex_querier_storegateway_instances_hit_per_query_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) by (le)) * 1",
|
||||
"expr": "histogram_quantile(0.99, sum(rate(cortex_querier_storegateway_instances_hit_per_query_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) by (le)) * 1",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "99th Percentile",
|
||||
"refId": "A"
|
||||
},
|
||||
{
|
||||
"expr": "histogram_quantile(0.50, sum(rate(cortex_querier_storegateway_instances_hit_per_query_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) by (le)) * 1",
|
||||
"expr": "histogram_quantile(0.50, sum(rate(cortex_querier_storegateway_instances_hit_per_query_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) by (le)) * 1",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "50th Percentile",
|
||||
"refId": "B"
|
||||
},
|
||||
{
|
||||
"expr": "sum(rate(cortex_querier_storegateway_instances_hit_per_query_sum{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) * 1 / sum(rate(cortex_querier_storegateway_instances_hit_per_query_count{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))",
|
||||
"expr": "sum(rate(cortex_querier_storegateway_instances_hit_per_query_sum{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) * 1 / sum(rate(cortex_querier_storegateway_instances_hit_per_query_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "Average",
|
||||
@@ -1206,21 +1206,21 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "histogram_quantile(0.99, sum(rate(cortex_querier_storegateway_refetches_per_query_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) by (le)) * 1",
|
||||
"expr": "histogram_quantile(0.99, sum(rate(cortex_querier_storegateway_refetches_per_query_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) by (le)) * 1",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "99th Percentile",
|
||||
"refId": "A"
|
||||
},
|
||||
{
|
||||
"expr": "histogram_quantile(0.50, sum(rate(cortex_querier_storegateway_refetches_per_query_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) by (le)) * 1",
|
||||
"expr": "histogram_quantile(0.50, sum(rate(cortex_querier_storegateway_refetches_per_query_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) by (le)) * 1",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "50th Percentile",
|
||||
"refId": "B"
|
||||
},
|
||||
{
|
||||
"expr": "sum(rate(cortex_querier_storegateway_refetches_per_query_sum{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) * 1 / sum(rate(cortex_querier_storegateway_refetches_per_query_count{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))",
|
||||
"expr": "sum(rate(cortex_querier_storegateway_refetches_per_query_sum{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) * 1 / sum(rate(cortex_querier_storegateway_refetches_per_query_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "Average",
|
||||
@@ -1297,7 +1297,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(rate(cortex_querier_blocks_consistency_checks_failed_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) / sum(rate(cortex_querier_blocks_consistency_checks_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))",
|
||||
"expr": "sum(rate(cortex_querier_blocks_consistency_checks_failed_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) / sum(rate(cortex_querier_blocks_consistency_checks_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "Failures / sec",
|
||||
@@ -1374,7 +1374,7 @@
|
||||
"span": 4,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum by(user) (rate(cortex_prometheus_notifications_errors_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n /\nsum by(user) (rate(cortex_prometheus_notifications_sent_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]) > 0)\n> 0\n",
|
||||
"expr": "sum by(user) (rate(cortex_prometheus_notifications_errors_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n /\nsum by(user) (rate(cortex_prometheus_notifications_sent_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]) > 0)\n> 0\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{ user }}",
|
||||
@@ -1422,7 +1422,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum by(user) (rate(cortex_prometheus_notifications_queue_length{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n /\nsum by(user) (rate(cortex_prometheus_notifications_queue_capacity{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) > 0\n",
|
||||
"expr": "sum by(user) (rate(cortex_prometheus_notifications_queue_length{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n /\nsum by(user) (rate(cortex_prometheus_notifications_queue_capacity{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) > 0\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{ user }}",
|
||||
@@ -1487,7 +1487,7 @@
|
||||
"span": 4,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum by (user) (increase(cortex_prometheus_notifications_dropped_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) > 0\n",
|
||||
"expr": "sum by (user) (increase(cortex_prometheus_notifications_dropped_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) > 0\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{ user }}",
|
||||
@@ -1541,7 +1541,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum by(user) (rate(cortex_prometheus_rule_group_iterations_missed_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) > 0",
|
||||
"expr": "sum by(user) (rate(cortex_prometheus_rule_group_iterations_missed_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) > 0",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{ user }}",
|
||||
@@ -1616,7 +1616,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "rate(cortex_prometheus_rule_group_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])\n /\nrate(cortex_prometheus_rule_group_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])\n",
|
||||
"expr": "rate(cortex_prometheus_rule_group_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])\n /\nrate(cortex_prometheus_rule_group_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{ user }}",
|
||||
@@ -1691,7 +1691,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum by(rule_group) (rate(cortex_prometheus_rule_evaluation_failures_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) > 0",
|
||||
"expr": "sum by(rule_group) (rate(cortex_prometheus_rule_evaluation_failures_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) > 0",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{ rule_group }}",
|
||||
@@ -1778,7 +1778,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum by(user) (rate(cortex_prometheus_rule_evaluation_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n /\nsum by(user) (rate(cortex_prometheus_rule_evaluation_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n",
|
||||
"expr": "sum by(user) (rate(cortex_prometheus_rule_evaluation_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n /\nsum by(user) (rate(cortex_prometheus_rule_evaluation_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{ user }}",
|
||||
|
||||
@@ -96,7 +96,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(\n (\n cortex_ingester_memory_series_created_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", user=\"$user\"}\n - cortex_ingester_memory_series_removed_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", user=\"$user\"}\n )\n / on(cluster, namespace) group_left\n max by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\"})\n)\n",
|
||||
"expr": "sum(\n (\n cortex_ingester_memory_series_created_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\", user=\"$user\"}\n - cortex_ingester_memory_series_removed_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\", user=\"$user\"}\n )\n / on(cluster, namespace) group_left\n max by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\"})\n)\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "in-memory",
|
||||
@@ -110,14 +110,14 @@
|
||||
"legendLink": null
|
||||
},
|
||||
{
|
||||
"expr": "sum(\n cortex_ingester_active_series{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", user=\"$user\"}\n / on(cluster, namespace) group_left\n max by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\"})\n)\n",
|
||||
"expr": "sum(\n cortex_ingester_active_series{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\", user=\"$user\"}\n / on(cluster, namespace) group_left\n max by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\"})\n)\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "active",
|
||||
"legendLink": null
|
||||
},
|
||||
{
|
||||
"expr": "sum by (name) (\n cortex_ingester_active_series_custom_tracker{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", user=\"$user\"}\n / on(cluster, namespace) group_left\n max by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\"})\n) > 0\n",
|
||||
"expr": "sum by (name) (\n cortex_ingester_active_series_custom_tracker{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\", user=\"$user\"}\n / on(cluster, namespace) group_left\n max by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\"})\n) > 0\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "active ({{ name }})",
|
||||
@@ -199,14 +199,14 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(\n cortex_ingester_active_native_histogram_series{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", user=\"$user\"}\n / on(cluster, namespace) group_left\n max by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\"})\n)\n",
|
||||
"expr": "sum(\n cortex_ingester_active_native_histogram_series{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\", user=\"$user\"}\n / on(cluster, namespace) group_left\n max by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\"})\n)\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "active",
|
||||
"legendLink": null
|
||||
},
|
||||
{
|
||||
"expr": "sum by (name) (\n cortex_ingester_active_native_histogram_series_custom_tracker{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", user=\"$user\"}\n / on(cluster, namespace) group_left\n max by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\"})\n) > 0\n",
|
||||
"expr": "sum by (name) (\n cortex_ingester_active_native_histogram_series_custom_tracker{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\", user=\"$user\"}\n / on(cluster, namespace) group_left\n max by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\"})\n) > 0\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "active ({{ name }})",
|
||||
@@ -288,14 +288,14 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(\n cortex_ingester_active_native_histogram_buckets{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", user=\"$user\"}\n / on(cluster, namespace) group_left\n max by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\"})\n)\n",
|
||||
"expr": "sum(\n cortex_ingester_active_native_histogram_buckets{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\", user=\"$user\"}\n / on(cluster, namespace) group_left\n max by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\"})\n)\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "buckets",
|
||||
"legendLink": null
|
||||
},
|
||||
{
|
||||
"expr": "sum by (name) (\n cortex_ingester_active_native_histogram_buckets_custom_tracker{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", user=\"$user\"}\n / on(cluster, namespace) group_left\n max by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\"})\n) > 0\n",
|
||||
"expr": "sum by (name) (\n cortex_ingester_active_native_histogram_buckets_custom_tracker{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\", user=\"$user\"}\n / on(cluster, namespace) group_left\n max by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\"})\n) > 0\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "buckets ({{ name }})",
|
||||
@@ -377,7 +377,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(\n cortex_ingester_tsdb_exemplar_series_with_exemplars_in_storage{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", user=\"$user\"}\n / on(cluster, namespace) group_left\n max by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\"})\n)\n",
|
||||
"expr": "sum(\n cortex_ingester_tsdb_exemplar_series_with_exemplars_in_storage{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\", user=\"$user\"}\n / on(cluster, namespace) group_left\n max by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\"})\n)\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "series",
|
||||
@@ -447,7 +447,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "time() - max(cortex_distributor_latest_seen_sample_timestamp_seconds{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", user=\"$user\"} > 0)",
|
||||
"expr": "time() - max(cortex_distributor_latest_seen_sample_timestamp_seconds{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\", user=\"$user\"} > 0)",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "age",
|
||||
@@ -517,7 +517,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "time() - min(cortex_ingester_tsdb_exemplar_last_exemplars_timestamp_seconds{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", user=\"$user\"} > 0)",
|
||||
"expr": "time() - min(cortex_ingester_tsdb_exemplar_last_exemplars_timestamp_seconds{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\", user=\"$user\"} > 0)",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "age",
|
||||
@@ -599,7 +599,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(rate(cortex_distributor_requests_in_total{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", user=\"$user\"}[$__rate_interval]))",
|
||||
"expr": "sum(rate(cortex_distributor_requests_in_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\", user=\"$user\"}[$__rate_interval]))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "rate",
|
||||
@@ -681,7 +681,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(rate(cortex_distributor_received_requests_total{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", user=\"$user\"}[$__rate_interval]))",
|
||||
"expr": "sum(rate(cortex_distributor_received_requests_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\", user=\"$user\"}[$__rate_interval]))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "rate",
|
||||
@@ -764,7 +764,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum by (reason) (rate(cortex_discarded_requests_total{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", user=\"$user\"}[$__rate_interval]))",
|
||||
"expr": "sum by (reason) (rate(cortex_discarded_requests_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\", user=\"$user\"}[$__rate_interval]))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{ reason }}",
|
||||
@@ -846,7 +846,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(rate(cortex_distributor_samples_in_total{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", user=\"$user\"}[$__rate_interval]))",
|
||||
"expr": "sum(rate(cortex_distributor_samples_in_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\", user=\"$user\"}[$__rate_interval]))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "rate",
|
||||
@@ -928,7 +928,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(rate(cortex_distributor_received_samples_total{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", user=\"$user\"}[$__rate_interval]))",
|
||||
"expr": "sum(rate(cortex_distributor_received_samples_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\", user=\"$user\"}[$__rate_interval]))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "rate",
|
||||
@@ -1011,14 +1011,14 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(rate(cortex_distributor_deduped_samples_total{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", user=\"$user\"}[$__rate_interval]))",
|
||||
"expr": "sum(rate(cortex_distributor_deduped_samples_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\", user=\"$user\"}[$__rate_interval]))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "deduplicated",
|
||||
"legendLink": null
|
||||
},
|
||||
{
|
||||
"expr": "sum(rate(cortex_distributor_non_ha_samples_received_total{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", user=\"$user\"}[$__rate_interval]))",
|
||||
"expr": "sum(rate(cortex_distributor_non_ha_samples_received_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\", user=\"$user\"}[$__rate_interval]))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "non-HA",
|
||||
@@ -1094,14 +1094,14 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum by (reason) (rate(cortex_discarded_samples_total{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", user=\"$user\"}[$__rate_interval]))",
|
||||
"expr": "sum by (reason) (rate(cortex_discarded_samples_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\", user=\"$user\"}[$__rate_interval]))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{ reason }} (distributor)",
|
||||
"legendLink": null
|
||||
},
|
||||
{
|
||||
"expr": "sum by (reason) (rate(cortex_discarded_samples_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", user=\"$user\"}[$__rate_interval]))",
|
||||
"expr": "sum by (reason) (rate(cortex_discarded_samples_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\", user=\"$user\"}[$__rate_interval]))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{ reason }} (ingester)",
|
||||
@@ -1183,7 +1183,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(rate(cortex_distributor_exemplars_in_total{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", user=\"$user\"}[$__rate_interval]))",
|
||||
"expr": "sum(rate(cortex_distributor_exemplars_in_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\", user=\"$user\"}[$__rate_interval]))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "rate",
|
||||
@@ -1253,7 +1253,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(rate(cortex_distributor_received_exemplars_total{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", user=\"$user\"}[$__rate_interval]))",
|
||||
"expr": "sum(rate(cortex_distributor_received_exemplars_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\", user=\"$user\"}[$__rate_interval]))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "rate",
|
||||
@@ -1329,7 +1329,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum by (reason) (rate(cortex_discarded_exemplars_total{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", user=\"$user\"}[$__rate_interval]))",
|
||||
"expr": "sum by (reason) (rate(cortex_discarded_exemplars_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\", user=\"$user\"}[$__rate_interval]))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{ reason }}",
|
||||
@@ -1399,7 +1399,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(\n rate(cortex_ingester_tsdb_exemplar_exemplars_appended_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", user=\"$user\"}[$__rate_interval])\n / on(cluster, namespace) group_left\n max by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\"})\n)\n",
|
||||
"expr": "sum(\n rate(cortex_ingester_tsdb_exemplar_exemplars_appended_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\", user=\"$user\"}[$__rate_interval])\n / on(cluster, namespace) group_left\n max by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\"})\n)\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "rate",
|
||||
@@ -1487,7 +1487,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum by (job) (cortex_ingester_tsdb_symbol_table_size_bytes{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", user=\"$user\"})",
|
||||
"expr": "sum by (job) (cortex_ingester_tsdb_symbol_table_size_bytes{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\", user=\"$user\"})",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{ job }}",
|
||||
@@ -1563,7 +1563,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum by (job) (cortex_ingester_tsdb_storage_blocks_bytes{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", user=\"$user\"})",
|
||||
"expr": "sum by (job) (cortex_ingester_tsdb_storage_blocks_bytes{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\", user=\"$user\"})",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{ job }}",
|
||||
@@ -1657,7 +1657,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "count(sum by (rule_group) (cortex_prometheus_rule_group_rules{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\", user=\"$user\"}))",
|
||||
"expr": "count(sum by (rule_group) (cortex_prometheus_rule_group_rules{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\", user=\"$user\"}))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "groups",
|
||||
@@ -1734,7 +1734,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(cortex_prometheus_rule_group_rules{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\", user=\"$user\"})",
|
||||
"expr": "sum(cortex_prometheus_rule_group_rules{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\", user=\"$user\"})",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "rules",
|
||||
@@ -1803,7 +1803,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(rate(cortex_prometheus_rule_evaluations_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\", user=\"$user\"}[$__rate_interval]))",
|
||||
"expr": "sum(rate(cortex_prometheus_rule_evaluations_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\", user=\"$user\"}[$__rate_interval]))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "rate",
|
||||
@@ -1878,7 +1878,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum by (rule_group) (rate(cortex_prometheus_rule_evaluation_failures_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\", user=\"$user\"}[$__rate_interval])) > 0",
|
||||
"expr": "sum by (rule_group) (rate(cortex_prometheus_rule_evaluation_failures_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\", user=\"$user\"}[$__rate_interval])) > 0",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{ rule_group }}",
|
||||
@@ -2003,7 +2003,7 @@
|
||||
],
|
||||
"targets": [
|
||||
{
|
||||
"expr": "topk($limit, sum by (rule_group) (cortex_prometheus_rule_group_rules{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\", user=\"$user\"}))",
|
||||
"expr": "topk($limit, sum by (rule_group) (cortex_prometheus_rule_group_rules{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\", user=\"$user\"}))",
|
||||
"format": "table",
|
||||
"instant": true,
|
||||
"intervalFactor": 2,
|
||||
@@ -2118,7 +2118,7 @@
|
||||
],
|
||||
"targets": [
|
||||
{
|
||||
"expr": "topk($limit, sum by (rule_group) (cortex_prometheus_rule_group_last_duration_seconds{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\", user=\"$user\"}))",
|
||||
"expr": "topk($limit, sum by (rule_group) (cortex_prometheus_rule_group_last_duration_seconds{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\", user=\"$user\"}))",
|
||||
"format": "table",
|
||||
"instant": true,
|
||||
"intervalFactor": 2,
|
||||
@@ -2201,7 +2201,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(rate(cortex_prometheus_notifications_sent_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\", user=\"$user\"}[$__rate_interval]))",
|
||||
"expr": "sum(rate(cortex_prometheus_notifications_sent_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\", user=\"$user\"}[$__rate_interval]))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "rate",
|
||||
@@ -2272,7 +2272,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(rate(cortex_prometheus_notifications_errors_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\", user=\"$user\"}[$__rate_interval]))",
|
||||
"expr": "sum(rate(cortex_prometheus_notifications_errors_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\", user=\"$user\"}[$__rate_interval]))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "rate",
|
||||
@@ -2359,7 +2359,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(rate(cortex_query_frontend_queries_total{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", user=\"$user\"}[$__rate_interval]))",
|
||||
"expr": "sum(rate(cortex_query_frontend_queries_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\", user=\"$user\"}[$__rate_interval]))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "Queries / Sec",
|
||||
|
||||
@@ -127,7 +127,7 @@
|
||||
],
|
||||
"targets": [
|
||||
{
|
||||
"expr": "topk($limit,\n sum by (user) (\n cortex_ingester_active_series{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}\n / on(cluster, namespace) group_left\n max by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\"})\n )\n)\n",
|
||||
"expr": "topk($limit,\n sum by (user) (\n cortex_ingester_active_series{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\"}\n / on(cluster, namespace) group_left\n max by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\"})\n )\n)\n",
|
||||
"format": "table",
|
||||
"instant": true,
|
||||
"intervalFactor": 2,
|
||||
@@ -254,7 +254,7 @@
|
||||
],
|
||||
"targets": [
|
||||
{
|
||||
"expr": "topk($limit, sum by (user) (\n (\n sum by (user, cluster, namespace) (cortex_ingester_memory_series_created_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"} )\n -\n sum by (user, cluster, namespace) (cortex_ingester_memory_series_removed_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"} )\n )\n / on(cluster, namespace) group_left\n max by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\"} )\n)\n)",
|
||||
"expr": "topk($limit, sum by (user) (\n (\n sum by (user, cluster, namespace) (cortex_ingester_memory_series_created_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\"} )\n -\n sum by (user, cluster, namespace) (cortex_ingester_memory_series_removed_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\"} )\n )\n / on(cluster, namespace) group_left\n max by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\"} )\n)\n)",
|
||||
"format": "table",
|
||||
"instant": true,
|
||||
"intervalFactor": 2,
|
||||
@@ -343,7 +343,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum by (user) (\n (\n sum by (user, cluster, namespace) (cortex_ingester_memory_series_created_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"} )\n -\n sum by (user, cluster, namespace) (cortex_ingester_memory_series_removed_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"} )\n )\n / on(cluster, namespace) group_left\n max by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\"} )\n)\n\nand\ntopk($limit, sum by (user) (\n (\n sum by (user, cluster, namespace) (cortex_ingester_memory_series_created_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"} @ end())\n -\n sum by (user, cluster, namespace) (cortex_ingester_memory_series_removed_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"} @ end())\n )\n / on(cluster, namespace) group_left\n max by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\"} @ end())\n)\n - sum by (user) (\n (\n sum by (user, cluster, namespace) (cortex_ingester_memory_series_created_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"} @ start())\n -\n sum by (user, cluster, namespace) (cortex_ingester_memory_series_removed_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"} @ start())\n )\n / on(cluster, namespace) group_left\n max by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\"} @ start())\n)\n)\n",
|
||||
"expr": "sum by (user) (\n (\n sum by (user, cluster, namespace) (cortex_ingester_memory_series_created_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\"} )\n -\n sum by (user, cluster, namespace) (cortex_ingester_memory_series_removed_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\"} )\n )\n / on(cluster, namespace) group_left\n max by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\"} )\n)\n\nand\ntopk($limit, sum by (user) (\n (\n sum by (user, cluster, namespace) (cortex_ingester_memory_series_created_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\"} @ end())\n -\n sum by (user, cluster, namespace) (cortex_ingester_memory_series_removed_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\"} @ end())\n )\n / on(cluster, namespace) group_left\n max by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\"} @ end())\n)\n - sum by (user) (\n (\n sum by (user, cluster, namespace) (cortex_ingester_memory_series_created_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\"} @ start())\n -\n sum by (user, cluster, namespace) (cortex_ingester_memory_series_removed_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\"} @ start())\n )\n / on(cluster, namespace) group_left\n max by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\"} @ start())\n)\n)\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{ user }}",
|
||||
@@ -468,7 +468,7 @@
|
||||
],
|
||||
"targets": [
|
||||
{
|
||||
"expr": "topk($limit, sum by (user) (rate(cortex_distributor_received_samples_total{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\"}[5m])))",
|
||||
"expr": "topk($limit, sum by (user) (rate(cortex_distributor_received_samples_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\"}[5m])))",
|
||||
"format": "table",
|
||||
"instant": true,
|
||||
"intervalFactor": 2,
|
||||
@@ -557,7 +557,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum by (user) (rate(cortex_distributor_received_samples_total{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\"}[$__rate_interval]))\nand\ntopk($limit,\n sum by (user) (rate(cortex_distributor_received_samples_total{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\"}[$__rate_interval] @ end()))\n -\n sum by (user) (rate(cortex_distributor_received_samples_total{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\"}[$__rate_interval] @ start()))\n)\n",
|
||||
"expr": "sum by (user) (rate(cortex_distributor_received_samples_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\"}[$__rate_interval]))\nand\ntopk($limit,\n sum by (user) (rate(cortex_distributor_received_samples_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\"}[$__rate_interval] @ end()))\n -\n sum by (user) (rate(cortex_distributor_received_samples_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\"}[$__rate_interval] @ start()))\n)\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{ user }}",
|
||||
@@ -682,7 +682,7 @@
|
||||
],
|
||||
"targets": [
|
||||
{
|
||||
"expr": "topk($limit, sum by (user) (rate(cortex_discarded_samples_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*|distributor|cortex|mimir|mimir-write.*))\"}[5m])))",
|
||||
"expr": "topk($limit, sum by (user) (rate(cortex_discarded_samples_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*|.*distributor|cortex|mimir|mimir-write.*))\"}[5m])))",
|
||||
"format": "table",
|
||||
"instant": true,
|
||||
"intervalFactor": 2,
|
||||
@@ -771,7 +771,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum by (user) (rate(cortex_discarded_samples_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*|distributor|cortex|mimir|mimir-write.*))\"}[$__rate_interval]))\nand\ntopk($limit,\n sum by (user) (rate(cortex_discarded_samples_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*|distributor|cortex|mimir|mimir-write.*))\"}[$__rate_interval] @ end()))\n -\n sum by (user) (rate(cortex_discarded_samples_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*|distributor|cortex|mimir|mimir-write.*))\"}[$__rate_interval] @ start()))\n)\n",
|
||||
"expr": "sum by (user) (rate(cortex_discarded_samples_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*|.*distributor|cortex|mimir|mimir-write.*))\"}[$__rate_interval]))\nand\ntopk($limit,\n sum by (user) (rate(cortex_discarded_samples_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*|.*distributor|cortex|mimir|mimir-write.*))\"}[$__rate_interval] @ end()))\n -\n sum by (user) (rate(cortex_discarded_samples_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*|.*distributor|cortex|mimir|mimir-write.*))\"}[$__rate_interval] @ start()))\n)\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{ user }}",
|
||||
@@ -896,7 +896,7 @@
|
||||
],
|
||||
"targets": [
|
||||
{
|
||||
"expr": "topk($limit,\n sum by (user) (\n cortex_ingester_tsdb_exemplar_series_with_exemplars_in_storage{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}\n / on(cluster, namespace) group_left\n max by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\"})\n )\n)\n",
|
||||
"expr": "topk($limit,\n sum by (user) (\n cortex_ingester_tsdb_exemplar_series_with_exemplars_in_storage{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\"}\n / on(cluster, namespace) group_left\n max by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\"})\n )\n)\n",
|
||||
"format": "table",
|
||||
"instant": true,
|
||||
"intervalFactor": 2,
|
||||
@@ -1023,7 +1023,7 @@
|
||||
],
|
||||
"targets": [
|
||||
{
|
||||
"expr": "topk($limit, sum by (user) (rate(cortex_distributor_received_exemplars_total{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\"}[5m])))",
|
||||
"expr": "topk($limit, sum by (user) (rate(cortex_distributor_received_exemplars_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\"}[5m])))",
|
||||
"format": "table",
|
||||
"instant": true,
|
||||
"intervalFactor": 2,
|
||||
@@ -1150,7 +1150,7 @@
|
||||
],
|
||||
"targets": [
|
||||
{
|
||||
"expr": "topk($limit, sum by (rule_group, user) (cortex_prometheus_rule_group_rules{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}))",
|
||||
"expr": "topk($limit, sum by (rule_group, user) (cortex_prometheus_rule_group_rules{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\"}))",
|
||||
"format": "table",
|
||||
"instant": true,
|
||||
"intervalFactor": 2,
|
||||
@@ -1277,7 +1277,7 @@
|
||||
],
|
||||
"targets": [
|
||||
{
|
||||
"expr": "topk($limit, sum by (rule_group, user) (cortex_prometheus_rule_group_last_duration_seconds{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}))",
|
||||
"expr": "topk($limit, sum by (rule_group, user) (cortex_prometheus_rule_group_last_duration_seconds{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\"}))",
|
||||
"format": "table",
|
||||
"instant": true,
|
||||
"intervalFactor": 2,
|
||||
|
||||
@@ -590,7 +590,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum by(pod) (cortex_ingester_memory_series{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"})",
|
||||
"expr": "sum by(pod) (cortex_ingester_memory_series{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\"})",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{pod}}",
|
||||
|
||||
@@ -90,7 +90,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(cluster_namespace_job:cortex_distributor_received_samples:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\"})",
|
||||
"expr": "sum(cluster_namespace_job:cortex_distributor_received_samples:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\"})",
|
||||
"format": "time_series",
|
||||
"instant": true,
|
||||
"intervalFactor": 2,
|
||||
@@ -167,7 +167,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(cluster_namespace_job:cortex_distributor_received_exemplars:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\"})",
|
||||
"expr": "sum(cluster_namespace_job:cortex_distributor_received_exemplars:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\"})",
|
||||
"format": "time_series",
|
||||
"instant": true,
|
||||
"intervalFactor": 2,
|
||||
@@ -244,7 +244,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(cortex_ingester_memory_series{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}\n/ on(cluster, namespace) group_left\nmax by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\"}))\n",
|
||||
"expr": "sum(cortex_ingester_memory_series{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\"}\n/ on(cluster, namespace) group_left\nmax by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\"}))\n",
|
||||
"format": "time_series",
|
||||
"instant": true,
|
||||
"intervalFactor": 2,
|
||||
@@ -321,7 +321,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(cortex_ingester_tsdb_exemplar_exemplars_in_storage{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}\n/ on(cluster, namespace) group_left\nmax by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\"}))\n",
|
||||
"expr": "sum(cortex_ingester_tsdb_exemplar_exemplars_in_storage{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\"}\n/ on(cluster, namespace) group_left\nmax by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\"}))\n",
|
||||
"format": "time_series",
|
||||
"instant": true,
|
||||
"intervalFactor": 2,
|
||||
@@ -397,7 +397,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "count(count by(user) (cortex_ingester_active_series{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}))",
|
||||
"expr": "count(count by(user) (cortex_ingester_active_series{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\"}))",
|
||||
"format": "time_series",
|
||||
"instant": true,
|
||||
"intervalFactor": 2,
|
||||
@@ -493,7 +493,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", route=~\"/distributor.Distributor/Push|/httpgrpc.*|api_(v1|prom)_push|otlp_v1_metrics\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-z]+)\"))\n",
|
||||
"expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\", route=~\"/distributor.Distributor/Push|/httpgrpc.*|api_(v1|prom)_push|otlp_v1_metrics\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-z]+)\"))\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{status}}",
|
||||
@@ -568,7 +568,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "histogram_quantile(0.99, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", route=~\"/distributor.Distributor/Push|/httpgrpc.*|api_(v1|prom)_push|otlp_v1_metrics\"})) * 1e3",
|
||||
"expr": "histogram_quantile(0.99, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\", route=~\"/distributor.Distributor/Push|/httpgrpc.*|api_(v1|prom)_push|otlp_v1_metrics\"})) * 1e3",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "99th Percentile",
|
||||
@@ -576,7 +576,7 @@
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"expr": "histogram_quantile(0.50, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", route=~\"/distributor.Distributor/Push|/httpgrpc.*|api_(v1|prom)_push|otlp_v1_metrics\"})) * 1e3",
|
||||
"expr": "histogram_quantile(0.50, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\", route=~\"/distributor.Distributor/Push|/httpgrpc.*|api_(v1|prom)_push|otlp_v1_metrics\"})) * 1e3",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "50th Percentile",
|
||||
@@ -584,7 +584,7 @@
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"expr": "1e3 * sum(cluster_job_route:cortex_request_duration_seconds_sum:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", route=~\"/distributor.Distributor/Push|/httpgrpc.*|api_(v1|prom)_push|otlp_v1_metrics\"}) / sum(cluster_job_route:cortex_request_duration_seconds_count:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", route=~\"/distributor.Distributor/Push|/httpgrpc.*|api_(v1|prom)_push|otlp_v1_metrics\"})",
|
||||
"expr": "1e3 * sum(cluster_job_route:cortex_request_duration_seconds_sum:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\", route=~\"/distributor.Distributor/Push|/httpgrpc.*|api_(v1|prom)_push|otlp_v1_metrics\"}) / sum(cluster_job_route:cortex_request_duration_seconds_count:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\", route=~\"/distributor.Distributor/Push|/httpgrpc.*|api_(v1|prom)_push|otlp_v1_metrics\"})",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "Average",
|
||||
@@ -668,7 +668,7 @@
|
||||
"targets": [
|
||||
{
|
||||
"exemplar": true,
|
||||
"expr": "histogram_quantile(0.99, sum by(le, pod) (rate(cortex_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", route=~\"/distributor.Distributor/Push|/httpgrpc.*|api_(v1|prom)_push|otlp_v1_metrics\"}[$__rate_interval])))",
|
||||
"expr": "histogram_quantile(0.99, sum by(le, pod) (rate(cortex_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\", route=~\"/distributor.Distributor/Push|/httpgrpc.*|api_(v1|prom)_push|otlp_v1_metrics\"}[$__rate_interval])))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "",
|
||||
@@ -731,7 +731,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\",route=\"/cortex.Ingester/Push\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-z]+)\"))\n",
|
||||
"expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\",route=\"/cortex.Ingester/Push\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-z]+)\"))\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{status}}",
|
||||
@@ -806,7 +806,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "histogram_quantile(0.99, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", route=\"/cortex.Ingester/Push\"})) * 1e3",
|
||||
"expr": "histogram_quantile(0.99, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\", route=\"/cortex.Ingester/Push\"})) * 1e3",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "99th Percentile",
|
||||
@@ -814,7 +814,7 @@
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"expr": "histogram_quantile(0.50, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", route=\"/cortex.Ingester/Push\"})) * 1e3",
|
||||
"expr": "histogram_quantile(0.50, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\", route=\"/cortex.Ingester/Push\"})) * 1e3",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "50th Percentile",
|
||||
@@ -822,7 +822,7 @@
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"expr": "1e3 * sum(cluster_job_route:cortex_request_duration_seconds_sum:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", route=\"/cortex.Ingester/Push\"}) / sum(cluster_job_route:cortex_request_duration_seconds_count:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", route=\"/cortex.Ingester/Push\"})",
|
||||
"expr": "1e3 * sum(cluster_job_route:cortex_request_duration_seconds_sum:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\", route=\"/cortex.Ingester/Push\"}) / sum(cluster_job_route:cortex_request_duration_seconds_count:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\", route=\"/cortex.Ingester/Push\"})",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "Average",
|
||||
@@ -906,7 +906,7 @@
|
||||
"targets": [
|
||||
{
|
||||
"exemplar": true,
|
||||
"expr": "histogram_quantile(0.99, sum by(le, pod) (rate(cortex_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", route=\"/cortex.Ingester/Push\"}[$__rate_interval])))",
|
||||
"expr": "histogram_quantile(0.99, sum by(le, pod) (rate(cortex_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\", route=\"/cortex.Ingester/Push\"}[$__rate_interval])))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "",
|
||||
@@ -1302,7 +1302,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_kv_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", kv_name=~\"distributor-hatracker\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-z]+)\"))\n",
|
||||
"expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_kv_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\", kv_name=~\"distributor-hatracker\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-z]+)\"))\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{status}}",
|
||||
@@ -1377,21 +1377,21 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "histogram_quantile(0.99, sum(rate(cortex_kv_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", kv_name=~\"distributor-hatracker\"}[$__rate_interval])) by (le)) * 1e3",
|
||||
"expr": "histogram_quantile(0.99, sum(rate(cortex_kv_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\", kv_name=~\"distributor-hatracker\"}[$__rate_interval])) by (le)) * 1e3",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "99th Percentile",
|
||||
"refId": "A"
|
||||
},
|
||||
{
|
||||
"expr": "histogram_quantile(0.50, sum(rate(cortex_kv_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", kv_name=~\"distributor-hatracker\"}[$__rate_interval])) by (le)) * 1e3",
|
||||
"expr": "histogram_quantile(0.50, sum(rate(cortex_kv_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\", kv_name=~\"distributor-hatracker\"}[$__rate_interval])) by (le)) * 1e3",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "50th Percentile",
|
||||
"refId": "B"
|
||||
},
|
||||
{
|
||||
"expr": "sum(rate(cortex_kv_request_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", kv_name=~\"distributor-hatracker\"}[$__rate_interval])) * 1e3 / sum(rate(cortex_kv_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", kv_name=~\"distributor-hatracker\"}[$__rate_interval]))",
|
||||
"expr": "sum(rate(cortex_kv_request_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\", kv_name=~\"distributor-hatracker\"}[$__rate_interval])) * 1e3 / sum(rate(cortex_kv_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\", kv_name=~\"distributor-hatracker\"}[$__rate_interval]))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "Average",
|
||||
@@ -1487,7 +1487,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_kv_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", kv_name=~\"distributor-(lifecycler|ring)\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-z]+)\"))\n",
|
||||
"expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_kv_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\", kv_name=~\"distributor-(lifecycler|ring)\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-z]+)\"))\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{status}}",
|
||||
@@ -1562,21 +1562,21 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "histogram_quantile(0.99, sum(rate(cortex_kv_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", kv_name=~\"distributor-(lifecycler|ring)\"}[$__rate_interval])) by (le)) * 1e3",
|
||||
"expr": "histogram_quantile(0.99, sum(rate(cortex_kv_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\", kv_name=~\"distributor-(lifecycler|ring)\"}[$__rate_interval])) by (le)) * 1e3",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "99th Percentile",
|
||||
"refId": "A"
|
||||
},
|
||||
{
|
||||
"expr": "histogram_quantile(0.50, sum(rate(cortex_kv_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", kv_name=~\"distributor-(lifecycler|ring)\"}[$__rate_interval])) by (le)) * 1e3",
|
||||
"expr": "histogram_quantile(0.50, sum(rate(cortex_kv_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\", kv_name=~\"distributor-(lifecycler|ring)\"}[$__rate_interval])) by (le)) * 1e3",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "50th Percentile",
|
||||
"refId": "B"
|
||||
},
|
||||
{
|
||||
"expr": "sum(rate(cortex_kv_request_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", kv_name=~\"distributor-(lifecycler|ring)\"}[$__rate_interval])) * 1e3 / sum(rate(cortex_kv_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", kv_name=~\"distributor-(lifecycler|ring)\"}[$__rate_interval]))",
|
||||
"expr": "sum(rate(cortex_kv_request_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\", kv_name=~\"distributor-(lifecycler|ring)\"}[$__rate_interval])) * 1e3 / sum(rate(cortex_kv_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\", kv_name=~\"distributor-(lifecycler|ring)\"}[$__rate_interval]))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "Average",
|
||||
@@ -1672,7 +1672,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_kv_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", kv_name=~\"ingester-.*\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-z]+)\"))\n",
|
||||
"expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_kv_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\", kv_name=~\"ingester-.*\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-z]+)\"))\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{status}}",
|
||||
@@ -1747,21 +1747,21 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "histogram_quantile(0.99, sum(rate(cortex_kv_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", kv_name=~\"ingester-.*\"}[$__rate_interval])) by (le)) * 1e3",
|
||||
"expr": "histogram_quantile(0.99, sum(rate(cortex_kv_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\", kv_name=~\"ingester-.*\"}[$__rate_interval])) by (le)) * 1e3",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "99th Percentile",
|
||||
"refId": "A"
|
||||
},
|
||||
{
|
||||
"expr": "histogram_quantile(0.50, sum(rate(cortex_kv_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", kv_name=~\"ingester-.*\"}[$__rate_interval])) by (le)) * 1e3",
|
||||
"expr": "histogram_quantile(0.50, sum(rate(cortex_kv_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\", kv_name=~\"ingester-.*\"}[$__rate_interval])) by (le)) * 1e3",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "50th Percentile",
|
||||
"refId": "B"
|
||||
},
|
||||
{
|
||||
"expr": "sum(rate(cortex_kv_request_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", kv_name=~\"ingester-.*\"}[$__rate_interval])) * 1e3 / sum(rate(cortex_kv_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", kv_name=~\"ingester-.*\"}[$__rate_interval]))",
|
||||
"expr": "sum(rate(cortex_kv_request_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\", kv_name=~\"ingester-.*\"}[$__rate_interval])) * 1e3 / sum(rate(cortex_kv_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\", kv_name=~\"ingester-.*\"}[$__rate_interval]))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "Average",
|
||||
@@ -1852,14 +1852,14 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(rate(cortex_ingester_shipper_uploads_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval])) - sum(rate(cortex_ingester_shipper_upload_failures_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval]))",
|
||||
"expr": "sum(rate(cortex_ingester_shipper_uploads_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval])) - sum(rate(cortex_ingester_shipper_upload_failures_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval]))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "successful",
|
||||
"legendLink": null
|
||||
},
|
||||
{
|
||||
"expr": "sum(rate(cortex_ingester_shipper_upload_failures_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval]))",
|
||||
"expr": "sum(rate(cortex_ingester_shipper_upload_failures_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval]))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "failed",
|
||||
@@ -1935,21 +1935,21 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "histogram_quantile(0.99, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\",component=\"ingester\",operation=\"upload\"}[$__rate_interval])) by (le)) * 1e3",
|
||||
"expr": "histogram_quantile(0.99, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\",component=\"ingester\",operation=\"upload\"}[$__rate_interval])) by (le)) * 1e3",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "99th Percentile",
|
||||
"refId": "A"
|
||||
},
|
||||
{
|
||||
"expr": "histogram_quantile(0.50, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\",component=\"ingester\",operation=\"upload\"}[$__rate_interval])) by (le)) * 1e3",
|
||||
"expr": "histogram_quantile(0.50, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\",component=\"ingester\",operation=\"upload\"}[$__rate_interval])) by (le)) * 1e3",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "50th Percentile",
|
||||
"refId": "B"
|
||||
},
|
||||
{
|
||||
"expr": "sum(rate(thanos_objstore_bucket_operation_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\",component=\"ingester\",operation=\"upload\"}[$__rate_interval])) * 1e3 / sum(rate(thanos_objstore_bucket_operation_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\",component=\"ingester\",operation=\"upload\"}[$__rate_interval]))",
|
||||
"expr": "sum(rate(thanos_objstore_bucket_operation_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\",component=\"ingester\",operation=\"upload\"}[$__rate_interval])) * 1e3 / sum(rate(thanos_objstore_bucket_operation_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\",component=\"ingester\",operation=\"upload\"}[$__rate_interval]))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "Average",
|
||||
@@ -2040,14 +2040,14 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(rate(cortex_ingester_tsdb_compactions_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval]))",
|
||||
"expr": "sum(rate(cortex_ingester_tsdb_compactions_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval]))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "successful",
|
||||
"legendLink": null
|
||||
},
|
||||
{
|
||||
"expr": "sum(rate(cortex_ingester_tsdb_compactions_failed_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval]))",
|
||||
"expr": "sum(rate(cortex_ingester_tsdb_compactions_failed_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval]))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "failed",
|
||||
@@ -2123,21 +2123,21 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "histogram_quantile(0.99, sum(rate(cortex_ingester_tsdb_compaction_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval])) by (le)) * 1e3",
|
||||
"expr": "histogram_quantile(0.99, sum(rate(cortex_ingester_tsdb_compaction_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval])) by (le)) * 1e3",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "99th Percentile",
|
||||
"refId": "A"
|
||||
},
|
||||
{
|
||||
"expr": "histogram_quantile(0.50, sum(rate(cortex_ingester_tsdb_compaction_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval])) by (le)) * 1e3",
|
||||
"expr": "histogram_quantile(0.50, sum(rate(cortex_ingester_tsdb_compaction_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval])) by (le)) * 1e3",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "50th Percentile",
|
||||
"refId": "B"
|
||||
},
|
||||
{
|
||||
"expr": "sum(rate(cortex_ingester_tsdb_compaction_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval])) * 1e3 / sum(rate(cortex_ingester_tsdb_compaction_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval]))",
|
||||
"expr": "sum(rate(cortex_ingester_tsdb_compaction_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval])) * 1e3 / sum(rate(cortex_ingester_tsdb_compaction_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval]))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "Average",
|
||||
@@ -2228,14 +2228,14 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(rate(cortex_ingester_tsdb_wal_truncations_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval])) - sum(rate(cortex_ingester_tsdb_wal_truncations_failed_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval]))",
|
||||
"expr": "sum(rate(cortex_ingester_tsdb_wal_truncations_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval])) - sum(rate(cortex_ingester_tsdb_wal_truncations_failed_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval]))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "successful",
|
||||
"legendLink": null
|
||||
},
|
||||
{
|
||||
"expr": "sum(rate(cortex_ingester_tsdb_wal_truncations_failed_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval]))",
|
||||
"expr": "sum(rate(cortex_ingester_tsdb_wal_truncations_failed_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval]))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "failed",
|
||||
@@ -2314,14 +2314,14 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(rate(cortex_ingester_tsdb_checkpoint_creations_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval])) - sum(rate(cortex_ingester_tsdb_checkpoint_creations_failed_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval]))",
|
||||
"expr": "sum(rate(cortex_ingester_tsdb_checkpoint_creations_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval])) - sum(rate(cortex_ingester_tsdb_checkpoint_creations_failed_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval]))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "successful",
|
||||
"legendLink": null
|
||||
},
|
||||
{
|
||||
"expr": "sum(rate(cortex_ingester_tsdb_checkpoint_creations_failed_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval]))",
|
||||
"expr": "sum(rate(cortex_ingester_tsdb_checkpoint_creations_failed_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval]))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "failed",
|
||||
@@ -2387,7 +2387,7 @@
|
||||
"span": 3,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(rate(cortex_ingester_tsdb_wal_truncate_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval]))\n/\nsum(rate(cortex_ingester_tsdb_wal_truncate_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval])) >= 0\n",
|
||||
"expr": "sum(rate(cortex_ingester_tsdb_wal_truncate_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval]))\n/\nsum(rate(cortex_ingester_tsdb_wal_truncate_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval])) >= 0\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "avg",
|
||||
@@ -2432,14 +2432,14 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(rate(cortex_ingester_tsdb_wal_corruptions_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval]))",
|
||||
"expr": "sum(rate(cortex_ingester_tsdb_wal_corruptions_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval]))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "WAL",
|
||||
"legendLink": null
|
||||
},
|
||||
{
|
||||
"expr": "sum(rate(cortex_ingester_tsdb_mmap_chunk_corruptions_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval]))",
|
||||
"expr": "sum(rate(cortex_ingester_tsdb_mmap_chunk_corruptions_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval]))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "mmap-ed chunks",
|
||||
@@ -2527,7 +2527,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(cluster_namespace_job:cortex_distributor_exemplars_in:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\"})",
|
||||
"expr": "sum(cluster_namespace_job:cortex_distributor_exemplars_in:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\"})",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "incoming exemplars",
|
||||
@@ -2603,7 +2603,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(cluster_namespace_job:cortex_distributor_received_exemplars:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\"})",
|
||||
"expr": "sum(cluster_namespace_job:cortex_distributor_received_exemplars:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\"})",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "received exemplars",
|
||||
@@ -2679,7 +2679,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(\n cluster_namespace_job:cortex_ingester_ingested_exemplars:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}\n / on(cluster, namespace) group_left\n max by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\"})\n)\n",
|
||||
"expr": "sum(\n cluster_namespace_job:cortex_ingester_ingested_exemplars:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\"}\n / on(cluster, namespace) group_left\n max by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\"})\n)\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "ingested exemplars",
|
||||
@@ -2755,7 +2755,7 @@
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(\n cluster_namespace_job:cortex_ingester_tsdb_exemplar_exemplars_appended:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}\n / on(cluster, namespace) group_left\n max by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\"})\n)\n",
|
||||
"expr": "sum(\n cluster_namespace_job:cortex_ingester_tsdb_exemplar_exemplars_appended:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\"}\n / on(cluster, namespace) group_left\n max by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\"})\n)\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "appended exemplars",
|
||||
|
||||
7010
charts/meta-monitoring/src/dashboards/tempo-operational.json
Normal file
7010
charts/meta-monitoring/src/dashboards/tempo-operational.json
Normal file
File diff suppressed because it is too large
Load Diff
1612
charts/meta-monitoring/src/dashboards/tempo-reads.json
Normal file
1612
charts/meta-monitoring/src/dashboards/tempo-reads.json
Normal file
File diff suppressed because it is too large
Load Diff
2431
charts/meta-monitoring/src/dashboards/tempo-resources.json
Normal file
2431
charts/meta-monitoring/src/dashboards/tempo-resources.json
Normal file
File diff suppressed because it is too large
Load Diff
1559
charts/meta-monitoring/src/dashboards/tempo-rollout-progress.json
Normal file
1559
charts/meta-monitoring/src/dashboards/tempo-rollout-progress.json
Normal file
File diff suppressed because it is too large
Load Diff
1181
charts/meta-monitoring/src/dashboards/tempo-tenants.json
Normal file
1181
charts/meta-monitoring/src/dashboards/tempo-tenants.json
Normal file
File diff suppressed because it is too large
Load Diff
1738
charts/meta-monitoring/src/dashboards/tempo-writes.json
Normal file
1738
charts/meta-monitoring/src/dashboards/tempo-writes.json
Normal file
File diff suppressed because it is too large
Load Diff
53
charts/meta-monitoring/src/rules/loki-rules.yaml
Normal file
53
charts/meta-monitoring/src/rules/loki-rules.yaml
Normal file
@@ -0,0 +1,53 @@
|
||||
groups:
|
||||
- name: "loki_rules"
|
||||
rules:
|
||||
- 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[1m]))
|
||||
by (le, cluster, job))"
|
||||
record: "cluster_job:loki_request_duration_seconds:50quantile"
|
||||
- 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[1m])) by (le, cluster, job)"
|
||||
record: "cluster_job:loki_request_duration_seconds_bucket:sum_rate"
|
||||
- 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[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[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[1m]))
|
||||
by (le, cluster, job, route))"
|
||||
record: "cluster_job_route:loki_request_duration_seconds:50quantile"
|
||||
- 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[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[1m])) by (cluster, job, route)"
|
||||
record: "cluster_job_route:loki_request_duration_seconds_sum:sum_rate"
|
||||
- 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[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[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[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[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[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[1m])) by (cluster, namespace,
|
||||
job, route)"
|
||||
record: "cluster_namespace_job_route:loki_request_duration_seconds_count:sum_rate"
|
||||
571
charts/meta-monitoring/src/rules/mimir-rules.yaml
Normal file
571
charts/meta-monitoring/src/rules/mimir-rules.yaml
Normal file
@@ -0,0 +1,571 @@
|
||||
groups:
|
||||
- name: "mimir_api_1"
|
||||
rules:
|
||||
- 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[1m]))
|
||||
by (le, cluster, job))"
|
||||
record: "cluster_job:cortex_request_duration_seconds:50quantile"
|
||||
- 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[1m])) by (le, cluster, job)"
|
||||
record: "cluster_job:cortex_request_duration_seconds_bucket:sum_rate"
|
||||
- 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[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[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[1m]))
|
||||
by (le, cluster, job, route))"
|
||||
record: "cluster_job_route:cortex_request_duration_seconds:50quantile"
|
||||
- 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[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[1m])) by (cluster, job, route)"
|
||||
record: "cluster_job_route:cortex_request_duration_seconds_sum:sum_rate"
|
||||
- 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[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[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[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[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[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[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[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[1m]))
|
||||
by (le, cluster, job))"
|
||||
record: "cluster_job:cortex_querier_request_duration_seconds:50quantile"
|
||||
- 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[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[1m])) by (cluster,
|
||||
job)"
|
||||
record: "cluster_job:cortex_querier_request_duration_seconds_sum:sum_rate"
|
||||
- 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[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[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[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[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[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[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[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[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[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[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[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[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[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[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[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[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[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[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[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[1m]))
|
||||
by (le, cluster, job))"
|
||||
record: "cluster_job:cortex_cache_request_duration_seconds:50quantile"
|
||||
- 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[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[1m])) by (cluster, job)"
|
||||
record: "cluster_job:cortex_cache_request_duration_seconds_sum:sum_rate"
|
||||
- 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[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[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[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[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[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[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[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[1m]))
|
||||
by (le, cluster, job))"
|
||||
record: "cluster_job:cortex_kv_request_duration_seconds:50quantile"
|
||||
- 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[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[1m])) by (cluster, job)"
|
||||
record: "cluster_job:cortex_kv_request_duration_seconds_sum:sum_rate"
|
||||
- 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[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[1m]))
|
||||
by (le, cluster, job))"
|
||||
record: "cluster_job:cortex_query_frontend_retries:50quantile"
|
||||
- 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[1m])) by (le, cluster, job)"
|
||||
record: "cluster_job:cortex_query_frontend_retries_bucket:sum_rate"
|
||||
- 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[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[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[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[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[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[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[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[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[1m]))
|
||||
by (le, cluster, job))"
|
||||
record: "cluster_job:cortex_ingester_queried_series:50quantile"
|
||||
- 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[1m])) by (le, cluster, job)"
|
||||
record: "cluster_job:cortex_ingester_queried_series_bucket:sum_rate"
|
||||
- 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[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[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[1m]))
|
||||
by (le, cluster, job))"
|
||||
record: "cluster_job:cortex_ingester_queried_samples:50quantile"
|
||||
- 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[1m])) by (le, cluster, job)"
|
||||
record: "cluster_job:cortex_ingester_queried_samples_bucket:sum_rate"
|
||||
- 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[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[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[1m]))
|
||||
by (le, cluster, job))"
|
||||
record: "cluster_job:cortex_ingester_queried_exemplars:50quantile"
|
||||
- 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[1m])) by (le, cluster,
|
||||
job)"
|
||||
record: "cluster_job:cortex_ingester_queried_exemplars_bucket:sum_rate"
|
||||
- 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[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]))"
|
||||
record: "cluster_namespace_job:cortex_distributor_received_samples:rate5m"
|
||||
- name: "mimir_exemplars_in"
|
||||
rules:
|
||||
- expr: "|
|
||||
sum by (cluster, namespace, job) (rate(cortex_distributor_exemplars_in_total[5m]))"
|
||||
record: "cluster_namespace_job:cortex_distributor_exemplars_in:rate5m"
|
||||
- name: "mimir_received_exemplars"
|
||||
rules:
|
||||
- expr: "|
|
||||
sum by (cluster, namespace, job) (rate(cortex_distributor_received_exemplars_total[5m]))"
|
||||
record: "cluster_namespace_job:cortex_distributor_received_exemplars:rate5m"
|
||||
- name: "mimir_exemplars_ingested"
|
||||
rules:
|
||||
- expr: "|
|
||||
sum by (cluster, namespace, job) (rate(cortex_ingester_ingested_exemplars_total[5m]))"
|
||||
record: "cluster_namespace_job:cortex_ingester_ingested_exemplars:rate5m"
|
||||
- name: "mimir_exemplars_appended"
|
||||
rules:
|
||||
- expr: "|
|
||||
sum by (cluster, namespace, job) (rate(cortex_ingester_tsdb_exemplar_exemplars_appended_total[5m]))"
|
||||
record: "cluster_namespace_job:cortex_ingester_tsdb_exemplar_exemplars_appended:rate5m"
|
||||
- name: "mimir_scaling_rules"
|
||||
rules:
|
||||
- expr: "|
|
||||
# Convenience rule to get the number of replicas for both a deployment and a statefulset.
|
||||
# Multi-zone deployments are grouped together removing the \"zone-X\" suffix.
|
||||
sum by (cluster, namespace, deployment) (
|
||||
label_replace(
|
||||
kube_deployment_spec_replicas,
|
||||
# The question mark in \"(.*?)\" is used to make it non-greedy, otherwise it
|
||||
# always matches everything and the (optional) zone is not removed.
|
||||
\"deployment\", \"$1\", \"deployment\", \"(.*?)(?:-zone-[a-z])?\"
|
||||
)
|
||||
)
|
||||
or
|
||||
sum by (cluster, namespace, deployment) (
|
||||
label_replace(kube_statefulset_replicas, \"deployment\", \"$1\", \"statefulset\", \"(.*?)(?:-zone-[a-z])?\")
|
||||
)"
|
||||
record: "cluster_namespace_deployment:actual_replicas:count"
|
||||
- expr: "|
|
||||
ceil(
|
||||
quantile_over_time(0.99,
|
||||
sum by (cluster, namespace) (
|
||||
cluster_namespace_job:cortex_distributor_received_samples:rate5m
|
||||
)[24h:]
|
||||
)
|
||||
/ 240000
|
||||
)"
|
||||
labels:
|
||||
deployment: "distributor"
|
||||
reason: "sample_rate"
|
||||
record: "cluster_namespace_deployment_reason:required_replicas:count"
|
||||
- expr: "|
|
||||
ceil(
|
||||
sum by (cluster, namespace) (cortex_limits_overrides{limit_name=\"ingestion_rate\"})
|
||||
* 0.59999999999999998 / 240000
|
||||
)"
|
||||
labels:
|
||||
deployment: "distributor"
|
||||
reason: "sample_rate_limits"
|
||||
record: "cluster_namespace_deployment_reason:required_replicas:count"
|
||||
- expr: "|
|
||||
ceil(
|
||||
quantile_over_time(0.99,
|
||||
sum by (cluster, namespace) (
|
||||
cluster_namespace_job:cortex_distributor_received_samples:rate5m
|
||||
)[24h:]
|
||||
)
|
||||
* 3 / 80000
|
||||
)"
|
||||
labels:
|
||||
deployment: "ingester"
|
||||
reason: "sample_rate"
|
||||
record: "cluster_namespace_deployment_reason:required_replicas:count"
|
||||
- expr: "|
|
||||
ceil(
|
||||
quantile_over_time(0.99,
|
||||
sum by(cluster, namespace) (
|
||||
cortex_ingester_memory_series
|
||||
)[24h:]
|
||||
)
|
||||
/ 1500000
|
||||
)"
|
||||
labels:
|
||||
deployment: "ingester"
|
||||
reason: "active_series"
|
||||
record: "cluster_namespace_deployment_reason:required_replicas:count"
|
||||
- expr: "|
|
||||
ceil(
|
||||
sum by (cluster, namespace) (cortex_limits_overrides{limit_name=\"max_global_series_per_user\"})
|
||||
* 3 * 0.59999999999999998 / 1500000
|
||||
)"
|
||||
labels:
|
||||
deployment: "ingester"
|
||||
reason: "active_series_limits"
|
||||
record: "cluster_namespace_deployment_reason:required_replicas:count"
|
||||
- expr: "|
|
||||
ceil(
|
||||
sum by (cluster, namespace) (cortex_limits_overrides{limit_name=\"ingestion_rate\"})
|
||||
* 0.59999999999999998 / 80000
|
||||
)"
|
||||
labels:
|
||||
deployment: "ingester"
|
||||
reason: "sample_rate_limits"
|
||||
record: "cluster_namespace_deployment_reason:required_replicas:count"
|
||||
- expr: "|
|
||||
ceil(
|
||||
(sum by (cluster, namespace) (
|
||||
cortex_ingester_tsdb_storage_blocks_bytes{job=~\".+/ingester.*\"}
|
||||
) / 4)
|
||||
/
|
||||
avg by (cluster, namespace) (
|
||||
memcached_limit_bytes{job=~\".+/memcached\"}
|
||||
)
|
||||
)"
|
||||
labels:
|
||||
deployment: "memcached"
|
||||
reason: "active_series"
|
||||
record: "cluster_namespace_deployment_reason:required_replicas:count"
|
||||
- expr: "|
|
||||
sum by (cluster, namespace, deployment) (
|
||||
label_replace(
|
||||
label_replace(
|
||||
sum by (cluster, namespace, pod)(rate(container_cpu_usage_seconds_total[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
|
||||
# always matches everything and the (optional) zone is not removed.
|
||||
\"deployment\", \"$1\", \"deployment\", \"(.*?)(?:-zone-[a-z])?\"
|
||||
)
|
||||
)"
|
||||
record: "cluster_namespace_deployment:container_cpu_usage_seconds_total:sum_rate"
|
||||
- expr: "|
|
||||
# Convenience rule to get the CPU request for both a deployment and a statefulset.
|
||||
# Multi-zone deployments are grouped together removing the \"zone-X\" suffix.
|
||||
# This recording rule is made compatible with the breaking changes introduced in kube-state-metrics v2
|
||||
# that remove resource metrics, ref:
|
||||
# - https://github.com/kubernetes/kube-state-metrics/blob/master/CHANGELOG.md#v200-alpha--2020-09-16
|
||||
# - https://github.com/kubernetes/kube-state-metrics/pull/1004
|
||||
#
|
||||
# This is the old expression, compatible with kube-state-metrics < v2.0.0,
|
||||
# where kube_pod_container_resource_requests_cpu_cores was removed:
|
||||
(
|
||||
sum by (cluster, namespace, deployment) (
|
||||
label_replace(
|
||||
label_replace(
|
||||
kube_pod_container_resource_requests_cpu_cores,
|
||||
\"deployment\", \"$1\", \"pod\", \"(.*)-(?:([0-9]+)|([a-z0-9]+)-([a-z0-9]+))\"
|
||||
),
|
||||
# The question mark in \"(.*?)\" is used to make it non-greedy, otherwise it
|
||||
# always matches everything and the (optional) zone is not removed.
|
||||
\"deployment\", \"$1\", \"deployment\", \"(.*?)(?:-zone-[a-z])?\"
|
||||
)
|
||||
)
|
||||
)
|
||||
or
|
||||
# This expression is compatible with kube-state-metrics >= v1.4.0,
|
||||
# where kube_pod_container_resource_requests was introduced.
|
||||
(
|
||||
sum by (cluster, namespace, deployment) (
|
||||
label_replace(
|
||||
label_replace(
|
||||
kube_pod_container_resource_requests{resource=\"cpu\"},
|
||||
\"deployment\", \"$1\", \"pod\", \"(.*)-(?:([0-9]+)|([a-z0-9]+)-([a-z0-9]+))\"
|
||||
),
|
||||
# The question mark in \"(.*?)\" is used to make it non-greedy, otherwise it
|
||||
# always matches everything and the (optional) zone is not removed.
|
||||
\"deployment\", \"$1\", \"deployment\", \"(.*?)(?:-zone-[a-z])?\"
|
||||
)
|
||||
)
|
||||
)"
|
||||
record: "cluster_namespace_deployment:kube_pod_container_resource_requests_cpu_cores:sum"
|
||||
- expr: "|
|
||||
# Jobs should be sized to their CPU usage.
|
||||
# We do this by comparing 99th percentile usage over the last 24hrs to
|
||||
# their current provisioned #replicas and resource requests.
|
||||
ceil(
|
||||
cluster_namespace_deployment:actual_replicas:count
|
||||
*
|
||||
quantile_over_time(0.99, cluster_namespace_deployment:container_cpu_usage_seconds_total:sum_rate[24h])
|
||||
/
|
||||
cluster_namespace_deployment:kube_pod_container_resource_requests_cpu_cores:sum
|
||||
)"
|
||||
labels:
|
||||
reason: "cpu_usage"
|
||||
record: "cluster_namespace_deployment_reason:required_replicas:count"
|
||||
- expr: "|
|
||||
# Convenience rule to get the Memory utilization for both a deployment and a statefulset.
|
||||
# Multi-zone deployments are grouped together removing the \"zone-X\" suffix.
|
||||
sum by (cluster, namespace, deployment) (
|
||||
label_replace(
|
||||
label_replace(
|
||||
container_memory_usage_bytes{image!=\"\"},
|
||||
\"deployment\", \"$1\", \"pod\", \"(.*)-(?:([0-9]+)|([a-z0-9]+)-([a-z0-9]+))\"
|
||||
),
|
||||
# The question mark in \"(.*?)\" is used to make it non-greedy, otherwise it
|
||||
# always matches everything and the (optional) zone is not removed.
|
||||
\"deployment\", \"$1\", \"deployment\", \"(.*?)(?:-zone-[a-z])?\"
|
||||
)
|
||||
)"
|
||||
record: "cluster_namespace_deployment:container_memory_usage_bytes:sum"
|
||||
- expr: "|
|
||||
# Convenience rule to get the Memory request for both a deployment and a statefulset.
|
||||
# Multi-zone deployments are grouped together removing the \"zone-X\" suffix.
|
||||
# This recording rule is made compatible with the breaking changes introduced in kube-state-metrics v2
|
||||
# that remove resource metrics, ref:
|
||||
# - https://github.com/kubernetes/kube-state-metrics/blob/master/CHANGELOG.md#v200-alpha--2020-09-16
|
||||
# - https://github.com/kubernetes/kube-state-metrics/pull/1004
|
||||
#
|
||||
# This is the old expression, compatible with kube-state-metrics < v2.0.0,
|
||||
# where kube_pod_container_resource_requests_memory_bytes was removed:
|
||||
(
|
||||
sum by (cluster, namespace, deployment) (
|
||||
label_replace(
|
||||
label_replace(
|
||||
kube_pod_container_resource_requests_memory_bytes,
|
||||
\"deployment\", \"$1\", \"pod\", \"(.*)-(?:([0-9]+)|([a-z0-9]+)-([a-z0-9]+))\"
|
||||
),
|
||||
# The question mark in \"(.*?)\" is used to make it non-greedy, otherwise it
|
||||
# always matches everything and the (optional) zone is not removed.
|
||||
\"deployment\", \"$1\", \"deployment\", \"(.*?)(?:-zone-[a-z])?\"
|
||||
)
|
||||
)
|
||||
)
|
||||
or
|
||||
# This expression is compatible with kube-state-metrics >= v1.4.0,
|
||||
# where kube_pod_container_resource_requests was introduced.
|
||||
(
|
||||
sum by (cluster, namespace, deployment) (
|
||||
label_replace(
|
||||
label_replace(
|
||||
kube_pod_container_resource_requests{resource=\"memory\"},
|
||||
\"deployment\", \"$1\", \"pod\", \"(.*)-(?:([0-9]+)|([a-z0-9]+)-([a-z0-9]+))\"
|
||||
),
|
||||
# The question mark in \"(.*?)\" is used to make it non-greedy, otherwise it
|
||||
# always matches everything and the (optional) zone is not removed.
|
||||
\"deployment\", \"$1\", \"deployment\", \"(.*?)(?:-zone-[a-z])?\"
|
||||
)
|
||||
)
|
||||
)"
|
||||
record: "cluster_namespace_deployment:kube_pod_container_resource_requests_memory_bytes:sum"
|
||||
- expr: "|
|
||||
# Jobs should be sized to their Memory usage.
|
||||
# We do this by comparing 99th percentile usage over the last 24hrs to
|
||||
# their current provisioned #replicas and resource requests.
|
||||
ceil(
|
||||
cluster_namespace_deployment:actual_replicas:count
|
||||
*
|
||||
quantile_over_time(0.99, cluster_namespace_deployment:container_memory_usage_bytes:sum[24h])
|
||||
/
|
||||
cluster_namespace_deployment:kube_pod_container_resource_requests_memory_bytes:sum
|
||||
)"
|
||||
labels:
|
||||
reason: "memory_usage"
|
||||
record: "cluster_namespace_deployment_reason:required_replicas:count"
|
||||
- name: "mimir_alertmanager_rules"
|
||||
rules:
|
||||
- expr: "|
|
||||
sum by (cluster, job, pod) (cortex_alertmanager_alerts)"
|
||||
record: "cluster_job_pod:cortex_alertmanager_alerts:sum"
|
||||
- expr: "|
|
||||
sum by (cluster, job, pod) (cortex_alertmanager_silences)"
|
||||
record: "cluster_job_pod:cortex_alertmanager_silences:sum"
|
||||
- expr: "|
|
||||
sum by (cluster, job) (rate(cortex_alertmanager_alerts_received_total[5m]))"
|
||||
record: "cluster_job:cortex_alertmanager_alerts_received_total:rate5m"
|
||||
- expr: "|
|
||||
sum by (cluster, job) (rate(cortex_alertmanager_alerts_invalid_total[5m]))"
|
||||
record: "cluster_job:cortex_alertmanager_alerts_invalid_total:rate5m"
|
||||
- expr: "|
|
||||
sum by (cluster, job, integration) (rate(cortex_alertmanager_notifications_total[5m]))"
|
||||
record: "cluster_job_integration:cortex_alertmanager_notifications_total:rate5m"
|
||||
- expr: "|
|
||||
sum by (cluster, job, integration) (rate(cortex_alertmanager_notifications_failed_total[5m]))"
|
||||
record: "cluster_job_integration:cortex_alertmanager_notifications_failed_total:rate5m"
|
||||
- expr: "|
|
||||
sum by (cluster, job) (rate(cortex_alertmanager_state_replication_total[5m]))"
|
||||
record: "cluster_job:cortex_alertmanager_state_replication_total:rate5m"
|
||||
- expr: "|
|
||||
sum by (cluster, job) (rate(cortex_alertmanager_state_replication_failed_total[5m]))"
|
||||
record: "cluster_job:cortex_alertmanager_state_replication_failed_total:rate5m"
|
||||
- expr: "|
|
||||
sum by (cluster, job) (rate(cortex_alertmanager_partial_state_merges_total[5m]))"
|
||||
record: "cluster_job:cortex_alertmanager_partial_state_merges_total:rate5m"
|
||||
- expr: "|
|
||||
sum by (cluster, job) (rate(cortex_alertmanager_partial_state_merges_failed_total[5m]))"
|
||||
record: "cluster_job:cortex_alertmanager_partial_state_merges_failed_total:rate5m"
|
||||
- name: "mimir_ingester_rules"
|
||||
rules:
|
||||
- expr: "|
|
||||
sum by(cluster, namespace, pod) (rate(cortex_ingester_ingested_samples_total[1m]))"
|
||||
record: "cluster_namespace_pod:cortex_ingester_ingested_samples_total:rate1m"
|
||||
15
charts/meta-monitoring/src/rules/tempo-rules.yaml
Normal file
15
charts/meta-monitoring/src/rules/tempo-rules.yaml
Normal file
@@ -0,0 +1,15 @@
|
||||
groups:
|
||||
- name: "tempo_rules"
|
||||
rules:
|
||||
- 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[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[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[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[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[1m])) by (cluster, namespace, job, route)"
|
||||
record: "cluster_namespace_job_route:tempo_request_duration_seconds_count:sum_rate"
|
||||
@@ -37,6 +37,8 @@ data:
|
||||
}
|
||||
}
|
||||
|
||||
// Logs
|
||||
|
||||
{{- if or .Values.local.logs.enabled .Values.cloud.logs.enabled }}
|
||||
loki.source.kubernetes "pods" {
|
||||
targets = discovery.relabel.rename_meta_labels.output
|
||||
@@ -58,13 +60,131 @@ data:
|
||||
{{- end }}
|
||||
{{- end }}
|
||||
|
||||
// Metrics
|
||||
|
||||
{{- if or .Values.local.metrics.enabled .Values.cloud.metrics.enabled }}
|
||||
prometheus.scrape "pods" {
|
||||
targets = discovery.relabel.rename_meta_labels.output
|
||||
forward_to = [ {{ include "agent.prometheus_write_targets" . }} ]
|
||||
}
|
||||
{{- if .Values.kubeStateMetrics.enabled }}
|
||||
|
||||
prometheus.scrape "kubeStateMetrics" {
|
||||
targets = [ { "__address__" = "{{ .Values.kubeStateMetrics.endpoint }}" } ]
|
||||
forward_to = [ {{ include "agent.prometheus_write_targets" . }} ]
|
||||
}
|
||||
{{- end }}
|
||||
|
||||
// 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"
|
||||
}
|
||||
|
||||
discovery.relabel "all_nodes" {
|
||||
targets = discovery.kubernetes.all_nodes.targets
|
||||
rule {
|
||||
source_labels = ["__meta_kubernetes_node_name"]
|
||||
target_label = "node"
|
||||
}
|
||||
rule {
|
||||
source_labels = ["__meta_kubernetes_namespace"]
|
||||
target_label = "namespace"
|
||||
}
|
||||
rule {
|
||||
source_labels = ["__meta_kubernetes_pod_name"]
|
||||
target_label = "pod"
|
||||
}
|
||||
rule {
|
||||
source_labels = ["__meta_kubernetes_namespace", "__meta_kubernetes_pod_label_app_kubernetes_io_name", "__meta_kubernetes_pod_label_app_kubernetes_io_component"]
|
||||
separator = "/"
|
||||
regex = "(.*)/(.*)/(.*)"
|
||||
replacement = "${1}/${2}-${3}"
|
||||
target_label = "job"
|
||||
}
|
||||
rule {
|
||||
target_label = "cluster"
|
||||
replacement = "{{- .Values.clusterName -}}"
|
||||
}
|
||||
}
|
||||
|
||||
prometheus.scrape "cadvisor" {
|
||||
targets = discovery.relabel.all_nodes.output
|
||||
forward_to = [ {{ include "agent.prometheus_write_targets" . }} ]
|
||||
|
||||
scrape_interval = "15s"
|
||||
metrics_path = "/metrics/cadvisor"
|
||||
scheme = "https"
|
||||
|
||||
bearer_token_file = "/var/run/secrets/kubernetes.io/serviceaccount/token"
|
||||
tls_config {
|
||||
ca_file = "/var/run/secrets/kubernetes.io/serviceaccount/ca.crt"
|
||||
}
|
||||
}
|
||||
|
||||
prometheus.scrape "kubelet" {
|
||||
targets = discovery.relabel.all_nodes.output
|
||||
forward_to = [ {{ include "agent.prometheus_write_targets" . }} ]
|
||||
|
||||
scrape_interval = "15s"
|
||||
metrics_path = "/metrics"
|
||||
scheme = "https"
|
||||
|
||||
bearer_token_file = "/var/run/secrets/kubernetes.io/serviceaccount/token"
|
||||
tls_config {
|
||||
ca_file = "/var/run/secrets/kubernetes.io/serviceaccount/ca.crt"
|
||||
}
|
||||
}
|
||||
|
||||
prometheus.exporter.unix {}
|
||||
|
||||
prometheus.scrape "node_exporter" {
|
||||
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 = [ {{ include "agent.prometheus_write_targets" . }} ]
|
||||
|
||||
rule {
|
||||
replacement = env("HOSTNAME")
|
||||
target_label = "nodename"
|
||||
}
|
||||
rule {
|
||||
replacement = "node-exporter"
|
||||
target_label = "job"
|
||||
}
|
||||
rule {
|
||||
source_labels = ["__meta_kubernetes_node_name"]
|
||||
target_label = "node"
|
||||
}
|
||||
rule {
|
||||
source_labels = ["__meta_kubernetes_namespace"]
|
||||
target_label = "namespace"
|
||||
}
|
||||
rule {
|
||||
source_labels = ["__meta_kubernetes_pod_name"]
|
||||
target_label = "pod"
|
||||
}
|
||||
rule {
|
||||
source_labels = ["__meta_kubernetes_namespace", "__meta_kubernetes_pod_label_app_kubernetes_io_name", "__meta_kubernetes_pod_label_app_kubernetes_io_component"]
|
||||
separator = "/"
|
||||
regex = "(.*)/(.*)/(.*)"
|
||||
replacement = "${1}/${2}-${3}"
|
||||
target_label = "job"
|
||||
}
|
||||
rule {
|
||||
target_label = "cluster"
|
||||
replacement = "{{- .Values.clusterName -}}"
|
||||
}
|
||||
}
|
||||
{{- end }}
|
||||
|
||||
// Traces
|
||||
|
||||
{{- 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" {
|
||||
|
||||
@@ -0,0 +1,19 @@
|
||||
{{- if .Values.dashboards.traces.enabled }}
|
||||
---
|
||||
apiVersion: v1
|
||||
kind: ConfigMap
|
||||
metadata:
|
||||
name: agent-dashboards-1
|
||||
namespace: {{ $.Release.Namespace }}
|
||||
data:
|
||||
"agent-logs-pipeline.json": |
|
||||
{{ $.Files.Get "src/dashboards/agent-logs-pipeline.json" | fromJson | toJson }}
|
||||
"agent-operational.json": |
|
||||
{{ $.Files.Get "src/dashboards/agent-operational.json" | fromJson | toJson }}
|
||||
"agent-remote-write.json": |
|
||||
{{ $.Files.Get "src/dashboards/agent-remote-write.json" | fromJson | toJson }}
|
||||
"agent-tracing-pipeline.json": |
|
||||
{{ $.Files.Get "src/dashboards/agent-tracing-pipeline.json" | fromJson | toJson }}
|
||||
"agent.json": |
|
||||
{{ $.Files.Get "src/dashboards/agent.json" | fromJson | toJson }}
|
||||
{{- end }}
|
||||
@@ -1,16 +1,16 @@
|
||||
{{- if or (or .Values.local.logs.enabled .Values.local.metrics.enabled) .Values.local.traces.enabled }}
|
||||
{{- if or (or .Values.dashboards.logs.enabled .Values.dashboards.metrics.enabled) .Values.dashboards.traces.enabled }}
|
||||
---
|
||||
apiVersion: v1
|
||||
kind: ConfigMap
|
||||
metadata:
|
||||
name: loki-dashboards-provisioning
|
||||
name: dashboards-provisioning
|
||||
namespace: {{ $.Release.Namespace }}
|
||||
data:
|
||||
dashboards.yaml: |
|
||||
---
|
||||
apiVersion: 1
|
||||
providers:
|
||||
{{- if .Values.local.logs.enabled }}
|
||||
{{- if .Values.dashboards.logs.enabled }}
|
||||
- disableDeletion: true
|
||||
editable: false
|
||||
folder: Loki
|
||||
@@ -28,7 +28,7 @@ data:
|
||||
orgId: 1
|
||||
type: file
|
||||
{{- end }}
|
||||
{{- if .Values.local.metrics.enabled }}
|
||||
{{- if .Values.dashboards.metrics.enabled }}
|
||||
- disableDeletion: true
|
||||
editable: false
|
||||
folder: Mimir
|
||||
@@ -70,4 +70,22 @@ data:
|
||||
orgId: 1
|
||||
type: file
|
||||
{{- end }}
|
||||
{{- if .Values.dashboards.traces.enabled }}
|
||||
- disableDeletion: true
|
||||
editable: false
|
||||
folder: Tempo
|
||||
name: tempo-1
|
||||
options:
|
||||
path: /var/lib/grafana/dashboards/tempo-1
|
||||
orgId: 1
|
||||
type: file
|
||||
{{- end }}
|
||||
- disableDeletion: true
|
||||
editable: false
|
||||
folder: Agent
|
||||
name: agent-1
|
||||
options:
|
||||
path: /var/lib/grafana/dashboards/agent-1
|
||||
orgId: 1
|
||||
type: file
|
||||
{{- end }}
|
||||
@@ -65,15 +65,17 @@ spec:
|
||||
name: grafana-pv
|
||||
- mountPath: /etc/grafana/provisioning/datasources
|
||||
name: datasources-provisioning
|
||||
{{- if or (or .Values.dashboards.logs.enabled .Values.dashboards.metrics.enabled) .Values.dashboards.traces.enabled }}
|
||||
- mountPath: /etc/grafana/provisioning/dashboards
|
||||
name: loki-dashboards-provisioning
|
||||
{{- if .Values.local.logs.enabled }}
|
||||
name: dashboards-provisioning
|
||||
{{- end }}
|
||||
{{- if .Values.dashboards.logs.enabled }}
|
||||
- mountPath: /var/lib/grafana/dashboards/loki-1
|
||||
name: loki-dashboards-1
|
||||
- mountPath: /var/lib/grafana/dashboards/loki-2
|
||||
name: loki-dashboards-2
|
||||
{{- end }}
|
||||
{{- if .Values.local.metrics.enabled }}
|
||||
{{- if .Values.dashboards.metrics.enabled }}
|
||||
- mountPath: /var/lib/grafana/dashboards/mimir-1
|
||||
name: mimir-dashboards-1
|
||||
- mountPath: /var/lib/grafana/dashboards/mimir-2
|
||||
@@ -85,6 +87,12 @@ spec:
|
||||
- mountPath: /var/lib/grafana/dashboards/mimir-5
|
||||
name: mimir-dashboards-5
|
||||
{{- end }}
|
||||
{{- if .Values.dashboards.traces.enabled }}
|
||||
- mountPath: /var/lib/grafana/dashboards/tempo-1
|
||||
name: tempo-dashboards-1
|
||||
{{- end }}
|
||||
- mountPath: /var/lib/grafana/dashboards/agent-1
|
||||
name: agent-dashboards-1
|
||||
volumes:
|
||||
- name: grafana-pv
|
||||
persistentVolumeClaim:
|
||||
@@ -92,10 +100,10 @@ spec:
|
||||
- name: datasources-provisioning
|
||||
configMap:
|
||||
name: datasources-provisioning
|
||||
{{- if .Values.local.logs.enabled }}
|
||||
- name: loki-dashboards-provisioning
|
||||
- name: dashboards-provisioning
|
||||
configMap:
|
||||
name: loki-dashboards-provisioning
|
||||
name: dashboards-provisioning
|
||||
{{- if .Values.dashboards.logs.enabled }}
|
||||
- name: loki-dashboards-1
|
||||
configMap:
|
||||
name: loki-dashboards-1
|
||||
@@ -103,10 +111,7 @@ spec:
|
||||
configMap:
|
||||
name: loki-dashboards-2
|
||||
{{- end }}
|
||||
{{- if .Values.local.metrics.enabled }}
|
||||
- name: mimir-dashboards-provisioning
|
||||
configMap:
|
||||
name: mimir-dashboards-provisioning
|
||||
{{- if .Values.dashboards.metrics.enabled }}
|
||||
- name: mimir-dashboards-1
|
||||
configMap:
|
||||
name: mimir-dashboards-1
|
||||
@@ -123,6 +128,14 @@ spec:
|
||||
configMap:
|
||||
name: mimir-dashboards-5
|
||||
{{- end }}
|
||||
{{- if .Values.dashboards.traces.enabled }}
|
||||
- name: tempo-dashboards-1
|
||||
configMap:
|
||||
name: tempo-dashboards-1
|
||||
{{- end }}
|
||||
- name: agent-dashboards-1
|
||||
configMap:
|
||||
name: agent-dashboards-1
|
||||
|
||||
---
|
||||
apiVersion: v1
|
||||
@@ -138,4 +151,4 @@ spec:
|
||||
app: grafana
|
||||
sessionAffinity: None
|
||||
type: ClusterIP # Make this configurable
|
||||
{{- end }}
|
||||
{{- end }}
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
{{- if .Values.local.logs.enabled }}
|
||||
{{- if .Values.dashboards.logs.enabled }}
|
||||
---
|
||||
apiVersion: v1
|
||||
kind: ConfigMap
|
||||
@@ -1,4 +1,4 @@
|
||||
{{- if .Values.local.logs.enabled }}
|
||||
{{- if .Values.dashboards.logs.enabled }}
|
||||
---
|
||||
apiVersion: v1
|
||||
kind: ConfigMap
|
||||
@@ -1,4 +1,4 @@
|
||||
{{- if .Values.local.metrics.enabled }}
|
||||
{{- if .Values.dashboards.metrics.enabled }}
|
||||
---
|
||||
apiVersion: v1
|
||||
kind: ConfigMap
|
||||
@@ -1,4 +1,4 @@
|
||||
{{- if .Values.local.metrics.enabled }}
|
||||
{{- if .Values.dashboards.metrics.enabled }}
|
||||
---
|
||||
apiVersion: v1
|
||||
kind: ConfigMap
|
||||
@@ -1,4 +1,4 @@
|
||||
{{- if .Values.local.metrics.enabled }}
|
||||
{{- if .Values.dashboards.metrics.enabled }}
|
||||
---
|
||||
apiVersion: v1
|
||||
kind: ConfigMap
|
||||
@@ -1,4 +1,4 @@
|
||||
{{- if .Values.local.metrics.enabled }}
|
||||
{{- if .Values.dashboards.metrics.enabled }}
|
||||
---
|
||||
apiVersion: v1
|
||||
kind: ConfigMap
|
||||
@@ -1,4 +1,4 @@
|
||||
{{- if .Values.local.metrics.enabled }}
|
||||
{{- if .Values.dashboards.metrics.enabled }}
|
||||
---
|
||||
apiVersion: v1
|
||||
kind: ConfigMap
|
||||
@@ -0,0 +1,21 @@
|
||||
{{- if .Values.dashboards.traces.enabled }}
|
||||
---
|
||||
apiVersion: v1
|
||||
kind: ConfigMap
|
||||
metadata:
|
||||
name: tempo-dashboards-1
|
||||
namespace: {{ $.Release.Namespace }}
|
||||
data:
|
||||
"tempo-operational.json": |
|
||||
{{ $.Files.Get "src/dashboards/tempo-operational.json" | fromJson | toJson }}
|
||||
"tempo-reads.json": |
|
||||
{{ $.Files.Get "src/dashboards/tempo-reads.json" | fromJson | toJson }}
|
||||
"tempo-resources.json": |
|
||||
{{ $.Files.Get "src/dashboards/tempo-resources.json" | fromJson | toJson }}
|
||||
"tempo-rollout-progress.json": |
|
||||
{{ $.Files.Get "src/dashboards/tempo-rollout-progress.json" | fromJson | toJson }}
|
||||
"tempo-tenants.json": |
|
||||
{{ $.Files.Get "src/dashboards/tempo-tenants.json" | fromJson | toJson }}
|
||||
"tempo-writes.json": |
|
||||
{{ $.Files.Get "src/dashboards/tempo-writes.json" | fromJson | toJson }}
|
||||
{{- end }}
|
||||
126
charts/meta-monitoring/templates/ruler/ruler.yaml
Normal file
126
charts/meta-monitoring/templates/ruler/ruler.yaml
Normal file
@@ -0,0 +1,126 @@
|
||||
{{- if .Values.local.metrics.enabled }}
|
||||
{{- if or (or .Values.dashboards.logs.enabled .Values.dashboards.metrics.enabled) .Values.dashboards.traces.enabled }}
|
||||
apiVersion: apps/v1
|
||||
kind: Deployment
|
||||
metadata:
|
||||
name: meta-mimir-ruler-for-dashboards
|
||||
namespace: {{ $.Release.Namespace }}
|
||||
spec:
|
||||
progressDeadlineSeconds: 600
|
||||
replicas: 1
|
||||
revisionHistoryLimit: 10
|
||||
selector:
|
||||
matchLabels:
|
||||
app.kubernetes.io/component: ruler-for-dashboards
|
||||
app.kubernetes.io/instance: meta
|
||||
app.kubernetes.io/name: mimir
|
||||
strategy:
|
||||
rollingUpdate:
|
||||
maxSurge: 50%
|
||||
maxUnavailable: 0
|
||||
type: RollingUpdate
|
||||
template:
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/component: ruler-for-dashboards
|
||||
app.kubernetes.io/instance: meta
|
||||
app.kubernetes.io/name: mimir
|
||||
namespace: {{ $.Release.Namespace }}
|
||||
spec:
|
||||
containers:
|
||||
- args:
|
||||
- -target=ruler
|
||||
- -log.level=debug
|
||||
- -ruler-storage.backend=local
|
||||
- -ruler-storage.local.directory=/etc/rules
|
||||
- -ruler.ring.prefix=dashboards/
|
||||
- -config.expand-env=true
|
||||
- -config.file=/etc/mimir/mimir.yaml
|
||||
image: grafana/mimir:2.8.0
|
||||
imagePullPolicy: IfNotPresent
|
||||
name: ruler
|
||||
ports:
|
||||
- containerPort: 8080
|
||||
name: http-metrics
|
||||
protocol: TCP
|
||||
- containerPort: 9095
|
||||
name: grpc
|
||||
protocol: TCP
|
||||
- containerPort: 7946
|
||||
name: memberlist
|
||||
protocol: TCP
|
||||
readinessProbe:
|
||||
failureThreshold: 3
|
||||
httpGet:
|
||||
path: /ready
|
||||
port: http-metrics
|
||||
scheme: HTTP
|
||||
initialDelaySeconds: 45
|
||||
periodSeconds: 10
|
||||
successThreshold: 1
|
||||
timeoutSeconds: 1
|
||||
resources:
|
||||
requests:
|
||||
cpu: 100m
|
||||
memory: 128Mi
|
||||
securityContext:
|
||||
allowPrivilegeEscalation: false
|
||||
capabilities:
|
||||
drop:
|
||||
- ALL
|
||||
readOnlyRootFilesystem: true
|
||||
terminationMessagePath: /dev/termination-log
|
||||
terminationMessagePolicy: File
|
||||
volumeMounts:
|
||||
- mountPath: /etc/mimir
|
||||
name: config
|
||||
- mountPath: /var/mimir
|
||||
name: runtime-config
|
||||
- mountPath: /data
|
||||
name: storage
|
||||
- mountPath: /active-query-tracker
|
||||
name: active-queries
|
||||
- mountPath: /etc/rules/anonymous
|
||||
name: rules
|
||||
dnsPolicy: ClusterFirst
|
||||
restartPolicy: Always
|
||||
schedulerName: default-scheduler
|
||||
securityContext:
|
||||
fsGroup: 10001
|
||||
runAsGroup: 10001
|
||||
runAsNonRoot: true
|
||||
runAsUser: 10001
|
||||
seccompProfile:
|
||||
type: RuntimeDefault
|
||||
terminationGracePeriodSeconds: 180
|
||||
topologySpreadConstraints:
|
||||
- labelSelector:
|
||||
matchLabels:
|
||||
app.kubernetes.io/component: ruler
|
||||
app.kubernetes.io/instance: meta
|
||||
app.kubernetes.io/name: mimir
|
||||
maxSkew: 1
|
||||
topologyKey: kubernetes.io/hostname
|
||||
whenUnsatisfiable: ScheduleAnyway
|
||||
volumes:
|
||||
- configMap:
|
||||
defaultMode: 420
|
||||
items:
|
||||
- key: mimir.yaml
|
||||
path: mimir.yaml
|
||||
name: meta-mimir-config
|
||||
name: config
|
||||
- configMap:
|
||||
defaultMode: 420
|
||||
name: meta-mimir-runtime
|
||||
name: runtime-config
|
||||
- emptyDir: {}
|
||||
name: storage
|
||||
- emptyDir: {}
|
||||
name: active-queries
|
||||
- configMap:
|
||||
defaultMode: 420
|
||||
name: rules
|
||||
name: rules
|
||||
{{- end }}
|
||||
{{- end }}
|
||||
20
charts/meta-monitoring/templates/ruler/rules-configmap.yaml
Normal file
20
charts/meta-monitoring/templates/ruler/rules-configmap.yaml
Normal file
@@ -0,0 +1,20 @@
|
||||
{{- if .Values.local.metrics.enabled }}
|
||||
{{- if or (or .Values.dashboards.logs.enabled .Values.dashboards.metrics.enabled) .Values.dashboards.traces.enabled }}
|
||||
---
|
||||
apiVersion: v1
|
||||
kind: ConfigMap
|
||||
metadata:
|
||||
name: rules
|
||||
namespace: {{ $.Release.Namespace }}
|
||||
data:
|
||||
{{- if .Values.dashboards.logs.enabled }}
|
||||
{{ ($.Files.Glob "src/rules/loki-rules.yaml").AsConfig | indent 2 }}
|
||||
{{- end }}
|
||||
{{- if .Values.dashboards.metrics.enabled }}
|
||||
{{ ($.Files.Glob "src/rules/mimir-rules.yaml").AsConfig | indent 2 }}
|
||||
{{- end }}
|
||||
{{- if .Values.dashboards.traces.enabled }}
|
||||
{{ ($.Files.Glob "src/rules/tempo-rules.yaml").AsConfig | indent 2 }}
|
||||
{{- end }}
|
||||
{{- end }}
|
||||
{{- end }}
|
||||
@@ -1,9 +1,30 @@
|
||||
# Specify the namespaces to monitor here
|
||||
namespacesToMonitor:
|
||||
- loki
|
||||
- mimir
|
||||
- tempo
|
||||
clusterName: "meta-monitoring" # TODO check if this can be derived
|
||||
# The name of the cluster where this will be installed
|
||||
clusterName: "meta-monitoring"
|
||||
|
||||
# Set to true to write logs, metrics or traces to Grafana Cloud
|
||||
cloud:
|
||||
logs:
|
||||
enabled: true
|
||||
endpoint: to_be_changed
|
||||
username: to_be_changed
|
||||
password: to_be_changed
|
||||
metrics:
|
||||
enabled: true
|
||||
endpoint: to_be_changed
|
||||
username: to_be_changed
|
||||
password: to_be_changed
|
||||
traces:
|
||||
enabled: true
|
||||
endpoint: to_be_changed
|
||||
username: to_be_changed
|
||||
password: to_be_changed
|
||||
|
||||
# Set to true for a local version of logs, metrics or traces
|
||||
local:
|
||||
logs:
|
||||
enabled: false
|
||||
@@ -14,25 +35,7 @@ local:
|
||||
minio:
|
||||
enabled: false # This should be set to true if any of the previous is enabled
|
||||
|
||||
|
||||
cloud:
|
||||
logs:
|
||||
enabled: true
|
||||
endpoint:
|
||||
username:
|
||||
password:
|
||||
metrics:
|
||||
enabled: true
|
||||
endpoint:
|
||||
username:
|
||||
password:
|
||||
traces:
|
||||
enabled: true
|
||||
endpoint:
|
||||
username:
|
||||
password:
|
||||
|
||||
# Adding regexes here will add a stage.replace block. For more information see
|
||||
# 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:
|
||||
piiRegexes:
|
||||
@@ -41,13 +44,30 @@ logs:
|
||||
# source: "" # Empty uses the log message
|
||||
# replace: "*****""
|
||||
|
||||
# Set enabled = true to add the default logs/metrics/traces dashboards to the local Grafana
|
||||
dashboards:
|
||||
logs:
|
||||
enabled: true
|
||||
metrics:
|
||||
enabled: true
|
||||
traces:
|
||||
enabled: true
|
||||
|
||||
global:
|
||||
minio:
|
||||
rootUser: "rootuser"
|
||||
rootPassword: "rootpassword"
|
||||
|
||||
kubeStateMetrics:
|
||||
# Scrape https://github.com/kubernetes/kube-state-metrics by default
|
||||
enabled: true
|
||||
# This endpoint is created when the helm chart from
|
||||
# https://artifacthub.io/packages/helm/prometheus-community/kube-state-metrics/
|
||||
# is used. Change this if kube-state-metrics is installed somewhere else.
|
||||
endpoint: kube-state-metrics.kube-state-metrics.svc.cluster.local:8080
|
||||
|
||||
# The following are configuration for the dependencies.
|
||||
# These should not be changed.
|
||||
# These should usually not be changed.
|
||||
|
||||
loki:
|
||||
loki:
|
||||
@@ -55,13 +75,22 @@ loki:
|
||||
storage:
|
||||
type: "s3"
|
||||
s3:
|
||||
endpoint: "meta-minio.meta.svc:9000"
|
||||
access_key_id: rootuser
|
||||
secret_access_key: rootpassword
|
||||
insecure: true
|
||||
s3ForcePathStyle: true
|
||||
bucketNames:
|
||||
chunks: loki-chunks
|
||||
ruler: loki-ruler
|
||||
structuredConfig:
|
||||
common:
|
||||
storage:
|
||||
s3:
|
||||
access_key_id: "{{ .Values.global.minio.rootUser }}"
|
||||
endpoint: "{{ .Release.Name }}-minio.{{ .Release.Namespace }}.svc:9000"
|
||||
secret_access_key: "{{ .Values.global.minio.rootPassword }}"
|
||||
compactor:
|
||||
retention_enabled: true
|
||||
limits_config:
|
||||
retention_period: 30d
|
||||
monitoring:
|
||||
dashboards:
|
||||
enabled: false
|
||||
@@ -112,6 +141,8 @@ mimir-distributed:
|
||||
endpoint: "{{ .Release.Name }}-minio.{{ .Release.Namespace }}.svc:9000"
|
||||
secret_access_key: "{{ .Values.global.minio.rootPassword }}"
|
||||
insecure: true
|
||||
limits:
|
||||
compactor_blocks_retention_period: 30d
|
||||
|
||||
tempo-distributed:
|
||||
tempo:
|
||||
@@ -125,6 +156,9 @@ tempo-distributed:
|
||||
access_key: "{{ .Values.global.minio.rootUser }}"
|
||||
secret_key: "{{ .Values.global.minio.rootPassword }}"
|
||||
insecure: true
|
||||
compactor:
|
||||
compaction:
|
||||
block_retention: 30d
|
||||
traces:
|
||||
otlp:
|
||||
http:
|
||||
@@ -159,4 +193,4 @@ minio:
|
||||
cpu: 100m
|
||||
memory: 128Mi
|
||||
# Changed the mc config path to '/tmp' from '/etc' as '/etc' is only writable by root and OpenShift will not permit this.
|
||||
configPathmc: "/tmp/minio/mc/"
|
||||
configPathmc: "/tmp/minio/mc/"
|
||||
|
||||
9
tools/kind.config
Normal file
9
tools/kind.config
Normal file
@@ -0,0 +1,9 @@
|
||||
kind: Cluster
|
||||
apiVersion: kind.x-k8s.io/v1alpha4
|
||||
name: meta
|
||||
nodes:
|
||||
- role: control-plane
|
||||
- role: worker
|
||||
- role: worker
|
||||
- role: worker
|
||||
|
||||
Reference in New Issue
Block a user