Compare commits

..

63 Commits

Author SHA1 Message Date
Michel Hollands
76908c1e9e Turn on cloud metrics and traces by default
Signed-off-by: Michel Hollands <michel.hollands@gmail.com>
2023-10-19 10:47:12 +01:00
Michel Hollands
bc5cdadb9f Rename file and do not run ruler when no mimir
Signed-off-by: Michel Hollands <michel.hollands@gmail.com>
2023-10-19 10:28:59 +01:00
Michel Hollands
687c77c0f6 Use cloud
Signed-off-by: Michel Hollands <michel.hollands@gmail.com>
2023-10-19 09:31:59 +01:00
Michel Hollands
f4934d6007 Remove space
Signed-off-by: Michel Hollands <michel.hollands@gmail.com>
2023-10-18 11:35:54 +01:00
Michel Hollands
1093e91741 Change namespace name
Signed-off-by: Michel Hollands <michel.hollands@gmail.com>
2023-08-18 11:45:57 +01:00
Michel Hollands
1ed196299b Increase timeout
Signed-off-by: Michel Hollands <michel.hollands@gmail.com>
2023-08-18 11:44:31 +01:00
Michel Hollands
faa0015c11 Install locally by default
Signed-off-by: Michel Hollands <michel.hollands@gmail.com>
2023-08-18 11:28:47 +01:00
Michel Hollands
53416e042c Use correct namespace
Signed-off-by: Michel Hollands <michel.hollands@gmail.com>
2023-08-18 11:26:35 +01:00
Michel Hollands
d804da13f1 Add test install
Signed-off-by: Michel Hollands <michel.hollands@gmail.com>
2023-08-18 11:20:20 +01:00
Michel Hollands
8c0b68fe02 Fix kind.config
Signed-off-by: Michel Hollands <michel.hollands@gmail.com>
2023-08-18 11:13:16 +01:00
Michel Hollands
99bb8f13c2 Apply linting 5
Signed-off-by: Michel Hollands <michel.hollands@gmail.com>
2023-08-18 11:10:36 +01:00
Michel Hollands
26ff679cbb Apply linting 4
Signed-off-by: Michel Hollands <michel.hollands@gmail.com>
2023-08-18 11:06:52 +01:00
Michel Hollands
fb3e3ece1b Apply linting 3
Signed-off-by: Michel Hollands <michel.hollands@gmail.com>
2023-08-18 11:05:21 +01:00
Michel Hollands
7a5358b322 Apply linting 2
Signed-off-by: Michel Hollands <michel.hollands@gmail.com>
2023-08-18 11:03:29 +01:00
Michel Hollands
9c92e18efe Apply linting
Signed-off-by: Michel Hollands <michel.hollands@gmail.com>
2023-08-18 11:02:07 +01:00
Michel Hollands
ffe220590d Update dependencies
Signed-off-by: Michel Hollands <michel.hollands@gmail.com>
2023-08-18 10:58:54 +01:00
Michel Hollands
e3708ce3fe Add ct.yaml
Signed-off-by: Michel Hollands <michel.hollands@gmail.com>
2023-08-18 10:44:43 +01:00
Michel Hollands
3149f4df9b Add install step
Signed-off-by: Michel Hollands <michel.hollands@gmail.com>
2023-08-18 10:22:14 +01:00
Michel Hollands
86ec586917 Fix typo
Signed-off-by: Michel Hollands <michel.hollands@gmail.com>
2023-08-17 10:31:56 +01:00
Michel Hollands
6cd12bee01 Add linted rule files
Signed-off-by: Michel Hollands <michel.hollands@gmail.com>
2023-08-17 10:29:24 +01:00
Michel Hollands
b042b396a2 Temp checkin
Signed-off-by: Michel Hollands <michel.hollands@gmail.com>
2023-08-17 10:27:42 +01:00
Michel Hollands
bcacb70e2d Merge pull request #5 from grafana/add_skip_cdrs_to_installation_step
Update readme
2023-08-16 11:07:05 +01:00
Michel Hollands
d9c3b60659 Update documentation
Signed-off-by: Michel Hollands <michel.hollands@gmail.com>
2023-08-16 11:02:16 +01:00
Michel Hollands
6d091d564e Add note about CRDs
Signed-off-by: Michel Hollands <michel.hollands@gmail.com>
2023-08-16 09:47:54 +01:00
Michel Hollands
8671993962 Update readme
Signed-off-by: Michel Hollands <michel.hollands@grafana.com>
2023-08-16 09:44:36 +01:00
Michel Hollands
f80c9d7c43 Merge pull request #15 from grafana/add_retention
Add retention for Loki, Mimir and Tempo
2023-08-15 16:54:41 +01:00
Michel Hollands
60853bc8b0 Merge pull request #12 from grafana/add_agent_dashboards
Add agent dashboards
2023-08-15 16:53:39 +01:00
Michel Hollands
debdd67283 Merge pull request #13 from grafana/fix_mimir_dashboards
Fix mimir dashboards
2023-08-15 16:53:15 +01:00
Michel Hollands
8bc465b2e6 Merge pull request #14 from grafana/fix_tempo_dashboards
Fix Tempo dashboards
2023-08-15 16:53:06 +01:00
Michel Hollands
18d24c39f7 Add Loki retention
Signed-off-by: Michel Hollands <michel.hollands@gmail.com>
2023-08-15 15:21:24 +01:00
Michel Hollands
23d14110a0 Add 1 day retention to Tempo and Mimir
Signed-off-by: Michel Hollands <michel.hollands@gmail.com>
2023-08-15 10:47:33 +01:00
Michel Hollands
092423c2b3 Fix
Signed-off-by: Michel Hollands <michel.hollands@gmail.com>
2023-08-14 15:22:40 +01:00
Michel Hollands
dcbe85a37a Fix
Signed-off-by: Michel Hollands <michel.hollands@gmail.com>
2023-08-14 15:18:42 +01:00
Michel Hollands
db8558982c Also for
Signed-off-by: Michel Hollands <michel.hollands@gmail.com>
2023-08-14 15:16:38 +01:00
Michel Hollands
49034b9f6b Fix dashboards
Signed-off-by: Michel Hollands <michel.hollands@gmail.com>
2023-08-14 15:05:29 +01:00
Michel Hollands
15f96d9cc6 Make work with mimir-distributed
Signed-off-by: Michel Hollands <michel.hollands@gmail.com>
2023-08-14 11:32:24 +01:00
Michel Hollands
b9f22ba27e Add further job possibilities for reads
Signed-off-by: Michel Hollands <michel.hollands@gmail.com>
2023-08-14 10:58:21 +01:00
Michel Hollands
2f79e7ef14 Add further job possibilities
Signed-off-by: Michel Hollands <michel.hollands@gmail.com>
2023-08-14 10:54:04 +01:00
Michel Hollands
aa988adb47 Add agent dashboards
Signed-off-by: Michel Hollands <michel.hollands@gmail.com>
2023-08-03 15:28:47 +01:00
Michel Hollands
6fb22ae671 Merge pull request #11 from grafana/add_scraping_of_cadvisor
Add metrics scraping of cadvisor and kubelet
2023-08-02 17:34:29 +01:00
Michel Hollands
d3878e1516 Merge pull request #10 from grafana/add_ruler
Add ruler and recording rules for Loki, Mimir and Tempo
2023-08-02 17:25:52 +01:00
Michel Hollands
8ae136e0c4 Add recording rules for Loki, Mimir and Tempo
Signed-off-by: Michel Hollands <michel.hollands@gmail.com>
2023-08-02 17:18:01 +01:00
Michel Hollands
ac3e4462f9 Merge pull request #9 from grafana/add_tempo_dashboards.yaml
Add tempo dashboards plus fixes
2023-08-02 17:16:31 +01:00
Michel Hollands
e9aab491db Rename dashboard configmaps
Signed-off-by: Michel Hollands <michel.hollands@gmail.com>
2023-08-02 17:15:40 +01:00
Michel Hollands
c95c0e2ca9 Add node exporter
Signed-off-by: Michel Hollands <michel.hollands@gmail.com>
2023-08-02 14:32:27 +01:00
Michel Hollands
c288a80bd4 Add metrics scraping of cadvisor and kubelet
Signed-off-by: Michel Hollands <michel.hollands@gmail.com>
2023-08-02 12:05:55 +01:00
Michel Hollands
93cac45b2e Add tempo dashboards plus fixes
Signed-off-by: Michel Hollands <michel.hollands@gmail.com>
2023-07-31 10:45:31 +01:00
Michel Hollands
6ce4be70e2 Merge pull request #8 from grafana/add_mimir_dashboards
Add Mimir dashboards
2023-07-28 09:46:17 +01:00
Michel Hollands
176312167c Merge pull request #7 from grafana/use_loki_ssd_dashboards
Use Loki SSD dashboards
2023-07-28 09:45:55 +01:00
Michel Hollands
07a336d9ed Merge pull request #6 from grafana/add_kube_state_metrics_scraping
Add scraping of kube state metrics
2023-07-28 09:42:16 +01:00
Michel Hollands
db493fbb39 Add Mimir dashboards
Signed-off-by: Michel Hollands <michel.hollands@gmail.com>
2023-07-27 15:35:34 +01:00
Michel Hollands
f4d5bcc018 Use Loki SSD dashboards
Signed-off-by: Michel Hollands <michel.hollands@gmail.com>
2023-07-27 13:48:42 +01:00
Michel Hollands
18f0dc932a Add scraping of kube state metrics
Signed-off-by: Michel Hollands <michel.hollands@gmail.com>
2023-07-27 09:23:09 +01:00
Michel Hollands
d999ef0110 Merge pull request #4 from grafana/add_regexes_to_filter_log_lines
Add regexes to filter log lines
2023-07-27 08:18:15 +01:00
Michel Hollands
9dd6584bee Add full object with stage replace block
Signed-off-by: Michel Hollands <michel.hollands@gmail.com>
2023-07-24 13:42:55 +01:00
Michel Hollands
04cf591478 cleanup and fix
Signed-off-by: Michel Hollands <michel.hollands@grafana.com>
2023-07-24 13:41:34 +01:00
Michel Hollands
9f54397e83 Add documentation for the regex
Signed-off-by: Michel Hollands <michel.hollands@grafana.com>
2023-07-24 13:41:34 +01:00
Michel Hollands
fa2b01708c Add regexes to filter out PII
Signed-off-by: Michel Hollands <michel.hollands@grafana.com>
2023-07-24 13:41:34 +01:00
Michel Hollands
a1cd5d36b0 Merge pull request #3 from grafana/add_validation
Add validation.yaml
2023-07-07 16:48:20 +01:00
Michel Hollands
a14b07239b Add check for empty list of namespaces to monitor
Signed-off-by: Michel Hollands <michel.hollands@grafana.com>
2023-07-06 14:11:08 +01:00
Michel Hollands
116586e383 Add check to if anything is enabled
Signed-off-by: Michel Hollands <michel.hollands@grafana.com>
2023-07-06 14:08:15 +01:00
Michel Hollands
67b13388a7 Add validation.yaml
Signed-off-by: Michel Hollands <michel.hollands@grafana.com>
2023-07-06 11:58:00 +01:00
Michel Hollands
39a187457c Merge pull request #2 from grafana/enable_dbs_individually
Enable DBs separately
2023-06-30 12:45:08 +01:00
75 changed files with 64724 additions and 253 deletions

66
.github/workflows/helm-ci.yml vendored Normal file
View 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
View 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

View File

@@ -3,6 +3,8 @@
This is a meta-monitoring chart for GEL, GEM and GET. It should be installed in a
separate namespace next to GEM, GEL or GET installations.
Note that this is pre-production software at the moment.
## Preparation
Create a values.yaml file based on the [default one](../charts/meta-monitoring/values.yaml).
@@ -15,29 +17,54 @@ Create a values.yaml file based on the [default one](../charts/meta-monitoring/v
## Local and cloud modes
The chart has 2 modes: local and cloud. In the local mode logs, metrics and traces are sent
The chart has 2 modes: local and cloud. In the local mode logs, metrics and/or traces are sent
to small Loki, Mimir and Tempo installations running in the meta-monitoring namespace.
![local mode](docs/images/Meta%20monitoring%20local.png)
To enable local mode set `local.enabled` to true.
To enable local mode set `local.<logs|metrics|traces>.enabled` to true.
In the cloud mode the logs, metrics and traces are sent to
In the cloud mode the logs, metrics and/or traces are sent to Grafana Cloud.
![cloud mode](docs/images/Meta%20monitoring%20cloud.png)
To enable cloud mode set `cloud.enabled` to true. The `endpoint`, `username` and `password` settings for your Grafana Cloud logs, metrics and traces instances have to be filled in as well.
To enable cloud mode set `cloud.<logs|metrics|traces>.enabled` to true. The `endpoint`, `username` and `password` settings for your Grafana Cloud logs, metrics and traces instances have to be filled in as well.
Both modes can be enabled at the same time.
## Installation
```
helm install -n meta -f values.yaml meta ./charts/meta-monitoring
helm install -n meta --skip-crds -f values.yaml meta ./charts/meta-monitoring
```
If the platform supports CRDs the `--skip-crds` option can be removed. However the CRDs are not used by this chart.
For more instructions including how to update the chart go to the [installation](docs/installation.md) page.
## Supported features
- Specify which namespaces are monitored
- Specify if logs, metrics or traces should be enabled for cloud or local
- Specify the cluster name used for the logs, metrics and traces
- Specify PII regexes that are applied to logs before they are sent to Loki (cloud or local). The capture group in the regex is replaced with *****.
- a Grafana instance is installed (when local mode is used) with the relevant datasources installed. The following dashboards are installed:
- logs dashboards
- metrics dashboards
- traces dashboards
- agent dashboards
- Retention is set to 24 hours
Most of these features are enabled by default. See the values.yaml file for how to enable/disable them.
## Caveats
- The [loki.source.kubernetes](https://grafana.com/docs/agent/latest/flow/reference/components/loki.source.kubernetes/) component of the Grafana Agent is used to scrape Kubernetes log files. This component is marked experimental at the moment.
- This has not been tested on Openshift yet.
- The underlying Loki, Mimir and Tempo are at the default size installed by the Helm chart. This might need changing when monitoring bigger Loki, Mimir or Tempo installations.
- MinIO is used as storage at the moment with a limited retention. At the moment this chart cannot be used for monitoring over longer periods.
- Agent self monitoring is not done at the moment.
## Developer help topics
- [update dependencies](docs/dev_update_dependencies.md)
- [update dependencies](docs/dev_update_dependencies.md)

View File

@@ -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"

View File

@@ -25,24 +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"
tags:
- local-logs
- local-metrics
- local-traces
condition: local.minio.enabled

View 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

View 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

View File

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

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

View File

@@ -0,0 +1,786 @@
{
"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
}

View File

@@ -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"
}
],

View File

@@ -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
}
}

View File

@@ -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": ""
}

View File

@@ -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}}",

View File

@@ -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,

View File

@@ -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",

View File

@@ -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
}
}

View File

@@ -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",

View File

@@ -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",

View File

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

File diff suppressed because it is too large Load Diff

View File

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

File diff suppressed because it is too large Load Diff

View File

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

View File

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

View File

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

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

View File

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

View File

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

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

View File

@@ -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"

View 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"

View 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"

View File

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

View File

@@ -37,20 +37,154 @@ data:
}
}
// Logs
{{- if or .Values.local.logs.enabled .Values.cloud.logs.enabled }}
loki.source.kubernetes "pods" {
targets = discovery.relabel.rename_meta_labels.output
forward_to = [ {{ include "agent.loki_process_targets" . }} ]
}
{{- if not (empty .Values.logs.piiRegexes) }}
loki.process "PII" {
forward_to = [ {{ include "agent.loki_write_targets" . }} ]
{{- range .Values.logs.piiRegexes }}
stage.replace {
expression = "{{ .expression }}"
source = "{{ .source }}"
replace = "{{ .replace }}"
}
{{- end }}
}
{{- 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" {

View File

@@ -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 }}

View File

@@ -1,15 +1,16 @@
{{- if .Values.local.logs.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.dashboards.logs.enabled }}
- disableDeletion: true
editable: false
folder: Loki
@@ -26,4 +27,65 @@ data:
path: /var/lib/grafana/dashboards/loki-2
orgId: 1
type: file
{{- end }}
{{- if .Values.dashboards.metrics.enabled }}
- disableDeletion: true
editable: false
folder: Mimir
name: mimir-1
options:
path: /var/lib/grafana/dashboards/mimir-1
orgId: 1
type: file
- disableDeletion: true
editable: false
folder: Mimir
name: mimir-2
options:
path: /var/lib/grafana/dashboards/mimir-2
orgId: 1
type: file
- disableDeletion: true
editable: false
folder: Mimir
name: mimir-3
options:
path: /var/lib/grafana/dashboards/mimir-3
orgId: 1
type: file
- disableDeletion: true
editable: false
folder: Mimir
name: mimir-4
options:
path: /var/lib/grafana/dashboards/mimir-4
orgId: 1
type: file
- disableDeletion: true
editable: false
folder: Mimir
name: mimir-5
options:
path: /var/lib/grafana/dashboards/mimir-5
orgId: 1
type: file
{{- end }}
{{- if .Values.dashboards.traces.enabled }}
- disableDeletion: true
editable: false
folder: Tempo
name: tempo-1
options:
path: /var/lib/grafana/dashboards/tempo-1
orgId: 1
type: file
{{- end }}
- disableDeletion: true
editable: false
folder: Agent
name: agent-1
options:
path: /var/lib/grafana/dashboards/agent-1
orgId: 1
type: file
{{- end }}

View File

@@ -3,7 +3,7 @@
apiVersion: v1
kind: ConfigMap
metadata:
name: loki-datasources-provisioning
name: datasources-provisioning
namespace: {{ $.Release.Namespace }}
data:
datasources.yaml: |

View File

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

View File

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

View File

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

View File

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

View File

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

View File

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

View File

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

View File

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

View File

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

View File

@@ -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 }}

View 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 }}

View File

@@ -0,0 +1,39 @@
{{- if not (eq .Values.local.minio.enabled (or .Values.local.traces.enabled (or .Values.local.logs.enabled .Values.local.metrics.enabled))) -}}
{{- fail "minio.enabled should be set to true if any of the the local databases is enabled " -}}
{{- end -}}
{{- if eq .Values.cloud.logs.enabled true -}}
{{- if or (empty .Values.cloud.logs.endpoint) (or (empty .Values.cloud.logs.username) (empty .Values.cloud.logs.password)) -}}
{{- fail "if cloud.logs is enabled then the endpoint, username and password have to be filled in" -}}
{{- end -}}
{{- end -}}
{{- if eq .Values.cloud.metrics.enabled true -}}
{{- if or (empty .Values.cloud.metrics.endpoint) (or (empty .Values.cloud.metrics.username) (empty .Values.cloud.metrics.password)) -}}
{{- fail "if cloud.metrics is enabled then the endpoint, username and password have to be filled in" -}}
{{- end -}}
{{- end -}}
{{- if eq .Values.cloud.traces.enabled true -}}
{{- if or (empty .Values.cloud.traces.endpoint) (or (empty .Values.cloud.traces.username) (empty .Values.cloud.traces.password)) -}}
{{- fail "if cloud.traces is enabled then the endpoint, username and password have to be filled in" -}}
{{- end -}}
{{- end -}}
{{- if eq .Values.cloud.traces.enabled false -}}
{{- if eq .Values.cloud.metrics.enabled false -}}
{{- if eq .Values.cloud.logs.enabled false -}}
{{- if eq .Values.local.traces.enabled false -}}
{{- if eq .Values.local.metrics.enabled false -}}
{{- if eq .Values.local.logs.enabled false -}}
{{- fail "nothing has been enabled" -}}
{{- end -}}
{{- end -}}
{{- end -}}
{{- end -}}
{{- end -}}
{{- end -}}
{{- if empty .Values.namespacesToMonitor -}}
{{- fail "No namespaces have been specified in namespacesToMonitor" -}}
{{- end -}}

View File

@@ -1,16 +1,30 @@
# Specify the namespaces to monitor here
namespacesToMonitor:
- loki
- mimir
- tempo
clusterName: "observability" # TODO check if this can be derived
# The name of the cluster where this will be installed
clusterName: "meta-monitoring"
# Turn on or off for local storing of metrics, logs or traces
tags:
local-logs: true
local-metrics: true
local-traces: true
# 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
# Unfortunately this is duplicate as Helm's tags and conditions fro dependencies are limited
# Set to true for a local version of logs, metrics or traces
local:
logs:
enabled: false
@@ -18,31 +32,42 @@ local:
enabled: false
traces:
enabled: false
minio:
enabled: false # This should be set to true if any of the previous is enabled
cloud:
# 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:
# This example replaces the word after password with *****
# - expression: "password (\\\\S+)"
# 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
endpoint:
username:
password:
metrics:
enabled: true
endpoint:
username:
password:
traces:
enabled: true
endpoint:
username:
password:
global:
minio:
rootUser: "rootuser"
rootPassword: "rootpassword"
kubeStateMetrics:
# Scrape https://github.com/kubernetes/kube-state-metrics by default
enabled: true
# This endpoint is created when the helm chart from
# https://artifacthub.io/packages/helm/prometheus-community/kube-state-metrics/
# is used. Change this if kube-state-metrics is installed somewhere else.
endpoint: kube-state-metrics.kube-state-metrics.svc.cluster.local:8080
# The following are configuration for the dependencies.
# These should not be changed.
# These should usually not be changed.
loki:
loki:
@@ -50,13 +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: 24h
monitoring:
dashboards:
enabled: false
@@ -107,6 +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: 24h
tempo-distributed:
tempo:
@@ -120,6 +156,9 @@ tempo-distributed:
access_key: "{{ .Values.global.minio.rootUser }}"
secret_key: "{{ .Values.global.minio.rootPassword }}"
insecure: true
compactor:
compaction:
block_retention: 24h
traces:
otlp:
http:
@@ -154,4 +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
View 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