This commit is contained in:
decentral1se 2022-03-17 10:18:32 +01:00
commit 4b2b931eb8
No known key found for this signature in database
GPG Key ID: 03789458B3D0C410
16 changed files with 4390 additions and 0 deletions

1
.gitignore vendored Normal file
View File

@ -0,0 +1 @@
/.envrc

3
README.md Normal file
View File

@ -0,0 +1,3 @@
# new-monitoring-experiment
WIP.

View File

@ -0,0 +1 @@
hi

29
monitoring/.env.sample Normal file
View File

@ -0,0 +1,29 @@
TYPE=monitoring
GRAFANA_DOMAIN=grafana.example.com
PROMETHEUS_DOMAIN=prometheus.example.com
LETS_ENCRYPT_ENV=production
# Edit this in order to allow collection of traefik metrics
#TRAEFIK_METRICS_ENABLED=1
#TRAEFIK_SERVICE_NAME=traefik_app
# grafana SMTP configuration (optional)
#GF_SMTP_HOST=changeme
#GF_SMTP_ENABLED=1
#GF_SMTP_FROM_ADDRESS=grafana@example.com
#GF_SMTP_SKIP_VERIFY=1
# Additional grafana settings (unlikely to require editing)
GF_SECURITY_ALLOW_EMBEDDING=1
GF_INSTALL_PLUGINS=grafana-piechart-panel
GF_SERVER_ROOT_URL=https://${GRAFANA_DOMAIN}
# Loki stores logs in object storage, fill these up with your
# minio configuration (or any s3-compatible object store)
#LOKI_AWS_ENDPOINT=https://minio/
#LOKI_AWS_REGION=eu-west-1
#LOKI_ACCESS_KEY_ID=
#LOKI_SECRET_ACCESS_KEY=
#LOKI_BUCKET_NAMES=loki

29
monitoring/README.md Normal file
View File

@ -0,0 +1,29 @@
# Monitoring
A server and application monitoring stack based on Prometheus, Loki and Grafana.
<!-- metadata -->
* **Category**: Utilities
* **Status**: 2, beta
* **Images**: [`prom/prometheus`](https://hub.docker.com/r/prom/prometheus) [`grafana/grafana`](https://hub.docker.com/r/grafana/grafana) [`grafana/loki`](https://hub.docker.com/r/grafana/loki), upstream
* **Healthcheck**: 3
* **Backups**: No
* **Email**: 3
* **Tests**: No
* **SSO**: 1
<!-- endmetadata -->
## Basic usage
1. Set up Docker Swarm and [`abra`]
2. Deploy [`coop-cloud/traefik`]
3. Deploy [`coop-cloud/minio`]
4. `abra app new monitoring --secrets` (optionally with `--pass` if you'd like
to save secrets in `pass`)
5. `abra app YOURAPPDOMAIN config` - be sure to change `GRAFANA_DOMAIN` and `PROMETHEUS_DOMAIN` to something that resolves to
your Docker swarm box
6. `abra app YOURAPPDOMAIN deploy`
7. Open the configured domain in your browser to finish set-up
[`abra`]: https://git.autonomic.zone/autonomic-cooperative/abra
[`coop-cloud/traefik`]: https://git.autonomic.zone/coop-cloud/traefik

9
monitoring/abra.sh Normal file
View File

@ -0,0 +1,9 @@
export PROMETHEUS_YML_VERSION=v2
export PROMTAIL_YML_VERSION=v1
export LOKI_YML_VERSION=v1
export NODE_EXPORTER_ENTRYPOINT_VERSION=v1
export GRAFANA_DATASOURCES_YML_VERSION=v1
export GRAFANA_DASHBOARDS_YML_VERSION=v1
export GRAFANA_SWARM_DASHBOARD_JSON_VERSION=v1
export GRAFANA_STACKS_DASHBOARD_JSON_VERSION=v1
export GRAFANA_TRAEFIK_DASHBOARD_JSON_VERSION=v1

129
monitoring/compose.yml Normal file
View File

@ -0,0 +1,129 @@
---
version: "3.8"
services:
app:
image: grafana/grafana
volumes:
- grafana-data:/var/lib/grafana:rw
configs:
- source: grafana_datasources_yml
target: /etc/grafana/provisioning/datasources/datasources.yml
- source: grafana_dashboards_yml
target: /etc/grafana/provisioning/dashboards/dashboards.yml
- source: grafana_swarm_dashboard_json
target: /var/lib/grafana/dashboards/docker-swarm-nodes.json
- source: grafana_stacks_dashboard_json
target: /var/lib/grafana/dashboards/docker-swarm-stacks.json
- source: grafana_traefik_dashboard_json
target: /var/lib/grafana/dashboards/traefik.json
networks:
- proxy
environment:
- GF_SMTP_HOST
- GF_SMTP_ENABLED
- GF_SMTP_FROM_ADDRESS
- GF_SMTP_SKIP_VERIFY
- GF_SECURITY_ALLOW_EMBEDDING
- GF_INSTALL_PLUGINS=grafana-piechart-panel
- GF_SERVER_ROOT_URL=https://${GRAFANA_DOMAIN}
deploy:
labels:
- "traefik.enable=true"
- "traefik.http.services.${STACK_NAME}-grafana.loadbalancer.server.port=3000"
- "traefik.http.routers.${STACK_NAME}-grafana.rule=Host(`${GRAFANA_DOMAIN}`)"
- "traefik.http.routers.${STACK_NAME}-grafana.entrypoints=web-secure"
- "traefik.http.routers.${STACK_NAME}-grafana.tls=true"
- "traefik.http.routers.${STACK_NAME}-grafana.tls.certresolver=${LETS_ENCRYPT_ENV}"
healthcheck:
test: "wget -q http://localhost:3000/ -O/dev/null"
interval: 5s
timeout: 10s
retries: 3
start_period: 10s
loki:
image: grafana/loki:2.0.0
command: -config.file=/etc/loki/local-config.yaml
networks:
- loki
- api
deploy:
endpoint_mode: dnsrr
ports:
- target: 3100
published: 3100
protocol: tcp
mode: host
configs:
- source: loki_yml
target: /etc/loki/local-config.yaml
volumes:
- loki-data:/loki
prometheus:
image: prom/prometheus:latest
volumes:
- prometheus-data:/prometheus:rw
configs:
- source: prometheus_yml
target: /etc/prometheus/prometheus.yml
networks:
api:
aliases:
- prometheus_api
exporters: ~
proxy: ~
deploy:
restart_policy:
condition: on-failure
labels:
- "traefik.enable=true"
- "traefik.http.services.${STACK_NAME}_prometheus.loadbalancer.server.port=9090"
- "traefik.http.routers.${STACK_NAME}-prometheus.rule=Host(`${PROMETHEUS_DOMAIN}`)"
- "traefik.http.routers.${STACK_NAME}-prometheus.entrypoints=web-secure"
- "traefik.http.routers.${STACK_NAME}-prometheus.tls=true"
- "traefik.http.routers.${STACK_NAME}-prometheus.tls.certresolver=${LETS_ENCRYPT_ENV}"
healthcheck:
test: "wget -q http://localhost:9090/graph -O/dev/null"
interval: 5s
timeout: 10s
retries: 3
start_period: 10s
configs:
prometheus_yml:
template_driver: golang
name: ${STACK_NAME}_prometheus_yml_${PROMETHEUS_YML_VERSION}
file: prometheus.yml.tmpl
promtail_yml:
name: ${STACK_NAME}_promtail_yml_${PROMTAIL_YML_VERSION}
file: promtail.yml
loki_yml:
template_driver: golang
name: ${STACK_NAME}_loki_yml_${LOKI_YML_VERSION}
file: loki.yml.tmpl
grafana_datasources_yml:
name: ${STACK_NAME}_grafana_datasources_yml_${GRAFANA_DATASOURCES_YML_VERSION}
file: grafana-datasources.yml
grafana_dashboards_yml:
name: ${STACK_NAME}_grafana_dashboards_yml_${GRAFANA_DASHBOARDS_YML_VERSION}
file: grafana-dashboards.yml
grafana_swarm_dashboard_json:
name: ${STACK_NAME}_grafana_swarm_dashboard_json_${GRAFANA_SWARM_DASHBOARD_JSON_VERSION}
file: grafana-swarm-dashboard.json
grafana_stacks_dashboard_json:
name: ${STACK_NAME}_grafana_stacks_dashboard_json_${GRAFANA_STACKS_DASHBOARD_JSON_VERSION}
file: grafana-stacks-dashboard.json
grafana_traefik_dashboard_json:
name: ${STACK_NAME}_grafana_traefik_dashboard_json_${GRAFANA_TRAEFIK_DASHBOARD_JSON_VERSION}
file: grafana-traefik-dashboard.json
volumes:
prometheus-data:
grafana-data:
loki-data:
networks:
proxy:
external: true

View File

@ -0,0 +1,13 @@
apiVersion: 1
providers:
- name: 'default-dashboard-provider'
orgId: 1
folder: 'default-dashboards'
type: file
disableDeletion: false
updateIntervalSeconds: 10
allowUiUpdates: true
options:
path: /var/lib/grafana/dashboards
foldersFromFilesStructure: true

View File

@ -0,0 +1,10 @@
apiVersion: 1
datasources:
- name: Prometheus
type: prometheus
access: proxy
orgId: 1
url: http://prometheus:9090
isDefault: true
editable: false

View File

@ -0,0 +1,745 @@
{
"annotations": {
"list": [
{
"builtIn": 1,
"datasource": "-- Grafana --",
"enable": true,
"hide": true,
"iconColor": "rgba(0, 211, 255, 1)",
"name": "Annotations & Alerts",
"type": "dashboard"
}
]
},
"description": "Simple docker swarm monitoring with relation to individual stacks.",
"editable": true,
"gnetId": 7007,
"graphTooltip": 1,
"id": 2,
"iteration": 1626744694222,
"links": [],
"panels": [
{
"cacheTimeout": null,
"datasource": "Prometheus",
"fieldConfig": {
"defaults": {
"color": {
"mode": "thresholds"
},
"decimals": 1,
"mappings": [
{
"options": {
"match": "null",
"result": {
"text": "N/A"
}
},
"type": "special"
}
],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "red",
"value": 80
}
]
},
"unit": "s"
},
"overrides": []
},
"gridPos": {
"h": 3,
"w": 4,
"x": 0,
"y": 0
},
"id": 10,
"interval": null,
"links": [],
"maxDataPoints": 100,
"options": {
"colorMode": "none",
"graphMode": "none",
"justifyMode": "auto",
"orientation": "horizontal",
"reduceOptions": {
"calcs": [
"mean"
],
"fields": "",
"values": false
},
"text": {},
"textMode": "auto"
},
"pluginVersion": "8.0.6",
"targets": [
{
"expr": "(time() - min(container_start_time_seconds{container_label_com_docker_stack_namespace=~\"$stack\"}))",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "",
"refId": "A"
}
],
"title": "Stack Uptime",
"type": "stat"
},
{
"aliasColors": {},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "Prometheus",
"decimals": null,
"fill": 5,
"fillGradient": 0,
"gridPos": {
"h": 7,
"w": 20,
"x": 4,
"y": 0
},
"height": "270px",
"hiddenSeries": false,
"id": 1,
"legend": {
"alignAsTable": true,
"avg": false,
"current": true,
"hideEmpty": false,
"hideZero": true,
"max": true,
"min": true,
"rightSide": true,
"show": true,
"total": false,
"values": true
},
"lines": true,
"linewidth": 1,
"links": [],
"nullPointMode": "null as zero",
"options": {
"alertThreshold": true
},
"percentage": false,
"pluginVersion": "8.0.6",
"pointradius": 5,
"points": false,
"renderer": "flot",
"seriesOverrides": [],
"spaceLength": 10,
"stack": true,
"steppedLine": false,
"targets": [
{
"expr": "sum(rate(container_cpu_usage_seconds_total{container_label_com_docker_stack_namespace=~\"$stack\"}[$interval])) by (container_label_com_docker_swarm_service_name, container_label_com_docker_swarm_task_id)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{ container_label_com_docker_swarm_service_name }} - {{ container_label_com_docker_swarm_task_id }}",
"refId": "A",
"step": 2
}
],
"thresholds": [],
"timeFrom": null,
"timeRegions": [],
"timeShift": null,
"title": "CPU Usage per Container",
"tooltip": {
"shared": true,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": []
},
"yaxes": [
{
"format": "percentunit",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
},
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": false
}
],
"yaxis": {
"align": false,
"alignLevel": null
}
},
{
"cacheTimeout": null,
"datasource": "Prometheus",
"fieldConfig": {
"defaults": {
"color": {
"mode": "thresholds"
},
"mappings": [
{
"options": {
"match": "null",
"result": {
"text": "N/A"
}
},
"type": "special"
}
],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "red",
"value": 80
}
]
},
"unit": "none"
},
"overrides": []
},
"gridPos": {
"h": 4,
"w": 4,
"x": 0,
"y": 3
},
"id": 3,
"interval": null,
"links": [],
"maxDataPoints": 100,
"options": {
"colorMode": "none",
"graphMode": "none",
"justifyMode": "auto",
"orientation": "horizontal",
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"text": {},
"textMode": "auto"
},
"pluginVersion": "8.0.6",
"targets": [
{
"expr": "count(rate(container_last_seen{container_label_com_docker_stack_namespace=~\"$stack\"}[$interval]))",
"format": "time_series",
"intervalFactor": 2,
"refId": "B",
"step": 4
}
],
"title": "Containers",
"type": "stat"
},
{
"aliasColors": {},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "Prometheus",
"fill": 3,
"fillGradient": 0,
"gridPos": {
"h": 7,
"w": 24,
"x": 0,
"y": 7
},
"height": "270px",
"hiddenSeries": false,
"id": 5,
"legend": {
"alignAsTable": true,
"avg": false,
"current": true,
"hideZero": true,
"max": true,
"min": true,
"rightSide": true,
"show": true,
"sort": "current",
"sortDesc": true,
"total": false,
"values": true
},
"lines": true,
"linewidth": 2,
"links": [],
"nullPointMode": "null as zero",
"options": {
"alertThreshold": true
},
"percentage": false,
"pluginVersion": "8.0.6",
"pointradius": 5,
"points": false,
"renderer": "flot",
"seriesOverrides": [],
"spaceLength": 10,
"stack": true,
"steppedLine": false,
"targets": [
{
"expr": "sum(container_memory_rss{container_label_com_docker_stack_namespace=~\"$stack\"}) by (container_label_com_docker_swarm_service_name, container_label_com_docker_swarm_task_id)",
"format": "time_series",
"hide": false,
"intervalFactor": 2,
"legendFormat": "{{ container_label_com_docker_swarm_service_name }} - {{ container_label_com_docker_swarm_task_id }}",
"metric": "container_memory_rss",
"refId": "A",
"step": 2
}
],
"thresholds": [],
"timeFrom": null,
"timeRegions": [],
"timeShift": null,
"title": "Memory Usage per Container",
"tooltip": {
"shared": true,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": []
},
"yaxes": [
{
"format": "bytes",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
},
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
}
],
"yaxis": {
"align": false,
"alignLevel": null
}
},
{
"aliasColors": {},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "Prometheus",
"fill": 1,
"fillGradient": 0,
"gridPos": {
"h": 7,
"w": 24,
"x": 0,
"y": 14
},
"height": "270px",
"hiddenSeries": false,
"id": 6,
"legend": {
"alignAsTable": true,
"avg": false,
"current": true,
"hideEmpty": false,
"hideZero": true,
"max": true,
"min": true,
"rightSide": true,
"show": true,
"sort": "current",
"sortDesc": true,
"total": false,
"values": true
},
"lines": true,
"linewidth": 2,
"links": [],
"nullPointMode": "null as zero",
"options": {
"alertThreshold": true
},
"percentage": false,
"pluginVersion": "8.0.6",
"pointradius": 5,
"points": false,
"renderer": "flot",
"seriesOverrides": [],
"spaceLength": 10,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "sum(rate(container_network_receive_bytes_total{container_label_com_docker_stack_namespace=~\"$stack\"}[$interval])) by (container_label_com_docker_swarm_service_name, container_label_com_docker_swarm_task_id)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{ container_label_com_docker_swarm_service_name }} - {{ container_label_com_docker_swarm_task_id }}",
"refId": "A",
"step": 2
}
],
"thresholds": [],
"timeFrom": null,
"timeRegions": [],
"timeShift": null,
"title": "Incoming Network Traffic per Container",
"tooltip": {
"shared": true,
"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": null,
"show": true
},
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
}
],
"yaxis": {
"align": false,
"alignLevel": null
}
},
{
"aliasColors": {},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "Prometheus",
"fill": 1,
"fillGradient": 0,
"gridPos": {
"h": 7,
"w": 24,
"x": 0,
"y": 21
},
"height": "270px",
"hiddenSeries": false,
"id": 8,
"legend": {
"alignAsTable": true,
"avg": false,
"current": true,
"hideEmpty": false,
"hideZero": true,
"max": true,
"min": true,
"rightSide": true,
"show": true,
"sort": "current",
"sortDesc": true,
"total": false,
"values": true
},
"lines": true,
"linewidth": 1,
"links": [],
"nullPointMode": "null",
"options": {
"alertThreshold": true
},
"percentage": false,
"pluginVersion": "8.0.6",
"pointradius": 5,
"points": false,
"renderer": "flot",
"seriesOverrides": [],
"spaceLength": 10,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "sum(rate(container_network_transmit_bytes_total{container_label_com_docker_stack_namespace=~\"$stack\"}[$interval])) by (container_label_com_docker_swarm_service_name, container_label_com_docker_swarm_task_id)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{ container_label_com_docker_swarm_service_name }} - {{ container_label_com_docker_swarm_task_id }}",
"refId": "A",
"step": 2
}
],
"thresholds": [],
"timeFrom": null,
"timeRegions": [],
"timeShift": null,
"title": "Outgoing Network Traffic per Container",
"tooltip": {
"shared": true,
"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": null,
"show": true
},
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": false
}
],
"yaxis": {
"align": false,
"alignLevel": null
}
}
],
"schemaVersion": 30,
"style": "dark",
"tags": [
"prometheus",
"cAdvisor",
"node-exporter",
"alertmanager"
],
"templating": {
"list": [
{
"allValue": null,
"current": {
"selected": false,
"text": "pretix",
"value": "pretix"
},
"datasource": "Prometheus",
"definition": "",
"description": null,
"error": null,
"hide": 0,
"includeAll": false,
"label": "Stack",
"multi": false,
"name": "stack",
"options": [],
"query": {
"query": "query_result(count(container_last_seen{container_label_com_docker_stack_namespace =~\".+\"}) by (container_label_com_docker_stack_namespace))",
"refId": "Prometheus-stack-Variable-Query"
},
"refresh": 1,
"regex": "/container_label_com_docker_stack_namespace=\"(.*)\"/",
"skipUrlSync": false,
"sort": 2,
"tagValuesQuery": "",
"tagsQuery": "",
"type": "query",
"useTags": false
},
{
"auto": true,
"auto_count": 50,
"auto_min": "50s",
"current": {
"selected": false,
"text": "auto",
"value": "$__auto_interval_interval"
},
"description": null,
"error": null,
"hide": 0,
"label": "Interval",
"name": "interval",
"options": [
{
"selected": true,
"text": "auto",
"value": "$__auto_interval_interval"
},
{
"selected": false,
"text": "30s",
"value": "30s"
},
{
"selected": false,
"text": "1m",
"value": "1m"
},
{
"selected": false,
"text": "2m",
"value": "2m"
},
{
"selected": false,
"text": "3m",
"value": "3m"
},
{
"selected": false,
"text": "5m",
"value": "5m"
},
{
"selected": false,
"text": "7m",
"value": "7m"
},
{
"selected": false,
"text": "10m",
"value": "10m"
},
{
"selected": false,
"text": "30m",
"value": "30m"
},
{
"selected": false,
"text": "1h",
"value": "1h"
},
{
"selected": false,
"text": "6h",
"value": "6h"
},
{
"selected": false,
"text": "12h",
"value": "12h"
},
{
"selected": false,
"text": "1d",
"value": "1d"
},
{
"selected": false,
"text": "7d",
"value": "7d"
},
{
"selected": false,
"text": "14d",
"value": "14d"
},
{
"selected": false,
"text": "30d",
"value": "30d"
}
],
"query": "30s,1m,2m,3m,5m,7m,10m,30m,1h,6h,12h,1d,7d,14d,30d",
"refresh": 2,
"skipUrlSync": false,
"type": "interval"
}
]
},
"time": {
"from": "now-30m",
"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": "browser",
"title": "Swarm Stack Monitoring",
"uid": "KdVoGQm7z",
"version": 1
}

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

71
monitoring/loki.yml.tmpl Normal file
View File

@ -0,0 +1,71 @@
auth_enabled: false
server:
http_listen_port: 3100
distributor:
ring:
kvstore:
store: memberlist
ingester:
lifecycler:
ring:
kvstore:
store: memberlist
replication_factor: 1
final_sleep: 0s
chunk_idle_period: 5m
chunk_retain_period: 30s
memberlist:
abort_if_cluster_join_fails: false
# Expose this port on all distributor, ingester
# and querier replicas.
bind_port: 7946
# You can use a headless k8s service for all distributor,
# ingester and querier components.
join_members:
- loki:7946
max_join_backoff: 1m
max_join_retries: 10
min_join_backoff: 1s
schema_config:
configs:
- from: 2020-11-25
store: boltdb-shipper
object_store: aws
schema: v11
index:
prefix: index_
period: 24h
storage_config:
boltdb_shipper:
active_index_directory: /loki/index
cache_location: /loki/index_cache
resync_interval: 5s
shared_store: aws
aws:
endpoint: {{ env LOKI_AWS_ENDPOINT }}
region: {{ env LOKI_AWS_REGION }}
access_key_id: {{ env LOKI_ACCESS_KEY_ID }}
secret_access_key: {{ env LOKI_SECRET_ACCESS_KEY }}
bucketnames: {{ env_LOKI_BUCKET_NAMES }}
insecure: false
sse_encryption: false
http_config:
idle_conn_timeout: 90s
response_header_timeout: 0s
insecure_skip_verify: false
s3forcepathstyle: true
limits_config:
enforce_metric_name: false
reject_old_samples: true
reject_old_samples_max_age: 168h

View File

@ -0,0 +1,9 @@
#!/bin/sh -e
NODE_NAME=$(cat /etc/nodename)
mkdir -p /etc/node-exporter
echo "node_meta{node_id=\"$NODE_ID\", container_label_com_docker_swarm_node_id=\"$NODE_ID\", node_name=\"$NODE_NAME\"} 1" > /etc/node-exporter/node-meta.prom
set -- /bin/node_exporter "$@"
exec "$@"

View File

@ -0,0 +1,58 @@
global:
scrape_interval: 30s # Set the scrape interval to every 15 seconds. Default is every 1 minute.
evaluation_interval: 30s # Evaluate rules every 15 seconds. The default is every 1 minute.
# scrape_timeout is set to the global default (10s).
# Alertmanager configuration
alerting:
alertmanagers:
- static_configs:
- targets:
# - alertmanager:9093
# Load rules once and periodically evaluate them according to the global 'evaluation_interval'.
rule_files:
# - "first_rules.yml"
# - "second_rules.yml"
# A scrape configuration containing exactly one endpoint to scrape:
# Here it's Prometheus itself.
scrape_configs:
# The job name is added as a label `job=<job_name>` to any timeseries scraped from this config.
- job_name: 'prometheus'
# metrics_path defaults to '/metrics'
# scheme defaults to 'http'.
static_configs:
- targets:
- localhost:9090
# http://node_exporter:9100/metrics
- job_name: node-exporter
scrape_interval: 10s
metrics_path: "/metrics"
dns_sd_configs:
- names:
- 'tasks.node_exporter'
type: 'A'
port: 9100
- job_name: 'cadvisor'
scrape_interval: 30s
metrics_path: '/metrics'
dns_sd_configs:
- names:
- 'tasks.cadvisor'
type: 'A'
port: 8080
{{ if eq (env "TRAEFIK_METRICS_ENABLED") "1" }}
- job_name: 'traefik'
scrape_interval: 30s
metrics_path: '/metrics'
dns_sd_configs:
- names:
- 'tasks.{{ (env "TRAEFIK_SERVICE_NAME") }}'
type: 'A'
port: 8082
{{ end }}

18
monitoring/promtail.yml Normal file
View File

@ -0,0 +1,18 @@
server:
http_listen_port: 9080
grpc_listen_port: 0
positions:
filename: /tmp/positions.yaml
clients:
- url: http://loki:3100/loki/api/v1/push
scrape_configs:
- job_name: system
static_configs:
- targets:
- localhost
labels:
job: varlogs
__path__: /var/log/*log