hackity hack hack loki now working

This commit is contained in:
decentral1se 2022-03-18 14:50:28 +01:00
parent 5ef8936388
commit e7dd69f38b
No known key found for this signature in database
GPG Key ID: 03789458B3D0C410
13 changed files with 55 additions and 4077 deletions

View File

@ -6,6 +6,8 @@
- [p.monitor.autonomic.zone](https://p.monitor.autonomic.zone)
- [l.monitor.autonomic.zone](https://l.monitor.autonomic.zone)
## setup
```
printf $(pass show hosts/swarm.autonomic.zone/minio/secret_key) | docker secret create gp_monitoring_loki_aws_secret_access_key_v1 -
printf password | docker secret create gp_monitoring_grafana_admin_password_v1 -
@ -24,3 +26,8 @@ docker context use monitor.autonomic.zone
docker stack deploy -c compose.yml gp_monitoring
```
## questions / TODO
- [ ] how to load in secrets from multiple hosts & keep a recipe generic?
- [ ] basic auth on gathering stack

View File

@ -10,16 +10,6 @@ services:
- grafana_admin_password
- grafana_oauth_client_secret
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
- source: grafana_custom_ini
target: /etc/grafana/grafana.ini
networks:
@ -56,6 +46,7 @@ services:
image: prom/prometheus:v2.34.0
secrets:
- prometheus_admin_password
- prometheus_admin_password_hashed
volumes:
- prometheus-data:/prometheus:rw
configs:
@ -102,7 +93,6 @@ services:
- ALERTMANAGER_SMTP_HOST
- ALERTMANAGER_SMTP_TO
# Note(d1): https://grafana.com/docs/loki/latest/operations/authentication/
web:
image: nginx:1.20.0
networks:
@ -117,7 +107,7 @@ services:
- source: htpasswd_conf
target: /etc/nginx/conf.d/loki.htpasswd
secrets:
- loki_admin_password
- loki_admin_password_hashed
deploy:
restart_policy:
condition: on-failure
@ -141,10 +131,11 @@ services:
secrets:
- loki_aws_secret_access_key
environment:
- LOKI_ACCESS_KEY_ID
- LOKI_AWS_ENDPOINT
- LOKI_AWS_REGION
- LOKI_ACCESS_KEY_ID
- LOKI_BUCKET_NAMES
- STACK_NAME
configs:
grafana_custom_ini:
@ -175,21 +166,6 @@ configs:
template_driver: golang
name: ${STACK_NAME}_htpasswd_${HTPASSWD_CONFIG_VERSION}
file: loki.htpasswd.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:
@ -212,12 +188,15 @@ secrets:
grafana_oauth_client_secret:
external: true
name: ${STACK_NAME}_grafana_oauth_client_secret_${SECRET_GRAFANA_OAUTH_CLIENT_SECRET_VERSION}
prometheus_admin_password_hashed:
external: true
name: ${STACK_NAME}_prometheus_admin_password_hashed_${SECRET_PROMETHEUS_ADMIN_PASSWORD_HASHED_VERSION}
prometheus_admin_password:
external: true
name: ${STACK_NAME}_prometheus_admin_password_${SECRET_PROMETHEUS_ADMIN_PASSWORD_VERSION}
alertmanager_smtp_password:
external: true
name: ${STACK_NAME}_alertmanager_smtp_password_${SECRET_ALERTMANAGER_SMTP_PASSWORD_VERSION}
loki_admin_password:
loki_admin_password_hashed:
external: true
name: ${STACK_NAME}_loki_admin_password_${SECRET_LOKI_ADMIN_PASSWORD_VERSION}
name: ${STACK_NAME}_loki_admin_password_hashed_${SECRET_LOKI_ADMIN_PASSWORD_HASHED_VERSION}

11
env
View File

@ -31,9 +31,9 @@ LOKI_ACCESS_KEY_ID=bush-debrief-approval-robust-scraggly-molecule
LOKI_BUCKET_NAMES=loki
# NOTE(d1): abra.sh env vars, while we deploy things manually
PROMETHEUS_YML_VERSION=v2
PROMETHEUS_YML_VERSION=v6
PROMTAIL_YML_VERSION=v1
LOKI_YML_VERSION=v1
LOKI_YML_VERSION=v2
NODE_EXPORTER_ENTRYPOINT_VERSION=v1
GRAFANA_DATASOURCES_YML_VERSION=v1
GRAFANA_DASHBOARDS_YML_VERSION=v1
@ -41,9 +41,9 @@ GRAFANA_SWARM_DASHBOARD_JSON_VERSION=v1
GRAFANA_STACKS_DASHBOARD_JSON_VERSION=v1
GRAFANA_TRAEFIK_DASHBOARD_JSON_VERSION=v1
GRAFANA_CUSTOM_INI_VERSION=v1
PROMETHEUS_WEB_YML_VERSION=v1
PROMETHEUS_WEB_YML_VERSION=v2
ALERTMANAGER_CONFIG_VERSION=v1
NGINX_CONFIG_VERSION=v1
NGINX_CONFIG_VERSION=v5
HTPASSWD_CONFIG_VERSION=v1
KEYCLOAK_AUTH_URL="https://id.autonomic.zone/auth/realms/autonomic/protocol/openid-connect/auth"
@ -54,8 +54,9 @@ SECRET_LOKI_AWS_SECRET_ACCESS_KEY_VERSION=v1
SECRET_GRAFANA_ADMIN_PASSWORD_VERSION=v1
SECRET_GRAFANA_OAUTH_CLIENT_SECRET_VERSION=v1
SECRET_PROMETHEUS_ADMIN_PASSWORD_VERSION=v1
SECRET_PROMETHEUS_ADMIN_PASSWORD_HASHED_VERSION=v1
SECRET_ALERTMANAGER_SMTP_PASSWORD_VERSION=v1
SECRET_LOKI_ADMIN_PASSWORD_VERSION=v1
SECRET_LOKI_ADMIN_PASSWORD_HASHED_VERSION=v1
ALERTMANAGER_SMTP_FROM=noreply@autonomic.zone
ALERTMANAGER_SMTP_HOST=mail.gandi.net:465

View File

@ -1,14 +0,0 @@
---
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

@ -1,11 +0,0 @@
---
apiVersion: 1
datasources:
- name: Prometheus
type: prometheus
access: proxy
orgId: 1
url: http://prometheus:9090
isDefault: true
editable: false

View File

@ -1,745 +0,0 @@
{
"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

View File

@ -1 +1 @@
loki:{{ secret "loki_admin_password" }}
loki:{{ secret "loki_admin_password_hashed" }}

View File

@ -22,7 +22,7 @@ memberlist:
abort_if_cluster_join_fails: false
bind_port: 7946
join_members:
- loki:7946
- {{ env "STACK_NAME" }}_loki:7946
max_join_backoff: 1m
max_join_retries: 10
min_join_backoff: 1s

View File

@ -7,14 +7,37 @@ events {
http {
include /etc/nginx/mime.types;
map $http_upgrade $connection_upgrade {
default upgrade;
'' close;
}
server {
listen 80;
server_name {{ env "LOKI_DOMAIN" }};
location /loki/api/v1 {
auth_basic "loki";
auth_basic_user_file /etc/nginx/conf.d/loki.htpasswd;
proxy_pass http://{{ env "STACK_NAME" }}_loki:3100/loki/api/v1;
auth_basic "loki";
auth_basic_user_file /etc/nginx/conf.d/loki.htpasswd;
location / {
proxy_read_timeout 1800s;
proxy_connect_timeout 1600s;
proxy_pass http://{{ env "STACK_NAME" }}_loki:3100;
proxy_http_version 1.1;
proxy_set_header Upgrade $http_upgrade;
proxy_set_header Connection $connection_upgrade;
proxy_set_header Connection "Keep-Alive";
proxy_set_header Proxy-Connection "Keep-Alive";
proxy_redirect off;
}
location /ready {
proxy_pass http://{{ env "STACK_NAME" }}_loki:3100;
proxy_http_version 1.1;
proxy_set_header Connection "Keep-Alive";
proxy_set_header Proxy-Connection "Keep-Alive";
proxy_redirect off;
auth_basic "off";
}
}
}

View File

@ -13,3 +13,6 @@ scrape_configs:
static_configs:
- targets:
- localhost:9090
basic_auth:
username: 'admin'
password: '{{ secret "prometheus_admin_password" }}'

View File

@ -1,2 +1,2 @@
basic_auth_users:
admin: {{ secret "prometheus_admin_password" }}
admin: {{ secret "prometheus_admin_password_hashed" }}