wip loki stuff
This commit is contained in:
parent
15cd881356
commit
cc8a0b2905
13
.env.sample
13
.env.sample
|
@ -6,22 +6,21 @@ DOMAIN=monitoring.example.com
|
|||
|
||||
# Gathering Metrics (Node Exporter, Cadvisor)
|
||||
COMPOSE_FILE="$COMPOSE_FILE:compose.metrics.yml"
|
||||
SECRET_BASIC_AUTH_ADMIN_PASSWORD_VERSION=v1
|
||||
|
||||
|
||||
# Gathering Logs (Promtail)
|
||||
# COMPOSE_FILE="$COMPOSE_FILE:compose.promtail.yml"
|
||||
# LOKI_PUSH_URL=https://l.monitor.autonomic.zone/loki/api/v1/push
|
||||
# LOKI_PUSH_URL=https://loki.monitoring.example.org/loki/api/v1/push
|
||||
|
||||
## Prometheus, Alertmanager
|
||||
#
|
||||
# COMPOSE_FILE="$COMPOSE_FILE:compose.prometheus.yml"
|
||||
# PROMETHEUS_YML_VERSION=v1
|
||||
# SECRET_PROMETHEUS_ADMIN_PASSWORD_VERSION=v1
|
||||
# ALERTMANAGER_CONFIG_VERSION=v1
|
||||
# ALERTMANAGER_SMTP_FROM=noreply@autonomic.zone
|
||||
# ALERTMANAGER_SMTP_HOST=mail.gandi.net:587
|
||||
# ALERTMANAGER_SMTP_TO=kaboom@autonomic.zone
|
||||
# SECRET_ALERTMANAGER_SMTP_PASSWORD_VERSION=v1
|
||||
|
||||
|
||||
## Loki
|
||||
# Loki Server
|
||||
#
|
||||
|
@ -35,13 +34,11 @@ COMPOSE_FILE="$COMPOSE_FILE:compose.metrics.yml"
|
|||
# LOKI_ACCESS_KEY_ID=bush-debrief-approval-robust-scraggly-molecule
|
||||
# LOKI_BUCKET_NAMES=loki
|
||||
# SECRET_LOKI_AWS_SECRET_ACCESS_KEY_VERSION=v1
|
||||
#
|
||||
|
||||
|
||||
# Grafana
|
||||
## Grafana
|
||||
#
|
||||
# COMPOSE_FILE="$COMPOSE_FILE:compose.grafana.yml"
|
||||
# GRAFANA_CUSTOM_INI_VERSION=v3
|
||||
# GF_SERVER_ROOT_URL=https://${DOMAIN}
|
||||
# SECRET_GRAFANA_ADMIN_PASSWORD_VERSION=v1
|
||||
#
|
||||
|
|
71
README.md
71
README.md
|
@ -15,10 +15,54 @@ A centralised grafana/prometheus/loki stack. This an alternative approach to [`c
|
|||
|
||||
<!-- endmetadata -->
|
||||
|
||||
## Setup
|
||||
## Setup a Metrics Gathering
|
||||
|
||||
Where gathering.org is the node you want to gather metrics from.
|
||||
|
||||
1. Configure DNS
|
||||
* monitoring.gathering.org
|
||||
* cadvisor.monitoring.gathering.org
|
||||
* node.monitoring.gathering.org
|
||||
1. Configure Traefik to use BasicAuth
|
||||
Generate userslist with httpasswd hashed password
|
||||
* `abra app config traefik.gathering.org`
|
||||
uncomment
|
||||
```
|
||||
# BASIC_AUTH
|
||||
COMPOSE_FILE="$COMPOSE_FILE:compose.basicauth.yml"
|
||||
BASIC_AUTH=1
|
||||
SECRET_USERSFILE_VERSION=v1
|
||||
```
|
||||
* Generate userslist with httpasswd hashed password
|
||||
`abra app secret insert traefik.gathering.org userslist v1 'admin:hashed-secret'`
|
||||
make sure there is no whitespace between admin:hashed-secret, it seems to break stuff...
|
||||
* `abra app deploy traefik` (might need to undeploy before)
|
||||
1. `abra app new monitoring-ng`
|
||||
1. `abra app config monitoring.gathering.org`
|
||||
for gathering only this is required:
|
||||
`COMPOSE_FILE="$COMPOSE_FILE:compose.metrics.yml"`
|
||||
1. `abra app deploy monitoring.gathering.org`
|
||||
1. check that endpoints are up and basic-auth works
|
||||
* cadvisor.monitoring.gathering.org
|
||||
* node.monitoring.gathering.org
|
||||
|
||||
## Setup Metrics Browser
|
||||
|
||||
1. Configure DNS
|
||||
* monitoring.example.org
|
||||
* loki.monitoring.example.org
|
||||
* loki.monitoring.example.org
|
||||
|
||||
|
||||
```
|
||||
cp scrape-config.example.yml gathering.org.yml
|
||||
# adjust domain
|
||||
# mkdir scrape_configs
|
||||
abra app cp monitoring.dev.local-it.cloud gathering.org.yml prometheus:/prometheus/scrape_configs/
|
||||
```
|
||||
|
||||
* check that all configured targets are up:
|
||||
https://prometheus.monitoring.example.org/targets
|
||||
|
||||
|
||||
###
|
||||
|
||||
|
@ -35,6 +79,29 @@ A centralised grafana/prometheus/loki stack. This an alternative approach to [`c
|
|||
| Cadvisor | traefik basic-auth | cadvisor.monitoring.example.org |
|
||||
| Node Exporter | traefik basic-auth | node.monitoring.example.org |
|
||||
|
||||
|
||||
|
||||
### TODO
|
||||
|
||||
* metrics.compose.yml -> compose.yml
|
||||
* [ ] Loki
|
||||
* [x]
|
||||
* [ ] s3 aws secret?
|
||||
* [ ] Promtail
|
||||
* [ ] Loki -> Grafana Datasource
|
||||
* prometheus retention!
|
||||
* traefik metrics
|
||||
* [uptime-kuma](https://github.com/louislam/uptime-kuma/wiki/Prometheus-Integration), [dashboard](https://grafana.com/grafana/dashboards/14847-uptime-kuma/)
|
||||
* authentik metrics?
|
||||
* cool alerts
|
||||
* note: alle gathering nodes will have the same httpasswd basic-auth secret ...
|
||||
-> this could be a use case to actually use docker swarm ...
|
||||
could use swarm_service_discovery then in prometheus
|
||||
-> multiple scrape_configs in prometheus
|
||||
service
|
||||
-> oauth / header? prometheus could do it, does promtail? does traefik?
|
||||
|
||||
|
||||
This stack requires 3 domains, one for grafana, prometheus, loki. This is due to the need for the gathering tools, such as node_exporter, to have a publicy accessible URL for making connections. We make use of the internal prometheus HTTP basic auth & wire up an Nginx proxy with HTTP basic auth for loki. Grafana uses Keycloak OpenId Connect sign in. The alertmanager setup remains internal and is only connected with grafana. It also assume that you are deploying the [`coop-cloud/gathering`](https://git.coopcloud.tech/knoflook/gathering/) recipe on the machines that you want to gather metrics & logs from. Each instance of the gathering recipe will report back and/or be scraped by your central install of monitoring-lite.
|
||||
|
||||
## Post-setup guide
|
||||
|
|
5
abra.sh
5
abra.sh
|
@ -4,5 +4,8 @@ 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
|
||||
export GRAFANA_CUSTOM_INI_VERSION=v1
|
||||
export PROMTAIL_YML_VERSION=v1
|
||||
export LOKI_YML_VERSION=v9
|
||||
export LOKI_YML_VERSION=v1
|
||||
export PROMETHEUS_YML_VERSION=v1
|
||||
export ALERTMANAGER_CONFIG_VERSION=v1
|
||||
|
|
|
@ -3,9 +3,10 @@ version: '3.8'
|
|||
services:
|
||||
loki:
|
||||
image: grafana/loki:2.0.0
|
||||
# entrypoint: 'tail -f /dev/null'
|
||||
command: -config.file=/etc/loki/local-config.yaml
|
||||
networks:
|
||||
- internal
|
||||
- proxy
|
||||
configs:
|
||||
- source: loki_yml
|
||||
target: /etc/loki/local-config.yaml
|
||||
|
@ -19,17 +20,19 @@ services:
|
|||
- LOKI_AWS_REGION
|
||||
- LOKI_BUCKET_NAMES
|
||||
- STACK_NAME
|
||||
- LOKI_STORAGE_FILESYSTEM
|
||||
- LOKI_STORAGE_S3
|
||||
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(`loki.${DOMAIN}`)"
|
||||
- "traefik.http.routers.${STACK_NAME}-prometheus.entrypoints=web-secure"
|
||||
- "traefik.http.routers.${STACK_NAME}-prometheus.tls=true"
|
||||
- "traefik.http.routers.${STACK_NAME}-prometheus.tls.certresolver=${LETS_ENCRYPT_ENV}"
|
||||
- "traefik.http.routers.${STACK_NAME}-prometheus.middlewares=basicauth@file"
|
||||
- "traefik.http.services.${STACK_NAME}_loki.loadbalancer.server.port=9090"
|
||||
- "traefik.http.routers.${STACK_NAME}-loki.rule=Host(`loki.${DOMAIN}`)"
|
||||
- "traefik.http.routers.${STACK_NAME}-loki.entrypoints=web-secure"
|
||||
- "traefik.http.routers.${STACK_NAME}-loki.tls=true"
|
||||
- "traefik.http.routers.${STACK_NAME}-loki.tls.certresolver=${LETS_ENCRYPT_ENV}"
|
||||
- "traefik.http.routers.${STACK_NAME}-loki.middlewares=basicauth@file"
|
||||
|
||||
|
||||
configs:
|
||||
|
|
|
@ -44,7 +44,7 @@ services:
|
|||
- "-docker_only"
|
||||
- "--enable_metrics=cpu,cpuLoad,disk,memory,network"
|
||||
# all possible metrics: advtcp,app,cpu,cpuLoad,cpu_topology,cpuset,disk,diskIO,hugetlb,memory,memory_numa,network,oom_event,percpu,perf_event,process,referenced_memory,resctrl,sched,tcp,udp.
|
||||
- "--housekeeping_interval=30s"
|
||||
- "--housekeeping_interval=60s"
|
||||
|
||||
volumes:
|
||||
- /var/lib/docker/:/var/lib/docker:ro
|
||||
|
|
|
@ -4,7 +4,7 @@ services:
|
|||
prometheus:
|
||||
image: prom/prometheus:v2.34.0
|
||||
secrets:
|
||||
- prometheus_admin_password
|
||||
- basic_auth_admin_password
|
||||
volumes:
|
||||
- prometheus-data:/prometheus:rw
|
||||
configs:
|
||||
|
@ -66,9 +66,6 @@ volumes:
|
|||
alertmanager-data:
|
||||
|
||||
secrets:
|
||||
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}
|
|
@ -2,7 +2,7 @@ version: "3.8"
|
|||
|
||||
services:
|
||||
promtail:
|
||||
image: grafana/promtail:2.0.0
|
||||
image: grafana/promtail:2.7.3
|
||||
volumes:
|
||||
- /var/log:/var/log:ro
|
||||
- /var/lib/docker/containers:/var/lib/docker/containers:ro
|
||||
|
@ -13,17 +13,12 @@ services:
|
|||
networks:
|
||||
- internal
|
||||
secrets:
|
||||
- loki_admin_password
|
||||
- basic_auth_admin_password
|
||||
environment:
|
||||
- LOKI_PUSH_URL
|
||||
|
||||
configs:
|
||||
promtail_yml:
|
||||
name: ${STACK_NAME}_promtail_yml_${PROMTAIL_YML_VERSION}
|
||||
file: promtail.yml.tmpl
|
||||
template_driver: golang
|
||||
|
||||
secrets:
|
||||
loki_admin_password:
|
||||
external: true
|
||||
name: ${STACK_NAME}_loki_admin_password_${SECRET_LOKI_ADMIN_PASSWORD_VERSION}
|
||||
|
||||
|
||||
|
|
|
@ -10,3 +10,8 @@ networks:
|
|||
proxy:
|
||||
external: true
|
||||
internal:
|
||||
|
||||
secrets:
|
||||
basic_auth_admin_password:
|
||||
external: true
|
||||
name: ${STACK_NAME}_basic_auth_admin_password_${SECRET_BASIC_AUTH_ADMIN_PASSWORD_VERSION}
|
||||
|
|
|
@ -8,3 +8,10 @@ datasources:
|
|||
url: http://prometheus:9090
|
||||
isDefault: true
|
||||
editable: false
|
||||
- name: Loki
|
||||
type: loki
|
||||
access: proxy
|
||||
orgId: 1
|
||||
url: http://loki:3100
|
||||
isDefault: false
|
||||
editable: false
|
|
@ -10,11 +10,11 @@ alerting:
|
|||
|
||||
scrape_configs:
|
||||
- job_name: "default"
|
||||
scrape_interval: 10s
|
||||
scrape_interval: 30s
|
||||
metrics_path: "/metrics"
|
||||
file_sd_configs:
|
||||
- files:
|
||||
- /prometheus/scrape_configs/*.yml
|
||||
basic_auth:
|
||||
username: admin
|
||||
password: {{ secret "prometheus_admin_password" }}
|
||||
password: {{ secret "basic_auth_admin_password" }}
|
|
@ -8,8 +8,8 @@ positions:
|
|||
clients:
|
||||
- url: {{ env "LOKI_PUSH_URL" }}
|
||||
basic_auth:
|
||||
username: loki
|
||||
password: {{ secret "loki_admin_password" }}
|
||||
username: admin
|
||||
password: {{ secret "basic_auth_admin_password" }}
|
||||
|
||||
scrape_configs:
|
||||
- job_name: system
|
||||
|
@ -25,5 +25,31 @@ scrape_configs:
|
|||
- targets:
|
||||
- localhost
|
||||
labels:
|
||||
job: containers
|
||||
job: containerlogs
|
||||
__path__: /var/lib/docker/containers/*/*log
|
||||
|
||||
pipeline_stages:
|
||||
- json:
|
||||
expressions:
|
||||
output: log
|
||||
stream: stream
|
||||
attrs:
|
||||
- json:
|
||||
expressions:
|
||||
tag:
|
||||
source: attrs
|
||||
- regex:
|
||||
expression: (?P<image_name>(?:[^|]*[^|])).(?P<container_name>(?:[^|]*[^|])).(?P<image_id>(?:[^|]*[^|])).(?P<container_id>(?:[^|]*[^|]))
|
||||
source: tag
|
||||
- timestamp:
|
||||
format: RFC3339Nano
|
||||
source: time
|
||||
- labels:
|
||||
tag:
|
||||
stream:
|
||||
image_name:
|
||||
container_name:
|
||||
image_id:
|
||||
container_id:
|
||||
- output:
|
||||
source: output
|
Loading…
Reference in New Issue