2 Commits

7 changed files with 71 additions and 40 deletions

View File

@ -36,7 +36,7 @@ Where gathering.org is the node you want to gather metrics from.
SECRET_USERSFILE_VERSION=v1
```
- Generate userslist with httpasswd hashed password
`abra app secret insert traefik.gathering.org userslist v1 'admin:<hashed-secret>'`
`abra app secret insert traefik.gathering.org usersfile v1 'admin:<hashed-secret>'`
make sure there is no whitespace in between `admin:<hashed-secret>`, it seems to break stuff...
- `abra app deploy -f traefik`
1. `abra app new monitoring-ng`

View File

@ -48,6 +48,7 @@ services:
deploy:
labels:
- "traefik.enable=true"
- "traefik.docker.network=proxy"
- "traefik.http.services.${STACK_NAME}-grafana.loadbalancer.server.port=3000"
- "traefik.http.routers.${STACK_NAME}-grafana.rule=Host(`${GRAFANA_DOMAIN:-$DOMAIN}`)"
- "traefik.http.routers.${STACK_NAME}-grafana.entrypoints=web-secure"

View File

@ -27,6 +27,7 @@ services:
condition: on-failure
labels:
- "traefik.enable=true"
- "traefik.docker.network=proxy"
- "traefik.http.services.${STACK_NAME}-loki.loadbalancer.server.port=3100"
- "traefik.http.routers.${STACK_NAME}-loki.rule=Host(`loki.${DOMAIN}`)"
- "traefik.http.routers.${STACK_NAME}-loki.entrypoints=web-secure"
@ -48,4 +49,4 @@ volumes:
# secrets:
# loki_aws_secret_access_key:
# external: true
# name: ${STACK_NAME}_loki_aws_secret_access_key_${SECRET_LOKI_AWS_SECRET_ACCESS_KEY_VERSION}
# name: ${STACK_NAME}_loki_aws_secret_access_key_${SECRET_LOKI_AWS_SECRET_ACCESS_KEY_VERSION}

View File

@ -24,12 +24,12 @@ services:
condition: on-failure
labels:
- "traefik.enable=true"
- "traefik.docker.network=proxy"
- "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=${LETS_ENCRYPT_ENV}"
- "traefik.http.routers.${STACK_NAME}-prometheus.middlewares=basicauth@file"
configs:
prometheus_yml:

View File

@ -17,6 +17,7 @@ services:
condition: on-failure
labels:
- "traefik.enable=true"
- "traefik.docker.network=proxy"
- "traefik.http.services.${STACK_NAME}-pushgateway.loadbalancer.server.port=9191"
- "traefik.http.routers.${STACK_NAME}-pushgateway.rule=Host(`pushgateway.${DOMAIN}`)"
- "traefik.http.routers.${STACK_NAME}-pushgateway.entrypoints=web-secure"

View File

@ -32,6 +32,7 @@ services:
labels:
- "backupbot.backup=${ENABLE_BACKUPS:-true}"
- "traefik.enable=true"
- "traefik.docker.network=proxy"
- "traefik.http.services.${STACK_NAME}-node.loadbalancer.server.port=9100"
- "traefik.http.routers.${STACK_NAME}-node.rule=Host(`node.${DOMAIN}`)"
- "traefik.http.routers.${STACK_NAME}-node.entrypoints=web-secure"
@ -63,6 +64,7 @@ services:
condition: on-failure
labels:
- "traefik.enable=true"
- "traefik.docker.network=proxy"
- "traefik.http.services.${STACK_NAME}-cadvisor.loadbalancer.server.port=8080"
- "traefik.http.routers.${STACK_NAME}-cadvisor.rule=Host(`cadvisor.${DOMAIN}`)"
- "traefik.http.routers.${STACK_NAME}-cadvisor.entrypoints=web-secure"

View File

@ -68,50 +68,76 @@
"condition": "B",
"data": [
{
"refId": "A",
"relativeTimeRange": { "from": 600, "to": 0 },
"datasourceUid": "PBFA97CFB590B2093",
"model": {
"disableTextWrap": false,
"editorMode": "builder",
"expr": "rate(backup[24h])",
"fullMetaSearch": false,
"includeNullMetadata": true,
"instant": true,
"intervalMs": 1000,
"legendFormat": "__auto",
"maxDataPoints": 43200,
"range": false,
"refId": "A",
"useBackend": false
}
"relativeTimeRange": {
"from": 28800,
"to": 0
},
"datasourceUid": "PBFA97CFB590B2093",
"model": {
"disableTextWrap": false,
"editorMode": "code",
"expr": "rate(backup[25h]) == 0",
"fullMetaSearch": false,
"includeNullMetadata": true,
"instant": true,
"intervalMs": 1000,
"legendFormat": "__auto",
"maxDataPoints": 43200,
"range": false,
"refId": "A",
"useBackend": false
}
},
{
"refId": "B",
"relativeTimeRange": { "from": 600, "to": 0 },
"datasourceUid": "__expr__",
"model": {
"conditions": [
{
"evaluator": { "params": [0, 0], "type": "within_range" },
"operator": { "type": "and" },
"query": { "params": ["C"] },
"reducer": { "params": [], "type": "last" },
"type": "query"
}
],
"datasource": { "type": "__expr__", "uid": "__expr__" },
"expression": "A",
"intervalMs": 1000,
"maxDataPoints": 43200,
"refId": "B",
"type": "threshold"
}
"relativeTimeRange": {
"from": 28800,
"to": 0
},
"datasourceUid": "__expr__",
"model": {
"conditions": [
{
"evaluator": {
"params": [
-1,
0
],
"type": "gt"
},
"operator": {
"type": "and"
},
"query": {
"params": []
},
"reducer": {
"params": [],
"type": "avg"
},
"type": "query"
}
],
"datasource": {
"name": "Expression",
"type": "__expr__",
"uid": "__expr__"
},
"expression": "A",
"hide": false,
"intervalMs": 1000,
"maxDataPoints": 43200,
"refId": "B",
"type": "threshold"
}
}
],
"noDataState": "NoData",
"execErrState": "Error",
"for": "5m",
"annotations": {},
"labels": {},
"isPaused": false
},
{{ end }}
@ -188,9 +214,9 @@
],
"noDataState": "NoData",
"execErrState": "Error",
"for": "20m",
"for": "60m",
"annotations": {
"summary": "Backup did not finish within 20 minutes"
"summary": "Backup did not finish within 60 minutes"
},
"labels": {},
"isPaused": false