feat: make alerts configurable #19
16
.env.sample
16
.env.sample
@ -6,7 +6,8 @@ DOMAIN=monitoring-ng.example.com
|
||||
ENABLE_BACKUPS=true
|
||||
|
||||
## Enable this secret for Promtail / Prometheus
|
||||
# SECRET_BASIC_AUTH_VERSION=v1
|
||||
#COMPOSE_FILE="$COMPOSE_FILE:compose.basic-auth.yml"
|
||||
#SECRET_BASIC_AUTH_VERSION=v1
|
||||
#
|
||||
# Promtail (Gathering Logs)
|
||||
# COMPOSE_FILE="$COMPOSE_FILE:compose.promtail.yml"
|
||||
@ -79,9 +80,10 @@ ENABLE_BACKUPS=true
|
||||
#GF_MATRIX_ROOM_ID="<room-id>"
|
||||
#GF_MATRIX_HOMESERVER_URL="<homeserver-url>"
|
||||
|
||||
# ALerts
|
||||
#ALERT_BACKUP_FAILED_ENABLED=true
|
||||
|
|
||||
#ALERT_BACKUP_MISSING_ENABLED=true
|
||||
#ALERT_BACKUP_NOT_SUCCESSFULL_ENABLED=true
|
||||
#ALERT_NODE_DISK_SPACE_ENABLED=true
|
||||
#ALERT_NODE_MEMORY_USAGE_ENABLED=true
|
||||
## ALerts
|
||||
|
||||
# Node disk space alert will trigger when free disk space left is below the given number in percent
|
||||
|
dannygroenewegen
commented
Good enough for now. But 10% of a 20GB disk or a 2TB disk is a bit different. Can imagine we want a bit more fine-grained control depending on disk size and usage. Good enough for now. But 10% of a 20GB disk or a 2TB disk is a bit different. Can imagine we want a bit more fine-grained control depending on disk size and usage.
|
||||
#ALERT_NODE_DISK_SPACE_LEFT=10
|
||||
|
||||
# Node memory usage alert will trigger when memory usage is above the given number in percent
|
||||
#ALERT_NODE_MEMORY_USAGE=85
|
||||
|
||||
12
README.md
12
README.md
@ -156,13 +156,9 @@ GF_MATRIX_HOME_SERVER_URL=
|
||||
```
|
||||
4. Configure Alertmanager webhook and set the url to `http://matrix-alertmanager-receiver:12345/alerts/<room-id>`
|
||||
|
||||
## alerts
|
||||
|
||||
It is possible to enable the following alerts, by setting the corresponding env variable to `true`:
|
||||
- backupbot failed: `ALERT_BACKUP_FAILED_ENABLED`
|
||||
- backupbot missing: `ALERT_BACKUP_MISSING_ENABLED`
|
||||
- backupbot not successfull: `ALERT_BACKUP_NOT_SUCCESSFULL_ENABLED`
|
||||
- node disk space: `ALERT_NODE_DISK_SPACE_ENABLED`
|
||||
- node memory usage: `ALERT_NODE_MEMORY_USAGE_ENABLED`
|
||||
## Alerts
|
||||
|
||||
It is possible to enable the following alerts, by uncommenting the corresponding env variable:
|
||||
|
||||
- node disk space: `ALERT_NODE_DISK_SPACE_LEFT`
|
||||
- node memory usage: `ALERT_NODE_MEMORY_USAGE`
|
||||
|
ammaratef45
commented
nit: should probably remove the options from here since they are explained in the env file, otherwise we would have to remember that these need to be updates in 2 places nit: should probably remove the options from here since they are explained in the env file, otherwise we would have to remember that these need to be updates in 2 places
p4u1
commented
Ah yes, good point! Ah yes, good point!
|
||||
|
||||
6
abra.sh
6
abra.sh
@ -9,9 +9,9 @@ export GRAFANA_CUSTOM_INI_VERSION=v4
|
||||
export PROMTAIL_YML_VERSION=v3
|
||||
export LOKI_YML_VERSION=v2
|
||||
export PROMETHEUS_YML_VERSION=v2
|
||||
export MATRIX_ALERTMANAGER_CONFIG_VERSION=e
|
||||
export MATRIX_ALERTMANAGER_ENTRYPOINT_VERSION=a
|
||||
export GRAFANA_ALERTS_NODE_VERSION=v1c
|
||||
export MATRIX_ALERTMANAGER_CONFIG_VERSION=v1
|
||||
export MATRIX_ALERTMANAGER_ENTRYPOINT_VERSION=v1
|
||||
export GRAFANA_ALERTS_NODE_VERSION=v2
|
||||
|
||||
# creates a default prometheus scrape config for a given node
|
||||
add_node(){
|
||||
|
||||
@ -2,13 +2,13 @@ apiVersion: 1
|
||||
|
||||
# List of alert rule UIDs that should be deleted
|
||||
deleteRules:
|
||||
{{ if ne (env "ALERT_NODE_DISK_SPACE_ENABLED") "true" }}
|
||||
{{ if not (env "ALERT_NODE_DISK_SPACE_LEFT") }}
|
||||
- orgId: 1
|
||||
uid: bds8bhxu97pxca
|
||||
uid: coopcloud_node_disk_space_left
|
||||
{{ end }}
|
||||
{{ if ne (env "ALERT_NODE_MEMORY_USAGE_ENABLED") "true" }}
|
||||
{{ if not (env "ALERT_NODE_MEMORY_USAGE") }}
|
||||
- orgId: 1
|
||||
uid: ads8cswmly96oa
|
||||
uid: coopcloud_node_memory_usage
|
||||
{{ end }}
|
||||
|
||||
groups:
|
||||
@ -17,8 +17,8 @@ groups:
|
||||
folder: node
|
||||
interval: 5m
|
||||
rules:
|
||||
{{ if eq (env "ALERT_NODE_DISK_SPACE_ENABLED") "true" }}
|
||||
- uid: bds8bhxu97pxca
|
||||
{{ if (env "ALERT_NODE_DISK_SPACE_LEFT") }}
|
||||
- uid: coopcloud_node_disk_space_left
|
||||
title: Node Disk Space
|
||||
condition: C
|
||||
data:
|
||||
@ -45,7 +45,7 @@ groups:
|
||||
conditions:
|
||||
- evaluator:
|
||||
params:
|
||||
- 10
|
||||
- {{ env "ALERT_NODE_DISK_SPACE_LEFT" }}
|
||||
type: lt
|
||||
operator:
|
||||
type: and
|
||||
@ -70,13 +70,13 @@ groups:
|
||||
annotations:
|
||||
description: ""
|
||||
runbook_url: ""
|
||||
summary: Less than 10% disk space left on {{`{{ $labels.instance }}`}} ({{`{{ (index $values "A").Value }}`}}% left)
|
||||
summary: Less than {{ env "ALERT_NODE_DISK_SPACE_LEFT" }}% disk space left on {{`{{ $labels.instance }}`}} ({{`{{ (index $values "A").Value }}`}}% left)
|
||||
labels:
|
||||
"": ""
|
||||
isPaused: false
|
||||
{{ end }}
|
||||
{{ if eq (env "ALERT_NODE_MEMORY_USAGE_ENABLED") "true" }}
|
||||
- uid: ads8cswmly96oa
|
||||
{{ if (env "ALERT_NODE_MEMORY_USAGE") }}
|
||||
- uid: coopcloud_node_memory_usage
|
||||
title: Node Memory Usage
|
||||
condition: C
|
||||
data:
|
||||
@ -103,7 +103,7 @@ groups:
|
||||
conditions:
|
||||
- evaluator:
|
||||
params:
|
||||
- 85
|
||||
- {{ env "ALERT_NODE_MEMORY_USAGE" }}
|
||||
type: gt
|
||||
operator:
|
||||
type: and
|
||||
@ -126,6 +126,6 @@ groups:
|
||||
execErrState: Error
|
||||
for: 5m
|
||||
annotations:
|
||||
summary: Memory usage is above 85% on {{`{{ $labels.instance }}`}} ({{`{{ printf "%.2f" (index $values "A").Value }}`}}% usage)
|
||||
summary: Memory usage is above {{ env "ALERT_NODE_MEMORY_USAGE" }}% on {{`{{ $labels.instance }}`}} ({{`{{ printf "%.2f" (index $values "A").Value }}`}}% usage)
|
||||
isPaused: false
|
||||
{{ end }}
|
||||
|
||||
7
compose.basic-auth.yml
Normal file
7
compose.basic-auth.yml
Normal file
@ -0,0 +1,7 @@
|
||||
---
|
||||
version: "3.8"
|
||||
|
||||
secrets:
|
||||
basic_auth:
|
||||
external: true
|
||||
name: ${STACK_NAME}_basic_auth_${SECRET_BASIC_AUTH_VERSION}
|
||||
@ -32,8 +32,8 @@ services:
|
||||
- GF_SECURITY_ADMIN_PASSWORD__FILE=/run/secrets/grafana_admin_password
|
||||
- GF_SECURITY_ALLOW_EMBEDDING
|
||||
- GF_INSTALL_PLUGINS
|
||||
- ALERT_NODE_DISK_SPACE_ENABLED
|
||||
- ALERT_NODE_MEMORY_USAGE_ENABLED
|
||||
- ALERT_NODE_DISK_SPACE_LEFT
|
||||
- ALERT_NODE_MEMORY_USAGE
|
||||
deploy:
|
||||
labels:
|
||||
- "traefik.enable=true"
|
||||
|
||||
@ -23,8 +23,3 @@ configs:
|
||||
name: ${STACK_NAME}_promtail_yml_${PROMTAIL_YML_VERSION}
|
||||
file: promtail.yml.tmpl
|
||||
template_driver: golang
|
||||
|
||||
secrets:
|
||||
basic_auth:
|
||||
external: true
|
||||
name: ${STACK_NAME}_basic_auth_${SECRET_BASIC_AUTH_VERSION}
|
||||
|
||||
Reference in New Issue
Block a user
I've seen mentions that these backup alerts don't work, but is that the case for everyone? Or could someone still be relying on this?
And if these envs are removed, then grafana-alerts.json.tmpl can also be removed?