CCCHH/ansible-infra
CCCHH/ansible-infra
2
2
Fork 2
Code Issues 7 Pull requests 4 Wiki Activity Actions

grafana: get alertmanager to be more chill
Some checks are pending
/ Ansible Lint (push) Waiting to run
Details

Browse source 
a bit of help to deal with alert fatigue
This commit is contained in:
chris 2026-01-25 21:41:20 +01:00
commit 11779ab21d
Signed by: c6ristian
SSH key fingerprint: SHA256:B3m+yzpaxGXSEcDBpPHfvza/DNC0wuX+CKMeGq8wgak
2 changed files with 8 additions and 19 deletions
Download patch file Download diff file Expand all files Collapse all files

23
resources/chaosknoten/grafana/docker_compose/alertmanager.yaml.j2
View file

@ -7,7 +7,7 @@ route:
group_by: [ "alertname", "site", "type", "hypervisor" ] group_by: [ "alertname", "site", "type", "hypervisor" ]
group_wait: 30s group_wait: 30s
group_interval: 5m group_interval: 5m
repeat_interval: 6h repeat_interval: 26h
routes: routes:
- receiver: "null" - receiver: "null"
matchers: matchers:
@ -16,49 +16,38 @@ route:
matchers: matchers:
- org = "ccchh" - org = "ccchh"
- severity = "critical", - severity = "critical",
repeat_interval: 18h repeat_interval: 26h
continue: true continue: true
- receiver: ntfy-ccchh - receiver: ntfy-ccchh
matchers: matchers:
- org = "ccchh" - org = "ccchh"
- severity =~ "info|warning", - severity =~ "info|warning",
repeat_interval: 36h repeat_interval: 52h
continue: true continue: true
- receiver: ntfy-fux-critical - receiver: ntfy-fux-critical
matchers: matchers:
- org = "fux" - org = "fux"
- severity = "critical", - severity = "critical",
repeat_interval: 18h repeat_interval: 26h
continue: true continue: true
- receiver: email-fux-critical - receiver: email-fux-critical
matchers: matchers:
- org = "fux" - org = "fux"
- severity = "critical", - severity = "critical",
repeat_interval: 36h repeat_interval: 52h
continue: true continue: true
- receiver: ntfy-fux - receiver: ntfy-fux
matchers: matchers:
- org = "fux" - org = "fux"
- severity =~ "info|warning", - severity =~ "info|warning",
repeat_interval: 36h repeat_interval: 52h
continue: true continue: true
- receiver: ccchh-infrastructure-alerts
matchers:
- org = "ccchh"
- severity =~ "info|warning|critical"
templates: templates:
- "/etc/alertmanager/templates/*.tmpl" - "/etc/alertmanager/templates/*.tmpl"
receivers: receivers:
- name: "null" - name: "null"
- name: "ccchh-infrastructure-alerts"
telegram_configs:
- send_resolved: true
bot_token: {{ secret__alertmanager_telegram_bot_token }}
chat_id: -1002434372415
parse_mode: HTML
message: {{ "'{{ template \"alert-message.telegram.ccchh\" . }}'" }}
- name: "ntfy-ccchh-critical" - name: "ntfy-ccchh-critical"
webhook_configs: webhook_configs:

4
resources/chaosknoten/grafana/docker_compose/compose.yaml.j2
View file

@ -19,7 +19,7 @@ services:
- prom_data:/prometheus - prom_data:/prometheus
alertmanager: alertmanager:
image: docker.io/prom/alertmanager:v0.30.0 image: docker.io/prom/alertmanager:v0.30.1
container_name: alertmanager container_name: alertmanager
command: command:
- '--config.file=/etc/alertmanager/alertmanager.yaml' - '--config.file=/etc/alertmanager/alertmanager.yaml'
@ -59,7 +59,7 @@ services:
- /dev/null:/etc/prometheus/pve.yml - /dev/null:/etc/prometheus/pve.yml
loki: loki:
image: docker.io/grafana/loki:3.6.3 image: docker.io/grafana/loki:3.6.4
container_name: loki container_name: loki
ports: ports:
- 13100:3100 - 13100:3100