feat(monitoring): заменить Prometheus на vmalert
ansible-core-mon / deploy (push) Successful in 37s
ansible-core-net / deploy (push) Successful in 56s
ansible-core-secrets / deploy (push) Successful in 16s
ansible-ger-nod-02 / deploy (push) Successful in 1m22s
ansible-opnsense / deploy (push) Successful in 6s
ansible-rus-central / deploy (push) Successful in 39s

Алерты считаются по VictoriaMetrics и уходят в тот же Alertmanager, второй сбор метрик больше не нужен.

Co-authored-by: Cursor <cursoragent@cursor.com>
This commit is contained in:
karpenokandCursor committed 2026-11-12 17:54:25 +07:00
1 parent 28b8bcf708
commit 57aa12b9c5
10 files changed
+59 -79

No files matched your search

@@ -1,23 +1,6 @@
name: monitoring
services:
prometheus:
image: prom/prometheus:v3.2.1
container_name: monitoring-prometheus
restart: unless-stopped
command:
- "--config.file=/etc/prometheus/prometheus.yml"
- "--storage.tsdb.path=/prometheus"
- "--storage.tsdb.retention.time={{ prometheus_retention }}"
- "--web.enable-lifecycle"
volumes:
- ./prometheus:/etc/prometheus:ro
- ./prometheus_data:/prometheus
ports:
- "9090:9090"
depends_on:
- alertmanager
alertmanager:
image: prom/alertmanager:v0.28.1
container_name: monitoring-alertmanager
@@ -76,7 +59,7 @@ services:
ports:
- "3000:3000"
depends_on:
- prometheus
- vmsingle
vmsingle:
image: {{ victoriametrics_image }}
@@ -85,6 +68,7 @@ services:
restart: unless-stopped
command:
- --storageDataPath=/victoria-metrics-data
- --retentionPeriod={{ victoriametrics_retention }}
volumes:
- ./victoria-metrics-data:/victoria-metrics-data
ports:
@@ -138,4 +122,23 @@ services:
- vmsingle
- cadvisor
vmalert:
image: {{ vmalert_image }}
container_name: monitoring-vmalert
restart: unless-stopped
command:
- -datasource.url=http://vmsingle:8428
- -notifier.url=http://alertmanager:9093
- -rule=/etc/vmalert/alerts.yml
- -evaluationInterval=15s
- -configCheckInterval=30s
- -httpListenAddr=0.0.0.0:8880
volumes:
- ./vmalert:/etc/vmalert:ro
ports:
- "127.0.0.1:8880:8880"
depends_on:
- vmsingle
- alertmanager
@@ -5,8 +5,8 @@ datasources:
uid: prometheus
type: prometheus
access: proxy
url: http://prometheus:9090
isDefault: true
url: http://vmsingle:8428
isDefault: false
jsonData:
timeInterval: 15s
@@ -15,7 +15,7 @@ datasources:
type: prometheus
access: proxy
url: http://vmsingle:8428
isDefault: false
isDefault: true
jsonData:
timeInterval: 15s
@@ -1,27 +0,0 @@
global:
scrape_interval: 15s
evaluation_interval: 15s
rule_files:
- "/etc/prometheus/alerts.yml"
alerting:
alertmanagers:
- static_configs:
- targets:
- "alertmanager:9093"
scrape_configs:
- job_name: "prometheus"
static_configs:
- targets: ["localhost:9090"]
- job_name: "{{ monitoring_scrape_job_name }}"
static_configs:
{% for target in monitoring_scrape_targets %}
- targets:
- "{{ target.address }}:{{ target.port }}"
labels:
host: "{{ target.name }}"
env: "{{ target.env }}"
{% endfor %}
@@ -5,3 +5,10 @@
labels:
instance: "{{ inventory_hostname }}"
cluster: "{{ vmagent_cluster }}"
{% for target in monitoring_scrape_targets if target.name not in vmagent_central_scrape_skip %}
- targets: ["{{ target.address }}:{{ target.port }}"]
labels:
instance: "{{ target.name }}"
cluster: "{{ vmagent_cluster }}"
host: "{{ target.name }}"
{% endfor %}