ha-prometheus/roles/ha-monitoring/templates/configs/prometheus/prometheus.yml

36 lines
1.4 KiB
YAML

# my global config
global:
scrape_interval: 15s # Set the scrape interval to every 15 seconds. Default is every 1 minute.
evaluation_interval: 15s # Evaluate rules every 15 seconds. The default is every 1 minute.
# scrape_timeout is set to the global default (10s).
external_labels:
replica: {{ inventory_hostname }}
# Alertmanager configuration
alerting:
alert_relabel_configs:
- regex: replica
action: labeldrop
alertmanagers:
- static_configs:
- targets: {{ groups['servers'] | product([':9093']) | map('join') | list }}
# Load rules once and periodically evaluate them according to the global 'evaluation_interval'.
rule_files:
- "alert_rules.yml"
# A scrape configuration containing exactly one endpoint to scrape:
# Here it's Prometheus itself.
scrape_configs:
# The job name is added as a label `job=<job_name>` to any timeseries scraped from this config.
- job_name: "prometheus"
static_configs:
- targets: {{ groups['servers'] | product([':9090']) | map('join') | list }}
- job_name: "node-exporter"
static_configs:
- targets: {{ groups['servers'] | product([':9100']) | map('join') | list + groups['exporters'] | product([':9100']) | map('join') | list }}
- job_name: "cadvisor"
static_configs:
- targets: {{ groups['servers'] | product([':8080']) | map('join') | list + groups['exporters'] | product([':8080']) | map('join') | list }}