Alexander Renz
13c2608fd7
- Ansible: basic, with-exporter, with-notifications, enterprise playbooks - Kubernetes: CronJob, ConfigMap, ServiceMonitor, PVC manifests - Prometheus: alerting rules (RPO/RTO/failure) and scrape configs - Terraform: AWS S3 bucket with lifecycle policies - Scripts: GFS backup rotation and health check (Nagios compatible) All playbooks support: - Scheduled backups with systemd timers - GFS retention policies - Prometheus metrics exporter - SMTP/Slack/webhook notifications - Encrypted backups with cloud upload
49 lines
1.2 KiB
YAML
49 lines
1.2 KiB
YAML
# Prometheus scrape configuration for dbbackup
|
|
# Add to your prometheus.yml
|
|
|
|
scrape_configs:
|
|
- job_name: 'dbbackup'
|
|
# Scrape interval - backup metrics don't change frequently
|
|
scrape_interval: 60s
|
|
scrape_timeout: 10s
|
|
|
|
# Static targets - list your database servers
|
|
static_configs:
|
|
- targets:
|
|
- 'db-server-01:9399'
|
|
- 'db-server-02:9399'
|
|
- 'db-server-03:9399'
|
|
labels:
|
|
environment: 'production'
|
|
|
|
- targets:
|
|
- 'db-staging:9399'
|
|
labels:
|
|
environment: 'staging'
|
|
|
|
# Relabeling (optional)
|
|
relabel_configs:
|
|
# Extract hostname from target
|
|
- source_labels: [__address__]
|
|
target_label: instance
|
|
regex: '([^:]+):\d+'
|
|
replacement: '$1'
|
|
|
|
# Alternative: File-based service discovery
|
|
# Useful when targets are managed by Ansible/Terraform
|
|
|
|
- job_name: 'dbbackup-sd'
|
|
scrape_interval: 60s
|
|
file_sd_configs:
|
|
- files:
|
|
- '/etc/prometheus/targets/dbbackup/*.yml'
|
|
refresh_interval: 5m
|
|
|
|
# Example target file (/etc/prometheus/targets/dbbackup/production.yml):
|
|
# - targets:
|
|
# - db-server-01:9399
|
|
# - db-server-02:9399
|
|
# labels:
|
|
# environment: production
|
|
# datacenter: us-east-1
|