Some checks failed
System Monitoring / Health Checks (push) Has been cancelled
System Monitoring / Performance Monitoring (push) Has been cancelled
System Monitoring / Database Monitoring (push) Has been cancelled
System Monitoring / Cache Monitoring (push) Has been cancelled
System Monitoring / Log Monitoring (push) Has been cancelled
System Monitoring / Resource Monitoring (push) Has been cancelled
System Monitoring / Uptime Monitoring (push) Has been cancelled
System Monitoring / Backup Monitoring (push) Has been cancelled
System Monitoring / Security Monitoring (push) Has been cancelled
System Monitoring / Monitoring Dashboard (push) Has been cancelled
System Monitoring / Alerting (push) Has been cancelled
Security Scanning / Dependency Scanning (push) Has been cancelled
Security Scanning / Code Security Scanning (push) Has been cancelled
Security Scanning / Secrets Scanning (push) Has been cancelled
Security Scanning / Container Security Scanning (push) Has been cancelled
Security Scanning / Compliance Checking (push) Has been cancelled
Security Scanning / Security Dashboard (push) Has been cancelled
Security Scanning / Security Remediation (push) Has been cancelled
99 lines
2.5 KiB
YAML
99 lines
2.5 KiB
YAML
global:
|
|
scrape_interval: 15s
|
|
evaluation_interval: 15s
|
|
|
|
# Alertmanager configuration
|
|
alerting:
|
|
alertmanagers:
|
|
- static_configs:
|
|
- targets:
|
|
- alertmanager:9093
|
|
|
|
# Load rules once and periodically evaluate them according to the global 'evaluation_interval'.
|
|
rule_files:
|
|
- "alert_rules.yml"
|
|
- "recording_rules.yml"
|
|
|
|
# Scrape configurations
|
|
scrape_configs:
|
|
# Prometheus itself
|
|
- job_name: 'prometheus'
|
|
static_configs:
|
|
- targets: ['localhost:9090']
|
|
|
|
# Node Exporter for system metrics
|
|
- job_name: 'node'
|
|
static_configs:
|
|
- targets: ['node-exporter:9100']
|
|
scrape_interval: 5s
|
|
metrics_path: '/metrics'
|
|
|
|
# Docker metrics
|
|
- job_name: 'docker'
|
|
static_configs:
|
|
- targets: ['cadvisor:8080']
|
|
scrape_interval: 10s
|
|
|
|
# Application metrics
|
|
- job_name: 'backend'
|
|
static_configs:
|
|
- targets: ['backend:8000']
|
|
scrape_interval: 10s
|
|
metrics_path: '/metrics'
|
|
scrape_timeout: 10s
|
|
|
|
# Database metrics
|
|
- job_name: 'postgres'
|
|
static_configs:
|
|
- targets: ['postgres-exporter:9187']
|
|
scrape_interval: 15s
|
|
|
|
# Redis metrics
|
|
- job_name: 'redis'
|
|
static_configs:
|
|
- targets: ['redis-exporter:9121']
|
|
scrape_interval: 15s
|
|
|
|
# Nginx metrics
|
|
- job_name: 'nginx'
|
|
static_configs:
|
|
- targets: ['nginx-exporter:9113']
|
|
scrape_interval: 15s
|
|
|
|
# Celery metrics
|
|
- job_name: 'celery'
|
|
static_configs:
|
|
- targets: ['flower:5555']
|
|
scrape_interval: 30s
|
|
metrics_path: '/metrics'
|
|
|
|
# Blackbox exporter for external monitoring
|
|
- job_name: 'blackbox'
|
|
metrics_path: /probe
|
|
params:
|
|
module: [http_2xx]
|
|
static_configs:
|
|
- targets:
|
|
- https://api.malaysian-sme-platform.com/health
|
|
- https://app.malaysian-sme-platform.com
|
|
- https://staging.malaysian-sme-platform.com/health
|
|
relabel_configs:
|
|
- source_labels: [__address__]
|
|
target_label: __param_target
|
|
- source_labels: [__param_target]
|
|
target_label: instance
|
|
- target_label: __address__
|
|
replacement: blackbox-exporter:9115
|
|
|
|
# Kubernetes metrics (if deployed on K8s)
|
|
- job_name: 'kubernetes-apiservers'
|
|
kubernetes_sd_configs:
|
|
- role: endpoints
|
|
scheme: https
|
|
tls_config:
|
|
ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
|
|
bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
|
|
relabel_configs:
|
|
- source_labels: [__meta_kubernetes_namespace, __meta_kubernetes_service_name, __meta_kubernetes_endpoint_port_name]
|
|
action: keep
|
|
regex: default;kubernetes;https |