heartbeat/hbd/config_multi_threshold_example.yaml

# ==============================================================================
# Heartbeat Daemon Multi-Threshold Configuration Example
# ==============================================================================
# This file demonstrates the new multi-threshold configuration feature that allows
# different threshold settings for different hosts/clients.
#
# Features:
#   - Define multiple named threshold configurations
#   - Map specific hosts to specific threshold configurations
#   - Set a default configuration for unmapped hosts
#   - Backward compatible with single threshold configuration
# ==============================================================================

# Global threshold settings
threshold_renotify_interval: 3600  # Re-notify every hour for ongoing alerts (seconds)

# Optional: Set default threshold config (defaults to "default" if not specified)
default_threshold_config: "default"

# ----------------------------------------------------------------------------
# Multiple Named Threshold Configurations
# ----------------------------------------------------------------------------
# Define multiple threshold configurations with different sensitivity levels
threshold_configs:
  
  # Default configuration - moderate thresholds for most servers
  default:
    thresholds:
      cpu_monitor:
        cpu_percent:
          warning: 80.0
          critical: 90.0
          operator: ">"
        load_1min:
          warning: 4.0
          critical: 8.0
          operator: ">"
      
      memory_monitor:
        percent:
          warning: 85.0
          critical: 95.0
          operator: ">"
      
      disk_monitor:
        partitions:
          /:
            percent:
              warning: 85.0
              critical: 95.0
              operator: ">"
      
      rtt:
        # RTT thresholds per remote host
        router:
          warning: 50.0   # ms
          critical: 200.0
        server1:
          warning: 100.0
          critical: 500.0
  
  # High sensitivity configuration - lower thresholds for critical systems
  high_sensitivity:
    thresholds:
      cpu_monitor:
        cpu_percent:
          warning: 60.0      # Alert earlier
          critical: 75.0
          operator: ">"
          hysteresis: 0.15   # More hysteresis to reduce flapping
        load_1min:
          warning: 2.0
          critical: 4.0
          operator: ">"
      
      memory_monitor:
        percent:
          warning: 75.0      # Alert at lower memory usage
          critical: 85.0
          operator: ">"
          display: "(threshold: {op_symbol} {threshold_value}%, total: {total_gb} GB)"
      
      disk_monitor:
        partitions:
          /:
            percent:
              warning: 75.0
              critical: 85.0
              operator: ">"
          /var:
            percent:
              warning: 80.0
              critical: 90.0
              operator: ">"
      
      rtt:
        router:
          warning: 30.0
          critical: 100.0
        server1:
          warning: 50.0
          critical: 200.0
  
  # Low sensitivity configuration - higher thresholds for development/test systems
  low_sensitivity:
    thresholds:
      cpu_monitor:
        cpu_percent:
          warning: 90.0      # Only alert at very high usage
          critical: 95.0
          operator: ">"
      
      memory_monitor:
        percent:
          warning: 90.0
          critical: 98.0
          operator: ">"
      
      disk_monitor:
        partitions:
          /:
            percent:
              warning: 90.0
              critical: 95.0
              operator: ">"
      
      rtt:
        router:
          warning: 100.0
          critical: 500.0
  
  # Production database servers - specialized thresholds
  database:
    thresholds:
      cpu_monitor:
        cpu_percent:
          warning: 70.0
          critical: 85.0
          operator: ">"
      
      memory_monitor:
        percent:
          warning: 90.0      # Databases can use high memory
          critical: 97.0
          operator: ">"
          display: "(threshold: {op_symbol} {threshold_value}%, total: {total_gb} GB, available: {available_gb} GB)"
      
      disk_monitor:
        partitions:
          /:
            percent:
              warning: 80.0
              critical: 90.0
              operator: ">"
          /var/lib/mysql:    # Database data partition
            percent:
              warning: 75.0  # Alert earlier for DB partition
              critical: 85.0
              operator: ">"
      
      rtt:
        router:
          warning: 20.0     # Stricter latency requirements
          critical: 50.0

# ----------------------------------------------------------------------------
# Host to Threshold Configuration Mapping
# ----------------------------------------------------------------------------
# Map specific hosts to specific threshold configurations
# Hosts not listed here will use the default_threshold_config
host_threshold_mapping:
  # Critical production servers
  prod-web-01: high_sensitivity
  prod-web-02: high_sensitivity
  prod-api-01: high_sensitivity
  
  # Database servers
  prod-db-01: database
  prod-db-02: database
  prod-db-replica: database
  
  # Development and test systems
  dev-server-01: low_sensitivity
  dev-server-02: low_sensitivity
  test-server-01: low_sensitivity
  test-server-02: low_sensitivity
  
  # Everything else uses 'default' (no need to list explicitly)

# ----------------------------------------------------------------------------
# Backward Compatibility Example
# ----------------------------------------------------------------------------
# The old single threshold format is still supported:
# Just use 'thresholds:' directly without 'threshold_configs:'
#
# thresholds:
#   cpu_monitor:
#     cpu_percent:
#       warning: 80.0
#       critical: 90.0
#
# This will apply the same thresholds to all hosts.