---
# Workload scenario selection (either 'homogeneous' or 'heterogeneous')
workload_scenario: homogeneous

# Workload configurations
homogeneous_workload:
  namespace: homogeneous-workload
  container:
    image: quay.io/kako1/stress:22
    resources:
      cpu: "250m"
      memory_request: "256Mi"
      memory_limit: "512Mi"
    args: ["--cpu", "1", "--timeout", "3600", "--vm", "1", "--vm-bytes", "128M", "--io", "2"]
  replicas: 40

heterogeneous_workload:
  namespace: heterogeneous-workload
  cpu_intensive:
    - size: large
      replicas: 20
      cpu: '4000m'
      memory_request: '512Mi'
      memory_limit: '1Gi'
      args: ['--cpu', '4', '--timeout', '3600', '--vm', '2', '--vm-bytes', '256M', '--vm-hang', '1']
    - size: medium
      replicas: 30
      cpu: '2000m'
      memory_request: '256Mi'
      memory_limit: '512Mi'
      args: ['--cpu', '2', '--timeout', '3600', '--vm', '1', '--vm-bytes', '128M', '--io', '2']
    - size: small
      replicas: 40
      cpu: '1000m'
      memory_request: '128Mi'
      memory_limit: '256Mi'
      args: ['--cpu', '1', '--timeout', '3600', '--vm', '1', '--vm-bytes', '64M', '--vm-stride', '128', '--hdd', '1', '--hdd-bytes', '128M']

# Prometheus metrics configuration
prometheus_queries:
  - query: 'count(kube_node_info)'
    metricName: 'NodeCount'
  - query: '(1 - (node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes)) * 100'
    metricName: 'NodeMemoryPercantage'
  - query: '100 - (avg(irate(node_cpu_seconds_total{mode="idle"}[1m])) by (instance) * 100)'
    metricName: 'CPUPercentageAllCores'
  - query: '(1 - (node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes)) * 100'
    metricName: 'NodeLatency'
  - query: 'histogram_quantile(0.99, sum(rate(apiserver_request_duration_seconds_bucket{apiserver="kube-apiserver", verb!~"WATCH", subresource!="log"}[2m])) by (verb,resource,subresource,instance,le)) > 0'
    metricName: 'API99thLatency'
  - query: 'histogram_quantile(0.99, sum(rate(kubelet_runtime_operations_duration_seconds_bucket{operation_type="create_container"}[5m])) by (instance, le)) > 0'
    metricName: 'ContainerStartupLatency'
  - query: 'count(kube_pod_status_phase{phase="Pending"})'
    metricName: 'PendingPods'
  - query: 'count(kube_pod_status_phase{phase="Pending"})'
    metricName: 'PendingPods'
  - query: 'count(kube_pod_status_phase)'
    metricName: 'TotalPods'
  - query: 'sum(rate(node_cpu_seconds_total{mode!="idle"}[1m]))'
    metricName: 'TotalCPUUtilization'
  - query: 'sum(node_memory_MemTotal_bytes - node_memory_MemAvailable_bytes) / 1024 / 1024'
    metricName: 'TotalMemoryUtilization'

# Metrics collection configuration
metrics_collection:
  # Port-forward service configuration
  port_forward_wait_timeout: 120  # increased timeout for stability
  
  # Prometheus health check configuration
  health_check_retries: 30
  health_check_delay: 20  # increased delay between retries
  
  # Metrics query configuration
  query_retries: 30
  query_delay: 20  # increased delay between retries
  query_step: "60s"  # increased step to reduce load