Nvidia Run:ai

{
  "id": "123e4567-e89b-12d3-a456-426614174000",
  "specversion": "1.0",
  "type": "workload",
  "source": "run_ai",
  "time": "2025-01-01T00:00:00Z",
  "subject": "my-customer-id",
  "data": {
    "name": "my-runai-workload",
    "namespace": "my-runai-benchmark-test",
    "phase": "Running",
    "project": "my-project-id",
    "department": "my-department-id",
    // Workload running for a minute
    "workload_minutes": 1.0,
    // 96 CPU cores for a minute (m5a.24xlarge)
    "cpu_limit_core_minutes": 96,
    "cpu_request_core_minutes": 96,
    "cpu_usage_core_minutes": 80,
    // 384 GB of CPU memory for a minute (m5a.24xlarge)
    "cpu_memory_limit_gigabyte_minutes": 384,
    "cpu_memory_request_gigabyte_minutes": 384,
    "cpu_memory_usage_gigabyte_minutes": 178,
    // 1 GPU for a minute
    "gpu_allocation_minutes": 1,
    "gpu_usage_minutes": 1,
    // 40 GB of GPU memory for a minute
    "gpu_memory_request_gigabyte_minutes": 40,
    "gpu_memory_usage_gigabyte_minutes": 27
  }
}

input:
  run_ai:
    url: '${RUNAI_URL:}'
    app_id: '${RUNAI_APP_ID:}'
    app_secret: '${RUNAI_APP_SECRET:}'
    schedule: '*/30 * * * * *'
    metrics_offset: '30s'
    resource_type: 'workload'
    metrics:
      - CPU_LIMIT_CORES
      - CPU_MEMORY_LIMIT_BYTES
      - CPU_MEMORY_REQUEST_BYTES
      - CPU_MEMORY_USAGE_BYTES
      - CPU_REQUEST_CORES
      - CPU_USAGE_CORES
      - GPU_ALLOCATION
      - GPU_MEMORY_REQUEST_BYTES
      - GPU_MEMORY_USAGE_BYTES
      - GPU_UTILIZATION
      - POD_COUNT
      - RUNNING_POD_COUNT
    http:
      timeout: 30s
      retry_count: 1
      retry_wait_time: 100ms
      retry_max_wait_time: 1s

pipeline:
  processors:
    - mapping: |
        let duration_seconds = (meta("scrape_interval").parse_duration() / 1000 / 1000 / 1000).round().int64()
        let gpu_allocation_minutes = this.allocatedResources.gpu.number(0) * $duration_seconds / 60
        let cpu_limit_core_minutes = this.metrics.values.CPU_LIMIT_CORES.number(0) * $duration_seconds / 60
        // Add metrics as needed...

        root = {
          "id": uuid_v4(),
          "specversion": "1.0",
          "type": meta("resource_type"),
          "source": "run_ai",
          "time": ,
          "subject": this.name,
          "data": {
            "tenant": this.tenantId,
            "project": this.projectId,
            "department": this.departmentId,
            "cluster": this.clusterId,
            "type": this.type,
            "gpuAllocationMinutes": gpu_allocation_minutes,
            "cpuLimitCoreMinutes": cpu_limit_core_minutes,
          }
        }

# Send processed events to OpenMeter
output:
  label: 'openmeter'
  drop_on:
    error: false
    error_patterns:
      - Bad Request
    output:
      http_client:
        url: '${OPENMETER_URL:https://openmeter.cloud}/api/v1/events'
        verb: POST
        headers:
          Authorization: 'Bearer ${OPENMETER_TOKEN:}'
          Content-Type: 'application/json'
        timeout: 30s
        retry_period: 15s
        retries: 3
        max_retry_backoff: 1m
        # Maximum number of concurrent requests
        max_in_flight: 64
        batch_as_multipart: false
        drop_on:
          - 400
        # Batch settings for efficient API usage
        batching:
          # Send up to 100 events in a single request
          count: 100
          # Or send after 1 second, whichever comes first
          period: 1s
          processors:
            # Track metrics on sent events
            - metric:
                type: counter
                name: openmeter_events_sent
                value: 1
            # Convert batch to JSON array format
            - archive:
                format: json_array
        dump_request_log_level: DEBUG