Profile Performance Node

Collect CPU, GPU, Memory utilization and FPS statistics to profile machine performance

Overview

This node collects CPU, GPU, Memory utilization and FPS statistics to profile machine performance, and adds them to metadata, where they can then be exported using Webhooks, Elasticsearch or saved with captured Clips and Snapshots.

Note that this is machine-level performance, so numbers are a cumulative of the number of pipelines and other processes you have running on your machine.

Inputs & Outputs

  • Inputs : 1, Media Format : Raw Video
  • Outputs : 1, Media Format: Raw Video
  • Output Metadata : Machine Performance Statistics

Properties

Property

Value

interval

Collect statistics at this interval (in frames)

Ex: 20

Metadata

Metadata Property

Description

nodes.<node_id>

Describes the stats and machine information collected by this node.
Format : as defined in the example below. Note that all memory values are in GB, and all frequency values are in MHz.

<node_id> for Profile Performance Nodes is of the form profileX (ex. profile1)

Example

"nodes": {
    "profile1": {
        "type": "profile",
        "stats": {
                        "present": true,
            "fps": 21,
            "process": {
                "running_pipelines_count": 1
             },
             "system": {
                 "is_jetson": true,
                 "gpu_count": 1,
                 "cpu_count": 4,
                 "machine_name": "Intel(R) Xeon(R) CPU @ 2.30GHz, 4 CPU, 16 GB, Tesla T4",
                 "cpu_freq": 2300,
                 "mem_total": 16,
                 "lumeo_version": "0.2.36",
                 "board": {
                        "gpus": [{
                            "type": "Tesla T4",
                        "mem_total": 8                      
                    }]                   
                 },
                 "driver": "495.29.05"
             },
             "cpu": {
                    "mem_available": 16,
                "mem_used": 10,
                "mem_percent_used": 62.5,
                "cpu_percent_used": 22
             },
             "gpu": [{
                    "type": "Telsa T4",
                "mem_total": 8,
                "mem_available": 4,
                "mem_percent_used": 50, 
                "gpu_percent_used": 22               
             }]
        }
    }
}

Did this page help you?