Nvidia Jetson

Supported OS Linux

이 페이지는 아직 한국어로 제공되지 않으며 번역 작업 중입니다. 번역에 관한 질문이나 의견이 있으시면 언제든지 저희에게 연락해 주십시오.

Overview

This check monitors an Nvidia Jetson board. It reports the metrics collected from tegrastats.

Setup

Installation

The Nvidia Jetson check is included in the Datadog Agent package. No additional installation is needed on your server.

Configuration

  1. Create a jetson.d/conf.yaml file in the conf.d/ folder at the root of your Agent’s configuration directory to start collecting your Jetson performance data. See the sample jetson.d/conf.yaml.example for all available configuration options.

  2. Restart the Agent.

Validation

Run the Agent’s status subcommand and look for jetson under the Checks section.

Data Collected

Metrics

nvidia.jetson.cpu.freq
(gauge)
CPU frequency
Shown as megahertz
nvidia.jetson.cpu.inactive_count
(gauge)
Number of inactive cores
Shown as unit
nvidia.jetson.cpu.total_count
(gauge)
Total number of cores
Shown as unit
nvidia.jetson.cpu.usage
(gauge)
Load statistics of the CPU core relative to the current running frequency or 'off' in case a core is currently powered down
Shown as percent
nvidia.jetson.emc.freq
(gauge)
EMC frequency
Shown as megahertz
nvidia.jetson.emc.usage
(gauge)
Percent of EMC memory bandwidth being used relative to the current running frequency
Shown as percent
nvidia.jetson.gpu.freq
(gauge)
GR3D frequency
Shown as megahertz
nvidia.jetson.gpu.usage
(gauge)
Percent of the GR3D that is being used relative to the current running frequency
Shown as percent
nvidia.jetson.iram.lfb
(gauge)
Size of the largest free block
Shown as byte
nvidia.jetson.iram.total
(gauge)
Total amount of IRAM memory available
Shown as byte
nvidia.jetson.iram.used
(gauge)
Amount of IRAM memory in use
Shown as byte
nvidia.jetson.mem.lfb
(gauge)
Size of the largest free block
Shown as byte
nvidia.jetson.mem.n_lfb
(gauge)
The number of free blocks of the largest size
Shown as unit
nvidia.jetson.mem.total
(gauge)
Total amount of RAM available for applications
Shown as byte
nvidia.jetson.mem.used
(gauge)
Amount of RAM in use
Shown as byte
nvidia.jetson.power.average
(gauge)
Average power consumption
Shown as milliwatt
nvidia.jetson.power.instant
(gauge)
Current power consumption
Shown as milliwatt
nvidia.jetson.swap.cached
(gauge)
Amount of SWAP cached in megabytes
Shown as byte
nvidia.jetson.swap.total
(gauge)
Total amount of SWAP available for applications
Shown as byte
nvidia.jetson.swap.used
(gauge)
Amount of SWAP in use in megabytes
Shown as byte
nvidia.jetson.temp
(gauge)
Temperature
Shown as degree celsius

Some metrics are reported only if use_sudo is set to true:

  • nvidia.jetson.iram.used
  • nvidia.jetson.iram.total
  • nvidia.jetson.iram.lfb
  • nvidia.jetson.emc.freq
  • nvidia.jetson.gpu.freq
  • nvidia.jetson.cpu.freq

Service Checks

The Nvidia Jetson integration does not include any service checks.

Events

The Nvidia Jetson integration does not include any events.

Troubleshooting

Need help? Contact Datadog support.

PREVIEWING: may/unit-testing