GPU Performance Monitoring

Get started

Collect and send GPU performance metrics directly from your application to an OpenTelemetry endpoint.

Install the OpenTelemetry GPU Collector as a Docker container to collect and send GPU performance metrics to an OpenTelemetry endpoint.

Using the SDK

Deploy Shield360

Git clone Shield360 repository

git clone git@github.com:ThinkfleetAI/Shield360.git

Start Docker Compose

From the root directory of the Shield360 distribution, Run the below command:

docker compose up -d

Install Shield360

Open your command line or terminal and run:

pip install shield360

Initialize Shield360 in your Application

Zero-code instrumentation
Manual instrumentation

Via CLI arguments
Via Environment Variables

# Start GPU monitoring instantly
shield360-instrument --collect-system-metrics python your_app.py

# With custom settings
shield360-instrument \
  --otlp-endpoint http://127.0.0.1:4318 \
  --service-name my-gpu-app \
  --environment production \
  --collect-system-metrics \
  python your_app.py

Set environment variables:

export OTEL_EXPORTER_OTLP_ENDPOINT="http://127.0.0.1:4318"
export SHIELD360_COLLECT_SYSTEM_METRICS=true
export OTEL_SERVICE_NAME=my-gpu-app

# Run your application
shield360-instrument python your_app.py

You can set up Shield360 in your application using either function arguments directly in your code or by using environment variables.

Parameters
Environment Variables

Add the following two lines to your application code:

import shield360

shield360.init(
  otlp_endpoint="http:127.0.0.1:4318",
  collect_system_metrics=True  # This enables GPU monitoring
)

Replace:

YOUR_OTEL_ENDPOINT with the URL of your OpenTelemetry backend, such as http://127.0.0.1:4318 if you are using Shield360 and a local OTel Collector.

Note: collect_system_metrics=True replaces the deprecated collect_gpu_stats=True

Configure your OTLP endpoint using environment variables:

export OTEL_EXPORTER_OTLP_ENDPOINT=""http://127.0.0.1:4318"
export SHIELD360_COLLECT_SYSTEM_METRICS=true

Add the following two lines to your application code:

import shield360

shield360.init(collect_system_metrics=True)

Replace:

YOUR_OTEL_ENDPOINT with the URL of your OpenTelemetry backend, such as http://127.0.0.1:4318 if you are using Shield360 and a local OTel Collector.

To send metrics to other Observability tools, refer to the supported destinations.

For more advanced configurations and application use cases, visit the SDK configuration reference.

Using the Collector

Deploy Shield360

Git clone Shield360 repository

git clone git@github.com:ThinkfleetAI/Shield360.git

Start Docker Compose

From the root directory of the Shield360 distribution, Run the below command:

docker compose up -d

Pull `otel-gpu-collector` Docker Image

You can quickly start using the OTel GPU Collector by pulling the Docker image:

docker pull ghcr.io/thinkfleetai/otel-gpu-collector:latest

Run `otel-gpu-collector` Docker container

You can quickly start using the OTel GPU Collector by pulling the Docker image: Here’s a quick example showing how to run the container with the required environment variables:

docker run --gpus all --pid=host \
    -e OTEL_SERVICE_NAME='chatbot' \
    -e OTEL_RESOURCE_ATTRIBUTES='deployment.environment=staging' \
    -e OTEL_EXPORTER_OTLP_ENDPOINT="http://127.0.0.1:4318" \
    ghcr.io/thinkfleetai/otel-gpu-collector:latest

--pid=host is required for per-process GPU attribution (cmdline, PID, zombie state).

For more advanced configurations of the collector, visit the GPU Collector documentation.

Note: If you’ve deployed Shield360 using Docker Compose (docker-compose.yml in the Shield360 distribution), make sure to use the host’s IP address or add OTel GPU Collector to the Docker Compose (docker-compose.yml in the Shield360 distribution):

Docker Compose: Add the following config under `services`

otel-gpu-collector:
  image: ghcr.io/thinkfleetai/otel-gpu-collector:latest
  pid: host
  environment:
    OTEL_SERVICE_NAME: 'chatbot'
    OTEL_RESOURCE_ATTRIBUTES: 'deployment.environment=staging'
    OTEL_EXPORTER_OTLP_ENDPOINT: "http://otel-collector:4318"
  device_requests:
  - driver: nvidia
    count: all
    capabilities: [gpu]
  depends_on:
  - otel-collector
  restart: always

Host IP: Use the Host IP to connect to OTel Collector

OTEL_EXPORTER_OTLP_ENDPOINT="http://192.168.10.15:4318"

Configuration

Configure the Shield360 SDK according to you requirements.

Integrations

60+ AI integrations with automatic instrumentation and performance tracking

Destinations

Send elemetry to Datadog, Grafana, New Relic, and other observability stacks