Is this page helpful?

Observability#

This guide explains how to monitor the health, queue depth, and throughput of the NIM for BGR. You can access operational metrics directly through the built-in status endpoint, or integrate with Prometheus and Grafana for continuous monitoring.

BGR-Specific Metrics#

NIM for BGR exposes operational metrics using the GET /v1/status endpoint. These metrics provide visibility into the batched geometry relaxation workload.

Aggregate Metrics#

Aggregate metrics track the combined geometry relaxation tasks, API requests, and overall queue depths across all active GPU workers:

Metric	Type	Description
`tasks_received`	counter	Total geometry relaxation tasks received
`tasks_completed`	counter	Total tasks completed
`queue_size_atoms`	gauge	Current number of atoms queued for processing
`queue_size_tasks`	gauge	Current number of tasks waiting in the queue
`requests_received`	counter	Total API requests received
`requests_completed`	counter	Total API requests completed
`requests_in_progress`	gauge	API requests currently being processed
`max_system_size`	gauge	Maximum atoms per batch for the current GPU configuration

Per-Worker Metrics#

Each GPU worker reports its own metrics from the following:

Metric	Type	Description
`device`	string	GPU device identifier (for example, `cuda:0`)
`tasks_received`	counter	Tasks received by this worker
`tasks_completed`	counter	Tasks completed by this worker
`queue_size_atoms`	gauge	Atoms queued on this worker
`queue_size_tasks`	gauge	Tasks queued on this worker
`batch_size`	gauge	Current batch size
`max_batch_size`	gauge	Maximum batch size for this GPU
`gpu_model`	string	GPU model name

Query Status#

Query the status endpoint to retrieve metrics:

curl -s http://localhost:8000/v1/status | python3 -m json.tool

For the full response schema and an example, refer to the GET /v1/status endpoint in the API Reference.

Prometheus#

NIM for BGR exposes Prometheus metrics for request statistics at http://localhost:8000/v1/metrics.

To install Prometheus and scrape metrics:

Download the latest Prometheus release for your system:

wget https://github.com/prometheus/prometheus/releases/download/v2.52.0/prometheus-2.52.0.linux-amd64.tar.gz
tar -xvzf prometheus-2.52.0.linux-amd64.tar.gz
cd prometheus-2.52.0.linux-amd64/

Edit the prometheus.yml file to scrape the NIM for BGR endpoint:

scrape_configs:
  - job_name: "nim-bgr"
    static_configs:
      - targets: ["localhost:8000"]

Start the Prometheus server:

./prometheus --config.file=./prometheus.yml

Verify the target in Prometheus by navigating to http://localhost:9090/targets?search=.

Grafana#

Visualize metrics with Grafana.

Install the latest Grafana release for your system:

wget https://dl.grafana.com/oss/release/grafana-11.0.0.linux-amd64.tar.gz
tar -zxvf grafana-11.0.0.linux-amd64.tar.gz
cd grafana-v11.0.0/

Start the Grafana server:
```
./bin/grafana-server
```
Access the dashboard by navigating to http://localhost:3000 and log in with the default credentials:
- Username: admin
- Password: admin
Configure the Prometheus data source:
- Click Data Source.
- Select Prometheus.
- Set the URL to localhost:9090.
- Save the configuration.