Nvidia SMI and DuckDB Integration

Input and output integration overview

The Nvidia SMI Plugin enables the retrieval of detailed statistics about NVIDIA GPUs attached to the host system, providing essential insights for performance monitoring.

This plugin enables Telegraf to write structured metrics into DuckDB using SQLite-compatible SQL connections, supporting lightweight local analytics and offline metric analysis.

Integration details

Nvidia SMI

The Nvidia SMI Plugin is designed to gather metrics regarding the performance and status of NVIDIA GPUs on the host machine. By leveraging the capabilities of the nvidia-smi command-line tool, this plugin pulls crucial information such as GPU memory utilization, temperature, fan speed, and various performance metrics. This data is essential for monitoring GPU health and performance in real-time, particularly in environments where GPU performance directly impacts computing tasks, such as machine learning, 3D rendering, and high-performance computing. The plugin provides flexibility by allowing users to specify the path to the nvidia-smi binary and configure polling timeouts, accommodating both Linux and Windows systems where the nvidia-smi tool is commonly located. With its ability to collect detailed statistics on each GPU, this plugin becomes a vital resource for any infrastructure relying on NVIDIA hardware, facilitating proactive management and performance tuning.

DuckDB

Use the Telegraf SQL plugin to write metrics into a local DuckDB database. DuckDB is an in-process OLAP database designed for efficient analytical queries on columnar data. Although it does not provide a traditional client-server interface, DuckDB can be accessed via SQLite-compatible drivers in embedded mode. This allows Telegraf to store time series metrics in DuckDB using SQL, enabling powerful analytics workflows using familiar SQL syntax, Jupyter notebooks, or integration with data science tools like Python and R. DuckDB’s columnar storage and vectorized execution make it ideal for compact and high-performance metric archives.

Configuration

Nvidia SMI

[[inputs.nvidia_smi]]
  ## Optional: path to nvidia-smi binary, defaults "/usr/bin/nvidia-smi"
  ## We will first try to locate the nvidia-smi binary with the explicitly specified value (or default value),
  ## if it is not found, we will try to locate it on PATH(exec.LookPath), if it is still not found, an error will be returned
  # bin_path = "/usr/bin/nvidia-smi"

  ## Optional: timeout for GPU polling
  # timeout = "5s"

DuckDB

[[outputs.sql]]
  ## Use the SQLite driver to connect to DuckDB via Go's database/sql
  driver = "sqlite3"

  ## DSN should point to the DuckDB database file
  dsn = "file:/var/lib/telegraf/metrics.duckdb"

  ## SQL INSERT statement with placeholders for metrics
  table_template = "INSERT INTO metrics (timestamp, name, value, tags) VALUES (?, ?, ?, ?)"

  ## Optional: manage connection pooling
  # max_open_connections = 1
  # max_idle_connections = 1
  # conn_max_lifetime = "0s"

  ## DuckDB does not require TLS or authentication by default

Input and output integration examples

Nvidia SMI

1. Real-Time GPU Monitoring for ML Training: Continuously monitor the GPU utilization and memory usage during machine learning model training. This enables data scientists to ensure that their GPUs are not being overutilized or underutilized, optimizing resource allocation and reviewing performance bottlenecks in real-time.

2. Automated Alerts for Overheating GPUs: Implement a system using the Nvidia SMI plugin to track GPU temperatures and set alerts for instances where temperatures exceed safe thresholds. This proactive monitoring can prevent hardware damage and improve system reliability by alerting administrators to potential cooling issues before they result in failure.

3. Performance Baselines for GPU Resources: Establish baseline performance metrics for your GPU resources. By regularly collecting data and analyzing trends in GPU usage, organizations can identify anomalies and optimize their workloads accordingly, leading to enhanced operational efficiency.

4. Dockerized GPU Usage Insights: In a containerized environment, use the plugin to monitor GPU performance from within a Docker container. This allows developers to track GPU performance of their applications in production, facilitating troubleshooting and performance optimization within isolated environments.

DuckDB

1. Embedded Metric Warehousing for Notebooks: Write metrics to a local DuckDB file from Telegraf and analyze them in Jupyter notebooks using Python or R. This workflow supports reproducible analytics, ideal for data science experiments or offline troubleshooting.

2. Batch Time-Series Processing on the Edge: Use Telegraf with DuckDB on edge devices to log metrics locally in SQL format. The compact storage and fast analytical capabilities of DuckDB make it ideal for batch processing and low-bandwidth environments.

3. Exploratory Querying of Historical Metrics: Accumulate system metrics over time in DuckDB and perform exploratory data analysis (EDA) using SQL joins, window functions, and aggregates. This enables insights that go beyond what typical time-series dashboards provide.

4. Self-Contained Metric Snapshots: Use DuckDB as a portable metrics archive by shipping .duckdb files between systems. Telegraf can collect and store data in this format, and analysts can later load and query it using the DuckDB CLI or integrations with tools like Tableau and Apache Arrow.

Feedback

Thank you for being part of our community! If you have any general feedback or found any bugs on these pages, we welcome and encourage your input. Please submit your feedback in the InfluxDB community Slack.