NATS and DuckDB Integration

Input and output integration overview

The NATS Consumer Input Plugin enables real-time data consumption from NATS messaging subjects, integrating seamlessly into the Telegraf data pipeline for monitoring and metrics gathering.

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

NATS

The NATS Consumer Plugin allows Telegraf to read metrics from specified NATS subjects and create metrics based on supported input data formats. Utilizing a Queue Group allows multiple instances of Telegraf to read from a NATS cluster in parallel, enhancing throughput and reliability. This plugin also supports various authentication methods, including username/password, NATS credentials files, and nkey seed files, ensuring secure communication with the NATS servers. It is particularly useful in environments where data persistence and message reliability are critical, thanks to features such as JetStream that facilitate the consumption of historical messages. Additionally, the ability to configure various operational parameters makes this plugin suitable for high-throughput scenarios while maintaining performance integrity.

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

NATS

[[inputs.nats_consumer]]
  ## urls of NATS servers
  servers = ["nats://localhost:4222"]

  ## subject(s) to consume
  ## If you use jetstream you need to set the subjects
  ## in jetstream_subjects
  subjects = ["telegraf"]

  ## jetstream subjects
  ## jetstream is a streaming technology inside of nats.
  ## With jetstream the nats-server persists messages and
  ## a consumer can consume historical messages. This is
  ## useful when telegraf needs to restart it don't miss a
  ## message. You need to configure the nats-server.
  ## https://docs.nats.io/nats-concepts/jetstream.
  jetstream_subjects = ["js_telegraf"]

  ## name a queue group
  queue_group = "telegraf_consumers"

  ## Optional authentication with username and password credentials
  # username = ""
  # password = ""

  ## Optional authentication with NATS credentials file (NATS 2.0)
  # credentials = "/etc/telegraf/nats.creds"

  ## Optional authentication with nkey seed file (NATS 2.0)
  # nkey_seed = "/etc/telegraf/seed.txt"

  ## Use Transport Layer Security
  # secure = false

  ## Optional TLS Config
  # tls_ca = "/etc/telegraf/ca.pem"
  # tls_cert = "/etc/telegraf/cert.pem"
  # tls_key = "/etc/telegraf/key.pem"
  ## Use TLS but skip chain & host verification
  # insecure_skip_verify = false

  ## Sets the limits for pending msgs and bytes for each subscription
  ## These shouldn't need to be adjusted except in very high throughput scenarios
  # pending_message_limit = 65536
  # pending_bytes_limit = 67108864

  ## Max undelivered messages
  ## This plugin uses tracking metrics, which ensure messages are read to
  ## outputs before acknowledging them to the original broker to ensure data
  ## is not lost. This option sets the maximum messages to read from the
  ## broker that have not been written by an output.
  ##
  ## This value needs to be picked with awareness of the agent's
  ## metric_batch_size value as well. Setting max undelivered messages too high
  ## can result in a constant stream of data batches to the output. While
  ## setting it too low may never flush the broker's messages.
  # max_undelivered_messages = 1000

  ## Data format to consume.
  ## Each data format has its own unique set of configuration options, read
  ## more about them here:
  ## https://github.com/influxdata/telegraf/blob/master/docs/DATA_FORMATS_INPUT.md
  data_format = "influx"

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

NATS

1. Real-Time Analytics Dashboard: Utilize the NATS plugin to gather metrics from various NATS subjects in real time and feed them into a centralized analytics dashboard. This setup allows for immediate visibility into live application performance, enabling teams to react swiftly to operational issues or performance degradation.

2. Distributed System Monitoring: Deploy multiple instances of Telegraf configured with the NATS plugin across a distributed architecture. This approach allows teams to aggregate metrics from various microservices efficiently, providing a holistic view of system health and performance while ensuring no messages are dropped during transmission.

3. Historical Message Recovery: Leverage the capabilities of NATS JetStream along with this plugin to recover and process historical messages after Telegraf has been restarted. This feature is particularly beneficial for applications that require high reliability, ensuring that no critical metrics are lost even in case of service disruptions.

4. Dynamic Load Balancing: Implement a dynamic load balancing scenario where Telegraf instances consume messages from a NATS cluster based on load. Adjust the queue group settings to control the number of active consumers, allowing for better resource utilization and performance scaling as demand fluctuations occur.

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.