Nvidia SMI and MySQL 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.

The Telegraf SQL plugin allows you to store metrics from Telegraf directly into a MySQL database, making it easier to analyze and visualize the collected metrics.

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.

MySQL

Telegraf’s SQL output plugin is designed to seamlessly write metric data to a SQL database by dynamically creating tables and columns based on the incoming metrics. When configured for MySQL, the plugin leverages the go-sql-driver/mysql, which requires enabling the ANSI_QUOTES SQL mode to ensure proper handling of quoted identifiers. This dynamic schema creation approach ensures that each metric is stored in its own table with a structure derived from its fields and tags, providing a detailed, timestamped record of system performance. The flexibility of the plugin allows it to handle high-throughput environments, making it ideal for scenarios that demand robust, granular metric logging and historical data analysis.

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"

MySQL

[[outputs.sql]]
  ## Database driver
  ## Valid options: mssql (Microsoft SQL Server), mysql (MySQL), pgx (Postgres),
  ##  sqlite (SQLite3), snowflake (snowflake.com) clickhouse (ClickHouse)
  driver = "mysql"

  ## Data source name
  ## The format of the data source name is different for each database driver.
  ## See the plugin readme for details.
  data_source_name = "username:password@tcp(host:port)/dbname"

  ## Timestamp column name
  timestamp_column = "timestamp"

  ## Table creation template
  ## Available template variables:
  ##  {TABLE} - table name as a quoted identifier
  ##  {TABLELITERAL} - table name as a quoted string literal
  ##  {COLUMNS} - column definitions (list of quoted identifiers and types)
  table_template = "CREATE TABLE {TABLE}({COLUMNS})"

  ## Table existence check template
  ## Available template variables:
  ##  {TABLE} - tablename as a quoted identifier
  table_exists_template = "SELECT 1 FROM {TABLE} LIMIT 1"

  ## Initialization SQL
  init_sql = "SET sql_mode='ANSI_QUOTES';"

  ## Maximum amount of time a connection may be idle. "0s" means connections are
  ## never closed due to idle time.
  connection_max_idle_time = "0s"

  ## Maximum amount of time a connection may be reused. "0s" means connections
  ## are never closed due to age.
  connection_max_lifetime = "0s"

  ## Maximum number of connections in the idle connection pool. 0 means unlimited.
  connection_max_idle = 2

  ## Maximum number of open connections to the database. 0 means unlimited.
  connection_max_open = 0

  ## NOTE: Due to the way TOML is parsed, tables must be at the END of the
  ## plugin definition, otherwise additional config options are read as part of the
  ## table

  ## Metric type to SQL type conversion
  ## The values on the left are the data types Telegraf has and the values on
  ## the right are the data types Telegraf will use when sending to a database.
  ##
  ## The database values used must be data types the destination database
  ## understands. It is up to the user to ensure that the selected data type is
  ## available in the database they are using. Refer to your database
  ## documentation for what data types are available and supported.
  #[outputs.sql.convert]
  #  integer              = "INT"
  #  real                 = "DOUBLE"
  #  text                 = "TEXT"
  #  timestamp            = "TIMESTAMP"
  #  defaultvalue         = "TEXT"
  #  unsigned             = "UNSIGNED"
  #  bool                 = "BOOL"
  #  ## This setting controls the behavior of the unsigned value. By default the
  #  ## setting will take the integer value and append the unsigned value to it. The other
  #  ## option is "literal", which will use the actual value the user provides to
  #  ## the unsigned option. This is useful for a database like ClickHouse where
  #  ## the unsigned value should use a value like "uint64".
  #  # conversion_style = "unsigned_suffix"

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.

MySQL

1. Real-Time Web Analytics Storage: Leverage the plugin to capture website performance metrics and store them in MySQL. This setup enables teams to monitor user interactions, analyze traffic patterns, and dynamically adjust site features based on real-time data insights.

2. IoT Device Monitoring: Utilize the plugin to collect metrics from a network of IoT sensors and log them into a MySQL database. This use case supports continuous monitoring of device health and performance, allowing for predictive maintenance and immediate response to anomalies.

3. Financial Transaction Logging: Record high-frequency financial transaction data with precise timestamps. This approach supports robust audit trails, real-time fraud detection, and comprehensive historical analysis for compliance and reporting purposes.

4. Application Performance Benchmarking: Integrate the plugin with application performance monitoring systems to log metrics into MySQL. This facilitates detailed benchmarking and trend analysis over time, enabling organizations to identify performance bottlenecks and optimize resource allocation effectively.

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.