Datadog’s Continuous Profiler for AWS Lambda functions gives you visibility into the exact method name, class name, and line number in your Lambda code that is causing CPU or I/O bottlenecks.

Usage

To enable profiling:

1. Ensure you have installed the associated tracing library in your Lambda function.
2. Set the DD_PROFILING_ENABLED environment variable to true.

Data is available after a minimum of 60 execution seconds of the Lambda function.

The profiler works by spawning a thread that periodically wakes up and takes a snapshot of the CPU and heap of running code. This includes the profiler itself. If you want the profiler to ignore itself, set DD_PROFILING_IGNORE_PROFILER to true.

Support

Depending on your runtime, this feature requires the following tracer and layer versions:

Further Reading

Additional helpful documentation, links, and articles:

Continuous ProfilerDOCUMENTATION Distributed Tracing for AWS LambdaDOCUMENTATION