Grafana Cloud


Profiling allows you to gather detailed information about the performance of your application. It helps you identify bottlenecks, optimize code, and improve the overall efficiency of your system.

In a cloud computing environment, profiling becomes crucial because your application might be distributed across multiple nodes and microservices. With Grafana Cloud Profiles, you can collect and analyze profiling data to gain insights into the behavior of your application.

Why use continuous profiling?

Because of the natural link between historical profiles of your application and the amount of resources used over time, profiling provides clear business and technical value to organizations.

From a business standpoint, continuous profiling delivers:

  • Cost cutting: Profiling identifies resource hotspots (like CPU and memory) and helps optimize them to reduce costs.
  • Revenue generation: In highly latency-sensitve industries like ridesharing, e-commerce, and fintech, minimizing end-user latency is critical for preventing customer churn and revenue loss. Profiling helps identify and remove code bottlenecks, ensuring a seamless user experience.
  • Incident resolution: Continuous profiling provides valuable insights into code performance and system behavior, enabling faster incident resolution by pinpointing the root cause with accuracy. Profiling can be the difference between a minor service disruption and a critical system-wide outage.

At the same time, from a technical perspective, continuous profiling provides:

  • Comprehensive code analysis: Continuous profiling offers a detailed understanding of code performance, resource utilization, and system interactions, allowing for thorough analysis and optimization.
  • Efficient optimization: By identifying bottlenecks through continuous profiling, critical functions can be optimized to improve overall system efficiency, resulting in better performance and resource utilization.
  • Effective capacity planning: Leveraging profiling data facilitates effective capacity planning and scaling efforts, ensuring that your application can handle increasing demands while maintaining optimal performance.

Continuous Profiling with Grafana Cloud Profiles

In March 2023, Grafana Labs acquired Pyroscope and began merging the Pyroscope project with the Phlare project. Grafana Cloud Profiles takes the best of each of these and runs the merged version of these two repositories behind the scenes. This improved version has been contributed back to the open source project as Pyroscope v1.0.

You can add profiling (with minimal overhead) to your application using either:

  • Grafana agent: A component that runs alongside your application and periodically pulls the profiles from it. This mode is suitable when you want to collect profiles from existing applications without modifying their source code.
  • Pyroscope language SDKs: Push profiles from your application directly to the Grafana Cloud server.

Analyzing profiling data with Grafana

Once you’ve chosen a method for sending profiles to the cloud, there are three main views to visualize and analyze Grafana Cloud Profiles data in Grafana:

  • Explore view
  • Dashboards view
  • Application plugin view

Explore view

The Explore view lets you create targeted queries to your profiling data or view your profiling data alongside matching logs, metrics, traces, K6 test results, or any other data that can be queried in Explore.

Explore view

To access this view, click Explore in the sidebar menu.

Dashboard view

The Dashboards view gives you a real-time understanding of what your application is doing and is customizable to help you gain a comprehensive understanding of your application’s performance and identify areas for optimization.

Dashboards view

To access this view, click Dashboards in the sidebar menu.

Application plugin view

The application plugin view offers profiling-specific functionality to enhance your analysis capabilities. This view presents a structured workflow, starting with a high-level overview of your application and its various labels.

From there, you can delve deeper, comparing profiles across different dimensions to uncover valuable insights. The app plugin view streamlines the profiling analysis process, making it easier to identify performance patterns, bottlenecks, and opportunities for optimization.

App plugin view

To access this view, navigate to Observability > Profiles in the sidebar menu.