Microsoft Performance-Tools, a series of open source tools for analyzing system performance

Microsoft unveiled recently andl launch of Performance-Tools, which are a series of open source tools to analyze performance and diagnose performance-related issues on Linux and Android platforms.

For work, a set of command line utilities is provided to analyze the performance of the entire system and to profile individual applications.

The LTTng, perf and Perfetto subsystems can be used as a source to track system activity and profiling applications.

LTTng allows to evaluate the work of the task scheduler, track process activity, analyze system calls, I / O and events on the FS, Perf is used to estimate the load on the CPU Perfetto can be used to analyze Android and browser performance based on the Chromium engine, and allows you to take into account the work of the task scheduler, estimate the load on the CPU and GPU, apply FTrace and trace typical events.

We wanted to announce and introduce you to a new set of powerful open source tools for analyzing system performance: Microsoft-Performance-Tools for Linux-Android. We just recently released version 1.2 adding Perfetto support, which we will cover in a separate blog post!

Microsoft-Performance-Tools for Linux-Android is a suite of trace processing tools that offers many of the great features, power, methodology, and ecosystem that have been used to drive Windows performance for the past 15 years with a set of Updated and evolving tools. 

The Toolkit it can also extract information from logs in dmesg, Cloud-Init and WaLinuxAgent formats (Azure Linux Guest Agent). Windows Performance Analyzer GUI integration, available for Windows only, supports visual trace analysis using graphs.

As mentioned in the post:

These types of tracing and tools provide amazing depth and insight into what the operating system is doing. and the application code; and can be used in a variety of diagnostic and performance scenarios. If the analysis scenario also involves Windows, then optionally the traces can be co-analyzed on the same timeline with the Windows performance traces.

In addition, it is mentioned that any program or GUI on any operating system can process events with plugins Microsoft-Performance-Tools SDK and Linux-Android. Also, if you are optionally on a Windows machine to analyze the traces, the toolkit has great integration with Windows Performance Analyzer so you can use a powerful GUI to analyze the traces.

It should be noted that the set of tools is based on open source .NET Core and the new microsoft-performance-toolkit-sdk. This means that the set of tools is cross-platform and the traces can be opened and analyzed on any operating system that supports .NET Core.

Separately, it is noted the appearance in Windows 11 Insider Preview Build 22518 of the ability to install the WSL environment (Windows Subsystem for Linux) as an application distributed through the Microsoft Store directory.

The new build is notable for the following:

  • This build will not be offered to ARM64 PCs due to an issue causing these devices to roll back when trying to upgrade to this build. We are working on a solution.
  • This build has several new features for Windows Insiders users to try, including Spotlight Collection backgrounds, an updated entry point for Weather Widgets, and voice access.
  • This build includes some general changes, including input switch updates.

At the same time, from the point of view of the technologies used, the WSL padding has remained the same, only the installation and update method has changed (WSL for Windows 11 is not integrated into the system image). It is claimed that distribution through the Microsoft Store will provide the opportunity to accelerate the delivery of updates and new WSL features, including allowing the installation of new versions of WSL without being tied to the Windows version.

Finally sIf you are interested in knowing more about it, You can check the details in the following links.

https://blogs.windows.com

DevBlogs


The content of the article adheres to our principles of editorial ethics. To report an error click here!.

A comment, leave yours

Leave a Comment

Your email address will not be published.

*

*

  1. Responsible for the data: Miguel Ángel Gatón
  2. Purpose of the data: Control SPAM, comment management.
  3. Legitimation: Your consent
  4. Communication of the data: The data will not be communicated to third parties except by legal obligation.
  5. Data storage: Database hosted by Occentus Networks (EU)
  6. Rights: At any time you can limit, recover and delete your information.

  1.   Stendall said

    With the amount of dependencies that it has, you will have few free resources to measure after installing that sample.