Скачать или смотреть Why Does My C Program Run 10 Times Slower on Windows Than Linux?

Discover the reasons behind significant performance differences between Windows and Linux for C programming, and learn how to optimize your code for better efficiency.
---
This video is based on the question https://stackoverflow.com/q/67809418/ asked by the user 'Piero' ( https://stackoverflow.com/u/14140509/ ) and on the answer https://stackoverflow.com/a/67810030/ provided by the user 'Willis Hershey' ( https://stackoverflow.com/u/13402733/ ) at 'Stack Overflow' website. Thanks to these great users and Stackexchange community for their contributions.

Visit these links for original content and any more details, such as alternate solutions, latest updates/developments on topic, comments, revision history etc. For example, the original title of the Question was: Same program is 10 times slower on windows

Also, Content (except music) licensed under CC BY-SA https://meta.stackexchange.com/help/l...
The original Question post is licensed under the 'CC BY-SA 4.0' ( https://creativecommons.org/licenses/... ) license, and the original Answer post is licensed under the 'CC BY-SA 4.0' ( https://creativecommons.org/licenses/... ) license.

If anything seems off to you, please feel free to write me at vlogize [AT] gmail [DOT] com.
---
Understanding the Performance Issue: Windows vs. Linux

When programming in C, especially for tasks involving file manipulation, it can be puzzling to see significant performance differences between operating systems. One user reported that their simple C program, which copies 10 million bytes from one file to another in reverse order, took over 20 seconds to run on Windows, yet only about 2.5 seconds on Linux. In this guide, we’ll explore potential reasons for this discrepancy and how it can be mitigated.

The Problem: A Simple Yet Slow File Copy Program

The program in question reads a byte from an input file, then writes it to an output file, repeating this process for a large dataset (10 million bytes). Here’s a simplified version of the code:

[[See Video to Reveal this Text or Code Snippet]]

The Performance Difference: Linux vs. Windows

The timing results from the original program showed an extensive delay on Windows, with the execution time extending to over 25 seconds compared to approximately 2.2 seconds on a Linux system. This raises an important question: What causes this vast difference in speed?

Analyzing the Causes

Here are some common factors that could influence the performance of your C program between these two operating systems:

1. Compiler Efficiency

Compiler Optimization: The C compiler on Linux might optimize the code more efficiently than the Windows version. This could involve reading more than one byte at a time rather than one at a time, which is less efficient.

Library Differences: The libraries that the Windows compiler uses for file operations (like fread() and fwrite()) may inherently be slower than their Linux counterparts.

2. File System Performance

File System Overhead: The file systems on Windows and Linux are significantly different. The overhead of file operations can vary, leading to slower performance on Windows. Specific proprietary optimizations may exist in Linux that are not present in Windows.

3. System Load and Environment

Background Processes: The performance on Windows can also be affected by other running background processes that may not be present on the Linux machine, leading to less CPU and IO contention.

Solution: Optimizing Your Code

After realizing this issue, the user sought a solution and discovered improved performance by switching to Cygwin rather than using MinGW as the compiler. This change reduced the execution time to about 4.3 seconds.

Recommended Steps

To address performance issues in your C programs, consider:

Experimenting With Compilers: Test different compilers (such as MinGW, Cygwin, or Microsoft's Visual Studio) and see which yields the best performance.

Batch Processing: Instead of reading and writing one byte at a time, experiment with reading and writing multiple bytes in a single operation, which reduces the number of I/O operations and can significantly speed up execution.

Profiling Your Code: Utilize profiling tools to measure where your program spends the most time and optimize those areas.

Conclusion: The Takeaway

The vast difference in execution times for a seemingly simple task highlights the importance of understanding how your code interacts with the underlying system. By considering compiler choices, file system interactions, and optimization techniques, you can enhance your C programming performance across different platforms.

Now you can run your programs more efficiently on both Windows and Linux. Happy coding!