HuaHuaY commented on PR #48851: URL: https://github.com/apache/arrow/pull/48851#issuecomment-3748838883
In previous comments, because of the use of Arrow IPC, we found that the `Compress` and `Decompress` functions of `Codec` need to be thread-safe. There are two solutions: 1. Use `thread_local` + `static`. However, I found that using `thread_local` introduces synchronization overhead, making context reuse slower than the original code. 2. Selectively reuse the context by declaring a new class `ZstdCodecOptions` that inherits from `CodecOptions`, and using comments to indicate that it should only be enabled when `Codec` is not shared. I chose option 2. But after repeated testing, I found that in my private environment, reusing the context only resulted in a significant performance improvement when the compression level was greater than or equal to 6. There was no performance improvement, and even a performance decrease, when the compression level was less than 6 or during decompression. In the screenshot, a template parameter explicitly set to true indicates context reuse. <img width="2462" height="974" alt="image" src="https://github.com/user-attachments/assets/f2f84cf3-9490-4103-9e45-d336fd63d6f5"; /> Therefore, I've decided to close this PR. Those interested can still view the PR's commits. -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected]
