stubz151 opened a new pull request, #14352: URL: https://github.com/apache/iceberg/pull/14352
### What am I doing Implementing vectored reading capabilities for S3FileIO, enabling efficient batch reading of multiple file ranges with automatic coalescing to minimize S3 requests. ### How am I doing it Using the Iceberg task manager and a executor thread pool to send requests to s3 concurrently. Range coalescing works by using a hashmap to link ranges that, it then sends one request and uses one stream to populate the buffers for the linked ranges. ### Testing: • Added some integration tests, will try add a few more, or will try read some more data. • Ran a benchmark and was happy with the result, will see what I can share later. -- 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] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
