dkranchii opened a new pull request, #18170: URL: https://github.com/apache/iceberg/pull/18170
## What changes are proposed? Improve `PuffinReader.readAll` by coalescing nearby blob ranges into fewer reads. - Merge ranges separated by at most 1 MiB. - Limit each coalesced region to 16 MiB. - Preserve lazy reading, blob ordering, and decompression behavior. - Add tests for range boundaries, oversized blobs, and buffer retention. - Add a JMH benchmark comparing coalesced and individual reads. ## Testing - IDE lint checks pass. - `git diff --check` passes. - Gradle tests and benchmark were not run locally because the Gradle wrapper download was blocked by the network environment. Suggested commands: `./gradlew :iceberg-core:test --tests org.apache.iceberg.puffin.TestPuffinReader` `./gradlew :iceberg-core:jmh -PjmhIncludeRegex=PuffinReaderBenchmark` --- **AI Disclosure** - Tool: Cursor -- 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]
