I want to add an item for the next Iceberg Spark Sync as discussed with
@Russell Spitzer.

Making Spark Readers Async

   - Presenter: Varun Lakhyani | Related: Github Issue (Spark related)
   <https://github.com/apache/iceberg/issues/15287> , Github PR
   <https://github.com/apache/iceberg/pull/15341>, Dev ML Thread
   <https://lists.apache.org/thread/b5jrlyv61lmw867kksw05sot2tro5ybn>,
Design/POC
   Doc
   
<https://docs.google.com/document/d/17vBz5t-gSDdmB0S40MYRceyvmcBSzw9Gii-FcU97Lds/edit?usp=sharing>
   - Short discussion on introducing optional asynchronous file opening in
   Spark readers to improve performance for workloads with many small files.
   Includes POC and benchmark results for compaction of multiple files.

Reply via email to