This plugin allows storing Apache Spark shuffle data on S3 compatible object storage (e.g. S3A, COS). It uses the Java Hadoop-Filesystem abstraction for interoperability for COS, S3A and even local ...
This project implements a remote shuffle service for batch data processing of Flink. By adopting the storage and compute separation architecture, it brings several important benefits: The scale ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback