b65b5433dc
### What changes were proposed in this pull request? Worker netty not release <img width="1729" alt="截屏2024-04-07 17 26 40" src="https://github.com/apache/celeborn/assets/46485123/5774f735-570b-448e-ab94-4c78661717f5"> Many push failed <img width="767" alt="截屏2024-04-07 17 27 46" src="https://github.com/apache/celeborn/assets/46485123/41866bd0-d634-4dbf-8518-b474c8d1faad"> 1. For spark shuffle client, enable it release push data body when rpc failure 2. For flink client, since it use wrapped bytbuf, we need release push data body when rpc failure and release origin body when rpc completed. 3. For worker replicate, we should enable it release push data body when rpc failure. ### Why are the changes needed? Avoid worker netty memory leak ### Does this PR introduce _any_ user-facing change? ### How was this patch tested? Closes #2449 from AngersZhuuuu/CELEBORN-1376. Authored-by: Angerszhuuuu <angers.zhu@gmail.com> Signed-off-by: mingji <fengmingxiao.fmx@alibaba-inc.com> |
||
|---|---|---|
| .. | ||
| benchmarks | ||
| src | ||
| pom.xml | ||