celeborn/worker
Shuang da84baed4d [CELEBORN-2027] Allow CelebornShuffleReader to decompress data on demand
### What changes were proposed in this pull request?
At a new parameter, allow CelebornShuffleReader to decompress data on demand

### Why are the changes needed?
In the current scenario of Gluten Fallback, a stage can have both Native and Java shuffles simultaneously. In [CELEBORN-1625](https://issues.apache.org/jira/browse/CELEBORN-1625), we introduced a new parameter to conditionally skip compression. Alongside this, we should add a corresponding parameter to ensure that the Celeborn shuffle reader does not decompress data when compression is skipped at pushOrMergeData.

### Does this PR introduce _any_ user-facing change?
No

### How was this patch tested?
Pass GA

Closes #3317 from RexXiong/CELEBORN-2027.

Authored-by: Shuang <lvshuang.xjs@alibaba-inc.com>
Signed-off-by: SteNicholas <programgeek@163.com>
2025-06-09 15:10:46 +08:00
..
src [CELEBORN-2027] Allow CelebornShuffleReader to decompress data on demand 2025-06-09 15:10:46 +08:00
pom.xml [CELEBORN-1994] Introduce disruptor dependency to support asynchronous logging of log4j2 2025-05-13 19:45:51 +08:00