marin-ma commented on code in PR #5536:
URL: https://github.com/apache/incubator-gluten/pull/5536#discussion_r1580321600
##########
cpp/velox/shuffle/VeloxShuffleWriter.cc:
##########
@@ -340,25 +340,42 @@ arrow::Status
VeloxShuffleWriter::split(std::shared_ptr<ColumnarBatch> cb, int64
START_TIMING(cpuWallTimingList_[CpuWallTimingFlattenRV]);
rv = veloxColumnBatch->getFlattenedRowVector();
END_TIMING();
- if (partitioner_->hasPid()) {
- auto pidArr = getFirstColumn(*rv);
- START_TIMING(cpuWallTimingList_[CpuWallTimingCompute]);
- RETURN_NOT_OK(partitioner_->compute(pidArr, rv->size(), row2Partition_,
partition2RowCount_));
- END_TIMING();
- auto strippedRv = getStrippedRowVector(*rv);
- RETURN_NOT_OK(initFromRowVector(*strippedRv));
- RETURN_NOT_OK(doSplit(*strippedRv, memLimit));
+ if (isExtremelyLargeBatch(rv)) {
+ auto numRows = rv->size();
+ int32_t offset = 0;
+ do {
Review Comment:
Is this logic covered by existing unit test? If not, could you add a new one?
--
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]
