wForget commented on code in PR #9521:
URL: https://github.com/apache/incubator-gluten/pull/9521#discussion_r2077330977
##########
backends-velox/src/main/scala/org/apache/spark/sql/execution/BroadcastUtils.scala:
##########
@@ -172,19 +172,21 @@ object BroadcastUtils {
if (filtered.isEmpty) {
return ColumnarBatchSerializeResult.EMPTY
}
- val handleArray =
- filtered.map(b =>
ColumnarBatches.getNativeHandle(BackendsApiManager.getBackendName, b))
- val serializeResult =
- try {
- ColumnarBatchSerializerJniWrapper
- .create(
- Runtimes
+ var rowNums = 0
+ val values = filtered.map(
+ b => {
+ val handle =
ColumnarBatches.getNativeHandle(BackendsApiManager.getBackendName, b)
+ rowNums += b.numRows()
+ try {
+ ColumnarBatchSerializerJniWrapper
+ .create(Runtimes
.contextInstance(BackendsApiManager.getBackendName,
"BroadcastUtils#serializeStream"))
- .serialize(handleArray)
- } finally {
- filtered.foreach(ColumnarBatches.release)
- }
- serializeResult
+ .serialize(handle)
+ } finally {
+ ColumnarBatches.release(b)
Review Comment:
Yes, there are two buffers in VeloxColumnarBatchSerializer to save
serialized data. If we serialize many columnarbatches at once, it may reserve a
large offheap memory:
https://github.com/apache/incubator-gluten/blob/c3aacfcd2593cda65e54a18b024b68cad6d0ade1/cpp/velox/operators/serializer/VeloxColumnarBatchSerializer.cc#L64
https://github.com/apache/incubator-gluten/blob/c3aacfcd2593cda65e54a18b024b68cad6d0ade1/cpp/velox/operators/serializer/VeloxColumnarBatchSerializer.cc#L78
--
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]
