Copilot commented on code in PR #12163:
URL: https://github.com/apache/gluten/pull/12163#discussion_r3541424344
##########
cpp/velox/substrait/SubstraitToVeloxPlan.cc:
##########
@@ -458,26 +458,8 @@ core::PlanNodePtr
SubstraitToVeloxPlanConverter::toVeloxPlan(const ::substrait::
} else if (
sJoin.has_advanced_extension() &&
SubstraitParser::configSetInOptimization(sJoin.advanced_extension(),
"isBHJ=")) {
- std::string hashTableId = sJoin.hashtableid();
-
- std::shared_ptr<core::OpaqueHashTable> opaqueSharedHashTable = nullptr;
- bool joinHasNullKeys = false;
-
- try {
- auto hashTableBuilder =
ObjectStore::retrieve<gluten::HashTableBuilder>(getJoin(hashTableId));
- joinHasNullKeys = hashTableBuilder->joinHasNullKeys();
- auto originalShared = hashTableBuilder->hashTable();
- opaqueSharedHashTable = std::shared_ptr<core::OpaqueHashTable>(
- originalShared,
reinterpret_cast<core::OpaqueHashTable*>(originalShared.get()));
-
- LOG(INFO) << "Successfully retrieved and aliased HashTable for reuse.
ID: " << hashTableId;
- } catch (const std::exception& e) {
- LOG(WARNING)
- << "Error retrieving HashTable from ObjectStore: " << e.what()
- << ". Falling back to building new table. To ensure correct results,
please verify that spark.gluten.velox.buildHashTableOncePerExecutor.enabled is
set to false.";
- opaqueSharedHashTable = nullptr;
- }
-
+ const auto& hashTableId = sJoin.hashtableid();
+ const auto joinNodeId = hashTableId.empty() ? nextPlanNodeId() :
hashTableId;
// Create HashJoinNode node
return std::make_shared<core::HashJoinNode>(
nextPlanNodeId(),
Review Comment:
`joinNodeId` is computed but never used, and `HashJoinNode` still gets a
fresh `nextPlanNodeId()` as its plan node id. This leaves an unused variable
(can fail builds with -Werror) and also defeats the intent of using a stable id
for BHJ hash table caching.
##########
gluten-substrait/src/main/scala/org/apache/gluten/execution/JoinExecTransformer.scala:
##########
@@ -397,7 +408,8 @@ abstract class BroadcastHashJoinExecTransformerBase(
override def joinBuildSide: BuildSide = buildSide
override def hashJoinType: JoinType = joinType
- lazy val buildHashTableId: String = buildPlan.id.toString
+ // Unique ID for builded hash table
Review Comment:
Typo in comment: "builded" should be "built".
--
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]
