zecookiez commented on code in PR #50572:
URL: https://github.com/apache/spark/pull/50572#discussion_r2052735734
##########
sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/StreamingSymmetricHashJoinExec.scala:
##########
@@ -307,19 +349,23 @@ case class StreamingSymmetricHashJoinExec(
assert(stateInfo.isDefined, "State info not defined")
val checkpointIds =
SymmetricHashJoinStateManager.getStateStoreCheckpointIds(
- partitionId, stateInfo.get)
+ partitionId, stateInfo.get, useVirtualColumnFamilies)
val inputSchema = left.output ++ right.output
val postJoinFilter =
Predicate.create(condition.bothSides.getOrElse(Literal(true)),
inputSchema).eval _
- val leftSideJoiner = new OneSideHashJoiner(
- LeftSide, left.output, leftKeys, leftInputIter,
- condition.leftSideOnly, postJoinFilter, stateWatermarkPredicates.left,
partitionId,
- checkpointIds.left.keyToNumValues, checkpointIds.left.valueToNumKeys,
skippedNullValueCount)
- val rightSideJoiner = new OneSideHashJoiner(
- RightSide, right.output, rightKeys, rightInputIter,
- condition.rightSideOnly, postJoinFilter, stateWatermarkPredicates.right,
partitionId,
- checkpointIds.right.keyToNumValues, checkpointIds.right.valueToNumKeys,
skippedNullValueCount)
+ // Create left and right side hash joiners and store in the joiner manager
Review Comment:
This is a refactor, it helped bundle the logic between implementations for
some of the OneSideHashJoiner-specific methods like merging metrics and getting
state store checkpoint info
--
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: reviews-unsubscr...@spark.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
