hvanhovell commented on code in PR #38613:
URL: https://github.com/apache/spark/pull/38613#discussion_r1020126889
##########
connector/connect/src/main/scala/org/apache/spark/sql/connect/service/SparkConnectStreamHandler.scala:
##########
@@ -184,9 +158,30 @@ class SparkConnectStreamHandler(responseObserver:
StreamObserver[Response]) exte
responseObserver.onNext(response.build())
numSent += 1
}
+ }
+
+ // Store collection results for worst case of 1 to N-1 partitions
+ val results = new Array[Array[Batch]](numPartitions - 1)
+ var lastIndex = -1 // index of last partition written
- currentPartitionId += 1
+ // Handler to eagerly write partitions in order
+ val resultHandler = (partitionId: Int, partition: Array[Batch]) => {
+ // If result is from next partition in order
+ if (partitionId - 1 == lastIndex) {
+ writeBatches(partition)
+ lastIndex += 1
+ // Write stored partitions that come next in order
+ while (lastIndex < results.length && results(lastIndex) != null) {
+ writeBatches(results(lastIndex))
+ results(lastIndex) = null
+ lastIndex += 1
+ }
+ } else {
+ // Store partitions received out of order
+ results(partitionId - 1) = partition
+ }
}
+ spark.sparkContext.runJob(batches, (iter: Iterator[Batch]) =>
iter.toArray, resultHandler)
Review Comment:
Why use a thread pool if you have thread sitting around?
--
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
