diff --git a/spark/src/main/scala/org/apache/comet/rules/EliminateRedundantTransitions.scala b/spark/src/main/scala/org/apache/comet/rules/EliminateRedundantTransitions.scala index b596ac45675..4d6609d34f7 100644 --- a/spark/src/main/scala/org/apache/comet/rules/EliminateRedundantTransitions.scala +++ b/spark/src/main/scala/org/apache/comet/rules/EliminateRedundantTransitions.scala @@ -25,7 +25,7 @@ import org.apache.spark.sql.SparkSession import org.apache.spark.sql.catalyst.rules.Rule import org.apache.spark.sql.catalyst.util.sideBySide import org.apache.spark.sql.comet.{CometCollectLimitExec, CometColumnarToRowExec, CometIcebergWriteExec, CometMapInBatchExec, CometNativeWriteExec, CometPlan, CometRangeExec, CometSparkToColumnarExec} -import org.apache.spark.sql.comet.execution.shuffle.{CometColumnarShuffle, CometShuffleExchangeExec} +import org.apache.spark.sql.comet.execution.shuffle.{CometColumnarShuffle, CometNativeShuffle, CometShuffleExchangeExec} import org.apache.spark.sql.comet.shims.{MapInBatchInfo, ShimCometMapInBatch} import org.apache.spark.sql.comet.util.Utils.containsVariantType import org.apache.spark.sql.execution.{ColumnarToRowExec, RowToColumnarExec, SparkPlan} @@ -176,6 +176,15 @@ case class EliminateRedundantTransitions(session: SparkSession) CometColumnarShuffle, _) => s.withNewChildren(Seq(child)) + + // Spark also adds `RowToColumnar` even when comet chose native shuffle. + // Native shuffle reads only Comet vectors, not Spark's vectors. + // Switch to row and drop the transition. + case s @ CometShuffleExchangeExec(_, RowToColumnarExec(child), _, _, CometNativeShuffle, _) + if CometShuffleExchangeExec.columnarShuffleSupports(s, child) => + val columnar = s.copy(child = child, shuffleType = CometColumnarShuffle) + columnar.copyTagsFrom(s) + columnar } eliminatedPlan match { diff --git a/spark/src/main/scala/org/apache/spark/sql/comet/execution/arrow/CometNativeArrowSource.scala b/spark/src/main/scala/org/apache/spark/sql/comet/execution/arrow/CometNativeArrowSource.scala index 997682f0984..96c4d7dab36 100644 --- a/spark/src/main/scala/org/apache/spark/sql/comet/execution/arrow/CometNativeArrowSource.scala +++ b/spark/src/main/scala/org/apache/spark/sql/comet/execution/arrow/CometNativeArrowSource.scala @@ -161,7 +161,12 @@ object CometArrowStream extends Logging { val first = buffered.head val expectedFields = expected.getFields val actualFields = (0 until first.numCols()).map { i => - val col = first.column(i).asInstanceOf[CometVector] + val col = first.column(i) match { + case c: CometVector => c + case other => + throw new IllegalStateException( + s"$name expects CometVector type, but column $i is a ${other.getClass.getName}") + } // The Arrow C Stream exports the producer's actual Arrow schema. If the // consumer-declared schema has fewer fields, fall back to the producer's diff --git a/spark/src/main/scala/org/apache/spark/sql/comet/execution/shuffle/CometShuffleExchangeExec.scala b/spark/src/main/scala/org/apache/spark/sql/comet/execution/shuffle/CometShuffleExchangeExec.scala index 8946d4a665c..baa41bffcaf 100644 --- a/spark/src/main/scala/org/apache/spark/sql/comet/execution/shuffle/CometShuffleExchangeExec.scala +++ b/spark/src/main/scala/org/apache/spark/sql/comet/execution/shuffle/CometShuffleExchangeExec.scala @@ -575,6 +575,15 @@ object CometShuffleExchangeExec nativeShuffleFailureReasons(s).isEmpty && !hashesDifferentlyFromSpark(s) + /** + * Whether the JVM columnar shuffle can take `s` with `rowChild`, a row-based plan, as its + * child. Pure: does not tag the node + */ + def columnarShuffleSupports(s: CometShuffleExchangeExec, rowChild: SparkPlan): Boolean = + !isCometCelebornShuffleManagerEnabled(s.conf) && + columnarShuffleFailureReasons( + ShuffleExchangeExec(s.outputPartitioning, rowChild, s.shuffleOrigin)).isEmpty + /** * Whether the shuffle hashes into more than one partition a key that native shuffle, reading * converted rows, may put in a different partition from Spark's partitioner. Native shuffle diff --git a/spark/src/test/scala/org/apache/comet/rules/EliminateRedundantTransitionsSuite.scala b/spark/src/test/scala/org/apache/comet/rules/EliminateRedundantTransitionsSuite.scala index b6625d4fd02..1d35971f5ca 100644 --- a/spark/src/test/scala/org/apache/comet/rules/EliminateRedundantTransitionsSuite.scala +++ b/spark/src/test/scala/org/apache/comet/rules/EliminateRedundantTransitionsSuite.scala @@ -19,9 +19,13 @@ package org.apache.comet.rules +import org.apache.spark.SparkException import org.apache.spark.sql.CometTestBase +import org.apache.spark.sql.catalyst.plans.physical.HashPartitioning import org.apache.spark.sql.comet.{CometColumnarToRowExec, CometPlan} -import org.apache.spark.sql.execution.{ColumnarToRowExec, SparkPlan, UnionExec} +import org.apache.spark.sql.comet.execution.shuffle.{CometColumnarShuffle, CometNativeShuffle, CometShuffleExchangeExec} +import org.apache.spark.sql.execution.{ColumnarToRowExec, RowToColumnarExec, SparkPlan, UnionExec} +import org.apache.spark.sql.execution.exchange.ShuffleExchangeExec import org.apache.comet.CometConf @@ -64,4 +68,31 @@ class EliminateRedundantTransitionsSuite extends CometTestBase { s"Spark-only branch should be left untouched:\n${result.treeString}") } } + + // A native shuffle reads Arrow-backed Comet vectors. If its child turns row-based after Comet + // chose native shuffle, Spark add its own `RowToColumnar` under it, whose vectors are unable + // to be read. + test("native shuffle over Spark's RowToColumnar moves to the JVM columnar shuffle") { + val rowChild = sparkPlanFor("SELECT id, CAST(id AS STRING) AS s FROM range(10)") + assert(!rowChild.supportsColumnar) + val partitioning = HashPartitioning(rowChild.output.take(1), 4) + val shuffle = CometShuffleExchangeExec( + partitioning, + RowToColumnarExec(rowChild), + ShuffleExchangeExec(partitioning, rowChild), + shuffleType = CometNativeShuffle) + + val result = EliminateRedundantTransitions(spark).apply(shuffle) + + result match { + case CometShuffleExchangeExec(_, child, _, _, CometColumnarShuffle, _) => + assert(child == rowChild, s"RowToColumnar should be removed:\n${result.treeString}") + case _ => + fail(s"Expected the JVM columnar shuffle:\n${result.treeString}") + } + assert(result.executeColumnar().map(_.numRows()).sum() == 10) + + val e = intercept[SparkException](shuffle.executeColumnar().count()) + assert(e.getMessage.contains("expects CometVector type"), e.getMessage) + } }