[VL] Add shuffle writer type to ColumnarExchange display string (#6799)

apache · Aug 14, 2024 · db799a4 · db799a4
1 parent 1205707
commit db799a4
Show file tree

Hide file tree

Showing 256 changed files with 1,050 additions and 1,060 deletions.
diff --git a/...ickhouse/src/main/scala/org/apache/gluten/backendsapi/clickhouse/CHSparkPlanExecApi.scala b/...ickhouse/src/main/scala/org/apache/gluten/backendsapi/clickhouse/CHSparkPlanExecApi.scala
@@ -433,6 +433,10 @@ class CHSparkPlanExecApi extends SparkPlanExecApi {
   }
   // scalastyle:on argcount
 
+  /** Determine whether to use sort-based shuffle based on shuffle partitioning and output. */
+  override def useSortBasedShuffle(partitioning: Partitioning, output: Seq[Attribute]): Boolean =
+    false
+
   /**
    * Generate ColumnarShuffleWriter for ColumnarShuffleManager.
    *

diff --git a/...ends-velox/src/main/scala/org/apache/gluten/backendsapi/velox/VeloxSparkPlanExecApi.scala b/...ends-velox/src/main/scala/org/apache/gluten/backendsapi/velox/VeloxSparkPlanExecApi.scala
@@ -548,6 +548,17 @@ class VeloxSparkPlanExecApi extends SparkPlanExecApi {
   }
   // scalastyle:on argcount
 
+  /** Determine whether to use sort-based shuffle based on shuffle partitioning and output. */
+  override def useSortBasedShuffle(partitioning: Partitioning, output: Seq[Attribute]): Boolean = {
+    val conf = GlutenConfig.getConf
+    lazy val isCelebornSortBasedShuffle = conf.isUseCelebornShuffleManager &&
+      conf.celebornShuffleWriterType == GlutenConfig.GLUTEN_SORT_SHUFFLE_WRITER
+    partitioning != SinglePartition &&
+    (partitioning.numPartitions >= GlutenConfig.getConf.columnarShuffleSortPartitionsThreshold ||
+      output.size >= GlutenConfig.getConf.columnarShuffleSortColumnsThreshold) ||
+    isCelebornSortBasedShuffle
+  }
+
   /**
    * Generate ColumnarShuffleWriter for ColumnarShuffleManager.
    *

diff --git a/backends-velox/src/test/resources/tpch-approved-plan/v1-bhj-ras/spark32/1.txt b/backends-velox/src/test/resources/tpch-approved-plan/v1-bhj-ras/spark32/1.txt
diff --git a/backends-velox/src/test/resources/tpch-approved-plan/v1-bhj-ras/spark32/10.txt b/backends-velox/src/test/resources/tpch-approved-plan/v1-bhj-ras/spark32/10.txt
diff --git a/backends-velox/src/test/resources/tpch-approved-plan/v1-bhj-ras/spark32/11.txt b/backends-velox/src/test/resources/tpch-approved-plan/v1-bhj-ras/spark32/11.txt
diff --git a/backends-velox/src/test/resources/tpch-approved-plan/v1-bhj-ras/spark32/12.txt b/backends-velox/src/test/resources/tpch-approved-plan/v1-bhj-ras/spark32/12.txt
diff --git a/backends-velox/src/test/resources/tpch-approved-plan/v1-bhj-ras/spark32/13.txt b/backends-velox/src/test/resources/tpch-approved-plan/v1-bhj-ras/spark32/13.txt
diff --git a/backends-velox/src/test/resources/tpch-approved-plan/v1-bhj-ras/spark32/14.txt b/backends-velox/src/test/resources/tpch-approved-plan/v1-bhj-ras/spark32/14.txt
diff --git a/backends-velox/src/test/resources/tpch-approved-plan/v1-bhj-ras/spark32/15.txt b/backends-velox/src/test/resources/tpch-approved-plan/v1-bhj-ras/spark32/15.txt
diff --git a/backends-velox/src/test/resources/tpch-approved-plan/v1-bhj-ras/spark32/16.txt b/backends-velox/src/test/resources/tpch-approved-plan/v1-bhj-ras/spark32/16.txt
diff --git a/backends-velox/src/test/resources/tpch-approved-plan/v1-bhj-ras/spark32/17.txt b/backends-velox/src/test/resources/tpch-approved-plan/v1-bhj-ras/spark32/17.txt
diff --git a/backends-velox/src/test/resources/tpch-approved-plan/v1-bhj-ras/spark32/18.txt b/backends-velox/src/test/resources/tpch-approved-plan/v1-bhj-ras/spark32/18.txt
diff --git a/backends-velox/src/test/resources/tpch-approved-plan/v1-bhj-ras/spark32/19.txt b/backends-velox/src/test/resources/tpch-approved-plan/v1-bhj-ras/spark32/19.txt
diff --git a/backends-velox/src/test/resources/tpch-approved-plan/v1-bhj-ras/spark32/20.txt b/backends-velox/src/test/resources/tpch-approved-plan/v1-bhj-ras/spark32/20.txt
diff --git a/backends-velox/src/test/resources/tpch-approved-plan/v1-bhj-ras/spark32/21.txt b/backends-velox/src/test/resources/tpch-approved-plan/v1-bhj-ras/spark32/21.txt
diff --git a/backends-velox/src/test/resources/tpch-approved-plan/v1-bhj-ras/spark32/22.txt b/backends-velox/src/test/resources/tpch-approved-plan/v1-bhj-ras/spark32/22.txt
diff --git a/backends-velox/src/test/resources/tpch-approved-plan/v1-bhj-ras/spark32/3.txt b/backends-velox/src/test/resources/tpch-approved-plan/v1-bhj-ras/spark32/3.txt
diff --git a/backends-velox/src/test/resources/tpch-approved-plan/v1-bhj-ras/spark32/4.txt b/backends-velox/src/test/resources/tpch-approved-plan/v1-bhj-ras/spark32/4.txt
diff --git a/backends-velox/src/test/resources/tpch-approved-plan/v1-bhj-ras/spark32/5.txt b/backends-velox/src/test/resources/tpch-approved-plan/v1-bhj-ras/spark32/5.txt
diff --git a/backends-velox/src/test/resources/tpch-approved-plan/v1-bhj-ras/spark32/6.txt b/backends-velox/src/test/resources/tpch-approved-plan/v1-bhj-ras/spark32/6.txt
diff --git a/backends-velox/src/test/resources/tpch-approved-plan/v1-bhj-ras/spark32/7.txt b/backends-velox/src/test/resources/tpch-approved-plan/v1-bhj-ras/spark32/7.txt
diff --git a/backends-velox/src/test/resources/tpch-approved-plan/v1-bhj-ras/spark32/8.txt b/backends-velox/src/test/resources/tpch-approved-plan/v1-bhj-ras/spark32/8.txt
diff --git a/backends-velox/src/test/resources/tpch-approved-plan/v1-bhj-ras/spark32/9.txt b/backends-velox/src/test/resources/tpch-approved-plan/v1-bhj-ras/spark32/9.txt