[GitHub] [spark] Dooyoung-Hwang commented on a change in pull request #22347: [SPARK-25353][SQL] executeTake in SparkPlan is modified to avoid unnecessary decoding.

[GitBox <gi...@apache.org>]

Dooyoung-Hwang commented on a change in pull request #22347: [SPARK-25353][SQL] executeTake in SparkPlan is modified to avoid unnecessary decoding.
URL: https://github.com/apache/spark/pull/22347#discussion_r299314691
 
 

 ##########
 File path: sql/core/src/main/scala/org/apache/spark/sql/execution/SparkPlan.scala
 ##########
 @@ -423,31 +424,37 @@ abstract class SparkPlan extends QueryPlan[SparkPlan] with Logging with Serializ
         // Otherwise, interpolate the number of partitions we need to try, but overestimate
         // it by 50%. We also cap the estimation in the end.
         val limitScaleUpFactor = Math.max(sqlContext.conf.limitScaleUpFactor, 2)
-        if (buf.isEmpty) {
+        if (scannedRowCount == 0) {
           numPartsToTry = partsScanned * limitScaleUpFactor
         } else {
-          val left = n - buf.size
+          val left = n - scannedRowCount
           // As left > 0, numPartsToTry is always >= 1
-          numPartsToTry = Math.ceil(1.5 * left * partsScanned / buf.size).toInt
+          numPartsToTry = Math.ceil(1.5 * left * partsScanned / scannedRowCount).toInt
           numPartsToTry = Math.min(numPartsToTry, partsScanned * limitScaleUpFactor)
         }
       }
 
       val p = partsScanned.until(math.min(partsScanned + numPartsToTry, totalParts).toInt)
       val sc = sqlContext.sparkContext
-      val res = sc.runJob(childRDD,
-        (it: Iterator[Array[Byte]]) => if (it.hasNext) it.next() else Array.empty[Byte], p)
-
-      buf ++= res.flatMap(decodeUnsafeRows)
-
+      val res = sc.runJob(childRDD, (it: Iterator[(Long, Array[Byte])]) =>
+        if (it.hasNext) it.next() else (0L, Array.empty[Byte]), p)
+
+      var i = 0
+      while (scannedRowCount < n && i < res.length) {
+        val rows = decodeUnsafeRows(res(i)._2)
 
 Review comment:
   Thank you for review. Looks much better!

----------------------------------------------------------------
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.
 
For queries about this service, please contact Infrastructure at:
users@infra.apache.org


With regards,
Apache Git Services

---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org