[incubator-kyuubi] branch master updated: [KYUUBI #2071] Using while-loop instead of map/range to improve performance in RowSet

[yao]

This is an automated email from the ASF dual-hosted git repository.

yao pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/incubator-kyuubi.git


The following commit(s) were added to refs/heads/master by this push:
     new e942df4  [KYUUBI #2071] Using while-loop instead of map/range to 
improve performance in RowSet
e942df4 is described below

commit e942df4006d364b4769f5b2c95d033273ea9548a
Author: Min Zhao <zhaomin1...@163.com>
AuthorDate: Sat Mar 12 16:26:43 2022 +0800

    [KYUUBI #2071] Using while-loop instead of map/range to improve performance 
in RowSet
    
    ### _Why are the changes needed?_
    
    Using while-loop instead of map/range to improve performance in RowSet
    ### _How was this patch tested?_
    - [ ] Add some test cases that check the changes thoroughly including 
negative and positive cases if possible
    
    - [ ] Add screenshots for manual tests if appropriate
    
    - [ ] [Run 
test](https://kyuubi.apache.org/docs/latest/develop_tools/testing.html#running-tests)
 locally before make a pull request
    
    Closes #2107 from zhaomin1423/improve_loop.
    
    Closes #2071
    
    b6d70b3a [Min Zhao] Merge branch 'improve_loop' of 
github.com:zhaomin1423/kyuubi into improve_loop
    43bca772 [Min Zhao] [Kyuubi #2071] Using while-loop instead of map/range to 
improve performance in RowSet
    ec2cb912 [Min Zhao] [Kyuubi #2071] Using while-loop instead of map/range to 
improve performance in RowSet
    
    Authored-by: Min Zhao <zhaomin1...@163.com>
    Signed-off-by: Kent Yao <y...@apache.org>
---
 .../apache/kyuubi/engine/spark/schema/RowSet.scala | 32 ++++++++++++++++------
 1 file changed, 23 insertions(+), 9 deletions(-)

diff --git 
a/externals/kyuubi-spark-sql-engine/src/main/scala/org/apache/kyuubi/engine/spark/schema/RowSet.scala
 
b/externals/kyuubi-spark-sql-engine/src/main/scala/org/apache/kyuubi/engine/spark/schema/RowSet.scala
index 8d2fe8d..a6eff9e 100644
--- 
a/externals/kyuubi-spark-sql-engine/src/main/scala/org/apache/kyuubi/engine/spark/schema/RowSet.scala
+++ 
b/externals/kyuubi-spark-sql-engine/src/main/scala/org/apache/kyuubi/engine/spark/schema/RowSet.scala
@@ -46,21 +46,35 @@ object RowSet {
   }
 
   def toRowBasedSet(rows: Seq[Row], schema: StructType, timeZone: ZoneId): 
TRowSet = {
-    val tRows = rows.map { row =>
+    val tRows = new java.util.ArrayList[TRow]()
+    var i = 0
+    val rowSize = rows.length
+    while (i < rowSize) {
+      val row = rows(i)
       val tRow = new TRow()
-      (0 until row.length).map(i => toTColumnValue(i, row, schema, timeZone))
-        .foreach(tRow.addToColVals)
-      tRow
-    }.asJava
+      var j = 0
+      val columnSize = row.length
+      while (j < columnSize) {
+        val columnValue = toTColumnValue(j, row, schema, timeZone)
+        tRow.addToColVals(columnValue)
+        j += 1
+      }
+      i += 1
+      tRows.add(tRow)
+    }
     new TRowSet(0, tRows)
   }
 
   def toColumnBasedSet(rows: Seq[Row], schema: StructType, timeZone: ZoneId): 
TRowSet = {
-    val size = rows.length
-    val tRowSet = new TRowSet(0, new java.util.ArrayList[TRow](size))
-    schema.zipWithIndex.foreach { case (filed, i) =>
-      val tColumn = toTColumn(rows, i, filed.dataType, timeZone)
+    val rowSize = rows.length
+    val tRowSet = new TRowSet(0, new java.util.ArrayList[TRow](rowSize))
+    var i = 0
+    val columnSize = schema.length
+    while (i < columnSize) {
+      val field = schema(i)
+      val tColumn = toTColumn(rows, i, field.dataType, timeZone)
       tRowSet.addToColumns(tColumn)
+      i += 1
     }
     tRowSet
   }