You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@spark.apache.org by "Takeshi Yamamuro (JIRA)" <ji...@apache.org> on 2017/07/09 06:13:00 UTC
[jira] [Updated] (SPARK-21351) Update nullability based on
children's output in optimized logical plan
[ https://issues.apache.org/jira/browse/SPARK-21351?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Takeshi Yamamuro updated SPARK-21351:
-------------------------------------
Description:
In the master, optimized plans do not respect the nullability that `Filter` might change when having `IsNotNull`.
This generates unnecessary code for NULL checks. For example:
{code}
scala> val df = Seq((Some(1), Some(2))).toDF("a", "b")
scala> val bIsNotNull = df.where($"b" =!= 2).select($"b")
scala> val targetQuery = bIsNotNull.distinct
scala> val targetQuery.queryExecution.optimizedPlan.output(0).nullable
res5: Boolean = true
scala> targetQuery.debugCodegen
Found 2 WholeStageCodegen subtrees.
== Subtree 1 / 2 ==
*HashAggregate(keys=[b#19], functions=[], output=[b#19])
+- Exchange hashpartitioning(b#19, 200)
+- *HashAggregate(keys=[b#19], functions=[], output=[b#19])
+- *Project [_2#16 AS b#19]
+- *Filter isnotnull(_2#16)
+- LocalTableScan [_1#15, _2#16]
Generated code:
...
/* 124 */ protected void processNext() throws java.io.IOException {
...
/* 132 */ // output the result
/* 133 */
/* 134 */ while (agg_mapIter.next()) {
/* 135 */ wholestagecodegen_numOutputRows.add(1);
/* 136 */ UnsafeRow agg_aggKey = (UnsafeRow) agg_mapIter.getKey();
/* 137 */ UnsafeRow agg_aggBuffer = (UnsafeRow) agg_mapIter.getValue();
/* 138 */
/* 139 */ boolean agg_isNull4 = agg_aggKey.isNullAt(0);
/* 140 */ int agg_value4 = agg_isNull4 ? -1 : (agg_aggKey.getInt(0));
/* 141 */ agg_rowWriter1.zeroOutNullBytes();
/* 142 */
// We don't need this NULL check because NULL is filtered out in `$"b" =!=2`
/* 143 */ if (agg_isNull4) {
/* 144 */ agg_rowWriter1.setNullAt(0);
/* 145 */ } else {
/* 146 */ agg_rowWriter1.write(0, agg_value4);
/* 147 */ }
/* 148 */ append(agg_result1);
/* 149 */
/* 150 */ if (shouldStop()) return;
/* 151 */ }
/* 152 */
/* 153 */ agg_mapIter.close();
/* 154 */ if (agg_sorter == null) {
/* 155 */ agg_hashMap.free();
/* 156 */ }
/* 157 */ }
/* 158 */
/* 159 */ }
{code}
In the line 143, we don't need this NULL check because NULL is filtered out in `$"b" =!=2`.
was:
In the master, optimized plans do not respect the nullability that `Filter` might change when having `IsNotNull`. This generates unnecessary code for NULL checks. For example:
{code}
scala> val df = Seq((Some(1), Some(2))).toDF("a", "b")
scala> val bIsNotNull = df.where($"b" =!= 2).select($"b")
scala> val targetQuery = bIsNotNull.distinct
scala> val targetQuery.queryExecution.optimizedPlan.output(0).nullable
res5: Boolean = true
scala> targetQuery.debugCodegen
Found 2 WholeStageCodegen subtrees.
== Subtree 1 / 2 ==
*HashAggregate(keys=[b#19], functions=[], output=[b#19])
+- Exchange hashpartitioning(b#19, 200)
+- *HashAggregate(keys=[b#19], functions=[], output=[b#19])
+- *Project [_2#16 AS b#19]
+- *Filter isnotnull(_2#16)
+- LocalTableScan [_1#15, _2#16]
Generated code:
...
/* 124 */ protected void processNext() throws java.io.IOException {
...
/* 132 */ // output the result
/* 133 */
/* 134 */ while (agg_mapIter.next()) {
/* 135 */ wholestagecodegen_numOutputRows.add(1);
/* 136 */ UnsafeRow agg_aggKey = (UnsafeRow) agg_mapIter.getKey();
/* 137 */ UnsafeRow agg_aggBuffer = (UnsafeRow) agg_mapIter.getValue();
/* 138 */
/* 139 */ boolean agg_isNull4 = agg_aggKey.isNullAt(0);
/* 140 */ int agg_value4 = agg_isNull4 ? -1 : (agg_aggKey.getInt(0));
/* 141 */ agg_rowWriter1.zeroOutNullBytes();
/* 142 */
// We don't need this NULL check because NULL is filtered out in `$"b" =!=2`
/* 143 */ if (agg_isNull4) {
/* 144 */ agg_rowWriter1.setNullAt(0);
/* 145 */ } else {
/* 146 */ agg_rowWriter1.write(0, agg_value4);
/* 147 */ }
/* 148 */ append(agg_result1);
/* 149 */
/* 150 */ if (shouldStop()) return;
/* 151 */ }
/* 152 */
/* 153 */ agg_mapIter.close();
/* 154 */ if (agg_sorter == null) {
/* 155 */ agg_hashMap.free();
/* 156 */ }
/* 157 */ }
/* 158 */
/* 159 */ }
{code}
In the line 143, we don't need this NULL check because NULL is filtered out in `$"b" =!=2`.
> Update nullability based on children's output in optimized logical plan
> -----------------------------------------------------------------------
>
> Key: SPARK-21351
> URL: https://issues.apache.org/jira/browse/SPARK-21351
> Project: Spark
> Issue Type: Improvement
> Components: SQL
> Affects Versions: 2.1.1
> Reporter: Takeshi Yamamuro
> Priority: Minor
>
> In the master, optimized plans do not respect the nullability that `Filter` might change when having `IsNotNull`.
> This generates unnecessary code for NULL checks. For example:
> {code}
> scala> val df = Seq((Some(1), Some(2))).toDF("a", "b")
> scala> val bIsNotNull = df.where($"b" =!= 2).select($"b")
> scala> val targetQuery = bIsNotNull.distinct
> scala> val targetQuery.queryExecution.optimizedPlan.output(0).nullable
> res5: Boolean = true
> scala> targetQuery.debugCodegen
> Found 2 WholeStageCodegen subtrees.
> == Subtree 1 / 2 ==
> *HashAggregate(keys=[b#19], functions=[], output=[b#19])
> +- Exchange hashpartitioning(b#19, 200)
> +- *HashAggregate(keys=[b#19], functions=[], output=[b#19])
> +- *Project [_2#16 AS b#19]
> +- *Filter isnotnull(_2#16)
> +- LocalTableScan [_1#15, _2#16]
> Generated code:
> ...
> /* 124 */ protected void processNext() throws java.io.IOException {
> ...
> /* 132 */ // output the result
> /* 133 */
> /* 134 */ while (agg_mapIter.next()) {
> /* 135 */ wholestagecodegen_numOutputRows.add(1);
> /* 136 */ UnsafeRow agg_aggKey = (UnsafeRow) agg_mapIter.getKey();
> /* 137 */ UnsafeRow agg_aggBuffer = (UnsafeRow) agg_mapIter.getValue();
> /* 138 */
> /* 139 */ boolean agg_isNull4 = agg_aggKey.isNullAt(0);
> /* 140 */ int agg_value4 = agg_isNull4 ? -1 : (agg_aggKey.getInt(0));
> /* 141 */ agg_rowWriter1.zeroOutNullBytes();
> /* 142 */
> // We don't need this NULL check because NULL is filtered out in `$"b" =!=2`
> /* 143 */ if (agg_isNull4) {
> /* 144 */ agg_rowWriter1.setNullAt(0);
> /* 145 */ } else {
> /* 146 */ agg_rowWriter1.write(0, agg_value4);
> /* 147 */ }
> /* 148 */ append(agg_result1);
> /* 149 */
> /* 150 */ if (shouldStop()) return;
> /* 151 */ }
> /* 152 */
> /* 153 */ agg_mapIter.close();
> /* 154 */ if (agg_sorter == null) {
> /* 155 */ agg_hashMap.free();
> /* 156 */ }
> /* 157 */ }
> /* 158 */
> /* 159 */ }
> {code}
> In the line 143, we don't need this NULL check because NULL is filtered out in `$"b" =!=2`.
--
This message was sent by Atlassian JIRA
(v6.4.14#64029)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscribe@spark.apache.org
For additional commands, e-mail: issues-help@spark.apache.org