You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@spark.apache.org by "Erik LaBianca (JIRA)" <ji...@apache.org> on 2017/01/20 22:32:26 UTC
[jira] [Commented] (SPARK-18859) Catalyst codegen does not mark
column as nullable when it should. Causes NPE
[ https://issues.apache.org/jira/browse/SPARK-18859?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15832516#comment-15832516 ]
Erik LaBianca commented on SPARK-18859:
---------------------------------------
Not quite a repro, but here's explain output.
{noformat}
val df = spark.read
.format("jdbc")
.options(DataSources.TelepathPlayDb.PostgresOptions + (
"dbtable" -> s"""(select
profiles_contact_points.id,
remote_id
|from profiles_contact_points
| left join profiles_contacts_connectors
| on profiles_contact_points.contact_id = profiles_contacts_connectors.contact_id
| where profiles_contact_points.user_id = 1
) t""".stripMargin
))
.load
//.as[ContactRemoteValue]
df.printSchema()
df.explain(true)
df.map(_ != null).count()
{noformat}
Results in the following.
{noformat}
df: org.apache.spark.sql.DataFrame = [id: bigint, remote_id: string]
root
|-- id: long (nullable = false)
|-- remote_id: string (nullable = false)
== Parsed Logical Plan ==
Relation[id#2018L,remote_id#2019] JDBCRelation((select
profiles_contact_points.id,
remote_id
from profiles_contact_points
left join profiles_contacts_connectors
on profiles_contact_points.contact_id = profiles_contacts_connectors.contact_id
where profiles_contact_points.user_id = 1
) t)
== Analyzed Logical Plan ==
id: bigint, remote_id: string
Relation[id#2018L,remote_id#2019] JDBCRelation((select
profiles_contact_points.id,
remote_id
from profiles_contact_points
left join profiles_contacts_connectors
on profiles_contact_points.contact_id = profiles_contacts_connectors.contact_id
where profiles_contact_points.user_id = 1
) t)
== Optimized Logical Plan ==
Relation[id#2018L,remote_id#2019] JDBCRelation((select
profiles_contact_points.id,
remote_id
from profiles_contact_points
left join profiles_contacts_connectors
on profiles_contact_points.contact_id = profiles_contacts_connectors.contact_id
where profiles_contact_points.user_id = 1
) t)
== Physical Plan ==
*Scan JDBCRelation((select
profiles_contact_points.id,
remote_id
from profiles_contact_points
left join profiles_contacts_connectors
on profiles_contact_points.contact_id = profiles_contacts_connectors.contact_id
where profiles_contact_points.user_id = 225
) t) [id#2018L,remote_id#2019] ReadSchema: struct<id:bigint,remote_id:string>
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 238.0 failed 4 times, most recent failure: Lost task 0.3 in stage 238.0 (TID 55547, ip-x.ec2.internal): java.lang.NullPointerException
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIterator.agg_doAggregateWithoutKey$(Unknown Source)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIterator.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenExec$$anonfun$8$$anon$1.hasNext(WholeStageCodegenExec.scala:370)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:408)
at org.apache.spark.shuffle.sort.BypassMergeSortShuffleWriter.write(BypassMergeSortShuffleWriter.java:125)
at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:79)
at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:47)
at org.apache.spark.scheduler.Task.run(Task.scala:86)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:274)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
at java.lang.Thread.run(Thread.java:745)
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1454)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1442)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1441)
at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1441)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:811)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:811)
at scala.Option.foreach(Option.scala:257)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:811)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1667)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1622)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1611)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:632)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1873)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1886)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1899)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1913)
at org.apache.spark.rdd.RDD$$anonfun$collect$1.apply(RDD.scala:912)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:112)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:358)
at org.apache.spark.rdd.RDD.collect(RDD.scala:911)
at org.apache.spark.sql.execution.SparkPlan.executeCollect(SparkPlan.scala:290)
at org.apache.spark.sql.Dataset$$anonfun$org$apache$spark$sql$Dataset$$execute$1$1.apply(Dataset.scala:2193)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:57)
at org.apache.spark.sql.Dataset.withNewExecutionId(Dataset.scala:2546)
at org.apache.spark.sql.Dataset.org$apache$spark$sql$Dataset$$execute$1(Dataset.scala:2192)
at org.apache.spark.sql.Dataset.org$apache$spark$sql$Dataset$$collect(Dataset.scala:2199)
at org.apache.spark.sql.Dataset$$anonfun$count$1.apply(Dataset.scala:2227)
at org.apache.spark.sql.Dataset$$anonfun$count$1.apply(Dataset.scala:2226)
at org.apache.spark.sql.Dataset.withCallback(Dataset.scala:2559)
at org.apache.spark.sql.Dataset.count(Dataset.scala:2226)
... 170 elided
Caused by: java.lang.NullPointerException
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIterator.agg_doAggregateWithoutKey$(Unknown Source)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIterator.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenExec$$anonfun$8$$anon$1.hasNext(WholeStageCodegenExec.scala:370)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:408)
at org.apache.spark.shuffle.sort.BypassMergeSortShuffleWriter.write(BypassMergeSortShuffleWriter.java:125)
at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:79)
at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:47)
at org.apache.spark.scheduler.Task.run(Task.scala:86)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:274)
... 3 more
{noformat}
> Catalyst codegen does not mark column as nullable when it should. Causes NPE
> ----------------------------------------------------------------------------
>
> Key: SPARK-18859
> URL: https://issues.apache.org/jira/browse/SPARK-18859
> Project: Spark
> Issue Type: Bug
> Components: Optimizer, SQL
> Affects Versions: 2.0.2
> Reporter: Mykhailo Osypov
> Priority: Critical
>
> When joining two tables via LEFT JOIN, columns in right table may be NULLs, however catalyst codegen cannot recognize it.
> Example:
> {code:title=schema.sql|borderStyle=solid}
> create table masterdata.testtable(
> id int not null,
> age int
> );
> create table masterdata.jointable(
> id int not null,
> name text not null
> );
> {code}
> {code:title=query_to_select.sql|borderStyle=solid}
> (select t.id, t.age, j.name from masterdata.testtable t left join masterdata.jointable j on t.id = j.id) as testtable;
> {code}
> {code:title=master code|borderStyle=solid}
> val df = sqlContext
> .read
> .format("jdbc")
> .option("dbTable", "query to select")
> ....
> .load
> //df generated schema
> /*
> root
> |-- id: integer (nullable = false)
> |-- age: integer (nullable = true)
> |-- name: string (nullable = false)
> */
> {code}
> {code:title=Codegen|borderStyle=solid}
> /* 038 */ scan_rowWriter.write(0, scan_value);
> /* 039 */
> /* 040 */ if (scan_isNull1) {
> /* 041 */ scan_rowWriter.setNullAt(1);
> /* 042 */ } else {
> /* 043 */ scan_rowWriter.write(1, scan_value1);
> /* 044 */ }
> /* 045 */
> /* 046 */ scan_rowWriter.write(2, scan_value2);
> {code}
> Since *j.name* is from right table of *left join* query, it may be null. However generated schema doesn't think so (probably because it defined as *name text not null*)
> {code:title=StackTrace|borderStyle=solid}
> java.lang.NullPointerException
> at org.apache.spark.sql.catalyst.expressions.codegen.UnsafeRowWriter.write(UnsafeRowWriter.java:210)
> at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIterator.processNext(Unknown Source)
> at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
> at org.apache.spark.sql.execution.WholeStageCodegenExec$$anonfun$8$$anon$1.hasNext(WholeStageCodegenExec.scala:370)
> at org.apache.spark.sql.execution.debug.package$DebugExec$$anonfun$3$$anon$1.hasNext(package.scala:146)
> at org.apache.spark.util.Utils$.getIteratorSize(Utils.scala:1763)
> at org.apache.spark.rdd.RDD$$anonfun$count$1.apply(RDD.scala:1134)
> at org.apache.spark.rdd.RDD$$anonfun$count$1.apply(RDD.scala:1134)
> at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:1899)
> at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:1899)
> at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:70)
> at org.apache.spark.scheduler.Task.run(Task.scala:86)
> at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:274)
> at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
> at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
> at java.lang.Thread.run(Thread.java:745)
> {code}
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscribe@spark.apache.org
For additional commands, e-mail: issues-help@spark.apache.org