[
https://issues.apache.org/jira/browse/SPARK-15822?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15331375#comment-15331375
]
Pete Robbins commented on SPARK-15822:
--------------------------------------
and the plan:
{noformat}
== Parsed Logical Plan ==
'Project [unresolvedalias('Origin, None), unresolvedalias('UniqueCarrier,
None), 'round((('count * 100) / 'total), 2) AS rank#173]
+- Project [Origin#16, UniqueCarrier#8, count#134L, total#97L]
+- Join Inner, ((Origin#16 = Origin#155) && (UniqueCarrier#8 =
UniqueCarrier#147))
:- Aggregate [Origin#16, UniqueCarrier#8], [Origin#16, UniqueCarrier#8,
count(1) AS count#134L]
: +- Filter (NOT (Cancelled#21 = 0) && (CancellationCode#22 = A))
: +- Filter (Dest#17 = ORD)
: +-
Relation[Year#0,Month#1,DayofMonth#2,DayOfWeek#3,DepTime#4,CRSDepTime#5,ArrTime#6,CRSArrTime#7,UniqueCarrier#8,FlightNum#9,TailNum#10,ActualElapsedTime#11,CRSElapsedTime#12,AirTime#13,ArrDelay#14,DepDelay#15,Origin#16,Dest#17,Distance#18,TaxiIn#19,TaxiOut#20,Cancelled#21,CancellationCode#22,Diverted#23,...
5 more fields] csv
+- Project [Origin#155, UniqueCarrier#147, count#92L AS total#97L]
+- Aggregate [Origin#155, UniqueCarrier#147], [Origin#155,
UniqueCarrier#147, count(1) AS count#92L]
+- Filter (Dest#156 = ORD)
+-
Relation[Year#139,Month#140,DayofMonth#141,DayOfWeek#142,DepTime#143,CRSDepTime#144,ArrTime#145,CRSArrTime#146,UniqueCarrier#147,FlightNum#148,TailNum#149,ActualElapsedTime#150,CRSElapsedTime#151,AirTime#152,ArrDelay#153,DepDelay#154,Origin#155,Dest#156,Distance#157,TaxiIn#158,TaxiOut#159,Cancelled#160,CancellationCode#161,Diverted#162,...
5 more fields] csv
== Analyzed Logical Plan ==
Origin: string, UniqueCarrier: string, rank: double
Project [Origin#16, UniqueCarrier#8, round((cast((count#134L * cast(100 as
bigint)) as double) / cast(total#97L as double)), 2) AS rank#173]
+- Project [Origin#16, UniqueCarrier#8, count#134L, total#97L]
+- Join Inner, ((Origin#16 = Origin#155) && (UniqueCarrier#8 =
UniqueCarrier#147))
:- Aggregate [Origin#16, UniqueCarrier#8], [Origin#16, UniqueCarrier#8,
count(1) AS count#134L]
: +- Filter (NOT (Cancelled#21 = 0) && (CancellationCode#22 = A))
: +- Filter (Dest#17 = ORD)
: +-
Relation[Year#0,Month#1,DayofMonth#2,DayOfWeek#3,DepTime#4,CRSDepTime#5,ArrTime#6,CRSArrTime#7,UniqueCarrier#8,FlightNum#9,TailNum#10,ActualElapsedTime#11,CRSElapsedTime#12,AirTime#13,ArrDelay#14,DepDelay#15,Origin#16,Dest#17,Distance#18,TaxiIn#19,TaxiOut#20,Cancelled#21,CancellationCode#22,Diverted#23,...
5 more fields] csv
+- Project [Origin#155, UniqueCarrier#147, count#92L AS total#97L]
+- Aggregate [Origin#155, UniqueCarrier#147], [Origin#155,
UniqueCarrier#147, count(1) AS count#92L]
+- Filter (Dest#156 = ORD)
+-
Relation[Year#139,Month#140,DayofMonth#141,DayOfWeek#142,DepTime#143,CRSDepTime#144,ArrTime#145,CRSArrTime#146,UniqueCarrier#147,FlightNum#148,TailNum#149,ActualElapsedTime#150,CRSElapsedTime#151,AirTime#152,ArrDelay#153,DepDelay#154,Origin#155,Dest#156,Distance#157,TaxiIn#158,TaxiOut#159,Cancelled#160,CancellationCode#161,Diverted#162,...
5 more fields] csv
== Optimized Logical Plan ==
Project [Origin#16, UniqueCarrier#8, round((cast((count#134L * 100) as double)
/ cast(total#97L as double)), 2) AS rank#173]
+- Join Inner, ((Origin#16 = Origin#155) && (UniqueCarrier#8 =
UniqueCarrier#147))
:- Aggregate [Origin#16, UniqueCarrier#8], [Origin#16, UniqueCarrier#8,
count(1) AS count#134L]
: +- Project [UniqueCarrier#8, Origin#16]
: +- Filter (((((((isnotnull(Origin#16) && isnotnull(UniqueCarrier#8))
&& isnotnull(Cancelled#21)) && isnotnull(CancellationCode#22)) && NOT
(Cancelled#21 = 0)) && (CancellationCode#22 = A)) && isnotnull(Dest#17)) &&
(Dest#17 = ORD))
: +-
Relation[Year#0,Month#1,DayofMonth#2,DayOfWeek#3,DepTime#4,CRSDepTime#5,ArrTime#6,CRSArrTime#7,UniqueCarrier#8,FlightNum#9,TailNum#10,ActualElapsedTime#11,CRSElapsedTime#12,AirTime#13,ArrDelay#14,DepDelay#15,Origin#16,Dest#17,Distance#18,TaxiIn#19,TaxiOut#20,Cancelled#21,CancellationCode#22,Diverted#23,...
5 more fields] csv
+- Aggregate [Origin#155, UniqueCarrier#147], [Origin#155,
UniqueCarrier#147, count(1) AS total#97L]
+- Project [UniqueCarrier#147, Origin#155]
+- Filter (((isnotnull(UniqueCarrier#147) && isnotnull(Origin#155)) &&
isnotnull(Dest#156)) && (Dest#156 = ORD))
+-
Relation[Year#139,Month#140,DayofMonth#141,DayOfWeek#142,DepTime#143,CRSDepTime#144,ArrTime#145,CRSArrTime#146,UniqueCarrier#147,FlightNum#148,TailNum#149,ActualElapsedTime#150,CRSElapsedTime#151,AirTime#152,ArrDelay#153,DepDelay#154,Origin#155,Dest#156,Distance#157,TaxiIn#158,TaxiOut#159,Cancelled#160,CancellationCode#161,Diverted#162,...
5 more fields] csv
== Physical Plan ==
*Project [Origin#16, UniqueCarrier#8, round((cast((count#134L * 100) as double)
/ cast(total#97L as double)), 2) AS rank#173]
+- *SortMergeJoin [Origin#16, UniqueCarrier#8], [Origin#155,
UniqueCarrier#147], Inner
:- *Sort [Origin#16 ASC, UniqueCarrier#8 ASC], false, 0
: +- *HashAggregate(key=[Origin#16,UniqueCarrier#8], functions=[count(1)],
output=[Origin#16,UniqueCarrier#8,count#134L])
: +- Exchange hashpartitioning(Origin#16, UniqueCarrier#8, 200)
: +- *HashAggregate(key=[Origin#16,UniqueCarrier#8],
functions=[partial_count(1)], output=[Origin#16,UniqueCarrier#8,count#296L])
: +- *Project [UniqueCarrier#8, Origin#16]
: +- *Filter (((((((isnotnull(Origin#16) &&
isnotnull(UniqueCarrier#8)) && isnotnull(Cancelled#21)) &&
isnotnull(CancellationCode#22)) && NOT (Cancelled#21 = 0)) &&
(CancellationCode#22 = A)) && isnotnull(Dest#17)) && (Dest#17 = ORD))
: +- *Scan csv
[UniqueCarrier#8,Origin#16,Dest#17,Cancelled#21,CancellationCode#22] Format:
CSV, InputPaths: file:/home/robbins/brandberry/2008.csv, PushedFilters:
[IsNotNull(Origin), IsNotNull(UniqueCarrier), IsNotNull(Cancelled),
IsNotNull(CancellationCode), ..., ReadSchema:
struct<UniqueCarrier:string,Origin:string,Dest:string,Cancelled:int,CancellationCode:string>
+- *Sort [Origin#155 ASC, UniqueCarrier#147 ASC], false, 0
+- *HashAggregate(key=[Origin#155,UniqueCarrier#147],
functions=[count(1)], output=[Origin#155,UniqueCarrier#147,total#97L])
+- Exchange hashpartitioning(Origin#155, UniqueCarrier#147, 200)
+- *HashAggregate(key=[Origin#155,UniqueCarrier#147],
functions=[partial_count(1)], output=[Origin#155,UniqueCarrier#147,count#303L])
+- *Project [UniqueCarrier#147, Origin#155]
+- *Filter (((isnotnull(UniqueCarrier#147) &&
isnotnull(Origin#155)) && isnotnull(Dest#156)) && (Dest#156 = ORD))
+- *Scan csv [UniqueCarrier#147,Origin#155,Dest#156]
Format: CSV, InputPaths: file:/home/robbins/brandberry/2008.csv, PushedFilters:
[IsNotNull(UniqueCarrier), IsNotNull(Origin), IsNotNull(Dest),
EqualTo(Dest,ORD)], ReadSchema:
struct<UniqueCarrier:string,Origin:string,Dest:string>
{noformat}
> segmentation violation in o.a.s.unsafe.types.UTF8String
> --------------------------------------------------------
>
> Key: SPARK-15822
> URL: https://issues.apache.org/jira/browse/SPARK-15822
> Project: Spark
> Issue Type: Bug
> Affects Versions: 2.0.0
> Environment: linux amd64
> openjdk version "1.8.0_91"
> OpenJDK Runtime Environment (build 1.8.0_91-b14)
> OpenJDK 64-Bit Server VM (build 25.91-b14, mixed mode)
> Reporter: Pete Robbins
> Assignee: Herman van Hovell
> Priority: Blocker
>
> Executors fail with segmentation violation while running application with
> spark.memory.offHeap.enabled true
> spark.memory.offHeap.size 512m
> Also now reproduced with
> spark.memory.offHeap.enabled false
> {noformat}
> #
> # A fatal error has been detected by the Java Runtime Environment:
> #
> # SIGSEGV (0xb) at pc=0x00007f4559b4d4bd, pid=14182, tid=139935319750400
> #
> # JRE version: OpenJDK Runtime Environment (8.0_91-b14) (build 1.8.0_91-b14)
> # Java VM: OpenJDK 64-Bit Server VM (25.91-b14 mixed mode linux-amd64
> compressed oops)
> # Problematic frame:
> # J 4816 C2
> org.apache.spark.unsafe.types.UTF8String.compareTo(Lorg/apache/spark/unsafe/types/UTF8String;)I
> (64 bytes) @ 0x00007f4559b4d4bd [0x00007f4559b4d460+0x5d]
> {noformat}
> We initially saw this on IBM java on PowerPC box but is recreatable on linux
> with OpenJDK. On linux with IBM Java 8 we see a null pointer exception at the
> same code point:
> {noformat}
> 16/06/08 11:14:58 ERROR Executor: Exception in task 1.0 in stage 5.0 (TID 48)
> java.lang.NullPointerException
> at
> org.apache.spark.unsafe.types.UTF8String.compareTo(UTF8String.java:831)
> at org.apache.spark.unsafe.types.UTF8String.compare(UTF8String.java:844)
> at
> org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIterator.findNextInnerJoinRows$(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$$anonfun$doExecute$2$$anon$2.hasNext(WholeStageCodegenExec.scala:377)
> at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:408)
> at
> scala.collection.convert.Wrappers$IteratorWrapper.hasNext(Wrappers.scala:30)
> at org.spark_project.guava.collect.Ordering.leastOf(Ordering.java:664)
> at org.apache.spark.util.collection.Utils$.takeOrdered(Utils.scala:37)
> at
> org.apache.spark.rdd.RDD$$anonfun$takeOrdered$1$$anonfun$30.apply(RDD.scala:1365)
> at
> org.apache.spark.rdd.RDD$$anonfun$takeOrdered$1$$anonfun$30.apply(RDD.scala:1362)
> at
> org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$23.apply(RDD.scala:757)
> at
> org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$23.apply(RDD.scala:757)
> at
> org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:318)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:282)
> at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:70)
> at org.apache.spark.scheduler.Task.run(Task.scala:85)
> at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:274)
> at
> java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1153)
> at
> java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:628)
> at java.lang.Thread.run(Thread.java:785)
> {noformat}
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
