Catalin Alexandru Zamfir created SPARK-11659:
------------------------------------------------
Summary: Codegen sporadically fails with same input character
Key: SPARK-11659
URL: https://issues.apache.org/jira/browse/SPARK-11659
Project: Spark
Issue Type: Bug
Components: Spark Core, SQL
Affects Versions: 1.5.1
Environment: Default, Linux (Jessie)
Reporter: Catalin Alexandru Zamfir
We pretty much have a default instalation of Spark 1.5.1. Some of our jobs
sporadically fail with the below exception for the same "input character" (we
don't have @ in our inputs, but jobs still fail) and when we re-run the same
job with the same input, all jobs pass without any failures. I believe it's a
bug in code-gen but I can't debug this on a production cluster (and it's almost
close to impossible to reproduce it).
{{Job aborted due to stage failure: Task 50 in stage 4.0 failed 4 times, most
recent failure: Lost task 50.3 in stage 4.0 (TID 894, 10.136.64.112):
java.util.concurrent.ExecutionException: java.lang.Exception: failed to
compile: org.codehaus.commons.compiler.CompileException: Line 15, Column 9:
Invalid character input "@" (character code 64)
public SpecificOrdering
generate(org.apache.spark.sql.catalyst.expressions.Expression[] expr) {
return new SpecificOrdering(expr);
}
class SpecificOrdering extends
org.apache.spark.sql.catalyst.expressions.codegen.BaseOrdering {
private org.apache.spark.sql.catalyst.expressions.Expression[] expressions;
public
SpecificOrdering(org.apache.spark.sql.catalyst.expressions.Expression[] expr) {
expressions = expr;
}
@Override
public int compare(InternalRow a, InternalRow b) {
InternalRow i = null; // Holds current row being evaluated.
i = a;
boolean isNullA2;
long primitiveA3;
{
/* input[0, LongType] */
boolean isNull0 = i.isNullAt(0);
long primitive1 = isNull0 ? -1L : (i.getLong(0));
isNullA2 = isNull0;
primitiveA3 = primitive1;
}
i = b;
boolean isNullB4;
long primitiveB5;
{
/* input[0, LongType] */
boolean isNull0 = i.isNullAt(0);
long primitive1 = isNull0 ? -1L : (i.getLong(0));
isNullB4 = isNull0;
primitiveB5 = primitive1;
}
if (isNullA2 && isNullB4) {
// Nothing
} else if (isNullA2) {
return -1;
} else if (isNullB4) {
return 1;
} else {
int comp = (primitiveA3 > primitiveB5 ? 1 : primitiveA3 < primitiveB5 ?
-1 : 0);
if (comp != 0) {
return comp;
}
}
i = a;
boolean isNullA8;
long primitiveA9;
{
/* input[1, LongType] */
boolean isNull6 = i.isNullAt(1);
long primitive7 = isNull6 ? -1L : (i.getLong(1));
isNullA8 = isNull6;
primitiveA9 = primitive7;
}
i = b;
boolean isNullB10;
long primitiveB11;
{
/* input[1, LongType] */
boolean isNull6 = i.isNullAt(1);
long primitive7 = isNull6 ? -1L : (i.getLong(1));
isNullB10 = isNull6;
primitiveB11 = primitive7;
}
if (isNullA8 && isNullB10) {
// Nothing
} else if (isNullA8) {
return -1;
} else if (isNullB10) {
return 1;
} else {
int comp = (primitiveA9 > primitiveB11 ? 1 : primitiveA9 < primitiveB11 ?
-1 : 0);
if (comp != 0) {
return comp;
}
}
i = a;
boolean isNullA14;
long primitiveA15;
{
/* input[2, LongType] */
boolean isNull12 = i.isNullAt(2);
long primitive13 = isNull12 ? -1L : (i.getLong(2));
isNullA14 = isNull12;
primitiveA15 = primitive13;
}
i = b;
boolean isNullB16;
long primitiveB17;
{
/* input[2, LongType] */
boolean isNull12 = i.isNullAt(2);
long primitive13 = isNull12 ? -1L : (i.getLong(2));
isNullB16 = isNull12;
primitiveB17 = primitive13;
}
if (isNullA14 && isNullB16) {
// Nothing
} else if (isNullA14) {
return -1;
} else if (isNullB16) {
return 1;
} else {
int comp = (primitiveA15 > primitiveB17 ? 1 : primitiveA15 < primitiveB17
? -1 : 0);
if (comp != 0) {
return comp;
}
}
return 0;
}
}
at
org.spark-project.guava.util.concurrent.AbstractFuture$Sync.getValue(AbstractFuture.java:306)
at
org.spark-project.guava.util.concurrent.AbstractFuture$Sync.get(AbstractFuture.java:293)
at
org.spark-project.guava.util.concurrent.AbstractFuture.get(AbstractFuture.java:116)
at
org.spark-project.guava.util.concurrent.Uninterruptibles.getUninterruptibly(Uninterruptibles.java:135)
at
org.spark-project.guava.cache.LocalCache$Segment.getAndRecordStats(LocalCache.java:2410)
at
org.spark-project.guava.cache.LocalCache$Segment.loadSync(LocalCache.java:2380)
at
org.spark-project.guava.cache.LocalCache$Segment.lockedGetOrLoad(LocalCache.java:2342)
at
org.spark-project.guava.cache.LocalCache$Segment.get(LocalCache.java:2257)
at org.spark-project.guava.cache.LocalCache.get(LocalCache.java:4000)
at
org.spark-project.guava.cache.LocalCache.getOrLoad(LocalCache.java:4004)
at
org.spark-project.guava.cache.LocalCache$LocalLoadingCache.get(LocalCache.java:4874)
at
org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator.compile(CodeGenerator.scala:362)
at
org.apache.spark.sql.catalyst.expressions.codegen.GenerateOrdering$.create(GenerateOrdering.scala:139)
at
org.apache.spark.sql.catalyst.expressions.codegen.GenerateOrdering$.create(GenerateOrdering.scala:49)
at
org.apache.spark.sql.catalyst.expressions.codegen.GenerateOrdering.create(GenerateOrdering.scala)
at
org.apache.spark.sql.execution.UnsafeKVExternalSorter.<init>(UnsafeKVExternalSorter.java:68)
at
org.apache.spark.sql.execution.UnsafeFixedWidthAggregationMap.destructAndCreateExternalSorter(UnsafeFixedWidthAggregationMap.java:257)
at
org.apache.spark.sql.execution.aggregate.TungstenAggregationIterator.switchToSortBasedAggregation(TungstenAggregationIterator.scala:435)
at
org.apache.spark.sql.execution.aggregate.TungstenAggregationIterator.processInputs(TungstenAggregationIterator.scala:379)
at
org.apache.spark.sql.execution.aggregate.TungstenAggregationIterator.start(TungstenAggregationIterator.scala:622)
at
org.apache.spark.sql.execution.aggregate.TungstenAggregate$$anonfun$doExecute$1.org$apache$spark$sql$execution$aggregate$TungstenAggregate$$anonfun$$executePartition$1(TungstenAggregate.scala:110)
at
org.apache.spark.sql.execution.aggregate.TungstenAggregate$$anonfun$doExecute$1$$anonfun$2.apply(TungstenAggregate.scala:119)
at
org.apache.spark.sql.execution.aggregate.TungstenAggregate$$anonfun$doExecute$1$$anonfun$2.apply(TungstenAggregate.scala:119)
at
org.apache.spark.rdd.MapPartitionsWithPreparationRDD.compute(MapPartitionsWithPreparationRDD.scala:64)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:297)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:264)
at
org.apache.spark.rdd.MapPartitionsWithPreparationRDD.compute(MapPartitionsWithPreparationRDD.scala:63)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:297)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:264)
at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:297)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:264)
at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:297)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:264)
at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:297)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:264)
at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:297)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:264)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
at org.apache.spark.scheduler.Task.run(Task.scala:88)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214)
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)
Caused by: java.lang.Exception: failed to compile:
org.codehaus.commons.compiler.CompileException: Line 15, Column 9: Invalid
character input "@" (character code 64)
public SpecificOrdering
generate(org.apache.spark.sql.catalyst.expressions.Expression[] expr) {
return new SpecificOrdering(expr);
}
class SpecificOrdering extends
org.apache.spark.sql.catalyst.expressions.codegen.BaseOrdering {
private org.apache.spark.sql.catalyst.expressions.Expression[] expressions;
public
SpecificOrdering(org.apache.spark.sql.catalyst.expressions.Expression[] expr) {
expressions = expr;
}
@Override
public int compare(InternalRow a, InternalRow b) {
InternalRow i = null; // Holds current row being evaluated.
i = a;
boolean isNullA2;
long primitiveA3;
{
/* input[0, LongType] */
boolean isNull0 = i.isNullAt(0);
long primitive1 = isNull0 ? -1L : (i.getLong(0));
isNullA2 = isNull0;
primitiveA3 = primitive1;
}
i = b;
boolean isNullB4;
long primitiveB5;
{
/* input[0, LongType] */
boolean isNull0 = i.isNullAt(0);
long primitive1 = isNull0 ? -1L : (i.getLong(0));
isNullB4 = isNull0;
primitiveB5 = primitive1;
}
if (isNullA2 && isNullB4) {
// Nothing
} else if (isNullA2) {
return -1;
} else if (isNullB4) {
return 1;
} else {
int comp = (primitiveA3 > primitiveB5 ? 1 : primitiveA3 < primitiveB5 ?
-1 : 0);
if (comp != 0) {
return comp;
}
}
i = a;
boolean isNullA8;
long primitiveA9;
{
/* input[1, LongType] */
boolean isNull6 = i.isNullAt(1);
long primitive7 = isNull6 ? -1L : (i.getLong(1));
isNullA8 = isNull6;
primitiveA9 = primitive7;
}
i = b;
boolean isNullB10;
long primitiveB11;
{
/* input[1, LongType] */
boolean isNull6 = i.isNullAt(1);
long primitive7 = isNull6 ? -1L : (i.getLong(1));
isNullB10 = isNull6;
primitiveB11 = primitive7;
}
if (isNullA8 && isNullB10) {
// Nothing
} else if (isNullA8) {
return -1;
} else if (isNullB10) {
return 1;
} else {
int comp = (primitiveA9 > primitiveB11 ? 1 : primitiveA9 < primitiveB11 ?
-1 : 0);
if (comp != 0) {
return comp;
}
}
i = a;
boolean isNullA14;
long primitiveA15;
{
/* input[2, LongType] */
boolean isNull12 = i.isNullAt(2);
long primitive13 = isNull12 ? -1L : (i.getLong(2));
isNullA14 = isNull12;
primitiveA15 = primitive13;
}
i = b;
boolean isNullB16;
long primitiveB17;
{
/* input[2, LongType] */
boolean isNull12 = i.isNullAt(2);
long primitive13 = isNull12 ? -1L : (i.getLong(2));
isNullB16 = isNull12;
primitiveB17 = primitive13;
}
if (isNullA14 && isNullB16) {
// Nothing
} else if (isNullA14) {
return -1;
} else if (isNullB16) {
return 1;
} else {
int comp = (primitiveA15 > primitiveB17 ? 1 : primitiveA15 < primitiveB17
? -1 : 0);
if (comp != 0) {
return comp;
}
}
return 0;
}
}
at
org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator.org$apache$spark$sql$catalyst$expressions$codegen$CodeGenerator$$doCompile(CodeGenerator.scala:392)
at
org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator$$anon$1.load(CodeGenerator.scala:412)
at
org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator$$anon$1.load(CodeGenerator.scala:409)
at
org.spark-project.guava.cache.LocalCache$LoadingValueReference.loadFuture(LocalCache.java:3599)
at
org.spark-project.guava.cache.LocalCache$Segment.loadSync(LocalCache.java:2379)
... 41 more
Caused by: org.codehaus.commons.compiler.CompileException: Line 15, Column 9:
Invalid character input "@" (character code 64)
at org.codehaus.janino.Scanner.internalRead(Scanner.java:838)
at org.codehaus.janino.Scanner.read(Scanner.java:261)
at org.codehaus.janino.Parser.readOperator(Parser.java:2387)
at
org.codehaus.janino.Parser.parseConstructorDeclarator(Parser.java:721)
at org.codehaus.janino.Parser.parseClassBodyDeclaration(Parser.java:435)
at org.codehaus.janino.Parser.parseClassBody(Parser.java:338)
at org.codehaus.janino.Parser.parseClassDeclarationRest(Parser.java:311)
at org.codehaus.janino.Parser.parseClassBodyDeclaration(Parser.java:406)
at
org.codehaus.janino.ClassBodyEvaluator.cook(ClassBodyEvaluator.java:220)
at org.codehaus.janino.SimpleCompiler.cook(SimpleCompiler.java:194)
at org.codehaus.commons.compiler.Cookable.cook(Cookable.java:80)
at org.codehaus.commons.compiler.Cookable.cook(Cookable.java:72)
at
org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator.org$apache$spark$sql$catalyst$expressions$codegen$CodeGenerator$$doCompile(CodeGenerator.scala:387)
... 45 more
Driver stacktrace:}}
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
