You are viewing a plain text version of this content. The canonical link for it is here.
Posted to user@spark.apache.org by "Zalzberg, Idan (Agoda)" <Id...@agoda.com> on 2014/09/23 07:07:59 UTC
RE: Exception with SparkSql and Avro
Hello,
I am trying to read a hive table that is stored in Avro DEFLATE files.
something simple like "SELECT * FROM X LIMIT 10"
I get 2 exceptions in the logs:
2014-09-23 09:27:50,157 WARN org.apache.spark.scheduler.TaskSetManager: Lost task 10.0 in stage 1.0 (TID 10, cl.local): org.apache.avro.AvroTypeException: Found com.a.bi.core.model.xxx.yyy, expecting org.apache.hadoop.hive.CannotDetermineSchemaSentinel, missing required field ERROR_ERROR_ERROR_ERROR_ERROR_ERROR_ERROR
org.apache.avro.io.ResolvingDecoder.doAction(ResolvingDecoder.java:231)
org.apache.avro.io.parsing.Parser.advance(Parser.java:88)
org.apache.avro.io.ResolvingDecoder.readFieldOrder(ResolvingDecoder.java:127)
org.apache.avro.generic.GenericDatumReader.readRecord(GenericDatumReader.java:176)
org.apache.avro.generic.GenericDatumReader.read(GenericDatumReader.java:151)
org.apache.avro.generic.GenericDatumReader.read(GenericDatumReader.java:142)
org.apache.avro.file.DataFileStream.next(DataFileStream.java:233)
org.apache.avro.file.DataFileStream.next(DataFileStream.java:220)
org.apache.hadoop.hive.ql.io.avro.AvroGenericRecordReader.next(AvroGenericRecordReader.java:149)
org.apache.hadoop.hive.ql.io.avro.AvroGenericRecordReader.next(AvroGenericRecordReader.java:52)
org.apache.spark.rdd.HadoopRDD$$anon$1.getNext(HadoopRDD.scala:219)
org.apache.spark.rdd.HadoopRDD$$anon$1.getNext(HadoopRDD.scala:188)
org.apache.spark.util.NextIterator.hasNext(NextIterator.scala:71)
org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:39)
scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
org.apache.spark.sql.columnar.InMemoryRelation$$anonfun$1$$anon$1.hasNext(InMemoryColumnarTableScan.scala:74)
org.apache.spark.storage.MemoryStore.unrollSafely(MemoryStore.scala:235)
org.apache.spark.CacheManager.putInBlockManager(CacheManager.scala:163)
org.apache.spark.CacheManager.getOrCompute(CacheManager.scala:70)
org.apache.spark.rdd.RDD.iterator(RDD.scala:227)
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35)
org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:262)
org.apache.spark.rdd.RDD.iterator(RDD.scala:229)
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35)
org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:262)
org.apache.spark.rdd.RDD.iterator(RDD.scala:229)
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35)
org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:262)
org.apache.spark.rdd.RDD.iterator(RDD.scala:229)
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35)
org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:262)
org.apache.spark.rdd.RDD.iterator(RDD.scala:229)
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35)
org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:262)
org.apache.spark.rdd.RDD.iterator(RDD.scala:229)
org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:68)
org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:41)
org.apache.spark.scheduler.Task.run(Task.scala:54)
org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:177)
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
java.lang.Thread.run(Thread.java:745)
2014-09-23 09:27:49,152 WARN org.apache.spark.scheduler.TaskSetManager: Lost task 2.0 in stage 1.0 (TID 2, cl.local): org.apache.hadoop.hive.serde2.avro.BadSchemaException:
org.apache.hadoop.hive.serde2.avro.AvroSerDe.deserialize(AvroSerDe.java:91)
org.apache.spark.sql.hive.HadoopTableReader$$anonfun$fillObject$1.apply(TableReader.scala:279)
org.apache.spark.sql.hive.HadoopTableReader$$anonfun$fillObject$1.apply(TableReader.scala:278)
scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
org.apache.spark.sql.columnar.InMemoryRelation$$anonfun$1$$anon$1.next(InMemoryColumnarTableScan.scala:62)
org.apache.spark.sql.columnar.InMemoryRelation$$anonfun$1$$anon$1.next(InMemoryColumnarTableScan.scala:50)
org.apache.spark.storage.MemoryStore.unrollSafely(MemoryStore.scala:236)
org.apache.spark.CacheManager.putInBlockManager(CacheManager.scala:163)
org.apache.spark.CacheManager.getOrCompute(CacheManager.scala:70)
org.apache.spark.rdd.RDD.iterator(RDD.scala:227)
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35)
org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:262)
org.apache.spark.rdd.RDD.iterator(RDD.scala:229)
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35)
org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:262)
org.apache.spark.rdd.RDD.iterator(RDD.scala:229)
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35)
org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:262)
org.apache.spark.rdd.RDD.iterator(RDD.scala:229)
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35)
org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:262)
org.apache.spark.rdd.RDD.iterator(RDD.scala:229)
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35)
org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:262)
org.apache.spark.rdd.RDD.iterator(RDD.scala:229)
org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:68)
org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:41)
org.apache.spark.scheduler.Task.run(Task.scala:54)
org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:177)
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
java.lang.Thread.run(Thread.java:745)
I would note that Spark Sql works perfectly for me on non-avro hive tables.
Thanks.
________________________________
This message is confidential and is for the sole use of the intended recipient(s). It may also be privileged or otherwise protected by copyright or other legal rules. If you have received it by mistake please let us know by reply email and delete it from your system. It is prohibited to copy this message or disclose its content to anyone. Any confidentiality or privilege is not waived or lost by any mistaken delivery or unauthorized disclosure of the message. All messages sent to and from Agoda may be monitored to ensure compliance with company policies, to protect the company's interests and to remove potential malware. Electronic messages may be intercepted, amended, lost or deleted, or contain viruses.
Re: Exception with SparkSql and Avro
Posted by "Zalzberg, Idan (Agoda)" <Id...@agoda.com>.
Thanks,
I didn't create the tables myself as I have no control over that process.
However these tables are read just fund using the Jdbc connection to the hiveserver2 so it should be possible
On Sep 24, 2014 12:48 AM, Michael Armbrust <mi...@databricks.com> wrote:
Can you show me the DDL you are using? Here is an example of a way I got the avro serde to work: https://github.com/apache/spark/blob/master/sql/hive/src/main/scala/org/apache/spark/sql/hive/TestHive.scala#L246
Also, this isn't ready for primetime yet, but a quick plug for some ongoing work: https://github.com/apache/spark/pull/2475
On Mon, Sep 22, 2014 at 10:07 PM, Zalzberg, Idan (Agoda) <Id...@agoda.com>> wrote:
Hello,
I am trying to read a hive table that is stored in Avro DEFLATE files.
something simple like “SELECT * FROM X LIMIT 10”
I get 2 exceptions in the logs:
2014-09-23 09:27:50,157 WARN org.apache.spark.scheduler.TaskSetManager: Lost task 10.0 in stage 1.0 (TID 10, cl.local): org.apache.avro.AvroTypeException: Found com.a.bi.core.model.xxx.yyy, expecting org.apache.hadoop.hive.CannotDetermineSchemaSentinel, missing required field ERROR_ERROR_ERROR_ERROR_ERROR_ERROR_ERROR
org.apache.avro.io.ResolvingDecoder.doAction(ResolvingDecoder.java:231)
org.apache.avro.io.parsing.Parser.advance(Parser.java:88)
org.apache.avro.io.ResolvingDecoder.readFieldOrder(ResolvingDecoder.java:127)
org.apache.avro.generic.GenericDatumReader.readRecord(GenericDatumReader.java:176)
org.apache.avro.generic.GenericDatumReader.read(GenericDatumReader.java:151)
org.apache.avro.generic.GenericDatumReader.read(GenericDatumReader.java:142)
org.apache.avro.file.DataFileStream.next(DataFileStream.java:233)
org.apache.avro.file.DataFileStream.next(DataFileStream.java:220)
org.apache.hadoop.hive.ql.io.avro.AvroGenericRecordReader.next(AvroGenericRecordReader.java:149)
org.apache.hadoop.hive.ql.io.avro.AvroGenericRecordReader.next(AvroGenericRecordReader.java:52)
org.apache.spark.rdd.HadoopRDD$$anon$1.getNext(HadoopRDD.scala:219)
org.apache.spark.rdd.HadoopRDD$$anon$1.getNext(HadoopRDD.scala:188)
org.apache.spark.util.NextIterator.hasNext(NextIterator.scala:71)
org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:39)
scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
org.apache.spark.sql.columnar.InMemoryRelation$$anonfun$1$$anon$1.hasNext(InMemoryColumnarTableScan.scala:74)
org.apache.spark.storage.MemoryStore.unrollSafely(MemoryStore.scala:235)
org.apache.spark.CacheManager.putInBlockManager(CacheManager.scala:163)
org.apache.spark.CacheManager.getOrCompute(CacheManager.scala:70)
org.apache.spark.rdd.RDD.iterator(RDD.scala:227)
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35)
org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:262)
org.apache.spark.rdd.RDD.iterator(RDD.scala:229)
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35)
org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:262)
org.apache.spark.rdd.RDD.iterator(RDD.scala:229)
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35)
org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:262)
org.apache.spark.rdd.RDD.iterator(RDD.scala:229)
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35)
org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:262)
org.apache.spark.rdd.RDD.iterator(RDD.scala:229)
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35)
org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:262)
org.apache.spark.rdd.RDD.iterator(RDD.scala:229)
org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:68)
org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:41)
org.apache.spark.scheduler.Task.run(Task.scala:54)
org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:177)
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
java.lang.Thread.run(Thread.java:745)
2014-09-23 09:27:49,152 WARN org.apache.spark.scheduler.TaskSetManager: Lost task 2.0 in stage 1.0 (TID 2, cl.local): org.apache.hadoop.hive.serde2.avro.BadSchemaException:
org.apache.hadoop.hive.serde2.avro.AvroSerDe.deserialize(AvroSerDe.java:91)
org.apache.spark.sql.hive.HadoopTableReader$$anonfun$fillObject$1.apply(TableReader.scala:279)
org.apache.spark.sql.hive.HadoopTableReader$$anonfun$fillObject$1.apply(TableReader.scala:278)
scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
org.apache.spark.sql.columnar.InMemoryRelation$$anonfun$1$$anon$1.next(InMemoryColumnarTableScan.scala:62)
org.apache.spark.sql.columnar.InMemoryRelation$$anonfun$1$$anon$1.next(InMemoryColumnarTableScan.scala:50)
org.apache.spark.storage.MemoryStore.unrollSafely(MemoryStore.scala:236)
org.apache.spark.CacheManager.putInBlockManager(CacheManager.scala:163)
org.apache.spark.CacheManager.getOrCompute(CacheManager.scala:70)
org.apache.spark.rdd.RDD.iterator(RDD.scala:227)
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35)
org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:262)
org.apache.spark.rdd.RDD.iterator(RDD.scala:229)
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35)
org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:262)
org.apache.spark.rdd.RDD.iterator(RDD.scala:229)
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35)
org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:262)
org.apache.spark.rdd.RDD.iterator(RDD.scala:229)
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35)
org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:262)
org.apache.spark.rdd.RDD.iterator(RDD.scala:229)
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35)
org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:262)
org.apache.spark.rdd.RDD.iterator(RDD.scala:229)
org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:68)
org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:41)
org.apache.spark.scheduler.Task.run(Task.scala:54)
org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:177)
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
java.lang.Thread.run(Thread.java:745)
I would note that Spark Sql works perfectly for me on non-avro hive tables.
Thanks.
________________________________
This message is confidential and is for the sole use of the intended recipient(s). It may also be privileged or otherwise protected by copyright or other legal rules. If you have received it by mistake please let us know by reply email and delete it from your system. It is prohibited to copy this message or disclose its content to anyone. Any confidentiality or privilege is not waived or lost by any mistaken delivery or unauthorized disclosure of the message. All messages sent to and from Agoda may be monitored to ensure compliance with company policies, to protect the company's interests and to remove potential malware. Electronic messages may be intercepted, amended, lost or deleted, or contain viruses.
---------------------------------------------------------------------
To unsubscribe, e-mail: user-unsubscribe@spark.apache.org
For additional commands, e-mail: user-help@spark.apache.org
Re: Exception with SparkSql and Avro
Posted by Michael Armbrust <mi...@databricks.com>.
Can you show me the DDL you are using? Here is an example of a way I got
the avro serde to work:
https://github.com/apache/spark/blob/master/sql/hive/src/main/scala/org/apache/spark/sql/hive/TestHive.scala#L246
Also, this isn't ready for primetime yet, but a quick plug for some ongoing
work: https://github.com/apache/spark/pull/2475
On Mon, Sep 22, 2014 at 10:07 PM, Zalzberg, Idan (Agoda) <
Idan.Zalzberg@agoda.com> wrote:
> Hello,
>
> I am trying to read a hive table that is stored in Avro DEFLATE files.
> something simple like “SELECT * FROM X LIMIT 10”
>
> I get 2 exceptions in the logs:
>
>
>
> 2014-09-23 09:27:50,157 WARN org.apache.spark.scheduler.TaskSetManager: Lost task 10.0 in stage 1.0 (TID 10, cl.local): org.apache.avro.AvroTypeException: Found com.a.bi.core.model.xxx.yyy, expecting org.apache.hadoop.hive.CannotDetermineSchemaSentinel, missing required field ERROR_ERROR_ERROR_ERROR_ERROR_ERROR_ERROR
>
> org.apache.avro.io.ResolvingDecoder.doAction(ResolvingDecoder.java:231)
>
> org.apache.avro.io.parsing.Parser.advance(Parser.java:88)
>
> org.apache.avro.io.ResolvingDecoder.readFieldOrder(ResolvingDecoder.java:127)
>
> org.apache.avro.generic.GenericDatumReader.readRecord(GenericDatumReader.java:176)
>
> org.apache.avro.generic.GenericDatumReader.read(GenericDatumReader.java:151)
>
> org.apache.avro.generic.GenericDatumReader.read(GenericDatumReader.java:142)
>
> org.apache.avro.file.DataFileStream.next(DataFileStream.java:233)
>
> org.apache.avro.file.DataFileStream.next(DataFileStream.java:220)
>
> org.apache.hadoop.hive.ql.io.avro.AvroGenericRecordReader.next(AvroGenericRecordReader.java:149)
>
> org.apache.hadoop.hive.ql.io.avro.AvroGenericRecordReader.next(AvroGenericRecordReader.java:52)
>
> org.apache.spark.rdd.HadoopRDD$$anon$1.getNext(HadoopRDD.scala:219)
>
> org.apache.spark.rdd.HadoopRDD$$anon$1.getNext(HadoopRDD.scala:188)
>
> org.apache.spark.util.NextIterator.hasNext(NextIterator.scala:71)
>
> org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:39)
>
> scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
>
> scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
>
> org.apache.spark.sql.columnar.InMemoryRelation$$anonfun$1$$anon$1.hasNext(InMemoryColumnarTableScan.scala:74)
>
> org.apache.spark.storage.MemoryStore.unrollSafely(MemoryStore.scala:235)
>
> org.apache.spark.CacheManager.putInBlockManager(CacheManager.scala:163)
>
> org.apache.spark.CacheManager.getOrCompute(CacheManager.scala:70)
>
> org.apache.spark.rdd.RDD.iterator(RDD.scala:227)
>
> org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35)
>
> org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:262)
>
> org.apache.spark.rdd.RDD.iterator(RDD.scala:229)
>
> org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35)
>
> org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:262)
>
> org.apache.spark.rdd.RDD.iterator(RDD.scala:229)
>
> org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35)
>
> org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:262)
>
> org.apache.spark.rdd.RDD.iterator(RDD.scala:229)
>
> org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35)
>
> org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:262)
>
> org.apache.spark.rdd.RDD.iterator(RDD.scala:229)
>
> org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35)
>
> org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:262)
>
> org.apache.spark.rdd.RDD.iterator(RDD.scala:229)
>
> org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:68)
>
> org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:41)
>
> org.apache.spark.scheduler.Task.run(Task.scala:54)
>
> org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:177)
>
> java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
>
> java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
>
> java.lang.Thread.run(Thread.java:745)
>
>
>
>
>
>
>
> 2014-09-23 09:27:49,152 WARN org.apache.spark.scheduler.TaskSetManager:
> Lost task 2.0 in stage 1.0 (TID 2, cl.local):
> org.apache.hadoop.hive.serde2.avro.BadSchemaException:
>
> org.apache.hadoop.hive.serde2.avro.AvroSerDe.deserialize(AvroSerDe.java:91)
>
>
> org.apache.spark.sql.hive.HadoopTableReader$$anonfun$fillObject$1.apply(TableReader.scala:279)
>
>
> org.apache.spark.sql.hive.HadoopTableReader$$anonfun$fillObject$1.apply(TableReader.scala:278)
>
> scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
>
>
> org.apache.spark.sql.columnar.InMemoryRelation$$anonfun$1$$anon$1.next(InMemoryColumnarTableScan.scala:62)
>
>
> org.apache.spark.sql.columnar.InMemoryRelation$$anonfun$1$$anon$1.next(InMemoryColumnarTableScan.scala:50)
>
> org.apache.spark.storage.MemoryStore.unrollSafely(MemoryStore.scala:236)
>
> org.apache.spark.CacheManager.putInBlockManager(CacheManager.scala:163)
>
> org.apache.spark.CacheManager.getOrCompute(CacheManager.scala:70)
>
> org.apache.spark.rdd.RDD.iterator(RDD.scala:227)
>
> org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35)
>
> org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:262)
>
> org.apache.spark.rdd.RDD.iterator(RDD.scala:229)
>
> org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35)
>
> org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:262)
>
> org.apache.spark.rdd.RDD.iterator(RDD.scala:229)
>
> org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35)
>
> org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:262)
>
> org.apache.spark.rdd.RDD.iterator(RDD.scala:229)
>
> org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35)
>
> org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:262)
>
> org.apache.spark.rdd.RDD.iterator(RDD.scala:229)
>
> org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35)
>
> org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:262)
>
> org.apache.spark.rdd.RDD.iterator(RDD.scala:229)
>
> org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:68)
>
> org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:41)
>
> org.apache.spark.scheduler.Task.run(Task.scala:54)
>
> org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:177)
>
>
> java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
>
>
> java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
>
> java.lang.Thread.run(Thread.java:745)
>
>
>
>
>
>
>
> I would note that Spark Sql works perfectly for me on non-avro hive tables.
>
>
>
> Thanks.
>
> ------------------------------
> This message is confidential and is for the sole use of the intended
> recipient(s). It may also be privileged or otherwise protected by copyright
> or other legal rules. If you have received it by mistake please let us know
> by reply email and delete it from your system. It is prohibited to copy
> this message or disclose its content to anyone. Any confidentiality or
> privilege is not waived or lost by any mistaken delivery or unauthorized
> disclosure of the message. All messages sent to and from Agoda may be
> monitored to ensure compliance with company policies, to protect the
> company's interests and to remove potential malware. Electronic messages
> may be intercepted, amended, lost or deleted, or contain viruses.
>