[
https://issues.apache.org/jira/browse/SPARK-9976?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15106372#comment-15106372
]
ocean commented on SPARK-9976:
------------------------------
Now I am migrating from HIVE to Sparksql. Now I encountered two problem.
first one:
the temporary udf function which extends GenericUDF can create, and you can
describe this udf function.
but when I use this function, some exception occurs.
I don't know where the problem is.
spark version: apache 1.5.1 /standalone mode/CLI
spark-sql> describe function devicemodel;
Function: deviceModel
Class: td.enterprise.hive.udfs.ConvertDeviceModel
Usage: deviceModel(expr) - return other information
Time taken: 0.041 seconds, Fetched 3 row(s)
spark-sql>
> select devicemodel(p.mobile_id, 'type', 'MOBILE_TYPE') as
mobile_type from analytics_device_profile_zh3 p limit 1;
16/01/19 15:19:46 ERROR Executor: Exception in task 0.0 in stage 14.0 (TID 15)
com.esotericsoftware.kryo.KryoException: Buffer underflow.
Serialization trace:
mobileAttributeCahceMap (td.enterprise.hive.udfs.ConvertDeviceModel)
at com.esotericsoftware.kryo.io.Input.require(Input.java:156)
at com.esotericsoftware.kryo.io.Input.readAscii_slow(Input.java:580)
at com.esotericsoftware.kryo.io.Input.readAscii(Input.java:558)
at com.esotericsoftware.kryo.io.Input.readString(Input.java:436)
at
com.esotericsoftware.kryo.serializers.DefaultSerializers$StringSerializer.read(DefaultSerializers.java:157)
at
com.esotericsoftware.kryo.serializers.DefaultSerializers$StringSerializer.read(DefaultSerializers.java:146)
at com.esotericsoftware.kryo.Kryo.readClassAndObject(Kryo.java:729)
at
com.esotericsoftware.kryo.serializers.MapSerializer.read(MapSerializer.java:134)
at
com.esotericsoftware.kryo.serializers.MapSerializer.read(MapSerializer.java:17)
at com.esotericsoftware.kryo.Kryo.readClassAndObject(Kryo.java:729)
at
com.esotericsoftware.kryo.serializers.MapSerializer.read(MapSerializer.java:134)
at
com.esotericsoftware.kryo.serializers.MapSerializer.read(MapSerializer.java:17)
at com.esotericsoftware.kryo.Kryo.readObject(Kryo.java:648)
at
com.esotericsoftware.kryo.serializers.FieldSerializer$ObjectField.read(FieldSerializer.java:605)
at
com.esotericsoftware.kryo.serializers.FieldSerializer.read(FieldSerializer.java:221)
at com.esotericsoftware.kryo.Kryo.readObject(Kryo.java:626)
at
org.apache.spark.sql.hive.HiveShim$HiveFunctionWrapper.deserializeObjectByKryo(HiveShim.scala:134)
at
org.apache.spark.sql.hive.HiveShim$HiveFunctionWrapper.deserializePlan(HiveShim.scala:150)
at
org.apache.spark.sql.hive.HiveShim$HiveFunctionWrapper.readExternal(HiveShim.scala:191)
at
java.io.ObjectInputStream.readExternalData(ObjectInputStream.java:1837)
at
java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1796)
at java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1350)
at
java.io.ObjectInputStream.defaultReadFields(ObjectInputStream.java:1990)
at java.io.ObjectInputStream.readSerialData(ObjectInputStream.java:1915)
at
java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1798)
at java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1350)
at
java.io.ObjectInputStream.defaultReadFields(ObjectInputStream.java:1990)
at java.io.ObjectInputStream.readSerialData(ObjectInputStream.java:1915)
at
java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1798)
at java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1350)
at java.io.ObjectInputStream.readArray(ObjectInputStream.java:1706)
at java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1344)
at
java.io.ObjectInputStream.defaultReadFields(ObjectInputStream.java:1990)
at java.io.ObjectInputStream.readSerialData(ObjectInputStream.java:1915)
at
java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1798)
at java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1350)
at
java.io.ObjectInputStream.defaultReadFields(ObjectInputStream.java:1990)
at java.io.ObjectInputStream.readSerialData(ObjectInputStream.java:1915)
at
java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1798)
at java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1350)
at
java.io.ObjectInputStream.defaultReadFields(ObjectInputStream.java:1990)
at java.io.ObjectInputStream.readSerialData(ObjectInputStream.java:1915)
at
java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1798)
at java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1350)
at
java.io.ObjectInputStream.defaultReadFields(ObjectInputStream.java:1990)
at java.io.ObjectInputStream.readSerialData(ObjectInputStream.java:1915)
at
java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1798)
at java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1350)
at
java.io.ObjectInputStream.defaultReadFields(ObjectInputStream.java:1990)
at java.io.ObjectInputStream.readSerialData(ObjectInputStream.java:1915)
at
java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1798)
at java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1350)
at
java.io.ObjectInputStream.defaultReadFields(ObjectInputStream.java:1990)
at java.io.ObjectInputStream.readSerialData(ObjectInputStream.java:1915)
at
java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1798)
at java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1350)
at java.io.ObjectInputStream.readObject(ObjectInputStream.java:370)
at scala.collection.immutable.$colon$colon.readObject(List.scala:362)
at sun.reflect.GeneratedMethodAccessor45.invoke(Unknown Source)
at
sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:606)
at
java.io.ObjectStreamClass.invokeReadObject(ObjectStreamClass.java:1017)
at java.io.ObjectInputStream.readSerialData(ObjectInputStream.java:1893)
at
java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1798)
at java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1350)
at
java.io.ObjectInputStream.defaultReadFields(ObjectInputStream.java:1990)
at java.io.ObjectInputStream.readSerialData(ObjectInputStream.java:1915)
at
java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1798)
at java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1350)
at
java.io.ObjectInputStream.defaultReadFields(ObjectInputStream.java:1990)
at java.io.ObjectInputStream.readSerialData(ObjectInputStream.java:1915)
at
java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1798)
at java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1350)
at java.io.ObjectInputStream.readObject(ObjectInputStream.java:370)
at
org.apache.spark.serializer.JavaDeserializationStream.readObject(JavaSerializer.scala:72)
at
org.apache.spark.serializer.JavaSerializerInstance.deserialize(JavaSerializer.scala:98)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:61)
at org.apache.spark.scheduler.Task.run(Task.scala:88)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214)
at
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:745)
16/01/19 15:19:46 WARN TaskSetManager: Lost task 0.0 in stage 14.0 (TID 15,
localhost): com.esotericsoftware.kryo.KryoException: Buffer underflow.
Serialization trace:
mobileAttributeCahceMap (td.enterprise.hive.udfs.ConvertDeviceModel)
at com.esotericsoftware.kryo.io.Input.require(Input.java:156)
at com.esotericsoftware.kryo.io.Input.readAscii_slow(Input.java:580)
at com.esotericsoftware.kryo.io.Input.readAscii(Input.java:558)
at com.esotericsoftware.kryo.io.Input.readString(Input.java:436)
> create function do not work
> ---------------------------
>
> Key: SPARK-9976
> URL: https://issues.apache.org/jira/browse/SPARK-9976
> Project: Spark
> Issue Type: Bug
> Components: SQL
> Affects Versions: 1.4.0, 1.4.1, 1.5.0
> Environment: spark 1.4.1 yarn 2.2.0
> Reporter: cen yuhai
>
> I use beeline to connect to ThriftServer, but add jar can not work, so I use
> create function , see the link below.
> http://www.cloudera.com/content/cloudera/en/documentation/core/v5-3-x/topics/cm_mc_hive_udf.html
> I do as blow:
> {code}
> create function gdecodeorder as 'com.hive.udf.GOrderDecode' USING JAR
> 'hdfs://mycluster/user/spark/lib/gorderdecode.jar';
> {code}
> It returns Ok, and I connect to the metastore, I see records in table FUNCS.
> {code}
> select gdecodeorder(t1) from tableX limit 1;
> {code}
> It returns error 'Couldn't find function default.gdecodeorder'
> This is the Exception
> {code}
> 15/08/14 14:53:51 ERROR UserGroupInformation: PriviledgedActionException
> as:xiaoju (auth:SIMPLE) cause:org.apache.hive.service.cli.HiveSQLException:
> java.lang.RuntimeException: Couldn't find function default.gdecodeorder
> 15/08/14 15:04:47 ERROR RetryingHMSHandler:
> MetaException(message:NoSuchObjectException(message:Function
> default.t_gdecodeorder does not exist))
> at
> org.apache.hadoop.hive.metastore.HiveMetaStore$HMSHandler.newMetaException(HiveMetaStore.java:4613)
> at
> org.apache.hadoop.hive.metastore.HiveMetaStore$HMSHandler.get_function(HiveMetaStore.java:4740)
> at sun.reflect.GeneratedMethodAccessor57.invoke(Unknown Source)
> at
> sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
> at java.lang.reflect.Method.invoke(Method.java:606)
> at
> org.apache.hadoop.hive.metastore.RetryingHMSHandler.invoke(RetryingHMSHandler.java:105)
> at com.sun.proxy.$Proxy21.get_function(Unknown Source)
> at
> org.apache.hadoop.hive.metastore.HiveMetaStoreClient.getFunction(HiveMetaStoreClient.java:1721)
> at sun.reflect.GeneratedMethodAccessor56.invoke(Unknown Source)
> at
> sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
> at java.lang.reflect.Method.invoke(Method.java:606)
> at
> org.apache.hadoop.hive.metastore.RetryingMetaStoreClient.invoke(RetryingMetaStoreClient.java:89)
> at com.sun.proxy.$Proxy22.getFunction(Unknown Source)
> at org.apache.hadoop.hive.ql.metadata.Hive.getFunction(Hive.java:2662)
> at
> org.apache.hadoop.hive.ql.exec.FunctionRegistry.getFunctionInfoFromMetastore(FunctionRegistry.java:546)
> at
> org.apache.hadoop.hive.ql.exec.FunctionRegistry.getQualifiedFunctionInfo(FunctionRegistry.java:579)
> at
> org.apache.hadoop.hive.ql.exec.FunctionRegistry.getFunctionInfo(FunctionRegistry.java:645)
> at
> org.apache.hadoop.hive.ql.exec.FunctionRegistry.getFunctionInfo(FunctionRegistry.java:652)
> at
> org.apache.spark.sql.hive.HiveFunctionRegistry.lookupFunction(hiveUdfs.scala:54)
> at
> org.apache.spark.sql.hive.HiveContext$$anon$3.org$apache$spark$sql$catalyst$analysis$OverrideFunctionRegistry$$super$lookupFunction(HiveContext.scala:376)
> at
> org.apache.spark.sql.catalyst.analysis.OverrideFunctionRegistry$$anonfun$lookupFunction$2.apply(FunctionRegistry.scala:44)
> at
> org.apache.spark.sql.catalyst.analysis.OverrideFunctionRegistry$$anonfun$lookupFunction$2.apply(FunctionRegistry.scala:44)
> at scala.Option.getOrElse(Option.scala:120)
> at
> org.apache.spark.sql.catalyst.analysis.OverrideFunctionRegistry$class.lookupFunction(FunctionRegistry.scala:44)
> at
> org.apache.spark.sql.hive.HiveContext$$anon$3.lookupFunction(HiveContext.scala:376)
> at
> org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveFunctions$$anonfun$apply$13$$anonfun$applyOrElse$5.applyOrElse(Analyzer.scala:465)
> at
> org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveFunctions$$anonfun$apply$13$$anonfun$applyOrElse$5.applyOrElse(Analyzer.scala:463)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$3.apply(TreeNode.scala:222)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$3.apply(TreeNode.scala:222)
> at
> org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:51)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:221)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$4.apply(TreeNode.scala:242)
> at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
> at scala.collection.Iterator$class.foreach(Iterator.scala:727)
> at scala.collection.AbstractIterator.foreach(Iterator.scala:1157)
> at
> scala.collection.generic.Growable$class.$plus$plus$eq(Growable.scala:48)
> at
> scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:103)
> at
> scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:47)
> at
> scala.collection.TraversableOnce$class.to(TraversableOnce.scala:273)
> at scala.collection.AbstractIterator.to(Iterator.scala:1157)
> at
> scala.collection.TraversableOnce$class.toBuffer(TraversableOnce.scala:265)
> at scala.collection.AbstractIterator.toBuffer(Iterator.scala:1157)
> at
> scala.collection.TraversableOnce$class.toArray(TraversableOnce.scala:252)
> at scala.collection.AbstractIterator.toArray(Iterator.scala:1157)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode.transformChildrenDown(TreeNode.scala:272)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:227)
> at
> org.apache.spark.sql.catalyst.plans.QueryPlan.org$apache$spark$sql$catalyst$plans$QueryPlan$$transformExpressionDown$1(QueryPlan.scala:75)
> 15/08/14 15:04:47 ERROR SparkExecuteStatementOperation: Error executing query:
> java.lang.RuntimeException: Couldn't find function gdecodeorder
> at scala.sys.package$.error(package.scala:27)
> at
> org.apache.spark.sql.hive.HiveFunctionRegistry$$anonfun$1.apply(hiveUdfs.scala:55)
> at
> org.apache.spark.sql.hive.HiveFunctionRegistry$$anonfun$1.apply(hiveUdfs.scala:55)
> at scala.Option.getOrElse(Option.scala:120)
> at
> org.apache.spark.sql.hive.HiveFunctionRegistry.lookupFunction(hiveUdfs.scala:54)
> at
> org.apache.spark.sql.hive.HiveContext$$anon$3.org$apache$spark$sql$catalyst$analysis$OverrideFunctionRegistry$$super$lookupFunction(HiveContext.scala:376)
> at
> org.apache.spark.sql.catalyst.analysis.OverrideFunctionRegistry$$anonfun$lookupFunction$2.apply(FunctionRegistry.scala:44)
> at
> org.apache.spark.sql.catalyst.analysis.OverrideFunctionRegistry$$anonfun$lookupFunction$2.apply(FunctionRegistry.scala:44)
> at scala.Option.getOrElse(Option.scala:120)
> at
> org.apache.spark.sql.catalyst.analysis.OverrideFunctionRegistry$class.lookupFunction(FunctionRegistry.scala:44)
> at
> org.apache.spark.sql.hive.HiveContext$$anon$3.lookupFunction(HiveContext.scala:376)
> at
> org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveFunctions$$anonfun$apply$13$$anonfun$applyOrElse$5.applyOrElse(Analyzer.scala:465)
> at
> org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveFunctions$$anonfun$apply$13$$anonfun$applyOrElse$5.applyOrElse(Analyzer.scala:463)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$3.apply(TreeNode.scala:222)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$3.apply(TreeNode.scala:222)
> at
> org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:51)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:221)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$4.apply(TreeNode.scala:242)
> at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
> at scala.collection.Iterator$class.foreach(Iterator.scala:727)
> at scala.collection.AbstractIterator.foreach(Iterator.scala:1157)
> at
> scala.collection.generic.Growable$class.$plus$plus$eq(Growable.scala:48)
> at
> scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:103)
> at
> scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:47)
> at
> scala.collection.TraversableOnce$class.to(TraversableOnce.scala:273)
> at scala.collection.AbstractIterator.to(Iterator.scala:1157)
> at
> scala.collection.TraversableOnce$class.toBuffer(TraversableOnce.scala:265)
> at scala.collection.AbstractIterator.toBuffer(Iterator.scala:1157)
> at
> scala.collection.TraversableOnce$class.toArray(TraversableOnce.scala:252)
> at scala.collection.AbstractIterator.toArray(Iterator.scala:1157)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode.transformChildrenDown(TreeNode.scala:272)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:227)
> at
> org.apache.spark.sql.catalyst.plans.QueryPlan.org$apache$spark$sql$catalyst$plans$QueryPlan$$transformExpressionDown$1(QueryPlan.scala:75)
> at
> org.apache.spark.sql.catalyst.plans.QueryPlan$$anonfun$1$$anonfun$apply$1.apply(QueryPlan.scala:90)
> at
> scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244)
> at
> scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244)
> at
> scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
> at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47)
> at
> scala.collection.TraversableLike$class.map(TraversableLike.scala:244)
> at scala.collection.AbstractTraversable.map(Traversable.scala:105)
> at
> org.apache.spark.sql.catalyst.plans.QueryPlan$$anonfun$1.apply(QueryPlan.scala:89)
> at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
> at scala.collection.Iterator$class.foreach(Iterator.scala:727)
> at scala.collection.AbstractIterator.foreach(Iterator.scala:1157)
> at
> scala.collection.generic.Growable$class.$plus$plus$eq(Growable.scala:48)
> at
> scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:103)
> at
> scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:47)
> at
> scala.collection.TraversableOnce$class.to(TraversableOnce.scala:273)
> at scala.collection.AbstractIterator.to(Iterator.scala:1157)
> at
> scala.collection.TraversableOnce$class.toBuffer(TraversableOnce.scala:265)
> at scala.collection.AbstractIterator.toBuffer(Iterator.scala:1157)
>
> {code}
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org
For additional commands, e-mail: issues-h...@spark.apache.org
