pin_zhang created SPARK-7480:
--------------------------------
Summary: Get exception when DataFrame saveAsTable and run sql on
the same table at the same time
Key: SPARK-7480
URL: https://issues.apache.org/jira/browse/SPARK-7480
Project: Spark
Issue Type: Bug
Components: SQL
Affects Versions: 1.3.1, 1.3.0
Reporter: pin_zhang
There is a case
1) In the main thread call DataFrame.saveAsTable(table,
SaveMode.Overwrite); save json rdd to hive table
2) In another thread run sql the table simultaneously
You can see many exceptions to indicate the table not exit or table is not
complete.
Does Spark SQL support such usage?
Thanks
[Main Thread]
DataFrame df = hiveContext_.jsonFile("test.json");
String table = "UNIT_TEST";
while (true) {
df = hiveContext_.jsonFile("test.json");
df.saveAsTable(table, SaveMode.Overwrite);
System.out.println(new Timestamp(System.currentTimeMillis()) + " [
"+Thread.currentThread().getName()
+ "] override table");
try {
Thread.sleep(3000);
} catch (InterruptedException e) {
e.printStackTrace();
}
}
[Query Thread]
DataFrame query = hiveContext_.sql("select * from UNIT_TEST");
Row[] rows = query.collect();
System.out.println(new Timestamp(System.currentTimeMillis()) +
" [ "+ Thread.currentThread().getName()
+ "] [query result count:] " + rows.length);
[Exceptions in log]
15/05/08 16:05:49 ERROR Hive: NoSuchObjectException(message:default.unit_test
table not found)
at
org.apache.hadoop.hive.metastore.HiveMetaStore$HMSHandler.get_table(HiveMetaStore.java:1560)
at sun.reflect.GeneratedMethodAccessor22.invoke(Unknown Source)
at
sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:601)
at
org.apache.hadoop.hive.metastore.RetryingHMSHandler.invoke(RetryingHMSHandler.java:105)
at com.sun.proxy.$Proxy20.get_table(Unknown Source)
at
org.apache.hadoop.hive.metastore.HiveMetaStoreClient.getTable(HiveMetaStoreClient.java:997)
at sun.reflect.GeneratedMethodAccessor23.invoke(Unknown Source)
at
sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:601)
at
org.apache.hadoop.hive.metastore.RetryingMetaStoreClient.invoke(RetryingMetaStoreClient.java:89)
at com.sun.proxy.$Proxy21.getTable(Unknown Source)
at org.apache.hadoop.hive.ql.metadata.Hive.getTable(Hive.java:976)
at org.apache.hadoop.hive.ql.metadata.Hive.getTable(Hive.java:950)
at
org.apache.spark.sql.hive.HiveMetastoreCatalog.lookupRelation(HiveMetastoreCatalog.scala:201)
at
org.apache.spark.sql.hive.HiveContext$$anon$2.org$apache$spark$sql$catalyst$analysis$OverrideCatalog$$super$lookupRelation(HiveContext.scala:262)
at
org.apache.spark.sql.catalyst.analysis.OverrideCatalog$$anonfun$lookupRelation$3.apply(Catalog.scala:161)
at
org.apache.spark.sql.catalyst.analysis.OverrideCatalog$$anonfun$lookupRelation$3.apply(Catalog.scala:161)
at scala.Option.getOrElse(Option.scala:120)
at
org.apache.spark.sql.catalyst.analysis.OverrideCatalog$class.lookupRelation(Catalog.scala:161)
at
org.apache.spark.sql.hive.HiveContext$$anon$2.lookupRelation(HiveContext.scala:262)
at
org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveRelations$.getTable(Analyzer.scala:174)
at
org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveRelations$$anonfun$apply$6.applyOrElse(Analyzer.scala:186)
at
org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveRelations$$anonfun$apply$6.applyOrElse(Analyzer.scala:181)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$3.apply(TreeNode.scala:188)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$3.apply(TreeNode.scala:188)
at
org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:51)
at
org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:187)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$4.apply(TreeNode.scala:208)
at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
at scala.collection.Iterator$class.foreach(Iterator.scala:727)
at scala.collection.AbstractIterator.foreach(Iterator.scala:1157)
at
scala.collection.generic.Growable$class.$plus$plus$eq(Growable.scala:48)
at
scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:103)
at
scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:47)
at scala.collection.TraversableOnce$class.to(TraversableOnce.scala:273)
at scala.collection.AbstractIterator.to(Iterator.scala:1157)
at
scala.collection.TraversableOnce$class.toBuffer(TraversableOnce.scala:265)
at scala.collection.AbstractIterator.toBuffer(Iterator.scala:1157)
at
scala.collection.TraversableOnce$class.toArray(TraversableOnce.scala:252)
at scala.collection.AbstractIterator.toArray(Iterator.scala:1157)
at
org.apache.spark.sql.catalyst.trees.TreeNode.transformChildrenDown(TreeNode.scala:238)
at
org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:193)
at
org.apache.spark.sql.catalyst.trees.TreeNode.transform(TreeNode.scala:178)
at
org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveRelations$.apply(Analyzer.scala:181)
at
org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveRelations$.apply(Analyzer.scala:171)
at
org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$apply$1$$anonfun$apply$2.apply(RuleExecutor.scala:61)
at
org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$apply$1$$anonfun$apply$2.apply(RuleExecutor.scala:59)
at
scala.collection.LinearSeqOptimized$class.foldLeft(LinearSeqOptimized.scala:111)
at scala.collection.immutable.List.foldLeft(List.scala:84)
at
org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$apply$1.apply(RuleExecutor.scala:59)
at
org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$apply$1.apply(RuleExecutor.scala:51)
at scala.collection.immutable.List.foreach(List.scala:318)
at
org.apache.spark.sql.catalyst.rules.RuleExecutor.apply(RuleExecutor.scala:51)
at
org.apache.spark.sql.SQLContext$QueryExecution.analyzed$lzycompute(SQLContext.scala:1082)
at
org.apache.spark.sql.SQLContext$QueryExecution.analyzed(SQLContext.scala:1082)
at
org.apache.spark.sql.SQLContext$QueryExecution.assertAnalyzed(SQLContext.scala:1080)
at org.apache.spark.sql.DataFrame.<init>(DataFrame.scala:133)
at org.apache.spark.sql.DataFrame$.apply(DataFrame.scala:51)
at org.apache.spark.sql.hive.HiveContext.sql(HiveContext.scala:101)
at
spark.streaming.test.SparkHiveTest$QueryWorker.query(SparkHiveTest.java:114)
at
spark.streaming.test.SparkHiveTest$QueryWorker.run(SparkHiveTest.java:108)
at
java.util.concurrent.Executors$RunnableAdapter.call(Executors.java:471)
at java.util.concurrent.FutureTask$Sync.innerRun(FutureTask.java:334)
at java.util.concurrent.FutureTask.run(FutureTask.java:166)
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:722)
15/05/08 16:06:29 ERROR Executor: Exception in task 0.0 in stage 1457.0 (TID
2551)
java.io.FileNotFoundException: File
file:/user/hive/warehouse/unit_test/part-r-00002.parquet does not exist
at
org.apache.hadoop.fs.RawLocalFileSystem.deprecatedGetFileStatus(RawLocalFileSystem.java:511)
at
org.apache.hadoop.fs.RawLocalFileSystem.getFileLinkStatusInternal(RawLocalFileSystem.java:724)
at
org.apache.hadoop.fs.RawLocalFileSystem.getFileStatus(RawLocalFileSystem.java:501)
at
org.apache.hadoop.fs.FilterFileSystem.getFileStatus(FilterFileSystem.java:397)
at
parquet.hadoop.ParquetFileReader.readFooter(ParquetFileReader.java:381)
at
parquet.hadoop.ParquetRecordReader.initializeInternalReader(ParquetRecordReader.java:155)
at
parquet.hadoop.ParquetRecordReader.initialize(ParquetRecordReader.java:138)
at
org.apache.spark.rdd.NewHadoopRDD$$anon$1.<init>(NewHadoopRDD.scala:133)
at org.apache.spark.rdd.NewHadoopRDD.compute(NewHadoopRDD.scala:104)
at org.apache.spark.rdd.NewHadoopRDD.compute(NewHadoopRDD.scala:66)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:277)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:244)
at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:277)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:244)
at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:277)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:244)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:61)
at org.apache.spark.scheduler.Task.run(Task.scala:64)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:203)
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:722)
--
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
