You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@spark.apache.org by "Apache Spark (Jira)" <ji...@apache.org> on 2020/07/21 13:59:00 UTC
[jira] [Assigned] (SPARK-32380) sparksql cannot access hive table
while data in hbase
[ https://issues.apache.org/jira/browse/SPARK-32380?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Apache Spark reassigned SPARK-32380:
------------------------------------
Assignee: Apache Spark
> sparksql cannot access hive table while data in hbase
> -----------------------------------------------------
>
> Key: SPARK-32380
> URL: https://issues.apache.org/jira/browse/SPARK-32380
> Project: Spark
> Issue Type: Bug
> Components: SQL
> Affects Versions: 3.0.0
> Environment: ||component||version||
> |hadoop|2.8.5|
> |hive|2.3.7|
> |spark|3.0.0|
> |hbase|1.4.9|
> Reporter: deyzhong
> Assignee: Apache Spark
> Priority: Major
> Original Estimate: 72h
> Remaining Estimate: 72h
>
> * step1: create hbase table
> {code:java}
> hbase(main):001:0>create 'hbase_test1', 'cf1'
> hbase(main):001:0> put 'hbase_test', 'r1', 'cf1:c1', '123'
> {code}
> * step2: create hive table related to hbase table
>
> {code:java}
> hive>
> CREATE EXTERNAL TABLE `hivetest.hbase_test`(
> `key` string COMMENT '',
> `value` string COMMENT '')
> ROW FORMAT SERDE
> 'org.apache.hadoop.hive.hbase.HBaseSerDe'
> STORED BY
> 'org.apache.hadoop.hive.hbase.HBaseStorageHandler'
> WITH SERDEPROPERTIES (
> 'hbase.columns.mapping'=':key,cf1:v1',
> 'serialization.format'='1')
> TBLPROPERTIES (
> 'hbase.table.name'='hbase_test')
> {code}
> * step3: sparksql query hive table while data in hbase
> {code:java}
> spark-sql --master yarn -e "select * from hivetest.hbase_test"
> {code}
>
> The error log as follow:
> java.io.IOException: Cannot create a record reader because of a previous error. Please look at the previous logs lines from the task's full log for more details.
> at org.apache.hadoop.hbase.mapreduce.TableInputFormatBase.getSplits(TableInputFormatBase.java:270)
> at org.apache.spark.rdd.NewHadoopRDD.getPartitions(NewHadoopRDD.scala:131)
> at org.apache.spark.rdd.RDD.$anonfun$partitions$2(RDD.scala:276)
> at scala.Option.getOrElse(Option.scala:189)
> at org.apache.spark.rdd.RDD.partitions(RDD.scala:272)
> at org.apache.spark.rdd.MapPartitionsRDD.getPartitions(MapPartitionsRDD.scala:49)
> at org.apache.spark.rdd.RDD.$anonfun$partitions$2(RDD.scala:276)
> at scala.Option.getOrElse(Option.scala:189)
> at org.apache.spark.rdd.RDD.partitions(RDD.scala:272)
> at org.apache.spark.rdd.MapPartitionsRDD.getPartitions(MapPartitionsRDD.scala:49)
> at org.apache.spark.rdd.RDD.$anonfun$partitions$2(RDD.scala:276)
> at scala.Option.getOrElse(Option.scala:189)
> at org.apache.spark.rdd.RDD.partitions(RDD.scala:272)
> at org.apache.spark.rdd.MapPartitionsRDD.getPartitions(MapPartitionsRDD.scala:49)
> at org.apache.spark.rdd.RDD.$anonfun$partitions$2(RDD.scala:276)
> at scala.Option.getOrElse(Option.scala:189)
> at org.apache.spark.rdd.RDD.partitions(RDD.scala:272)
> at org.apache.spark.rdd.MapPartitionsRDD.getPartitions(MapPartitionsRDD.scala:49)
> at org.apache.spark.rdd.RDD.$anonfun$partitions$2(RDD.scala:276)
> at scala.Option.getOrElse(Option.scala:189)
> at org.apache.spark.rdd.RDD.partitions(RDD.scala:272)
> at org.apache.spark.SparkContext.runJob(SparkContext.scala:2158)
> at org.apache.spark.rdd.RDD.$anonfun$collect$1(RDD.scala:1004)
> at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
> at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:112)
> at org.apache.spark.rdd.RDD.withScope(RDD.scala:388)
> at org.apache.spark.rdd.RDD.collect(RDD.scala:1003)
> at org.apache.spark.sql.execution.SparkPlan.executeCollect(SparkPlan.scala:385)
> at org.apache.spark.sql.execution.SparkPlan.executeCollectPublic(SparkPlan.scala:412)
> at org.apache.spark.sql.execution.HiveResult$.hiveResultString(HiveResult.scala:58)
> at org.apache.spark.sql.hive.thriftserver.SparkSQLDriver.$anonfun$run$1(SparkSQLDriver.scala:65)
> at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$5(SQLExecution.scala:100)
> at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:160)
> at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:87)
> at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:763)
> at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:64)
> at org.apache.spark.sql.hive.thriftserver.SparkSQLDriver.run(SparkSQLDriver.scala:65)
> at org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.processCmd(SparkSQLCLIDriver.scala:377)
> at org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.$anonfun$processLine$1(SparkSQLCLIDriver.scala:496)
> at scala.collection.Iterator.foreach(Iterator.scala:941)
> at scala.collection.Iterator.foreach$(Iterator.scala:941)
> at scala.collection.AbstractIterator.foreach(Iterator.scala:1429)
> at scala.collection.IterableLike.foreach(IterableLike.scala:74)
> at scala.collection.IterableLike.foreach$(IterableLike.scala:73)
> at scala.collection.AbstractIterable.foreach(Iterable.scala:56)
> at org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.processLine(SparkSQLCLIDriver.scala:490)
> at org.apache.hadoop.hive.cli.CliDriver.processLine(CliDriver.java:336)
> at org.apache.hadoop.hive.cli.CliDriver.processReader(CliDriver.java:474)
> at org.apache.hadoop.hive.cli.CliDriver.processFile(CliDriver.java:490)
> at org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver$.main(SparkSQLCLIDriver.scala:206)
> at org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.main(SparkSQLCLIDriver.scala)
> at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
> at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
> at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
> at java.lang.reflect.Method.invoke(Method.java:498)
> at org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
> at org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:928)
> at org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:180)
> at org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:203)
> at org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:90)
> at org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1007)
> at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1016)
> at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
> Caused by: java.lang.IllegalStateException: The input format instance has not been properly initialized. Ensure you call initializeTable either in your constructor or initialize method
> at org.apache.hadoop.hbase.mapreduce.TableInputFormatBase.getTable(TableInputFormatBase.java:652)
> at org.apache.hadoop.hbase.mapreduce.TableInputFormatBase.getSplits(TableInputFormatBase.java:265)
> ... 62 more
> java.io.IOException: Cannot create a record reader because of a previous error. Please look at the previous logs lines from the task's full log for more details.
> at org.apache.hadoop.hbase.mapreduce.TableInputFormatBase.getSplits(TableInputFormatBase.java:270)
> at org.apache.spark.rdd.NewHadoopRDD.getPartitions(NewHadoopRDD.scala:131)
> at org.apache.spark.rdd.RDD.$anonfun$partitions$2(RDD.scala:276)
> at scala.Option.getOrElse(Option.scala:189)
> at org.apache.spark.rdd.RDD.partitions(RDD.scala:272)
> at org.apache.spark.rdd.MapPartitionsRDD.getPartitions(MapPartitionsRDD.scala:49)
> at org.apache.spark.rdd.RDD.$anonfun$partitions$2(RDD.scala:276)
> at scala.Option.getOrElse(Option.scala:189)
> at org.apache.spark.rdd.RDD.partitions(RDD.scala:272)
> at org.apache.spark.rdd.MapPartitionsRDD.getPartitions(MapPartitionsRDD.scala:49)
> at org.apache.spark.rdd.RDD.$anonfun$partitions$2(RDD.scala:276)
> at scala.Option.getOrElse(Option.scala:189)
> at org.apache.spark.rdd.RDD.partitions(RDD.scala:272)
> at org.apache.spark.rdd.MapPartitionsRDD.getPartitions(MapPartitionsRDD.scala:49)
> at org.apache.spark.rdd.RDD.$anonfun$partitions$2(RDD.scala:276)
> at scala.Option.getOrElse(Option.scala:189)
> at org.apache.spark.rdd.RDD.partitions(RDD.scala:272)
> at org.apache.spark.rdd.MapPartitionsRDD.getPartitions(MapPartitionsRDD.scala:49)
> at org.apache.spark.rdd.RDD.$anonfun$partitions$2(RDD.scala:276)
> at scala.Option.getOrElse(Option.scala:189)
> at org.apache.spark.rdd.RDD.partitions(RDD.scala:272)
> at org.apache.spark.SparkContext.runJob(SparkContext.scala:2158)
> at org.apache.spark.rdd.RDD.$anonfun$collect$1(RDD.scala:1004)
> at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
> at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:112)
> at org.apache.spark.rdd.RDD.withScope(RDD.scala:388)
> at org.apache.spark.rdd.RDD.collect(RDD.scala:1003)
> at org.apache.spark.sql.execution.SparkPlan.executeCollect(SparkPlan.scala:385)
> at org.apache.spark.sql.execution.SparkPlan.executeCollectPublic(SparkPlan.scala:412)
> at org.apache.spark.sql.execution.HiveResult$.hiveResultString(HiveResult.scala:58)
> at org.apache.spark.sql.hive.thriftserver.SparkSQLDriver.$anonfun$run$1(SparkSQLDriver.scala:65)
> at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$5(SQLExecution.scala:100)
> at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:160)
> at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:87)
> at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:763)
> at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:64)
> at org.apache.spark.sql.hive.thriftserver.SparkSQLDriver.run(SparkSQLDriver.scala:65)
> at org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.processCmd(SparkSQLCLIDriver.scala:377)
> at org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.$anonfun$processLine$1(SparkSQLCLIDriver.scala:496)
> at scala.collection.Iterator.foreach(Iterator.scala:941)
> at scala.collection.Iterator.foreach$(Iterator.scala:941)
> at scala.collection.AbstractIterator.foreach(Iterator.scala:1429)
> at scala.collection.IterableLike.foreach(IterableLike.scala:74)
> at scala.collection.IterableLike.foreach$(IterableLike.scala:73)
> at scala.collection.AbstractIterable.foreach(Iterable.scala:56)
> at org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.processLine(SparkSQLCLIDriver.scala:490)
> at org.apache.hadoop.hive.cli.CliDriver.processLine(CliDriver.java:336)
> at org.apache.hadoop.hive.cli.CliDriver.processReader(CliDriver.java:474)
> at org.apache.hadoop.hive.cli.CliDriver.processFile(CliDriver.java:490)
> at org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver$.main(SparkSQLCLIDriver.scala:206)
> at org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.main(SparkSQLCLIDriver.scala)
> at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
> at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
> at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
> at java.lang.reflect.Method.invoke(Method.java:498)
> at org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
> at org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:928)
> at org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:180)
> at org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:203)
> at org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:90)
> at org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1007)
> at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1016)
> at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
> Caused by: java.lang.IllegalStateException: The input format instance has not been properly initialized. Ensure you call initializeTable either in your constructor or initialize method
> at org.apache.hadoop.hbase.mapreduce.TableInputFormatBase.getTable(TableInputFormatBase.java:652)
> at org.apache.hadoop.hbase.mapreduce.TableInputFormatBase.getSplits(TableInputFormatBase.java:265)
> ... 62 more
--
This message was sent by Atlassian Jira
(v8.3.4#803005)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscribe@spark.apache.org
For additional commands, e-mail: issues-help@spark.apache.org