[HIVE-17829] ArrayIndexOutOfBoundsException - HBASE-backed tables with Avro schema in Hive2

• Type: Bug
• Status: Closed
• Priority: Critical
• Resolution: Fixed
• Affects Version/s: 2.1.0
• Fix Version/s: 3.0.0
• Component/s: HBase Handler
• Labels: pull-request-available
• Assignee: Anishek Agarwal
• Reporter: Chiran Ravani
• Created: 18/Oct/17 06:02
• Updated: 27/Jul/18 05:13
• Resolved: 22/Dec/17 04:41

Description

Stack

2017-10-09T09:39:54,804 ERROR [HiveServer2-Background-Pool: Thread-95]: metadata.Table (Table.java:getColsInternal(642)) - Unable to get field from serde: org.apache.hadoop.hive.hbase.HBaseSerDe
java.lang.ArrayIndexOutOfBoundsException: 1
        at java.util.Arrays$ArrayList.get(Arrays.java:3841) ~[?:1.8.0_77]
        at org.apache.hadoop.hive.serde2.BaseStructObjectInspector.init(BaseStructObjectInspector.java:104) ~[hive-exec-2.1.0.2.6.2.0-205.jar:2.1.0.2.6.2.0-205]
        at org.apache.hadoop.hive.serde2.lazy.objectinspector.LazySimpleStructObjectInspector.init(LazySimpleStructObjectInspector.java:97) ~[hive-exec-2.1.0.2.6.2.0-205.jar:2.1.0.2.6.2.0-205]
        at org.apache.hadoop.hive.serde2.lazy.objectinspector.LazySimpleStructObjectInspector.<init>(LazySimpleStructObjectInspector.java:77) ~[hive-exec-2.1.0.2.6.2.0-205.jar:2.1.0.2.6.2.0-205]
        at org.apache.hadoop.hive.serde2.lazy.objectinspector.LazyObjectInspectorFactory.getLazySimpleStructObjectInspector(LazyObjectInspectorFactory.java:115) ~[hive-exec-2.1.0.2.6.2.0-205.jar:2.1.0.2.6.2.0-205]
        at org.apache.hadoop.hive.hbase.HBaseLazyObjectFactory.createLazyHBaseStructInspector(HBaseLazyObjectFactory.java:79) ~[hive-hbase-handler-2.1.0.2.6.2.0-205.jar:2.1.0.2.6.2.0-205]
        at org.apache.hadoop.hive.hbase.HBaseSerDe.initialize(HBaseSerDe.java:127) ~[hive-hbase-handler-2.1.0.2.6.2.0-205.jar:2.1.0.2.6.2.0-205]
        at org.apache.hadoop.hive.serde2.AbstractSerDe.initialize(AbstractSerDe.java:54) ~[hive-exec-2.1.0.2.6.2.0-205.jar:2.1.0.2.6.2.0-205]
        at org.apache.hadoop.hive.serde2.SerDeUtils.initializeSerDe(SerDeUtils.java:531) ~[hive-exec-2.1.0.2.6.2.0-205.jar:2.1.0.2.6.2.0-205]
        at org.apache.hadoop.hive.metastore.MetaStoreUtils.getDeserializer(MetaStoreUtils.java:424) ~[hive-exec-2.1.0.2.6.2.0-205.jar:2.1.0.2.6.2.0-205]
        at org.apache.hadoop.hive.metastore.MetaStoreUtils.getDeserializer(MetaStoreUtils.java:411) ~[hive-exec-2.1.0.2.6.2.0-205.jar:2.1.0.2.6.2.0-205]
        at org.apache.hadoop.hive.ql.metadata.Table.getDeserializerFromMetaStore(Table.java:279) ~[hive-exec-2.1.0.2.6.2.0-205.jar:2.1.0.2.6.2.0-205]
        at org.apache.hadoop.hive.ql.metadata.Table.getDeserializer(Table.java:261) ~[hive-exec-2.1.0.2.6.2.0-205.jar:2.1.0.2.6.2.0-205]
        at org.apache.hadoop.hive.ql.metadata.Table.getColsInternal(Table.java:639) [hive-exec-2.1.0.2.6.2.0-205.jar:2.1.0.2.6.2.0-205]
        at org.apache.hadoop.hive.ql.metadata.Table.getCols(Table.java:622) [hive-exec-2.1.0.2.6.2.0-205.jar:2.1.0.2.6.2.0-205]
        at org.apache.hadoop.hive.ql.metadata.Hive.createTable(Hive.java:833) [hive-exec-2.1.0.2.6.2.0-205.jar:2.1.0.2.6.2.0-205]
        at org.apache.hadoop.hive.ql.metadata.Hive.createTable(Hive.java:869) [hive-exec-2.1.0.2.6.2.0-205.jar:2.1.0.2.6.2.0-205]
        at org.apache.hadoop.hive.ql.exec.DDLTask.createTable(DDLTask.java:4228) [hive-exec-2.1.0.2.6.2.0-205.jar:2.1.0.2.6.2.0-205]
        at org.apache.hadoop.hive.ql.exec.DDLTask.execute(DDLTask.java:347) [hive-exec-2.1.0.2.6.2.0-205.jar:2.1.0.2.6.2.0-205]
        at org.apache.hadoop.hive.ql.exec.Task.executeTask(Task.java:197) [hive-exec-2.1.0.2.6.2.0-205.jar:2.1.0.2.6.2.0-205]
        at org.apache.hadoop.hive.ql.exec.TaskRunner.runSequential(TaskRunner.java:100) [hive-exec-2.1.0.2.6.2.0-205.jar:2.1.0.2.6.2.0-205]
        at org.apache.hadoop.hive.ql.Driver.launchTask(Driver.java:1905) [hive-exec-2.1.0.2.6.2.0-205.jar:2.1.0.2.6.2.0-205]
        at org.apache.hadoop.hive.ql.Driver.execute(Driver.java:1607) [hive-exec-2.1.0.2.6.2.0-205.jar:2.1.0.2.6.2.0-205]
        at org.apache.hadoop.hive.ql.Driver.runInternal(Driver.java:1354) [hive-exec-2.1.0.2.6.2.0-205.jar:2.1.0.2.6.2.0-205]
        at org.apache.hadoop.hive.ql.Driver.run(Driver.java:1123) [hive-exec-2.1.0.2.6.2.0-205.jar:2.1.0.2.6.2.0-205]
        at org.apache.hadoop.hive.ql.Driver.run(Driver.java:1116) [hive-exec-2.1.0.2.6.2.0-205.jar:2.1.0.2.6.2.0-205]
        at org.apache.hive.service.cli.operation.SQLOperation.runQuery(SQLOperation.java:242) [hive-service-2.1.0.2.6.2.0-205.jar:2.1.0.2.6.2.0-205]
        at org.apache.hive.service.cli.operation.SQLOperation.access$800(SQLOperation.java:91) [hive-service-2.1.0.2.6.2.0-205.jar:2.1.0.2.6.2.0-205]
        at org.apache.hive.service.cli.operation.SQLOperation$BackgroundWork$1.run(SQLOperation.java:334) [hive-service-2.1.0.2.6.2.0-205.jar:2.1.0.2.6.2.0-205]
        at java.security.AccessController.doPrivileged(Native Method) ~[?:1.8.0_77]
        at javax.security.auth.Subject.doAs(Subject.java:422) [?:1.8.0_77]
        at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1866) [hadoop-common-2.7.3.2.6.2.0-205.jar:?]
        at org.apache.hive.service.cli.operation.SQLOperation$BackgroundWork.run(SQLOperation.java:348) [hive-service-2.1.0.2.6.2.0-205.jar:2.1.0.2.6.2.0-205]
        at java.util.concurrent.Executors$RunnableAdapter.call(Executors.java:511) [?:1.8.0_77]
        at java.util.concurrent.FutureTask.run(FutureTask.java:266) [?:1.8.0_77]
        at java.util.concurrent.Executors$RunnableAdapter.call(Executors.java:511) [?:1.8.0_77]
        at java.util.concurrent.FutureTask.run(FutureTask.java:266) [?:1.8.0_77]
        at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142) [?:1.8.0_77]
        at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617) [?:1.8.0_77]
        at java.lang.Thread.run(Thread.java:745) [?:1.8.0_77]

Steps to Repro:

Create Hbase Table:
========================
create 'hbase_avro_table', 'test_col_fam', 'test_col'

Create Hive Table:
=========================
CREATE EXTERNAL TABLE test_hbase_avro2
ROW FORMAT SERDE 'org.apache.hadoop.hive.hbase.HBaseSerDe'
STORED BY 'org.apache.hadoop.hive.hbase.HBaseStorageHandler'
WITH SERDEPROPERTIES (
"hbase.columns.mapping" = ":key,test_col_fam:test_col",
"test_col_fam.test_col.serialization.type" = "avro",
"test_col_fam.test_col.avro.schema.url" = "hdfs://rpathak-h1.openstacklocal:8020/user/hive/schema.avsc")
TBLPROPERTIES (
"hbase.table.name" = "hbase_avro_table",
"hbase.mapred.output.outputtable" = "hbase_avro_table",
"hbase.struct.autogenerate"="true",
"avro.schema.literal"='{
"type": "record",
"name": "test_hbase_avro",
"fields": [
{ "name":"test_col", "type":"string"}
]
}');

The same query works with Hive 1.2.1

Issue Links

• is broken by: HIVE-12245 Support column comments for an HBase backed table
• is duplicated by: HIVE-18290 hbase backed table creation fails where no column comments present
• links to: GitHub Pull Request #283