Hi Team,
I am getting the below error when i am executing the queries on HIVE source.
Could you please help me to resolve this issue -
DATA_READ ERROR: Failed to initialize Hive record reader
Dataset split key 142
Partition values rh_load_time=20200710120328,rh_date=1594166400000
Table properties columns.types -> string:string:string:string:string:string:string:string:string:string:string:string:string:string:string:string:string:bigint:bigint:bigint:bigint:bigint:bigint:bigint:bigint:bigint:bigint:bigint:bigint:bigint:bigint:bigint:bigint:bigint:bigint:bigint:bigint:bigint:bigint:bigint:bigint:bigint:bigint:bigint:bigint:bigint:bigint:decimal(20,0):decimal(20,0):decimal(20,0):decimal(23,0):bigint:bigint:bigint:decimal(10,0):date
location -> hdfs://MERCURY/apps/hive/warehouse/jam_zmng1.db/mediation_segment_fact_trf_ha001
spark.sql.sources.schema.numParts -> 2
columns -> datetime,interaction_type_code,skill_grp_ent_name,ct_circle_id,zone,apex_circle_text,ct_segment_id,segment_text,call_type_ent_name,ct_language_id,language_text,lob,lob_text,master_queue,rcc_text,call_type_queue,location_name,rh_calls_offered_count,rh_calls_handled_count,rh_calls_answered_count,rh_ans_interval1_count,rh_ans_005_sec_count,rh_ans_010_sec_count,rh_ans_015_sec_count,rh_ans_020_sec_count,rh_ans_030_sec_count,rh_ans_060_sec_count,rh_ans_090_sec_count,rh_ans_120_sec_count,rh_ans_180_sec_count,rh_ans_gt_180_sec_count,rh_abandoned_calls_count,rh_abandoned_005_sec_count,rh_abandoned_010_sec_count,rh_abandoned_015_sec_count,rh_abandoned_020_sec_count,rh_abandoned_030_sec_count,rh_abandoned_060_sec_count,rh_abandoned_090_sec_count,rh_abandoned_120_sec_count,rh_abandoned_180_sec_count,rh_abandoned_gt_180_sec_count,rh_calls_onhold_count,rh_error_count,rh_shortcalls_count,rh_router_calls_dequeued_count,rh_agent_error_count,rh_talk_time_sec,rh_hold_time_sec,rh_wrap_time_sec,rh_answer_wait_time_sec,rh_cleared_count,rh_abandoned_invite_count,rh_routed_other_count,rh_max_call_wait_time_sec,rh_load_date
spark.sql.sources.schema.partCol.1 -> rh_date
spark.sql.sources.schema.partCol.0 -> rh_load_time
partition_columns.types -> string:date
serialization.format -> 1
spark.sql.create.version -> 2.3.0.2.6.5.0-292
serialization.ddl -> struct mediation_segment_fact_trf_ha001 { string datetime, string interaction_type_code, string skill_grp_ent_name, string ct_circle_id, string zone, string apex_circle_text, string ct_segment_id, string segment_text, string call_type_ent_name, string ct_language_id, string language_text, string lob, string lob_text, string master_queue, string rcc_text, string call_type_queue, string location_name, i64 rh_calls_offered_count, i64 rh_calls_handled_count, i64 rh_calls_answered_count, i64 rh_ans_interval1_count, i64 rh_ans_005_sec_count, i64 rh_ans_010_sec_count, i64 rh_ans_015_sec_count, i64 rh_ans_020_sec_count, i64 rh_ans_030_sec_count, i64 rh_ans_060_sec_count, i64 rh_ans_090_sec_count, i64 rh_ans_120_sec_count, i64 rh_ans_180_sec_count, i64 rh_ans_gt_180_sec_count, i64 rh_abandoned_calls_count, i64 rh_abandoned_005_sec_count, i64 rh_abandoned_010_sec_count, i64 rh_abandoned_015_sec_count, i64 rh_abandoned_020_sec_count, i64 rh_abandoned_030_sec_count, i64 rh_abandoned_060_sec_count, i64 rh_abandoned_090_sec_count, i64 rh_abandoned_120_sec_count, i64 rh_abandoned_180_sec_count, i64 rh_abandoned_gt_180_sec_count, i64 rh_calls_onhold_count, i64 rh_error_count, i64 rh_shortcalls_count, i64 rh_router_calls_dequeued_count, i64 rh_agent_error_count, decimal(20,0) rh_talk_time_sec, decimal(20,0) rh_hold_time_sec, decimal(20,0) rh_wrap_time_sec, decimal(23,0) rh_answer_wait_time_sec, i64 rh_cleared_count, i64 rh_abandoned_invite_count, i64 rh_routed_other_count, decimal(10,0) rh_max_call_wait_time_sec, date rh_load_date}
transient_lastDdlTime -> 1585724909
columns.comments ->
bucket_count -> -1
file.outputformat -> org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
path -> hdfs://MERCURY/apps/hive/warehouse/jam_zmng1.db/mediation_segment_fact_trf_ha001
serialization.lib -> org.apache.hadoop.hive.ql.io.orc.OrcSerde
partition_columns -> rh_load_time/rh_date
spark.sql.partitionProvider -> catalog
spark.sql.sources.schema.numPartCols -> 2
spark.sql.sources.schema.part.1 -> bandoned_invite_count",“type”:“long”,“nullable”:true,“metadata”:{}},{“name”:“rh_routed_other_count”,“type”:“long”,“nullable”:true,“metadata”:{}},{“name”:“rh_max_call_wait_time_sec”,“type”:“decimal(10,0)”,“nullable”:true,“metadata”:{}},{“name”:“rh_load_date”,“type”:“date”,“nullable”:true,“metadata”:{}},{“name”:“rh_load_time”,“type”:“string”,“nullable”:true,“metadata”:{}},{“name”:“rh_date”,“type”:“date”,“nullable”:true,“metadata”:{}}]}
spark.sql.sources.schema.part.0 -> {“type”:“struct”,“fields”:[{“name”:“datetime”,“type”:“string”,“nullable”:true,“metadata”:{}},{“name”:“interaction_type_code”,“type”:“string”,“nullable”:true,“metadata”:{}},{“name”:“skill_grp_ent_name”,“type”:“string”,“nullable”:true,“metadata”:{}},{“name”:“ct_circle_id”,“type”:“string”,“nullable”:true,“metadata”:{}},{“name”:“zone”,“type”:“string”,“nullable”:true,“metadata”:{}},{“name”:“apex_circle_text”,“type”:“string”,“nullable”:true,“metadata”:{}},{“name”:“ct_segment_id”,“type”:“string”,“nullable”:true,“metadata”:{}},{“name”:“segment_text”,“type”:“string”,“nullable”:true,“metadata”:{}},{“name”:“call_type_ent_name”,“type”:“string”,“nullable”:true,“metadata”:{}},{“name”:“ct_language_id”,“type”:“string”,“nullable”:true,“metadata”:{}},{“name”:“language_text”,“type”:“string”,“nullable”:true,“metadata”:{}},{“name”:“lob”,“type”:“string”,“nullable”:true,“metadata”:{}},{“name”:“lob_text”,“type”:“string”,“nullable”:true,“metadata”:{}},{“name”:“master_queue”,“type”:“string”,“nullable”:true,“metadata”:{}},{“name”:“rcc_text”,“type”:“string”,“nullable”:true,“metadata”:{}},{“name”:“call_type_queue”,“type”:“string”,“nullable”:true,“metadata”:{}},{“name”:“location_name”,“type”:“string”,“nullable”:true,“metadata”:{}},{“name”:“rh_calls_offered_count”,“type”:“long”,“nullable”:true,“metadata”:{}},{“name”:“rh_calls_handled_count”,“type”:“long”,“nullable”:true,“metadata”:{}},{“name”:“rh_calls_answered_count”,“type”:“long”,“nullable”:true,“metadata”:{}},{“name”:“rh_ans_interval1_count”,“type”:“long”,“nullable”:true,“metadata”:{}},{“name”:“rh_ans_005_sec_count”,“type”:“long”,“nullable”:true,“metadata”:{}},{“name”:“rh_ans_010_sec_count”,“type”:“long”,“nullable”:true,“metadata”:{}},{“name”:“rh_ans_015_sec_count”,“type”:“long”,“nullable”:true,“metadata”:{}},{“name”:“rh_ans_020_sec_count”,“type”:“long”,“nullable”:true,“metadata”:{}},{“name”:“rh_ans_030_sec_count”,“type”:“long”,“nullable”:true,“metadata”:{}},{“name”:“rh_ans_060_sec_count”,“type”:“long”,“nullable”:true,“metadata”:{}},{“name”:“rh_ans_090_sec_count”,“type”:“long”,“nullable”:true,“metadata”:{}},{“name”:“rh_ans_120_sec_count”,“type”:“long”,“nullable”:true,“metadata”:{}},{“name”:“rh_ans_180_sec_count”,“type”:“long”,“nullable”:true,“metadata”:{}},{“name”:“rh_ans_gt_180_sec_count”,“type”:“long”,“nullable”:true,“metadata”:{}},{“name”:“rh_abandoned_calls_count”,“type”:“long”,“nullable”:true,“metadata”:{}},{“name”:“rh_abandoned_005_sec_count”,“type”:“long”,“nullable”:true,“metadata”:{}},{“name”:“rh_abandoned_010_sec_count”,“type”:“long”,“nullable”:true,“metadata”:{}},{“name”:“rh_abandoned_015_sec_count”,“type”:“long”,“nullable”:true,“metadata”:{}},{“name”:“rh_abandoned_020_sec_count”,“type”:“long”,“nullable”:true,“metadata”:{}},{“name”:“rh_abandoned_030_sec_count”,“type”:“long”,“nullable”:true,“metadata”:{}},{“name”:“rh_abandoned_060_sec_count”,“type”:“long”,“nullable”:true,“metadata”:{}},{“name”:“rh_abandoned_090_sec_count”,“type”:“long”,“nullable”:true,“metadata”:{}},{“name”:“rh_abandoned_120_sec_count”,“type”:“long”,“nullable”:true,“metadata”:{}},{“name”:“rh_abandoned_180_sec_count”,“type”:“long”,“nullable”:true,“metadata”:{}},{“name”:“rh_abandoned_gt_180_sec_count”,“type”:“long”,“nullable”:true,“metadata”:{}},{“name”:“rh_calls_onhold_count”,“type”:“long”,“nullable”:true,“metadata”:{}},{“name”:“rh_error_count”,“type”:“long”,“nullable”:true,“metadata”:{}},{“name”:“rh_shortcalls_count”,“type”:“long”,“nullable”:true,“metadata”:{}},{“name”:“rh_router_calls_dequeued_count”,“type”:“long”,“nullable”:true,“metadata”:{}},{“name”:“rh_agent_error_count”,“type”:“long”,“nullable”:true,“metadata”:{}},{“name”:“rh_talk_time_sec”,“type”:“decimal(20,0)”,“nullable”:true,“metadata”:{}},{“name”:“rh_hold_time_sec”,“type”:“decimal(20,0)”,“nullable”:true,“metadata”:{}},{“name”:“rh_wrap_time_sec”,“type”:“decimal(20,0)”,“nullable”:true,“metadata”:{}},{“name”:“rh_answer_wait_time_sec”,“type”:“decimal(23,0)”,“nullable”:true,“metadata”:{}},{“name”:“rh_cleared_count”,“type”:“long”,“nullable”:true,“metadata”:{}},{“name”:"rh_a
file.inputformat -> org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
spark.sql.sources.provider -> orc
name -> jam_zmng1.mediation_segment_fact_trf_ha001
SqlOperatorImpl HIVE_SUB_SCAN
Location 1:5:3
SqlOperatorImpl HIVE_SUB_SCAN
Location 1:5:3
Fragment 1:0
[Error Id: 0be22e20-8ce2-4268-bdfc-6149a6e0439b on bdpdata0504.abc.com:0]
(java.lang.NullPointerException) null
sun.nio.ch.EPollArrayWrapper.isEventsHighKilled():174
sun.nio.ch.EPollArrayWrapper.setUpdateEvents():190
sun.nio.ch.EPollArrayWrapper.add():239
sun.nio.ch.EPollSelectorImpl.implRegister():178
sun.nio.ch.SelectorImpl.register():132
java.nio.channels.spi.AbstractSelectableChannel.register():212
java.nio.channels.SelectableChannel.register():280
org.apache.hadoop.net.SocketIOWithTimeout$SelectorPool.select():334
org.apache.hadoop.net.SocketIOWithTimeout.connect():203
org.apache.hadoop.net.NetUtils.connect():533
org.apache.hadoop.hdfs.DFSClient.newConnectedPeer():2940
org.apache.hadoop.hdfs.client.impl.BlockReaderFactory.nextTcpPeer():822
org.apache.hadoop.hdfs.client.impl.BlockReaderFactory.getRemoteBlockReaderFromTcp():747
org.apache.hadoop.hdfs.client.impl.BlockReaderFactory.build():380
org.apache.hadoop.hdfs.DFSInputStream.getBlockReader():645
org.apache.hadoop.hdfs.DFSInputStream.blockSeekTo():576
org.apache.hadoop.hdfs.DFSInputStream.readWithStrategy():758
org.apache.hadoop.hdfs.DFSInputStream.read():830
java.io.DataInputStream.read():149
com.dremio.exec.hadoop.FSDataInputStreamWrapper.read():119
com.dremio.exec.store.hive.exec.FSInputStreamWrapper.readFully():51
org.apache.hadoop.fs.FSDataInputStream.readFully():111
com.dremio.exec.store.hive.exec.apache.FSDataInputStreamWrapper.readFully():83
com.dremio.exec.store.hive.exec.apache.FSDataInputStreamWithStatsWrapper.readFully():66
org.apache.orc.impl.ReaderImpl.extractFileTail():501
org.apache.orc.impl.ReaderImpl.():369
org.apache.hadoop.hive.ql.io.orc.ReaderImpl.():62
org.apache.hadoop.hive.ql.io.orc.OrcFile.createReader():89
com.dremio.exec.store.hive.exec.HiveORCVectorizedReader.internalInit():301
com.dremio.exec.store.hive.exec.HiveAbstractReader.lambda$setup$0():223
java.security.AccessController.doPrivileged():-2
javax.security.auth.Subject.doAs():422
org.apache.hadoop.security.UserGroupInformation.doAs():1844
com.dremio.exec.store.hive.exec.HiveAbstractReader.setup():226
com.dremio.sabot.op.scan.ScanOperator.setupReaderAsCorrectUser():231
com.dremio.sabot.op.scan.ScanOperator.setupReader():204
com.dremio.sabot.op.scan.ScanOperator.setup():190
com.dremio.sabot.driver.SmartOp$SmartProducer.setup():563
com.dremio.sabot.driver.Pipe$SetupVisitor.visitProducer():79
com.dremio.sabot.driver.Pipe$SetupVisitor.visitProducer():63
com.dremio.sabot.driver.SmartOp$SmartProducer.accept():533
com.dremio.sabot.driver.StraightPipe.setup():102
com.dremio.sabot.driver.StraightPipe.setup():102
com.dremio.sabot.driver.StraightPipe.setup():102
com.dremio.sabot.driver.Pipeline.setup():68
com.dremio.sabot.exec.fragment.FragmentExecutor.setupExecution():388
com.dremio.sabot.exec.fragment.FragmentExecutor.run():270
com.dremio.sabot.exec.fragment.FragmentExecutor.access$1200():92
com.dremio.sabot.exec.fragment.FragmentExecutor$AsyncTaskImpl.run():677
com.dremio.sabot.task.AsyncTaskWrapper.run():112
com.dremio.sabot.task.slicing.SlicingThread.mainExecutionLoop():226
com.dremio.sabot.task.slicing.SlicingThread.run():156