[ https://issues.apache.org/jira/browse/HIVE-11045?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14592502#comment-14592502 ]
Soundararajan Velu commented on HIVE-11045: ------------------------------------------- Vikram, I face this issue only with Hive on Tez, my data is in json format and I use JsonSerde from https://github.com/rcongiu/Hive-JSON-Serde, The query runs perfectly fine on Hive. This only occurs with Tez. Data set is huge and I have no clue on which records this exception arises, The query is as below, SELECT t1.return_id AS return_id, t1.approve_date AS approve_date, t1.approve_date_key AS approve_date_key, t1.cancel_date AS cancel_date, t1.cancel_date_key AS cancel_date_key, t1.complete_date AS complete_date, t1.complete_date_key AS complete_date_key, t1.init_cancellation_date AS init_cancellation_date, t1.init_cancellation_date_key AS init_cancellation_date_key, t1.reject_date AS reject_date, t1.reject_date_key AS reject_date_key, t1.unhold_date AS unhold_date, t1.unhold_date_key AS unhold_date_key, t1.request_service_date AS request_service_date, t1.request_service_date_key AS request_service_date_key, t1.service_approve_return_date AS service_approve_return_date, t1.service_approve_return_date_key AS service_approve_return_date_key, CASE WHEN t2.action_override_status_time IS NULL THEN 0 ELSE 1 END AS flag_action_override, CASE WHEN t2.action_override_status_time IS NULL THEN NULL ELSE t2.action_override_status_time END AS action_override_status_time, CASE WHEN t2.action_override_user_login IS NULL THEN 'NA' ELSE t2.action_override_user_login END AS action_override_user_login, CASE WHEN t2.action_override_change_reason IS NULL THEN 'NA' ELSE t2.action_override_change_reason END AS action_override_change_reason, CASE WHEN t2.action_override_change_sub_reason IS NULL THEN 'NA' ELSE t2.action_override_change_sub_reason END AS action_override_change_sub_reason, CASE WHEN t2.action_override_count IS NULL THEN cast(0 AS bigint) ELSE t2.action_override_count END AS action_override_count, CASE WHEN t2.action_change_data IS NULL THEN 'NA' ELSE t2.action_change_data END AS action_change_data, CASE WHEN t3.policy_override_status_time IS NULL THEN 0 ELSE 1 END AS flag_policy_override, CASE WHEN t3.policy_override_status_time IS NULL THEN NULL ELSE t3.policy_override_status_time END AS policy_override_status_time, CASE WHEN t3.policy_override_user_login IS NULL THEN 'NA' ELSE t3.policy_override_user_login END AS policy_override_user_login, CASE WHEN t3.policy_override_change_reason IS NULL THEN 'NA' ELSE t3.policy_override_change_reason END AS policy_override_change_reason, CASE WHEN t3.policy_override_change_sub_reason IS NULL THEN 'NA' ELSE t3.policy_override_change_sub_reason END AS policy_override_change_sub_reason, CASE WHEN t3.policy_override_count IS NULL THEN cast(0 AS bigint) ELSE t3.policy_override_count END AS policy_override_count, CASE WHEN t3.policy_change_data IS NULL THEN 'NA' ELSE t3.policy_change_data END AS policy_change_data, cast(0 AS bigint) AS temp_flag, CASE WHEN t3.policy_override_status_date_key IS NULL THEN 0 ELSE t3.policy_override_status_date_key END AS policy_override_status_date_key, CASE WHEN t2.action_override_status_date_key IS NULL THEN 0 ELSE t2.action_override_status_date_key END AS action_override_status_date_key, t1.user_approved_by AS user_approved_by, t1.user_rejected_by AS user_rejected_by, t1.user_cancelled_by AS user_cancelled_by, t1.reject_reason AS reject_reason, t1.reject_sub_reason AS reject_sub_reason, t1.reject_change_data AS reject_change_data FROM (SELECT rh1.`data`.return_id, MIN (CASE WHEN rh1.`data`.event = 'approve' THEN rh1.`data`.status_time ELSE NULL END) AS approve_date, MIN (CASE WHEN rh1.`data`.event = 'cancel' THEN rh1.`data`.status_time ELSE NULL END) AS cancel_date, MIN (CASE WHEN rh1.`data`.event = 'complete' THEN rh1.`data`.status_time ELSE NULL END) AS complete_date, MIN (CASE WHEN rh1.`data`.event = 'init_cancellation' THEN rh1.`data`.status_time ELSE NULL END) AS init_cancellation_date, MIN (CASE WHEN rh1.`data`.event = 'reject' THEN rh1.`data`.status_time ELSE NULL END) AS reject_date, MIN (CASE WHEN rh1.`data`.event = 'unhold' THEN rh1.`data`.status_time ELSE NULL END) AS unhold_date, MIN (CASE WHEN rh1.`data`.event = 'request_service' THEN rh1.`data`.status_time ELSE NULL END) AS request_service_date, MIN (CASE WHEN rh1.`data`.event = 'service_approve_return' THEN rh1.`data`.status_time ELSE NULL END) AS service_approve_return_date, MIN (CASE WHEN rh1.`data`.event = 'approve' THEN lookup_date(rh1.`data`.status_time) ELSE NULL END) AS approve_date_key, MIN (CASE WHEN rh1.`data`.event = 'cancel' THEN lookup_date(rh1.`data`.status_time) ELSE NULL END) AS cancel_date_key, MIN (CASE WHEN rh1.`data`.event = 'complete' THEN lookup_date(rh1.`data`.status_time) ELSE NULL END) AS complete_date_key, MIN (CASE WHEN rh1.`data`.event = 'init_cancellation' THEN lookup_date(rh1.`data`.status_time) ELSE NULL END) AS init_cancellation_date_key, MIN (CASE WHEN rh1.`data`.event = 'reject' THEN lookup_date(rh1.`data`.status_time) ELSE NULL END) AS reject_date_key, MIN (CASE WHEN rh1.`data`.event = 'unhold' THEN lookup_date(rh1.`data`.status_time) ELSE NULL END) AS unhold_date_key, MIN (CASE WHEN rh1.`data`.event = 'request_service' THEN lookup_date(rh1.`data`.status_time) ELSE NULL END) AS request_service_date_key, MIN (CASE WHEN rh1.`data`.event = 'service_approve_return' THEN lookup_date(rh1.`data`.status_time) ELSE NULL END) AS service_approve_return_date_key, MIN (CASE WHEN rh1.`data`.event = 'approve' THEN rh1.`data`.user_login ELSE NULL END) AS user_approved_by, MIN (CASE WHEN rh1.`data`.event = 'cancel' THEN rh1.`data`.user_login ELSE NULL END) AS user_cancelled_by, MIN (CASE WHEN rh1.`data`.event = 'reject' THEN rh1.`data`.user_login ELSE NULL END) AS user_rejected_by, MIN (CASE WHEN rh1.`data`.event = 'reject' THEN rh1.`data`.change_data ELSE NULL END) AS reject_change_data, MIN (CASE WHEN rh1.`data`.event = 'reject' THEN rh1.`data`.change_reason ELSE NULL END) AS reject_reason, MIN (CASE WHEN rh1.`data`.event = 'reject' THEN rh1.`data`.change_sub_reason ELSE NULL END) AS reject_sub_reason FROM dart_fkint_scp_rrr_return_history_1_0_view rh1 GROUP BY rh1.`data`.return_id) t1 LEFT OUTER JOIN (SELECT rh2.`data`.return_id, max(rh2.`data`.status_time) AS action_override_status_time, max(lookup_date(rh2.`data`.status_time)) AS action_override_status_date_key, max(rh2.`data`.user_login) AS action_override_user_login, max(rh2.`data`.change_reason) AS action_override_change_reason, max(rh2.`data`.change_sub_reason) AS action_override_change_sub_reason, max(rh2.`data`.change_data) AS action_change_data, count(DISTINCT rh2.`data`.status_time) AS action_override_count FROM dart_fkint_scp_rrr_return_history_1_0_view rh2 WHERE rh2.`data`.change_reason='action_override' GROUP BY rh2.`data`.return_id) t2 ON t1.return_id = t2.return_id LEFT OUTER JOIN (SELECT rh3.`data`.return_id, max(rh3.`data`.status_time) AS policy_override_status_time, max(lookup_date(rh3.`data`.status_time)) AS policy_override_status_date_key, max(rh3.`data`.user_login) AS policy_override_user_login, max(rh3.`data`.change_reason) AS policy_override_change_reason, max(rh3.`data`.change_sub_reason) AS policy_override_change_sub_reason, max(rh3.`data`.change_data) AS policy_change_data, count(DISTINCT rh3.`data`.status_time) AS policy_override_count FROM dart_fkint_scp_rrr_return_history_1_0_view rh3 WHERE rh3.`data`.change_reason='policy_override' GROUP BY rh3.`data`.return_id) t3 ON t1.return_id = t3.return_id ; > ArrayIndexOutOfBoundsException with Hive 1.2.0 and Tez 0.7.0 > ------------------------------------------------------------ > > Key: HIVE-11045 > URL: https://issues.apache.org/jira/browse/HIVE-11045 > Project: Hive > Issue Type: Bug > Components: Hive > Affects Versions: 1.2.0 > Environment: Hive 1.2.0, HDP 2.2, Hadoop 2.6, Tez 0.7.0 > Reporter: Soundararajan Velu > > TaskAttempt 3 failed, info=[Error: Failure while running > task:java.lang.RuntimeException: java.lang.RuntimeException: > org.apache.hadoop.hive.ql.metadata.HiveException: Hive Runtime Error while > processing row (tag=0) > {"key":{"_col0":4457890},"value":{"_col0":null,"_col1":null,"_col2":null,"_col3":null,"_col4":null,"_col5":null,"_col6":null,"_col7":null,"_col8":null,"_col9":null,"_col10":null,"_col11":null,"_col12":null,"_col13":null,"_col14":null,"_col15":null,"_col16":null,"_col17":"fkl_shipping_b2c","_col18":null,"_col19":null,"_col20":null,"_col21":null}} > at > org.apache.hadoop.hive.ql.exec.tez.TezProcessor.initializeAndRunProcessor(TezProcessor.java:171) > at > org.apache.hadoop.hive.ql.exec.tez.TezProcessor.run(TezProcessor.java:137) > at > org.apache.tez.runtime.LogicalIOProcessorRuntimeTask.run(LogicalIOProcessorRuntimeTask.java:345) > at > org.apache.tez.runtime.task.TezTaskRunner$TaskRunnerCallable$1.run(TezTaskRunner.java:179) > at > org.apache.tez.runtime.task.TezTaskRunner$TaskRunnerCallable$1.run(TezTaskRunner.java:171) > at java.security.AccessController.doPrivileged(Native Method) > at javax.security.auth.Subject.doAs(Subject.java:415) > at > org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1628) > at > org.apache.tez.runtime.task.TezTaskRunner$TaskRunnerCallable.callInternal(TezTaskRunner.java:171) > at > org.apache.tez.runtime.task.TezTaskRunner$TaskRunnerCallable.callInternal(TezTaskRunner.java:167) > at org.apache.tez.common.CallableWithNdc.call(CallableWithNdc.java:36) > at java.util.concurrent.FutureTask.run(FutureTask.java:262) > at > java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145) > at > java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615) > at java.lang.Thread.run(Thread.java:745) > Caused by: java.lang.RuntimeException: > org.apache.hadoop.hive.ql.metadata.HiveException: Hive Runtime Error while > processing row (tag=0) > {"key":{"_col0":4457890},"value":{"_col0":null,"_col1":null,"_col2":null,"_col3":null,"_col4":null,"_col5":null,"_col6":null,"_col7":null,"_col8":null,"_col9":null,"_col10":null,"_col11":null,"_col12":null,"_col13":null,"_col14":null,"_col15":null,"_col16":null,"_col17":"fkl_shipping_b2c","_col18":null,"_col19":null,"_col20":null,"_col21":null}} > at > org.apache.hadoop.hive.ql.exec.tez.ReduceRecordSource.pushRecord(ReduceRecordSource.java:302) > at > org.apache.hadoop.hive.ql.exec.tez.ReduceRecordProcessor.run(ReduceRecordProcessor.java:249) > at > org.apache.hadoop.hive.ql.exec.tez.TezProcessor.initializeAndRunProcessor(TezProcessor.java:148) > ... 14 more > Caused by: org.apache.hadoop.hive.ql.metadata.HiveException: Hive Runtime > Error while processing row (tag=0) > {"key":{"_col0":4457890},"value":{"_col0":null,"_col1":null,"_col2":null,"_col3":null,"_col4":null,"_col5":null,"_col6":null,"_col7":null,"_col8":null,"_col9":null,"_col10":null,"_col11":null,"_col12":null,"_col13":null,"_col14":null,"_col15":null,"_col16":null,"_col17":"fkl_shipping_b2c","_col18":null,"_col19":null,"_col20":null,"_col21":null}} > at > org.apache.hadoop.hive.ql.exec.tez.ReduceRecordSource$GroupIterator.next(ReduceRecordSource.java:370) > at > org.apache.hadoop.hive.ql.exec.tez.ReduceRecordSource.pushRecord(ReduceRecordSource.java:292) > ... 16 more > Caused by: org.apache.hadoop.hive.ql.metadata.HiveException: > java.lang.RuntimeException: org.apache.hadoop.hive.ql.metadata.HiveException: > Hive Runtime Error while processing row (tag=1) > {"key":{"_col0":6417306,"_col1":{0:{"_col0":"2014-08-01 > 02:14:02"}}},"value":{"_col0":"2014-08-01 > 02:14:02","_col1":20140801,"_col2":"sc_jarvis_b2c","_col3":"action_override","_col4":"WITHIN_GRACE_PERIOD","_col5":"policy_override"}} > at > org.apache.hadoop.hive.ql.exec.CommonMergeJoinOperator.fetchOneRow(CommonMergeJoinOperator.java:413) > at > org.apache.hadoop.hive.ql.exec.CommonMergeJoinOperator.fetchNextGroup(CommonMergeJoinOperator.java:381) > at > org.apache.hadoop.hive.ql.exec.CommonMergeJoinOperator.process(CommonMergeJoinOperator.java:206) > at org.apache.hadoop.hive.ql.exec.Operator.forward(Operator.java:837) > at > org.apache.hadoop.hive.ql.exec.GroupByOperator.forward(GroupByOperator.java:1016) > at > org.apache.hadoop.hive.ql.exec.GroupByOperator.processAggr(GroupByOperator.java:821) > at > org.apache.hadoop.hive.ql.exec.GroupByOperator.processKey(GroupByOperator.java:695) > at > org.apache.hadoop.hive.ql.exec.GroupByOperator.process(GroupByOperator.java:761) > at > org.apache.hadoop.hive.ql.exec.tez.ReduceRecordSource$GroupIterator.next(ReduceRecordSource.java:361) > ... 17 more > Caused by: java.lang.RuntimeException: > org.apache.hadoop.hive.ql.metadata.HiveException: Hive Runtime Error while > processing row (tag=1) > {"key":{"_col0":6417306,"_col1":{0:{"_col0":"2014-08-01 > 02:14:02"}}},"value":{"_col0":"2014-08-01 > 02:14:02","_col1":20140801,"_col2":"sc_jarvis_b2c","_col3":"action_override","_col4":"WITHIN_GRACE_PERIOD","_col5":"policy_override"}} > at > org.apache.hadoop.hive.ql.exec.tez.ReduceRecordSource.pushRecord(ReduceRecordSource.java:302) > at > org.apache.hadoop.hive.ql.exec.CommonMergeJoinOperator.fetchOneRow(CommonMergeJoinOperator.java:405) > ... 25 more > Caused by: org.apache.hadoop.hive.ql.metadata.HiveException: Hive Runtime > Error while processing row (tag=1) > {"key":{"_col0":6417306,"_col1":{0:{"_col0":"2014-08-01 > 02:14:02"}}},"value":{"_col0":"2014-08-01 > 02:14:02","_col1":20140801,"_col2":"sc_jarvis_b2c","_col3":"action_override","_col4":"WITHIN_GRACE_PERIOD","_col5":"policy_override"}} > at > org.apache.hadoop.hive.ql.exec.tez.ReduceRecordSource$GroupIterator.next(ReduceRecordSource.java:370) > at > org.apache.hadoop.hive.ql.exec.tez.ReduceRecordSource.pushRecord(ReduceRecordSource.java:292) > ... 26 more > Caused by: java.lang.ArrayIndexOutOfBoundsException: 1 > at > org.apache.hadoop.hive.ql.exec.GroupByOperator.process(GroupByOperator.java:708) > at > org.apache.hadoop.hive.ql.exec.tez.ReduceRecordSource$GroupIterator.next(ReduceRecordSource.java:361) > ... 27 more -- This message was sent by Atlassian JIRA (v6.3.4#6332)