[ https://issues.apache.org/jira/browse/HIVE-8589?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Vikram Dixit K updated HIVE-8589: --------------------------------- Description: {code} WITH all_sales AS ( SELECT d_year ,i_brand_id ,i_class_id ,i_category_id ,i_manufact_id ,SUM(sales_cnt) AS sales_cnt ,SUM(sales_amt) AS sales_amt FROM (SELECT d_year ,i_brand_id ,i_class_id ,i_category_id ,i_manufact_id ,cs_quantity - COALESCE(cr_return_quantity,0) AS sales_cnt ,cs_ext_sales_price - COALESCE(cr_return_amount,0.0) AS sales_amt FROM catalog_sales JOIN item ON i_item_sk=cs_item_sk JOIN date_dim ON d_date_sk=cs_sold_date_sk LEFT JOIN catalog_returns ON (cs_order_number=cr_order_number AND cs_item_sk=cr_item_sk) WHERE i_category='Sports' UNION ALL SELECT d_year ,i_brand_id ,i_class_id ,i_category_id ,i_manufact_id ,ss_quantity - COALESCE(sr_return_quantity,0) AS sales_cnt ,ss_ext_sales_price - COALESCE(sr_return_amt,0.0) AS sales_amt FROM store_sales JOIN item ON i_item_sk=ss_item_sk JOIN date_dim ON d_date_sk=ss_sold_date_sk LEFT JOIN store_returns ON (ss_ticket_number=sr_ticket_number AND ss_item_sk=sr_item_sk) WHERE i_category='Sports' UNION ALL SELECT d_year ,i_brand_id ,i_class_id ,i_category_id ,i_manufact_id ,ws_quantity - COALESCE(wr_return_quantity,0) AS sales_cnt ,ws_ext_sales_price - COALESCE(wr_return_amt,0.0) AS sales_amt FROM web_sales JOIN item ON i_item_sk=ws_item_sk JOIN date_dim ON d_date_sk=ws_sold_date_sk LEFT JOIN web_returns ON (ws_order_number=wr_order_number AND ws_item_sk=wr_item_sk) WHERE i_category='Sports') sales_detail GROUP BY d_year, i_brand_id, i_class_id, i_category_id, i_manufact_id) SELECT prev_yr.d_year AS prev_year ,curr_yr.d_year AS year ,curr_yr.i_brand_id ,curr_yr.i_class_id ,curr_yr.i_category_id ,curr_yr.i_manufact_id ,prev_yr.sales_cnt AS prev_yr_cnt ,curr_yr.sales_cnt AS curr_yr_cnt ,curr_yr.sales_cnt-prev_yr.sales_cnt AS sales_cnt_diff ,curr_yr.sales_amt-prev_yr.sales_amt AS sales_amt_diff FROM all_sales curr_yr, all_sales prev_yr WHERE curr_yr.i_brand_id=prev_yr.i_brand_id AND curr_yr.i_class_id=prev_yr.i_class_id AND curr_yr.i_category_id=prev_yr.i_category_id AND curr_yr.i_manufact_id=prev_yr.i_manufact_id AND curr_yr.d_year=2002 AND prev_yr.d_year=2002-1 AND CAST(curr_yr.sales_cnt AS DECIMAL(17,2))/CAST(prev_yr.sales_cnt AS DECIMAL(17,2))<0.9 ORDER BY sales_cnt_diff limit 100 {code} throws a null pointer exception when executed via tez. {code} java.lang.IllegalArgumentException: Output vertex null doesn't exist! at org.apache.tez.dag.api.DAG.addEdge(DAG.java:236) at org.apache.hadoop.hive.ql.exec.tez.TezTask.build(TezTask.java:340) at org.apache.hadoop.hive.ql.exec.tez.TezTask.execute(TezTask.java:152) at org.apache.hadoop.hive.ql.exec.Task.executeTask(Task.java:161) at org.apache.hadoop.hive.ql.exec.TaskRunner.runSequential(TaskRunner.java:85) at org.apache.hadoop.hive.ql.Driver.launchTask(Driver.java:1604) at org.apache.hadoop.hive.ql.Driver.execute(Driver.java:1364) at org.apache.hadoop.hive.ql.Driver.runInternal(Driver.java:1177) at org.apache.hadoop.hive.ql.Driver.run(Driver.java:1004) at org.apache.hadoop.hive.ql.Driver.run(Driver.java:994) at org.apache.hadoop.hive.cli.CliDriver.processLocalCmd(CliDriver.java:247) at org.apache.hadoop.hive.cli.CliDriver.processCmd(CliDriver.java:199) at org.apache.hadoop.hive.cli.CliDriver.processLine(CliDriver.java:410) at org.apache.hadoop.hive.cli.CliDriver.executeDriver(CliDriver.java:783) at org.apache.hadoop.hive.cli.CliDriver.run(CliDriver.java:677) at org.apache.hadoop.hive.cli.CliDriver.main(CliDriver.java:616) at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method) at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57) at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) at java.lang.reflect.Method.invoke(Method.java:606) at org.apache.hadoop.util.RunJar.main(RunJar.java:212) {code} was: {code} WITH all_sales AS ( SELECT d_year ,i_brand_id ,i_class_id ,i_category_id ,i_manufact_id ,SUM(sales_cnt) AS sales_cnt ,SUM(sales_amt) AS sales_amt FROM (SELECT d_year ,i_brand_id ,i_class_id ,i_category_id ,i_manufact_id ,cs_quantity - COALESCE(cr_return_quantity,0) AS sales_cnt ,cs_ext_sales_price - COALESCE(cr_return_amount,0.0) AS sales_amt FROM catalog_sales JOIN item ON i_item_sk=cs_item_sk JOIN date_dim ON d_date_sk=cs_sold_date_sk LEFT JOIN catalog_returns ON (cs_order_number=cr_order_number AND cs_item_sk=cr_item_sk) WHERE i_category='Sports' UNION ALL SELECT d_year ,i_brand_id ,i_class_id ,i_category_id ,i_manufact_id ,ss_quantity - COALESCE(sr_return_quantity,0) AS sales_cnt ,ss_ext_sales_price - COALESCE(sr_return_amt,0.0) AS sales_amt FROM store_sales JOIN item ON i_item_sk=ss_item_sk JOIN date_dim ON d_date_sk=ss_sold_date_sk LEFT JOIN store_returns ON (ss_ticket_number=sr_ticket_number AND ss_item_sk=sr_item_sk) WHERE i_category='Sports' UNION ALL SELECT d_year ,i_brand_id ,i_class_id ,i_category_id ,i_manufact_id ,ws_quantity - COALESCE(wr_return_quantity,0) AS sales_cnt ,ws_ext_sales_price - COALESCE(wr_return_amt,0.0) AS sales_amt FROM web_sales JOIN item ON i_item_sk=ws_item_sk JOIN date_dim ON d_date_sk=ws_sold_date_sk LEFT JOIN web_returns ON (ws_order_number=wr_order_number AND ws_item_sk=wr_item_sk) WHERE i_category='Sports') sales_detail GROUP BY d_year, i_brand_id, i_class_id, i_category_id, i_manufact_id) SELECT prev_yr.d_year AS prev_year ,curr_yr.d_year AS year ,curr_yr.i_brand_id ,curr_yr.i_class_id ,curr_yr.i_category_id ,curr_yr.i_manufact_id ,prev_yr.sales_cnt AS prev_yr_cnt ,curr_yr.sales_cnt AS curr_yr_cnt ,curr_yr.sales_cnt-prev_yr.sales_cnt AS sales_cnt_diff ,curr_yr.sales_amt-prev_yr.sales_amt AS sales_amt_diff FROM all_sales curr_yr, all_sales prev_yr WHERE curr_yr.i_brand_id=prev_yr.i_brand_id AND curr_yr.i_class_id=prev_yr.i_class_id AND curr_yr.i_category_id=prev_yr.i_category_id AND curr_yr.i_manufact_id=prev_yr.i_manufact_id AND curr_yr.d_year=2002 AND prev_yr.d_year=2002-1 AND CAST(curr_yr.sales_cnt AS DECIMAL(17,2))/CAST(prev_yr.sales_cnt AS DECIMAL(17,2))<0.9 ORDER BY sales_cnt_diff limit 100 {code} throws a null pointer exception when executed via tez. > TPCDS query 75 fails with tez > ----------------------------- > > Key: HIVE-8589 > URL: https://issues.apache.org/jira/browse/HIVE-8589 > Project: Hive > Issue Type: Bug > Affects Versions: 0.14.0 > Reporter: Vikram Dixit K > Assignee: Vikram Dixit K > Priority: Critical > Attachments: HIVE-8589.1.patch > > > {code} > WITH all_sales AS ( > SELECT d_year > ,i_brand_id > ,i_class_id > ,i_category_id > ,i_manufact_id > ,SUM(sales_cnt) AS sales_cnt > ,SUM(sales_amt) AS sales_amt > FROM (SELECT d_year > ,i_brand_id > ,i_class_id > ,i_category_id > ,i_manufact_id > ,cs_quantity - COALESCE(cr_return_quantity,0) AS sales_cnt > ,cs_ext_sales_price - COALESCE(cr_return_amount,0.0) AS sales_amt > FROM catalog_sales JOIN item ON i_item_sk=cs_item_sk > JOIN date_dim ON d_date_sk=cs_sold_date_sk > LEFT JOIN catalog_returns ON > (cs_order_number=cr_order_number > AND cs_item_sk=cr_item_sk) > WHERE i_category='Sports' > UNION ALL > SELECT d_year > ,i_brand_id > ,i_class_id > ,i_category_id > ,i_manufact_id > ,ss_quantity - COALESCE(sr_return_quantity,0) AS sales_cnt > ,ss_ext_sales_price - COALESCE(sr_return_amt,0.0) AS sales_amt > FROM store_sales JOIN item ON i_item_sk=ss_item_sk > JOIN date_dim ON d_date_sk=ss_sold_date_sk > LEFT JOIN store_returns ON > (ss_ticket_number=sr_ticket_number > AND ss_item_sk=sr_item_sk) > WHERE i_category='Sports' > UNION ALL > SELECT d_year > ,i_brand_id > ,i_class_id > ,i_category_id > ,i_manufact_id > ,ws_quantity - COALESCE(wr_return_quantity,0) AS sales_cnt > ,ws_ext_sales_price - COALESCE(wr_return_amt,0.0) AS sales_amt > FROM web_sales JOIN item ON i_item_sk=ws_item_sk > JOIN date_dim ON d_date_sk=ws_sold_date_sk > LEFT JOIN web_returns ON > (ws_order_number=wr_order_number > AND ws_item_sk=wr_item_sk) > WHERE i_category='Sports') sales_detail > GROUP BY d_year, i_brand_id, i_class_id, i_category_id, i_manufact_id) > SELECT prev_yr.d_year AS prev_year > ,curr_yr.d_year AS year > ,curr_yr.i_brand_id > ,curr_yr.i_class_id > ,curr_yr.i_category_id > ,curr_yr.i_manufact_id > ,prev_yr.sales_cnt AS prev_yr_cnt > ,curr_yr.sales_cnt AS curr_yr_cnt > ,curr_yr.sales_cnt-prev_yr.sales_cnt AS > sales_cnt_diff > ,curr_yr.sales_amt-prev_yr.sales_amt AS > sales_amt_diff > FROM all_sales curr_yr, all_sales prev_yr > WHERE curr_yr.i_brand_id=prev_yr.i_brand_id > AND curr_yr.i_class_id=prev_yr.i_class_id > AND curr_yr.i_category_id=prev_yr.i_category_id > AND curr_yr.i_manufact_id=prev_yr.i_manufact_id > AND curr_yr.d_year=2002 > AND prev_yr.d_year=2002-1 > AND CAST(curr_yr.sales_cnt AS DECIMAL(17,2))/CAST(prev_yr.sales_cnt AS > DECIMAL(17,2))<0.9 > ORDER BY sales_cnt_diff > limit 100 > {code} > throws a null pointer exception when executed via tez. > {code} > java.lang.IllegalArgumentException: Output vertex null doesn't exist! > at org.apache.tez.dag.api.DAG.addEdge(DAG.java:236) > at org.apache.hadoop.hive.ql.exec.tez.TezTask.build(TezTask.java:340) > at > org.apache.hadoop.hive.ql.exec.tez.TezTask.execute(TezTask.java:152) > at org.apache.hadoop.hive.ql.exec.Task.executeTask(Task.java:161) > at > org.apache.hadoop.hive.ql.exec.TaskRunner.runSequential(TaskRunner.java:85) > at org.apache.hadoop.hive.ql.Driver.launchTask(Driver.java:1604) > at org.apache.hadoop.hive.ql.Driver.execute(Driver.java:1364) > at org.apache.hadoop.hive.ql.Driver.runInternal(Driver.java:1177) > at org.apache.hadoop.hive.ql.Driver.run(Driver.java:1004) > at org.apache.hadoop.hive.ql.Driver.run(Driver.java:994) > at > org.apache.hadoop.hive.cli.CliDriver.processLocalCmd(CliDriver.java:247) > at org.apache.hadoop.hive.cli.CliDriver.processCmd(CliDriver.java:199) > at > org.apache.hadoop.hive.cli.CliDriver.processLine(CliDriver.java:410) > at > org.apache.hadoop.hive.cli.CliDriver.executeDriver(CliDriver.java:783) > at org.apache.hadoop.hive.cli.CliDriver.run(CliDriver.java:677) > at org.apache.hadoop.hive.cli.CliDriver.main(CliDriver.java:616) > at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method) > at > sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57) > at > sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) > at java.lang.reflect.Method.invoke(Method.java:606) > at org.apache.hadoop.util.RunJar.main(RunJar.java:212) > {code} -- This message was sent by Atlassian JIRA (v6.3.4#6332)