PREHOOK: query: DROP TABLE orcfile_merge1 PREHOOK: type: DROPTABLE POSTHOOK: query: DROP TABLE orcfile_merge1 POSTHOOK: type: DROPTABLE PREHOOK: query: DROP TABLE orcfile_merge1b PREHOOK: type: DROPTABLE POSTHOOK: query: DROP TABLE orcfile_merge1b POSTHOOK: type: DROPTABLE PREHOOK: query: DROP TABLE orcfile_merge1c PREHOOK: type: DROPTABLE POSTHOOK: query: DROP TABLE orcfile_merge1c POSTHOOK: type: DROPTABLE PREHOOK: query: CREATE TABLE orcfile_merge1 (key INT, value STRING) PARTITIONED BY (ds STRING, part STRING) STORED AS ORC PREHOOK: type: CREATETABLE PREHOOK: Output: database:default PREHOOK: Output: default@orcfile_merge1 POSTHOOK: query: CREATE TABLE orcfile_merge1 (key INT, value STRING) PARTITIONED BY (ds STRING, part STRING) STORED AS ORC POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default POSTHOOK: Output: default@orcfile_merge1 PREHOOK: query: CREATE TABLE orcfile_merge1b (key INT, value STRING) PARTITIONED BY (ds STRING, part STRING) STORED AS ORC PREHOOK: type: CREATETABLE PREHOOK: Output: database:default PREHOOK: Output: default@orcfile_merge1b POSTHOOK: query: CREATE TABLE orcfile_merge1b (key INT, value STRING) PARTITIONED BY (ds STRING, part STRING) STORED AS ORC POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default POSTHOOK: Output: default@orcfile_merge1b PREHOOK: query: CREATE TABLE orcfile_merge1c (key INT, value STRING) PARTITIONED BY (ds STRING, part STRING) STORED AS ORC PREHOOK: type: CREATETABLE PREHOOK: Output: database:default PREHOOK: Output: default@orcfile_merge1c POSTHOOK: query: CREATE TABLE orcfile_merge1c (key INT, value STRING) PARTITIONED BY (ds STRING, part STRING) STORED AS ORC POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default POSTHOOK: Output: default@orcfile_merge1c PREHOOK: query: -- merge disabled EXPLAIN INSERT OVERWRITE TABLE orcfile_merge1 PARTITION (ds='1', part) SELECT key, value, PMOD(HASH(key), 2) as part FROM src PREHOOK: type: QUERY POSTHOOK: query: -- merge disabled EXPLAIN INSERT OVERWRITE TABLE orcfile_merge1 PARTITION (ds='1', part) SELECT key, value, PMOD(HASH(key), 2) as part FROM src POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-1 is a root stage Stage-0 depends on stages: Stage-1 Stage-2 depends on stages: Stage-0 STAGE PLANS: Stage: Stage-1 Map Reduce Map Operator Tree: TableScan alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: UDFToInteger(key) (type: int), value (type: string), (hash(key) pmod 2) (type: int) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde name: default.orcfile_merge1 Stage: Stage-0 Move Operator tables: partition: ds 1 part replace: true table: input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde name: default.orcfile_merge1 Stage: Stage-2 Stats-Aggr Operator PREHOOK: query: INSERT OVERWRITE TABLE orcfile_merge1 PARTITION (ds='1', part) SELECT key, value, PMOD(HASH(key), 2) as part FROM src PREHOOK: type: QUERY PREHOOK: Input: default@src PREHOOK: Output: default@orcfile_merge1@ds=1 POSTHOOK: query: INSERT OVERWRITE TABLE orcfile_merge1 PARTITION (ds='1', part) SELECT key, value, PMOD(HASH(key), 2) as part FROM src POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Output: default@orcfile_merge1@ds=1/part=0 POSTHOOK: Output: default@orcfile_merge1@ds=1/part=1 POSTHOOK: Lineage: orcfile_merge1 PARTITION(ds=1,part=0).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: orcfile_merge1 PARTITION(ds=1,part=0).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: orcfile_merge1 PARTITION(ds=1,part=1).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: orcfile_merge1 PARTITION(ds=1,part=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] Found 2 items #### A masked pattern was here #### PREHOOK: query: -- auto-merge slow way EXPLAIN INSERT OVERWRITE TABLE orcfile_merge1b PARTITION (ds='1', part) SELECT key, value, PMOD(HASH(key), 2) as part FROM src PREHOOK: type: QUERY POSTHOOK: query: -- auto-merge slow way EXPLAIN INSERT OVERWRITE TABLE orcfile_merge1b PARTITION (ds='1', part) SELECT key, value, PMOD(HASH(key), 2) as part FROM src POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-1 is a root stage Stage-7 depends on stages: Stage-1 , consists of Stage-4, Stage-3, Stage-5 Stage-4 Stage-0 depends on stages: Stage-4, Stage-3, Stage-6 Stage-2 depends on stages: Stage-0 Stage-3 Stage-5 Stage-6 depends on stages: Stage-5 STAGE PLANS: Stage: Stage-1 Map Reduce Map Operator Tree: TableScan alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: UDFToInteger(key) (type: int), value (type: string), (hash(key) pmod 2) (type: int) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde name: default.orcfile_merge1b Stage: Stage-7 Conditional Operator Stage: Stage-4 Move Operator files: hdfs directory: true #### A masked pattern was here #### Stage: Stage-0 Move Operator tables: partition: ds 1 part replace: true table: input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde name: default.orcfile_merge1b Stage: Stage-2 Stats-Aggr Operator Stage: Stage-3 Map Reduce Map Operator Tree: TableScan File Output Operator compressed: false table: input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde name: default.orcfile_merge1b Stage: Stage-5 Map Reduce Map Operator Tree: TableScan File Output Operator compressed: false table: input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde name: default.orcfile_merge1b Stage: Stage-6 Move Operator files: hdfs directory: true #### A masked pattern was here #### PREHOOK: query: INSERT OVERWRITE TABLE orcfile_merge1b PARTITION (ds='1', part) SELECT key, value, PMOD(HASH(key), 2) as part FROM src PREHOOK: type: QUERY PREHOOK: Input: default@src PREHOOK: Output: default@orcfile_merge1b@ds=1 POSTHOOK: query: INSERT OVERWRITE TABLE orcfile_merge1b PARTITION (ds='1', part) SELECT key, value, PMOD(HASH(key), 2) as part FROM src POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Output: default@orcfile_merge1b@ds=1/part=0 POSTHOOK: Output: default@orcfile_merge1b@ds=1/part=1 POSTHOOK: Lineage: orcfile_merge1b PARTITION(ds=1,part=0).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: orcfile_merge1b PARTITION(ds=1,part=0).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: orcfile_merge1b PARTITION(ds=1,part=1).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: orcfile_merge1b PARTITION(ds=1,part=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] Found 1 items #### A masked pattern was here #### PREHOOK: query: -- auto-merge fast way EXPLAIN INSERT OVERWRITE TABLE orcfile_merge1c PARTITION (ds='1', part) SELECT key, value, PMOD(HASH(key), 2) as part FROM src PREHOOK: type: QUERY POSTHOOK: query: -- auto-merge fast way EXPLAIN INSERT OVERWRITE TABLE orcfile_merge1c PARTITION (ds='1', part) SELECT key, value, PMOD(HASH(key), 2) as part FROM src POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-1 is a root stage Stage-7 depends on stages: Stage-1 , consists of Stage-4, Stage-3, Stage-5 Stage-4 Stage-0 depends on stages: Stage-4, Stage-3, Stage-6 Stage-2 depends on stages: Stage-0 Stage-3 Stage-5 Stage-6 depends on stages: Stage-5 STAGE PLANS: Stage: Stage-1 Map Reduce Map Operator Tree: TableScan alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: UDFToInteger(key) (type: int), value (type: string), (hash(key) pmod 2) (type: int) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde name: default.orcfile_merge1c Stage: Stage-7 Conditional Operator Stage: Stage-4 Move Operator files: hdfs directory: true #### A masked pattern was here #### Stage: Stage-0 Move Operator tables: partition: ds 1 part replace: true table: input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde name: default.orcfile_merge1c Stage: Stage-2 Stats-Aggr Operator Stage: Stage-3 Merge File Operator Map Operator Tree: ORC File Merge Operator merge level: stripe input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat Stage: Stage-5 Merge File Operator Map Operator Tree: ORC File Merge Operator merge level: stripe input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat Stage: Stage-6 Move Operator files: hdfs directory: true #### A masked pattern was here #### PREHOOK: query: INSERT OVERWRITE TABLE orcfile_merge1c PARTITION (ds='1', part) SELECT key, value, PMOD(HASH(key), 2) as part FROM src PREHOOK: type: QUERY PREHOOK: Input: default@src PREHOOK: Output: default@orcfile_merge1c@ds=1 POSTHOOK: query: INSERT OVERWRITE TABLE orcfile_merge1c PARTITION (ds='1', part) SELECT key, value, PMOD(HASH(key), 2) as part FROM src POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Output: default@orcfile_merge1c@ds=1/part=0 POSTHOOK: Output: default@orcfile_merge1c@ds=1/part=1 POSTHOOK: Lineage: orcfile_merge1c PARTITION(ds=1,part=0).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: orcfile_merge1c PARTITION(ds=1,part=0).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: orcfile_merge1c PARTITION(ds=1,part=1).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: orcfile_merge1c PARTITION(ds=1,part=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] Found 1 items #### A masked pattern was here #### PREHOOK: query: -- Verify SELECT SUM(HASH(c)) FROM ( SELECT TRANSFORM(*) USING 'tr \t _' AS (c) FROM orcfile_merge1 WHERE ds='1' ) t PREHOOK: type: QUERY PREHOOK: Input: default@orcfile_merge1 PREHOOK: Input: default@orcfile_merge1@ds=1/part=0 PREHOOK: Input: default@orcfile_merge1@ds=1/part=1 #### A masked pattern was here #### POSTHOOK: query: -- Verify SELECT SUM(HASH(c)) FROM ( SELECT TRANSFORM(*) USING 'tr \t _' AS (c) FROM orcfile_merge1 WHERE ds='1' ) t POSTHOOK: type: QUERY POSTHOOK: Input: default@orcfile_merge1 POSTHOOK: Input: default@orcfile_merge1@ds=1/part=0 POSTHOOK: Input: default@orcfile_merge1@ds=1/part=1 #### A masked pattern was here #### -21975308766 PREHOOK: query: SELECT SUM(HASH(c)) FROM ( SELECT TRANSFORM(*) USING 'tr \t _' AS (c) FROM orcfile_merge1b WHERE ds='1' ) t PREHOOK: type: QUERY PREHOOK: Input: default@orcfile_merge1b PREHOOK: Input: default@orcfile_merge1b@ds=1/part=0 PREHOOK: Input: default@orcfile_merge1b@ds=1/part=1 #### A masked pattern was here #### POSTHOOK: query: SELECT SUM(HASH(c)) FROM ( SELECT TRANSFORM(*) USING 'tr \t _' AS (c) FROM orcfile_merge1b WHERE ds='1' ) t POSTHOOK: type: QUERY POSTHOOK: Input: default@orcfile_merge1b POSTHOOK: Input: default@orcfile_merge1b@ds=1/part=0 POSTHOOK: Input: default@orcfile_merge1b@ds=1/part=1 #### A masked pattern was here #### -21975308766 PREHOOK: query: SELECT SUM(HASH(c)) FROM ( SELECT TRANSFORM(*) USING 'tr \t _' AS (c) FROM orcfile_merge1c WHERE ds='1' ) t PREHOOK: type: QUERY PREHOOK: Input: default@orcfile_merge1c PREHOOK: Input: default@orcfile_merge1c@ds=1/part=0 PREHOOK: Input: default@orcfile_merge1c@ds=1/part=1 #### A masked pattern was here #### POSTHOOK: query: SELECT SUM(HASH(c)) FROM ( SELECT TRANSFORM(*) USING 'tr \t _' AS (c) FROM orcfile_merge1c WHERE ds='1' ) t POSTHOOK: type: QUERY POSTHOOK: Input: default@orcfile_merge1c POSTHOOK: Input: default@orcfile_merge1c@ds=1/part=0 POSTHOOK: Input: default@orcfile_merge1c@ds=1/part=1 #### A masked pattern was here #### -21975308766 PREHOOK: query: select count(*) from orcfile_merge1 PREHOOK: type: QUERY PREHOOK: Input: default@orcfile_merge1 PREHOOK: Input: default@orcfile_merge1@ds=1/part=0 PREHOOK: Input: default@orcfile_merge1@ds=1/part=1 #### A masked pattern was here #### POSTHOOK: query: select count(*) from orcfile_merge1 POSTHOOK: type: QUERY POSTHOOK: Input: default@orcfile_merge1 POSTHOOK: Input: default@orcfile_merge1@ds=1/part=0 POSTHOOK: Input: default@orcfile_merge1@ds=1/part=1 #### A masked pattern was here #### 500 PREHOOK: query: select count(*) from orcfile_merge1b PREHOOK: type: QUERY PREHOOK: Input: default@orcfile_merge1b PREHOOK: Input: default@orcfile_merge1b@ds=1/part=0 PREHOOK: Input: default@orcfile_merge1b@ds=1/part=1 #### A masked pattern was here #### POSTHOOK: query: select count(*) from orcfile_merge1b POSTHOOK: type: QUERY POSTHOOK: Input: default@orcfile_merge1b POSTHOOK: Input: default@orcfile_merge1b@ds=1/part=0 POSTHOOK: Input: default@orcfile_merge1b@ds=1/part=1 #### A masked pattern was here #### 500 PREHOOK: query: select count(*) from orcfile_merge1c PREHOOK: type: QUERY PREHOOK: Input: default@orcfile_merge1c PREHOOK: Input: default@orcfile_merge1c@ds=1/part=0 PREHOOK: Input: default@orcfile_merge1c@ds=1/part=1 #### A masked pattern was here #### POSTHOOK: query: select count(*) from orcfile_merge1c POSTHOOK: type: QUERY POSTHOOK: Input: default@orcfile_merge1c POSTHOOK: Input: default@orcfile_merge1c@ds=1/part=0 POSTHOOK: Input: default@orcfile_merge1c@ds=1/part=1 #### A masked pattern was here #### 500 PREHOOK: query: DROP TABLE orcfile_merge1 PREHOOK: type: DROPTABLE PREHOOK: Input: default@orcfile_merge1 PREHOOK: Output: default@orcfile_merge1 POSTHOOK: query: DROP TABLE orcfile_merge1 POSTHOOK: type: DROPTABLE POSTHOOK: Input: default@orcfile_merge1 POSTHOOK: Output: default@orcfile_merge1 PREHOOK: query: DROP TABLE orcfile_merge1b PREHOOK: type: DROPTABLE PREHOOK: Input: default@orcfile_merge1b PREHOOK: Output: default@orcfile_merge1b POSTHOOK: query: DROP TABLE orcfile_merge1b POSTHOOK: type: DROPTABLE POSTHOOK: Input: default@orcfile_merge1b POSTHOOK: Output: default@orcfile_merge1b PREHOOK: query: DROP TABLE orcfile_merge1c PREHOOK: type: DROPTABLE PREHOOK: Input: default@orcfile_merge1c PREHOOK: Output: default@orcfile_merge1c POSTHOOK: query: DROP TABLE orcfile_merge1c POSTHOOK: type: DROPTABLE POSTHOOK: Input: default@orcfile_merge1c POSTHOOK: Output: default@orcfile_merge1c