PREHOOK: query: CREATE TABLE tmpT1(key STRING, val STRING) STORED AS TEXTFILE PREHOOK: type: CREATETABLE PREHOOK: Output: database:default PREHOOK: Output: default@tmpT1 POSTHOOK: query: CREATE TABLE tmpT1(key STRING, val STRING) STORED AS TEXTFILE POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default POSTHOOK: Output: default@tmpT1 PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T1.txt' INTO TABLE tmpT1 PREHOOK: type: LOAD #### A masked pattern was here #### PREHOOK: Output: default@tmpt1 POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T1.txt' INTO TABLE tmpT1 POSTHOOK: type: LOAD #### A masked pattern was here #### POSTHOOK: Output: default@tmpt1 PREHOOK: query: -- testing skew on other data types - int CREATE TABLE T1(key INT, val STRING) SKEWED BY (key) ON ((2)) PREHOOK: type: CREATETABLE PREHOOK: Output: database:default PREHOOK: Output: default@T1 POSTHOOK: query: -- testing skew on other data types - int CREATE TABLE T1(key INT, val STRING) SKEWED BY (key) ON ((2)) POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default POSTHOOK: Output: default@T1 PREHOOK: query: INSERT OVERWRITE TABLE T1 SELECT key, val FROM tmpT1 PREHOOK: type: QUERY PREHOOK: Input: default@tmpt1 PREHOOK: Output: default@t1 POSTHOOK: query: INSERT OVERWRITE TABLE T1 SELECT key, val FROM tmpT1 POSTHOOK: type: QUERY POSTHOOK: Input: default@tmpt1 POSTHOOK: Output: default@t1 POSTHOOK: Lineage: t1.key EXPRESSION [(tmpt1)tmpt1.FieldSchema(name:key, type:string, comment:null), ] POSTHOOK: Lineage: t1.val SIMPLE [(tmpt1)tmpt1.FieldSchema(name:val, type:string, comment:null), ] PREHOOK: query: -- Tke skewed column is same in both the tables, however it is -- INT in one of the tables, and STRING in the other table CREATE TABLE T2(key STRING, val STRING) SKEWED BY (key) ON ((3)) STORED AS TEXTFILE PREHOOK: type: CREATETABLE PREHOOK: Output: database:default PREHOOK: Output: default@T2 POSTHOOK: query: -- Tke skewed column is same in both the tables, however it is -- INT in one of the tables, and STRING in the other table CREATE TABLE T2(key STRING, val STRING) SKEWED BY (key) ON ((3)) STORED AS TEXTFILE POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default POSTHOOK: Output: default@T2 PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T2.txt' INTO TABLE T2 PREHOOK: type: LOAD #### A masked pattern was here #### PREHOOK: Output: default@t2 POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T2.txt' INTO TABLE T2 POSTHOOK: type: LOAD #### A masked pattern was here #### POSTHOOK: Output: default@t2 PREHOOK: query: -- Once HIVE-3445 is fixed, the compile time skew join optimization would be -- applicable here. Till the above jira is fixed, it would be performed as a -- regular join -- adding a order by at the end to make the results deterministic EXPLAIN SELECT a.*, b.* FROM T1 a JOIN T2 b ON a.key = b.key PREHOOK: type: QUERY POSTHOOK: query: -- Once HIVE-3445 is fixed, the compile time skew join optimization would be -- applicable here. Till the above jira is fixed, it would be performed as a -- regular join -- adding a order by at the end to make the results deterministic EXPLAIN SELECT a.*, b.* FROM T1 a JOIN T2 b ON a.key = b.key POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-1 is a root stage Stage-0 depends on stages: Stage-1 STAGE PLANS: Stage: Stage-1 Map Reduce Map Operator Tree: TableScan alias: a Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: UDFToDouble(key) is not null (type: boolean) Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: UDFToDouble(key) (type: double) sort order: + Map-reduce partition columns: UDFToDouble(key) (type: double) Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE value expressions: key (type: int), val (type: string) TableScan alias: b Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE Filter Operator predicate: UDFToDouble(key) is not null (type: boolean) Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Reduce Output Operator key expressions: UDFToDouble(key) (type: double) sort order: + Map-reduce partition columns: UDFToDouble(key) (type: double) Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE value expressions: key (type: string), val (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: 0 UDFToDouble(key) (type: double) 1 UDFToDouble(key) (type: double) outputColumnNames: _col0, _col1, _col5, _col6 Statistics: Num rows: 3 Data size: 13 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), _col1 (type: string), _col5 (type: string), _col6 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 3 Data size: 13 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false Statistics: Num rows: 3 Data size: 13 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator limit: -1 Processor Tree: ListSink PREHOOK: query: SELECT a.*, b.* FROM T1 a JOIN T2 b ON a.key = b.key ORDER BY a.key, b.key, a.val, b.val PREHOOK: type: QUERY PREHOOK: Input: default@t1 PREHOOK: Input: default@t2 #### A masked pattern was here #### POSTHOOK: query: SELECT a.*, b.* FROM T1 a JOIN T2 b ON a.key = b.key ORDER BY a.key, b.key, a.val, b.val POSTHOOK: type: QUERY POSTHOOK: Input: default@t1 POSTHOOK: Input: default@t2 #### A masked pattern was here #### 2 12 2 22 3 13 3 13 8 18 8 18 8 18 8 18 8 28 8 18 8 28 8 18