PREHOOK: query: -- INCLUDE_HADOOP_MAJOR_VERSIONS(0.20) create table t1(key string, value string) partitioned by (ds string) PREHOOK: type: CREATETABLE POSTHOOK: query: -- INCLUDE_HADOOP_MAJOR_VERSIONS(0.20) create table t1(key string, value string) partitioned by (ds string) POSTHOOK: type: CREATETABLE POSTHOOK: Output: default@t1 PREHOOK: query: create table t2(key string, value string) partitioned by (ds string) PREHOOK: type: CREATETABLE POSTHOOK: query: create table t2(key string, value string) partitioned by (ds string) POSTHOOK: type: CREATETABLE POSTHOOK: Output: default@t2 PREHOOK: query: insert overwrite table t1 partition (ds='1') select key, value from src PREHOOK: type: QUERY PREHOOK: Input: default@src PREHOOK: Output: default@t1@ds=1 POSTHOOK: query: insert overwrite table t1 partition (ds='1') select key, value from src POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Output: default@t1@ds=1 POSTHOOK: Lineage: t1 PARTITION(ds=1).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: t1 PARTITION(ds=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: insert overwrite table t1 partition (ds='2') select key, value from src PREHOOK: type: QUERY PREHOOK: Input: default@src PREHOOK: Output: default@t1@ds=2 POSTHOOK: query: insert overwrite table t1 partition (ds='2') select key, value from src POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Output: default@t1@ds=2 POSTHOOK: Lineage: t1 PARTITION(ds=1).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: t1 PARTITION(ds=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: t1 PARTITION(ds=2).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: t1 PARTITION(ds=2).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: insert overwrite table t2 partition (ds='1') select key, value from src PREHOOK: type: QUERY PREHOOK: Input: default@src PREHOOK: Output: default@t2@ds=1 POSTHOOK: query: insert overwrite table t2 partition (ds='1') select key, value from src POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Output: default@t2@ds=1 POSTHOOK: Lineage: t1 PARTITION(ds=1).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: t1 PARTITION(ds=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: t1 PARTITION(ds=2).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: t1 PARTITION(ds=2).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: t2 PARTITION(ds=1).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: t2 PARTITION(ds=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: explain select count(1) from t1 join t2 on t1.key=t2.key where t1.ds='1' and t2.ds='1' PREHOOK: type: QUERY POSTHOOK: query: explain select count(1) from t1 join t2 on t1.key=t2.key where t1.ds='1' and t2.ds='1' POSTHOOK: type: QUERY POSTHOOK: Lineage: t1 PARTITION(ds=1).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: t1 PARTITION(ds=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: t1 PARTITION(ds=2).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: t1 PARTITION(ds=2).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: t2 PARTITION(ds=1).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: t2 PARTITION(ds=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] ABSTRACT SYNTAX TREE: (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_TABREF (TOK_TABNAME t1)) (TOK_TABREF (TOK_TABNAME t2)) (= (. (TOK_TABLE_OR_COL t1) key) (. (TOK_TABLE_OR_COL t2) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_FUNCTION count 1))) (TOK_WHERE (and (= (. (TOK_TABLE_OR_COL t1) ds) '1') (= (. (TOK_TABLE_OR_COL t2) ds) '1'))))) STAGE DEPENDENCIES: Stage-1 is a root stage Stage-2 depends on stages: Stage-1 Stage-0 is a root stage STAGE PLANS: Stage: Stage-1 Map Reduce Alias -> Map Operator Tree: t1 TableScan alias: t1 Filter Operator predicate: expr: (((hash(rand(460476415)) & 2147483647) % 32) = 0) type: boolean Reduce Output Operator key expressions: expr: key type: string sort order: + Map-reduce partition columns: expr: key type: string tag: 0 value expressions: expr: ds type: string t2 TableScan alias: t2 Filter Operator predicate: expr: (((hash(rand(460476415)) & 2147483647) % 32) = 0) type: boolean Reduce Output Operator key expressions: expr: key type: string sort order: + Map-reduce partition columns: expr: key type: string tag: 1 value expressions: expr: ds type: string Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 condition expressions: 0 {VALUE._col2} 1 {VALUE._col2} handleSkewJoin: false outputColumnNames: _col2, _col7 Select Operator Group By Operator aggregations: expr: count(1) bucketGroup: false mode: hash outputColumnNames: _col0 File Output Operator compressed: false GlobalTableId: 0 table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat Stage: Stage-2 Map Reduce Alias -> Map Operator Tree: #### A masked pattern was here #### Reduce Output Operator sort order: tag: -1 value expressions: expr: _col0 type: bigint Reduce Operator Tree: Group By Operator aggregations: expr: count(VALUE._col0) bucketGroup: false mode: mergepartial outputColumnNames: _col0 Select Operator expressions: expr: _col0 type: bigint outputColumnNames: _col0 File Output Operator compressed: false GlobalTableId: 0 table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat Stage: Stage-0 Fetch Operator limit: -1 PREHOOK: query: select count(1) from t1 join t2 on t1.key=t2.key where t1.ds='1' and t2.ds='1' PREHOOK: type: QUERY PREHOOK: Input: default@t1@ds=1 PREHOOK: Input: default@t2@ds=1 #### A masked pattern was here #### POSTHOOK: query: select count(1) from t1 join t2 on t1.key=t2.key where t1.ds='1' and t2.ds='1' POSTHOOK: type: QUERY POSTHOOK: Input: default@t1@ds=1 POSTHOOK: Input: default@t2@ds=1 #### A masked pattern was here #### POSTHOOK: Lineage: t1 PARTITION(ds=1).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: t1 PARTITION(ds=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: t1 PARTITION(ds=2).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: t1 PARTITION(ds=2).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: t2 PARTITION(ds=1).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: t2 PARTITION(ds=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] 18 mapred.job.tracker=localhost:58