PREHOOK: query: CREATE TABLE dest1(c1 DOUBLE, c2 DOUBLE, c3 DOUBLE, c4 DOUBLE, c5 DOUBLE, c6 DOUBLE, c7 DOUBLE, c8 DOUBLE, c9 DOUBLE) STORED AS TEXTFILE PREHOOK: type: CREATETABLE POSTHOOK: query: CREATE TABLE dest1(c1 DOUBLE, c2 DOUBLE, c3 DOUBLE, c4 DOUBLE, c5 DOUBLE, c6 DOUBLE, c7 DOUBLE, c8 DOUBLE, c9 DOUBLE) STORED AS TEXTFILE POSTHOOK: type: CREATETABLE POSTHOOK: Output: default@dest1 PREHOOK: query: EXPLAIN FROM src INSERT OVERWRITE TABLE dest1 SELECT sum(substr(src.value,5)), avg(substr(src.value,5)), avg(DISTINCT substr(src.value,5)), max(substr(src.value,5)), min(substr(src.value,5)), std(substr(src.value,5)), stddev_samp(substr(src.value,5)), variance(substr(src.value,5)), var_samp(substr(src.value,5)) PREHOOK: type: QUERY POSTHOOK: query: EXPLAIN FROM src INSERT OVERWRITE TABLE dest1 SELECT sum(substr(src.value,5)), avg(substr(src.value,5)), avg(DISTINCT substr(src.value,5)), max(substr(src.value,5)), min(substr(src.value,5)), std(substr(src.value,5)), stddev_samp(substr(src.value,5)), variance(substr(src.value,5)), var_samp(substr(src.value,5)) POSTHOOK: type: QUERY ABSTRACT SYNTAX TREE: (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME src))) (TOK_INSERT (TOK_DESTINATION (TOK_TAB (TOK_TABNAME dest1))) (TOK_SELECT (TOK_SELEXPR (TOK_FUNCTION sum (TOK_FUNCTION substr (. (TOK_TABLE_OR_COL src) value) 5))) (TOK_SELEXPR (TOK_FUNCTION avg (TOK_FUNCTION substr (. (TOK_TABLE_OR_COL src) value) 5))) (TOK_SELEXPR (TOK_FUNCTIONDI avg (TOK_FUNCTION substr (. (TOK_TABLE_OR_COL src) value) 5))) (TOK_SELEXPR (TOK_FUNCTION max (TOK_FUNCTION substr (. (TOK_TABLE_OR_COL src) value) 5))) (TOK_SELEXPR (TOK_FUNCTION min (TOK_FUNCTION substr (. (TOK_TABLE_OR_COL src) value) 5))) (TOK_SELEXPR (TOK_FUNCTION std (TOK_FUNCTION substr (. (TOK_TABLE_OR_COL src) value) 5))) (TOK_SELEXPR (TOK_FUNCTION stddev_samp (TOK_FUNCTION substr (. (TOK_TABLE_OR_COL src) value) 5))) (TOK_SELEXPR (TOK_FUNCTION variance (TOK_FUNCTION substr (. (TOK_TABLE_OR_COL src) value) 5))) (TOK_SELEXPR (TOK_FUNCTION var_samp (TOK_FUNCTION substr (. (TOK_TABLE_OR_COL src) value) 5)))))) 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 Alias -> Map Operator Tree: src TableScan alias: src Select Operator expressions: expr: value type: string outputColumnNames: value Reduce Output Operator key expressions: expr: substr(value, 5) type: string sort order: + tag: -1 Reduce Operator Tree: Group By Operator aggregations: expr: sum(KEY._col0:0._col0) expr: avg(KEY._col0:0._col0) expr: avg(DISTINCT KEY._col0:0._col0) expr: max(KEY._col0:0._col0) expr: min(KEY._col0:0._col0) expr: std(KEY._col0:0._col0) expr: stddev_samp(KEY._col0:0._col0) expr: variance(KEY._col0:0._col0) expr: var_samp(KEY._col0:0._col0) bucketGroup: false mode: complete outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 Select Operator expressions: expr: _col0 type: double expr: _col1 type: double expr: _col2 type: double expr: _col3 type: string expr: _col4 type: string expr: _col5 type: double expr: _col6 type: double expr: _col7 type: double expr: _col8 type: double outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 Select Operator expressions: expr: _col0 type: double expr: _col1 type: double expr: _col2 type: double expr: UDFToDouble(_col3) type: double expr: UDFToDouble(_col4) type: double expr: _col5 type: double expr: _col6 type: double expr: _col7 type: double expr: _col8 type: double outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 File Output Operator compressed: false GlobalTableId: 1 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 name: default.dest1 Stage: Stage-0 Move Operator tables: replace: true 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 name: default.dest1 Stage: Stage-2 Stats-Aggr Operator PREHOOK: query: FROM src INSERT OVERWRITE TABLE dest1 SELECT sum(substr(src.value,5)), avg(substr(src.value,5)), avg(DISTINCT substr(src.value,5)), max(substr(src.value,5)), min(substr(src.value,5)), std(substr(src.value,5)), stddev_samp(substr(src.value,5)), variance(substr(src.value,5)), var_samp(substr(src.value,5)) PREHOOK: type: QUERY PREHOOK: Input: default@src PREHOOK: Output: default@dest1 POSTHOOK: query: FROM src INSERT OVERWRITE TABLE dest1 SELECT sum(substr(src.value,5)), avg(substr(src.value,5)), avg(DISTINCT substr(src.value,5)), max(substr(src.value,5)), min(substr(src.value,5)), std(substr(src.value,5)), stddev_samp(substr(src.value,5)), variance(substr(src.value,5)), var_samp(substr(src.value,5)) POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Output: default@dest1 POSTHOOK: Lineage: dest1.c1 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: dest1.c2 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: dest1.c3 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: dest1.c4 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: dest1.c5 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: dest1.c6 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: dest1.c7 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: dest1.c8 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: dest1.c9 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: SELECT dest1.* FROM dest1 PREHOOK: type: QUERY PREHOOK: Input: default@dest1 PREHOOK: Output: file:/tmp/sdong/hive_2011-02-10_01-50-51_210_190586667911739988/-mr-10000 POSTHOOK: query: SELECT dest1.* FROM dest1 POSTHOOK: type: QUERY POSTHOOK: Input: default@dest1 POSTHOOK: Output: file:/tmp/sdong/hive_2011-02-10_01-50-51_210_190586667911739988/-mr-10000 POSTHOOK: Lineage: dest1.c1 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: dest1.c2 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: dest1.c3 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: dest1.c4 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: dest1.c5 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: dest1.c6 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: dest1.c7 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: dest1.c8 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: dest1.c9 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] 130091.0 260.182 256.10355987055016 98.0 0.0 142.92680950752379 143.06995106518903 20428.07287599999 20469.010897795582