PREHOOK: query: create table src2 as select key, count(1) as count from src group by key PREHOOK: type: CREATETABLE_AS_SELECT PREHOOK: Input: default@src POSTHOOK: query: create table src2 as select key, count(1) as count from src group by key POSTHOOK: type: CREATETABLE_AS_SELECT POSTHOOK: Input: default@src POSTHOOK: Output: default@src2 PREHOOK: query: create table src3 as select * from src2 PREHOOK: type: CREATETABLE_AS_SELECT PREHOOK: Input: default@src2 POSTHOOK: query: create table src3 as select * from src2 POSTHOOK: type: CREATETABLE_AS_SELECT POSTHOOK: Input: default@src2 POSTHOOK: Output: default@src3 PREHOOK: query: create table src4 as select * from src2 PREHOOK: type: CREATETABLE_AS_SELECT PREHOOK: Input: default@src2 POSTHOOK: query: create table src4 as select * from src2 POSTHOOK: type: CREATETABLE_AS_SELECT POSTHOOK: Input: default@src2 POSTHOOK: Output: default@src4 PREHOOK: query: create table src5 as select * from src2 PREHOOK: type: CREATETABLE_AS_SELECT PREHOOK: Input: default@src2 POSTHOOK: query: create table src5 as select * from src2 POSTHOOK: type: CREATETABLE_AS_SELECT POSTHOOK: Input: default@src2 POSTHOOK: Output: default@src5 PREHOOK: query: explain extended select s.key, s.count from ( select key, count from src2 where key < 10 union all select key, count from src3 where key < 10 union all select key, count from src4 where key < 10 union all select key, count(1) as count from src5 where key < 10 group by key )s order by s.key PREHOOK: type: QUERY POSTHOOK: query: explain extended select s.key, s.count from ( select key, count from src2 where key < 10 union all select key, count from src3 where key < 10 union all select key, count from src4 where key < 10 union all select key, count(1) as count from src5 where key < 10 group by key )s order by s.key POSTHOOK: type: QUERY ABSTRACT SYNTAX TREE: (TOK_QUERY (TOK_FROM (TOK_SUBQUERY (TOK_UNION (TOK_UNION (TOK_UNION (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME src2))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL key)) (TOK_SELEXPR (TOK_TABLE_OR_COL count))) (TOK_WHERE (< (TOK_TABLE_OR_COL key) 10)))) (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME src3))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL key)) (TOK_SELEXPR (TOK_TABLE_OR_COL count))) (TOK_WHERE (< (TOK_TABLE_OR_COL key) 10))))) (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME src4))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL key)) (TOK_SELEXPR (TOK_TABLE_OR_COL count))) (TOK_WHERE (< (TOK_TABLE_OR_COL key) 10))))) (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME src5))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL key)) (TOK_SELEXPR (TOK_FUNCTION count 1) count)) (TOK_WHERE (< (TOK_TABLE_OR_COL key) 10)) (TOK_GROUPBY (TOK_TABLE_OR_COL key))))) s)) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL s) key)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL s) count))) (TOK_ORDERBY (TOK_TABSORTCOLNAMEASC (. (TOK_TABLE_OR_COL s) key))))) STAGE DEPENDENCIES: Stage-1 is a root stage Stage-2 depends on stages: Stage-1, Stage-3, Stage-4, Stage-5 Stage-3 is a root stage Stage-4 is a root stage Stage-5 is a root stage Stage-0 is a root stage STAGE PLANS: Stage: Stage-1 Map Reduce Alias -> Map Operator Tree: null-subquery1-subquery2:s-subquery1-subquery2:src4 TableScan alias: src4 GatherStats: false Filter Operator isSamplingPred: false predicate: expr: (key < 10) type: boolean Select Operator expressions: expr: key type: string expr: count type: bigint outputColumnNames: _col0, _col1 File Output Operator compressed: false GlobalTableId: 0 directory: file:/tmp/njain/hive_2011-12-07_18-05-41_298_8482350737870409263/-mr-10002 NumFilesPerFileSink: 1 table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col0,_col1 columns.types string,bigint escape.delim \ TotalFiles: 1 GatherStats: false MultiFileSpray: false Needs Tagging: false Path -> Alias: pfile:/data/users/njain/hive_commit2/build/ql/test/data/warehouse/src4 [null-subquery1-subquery2:s-subquery1-subquery2:src4] Path -> Partition: pfile:/data/users/njain/hive_commit2/build/ql/test/data/warehouse/src4 Partition base file name: src4 input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: bucket_count -1 columns key,count columns.types string:bigint file.inputformat org.apache.hadoop.mapred.TextInputFormat file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat location pfile:/data/users/njain/hive_commit2/build/ql/test/data/warehouse/src4 name default.src4 numFiles 1 numPartitions 0 numRows 309 rawDataSize 1482 serialization.ddl struct src4 { string key, i64 count} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe totalSize 1791 transient_lastDdlTime 1323309936 serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: bucket_count -1 columns key,count columns.types string:bigint file.inputformat org.apache.hadoop.mapred.TextInputFormat file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat location pfile:/data/users/njain/hive_commit2/build/ql/test/data/warehouse/src4 name default.src4 numFiles 1 numPartitions 0 numRows 309 rawDataSize 1482 serialization.ddl struct src4 { string key, i64 count} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe totalSize 1791 transient_lastDdlTime 1323309936 serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.src4 name: default.src4 Stage: Stage-2 Map Reduce Alias -> Map Operator Tree: file:/tmp/njain/hive_2011-12-07_18-05-41_298_8482350737870409263/-mr-10002 Union Select Operator expressions: expr: _col0 type: string expr: _col1 type: bigint outputColumnNames: _col0, _col1 Reduce Output Operator key expressions: expr: _col0 type: string sort order: + tag: -1 value expressions: expr: _col0 type: string expr: _col1 type: bigint file:/tmp/njain/hive_2011-12-07_18-05-41_298_8482350737870409263/-mr-10003 Union Select Operator expressions: expr: _col0 type: string expr: _col1 type: bigint outputColumnNames: _col0, _col1 Reduce Output Operator key expressions: expr: _col0 type: string sort order: + tag: -1 value expressions: expr: _col0 type: string expr: _col1 type: bigint file:/tmp/njain/hive_2011-12-07_18-05-41_298_8482350737870409263/-mr-10004 Union Select Operator expressions: expr: _col0 type: string expr: _col1 type: bigint outputColumnNames: _col0, _col1 Reduce Output Operator key expressions: expr: _col0 type: string sort order: + tag: -1 value expressions: expr: _col0 type: string expr: _col1 type: bigint file:/tmp/njain/hive_2011-12-07_18-05-41_298_8482350737870409263/-mr-10005 Union Select Operator expressions: expr: _col0 type: string expr: _col1 type: bigint outputColumnNames: _col0, _col1 Reduce Output Operator key expressions: expr: _col0 type: string sort order: + tag: -1 value expressions: expr: _col0 type: string expr: _col1 type: bigint Needs Tagging: false Path -> Alias: file:/tmp/njain/hive_2011-12-07_18-05-41_298_8482350737870409263/-mr-10002 [file:/tmp/njain/hive_2011-12-07_18-05-41_298_8482350737870409263/-mr-10002] file:/tmp/njain/hive_2011-12-07_18-05-41_298_8482350737870409263/-mr-10003 [file:/tmp/njain/hive_2011-12-07_18-05-41_298_8482350737870409263/-mr-10003] file:/tmp/njain/hive_2011-12-07_18-05-41_298_8482350737870409263/-mr-10004 [file:/tmp/njain/hive_2011-12-07_18-05-41_298_8482350737870409263/-mr-10004] file:/tmp/njain/hive_2011-12-07_18-05-41_298_8482350737870409263/-mr-10005 [file:/tmp/njain/hive_2011-12-07_18-05-41_298_8482350737870409263/-mr-10005] Path -> Partition: file:/tmp/njain/hive_2011-12-07_18-05-41_298_8482350737870409263/-mr-10002 Partition base file name: -mr-10002 input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col0,_col1 columns.types string,bigint escape.delim \ input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col0,_col1 columns.types string,bigint escape.delim \ file:/tmp/njain/hive_2011-12-07_18-05-41_298_8482350737870409263/-mr-10003 Partition base file name: -mr-10003 input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col0,_col1 columns.types string,bigint escape.delim \ input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col0,_col1 columns.types string,bigint escape.delim \ file:/tmp/njain/hive_2011-12-07_18-05-41_298_8482350737870409263/-mr-10004 Partition base file name: -mr-10004 input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col0,_col1 columns.types string,bigint escape.delim \ input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col0,_col1 columns.types string,bigint escape.delim \ file:/tmp/njain/hive_2011-12-07_18-05-41_298_8482350737870409263/-mr-10005 Partition base file name: -mr-10005 input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col0,_col1 columns.types string,bigint escape.delim \ input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col0,_col1 columns.types string,bigint escape.delim \ Reduce Operator Tree: Extract File Output Operator compressed: false GlobalTableId: 0 directory: file:/tmp/njain/hive_2011-12-07_18-05-41_298_8482350737870409263/-ext-10001 NumFilesPerFileSink: 1 Stats Publishing Key Prefix: file:/tmp/njain/hive_2011-12-07_18-05-41_298_8482350737870409263/-ext-10001/ table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: columns _col0,_col1 columns.types string:bigint escape.delim \ serialization.format 1 TotalFiles: 1 GatherStats: false MultiFileSpray: false Stage: Stage-3 Map Reduce Alias -> Map Operator Tree: null-subquery2:s-subquery2:src5 TableScan alias: src5 GatherStats: false Filter Operator isSamplingPred: false predicate: expr: (key < 10) type: boolean Select Operator expressions: expr: key type: string outputColumnNames: key Group By Operator aggregations: expr: count(1) bucketGroup: false keys: expr: key type: string mode: hash outputColumnNames: _col0, _col1 Reduce Output Operator key expressions: expr: _col0 type: string sort order: + Map-reduce partition columns: expr: _col0 type: string tag: -1 value expressions: expr: _col1 type: bigint Needs Tagging: false Path -> Alias: pfile:/data/users/njain/hive_commit2/build/ql/test/data/warehouse/src5 [null-subquery2:s-subquery2:src5] Path -> Partition: pfile:/data/users/njain/hive_commit2/build/ql/test/data/warehouse/src5 Partition base file name: src5 input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: bucket_count -1 columns key,count columns.types string:bigint file.inputformat org.apache.hadoop.mapred.TextInputFormat file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat location pfile:/data/users/njain/hive_commit2/build/ql/test/data/warehouse/src5 name default.src5 numFiles 1 numPartitions 0 numRows 309 rawDataSize 1482 serialization.ddl struct src5 { string key, i64 count} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe totalSize 1791 transient_lastDdlTime 1323309941 serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: bucket_count -1 columns key,count columns.types string:bigint file.inputformat org.apache.hadoop.mapred.TextInputFormat file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat location pfile:/data/users/njain/hive_commit2/build/ql/test/data/warehouse/src5 name default.src5 numFiles 1 numPartitions 0 numRows 309 rawDataSize 1482 serialization.ddl struct src5 { string key, i64 count} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe totalSize 1791 transient_lastDdlTime 1323309941 serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.src5 name: default.src5 Reduce Operator Tree: Group By Operator aggregations: expr: count(VALUE._col0) bucketGroup: false keys: expr: KEY._col0 type: string mode: mergepartial outputColumnNames: _col0, _col1 Select Operator expressions: expr: _col0 type: string expr: _col1 type: bigint outputColumnNames: _col0, _col1 File Output Operator compressed: false GlobalTableId: 0 directory: file:/tmp/njain/hive_2011-12-07_18-05-41_298_8482350737870409263/-mr-10003 NumFilesPerFileSink: 1 table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col0,_col1 columns.types string,bigint escape.delim \ TotalFiles: 1 GatherStats: false MultiFileSpray: false Stage: Stage-4 Map Reduce Alias -> Map Operator Tree: null-subquery1-subquery1-subquery2:s-subquery1-subquery1-subquery2:src3 TableScan alias: src3 GatherStats: false Filter Operator isSamplingPred: false predicate: expr: (key < 10) type: boolean Select Operator expressions: expr: key type: string expr: count type: bigint outputColumnNames: _col0, _col1 File Output Operator compressed: false GlobalTableId: 0 directory: file:/tmp/njain/hive_2011-12-07_18-05-41_298_8482350737870409263/-mr-10004 NumFilesPerFileSink: 1 table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col0,_col1 columns.types string,bigint escape.delim \ TotalFiles: 1 GatherStats: false MultiFileSpray: false Needs Tagging: false Path -> Alias: pfile:/data/users/njain/hive_commit2/build/ql/test/data/warehouse/src3 [null-subquery1-subquery1-subquery2:s-subquery1-subquery1-subquery2:src3] Path -> Partition: pfile:/data/users/njain/hive_commit2/build/ql/test/data/warehouse/src3 Partition base file name: src3 input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: bucket_count -1 columns key,count columns.types string:bigint file.inputformat org.apache.hadoop.mapred.TextInputFormat file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat location pfile:/data/users/njain/hive_commit2/build/ql/test/data/warehouse/src3 name default.src3 numFiles 1 numPartitions 0 numRows 309 rawDataSize 1482 serialization.ddl struct src3 { string key, i64 count} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe totalSize 1791 transient_lastDdlTime 1323309930 serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: bucket_count -1 columns key,count columns.types string:bigint file.inputformat org.apache.hadoop.mapred.TextInputFormat file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat location pfile:/data/users/njain/hive_commit2/build/ql/test/data/warehouse/src3 name default.src3 numFiles 1 numPartitions 0 numRows 309 rawDataSize 1482 serialization.ddl struct src3 { string key, i64 count} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe totalSize 1791 transient_lastDdlTime 1323309930 serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.src3 name: default.src3 Stage: Stage-5 Map Reduce Alias -> Map Operator Tree: null-subquery1-subquery1-subquery1:s-subquery1-subquery1-subquery1:src2 TableScan alias: src2 GatherStats: false Filter Operator isSamplingPred: false predicate: expr: (key < 10) type: boolean Select Operator expressions: expr: key type: string expr: count type: bigint outputColumnNames: _col0, _col1 File Output Operator compressed: false GlobalTableId: 0 directory: file:/tmp/njain/hive_2011-12-07_18-05-41_298_8482350737870409263/-mr-10005 NumFilesPerFileSink: 1 table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col0,_col1 columns.types string,bigint escape.delim \ TotalFiles: 1 GatherStats: false MultiFileSpray: false Needs Tagging: false Path -> Alias: pfile:/data/users/njain/hive_commit2/build/ql/test/data/warehouse/src2 [null-subquery1-subquery1-subquery1:s-subquery1-subquery1-subquery1:src2] Path -> Partition: pfile:/data/users/njain/hive_commit2/build/ql/test/data/warehouse/src2 Partition base file name: src2 input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: bucket_count -1 columns key,count columns.types string:bigint file.inputformat org.apache.hadoop.mapred.TextInputFormat file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat location pfile:/data/users/njain/hive_commit2/build/ql/test/data/warehouse/src2 name default.src2 numFiles 1 numPartitions 0 numRows 309 rawDataSize 1482 serialization.ddl struct src2 { string key, i64 count} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe totalSize 1791 transient_lastDdlTime 1323309926 serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: bucket_count -1 columns key,count columns.types string:bigint file.inputformat org.apache.hadoop.mapred.TextInputFormat file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat location pfile:/data/users/njain/hive_commit2/build/ql/test/data/warehouse/src2 name default.src2 numFiles 1 numPartitions 0 numRows 309 rawDataSize 1482 serialization.ddl struct src2 { string key, i64 count} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe totalSize 1791 transient_lastDdlTime 1323309926 serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.src2 name: default.src2 Stage: Stage-0 Fetch Operator limit: -1 PREHOOK: query: select s.key, s.count from ( select key, count from src2 where key < 10 union all select key, count from src3 where key < 10 union all select key, count from src4 where key < 10 union all select key, count(1) as count from src5 where key < 10 group by key )s order by s.key PREHOOK: type: QUERY PREHOOK: Input: default@src2 PREHOOK: Input: default@src3 PREHOOK: Input: default@src4 PREHOOK: Input: default@src5 PREHOOK: Output: file:/tmp/njain/hive_2011-12-07_18-05-41_450_3758431232103877540/-mr-10000 POSTHOOK: query: select s.key, s.count from ( select key, count from src2 where key < 10 union all select key, count from src3 where key < 10 union all select key, count from src4 where key < 10 union all select key, count(1) as count from src5 where key < 10 group by key )s order by s.key POSTHOOK: type: QUERY POSTHOOK: Input: default@src2 POSTHOOK: Input: default@src3 POSTHOOK: Input: default@src4 POSTHOOK: Input: default@src5 POSTHOOK: Output: file:/tmp/njain/hive_2011-12-07_18-05-41_450_3758431232103877540/-mr-10000 0 3 0 1 0 3 0 3 2 1 2 1 2 1 2 1 4 1 4 1 4 1 4 1 5 3 5 3 5 1 5 3 8 1 8 1 8 1 8 1 9 1 9 1 9 1 9 1 PREHOOK: query: explain extended select s.key, s.count from ( select key, count from src2 where key < 10 union all select key, count from src3 where key < 10 union all select a.key as key, b.count as count from src4 a join src5 b on a.key=b.key where a.key < 10 )s order by s.key PREHOOK: type: QUERY POSTHOOK: query: explain extended select s.key, s.count from ( select key, count from src2 where key < 10 union all select key, count from src3 where key < 10 union all select a.key as key, b.count as count from src4 a join src5 b on a.key=b.key where a.key < 10 )s order by s.key POSTHOOK: type: QUERY ABSTRACT SYNTAX TREE: (TOK_QUERY (TOK_FROM (TOK_SUBQUERY (TOK_UNION (TOK_UNION (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME src2))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL key)) (TOK_SELEXPR (TOK_TABLE_OR_COL count))) (TOK_WHERE (< (TOK_TABLE_OR_COL key) 10)))) (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME src3))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL key)) (TOK_SELEXPR (TOK_TABLE_OR_COL count))) (TOK_WHERE (< (TOK_TABLE_OR_COL key) 10))))) (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_TABREF (TOK_TABNAME src4) a) (TOK_TABREF (TOK_TABNAME src5) b) (= (. (TOK_TABLE_OR_COL a) key) (. (TOK_TABLE_OR_COL b) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL a) key) key) (TOK_SELEXPR (. (TOK_TABLE_OR_COL b) count) count)) (TOK_WHERE (< (. (TOK_TABLE_OR_COL a) key) 10))))) s)) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL s) key)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL s) count))) (TOK_ORDERBY (TOK_TABSORTCOLNAMEASC (. (TOK_TABLE_OR_COL s) key))))) STAGE DEPENDENCIES: Stage-1 is a root stage Stage-2 depends on stages: Stage-1, Stage-4, Stage-5 Stage-4 is a root stage Stage-5 is a root stage Stage-0 is a root stage STAGE PLANS: Stage: Stage-1 Map Reduce Alias -> Map Operator Tree: null-subquery2:s-subquery2:a TableScan alias: a GatherStats: false Filter Operator isSamplingPred: false predicate: expr: (key < 10) 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: key type: string null-subquery2:s-subquery2:b TableScan alias: b GatherStats: false Filter Operator isSamplingPred: false predicate: expr: (key < 10) 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: count type: bigint Needs Tagging: true Path -> Alias: pfile:/data/users/njain/hive_commit2/build/ql/test/data/warehouse/src4 [null-subquery2:s-subquery2:a] pfile:/data/users/njain/hive_commit2/build/ql/test/data/warehouse/src5 [null-subquery2:s-subquery2:b] Path -> Partition: pfile:/data/users/njain/hive_commit2/build/ql/test/data/warehouse/src4 Partition base file name: src4 input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: bucket_count -1 columns key,count columns.types string:bigint file.inputformat org.apache.hadoop.mapred.TextInputFormat file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat location pfile:/data/users/njain/hive_commit2/build/ql/test/data/warehouse/src4 name default.src4 numFiles 1 numPartitions 0 numRows 309 rawDataSize 1482 serialization.ddl struct src4 { string key, i64 count} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe totalSize 1791 transient_lastDdlTime 1323309936 serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: bucket_count -1 columns key,count columns.types string:bigint file.inputformat org.apache.hadoop.mapred.TextInputFormat file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat location pfile:/data/users/njain/hive_commit2/build/ql/test/data/warehouse/src4 name default.src4 numFiles 1 numPartitions 0 numRows 309 rawDataSize 1482 serialization.ddl struct src4 { string key, i64 count} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe totalSize 1791 transient_lastDdlTime 1323309936 serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.src4 name: default.src4 pfile:/data/users/njain/hive_commit2/build/ql/test/data/warehouse/src5 Partition base file name: src5 input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: bucket_count -1 columns key,count columns.types string:bigint file.inputformat org.apache.hadoop.mapred.TextInputFormat file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat location pfile:/data/users/njain/hive_commit2/build/ql/test/data/warehouse/src5 name default.src5 numFiles 1 numPartitions 0 numRows 309 rawDataSize 1482 serialization.ddl struct src5 { string key, i64 count} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe totalSize 1791 transient_lastDdlTime 1323309941 serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: bucket_count -1 columns key,count columns.types string:bigint file.inputformat org.apache.hadoop.mapred.TextInputFormat file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat location pfile:/data/users/njain/hive_commit2/build/ql/test/data/warehouse/src5 name default.src5 numFiles 1 numPartitions 0 numRows 309 rawDataSize 1482 serialization.ddl struct src5 { string key, i64 count} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe totalSize 1791 transient_lastDdlTime 1323309941 serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.src5 name: default.src5 Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 condition expressions: 0 {VALUE._col0} 1 {VALUE._col1} handleSkewJoin: false outputColumnNames: _col0, _col5 Select Operator expressions: expr: _col0 type: string expr: _col5 type: bigint outputColumnNames: _col0, _col1 File Output Operator compressed: false GlobalTableId: 0 directory: file:/tmp/njain/hive_2011-12-07_18-05-57_369_5480373477963759883/-mr-10002 NumFilesPerFileSink: 1 table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col0,_col1 columns.types string,bigint escape.delim \ TotalFiles: 1 GatherStats: false MultiFileSpray: false Stage: Stage-2 Map Reduce Alias -> Map Operator Tree: file:/tmp/njain/hive_2011-12-07_18-05-57_369_5480373477963759883/-mr-10002 Union Select Operator expressions: expr: _col0 type: string expr: _col1 type: bigint outputColumnNames: _col0, _col1 Reduce Output Operator key expressions: expr: _col0 type: string sort order: + tag: -1 value expressions: expr: _col0 type: string expr: _col1 type: bigint file:/tmp/njain/hive_2011-12-07_18-05-57_369_5480373477963759883/-mr-10003 Union Select Operator expressions: expr: _col0 type: string expr: _col1 type: bigint outputColumnNames: _col0, _col1 Reduce Output Operator key expressions: expr: _col0 type: string sort order: + tag: -1 value expressions: expr: _col0 type: string expr: _col1 type: bigint file:/tmp/njain/hive_2011-12-07_18-05-57_369_5480373477963759883/-mr-10004 Union Select Operator expressions: expr: _col0 type: string expr: _col1 type: bigint outputColumnNames: _col0, _col1 Reduce Output Operator key expressions: expr: _col0 type: string sort order: + tag: -1 value expressions: expr: _col0 type: string expr: _col1 type: bigint Needs Tagging: false Path -> Alias: file:/tmp/njain/hive_2011-12-07_18-05-57_369_5480373477963759883/-mr-10002 [file:/tmp/njain/hive_2011-12-07_18-05-57_369_5480373477963759883/-mr-10002] file:/tmp/njain/hive_2011-12-07_18-05-57_369_5480373477963759883/-mr-10003 [file:/tmp/njain/hive_2011-12-07_18-05-57_369_5480373477963759883/-mr-10003] file:/tmp/njain/hive_2011-12-07_18-05-57_369_5480373477963759883/-mr-10004 [file:/tmp/njain/hive_2011-12-07_18-05-57_369_5480373477963759883/-mr-10004] Path -> Partition: file:/tmp/njain/hive_2011-12-07_18-05-57_369_5480373477963759883/-mr-10002 Partition base file name: -mr-10002 input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col0,_col1 columns.types string,bigint escape.delim \ input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col0,_col1 columns.types string,bigint escape.delim \ file:/tmp/njain/hive_2011-12-07_18-05-57_369_5480373477963759883/-mr-10003 Partition base file name: -mr-10003 input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col0,_col1 columns.types string,bigint escape.delim \ input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col0,_col1 columns.types string,bigint escape.delim \ file:/tmp/njain/hive_2011-12-07_18-05-57_369_5480373477963759883/-mr-10004 Partition base file name: -mr-10004 input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col0,_col1 columns.types string,bigint escape.delim \ input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col0,_col1 columns.types string,bigint escape.delim \ Reduce Operator Tree: Extract File Output Operator compressed: false GlobalTableId: 0 directory: file:/tmp/njain/hive_2011-12-07_18-05-57_369_5480373477963759883/-ext-10001 NumFilesPerFileSink: 1 Stats Publishing Key Prefix: file:/tmp/njain/hive_2011-12-07_18-05-57_369_5480373477963759883/-ext-10001/ table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: columns _col0,_col1 columns.types string:bigint escape.delim \ serialization.format 1 TotalFiles: 1 GatherStats: false MultiFileSpray: false Stage: Stage-4 Map Reduce Alias -> Map Operator Tree: null-subquery1-subquery1:s-subquery1-subquery1:src2 TableScan alias: src2 GatherStats: false Filter Operator isSamplingPred: false predicate: expr: (key < 10) type: boolean Select Operator expressions: expr: key type: string expr: count type: bigint outputColumnNames: _col0, _col1 File Output Operator compressed: false GlobalTableId: 0 directory: file:/tmp/njain/hive_2011-12-07_18-05-57_369_5480373477963759883/-mr-10003 NumFilesPerFileSink: 1 table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col0,_col1 columns.types string,bigint escape.delim \ TotalFiles: 1 GatherStats: false MultiFileSpray: false Needs Tagging: false Path -> Alias: pfile:/data/users/njain/hive_commit2/build/ql/test/data/warehouse/src2 [null-subquery1-subquery1:s-subquery1-subquery1:src2] Path -> Partition: pfile:/data/users/njain/hive_commit2/build/ql/test/data/warehouse/src2 Partition base file name: src2 input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: bucket_count -1 columns key,count columns.types string:bigint file.inputformat org.apache.hadoop.mapred.TextInputFormat file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat location pfile:/data/users/njain/hive_commit2/build/ql/test/data/warehouse/src2 name default.src2 numFiles 1 numPartitions 0 numRows 309 rawDataSize 1482 serialization.ddl struct src2 { string key, i64 count} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe totalSize 1791 transient_lastDdlTime 1323309926 serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: bucket_count -1 columns key,count columns.types string:bigint file.inputformat org.apache.hadoop.mapred.TextInputFormat file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat location pfile:/data/users/njain/hive_commit2/build/ql/test/data/warehouse/src2 name default.src2 numFiles 1 numPartitions 0 numRows 309 rawDataSize 1482 serialization.ddl struct src2 { string key, i64 count} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe totalSize 1791 transient_lastDdlTime 1323309926 serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.src2 name: default.src2 Stage: Stage-5 Map Reduce Alias -> Map Operator Tree: null-subquery1-subquery2:s-subquery1-subquery2:src3 TableScan alias: src3 GatherStats: false Filter Operator isSamplingPred: false predicate: expr: (key < 10) type: boolean Select Operator expressions: expr: key type: string expr: count type: bigint outputColumnNames: _col0, _col1 File Output Operator compressed: false GlobalTableId: 0 directory: file:/tmp/njain/hive_2011-12-07_18-05-57_369_5480373477963759883/-mr-10004 NumFilesPerFileSink: 1 table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col0,_col1 columns.types string,bigint escape.delim \ TotalFiles: 1 GatherStats: false MultiFileSpray: false Needs Tagging: false Path -> Alias: pfile:/data/users/njain/hive_commit2/build/ql/test/data/warehouse/src3 [null-subquery1-subquery2:s-subquery1-subquery2:src3] Path -> Partition: pfile:/data/users/njain/hive_commit2/build/ql/test/data/warehouse/src3 Partition base file name: src3 input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: bucket_count -1 columns key,count columns.types string:bigint file.inputformat org.apache.hadoop.mapred.TextInputFormat file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat location pfile:/data/users/njain/hive_commit2/build/ql/test/data/warehouse/src3 name default.src3 numFiles 1 numPartitions 0 numRows 309 rawDataSize 1482 serialization.ddl struct src3 { string key, i64 count} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe totalSize 1791 transient_lastDdlTime 1323309930 serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: bucket_count -1 columns key,count columns.types string:bigint file.inputformat org.apache.hadoop.mapred.TextInputFormat file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat location pfile:/data/users/njain/hive_commit2/build/ql/test/data/warehouse/src3 name default.src3 numFiles 1 numPartitions 0 numRows 309 rawDataSize 1482 serialization.ddl struct src3 { string key, i64 count} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe totalSize 1791 transient_lastDdlTime 1323309930 serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.src3 name: default.src3 Stage: Stage-0 Fetch Operator limit: -1 PREHOOK: query: select s.key, s.count from ( select key, count from src2 where key < 10 union all select key, count from src3 where key < 10 union all select a.key as key, b.count as count from src4 a join src5 b on a.key=b.key where a.key < 10 )s order by s.key PREHOOK: type: QUERY PREHOOK: Input: default@src2 PREHOOK: Input: default@src3 PREHOOK: Input: default@src4 PREHOOK: Input: default@src5 PREHOOK: Output: file:/tmp/njain/hive_2011-12-07_18-05-57_532_8796691937141834686/-mr-10000 POSTHOOK: query: select s.key, s.count from ( select key, count from src2 where key < 10 union all select key, count from src3 where key < 10 union all select a.key as key, b.count as count from src4 a join src5 b on a.key=b.key where a.key < 10 )s order by s.key POSTHOOK: type: QUERY POSTHOOK: Input: default@src2 POSTHOOK: Input: default@src3 POSTHOOK: Input: default@src4 POSTHOOK: Input: default@src5 POSTHOOK: Output: file:/tmp/njain/hive_2011-12-07_18-05-57_532_8796691937141834686/-mr-10000 0 3 0 3 0 3 2 1 2 1 2 1 4 1 4 1 4 1 5 3 5 3 5 3 8 1 8 1 8 1 9 1 9 1 9 1 PREHOOK: query: explain extended select s.key, s.count from ( select key, count from src2 where key < 10 union all select key, count from src3 where key < 10 union all select a.key as key, count(1) as count from src4 a join src5 b on a.key=b.key where a.key < 10 group by a.key )s order by s.key PREHOOK: type: QUERY POSTHOOK: query: explain extended select s.key, s.count from ( select key, count from src2 where key < 10 union all select key, count from src3 where key < 10 union all select a.key as key, count(1) as count from src4 a join src5 b on a.key=b.key where a.key < 10 group by a.key )s order by s.key POSTHOOK: type: QUERY ABSTRACT SYNTAX TREE: (TOK_QUERY (TOK_FROM (TOK_SUBQUERY (TOK_UNION (TOK_UNION (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME src2))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL key)) (TOK_SELEXPR (TOK_TABLE_OR_COL count))) (TOK_WHERE (< (TOK_TABLE_OR_COL key) 10)))) (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME src3))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL key)) (TOK_SELEXPR (TOK_TABLE_OR_COL count))) (TOK_WHERE (< (TOK_TABLE_OR_COL key) 10))))) (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_TABREF (TOK_TABNAME src4) a) (TOK_TABREF (TOK_TABNAME src5) b) (= (. (TOK_TABLE_OR_COL a) key) (. (TOK_TABLE_OR_COL b) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL a) key) key) (TOK_SELEXPR (TOK_FUNCTION count 1) count)) (TOK_WHERE (< (. (TOK_TABLE_OR_COL a) key) 10)) (TOK_GROUPBY (. (TOK_TABLE_OR_COL a) key))))) s)) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL s) key)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL s) count))) (TOK_ORDERBY (TOK_TABSORTCOLNAMEASC (. (TOK_TABLE_OR_COL s) key))))) STAGE DEPENDENCIES: Stage-1 is a root stage Stage-2 depends on stages: Stage-1 Stage-3 depends on stages: Stage-2, Stage-5, Stage-6 Stage-5 is a root stage Stage-6 is a root stage Stage-0 is a root stage STAGE PLANS: Stage: Stage-1 Map Reduce Alias -> Map Operator Tree: null-subquery2:s-subquery2:a TableScan alias: a GatherStats: false Filter Operator isSamplingPred: false predicate: expr: (key < 10) 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: key type: string null-subquery2:s-subquery2:b TableScan alias: b GatherStats: false Filter Operator isSamplingPred: false predicate: expr: (key < 10) type: boolean Reduce Output Operator key expressions: expr: key type: string sort order: + Map-reduce partition columns: expr: key type: string tag: 1 Needs Tagging: true Path -> Alias: pfile:/data/users/njain/hive_commit2/build/ql/test/data/warehouse/src4 [null-subquery2:s-subquery2:a] pfile:/data/users/njain/hive_commit2/build/ql/test/data/warehouse/src5 [null-subquery2:s-subquery2:b] Path -> Partition: pfile:/data/users/njain/hive_commit2/build/ql/test/data/warehouse/src4 Partition base file name: src4 input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: bucket_count -1 columns key,count columns.types string:bigint file.inputformat org.apache.hadoop.mapred.TextInputFormat file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat location pfile:/data/users/njain/hive_commit2/build/ql/test/data/warehouse/src4 name default.src4 numFiles 1 numPartitions 0 numRows 309 rawDataSize 1482 serialization.ddl struct src4 { string key, i64 count} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe totalSize 1791 transient_lastDdlTime 1323309936 serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: bucket_count -1 columns key,count columns.types string:bigint file.inputformat org.apache.hadoop.mapred.TextInputFormat file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat location pfile:/data/users/njain/hive_commit2/build/ql/test/data/warehouse/src4 name default.src4 numFiles 1 numPartitions 0 numRows 309 rawDataSize 1482 serialization.ddl struct src4 { string key, i64 count} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe totalSize 1791 transient_lastDdlTime 1323309936 serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.src4 name: default.src4 pfile:/data/users/njain/hive_commit2/build/ql/test/data/warehouse/src5 Partition base file name: src5 input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: bucket_count -1 columns key,count columns.types string:bigint file.inputformat org.apache.hadoop.mapred.TextInputFormat file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat location pfile:/data/users/njain/hive_commit2/build/ql/test/data/warehouse/src5 name default.src5 numFiles 1 numPartitions 0 numRows 309 rawDataSize 1482 serialization.ddl struct src5 { string key, i64 count} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe totalSize 1791 transient_lastDdlTime 1323309941 serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: bucket_count -1 columns key,count columns.types string:bigint file.inputformat org.apache.hadoop.mapred.TextInputFormat file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat location pfile:/data/users/njain/hive_commit2/build/ql/test/data/warehouse/src5 name default.src5 numFiles 1 numPartitions 0 numRows 309 rawDataSize 1482 serialization.ddl struct src5 { string key, i64 count} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe totalSize 1791 transient_lastDdlTime 1323309941 serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.src5 name: default.src5 Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 condition expressions: 0 {VALUE._col0} 1 handleSkewJoin: false outputColumnNames: _col0 Select Operator expressions: expr: _col0 type: string outputColumnNames: _col0 Group By Operator aggregations: expr: count(1) bucketGroup: false keys: expr: _col0 type: string mode: hash outputColumnNames: _col0, _col1 File Output Operator compressed: false GlobalTableId: 0 directory: file:/tmp/njain/hive_2011-12-07_18-06-10_646_288553186490152714/-mr-10002 NumFilesPerFileSink: 1 table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col0,_col1 columns.types string,bigint escape.delim \ TotalFiles: 1 GatherStats: false MultiFileSpray: false Stage: Stage-2 Map Reduce Alias -> Map Operator Tree: file:/tmp/njain/hive_2011-12-07_18-06-10_646_288553186490152714/-mr-10002 Reduce Output Operator key expressions: expr: _col0 type: string sort order: + Map-reduce partition columns: expr: _col0 type: string tag: -1 value expressions: expr: _col1 type: bigint Needs Tagging: false Path -> Alias: file:/tmp/njain/hive_2011-12-07_18-06-10_646_288553186490152714/-mr-10002 [file:/tmp/njain/hive_2011-12-07_18-06-10_646_288553186490152714/-mr-10002] Path -> Partition: file:/tmp/njain/hive_2011-12-07_18-06-10_646_288553186490152714/-mr-10002 Partition base file name: -mr-10002 input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col0,_col1 columns.types string,bigint escape.delim \ input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col0,_col1 columns.types string,bigint escape.delim \ Reduce Operator Tree: Group By Operator aggregations: expr: count(VALUE._col0) bucketGroup: false keys: expr: KEY._col0 type: string mode: mergepartial outputColumnNames: _col0, _col1 Select Operator expressions: expr: _col0 type: string expr: _col1 type: bigint outputColumnNames: _col0, _col1 File Output Operator compressed: false GlobalTableId: 0 directory: file:/tmp/njain/hive_2011-12-07_18-06-10_646_288553186490152714/-mr-10003 NumFilesPerFileSink: 1 table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col0,_col1 columns.types string,bigint escape.delim \ TotalFiles: 1 GatherStats: false MultiFileSpray: false Stage: Stage-3 Map Reduce Alias -> Map Operator Tree: file:/tmp/njain/hive_2011-12-07_18-06-10_646_288553186490152714/-mr-10003 Union Select Operator expressions: expr: _col0 type: string expr: _col1 type: bigint outputColumnNames: _col0, _col1 Reduce Output Operator key expressions: expr: _col0 type: string sort order: + tag: -1 value expressions: expr: _col0 type: string expr: _col1 type: bigint file:/tmp/njain/hive_2011-12-07_18-06-10_646_288553186490152714/-mr-10004 Union Select Operator expressions: expr: _col0 type: string expr: _col1 type: bigint outputColumnNames: _col0, _col1 Reduce Output Operator key expressions: expr: _col0 type: string sort order: + tag: -1 value expressions: expr: _col0 type: string expr: _col1 type: bigint file:/tmp/njain/hive_2011-12-07_18-06-10_646_288553186490152714/-mr-10005 Union Select Operator expressions: expr: _col0 type: string expr: _col1 type: bigint outputColumnNames: _col0, _col1 Reduce Output Operator key expressions: expr: _col0 type: string sort order: + tag: -1 value expressions: expr: _col0 type: string expr: _col1 type: bigint Needs Tagging: false Path -> Alias: file:/tmp/njain/hive_2011-12-07_18-06-10_646_288553186490152714/-mr-10003 [file:/tmp/njain/hive_2011-12-07_18-06-10_646_288553186490152714/-mr-10003] file:/tmp/njain/hive_2011-12-07_18-06-10_646_288553186490152714/-mr-10004 [file:/tmp/njain/hive_2011-12-07_18-06-10_646_288553186490152714/-mr-10004] file:/tmp/njain/hive_2011-12-07_18-06-10_646_288553186490152714/-mr-10005 [file:/tmp/njain/hive_2011-12-07_18-06-10_646_288553186490152714/-mr-10005] Path -> Partition: file:/tmp/njain/hive_2011-12-07_18-06-10_646_288553186490152714/-mr-10003 Partition base file name: -mr-10003 input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col0,_col1 columns.types string,bigint escape.delim \ input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col0,_col1 columns.types string,bigint escape.delim \ file:/tmp/njain/hive_2011-12-07_18-06-10_646_288553186490152714/-mr-10004 Partition base file name: -mr-10004 input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col0,_col1 columns.types string,bigint escape.delim \ input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col0,_col1 columns.types string,bigint escape.delim \ file:/tmp/njain/hive_2011-12-07_18-06-10_646_288553186490152714/-mr-10005 Partition base file name: -mr-10005 input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col0,_col1 columns.types string,bigint escape.delim \ input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col0,_col1 columns.types string,bigint escape.delim \ Reduce Operator Tree: Extract File Output Operator compressed: false GlobalTableId: 0 directory: file:/tmp/njain/hive_2011-12-07_18-06-10_646_288553186490152714/-ext-10001 NumFilesPerFileSink: 1 Stats Publishing Key Prefix: file:/tmp/njain/hive_2011-12-07_18-06-10_646_288553186490152714/-ext-10001/ table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: columns _col0,_col1 columns.types string:bigint escape.delim \ serialization.format 1 TotalFiles: 1 GatherStats: false MultiFileSpray: false Stage: Stage-5 Map Reduce Alias -> Map Operator Tree: null-subquery1-subquery1:s-subquery1-subquery1:src2 TableScan alias: src2 GatherStats: false Filter Operator isSamplingPred: false predicate: expr: (key < 10) type: boolean Select Operator expressions: expr: key type: string expr: count type: bigint outputColumnNames: _col0, _col1 File Output Operator compressed: false GlobalTableId: 0 directory: file:/tmp/njain/hive_2011-12-07_18-06-10_646_288553186490152714/-mr-10004 NumFilesPerFileSink: 1 table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col0,_col1 columns.types string,bigint escape.delim \ TotalFiles: 1 GatherStats: false MultiFileSpray: false Needs Tagging: false Path -> Alias: pfile:/data/users/njain/hive_commit2/build/ql/test/data/warehouse/src2 [null-subquery1-subquery1:s-subquery1-subquery1:src2] Path -> Partition: pfile:/data/users/njain/hive_commit2/build/ql/test/data/warehouse/src2 Partition base file name: src2 input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: bucket_count -1 columns key,count columns.types string:bigint file.inputformat org.apache.hadoop.mapred.TextInputFormat file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat location pfile:/data/users/njain/hive_commit2/build/ql/test/data/warehouse/src2 name default.src2 numFiles 1 numPartitions 0 numRows 309 rawDataSize 1482 serialization.ddl struct src2 { string key, i64 count} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe totalSize 1791 transient_lastDdlTime 1323309926 serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: bucket_count -1 columns key,count columns.types string:bigint file.inputformat org.apache.hadoop.mapred.TextInputFormat file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat location pfile:/data/users/njain/hive_commit2/build/ql/test/data/warehouse/src2 name default.src2 numFiles 1 numPartitions 0 numRows 309 rawDataSize 1482 serialization.ddl struct src2 { string key, i64 count} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe totalSize 1791 transient_lastDdlTime 1323309926 serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.src2 name: default.src2 Stage: Stage-6 Map Reduce Alias -> Map Operator Tree: null-subquery1-subquery2:s-subquery1-subquery2:src3 TableScan alias: src3 GatherStats: false Filter Operator isSamplingPred: false predicate: expr: (key < 10) type: boolean Select Operator expressions: expr: key type: string expr: count type: bigint outputColumnNames: _col0, _col1 File Output Operator compressed: false GlobalTableId: 0 directory: file:/tmp/njain/hive_2011-12-07_18-06-10_646_288553186490152714/-mr-10005 NumFilesPerFileSink: 1 table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col0,_col1 columns.types string,bigint escape.delim \ TotalFiles: 1 GatherStats: false MultiFileSpray: false Needs Tagging: false Path -> Alias: pfile:/data/users/njain/hive_commit2/build/ql/test/data/warehouse/src3 [null-subquery1-subquery2:s-subquery1-subquery2:src3] Path -> Partition: pfile:/data/users/njain/hive_commit2/build/ql/test/data/warehouse/src3 Partition base file name: src3 input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: bucket_count -1 columns key,count columns.types string:bigint file.inputformat org.apache.hadoop.mapred.TextInputFormat file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat location pfile:/data/users/njain/hive_commit2/build/ql/test/data/warehouse/src3 name default.src3 numFiles 1 numPartitions 0 numRows 309 rawDataSize 1482 serialization.ddl struct src3 { string key, i64 count} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe totalSize 1791 transient_lastDdlTime 1323309930 serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: bucket_count -1 columns key,count columns.types string:bigint file.inputformat org.apache.hadoop.mapred.TextInputFormat file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat location pfile:/data/users/njain/hive_commit2/build/ql/test/data/warehouse/src3 name default.src3 numFiles 1 numPartitions 0 numRows 309 rawDataSize 1482 serialization.ddl struct src3 { string key, i64 count} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe totalSize 1791 transient_lastDdlTime 1323309930 serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.src3 name: default.src3 Stage: Stage-0 Fetch Operator limit: -1 PREHOOK: query: select s.key, s.count from ( select key, count from src2 where key < 10 union all select key, count from src3 where key < 10 union all select a.key as key, count(1) as count from src4 a join src5 b on a.key=b.key where a.key < 10 group by a.key )s order by s.key PREHOOK: type: QUERY PREHOOK: Input: default@src2 PREHOOK: Input: default@src3 PREHOOK: Input: default@src4 PREHOOK: Input: default@src5 PREHOOK: Output: file:/tmp/njain/hive_2011-12-07_18-06-10_797_9067066248849265470/-mr-10000 POSTHOOK: query: select s.key, s.count from ( select key, count from src2 where key < 10 union all select key, count from src3 where key < 10 union all select a.key as key, count(1) as count from src4 a join src5 b on a.key=b.key where a.key < 10 group by a.key )s order by s.key POSTHOOK: type: QUERY POSTHOOK: Input: default@src2 POSTHOOK: Input: default@src3 POSTHOOK: Input: default@src4 POSTHOOK: Input: default@src5 POSTHOOK: Output: file:/tmp/njain/hive_2011-12-07_18-06-10_797_9067066248849265470/-mr-10000 0 1 0 3 0 3 2 1 2 1 2 1 4 1 4 1 4 1 5 3 5 1 5 3 8 1 8 1 8 1 9 1 9 1 9 1