Added: hive/trunk/ql/src/test/results/clientpositive/auto_sortmerge_join_7.q.out URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/test/results/clientpositive/auto_sortmerge_join_7.q.out?rev=1447593&view=auto ============================================================================== --- hive/trunk/ql/src/test/results/clientpositive/auto_sortmerge_join_7.q.out (added) +++ hive/trunk/ql/src/test/results/clientpositive/auto_sortmerge_join_7.q.out Tue Feb 19 05:17:52 2013 @@ -0,0 +1,490 @@ +PREHOOK: query: -- small 2 part, 4 bucket & big 2 part, 2 bucket +CREATE TABLE bucket_small (key string, value string) partitioned by (ds string) CLUSTERED BY (key) SORTED BY (key) INTO 4 BUCKETS STORED AS TEXTFILE +PREHOOK: type: CREATETABLE +POSTHOOK: query: -- small 2 part, 4 bucket & big 2 part, 2 bucket +CREATE TABLE bucket_small (key string, value string) partitioned by (ds string) CLUSTERED BY (key) SORTED BY (key) INTO 4 BUCKETS STORED AS TEXTFILE +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: default@bucket_small +PREHOOK: query: load data local inpath '../data/files/smallsrcsortbucket1outof4.txt' INTO TABLE bucket_small partition(ds='2008-04-08') +PREHOOK: type: LOAD +PREHOOK: Output: default@bucket_small +POSTHOOK: query: load data local inpath '../data/files/smallsrcsortbucket1outof4.txt' INTO TABLE bucket_small partition(ds='2008-04-08') +POSTHOOK: type: LOAD +POSTHOOK: Output: default@bucket_small +POSTHOOK: Output: default@bucket_small@ds=2008-04-08 +PREHOOK: query: load data local inpath '../data/files/smallsrcsortbucket2outof4.txt' INTO TABLE bucket_small partition(ds='2008-04-08') +PREHOOK: type: LOAD +PREHOOK: Output: default@bucket_small@ds=2008-04-08 +POSTHOOK: query: load data local inpath '../data/files/smallsrcsortbucket2outof4.txt' INTO TABLE bucket_small partition(ds='2008-04-08') +POSTHOOK: type: LOAD +POSTHOOK: Output: default@bucket_small@ds=2008-04-08 +PREHOOK: query: load data local inpath '../data/files/smallsrcsortbucket3outof4.txt' INTO TABLE bucket_small partition(ds='2008-04-08') +PREHOOK: type: LOAD +PREHOOK: Output: default@bucket_small@ds=2008-04-08 +POSTHOOK: query: load data local inpath '../data/files/smallsrcsortbucket3outof4.txt' INTO TABLE bucket_small partition(ds='2008-04-08') +POSTHOOK: type: LOAD +POSTHOOK: Output: default@bucket_small@ds=2008-04-08 +PREHOOK: query: load data local inpath '../data/files/smallsrcsortbucket4outof4.txt' INTO TABLE bucket_small partition(ds='2008-04-08') +PREHOOK: type: LOAD +PREHOOK: Output: default@bucket_small@ds=2008-04-08 +POSTHOOK: query: load data local inpath '../data/files/smallsrcsortbucket4outof4.txt' INTO TABLE bucket_small partition(ds='2008-04-08') +POSTHOOK: type: LOAD +POSTHOOK: Output: default@bucket_small@ds=2008-04-08 +PREHOOK: query: load data local inpath '../data/files/smallsrcsortbucket1outof4.txt' INTO TABLE bucket_small partition(ds='2008-04-09') +PREHOOK: type: LOAD +PREHOOK: Output: default@bucket_small +POSTHOOK: query: load data local inpath '../data/files/smallsrcsortbucket1outof4.txt' INTO TABLE bucket_small partition(ds='2008-04-09') +POSTHOOK: type: LOAD +POSTHOOK: Output: default@bucket_small +POSTHOOK: Output: default@bucket_small@ds=2008-04-09 +PREHOOK: query: load data local inpath '../data/files/smallsrcsortbucket2outof4.txt' INTO TABLE bucket_small partition(ds='2008-04-09') +PREHOOK: type: LOAD +PREHOOK: Output: default@bucket_small@ds=2008-04-09 +POSTHOOK: query: load data local inpath '../data/files/smallsrcsortbucket2outof4.txt' INTO TABLE bucket_small partition(ds='2008-04-09') +POSTHOOK: type: LOAD +POSTHOOK: Output: default@bucket_small@ds=2008-04-09 +PREHOOK: query: load data local inpath '../data/files/smallsrcsortbucket3outof4.txt' INTO TABLE bucket_small partition(ds='2008-04-09') +PREHOOK: type: LOAD +PREHOOK: Output: default@bucket_small@ds=2008-04-09 +POSTHOOK: query: load data local inpath '../data/files/smallsrcsortbucket3outof4.txt' INTO TABLE bucket_small partition(ds='2008-04-09') +POSTHOOK: type: LOAD +POSTHOOK: Output: default@bucket_small@ds=2008-04-09 +PREHOOK: query: load data local inpath '../data/files/smallsrcsortbucket4outof4.txt' INTO TABLE bucket_small partition(ds='2008-04-09') +PREHOOK: type: LOAD +PREHOOK: Output: default@bucket_small@ds=2008-04-09 +POSTHOOK: query: load data local inpath '../data/files/smallsrcsortbucket4outof4.txt' INTO TABLE bucket_small partition(ds='2008-04-09') +POSTHOOK: type: LOAD +POSTHOOK: Output: default@bucket_small@ds=2008-04-09 +PREHOOK: query: CREATE TABLE bucket_big (key string, value string) partitioned by (ds string) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS STORED AS TEXTFILE +PREHOOK: type: CREATETABLE +POSTHOOK: query: CREATE TABLE bucket_big (key string, value string) partitioned by (ds string) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS STORED AS TEXTFILE +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: default@bucket_big +PREHOOK: query: load data local inpath '../data/files/srcsortbucket1outof4.txt' INTO TABLE bucket_big partition(ds='2008-04-08') +PREHOOK: type: LOAD +PREHOOK: Output: default@bucket_big +POSTHOOK: query: load data local inpath '../data/files/srcsortbucket1outof4.txt' INTO TABLE bucket_big partition(ds='2008-04-08') +POSTHOOK: type: LOAD +POSTHOOK: Output: default@bucket_big +POSTHOOK: Output: default@bucket_big@ds=2008-04-08 +PREHOOK: query: load data local inpath '../data/files/srcsortbucket2outof4.txt' INTO TABLE bucket_big partition(ds='2008-04-08') +PREHOOK: type: LOAD +PREHOOK: Output: default@bucket_big@ds=2008-04-08 +POSTHOOK: query: load data local inpath '../data/files/srcsortbucket2outof4.txt' INTO TABLE bucket_big partition(ds='2008-04-08') +POSTHOOK: type: LOAD +POSTHOOK: Output: default@bucket_big@ds=2008-04-08 +PREHOOK: query: load data local inpath '../data/files/srcsortbucket1outof4.txt' INTO TABLE bucket_big partition(ds='2008-04-09') +PREHOOK: type: LOAD +PREHOOK: Output: default@bucket_big +POSTHOOK: query: load data local inpath '../data/files/srcsortbucket1outof4.txt' INTO TABLE bucket_big partition(ds='2008-04-09') +POSTHOOK: type: LOAD +POSTHOOK: Output: default@bucket_big +POSTHOOK: Output: default@bucket_big@ds=2008-04-09 +PREHOOK: query: load data local inpath '../data/files/srcsortbucket2outof4.txt' INTO TABLE bucket_big partition(ds='2008-04-09') +PREHOOK: type: LOAD +PREHOOK: Output: default@bucket_big@ds=2008-04-09 +POSTHOOK: query: load data local inpath '../data/files/srcsortbucket2outof4.txt' INTO TABLE bucket_big partition(ds='2008-04-09') +POSTHOOK: type: LOAD +POSTHOOK: Output: default@bucket_big@ds=2008-04-09 +PREHOOK: query: -- Since size is being used to find the big table, the order of the tables in the join does not matter +explain extended select count(*) FROM bucket_small a JOIN bucket_big b ON a.key = b.key +PREHOOK: type: QUERY +POSTHOOK: query: -- Since size is being used to find the big table, the order of the tables in the join does not matter +explain extended select count(*) FROM bucket_small a JOIN bucket_big b ON a.key = b.key +POSTHOOK: type: QUERY +ABSTRACT SYNTAX TREE: + (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_TABREF (TOK_TABNAME bucket_small) a) (TOK_TABREF (TOK_TABNAME bucket_big) 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_FUNCTIONSTAR count))))) + +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 is a root stage + +STAGE PLANS: + Stage: Stage-1 + Map Reduce + Alias -> Map Operator Tree: + b + TableScan + alias: b + GatherStats: false + Sorted Merge Bucket Map Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 + 1 + handleSkewJoin: false + keys: + 0 [Column[key]] + 1 [Column[key]] + Position of Big Table: 1 + Select Operator + Group By Operator + aggregations: + expr: count() + bucketGroup: false + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + tag: -1 + value expressions: + expr: _col0 + type: bigint + Needs Tagging: false + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: ds=2008-04-08 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2008-04-08 + properties: + bucket_count 2 + bucket_field_name key + columns key,value + columns.types string:string +#### A masked pattern was here #### + name default.bucket_big + numFiles 2 + numRows 0 + partition_columns ds + rawDataSize 0 + serialization.ddl struct bucket_big { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 2750 +#### A masked pattern was here #### + 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: + SORTBUCKETCOLSPREFIX TRUE + bucket_count 2 + bucket_field_name key + columns key,value + columns.types string:string +#### A masked pattern was here #### + name default.bucket_big + numFiles 4 + numPartitions 2 + numRows 0 + partition_columns ds + rawDataSize 0 + serialization.ddl struct bucket_big { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5500 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.bucket_big + name: default.bucket_big +#### A masked pattern was here #### + Partition + base file name: ds=2008-04-09 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2008-04-09 + properties: + bucket_count 2 + bucket_field_name key + columns key,value + columns.types string:string +#### A masked pattern was here #### + name default.bucket_big + numFiles 2 + numRows 0 + partition_columns ds + rawDataSize 0 + serialization.ddl struct bucket_big { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 2750 +#### A masked pattern was here #### + 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: + SORTBUCKETCOLSPREFIX TRUE + bucket_count 2 + bucket_field_name key + columns key,value + columns.types string:string +#### A masked pattern was here #### + name default.bucket_big + numFiles 4 + numPartitions 2 + numRows 0 + partition_columns ds + rawDataSize 0 + serialization.ddl struct bucket_big { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5500 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.bucket_big + name: default.bucket_big + 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 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0 + columns.types bigint + escape.delim \ + serialization.format 1 + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + Truncated Path -> Alias: + /bucket_big/ds=2008-04-08 [b] + /bucket_big/ds=2008-04-09 [b] + + Stage: Stage-0 + Fetch Operator + limit: -1 + + +PREHOOK: query: select count(*) FROM bucket_small a JOIN bucket_big b ON a.key = b.key +PREHOOK: type: QUERY +PREHOOK: Input: default@bucket_big +PREHOOK: Input: default@bucket_big@ds=2008-04-08 +PREHOOK: Input: default@bucket_big@ds=2008-04-09 +PREHOOK: Input: default@bucket_small +PREHOOK: Input: default@bucket_small@ds=2008-04-08 +PREHOOK: Input: default@bucket_small@ds=2008-04-09 +#### A masked pattern was here #### +POSTHOOK: query: select count(*) FROM bucket_small a JOIN bucket_big b ON a.key = b.key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@bucket_big +POSTHOOK: Input: default@bucket_big@ds=2008-04-08 +POSTHOOK: Input: default@bucket_big@ds=2008-04-09 +POSTHOOK: Input: default@bucket_small +POSTHOOK: Input: default@bucket_small@ds=2008-04-08 +POSTHOOK: Input: default@bucket_small@ds=2008-04-09 +#### A masked pattern was here #### +76 +PREHOOK: query: explain extended select count(*) FROM bucket_big a JOIN bucket_small b ON a.key = b.key +PREHOOK: type: QUERY +POSTHOOK: query: explain extended select count(*) FROM bucket_big a JOIN bucket_small b ON a.key = b.key +POSTHOOK: type: QUERY +ABSTRACT SYNTAX TREE: + (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_TABREF (TOK_TABNAME bucket_big) a) (TOK_TABREF (TOK_TABNAME bucket_small) 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_FUNCTIONSTAR count))))) + +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 is a root stage + +STAGE PLANS: + Stage: Stage-1 + Map Reduce + Alias -> Map Operator Tree: + a + TableScan + alias: a + GatherStats: false + Sorted Merge Bucket Map Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 + 1 + handleSkewJoin: false + keys: + 0 [Column[key]] + 1 [Column[key]] + Position of Big Table: 0 + Select Operator + Group By Operator + aggregations: + expr: count() + bucketGroup: false + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + tag: -1 + value expressions: + expr: _col0 + type: bigint + Needs Tagging: false + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: ds=2008-04-08 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2008-04-08 + properties: + bucket_count 2 + bucket_field_name key + columns key,value + columns.types string:string +#### A masked pattern was here #### + name default.bucket_big + numFiles 2 + numRows 0 + partition_columns ds + rawDataSize 0 + serialization.ddl struct bucket_big { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 2750 +#### A masked pattern was here #### + 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: + SORTBUCKETCOLSPREFIX TRUE + bucket_count 2 + bucket_field_name key + columns key,value + columns.types string:string +#### A masked pattern was here #### + name default.bucket_big + numFiles 4 + numPartitions 2 + numRows 0 + partition_columns ds + rawDataSize 0 + serialization.ddl struct bucket_big { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5500 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.bucket_big + name: default.bucket_big +#### A masked pattern was here #### + Partition + base file name: ds=2008-04-09 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2008-04-09 + properties: + bucket_count 2 + bucket_field_name key + columns key,value + columns.types string:string +#### A masked pattern was here #### + name default.bucket_big + numFiles 2 + numRows 0 + partition_columns ds + rawDataSize 0 + serialization.ddl struct bucket_big { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 2750 +#### A masked pattern was here #### + 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: + SORTBUCKETCOLSPREFIX TRUE + bucket_count 2 + bucket_field_name key + columns key,value + columns.types string:string +#### A masked pattern was here #### + name default.bucket_big + numFiles 4 + numPartitions 2 + numRows 0 + partition_columns ds + rawDataSize 0 + serialization.ddl struct bucket_big { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5500 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.bucket_big + name: default.bucket_big + 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 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0 + columns.types bigint + escape.delim \ + serialization.format 1 + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + Truncated Path -> Alias: + /bucket_big/ds=2008-04-08 [a] + /bucket_big/ds=2008-04-09 [a] + + Stage: Stage-0 + Fetch Operator + limit: -1 + + +PREHOOK: query: select count(*) FROM bucket_big a JOIN bucket_small b ON a.key = b.key +PREHOOK: type: QUERY +PREHOOK: Input: default@bucket_big +PREHOOK: Input: default@bucket_big@ds=2008-04-08 +PREHOOK: Input: default@bucket_big@ds=2008-04-09 +PREHOOK: Input: default@bucket_small +PREHOOK: Input: default@bucket_small@ds=2008-04-08 +PREHOOK: Input: default@bucket_small@ds=2008-04-09 +#### A masked pattern was here #### +POSTHOOK: query: select count(*) FROM bucket_big a JOIN bucket_small b ON a.key = b.key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@bucket_big +POSTHOOK: Input: default@bucket_big@ds=2008-04-08 +POSTHOOK: Input: default@bucket_big@ds=2008-04-09 +POSTHOOK: Input: default@bucket_small +POSTHOOK: Input: default@bucket_small@ds=2008-04-08 +POSTHOOK: Input: default@bucket_small@ds=2008-04-09 +#### A masked pattern was here #### +76
Added: hive/trunk/ql/src/test/results/clientpositive/auto_sortmerge_join_8.q.out URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/test/results/clientpositive/auto_sortmerge_join_8.q.out?rev=1447593&view=auto ============================================================================== --- hive/trunk/ql/src/test/results/clientpositive/auto_sortmerge_join_8.q.out (added) +++ hive/trunk/ql/src/test/results/clientpositive/auto_sortmerge_join_8.q.out Tue Feb 19 05:17:52 2013 @@ -0,0 +1,490 @@ +PREHOOK: query: -- small 2 part, 2 bucket & big 2 part, 4 bucket +CREATE TABLE bucket_small (key string, value string) partitioned by (ds string) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS STORED AS TEXTFILE +PREHOOK: type: CREATETABLE +POSTHOOK: query: -- small 2 part, 2 bucket & big 2 part, 4 bucket +CREATE TABLE bucket_small (key string, value string) partitioned by (ds string) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS STORED AS TEXTFILE +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: default@bucket_small +PREHOOK: query: load data local inpath '../data/files/smallsrcsortbucket1outof4.txt' INTO TABLE bucket_small partition(ds='2008-04-08') +PREHOOK: type: LOAD +PREHOOK: Output: default@bucket_small +POSTHOOK: query: load data local inpath '../data/files/smallsrcsortbucket1outof4.txt' INTO TABLE bucket_small partition(ds='2008-04-08') +POSTHOOK: type: LOAD +POSTHOOK: Output: default@bucket_small +POSTHOOK: Output: default@bucket_small@ds=2008-04-08 +PREHOOK: query: load data local inpath '../data/files/smallsrcsortbucket2outof4.txt' INTO TABLE bucket_small partition(ds='2008-04-08') +PREHOOK: type: LOAD +PREHOOK: Output: default@bucket_small@ds=2008-04-08 +POSTHOOK: query: load data local inpath '../data/files/smallsrcsortbucket2outof4.txt' INTO TABLE bucket_small partition(ds='2008-04-08') +POSTHOOK: type: LOAD +POSTHOOK: Output: default@bucket_small@ds=2008-04-08 +PREHOOK: query: load data local inpath '../data/files/smallsrcsortbucket1outof4.txt' INTO TABLE bucket_small partition(ds='2008-04-09') +PREHOOK: type: LOAD +PREHOOK: Output: default@bucket_small +POSTHOOK: query: load data local inpath '../data/files/smallsrcsortbucket1outof4.txt' INTO TABLE bucket_small partition(ds='2008-04-09') +POSTHOOK: type: LOAD +POSTHOOK: Output: default@bucket_small +POSTHOOK: Output: default@bucket_small@ds=2008-04-09 +PREHOOK: query: load data local inpath '../data/files/smallsrcsortbucket2outof4.txt' INTO TABLE bucket_small partition(ds='2008-04-09') +PREHOOK: type: LOAD +PREHOOK: Output: default@bucket_small@ds=2008-04-09 +POSTHOOK: query: load data local inpath '../data/files/smallsrcsortbucket2outof4.txt' INTO TABLE bucket_small partition(ds='2008-04-09') +POSTHOOK: type: LOAD +POSTHOOK: Output: default@bucket_small@ds=2008-04-09 +PREHOOK: query: CREATE TABLE bucket_big (key string, value string) partitioned by (ds string) CLUSTERED BY (key) SORTED BY (key) INTO 4 BUCKETS STORED AS TEXTFILE +PREHOOK: type: CREATETABLE +POSTHOOK: query: CREATE TABLE bucket_big (key string, value string) partitioned by (ds string) CLUSTERED BY (key) SORTED BY (key) INTO 4 BUCKETS STORED AS TEXTFILE +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: default@bucket_big +PREHOOK: query: load data local inpath '../data/files/srcsortbucket1outof4.txt' INTO TABLE bucket_big partition(ds='2008-04-08') +PREHOOK: type: LOAD +PREHOOK: Output: default@bucket_big +POSTHOOK: query: load data local inpath '../data/files/srcsortbucket1outof4.txt' INTO TABLE bucket_big partition(ds='2008-04-08') +POSTHOOK: type: LOAD +POSTHOOK: Output: default@bucket_big +POSTHOOK: Output: default@bucket_big@ds=2008-04-08 +PREHOOK: query: load data local inpath '../data/files/srcsortbucket2outof4.txt' INTO TABLE bucket_big partition(ds='2008-04-08') +PREHOOK: type: LOAD +PREHOOK: Output: default@bucket_big@ds=2008-04-08 +POSTHOOK: query: load data local inpath '../data/files/srcsortbucket2outof4.txt' INTO TABLE bucket_big partition(ds='2008-04-08') +POSTHOOK: type: LOAD +POSTHOOK: Output: default@bucket_big@ds=2008-04-08 +PREHOOK: query: load data local inpath '../data/files/srcsortbucket3outof4.txt' INTO TABLE bucket_big partition(ds='2008-04-08') +PREHOOK: type: LOAD +PREHOOK: Output: default@bucket_big@ds=2008-04-08 +POSTHOOK: query: load data local inpath '../data/files/srcsortbucket3outof4.txt' INTO TABLE bucket_big partition(ds='2008-04-08') +POSTHOOK: type: LOAD +POSTHOOK: Output: default@bucket_big@ds=2008-04-08 +PREHOOK: query: load data local inpath '../data/files/srcsortbucket4outof4.txt' INTO TABLE bucket_big partition(ds='2008-04-08') +PREHOOK: type: LOAD +PREHOOK: Output: default@bucket_big@ds=2008-04-08 +POSTHOOK: query: load data local inpath '../data/files/srcsortbucket4outof4.txt' INTO TABLE bucket_big partition(ds='2008-04-08') +POSTHOOK: type: LOAD +POSTHOOK: Output: default@bucket_big@ds=2008-04-08 +PREHOOK: query: load data local inpath '../data/files/srcsortbucket1outof4.txt' INTO TABLE bucket_big partition(ds='2008-04-09') +PREHOOK: type: LOAD +PREHOOK: Output: default@bucket_big +POSTHOOK: query: load data local inpath '../data/files/srcsortbucket1outof4.txt' INTO TABLE bucket_big partition(ds='2008-04-09') +POSTHOOK: type: LOAD +POSTHOOK: Output: default@bucket_big +POSTHOOK: Output: default@bucket_big@ds=2008-04-09 +PREHOOK: query: load data local inpath '../data/files/srcsortbucket2outof4.txt' INTO TABLE bucket_big partition(ds='2008-04-09') +PREHOOK: type: LOAD +PREHOOK: Output: default@bucket_big@ds=2008-04-09 +POSTHOOK: query: load data local inpath '../data/files/srcsortbucket2outof4.txt' INTO TABLE bucket_big partition(ds='2008-04-09') +POSTHOOK: type: LOAD +POSTHOOK: Output: default@bucket_big@ds=2008-04-09 +PREHOOK: query: load data local inpath '../data/files/srcsortbucket3outof4.txt' INTO TABLE bucket_big partition(ds='2008-04-09') +PREHOOK: type: LOAD +PREHOOK: Output: default@bucket_big@ds=2008-04-09 +POSTHOOK: query: load data local inpath '../data/files/srcsortbucket3outof4.txt' INTO TABLE bucket_big partition(ds='2008-04-09') +POSTHOOK: type: LOAD +POSTHOOK: Output: default@bucket_big@ds=2008-04-09 +PREHOOK: query: load data local inpath '../data/files/srcsortbucket4outof4.txt' INTO TABLE bucket_big partition(ds='2008-04-09') +PREHOOK: type: LOAD +PREHOOK: Output: default@bucket_big@ds=2008-04-09 +POSTHOOK: query: load data local inpath '../data/files/srcsortbucket4outof4.txt' INTO TABLE bucket_big partition(ds='2008-04-09') +POSTHOOK: type: LOAD +POSTHOOK: Output: default@bucket_big@ds=2008-04-09 +PREHOOK: query: -- Since size is being used to find the big table, the order of the tables in the join does not matter +explain extended select count(*) FROM bucket_small a JOIN bucket_big b ON a.key = b.key +PREHOOK: type: QUERY +POSTHOOK: query: -- Since size is being used to find the big table, the order of the tables in the join does not matter +explain extended select count(*) FROM bucket_small a JOIN bucket_big b ON a.key = b.key +POSTHOOK: type: QUERY +ABSTRACT SYNTAX TREE: + (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_TABREF (TOK_TABNAME bucket_small) a) (TOK_TABREF (TOK_TABNAME bucket_big) 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_FUNCTIONSTAR count))))) + +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 is a root stage + +STAGE PLANS: + Stage: Stage-1 + Map Reduce + Alias -> Map Operator Tree: + b + TableScan + alias: b + GatherStats: false + Sorted Merge Bucket Map Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 + 1 + handleSkewJoin: false + keys: + 0 [Column[key]] + 1 [Column[key]] + Position of Big Table: 1 + Select Operator + Group By Operator + aggregations: + expr: count() + bucketGroup: false + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + tag: -1 + value expressions: + expr: _col0 + type: bigint + Needs Tagging: false + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: ds=2008-04-08 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2008-04-08 + properties: + bucket_count 4 + bucket_field_name key + columns key,value + columns.types string:string +#### A masked pattern was here #### + name default.bucket_big + numFiles 4 + numRows 0 + partition_columns ds + rawDataSize 0 + serialization.ddl struct bucket_big { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + 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: + SORTBUCKETCOLSPREFIX TRUE + bucket_count 4 + bucket_field_name key + columns key,value + columns.types string:string +#### A masked pattern was here #### + name default.bucket_big + numFiles 8 + numPartitions 2 + numRows 0 + partition_columns ds + rawDataSize 0 + serialization.ddl struct bucket_big { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 11624 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.bucket_big + name: default.bucket_big +#### A masked pattern was here #### + Partition + base file name: ds=2008-04-09 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2008-04-09 + properties: + bucket_count 4 + bucket_field_name key + columns key,value + columns.types string:string +#### A masked pattern was here #### + name default.bucket_big + numFiles 4 + numRows 0 + partition_columns ds + rawDataSize 0 + serialization.ddl struct bucket_big { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + 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: + SORTBUCKETCOLSPREFIX TRUE + bucket_count 4 + bucket_field_name key + columns key,value + columns.types string:string +#### A masked pattern was here #### + name default.bucket_big + numFiles 8 + numPartitions 2 + numRows 0 + partition_columns ds + rawDataSize 0 + serialization.ddl struct bucket_big { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 11624 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.bucket_big + name: default.bucket_big + 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 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0 + columns.types bigint + escape.delim \ + serialization.format 1 + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + Truncated Path -> Alias: + /bucket_big/ds=2008-04-08 [b] + /bucket_big/ds=2008-04-09 [b] + + Stage: Stage-0 + Fetch Operator + limit: -1 + + +PREHOOK: query: select count(*) FROM bucket_small a JOIN bucket_big b ON a.key = b.key +PREHOOK: type: QUERY +PREHOOK: Input: default@bucket_big +PREHOOK: Input: default@bucket_big@ds=2008-04-08 +PREHOOK: Input: default@bucket_big@ds=2008-04-09 +PREHOOK: Input: default@bucket_small +PREHOOK: Input: default@bucket_small@ds=2008-04-08 +PREHOOK: Input: default@bucket_small@ds=2008-04-09 +#### A masked pattern was here #### +POSTHOOK: query: select count(*) FROM bucket_small a JOIN bucket_big b ON a.key = b.key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@bucket_big +POSTHOOK: Input: default@bucket_big@ds=2008-04-08 +POSTHOOK: Input: default@bucket_big@ds=2008-04-09 +POSTHOOK: Input: default@bucket_small +POSTHOOK: Input: default@bucket_small@ds=2008-04-08 +POSTHOOK: Input: default@bucket_small@ds=2008-04-09 +#### A masked pattern was here #### +76 +PREHOOK: query: explain extended select count(*) FROM bucket_big a JOIN bucket_small b ON a.key = b.key +PREHOOK: type: QUERY +POSTHOOK: query: explain extended select count(*) FROM bucket_big a JOIN bucket_small b ON a.key = b.key +POSTHOOK: type: QUERY +ABSTRACT SYNTAX TREE: + (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_TABREF (TOK_TABNAME bucket_big) a) (TOK_TABREF (TOK_TABNAME bucket_small) 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_FUNCTIONSTAR count))))) + +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 is a root stage + +STAGE PLANS: + Stage: Stage-1 + Map Reduce + Alias -> Map Operator Tree: + a + TableScan + alias: a + GatherStats: false + Sorted Merge Bucket Map Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 + 1 + handleSkewJoin: false + keys: + 0 [Column[key]] + 1 [Column[key]] + Position of Big Table: 0 + Select Operator + Group By Operator + aggregations: + expr: count() + bucketGroup: false + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + tag: -1 + value expressions: + expr: _col0 + type: bigint + Needs Tagging: false + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: ds=2008-04-08 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2008-04-08 + properties: + bucket_count 4 + bucket_field_name key + columns key,value + columns.types string:string +#### A masked pattern was here #### + name default.bucket_big + numFiles 4 + numRows 0 + partition_columns ds + rawDataSize 0 + serialization.ddl struct bucket_big { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + 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: + SORTBUCKETCOLSPREFIX TRUE + bucket_count 4 + bucket_field_name key + columns key,value + columns.types string:string +#### A masked pattern was here #### + name default.bucket_big + numFiles 8 + numPartitions 2 + numRows 0 + partition_columns ds + rawDataSize 0 + serialization.ddl struct bucket_big { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 11624 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.bucket_big + name: default.bucket_big +#### A masked pattern was here #### + Partition + base file name: ds=2008-04-09 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2008-04-09 + properties: + bucket_count 4 + bucket_field_name key + columns key,value + columns.types string:string +#### A masked pattern was here #### + name default.bucket_big + numFiles 4 + numRows 0 + partition_columns ds + rawDataSize 0 + serialization.ddl struct bucket_big { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + 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: + SORTBUCKETCOLSPREFIX TRUE + bucket_count 4 + bucket_field_name key + columns key,value + columns.types string:string +#### A masked pattern was here #### + name default.bucket_big + numFiles 8 + numPartitions 2 + numRows 0 + partition_columns ds + rawDataSize 0 + serialization.ddl struct bucket_big { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 11624 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.bucket_big + name: default.bucket_big + 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 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0 + columns.types bigint + escape.delim \ + serialization.format 1 + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + Truncated Path -> Alias: + /bucket_big/ds=2008-04-08 [a] + /bucket_big/ds=2008-04-09 [a] + + Stage: Stage-0 + Fetch Operator + limit: -1 + + +PREHOOK: query: select count(*) FROM bucket_big a JOIN bucket_small b ON a.key = b.key +PREHOOK: type: QUERY +PREHOOK: Input: default@bucket_big +PREHOOK: Input: default@bucket_big@ds=2008-04-08 +PREHOOK: Input: default@bucket_big@ds=2008-04-09 +PREHOOK: Input: default@bucket_small +PREHOOK: Input: default@bucket_small@ds=2008-04-08 +PREHOOK: Input: default@bucket_small@ds=2008-04-09 +#### A masked pattern was here #### +POSTHOOK: query: select count(*) FROM bucket_big a JOIN bucket_small b ON a.key = b.key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@bucket_big +POSTHOOK: Input: default@bucket_big@ds=2008-04-08 +POSTHOOK: Input: default@bucket_big@ds=2008-04-09 +POSTHOOK: Input: default@bucket_small +POSTHOOK: Input: default@bucket_small@ds=2008-04-08 +POSTHOOK: Input: default@bucket_small@ds=2008-04-09 +#### A masked pattern was here #### +76
