Saving all output to "!!{outputDirectory}!!/smb_mapjoin_10.q.raw". Enter "record" with no arguments to stop it.
>>>  !run !!{qFileDirectory}!!/smb_mapjoin_10.q
>>>  
>>>  create table tmp_smb_bucket_10(userid int, pageid int, postid int, type string) partitioned by (ds string) CLUSTERED BY (userid) SORTED BY (pageid, postid, type, userid) INTO 2 BUCKETS STORED AS RCFILE;
No rows affected 
>>>  
>>>  alter table tmp_smb_bucket_10 add partition (ds = '1');
No rows affected 
>>>  alter table tmp_smb_bucket_10 add partition (ds = '2');
No rows affected 
>>>  
>>>  -- add dummy files to make sure that the number of files in each partition is same as number of buckets
>>>  
>>>  load data local inpath '../data/files/smbbucket_1.rc' INTO TABLE tmp_smb_bucket_10 partition(ds='1');
No rows affected 
>>>  load data local inpath '../data/files/smbbucket_2.rc' INTO TABLE tmp_smb_bucket_10 partition(ds='1');
No rows affected 
>>>  
>>>  load data local inpath '../data/files/smbbucket_1.rc' INTO TABLE tmp_smb_bucket_10 partition(ds='2');
No rows affected 
>>>  load data local inpath '../data/files/smbbucket_2.rc' INTO TABLE tmp_smb_bucket_10 partition(ds='2');
No rows affected 
>>>  
>>>  set hive.optimize.bucketmapjoin = true;
No rows affected 
>>>  set hive.optimize.bucketmapjoin.sortedmerge = true;
No rows affected 
>>>  set hive.input.format = org.apache.hadoop.hive.ql.io.BucketizedHiveInputFormat;
No rows affected 
>>>  
>>>  explain 
select /*+mapjoin(a)*/ * from tmp_smb_bucket_10 a join tmp_smb_bucket_10 b 
on (a.ds = '1' and b.ds = '2' and 
a.userid = b.userid and 
a.pageid = b.pageid and 
a.postid = b.postid and 
a.type = b.type);
'Explain'
'ABSTRACT SYNTAX TREE:'
'  (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_TABREF (TOK_TABNAME tmp_smb_bucket_10) a) (TOK_TABREF (TOK_TABNAME tmp_smb_bucket_10) b) (and (and (and (and (and (= (. (TOK_TABLE_OR_COL a) ds) '1') (= (. (TOK_TABLE_OR_COL b) ds) '2')) (= (. (TOK_TABLE_OR_COL a) userid) (. (TOK_TABLE_OR_COL b) userid))) (= (. (TOK_TABLE_OR_COL a) pageid) (. (TOK_TABLE_OR_COL b) pageid))) (= (. (TOK_TABLE_OR_COL a) postid) (. (TOK_TABLE_OR_COL b) postid))) (= (. (TOK_TABLE_OR_COL a) type) (. (TOK_TABLE_OR_COL b) type))))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_HINTLIST (TOK_HINT TOK_MAPJOIN (TOK_HINTARGLIST a))) (TOK_SELEXPR TOK_ALLCOLREF))))'
''
'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'
'            Sorted Merge Bucket Map Join Operator'
'              condition map:'
'                   Inner Join 0 to 1'
'              condition expressions:'
'                0 {userid} {pageid} {postid} {type} {ds}'
'                1 {userid} {pageid} {postid} {type} {ds}'
'              handleSkewJoin: false'
'              keys:'
'                0 [Column[userid], Column[pageid], Column[postid], Column[type]]'
'                1 [Column[userid], Column[pageid], Column[postid], Column[type]]'
'              outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col7, _col8, _col9, _col10, _col11'
'              Position of Big Table: 1'
'              Select Operator'
'                expressions:'
'                      expr: _col0'
'                      type: int'
'                      expr: _col1'
'                      type: int'
'                      expr: _col2'
'                      type: int'
'                      expr: _col3'
'                      type: string'
'                      expr: _col4'
'                      type: string'
'                      expr: _col7'
'                      type: int'
'                      expr: _col8'
'                      type: int'
'                      expr: _col9'
'                      type: int'
'                      expr: _col10'
'                      type: string'
'                      expr: _col11'
'                      type: string'
'                outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col7, _col8, _col9, _col10, _col11'
'                Select Operator'
'                  expressions:'
'                        expr: _col0'
'                        type: int'
'                        expr: _col1'
'                        type: int'
'                        expr: _col2'
'                        type: int'
'                        expr: _col3'
'                        type: string'
'                        expr: _col4'
'                        type: string'
'                        expr: _col7'
'                        type: int'
'                        expr: _col8'
'                        type: int'
'                        expr: _col9'
'                        type: int'
'                        expr: _col10'
'                        type: string'
'                        expr: _col11'
'                        type: string'
'                  outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9'
'                  File Output Operator'
'                    compressed: false'
'                    GlobalTableId: 0'
'                    table:'
'                        input format: org.apache.hadoop.mapred.TextInputFormat'
'                        output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat'
''
'  Stage: Stage-0'
'    Fetch Operator'
'      limit: -1'
''
''
84 rows selected 
>>>  
>>>  !record