diff --git a/ql/src/test/queries/clientpositive/bucket_map_join_tez2.q b/ql/src/test/queries/clientpositive/bucket_map_join_tez2.q index 2ce859f..16bb5d1 100644 --- a/ql/src/test/queries/clientpositive/bucket_map_join_tez2.q +++ b/ql/src/test/queries/clientpositive/bucket_map_join_tez2.q @@ -38,7 +38,10 @@ set hive.auto.convert.join.noconditionaltask.size=1500; set hive.convert.join.bucket.mapjoin.tez = false; explain select a.key, b.key from tab_part a join tab_part c on a.key = c.key join tab_part b on a.value = b.value; set hive.convert.join.bucket.mapjoin.tez = true; +set defaults:cbo = ${hiveconf:hive.cbo.enable}; +set hive.cbo.enable=false; explain select a.key, b.key from tab_part a join tab_part c on a.key = c.key join tab_part b on a.value = b.value; +set hive.cbo.enable=${defaults:cbo}; CREATE TABLE tab1(key int, value string) CLUSTERED BY (key) INTO 2 BUCKETS STORED AS TEXTFILE; insert overwrite table tab1 @@ -118,4 +121,4 @@ insert into small values (1),(2),(3),(4),(5),(6); insert into big partition(k=1) values(1),(3),(5),(7),(9); insert into big partition(k=2) values(0),(2),(4),(6),(8); explain select small.i, big.i from small,big where small.i=big.i; -select small.i, big.i from small,big where small.i=big.i order by small.i, big.i; \ No newline at end of file +select small.i, big.i from small,big where small.i=big.i order by small.i, big.i; diff --git a/ql/src/test/results/clientpositive/autoColumnStats_2.q.out b/ql/src/test/results/clientpositive/autoColumnStats_2.q.out index b209ff0..b1161b5 100644 --- a/ql/src/test/results/clientpositive/autoColumnStats_2.q.out +++ b/ql/src/test/results/clientpositive/autoColumnStats_2.q.out @@ -129,7 +129,7 @@ data_type string min max num_nulls 0 -distinct_count 309 +distinct_count 316 avg_col_len 2.812 max_col_len 3 num_trues @@ -148,7 +148,7 @@ data_type string min max num_nulls 0 -distinct_count 309 +distinct_count 316 avg_col_len 2.812 max_col_len 3 num_trues @@ -253,7 +253,7 @@ data_type string min max num_nulls 0 -distinct_count 309 +distinct_count 316 avg_col_len 2.812 max_col_len 3 num_trues @@ -272,7 +272,7 @@ data_type string min max num_nulls 0 -distinct_count 309 +distinct_count 307 avg_col_len 6.812 max_col_len 7 num_trues @@ -301,7 +301,7 @@ data_type string min max num_nulls 10 -distinct_count 309 +distinct_count 316 avg_col_len 2.812 max_col_len 3 num_trues @@ -320,7 +320,7 @@ data_type string min max num_nulls 10 -distinct_count 309 +distinct_count 307 avg_col_len 6.812 max_col_len 7 num_trues @@ -349,7 +349,7 @@ data_type string min max num_nulls 20 -distinct_count 309 +distinct_count 316 avg_col_len 2.812 max_col_len 3 num_trues @@ -368,7 +368,7 @@ data_type string min max num_nulls 10 -distinct_count 319 +distinct_count 316 avg_col_len 8.0 max_col_len 8 num_trues diff --git a/ql/src/test/results/clientpositive/autoColumnStats_9.q.out b/ql/src/test/results/clientpositive/autoColumnStats_9.q.out index 0dfcf04..3466936 100644 --- a/ql/src/test/results/clientpositive/autoColumnStats_9.q.out +++ b/ql/src/test/results/clientpositive/autoColumnStats_9.q.out @@ -251,7 +251,7 @@ data_type int min 0 max 498 num_nulls 0 -distinct_count 309 +distinct_count 303 avg_col_len max_col_len num_trues @@ -270,7 +270,7 @@ data_type string min max num_nulls 0 -distinct_count 309 +distinct_count 307 avg_col_len 6.834630350194552 max_col_len 7 num_trues diff --git a/ql/src/test/results/clientpositive/bitvector.q.out b/ql/src/test/results/clientpositive/bitvector.q.out index 1e0284f..e310ebe 100644 --- a/ql/src/test/results/clientpositive/bitvector.q.out +++ b/ql/src/test/results/clientpositive/bitvector.q.out @@ -9,7 +9,7 @@ data_type string min max num_nulls 0 -distinct_count 309 +distinct_count 316 avg_col_len 2.812 max_col_len 3 num_trues diff --git a/ql/src/test/results/clientpositive/compute_stats_date.q.out b/ql/src/test/results/clientpositive/compute_stats_date.q.out index 1c12421..a91fe3c 100644 --- a/ql/src/test/results/clientpositive/compute_stats_date.q.out +++ b/ql/src/test/results/clientpositive/compute_stats_date.q.out @@ -43,7 +43,7 @@ POSTHOOK: query: select compute_stats(fl_date, 'hll') from tab_date POSTHOOK: type: QUERY POSTHOOK: Input: default@tab_date #### A masked pattern was here #### -{"columntype":"Date","min":"2000-11-20","max":"2010-10-29","countnulls":0,"numdistinctvalues":19,"ndvbitvector":HLL�ê����!���]����������������Y���T��P��R������W��� �ĈN������������} +{"columntype":"Date","min":"2000-11-20","max":"2010-10-29","countnulls":0,"numdistinctvalues":19,"ndvbitvector":HLL�Ǫ����!���]����������������Y���T���P��R������W��� �ĈN������������} PREHOOK: query: explain analyze table tab_date compute statistics for columns fl_date PREHOOK: type: QUERY diff --git a/ql/src/test/results/clientpositive/confirm_initial_tbl_stats.q.out b/ql/src/test/results/clientpositive/confirm_initial_tbl_stats.q.out index a900194..846b600 100644 --- a/ql/src/test/results/clientpositive/confirm_initial_tbl_stats.q.out +++ b/ql/src/test/results/clientpositive/confirm_initial_tbl_stats.q.out @@ -19,7 +19,7 @@ data_type string min max num_nulls 0 -distinct_count 309 +distinct_count 316 avg_col_len 2.812 max_col_len 3 num_trues @@ -105,7 +105,7 @@ data_type string min max num_nulls 0 -distinct_count 309 +distinct_count 307 avg_col_len 6.812 max_col_len 7 num_trues @@ -134,7 +134,7 @@ data_type string min max num_nulls 0 -distinct_count 430 +distinct_count 431 avg_col_len 6.802 max_col_len 7 num_trues @@ -163,7 +163,7 @@ data_type string min max num_nulls 0 -distinct_count 309 +distinct_count 307 avg_col_len 6.812 max_col_len 7 num_trues @@ -199,7 +199,7 @@ data_type string min max num_nulls 0 -distinct_count 309 +distinct_count 316 avg_col_len 2.812 max_col_len 3 num_trues diff --git a/ql/src/test/results/clientpositive/cross_join_merge.q.out b/ql/src/test/results/clientpositive/cross_join_merge.q.out index 7241dfe..f4956de 100644 --- a/ql/src/test/results/clientpositive/cross_join_merge.q.out +++ b/ql/src/test/results/clientpositive/cross_join_merge.q.out @@ -233,7 +233,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join JOIN[11][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product +Warning: Shuffle Join JOIN[14][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Stage-2:MAPRED' is a cross product PREHOOK: query: explain select src1.key from src src1 join src src2 on 5 = src2.key join src src3 on src1.key=src3.key PREHOOK: type: QUERY @@ -250,7 +250,7 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src3 + alias: src1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) @@ -260,29 +260,34 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - sort order: + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string) TableScan - alias: src2 + alias: src3 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (5.0 = UDFToDouble(key)) (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + predicate: key is not null (type: boolean) + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - sort order: - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 - 1 + 0 _col0 (type: string) + 1 _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 125000 Data size: 2781000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -295,45 +300,36 @@ STAGE PLANS: Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 125000 Data size: 2781000 Basic stats: COMPLETE Column stats: NONE + sort order: + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: string) TableScan - alias: src1 + alias: src2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + predicate: (5.0 = UDFToDouble(key)) (type: boolean) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + sort order: + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col2 - Statistics: Num rows: 137500 Data size: 3059100 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col2 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 137500 Data size: 3059100 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 137500 Data size: 3059100 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + 0 + 1 + outputColumnNames: _col0 + Statistics: Num rows: 137500 Data size: 3059050 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 137500 Data size: 3059050 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/describe_table.q.out b/ql/src/test/results/clientpositive/describe_table.q.out index 8f7d0f6..5657eb1 100644 --- a/ql/src/test/results/clientpositive/describe_table.q.out +++ b/ql/src/test/results/clientpositive/describe_table.q.out @@ -205,7 +205,7 @@ data_type string min max num_nulls 0 -distinct_count 309 +distinct_count 316 avg_col_len 2.812 max_col_len 3 num_trues @@ -302,7 +302,7 @@ data_type string min max num_nulls 0 -distinct_count 309 +distinct_count 316 avg_col_len 2.812 max_col_len 3 num_trues diff --git a/ql/src/test/results/clientpositive/encrypted/encryption_move_tbl.q.out b/ql/src/test/results/clientpositive/encrypted/encryption_move_tbl.q.out index 4eee575..5d7e2cb 100644 --- a/ql/src/test/results/clientpositive/encrypted/encryption_move_tbl.q.out +++ b/ql/src/test/results/clientpositive/encrypted/encryption_move_tbl.q.out @@ -66,7 +66,7 @@ data_type int min 0 max 498 num_nulls 0 -distinct_count 309 +distinct_count 303 avg_col_len max_col_len num_trues @@ -85,7 +85,7 @@ data_type string min max num_nulls 0 -distinct_count 309 +distinct_count 307 avg_col_len 6.812 max_col_len 7 num_trues @@ -117,7 +117,7 @@ data_type int min 0 max 498 num_nulls 0 -distinct_count 309 +distinct_count 303 avg_col_len max_col_len num_trues @@ -136,7 +136,7 @@ data_type string min max num_nulls 0 -distinct_count 309 +distinct_count 307 avg_col_len 6.812 max_col_len 7 num_trues diff --git a/ql/src/test/results/clientpositive/hll.q.out b/ql/src/test/results/clientpositive/hll.q.out index 3b90b56..0c80e7e 100644 --- a/ql/src/test/results/clientpositive/hll.q.out +++ b/ql/src/test/results/clientpositive/hll.q.out @@ -182,7 +182,7 @@ data_type int min 0 max 498 num_nulls 0 -distinct_count 309 +distinct_count 303 avg_col_len max_col_len num_trues @@ -236,7 +236,7 @@ data_type double min 0.0 max 498.0 num_nulls 0 -distinct_count 309 +distinct_count 316 avg_col_len max_col_len num_trues @@ -290,7 +290,7 @@ data_type decimal(10,0) min 0 max 498 num_nulls 0 -distinct_count 309 +distinct_count 316 avg_col_len max_col_len num_trues diff --git a/ql/src/test/results/clientpositive/llap/acid_no_buckets.q.out b/ql/src/test/results/clientpositive/llap/acid_no_buckets.q.out index 5fe7544..e02df1b 100644 --- a/ql/src/test/results/clientpositive/llap/acid_no_buckets.q.out +++ b/ql/src/test/results/clientpositive/llap/acid_no_buckets.q.out @@ -302,15 +302,15 @@ STAGE PLANS: Statistics: Num rows: 2015 Data size: 916825 Basic stats: COMPLETE Column stats: PARTIAL Filter Operator predicate: (key) IN ('1001', '213', '43') (type: boolean) - Statistics: Num rows: 20 Data size: 9100 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 19 Data size: 8645 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: ROW__ID (type: struct), ds (type: string), hr (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 20 Data size: 8880 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 19 Data size: 8436 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator key expressions: _col0 (type: struct) sort order: + - Statistics: Num rows: 20 Data size: 8880 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 19 Data size: 8436 Basic stats: COMPLETE Column stats: PARTIAL value expressions: _col1 (type: string), _col2 (type: string) Execution mode: llap LLAP IO: may be used (ACID table) @@ -320,10 +320,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: struct), VALUE._col0 (type: string), VALUE._col1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 20 Data size: 8880 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 19 Data size: 8436 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 8880 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 19 Data size: 8436 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat @@ -800,16 +800,16 @@ STAGE PLANS: Statistics: Num rows: 2015 Data size: 916825 Basic stats: COMPLETE Column stats: PARTIAL Filter Operator predicate: (key) IN ('1001', '213', '43') (type: boolean) - Statistics: Num rows: 20 Data size: 9100 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 19 Data size: 8645 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: ROW__ID (type: struct), ds (type: string), hr (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 20 Data size: 8880 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 19 Data size: 8436 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator key expressions: _col0 (type: struct) sort order: + Map-reduce partition columns: UDFToInteger(_col0) (type: int) - Statistics: Num rows: 20 Data size: 8880 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 19 Data size: 8436 Basic stats: COMPLETE Column stats: PARTIAL value expressions: _col1 (type: string), _col2 (type: string) Execution mode: llap LLAP IO: may be used (ACID table) @@ -819,10 +819,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: struct), VALUE._col0 (type: string), VALUE._col1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 20 Data size: 8880 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 19 Data size: 8436 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 8880 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 19 Data size: 8436 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/autoColumnStats_2.q.out b/ql/src/test/results/clientpositive/llap/autoColumnStats_2.q.out index 0cc0c05..1bf1dff 100644 --- a/ql/src/test/results/clientpositive/llap/autoColumnStats_2.q.out +++ b/ql/src/test/results/clientpositive/llap/autoColumnStats_2.q.out @@ -127,7 +127,7 @@ data_type string min max num_nulls 0 -distinct_count 309 +distinct_count 316 avg_col_len 2.812 max_col_len 3 num_trues @@ -146,7 +146,7 @@ data_type string min max num_nulls 0 -distinct_count 309 +distinct_count 316 avg_col_len 2.812 max_col_len 3 num_trues @@ -251,7 +251,7 @@ data_type string min max num_nulls 0 -distinct_count 309 +distinct_count 316 avg_col_len 2.812 max_col_len 3 num_trues @@ -270,7 +270,7 @@ data_type string min max num_nulls 0 -distinct_count 309 +distinct_count 307 avg_col_len 6.812 max_col_len 7 num_trues @@ -299,7 +299,7 @@ data_type string min max num_nulls 10 -distinct_count 309 +distinct_count 316 avg_col_len 2.812 max_col_len 3 num_trues @@ -318,7 +318,7 @@ data_type string min max num_nulls 10 -distinct_count 309 +distinct_count 307 avg_col_len 6.812 max_col_len 7 num_trues @@ -347,7 +347,7 @@ data_type string min max num_nulls 20 -distinct_count 309 +distinct_count 316 avg_col_len 2.812 max_col_len 3 num_trues @@ -366,7 +366,7 @@ data_type string min max num_nulls 10 -distinct_count 319 +distinct_count 316 avg_col_len 8.0 max_col_len 8 num_trues diff --git a/ql/src/test/results/clientpositive/llap/auto_join1.q.out b/ql/src/test/results/clientpositive/llap/auto_join1.q.out index 9146560..d673ec5 100644 --- a/ql/src/test/results/clientpositive/llap/auto_join1.q.out +++ b/ql/src/test/results/clientpositive/llap/auto_join1.q.out @@ -69,14 +69,14 @@ STAGE PLANS: outputColumnNames: _col0, _col2 input vertices: 0 Map 1 - Statistics: Num rows: 809 Data size: 144002 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), _col2 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 809 Data size: 76855 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 75145 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 809 Data size: 76855 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 75145 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/auto_join21.q.out b/ql/src/test/results/clientpositive/llap/auto_join21.q.out index 4956af4..e79e3a9 100644 --- a/ql/src/test/results/clientpositive/llap/auto_join21.q.out +++ b/ql/src/test/results/clientpositive/llap/auto_join21.q.out @@ -75,25 +75,25 @@ STAGE PLANS: 1 key (type: string) 2 key (type: string) outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11 - Statistics: Num rows: 434 Data size: 231756 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 415 Data size: 221610 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 434 Data size: 231756 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 415 Data size: 221610 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) sort order: ++++++ - Statistics: Num rows: 434 Data size: 231756 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 415 Data size: 221610 Basic stats: COMPLETE Column stats: COMPLETE Reducer 3 Execution mode: llap Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string), KEY.reducesinkkey4 (type: string), KEY.reducesinkkey5 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 434 Data size: 231756 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 415 Data size: 221610 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 434 Data size: 231756 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 415 Data size: 221610 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/auto_join29.q.out b/ql/src/test/results/clientpositive/llap/auto_join29.q.out index 3fb3184..c8fd93f 100644 --- a/ql/src/test/results/clientpositive/llap/auto_join29.q.out +++ b/ql/src/test/results/clientpositive/llap/auto_join29.q.out @@ -75,25 +75,25 @@ STAGE PLANS: 1 key (type: string) 2 key (type: string) outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11 - Statistics: Num rows: 434 Data size: 231756 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 415 Data size: 221610 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 434 Data size: 231756 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 415 Data size: 221610 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) sort order: ++++++ - Statistics: Num rows: 434 Data size: 231756 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 415 Data size: 221610 Basic stats: COMPLETE Column stats: COMPLETE Reducer 3 Execution mode: llap Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string), KEY.reducesinkkey4 (type: string), KEY.reducesinkkey5 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 434 Data size: 231756 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 415 Data size: 221610 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 434 Data size: 231756 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 415 Data size: 221610 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -693,25 +693,25 @@ STAGE PLANS: 1 key (type: string) 2 key (type: string) outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11 - Statistics: Num rows: 143 Data size: 76362 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 137 Data size: 73158 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 143 Data size: 76362 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 137 Data size: 73158 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) sort order: ++++++ - Statistics: Num rows: 143 Data size: 76362 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 137 Data size: 73158 Basic stats: COMPLETE Column stats: COMPLETE Reducer 3 Execution mode: llap Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string), KEY.reducesinkkey4 (type: string), KEY.reducesinkkey5 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 143 Data size: 76362 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 137 Data size: 73158 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 143 Data size: 76362 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 137 Data size: 73158 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1311,25 +1311,25 @@ STAGE PLANS: 1 key (type: string) 2 key (type: string) outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11 - Statistics: Num rows: 432 Data size: 230688 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 415 Data size: 221610 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 432 Data size: 230688 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 415 Data size: 221610 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) sort order: ++++++ - Statistics: Num rows: 432 Data size: 230688 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 415 Data size: 221610 Basic stats: COMPLETE Column stats: COMPLETE Reducer 3 Execution mode: llap Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string), KEY.reducesinkkey4 (type: string), KEY.reducesinkkey5 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 432 Data size: 230688 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 415 Data size: 221610 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 432 Data size: 230688 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 415 Data size: 221610 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1938,25 +1938,25 @@ STAGE PLANS: 1 key (type: string) 2 key (type: string) outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11 - Statistics: Num rows: 434 Data size: 231756 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 415 Data size: 221610 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 434 Data size: 231756 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 415 Data size: 221610 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) sort order: ++++++ - Statistics: Num rows: 434 Data size: 231756 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 415 Data size: 221610 Basic stats: COMPLETE Column stats: COMPLETE Reducer 3 Execution mode: llap Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string), KEY.reducesinkkey4 (type: string), KEY.reducesinkkey5 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 434 Data size: 231756 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 415 Data size: 221610 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 434 Data size: 231756 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 415 Data size: 221610 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -2567,25 +2567,25 @@ STAGE PLANS: 1 key (type: string) 2 key (type: string) outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11 - Statistics: Num rows: 143 Data size: 76362 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 135 Data size: 72090 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 143 Data size: 76362 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 135 Data size: 72090 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) sort order: ++++++ - Statistics: Num rows: 143 Data size: 76362 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 135 Data size: 72090 Basic stats: COMPLETE Column stats: COMPLETE Reducer 3 Execution mode: llap Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string), KEY.reducesinkkey4 (type: string), KEY.reducesinkkey5 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 143 Data size: 76362 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 135 Data size: 72090 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 143 Data size: 76362 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 135 Data size: 72090 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -2685,25 +2685,25 @@ STAGE PLANS: 1 key (type: string) 2 key (type: string) outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11 - Statistics: Num rows: 143 Data size: 76362 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 136 Data size: 72624 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 143 Data size: 76362 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 136 Data size: 72624 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) sort order: ++++++ - Statistics: Num rows: 143 Data size: 76362 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 136 Data size: 72624 Basic stats: COMPLETE Column stats: COMPLETE Reducer 3 Execution mode: llap Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string), KEY.reducesinkkey4 (type: string), KEY.reducesinkkey5 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 143 Data size: 76362 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 136 Data size: 72624 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 143 Data size: 76362 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 136 Data size: 72624 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -3263,15 +3263,15 @@ STAGE PLANS: input vertices: 1 Map 3 2 Map 4 - Statistics: Num rows: 143 Data size: 76362 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 136 Data size: 72624 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 143 Data size: 76362 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 136 Data size: 72624 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) sort order: ++++++ - Statistics: Num rows: 143 Data size: 76362 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 136 Data size: 72624 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Map 3 @@ -3312,10 +3312,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string), KEY.reducesinkkey4 (type: string), KEY.reducesinkkey5 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 143 Data size: 76362 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 136 Data size: 72624 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 143 Data size: 76362 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 136 Data size: 72624 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -3394,15 +3394,15 @@ STAGE PLANS: input vertices: 0 Map 1 2 Map 4 - Statistics: Num rows: 431 Data size: 230154 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 414 Data size: 221076 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 431 Data size: 230154 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 414 Data size: 221076 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) sort order: ++++++ - Statistics: Num rows: 431 Data size: 230154 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 414 Data size: 221076 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Map 4 @@ -3427,10 +3427,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string), KEY.reducesinkkey4 (type: string), KEY.reducesinkkey5 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 431 Data size: 230154 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 414 Data size: 221076 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 431 Data size: 230154 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 414 Data size: 221076 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -3511,15 +3511,15 @@ STAGE PLANS: input vertices: 1 Map 3 2 Map 4 - Statistics: Num rows: 143 Data size: 76362 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 135 Data size: 72090 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 143 Data size: 76362 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 135 Data size: 72090 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) sort order: ++++++ - Statistics: Num rows: 143 Data size: 76362 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 135 Data size: 72090 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Map 3 @@ -3560,10 +3560,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string), KEY.reducesinkkey4 (type: string), KEY.reducesinkkey5 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 143 Data size: 76362 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 135 Data size: 72090 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 143 Data size: 76362 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 135 Data size: 72090 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/auto_join30.q.out b/ql/src/test/results/clientpositive/llap/auto_join30.q.out index e5f5fda..271f806 100644 --- a/ql/src/test/results/clientpositive/llap/auto_join30.q.out +++ b/ql/src/test/results/clientpositive/llap/auto_join30.q.out @@ -67,7 +67,7 @@ STAGE PLANS: outputColumnNames: _col2, _col3 input vertices: 0 Map 1 - Statistics: Num rows: 809 Data size: 144002 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(hash(_col2,_col3)) mode: hash @@ -167,7 +167,7 @@ STAGE PLANS: outputColumnNames: _col2, _col3 input vertices: 1 Map 3 - Statistics: Num rows: 809 Data size: 144002 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(hash(_col2,_col3)) mode: hash @@ -300,7 +300,7 @@ STAGE PLANS: outputColumnNames: _col2, _col3 input vertices: 0 Map 1 - Statistics: Num rows: 809 Data size: 144002 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(hash(_col2,_col3)) mode: hash @@ -431,7 +431,7 @@ STAGE PLANS: input vertices: 0 Map 1 2 Map 4 - Statistics: Num rows: 1309 Data size: 233002 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1251 Data size: 222678 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(hash(_col2,_col3)) mode: hash @@ -605,7 +605,7 @@ STAGE PLANS: 1 _col0 (type: string) 2 _col0 (type: string) outputColumnNames: _col2, _col3 - Statistics: Num rows: 1309 Data size: 233002 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1251 Data size: 222678 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(hash(_col2,_col3)) mode: hash @@ -758,7 +758,7 @@ STAGE PLANS: 1 _col0 (type: string) 2 _col0 (type: string) outputColumnNames: _col2, _col3 - Statistics: Num rows: 1309 Data size: 233002 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1251 Data size: 222678 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(hash(_col2,_col3)) mode: hash @@ -911,7 +911,7 @@ STAGE PLANS: 1 _col0 (type: string) 2 _col0 (type: string) outputColumnNames: _col2, _col3 - Statistics: Num rows: 1309 Data size: 233002 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1251 Data size: 222678 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(hash(_col2,_col3)) mode: hash @@ -1064,7 +1064,7 @@ STAGE PLANS: 1 _col0 (type: string) 2 _col0 (type: string) outputColumnNames: _col2, _col3 - Statistics: Num rows: 1309 Data size: 233002 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1251 Data size: 222678 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(hash(_col2,_col3)) mode: hash diff --git a/ql/src/test/results/clientpositive/llap/bucket_map_join_tez1.q.out b/ql/src/test/results/clientpositive/llap/bucket_map_join_tez1.q.out index 4df0d41..6a55484 100644 --- a/ql/src/test/results/clientpositive/llap/bucket_map_join_tez1.q.out +++ b/ql/src/test/results/clientpositive/llap/bucket_map_join_tez1.q.out @@ -235,25 +235,25 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 391 Data size: 72726 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 399 Data size: 74214 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 391 Data size: 72726 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 399 Data size: 74214 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string) sort order: +++ - Statistics: Num rows: 391 Data size: 72726 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 399 Data size: 74214 Basic stats: COMPLETE Column stats: COMPLETE Reducer 3 Execution mode: llap Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 391 Data size: 72726 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 399 Data size: 74214 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 391 Data size: 72726 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 399 Data size: 74214 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -823,15 +823,15 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col3 input vertices: 0 Map 1 - Statistics: Num rows: 391 Data size: 72726 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 399 Data size: 74214 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 391 Data size: 72726 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 399 Data size: 74214 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string) sort order: +++ - Statistics: Num rows: 391 Data size: 72726 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 399 Data size: 74214 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Reducer 3 @@ -840,10 +840,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 391 Data size: 72726 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 399 Data size: 74214 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 391 Data size: 72726 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 399 Data size: 74214 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1436,7 +1436,7 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 195 Data size: 1560 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 199 Data size: 1592 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash @@ -1565,7 +1565,7 @@ STAGE PLANS: 1 _col0 (type: int) input vertices: 1 Map 4 - Statistics: Num rows: 195 Data size: 1560 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 199 Data size: 1592 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash @@ -1696,7 +1696,7 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 632 Data size: 5056 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 658 Data size: 5264 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash @@ -1731,16 +1731,16 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col1 - Statistics: Num rows: 391 Data size: 1564 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 399 Data size: 1596 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 391 Data size: 1564 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 399 Data size: 1596 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 391 Data size: 1564 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 399 Data size: 1596 Basic stats: COMPLETE Column stats: COMPLETE Stage: Stage-0 Fetch Operator @@ -1838,11 +1838,11 @@ STAGE PLANS: outputColumnNames: _col1 input vertices: 1 Map 4 - Statistics: Num rows: 391 Data size: 1564 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 399 Data size: 1596 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 391 Data size: 1564 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 399 Data size: 1596 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -1851,7 +1851,7 @@ STAGE PLANS: 1 _col0 (type: int) input vertices: 0 Map 1 - Statistics: Num rows: 632 Data size: 5056 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 658 Data size: 5264 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash @@ -2007,7 +2007,7 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 632 Data size: 5056 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 658 Data size: 5264 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash @@ -2042,16 +2042,16 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col1 - Statistics: Num rows: 391 Data size: 1564 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 399 Data size: 1596 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 391 Data size: 1564 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 399 Data size: 1596 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 391 Data size: 1564 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 399 Data size: 1596 Basic stats: COMPLETE Column stats: COMPLETE Stage: Stage-0 Fetch Operator @@ -2149,11 +2149,11 @@ STAGE PLANS: outputColumnNames: _col1 input vertices: 1 Map 4 - Statistics: Num rows: 391 Data size: 1564 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 399 Data size: 1596 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 391 Data size: 1564 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 399 Data size: 1596 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -2162,7 +2162,7 @@ STAGE PLANS: 1 _col0 (type: int) input vertices: 0 Map 1 - Statistics: Num rows: 632 Data size: 5056 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 658 Data size: 5264 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash @@ -2566,11 +2566,11 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col1, _col2 - Statistics: Num rows: 391 Data size: 37145 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 399 Data size: 37905 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: int), substr(_col2, 5) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 391 Data size: 37145 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 399 Data size: 37905 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col1) keys: _col0 (type: int) @@ -2708,11 +2708,11 @@ STAGE PLANS: outputColumnNames: _col1, _col2 input vertices: 0 Map 2 - Statistics: Num rows: 391 Data size: 37145 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 399 Data size: 37905 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: int), substr(_col2, 5) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 391 Data size: 37145 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 399 Data size: 37905 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col1) keys: _col0 (type: int) @@ -2866,14 +2866,14 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col1 (type: int) outputColumnNames: _col1, _col2, _col3 - Statistics: Num rows: 247 Data size: 25441 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 252 Data size: 25956 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col3 (type: int), _col2 (type: double), _col1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 247 Data size: 25441 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 252 Data size: 25956 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 247 Data size: 25441 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 252 Data size: 25956 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -2949,14 +2949,14 @@ STAGE PLANS: outputColumnNames: _col1, _col2, _col3 input vertices: 1 Reducer 3 - Statistics: Num rows: 247 Data size: 25441 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 252 Data size: 25956 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col3 (type: int), _col2 (type: double), _col1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 247 Data size: 25441 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 252 Data size: 25956 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 247 Data size: 25441 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 252 Data size: 25956 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -3139,14 +3139,14 @@ STAGE PLANS: 1 _col0 (type: int) 2 _col0 (type: int) outputColumnNames: _col0, _col1, _col4 - Statistics: Num rows: 619 Data size: 115134 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 631 Data size: 117366 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: string), _col4 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 619 Data size: 115134 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 631 Data size: 117366 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 619 Data size: 115134 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 631 Data size: 117366 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -3202,14 +3202,14 @@ STAGE PLANS: input vertices: 1 Map 2 2 Map 3 - Statistics: Num rows: 619 Data size: 115134 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 631 Data size: 117366 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: string), _col4 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 619 Data size: 115134 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 631 Data size: 117366 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 619 Data size: 115134 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 631 Data size: 117366 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -3304,12 +3304,12 @@ STAGE PLANS: outputColumnNames: _col0, _col1 input vertices: 1 Map 3 - Statistics: Num rows: 391 Data size: 37145 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 399 Data size: 37905 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 391 Data size: 37145 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 399 Data size: 37905 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Execution mode: llap LLAP IO: no inputs @@ -3362,14 +3362,14 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 618 Data size: 114948 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 631 Data size: 117366 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 618 Data size: 114948 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 631 Data size: 117366 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 618 Data size: 114948 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 631 Data size: 117366 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -3422,7 +3422,7 @@ STAGE PLANS: outputColumnNames: _col0, _col1 input vertices: 1 Map 2 - Statistics: Num rows: 391 Data size: 37145 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 399 Data size: 37905 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -3432,14 +3432,14 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col3 input vertices: 1 Map 3 - Statistics: Num rows: 618 Data size: 114948 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 631 Data size: 117366 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 618 Data size: 114948 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 631 Data size: 117366 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 618 Data size: 114948 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 631 Data size: 117366 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -3586,14 +3586,14 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 195 Data size: 20085 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 199 Data size: 20497 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: double), _col3 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 195 Data size: 20085 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 199 Data size: 20497 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 195 Data size: 20085 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 199 Data size: 20497 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -3675,14 +3675,14 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col3 input vertices: 0 Reducer 2 - Statistics: Num rows: 195 Data size: 20085 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 199 Data size: 20497 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: double), _col3 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 195 Data size: 20085 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 199 Data size: 20497 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 195 Data size: 20085 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 199 Data size: 20497 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -3799,14 +3799,14 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 247 Data size: 25441 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 252 Data size: 25956 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: double), _col3 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 247 Data size: 25441 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 252 Data size: 25956 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 247 Data size: 25441 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 252 Data size: 25956 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -3882,14 +3882,14 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col3 input vertices: 0 Reducer 2 - Statistics: Num rows: 247 Data size: 25441 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 252 Data size: 25956 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: double), _col3 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 247 Data size: 25441 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 252 Data size: 25956 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 247 Data size: 25441 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 252 Data size: 25956 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -3987,10 +3987,10 @@ STAGE PLANS: 0 _col1 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 391 Data size: 72726 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 394 Data size: 73284 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 391 Data size: 72726 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 394 Data size: 73284 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -4071,10 +4071,10 @@ STAGE PLANS: 0 _col1 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 391 Data size: 72726 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 394 Data size: 73284 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 391 Data size: 72726 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 394 Data size: 73284 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -4293,7 +4293,7 @@ STAGE PLANS: #### A masked pattern was here #### Edges: Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) - Reducer 3 <- Map 1 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) + Reducer 3 <- Map 5 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 @@ -4309,11 +4309,18 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: _col0 (type: int) + key expressions: _col1 (type: string) sort order: + - Map-reduce partition columns: _col0 (type: int) + Map-reduce partition columns: _col1 (type: string) Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: string) + value expressions: _col0 (type: int) + Execution mode: llap + LLAP IO: no inputs + Map 4 + Map Operator Tree: + TableScan + alias: b + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: value is not null (type: boolean) Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE @@ -4329,7 +4336,7 @@ STAGE PLANS: value expressions: _col0 (type: int) Execution mode: llap LLAP IO: no inputs - Map 4 + Map 5 Map Operator Tree: TableScan alias: c @@ -4355,16 +4362,16 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 809 Data size: 76855 Basic stats: COMPLETE Column stats: COMPLETE + 0 _col1 (type: string) + 1 _col1 (type: string) + outputColumnNames: _col0, _col2 + Statistics: Num rows: 814 Data size: 6512 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: _col1 (type: string) + key expressions: _col0 (type: int) sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 809 Data size: 76855 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: int) + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 814 Data size: 6512 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col2 (type: int) Reducer 3 Execution mode: llap Reduce Operator Tree: @@ -4372,17 +4379,17 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col1 (type: string) - 1 _col1 (type: string) - outputColumnNames: _col0, _col3 - Statistics: Num rows: 1309 Data size: 10472 Basic stats: COMPLETE Column stats: COMPLETE + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0, _col2 + Statistics: Num rows: 1343 Data size: 10744 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: _col0 (type: int), _col3 (type: int) + expressions: _col0 (type: int), _col2 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1309 Data size: 10472 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1343 Data size: 10744 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1309 Data size: 10472 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1343 Data size: 10744 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -4407,8 +4414,8 @@ STAGE PLANS: Tez #### A masked pattern was here #### Edges: - Map 1 <- Map 3 (CUSTOM_EDGE) Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) + Reducer 3 <- Map 5 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 @@ -4423,41 +4430,12 @@ STAGE PLANS: expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1 - input vertices: - 1 Map 3 - Statistics: Num rows: 809 Data size: 76855 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col1 (type: string) - sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 809 Data size: 76855 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: int) - Execution mode: llap - LLAP IO: no inputs - Map 3 - Map Operator Tree: - TableScan - alias: c - Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: _col0 (type: int) + key expressions: _col1 (type: string) sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE + Map-reduce partition columns: _col1 (type: string) + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: int) Execution mode: llap LLAP IO: no inputs Map 4 @@ -4480,6 +4458,25 @@ STAGE PLANS: value expressions: _col0 (type: int) Execution mode: llap LLAP IO: no inputs + Map 5 + Map Operator Tree: + TableScan + alias: c + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: llap + LLAP IO: no inputs Reducer 2 Execution mode: llap Reduce Operator Tree: @@ -4489,15 +4486,32 @@ STAGE PLANS: keys: 0 _col1 (type: string) 1 _col1 (type: string) - outputColumnNames: _col0, _col3 - Statistics: Num rows: 1309 Data size: 10472 Basic stats: COMPLETE Column stats: COMPLETE + outputColumnNames: _col0, _col2 + Statistics: Num rows: 814 Data size: 6512 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 814 Data size: 6512 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col2 (type: int) + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0, _col2 + Statistics: Num rows: 1343 Data size: 10744 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: _col0 (type: int), _col3 (type: int) + expressions: _col0 (type: int), _col2 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1309 Data size: 10472 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1343 Data size: 10744 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1309 Data size: 10472 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1343 Data size: 10744 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -4594,14 +4608,14 @@ STAGE PLANS: 0 _col0 (type: int), _col2 (type: string) 1 _col0 (type: int), _col2 (type: string) outputColumnNames: _col0, _col1, _col4 - Statistics: Num rows: 391 Data size: 72726 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 399 Data size: 74214 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: string), _col4 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 391 Data size: 72726 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 399 Data size: 74214 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 391 Data size: 72726 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 399 Data size: 74214 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -4698,14 +4712,14 @@ STAGE PLANS: 0 _col0 (type: int), _col2 (type: string) 1 _col0 (type: int), _col2 (type: string) outputColumnNames: _col0, _col1, _col4 - Statistics: Num rows: 391 Data size: 72726 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 399 Data size: 74214 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: string), _col4 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 391 Data size: 72726 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 399 Data size: 74214 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 391 Data size: 72726 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 399 Data size: 74214 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -4783,14 +4797,14 @@ STAGE PLANS: 0 _col0 (type: int), _col1 (type: string) 1 _col0 (type: int), _col1 (type: string) outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 391 Data size: 72726 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 394 Data size: 73284 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 391 Data size: 72726 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 394 Data size: 73284 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 391 Data size: 72726 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 394 Data size: 73284 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -5358,14 +5372,14 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col3 input vertices: 0 Map 1 - Statistics: Num rows: 391 Data size: 72726 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 394 Data size: 73284 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 391 Data size: 72726 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 394 Data size: 73284 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 391 Data size: 72726 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 394 Data size: 73284 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -5979,14 +5993,14 @@ STAGE PLANS: 0 _col0 (type: int), _col1 (type: string) 1 _col0 (type: int), _col1 (type: string) outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 391 Data size: 72726 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 394 Data size: 73284 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 391 Data size: 72726 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 394 Data size: 73284 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 391 Data size: 72726 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 394 Data size: 73284 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -6554,14 +6568,14 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col3 input vertices: 0 Map 1 - Statistics: Num rows: 391 Data size: 72726 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 394 Data size: 73284 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 391 Data size: 72726 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 394 Data size: 73284 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 391 Data size: 72726 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 394 Data size: 73284 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/bucket_map_join_tez2.q.out b/ql/src/test/results/clientpositive/llap/bucket_map_join_tez2.q.out index b84edde..ee951ec 100644 --- a/ql/src/test/results/clientpositive/llap/bucket_map_join_tez2.q.out +++ b/ql/src/test/results/clientpositive/llap/bucket_map_join_tez2.q.out @@ -178,7 +178,7 @@ STAGE PLANS: #### A masked pattern was here #### Edges: Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) - Reducer 3 <- Map 1 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) + Reducer 3 <- Map 5 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 @@ -194,11 +194,18 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: _col0 (type: int) + key expressions: _col1 (type: string) sort order: + - Map-reduce partition columns: _col0 (type: int) + Map-reduce partition columns: _col1 (type: string) Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: string) + value expressions: _col0 (type: int) + Execution mode: llap + LLAP IO: no inputs + Map 4 + Map Operator Tree: + TableScan + alias: b + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: value is not null (type: boolean) Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE @@ -214,7 +221,7 @@ STAGE PLANS: value expressions: _col0 (type: int) Execution mode: llap LLAP IO: no inputs - Map 4 + Map 5 Map Operator Tree: TableScan alias: c @@ -240,16 +247,16 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 809 Data size: 76855 Basic stats: COMPLETE Column stats: COMPLETE + 0 _col1 (type: string) + 1 _col1 (type: string) + outputColumnNames: _col0, _col2 + Statistics: Num rows: 814 Data size: 6512 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: _col1 (type: string) + key expressions: _col0 (type: int) sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 809 Data size: 76855 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: int) + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 814 Data size: 6512 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col2 (type: int) Reducer 3 Execution mode: llap Reduce Operator Tree: @@ -257,17 +264,17 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col1 (type: string) - 1 _col1 (type: string) - outputColumnNames: _col0, _col3 - Statistics: Num rows: 1309 Data size: 10472 Basic stats: COMPLETE Column stats: COMPLETE + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0, _col2 + Statistics: Num rows: 1343 Data size: 10744 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: _col0 (type: int), _col3 (type: int) + expressions: _col0 (type: int), _col2 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1309 Data size: 10472 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1343 Data size: 10744 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1309 Data size: 10472 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1343 Data size: 10744 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -304,26 +311,22 @@ STAGE PLANS: Filter Operator predicate: (key is not null and value is not null) (type: boolean) Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int), value (type: string) + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 key (type: int) + 1 key (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1 - input vertices: - 1 Map 3 - Statistics: Num rows: 809 Data size: 76855 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col1 (type: string) - sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 809 Data size: 76855 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: int) + input vertices: + 1 Map 3 + Statistics: Num rows: 825 Data size: 78375 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: string) + sort order: + + Map-reduce partition columns: _col1 (type: string) + Statistics: Num rows: 825 Data size: 78375 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: int) Execution mode: llap LLAP IO: no inputs Map 3 @@ -334,15 +337,11 @@ STAGE PLANS: Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 + Reduce Output Operator + key expressions: key (type: int) + sort order: + + Map-reduce partition columns: key (type: int) Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Map 4 @@ -353,16 +352,12 @@ STAGE PLANS: Filter Operator predicate: value is not null (type: boolean) Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: value (type: string) + sort order: + + Map-reduce partition columns: value (type: string) Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col1 (type: string) - sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: int) + value expressions: key (type: int) Execution mode: llap LLAP IO: no inputs Reducer 2 @@ -373,16 +368,16 @@ STAGE PLANS: Inner Join 0 to 1 keys: 0 _col1 (type: string) - 1 _col1 (type: string) - outputColumnNames: _col0, _col3 - Statistics: Num rows: 1309 Data size: 10472 Basic stats: COMPLETE Column stats: COMPLETE + 1 value (type: string) + outputColumnNames: _col0, _col12 + Statistics: Num rows: 1343 Data size: 10744 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: _col0 (type: int), _col3 (type: int) + expressions: _col0 (type: int), _col12 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1309 Data size: 10472 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1343 Data size: 10744 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1309 Data size: 10472 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1343 Data size: 10744 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -496,14 +491,14 @@ STAGE PLANS: 0 UDFToDouble(_col0) (type: double) 1 UDFToDouble(_col0) (type: double) outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 391 Data size: 72726 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 382 Data size: 71052 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 391 Data size: 72726 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 382 Data size: 71052 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 391 Data size: 72726 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 382 Data size: 71052 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -585,14 +580,14 @@ STAGE PLANS: 0 UDFToDouble(_col0) (type: double) 1 UDFToDouble(_col0) (type: double) outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 391 Data size: 72726 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 382 Data size: 71052 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 391 Data size: 72726 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 382 Data size: 71052 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 391 Data size: 72726 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 382 Data size: 71052 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -670,10 +665,10 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 267 Data size: 2136 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 272 Data size: 2176 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 267 Data size: 2136 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 272 Data size: 2176 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -724,10 +719,10 @@ STAGE PLANS: outputColumnNames: _col0, _col1 input vertices: 1 Map 2 - Statistics: Num rows: 267 Data size: 2136 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 272 Data size: 2176 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 267 Data size: 2136 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 272 Data size: 2176 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -826,10 +821,10 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 267 Data size: 2136 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 272 Data size: 2176 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 267 Data size: 2136 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 272 Data size: 2176 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -880,10 +875,10 @@ STAGE PLANS: outputColumnNames: _col0, _col1 input vertices: 1 Map 2 - Statistics: Num rows: 267 Data size: 2136 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 272 Data size: 2176 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 267 Data size: 2136 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 272 Data size: 2176 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -982,10 +977,10 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 267 Data size: 2136 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 272 Data size: 2176 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 267 Data size: 2136 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 272 Data size: 2176 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1055,10 +1050,10 @@ STAGE PLANS: outputColumnNames: _col0, _col1 input vertices: 0 Map 1 - Statistics: Num rows: 267 Data size: 2136 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 272 Data size: 2176 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 267 Data size: 2136 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 272 Data size: 2176 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1565,7 +1560,7 @@ STAGE PLANS: keys: 0 _col0 (type: int), _col1 (type: string) 1 _col0 (type: int), _col1 (type: string) - Statistics: Num rows: 195 Data size: 1560 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 197 Data size: 1576 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash @@ -1675,7 +1670,7 @@ STAGE PLANS: 1 _col0 (type: int), _col1 (type: string) input vertices: 1 Map 4 - Statistics: Num rows: 195 Data size: 1560 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 197 Data size: 1576 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash @@ -1768,15 +1763,11 @@ STAGE PLANS: Filter Operator predicate: i is not null (type: boolean) Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: i (type: int) - outputColumnNames: _col0 + Reduce Output Operator + key expressions: i (type: int) + sort order: + + Map-reduce partition columns: i (type: int) Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Execution mode: llap LLAP IO: all inputs Map 2 @@ -1787,27 +1778,30 @@ STAGE PLANS: Filter Operator predicate: i is not null (type: boolean) Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: i (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1 - input vertices: - 0 Map 1 - Statistics: Num rows: 11 Data size: 88 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 11 Data size: 88 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 i (type: int) + 1 i (type: int) + outputColumnNames: _col0, _col4 + input vertices: + 0 Map 1 + Statistics: Num rows: 11 Data size: 88 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (_col0 = _col4) (type: boolean) + Statistics: Num rows: 5 Data size: 40 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: int), _col4 (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 5 Data size: 40 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 5 Data size: 40 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Execution mode: llap LLAP IO: all inputs diff --git a/ql/src/test/results/clientpositive/llap/correlationoptimizer1.q.out b/ql/src/test/results/clientpositive/llap/correlationoptimizer1.q.out index b138a2d..ed5a7a5 100644 --- a/ql/src/test/results/clientpositive/llap/correlationoptimizer1.q.out +++ b/ql/src/test/results/clientpositive/llap/correlationoptimizer1.q.out @@ -72,7 +72,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 40 Data size: 3440 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 3354 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string) @@ -220,7 +220,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 40 Data size: 3440 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 3354 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string) @@ -360,7 +360,7 @@ STAGE PLANS: outputColumnNames: _col0 input vertices: 0 Map 1 - Statistics: Num rows: 40 Data size: 3440 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 3354 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string) @@ -515,18 +515,18 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 20 Data size: 1720 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 19 Data size: 1634 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 940 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 9 Data size: 846 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 10 Data size: 940 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 9 Data size: 846 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Reducer 3 Execution mode: llap @@ -536,11 +536,11 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 940 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 9 Data size: 846 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: hash(_col0) (type: int), hash(_col1) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 940 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 9 Data size: 846 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col0), sum(_col1) mode: hash @@ -668,18 +668,18 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 20 Data size: 1720 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 19 Data size: 1634 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 940 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 9 Data size: 846 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 10 Data size: 940 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 9 Data size: 846 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Reducer 3 Execution mode: llap @@ -689,11 +689,11 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 940 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 9 Data size: 846 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: hash(_col0) (type: int), hash(_col1) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 940 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 9 Data size: 846 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col0), sum(_col1) mode: hash @@ -810,7 +810,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 40 Data size: 3440 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 3354 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string) @@ -952,7 +952,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 40 Data size: 3440 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 3354 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string) @@ -1094,7 +1094,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col1 - Statistics: Num rows: 40 Data size: 3480 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 3393 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col1 (type: string) @@ -1236,7 +1236,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col1 - Statistics: Num rows: 40 Data size: 3480 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 3393 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col1 (type: string) @@ -1375,18 +1375,18 @@ STAGE PLANS: 0 _col0 (type: string), _col1 (type: string) 1 _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col3 - Statistics: Num rows: 40 Data size: 7080 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6903 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string), _col3 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 20 Data size: 3700 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 19 Data size: 3515 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 20 Data size: 3700 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 19 Data size: 3515 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: bigint) Reducer 3 Execution mode: llap @@ -1396,10 +1396,10 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 20 Data size: 3700 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 19 Data size: 3515 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 3700 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 19 Data size: 3515 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1506,18 +1506,18 @@ STAGE PLANS: 0 _col0 (type: string), _col1 (type: string) 1 _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col3 - Statistics: Num rows: 40 Data size: 7080 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6903 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string), _col3 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 20 Data size: 3700 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 19 Data size: 3515 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 20 Data size: 3700 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 19 Data size: 3515 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: bigint) Reducer 3 Execution mode: llap @@ -1527,10 +1527,10 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 20 Data size: 3700 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 19 Data size: 3515 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 3700 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 19 Data size: 3515 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1924,7 +1924,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 3526 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 3440 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string) @@ -2066,7 +2066,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 3526 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 3440 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string) @@ -2208,7 +2208,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 525 Data size: 3526 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 525 Data size: 3440 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string) @@ -2350,7 +2350,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 525 Data size: 3526 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 525 Data size: 3440 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string) @@ -2499,18 +2499,18 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 40 Data size: 7000 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6825 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 20 Data size: 3660 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 19 Data size: 3477 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 20 Data size: 3660 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 19 Data size: 3477 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: bigint) Reducer 3 Execution mode: llap @@ -2520,11 +2520,11 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 20 Data size: 3660 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 19 Data size: 3477 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: hash(_col0) (type: int), hash(_col1) (type: int), hash(_col2) (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 20 Data size: 3660 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 19 Data size: 3477 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col0), sum(_col1), sum(_col2) mode: hash @@ -2648,18 +2648,18 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 40 Data size: 7000 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6825 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 20 Data size: 3660 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 19 Data size: 3477 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 20 Data size: 3660 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 19 Data size: 3477 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: bigint) Reducer 3 Execution mode: llap @@ -2669,11 +2669,11 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 20 Data size: 3660 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 19 Data size: 3477 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: hash(_col0) (type: int), hash(_col1) (type: int), hash(_col2) (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 20 Data size: 3660 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 19 Data size: 3477 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col0), sum(_col1), sum(_col2) mode: hash @@ -2796,7 +2796,7 @@ STAGE PLANS: 0 _col0 (type: string), _col1 (type: string) 1 _col0 (type: string), _col1 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 40 Data size: 3440 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 3354 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string) @@ -2944,7 +2944,7 @@ STAGE PLANS: 0 _col0 (type: string), _col1 (type: string) 1 _col0 (type: string), _col1 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 40 Data size: 3440 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 3354 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string) diff --git a/ql/src/test/results/clientpositive/llap/correlationoptimizer2.q.out b/ql/src/test/results/clientpositive/llap/correlationoptimizer2.q.out index 64248e7..0a39763 100644 --- a/ql/src/test/results/clientpositive/llap/correlationoptimizer2.q.out +++ b/ql/src/test/results/clientpositive/llap/correlationoptimizer2.q.out @@ -1804,16 +1804,16 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col1, _col2 - Statistics: Num rows: 40 Data size: 7000 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6825 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string), _col2 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 40 Data size: 7000 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6825 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 40 Data size: 7000 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6825 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reducer 3 Execution mode: llap @@ -1825,11 +1825,11 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 30 Data size: 8070 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 29 Data size: 7801 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: hash(_col0) (type: int), hash(_col1) (type: int), hash(_col2) (type: int), hash(_col3) (type: int) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 30 Data size: 8070 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 29 Data size: 7801 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col0), sum(_col1), sum(_col2), sum(_col3) mode: hash @@ -1985,16 +1985,16 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col1, _col2 - Statistics: Num rows: 40 Data size: 7000 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6825 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string), _col2 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 40 Data size: 7000 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6825 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 40 Data size: 7000 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6825 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reducer 3 Execution mode: llap @@ -2006,11 +2006,11 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 30 Data size: 8070 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 29 Data size: 7801 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: hash(_col0) (type: int), hash(_col1) (type: int), hash(_col2) (type: int), hash(_col3) (type: int) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 30 Data size: 8070 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 29 Data size: 7801 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col0), sum(_col1), sum(_col2), sum(_col3) mode: hash diff --git a/ql/src/test/results/clientpositive/llap/correlationoptimizer3.q.out b/ql/src/test/results/clientpositive/llap/correlationoptimizer3.q.out index 0d3c3bc..005af0e 100644 --- a/ql/src/test/results/clientpositive/llap/correlationoptimizer3.q.out +++ b/ql/src/test/results/clientpositive/llap/correlationoptimizer3.q.out @@ -101,16 +101,16 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col1, _col2 - Statistics: Num rows: 40 Data size: 7000 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6825 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string), _col2 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 40 Data size: 7000 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6825 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 40 Data size: 7000 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6825 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reducer 3 Execution mode: llap @@ -122,11 +122,11 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 40 Data size: 7320 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 7137 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: hash(_col0) (type: int), hash(_col3) (type: int), hash(_col1) (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 40 Data size: 7320 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 7137 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col0), sum(_col1), sum(_col2) mode: hash @@ -161,7 +161,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col1 - Statistics: Num rows: 40 Data size: 3440 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 3354 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col1 (type: string) @@ -318,16 +318,16 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col1, _col2 - Statistics: Num rows: 40 Data size: 7000 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6825 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string), _col2 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 40 Data size: 7000 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6825 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 40 Data size: 7000 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6825 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reducer 3 Execution mode: llap @@ -339,11 +339,11 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 40 Data size: 7320 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 7137 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: hash(_col0) (type: int), hash(_col3) (type: int), hash(_col1) (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 40 Data size: 7320 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 7137 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col0), sum(_col1), sum(_col2) mode: hash @@ -378,7 +378,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col1 - Statistics: Num rows: 40 Data size: 3440 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 3354 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col1 (type: string) @@ -482,11 +482,11 @@ STAGE PLANS: outputColumnNames: _col1, _col2 input vertices: 1 Map 3 - Statistics: Num rows: 40 Data size: 7000 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6825 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string), _col2 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 40 Data size: 7000 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6825 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -496,11 +496,11 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col3 input vertices: 1 Reducer 5 - Statistics: Num rows: 40 Data size: 7320 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 7137 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: hash(_col0) (type: int), hash(_col3) (type: int), hash(_col1) (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 40 Data size: 7320 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 7137 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col0), sum(_col1), sum(_col2) mode: hash @@ -553,7 +553,7 @@ STAGE PLANS: outputColumnNames: _col1 input vertices: 1 Map 6 - Statistics: Num rows: 40 Data size: 3440 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 3354 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col1 (type: string) @@ -746,16 +746,16 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col1, _col2 - Statistics: Num rows: 40 Data size: 7000 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6825 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string), _col2 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 40 Data size: 7000 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6825 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 40 Data size: 7000 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6825 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reducer 3 Execution mode: llap @@ -767,11 +767,11 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col1, _col2, _col3 - Statistics: Num rows: 40 Data size: 7320 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 7137 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: hash(_col2) (type: int), hash(_col3) (type: int), hash(_col1) (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 40 Data size: 7320 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 7137 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col0), sum(_col1), sum(_col2) mode: hash @@ -806,7 +806,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col1 - Statistics: Num rows: 40 Data size: 3440 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 3354 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col1 (type: string) @@ -963,16 +963,16 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col1, _col2 - Statistics: Num rows: 40 Data size: 7000 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6825 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string), _col2 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 40 Data size: 7000 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6825 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 40 Data size: 7000 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6825 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reducer 3 Execution mode: llap @@ -984,11 +984,11 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col1, _col2, _col3 - Statistics: Num rows: 40 Data size: 7320 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 7137 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: hash(_col2) (type: int), hash(_col3) (type: int), hash(_col1) (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 40 Data size: 7320 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 7137 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col0), sum(_col1), sum(_col2) mode: hash @@ -1023,7 +1023,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col1 - Statistics: Num rows: 40 Data size: 3440 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 3354 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col1 (type: string) @@ -1127,11 +1127,11 @@ STAGE PLANS: outputColumnNames: _col1, _col2 input vertices: 1 Map 3 - Statistics: Num rows: 40 Data size: 7000 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6825 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string), _col2 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 40 Data size: 7000 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6825 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -1141,11 +1141,11 @@ STAGE PLANS: outputColumnNames: _col1, _col2, _col3 input vertices: 1 Reducer 5 - Statistics: Num rows: 40 Data size: 7320 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 7137 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: hash(_col2) (type: int), hash(_col3) (type: int), hash(_col1) (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 40 Data size: 7320 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 7137 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col0), sum(_col1), sum(_col2) mode: hash @@ -1198,7 +1198,7 @@ STAGE PLANS: outputColumnNames: _col1 input vertices: 1 Map 6 - Statistics: Num rows: 40 Data size: 3440 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 3354 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col1 (type: string) diff --git a/ql/src/test/results/clientpositive/llap/correlationoptimizer6.q.out b/ql/src/test/results/clientpositive/llap/correlationoptimizer6.q.out index d94dda2..6742bb7 100644 --- a/ql/src/test/results/clientpositive/llap/correlationoptimizer6.q.out +++ b/ql/src/test/results/clientpositive/llap/correlationoptimizer6.q.out @@ -172,18 +172,18 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 809 Data size: 70383 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 68817 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Reducer 8 Execution mode: llap @@ -193,12 +193,12 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Stage: Stage-0 @@ -416,18 +416,18 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 809 Data size: 70383 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 68817 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Reducer 8 Execution mode: llap @@ -437,12 +437,12 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Stage: Stage-0 @@ -593,18 +593,18 @@ STAGE PLANS: outputColumnNames: _col0 input vertices: 1 Map 6 - Statistics: Num rows: 809 Data size: 70383 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 68817 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: llap LLAP IO: no inputs @@ -650,7 +650,7 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -788,10 +788,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 20 Data size: 3620 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 19 Data size: 3439 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 3620 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 19 Data size: 3439 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -929,10 +929,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 20 Data size: 3620 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 19 Data size: 3439 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 3620 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 19 Data size: 3439 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1105,18 +1105,18 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 809 Data size: 70383 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 68817 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Reducer 5 Execution mode: llap @@ -1126,12 +1126,12 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Stage: Stage-0 @@ -1286,18 +1286,18 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 809 Data size: 70383 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 68817 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Reducer 5 Execution mode: llap @@ -1307,12 +1307,12 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Stage: Stage-0 @@ -1864,14 +1864,14 @@ STAGE PLANS: 1 _col0 (type: string) 2 _col0 (type: string) outputColumnNames: _col1, _col2, _col3 - Statistics: Num rows: 40 Data size: 7240 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 7059 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string), _col2 (type: string), _col3 (type: bigint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 40 Data size: 7240 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 7059 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 40 Data size: 7240 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 7059 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1886,18 +1886,18 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 809 Data size: 70383 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 68817 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Reducer 5 Execution mode: llap @@ -1907,12 +1907,12 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Stage: Stage-0 @@ -2082,14 +2082,14 @@ STAGE PLANS: 1 _col0 (type: string) 2 _col0 (type: string) outputColumnNames: _col1, _col2, _col3 - Statistics: Num rows: 40 Data size: 7240 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 7059 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string), _col2 (type: string), _col3 (type: bigint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 40 Data size: 7240 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 7059 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 40 Data size: 7240 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 7059 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -2104,18 +2104,18 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 809 Data size: 70383 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 68817 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Reducer 5 Execution mode: llap @@ -2125,12 +2125,12 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Stage: Stage-0 @@ -2298,18 +2298,18 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 809 Data size: 70383 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 68817 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Reducer 3 Execution mode: llap @@ -2319,12 +2319,12 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Reducer 4 Execution mode: llap @@ -2338,14 +2338,14 @@ STAGE PLANS: 1 _col0 (type: string) 2 _col0 (type: string) outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 40 Data size: 7240 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 7059 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col3 (type: string), _col0 (type: string), _col1 (type: bigint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 40 Data size: 7240 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 7059 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 40 Data size: 7240 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 7059 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -2516,18 +2516,18 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 809 Data size: 70383 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 68817 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Reducer 3 Execution mode: llap @@ -2537,12 +2537,12 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Reducer 4 Execution mode: llap @@ -2556,14 +2556,14 @@ STAGE PLANS: 1 _col0 (type: string) 2 _col0 (type: string) outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 40 Data size: 7240 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 7059 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col3 (type: string), _col0 (type: string), _col1 (type: bigint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 40 Data size: 7240 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 7059 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 40 Data size: 7240 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 7059 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -3327,18 +3327,18 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 809 Data size: 144002 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 404 Data size: 75144 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 395 Data size: 73470 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 404 Data size: 75144 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 395 Data size: 73470 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: bigint) Reducer 9 Execution mode: llap @@ -3348,12 +3348,12 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 404 Data size: 75144 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 395 Data size: 73470 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 404 Data size: 75144 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 395 Data size: 73470 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col2 (type: bigint) Stage: Stage-0 @@ -3572,18 +3572,18 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 809 Data size: 144002 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 404 Data size: 75144 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 395 Data size: 73470 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 404 Data size: 75144 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 395 Data size: 73470 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: bigint) Reducer 8 Execution mode: llap @@ -3593,12 +3593,12 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 404 Data size: 75144 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 395 Data size: 73470 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 404 Data size: 75144 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 395 Data size: 73470 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col2 (type: bigint) Stage: Stage-0 @@ -3749,18 +3749,18 @@ STAGE PLANS: outputColumnNames: _col0, _col1 input vertices: 1 Map 6 - Statistics: Num rows: 809 Data size: 144002 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 404 Data size: 75144 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 395 Data size: 73470 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 404 Data size: 75144 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 395 Data size: 73470 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: bigint) Execution mode: llap LLAP IO: no inputs @@ -3806,7 +3806,7 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 404 Data size: 75144 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 395 Data size: 73470 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 diff --git a/ql/src/test/results/clientpositive/llap/cross_join.q.out b/ql/src/test/results/clientpositive/llap/cross_join.q.out index 6bde893..f5666a8 100644 --- a/ql/src/test/results/clientpositive/llap/cross_join.q.out +++ b/ql/src/test/results/clientpositive/llap/cross_join.q.out @@ -200,10 +200,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 809 Data size: 70383 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 68817 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 809 Data size: 70383 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 68817 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -390,10 +390,10 @@ STAGE PLANS: outputColumnNames: _col0 input vertices: 1 Map 2 - Statistics: Num rows: 809 Data size: 70383 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 68817 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 809 Data size: 70383 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 68817 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/dynamic_semijoin_reduction.q.out b/ql/src/test/results/clientpositive/llap/dynamic_semijoin_reduction.q.out index 89af586..6dd4dbf 100644 --- a/ql/src/test/results/clientpositive/llap/dynamic_semijoin_reduction.q.out +++ b/ql/src/test/results/clientpositive/llap/dynamic_semijoin_reduction.q.out @@ -452,12 +452,12 @@ STAGE PLANS: keys: _col0 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 309 Data size: 26883 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 27492 Basic stats: COMPLETE Column stats: COMPLETE Dynamic Partitioning Event Operator Target column: ds (string) Target Input: srcpart_small Partition key expr: ds - Statistics: Num rows: 309 Data size: 26883 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 27492 Basic stats: COMPLETE Column stats: COMPLETE Target Vertex: Map 4 Execution mode: llap LLAP IO: all inputs @@ -723,7 +723,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 2000 Data size: 174000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: min(_col0), max(_col0), bloom_filter(_col0, expectedEntries=309) + aggregations: min(_col0), max(_col0), bloom_filter(_col0, expectedEntries=316) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE @@ -826,7 +826,7 @@ STAGE PLANS: Execution mode: llap Reduce Operator Tree: Group By Operator - aggregations: min(VALUE._col0), max(VALUE._col1), bloom_filter(VALUE._col2, expectedEntries=309) + aggregations: min(VALUE._col0), max(VALUE._col1), bloom_filter(VALUE._col2, expectedEntries=316) mode: final outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE diff --git a/ql/src/test/results/clientpositive/llap/dynamic_semijoin_reduction_sw.q.out b/ql/src/test/results/clientpositive/llap/dynamic_semijoin_reduction_sw.q.out index 81b6bde..11d76b7 100644 --- a/ql/src/test/results/clientpositive/llap/dynamic_semijoin_reduction_sw.q.out +++ b/ql/src/test/results/clientpositive/llap/dynamic_semijoin_reduction_sw.q.out @@ -231,7 +231,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 1000 Data size: 87000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: min(_col0), max(_col0), bloom_filter(_col0, expectedEntries=309) + aggregations: min(_col0), max(_col0), bloom_filter(_col0, expectedEntries=316) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE @@ -284,7 +284,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 1000 Data size: 87000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: min(_col0), max(_col0), bloom_filter(_col0, expectedEntries=309) + aggregations: min(_col0), max(_col0), bloom_filter(_col0, expectedEntries=316) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE @@ -369,7 +369,7 @@ STAGE PLANS: Execution mode: llap Reduce Operator Tree: Group By Operator - aggregations: min(VALUE._col0), max(VALUE._col1), bloom_filter(VALUE._col2, expectedEntries=309) + aggregations: min(VALUE._col0), max(VALUE._col1), bloom_filter(VALUE._col2, expectedEntries=316) mode: final outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE @@ -430,7 +430,7 @@ STAGE PLANS: Execution mode: llap Reduce Operator Tree: Group By Operator - aggregations: min(VALUE._col0), max(VALUE._col1), bloom_filter(VALUE._col2, expectedEntries=309) + aggregations: min(VALUE._col0), max(VALUE._col1), bloom_filter(VALUE._col2, expectedEntries=316) mode: final outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE diff --git a/ql/src/test/results/clientpositive/llap/dynamic_semijoin_user_level.q.out b/ql/src/test/results/clientpositive/llap/dynamic_semijoin_user_level.q.out index 30596ee..b66ea3b 100644 --- a/ql/src/test/results/clientpositive/llap/dynamic_semijoin_user_level.q.out +++ b/ql/src/test/results/clientpositive/llap/dynamic_semijoin_user_level.q.out @@ -256,8 +256,8 @@ Stage-0 predicate:key is not null TableScan [TS_0] (rows=2000 width=87) default@srcpart_date,srcpart_date,Tbl:COMPLETE,Col:COMPLETE,Output:["key"] - Dynamic Partitioning Event Operator [EVENT_21] (rows=309 width=87) - Group By Operator [GBY_20] (rows=309 width=87) + Dynamic Partitioning Event Operator [EVENT_21] (rows=316 width=87) + Group By Operator [GBY_20] (rows=316 width=87) Output:["_col0"],keys:_col0 Select Operator [SEL_19] (rows=2000 width=87) Output:["_col0"] @@ -434,11 +434,11 @@ Stage-0 <-Reducer 4 [BROADCAST_EDGE] llap BROADCAST [RS_44] Group By Operator [GBY_41] (rows=1 width=552) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=309)"] + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=316)"] <-Map 1 [CUSTOM_SIMPLE_EDGE] llap PARTITION_ONLY_SHUFFLE [RS_40] Group By Operator [GBY_39] (rows=1 width=552) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=309)"] + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=316)"] Select Operator [SEL_38] (rows=2000 width=87) Output:["_col0"] Please refer to the previous Select Operator [SEL_2] diff --git a/ql/src/test/results/clientpositive/llap/explainanalyze_2.q.out b/ql/src/test/results/clientpositive/llap/explainanalyze_2.q.out index 55f3a78..acf3986 100644 --- a/ql/src/test/results/clientpositive/llap/explainanalyze_2.q.out +++ b/ql/src/test/results/clientpositive/llap/explainanalyze_2.q.out @@ -41,134 +41,129 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Map 1 <- Union 2 (CONTAINS) +Map 12 <- Union 10 (CONTAINS) Map 13 <- Union 14 (CONTAINS) Map 16 <- Union 14 (CONTAINS) -Map 8 <- Union 2 (CONTAINS) -Reducer 10 <- Map 9 (SIMPLE_EDGE), Reducer 15 (SIMPLE_EDGE) -Reducer 11 <- Map 17 (SIMPLE_EDGE), Reducer 10 (SIMPLE_EDGE), Union 6 (CONTAINS) +Map 9 <- Union 10 (CONTAINS) +Reducer 11 <- Union 10 (SIMPLE_EDGE) Reducer 15 <- Union 14 (SIMPLE_EDGE) -Reducer 3 <- Union 2 (SIMPLE_EDGE) -Reducer 4 <- Map 9 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) -Reducer 5 <- Map 12 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE), Union 6 (CONTAINS) -Reducer 7 <- Union 6 (SIMPLE_EDGE) +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) +Reducer 3 <- Reducer 11 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE), Union 4 (CONTAINS) +Reducer 5 <- Union 4 (SIMPLE_EDGE) +Reducer 6 <- Map 1 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) +Reducer 7 <- Reducer 15 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE), Union 4 (CONTAINS) Stage-0 Fetch Operator limit:-1 Stage-1 - Reducer 7 llap + Reducer 5 llap File Output Operator [FS_56] - Group By Operator [GBY_54] (rows=32/15 width=177) + Group By Operator [GBY_54] (rows=48/15 width=177) Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 - <-Union 6 [SIMPLE_EDGE] - <-Reducer 11 [CONTAINS] llap + <-Union 4 [SIMPLE_EDGE] + <-Reducer 3 [CONTAINS] llap Reduce Output Operator [RS_53] PartitionCols:_col0, _col1 - Select Operator [SEL_49] (rows=67/61 width=177) + Select Operator [SEL_24] (rows=66/61 width=177) Output:["_col0","_col1"] - Merge Join Operator [MERGEJOIN_82] (rows=67/61 width=177) - Conds:RS_46._col2=RS_47._col0(Inner),Output:["_col1","_col2"] - <-Map 17 [SIMPLE_EDGE] llap - SHUFFLE [RS_47] - PartitionCols:_col0 - Select Operator [SEL_42] (rows=500/500 width=87) - Output:["_col0"] - Filter Operator [FIL_78] (rows=500/500 width=87) - predicate:key is not null - TableScan [TS_40] (rows=500/500 width=87) - default@src,y,Tbl:COMPLETE,Col:COMPLETE,Output:["key"] - <-Reducer 10 [SIMPLE_EDGE] llap - SHUFFLE [RS_46] + Merge Join Operator [MERGEJOIN_79] (rows=66/61 width=177) + Conds:RS_21._col2=RS_22._col1(Inner),Output:["_col1","_col4"] + <-Reducer 11 [SIMPLE_EDGE] llap + SHUFFLE [RS_22] + PartitionCols:_col1 + Select Operator [SEL_17] (rows=525/319 width=178) + Output:["_col1"] + Group By Operator [GBY_16] (rows=525/319 width=178) + Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 + <-Union 10 [SIMPLE_EDGE] + <-Map 12 [CONTAINS] llap + Reduce Output Operator [RS_15] + PartitionCols:_col1, _col0 + Select Operator [SEL_11] (rows=500/500 width=178) + Output:["_col0","_col1"] + Filter Operator [FIL_72] (rows=500/500 width=178) + predicate:value is not null + TableScan [TS_9] (rows=500/500 width=178) + Output:["key","value"] + <-Map 9 [CONTAINS] llap + Reduce Output Operator [RS_15] + PartitionCols:_col1, _col0 + Select Operator [SEL_8] (rows=25/25 width=175) + Output:["_col0","_col1"] + Filter Operator [FIL_71] (rows=25/25 width=175) + predicate:value is not null + TableScan [TS_6] (rows=25/25 width=175) + Output:["key","value"] + <-Reducer 2 [SIMPLE_EDGE] llap + SHUFFLE [RS_21] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_81] (rows=42/52 width=177) - Conds:RS_43._col1=RS_44._col1(Inner),Output:["_col1","_col2"] - <-Map 9 [SIMPLE_EDGE] llap - SHUFFLE [RS_44] - PartitionCols:_col1 - Select Operator [SEL_14] (rows=25/25 width=175) + Merge Join Operator [MERGEJOIN_77] (rows=39/37 width=175) + Conds:RS_18._col0=RS_19._col0(Inner),Output:["_col1","_col2"] + <-Map 1 [SIMPLE_EDGE] llap + SHUFFLE [RS_18] + PartitionCols:_col0 + Select Operator [SEL_2] (rows=500/500 width=87) + Output:["_col0"] + Filter Operator [FIL_69] (rows=500/500 width=87) + predicate:key is not null + TableScan [TS_0] (rows=500/500 width=87) + default@src,y,Tbl:COMPLETE,Col:COMPLETE,Output:["key"] + <-Map 8 [SIMPLE_EDGE] llap + SHUFFLE [RS_19] + PartitionCols:_col0 + Select Operator [SEL_5] (rows=25/25 width=175) Output:["_col0","_col1"] - Filter Operator [FIL_73] (rows=25/25 width=175) + Filter Operator [FIL_70] (rows=25/25 width=175) predicate:(key is not null and value is not null) - TableScan [TS_12] (rows=25/25 width=175) + TableScan [TS_3] (rows=25/25 width=175) default@src1,x,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"] - <-Reducer 15 [SIMPLE_EDGE] llap - SHUFFLE [RS_43] - PartitionCols:_col1 - Select Operator [SEL_36] (rows=525/319 width=178) - Output:["_col1"] - Group By Operator [GBY_35] (rows=525/319 width=178) - Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 - <-Union 14 [SIMPLE_EDGE] - <-Map 13 [CONTAINS] llap - Reduce Output Operator [RS_34] - PartitionCols:_col1, _col0 - Select Operator [SEL_27] (rows=25/25 width=175) - Output:["_col0","_col1"] - Filter Operator [FIL_75] (rows=25/25 width=175) - predicate:value is not null - TableScan [TS_25] (rows=25/25 width=175) - Output:["key","value"] - <-Map 16 [CONTAINS] llap - Reduce Output Operator [RS_34] - PartitionCols:_col1, _col0 - Select Operator [SEL_30] (rows=500/500 width=178) - Output:["_col0","_col1"] - Filter Operator [FIL_76] (rows=500/500 width=178) - predicate:value is not null - TableScan [TS_28] (rows=500/500 width=178) - Output:["key","value"] - <-Reducer 5 [CONTAINS] llap + <-Reducer 7 [CONTAINS] llap Reduce Output Operator [RS_53] PartitionCols:_col0, _col1 - Select Operator [SEL_24] (rows=67/61 width=177) + Select Operator [SEL_49] (rows=66/61 width=177) Output:["_col0","_col1"] - Merge Join Operator [MERGEJOIN_80] (rows=67/61 width=177) - Conds:RS_21._col2=RS_22._col0(Inner),Output:["_col1","_col2"] - <-Map 12 [SIMPLE_EDGE] llap - SHUFFLE [RS_22] - PartitionCols:_col0 - Select Operator [SEL_17] (rows=500/500 width=87) - Output:["_col0"] - Filter Operator [FIL_74] (rows=500/500 width=87) - predicate:key is not null - TableScan [TS_15] (rows=500/500 width=87) - default@src,y,Tbl:COMPLETE,Col:COMPLETE,Output:["key"] - <-Reducer 4 [SIMPLE_EDGE] llap - SHUFFLE [RS_21] + Merge Join Operator [MERGEJOIN_80] (rows=66/61 width=177) + Conds:RS_46._col2=RS_47._col1(Inner),Output:["_col1","_col4"] + <-Reducer 15 [SIMPLE_EDGE] llap + SHUFFLE [RS_47] + PartitionCols:_col1 + Select Operator [SEL_42] (rows=525/319 width=178) + Output:["_col1"] + Group By Operator [GBY_41] (rows=525/319 width=178) + Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 + <-Union 14 [SIMPLE_EDGE] + <-Map 13 [CONTAINS] llap + Reduce Output Operator [RS_40] + PartitionCols:_col1, _col0 + Select Operator [SEL_33] (rows=25/25 width=175) + Output:["_col0","_col1"] + Filter Operator [FIL_75] (rows=25/25 width=175) + predicate:value is not null + TableScan [TS_31] (rows=25/25 width=175) + Output:["key","value"] + <-Map 16 [CONTAINS] llap + Reduce Output Operator [RS_40] + PartitionCols:_col1, _col0 + Select Operator [SEL_36] (rows=500/500 width=178) + Output:["_col0","_col1"] + Filter Operator [FIL_76] (rows=500/500 width=178) + predicate:value is not null + TableScan [TS_34] (rows=500/500 width=178) + Output:["key","value"] + <-Reducer 6 [SIMPLE_EDGE] llap + SHUFFLE [RS_46] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_79] (rows=42/52 width=177) - Conds:RS_18._col1=RS_19._col1(Inner),Output:["_col1","_col2"] - <-Map 9 [SIMPLE_EDGE] llap - SHUFFLE [RS_19] - PartitionCols:_col1 - Please refer to the previous Select Operator [SEL_14] - <-Reducer 3 [SIMPLE_EDGE] llap - SHUFFLE [RS_18] - PartitionCols:_col1 - Select Operator [SEL_11] (rows=525/319 width=178) - Output:["_col1"] - Group By Operator [GBY_10] (rows=525/319 width=178) - Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 - <-Union 2 [SIMPLE_EDGE] - <-Map 1 [CONTAINS] llap - Reduce Output Operator [RS_9] - PartitionCols:_col1, _col0 - Select Operator [SEL_2] (rows=25/25 width=175) - Output:["_col0","_col1"] - Filter Operator [FIL_71] (rows=25/25 width=175) - predicate:value is not null - TableScan [TS_0] (rows=25/25 width=175) - Output:["key","value"] - <-Map 8 [CONTAINS] llap - Reduce Output Operator [RS_9] - PartitionCols:_col1, _col0 - Select Operator [SEL_5] (rows=500/500 width=178) - Output:["_col0","_col1"] - Filter Operator [FIL_72] (rows=500/500 width=178) - predicate:value is not null - TableScan [TS_3] (rows=500/500 width=178) - Output:["key","value"] + Merge Join Operator [MERGEJOIN_78] (rows=39/37 width=175) + Conds:RS_43._col0=RS_44._col0(Inner),Output:["_col1","_col2"] + <-Map 1 [SIMPLE_EDGE] llap + SHUFFLE [RS_43] + PartitionCols:_col0 + Please refer to the previous Select Operator [SEL_2] + <-Map 8 [SIMPLE_EDGE] llap + SHUFFLE [RS_44] + PartitionCols:_col0 + Please refer to the previous Select Operator [SEL_5] PREHOOK: query: SELECT x.key, y.value FROM src1 x JOIN src y ON (x.key = y.key) @@ -229,249 +224,244 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Map 1 <- Union 2 (CONTAINS) -Map 10 <- Union 2 (CONTAINS) +Map 13 <- Union 14 (CONTAINS) +Map 16 <- Union 14 (CONTAINS) Map 17 <- Union 18 (CONTAINS) Map 22 <- Union 18 (CONTAINS) Map 23 <- Union 20 (CONTAINS) -Map 25 <- Union 26 (CONTAINS) -Map 32 <- Union 26 (CONTAINS) -Map 33 <- Union 28 (CONTAINS) -Map 34 <- Union 30 (CONTAINS) -Reducer 12 <- Map 11 (SIMPLE_EDGE), Reducer 21 (SIMPLE_EDGE) -Reducer 13 <- Map 24 (SIMPLE_EDGE), Reducer 12 (SIMPLE_EDGE), Union 6 (CONTAINS) -Reducer 14 <- Map 11 (SIMPLE_EDGE), Reducer 31 (SIMPLE_EDGE) -Reducer 15 <- Map 16 (SIMPLE_EDGE), Reducer 14 (SIMPLE_EDGE), Union 8 (CONTAINS) +Map 24 <- Union 25 (CONTAINS) +Map 31 <- Union 25 (CONTAINS) +Map 32 <- Union 27 (CONTAINS) +Map 33 <- Union 29 (CONTAINS) +Reducer 10 <- Map 1 (SIMPLE_EDGE), Map 12 (SIMPLE_EDGE) +Reducer 11 <- Reducer 10 (SIMPLE_EDGE), Reducer 30 (SIMPLE_EDGE), Union 6 (CONTAINS) +Reducer 15 <- Union 14 (SIMPLE_EDGE) Reducer 19 <- Union 18 (SIMPLE_EDGE), Union 20 (CONTAINS) +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 12 (SIMPLE_EDGE) Reducer 21 <- Union 20 (SIMPLE_EDGE) -Reducer 27 <- Union 26 (SIMPLE_EDGE), Union 28 (CONTAINS) -Reducer 29 <- Union 28 (SIMPLE_EDGE), Union 30 (CONTAINS) -Reducer 3 <- Union 2 (SIMPLE_EDGE) -Reducer 31 <- Union 30 (SIMPLE_EDGE) -Reducer 4 <- Map 11 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) -Reducer 5 <- Map 16 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE), Union 6 (CONTAINS) -Reducer 7 <- Union 6 (SIMPLE_EDGE), Union 8 (CONTAINS) -Reducer 9 <- Union 8 (SIMPLE_EDGE) +Reducer 26 <- Union 25 (SIMPLE_EDGE), Union 27 (CONTAINS) +Reducer 28 <- Union 27 (SIMPLE_EDGE), Union 29 (CONTAINS) +Reducer 3 <- Reducer 15 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE), Union 4 (CONTAINS) +Reducer 30 <- Union 29 (SIMPLE_EDGE) +Reducer 5 <- Union 4 (SIMPLE_EDGE), Union 6 (CONTAINS) +Reducer 7 <- Union 6 (SIMPLE_EDGE) +Reducer 8 <- Map 1 (SIMPLE_EDGE), Map 12 (SIMPLE_EDGE) +Reducer 9 <- Reducer 21 (SIMPLE_EDGE), Reducer 8 (SIMPLE_EDGE), Union 4 (CONTAINS) Stage-0 Fetch Operator limit:-1 Stage-1 - Reducer 9 llap + Reducer 7 llap File Output Operator [FS_114] - Group By Operator [GBY_112] (rows=398/15 width=177) + Group By Operator [GBY_112] (rows=384/15 width=177) Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 - <-Union 8 [SIMPLE_EDGE] - <-Reducer 15 [CONTAINS] llap + <-Union 6 [SIMPLE_EDGE] + <-Reducer 11 [CONTAINS] llap Reduce Output Operator [RS_111] PartitionCols:_col0, _col1 - Select Operator [SEL_107] (rows=199/61 width=177) + Select Operator [SEL_107] (rows=193/61 width=177) Output:["_col0","_col1"] - Merge Join Operator [MERGEJOIN_162] (rows=199/61 width=177) - Conds:RS_104._col2=RS_105._col0(Inner),Output:["_col2","_col5"] - <-Map 16 [SIMPLE_EDGE] llap - SHUFFLE [RS_105] - PartitionCols:_col0 - Select Operator [SEL_17] (rows=500/500 width=178) - Output:["_col0","_col1"] - Filter Operator [FIL_145] (rows=500/500 width=178) - predicate:key is not null - TableScan [TS_15] (rows=500/500 width=178) - default@src,y,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"] - <-Reducer 14 [SIMPLE_EDGE] llap + Merge Join Operator [MERGEJOIN_156] (rows=193/61 width=177) + Conds:RS_104._col3=RS_105._col1(Inner),Output:["_col1","_col2"] + <-Reducer 10 [SIMPLE_EDGE] llap SHUFFLE [RS_104] - PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_161] (rows=123/52 width=86) - Conds:RS_101._col1=RS_102._col1(Inner),Output:["_col2"] - <-Map 11 [SIMPLE_EDGE] llap + PartitionCols:_col3 + Merge Join Operator [MERGEJOIN_153] (rows=39/37 width=266) + Conds:RS_101._col0=RS_102._col0(Inner),Output:["_col1","_col2","_col3"] + <-Map 1 [SIMPLE_EDGE] llap + SHUFFLE [RS_101] + PartitionCols:_col0 + Select Operator [SEL_2] (rows=500/500 width=178) + Output:["_col0","_col1"] + Filter Operator [FIL_136] (rows=500/500 width=178) + predicate:key is not null + TableScan [TS_0] (rows=500/500 width=178) + default@src,y,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"] + <-Map 12 [SIMPLE_EDGE] llap SHUFFLE [RS_102] - PartitionCols:_col1 - Select Operator [SEL_14] (rows=25/25 width=175) + PartitionCols:_col0 + Select Operator [SEL_5] (rows=25/25 width=175) Output:["_col0","_col1"] - Filter Operator [FIL_144] (rows=25/25 width=175) + Filter Operator [FIL_137] (rows=25/25 width=175) predicate:(key is not null and value is not null) - TableScan [TS_12] (rows=25/25 width=175) + TableScan [TS_3] (rows=25/25 width=175) default@src1,x,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"] - <-Reducer 31 [SIMPLE_EDGE] llap - SHUFFLE [RS_101] - PartitionCols:_col1 - Select Operator [SEL_94] (rows=1525/319 width=178) - Output:["_col1"] - Group By Operator [GBY_93] (rows=1525/319 width=178) - Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 - <-Union 30 [SIMPLE_EDGE] - <-Map 34 [CONTAINS] llap - Reduce Output Operator [RS_92] - PartitionCols:_col1, _col0 - Select Operator [SEL_88] (rows=500/500 width=178) - Output:["_col0","_col1"] - Filter Operator [FIL_154] (rows=500/500 width=178) - predicate:value is not null - TableScan [TS_86] (rows=500/500 width=178) - Output:["key","value"] - <-Reducer 29 [CONTAINS] llap - Reduce Output Operator [RS_92] - PartitionCols:_col1, _col0 - Select Operator [SEL_85] (rows=1025/319 width=178) - Output:["_col0","_col1"] - Group By Operator [GBY_84] (rows=1025/319 width=178) - Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 - <-Union 28 [SIMPLE_EDGE] - <-Map 33 [CONTAINS] llap - Reduce Output Operator [RS_83] - PartitionCols:_col1, _col0 - Select Operator [SEL_79] (rows=500/500 width=178) - Output:["_col0","_col1"] - Filter Operator [FIL_153] (rows=500/500 width=178) - predicate:value is not null - TableScan [TS_77] (rows=500/500 width=178) - Output:["key","value"] - <-Reducer 27 [CONTAINS] llap - Reduce Output Operator [RS_83] - PartitionCols:_col1, _col0 - Select Operator [SEL_76] (rows=525/319 width=178) - Output:["_col0","_col1"] - Group By Operator [GBY_75] (rows=525/319 width=178) - Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 - <-Union 26 [SIMPLE_EDGE] - <-Map 25 [CONTAINS] llap - Reduce Output Operator [RS_74] - PartitionCols:_col1, _col0 - Select Operator [SEL_67] (rows=25/25 width=175) - Output:["_col0","_col1"] - Filter Operator [FIL_151] (rows=25/25 width=175) - predicate:value is not null - TableScan [TS_65] (rows=25/25 width=175) - Output:["key","value"] - <-Map 32 [CONTAINS] llap - Reduce Output Operator [RS_74] - PartitionCols:_col1, _col0 - Select Operator [SEL_70] (rows=500/500 width=178) - Output:["_col0","_col1"] - Filter Operator [FIL_152] (rows=500/500 width=178) - predicate:value is not null - TableScan [TS_68] (rows=500/500 width=178) - Output:["key","value"] - <-Reducer 7 [CONTAINS] llap + <-Reducer 30 [SIMPLE_EDGE] llap + SHUFFLE [RS_105] + PartitionCols:_col1 + Select Operator [SEL_100] (rows=1525/319 width=178) + Output:["_col1"] + Group By Operator [GBY_99] (rows=1525/319 width=178) + Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 + <-Union 29 [SIMPLE_EDGE] + <-Map 33 [CONTAINS] llap + Reduce Output Operator [RS_98] + PartitionCols:_col1, _col0 + Select Operator [SEL_94] (rows=500/500 width=178) + Output:["_col0","_col1"] + Filter Operator [FIL_150] (rows=500/500 width=178) + predicate:value is not null + TableScan [TS_92] (rows=500/500 width=178) + Output:["key","value"] + <-Reducer 28 [CONTAINS] llap + Reduce Output Operator [RS_98] + PartitionCols:_col1, _col0 + Select Operator [SEL_91] (rows=1025/319 width=178) + Output:["_col0","_col1"] + Group By Operator [GBY_90] (rows=1025/319 width=178) + Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 + <-Union 27 [SIMPLE_EDGE] + <-Map 32 [CONTAINS] llap + Reduce Output Operator [RS_89] + PartitionCols:_col1, _col0 + Select Operator [SEL_85] (rows=500/500 width=178) + Output:["_col0","_col1"] + Filter Operator [FIL_149] (rows=500/500 width=178) + predicate:value is not null + TableScan [TS_83] (rows=500/500 width=178) + Output:["key","value"] + <-Reducer 26 [CONTAINS] llap + Reduce Output Operator [RS_89] + PartitionCols:_col1, _col0 + Select Operator [SEL_82] (rows=525/319 width=178) + Output:["_col0","_col1"] + Group By Operator [GBY_81] (rows=525/319 width=178) + Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 + <-Union 25 [SIMPLE_EDGE] + <-Map 24 [CONTAINS] llap + Reduce Output Operator [RS_80] + PartitionCols:_col1, _col0 + Select Operator [SEL_73] (rows=25/25 width=175) + Output:["_col0","_col1"] + Filter Operator [FIL_147] (rows=25/25 width=175) + predicate:value is not null + TableScan [TS_71] (rows=25/25 width=175) + Output:["key","value"] + <-Map 31 [CONTAINS] llap + Reduce Output Operator [RS_80] + PartitionCols:_col1, _col0 + Select Operator [SEL_76] (rows=500/500 width=178) + Output:["_col0","_col1"] + Filter Operator [FIL_148] (rows=500/500 width=178) + predicate:value is not null + TableScan [TS_74] (rows=500/500 width=178) + Output:["key","value"] + <-Reducer 5 [CONTAINS] llap Reduce Output Operator [RS_111] PartitionCols:_col0, _col1 - Group By Operator [GBY_63] (rows=199/15 width=177) + Group By Operator [GBY_63] (rows=196/15 width=177) Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 - <-Union 6 [SIMPLE_EDGE] - <-Reducer 13 [CONTAINS] llap + <-Union 4 [SIMPLE_EDGE] + <-Reducer 3 [CONTAINS] llap Reduce Output Operator [RS_62] PartitionCols:_col0, _col1 - Select Operator [SEL_58] (rows=132/61 width=177) + Select Operator [SEL_24] (rows=66/61 width=177) Output:["_col0","_col1"] - Merge Join Operator [MERGEJOIN_160] (rows=132/61 width=177) - Conds:RS_55._col2=RS_56._col0(Inner),Output:["_col2","_col5"] - <-Map 24 [SIMPLE_EDGE] llap - SHUFFLE [RS_56] - PartitionCols:_col0 - Select Operator [SEL_51] (rows=500/500 width=178) - Output:["_col0","_col1"] - Filter Operator [FIL_150] (rows=500/500 width=178) - predicate:key is not null - TableScan [TS_49] (rows=500/500 width=178) - default@src,y,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"] - <-Reducer 12 [SIMPLE_EDGE] llap - SHUFFLE [RS_55] - PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_159] (rows=82/52 width=86) - Conds:RS_52._col1=RS_53._col1(Inner),Output:["_col2"] - <-Map 11 [SIMPLE_EDGE] llap - SHUFFLE [RS_53] - PartitionCols:_col1 - Please refer to the previous Select Operator [SEL_14] - <-Reducer 21 [SIMPLE_EDGE] llap - SHUFFLE [RS_52] - PartitionCols:_col1 - Select Operator [SEL_45] (rows=1025/319 width=178) - Output:["_col1"] - Group By Operator [GBY_44] (rows=1025/319 width=178) - Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 - <-Union 20 [SIMPLE_EDGE] - <-Map 23 [CONTAINS] llap - Reduce Output Operator [RS_43] - PartitionCols:_col1, _col0 - Select Operator [SEL_39] (rows=500/500 width=178) - Output:["_col0","_col1"] - Filter Operator [FIL_148] (rows=500/500 width=178) - predicate:value is not null - TableScan [TS_37] (rows=500/500 width=178) - Output:["key","value"] - <-Reducer 19 [CONTAINS] llap - Reduce Output Operator [RS_43] - PartitionCols:_col1, _col0 - Select Operator [SEL_36] (rows=525/319 width=178) - Output:["_col0","_col1"] - Group By Operator [GBY_35] (rows=525/319 width=178) - Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 - <-Union 18 [SIMPLE_EDGE] - <-Map 17 [CONTAINS] llap - Reduce Output Operator [RS_34] - PartitionCols:_col1, _col0 - Select Operator [SEL_27] (rows=25/25 width=175) - Output:["_col0","_col1"] - Filter Operator [FIL_146] (rows=25/25 width=175) - predicate:value is not null - TableScan [TS_25] (rows=25/25 width=175) - Output:["key","value"] - <-Map 22 [CONTAINS] llap - Reduce Output Operator [RS_34] - PartitionCols:_col1, _col0 - Select Operator [SEL_30] (rows=500/500 width=178) - Output:["_col0","_col1"] - Filter Operator [FIL_147] (rows=500/500 width=178) - predicate:value is not null - TableScan [TS_28] (rows=500/500 width=178) - Output:["key","value"] - <-Reducer 5 [CONTAINS] llap - Reduce Output Operator [RS_62] - PartitionCols:_col0, _col1 - Select Operator [SEL_24] (rows=67/61 width=177) - Output:["_col0","_col1"] - Merge Join Operator [MERGEJOIN_158] (rows=67/61 width=177) - Conds:RS_21._col2=RS_22._col0(Inner),Output:["_col2","_col5"] - <-Map 16 [SIMPLE_EDGE] llap + Merge Join Operator [MERGEJOIN_154] (rows=66/61 width=177) + Conds:RS_21._col3=RS_22._col1(Inner),Output:["_col1","_col2"] + <-Reducer 15 [SIMPLE_EDGE] llap SHUFFLE [RS_22] - PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_17] - <-Reducer 4 [SIMPLE_EDGE] llap + PartitionCols:_col1 + Select Operator [SEL_17] (rows=525/319 width=178) + Output:["_col1"] + Group By Operator [GBY_16] (rows=525/319 width=178) + Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 + <-Union 14 [SIMPLE_EDGE] + <-Map 13 [CONTAINS] llap + Reduce Output Operator [RS_15] + PartitionCols:_col1, _col0 + Select Operator [SEL_8] (rows=25/25 width=175) + Output:["_col0","_col1"] + Filter Operator [FIL_138] (rows=25/25 width=175) + predicate:value is not null + TableScan [TS_6] (rows=25/25 width=175) + Output:["key","value"] + <-Map 16 [CONTAINS] llap + Reduce Output Operator [RS_15] + PartitionCols:_col1, _col0 + Select Operator [SEL_11] (rows=500/500 width=178) + Output:["_col0","_col1"] + Filter Operator [FIL_139] (rows=500/500 width=178) + predicate:value is not null + TableScan [TS_9] (rows=500/500 width=178) + Output:["key","value"] + <-Reducer 2 [SIMPLE_EDGE] llap SHUFFLE [RS_21] - PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_157] (rows=42/52 width=86) - Conds:RS_18._col1=RS_19._col1(Inner),Output:["_col2"] - <-Map 11 [SIMPLE_EDGE] llap - SHUFFLE [RS_19] - PartitionCols:_col1 - Please refer to the previous Select Operator [SEL_14] - <-Reducer 3 [SIMPLE_EDGE] llap + PartitionCols:_col3 + Merge Join Operator [MERGEJOIN_151] (rows=39/37 width=266) + Conds:RS_18._col0=RS_19._col0(Inner),Output:["_col1","_col2","_col3"] + <-Map 1 [SIMPLE_EDGE] llap SHUFFLE [RS_18] - PartitionCols:_col1 - Select Operator [SEL_11] (rows=525/319 width=178) - Output:["_col1"] - Group By Operator [GBY_10] (rows=525/319 width=178) - Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 - <-Union 2 [SIMPLE_EDGE] - <-Map 1 [CONTAINS] llap - Reduce Output Operator [RS_9] - PartitionCols:_col1, _col0 - Select Operator [SEL_2] (rows=25/25 width=175) - Output:["_col0","_col1"] - Filter Operator [FIL_142] (rows=25/25 width=175) - predicate:value is not null - TableScan [TS_0] (rows=25/25 width=175) - Output:["key","value"] - <-Map 10 [CONTAINS] llap - Reduce Output Operator [RS_9] - PartitionCols:_col1, _col0 - Select Operator [SEL_5] (rows=500/500 width=178) - Output:["_col0","_col1"] - Filter Operator [FIL_143] (rows=500/500 width=178) - predicate:value is not null - TableScan [TS_3] (rows=500/500 width=178) - Output:["key","value"] + PartitionCols:_col0 + Please refer to the previous Select Operator [SEL_2] + <-Map 12 [SIMPLE_EDGE] llap + SHUFFLE [RS_19] + PartitionCols:_col0 + Please refer to the previous Select Operator [SEL_5] + <-Reducer 9 [CONTAINS] llap + Reduce Output Operator [RS_62] + PartitionCols:_col0, _col1 + Select Operator [SEL_58] (rows=130/61 width=177) + Output:["_col0","_col1"] + Merge Join Operator [MERGEJOIN_155] (rows=130/61 width=177) + Conds:RS_55._col3=RS_56._col1(Inner),Output:["_col1","_col2"] + <-Reducer 21 [SIMPLE_EDGE] llap + SHUFFLE [RS_56] + PartitionCols:_col1 + Select Operator [SEL_51] (rows=1025/319 width=178) + Output:["_col1"] + Group By Operator [GBY_50] (rows=1025/319 width=178) + Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 + <-Union 20 [SIMPLE_EDGE] + <-Map 23 [CONTAINS] llap + Reduce Output Operator [RS_49] + PartitionCols:_col1, _col0 + Select Operator [SEL_45] (rows=500/500 width=178) + Output:["_col0","_col1"] + Filter Operator [FIL_144] (rows=500/500 width=178) + predicate:value is not null + TableScan [TS_43] (rows=500/500 width=178) + Output:["key","value"] + <-Reducer 19 [CONTAINS] llap + Reduce Output Operator [RS_49] + PartitionCols:_col1, _col0 + Select Operator [SEL_42] (rows=525/319 width=178) + Output:["_col0","_col1"] + Group By Operator [GBY_41] (rows=525/319 width=178) + Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 + <-Union 18 [SIMPLE_EDGE] + <-Map 17 [CONTAINS] llap + Reduce Output Operator [RS_40] + PartitionCols:_col1, _col0 + Select Operator [SEL_33] (rows=25/25 width=175) + Output:["_col0","_col1"] + Filter Operator [FIL_142] (rows=25/25 width=175) + predicate:value is not null + TableScan [TS_31] (rows=25/25 width=175) + Output:["key","value"] + <-Map 22 [CONTAINS] llap + Reduce Output Operator [RS_40] + PartitionCols:_col1, _col0 + Select Operator [SEL_36] (rows=500/500 width=178) + Output:["_col0","_col1"] + Filter Operator [FIL_143] (rows=500/500 width=178) + predicate:value is not null + TableScan [TS_34] (rows=500/500 width=178) + Output:["key","value"] + <-Reducer 8 [SIMPLE_EDGE] llap + SHUFFLE [RS_55] + PartitionCols:_col3 + Merge Join Operator [MERGEJOIN_152] (rows=39/37 width=266) + Conds:RS_52._col0=RS_53._col0(Inner),Output:["_col1","_col2","_col3"] + <-Map 1 [SIMPLE_EDGE] llap + SHUFFLE [RS_52] + PartitionCols:_col0 + Please refer to the previous Select Operator [SEL_2] + <-Map 12 [SIMPLE_EDGE] llap + SHUFFLE [RS_53] + PartitionCols:_col0 + Please refer to the previous Select Operator [SEL_5] PREHOOK: query: CREATE TABLE srcbucket_mapjoin(key int, value string) partitioned by (ds string) CLUSTERED BY (key) INTO 2 BUCKETS STORED AS TEXTFILE PREHOOK: type: CREATETABLE @@ -853,7 +843,7 @@ Stage-0 Output:["_col0"],aggregations:["count()"] <-Reducer 3 [CUSTOM_SIMPLE_EDGE] llap PARTITION_ONLY_SHUFFLE [RS_22] - Merge Join Operator [MERGEJOIN_38] (rows=1009/1646 width=8) + Merge Join Operator [MERGEJOIN_38] (rows=1029/1646 width=8) Conds:Union 2._col0=RS_19._col0(Inner) <-Map 7 [SIMPLE_EDGE] llap SHUFFLE [RS_19] @@ -942,7 +932,7 @@ Stage-0 Output:["_col0"],aggregations:["count()"] <-Reducer 4 [CUSTOM_SIMPLE_EDGE] llap PARTITION_ONLY_SHUFFLE [RS_28] - Merge Join Operator [MERGEJOIN_50] (rows=1368/3768 width=8) + Merge Join Operator [MERGEJOIN_50] (rows=1396/3768 width=8) Conds:Union 3._col0=RS_25._col0(Inner) <-Map 9 [SIMPLE_EDGE] llap SHUFFLE [RS_25] @@ -1106,24 +1096,21 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Map 1 <- Union 2 (CONTAINS) -Map 16 <- Union 17 (CONTAINS) -Map 18 <- Union 17 (CONTAINS) -Map 19 <- Union 17 (CONTAINS) -Map 22 <- Union 23 (CONTAINS) -Map 24 <- Union 23 (CONTAINS) -Map 25 <- Union 23 (CONTAINS) -Map 26 <- Union 23 (CONTAINS) -Map 9 <- Union 2 (CONTAINS) -Reducer 11 <- Map 10 (SIMPLE_EDGE), Map 21 (SIMPLE_EDGE) -Reducer 12 <- Reducer 11 (SIMPLE_EDGE), Union 23 (SIMPLE_EDGE), Union 5 (CONTAINS) -Reducer 14 <- Map 13 (SIMPLE_EDGE), Union 17 (SIMPLE_EDGE) -Reducer 15 <- Map 20 (SIMPLE_EDGE), Reducer 14 (SIMPLE_EDGE), Union 5 (CONTAINS) -Reducer 3 <- Map 10 (SIMPLE_EDGE), Union 2 (SIMPLE_EDGE) -Reducer 4 <- Map 13 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE), Union 5 (CONTAINS) -Reducer 6 <- Union 5 (CUSTOM_SIMPLE_EDGE) -Reducer 7 <- Union 5 (CUSTOM_SIMPLE_EDGE) -Reducer 8 <- Union 5 (CUSTOM_SIMPLE_EDGE) +Map 10 <- Union 11 (CONTAINS) +Map 12 <- Union 11 (CONTAINS) +Map 14 <- Union 15 (CONTAINS) +Map 16 <- Union 15 (CONTAINS) +Map 17 <- Union 15 (CONTAINS) +Map 19 <- Union 20 (CONTAINS) +Map 21 <- Union 20 (CONTAINS) +Map 22 <- Union 20 (CONTAINS) +Map 23 <- Union 20 (CONTAINS) +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 7 (SIMPLE_EDGE) +Reducer 3 <- Reducer 2 (SIMPLE_EDGE), Union 11 (SIMPLE_EDGE), Union 4 (CONTAINS) +Reducer 5 <- Map 1 (SIMPLE_EDGE), Map 13 (SIMPLE_EDGE) +Reducer 6 <- Reducer 5 (SIMPLE_EDGE), Union 15 (SIMPLE_EDGE), Union 4 (CONTAINS) +Reducer 8 <- Map 18 (SIMPLE_EDGE), Map 7 (SIMPLE_EDGE) +Reducer 9 <- Reducer 8 (SIMPLE_EDGE), Union 20 (SIMPLE_EDGE), Union 4 (CONTAINS) Stage-5 Stats Work{} @@ -1133,243 +1120,193 @@ Stage-5 Stage-4 Dependency Collection{} Stage-3 - Reducer 6 llap - File Output Operator [FS_5] - Group By Operator [GBY_3] (rows=1/1 width=880) - Output:["_col0","_col1"],aggregations:["compute_stats(VALUE._col0, 'hll')","compute_stats(VALUE._col2, 'hll')"] - <-Union 5 [CUSTOM_SIMPLE_EDGE] - <-Reducer 12 [CONTAINS] llap - File Output Operator [FS_75] - table:{"name:":"default.a"} - Select Operator [SEL_72] (rows=192/820 width=175) - Output:["_col0","_col1"] - Merge Join Operator [MERGEJOIN_124] (rows=192/820 width=175) - Conds:RS_69._col1=Union 23._col0(Inner),Output:["_col0","_col3"] - <-Reducer 11 [SIMPLE_EDGE] llap - SHUFFLE [RS_69] - PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_123] (rows=39/115 width=264) - Conds:RS_66._col0=RS_67._col0(Inner),Output:["_col0","_col1","_col3"] - <-Map 10 [SIMPLE_EDGE] llap - SHUFFLE [RS_66] - PartitionCols:_col0 - Select Operator [SEL_10] (rows=25/25 width=175) - Output:["_col0","_col1"] - Filter Operator [FIL_106] (rows=25/25 width=175) - predicate:(key is not null and value is not null) - TableScan [TS_8] (rows=25/25 width=175) - default@src1,x,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"] - <-Map 21 [SIMPLE_EDGE] llap - SHUFFLE [RS_67] - PartitionCols:_col0 - Select Operator [SEL_51] (rows=25/25 width=175) - Output:["_col0","_col1"] - Filter Operator [FIL_114] (rows=25/25 width=175) - predicate:key is not null - TableScan [TS_49] (rows=25/25 width=175) - default@src1,y,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"] - <-Union 23 [SIMPLE_EDGE] - <-Map 22 [CONTAINS] llap - Reduce Output Operator [RS_70] - PartitionCols:_col0 - Select Operator [SEL_54] (rows=25/25 width=89) - Output:["_col0"] - Filter Operator [FIL_115] (rows=25/25 width=89) - predicate:value is not null - TableScan [TS_52] (rows=25/25 width=89) - Output:["value"] - <-Map 24 [CONTAINS] llap - Reduce Output Operator [RS_70] - PartitionCols:_col0 - Select Operator [SEL_57] (rows=500/500 width=91) - Output:["_col0"] - Filter Operator [FIL_116] (rows=500/500 width=91) - predicate:value is not null - TableScan [TS_55] (rows=500/500 width=91) - Output:["value"] - <-Map 25 [CONTAINS] llap - Reduce Output Operator [RS_70] - PartitionCols:_col0 - Select Operator [SEL_61] (rows=500/500 width=91) - Output:["_col0"] - Filter Operator [FIL_117] (rows=500/500 width=91) - predicate:value is not null - TableScan [TS_59] (rows=500/500 width=91) - Output:["value"] - <-Map 26 [CONTAINS] llap - Reduce Output Operator [RS_70] - PartitionCols:_col0 - Select Operator [SEL_64] (rows=500/500 width=91) - Output:["_col0"] - Filter Operator [FIL_118] (rows=500/500 width=91) - predicate:value is not null - TableScan [TS_62] (rows=500/500 width=91) - Output:["value"] - Reduce Output Operator [RS_2] - Select Operator [SEL_1] (rows=2941/6411 width=178) - Output:["key","value"] - Please refer to the previous Select Operator [SEL_72] - File Output Operator [FS_77] - table:{"name:":"default.b"} - Please refer to the previous Select Operator [SEL_72] - Reduce Output Operator [RS_2] - Select Operator [SEL_1] (rows=2941/6411 width=178) - Output:["key","value"] - Please refer to the previous Select Operator [SEL_72] - File Output Operator [FS_79] - table:{"name:":"default.c"} - Please refer to the previous Select Operator [SEL_72] - Reduce Output Operator [RS_2] - Select Operator [SEL_1] (rows=2941/6411 width=178) - Output:["key","value"] - Please refer to the previous Select Operator [SEL_72] - <-Reducer 15 [CONTAINS] llap - File Output Operator [FS_75] - table:{"name:":"default.a"} - Select Operator [SEL_44] (rows=2682/5421 width=178) - Output:["_col0","_col1"] - Merge Join Operator [MERGEJOIN_122] (rows=2682/5421 width=178) - Conds:RS_41._col1=RS_42._col0(Inner),Output:["_col1","_col4"] - <-Map 20 [SIMPLE_EDGE] llap - SHUFFLE [RS_42] + Union 4 + <-Reducer 3 [CONTAINS] llap + File Output Operator [FS_75] + table:{"name:":"default.a"} + Select Operator [SEL_20] (rows=66/170 width=177) + Output:["_col0","_col1"] + Merge Join Operator [MERGEJOIN_119] (rows=66/170 width=177) + Conds:RS_17._col3=Union 11._col0(Inner),Output:["_col1","_col2"] + <-Reducer 2 [SIMPLE_EDGE] llap + SHUFFLE [RS_17] + PartitionCols:_col3 + Merge Join Operator [MERGEJOIN_116] (rows=39/37 width=266) + Conds:RS_14._col0=RS_15._col0(Inner),Output:["_col1","_col2","_col3"] + <-Map 1 [SIMPLE_EDGE] llap + SHUFFLE [RS_14] PartitionCols:_col0 - Select Operator [SEL_37] (rows=500/500 width=178) + Select Operator [SEL_2] (rows=500/500 width=178) Output:["_col0","_col1"] - Filter Operator [FIL_112] (rows=500/500 width=178) + Filter Operator [FIL_101] (rows=500/500 width=178) predicate:key is not null - TableScan [TS_35] (rows=500/500 width=178) + TableScan [TS_0] (rows=500/500 width=178) default@src,y,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"] - <-Reducer 14 [SIMPLE_EDGE] llap - SHUFFLE [RS_41] - PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_121] (rows=1658/2097 width=87) - Conds:Union 17._col0=RS_39._col1(Inner),Output:["_col1"] - <-Map 13 [SIMPLE_EDGE] llap - SHUFFLE [RS_39] - PartitionCols:_col1 - Select Operator [SEL_34] (rows=500/500 width=178) - Output:["_col0","_col1"] - Filter Operator [FIL_111] (rows=500/500 width=178) - predicate:(key is not null and value is not null) - TableScan [TS_11] (rows=500/500 width=178) - default@src,y,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"] - <-Union 17 [SIMPLE_EDGE] - <-Map 16 [CONTAINS] llap - Reduce Output Operator [RS_38] - PartitionCols:_col0 - Select Operator [SEL_23] (rows=25/25 width=89) - Output:["_col0"] - Filter Operator [FIL_108] (rows=25/25 width=89) - predicate:value is not null - TableScan [TS_21] (rows=25/25 width=89) - Output:["value"] - <-Map 18 [CONTAINS] llap - Reduce Output Operator [RS_38] - PartitionCols:_col0 - Select Operator [SEL_26] (rows=500/500 width=91) - Output:["_col0"] - Filter Operator [FIL_109] (rows=500/500 width=91) - predicate:value is not null - TableScan [TS_24] (rows=500/500 width=91) - Output:["value"] - <-Map 19 [CONTAINS] llap - Reduce Output Operator [RS_38] - PartitionCols:_col0 - Select Operator [SEL_30] (rows=500/500 width=91) - Output:["_col0"] - Filter Operator [FIL_110] (rows=500/500 width=91) - predicate:value is not null - TableScan [TS_28] (rows=500/500 width=91) - Output:["value"] - Reduce Output Operator [RS_2] - Select Operator [SEL_1] (rows=2941/6411 width=178) - Output:["key","value"] - Please refer to the previous Select Operator [SEL_44] - File Output Operator [FS_77] - table:{"name:":"default.b"} - Please refer to the previous Select Operator [SEL_44] - Reduce Output Operator [RS_2] - Select Operator [SEL_1] (rows=2941/6411 width=178) - Output:["key","value"] - Please refer to the previous Select Operator [SEL_44] - File Output Operator [FS_79] - table:{"name:":"default.c"} - Please refer to the previous Select Operator [SEL_44] - Reduce Output Operator [RS_2] - Select Operator [SEL_1] (rows=2941/6411 width=178) - Output:["key","value"] - Please refer to the previous Select Operator [SEL_44] - <-Reducer 4 [CONTAINS] llap - File Output Operator [FS_75] - table:{"name:":"default.a"} - Select Operator [SEL_20] (rows=67/170 width=177) - Output:["_col0","_col1"] - Merge Join Operator [MERGEJOIN_120] (rows=67/170 width=177) - Conds:RS_17._col1=RS_18._col0(Inner),Output:["_col1","_col4"] + <-Map 7 [SIMPLE_EDGE] llap + SHUFFLE [RS_15] + PartitionCols:_col0 + Select Operator [SEL_5] (rows=25/25 width=175) + Output:["_col0","_col1"] + Filter Operator [FIL_102] (rows=25/25 width=175) + predicate:(key is not null and value is not null) + TableScan [TS_3] (rows=25/25 width=175) + default@src1,x,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"] + <-Union 11 [SIMPLE_EDGE] + <-Map 10 [CONTAINS] llap + Reduce Output Operator [RS_18] + PartitionCols:_col0 + Select Operator [SEL_8] (rows=25/25 width=89) + Output:["_col0"] + Filter Operator [FIL_103] (rows=25/25 width=89) + predicate:value is not null + TableScan [TS_6] (rows=25/25 width=89) + Output:["value"] + <-Map 12 [CONTAINS] llap + Reduce Output Operator [RS_18] + PartitionCols:_col0 + Select Operator [SEL_11] (rows=500/500 width=91) + Output:["_col0"] + Filter Operator [FIL_104] (rows=500/500 width=91) + predicate:value is not null + TableScan [TS_9] (rows=500/500 width=91) + Output:["value"] + File Output Operator [FS_77] + table:{"name:":"default.b"} + Please refer to the previous Select Operator [SEL_20] + File Output Operator [FS_79] + table:{"name:":"default.c"} + Please refer to the previous Select Operator [SEL_20] + <-Reducer 6 [CONTAINS] llap + File Output Operator [FS_75] + table:{"name:":"default.a"} + Select Operator [SEL_44] (rows=2640/5421 width=178) + Output:["_col0","_col1"] + Merge Join Operator [MERGEJOIN_120] (rows=2640/5421 width=178) + Conds:RS_41._col1=Union 15._col0(Inner),Output:["_col0","_col3"] + <-Reducer 5 [SIMPLE_EDGE] llap + SHUFFLE [RS_41] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_117] (rows=791/1028 width=269) + Conds:RS_38._col0=RS_39._col0(Inner),Output:["_col0","_col1","_col3"] + <-Map 1 [SIMPLE_EDGE] llap + SHUFFLE [RS_38] + PartitionCols:_col0 + Select Operator [SEL_23] (rows=500/500 width=178) + Output:["_col0","_col1"] + Filter Operator [FIL_105] (rows=500/500 width=178) + predicate:(key is not null and value is not null) + Please refer to the previous TableScan [TS_0] <-Map 13 [SIMPLE_EDGE] llap - SHUFFLE [RS_18] + SHUFFLE [RS_39] + PartitionCols:_col0 + Select Operator [SEL_26] (rows=500/500 width=178) + Output:["_col0","_col1"] + Filter Operator [FIL_106] (rows=500/500 width=178) + predicate:key is not null + TableScan [TS_24] (rows=500/500 width=178) + default@src,y,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"] + <-Union 15 [SIMPLE_EDGE] + <-Map 14 [CONTAINS] llap + Reduce Output Operator [RS_42] + PartitionCols:_col0 + Select Operator [SEL_29] (rows=25/25 width=89) + Output:["_col0"] + Filter Operator [FIL_107] (rows=25/25 width=89) + predicate:value is not null + TableScan [TS_27] (rows=25/25 width=89) + Output:["value"] + <-Map 16 [CONTAINS] llap + Reduce Output Operator [RS_42] + PartitionCols:_col0 + Select Operator [SEL_32] (rows=500/500 width=91) + Output:["_col0"] + Filter Operator [FIL_108] (rows=500/500 width=91) + predicate:value is not null + TableScan [TS_30] (rows=500/500 width=91) + Output:["value"] + <-Map 17 [CONTAINS] llap + Reduce Output Operator [RS_42] + PartitionCols:_col0 + Select Operator [SEL_36] (rows=500/500 width=91) + Output:["_col0"] + Filter Operator [FIL_109] (rows=500/500 width=91) + predicate:value is not null + TableScan [TS_34] (rows=500/500 width=91) + Output:["value"] + File Output Operator [FS_77] + table:{"name:":"default.b"} + Please refer to the previous Select Operator [SEL_44] + File Output Operator [FS_79] + table:{"name:":"default.c"} + Please refer to the previous Select Operator [SEL_44] + <-Reducer 9 [CONTAINS] llap + File Output Operator [FS_75] + table:{"name:":"default.a"} + Select Operator [SEL_72] (rows=193/820 width=175) + Output:["_col0","_col1"] + Merge Join Operator [MERGEJOIN_121] (rows=193/820 width=175) + Conds:RS_69._col1=Union 20._col0(Inner),Output:["_col0","_col3"] + <-Reducer 8 [SIMPLE_EDGE] llap + SHUFFLE [RS_69] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_118] (rows=39/115 width=264) + Conds:RS_66._col0=RS_67._col0(Inner),Output:["_col0","_col1","_col3"] + <-Map 7 [SIMPLE_EDGE] llap + SHUFFLE [RS_66] + PartitionCols:_col0 + Please refer to the previous Select Operator [SEL_5] + <-Map 18 [SIMPLE_EDGE] llap + SHUFFLE [RS_67] PartitionCols:_col0 Select Operator [SEL_13] (rows=500/500 width=178) Output:["_col0","_col1"] - Filter Operator [FIL_107] (rows=500/500 width=178) + Filter Operator [FIL_111] (rows=25/25 width=175) predicate:key is not null - Please refer to the previous TableScan [TS_11] - <-Reducer 3 [SIMPLE_EDGE] llap - SHUFFLE [RS_17] - PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_119] (rows=42/108 width=86) - Conds:Union 2._col0=RS_15._col1(Inner),Output:["_col1"] - <-Map 10 [SIMPLE_EDGE] llap - SHUFFLE [RS_15] - PartitionCols:_col1 - Please refer to the previous Select Operator [SEL_10] - <-Union 2 [SIMPLE_EDGE] - <-Map 1 [CONTAINS] llap - Reduce Output Operator [RS_14] - PartitionCols:_col0 - Select Operator [SEL_2] (rows=25/25 width=89) - Output:["_col0"] - Filter Operator [FIL_104] (rows=25/25 width=89) - predicate:value is not null - TableScan [TS_0] (rows=25/25 width=89) - Output:["value"] - <-Map 9 [CONTAINS] llap - Reduce Output Operator [RS_14] - PartitionCols:_col0 - Select Operator [SEL_5] (rows=500/500 width=91) - Output:["_col0"] - Filter Operator [FIL_105] (rows=500/500 width=91) - predicate:value is not null - TableScan [TS_3] (rows=500/500 width=91) - Output:["value"] - Reduce Output Operator [RS_2] - Select Operator [SEL_1] (rows=2941/6411 width=178) - Output:["key","value"] - Please refer to the previous Select Operator [SEL_20] - File Output Operator [FS_77] - table:{"name:":"default.b"} - Please refer to the previous Select Operator [SEL_20] - Reduce Output Operator [RS_2] - Select Operator [SEL_1] (rows=2941/6411 width=178) - Output:["key","value"] - Please refer to the previous Select Operator [SEL_20] - File Output Operator [FS_79] - table:{"name:":"default.c"} - Please refer to the previous Select Operator [SEL_20] - Reduce Output Operator [RS_2] - Select Operator [SEL_1] (rows=2941/6411 width=178) - Output:["key","value"] - Please refer to the previous Select Operator [SEL_20] - Reducer 7 llap - File Output Operator [FS_5] - Group By Operator [GBY_3] (rows=1/1 width=880) - Output:["_col0","_col1"],aggregations:["compute_stats(VALUE._col0, 'hll')","compute_stats(VALUE._col2, 'hll')"] - <- Please refer to the previous Union 5 [CUSTOM_SIMPLE_EDGE] - Reducer 8 llap - File Output Operator [FS_5] - Group By Operator [GBY_3] (rows=1/1 width=880) - Output:["_col0","_col1"],aggregations:["compute_stats(VALUE._col0, 'hll')","compute_stats(VALUE._col2, 'hll')"] - <- Please refer to the previous Union 5 [CUSTOM_SIMPLE_EDGE] + TableScan [TS_49] (rows=25/25 width=175) + default@src1,y,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"] + <-Union 20 [SIMPLE_EDGE] + <-Map 19 [CONTAINS] llap + Reduce Output Operator [RS_70] + PartitionCols:_col0 + Select Operator [SEL_54] (rows=25/25 width=89) + Output:["_col0"] + Filter Operator [FIL_112] (rows=25/25 width=89) + predicate:value is not null + TableScan [TS_52] (rows=25/25 width=89) + Output:["value"] + <-Map 21 [CONTAINS] llap + Reduce Output Operator [RS_70] + PartitionCols:_col0 + Select Operator [SEL_57] (rows=500/500 width=91) + Output:["_col0"] + Filter Operator [FIL_113] (rows=500/500 width=91) + predicate:value is not null + TableScan [TS_55] (rows=500/500 width=91) + Output:["value"] + <-Map 22 [CONTAINS] llap + Reduce Output Operator [RS_70] + PartitionCols:_col0 + Select Operator [SEL_61] (rows=500/500 width=91) + Output:["_col0"] + Filter Operator [FIL_114] (rows=500/500 width=91) + predicate:value is not null + TableScan [TS_59] (rows=500/500 width=91) + Output:["value"] + <-Map 23 [CONTAINS] llap + Reduce Output Operator [RS_70] + PartitionCols:_col0 + Select Operator [SEL_64] (rows=500/500 width=91) + Output:["_col0"] + Filter Operator [FIL_115] (rows=500/500 width=91) + predicate:value is not null + TableScan [TS_62] (rows=500/500 width=91) + Output:["value"] + File Output Operator [FS_77] + table:{"name:":"default.b"} + Please refer to the previous Select Operator [SEL_72] + File Output Operator [FS_79] + table:{"name:":"default.c"} + Please refer to the previous Select Operator [SEL_72] Stage-6 Stats Work{} Stage-1 @@ -1458,32 +1395,29 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Map 1 <- Union 2 (CONTAINS) -Map 13 <- Union 2 (CONTAINS) -Map 20 <- Union 21 (CONTAINS) -Map 25 <- Union 21 (CONTAINS) -Map 26 <- Union 23 (CONTAINS) -Map 29 <- Union 30 (CONTAINS) -Map 36 <- Union 30 (CONTAINS) -Map 37 <- Union 32 (CONTAINS) -Map 38 <- Union 34 (CONTAINS) -Reducer 10 <- Reducer 9 (CUSTOM_SIMPLE_EDGE) -Reducer 11 <- Reducer 9 (CUSTOM_SIMPLE_EDGE) -Reducer 12 <- Reducer 9 (CUSTOM_SIMPLE_EDGE) -Reducer 15 <- Map 14 (SIMPLE_EDGE), Map 28 (SIMPLE_EDGE) -Reducer 16 <- Reducer 15 (SIMPLE_EDGE), Reducer 35 (SIMPLE_EDGE), Union 8 (CONTAINS) -Reducer 18 <- Map 17 (SIMPLE_EDGE), Reducer 24 (SIMPLE_EDGE) -Reducer 19 <- Map 27 (SIMPLE_EDGE), Reducer 18 (SIMPLE_EDGE), Union 6 (CONTAINS) -Reducer 22 <- Union 21 (SIMPLE_EDGE), Union 23 (CONTAINS) -Reducer 24 <- Union 23 (SIMPLE_EDGE) -Reducer 3 <- Union 2 (SIMPLE_EDGE) -Reducer 31 <- Union 30 (SIMPLE_EDGE), Union 32 (CONTAINS) -Reducer 33 <- Union 32 (SIMPLE_EDGE), Union 34 (CONTAINS) -Reducer 35 <- Union 34 (SIMPLE_EDGE) -Reducer 4 <- Map 14 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) -Reducer 5 <- Map 17 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE), Union 6 (CONTAINS) -Reducer 7 <- Union 6 (SIMPLE_EDGE), Union 8 (CONTAINS) -Reducer 9 <- Union 8 (SIMPLE_EDGE) +Map 13 <- Union 14 (CONTAINS) +Map 16 <- Union 14 (CONTAINS) +Map 18 <- Union 19 (CONTAINS) +Map 23 <- Union 19 (CONTAINS) +Map 24 <- Union 21 (CONTAINS) +Map 26 <- Union 27 (CONTAINS) +Map 33 <- Union 27 (CONTAINS) +Map 34 <- Union 29 (CONTAINS) +Map 35 <- Union 31 (CONTAINS) +Reducer 11 <- Map 10 (SIMPLE_EDGE), Map 25 (SIMPLE_EDGE) +Reducer 12 <- Reducer 11 (SIMPLE_EDGE), Reducer 32 (SIMPLE_EDGE), Union 6 (CONTAINS) +Reducer 15 <- Union 14 (SIMPLE_EDGE) +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 10 (SIMPLE_EDGE) +Reducer 20 <- Union 19 (SIMPLE_EDGE), Union 21 (CONTAINS) +Reducer 22 <- Union 21 (SIMPLE_EDGE) +Reducer 28 <- Union 27 (SIMPLE_EDGE), Union 29 (CONTAINS) +Reducer 3 <- Reducer 15 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE), Union 4 (CONTAINS) +Reducer 30 <- Union 29 (SIMPLE_EDGE), Union 31 (CONTAINS) +Reducer 32 <- Union 31 (SIMPLE_EDGE) +Reducer 5 <- Union 4 (SIMPLE_EDGE), Union 6 (CONTAINS) +Reducer 7 <- Union 6 (SIMPLE_EDGE) +Reducer 8 <- Map 1 (SIMPLE_EDGE), Map 17 (SIMPLE_EDGE) +Reducer 9 <- Reducer 22 (SIMPLE_EDGE), Reducer 8 (SIMPLE_EDGE), Union 4 (CONTAINS) Stage-5 Stats Work{} @@ -1493,138 +1427,80 @@ Stage-5 Stage-4 Dependency Collection{} Stage-3 - Reducer 10 llap - File Output Operator [FS_5] - Group By Operator [GBY_3] (rows=1/1 width=880) - Output:["_col0","_col1"],aggregations:["compute_stats(VALUE._col0, 'hll')","compute_stats(VALUE._col2, 'hll')"] - <-Reducer 9 [CUSTOM_SIMPLE_EDGE] llap - PARTITION_ONLY_SHUFFLE [RS_2] - Select Operator [SEL_1] (rows=2941/319 width=178) - Output:["key","value"] - Group By Operator [GBY_112] (rows=2941/319 width=178) - Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 - <-Union 8 [SIMPLE_EDGE] - <-Reducer 16 [CONTAINS] llap - Reduce Output Operator [RS_111] - PartitionCols:_col0, _col1 - Select Operator [SEL_107] (rows=192/304 width=175) - Output:["_col0","_col1"] - Merge Join Operator [MERGEJOIN_164] (rows=192/304 width=175) - Conds:RS_104._col1=RS_105._col1(Inner),Output:["_col0","_col3"] - <-Reducer 15 [SIMPLE_EDGE] llap - SHUFFLE [RS_104] - PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_163] (rows=39/115 width=264) - Conds:RS_101._col0=RS_102._col0(Inner),Output:["_col0","_col1","_col3"] - <-Map 14 [SIMPLE_EDGE] llap - SHUFFLE [RS_101] - PartitionCols:_col0 - Select Operator [SEL_14] (rows=25/25 width=175) - Output:["_col0","_col1"] - Filter Operator [FIL_146] (rows=25/25 width=175) - predicate:(key is not null and value is not null) - TableScan [TS_12] (rows=25/25 width=175) - default@src1,x,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"] - <-Map 28 [SIMPLE_EDGE] llap - SHUFFLE [RS_102] - PartitionCols:_col0 - Select Operator [SEL_70] (rows=25/25 width=175) - Output:["_col0","_col1"] - Filter Operator [FIL_154] (rows=25/25 width=175) - predicate:key is not null - TableScan [TS_68] (rows=25/25 width=175) - default@src1,y,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"] - <-Reducer 35 [SIMPLE_EDGE] llap - SHUFFLE [RS_105] - PartitionCols:_col1 - Select Operator [SEL_100] (rows=1525/319 width=178) - Output:["_col1"] - Group By Operator [GBY_99] (rows=1525/319 width=178) - Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 - <-Union 34 [SIMPLE_EDGE] - <-Map 38 [CONTAINS] llap - Reduce Output Operator [RS_98] - PartitionCols:_col1, _col0 - Select Operator [SEL_94] (rows=500/500 width=178) - Output:["_col0","_col1"] - Filter Operator [FIL_158] (rows=500/500 width=178) - predicate:value is not null - TableScan [TS_92] (rows=500/500 width=178) - Output:["key","value"] - <-Reducer 33 [CONTAINS] llap - Reduce Output Operator [RS_98] - PartitionCols:_col1, _col0 - Select Operator [SEL_91] (rows=1025/319 width=178) - Output:["_col0","_col1"] - Group By Operator [GBY_90] (rows=1025/319 width=178) - Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 - <-Union 32 [SIMPLE_EDGE] - <-Map 37 [CONTAINS] llap - Reduce Output Operator [RS_89] - PartitionCols:_col1, _col0 - Select Operator [SEL_85] (rows=500/500 width=178) - Output:["_col0","_col1"] - Filter Operator [FIL_157] (rows=500/500 width=178) - predicate:value is not null - TableScan [TS_83] (rows=500/500 width=178) - Output:["key","value"] - <-Reducer 31 [CONTAINS] llap - Reduce Output Operator [RS_89] - PartitionCols:_col1, _col0 - Select Operator [SEL_82] (rows=525/319 width=178) - Output:["_col0","_col1"] - Group By Operator [GBY_81] (rows=525/319 width=178) - Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 - <-Union 30 [SIMPLE_EDGE] - <-Map 29 [CONTAINS] llap - Reduce Output Operator [RS_80] - PartitionCols:_col1, _col0 - Select Operator [SEL_73] (rows=25/25 width=175) - Output:["_col0","_col1"] - Filter Operator [FIL_155] (rows=25/25 width=175) - predicate:value is not null - TableScan [TS_71] (rows=25/25 width=175) - Output:["key","value"] - <-Map 36 [CONTAINS] llap - Reduce Output Operator [RS_80] - PartitionCols:_col1, _col0 - Select Operator [SEL_76] (rows=500/500 width=178) - Output:["_col0","_col1"] - Filter Operator [FIL_156] (rows=500/500 width=178) - predicate:value is not null - TableScan [TS_74] (rows=500/500 width=178) - Output:["key","value"] - <-Reducer 7 [CONTAINS] llap - Reduce Output Operator [RS_111] - PartitionCols:_col0, _col1 - Group By Operator [GBY_63] (rows=2749/309 width=178) - Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 - <-Union 6 [SIMPLE_EDGE] - <-Reducer 19 [CONTAINS] llap - Reduce Output Operator [RS_62] - PartitionCols:_col0, _col1 - Select Operator [SEL_58] (rows=2682/1056 width=178) - Output:["_col0","_col1"] - Merge Join Operator [MERGEJOIN_162] (rows=2682/1056 width=178) - Conds:RS_55._col2=RS_56._col0(Inner),Output:["_col2","_col5"] - <-Map 27 [SIMPLE_EDGE] llap - SHUFFLE [RS_56] - PartitionCols:_col0 - Select Operator [SEL_51] (rows=500/500 width=178) - Output:["_col0","_col1"] - Filter Operator [FIL_152] (rows=500/500 width=178) - predicate:key is not null - TableScan [TS_49] (rows=500/500 width=178) - default@src,y,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"] - <-Reducer 18 [SIMPLE_EDGE] llap - SHUFFLE [RS_55] - PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_161] (rows=1658/512 width=87) - Conds:RS_52._col1=RS_53._col1(Inner),Output:["_col2"] - <-Map 17 [SIMPLE_EDGE] llap - SHUFFLE [RS_53] - PartitionCols:_col1 - Select Operator [SEL_48] (rows=500/500 width=178) + Reducer 7 llap + File Output Operator [FS_115] + table:{"name:":"default.a"} + Group By Operator [GBY_112] (rows=2899/319 width=178) + Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 + <-Union 6 [SIMPLE_EDGE] + <-Reducer 12 [CONTAINS] llap + Reduce Output Operator [RS_111] + PartitionCols:_col0, _col1 + Select Operator [SEL_107] (rows=193/304 width=175) + Output:["_col0","_col1"] + Merge Join Operator [MERGEJOIN_161] (rows=193/304 width=175) + Conds:RS_104._col1=RS_105._col1(Inner),Output:["_col0","_col3"] + <-Reducer 11 [SIMPLE_EDGE] llap + SHUFFLE [RS_104] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_158] (rows=39/115 width=264) + Conds:RS_101._col0=RS_102._col0(Inner),Output:["_col0","_col1","_col3"] + <-Map 10 [SIMPLE_EDGE] llap + SHUFFLE [RS_101] + PartitionCols:_col0 + Select Operator [SEL_5] (rows=25/25 width=175) + Output:["_col0","_col1"] + Filter Operator [FIL_142] (rows=25/25 width=175) + predicate:(key is not null and value is not null) + TableScan [TS_3] (rows=25/25 width=175) + default@src1,x,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"] + <-Map 25 [SIMPLE_EDGE] llap + SHUFFLE [RS_102] + PartitionCols:_col0 + Select Operator [SEL_70] (rows=25/25 width=175) + Output:["_col0","_col1"] + Filter Operator [FIL_151] (rows=25/25 width=175) + predicate:key is not null + TableScan [TS_68] (rows=25/25 width=175) + default@src1,y,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"] + <-Reducer 32 [SIMPLE_EDGE] llap + SHUFFLE [RS_105] + PartitionCols:_col1 + Select Operator [SEL_100] (rows=1525/319 width=178) + Output:["_col1"] + Group By Operator [GBY_99] (rows=1525/319 width=178) + Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 + <-Union 31 [SIMPLE_EDGE] + <-Map 35 [CONTAINS] llap + Reduce Output Operator [RS_98] + PartitionCols:_col1, _col0 + Select Operator [SEL_94] (rows=500/500 width=178) + Output:["_col0","_col1"] + Filter Operator [FIL_155] (rows=500/500 width=178) + predicate:value is not null + TableScan [TS_92] (rows=500/500 width=178) + Output:["key","value"] + <-Reducer 30 [CONTAINS] llap + Reduce Output Operator [RS_98] + PartitionCols:_col1, _col0 + Select Operator [SEL_91] (rows=1025/319 width=178) + Output:["_col0","_col1"] + Group By Operator [GBY_90] (rows=1025/319 width=178) + Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 + <-Union 29 [SIMPLE_EDGE] + <-Map 34 [CONTAINS] llap + Reduce Output Operator [RS_89] + PartitionCols:_col1, _col0 + Select Operator [SEL_85] (rows=500/500 width=178) + Output:["_col0","_col1"] + Filter Operator [FIL_154] (rows=500/500 width=178) + predicate:value is not null + TableScan [TS_83] (rows=500/500 width=178) + Output:["key","value"] + <-Reducer 28 [CONTAINS] llap + Reduce Output Operator [RS_89] + PartitionCols:_col1, _col0 + Select Operator [SEL_82] (rows=525/319 width=178) Output:["_col0","_col1"] Filter Operator [FIL_151] (rows=500/500 width=178) predicate:(key is not null and value is not null) @@ -1643,7 +1519,7 @@ Stage-5 PartitionCols:_col1, _col0 Select Operator [SEL_39] (rows=500/500 width=178) Output:["_col0","_col1"] - Filter Operator [FIL_150] (rows=500/500 width=178) + Filter Operator [FIL_152] (rows=25/25 width=175) predicate:value is not null TableScan [TS_37] (rows=500/500 width=178) Output:["key","value"] @@ -1652,95 +1528,145 @@ Stage-5 PartitionCols:_col1, _col0 Select Operator [SEL_36] (rows=525/319 width=178) Output:["_col0","_col1"] - Group By Operator [GBY_35] (rows=525/319 width=178) - Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 - <-Union 21 [SIMPLE_EDGE] - <-Map 20 [CONTAINS] llap - Reduce Output Operator [RS_34] - PartitionCols:_col1, _col0 - Select Operator [SEL_27] (rows=25/25 width=175) - Output:["_col0","_col1"] - Filter Operator [FIL_148] (rows=25/25 width=175) - predicate:value is not null - TableScan [TS_25] (rows=25/25 width=175) - Output:["key","value"] - <-Map 25 [CONTAINS] llap - Reduce Output Operator [RS_34] - PartitionCols:_col1, _col0 - Select Operator [SEL_30] (rows=500/500 width=178) - Output:["_col0","_col1"] - Filter Operator [FIL_149] (rows=500/500 width=178) - predicate:value is not null - TableScan [TS_28] (rows=500/500 width=178) - Output:["key","value"] - <-Reducer 5 [CONTAINS] llap - Reduce Output Operator [RS_62] - PartitionCols:_col0, _col1 - Select Operator [SEL_24] (rows=67/61 width=177) - Output:["_col0","_col1"] - Merge Join Operator [MERGEJOIN_160] (rows=67/61 width=177) - Conds:RS_21._col2=RS_22._col0(Inner),Output:["_col2","_col5"] - <-Map 17 [SIMPLE_EDGE] llap - SHUFFLE [RS_22] - PartitionCols:_col0 - Select Operator [SEL_17] (rows=500/500 width=178) - Output:["_col0","_col1"] - Filter Operator [FIL_147] (rows=500/500 width=178) - predicate:key is not null - Please refer to the previous TableScan [TS_15] - <-Reducer 4 [SIMPLE_EDGE] llap - SHUFFLE [RS_21] - PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_159] (rows=42/52 width=86) - Conds:RS_18._col1=RS_19._col1(Inner),Output:["_col2"] - <-Map 14 [SIMPLE_EDGE] llap - SHUFFLE [RS_19] - PartitionCols:_col1 - Please refer to the previous Select Operator [SEL_14] - <-Reducer 3 [SIMPLE_EDGE] llap - SHUFFLE [RS_18] - PartitionCols:_col1 - Select Operator [SEL_11] (rows=525/319 width=178) - Output:["_col1"] - Group By Operator [GBY_10] (rows=525/319 width=178) - Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 - <-Union 2 [SIMPLE_EDGE] - <-Map 1 [CONTAINS] llap - Reduce Output Operator [RS_9] - PartitionCols:_col1, _col0 - Select Operator [SEL_2] (rows=25/25 width=175) - Output:["_col0","_col1"] - Filter Operator [FIL_144] (rows=25/25 width=175) + Filter Operator [FIL_153] (rows=500/500 width=178) predicate:value is not null TableScan [TS_0] (rows=25/25 width=175) Output:["key","value"] - <-Map 13 [CONTAINS] llap - Reduce Output Operator [RS_9] - PartitionCols:_col1, _col0 - Select Operator [SEL_5] (rows=500/500 width=178) - Output:["_col0","_col1"] - Filter Operator [FIL_145] (rows=500/500 width=178) - predicate:value is not null - TableScan [TS_3] (rows=500/500 width=178) - Output:["key","value"] - Reducer 11 llap - File Output Operator [FS_5] - Group By Operator [GBY_3] (rows=1/1 width=880) - Output:["_col0","_col1"],aggregations:["compute_stats(VALUE._col0, 'hll')","compute_stats(VALUE._col2, 'hll')"] - <-Reducer 9 [CUSTOM_SIMPLE_EDGE] llap - PARTITION_ONLY_SHUFFLE [RS_2] - Select Operator [SEL_1] (rows=2941/319 width=178) - Output:["key","value"] - Please refer to the previous Group By Operator [GBY_112] - Reducer 12 llap - File Output Operator [FS_5] - Group By Operator [GBY_3] (rows=1/1 width=880) - Output:["_col0","_col1"],aggregations:["compute_stats(VALUE._col0, 'hll')","compute_stats(VALUE._col2, 'hll')"] - <-Reducer 9 [CUSTOM_SIMPLE_EDGE] llap - PARTITION_ONLY_SHUFFLE [RS_2] - Select Operator [SEL_1] (rows=2941/319 width=178) - Output:["key","value"] - Please refer to the previous Group By Operator [GBY_112] + <-Reducer 5 [CONTAINS] llap + Reduce Output Operator [RS_111] + PartitionCols:_col0, _col1 + Group By Operator [GBY_63] (rows=2706/309 width=178) + Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 + <-Union 4 [SIMPLE_EDGE] + <-Reducer 3 [CONTAINS] llap + Reduce Output Operator [RS_62] + PartitionCols:_col0, _col1 + Select Operator [SEL_24] (rows=66/61 width=177) + Output:["_col0","_col1"] + Merge Join Operator [MERGEJOIN_159] (rows=66/61 width=177) + Conds:RS_21._col3=RS_22._col1(Inner),Output:["_col1","_col2"] + <-Reducer 15 [SIMPLE_EDGE] llap + SHUFFLE [RS_22] + PartitionCols:_col1 + Select Operator [SEL_17] (rows=525/319 width=178) + Output:["_col1"] + Group By Operator [GBY_16] (rows=525/319 width=178) + Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 + <-Union 14 [SIMPLE_EDGE] + <-Map 13 [CONTAINS] llap + Reduce Output Operator [RS_15] + PartitionCols:_col1, _col0 + Select Operator [SEL_8] (rows=25/25 width=175) + Output:["_col0","_col1"] + Filter Operator [FIL_143] (rows=25/25 width=175) + predicate:value is not null + TableScan [TS_6] (rows=25/25 width=175) + Output:["key","value"] + <-Map 16 [CONTAINS] llap + Reduce Output Operator [RS_15] + PartitionCols:_col1, _col0 + Select Operator [SEL_11] (rows=500/500 width=178) + Output:["_col0","_col1"] + Filter Operator [FIL_144] (rows=500/500 width=178) + predicate:value is not null + TableScan [TS_9] (rows=500/500 width=178) + Output:["key","value"] + <-Reducer 2 [SIMPLE_EDGE] llap + SHUFFLE [RS_21] + PartitionCols:_col3 + Merge Join Operator [MERGEJOIN_156] (rows=39/37 width=266) + Conds:RS_18._col0=RS_19._col0(Inner),Output:["_col1","_col2","_col3"] + <-Map 1 [SIMPLE_EDGE] llap + SHUFFLE [RS_18] + PartitionCols:_col0 + Select Operator [SEL_2] (rows=500/500 width=178) + Output:["_col0","_col1"] + Filter Operator [FIL_141] (rows=500/500 width=178) + predicate:key is not null + TableScan [TS_0] (rows=500/500 width=178) + default@src,y,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"] + <-Map 10 [SIMPLE_EDGE] llap + SHUFFLE [RS_19] + PartitionCols:_col0 + Please refer to the previous Select Operator [SEL_5] + <-Reducer 9 [CONTAINS] llap + Reduce Output Operator [RS_62] + PartitionCols:_col0, _col1 + Select Operator [SEL_58] (rows=2640/1056 width=178) + Output:["_col0","_col1"] + Merge Join Operator [MERGEJOIN_160] (rows=2640/1056 width=178) + Conds:RS_55._col1=RS_56._col1(Inner),Output:["_col0","_col3"] + <-Reducer 22 [SIMPLE_EDGE] llap + SHUFFLE [RS_56] + PartitionCols:_col1 + Select Operator [SEL_51] (rows=1025/319 width=178) + Output:["_col1"] + Group By Operator [GBY_50] (rows=1025/319 width=178) + Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 + <-Union 21 [SIMPLE_EDGE] + <-Map 24 [CONTAINS] llap + Reduce Output Operator [RS_49] + PartitionCols:_col1, _col0 + Select Operator [SEL_45] (rows=500/500 width=178) + Output:["_col0","_col1"] + Filter Operator [FIL_149] (rows=500/500 width=178) + predicate:value is not null + TableScan [TS_43] (rows=500/500 width=178) + Output:["key","value"] + <-Reducer 20 [CONTAINS] llap + Reduce Output Operator [RS_49] + PartitionCols:_col1, _col0 + Select Operator [SEL_42] (rows=525/319 width=178) + Output:["_col0","_col1"] + Group By Operator [GBY_41] (rows=525/319 width=178) + Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 + <-Union 19 [SIMPLE_EDGE] + <-Map 18 [CONTAINS] llap + Reduce Output Operator [RS_40] + PartitionCols:_col1, _col0 + Select Operator [SEL_33] (rows=25/25 width=175) + Output:["_col0","_col1"] + Filter Operator [FIL_147] (rows=25/25 width=175) + predicate:value is not null + TableScan [TS_31] (rows=25/25 width=175) + Output:["key","value"] + <-Map 23 [CONTAINS] llap + Reduce Output Operator [RS_40] + PartitionCols:_col1, _col0 + Select Operator [SEL_36] (rows=500/500 width=178) + Output:["_col0","_col1"] + Filter Operator [FIL_148] (rows=500/500 width=178) + predicate:value is not null + TableScan [TS_34] (rows=500/500 width=178) + Output:["key","value"] + <-Reducer 8 [SIMPLE_EDGE] llap + SHUFFLE [RS_55] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_157] (rows=791/1028 width=269) + Conds:RS_52._col0=RS_53._col0(Inner),Output:["_col0","_col1","_col3"] + <-Map 1 [SIMPLE_EDGE] llap + SHUFFLE [RS_52] + PartitionCols:_col0 + Select Operator [SEL_27] (rows=500/500 width=178) + Output:["_col0","_col1"] + Filter Operator [FIL_145] (rows=500/500 width=178) + predicate:(key is not null and value is not null) + Please refer to the previous TableScan [TS_0] + <-Map 17 [SIMPLE_EDGE] llap + SHUFFLE [RS_53] + PartitionCols:_col0 + Select Operator [SEL_30] (rows=500/500 width=178) + Output:["_col0","_col1"] + Filter Operator [FIL_146] (rows=500/500 width=178) + predicate:key is not null + TableScan [TS_28] (rows=500/500 width=178) + default@src,y,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"] + File Output Operator [FS_117] + table:{"name:":"default.b"} + Please refer to the previous Group By Operator [GBY_112] + File Output Operator [FS_119] + table:{"name:":"default.c"} + Please refer to the previous Group By Operator [GBY_112] Stage-6 Stats Work{} Stage-1 @@ -1820,54 +1746,40 @@ Stage-4 Stage-3 Dependency Collection{} Stage-2 - Reducer 6 llap - File Output Operator [FS_5] - Group By Operator [GBY_3] (rows=1/2 width=880) - Output:["_col0","_col1"],aggregations:["compute_stats(VALUE._col0, 'hll')","compute_stats(VALUE._col2, 'hll')"] - <-Reducer 5 [CUSTOM_SIMPLE_EDGE] llap - File Output Operator [FS_18] - table:{"name:":"default.dest1"} - Select Operator [SEL_16] (rows=309/310 width=272) - Output:["_col0","_col1"] - Group By Operator [GBY_15] (rows=309/310 width=96) - Output:["_col0","_col1"],aggregations:["count(DISTINCT KEY._col1:0._col0)"],keys:KEY._col0 - <-Reducer 4 [SIMPLE_EDGE] llap - PARTITION_ONLY_SHUFFLE [RS_14] - PartitionCols:_col0 - Group By Operator [GBY_11] (rows=501/310 width=272) - Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 - <-Union 3 [SIMPLE_EDGE] - <-Map 8 [CONTAINS] llap - Reduce Output Operator [RS_10] - PartitionCols:_col0, _col1 - Select Operator [SEL_6] (rows=500/500 width=178) - Output:["_col0","_col1"] - TableScan [TS_5] (rows=500/500 width=178) - Output:["key","value"] - <-Reducer 2 [CONTAINS] llap - Reduce Output Operator [RS_10] - PartitionCols:_col0, _col1 - Select Operator [SEL_4] (rows=1/1 width=272) - Output:["_col0","_col1"] - Group By Operator [GBY_3] (rows=1/2 width=8) - Output:["_col0"],aggregations:["count()"] - <-Map 1 [CUSTOM_SIMPLE_EDGE] llap - PARTITION_ONLY_SHUFFLE [RS_2] - Select Operator [SEL_1] (rows=500/310 width=10) - TableScan [TS_0] (rows=500/500 width=10) - default@src,s1,Tbl:COMPLETE,Col:COMPLETE - PARTITION_ONLY_SHUFFLE [RS_2] - Select Operator [SEL_1] (rows=309/310 width=272) - Output:["key","value"] - Please refer to the previous Select Operator [SEL_16] - Reducer 7 llap - File Output Operator [FS_5] - Group By Operator [GBY_3] (rows=1/2 width=1320) - Output:["_col0","_col1","_col2"],aggregations:["compute_stats(VALUE._col0, 'hll')","compute_stats(VALUE._col2, 'hll')","compute_stats(VALUE._col3, 'hll')"] - <-Reducer 4 [CUSTOM_SIMPLE_EDGE] llap - PARTITION_ONLY_SHUFFLE [RS_2] - Select Operator [SEL_1] (rows=501/310 width=456) - Output:["key","val1","val2"] + Reducer 5 llap + File Output Operator [FS_18] + table:{"name:":"default.dest1"} + Select Operator [SEL_16] (rows=316/310 width=272) + Output:["_col0","_col1"] + Group By Operator [GBY_15] (rows=316/310 width=96) + Output:["_col0","_col1"],aggregations:["count(DISTINCT KEY._col1:0._col0)"],keys:KEY._col0 + <-Reducer 4 [SIMPLE_EDGE] llap + SHUFFLE [RS_14] + PartitionCols:_col0 + Group By Operator [GBY_11] (rows=501/310 width=272) + Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 + <-Union 3 [SIMPLE_EDGE] + <-Map 6 [CONTAINS] llap + Reduce Output Operator [RS_10] + PartitionCols:_col0, _col1 + Select Operator [SEL_6] (rows=500/500 width=178) + Output:["_col0","_col1"] + TableScan [TS_5] (rows=500/500 width=178) + Output:["key","value"] + <-Reducer 2 [CONTAINS] llap + Reduce Output Operator [RS_10] + PartitionCols:_col0, _col1 + Select Operator [SEL_4] (rows=1/1 width=272) + Output:["_col0","_col1"] + Group By Operator [GBY_3] (rows=1/1 width=8) + Output:["_col0"],aggregations:["count()"] + <-Map 1 [CUSTOM_SIMPLE_EDGE] llap + PARTITION_ONLY_SHUFFLE [RS_2] + Select Operator [SEL_1] (rows=500/500 width=10) + TableScan [TS_0] (rows=500/500 width=10) + default@src,s1,Tbl:COMPLETE,Col:COMPLETE + File Output Operator [FS_24] + table:{"name:":"default.dest2"} Select Operator [SEL_22] (rows=501/310 width=456) Output:["_col0","_col1","_col2"] Group By Operator [GBY_21] (rows=501/310 width=280) @@ -1915,9 +1827,9 @@ Stage-0 Stage-1 Reducer 2 llap File Output Operator [FS_8] - Select Operator [SEL_7] (rows=261/4122 width=260) + Select Operator [SEL_7] (rows=250/4122 width=260) Output:["_col0","_col1","_col2"] - Merge Join Operator [MERGEJOIN_9] (rows=261/4122 width=260) + Merge Join Operator [MERGEJOIN_9] (rows=250/4122 width=260) Conds:RS_3.key=RS_3.key(Unique),RS_3.key=RS_3.key(Unique),RS_3.key=RS_3.key(Unique),Output:["_col0","_col5","_col10"] <-Map 1 [SIMPLE_EDGE] llap SHUFFLE [RS_3] @@ -2010,6 +1922,49 @@ Stage-4 Stage-3 Dependency Collection{} Stage-2 + Reducer 4 llap + File Output Operator [FS_16] + table:{"name:":"default.dest1"} + Select Operator [SEL_14] (rows=316/310 width=272) + Output:["_col0","_col1"] + Group By Operator [GBY_13] (rows=316/310 width=96) + Output:["_col0","_col1"],aggregations:["count(DISTINCT KEY._col1:0._col0)"],keys:KEY._col0 + <-Union 3 [SIMPLE_EDGE] + <-Map 6 [CONTAINS] llap + Reduce Output Operator [RS_12] + PartitionCols:_col0 + Select Operator [SEL_6] (rows=500/500 width=178) + Output:["_col0","_col1"] + TableScan [TS_5] (rows=500/500 width=178) + Output:["key","value"] + Reduce Output Operator [RS_18] + PartitionCols:_col0, _col1 + Please refer to the previous Select Operator [SEL_6] + <-Map 7 [CONTAINS] llap + Reduce Output Operator [RS_12] + PartitionCols:_col0 + Select Operator [SEL_9] (rows=500/500 width=178) + Output:["_col0","_col1"] + TableScan [TS_8] (rows=500/500 width=178) + Output:["key","value"] + Reduce Output Operator [RS_18] + PartitionCols:_col0, _col1 + Please refer to the previous Select Operator [SEL_9] + <-Reducer 2 [CONTAINS] llap + Reduce Output Operator [RS_12] + PartitionCols:_col0 + Select Operator [SEL_4] (rows=1/1 width=272) + Output:["_col0","_col1"] + Group By Operator [GBY_3] (rows=1/1 width=8) + Output:["_col0"],aggregations:["count()"] + <-Map 1 [CUSTOM_SIMPLE_EDGE] llap + PARTITION_ONLY_SHUFFLE [RS_2] + Select Operator [SEL_1] (rows=500/500 width=10) + TableScan [TS_0] (rows=500/500 width=10) + default@src,s1,Tbl:COMPLETE,Col:COMPLETE + Reduce Output Operator [RS_18] + PartitionCols:_col0, _col1 + Please refer to the previous Select Operator [SEL_4] Reducer 5 llap File Output Operator [FS_5] Group By Operator [GBY_3] (rows=1/2 width=880) @@ -2146,6 +2101,39 @@ Stage-4 Stage-3 Dependency Collection{} Stage-2 + Reducer 4 llap + File Output Operator [FS_14] + table:{"name:":"default.dest1"} + Select Operator [SEL_12] (rows=316/310 width=272) + Output:["_col0","_col1"] + Group By Operator [GBY_11] (rows=316/310 width=96) + Output:["_col0","_col1"],aggregations:["count(DISTINCT KEY._col1:0._col0)"],keys:KEY._col0 + <-Union 3 [SIMPLE_EDGE] + <-Map 6 [CONTAINS] llap + Reduce Output Operator [RS_10] + PartitionCols:_col0 + Select Operator [SEL_6] (rows=500/500 width=178) + Output:["_col0","_col1"] + TableScan [TS_5] (rows=500/500 width=178) + Output:["key","value"] + Reduce Output Operator [RS_16] + PartitionCols:_col0, _col1 + Please refer to the previous Select Operator [SEL_6] + <-Reducer 2 [CONTAINS] llap + Reduce Output Operator [RS_10] + PartitionCols:_col0 + Select Operator [SEL_4] (rows=1/1 width=272) + Output:["_col0","_col1"] + Group By Operator [GBY_3] (rows=1/1 width=8) + Output:["_col0"],aggregations:["count()"] + <-Map 1 [CUSTOM_SIMPLE_EDGE] llap + PARTITION_ONLY_SHUFFLE [RS_2] + Select Operator [SEL_1] (rows=500/500 width=10) + TableScan [TS_0] (rows=500/500 width=10) + default@src,s1,Tbl:COMPLETE,Col:COMPLETE + Reduce Output Operator [RS_16] + PartitionCols:_col0, _col1 + Please refer to the previous Select Operator [SEL_4] Reducer 5 llap File Output Operator [FS_5] Group By Operator [GBY_3] (rows=1/2 width=880) diff --git a/ql/src/test/results/clientpositive/llap/explainuser_1.q.out b/ql/src/test/results/clientpositive/llap/explainuser_1.q.out index 8ab5e3a..8c2e2fc 100644 --- a/ql/src/test/results/clientpositive/llap/explainuser_1.q.out +++ b/ql/src/test/results/clientpositive/llap/explainuser_1.q.out @@ -1713,9 +1713,9 @@ Stage-0 Stage-1 Reducer 2 llap File Output Operator [FS_19] - Select Operator [SEL_18] (rows=366 width=178) + Select Operator [SEL_18] (rows=365 width=178) Output:["_col0","_col1"] - Filter Operator [FIL_17] (rows=366 width=179) + Filter Operator [FIL_17] (rows=365 width=179) predicate:_col3 is null Merge Join Operator [MERGEJOIN_22] (rows=500 width=179) Conds:RS_14._col1=RS_15._col0(Left Outer),Output:["_col0","_col1","_col3"] @@ -1777,9 +1777,9 @@ Stage-0 Stage-1 Reducer 3 llap File Output Operator [FS_18] - Select Operator [SEL_17] (rows=183 width=178) + Select Operator [SEL_17] (rows=185 width=178) Output:["_col0","_col1"] - Filter Operator [FIL_16] (rows=183 width=179) + Filter Operator [FIL_16] (rows=185 width=179) predicate:_col4 is null Merge Join Operator [MERGEJOIN_21] (rows=250 width=179) Conds:RS_13._col0, _col1=RS_14._col0, _col1(Left Outer),Output:["_col0","_col1","_col4"] @@ -1852,7 +1852,7 @@ Stage-0 Stage-1 Reducer 2 llap File Output Operator [FS_12] - Merge Join Operator [MERGEJOIN_17] (rows=133 width=178) + Merge Join Operator [MERGEJOIN_17] (rows=131 width=178) Conds:RS_8._col0, _col1=RS_9._col0, _col1(Left Semi),Output:["_col0","_col1"] <-Map 1 [SIMPLE_EDGE] llap SHUFFLE [RS_8] @@ -1904,7 +1904,7 @@ Stage-0 Stage-1 Reducer 2 llap File Output Operator [FS_12] - Merge Join Operator [MERGEJOIN_17] (rows=133 width=178) + Merge Join Operator [MERGEJOIN_17] (rows=131 width=178) Conds:RS_8._col0, _col1=RS_9._col0, _col1(Left Semi),Output:["_col0","_col1"] <-Map 1 [SIMPLE_EDGE] llap SHUFFLE [RS_8] @@ -1946,7 +1946,7 @@ Stage-0 Stage-1 Reducer 2 llap File Output Operator [FS_12] - Merge Join Operator [MERGEJOIN_17] (rows=133 width=178) + Merge Join Operator [MERGEJOIN_17] (rows=131 width=178) Conds:RS_8._col0=RS_9._col0(Left Semi),Output:["_col0","_col1"] <-Map 1 [SIMPLE_EDGE] llap SHUFFLE [RS_8] @@ -2067,16 +2067,16 @@ Stage-0 <-Reducer 3 [SIMPLE_EDGE] llap SHUFFLE [RS_27] PartitionCols:_col2 - Filter Operator [FIL_37] (rows=66 width=186) + Filter Operator [FIL_37] (rows=65 width=186) predicate:_col2 is not null - Group By Operator [GBY_14] (rows=66 width=186) + Group By Operator [GBY_14] (rows=65 width=186) Output:["_col0","_col1","_col2"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1 <-Reducer 2 [SIMPLE_EDGE] llap SHUFFLE [RS_13] PartitionCols:_col0, _col1 - Group By Operator [GBY_12] (rows=66 width=186) + Group By Operator [GBY_12] (rows=65 width=186) Output:["_col0","_col1","_col2"],aggregations:["count()"],keys:_col0, _col1 - Merge Join Operator [MERGEJOIN_43] (rows=133 width=178) + Merge Join Operator [MERGEJOIN_43] (rows=131 width=178) Conds:RS_8._col0=RS_9._col0(Left Semi),Output:["_col0","_col1"] <-Map 5 [SIMPLE_EDGE] llap SHUFFLE [RS_9] @@ -2676,7 +2676,7 @@ Stage-0 PartitionCols:_col0 Group By Operator [GBY_10] (rows=16 width=94) Output:["_col0","_col1"],aggregations:["count()"],keys:_col0 - Merge Join Operator [MERGEJOIN_24] (rows=40 width=86) + Merge Join Operator [MERGEJOIN_24] (rows=39 width=86) Conds:RS_6._col0=RS_7._col0(Inner),Output:["_col0"] <-Map 1 [SIMPLE_EDGE] llap SHUFFLE [RS_6] @@ -2737,7 +2737,7 @@ Stage-0 PartitionCols:_col0 Group By Operator [GBY_10] (rows=16 width=94) Output:["_col0","_col1"],aggregations:["count()"],keys:_col0 - Merge Join Operator [MERGEJOIN_24] (rows=40 width=86) + Merge Join Operator [MERGEJOIN_24] (rows=39 width=86) Conds:RS_6._col0=RS_7._col0(Inner),Output:["_col0"] <-Map 1 [SIMPLE_EDGE] llap SHUFFLE [RS_6] @@ -2798,7 +2798,7 @@ Stage-0 PartitionCols:_col0 Group By Operator [GBY_10] (rows=16 width=94) Output:["_col0","_col1"],aggregations:["count()"],keys:_col0 - Map Join Operator [MAPJOIN_24] (rows=40 width=86) + Map Join Operator [MAPJOIN_24] (rows=39 width=86) Conds:RS_6._col0=SEL_5._col0(Inner),Output:["_col0"] <-Map 1 [BROADCAST_EDGE] llap BROADCAST [RS_6] @@ -2847,16 +2847,16 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_18] Group By Operator [GBY_17] (rows=1 width=16) Output:["_col0","_col1"],aggregations:["sum(_col0)","sum(_col1)"] - Select Operator [SEL_15] (rows=10 width=94) + Select Operator [SEL_15] (rows=9 width=94) Output:["_col0","_col1"] - Group By Operator [GBY_14] (rows=10 width=94) + Group By Operator [GBY_14] (rows=9 width=94) Output:["_col0","_col1"],aggregations:["count(VALUE._col0)"],keys:KEY._col0 <-Reducer 2 [SIMPLE_EDGE] llap SHUFFLE [RS_13] PartitionCols:_col0 - Group By Operator [GBY_12] (rows=10 width=94) + Group By Operator [GBY_12] (rows=9 width=94) Output:["_col0","_col1"],aggregations:["count()"],keys:_col0 - Merge Join Operator [MERGEJOIN_26] (rows=20 width=86) + Merge Join Operator [MERGEJOIN_26] (rows=19 width=86) Conds:RS_8._col0=RS_9._col0(Left Semi),Output:["_col0"] <-Map 1 [SIMPLE_EDGE] llap SHUFFLE [RS_8] @@ -5323,44 +5323,31 @@ Stage-3 Stage-2 Dependency Collection{} Stage-1 - Reducer 4 llap - File Output Operator [FS_7] - Group By Operator [GBY_5] (rows=1 width=880) - Output:["_col0","_col1"],aggregations:["compute_stats(VALUE._col0)","compute_stats(VALUE._col1)"] - <-Reducer 3 [CUSTOM_SIMPLE_EDGE] llap - PARTITION_ONLY_SHUFFLE [RS_4] - Group By Operator [GBY_3] (rows=1 width=864) - Output:["_col0","_col1"],aggregations:["compute_stats(VALUE._col0, 'hll')","compute_stats(VALUE._col2, 'hll')"] - <-Reducer 2 [CUSTOM_SIMPLE_EDGE] llap - File Output Operator [FS_11] - table:{"name:":"default.dest_j1"} - Select Operator [SEL_9] (rows=809 width=95) - Output:["_col0","_col1"] - Merge Join Operator [MERGEJOIN_16] (rows=809 width=178) - Conds:RS_6._col0=RS_7._col0(Inner),Output:["_col0","_col2"] - <-Map 1 [SIMPLE_EDGE] llap - SHUFFLE [RS_6] - PartitionCols:_col0 - Select Operator [SEL_2] (rows=500 width=87) - Output:["_col0"] - Filter Operator [FIL_14] (rows=500 width=87) - predicate:key is not null - TableScan [TS_0] (rows=500 width=87) - default@src,src1,Tbl:COMPLETE,Col:COMPLETE,Output:["key"] - <-Map 5 [SIMPLE_EDGE] llap - SHUFFLE [RS_7] - PartitionCols:_col0 - Select Operator [SEL_5] (rows=500 width=178) - Output:["_col0","_col1"] - Filter Operator [FIL_15] (rows=500 width=178) - predicate:key is not null - TableScan [TS_3] (rows=500 width=178) - default@src,src2,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"] - PARTITION_ONLY_SHUFFLE [RS_2] - PartitionCols:rand() - Select Operator [SEL_1] (rows=809 width=95) - Output:["key","value"] - Please refer to the previous Select Operator [SEL_9] + Reducer 2 llap + File Output Operator [FS_11] + table:{"name:":"default.dest_j1"} + Select Operator [SEL_9] (rows=791 width=95) + Output:["_col0","_col1"] + Merge Join Operator [MERGEJOIN_16] (rows=791 width=178) + Conds:RS_6._col0=RS_7._col0(Inner),Output:["_col0","_col2"] + <-Map 1 [SIMPLE_EDGE] llap + SHUFFLE [RS_6] + PartitionCols:_col0 + Select Operator [SEL_2] (rows=500 width=87) + Output:["_col0"] + Filter Operator [FIL_14] (rows=500 width=87) + predicate:key is not null + TableScan [TS_0] (rows=500 width=87) + default@src,src1,Tbl:COMPLETE,Col:COMPLETE,Output:["key"] + <-Map 3 [SIMPLE_EDGE] llap + SHUFFLE [RS_7] + PartitionCols:_col0 + Select Operator [SEL_5] (rows=500 width=178) + Output:["_col0","_col1"] + Filter Operator [FIL_15] (rows=500 width=178) + predicate:key is not null + TableScan [TS_3] (rows=500 width=178) + default@src,src2,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"] PREHOOK: query: FROM src src1 JOIN src src2 ON (src1.key = src2.key) INSERT OVERWRITE TABLE dest_j1 select src1.key, src2.value @@ -5578,7 +5565,7 @@ Stage-0 Stage-1 Reducer 2 llap File Output Operator [FS_10] - Merge Join Operator [MERGEJOIN_15] (rows=809 width=356) + Merge Join Operator [MERGEJOIN_15] (rows=791 width=356) Conds:RS_6._col0=RS_7._col0(Inner),Output:["_col0","_col1","_col2","_col3"] <-Map 1 [SIMPLE_EDGE] llap SHUFFLE [RS_6] diff --git a/ql/src/test/results/clientpositive/llap/explainuser_2.q.out b/ql/src/test/results/clientpositive/llap/explainuser_2.q.out index 4f8e327..3977bb9 100644 --- a/ql/src/test/results/clientpositive/llap/explainuser_2.q.out +++ b/ql/src/test/results/clientpositive/llap/explainuser_2.q.out @@ -192,9 +192,9 @@ Stage-0 Stage-1 Reducer 3 llap File Output Operator [FS_16] - Select Operator [SEL_15] (rows=64 width=268) + Select Operator [SEL_15] (rows=63 width=268) Output:["_col0","_col1","_col2"] - Merge Join Operator [MERGEJOIN_26] (rows=64 width=268) + Merge Join Operator [MERGEJOIN_26] (rows=63 width=268) Conds:RS_12._col3=RS_13._col0(Inner),Output:["_col1","_col2","_col4"] <-Map 5 [SIMPLE_EDGE] llap SHUFFLE [RS_13] @@ -208,7 +208,7 @@ Stage-0 <-Reducer 2 [SIMPLE_EDGE] llap SHUFFLE [RS_12] PartitionCols:_col3 - Merge Join Operator [MERGEJOIN_25] (rows=40 width=266) + Merge Join Operator [MERGEJOIN_25] (rows=39 width=266) Conds:RS_9._col0=RS_10._col0(Inner),Output:["_col1","_col2","_col3"] <-Map 1 [SIMPLE_EDGE] llap SHUFFLE [RS_9] @@ -443,146 +443,141 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Map 1 <- Union 2 (CONTAINS) +Map 12 <- Union 10 (CONTAINS) Map 13 <- Union 14 (CONTAINS) Map 16 <- Union 14 (CONTAINS) -Map 8 <- Union 2 (CONTAINS) -Reducer 10 <- Map 9 (SIMPLE_EDGE), Reducer 15 (SIMPLE_EDGE) -Reducer 11 <- Map 17 (SIMPLE_EDGE), Reducer 10 (SIMPLE_EDGE), Union 6 (CONTAINS) +Map 9 <- Union 10 (CONTAINS) +Reducer 11 <- Union 10 (SIMPLE_EDGE) Reducer 15 <- Union 14 (SIMPLE_EDGE) -Reducer 3 <- Union 2 (SIMPLE_EDGE) -Reducer 4 <- Map 9 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) -Reducer 5 <- Map 12 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE), Union 6 (CONTAINS) -Reducer 7 <- Union 6 (SIMPLE_EDGE) +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) +Reducer 3 <- Reducer 11 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE), Union 4 (CONTAINS) +Reducer 5 <- Union 4 (SIMPLE_EDGE) +Reducer 6 <- Map 1 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) +Reducer 7 <- Reducer 15 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE), Union 4 (CONTAINS) Stage-0 Fetch Operator limit:-1 Stage-1 - Reducer 7 llap + Reducer 5 llap File Output Operator [FS_59] - Group By Operator [GBY_57] (rows=28 width=177) + Group By Operator [GBY_57] (rows=33 width=177) Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 - <-Union 6 [SIMPLE_EDGE] - <-Reducer 11 [CONTAINS] llap + <-Union 4 [SIMPLE_EDGE] + <-Reducer 3 [CONTAINS] llap Reduce Output Operator [RS_56] PartitionCols:_col0, _col1 - Group By Operator [GBY_55] (rows=28 width=177) + Group By Operator [GBY_55] (rows=33 width=177) Output:["_col0","_col1"],keys:_col0, _col1 - Select Operator [SEL_51] (rows=33 width=177) + Select Operator [SEL_25] (rows=33 width=177) Output:["_col0","_col1"] - Merge Join Operator [MERGEJOIN_85] (rows=33 width=177) - Conds:RS_48._col2=RS_49._col0(Inner),Output:["_col1","_col2"] - <-Map 17 [SIMPLE_EDGE] llap - SHUFFLE [RS_49] - PartitionCols:_col0 - Select Operator [SEL_44] (rows=500 width=87) - Output:["_col0"] - Filter Operator [FIL_81] (rows=500 width=87) - predicate:key is not null - TableScan [TS_42] (rows=500 width=87) - default@src,y,Tbl:COMPLETE,Col:COMPLETE,Output:["key"] - <-Reducer 10 [SIMPLE_EDGE] llap - SHUFFLE [RS_48] + Merge Join Operator [MERGEJOIN_82] (rows=33 width=177) + Conds:RS_22._col2=RS_23._col1(Inner),Output:["_col1","_col4"] + <-Reducer 11 [SIMPLE_EDGE] llap + SHUFFLE [RS_23] + PartitionCols:_col1 + Select Operator [SEL_18] (rows=262 width=178) + Output:["_col1"] + Group By Operator [GBY_17] (rows=262 width=178) + Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 + <-Union 10 [SIMPLE_EDGE] + <-Map 12 [CONTAINS] llap + Reduce Output Operator [RS_16] + PartitionCols:_col0, _col1 + Group By Operator [GBY_15] (rows=262 width=178) + Output:["_col0","_col1"],keys:_col1, _col0 + Select Operator [SEL_11] (rows=500 width=178) + Output:["_col0","_col1"] + Filter Operator [FIL_75] (rows=500 width=178) + predicate:value is not null + TableScan [TS_9] (rows=500 width=178) + Output:["key","value"] + <-Map 9 [CONTAINS] llap + Reduce Output Operator [RS_16] + PartitionCols:_col0, _col1 + Group By Operator [GBY_15] (rows=262 width=178) + Output:["_col0","_col1"],keys:_col1, _col0 + Select Operator [SEL_8] (rows=25 width=175) + Output:["_col0","_col1"] + Filter Operator [FIL_74] (rows=25 width=175) + predicate:value is not null + TableScan [TS_6] (rows=25 width=175) + Output:["key","value"] + <-Reducer 2 [SIMPLE_EDGE] llap + SHUFFLE [RS_22] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_84] (rows=21 width=177) - Conds:RS_45._col1=RS_46._col1(Inner),Output:["_col1","_col2"] - <-Map 9 [SIMPLE_EDGE] llap - SHUFFLE [RS_46] - PartitionCols:_col1 - Select Operator [SEL_15] (rows=25 width=175) + Merge Join Operator [MERGEJOIN_80] (rows=39 width=175) + Conds:RS_19._col0=RS_20._col0(Inner),Output:["_col1","_col2"] + <-Map 1 [SIMPLE_EDGE] llap + SHUFFLE [RS_19] + PartitionCols:_col0 + Select Operator [SEL_2] (rows=500 width=87) + Output:["_col0"] + Filter Operator [FIL_72] (rows=500 width=87) + predicate:key is not null + TableScan [TS_0] (rows=500 width=87) + default@src,y,Tbl:COMPLETE,Col:COMPLETE,Output:["key"] + <-Map 8 [SIMPLE_EDGE] llap + SHUFFLE [RS_20] + PartitionCols:_col0 + Select Operator [SEL_5] (rows=25 width=175) Output:["_col0","_col1"] - Filter Operator [FIL_76] (rows=25 width=175) + Filter Operator [FIL_73] (rows=25 width=175) predicate:(key is not null and value is not null) - TableScan [TS_13] (rows=25 width=175) + TableScan [TS_3] (rows=25 width=175) default@src1,x,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"] - <-Reducer 15 [SIMPLE_EDGE] llap - SHUFFLE [RS_45] - PartitionCols:_col1 - Select Operator [SEL_38] (rows=262 width=178) - Output:["_col1"] - Group By Operator [GBY_37] (rows=262 width=178) - Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 - <-Union 14 [SIMPLE_EDGE] - <-Map 13 [CONTAINS] llap - Reduce Output Operator [RS_36] - PartitionCols:_col0, _col1 - Group By Operator [GBY_35] (rows=262 width=178) - Output:["_col0","_col1"],keys:_col1, _col0 - Select Operator [SEL_28] (rows=25 width=175) - Output:["_col0","_col1"] - Filter Operator [FIL_78] (rows=25 width=175) - predicate:value is not null - TableScan [TS_26] (rows=25 width=175) - Output:["key","value"] - <-Map 16 [CONTAINS] llap - Reduce Output Operator [RS_36] - PartitionCols:_col0, _col1 - Group By Operator [GBY_35] (rows=262 width=178) - Output:["_col0","_col1"],keys:_col1, _col0 - Select Operator [SEL_31] (rows=500 width=178) - Output:["_col0","_col1"] - Filter Operator [FIL_79] (rows=500 width=178) - predicate:value is not null - TableScan [TS_29] (rows=500 width=178) - Output:["key","value"] - <-Reducer 5 [CONTAINS] llap + <-Reducer 7 [CONTAINS] llap Reduce Output Operator [RS_56] PartitionCols:_col0, _col1 - Group By Operator [GBY_55] (rows=28 width=177) + Group By Operator [GBY_55] (rows=33 width=177) Output:["_col0","_col1"],keys:_col0, _col1 - Select Operator [SEL_25] (rows=33 width=177) + Select Operator [SEL_51] (rows=33 width=177) Output:["_col0","_col1"] Merge Join Operator [MERGEJOIN_83] (rows=33 width=177) - Conds:RS_22._col2=RS_23._col0(Inner),Output:["_col1","_col2"] - <-Map 12 [SIMPLE_EDGE] llap - SHUFFLE [RS_23] - PartitionCols:_col0 - Select Operator [SEL_18] (rows=500 width=87) - Output:["_col0"] - Filter Operator [FIL_77] (rows=500 width=87) - predicate:key is not null - TableScan [TS_16] (rows=500 width=87) - default@src,y,Tbl:COMPLETE,Col:COMPLETE,Output:["key"] - <-Reducer 4 [SIMPLE_EDGE] llap - SHUFFLE [RS_22] + Conds:RS_48._col2=RS_49._col1(Inner),Output:["_col1","_col4"] + <-Reducer 15 [SIMPLE_EDGE] llap + SHUFFLE [RS_49] + PartitionCols:_col1 + Select Operator [SEL_44] (rows=262 width=178) + Output:["_col1"] + Group By Operator [GBY_43] (rows=262 width=178) + Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 + <-Union 14 [SIMPLE_EDGE] + <-Map 13 [CONTAINS] llap + Reduce Output Operator [RS_42] + PartitionCols:_col0, _col1 + Group By Operator [GBY_41] (rows=262 width=178) + Output:["_col0","_col1"],keys:_col1, _col0 + Select Operator [SEL_34] (rows=25 width=175) + Output:["_col0","_col1"] + Filter Operator [FIL_78] (rows=25 width=175) + predicate:value is not null + TableScan [TS_32] (rows=25 width=175) + Output:["key","value"] + <-Map 16 [CONTAINS] llap + Reduce Output Operator [RS_42] + PartitionCols:_col0, _col1 + Group By Operator [GBY_41] (rows=262 width=178) + Output:["_col0","_col1"],keys:_col1, _col0 + Select Operator [SEL_37] (rows=500 width=178) + Output:["_col0","_col1"] + Filter Operator [FIL_79] (rows=500 width=178) + predicate:value is not null + TableScan [TS_35] (rows=500 width=178) + Output:["key","value"] + <-Reducer 6 [SIMPLE_EDGE] llap + SHUFFLE [RS_48] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_82] (rows=21 width=177) - Conds:RS_19._col1=RS_20._col1(Inner),Output:["_col1","_col2"] - <-Map 9 [SIMPLE_EDGE] llap - SHUFFLE [RS_20] - PartitionCols:_col1 - Please refer to the previous Select Operator [SEL_15] - <-Reducer 3 [SIMPLE_EDGE] llap - SHUFFLE [RS_19] - PartitionCols:_col1 - Select Operator [SEL_12] (rows=262 width=178) - Output:["_col1"] - Group By Operator [GBY_11] (rows=262 width=178) - Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 - <-Union 2 [SIMPLE_EDGE] - <-Map 1 [CONTAINS] llap - Reduce Output Operator [RS_10] - PartitionCols:_col0, _col1 - Group By Operator [GBY_9] (rows=262 width=178) - Output:["_col0","_col1"],keys:_col1, _col0 - Select Operator [SEL_2] (rows=25 width=175) - Output:["_col0","_col1"] - Filter Operator [FIL_74] (rows=25 width=175) - predicate:value is not null - TableScan [TS_0] (rows=25 width=175) - Output:["key","value"] - <-Map 8 [CONTAINS] llap - Reduce Output Operator [RS_10] - PartitionCols:_col0, _col1 - Group By Operator [GBY_9] (rows=262 width=178) - Output:["_col0","_col1"],keys:_col1, _col0 - Select Operator [SEL_5] (rows=500 width=178) - Output:["_col0","_col1"] - Filter Operator [FIL_75] (rows=500 width=178) - predicate:value is not null - TableScan [TS_3] (rows=500 width=178) - Output:["key","value"] + Merge Join Operator [MERGEJOIN_81] (rows=39 width=175) + Conds:RS_45._col0=RS_46._col0(Inner),Output:["_col1","_col2"] + <-Map 1 [SIMPLE_EDGE] llap + SHUFFLE [RS_45] + PartitionCols:_col0 + Please refer to the previous Select Operator [SEL_2] + <-Map 8 [SIMPLE_EDGE] llap + SHUFFLE [RS_46] + PartitionCols:_col0 + Please refer to the previous Select Operator [SEL_5] PREHOOK: query: explain SELECT x.key, y.value @@ -613,281 +608,276 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Map 1 <- Union 2 (CONTAINS) -Map 10 <- Union 2 (CONTAINS) +Map 13 <- Union 14 (CONTAINS) +Map 16 <- Union 14 (CONTAINS) Map 17 <- Union 18 (CONTAINS) Map 22 <- Union 18 (CONTAINS) Map 23 <- Union 20 (CONTAINS) -Map 25 <- Union 26 (CONTAINS) -Map 32 <- Union 26 (CONTAINS) -Map 33 <- Union 28 (CONTAINS) -Map 34 <- Union 30 (CONTAINS) -Reducer 12 <- Map 11 (SIMPLE_EDGE), Reducer 21 (SIMPLE_EDGE) -Reducer 13 <- Map 24 (SIMPLE_EDGE), Reducer 12 (SIMPLE_EDGE), Union 6 (CONTAINS) -Reducer 14 <- Map 11 (SIMPLE_EDGE), Reducer 31 (SIMPLE_EDGE) -Reducer 15 <- Map 16 (SIMPLE_EDGE), Reducer 14 (SIMPLE_EDGE), Union 8 (CONTAINS) +Map 24 <- Union 25 (CONTAINS) +Map 31 <- Union 25 (CONTAINS) +Map 32 <- Union 27 (CONTAINS) +Map 33 <- Union 29 (CONTAINS) +Reducer 10 <- Map 1 (SIMPLE_EDGE), Map 12 (SIMPLE_EDGE) +Reducer 11 <- Reducer 10 (SIMPLE_EDGE), Reducer 30 (SIMPLE_EDGE), Union 6 (CONTAINS) +Reducer 15 <- Union 14 (SIMPLE_EDGE) Reducer 19 <- Union 18 (SIMPLE_EDGE), Union 20 (CONTAINS) +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 12 (SIMPLE_EDGE) Reducer 21 <- Union 20 (SIMPLE_EDGE) -Reducer 27 <- Union 26 (SIMPLE_EDGE), Union 28 (CONTAINS) -Reducer 29 <- Union 28 (SIMPLE_EDGE), Union 30 (CONTAINS) -Reducer 3 <- Union 2 (SIMPLE_EDGE) -Reducer 31 <- Union 30 (SIMPLE_EDGE) -Reducer 4 <- Map 11 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) -Reducer 5 <- Map 16 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE), Union 6 (CONTAINS) -Reducer 7 <- Union 6 (SIMPLE_EDGE), Union 8 (CONTAINS) -Reducer 9 <- Union 8 (SIMPLE_EDGE) +Reducer 26 <- Union 25 (SIMPLE_EDGE), Union 27 (CONTAINS) +Reducer 28 <- Union 27 (SIMPLE_EDGE), Union 29 (CONTAINS) +Reducer 3 <- Reducer 15 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE), Union 4 (CONTAINS) +Reducer 30 <- Union 29 (SIMPLE_EDGE) +Reducer 5 <- Union 4 (SIMPLE_EDGE), Union 6 (CONTAINS) +Reducer 7 <- Union 6 (SIMPLE_EDGE) +Reducer 8 <- Map 1 (SIMPLE_EDGE), Map 12 (SIMPLE_EDGE) +Reducer 9 <- Reducer 21 (SIMPLE_EDGE), Reducer 8 (SIMPLE_EDGE), Union 4 (CONTAINS) Stage-0 Fetch Operator limit:-1 Stage-1 - Reducer 9 llap + Reducer 7 llap File Output Operator [FS_122] - Group By Operator [GBY_120] (rows=48 width=177) + Group By Operator [GBY_120] (rows=47 width=177) Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 - <-Union 8 [SIMPLE_EDGE] - <-Reducer 15 [CONTAINS] llap + <-Union 6 [SIMPLE_EDGE] + <-Reducer 11 [CONTAINS] llap Reduce Output Operator [RS_119] PartitionCols:_col0, _col1 - Group By Operator [GBY_118] (rows=48 width=177) + Group By Operator [GBY_118] (rows=47 width=177) Output:["_col0","_col1"],keys:_col0, _col1 - Select Operator [SEL_114] (rows=56 width=177) + Select Operator [SEL_114] (rows=55 width=177) Output:["_col0","_col1"] - Merge Join Operator [MERGEJOIN_170] (rows=56 width=177) - Conds:RS_111._col2=RS_112._col0(Inner),Output:["_col2","_col5"] - <-Map 16 [SIMPLE_EDGE] llap - SHUFFLE [RS_112] - PartitionCols:_col0 - Select Operator [SEL_18] (rows=500 width=178) - Output:["_col0","_col1"] - Filter Operator [FIL_153] (rows=500 width=178) - predicate:key is not null - TableScan [TS_16] (rows=500 width=178) - default@src,y,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"] - <-Reducer 14 [SIMPLE_EDGE] llap + Merge Join Operator [MERGEJOIN_164] (rows=55 width=177) + Conds:RS_111._col3=RS_112._col1(Inner),Output:["_col1","_col2"] + <-Reducer 10 [SIMPLE_EDGE] llap SHUFFLE [RS_111] - PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_169] (rows=35 width=86) - Conds:RS_108._col1=RS_109._col1(Inner),Output:["_col2"] - <-Map 11 [SIMPLE_EDGE] llap + PartitionCols:_col3 + Merge Join Operator [MERGEJOIN_161] (rows=39 width=266) + Conds:RS_108._col0=RS_109._col0(Inner),Output:["_col1","_col2","_col3"] + <-Map 1 [SIMPLE_EDGE] llap + SHUFFLE [RS_108] + PartitionCols:_col0 + Select Operator [SEL_2] (rows=500 width=178) + Output:["_col0","_col1"] + Filter Operator [FIL_144] (rows=500 width=178) + predicate:key is not null + TableScan [TS_0] (rows=500 width=178) + default@src,y,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"] + <-Map 12 [SIMPLE_EDGE] llap SHUFFLE [RS_109] - PartitionCols:_col1 - Select Operator [SEL_15] (rows=25 width=175) + PartitionCols:_col0 + Select Operator [SEL_5] (rows=25 width=175) Output:["_col0","_col1"] - Filter Operator [FIL_152] (rows=25 width=175) + Filter Operator [FIL_145] (rows=25 width=175) predicate:(key is not null and value is not null) - TableScan [TS_13] (rows=25 width=175) + TableScan [TS_3] (rows=25 width=175) default@src1,x,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"] - <-Reducer 31 [SIMPLE_EDGE] llap - SHUFFLE [RS_108] - PartitionCols:_col1 - Select Operator [SEL_101] (rows=440 width=178) - Output:["_col1"] - Group By Operator [GBY_100] (rows=440 width=178) - Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 - <-Union 30 [SIMPLE_EDGE] - <-Map 34 [CONTAINS] llap - Reduce Output Operator [RS_99] - PartitionCols:_col0, _col1 - Group By Operator [GBY_98] (rows=440 width=178) - Output:["_col0","_col1"],keys:_col1, _col0 - Select Operator [SEL_94] (rows=500 width=178) - Output:["_col0","_col1"] - Filter Operator [FIL_162] (rows=500 width=178) - predicate:value is not null - TableScan [TS_92] (rows=500 width=178) - Output:["key","value"] - <-Reducer 29 [CONTAINS] llap - Reduce Output Operator [RS_99] - PartitionCols:_col0, _col1 - Group By Operator [GBY_98] (rows=440 width=178) - Output:["_col0","_col1"],keys:_col1, _col0 - Select Operator [SEL_91] (rows=381 width=178) - Output:["_col0","_col1"] - Group By Operator [GBY_90] (rows=381 width=178) - Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 - <-Union 28 [SIMPLE_EDGE] - <-Map 33 [CONTAINS] llap - Reduce Output Operator [RS_89] - PartitionCols:_col0, _col1 - Group By Operator [GBY_88] (rows=381 width=178) - Output:["_col0","_col1"],keys:_col1, _col0 - Select Operator [SEL_84] (rows=500 width=178) - Output:["_col0","_col1"] - Filter Operator [FIL_161] (rows=500 width=178) - predicate:value is not null - TableScan [TS_82] (rows=500 width=178) - Output:["key","value"] - <-Reducer 27 [CONTAINS] llap - Reduce Output Operator [RS_89] - PartitionCols:_col0, _col1 - Group By Operator [GBY_88] (rows=381 width=178) - Output:["_col0","_col1"],keys:_col1, _col0 - Select Operator [SEL_81] (rows=262 width=178) - Output:["_col0","_col1"] - Group By Operator [GBY_80] (rows=262 width=178) - Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 - <-Union 26 [SIMPLE_EDGE] - <-Map 25 [CONTAINS] llap - Reduce Output Operator [RS_79] - PartitionCols:_col0, _col1 - Group By Operator [GBY_78] (rows=262 width=178) - Output:["_col0","_col1"],keys:_col1, _col0 - Select Operator [SEL_71] (rows=25 width=175) - Output:["_col0","_col1"] - Filter Operator [FIL_159] (rows=25 width=175) - predicate:value is not null - TableScan [TS_69] (rows=25 width=175) - Output:["key","value"] - <-Map 32 [CONTAINS] llap - Reduce Output Operator [RS_79] - PartitionCols:_col0, _col1 - Group By Operator [GBY_78] (rows=262 width=178) - Output:["_col0","_col1"],keys:_col1, _col0 - Select Operator [SEL_74] (rows=500 width=178) - Output:["_col0","_col1"] - Filter Operator [FIL_160] (rows=500 width=178) - predicate:value is not null - TableScan [TS_72] (rows=500 width=178) - Output:["key","value"] - <-Reducer 7 [CONTAINS] llap + <-Reducer 30 [SIMPLE_EDGE] llap + SHUFFLE [RS_112] + PartitionCols:_col1 + Select Operator [SEL_107] (rows=440 width=178) + Output:["_col1"] + Group By Operator [GBY_106] (rows=440 width=178) + Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 + <-Union 29 [SIMPLE_EDGE] + <-Map 33 [CONTAINS] llap + Reduce Output Operator [RS_105] + PartitionCols:_col0, _col1 + Group By Operator [GBY_104] (rows=440 width=178) + Output:["_col0","_col1"],keys:_col1, _col0 + Select Operator [SEL_100] (rows=500 width=178) + Output:["_col0","_col1"] + Filter Operator [FIL_158] (rows=500 width=178) + predicate:value is not null + TableScan [TS_98] (rows=500 width=178) + Output:["key","value"] + <-Reducer 28 [CONTAINS] llap + Reduce Output Operator [RS_105] + PartitionCols:_col0, _col1 + Group By Operator [GBY_104] (rows=440 width=178) + Output:["_col0","_col1"],keys:_col1, _col0 + Select Operator [SEL_97] (rows=381 width=178) + Output:["_col0","_col1"] + Group By Operator [GBY_96] (rows=381 width=178) + Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 + <-Union 27 [SIMPLE_EDGE] + <-Map 32 [CONTAINS] llap + Reduce Output Operator [RS_95] + PartitionCols:_col0, _col1 + Group By Operator [GBY_94] (rows=381 width=178) + Output:["_col0","_col1"],keys:_col1, _col0 + Select Operator [SEL_90] (rows=500 width=178) + Output:["_col0","_col1"] + Filter Operator [FIL_157] (rows=500 width=178) + predicate:value is not null + TableScan [TS_88] (rows=500 width=178) + Output:["key","value"] + <-Reducer 26 [CONTAINS] llap + Reduce Output Operator [RS_95] + PartitionCols:_col0, _col1 + Group By Operator [GBY_94] (rows=381 width=178) + Output:["_col0","_col1"],keys:_col1, _col0 + Select Operator [SEL_87] (rows=262 width=178) + Output:["_col0","_col1"] + Group By Operator [GBY_86] (rows=262 width=178) + Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 + <-Union 25 [SIMPLE_EDGE] + <-Map 24 [CONTAINS] llap + Reduce Output Operator [RS_85] + PartitionCols:_col0, _col1 + Group By Operator [GBY_84] (rows=262 width=178) + Output:["_col0","_col1"],keys:_col1, _col0 + Select Operator [SEL_77] (rows=25 width=175) + Output:["_col0","_col1"] + Filter Operator [FIL_155] (rows=25 width=175) + predicate:value is not null + TableScan [TS_75] (rows=25 width=175) + Output:["key","value"] + <-Map 31 [CONTAINS] llap + Reduce Output Operator [RS_85] + PartitionCols:_col0, _col1 + Group By Operator [GBY_84] (rows=262 width=178) + Output:["_col0","_col1"],keys:_col1, _col0 + Select Operator [SEL_80] (rows=500 width=178) + Output:["_col0","_col1"] + Filter Operator [FIL_156] (rows=500 width=178) + predicate:value is not null + TableScan [TS_78] (rows=500 width=178) + Output:["key","value"] + <-Reducer 5 [CONTAINS] llap Reduce Output Operator [RS_119] PartitionCols:_col0, _col1 - Group By Operator [GBY_118] (rows=48 width=177) + Group By Operator [GBY_118] (rows=47 width=177) Output:["_col0","_col1"],keys:_col0, _col1 Group By Operator [GBY_67] (rows=40 width=177) Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 - <-Union 6 [SIMPLE_EDGE] - <-Reducer 13 [CONTAINS] llap + <-Union 4 [SIMPLE_EDGE] + <-Reducer 3 [CONTAINS] llap Reduce Output Operator [RS_66] PartitionCols:_col0, _col1 Group By Operator [GBY_65] (rows=40 width=177) Output:["_col0","_col1"],keys:_col0, _col1 - Select Operator [SEL_61] (rows=48 width=177) + Select Operator [SEL_25] (rows=33 width=177) Output:["_col0","_col1"] - Merge Join Operator [MERGEJOIN_168] (rows=48 width=177) - Conds:RS_58._col2=RS_59._col0(Inner),Output:["_col2","_col5"] - <-Map 24 [SIMPLE_EDGE] llap - SHUFFLE [RS_59] - PartitionCols:_col0 - Select Operator [SEL_54] (rows=500 width=178) - Output:["_col0","_col1"] - Filter Operator [FIL_158] (rows=500 width=178) - predicate:key is not null - TableScan [TS_52] (rows=500 width=178) - default@src,y,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"] - <-Reducer 12 [SIMPLE_EDGE] llap - SHUFFLE [RS_58] - PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_167] (rows=30 width=86) - Conds:RS_55._col1=RS_56._col1(Inner),Output:["_col2"] - <-Map 11 [SIMPLE_EDGE] llap - SHUFFLE [RS_56] - PartitionCols:_col1 - Please refer to the previous Select Operator [SEL_15] - <-Reducer 21 [SIMPLE_EDGE] llap - SHUFFLE [RS_55] - PartitionCols:_col1 - Select Operator [SEL_48] (rows=381 width=178) - Output:["_col1"] - Group By Operator [GBY_47] (rows=381 width=178) - Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 - <-Union 20 [SIMPLE_EDGE] - <-Map 23 [CONTAINS] llap - Reduce Output Operator [RS_46] - PartitionCols:_col0, _col1 - Group By Operator [GBY_45] (rows=381 width=178) - Output:["_col0","_col1"],keys:_col1, _col0 - Select Operator [SEL_41] (rows=500 width=178) - Output:["_col0","_col1"] - Filter Operator [FIL_156] (rows=500 width=178) - predicate:value is not null - TableScan [TS_39] (rows=500 width=178) - Output:["key","value"] - <-Reducer 19 [CONTAINS] llap - Reduce Output Operator [RS_46] - PartitionCols:_col0, _col1 - Group By Operator [GBY_45] (rows=381 width=178) - Output:["_col0","_col1"],keys:_col1, _col0 - Select Operator [SEL_38] (rows=262 width=178) - Output:["_col0","_col1"] - Group By Operator [GBY_37] (rows=262 width=178) - Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 - <-Union 18 [SIMPLE_EDGE] - <-Map 17 [CONTAINS] llap - Reduce Output Operator [RS_36] - PartitionCols:_col0, _col1 - Group By Operator [GBY_35] (rows=262 width=178) - Output:["_col0","_col1"],keys:_col1, _col0 - Select Operator [SEL_28] (rows=25 width=175) - Output:["_col0","_col1"] - Filter Operator [FIL_154] (rows=25 width=175) - predicate:value is not null - TableScan [TS_26] (rows=25 width=175) - Output:["key","value"] - <-Map 22 [CONTAINS] llap - Reduce Output Operator [RS_36] - PartitionCols:_col0, _col1 - Group By Operator [GBY_35] (rows=262 width=178) - Output:["_col0","_col1"],keys:_col1, _col0 - Select Operator [SEL_31] (rows=500 width=178) - Output:["_col0","_col1"] - Filter Operator [FIL_155] (rows=500 width=178) - predicate:value is not null - TableScan [TS_29] (rows=500 width=178) - Output:["key","value"] - <-Reducer 5 [CONTAINS] llap + Merge Join Operator [MERGEJOIN_162] (rows=33 width=177) + Conds:RS_22._col3=RS_23._col1(Inner),Output:["_col1","_col2"] + <-Reducer 15 [SIMPLE_EDGE] llap + SHUFFLE [RS_23] + PartitionCols:_col1 + Select Operator [SEL_18] (rows=262 width=178) + Output:["_col1"] + Group By Operator [GBY_17] (rows=262 width=178) + Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 + <-Union 14 [SIMPLE_EDGE] + <-Map 13 [CONTAINS] llap + Reduce Output Operator [RS_16] + PartitionCols:_col0, _col1 + Group By Operator [GBY_15] (rows=262 width=178) + Output:["_col0","_col1"],keys:_col1, _col0 + Select Operator [SEL_8] (rows=25 width=175) + Output:["_col0","_col1"] + Filter Operator [FIL_146] (rows=25 width=175) + predicate:value is not null + TableScan [TS_6] (rows=25 width=175) + Output:["key","value"] + <-Map 16 [CONTAINS] llap + Reduce Output Operator [RS_16] + PartitionCols:_col0, _col1 + Group By Operator [GBY_15] (rows=262 width=178) + Output:["_col0","_col1"],keys:_col1, _col0 + Select Operator [SEL_11] (rows=500 width=178) + Output:["_col0","_col1"] + Filter Operator [FIL_147] (rows=500 width=178) + predicate:value is not null + TableScan [TS_9] (rows=500 width=178) + Output:["key","value"] + <-Reducer 2 [SIMPLE_EDGE] llap + SHUFFLE [RS_22] + PartitionCols:_col3 + Merge Join Operator [MERGEJOIN_159] (rows=39 width=266) + Conds:RS_19._col0=RS_20._col0(Inner),Output:["_col1","_col2","_col3"] + <-Map 1 [SIMPLE_EDGE] llap + SHUFFLE [RS_19] + PartitionCols:_col0 + Please refer to the previous Select Operator [SEL_2] + <-Map 12 [SIMPLE_EDGE] llap + SHUFFLE [RS_20] + PartitionCols:_col0 + Please refer to the previous Select Operator [SEL_5] + <-Reducer 9 [CONTAINS] llap Reduce Output Operator [RS_66] PartitionCols:_col0, _col1 Group By Operator [GBY_65] (rows=40 width=177) Output:["_col0","_col1"],keys:_col0, _col1 - Select Operator [SEL_25] (rows=33 width=177) + Select Operator [SEL_61] (rows=48 width=177) Output:["_col0","_col1"] - Merge Join Operator [MERGEJOIN_166] (rows=33 width=177) - Conds:RS_22._col2=RS_23._col0(Inner),Output:["_col2","_col5"] - <-Map 16 [SIMPLE_EDGE] llap - SHUFFLE [RS_23] - PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_18] - <-Reducer 4 [SIMPLE_EDGE] llap - SHUFFLE [RS_22] - PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_165] (rows=21 width=86) - Conds:RS_19._col1=RS_20._col1(Inner),Output:["_col2"] - <-Map 11 [SIMPLE_EDGE] llap - SHUFFLE [RS_20] - PartitionCols:_col1 - Please refer to the previous Select Operator [SEL_15] - <-Reducer 3 [SIMPLE_EDGE] llap - SHUFFLE [RS_19] - PartitionCols:_col1 - Select Operator [SEL_12] (rows=262 width=178) - Output:["_col1"] - Group By Operator [GBY_11] (rows=262 width=178) - Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 - <-Union 2 [SIMPLE_EDGE] - <-Map 1 [CONTAINS] llap - Reduce Output Operator [RS_10] - PartitionCols:_col0, _col1 - Group By Operator [GBY_9] (rows=262 width=178) - Output:["_col0","_col1"],keys:_col1, _col0 - Select Operator [SEL_2] (rows=25 width=175) - Output:["_col0","_col1"] - Filter Operator [FIL_150] (rows=25 width=175) - predicate:value is not null - TableScan [TS_0] (rows=25 width=175) - Output:["key","value"] - <-Map 10 [CONTAINS] llap - Reduce Output Operator [RS_10] - PartitionCols:_col0, _col1 - Group By Operator [GBY_9] (rows=262 width=178) - Output:["_col0","_col1"],keys:_col1, _col0 - Select Operator [SEL_5] (rows=500 width=178) - Output:["_col0","_col1"] - Filter Operator [FIL_151] (rows=500 width=178) - predicate:value is not null - TableScan [TS_3] (rows=500 width=178) - Output:["key","value"] + Merge Join Operator [MERGEJOIN_163] (rows=48 width=177) + Conds:RS_58._col3=RS_59._col1(Inner),Output:["_col1","_col2"] + <-Reducer 21 [SIMPLE_EDGE] llap + SHUFFLE [RS_59] + PartitionCols:_col1 + Select Operator [SEL_54] (rows=381 width=178) + Output:["_col1"] + Group By Operator [GBY_53] (rows=381 width=178) + Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 + <-Union 20 [SIMPLE_EDGE] + <-Map 23 [CONTAINS] llap + Reduce Output Operator [RS_52] + PartitionCols:_col0, _col1 + Group By Operator [GBY_51] (rows=381 width=178) + Output:["_col0","_col1"],keys:_col1, _col0 + Select Operator [SEL_47] (rows=500 width=178) + Output:["_col0","_col1"] + Filter Operator [FIL_152] (rows=500 width=178) + predicate:value is not null + TableScan [TS_45] (rows=500 width=178) + Output:["key","value"] + <-Reducer 19 [CONTAINS] llap + Reduce Output Operator [RS_52] + PartitionCols:_col0, _col1 + Group By Operator [GBY_51] (rows=381 width=178) + Output:["_col0","_col1"],keys:_col1, _col0 + Select Operator [SEL_44] (rows=262 width=178) + Output:["_col0","_col1"] + Group By Operator [GBY_43] (rows=262 width=178) + Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 + <-Union 18 [SIMPLE_EDGE] + <-Map 17 [CONTAINS] llap + Reduce Output Operator [RS_42] + PartitionCols:_col0, _col1 + Group By Operator [GBY_41] (rows=262 width=178) + Output:["_col0","_col1"],keys:_col1, _col0 + Select Operator [SEL_34] (rows=25 width=175) + Output:["_col0","_col1"] + Filter Operator [FIL_150] (rows=25 width=175) + predicate:value is not null + TableScan [TS_32] (rows=25 width=175) + Output:["key","value"] + <-Map 22 [CONTAINS] llap + Reduce Output Operator [RS_42] + PartitionCols:_col0, _col1 + Group By Operator [GBY_41] (rows=262 width=178) + Output:["_col0","_col1"],keys:_col1, _col0 + Select Operator [SEL_37] (rows=500 width=178) + Output:["_col0","_col1"] + Filter Operator [FIL_151] (rows=500 width=178) + predicate:value is not null + TableScan [TS_35] (rows=500 width=178) + Output:["key","value"] + <-Reducer 8 [SIMPLE_EDGE] llap + SHUFFLE [RS_58] + PartitionCols:_col3 + Merge Join Operator [MERGEJOIN_160] (rows=39 width=266) + Conds:RS_55._col0=RS_56._col0(Inner),Output:["_col1","_col2","_col3"] + <-Map 1 [SIMPLE_EDGE] llap + SHUFFLE [RS_55] + PartitionCols:_col0 + Please refer to the previous Select Operator [SEL_2] + <-Map 12 [SIMPLE_EDGE] llap + SHUFFLE [RS_56] + PartitionCols:_col0 + Please refer to the previous Select Operator [SEL_5] PREHOOK: query: EXPLAIN SELECT x.key, z.value, y.value @@ -1133,135 +1123,132 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Map 1 <- Union 2 (CONTAINS) -Map 12 <- Union 10 (CONTAINS) -Map 6 <- Union 2 (CONTAINS) -Map 9 <- Union 10 (CONTAINS) -Reducer 11 <- Map 13 (BROADCAST_EDGE), Map 14 (BROADCAST_EDGE), Union 10 (SIMPLE_EDGE), Union 4 (CONTAINS) -Reducer 3 <- Map 7 (BROADCAST_EDGE), Map 8 (BROADCAST_EDGE), Union 2 (SIMPLE_EDGE), Union 4 (CONTAINS) -Reducer 5 <- Union 4 (SIMPLE_EDGE) +Map 1 <- Map 2 (BROADCAST_EDGE) +Map 10 <- Union 11 (CONTAINS) +Map 13 <- Union 11 (CONTAINS) +Map 3 <- Union 4 (CONTAINS) +Map 8 <- Union 4 (CONTAINS) +Map 9 <- Map 2 (BROADCAST_EDGE) +Reducer 12 <- Map 9 (BROADCAST_EDGE), Union 11 (SIMPLE_EDGE), Union 6 (CONTAINS) +Reducer 5 <- Map 1 (BROADCAST_EDGE), Union 4 (SIMPLE_EDGE), Union 6 (CONTAINS) +Reducer 7 <- Union 6 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 - Reducer 5 llap + Reducer 7 llap File Output Operator [FS_59] - Group By Operator [GBY_57] (rows=550 width=10) + Group By Operator [GBY_57] (rows=605 width=10) Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 - <-Union 4 [SIMPLE_EDGE] - <-Reducer 11 [CONTAINS] llap + <-Union 6 [SIMPLE_EDGE] + <-Reducer 12 [CONTAINS] llap Reduce Output Operator [RS_56] PartitionCols:_col0, _col1 - Group By Operator [GBY_55] (rows=1100 width=10) + Group By Operator [GBY_55] (rows=1210 width=10) Output:["_col0","_col1"],keys:_col0, _col1 - Select Operator [SEL_51] (rows=550 width=10) + Select Operator [SEL_51] (rows=605 width=10) Output:["_col0","_col1"] - Map Join Operator [MAPJOIN_85] (rows=550 width=10) - Conds:MAPJOIN_84._col2=RS_49._col0(Inner),Output:["_col1","_col2"] - <-Map 14 [BROADCAST_EDGE] llap - BROADCAST [RS_49] - PartitionCols:_col0 - Select Operator [SEL_44] (rows=500 width=10) - Output:["_col0"] - Filter Operator [FIL_81] (rows=500 width=10) - predicate:key is not null - TableScan [TS_42] (rows=500 width=10) - default@src,y,Tbl:COMPLETE,Col:NONE,Output:["key"] - <-Map Join Operator [MAPJOIN_84] (rows=288 width=10) - Conds:SEL_38._col1=RS_46._col1(Inner),Output:["_col1","_col2"] - <-Map 13 [BROADCAST_EDGE] llap - BROADCAST [RS_46] - PartitionCols:_col1 - Select Operator [SEL_41] (rows=25 width=7) - Output:["_col0","_col1"] - Filter Operator [FIL_80] (rows=25 width=7) - predicate:(key is not null and value is not null) - TableScan [TS_39] (rows=25 width=7) - default@src1,x,Tbl:COMPLETE,Col:NONE,Output:["key","value"] - <-Select Operator [SEL_38] (rows=262 width=10) - Output:["_col1"] - Group By Operator [GBY_37] (rows=262 width=10) - Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 - <-Union 10 [SIMPLE_EDGE] - <-Map 12 [CONTAINS] llap - Reduce Output Operator [RS_36] - PartitionCols:_col0, _col1 - Group By Operator [GBY_35] (rows=525 width=10) - Output:["_col0","_col1"],keys:_col1, _col0 - Select Operator [SEL_31] (rows=500 width=10) - Output:["_col0","_col1"] - Filter Operator [FIL_79] (rows=500 width=10) - predicate:value is not null - TableScan [TS_29] (rows=500 width=10) - Output:["key","value"] - <-Map 9 [CONTAINS] llap - Reduce Output Operator [RS_36] - PartitionCols:_col0, _col1 - Group By Operator [GBY_35] (rows=525 width=10) - Output:["_col0","_col1"],keys:_col1, _col0 - Select Operator [SEL_28] (rows=25 width=7) - Output:["_col0","_col1"] - Filter Operator [FIL_78] (rows=25 width=7) - predicate:value is not null - TableScan [TS_26] (rows=25 width=7) - Output:["key","value"] - <-Reducer 3 [CONTAINS] llap + Map Join Operator [MAPJOIN_83] (rows=605 width=10) + Conds:RS_48._col2=SEL_44._col1(Inner),Output:["_col1","_col4"] + <-Map 9 [BROADCAST_EDGE] llap + BROADCAST [RS_48] + PartitionCols:_col2 + Map Join Operator [MAPJOIN_81] (rows=550 width=10) + Conds:SEL_28._col0=RS_46._col0(Inner),Output:["_col1","_col2"] + <-Map 2 [BROADCAST_EDGE] llap + BROADCAST [RS_46] + PartitionCols:_col0 + Select Operator [SEL_5] (rows=25 width=7) + Output:["_col0","_col1"] + Filter Operator [FIL_73] (rows=25 width=7) + predicate:(key is not null and value is not null) + TableScan [TS_3] (rows=25 width=7) + default@src1,x,Tbl:COMPLETE,Col:NONE,Output:["key","value"] + <-Select Operator [SEL_28] (rows=500 width=10) + Output:["_col0"] + Filter Operator [FIL_76] (rows=500 width=10) + predicate:key is not null + TableScan [TS_26] (rows=500 width=10) + default@src,y,Tbl:COMPLETE,Col:NONE,Output:["key"] + <-Select Operator [SEL_44] (rows=262 width=10) + Output:["_col1"] + Group By Operator [GBY_43] (rows=262 width=10) + Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 + <-Union 11 [SIMPLE_EDGE] + <-Map 10 [CONTAINS] llap + Reduce Output Operator [RS_42] + PartitionCols:_col0, _col1 + Group By Operator [GBY_41] (rows=525 width=10) + Output:["_col0","_col1"],keys:_col1, _col0 + Select Operator [SEL_34] (rows=25 width=7) + Output:["_col0","_col1"] + Filter Operator [FIL_78] (rows=25 width=7) + predicate:value is not null + TableScan [TS_32] (rows=25 width=7) + Output:["key","value"] + <-Map 13 [CONTAINS] llap + Reduce Output Operator [RS_42] + PartitionCols:_col0, _col1 + Group By Operator [GBY_41] (rows=525 width=10) + Output:["_col0","_col1"],keys:_col1, _col0 + Select Operator [SEL_37] (rows=500 width=10) + Output:["_col0","_col1"] + Filter Operator [FIL_79] (rows=500 width=10) + predicate:value is not null + TableScan [TS_35] (rows=500 width=10) + Output:["key","value"] + <-Reducer 5 [CONTAINS] llap Reduce Output Operator [RS_56] PartitionCols:_col0, _col1 - Group By Operator [GBY_55] (rows=1100 width=10) + Group By Operator [GBY_55] (rows=1210 width=10) Output:["_col0","_col1"],keys:_col0, _col1 - Select Operator [SEL_25] (rows=550 width=10) + Select Operator [SEL_25] (rows=605 width=10) Output:["_col0","_col1"] - Map Join Operator [MAPJOIN_83] (rows=550 width=10) - Conds:MAPJOIN_82._col2=RS_23._col0(Inner),Output:["_col1","_col2"] - <-Map 8 [BROADCAST_EDGE] llap - BROADCAST [RS_23] - PartitionCols:_col0 - Select Operator [SEL_18] (rows=500 width=10) - Output:["_col0"] - Filter Operator [FIL_77] (rows=500 width=10) - predicate:key is not null - TableScan [TS_16] (rows=500 width=10) - default@src,y,Tbl:COMPLETE,Col:NONE,Output:["key"] - <-Map Join Operator [MAPJOIN_82] (rows=288 width=10) - Conds:SEL_12._col1=RS_20._col1(Inner),Output:["_col1","_col2"] - <-Map 7 [BROADCAST_EDGE] llap - BROADCAST [RS_20] - PartitionCols:_col1 - Select Operator [SEL_15] (rows=25 width=7) - Output:["_col0","_col1"] - Filter Operator [FIL_76] (rows=25 width=7) - predicate:(key is not null and value is not null) - TableScan [TS_13] (rows=25 width=7) - default@src1,x,Tbl:COMPLETE,Col:NONE,Output:["key","value"] - <-Select Operator [SEL_12] (rows=262 width=10) - Output:["_col1"] - Group By Operator [GBY_11] (rows=262 width=10) - Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 - <-Union 2 [SIMPLE_EDGE] - <-Map 1 [CONTAINS] llap - Reduce Output Operator [RS_10] - PartitionCols:_col0, _col1 - Group By Operator [GBY_9] (rows=525 width=10) - Output:["_col0","_col1"],keys:_col1, _col0 - Select Operator [SEL_2] (rows=25 width=7) - Output:["_col0","_col1"] - Filter Operator [FIL_74] (rows=25 width=7) - predicate:value is not null - TableScan [TS_0] (rows=25 width=7) - Output:["key","value"] - <-Map 6 [CONTAINS] llap - Reduce Output Operator [RS_10] - PartitionCols:_col0, _col1 - Group By Operator [GBY_9] (rows=525 width=10) - Output:["_col0","_col1"],keys:_col1, _col0 - Select Operator [SEL_5] (rows=500 width=10) - Output:["_col0","_col1"] - Filter Operator [FIL_75] (rows=500 width=10) - predicate:value is not null - TableScan [TS_3] (rows=500 width=10) - Output:["key","value"] + Map Join Operator [MAPJOIN_82] (rows=605 width=10) + Conds:RS_22._col2=SEL_18._col1(Inner),Output:["_col1","_col4"] + <-Map 1 [BROADCAST_EDGE] llap + BROADCAST [RS_22] + PartitionCols:_col2 + Map Join Operator [MAPJOIN_80] (rows=550 width=10) + Conds:SEL_2._col0=RS_20._col0(Inner),Output:["_col1","_col2"] + <-Map 2 [BROADCAST_EDGE] llap + BROADCAST [RS_20] + PartitionCols:_col0 + Please refer to the previous Select Operator [SEL_5] + <-Select Operator [SEL_2] (rows=500 width=10) + Output:["_col0"] + Filter Operator [FIL_72] (rows=500 width=10) + predicate:key is not null + TableScan [TS_0] (rows=500 width=10) + default@src,y,Tbl:COMPLETE,Col:NONE,Output:["key"] + <-Select Operator [SEL_18] (rows=262 width=10) + Output:["_col1"] + Group By Operator [GBY_17] (rows=262 width=10) + Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 + <-Union 4 [SIMPLE_EDGE] + <-Map 3 [CONTAINS] llap + Reduce Output Operator [RS_16] + PartitionCols:_col0, _col1 + Group By Operator [GBY_15] (rows=525 width=10) + Output:["_col0","_col1"],keys:_col1, _col0 + Select Operator [SEL_8] (rows=25 width=7) + Output:["_col0","_col1"] + Filter Operator [FIL_74] (rows=25 width=7) + predicate:value is not null + TableScan [TS_6] (rows=25 width=7) + Output:["key","value"] + <-Map 8 [CONTAINS] llap + Reduce Output Operator [RS_16] + PartitionCols:_col0, _col1 + Group By Operator [GBY_15] (rows=525 width=10) + Output:["_col0","_col1"],keys:_col1, _col0 + Select Operator [SEL_11] (rows=500 width=10) + Output:["_col0","_col1"] + Filter Operator [FIL_75] (rows=500 width=10) + predicate:value is not null + TableScan [TS_9] (rows=500 width=10) + Output:["key","value"] PREHOOK: query: explain SELECT x.key, y.value @@ -1292,262 +1279,253 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Map 1 <- Union 2 (CONTAINS) -Map 11 <- Union 12 (CONTAINS) -Map 16 <- Union 12 (CONTAINS) -Map 17 <- Union 14 (CONTAINS) -Map 20 <- Union 21 (CONTAINS) -Map 27 <- Union 21 (CONTAINS) -Map 28 <- Union 23 (CONTAINS) -Map 29 <- Union 25 (CONTAINS) -Map 8 <- Union 2 (CONTAINS) -Reducer 13 <- Union 12 (SIMPLE_EDGE), Union 14 (CONTAINS) -Reducer 15 <- Map 18 (BROADCAST_EDGE), Map 19 (BROADCAST_EDGE), Union 14 (SIMPLE_EDGE), Union 4 (CONTAINS) -Reducer 22 <- Union 21 (SIMPLE_EDGE), Union 23 (CONTAINS) -Reducer 24 <- Union 23 (SIMPLE_EDGE), Union 25 (CONTAINS) -Reducer 26 <- Map 10 (BROADCAST_EDGE), Map 9 (BROADCAST_EDGE), Union 25 (SIMPLE_EDGE), Union 6 (CONTAINS) -Reducer 3 <- Map 10 (BROADCAST_EDGE), Map 9 (BROADCAST_EDGE), Union 2 (SIMPLE_EDGE), Union 4 (CONTAINS) -Reducer 5 <- Union 4 (SIMPLE_EDGE), Union 6 (CONTAINS) -Reducer 7 <- Union 6 (SIMPLE_EDGE) +Map 1 <- Map 2 (BROADCAST_EDGE) +Map 10 <- Union 4 (CONTAINS) +Map 11 <- Map 2 (BROADCAST_EDGE) +Map 12 <- Union 13 (CONTAINS) +Map 17 <- Union 13 (CONTAINS) +Map 18 <- Union 15 (CONTAINS) +Map 19 <- Union 20 (CONTAINS) +Map 26 <- Union 20 (CONTAINS) +Map 27 <- Union 22 (CONTAINS) +Map 28 <- Union 24 (CONTAINS) +Map 3 <- Union 4 (CONTAINS) +Reducer 14 <- Union 13 (SIMPLE_EDGE), Union 15 (CONTAINS) +Reducer 16 <- Map 11 (BROADCAST_EDGE), Union 15 (SIMPLE_EDGE), Union 6 (CONTAINS) +Reducer 21 <- Union 20 (SIMPLE_EDGE), Union 22 (CONTAINS) +Reducer 23 <- Union 22 (SIMPLE_EDGE), Union 24 (CONTAINS) +Reducer 25 <- Map 1 (BROADCAST_EDGE), Union 24 (SIMPLE_EDGE), Union 8 (CONTAINS) +Reducer 5 <- Map 1 (BROADCAST_EDGE), Union 4 (SIMPLE_EDGE), Union 6 (CONTAINS) +Reducer 7 <- Union 6 (SIMPLE_EDGE), Union 8 (CONTAINS) +Reducer 9 <- Union 8 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 - Reducer 7 llap + Reducer 9 llap File Output Operator [FS_122] - Group By Operator [GBY_120] (rows=550 width=10) + Group By Operator [GBY_120] (rows=605 width=10) Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 - <-Union 6 [SIMPLE_EDGE] - <-Reducer 26 [CONTAINS] llap + <-Union 8 [SIMPLE_EDGE] + <-Reducer 25 [CONTAINS] llap Reduce Output Operator [RS_119] PartitionCols:_col0, _col1 - Group By Operator [GBY_118] (rows=1100 width=10) + Group By Operator [GBY_118] (rows=1210 width=10) Output:["_col0","_col1"],keys:_col0, _col1 - Select Operator [SEL_114] (rows=550 width=10) + Select Operator [SEL_114] (rows=605 width=10) Output:["_col0","_col1"] - Map Join Operator [MAPJOIN_170] (rows=550 width=10) - Conds:MAPJOIN_169._col2=RS_112._col0(Inner),Output:["_col2","_col5"] - <-Map 10 [BROADCAST_EDGE] llap - BROADCAST [RS_112] - PartitionCols:_col0 - Select Operator [SEL_18] (rows=500 width=10) - Output:["_col0","_col1"] - Filter Operator [FIL_153] (rows=500 width=10) - predicate:key is not null - TableScan [TS_16] (rows=500 width=10) - default@src,y,Tbl:COMPLETE,Col:NONE,Output:["key","value"] - <-Map Join Operator [MAPJOIN_169] (rows=484 width=10) - Conds:SEL_101._col1=RS_109._col1(Inner),Output:["_col2"] - <-Map 9 [BROADCAST_EDGE] llap - BROADCAST [RS_109] - PartitionCols:_col1 - Select Operator [SEL_15] (rows=25 width=7) - Output:["_col0","_col1"] - Filter Operator [FIL_152] (rows=25 width=7) - predicate:(key is not null and value is not null) - TableScan [TS_13] (rows=25 width=7) - default@src1,x,Tbl:COMPLETE,Col:NONE,Output:["key","value"] - <-Select Operator [SEL_101] (rows=440 width=10) - Output:["_col1"] - Group By Operator [GBY_100] (rows=440 width=10) - Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 - <-Union 25 [SIMPLE_EDGE] - <-Map 29 [CONTAINS] llap - Reduce Output Operator [RS_99] - PartitionCols:_col0, _col1 - Group By Operator [GBY_98] (rows=881 width=10) - Output:["_col0","_col1"],keys:_col1, _col0 - Select Operator [SEL_94] (rows=500 width=10) - Output:["_col0","_col1"] - Filter Operator [FIL_162] (rows=500 width=10) - predicate:value is not null - TableScan [TS_92] (rows=500 width=10) - Output:["key","value"] - <-Reducer 24 [CONTAINS] llap - Reduce Output Operator [RS_99] - PartitionCols:_col0, _col1 - Group By Operator [GBY_98] (rows=881 width=10) - Output:["_col0","_col1"],keys:_col1, _col0 - Select Operator [SEL_91] (rows=381 width=10) - Output:["_col0","_col1"] - Group By Operator [GBY_90] (rows=381 width=10) - Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 - <-Union 23 [SIMPLE_EDGE] - <-Map 28 [CONTAINS] llap - Reduce Output Operator [RS_89] - PartitionCols:_col0, _col1 - Group By Operator [GBY_88] (rows=762 width=10) - Output:["_col0","_col1"],keys:_col1, _col0 - Select Operator [SEL_84] (rows=500 width=10) - Output:["_col0","_col1"] - Filter Operator [FIL_161] (rows=500 width=10) - predicate:value is not null - TableScan [TS_82] (rows=500 width=10) - Output:["key","value"] - <-Reducer 22 [CONTAINS] llap - Reduce Output Operator [RS_89] - PartitionCols:_col0, _col1 - Group By Operator [GBY_88] (rows=762 width=10) - Output:["_col0","_col1"],keys:_col1, _col0 - Select Operator [SEL_81] (rows=262 width=10) - Output:["_col0","_col1"] - Group By Operator [GBY_80] (rows=262 width=10) - Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 - <-Union 21 [SIMPLE_EDGE] - <-Map 20 [CONTAINS] llap - Reduce Output Operator [RS_79] - PartitionCols:_col0, _col1 - Group By Operator [GBY_78] (rows=525 width=10) - Output:["_col0","_col1"],keys:_col1, _col0 - Select Operator [SEL_71] (rows=25 width=7) - Output:["_col0","_col1"] - Filter Operator [FIL_159] (rows=25 width=7) - predicate:value is not null - TableScan [TS_69] (rows=25 width=7) - Output:["key","value"] - <-Map 27 [CONTAINS] llap - Reduce Output Operator [RS_79] - PartitionCols:_col0, _col1 - Group By Operator [GBY_78] (rows=525 width=10) - Output:["_col0","_col1"],keys:_col1, _col0 - Select Operator [SEL_74] (rows=500 width=10) - Output:["_col0","_col1"] - Filter Operator [FIL_160] (rows=500 width=10) - predicate:value is not null - TableScan [TS_72] (rows=500 width=10) - Output:["key","value"] - <-Reducer 5 [CONTAINS] llap - Reduce Output Operator [RS_119] - PartitionCols:_col0, _col1 - Group By Operator [GBY_118] (rows=1100 width=10) - Output:["_col0","_col1"],keys:_col0, _col1 - Group By Operator [GBY_67] (rows=550 width=10) - Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 - <-Union 4 [SIMPLE_EDGE] - <-Reducer 15 [CONTAINS] llap - Reduce Output Operator [RS_66] - PartitionCols:_col0, _col1 - Group By Operator [GBY_65] (rows=1100 width=10) - Output:["_col0","_col1"],keys:_col0, _col1 - Select Operator [SEL_61] (rows=550 width=10) + Map Join Operator [MAPJOIN_164] (rows=605 width=10) + Conds:RS_111._col3=SEL_107._col1(Inner),Output:["_col1","_col2"] + <-Map 1 [BROADCAST_EDGE] llap + BROADCAST [RS_111] + PartitionCols:_col3 + Map Join Operator [MAPJOIN_159] (rows=550 width=10) + Conds:SEL_2._col0=RS_20._col0(Inner),Output:["_col1","_col2","_col3"] + <-Map 2 [BROADCAST_EDGE] llap + BROADCAST [RS_20] + PartitionCols:_col0 + Select Operator [SEL_5] (rows=25 width=7) + Output:["_col0","_col1"] + Filter Operator [FIL_145] (rows=25 width=7) + predicate:(key is not null and value is not null) + TableScan [TS_3] (rows=25 width=7) + default@src1,x,Tbl:COMPLETE,Col:NONE,Output:["key","value"] + <-Select Operator [SEL_2] (rows=500 width=10) Output:["_col0","_col1"] - Map Join Operator [MAPJOIN_168] (rows=550 width=10) - Conds:MAPJOIN_167._col2=RS_59._col0(Inner),Output:["_col2","_col5"] - <-Map 19 [BROADCAST_EDGE] llap - BROADCAST [RS_59] - PartitionCols:_col0 - Select Operator [SEL_54] (rows=500 width=10) + Filter Operator [FIL_144] (rows=500 width=10) + predicate:key is not null + TableScan [TS_0] (rows=500 width=10) + default@src,y,Tbl:COMPLETE,Col:NONE,Output:["key","value"] + <-Select Operator [SEL_107] (rows=440 width=10) + Output:["_col1"] + Group By Operator [GBY_106] (rows=440 width=10) + Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 + <-Union 24 [SIMPLE_EDGE] + <-Map 28 [CONTAINS] llap + Reduce Output Operator [RS_105] + PartitionCols:_col0, _col1 + Group By Operator [GBY_104] (rows=881 width=10) + Output:["_col0","_col1"],keys:_col1, _col0 + Select Operator [SEL_100] (rows=500 width=10) Output:["_col0","_col1"] Filter Operator [FIL_158] (rows=500 width=10) - predicate:key is not null - TableScan [TS_52] (rows=500 width=10) - default@src,y,Tbl:COMPLETE,Col:NONE,Output:["key","value"] - <-Map Join Operator [MAPJOIN_167] (rows=419 width=10) - Conds:SEL_48._col1=RS_56._col1(Inner),Output:["_col2"] - <-Map 18 [BROADCAST_EDGE] llap - BROADCAST [RS_56] - PartitionCols:_col1 - Select Operator [SEL_51] (rows=25 width=7) - Output:["_col0","_col1"] - Filter Operator [FIL_157] (rows=25 width=7) - predicate:(key is not null and value is not null) - TableScan [TS_49] (rows=25 width=7) - default@src1,x,Tbl:COMPLETE,Col:NONE,Output:["key","value"] - <-Select Operator [SEL_48] (rows=381 width=10) - Output:["_col1"] - Group By Operator [GBY_47] (rows=381 width=10) + predicate:value is not null + TableScan [TS_98] (rows=500 width=10) + Output:["key","value"] + <-Reducer 23 [CONTAINS] llap + Reduce Output Operator [RS_105] + PartitionCols:_col0, _col1 + Group By Operator [GBY_104] (rows=881 width=10) + Output:["_col0","_col1"],keys:_col1, _col0 + Select Operator [SEL_97] (rows=381 width=10) + Output:["_col0","_col1"] + Group By Operator [GBY_96] (rows=381 width=10) Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 - <-Union 14 [SIMPLE_EDGE] - <-Map 17 [CONTAINS] llap - Reduce Output Operator [RS_46] + <-Union 22 [SIMPLE_EDGE] + <-Map 27 [CONTAINS] llap + Reduce Output Operator [RS_95] PartitionCols:_col0, _col1 - Group By Operator [GBY_45] (rows=762 width=10) + Group By Operator [GBY_94] (rows=762 width=10) Output:["_col0","_col1"],keys:_col1, _col0 - Select Operator [SEL_41] (rows=500 width=10) + Select Operator [SEL_90] (rows=500 width=10) Output:["_col0","_col1"] - Filter Operator [FIL_156] (rows=500 width=10) + Filter Operator [FIL_157] (rows=500 width=10) predicate:value is not null - TableScan [TS_39] (rows=500 width=10) + TableScan [TS_88] (rows=500 width=10) Output:["key","value"] - <-Reducer 13 [CONTAINS] llap - Reduce Output Operator [RS_46] + <-Reducer 21 [CONTAINS] llap + Reduce Output Operator [RS_95] PartitionCols:_col0, _col1 - Group By Operator [GBY_45] (rows=762 width=10) + Group By Operator [GBY_94] (rows=762 width=10) Output:["_col0","_col1"],keys:_col1, _col0 - Select Operator [SEL_38] (rows=262 width=10) + Select Operator [SEL_87] (rows=262 width=10) Output:["_col0","_col1"] - Group By Operator [GBY_37] (rows=262 width=10) + Group By Operator [GBY_86] (rows=262 width=10) Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 - <-Union 12 [SIMPLE_EDGE] - <-Map 11 [CONTAINS] llap - Reduce Output Operator [RS_36] + <-Union 20 [SIMPLE_EDGE] + <-Map 19 [CONTAINS] llap + Reduce Output Operator [RS_85] PartitionCols:_col0, _col1 - Group By Operator [GBY_35] (rows=525 width=10) + Group By Operator [GBY_84] (rows=525 width=10) Output:["_col0","_col1"],keys:_col1, _col0 - Select Operator [SEL_28] (rows=25 width=7) + Select Operator [SEL_77] (rows=25 width=7) Output:["_col0","_col1"] - Filter Operator [FIL_154] (rows=25 width=7) + Filter Operator [FIL_155] (rows=25 width=7) predicate:value is not null - TableScan [TS_26] (rows=25 width=7) + TableScan [TS_75] (rows=25 width=7) Output:["key","value"] - <-Map 16 [CONTAINS] llap - Reduce Output Operator [RS_36] + <-Map 26 [CONTAINS] llap + Reduce Output Operator [RS_85] PartitionCols:_col0, _col1 - Group By Operator [GBY_35] (rows=525 width=10) + Group By Operator [GBY_84] (rows=525 width=10) Output:["_col0","_col1"],keys:_col1, _col0 - Select Operator [SEL_31] (rows=500 width=10) + Select Operator [SEL_80] (rows=500 width=10) Output:["_col0","_col1"] - Filter Operator [FIL_155] (rows=500 width=10) + Filter Operator [FIL_156] (rows=500 width=10) predicate:value is not null - TableScan [TS_29] (rows=500 width=10) + TableScan [TS_78] (rows=500 width=10) Output:["key","value"] - <-Reducer 3 [CONTAINS] llap + <-Reducer 7 [CONTAINS] llap + Reduce Output Operator [RS_119] + PartitionCols:_col0, _col1 + Group By Operator [GBY_118] (rows=1210 width=10) + Output:["_col0","_col1"],keys:_col0, _col1 + Group By Operator [GBY_67] (rows=605 width=10) + Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 + <-Union 6 [SIMPLE_EDGE] + <-Reducer 16 [CONTAINS] llap Reduce Output Operator [RS_66] PartitionCols:_col0, _col1 - Group By Operator [GBY_65] (rows=1100 width=10) + Group By Operator [GBY_65] (rows=1210 width=10) Output:["_col0","_col1"],keys:_col0, _col1 - Select Operator [SEL_25] (rows=550 width=10) + Select Operator [SEL_61] (rows=605 width=10) Output:["_col0","_col1"] - Map Join Operator [MAPJOIN_166] (rows=550 width=10) - Conds:MAPJOIN_165._col2=RS_23._col0(Inner),Output:["_col2","_col5"] - <-Map 10 [BROADCAST_EDGE] llap - BROADCAST [RS_23] - PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_18] - <-Map Join Operator [MAPJOIN_165] (rows=288 width=10) - Conds:SEL_12._col1=RS_20._col1(Inner),Output:["_col2"] - <-Map 9 [BROADCAST_EDGE] llap - BROADCAST [RS_20] - PartitionCols:_col1 - Please refer to the previous Select Operator [SEL_15] - <-Select Operator [SEL_12] (rows=262 width=10) - Output:["_col1"] - Group By Operator [GBY_11] (rows=262 width=10) - Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 - <-Union 2 [SIMPLE_EDGE] - <-Map 1 [CONTAINS] llap - Reduce Output Operator [RS_10] - PartitionCols:_col0, _col1 - Group By Operator [GBY_9] (rows=525 width=10) - Output:["_col0","_col1"],keys:_col1, _col0 - Select Operator [SEL_2] (rows=25 width=7) - Output:["_col0","_col1"] - Filter Operator [FIL_150] (rows=25 width=7) - predicate:value is not null - TableScan [TS_0] (rows=25 width=7) - Output:["key","value"] - <-Map 8 [CONTAINS] llap - Reduce Output Operator [RS_10] - PartitionCols:_col0, _col1 - Group By Operator [GBY_9] (rows=525 width=10) - Output:["_col0","_col1"],keys:_col1, _col0 - Select Operator [SEL_5] (rows=500 width=10) - Output:["_col0","_col1"] - Filter Operator [FIL_151] (rows=500 width=10) - predicate:value is not null - TableScan [TS_3] (rows=500 width=10) - Output:["key","value"] + Map Join Operator [MAPJOIN_163] (rows=605 width=10) + Conds:RS_58._col3=SEL_54._col1(Inner),Output:["_col1","_col2"] + <-Map 11 [BROADCAST_EDGE] llap + BROADCAST [RS_58] + PartitionCols:_col3 + Map Join Operator [MAPJOIN_160] (rows=550 width=10) + Conds:SEL_28._col0=RS_56._col0(Inner),Output:["_col1","_col2","_col3"] + <-Map 2 [BROADCAST_EDGE] llap + BROADCAST [RS_56] + PartitionCols:_col0 + Please refer to the previous Select Operator [SEL_5] + <-Select Operator [SEL_28] (rows=500 width=10) + Output:["_col0","_col1"] + Filter Operator [FIL_148] (rows=500 width=10) + predicate:key is not null + TableScan [TS_26] (rows=500 width=10) + default@src,y,Tbl:COMPLETE,Col:NONE,Output:["key","value"] + <-Select Operator [SEL_54] (rows=381 width=10) + Output:["_col1"] + Group By Operator [GBY_53] (rows=381 width=10) + Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 + <-Union 15 [SIMPLE_EDGE] + <-Map 18 [CONTAINS] llap + Reduce Output Operator [RS_52] + PartitionCols:_col0, _col1 + Group By Operator [GBY_51] (rows=762 width=10) + Output:["_col0","_col1"],keys:_col1, _col0 + Select Operator [SEL_47] (rows=500 width=10) + Output:["_col0","_col1"] + Filter Operator [FIL_152] (rows=500 width=10) + predicate:value is not null + TableScan [TS_45] (rows=500 width=10) + Output:["key","value"] + <-Reducer 14 [CONTAINS] llap + Reduce Output Operator [RS_52] + PartitionCols:_col0, _col1 + Group By Operator [GBY_51] (rows=762 width=10) + Output:["_col0","_col1"],keys:_col1, _col0 + Select Operator [SEL_44] (rows=262 width=10) + Output:["_col0","_col1"] + Group By Operator [GBY_43] (rows=262 width=10) + Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 + <-Union 13 [SIMPLE_EDGE] + <-Map 12 [CONTAINS] llap + Reduce Output Operator [RS_42] + PartitionCols:_col0, _col1 + Group By Operator [GBY_41] (rows=525 width=10) + Output:["_col0","_col1"],keys:_col1, _col0 + Select Operator [SEL_34] (rows=25 width=7) + Output:["_col0","_col1"] + Filter Operator [FIL_150] (rows=25 width=7) + predicate:value is not null + TableScan [TS_32] (rows=25 width=7) + Output:["key","value"] + <-Map 17 [CONTAINS] llap + Reduce Output Operator [RS_42] + PartitionCols:_col0, _col1 + Group By Operator [GBY_41] (rows=525 width=10) + Output:["_col0","_col1"],keys:_col1, _col0 + Select Operator [SEL_37] (rows=500 width=10) + Output:["_col0","_col1"] + Filter Operator [FIL_151] (rows=500 width=10) + predicate:value is not null + TableScan [TS_35] (rows=500 width=10) + Output:["key","value"] + <-Reducer 5 [CONTAINS] llap + Reduce Output Operator [RS_66] + PartitionCols:_col0, _col1 + Group By Operator [GBY_65] (rows=1210 width=10) + Output:["_col0","_col1"],keys:_col0, _col1 + Select Operator [SEL_25] (rows=605 width=10) + Output:["_col0","_col1"] + Map Join Operator [MAPJOIN_162] (rows=605 width=10) + Conds:RS_22._col3=SEL_18._col1(Inner),Output:["_col1","_col2"] + <-Map 1 [BROADCAST_EDGE] llap + BROADCAST [RS_22] + PartitionCols:_col3 + Please refer to the previous Map Join Operator [MAPJOIN_159] + <-Select Operator [SEL_18] (rows=262 width=10) + Output:["_col1"] + Group By Operator [GBY_17] (rows=262 width=10) + Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 + <-Union 4 [SIMPLE_EDGE] + <-Map 10 [CONTAINS] llap + Reduce Output Operator [RS_16] + PartitionCols:_col0, _col1 + Group By Operator [GBY_15] (rows=525 width=10) + Output:["_col0","_col1"],keys:_col1, _col0 + Select Operator [SEL_11] (rows=500 width=10) + Output:["_col0","_col1"] + Filter Operator [FIL_147] (rows=500 width=10) + predicate:value is not null + TableScan [TS_9] (rows=500 width=10) + Output:["key","value"] + <-Map 3 [CONTAINS] llap + Reduce Output Operator [RS_16] + PartitionCols:_col0, _col1 + Group By Operator [GBY_15] (rows=525 width=10) + Output:["_col0","_col1"],keys:_col1, _col0 + Select Operator [SEL_8] (rows=25 width=7) + Output:["_col0","_col1"] + Filter Operator [FIL_146] (rows=25 width=7) + predicate:value is not null + TableScan [TS_6] (rows=25 width=7) + Output:["key","value"] PREHOOK: query: CREATE TABLE srcbucket_mapjoin(key int, value string) partitioned by (ds string) CLUSTERED BY (key) INTO 2 BUCKETS STORED AS TEXTFILE PREHOOK: type: CREATETABLE @@ -2016,54 +1994,55 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Map 1 <- Map 6 (BROADCAST_EDGE), Union 2 (CONTAINS) -Map 10 <- Union 11 (CONTAINS) -Map 12 <- Union 11 (CONTAINS) -Map 13 <- Union 11 (CONTAINS) -Map 16 <- Map 6 (BROADCAST_EDGE), Union 4 (CONTAINS) -Map 17 <- Map 6 (BROADCAST_EDGE), Union 4 (CONTAINS) -Map 18 <- Map 6 (BROADCAST_EDGE), Union 4 (CONTAINS) -Map 19 <- Map 6 (BROADCAST_EDGE), Union 4 (CONTAINS) -Map 5 <- Map 6 (BROADCAST_EDGE), Union 2 (CONTAINS) +Map 1 <- Map 6 (BROADCAST_EDGE) +Map 11 <- Union 12 (CONTAINS) +Map 13 <- Union 12 (CONTAINS) +Map 14 <- Union 12 (CONTAINS) +Map 16 <- Map 6 (BROADCAST_EDGE), Union 3 (CONTAINS) +Map 17 <- Map 6 (BROADCAST_EDGE), Union 3 (CONTAINS) +Map 18 <- Map 6 (BROADCAST_EDGE), Union 3 (CONTAINS) +Map 19 <- Map 6 (BROADCAST_EDGE), Union 3 (CONTAINS) Map 6 <- Map 15 (BROADCAST_EDGE) -Reducer 3 <- Map 7 (SIMPLE_EDGE), Union 2 (SIMPLE_EDGE), Union 4 (CONTAINS) -Reducer 8 <- Map 7 (SIMPLE_EDGE), Union 11 (SIMPLE_EDGE) -Reducer 9 <- Map 14 (SIMPLE_EDGE), Reducer 8 (SIMPLE_EDGE), Union 4 (CONTAINS) +Map 7 <- Union 8 (CONTAINS) +Map 9 <- Union 8 (CONTAINS) +Reducer 2 <- Map 1 (SIMPLE_EDGE), Union 3 (CONTAINS), Union 8 (SIMPLE_EDGE) +Reducer 4 <- Map 1 (SIMPLE_EDGE), Map 10 (SIMPLE_EDGE) +Reducer 5 <- Reducer 4 (SIMPLE_EDGE), Union 12 (SIMPLE_EDGE), Union 3 (CONTAINS) Stage-0 Fetch Operator limit:-1 Stage-1 - Union 4 + Union 3 <-Map 16 [CONTAINS] llap File Output Operator [FS_74] Select Operator [SEL_72] (rows=1677 width=10) Output:["_col0","_col1"] - Map Join Operator [MAPJOIN_119] (rows=1677 width=10) + Map Join Operator [MAPJOIN_116] (rows=1677 width=10) Conds:RS_69._col1=SEL_54._col0(Inner),Output:["_col0","_col3"] <-Map 6 [BROADCAST_EDGE] llap BROADCAST [RS_69] PartitionCols:_col1 - Map Join Operator [MAPJOIN_118] (rows=27 width=7) - Conds:SEL_10._col0=RS_67._col0(Inner),Output:["_col0","_col1","_col3"] + Map Join Operator [MAPJOIN_113] (rows=27 width=7) + Conds:SEL_5._col0=RS_67._col0(Inner),Output:["_col0","_col1","_col3"] <-Map 15 [BROADCAST_EDGE] llap BROADCAST [RS_67] PartitionCols:_col0 Select Operator [SEL_51] (rows=25 width=7) Output:["_col0","_col1"] - Filter Operator [FIL_109] (rows=25 width=7) + Filter Operator [FIL_106] (rows=25 width=7) predicate:key is not null TableScan [TS_49] (rows=25 width=7) default@src1,y,Tbl:COMPLETE,Col:NONE,Output:["key","value"] - <-Select Operator [SEL_10] (rows=25 width=7) + <-Select Operator [SEL_5] (rows=25 width=7) Output:["_col0","_col1"] - Filter Operator [FIL_101] (rows=25 width=7) + Filter Operator [FIL_97] (rows=25 width=7) predicate:(key is not null and value is not null) - TableScan [TS_8] (rows=25 width=7) + TableScan [TS_3] (rows=25 width=7) default@src1,x,Tbl:COMPLETE,Col:NONE,Output:["key","value"] <-Select Operator [SEL_54] (rows=25 width=7) Output:["_col0"] - Filter Operator [FIL_110] (rows=25 width=7) + Filter Operator [FIL_107] (rows=25 width=7) predicate:value is not null TableScan [TS_52] (rows=25 width=7) Output:["value"] @@ -2071,15 +2050,15 @@ Stage-0 File Output Operator [FS_74] Select Operator [SEL_72] (rows=1677 width=10) Output:["_col0","_col1"] - Map Join Operator [MAPJOIN_119] (rows=1677 width=10) - Conds:RS_124._col1=SEL_57._col0(Inner),Output:["_col0","_col3"] + Map Join Operator [MAPJOIN_116] (rows=1677 width=10) + Conds:RS_120._col1=SEL_57._col0(Inner),Output:["_col0","_col3"] <-Map 6 [BROADCAST_EDGE] llap - BROADCAST [RS_124] + BROADCAST [RS_120] PartitionCols:_col1 - Please refer to the previous Map Join Operator [MAPJOIN_118] + Please refer to the previous Map Join Operator [MAPJOIN_113] <-Select Operator [SEL_57] (rows=500 width=10) Output:["_col0"] - Filter Operator [FIL_111] (rows=500 width=10) + Filter Operator [FIL_108] (rows=500 width=10) predicate:value is not null TableScan [TS_55] (rows=500 width=10) Output:["value"] @@ -2087,15 +2066,15 @@ Stage-0 File Output Operator [FS_74] Select Operator [SEL_72] (rows=1677 width=10) Output:["_col0","_col1"] - Map Join Operator [MAPJOIN_119] (rows=1677 width=10) - Conds:RS_125._col1=SEL_61._col0(Inner),Output:["_col0","_col3"] + Map Join Operator [MAPJOIN_116] (rows=1677 width=10) + Conds:RS_121._col1=SEL_61._col0(Inner),Output:["_col0","_col3"] <-Map 6 [BROADCAST_EDGE] llap - BROADCAST [RS_125] + BROADCAST [RS_121] PartitionCols:_col1 - Please refer to the previous Map Join Operator [MAPJOIN_118] + Please refer to the previous Map Join Operator [MAPJOIN_113] <-Select Operator [SEL_61] (rows=500 width=10) Output:["_col0"] - Filter Operator [FIL_112] (rows=500 width=10) + Filter Operator [FIL_109] (rows=500 width=10) predicate:value is not null TableScan [TS_59] (rows=500 width=10) Output:["value"] @@ -2103,120 +2082,114 @@ Stage-0 File Output Operator [FS_74] Select Operator [SEL_72] (rows=1677 width=10) Output:["_col0","_col1"] - Map Join Operator [MAPJOIN_119] (rows=1677 width=10) - Conds:RS_126._col1=SEL_64._col0(Inner),Output:["_col0","_col3"] + Map Join Operator [MAPJOIN_116] (rows=1677 width=10) + Conds:RS_122._col1=SEL_64._col0(Inner),Output:["_col0","_col3"] <-Map 6 [BROADCAST_EDGE] llap - BROADCAST [RS_126] + BROADCAST [RS_122] PartitionCols:_col1 - Please refer to the previous Map Join Operator [MAPJOIN_118] + Please refer to the previous Map Join Operator [MAPJOIN_113] <-Select Operator [SEL_64] (rows=500 width=10) Output:["_col0"] - Filter Operator [FIL_113] (rows=500 width=10) + Filter Operator [FIL_110] (rows=500 width=10) predicate:value is not null TableScan [TS_62] (rows=500 width=10) Output:["value"] - <-Reducer 3 [CONTAINS] llap + <-Reducer 2 [CONTAINS] llap File Output Operator [FS_74] - Select Operator [SEL_20] (rows=634 width=10) + Select Operator [SEL_20] (rows=605 width=10) Output:["_col0","_col1"] - Merge Join Operator [MERGEJOIN_115] (rows=634 width=10) - Conds:Union 2._col1=RS_18._col0(Inner),Output:["_col1","_col4"] - <-Map 7 [SIMPLE_EDGE] llap - SHUFFLE [RS_18] - PartitionCols:_col0 - Select Operator [SEL_13] (rows=500 width=10) - Output:["_col0","_col1"] - Filter Operator [FIL_102] (rows=500 width=10) - predicate:key is not null - TableScan [TS_11] (rows=500 width=10) - default@src,y,Tbl:COMPLETE,Col:NONE,Output:["key","value"] - <-Union 2 [SIMPLE_EDGE] - <-Map 1 [CONTAINS] llap - Reduce Output Operator [RS_17] - PartitionCols:_col1 - Map Join Operator [MAPJOIN_114] (rows=577 width=10) - Conds:SEL_2._col0=RS_15._col1(Inner),Output:["_col1"] - <-Map 6 [BROADCAST_EDGE] llap - BROADCAST [RS_15] - PartitionCols:_col1 - Please refer to the previous Select Operator [SEL_10] - <-Select Operator [SEL_2] (rows=25 width=7) - Output:["_col0"] - Filter Operator [FIL_99] (rows=25 width=7) - predicate:value is not null - TableScan [TS_0] (rows=25 width=7) - Output:["value"] - <-Map 5 [CONTAINS] llap - Reduce Output Operator [RS_17] - PartitionCols:_col1 - Map Join Operator [MAPJOIN_114] (rows=577 width=10) - Conds:SEL_5._col0=RS_120._col1(Inner),Output:["_col1"] - <-Map 6 [BROADCAST_EDGE] llap - BROADCAST [RS_120] - PartitionCols:_col1 - Please refer to the previous Select Operator [SEL_10] - <-Select Operator [SEL_5] (rows=500 width=10) - Output:["_col0"] - Filter Operator [FIL_100] (rows=500 width=10) - predicate:value is not null - TableScan [TS_3] (rows=500 width=10) - Output:["value"] - <-Reducer 9 [CONTAINS] llap + Merge Join Operator [MERGEJOIN_114] (rows=605 width=10) + Conds:RS_17._col3=Union 8._col0(Inner),Output:["_col1","_col2"] + <-Map 1 [SIMPLE_EDGE] llap + SHUFFLE [RS_17] + PartitionCols:_col3 + Map Join Operator [MAPJOIN_111] (rows=550 width=10) + Conds:SEL_2._col0=RS_15._col0(Inner),Output:["_col1","_col2","_col3"] + <-Map 6 [BROADCAST_EDGE] llap + BROADCAST [RS_15] + PartitionCols:_col0 + Please refer to the previous Select Operator [SEL_5] + <-Select Operator [SEL_2] (rows=500 width=10) + Output:["_col0","_col1"] + Filter Operator [FIL_96] (rows=500 width=10) + predicate:key is not null + TableScan [TS_0] (rows=500 width=10) + default@src,y,Tbl:COMPLETE,Col:NONE,Output:["key","value"] + <-Union 8 [SIMPLE_EDGE] + <-Map 7 [CONTAINS] llap + Reduce Output Operator [RS_18] + PartitionCols:_col0 + Select Operator [SEL_8] (rows=25 width=7) + Output:["_col0"] + Filter Operator [FIL_98] (rows=25 width=7) + predicate:value is not null + TableScan [TS_6] (rows=25 width=7) + Output:["value"] + <-Map 9 [CONTAINS] llap + Reduce Output Operator [RS_18] + PartitionCols:_col0 + Select Operator [SEL_11] (rows=500 width=10) + Output:["_col0"] + Filter Operator [FIL_99] (rows=500 width=10) + predicate:value is not null + TableScan [TS_9] (rows=500 width=10) + Output:["value"] + <-Reducer 5 [CONTAINS] llap File Output Operator [FS_74] - Select Operator [SEL_44] (rows=1239 width=10) + Select Operator [SEL_44] (rows=1127 width=10) Output:["_col0","_col1"] - Merge Join Operator [MERGEJOIN_117] (rows=1239 width=10) - Conds:RS_41._col1=RS_42._col0(Inner),Output:["_col1","_col4"] - <-Map 14 [SIMPLE_EDGE] llap - SHUFFLE [RS_42] - PartitionCols:_col0 - Select Operator [SEL_37] (rows=500 width=10) - Output:["_col0","_col1"] - Filter Operator [FIL_107] (rows=500 width=10) - predicate:key is not null - TableScan [TS_35] (rows=500 width=10) - default@src,y,Tbl:COMPLETE,Col:NONE,Output:["key","value"] - <-Reducer 8 [SIMPLE_EDGE] llap + Merge Join Operator [MERGEJOIN_115] (rows=1127 width=10) + Conds:RS_41._col1=Union 12._col0(Inner),Output:["_col0","_col3"] + <-Reducer 4 [SIMPLE_EDGE] llap SHUFFLE [RS_41] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_116] (rows=1127 width=10) - Conds:Union 11._col0=RS_39._col1(Inner),Output:["_col1"] - <-Map 7 [SIMPLE_EDGE] llap - SHUFFLE [RS_39] - PartitionCols:_col1 - Select Operator [SEL_34] (rows=500 width=10) + Merge Join Operator [MERGEJOIN_112] (rows=550 width=10) + Conds:RS_38._col0=RS_39._col0(Inner),Output:["_col0","_col1","_col3"] + <-Map 1 [SIMPLE_EDGE] llap + SHUFFLE [RS_38] + PartitionCols:_col0 + Select Operator [SEL_23] (rows=500 width=10) Output:["_col0","_col1"] - Filter Operator [FIL_106] (rows=500 width=10) + Filter Operator [FIL_100] (rows=500 width=10) predicate:(key is not null and value is not null) - Please refer to the previous TableScan [TS_11] - <-Union 11 [SIMPLE_EDGE] - <-Map 10 [CONTAINS] llap - Reduce Output Operator [RS_38] - PartitionCols:_col0 - Select Operator [SEL_23] (rows=25 width=7) - Output:["_col0"] - Filter Operator [FIL_103] (rows=25 width=7) - predicate:value is not null - TableScan [TS_21] (rows=25 width=7) - Output:["value"] - <-Map 12 [CONTAINS] llap - Reduce Output Operator [RS_38] - PartitionCols:_col0 - Select Operator [SEL_26] (rows=500 width=10) - Output:["_col0"] - Filter Operator [FIL_104] (rows=500 width=10) - predicate:value is not null - TableScan [TS_24] (rows=500 width=10) - Output:["value"] - <-Map 13 [CONTAINS] llap - Reduce Output Operator [RS_38] - PartitionCols:_col0 - Select Operator [SEL_30] (rows=500 width=10) - Output:["_col0"] - Filter Operator [FIL_105] (rows=500 width=10) - predicate:value is not null - TableScan [TS_28] (rows=500 width=10) - Output:["value"] + Please refer to the previous TableScan [TS_0] + <-Map 10 [SIMPLE_EDGE] llap + SHUFFLE [RS_39] + PartitionCols:_col0 + Select Operator [SEL_26] (rows=500 width=10) + Output:["_col0","_col1"] + Filter Operator [FIL_101] (rows=500 width=10) + predicate:key is not null + TableScan [TS_24] (rows=500 width=10) + default@src,y,Tbl:COMPLETE,Col:NONE,Output:["key","value"] + <-Union 12 [SIMPLE_EDGE] + <-Map 11 [CONTAINS] llap + Reduce Output Operator [RS_42] + PartitionCols:_col0 + Select Operator [SEL_29] (rows=25 width=7) + Output:["_col0"] + Filter Operator [FIL_102] (rows=25 width=7) + predicate:value is not null + TableScan [TS_27] (rows=25 width=7) + Output:["value"] + <-Map 13 [CONTAINS] llap + Reduce Output Operator [RS_42] + PartitionCols:_col0 + Select Operator [SEL_32] (rows=500 width=10) + Output:["_col0"] + Filter Operator [FIL_103] (rows=500 width=10) + predicate:value is not null + TableScan [TS_30] (rows=500 width=10) + Output:["value"] + <-Map 14 [CONTAINS] llap + Reduce Output Operator [RS_42] + PartitionCols:_col0 + Select Operator [SEL_36] (rows=500 width=10) + Output:["_col0"] + Filter Operator [FIL_104] (rows=500 width=10) + predicate:value is not null + TableScan [TS_34] (rows=500 width=10) + Output:["value"] PREHOOK: query: explain SELECT x.key, y.value @@ -2247,65 +2220,66 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Map 1 <- Union 2 (CONTAINS) -Map 10 <- Map 22 (BROADCAST_EDGE) -Map 14 <- Union 15 (CONTAINS) -Map 19 <- Union 15 (CONTAINS) -Map 20 <- Union 17 (CONTAINS) +Map 1 <- Map 9 (BROADCAST_EDGE) +Map 10 <- Union 11 (CONTAINS) +Map 13 <- Union 11 (CONTAINS) +Map 15 <- Union 16 (CONTAINS) +Map 20 <- Union 16 (CONTAINS) +Map 21 <- Union 18 (CONTAINS) Map 23 <- Union 24 (CONTAINS) Map 30 <- Union 24 (CONTAINS) Map 31 <- Union 26 (CONTAINS) Map 32 <- Union 28 (CONTAINS) -Map 9 <- Union 2 (CONTAINS) -Reducer 12 <- Map 11 (SIMPLE_EDGE), Reducer 18 (SIMPLE_EDGE) -Reducer 13 <- Map 21 (SIMPLE_EDGE), Reducer 12 (SIMPLE_EDGE), Union 5 (CONTAINS) -Reducer 16 <- Union 15 (SIMPLE_EDGE), Union 17 (CONTAINS) -Reducer 18 <- Union 17 (SIMPLE_EDGE) +Map 9 <- Map 22 (BROADCAST_EDGE) +Reducer 12 <- Union 11 (SIMPLE_EDGE) +Reducer 17 <- Union 16 (SIMPLE_EDGE), Union 18 (CONTAINS) +Reducer 19 <- Union 18 (SIMPLE_EDGE) +Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 12 (SIMPLE_EDGE), Union 3 (CONTAINS) Reducer 25 <- Union 24 (SIMPLE_EDGE), Union 26 (CONTAINS) Reducer 27 <- Union 26 (SIMPLE_EDGE), Union 28 (CONTAINS) -Reducer 29 <- Map 10 (BROADCAST_EDGE), Union 28 (SIMPLE_EDGE), Union 7 (CONTAINS) -Reducer 3 <- Map 10 (BROADCAST_EDGE), Union 2 (SIMPLE_EDGE) -Reducer 4 <- Map 11 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE), Union 5 (CONTAINS) -Reducer 6 <- Union 5 (SIMPLE_EDGE), Union 7 (CONTAINS) -Reducer 8 <- Union 7 (SIMPLE_EDGE) +Reducer 29 <- Map 9 (BROADCAST_EDGE), Union 28 (SIMPLE_EDGE), Union 5 (CONTAINS) +Reducer 4 <- Union 3 (SIMPLE_EDGE), Union 5 (CONTAINS) +Reducer 6 <- Union 5 (SIMPLE_EDGE) +Reducer 7 <- Map 1 (SIMPLE_EDGE), Map 14 (SIMPLE_EDGE) +Reducer 8 <- Reducer 19 (SIMPLE_EDGE), Reducer 7 (SIMPLE_EDGE), Union 3 (CONTAINS) Stage-0 Fetch Operator limit:-1 Stage-1 - Reducer 8 llap + Reducer 6 llap File Output Operator [FS_122] - Group By Operator [GBY_120] (rows=530 width=10) + Group By Operator [GBY_120] (rows=544 width=10) Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 - <-Union 7 [SIMPLE_EDGE] + <-Union 5 [SIMPLE_EDGE] <-Reducer 29 [CONTAINS] llap Reduce Output Operator [RS_119] PartitionCols:_col0, _col1 - Group By Operator [GBY_118] (rows=1061 width=10) + Group By Operator [GBY_118] (rows=1089 width=10) Output:["_col0","_col1"],keys:_col0, _col1 Select Operator [SEL_114] (rows=484 width=10) Output:["_col0","_col1"] - Map Join Operator [MAPJOIN_167] (rows=484 width=10) + Map Join Operator [MAPJOIN_164] (rows=484 width=10) Conds:RS_111._col1=SEL_107._col1(Inner),Output:["_col0","_col3"] - <-Map 10 [BROADCAST_EDGE] llap + <-Map 9 [BROADCAST_EDGE] llap BROADCAST [RS_111] PartitionCols:_col1 - Map Join Operator [MAPJOIN_166] (rows=27 width=7) - Conds:SEL_15._col0=RS_109._col0(Inner),Output:["_col0","_col1","_col3"] + Map Join Operator [MAPJOIN_161] (rows=27 width=7) + Conds:SEL_5._col0=RS_109._col0(Inner),Output:["_col0","_col1","_col3"] <-Map 22 [BROADCAST_EDGE] llap BROADCAST [RS_109] PartitionCols:_col0 Select Operator [SEL_74] (rows=25 width=7) Output:["_col0","_col1"] - Filter Operator [FIL_157] (rows=25 width=7) + Filter Operator [FIL_154] (rows=25 width=7) predicate:key is not null TableScan [TS_72] (rows=25 width=7) default@src1,y,Tbl:COMPLETE,Col:NONE,Output:["key","value"] - <-Select Operator [SEL_15] (rows=25 width=7) + <-Select Operator [SEL_5] (rows=25 width=7) Output:["_col0","_col1"] - Filter Operator [FIL_149] (rows=25 width=7) + Filter Operator [FIL_145] (rows=25 width=7) predicate:(key is not null and value is not null) - TableScan [TS_13] (rows=25 width=7) + TableScan [TS_3] (rows=25 width=7) default@src1,x,Tbl:COMPLETE,Col:NONE,Output:["key","value"] <-Select Operator [SEL_107] (rows=440 width=10) Output:["_col1"] @@ -2319,7 +2293,7 @@ Stage-0 Output:["_col0","_col1"],keys:_col1, _col0 Select Operator [SEL_100] (rows=500 width=10) Output:["_col0","_col1"] - Filter Operator [FIL_161] (rows=500 width=10) + Filter Operator [FIL_158] (rows=500 width=10) predicate:value is not null TableScan [TS_98] (rows=500 width=10) Output:["key","value"] @@ -2340,7 +2314,7 @@ Stage-0 Output:["_col0","_col1"],keys:_col1, _col0 Select Operator [SEL_90] (rows=500 width=10) Output:["_col0","_col1"] - Filter Operator [FIL_160] (rows=500 width=10) + Filter Operator [FIL_157] (rows=500 width=10) predicate:value is not null TableScan [TS_88] (rows=500 width=10) Output:["key","value"] @@ -2361,7 +2335,7 @@ Stage-0 Output:["_col0","_col1"],keys:_col1, _col0 Select Operator [SEL_77] (rows=25 width=7) Output:["_col0","_col1"] - Filter Operator [FIL_158] (rows=25 width=7) + Filter Operator [FIL_155] (rows=25 width=7) predicate:value is not null TableScan [TS_75] (rows=25 width=7) Output:["key","value"] @@ -2372,154 +2346,154 @@ Stage-0 Output:["_col0","_col1"],keys:_col1, _col0 Select Operator [SEL_80] (rows=500 width=10) Output:["_col0","_col1"] - Filter Operator [FIL_159] (rows=500 width=10) + Filter Operator [FIL_156] (rows=500 width=10) predicate:value is not null TableScan [TS_78] (rows=500 width=10) Output:["key","value"] - <-Reducer 6 [CONTAINS] llap + <-Reducer 4 [CONTAINS] llap Reduce Output Operator [RS_119] PartitionCols:_col0, _col1 - Group By Operator [GBY_118] (rows=1061 width=10) + Group By Operator [GBY_118] (rows=1089 width=10) Output:["_col0","_col1"],keys:_col0, _col1 - Group By Operator [GBY_67] (rows=577 width=10) + Group By Operator [GBY_67] (rows=605 width=10) Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 - <-Union 5 [SIMPLE_EDGE] - <-Reducer 13 [CONTAINS] llap + <-Union 3 [SIMPLE_EDGE] + <-Reducer 2 [CONTAINS] llap + Reduce Output Operator [RS_66] + PartitionCols:_col0, _col1 + Group By Operator [GBY_65] (rows=1210 width=10) + Output:["_col0","_col1"],keys:_col0, _col1 + Select Operator [SEL_25] (rows=605 width=10) + Output:["_col0","_col1"] + Merge Join Operator [MERGEJOIN_162] (rows=605 width=10) + Conds:RS_22._col3=RS_23._col1(Inner),Output:["_col1","_col2"] + <-Map 1 [SIMPLE_EDGE] llap + SHUFFLE [RS_22] + PartitionCols:_col3 + Map Join Operator [MAPJOIN_159] (rows=550 width=10) + Conds:SEL_2._col0=RS_20._col0(Inner),Output:["_col1","_col2","_col3"] + <-Map 9 [BROADCAST_EDGE] llap + BROADCAST [RS_20] + PartitionCols:_col0 + Please refer to the previous Select Operator [SEL_5] + <-Select Operator [SEL_2] (rows=500 width=10) + Output:["_col0","_col1"] + Filter Operator [FIL_144] (rows=500 width=10) + predicate:key is not null + TableScan [TS_0] (rows=500 width=10) + default@src,y,Tbl:COMPLETE,Col:NONE,Output:["key","value"] + <-Reducer 12 [SIMPLE_EDGE] llap + SHUFFLE [RS_23] + PartitionCols:_col1 + Select Operator [SEL_18] (rows=262 width=10) + Output:["_col1"] + Group By Operator [GBY_17] (rows=262 width=10) + Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 + <-Union 11 [SIMPLE_EDGE] + <-Map 10 [CONTAINS] llap + Reduce Output Operator [RS_16] + PartitionCols:_col0, _col1 + Group By Operator [GBY_15] (rows=525 width=10) + Output:["_col0","_col1"],keys:_col1, _col0 + Select Operator [SEL_8] (rows=25 width=7) + Output:["_col0","_col1"] + Filter Operator [FIL_146] (rows=25 width=7) + predicate:value is not null + TableScan [TS_6] (rows=25 width=7) + Output:["key","value"] + <-Map 13 [CONTAINS] llap + Reduce Output Operator [RS_16] + PartitionCols:_col0, _col1 + Group By Operator [GBY_15] (rows=525 width=10) + Output:["_col0","_col1"],keys:_col1, _col0 + Select Operator [SEL_11] (rows=500 width=10) + Output:["_col0","_col1"] + Filter Operator [FIL_147] (rows=500 width=10) + predicate:value is not null + TableScan [TS_9] (rows=500 width=10) + Output:["key","value"] + <-Reducer 8 [CONTAINS] llap Reduce Output Operator [RS_66] PartitionCols:_col0, _col1 - Group By Operator [GBY_65] (rows=1155 width=10) + Group By Operator [GBY_65] (rows=1210 width=10) Output:["_col0","_col1"],keys:_col0, _col1 Select Operator [SEL_61] (rows=605 width=10) Output:["_col0","_col1"] - Merge Join Operator [MERGEJOIN_165] (rows=605 width=10) - Conds:RS_58._col2=RS_59._col0(Inner),Output:["_col2","_col5"] - <-Map 21 [SIMPLE_EDGE] llap + Merge Join Operator [MERGEJOIN_163] (rows=605 width=10) + Conds:RS_58._col1=RS_59._col1(Inner),Output:["_col0","_col3"] + <-Reducer 19 [SIMPLE_EDGE] llap SHUFFLE [RS_59] - PartitionCols:_col0 - Select Operator [SEL_54] (rows=500 width=10) - Output:["_col0","_col1"] - Filter Operator [FIL_155] (rows=500 width=10) - predicate:key is not null - TableScan [TS_52] (rows=500 width=10) - default@src,y,Tbl:COMPLETE,Col:NONE,Output:["key","value"] - <-Reducer 12 [SIMPLE_EDGE] llap + PartitionCols:_col1 + Select Operator [SEL_54] (rows=381 width=10) + Output:["_col1"] + Group By Operator [GBY_53] (rows=381 width=10) + Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 + <-Union 18 [SIMPLE_EDGE] + <-Map 21 [CONTAINS] llap + Reduce Output Operator [RS_52] + PartitionCols:_col0, _col1 + Group By Operator [GBY_51] (rows=762 width=10) + Output:["_col0","_col1"],keys:_col1, _col0 + Select Operator [SEL_47] (rows=500 width=10) + Output:["_col0","_col1"] + Filter Operator [FIL_152] (rows=500 width=10) + predicate:value is not null + TableScan [TS_45] (rows=500 width=10) + Output:["key","value"] + <-Reducer 17 [CONTAINS] llap + Reduce Output Operator [RS_52] + PartitionCols:_col0, _col1 + Group By Operator [GBY_51] (rows=762 width=10) + Output:["_col0","_col1"],keys:_col1, _col0 + Select Operator [SEL_44] (rows=262 width=10) + Output:["_col0","_col1"] + Group By Operator [GBY_43] (rows=262 width=10) + Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 + <-Union 16 [SIMPLE_EDGE] + <-Map 15 [CONTAINS] llap + Reduce Output Operator [RS_42] + PartitionCols:_col0, _col1 + Group By Operator [GBY_41] (rows=525 width=10) + Output:["_col0","_col1"],keys:_col1, _col0 + Select Operator [SEL_34] (rows=25 width=7) + Output:["_col0","_col1"] + Filter Operator [FIL_150] (rows=25 width=7) + predicate:value is not null + TableScan [TS_32] (rows=25 width=7) + Output:["key","value"] + <-Map 20 [CONTAINS] llap + Reduce Output Operator [RS_42] + PartitionCols:_col0, _col1 + Group By Operator [GBY_41] (rows=525 width=10) + Output:["_col0","_col1"],keys:_col1, _col0 + Select Operator [SEL_37] (rows=500 width=10) + Output:["_col0","_col1"] + Filter Operator [FIL_151] (rows=500 width=10) + predicate:value is not null + TableScan [TS_35] (rows=500 width=10) + Output:["key","value"] + <-Reducer 7 [SIMPLE_EDGE] llap SHUFFLE [RS_58] - PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_164] (rows=550 width=10) - Conds:RS_55._col1=RS_56._col1(Inner),Output:["_col2"] - <-Map 11 [SIMPLE_EDGE] llap - SHUFFLE [RS_56] - PartitionCols:_col1 - Select Operator [SEL_51] (rows=500 width=10) + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_160] (rows=550 width=10) + Conds:RS_55._col0=RS_56._col0(Inner),Output:["_col0","_col1","_col3"] + <-Map 1 [SIMPLE_EDGE] llap + SHUFFLE [RS_55] + PartitionCols:_col0 + Select Operator [SEL_28] (rows=500 width=10) Output:["_col0","_col1"] - Filter Operator [FIL_154] (rows=500 width=10) + Filter Operator [FIL_148] (rows=500 width=10) predicate:(key is not null and value is not null) - TableScan [TS_16] (rows=500 width=10) + Please refer to the previous TableScan [TS_0] + <-Map 14 [SIMPLE_EDGE] llap + SHUFFLE [RS_56] + PartitionCols:_col0 + Select Operator [SEL_31] (rows=500 width=10) + Output:["_col0","_col1"] + Filter Operator [FIL_149] (rows=500 width=10) + predicate:key is not null + TableScan [TS_29] (rows=500 width=10) default@src,y,Tbl:COMPLETE,Col:NONE,Output:["key","value"] - <-Reducer 18 [SIMPLE_EDGE] llap - SHUFFLE [RS_55] - PartitionCols:_col1 - Select Operator [SEL_48] (rows=381 width=10) - Output:["_col1"] - Group By Operator [GBY_47] (rows=381 width=10) - Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 - <-Union 17 [SIMPLE_EDGE] - <-Map 20 [CONTAINS] llap - Reduce Output Operator [RS_46] - PartitionCols:_col0, _col1 - Group By Operator [GBY_45] (rows=762 width=10) - Output:["_col0","_col1"],keys:_col1, _col0 - Select Operator [SEL_41] (rows=500 width=10) - Output:["_col0","_col1"] - Filter Operator [FIL_153] (rows=500 width=10) - predicate:value is not null - TableScan [TS_39] (rows=500 width=10) - Output:["key","value"] - <-Reducer 16 [CONTAINS] llap - Reduce Output Operator [RS_46] - PartitionCols:_col0, _col1 - Group By Operator [GBY_45] (rows=762 width=10) - Output:["_col0","_col1"],keys:_col1, _col0 - Select Operator [SEL_38] (rows=262 width=10) - Output:["_col0","_col1"] - Group By Operator [GBY_37] (rows=262 width=10) - Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 - <-Union 15 [SIMPLE_EDGE] - <-Map 14 [CONTAINS] llap - Reduce Output Operator [RS_36] - PartitionCols:_col0, _col1 - Group By Operator [GBY_35] (rows=525 width=10) - Output:["_col0","_col1"],keys:_col1, _col0 - Select Operator [SEL_28] (rows=25 width=7) - Output:["_col0","_col1"] - Filter Operator [FIL_151] (rows=25 width=7) - predicate:value is not null - TableScan [TS_26] (rows=25 width=7) - Output:["key","value"] - <-Map 19 [CONTAINS] llap - Reduce Output Operator [RS_36] - PartitionCols:_col0, _col1 - Group By Operator [GBY_35] (rows=525 width=10) - Output:["_col0","_col1"],keys:_col1, _col0 - Select Operator [SEL_31] (rows=500 width=10) - Output:["_col0","_col1"] - Filter Operator [FIL_152] (rows=500 width=10) - predicate:value is not null - TableScan [TS_29] (rows=500 width=10) - Output:["key","value"] - <-Reducer 4 [CONTAINS] llap - Reduce Output Operator [RS_66] - PartitionCols:_col0, _col1 - Group By Operator [GBY_65] (rows=1155 width=10) - Output:["_col0","_col1"],keys:_col0, _col1 - Select Operator [SEL_25] (rows=550 width=10) - Output:["_col0","_col1"] - Merge Join Operator [MERGEJOIN_163] (rows=550 width=10) - Conds:RS_22._col2=RS_23._col0(Inner),Output:["_col2","_col5"] - <-Map 11 [SIMPLE_EDGE] llap - SHUFFLE [RS_23] - PartitionCols:_col0 - Select Operator [SEL_18] (rows=500 width=10) - Output:["_col0","_col1"] - Filter Operator [FIL_150] (rows=500 width=10) - predicate:key is not null - Please refer to the previous TableScan [TS_16] - <-Reducer 3 [SIMPLE_EDGE] llap - SHUFFLE [RS_22] - PartitionCols:_col2 - Map Join Operator [MAPJOIN_162] (rows=288 width=10) - Conds:SEL_12._col1=RS_20._col1(Inner),Output:["_col2"] - <-Map 10 [BROADCAST_EDGE] llap - BROADCAST [RS_20] - PartitionCols:_col1 - Please refer to the previous Select Operator [SEL_15] - <-Select Operator [SEL_12] (rows=262 width=10) - Output:["_col1"] - Group By Operator [GBY_11] (rows=262 width=10) - Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 - <-Union 2 [SIMPLE_EDGE] - <-Map 1 [CONTAINS] llap - Reduce Output Operator [RS_10] - PartitionCols:_col0, _col1 - Group By Operator [GBY_9] (rows=525 width=10) - Output:["_col0","_col1"],keys:_col1, _col0 - Select Operator [SEL_2] (rows=25 width=7) - Output:["_col0","_col1"] - Filter Operator [FIL_147] (rows=25 width=7) - predicate:value is not null - TableScan [TS_0] (rows=25 width=7) - Output:["key","value"] - <-Map 9 [CONTAINS] llap - Reduce Output Operator [RS_10] - PartitionCols:_col0, _col1 - Group By Operator [GBY_9] (rows=525 width=10) - Output:["_col0","_col1"],keys:_col1, _col0 - Select Operator [SEL_5] (rows=500 width=10) - Output:["_col0","_col1"] - Filter Operator [FIL_148] (rows=500 width=10) - predicate:value is not null - TableScan [TS_3] (rows=500 width=10) - Output:["key","value"] PREHOOK: query: CREATE TABLE a(key STRING, value STRING) STORED AS TEXTFILE PREHOOK: type: CREATETABLE @@ -2586,22 +2560,23 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Map 1 <- Map 9 (BROADCAST_EDGE), Union 2 (CONTAINS) -Map 13 <- Union 14 (CONTAINS) -Map 15 <- Union 14 (CONTAINS) -Map 16 <- Union 14 (CONTAINS) -Map 19 <- Map 9 (BROADCAST_EDGE), Union 4 (CONTAINS) -Map 20 <- Map 9 (BROADCAST_EDGE), Union 4 (CONTAINS) -Map 21 <- Map 9 (BROADCAST_EDGE), Union 4 (CONTAINS) -Map 22 <- Map 9 (BROADCAST_EDGE), Union 4 (CONTAINS) -Map 8 <- Map 9 (BROADCAST_EDGE), Union 2 (CONTAINS) +Map 1 <- Map 9 (BROADCAST_EDGE) +Map 10 <- Union 11 (CONTAINS) +Map 12 <- Union 11 (CONTAINS) +Map 14 <- Union 15 (CONTAINS) +Map 16 <- Union 15 (CONTAINS) +Map 17 <- Union 15 (CONTAINS) +Map 19 <- Map 9 (BROADCAST_EDGE), Union 3 (CONTAINS) +Map 20 <- Map 9 (BROADCAST_EDGE), Union 3 (CONTAINS) +Map 21 <- Map 9 (BROADCAST_EDGE), Union 3 (CONTAINS) +Map 22 <- Map 9 (BROADCAST_EDGE), Union 3 (CONTAINS) Map 9 <- Map 18 (BROADCAST_EDGE) -Reducer 11 <- Map 10 (SIMPLE_EDGE), Union 14 (SIMPLE_EDGE) -Reducer 12 <- Map 17 (SIMPLE_EDGE), Reducer 11 (SIMPLE_EDGE), Union 4 (CONTAINS) -Reducer 3 <- Map 10 (SIMPLE_EDGE), Union 2 (SIMPLE_EDGE), Union 4 (CONTAINS) -Reducer 5 <- Union 4 (CUSTOM_SIMPLE_EDGE) -Reducer 6 <- Union 4 (CUSTOM_SIMPLE_EDGE) -Reducer 7 <- Union 4 (CUSTOM_SIMPLE_EDGE) +Reducer 2 <- Map 1 (SIMPLE_EDGE), Union 11 (SIMPLE_EDGE), Union 3 (CONTAINS) +Reducer 4 <- Union 3 (CUSTOM_SIMPLE_EDGE) +Reducer 5 <- Union 3 (CUSTOM_SIMPLE_EDGE) +Reducer 6 <- Union 3 (CUSTOM_SIMPLE_EDGE) +Reducer 7 <- Map 1 (SIMPLE_EDGE), Map 13 (SIMPLE_EDGE) +Reducer 8 <- Reducer 7 (SIMPLE_EDGE), Union 15 (SIMPLE_EDGE), Union 3 (CONTAINS) Stage-5 Stats Work{} @@ -2611,48 +2586,48 @@ Stage-5 Stage-4 Dependency Collection{} Stage-3 - Reducer 5 llap + Reducer 4 llap File Output Operator [FS_6] Group By Operator [GBY_4] (rows=1 width=880) Output:["_col0","_col1"],aggregations:["compute_stats(VALUE._col0)","compute_stats(VALUE._col1)"] - <-Union 4 [CUSTOM_SIMPLE_EDGE] + <-Union 3 [CUSTOM_SIMPLE_EDGE] <-Map 19 [CONTAINS] llap File Output Operator [FS_75] table:{"name:":"default.a"} Select Operator [SEL_72] (rows=1677 width=10) Output:["_col0","_col1"] - Map Join Operator [MAPJOIN_124] (rows=1677 width=10) + Map Join Operator [MAPJOIN_121] (rows=1677 width=10) Conds:RS_69._col1=SEL_54._col0(Inner),Output:["_col0","_col3"] <-Map 9 [BROADCAST_EDGE] llap BROADCAST [RS_69] PartitionCols:_col1 - Map Join Operator [MAPJOIN_123] (rows=27 width=7) - Conds:SEL_10._col0=RS_67._col0(Inner),Output:["_col0","_col1","_col3"] + Map Join Operator [MAPJOIN_118] (rows=27 width=7) + Conds:SEL_5._col0=RS_67._col0(Inner),Output:["_col0","_col1","_col3"] <-Map 18 [BROADCAST_EDGE] llap BROADCAST [RS_67] PartitionCols:_col0 Select Operator [SEL_51] (rows=25 width=7) Output:["_col0","_col1"] - Filter Operator [FIL_114] (rows=25 width=7) + Filter Operator [FIL_111] (rows=25 width=7) predicate:key is not null TableScan [TS_49] (rows=25 width=7) default@src1,y,Tbl:COMPLETE,Col:NONE,Output:["key","value"] - <-Select Operator [SEL_10] (rows=25 width=7) + <-Select Operator [SEL_5] (rows=25 width=7) Output:["_col0","_col1"] - Filter Operator [FIL_106] (rows=25 width=7) + Filter Operator [FIL_102] (rows=25 width=7) predicate:(key is not null and value is not null) - TableScan [TS_8] (rows=25 width=7) + TableScan [TS_3] (rows=25 width=7) default@src1,x,Tbl:COMPLETE,Col:NONE,Output:["key","value"] <-Select Operator [SEL_54] (rows=25 width=7) Output:["_col0"] - Filter Operator [FIL_115] (rows=25 width=7) + Filter Operator [FIL_112] (rows=25 width=7) predicate:value is not null TableScan [TS_52] (rows=25 width=7) Output:["value"] Reduce Output Operator [RS_3] Group By Operator [GBY_2] (rows=1 width=880) Output:["_col0","_col1"],aggregations:["compute_stats(key, 'hll')","compute_stats(value, 'hll')"] - Select Operator [SEL_1] (rows=3550 width=10) + Select Operator [SEL_1] (rows=3409 width=10) Output:["key","value"] Please refer to the previous Select Operator [SEL_72] File Output Operator [FS_77] @@ -2661,7 +2636,7 @@ Stage-5 Reduce Output Operator [RS_3] Group By Operator [GBY_2] (rows=1 width=880) Output:["_col0","_col1"],aggregations:["compute_stats(key, 'hll')","compute_stats(value, 'hll')"] - Select Operator [SEL_1] (rows=3550 width=10) + Select Operator [SEL_1] (rows=3409 width=10) Output:["key","value"] Please refer to the previous Select Operator [SEL_72] File Output Operator [FS_79] @@ -2670,7 +2645,7 @@ Stage-5 Reduce Output Operator [RS_3] Group By Operator [GBY_2] (rows=1 width=880) Output:["_col0","_col1"],aggregations:["compute_stats(key, 'hll')","compute_stats(value, 'hll')"] - Select Operator [SEL_1] (rows=3550 width=10) + Select Operator [SEL_1] (rows=3409 width=10) Output:["key","value"] Please refer to the previous Select Operator [SEL_72] <-Map 20 [CONTAINS] llap @@ -2678,22 +2653,22 @@ Stage-5 table:{"name:":"default.a"} Select Operator [SEL_72] (rows=1677 width=10) Output:["_col0","_col1"] - Map Join Operator [MAPJOIN_124] (rows=1677 width=10) - Conds:RS_129._col1=SEL_57._col0(Inner),Output:["_col0","_col3"] + Map Join Operator [MAPJOIN_121] (rows=1677 width=10) + Conds:RS_125._col1=SEL_57._col0(Inner),Output:["_col0","_col3"] <-Map 9 [BROADCAST_EDGE] llap - BROADCAST [RS_129] + BROADCAST [RS_125] PartitionCols:_col1 - Please refer to the previous Map Join Operator [MAPJOIN_123] + Please refer to the previous Map Join Operator [MAPJOIN_118] <-Select Operator [SEL_57] (rows=500 width=10) Output:["_col0"] - Filter Operator [FIL_116] (rows=500 width=10) + Filter Operator [FIL_113] (rows=500 width=10) predicate:value is not null TableScan [TS_55] (rows=500 width=10) Output:["value"] Reduce Output Operator [RS_3] Group By Operator [GBY_2] (rows=1 width=880) Output:["_col0","_col1"],aggregations:["compute_stats(key, 'hll')","compute_stats(value, 'hll')"] - Select Operator [SEL_1] (rows=3550 width=10) + Select Operator [SEL_1] (rows=3409 width=10) Output:["key","value"] Please refer to the previous Select Operator [SEL_72] File Output Operator [FS_77] @@ -2702,7 +2677,7 @@ Stage-5 Reduce Output Operator [RS_3] Group By Operator [GBY_2] (rows=1 width=880) Output:["_col0","_col1"],aggregations:["compute_stats(key, 'hll')","compute_stats(value, 'hll')"] - Select Operator [SEL_1] (rows=3550 width=10) + Select Operator [SEL_1] (rows=3409 width=10) Output:["key","value"] Please refer to the previous Select Operator [SEL_72] File Output Operator [FS_79] @@ -2711,7 +2686,7 @@ Stage-5 Reduce Output Operator [RS_3] Group By Operator [GBY_2] (rows=1 width=880) Output:["_col0","_col1"],aggregations:["compute_stats(key, 'hll')","compute_stats(value, 'hll')"] - Select Operator [SEL_1] (rows=3550 width=10) + Select Operator [SEL_1] (rows=3409 width=10) Output:["key","value"] Please refer to the previous Select Operator [SEL_72] <-Map 21 [CONTAINS] llap @@ -2719,22 +2694,22 @@ Stage-5 table:{"name:":"default.a"} Select Operator [SEL_72] (rows=1677 width=10) Output:["_col0","_col1"] - Map Join Operator [MAPJOIN_124] (rows=1677 width=10) - Conds:RS_130._col1=SEL_61._col0(Inner),Output:["_col0","_col3"] + Map Join Operator [MAPJOIN_121] (rows=1677 width=10) + Conds:RS_126._col1=SEL_61._col0(Inner),Output:["_col0","_col3"] <-Map 9 [BROADCAST_EDGE] llap - BROADCAST [RS_130] + BROADCAST [RS_126] PartitionCols:_col1 - Please refer to the previous Map Join Operator [MAPJOIN_123] + Please refer to the previous Map Join Operator [MAPJOIN_118] <-Select Operator [SEL_61] (rows=500 width=10) Output:["_col0"] - Filter Operator [FIL_117] (rows=500 width=10) + Filter Operator [FIL_114] (rows=500 width=10) predicate:value is not null TableScan [TS_59] (rows=500 width=10) Output:["value"] Reduce Output Operator [RS_3] Group By Operator [GBY_2] (rows=1 width=880) Output:["_col0","_col1"],aggregations:["compute_stats(key, 'hll')","compute_stats(value, 'hll')"] - Select Operator [SEL_1] (rows=3550 width=10) + Select Operator [SEL_1] (rows=3409 width=10) Output:["key","value"] Please refer to the previous Select Operator [SEL_72] File Output Operator [FS_77] @@ -2743,7 +2718,7 @@ Stage-5 Reduce Output Operator [RS_3] Group By Operator [GBY_2] (rows=1 width=880) Output:["_col0","_col1"],aggregations:["compute_stats(key, 'hll')","compute_stats(value, 'hll')"] - Select Operator [SEL_1] (rows=3550 width=10) + Select Operator [SEL_1] (rows=3409 width=10) Output:["key","value"] Please refer to the previous Select Operator [SEL_72] File Output Operator [FS_79] @@ -2752,7 +2727,7 @@ Stage-5 Reduce Output Operator [RS_3] Group By Operator [GBY_2] (rows=1 width=880) Output:["_col0","_col1"],aggregations:["compute_stats(key, 'hll')","compute_stats(value, 'hll')"] - Select Operator [SEL_1] (rows=3550 width=10) + Select Operator [SEL_1] (rows=3409 width=10) Output:["key","value"] Please refer to the previous Select Operator [SEL_72] <-Map 22 [CONTAINS] llap @@ -2760,22 +2735,22 @@ Stage-5 table:{"name:":"default.a"} Select Operator [SEL_72] (rows=1677 width=10) Output:["_col0","_col1"] - Map Join Operator [MAPJOIN_124] (rows=1677 width=10) - Conds:RS_131._col1=SEL_64._col0(Inner),Output:["_col0","_col3"] + Map Join Operator [MAPJOIN_121] (rows=1677 width=10) + Conds:RS_127._col1=SEL_64._col0(Inner),Output:["_col0","_col3"] <-Map 9 [BROADCAST_EDGE] llap - BROADCAST [RS_131] + BROADCAST [RS_127] PartitionCols:_col1 - Please refer to the previous Map Join Operator [MAPJOIN_123] + Please refer to the previous Map Join Operator [MAPJOIN_118] <-Select Operator [SEL_64] (rows=500 width=10) Output:["_col0"] - Filter Operator [FIL_118] (rows=500 width=10) + Filter Operator [FIL_115] (rows=500 width=10) predicate:value is not null TableScan [TS_62] (rows=500 width=10) Output:["value"] Reduce Output Operator [RS_3] Group By Operator [GBY_2] (rows=1 width=880) Output:["_col0","_col1"],aggregations:["compute_stats(key, 'hll')","compute_stats(value, 'hll')"] - Select Operator [SEL_1] (rows=3550 width=10) + Select Operator [SEL_1] (rows=3409 width=10) Output:["key","value"] Please refer to the previous Select Operator [SEL_72] File Output Operator [FS_77] @@ -2784,7 +2759,7 @@ Stage-5 Reduce Output Operator [RS_3] Group By Operator [GBY_2] (rows=1 width=880) Output:["_col0","_col1"],aggregations:["compute_stats(key, 'hll')","compute_stats(value, 'hll')"] - Select Operator [SEL_1] (rows=3550 width=10) + Select Operator [SEL_1] (rows=3409 width=10) Output:["key","value"] Please refer to the previous Select Operator [SEL_72] File Output Operator [FS_79] @@ -2793,171 +2768,165 @@ Stage-5 Reduce Output Operator [RS_3] Group By Operator [GBY_2] (rows=1 width=880) Output:["_col0","_col1"],aggregations:["compute_stats(key, 'hll')","compute_stats(value, 'hll')"] - Select Operator [SEL_1] (rows=3550 width=10) + Select Operator [SEL_1] (rows=3409 width=10) Output:["key","value"] Please refer to the previous Select Operator [SEL_72] - <-Reducer 12 [CONTAINS] llap + <-Reducer 2 [CONTAINS] llap File Output Operator [FS_75] table:{"name:":"default.a"} - Select Operator [SEL_44] (rows=1239 width=10) + Select Operator [SEL_20] (rows=605 width=10) Output:["_col0","_col1"] - Merge Join Operator [MERGEJOIN_122] (rows=1239 width=10) - Conds:RS_41._col1=RS_42._col0(Inner),Output:["_col1","_col4"] - <-Map 17 [SIMPLE_EDGE] llap - SHUFFLE [RS_42] - PartitionCols:_col0 - Select Operator [SEL_37] (rows=500 width=10) - Output:["_col0","_col1"] - Filter Operator [FIL_112] (rows=500 width=10) - predicate:key is not null - TableScan [TS_35] (rows=500 width=10) - default@src,y,Tbl:COMPLETE,Col:NONE,Output:["key","value"] - <-Reducer 11 [SIMPLE_EDGE] llap - SHUFFLE [RS_41] - PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_121] (rows=1127 width=10) - Conds:Union 14._col0=RS_39._col1(Inner),Output:["_col1"] - <-Map 10 [SIMPLE_EDGE] llap - SHUFFLE [RS_39] - PartitionCols:_col1 - Select Operator [SEL_34] (rows=500 width=10) - Output:["_col0","_col1"] - Filter Operator [FIL_111] (rows=500 width=10) - predicate:(key is not null and value is not null) - TableScan [TS_11] (rows=500 width=10) - default@src,y,Tbl:COMPLETE,Col:NONE,Output:["key","value"] - <-Union 14 [SIMPLE_EDGE] - <-Map 13 [CONTAINS] llap - Reduce Output Operator [RS_38] - PartitionCols:_col0 - Select Operator [SEL_23] (rows=25 width=7) - Output:["_col0"] - Filter Operator [FIL_108] (rows=25 width=7) - predicate:value is not null - TableScan [TS_21] (rows=25 width=7) - Output:["value"] - <-Map 15 [CONTAINS] llap - Reduce Output Operator [RS_38] - PartitionCols:_col0 - Select Operator [SEL_26] (rows=500 width=10) - Output:["_col0"] - Filter Operator [FIL_109] (rows=500 width=10) - predicate:value is not null - TableScan [TS_24] (rows=500 width=10) - Output:["value"] - <-Map 16 [CONTAINS] llap - Reduce Output Operator [RS_38] - PartitionCols:_col0 - Select Operator [SEL_30] (rows=500 width=10) - Output:["_col0"] - Filter Operator [FIL_110] (rows=500 width=10) - predicate:value is not null - TableScan [TS_28] (rows=500 width=10) - Output:["value"] + Merge Join Operator [MERGEJOIN_119] (rows=605 width=10) + Conds:RS_17._col3=Union 11._col0(Inner),Output:["_col1","_col2"] + <-Map 1 [SIMPLE_EDGE] llap + SHUFFLE [RS_17] + PartitionCols:_col3 + Map Join Operator [MAPJOIN_116] (rows=550 width=10) + Conds:SEL_2._col0=RS_15._col0(Inner),Output:["_col1","_col2","_col3"] + <-Map 9 [BROADCAST_EDGE] llap + BROADCAST [RS_15] + PartitionCols:_col0 + Please refer to the previous Select Operator [SEL_5] + <-Select Operator [SEL_2] (rows=500 width=10) + Output:["_col0","_col1"] + Filter Operator [FIL_101] (rows=500 width=10) + predicate:key is not null + TableScan [TS_0] (rows=500 width=10) + default@src,y,Tbl:COMPLETE,Col:NONE,Output:["key","value"] + <-Union 11 [SIMPLE_EDGE] + <-Map 10 [CONTAINS] llap + Reduce Output Operator [RS_18] + PartitionCols:_col0 + Select Operator [SEL_8] (rows=25 width=7) + Output:["_col0"] + Filter Operator [FIL_103] (rows=25 width=7) + predicate:value is not null + TableScan [TS_6] (rows=25 width=7) + Output:["value"] + <-Map 12 [CONTAINS] llap + Reduce Output Operator [RS_18] + PartitionCols:_col0 + Select Operator [SEL_11] (rows=500 width=10) + Output:["_col0"] + Filter Operator [FIL_104] (rows=500 width=10) + predicate:value is not null + TableScan [TS_9] (rows=500 width=10) + Output:["value"] Reduce Output Operator [RS_3] Group By Operator [GBY_2] (rows=1 width=880) Output:["_col0","_col1"],aggregations:["compute_stats(key, 'hll')","compute_stats(value, 'hll')"] - Select Operator [SEL_1] (rows=3550 width=10) + Select Operator [SEL_1] (rows=3409 width=10) Output:["key","value"] - Please refer to the previous Select Operator [SEL_44] + Please refer to the previous Select Operator [SEL_20] File Output Operator [FS_77] table:{"name:":"default.b"} - Please refer to the previous Select Operator [SEL_44] + Please refer to the previous Select Operator [SEL_20] Reduce Output Operator [RS_3] Group By Operator [GBY_2] (rows=1 width=880) Output:["_col0","_col1"],aggregations:["compute_stats(key, 'hll')","compute_stats(value, 'hll')"] - Select Operator [SEL_1] (rows=3550 width=10) + Select Operator [SEL_1] (rows=3409 width=10) Output:["key","value"] - Please refer to the previous Select Operator [SEL_44] + Please refer to the previous Select Operator [SEL_20] File Output Operator [FS_79] table:{"name:":"default.c"} - Please refer to the previous Select Operator [SEL_44] + Please refer to the previous Select Operator [SEL_20] Reduce Output Operator [RS_3] Group By Operator [GBY_2] (rows=1 width=880) Output:["_col0","_col1"],aggregations:["compute_stats(key, 'hll')","compute_stats(value, 'hll')"] - Select Operator [SEL_1] (rows=3550 width=10) + Select Operator [SEL_1] (rows=3409 width=10) Output:["key","value"] - Please refer to the previous Select Operator [SEL_44] - <-Reducer 3 [CONTAINS] llap + Please refer to the previous Select Operator [SEL_20] + <-Reducer 8 [CONTAINS] llap File Output Operator [FS_75] table:{"name:":"default.a"} - Select Operator [SEL_20] (rows=634 width=10) + Select Operator [SEL_44] (rows=1127 width=10) Output:["_col0","_col1"] - Merge Join Operator [MERGEJOIN_120] (rows=634 width=10) - Conds:Union 2._col1=RS_18._col0(Inner),Output:["_col1","_col4"] - <-Map 10 [SIMPLE_EDGE] llap - SHUFFLE [RS_18] - PartitionCols:_col0 - Select Operator [SEL_13] (rows=500 width=10) - Output:["_col0","_col1"] - Filter Operator [FIL_107] (rows=500 width=10) - predicate:key is not null - Please refer to the previous TableScan [TS_11] - <-Union 2 [SIMPLE_EDGE] - <-Map 1 [CONTAINS] llap - Reduce Output Operator [RS_17] - PartitionCols:_col1 - Map Join Operator [MAPJOIN_119] (rows=577 width=10) - Conds:SEL_2._col0=RS_15._col1(Inner),Output:["_col1"] - <-Map 9 [BROADCAST_EDGE] llap - BROADCAST [RS_15] - PartitionCols:_col1 - Please refer to the previous Select Operator [SEL_10] - <-Select Operator [SEL_2] (rows=25 width=7) - Output:["_col0"] - Filter Operator [FIL_104] (rows=25 width=7) - predicate:value is not null - TableScan [TS_0] (rows=25 width=7) - Output:["value"] - <-Map 8 [CONTAINS] llap - Reduce Output Operator [RS_17] - PartitionCols:_col1 - Map Join Operator [MAPJOIN_119] (rows=577 width=10) - Conds:SEL_5._col0=RS_125._col1(Inner),Output:["_col1"] - <-Map 9 [BROADCAST_EDGE] llap - BROADCAST [RS_125] - PartitionCols:_col1 - Please refer to the previous Select Operator [SEL_10] - <-Select Operator [SEL_5] (rows=500 width=10) - Output:["_col0"] + Merge Join Operator [MERGEJOIN_120] (rows=1127 width=10) + Conds:RS_41._col1=Union 15._col0(Inner),Output:["_col0","_col3"] + <-Reducer 7 [SIMPLE_EDGE] llap + SHUFFLE [RS_41] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_117] (rows=550 width=10) + Conds:RS_38._col0=RS_39._col0(Inner),Output:["_col0","_col1","_col3"] + <-Map 1 [SIMPLE_EDGE] llap + SHUFFLE [RS_38] + PartitionCols:_col0 + Select Operator [SEL_23] (rows=500 width=10) + Output:["_col0","_col1"] Filter Operator [FIL_105] (rows=500 width=10) - predicate:value is not null - TableScan [TS_3] (rows=500 width=10) - Output:["value"] + predicate:(key is not null and value is not null) + Please refer to the previous TableScan [TS_0] + <-Map 13 [SIMPLE_EDGE] llap + SHUFFLE [RS_39] + PartitionCols:_col0 + Select Operator [SEL_26] (rows=500 width=10) + Output:["_col0","_col1"] + Filter Operator [FIL_106] (rows=500 width=10) + predicate:key is not null + TableScan [TS_24] (rows=500 width=10) + default@src,y,Tbl:COMPLETE,Col:NONE,Output:["key","value"] + <-Union 15 [SIMPLE_EDGE] + <-Map 14 [CONTAINS] llap + Reduce Output Operator [RS_42] + PartitionCols:_col0 + Select Operator [SEL_29] (rows=25 width=7) + Output:["_col0"] + Filter Operator [FIL_107] (rows=25 width=7) + predicate:value is not null + TableScan [TS_27] (rows=25 width=7) + Output:["value"] + <-Map 16 [CONTAINS] llap + Reduce Output Operator [RS_42] + PartitionCols:_col0 + Select Operator [SEL_32] (rows=500 width=10) + Output:["_col0"] + Filter Operator [FIL_108] (rows=500 width=10) + predicate:value is not null + TableScan [TS_30] (rows=500 width=10) + Output:["value"] + <-Map 17 [CONTAINS] llap + Reduce Output Operator [RS_42] + PartitionCols:_col0 + Select Operator [SEL_36] (rows=500 width=10) + Output:["_col0"] + Filter Operator [FIL_109] (rows=500 width=10) + predicate:value is not null + TableScan [TS_34] (rows=500 width=10) + Output:["value"] Reduce Output Operator [RS_3] Group By Operator [GBY_2] (rows=1 width=880) Output:["_col0","_col1"],aggregations:["compute_stats(key, 'hll')","compute_stats(value, 'hll')"] - Select Operator [SEL_1] (rows=3550 width=10) + Select Operator [SEL_1] (rows=3409 width=10) Output:["key","value"] - Please refer to the previous Select Operator [SEL_20] + Please refer to the previous Select Operator [SEL_44] File Output Operator [FS_77] table:{"name:":"default.b"} - Please refer to the previous Select Operator [SEL_20] + Please refer to the previous Select Operator [SEL_44] Reduce Output Operator [RS_3] Group By Operator [GBY_2] (rows=1 width=880) Output:["_col0","_col1"],aggregations:["compute_stats(key, 'hll')","compute_stats(value, 'hll')"] - Select Operator [SEL_1] (rows=3550 width=10) + Select Operator [SEL_1] (rows=3409 width=10) Output:["key","value"] - Please refer to the previous Select Operator [SEL_20] + Please refer to the previous Select Operator [SEL_44] File Output Operator [FS_79] table:{"name:":"default.c"} - Please refer to the previous Select Operator [SEL_20] + Please refer to the previous Select Operator [SEL_44] Reduce Output Operator [RS_3] Group By Operator [GBY_2] (rows=1 width=880) Output:["_col0","_col1"],aggregations:["compute_stats(key, 'hll')","compute_stats(value, 'hll')"] - Select Operator [SEL_1] (rows=3550 width=10) + Select Operator [SEL_1] (rows=3409 width=10) Output:["key","value"] - Please refer to the previous Select Operator [SEL_20] - Reducer 6 llap + Please refer to the previous Select Operator [SEL_44] + Reducer 5 llap File Output Operator [FS_6] Group By Operator [GBY_4] (rows=1 width=880) Output:["_col0","_col1"],aggregations:["compute_stats(VALUE._col0)","compute_stats(VALUE._col1)"] - <- Please refer to the previous Union 4 [CUSTOM_SIMPLE_EDGE] - Reducer 7 llap + <- Please refer to the previous Union 3 [CUSTOM_SIMPLE_EDGE] + Reducer 6 llap File Output Operator [FS_6] Group By Operator [GBY_4] (rows=1 width=880) Output:["_col0","_col1"],aggregations:["compute_stats(VALUE._col0)","compute_stats(VALUE._col1)"] - <- Please refer to the previous Union 4 [CUSTOM_SIMPLE_EDGE] + <- Please refer to the previous Union 3 [CUSTOM_SIMPLE_EDGE] Stage-6 Stats Work{} Stage-1 @@ -3006,30 +2975,31 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Map 1 <- Union 2 (CONTAINS) -Map 12 <- Union 2 (CONTAINS) -Map 13 <- Map 25 (BROADCAST_EDGE) -Map 17 <- Union 18 (CONTAINS) -Map 22 <- Union 18 (CONTAINS) -Map 23 <- Union 20 (CONTAINS) +Map 1 <- Map 12 (BROADCAST_EDGE) +Map 12 <- Map 25 (BROADCAST_EDGE) +Map 13 <- Union 14 (CONTAINS) +Map 16 <- Union 14 (CONTAINS) +Map 18 <- Union 19 (CONTAINS) +Map 23 <- Union 19 (CONTAINS) +Map 24 <- Union 21 (CONTAINS) Map 26 <- Union 27 (CONTAINS) Map 33 <- Union 27 (CONTAINS) Map 34 <- Union 29 (CONTAINS) Map 35 <- Union 31 (CONTAINS) -Reducer 10 <- Reducer 8 (CUSTOM_SIMPLE_EDGE) -Reducer 11 <- Reducer 8 (CUSTOM_SIMPLE_EDGE) -Reducer 15 <- Map 14 (SIMPLE_EDGE), Reducer 21 (SIMPLE_EDGE) -Reducer 16 <- Map 24 (SIMPLE_EDGE), Reducer 15 (SIMPLE_EDGE), Union 5 (CONTAINS) -Reducer 19 <- Union 18 (SIMPLE_EDGE), Union 20 (CONTAINS) -Reducer 21 <- Union 20 (SIMPLE_EDGE) +Reducer 10 <- Map 1 (SIMPLE_EDGE), Map 17 (SIMPLE_EDGE) +Reducer 11 <- Reducer 10 (SIMPLE_EDGE), Reducer 22 (SIMPLE_EDGE), Union 3 (CONTAINS) +Reducer 15 <- Union 14 (SIMPLE_EDGE) +Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 15 (SIMPLE_EDGE), Union 3 (CONTAINS) +Reducer 20 <- Union 19 (SIMPLE_EDGE), Union 21 (CONTAINS) +Reducer 22 <- Union 21 (SIMPLE_EDGE) Reducer 28 <- Union 27 (SIMPLE_EDGE), Union 29 (CONTAINS) -Reducer 3 <- Map 13 (BROADCAST_EDGE), Union 2 (SIMPLE_EDGE) Reducer 30 <- Union 29 (SIMPLE_EDGE), Union 31 (CONTAINS) -Reducer 32 <- Map 13 (BROADCAST_EDGE), Union 31 (SIMPLE_EDGE), Union 7 (CONTAINS) -Reducer 4 <- Map 14 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE), Union 5 (CONTAINS) -Reducer 6 <- Union 5 (SIMPLE_EDGE), Union 7 (CONTAINS) -Reducer 8 <- Union 7 (SIMPLE_EDGE) -Reducer 9 <- Reducer 8 (CUSTOM_SIMPLE_EDGE) +Reducer 32 <- Map 12 (BROADCAST_EDGE), Union 31 (SIMPLE_EDGE), Union 5 (CONTAINS) +Reducer 4 <- Union 3 (SIMPLE_EDGE), Union 5 (CONTAINS) +Reducer 6 <- Union 5 (SIMPLE_EDGE) +Reducer 7 <- Reducer 6 (CUSTOM_SIMPLE_EDGE) +Reducer 8 <- Reducer 6 (CUSTOM_SIMPLE_EDGE) +Reducer 9 <- Reducer 6 (CUSTOM_SIMPLE_EDGE) Stage-5 Stats Work{} @@ -3039,47 +3009,47 @@ Stage-5 Stage-4 Dependency Collection{} Stage-3 - Reducer 10 llap + Reducer 7 llap File Output Operator [FS_6] Group By Operator [GBY_4] (rows=1 width=880) Output:["_col0","_col1"],aggregations:["compute_stats(VALUE._col0)","compute_stats(VALUE._col1)"] - <-Reducer 8 [CUSTOM_SIMPLE_EDGE] llap + <-Reducer 6 [CUSTOM_SIMPLE_EDGE] llap PARTITION_ONLY_SHUFFLE [RS_3] Group By Operator [GBY_2] (rows=1 width=880) Output:["_col0","_col1"],aggregations:["compute_stats(key, 'hll')","compute_stats(value, 'hll')"] - Select Operator [SEL_1] (rows=530 width=10) + Select Operator [SEL_1] (rows=544 width=10) Output:["key","value"] - Group By Operator [GBY_120] (rows=530 width=10) + Group By Operator [GBY_120] (rows=544 width=10) Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 - <-Union 7 [SIMPLE_EDGE] + <-Union 5 [SIMPLE_EDGE] <-Reducer 32 [CONTAINS] llap Reduce Output Operator [RS_119] PartitionCols:_col0, _col1 - Group By Operator [GBY_118] (rows=1061 width=10) + Group By Operator [GBY_118] (rows=1089 width=10) Output:["_col0","_col1"],keys:_col0, _col1 Select Operator [SEL_114] (rows=484 width=10) Output:["_col0","_col1"] - Map Join Operator [MAPJOIN_172] (rows=484 width=10) + Map Join Operator [MAPJOIN_169] (rows=484 width=10) Conds:RS_111._col1=SEL_107._col1(Inner),Output:["_col0","_col3"] - <-Map 13 [BROADCAST_EDGE] llap + <-Map 12 [BROADCAST_EDGE] llap BROADCAST [RS_111] PartitionCols:_col1 - Map Join Operator [MAPJOIN_171] (rows=27 width=7) - Conds:SEL_15._col0=RS_109._col0(Inner),Output:["_col0","_col1","_col3"] + Map Join Operator [MAPJOIN_166] (rows=27 width=7) + Conds:SEL_5._col0=RS_109._col0(Inner),Output:["_col0","_col1","_col3"] <-Map 25 [BROADCAST_EDGE] llap BROADCAST [RS_109] PartitionCols:_col0 Select Operator [SEL_74] (rows=25 width=7) Output:["_col0","_col1"] - Filter Operator [FIL_162] (rows=25 width=7) + Filter Operator [FIL_159] (rows=25 width=7) predicate:key is not null TableScan [TS_72] (rows=25 width=7) default@src1,y,Tbl:COMPLETE,Col:NONE,Output:["key","value"] - <-Select Operator [SEL_15] (rows=25 width=7) + <-Select Operator [SEL_5] (rows=25 width=7) Output:["_col0","_col1"] - Filter Operator [FIL_154] (rows=25 width=7) + Filter Operator [FIL_150] (rows=25 width=7) predicate:(key is not null and value is not null) - TableScan [TS_13] (rows=25 width=7) + TableScan [TS_3] (rows=25 width=7) default@src1,x,Tbl:COMPLETE,Col:NONE,Output:["key","value"] <-Select Operator [SEL_107] (rows=440 width=10) Output:["_col1"] @@ -3093,7 +3063,7 @@ Stage-5 Output:["_col0","_col1"],keys:_col1, _col0 Select Operator [SEL_100] (rows=500 width=10) Output:["_col0","_col1"] - Filter Operator [FIL_166] (rows=500 width=10) + Filter Operator [FIL_163] (rows=500 width=10) predicate:value is not null TableScan [TS_98] (rows=500 width=10) Output:["key","value"] @@ -3114,7 +3084,7 @@ Stage-5 Output:["_col0","_col1"],keys:_col1, _col0 Select Operator [SEL_90] (rows=500 width=10) Output:["_col0","_col1"] - Filter Operator [FIL_165] (rows=500 width=10) + Filter Operator [FIL_162] (rows=500 width=10) predicate:value is not null TableScan [TS_88] (rows=500 width=10) Output:["key","value"] @@ -3135,7 +3105,7 @@ Stage-5 Output:["_col0","_col1"],keys:_col1, _col0 Select Operator [SEL_77] (rows=25 width=7) Output:["_col0","_col1"] - Filter Operator [FIL_163] (rows=25 width=7) + Filter Operator [FIL_160] (rows=25 width=7) predicate:value is not null TableScan [TS_75] (rows=25 width=7) Output:["key","value"] @@ -3146,174 +3116,174 @@ Stage-5 Output:["_col0","_col1"],keys:_col1, _col0 Select Operator [SEL_80] (rows=500 width=10) Output:["_col0","_col1"] - Filter Operator [FIL_164] (rows=500 width=10) + Filter Operator [FIL_161] (rows=500 width=10) predicate:value is not null TableScan [TS_78] (rows=500 width=10) Output:["key","value"] - <-Reducer 6 [CONTAINS] llap + <-Reducer 4 [CONTAINS] llap Reduce Output Operator [RS_119] PartitionCols:_col0, _col1 - Group By Operator [GBY_118] (rows=1061 width=10) + Group By Operator [GBY_118] (rows=1089 width=10) Output:["_col0","_col1"],keys:_col0, _col1 - Group By Operator [GBY_67] (rows=577 width=10) + Group By Operator [GBY_67] (rows=605 width=10) Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 - <-Union 5 [SIMPLE_EDGE] - <-Reducer 16 [CONTAINS] llap + <-Union 3 [SIMPLE_EDGE] + <-Reducer 11 [CONTAINS] llap Reduce Output Operator [RS_66] PartitionCols:_col0, _col1 - Group By Operator [GBY_65] (rows=1155 width=10) + Group By Operator [GBY_65] (rows=1210 width=10) Output:["_col0","_col1"],keys:_col0, _col1 Select Operator [SEL_61] (rows=605 width=10) Output:["_col0","_col1"] - Merge Join Operator [MERGEJOIN_170] (rows=605 width=10) - Conds:RS_58._col2=RS_59._col0(Inner),Output:["_col2","_col5"] - <-Map 24 [SIMPLE_EDGE] llap - SHUFFLE [RS_59] - PartitionCols:_col0 - Select Operator [SEL_54] (rows=500 width=10) - Output:["_col0","_col1"] - Filter Operator [FIL_160] (rows=500 width=10) - predicate:key is not null - TableScan [TS_52] (rows=500 width=10) - default@src,y,Tbl:COMPLETE,Col:NONE,Output:["key","value"] - <-Reducer 15 [SIMPLE_EDGE] llap + Merge Join Operator [MERGEJOIN_168] (rows=605 width=10) + Conds:RS_58._col1=RS_59._col1(Inner),Output:["_col0","_col3"] + <-Reducer 10 [SIMPLE_EDGE] llap SHUFFLE [RS_58] - PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_169] (rows=550 width=10) - Conds:RS_55._col1=RS_56._col1(Inner),Output:["_col2"] - <-Map 14 [SIMPLE_EDGE] llap - SHUFFLE [RS_56] - PartitionCols:_col1 - Select Operator [SEL_51] (rows=500 width=10) + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_165] (rows=550 width=10) + Conds:RS_55._col0=RS_56._col0(Inner),Output:["_col0","_col1","_col3"] + <-Map 1 [SIMPLE_EDGE] llap + SHUFFLE [RS_55] + PartitionCols:_col0 + Select Operator [SEL_28] (rows=500 width=10) Output:["_col0","_col1"] - Filter Operator [FIL_159] (rows=500 width=10) + Filter Operator [FIL_153] (rows=500 width=10) predicate:(key is not null and value is not null) - TableScan [TS_16] (rows=500 width=10) + TableScan [TS_0] (rows=500 width=10) default@src,y,Tbl:COMPLETE,Col:NONE,Output:["key","value"] - <-Reducer 21 [SIMPLE_EDGE] llap - SHUFFLE [RS_55] - PartitionCols:_col1 - Select Operator [SEL_48] (rows=381 width=10) - Output:["_col1"] - Group By Operator [GBY_47] (rows=381 width=10) - Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 - <-Union 20 [SIMPLE_EDGE] - <-Map 23 [CONTAINS] llap - Reduce Output Operator [RS_46] - PartitionCols:_col0, _col1 - Group By Operator [GBY_45] (rows=762 width=10) - Output:["_col0","_col1"],keys:_col1, _col0 - Select Operator [SEL_41] (rows=500 width=10) - Output:["_col0","_col1"] - Filter Operator [FIL_158] (rows=500 width=10) - predicate:value is not null - TableScan [TS_39] (rows=500 width=10) - Output:["key","value"] - <-Reducer 19 [CONTAINS] llap - Reduce Output Operator [RS_46] - PartitionCols:_col0, _col1 - Group By Operator [GBY_45] (rows=762 width=10) - Output:["_col0","_col1"],keys:_col1, _col0 - Select Operator [SEL_38] (rows=262 width=10) - Output:["_col0","_col1"] - Group By Operator [GBY_37] (rows=262 width=10) - Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 - <-Union 18 [SIMPLE_EDGE] - <-Map 17 [CONTAINS] llap - Reduce Output Operator [RS_36] - PartitionCols:_col0, _col1 - Group By Operator [GBY_35] (rows=525 width=10) - Output:["_col0","_col1"],keys:_col1, _col0 - Select Operator [SEL_28] (rows=25 width=7) - Output:["_col0","_col1"] - Filter Operator [FIL_156] (rows=25 width=7) - predicate:value is not null - TableScan [TS_26] (rows=25 width=7) - Output:["key","value"] - <-Map 22 [CONTAINS] llap - Reduce Output Operator [RS_36] - PartitionCols:_col0, _col1 - Group By Operator [GBY_35] (rows=525 width=10) - Output:["_col0","_col1"],keys:_col1, _col0 - Select Operator [SEL_31] (rows=500 width=10) - Output:["_col0","_col1"] - Filter Operator [FIL_157] (rows=500 width=10) - predicate:value is not null - TableScan [TS_29] (rows=500 width=10) - Output:["key","value"] - <-Reducer 4 [CONTAINS] llap + <-Map 17 [SIMPLE_EDGE] llap + SHUFFLE [RS_56] + PartitionCols:_col0 + Select Operator [SEL_31] (rows=500 width=10) + Output:["_col0","_col1"] + Filter Operator [FIL_154] (rows=500 width=10) + predicate:key is not null + TableScan [TS_29] (rows=500 width=10) + default@src,y,Tbl:COMPLETE,Col:NONE,Output:["key","value"] + <-Reducer 22 [SIMPLE_EDGE] llap + SHUFFLE [RS_59] + PartitionCols:_col1 + Select Operator [SEL_54] (rows=381 width=10) + Output:["_col1"] + Group By Operator [GBY_53] (rows=381 width=10) + Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 + <-Union 21 [SIMPLE_EDGE] + <-Map 24 [CONTAINS] llap + Reduce Output Operator [RS_52] + PartitionCols:_col0, _col1 + Group By Operator [GBY_51] (rows=762 width=10) + Output:["_col0","_col1"],keys:_col1, _col0 + Select Operator [SEL_47] (rows=500 width=10) + Output:["_col0","_col1"] + Filter Operator [FIL_157] (rows=500 width=10) + predicate:value is not null + TableScan [TS_45] (rows=500 width=10) + Output:["key","value"] + <-Reducer 20 [CONTAINS] llap + Reduce Output Operator [RS_52] + PartitionCols:_col0, _col1 + Group By Operator [GBY_51] (rows=762 width=10) + Output:["_col0","_col1"],keys:_col1, _col0 + Select Operator [SEL_44] (rows=262 width=10) + Output:["_col0","_col1"] + Group By Operator [GBY_43] (rows=262 width=10) + Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 + <-Union 19 [SIMPLE_EDGE] + <-Map 18 [CONTAINS] llap + Reduce Output Operator [RS_42] + PartitionCols:_col0, _col1 + Group By Operator [GBY_41] (rows=525 width=10) + Output:["_col0","_col1"],keys:_col1, _col0 + Select Operator [SEL_34] (rows=25 width=7) + Output:["_col0","_col1"] + Filter Operator [FIL_155] (rows=25 width=7) + predicate:value is not null + TableScan [TS_32] (rows=25 width=7) + Output:["key","value"] + <-Map 23 [CONTAINS] llap + Reduce Output Operator [RS_42] + PartitionCols:_col0, _col1 + Group By Operator [GBY_41] (rows=525 width=10) + Output:["_col0","_col1"],keys:_col1, _col0 + Select Operator [SEL_37] (rows=500 width=10) + Output:["_col0","_col1"] + Filter Operator [FIL_156] (rows=500 width=10) + predicate:value is not null + TableScan [TS_35] (rows=500 width=10) + Output:["key","value"] + <-Reducer 2 [CONTAINS] llap Reduce Output Operator [RS_66] PartitionCols:_col0, _col1 - Group By Operator [GBY_65] (rows=1155 width=10) + Group By Operator [GBY_65] (rows=1210 width=10) Output:["_col0","_col1"],keys:_col0, _col1 - Select Operator [SEL_25] (rows=550 width=10) + Select Operator [SEL_25] (rows=605 width=10) Output:["_col0","_col1"] - Merge Join Operator [MERGEJOIN_168] (rows=550 width=10) - Conds:RS_22._col2=RS_23._col0(Inner),Output:["_col2","_col5"] - <-Map 14 [SIMPLE_EDGE] llap - SHUFFLE [RS_23] - PartitionCols:_col0 - Select Operator [SEL_18] (rows=500 width=10) - Output:["_col0","_col1"] - Filter Operator [FIL_155] (rows=500 width=10) - predicate:key is not null - Please refer to the previous TableScan [TS_16] - <-Reducer 3 [SIMPLE_EDGE] llap + Merge Join Operator [MERGEJOIN_167] (rows=605 width=10) + Conds:RS_22._col3=RS_23._col1(Inner),Output:["_col1","_col2"] + <-Map 1 [SIMPLE_EDGE] llap SHUFFLE [RS_22] - PartitionCols:_col2 - Map Join Operator [MAPJOIN_167] (rows=288 width=10) - Conds:SEL_12._col1=RS_20._col1(Inner),Output:["_col2"] - <-Map 13 [BROADCAST_EDGE] llap + PartitionCols:_col3 + Map Join Operator [MAPJOIN_164] (rows=550 width=10) + Conds:SEL_2._col0=RS_20._col0(Inner),Output:["_col1","_col2","_col3"] + <-Map 12 [BROADCAST_EDGE] llap BROADCAST [RS_20] - PartitionCols:_col1 - Please refer to the previous Select Operator [SEL_15] - <-Select Operator [SEL_12] (rows=262 width=10) - Output:["_col1"] - Group By Operator [GBY_11] (rows=262 width=10) - Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 - <-Union 2 [SIMPLE_EDGE] - <-Map 1 [CONTAINS] llap - Reduce Output Operator [RS_10] - PartitionCols:_col0, _col1 - Group By Operator [GBY_9] (rows=525 width=10) - Output:["_col0","_col1"],keys:_col1, _col0 - Select Operator [SEL_2] (rows=25 width=7) - Output:["_col0","_col1"] - Filter Operator [FIL_152] (rows=25 width=7) - predicate:value is not null - TableScan [TS_0] (rows=25 width=7) - Output:["key","value"] - <-Map 12 [CONTAINS] llap - Reduce Output Operator [RS_10] - PartitionCols:_col0, _col1 - Group By Operator [GBY_9] (rows=525 width=10) - Output:["_col0","_col1"],keys:_col1, _col0 - Select Operator [SEL_5] (rows=500 width=10) - Output:["_col0","_col1"] - Filter Operator [FIL_153] (rows=500 width=10) - predicate:value is not null - TableScan [TS_3] (rows=500 width=10) - Output:["key","value"] - Reducer 11 llap + PartitionCols:_col0 + Please refer to the previous Select Operator [SEL_5] + <-Select Operator [SEL_2] (rows=500 width=10) + Output:["_col0","_col1"] + Filter Operator [FIL_149] (rows=500 width=10) + predicate:key is not null + Please refer to the previous TableScan [TS_0] + <-Reducer 15 [SIMPLE_EDGE] llap + SHUFFLE [RS_23] + PartitionCols:_col1 + Select Operator [SEL_18] (rows=262 width=10) + Output:["_col1"] + Group By Operator [GBY_17] (rows=262 width=10) + Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 + <-Union 14 [SIMPLE_EDGE] + <-Map 13 [CONTAINS] llap + Reduce Output Operator [RS_16] + PartitionCols:_col0, _col1 + Group By Operator [GBY_15] (rows=525 width=10) + Output:["_col0","_col1"],keys:_col1, _col0 + Select Operator [SEL_8] (rows=25 width=7) + Output:["_col0","_col1"] + Filter Operator [FIL_151] (rows=25 width=7) + predicate:value is not null + TableScan [TS_6] (rows=25 width=7) + Output:["key","value"] + <-Map 16 [CONTAINS] llap + Reduce Output Operator [RS_16] + PartitionCols:_col0, _col1 + Group By Operator [GBY_15] (rows=525 width=10) + Output:["_col0","_col1"],keys:_col1, _col0 + Select Operator [SEL_11] (rows=500 width=10) + Output:["_col0","_col1"] + Filter Operator [FIL_152] (rows=500 width=10) + predicate:value is not null + TableScan [TS_9] (rows=500 width=10) + Output:["key","value"] + Reducer 8 llap File Output Operator [FS_6] Group By Operator [GBY_4] (rows=1 width=880) Output:["_col0","_col1"],aggregations:["compute_stats(VALUE._col0)","compute_stats(VALUE._col1)"] - <-Reducer 8 [CUSTOM_SIMPLE_EDGE] llap + <-Reducer 6 [CUSTOM_SIMPLE_EDGE] llap PARTITION_ONLY_SHUFFLE [RS_3] Group By Operator [GBY_2] (rows=1 width=880) Output:["_col0","_col1"],aggregations:["compute_stats(key, 'hll')","compute_stats(value, 'hll')"] - Select Operator [SEL_1] (rows=530 width=10) + Select Operator [SEL_1] (rows=544 width=10) Output:["key","value"] Please refer to the previous Group By Operator [GBY_120] Reducer 9 llap File Output Operator [FS_6] Group By Operator [GBY_4] (rows=1 width=880) Output:["_col0","_col1"],aggregations:["compute_stats(VALUE._col0)","compute_stats(VALUE._col1)"] - <-Reducer 8 [CUSTOM_SIMPLE_EDGE] llap + <-Reducer 6 [CUSTOM_SIMPLE_EDGE] llap PARTITION_ONLY_SHUFFLE [RS_3] Group By Operator [GBY_2] (rows=1 width=880) Output:["_col0","_col1"],aggregations:["compute_stats(key, 'hll')","compute_stats(value, 'hll')"] - Select Operator [SEL_1] (rows=530 width=10) + Select Operator [SEL_1] (rows=544 width=10) Output:["key","value"] Please refer to the previous Group By Operator [GBY_120] Stage-6 diff --git a/ql/src/test/results/clientpositive/llap/explainuser_4.q.out b/ql/src/test/results/clientpositive/llap/explainuser_4.q.out index c4fdc18..d5f8cb7 100644 --- a/ql/src/test/results/clientpositive/llap/explainuser_4.q.out +++ b/ql/src/test/results/clientpositive/llap/explainuser_4.q.out @@ -26,11 +26,11 @@ Stage-0 Stage-1 Reducer 3 llap File Output Operator [FS_12] - Select Operator [SEL_11] (rows=2076 width=553) + Select Operator [SEL_11] (rows=2048 width=552) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col19","_col20","_col21","_col22","_col23"] <-Reducer 2 [SIMPLE_EDGE] llap SHUFFLE [RS_10] - Merge Join Operator [MERGEJOIN_17] (rows=2076 width=553) + Merge Join Operator [MERGEJOIN_17] (rows=2048 width=552) Conds:RS_6._col2=RS_7._col2(Inner),Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col19","_col20","_col21","_col22","_col23"] <-Map 1 [SIMPLE_EDGE] llap SHUFFLE [RS_6] @@ -111,7 +111,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_11] Group By Operator [GBY_10] (rows=1 width=8) Output:["_col0"],aggregations:["count()"] - Merge Join Operator [MERGEJOIN_19] (rows=2076 width=8) + Merge Join Operator [MERGEJOIN_19] (rows=2048 width=8) Conds:RS_6._col0=RS_7._col0(Inner) <-Map 1 [SIMPLE_EDGE] llap SHUFFLE [RS_6] @@ -180,18 +180,18 @@ Stage-0 Stage-1 Reducer 4 llap File Output Operator [FS_16] - Select Operator [SEL_15] (rows=623 width=11) + Select Operator [SEL_15] (rows=631 width=11) Output:["_col0","_col1"] <-Reducer 3 [SIMPLE_EDGE] llap SHUFFLE [RS_14] - Group By Operator [GBY_12] (rows=623 width=11) + Group By Operator [GBY_12] (rows=631 width=11) Output:["_col0","_col1"],aggregations:["count(VALUE._col0)"],keys:KEY._col0 <-Reducer 2 [SIMPLE_EDGE] llap SHUFFLE [RS_11] PartitionCols:_col0 - Group By Operator [GBY_10] (rows=623 width=11) + Group By Operator [GBY_10] (rows=631 width=11) Output:["_col0","_col1"],aggregations:["count()"],keys:_col0 - Merge Join Operator [MERGEJOIN_21] (rows=2076 width=3) + Merge Join Operator [MERGEJOIN_21] (rows=2048 width=3) Conds:RS_6._col1=RS_7._col0(Inner),Output:["_col0"] <-Map 1 [SIMPLE_EDGE] llap SHUFFLE [RS_6] diff --git a/ql/src/test/results/clientpositive/llap/groupby1.q.out b/ql/src/test/results/clientpositive/llap/groupby1.q.out index d58a9fd..d60895d 100644 --- a/ql/src/test/results/clientpositive/llap/groupby1.q.out +++ b/ql/src/test/results/clientpositive/llap/groupby1.q.out @@ -67,14 +67,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: final outputColumnNames: _col0, _col1 - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), _col1 (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 309 Data size: 3708 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 3792 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 309 Data size: 3708 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 3792 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/groupby2.q.out b/ql/src/test/results/clientpositive/llap/groupby2.q.out index c452719..49733b6 100644 --- a/ql/src/test/results/clientpositive/llap/groupby2.q.out +++ b/ql/src/test/results/clientpositive/llap/groupby2.q.out @@ -70,14 +70,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: final outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 309 Data size: 61800 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 63200 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), UDFToInteger(_col1) (type: int), concat(_col0, _col2) (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 309 Data size: 114948 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 117552 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 309 Data size: 114948 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 117552 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/groupby_resolution.q.out b/ql/src/test/results/clientpositive/llap/groupby_resolution.q.out index d3b85f8..d026bd9 100644 --- a/ql/src/test/results/clientpositive/llap/groupby_resolution.q.out +++ b/ql/src/test/results/clientpositive/llap/groupby_resolution.q.out @@ -38,10 +38,10 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -93,10 +93,10 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -164,10 +164,10 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: final outputColumnNames: _col0, _col1 - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -235,10 +235,10 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: final outputColumnNames: _col0, _col1 - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/hybridgrace_hashjoin_1.q.out b/ql/src/test/results/clientpositive/llap/hybridgrace_hashjoin_1.q.out index 02dc49d..8a6d5b6 100644 --- a/ql/src/test/results/clientpositive/llap/hybridgrace_hashjoin_1.q.out +++ b/ql/src/test/results/clientpositive/llap/hybridgrace_hashjoin_1.q.out @@ -56,7 +56,7 @@ STAGE PLANS: 1 _col0 (type: int) input vertices: 1 Map 3 - Statistics: Num rows: 25044 Data size: 200352 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 24737 Data size: 197896 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash @@ -177,7 +177,7 @@ STAGE PLANS: 1 _col0 (type: int) input vertices: 1 Map 3 - Statistics: Num rows: 25044 Data size: 200352 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 24737 Data size: 197896 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash @@ -296,7 +296,7 @@ STAGE PLANS: 1 _col0 (type: int) input vertices: 1 Map 3 - Statistics: Num rows: 18694 Data size: 149552 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 18464 Data size: 147712 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash @@ -413,7 +413,7 @@ STAGE PLANS: 1 _col0 (type: int) input vertices: 1 Map 3 - Statistics: Num rows: 18694 Data size: 149552 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 18464 Data size: 147712 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash @@ -527,7 +527,7 @@ STAGE PLANS: 1 _col0 (type: int) input vertices: 1 Map 3 - Statistics: Num rows: 25044 Data size: 200352 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 24737 Data size: 197896 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash @@ -638,7 +638,7 @@ STAGE PLANS: 1 _col0 (type: int) input vertices: 1 Map 3 - Statistics: Num rows: 25044 Data size: 200352 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 24737 Data size: 197896 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash diff --git a/ql/src/test/results/clientpositive/llap/join1.q.out b/ql/src/test/results/clientpositive/llap/join1.q.out index 3c0a155..810a227 100644 --- a/ql/src/test/results/clientpositive/llap/join1.q.out +++ b/ql/src/test/results/clientpositive/llap/join1.q.out @@ -78,14 +78,14 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col2 - Statistics: Num rows: 809 Data size: 144002 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), _col2 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 809 Data size: 76855 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 75145 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 809 Data size: 76855 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 75145 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/join32_lessSize.q.out b/ql/src/test/results/clientpositive/llap/join32_lessSize.q.out index 5b5be13..1022b90 100644 --- a/ql/src/test/results/clientpositive/llap/join32_lessSize.q.out +++ b/ql/src/test/results/clientpositive/llap/join32_lessSize.q.out @@ -67,13 +67,13 @@ STAGE PLANS: input vertices: 1 Map 4 Position of Big Table: 0 - Statistics: Num rows: 40 Data size: 10640 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 10374 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col3 (type: string) null sort order: a sort order: + Map-reduce partition columns: _col3 (type: string) - Statistics: Num rows: 40 Data size: 10640 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 10374 Basic stats: COMPLETE Column stats: COMPLETE tag: 0 value expressions: _col1 (type: string), _col2 (type: string) auto parallelism: true @@ -295,17 +295,17 @@ STAGE PLANS: 1 _col0 (type: string) outputColumnNames: _col1, _col2, _col4 Position of Big Table: 1 - Statistics: Num rows: 64 Data size: 17152 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 63 Data size: 16884 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: string), _col4 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 64 Data size: 17152 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 63 Data size: 16884 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 64 Data size: 17152 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 63 Data size: 16884 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -562,10 +562,8 @@ STAGE PLANS: Tez #### A masked pattern was here #### Edges: - Map 1 <- Map 5 (BROADCAST_EDGE) - Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 6 (SIMPLE_EDGE) - Reducer 3 <- Map 7 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) - Reducer 4 <- Reducer 3 (CUSTOM_SIMPLE_EDGE) + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) + Reducer 3 <- Map 6 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 @@ -582,27 +580,15 @@ STAGE PLANS: expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE - Map Join Operator - condition map: - Inner Join 0 to 1 - Estimated key counts: Map 5 => 25 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col3 - input vertices: - 1 Map 5 - Position of Big Table: 0 - Statistics: Num rows: 39 Data size: 10296 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col1 (type: string) - null sort order: a - sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 39 Data size: 10296 Basic stats: COMPLETE Column stats: COMPLETE - tag: 0 - value expressions: _col0 (type: string), _col3 (type: string) - auto parallelism: true + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: a + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE + tag: 0 + value expressions: _col1 (type: string) + auto parallelism: true Execution mode: llap LLAP IO: no inputs Path -> Alias: @@ -735,24 +721,25 @@ STAGE PLANS: Map 6 Map Operator Tree: TableScan - alias: w - Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE + alias: y + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false - predicate: value is not null (type: boolean) - Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE + predicate: key is not null (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: value (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE - tag: 1 + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + tag: 2 + value expressions: _col1 (type: string) auto parallelism: true Execution mode: llap LLAP IO: no inputs @@ -806,29 +793,28 @@ STAGE PLANS: name: default.src name: default.src Truncated Path -> Alias: - /src [w] - Map 7 + /src [y] + Map 6 Map Operator Tree: TableScan - alias: y - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + alias: w + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false - predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + predicate: value is not null (type: boolean) + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + expressions: value (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE tag: 1 - value expressions: _col1 (type: string) auto parallelism: true Execution mode: llap LLAP IO: no inputs @@ -882,7 +868,7 @@ STAGE PLANS: name: default.src name: default.src Truncated Path -> Alias: - /src [y] + /src [w] Reducer 2 Execution mode: llap Needs Tagging: false @@ -890,20 +876,22 @@ STAGE PLANS: Merge Join Operator condition map: Inner Join 0 to 1 + Inner Join 0 to 2 keys: - 0 _col1 (type: string) + 0 _col0 (type: string) 1 _col0 (type: string) - outputColumnNames: _col0, _col3 - Position of Big Table: 1 - Statistics: Num rows: 63 Data size: 11025 Basic stats: COMPLETE Column stats: COMPLETE + 2 _col0 (type: string) + outputColumnNames: _col0, _col1, _col3, _col5 + Position of Big Table: 2 + Statistics: Num rows: 61 Data size: 21655 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: _col1 (type: string) null sort order: a sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 63 Data size: 11025 Basic stats: COMPLETE Column stats: COMPLETE + Map-reduce partition columns: _col1 (type: string) + Statistics: Num rows: 61 Data size: 21655 Basic stats: COMPLETE Column stats: COMPLETE tag: 0 - value expressions: _col3 (type: string) + value expressions: _col0 (type: string), _col3 (type: string), _col5 (type: string) auto parallelism: true Reducer 3 Execution mode: llap @@ -913,21 +901,21 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) + 0 _col1 (type: string) 1 _col0 (type: string) - outputColumnNames: _col0, _col3, _col6 + outputColumnNames: _col0, _col3, _col5 Position of Big Table: 0 - Statistics: Num rows: 101 Data size: 26866 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 99 Data size: 26334 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: _col0 (type: string), _col3 (type: string), _col6 (type: string) + expressions: _col0 (type: string), _col3 (type: string), _col5 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 101 Data size: 26866 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 99 Data size: 26334 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 101 Data size: 26866 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 99 Data size: 26334 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -1287,17 +1275,17 @@ STAGE PLANS: input vertices: 1 Map 5 Position of Big Table: 0 - Statistics: Num rows: 40 Data size: 7000 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6825 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string), _col2 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 40 Data size: 7000 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6825 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) null sort order: a sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 40 Data size: 7000 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6825 Basic stats: COMPLETE Column stats: COMPLETE tag: 1 value expressions: _col0 (type: string) auto parallelism: true @@ -1442,17 +1430,17 @@ STAGE PLANS: 1 _col1 (type: string) outputColumnNames: _col0, _col3, _col4 Position of Big Table: 0 - Statistics: Num rows: 64 Data size: 17024 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 63 Data size: 16758 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col3 (type: string), _col0 (type: string), _col4 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 64 Data size: 17024 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 63 Data size: 16758 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 64 Data size: 17024 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 63 Data size: 16758 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -1948,17 +1936,17 @@ STAGE PLANS: 1 _col1 (type: string) outputColumnNames: _col0, _col3, _col4 Position of Big Table: 1 - Statistics: Num rows: 64 Data size: 17024 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 63 Data size: 16758 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col3 (type: string), _col0 (type: string), _col4 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 64 Data size: 17024 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 63 Data size: 16758 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 64 Data size: 17024 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 63 Data size: 16758 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -2044,17 +2032,17 @@ STAGE PLANS: 1 _col0 (type: string) outputColumnNames: _col1, _col2 Position of Big Table: 1 - Statistics: Num rows: 40 Data size: 7000 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6825 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string), _col2 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 40 Data size: 7000 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6825 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) null sort order: a sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 40 Data size: 7000 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6825 Basic stats: COMPLETE Column stats: COMPLETE tag: 1 value expressions: _col0 (type: string) auto parallelism: true @@ -2295,17 +2283,17 @@ STAGE PLANS: 1 _col0 (type: string) outputColumnNames: _col1, _col2 input vertices: - 1 Map 5 - Statistics: Num rows: 40 Data size: 7000 Basic stats: COMPLETE Column stats: COMPLETE + 1 Map 4 + Statistics: Num rows: 39 Data size: 6825 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string), _col2 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 40 Data size: 7000 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6825 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 40 Data size: 7000 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6825 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string) Execution mode: llap LLAP IO: no inputs @@ -2339,14 +2327,14 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col1 (type: string) outputColumnNames: _col0, _col3, _col4 - Statistics: Num rows: 64 Data size: 17024 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 63 Data size: 16758 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col3 (type: string), _col0 (type: string), _col4 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 64 Data size: 17024 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 63 Data size: 16758 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 64 Data size: 17024 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 63 Data size: 16758 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -2585,17 +2573,17 @@ STAGE PLANS: 1 _col0 (type: string) outputColumnNames: _col1, _col2 input vertices: - 1 Map 5 - Statistics: Num rows: 40 Data size: 7000 Basic stats: COMPLETE Column stats: COMPLETE + 1 Map 4 + Statistics: Num rows: 39 Data size: 6825 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string), _col2 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 40 Data size: 7000 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6825 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 40 Data size: 7000 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6825 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string) Execution mode: llap LLAP IO: no inputs @@ -2629,14 +2617,14 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col1 (type: string) outputColumnNames: _col0, _col3, _col4 - Statistics: Num rows: 64 Data size: 17024 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 63 Data size: 16758 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col3 (type: string), _col0 (type: string), _col4 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 64 Data size: 17024 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 63 Data size: 16758 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 64 Data size: 17024 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 63 Data size: 16758 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/join_max_hashtable.q.out b/ql/src/test/results/clientpositive/llap/join_max_hashtable.q.out index ef1a6f3..cb090c2 100644 --- a/ql/src/test/results/clientpositive/llap/join_max_hashtable.q.out +++ b/ql/src/test/results/clientpositive/llap/join_max_hashtable.q.out @@ -39,10 +39,10 @@ STAGE PLANS: outputColumnNames: _col0, _col1 input vertices: 1 Map 2 - Statistics: Num rows: 809 Data size: 144002 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 809 Data size: 144002 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -116,10 +116,10 @@ STAGE PLANS: outputColumnNames: _col0, _col1 input vertices: 1 Map 2 - Statistics: Num rows: 809 Data size: 144002 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 809 Data size: 144002 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -223,11 +223,11 @@ STAGE PLANS: outputColumnNames: _col0, _col1 input vertices: 1 Map 3 - Statistics: Num rows: 809 Data size: 144002 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE HybridGraceHashJoin: true File Output Operator compressed: false - Statistics: Num rows: 809 Data size: 144002 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -309,11 +309,11 @@ STAGE PLANS: outputColumnNames: _col0, _col1 input vertices: 1 Map 3 - Statistics: Num rows: 809 Data size: 144002 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE HybridGraceHashJoin: true File Output Operator compressed: false - Statistics: Num rows: 809 Data size: 144002 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -396,11 +396,11 @@ STAGE PLANS: outputColumnNames: _col0, _col1 input vertices: 1 Map 3 - Statistics: Num rows: 809 Data size: 144002 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE HybridGraceHashJoin: true File Output Operator compressed: false - Statistics: Num rows: 809 Data size: 144002 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -482,11 +482,11 @@ STAGE PLANS: outputColumnNames: _col0, _col1 input vertices: 1 Map 3 - Statistics: Num rows: 809 Data size: 144002 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE HybridGraceHashJoin: true File Output Operator compressed: false - Statistics: Num rows: 809 Data size: 144002 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -539,10 +539,10 @@ STAGE PLANS: outputColumnNames: _col0, _col1 input vertices: 1 Map 2 - Statistics: Num rows: 809 Data size: 144002 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 809 Data size: 144002 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -616,10 +616,10 @@ STAGE PLANS: outputColumnNames: _col0, _col1 input vertices: 1 Map 2 - Statistics: Num rows: 809 Data size: 144002 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 809 Data size: 144002 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/limit_join_transpose.q.out b/ql/src/test/results/clientpositive/llap/limit_join_transpose.q.out index 4dd7432..ebaac18 100644 --- a/ql/src/test/results/clientpositive/llap/limit_join_transpose.q.out +++ b/ql/src/test/results/clientpositive/llap/limit_join_transpose.q.out @@ -66,7 +66,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 809 Data size: 288004 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 1 Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE @@ -167,7 +167,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 809 Data size: 288004 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 1 Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE @@ -954,7 +954,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 809 Data size: 288004 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 1 Offset of rows: 1 @@ -1056,7 +1056,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 809 Data size: 288004 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 1 Offset of rows: 1 diff --git a/ql/src/test/results/clientpositive/llap/limit_pushdown.q.out b/ql/src/test/results/clientpositive/llap/limit_pushdown.q.out index b067e45..a4040bd 100644 --- a/ql/src/test/results/clientpositive/llap/limit_pushdown.q.out +++ b/ql/src/test/results/clientpositive/llap/limit_pushdown.q.out @@ -395,12 +395,12 @@ STAGE PLANS: keys: cdouble (type: double) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 5570 Data size: 33272 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5528 Data size: 33024 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: double) sort order: + Map-reduce partition columns: _col0 (type: double) - Statistics: Num rows: 5570 Data size: 33272 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5528 Data size: 33024 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.3 Execution mode: llap LLAP IO: all inputs @@ -411,7 +411,7 @@ STAGE PLANS: keys: KEY._col0 (type: double) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 5570 Data size: 33272 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5528 Data size: 33024 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 20 Statistics: Num rows: 20 Data size: 128 Basic stats: COMPLETE Column stats: COMPLETE @@ -1070,7 +1070,7 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 309 Data size: 30591 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 307 Data size: 30393 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 20 Statistics: Num rows: 20 Data size: 1980 Basic stats: COMPLETE Column stats: COMPLETE diff --git a/ql/src/test/results/clientpositive/llap/limit_pushdown3.q.out b/ql/src/test/results/clientpositive/llap/limit_pushdown3.q.out index 470cffe..8f4fb0d 100644 --- a/ql/src/test/results/clientpositive/llap/limit_pushdown3.q.out +++ b/ql/src/test/results/clientpositive/llap/limit_pushdown3.q.out @@ -424,12 +424,12 @@ STAGE PLANS: keys: cdouble (type: double) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 5570 Data size: 33272 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5528 Data size: 33024 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: double) sort order: + Map-reduce partition columns: _col0 (type: double) - Statistics: Num rows: 5570 Data size: 33272 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5528 Data size: 33024 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.3 Execution mode: llap LLAP IO: all inputs @@ -440,11 +440,11 @@ STAGE PLANS: keys: KEY._col0 (type: double) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 5570 Data size: 33272 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5528 Data size: 33024 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: double) sort order: + - Statistics: Num rows: 5570 Data size: 33272 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5528 Data size: 33024 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.3 Reducer 3 Execution mode: llap @@ -452,7 +452,7 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: double) outputColumnNames: _col0 - Statistics: Num rows: 5570 Data size: 33272 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5528 Data size: 33024 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 20 Statistics: Num rows: 20 Data size: 128 Basic stats: COMPLETE Column stats: COMPLETE @@ -1009,11 +1009,11 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 309 Data size: 30591 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 307 Data size: 30393 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 309 Data size: 30591 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 307 Data size: 30393 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.3 value expressions: _col1 (type: double) Reducer 3 @@ -1022,7 +1022,7 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 309 Data size: 30591 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 307 Data size: 30393 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 20 Statistics: Num rows: 20 Data size: 1980 Basic stats: COMPLETE Column stats: COMPLETE diff --git a/ql/src/test/results/clientpositive/llap/llap_vector_nohybridgrace.q.out b/ql/src/test/results/clientpositive/llap/llap_vector_nohybridgrace.q.out index 2c13d5d..b361b1e 100644 --- a/ql/src/test/results/clientpositive/llap/llap_vector_nohybridgrace.q.out +++ b/ql/src/test/results/clientpositive/llap/llap_vector_nohybridgrace.q.out @@ -65,7 +65,7 @@ STAGE PLANS: nativeConditionsMet: hive.mapjoin.optimized.hashtable IS true, hive.vectorized.execution.mapjoin.native.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, One MapJoin Condition IS true, No nullsafe IS true, Small table vectorizes IS true, Fast Hash Table and No Hybrid Hash Join IS true input vertices: 1 Map 3 - Statistics: Num rows: 25044 Data size: 200352 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 24737 Data size: 197896 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() Group By Vectorization: @@ -244,7 +244,7 @@ STAGE PLANS: nativeConditionsMet: hive.mapjoin.optimized.hashtable IS true, hive.vectorized.execution.mapjoin.native.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, One MapJoin Condition IS true, No nullsafe IS true, Small table vectorizes IS true, Fast Hash Table and No Hybrid Hash Join IS true input vertices: 1 Map 3 - Statistics: Num rows: 25044 Data size: 200352 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 24737 Data size: 197896 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() Group By Vectorization: diff --git a/ql/src/test/results/clientpositive/llap/llapdecider.q.out b/ql/src/test/results/clientpositive/llap/llapdecider.q.out index f093dd6..3e493ca 100644 --- a/ql/src/test/results/clientpositive/llap/llapdecider.q.out +++ b/ql/src/test/results/clientpositive/llap/llapdecider.q.out @@ -376,21 +376,21 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 809 Data size: 288004 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col3 (type: string) sort order: + - Statistics: Num rows: 809 Data size: 288004 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) Reducer 3 Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: string), VALUE._col1 (type: string), VALUE._col2 (type: string), KEY.reducesinkkey0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 809 Data size: 288004 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 809 Data size: 288004 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -469,11 +469,11 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 809 Data size: 288004 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col3 (type: string) sort order: + - Statistics: Num rows: 809 Data size: 288004 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) Reducer 3 Execution mode: llap @@ -481,10 +481,10 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: string), VALUE._col1 (type: string), VALUE._col2 (type: string), KEY.reducesinkkey0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 809 Data size: 288004 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 809 Data size: 288004 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -561,11 +561,11 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 809 Data size: 288004 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col3 (type: string) sort order: + - Statistics: Num rows: 809 Data size: 288004 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) Reducer 3 Execution mode: llap @@ -573,10 +573,10 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: string), VALUE._col1 (type: string), VALUE._col2 (type: string), KEY.reducesinkkey0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 809 Data size: 288004 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 809 Data size: 288004 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -650,21 +650,21 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 809 Data size: 288004 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col3 (type: string) sort order: + - Statistics: Num rows: 809 Data size: 288004 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) Reducer 3 Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: string), VALUE._col1 (type: string), VALUE._col2 (type: string), KEY.reducesinkkey0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 809 Data size: 288004 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 809 Data size: 288004 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -738,21 +738,21 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 809 Data size: 288004 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col3 (type: string) sort order: + - Statistics: Num rows: 809 Data size: 288004 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) Reducer 3 Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: string), VALUE._col1 (type: string), VALUE._col2 (type: string), KEY.reducesinkkey0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 809 Data size: 288004 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 809 Data size: 288004 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -830,21 +830,21 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 809 Data size: 288004 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col3 (type: string) sort order: + - Statistics: Num rows: 809 Data size: 288004 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) Reducer 3 Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: string), VALUE._col1 (type: string), VALUE._col2 (type: string), KEY.reducesinkkey0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 809 Data size: 288004 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 809 Data size: 288004 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -918,21 +918,21 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 809 Data size: 288004 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col3 (type: string) sort order: + - Statistics: Num rows: 809 Data size: 288004 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) Reducer 3 Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: string), VALUE._col1 (type: string), VALUE._col2 (type: string), KEY.reducesinkkey0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 809 Data size: 288004 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 809 Data size: 288004 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1011,11 +1011,11 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 809 Data size: 288004 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col3 (type: string) sort order: + - Statistics: Num rows: 809 Data size: 288004 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) Reducer 3 Execution mode: llap @@ -1023,10 +1023,10 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: string), VALUE._col1 (type: string), VALUE._col2 (type: string), KEY.reducesinkkey0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 809 Data size: 288004 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 809 Data size: 288004 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/mapjoin_mapjoin.q.out b/ql/src/test/results/clientpositive/llap/mapjoin_mapjoin.q.out index c4361de..5c68ff2 100644 --- a/ql/src/test/results/clientpositive/llap/mapjoin_mapjoin.q.out +++ b/ql/src/test/results/clientpositive/llap/mapjoin_mapjoin.q.out @@ -572,9 +572,9 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col1 (type: string) + 0 _col0 (type: string) 1 _col0 (type: string) - outputColumnNames: _col0, _col2 + outputColumnNames: _col1, _col2 input vertices: 1 Map 3 Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE @@ -582,7 +582,7 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) + 0 _col1 (type: string) 1 _col0 (type: string) outputColumnNames: _col2 input vertices: @@ -605,13 +605,13 @@ STAGE PLANS: Map 3 Map Operator Tree: TableScan - alias: src + alias: src1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: value is not null (type: boolean) + predicate: key is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: value (type: string) + expressions: key (type: string) outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator @@ -624,13 +624,13 @@ STAGE PLANS: Map 4 Map Operator Tree: TableScan - alias: src1 + alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: key is not null (type: boolean) + predicate: value is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) + expressions: value (type: string) outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator diff --git a/ql/src/test/results/clientpositive/llap/mergejoin.q.out b/ql/src/test/results/clientpositive/llap/mergejoin.q.out index ff0b1f1..05338c3 100644 --- a/ql/src/test/results/clientpositive/llap/mergejoin.q.out +++ b/ql/src/test/results/clientpositive/llap/mergejoin.q.out @@ -170,10 +170,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 40 Data size: 14120 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 13767 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 40 Data size: 14120 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 13767 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -520,7 +520,7 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 391 Data size: 3128 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 399 Data size: 3192 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash @@ -1687,7 +1687,7 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 391 Data size: 3128 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 399 Data size: 3192 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash @@ -2407,7 +2407,7 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 63 Data size: 504 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 64 Data size: 512 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash @@ -2693,7 +2693,7 @@ STAGE PLANS: keys: 0 _col1 (type: string) 1 _col1 (type: string) - Statistics: Num rows: 391 Data size: 3128 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 394 Data size: 3152 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash @@ -3031,7 +3031,7 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 1009 Data size: 8072 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1029 Data size: 8232 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash @@ -3226,7 +3226,7 @@ STAGE PLANS: keys: 0 _col1 (type: string) 1 _col1 (type: string) - Statistics: Num rows: 391 Data size: 3128 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 394 Data size: 3152 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash @@ -3552,7 +3552,7 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 63 Data size: 504 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 64 Data size: 512 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash @@ -3968,7 +3968,7 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 1009 Data size: 8072 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1029 Data size: 8232 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash @@ -4210,7 +4210,7 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 391 Data size: 3128 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 399 Data size: 3192 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash diff --git a/ql/src/test/results/clientpositive/llap/mrr.q.out b/ql/src/test/results/clientpositive/llap/mrr.q.out index bfa26e4..0737c6e 100644 --- a/ql/src/test/results/clientpositive/llap/mrr.q.out +++ b/ql/src/test/results/clientpositive/llap/mrr.q.out @@ -457,17 +457,17 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col1, _col2 - Statistics: Num rows: 809 Data size: 144002 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col1 (type: string), _col2 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 404 Data size: 71912 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 395 Data size: 70310 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 404 Data size: 71912 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 395 Data size: 70310 Basic stats: COMPLETE Column stats: COMPLETE Reducer 3 Execution mode: llap Reduce Operator Tree: @@ -475,27 +475,27 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 404 Data size: 71912 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 395 Data size: 70310 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(_col1) keys: _col0 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: bigint), _col0 (type: string) sort order: ++ - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE Reducer 4 Execution mode: llap Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -882,17 +882,17 @@ STAGE PLANS: outputColumnNames: _col1, _col2 input vertices: 0 Map 1 - Statistics: Num rows: 809 Data size: 144002 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col1 (type: string), _col2 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 404 Data size: 71912 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 395 Data size: 70310 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 404 Data size: 71912 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 395 Data size: 70310 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Reducer 3 @@ -902,27 +902,27 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 404 Data size: 71912 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 395 Data size: 70310 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(_col1) keys: _col0 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: bigint), _col0 (type: string) sort order: ++ - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE Reducer 4 Execution mode: llap Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1360,15 +1360,15 @@ STAGE PLANS: 1 _col0 (type: string) 2 _col0 (type: string) outputColumnNames: _col0, _col1, _col3, _col4, _col5 - Statistics: Num rows: 54 Data size: 10692 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 51 Data size: 10098 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col3 (type: bigint), _col1 (type: bigint), _col4 (type: string), _col5 (type: bigint) outputColumnNames: _col0, _col1, _col3, _col4, _col5 - Statistics: Num rows: 54 Data size: 15390 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 51 Data size: 14535 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 54 Data size: 15390 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 51 Data size: 14535 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint), _col3 (type: bigint), _col4 (type: string), _col5 (type: bigint) Reducer 4 Execution mode: llap @@ -1376,10 +1376,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: bigint), KEY.reducesinkkey0 (type: string), VALUE._col1 (type: bigint), VALUE._col2 (type: string), VALUE._col3 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 54 Data size: 15390 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 51 Data size: 14535 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 54 Data size: 15390 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 51 Data size: 14535 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/multiMapJoin2.q.out b/ql/src/test/results/clientpositive/llap/multiMapJoin2.q.out index 05ec048..1061c1d 100644 --- a/ql/src/test/results/clientpositive/llap/multiMapJoin2.q.out +++ b/ql/src/test/results/clientpositive/llap/multiMapJoin2.q.out @@ -47,11 +47,11 @@ STAGE PLANS: outputColumnNames: _col0 input vertices: 1 Map 4 - Statistics: Num rows: 40 Data size: 3480 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 3393 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 80 Data size: 6960 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 78 Data size: 6786 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Map 4 @@ -94,11 +94,11 @@ STAGE PLANS: outputColumnNames: _col0 input vertices: 1 Map 6 - Statistics: Num rows: 40 Data size: 3480 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 3393 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 80 Data size: 6960 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 78 Data size: 6786 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Map 6 @@ -126,10 +126,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 80 Data size: 6960 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 78 Data size: 6786 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 80 Data size: 6960 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 78 Data size: 6786 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -350,21 +350,21 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 40 Data size: 3480 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 3393 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 80 Data size: 6960 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 78 Data size: 6786 Basic stats: COMPLETE Column stats: COMPLETE Reducer 4 Execution mode: llap Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 80 Data size: 6960 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 78 Data size: 6786 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 80 Data size: 6960 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 78 Data size: 6786 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -379,11 +379,11 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 40 Data size: 3480 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 3393 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 80 Data size: 6960 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 78 Data size: 6786 Basic stats: COMPLETE Column stats: COMPLETE Union 3 Vertex: Union 3 @@ -556,11 +556,11 @@ STAGE PLANS: outputColumnNames: _col0 input vertices: 1 Map 6 - Statistics: Num rows: 40 Data size: 3480 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 3393 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 52 Data size: 4512 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 51 Data size: 4425 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Map 6 @@ -593,17 +593,17 @@ STAGE PLANS: Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 52 Data size: 4512 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 51 Data size: 4425 Basic stats: COMPLETE Column stats: COMPLETE Reducer 4 Execution mode: llap Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 52 Data size: 4524 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 51 Data size: 4437 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 52 Data size: 4524 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 51 Data size: 4437 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -750,7 +750,7 @@ STAGE PLANS: outputColumnNames: _col0 input vertices: 1 Map 5 - Statistics: Num rows: 40 Data size: 3480 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 3393 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string) mode: hash @@ -808,7 +808,7 @@ STAGE PLANS: outputColumnNames: _col0 input vertices: 1 Map 5 - Statistics: Num rows: 40 Data size: 3480 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 3393 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string) mode: hash @@ -990,7 +990,7 @@ STAGE PLANS: outputColumnNames: _col0 input vertices: 1 Map 5 - Statistics: Num rows: 40 Data size: 3480 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 3393 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string) mode: hash @@ -1048,7 +1048,7 @@ STAGE PLANS: outputColumnNames: _col0 input vertices: 1 Map 5 - Statistics: Num rows: 40 Data size: 3480 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 3393 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string) mode: hash @@ -1230,7 +1230,7 @@ STAGE PLANS: outputColumnNames: _col0 input vertices: 1 Map 5 - Statistics: Num rows: 40 Data size: 3480 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 3393 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string) mode: hash @@ -1454,7 +1454,7 @@ STAGE PLANS: outputColumnNames: _col0 input vertices: 1 Map 5 - Statistics: Num rows: 40 Data size: 3480 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 3393 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string) mode: hash @@ -1857,17 +1857,17 @@ STAGE PLANS: outputColumnNames: _col0 input vertices: 1 Map 5 - Statistics: Num rows: 809 Data size: 70383 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 68817 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 309 Data size: 26883 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 27492 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 309 Data size: 26883 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 27492 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Map 5 @@ -1896,17 +1896,17 @@ STAGE PLANS: outputColumnNames: _col0 input vertices: 1 Map 7 - Statistics: Num rows: 809 Data size: 70383 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 68817 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 309 Data size: 26883 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 27492 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 309 Data size: 26883 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 27492 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Map 6 diff --git a/ql/src/test/results/clientpositive/llap/offset_limit_ppd_optimizer.q.out b/ql/src/test/results/clientpositive/llap/offset_limit_ppd_optimizer.q.out index b6bc569..6d25176 100644 --- a/ql/src/test/results/clientpositive/llap/offset_limit_ppd_optimizer.q.out +++ b/ql/src/test/results/clientpositive/llap/offset_limit_ppd_optimizer.q.out @@ -399,12 +399,12 @@ STAGE PLANS: keys: cdouble (type: double) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 5570 Data size: 33272 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5528 Data size: 33024 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: double) sort order: + Map-reduce partition columns: _col0 (type: double) - Statistics: Num rows: 5570 Data size: 33272 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5528 Data size: 33024 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.3 Execution mode: llap LLAP IO: all inputs @@ -415,7 +415,7 @@ STAGE PLANS: keys: KEY._col0 (type: double) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 5570 Data size: 33272 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5528 Data size: 33024 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 20 Offset of rows: 10 @@ -933,7 +933,7 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 309 Data size: 30591 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 307 Data size: 30393 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 20 Offset of rows: 10 @@ -1335,7 +1335,7 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 20 Offset of rows: 10 @@ -1379,7 +1379,7 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 20 Offset of rows: 20 diff --git a/ql/src/test/results/clientpositive/llap/partialdhj.q.out b/ql/src/test/results/clientpositive/llap/partialdhj.q.out index 4e62c4f..14298ae 100644 --- a/ql/src/test/results/clientpositive/llap/partialdhj.q.out +++ b/ql/src/test/results/clientpositive/llap/partialdhj.q.out @@ -143,11 +143,11 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2 input vertices: 0 Reducer 3 - Statistics: Num rows: 25 Data size: 6675 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 26 Data size: 6942 Basic stats: COMPLETE Column stats: COMPLETE HybridGraceHashJoin: true File Output Operator compressed: false - Statistics: Num rows: 25 Data size: 6675 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 26 Data size: 6942 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -336,11 +336,11 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2 input vertices: 1 Reducer 5 - Statistics: Num rows: 25 Data size: 6675 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 26 Data size: 6942 Basic stats: COMPLETE Column stats: COMPLETE HybridGraceHashJoin: true File Output Operator compressed: false - Statistics: Num rows: 25 Data size: 6675 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 26 Data size: 6942 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/reduce_deduplicate_extended.q.out b/ql/src/test/results/clientpositive/llap/reduce_deduplicate_extended.q.out index b4ac5a6..ab8da2b 100644 --- a/ql/src/test/results/clientpositive/llap/reduce_deduplicate_extended.q.out +++ b/ql/src/test/results/clientpositive/llap/reduce_deduplicate_extended.q.out @@ -42,10 +42,10 @@ STAGE PLANS: keys: _col0 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -313,18 +313,18 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 40 Data size: 7120 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6942 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col0) keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 20 Data size: 3720 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 19 Data size: 3534 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 20 Data size: 3720 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 19 Data size: 3534 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: double) Reducer 3 Execution mode: llap @@ -334,14 +334,14 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 20 Data size: 3720 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 19 Data size: 3534 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col2 (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 20 Data size: 1900 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 19 Data size: 1805 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 1900 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 19 Data size: 1805 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -419,21 +419,21 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 40 Data size: 7120 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6942 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ - Statistics: Num rows: 40 Data size: 7120 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6942 Basic stats: COMPLETE Column stats: COMPLETE Reducer 3 Execution mode: llap Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 40 Data size: 7120 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6942 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 40 Data size: 7120 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6942 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -2596,10 +2596,10 @@ STAGE PLANS: keys: _col0 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -2779,10 +2779,10 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -2860,12 +2860,12 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 40 Data size: 7120 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6942 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 40 Data size: 7120 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6942 Basic stats: COMPLETE Column stats: COMPLETE Reducer 3 Execution mode: llap Reduce Operator Tree: @@ -2874,14 +2874,14 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: complete outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 40 Data size: 7440 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 7254 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col2 (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 40 Data size: 3800 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 3705 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 40 Data size: 3800 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 3705 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -2959,21 +2959,21 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 40 Data size: 7120 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6942 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ - Statistics: Num rows: 40 Data size: 7120 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6942 Basic stats: COMPLETE Column stats: COMPLETE Reducer 3 Execution mode: llap Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 40 Data size: 7120 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6942 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 40 Data size: 7120 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6942 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -3033,10 +3033,10 @@ STAGE PLANS: keys: _col0 (type: string) mode: complete outputColumnNames: _col0 - Statistics: Num rows: 309 Data size: 26883 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 27492 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 309 Data size: 26883 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 27492 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -3093,10 +3093,10 @@ STAGE PLANS: keys: _col0 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/semijoin_hint.q.out b/ql/src/test/results/clientpositive/llap/semijoin_hint.q.out index cdfa733..5493633 100644 --- a/ql/src/test/results/clientpositive/llap/semijoin_hint.q.out +++ b/ql/src/test/results/clientpositive/llap/semijoin_hint.q.out @@ -222,7 +222,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 1000 Data size: 87000 Basic stats: PARTIAL Column stats: PARTIAL Group By Operator - aggregations: min(_col0), max(_col0), bloom_filter(_col0, expectedEntries=309) + aggregations: min(_col0), max(_col0), bloom_filter(_col0, expectedEntries=20) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1 Data size: 639 Basic stats: PARTIAL Column stats: PARTIAL @@ -272,7 +272,7 @@ STAGE PLANS: Execution mode: llap Reduce Operator Tree: Group By Operator - aggregations: min(VALUE._col0), max(VALUE._col1), bloom_filter(VALUE._col2, expectedEntries=309) + aggregations: min(VALUE._col0), max(VALUE._col1), bloom_filter(VALUE._col2, expectedEntries=20) mode: final outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1 Data size: 639 Basic stats: PARTIAL Column stats: PARTIAL @@ -478,16 +478,16 @@ STAGE PLANS: 0 cstring (type: string) 1 value (type: string) outputColumnNames: str - Statistics: Num rows: 4056 Data size: 352872 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4110 Data size: 357570 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: str (type: string) sort order: + Map-reduce partition columns: str (type: string) - Statistics: Num rows: 4056 Data size: 352872 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4110 Data size: 357570 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: str (type: string) outputColumnNames: _col0 - Statistics: Num rows: 4056 Data size: 352872 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4110 Data size: 357570 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: min(_col0), max(_col0), bloom_filter(_col0, expectedEntries=5000) mode: hash @@ -506,9 +506,9 @@ STAGE PLANS: keys: 0 str (type: string) 1 key1 (type: string) - Statistics: Num rows: 4461 Data size: 388159 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 4521 Data size: 393327 Basic stats: PARTIAL Column stats: NONE Select Operator - Statistics: Num rows: 4461 Data size: 388159 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 4521 Data size: 393327 Basic stats: PARTIAL Column stats: NONE Group By Operator aggregations: count() mode: hash @@ -1476,16 +1476,16 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col1 (type: string) outputColumnNames: _col1 - Statistics: Num rows: 4056 Data size: 352872 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4110 Data size: 357570 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 4056 Data size: 352872 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4110 Data size: 357570 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 4056 Data size: 352872 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4110 Data size: 357570 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: min(_col0), max(_col0), bloom_filter(_col0, expectedEntries=5000) mode: hash @@ -1504,7 +1504,7 @@ STAGE PLANS: keys: 0 _col1 (type: string) 1 _col0 (type: string) - Statistics: Num rows: 4461 Data size: 388159 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 4521 Data size: 393327 Basic stats: PARTIAL Column stats: NONE Group By Operator aggregations: count() mode: hash @@ -2190,7 +2190,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 1000 Data size: 87000 Basic stats: PARTIAL Column stats: PARTIAL Group By Operator - aggregations: min(_col0), max(_col0), bloom_filter(_col0, expectedEntries=309) + aggregations: min(_col0), max(_col0), bloom_filter(_col0, expectedEntries=20) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1 Data size: 639 Basic stats: PARTIAL Column stats: PARTIAL @@ -2238,7 +2238,7 @@ STAGE PLANS: Execution mode: llap Reduce Operator Tree: Group By Operator - aggregations: min(VALUE._col0), max(VALUE._col1), bloom_filter(VALUE._col2, expectedEntries=309) + aggregations: min(VALUE._col0), max(VALUE._col1), bloom_filter(VALUE._col2, expectedEntries=20) mode: final outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1 Data size: 639 Basic stats: PARTIAL Column stats: PARTIAL diff --git a/ql/src/test/results/clientpositive/llap/skewjoin.q.out b/ql/src/test/results/clientpositive/llap/skewjoin.q.out index 67c6e21..21d2db8 100644 --- a/ql/src/test/results/clientpositive/llap/skewjoin.q.out +++ b/ql/src/test/results/clientpositive/llap/skewjoin.q.out @@ -142,14 +142,14 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col2 - Statistics: Num rows: 809 Data size: 144002 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), _col2 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 809 Data size: 76855 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 75145 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 809 Data size: 76855 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 75145 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -688,7 +688,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col2, _col3 - Statistics: Num rows: 809 Data size: 144002 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(hash(_col2)), sum(hash(_col3)) mode: hash @@ -815,7 +815,7 @@ STAGE PLANS: 0 _col0 (type: string), UDFToDouble(substring(_col1, 5)) (type: double) 1 _col0 (type: string), (substring(_col1, 5) + 1) (type: double) outputColumnNames: _col2, _col3 - Statistics: Num rows: 809 Data size: 144002 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(hash(_col2)), sum(hash(_col3)) mode: hash @@ -971,7 +971,7 @@ STAGE PLANS: 1 _col0 (type: string) 2 _col0 (type: string) outputColumnNames: _col0, _col3 - Statistics: Num rows: 143 Data size: 25454 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 135 Data size: 24030 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(hash(_col0)), sum(hash(_col3)) mode: hash diff --git a/ql/src/test/results/clientpositive/llap/subquery_exists.q.out b/ql/src/test/results/clientpositive/llap/subquery_exists.q.out index 02dc7cb..2b5e673 100644 --- a/ql/src/test/results/clientpositive/llap/subquery_exists.q.out +++ b/ql/src/test/results/clientpositive/llap/subquery_exists.q.out @@ -81,10 +81,10 @@ STAGE PLANS: 0 _col0 (type: string), _col1 (type: string) 1 _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 133 Data size: 23674 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 131 Data size: 23318 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 133 Data size: 23674 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 131 Data size: 23318 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -289,10 +289,10 @@ STAGE PLANS: 0 _col1 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 404 Data size: 71912 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 407 Data size: 72446 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 404 Data size: 71912 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 407 Data size: 72446 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/subquery_in.q.out b/ql/src/test/results/clientpositive/llap/subquery_in.q.out index ba26075..4807816 100644 --- a/ql/src/test/results/clientpositive/llap/subquery_in.q.out +++ b/ql/src/test/results/clientpositive/llap/subquery_in.q.out @@ -74,10 +74,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 133 Data size: 23674 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 131 Data size: 23318 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 133 Data size: 23674 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 131 Data size: 23318 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -195,10 +195,10 @@ STAGE PLANS: 0 _col0 (type: string), _col1 (type: string) 1 _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 133 Data size: 23674 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 131 Data size: 23318 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 133 Data size: 23674 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 131 Data size: 23318 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -684,10 +684,10 @@ STAGE PLANS: 0 _col0 (type: string), _col1 (type: string) 1 _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 133 Data size: 23674 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 131 Data size: 23318 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 133 Data size: 23674 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 131 Data size: 23318 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -812,14 +812,14 @@ STAGE PLANS: 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col3 residual filter predicates: {(_col1 <> _col3)} - Statistics: Num rows: 66 Data size: 17490 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 64 Data size: 16960 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 66 Data size: 11748 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 64 Data size: 11392 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 66 Data size: 11748 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 64 Data size: 11392 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -950,15 +950,18 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 67 Data size: 11926 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 67 Data size: 11926 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Reducer 3 + Statistics: Num rows: 41666 Data size: 7416548 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: _col0 (type: string), _col1 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 10918 Data size: 1943404 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Statistics: Num rows: 10918 Data size: 1943404 Basic stats: COMPLETE Column stats: COMPLETE + Reducer 5 Execution mode: llap Reduce Operator Tree: Group By Operator @@ -2723,18 +2726,18 @@ STAGE PLANS: 0 _col1 (type: string) 1 _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 404 Data size: 35148 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 407 Data size: 35409 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 202 Data size: 19190 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 203 Data size: 19285 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 202 Data size: 19190 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 203 Data size: 19285 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Reducer 3 Execution mode: llap @@ -2744,15 +2747,15 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 202 Data size: 19190 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 203 Data size: 19285 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: _col1 is not null (type: boolean) - Statistics: Num rows: 202 Data size: 19190 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 203 Data size: 19285 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: bigint) sort order: + Map-reduce partition columns: _col1 (type: bigint) - Statistics: Num rows: 202 Data size: 19190 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 203 Data size: 19285 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string) Reducer 4 Execution mode: llap @@ -2944,18 +2947,18 @@ STAGE PLANS: 0 _col0 (type: string), _col1 (type: string) 1 _col0 (type: string), _col1 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 404 Data size: 35148 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 395 Data size: 34365 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 202 Data size: 19190 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 197 Data size: 18715 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 202 Data size: 19190 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 197 Data size: 18715 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Reducer 3 Execution mode: llap @@ -2965,15 +2968,15 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 202 Data size: 19190 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 197 Data size: 18715 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: _col1 is not null (type: boolean) - Statistics: Num rows: 202 Data size: 19190 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 197 Data size: 18715 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: bigint) sort order: + Map-reduce partition columns: _col1 (type: bigint) - Statistics: Num rows: 202 Data size: 19190 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 197 Data size: 18715 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string) Reducer 4 Execution mode: llap @@ -3475,10 +3478,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 40 Data size: 7120 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6942 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 40 Data size: 7120 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6942 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/subquery_in_having.q.out b/ql/src/test/results/clientpositive/llap/subquery_in_having.q.out index 50ac656..e535e4c 100644 --- a/ql/src/test/results/clientpositive/llap/subquery_in_having.q.out +++ b/ql/src/test/results/clientpositive/llap/subquery_in_having.q.out @@ -620,18 +620,18 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 133 Data size: 23674 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 131 Data size: 23318 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 66 Data size: 12276 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 65 Data size: 12090 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 66 Data size: 12276 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 65 Data size: 12090 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: bigint) Reducer 3 Execution mode: llap @@ -641,15 +641,15 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 66 Data size: 12276 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 65 Data size: 12090 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: _col2 is not null (type: boolean) - Statistics: Num rows: 66 Data size: 12276 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 65 Data size: 12090 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col2 (type: bigint) sort order: + Map-reduce partition columns: _col2 (type: bigint) - Statistics: Num rows: 66 Data size: 12276 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 65 Data size: 12090 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string) Reducer 4 Execution mode: llap @@ -785,18 +785,18 @@ STAGE PLANS: outputColumnNames: _col0, _col1 input vertices: 1 Map 3 - Statistics: Num rows: 133 Data size: 23674 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 131 Data size: 23318 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 66 Data size: 12276 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 65 Data size: 12090 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 66 Data size: 12276 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 65 Data size: 12090 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: bigint) Execution mode: llap LLAP IO: no inputs @@ -847,10 +847,10 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 66 Data size: 12276 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 65 Data size: 12090 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: _col2 is not null (type: boolean) - Statistics: Num rows: 66 Data size: 12276 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 65 Data size: 12090 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Left Semi Join 0 to 1 @@ -954,18 +954,18 @@ STAGE PLANS: outputColumnNames: _col0, _col1 input vertices: 1 Map 3 - Statistics: Num rows: 404 Data size: 71912 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 395 Data size: 70310 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 202 Data size: 37572 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 197 Data size: 36642 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 202 Data size: 37572 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 197 Data size: 36642 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: bigint) Execution mode: llap LLAP IO: no inputs @@ -1023,10 +1023,10 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 202 Data size: 37572 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 197 Data size: 36642 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: _col2 is not null (type: boolean) - Statistics: Num rows: 202 Data size: 37572 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 197 Data size: 36642 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Left Semi Join 0 to 1 diff --git a/ql/src/test/results/clientpositive/llap/subquery_multi.q.out b/ql/src/test/results/clientpositive/llap/subquery_multi.q.out index 975fd13..b316893 100644 --- a/ql/src/test/results/clientpositive/llap/subquery_multi.q.out +++ b/ql/src/test/results/clientpositive/llap/subquery_multi.q.out @@ -3221,18 +3221,18 @@ STAGE PLANS: 0 _col0 (type: string), _col1 (type: string) 1 _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 404 Data size: 71912 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 395 Data size: 70310 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 202 Data size: 37572 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 197 Data size: 36642 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 202 Data size: 37572 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 197 Data size: 36642 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: bigint) Reducer 3 Execution mode: llap @@ -3242,15 +3242,15 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 202 Data size: 37572 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 197 Data size: 36642 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: _col2 is not null (type: boolean) - Statistics: Num rows: 202 Data size: 37572 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 197 Data size: 36642 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col2 (type: bigint) sort order: + Map-reduce partition columns: _col2 (type: bigint) - Statistics: Num rows: 202 Data size: 37572 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 197 Data size: 36642 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string) Reducer 4 Execution mode: llap @@ -3280,7 +3280,7 @@ STAGE PLANS: 0 _col1 (type: string) 1 _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 134 Data size: 11658 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 135 Data size: 11745 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string) @@ -4115,10 +4115,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col1, _col2, _col4 - Statistics: Num rows: 500 Data size: 50040 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 50028 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 500 Data size: 50040 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 50028 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col2 (type: bigint), _col4 (type: boolean) Reducer 4 Execution mode: llap @@ -4130,12 +4130,12 @@ STAGE PLANS: 0 1 outputColumnNames: _col1, _col2, _col4, _col5 - Statistics: Num rows: 500 Data size: 52040 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 52028 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((_col4 is not null and (_col2 <> 0)) or _col1 is not null or _col5 is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 52040 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 52028 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 500 Data size: 52040 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 52028 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash diff --git a/ql/src/test/results/clientpositive/llap/subquery_notin.q.out b/ql/src/test/results/clientpositive/llap/subquery_notin.q.out index 9cc1262..46ae56d 100644 --- a/ql/src/test/results/clientpositive/llap/subquery_notin.q.out +++ b/ql/src/test/results/clientpositive/llap/subquery_notin.q.out @@ -104,10 +104,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col5 - Statistics: Num rows: 500 Data size: 97540 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 97528 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((_col2 = 0) or (_col5 is null and _col0 is not null and (_col3 >= _col2))) (type: boolean) - Statistics: Num rows: 500 Data size: 97540 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 97528 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 @@ -1560,10 +1560,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col4 - Statistics: Num rows: 166 Data size: 17366 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 166 Data size: 17358 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((_col1 = 0) or (_col4 is null and _col0 is not null and (_col2 >= _col1))) (type: boolean) - Statistics: Num rows: 166 Data size: 17366 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 166 Data size: 17358 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string) outputColumnNames: _col0 @@ -3699,14 +3699,14 @@ STAGE PLANS: 0 _col1 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col5 - Statistics: Num rows: 500 Data size: 98620 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 98584 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((_col2 = 0) or (_col5 is null and _col1 is not null and (_col3 >= _col2))) (type: boolean) - Statistics: Num rows: 500 Data size: 98620 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 98584 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 98620 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 98584 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string) @@ -3971,12 +3971,12 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col3, _col4 - Statistics: Num rows: 500 Data size: 95480 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 95336 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 500 Data size: 95480 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 95336 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: bigint), _col4 (type: bigint) Reducer 3 Execution mode: llap @@ -3988,14 +3988,14 @@ STAGE PLANS: 0 _col0 (type: string), _col1 (type: string) 1 _col1 (type: string), _col0 (type: string) outputColumnNames: _col0, _col1, _col3, _col4, _col7 - Statistics: Num rows: 500 Data size: 97100 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 96920 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (not CASE WHEN ((_col3 = 0)) THEN (false) WHEN (_col3 is null) THEN (false) WHEN (_col7 is not null) THEN (true) WHEN (_col1 is null) THEN (null) WHEN ((_col4 < _col3)) THEN (true) ELSE (false) END) (type: boolean) - Statistics: Num rows: 250 Data size: 48560 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 250 Data size: 48460 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 48560 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 250 Data size: 48460 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string) @@ -4774,10 +4774,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col5 - Statistics: Num rows: 500 Data size: 97164 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 97160 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((_col2 = 0) or (_col5 is null and _col0 is not null and (_col3 >= _col2))) (type: boolean) - Statistics: Num rows: 500 Data size: 97164 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 97160 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 @@ -7232,13 +7232,13 @@ STAGE PLANS: 0 _col1 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col3, _col4 - Statistics: Num rows: 500 Data size: 91672 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 91688 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 91672 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: string), _col3 (type: bigint), _col4 (type: bigint) + key expressions: _col0 (type: string), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Statistics: Num rows: 500 Data size: 91688 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col3 (type: bigint), _col4 (type: bigint) Reducer 3 Execution mode: llap Reduce Operator Tree: @@ -7246,21 +7246,20 @@ STAGE PLANS: condition map: Left Outer Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col3, _col4, _col6, _col7 - residual filter predicates: {(_col1 > _col6)} - Statistics: Num rows: 500 Data size: 104497 Basic stats: COMPLETE Column stats: COMPLETE + 0 _col0 (type: string), _col1 (type: string) + 1 _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1, _col3, _col4, _col7 + Statistics: Num rows: 5704 Data size: 1124080 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (not CASE WHEN ((_col3 = 0)) THEN (false) WHEN (_col3 is null) THEN (false) WHEN (_col7 is not null) THEN (true) WHEN (_col0 is null) THEN (null) WHEN ((_col4 < _col3)) THEN (true) ELSE (false) END) (type: boolean) - Statistics: Num rows: 250 Data size: 52304 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2852 Data size: 562040 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2852 Data size: 507656 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2852 Data size: 507656 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/subquery_scalar.q.out b/ql/src/test/results/clientpositive/llap/subquery_scalar.q.out index 64337ed..a409827 100644 --- a/ql/src/test/results/clientpositive/llap/subquery_scalar.q.out +++ b/ql/src/test/results/clientpositive/llap/subquery_scalar.q.out @@ -5503,18 +5503,18 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 133 Data size: 23674 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 131 Data size: 23318 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 66 Data size: 12276 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 65 Data size: 12090 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 66 Data size: 12276 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 65 Data size: 12090 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: bigint) Reducer 3 Execution mode: llap @@ -5524,10 +5524,10 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 66 Data size: 12276 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 65 Data size: 12090 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 66 Data size: 12276 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 65 Data size: 12090 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) Reducer 4 Execution mode: llap @@ -5540,14 +5540,14 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1, _col2, _col3 residual filter predicates: {(_col2 > _col3)} - Statistics: Num rows: 22 Data size: 4268 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 21 Data size: 4074 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 22 Data size: 4092 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 21 Data size: 3906 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 22 Data size: 4092 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 21 Data size: 3906 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/subquery_select.q.out b/ql/src/test/results/clientpositive/llap/subquery_select.q.out index b090cd0..fafc3b8 100644 --- a/ql/src/test/results/clientpositive/llap/subquery_select.q.out +++ b/ql/src/test/results/clientpositive/llap/subquery_select.q.out @@ -1869,10 +1869,10 @@ STAGE PLANS: 0 _col0 (type: string), _col1 (type: string) 1 _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 134 Data size: 23852 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 131 Data size: 23318 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 134 Data size: 23852 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 131 Data size: 23318 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -2035,10 +2035,10 @@ STAGE PLANS: 0 _col0 (type: string), _col1 (type: string) 1 _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 108 Data size: 19224 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 106 Data size: 18868 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 108 Data size: 19224 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 106 Data size: 18868 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -2053,11 +2053,11 @@ STAGE PLANS: 0 _col1 (type: string) 1 _col1 (type: string) outputColumnNames: _col1, _col2 - Statistics: Num rows: 134 Data size: 36850 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 135 Data size: 37125 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 134 Data size: 36850 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 135 Data size: 37125 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string), _col1 (type: string) mode: hash diff --git a/ql/src/test/results/clientpositive/llap/subquery_views.q.out b/ql/src/test/results/clientpositive/llap/subquery_views.q.out index af69569..637f9ce 100644 --- a/ql/src/test/results/clientpositive/llap/subquery_views.q.out +++ b/ql/src/test/results/clientpositive/llap/subquery_views.q.out @@ -260,12 +260,12 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col2, _col3, _col4 - Statistics: Num rows: 67 Data size: 12194 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 65 Data size: 11830 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col4 (type: string), _col2 (type: string) sort order: ++ Map-reduce partition columns: _col4 (type: string), _col2 (type: string) - Statistics: Num rows: 67 Data size: 12194 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 65 Data size: 11830 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: boolean) Reducer 12 Execution mode: llap @@ -305,19 +305,19 @@ STAGE PLANS: 1 _col0 (type: string), _col1 (type: string) 2 _col4 (type: string), _col2 (type: string) outputColumnNames: _col0, _col1, _col4, _col5, _col9 - Statistics: Num rows: 87 Data size: 17226 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 81 Data size: 16038 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: CASE WHEN ((_col4 = 0)) THEN (true) WHEN (_col4 is null) THEN (true) WHEN (_col9 is not null) THEN (false) WHEN (_col0 is null) THEN (null) WHEN ((_col5 < _col4)) THEN (false) ELSE (true) END (type: boolean) - Statistics: Num rows: 43 Data size: 8514 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 40 Data size: 7920 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 43 Data size: 7654 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 40 Data size: 7120 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 43 Data size: 7654 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 40 Data size: 7120 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reducer 3 Execution mode: llap @@ -329,10 +329,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 43 Data size: 7654 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 40 Data size: 7120 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 43 Data size: 7654 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 40 Data size: 7120 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -380,12 +380,12 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col2, _col3, _col4 - Statistics: Num rows: 67 Data size: 12194 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 65 Data size: 11830 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col4 (type: string), _col2 (type: string) sort order: ++ Map-reduce partition columns: _col4 (type: string), _col2 (type: string) - Statistics: Num rows: 67 Data size: 12194 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 65 Data size: 11830 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: boolean) Reducer 7 Execution mode: llap @@ -399,24 +399,24 @@ STAGE PLANS: 1 _col0 (type: string), _col1 (type: string) 2 _col4 (type: string), _col2 (type: string) outputColumnNames: _col0, _col4, _col5, _col9 - Statistics: Num rows: 87 Data size: 9309 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 81 Data size: 8667 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: CASE WHEN ((_col4 = 0)) THEN (true) WHEN (_col4 is null) THEN (true) WHEN (_col9 is not null) THEN (false) WHEN (_col0 is null) THEN (null) WHEN ((_col5 < _col4)) THEN (false) ELSE (true) END (type: boolean) - Statistics: Num rows: 43 Data size: 4601 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 40 Data size: 4280 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 43 Data size: 3741 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 40 Data size: 3480 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 8 Data size: 696 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 609 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 8 Data size: 696 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 609 Basic stats: COMPLETE Column stats: COMPLETE Reducer 8 Execution mode: llap Reduce Operator Tree: diff --git a/ql/src/test/results/clientpositive/llap/tez_dynpart_hashjoin_1.q.out b/ql/src/test/results/clientpositive/llap/tez_dynpart_hashjoin_1.q.out index b63b25f..05ea133 100644 --- a/ql/src/test/results/clientpositive/llap/tez_dynpart_hashjoin_1.q.out +++ b/ql/src/test/results/clientpositive/llap/tez_dynpart_hashjoin_1.q.out @@ -77,11 +77,11 @@ STAGE PLANS: 0 _col2 (type: int) 1 _col2 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23 - Statistics: Num rows: 2076 Data size: 1148660 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2048 Data size: 1131300 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col2 (type: int) sort order: + - Statistics: Num rows: 2076 Data size: 1148660 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2048 Data size: 1131300 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: tinyint), _col1 (type: smallint), _col3 (type: bigint), _col4 (type: float), _col5 (type: double), _col6 (type: string), _col7 (type: string), _col8 (type: timestamp), _col9 (type: timestamp), _col10 (type: boolean), _col11 (type: boolean), _col12 (type: tinyint), _col13 (type: smallint), _col14 (type: int), _col15 (type: bigint), _col16 (type: float), _col17 (type: double), _col18 (type: string), _col19 (type: string), _col20 (type: timestamp), _col21 (type: timestamp), _col22 (type: boolean), _col23 (type: boolean) Reducer 3 Execution mode: llap @@ -89,10 +89,10 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: tinyint), VALUE._col1 (type: smallint), KEY.reducesinkkey0 (type: int), VALUE._col2 (type: bigint), VALUE._col3 (type: float), VALUE._col4 (type: double), VALUE._col5 (type: string), VALUE._col6 (type: string), VALUE._col7 (type: timestamp), VALUE._col8 (type: timestamp), VALUE._col9 (type: boolean), VALUE._col10 (type: boolean), VALUE._col11 (type: tinyint), VALUE._col12 (type: smallint), VALUE._col13 (type: int), VALUE._col14 (type: bigint), VALUE._col15 (type: float), VALUE._col16 (type: double), VALUE._col17 (type: string), VALUE._col18 (type: string), VALUE._col19 (type: timestamp), VALUE._col20 (type: timestamp), VALUE._col21 (type: boolean), VALUE._col22 (type: boolean) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23 - Statistics: Num rows: 2076 Data size: 1148660 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2048 Data size: 1131300 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 2076 Data size: 1148660 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2048 Data size: 1131300 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -206,7 +206,7 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 2076 Data size: 16608 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2048 Data size: 16384 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash @@ -336,18 +336,18 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col0 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 2076 Data size: 6924 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2048 Data size: 6812 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: smallint) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 623 Data size: 7064 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 631 Data size: 7148 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: smallint) sort order: + Map-reduce partition columns: _col0 (type: smallint) - Statistics: Num rows: 623 Data size: 7064 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 631 Data size: 7148 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Reducer 3 Execution mode: llap @@ -357,11 +357,11 @@ STAGE PLANS: keys: KEY._col0 (type: smallint) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 623 Data size: 7064 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 631 Data size: 7148 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: bigint) sort order: + - Statistics: Num rows: 623 Data size: 7064 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 631 Data size: 7148 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: smallint) Reducer 4 Execution mode: llap @@ -369,10 +369,10 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: smallint), KEY.reducesinkkey0 (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 623 Data size: 7064 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 631 Data size: 7148 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 623 Data size: 7064 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 631 Data size: 7148 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/tez_dynpart_hashjoin_2.q.out b/ql/src/test/results/clientpositive/llap/tez_dynpart_hashjoin_2.q.out index 642bda2..2b8a4ed 100644 --- a/ql/src/test/results/clientpositive/llap/tez_dynpart_hashjoin_2.q.out +++ b/ql/src/test/results/clientpositive/llap/tez_dynpart_hashjoin_2.q.out @@ -105,11 +105,11 @@ STAGE PLANS: 1 UDFToInteger(_col0) (type: int) 2 (UDFToInteger(_col0) + 0) (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 1776 Data size: 312050 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1715 Data size: 293140 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: smallint), _col0 (type: tinyint), _col2 (type: int) sort order: +++ - Statistics: Num rows: 1776 Data size: 312050 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1715 Data size: 293140 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: bigint), _col4 (type: float), _col5 (type: double), _col6 (type: string), _col7 (type: string), _col8 (type: timestamp), _col9 (type: timestamp), _col10 (type: boolean), _col11 (type: boolean) Reducer 3 Execution mode: llap @@ -117,10 +117,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey1 (type: tinyint), KEY.reducesinkkey0 (type: smallint), KEY.reducesinkkey2 (type: int), VALUE._col0 (type: bigint), VALUE._col1 (type: float), VALUE._col2 (type: double), VALUE._col3 (type: string), VALUE._col4 (type: string), VALUE._col5 (type: timestamp), VALUE._col6 (type: timestamp), VALUE._col7 (type: boolean), VALUE._col8 (type: boolean) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 1776 Data size: 312050 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1715 Data size: 293140 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1776 Data size: 312050 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1715 Data size: 293140 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -296,11 +296,11 @@ STAGE PLANS: 1 UDFToInteger(_col0) (type: int) 2 (UDFToInteger(_col0) + 0) (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 1776 Data size: 312050 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1715 Data size: 293140 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: smallint), _col0 (type: tinyint), _col2 (type: int) sort order: +++ - Statistics: Num rows: 1776 Data size: 312050 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1715 Data size: 293140 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: bigint), _col4 (type: float), _col5 (type: double), _col6 (type: string), _col7 (type: string), _col8 (type: timestamp), _col9 (type: timestamp), _col10 (type: boolean), _col11 (type: boolean) Reducer 3 Execution mode: llap @@ -308,10 +308,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey1 (type: tinyint), KEY.reducesinkkey0 (type: smallint), KEY.reducesinkkey2 (type: int), VALUE._col0 (type: bigint), VALUE._col1 (type: float), VALUE._col2 (type: double), VALUE._col3 (type: string), VALUE._col4 (type: string), VALUE._col5 (type: timestamp), VALUE._col6 (type: timestamp), VALUE._col7 (type: boolean), VALUE._col8 (type: boolean) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 1776 Data size: 312050 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1715 Data size: 293140 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1776 Data size: 312050 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1715 Data size: 293140 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -487,11 +487,11 @@ STAGE PLANS: 1 UDFToInteger(_col0) (type: int) 2 (UDFToInteger(_col0) + 0) (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 1776 Data size: 312050 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1715 Data size: 293140 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: smallint), _col0 (type: tinyint), _col2 (type: int) sort order: +++ - Statistics: Num rows: 1776 Data size: 312050 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1715 Data size: 293140 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: bigint), _col4 (type: float), _col5 (type: double), _col6 (type: string), _col7 (type: string), _col8 (type: timestamp), _col9 (type: timestamp), _col10 (type: boolean), _col11 (type: boolean) Reducer 3 Execution mode: llap @@ -499,10 +499,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey1 (type: tinyint), KEY.reducesinkkey0 (type: smallint), KEY.reducesinkkey2 (type: int), VALUE._col0 (type: bigint), VALUE._col1 (type: float), VALUE._col2 (type: double), VALUE._col3 (type: string), VALUE._col4 (type: string), VALUE._col5 (type: timestamp), VALUE._col6 (type: timestamp), VALUE._col7 (type: boolean), VALUE._col8 (type: boolean) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 1776 Data size: 312050 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1715 Data size: 293140 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1776 Data size: 312050 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1715 Data size: 293140 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/tez_join_hash.q.out b/ql/src/test/results/clientpositive/llap/tez_join_hash.q.out index cce289d..ec2ed8d 100644 --- a/ql/src/test/results/clientpositive/llap/tez_join_hash.q.out +++ b/ql/src/test/results/clientpositive/llap/tez_join_hash.q.out @@ -207,7 +207,7 @@ STAGE PLANS: key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 14944 Data size: 2660032 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 14658 Data size: 2609124 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string) Execution mode: vectorized, llap LLAP IO: no inputs @@ -240,16 +240,16 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col1, _col2 - Statistics: Num rows: 12944 Data size: 2304032 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 12658 Data size: 2253124 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 12944 Data size: 2304032 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 12658 Data size: 2253124 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 14944 Data size: 2660032 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 14658 Data size: 2609124 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string) Reducer 4 Execution mode: llap @@ -261,18 +261,18 @@ STAGE PLANS: 0 _col1 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 24181 Data size: 4304218 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 23872 Data size: 4249216 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 12090 Data size: 2248740 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11936 Data size: 2220096 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 12090 Data size: 2248740 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11936 Data size: 2220096 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: bigint) Reducer 5 Execution mode: vectorized, llap @@ -282,14 +282,14 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 12090 Data size: 2248740 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11936 Data size: 2220096 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col2 (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 12090 Data size: 1148550 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11936 Data size: 1133920 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 12090 Data size: 1148550 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11936 Data size: 1133920 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/tez_join_tests.q.out b/ql/src/test/results/clientpositive/llap/tez_join_tests.q.out index 75879fb..e25d256 100644 --- a/ql/src/test/results/clientpositive/llap/tez_join_tests.q.out +++ b/ql/src/test/results/clientpositive/llap/tez_join_tests.q.out @@ -71,12 +71,12 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 40 Data size: 7120 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6942 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 40 Data size: 7120 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6942 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string) Reducer 3 Execution mode: llap @@ -88,11 +88,11 @@ STAGE PLANS: 0 _col1 (type: string) 1 _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 100570 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 100392 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 500 Data size: 100570 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 100392 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string) Reducer 4 Execution mode: llap @@ -100,10 +100,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string), VALUE._col1 (type: string), VALUE._col2 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 100570 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 100392 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 100570 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 100392 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/tez_joins_explain.q.out b/ql/src/test/results/clientpositive/llap/tez_joins_explain.q.out index 3790b37..8867c95 100644 --- a/ql/src/test/results/clientpositive/llap/tez_joins_explain.q.out +++ b/ql/src/test/results/clientpositive/llap/tez_joins_explain.q.out @@ -71,12 +71,12 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 40 Data size: 7120 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6942 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 40 Data size: 7120 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6942 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string) Reducer 3 Execution mode: llap @@ -88,11 +88,11 @@ STAGE PLANS: 0 _col1 (type: string) 1 _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 100570 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 100392 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 500 Data size: 100570 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 100392 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string) Reducer 4 Execution mode: llap @@ -100,10 +100,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string), VALUE._col1 (type: string), VALUE._col2 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 100570 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 100392 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 100570 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 100392 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/tez_smb_main.q.out b/ql/src/test/results/clientpositive/llap/tez_smb_main.q.out index f457814..e950d21 100644 --- a/ql/src/test/results/clientpositive/llap/tez_smb_main.q.out +++ b/ql/src/test/results/clientpositive/llap/tez_smb_main.q.out @@ -66,10 +66,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 40 Data size: 14120 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 13767 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 40 Data size: 14120 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 13767 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -263,33 +263,33 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 242 Data size: 3490 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 968 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 230 Data size: 3316 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 968 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 230 Data size: 3316 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 968 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 230 Data size: 3316 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 968 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Map 2 Map Operator Tree: TableScan alias: b - Statistics: Num rows: 500 Data size: 7216 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 475 Data size: 6855 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 475 Data size: 6855 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -298,15 +298,15 @@ STAGE PLANS: 1 _col0 (type: int) input vertices: 0 Map 1 - Statistics: Num rows: 522 Data size: 7540 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 399 Data size: 3192 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: llap LLAP IO: no inputs @@ -317,10 +317,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -374,33 +374,33 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 242 Data size: 3490 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 968 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 230 Data size: 3316 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 968 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 230 Data size: 3316 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 968 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 230 Data size: 3316 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 968 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Map 2 Map Operator Tree: TableScan alias: b - Statistics: Num rows: 500 Data size: 7216 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 475 Data size: 6855 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 475 Data size: 6855 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -409,15 +409,15 @@ STAGE PLANS: 1 _col0 (type: int) input vertices: 0 Map 1 - Statistics: Num rows: 522 Data size: 7540 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 399 Data size: 3192 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: llap LLAP IO: no inputs @@ -428,10 +428,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1674,14 +1674,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: s1 - Statistics: Num rows: 242 Data size: 924 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 968 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 230 Data size: 878 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 968 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 230 Data size: 878 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 968 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -1691,7 +1691,7 @@ STAGE PLANS: outputColumnNames: _col0 input vertices: 1 Map 4 - Statistics: Num rows: 253 Data size: 965 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 382 Data size: 1528 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -1700,15 +1700,15 @@ STAGE PLANS: 1 _col0 (type: int) input vertices: 1 Map 6 - Statistics: Num rows: 531 Data size: 2027 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1029 Data size: 8232 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: llap LLAP IO: no inputs @@ -1716,33 +1716,33 @@ STAGE PLANS: Map Operator Tree: TableScan alias: s3 - Statistics: Num rows: 242 Data size: 924 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 968 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 230 Data size: 878 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 968 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 230 Data size: 878 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 968 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 230 Data size: 878 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 968 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Map 5 Map Operator Tree: TableScan alias: s2 - Statistics: Num rows: 242 Data size: 924 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 968 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 230 Data size: 878 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 968 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 230 Data size: 878 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 968 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -1751,15 +1751,15 @@ STAGE PLANS: 1 _col0 (type: int) input vertices: 1 Map 6 - Statistics: Num rows: 531 Data size: 2027 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1029 Data size: 8232 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: llap LLAP IO: no inputs @@ -1767,24 +1767,24 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 500 Data size: 1904 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 475 Data size: 1808 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 475 Data size: 1808 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 475 Data size: 1808 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 475 Data size: 1808 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Reducer 3 @@ -1794,10 +1794,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1838,7 +1838,8 @@ STAGE PLANS: Tez #### A masked pattern was here #### Edges: - Reducer 4 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) + Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 4 <- Map 3 (SIMPLE_EDGE), Reducer 2 (CUSTOM_SIMPLE_EDGE) Reducer 5 <- Reducer 4 (CUSTOM_SIMPLE_EDGE) #### A masked pattern was here #### Vertices: @@ -1846,65 +1847,74 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1 - Statistics: Num rows: 242 Data size: 45994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 22990 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 230 Data size: 43713 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 22990 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 230 Data size: 43713 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 22990 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string) sort order: ++ - Statistics: Num rows: 230 Data size: 43713 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 22990 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Map 3 Map Operator Tree: TableScan alias: t2 - Statistics: Num rows: 500 Data size: 94800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 475 Data size: 90060 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 475 Data size: 90060 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string) sort order: ++ - Statistics: Num rows: 475 Data size: 90060 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs - Reducer 4 + Reducer 2 + Execution mode: llap Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 230 Data size: 43713 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 968 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 242 Data size: 968 Basic stats: COMPLETE Column stats: COMPLETE + Reducer 4 Execution mode: llap Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 475 Data size: 90060 Basic stats: COMPLETE Column stats: NONE - Merge Join Operator + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator condition map: Inner Join 0 to 1 keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 522 Data size: 99066 Basic stats: COMPLETE Column stats: NONE + input vertices: + 0 Reducer 2 + Statistics: Num rows: 399 Data size: 3192 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Reducer 5 Execution mode: llap @@ -1913,10 +1923,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/tez_union.q.out b/ql/src/test/results/clientpositive/llap/tez_union.q.out index 9118403..f93922a 100644 --- a/ql/src/test/results/clientpositive/llap/tez_union.q.out +++ b/ql/src/test/results/clientpositive/llap/tez_union.q.out @@ -42,10 +42,10 @@ STAGE PLANS: outputColumnNames: _col0, _col1 input vertices: 1 Map 3 - Statistics: Num rows: 809 Data size: 144002 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1309 Data size: 233002 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1291 Data size: 229798 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -82,7 +82,7 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1309 Data size: 233002 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1291 Data size: 229798 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -264,7 +264,7 @@ STAGE PLANS: keys: 0 _col0 (type: string) 1 _col0 (type: string) - Statistics: Num rows: 3236 Data size: 25888 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3164 Data size: 25312 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash @@ -400,10 +400,10 @@ STAGE PLANS: outputColumnNames: _col0, _col1 input vertices: 0 Map 1 - Statistics: Num rows: 1618 Data size: 281532 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1582 Data size: 275268 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1618 Data size: 281532 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1582 Data size: 275268 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -431,10 +431,10 @@ STAGE PLANS: outputColumnNames: _col0, _col1 input vertices: 0 Map 1 - Statistics: Num rows: 1618 Data size: 281532 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1582 Data size: 275268 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1618 Data size: 281532 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1582 Data size: 275268 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -556,7 +556,7 @@ STAGE PLANS: outputColumnNames: _col0 input vertices: 1 Map 4 - Statistics: Num rows: 809 Data size: 70383 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 68817 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -569,15 +569,15 @@ STAGE PLANS: input vertices: 1 Map 9 2 Map 10 - Statistics: Num rows: 6354 Data size: 1658394 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5941 Data size: 1550601 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string), _col0 (type: string), _col2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6354 Data size: 1658394 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5941 Data size: 1550601 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col2 (type: string) sort order: + - Statistics: Num rows: 6354 Data size: 1658394 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5941 Data size: 1550601 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string) Execution mode: llap LLAP IO: no inputs @@ -650,7 +650,7 @@ STAGE PLANS: outputColumnNames: _col0 input vertices: 1 Map 6 - Statistics: Num rows: 809 Data size: 70383 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 68817 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -663,15 +663,15 @@ STAGE PLANS: input vertices: 1 Map 9 2 Map 10 - Statistics: Num rows: 6354 Data size: 1658394 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5941 Data size: 1550601 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string), _col0 (type: string), _col2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6354 Data size: 1658394 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5941 Data size: 1550601 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col2 (type: string) sort order: + - Statistics: Num rows: 6354 Data size: 1658394 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5941 Data size: 1550601 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string) Execution mode: llap LLAP IO: no inputs @@ -715,7 +715,7 @@ STAGE PLANS: outputColumnNames: _col0 input vertices: 1 Map 8 - Statistics: Num rows: 809 Data size: 70383 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 68817 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -728,15 +728,15 @@ STAGE PLANS: input vertices: 1 Map 9 2 Map 10 - Statistics: Num rows: 6354 Data size: 1658394 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5941 Data size: 1550601 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string), _col0 (type: string), _col2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6354 Data size: 1658394 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5941 Data size: 1550601 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col2 (type: string) sort order: + - Statistics: Num rows: 6354 Data size: 1658394 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5941 Data size: 1550601 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string) Execution mode: llap LLAP IO: no inputs @@ -794,10 +794,10 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: string), VALUE._col1 (type: string), KEY.reducesinkkey0 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6354 Data size: 1658394 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5941 Data size: 1550601 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 6354 Data size: 1658394 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5941 Data size: 1550601 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -996,10 +996,10 @@ STAGE PLANS: outputColumnNames: _col0 input vertices: 1 Map 3 - Statistics: Num rows: 809 Data size: 70383 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 68817 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1618 Data size: 140766 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1582 Data size: 137634 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1046,10 +1046,10 @@ STAGE PLANS: outputColumnNames: _col0 input vertices: 1 Map 5 - Statistics: Num rows: 809 Data size: 70383 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 68817 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1618 Data size: 140766 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1582 Data size: 137634 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1186,10 +1186,10 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3 input vertices: 1 Map 4 - Statistics: Num rows: 1618 Data size: 576008 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1582 Data size: 563192 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1618 Data size: 576008 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1582 Data size: 563192 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1214,10 +1214,10 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3 input vertices: 1 Map 4 - Statistics: Num rows: 1618 Data size: 576008 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1582 Data size: 563192 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1618 Data size: 576008 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1582 Data size: 563192 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1330,10 +1330,10 @@ STAGE PLANS: outputColumnNames: _col0, _col1 input vertices: 0 Union 2 - Statistics: Num rows: 1618 Data size: 281532 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1582 Data size: 275268 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1618 Data size: 281532 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1582 Data size: 275268 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/tez_union2.q.out b/ql/src/test/results/clientpositive/llap/tez_union2.q.out index 1c8dd11..b379340 100644 --- a/ql/src/test/results/clientpositive/llap/tez_union2.q.out +++ b/ql/src/test/results/clientpositive/llap/tez_union2.q.out @@ -61,12 +61,12 @@ STAGE PLANS: keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 404 Data size: 71912 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 408 Data size: 72624 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 404 Data size: 71912 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 408 Data size: 72624 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Map 4 @@ -118,10 +118,10 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 404 Data size: 71912 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 408 Data size: 72624 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 404 Data size: 71912 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 408 Data size: 72624 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -142,21 +142,21 @@ STAGE PLANS: keys: _col0 (type: string) mode: complete outputColumnNames: _col0 - Statistics: Num rows: 309 Data size: 26883 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 27492 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 309 Data size: 53766 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 54984 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 404 Data size: 71912 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 408 Data size: 72624 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 404 Data size: 71912 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 408 Data size: 72624 Basic stats: COMPLETE Column stats: COMPLETE Union 2 Vertex: Union 2 Union 5 diff --git a/ql/src/test/results/clientpositive/llap/tez_union_multiinsert.q.out b/ql/src/test/results/clientpositive/llap/tez_union_multiinsert.q.out index 16f10e7..c201312 100644 --- a/ql/src/test/results/clientpositive/llap/tez_union_multiinsert.q.out +++ b/ql/src/test/results/clientpositive/llap/tez_union_multiinsert.q.out @@ -188,14 +188,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 309 Data size: 29664 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30336 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), UDFToString(_col1) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 309 Data size: 84048 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 85952 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 309 Data size: 84048 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 85952 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -1129,14 +1129,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 309 Data size: 29664 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30336 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), UDFToString(_col1) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 309 Data size: 84048 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 85952 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 309 Data size: 84048 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 85952 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -2100,14 +2100,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 309 Data size: 29664 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30336 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), UDFToString(_col1) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 309 Data size: 84048 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 85952 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 309 Data size: 84048 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 85952 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/tez_vector_dynpart_hashjoin_1.q.out b/ql/src/test/results/clientpositive/llap/tez_vector_dynpart_hashjoin_1.q.out index d0a5e62..049f46b 100644 --- a/ql/src/test/results/clientpositive/llap/tez_vector_dynpart_hashjoin_1.q.out +++ b/ql/src/test/results/clientpositive/llap/tez_vector_dynpart_hashjoin_1.q.out @@ -77,11 +77,11 @@ STAGE PLANS: 0 _col2 (type: int) 1 _col2 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23 - Statistics: Num rows: 2076 Data size: 1148660 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2048 Data size: 1131300 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col2 (type: int) sort order: + - Statistics: Num rows: 2076 Data size: 1148660 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2048 Data size: 1131300 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: tinyint), _col1 (type: smallint), _col3 (type: bigint), _col4 (type: float), _col5 (type: double), _col6 (type: string), _col7 (type: string), _col8 (type: timestamp), _col9 (type: timestamp), _col10 (type: boolean), _col11 (type: boolean), _col12 (type: tinyint), _col13 (type: smallint), _col14 (type: int), _col15 (type: bigint), _col16 (type: float), _col17 (type: double), _col18 (type: string), _col19 (type: string), _col20 (type: timestamp), _col21 (type: timestamp), _col22 (type: boolean), _col23 (type: boolean) Reducer 3 Execution mode: llap @@ -89,10 +89,10 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: tinyint), VALUE._col1 (type: smallint), KEY.reducesinkkey0 (type: int), VALUE._col2 (type: bigint), VALUE._col3 (type: float), VALUE._col4 (type: double), VALUE._col5 (type: string), VALUE._col6 (type: string), VALUE._col7 (type: timestamp), VALUE._col8 (type: timestamp), VALUE._col9 (type: boolean), VALUE._col10 (type: boolean), VALUE._col11 (type: tinyint), VALUE._col12 (type: smallint), VALUE._col13 (type: int), VALUE._col14 (type: bigint), VALUE._col15 (type: float), VALUE._col16 (type: double), VALUE._col17 (type: string), VALUE._col18 (type: string), VALUE._col19 (type: timestamp), VALUE._col20 (type: timestamp), VALUE._col21 (type: boolean), VALUE._col22 (type: boolean) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23 - Statistics: Num rows: 2076 Data size: 1148660 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2048 Data size: 1131300 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 2076 Data size: 1148660 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2048 Data size: 1131300 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -206,7 +206,7 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 2076 Data size: 16608 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2048 Data size: 16384 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash @@ -336,18 +336,18 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col0 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 2076 Data size: 6924 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2048 Data size: 6812 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: smallint) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 623 Data size: 7064 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 631 Data size: 7148 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: smallint) sort order: + Map-reduce partition columns: _col0 (type: smallint) - Statistics: Num rows: 623 Data size: 7064 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 631 Data size: 7148 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Reducer 3 Execution mode: llap @@ -357,11 +357,11 @@ STAGE PLANS: keys: KEY._col0 (type: smallint) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 623 Data size: 7064 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 631 Data size: 7148 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: bigint) sort order: + - Statistics: Num rows: 623 Data size: 7064 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 631 Data size: 7148 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: smallint) Reducer 4 Execution mode: llap @@ -369,10 +369,10 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: smallint), KEY.reducesinkkey0 (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 623 Data size: 7064 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 631 Data size: 7148 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 623 Data size: 7064 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 631 Data size: 7148 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/tez_vector_dynpart_hashjoin_2.q.out b/ql/src/test/results/clientpositive/llap/tez_vector_dynpart_hashjoin_2.q.out index 1ce7a3a..0f1883a 100644 --- a/ql/src/test/results/clientpositive/llap/tez_vector_dynpart_hashjoin_2.q.out +++ b/ql/src/test/results/clientpositive/llap/tez_vector_dynpart_hashjoin_2.q.out @@ -105,11 +105,11 @@ STAGE PLANS: 1 UDFToInteger(_col0) (type: int) 2 (UDFToInteger(_col0) + 0) (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 1776 Data size: 312050 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1715 Data size: 293140 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: smallint), _col0 (type: tinyint), _col2 (type: int) sort order: +++ - Statistics: Num rows: 1776 Data size: 312050 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1715 Data size: 293140 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: bigint), _col4 (type: float), _col5 (type: double), _col6 (type: string), _col7 (type: string), _col8 (type: timestamp), _col9 (type: timestamp), _col10 (type: boolean), _col11 (type: boolean) Reducer 3 Execution mode: llap @@ -117,10 +117,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey1 (type: tinyint), KEY.reducesinkkey0 (type: smallint), KEY.reducesinkkey2 (type: int), VALUE._col0 (type: bigint), VALUE._col1 (type: float), VALUE._col2 (type: double), VALUE._col3 (type: string), VALUE._col4 (type: string), VALUE._col5 (type: timestamp), VALUE._col6 (type: timestamp), VALUE._col7 (type: boolean), VALUE._col8 (type: boolean) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 1776 Data size: 312050 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1715 Data size: 293140 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1776 Data size: 312050 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1715 Data size: 293140 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -296,11 +296,11 @@ STAGE PLANS: 1 UDFToInteger(_col0) (type: int) 2 (UDFToInteger(_col0) + 0) (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 1776 Data size: 312050 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1715 Data size: 293140 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: smallint), _col0 (type: tinyint), _col2 (type: int) sort order: +++ - Statistics: Num rows: 1776 Data size: 312050 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1715 Data size: 293140 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: bigint), _col4 (type: float), _col5 (type: double), _col6 (type: string), _col7 (type: string), _col8 (type: timestamp), _col9 (type: timestamp), _col10 (type: boolean), _col11 (type: boolean) Reducer 3 Execution mode: vectorized, llap @@ -308,10 +308,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey1 (type: tinyint), KEY.reducesinkkey0 (type: smallint), KEY.reducesinkkey2 (type: int), VALUE._col0 (type: bigint), VALUE._col1 (type: float), VALUE._col2 (type: double), VALUE._col3 (type: string), VALUE._col4 (type: string), VALUE._col5 (type: timestamp), VALUE._col6 (type: timestamp), VALUE._col7 (type: boolean), VALUE._col8 (type: boolean) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 1776 Data size: 312050 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1715 Data size: 293140 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1776 Data size: 312050 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1715 Data size: 293140 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -487,11 +487,11 @@ STAGE PLANS: 1 UDFToInteger(_col0) (type: int) 2 (UDFToInteger(_col0) + 0) (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 1776 Data size: 312050 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1715 Data size: 293140 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: smallint), _col0 (type: tinyint), _col2 (type: int) sort order: +++ - Statistics: Num rows: 1776 Data size: 312050 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1715 Data size: 293140 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: bigint), _col4 (type: float), _col5 (type: double), _col6 (type: string), _col7 (type: string), _col8 (type: timestamp), _col9 (type: timestamp), _col10 (type: boolean), _col11 (type: boolean) Reducer 3 Execution mode: vectorized, llap @@ -499,10 +499,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey1 (type: tinyint), KEY.reducesinkkey0 (type: smallint), KEY.reducesinkkey2 (type: int), VALUE._col0 (type: bigint), VALUE._col1 (type: float), VALUE._col2 (type: double), VALUE._col3 (type: string), VALUE._col4 (type: string), VALUE._col5 (type: timestamp), VALUE._col6 (type: timestamp), VALUE._col7 (type: boolean), VALUE._col8 (type: boolean) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 1776 Data size: 312050 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1715 Data size: 293140 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1776 Data size: 312050 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1715 Data size: 293140 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/unionDistinct_3.q.out b/ql/src/test/results/clientpositive/llap/unionDistinct_3.q.out index 146cc62..2fff86d 100644 --- a/ql/src/test/results/clientpositive/llap/unionDistinct_3.q.out +++ b/ql/src/test/results/clientpositive/llap/unionDistinct_3.q.out @@ -1780,10 +1780,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 66 Data size: 35904 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 65 Data size: 35360 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 66 Data size: 35904 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 65 Data size: 35360 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1929,12 +1929,12 @@ STAGE PLANS: keys: _col0 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 309 Data size: 56856 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 58144 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 309 Data size: 56856 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 58144 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Map 10 @@ -1950,12 +1950,12 @@ STAGE PLANS: keys: _col0 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 309 Data size: 56856 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 58144 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 309 Data size: 56856 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 58144 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Map 11 @@ -1971,12 +1971,12 @@ STAGE PLANS: keys: _col0 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 309 Data size: 56856 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 58144 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 309 Data size: 56856 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 58144 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Map 12 @@ -1992,12 +1992,12 @@ STAGE PLANS: keys: _col0 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 160 Data size: 29440 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 163 Data size: 29992 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 160 Data size: 29440 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 163 Data size: 29992 Basic stats: COMPLETE Column stats: PARTIAL Execution mode: llap LLAP IO: no inputs Map 13 @@ -2013,12 +2013,12 @@ STAGE PLANS: keys: _col0 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 85 Data size: 15640 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 87 Data size: 16008 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 85 Data size: 15640 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 87 Data size: 16008 Basic stats: COMPLETE Column stats: PARTIAL Execution mode: llap LLAP IO: no inputs Reducer 3 @@ -2028,17 +2028,17 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 309 Data size: 56856 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 58144 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 309 Data size: 56856 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 58144 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 309 Data size: 56856 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 58144 Basic stats: COMPLETE Column stats: COMPLETE Reducer 5 Execution mode: llap Reduce Operator Tree: @@ -2046,17 +2046,17 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 309 Data size: 56856 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 58144 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 160 Data size: 29440 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 163 Data size: 29992 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 160 Data size: 29440 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 163 Data size: 29992 Basic stats: COMPLETE Column stats: PARTIAL Reducer 7 Execution mode: llap Reduce Operator Tree: @@ -2064,17 +2064,17 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 160 Data size: 29440 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 163 Data size: 29992 Basic stats: COMPLETE Column stats: PARTIAL Group By Operator keys: _col0 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 85 Data size: 15640 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 87 Data size: 16008 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 85 Data size: 15640 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 87 Data size: 16008 Basic stats: COMPLETE Column stats: PARTIAL Reducer 9 Execution mode: llap Reduce Operator Tree: @@ -2082,16 +2082,16 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 85 Data size: 15640 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 87 Data size: 16008 Basic stats: COMPLETE Column stats: PARTIAL Group By Operator aggregations: count(1) keys: _col0 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 85 Data size: 16320 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 87 Data size: 16704 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 85 Data size: 16320 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 87 Data size: 16704 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/union_top_level.q.out b/ql/src/test/results/clientpositive/llap/union_top_level.q.out index 0cf6732..2999d32 100644 --- a/ql/src/test/results/clientpositive/llap/union_top_level.q.out +++ b/ql/src/test/results/clientpositive/llap/union_top_level.q.out @@ -274,15 +274,15 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col1, _col2 - Statistics: Num rows: 809 Data size: 144002 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 809 Data size: 144002 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 809 Data size: 144002 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: string) Reducer 3 @@ -291,7 +291,7 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 809 Data size: 144002 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE @@ -312,15 +312,15 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col1, _col2 - Statistics: Num rows: 809 Data size: 144002 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 809 Data size: 144002 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 809 Data size: 144002 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: string) Reducer 6 @@ -329,7 +329,7 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 809 Data size: 144002 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE diff --git a/ql/src/test/results/clientpositive/llap/vector_groupby_mapjoin.q.out b/ql/src/test/results/clientpositive/llap/vector_groupby_mapjoin.q.out index 82b6ba0..43a6ddd 100644 --- a/ql/src/test/results/clientpositive/llap/vector_groupby_mapjoin.q.out +++ b/ql/src/test/results/clientpositive/llap/vector_groupby_mapjoin.q.out @@ -155,10 +155,10 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3, _col5 input vertices: 1 Reducer 6 - Statistics: Num rows: 500 Data size: 98620 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 98584 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((_col2 = 0) or (_col5 is null and _col0 is not null and (_col3 >= _col2))) (type: boolean) - Statistics: Num rows: 500 Data size: 98620 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 98584 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 diff --git a/ql/src/test/results/clientpositive/llap/vector_left_outer_join.q.out b/ql/src/test/results/clientpositive/llap/vector_left_outer_join.q.out index dc8f47e..b269f9b 100644 --- a/ql/src/test/results/clientpositive/llap/vector_left_outer_join.q.out +++ b/ql/src/test/results/clientpositive/llap/vector_left_outer_join.q.out @@ -51,7 +51,7 @@ STAGE PLANS: outputColumnNames: _col0 input vertices: 1 Map 3 - Statistics: Num rows: 25044 Data size: 87720 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 24737 Data size: 86492 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Left Outer Join 0 to 1 @@ -60,7 +60,7 @@ STAGE PLANS: 1 _col0 (type: tinyint) input vertices: 1 Map 4 - Statistics: Num rows: 2423154 Data size: 19385232 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2393450 Data size: 19147600 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash diff --git a/ql/src/test/results/clientpositive/llap/vectorization_short_regress.q.out b/ql/src/test/results/clientpositive/llap/vectorization_short_regress.q.out index 0027ab5..facf121 100644 --- a/ql/src/test/results/clientpositive/llap/vectorization_short_regress.q.out +++ b/ql/src/test/results/clientpositive/llap/vectorization_short_regress.q.out @@ -2202,7 +2202,7 @@ STAGE PLANS: keys: csmallint (type: smallint) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1141 Data size: 204228 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1156 Data size: 206912 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: smallint) sort order: + @@ -2211,7 +2211,7 @@ STAGE PLANS: className: VectorReduceSinkLongOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 1141 Data size: 204228 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1156 Data size: 206912 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: struct), _col2 (type: bigint), _col3 (type: struct), _col4 (type: bigint) Execution mode: vectorized, llap LLAP IO: all inputs @@ -2246,7 +2246,7 @@ STAGE PLANS: keys: KEY._col0 (type: smallint) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1141 Data size: 39924 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1156 Data size: 40448 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: smallint), (UDFToInteger(_col0) % -75) (type: int), _col1 (type: double), (-1.389 / CAST( _col0 AS decimal(5,0))) (type: decimal(10,9)), _col2 (type: bigint), (UDFToDouble((UDFToInteger(_col0) % -75)) / UDFToDouble(_col2)) (type: double), (- (UDFToInteger(_col0) % -75)) (type: int), _col3 (type: double), (- (- (UDFToInteger(_col0) % -75))) (type: int), _col4 (type: bigint), (_col4 - -89010) (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 @@ -2255,7 +2255,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [0, 5, 1, 7, 2, 11, 12, 3, 8, 4, 13] selectExpressions: LongColModuloLongScalar(col 0:int, val -75)(children: col 0:smallint) -> 5:int, DecimalScalarDivideDecimalColumn(val -1.389, col 6:decimal(5,0))(children: CastLongToDecimal(col 0:smallint) -> 6:decimal(5,0)) -> 7:decimal(10,9), DoubleColDivideDoubleColumn(col 9:double, col 10:double)(children: CastLongToDouble(col 8:int)(children: LongColModuloLongScalar(col 0:int, val -75)(children: col 0:smallint) -> 8:int) -> 9:double, CastLongToDouble(col 2:bigint) -> 10:double) -> 11:double, LongColUnaryMinus(col 8:int)(children: LongColModuloLongScalar(col 0:int, val -75)(children: col 0:smallint) -> 8:int) -> 12:int, LongColUnaryMinus(col 13:int)(children: LongColUnaryMinus(col 8:int)(children: LongColModuloLongScalar(col 0:int, val -75)(children: col 0:smallint) -> 8:int) -> 13:int) -> 8:int, LongColSubtractLongScalar(col 4:bigint, val -89010) -> 13:bigint - Statistics: Num rows: 1141 Data size: 199664 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1156 Data size: 202288 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: double), _col3 (type: decimal(10,9)), _col4 (type: bigint), _col5 (type: double), _col6 (type: int), _col7 (type: double), _col8 (type: int), _col9 (type: bigint), _col10 (type: bigint) sort order: +++++++++++ @@ -2263,7 +2263,7 @@ STAGE PLANS: className: VectorReduceSinkObjectHashOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 1141 Data size: 199664 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1156 Data size: 202288 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 Reducer 3 Execution mode: vectorized, llap @@ -2281,7 +2281,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10] - Statistics: Num rows: 1141 Data size: 199664 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1156 Data size: 202288 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 20 Limit Vectorization: @@ -2478,7 +2478,7 @@ STAGE PLANS: keys: cdouble (type: double) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 1136 Data size: 306696 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1127 Data size: 304272 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: double) sort order: + @@ -2487,7 +2487,7 @@ STAGE PLANS: className: VectorReduceSinkMultiKeyOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 1136 Data size: 306696 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1127 Data size: 304272 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: struct), _col2 (type: bigint), _col3 (type: double), _col4 (type: struct), _col5 (type: struct), _col6 (type: double) Execution mode: vectorized, llap LLAP IO: all inputs @@ -2522,7 +2522,7 @@ STAGE PLANS: keys: KEY._col0 (type: double) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 1136 Data size: 61320 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1127 Data size: 60840 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: double), _col1 (type: double), (2563.58 * _col1) (type: double), (- _col1) (type: double), _col2 (type: bigint), ((2563.58 * _col1) + -5638.15) (type: double), ((- _col1) * ((2563.58 * _col1) + -5638.15)) (type: double), _col3 (type: double), _col4 (type: double), (_col0 - (- _col1)) (type: double), _col5 (type: double), (_col0 + _col1) (type: double), (_col0 * 762.0) (type: double), _col6 (type: double), (-863.257 % (_col0 * 762.0)) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 @@ -2531,7 +2531,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [0, 1, 7, 8, 2, 10, 11, 3, 4, 12, 5, 9, 13, 6, 15] selectExpressions: DoubleScalarMultiplyDoubleColumn(val 2563.58, col 1:double) -> 7:double, DoubleColUnaryMinus(col 1:double) -> 8:double, DoubleColAddDoubleScalar(col 9:double, val -5638.15)(children: DoubleScalarMultiplyDoubleColumn(val 2563.58, col 1:double) -> 9:double) -> 10:double, DoubleColMultiplyDoubleColumn(col 9:double, col 12:double)(children: DoubleColUnaryMinus(col 1:double) -> 9:double, DoubleColAddDoubleScalar(col 11:double, val -5638.15)(children: DoubleScalarMultiplyDoubleColumn(val 2563.58, col 1:double) -> 11:double) -> 12:double) -> 11:double, DoubleColSubtractDoubleColumn(col 0:double, col 9:double)(children: DoubleColUnaryMinus(col 1:double) -> 9:double) -> 12:double, DoubleColAddDoubleColumn(col 0:double, col 1:double) -> 9:double, DoubleColMultiplyDoubleScalar(col 0:double, val 762.0) -> 13:double, DoubleScalarModuloDoubleColumn(val -863.257, col 14:double)(children: DoubleColMultiplyDoubleScalar(col 0:double, val 762.0) -> 14:double) -> 15:double - Statistics: Num rows: 1136 Data size: 143112 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1127 Data size: 141984 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: double) sort order: + @@ -2539,7 +2539,7 @@ STAGE PLANS: className: VectorReduceSinkObjectHashOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 1136 Data size: 143112 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1127 Data size: 141984 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: double), _col2 (type: double), _col3 (type: double), _col4 (type: bigint), _col5 (type: double), _col6 (type: double), _col7 (type: double), _col8 (type: double), _col9 (type: double), _col10 (type: double), _col11 (type: double), _col12 (type: double), _col13 (type: double), _col14 (type: double) Reducer 3 Execution mode: vectorized, llap @@ -2557,13 +2557,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 13] - Statistics: Num rows: 1136 Data size: 143112 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1127 Data size: 141984 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 1136 Data size: 143112 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1127 Data size: 141984 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/vectorized_mapjoin.q.out b/ql/src/test/results/clientpositive/llap/vectorized_mapjoin.q.out index 0dff57a..6916b33 100644 --- a/ql/src/test/results/clientpositive/llap/vectorized_mapjoin.q.out +++ b/ql/src/test/results/clientpositive/llap/vectorized_mapjoin.q.out @@ -58,7 +58,7 @@ STAGE PLANS: outputColumnNames: _col0, _col1 input vertices: 1 Map 3 - Statistics: Num rows: 18694 Data size: 130960 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 18464 Data size: 129120 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: int), (_col0 + _col1) (type: int) outputColumnNames: _col0, _col1, _col2 @@ -67,7 +67,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [2, 2, 13] selectExpressions: LongColAddLongColumn(col 2:int, col 2:int) -> 13:int - Statistics: Num rows: 18694 Data size: 130960 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 18464 Data size: 129120 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(_col0), max(_col1), min(_col0), avg(_col2) Group By Vectorization: diff --git a/ql/src/test/results/clientpositive/llap/vectorized_nested_mapjoin.q.out b/ql/src/test/results/clientpositive/llap/vectorized_nested_mapjoin.q.out index 80e1cab..f876656 100644 --- a/ql/src/test/results/clientpositive/llap/vectorized_nested_mapjoin.q.out +++ b/ql/src/test/results/clientpositive/llap/vectorized_nested_mapjoin.q.out @@ -54,7 +54,7 @@ STAGE PLANS: outputColumnNames: _col1 input vertices: 1 Map 4 - Statistics: Num rows: 1284939 Data size: 10267240 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1268540 Data size: 10136048 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col1) mode: hash diff --git a/ql/src/test/results/clientpositive/llap/vectorized_shufflejoin.q.out b/ql/src/test/results/clientpositive/llap/vectorized_shufflejoin.q.out index 72216d3..ba11284 100644 --- a/ql/src/test/results/clientpositive/llap/vectorized_shufflejoin.q.out +++ b/ql/src/test/results/clientpositive/llap/vectorized_shufflejoin.q.out @@ -118,11 +118,11 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 18694 Data size: 130960 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 18464 Data size: 129120 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: int), (_col0 + _col1) (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 18694 Data size: 130960 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 18464 Data size: 129120 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(_col0), max(_col1), min(_col0), avg(_col2) mode: hash diff --git a/ql/src/test/results/clientpositive/mapjoin_mapjoin.q.out b/ql/src/test/results/clientpositive/mapjoin_mapjoin.q.out index c2c514f..f78c32c 100644 --- a/ql/src/test/results/clientpositive/mapjoin_mapjoin.q.out +++ b/ql/src/test/results/clientpositive/mapjoin_mapjoin.q.out @@ -526,24 +526,24 @@ STAGE PLANS: Stage: Stage-9 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_1:src + $hdt$_1:src1 Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_1:src + $hdt$_1:src1 TableScan - alias: src + alias: src1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: value is not null (type: boolean) + predicate: key is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: value (type: string) + expressions: key (type: string) outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col1 (type: string) + 0 _col0 (type: string) 1 _col0 (type: string) Stage: Stage-7 @@ -563,9 +563,9 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col1 (type: string) + 0 _col0 (type: string) 1 _col0 (type: string) - outputColumnNames: _col0, _col2 + outputColumnNames: _col1, _col2 Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -579,24 +579,24 @@ STAGE PLANS: Stage: Stage-8 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_2:src1 + $hdt$_2:src Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_2:src1 + $hdt$_2:src TableScan - alias: src1 + alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: key is not null (type: boolean) + predicate: value is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) + expressions: value (type: string) outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col0 (type: string) + 0 _col1 (type: string) 1 _col0 (type: string) Stage: Stage-3 @@ -607,7 +607,7 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) + 0 _col1 (type: string) 1 _col0 (type: string) outputColumnNames: _col2 Statistics: Num rows: 2420 Data size: 25709 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/spark/bucket_map_join_tez1.q.out b/ql/src/test/results/clientpositive/spark/bucket_map_join_tez1.q.out index 461c7da..2c86b3a 100644 --- a/ql/src/test/results/clientpositive/spark/bucket_map_join_tez1.q.out +++ b/ql/src/test/results/clientpositive/spark/bucket_map_join_tez1.q.out @@ -4269,74 +4269,74 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: int) + key expressions: _col1 (type: string) sort order: + - Map-reduce partition columns: _col0 (type: int) + Map-reduce partition columns: _col1 (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: _col0 (type: int) Map 4 Map Operator Tree: TableScan - alias: c + alias: b Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: key is not null (type: boolean) + predicate: value is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: int) - outputColumnNames: _col0 + expressions: key (type: int), value (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: int) + key expressions: _col1 (type: string) sort order: + - Map-reduce partition columns: _col0 (type: int) + Map-reduce partition columns: _col1 (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int) Map 5 Map Operator Tree: TableScan - alias: b + alias: c Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: value is not null (type: boolean) + predicate: key is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 + expressions: key (type: int) + outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col1 (type: string) + key expressions: _col0 (type: int) sort order: + - Map-reduce partition columns: _col1 (type: string) + Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int) Reducer 2 Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1 + 0 _col1 (type: string) + 1 _col1 (type: string) + outputColumnNames: _col0, _col2 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col1 (type: string) + key expressions: _col0 (type: int) sort order: + - Map-reduce partition columns: _col1 (type: string) + Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int) + value expressions: _col2 (type: int) Reducer 3 Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col1 (type: string) - 1 _col1 (type: string) - outputColumnNames: _col0, _col3 + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0, _col2 Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: int), _col3 (type: int) + expressions: _col0 (type: int), _col2 (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -4382,74 +4382,74 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: int) + key expressions: _col1 (type: string) sort order: + - Map-reduce partition columns: _col0 (type: int) + Map-reduce partition columns: _col1 (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: _col0 (type: int) Map 4 Map Operator Tree: TableScan - alias: c + alias: b Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: key is not null (type: boolean) + predicate: value is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: int) - outputColumnNames: _col0 + expressions: key (type: int), value (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: int) + key expressions: _col1 (type: string) sort order: + - Map-reduce partition columns: _col0 (type: int) + Map-reduce partition columns: _col1 (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int) Map 5 Map Operator Tree: TableScan - alias: b + alias: c Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: value is not null (type: boolean) + predicate: key is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 + expressions: key (type: int) + outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col1 (type: string) + key expressions: _col0 (type: int) sort order: + - Map-reduce partition columns: _col1 (type: string) + Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int) Reducer 2 Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1 + 0 _col1 (type: string) + 1 _col1 (type: string) + outputColumnNames: _col0, _col2 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col1 (type: string) + key expressions: _col0 (type: int) sort order: + - Map-reduce partition columns: _col1 (type: string) + Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int) + value expressions: _col2 (type: int) Reducer 3 Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col1 (type: string) - 1 _col1 (type: string) - outputColumnNames: _col0, _col3 + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0, _col2 Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: int), _col3 (type: int) + expressions: _col0 (type: int), _col2 (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE File Output Operator diff --git a/ql/src/test/results/clientpositive/spark/bucket_map_join_tez2.q.out b/ql/src/test/results/clientpositive/spark/bucket_map_join_tez2.q.out index 3ce67e2..f26a318 100644 --- a/ql/src/test/results/clientpositive/spark/bucket_map_join_tez2.q.out +++ b/ql/src/test/results/clientpositive/spark/bucket_map_join_tez2.q.out @@ -193,74 +193,74 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: int) + key expressions: _col1 (type: string) sort order: + - Map-reduce partition columns: _col0 (type: int) + Map-reduce partition columns: _col1 (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: _col0 (type: int) Map 4 Map Operator Tree: TableScan - alias: c + alias: b Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: key is not null (type: boolean) + predicate: value is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: int) - outputColumnNames: _col0 + expressions: key (type: int), value (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: int) + key expressions: _col1 (type: string) sort order: + - Map-reduce partition columns: _col0 (type: int) + Map-reduce partition columns: _col1 (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int) Map 5 Map Operator Tree: TableScan - alias: b + alias: c Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: value is not null (type: boolean) + predicate: key is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 + expressions: key (type: int) + outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col1 (type: string) + key expressions: _col0 (type: int) sort order: + - Map-reduce partition columns: _col1 (type: string) + Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int) Reducer 2 Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1 + 0 _col1 (type: string) + 1 _col1 (type: string) + outputColumnNames: _col0, _col2 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col1 (type: string) + key expressions: _col0 (type: int) sort order: + - Map-reduce partition columns: _col1 (type: string) + Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int) + value expressions: _col2 (type: int) Reducer 3 Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col1 (type: string) - 1 _col1 (type: string) - outputColumnNames: _col0, _col3 + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0, _col2 Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: int), _col3 (type: int) + expressions: _col0 (type: int), _col2 (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -306,74 +306,74 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: int) + key expressions: _col1 (type: string) sort order: + - Map-reduce partition columns: _col0 (type: int) + Map-reduce partition columns: _col1 (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: _col0 (type: int) Map 4 Map Operator Tree: TableScan - alias: c + alias: b Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: key is not null (type: boolean) + predicate: value is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: int) - outputColumnNames: _col0 + expressions: key (type: int), value (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: int) + key expressions: _col1 (type: string) sort order: + - Map-reduce partition columns: _col0 (type: int) + Map-reduce partition columns: _col1 (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int) Map 5 Map Operator Tree: TableScan - alias: b + alias: c Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: value is not null (type: boolean) + predicate: key is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 + expressions: key (type: int) + outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col1 (type: string) + key expressions: _col0 (type: int) sort order: + - Map-reduce partition columns: _col1 (type: string) + Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int) Reducer 2 Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1 + 0 _col1 (type: string) + 1 _col1 (type: string) + outputColumnNames: _col0, _col2 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col1 (type: string) + key expressions: _col0 (type: int) sort order: + - Map-reduce partition columns: _col1 (type: string) + Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int) + value expressions: _col2 (type: int) Reducer 3 Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col1 (type: string) - 1 _col1 (type: string) - outputColumnNames: _col0, _col3 + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0, _col2 Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: int), _col3 (type: int) + expressions: _col0 (type: int), _col2 (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE File Output Operator diff --git a/ql/src/test/results/clientpositive/spark/join32_lessSize.q.out b/ql/src/test/results/clientpositive/spark/join32_lessSize.q.out index d3e648f..ba60639 100644 --- a/ql/src/test/results/clientpositive/spark/join32_lessSize.q.out +++ b/ql/src/test/results/clientpositive/spark/join32_lessSize.q.out @@ -478,26 +478,25 @@ JOIN src y ON (x.key = y.key) JOIN src1 z ON (x.key = z.key) POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-4 is a root stage - Stage-3 depends on stages: Stage-4 + Stage-3 is a root stage Stage-1 depends on stages: Stage-3 Stage-0 depends on stages: Stage-1 Stage-2 depends on stages: Stage-0 STAGE PLANS: - Stage: Stage-4 + Stage: Stage-3 Spark #### A masked pattern was here #### Vertices: - Map 2 + Map 1 Map Operator Tree: TableScan - alias: z + alias: x Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false - predicate: key is not null (type: boolean) + predicate: (key is not null and value is not null) (type: boolean) Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) @@ -507,7 +506,8 @@ STAGE PLANS: keys: 0 _col0 (type: string) 1 _col0 (type: string) - Position of Big Table: 0 + 2 _col0 (type: string) + Position of Big Table: 2 Local Work: Map Reduce Local Work Path -> Alias: @@ -560,42 +560,27 @@ STAGE PLANS: name: default.src1 name: default.src1 Truncated Path -> Alias: - /src1 [$hdt$_3:z] - - Stage: Stage-3 - Spark -#### A masked pattern was here #### - Vertices: - Map 1 + /src1 [$hdt$_2:x] + Map 2 Map Operator Tree: TableScan - alias: x + alias: z Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false - predicate: (key is not null and value is not null) (type: boolean) + predicate: key is not null (type: boolean) Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 + Spark HashTable Sink Operator keys: 0 _col0 (type: string) 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col3 - input vertices: - 1 Map 2 - Position of Big Table: 0 - Statistics: Num rows: 27 Data size: 210 Basic stats: COMPLETE Column stats: NONE - Spark HashTable Sink Operator - keys: - 0 _col1 (type: string) - 1 _col0 (type: string) - Position of Big Table: 1 + 2 _col0 (type: string) + Position of Big Table: 2 Local Work: Map Reduce Local Work Path -> Alias: @@ -648,24 +633,24 @@ STAGE PLANS: name: default.src1 name: default.src1 Truncated Path -> Alias: - /src1 [$hdt$_2:x] + /src1 [$hdt$_3:z] Map 4 Map Operator Tree: TableScan - alias: y + alias: w Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false - predicate: key is not null (type: boolean) + predicate: value is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + expressions: value (type: string) + outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Spark HashTable Sink Operator keys: - 0 _col0 (type: string) + 0 _col1 (type: string) 1 _col0 (type: string) Position of Big Table: 0 Local Work: @@ -720,7 +705,7 @@ STAGE PLANS: name: default.src name: default.src Truncated Path -> Alias: - /src [$hdt$_0:y] + /src [$hdt$_0:w] Stage: Stage-1 Spark @@ -729,49 +714,52 @@ STAGE PLANS: Map 3 Map Operator Tree: TableScan - alias: w + alias: y Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false - predicate: value is not null (type: boolean) + predicate: key is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: value (type: string) - outputColumnNames: _col0 + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 + Inner Join 0 to 2 keys: - 0 _col1 (type: string) + 0 _col0 (type: string) 1 _col0 (type: string) - outputColumnNames: _col0, _col3 + 2 _col0 (type: string) + outputColumnNames: _col0, _col1, _col3, _col5 input vertices: 0 Map 1 - Position of Big Table: 1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + 1 Map 2 + Position of Big Table: 2 + Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) + 0 _col1 (type: string) 1 _col0 (type: string) - outputColumnNames: _col0, _col3, _col6 + outputColumnNames: _col0, _col3, _col5 input vertices: 1 Map 4 Position of Big Table: 0 - Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1210 Data size: 12854 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col3 (type: string), _col6 (type: string) + expressions: _col0 (type: string), _col3 (type: string), _col5 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1210 Data size: 12854 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1210 Data size: 12854 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -850,7 +838,7 @@ STAGE PLANS: name: default.src name: default.src Truncated Path -> Alias: - /src [$hdt$_1:w] + /src [$hdt$_1:y] Stage: Stage-0 Move Operator diff --git a/ql/src/test/results/clientpositive/spark/mapjoin_mapjoin.q.out b/ql/src/test/results/clientpositive/spark/mapjoin_mapjoin.q.out index 618c7e0..98a3446 100644 --- a/ql/src/test/results/clientpositive/spark/mapjoin_mapjoin.q.out +++ b/ql/src/test/results/clientpositive/spark/mapjoin_mapjoin.q.out @@ -552,18 +552,18 @@ STAGE PLANS: Map 5 Map Operator Tree: TableScan - alias: src1 + alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: key is not null (type: boolean) + predicate: value is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) + expressions: value (type: string) outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Spark HashTable Sink Operator keys: - 0 _col0 (type: string) + 0 _col1 (type: string) 1 _col0 (type: string) Local Work: Map Reduce Local Work @@ -588,21 +588,21 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col1 (type: string) + key expressions: _col0 (type: string) sort order: + - Map-reduce partition columns: _col1 (type: string) + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col2 (type: string) + value expressions: _col1 (type: string), _col2 (type: string) Map 4 Map Operator Tree: TableScan - alias: src + alias: src1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: value is not null (type: boolean) + predicate: key is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: value (type: string) + expressions: key (type: string) outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator @@ -618,15 +618,15 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col1 (type: string) + 0 _col0 (type: string) 1 _col0 (type: string) - outputColumnNames: _col0, _col2 + outputColumnNames: _col1, _col2 Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) + 0 _col1 (type: string) 1 _col0 (type: string) outputColumnNames: _col2 input vertices: diff --git a/ql/src/test/results/clientpositive/spark/spark_explainuser_1.q.out b/ql/src/test/results/clientpositive/spark/spark_explainuser_1.q.out index 257d316..5417a24 100644 --- a/ql/src/test/results/clientpositive/spark/spark_explainuser_1.q.out +++ b/ql/src/test/results/clientpositive/spark/spark_explainuser_1.q.out @@ -1693,9 +1693,9 @@ Stage-0 Stage-1 Reducer 2 File Output Operator [FS_19] - Select Operator [SEL_18] (rows=366 width=178) + Select Operator [SEL_18] (rows=365 width=178) Output:["_col0","_col1"] - Filter Operator [FIL_17] (rows=366 width=179) + Filter Operator [FIL_17] (rows=365 width=179) predicate:_col3 is null Join Operator [JOIN_16] (rows=500 width=179) Output:["_col0","_col1","_col3"],condition map:[{"":"{\"type\":\"Left Outer\",\"left\":0,\"right\":1}"}],keys:{"0":"_col1","1":"_col0"} @@ -1758,9 +1758,9 @@ Stage-0 Stage-1 Reducer 3 File Output Operator [FS_18] - Select Operator [SEL_17] (rows=183 width=178) + Select Operator [SEL_17] (rows=185 width=178) Output:["_col0","_col1"] - Filter Operator [FIL_16] (rows=183 width=179) + Filter Operator [FIL_16] (rows=185 width=179) predicate:_col4 is null Join Operator [JOIN_15] (rows=250 width=179) Output:["_col0","_col1","_col4"],condition map:[{"":"{\"type\":\"Left Outer\",\"left\":0,\"right\":1}"}],keys:{"0":"_col0, _col1","1":"_col0, _col1"} @@ -1834,7 +1834,7 @@ Stage-0 Stage-1 Reducer 2 File Output Operator [FS_12] - Join Operator [JOIN_10] (rows=133 width=178) + Join Operator [JOIN_10] (rows=131 width=178) Output:["_col0","_col1"],condition map:[{"":"{\"type\":\"Left Semi\",\"left\":0,\"right\":1}"}],keys:{"0":"_col0, _col1","1":"_col0, _col1"} <-Map 1 [PARTITION-LEVEL SORT] PARTITION-LEVEL SORT [RS_8] @@ -1886,7 +1886,7 @@ Stage-0 Stage-1 Reducer 2 File Output Operator [FS_12] - Join Operator [JOIN_10] (rows=133 width=178) + Join Operator [JOIN_10] (rows=131 width=178) Output:["_col0","_col1"],condition map:[{"":"{\"type\":\"Left Semi\",\"left\":0,\"right\":1}"}],keys:{"0":"_col0, _col1","1":"_col0, _col1"} <-Map 1 [PARTITION-LEVEL SORT] PARTITION-LEVEL SORT [RS_8] @@ -1928,7 +1928,7 @@ Stage-0 Stage-1 Reducer 2 File Output Operator [FS_12] - Join Operator [JOIN_10] (rows=133 width=178) + Join Operator [JOIN_10] (rows=131 width=178) Output:["_col0","_col1"],condition map:[{"":"{\"type\":\"Left Semi\",\"left\":0,\"right\":1}"}],keys:{"0":"_col0","1":"_col0"} <-Map 1 [PARTITION-LEVEL SORT] PARTITION-LEVEL SORT [RS_8] @@ -2049,16 +2049,16 @@ Stage-0 <-Reducer 3 [PARTITION-LEVEL SORT] PARTITION-LEVEL SORT [RS_27] PartitionCols:_col2 - Filter Operator [FIL_15] (rows=66 width=186) + Filter Operator [FIL_15] (rows=65 width=186) predicate:_col2 is not null - Group By Operator [GBY_14] (rows=66 width=186) + Group By Operator [GBY_14] (rows=65 width=186) Output:["_col0","_col1","_col2"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1 <-Reducer 2 [GROUP] GROUP [RS_13] PartitionCols:_col0, _col1 - Group By Operator [GBY_12] (rows=66 width=186) + Group By Operator [GBY_12] (rows=65 width=186) Output:["_col0","_col1","_col2"],aggregations:["count()"],keys:_col0, _col1 - Join Operator [JOIN_10] (rows=133 width=178) + Join Operator [JOIN_10] (rows=131 width=178) Output:["_col0","_col1"],condition map:[{"":"{\"type\":\"Left Semi\",\"left\":0,\"right\":1}"}],keys:{"0":"_col0","1":"_col0"} <-Map 1 [PARTITION-LEVEL SORT] PARTITION-LEVEL SORT [RS_8] @@ -2658,7 +2658,7 @@ Stage-0 PartitionCols:_col0 Group By Operator [GBY_10] (rows=16 width=94) Output:["_col0","_col1"],aggregations:["count()"],keys:_col0 - Join Operator [JOIN_8] (rows=40 width=86) + Join Operator [JOIN_8] (rows=39 width=86) Output:["_col0"],condition map:[{"":"{\"type\":\"Inner\",\"left\":0,\"right\":1}"}],keys:{"0":"_col0","1":"_col0"} <-Map 1 [PARTITION-LEVEL SORT] PARTITION-LEVEL SORT [RS_6] @@ -2719,7 +2719,7 @@ Stage-0 PartitionCols:_col0 Group By Operator [GBY_10] (rows=16 width=94) Output:["_col0","_col1"],aggregations:["count()"],keys:_col0 - Join Operator [JOIN_8] (rows=40 width=86) + Join Operator [JOIN_8] (rows=39 width=86) Output:["_col0"],condition map:[{"":"{\"type\":\"Inner\",\"left\":0,\"right\":1}"}],keys:{"0":"_col0","1":"_col0"} <-Map 1 [PARTITION-LEVEL SORT] PARTITION-LEVEL SORT [RS_6] @@ -2779,7 +2779,7 @@ Stage-0 PartitionCols:_col0 Group By Operator [GBY_10] (rows=16 width=94) Output:["_col0","_col1"],aggregations:["count()"],keys:_col0 - Map Join Operator [MAPJOIN_22] (rows=40 width=86) + Map Join Operator [MAPJOIN_22] (rows=39 width=86) Conds:SEL_5._col0=SEL_5._col0(Inner),Output:["_col0"] <-Select Operator [SEL_5] (rows=500 width=87) Output:["_col0"] @@ -2831,16 +2831,16 @@ Stage-0 GROUP [RS_18] Group By Operator [GBY_17] (rows=1 width=16) Output:["_col0","_col1"],aggregations:["sum(_col0)","sum(_col1)"] - Select Operator [SEL_15] (rows=10 width=94) + Select Operator [SEL_15] (rows=9 width=94) Output:["_col0","_col1"] - Group By Operator [GBY_14] (rows=10 width=94) + Group By Operator [GBY_14] (rows=9 width=94) Output:["_col0","_col1"],aggregations:["count(VALUE._col0)"],keys:KEY._col0 <-Reducer 2 [GROUP] GROUP [RS_13] PartitionCols:_col0 - Group By Operator [GBY_12] (rows=10 width=94) + Group By Operator [GBY_12] (rows=9 width=94) Output:["_col0","_col1"],aggregations:["count()"],keys:_col0 - Join Operator [JOIN_10] (rows=20 width=86) + Join Operator [JOIN_10] (rows=19 width=86) Output:["_col0"],condition map:[{"":"{\"type\":\"Left Semi\",\"left\":0,\"right\":1}"}],keys:{"0":"_col0","1":"_col0"} <-Map 1 [PARTITION-LEVEL SORT] PARTITION-LEVEL SORT [RS_8] @@ -5237,9 +5237,9 @@ Stage-2 Reducer 2 File Output Operator [FS_11] table:{"name:":"default.dest_j1"} - Select Operator [SEL_9] (rows=809 width=95) + Select Operator [SEL_9] (rows=791 width=95) Output:["_col0","_col1"] - Join Operator [JOIN_8] (rows=809 width=178) + Join Operator [JOIN_8] (rows=791 width=178) Output:["_col0","_col2"],condition map:[{"":"{\"type\":\"Inner\",\"left\":0,\"right\":1}"}],keys:{"0":"_col0","1":"_col0"} <-Map 1 [PARTITION-LEVEL SORT] PARTITION-LEVEL SORT [RS_6] @@ -5263,7 +5263,7 @@ Stage-2 Map 4 File Output Operator [FS_11] table:{"name:":"default.dest_j1"} - Select Operator [SEL_9] (rows=809 width=95) + Select Operator [SEL_9] (rows=791 width=95) Output:["_col0","_col1"] Map Join Operator [MAPJOIN_16] Conds:TS_14.reducesinkkey0=TS_14.reducesinkkey0(Inner),Output:["_col0","_col2"] @@ -5518,7 +5518,7 @@ Stage-0 Stage-1 Reducer 2 File Output Operator [FS_10] - Join Operator [JOIN_8] (rows=809 width=356) + Join Operator [JOIN_8] (rows=791 width=356) Output:["_col0","_col1","_col2","_col3"],condition map:[{"":"{\"type\":\"Inner\",\"left\":0,\"right\":1}"}],keys:{"0":"_col0","1":"_col0"} <-Map 1 [PARTITION-LEVEL SORT] PARTITION-LEVEL SORT [RS_6] diff --git a/ql/src/test/results/clientpositive/tez/explainanalyze_1.q.out b/ql/src/test/results/clientpositive/tez/explainanalyze_1.q.out index 8e735f9..61c28b5 100644 --- a/ql/src/test/results/clientpositive/tez/explainanalyze_1.q.out +++ b/ql/src/test/results/clientpositive/tez/explainanalyze_1.q.out @@ -251,7 +251,7 @@ Stage-0 Stage-1 Reducer 2 File Output Operator [FS_5] - Group By Operator [GBY_3] (rows=309/309 width=95) + Group By Operator [GBY_3] (rows=316/309 width=95) Output:["_col0","_col1"],aggregations:["count(KEY._col0)"],keys:KEY._col0 <-Map 1 [SIMPLE_EDGE] SHUFFLE [RS_2] @@ -298,7 +298,7 @@ Stage-0 Output:["_col0"],aggregations:["count()"] <-Reducer 2 [CUSTOM_SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_10] - Merge Join Operator [MERGEJOIN_18] (rows=267/0 width=8) + Merge Join Operator [MERGEJOIN_18] (rows=262/0 width=8) Conds:RS_6._col0=RS_7._col0(Inner) <-Map 1 [SIMPLE_EDGE] SHUFFLE [RS_6] @@ -347,7 +347,7 @@ Stage-0 Output:["_col0"],aggregations:["count()"] <-Reducer 2 [CUSTOM_SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_10] - Merge Join Operator [MERGEJOIN_18] (rows=267/1019 width=8) + Merge Join Operator [MERGEJOIN_18] (rows=262/1019 width=8) Conds:RS_6._col0=RS_7._col0(Inner) <-Map 1 [SIMPLE_EDGE] SHUFFLE [RS_6] @@ -451,9 +451,9 @@ Stage-0 Stage-1 Reducer 2 File Output Operator [FS_10] - Select Operator [SEL_9] (rows=809/1028 width=178) + Select Operator [SEL_9] (rows=791/1028 width=178) Output:["_col0","_col1"] - Merge Join Operator [MERGEJOIN_15] (rows=809/1028 width=178) + Merge Join Operator [MERGEJOIN_15] (rows=791/1028 width=178) Conds:RS_6._col0=RS_7._col0(Inner),Output:["_col0","_col2"] <-Map 1 [SIMPLE_EDGE] SHUFFLE [RS_6] @@ -513,9 +513,9 @@ Stage-0 Stage-1 Reducer 2 File Output Operator [FS_9] - Transform Operator [SCR_8] (rows=809/1028 width=178) + Transform Operator [SCR_8] (rows=791/1028 width=178) command:cat - Merge Join Operator [MERGEJOIN_14] (rows=809/1028 width=178) + Merge Join Operator [MERGEJOIN_14] (rows=791/1028 width=178) Conds:RS_3.key=RS_5.key(Inner),Output:["_col0","_col1"] <-Map 1 [SIMPLE_EDGE] SHUFFLE [RS_3] diff --git a/ql/src/test/results/clientpositive/tez/explainanalyze_4.q.out b/ql/src/test/results/clientpositive/tez/explainanalyze_4.q.out index 9c678ac..1e02610 100644 --- a/ql/src/test/results/clientpositive/tez/explainanalyze_4.q.out +++ b/ql/src/test/results/clientpositive/tez/explainanalyze_4.q.out @@ -44,11 +44,11 @@ Stage-0 Stage-1 Reducer 3 File Output Operator [FS_12] - Select Operator [SEL_11] (rows=2076/10 width=553) + Select Operator [SEL_11] (rows=2048/10 width=552) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col19","_col20","_col21","_col22","_col23"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_10] - Merge Join Operator [MERGEJOIN_17] (rows=2076/10 width=553) + Merge Join Operator [MERGEJOIN_17] (rows=2048/10 width=552) Conds:RS_6._col2=RS_7._col2(Inner),Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col19","_col20","_col21","_col22","_col23"] <-Map 1 [SIMPLE_EDGE] SHUFFLE [RS_6] @@ -143,7 +143,7 @@ Stage-0 Output:["_col0"],aggregations:["count()"] <-Reducer 2 [CUSTOM_SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_10] - Merge Join Operator [MERGEJOIN_18] (rows=2076/10 width=8) + Merge Join Operator [MERGEJOIN_18] (rows=2048/10 width=8) Conds:RS_6._col0=RS_7._col0(Inner) <-Map 1 [SIMPLE_EDGE] SHUFFLE [RS_6] @@ -232,16 +232,16 @@ Stage-0 Stage-1 Reducer 4 File Output Operator [FS_15] - Select Operator [SEL_14] (rows=623/5 width=11) + Select Operator [SEL_14] (rows=631/5 width=11) Output:["_col0","_col1"] <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_13] - Group By Operator [GBY_11] (rows=623/5 width=11) + Group By Operator [GBY_11] (rows=631/5 width=11) Output:["_col0","_col1"],aggregations:["count()"],keys:KEY._col0 <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_10] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_20] (rows=2076/10 width=3) + Merge Join Operator [MERGEJOIN_20] (rows=2048/10 width=3) Conds:RS_6._col1=RS_7._col0(Inner),Output:["_col0"] <-Map 1 [SIMPLE_EDGE] SHUFFLE [RS_6] diff --git a/ql/src/test/results/clientpositive/tez/explainanalyze_5.q.out b/ql/src/test/results/clientpositive/tez/explainanalyze_5.q.out index 6b0f531..c29c3e3 100644 --- a/ql/src/test/results/clientpositive/tez/explainanalyze_5.q.out +++ b/ql/src/test/results/clientpositive/tez/explainanalyze_5.q.out @@ -114,9 +114,9 @@ Stage-3 <-Reducer 4 [CUSTOM_SIMPLE_EDGE] File Output Operator [FS_19] table:{"name:":"default.src_multi2"} - Select Operator [SEL_18] (rows=849/508 width=178) + Select Operator [SEL_18] (rows=830/508 width=178) Output:["_col0","_col1"] - Merge Join Operator [MERGEJOIN_26] (rows=849/508 width=178) + Merge Join Operator [MERGEJOIN_26] (rows=830/508 width=178) Conds:RS_15._col0=RS_16._col0(Inner),Output:["_col0","_col3"] <-Map 7 [SIMPLE_EDGE] SHUFFLE [RS_16] @@ -154,7 +154,7 @@ Stage-3 TableScan [TS_3] (rows=25/25 width=175) Output:["key","value"] PARTITION_ONLY_SHUFFLE [RS_2] - Select Operator [SEL_1] (rows=849/508 width=178) + Select Operator [SEL_1] (rows=830/508 width=178) Output:["key","value"] Please refer to the previous Select Operator [SEL_18] diff --git a/ql/src/test/results/clientpositive/tez/hybridgrace_hashjoin_1.q.out b/ql/src/test/results/clientpositive/tez/hybridgrace_hashjoin_1.q.out index a709920..535c124 100644 --- a/ql/src/test/results/clientpositive/tez/hybridgrace_hashjoin_1.q.out +++ b/ql/src/test/results/clientpositive/tez/hybridgrace_hashjoin_1.q.out @@ -56,7 +56,7 @@ STAGE PLANS: 1 _col0 (type: int) input vertices: 1 Map 3 - Statistics: Num rows: 25044 Data size: 200352 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 24737 Data size: 197896 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash @@ -172,7 +172,7 @@ STAGE PLANS: 1 _col0 (type: int) input vertices: 1 Map 3 - Statistics: Num rows: 25044 Data size: 200352 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 24737 Data size: 197896 Basic stats: COMPLETE Column stats: COMPLETE HybridGraceHashJoin: true Group By Operator aggregations: count() @@ -287,7 +287,7 @@ STAGE PLANS: 1 _col0 (type: int) input vertices: 1 Map 3 - Statistics: Num rows: 18694 Data size: 149552 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 18464 Data size: 147712 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash @@ -399,7 +399,7 @@ STAGE PLANS: 1 _col0 (type: int) input vertices: 1 Map 3 - Statistics: Num rows: 18694 Data size: 149552 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 18464 Data size: 147712 Basic stats: COMPLETE Column stats: COMPLETE HybridGraceHashJoin: true Group By Operator aggregations: count() @@ -509,7 +509,7 @@ STAGE PLANS: 1 _col0 (type: int) input vertices: 1 Map 3 - Statistics: Num rows: 25044 Data size: 200352 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 24737 Data size: 197896 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash @@ -615,7 +615,7 @@ STAGE PLANS: 1 _col0 (type: int) input vertices: 1 Map 3 - Statistics: Num rows: 25044 Data size: 200352 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 24737 Data size: 197896 Basic stats: COMPLETE Column stats: COMPLETE HybridGraceHashJoin: true Group By Operator aggregations: count() diff --git a/ql/src/test/results/clientpositive/tez/hybridgrace_hashjoin_2.q.out b/ql/src/test/results/clientpositive/tez/hybridgrace_hashjoin_2.q.out index 0b71be9..2a12203 100644 --- a/ql/src/test/results/clientpositive/tez/hybridgrace_hashjoin_2.q.out +++ b/ql/src/test/results/clientpositive/tez/hybridgrace_hashjoin_2.q.out @@ -71,7 +71,7 @@ STAGE PLANS: input vertices: 0 Map 1 2 Map 4 - Statistics: Num rows: 261 Data size: 2088 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 250 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash @@ -195,7 +195,7 @@ STAGE PLANS: input vertices: 0 Map 1 2 Map 4 - Statistics: Num rows: 261 Data size: 2088 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 250 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE HybridGraceHashJoin: true Group By Operator aggregations: count() @@ -334,7 +334,7 @@ STAGE PLANS: 0 Map 1 2 Map 4 3 Map 5 - Statistics: Num rows: 1694 Data size: 13552 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1584 Data size: 12672 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash @@ -478,7 +478,7 @@ STAGE PLANS: 0 Map 1 2 Map 4 3 Map 5 - Statistics: Num rows: 1694 Data size: 13552 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1584 Data size: 12672 Basic stats: COMPLETE Column stats: COMPLETE HybridGraceHashJoin: true Group By Operator aggregations: count() @@ -651,7 +651,7 @@ STAGE PLANS: input vertices: 0 Map 1 2 Map 6 - Statistics: Num rows: 261 Data size: 2088 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 250 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash @@ -706,7 +706,7 @@ STAGE PLANS: input vertices: 0 Map 7 2 Map 10 - Statistics: Num rows: 261 Data size: 2088 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 265 Data size: 2120 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash @@ -886,7 +886,7 @@ STAGE PLANS: input vertices: 0 Map 1 2 Map 6 - Statistics: Num rows: 261 Data size: 2088 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 250 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE HybridGraceHashJoin: true Group By Operator aggregations: count() @@ -942,7 +942,7 @@ STAGE PLANS: input vertices: 0 Map 7 2 Map 10 - Statistics: Num rows: 261 Data size: 2088 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 265 Data size: 2120 Basic stats: COMPLETE Column stats: COMPLETE HybridGraceHashJoin: true Group By Operator aggregations: count() @@ -1120,7 +1120,7 @@ STAGE PLANS: input vertices: 0 Map 1 2 Map 4 - Statistics: Num rows: 20 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 19 Data size: 1691 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -1132,7 +1132,7 @@ STAGE PLANS: input vertices: 1 Map 5 2 Map 6 - Statistics: Num rows: 204 Data size: 1632 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 196 Data size: 1568 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash @@ -1304,7 +1304,7 @@ STAGE PLANS: input vertices: 0 Map 1 2 Map 4 - Statistics: Num rows: 20 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 19 Data size: 1691 Basic stats: COMPLETE Column stats: COMPLETE HybridGraceHashJoin: true Map Join Operator condition map: @@ -1317,7 +1317,7 @@ STAGE PLANS: input vertices: 1 Map 5 2 Map 6 - Statistics: Num rows: 204 Data size: 1632 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 196 Data size: 1568 Basic stats: COMPLETE Column stats: COMPLETE HybridGraceHashJoin: true Group By Operator aggregations: count() diff --git a/ql/src/test/results/clientpositive/tez/vectorization_limit.q.out b/ql/src/test/results/clientpositive/tez/vectorization_limit.q.out index 99544bb..3cb57a3 100644 --- a/ql/src/test/results/clientpositive/tez/vectorization_limit.q.out +++ b/ql/src/test/results/clientpositive/tez/vectorization_limit.q.out @@ -790,7 +790,7 @@ STAGE PLANS: keys: cdouble (type: double) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 4159 Data size: 58120 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4127 Data size: 57672 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: double) sort order: + @@ -801,7 +801,7 @@ STAGE PLANS: native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true valueColumnNums: [1] - Statistics: Num rows: 4159 Data size: 58120 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4127 Data size: 57672 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Map Vectorization: @@ -848,7 +848,7 @@ STAGE PLANS: keys: KEY._col0 (type: double) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 4159 Data size: 58120 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4127 Data size: 57672 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: bigint), _col0 (type: double) sort order: ++ @@ -858,7 +858,7 @@ STAGE PLANS: native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true valueColumnNums: [] - Statistics: Num rows: 4159 Data size: 58120 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4127 Data size: 57672 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.3 Reducer 3 Execution mode: vectorized @@ -883,7 +883,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [1, 0] - Statistics: Num rows: 4159 Data size: 58120 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4127 Data size: 57672 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 20 Limit Vectorization: diff --git a/standalone-metastore/src/main/java/org/apache/hadoop/hive/common/ndv/NumDistinctValueEstimatorFactory.java b/standalone-metastore/src/main/java/org/apache/hadoop/hive/common/ndv/NumDistinctValueEstimatorFactory.java index 4e4dfb7..b630fa3 100644 --- a/standalone-metastore/src/main/java/org/apache/hadoop/hive/common/ndv/NumDistinctValueEstimatorFactory.java +++ b/standalone-metastore/src/main/java/org/apache/hadoop/hive/common/ndv/NumDistinctValueEstimatorFactory.java @@ -25,6 +25,7 @@ import org.apache.hadoop.hive.common.ndv.fm.FMSketch; import org.apache.hadoop.hive.common.ndv.fm.FMSketchUtils; import org.apache.hadoop.hive.common.ndv.hll.HyperLogLog; +import org.apache.hadoop.hive.common.ndv.hll.HyperLogLogUtils; public class NumDistinctValueEstimatorFactory { @@ -44,7 +45,7 @@ public static NumDistinctValueEstimator getNumDistinctValueEstimator(byte[] buf) if (isFMSketch(buf)) { return FMSketchUtils.deserializeFM(buf); } else { - return HyperLogLog.builder().build().deserialize(buf); + return HyperLogLogUtils.deserializeHLL(buf); } } catch (IOException e) { throw new RuntimeException(e); @@ -56,7 +57,7 @@ public static NumDistinctValueEstimator getEmptyNumDistinctValueEstimator( if (n instanceof FMSketch) { return new FMSketch(((FMSketch) n).getNumBitVectors()); } else { - return HyperLogLog.builder().build(); + return HyperLogLog.builder().setSizeOptimized().build(); } } @@ -65,7 +66,7 @@ public static NumDistinctValueEstimator getEmptyNumDistinctValueEstimator(String if ("fm".equals(func.toLowerCase())) { return new FMSketch(numBitVectors); } else if ("hll".equals(func.toLowerCase())) { - return HyperLogLog.builder().build(); + return HyperLogLog.builder().setSizeOptimized().build(); } else { throw new RuntimeException("Can not recognize " + func); } diff --git a/standalone-metastore/src/main/java/org/apache/hadoop/hive/common/ndv/hll/HLLDenseRegister.java b/standalone-metastore/src/main/java/org/apache/hadoop/hive/common/ndv/hll/HLLDenseRegister.java index 12897fc..422bfbe 100644 --- a/standalone-metastore/src/main/java/org/apache/hadoop/hive/common/ndv/hll/HLLDenseRegister.java +++ b/standalone-metastore/src/main/java/org/apache/hadoop/hive/common/ndv/hll/HLLDenseRegister.java @@ -62,6 +62,31 @@ public boolean add(long hashcode) { return set(registerIdx, (byte) lr); } + // this is a lossy invert of the function above, which produces a hashcode + // which collides with the current winner of the register (we lose all higher + // bits, but we get all bits useful for lesser p-bit options) + + // +-------------|-------------+ + // |xxxx100000000|1000000000000| (lr=9 + idx=1024) + // +-------------|-------------+ + // \ + // +---------------|-----------+ + // |xxxx10000000010|00000000000| (lr=2 + idx=0) + // +---------------|-----------+ + + // This shows the relevant bits of the original hash value + // and how the conversion is moving bits from the index value + // over to the leading zero computation + + public void extractLowBitsTo(HLLRegister dest) { + for (int idx = 0; idx < register.length; idx++) { + byte lr = register[idx]; // this can be a max of 65, never > 127 + if (lr != 0) { + dest.add((long) ((1 << (p + lr - 1)) | idx)); + } + } + } + public boolean set(int idx, byte value) { boolean updated = false; if (idx < register.length && value > register[idx]) { diff --git a/standalone-metastore/src/main/java/org/apache/hadoop/hive/common/ndv/hll/HLLSparseRegister.java b/standalone-metastore/src/main/java/org/apache/hadoop/hive/common/ndv/hll/HLLSparseRegister.java index 82085dd..deaca9d 100644 --- a/standalone-metastore/src/main/java/org/apache/hadoop/hive/common/ndv/hll/HLLSparseRegister.java +++ b/standalone-metastore/src/main/java/org/apache/hadoop/hive/common/ndv/hll/HLLSparseRegister.java @@ -19,6 +19,7 @@ package org.apache.hadoop.hive.common.ndv.hll; import java.util.Map; +import java.util.Map.Entry; import java.util.TreeMap; public class HLLSparseRegister implements HLLRegister { @@ -199,6 +200,18 @@ public boolean set(int key, byte value) { return sparseMap; } + // this is effectively the same as the dense register impl. + public void extractLowBitsTo(HLLRegister dest) { + for (Entry entry : sparseMap.entrySet()) { + int idx = entry.getKey(); + byte lr = entry.getValue(); // this can be a max of 65, never > 127 + if (lr != 0) { + // should be a no-op for sparse + dest.add((long) ((1 << (p + lr - 1)) | idx)); + } + } + } + public int getP() { return p; } diff --git a/standalone-metastore/src/main/java/org/apache/hadoop/hive/common/ndv/hll/HyperLogLog.java b/standalone-metastore/src/main/java/org/apache/hadoop/hive/common/ndv/hll/HyperLogLog.java index 8bdb47b..ec33691 100644 --- a/standalone-metastore/src/main/java/org/apache/hadoop/hive/common/ndv/hll/HyperLogLog.java +++ b/standalone-metastore/src/main/java/org/apache/hadoop/hive/common/ndv/hll/HyperLogLog.java @@ -18,10 +18,8 @@ package org.apache.hadoop.hive.common.ndv.hll; -import java.io.ByteArrayInputStream; import java.io.ByteArrayOutputStream; import java.io.IOException; -import java.io.InputStream; import java.nio.ByteBuffer; import java.nio.charset.Charset; import java.util.Map; @@ -163,6 +161,13 @@ public HyperLogLogBuilder setNumRegisterIndexBits(int b) { return this; } + public HyperLogLogBuilder setSizeOptimized() { + // allowing this to be increased via config breaks the merge impl + // p=10 = ~1kb per vector or smaller + this.numRegisterIndexBits = 10; + return this; + } + public HyperLogLogBuilder setEncoding(EncodingType enc) { this.encoding = enc; return this; @@ -440,12 +445,23 @@ public void setHLLDenseRegister(byte[] reg) { * @throws IllegalArgumentException */ public void merge(HyperLogLog hll) { - if (p != hll.p || chosenHashBits != hll.chosenHashBits) { + if (chosenHashBits != hll.chosenHashBits) { throw new IllegalArgumentException( "HyperLogLog cannot be merged as either p or hashbits are different. Current: " + toString() + " Provided: " + hll.toString()); } + if (p > hll.p) { + throw new IllegalArgumentException( + "HyperLogLog cannot merge a smaller p into a larger one : " + + toString() + " Provided: " + hll.toString()); + } + + if (p != hll.p) { + // invariant: p > hll.p + hll = hll.squash(p); + } + EncodingType otherEncoding = hll.getEncoding(); if (encoding.equals(EncodingType.SPARSE) && otherEncoding.equals(EncodingType.SPARSE)) { @@ -473,7 +489,37 @@ public void merge(HyperLogLog hll) { } /** - * Converts sparse to dense hll register + * Reduces the accuracy of the HLL provided to a smaller size + * @param p0 + * - new p size for the new HyperLogLog (smaller or no change) + * @return reduced (or same) HyperLogLog instance + */ + public HyperLogLog squash(final int p0) { + if (p0 > p) { + throw new IllegalArgumentException( + "HyperLogLog cannot be be squashed to be bigger. Current: " + + toString() + " Provided: " + p0); + } + + if (p0 == p) { + return this; + } + + final HyperLogLog hll = new HyperLogLogBuilder() + .setNumRegisterIndexBits(p0).setEncoding(EncodingType.DENSE) + .enableNoBias(noBias).build(); + final HLLDenseRegister result = hll.denseRegister; + + if (encoding == EncodingType.SPARSE) { + sparseRegister.extractLowBitsTo(result); + } else if (encoding == EncodingType.DENSE) { + denseRegister.extractLowBitsTo(result); + } + return hll; + } + + /** + * Converts sparse to dense hll register. * @param sparseRegister * - sparse register to be converted * @return converted dense register @@ -585,14 +631,7 @@ public void reset() { @Override public NumDistinctValueEstimator deserialize(byte[] buf) { - InputStream is = new ByteArrayInputStream(buf); - try { - HyperLogLog result = HyperLogLogUtils.deserializeHLL(is); - is.close(); - return result; - } catch (IOException e) { - throw new RuntimeException(e); - } + return HyperLogLogUtils.deserializeHLL(buf); } @Override diff --git a/standalone-metastore/src/main/java/org/apache/hadoop/hive/common/ndv/hll/HyperLogLogUtils.java b/standalone-metastore/src/main/java/org/apache/hadoop/hive/common/ndv/hll/HyperLogLogUtils.java index 4e6510b..aeba2e9 100644 --- a/standalone-metastore/src/main/java/org/apache/hadoop/hive/common/ndv/hll/HyperLogLogUtils.java +++ b/standalone-metastore/src/main/java/org/apache/hadoop/hive/common/ndv/hll/HyperLogLogUtils.java @@ -18,6 +18,7 @@ package org.apache.hadoop.hive.common.ndv.hll; +import java.io.ByteArrayInputStream; import java.io.EOFException; import java.io.IOException; import java.io.InputStream; @@ -126,7 +127,7 @@ public static void serializeHLL(OutputStream out, HyperLogLog hll) throws IOExce } /** - * Refer serializeHLL() for format of serialization. This funtions + * Refer serializeHLL() for format of serialization. This function * deserializes the serialized hyperloglogs * @param in * - input stream @@ -198,6 +199,22 @@ public static HyperLogLog deserializeHLL(InputStream in) throws IOException { return result; } + /** + * This function deserializes the serialized hyperloglogs from a byte array. + * @param buf - to deserialize + * @return HyperLogLog + */ + public static HyperLogLog deserializeHLL(final byte[] buf) { + InputStream is = new ByteArrayInputStream(buf); // TODO: use faster non-sync inputstream + try { + HyperLogLog result = deserializeHLL(is); + is.close(); + return result; + } catch (IOException e) { + throw new RuntimeException(e); + } + } + private static void bitpackHLLRegister(OutputStream out, byte[] register, int bitWidth) throws IOException { int bitsLeft = 8; diff --git a/standalone-metastore/src/test/java/org/apache/hadoop/hive/common/ndv/hll/TestHyperLogLog.java b/standalone-metastore/src/test/java/org/apache/hadoop/hive/common/ndv/hll/TestHyperLogLog.java index b0eaad8..56ed407 100644 --- a/standalone-metastore/src/test/java/org/apache/hadoop/hive/common/ndv/hll/TestHyperLogLog.java +++ b/standalone-metastore/src/test/java/org/apache/hadoop/hive/common/ndv/hll/TestHyperLogLog.java @@ -34,14 +34,18 @@ public void testHLLDenseMerge() { HyperLogLog hll3 = HyperLogLog.builder().setEncoding(EncodingType.DENSE).build(); HyperLogLog hll4 = HyperLogLog.builder().setNumRegisterIndexBits(16) .setEncoding(EncodingType.DENSE).build(); + HyperLogLog hll5 = HyperLogLog.builder().setNumRegisterIndexBits(12) + .setEncoding(EncodingType.DENSE).build(); int size = 1000; for (int i = 0; i < size; i++) { hll.addLong(i); hll2.addLong(size + i); hll3.addLong(2 * size + i); + hll4.addLong(3 * size + i); } double threshold = size > 40000 ? longRangeTolerance : shortRangeTolerance; double delta = threshold * size / 100; + double delta4 = threshold * (4*size) / 100; assertEquals((double) size, (double) hll.count(), delta); assertEquals((double) size, (double) hll2.count(), delta); @@ -60,8 +64,13 @@ public void testHLLDenseMerge() { assertEquals((double) 3 * size, (double) hll.count(), delta); assertEquals(EncodingType.DENSE, hll.getEncoding()); - // invalid merge -- register set size doesn't match + // valid merge -- register set size gets bigger (also 4k items hll.merge(hll4); + assertEquals((double) 4 * size, (double) hll.count(), delta4); + assertEquals(EncodingType.DENSE, hll.getEncoding()); + + // invalid merge -- smaller register merge to bigger + hll.merge(hll5); } @Test(expected = IllegalArgumentException.class) @@ -71,14 +80,18 @@ public void testHLLSparseMerge() { HyperLogLog hll3 = HyperLogLog.builder().setEncoding(EncodingType.SPARSE).build(); HyperLogLog hll4 = HyperLogLog.builder().setNumRegisterIndexBits(16) .setEncoding(EncodingType.SPARSE).build(); + HyperLogLog hll5 = HyperLogLog.builder().setNumRegisterIndexBits(12) + .setEncoding(EncodingType.SPARSE).build(); int size = 500; for (int i = 0; i < size; i++) { hll.addLong(i); hll2.addLong(size + i); hll3.addLong(2 * size + i); + hll4.addLong(3 * size + i); } double threshold = size > 40000 ? longRangeTolerance : shortRangeTolerance; double delta = threshold * size / 100; + double delta4 = threshold * (4*size) / 100; assertEquals((double) size, (double) hll.count(), delta); assertEquals((double) size, (double) hll2.count(), delta); @@ -97,8 +110,13 @@ public void testHLLSparseMerge() { assertEquals((double) 3 * size, (double) hll.count(), delta); assertEquals(EncodingType.SPARSE, hll.getEncoding()); - // invalid merge -- register set size doesn't match + // valid merge -- register set size gets bigger & dense automatically hll.merge(hll4); + assertEquals((double) 4 * size, (double) hll.count(), delta4); + assertEquals(EncodingType.DENSE, hll.getEncoding()); + + // invalid merge -- smaller register merge to bigger + hll.merge(hll5); } @Test(expected = IllegalArgumentException.class) @@ -108,11 +126,14 @@ public void testHLLSparseDenseMerge() { HyperLogLog hll3 = HyperLogLog.builder().setEncoding(EncodingType.DENSE).build(); HyperLogLog hll4 = HyperLogLog.builder().setNumRegisterIndexBits(16) .setEncoding(EncodingType.DENSE).build(); + HyperLogLog hll5 = HyperLogLog.builder().setNumRegisterIndexBits(12) + .setEncoding(EncodingType.DENSE).build(); int size = 1000; for (int i = 0; i < size; i++) { hll.addLong(i); hll2.addLong(size + i); hll3.addLong(2 * size + i); + hll4.addLong(3 * size + i); } double threshold = size > 40000 ? longRangeTolerance : shortRangeTolerance; double delta = threshold * size / 100; @@ -134,8 +155,13 @@ public void testHLLSparseDenseMerge() { assertEquals((double) 3 * size, (double) hll.count(), delta); assertEquals(EncodingType.DENSE, hll.getEncoding()); - // invalid merge -- register set size doesn't match - hll.merge(hll4); + // merge should convert hll2 to DENSE + hll2.merge(hll4); + assertEquals((double) 2 * size, (double) hll2.count(), delta); + assertEquals(EncodingType.DENSE, hll2.getEncoding()); + + // invalid merge -- smaller register merge to bigger + hll.merge(hll5); } @Test(expected = IllegalArgumentException.class) @@ -145,11 +171,14 @@ public void testHLLDenseSparseMerge() { HyperLogLog hll3 = HyperLogLog.builder().setEncoding(EncodingType.SPARSE).build(); HyperLogLog hll4 = HyperLogLog.builder().setNumRegisterIndexBits(16) .setEncoding(EncodingType.SPARSE).build(); + HyperLogLog hll5 = HyperLogLog.builder().setNumRegisterIndexBits(12) + .setEncoding(EncodingType.SPARSE).build(); int size = 1000; for (int i = 0; i < size; i++) { hll.addLong(i); hll2.addLong(size + i); hll3.addLong(2 * size + i); + hll4.addLong(3 * size + i); } double threshold = size > 40000 ? longRangeTolerance : shortRangeTolerance; double delta = threshold * size / 100; @@ -171,8 +200,14 @@ public void testHLLDenseSparseMerge() { assertEquals((double) 3 * size, (double) hll.count(), delta); assertEquals(EncodingType.DENSE, hll.getEncoding()); - // invalid merge -- register set size doesn't match - hll.merge(hll4); + // merge should convert hll3 to DENSE + hll3.merge(hll4); + assertEquals((double) 2 * size, (double) hll3.count(), delta); + assertEquals(EncodingType.DENSE, hll3.getEncoding()); + + // invalid merge -- smaller register merge to bigger + hll.merge(hll5); + } @Test(expected = IllegalArgumentException.class) @@ -182,11 +217,14 @@ public void testHLLSparseOverflowMerge() { HyperLogLog hll3 = HyperLogLog.builder().setEncoding(EncodingType.SPARSE).build(); HyperLogLog hll4 = HyperLogLog.builder().setNumRegisterIndexBits(16) .setEncoding(EncodingType.SPARSE).build(); + HyperLogLog hll5 = HyperLogLog.builder().setNumRegisterIndexBits(12) + .setEncoding(EncodingType.SPARSE).build(); int size = 1000; for (int i = 0; i < size; i++) { hll.addLong(i); hll2.addLong(size + i); hll3.addLong(2 * size + i); + hll4.addLong(3 * size + i); } double threshold = size > 40000 ? longRangeTolerance : shortRangeTolerance; double delta = threshold * size / 100; @@ -208,8 +246,13 @@ public void testHLLSparseOverflowMerge() { assertEquals((double) 3 * size, (double) hll.count(), delta); assertEquals(EncodingType.DENSE, hll.getEncoding()); - // invalid merge -- register set size doesn't match - hll.merge(hll4); + // merge should convert hll2 to DENSE + hll2.merge(hll4); + assertEquals((double) 2 * size, (double) hll2.count(), delta); + assertEquals(EncodingType.DENSE, hll2.getEncoding()); + + // invalid merge -- smaller register merge to bigger + hll.merge(hll5); } @Test @@ -224,4 +267,69 @@ public void testHLLSparseMoreRegisterBits() { double delta = threshold * size / 100; assertEquals((double) size, (double) hll.count(), delta); } + + @Test + public void testHLLSquash() { + + int[] sizes = new int[] { 500, 1000, 2300, 4096}; + int minBits = 9; + for (final int size : sizes) { + + HyperLogLog hlls[] = new HyperLogLog[16]; + for (int k = minBits; k < hlls.length; k++) { + final HyperLogLog hll = HyperLogLog.builder() + .setEncoding(EncodingType.DENSE).setNumRegisterIndexBits(k).build(); + for (int i = 0; i < size; i++) { + hll.addLong(i); + } + hlls[k] = hll; + } + + for (int k = minBits; k < hlls.length; k++) { + for (int j = k + 1; j < hlls.length; j++) { + final HyperLogLog large = hlls[j]; + final HyperLogLog small = hlls[k]; + final HyperLogLog mush = large + .squash(small.getNumRegisterIndexBits()); + assertEquals(small.count(), mush.count(), 0); + double delta = Math.ceil(small.getStandardError()*size); + assertEquals((double) size, (double) mush.count(), delta); + } + } + } + } + + @Test + public void testHLLDenseDenseSquash() { + HyperLogLog p14HLL = HyperLogLog.builder().setEncoding(EncodingType.DENSE).setNumRegisterIndexBits(14).build(); + HyperLogLog p10HLL = HyperLogLog.builder().setEncoding(EncodingType.DENSE).setNumRegisterIndexBits(10).build(); + int size = 1_000_000; + for (int i = 0; i < size; i++) { + p14HLL.addLong(i); + } + + for (int i = 0; i < 10_000; i++) { + p10HLL.addLong(i); + } + + p14HLL.squash(p10HLL.getNumRegisterIndexBits()); + assertEquals((double) size, p14HLL.count(), longRangeTolerance * size / 100.0); + } + + @Test + public void testHLLSparseDenseSquash() { + HyperLogLog p14HLL = HyperLogLog.builder().setEncoding(EncodingType.SPARSE).setNumRegisterIndexBits(14).build(); + HyperLogLog p10HLL = HyperLogLog.builder().setEncoding(EncodingType.DENSE).setNumRegisterIndexBits(10).build(); + int size = 2000; + for (int i = 0; i < size; i++) { + p14HLL.addLong(i); + } + + for (int i = 0; i < 10_000; i++) { + p10HLL.addLong(i); + } + + p14HLL.squash(p10HLL.getNumRegisterIndexBits()); + assertEquals((double) size, p14HLL.count(), longRangeTolerance * size / 100.0); + } } diff --git a/standalone-metastore/src/test/java/org/apache/hadoop/hive/common/ndv/hll/TestHyperLogLogMerge.java b/standalone-metastore/src/test/java/org/apache/hadoop/hive/common/ndv/hll/TestHyperLogLogMerge.java new file mode 100644 index 0000000..2007c6f --- /dev/null +++ b/standalone-metastore/src/test/java/org/apache/hadoop/hive/common/ndv/hll/TestHyperLogLogMerge.java @@ -0,0 +1,147 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one + * or more contributor license agreements. See the NOTICE file + * distributed with this work for additional information + * regarding copyright ownership. The ASF licenses this file + * to you under the Apache License, Version 2.0 (the + * "License"); you may not use this file except in compliance + * with the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ +package org.apache.hadoop.hive.common.ndv.hll; + +import static org.junit.Assert.assertEquals; + +import java.util.Arrays; +import java.util.Collection; + +import org.junit.Test; +import org.junit.runner.RunWith; +import org.junit.runners.Parameterized; + +@RunWith(Parameterized.class) +public class TestHyperLogLogMerge { + // 5% tolerance for estimated count + private float longRangeTolerance = 5.0f; + private float shortRangeTolerance = 2.0f; + + int size; + + @Parameterized.Parameters + public static Collection data() { + return Arrays.asList(new Object[][] { + { 1_000 }, { 10_000 }, { 100_000 }, { 1_000_000 }, { 10_000_000 } + // { 100_000_000 }, { 1_000_000_000 } 1B passed but is super slow + }); + } + + public TestHyperLogLogMerge(int size) { + this.size = size; + } + + @Test + public void testHLLMergeDisjoint() { + HyperLogLog hll1 = HyperLogLog.builder().setNumRegisterIndexBits(16).build(); + for (int i = 0; i < size; i++) { + hll1.addLong(i); + } + HyperLogLog hll2 = HyperLogLog.builder().setNumRegisterIndexBits(16).build(); + for (int i = size; i < 2 * size; i++) { + hll2.addLong(i); + } + hll1.merge(hll2); + double threshold = size > 40000 ? longRangeTolerance : shortRangeTolerance; + double delta = threshold * size / 100; + long expected = 2 * size; + long actual = hll1.count(); + assertEquals(expected, actual, delta); + } + + @Test + public void testHLLMerge25PercentOverlap() { + HyperLogLog hll1 = HyperLogLog.builder().setNumRegisterIndexBits(16).build(); + for (int i = 0; i < size; i++) { + hll1.addLong(i); + } + HyperLogLog hll2 = HyperLogLog.builder().setNumRegisterIndexBits(16).build(); + int start = (int) (0.75 * size); + int end = (int) (size * 1.75); + for (int i = start; i < end; i++) { + hll2.addLong(i); + } + hll1.merge(hll2); + double threshold = size > 40000 ? longRangeTolerance : shortRangeTolerance; + double delta = threshold * size / 100; + long expected = (long) (1.75 * size); + long actual = hll1.count(); + assertEquals(expected, actual, delta); + } + + @Test + public void testHLLMerge50PercentOverlap() { + HyperLogLog hll1 = HyperLogLog.builder().setNumRegisterIndexBits(16).build(); + for (int i = 0; i < size; i++) { + hll1.addLong(i); + } + HyperLogLog hll2 = HyperLogLog.builder().setNumRegisterIndexBits(16).build(); + int start = (int) (0.5 * size); + int end = (int) (size * 1.5); + for (int i = start; i < end; i++) { + hll2.addLong(i); + } + hll1.merge(hll2); + double threshold = size > 40000 ? longRangeTolerance : shortRangeTolerance; + double delta = threshold * size / 100; + long expected = (long) (1.5 * size); + long actual = hll1.count(); + assertEquals(expected, actual, delta); + } + + + @Test + public void testHLLMerge75PercentOverlap() { + HyperLogLog hll1 = HyperLogLog.builder().setNumRegisterIndexBits(16).build(); + for (int i = 0; i < size; i++) { + hll1.addLong(i); + } + HyperLogLog hll2 = HyperLogLog.builder().setNumRegisterIndexBits(16).build(); + int start = (int) (0.25 * size); + int end = (int) (size * 1.25); + for (int i = start; i < end; i++) { + hll2.addLong(i); + } + hll1.merge(hll2); + double threshold = size > 40000 ? longRangeTolerance : shortRangeTolerance; + double delta = threshold * size / 100; + long expected = (long) (1.25 * size); + long actual = hll1.count(); + assertEquals(expected, actual, delta); + } + + + @Test + public void testHLLMerge100PercentOverlap() { + HyperLogLog hll1 = HyperLogLog.builder().setNumRegisterIndexBits(16).build(); + for (int i = 0; i < size; i++) { + hll1.addLong(i); + } + HyperLogLog hll2 = HyperLogLog.builder().setNumRegisterIndexBits(16).build(); + for (int i = 0; i < size; i++) { + hll2.addLong(i); + } + hll1.merge(hll2); + double threshold = size > 40000 ? longRangeTolerance : shortRangeTolerance; + double delta = threshold * size / 100; + long expected = size; + long actual = hll1.count(); + assertEquals(expected, actual, delta); + } + +}