You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by px...@apache.org on 2016/01/29 20:06:28 UTC
[26/33] hive git commit: HIVE-12709: further improve user level
explain (Pengcheng Xiong, reviewed by Laljo John Pullokkaran)
http://git-wip-us.apache.org/repos/asf/hive/blob/be9735e1/ql/src/test/results/clientpositive/perf/query32.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/perf/query32.q.out b/ql/src/test/results/clientpositive/perf/query32.q.out
index ecc5834..dc085dd 100644
--- a/ql/src/test/results/clientpositive/perf/query32.q.out
+++ b/ql/src/test/results/clientpositive/perf/query32.q.out
@@ -46,160 +46,87 @@ Reducer 8 <- Map 10 (SIMPLE_EDGE), Map 7 (SIMPLE_EDGE)
Reducer 9 <- Reducer 8 (SIMPLE_EDGE)
Stage-0
- Fetch Operator
- limit:-1
- Stage-1
- Reducer 4
- File Output Operator [FS_37]
- compressed:false
- Statistics:Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE
- table:{"input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat","serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe"}
- Group By Operator [GBY_35]
- | aggregations:["sum(VALUE._col0)"]
- | outputColumnNames:["_col0"]
- | Statistics:Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE
- |<-Reducer 3 [SIMPLE_EDGE]
- Reduce Output Operator [RS_34]
- sort order:
- Statistics:Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE
- value expressions:_col0 (type: decimal(17,2))
- Group By Operator [GBY_33]
- aggregations:["sum(_col1)"]
- outputColumnNames:["_col0"]
- Statistics:Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE
- Select Operator [SEL_32]
- outputColumnNames:["_col1"]
- Statistics:Num rows: 169400 Data size: 243305505 Basic stats: COMPLETE Column stats: NONE
- Filter Operator [FIL_31]
- predicate:(_col1 > CAST( _col5 AS decimal(20,15))) (type: boolean)
- Statistics:Num rows: 169400 Data size: 243305505 Basic stats: COMPLETE Column stats: NONE
- Merge Join Operator [MERGEJOIN_59]
- | condition map:[{"":"Inner Join 0 to 1"},{"":"Inner Join 1 to 2"}]
- | keys:{"0":"_col0 (type: int)","1":"_col0 (type: int)","2":"_col0 (type: int)"}
- | outputColumnNames:["_col1","_col5"]
- | Statistics:Num rows: 508200 Data size: 729916517 Basic stats: COMPLETE Column stats: NONE
- |<-Map 6 [SIMPLE_EDGE]
- | Reduce Output Operator [RS_28]
- | key expressions:_col0 (type: int)
- | Map-reduce partition columns:_col0 (type: int)
- | sort order:+
- | Statistics:Num rows: 231000 Data size: 331780228 Basic stats: COMPLETE Column stats: NONE
- | Select Operator [SEL_12]
- | outputColumnNames:["_col0"]
- | Statistics:Num rows: 231000 Data size: 331780228 Basic stats: COMPLETE Column stats: NONE
- | Filter Operator [FIL_54]
- | predicate:(i_item_sk is not null and (i_manufact_id = 436)) (type: boolean)
- | Statistics:Num rows: 231000 Data size: 331780228 Basic stats: COMPLETE Column stats: NONE
- | TableScan [TS_10]
- | alias:i
- | Statistics:Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE
- |<-Reducer 2 [SIMPLE_EDGE]
- | Reduce Output Operator [RS_27]
- | key expressions:_col0 (type: int)
- | Map-reduce partition columns:_col0 (type: int)
- | sort order:+
- | Statistics:Num rows: 40176 Data size: 44957392 Basic stats: COMPLETE Column stats: NONE
- | value expressions:_col1 (type: decimal(7,2))
- | Select Operator [SEL_9]
- | outputColumnNames:["_col0","_col1"]
- | Statistics:Num rows: 40176 Data size: 44957392 Basic stats: COMPLETE Column stats: NONE
- | Merge Join Operator [MERGEJOIN_57]
- | | condition map:[{"":"Inner Join 0 to 1"}]
- | | keys:{"0":"_col0 (type: int)","1":"_col0 (type: int)"}
- | | outputColumnNames:["_col1","_col2"]
- | | Statistics:Num rows: 40176 Data size: 44957392 Basic stats: COMPLETE Column stats: NONE
- | |<-Map 1 [SIMPLE_EDGE]
- | | Reduce Output Operator [RS_6]
- | | key expressions:_col0 (type: int)
- | | Map-reduce partition columns:_col0 (type: int)
- | | sort order:+
- | | Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- | | value expressions:_col1 (type: int), _col2 (type: decimal(7,2))
- | | Select Operator [SEL_2]
- | | outputColumnNames:["_col0","_col1","_col2"]
- | | Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- | | Filter Operator [FIL_52]
- | | predicate:(cs_sold_date_sk is not null and cs_item_sk is not null) (type: boolean)
- | | Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- | | TableScan [TS_0]
- | | alias:cs
- | | Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- | |<-Map 5 [SIMPLE_EDGE]
- | Reduce Output Operator [RS_7]
- | key expressions:_col0 (type: int)
- | Map-reduce partition columns:_col0 (type: int)
- | sort order:+
- | Statistics:Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE
- | Select Operator [SEL_5]
- | outputColumnNames:["_col0"]
- | Statistics:Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE
- | Filter Operator [FIL_53]
- | predicate:(d_date_sk is not null and d_date BETWEEN '2000-01-27' AND '2000-04-27') (type: boolean)
- | Statistics:Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE
- | TableScan [TS_3]
- | alias:d
- | Statistics:Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE
- |<-Reducer 9 [SIMPLE_EDGE]
- Reduce Output Operator [RS_29]
- key expressions:_col0 (type: int)
- Map-reduce partition columns:_col0 (type: int)
- sort order:+
- Statistics:Num rows: 20088 Data size: 22478696 Basic stats: COMPLETE Column stats: NONE
- value expressions:_col1 (type: double)
- Select Operator [SEL_26]
- outputColumnNames:["_col0","_col1"]
- Statistics:Num rows: 20088 Data size: 22478696 Basic stats: COMPLETE Column stats: NONE
- Group By Operator [GBY_25]
- | aggregations:["avg(VALUE._col0)"]
- | keys:KEY._col0 (type: int)
- | outputColumnNames:["_col0","_col1"]
- | Statistics:Num rows: 20088 Data size: 22478696 Basic stats: COMPLETE Column stats: NONE
- |<-Reducer 8 [SIMPLE_EDGE]
- Reduce Output Operator [RS_24]
- key expressions:_col0 (type: int)
- Map-reduce partition columns:_col0 (type: int)
- sort order:+
- Statistics:Num rows: 40176 Data size: 44957392 Basic stats: COMPLETE Column stats: NONE
- value expressions:_col1 (type: struct<count:bigint,sum:decimal(17,2),input:decimal(7,2)>)
- Group By Operator [GBY_23]
- aggregations:["avg(_col2)"]
- keys:_col1 (type: int)
- outputColumnNames:["_col0","_col1"]
- Statistics:Num rows: 40176 Data size: 44957392 Basic stats: COMPLETE Column stats: NONE
- Merge Join Operator [MERGEJOIN_58]
- | condition map:[{"":"Inner Join 0 to 1"}]
- | keys:{"0":"_col0 (type: int)","1":"_col0 (type: int)"}
- | outputColumnNames:["_col1","_col2"]
- | Statistics:Num rows: 40176 Data size: 44957392 Basic stats: COMPLETE Column stats: NONE
- |<-Map 10 [SIMPLE_EDGE]
- | Reduce Output Operator [RS_20]
- | key expressions:_col0 (type: int)
- | Map-reduce partition columns:_col0 (type: int)
- | sort order:+
- | Statistics:Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE
- | Select Operator [SEL_18]
- | outputColumnNames:["_col0"]
- | Statistics:Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE
- | Filter Operator [FIL_56]
- | predicate:(d_date_sk is not null and d_date BETWEEN '2000-01-27' AND '2000-04-27') (type: boolean)
- | Statistics:Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE
- | TableScan [TS_16]
- | alias:d
- | Statistics:Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE
- |<-Map 7 [SIMPLE_EDGE]
- Reduce Output Operator [RS_19]
- key expressions:_col0 (type: int)
- Map-reduce partition columns:_col0 (type: int)
- sort order:+
- Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- value expressions:_col1 (type: int), _col2 (type: decimal(7,2))
- Select Operator [SEL_15]
- outputColumnNames:["_col0","_col1","_col2"]
- Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- Filter Operator [FIL_55]
- predicate:(cs_sold_date_sk is not null and cs_item_sk is not null) (type: boolean)
- Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- TableScan [TS_13]
- alias:cs
- Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
+ Fetch Operator
+ limit:-1
+ Stage-1
+ Reducer 4
+ File Output Operator [FS_37]
+ Group By Operator [GBY_35] (rows=1 width=112)
+ Output:["_col0"],aggregations:["sum(VALUE._col0)"]
+ <-Reducer 3 [SIMPLE_EDGE]
+ SHUFFLE [RS_34]
+ Group By Operator [GBY_33] (rows=1 width=112)
+ Output:["_col0"],aggregations:["sum(_col1)"]
+ Select Operator [SEL_32] (rows=169400 width=1436)
+ Output:["_col1"]
+ Filter Operator [FIL_31] (rows=169400 width=1436)
+ predicate:(_col1 > CAST( _col5 AS decimal(20,15)))
+ Merge Join Operator [MERGEJOIN_59] (rows=508200 width=1436)
+ Conds:RS_27._col0=RS_28._col0(Inner),RS_28._col0=RS_29._col0(Inner),Output:["_col1","_col5"]
+ <-Map 6 [SIMPLE_EDGE]
+ SHUFFLE [RS_28]
+ PartitionCols:_col0
+ Select Operator [SEL_12] (rows=231000 width=1436)
+ Output:["_col0"]
+ Filter Operator [FIL_54] (rows=231000 width=1436)
+ predicate:(i_item_sk is not null and (i_manufact_id = 436))
+ TableScan [TS_10] (rows=462000 width=1436)
+ default@item,i,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_manufact_id"]
+ <-Reducer 2 [SIMPLE_EDGE]
+ SHUFFLE [RS_27]
+ PartitionCols:_col0
+ Select Operator [SEL_9] (rows=40176 width=1119)
+ Output:["_col0","_col1"]
+ Merge Join Operator [MERGEJOIN_57] (rows=40176 width=1119)
+ Conds:RS_6._col0=RS_7._col0(Inner),Output:["_col1","_col2"]
+ <-Map 1 [SIMPLE_EDGE]
+ SHUFFLE [RS_6]
+ PartitionCols:_col0
+ Select Operator [SEL_2] (rows=1 width=0)
+ Output:["_col0","_col1","_col2"]
+ Filter Operator [FIL_52] (rows=1 width=0)
+ predicate:(cs_sold_date_sk is not null and cs_item_sk is not null)
+ TableScan [TS_0] (rows=1 width=0)
+ default@catalog_sales,cs,Tbl:PARTIAL,Col:NONE,Output:["cs_sold_date_sk","cs_item_sk","cs_ext_discount_amt"]
+ <-Map 5 [SIMPLE_EDGE]
+ SHUFFLE [RS_7]
+ PartitionCols:_col0
+ Select Operator [SEL_5] (rows=36524 width=1119)
+ Output:["_col0"]
+ Filter Operator [FIL_53] (rows=36524 width=1119)
+ predicate:(d_date_sk is not null and d_date BETWEEN '2000-01-27' AND '2000-04-27')
+ TableScan [TS_3] (rows=73049 width=1119)
+ default@date_dim,d,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_date"]
+ <-Reducer 9 [SIMPLE_EDGE]
+ SHUFFLE [RS_29]
+ PartitionCols:_col0
+ Select Operator [SEL_26] (rows=20088 width=1119)
+ Output:["_col0","_col1"]
+ Group By Operator [GBY_25] (rows=20088 width=1119)
+ Output:["_col0","_col1"],aggregations:["avg(VALUE._col0)"],keys:KEY._col0
+ <-Reducer 8 [SIMPLE_EDGE]
+ SHUFFLE [RS_24]
+ PartitionCols:_col0
+ Group By Operator [GBY_23] (rows=40176 width=1119)
+ Output:["_col0","_col1"],aggregations:["avg(_col2)"],keys:_col1
+ Merge Join Operator [MERGEJOIN_58] (rows=40176 width=1119)
+ Conds:RS_19._col0=RS_20._col0(Inner),Output:["_col1","_col2"]
+ <-Map 10 [SIMPLE_EDGE]
+ SHUFFLE [RS_20]
+ PartitionCols:_col0
+ Select Operator [SEL_18] (rows=36524 width=1119)
+ Output:["_col0"]
+ Filter Operator [FIL_56] (rows=36524 width=1119)
+ predicate:(d_date_sk is not null and d_date BETWEEN '2000-01-27' AND '2000-04-27')
+ TableScan [TS_16] (rows=73049 width=1119)
+ default@date_dim,d,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_date"]
+ <-Map 7 [SIMPLE_EDGE]
+ SHUFFLE [RS_19]
+ PartitionCols:_col0
+ Select Operator [SEL_15] (rows=1 width=0)
+ Output:["_col0","_col1","_col2"]
+ Filter Operator [FIL_55] (rows=1 width=0)
+ predicate:(cs_sold_date_sk is not null and cs_item_sk is not null)
+ TableScan [TS_13] (rows=1 width=0)
+ default@catalog_sales,cs,Tbl:PARTIAL,Col:NONE,Output:["cs_sold_date_sk","cs_item_sk","cs_ext_discount_amt"]
http://git-wip-us.apache.org/repos/asf/hive/blob/be9735e1/ql/src/test/results/clientpositive/perf/query34.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/perf/query34.q.out b/ql/src/test/results/clientpositive/perf/query34.q.out
index 7976863..037bc76 100644
--- a/ql/src/test/results/clientpositive/perf/query34.q.out
+++ b/ql/src/test/results/clientpositive/perf/query34.q.out
@@ -13,165 +13,88 @@ Reducer 6 <- Map 11 (SIMPLE_EDGE), Reducer 5 (SIMPLE_EDGE)
Reducer 7 <- Reducer 6 (SIMPLE_EDGE)
Stage-0
- Fetch Operator
- limit:-1
- Stage-1
- Reducer 7
- File Output Operator [FS_37]
- compressed:false
- Statistics:Num rows: 88000001 Data size: 75681779077 Basic stats: COMPLETE Column stats: NONE
- table:{"input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat","serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe"}
- Select Operator [SEL_36]
- | outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5"]
- | Statistics:Num rows: 88000001 Data size: 75681779077 Basic stats: COMPLETE Column stats: NONE
- |<-Reducer 6 [SIMPLE_EDGE]
- Reduce Output Operator [RS_35]
- key expressions:_col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string)
- sort order:+++-
- Statistics:Num rows: 88000001 Data size: 75681779077 Basic stats: COMPLETE Column stats: NONE
- value expressions:_col4 (type: int), _col5 (type: bigint)
- Select Operator [SEL_34]
- outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5"]
- Statistics:Num rows: 88000001 Data size: 75681779077 Basic stats: COMPLETE Column stats: NONE
- Merge Join Operator [MERGEJOIN_60]
- | condition map:[{"":"Inner Join 0 to 1"}]
- | keys:{"0":"_col1 (type: int)","1":"_col0 (type: int)"}
- | outputColumnNames:["_col0","_col2","_col4","_col5","_col6","_col7"]
- | Statistics:Num rows: 88000001 Data size: 75681779077 Basic stats: COMPLETE Column stats: NONE
- |<-Map 11 [SIMPLE_EDGE]
- | Reduce Output Operator [RS_32]
- | key expressions:_col0 (type: int)
- | Map-reduce partition columns:_col0 (type: int)
- | sort order:+
- | Statistics:Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE
- | value expressions:_col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string)
- | Select Operator [SEL_30]
- | outputColumnNames:["_col0","_col1","_col2","_col3","_col4"]
- | Statistics:Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE
- | Filter Operator [FIL_56]
- | predicate:c_customer_sk is not null (type: boolean)
- | Statistics:Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE
- | TableScan [TS_28]
- | alias:customer
- | Statistics:Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE
- |<-Reducer 5 [SIMPLE_EDGE]
- Reduce Output Operator [RS_31]
- key expressions:_col1 (type: int)
- Map-reduce partition columns:_col1 (type: int)
- sort order:+
- Statistics:Num rows: 12153 Data size: 13599611 Basic stats: COMPLETE Column stats: NONE
- value expressions:_col0 (type: int), _col2 (type: bigint)
- Filter Operator [FIL_26]
- predicate:_col2 BETWEEN 15 AND 20 (type: boolean)
- Statistics:Num rows: 12153 Data size: 13599611 Basic stats: COMPLETE Column stats: NONE
- Select Operator [SEL_25]
- outputColumnNames:["_col0","_col1","_col2"]
- Statistics:Num rows: 24306 Data size: 27199223 Basic stats: COMPLETE Column stats: NONE
- Group By Operator [GBY_24]
- | aggregations:["count(VALUE._col0)"]
- | keys:KEY._col0 (type: int), KEY._col1 (type: int)
- | outputColumnNames:["_col0","_col1","_col2"]
- | Statistics:Num rows: 24306 Data size: 27199223 Basic stats: COMPLETE Column stats: NONE
- |<-Reducer 4 [SIMPLE_EDGE]
- Reduce Output Operator [RS_23]
- key expressions:_col0 (type: int), _col1 (type: int)
- Map-reduce partition columns:_col0 (type: int), _col1 (type: int)
- sort order:++
- Statistics:Num rows: 48612 Data size: 54398446 Basic stats: COMPLETE Column stats: NONE
- value expressions:_col2 (type: bigint)
- Group By Operator [GBY_22]
- aggregations:["count()"]
- keys:_col1 (type: int), _col4 (type: int)
- outputColumnNames:["_col0","_col1","_col2"]
- Statistics:Num rows: 48612 Data size: 54398446 Basic stats: COMPLETE Column stats: NONE
- Merge Join Operator [MERGEJOIN_59]
- | condition map:[{"":"Inner Join 0 to 1"}]
- | keys:{"0":"_col2 (type: int)","1":"_col0 (type: int)"}
- | outputColumnNames:["_col1","_col4"]
- | Statistics:Num rows: 48612 Data size: 54398446 Basic stats: COMPLETE Column stats: NONE
- |<-Map 10 [SIMPLE_EDGE]
- | Reduce Output Operator [RS_19]
- | key expressions:_col0 (type: int)
- | Map-reduce partition columns:_col0 (type: int)
- | sort order:+
- | Statistics:Num rows: 800 Data size: 85600 Basic stats: COMPLETE Column stats: NONE
- | Select Operator [SEL_11]
- | outputColumnNames:["_col0"]
- | Statistics:Num rows: 800 Data size: 85600 Basic stats: COMPLETE Column stats: NONE
- | Filter Operator [FIL_55]
- | predicate:(((((hd_buy_potential = '1001-5000') or (hd_buy_potential = '5001-10000')) and (hd_vehicle_count > 0)) and (CASE WHEN ((hd_vehicle_count > 0)) THEN ((UDFToDouble(hd_dep_count) / UDFToDouble(hd_vehicle_count))) ELSE (null) END > 1.2)) and hd_demo_sk is not null) (type: boolean)
- | Statistics:Num rows: 800 Data size: 85600 Basic stats: COMPLETE Column stats: NONE
- | TableScan [TS_9]
- | alias:household_demographics
- | Statistics:Num rows: 7200 Data size: 770400 Basic stats: COMPLETE Column stats: NONE
- |<-Reducer 3 [SIMPLE_EDGE]
- Reduce Output Operator [RS_18]
- key expressions:_col2 (type: int)
- Map-reduce partition columns:_col2 (type: int)
- sort order:+
- Statistics:Num rows: 44193 Data size: 49453132 Basic stats: COMPLETE Column stats: NONE
- value expressions:_col1 (type: int), _col4 (type: int)
- Merge Join Operator [MERGEJOIN_58]
- | condition map:[{"":"Inner Join 0 to 1"}]
- | keys:{"0":"_col3 (type: int)","1":"_col0 (type: int)"}
- | outputColumnNames:["_col1","_col2","_col4"]
- | Statistics:Num rows: 44193 Data size: 49453132 Basic stats: COMPLETE Column stats: NONE
- |<-Map 9 [SIMPLE_EDGE]
- | Reduce Output Operator [RS_16]
- | key expressions:_col0 (type: int)
- | Map-reduce partition columns:_col0 (type: int)
- | sort order:+
- | Statistics:Num rows: 852 Data size: 1628138 Basic stats: COMPLETE Column stats: NONE
- | Select Operator [SEL_8]
- | outputColumnNames:["_col0"]
- | Statistics:Num rows: 852 Data size: 1628138 Basic stats: COMPLETE Column stats: NONE
- | Filter Operator [FIL_54]
- | predicate:((s_county) IN ('Kittitas County', 'Adams County', 'Richland County', 'Furnas County', 'Orange County', 'Appanoose County', 'Franklin Parish', 'Tehama County') and s_store_sk is not null) (type: boolean)
- | Statistics:Num rows: 852 Data size: 1628138 Basic stats: COMPLETE Column stats: NONE
- | TableScan [TS_6]
- | alias:store
- | Statistics:Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE
- |<-Reducer 2 [SIMPLE_EDGE]
- Reduce Output Operator [RS_15]
- key expressions:_col3 (type: int)
- Map-reduce partition columns:_col3 (type: int)
- sort order:+
- Statistics:Num rows: 40176 Data size: 44957392 Basic stats: COMPLETE Column stats: NONE
- value expressions:_col1 (type: int), _col2 (type: int), _col4 (type: int)
- Merge Join Operator [MERGEJOIN_57]
- | condition map:[{"":"Inner Join 0 to 1"}]
- | keys:{"0":"_col0 (type: int)","1":"_col0 (type: int)"}
- | outputColumnNames:["_col1","_col2","_col3","_col4"]
- | Statistics:Num rows: 40176 Data size: 44957392 Basic stats: COMPLETE Column stats: NONE
- |<-Map 1 [SIMPLE_EDGE]
- | Reduce Output Operator [RS_12]
- | key expressions:_col0 (type: int)
- | Map-reduce partition columns:_col0 (type: int)
- | sort order:+
- | Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- | value expressions:_col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: int)
- | Select Operator [SEL_2]
- | outputColumnNames:["_col0","_col1","_col2","_col3","_col4"]
- | Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- | Filter Operator [FIL_52]
- | predicate:(((ss_sold_date_sk is not null and ss_store_sk is not null) and ss_hdemo_sk is not null) and ss_customer_sk is not null) (type: boolean)
- | Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- | TableScan [TS_0]
- | alias:store_sales
- | Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- |<-Map 8 [SIMPLE_EDGE]
- Reduce Output Operator [RS_13]
- key expressions:_col0 (type: int)
- Map-reduce partition columns:_col0 (type: int)
- sort order:+
- Statistics:Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE
- Select Operator [SEL_5]
- outputColumnNames:["_col0"]
- Statistics:Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE
- Filter Operator [FIL_53]
- predicate:(((d_dom BETWEEN 1 AND 3 or d_dom BETWEEN 25 AND 28) and (d_year) IN (1998, 1999, 2000)) and d_date_sk is not null) (type: boolean)
- Statistics:Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE
- TableScan [TS_3]
- alias:date_dim
- Statistics:Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE
+ Fetch Operator
+ limit:-1
+ Stage-1
+ Reducer 7
+ File Output Operator [FS_37]
+ Select Operator [SEL_36] (rows=88000001 width=860)
+ Output:["_col0","_col1","_col2","_col3","_col4","_col5"]
+ <-Reducer 6 [SIMPLE_EDGE]
+ SHUFFLE [RS_35]
+ Select Operator [SEL_34] (rows=88000001 width=860)
+ Output:["_col0","_col1","_col2","_col3","_col4","_col5"]
+ Merge Join Operator [MERGEJOIN_60] (rows=88000001 width=860)
+ Conds:RS_31._col1=RS_32._col0(Inner),Output:["_col0","_col2","_col4","_col5","_col6","_col7"]
+ <-Map 11 [SIMPLE_EDGE]
+ SHUFFLE [RS_32]
+ PartitionCols:_col0
+ Select Operator [SEL_30] (rows=80000000 width=860)
+ Output:["_col0","_col1","_col2","_col3","_col4"]
+ Filter Operator [FIL_56] (rows=80000000 width=860)
+ predicate:c_customer_sk is not null
+ TableScan [TS_28] (rows=80000000 width=860)
+ default@customer,customer,Tbl:COMPLETE,Col:NONE,Output:["c_customer_sk","c_salutation","c_first_name","c_last_name","c_preferred_cust_flag"]
+ <-Reducer 5 [SIMPLE_EDGE]
+ SHUFFLE [RS_31]
+ PartitionCols:_col1
+ Filter Operator [FIL_26] (rows=12153 width=1119)
+ predicate:_col2 BETWEEN 15 AND 20
+ Select Operator [SEL_25] (rows=24306 width=1119)
+ Output:["_col0","_col1","_col2"]
+ Group By Operator [GBY_24] (rows=24306 width=1119)
+ Output:["_col0","_col1","_col2"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1
+ <-Reducer 4 [SIMPLE_EDGE]
+ SHUFFLE [RS_23]
+ PartitionCols:_col0, _col1
+ Group By Operator [GBY_22] (rows=48612 width=1119)
+ Output:["_col0","_col1","_col2"],aggregations:["count()"],keys:_col1, _col4
+ Merge Join Operator [MERGEJOIN_59] (rows=48612 width=1119)
+ Conds:RS_18._col2=RS_19._col0(Inner),Output:["_col1","_col4"]
+ <-Map 10 [SIMPLE_EDGE]
+ SHUFFLE [RS_19]
+ PartitionCols:_col0
+ Select Operator [SEL_11] (rows=800 width=107)
+ Output:["_col0"]
+ Filter Operator [FIL_55] (rows=800 width=107)
+ predicate:(((((hd_buy_potential = '1001-5000') or (hd_buy_potential = '5001-10000')) and (hd_vehicle_count > 0)) and (CASE WHEN ((hd_vehicle_count > 0)) THEN ((UDFToDouble(hd_dep_count) / UDFToDouble(hd_vehicle_count))) ELSE (null) END > 1.2)) and hd_demo_sk is not null)
+ TableScan [TS_9] (rows=7200 width=107)
+ default@household_demographics,household_demographics,Tbl:COMPLETE,Col:NONE,Output:["hd_demo_sk","hd_buy_potential","hd_dep_count","hd_vehicle_count"]
+ <-Reducer 3 [SIMPLE_EDGE]
+ SHUFFLE [RS_18]
+ PartitionCols:_col2
+ Merge Join Operator [MERGEJOIN_58] (rows=44193 width=1119)
+ Conds:RS_15._col3=RS_16._col0(Inner),Output:["_col1","_col2","_col4"]
+ <-Map 9 [SIMPLE_EDGE]
+ SHUFFLE [RS_16]
+ PartitionCols:_col0
+ Select Operator [SEL_8] (rows=852 width=1910)
+ Output:["_col0"]
+ Filter Operator [FIL_54] (rows=852 width=1910)
+ predicate:((s_county) IN ('Kittitas County', 'Adams County', 'Richland County', 'Furnas County', 'Orange County', 'Appanoose County', 'Franklin Parish', 'Tehama County') and s_store_sk is not null)
+ TableScan [TS_6] (rows=1704 width=1910)
+ default@store,store,Tbl:COMPLETE,Col:NONE,Output:["s_store_sk","s_county"]
+ <-Reducer 2 [SIMPLE_EDGE]
+ SHUFFLE [RS_15]
+ PartitionCols:_col3
+ Merge Join Operator [MERGEJOIN_57] (rows=40176 width=1119)
+ Conds:RS_12._col0=RS_13._col0(Inner),Output:["_col1","_col2","_col3","_col4"]
+ <-Map 1 [SIMPLE_EDGE]
+ SHUFFLE [RS_12]
+ PartitionCols:_col0
+ Select Operator [SEL_2] (rows=1 width=0)
+ Output:["_col0","_col1","_col2","_col3","_col4"]
+ Filter Operator [FIL_52] (rows=1 width=0)
+ predicate:(((ss_sold_date_sk is not null and ss_store_sk is not null) and ss_hdemo_sk is not null) and ss_customer_sk is not null)
+ TableScan [TS_0] (rows=1 width=0)
+ default@store_sales,store_sales,Tbl:PARTIAL,Col:NONE,Output:["ss_sold_date_sk","ss_customer_sk","ss_hdemo_sk","ss_store_sk","ss_ticket_number"]
+ <-Map 8 [SIMPLE_EDGE]
+ SHUFFLE [RS_13]
+ PartitionCols:_col0
+ Select Operator [SEL_5] (rows=36524 width=1119)
+ Output:["_col0"]
+ Filter Operator [FIL_53] (rows=36524 width=1119)
+ predicate:(((d_dom BETWEEN 1 AND 3 or d_dom BETWEEN 25 AND 28) and (d_year) IN (1998, 1999, 2000)) and d_date_sk is not null)
+ TableScan [TS_3] (rows=73049 width=1119)
+ default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year","d_dom"]
http://git-wip-us.apache.org/repos/asf/hive/blob/be9735e1/ql/src/test/results/clientpositive/perf/query39.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/perf/query39.q.out b/ql/src/test/results/clientpositive/perf/query39.q.out
index 14e3dfc..7dcf01d 100644
--- a/ql/src/test/results/clientpositive/perf/query39.q.out
+++ b/ql/src/test/results/clientpositive/perf/query39.q.out
@@ -17,285 +17,151 @@ Reducer 6 <- Reducer 15 (SIMPLE_EDGE), Reducer 5 (SIMPLE_EDGE)
Reducer 7 <- Reducer 6 (SIMPLE_EDGE)
Stage-0
- Fetch Operator
- limit:-1
- Stage-1
- Reducer 7
- File Output Operator [FS_62]
- compressed:false
- Statistics:Num rows: 112735 Data size: 161919824 Basic stats: COMPLETE Column stats: NONE
- table:{"input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat","serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe"}
- Select Operator [SEL_61]
- | outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9"]
- | Statistics:Num rows: 112735 Data size: 161919824 Basic stats: COMPLETE Column stats: NONE
- |<-Reducer 6 [SIMPLE_EDGE]
- Reduce Output Operator [RS_60]
- key expressions:_col0 (type: int), _col1 (type: int), 3 (type: int), _col3 (type: double), _col4 (type: double), 4 (type: int), _col8 (type: double), _col9 (type: double)
- sort order:++++++++
- Statistics:Num rows: 112735 Data size: 161919824 Basic stats: COMPLETE Column stats: NONE
- value expressions:_col5 (type: int), _col6 (type: int)
- Select Operator [SEL_59]
- outputColumnNames:["_col0","_col1","_col3","_col4","_col5","_col6","_col8","_col9"]
- Statistics:Num rows: 112735 Data size: 161919824 Basic stats: COMPLETE Column stats: NONE
- Merge Join Operator [MERGEJOIN_105]
- | condition map:[{"":"Inner Join 0 to 1"}]
- | keys:{"0":"_col2 (type: int), _col1 (type: int)","1":"_col2 (type: int), _col1 (type: int)"}
- | outputColumnNames:["_col1","_col2","_col4","_col5","_col7","_col8","_col10","_col11"]
- | Statistics:Num rows: 112735 Data size: 161919824 Basic stats: COMPLETE Column stats: NONE
- |<-Reducer 15 [SIMPLE_EDGE]
- | Reduce Output Operator [RS_57]
- | key expressions:_col2 (type: int), _col1 (type: int)
- | Map-reduce partition columns:_col2 (type: int), _col1 (type: int)
- | sort order:++
- | Statistics:Num rows: 102487 Data size: 147199837 Basic stats: COMPLETE Column stats: NONE
- | value expressions:_col4 (type: double), _col5 (type: double)
- | Select Operator [SEL_55]
- | outputColumnNames:["_col1","_col2","_col4","_col5"]
- | Statistics:Num rows: 102487 Data size: 147199837 Basic stats: COMPLETE Column stats: NONE
- | Filter Operator [FIL_54]
- | predicate:(CASE (_col4) WHEN (0) THEN (0) ELSE ((_col5 / _col4)) END > 1.0) (type: boolean)
- | Statistics:Num rows: 102487 Data size: 147199837 Basic stats: COMPLETE Column stats: NONE
- | Select Operator [SEL_97]
- | outputColumnNames:["_col1","_col2","_col4","_col5"]
- | Statistics:Num rows: 307461 Data size: 441599512 Basic stats: COMPLETE Column stats: NONE
- | Group By Operator [GBY_53]
- | | aggregations:["avg(VALUE._col0)","stddev_samp(VALUE._col1)"]
- | | keys:KEY._col0 (type: string), KEY._col1 (type: int), KEY._col2 (type: int), 4 (type: int)
- | | outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5"]
- | | Statistics:Num rows: 307461 Data size: 441599512 Basic stats: COMPLETE Column stats: NONE
- | |<-Reducer 14 [SIMPLE_EDGE]
- | Reduce Output Operator [RS_52]
- | key expressions:_col0 (type: string), _col1 (type: int), _col2 (type: int), 4 (type: int)
- | Map-reduce partition columns:_col0 (type: string), _col1 (type: int), _col2 (type: int), 4 (type: int)
- | sort order:++++
- | Statistics:Num rows: 614922 Data size: 883199024 Basic stats: COMPLETE Column stats: NONE
- | value expressions:_col4 (type: struct<count:bigint,sum:double,input:int>), _col5 (type: struct<count:bigint,sum:double,variance:double>)
- | Group By Operator [GBY_51]
- | aggregations:["avg(_col4)","stddev_samp(_col4)"]
- | keys:_col0 (type: string), _col1 (type: int), _col2 (type: int), 4 (type: int)
- | outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5"]
- | Statistics:Num rows: 614922 Data size: 883199024 Basic stats: COMPLETE Column stats: NONE
- | Select Operator [SEL_49]
- | outputColumnNames:["_col0","_col1","_col2","_col4"]
- | Statistics:Num rows: 614922 Data size: 883199024 Basic stats: COMPLETE Column stats: NONE
- | Merge Join Operator [MERGEJOIN_104]
- | | condition map:[{"":"Inner Join 0 to 1"}]
- | | keys:{"0":"_col0 (type: int)","1":"_col0 (type: int)"}
- | | outputColumnNames:["_col3","_col4","_col5","_col6"]
- | | Statistics:Num rows: 614922 Data size: 883199024 Basic stats: COMPLETE Column stats: NONE
- | |<-Map 18 [SIMPLE_EDGE]
- | | Reduce Output Operator [RS_47]
- | | key expressions:_col0 (type: int)
- | | Map-reduce partition columns:_col0 (type: int)
- | | sort order:+
- | | Statistics:Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE
- | | Select Operator [SEL_39]
- | | outputColumnNames:["_col0"]
- | | Statistics:Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE
- | | Filter Operator [FIL_96]
- | | predicate:(((d_year = 1999) and d_date_sk is not null) and (d_moy = 4)) (type: boolean)
- | | Statistics:Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE
- | | TableScan [TS_37]
- | | alias:date_dim
- | | Statistics:Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE
- | |<-Reducer 13 [SIMPLE_EDGE]
- | Reduce Output Operator [RS_46]
- | key expressions:_col0 (type: int)
- | Map-reduce partition columns:_col0 (type: int)
- | sort order:+
- | Statistics:Num rows: 559020 Data size: 802908187 Basic stats: COMPLETE Column stats: NONE
- | value expressions:_col3 (type: int), _col4 (type: int), _col5 (type: int), _col6 (type: string)
- | Merge Join Operator [MERGEJOIN_103]
- | | condition map:[{"":"Inner Join 0 to 1"}]
- | | keys:{"0":"_col2 (type: int)","1":"_col0 (type: int)"}
- | | outputColumnNames:["_col0","_col3","_col4","_col5","_col6"]
- | | Statistics:Num rows: 559020 Data size: 802908187 Basic stats: COMPLETE Column stats: NONE
- | |<-Map 17 [SIMPLE_EDGE]
- | | Reduce Output Operator [RS_44]
- | | key expressions:_col0 (type: int)
- | | Map-reduce partition columns:_col0 (type: int)
- | | sort order:+
- | | Statistics:Num rows: 27 Data size: 27802 Basic stats: COMPLETE Column stats: NONE
- | | value expressions:_col1 (type: string)
- | | Select Operator [SEL_36]
- | | outputColumnNames:["_col0","_col1"]
- | | Statistics:Num rows: 27 Data size: 27802 Basic stats: COMPLETE Column stats: NONE
- | | Filter Operator [FIL_95]
- | | predicate:w_warehouse_sk is not null (type: boolean)
- | | Statistics:Num rows: 27 Data size: 27802 Basic stats: COMPLETE Column stats: NONE
- | | TableScan [TS_34]
- | | alias:warehouse
- | | Statistics:Num rows: 27 Data size: 27802 Basic stats: COMPLETE Column stats: NONE
- | |<-Reducer 12 [SIMPLE_EDGE]
- | Reduce Output Operator [RS_43]
- | key expressions:_col2 (type: int)
- | Map-reduce partition columns:_col2 (type: int)
- | sort order:+
- | Statistics:Num rows: 508200 Data size: 729916518 Basic stats: COMPLETE Column stats: NONE
- | value expressions:_col0 (type: int), _col3 (type: int), _col4 (type: int)
- | Merge Join Operator [MERGEJOIN_102]
- | | condition map:[{"":"Inner Join 0 to 1"}]
- | | keys:{"0":"_col1 (type: int)","1":"_col0 (type: int)"}
- | | outputColumnNames:["_col0","_col2","_col3","_col4"]
- | | Statistics:Num rows: 508200 Data size: 729916518 Basic stats: COMPLETE Column stats: NONE
- | |<-Map 11 [SIMPLE_EDGE]
- | | Reduce Output Operator [RS_40]
- | | key expressions:_col1 (type: int)
- | | Map-reduce partition columns:_col1 (type: int)
- | | sort order:+
- | | Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- | | value expressions:_col0 (type: int), _col2 (type: int), _col3 (type: int)
- | | Select Operator [SEL_30]
- | | outputColumnNames:["_col0","_col1","_col2","_col3"]
- | | Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- | | Filter Operator [FIL_93]
- | | predicate:((inv_item_sk is not null and inv_warehouse_sk is not null) and inv_date_sk is not null) (type: boolean)
- | | Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- | | TableScan [TS_28]
- | | alias:inventory
- | | Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- | |<-Map 16 [SIMPLE_EDGE]
- | Reduce Output Operator [RS_41]
- | key expressions:_col0 (type: int)
- | Map-reduce partition columns:_col0 (type: int)
- | sort order:+
- | Statistics:Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE
- | Select Operator [SEL_33]
- | outputColumnNames:["_col0"]
- | Statistics:Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE
- | Filter Operator [FIL_94]
- | predicate:i_item_sk is not null (type: boolean)
- | Statistics:Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE
- | TableScan [TS_31]
- | alias:item
- | Statistics:Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE
- |<-Reducer 5 [SIMPLE_EDGE]
- Reduce Output Operator [RS_56]
- key expressions:_col2 (type: int), _col1 (type: int)
- Map-reduce partition columns:_col2 (type: int), _col1 (type: int)
- sort order:++
- Statistics:Num rows: 102487 Data size: 147199837 Basic stats: COMPLETE Column stats: NONE
- value expressions:_col4 (type: double), _col5 (type: double)
- Select Operator [SEL_27]
- outputColumnNames:["_col1","_col2","_col4","_col5"]
- Statistics:Num rows: 102487 Data size: 147199837 Basic stats: COMPLETE Column stats: NONE
- Filter Operator [FIL_26]
- predicate:(CASE (_col4) WHEN (0) THEN (0) ELSE ((_col5 / _col4)) END > 1.0) (type: boolean)
- Statistics:Num rows: 102487 Data size: 147199837 Basic stats: COMPLETE Column stats: NONE
- Select Operator [SEL_98]
- outputColumnNames:["_col1","_col2","_col4","_col5"]
- Statistics:Num rows: 307461 Data size: 441599512 Basic stats: COMPLETE Column stats: NONE
- Group By Operator [GBY_25]
- | aggregations:["avg(VALUE._col0)","stddev_samp(VALUE._col1)"]
- | keys:KEY._col0 (type: string), KEY._col1 (type: int), KEY._col2 (type: int), 3 (type: int)
- | outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5"]
- | Statistics:Num rows: 307461 Data size: 441599512 Basic stats: COMPLETE Column stats: NONE
- |<-Reducer 4 [SIMPLE_EDGE]
- Reduce Output Operator [RS_24]
- key expressions:_col0 (type: string), _col1 (type: int), _col2 (type: int), 3 (type: int)
- Map-reduce partition columns:_col0 (type: string), _col1 (type: int), _col2 (type: int), 3 (type: int)
- sort order:++++
- Statistics:Num rows: 614922 Data size: 883199024 Basic stats: COMPLETE Column stats: NONE
- value expressions:_col4 (type: struct<count:bigint,sum:double,input:int>), _col5 (type: struct<count:bigint,sum:double,variance:double>)
- Group By Operator [GBY_23]
- aggregations:["avg(_col4)","stddev_samp(_col4)"]
- keys:_col0 (type: string), _col1 (type: int), _col2 (type: int), 3 (type: int)
- outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5"]
- Statistics:Num rows: 614922 Data size: 883199024 Basic stats: COMPLETE Column stats: NONE
- Select Operator [SEL_21]
- outputColumnNames:["_col0","_col1","_col2","_col4"]
- Statistics:Num rows: 614922 Data size: 883199024 Basic stats: COMPLETE Column stats: NONE
- Merge Join Operator [MERGEJOIN_101]
- | condition map:[{"":"Inner Join 0 to 1"}]
- | keys:{"0":"_col0 (type: int)","1":"_col0 (type: int)"}
- | outputColumnNames:["_col3","_col4","_col5","_col6"]
- | Statistics:Num rows: 614922 Data size: 883199024 Basic stats: COMPLETE Column stats: NONE
- |<-Map 10 [SIMPLE_EDGE]
- | Reduce Output Operator [RS_19]
- | key expressions:_col0 (type: int)
- | Map-reduce partition columns:_col0 (type: int)
- | sort order:+
- | Statistics:Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE
- | Select Operator [SEL_11]
- | outputColumnNames:["_col0"]
- | Statistics:Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE
- | Filter Operator [FIL_92]
- | predicate:(((d_year = 1999) and d_date_sk is not null) and (d_moy = 3)) (type: boolean)
- | Statistics:Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE
- | TableScan [TS_9]
- | alias:date_dim
- | Statistics:Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE
- |<-Reducer 3 [SIMPLE_EDGE]
- Reduce Output Operator [RS_18]
- key expressions:_col0 (type: int)
- Map-reduce partition columns:_col0 (type: int)
- sort order:+
- Statistics:Num rows: 559020 Data size: 802908187 Basic stats: COMPLETE Column stats: NONE
- value expressions:_col3 (type: int), _col4 (type: int), _col5 (type: int), _col6 (type: string)
- Merge Join Operator [MERGEJOIN_100]
- | condition map:[{"":"Inner Join 0 to 1"}]
- | keys:{"0":"_col2 (type: int)","1":"_col0 (type: int)"}
- | outputColumnNames:["_col0","_col3","_col4","_col5","_col6"]
- | Statistics:Num rows: 559020 Data size: 802908187 Basic stats: COMPLETE Column stats: NONE
- |<-Map 9 [SIMPLE_EDGE]
- | Reduce Output Operator [RS_16]
- | key expressions:_col0 (type: int)
- | Map-reduce partition columns:_col0 (type: int)
- | sort order:+
- | Statistics:Num rows: 27 Data size: 27802 Basic stats: COMPLETE Column stats: NONE
- | value expressions:_col1 (type: string)
- | Select Operator [SEL_8]
- | outputColumnNames:["_col0","_col1"]
- | Statistics:Num rows: 27 Data size: 27802 Basic stats: COMPLETE Column stats: NONE
- | Filter Operator [FIL_91]
- | predicate:w_warehouse_sk is not null (type: boolean)
- | Statistics:Num rows: 27 Data size: 27802 Basic stats: COMPLETE Column stats: NONE
- | TableScan [TS_6]
- | alias:warehouse
- | Statistics:Num rows: 27 Data size: 27802 Basic stats: COMPLETE Column stats: NONE
- |<-Reducer 2 [SIMPLE_EDGE]
- Reduce Output Operator [RS_15]
- key expressions:_col2 (type: int)
- Map-reduce partition columns:_col2 (type: int)
- sort order:+
- Statistics:Num rows: 508200 Data size: 729916518 Basic stats: COMPLETE Column stats: NONE
- value expressions:_col0 (type: int), _col3 (type: int), _col4 (type: int)
- Merge Join Operator [MERGEJOIN_99]
- | condition map:[{"":"Inner Join 0 to 1"}]
- | keys:{"0":"_col1 (type: int)","1":"_col0 (type: int)"}
- | outputColumnNames:["_col0","_col2","_col3","_col4"]
- | Statistics:Num rows: 508200 Data size: 729916518 Basic stats: COMPLETE Column stats: NONE
- |<-Map 1 [SIMPLE_EDGE]
- | Reduce Output Operator [RS_12]
- | key expressions:_col1 (type: int)
- | Map-reduce partition columns:_col1 (type: int)
- | sort order:+
- | Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- | value expressions:_col0 (type: int), _col2 (type: int), _col3 (type: int)
- | Select Operator [SEL_2]
- | outputColumnNames:["_col0","_col1","_col2","_col3"]
- | Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- | Filter Operator [FIL_89]
- | predicate:((inv_item_sk is not null and inv_warehouse_sk is not null) and inv_date_sk is not null) (type: boolean)
- | Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- | TableScan [TS_0]
- | alias:inventory
- | Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- |<-Map 8 [SIMPLE_EDGE]
- Reduce Output Operator [RS_13]
- key expressions:_col0 (type: int)
- Map-reduce partition columns:_col0 (type: int)
- sort order:+
- Statistics:Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE
- Select Operator [SEL_5]
- outputColumnNames:["_col0"]
- Statistics:Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE
- Filter Operator [FIL_90]
- predicate:i_item_sk is not null (type: boolean)
- Statistics:Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE
- TableScan [TS_3]
- alias:item
- Statistics:Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE
+ Fetch Operator
+ limit:-1
+ Stage-1
+ Reducer 7
+ File Output Operator [FS_62]
+ Select Operator [SEL_61] (rows=112735 width=1436)
+ Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9"]
+ <-Reducer 6 [SIMPLE_EDGE]
+ SHUFFLE [RS_60]
+ Select Operator [SEL_59] (rows=112735 width=1436)
+ Output:["_col0","_col1","_col3","_col4","_col5","_col6","_col8","_col9"]
+ Merge Join Operator [MERGEJOIN_105] (rows=112735 width=1436)
+ Conds:RS_56._col2, _col1=RS_57._col2, _col1(Inner),Output:["_col1","_col2","_col4","_col5","_col7","_col8","_col10","_col11"]
+ <-Reducer 15 [SIMPLE_EDGE]
+ SHUFFLE [RS_57]
+ PartitionCols:_col2, _col1
+ Select Operator [SEL_55] (rows=102487 width=1436)
+ Output:["_col1","_col2","_col4","_col5"]
+ Filter Operator [FIL_54] (rows=102487 width=1436)
+ predicate:(CASE (_col4) WHEN (0) THEN (0) ELSE ((_col5 / _col4)) END > 1.0)
+ Select Operator [SEL_97] (rows=307461 width=1436)
+ Output:["_col1","_col2","_col4","_col5"]
+ Group By Operator [GBY_53] (rows=307461 width=1436)
+ Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["avg(VALUE._col0)","stddev_samp(VALUE._col1)"],keys:KEY._col0, KEY._col1, KEY._col2, 4
+ <-Reducer 14 [SIMPLE_EDGE]
+ SHUFFLE [RS_52]
+ PartitionCols:_col0, _col1, _col2, 4
+ Group By Operator [GBY_51] (rows=614922 width=1436)
+ Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["avg(_col4)","stddev_samp(_col4)"],keys:_col0, _col1, _col2, 4
+ Select Operator [SEL_49] (rows=614922 width=1436)
+ Output:["_col0","_col1","_col2","_col4"]
+ Merge Join Operator [MERGEJOIN_104] (rows=614922 width=1436)
+ Conds:RS_46._col0=RS_47._col0(Inner),Output:["_col3","_col4","_col5","_col6"]
+ <-Map 18 [SIMPLE_EDGE]
+ SHUFFLE [RS_47]
+ PartitionCols:_col0
+ Select Operator [SEL_39] (rows=18262 width=1119)
+ Output:["_col0"]
+ Filter Operator [FIL_96] (rows=18262 width=1119)
+ predicate:(((d_year = 1999) and d_date_sk is not null) and (d_moy = 4))
+ TableScan [TS_37] (rows=73049 width=1119)
+ default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year","d_moy"]
+ <-Reducer 13 [SIMPLE_EDGE]
+ SHUFFLE [RS_46]
+ PartitionCols:_col0
+ Merge Join Operator [MERGEJOIN_103] (rows=559020 width=1436)
+ Conds:RS_43._col2=RS_44._col0(Inner),Output:["_col0","_col3","_col4","_col5","_col6"]
+ <-Map 17 [SIMPLE_EDGE]
+ SHUFFLE [RS_44]
+ PartitionCols:_col0
+ Select Operator [SEL_36] (rows=27 width=1029)
+ Output:["_col0","_col1"]
+ Filter Operator [FIL_95] (rows=27 width=1029)
+ predicate:w_warehouse_sk is not null
+ TableScan [TS_34] (rows=27 width=1029)
+ default@warehouse,warehouse,Tbl:COMPLETE,Col:NONE,Output:["w_warehouse_sk","w_warehouse_name"]
+ <-Reducer 12 [SIMPLE_EDGE]
+ SHUFFLE [RS_43]
+ PartitionCols:_col2
+ Merge Join Operator [MERGEJOIN_102] (rows=508200 width=1436)
+ Conds:RS_40._col1=RS_41._col0(Inner),Output:["_col0","_col2","_col3","_col4"]
+ <-Map 11 [SIMPLE_EDGE]
+ SHUFFLE [RS_40]
+ PartitionCols:_col1
+ Select Operator [SEL_30] (rows=1 width=0)
+ Output:["_col0","_col1","_col2","_col3"]
+ Filter Operator [FIL_93] (rows=1 width=0)
+ predicate:((inv_item_sk is not null and inv_warehouse_sk is not null) and inv_date_sk is not null)
+ TableScan [TS_28] (rows=1 width=0)
+ default@inventory,inventory,Tbl:PARTIAL,Col:NONE,Output:["inv_date_sk","inv_item_sk","inv_warehouse_sk","inv_quantity_on_hand"]
+ <-Map 16 [SIMPLE_EDGE]
+ SHUFFLE [RS_41]
+ PartitionCols:_col0
+ Select Operator [SEL_33] (rows=462000 width=1436)
+ Output:["_col0"]
+ Filter Operator [FIL_94] (rows=462000 width=1436)
+ predicate:i_item_sk is not null
+ TableScan [TS_31] (rows=462000 width=1436)
+ default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk"]
+ <-Reducer 5 [SIMPLE_EDGE]
+ SHUFFLE [RS_56]
+ PartitionCols:_col2, _col1
+ Select Operator [SEL_27] (rows=102487 width=1436)
+ Output:["_col1","_col2","_col4","_col5"]
+ Filter Operator [FIL_26] (rows=102487 width=1436)
+ predicate:(CASE (_col4) WHEN (0) THEN (0) ELSE ((_col5 / _col4)) END > 1.0)
+ Select Operator [SEL_98] (rows=307461 width=1436)
+ Output:["_col1","_col2","_col4","_col5"]
+ Group By Operator [GBY_25] (rows=307461 width=1436)
+ Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["avg(VALUE._col0)","stddev_samp(VALUE._col1)"],keys:KEY._col0, KEY._col1, KEY._col2, 3
+ <-Reducer 4 [SIMPLE_EDGE]
+ SHUFFLE [RS_24]
+ PartitionCols:_col0, _col1, _col2, 3
+ Group By Operator [GBY_23] (rows=614922 width=1436)
+ Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["avg(_col4)","stddev_samp(_col4)"],keys:_col0, _col1, _col2, 3
+ Select Operator [SEL_21] (rows=614922 width=1436)
+ Output:["_col0","_col1","_col2","_col4"]
+ Merge Join Operator [MERGEJOIN_101] (rows=614922 width=1436)
+ Conds:RS_18._col0=RS_19._col0(Inner),Output:["_col3","_col4","_col5","_col6"]
+ <-Map 10 [SIMPLE_EDGE]
+ SHUFFLE [RS_19]
+ PartitionCols:_col0
+ Select Operator [SEL_11] (rows=18262 width=1119)
+ Output:["_col0"]
+ Filter Operator [FIL_92] (rows=18262 width=1119)
+ predicate:(((d_year = 1999) and d_date_sk is not null) and (d_moy = 3))
+ TableScan [TS_9] (rows=73049 width=1119)
+ default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year","d_moy"]
+ <-Reducer 3 [SIMPLE_EDGE]
+ SHUFFLE [RS_18]
+ PartitionCols:_col0
+ Merge Join Operator [MERGEJOIN_100] (rows=559020 width=1436)
+ Conds:RS_15._col2=RS_16._col0(Inner),Output:["_col0","_col3","_col4","_col5","_col6"]
+ <-Map 9 [SIMPLE_EDGE]
+ SHUFFLE [RS_16]
+ PartitionCols:_col0
+ Select Operator [SEL_8] (rows=27 width=1029)
+ Output:["_col0","_col1"]
+ Filter Operator [FIL_91] (rows=27 width=1029)
+ predicate:w_warehouse_sk is not null
+ TableScan [TS_6] (rows=27 width=1029)
+ default@warehouse,warehouse,Tbl:COMPLETE,Col:NONE,Output:["w_warehouse_sk","w_warehouse_name"]
+ <-Reducer 2 [SIMPLE_EDGE]
+ SHUFFLE [RS_15]
+ PartitionCols:_col2
+ Merge Join Operator [MERGEJOIN_99] (rows=508200 width=1436)
+ Conds:RS_12._col1=RS_13._col0(Inner),Output:["_col0","_col2","_col3","_col4"]
+ <-Map 1 [SIMPLE_EDGE]
+ SHUFFLE [RS_12]
+ PartitionCols:_col1
+ Select Operator [SEL_2] (rows=1 width=0)
+ Output:["_col0","_col1","_col2","_col3"]
+ Filter Operator [FIL_89] (rows=1 width=0)
+ predicate:((inv_item_sk is not null and inv_warehouse_sk is not null) and inv_date_sk is not null)
+ TableScan [TS_0] (rows=1 width=0)
+ default@inventory,inventory,Tbl:PARTIAL,Col:NONE,Output:["inv_date_sk","inv_item_sk","inv_warehouse_sk","inv_quantity_on_hand"]
+ <-Map 8 [SIMPLE_EDGE]
+ SHUFFLE [RS_13]
+ PartitionCols:_col0
+ Select Operator [SEL_5] (rows=462000 width=1436)
+ Output:["_col0"]
+ Filter Operator [FIL_90] (rows=462000 width=1436)
+ predicate:i_item_sk is not null
+ TableScan [TS_3] (rows=462000 width=1436)
+ default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk"]
PREHOOK: query: with inv as (select w_warehouse_name,w_warehouse_sk,i_item_sk,d_moy ,stdev,mean, case mean when 0 then null else stdev/mean end cov from(select w_warehouse_name,w_warehouse_sk,i_item_sk,d_moy ,stddev_samp(inv_quantity_on_hand) stdev,avg(inv_quantity_on_hand) mean from inventory ,item ,warehouse ,date_dim where inv_item_sk = i_item_sk and inv_warehouse_sk = w_warehouse_sk and inv_date_sk = d_date_sk and d_year =1999 group by w_warehouse_name,w_warehouse_sk,i_item_sk,d_moy) foo where case mean when 0 then 0 else stdev/mean end > 1) select inv1.w_warehouse_sk,inv1.i_item_sk,inv1.d_moy,inv1.mean, inv1.cov ,inv2.w_warehouse_sk,inv2.i_item_sk,inv2.d_moy,inv2.mean, inv2.cov from inv inv1,inv inv2 where inv1.i_item_sk = inv2.i_item_sk and inv1.w_warehouse_sk = inv2.w_warehouse_sk and inv1.d_moy=3 and inv2.d_moy=3+1 and inv1.cov > 1.5 order by inv1.w_warehouse_sk,inv1.i_item_sk,inv1.d_moy,inv1.mean,inv1.cov ,inv2.d_moy,inv2.mean, inv2.cov
PREHOOK: type: QUERY