You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by ha...@apache.org on 2017/02/15 01:26:08 UTC
[06/15] hive git commit: HIVE-15905 : Inefficient plan for correlated
subqueries (Vineet Garg via Ashutosh Chauhan)
http://git-wip-us.apache.org/repos/asf/hive/blob/bddf5a7a/ql/src/test/results/clientpositive/perf/query69.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/perf/query69.q.out b/ql/src/test/results/clientpositive/perf/query69.q.out
index 71ddd71..38c7fa7 100644
--- a/ql/src/test/results/clientpositive/perf/query69.q.out
+++ b/ql/src/test/results/clientpositive/perf/query69.q.out
@@ -1,12 +1,9 @@
-Warning: Shuffle Join MERGEJOIN[261][tables = [$hdt$_2, $hdt$_3, $hdt$_4]] in Stage 'Reducer 17' is a cross product
-Warning: Shuffle Join MERGEJOIN[262][tables = [$hdt$_1, $hdt$_2, $hdt$_3]] in Stage 'Reducer 22' is a cross product
-Warning: Shuffle Join MERGEJOIN[273][tables = [$hdt$_3, $hdt$_4, $hdt$_2, $hdt$_1]] in Stage 'Reducer 13' is a cross product
-Warning: Shuffle Join MERGEJOIN[263][tables = [$hdt$_1, $hdt$_2, $hdt$_3]] in Stage 'Reducer 33' is a cross product
-Warning: Shuffle Join MERGEJOIN[264][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 38' is a cross product
-Warning: Shuffle Join MERGEJOIN[275][tables = [$hdt$_2, $hdt$_3, $hdt$_1, $hdt$_0]] in Stage 'Reducer 29' is a cross product
-Warning: Shuffle Join MERGEJOIN[265][tables = [$hdt$_2, $hdt$_3, $hdt$_4]] in Stage 'Reducer 49' is a cross product
-Warning: Shuffle Join MERGEJOIN[266][tables = [$hdt$_1, $hdt$_2, $hdt$_3]] in Stage 'Reducer 54' is a cross product
-Warning: Shuffle Join MERGEJOIN[278][tables = [$hdt$_3, $hdt$_4, $hdt$_2, $hdt$_1]] in Stage 'Reducer 45' is a cross product
+Warning: Shuffle Join MERGEJOIN[177][tables = [$hdt$_1, $hdt$_2, $hdt$_3]] in Stage 'Reducer 16' is a cross product
+Warning: Shuffle Join MERGEJOIN[185][tables = [$hdt$_2, $hdt$_3, $hdt$_1]] in Stage 'Reducer 12' is a cross product
+Warning: Shuffle Join MERGEJOIN[178][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 26' is a cross product
+Warning: Shuffle Join MERGEJOIN[186][tables = [$hdt$_1, $hdt$_2, $hdt$_0]] in Stage 'Reducer 22' is a cross product
+Warning: Shuffle Join MERGEJOIN[179][tables = [$hdt$_1, $hdt$_2, $hdt$_3]] in Stage 'Reducer 36' is a cross product
+Warning: Shuffle Join MERGEJOIN[188][tables = [$hdt$_2, $hdt$_3, $hdt$_1]] in Stage 'Reducer 32' is a cross product
PREHOOK: query: explain select
cd_gender,
cd_marital_status,
@@ -100,34 +97,25 @@ POSTHOOK: type: QUERY
Plan optimized by CBO.
Vertex dependency in root stage
-Reducer 11 <- Map 10 (SIMPLE_EDGE), Map 15 (SIMPLE_EDGE)
-Reducer 12 <- Reducer 11 (SIMPLE_EDGE), Reducer 18 (SIMPLE_EDGE)
-Reducer 13 <- Reducer 12 (CUSTOM_SIMPLE_EDGE), Reducer 23 (CUSTOM_SIMPLE_EDGE)
-Reducer 14 <- Reducer 13 (SIMPLE_EDGE)
-Reducer 17 <- Map 16 (CUSTOM_SIMPLE_EDGE), Map 19 (CUSTOM_SIMPLE_EDGE), Map 20 (CUSTOM_SIMPLE_EDGE)
-Reducer 18 <- Reducer 17 (SIMPLE_EDGE)
+Reducer 11 <- Map 10 (SIMPLE_EDGE), Map 14 (SIMPLE_EDGE)
+Reducer 12 <- Reducer 11 (CUSTOM_SIMPLE_EDGE), Reducer 17 (CUSTOM_SIMPLE_EDGE)
+Reducer 13 <- Reducer 12 (SIMPLE_EDGE)
+Reducer 16 <- Map 15 (CUSTOM_SIMPLE_EDGE), Map 18 (CUSTOM_SIMPLE_EDGE), Map 19 (CUSTOM_SIMPLE_EDGE)
+Reducer 17 <- Reducer 16 (SIMPLE_EDGE)
Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE)
-Reducer 22 <- Map 21 (CUSTOM_SIMPLE_EDGE), Map 24 (CUSTOM_SIMPLE_EDGE), Map 25 (CUSTOM_SIMPLE_EDGE)
+Reducer 21 <- Map 20 (SIMPLE_EDGE), Map 24 (SIMPLE_EDGE)
+Reducer 22 <- Reducer 21 (CUSTOM_SIMPLE_EDGE), Reducer 27 (CUSTOM_SIMPLE_EDGE)
Reducer 23 <- Reducer 22 (SIMPLE_EDGE)
-Reducer 27 <- Map 26 (SIMPLE_EDGE), Map 31 (SIMPLE_EDGE)
-Reducer 28 <- Reducer 27 (SIMPLE_EDGE), Reducer 34 (SIMPLE_EDGE)
-Reducer 29 <- Reducer 28 (CUSTOM_SIMPLE_EDGE), Reducer 39 (CUSTOM_SIMPLE_EDGE)
+Reducer 26 <- Map 25 (CUSTOM_SIMPLE_EDGE), Map 28 (CUSTOM_SIMPLE_EDGE), Map 29 (CUSTOM_SIMPLE_EDGE)
+Reducer 27 <- Reducer 26 (SIMPLE_EDGE)
Reducer 3 <- Map 9 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE)
-Reducer 30 <- Reducer 29 (SIMPLE_EDGE)
-Reducer 33 <- Map 32 (CUSTOM_SIMPLE_EDGE), Map 35 (CUSTOM_SIMPLE_EDGE), Map 36 (CUSTOM_SIMPLE_EDGE)
-Reducer 34 <- Reducer 33 (SIMPLE_EDGE)
-Reducer 38 <- Map 37 (CUSTOM_SIMPLE_EDGE), Map 40 (CUSTOM_SIMPLE_EDGE), Map 41 (CUSTOM_SIMPLE_EDGE)
-Reducer 39 <- Reducer 38 (SIMPLE_EDGE)
-Reducer 4 <- Reducer 14 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE), Reducer 30 (SIMPLE_EDGE)
-Reducer 43 <- Map 42 (SIMPLE_EDGE), Map 47 (SIMPLE_EDGE)
-Reducer 44 <- Reducer 43 (SIMPLE_EDGE), Reducer 50 (SIMPLE_EDGE)
-Reducer 45 <- Reducer 44 (CUSTOM_SIMPLE_EDGE), Reducer 55 (CUSTOM_SIMPLE_EDGE)
-Reducer 46 <- Reducer 45 (SIMPLE_EDGE)
-Reducer 49 <- Map 48 (CUSTOM_SIMPLE_EDGE), Map 51 (CUSTOM_SIMPLE_EDGE), Map 52 (CUSTOM_SIMPLE_EDGE)
-Reducer 5 <- Reducer 4 (SIMPLE_EDGE), Reducer 46 (SIMPLE_EDGE)
-Reducer 50 <- Reducer 49 (SIMPLE_EDGE)
-Reducer 54 <- Map 53 (CUSTOM_SIMPLE_EDGE), Map 56 (CUSTOM_SIMPLE_EDGE), Map 57 (CUSTOM_SIMPLE_EDGE)
-Reducer 55 <- Reducer 54 (SIMPLE_EDGE)
+Reducer 31 <- Map 30 (SIMPLE_EDGE), Map 34 (SIMPLE_EDGE)
+Reducer 32 <- Reducer 31 (CUSTOM_SIMPLE_EDGE), Reducer 37 (CUSTOM_SIMPLE_EDGE)
+Reducer 33 <- Reducer 32 (SIMPLE_EDGE)
+Reducer 36 <- Map 35 (CUSTOM_SIMPLE_EDGE), Map 38 (CUSTOM_SIMPLE_EDGE), Map 39 (CUSTOM_SIMPLE_EDGE)
+Reducer 37 <- Reducer 36 (SIMPLE_EDGE)
+Reducer 4 <- Reducer 13 (SIMPLE_EDGE), Reducer 23 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE)
+Reducer 5 <- Reducer 33 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE)
Reducer 6 <- Reducer 5 (SIMPLE_EDGE)
Reducer 7 <- Reducer 6 (SIMPLE_EDGE)
@@ -136,360 +124,259 @@ Stage-0
limit:100
Stage-1
Reducer 7
- File Output Operator [FS_184]
- Limit [LIM_183] (rows=100 width=1)
+ File Output Operator [FS_130]
+ Limit [LIM_129] (rows=100 width=1)
Number of rows:100
- Select Operator [SEL_182] (rows=1268213682555322368 width=1)
+ Select Operator [SEL_128] (rows=1268213682555322368 width=1)
Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"]
<-Reducer 6 [SIMPLE_EDGE]
- SHUFFLE [RS_181]
- Select Operator [SEL_180] (rows=1268213682555322368 width=1)
+ SHUFFLE [RS_127]
+ Select Operator [SEL_126] (rows=1268213682555322368 width=1)
Output:["_col0","_col1","_col2","_col3","_col4","_col6"]
- Group By Operator [GBY_179] (rows=1268213682555322368 width=1)
+ Group By Operator [GBY_125] (rows=1268213682555322368 width=1)
Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4
<-Reducer 5 [SIMPLE_EDGE]
- SHUFFLE [RS_178]
+ SHUFFLE [RS_124]
PartitionCols:_col0, _col1, _col2, _col3, _col4
- Group By Operator [GBY_177] (rows=2536427365110644736 width=1)
+ Group By Operator [GBY_123] (rows=2536427365110644736 width=1)
Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["count()"],keys:_col6, _col7, _col8, _col9, _col10
- Select Operator [SEL_176] (rows=2536427365110644736 width=1)
+ Select Operator [SEL_122] (rows=2536427365110644736 width=1)
Output:["_col6","_col7","_col8","_col9","_col10"]
- Filter Operator [FIL_175] (rows=2536427365110644736 width=1)
+ Filter Operator [FIL_121] (rows=2536427365110644736 width=1)
predicate:_col15 is null
- Merge Join Operator [MERGEJOIN_279] (rows=5072854730221289472 width=1)
- Conds:RS_172._col0=RS_173._col0(Left Outer),Output:["_col6","_col7","_col8","_col9","_col10","_col15"]
+ Merge Join Operator [MERGEJOIN_189] (rows=5072854730221289472 width=1)
+ Conds:RS_118._col0=RS_119._col0(Left Outer),Output:["_col6","_col7","_col8","_col9","_col10","_col15"]
+ <-Reducer 33 [SIMPLE_EDGE]
+ SHUFFLE [RS_119]
+ PartitionCols:_col0
+ Select Operator [SEL_117] (rows=4611686018427387903 width=1)
+ Output:["_col0","_col1"]
+ Group By Operator [GBY_116] (rows=4611686018427387903 width=1)
+ Output:["_col0"],keys:KEY._col0
+ <-Reducer 32 [SIMPLE_EDGE]
+ SHUFFLE [RS_115]
+ PartitionCols:_col0
+ Group By Operator [GBY_114] (rows=9223372036854775807 width=1)
+ Output:["_col0"],keys:_col5
+ Merge Join Operator [MERGEJOIN_188] (rows=9223372036854775807 width=1)
+ Conds:(Inner),Output:["_col5"]
+ <-Reducer 31 [CUSTOM_SIMPLE_EDGE]
+ PARTITION_ONLY_SHUFFLE [RS_110]
+ Merge Join Operator [MERGEJOIN_184] (rows=158394413 width=135)
+ Conds:RS_107._col0=RS_108._col0(Inner)
+ <-Map 30 [SIMPLE_EDGE]
+ SHUFFLE [RS_107]
+ PartitionCols:_col0
+ Select Operator [SEL_88] (rows=143994918 width=135)
+ Output:["_col0"]
+ Filter Operator [FIL_174] (rows=143994918 width=135)
+ predicate:((cs_ship_customer_sk = cs_ship_customer_sk) and cs_sold_date_sk is not null)
+ TableScan [TS_86] (rows=287989836 width=135)
+ default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:NONE,Output:["cs_sold_date_sk","cs_ship_customer_sk"]
+ <-Map 34 [SIMPLE_EDGE]
+ SHUFFLE [RS_108]
+ PartitionCols:_col0
+ Select Operator [SEL_91] (rows=4058 width=1119)
+ Output:["_col0"]
+ Filter Operator [FIL_175] (rows=4058 width=1119)
+ predicate:((d_year = 1999) and d_moy BETWEEN 1 AND 3 and d_date_sk is not null)
+ TableScan [TS_89] (rows=73049 width=1119)
+ default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year","d_moy"]
+ <-Reducer 37 [CUSTOM_SIMPLE_EDGE]
+ PARTITION_ONLY_SHUFFLE [RS_111]
+ Group By Operator [GBY_105] (rows=4611686018427387903 width=1)
+ Output:["_col0"],keys:KEY._col0
+ <-Reducer 36 [SIMPLE_EDGE]
+ SHUFFLE [RS_104]
+ PartitionCols:_col0
+ Group By Operator [GBY_103] (rows=9223372036854775807 width=1)
+ Output:["_col0"],keys:_col2
+ Merge Join Operator [MERGEJOIN_179] (rows=9223372036854775807 width=1)
+ Conds:(Inner),(Inner),Output:["_col2"]
+ <-Map 35 [CUSTOM_SIMPLE_EDGE]
+ PARTITION_ONLY_SHUFFLE [RS_98]
+ Select Operator [SEL_93] (rows=40000000 width=4)
+ TableScan [TS_92] (rows=40000000 width=1014)
+ default@customer_address,ca,Tbl:COMPLETE,Col:COMPLETE
+ <-Map 38 [CUSTOM_SIMPLE_EDGE]
+ PARTITION_ONLY_SHUFFLE [RS_99]
+ Select Operator [SEL_95] (rows=1861800 width=4)
+ TableScan [TS_94] (rows=1861800 width=385)
+ default@customer_demographics,customer_demographics,Tbl:COMPLETE,Col:COMPLETE
+ <-Map 39 [CUSTOM_SIMPLE_EDGE]
+ PARTITION_ONLY_SHUFFLE [RS_100]
+ Select Operator [SEL_97] (rows=80000000 width=860)
+ Output:["_col0"]
+ TableScan [TS_96] (rows=80000000 width=860)
+ default@customer,c,Tbl:COMPLETE,Col:NONE,Output:["c_customer_sk"]
<-Reducer 4 [SIMPLE_EDGE]
- SHUFFLE [RS_172]
+ SHUFFLE [RS_118]
PartitionCols:_col0
- Select Operator [SEL_121] (rows=4611686018427387903 width=1)
+ Select Operator [SEL_85] (rows=4611686018427387903 width=1)
Output:["_col0","_col10","_col6","_col7","_col8","_col9"]
- Filter Operator [FIL_120] (rows=4611686018427387903 width=1)
+ Filter Operator [FIL_84] (rows=4611686018427387903 width=1)
predicate:_col13 is null
- Select Operator [SEL_119] (rows=9223372036854775807 width=1)
- Output:["_col0","_col6","_col7","_col8","_col9","_col10","_col13"]
- Merge Join Operator [MERGEJOIN_276] (rows=9223372036854775807 width=1)
- Conds:RS_115._col0=RS_116._col0(Left Outer),RS_115._col0=RS_117._col0(Inner),Output:["_col0","_col6","_col7","_col8","_col9","_col10","_col12"]
- <-Reducer 14 [SIMPLE_EDGE]
- SHUFFLE [RS_116]
- PartitionCols:_col0
- Select Operator [SEL_58] (rows=4611686018427387903 width=1)
- Output:["_col0","_col1"]
- Group By Operator [GBY_57] (rows=4611686018427387903 width=1)
- Output:["_col0"],keys:KEY._col0
- <-Reducer 13 [SIMPLE_EDGE]
- SHUFFLE [RS_56]
- PartitionCols:_col0
- Group By Operator [GBY_55] (rows=9223372036854775807 width=1)
- Output:["_col0"],keys:_col6
- Merge Join Operator [MERGEJOIN_273] (rows=9223372036854775807 width=1)
- Conds:(Inner),Output:["_col6"]
- <-Reducer 12 [CUSTOM_SIMPLE_EDGE]
- PARTITION_ONLY_SHUFFLE [RS_51]
- Merge Join Operator [MERGEJOIN_272] (rows=5072854730221289472 width=1)
- Conds:RS_48._col1=RS_49._col0(Inner)
- <-Reducer 11 [SIMPLE_EDGE]
- SHUFFLE [RS_48]
- PartitionCols:_col1
- Merge Join Operator [MERGEJOIN_269] (rows=158402938 width=135)
- Conds:RS_45._col0=RS_46._col0(Inner),Output:["_col1"]
- <-Map 10 [SIMPLE_EDGE]
- SHUFFLE [RS_45]
- PartitionCols:_col0
- Select Operator [SEL_11] (rows=144002668 width=135)
- Output:["_col0","_col1"]
- Filter Operator [FIL_249] (rows=144002668 width=135)
- predicate:ws_sold_date_sk is not null
- TableScan [TS_9] (rows=144002668 width=135)
- default@web_sales,web_sales,Tbl:COMPLETE,Col:NONE,Output:["ws_sold_date_sk","ws_bill_customer_sk"]
- <-Map 15 [SIMPLE_EDGE]
- SHUFFLE [RS_46]
- PartitionCols:_col0
- Select Operator [SEL_14] (rows=4058 width=1119)
- Output:["_col0"]
- Filter Operator [FIL_250] (rows=4058 width=1119)
- predicate:((d_year = 1999) and d_moy BETWEEN 1 AND 3 and d_date_sk is not null)
- TableScan [TS_12] (rows=73049 width=1119)
- default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year","d_moy"]
- <-Reducer 18 [SIMPLE_EDGE]
- SHUFFLE [RS_49]
- PartitionCols:_col0
- Group By Operator [GBY_28] (rows=4611686018427387903 width=1)
- Output:["_col0"],keys:KEY._col0
- <-Reducer 17 [SIMPLE_EDGE]
- SHUFFLE [RS_27]
- PartitionCols:_col0
- Group By Operator [GBY_26] (rows=9223372036854775807 width=1)
- Output:["_col0"],keys:_col2
- Merge Join Operator [MERGEJOIN_261] (rows=9223372036854775807 width=1)
- Conds:(Inner),(Inner),Output:["_col2"]
- <-Map 16 [CUSTOM_SIMPLE_EDGE]
- PARTITION_ONLY_SHUFFLE [RS_21]
- Select Operator [SEL_16] (rows=40000000 width=4)
- TableScan [TS_15] (rows=40000000 width=1014)
- default@customer_address,ca,Tbl:COMPLETE,Col:COMPLETE
- <-Map 19 [CUSTOM_SIMPLE_EDGE]
- PARTITION_ONLY_SHUFFLE [RS_22]
- Select Operator [SEL_18] (rows=1861800 width=4)
- TableScan [TS_17] (rows=1861800 width=385)
- default@customer_demographics,customer_demographics,Tbl:COMPLETE,Col:COMPLETE
- <-Map 20 [CUSTOM_SIMPLE_EDGE]
- PARTITION_ONLY_SHUFFLE [RS_23]
- Select Operator [SEL_20] (rows=80000000 width=860)
- Output:["_col0"]
- TableScan [TS_19] (rows=80000000 width=860)
- default@customer,c,Tbl:COMPLETE,Col:NONE,Output:["c_customer_sk"]
- <-Reducer 23 [CUSTOM_SIMPLE_EDGE]
- PARTITION_ONLY_SHUFFLE [RS_52]
- Group By Operator [GBY_43] (rows=4611686018427387903 width=1)
- Output:["_col0"],keys:KEY._col0
- <-Reducer 22 [SIMPLE_EDGE]
- SHUFFLE [RS_42]
- PartitionCols:_col0
- Group By Operator [GBY_41] (rows=9223372036854775807 width=1)
- Output:["_col0"],keys:_col2
- Merge Join Operator [MERGEJOIN_262] (rows=9223372036854775807 width=1)
- Conds:(Inner),(Inner),Output:["_col2"]
- <-Map 21 [CUSTOM_SIMPLE_EDGE]
- PARTITION_ONLY_SHUFFLE [RS_36]
- Select Operator [SEL_31] (rows=40000000 width=4)
- TableScan [TS_30] (rows=40000000 width=1014)
- default@customer_address,ca,Tbl:COMPLETE,Col:COMPLETE
- <-Map 24 [CUSTOM_SIMPLE_EDGE]
- PARTITION_ONLY_SHUFFLE [RS_37]
- Select Operator [SEL_33] (rows=1861800 width=4)
- TableScan [TS_32] (rows=1861800 width=385)
- default@customer_demographics,customer_demographics,Tbl:COMPLETE,Col:COMPLETE
- <-Map 25 [CUSTOM_SIMPLE_EDGE]
- PARTITION_ONLY_SHUFFLE [RS_38]
- Select Operator [SEL_35] (rows=80000000 width=860)
- Output:["_col0"]
- TableScan [TS_34] (rows=80000000 width=860)
- default@customer,c,Tbl:COMPLETE,Col:NONE,Output:["c_customer_sk"]
- <-Reducer 3 [SIMPLE_EDGE]
- SHUFFLE [RS_115]
- PartitionCols:_col0
- Merge Join Operator [MERGEJOIN_268] (rows=96800003 width=860)
- Conds:RS_112._col1=RS_113._col0(Inner),Output:["_col0","_col6","_col7","_col8","_col9","_col10"]
- <-Map 9 [SIMPLE_EDGE]
- SHUFFLE [RS_113]
- PartitionCols:_col0
- Select Operator [SEL_8] (rows=1861800 width=385)
- Output:["_col0","_col1","_col2","_col3","_col4","_col5"]
- Filter Operator [FIL_248] (rows=1861800 width=385)
- predicate:cd_demo_sk is not null
- TableScan [TS_6] (rows=1861800 width=385)
- default@customer_demographics,customer_demographics,Tbl:COMPLETE,Col:NONE,Output:["cd_demo_sk","cd_gender","cd_marital_status","cd_education_status","cd_purchase_estimate","cd_credit_rating"]
- <-Reducer 2 [SIMPLE_EDGE]
- SHUFFLE [RS_112]
- PartitionCols:_col1
- Merge Join Operator [MERGEJOIN_267] (rows=88000001 width=860)
- Conds:RS_109._col2=RS_110._col0(Inner),Output:["_col0","_col1"]
- <-Map 1 [SIMPLE_EDGE]
- SHUFFLE [RS_109]
- PartitionCols:_col2
- Select Operator [SEL_2] (rows=80000000 width=860)
- Output:["_col0","_col1","_col2"]
- Filter Operator [FIL_246] (rows=80000000 width=860)
- predicate:(c_current_addr_sk is not null and c_current_cdemo_sk is not null)
- TableScan [TS_0] (rows=80000000 width=860)
- default@customer,c,Tbl:COMPLETE,Col:NONE,Output:["c_customer_sk","c_current_cdemo_sk","c_current_addr_sk"]
- <-Map 8 [SIMPLE_EDGE]
- SHUFFLE [RS_110]
- PartitionCols:_col0
- Select Operator [SEL_5] (rows=20000000 width=1014)
- Output:["_col0"]
- Filter Operator [FIL_247] (rows=20000000 width=1014)
- predicate:((ca_state) IN ('CO', 'IL', 'MN') and ca_address_sk is not null)
- TableScan [TS_3] (rows=40000000 width=1014)
- default@customer_address,ca,Tbl:COMPLETE,Col:NONE,Output:["ca_address_sk","ca_state"]
- <-Reducer 30 [SIMPLE_EDGE]
- SHUFFLE [RS_117]
- PartitionCols:_col0
- Group By Operator [GBY_107] (rows=4611686018427387903 width=1)
+ Merge Join Operator [MERGEJOIN_187] (rows=9223372036854775807 width=1)
+ Conds:RS_79._col0=RS_80._col0(Inner),RS_79._col0=RS_81._col0(Left Outer),Output:["_col0","_col6","_col7","_col8","_col9","_col10","_col13"]
+ <-Reducer 13 [SIMPLE_EDGE]
+ SHUFFLE [RS_80]
+ PartitionCols:_col0
+ Group By Operator [GBY_39] (rows=4611686018427387903 width=1)
+ Output:["_col0"],keys:KEY._col0
+ <-Reducer 12 [SIMPLE_EDGE]
+ SHUFFLE [RS_38]
+ PartitionCols:_col0
+ Group By Operator [GBY_37] (rows=9223372036854775807 width=1)
+ Output:["_col0"],keys:_col5
+ Merge Join Operator [MERGEJOIN_185] (rows=9223372036854775807 width=1)
+ Conds:(Inner),Output:["_col5"]
+ <-Reducer 11 [CUSTOM_SIMPLE_EDGE]
+ PARTITION_ONLY_SHUFFLE [RS_33]
+ Merge Join Operator [MERGEJOIN_182] (rows=316797605 width=88)
+ Conds:RS_30._col0=RS_31._col0(Inner)
+ <-Map 10 [SIMPLE_EDGE]
+ SHUFFLE [RS_30]
+ PartitionCols:_col0
+ Select Operator [SEL_11] (rows=287997817 width=88)
+ Output:["_col0"]
+ Filter Operator [FIL_168] (rows=287997817 width=88)
+ predicate:((ss_customer_sk = ss_customer_sk) and ss_sold_date_sk is not null)
+ TableScan [TS_9] (rows=575995635 width=88)
+ default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_customer_sk"]
+ <-Map 14 [SIMPLE_EDGE]
+ SHUFFLE [RS_31]
+ PartitionCols:_col0
+ Select Operator [SEL_14] (rows=4058 width=1119)
+ Output:["_col0"]
+ Filter Operator [FIL_169] (rows=4058 width=1119)
+ predicate:((d_year = 1999) and d_moy BETWEEN 1 AND 3 and d_date_sk is not null)
+ TableScan [TS_12] (rows=73049 width=1119)
+ default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year","d_moy"]
+ <-Reducer 17 [CUSTOM_SIMPLE_EDGE]
+ PARTITION_ONLY_SHUFFLE [RS_34]
+ Group By Operator [GBY_28] (rows=4611686018427387903 width=1)
+ Output:["_col0"],keys:KEY._col0
+ <-Reducer 16 [SIMPLE_EDGE]
+ SHUFFLE [RS_27]
+ PartitionCols:_col0
+ Group By Operator [GBY_26] (rows=9223372036854775807 width=1)
+ Output:["_col0"],keys:_col2
+ Merge Join Operator [MERGEJOIN_177] (rows=9223372036854775807 width=1)
+ Conds:(Inner),(Inner),Output:["_col2"]
+ <-Map 15 [CUSTOM_SIMPLE_EDGE]
+ PARTITION_ONLY_SHUFFLE [RS_21]
+ Select Operator [SEL_16] (rows=40000000 width=4)
+ TableScan [TS_15] (rows=40000000 width=1014)
+ default@customer_address,ca,Tbl:COMPLETE,Col:COMPLETE
+ <-Map 18 [CUSTOM_SIMPLE_EDGE]
+ PARTITION_ONLY_SHUFFLE [RS_22]
+ Select Operator [SEL_18] (rows=1861800 width=4)
+ TableScan [TS_17] (rows=1861800 width=385)
+ default@customer_demographics,customer_demographics,Tbl:COMPLETE,Col:COMPLETE
+ <-Map 19 [CUSTOM_SIMPLE_EDGE]
+ PARTITION_ONLY_SHUFFLE [RS_23]
+ Select Operator [SEL_20] (rows=80000000 width=860)
+ Output:["_col0"]
+ TableScan [TS_19] (rows=80000000 width=860)
+ default@customer,c,Tbl:COMPLETE,Col:NONE,Output:["c_customer_sk"]
+ <-Reducer 23 [SIMPLE_EDGE]
+ SHUFFLE [RS_81]
+ PartitionCols:_col0
+ Select Operator [SEL_72] (rows=4611686018427387903 width=1)
+ Output:["_col0","_col1"]
+ Group By Operator [GBY_71] (rows=4611686018427387903 width=1)
Output:["_col0"],keys:KEY._col0
- <-Reducer 29 [SIMPLE_EDGE]
- SHUFFLE [RS_106]
+ <-Reducer 22 [SIMPLE_EDGE]
+ SHUFFLE [RS_70]
PartitionCols:_col0
- Group By Operator [GBY_105] (rows=9223372036854775807 width=1)
- Output:["_col0"],keys:_col6
- Merge Join Operator [MERGEJOIN_275] (rows=9223372036854775807 width=1)
- Conds:(Inner),Output:["_col6"]
- <-Reducer 28 [CUSTOM_SIMPLE_EDGE]
- PARTITION_ONLY_SHUFFLE [RS_101]
- Merge Join Operator [MERGEJOIN_274] (rows=5072854730221289472 width=1)
- Conds:RS_98._col1=RS_99._col0(Inner)
- <-Reducer 27 [SIMPLE_EDGE]
- SHUFFLE [RS_98]
- PartitionCols:_col1
- Merge Join Operator [MERGEJOIN_270] (rows=633595212 width=88)
- Conds:RS_95._col0=RS_96._col0(Inner),Output:["_col1"]
- <-Map 26 [SIMPLE_EDGE]
- SHUFFLE [RS_95]
- PartitionCols:_col0
- Select Operator [SEL_61] (rows=575995635 width=88)
- Output:["_col0","_col1"]
- Filter Operator [FIL_253] (rows=575995635 width=88)
- predicate:ss_sold_date_sk is not null
- TableScan [TS_59] (rows=575995635 width=88)
- default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_customer_sk"]
- <-Map 31 [SIMPLE_EDGE]
- SHUFFLE [RS_96]
- PartitionCols:_col0
- Select Operator [SEL_64] (rows=4058 width=1119)
- Output:["_col0"]
- Filter Operator [FIL_254] (rows=4058 width=1119)
- predicate:((d_year = 1999) and d_moy BETWEEN 1 AND 3 and d_date_sk is not null)
- TableScan [TS_62] (rows=73049 width=1119)
- default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year","d_moy"]
- <-Reducer 34 [SIMPLE_EDGE]
- SHUFFLE [RS_99]
+ Group By Operator [GBY_69] (rows=9223372036854775807 width=1)
+ Output:["_col0"],keys:_col5
+ Merge Join Operator [MERGEJOIN_186] (rows=9223372036854775807 width=1)
+ Conds:(Inner),Output:["_col5"]
+ <-Reducer 21 [CUSTOM_SIMPLE_EDGE]
+ PARTITION_ONLY_SHUFFLE [RS_65]
+ Merge Join Operator [MERGEJOIN_183] (rows=79201469 width=135)
+ Conds:RS_62._col0=RS_63._col0(Inner)
+ <-Map 20 [SIMPLE_EDGE]
+ SHUFFLE [RS_62]
+ PartitionCols:_col0
+ Select Operator [SEL_43] (rows=72001334 width=135)
+ Output:["_col0"]
+ Filter Operator [FIL_171] (rows=72001334 width=135)
+ predicate:((ws_bill_customer_sk = ws_bill_customer_sk) and ws_sold_date_sk is not null)
+ TableScan [TS_41] (rows=144002668 width=135)
+ default@web_sales,web_sales,Tbl:COMPLETE,Col:NONE,Output:["ws_sold_date_sk","ws_bill_customer_sk"]
+ <-Map 24 [SIMPLE_EDGE]
+ SHUFFLE [RS_63]
PartitionCols:_col0
- Group By Operator [GBY_78] (rows=4611686018427387903 width=1)
- Output:["_col0"],keys:KEY._col0
- <-Reducer 33 [SIMPLE_EDGE]
- SHUFFLE [RS_77]
- PartitionCols:_col0
- Group By Operator [GBY_76] (rows=9223372036854775807 width=1)
- Output:["_col0"],keys:_col2
- Merge Join Operator [MERGEJOIN_263] (rows=9223372036854775807 width=1)
- Conds:(Inner),(Inner),Output:["_col2"]
- <-Map 32 [CUSTOM_SIMPLE_EDGE]
- PARTITION_ONLY_SHUFFLE [RS_71]
- Select Operator [SEL_66] (rows=40000000 width=4)
- TableScan [TS_65] (rows=40000000 width=1014)
- default@customer_address,ca,Tbl:COMPLETE,Col:COMPLETE
- <-Map 35 [CUSTOM_SIMPLE_EDGE]
- PARTITION_ONLY_SHUFFLE [RS_72]
- Select Operator [SEL_68] (rows=1861800 width=4)
- TableScan [TS_67] (rows=1861800 width=385)
- default@customer_demographics,customer_demographics,Tbl:COMPLETE,Col:COMPLETE
- <-Map 36 [CUSTOM_SIMPLE_EDGE]
- PARTITION_ONLY_SHUFFLE [RS_73]
- Select Operator [SEL_70] (rows=80000000 width=860)
- Output:["_col0"]
- TableScan [TS_69] (rows=80000000 width=860)
- default@customer,c,Tbl:COMPLETE,Col:NONE,Output:["c_customer_sk"]
- <-Reducer 39 [CUSTOM_SIMPLE_EDGE]
- PARTITION_ONLY_SHUFFLE [RS_102]
- Group By Operator [GBY_93] (rows=4611686018427387903 width=1)
+ Select Operator [SEL_46] (rows=4058 width=1119)
+ Output:["_col0"]
+ Filter Operator [FIL_172] (rows=4058 width=1119)
+ predicate:((d_year = 1999) and d_moy BETWEEN 1 AND 3 and d_date_sk is not null)
+ TableScan [TS_44] (rows=73049 width=1119)
+ default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year","d_moy"]
+ <-Reducer 27 [CUSTOM_SIMPLE_EDGE]
+ PARTITION_ONLY_SHUFFLE [RS_66]
+ Group By Operator [GBY_60] (rows=4611686018427387903 width=1)
Output:["_col0"],keys:KEY._col0
- <-Reducer 38 [SIMPLE_EDGE]
- SHUFFLE [RS_92]
+ <-Reducer 26 [SIMPLE_EDGE]
+ SHUFFLE [RS_59]
PartitionCols:_col0
- Group By Operator [GBY_91] (rows=9223372036854775807 width=1)
+ Group By Operator [GBY_58] (rows=9223372036854775807 width=1)
Output:["_col0"],keys:_col2
- Merge Join Operator [MERGEJOIN_264] (rows=9223372036854775807 width=1)
+ Merge Join Operator [MERGEJOIN_178] (rows=9223372036854775807 width=1)
Conds:(Inner),(Inner),Output:["_col2"]
- <-Map 37 [CUSTOM_SIMPLE_EDGE]
- PARTITION_ONLY_SHUFFLE [RS_86]
- Select Operator [SEL_81] (rows=40000000 width=4)
- TableScan [TS_80] (rows=40000000 width=1014)
+ <-Map 25 [CUSTOM_SIMPLE_EDGE]
+ PARTITION_ONLY_SHUFFLE [RS_53]
+ Select Operator [SEL_48] (rows=40000000 width=4)
+ TableScan [TS_47] (rows=40000000 width=1014)
default@customer_address,ca,Tbl:COMPLETE,Col:COMPLETE
- <-Map 40 [CUSTOM_SIMPLE_EDGE]
- PARTITION_ONLY_SHUFFLE [RS_87]
- Select Operator [SEL_83] (rows=1861800 width=4)
- TableScan [TS_82] (rows=1861800 width=385)
+ <-Map 28 [CUSTOM_SIMPLE_EDGE]
+ PARTITION_ONLY_SHUFFLE [RS_54]
+ Select Operator [SEL_50] (rows=1861800 width=4)
+ TableScan [TS_49] (rows=1861800 width=385)
default@customer_demographics,customer_demographics,Tbl:COMPLETE,Col:COMPLETE
- <-Map 41 [CUSTOM_SIMPLE_EDGE]
- PARTITION_ONLY_SHUFFLE [RS_88]
- Select Operator [SEL_85] (rows=80000000 width=860)
+ <-Map 29 [CUSTOM_SIMPLE_EDGE]
+ PARTITION_ONLY_SHUFFLE [RS_55]
+ Select Operator [SEL_52] (rows=80000000 width=860)
Output:["_col0"]
- TableScan [TS_84] (rows=80000000 width=860)
+ TableScan [TS_51] (rows=80000000 width=860)
default@customer,c,Tbl:COMPLETE,Col:NONE,Output:["c_customer_sk"]
- <-Reducer 46 [SIMPLE_EDGE]
- SHUFFLE [RS_173]
- PartitionCols:_col0
- Select Operator [SEL_171] (rows=4611686018427387903 width=1)
- Output:["_col0","_col1"]
- Group By Operator [GBY_170] (rows=4611686018427387903 width=1)
- Output:["_col0"],keys:KEY._col0
- <-Reducer 45 [SIMPLE_EDGE]
- SHUFFLE [RS_169]
- PartitionCols:_col0
- Group By Operator [GBY_168] (rows=9223372036854775807 width=1)
- Output:["_col0"],keys:_col6
- Merge Join Operator [MERGEJOIN_278] (rows=9223372036854775807 width=1)
- Conds:(Inner),Output:["_col6"]
- <-Reducer 44 [CUSTOM_SIMPLE_EDGE]
- PARTITION_ONLY_SHUFFLE [RS_164]
- Merge Join Operator [MERGEJOIN_277] (rows=5072854730221289472 width=1)
- Conds:RS_161._col1=RS_162._col0(Inner)
- <-Reducer 43 [SIMPLE_EDGE]
- SHUFFLE [RS_161]
- PartitionCols:_col1
- Merge Join Operator [MERGEJOIN_271] (rows=316788826 width=135)
- Conds:RS_158._col0=RS_159._col0(Inner),Output:["_col1"]
- <-Map 42 [SIMPLE_EDGE]
- SHUFFLE [RS_158]
- PartitionCols:_col0
- Select Operator [SEL_124] (rows=287989836 width=135)
- Output:["_col0","_col1"]
- Filter Operator [FIL_257] (rows=287989836 width=135)
- predicate:cs_sold_date_sk is not null
- TableScan [TS_122] (rows=287989836 width=135)
- default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:NONE,Output:["cs_sold_date_sk","cs_ship_customer_sk"]
- <-Map 47 [SIMPLE_EDGE]
- SHUFFLE [RS_159]
- PartitionCols:_col0
- Select Operator [SEL_127] (rows=4058 width=1119)
- Output:["_col0"]
- Filter Operator [FIL_258] (rows=4058 width=1119)
- predicate:((d_year = 1999) and d_moy BETWEEN 1 AND 3 and d_date_sk is not null)
- TableScan [TS_125] (rows=73049 width=1119)
- default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year","d_moy"]
- <-Reducer 50 [SIMPLE_EDGE]
- SHUFFLE [RS_162]
+ <-Reducer 3 [SIMPLE_EDGE]
+ SHUFFLE [RS_79]
+ PartitionCols:_col0
+ Merge Join Operator [MERGEJOIN_181] (rows=96800003 width=860)
+ Conds:RS_76._col1=RS_77._col0(Inner),Output:["_col0","_col6","_col7","_col8","_col9","_col10"]
+ <-Map 9 [SIMPLE_EDGE]
+ SHUFFLE [RS_77]
+ PartitionCols:_col0
+ Select Operator [SEL_8] (rows=1861800 width=385)
+ Output:["_col0","_col1","_col2","_col3","_col4","_col5"]
+ Filter Operator [FIL_167] (rows=1861800 width=385)
+ predicate:cd_demo_sk is not null
+ TableScan [TS_6] (rows=1861800 width=385)
+ default@customer_demographics,customer_demographics,Tbl:COMPLETE,Col:NONE,Output:["cd_demo_sk","cd_gender","cd_marital_status","cd_education_status","cd_purchase_estimate","cd_credit_rating"]
+ <-Reducer 2 [SIMPLE_EDGE]
+ SHUFFLE [RS_76]
+ PartitionCols:_col1
+ Merge Join Operator [MERGEJOIN_180] (rows=88000001 width=860)
+ Conds:RS_73._col2=RS_74._col0(Inner),Output:["_col0","_col1"]
+ <-Map 1 [SIMPLE_EDGE]
+ SHUFFLE [RS_73]
+ PartitionCols:_col2
+ Select Operator [SEL_2] (rows=80000000 width=860)
+ Output:["_col0","_col1","_col2"]
+ Filter Operator [FIL_165] (rows=80000000 width=860)
+ predicate:(c_current_addr_sk is not null and c_current_cdemo_sk is not null)
+ TableScan [TS_0] (rows=80000000 width=860)
+ default@customer,c,Tbl:COMPLETE,Col:NONE,Output:["c_customer_sk","c_current_cdemo_sk","c_current_addr_sk"]
+ <-Map 8 [SIMPLE_EDGE]
+ SHUFFLE [RS_74]
PartitionCols:_col0
- Group By Operator [GBY_141] (rows=4611686018427387903 width=1)
- Output:["_col0"],keys:KEY._col0
- <-Reducer 49 [SIMPLE_EDGE]
- SHUFFLE [RS_140]
- PartitionCols:_col0
- Group By Operator [GBY_139] (rows=9223372036854775807 width=1)
- Output:["_col0"],keys:_col2
- Merge Join Operator [MERGEJOIN_265] (rows=9223372036854775807 width=1)
- Conds:(Inner),(Inner),Output:["_col2"]
- <-Map 48 [CUSTOM_SIMPLE_EDGE]
- PARTITION_ONLY_SHUFFLE [RS_134]
- Select Operator [SEL_129] (rows=40000000 width=4)
- TableScan [TS_128] (rows=40000000 width=1014)
- default@customer_address,ca,Tbl:COMPLETE,Col:COMPLETE
- <-Map 51 [CUSTOM_SIMPLE_EDGE]
- PARTITION_ONLY_SHUFFLE [RS_135]
- Select Operator [SEL_131] (rows=1861800 width=4)
- TableScan [TS_130] (rows=1861800 width=385)
- default@customer_demographics,customer_demographics,Tbl:COMPLETE,Col:COMPLETE
- <-Map 52 [CUSTOM_SIMPLE_EDGE]
- PARTITION_ONLY_SHUFFLE [RS_136]
- Select Operator [SEL_133] (rows=80000000 width=860)
- Output:["_col0"]
- TableScan [TS_132] (rows=80000000 width=860)
- default@customer,c,Tbl:COMPLETE,Col:NONE,Output:["c_customer_sk"]
- <-Reducer 55 [CUSTOM_SIMPLE_EDGE]
- PARTITION_ONLY_SHUFFLE [RS_165]
- Group By Operator [GBY_156] (rows=4611686018427387903 width=1)
- Output:["_col0"],keys:KEY._col0
- <-Reducer 54 [SIMPLE_EDGE]
- SHUFFLE [RS_155]
- PartitionCols:_col0
- Group By Operator [GBY_154] (rows=9223372036854775807 width=1)
- Output:["_col0"],keys:_col2
- Merge Join Operator [MERGEJOIN_266] (rows=9223372036854775807 width=1)
- Conds:(Inner),(Inner),Output:["_col2"]
- <-Map 53 [CUSTOM_SIMPLE_EDGE]
- PARTITION_ONLY_SHUFFLE [RS_149]
- Select Operator [SEL_144] (rows=40000000 width=4)
- TableScan [TS_143] (rows=40000000 width=1014)
- default@customer_address,ca,Tbl:COMPLETE,Col:COMPLETE
- <-Map 56 [CUSTOM_SIMPLE_EDGE]
- PARTITION_ONLY_SHUFFLE [RS_150]
- Select Operator [SEL_146] (rows=1861800 width=4)
- TableScan [TS_145] (rows=1861800 width=385)
- default@customer_demographics,customer_demographics,Tbl:COMPLETE,Col:COMPLETE
- <-Map 57 [CUSTOM_SIMPLE_EDGE]
- PARTITION_ONLY_SHUFFLE [RS_151]
- Select Operator [SEL_148] (rows=80000000 width=860)
- Output:["_col0"]
- TableScan [TS_147] (rows=80000000 width=860)
- default@customer,c,Tbl:COMPLETE,Col:NONE,Output:["c_customer_sk"]
+ Select Operator [SEL_5] (rows=20000000 width=1014)
+ Output:["_col0"]
+ Filter Operator [FIL_166] (rows=20000000 width=1014)
+ predicate:((ca_state) IN ('CO', 'IL', 'MN') and ca_address_sk is not null)
+ TableScan [TS_3] (rows=40000000 width=1014)
+ default@customer_address,ca,Tbl:COMPLETE,Col:NONE,Output:["ca_address_sk","ca_state"]