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 2018/07/14 05:16:27 UTC
[04/12] hive git commit: HIVE-20090 : Extend creation of semijoin
reduction filters to be able to discover new opportunities (Jesus Camacho
Rodriguez via Deepak Jaiswal)
http://git-wip-us.apache.org/repos/asf/hive/blob/ab9e954d/ql/src/test/results/clientpositive/perf/tez/query69.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/perf/tez/query69.q.out b/ql/src/test/results/clientpositive/perf/tez/query69.q.out
index a9c7ac3..aad5b81 100644
--- a/ql/src/test/results/clientpositive/perf/tez/query69.q.out
+++ b/ql/src/test/results/clientpositive/perf/tez/query69.q.out
@@ -117,16 +117,16 @@ Stage-0
limit:100
Stage-1
Reducer 7 vectorized
- File Output Operator [FS_230]
- Limit [LIM_229] (rows=100 width=88)
+ File Output Operator [FS_232]
+ Limit [LIM_231] (rows=100 width=88)
Number of rows:100
- Select Operator [SEL_228] (rows=191662559 width=88)
+ Select Operator [SEL_230] (rows=191662559 width=88)
Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"]
<-Reducer 6 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_227]
- Select Operator [SEL_226] (rows=191662559 width=88)
+ SHUFFLE [RS_229]
+ Select Operator [SEL_228] (rows=191662559 width=88)
Output:["_col0","_col1","_col2","_col3","_col4","_col6"]
- Group By Operator [GBY_225] (rows=191662559 width=88)
+ Group By Operator [GBY_227] (rows=191662559 width=88)
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_67]
@@ -137,51 +137,51 @@ Stage-0
Output:["_col6","_col7","_col8","_col9","_col10"]
Filter Operator [FIL_64] (rows=383325119 width=88)
predicate:_col14 is null
- Merge Join Operator [MERGEJOIN_178] (rows=766650239 width=88)
- Conds:RS_61._col0=RS_224._col0(Left Outer),Output:["_col6","_col7","_col8","_col9","_col10","_col14"]
+ Merge Join Operator [MERGEJOIN_180] (rows=766650239 width=88)
+ Conds:RS_61._col0=RS_226._col0(Left Outer),Output:["_col6","_col7","_col8","_col9","_col10","_col14"]
<-Reducer 19 [ONE_TO_ONE_EDGE] vectorized
- FORWARD [RS_224]
+ FORWARD [RS_226]
PartitionCols:_col0
- Select Operator [SEL_223] (rows=158394413 width=135)
+ Select Operator [SEL_225] (rows=158394413 width=135)
Output:["_col0","_col1"]
- Group By Operator [GBY_222] (rows=158394413 width=135)
+ Group By Operator [GBY_224] (rows=158394413 width=135)
Output:["_col0"],keys:KEY._col0
<-Reducer 18 [SIMPLE_EDGE]
SHUFFLE [RS_58]
PartitionCols:_col0
Group By Operator [GBY_57] (rows=316788826 width=135)
Output:["_col0"],keys:_col1
- Merge Join Operator [MERGEJOIN_176] (rows=316788826 width=135)
- Conds:RS_221._col0=RS_194._col0(Inner),Output:["_col1"]
+ Merge Join Operator [MERGEJOIN_178] (rows=316788826 width=135)
+ Conds:RS_223._col0=RS_196._col0(Inner),Output:["_col1"]
<-Map 13 [SIMPLE_EDGE] vectorized
- PARTITION_ONLY_SHUFFLE [RS_194]
+ PARTITION_ONLY_SHUFFLE [RS_196]
PartitionCols:_col0
- Select Operator [SEL_189] (rows=4058 width=1119)
+ Select Operator [SEL_191] (rows=4058 width=1119)
Output:["_col0"]
- Filter Operator [FIL_188] (rows=4058 width=1119)
+ Filter Operator [FIL_190] (rows=4058 width=1119)
predicate:((d_year = 1999) and d_date_sk is not null and d_moy BETWEEN 1 AND 3)
TableScan [TS_12] (rows=73049 width=1119)
default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year","d_moy"]
<-Map 22 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_221]
+ SHUFFLE [RS_223]
PartitionCols:_col0
- Select Operator [SEL_220] (rows=287989836 width=135)
+ Select Operator [SEL_222] (rows=287989836 width=135)
Output:["_col0","_col1"]
- Filter Operator [FIL_219] (rows=287989836 width=135)
+ Filter Operator [FIL_221] (rows=287989836 width=135)
predicate:((cs_sold_date_sk BETWEEN DynamicValue(RS_54_date_dim_d_date_sk_min) AND DynamicValue(RS_54_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_54_date_dim_d_date_sk_bloom_filter))) and cs_ship_customer_sk is not null and cs_sold_date_sk is not null)
TableScan [TS_47] (rows=287989836 width=135)
default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:NONE,Output:["cs_sold_date_sk","cs_ship_customer_sk"]
<-Reducer 20 [BROADCAST_EDGE] vectorized
- BROADCAST [RS_218]
- Group By Operator [GBY_217] (rows=1 width=12)
+ BROADCAST [RS_220]
+ Group By Operator [GBY_219] (rows=1 width=12)
Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"]
<-Map 13 [CUSTOM_SIMPLE_EDGE] vectorized
- PARTITION_ONLY_SHUFFLE [RS_201]
- Group By Operator [GBY_198] (rows=1 width=12)
+ PARTITION_ONLY_SHUFFLE [RS_203]
+ Group By Operator [GBY_200] (rows=1 width=12)
Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
- Select Operator [SEL_195] (rows=4058 width=1119)
+ Select Operator [SEL_197] (rows=4058 width=1119)
Output:["_col0"]
- Please refer to the previous Select Operator [SEL_189]
+ Please refer to the previous Select Operator [SEL_191]
<-Reducer 4 [ONE_TO_ONE_EDGE]
FORWARD [RS_61]
PartitionCols:_col0
@@ -189,42 +189,42 @@ Stage-0
Output:["_col0","_col6","_col7","_col8","_col9","_col10"]
Filter Operator [FIL_45] (rows=696954748 width=88)
predicate:_col12 is null
- Merge Join Operator [MERGEJOIN_177] (rows=1393909496 width=88)
- Conds:RS_41._col0=RS_42._col0(Left Semi),RS_41._col0=RS_216._col0(Left Outer),Output:["_col0","_col6","_col7","_col8","_col9","_col10","_col12"]
+ Merge Join Operator [MERGEJOIN_179] (rows=1393909496 width=88)
+ Conds:RS_41._col0=RS_42._col0(Left Semi),RS_41._col0=RS_218._col0(Left Outer),Output:["_col0","_col6","_col7","_col8","_col9","_col10","_col12"]
<-Reducer 3 [SIMPLE_EDGE]
PARTITION_ONLY_SHUFFLE [RS_41]
PartitionCols:_col0
- Merge Join Operator [MERGEJOIN_173] (rows=96800003 width=860)
- Conds:RS_36._col1=RS_187._col0(Inner),Output:["_col0","_col6","_col7","_col8","_col9","_col10"]
+ Merge Join Operator [MERGEJOIN_175] (rows=96800003 width=860)
+ Conds:RS_36._col1=RS_189._col0(Inner),Output:["_col0","_col6","_col7","_col8","_col9","_col10"]
<-Map 10 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_187]
+ SHUFFLE [RS_189]
PartitionCols:_col0
- Select Operator [SEL_186] (rows=1861800 width=385)
+ Select Operator [SEL_188] (rows=1861800 width=385)
Output:["_col0","_col1","_col2","_col3","_col4","_col5"]
- Filter Operator [FIL_185] (rows=1861800 width=385)
+ Filter Operator [FIL_187] (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_36]
PartitionCols:_col1
- Merge Join Operator [MERGEJOIN_172] (rows=88000001 width=860)
- Conds:RS_181._col2=RS_184._col0(Inner),Output:["_col0","_col1"]
+ Merge Join Operator [MERGEJOIN_174] (rows=88000001 width=860)
+ Conds:RS_183._col2=RS_186._col0(Inner),Output:["_col0","_col1"]
<-Map 1 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_181]
+ SHUFFLE [RS_183]
PartitionCols:_col2
- Select Operator [SEL_180] (rows=80000000 width=860)
+ Select Operator [SEL_182] (rows=80000000 width=860)
Output:["_col0","_col1","_col2"]
- Filter Operator [FIL_179] (rows=80000000 width=860)
+ Filter Operator [FIL_181] (rows=80000000 width=860)
predicate:(c_current_addr_sk is not null and c_current_cdemo_sk is not null and c_customer_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 9 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_184]
+ SHUFFLE [RS_186]
PartitionCols:_col0
- Select Operator [SEL_183] (rows=20000000 width=1014)
+ Select Operator [SEL_185] (rows=20000000 width=1014)
Output:["_col0"]
- Filter Operator [FIL_182] (rows=20000000 width=1014)
+ Filter Operator [FIL_184] (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"]
@@ -235,35 +235,35 @@ Stage-0
Output:["_col0"],keys:_col0
Select Operator [SEL_18] (rows=633595212 width=88)
Output:["_col0"]
- Merge Join Operator [MERGEJOIN_174] (rows=633595212 width=88)
- Conds:RS_208._col0=RS_190._col0(Inner),Output:["_col1"]
+ Merge Join Operator [MERGEJOIN_176] (rows=633595212 width=88)
+ Conds:RS_210._col0=RS_192._col0(Inner),Output:["_col1"]
<-Map 13 [SIMPLE_EDGE] vectorized
- PARTITION_ONLY_SHUFFLE [RS_190]
+ PARTITION_ONLY_SHUFFLE [RS_192]
PartitionCols:_col0
- Please refer to the previous Select Operator [SEL_189]
+ Please refer to the previous Select Operator [SEL_191]
<-Map 11 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_208]
+ SHUFFLE [RS_210]
PartitionCols:_col0
- Select Operator [SEL_207] (rows=575995635 width=88)
+ Select Operator [SEL_209] (rows=575995635 width=88)
Output:["_col0","_col1"]
- Filter Operator [FIL_206] (rows=575995635 width=88)
+ Filter Operator [FIL_208] (rows=575995635 width=88)
predicate:((ss_customer_sk BETWEEN DynamicValue(RS_41_c_c_customer_sk_min) AND DynamicValue(RS_41_c_c_customer_sk_max) and in_bloom_filter(ss_customer_sk, DynamicValue(RS_41_c_c_customer_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_16_date_dim_d_date_sk_min) AND DynamicValue(RS_16_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_16_date_dim_d_date_sk_bloom_filter))) and ss_customer_sk is not null 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"]
<-Reducer 14 [BROADCAST_EDGE] vectorized
- BROADCAST [RS_203]
- Group By Operator [GBY_202] (rows=1 width=12)
+ BROADCAST [RS_205]
+ Group By Operator [GBY_204] (rows=1 width=12)
Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"]
<-Map 13 [CUSTOM_SIMPLE_EDGE] vectorized
- PARTITION_ONLY_SHUFFLE [RS_199]
- Group By Operator [GBY_196] (rows=1 width=12)
+ PARTITION_ONLY_SHUFFLE [RS_201]
+ Group By Operator [GBY_198] (rows=1 width=12)
Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
- Select Operator [SEL_191] (rows=4058 width=1119)
+ Select Operator [SEL_193] (rows=4058 width=1119)
Output:["_col0"]
- Please refer to the previous Select Operator [SEL_189]
+ Please refer to the previous Select Operator [SEL_191]
<-Reducer 8 [BROADCAST_EDGE] vectorized
- BROADCAST [RS_205]
- Group By Operator [GBY_204] (rows=1 width=12)
+ BROADCAST [RS_207]
+ Group By Operator [GBY_206] (rows=1 width=12)
Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=96800000)"]
<-Reducer 3 [CUSTOM_SIMPLE_EDGE]
PARTITION_ONLY_SHUFFLE [RS_137]
@@ -271,43 +271,43 @@ Stage-0
Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=96800000)"]
Select Operator [SEL_135] (rows=96800003 width=860)
Output:["_col0"]
- Please refer to the previous Merge Join Operator [MERGEJOIN_173]
+ Please refer to the previous Merge Join Operator [MERGEJOIN_175]
<-Reducer 16 [ONE_TO_ONE_EDGE] vectorized
- FORWARD [RS_216]
+ FORWARD [RS_218]
PartitionCols:_col0
- Select Operator [SEL_215] (rows=79201469 width=135)
+ Select Operator [SEL_217] (rows=79201469 width=135)
Output:["_col0","_col1"]
- Group By Operator [GBY_214] (rows=79201469 width=135)
+ Group By Operator [GBY_216] (rows=79201469 width=135)
Output:["_col0"],keys:KEY._col0
<-Reducer 15 [SIMPLE_EDGE]
SHUFFLE [RS_30]
PartitionCols:_col0
Group By Operator [GBY_29] (rows=158402938 width=135)
Output:["_col0"],keys:_col1
- Merge Join Operator [MERGEJOIN_175] (rows=158402938 width=135)
- Conds:RS_213._col0=RS_192._col0(Inner),Output:["_col1"]
+ Merge Join Operator [MERGEJOIN_177] (rows=158402938 width=135)
+ Conds:RS_215._col0=RS_194._col0(Inner),Output:["_col1"]
<-Map 13 [SIMPLE_EDGE] vectorized
- PARTITION_ONLY_SHUFFLE [RS_192]
+ PARTITION_ONLY_SHUFFLE [RS_194]
PartitionCols:_col0
- Please refer to the previous Select Operator [SEL_189]
+ Please refer to the previous Select Operator [SEL_191]
<-Map 21 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_213]
+ SHUFFLE [RS_215]
PartitionCols:_col0
- Select Operator [SEL_212] (rows=144002668 width=135)
+ Select Operator [SEL_214] (rows=144002668 width=135)
Output:["_col0","_col1"]
- Filter Operator [FIL_211] (rows=144002668 width=135)
+ Filter Operator [FIL_213] (rows=144002668 width=135)
predicate:((ws_sold_date_sk BETWEEN DynamicValue(RS_26_date_dim_d_date_sk_min) AND DynamicValue(RS_26_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_26_date_dim_d_date_sk_bloom_filter))) and ws_bill_customer_sk is not null and ws_sold_date_sk is not null)
TableScan [TS_19] (rows=144002668 width=135)
default@web_sales,web_sales,Tbl:COMPLETE,Col:NONE,Output:["ws_sold_date_sk","ws_bill_customer_sk"]
<-Reducer 17 [BROADCAST_EDGE] vectorized
- BROADCAST [RS_210]
- Group By Operator [GBY_209] (rows=1 width=12)
+ BROADCAST [RS_212]
+ Group By Operator [GBY_211] (rows=1 width=12)
Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"]
<-Map 13 [CUSTOM_SIMPLE_EDGE] vectorized
- PARTITION_ONLY_SHUFFLE [RS_200]
- Group By Operator [GBY_197] (rows=1 width=12)
+ PARTITION_ONLY_SHUFFLE [RS_202]
+ Group By Operator [GBY_199] (rows=1 width=12)
Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
- Select Operator [SEL_193] (rows=4058 width=1119)
+ Select Operator [SEL_195] (rows=4058 width=1119)
Output:["_col0"]
- Please refer to the previous Select Operator [SEL_189]
+ Please refer to the previous Select Operator [SEL_191]
http://git-wip-us.apache.org/repos/asf/hive/blob/ab9e954d/ql/src/test/results/clientpositive/perf/tez/query72.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/perf/tez/query72.q.out b/ql/src/test/results/clientpositive/perf/tez/query72.q.out
index 48682e3..65a60ea 100644
--- a/ql/src/test/results/clientpositive/perf/tez/query72.q.out
+++ b/ql/src/test/results/clientpositive/perf/tez/query72.q.out
@@ -86,14 +86,14 @@ Stage-0
limit:100
Stage-1
Reducer 7 vectorized
- File Output Operator [FS_311]
- Limit [LIM_310] (rows=100 width=135)
+ File Output Operator [FS_315]
+ Limit [LIM_314] (rows=100 width=135)
Number of rows:100
- Select Operator [SEL_309] (rows=37725837 width=135)
+ Select Operator [SEL_313] (rows=37725837 width=135)
Output:["_col0","_col1","_col2","_col3","_col4","_col5"]
<-Reducer 6 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_308]
- Group By Operator [GBY_307] (rows=37725837 width=135)
+ SHUFFLE [RS_312]
+ Group By Operator [GBY_311] (rows=37725837 width=135)
Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["count(VALUE._col0)","count(VALUE._col1)","count(VALUE._col2)"],keys:KEY._col0, KEY._col1, KEY._col2
<-Reducer 5 [SIMPLE_EDGE]
SHUFFLE [RS_69]
@@ -102,14 +102,14 @@ Stage-0
Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["count(_col3)","count(_col4)","count()"],keys:_col0, _col1, _col2
Select Operator [SEL_66] (rows=75451675 width=135)
Output:["_col0","_col1","_col2","_col3","_col4"]
- Merge Join Operator [MERGEJOIN_247] (rows=75451675 width=135)
- Conds:RS_63._col4, _col6=RS_306._col0, _col1(Left Outer),Output:["_col13","_col15","_col22","_col28"]
+ Merge Join Operator [MERGEJOIN_251] (rows=75451675 width=135)
+ Conds:RS_63._col4, _col6=RS_310._col0, _col1(Left Outer),Output:["_col13","_col15","_col22","_col28"]
<-Map 29 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_306]
+ SHUFFLE [RS_310]
PartitionCols:_col0, _col1
- Select Operator [SEL_305] (rows=28798881 width=106)
+ Select Operator [SEL_309] (rows=28798881 width=106)
Output:["_col0","_col1"]
- Filter Operator [FIL_304] (rows=28798881 width=106)
+ Filter Operator [FIL_308] (rows=28798881 width=106)
predicate:cr_item_sk is not null
TableScan [TS_60] (rows=28798881 width=106)
default@catalog_returns,catalog_returns,Tbl:COMPLETE,Col:NONE,Output:["cr_item_sk","cr_order_number"]
@@ -118,14 +118,14 @@ Stage-0
PartitionCols:_col4, _col6
Select Operator [SEL_59] (rows=68592431 width=135)
Output:["_col4","_col6","_col13","_col15","_col22","_col28"]
- Merge Join Operator [MERGEJOIN_246] (rows=68592431 width=135)
- Conds:RS_56._col0, _col20=RS_303._col0, _col1(Inner),Output:["_col5","_col9","_col14","_col16","_col20","_col26"]
+ Merge Join Operator [MERGEJOIN_250] (rows=68592431 width=135)
+ Conds:RS_56._col0, _col20=RS_307._col0, _col1(Inner),Output:["_col5","_col9","_col14","_col16","_col20","_col26"]
<-Map 28 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_303]
+ SHUFFLE [RS_307]
PartitionCols:_col0, _col1
- Select Operator [SEL_302] (rows=73049 width=1119)
+ Select Operator [SEL_306] (rows=73049 width=1119)
Output:["_col0","_col1"]
- Filter Operator [FIL_301] (rows=73049 width=1119)
+ Filter Operator [FIL_305] (rows=73049 width=1119)
predicate:(d_date_sk is not null and d_week_seq is not null)
TableScan [TS_46] (rows=73049 width=1119)
default@date_dim,d2,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_week_seq"]
@@ -134,28 +134,28 @@ Stage-0
PartitionCols:_col0, _col20
Filter Operator [FIL_55] (rows=62356755 width=135)
predicate:(_col3 < _col17)
- Merge Join Operator [MERGEJOIN_245] (rows=187070265 width=135)
+ Merge Join Operator [MERGEJOIN_249] (rows=187070265 width=135)
Conds:RS_52._col1=RS_53._col8(Inner),Output:["_col0","_col3","_col5","_col9","_col14","_col16","_col17","_col20","_col26"]
<-Reducer 2 [SIMPLE_EDGE]
PARTITION_ONLY_SHUFFLE [RS_52]
PartitionCols:_col1
- Merge Join Operator [MERGEJOIN_238] (rows=41342400 width=15)
- Conds:RS_250._col2=RS_253._col0(Inner),Output:["_col0","_col1","_col3","_col5"]
+ Merge Join Operator [MERGEJOIN_242] (rows=41342400 width=15)
+ Conds:RS_254._col2=RS_257._col0(Inner),Output:["_col0","_col1","_col3","_col5"]
<-Map 1 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_250]
+ SHUFFLE [RS_254]
PartitionCols:_col2
- Select Operator [SEL_249] (rows=37584000 width=15)
+ Select Operator [SEL_253] (rows=37584000 width=15)
Output:["_col0","_col1","_col2","_col3"]
- Filter Operator [FIL_248] (rows=37584000 width=15)
+ Filter Operator [FIL_252] (rows=37584000 width=15)
predicate:(inv_date_sk is not null and inv_item_sk is not null and inv_warehouse_sk is not null)
TableScan [TS_0] (rows=37584000 width=15)
default@inventory,inventory,Tbl:COMPLETE,Col:NONE,Output:["inv_date_sk","inv_item_sk","inv_warehouse_sk","inv_quantity_on_hand"]
<-Map 9 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_253]
+ SHUFFLE [RS_257]
PartitionCols:_col0
- Select Operator [SEL_252] (rows=27 width=1029)
+ Select Operator [SEL_256] (rows=27 width=1029)
Output:["_col0","_col1"]
- Filter Operator [FIL_251] (rows=27 width=1029)
+ Filter Operator [FIL_255] (rows=27 width=1029)
predicate:w_warehouse_sk is not null
TableScan [TS_3] (rows=27 width=1029)
default@warehouse,warehouse,Tbl:COMPLETE,Col:NONE,Output:["w_warehouse_sk","w_warehouse_name"]
@@ -166,152 +166,152 @@ Stage-0
Output:["_col3","_col8","_col10","_col11","_col14","_col20"]
Filter Operator [FIL_44] (rows=170063874 width=135)
predicate:(UDFToDouble(_col20) > (UDFToDouble(_col9) + 5.0D))
- Merge Join Operator [MERGEJOIN_244] (rows=510191624 width=135)
- Conds:RS_41._col1=RS_290._col0(Inner),Output:["_col4","_col6","_col7","_col9","_col10","_col16","_col18","_col20"]
+ Merge Join Operator [MERGEJOIN_248] (rows=510191624 width=135)
+ Conds:RS_41._col1=RS_294._col0(Inner),Output:["_col4","_col6","_col7","_col9","_col10","_col16","_col18","_col20"]
<-Map 26 [SIMPLE_EDGE] vectorized
- PARTITION_ONLY_SHUFFLE [RS_290]
+ PARTITION_ONLY_SHUFFLE [RS_294]
PartitionCols:_col0
- Select Operator [SEL_289] (rows=73049 width=1119)
+ Select Operator [SEL_293] (rows=73049 width=1119)
Output:["_col0","_col1"]
- Filter Operator [FIL_288] (rows=73049 width=1119)
+ Filter Operator [FIL_292] (rows=73049 width=1119)
predicate:d_date_sk is not null
TableScan [TS_23] (rows=73049 width=1119)
default@date_dim,d3,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_date"]
<-Reducer 15 [SIMPLE_EDGE]
SHUFFLE [RS_41]
PartitionCols:_col1
- Merge Join Operator [MERGEJOIN_243] (rows=463810558 width=135)
- Conds:RS_38._col4=RS_280._col0(Inner),Output:["_col1","_col4","_col6","_col7","_col9","_col10","_col16","_col18"]
+ Merge Join Operator [MERGEJOIN_247] (rows=463810558 width=135)
+ Conds:RS_38._col4=RS_284._col0(Inner),Output:["_col1","_col4","_col6","_col7","_col9","_col10","_col16","_col18"]
<-Map 24 [SIMPLE_EDGE] vectorized
- PARTITION_ONLY_SHUFFLE [RS_280]
+ PARTITION_ONLY_SHUFFLE [RS_284]
PartitionCols:_col0
- Select Operator [SEL_279] (rows=462000 width=1436)
+ Select Operator [SEL_283] (rows=462000 width=1436)
Output:["_col0","_col1"]
- Filter Operator [FIL_278] (rows=462000 width=1436)
+ Filter Operator [FIL_282] (rows=462000 width=1436)
predicate:i_item_sk is not null
TableScan [TS_20] (rows=462000 width=1436)
default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_item_desc"]
<-Reducer 14 [SIMPLE_EDGE]
SHUFFLE [RS_38]
PartitionCols:_col4
- Merge Join Operator [MERGEJOIN_242] (rows=421645953 width=135)
- Conds:RS_35._col5=RS_300._col0(Left Outer),Output:["_col1","_col4","_col6","_col7","_col9","_col10","_col16"]
+ Merge Join Operator [MERGEJOIN_246] (rows=421645953 width=135)
+ Conds:RS_35._col5=RS_304._col0(Left Outer),Output:["_col1","_col4","_col6","_col7","_col9","_col10","_col16"]
<-Map 23 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_300]
+ SHUFFLE [RS_304]
PartitionCols:_col0
- Select Operator [SEL_299] (rows=2300 width=1179)
+ Select Operator [SEL_303] (rows=2300 width=1179)
Output:["_col0"]
TableScan [TS_18] (rows=2300 width=1179)
default@promotion,promotion,Tbl:COMPLETE,Col:NONE,Output:["p_promo_sk"]
<-Reducer 13 [SIMPLE_EDGE]
SHUFFLE [RS_35]
PartitionCols:_col5
- Merge Join Operator [MERGEJOIN_241] (rows=383314495 width=135)
- Conds:RS_32._col3=RS_272._col0(Inner),Output:["_col1","_col4","_col5","_col6","_col7","_col9","_col10"]
+ Merge Join Operator [MERGEJOIN_245] (rows=383314495 width=135)
+ Conds:RS_32._col3=RS_276._col0(Inner),Output:["_col1","_col4","_col5","_col6","_col7","_col9","_col10"]
<-Map 21 [SIMPLE_EDGE] vectorized
- PARTITION_ONLY_SHUFFLE [RS_272]
+ PARTITION_ONLY_SHUFFLE [RS_276]
PartitionCols:_col0
- Select Operator [SEL_271] (rows=3600 width=107)
+ Select Operator [SEL_275] (rows=3600 width=107)
Output:["_col0"]
- Filter Operator [FIL_270] (rows=3600 width=107)
+ Filter Operator [FIL_274] (rows=3600 width=107)
predicate:((hd_buy_potential = '1001-5000') and hd_demo_sk is not null)
TableScan [TS_15] (rows=7200 width=107)
default@household_demographics,household_demographics,Tbl:COMPLETE,Col:NONE,Output:["hd_demo_sk","hd_buy_potential"]
<-Reducer 12 [SIMPLE_EDGE]
SHUFFLE [RS_32]
PartitionCols:_col3
- Merge Join Operator [MERGEJOIN_240] (rows=348467716 width=135)
- Conds:RS_29._col2=RS_264._col0(Inner),Output:["_col1","_col3","_col4","_col5","_col6","_col7","_col9","_col10"]
+ Merge Join Operator [MERGEJOIN_244] (rows=348467716 width=135)
+ Conds:RS_29._col2=RS_268._col0(Inner),Output:["_col1","_col3","_col4","_col5","_col6","_col7","_col9","_col10"]
<-Map 19 [SIMPLE_EDGE] vectorized
- PARTITION_ONLY_SHUFFLE [RS_264]
+ PARTITION_ONLY_SHUFFLE [RS_268]
PartitionCols:_col0
- Select Operator [SEL_263] (rows=930900 width=385)
+ Select Operator [SEL_267] (rows=930900 width=385)
Output:["_col0"]
- Filter Operator [FIL_262] (rows=930900 width=385)
+ Filter Operator [FIL_266] (rows=930900 width=385)
predicate:((cd_marital_status = 'M') and cd_demo_sk is not null)
TableScan [TS_12] (rows=1861800 width=385)
default@customer_demographics,customer_demographics,Tbl:COMPLETE,Col:NONE,Output:["cd_demo_sk","cd_marital_status"]
<-Reducer 11 [SIMPLE_EDGE]
SHUFFLE [RS_29]
PartitionCols:_col2
- Merge Join Operator [MERGEJOIN_239] (rows=316788826 width=135)
- Conds:RS_298._col0=RS_256._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col9","_col10"]
+ Merge Join Operator [MERGEJOIN_243] (rows=316788826 width=135)
+ Conds:RS_302._col0=RS_260._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col9","_col10"]
<-Map 17 [SIMPLE_EDGE] vectorized
- PARTITION_ONLY_SHUFFLE [RS_256]
+ PARTITION_ONLY_SHUFFLE [RS_260]
PartitionCols:_col0
- Select Operator [SEL_255] (rows=36524 width=1119)
+ Select Operator [SEL_259] (rows=36524 width=1119)
Output:["_col0","_col1","_col2"]
- Filter Operator [FIL_254] (rows=36524 width=1119)
+ Filter Operator [FIL_258] (rows=36524 width=1119)
predicate:((d_year = 2001) and d_date_sk is not null and d_week_seq is not null)
TableScan [TS_9] (rows=73049 width=1119)
default@date_dim,d1,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_date","d_week_seq","d_year"]
<-Map 10 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_298]
+ SHUFFLE [RS_302]
PartitionCols:_col0
- Select Operator [SEL_297] (rows=287989836 width=135)
+ Select Operator [SEL_301] (rows=287989836 width=135)
Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"]
- Filter Operator [FIL_296] (rows=287989836 width=135)
+ Filter Operator [FIL_300] (rows=287989836 width=135)
predicate:((cs_bill_cdemo_sk BETWEEN DynamicValue(RS_30_customer_demographics_cd_demo_sk_min) AND DynamicValue(RS_30_customer_demographics_cd_demo_sk_max) and in_bloom_filter(cs_bill_cdemo_sk, DynamicValue(RS_30_customer_demographics_cd_demo_sk_bloom_filter))) and (cs_bill_hdemo_sk BETWEEN DynamicValue(RS_33_household_demographics_hd_demo_sk_min) AND DynamicValue(RS_33_household_demographics_hd_demo_sk_max) and in_bloom_filter(cs_bill_hdemo_sk, DynamicValue(RS_33_household_demographics_hd_demo_sk_bloom_filter))) and (cs_item_sk BETWEEN DynamicValue(RS_39_item_i_item_sk_min) AND DynamicValue(RS_39_item_i_item_sk_max) and in_bloom_filter(cs_item_sk, DynamicValue(RS_39_item_i_item_sk_bloom_filter))) and (cs_item_sk BETWEEN DynamicValue(RS_52_inventory_inv_item_sk_min) AND DynamicValue(RS_52_inventory_inv_item_sk_max) and in_bloom_filter(cs_item_sk, DynamicValue(RS_52_inventory_inv_item_sk_bloom_filter))) and (cs_ship
_date_sk BETWEEN DynamicValue(RS_42_d3_d_date_sk_min) AND DynamicValue(RS_42_d3_d_date_sk_max) and in_bloom_filter(cs_ship_date_sk, DynamicValue(RS_42_d3_d_date_sk_bloom_filter))) and (cs_sold_date_sk BETWEEN DynamicValue(RS_27_d1_d_date_sk_min) AND DynamicValue(RS_27_d1_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_27_d1_d_date_sk_bloom_filter))) and cs_bill_cdemo_sk is not null and cs_bill_hdemo_sk is not null and cs_item_sk is not null and cs_ship_date_sk is not null and cs_sold_date_sk is not null)
TableScan [TS_6] (rows=287989836 width=135)
default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:NONE,Output:["cs_sold_date_sk","cs_ship_date_sk","cs_bill_cdemo_sk","cs_bill_hdemo_sk","cs_item_sk","cs_promo_sk","cs_order_number","cs_quantity"]
<-Reducer 18 [BROADCAST_EDGE] vectorized
- BROADCAST [RS_261]
- Group By Operator [GBY_260] (rows=1 width=12)
+ BROADCAST [RS_265]
+ Group By Operator [GBY_264] (rows=1 width=12)
Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"]
<-Map 17 [CUSTOM_SIMPLE_EDGE] vectorized
- PARTITION_ONLY_SHUFFLE [RS_259]
- Group By Operator [GBY_258] (rows=1 width=12)
+ PARTITION_ONLY_SHUFFLE [RS_263]
+ Group By Operator [GBY_262] (rows=1 width=12)
Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
- Select Operator [SEL_257] (rows=36524 width=1119)
+ Select Operator [SEL_261] (rows=36524 width=1119)
Output:["_col0"]
- Please refer to the previous Select Operator [SEL_255]
+ Please refer to the previous Select Operator [SEL_259]
<-Reducer 20 [BROADCAST_EDGE] vectorized
- BROADCAST [RS_269]
- Group By Operator [GBY_268] (rows=1 width=12)
+ BROADCAST [RS_273]
+ Group By Operator [GBY_272] (rows=1 width=12)
Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"]
<-Map 19 [CUSTOM_SIMPLE_EDGE] vectorized
- PARTITION_ONLY_SHUFFLE [RS_267]
- Group By Operator [GBY_266] (rows=1 width=12)
+ PARTITION_ONLY_SHUFFLE [RS_271]
+ Group By Operator [GBY_270] (rows=1 width=12)
Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
- Select Operator [SEL_265] (rows=930900 width=385)
+ Select Operator [SEL_269] (rows=930900 width=385)
Output:["_col0"]
- Please refer to the previous Select Operator [SEL_263]
+ Please refer to the previous Select Operator [SEL_267]
<-Reducer 22 [BROADCAST_EDGE] vectorized
- BROADCAST [RS_277]
- Group By Operator [GBY_276] (rows=1 width=12)
+ BROADCAST [RS_281]
+ Group By Operator [GBY_280] (rows=1 width=12)
Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"]
<-Map 21 [CUSTOM_SIMPLE_EDGE] vectorized
- PARTITION_ONLY_SHUFFLE [RS_275]
- Group By Operator [GBY_274] (rows=1 width=12)
+ PARTITION_ONLY_SHUFFLE [RS_279]
+ Group By Operator [GBY_278] (rows=1 width=12)
Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
- Select Operator [SEL_273] (rows=3600 width=107)
+ Select Operator [SEL_277] (rows=3600 width=107)
Output:["_col0"]
- Please refer to the previous Select Operator [SEL_271]
+ Please refer to the previous Select Operator [SEL_275]
<-Reducer 25 [BROADCAST_EDGE] vectorized
- BROADCAST [RS_285]
- Group By Operator [GBY_284] (rows=1 width=12)
+ BROADCAST [RS_289]
+ Group By Operator [GBY_288] (rows=1 width=12)
Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"]
<-Map 24 [CUSTOM_SIMPLE_EDGE] vectorized
- PARTITION_ONLY_SHUFFLE [RS_283]
- Group By Operator [GBY_282] (rows=1 width=12)
+ PARTITION_ONLY_SHUFFLE [RS_287]
+ Group By Operator [GBY_286] (rows=1 width=12)
Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
- Select Operator [SEL_281] (rows=462000 width=1436)
+ Select Operator [SEL_285] (rows=462000 width=1436)
Output:["_col0"]
- Please refer to the previous Select Operator [SEL_279]
+ Please refer to the previous Select Operator [SEL_283]
<-Reducer 27 [BROADCAST_EDGE] vectorized
- BROADCAST [RS_295]
- Group By Operator [GBY_294] (rows=1 width=12)
+ BROADCAST [RS_299]
+ Group By Operator [GBY_298] (rows=1 width=12)
Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"]
<-Map 26 [CUSTOM_SIMPLE_EDGE] vectorized
- PARTITION_ONLY_SHUFFLE [RS_293]
- Group By Operator [GBY_292] (rows=1 width=12)
+ PARTITION_ONLY_SHUFFLE [RS_297]
+ Group By Operator [GBY_296] (rows=1 width=12)
Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
- Select Operator [SEL_291] (rows=73049 width=1119)
+ Select Operator [SEL_295] (rows=73049 width=1119)
Output:["_col0"]
- Please refer to the previous Select Operator [SEL_289]
+ Please refer to the previous Select Operator [SEL_293]
<-Reducer 8 [BROADCAST_EDGE] vectorized
- BROADCAST [RS_287]
- Group By Operator [GBY_286] (rows=1 width=12)
+ BROADCAST [RS_291]
+ Group By Operator [GBY_290] (rows=1 width=12)
Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=41342400)"]
<-Reducer 2 [CUSTOM_SIMPLE_EDGE]
PARTITION_ONLY_SHUFFLE [RS_174]
@@ -319,5 +319,5 @@ Stage-0
Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=41342400)"]
Select Operator [SEL_172] (rows=41342400 width=15)
Output:["_col0"]
- Please refer to the previous Merge Join Operator [MERGEJOIN_238]
+ Please refer to the previous Merge Join Operator [MERGEJOIN_242]