You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by se...@apache.org on 2018/07/19 21:44:43 UTC
[05/54] [abbrv] hive git commit: HIVE-17896: TopNKey: Create a
standalone vectorizable TopNKey operator (Teddy Choi,
reviewed by Jesus Camacho Rodriguez)
http://git-wip-us.apache.org/repos/asf/hive/blob/851c8aba/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 aad5b81..738508a 100644
--- a/ql/src/test/results/clientpositive/perf/tez/query69.q.out
+++ b/ql/src/test/results/clientpositive/perf/tez/query69.q.out
@@ -117,197 +117,199 @@ Stage-0
limit:100
Stage-1
Reducer 7 vectorized
- File Output Operator [FS_232]
- Limit [LIM_231] (rows=100 width=88)
+ File Output Operator [FS_233]
+ Limit [LIM_232] (rows=100 width=88)
Number of rows:100
- Select Operator [SEL_230] (rows=191662559 width=88)
+ Select Operator [SEL_231] (rows=191662559 width=88)
Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"]
<-Reducer 6 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_229]
- Select Operator [SEL_228] (rows=191662559 width=88)
+ SHUFFLE [RS_230]
+ Select Operator [SEL_229] (rows=191662559 width=88)
Output:["_col0","_col1","_col2","_col3","_col4","_col6"]
- Group By Operator [GBY_227] (rows=191662559 width=88)
+ Group By Operator [GBY_228] (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]
PartitionCols:_col0, _col1, _col2, _col3, _col4
Group By Operator [GBY_66] (rows=383325119 width=88)
Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["count()"],keys:_col6, _col7, _col8, _col9, _col10
- Select Operator [SEL_65] (rows=383325119 width=88)
- Output:["_col6","_col7","_col8","_col9","_col10"]
- Filter Operator [FIL_64] (rows=383325119 width=88)
- predicate:_col14 is null
- 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_226]
- PartitionCols:_col0
- Select Operator [SEL_225] (rows=158394413 width=135)
- Output:["_col0","_col1"]
- 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_178] (rows=316788826 width=135)
- Conds:RS_223._col0=RS_196._col0(Inner),Output:["_col1"]
- <-Map 13 [SIMPLE_EDGE] vectorized
- PARTITION_ONLY_SHUFFLE [RS_196]
- PartitionCols:_col0
- Select Operator [SEL_191] (rows=4058 width=1119)
- Output:["_col0"]
- 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_223]
- PartitionCols:_col0
- Select Operator [SEL_222] (rows=287989836 width=135)
- Output:["_col0","_col1"]
- 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_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_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_197] (rows=4058 width=1119)
- Output:["_col0"]
- Please refer to the previous Select Operator [SEL_191]
- <-Reducer 4 [ONE_TO_ONE_EDGE]
- FORWARD [RS_61]
- PartitionCols:_col0
- Select Operator [SEL_46] (rows=696954748 width=88)
- Output:["_col0","_col6","_col7","_col8","_col9","_col10"]
- Filter Operator [FIL_45] (rows=696954748 width=88)
- predicate:_col12 is null
- 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_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_189]
- PartitionCols:_col0
- Select Operator [SEL_188] (rows=1861800 width=385)
- Output:["_col0","_col1","_col2","_col3","_col4","_col5"]
- 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_174] (rows=88000001 width=860)
- Conds:RS_183._col2=RS_186._col0(Inner),Output:["_col0","_col1"]
- <-Map 1 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_183]
- PartitionCols:_col2
- Select Operator [SEL_182] (rows=80000000 width=860)
- Output:["_col0","_col1","_col2"]
- 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_186]
- PartitionCols:_col0
- Select Operator [SEL_185] (rows=20000000 width=1014)
- Output:["_col0"]
- 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"]
- <-Reducer 12 [SIMPLE_EDGE]
- SHUFFLE [RS_42]
- PartitionCols:_col0
- Group By Operator [GBY_40] (rows=633595212 width=88)
- Output:["_col0"],keys:_col0
- Select Operator [SEL_18] (rows=633595212 width=88)
- Output:["_col0"]
- 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_192]
- PartitionCols:_col0
- Please refer to the previous Select Operator [SEL_191]
- <-Map 11 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_210]
- PartitionCols:_col0
- Select Operator [SEL_209] (rows=575995635 width=88)
- Output:["_col0","_col1"]
- 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_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_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_193] (rows=4058 width=1119)
- Output:["_col0"]
- Please refer to the previous Select Operator [SEL_191]
- <-Reducer 8 [BROADCAST_EDGE] vectorized
- 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]
- Group By Operator [GBY_136] (rows=1 width=12)
- 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_175]
- <-Reducer 16 [ONE_TO_ONE_EDGE] vectorized
- FORWARD [RS_218]
+ Top N Key Operator [TNK_105] (rows=383325119 width=88)
+ keys:_col6, _col7, _col8, _col9, _col10,sort order:+++++,top n:100
+ Select Operator [SEL_65] (rows=383325119 width=88)
+ Output:["_col6","_col7","_col8","_col9","_col10"]
+ Filter Operator [FIL_64] (rows=383325119 width=88)
+ predicate:_col14 is null
+ Merge Join Operator [MERGEJOIN_181] (rows=766650239 width=88)
+ Conds:RS_61._col0=RS_227._col0(Left Outer),Output:["_col6","_col7","_col8","_col9","_col10","_col14"]
+ <-Reducer 19 [ONE_TO_ONE_EDGE] vectorized
+ FORWARD [RS_227]
+ PartitionCols:_col0
+ Select Operator [SEL_226] (rows=158394413 width=135)
+ Output:["_col0","_col1"]
+ Group By Operator [GBY_225] (rows=158394413 width=135)
+ Output:["_col0"],keys:KEY._col0
+ <-Reducer 18 [SIMPLE_EDGE]
+ SHUFFLE [RS_58]
PartitionCols:_col0
- Select Operator [SEL_217] (rows=79201469 width=135)
- Output:["_col0","_col1"]
- Group By Operator [GBY_216] (rows=79201469 width=135)
- Output:["_col0"],keys:KEY._col0
- <-Reducer 15 [SIMPLE_EDGE]
- SHUFFLE [RS_30]
+ Group By Operator [GBY_57] (rows=316788826 width=135)
+ Output:["_col0"],keys:_col1
+ Merge Join Operator [MERGEJOIN_179] (rows=316788826 width=135)
+ Conds:RS_224._col0=RS_197._col0(Inner),Output:["_col1"]
+ <-Map 13 [SIMPLE_EDGE] vectorized
+ PARTITION_ONLY_SHUFFLE [RS_197]
+ PartitionCols:_col0
+ Select Operator [SEL_192] (rows=4058 width=1119)
+ Output:["_col0"]
+ Filter Operator [FIL_191] (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_224]
+ PartitionCols:_col0
+ Select Operator [SEL_223] (rows=287989836 width=135)
+ Output:["_col0","_col1"]
+ Filter Operator [FIL_222] (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_221]
+ Group By Operator [GBY_220] (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_204]
+ Group By Operator [GBY_201] (rows=1 width=12)
+ Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
+ Select Operator [SEL_198] (rows=4058 width=1119)
+ Output:["_col0"]
+ Please refer to the previous Select Operator [SEL_192]
+ <-Reducer 4 [ONE_TO_ONE_EDGE]
+ FORWARD [RS_61]
+ PartitionCols:_col0
+ Select Operator [SEL_46] (rows=696954748 width=88)
+ Output:["_col0","_col6","_col7","_col8","_col9","_col10"]
+ Filter Operator [FIL_45] (rows=696954748 width=88)
+ predicate:_col12 is null
+ Merge Join Operator [MERGEJOIN_180] (rows=1393909496 width=88)
+ Conds:RS_41._col0=RS_42._col0(Left Semi),RS_41._col0=RS_219._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_176] (rows=96800003 width=860)
+ Conds:RS_36._col1=RS_190._col0(Inner),Output:["_col0","_col6","_col7","_col8","_col9","_col10"]
+ <-Map 10 [SIMPLE_EDGE] vectorized
+ SHUFFLE [RS_190]
PartitionCols:_col0
- Group By Operator [GBY_29] (rows=158402938 width=135)
- Output:["_col0"],keys:_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_194]
- PartitionCols:_col0
- Please refer to the previous Select Operator [SEL_191]
- <-Map 21 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_215]
- PartitionCols:_col0
- Select Operator [SEL_214] (rows=144002668 width=135)
- Output:["_col0","_col1"]
- 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_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_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_195] (rows=4058 width=1119)
- Output:["_col0"]
- Please refer to the previous Select Operator [SEL_191]
+ Select Operator [SEL_189] (rows=1861800 width=385)
+ Output:["_col0","_col1","_col2","_col3","_col4","_col5"]
+ Filter Operator [FIL_188] (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_175] (rows=88000001 width=860)
+ Conds:RS_184._col2=RS_187._col0(Inner),Output:["_col0","_col1"]
+ <-Map 1 [SIMPLE_EDGE] vectorized
+ SHUFFLE [RS_184]
+ PartitionCols:_col2
+ Select Operator [SEL_183] (rows=80000000 width=860)
+ Output:["_col0","_col1","_col2"]
+ Filter Operator [FIL_182] (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_187]
+ PartitionCols:_col0
+ Select Operator [SEL_186] (rows=20000000 width=1014)
+ Output:["_col0"]
+ Filter Operator [FIL_185] (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 12 [SIMPLE_EDGE]
+ SHUFFLE [RS_42]
+ PartitionCols:_col0
+ Group By Operator [GBY_40] (rows=633595212 width=88)
+ Output:["_col0"],keys:_col0
+ Select Operator [SEL_18] (rows=633595212 width=88)
+ Output:["_col0"]
+ Merge Join Operator [MERGEJOIN_177] (rows=633595212 width=88)
+ Conds:RS_211._col0=RS_193._col0(Inner),Output:["_col1"]
+ <-Map 13 [SIMPLE_EDGE] vectorized
+ PARTITION_ONLY_SHUFFLE [RS_193]
+ PartitionCols:_col0
+ Please refer to the previous Select Operator [SEL_192]
+ <-Map 11 [SIMPLE_EDGE] vectorized
+ SHUFFLE [RS_211]
+ PartitionCols:_col0
+ Select Operator [SEL_210] (rows=575995635 width=88)
+ Output:["_col0","_col1"]
+ Filter Operator [FIL_209] (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_206]
+ Group By Operator [GBY_205] (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_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_194] (rows=4058 width=1119)
+ Output:["_col0"]
+ Please refer to the previous Select Operator [SEL_192]
+ <-Reducer 8 [BROADCAST_EDGE] vectorized
+ BROADCAST [RS_208]
+ Group By Operator [GBY_207] (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_138]
+ Group By Operator [GBY_137] (rows=1 width=12)
+ Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=96800000)"]
+ Select Operator [SEL_136] (rows=96800003 width=860)
+ Output:["_col0"]
+ Please refer to the previous Merge Join Operator [MERGEJOIN_176]
+ <-Reducer 16 [ONE_TO_ONE_EDGE] vectorized
+ FORWARD [RS_219]
+ PartitionCols:_col0
+ Select Operator [SEL_218] (rows=79201469 width=135)
+ Output:["_col0","_col1"]
+ Group By Operator [GBY_217] (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_178] (rows=158402938 width=135)
+ Conds:RS_216._col0=RS_195._col0(Inner),Output:["_col1"]
+ <-Map 13 [SIMPLE_EDGE] vectorized
+ PARTITION_ONLY_SHUFFLE [RS_195]
+ PartitionCols:_col0
+ Please refer to the previous Select Operator [SEL_192]
+ <-Map 21 [SIMPLE_EDGE] vectorized
+ SHUFFLE [RS_216]
+ PartitionCols:_col0
+ Select Operator [SEL_215] (rows=144002668 width=135)
+ Output:["_col0","_col1"]
+ Filter Operator [FIL_214] (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_213]
+ Group By Operator [GBY_212] (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_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_196] (rows=4058 width=1119)
+ Output:["_col0"]
+ Please refer to the previous Select Operator [SEL_192]
http://git-wip-us.apache.org/repos/asf/hive/blob/851c8aba/ql/src/test/results/clientpositive/perf/tez/query7.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/perf/tez/query7.q.out b/ql/src/test/results/clientpositive/perf/tez/query7.q.out
index 2bb39dd..c78e1e6 100644
--- a/ql/src/test/results/clientpositive/perf/tez/query7.q.out
+++ b/ql/src/test/results/clientpositive/perf/tez/query7.q.out
@@ -58,126 +58,128 @@ Stage-0
limit:100
Stage-1
Reducer 7 vectorized
- File Output Operator [FS_139]
- Limit [LIM_138] (rows=100 width=88)
+ File Output Operator [FS_140]
+ Limit [LIM_139] (rows=100 width=88)
Number of rows:100
- Select Operator [SEL_137] (rows=421657640 width=88)
+ Select Operator [SEL_138] (rows=421657640 width=88)
Output:["_col0","_col1","_col2","_col3","_col4"]
<-Reducer 6 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_136]
- Select Operator [SEL_135] (rows=421657640 width=88)
+ SHUFFLE [RS_137]
+ Select Operator [SEL_136] (rows=421657640 width=88)
Output:["_col0","_col1","_col2","_col3","_col4"]
- Group By Operator [GBY_134] (rows=421657640 width=88)
+ Group By Operator [GBY_135] (rows=421657640 width=88)
Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"],aggregations:["sum(VALUE._col0)","count(VALUE._col1)","sum(VALUE._col2)","count(VALUE._col3)","sum(VALUE._col4)","count(VALUE._col5)","sum(VALUE._col6)","count(VALUE._col7)"],keys:KEY._col0
<-Reducer 5 [SIMPLE_EDGE]
SHUFFLE [RS_29]
PartitionCols:_col0
Group By Operator [GBY_28] (rows=843315281 width=88)
Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"],aggregations:["sum(_col4)","count(_col4)","sum(_col5)","count(_col5)","sum(_col7)","count(_col7)","sum(_col6)","count(_col6)"],keys:_col18
- Merge Join Operator [MERGEJOIN_98] (rows=843315281 width=88)
- Conds:RS_24._col1=RS_125._col0(Inner),Output:["_col4","_col5","_col6","_col7","_col18"]
- <-Map 14 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_125]
- PartitionCols:_col0
- Select Operator [SEL_124] (rows=462000 width=1436)
- Output:["_col0","_col1"]
- Filter Operator [FIL_123] (rows=462000 width=1436)
- predicate:i_item_sk is not null
- TableScan [TS_12] (rows=462000 width=1436)
- default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_item_id"]
- <-Reducer 4 [SIMPLE_EDGE]
- SHUFFLE [RS_24]
- PartitionCols:_col1
- Merge Join Operator [MERGEJOIN_97] (rows=766650239 width=88)
- Conds:RS_21._col3=RS_117._col0(Inner),Output:["_col1","_col4","_col5","_col6","_col7"]
- <-Map 12 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_117]
- PartitionCols:_col0
- Select Operator [SEL_116] (rows=2300 width=1179)
- Output:["_col0"]
- Filter Operator [FIL_115] (rows=2300 width=1179)
- predicate:(((p_channel_email = 'N') or (p_channel_event = 'N')) and p_promo_sk is not null)
- TableScan [TS_9] (rows=2300 width=1179)
- default@promotion,promotion,Tbl:COMPLETE,Col:NONE,Output:["p_promo_sk","p_channel_email","p_channel_event"]
- <-Reducer 3 [SIMPLE_EDGE]
- SHUFFLE [RS_21]
- PartitionCols:_col3
- Merge Join Operator [MERGEJOIN_96] (rows=696954748 width=88)
- Conds:RS_18._col0=RS_109._col0(Inner),Output:["_col1","_col3","_col4","_col5","_col6","_col7"]
- <-Map 10 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_109]
- PartitionCols:_col0
- Select Operator [SEL_108] (rows=36524 width=1119)
- Output:["_col0"]
- Filter Operator [FIL_107] (rows=36524 width=1119)
- predicate:((d_year = 1998) and d_date_sk is not null)
- TableScan [TS_6] (rows=73049 width=1119)
- default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"]
- <-Reducer 2 [SIMPLE_EDGE]
- SHUFFLE [RS_18]
- PartitionCols:_col0
- Merge Join Operator [MERGEJOIN_95] (rows=633595212 width=88)
- Conds:RS_133._col2=RS_101._col0(Inner),Output:["_col0","_col1","_col3","_col4","_col5","_col6","_col7"]
- <-Map 8 [SIMPLE_EDGE] vectorized
- PARTITION_ONLY_SHUFFLE [RS_101]
- PartitionCols:_col0
- Select Operator [SEL_100] (rows=232725 width=385)
- Output:["_col0"]
- Filter Operator [FIL_99] (rows=232725 width=385)
- predicate:((cd_education_status = 'Primary') and (cd_gender = 'F') and (cd_marital_status = 'W') and cd_demo_sk is not null)
- TableScan [TS_3] (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"]
- <-Map 1 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_133]
- PartitionCols:_col2
- Select Operator [SEL_132] (rows=575995635 width=88)
- Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"]
- Filter Operator [FIL_131] (rows=575995635 width=88)
- predicate:((ss_cdemo_sk BETWEEN DynamicValue(RS_16_customer_demographics_cd_demo_sk_min) AND DynamicValue(RS_16_customer_demographics_cd_demo_sk_max) and in_bloom_filter(ss_cdemo_sk, DynamicValue(RS_16_customer_demographics_cd_demo_sk_bloom_filter))) and (ss_item_sk BETWEEN DynamicValue(RS_25_item_i_item_sk_min) AND DynamicValue(RS_25_item_i_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_25_item_i_item_sk_bloom_filter))) and (ss_promo_sk BETWEEN DynamicValue(RS_22_promotion_p_promo_sk_min) AND DynamicValue(RS_22_promotion_p_promo_sk_max) and in_bloom_filter(ss_promo_sk, DynamicValue(RS_22_promotion_p_promo_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_19_date_dim_d_date_sk_min) AND DynamicValue(RS_19_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_19_date_dim_d_date_sk_bloom_filter))) and ss_cdemo_sk is not null and ss_item_sk is not null and ss_promo_sk is not null and ss_sold_dat
e_sk is not null)
- TableScan [TS_0] (rows=575995635 width=88)
- default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_item_sk","ss_cdemo_sk","ss_promo_sk","ss_quantity","ss_list_price","ss_sales_price","ss_coupon_amt"]
- <-Reducer 11 [BROADCAST_EDGE] vectorized
- BROADCAST [RS_114]
- Group By Operator [GBY_113] (rows=1 width=12)
- Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"]
- <-Map 10 [CUSTOM_SIMPLE_EDGE] vectorized
- SHUFFLE [RS_112]
- Group By Operator [GBY_111] (rows=1 width=12)
- Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
- Select Operator [SEL_110] (rows=36524 width=1119)
- Output:["_col0"]
- Please refer to the previous Select Operator [SEL_108]
- <-Reducer 13 [BROADCAST_EDGE] vectorized
- BROADCAST [RS_122]
- Group By Operator [GBY_121] (rows=1 width=12)
- Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"]
- <-Map 12 [CUSTOM_SIMPLE_EDGE] vectorized
- SHUFFLE [RS_120]
- Group By Operator [GBY_119] (rows=1 width=12)
- Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
- Select Operator [SEL_118] (rows=2300 width=1179)
- Output:["_col0"]
- Please refer to the previous Select Operator [SEL_116]
- <-Reducer 15 [BROADCAST_EDGE] vectorized
- BROADCAST [RS_130]
- Group By Operator [GBY_129] (rows=1 width=12)
- Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"]
- <-Map 14 [CUSTOM_SIMPLE_EDGE] vectorized
- SHUFFLE [RS_128]
- Group By Operator [GBY_127] (rows=1 width=12)
- Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
- Select Operator [SEL_126] (rows=462000 width=1436)
- Output:["_col0"]
- Please refer to the previous Select Operator [SEL_124]
- <-Reducer 9 [BROADCAST_EDGE] vectorized
- BROADCAST [RS_106]
- Group By Operator [GBY_105] (rows=1 width=12)
- Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"]
- <-Map 8 [CUSTOM_SIMPLE_EDGE] vectorized
- PARTITION_ONLY_SHUFFLE [RS_104]
- Group By Operator [GBY_103] (rows=1 width=12)
- Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
- Select Operator [SEL_102] (rows=232725 width=385)
- Output:["_col0"]
- Please refer to the previous Select Operator [SEL_100]
+ Top N Key Operator [TNK_55] (rows=843315281 width=88)
+ keys:_col18,sort order:+,top n:100
+ Merge Join Operator [MERGEJOIN_99] (rows=843315281 width=88)
+ Conds:RS_24._col1=RS_126._col0(Inner),Output:["_col4","_col5","_col6","_col7","_col18"]
+ <-Map 14 [SIMPLE_EDGE] vectorized
+ SHUFFLE [RS_126]
+ PartitionCols:_col0
+ Select Operator [SEL_125] (rows=462000 width=1436)
+ Output:["_col0","_col1"]
+ Filter Operator [FIL_124] (rows=462000 width=1436)
+ predicate:i_item_sk is not null
+ TableScan [TS_12] (rows=462000 width=1436)
+ default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_item_id"]
+ <-Reducer 4 [SIMPLE_EDGE]
+ SHUFFLE [RS_24]
+ PartitionCols:_col1
+ Merge Join Operator [MERGEJOIN_98] (rows=766650239 width=88)
+ Conds:RS_21._col3=RS_118._col0(Inner),Output:["_col1","_col4","_col5","_col6","_col7"]
+ <-Map 12 [SIMPLE_EDGE] vectorized
+ SHUFFLE [RS_118]
+ PartitionCols:_col0
+ Select Operator [SEL_117] (rows=2300 width=1179)
+ Output:["_col0"]
+ Filter Operator [FIL_116] (rows=2300 width=1179)
+ predicate:(((p_channel_email = 'N') or (p_channel_event = 'N')) and p_promo_sk is not null)
+ TableScan [TS_9] (rows=2300 width=1179)
+ default@promotion,promotion,Tbl:COMPLETE,Col:NONE,Output:["p_promo_sk","p_channel_email","p_channel_event"]
+ <-Reducer 3 [SIMPLE_EDGE]
+ SHUFFLE [RS_21]
+ PartitionCols:_col3
+ Merge Join Operator [MERGEJOIN_97] (rows=696954748 width=88)
+ Conds:RS_18._col0=RS_110._col0(Inner),Output:["_col1","_col3","_col4","_col5","_col6","_col7"]
+ <-Map 10 [SIMPLE_EDGE] vectorized
+ SHUFFLE [RS_110]
+ PartitionCols:_col0
+ Select Operator [SEL_109] (rows=36524 width=1119)
+ Output:["_col0"]
+ Filter Operator [FIL_108] (rows=36524 width=1119)
+ predicate:((d_year = 1998) and d_date_sk is not null)
+ TableScan [TS_6] (rows=73049 width=1119)
+ default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"]
+ <-Reducer 2 [SIMPLE_EDGE]
+ SHUFFLE [RS_18]
+ PartitionCols:_col0
+ Merge Join Operator [MERGEJOIN_96] (rows=633595212 width=88)
+ Conds:RS_134._col2=RS_102._col0(Inner),Output:["_col0","_col1","_col3","_col4","_col5","_col6","_col7"]
+ <-Map 8 [SIMPLE_EDGE] vectorized
+ PARTITION_ONLY_SHUFFLE [RS_102]
+ PartitionCols:_col0
+ Select Operator [SEL_101] (rows=232725 width=385)
+ Output:["_col0"]
+ Filter Operator [FIL_100] (rows=232725 width=385)
+ predicate:((cd_education_status = 'Primary') and (cd_gender = 'F') and (cd_marital_status = 'W') and cd_demo_sk is not null)
+ TableScan [TS_3] (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"]
+ <-Map 1 [SIMPLE_EDGE] vectorized
+ SHUFFLE [RS_134]
+ PartitionCols:_col2
+ Select Operator [SEL_133] (rows=575995635 width=88)
+ Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"]
+ Filter Operator [FIL_132] (rows=575995635 width=88)
+ predicate:((ss_cdemo_sk BETWEEN DynamicValue(RS_16_customer_demographics_cd_demo_sk_min) AND DynamicValue(RS_16_customer_demographics_cd_demo_sk_max) and in_bloom_filter(ss_cdemo_sk, DynamicValue(RS_16_customer_demographics_cd_demo_sk_bloom_filter))) and (ss_item_sk BETWEEN DynamicValue(RS_25_item_i_item_sk_min) AND DynamicValue(RS_25_item_i_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_25_item_i_item_sk_bloom_filter))) and (ss_promo_sk BETWEEN DynamicValue(RS_22_promotion_p_promo_sk_min) AND DynamicValue(RS_22_promotion_p_promo_sk_max) and in_bloom_filter(ss_promo_sk, DynamicValue(RS_22_promotion_p_promo_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_19_date_dim_d_date_sk_min) AND DynamicValue(RS_19_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_19_date_dim_d_date_sk_bloom_filter))) and ss_cdemo_sk is not null and ss_item_sk is not null and ss_promo_sk is not null and ss_sold_d
ate_sk is not null)
+ TableScan [TS_0] (rows=575995635 width=88)
+ default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_item_sk","ss_cdemo_sk","ss_promo_sk","ss_quantity","ss_list_price","ss_sales_price","ss_coupon_amt"]
+ <-Reducer 11 [BROADCAST_EDGE] vectorized
+ BROADCAST [RS_115]
+ Group By Operator [GBY_114] (rows=1 width=12)
+ Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"]
+ <-Map 10 [CUSTOM_SIMPLE_EDGE] vectorized
+ SHUFFLE [RS_113]
+ Group By Operator [GBY_112] (rows=1 width=12)
+ Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
+ Select Operator [SEL_111] (rows=36524 width=1119)
+ Output:["_col0"]
+ Please refer to the previous Select Operator [SEL_109]
+ <-Reducer 13 [BROADCAST_EDGE] vectorized
+ BROADCAST [RS_123]
+ Group By Operator [GBY_122] (rows=1 width=12)
+ Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"]
+ <-Map 12 [CUSTOM_SIMPLE_EDGE] vectorized
+ SHUFFLE [RS_121]
+ Group By Operator [GBY_120] (rows=1 width=12)
+ Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
+ Select Operator [SEL_119] (rows=2300 width=1179)
+ Output:["_col0"]
+ Please refer to the previous Select Operator [SEL_117]
+ <-Reducer 15 [BROADCAST_EDGE] vectorized
+ BROADCAST [RS_131]
+ Group By Operator [GBY_130] (rows=1 width=12)
+ Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"]
+ <-Map 14 [CUSTOM_SIMPLE_EDGE] vectorized
+ SHUFFLE [RS_129]
+ Group By Operator [GBY_128] (rows=1 width=12)
+ Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
+ Select Operator [SEL_127] (rows=462000 width=1436)
+ Output:["_col0"]
+ Please refer to the previous Select Operator [SEL_125]
+ <-Reducer 9 [BROADCAST_EDGE] vectorized
+ BROADCAST [RS_107]
+ Group By Operator [GBY_106] (rows=1 width=12)
+ Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"]
+ <-Map 8 [CUSTOM_SIMPLE_EDGE] vectorized
+ PARTITION_ONLY_SHUFFLE [RS_105]
+ Group By Operator [GBY_104] (rows=1 width=12)
+ Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
+ Select Operator [SEL_103] (rows=232725 width=385)
+ Output:["_col0"]
+ Please refer to the previous Select Operator [SEL_101]