You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by jc...@apache.org on 2018/10/13 18:16:09 UTC
[3/6] hive git commit: HIVE-20704: Extend HivePreFilteringRule to
support other functions (Jesus Camacho Rodriguez,
reviewed by Ashutosh Chauhan)
http://git-wip-us.apache.org/repos/asf/hive/blob/f0b76e24/ql/src/test/results/clientpositive/perf/tez/query13.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/perf/tez/query13.q.out b/ql/src/test/results/clientpositive/perf/tez/query13.q.out
index c33e50e..53edb5e 100644
--- a/ql/src/test/results/clientpositive/perf/tez/query13.q.out
+++ b/ql/src/test/results/clientpositive/perf/tez/query13.q.out
@@ -115,166 +115,156 @@ POSTHOOK: Output: hdfs://### HDFS PATH ###
Plan optimized by CBO.
Vertex dependency in root stage
-Map 1 <- Reducer 11 (BROADCAST_EDGE), Reducer 13 (BROADCAST_EDGE), Reducer 15 (BROADCAST_EDGE), Reducer 17 (BROADCAST_EDGE), Reducer 9 (BROADCAST_EDGE)
+Map 9 <- Reducer 11 (BROADCAST_EDGE), Reducer 13 (BROADCAST_EDGE), Reducer 16 (BROADCAST_EDGE), Reducer 8 (BROADCAST_EDGE)
Reducer 11 <- Map 10 (CUSTOM_SIMPLE_EDGE)
Reducer 13 <- Map 12 (CUSTOM_SIMPLE_EDGE)
-Reducer 15 <- Map 14 (CUSTOM_SIMPLE_EDGE)
-Reducer 17 <- Map 16 (CUSTOM_SIMPLE_EDGE)
-Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE)
+Reducer 16 <- Map 15 (CUSTOM_SIMPLE_EDGE)
+Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 9 (SIMPLE_EDGE)
Reducer 3 <- Map 10 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE)
Reducer 4 <- Map 12 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE)
Reducer 5 <- Map 14 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE)
-Reducer 6 <- Map 16 (SIMPLE_EDGE), Reducer 5 (SIMPLE_EDGE)
+Reducer 6 <- Map 15 (SIMPLE_EDGE), Reducer 5 (SIMPLE_EDGE)
Reducer 7 <- Reducer 6 (CUSTOM_SIMPLE_EDGE)
-Reducer 9 <- Map 8 (CUSTOM_SIMPLE_EDGE)
+Reducer 8 <- Map 1 (CUSTOM_SIMPLE_EDGE)
Stage-0
Fetch Operator
limit:-1
Stage-1
Reducer 7 vectorized
- File Output Operator [FS_167]
- Select Operator [SEL_166] (rows=1 width=256)
+ File Output Operator [FS_162]
+ Select Operator [SEL_161] (rows=1 width=256)
Output:["_col0","_col1","_col2","_col3"]
- Group By Operator [GBY_165] (rows=1 width=256)
+ Group By Operator [GBY_160] (rows=1 width=256)
Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(VALUE._col0)","count(VALUE._col1)","sum(VALUE._col2)","count(VALUE._col3)","sum(VALUE._col4)","count(VALUE._col5)"]
<-Reducer 6 [CUSTOM_SIMPLE_EDGE]
PARTITION_ONLY_SHUFFLE [RS_37]
Group By Operator [GBY_36] (rows=1 width=256)
- Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(_col5)","count(_col5)","sum(_col7)","count(_col7)","sum(_col8)","count(_col8)"]
- Merge Join Operator [MERGEJOIN_121] (rows=8066665 width=1014)
- Conds:RS_32._col4=RS_156._col0(Inner),Output:["_col5","_col7","_col8"]
- <-Map 16 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_156]
- PartitionCols:_col0
- Select Operator [SEL_155] (rows=1704 width=1910)
- Output:["_col0"]
- Filter Operator [FIL_154] (rows=1704 width=1910)
- predicate:s_store_sk is not null
- TableScan [TS_15] (rows=1704 width=1910)
- default@store,store,Tbl:COMPLETE,Col:NONE,Output:["s_store_sk"]
- <-Reducer 5 [SIMPLE_EDGE]
- SHUFFLE [RS_32]
- PartitionCols:_col4
- Filter Operator [FIL_31] (rows=7333332 width=1014)
- predicate:(((_col18) IN ('KY', 'GA', 'NM') and _col9 BETWEEN 100 AND 200) or ((_col18) IN ('MT', 'OR', 'IN') and _col9 BETWEEN 150 AND 300) or ((_col18) IN ('WI', 'MO', 'WV') and _col9 BETWEEN 50 AND 250))
- Merge Join Operator [MERGEJOIN_120] (rows=22000000 width=1014)
- Conds:RS_28._col3=RS_148._col0(Inner),Output:["_col4","_col5","_col7","_col8","_col9","_col18"]
- <-Map 14 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_148]
- PartitionCols:_col0
- Select Operator [SEL_147] (rows=20000000 width=1014)
- Output:["_col0","_col1"]
- Filter Operator [FIL_146] (rows=20000000 width=1014)
- predicate:((ca_country = 'United States') and ca_address_sk is not null)
- TableScan [TS_12] (rows=40000000 width=1014)
- default@customer_address,customer_address,Tbl:COMPLETE,Col:NONE,Output:["ca_address_sk","ca_state","ca_country"]
- <-Reducer 4 [SIMPLE_EDGE]
- SHUFFLE [RS_28]
- PartitionCols:_col3
- Filter Operator [FIL_27] (rows=10647918 width=88)
- predicate:(((_col13 = 'D') and (_col14 = 'Primary') and _col6 BETWEEN 50 AND 100 and (_col16 = 1)) or ((_col13 = 'M') and (_col14 = '4 yr Degree') and _col6 BETWEEN 100 AND 150 and (_col16 = 3)) or ((_col13 = 'U') and (_col14 = 'Advanced Degree') and _col6 BETWEEN 150 AND 200 and (_col16 = 1)))
- Merge Join Operator [MERGEJOIN_119] (rows=255550079 width=88)
- Conds:RS_24._col2=RS_140._col0(Inner),Output:["_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col13","_col14","_col16"]
- <-Map 12 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_140]
- PartitionCols:_col0
- Select Operator [SEL_139] (rows=7200 width=107)
- Output:["_col0","_col1"]
- Filter Operator [FIL_138] (rows=7200 width=107)
- predicate:((hd_dep_count) IN (3, 1) and hd_demo_sk is not null)
- TableScan [TS_9] (rows=7200 width=107)
- default@household_demographics,household_demographics,Tbl:COMPLETE,Col:NONE,Output:["hd_demo_sk","hd_dep_count"]
- <-Reducer 3 [SIMPLE_EDGE]
- SHUFFLE [RS_24]
- PartitionCols:_col2
- Merge Join Operator [MERGEJOIN_118] (rows=232318249 width=88)
- Conds:RS_21._col1=RS_132._col0(Inner),Output:["_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col13","_col14"]
- <-Map 10 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_132]
- PartitionCols:_col0
- Select Operator [SEL_131] (rows=1861800 width=385)
- Output:["_col0","_col1","_col2"]
- Filter Operator [FIL_130] (rows=1861800 width=385)
- predicate:((cd_education_status) IN ('4 yr Degree', 'Primary', 'Advanced Degree') and (cd_marital_status) IN ('M', 'D', 'U') and 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_marital_status","cd_education_status"]
- <-Reducer 2 [SIMPLE_EDGE]
- SHUFFLE [RS_21]
- PartitionCols:_col1
- Merge Join Operator [MERGEJOIN_117] (rows=211198404 width=88)
- Conds:RS_164._col0=RS_124._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9"]
- <-Map 8 [SIMPLE_EDGE] vectorized
- PARTITION_ONLY_SHUFFLE [RS_124]
- PartitionCols:_col0
- Select Operator [SEL_123] (rows=36524 width=1119)
- Output:["_col0"]
- Filter Operator [FIL_122] (rows=36524 width=1119)
- predicate:((d_year = 2001) and d_date_sk is not null)
- TableScan [TS_3] (rows=73049 width=1119)
- default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"]
- <-Map 1 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_164]
- PartitionCols:_col0
- Select Operator [SEL_163] (rows=191998545 width=88)
- Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9"]
- Filter Operator [FIL_162] (rows=191998545 width=88)
- predicate:((ss_addr_sk BETWEEN DynamicValue(RS_29_customer_address_ca_address_sk_min) AND DynamicValue(RS_29_customer_address_ca_address_sk_max) and in_bloom_filter(ss_addr_sk, DynamicValue(RS_29_customer_address_ca_address_sk_bloom_filter))) and (ss_cdemo_sk BETWEEN DynamicValue(RS_22_customer_demographics_cd_demo_sk_min) AND DynamicValue(RS_22_customer_demographics_cd_demo_sk_max) and in_bloom_filter(ss_cdemo_sk, DynamicValue(RS_22_customer_demographics_cd_demo_sk_bloom_filter))) and (ss_hdemo_sk BETWEEN DynamicValue(RS_25_household_demographics_hd_demo_sk_min) AND DynamicValue(RS_25_household_demographics_hd_demo_sk_max) and in_bloom_filter(ss_hdemo_sk, DynamicValue(RS_25_household_demographics_hd_demo_sk_bloom_filter))) and (ss_sales_price BETWEEN 100 AND 150 or ss_sales_price BETWEEN 50 AND 100 or ss_sales_price BETWEEN 150 AND 200) 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_store_sk BETWEEN DynamicValue(RS_33_store_s_store_sk_min) AND DynamicValue(RS_33_store_s_store_sk_max) and in_bloom_filter(ss_store_sk, DynamicValue(RS_33_store_s_store_sk_bloom_filter))) and ss_addr_sk is not null and ss_cdemo_sk is not null and ss_hdemo_sk is not null and ss_sold_date_sk is not null and ss_store_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_cdemo_sk","ss_hdemo_sk","ss_addr_sk","ss_store_sk","ss_quantity","ss_sales_price","ss_ext_sales_price","ss_ext_wholesale_cost","ss_net_profit"]
- <-Reducer 11 [BROADCAST_EDGE] vectorized
- BROADCAST [RS_137]
- Group By Operator [GBY_136] (rows=1 width=12)
- Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1861800)"]
- <-Map 10 [CUSTOM_SIMPLE_EDGE] vectorized
- SHUFFLE [RS_135]
- Group By Operator [GBY_134] (rows=1 width=12)
- Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1861800)"]
- Select Operator [SEL_133] (rows=1861800 width=385)
- Output:["_col0"]
- Please refer to the previous Select Operator [SEL_131]
- <-Reducer 13 [BROADCAST_EDGE] vectorized
- BROADCAST [RS_145]
- Group By Operator [GBY_144] (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_143]
- Group By Operator [GBY_142] (rows=1 width=12)
- Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
- Select Operator [SEL_141] (rows=7200 width=107)
- Output:["_col0"]
- Please refer to the previous Select Operator [SEL_139]
- <-Reducer 15 [BROADCAST_EDGE] vectorized
- BROADCAST [RS_153]
- Group By Operator [GBY_152] (rows=1 width=12)
- Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=20000000)"]
- <-Map 14 [CUSTOM_SIMPLE_EDGE] vectorized
- SHUFFLE [RS_151]
- Group By Operator [GBY_150] (rows=1 width=12)
- Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=20000000)"]
- Select Operator [SEL_149] (rows=20000000 width=1014)
- Output:["_col0"]
- Please refer to the previous Select Operator [SEL_147]
- <-Reducer 17 [BROADCAST_EDGE] vectorized
- BROADCAST [RS_161]
- Group By Operator [GBY_160] (rows=1 width=12)
- Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"]
- <-Map 16 [CUSTOM_SIMPLE_EDGE] vectorized
- SHUFFLE [RS_159]
- Group By Operator [GBY_158] (rows=1 width=12)
- Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
- Select Operator [SEL_157] (rows=1704 width=1910)
- Output:["_col0"]
- Please refer to the previous Select Operator [SEL_155]
- <-Reducer 9 [BROADCAST_EDGE] vectorized
- BROADCAST [RS_129]
- Group By Operator [GBY_128] (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_127]
- Group By Operator [GBY_126] (rows=1 width=12)
- Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
- Select Operator [SEL_125] (rows=36524 width=1119)
- Output:["_col0"]
- Please refer to the previous Select Operator [SEL_123]
+ Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(_col6)","count(_col6)","sum(_col8)","count(_col8)","sum(_col9)","count(_col9)"]
+ Select Operator [SEL_35] (rows=1431552 width=88)
+ Output:["_col6","_col8","_col9"]
+ Filter Operator [FIL_34] (rows=1431552 width=88)
+ predicate:(((_col19 = 'D') and (_col20 = 'Primary') and _col7 BETWEEN 50 AND 100 and (_col14 = 1)) or ((_col19 = 'M') and (_col20 = '4 yr Degree') and _col7 BETWEEN 100 AND 150 and (_col14 = 3)) or ((_col19 = 'U') and (_col20 = 'Advanced Degree') and _col7 BETWEEN 150 AND 200 and (_col14 = 1)))
+ Merge Join Operator [MERGEJOIN_121] (rows=34357287 width=88)
+ Conds:RS_31._col2=RS_148._col0(Inner),Output:["_col6","_col7","_col8","_col9","_col14","_col19","_col20"]
+ <-Map 15 [SIMPLE_EDGE] vectorized
+ SHUFFLE [RS_148]
+ PartitionCols:_col0
+ Select Operator [SEL_147] (rows=1861800 width=385)
+ Output:["_col0","_col1","_col2"]
+ Filter Operator [FIL_146] (rows=1861800 width=385)
+ predicate:((cd_education_status) IN ('4 yr Degree', 'Primary', 'Advanced Degree') and (cd_marital_status) IN ('M', 'D', 'U') and cd_demo_sk is not null)
+ TableScan [TS_15] (rows=1861800 width=385)
+ default@customer_demographics,customer_demographics,Tbl:COMPLETE,Col:NONE,Output:["cd_demo_sk","cd_marital_status","cd_education_status"]
+ <-Reducer 5 [SIMPLE_EDGE]
+ SHUFFLE [RS_31]
+ PartitionCols:_col2
+ Filter Operator [FIL_30] (rows=31233897 width=88)
+ predicate:(((_col16) IN ('KY', 'GA', 'NM') and _col10 BETWEEN 100 AND 200) or ((_col16) IN ('MT', 'OR', 'IN') and _col10 BETWEEN 150 AND 300) or ((_col16) IN ('WI', 'MO', 'WV') and _col10 BETWEEN 50 AND 250))
+ Merge Join Operator [MERGEJOIN_120] (rows=93701693 width=88)
+ Conds:RS_27._col4=RS_159._col0(Inner),Output:["_col2","_col6","_col7","_col8","_col9","_col10","_col14","_col16"]
+ <-Map 14 [SIMPLE_EDGE] vectorized
+ SHUFFLE [RS_159]
+ PartitionCols:_col0
+ Select Operator [SEL_158] (rows=20000000 width=1014)
+ Output:["_col0","_col1"]
+ Filter Operator [FIL_157] (rows=20000000 width=1014)
+ predicate:((ca_country = 'United States') and (ca_state) IN ('KY', 'GA', 'NM', 'MT', 'OR', 'IN', 'WI', 'MO', 'WV') and ca_address_sk is not null)
+ TableScan [TS_12] (rows=40000000 width=1014)
+ default@customer_address,customer_address,Tbl:COMPLETE,Col:NONE,Output:["ca_address_sk","ca_state","ca_country"]
+ <-Reducer 4 [SIMPLE_EDGE]
+ SHUFFLE [RS_27]
+ PartitionCols:_col4
+ Merge Join Operator [MERGEJOIN_119] (rows=85183356 width=88)
+ Conds:RS_24._col3=RS_140._col0(Inner),Output:["_col2","_col4","_col6","_col7","_col8","_col9","_col10","_col14"]
+ <-Map 12 [SIMPLE_EDGE] vectorized
+ SHUFFLE [RS_140]
+ PartitionCols:_col0
+ Select Operator [SEL_139] (rows=7200 width=107)
+ Output:["_col0","_col1"]
+ Filter Operator [FIL_138] (rows=7200 width=107)
+ predicate:((hd_dep_count) IN (3, 1) and hd_demo_sk is not null)
+ TableScan [TS_9] (rows=7200 width=107)
+ default@household_demographics,household_demographics,Tbl:COMPLETE,Col:NONE,Output:["hd_demo_sk","hd_dep_count"]
+ <-Reducer 3 [SIMPLE_EDGE]
+ SHUFFLE [RS_24]
+ PartitionCols:_col3
+ Merge Join Operator [MERGEJOIN_118] (rows=77439413 width=88)
+ Conds:RS_21._col1=RS_132._col0(Inner),Output:["_col2","_col3","_col4","_col6","_col7","_col8","_col9","_col10"]
+ <-Map 10 [SIMPLE_EDGE] vectorized
+ SHUFFLE [RS_132]
+ PartitionCols:_col0
+ Select Operator [SEL_131] (rows=36524 width=1119)
+ Output:["_col0"]
+ Filter Operator [FIL_130] (rows=36524 width=1119)
+ predicate:((d_year = 2001) 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_21]
+ PartitionCols:_col1
+ Merge Join Operator [MERGEJOIN_117] (rows=70399465 width=88)
+ Conds:RS_124._col0=RS_156._col4(Inner),Output:["_col1","_col2","_col3","_col4","_col6","_col7","_col8","_col9","_col10"]
+ <-Map 1 [SIMPLE_EDGE] vectorized
+ PARTITION_ONLY_SHUFFLE [RS_124]
+ PartitionCols:_col0
+ Select Operator [SEL_123] (rows=1704 width=1910)
+ Output:["_col0"]
+ Filter Operator [FIL_122] (rows=1704 width=1910)
+ predicate:s_store_sk is not null
+ TableScan [TS_0] (rows=1704 width=1910)
+ default@store,store,Tbl:COMPLETE,Col:NONE,Output:["s_store_sk"]
+ <-Map 9 [SIMPLE_EDGE] vectorized
+ SHUFFLE [RS_156]
+ PartitionCols:_col4
+ Select Operator [SEL_155] (rows=63999513 width=88)
+ Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9"]
+ Filter Operator [FIL_154] (rows=63999513 width=88)
+ predicate:((ss_cdemo_sk BETWEEN DynamicValue(RS_32_customer_demographics_cd_demo_sk_min) AND DynamicValue(RS_32_customer_demographics_cd_demo_sk_max) and in_bloom_filter(ss_cdemo_sk, DynamicValue(RS_32_customer_demographics_cd_demo_sk_bloom_filter))) and (ss_hdemo_sk BETWEEN DynamicValue(RS_25_household_demographics_hd_demo_sk_min) AND DynamicValue(RS_25_household_demographics_hd_demo_sk_max) and in_bloom_filter(ss_hdemo_sk, DynamicValue(RS_25_household_demographics_hd_demo_sk_bloom_filter))) and (ss_net_profit BETWEEN 100 AND 200 or ss_net_profit BETWEEN 150 AND 300 or ss_net_profit BETWEEN 50 AND 250) and (ss_sales_price BETWEEN 100 AND 150 or ss_sales_price BETWEEN 50 AND 100 or ss_sales_price BETWEEN 150 AND 200) and (ss_sold_date_sk BETWEEN DynamicValue(RS_22_date_dim_d_date_sk_min) AND DynamicValue(RS_22_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_22_date_dim_d_date_sk_bloom_filter))) and (ss_store_
sk BETWEEN DynamicValue(RS_18_store_s_store_sk_min) AND DynamicValue(RS_18_store_s_store_sk_max) and in_bloom_filter(ss_store_sk, DynamicValue(RS_18_store_s_store_sk_bloom_filter))) and ss_addr_sk is not null and ss_cdemo_sk is not null and ss_hdemo_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null)
+ TableScan [TS_3] (rows=575995635 width=88)
+ default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_cdemo_sk","ss_hdemo_sk","ss_addr_sk","ss_store_sk","ss_quantity","ss_sales_price","ss_ext_sales_price","ss_ext_wholesale_cost","ss_net_profit"]
+ <-Reducer 11 [BROADCAST_EDGE] vectorized
+ BROADCAST [RS_137]
+ Group By Operator [GBY_136] (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_135]
+ Group By Operator [GBY_134] (rows=1 width=12)
+ Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
+ Select Operator [SEL_133] (rows=36524 width=1119)
+ Output:["_col0"]
+ Please refer to the previous Select Operator [SEL_131]
+ <-Reducer 13 [BROADCAST_EDGE] vectorized
+ BROADCAST [RS_145]
+ Group By Operator [GBY_144] (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_143]
+ Group By Operator [GBY_142] (rows=1 width=12)
+ Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
+ Select Operator [SEL_141] (rows=7200 width=107)
+ Output:["_col0"]
+ Please refer to the previous Select Operator [SEL_139]
+ <-Reducer 16 [BROADCAST_EDGE] vectorized
+ BROADCAST [RS_153]
+ Group By Operator [GBY_152] (rows=1 width=12)
+ Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1861800)"]
+ <-Map 15 [CUSTOM_SIMPLE_EDGE] vectorized
+ SHUFFLE [RS_151]
+ Group By Operator [GBY_150] (rows=1 width=12)
+ Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1861800)"]
+ Select Operator [SEL_149] (rows=1861800 width=385)
+ Output:["_col0"]
+ Please refer to the previous Select Operator [SEL_147]
+ <-Reducer 8 [BROADCAST_EDGE] vectorized
+ BROADCAST [RS_129]
+ Group By Operator [GBY_128] (rows=1 width=12)
+ Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"]
+ <-Map 1 [CUSTOM_SIMPLE_EDGE] vectorized
+ PARTITION_ONLY_SHUFFLE [RS_127]
+ Group By Operator [GBY_126] (rows=1 width=12)
+ Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
+ Select Operator [SEL_125] (rows=1704 width=1910)
+ Output:["_col0"]
+ Please refer to the previous Select Operator [SEL_123]
http://git-wip-us.apache.org/repos/asf/hive/blob/f0b76e24/ql/src/test/results/clientpositive/perf/tez/query47.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/perf/tez/query47.q.out b/ql/src/test/results/clientpositive/perf/tez/query47.q.out
index 0ba3fbf..f9c21aa 100644
--- a/ql/src/test/results/clientpositive/perf/tez/query47.q.out
+++ b/ql/src/test/results/clientpositive/perf/tez/query47.q.out
@@ -152,30 +152,30 @@ Stage-0
Select Operator [SEL_328] (rows=63887519 width=88)
Output:["rank_window_1","_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"]
Filter Operator [FIL_327] (rows=63887519 width=88)
- predicate:((_col0 > 0) and (_col1 = 2000) and rank_window_1 is not null)
+ predicate:((_col0 > 0) and (_col3 = 2000) and rank_window_1 is not null)
PTF Operator [PTF_326] (rows=383325119 width=88)
- Function definitions:[{},{"name:":"windowingtablefunction","order by:":"_col1 ASC NULLS LAST, _col2 ASC NULLS LAST","partition by:":"_col4, _col3, _col5, _col6"}]
+ Function definitions:[{},{"name:":"windowingtablefunction","order by:":"_col3 ASC NULLS LAST, _col4 ASC NULLS LAST","partition by:":"_col2, _col1, _col5, _col6"}]
Select Operator [SEL_325] (rows=383325119 width=88)
Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"]
<-Reducer 10 [SIMPLE_EDGE] vectorized
SHUFFLE [RS_324]
- PartitionCols:_col3, _col2, _col4, _col5
+ PartitionCols:_col1, _col0, _col4, _col5
Select Operator [SEL_323] (rows=383325119 width=88)
Output:["avg_window_0","_col0","_col1","_col2","_col3","_col4","_col5","_col6"]
PTF Operator [PTF_322] (rows=383325119 width=88)
- Function definitions:[{},{"name:":"windowingtablefunction","order by:":"_col3 ASC NULLS FIRST, _col2 ASC NULLS FIRST, _col4 ASC NULLS FIRST, _col5 ASC NULLS FIRST, _col0 ASC NULLS FIRST","partition by:":"_col3, _col2, _col4, _col5, _col0"}]
+ Function definitions:[{},{"name:":"windowingtablefunction","order by:":"_col1 ASC NULLS FIRST, _col0 ASC NULLS FIRST, _col4 ASC NULLS FIRST, _col5 ASC NULLS FIRST, _col2 ASC NULLS FIRST","partition by:":"_col1, _col0, _col4, _col5, _col2"}]
Select Operator [SEL_321] (rows=383325119 width=88)
Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"]
<-Reducer 5 [SIMPLE_EDGE] vectorized
SHUFFLE [RS_310]
- PartitionCols:_col3, _col2, _col4, _col5, _col0
+ PartitionCols:_col1, _col0, _col4, _col5, _col2
Group By Operator [GBY_307] (rows=383325119 width=88)
Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4, KEY._col5
<-Reducer 4 [SIMPLE_EDGE]
SHUFFLE [RS_93]
PartitionCols:_col0, _col1, _col2, _col3, _col4, _col5
Group By Operator [GBY_92] (rows=766650239 width=88)
- Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"],aggregations:["sum(_col3)"],keys:_col5, _col6, _col8, _col9, _col11, _col12
+ Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"],aggregations:["sum(_col3)"],keys:_col8, _col9, _col5, _col6, _col11, _col12
Merge Join Operator [MERGEJOIN_278] (rows=766650239 width=88)
Conds:RS_88._col2=RS_298._col0(Inner),Output:["_col3","_col5","_col6","_col8","_col9","_col11","_col12"]
<-Map 16 [SIMPLE_EDGE] vectorized
@@ -212,7 +212,7 @@ Stage-0
Select Operator [SEL_281] (rows=73049 width=1119)
Output:["_col0","_col1","_col2"]
Filter Operator [FIL_280] (rows=73049 width=1119)
- predicate:(((struct(d_year,d_moy)) IN (const struct(1999,12), const struct(2001,1)) or (d_year = 2000)) and d_date_sk is not null)
+ predicate:(((d_year = 2000) or (struct(d_year,d_moy)) IN (const struct(1999,12), const struct(2001,1))) and (d_year) IN (2000, 1999, 2001) and d_date_sk is not null)
TableScan [TS_73] (rows=73049 width=1119)
default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year","d_moy"]
<-Map 1 [SIMPLE_EDGE] vectorized
@@ -265,12 +265,12 @@ Stage-0
Filter Operator [FIL_313] (rows=383325119 width=88)
predicate:rank_window_0 is not null
PTF Operator [PTF_312] (rows=383325119 width=88)
- Function definitions:[{},{"name:":"windowingtablefunction","order by:":"_col0 ASC NULLS LAST, _col1 ASC NULLS LAST","partition by:":"_col3, _col2, _col4, _col5"}]
+ Function definitions:[{},{"name:":"windowingtablefunction","order by:":"_col2 ASC NULLS LAST, _col3 ASC NULLS LAST","partition by:":"_col1, _col0, _col4, _col5"}]
Select Operator [SEL_311] (rows=383325119 width=88)
Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"]
<-Reducer 5 [SIMPLE_EDGE] vectorized
SHUFFLE [RS_308]
- PartitionCols:_col3, _col2, _col4, _col5
+ PartitionCols:_col1, _col0, _col4, _col5
Please refer to the previous Group By Operator [GBY_307]
<-Reducer 9 [SIMPLE_EDGE] vectorized
SHUFFLE [RS_320]
@@ -280,11 +280,11 @@ Stage-0
Filter Operator [FIL_318] (rows=383325119 width=88)
predicate:rank_window_0 is not null
PTF Operator [PTF_317] (rows=383325119 width=88)
- Function definitions:[{},{"name:":"windowingtablefunction","order by:":"_col0 ASC NULLS LAST, _col1 ASC NULLS LAST","partition by:":"_col3, _col2, _col4, _col5"}]
+ Function definitions:[{},{"name:":"windowingtablefunction","order by:":"_col2 ASC NULLS LAST, _col3 ASC NULLS LAST","partition by:":"_col1, _col0, _col4, _col5"}]
Select Operator [SEL_316] (rows=383325119 width=88)
Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"]
<-Reducer 5 [SIMPLE_EDGE] vectorized
SHUFFLE [RS_309]
- PartitionCols:_col3, _col2, _col4, _col5
+ PartitionCols:_col1, _col0, _col4, _col5
Please refer to the previous Group By Operator [GBY_307]
http://git-wip-us.apache.org/repos/asf/hive/blob/f0b76e24/ql/src/test/results/clientpositive/perf/tez/query48.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/perf/tez/query48.q.out b/ql/src/test/results/clientpositive/perf/tez/query48.q.out
index e07c160..ffb9aa2 100644
--- a/ql/src/test/results/clientpositive/perf/tez/query48.q.out
+++ b/ql/src/test/results/clientpositive/perf/tez/query48.q.out
@@ -143,135 +143,125 @@ POSTHOOK: Output: hdfs://### HDFS PATH ###
Plan optimized by CBO.
Vertex dependency in root stage
-Map 1 <- Reducer 10 (BROADCAST_EDGE), Reducer 12 (BROADCAST_EDGE), Reducer 14 (BROADCAST_EDGE), Reducer 8 (BROADCAST_EDGE)
+Map 8 <- Reducer 10 (BROADCAST_EDGE), Reducer 12 (BROADCAST_EDGE), Reducer 7 (BROADCAST_EDGE)
Reducer 10 <- Map 9 (CUSTOM_SIMPLE_EDGE)
Reducer 12 <- Map 11 (CUSTOM_SIMPLE_EDGE)
-Reducer 14 <- Map 13 (CUSTOM_SIMPLE_EDGE)
-Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 7 (SIMPLE_EDGE)
+Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE)
Reducer 3 <- Map 9 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE)
Reducer 4 <- Map 11 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE)
Reducer 5 <- Map 13 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE)
Reducer 6 <- Reducer 5 (CUSTOM_SIMPLE_EDGE)
-Reducer 8 <- Map 7 (CUSTOM_SIMPLE_EDGE)
+Reducer 7 <- Map 1 (CUSTOM_SIMPLE_EDGE)
Stage-0
Fetch Operator
limit:-1
Stage-1
Reducer 6 vectorized
- File Output Operator [FS_133]
- Group By Operator [GBY_132] (rows=1 width=8)
+ File Output Operator [FS_128]
+ Group By Operator [GBY_127] (rows=1 width=8)
Output:["_col0"],aggregations:["sum(VALUE._col0)"]
<-Reducer 5 [CUSTOM_SIMPLE_EDGE]
PARTITION_ONLY_SHUFFLE [RS_30]
Group By Operator [GBY_29] (rows=1 width=8)
- Output:["_col0"],aggregations:["sum(_col4)"]
- Merge Join Operator [MERGEJOIN_96] (rows=93701696 width=88)
- Conds:RS_25._col3=RS_123._col0(Inner),Output:["_col4"]
- <-Map 13 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_123]
- PartitionCols:_col0
- Select Operator [SEL_122] (rows=1704 width=1910)
- Output:["_col0"]
- Filter Operator [FIL_121] (rows=1704 width=1910)
- predicate:s_store_sk is not null
- TableScan [TS_12] (rows=1704 width=1910)
- default@store,store,Tbl:COMPLETE,Col:NONE,Output:["s_store_sk"]
- <-Reducer 4 [SIMPLE_EDGE]
- SHUFFLE [RS_25]
- PartitionCols:_col3
- Filter Operator [FIL_24] (rows=85183359 width=88)
- predicate:(((_col13) IN ('KY', 'GA', 'NM') and _col6 BETWEEN 0 AND 2000) or ((_col13) IN ('MT', 'OR', 'IN') and _col6 BETWEEN 150 AND 3000) or ((_col13) IN ('WI', 'MO', 'WV') and _col6 BETWEEN 50 AND 25000))
- Merge Join Operator [MERGEJOIN_95] (rows=255550079 width=88)
- Conds:RS_21._col2=RS_115._col0(Inner),Output:["_col3","_col4","_col6","_col13"]
- <-Map 11 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_115]
- PartitionCols:_col0
- Select Operator [SEL_114] (rows=20000000 width=1014)
- Output:["_col0","_col1"]
- Filter Operator [FIL_113] (rows=20000000 width=1014)
- predicate:((ca_country = 'United States') and ca_address_sk is not null)
- TableScan [TS_9] (rows=40000000 width=1014)
- default@customer_address,customer_address,Tbl:COMPLETE,Col:NONE,Output:["ca_address_sk","ca_state","ca_country"]
- <-Reducer 3 [SIMPLE_EDGE]
- SHUFFLE [RS_21]
- PartitionCols:_col2
- Merge Join Operator [MERGEJOIN_94] (rows=232318249 width=88)
- Conds:RS_18._col1=RS_107._col0(Inner),Output:["_col2","_col3","_col4","_col6"]
- <-Map 9 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_107]
- PartitionCols:_col0
- Select Operator [SEL_106] (rows=465450 width=385)
- Output:["_col0"]
- Filter Operator [FIL_105] (rows=465450 width=385)
- predicate:((cd_education_status = '4 yr Degree') and (cd_marital_status = 'M') and 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_marital_status","cd_education_status"]
- <-Reducer 2 [SIMPLE_EDGE]
- SHUFFLE [RS_18]
- PartitionCols:_col1
- Merge Join Operator [MERGEJOIN_93] (rows=211198404 width=88)
- Conds:RS_131._col0=RS_99._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col6"]
- <-Map 7 [SIMPLE_EDGE] vectorized
- PARTITION_ONLY_SHUFFLE [RS_99]
- PartitionCols:_col0
- Select Operator [SEL_98] (rows=36524 width=1119)
- Output:["_col0"]
- Filter Operator [FIL_97] (rows=36524 width=1119)
- predicate:((d_year = 1998) and d_date_sk is not null)
- TableScan [TS_3] (rows=73049 width=1119)
- default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"]
- <-Map 1 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_131]
- PartitionCols:_col0
- Select Operator [SEL_130] (rows=191998545 width=88)
- Output:["_col0","_col1","_col2","_col3","_col4","_col6"]
- Filter Operator [FIL_129] (rows=191998545 width=88)
- predicate:((ss_addr_sk BETWEEN DynamicValue(RS_22_customer_address_ca_address_sk_min) AND DynamicValue(RS_22_customer_address_ca_address_sk_max) and in_bloom_filter(ss_addr_sk, DynamicValue(RS_22_customer_address_ca_address_sk_bloom_filter))) and (ss_cdemo_sk BETWEEN DynamicValue(RS_19_customer_demographics_cd_demo_sk_min) AND DynamicValue(RS_19_customer_demographics_cd_demo_sk_max) and in_bloom_filter(ss_cdemo_sk, DynamicValue(RS_19_customer_demographics_cd_demo_sk_bloom_filter))) and (ss_sales_price BETWEEN 100 AND 150 or ss_sales_price BETWEEN 50 AND 100 or ss_sales_price BETWEEN 150 AND 200) 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_store_sk BETWEEN DynamicValue(RS_26_store_s_store_sk_min) AND DynamicValue(RS_26_store_s_store_sk_max) and in_bloom_filter(ss_store_sk, Dyna
micValue(RS_26_store_s_store_sk_bloom_filter))) and ss_addr_sk is not null and ss_cdemo_sk is not null and ss_sold_date_sk is not null and ss_store_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_cdemo_sk","ss_addr_sk","ss_store_sk","ss_quantity","ss_sales_price","ss_net_profit"]
- <-Reducer 10 [BROADCAST_EDGE] vectorized
- BROADCAST [RS_112]
- Group By Operator [GBY_111] (rows=1 width=12)
- Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"]
- <-Map 9 [CUSTOM_SIMPLE_EDGE] vectorized
- SHUFFLE [RS_110]
- Group By Operator [GBY_109] (rows=1 width=12)
- Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
- Select Operator [SEL_108] (rows=465450 width=385)
- Output:["_col0"]
- Please refer to the previous Select Operator [SEL_106]
- <-Reducer 12 [BROADCAST_EDGE] vectorized
- BROADCAST [RS_120]
- Group By Operator [GBY_119] (rows=1 width=12)
- Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=20000000)"]
- <-Map 11 [CUSTOM_SIMPLE_EDGE] vectorized
- SHUFFLE [RS_118]
- Group By Operator [GBY_117] (rows=1 width=12)
- Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=20000000)"]
- Select Operator [SEL_116] (rows=20000000 width=1014)
- Output:["_col0"]
- Please refer to the previous Select Operator [SEL_114]
- <-Reducer 14 [BROADCAST_EDGE] vectorized
- BROADCAST [RS_128]
- Group By Operator [GBY_127] (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
- SHUFFLE [RS_126]
- Group By Operator [GBY_125] (rows=1 width=12)
- Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
- Select Operator [SEL_124] (rows=1704 width=1910)
- Output:["_col0"]
- Please refer to the previous Select Operator [SEL_122]
- <-Reducer 8 [BROADCAST_EDGE] vectorized
- BROADCAST [RS_104]
- Group By Operator [GBY_103] (rows=1 width=12)
- Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"]
- <-Map 7 [CUSTOM_SIMPLE_EDGE] vectorized
- PARTITION_ONLY_SHUFFLE [RS_102]
- Group By Operator [GBY_101] (rows=1 width=12)
- Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
- Select Operator [SEL_100] (rows=36524 width=1119)
- Output:["_col0"]
- Please refer to the previous Select Operator [SEL_98]
+ Output:["_col0"],aggregations:["sum(_col5)"]
+ Select Operator [SEL_28] (rows=31233897 width=88)
+ Output:["_col5"]
+ Filter Operator [FIL_27] (rows=31233897 width=88)
+ predicate:(((_col14) IN ('KY', 'GA', 'NM') and _col7 BETWEEN 0 AND 2000) or ((_col14) IN ('MT', 'OR', 'IN') and _col7 BETWEEN 150 AND 3000) or ((_col14) IN ('WI', 'MO', 'WV') and _col7 BETWEEN 50 AND 25000))
+ Merge Join Operator [MERGEJOIN_96] (rows=93701693 width=88)
+ Conds:RS_24._col3=RS_126._col0(Inner),Output:["_col5","_col7","_col14"]
+ <-Map 13 [SIMPLE_EDGE] vectorized
+ SHUFFLE [RS_126]
+ PartitionCols:_col0
+ Select Operator [SEL_125] (rows=20000000 width=1014)
+ Output:["_col0","_col1"]
+ Filter Operator [FIL_124] (rows=20000000 width=1014)
+ predicate:((ca_country = 'United States') and (ca_state) IN ('KY', 'GA', 'NM', 'MT', 'OR', 'IN', 'WI', 'MO', 'WV') and ca_address_sk is not null)
+ TableScan [TS_12] (rows=40000000 width=1014)
+ default@customer_address,customer_address,Tbl:COMPLETE,Col:NONE,Output:["ca_address_sk","ca_state","ca_country"]
+ <-Reducer 4 [SIMPLE_EDGE]
+ SHUFFLE [RS_24]
+ PartitionCols:_col3
+ Merge Join Operator [MERGEJOIN_95] (rows=85183356 width=88)
+ Conds:RS_21._col2=RS_115._col0(Inner),Output:["_col3","_col5","_col7"]
+ <-Map 11 [SIMPLE_EDGE] vectorized
+ SHUFFLE [RS_115]
+ PartitionCols:_col0
+ Select Operator [SEL_114] (rows=465450 width=385)
+ Output:["_col0"]
+ Filter Operator [FIL_113] (rows=465450 width=385)
+ predicate:((cd_education_status = '4 yr Degree') and (cd_marital_status = 'M') and cd_demo_sk is not null)
+ TableScan [TS_9] (rows=1861800 width=385)
+ default@customer_demographics,customer_demographics,Tbl:COMPLETE,Col:NONE,Output:["cd_demo_sk","cd_marital_status","cd_education_status"]
+ <-Reducer 3 [SIMPLE_EDGE]
+ SHUFFLE [RS_21]
+ PartitionCols:_col2
+ Merge Join Operator [MERGEJOIN_94] (rows=77439413 width=88)
+ Conds:RS_18._col1=RS_107._col0(Inner),Output:["_col2","_col3","_col5","_col7"]
+ <-Map 9 [SIMPLE_EDGE] vectorized
+ SHUFFLE [RS_107]
+ PartitionCols:_col0
+ Select Operator [SEL_106] (rows=36524 width=1119)
+ Output:["_col0"]
+ Filter Operator [FIL_105] (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:_col1
+ Merge Join Operator [MERGEJOIN_93] (rows=70399465 width=88)
+ Conds:RS_99._col0=RS_123._col3(Inner),Output:["_col1","_col2","_col3","_col5","_col7"]
+ <-Map 1 [SIMPLE_EDGE] vectorized
+ PARTITION_ONLY_SHUFFLE [RS_99]
+ PartitionCols:_col0
+ Select Operator [SEL_98] (rows=1704 width=1910)
+ Output:["_col0"]
+ Filter Operator [FIL_97] (rows=1704 width=1910)
+ predicate:s_store_sk is not null
+ TableScan [TS_0] (rows=1704 width=1910)
+ default@store,store,Tbl:COMPLETE,Col:NONE,Output:["s_store_sk"]
+ <-Map 8 [SIMPLE_EDGE] vectorized
+ SHUFFLE [RS_123]
+ PartitionCols:_col3
+ Select Operator [SEL_122] (rows=63999513 width=88)
+ Output:["_col0","_col1","_col2","_col3","_col4","_col6"]
+ Filter Operator [FIL_121] (rows=63999513 width=88)
+ predicate:((ss_cdemo_sk BETWEEN DynamicValue(RS_22_customer_demographics_cd_demo_sk_min) AND DynamicValue(RS_22_customer_demographics_cd_demo_sk_max) and in_bloom_filter(ss_cdemo_sk, DynamicValue(RS_22_customer_demographics_cd_demo_sk_bloom_filter))) and (ss_net_profit BETWEEN 0 AND 2000 or ss_net_profit BETWEEN 150 AND 3000 or ss_net_profit BETWEEN 50 AND 25000) and (ss_sales_price BETWEEN 100 AND 150 or ss_sales_price BETWEEN 50 AND 100 or ss_sales_price BETWEEN 150 AND 200) 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_store_sk BETWEEN DynamicValue(RS_15_store_s_store_sk_min) AND DynamicValue(RS_15_store_s_store_sk_max) and in_bloom_filter(ss_store_sk, DynamicValue(RS_15_store_s_store_sk_bloom_filter))) and ss_addr_sk is not null and ss_cdemo_sk is not null and ss_sold_date
_sk is not null and ss_store_sk is not null)
+ TableScan [TS_3] (rows=575995635 width=88)
+ default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_cdemo_sk","ss_addr_sk","ss_store_sk","ss_quantity","ss_sales_price","ss_net_profit"]
+ <-Reducer 10 [BROADCAST_EDGE] vectorized
+ BROADCAST [RS_112]
+ Group By Operator [GBY_111] (rows=1 width=12)
+ Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"]
+ <-Map 9 [CUSTOM_SIMPLE_EDGE] vectorized
+ SHUFFLE [RS_110]
+ Group By Operator [GBY_109] (rows=1 width=12)
+ Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
+ Select Operator [SEL_108] (rows=36524 width=1119)
+ Output:["_col0"]
+ Please refer to the previous Select Operator [SEL_106]
+ <-Reducer 12 [BROADCAST_EDGE] vectorized
+ BROADCAST [RS_120]
+ Group By Operator [GBY_119] (rows=1 width=12)
+ Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"]
+ <-Map 11 [CUSTOM_SIMPLE_EDGE] vectorized
+ SHUFFLE [RS_118]
+ Group By Operator [GBY_117] (rows=1 width=12)
+ Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
+ Select Operator [SEL_116] (rows=465450 width=385)
+ Output:["_col0"]
+ Please refer to the previous Select Operator [SEL_114]
+ <-Reducer 7 [BROADCAST_EDGE] vectorized
+ BROADCAST [RS_104]
+ Group By Operator [GBY_103] (rows=1 width=12)
+ Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"]
+ <-Map 1 [CUSTOM_SIMPLE_EDGE] vectorized
+ PARTITION_ONLY_SHUFFLE [RS_102]
+ Group By Operator [GBY_101] (rows=1 width=12)
+ Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
+ Select Operator [SEL_100] (rows=1704 width=1910)
+ Output:["_col0"]
+ Please refer to the previous Select Operator [SEL_98]
http://git-wip-us.apache.org/repos/asf/hive/blob/f0b76e24/ql/src/test/results/clientpositive/perf/tez/query53.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/perf/tez/query53.q.out b/ql/src/test/results/clientpositive/perf/tez/query53.q.out
index fec6b41..87857e8 100644
--- a/ql/src/test/results/clientpositive/perf/tez/query53.q.out
+++ b/ql/src/test/results/clientpositive/perf/tez/query53.q.out
@@ -140,7 +140,7 @@ Stage-0
Select Operator [SEL_86] (rows=462000 width=1436)
Output:["_col0","_col4"]
Filter Operator [FIL_85] (rows=462000 width=1436)
- predicate:((((i_category) IN ('Books', 'Children', 'Electronics') and (i_class) IN ('personal', 'portable', 'reference', 'self-help') and (i_brand) IN ('scholaramalgamalg #14', 'scholaramalgamalg #7', 'exportiunivamalg #9', 'scholaramalgamalg #9')) or ((i_category) IN ('Women', 'Music', 'Men') and (i_class) IN ('accessories', 'classical', 'fragrances', 'pants') and (i_brand) IN ('amalgimporto #1', 'edu packscholar #1', 'exportiimporto #1', 'importoamalg #1'))) and i_item_sk is not null)
+ predicate:((((i_category) IN ('Books', 'Children', 'Electronics') and (i_class) IN ('personal', 'portable', 'reference', 'self-help') and (i_brand) IN ('scholaramalgamalg #14', 'scholaramalgamalg #7', 'exportiunivamalg #9', 'scholaramalgamalg #9')) or ((i_category) IN ('Women', 'Music', 'Men') and (i_class) IN ('accessories', 'classical', 'fragrances', 'pants') and (i_brand) IN ('amalgimporto #1', 'edu packscholar #1', 'exportiimporto #1', 'importoamalg #1'))) and (i_brand) IN ('scholaramalgamalg #14', 'scholaramalgamalg #7', 'exportiunivamalg #9', 'scholaramalgamalg #9', 'amalgimporto #1', 'edu packscholar #1', 'exportiimporto #1', 'importoamalg #1') and (i_category) IN ('Books', 'Children', 'Electronics', 'Women', 'Music', 'Men') and (i_class) IN ('personal', 'portable', 'reference', 'self-help', 'accessories', 'classical', 'fragrances', 'pants') and i_item_sk is not null)
TableScan [TS_3] (rows=462000 width=1436)
default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_brand","i_class","i_category","i_manufact_id"]
<-Map 1 [SIMPLE_EDGE] vectorized
http://git-wip-us.apache.org/repos/asf/hive/blob/f0b76e24/ql/src/test/results/clientpositive/perf/tez/query57.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/perf/tez/query57.q.out b/ql/src/test/results/clientpositive/perf/tez/query57.q.out
index 1d1f870..7299f9f 100644
--- a/ql/src/test/results/clientpositive/perf/tez/query57.q.out
+++ b/ql/src/test/results/clientpositive/perf/tez/query57.q.out
@@ -146,30 +146,30 @@ Stage-0
Select Operator [SEL_328] (rows=31942874 width=135)
Output:["rank_window_1","_col0","_col1","_col2","_col3","_col4","_col5","_col6"]
Filter Operator [FIL_327] (rows=31942874 width=135)
- predicate:((_col0 > 0) and (_col1 = 2000) and rank_window_1 is not null)
+ predicate:((_col0 > 0) and (_col3 = 2000) and rank_window_1 is not null)
PTF Operator [PTF_326] (rows=191657247 width=135)
- Function definitions:[{},{"name:":"windowingtablefunction","order by:":"_col1 ASC NULLS LAST, _col2 ASC NULLS LAST","partition by:":"_col5, _col4, _col3"}]
+ Function definitions:[{},{"name:":"windowingtablefunction","order by:":"_col3 ASC NULLS LAST, _col4 ASC NULLS LAST","partition by:":"_col2, _col1, _col5"}]
Select Operator [SEL_325] (rows=191657247 width=135)
Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"]
<-Reducer 10 [SIMPLE_EDGE] vectorized
SHUFFLE [RS_324]
- PartitionCols:_col4, _col3, _col2
+ PartitionCols:_col1, _col0, _col4
Select Operator [SEL_323] (rows=191657247 width=135)
Output:["avg_window_0","_col0","_col1","_col2","_col3","_col4","_col5"]
PTF Operator [PTF_322] (rows=191657247 width=135)
- Function definitions:[{},{"name:":"windowingtablefunction","order by:":"_col4 ASC NULLS FIRST, _col3 ASC NULLS FIRST, _col2 ASC NULLS FIRST, _col0 ASC NULLS FIRST","partition by:":"_col4, _col3, _col2, _col0"}]
+ Function definitions:[{},{"name:":"windowingtablefunction","order by:":"_col1 ASC NULLS FIRST, _col0 ASC NULLS FIRST, _col4 ASC NULLS FIRST, _col2 ASC NULLS FIRST","partition by:":"_col1, _col0, _col4, _col2"}]
Select Operator [SEL_321] (rows=191657247 width=135)
Output:["_col0","_col1","_col2","_col3","_col4","_col5"]
<-Reducer 5 [SIMPLE_EDGE] vectorized
SHUFFLE [RS_310]
- PartitionCols:_col4, _col3, _col2, _col0
+ PartitionCols:_col1, _col0, _col4, _col2
Group By Operator [GBY_307] (rows=191657247 width=135)
Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4
<-Reducer 4 [SIMPLE_EDGE]
SHUFFLE [RS_93]
PartitionCols:_col0, _col1, _col2, _col3, _col4
Group By Operator [GBY_92] (rows=383314495 width=135)
- Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(_col3)"],keys:_col5, _col6, _col8, _col10, _col11
+ Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(_col3)"],keys:_col10, _col11, _col5, _col6, _col8
Merge Join Operator [MERGEJOIN_278] (rows=383314495 width=135)
Conds:RS_88._col2=RS_298._col0(Inner),Output:["_col3","_col5","_col6","_col8","_col10","_col11"]
<-Map 16 [SIMPLE_EDGE] vectorized
@@ -206,7 +206,7 @@ Stage-0
Select Operator [SEL_281] (rows=73049 width=1119)
Output:["_col0","_col1","_col2"]
Filter Operator [FIL_280] (rows=73049 width=1119)
- predicate:(((struct(d_year,d_moy)) IN (const struct(1999,12), const struct(2001,1)) or (d_year = 2000)) and d_date_sk is not null)
+ predicate:(((d_year = 2000) or (struct(d_year,d_moy)) IN (const struct(1999,12), const struct(2001,1))) and (d_year) IN (2000, 1999, 2001) and d_date_sk is not null)
TableScan [TS_73] (rows=73049 width=1119)
default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year","d_moy"]
<-Map 1 [SIMPLE_EDGE] vectorized
@@ -259,12 +259,12 @@ Stage-0
Filter Operator [FIL_313] (rows=191657247 width=135)
predicate:rank_window_0 is not null
PTF Operator [PTF_312] (rows=191657247 width=135)
- Function definitions:[{},{"name:":"windowingtablefunction","order by:":"_col0 ASC NULLS LAST, _col1 ASC NULLS LAST","partition by:":"_col4, _col3, _col2"}]
+ Function definitions:[{},{"name:":"windowingtablefunction","order by:":"_col2 ASC NULLS LAST, _col3 ASC NULLS LAST","partition by:":"_col1, _col0, _col4"}]
Select Operator [SEL_311] (rows=191657247 width=135)
Output:["_col0","_col1","_col2","_col3","_col4","_col5"]
<-Reducer 5 [SIMPLE_EDGE] vectorized
SHUFFLE [RS_308]
- PartitionCols:_col4, _col3, _col2
+ PartitionCols:_col1, _col0, _col4
Please refer to the previous Group By Operator [GBY_307]
<-Reducer 9 [SIMPLE_EDGE] vectorized
SHUFFLE [RS_320]
@@ -274,11 +274,11 @@ Stage-0
Filter Operator [FIL_318] (rows=191657247 width=135)
predicate:rank_window_0 is not null
PTF Operator [PTF_317] (rows=191657247 width=135)
- Function definitions:[{},{"name:":"windowingtablefunction","order by:":"_col0 ASC NULLS LAST, _col1 ASC NULLS LAST","partition by:":"_col4, _col3, _col2"}]
+ Function definitions:[{},{"name:":"windowingtablefunction","order by:":"_col2 ASC NULLS LAST, _col3 ASC NULLS LAST","partition by:":"_col1, _col0, _col4"}]
Select Operator [SEL_316] (rows=191657247 width=135)
Output:["_col0","_col1","_col2","_col3","_col4","_col5"]
<-Reducer 5 [SIMPLE_EDGE] vectorized
SHUFFLE [RS_309]
- PartitionCols:_col4, _col3, _col2
+ PartitionCols:_col1, _col0, _col4
Please refer to the previous Group By Operator [GBY_307]
http://git-wip-us.apache.org/repos/asf/hive/blob/f0b76e24/ql/src/test/results/clientpositive/perf/tez/query63.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/perf/tez/query63.q.out b/ql/src/test/results/clientpositive/perf/tez/query63.q.out
index 941ee5e..d05da86 100644
--- a/ql/src/test/results/clientpositive/perf/tez/query63.q.out
+++ b/ql/src/test/results/clientpositive/perf/tez/query63.q.out
@@ -142,7 +142,7 @@ Stage-0
Select Operator [SEL_86] (rows=462000 width=1436)
Output:["_col0","_col4"]
Filter Operator [FIL_85] (rows=462000 width=1436)
- predicate:((((i_category) IN ('Books', 'Children', 'Electronics') and (i_class) IN ('personal', 'portable', 'refernece', 'self-help') and (i_brand) IN ('scholaramalgamalg #14', 'scholaramalgamalg #7', 'exportiunivamalg #9', 'scholaramalgamalg #9')) or ((i_category) IN ('Women', 'Music', 'Men') and (i_class) IN ('accessories', 'classical', 'fragrances', 'pants') and (i_brand) IN ('amalgimporto #1', 'edu packscholar #1', 'exportiimporto #1', 'importoamalg #1'))) and i_item_sk is not null)
+ predicate:((((i_category) IN ('Books', 'Children', 'Electronics') and (i_class) IN ('personal', 'portable', 'refernece', 'self-help') and (i_brand) IN ('scholaramalgamalg #14', 'scholaramalgamalg #7', 'exportiunivamalg #9', 'scholaramalgamalg #9')) or ((i_category) IN ('Women', 'Music', 'Men') and (i_class) IN ('accessories', 'classical', 'fragrances', 'pants') and (i_brand) IN ('amalgimporto #1', 'edu packscholar #1', 'exportiimporto #1', 'importoamalg #1'))) and (i_brand) IN ('scholaramalgamalg #14', 'scholaramalgamalg #7', 'exportiunivamalg #9', 'scholaramalgamalg #9', 'amalgimporto #1', 'edu packscholar #1', 'exportiimporto #1', 'importoamalg #1') and (i_category) IN ('Books', 'Children', 'Electronics', 'Women', 'Music', 'Men') and (i_class) IN ('personal', 'portable', 'refernece', 'self-help', 'accessories', 'classical', 'fragrances', 'pants') and i_item_sk is not null)
TableScan [TS_3] (rows=462000 width=1436)
default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_brand","i_class","i_category","i_manager_id"]
<-Map 1 [SIMPLE_EDGE] vectorized