http://git-wip-us.apache.org/repos/asf/hive/blob/55887646/ql/src/test/results/clientpositive/perf/tez/query91.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/tez/query91.q.out b/ql/src/test/results/clientpositive/perf/tez/query91.q.out index 5b4952d..98e8adf 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query91.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query91.q.out @@ -104,13 +104,13 @@ Stage-0 SHUFFLE [RS_42] PartitionCols:_col0, _col1, _col2, _col3, _col4 Group By Operator [GBY_41] (rows=1 width=585) - Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(_col12)"],keys:_col5, _col6, _col17, _col18, _col19 + Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(_col11)"],keys:_col5, _col6, _col14, _col15, _col16 Merge Join Operator [MERGEJOIN_144] (rows=10438 width=473) - Conds:RS_37._col2=RS_165._col0(Inner),Output:["_col5","_col6","_col12","_col17","_col18","_col19"] + Conds:RS_37._col2=RS_165._col0(Inner),Output:["_col5","_col6","_col11","_col14","_col15","_col16"] <-Map 15 [SIMPLE_EDGE] vectorized SHUFFLE [RS_165] PartitionCols:_col0 - Select Operator [SEL_164] (rows=3600 width=96) + Select Operator [SEL_164] (rows=3600 width=4) Output:["_col0"] Filter Operator [FIL_163] (rows=3600 width=96) predicate:((hd_buy_potential like '0-500%') and hd_demo_sk is not null) @@ -120,12 +120,12 @@ Stage-0 SHUFFLE [RS_37] PartitionCols:_col2 Merge Join Operator [MERGEJOIN_143] (rows=20876 width=473) - Conds:RS_34._col0=RS_35._col1(Inner),Output:["_col2","_col5","_col6","_col12","_col17","_col18","_col19"] + Conds:RS_34._col0=RS_35._col1(Inner),Output:["_col2","_col5","_col6","_col11","_col14","_col15","_col16"] <-Reducer 12 [SIMPLE_EDGE] SHUFFLE [RS_35] PartitionCols:_col1 Merge Join Operator [MERGEJOIN_142] (rows=657590 width=312) - Conds:RS_21._col2=RS_162._col0(Inner),Output:["_col1","_col3","_col8","_col9","_col10"] + Conds:RS_21._col2=RS_162._col0(Inner),Output:["_col1","_col3","_col6","_col7","_col8"] <-Map 14 [SIMPLE_EDGE] vectorized SHUFFLE [RS_162] PartitionCols:_col0 @@ -152,7 +152,7 @@ Stage-0 <-Map 13 [SIMPLE_EDGE] vectorized SHUFFLE [RS_159] PartitionCols:_col0 - Select Operator [SEL_158] (rows=50 width=12) + Select Operator [SEL_158] (rows=50 width=4) Output:["_col0"] Filter Operator [FIL_157] (rows=50 width=12) predicate:((d_moy = 11) and (d_year = 1999) and d_date_sk is not null) @@ -166,7 +166,7 @@ Stage-0 <-Map 9 [SIMPLE_EDGE] vectorized SHUFFLE [RS_153] PartitionCols:_col0 - Select Operator [SEL_152] (rows=8000000 width=116) + Select Operator [SEL_152] (rows=8000000 width=4) Output:["_col0"] Filter Operator [FIL_151] (rows=8000000 width=112) predicate:((ca_gmt_offset = -7) and ca_address_sk is not null)
http://git-wip-us.apache.org/repos/asf/hive/blob/55887646/ql/src/test/results/clientpositive/perf/tez/query92.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/tez/query92.q.out b/ql/src/test/results/clientpositive/perf/tez/query92.q.out index 50918f0..1f837dd 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query92.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query92.q.out @@ -104,9 +104,9 @@ Stage-0 Select Operator [SEL_34] (rows=2478 width=112) Output:["_col2"] Filter Operator [FIL_33] (rows=2478 width=112) - predicate:(_col2 > CAST( (1.3 * _col6) AS decimal(14,7))) + predicate:(_col2 > _col5) Merge Join Operator [MERGEJOIN_107] (rows=7434 width=112) - Conds:RS_30._col1=RS_31._col2(Inner),Output:["_col2","_col6"] + Conds:RS_30._col1=RS_31._col2(Inner),Output:["_col2","_col5"] <-Reducer 2 [SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_30] PartitionCols:_col1 @@ -115,7 +115,7 @@ Stage-0 <-Map 7 [SIMPLE_EDGE] vectorized SHUFFLE [RS_110] PartitionCols:_col0 - Select Operator [SEL_109] (rows=8116 width=98) + Select Operator [SEL_109] (rows=8116 width=4) Output:["_col0"] Filter Operator [FIL_108] (rows=8116 width=98) predicate:(CAST( d_date AS TIMESTAMP) BETWEEN TIMESTAMP'1998-03-18 00:00:00' AND TIMESTAMP'1998-06-16 00:00:00' and d_date_sk is not null) @@ -140,7 +140,7 @@ Stage-0 Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] Select Operator [SEL_123] (rows=669 width=4) Output:["_col0"] - Select Operator [SEL_121] (rows=669 width=8) + Select Operator [SEL_121] (rows=669 width=4) Output:["_col0"] Filter Operator [FIL_120] (rows=669 width=7) predicate:((i_manufact_id = 269) and i_item_sk is not null) http://git-wip-us.apache.org/repos/asf/hive/blob/55887646/ql/src/test/results/clientpositive/perf/tez/query93.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/tez/query93.q.out b/ql/src/test/results/clientpositive/perf/tez/query93.q.out index 2891fcc..45e6e9f 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query93.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query93.q.out @@ -68,22 +68,22 @@ Stage-0 <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_18] PartitionCols:_col0 - Group By Operator [GBY_17] (rows=38308 width=112) + Group By Operator [GBY_17] (rows=306464 width=112) Output:["_col0","_col1"],aggregations:["sum(_col1)"],keys:_col0 - Select Operator [SEL_15] (rows=15586502 width=3) + Select Operator [SEL_15] (rows=15586502 width=119) Output:["_col0","_col1"] - Merge Join Operator [MERGEJOIN_64] (rows=15586502 width=3) - Conds:RS_12._col0, _col2=RS_77._col0, _col2(Inner),Output:["_col3","_col7","_col9","_col10"] + Merge Join Operator [MERGEJOIN_64] (rows=15586502 width=119) + Conds:RS_12._col0, _col2=RS_77._col0, _col2(Inner),Output:["_col3","_col4","_col7","_col9","_col10","_col11"] <-Reducer 2 [SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_12] PartitionCols:_col0, _col2 - Merge Join Operator [MERGEJOIN_63] (rows=1522298 width=8) - Conds:RS_67._col1=RS_70._col0(Inner),Output:["_col0","_col2","_col3"] + Merge Join Operator [MERGEJOIN_63] (rows=1522298 width=12) + Conds:RS_67._col1=RS_70._col0(Inner),Output:["_col0","_col2","_col3","_col4"] <-Map 1 [SIMPLE_EDGE] vectorized SHUFFLE [RS_67] PartitionCols:_col1 - Select Operator [SEL_66] (rows=55574563 width=15) - Output:["_col0","_col1","_col2","_col3"] + Select Operator [SEL_66] (rows=55574563 width=19) + Output:["_col0","_col1","_col2","_col3","_col4"] Filter Operator [FIL_65] (rows=55574563 width=15) predicate:(sr_item_sk is not null and sr_reason_sk is not null and sr_ticket_number is not null) TableScan [TS_0] (rows=57591150 width=15) @@ -91,7 +91,7 @@ Stage-0 <-Map 8 [SIMPLE_EDGE] vectorized SHUFFLE [RS_70] PartitionCols:_col0 - Select Operator [SEL_69] (rows=1 width=113) + Select Operator [SEL_69] (rows=1 width=4) Output:["_col0"] Filter Operator [FIL_68] (rows=1 width=101) predicate:((r_reason_desc = 'Did not like the warranty') and r_reason_sk is not null) @@ -100,8 +100,8 @@ Stage-0 <-Map 9 [SIMPLE_EDGE] vectorized SHUFFLE [RS_77] PartitionCols:_col0, _col2 - Select Operator [SEL_76] (rows=575995635 width=122) - Output:["_col0","_col1","_col2","_col3","_col4"] + Select Operator [SEL_76] (rows=575995635 width=234) + Output:["_col0","_col1","_col2","_col3","_col4","_col5"] Filter Operator [FIL_75] (rows=575995635 width=122) predicate:((ss_item_sk BETWEEN DynamicValue(RS_12_store_returns_sr_item_sk_min) AND DynamicValue(RS_12_store_returns_sr_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_12_store_returns_sr_item_sk_bloom_filter))) and (ss_ticket_number BETWEEN DynamicValue(RS_12_store_returns_sr_ticket_number_min) AND DynamicValue(RS_12_store_returns_sr_ticket_number_max) and in_bloom_filter(ss_ticket_number, DynamicValue(RS_12_store_returns_sr_ticket_number_bloom_filter))) and ss_item_sk is not null and ss_ticket_number is not null) TableScan [TS_6] (rows=575995635 width=122) http://git-wip-us.apache.org/repos/asf/hive/blob/55887646/ql/src/test/results/clientpositive/perf/tez/query95.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/tez/query95.q.out b/ql/src/test/results/clientpositive/perf/tez/query95.q.out index 49e8e86..885e670 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query95.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query95.q.out @@ -141,7 +141,7 @@ Stage-0 <-Map 16 [SIMPLE_EDGE] vectorized SHUFFLE [RS_260] PartitionCols:_col0 - Select Operator [SEL_259] (rows=12 width=91) + Select Operator [SEL_259] (rows=12 width=4) Output:["_col0"] Filter Operator [FIL_258] (rows=12 width=92) predicate:((web_company_name = 'pri') and web_site_sk is not null) @@ -155,7 +155,7 @@ Stage-0 <-Map 14 [SIMPLE_EDGE] vectorized SHUFFLE [RS_252] PartitionCols:_col0 - Select Operator [SEL_251] (rows=784314 width=90) + Select Operator [SEL_251] (rows=784314 width=4) Output:["_col0"] Filter Operator [FIL_250] (rows=784314 width=90) predicate:((ca_state = 'TX') and ca_address_sk is not null) http://git-wip-us.apache.org/repos/asf/hive/blob/55887646/ql/src/test/results/clientpositive/perf/tez/query96.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/tez/query96.q.out b/ql/src/test/results/clientpositive/perf/tez/query96.q.out index d06ad6a..0c80233 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query96.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query96.q.out @@ -76,7 +76,7 @@ Stage-0 <-Map 11 [SIMPLE_EDGE] vectorized SHUFFLE [RS_95] PartitionCols:_col0 - Select Operator [SEL_94] (rows=155 width=91) + Select Operator [SEL_94] (rows=155 width=4) Output:["_col0"] Filter Operator [FIL_93] (rows=155 width=92) predicate:((s_store_name = 'ese') and s_store_sk is not null) @@ -90,7 +90,7 @@ Stage-0 <-Map 9 [SIMPLE_EDGE] vectorized SHUFFLE [RS_87] PartitionCols:_col0 - Select Operator [SEL_86] (rows=655 width=8) + Select Operator [SEL_86] (rows=655 width=4) Output:["_col0"] Filter Operator [FIL_85] (rows=655 width=8) predicate:((hd_dep_count = 5) and hd_demo_sk is not null) @@ -104,7 +104,7 @@ Stage-0 <-Map 7 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_79] PartitionCols:_col0 - Select Operator [SEL_78] (rows=1515 width=12) + Select Operator [SEL_78] (rows=1515 width=4) Output:["_col0"] Filter Operator [FIL_77] (rows=1515 width=12) predicate:((t_hour = 8) and (t_minute >= 30) and t_time_sk is not null) http://git-wip-us.apache.org/repos/asf/hive/blob/55887646/ql/src/test/results/clientpositive/perf/tez/query97.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/tez/query97.q.out b/ql/src/test/results/clientpositive/perf/tez/query97.q.out index 21daca3..8cd15fb 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query97.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query97.q.out @@ -101,7 +101,7 @@ Stage-0 <-Map 6 [SIMPLE_EDGE] vectorized SHUFFLE [RS_72] PartitionCols:_col0 - Select Operator [SEL_71] (rows=317 width=8) + Select Operator [SEL_71] (rows=317 width=4) Output:["_col0"] Filter Operator [FIL_70] (rows=317 width=8) predicate:(d_date_sk is not null and d_month_seq BETWEEN 1212 AND 1223) http://git-wip-us.apache.org/repos/asf/hive/blob/55887646/ql/src/test/results/clientpositive/perf/tez/query98.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/tez/query98.q.out b/ql/src/test/results/clientpositive/perf/tez/query98.q.out index 8403d20..5be1e37 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query98.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query98.q.out @@ -105,9 +105,9 @@ Stage-0 SHUFFLE [RS_17] PartitionCols:_col0, _col1, _col2, _col3, _col4 Group By Operator [GBY_16] (rows=138600 width=689) - Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(_col2)"],keys:_col10, _col9, _col6, _col7, _col8 + Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(_col2)"],keys:_col9, _col8, _col5, _col6, _col7 Merge Join Operator [MERGEJOIN_57] (rows=18334631 width=577) - Conds:RS_12._col1=RS_68._col0(Inner),Output:["_col2","_col6","_col7","_col8","_col9","_col10"] + Conds:RS_12._col1=RS_68._col0(Inner),Output:["_col2","_col5","_col6","_col7","_col8","_col9"] <-Map 9 [SIMPLE_EDGE] vectorized SHUFFLE [RS_68] PartitionCols:_col0 @@ -125,7 +125,7 @@ Stage-0 <-Map 7 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_60] PartitionCols:_col0 - Select Operator [SEL_59] (rows=8116 width=98) + Select Operator [SEL_59] (rows=8116 width=4) Output:["_col0"] Filter Operator [FIL_58] (rows=8116 width=98) predicate:(CAST( d_date AS TIMESTAMP) BETWEEN TIMESTAMP'2001-01-12 00:00:00' AND TIMESTAMP'2001-02-11 00:00:00' and d_date_sk is not null) http://git-wip-us.apache.org/repos/asf/hive/blob/55887646/ql/src/test/results/clientpositive/perf/tez/query99.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/tez/query99.q.out b/ql/src/test/results/clientpositive/perf/tez/query99.q.out index 745c5a9..0d9d1f8 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query99.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query99.q.out @@ -96,108 +96,106 @@ Stage-0 limit:-1 Stage-1 Reducer 7 vectorized - File Output Operator [FS_132] - Limit [LIM_131] (rows=100 width=590) + File Output Operator [FS_131] + Limit [LIM_130] (rows=100 width=590) Number of rows:100 - Select Operator [SEL_130] (rows=3869553 width=590) + Select Operator [SEL_129] (rows=3869553 width=590) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] <-Reducer 6 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_129] - Select Operator [SEL_128] (rows=3869553 width=590) + SHUFFLE [RS_128] + Select Operator [SEL_127] (rows=3869553 width=590) Output:["_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"] - Group By Operator [GBY_127] (rows=3869553 width=406) + Group By Operator [GBY_126] (rows=3869553 width=406) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)","sum(VALUE._col3)","sum(VALUE._col4)"],keys:KEY._col0, KEY._col1, KEY._col2 <-Reducer 5 [SIMPLE_EDGE] - SHUFFLE [RS_30] + SHUFFLE [RS_29] PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_29] (rows=7739106 width=406) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"],aggregations:["sum(_col3)","sum(_col4)","sum(_col5)","sum(_col6)","sum(_col7)"],keys:_col0, _col1, _col2 - Top N Key Operator [TNK_57] (rows=15478212 width=289) - keys:_col0, _col1, _col2,sort order:+++,top n:100 - Select Operator [SEL_27] (rows=15478212 width=289) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] - Merge Join Operator [MERGEJOIN_101] (rows=15478212 width=289) - Conds:RS_24._col3=RS_112._col0(Inner),Output:["_col0","_col1","_col8","_col10","_col12"] - <-Map 12 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_112] - PartitionCols:_col0 - Select Operator [SEL_111] (rows=1 width=88) - Output:["_col0","_col1"] - Filter Operator [FIL_110] (rows=1 width=88) - predicate:sm_ship_mode_sk is not null - TableScan [TS_12] (rows=1 width=88) - default@ship_mode,ship_mode,Tbl:COMPLETE,Col:COMPLETE,Output:["sm_ship_mode_sk","sm_type"] - <-Reducer 4 [SIMPLE_EDGE] - SHUFFLE [RS_24] - PartitionCols:_col3 - Merge Join Operator [MERGEJOIN_100] (rows=46434637 width=209) - Conds:RS_21._col4=RS_126._col0(Inner),Output:["_col0","_col1","_col3","_col8","_col10"] - <-Map 11 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_126] - PartitionCols:_col0 - Select Operator [SEL_125] (rows=27 width=104) - Output:["_col0","_col1"] - Filter Operator [FIL_124] (rows=27 width=104) - predicate:w_warehouse_sk is not null - TableScan [TS_9] (rows=27 width=104) - default@warehouse,warehouse,Tbl:COMPLETE,Col:COMPLETE,Output:["w_warehouse_sk","w_warehouse_name"] - <-Reducer 3 [SIMPLE_EDGE] - SHUFFLE [RS_21] - PartitionCols:_col4 - Merge Join Operator [MERGEJOIN_99] (rows=46434637 width=113) - Conds:RS_18._col2=RS_123._col0(Inner),Output:["_col0","_col1","_col3","_col4","_col8"] - <-Map 10 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_123] - PartitionCols:_col0 - Select Operator [SEL_122] (rows=60 width=102) - Output:["_col0","_col1"] - Filter Operator [FIL_121] (rows=60 width=102) - predicate:cc_call_center_sk is not null - TableScan [TS_6] (rows=60 width=102) - default@call_center,call_center,Tbl:COMPLETE,Col:COMPLETE,Output:["cc_call_center_sk","cc_name"] - <-Reducer 2 [SIMPLE_EDGE] - SHUFFLE [RS_18] - PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_98] (rows=46434637 width=19) - Conds:RS_120._col1=RS_104._col0(Inner),Output:["_col0","_col1","_col2","_col3","_col4"] - <-Map 8 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_104] - PartitionCols:_col0 - Select Operator [SEL_103] (rows=317 width=8) - Output:["_col0"] - Filter Operator [FIL_102] (rows=317 width=8) - predicate:(d_date_sk is not null and d_month_seq BETWEEN 1212 AND 1223) - TableScan [TS_3] (rows=73049 width=8) - default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_month_seq"] - <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_120] - PartitionCols:_col1 - Select Operator [SEL_119] (rows=282273729 width=19) - Output:["_col0","_col1","_col2","_col3","_col4"] - Filter Operator [FIL_118] (rows=282273729 width=19) - predicate:((cs_ship_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(cs_ship_date_sk, DynamicValue(RS_16_date_dim_d_date_sk_bloom_filter))) and (cs_ship_mode_sk BETWEEN DynamicValue(RS_25_ship_mode_sm_ship_mode_sk_min) AND DynamicValue(RS_25_ship_mode_sm_ship_mode_sk_max) and in_bloom_filter(cs_ship_mode_sk, DynamicValue(RS_25_ship_mode_sm_ship_mode_sk_bloom_filter))) and cs_call_center_sk is not null and cs_ship_date_sk is not null and cs_ship_mode_sk is not null and cs_warehouse_sk is not null) - TableScan [TS_0] (rows=287989836 width=19) - default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["cs_sold_date_sk","cs_ship_date_sk","cs_call_center_sk","cs_ship_mode_sk","cs_warehouse_sk"] - <-Reducer 13 [BROADCAST_EDGE] vectorized - BROADCAST [RS_117] - Group By Operator [GBY_116] (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_115] - Group By Operator [GBY_114] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_113] (rows=1 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_111] - <-Reducer 9 [BROADCAST_EDGE] vectorized - BROADCAST [RS_109] - Group By Operator [GBY_108] (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_107] - Group By Operator [GBY_106] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_105] (rows=317 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_103] + Group By Operator [GBY_28] (rows=7739106 width=406) + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"],aggregations:["sum(_col4)","sum(_col5)","sum(_col6)","sum(_col7)","sum(_col8)"],keys:_col13, _col15, _col11 + Top N Key Operator [TNK_56] (rows=15478212 width=386) + keys:_col13, _col15, _col11,sort order:+++,top n:100 + Merge Join Operator [MERGEJOIN_100] (rows=15478212 width=386) + Conds:RS_24._col2=RS_111._col0(Inner),Output:["_col4","_col5","_col6","_col7","_col8","_col11","_col13","_col15"] + <-Map 12 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_111] + PartitionCols:_col0 + Select Operator [SEL_110] (rows=1 width=88) + Output:["_col0","_col1"] + Filter Operator [FIL_109] (rows=1 width=88) + predicate:sm_ship_mode_sk is not null + TableScan [TS_12] (rows=1 width=88) + default@ship_mode,ship_mode,Tbl:COMPLETE,Col:COMPLETE,Output:["sm_ship_mode_sk","sm_type"] + <-Reducer 4 [SIMPLE_EDGE] + SHUFFLE [RS_24] + PartitionCols:_col2 + Merge Join Operator [MERGEJOIN_99] (rows=46434637 width=305) + Conds:RS_21._col3=RS_125._col0(Inner),Output:["_col2","_col4","_col5","_col6","_col7","_col8","_col11","_col13"] + <-Map 11 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_125] + PartitionCols:_col0 + Select Operator [SEL_124] (rows=27 width=188) + Output:["_col0","_col1"] + Filter Operator [FIL_123] (rows=27 width=104) + predicate:w_warehouse_sk is not null + TableScan [TS_9] (rows=27 width=104) + default@warehouse,warehouse,Tbl:COMPLETE,Col:COMPLETE,Output:["w_warehouse_sk","w_warehouse_name"] + <-Reducer 3 [SIMPLE_EDGE] + SHUFFLE [RS_21] + PartitionCols:_col3 + Merge Join Operator [MERGEJOIN_98] (rows=46434637 width=125) + Conds:RS_18._col1=RS_122._col0(Inner),Output:["_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col11"] + <-Map 10 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_122] + PartitionCols:_col0 + Select Operator [SEL_121] (rows=60 width=102) + Output:["_col0","_col1"] + Filter Operator [FIL_120] (rows=60 width=102) + predicate:cc_call_center_sk is not null + TableScan [TS_6] (rows=60 width=102) + default@call_center,call_center,Tbl:COMPLETE,Col:COMPLETE,Output:["cc_call_center_sk","cc_name"] + <-Reducer 2 [SIMPLE_EDGE] + SHUFFLE [RS_18] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_97] (rows=46434637 width=31) + Conds:RS_119._col0=RS_103._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"] + <-Map 8 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_103] + PartitionCols:_col0 + Select Operator [SEL_102] (rows=317 width=4) + Output:["_col0"] + Filter Operator [FIL_101] (rows=317 width=8) + predicate:(d_date_sk is not null and d_month_seq BETWEEN 1212 AND 1223) + TableScan [TS_3] (rows=73049 width=8) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_month_seq"] + <-Map 1 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_119] + PartitionCols:_col0 + Select Operator [SEL_118] (rows=282273729 width=35) + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"] + Filter Operator [FIL_117] (rows=282273729 width=19) + predicate:((cs_ship_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(cs_ship_date_sk, DynamicValue(RS_16_date_dim_d_date_sk_bloom_filter))) and (cs_ship_mode_sk BETWEEN DynamicValue(RS_25_ship_mode_sm_ship_mode_sk_min) AND DynamicValue(RS_25_ship_mode_sm_ship_mode_sk_max) and in_bloom_filter(cs_ship_mode_sk, DynamicValue(RS_25_ship_mode_sm_ship_mode_sk_bloom_filter))) and cs_call_center_sk is not null and cs_ship_date_sk is not null and cs_ship_mode_sk is not null and cs_warehouse_sk is not null) + TableScan [TS_0] (rows=287989836 width=19) + default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["cs_sold_date_sk","cs_ship_date_sk","cs_call_center_sk","cs_ship_mode_sk","cs_warehouse_sk"] + <-Reducer 13 [BROADCAST_EDGE] vectorized + BROADCAST [RS_116] + Group By Operator [GBY_115] (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_114] + Group By Operator [GBY_113] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_112] (rows=1 width=4) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_110] + <-Reducer 9 [BROADCAST_EDGE] vectorized + BROADCAST [RS_108] + Group By Operator [GBY_107] (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_106] + Group By Operator [GBY_105] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_104] (rows=317 width=4) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_102] http://git-wip-us.apache.org/repos/asf/hive/blob/55887646/ql/src/test/results/clientpositive/pointlookup2.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/pointlookup2.q.out b/ql/src/test/results/clientpositive/pointlookup2.q.out index 8d906be..42d2c78 100644 --- a/ql/src/test/results/clientpositive/pointlookup2.q.out +++ b/ql/src/test/results/clientpositive/pointlookup2.q.out @@ -294,15 +294,15 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@pcr_t1_n2 POSTHOOK: Input: default@pcr_t1_n2@ds=2000-04-08 #### A masked pattern was here #### -OPTIMIZED SQL: SELECT `t4`.`key`, `t4`.`value`, CAST('2000-04-08' AS STRING) AS `ds`, `t4`.`key1`, `t4`.`value1`, CAST('2000-04-08' AS STRING) AS `ds1` -FROM (SELECT `t0`.`key`, `t0`.`value`, `t2`.`key` AS `key1`, `t2`.`value` AS `value1` -FROM (SELECT `key`, `value`, CAST('2000-04-08' AS STRING) AS `ds` +OPTIMIZED SQL: SELECT `t3`.`key`, `t3`.`value`, CAST('2000-04-08' AS STRING) AS `ds`, `t3`.`key0` AS `key1`, `t3`.`value0` AS `value1`, CAST('2000-04-08' AS STRING) AS `ds1` +FROM (SELECT * +FROM (SELECT `key`, `value` FROM `default`.`pcr_t1_n2` WHERE `ds` = '2000-04-08' AND `key` IS NOT NULL) AS `t0` -INNER JOIN (SELECT `key`, `value`, CAST('2000-04-08' AS STRING) AS `ds` +INNER JOIN (SELECT `key`, `value` FROM `default`.`pcr_t1_n2` WHERE `ds` = '2000-04-08' AND `key` IS NOT NULL) AS `t2` ON `t0`.`key` = `t2`.`key` -ORDER BY `t0`.`key`) AS `t4` +ORDER BY `t0`.`key`) AS `t3` STAGE DEPENDENCIES: Stage-1 is a root stage Stage-2 depends on stages: Stage-1 @@ -417,30 +417,26 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col3, _col4 + outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: int), _col1 (type: string), _col3 (type: int), _col4 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 + File Output Operator + compressed: false + GlobalTableId: 0 #### A masked pattern was here #### - NumFilesPerFileSink: 1 - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - column.name.delimiter , - columns _col0,_col1,_col2,_col3 - columns.types int,string,int,string - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + NumFilesPerFileSink: 1 + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + column.name.delimiter , + columns _col0,_col1,_col2,_col3 + columns.types int,string,int,string + escape.delim \ + serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-2 Map Reduce @@ -538,15 +534,15 @@ POSTHOOK: Input: default@pcr_t1_n2 POSTHOOK: Input: default@pcr_t1_n2@ds=2000-04-08 POSTHOOK: Input: default@pcr_t1_n2@ds=2000-04-09 #### A masked pattern was here #### -OPTIMIZED SQL: SELECT `t4`.`key`, `t4`.`value`, CAST('2000-04-08' AS STRING) AS `ds`, `t4`.`key1`, `t4`.`value1`, CAST('2000-04-09' AS STRING) AS `ds1` -FROM (SELECT `t0`.`key`, `t0`.`value`, `t2`.`key` AS `key1`, `t2`.`value` AS `value1` -FROM (SELECT `key`, `value`, CAST('2000-04-08' AS STRING) AS `ds` +OPTIMIZED SQL: SELECT `t3`.`key`, `t3`.`value`, CAST('2000-04-08' AS STRING) AS `ds`, `t3`.`key0` AS `key1`, `t3`.`value0` AS `value1`, CAST('2000-04-09' AS STRING) AS `ds1` +FROM (SELECT * +FROM (SELECT `key`, `value` FROM `default`.`pcr_t1_n2` WHERE `ds` = '2000-04-08' AND `key` IS NOT NULL) AS `t0` -INNER JOIN (SELECT `key`, `value`, CAST('2000-04-09' AS STRING) AS `ds` +INNER JOIN (SELECT `key`, `value` FROM `default`.`pcr_t1_n2` WHERE `ds` = '2000-04-09' AND `key` IS NOT NULL) AS `t2` ON `t0`.`key` = `t2`.`key` -ORDER BY `t0`.`key`) AS `t4` +ORDER BY `t0`.`key`) AS `t3` STAGE DEPENDENCIES: Stage-1 is a root stage Stage-2 depends on stages: Stage-1 @@ -710,30 +706,26 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col3, _col4 + outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: int), _col1 (type: string), _col3 (type: int), _col4 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 + File Output Operator + compressed: false + GlobalTableId: 0 #### A masked pattern was here #### - NumFilesPerFileSink: 1 - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - column.name.delimiter , - columns _col0,_col1,_col2,_col3 - columns.types int,string,int,string - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + NumFilesPerFileSink: 1 + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + column.name.delimiter , + columns _col0,_col1,_col2,_col3 + columns.types int,string,int,string + escape.delim \ + serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-2 Map Reduce @@ -834,14 +826,6 @@ POSTHOOK: Input: default@pcr_t1_n2@ds=2000-04-08 POSTHOOK: Input: default@pcr_t1_n2@ds=2000-04-09 POSTHOOK: Input: default@pcr_t2_n0 #### A masked pattern was here #### -OPTIMIZED SQL: SELECT * -FROM (SELECT `key`, `value`, `ds` -FROM `default`.`pcr_t1_n2` -WHERE `ds` = '2000-04-08' OR `ds` = '2000-04-09') AS `t0` -INNER JOIN (SELECT `ds`, `key`, `value` -FROM `default`.`pcr_t2_n0` -WHERE `key` = 1 OR `key` = 2) AS `t2` ON `t0`.`ds` = '2000-04-08' AND `t2`.`key` = 1 OR `t0`.`ds` = '2000-04-09' AND `t2`.`key` = 2 -ORDER BY `t2`.`key`, `t2`.`value`, `t0`.`ds` STAGE DEPENDENCIES: Stage-1 is a root stage Stage-2 depends on stages: Stage-1 @@ -857,15 +841,15 @@ STAGE PLANS: Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE GatherStats: false Select Operator - expressions: key (type: int), value (type: string), ds (type: string) - outputColumnNames: _col0, _col1, _col2 + expressions: key (type: int), value (type: string), ds (type: string), (ds = '2000-04-08') (type: boolean), (ds = '2000-04-09') (type: boolean) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator null sort order: sort order: Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE tag: 0 - value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string) + value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: boolean), _col4 (type: boolean) auto parallelism: false TableScan alias: t2 @@ -877,15 +861,15 @@ STAGE PLANS: predicate: ((key = 1) or (key = 2)) (type: boolean) Statistics: Num rows: 1 Data size: 18 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: ds (type: string), key (type: int), value (type: string) - outputColumnNames: _col0, _col1, _col2 + expressions: ds (type: string), key (type: int), value (type: string), (key = 1) (type: boolean), (key = 2) (type: boolean) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 1 Data size: 18 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator null sort order: sort order: Statistics: Num rows: 1 Data size: 18 Basic stats: COMPLETE Column stats: NONE tag: 1 - value expressions: _col0 (type: string), _col1 (type: int), _col2 (type: string) + value expressions: _col0 (type: string), _col1 (type: int), _col2 (type: string), _col3 (type: boolean), _col4 (type: boolean) auto parallelism: false Path -> Alias: #### A masked pattern was here #### @@ -1046,30 +1030,34 @@ STAGE PLANS: keys: 0 1 - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 Statistics: Num rows: 40 Data size: 1080 Basic stats: COMPLETE Column stats: NONE Filter Operator isSamplingPred: false - predicate: (((_col2 = '2000-04-08') and (_col4 = 1)) or ((_col2 = '2000-04-09') and (_col4 = 2))) (type: boolean) + predicate: ((_col3 and _col8) or (_col4 and _col9)) (type: boolean) Statistics: Num rows: 20 Data size: 540 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - column.name.delimiter , - columns _col0,_col1,_col2,_col3,_col4,_col5 - columns.types int,string,string,string,int,string - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + Select Operator + expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col5 (type: string), _col6 (type: int), _col7 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 20 Data size: 540 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + column.name.delimiter , + columns _col0,_col1,_col2,_col3,_col4,_col5 + columns.types int,string,string,string,int,string + escape.delim \ + serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-2 Map Reduce @@ -1172,14 +1160,6 @@ POSTHOOK: Input: default@pcr_t1_n2@ds=2000-04-09 POSTHOOK: Input: default@pcr_t1_n2@ds=2000-04-10 POSTHOOK: Input: default@pcr_t2_n0 #### A masked pattern was here #### -OPTIMIZED SQL: SELECT * -FROM (SELECT `key`, `value`, `ds` -FROM `default`.`pcr_t1_n2` -WHERE `key` = 1 OR `key` = 2) AS `t0` -INNER JOIN (SELECT `ds`, `key`, `value` -FROM `default`.`pcr_t2_n0` -WHERE `ds` = '2000-04-08' OR `ds` = '2000-04-09') AS `t2` ON `t2`.`ds` = '2000-04-08' AND `t0`.`key` = 1 OR `t2`.`ds` = '2000-04-09' AND `t0`.`key` = 2 -ORDER BY `t0`.`key`, `t0`.`value`, `t2`.`ds` STAGE DEPENDENCIES: Stage-1 is a root stage Stage-2 depends on stages: Stage-1 @@ -1199,15 +1179,15 @@ STAGE PLANS: predicate: ((key = 1) or (key = 2)) (type: boolean) Statistics: Num rows: 60 Data size: 480 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: int), value (type: string), ds (type: string) - outputColumnNames: _col0, _col1, _col2 + expressions: key (type: int), value (type: string), ds (type: string), (key = 1) (type: boolean), (key = 2) (type: boolean) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 60 Data size: 480 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator null sort order: sort order: Statistics: Num rows: 60 Data size: 480 Basic stats: COMPLETE Column stats: NONE tag: 0 - value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string) + value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: boolean), _col4 (type: boolean) auto parallelism: false TableScan alias: t2 @@ -1219,15 +1199,15 @@ STAGE PLANS: predicate: ((ds = '2000-04-08') or (ds = '2000-04-09')) (type: boolean) Statistics: Num rows: 1 Data size: 18 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: ds (type: string), key (type: int), value (type: string) - outputColumnNames: _col0, _col1, _col2 + expressions: ds (type: string), key (type: int), value (type: string), (ds = '2000-04-08') (type: boolean), (ds = '2000-04-09') (type: boolean) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 1 Data size: 18 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator null sort order: sort order: Statistics: Num rows: 1 Data size: 18 Basic stats: COMPLETE Column stats: NONE tag: 1 - value expressions: _col0 (type: string), _col1 (type: int), _col2 (type: string) + value expressions: _col0 (type: string), _col1 (type: int), _col2 (type: string), _col3 (type: boolean), _col4 (type: boolean) auto parallelism: false Path -> Alias: #### A masked pattern was here #### @@ -1437,30 +1417,34 @@ STAGE PLANS: keys: 0 1 - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 Statistics: Num rows: 60 Data size: 1620 Basic stats: COMPLETE Column stats: NONE Filter Operator isSamplingPred: false - predicate: (((_col3 = '2000-04-08') and (_col0 = 1)) or ((_col3 = '2000-04-09') and (_col0 = 2))) (type: boolean) + predicate: ((_col8 and _col3) or (_col9 and _col4)) (type: boolean) Statistics: Num rows: 30 Data size: 810 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - column.name.delimiter , - columns _col0,_col1,_col2,_col3,_col4,_col5 - columns.types int,string,string,string,int,string - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + Select Operator + expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col5 (type: string), _col6 (type: int), _col7 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 30 Data size: 810 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + column.name.delimiter , + columns _col0,_col1,_col2,_col3,_col4,_col5 + columns.types int,string,string,string,int,string + escape.delim \ + serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-2 Map Reduce @@ -1920,15 +1904,15 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@pcr_t1_n2 POSTHOOK: Input: default@pcr_t1_n2@ds=2000-04-08 #### A masked pattern was here #### -OPTIMIZED SQL: SELECT `t4`.`key`, `t4`.`value`, CAST('2000-04-08' AS STRING) AS `ds`, `t4`.`key1`, `t4`.`value1`, CAST('2000-04-08' AS STRING) AS `ds1` -FROM (SELECT `t0`.`key`, `t0`.`value`, `t2`.`key` AS `key1`, `t2`.`value` AS `value1` -FROM (SELECT `key`, `value`, CAST('2000-04-08' AS STRING) AS `ds` +OPTIMIZED SQL: SELECT `t3`.`key`, `t3`.`value`, CAST('2000-04-08' AS STRING) AS `ds`, `t3`.`key0` AS `key1`, `t3`.`value0` AS `value1`, CAST('2000-04-08' AS STRING) AS `ds1` +FROM (SELECT * +FROM (SELECT `key`, `value` FROM `default`.`pcr_t1_n2` WHERE `ds` = '2000-04-08' AND `key` IS NOT NULL) AS `t0` -INNER JOIN (SELECT `key`, `value`, CAST('2000-04-08' AS STRING) AS `ds` +INNER JOIN (SELECT `key`, `value` FROM `default`.`pcr_t1_n2` WHERE `ds` = '2000-04-08' AND `key` IS NOT NULL) AS `t2` ON `t0`.`key` = `t2`.`key` -ORDER BY `t0`.`key`) AS `t4` +ORDER BY `t0`.`key`) AS `t3` STAGE DEPENDENCIES: Stage-1 is a root stage Stage-2 depends on stages: Stage-1 @@ -2043,30 +2027,26 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col3, _col4 + outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: int), _col1 (type: string), _col3 (type: int), _col4 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 + File Output Operator + compressed: false + GlobalTableId: 0 #### A masked pattern was here #### - NumFilesPerFileSink: 1 - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - column.name.delimiter , - columns _col0,_col1,_col2,_col3 - columns.types int,string,int,string - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + NumFilesPerFileSink: 1 + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + column.name.delimiter , + columns _col0,_col1,_col2,_col3 + columns.types int,string,int,string + escape.delim \ + serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-2 Map Reduce @@ -2164,15 +2144,15 @@ POSTHOOK: Input: default@pcr_t1_n2 POSTHOOK: Input: default@pcr_t1_n2@ds=2000-04-08 POSTHOOK: Input: default@pcr_t1_n2@ds=2000-04-09 #### A masked pattern was here #### -OPTIMIZED SQL: SELECT `t4`.`key`, `t4`.`value`, CAST('2000-04-08' AS STRING) AS `ds`, `t4`.`key1`, `t4`.`value1`, CAST('2000-04-09' AS STRING) AS `ds1` -FROM (SELECT `t0`.`key`, `t0`.`value`, `t2`.`key` AS `key1`, `t2`.`value` AS `value1` -FROM (SELECT `key`, `value`, CAST('2000-04-08' AS STRING) AS `ds` +OPTIMIZED SQL: SELECT `t3`.`key`, `t3`.`value`, CAST('2000-04-08' AS STRING) AS `ds`, `t3`.`key0` AS `key1`, `t3`.`value0` AS `value1`, CAST('2000-04-09' AS STRING) AS `ds1` +FROM (SELECT * +FROM (SELECT `key`, `value` FROM `default`.`pcr_t1_n2` WHERE `ds` = '2000-04-08' AND `key` IS NOT NULL) AS `t0` -INNER JOIN (SELECT `key`, `value`, CAST('2000-04-09' AS STRING) AS `ds` +INNER JOIN (SELECT `key`, `value` FROM `default`.`pcr_t1_n2` WHERE `ds` = '2000-04-09' AND `key` IS NOT NULL) AS `t2` ON `t0`.`key` = `t2`.`key` -ORDER BY `t0`.`key`) AS `t4` +ORDER BY `t0`.`key`) AS `t3` STAGE DEPENDENCIES: Stage-1 is a root stage Stage-2 depends on stages: Stage-1 @@ -2336,30 +2316,26 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col3, _col4 + outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: int), _col1 (type: string), _col3 (type: int), _col4 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 + File Output Operator + compressed: false + GlobalTableId: 0 #### A masked pattern was here #### - NumFilesPerFileSink: 1 - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - column.name.delimiter , - columns _col0,_col1,_col2,_col3 - columns.types int,string,int,string - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + NumFilesPerFileSink: 1 + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + column.name.delimiter , + columns _col0,_col1,_col2,_col3 + columns.types int,string,int,string + escape.delim \ + serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-2 Map Reduce
