http://git-wip-us.apache.org/repos/asf/hive/blob/47dd953c/ql/src/test/results/clientpositive/perf/tez/query74.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/tez/query74.q.out b/ql/src/test/results/clientpositive/perf/tez/query74.q.out index 738e64f..854e6dc 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query74.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query74.q.out @@ -121,10 +121,10 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Map 1 <- Reducer 22 (BROADCAST_EDGE) -Map 11 <- Reducer 21 (BROADCAST_EDGE), Reducer 25 (BROADCAST_EDGE) -Map 15 <- Reducer 20 (BROADCAST_EDGE) -Map 7 <- Reducer 23 (BROADCAST_EDGE), Reducer 26 (BROADCAST_EDGE) +Map 1 <- Reducer 21 (BROADCAST_EDGE) +Map 11 <- Reducer 23 (BROADCAST_EDGE) +Map 15 <- Reducer 20 (BROADCAST_EDGE), Reducer 25 (BROADCAST_EDGE) +Map 7 <- Reducer 22 (BROADCAST_EDGE), Reducer 26 (BROADCAST_EDGE) Reducer 10 <- Reducer 9 (SIMPLE_EDGE) Reducer 12 <- Map 11 (SIMPLE_EDGE), Map 19 (SIMPLE_EDGE) Reducer 13 <- Map 24 (SIMPLE_EDGE), Reducer 12 (SIMPLE_EDGE) @@ -154,36 +154,36 @@ Stage-0 File Output Operator [FS_356] Limit [LIM_355] (rows=100 width=88) Number of rows:100 - Select Operator [SEL_354] (rows=383325119 width=88) + Select Operator [SEL_354] (rows=574987679 width=88) Output:["_col0","_col1","_col2"] <-Reducer 5 [SIMPLE_EDGE] SHUFFLE [RS_89] - Select Operator [SEL_88] (rows=383325119 width=88) + Select Operator [SEL_88] (rows=574987679 width=88) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_87] (rows=383325119 width=88) - predicate:((_col9 / _col1) > (_col7 / _col3)) + Filter Operator [FIL_87] (rows=574987679 width=88) + predicate:CASE WHEN (_col3 is not null) THEN (CASE WHEN (_col5 is not null) THEN (((_col1 / _col5) > (_col9 / _col3))) ELSE ((null > (_col9 / _col3))) END) ELSE (CASE WHEN (_col5 is not null) THEN (((_col1 / _col5) > null)) ELSE (null) END) END Merge Join Operator [MERGEJOIN_279] (rows=1149975359 width=88) - Conds:RS_323._col0=RS_335._col0(Inner),RS_335._col0=RS_345._col0(Inner),RS_335._col0=RS_353._col0(Inner),Output:["_col1","_col3","_col4","_col5","_col6","_col7","_col9"] + Conds:RS_321._col0=RS_333._col0(Inner),RS_333._col0=RS_343._col0(Inner),RS_333._col0=RS_353._col0(Inner),Output:["_col1","_col3","_col5","_col6","_col7","_col8","_col9"] <-Reducer 10 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_335] + SHUFFLE [RS_333] PartitionCols:_col0 - Select Operator [SEL_334] (rows=116159124 width=88) + Select Operator [SEL_332] (rows=116159124 width=88) Output:["_col0","_col1"] - Filter Operator [FIL_333] (rows=116159124 width=88) + Filter Operator [FIL_331] (rows=116159124 width=88) predicate:(_col4 > 0) - Select Operator [SEL_332] (rows=348477374 width=88) + Select Operator [SEL_330] (rows=348477374 width=88) Output:["_col0","_col4"] - Group By Operator [GBY_331] (rows=348477374 width=88) + Group By Operator [GBY_329] (rows=348477374 width=88) Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["max(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3 <-Reducer 9 [SIMPLE_EDGE] - SHUFFLE [RS_38] + SHUFFLE [RS_37] PartitionCols:_col0, _col1, _col2, _col3 - Group By Operator [GBY_37] (rows=696954748 width=88) + Group By Operator [GBY_36] (rows=696954748 width=88) Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["max(_col2)"],keys:_col6, _col7, _col8, _col4 Merge Join Operator [MERGEJOIN_274] (rows=696954748 width=88) - Conds:RS_33._col1=RS_313._col0(Inner),Output:["_col2","_col4","_col6","_col7","_col8"] + Conds:RS_32._col1=RS_312._col0(Inner),Output:["_col2","_col4","_col6","_col7","_col8"] <-Map 24 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_313] + SHUFFLE [RS_312] PartitionCols:_col0 Select Operator [SEL_308] (rows=80000000 width=860) Output:["_col0","_col1","_col2","_col3"] @@ -192,212 +192,212 @@ Stage-0 TableScan [TS_68] (rows=80000000 width=860) default@customer,customer,Tbl:COMPLETE,Col:NONE,Output:["c_customer_sk","c_customer_id","c_first_name","c_last_name"] <-Reducer 8 [SIMPLE_EDGE] - SHUFFLE [RS_33] + SHUFFLE [RS_32] PartitionCols:_col1 Merge Join Operator [MERGEJOIN_273] (rows=633595212 width=88) - Conds:RS_330._col0=RS_292._col0(Inner),Output:["_col1","_col2","_col4"] + Conds:RS_328._col0=RS_290._col0(Inner),Output:["_col1","_col2","_col4"] <-Map 19 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_292] + SHUFFLE [RS_290] PartitionCols:_col0 - Select Operator [SEL_285] (rows=18262 width=1119) + Select Operator [SEL_284] (rows=18262 width=1119) Output:["_col0","_col1"] - Filter Operator [FIL_282] (rows=18262 width=1119) + Filter Operator [FIL_281] (rows=18262 width=1119) predicate:((d_year = 2001) and (d_year) IN (2001, 2002) and d_date_sk is not null) TableScan [TS_65] (rows=73049 width=1119) default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"] <-Map 7 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_330] + SHUFFLE [RS_328] PartitionCols:_col0 - Select Operator [SEL_329] (rows=575995635 width=88) + Select Operator [SEL_327] (rows=575995635 width=88) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_328] (rows=575995635 width=88) - predicate:((ss_customer_sk BETWEEN DynamicValue(RS_34_customer_c_customer_sk_min) AND DynamicValue(RS_34_customer_c_customer_sk_max) and in_bloom_filter(ss_customer_sk, DynamicValue(RS_34_customer_c_customer_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_31_date_dim_d_date_sk_min) AND DynamicValue(RS_31_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_31_date_dim_d_date_sk_bloom_filter))) and ss_customer_sk is not null and ss_sold_date_sk is not null) - TableScan [TS_21] (rows=575995635 width=88) + Filter Operator [FIL_326] (rows=575995635 width=88) + predicate:((ss_customer_sk BETWEEN DynamicValue(RS_33_customer_c_customer_sk_min) AND DynamicValue(RS_33_customer_c_customer_sk_max) and in_bloom_filter(ss_customer_sk, DynamicValue(RS_33_customer_c_customer_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_30_date_dim_d_date_sk_min) AND DynamicValue(RS_30_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_30_date_dim_d_date_sk_bloom_filter))) and ss_customer_sk is not null and ss_sold_date_sk is not null) + TableScan [TS_20] (rows=575995635 width=88) default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_customer_sk","ss_net_paid"] - <-Reducer 23 [BROADCAST_EDGE] vectorized - BROADCAST [RS_325] - Group By Operator [GBY_324] (rows=1 width=12) + <-Reducer 22 [BROADCAST_EDGE] vectorized + BROADCAST [RS_323] + Group By Operator [GBY_322] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Map 19 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_301] - Group By Operator [GBY_297] (rows=1 width=12) + SHUFFLE [RS_300] + Group By Operator [GBY_296] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_293] (rows=18262 width=1119) + Select Operator [SEL_291] (rows=18262 width=1119) Output:["_col0"] - Please refer to the previous Select Operator [SEL_285] + Please refer to the previous Select Operator [SEL_284] <-Reducer 26 [BROADCAST_EDGE] vectorized - BROADCAST [RS_327] - Group By Operator [GBY_326] (rows=1 width=12) + BROADCAST [RS_325] + Group By Operator [GBY_324] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=80000000)"] <-Map 24 [CUSTOM_SIMPLE_EDGE] vectorized SHUFFLE [RS_318] Group By Operator [GBY_316] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=80000000)"] - Select Operator [SEL_314] (rows=80000000 width=860) + Select Operator [SEL_313] (rows=80000000 width=860) Output:["_col0"] Please refer to the previous Select Operator [SEL_308] <-Reducer 14 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_345] + SHUFFLE [RS_343] + PartitionCols:_col0 + Select Operator [SEL_342] (rows=29040539 width=135) + Output:["_col0","_col1"] + Filter Operator [FIL_341] (rows=29040539 width=135) + predicate:(_col4 > 0) + Select Operator [SEL_340] (rows=87121617 width=135) + Output:["_col0","_col4"] + Group By Operator [GBY_339] (rows=87121617 width=135) + Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["max(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3 + <-Reducer 13 [SIMPLE_EDGE] + SHUFFLE [RS_58] + PartitionCols:_col0, _col1, _col2, _col3 + Group By Operator [GBY_57] (rows=174243235 width=135) + Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["max(_col2)"],keys:_col6, _col7, _col8, _col4 + Merge Join Operator [MERGEJOIN_276] (rows=174243235 width=135) + Conds:RS_53._col1=RS_314._col0(Inner),Output:["_col2","_col4","_col6","_col7","_col8"] + <-Map 24 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_314] + PartitionCols:_col0 + Please refer to the previous Select Operator [SEL_308] + <-Reducer 12 [SIMPLE_EDGE] + SHUFFLE [RS_53] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_275] (rows=158402938 width=135) + Conds:RS_338._col0=RS_292._col0(Inner),Output:["_col1","_col2","_col4"] + <-Map 19 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_292] + PartitionCols:_col0 + Select Operator [SEL_285] (rows=18262 width=1119) + Output:["_col0","_col1"] + Filter Operator [FIL_282] (rows=18262 width=1119) + predicate:((d_year = 2001) and (d_year) IN (2001, 2002) and d_date_sk is not null) + Please refer to the previous TableScan [TS_65] + <-Map 11 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_338] + PartitionCols:_col0 + Select Operator [SEL_337] (rows=144002668 width=135) + Output:["_col0","_col1","_col2"] + Filter Operator [FIL_336] (rows=144002668 width=135) + predicate:((ws_sold_date_sk BETWEEN DynamicValue(RS_51_date_dim_d_date_sk_min) AND DynamicValue(RS_51_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_51_date_dim_d_date_sk_bloom_filter))) and ws_bill_customer_sk is not null and ws_sold_date_sk is not null) + TableScan [TS_41] (rows=144002668 width=135) + default@web_sales,web_sales,Tbl:COMPLETE,Col:NONE,Output:["ws_sold_date_sk","ws_bill_customer_sk","ws_net_paid"] + <-Reducer 23 [BROADCAST_EDGE] vectorized + BROADCAST [RS_335] + Group By Operator [GBY_334] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 19 [CUSTOM_SIMPLE_EDGE] vectorized + SHUFFLE [RS_301] + Group By Operator [GBY_297] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_293] (rows=18262 width=1119) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_285] + <-Reducer 18 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_353] PartitionCols:_col0 - Select Operator [SEL_344] (rows=348477374 width=88) + Select Operator [SEL_352] (rows=348477374 width=88) Output:["_col0","_col1","_col2","_col3"] - Group By Operator [GBY_343] (rows=348477374 width=88) + Group By Operator [GBY_351] (rows=348477374 width=88) Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["max(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3 - <-Reducer 13 [SIMPLE_EDGE] - SHUFFLE [RS_59] + <-Reducer 17 [SIMPLE_EDGE] + SHUFFLE [RS_79] PartitionCols:_col0, _col1, _col2, _col3 - Group By Operator [GBY_58] (rows=696954748 width=88) + Group By Operator [GBY_78] (rows=696954748 width=88) Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["max(_col2)"],keys:_col6, _col7, _col8, _col4 - Merge Join Operator [MERGEJOIN_276] (rows=696954748 width=88) - Conds:RS_54._col1=RS_310._col0(Inner),Output:["_col2","_col4","_col6","_col7","_col8"] + Merge Join Operator [MERGEJOIN_278] (rows=696954748 width=88) + Conds:RS_74._col1=RS_309._col0(Inner),Output:["_col2","_col4","_col6","_col7","_col8"] <-Map 24 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_310] + SHUFFLE [RS_309] PartitionCols:_col0 Please refer to the previous Select Operator [SEL_308] - <-Reducer 12 [SIMPLE_EDGE] - SHUFFLE [RS_54] + <-Reducer 16 [SIMPLE_EDGE] + SHUFFLE [RS_74] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_275] (rows=633595212 width=88) - Conds:RS_342._col0=RS_288._col0(Inner),Output:["_col1","_col2","_col4"] + Merge Join Operator [MERGEJOIN_277] (rows=633595212 width=88) + Conds:RS_350._col0=RS_286._col0(Inner),Output:["_col1","_col2","_col4"] <-Map 19 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_288] + SHUFFLE [RS_286] PartitionCols:_col0 Select Operator [SEL_283] (rows=18262 width=1119) Output:["_col0","_col1"] Filter Operator [FIL_280] (rows=18262 width=1119) predicate:((d_year = 2002) and (d_year) IN (2001, 2002) and d_date_sk is not null) Please refer to the previous TableScan [TS_65] - <-Map 11 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_342] + <-Map 15 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_350] PartitionCols:_col0 - Select Operator [SEL_341] (rows=575995635 width=88) + Select Operator [SEL_349] (rows=575995635 width=88) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_340] (rows=575995635 width=88) - predicate:((ss_customer_sk BETWEEN DynamicValue(RS_55_customer_c_customer_sk_min) AND DynamicValue(RS_55_customer_c_customer_sk_max) and in_bloom_filter(ss_customer_sk, DynamicValue(RS_55_customer_c_customer_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_52_date_dim_d_date_sk_min) AND DynamicValue(RS_52_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_52_date_dim_d_date_sk_bloom_filter))) and ss_customer_sk is not null and ss_sold_date_sk is not null) - TableScan [TS_42] (rows=575995635 width=88) + Filter Operator [FIL_348] (rows=575995635 width=88) + predicate:((ss_customer_sk BETWEEN DynamicValue(RS_75_customer_c_customer_sk_min) AND DynamicValue(RS_75_customer_c_customer_sk_max) and in_bloom_filter(ss_customer_sk, DynamicValue(RS_75_customer_c_customer_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_72_date_dim_d_date_sk_min) AND DynamicValue(RS_72_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_72_date_dim_d_date_sk_bloom_filter))) and ss_customer_sk is not null and ss_sold_date_sk is not null) + TableScan [TS_62] (rows=575995635 width=88) default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_customer_sk","ss_net_paid"] - <-Reducer 21 [BROADCAST_EDGE] vectorized - BROADCAST [RS_337] - Group By Operator [GBY_336] (rows=1 width=12) + <-Reducer 20 [BROADCAST_EDGE] vectorized + BROADCAST [RS_345] + Group By Operator [GBY_344] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Map 19 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_299] - Group By Operator [GBY_295] (rows=1 width=12) + SHUFFLE [RS_298] + Group By Operator [GBY_294] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_289] (rows=18262 width=1119) + Select Operator [SEL_287] (rows=18262 width=1119) Output:["_col0"] Please refer to the previous Select Operator [SEL_283] <-Reducer 25 [BROADCAST_EDGE] vectorized - BROADCAST [RS_339] - Group By Operator [GBY_338] (rows=1 width=12) + BROADCAST [RS_347] + Group By Operator [GBY_346] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=80000000)"] <-Map 24 [CUSTOM_SIMPLE_EDGE] vectorized SHUFFLE [RS_317] Group By Operator [GBY_315] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=80000000)"] - Select Operator [SEL_311] (rows=80000000 width=860) + Select Operator [SEL_310] (rows=80000000 width=860) Output:["_col0"] Please refer to the previous Select Operator [SEL_308] - <-Reducer 18 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_353] + <-Reducer 4 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_321] PartitionCols:_col0 - Select Operator [SEL_352] (rows=87121617 width=135) + Select Operator [SEL_320] (rows=87121617 width=135) Output:["_col0","_col1"] - Group By Operator [GBY_351] (rows=87121617 width=135) + Group By Operator [GBY_319] (rows=87121617 width=135) Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["max(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3 - <-Reducer 17 [SIMPLE_EDGE] - SHUFFLE [RS_79] + <-Reducer 3 [SIMPLE_EDGE] + SHUFFLE [RS_17] PartitionCols:_col0, _col1, _col2, _col3 - Group By Operator [GBY_78] (rows=174243235 width=135) + Group By Operator [GBY_16] (rows=174243235 width=135) Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["max(_col2)"],keys:_col6, _col7, _col8, _col4 - Merge Join Operator [MERGEJOIN_278] (rows=174243235 width=135) - Conds:RS_74._col1=RS_309._col0(Inner),Output:["_col2","_col4","_col6","_col7","_col8"] + Merge Join Operator [MERGEJOIN_272] (rows=174243235 width=135) + Conds:RS_12._col1=RS_311._col0(Inner),Output:["_col2","_col4","_col6","_col7","_col8"] <-Map 24 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_309] + SHUFFLE [RS_311] PartitionCols:_col0 Please refer to the previous Select Operator [SEL_308] - <-Reducer 16 [SIMPLE_EDGE] - SHUFFLE [RS_74] + <-Reducer 2 [SIMPLE_EDGE] + SHUFFLE [RS_12] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_277] (rows=158402938 width=135) - Conds:RS_350._col0=RS_286._col0(Inner),Output:["_col1","_col2","_col4"] + Merge Join Operator [MERGEJOIN_271] (rows=158402938 width=135) + Conds:RS_306._col0=RS_288._col0(Inner),Output:["_col1","_col2","_col4"] <-Map 19 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_286] + SHUFFLE [RS_288] PartitionCols:_col0 Please refer to the previous Select Operator [SEL_283] - <-Map 15 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_350] + <-Map 1 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_306] PartitionCols:_col0 - Select Operator [SEL_349] (rows=144002668 width=135) + Select Operator [SEL_305] (rows=144002668 width=135) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_348] (rows=144002668 width=135) - predicate:((ws_sold_date_sk BETWEEN DynamicValue(RS_72_date_dim_d_date_sk_min) AND DynamicValue(RS_72_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_72_date_dim_d_date_sk_bloom_filter))) and ws_bill_customer_sk is not null and ws_sold_date_sk is not null) - TableScan [TS_62] (rows=144002668 width=135) + Filter Operator [FIL_304] (rows=144002668 width=135) + predicate:((ws_sold_date_sk BETWEEN DynamicValue(RS_10_date_dim_d_date_sk_min) AND DynamicValue(RS_10_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_10_date_dim_d_date_sk_bloom_filter))) and ws_bill_customer_sk is not null and ws_sold_date_sk is not null) + TableScan [TS_0] (rows=144002668 width=135) default@web_sales,web_sales,Tbl:COMPLETE,Col:NONE,Output:["ws_sold_date_sk","ws_bill_customer_sk","ws_net_paid"] - <-Reducer 20 [BROADCAST_EDGE] vectorized - BROADCAST [RS_347] - Group By Operator [GBY_346] (rows=1 width=12) + <-Reducer 21 [BROADCAST_EDGE] vectorized + BROADCAST [RS_303] + Group By Operator [GBY_302] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Map 19 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_298] - Group By Operator [GBY_294] (rows=1 width=12) + SHUFFLE [RS_299] + Group By Operator [GBY_295] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_287] (rows=18262 width=1119) + Select Operator [SEL_289] (rows=18262 width=1119) Output:["_col0"] Please refer to the previous Select Operator [SEL_283] - <-Reducer 4 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_323] - PartitionCols:_col0 - Select Operator [SEL_322] (rows=29040539 width=135) - Output:["_col0","_col1"] - Filter Operator [FIL_321] (rows=29040539 width=135) - predicate:(_col4 > 0) - Select Operator [SEL_320] (rows=87121617 width=135) - Output:["_col0","_col4"] - Group By Operator [GBY_319] (rows=87121617 width=135) - Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["max(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3 - <-Reducer 3 [SIMPLE_EDGE] - SHUFFLE [RS_17] - PartitionCols:_col0, _col1, _col2, _col3 - Group By Operator [GBY_16] (rows=174243235 width=135) - Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["max(_col2)"],keys:_col6, _col7, _col8, _col4 - Merge Join Operator [MERGEJOIN_272] (rows=174243235 width=135) - Conds:RS_12._col1=RS_312._col0(Inner),Output:["_col2","_col4","_col6","_col7","_col8"] - <-Map 24 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_312] - PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_308] - <-Reducer 2 [SIMPLE_EDGE] - SHUFFLE [RS_12] - PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_271] (rows=158402938 width=135) - Conds:RS_306._col0=RS_290._col0(Inner),Output:["_col1","_col2","_col4"] - <-Map 19 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_290] - PartitionCols:_col0 - Select Operator [SEL_284] (rows=18262 width=1119) - Output:["_col0","_col1"] - Filter Operator [FIL_281] (rows=18262 width=1119) - predicate:((d_year = 2001) and (d_year) IN (2001, 2002) and d_date_sk is not null) - Please refer to the previous TableScan [TS_65] - <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_306] - PartitionCols:_col0 - Select Operator [SEL_305] (rows=144002668 width=135) - Output:["_col0","_col1","_col2"] - Filter Operator [FIL_304] (rows=144002668 width=135) - predicate:((ws_sold_date_sk BETWEEN DynamicValue(RS_10_date_dim_d_date_sk_min) AND DynamicValue(RS_10_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_10_date_dim_d_date_sk_bloom_filter))) and ws_bill_customer_sk is not null and ws_sold_date_sk is not null) - TableScan [TS_0] (rows=144002668 width=135) - default@web_sales,web_sales,Tbl:COMPLETE,Col:NONE,Output:["ws_sold_date_sk","ws_bill_customer_sk","ws_net_paid"] - <-Reducer 22 [BROADCAST_EDGE] vectorized - BROADCAST [RS_303] - Group By Operator [GBY_302] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 19 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_300] - Group By Operator [GBY_296] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_291] (rows=18262 width=1119) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_284]
http://git-wip-us.apache.org/repos/asf/hive/blob/47dd953c/ql/src/test/results/clientpositive/spark/constprog_semijoin.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/constprog_semijoin.q.out b/ql/src/test/results/clientpositive/spark/constprog_semijoin.q.out index 7509697..df4e476 100644 --- a/ql/src/test/results/clientpositive/spark/constprog_semijoin.q.out +++ b/ql/src/test/results/clientpositive/spark/constprog_semijoin.q.out @@ -468,25 +468,26 @@ STAGE PLANS: Map Operator Tree: TableScan alias: table3_n0 - filterExpr: (id = 100) (type: boolean) - Statistics: Num rows: 5 Data size: 15 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (id = 100) (type: boolean) - Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: 100 (type: int), true (type: boolean) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: int), _col1 (type: boolean) - mode: hash + Statistics: Num rows: 5 Data size: 15 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: false (type: boolean) + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: 100 (type: int), true (type: boolean) outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: boolean) - sort order: ++ - Map-reduce partition columns: _col0 (type: int), _col1 (type: boolean) - Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: _col0 (type: int), _col1 (type: boolean) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: boolean) + sort order: ++ + Map-reduce partition columns: _col0 (type: int), _col1 (type: boolean) + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reducer 2 Reduce Operator Tree: @@ -497,10 +498,10 @@ STAGE PLANS: 0 100 (type: int), true (type: boolean) 1 _col0 (type: int), _col1 (type: boolean) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 22 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 22 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -655,25 +656,26 @@ STAGE PLANS: Map Operator Tree: TableScan alias: table3_n0 - filterExpr: (id = 100) (type: boolean) - Statistics: Num rows: 5 Data size: 15 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (id = 100) (type: boolean) - Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: 100 (type: int), true (type: boolean) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: int), _col1 (type: boolean) - mode: hash + Statistics: Num rows: 5 Data size: 15 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: false (type: boolean) + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: 100 (type: int), true (type: boolean) outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: boolean) - sort order: ++ - Map-reduce partition columns: _col0 (type: int), _col1 (type: boolean) - Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: _col0 (type: int), _col1 (type: boolean) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: boolean) + sort order: ++ + Map-reduce partition columns: _col0 (type: int), _col1 (type: boolean) + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reducer 2 Reduce Operator Tree: @@ -684,10 +686,10 @@ STAGE PLANS: 0 100 (type: int), true (type: boolean) 1 _col0 (type: int), _col1 (type: boolean) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 22 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 22 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat http://git-wip-us.apache.org/repos/asf/hive/blob/47dd953c/ql/src/test/results/clientpositive/spark/pcr.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/pcr.q.out b/ql/src/test/results/clientpositive/spark/pcr.q.out index 11c7891..83437e5 100644 --- a/ql/src/test/results/clientpositive/spark/pcr.q.out +++ b/ql/src/test/results/clientpositive/spark/pcr.q.out @@ -1927,7 +1927,7 @@ POSTHOOK: query: explain extended select key, value from pcr_t1 where ds>='2000- POSTHOOK: type: QUERY OPTIMIZED SQL: SELECT `key`, `value` FROM `default`.`pcr_t1` -WHERE `ds` >= '2000-04-08' OR `ds` < '2000-04-10' +WHERE `ds` >= '2000-04-08' OR `ds` IS NOT NULL ORDER BY `key`, `value` STAGE DEPENDENCIES: Stage-1 is a root stage @@ -1944,7 +1944,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: pcr_t1 - filterExpr: ((ds >= '2000-04-08') or (ds < '2000-04-10')) (type: boolean) + filterExpr: ((ds >= '2000-04-08') or ds is not null) (type: boolean) Statistics: Num rows: 60 Data size: 480 Basic stats: COMPLETE Column stats: NONE GatherStats: false Select Operator http://git-wip-us.apache.org/repos/asf/hive/blob/47dd953c/ql/src/test/results/clientpositive/spark/spark_explainuser_1.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/spark_explainuser_1.q.out b/ql/src/test/results/clientpositive/spark/spark_explainuser_1.q.out index b488129..c5d0d63 100644 --- a/ql/src/test/results/clientpositive/spark/spark_explainuser_1.q.out +++ b/ql/src/test/results/clientpositive/spark/spark_explainuser_1.q.out @@ -428,24 +428,24 @@ Stage-0 limit:-1 Stage-1 Reducer 4 - File Output Operator [FS_32] - Select Operator [SEL_30] (rows=1 width=20) + File Output Operator [FS_33] + Select Operator [SEL_31] (rows=1 width=20) Output:["_col0","_col1","_col2"] <-Reducer 3 [SORT] - SORT [RS_29] - Select Operator [SEL_28] (rows=1 width=28) + SORT [RS_30] + Select Operator [SEL_29] (rows=1 width=28) Output:["_col0","_col1","_col2","_col3"] - Group By Operator [GBY_27] (rows=1 width=20) + Group By Operator [GBY_28] (rows=1 width=20) Output:["_col0","_col1","_col2"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1 <-Reducer 2 [GROUP] - GROUP [RS_26] + GROUP [RS_27] PartitionCols:_col0, _col1 - Group By Operator [GBY_25] (rows=1 width=20) + Group By Operator [GBY_26] (rows=1 width=20) Output:["_col0","_col1","_col2"],aggregations:["count()"],keys:_col1, _col4 - Select Operator [SEL_24] (rows=1 width=20) + Select Operator [SEL_25] (rows=1 width=20) Output:["_col1","_col4"] Filter Operator [FIL_21] (rows=1 width=20) - predicate:(((UDFToLong(_col1) + _col4) >= 0) and ((_col1 >= 1) or (_col4 >= 1L)) and ((_col3 + _col6) >= 0)) + predicate:(((UDFToLong(_col1) + _col4) >= 0) and ((_col1 >= 1) or (_col4 >= 1L)) and ((_col3 + _col6) >= 0) and ((_col3 > 0) or _col1 is not null)) Join Operator [JOIN_20] (rows=3 width=18) Output:["_col1","_col3","_col4","_col6"],condition map:[{"":"{\"type\":\"Inner\",\"left\":0,\"right\":1}"},{"":"{\"type\":\"Inner\",\"left\":1,\"right\":2}"}],keys:{"0":"_col0","1":"_col0","2":"_col0"} <-Map 1 [PARTITION-LEVEL SORT] @@ -453,7 +453,7 @@ Stage-0 PartitionCols:_col0 Select Operator [SEL_2] (rows=18 width=84) Output:["_col0","_col1"] - Filter Operator [FIL_33] (rows=18 width=84) + Filter Operator [FIL_34] (rows=18 width=84) predicate:((c_int > 0) and key is not null) TableScan [TS_0] (rows=20 width=84) default@cbo_t3,cbo_t3,Tbl:COMPLETE,Col:COMPLETE,Output:["key","c_int"] @@ -469,8 +469,8 @@ Stage-0 PartitionCols:_col0, _col1, _col2 Group By Operator [GBY_6] (rows=1 width=101) Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(c_int)"],keys:key, c_int, c_float - Filter Operator [FIL_34] (rows=2 width=93) - predicate:(((UDFToFloat(c_int) + c_float) >= 0) and ((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0)) and ((c_int >= 1) or (c_float >= 1)) and (c_float > 0) and key is not null) + Filter Operator [FIL_35] (rows=2 width=93) + predicate:(((UDFToFloat(c_int) + c_float) >= 0) and ((c_int + 1) >= 0) and ((c_int > 0) or c_float is not null) and ((c_int >= 1) or (c_float >= 1)) and (c_float > 0) and key is not null) TableScan [TS_3] (rows=20 width=88) default@cbo_t1,cbo_t1,Tbl:COMPLETE,Col:COMPLETE,Output:["key","c_int","c_float"] <-Reducer 8 [PARTITION-LEVEL SORT] @@ -485,8 +485,8 @@ Stage-0 PartitionCols:_col0, _col1, _col2 Group By Operator [GBY_13] (rows=1 width=93) Output:["_col0","_col1","_col2"],keys:key, c_int, c_float - Filter Operator [FIL_35] (rows=2 width=93) - predicate:(((UDFToFloat(c_int) + c_float) >= 0) and ((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0)) and ((c_int >= 1) or (c_float >= 1)) and (c_float > 0) and key is not null) + Filter Operator [FIL_36] (rows=2 width=93) + predicate:(((UDFToFloat(c_int) + c_float) >= 0) and ((c_int + 1) >= 0) and ((c_int > 0) or c_float is not null) and ((c_int >= 1) or (c_float >= 1)) and (c_float > 0) and key is not null) TableScan [TS_10] (rows=20 width=88) default@cbo_t2,cbo_t2,Tbl:COMPLETE,Col:COMPLETE,Output:["key","c_int","c_float"] @@ -543,7 +543,7 @@ Stage-0 Group By Operator [GBY_6] (rows=1 width=101) Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(c_int)"],keys:key, c_int, c_float Filter Operator [FIL_30] (rows=2 width=93) - predicate:(((UDFToFloat(c_int) + c_float) >= 0) and ((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0)) and ((c_int >= 1) or (c_float >= 1)) and (c_float > 0) and key is not null) + predicate:(((UDFToFloat(c_int) + c_float) >= 0) and ((c_int + 1) >= 0) and ((c_int > 0) or c_float is not null) and ((c_int >= 1) or (c_float >= 1)) and (c_float > 0) and key is not null) TableScan [TS_3] (rows=20 width=88) default@cbo_t1,cbo_t1,Tbl:COMPLETE,Col:COMPLETE,Output:["key","c_int","c_float"] <-Reducer 7 [PARTITION-LEVEL SORT] @@ -559,7 +559,7 @@ Stage-0 Group By Operator [GBY_13] (rows=1 width=93) Output:["_col0","_col1","_col2"],keys:key, c_int, c_float Filter Operator [FIL_31] (rows=2 width=93) - predicate:(((UDFToFloat(c_int) + c_float) >= 0) and ((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0)) and ((c_int >= 1) or (c_float >= 1)) and (c_float > 0) and key is not null) + predicate:(((UDFToFloat(c_int) + c_float) >= 0) and ((c_int + 1) >= 0) and ((c_int > 0) or c_float is not null) and ((c_int >= 1) or (c_float >= 1)) and (c_float > 0) and key is not null) TableScan [TS_10] (rows=20 width=88) default@cbo_t2,cbo_t2,Tbl:COMPLETE,Col:COMPLETE,Output:["key","c_int","c_float"] @@ -581,22 +581,22 @@ Stage-0 limit:-1 Stage-1 Reducer 4 - File Output Operator [FS_31] - Select Operator [SEL_30] (rows=1 width=20) + File Output Operator [FS_32] + Select Operator [SEL_31] (rows=1 width=20) Output:["_col0","_col1","_col2"] <-Reducer 3 [SORT] - SORT [RS_29] - Group By Operator [GBY_27] (rows=1 width=20) + SORT [RS_30] + Group By Operator [GBY_28] (rows=1 width=20) Output:["_col0","_col1","_col2"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1 <-Reducer 2 [GROUP] - GROUP [RS_26] + GROUP [RS_27] PartitionCols:_col0, _col1 - Group By Operator [GBY_25] (rows=1 width=20) + Group By Operator [GBY_26] (rows=1 width=20) Output:["_col0","_col1","_col2"],aggregations:["count()"],keys:_col1, _col4 - Select Operator [SEL_24] (rows=1 width=20) + Select Operator [SEL_25] (rows=1 width=20) Output:["_col1","_col4"] Filter Operator [FIL_21] (rows=1 width=20) - predicate:(((UDFToLong(_col1) + _col4) >= 0) and ((_col1 >= 1) or (_col4 >= 1L)) and ((_col3 + _col6) >= 0)) + predicate:(((UDFToLong(_col1) + _col4) >= 0) and ((_col1 >= 1) or (_col4 >= 1L)) and ((_col3 + _col6) >= 0) and ((_col3 > 0) or _col1 is not null)) Join Operator [JOIN_20] (rows=3 width=18) Output:["_col1","_col3","_col4","_col6"],condition map:[{"":"{\"type\":\"Inner\",\"left\":0,\"right\":1}"},{"":"{\"type\":\"Inner\",\"left\":1,\"right\":2}"}],keys:{"0":"_col0","1":"_col0","2":"_col0"} <-Map 1 [PARTITION-LEVEL SORT] @@ -604,7 +604,7 @@ Stage-0 PartitionCols:_col0 Select Operator [SEL_2] (rows=18 width=84) Output:["_col0","_col1"] - Filter Operator [FIL_32] (rows=18 width=84) + Filter Operator [FIL_33] (rows=18 width=84) predicate:((c_int > 0) and key is not null) TableScan [TS_0] (rows=20 width=84) default@cbo_t3,cbo_t3,Tbl:COMPLETE,Col:COMPLETE,Output:["key","c_int"] @@ -620,8 +620,8 @@ Stage-0 PartitionCols:_col0, _col1, _col2 Group By Operator [GBY_6] (rows=1 width=101) Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(c_int)"],keys:key, c_int, c_float - Filter Operator [FIL_33] (rows=2 width=93) - predicate:(((UDFToFloat(c_int) + c_float) >= 0) and ((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0)) and ((c_int >= 1) or (c_float >= 1)) and (c_float > 0) and key is not null) + Filter Operator [FIL_34] (rows=2 width=93) + predicate:(((UDFToFloat(c_int) + c_float) >= 0) and ((c_int + 1) >= 0) and ((c_int > 0) or c_float is not null) and ((c_int >= 1) or (c_float >= 1)) and (c_float > 0) and key is not null) TableScan [TS_3] (rows=20 width=88) default@cbo_t1,cbo_t1,Tbl:COMPLETE,Col:COMPLETE,Output:["key","c_int","c_float"] <-Reducer 8 [PARTITION-LEVEL SORT] @@ -636,8 +636,8 @@ Stage-0 PartitionCols:_col0, _col1, _col2 Group By Operator [GBY_13] (rows=1 width=93) Output:["_col0","_col1","_col2"],keys:key, c_int, c_float - Filter Operator [FIL_34] (rows=2 width=93) - predicate:(((UDFToFloat(c_int) + c_float) >= 0) and ((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0)) and ((c_int >= 1) or (c_float >= 1)) and (c_float > 0) and key is not null) + Filter Operator [FIL_35] (rows=2 width=93) + predicate:(((UDFToFloat(c_int) + c_float) >= 0) and ((c_int + 1) >= 0) and ((c_int > 0) or c_float is not null) and ((c_int >= 1) or (c_float >= 1)) and (c_float > 0) and key is not null) TableScan [TS_10] (rows=20 width=88) default@cbo_t2,cbo_t2,Tbl:COMPLETE,Col:COMPLETE,Output:["key","c_int","c_float"] @@ -694,7 +694,7 @@ Stage-0 Group By Operator [GBY_6] (rows=1 width=101) Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(c_int)"],keys:key, c_int, c_float Filter Operator [FIL_30] (rows=2 width=93) - predicate:(((UDFToFloat(c_int) + c_float) >= 0) and ((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0)) and ((c_int >= 1) or (c_float >= 1)) and (c_float > 0) and key is not null) + predicate:(((UDFToFloat(c_int) + c_float) >= 0) and ((c_int + 1) >= 0) and ((c_int > 0) or c_float is not null) and ((c_int >= 1) or (c_float >= 1)) and (c_float > 0) and key is not null) TableScan [TS_3] (rows=20 width=88) default@cbo_t1,cbo_t1,Tbl:COMPLETE,Col:COMPLETE,Output:["key","c_int","c_float"] <-Reducer 7 [PARTITION-LEVEL SORT] @@ -710,7 +710,7 @@ Stage-0 Group By Operator [GBY_13] (rows=1 width=93) Output:["_col0","_col1","_col2"],keys:key, c_int, c_float Filter Operator [FIL_31] (rows=2 width=93) - predicate:(((UDFToFloat(c_int) + c_float) >= 0) and ((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0)) and ((c_int >= 1) or (c_float >= 1)) and (c_float > 0) and key is not null) + predicate:(((UDFToFloat(c_int) + c_float) >= 0) and ((c_int + 1) >= 0) and ((c_int > 0) or c_float is not null) and ((c_int >= 1) or (c_float >= 1)) and (c_float > 0) and key is not null) TableScan [TS_10] (rows=20 width=88) default@cbo_t2,cbo_t2,Tbl:COMPLETE,Col:COMPLETE,Output:["key","c_int","c_float"] @@ -1537,7 +1537,7 @@ Stage-0 Group By Operator [GBY_3] (rows=1 width=101) Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(c_int)"],keys:key, c_int, c_float Filter Operator [FIL_35] (rows=1 width=93) - predicate:((((c_int + 1) + 1) >= 0) and (((c_int + 1) > 0) or (UDFToDouble(key) >= 0.0D)) and ((UDFToFloat(c_int) + c_float) >= 0) and ((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0)) and ((c_int >= 1) or (c_float >= 1)) and (UDFToDouble(key) > 0.0D) and (c_float > 0)) + predicate:((((c_int + 1) + 1) >= 0) and (((c_int + 1) > 0) or (UDFToDouble(key) >= 0.0D)) and ((UDFToFloat(c_int) + c_float) >= 0) and ((c_int + 1) >= 0) and ((c_int > 0) or c_float is not null) and ((c_int >= 1) or (c_float >= 1)) and (UDFToDouble(key) > 0.0D) and (c_float > 0)) TableScan [TS_0] (rows=20 width=88) default@cbo_t1,cbo_t1,Tbl:COMPLETE,Col:COMPLETE,Output:["key","c_int","c_float"] <-Reducer 7 [PARTITION-LEVEL SORT] @@ -1555,7 +1555,7 @@ Stage-0 Group By Operator [GBY_12] (rows=1 width=93) Output:["_col0","_col1","_col2"],keys:key, c_int, c_float Filter Operator [FIL_36] (rows=1 width=93) - predicate:(((UDFToFloat(c_int) + c_float) >= 0) and ((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0)) and ((c_int >= 1) or (c_float >= 1)) and (UDFToDouble(key) > 0.0D) and (c_float > 0)) + predicate:(((UDFToFloat(c_int) + c_float) >= 0) and ((c_int + 1) >= 0) and ((c_int > 0) or c_float is not null) and ((c_int >= 1) or (c_float >= 1)) and (UDFToDouble(key) > 0.0D) and (c_float > 0)) TableScan [TS_9] (rows=20 width=88) default@cbo_t2,cbo_t2,Tbl:COMPLETE,Col:COMPLETE,Output:["key","c_int","c_float"] http://git-wip-us.apache.org/repos/asf/hive/blob/47dd953c/ql/src/test/results/clientpositive/spark/subquery_multi.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/subquery_multi.q.out b/ql/src/test/results/clientpositive/spark/subquery_multi.q.out index 80a48b7..8d3635e 100644 --- a/ql/src/test/results/clientpositive/spark/subquery_multi.q.out +++ b/ql/src/test/results/clientpositive/spark/subquery_multi.q.out @@ -859,7 +859,7 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col10, _col11, _col13 Statistics: Num rows: 1 Data size: 39416 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((_col10 = 0L) or (_col13 is null and _col3 is not null and (_col11 >= _col10))) (type: boolean) + predicate: ((_col10 = 0L) or (_col13 is null and (_col11 >= _col10))) (type: boolean) Statistics: Num rows: 1 Data size: 39416 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) http://git-wip-us.apache.org/repos/asf/hive/blob/47dd953c/ql/src/test/results/clientpositive/spark/subquery_scalar.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/subquery_scalar.q.out b/ql/src/test/results/clientpositive/spark/subquery_scalar.q.out index 9105f58..e2d51e8 100644 --- a/ql/src/test/results/clientpositive/spark/subquery_scalar.q.out +++ b/ql/src/test/results/clientpositive/spark/subquery_scalar.q.out @@ -1788,15 +1788,15 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col12 Statistics: Num rows: 28 Data size: 3601 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: _col5 BETWEEN CASE WHEN (_col10 is null) THEN (null) ELSE (_col9) END AND _col12 (type: boolean) - Statistics: Num rows: 3 Data size: 385 Basic stats: COMPLETE Column stats: NONE + predicate: CASE WHEN (_col10 is null) THEN (_col5 BETWEEN null AND _col12) ELSE (_col5 BETWEEN _col9 AND _col12) END (type: boolean) + Statistics: Num rows: 14 Data size: 1800 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 3 Data size: 385 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 14 Data size: 1800 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 3 Data size: 385 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 14 Data size: 1800 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -2307,15 +2307,15 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (UDFToLong(_col5) <> CASE WHEN (_col10 is null) THEN (0) ELSE (_col9) END) (type: boolean) - Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE + predicate: CASE WHEN (_col10 is null) THEN ((UDFToLong(_col5) <> 0)) ELSE ((UDFToLong(_col5) <> _col9)) END (type: boolean) + Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -4624,15 +4624,15 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 Statistics: Num rows: 5 Data size: 261 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (UDFToLong(_col2) <> CASE WHEN (_col11 is null) THEN (0) ELSE (_col10) END) (type: boolean) - Statistics: Num rows: 5 Data size: 261 Basic stats: COMPLETE Column stats: NONE + predicate: CASE WHEN (_col11 is null) THEN ((UDFToLong(_col2) <> 0)) ELSE ((UDFToLong(_col2) <> _col10)) END (type: boolean) + Statistics: Num rows: 2 Data size: 104 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), _col1 (type: string), _col2 (type: int), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: int), _col7 (type: boolean), _col8 (type: boolean), _col9 (type: date) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 - Statistics: Num rows: 5 Data size: 261 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 104 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 5 Data size: 261 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 104 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -4886,17 +4886,17 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 Statistics: Num rows: 5 Data size: 261 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (UDFToLong(_col2) <> CASE WHEN (_col11 is null) THEN (0) ELSE (_col10) END) (type: boolean) - Statistics: Num rows: 5 Data size: 261 Basic stats: COMPLETE Column stats: NONE + predicate: CASE WHEN (_col11 is null) THEN ((UDFToLong(_col2) <> 0)) ELSE ((UDFToLong(_col2) <> _col10)) END (type: boolean) + Statistics: Num rows: 2 Data size: 104 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), _col1 (type: string), _col2 (type: int), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: int), _col7 (type: boolean), _col8 (type: boolean), _col9 (type: date) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 - Statistics: Num rows: 5 Data size: 261 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 104 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col2 (type: int) sort order: + Map-reduce partition columns: _col2 (type: int) - Statistics: Num rows: 5 Data size: 261 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 104 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: int), _col7 (type: boolean), _col8 (type: boolean), _col9 (type: date) Reducer 3 Reduce Operator Tree: @@ -4907,9 +4907,9 @@ STAGE PLANS: 0 _col2 (type: int) 1 _col2 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col13, _col14 - Statistics: Num rows: 5 Data size: 287 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 114 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (UDFToLong(_col0) > CASE WHEN (_col14 is null) THEN (0) ELSE (_col13) END) (type: boolean) + predicate: CASE WHEN (_col14 is null) THEN ((UDFToLong(_col0) > 0)) ELSE ((UDFToLong(_col0) > _col13)) END (type: boolean) Statistics: Num rows: 1 Data size: 57 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), _col1 (type: string), _col2 (type: int), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: int), _col7 (type: boolean), _col8 (type: boolean), _col9 (type: date) @@ -5913,15 +5913,15 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 Statistics: Num rows: 185 Data size: 45180 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (UDFToLong(_col5) <> CASE WHEN (_col10 is null) THEN (0) ELSE (_col9) END) (type: boolean) - Statistics: Num rows: 185 Data size: 45180 Basic stats: COMPLETE Column stats: NONE + predicate: CASE WHEN (_col10 is null) THEN ((UDFToLong(_col5) <> 0)) ELSE ((UDFToLong(_col5) <> _col9)) END (type: boolean) + Statistics: Num rows: 92 Data size: 22467 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 185 Data size: 45180 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 92 Data size: 22467 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 185 Data size: 45180 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 92 Data size: 22467 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat http://git-wip-us.apache.org/repos/asf/hive/blob/47dd953c/ql/src/test/results/clientpositive/spark/subquery_views.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/subquery_views.q.out b/ql/src/test/results/clientpositive/spark/subquery_views.q.out index 67711c2..54a8894 100644 --- a/ql/src/test/results/clientpositive/spark/subquery_views.q.out +++ b/ql/src/test/results/clientpositive/spark/subquery_views.q.out @@ -337,7 +337,7 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col4, _col5, _col8 Statistics: Num rows: 365 Data size: 3878 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: CASE WHEN ((_col4 = 0L)) THEN (true) WHEN (_col4 is null) THEN (true) WHEN (_col8 is not null) THEN (false) WHEN (_col0 is null) THEN (null) WHEN ((_col5 < _col4)) THEN (false) ELSE (true) END (type: boolean) + predicate: CASE WHEN ((_col4 = 0L)) THEN (true) WHEN (_col4 is null) THEN (true) WHEN (_col8 is not null) THEN (false) WHEN ((_col5 < _col4)) THEN (false) ELSE (true) END (type: boolean) Statistics: Num rows: 182 Data size: 1933 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: string) http://git-wip-us.apache.org/repos/asf/hive/blob/47dd953c/ql/src/test/results/clientpositive/spark/vectorized_case.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/vectorized_case.q.out b/ql/src/test/results/clientpositive/spark/vectorized_case.q.out index 4d322cf..0bf2a4b 100644 --- a/ql/src/test/results/clientpositive/spark/vectorized_case.q.out +++ b/ql/src/test/results/clientpositive/spark/vectorized_case.q.out @@ -1239,7 +1239,7 @@ where (case when cint % 2 = 0 then cint else 0 end) = cint) a POSTHOOK: type: QUERY POSTHOOK: Input: default@alltypesorc #### A masked pattern was here #### -0 +4086 PREHOOK: query: select count(*) from ( select http://git-wip-us.apache.org/repos/asf/hive/blob/47dd953c/ql/src/test/results/clientpositive/stat_estimate_related_col.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/stat_estimate_related_col.q.out b/ql/src/test/results/clientpositive/stat_estimate_related_col.q.out index 78524d6..669adaf 100644 --- a/ql/src/test/results/clientpositive/stat_estimate_related_col.q.out +++ b/ql/src/test/results/clientpositive/stat_estimate_related_col.q.out @@ -594,10 +594,10 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t8 - filterExpr: ((b = 2) and ((b = 1) or (b = 2))) (type: boolean) + filterExpr: (b = 2) (type: boolean) Statistics: Num rows: 40/40 Data size: 320 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: (((b = 1) or (b = 2)) and (b = 2)) (type: boolean) + predicate: (b = 2) (type: boolean) Statistics: Num rows: 8/8 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: a (type: int) @@ -663,27 +663,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t8 - filterExpr: ((b = 2) and ((b = 1) or (b = 2)) and ((b = 1) or (b = 3))) (type: boolean) - Statistics: Num rows: 40/40 Data size: 320 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 40/1 Data size: 320 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: (((b = 1) or (b = 2)) and ((b = 1) or (b = 3)) and (b = 2)) (type: boolean) - Statistics: Num rows: 8/0 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: a (type: int) - outputColumnNames: _col1 - Statistics: Num rows: 8/0 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: sum(_col1) - keys: 2 (type: int) - mode: hash - outputColumnNames: _col0, _col1 + predicate: false (type: boolean) + Statistics: Num rows: 1/0 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(a) + keys: b (type: int) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1/0 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 1/0 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1/0 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: bigint) + value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -748,10 +743,10 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t8 - filterExpr: ((b = 2) and ((b = 1) or (b = 2)) and (a = 3) and ((a = 3) or (a = 4))) (type: boolean) + filterExpr: ((b = 2) and (a = 3)) (type: boolean) Statistics: Num rows: 40/40 Data size: 320 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: (((a = 3) or (a = 4)) and ((b = 1) or (b = 2)) and (a = 3) and (b = 2)) (type: boolean) + predicate: ((a = 3) and (b = 2)) (type: boolean) Statistics: Num rows: 8/0 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE Select Operator Statistics: Num rows: 8/0 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE
