http://git-wip-us.apache.org/repos/asf/hive/blob/b8299551/ql/src/test/results/clientpositive/perf/tez/constraints/query43.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/query43.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/query43.q.out new file mode 100644 index 0000000..495b6bd --- /dev/null +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/query43.q.out @@ -0,0 +1,135 @@ +PREHOOK: query: explain +select s_store_name, s_store_id, + sum(case when (d_day_name='Sunday') then ss_sales_price else null end) sun_sales, + sum(case when (d_day_name='Monday') then ss_sales_price else null end) mon_sales, + sum(case when (d_day_name='Tuesday') then ss_sales_price else null end) tue_sales, + sum(case when (d_day_name='Wednesday') then ss_sales_price else null end) wed_sales, + sum(case when (d_day_name='Thursday') then ss_sales_price else null end) thu_sales, + sum(case when (d_day_name='Friday') then ss_sales_price else null end) fri_sales, + sum(case when (d_day_name='Saturday') then ss_sales_price else null end) sat_sales + from date_dim, store_sales, store + where d_date_sk = ss_sold_date_sk and + s_store_sk = ss_store_sk and + s_gmt_offset = -6 and + d_year = 1998 + group by s_store_name, s_store_id + order by s_store_name, s_store_id,sun_sales,mon_sales,tue_sales,wed_sales,thu_sales,fri_sales,sat_sales + limit 100 +PREHOOK: type: QUERY +PREHOOK: Input: default@date_dim +PREHOOK: Input: default@store +PREHOOK: Input: default@store_sales +PREHOOK: Output: hdfs://### HDFS PATH ### +POSTHOOK: query: explain +select s_store_name, s_store_id, + sum(case when (d_day_name='Sunday') then ss_sales_price else null end) sun_sales, + sum(case when (d_day_name='Monday') then ss_sales_price else null end) mon_sales, + sum(case when (d_day_name='Tuesday') then ss_sales_price else null end) tue_sales, + sum(case when (d_day_name='Wednesday') then ss_sales_price else null end) wed_sales, + sum(case when (d_day_name='Thursday') then ss_sales_price else null end) thu_sales, + sum(case when (d_day_name='Friday') then ss_sales_price else null end) fri_sales, + sum(case when (d_day_name='Saturday') then ss_sales_price else null end) sat_sales + from date_dim, store_sales, store + where d_date_sk = ss_sold_date_sk and + s_store_sk = ss_store_sk and + s_gmt_offset = -6 and + d_year = 1998 + group by s_store_name, s_store_id + order by s_store_name, s_store_id,sun_sales,mon_sales,tue_sales,wed_sales,thu_sales,fri_sales,sat_sales + limit 100 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@date_dim +POSTHOOK: Input: default@store +POSTHOOK: Input: default@store_sales +POSTHOOK: Output: hdfs://### HDFS PATH ### +Plan optimized by CBO. + +Vertex dependency in root stage +Map 1 <- Reducer 7 (BROADCAST_EDGE), Reducer 9 (BROADCAST_EDGE) +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 6 (SIMPLE_EDGE) +Reducer 3 <- Map 8 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) +Reducer 4 <- Reducer 3 (SIMPLE_EDGE) +Reducer 5 <- Reducer 4 (SIMPLE_EDGE) +Reducer 7 <- Map 6 (CUSTOM_SIMPLE_EDGE) +Reducer 9 <- Map 8 (CUSTOM_SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:100 + Stage-1 + Reducer 5 vectorized + File Output Operator [FS_79] + Limit [LIM_78] (rows=100 width=972) + Number of rows:100 + Select Operator [SEL_77] (rows=3751 width=972) + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"] + <-Reducer 4 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_76] + Group By Operator [GBY_75] (rows=3751 width=972) + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)","sum(VALUE._col3)","sum(VALUE._col4)","sum(VALUE._col5)","sum(VALUE._col6)"],keys:KEY._col0, KEY._col1 + <-Reducer 3 [SIMPLE_EDGE] + SHUFFLE [RS_18] + PartitionCols:_col0, _col1 + Group By Operator [GBY_17] (rows=142538 width=972) + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"],aggregations:["sum(_col2)","sum(_col3)","sum(_col4)","sum(_col5)","sum(_col6)","sum(_col7)","sum(_col8)"],keys:_col0, _col1 + Top N Key Operator [TNK_33] (rows=37536846 width=257) + keys:_col0, _col1,sort order:++,top n:100 + Select Operator [SEL_15] (rows=37536846 width=257) + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"] + Merge Join Operator [MERGEJOIN_55] (rows=37536846 width=257) + Conds:RS_12._col1=RS_66._col0(Inner),Output:["_col2","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col12","_col13"] + <-Map 8 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_66] + PartitionCols:_col0 + Select Operator [SEL_65] (rows=341 width=192) + Output:["_col0","_col1","_col2"] + Filter Operator [FIL_64] (rows=341 width=303) + predicate:(s_gmt_offset = -6) + TableScan [TS_6] (rows=1704 width=303) + default@store,store,Tbl:COMPLETE,Col:COMPLETE,Output:["s_store_sk","s_store_id","s_store_name","s_gmt_offset"] + <-Reducer 2 [SIMPLE_EDGE] + SHUFFLE [RS_12] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_54] (rows=187574154 width=129) + Conds:RS_74._col0=RS_58._col0(Inner),Output:["_col1","_col2","_col4","_col5","_col6","_col7","_col8","_col9","_col10"] + <-Map 6 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_58] + PartitionCols:_col0 + Select Operator [SEL_57] (rows=652 width=32) + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] + Filter Operator [FIL_56] (rows=652 width=99) + predicate:(d_year = 1998) + TableScan [TS_3] (rows=73049 width=99) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year","d_day_name"] + <-Map 1 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_74] + PartitionCols:_col0 + Select Operator [SEL_73] (rows=525329897 width=114) + Output:["_col0","_col1","_col2"] + Filter Operator [FIL_72] (rows=525329897 width=114) + predicate:((ss_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(ss_sold_date_sk, DynamicValue(RS_10_date_dim_d_date_sk_bloom_filter))) and (ss_store_sk BETWEEN DynamicValue(RS_13_store_s_store_sk_min) AND DynamicValue(RS_13_store_s_store_sk_max) and in_bloom_filter(ss_store_sk, DynamicValue(RS_13_store_s_store_sk_bloom_filter))) and ss_sold_date_sk is not null and ss_store_sk is not null) + TableScan [TS_0] (rows=575995635 width=114) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_store_sk","ss_sales_price"] + <-Reducer 7 [BROADCAST_EDGE] vectorized + BROADCAST [RS_63] + Group By Operator [GBY_62] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 6 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_61] + Group By Operator [GBY_60] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_59] (rows=652 width=4) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_57] + <-Reducer 9 [BROADCAST_EDGE] vectorized + BROADCAST [RS_71] + Group By Operator [GBY_70] (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_69] + Group By Operator [GBY_68] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_67] (rows=341 width=4) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_65] +
http://git-wip-us.apache.org/repos/asf/hive/blob/b8299551/ql/src/test/results/clientpositive/perf/tez/constraints/query44.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/query44.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/query44.q.out new file mode 100644 index 0000000..13b0936 --- /dev/null +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/query44.q.out @@ -0,0 +1,193 @@ +Warning: Shuffle Join MERGEJOIN[101][tables = [$hdt$_1, $hdt$_2]] in Stage 'Reducer 8' is a cross product +PREHOOK: query: explain +select asceding.rnk, i1.i_product_name best_performing, i2.i_product_name worst_performing +from(select * + from (select item_sk,rank() over (order by rank_col asc) rnk + from (select ss_item_sk item_sk,avg(ss_net_profit) rank_col + from store_sales ss1 + where ss_store_sk = 410 + group by ss_item_sk + having avg(ss_net_profit) > 0.9*(select avg(ss_net_profit) rank_col + from store_sales + where ss_store_sk = 410 + and ss_hdemo_sk is null + group by ss_store_sk))V1)V11 + where rnk < 11) asceding, + (select * + from (select item_sk,rank() over (order by rank_col desc) rnk + from (select ss_item_sk item_sk,avg(ss_net_profit) rank_col + from store_sales ss1 + where ss_store_sk = 410 + group by ss_item_sk + having avg(ss_net_profit) > 0.9*(select avg(ss_net_profit) rank_col + from store_sales + where ss_store_sk = 410 + and ss_hdemo_sk is null + group by ss_store_sk))V2)V21 + where rnk < 11) descending, +item i1, +item i2 +where asceding.rnk = descending.rnk + and i1.i_item_sk=asceding.item_sk + and i2.i_item_sk=descending.item_sk +order by asceding.rnk +limit 100 +PREHOOK: type: QUERY +PREHOOK: Input: default@item +PREHOOK: Input: default@store_sales +PREHOOK: Output: hdfs://### HDFS PATH ### +POSTHOOK: query: explain +select asceding.rnk, i1.i_product_name best_performing, i2.i_product_name worst_performing +from(select * + from (select item_sk,rank() over (order by rank_col asc) rnk + from (select ss_item_sk item_sk,avg(ss_net_profit) rank_col + from store_sales ss1 + where ss_store_sk = 410 + group by ss_item_sk + having avg(ss_net_profit) > 0.9*(select avg(ss_net_profit) rank_col + from store_sales + where ss_store_sk = 410 + and ss_hdemo_sk is null + group by ss_store_sk))V1)V11 + where rnk < 11) asceding, + (select * + from (select item_sk,rank() over (order by rank_col desc) rnk + from (select ss_item_sk item_sk,avg(ss_net_profit) rank_col + from store_sales ss1 + where ss_store_sk = 410 + group by ss_item_sk + having avg(ss_net_profit) > 0.9*(select avg(ss_net_profit) rank_col + from store_sales + where ss_store_sk = 410 + and ss_hdemo_sk is null + group by ss_store_sk))V2)V21 + where rnk < 11) descending, +item i1, +item i2 +where asceding.rnk = descending.rnk + and i1.i_item_sk=asceding.item_sk + and i2.i_item_sk=descending.item_sk +order by asceding.rnk +limit 100 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@item +POSTHOOK: Input: default@store_sales +POSTHOOK: Output: hdfs://### HDFS PATH ### +Plan optimized by CBO. + +Vertex dependency in root stage +Reducer 10 <- Reducer 8 (SIMPLE_EDGE) +Reducer 12 <- Map 11 (SIMPLE_EDGE) +Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 9 (SIMPLE_EDGE) +Reducer 3 <- Reducer 2 (SIMPLE_EDGE), Reducer 5 (SIMPLE_EDGE) +Reducer 4 <- Reducer 3 (SIMPLE_EDGE) +Reducer 5 <- Map 1 (SIMPLE_EDGE), Reducer 10 (SIMPLE_EDGE) +Reducer 7 <- Map 6 (SIMPLE_EDGE) +Reducer 8 <- Reducer 12 (CUSTOM_SIMPLE_EDGE), Reducer 7 (CUSTOM_SIMPLE_EDGE) +Reducer 9 <- Reducer 8 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:100 + Stage-1 + Reducer 4 vectorized + File Output Operator [FS_135] + Limit [LIM_134] (rows=100 width=218) + Number of rows:100 + Select Operator [SEL_133] (rows=6951 width=218) + Output:["_col0","_col1","_col2"] + <-Reducer 3 [SIMPLE_EDGE] + SHUFFLE [RS_67] + Select Operator [SEL_66] (rows=6951 width=218) + Output:["_col0","_col1","_col2"] + Merge Join Operator [MERGEJOIN_105] (rows=6951 width=218) + Conds:RS_63._col3=RS_64._col3(Inner),Output:["_col1","_col3","_col5"] + <-Reducer 2 [SIMPLE_EDGE] + SHUFFLE [RS_63] + PartitionCols:_col3 + Merge Join Operator [MERGEJOIN_102] (rows=6951 width=111) + Conds:RS_107._col0=RS_127._col0(Inner),Output:["_col1","_col3"] + <-Map 1 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_107] + PartitionCols:_col0 + Select Operator [SEL_106] (rows=462000 width=111) + Output:["_col0","_col1"] + TableScan [TS_0] (rows=462000 width=111) + default@item,i1,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_product_name"] + <-Reducer 9 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_127] + PartitionCols:_col0 + Select Operator [SEL_126] (rows=6951 width=8) + Output:["_col0","_col1"] + Filter Operator [FIL_125] (rows=6951 width=116) + predicate:(rank_window_0 < 11) + PTF Operator [PTF_124] (rows=20854 width=116) + Function definitions:[{},{"name:":"windowingtablefunction","order by:":"_col1 ASC NULLS FIRST","partition by:":"0"}] + Select Operator [SEL_123] (rows=20854 width=116) + Output:["_col0","_col1"] + <-Reducer 8 [SIMPLE_EDGE] + SHUFFLE [RS_21] + PartitionCols:0 + Filter Operator [FIL_20] (rows=20854 width=228) + predicate:(_col1 > _col2) + Merge Join Operator [MERGEJOIN_101] (rows=62562 width=228) + Conds:(Inner),Output:["_col0","_col1","_col2"] + <-Reducer 12 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_122] + Select Operator [SEL_121] (rows=1 width=112) + Output:["_col0"] + Group By Operator [GBY_120] (rows=1 width=124) + Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)","count(VALUE._col1)"],keys:KEY._col0 + <-Map 11 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_119] + PartitionCols:_col0 + Group By Operator [GBY_118] (rows=258 width=124) + Output:["_col0","_col1","_col2"],aggregations:["sum(_col1)","count(_col1)"],keys:true + Select Operator [SEL_117] (rows=287946 width=114) + Output:["_col1"] + Filter Operator [FIL_116] (rows=287946 width=114) + predicate:((ss_store_sk = 410) and ss_hdemo_sk is null) + TableScan [TS_9] (rows=575995635 width=114) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_hdemo_sk","ss_store_sk","ss_net_profit"] + <-Reducer 7 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_115] + Select Operator [SEL_114] (rows=62562 width=116) + Output:["_col0","_col1"] + Group By Operator [GBY_113] (rows=62562 width=124) + Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)","count(VALUE._col1)"],keys:KEY._col0 + <-Map 6 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_112] + PartitionCols:_col0 + Group By Operator [GBY_111] (rows=3199976 width=124) + Output:["_col0","_col1","_col2"],aggregations:["sum(ss_net_profit)","count(ss_net_profit)"],keys:ss_item_sk + Select Operator [SEL_110] (rows=6399952 width=114) + Output:["ss_item_sk","ss_net_profit"] + Filter Operator [FIL_109] (rows=6399952 width=114) + predicate:(ss_store_sk = 410) + TableScan [TS_2] (rows=575995635 width=114) + default@store_sales,ss1,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_item_sk","ss_store_sk","ss_net_profit"] + <-Reducer 5 [SIMPLE_EDGE] + SHUFFLE [RS_64] + PartitionCols:_col3 + Merge Join Operator [MERGEJOIN_104] (rows=6951 width=111) + Conds:RS_108._col0=RS_132._col0(Inner),Output:["_col1","_col3"] + <-Map 1 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_108] + PartitionCols:_col0 + Please refer to the previous Select Operator [SEL_106] + <-Reducer 10 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_132] + PartitionCols:_col0 + Select Operator [SEL_131] (rows=6951 width=8) + Output:["_col0","_col1"] + Filter Operator [FIL_130] (rows=6951 width=116) + predicate:(rank_window_0 < 11) + PTF Operator [PTF_129] (rows=20854 width=116) + Function definitions:[{},{"name:":"windowingtablefunction","order by:":"_col1 DESC NULLS LAST","partition by:":"0"}] + Select Operator [SEL_128] (rows=20854 width=116) + Output:["_col0","_col1"] + <-Reducer 8 [SIMPLE_EDGE] + SHUFFLE [RS_49] + PartitionCols:0 + Please refer to the previous Filter Operator [FIL_20] + http://git-wip-us.apache.org/repos/asf/hive/blob/b8299551/ql/src/test/results/clientpositive/perf/tez/constraints/query45.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/query45.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/query45.q.out new file mode 100644 index 0000000..bf620c8 --- /dev/null +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/query45.q.out @@ -0,0 +1,183 @@ +PREHOOK: query: explain +select ca_zip, ca_county, sum(ws_sales_price) + from web_sales, customer, customer_address, date_dim, item + where ws_bill_customer_sk = c_customer_sk + and c_current_addr_sk = ca_address_sk + and ws_item_sk = i_item_sk + and ( substr(ca_zip,1,5) in ('85669', '86197','88274','83405','86475', '85392', '85460', '80348', '81792') + or + i_item_id in (select i_item_id + from item + where i_item_sk in (2, 3, 5, 7, 11, 13, 17, 19, 23, 29) + ) + ) + and ws_sold_date_sk = d_date_sk + and d_qoy = 2 and d_year = 2000 + group by ca_zip, ca_county + order by ca_zip, ca_county + limit 100 +PREHOOK: type: QUERY +PREHOOK: Input: default@customer +PREHOOK: Input: default@customer_address +PREHOOK: Input: default@date_dim +PREHOOK: Input: default@item +PREHOOK: Input: default@web_sales +PREHOOK: Output: hdfs://### HDFS PATH ### +POSTHOOK: query: explain +select ca_zip, ca_county, sum(ws_sales_price) + from web_sales, customer, customer_address, date_dim, item + where ws_bill_customer_sk = c_customer_sk + and c_current_addr_sk = ca_address_sk + and ws_item_sk = i_item_sk + and ( substr(ca_zip,1,5) in ('85669', '86197','88274','83405','86475', '85392', '85460', '80348', '81792') + or + i_item_id in (select i_item_id + from item + where i_item_sk in (2, 3, 5, 7, 11, 13, 17, 19, 23, 29) + ) + ) + and ws_sold_date_sk = d_date_sk + and d_qoy = 2 and d_year = 2000 + group by ca_zip, ca_county + order by ca_zip, ca_county + limit 100 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@customer +POSTHOOK: Input: default@customer_address +POSTHOOK: Input: default@date_dim +POSTHOOK: Input: default@item +POSTHOOK: Input: default@web_sales +POSTHOOK: Output: hdfs://### HDFS PATH ### +Plan optimized by CBO. + +Vertex dependency in root stage +Map 11 <- Reducer 14 (BROADCAST_EDGE) +Reducer 10 <- Map 7 (SIMPLE_EDGE) +Reducer 12 <- Map 11 (SIMPLE_EDGE), Map 13 (SIMPLE_EDGE) +Reducer 14 <- Map 13 (CUSTOM_SIMPLE_EDGE) +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 6 (SIMPLE_EDGE) +Reducer 3 <- Reducer 2 (SIMPLE_EDGE), Reducer 9 (SIMPLE_EDGE) +Reducer 4 <- Reducer 3 (SIMPLE_EDGE) +Reducer 5 <- Reducer 4 (SIMPLE_EDGE) +Reducer 8 <- Map 7 (SIMPLE_EDGE), Reducer 10 (ONE_TO_ONE_EDGE) +Reducer 9 <- Reducer 12 (SIMPLE_EDGE), Reducer 8 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:100 + Stage-1 + Reducer 5 vectorized + File Output Operator [FS_149] + Limit [LIM_148] (rows=100 width=299) + Number of rows:100 + Select Operator [SEL_147] (rows=285780 width=299) + Output:["_col0","_col1","_col2"] + <-Reducer 4 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_146] + Group By Operator [GBY_145] (rows=285780 width=299) + Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1 + <-Reducer 3 [SIMPLE_EDGE] + SHUFFLE [RS_41] + PartitionCols:_col0, _col1 + Group By Operator [GBY_40] (rows=3715140 width=299) + Output:["_col0","_col1","_col2"],aggregations:["sum(_col3)"],keys:_col8, _col7 + Top N Key Operator [TNK_69] (rows=10246864 width=302) + keys:_col8, _col7,sort order:++,top n:100 + Select Operator [SEL_39] (rows=10246864 width=302) + Output:["_col3","_col7","_col8"] + Filter Operator [FIL_38] (rows=10246864 width=302) + predicate:((substr(_col8, 1, 5)) IN ('85669', '86197', '88274', '83405', '86475', '85392', '85460', '80348', '81792') or _col15 is not null) + Select Operator [SEL_37] (rows=10246864 width=302) + Output:["_col3","_col7","_col8","_col15"] + Merge Join Operator [MERGEJOIN_119] (rows=10246864 width=302) + Conds:RS_34._col0=RS_35._col6(Inner),Output:["_col3","_col4","_col8","_col12"] + <-Reducer 2 [SIMPLE_EDGE] + SHUFFLE [RS_34] + PartitionCols:_col0 + Merge Join Operator [MERGEJOIN_115] (rows=80000000 width=191) + Conds:RS_122._col1=RS_124._col0(Inner),Output:["_col0","_col3","_col4"] + <-Map 1 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_122] + PartitionCols:_col1 + Select Operator [SEL_121] (rows=80000000 width=8) + Output:["_col0","_col1"] + Filter Operator [FIL_120] (rows=80000000 width=8) + predicate:c_current_addr_sk is not null + TableScan [TS_0] (rows=80000000 width=8) + default@customer,customer,Tbl:COMPLETE,Col:COMPLETE,Output:["c_customer_sk","c_current_addr_sk"] + <-Map 6 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_124] + PartitionCols:_col0 + Select Operator [SEL_123] (rows=40000000 width=191) + Output:["_col0","_col1","_col2"] + TableScan [TS_3] (rows=40000000 width=191) + default@customer_address,customer_address,Tbl:COMPLETE,Col:COMPLETE,Output:["ca_address_sk","ca_county","ca_zip"] + <-Reducer 9 [SIMPLE_EDGE] + SHUFFLE [RS_35] + PartitionCols:_col6 + Merge Join Operator [MERGEJOIN_118] (rows=10246864 width=119) + Conds:RS_27._col0=RS_28._col1(Inner),Output:["_col3","_col6","_col7"] + <-Reducer 12 [SIMPLE_EDGE] + SHUFFLE [RS_28] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_117] (rows=10246864 width=119) + Conds:RS_144._col0=RS_136._col0(Inner),Output:["_col1","_col2","_col3"] + <-Map 13 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_136] + PartitionCols:_col0 + Select Operator [SEL_135] (rows=130 width=12) + Output:["_col0"] + Filter Operator [FIL_134] (rows=130 width=12) + predicate:((d_qoy = 2) and (d_year = 2000)) + TableScan [TS_17] (rows=73049 width=12) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year","d_qoy"] + <-Map 11 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_144] + PartitionCols:_col0 + Select Operator [SEL_143] (rows=143930993 width=123) + Output:["_col0","_col1","_col2","_col3"] + Filter Operator [FIL_142] (rows=143930993 width=123) + predicate:((ws_sold_date_sk BETWEEN DynamicValue(RS_21_date_dim_d_date_sk_min) AND DynamicValue(RS_21_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_21_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_14] (rows=144002668 width=123) + default@web_sales,web_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_sold_date_sk","ws_item_sk","ws_bill_customer_sk","ws_sales_price"] + <-Reducer 14 [BROADCAST_EDGE] vectorized + BROADCAST [RS_141] + Group By Operator [GBY_140] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 13 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_139] + Group By Operator [GBY_138] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_137] (rows=130 width=4) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_135] + <-Reducer 8 [SIMPLE_EDGE] + SHUFFLE [RS_27] + PartitionCols:_col0 + Merge Join Operator [MERGEJOIN_116] (rows=462007 width=4) + Conds:RS_127._col1=RS_133._col0(Left Outer),Output:["_col0","_col3"] + <-Map 7 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_127] + PartitionCols:_col1 + Select Operator [SEL_125] (rows=462000 width=104) + Output:["_col0","_col1"] + TableScan [TS_5] (rows=462000 width=104) + default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_item_id"] + <-Reducer 10 [ONE_TO_ONE_EDGE] vectorized + FORWARD [RS_133] + PartitionCols:_col0 + Select Operator [SEL_132] (rows=5 width=104) + Output:["_col0","_col1"] + Group By Operator [GBY_131] (rows=5 width=100) + Output:["_col0"],keys:KEY._col0 + <-Map 7 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_130] + PartitionCols:_col0 + Group By Operator [GBY_129] (rows=5 width=100) + Output:["_col0"],keys:i_item_id + Select Operator [SEL_128] (rows=11 width=104) + Output:["i_item_id"] + Filter Operator [FIL_126] (rows=11 width=104) + predicate:(i_item_sk) IN (2, 3, 5, 7, 11, 13, 17, 19, 23, 29) + Please refer to the previous TableScan [TS_5] + http://git-wip-us.apache.org/repos/asf/hive/blob/b8299551/ql/src/test/results/clientpositive/perf/tez/constraints/query46.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/query46.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/query46.q.out new file mode 100644 index 0000000..b7a6bd6 --- /dev/null +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/query46.q.out @@ -0,0 +1,240 @@ +PREHOOK: query: explain +select c_last_name + ,c_first_name + ,ca_city + ,bought_city + ,ss_ticket_number + ,amt,profit + from + (select ss_ticket_number + ,ss_customer_sk + ,ca_city bought_city + ,sum(ss_coupon_amt) amt + ,sum(ss_net_profit) profit + from store_sales,date_dim,store,household_demographics,customer_address + where store_sales.ss_sold_date_sk = date_dim.d_date_sk + and store_sales.ss_store_sk = store.s_store_sk + and store_sales.ss_hdemo_sk = household_demographics.hd_demo_sk + and store_sales.ss_addr_sk = customer_address.ca_address_sk + and (household_demographics.hd_dep_count = 2 or + household_demographics.hd_vehicle_count= 1) + and date_dim.d_dow in (6,0) + and date_dim.d_year in (1998,1998+1,1998+2) + and store.s_city in ('Cedar Grove','Wildwood','Union','Salem','Highland Park') + group by ss_ticket_number,ss_customer_sk,ss_addr_sk,ca_city) dn,customer,customer_address current_addr + where ss_customer_sk = c_customer_sk + and customer.c_current_addr_sk = current_addr.ca_address_sk + and current_addr.ca_city <> bought_city + order by c_last_name + ,c_first_name + ,ca_city + ,bought_city + ,ss_ticket_number + limit 100 +PREHOOK: type: QUERY +PREHOOK: Input: default@customer +PREHOOK: Input: default@customer_address +PREHOOK: Input: default@date_dim +PREHOOK: Input: default@household_demographics +PREHOOK: Input: default@store +PREHOOK: Input: default@store_sales +PREHOOK: Output: hdfs://### HDFS PATH ### +POSTHOOK: query: explain +select c_last_name + ,c_first_name + ,ca_city + ,bought_city + ,ss_ticket_number + ,amt,profit + from + (select ss_ticket_number + ,ss_customer_sk + ,ca_city bought_city + ,sum(ss_coupon_amt) amt + ,sum(ss_net_profit) profit + from store_sales,date_dim,store,household_demographics,customer_address + where store_sales.ss_sold_date_sk = date_dim.d_date_sk + and store_sales.ss_store_sk = store.s_store_sk + and store_sales.ss_hdemo_sk = household_demographics.hd_demo_sk + and store_sales.ss_addr_sk = customer_address.ca_address_sk + and (household_demographics.hd_dep_count = 2 or + household_demographics.hd_vehicle_count= 1) + and date_dim.d_dow in (6,0) + and date_dim.d_year in (1998,1998+1,1998+2) + and store.s_city in ('Cedar Grove','Wildwood','Union','Salem','Highland Park') + group by ss_ticket_number,ss_customer_sk,ss_addr_sk,ca_city) dn,customer,customer_address current_addr + where ss_customer_sk = c_customer_sk + and customer.c_current_addr_sk = current_addr.ca_address_sk + and current_addr.ca_city <> bought_city + order by c_last_name + ,c_first_name + ,ca_city + ,bought_city + ,ss_ticket_number + limit 100 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@customer +POSTHOOK: Input: default@customer_address +POSTHOOK: Input: default@date_dim +POSTHOOK: Input: default@household_demographics +POSTHOOK: Input: default@store +POSTHOOK: Input: default@store_sales +POSTHOOK: Output: hdfs://### HDFS PATH ### +Plan optimized by CBO. + +Vertex dependency in root stage +Map 8 <- Reducer 13 (BROADCAST_EDGE), Reducer 15 (BROADCAST_EDGE), Reducer 17 (BROADCAST_EDGE) +Reducer 10 <- Map 14 (SIMPLE_EDGE), Reducer 9 (SIMPLE_EDGE) +Reducer 11 <- Map 16 (SIMPLE_EDGE), Reducer 10 (SIMPLE_EDGE) +Reducer 13 <- Map 12 (CUSTOM_SIMPLE_EDGE) +Reducer 15 <- Map 14 (CUSTOM_SIMPLE_EDGE) +Reducer 17 <- Map 16 (CUSTOM_SIMPLE_EDGE) +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) +Reducer 3 <- Reducer 2 (SIMPLE_EDGE), Reducer 7 (SIMPLE_EDGE) +Reducer 4 <- Reducer 3 (SIMPLE_EDGE) +Reducer 6 <- Map 5 (SIMPLE_EDGE), Reducer 11 (SIMPLE_EDGE) +Reducer 7 <- Reducer 6 (SIMPLE_EDGE) +Reducer 9 <- Map 12 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:100 + Stage-1 + Reducer 4 vectorized + File Output Operator [FS_182] + Limit [LIM_181] (rows=100 width=594) + Number of rows:100 + Select Operator [SEL_180] (rows=20351707 width=594) + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"] + <-Reducer 3 [SIMPLE_EDGE] + SHUFFLE [RS_44] + Select Operator [SEL_43] (rows=20351707 width=594) + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"] + Filter Operator [FIL_42] (rows=20351707 width=594) + predicate:(_col5 <> _col8) + Merge Join Operator [MERGEJOIN_143] (rows=20351707 width=594) + Conds:RS_39._col0=RS_179._col1(Inner),Output:["_col2","_col3","_col5","_col6","_col8","_col9","_col10"] + <-Reducer 2 [SIMPLE_EDGE] + SHUFFLE [RS_39] + PartitionCols:_col0 + Merge Join Operator [MERGEJOIN_138] (rows=80000000 width=277) + Conds:RS_146._col1=RS_148._col0(Inner),Output:["_col0","_col2","_col3","_col5"] + <-Map 5 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_148] + PartitionCols:_col0 + Select Operator [SEL_147] (rows=40000000 width=97) + Output:["_col0","_col1"] + TableScan [TS_3] (rows=40000000 width=97) + default@customer_address,current_addr,Tbl:COMPLETE,Col:COMPLETE,Output:["ca_address_sk","ca_city"] + <-Map 1 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_146] + PartitionCols:_col1 + Select Operator [SEL_145] (rows=80000000 width=188) + Output:["_col0","_col1","_col2","_col3"] + Filter Operator [FIL_144] (rows=80000000 width=188) + predicate:c_current_addr_sk is not null + TableScan [TS_0] (rows=80000000 width=188) + default@customer,customer,Tbl:COMPLETE,Col:COMPLETE,Output:["c_customer_sk","c_current_addr_sk","c_first_name","c_last_name"] + <-Reducer 7 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_179] + PartitionCols:_col1 + Select Operator [SEL_178] (rows=20351707 width=321) + Output:["_col0","_col1","_col2","_col3","_col4"] + Group By Operator [GBY_177] (rows=20351707 width=321) + Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3 + <-Reducer 6 [SIMPLE_EDGE] + SHUFFLE [RS_33] + PartitionCols:_col0, _col1, _col2, _col3 + Group By Operator [GBY_32] (rows=20351707 width=321) + Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(_col6)","sum(_col7)"],keys:_col1, _col12, _col3, _col5 + Merge Join Operator [MERGEJOIN_142] (rows=20351707 width=97) + Conds:RS_28._col3=RS_149._col0(Inner),Output:["_col1","_col3","_col5","_col6","_col7","_col12"] + <-Map 5 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_149] + PartitionCols:_col0 + Please refer to the previous Select Operator [SEL_147] + <-Reducer 11 [SIMPLE_EDGE] + SHUFFLE [RS_28] + PartitionCols:_col3 + Merge Join Operator [MERGEJOIN_141] (rows=20351707 width=4) + Conds:RS_25._col2=RS_168._col0(Inner),Output:["_col1","_col3","_col5","_col6","_col7"] + <-Map 16 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_168] + PartitionCols:_col0 + Select Operator [SEL_167] (rows=1855 width=4) + Output:["_col0"] + Filter Operator [FIL_166] (rows=1855 width=12) + predicate:((hd_dep_count = 2) or (hd_vehicle_count = 1)) + TableScan [TS_14] (rows=7200 width=12) + default@household_demographics,household_demographics,Tbl:COMPLETE,Col:COMPLETE,Output:["hd_demo_sk","hd_dep_count","hd_vehicle_count"] + <-Reducer 10 [SIMPLE_EDGE] + SHUFFLE [RS_25] + PartitionCols:_col2 + Merge Join Operator [MERGEJOIN_140] (rows=78993142 width=178) + Conds:RS_22._col4=RS_160._col0(Inner),Output:["_col1","_col2","_col3","_col5","_col6","_col7"] + <-Map 14 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_160] + PartitionCols:_col0 + Select Operator [SEL_159] (rows=85 width=4) + Output:["_col0"] + Filter Operator [FIL_158] (rows=85 width=97) + predicate:(s_city) IN ('Cedar Grove', 'Wildwood', 'Union', 'Salem', 'Highland Park') + TableScan [TS_11] (rows=1704 width=97) + default@store,store,Tbl:COMPLETE,Col:COMPLETE,Output:["s_store_sk","s_city"] + <-Reducer 9 [SIMPLE_EDGE] + SHUFFLE [RS_22] + PartitionCols:_col4 + Merge Join Operator [MERGEJOIN_139] (rows=196204013 width=218) + Conds:RS_176._col0=RS_152._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col6","_col7"] + <-Map 12 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_152] + PartitionCols:_col0 + Select Operator [SEL_151] (rows=783 width=4) + Output:["_col0"] + Filter Operator [FIL_150] (rows=783 width=12) + predicate:((d_dow) IN (6, 0) and (d_year) IN (1998, 1999, 2000)) + TableScan [TS_8] (rows=73049 width=12) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year","d_dow"] + <-Map 8 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_176] + PartitionCols:_col0 + Select Operator [SEL_175] (rows=457565061 width=237) + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] + Filter Operator [FIL_174] (rows=457565061 width=237) + predicate:((ss_hdemo_sk BETWEEN DynamicValue(RS_26_household_demographics_hd_demo_sk_min) AND DynamicValue(RS_26_household_demographics_hd_demo_sk_max) and in_bloom_filter(ss_hdemo_sk, DynamicValue(RS_26_household_demographics_hd_demo_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_20_date_dim_d_date_sk_min) AND DynamicValue(RS_20_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_20_date_dim_d_date_sk_bloom_filter))) and (ss_store_sk BETWEEN DynamicValue(RS_23_store_s_store_sk_min) AND DynamicValue(RS_23_store_s_store_sk_max) and in_bloom_filter(ss_store_sk, DynamicValue(RS_23_store_s_store_sk_bloom_filter))) and ss_addr_sk is not null and ss_customer_sk is not null and ss_hdemo_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null) + TableScan [TS_5] (rows=575995635 width=237) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_customer_sk","ss_hdemo_sk","ss_addr_sk","ss_store_sk","ss_ticket_number","ss_coupon_amt","ss_net_profit"] + <-Reducer 13 [BROADCAST_EDGE] vectorized + BROADCAST [RS_157] + Group By Operator [GBY_156] (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_155] + Group By Operator [GBY_154] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_153] (rows=783 width=4) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_151] + <-Reducer 15 [BROADCAST_EDGE] vectorized + BROADCAST [RS_165] + Group By Operator [GBY_164] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 14 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_163] + Group By Operator [GBY_162] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_161] (rows=85 width=4) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_159] + <-Reducer 17 [BROADCAST_EDGE] vectorized + BROADCAST [RS_173] + Group By Operator [GBY_172] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 16 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_171] + Group By Operator [GBY_170] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_169] (rows=1855 width=4) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_167] + http://git-wip-us.apache.org/repos/asf/hive/blob/b8299551/ql/src/test/results/clientpositive/perf/tez/constraints/query47.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/query47.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/query47.q.out new file mode 100644 index 0000000..e905b1178 --- /dev/null +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/query47.q.out @@ -0,0 +1,266 @@ +PREHOOK: query: explain +with v1 as( + select i_category, i_brand, + s_store_name, s_company_name, + d_year, d_moy, + sum(ss_sales_price) sum_sales, + avg(sum(ss_sales_price)) over + (partition by i_category, i_brand, + s_store_name, s_company_name, d_year) + avg_monthly_sales, + rank() over + (partition by i_category, i_brand, + s_store_name, s_company_name + order by d_year, d_moy) rn + from item, store_sales, date_dim, store + where ss_item_sk = i_item_sk and + ss_sold_date_sk = d_date_sk and + ss_store_sk = s_store_sk and + ( + d_year = 2000 or + ( d_year = 2000-1 and d_moy =12) or + ( d_year = 2000+1 and d_moy =1) + ) + group by i_category, i_brand, + s_store_name, s_company_name, + d_year, d_moy), + v2 as( + select v1.i_category + ,v1.d_year, v1.d_moy + ,v1.avg_monthly_sales + ,v1.sum_sales, v1_lag.sum_sales psum, v1_lead.sum_sales nsum + from v1, v1 v1_lag, v1 v1_lead + where v1.i_category = v1_lag.i_category and + v1.i_category = v1_lead.i_category and + v1.i_brand = v1_lag.i_brand and + v1.i_brand = v1_lead.i_brand and + v1.s_store_name = v1_lag.s_store_name and + v1.s_store_name = v1_lead.s_store_name and + v1.s_company_name = v1_lag.s_company_name and + v1.s_company_name = v1_lead.s_company_name and + v1.rn = v1_lag.rn + 1 and + v1.rn = v1_lead.rn - 1) + select * + from v2 + where d_year = 2000 and + avg_monthly_sales > 0 and + case when avg_monthly_sales > 0 then abs(sum_sales - avg_monthly_sales) / avg_monthly_sales else null end > 0.1 + order by sum_sales - avg_monthly_sales, 3 + limit 100 +PREHOOK: type: QUERY +PREHOOK: Input: default@date_dim +PREHOOK: Input: default@item +PREHOOK: Input: default@store +PREHOOK: Input: default@store_sales +PREHOOK: Output: hdfs://### HDFS PATH ### +POSTHOOK: query: explain +with v1 as( + select i_category, i_brand, + s_store_name, s_company_name, + d_year, d_moy, + sum(ss_sales_price) sum_sales, + avg(sum(ss_sales_price)) over + (partition by i_category, i_brand, + s_store_name, s_company_name, d_year) + avg_monthly_sales, + rank() over + (partition by i_category, i_brand, + s_store_name, s_company_name + order by d_year, d_moy) rn + from item, store_sales, date_dim, store + where ss_item_sk = i_item_sk and + ss_sold_date_sk = d_date_sk and + ss_store_sk = s_store_sk and + ( + d_year = 2000 or + ( d_year = 2000-1 and d_moy =12) or + ( d_year = 2000+1 and d_moy =1) + ) + group by i_category, i_brand, + s_store_name, s_company_name, + d_year, d_moy), + v2 as( + select v1.i_category + ,v1.d_year, v1.d_moy + ,v1.avg_monthly_sales + ,v1.sum_sales, v1_lag.sum_sales psum, v1_lead.sum_sales nsum + from v1, v1 v1_lag, v1 v1_lead + where v1.i_category = v1_lag.i_category and + v1.i_category = v1_lead.i_category and + v1.i_brand = v1_lag.i_brand and + v1.i_brand = v1_lead.i_brand and + v1.s_store_name = v1_lag.s_store_name and + v1.s_store_name = v1_lead.s_store_name and + v1.s_company_name = v1_lag.s_company_name and + v1.s_company_name = v1_lead.s_company_name and + v1.rn = v1_lag.rn + 1 and + v1.rn = v1_lead.rn - 1) + select * + from v2 + where d_year = 2000 and + avg_monthly_sales > 0 and + case when avg_monthly_sales > 0 then abs(sum_sales - avg_monthly_sales) / avg_monthly_sales else null end > 0.1 + order by sum_sales - avg_monthly_sales, 3 + limit 100 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@date_dim +POSTHOOK: Input: default@item +POSTHOOK: Input: default@store +POSTHOOK: Input: default@store_sales +POSTHOOK: Output: hdfs://### HDFS PATH ### +Plan optimized by CBO. + +Vertex dependency in root stage +Map 1 <- Reducer 13 (BROADCAST_EDGE) +Reducer 10 <- Reducer 5 (SIMPLE_EDGE) +Reducer 11 <- Reducer 10 (SIMPLE_EDGE) +Reducer 13 <- Map 12 (CUSTOM_SIMPLE_EDGE) +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 12 (SIMPLE_EDGE) +Reducer 3 <- Map 14 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) +Reducer 4 <- Map 15 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) +Reducer 5 <- Reducer 4 (SIMPLE_EDGE) +Reducer 6 <- Reducer 5 (SIMPLE_EDGE) +Reducer 7 <- Reducer 6 (SIMPLE_EDGE), Reducer 9 (ONE_TO_ONE_EDGE) +Reducer 8 <- Reducer 7 (SIMPLE_EDGE) +Reducer 9 <- Reducer 11 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 8 vectorized + File Output Operator [FS_321] + Limit [LIM_320] (rows=100 width=658) + Number of rows:100 + Select Operator [SEL_319] (rows=241454 width=658) + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"] + <-Reducer 7 [SIMPLE_EDGE] + SHUFFLE [RS_110] + Select Operator [SEL_109] (rows=241454 width=658) + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] + Merge Join Operator [MERGEJOIN_278] (rows=241454 width=546) + Conds:RS_106._col6, _col7, _col8, _col9, _col14=RS_306._col0, _col1, _col2, _col3, _col5(Inner),Output:["_col4","_col6","_col10","_col11","_col12","_col13","_col19"] + <-Reducer 6 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_306] + PartitionCols:_col0, _col1, _col2, _col3, _col5 + Select Operator [SEL_304] (rows=162257387 width=485) + Output:["_col0","_col1","_col2","_col3","_col4","_col5"] + Filter Operator [FIL_302] (rows=162257387 width=489) + predicate:rank_window_0 is not null + PTF Operator [PTF_300] (rows=162257387 width=489) + Function definitions:[{},{"name:":"windowingtablefunction","order by:":"_col2 ASC NULLS LAST, _col3 ASC NULLS LAST","partition by:":"_col1, _col0, _col4, _col5"}] + Select Operator [SEL_299] (rows=162257387 width=489) + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"] + <-Reducer 5 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_297] + PartitionCols:_col1, _col0, _col4, _col5 + Group By Operator [GBY_296] (rows=162257387 width=489) + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4, KEY._col5 + <-Reducer 4 [SIMPLE_EDGE] + SHUFFLE [RS_93] + PartitionCols:_col0, _col1, _col2, _col3, _col4, _col5 + Group By Operator [GBY_92] (rows=162257387 width=489) + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"],aggregations:["sum(_col3)"],keys:_col8, _col9, _col5, _col6, _col11, _col12 + Merge Join Operator [MERGEJOIN_276] (rows=162257387 width=472) + Conds:RS_88._col2=RS_295._col0(Inner),Output:["_col3","_col5","_col6","_col8","_col9","_col11","_col12"] + <-Map 15 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_295] + PartitionCols:_col0 + Select Operator [SEL_294] (rows=1704 width=183) + Output:["_col0","_col1","_col2"] + Filter Operator [FIL_293] (rows=1704 width=183) + predicate:(s_company_name is not null and s_store_name is not null) + TableScan [TS_79] (rows=1704 width=183) + default@store,store,Tbl:COMPLETE,Col:COMPLETE,Output:["s_store_sk","s_store_name","s_company_name"] + <-Reducer 3 [SIMPLE_EDGE] + SHUFFLE [RS_88] + PartitionCols:_col2 + Merge Join Operator [MERGEJOIN_275] (rows=162257387 width=297) + Conds:RS_85._col1=RS_292._col0(Inner),Output:["_col2","_col3","_col5","_col6","_col8","_col9"] + <-Map 14 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_292] + PartitionCols:_col0 + Select Operator [SEL_291] (rows=462000 width=194) + Output:["_col0","_col1","_col2"] + Filter Operator [FIL_290] (rows=462000 width=194) + predicate:(i_brand is not null and i_category is not null) + TableScan [TS_76] (rows=462000 width=194) + default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_brand","i_category"] + <-Reducer 2 [SIMPLE_EDGE] + SHUFFLE [RS_85] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_274] (rows=162257387 width=111) + Conds:RS_289._col0=RS_281._col0(Inner),Output:["_col1","_col2","_col3","_col5","_col6"] + <-Map 12 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_281] + PartitionCols:_col0 + Select Operator [SEL_280] (rows=564 width=12) + Output:["_col0","_col1","_col2"] + Filter Operator [FIL_279] (rows=564 width=12) + predicate:(((d_year = 2000) or (struct(d_year,d_moy)) IN (const struct(1999,12), const struct(2001,1))) and (d_year) IN (2000, 1999, 2001)) + TableScan [TS_73] (rows=73049 width=12) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year","d_moy"] + <-Map 1 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_289] + PartitionCols:_col0 + Select Operator [SEL_288] (rows=525329897 width=118) + Output:["_col0","_col1","_col2","_col3"] + Filter Operator [FIL_287] (rows=525329897 width=118) + predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_83_date_dim_d_date_sk_min) AND DynamicValue(RS_83_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_83_date_dim_d_date_sk_bloom_filter))) and ss_sold_date_sk is not null and ss_store_sk is not null) + TableScan [TS_70] (rows=575995635 width=118) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_item_sk","ss_store_sk","ss_sales_price"] + <-Reducer 13 [BROADCAST_EDGE] vectorized + BROADCAST [RS_286] + Group By Operator [GBY_285] (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_284] + Group By Operator [GBY_283] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_282] (rows=564 width=4) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_280] + <-Reducer 9 [ONE_TO_ONE_EDGE] + FORWARD [RS_106] + PartitionCols:_col6, _col7, _col8, _col9, _col14 + Merge Join Operator [MERGEJOIN_277] (rows=241454 width=717) + Conds:RS_307._col0, _col1, _col2, _col3, _col5=RS_318._col0, _col1, _col2, _col3, _col8(Inner),Output:["_col4","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14"] + <-Reducer 6 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_307] + PartitionCols:_col0, _col1, _col2, _col3, _col5 + Select Operator [SEL_305] (rows=162257387 width=485) + Output:["_col0","_col1","_col2","_col3","_col4","_col5"] + Filter Operator [FIL_303] (rows=162257387 width=489) + predicate:rank_window_0 is not null + PTF Operator [PTF_301] (rows=162257387 width=489) + Function definitions:[{},{"name:":"windowingtablefunction","order by:":"_col2 ASC NULLS LAST, _col3 ASC NULLS LAST","partition by:":"_col1, _col0, _col4, _col5"}] + Please refer to the previous Select Operator [SEL_299] + <-Reducer 11 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_318] + PartitionCols:_col0, _col1, _col2, _col3, _col8 + Select Operator [SEL_317] (rows=241454 width=605) + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"] + Filter Operator [FIL_316] (rows=241454 width=605) + predicate:CASE WHEN ((_col0 > 0)) THEN (((abs((_col7 - _col0)) / _col0) > 0.1)) ELSE (null) END + Select Operator [SEL_315] (rows=482909 width=601) + Output:["rank_window_1","_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] + Filter Operator [FIL_314] (rows=482909 width=601) + predicate:((_col0 > 0) and (_col3 = 2000) and rank_window_1 is not null) + PTF Operator [PTF_313] (rows=162257387 width=601) + Function definitions:[{},{"name:":"windowingtablefunction","order by:":"_col3 ASC NULLS LAST, _col4 ASC NULLS LAST","partition by:":"_col2, _col1, _col5, _col6"}] + Select Operator [SEL_312] (rows=162257387 width=601) + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] + <-Reducer 10 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_311] + PartitionCols:_col1, _col0, _col4, _col5 + Select Operator [SEL_310] (rows=162257387 width=489) + Output:["avg_window_0","_col0","_col1","_col2","_col3","_col4","_col5","_col6"] + PTF Operator [PTF_309] (rows=162257387 width=489) + Function definitions:[{},{"name:":"windowingtablefunction","order by:":"_col1 ASC NULLS FIRST, _col0 ASC NULLS FIRST, _col4 ASC NULLS FIRST, _col5 ASC NULLS FIRST, _col2 ASC NULLS FIRST","partition by:":"_col1, _col0, _col4, _col5, _col2"}] + Select Operator [SEL_308] (rows=162257387 width=489) + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"] + <-Reducer 5 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_298] + PartitionCols:_col1, _col0, _col4, _col5, _col2 + Please refer to the previous Group By Operator [GBY_296] + http://git-wip-us.apache.org/repos/asf/hive/blob/b8299551/ql/src/test/results/clientpositive/perf/tez/constraints/query48.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/query48.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/query48.q.out new file mode 100644 index 0000000..b84dfce --- /dev/null +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/query48.q.out @@ -0,0 +1,252 @@ +PREHOOK: query: explain +select sum (ss_quantity) + from store_sales, store, customer_demographics, customer_address, date_dim + where s_store_sk = ss_store_sk + and ss_sold_date_sk = d_date_sk and d_year = 1998 + and + ( + ( + cd_demo_sk = ss_cdemo_sk + and + cd_marital_status = 'M' + and + cd_education_status = '4 yr Degree' + and + ss_sales_price between 100.00 and 150.00 + ) + or + ( + cd_demo_sk = ss_cdemo_sk + and + cd_marital_status = 'M' + and + cd_education_status = '4 yr Degree' + and + ss_sales_price between 50.00 and 100.00 + ) + or + ( + cd_demo_sk = ss_cdemo_sk + and + cd_marital_status = 'M' + and + cd_education_status = '4 yr Degree' + and + ss_sales_price between 150.00 and 200.00 + ) + ) + and + ( + ( + ss_addr_sk = ca_address_sk + and + ca_country = 'United States' + and + ca_state in ('KY', 'GA', 'NM') + and ss_net_profit between 0 and 2000 + ) + or + (ss_addr_sk = ca_address_sk + and + ca_country = 'United States' + and + ca_state in ('MT', 'OR', 'IN') + and ss_net_profit between 150 and 3000 + ) + or + (ss_addr_sk = ca_address_sk + and + ca_country = 'United States' + and + ca_state in ('WI', 'MO', 'WV') + and ss_net_profit between 50 and 25000 + ) + ) +PREHOOK: type: QUERY +PREHOOK: Input: default@customer_address +PREHOOK: Input: default@customer_demographics +PREHOOK: Input: default@date_dim +PREHOOK: Input: default@store +PREHOOK: Input: default@store_sales +PREHOOK: Output: hdfs://### HDFS PATH ### +POSTHOOK: query: explain +select sum (ss_quantity) + from store_sales, store, customer_demographics, customer_address, date_dim + where s_store_sk = ss_store_sk + and ss_sold_date_sk = d_date_sk and d_year = 1998 + and + ( + ( + cd_demo_sk = ss_cdemo_sk + and + cd_marital_status = 'M' + and + cd_education_status = '4 yr Degree' + and + ss_sales_price between 100.00 and 150.00 + ) + or + ( + cd_demo_sk = ss_cdemo_sk + and + cd_marital_status = 'M' + and + cd_education_status = '4 yr Degree' + and + ss_sales_price between 50.00 and 100.00 + ) + or + ( + cd_demo_sk = ss_cdemo_sk + and + cd_marital_status = 'M' + and + cd_education_status = '4 yr Degree' + and + ss_sales_price between 150.00 and 200.00 + ) + ) + and + ( + ( + ss_addr_sk = ca_address_sk + and + ca_country = 'United States' + and + ca_state in ('KY', 'GA', 'NM') + and ss_net_profit between 0 and 2000 + ) + or + (ss_addr_sk = ca_address_sk + and + ca_country = 'United States' + and + ca_state in ('MT', 'OR', 'IN') + and ss_net_profit between 150 and 3000 + ) + or + (ss_addr_sk = ca_address_sk + and + ca_country = 'United States' + and + ca_state in ('WI', 'MO', 'WV') + and ss_net_profit between 50 and 25000 + ) + ) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@customer_address +POSTHOOK: Input: default@customer_demographics +POSTHOOK: Input: default@date_dim +POSTHOOK: Input: default@store +POSTHOOK: Input: default@store_sales +POSTHOOK: Output: hdfs://### HDFS PATH ### +Plan optimized by CBO. + +Vertex dependency in root stage +Map 7 <- Reducer 11 (BROADCAST_EDGE), Reducer 6 (BROADCAST_EDGE), Reducer 9 (BROADCAST_EDGE) +Reducer 11 <- Map 10 (CUSTOM_SIMPLE_EDGE) +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 7 (SIMPLE_EDGE) +Reducer 3 <- Map 8 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) +Reducer 4 <- Map 10 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) +Reducer 5 <- Reducer 4 (CUSTOM_SIMPLE_EDGE) +Reducer 6 <- Map 1 (CUSTOM_SIMPLE_EDGE) +Reducer 9 <- Map 8 (CUSTOM_SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 5 vectorized + File Output Operator [FS_102] + Group By Operator [GBY_101] (rows=1 width=8) + Output:["_col0"],aggregations:["sum(VALUE._col0)"] + <-Reducer 4 [CUSTOM_SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_24] + Group By Operator [GBY_23] (rows=1 width=8) + Output:["_col0"],aggregations:["sum(_col4)"] + Select Operator [SEL_22] (rows=20247 width=24) + Output:["_col4"] + Filter Operator [FIL_21] (rows=20247 width=24) + predicate:((_col10 and _col5) or (_col11 and _col6) or (_col12 and _col7)) + Merge Join Operator [MERGEJOIN_73] (rows=26999 width=24) + Conds:RS_18._col3=RS_92._col0(Inner),Output:["_col4","_col5","_col6","_col7","_col10","_col11","_col12"] + <-Map 10 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_92] + PartitionCols:_col0 + Select Operator [SEL_91] (rows=3529412 width=16) + Output:["_col0","_col1","_col2","_col3"] + Filter Operator [FIL_90] (rows=3529412 width=187) + predicate:((ca_country = 'United States') and (ca_state) IN ('KY', 'GA', 'NM', 'MT', 'OR', 'IN', 'WI', 'MO', 'WV')) + TableScan [TS_9] (rows=40000000 width=187) + default@customer_address,customer_address,Tbl:COMPLETE,Col:COMPLETE,Output:["ca_address_sk","ca_state","ca_country"] + <-Reducer 3 [SIMPLE_EDGE] + SHUFFLE [RS_18] + PartitionCols:_col3 + Merge Join Operator [MERGEJOIN_72] (rows=305980 width=12) + Conds:RS_15._col1=RS_84._col0(Inner),Output:["_col3","_col4","_col5","_col6","_col7"] + <-Map 8 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_84] + PartitionCols:_col0 + Select Operator [SEL_83] (rows=652 width=4) + Output:["_col0"] + Filter Operator [FIL_82] (rows=652 width=8) + predicate:(d_year = 1998) + TableScan [TS_6] (rows=73049 width=8) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year"] + <-Reducer 2 [SIMPLE_EDGE] + SHUFFLE [RS_15] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_71] (rows=856943 width=12) + Conds:RS_76._col0=RS_100._col1(Inner),Output:["_col1","_col3","_col4","_col5","_col6","_col7"] + <-Map 1 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_76] + PartitionCols:_col0 + Select Operator [SEL_75] (rows=29552 width=4) + Output:["_col0"] + Filter Operator [FIL_74] (rows=29552 width=183) + predicate:((cd_education_status = '4 yr Degree') and (cd_marital_status = 'M')) + TableScan [TS_0] (rows=1861800 width=183) + default@customer_demographics,customer_demographics,Tbl:COMPLETE,Col:COMPLETE,Output:["cd_demo_sk","cd_marital_status","cd_education_status"] + <-Map 7 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_100] + PartitionCols:_col1 + Select Operator [SEL_99] (rows=53235296 width=27) + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"] + Filter Operator [FIL_98] (rows=53235296 width=233) + predicate:((ss_addr_sk BETWEEN DynamicValue(RS_19_customer_address_ca_address_sk_min) AND DynamicValue(RS_19_customer_address_ca_address_sk_max) and in_bloom_filter(ss_addr_sk, DynamicValue(RS_19_customer_address_ca_address_sk_bloom_filter))) and (ss_cdemo_sk BETWEEN DynamicValue(RS_12_customer_demographics_cd_demo_sk_min) AND DynamicValue(RS_12_customer_demographics_cd_demo_sk_max) and in_bloom_filter(ss_cdemo_sk, DynamicValue(RS_12_customer_demographics_cd_demo_sk_bloom_filter))) and (ss_net_profit BETWEEN 0 AND 2000 or ss_net_profit BETWEEN 150 AND 3000 or ss_net_profit BETWEEN 50 AND 25000) and (ss_sales_price BETWEEN 100 AND 150 or ss_sales_price BETWEEN 50 AND 100 or ss_sales_price BETWEEN 150 AND 200) and (ss_sold_date_sk BETWEEN DynamicValue(RS_16_date_dim_d_date_sk_min) AND DynamicValue(RS_16_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_16_date_dim_d_date_sk_bloom_filter))) and ss_addr_sk is not null and ss_c demo_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null) + TableScan [TS_3] (rows=575995635 width=233) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_cdemo_sk","ss_addr_sk","ss_store_sk","ss_quantity","ss_sales_price","ss_net_profit"] + <-Reducer 11 [BROADCAST_EDGE] vectorized + BROADCAST [RS_97] + Group By Operator [GBY_96] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=3529412)"] + <-Map 10 [CUSTOM_SIMPLE_EDGE] vectorized + SHUFFLE [RS_95] + Group By Operator [GBY_94] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=3529412)"] + Select Operator [SEL_93] (rows=3529412 width=4) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_91] + <-Reducer 6 [BROADCAST_EDGE] vectorized + BROADCAST [RS_81] + Group By Operator [GBY_80] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 1 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_79] + Group By Operator [GBY_78] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_77] (rows=29552 width=4) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_75] + <-Reducer 9 [BROADCAST_EDGE] vectorized + BROADCAST [RS_89] + Group By Operator [GBY_88] (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_87] + Group By Operator [GBY_86] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_85] (rows=652 width=4) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_83] +
