http://git-wip-us.apache.org/repos/asf/hive/blob/851c8aba/ql/src/test/results/clientpositive/perf/tez/query29.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/tez/query29.q.out b/ql/src/test/results/clientpositive/perf/tez/query29.q.out index 791ddb6..9bfcdfa 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query29.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query29.q.out @@ -117,200 +117,202 @@ Stage-0 limit:100 Stage-1 Reducer 5 vectorized - File Output Operator [FS_259] - Limit [LIM_258] (rows=100 width=88) + File Output Operator [FS_260] + Limit [LIM_259] (rows=100 width=88) Number of rows:100 - Select Operator [SEL_257] (rows=463823414 width=88) + Select Operator [SEL_258] (rows=463823414 width=88) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"] <-Reducer 4 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_256] - Group By Operator [GBY_255] (rows=463823414 width=88) + SHUFFLE [RS_257] + Group By Operator [GBY_256] (rows=463823414 width=88) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3 <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_49] PartitionCols:_col0, _col1, _col2, _col3 Group By Operator [GBY_48] (rows=927646829 width=88) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"],aggregations:["sum(_col14)","sum(_col22)","sum(_col3)"],keys:_col7, _col8, _col27, _col28 - Merge Join Operator [MERGEJOIN_204] (rows=927646829 width=88) - Conds:RS_44._col1, _col2=RS_45._col14, _col13(Inner),Output:["_col3","_col7","_col8","_col14","_col22","_col27","_col28"] - <-Reducer 12 [SIMPLE_EDGE] - SHUFFLE [RS_45] - PartitionCols:_col14, _col13 - Select Operator [SEL_40] (rows=843315281 width=88) - Output:["_col1","_col2","_col8","_col13","_col14","_col16","_col21","_col22"] - Merge Join Operator [MERGEJOIN_203] (rows=843315281 width=88) - Conds:RS_37._col3=RS_246._col0(Inner),Output:["_col5","_col10","_col11","_col13","_col18","_col19","_col21","_col22"] - <-Map 22 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_246] + Top N Key Operator [TNK_93] (rows=927646829 width=88) + keys:_col7, _col8, _col27, _col28,sort order:++++,top n:100 + Merge Join Operator [MERGEJOIN_205] (rows=927646829 width=88) + Conds:RS_44._col1, _col2=RS_45._col14, _col13(Inner),Output:["_col3","_col7","_col8","_col14","_col22","_col27","_col28"] + <-Reducer 12 [SIMPLE_EDGE] + SHUFFLE [RS_45] + PartitionCols:_col14, _col13 + Select Operator [SEL_40] (rows=843315281 width=88) + Output:["_col1","_col2","_col8","_col13","_col14","_col16","_col21","_col22"] + Merge Join Operator [MERGEJOIN_204] (rows=843315281 width=88) + Conds:RS_37._col3=RS_247._col0(Inner),Output:["_col5","_col10","_col11","_col13","_col18","_col19","_col21","_col22"] + <-Map 22 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_247] + PartitionCols:_col0 + Select Operator [SEL_246] (rows=1704 width=1910) + Output:["_col0","_col1","_col2"] + Filter Operator [FIL_245] (rows=1704 width=1910) + predicate:s_store_sk is not null + TableScan [TS_25] (rows=1704 width=1910) + default@store,store,Tbl:COMPLETE,Col:NONE,Output:["s_store_sk","s_store_id","s_store_name"] + <-Reducer 11 [SIMPLE_EDGE] + SHUFFLE [RS_37] + PartitionCols:_col3 + Merge Join Operator [MERGEJOIN_203] (rows=766650239 width=88) + Conds:RS_34._col1=RS_239._col0(Inner),Output:["_col3","_col5","_col10","_col11","_col13","_col18","_col19"] + <-Map 20 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_239] + PartitionCols:_col0 + Select Operator [SEL_238] (rows=462000 width=1436) + Output:["_col0","_col1","_col2"] + Filter Operator [FIL_237] (rows=462000 width=1436) + predicate:i_item_sk is not null + TableScan [TS_22] (rows=462000 width=1436) + default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_item_id","i_item_desc"] + <-Reducer 10 [SIMPLE_EDGE] + SHUFFLE [RS_34] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_202] (rows=696954748 width=88) + Conds:RS_31._col1, _col2, _col4=RS_32._col1, _col2, _col3(Inner),Output:["_col1","_col3","_col5","_col10","_col11","_col13"] + <-Reducer 15 [SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_32] + PartitionCols:_col1, _col2, _col3 + Merge Join Operator [MERGEJOIN_201] (rows=63350266 width=77) + Conds:RS_230._col0=RS_223._col0(Inner),Output:["_col1","_col2","_col3","_col4"] + <-Map 13 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_223] + PartitionCols:_col0 + Select Operator [SEL_220] (rows=4058 width=1119) + Output:["_col0"] + Filter Operator [FIL_218] (rows=4058 width=1119) + predicate:((d_year = 1999) and d_date_sk is not null and d_moy BETWEEN 4 AND 7) + TableScan [TS_9] (rows=73049 width=1119) + default@date_dim,d1,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year","d_moy"] + <-Map 19 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_230] + PartitionCols:_col0 + Select Operator [SEL_229] (rows=57591150 width=77) + Output:["_col0","_col1","_col2","_col3","_col4"] + Filter Operator [FIL_228] (rows=57591150 width=77) + predicate:(sr_customer_sk is not null and sr_item_sk is not null and sr_returned_date_sk is not null and sr_ticket_number is not null) + TableScan [TS_12] (rows=57591150 width=77) + default@store_returns,store_returns,Tbl:COMPLETE,Col:NONE,Output:["sr_returned_date_sk","sr_item_sk","sr_customer_sk","sr_ticket_number","sr_return_quantity"] + <-Reducer 9 [SIMPLE_EDGE] + SHUFFLE [RS_31] + PartitionCols:_col1, _col2, _col4 + Merge Join Operator [MERGEJOIN_200] (rows=633595212 width=88) + Conds:RS_255._col0=RS_221._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5"] + <-Map 13 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_221] + PartitionCols:_col0 + Select Operator [SEL_219] (rows=18262 width=1119) + Output:["_col0"] + Filter Operator [FIL_217] (rows=18262 width=1119) + predicate:((d_moy = 4) and (d_year = 1999) and d_date_sk is not null) + Please refer to the previous TableScan [TS_9] + <-Map 8 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_255] + PartitionCols:_col0 + Select Operator [SEL_254] (rows=575995635 width=88) + Output:["_col0","_col1","_col2","_col3","_col4","_col5"] + Filter Operator [FIL_253] (rows=575995635 width=88) + predicate:((ss_customer_sk BETWEEN DynamicValue(RS_32_store_returns_sr_customer_sk_min) AND DynamicValue(RS_32_store_returns_sr_customer_sk_max) and in_bloom_filter(ss_customer_sk, DynamicValue(RS_32_store_returns_sr_customer_sk_bloom_filter))) and (ss_item_sk BETWEEN DynamicValue(RS_32_store_returns_sr_item_sk_min) AND DynamicValue(RS_32_store_returns_sr_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_32_store_returns_sr_item_sk_bloom_filter))) and (ss_item_sk BETWEEN DynamicValue(RS_35_item_i_item_sk_min) AND DynamicValue(RS_35_item_i_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_35_item_i_item_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_29_d1_d_date_sk_min) AND DynamicValue(RS_29_d1_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_29_d1_d_date_sk_bloom_filter))) and (ss_store_sk BETWEEN DynamicValue(RS_38_store_s_store_sk_min) AND DynamicValue(RS_38_store_s_store_sk_ max) and in_bloom_filter(ss_store_sk, DynamicValue(RS_38_store_s_store_sk_bloom_filter))) and (ss_ticket_number BETWEEN DynamicValue(RS_32_store_returns_sr_ticket_number_min) AND DynamicValue(RS_32_store_returns_sr_ticket_number_max) and in_bloom_filter(ss_ticket_number, DynamicValue(RS_32_store_returns_sr_ticket_number_bloom_filter))) and ss_customer_sk is not null and ss_item_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null and ss_ticket_number is not null) + TableScan [TS_6] (rows=575995635 width=88) + default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_item_sk","ss_customer_sk","ss_store_sk","ss_ticket_number","ss_quantity"] + <-Reducer 14 [BROADCAST_EDGE] vectorized + BROADCAST [RS_227] + Group By Operator [GBY_226] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 13 [CUSTOM_SIMPLE_EDGE] vectorized + SHUFFLE [RS_225] + Group By Operator [GBY_224] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_222] (rows=18262 width=1119) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_219] + <-Reducer 16 [BROADCAST_EDGE] vectorized + BROADCAST [RS_232] + Group By Operator [GBY_231] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=63350264)"] + <-Reducer 15 [CUSTOM_SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_121] + Group By Operator [GBY_120] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=63350264)"] + Select Operator [SEL_119] (rows=63350266 width=77) + Output:["_col0"] + Please refer to the previous Merge Join Operator [MERGEJOIN_201] + <-Reducer 17 [BROADCAST_EDGE] vectorized + BROADCAST [RS_234] + Group By Operator [GBY_233] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=63350264)"] + <-Reducer 15 [CUSTOM_SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_126] + Group By Operator [GBY_125] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=63350264)"] + Select Operator [SEL_124] (rows=63350266 width=77) + Output:["_col0"] + Please refer to the previous Merge Join Operator [MERGEJOIN_201] + <-Reducer 18 [BROADCAST_EDGE] vectorized + BROADCAST [RS_236] + Group By Operator [GBY_235] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=63350264)"] + <-Reducer 15 [CUSTOM_SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_131] + Group By Operator [GBY_130] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=63350264)"] + Select Operator [SEL_129] (rows=63350266 width=77) + Output:["_col0"] + Please refer to the previous Merge Join Operator [MERGEJOIN_201] + <-Reducer 21 [BROADCAST_EDGE] vectorized + BROADCAST [RS_244] + Group By Operator [GBY_243] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 20 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_242] + Group By Operator [GBY_241] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_240] (rows=462000 width=1436) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_238] + <-Reducer 23 [BROADCAST_EDGE] vectorized + BROADCAST [RS_252] + Group By Operator [GBY_251] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 22 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_250] + Group By Operator [GBY_249] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_248] (rows=1704 width=1910) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_246] + <-Reducer 2 [SIMPLE_EDGE] + SHUFFLE [RS_44] + PartitionCols:_col1, _col2 + Merge Join Operator [MERGEJOIN_199] (rows=316788826 width=135) + Conds:RS_216._col0=RS_208._col0(Inner),Output:["_col1","_col2","_col3"] + <-Map 6 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_208] PartitionCols:_col0 - Select Operator [SEL_245] (rows=1704 width=1910) - Output:["_col0","_col1","_col2"] - Filter Operator [FIL_244] (rows=1704 width=1910) - predicate:s_store_sk is not null - TableScan [TS_25] (rows=1704 width=1910) - default@store,store,Tbl:COMPLETE,Col:NONE,Output:["s_store_sk","s_store_id","s_store_name"] - <-Reducer 11 [SIMPLE_EDGE] - SHUFFLE [RS_37] - PartitionCols:_col3 - Merge Join Operator [MERGEJOIN_202] (rows=766650239 width=88) - Conds:RS_34._col1=RS_238._col0(Inner),Output:["_col3","_col5","_col10","_col11","_col13","_col18","_col19"] - <-Map 20 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_238] - PartitionCols:_col0 - Select Operator [SEL_237] (rows=462000 width=1436) - Output:["_col0","_col1","_col2"] - Filter Operator [FIL_236] (rows=462000 width=1436) - predicate:i_item_sk is not null - TableScan [TS_22] (rows=462000 width=1436) - default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_item_id","i_item_desc"] - <-Reducer 10 [SIMPLE_EDGE] - SHUFFLE [RS_34] - PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_201] (rows=696954748 width=88) - Conds:RS_31._col1, _col2, _col4=RS_32._col1, _col2, _col3(Inner),Output:["_col1","_col3","_col5","_col10","_col11","_col13"] - <-Reducer 15 [SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_32] - PartitionCols:_col1, _col2, _col3 - Merge Join Operator [MERGEJOIN_200] (rows=63350266 width=77) - Conds:RS_229._col0=RS_222._col0(Inner),Output:["_col1","_col2","_col3","_col4"] - <-Map 13 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_222] - PartitionCols:_col0 - Select Operator [SEL_219] (rows=4058 width=1119) - Output:["_col0"] - Filter Operator [FIL_217] (rows=4058 width=1119) - predicate:((d_year = 1999) and d_date_sk is not null and d_moy BETWEEN 4 AND 7) - TableScan [TS_9] (rows=73049 width=1119) - default@date_dim,d1,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year","d_moy"] - <-Map 19 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_229] - PartitionCols:_col0 - Select Operator [SEL_228] (rows=57591150 width=77) - Output:["_col0","_col1","_col2","_col3","_col4"] - Filter Operator [FIL_227] (rows=57591150 width=77) - predicate:(sr_customer_sk is not null and sr_item_sk is not null and sr_returned_date_sk is not null and sr_ticket_number is not null) - TableScan [TS_12] (rows=57591150 width=77) - default@store_returns,store_returns,Tbl:COMPLETE,Col:NONE,Output:["sr_returned_date_sk","sr_item_sk","sr_customer_sk","sr_ticket_number","sr_return_quantity"] - <-Reducer 9 [SIMPLE_EDGE] - SHUFFLE [RS_31] - PartitionCols:_col1, _col2, _col4 - Merge Join Operator [MERGEJOIN_199] (rows=633595212 width=88) - Conds:RS_254._col0=RS_220._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5"] - <-Map 13 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_220] - PartitionCols:_col0 - Select Operator [SEL_218] (rows=18262 width=1119) - Output:["_col0"] - Filter Operator [FIL_216] (rows=18262 width=1119) - predicate:((d_moy = 4) and (d_year = 1999) and d_date_sk is not null) - Please refer to the previous TableScan [TS_9] - <-Map 8 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_254] - PartitionCols:_col0 - Select Operator [SEL_253] (rows=575995635 width=88) - Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - Filter Operator [FIL_252] (rows=575995635 width=88) - predicate:((ss_customer_sk BETWEEN DynamicValue(RS_32_store_returns_sr_customer_sk_min) AND DynamicValue(RS_32_store_returns_sr_customer_sk_max) and in_bloom_filter(ss_customer_sk, DynamicValue(RS_32_store_returns_sr_customer_sk_bloom_filter))) and (ss_item_sk BETWEEN DynamicValue(RS_32_store_returns_sr_item_sk_min) AND DynamicValue(RS_32_store_returns_sr_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_32_store_returns_sr_item_sk_bloom_filter))) and (ss_item_sk BETWEEN DynamicValue(RS_35_item_i_item_sk_min) AND DynamicValue(RS_35_item_i_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_35_item_i_item_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_29_d1_d_date_sk_min) AND DynamicValue(RS_29_d1_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_29_d1_d_date_sk_bloom_filter))) and (ss_store_sk BETWEEN DynamicValue(RS_38_store_s_store_sk_min) AND DynamicValue(RS_38_store_s_store_sk_ma x) and in_bloom_filter(ss_store_sk, DynamicValue(RS_38_store_s_store_sk_bloom_filter))) and (ss_ticket_number BETWEEN DynamicValue(RS_32_store_returns_sr_ticket_number_min) AND DynamicValue(RS_32_store_returns_sr_ticket_number_max) and in_bloom_filter(ss_ticket_number, DynamicValue(RS_32_store_returns_sr_ticket_number_bloom_filter))) and ss_customer_sk is not null and ss_item_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null and ss_ticket_number is not null) - TableScan [TS_6] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_item_sk","ss_customer_sk","ss_store_sk","ss_ticket_number","ss_quantity"] - <-Reducer 14 [BROADCAST_EDGE] vectorized - BROADCAST [RS_226] - Group By Operator [GBY_225] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 13 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_224] - Group By Operator [GBY_223] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_221] (rows=18262 width=1119) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_218] - <-Reducer 16 [BROADCAST_EDGE] vectorized - BROADCAST [RS_231] - Group By Operator [GBY_230] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=63350264)"] - <-Reducer 15 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_120] - Group By Operator [GBY_119] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=63350264)"] - Select Operator [SEL_118] (rows=63350266 width=77) - Output:["_col0"] - Please refer to the previous Merge Join Operator [MERGEJOIN_200] - <-Reducer 17 [BROADCAST_EDGE] vectorized - BROADCAST [RS_233] - Group By Operator [GBY_232] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=63350264)"] - <-Reducer 15 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_125] - Group By Operator [GBY_124] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=63350264)"] - Select Operator [SEL_123] (rows=63350266 width=77) - Output:["_col0"] - Please refer to the previous Merge Join Operator [MERGEJOIN_200] - <-Reducer 18 [BROADCAST_EDGE] vectorized - BROADCAST [RS_235] - Group By Operator [GBY_234] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=63350264)"] - <-Reducer 15 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_130] - Group By Operator [GBY_129] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=63350264)"] - Select Operator [SEL_128] (rows=63350266 width=77) - Output:["_col0"] - Please refer to the previous Merge Join Operator [MERGEJOIN_200] - <-Reducer 21 [BROADCAST_EDGE] vectorized - BROADCAST [RS_243] - Group By Operator [GBY_242] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 20 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_241] - Group By Operator [GBY_240] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_239] (rows=462000 width=1436) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_237] - <-Reducer 23 [BROADCAST_EDGE] vectorized - BROADCAST [RS_251] - Group By Operator [GBY_250] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 22 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_249] - Group By Operator [GBY_248] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_247] (rows=1704 width=1910) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_245] - <-Reducer 2 [SIMPLE_EDGE] - SHUFFLE [RS_44] - PartitionCols:_col1, _col2 - Merge Join Operator [MERGEJOIN_198] (rows=316788826 width=135) - Conds:RS_215._col0=RS_207._col0(Inner),Output:["_col1","_col2","_col3"] - <-Map 6 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_207] - PartitionCols:_col0 - Select Operator [SEL_206] (rows=36525 width=1119) - Output:["_col0"] - Filter Operator [FIL_205] (rows=36525 width=1119) - predicate:((d_year) IN (1999, 2000, 2001) and d_date_sk is not null) - TableScan [TS_3] (rows=73049 width=1119) - default@date_dim,d3,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"] - <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_215] - PartitionCols:_col0 - Select Operator [SEL_214] (rows=287989836 width=135) - Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_213] (rows=287989836 width=135) - predicate:((cs_sold_date_sk BETWEEN DynamicValue(RS_42_d3_d_date_sk_min) AND DynamicValue(RS_42_d3_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_42_d3_d_date_sk_bloom_filter))) and cs_bill_customer_sk is not null and cs_item_sk is not null and cs_sold_date_sk is not null) - TableScan [TS_0] (rows=287989836 width=135) - default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:NONE,Output:["cs_sold_date_sk","cs_bill_customer_sk","cs_item_sk","cs_quantity"] - <-Reducer 7 [BROADCAST_EDGE] vectorized - BROADCAST [RS_212] - Group By Operator [GBY_211] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 6 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_210] - Group By Operator [GBY_209] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_208] (rows=36525 width=1119) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_206] + Select Operator [SEL_207] (rows=36525 width=1119) + Output:["_col0"] + Filter Operator [FIL_206] (rows=36525 width=1119) + predicate:((d_year) IN (1999, 2000, 2001) and d_date_sk is not null) + TableScan [TS_3] (rows=73049 width=1119) + default@date_dim,d3,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"] + <-Map 1 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_216] + PartitionCols:_col0 + Select Operator [SEL_215] (rows=287989836 width=135) + Output:["_col0","_col1","_col2","_col3"] + Filter Operator [FIL_214] (rows=287989836 width=135) + predicate:((cs_sold_date_sk BETWEEN DynamicValue(RS_42_d3_d_date_sk_min) AND DynamicValue(RS_42_d3_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_42_d3_d_date_sk_bloom_filter))) and cs_bill_customer_sk is not null and cs_item_sk is not null and cs_sold_date_sk is not null) + TableScan [TS_0] (rows=287989836 width=135) + default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:NONE,Output:["cs_sold_date_sk","cs_bill_customer_sk","cs_item_sk","cs_quantity"] + <-Reducer 7 [BROADCAST_EDGE] vectorized + BROADCAST [RS_213] + Group By Operator [GBY_212] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 6 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_211] + Group By Operator [GBY_210] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_209] (rows=36525 width=1119) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_207]
http://git-wip-us.apache.org/repos/asf/hive/blob/851c8aba/ql/src/test/results/clientpositive/perf/tez/query35.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/tez/query35.q.out b/ql/src/test/results/clientpositive/perf/tez/query35.q.out index 4fe3856..4ad92c2 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query35.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query35.q.out @@ -136,188 +136,190 @@ Stage-0 limit:-1 Stage-1 Reducer 6 vectorized - File Output Operator [FS_225] - Limit [LIM_224] (rows=100 width=88) + File Output Operator [FS_226] + Limit [LIM_225] (rows=100 width=88) Number of rows:100 - Select Operator [SEL_223] (rows=1045432122 width=88) + Select Operator [SEL_224] (rows=1045432122 width=88) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16"] <-Reducer 5 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_222] - Select Operator [SEL_221] (rows=1045432122 width=88) + SHUFFLE [RS_223] + Select Operator [SEL_222] (rows=1045432122 width=88) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col9","_col10","_col11","_col12","_col14","_col15","_col16","_col17"] - Group By Operator [GBY_220] (rows=1045432122 width=88) + Group By Operator [GBY_221] (rows=1045432122 width=88) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15"],aggregations:["count(VALUE._col0)","sum(VALUE._col1)","count(VALUE._col2)","max(VALUE._col3)","sum(VALUE._col4)","count(VALUE._col5)","max(VALUE._col6)","sum(VALUE._col7)","count(VALUE._col8)","max(VALUE._col9)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4, KEY._col5 <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_63] PartitionCols:_col0, _col1, _col2, _col3, _col4, _col5 Group By Operator [GBY_62] (rows=2090864244 width=88) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15"],aggregations:["count()","sum(_col8)","count(_col8)","max(_col8)","sum(_col9)","count(_col9)","max(_col9)","sum(_col10)","count(_col10)","max(_col10)"],keys:_col4, _col6, _col7, _col8, _col9, _col10 - Select Operator [SEL_61] (rows=2090864244 width=88) - Output:["_col4","_col6","_col7","_col8","_col9","_col10"] - Filter Operator [FIL_60] (rows=2090864244 width=88) - predicate:(_col12 is not null or _col14 is not null) - Merge Join Operator [MERGEJOIN_173] (rows=2090864244 width=88) - Conds:RS_55._col0=RS_56._col0(Left Semi),RS_55._col0=RS_211._col0(Left Outer),RS_55._col0=RS_219._col0(Left Outer),Output:["_col4","_col6","_col7","_col8","_col9","_col10","_col12","_col14"] - <-Reducer 3 [SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_55] - PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_169] (rows=96800003 width=860) - Conds:RS_50._col1=RS_182._col0(Inner),Output:["_col0","_col4","_col6","_col7","_col8","_col9","_col10"] - <-Map 9 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_182] - PartitionCols:_col0 - Select Operator [SEL_181] (rows=1861800 width=385) - Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - Filter Operator [FIL_180] (rows=1861800 width=385) - predicate:cd_demo_sk is not null - TableScan [TS_6] (rows=1861800 width=385) - default@customer_demographics,customer_demographics,Tbl:COMPLETE,Col:NONE,Output:["cd_demo_sk","cd_gender","cd_marital_status","cd_dep_count","cd_dep_employed_count","cd_dep_college_count"] - <-Reducer 2 [SIMPLE_EDGE] - SHUFFLE [RS_50] - PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_168] (rows=88000001 width=860) - Conds:RS_176._col2=RS_179._col0(Inner),Output:["_col0","_col1","_col4"] - <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_176] - PartitionCols:_col2 - Select Operator [SEL_175] (rows=80000000 width=860) - Output:["_col0","_col1","_col2"] - Filter Operator [FIL_174] (rows=80000000 width=860) - predicate:(c_current_addr_sk is not null and c_current_cdemo_sk is not null and c_customer_sk is not null) - TableScan [TS_0] (rows=80000000 width=860) - default@customer,c,Tbl:COMPLETE,Col:NONE,Output:["c_customer_sk","c_current_cdemo_sk","c_current_addr_sk"] - <-Map 8 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_179] - PartitionCols:_col0 - Select Operator [SEL_178] (rows=40000000 width=1014) - Output:["_col0","_col1"] - Filter Operator [FIL_177] (rows=40000000 width=1014) - predicate:ca_address_sk is not null - TableScan [TS_3] (rows=40000000 width=1014) - default@customer_address,ca,Tbl:COMPLETE,Col:NONE,Output:["ca_address_sk","ca_state"] - <-Reducer 11 [SIMPLE_EDGE] - SHUFFLE [RS_56] - PartitionCols:_col0 - Group By Operator [GBY_54] (rows=633595212 width=88) - Output:["_col0"],keys:_col0 - Select Operator [SEL_18] (rows=633595212 width=88) - Output:["_col0"] - Merge Join Operator [MERGEJOIN_170] (rows=633595212 width=88) - Conds:RS_203._col0=RS_185._col0(Inner),Output:["_col1"] - <-Map 12 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_185] + Top N Key Operator [TNK_104] (rows=2090864244 width=88) + keys:_col4, _col6, _col7, _col8, _col9, _col10,sort order:++++++,top n:100 + Select Operator [SEL_61] (rows=2090864244 width=88) + Output:["_col4","_col6","_col7","_col8","_col9","_col10"] + Filter Operator [FIL_60] (rows=2090864244 width=88) + predicate:(_col12 is not null or _col14 is not null) + Merge Join Operator [MERGEJOIN_174] (rows=2090864244 width=88) + Conds:RS_55._col0=RS_56._col0(Left Semi),RS_55._col0=RS_212._col0(Left Outer),RS_55._col0=RS_220._col0(Left Outer),Output:["_col4","_col6","_col7","_col8","_col9","_col10","_col12","_col14"] + <-Reducer 3 [SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_55] + PartitionCols:_col0 + Merge Join Operator [MERGEJOIN_170] (rows=96800003 width=860) + Conds:RS_50._col1=RS_183._col0(Inner),Output:["_col0","_col4","_col6","_col7","_col8","_col9","_col10"] + <-Map 9 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_183] + PartitionCols:_col0 + Select Operator [SEL_182] (rows=1861800 width=385) + Output:["_col0","_col1","_col2","_col3","_col4","_col5"] + Filter Operator [FIL_181] (rows=1861800 width=385) + predicate:cd_demo_sk is not null + TableScan [TS_6] (rows=1861800 width=385) + default@customer_demographics,customer_demographics,Tbl:COMPLETE,Col:NONE,Output:["cd_demo_sk","cd_gender","cd_marital_status","cd_dep_count","cd_dep_employed_count","cd_dep_college_count"] + <-Reducer 2 [SIMPLE_EDGE] + SHUFFLE [RS_50] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_169] (rows=88000001 width=860) + Conds:RS_177._col2=RS_180._col0(Inner),Output:["_col0","_col1","_col4"] + <-Map 1 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_177] + PartitionCols:_col2 + Select Operator [SEL_176] (rows=80000000 width=860) + Output:["_col0","_col1","_col2"] + Filter Operator [FIL_175] (rows=80000000 width=860) + predicate:(c_current_addr_sk is not null and c_current_cdemo_sk is not null and c_customer_sk is not null) + TableScan [TS_0] (rows=80000000 width=860) + default@customer,c,Tbl:COMPLETE,Col:NONE,Output:["c_customer_sk","c_current_cdemo_sk","c_current_addr_sk"] + <-Map 8 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_180] + PartitionCols:_col0 + Select Operator [SEL_179] (rows=40000000 width=1014) + Output:["_col0","_col1"] + Filter Operator [FIL_178] (rows=40000000 width=1014) + predicate:ca_address_sk is not null + TableScan [TS_3] (rows=40000000 width=1014) + default@customer_address,ca,Tbl:COMPLETE,Col:NONE,Output:["ca_address_sk","ca_state"] + <-Reducer 11 [SIMPLE_EDGE] + SHUFFLE [RS_56] + PartitionCols:_col0 + Group By Operator [GBY_54] (rows=633595212 width=88) + Output:["_col0"],keys:_col0 + Select Operator [SEL_18] (rows=633595212 width=88) + Output:["_col0"] + Merge Join Operator [MERGEJOIN_171] (rows=633595212 width=88) + Conds:RS_204._col0=RS_186._col0(Inner),Output:["_col1"] + <-Map 12 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_186] + PartitionCols:_col0 + Select Operator [SEL_185] (rows=12174 width=1119) + Output:["_col0"] + Filter Operator [FIL_184] (rows=12174 width=1119) + predicate:((d_qoy < 4) and (d_year = 1999) and d_date_sk is not null) + TableScan [TS_12] (rows=73049 width=1119) + default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year","d_qoy"] + <-Map 10 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_204] + PartitionCols:_col0 + Select Operator [SEL_203] (rows=575995635 width=88) + Output:["_col0","_col1"] + Filter Operator [FIL_202] (rows=575995635 width=88) + predicate:((ss_customer_sk BETWEEN DynamicValue(RS_55_c_c_customer_sk_min) AND DynamicValue(RS_55_c_c_customer_sk_max) and in_bloom_filter(ss_customer_sk, DynamicValue(RS_55_c_c_customer_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_16_date_dim_d_date_sk_min) AND DynamicValue(RS_16_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_16_date_dim_d_date_sk_bloom_filter))) and ss_customer_sk is not null and ss_sold_date_sk is not null) + TableScan [TS_9] (rows=575995635 width=88) + default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_customer_sk"] + <-Reducer 13 [BROADCAST_EDGE] vectorized + BROADCAST [RS_199] + Group By Operator [GBY_198] (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 + PARTITION_ONLY_SHUFFLE [RS_195] + Group By Operator [GBY_192] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_187] (rows=12174 width=1119) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_185] + <-Reducer 7 [BROADCAST_EDGE] vectorized + BROADCAST [RS_201] + Group By Operator [GBY_200] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=96800000)"] + <-Reducer 3 [CUSTOM_SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_137] + Group By Operator [GBY_136] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=96800000)"] + Select Operator [SEL_135] (rows=96800003 width=860) + Output:["_col0"] + Please refer to the previous Merge Join Operator [MERGEJOIN_170] + <-Reducer 15 [ONE_TO_ONE_EDGE] vectorized + FORWARD [RS_212] + PartitionCols:_col0 + Select Operator [SEL_211] (rows=79201469 width=135) + Output:["_col0","_col1"] + Group By Operator [GBY_210] (rows=79201469 width=135) + Output:["_col0"],keys:KEY._col0 + <-Reducer 14 [SIMPLE_EDGE] + SHUFFLE [RS_30] PartitionCols:_col0 - Select Operator [SEL_184] (rows=12174 width=1119) - Output:["_col0"] - Filter Operator [FIL_183] (rows=12174 width=1119) - predicate:((d_qoy < 4) and (d_year = 1999) and d_date_sk is not null) - TableScan [TS_12] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year","d_qoy"] - <-Map 10 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_203] + Group By Operator [GBY_29] (rows=158402938 width=135) + Output:["_col0"],keys:_col1 + Merge Join Operator [MERGEJOIN_172] (rows=158402938 width=135) + Conds:RS_209._col0=RS_188._col0(Inner),Output:["_col1"] + <-Map 12 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_188] + PartitionCols:_col0 + Please refer to the previous Select Operator [SEL_185] + <-Map 20 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_209] + PartitionCols:_col0 + Select Operator [SEL_208] (rows=144002668 width=135) + Output:["_col0","_col1"] + Filter Operator [FIL_207] (rows=144002668 width=135) + predicate:((ws_sold_date_sk BETWEEN DynamicValue(RS_26_date_dim_d_date_sk_min) AND DynamicValue(RS_26_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_26_date_dim_d_date_sk_bloom_filter))) and ws_bill_customer_sk is not null and ws_sold_date_sk is not null) + TableScan [TS_19] (rows=144002668 width=135) + default@web_sales,web_sales,Tbl:COMPLETE,Col:NONE,Output:["ws_sold_date_sk","ws_bill_customer_sk"] + <-Reducer 16 [BROADCAST_EDGE] vectorized + BROADCAST [RS_206] + Group By Operator [GBY_205] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 12 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_196] + Group By Operator [GBY_193] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_189] (rows=12174 width=1119) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_185] + <-Reducer 18 [ONE_TO_ONE_EDGE] vectorized + FORWARD [RS_220] + PartitionCols:_col0 + Select Operator [SEL_219] (rows=158394413 width=135) + Output:["_col0","_col1"] + Group By Operator [GBY_218] (rows=158394413 width=135) + Output:["_col0"],keys:KEY._col0 + <-Reducer 17 [SIMPLE_EDGE] + SHUFFLE [RS_44] PartitionCols:_col0 - Select Operator [SEL_202] (rows=575995635 width=88) - Output:["_col0","_col1"] - Filter Operator [FIL_201] (rows=575995635 width=88) - predicate:((ss_customer_sk BETWEEN DynamicValue(RS_55_c_c_customer_sk_min) AND DynamicValue(RS_55_c_c_customer_sk_max) and in_bloom_filter(ss_customer_sk, DynamicValue(RS_55_c_c_customer_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_16_date_dim_d_date_sk_min) AND DynamicValue(RS_16_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_16_date_dim_d_date_sk_bloom_filter))) and ss_customer_sk is not null and ss_sold_date_sk is not null) - TableScan [TS_9] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_customer_sk"] - <-Reducer 13 [BROADCAST_EDGE] vectorized - BROADCAST [RS_198] - Group By Operator [GBY_197] (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 - PARTITION_ONLY_SHUFFLE [RS_194] - Group By Operator [GBY_191] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_186] (rows=12174 width=1119) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_184] - <-Reducer 7 [BROADCAST_EDGE] vectorized - BROADCAST [RS_200] - Group By Operator [GBY_199] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=96800000)"] - <-Reducer 3 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_136] - Group By Operator [GBY_135] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=96800000)"] - Select Operator [SEL_134] (rows=96800003 width=860) - Output:["_col0"] - Please refer to the previous Merge Join Operator [MERGEJOIN_169] - <-Reducer 15 [ONE_TO_ONE_EDGE] vectorized - FORWARD [RS_211] - PartitionCols:_col0 - Select Operator [SEL_210] (rows=79201469 width=135) - Output:["_col0","_col1"] - Group By Operator [GBY_209] (rows=79201469 width=135) - Output:["_col0"],keys:KEY._col0 - <-Reducer 14 [SIMPLE_EDGE] - SHUFFLE [RS_30] - PartitionCols:_col0 - Group By Operator [GBY_29] (rows=158402938 width=135) - Output:["_col0"],keys:_col1 - Merge Join Operator [MERGEJOIN_171] (rows=158402938 width=135) - Conds:RS_208._col0=RS_187._col0(Inner),Output:["_col1"] - <-Map 12 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_187] - PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_184] - <-Map 20 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_208] - PartitionCols:_col0 - Select Operator [SEL_207] (rows=144002668 width=135) - Output:["_col0","_col1"] - Filter Operator [FIL_206] (rows=144002668 width=135) - predicate:((ws_sold_date_sk BETWEEN DynamicValue(RS_26_date_dim_d_date_sk_min) AND DynamicValue(RS_26_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_26_date_dim_d_date_sk_bloom_filter))) and ws_bill_customer_sk is not null and ws_sold_date_sk is not null) - TableScan [TS_19] (rows=144002668 width=135) - default@web_sales,web_sales,Tbl:COMPLETE,Col:NONE,Output:["ws_sold_date_sk","ws_bill_customer_sk"] - <-Reducer 16 [BROADCAST_EDGE] vectorized - BROADCAST [RS_205] - Group By Operator [GBY_204] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 12 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_195] - Group By Operator [GBY_192] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_188] (rows=12174 width=1119) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_184] - <-Reducer 18 [ONE_TO_ONE_EDGE] vectorized - FORWARD [RS_219] - PartitionCols:_col0 - Select Operator [SEL_218] (rows=158394413 width=135) - Output:["_col0","_col1"] - Group By Operator [GBY_217] (rows=158394413 width=135) - Output:["_col0"],keys:KEY._col0 - <-Reducer 17 [SIMPLE_EDGE] - SHUFFLE [RS_44] - PartitionCols:_col0 - Group By Operator [GBY_43] (rows=316788826 width=135) - Output:["_col0"],keys:_col1 - Merge Join Operator [MERGEJOIN_172] (rows=316788826 width=135) - Conds:RS_216._col0=RS_189._col0(Inner),Output:["_col1"] - <-Map 12 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_189] - PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_184] - <-Map 21 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_216] - PartitionCols:_col0 - Select Operator [SEL_215] (rows=287989836 width=135) - Output:["_col0","_col1"] - Filter Operator [FIL_214] (rows=287989836 width=135) - predicate:((cs_sold_date_sk BETWEEN DynamicValue(RS_40_date_dim_d_date_sk_min) AND DynamicValue(RS_40_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_40_date_dim_d_date_sk_bloom_filter))) and cs_ship_customer_sk is not null and cs_sold_date_sk is not null) - TableScan [TS_33] (rows=287989836 width=135) - default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:NONE,Output:["cs_sold_date_sk","cs_ship_customer_sk"] - <-Reducer 19 [BROADCAST_EDGE] vectorized - BROADCAST [RS_213] - Group By Operator [GBY_212] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 12 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_196] - Group By Operator [GBY_193] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_190] (rows=12174 width=1119) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_184] + Group By Operator [GBY_43] (rows=316788826 width=135) + Output:["_col0"],keys:_col1 + Merge Join Operator [MERGEJOIN_173] (rows=316788826 width=135) + Conds:RS_217._col0=RS_190._col0(Inner),Output:["_col1"] + <-Map 12 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_190] + PartitionCols:_col0 + Please refer to the previous Select Operator [SEL_185] + <-Map 21 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_217] + PartitionCols:_col0 + Select Operator [SEL_216] (rows=287989836 width=135) + Output:["_col0","_col1"] + Filter Operator [FIL_215] (rows=287989836 width=135) + predicate:((cs_sold_date_sk BETWEEN DynamicValue(RS_40_date_dim_d_date_sk_min) AND DynamicValue(RS_40_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_40_date_dim_d_date_sk_bloom_filter))) and cs_ship_customer_sk is not null and cs_sold_date_sk is not null) + TableScan [TS_33] (rows=287989836 width=135) + default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:NONE,Output:["cs_sold_date_sk","cs_ship_customer_sk"] + <-Reducer 19 [BROADCAST_EDGE] vectorized + BROADCAST [RS_214] + Group By Operator [GBY_213] (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 + PARTITION_ONLY_SHUFFLE [RS_197] + Group By Operator [GBY_194] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_191] (rows=12174 width=1119) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_185] http://git-wip-us.apache.org/repos/asf/hive/blob/851c8aba/ql/src/test/results/clientpositive/perf/tez/query37.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/tez/query37.q.out b/ql/src/test/results/clientpositive/perf/tez/query37.q.out index 9db8538..2b3ae52 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query37.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query37.q.out @@ -46,83 +46,85 @@ Stage-0 limit:100 Stage-1 Reducer 4 vectorized - File Output Operator [FS_96] - Limit [LIM_95] (rows=100 width=135) + File Output Operator [FS_97] + Limit [LIM_96] (rows=100 width=135) Number of rows:100 - Select Operator [SEL_94] (rows=316788826 width=135) + Select Operator [SEL_95] (rows=316788826 width=135) Output:["_col0","_col1","_col2"] <-Reducer 3 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_93] - Group By Operator [GBY_92] (rows=316788826 width=135) + SHUFFLE [RS_94] + Group By Operator [GBY_93] (rows=316788826 width=135) Output:["_col0","_col1","_col2"],keys:KEY._col0, KEY._col1, KEY._col2 <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_22] PartitionCols:_col0, _col1, _col2 Group By Operator [GBY_21] (rows=633577652 width=135) Output:["_col0","_col1","_col2"],keys:_col2, _col3, _col4 - Merge Join Operator [MERGEJOIN_72] (rows=633577652 width=135) - Conds:RS_91._col0=RS_75._col0(Inner),RS_75._col0=RS_18._col1(Inner),Output:["_col2","_col3","_col4"] - <-Map 5 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_75] - PartitionCols:_col0 - Select Operator [SEL_74] (rows=25666 width=1436) - Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_73] (rows=25666 width=1436) - predicate:((i_manufact_id) IN (678, 964, 918, 849) and i_current_price BETWEEN 22 AND 52 and i_item_sk is not null) - TableScan [TS_3] (rows=462000 width=1436) - default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_item_id","i_item_desc","i_current_price","i_manufact_id"] - <-Reducer 8 [SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_18] - PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_71] (rows=4593600 width=15) - Conds:RS_83._col0=RS_86._col0(Inner),Output:["_col1"] - <-Map 10 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_86] - PartitionCols:_col0 - Select Operator [SEL_85] (rows=8116 width=1119) - Output:["_col0"] - Filter Operator [FIL_84] (rows=8116 width=1119) - predicate:(CAST( d_date AS TIMESTAMP) BETWEEN TIMESTAMP'2001-06-02 00:00:00' AND TIMESTAMP'2001-08-01 00:00:00' and d_date_sk is not null) - TableScan [TS_9] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_date"] - <-Map 7 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_83] - PartitionCols:_col0 - Select Operator [SEL_82] (rows=4176000 width=15) - Output:["_col0","_col1"] - Filter Operator [FIL_81] (rows=4176000 width=15) - predicate:(inv_date_sk is not null and inv_item_sk is not null and inv_quantity_on_hand BETWEEN 100 AND 500) - TableScan [TS_6] (rows=37584000 width=15) - default@inventory,inventory,Tbl:COMPLETE,Col:NONE,Output:["inv_date_sk","inv_item_sk","inv_quantity_on_hand"] - <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_91] - PartitionCols:_col0 - Select Operator [SEL_90] (rows=287989836 width=135) - Output:["_col0"] - Filter Operator [FIL_89] (rows=287989836 width=135) - predicate:((cs_item_sk BETWEEN DynamicValue(RS_17_item_i_item_sk_min) AND DynamicValue(RS_17_item_i_item_sk_max) and in_bloom_filter(cs_item_sk, DynamicValue(RS_17_item_i_item_sk_bloom_filter))) and (cs_item_sk BETWEEN DynamicValue(RS_18_inventory_inv_item_sk_min) AND DynamicValue(RS_18_inventory_inv_item_sk_max) and in_bloom_filter(cs_item_sk, DynamicValue(RS_18_inventory_inv_item_sk_bloom_filter))) and cs_item_sk is not null) - TableScan [TS_0] (rows=287989836 width=135) - default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:NONE,Output:["cs_item_sk"] - <-Reducer 6 [BROADCAST_EDGE] vectorized - BROADCAST [RS_80] - Group By Operator [GBY_79] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 5 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_78] - Group By Operator [GBY_77] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_76] (rows=25666 width=1436) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_74] - <-Reducer 9 [BROADCAST_EDGE] vectorized - BROADCAST [RS_88] - Group By Operator [GBY_87] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=4593600)"] - <-Reducer 8 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_50] - Group By Operator [GBY_49] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=4593600)"] - Select Operator [SEL_48] (rows=4593600 width=15) - Output:["_col0"] - Please refer to the previous Merge Join Operator [MERGEJOIN_71] + Top N Key Operator [TNK_43] (rows=633577652 width=135) + keys:_col2, _col3, _col4,sort order:+++,top n:100 + Merge Join Operator [MERGEJOIN_73] (rows=633577652 width=135) + Conds:RS_92._col0=RS_76._col0(Inner),RS_76._col0=RS_18._col1(Inner),Output:["_col2","_col3","_col4"] + <-Map 5 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_76] + PartitionCols:_col0 + Select Operator [SEL_75] (rows=25666 width=1436) + Output:["_col0","_col1","_col2","_col3"] + Filter Operator [FIL_74] (rows=25666 width=1436) + predicate:((i_manufact_id) IN (678, 964, 918, 849) and i_current_price BETWEEN 22 AND 52 and i_item_sk is not null) + TableScan [TS_3] (rows=462000 width=1436) + default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_item_id","i_item_desc","i_current_price","i_manufact_id"] + <-Reducer 8 [SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_18] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_72] (rows=4593600 width=15) + Conds:RS_84._col0=RS_87._col0(Inner),Output:["_col1"] + <-Map 10 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_87] + PartitionCols:_col0 + Select Operator [SEL_86] (rows=8116 width=1119) + Output:["_col0"] + Filter Operator [FIL_85] (rows=8116 width=1119) + predicate:(CAST( d_date AS TIMESTAMP) BETWEEN TIMESTAMP'2001-06-02 00:00:00' AND TIMESTAMP'2001-08-01 00:00:00' and d_date_sk is not null) + TableScan [TS_9] (rows=73049 width=1119) + default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_date"] + <-Map 7 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_84] + PartitionCols:_col0 + Select Operator [SEL_83] (rows=4176000 width=15) + Output:["_col0","_col1"] + Filter Operator [FIL_82] (rows=4176000 width=15) + predicate:(inv_date_sk is not null and inv_item_sk is not null and inv_quantity_on_hand BETWEEN 100 AND 500) + TableScan [TS_6] (rows=37584000 width=15) + default@inventory,inventory,Tbl:COMPLETE,Col:NONE,Output:["inv_date_sk","inv_item_sk","inv_quantity_on_hand"] + <-Map 1 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_92] + PartitionCols:_col0 + Select Operator [SEL_91] (rows=287989836 width=135) + Output:["_col0"] + Filter Operator [FIL_90] (rows=287989836 width=135) + predicate:((cs_item_sk BETWEEN DynamicValue(RS_17_item_i_item_sk_min) AND DynamicValue(RS_17_item_i_item_sk_max) and in_bloom_filter(cs_item_sk, DynamicValue(RS_17_item_i_item_sk_bloom_filter))) and (cs_item_sk BETWEEN DynamicValue(RS_18_inventory_inv_item_sk_min) AND DynamicValue(RS_18_inventory_inv_item_sk_max) and in_bloom_filter(cs_item_sk, DynamicValue(RS_18_inventory_inv_item_sk_bloom_filter))) and cs_item_sk is not null) + TableScan [TS_0] (rows=287989836 width=135) + default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:NONE,Output:["cs_item_sk"] + <-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 5 [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=25666 width=1436) + 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=4593600)"] + <-Reducer 8 [CUSTOM_SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_51] + Group By Operator [GBY_50] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=4593600)"] + Select Operator [SEL_49] (rows=4593600 width=15) + Output:["_col0"] + Please refer to the previous Merge Join Operator [MERGEJOIN_72]
