+----------------------------------------------------+ | Explain | +----------------------------------------------------+ | Plan optimized by CBO. | | | | Vertex dependency in root stage | | Map 1 <- Map 6 (BROADCAST_EDGE), Reducer 8 (BROADCAST_EDGE) | | Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE), Map 7 (CUSTOM_SIMPLE_EDGE) | | Reducer 3 <- Map 9 (CUSTOM_SIMPLE_EDGE), Reducer 2 (CUSTOM_SIMPLE_EDGE) | | Reducer 4 <- Reducer 3 (SIMPLE_EDGE) | | Reducer 5 <- Reducer 4 (SIMPLE_EDGE) | | Reducer 8 <- Map 7 (CUSTOM_SIMPLE_EDGE) | | | | Stage-0 | | Fetch Operator | | limit:100 | | Stage-1 | | Reducer 5 vectorized | | File Output Operator [FS_105] | | Limit [LIM_104] (rows=100 width=23) | | Number of rows:100 | | Select Operator [SEL_103] (rows=905837553 width=23) | | Output:["_col0","_col1"] | | <-Reducer 4 [SIMPLE_EDGE] vectorized | | SHUFFLE [RS_102] | | Group By Operator [GBY_101] (rows=905837553 width=23) | | Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 | | <-Reducer 3 [SIMPLE_EDGE] vectorized | | SHUFFLE [RS_100] | | PartitionCols:_col0 | | Group By Operator [GBY_99] (rows=1811675106 width=23) | | Output:["_col0","_col1"],aggregations:["sum(_col1)"],keys:_col10 | | Select Operator [SEL_98] (rows=1811675106 width=23) | | Output:["_col1","_col10"] | | Filter Operator [FIL_97] (rows=1811675106 width=23) | | predicate:((substr(_col10, 1, 5)) IN ('85669', '86197', '88274', '83405', '86475', '85392', '85460', '80348', '81792') or (_col9) IN ('CA', 'WA', 'GA') or (_col1 > 500.0D)) | | Map Join Operator [MAPJOIN_96] (rows=1811675106 width=23) | | Conds:RS_92.KEY.reducesinkkey0=RS_95.KEY.reducesinkkey0(Inner),Output:["_col1","_col9","_col10"] | | <-Map 9 [CUSTOM_SIMPLE_EDGE] vectorized | | PARTITION_ONLY_SHUFFLE [RS_95] | | PartitionCols:_col0 | | Select Operator [SEL_94] (rows=5700000 width=357) | | Output:["_col0","_col1","_col2"] | | Filter Operator [FIL_93] (rows=5700000 width=357) | | predicate:ca_address_sk is not null | | TableScan [TS_9] (rows=6000000 width=357) | | tpcds_bin_partitioned_orc_1000@customer_address,customer_address,Tbl:COMPLETE,Col:NONE,Output:["ca_address_sk","ca_state","ca_zip"] | | <-Reducer 2 [CUSTOM_SIMPLE_EDGE] vectorized | | PARTITION_ONLY_SHUFFLE [RS_92] | | PartitionCols:_col7 | | Map Join Operator [MAPJOIN_91] (rows=1646977334 width=23) | | Conds:RS_90.KEY.reducesinkkey0=RS_81.KEY.reducesinkkey0(Inner),Output:["_col1","_col7"] | | <-Map 7 [CUSTOM_SIMPLE_EDGE] vectorized | | PARTITION_ONLY_SHUFFLE [RS_81] | | PartitionCols:_col0 | | Select Operator [SEL_80] (rows=10800000 width=15) | | Output:["_col0","_col1"] | | Filter Operator [FIL_79] (rows=10800000 width=15) | | predicate:(c_customer_sk is not null and c_current_addr_sk is not null) | | TableScan [TS_6] (rows=12000000 width=15) | | tpcds_bin_partitioned_orc_1000@customer,customer,Tbl:COMPLETE,Col:NONE,Output:["c_customer_sk","c_current_addr_sk"] | | <-Map 1 [CUSTOM_SIMPLE_EDGE] vectorized | | PARTITION_ONLY_SHUFFLE [RS_90] | | PartitionCols:_col0 | | Map Join Operator [MAPJOIN_89] (rows=1497252090 width=23) | | Conds:SEL_88._col2=RS_75._col0(Inner),Output:["_col0","_col1"] | | <-Map 6 [BROADCAST_EDGE] vectorized | | BROADCAST [RS_75] | | PartitionCols:_col0 | | Select Operator [SEL_74] (rows=1 width=15) | | Output:["_col0"] | | Filter Operator [FIL_73] (rows=1 width=15) | | predicate:((d_qoy = 2) and (d_year = 2000) and d_date_sk is not null) | | TableScan [TS_3] (rows=73049 width=15) | | tpcds_bin_partitioned_orc_1000@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year","d_qoy"] | | Dynamic Partitioning Event Operator [EVENT_78] (rows=1 width=15) | | Group By Operator [GBY_77] (rows=1 width=15) | | Output:["_col0"],keys:_col0 | | Select Operator [SEL_76] (rows=1 width=15) | | Output:["_col0"] | | Please refer to the previous Select Operator [SEL_74] | | <-Select Operator [SEL_88] (rows=1361138235 width=23) | | Output:["_col0","_col1","_col2"] | | Filter Operator [FIL_87] (rows=1361138235 width=23) | | predicate:(cs_bill_customer_sk is not null and (cs_bill_customer_sk BETWEEN DynamicValue(RS_16_customer_c_customer_sk_min) AND DynamicValue(RS_16_customer_c_customer_sk_max) and in_bloom_filter(cs_bill_customer_sk, DynamicValue(RS_16_customer_c_customer_sk_bloom_filter)))) | | TableScan [TS_0] (rows=1432777090 width=23) | | tpcds_bin_partitioned_orc_1000@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:PARTIAL,Output:["cs_bill_customer_sk","cs_sales_price"] | | <-Reducer 8 [BROADCAST_EDGE] vectorized | | BROADCAST [RS_86] | | Group By Operator [GBY_85] (rows=1 width=40) | | Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=10800000)"] | | | +----------------------------------------------------+