http://git-wip-us.apache.org/repos/asf/hive/blob/bd371246/ql/src/test/results/clientpositive/perf/spark/query80.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/spark/query80.q.out b/ql/src/test/results/clientpositive/perf/spark/query80.q.out new file mode 100644 index 0000000..606d23c --- /dev/null +++ b/ql/src/test/results/clientpositive/perf/spark/query80.q.out @@ -0,0 +1,903 @@ +PREHOOK: query: explain +with ssr as + (select s_store_id as store_id, + sum(ss_ext_sales_price) as sales, + sum(coalesce(sr_return_amt, 0)) as returns, + sum(ss_net_profit - coalesce(sr_net_loss, 0)) as profit + from store_sales left outer join store_returns on + (ss_item_sk = sr_item_sk and ss_ticket_number = sr_ticket_number), + date_dim, + store, + item, + promotion + where ss_sold_date_sk = d_date_sk + and d_date between cast('1998-08-04' as date) + and (cast('1998-08-04' as date) + 30 days) + and ss_store_sk = s_store_sk + and ss_item_sk = i_item_sk + and i_current_price > 50 + and ss_promo_sk = p_promo_sk + and p_channel_tv = 'N' + group by s_store_id) + , + csr as + (select cp_catalog_page_id as catalog_page_id, + sum(cs_ext_sales_price) as sales, + sum(coalesce(cr_return_amount, 0)) as returns, + sum(cs_net_profit - coalesce(cr_net_loss, 0)) as profit + from catalog_sales left outer join catalog_returns on + (cs_item_sk = cr_item_sk and cs_order_number = cr_order_number), + date_dim, + catalog_page, + item, + promotion + where cs_sold_date_sk = d_date_sk + and d_date between cast('1998-08-04' as date) + and (cast('1998-08-04' as date) + 30 days) + and cs_catalog_page_sk = cp_catalog_page_sk + and cs_item_sk = i_item_sk + and i_current_price > 50 + and cs_promo_sk = p_promo_sk + and p_channel_tv = 'N' +group by cp_catalog_page_id) + , + wsr as + (select web_site_id, + sum(ws_ext_sales_price) as sales, + sum(coalesce(wr_return_amt, 0)) as returns, + sum(ws_net_profit - coalesce(wr_net_loss, 0)) as profit + from web_sales left outer join web_returns on + (ws_item_sk = wr_item_sk and ws_order_number = wr_order_number), + date_dim, + web_site, + item, + promotion + where ws_sold_date_sk = d_date_sk + and d_date between cast('1998-08-04' as date) + and (cast('1998-08-04' as date) + 30 days) + and ws_web_site_sk = web_site_sk + and ws_item_sk = i_item_sk + and i_current_price > 50 + and ws_promo_sk = p_promo_sk + and p_channel_tv = 'N' +group by web_site_id) + select channel + , id + , sum(sales) as sales + , sum(returns) as returns + , sum(profit) as profit + from + (select 'store channel' as channel + , 'store' || store_id as id + , sales + , returns + , profit + from ssr + union all + select 'catalog channel' as channel + , 'catalog_page' || catalog_page_id as id + , sales + , returns + , profit + from csr + union all + select 'web channel' as channel + , 'web_site' || web_site_id as id + , sales + , returns + , profit + from wsr + ) x + group by rollup (channel, id) + order by channel + ,id + limit 100 +PREHOOK: type: QUERY +POSTHOOK: query: explain +with ssr as + (select s_store_id as store_id, + sum(ss_ext_sales_price) as sales, + sum(coalesce(sr_return_amt, 0)) as returns, + sum(ss_net_profit - coalesce(sr_net_loss, 0)) as profit + from store_sales left outer join store_returns on + (ss_item_sk = sr_item_sk and ss_ticket_number = sr_ticket_number), + date_dim, + store, + item, + promotion + where ss_sold_date_sk = d_date_sk + and d_date between cast('1998-08-04' as date) + and (cast('1998-08-04' as date) + 30 days) + and ss_store_sk = s_store_sk + and ss_item_sk = i_item_sk + and i_current_price > 50 + and ss_promo_sk = p_promo_sk + and p_channel_tv = 'N' + group by s_store_id) + , + csr as + (select cp_catalog_page_id as catalog_page_id, + sum(cs_ext_sales_price) as sales, + sum(coalesce(cr_return_amount, 0)) as returns, + sum(cs_net_profit - coalesce(cr_net_loss, 0)) as profit + from catalog_sales left outer join catalog_returns on + (cs_item_sk = cr_item_sk and cs_order_number = cr_order_number), + date_dim, + catalog_page, + item, + promotion + where cs_sold_date_sk = d_date_sk + and d_date between cast('1998-08-04' as date) + and (cast('1998-08-04' as date) + 30 days) + and cs_catalog_page_sk = cp_catalog_page_sk + and cs_item_sk = i_item_sk + and i_current_price > 50 + and cs_promo_sk = p_promo_sk + and p_channel_tv = 'N' +group by cp_catalog_page_id) + , + wsr as + (select web_site_id, + sum(ws_ext_sales_price) as sales, + sum(coalesce(wr_return_amt, 0)) as returns, + sum(ws_net_profit - coalesce(wr_net_loss, 0)) as profit + from web_sales left outer join web_returns on + (ws_item_sk = wr_item_sk and ws_order_number = wr_order_number), + date_dim, + web_site, + item, + promotion + where ws_sold_date_sk = d_date_sk + and d_date between cast('1998-08-04' as date) + and (cast('1998-08-04' as date) + 30 days) + and ws_web_site_sk = web_site_sk + and ws_item_sk = i_item_sk + and i_current_price > 50 + and ws_promo_sk = p_promo_sk + and p_channel_tv = 'N' +group by web_site_id) + select channel + , id + , sum(sales) as sales + , sum(returns) as returns + , sum(profit) as profit + from + (select 'store channel' as channel + , 'store' || store_id as id + , sales + , returns + , profit + from ssr + union all + select 'catalog channel' as channel + , 'catalog_page' || catalog_page_id as id + , sales + , returns + , profit + from csr + union all + select 'web channel' as channel + , 'web_site' || web_site_id as id + , sales + , returns + , profit + from wsr + ) x + group by rollup (channel, id) + order by channel + ,id + limit 100 +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-2 is a root stage + Stage-3 depends on stages: Stage-2 + Stage-4 depends on stages: Stage-3 + Stage-5 depends on stages: Stage-4 + Stage-6 depends on stages: Stage-5 + Stage-7 depends on stages: Stage-6 + Stage-1 depends on stages: Stage-7 + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-2 + Spark +#### A masked pattern was here #### + Vertices: + Map 10 + Map Operator Tree: + TableScan + alias: promotion + Statistics: Num rows: 2300 Data size: 2713420 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((p_channel_tv = 'N') and p_promo_sk is not null) (type: boolean) + Statistics: Num rows: 1150 Data size: 1356710 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: p_promo_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 1150 Data size: 1356710 Basic stats: COMPLETE Column stats: NONE + Spark HashTable Sink Operator + keys: + 0 _col3 (type: int) + 1 _col0 (type: int) + Local Work: + Map Reduce Local Work + Map 11 + Map Operator Tree: + TableScan + alias: store + Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: s_store_sk is not null (type: boolean) + Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: s_store_sk (type: int), s_store_id (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Spark HashTable Sink Operator + keys: + 0 _col2 (type: int) + 1 _col0 (type: int) + Local Work: + Map Reduce Local Work + + Stage: Stage-3 + Spark +#### A masked pattern was here #### + Vertices: + Map 8 + Map Operator Tree: + TableScan + alias: date_dim + Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (CAST( d_date AS TIMESTAMP) BETWEEN 1998-08-04 00:00:00.0 AND 1998-09-03 00:00:00.0 and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: d_date_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + Local Work: + Map Reduce Local Work + + Stage: Stage-4 + Spark +#### A masked pattern was here #### + Vertices: + Map 20 + Map Operator Tree: + TableScan + alias: promotion + Statistics: Num rows: 2300 Data size: 2713420 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((p_channel_tv = 'N') and p_promo_sk is not null) (type: boolean) + Statistics: Num rows: 1150 Data size: 1356710 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: p_promo_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 1150 Data size: 1356710 Basic stats: COMPLETE Column stats: NONE + Spark HashTable Sink Operator + keys: + 0 _col3 (type: int) + 1 _col0 (type: int) + Local Work: + Map Reduce Local Work + + Stage: Stage-5 + Spark +#### A masked pattern was here #### + Vertices: + Map 18 + Map Operator Tree: + TableScan + alias: date_dim + Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (CAST( d_date AS TIMESTAMP) BETWEEN 1998-08-04 00:00:00.0 AND 1998-09-03 00:00:00.0 and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: d_date_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + Local Work: + Map Reduce Local Work + + Stage: Stage-6 + Spark +#### A masked pattern was here #### + Vertices: + Map 29 + Map Operator Tree: + TableScan + alias: promotion + Statistics: Num rows: 2300 Data size: 2713420 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((p_channel_tv = 'N') and p_promo_sk is not null) (type: boolean) + Statistics: Num rows: 1150 Data size: 1356710 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: p_promo_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 1150 Data size: 1356710 Basic stats: COMPLETE Column stats: NONE + Spark HashTable Sink Operator + keys: + 0 _col3 (type: int) + 1 _col0 (type: int) + Local Work: + Map Reduce Local Work + Map 30 + Map Operator Tree: + TableScan + alias: web_site + Statistics: Num rows: 84 Data size: 155408 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: web_site_sk is not null (type: boolean) + Statistics: Num rows: 84 Data size: 155408 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: web_site_sk (type: int), web_site_id (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 84 Data size: 155408 Basic stats: COMPLETE Column stats: NONE + Spark HashTable Sink Operator + keys: + 0 _col2 (type: int) + 1 _col0 (type: int) + Local Work: + Map Reduce Local Work + + Stage: Stage-7 + Spark +#### A masked pattern was here #### + Vertices: + Map 27 + Map Operator Tree: + TableScan + alias: date_dim + Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (CAST( d_date AS TIMESTAMP) BETWEEN 1998-08-04 00:00:00.0 AND 1998-09-03 00:00:00.0 and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: d_date_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + Local Work: + Map Reduce Local Work + + Stage: Stage-1 + Spark + Edges: + Reducer 13 <- Map 12 (PARTITION-LEVEL SORT, 329), Map 17 (PARTITION-LEVEL SORT, 329) + Reducer 14 <- Map 19 (PARTITION-LEVEL SORT, 371), Reducer 13 (PARTITION-LEVEL SORT, 371) + Reducer 15 <- Map 21 (PARTITION-LEVEL SORT, 447), Reducer 14 (PARTITION-LEVEL SORT, 447) + Reducer 16 <- Reducer 15 (GROUP, 491) + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 432), Map 7 (PARTITION-LEVEL SORT, 432) + Reducer 23 <- Map 22 (PARTITION-LEVEL SORT, 164), Map 26 (PARTITION-LEVEL SORT, 164) + Reducer 24 <- Map 28 (PARTITION-LEVEL SORT, 187), Reducer 23 (PARTITION-LEVEL SORT, 187) + Reducer 25 <- Reducer 24 (GROUP, 247) + Reducer 3 <- Map 19 (PARTITION-LEVEL SORT, 483), Reducer 2 (PARTITION-LEVEL SORT, 483) + Reducer 4 <- Reducer 3 (GROUP, 640) + Reducer 5 <- Reducer 16 (GROUP, 1009), Reducer 25 (GROUP, 1009), Reducer 4 (GROUP, 1009) + Reducer 6 <- Reducer 5 (SORT, 1) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: store_sales + Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (ss_item_sk is not null and ss_promo_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null) (type: boolean) + Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: ss_sold_date_sk (type: int), ss_item_sk (type: int), ss_store_sk (type: int), ss_promo_sk (type: int), ss_ticket_number (type: int), ss_ext_sales_price (type: decimal(7,2)), ss_net_profit (type: decimal(7,2)) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 + Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col1 (type: int), _col4 (type: int) + sort order: ++ + Map-reduce partition columns: _col1 (type: int), _col4 (type: int) + Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int), _col2 (type: int), _col3 (type: int), _col5 (type: decimal(7,2)), _col6 (type: decimal(7,2)) + Map 12 + Map Operator Tree: + TableScan + alias: catalog_sales + Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (cs_catalog_page_sk is not null and cs_item_sk is not null and cs_promo_sk is not null and cs_sold_date_sk is not null) (type: boolean) + Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: cs_sold_date_sk (type: int), cs_catalog_page_sk (type: int), cs_item_sk (type: int), cs_promo_sk (type: int), cs_order_number (type: int), cs_ext_sales_price (type: decimal(7,2)), cs_net_profit (type: decimal(7,2)) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 + Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col2 (type: int), _col4 (type: int) + sort order: ++ + Map-reduce partition columns: _col2 (type: int), _col4 (type: int) + Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int), _col1 (type: int), _col3 (type: int), _col5 (type: decimal(7,2)), _col6 (type: decimal(7,2)) + Map 17 + Map Operator Tree: + TableScan + alias: catalog_returns + Statistics: Num rows: 28798881 Data size: 3057234680 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: cr_item_sk is not null (type: boolean) + Statistics: Num rows: 28798881 Data size: 3057234680 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: cr_item_sk (type: int), cr_order_number (type: int), cr_return_amount (type: decimal(7,2)), cr_net_loss (type: decimal(7,2)) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 28798881 Data size: 3057234680 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: int) + sort order: ++ + Map-reduce partition columns: _col0 (type: int), _col1 (type: int) + Statistics: Num rows: 28798881 Data size: 3057234680 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: decimal(7,2)), _col3 (type: decimal(7,2)) + Map 19 + Map Operator Tree: + TableScan + alias: item + Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((i_current_price > 50) and i_item_sk is not null) (type: boolean) + Statistics: Num rows: 154000 Data size: 221186819 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: i_item_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 154000 Data size: 221186819 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 154000 Data size: 221186819 Basic stats: COMPLETE Column stats: NONE + Map 21 + Map Operator Tree: + TableScan + alias: catalog_page + Statistics: Num rows: 46000 Data size: 21198808 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: cp_catalog_page_sk is not null (type: boolean) + Statistics: Num rows: 46000 Data size: 21198808 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: cp_catalog_page_sk (type: int), cp_catalog_page_id (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 46000 Data size: 21198808 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 46000 Data size: 21198808 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) + Map 22 + Map Operator Tree: + TableScan + alias: web_sales + Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (ws_item_sk is not null and ws_promo_sk is not null and ws_sold_date_sk is not null and ws_web_site_sk is not null) (type: boolean) + Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: ws_sold_date_sk (type: int), ws_item_sk (type: int), ws_web_site_sk (type: int), ws_promo_sk (type: int), ws_order_number (type: int), ws_ext_sales_price (type: decimal(7,2)), ws_net_profit (type: decimal(7,2)) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 + Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col1 (type: int), _col4 (type: int) + sort order: ++ + Map-reduce partition columns: _col1 (type: int), _col4 (type: int) + Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int), _col2 (type: int), _col3 (type: int), _col5 (type: decimal(7,2)), _col6 (type: decimal(7,2)) + Map 26 + Map Operator Tree: + TableScan + alias: web_returns + Statistics: Num rows: 14398467 Data size: 1325194184 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: wr_item_sk is not null (type: boolean) + Statistics: Num rows: 14398467 Data size: 1325194184 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: wr_item_sk (type: int), wr_order_number (type: int), wr_return_amt (type: decimal(7,2)), wr_net_loss (type: decimal(7,2)) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 14398467 Data size: 1325194184 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: int) + sort order: ++ + Map-reduce partition columns: _col0 (type: int), _col1 (type: int) + Statistics: Num rows: 14398467 Data size: 1325194184 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: decimal(7,2)), _col3 (type: decimal(7,2)) + Map 28 + Map Operator Tree: + TableScan + alias: item + Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((i_current_price > 50) and i_item_sk is not null) (type: boolean) + Statistics: Num rows: 154000 Data size: 221186819 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: i_item_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 154000 Data size: 221186819 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 154000 Data size: 221186819 Basic stats: COMPLETE Column stats: NONE + Map 7 + Map Operator Tree: + TableScan + alias: store_returns + Statistics: Num rows: 57591150 Data size: 4462194832 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: sr_item_sk is not null (type: boolean) + Statistics: Num rows: 57591150 Data size: 4462194832 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: sr_item_sk (type: int), sr_ticket_number (type: int), sr_return_amt (type: decimal(7,2)), sr_net_loss (type: decimal(7,2)) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 57591150 Data size: 4462194832 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: int) + sort order: ++ + Map-reduce partition columns: _col0 (type: int), _col1 (type: int) + Statistics: Num rows: 57591150 Data size: 4462194832 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: decimal(7,2)), _col3 (type: decimal(7,2)) + Reducer 13 + Local Work: + Map Reduce Local Work + Reduce Operator Tree: + Join Operator + condition map: + Left Outer Join 0 to 1 + keys: + 0 _col2 (type: int), _col4 (type: int) + 1 _col0 (type: int), _col1 (type: int) + outputColumnNames: _col0, _col1, _col2, _col3, _col5, _col6, _col9, _col10 + Statistics: Num rows: 316788826 Data size: 42899570777 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col3, _col5, _col6, _col9, _col10 + input vertices: + 1 Map 18 + Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col2 (type: int) + sort order: + + Map-reduce partition columns: _col2 (type: int) + Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: int), _col3 (type: int), _col5 (type: decimal(7,2)), _col6 (type: decimal(7,2)), _col9 (type: decimal(7,2)), _col10 (type: decimal(7,2)) + Reducer 14 + Local Work: + Map Reduce Local Work + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col2 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col3, _col5, _col6, _col9, _col10 + Statistics: Num rows: 383314495 Data size: 51908482889 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col3 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col5, _col6, _col9, _col10 + input vertices: + 1 Map 20 + Statistics: Num rows: 421645953 Data size: 57099332415 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col1 (type: int) + sort order: + + Map-reduce partition columns: _col1 (type: int) + Statistics: Num rows: 421645953 Data size: 57099332415 Basic stats: COMPLETE Column stats: NONE + value expressions: _col5 (type: decimal(7,2)), _col6 (type: decimal(7,2)), _col9 (type: decimal(7,2)), _col10 (type: decimal(7,2)) + Reducer 15 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col5, _col6, _col9, _col10, _col18 + Statistics: Num rows: 463810558 Data size: 62809267017 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col18 (type: string), _col5 (type: decimal(7,2)), COALESCE(_col9,0) (type: decimal(12,2)), (_col6 - COALESCE(_col10,0)) (type: decimal(13,2)) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 463810558 Data size: 62809267017 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(_col1), sum(_col2), sum(_col3) + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 463810558 Data size: 62809267017 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 463810558 Data size: 62809267017 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: decimal(17,2)), _col2 (type: decimal(22,2)), _col3 (type: decimal(23,2)) + Reducer 16 + Reduce Operator Tree: + Group By Operator + aggregations: sum(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 231905279 Data size: 31404633508 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: 'catalog channel' (type: string), concat('catalog_page', _col0) (type: string), _col1 (type: decimal(17,2)), _col2 (type: decimal(22,2)), _col3 (type: decimal(23,2)) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 231905279 Data size: 31404633508 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(_col2), sum(_col3), sum(_col4) + keys: _col0 (type: string), _col1 (type: string), 0 (type: int) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 2435062716 Data size: 264270971781 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: int) + sort order: +++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: int) + Statistics: Num rows: 2435062716 Data size: 264270971781 Basic stats: COMPLETE Column stats: NONE + TopN Hash Memory Usage: 0.1 + value expressions: _col3 (type: decimal(27,2)), _col4 (type: decimal(32,2)), _col5 (type: decimal(33,2)) + Reducer 2 + Local Work: + Map Reduce Local Work + Reduce Operator Tree: + Join Operator + condition map: + Left Outer Join 0 to 1 + keys: + 0 _col1 (type: int), _col4 (type: int) + 1 _col0 (type: int), _col1 (type: int) + outputColumnNames: _col0, _col1, _col2, _col3, _col5, _col6, _col9, _col10 + Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col3, _col5, _col6, _col9, _col10 + input vertices: + 1 Map 8 + Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col1 (type: int) + sort order: + + Map-reduce partition columns: _col1 (type: int) + Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: int), _col3 (type: int), _col5 (type: decimal(7,2)), _col6 (type: decimal(7,2)), _col9 (type: decimal(7,2)), _col10 (type: decimal(7,2)) + Reducer 23 + Local Work: + Map Reduce Local Work + Reduce Operator Tree: + Join Operator + condition map: + Left Outer Join 0 to 1 + keys: + 0 _col1 (type: int), _col4 (type: int) + 1 _col0 (type: int), _col1 (type: int) + outputColumnNames: _col0, _col1, _col2, _col3, _col5, _col6, _col9, _col10 + Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col3, _col5, _col6, _col9, _col10 + input vertices: + 1 Map 27 + Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col1 (type: int) + sort order: + + Map-reduce partition columns: _col1 (type: int) + Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: int), _col3 (type: int), _col5 (type: decimal(7,2)), _col6 (type: decimal(7,2)), _col9 (type: decimal(7,2)), _col10 (type: decimal(7,2)) + Reducer 24 + Local Work: + Map Reduce Local Work + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col2, _col3, _col5, _col6, _col9, _col10 + Statistics: Num rows: 191667562 Data size: 26061245514 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col3 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col2, _col5, _col6, _col9, _col10 + input vertices: + 1 Map 29 + Statistics: Num rows: 210834322 Data size: 28667370686 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col2 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col5, _col6, _col9, _col10, _col18 + input vertices: + 1 Map 30 + Statistics: Num rows: 231917759 Data size: 31534108438 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col18 (type: string), _col5 (type: decimal(7,2)), COALESCE(_col9,0) (type: decimal(12,2)), (_col6 - COALESCE(_col10,0)) (type: decimal(13,2)) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 231917759 Data size: 31534108438 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(_col1), sum(_col2), sum(_col3) + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 231917759 Data size: 31534108438 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 231917759 Data size: 31534108438 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: decimal(17,2)), _col2 (type: decimal(22,2)), _col3 (type: decimal(23,2)) + Reducer 25 + Reduce Operator Tree: + Group By Operator + aggregations: sum(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 115958879 Data size: 15767054151 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: 'web channel' (type: string), concat('web_site', _col0) (type: string), _col1 (type: decimal(17,2)), _col2 (type: decimal(22,2)), _col3 (type: decimal(23,2)) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 115958879 Data size: 15767054151 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(_col2), sum(_col3), sum(_col4) + keys: _col0 (type: string), _col1 (type: string), 0 (type: int) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 2435062716 Data size: 264270971781 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: int) + sort order: +++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: int) + Statistics: Num rows: 2435062716 Data size: 264270971781 Basic stats: COMPLETE Column stats: NONE + TopN Hash Memory Usage: 0.1 + value expressions: _col3 (type: decimal(27,2)), _col4 (type: decimal(32,2)), _col5 (type: decimal(33,2)) + Reducer 3 + Local Work: + Map Reduce Local Work + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col2, _col3, _col5, _col6, _col9, _col10 + Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col3 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col2, _col5, _col6, _col9, _col10 + input vertices: + 1 Map 10 + Statistics: Num rows: 843315281 Data size: 74397518956 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col2 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col5, _col6, _col9, _col10, _col18 + input vertices: + 1 Map 11 + Statistics: Num rows: 927646829 Data size: 81837272625 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col18 (type: string), _col5 (type: decimal(7,2)), COALESCE(_col9,0) (type: decimal(12,2)), (_col6 - COALESCE(_col10,0)) (type: decimal(13,2)) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 927646829 Data size: 81837272625 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(_col1), sum(_col2), sum(_col3) + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 927646829 Data size: 81837272625 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 927646829 Data size: 81837272625 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: decimal(17,2)), _col2 (type: decimal(22,2)), _col3 (type: decimal(23,2)) + Reducer 4 + Reduce Operator Tree: + Group By Operator + aggregations: sum(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 463823414 Data size: 40918636268 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: 'store channel' (type: string), concat('store', _col0) (type: string), _col1 (type: decimal(17,2)), _col2 (type: decimal(22,2)), _col3 (type: decimal(23,2)) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 463823414 Data size: 40918636268 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(_col2), sum(_col3), sum(_col4) + keys: _col0 (type: string), _col1 (type: string), 0 (type: int) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 2435062716 Data size: 264270971781 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: int) + sort order: +++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: int) + Statistics: Num rows: 2435062716 Data size: 264270971781 Basic stats: COMPLETE Column stats: NONE + TopN Hash Memory Usage: 0.1 + value expressions: _col3 (type: decimal(27,2)), _col4 (type: decimal(32,2)), _col5 (type: decimal(33,2)) + Reducer 5 + Reduce Operator Tree: + Group By Operator + aggregations: sum(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2) + keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: int) + mode: mergepartial + outputColumnNames: _col0, _col1, _col3, _col4, _col5 + Statistics: Num rows: 1217531358 Data size: 132135485890 Basic stats: COMPLETE Column stats: NONE + pruneGroupingSetId: true + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col3 (type: decimal(27,2)), _col4 (type: decimal(32,2)), _col5 (type: decimal(33,2)) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 1217531358 Data size: 132135485890 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + sort order: ++ + Statistics: Num rows: 1217531358 Data size: 132135485890 Basic stats: COMPLETE Column stats: NONE + TopN Hash Memory Usage: 0.1 + value expressions: _col2 (type: decimal(27,2)), _col3 (type: decimal(32,2)), _col4 (type: decimal(33,2)) + Reducer 6 + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), VALUE._col0 (type: decimal(27,2)), VALUE._col1 (type: decimal(32,2)), VALUE._col2 (type: decimal(33,2)) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 1217531358 Data size: 132135485890 Basic stats: COMPLETE Column stats: NONE + Limit + Number of rows: 100 + Statistics: Num rows: 100 Data size: 10800 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 100 Data size: 10800 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: 100 + Processor Tree: + ListSink +
http://git-wip-us.apache.org/repos/asf/hive/blob/bd371246/ql/src/test/results/clientpositive/perf/spark/query81.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/spark/query81.q.out b/ql/src/test/results/clientpositive/perf/spark/query81.q.out new file mode 100644 index 0000000..be6a5fa --- /dev/null +++ b/ql/src/test/results/clientpositive/perf/spark/query81.q.out @@ -0,0 +1,429 @@ +PREHOOK: query: explain +with customer_total_return as + (select cr_returning_customer_sk as ctr_customer_sk + ,ca_state as ctr_state, + sum(cr_return_amt_inc_tax) as ctr_total_return + from catalog_returns + ,date_dim + ,customer_address + where cr_returned_date_sk = d_date_sk + and d_year =1998 + and cr_returning_addr_sk = ca_address_sk + group by cr_returning_customer_sk + ,ca_state ) + select c_customer_id,c_salutation,c_first_name,c_last_name,ca_street_number,ca_street_name + ,ca_street_type,ca_suite_number,ca_city,ca_county,ca_state,ca_zip,ca_country,ca_gmt_offset + ,ca_location_type,ctr_total_return + from customer_total_return ctr1 + ,customer_address + ,customer + where ctr1.ctr_total_return > (select avg(ctr_total_return)*1.2 + from customer_total_return ctr2 + where ctr1.ctr_state = ctr2.ctr_state) + and ca_address_sk = c_current_addr_sk + and ca_state = 'IL' + and ctr1.ctr_customer_sk = c_customer_sk + order by c_customer_id,c_salutation,c_first_name,c_last_name,ca_street_number,ca_street_name + ,ca_street_type,ca_suite_number,ca_city,ca_county,ca_state,ca_zip,ca_country,ca_gmt_offset + ,ca_location_type,ctr_total_return + limit 100 +PREHOOK: type: QUERY +POSTHOOK: query: explain +with customer_total_return as + (select cr_returning_customer_sk as ctr_customer_sk + ,ca_state as ctr_state, + sum(cr_return_amt_inc_tax) as ctr_total_return + from catalog_returns + ,date_dim + ,customer_address + where cr_returned_date_sk = d_date_sk + and d_year =1998 + and cr_returning_addr_sk = ca_address_sk + group by cr_returning_customer_sk + ,ca_state ) + select c_customer_id,c_salutation,c_first_name,c_last_name,ca_street_number,ca_street_name + ,ca_street_type,ca_suite_number,ca_city,ca_county,ca_state,ca_zip,ca_country,ca_gmt_offset + ,ca_location_type,ctr_total_return + from customer_total_return ctr1 + ,customer_address + ,customer + where ctr1.ctr_total_return > (select avg(ctr_total_return)*1.2 + from customer_total_return ctr2 + where ctr1.ctr_state = ctr2.ctr_state) + and ca_address_sk = c_current_addr_sk + and ca_state = 'IL' + and ctr1.ctr_customer_sk = c_customer_sk + order by c_customer_id,c_salutation,c_first_name,c_last_name,ca_street_number,ca_street_name + ,ca_street_type,ca_suite_number,ca_city,ca_county,ca_state,ca_zip,ca_country,ca_gmt_offset + ,ca_location_type,ctr_total_return + limit 100 +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Spark + Edges: + Reducer 10 <- Reducer 16 (PARTITION-LEVEL SORT, 262), Reducer 9 (PARTITION-LEVEL SORT, 262) + Reducer 14 <- Map 13 (PARTITION-LEVEL SORT, 25), Map 17 (PARTITION-LEVEL SORT, 25) + Reducer 15 <- Map 18 (PARTITION-LEVEL SORT, 344), Reducer 14 (PARTITION-LEVEL SORT, 344) + Reducer 16 <- Reducer 15 (GROUP PARTITION-LEVEL SORT, 349) + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 697), Map 5 (PARTITION-LEVEL SORT, 697) + Reducer 3 <- Reducer 10 (PARTITION-LEVEL SORT, 656), Reducer 2 (PARTITION-LEVEL SORT, 656) + Reducer 4 <- Reducer 3 (SORT, 1) + Reducer 7 <- Map 11 (PARTITION-LEVEL SORT, 25), Map 6 (PARTITION-LEVEL SORT, 25) + Reducer 8 <- Map 12 (PARTITION-LEVEL SORT, 344), Reducer 7 (PARTITION-LEVEL SORT, 344) + Reducer 9 <- Reducer 8 (GROUP, 349) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: customer + Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (c_current_addr_sk is not null and c_customer_sk is not null) (type: boolean) + Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: c_customer_sk (type: int), c_customer_id (type: string), c_current_addr_sk (type: int), c_salutation (type: string), c_first_name (type: string), c_last_name (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col2 (type: int) + sort order: + + Map-reduce partition columns: _col2 (type: int) + Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) + Map 11 + Map Operator Tree: + TableScan + alias: date_dim + Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((d_year = 1998) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: d_date_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE + Map 12 + Map Operator Tree: + TableScan + alias: customer_address + Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ca_address_sk is not null (type: boolean) + Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: ca_address_sk (type: int), ca_state (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) + Map 13 + Map Operator Tree: + TableScan + alias: catalog_returns + Statistics: Num rows: 28798881 Data size: 3057234680 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (cr_returned_date_sk is not null and cr_returning_addr_sk is not null) (type: boolean) + Statistics: Num rows: 28798881 Data size: 3057234680 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: cr_returned_date_sk (type: int), cr_returning_customer_sk (type: int), cr_returning_addr_sk (type: int), cr_return_amt_inc_tax (type: decimal(7,2)) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 28798881 Data size: 3057234680 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 28798881 Data size: 3057234680 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: decimal(7,2)) + Map 17 + Map Operator Tree: + TableScan + alias: date_dim + Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((d_year = 1998) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: d_date_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE + Map 18 + Map Operator Tree: + TableScan + alias: customer_address + Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (ca_address_sk is not null and ca_state is not null) (type: boolean) + Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: ca_address_sk (type: int), ca_state (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) + Map 5 + Map Operator Tree: + TableScan + alias: customer_address + Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((ca_state = 'IL') and ca_address_sk is not null) (type: boolean) + Statistics: Num rows: 20000000 Data size: 20297597642 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: ca_address_sk (type: int), ca_street_number (type: string), ca_street_name (type: string), ca_street_type (type: string), ca_suite_number (type: string), ca_city (type: string), ca_county (type: string), ca_zip (type: string), ca_country (type: string), ca_gmt_offset (type: decimal(5,2)), ca_location_type (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col8, _col9, _col10, _col11 + Statistics: Num rows: 20000000 Data size: 20297597642 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 20000000 Data size: 20297597642 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string), _col8 (type: string), _col9 (type: string), _col10 (type: decimal(5,2)), _col11 (type: string) + Map 6 + Map Operator Tree: + TableScan + alias: catalog_returns + Statistics: Num rows: 28798881 Data size: 3057234680 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (cr_returned_date_sk is not null and cr_returning_addr_sk is not null and cr_returning_customer_sk is not null) (type: boolean) + Statistics: Num rows: 28798881 Data size: 3057234680 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: cr_returned_date_sk (type: int), cr_returning_customer_sk (type: int), cr_returning_addr_sk (type: int), cr_return_amt_inc_tax (type: decimal(7,2)) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 28798881 Data size: 3057234680 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 28798881 Data size: 3057234680 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: decimal(7,2)) + Reducer 10 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: string) + 1 _col2 (type: string) + outputColumnNames: _col0, _col2, _col3, _col4 + Statistics: Num rows: 24200000 Data size: 24560094211 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (_col2 > CASE WHEN (_col4 is null) THEN (null) ELSE (_col3) END) (type: boolean) + Statistics: Num rows: 8066666 Data size: 8186697393 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: int), _col2 (type: decimal(17,2)) + outputColumnNames: _col0, _col2 + Statistics: Num rows: 8066666 Data size: 8186697393 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 8066666 Data size: 8186697393 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: decimal(17,2)) + Reducer 14 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col3 + Statistics: Num rows: 31678769 Data size: 3362958220 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col2 (type: int) + sort order: + + Map-reduce partition columns: _col2 (type: int) + Statistics: Num rows: 31678769 Data size: 3362958220 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: int), _col3 (type: decimal(7,2)) + Reducer 15 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col2 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col3, _col7 + Statistics: Num rows: 44000000 Data size: 44654715780 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(_col3) + keys: _col7 (type: string), _col1 (type: int) + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 44000000 Data size: 44654715780 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: int) + sort order: ++ + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 44000000 Data size: 44654715780 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: decimal(17,2)) + Reducer 16 + Reduce Operator Tree: + Group By Operator + aggregations: sum(VALUE._col0) + keys: KEY._col0 (type: string), KEY._col1 (type: int) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 22000000 Data size: 22327357890 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: string), _col2 (type: decimal(17,2)) + outputColumnNames: _col0, _col2 + Statistics: Num rows: 22000000 Data size: 22327357890 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: avg(_col2) + keys: _col0 (type: string) + mode: complete + outputColumnNames: _col0, _col1 + Statistics: Num rows: 11000000 Data size: 11163678945 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: (_col1 * 1.2) (type: decimal(24,7)), true (type: boolean), _col0 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 11000000 Data size: 11163678945 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col2 (type: string) + sort order: + + Map-reduce partition columns: _col2 (type: string) + Statistics: Num rows: 11000000 Data size: 11163678945 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: decimal(24,7)), _col1 (type: boolean) + Reducer 2 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col2 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0, _col1, _col3, _col4, _col5, _col7, _col8, _col9, _col10, _col11, _col12, _col14, _col15, _col16, _col17 + Statistics: Num rows: 88000001 Data size: 75681779077 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 88000001 Data size: 75681779077 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col7 (type: string), _col8 (type: string), _col9 (type: string), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col14 (type: string), _col15 (type: string), _col16 (type: decimal(5,2)), _col17 (type: string) + Reducer 3 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col3, _col4, _col5, _col7, _col8, _col9, _col10, _col11, _col12, _col14, _col15, _col16, _col17, _col20 + Statistics: Num rows: 96800003 Data size: 83249958789 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col1 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col7 (type: string), _col8 (type: string), _col9 (type: string), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col14 (type: string), _col15 (type: string), _col16 (type: decimal(5,2)), _col17 (type: string), _col20 (type: decimal(17,2)) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 + Statistics: Num rows: 96800003 Data size: 83249958789 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string), _col7 (type: string), _col8 (type: string), _col9 (type: string), _col10 (type: string), _col11 (type: string), _col12 (type: decimal(5,2)), _col13 (type: string), _col14 (type: decimal(17,2)) + sort order: +++++++++++++++ + Statistics: Num rows: 96800003 Data size: 83249958789 Basic stats: COMPLETE Column stats: NONE + TopN Hash Memory Usage: 0.1 + Reducer 4 + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string), KEY.reducesinkkey4 (type: string), KEY.reducesinkkey5 (type: string), KEY.reducesinkkey6 (type: string), KEY.reducesinkkey7 (type: string), KEY.reducesinkkey8 (type: string), KEY.reducesinkkey9 (type: string), KEY.reducesinkkey10 (type: string), KEY.reducesinkkey11 (type: string), KEY.reducesinkkey12 (type: decimal(5,2)), KEY.reducesinkkey13 (type: string), KEY.reducesinkkey14 (type: decimal(17,2)) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 + Statistics: Num rows: 96800003 Data size: 83249958789 Basic stats: COMPLETE Column stats: NONE + Limit + Number of rows: 100 + Statistics: Num rows: 100 Data size: 86000 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string), _col7 (type: string), _col8 (type: string), _col9 (type: string), 'IL' (type: string), _col10 (type: string), _col11 (type: string), _col12 (type: decimal(5,2)), _col13 (type: string), _col14 (type: decimal(17,2)) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15 + Statistics: Num rows: 100 Data size: 86000 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 100 Data size: 86000 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 7 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col3 + Statistics: Num rows: 31678769 Data size: 3362958220 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col2 (type: int) + sort order: + + Map-reduce partition columns: _col2 (type: int) + Statistics: Num rows: 31678769 Data size: 3362958220 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: int), _col3 (type: decimal(7,2)) + Reducer 8 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col2 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col3, _col7 + Statistics: Num rows: 44000000 Data size: 44654715780 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(_col3) + keys: _col7 (type: string), _col1 (type: int) + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 44000000 Data size: 44654715780 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: int) + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: int) + Statistics: Num rows: 44000000 Data size: 44654715780 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: decimal(17,2)) + Reducer 9 + Reduce Operator Tree: + Group By Operator + aggregations: sum(VALUE._col0) + keys: KEY._col0 (type: string), KEY._col1 (type: int) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 22000000 Data size: 22327357890 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col1 (type: int), _col0 (type: string), _col2 (type: decimal(17,2)) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 22000000 Data size: 22327357890 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col1 (type: string) + sort order: + + Map-reduce partition columns: _col1 (type: string) + Statistics: Num rows: 22000000 Data size: 22327357890 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int), _col2 (type: decimal(17,2)) + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + http://git-wip-us.apache.org/repos/asf/hive/blob/bd371246/ql/src/test/results/clientpositive/perf/spark/query82.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/spark/query82.q.out b/ql/src/test/results/clientpositive/perf/spark/query82.q.out new file mode 100644 index 0000000..b45f8d0 --- /dev/null +++ b/ql/src/test/results/clientpositive/perf/spark/query82.q.out @@ -0,0 +1,192 @@ +PREHOOK: query: explain +select i_item_id + ,i_item_desc + ,i_current_price + from item, inventory, date_dim, store_sales + where i_current_price between 30 and 30+30 + and inv_item_sk = i_item_sk + and d_date_sk=inv_date_sk + and d_date between cast('2002-05-30' as date) and (cast('2002-05-30' as date) + 60 days) + and i_manufact_id in (437,129,727,663) + and inv_quantity_on_hand between 100 and 500 + and ss_item_sk = i_item_sk + group by i_item_id,i_item_desc,i_current_price + order by i_item_id + limit 100 +PREHOOK: type: QUERY +POSTHOOK: query: explain +select i_item_id + ,i_item_desc + ,i_current_price + from item, inventory, date_dim, store_sales + where i_current_price between 30 and 30+30 + and inv_item_sk = i_item_sk + and d_date_sk=inv_date_sk + and d_date between cast('2002-05-30' as date) and (cast('2002-05-30' as date) + 60 days) + and i_manufact_id in (437,129,727,663) + and inv_quantity_on_hand between 100 and 500 + and ss_item_sk = i_item_sk + group by i_item_id,i_item_desc,i_current_price + order by i_item_id + limit 100 +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-2 is a root stage + Stage-1 depends on stages: Stage-2 + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-2 + Spark +#### A masked pattern was here #### + Vertices: + Map 7 + Map Operator Tree: + TableScan + alias: date_dim + Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (CAST( d_date AS TIMESTAMP) BETWEEN 2002-05-30 00:00:00.0 AND 2002-07-29 00:00:00.0 and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: d_date_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + Local Work: + Map Reduce Local Work + + Stage: Stage-1 + Spark + Edges: + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 398), Map 5 (PARTITION-LEVEL SORT, 398), Map 6 (PARTITION-LEVEL SORT, 398) + Reducer 3 <- Reducer 2 (GROUP, 874) + Reducer 4 <- Reducer 3 (SORT, 1) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: store_sales + Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ss_item_sk is not null (type: boolean) + Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: ss_item_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Map 5 + Map Operator Tree: + TableScan + alias: item + Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((i_manufact_id) IN (437, 129, 727, 663) and i_current_price BETWEEN 30 AND 60 and i_item_sk is not null) (type: boolean) + Statistics: Num rows: 25666 Data size: 36863512 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: i_item_sk (type: int), i_item_id (type: string), i_item_desc (type: string), i_current_price (type: decimal(7,2)) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 25666 Data size: 36863512 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 25666 Data size: 36863512 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: decimal(7,2)) + Map 6 + Map Operator Tree: + TableScan + alias: inventory + Statistics: Num rows: 37584000 Data size: 593821104 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (inv_date_sk is not null and inv_item_sk is not null and inv_quantity_on_hand BETWEEN 100 AND 500) (type: boolean) + Statistics: Num rows: 4176000 Data size: 65980122 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: inv_date_sk (type: int), inv_item_sk (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 4176000 Data size: 65980122 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1 + input vertices: + 1 Map 7 + Statistics: Num rows: 4593600 Data size: 72578135 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col1 (type: int) + sort order: + + Map-reduce partition columns: _col1 (type: int) + Statistics: Num rows: 4593600 Data size: 72578135 Basic stats: COMPLETE Column stats: NONE + Local Work: + Map Reduce Local Work + Reducer 2 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + Inner Join 1 to 2 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + 2 _col1 (type: int) + outputColumnNames: _col2, _col3, _col4 + Statistics: Num rows: 1267190424 Data size: 111791907016 Basic stats: COMPLETE Column stats: NONE + Group By Operator + keys: _col2 (type: string), _col3 (type: string), _col4 (type: decimal(7,2)) + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1267190424 Data size: 111791907016 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: decimal(7,2)) + sort order: +++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: decimal(7,2)) + Statistics: Num rows: 1267190424 Data size: 111791907016 Basic stats: COMPLETE Column stats: NONE + TopN Hash Memory Usage: 0.1 + Reducer 3 + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: decimal(7,2)) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE + TopN Hash Memory Usage: 0.1 + value expressions: _col1 (type: string), _col2 (type: decimal(7,2)) + Reducer 4 + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string), VALUE._col1 (type: decimal(7,2)) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE + Limit + Number of rows: 100 + Statistics: Num rows: 100 Data size: 8800 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 100 Data size: 8800 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: 100 + Processor Tree: + ListSink +