http://git-wip-us.apache.org/repos/asf/hive/blob/bd371246/ql/src/test/results/clientpositive/perf/spark/query5.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/spark/query5.q.out b/ql/src/test/results/clientpositive/perf/spark/query5.q.out new file mode 100644 index 0000000..14e0bdb --- /dev/null +++ b/ql/src/test/results/clientpositive/perf/spark/query5.q.out @@ -0,0 +1,740 @@ +PREHOOK: query: explain +with ssr as + (select s_store_id, + sum(sales_price) as sales, + sum(profit) as profit, + sum(return_amt) as returns, + sum(net_loss) as profit_loss + from + ( select ss_store_sk as store_sk, + ss_sold_date_sk as date_sk, + ss_ext_sales_price as sales_price, + ss_net_profit as profit, + cast(0 as decimal(7,2)) as return_amt, + cast(0 as decimal(7,2)) as net_loss + from store_sales + union all + select sr_store_sk as store_sk, + sr_returned_date_sk as date_sk, + cast(0 as decimal(7,2)) as sales_price, + cast(0 as decimal(7,2)) as profit, + sr_return_amt as return_amt, + sr_net_loss as net_loss + from store_returns + ) salesreturns, + date_dim, + store + where date_sk = d_date_sk + and d_date between cast('1998-08-04' as date) + and (cast('1998-08-04' as date) + 14 days) + and store_sk = s_store_sk + group by s_store_id) + , + csr as + (select cp_catalog_page_id, + sum(sales_price) as sales, + sum(profit) as profit, + sum(return_amt) as returns, + sum(net_loss) as profit_loss + from + ( select cs_catalog_page_sk as page_sk, + cs_sold_date_sk as date_sk, + cs_ext_sales_price as sales_price, + cs_net_profit as profit, + cast(0 as decimal(7,2)) as return_amt, + cast(0 as decimal(7,2)) as net_loss + from catalog_sales + union all + select cr_catalog_page_sk as page_sk, + cr_returned_date_sk as date_sk, + cast(0 as decimal(7,2)) as sales_price, + cast(0 as decimal(7,2)) as profit, + cr_return_amount as return_amt, + cr_net_loss as net_loss + from catalog_returns + ) salesreturns, + date_dim, + catalog_page + where date_sk = d_date_sk + and d_date between cast('1998-08-04' as date) + and (cast('1998-08-04' as date) + 14 days) + and page_sk = cp_catalog_page_sk + group by cp_catalog_page_id) + , + wsr as + (select web_site_id, + sum(sales_price) as sales, + sum(profit) as profit, + sum(return_amt) as returns, + sum(net_loss) as profit_loss + from + ( select ws_web_site_sk as wsr_web_site_sk, + ws_sold_date_sk as date_sk, + ws_ext_sales_price as sales_price, + ws_net_profit as profit, + cast(0 as decimal(7,2)) as return_amt, + cast(0 as decimal(7,2)) as net_loss + from web_sales + union all + select ws_web_site_sk as wsr_web_site_sk, + wr_returned_date_sk as date_sk, + cast(0 as decimal(7,2)) as sales_price, + cast(0 as decimal(7,2)) as profit, + wr_return_amt as return_amt, + wr_net_loss as net_loss + from web_returns left outer join web_sales on + ( wr_item_sk = ws_item_sk + and wr_order_number = ws_order_number) + ) salesreturns, + date_dim, + web_site + where date_sk = d_date_sk + and d_date between cast('1998-08-04' as date) + and (cast('1998-08-04' as date) + 14 days) + and wsr_web_site_sk = web_site_sk + 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' || s_store_id as id + , sales + , returns + , (profit - profit_loss) as profit + from ssr + union all + select 'catalog channel' as channel + , 'catalog_page' || cp_catalog_page_id as id + , sales + , returns + , (profit - profit_loss) as profit + from csr + union all + select 'web channel' as channel + , 'web_site' || web_site_id as id + , sales + , returns + , (profit - profit_loss) as 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, + sum(sales_price) as sales, + sum(profit) as profit, + sum(return_amt) as returns, + sum(net_loss) as profit_loss + from + ( select ss_store_sk as store_sk, + ss_sold_date_sk as date_sk, + ss_ext_sales_price as sales_price, + ss_net_profit as profit, + cast(0 as decimal(7,2)) as return_amt, + cast(0 as decimal(7,2)) as net_loss + from store_sales + union all + select sr_store_sk as store_sk, + sr_returned_date_sk as date_sk, + cast(0 as decimal(7,2)) as sales_price, + cast(0 as decimal(7,2)) as profit, + sr_return_amt as return_amt, + sr_net_loss as net_loss + from store_returns + ) salesreturns, + date_dim, + store + where date_sk = d_date_sk + and d_date between cast('1998-08-04' as date) + and (cast('1998-08-04' as date) + 14 days) + and store_sk = s_store_sk + group by s_store_id) + , + csr as + (select cp_catalog_page_id, + sum(sales_price) as sales, + sum(profit) as profit, + sum(return_amt) as returns, + sum(net_loss) as profit_loss + from + ( select cs_catalog_page_sk as page_sk, + cs_sold_date_sk as date_sk, + cs_ext_sales_price as sales_price, + cs_net_profit as profit, + cast(0 as decimal(7,2)) as return_amt, + cast(0 as decimal(7,2)) as net_loss + from catalog_sales + union all + select cr_catalog_page_sk as page_sk, + cr_returned_date_sk as date_sk, + cast(0 as decimal(7,2)) as sales_price, + cast(0 as decimal(7,2)) as profit, + cr_return_amount as return_amt, + cr_net_loss as net_loss + from catalog_returns + ) salesreturns, + date_dim, + catalog_page + where date_sk = d_date_sk + and d_date between cast('1998-08-04' as date) + and (cast('1998-08-04' as date) + 14 days) + and page_sk = cp_catalog_page_sk + group by cp_catalog_page_id) + , + wsr as + (select web_site_id, + sum(sales_price) as sales, + sum(profit) as profit, + sum(return_amt) as returns, + sum(net_loss) as profit_loss + from + ( select ws_web_site_sk as wsr_web_site_sk, + ws_sold_date_sk as date_sk, + ws_ext_sales_price as sales_price, + ws_net_profit as profit, + cast(0 as decimal(7,2)) as return_amt, + cast(0 as decimal(7,2)) as net_loss + from web_sales + union all + select ws_web_site_sk as wsr_web_site_sk, + wr_returned_date_sk as date_sk, + cast(0 as decimal(7,2)) as sales_price, + cast(0 as decimal(7,2)) as profit, + wr_return_amt as return_amt, + wr_net_loss as net_loss + from web_returns left outer join web_sales on + ( wr_item_sk = ws_item_sk + and wr_order_number = ws_order_number) + ) salesreturns, + date_dim, + web_site + where date_sk = d_date_sk + and d_date between cast('1998-08-04' as date) + and (cast('1998-08-04' as date) + 14 days) + and wsr_web_site_sk = web_site_sk + 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' || s_store_id as id + , sales + , returns + , (profit - profit_loss) as profit + from ssr + union all + select 'catalog channel' as channel + , 'catalog_page' || cp_catalog_page_id as id + , sales + , returns + , (profit - profit_loss) as profit + from csr + union all + select 'web channel' as channel + , 'web_site' || web_site_id as id + , sales + , returns + , (profit - profit_loss) as 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-1 depends on stages: Stage-3 + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-2 + Spark +#### A masked pattern was here #### + Vertices: + Map 8 + 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 _col0 (type: int) + 1 _col0 (type: int) + Local Work: + Map Reduce Local Work + + Stage: Stage-3 + Spark +#### A masked pattern was here #### + Vertices: + Map 23 + 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 _col0 (type: int) + 1 _col0 (type: int) + Local Work: + Map Reduce Local Work + + Stage: Stage-1 + Spark + Edges: + Reducer 10 <- Map 13 (PARTITION-LEVEL SORT, 329), Map 14 (PARTITION-LEVEL SORT, 329), Map 9 (PARTITION-LEVEL SORT, 329) + Reducer 11 <- Map 15 (PARTITION-LEVEL SORT, 362), Reducer 10 (PARTITION-LEVEL SORT, 362) + Reducer 12 <- Reducer 11 (GROUP, 398) + Reducer 17 <- Map 14 (PARTITION-LEVEL SORT, 322), Map 16 (PARTITION-LEVEL SORT, 322), Reducer 20 (PARTITION-LEVEL SORT, 322) + Reducer 18 <- Reducer 17 (GROUP, 389) + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 432), Map 6 (PARTITION-LEVEL SORT, 432), Map 7 (PARTITION-LEVEL SORT, 432) + Reducer 20 <- Map 19 (PARTITION-LEVEL SORT, 164), Map 21 (PARTITION-LEVEL SORT, 164) + Reducer 3 <- Reducer 2 (GROUP, 523) + Reducer 4 <- Reducer 12 (GROUP, 1009), Reducer 18 (GROUP, 1009), Reducer 3 (GROUP, 1009) + Reducer 5 <- Reducer 4 (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_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_store_sk (type: int), ss_sold_date_sk (type: int), ss_ext_sales_price (type: decimal(7,2)), ss_net_profit (type: decimal(7,2)), 0 (type: decimal(7,2)), 0 (type: decimal(7,2)) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 575995635 Data size: 50814502088 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: 633586785 Data size: 55276696920 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int), _col2 (type: decimal(7,2)), _col3 (type: decimal(7,2)), _col4 (type: decimal(7,2)), _col5 (type: decimal(7,2)) + 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_catalog_page_sk is not null and cr_returned_date_sk is not null) (type: boolean) + Statistics: Num rows: 28798881 Data size: 3057234680 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: cr_catalog_page_sk (type: int), cr_returned_date_sk (type: int), 0 (type: decimal(7,2)), 0 (type: decimal(7,2)), cr_return_amount (type: decimal(7,2)), cr_net_loss (type: decimal(7,2)) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 28798881 Data size: 3057234680 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: 316788717 Data size: 42056843632 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int), _col2 (type: decimal(7,2)), _col3 (type: decimal(7,2)), _col4 (type: decimal(7,2)), _col5 (type: decimal(7,2)) + Map 14 + 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 1998-08-18 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 + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE + Map 15 + 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 16 + Map Operator Tree: + TableScan + alias: web_sales + Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (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_web_site_sk (type: int), ws_sold_date_sk (type: int), ws_ext_sales_price (type: decimal(7,2)), ws_net_profit (type: decimal(7,2)), 0 (type: decimal(7,2)), 0 (type: decimal(7,2)) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 144002668 Data size: 19580198212 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: 302405606 Data size: 41118416712 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int), _col2 (type: decimal(7,2)), _col3 (type: decimal(7,2)), _col4 (type: decimal(7,2)), _col5 (type: decimal(7,2)) + Map 19 + 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_order_number 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_item_sk (type: int), ws_web_site_sk (type: int), ws_order_number (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col2 (type: int) + sort order: ++ + Map-reduce partition columns: _col0 (type: int), _col2 (type: int) + Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: int) + Map 21 + 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 and wr_order_number is not null and wr_returned_date_sk is not null) (type: boolean) + Statistics: Num rows: 14398467 Data size: 1325194184 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: wr_returned_date_sk (type: int), 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, _col4 + Statistics: Num rows: 14398467 Data size: 1325194184 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col1 (type: int), _col2 (type: int) + sort order: ++ + Map-reduce partition columns: _col1 (type: int), _col2 (type: int) + Statistics: Num rows: 14398467 Data size: 1325194184 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int), _col3 (type: decimal(7,2)), _col4 (type: decimal(7,2)) + Map 6 + Map Operator Tree: + TableScan + alias: store_returns + Statistics: Num rows: 57591150 Data size: 4462194832 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (sr_returned_date_sk is not null and sr_store_sk is not null) (type: boolean) + Statistics: Num rows: 57591150 Data size: 4462194832 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: sr_store_sk (type: int), sr_returned_date_sk (type: int), 0 (type: decimal(7,2)), 0 (type: decimal(7,2)), sr_return_amt (type: decimal(7,2)), sr_net_loss (type: decimal(7,2)) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 57591150 Data size: 4462194832 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: 633586785 Data size: 55276696920 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int), _col2 (type: decimal(7,2)), _col3 (type: decimal(7,2)), _col4 (type: decimal(7,2)), _col5 (type: decimal(7,2)) + 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 1998-08-04 00:00:00.0 AND 1998-08-18 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 + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE + Map 9 + 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_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_catalog_page_sk (type: int), cs_sold_date_sk (type: int), cs_ext_sales_price (type: decimal(7,2)), cs_net_profit (type: decimal(7,2)), 0 (type: decimal(7,2)), 0 (type: decimal(7,2)) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 287989836 Data size: 38999608952 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: 316788717 Data size: 42056843632 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int), _col2 (type: decimal(7,2)), _col3 (type: decimal(7,2)), _col4 (type: decimal(7,2)), _col5 (type: decimal(7,2)) + Reducer 10 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0, _col2, _col3, _col4, _col5 + Statistics: Num rows: 348467596 Data size: 46262528997 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: 348467596 Data size: 46262528997 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: decimal(7,2)), _col3 (type: decimal(7,2)), _col4 (type: decimal(7,2)), _col5 (type: decimal(7,2)) + Reducer 11 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col2, _col3, _col4, _col5, _col9 + Statistics: Num rows: 383314363 Data size: 50888782999 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(_col2), sum(_col4), sum(_col3), sum(_col5) + keys: _col9 (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 383314363 Data size: 50888782999 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: 383314363 Data size: 50888782999 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: decimal(17,2)), _col2 (type: decimal(17,2)), _col3 (type: decimal(17,2)), _col4 (type: decimal(17,2)) + Reducer 12 + Reduce Operator Tree: + Group By Operator + aggregations: sum(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2), sum(VALUE._col3) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 191657181 Data size: 25444391433 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(17,2)), (_col3 - _col4) (type: decimal(18,2)) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 191657181 Data size: 25444391433 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: 2273797803 Data size: 251290313118 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: 2273797803 Data size: 251290313118 Basic stats: COMPLETE Column stats: NONE + TopN Hash Memory Usage: 0.1 + value expressions: _col3 (type: decimal(27,2)), _col4 (type: decimal(27,2)), _col5 (type: decimal(28,2)) + Reducer 17 + 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: _col0, _col2, _col3, _col4, _col5 + Statistics: Num rows: 332646173 Data size: 45230259363 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: _col2, _col3, _col4, _col5, _col9 + input vertices: + 1 Map 23 + Statistics: Num rows: 365910798 Data size: 49753286377 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(_col2), sum(_col4), sum(_col3), sum(_col5) + keys: _col9 (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 365910798 Data size: 49753286377 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: 365910798 Data size: 49753286377 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: decimal(17,2)), _col2 (type: decimal(17,2)), _col3 (type: decimal(17,2)), _col4 (type: decimal(17,2)) + Reducer 18 + Reduce Operator Tree: + Group By Operator + aggregations: sum(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2), sum(VALUE._col3) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 182955399 Data size: 24876643188 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(17,2)), (_col3 - _col4) (type: decimal(18,2)) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 182955399 Data size: 24876643188 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: 2273797803 Data size: 251290313118 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: 2273797803 Data size: 251290313118 Basic stats: COMPLETE Column stats: NONE + TopN Hash Memory Usage: 0.1 + value expressions: _col3 (type: decimal(27,2)), _col4 (type: decimal(27,2)), _col5 (type: decimal(28,2)) + Reducer 2 + 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: _col0, _col2, _col3, _col4, _col5 + Statistics: Num rows: 696945478 Data size: 60804367929 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: _col2, _col3, _col4, _col5, _col9 + input vertices: + 1 Map 8 + Statistics: Num rows: 766640042 Data size: 66884806171 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(_col2), sum(_col4), sum(_col3), sum(_col5) + keys: _col9 (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 766640042 Data size: 66884806171 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: 766640042 Data size: 66884806171 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: decimal(17,2)), _col2 (type: decimal(17,2)), _col3 (type: decimal(17,2)), _col4 (type: decimal(17,2)) + Reducer 20 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + outputColumnNames: _col1, _col3, _col6, _col7 + Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col1 (type: int), _col3 (type: int), 0 (type: decimal(7,2)), 0 (type: decimal(7,2)), _col6 (type: decimal(7,2)), _col7 (type: decimal(7,2)) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 158402938 Data size: 21538218500 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: 302405606 Data size: 41118416712 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int), _col2 (type: decimal(7,2)), _col3 (type: decimal(7,2)), _col4 (type: decimal(7,2)), _col5 (type: decimal(7,2)) + Reducer 3 + Reduce Operator Tree: + Group By Operator + aggregations: sum(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2), sum(VALUE._col3) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 383320021 Data size: 33442403085 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(17,2)), (_col3 - _col4) (type: decimal(18,2)) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 383320021 Data size: 33442403085 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: 2273797803 Data size: 251290313118 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: 2273797803 Data size: 251290313118 Basic stats: COMPLETE Column stats: NONE + TopN Hash Memory Usage: 0.1 + value expressions: _col3 (type: decimal(27,2)), _col4 (type: decimal(27,2)), _col5 (type: decimal(28,2)) + Reducer 4 + 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: 1136898901 Data size: 125645156503 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(27,2)), _col5 (type: decimal(28,2)) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 1136898901 Data size: 125645156503 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + sort order: ++ + Statistics: Num rows: 1136898901 Data size: 125645156503 Basic stats: COMPLETE Column stats: NONE + TopN Hash Memory Usage: 0.1 + value expressions: _col2 (type: decimal(27,2)), _col3 (type: decimal(27,2)), _col4 (type: decimal(28,2)) + Reducer 5 + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), VALUE._col0 (type: decimal(27,2)), VALUE._col1 (type: decimal(27,2)), VALUE._col2 (type: decimal(28,2)) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 1136898901 Data size: 125645156503 Basic stats: COMPLETE Column stats: NONE + Limit + Number of rows: 100 + Statistics: Num rows: 100 Data size: 11000 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 100 Data size: 11000 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/query50.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/spark/query50.q.out b/ql/src/test/results/clientpositive/perf/spark/query50.q.out new file mode 100644 index 0000000..fde0c4e --- /dev/null +++ b/ql/src/test/results/clientpositive/perf/spark/query50.q.out @@ -0,0 +1,333 @@ +PREHOOK: query: explain +select + s_store_name + ,s_company_id + ,s_street_number + ,s_street_name + ,s_street_type + ,s_suite_number + ,s_city + ,s_county + ,s_state + ,s_zip + ,sum(case when (sr_returned_date_sk - ss_sold_date_sk <= 30 ) then 1 else 0 end) as `30 days` + ,sum(case when (sr_returned_date_sk - ss_sold_date_sk > 30) and + (sr_returned_date_sk - ss_sold_date_sk <= 60) then 1 else 0 end ) as `31-60 days` + ,sum(case when (sr_returned_date_sk - ss_sold_date_sk > 60) and + (sr_returned_date_sk - ss_sold_date_sk <= 90) then 1 else 0 end) as `61-90 days` + ,sum(case when (sr_returned_date_sk - ss_sold_date_sk > 90) and + (sr_returned_date_sk - ss_sold_date_sk <= 120) then 1 else 0 end) as `91-120 days` + ,sum(case when (sr_returned_date_sk - ss_sold_date_sk > 120) then 1 else 0 end) as `>120 days` +from + store_sales + ,store_returns + ,store + ,date_dim d1 + ,date_dim d2 +where + d2.d_year = 2000 +and d2.d_moy = 9 +and ss_ticket_number = sr_ticket_number +and ss_item_sk = sr_item_sk +and ss_sold_date_sk = d1.d_date_sk +and sr_returned_date_sk = d2.d_date_sk +and ss_customer_sk = sr_customer_sk +and ss_store_sk = s_store_sk +group by + s_store_name + ,s_company_id + ,s_street_number + ,s_street_name + ,s_street_type + ,s_suite_number + ,s_city + ,s_county + ,s_state + ,s_zip +order by s_store_name + ,s_company_id + ,s_street_number + ,s_street_name + ,s_street_type + ,s_suite_number + ,s_city + ,s_county + ,s_state + ,s_zip +limit 100 +PREHOOK: type: QUERY +POSTHOOK: query: explain +select + s_store_name + ,s_company_id + ,s_street_number + ,s_street_name + ,s_street_type + ,s_suite_number + ,s_city + ,s_county + ,s_state + ,s_zip + ,sum(case when (sr_returned_date_sk - ss_sold_date_sk <= 30 ) then 1 else 0 end) as `30 days` + ,sum(case when (sr_returned_date_sk - ss_sold_date_sk > 30) and + (sr_returned_date_sk - ss_sold_date_sk <= 60) then 1 else 0 end ) as `31-60 days` + ,sum(case when (sr_returned_date_sk - ss_sold_date_sk > 60) and + (sr_returned_date_sk - ss_sold_date_sk <= 90) then 1 else 0 end) as `61-90 days` + ,sum(case when (sr_returned_date_sk - ss_sold_date_sk > 90) and + (sr_returned_date_sk - ss_sold_date_sk <= 120) then 1 else 0 end) as `91-120 days` + ,sum(case when (sr_returned_date_sk - ss_sold_date_sk > 120) then 1 else 0 end) as `>120 days` +from + store_sales + ,store_returns + ,store + ,date_dim d1 + ,date_dim d2 +where + d2.d_year = 2000 +and d2.d_moy = 9 +and ss_ticket_number = sr_ticket_number +and ss_item_sk = sr_item_sk +and ss_sold_date_sk = d1.d_date_sk +and sr_returned_date_sk = d2.d_date_sk +and ss_customer_sk = sr_customer_sk +and ss_store_sk = s_store_sk +group by + s_store_name + ,s_company_id + ,s_street_number + ,s_street_name + ,s_street_type + ,s_suite_number + ,s_city + ,s_county + ,s_state + ,s_zip +order by s_store_name + ,s_company_id + ,s_street_number + ,s_street_name + ,s_street_type + ,s_suite_number + ,s_city + ,s_county + ,s_state + ,s_zip +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 10 + 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_name (type: string), s_company_id (type: int), s_street_number (type: string), s_street_name (type: string), s_street_type (type: string), s_suite_number (type: string), s_city (type: string), s_county (type: string), s_state (type: string), s_zip (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 + Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Spark HashTable Sink Operator + keys: + 0 _col10 (type: int) + 1 _col0 (type: int) + Local Work: + Map Reduce Local Work + + Stage: Stage-1 + Spark + Edges: + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 36), Map 7 (PARTITION-LEVEL SORT, 36) + Reducer 3 <- Map 8 (PARTITION-LEVEL SORT, 436), Reducer 2 (PARTITION-LEVEL SORT, 436) + Reducer 4 <- Map 9 (PARTITION-LEVEL SORT, 438), Reducer 3 (PARTITION-LEVEL SORT, 438) + Reducer 5 <- Reducer 4 (GROUP, 529) + Reducer 6 <- Reducer 5 (SORT, 1) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: store_returns + Statistics: Num rows: 57591150 Data size: 4462194832 Basic stats: COMPLETE Column stats: NONE + Filter Operator + 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) (type: boolean) + Statistics: Num rows: 57591150 Data size: 4462194832 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: sr_returned_date_sk (type: int), sr_item_sk (type: int), sr_customer_sk (type: int), sr_ticket_number (type: int) + 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) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 57591150 Data size: 4462194832 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: int) + Map 7 + Map Operator Tree: + TableScan + alias: d2 + Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((d_moy = 9) and (d_year = 2000) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: d_date_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 18262 Data size: 20435178 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: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE + Map 8 + Map Operator Tree: + TableScan + alias: store_sales + Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (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) (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_customer_sk (type: int), ss_store_sk (type: int), ss_ticket_number (type: int) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col1 (type: int), _col2 (type: int), _col4 (type: int) + sort order: +++ + Map-reduce partition columns: _col1 (type: int), _col2 (type: int), _col4 (type: int) + Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int), _col3 (type: int) + Map 9 + Map Operator Tree: + TableScan + alias: d1 + Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: d_date_sk is not null (type: boolean) + Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: d_date_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 73049 Data size: 81741831 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: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Reducer 2 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 63350266 Data size: 4908414421 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col1 (type: int), _col2 (type: int), _col3 (type: int) + sort order: +++ + Map-reduce partition columns: _col1 (type: int), _col2 (type: int), _col3 (type: int) + Statistics: Num rows: 63350266 Data size: 4908414421 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int) + Reducer 3 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int), _col2 (type: int), _col3 (type: int) + 1 _col1 (type: int), _col2 (type: int), _col4 (type: int) + outputColumnNames: _col0, _col7, _col10 + Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col7 (type: int) + sort order: + + Map-reduce partition columns: _col7 (type: int) + Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int), _col10 (type: int) + Reducer 4 + Local Work: + Map Reduce Local Work + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col7 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0, _col7, _col10 + Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col10 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0, _col7, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23 + input vertices: + 1 Map 10 + Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col14 (type: string), _col15 (type: int), _col16 (type: string), _col17 (type: string), _col18 (type: string), _col19 (type: string), _col20 (type: string), _col21 (type: string), _col22 (type: string), _col23 (type: string), CASE WHEN (((_col0 - _col7) <= 30)) THEN (1) ELSE (0) END (type: int), CASE WHEN ((((_col0 - _col7) > 30) and ((_col0 - _col7) <= 60))) THEN (1) ELSE (0) END (type: int), CASE WHEN ((((_col0 - _col7) > 60) and ((_col0 - _col7) <= 90))) THEN (1) ELSE (0) END (type: int), CASE WHEN ((((_col0 - _col7) > 90) and ((_col0 - _col7) <= 120))) THEN (1) ELSE (0) END (type: int), CASE WHEN (((_col0 - _col7) > 120)) THEN (1) ELSE (0) END (type: int) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 + Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(_col10), sum(_col11), sum(_col12), sum(_col13), sum(_col14) + keys: _col0 (type: string), _col1 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string), _col7 (type: string), _col8 (type: string), _col9 (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 + Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string), _col7 (type: string), _col8 (type: string), _col9 (type: string) + sort order: ++++++++++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string), _col7 (type: string), _col8 (type: string), _col9 (type: string) + Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE + TopN Hash Memory Usage: 0.1 + value expressions: _col10 (type: bigint), _col11 (type: bigint), _col12 (type: bigint), _col13 (type: bigint), _col14 (type: bigint) + Reducer 5 + Reduce Operator Tree: + Group By Operator + aggregations: sum(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2), sum(VALUE._col3), sum(VALUE._col4) + keys: KEY._col0 (type: string), KEY._col1 (type: int), KEY._col2 (type: string), KEY._col3 (type: string), KEY._col4 (type: string), KEY._col5 (type: string), KEY._col6 (type: string), KEY._col7 (type: string), KEY._col8 (type: string), KEY._col9 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 + Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string), _col7 (type: string), _col8 (type: string), _col9 (type: string) + sort order: ++++++++++ + Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE + TopN Hash Memory Usage: 0.1 + value expressions: _col10 (type: bigint), _col11 (type: bigint), _col12 (type: bigint), _col13 (type: bigint), _col14 (type: bigint) + Reducer 6 + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: int), 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), VALUE._col0 (type: bigint), VALUE._col1 (type: bigint), VALUE._col2 (type: bigint), VALUE._col3 (type: bigint), VALUE._col4 (type: bigint) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 + Statistics: Num rows: 383325119 Data size: 33817053293 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 + http://git-wip-us.apache.org/repos/asf/hive/blob/bd371246/ql/src/test/results/clientpositive/perf/spark/query51.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/spark/query51.q.out b/ql/src/test/results/clientpositive/perf/spark/query51.q.out new file mode 100644 index 0000000..4a13589 --- /dev/null +++ b/ql/src/test/results/clientpositive/perf/spark/query51.q.out @@ -0,0 +1,383 @@ +PREHOOK: query: explain +WITH web_v1 as ( +select + ws_item_sk item_sk, d_date, + sum(sum(ws_sales_price)) + over (partition by ws_item_sk order by d_date rows between unbounded preceding and current row) cume_sales +from web_sales + ,date_dim +where ws_sold_date_sk=d_date_sk + and d_month_seq between 1212 and 1212+11 + and ws_item_sk is not NULL +group by ws_item_sk, d_date), +store_v1 as ( +select + ss_item_sk item_sk, d_date, + sum(sum(ss_sales_price)) + over (partition by ss_item_sk order by d_date rows between unbounded preceding and current row) cume_sales +from store_sales + ,date_dim +where ss_sold_date_sk=d_date_sk + and d_month_seq between 1212 and 1212+11 + and ss_item_sk is not NULL +group by ss_item_sk, d_date) + select * +from (select item_sk + ,d_date + ,web_sales + ,store_sales + ,max(web_sales) + over (partition by item_sk order by d_date rows between unbounded preceding and current row) web_cumulative + ,max(store_sales) + over (partition by item_sk order by d_date rows between unbounded preceding and current row) store_cumulative + from (select case when web.item_sk is not null then web.item_sk else store.item_sk end item_sk + ,case when web.d_date is not null then web.d_date else store.d_date end d_date + ,web.cume_sales web_sales + ,store.cume_sales store_sales + from web_v1 web full outer join store_v1 store on (web.item_sk = store.item_sk + and web.d_date = store.d_date) + )x )y +where web_cumulative > store_cumulative +order by item_sk + ,d_date +limit 100 +PREHOOK: type: QUERY +POSTHOOK: query: explain +WITH web_v1 as ( +select + ws_item_sk item_sk, d_date, + sum(sum(ws_sales_price)) + over (partition by ws_item_sk order by d_date rows between unbounded preceding and current row) cume_sales +from web_sales + ,date_dim +where ws_sold_date_sk=d_date_sk + and d_month_seq between 1212 and 1212+11 + and ws_item_sk is not NULL +group by ws_item_sk, d_date), +store_v1 as ( +select + ss_item_sk item_sk, d_date, + sum(sum(ss_sales_price)) + over (partition by ss_item_sk order by d_date rows between unbounded preceding and current row) cume_sales +from store_sales + ,date_dim +where ss_sold_date_sk=d_date_sk + and d_month_seq between 1212 and 1212+11 + and ss_item_sk is not NULL +group by ss_item_sk, d_date) + select * +from (select item_sk + ,d_date + ,web_sales + ,store_sales + ,max(web_sales) + over (partition by item_sk order by d_date rows between unbounded preceding and current row) web_cumulative + ,max(store_sales) + over (partition by item_sk order by d_date rows between unbounded preceding and current row) store_cumulative + from (select case when web.item_sk is not null then web.item_sk else store.item_sk end item_sk + ,case when web.d_date is not null then web.d_date else store.d_date end d_date + ,web.cume_sales web_sales + ,store.cume_sales store_sales + from web_v1 web full outer join store_v1 store on (web.item_sk = store.item_sk + and web.d_date = store.d_date) + )x )y +where web_cumulative > store_cumulative +order by item_sk + ,d_date +limit 100 +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-2 is a root stage + Stage-3 depends on stages: Stage-2 + Stage-1 depends on stages: Stage-3 + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-2 + Spark +#### A masked pattern was here #### + Vertices: + Map 6 + Map Operator Tree: + TableScan + alias: date_dim + Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (d_date_sk is not null and d_month_seq BETWEEN 1212 AND 1223) (type: boolean) + Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: d_date_sk (type: int), d_date (type: string) + outputColumnNames: _col0, _col1 + 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-3 + Spark +#### A masked pattern was here #### + Vertices: + Map 9 + Map Operator Tree: + TableScan + alias: date_dim + Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (d_date_sk is not null and d_month_seq BETWEEN 1212 AND 1223) (type: boolean) + Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: d_date_sk (type: int), d_date (type: string) + outputColumnNames: _col0, _col1 + 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 (GROUP PARTITION-LEVEL SORT, 437) + Reducer 3 <- Reducer 2 (PARTITION-LEVEL SORT, 303), Reducer 8 (PARTITION-LEVEL SORT, 303) + Reducer 4 <- Reducer 3 (PARTITION-LEVEL SORT, 241) + Reducer 5 <- Reducer 4 (SORT, 1) + Reducer 8 <- Map 7 (GROUP PARTITION-LEVEL SORT, 169) +#### 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_sold_date_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_sales_price (type: decimal(7,2)) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 575995635 Data size: 50814502088 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, _col4 + input vertices: + 1 Map 6 + Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(_col2) + keys: _col1 (type: int), _col4 (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: decimal(17,2)) + Local Work: + Map Reduce Local Work + Map 7 + 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_sold_date_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_sales_price (type: decimal(7,2)) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 144002668 Data size: 19580198212 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, _col4 + input vertices: + 1 Map 9 + Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(_col2) + keys: _col1 (type: int), _col4 (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: decimal(17,2)) + Local Work: + Map Reduce Local Work + Reducer 2 + Reduce Operator Tree: + Group By Operator + aggregations: sum(VALUE._col0) + keys: KEY._col0 (type: int), KEY._col1 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 316797606 Data size: 27947976754 Basic stats: COMPLETE Column stats: NONE + PTF Operator + Function definitions: + Input definition + input alias: ptf_0 + output shape: _col0: int, _col1: string, _col2: decimal(17,2) + type: WINDOWING + Windowing table definition + input alias: ptf_1 + name: windowingtablefunction + order by: _col1 ASC NULLS FIRST + partition by: _col0 + raw input shape: + window functions: + window function definition + alias: sum_window_0 + arguments: _col2 + name: sum + window function: GenericUDAFSumHiveDecimal + window frame: ROWS PRECEDING(MAX)~CURRENT + Statistics: Num rows: 316797606 Data size: 27947976754 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: int), _col1 (type: string), sum_window_0 (type: decimal(27,2)) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 316797606 Data size: 27947976754 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: int), _col1 (type: string) + Statistics: Num rows: 316797606 Data size: 27947976754 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: decimal(27,2)) + Reducer 3 + Reduce Operator Tree: + Join Operator + condition map: + Outer Join 0 to 1 + keys: + 0 _col0 (type: int), _col1 (type: string) + 1 _col0 (type: int), _col1 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: CASE WHEN (_col3 is not null) THEN (_col3) ELSE (_col0) END (type: int), CASE WHEN (_col4 is not null) THEN (_col4) ELSE (_col1) END (type: string) + sort order: ++ + Map-reduce partition columns: CASE WHEN (_col3 is not null) THEN (_col3) ELSE (_col0) END (type: int) + Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: decimal(27,2)), _col3 (type: int), _col4 (type: string), _col5 (type: decimal(27,2)) + Reducer 4 + Reduce Operator Tree: + Select Operator + expressions: VALUE._col0 (type: int), VALUE._col1 (type: string), VALUE._col2 (type: decimal(27,2)), VALUE._col3 (type: int), VALUE._col4 (type: string), VALUE._col5 (type: decimal(27,2)) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE + PTF Operator + Function definitions: + Input definition + input alias: ptf_0 + output shape: _col0: int, _col1: string, _col2: decimal(27,2), _col3: int, _col4: string, _col5: decimal(27,2) + type: WINDOWING + Windowing table definition + input alias: ptf_1 + name: windowingtablefunction + order by: CASE WHEN (_col4 is not null) THEN (_col4) ELSE (_col1) END ASC NULLS FIRST + partition by: CASE WHEN (_col3 is not null) THEN (_col3) ELSE (_col0) END + raw input shape: + window functions: + window function definition + alias: max_window_0 + arguments: _col5 + name: max + window function: GenericUDAFMaxEvaluator + window frame: ROWS PRECEDING(MAX)~CURRENT + window function definition + alias: max_window_1 + arguments: _col2 + name: max + window function: GenericUDAFMaxEvaluator + window frame: ROWS PRECEDING(MAX)~CURRENT + Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (max_window_0 > max_window_1) (type: boolean) + Statistics: Num rows: 116159124 Data size: 10247591639 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: CASE WHEN (_col3 is not null) THEN (_col3) ELSE (_col0) END (type: int), CASE WHEN (_col4 is not null) THEN (_col4) ELSE (_col1) END (type: string), _col5 (type: decimal(27,2)), _col2 (type: decimal(27,2)), max_window_0 (type: decimal(27,2)), max_window_1 (type: decimal(27,2)) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 116159124 Data size: 10247591639 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: string) + sort order: ++ + Statistics: Num rows: 116159124 Data size: 10247591639 Basic stats: COMPLETE Column stats: NONE + TopN Hash Memory Usage: 0.1 + value expressions: _col2 (type: decimal(27,2)), _col3 (type: decimal(27,2)), _col4 (type: decimal(27,2)), _col5 (type: decimal(27,2)) + Reducer 5 + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string), VALUE._col0 (type: decimal(27,2)), VALUE._col1 (type: decimal(27,2)), VALUE._col2 (type: decimal(27,2)), VALUE._col3 (type: decimal(27,2)) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 116159124 Data size: 10247591639 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 + Reducer 8 + Reduce Operator Tree: + Group By Operator + aggregations: sum(VALUE._col0) + keys: KEY._col0 (type: int), KEY._col1 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 79201469 Data size: 10769109250 Basic stats: COMPLETE Column stats: NONE + PTF Operator + Function definitions: + Input definition + input alias: ptf_0 + output shape: _col0: int, _col1: string, _col2: decimal(17,2) + type: WINDOWING + Windowing table definition + input alias: ptf_1 + name: windowingtablefunction + order by: _col1 ASC NULLS FIRST + partition by: _col0 + raw input shape: + window functions: + window function definition + alias: sum_window_0 + arguments: _col2 + name: sum + window function: GenericUDAFSumHiveDecimal + window frame: ROWS PRECEDING(MAX)~CURRENT + Statistics: Num rows: 79201469 Data size: 10769109250 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: int), _col1 (type: string), sum_window_0 (type: decimal(27,2)) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 79201469 Data size: 10769109250 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: int), _col1 (type: string) + Statistics: Num rows: 79201469 Data size: 10769109250 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: decimal(27,2)) + + Stage: Stage-0 + Fetch Operator + limit: 100 + Processor Tree: + ListSink +