Repository: hive Updated Branches: refs/heads/master 365c03107 -> bd371246e
http://git-wip-us.apache.org/repos/asf/hive/blob/bd371246/ql/src/test/results/clientpositive/perf/spark/query97.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/spark/query97.q.out b/ql/src/test/results/clientpositive/perf/spark/query97.q.out new file mode 100644 index 0000000..14a2aed --- /dev/null +++ b/ql/src/test/results/clientpositive/perf/spark/query97.q.out @@ -0,0 +1,250 @@ +PREHOOK: query: explain +with ssci as ( +select ss_customer_sk customer_sk + ,ss_item_sk item_sk +from store_sales,date_dim +where ss_sold_date_sk = d_date_sk + and d_month_seq between 1212 and 1212 + 11 +group by ss_customer_sk + ,ss_item_sk), +csci as( + select cs_bill_customer_sk customer_sk + ,cs_item_sk item_sk +from catalog_sales,date_dim +where cs_sold_date_sk = d_date_sk + and d_month_seq between 1212 and 1212 + 11 +group by cs_bill_customer_sk + ,cs_item_sk) + select sum(case when ssci.customer_sk is not null and csci.customer_sk is null then 1 else 0 end) store_only + ,sum(case when ssci.customer_sk is null and csci.customer_sk is not null then 1 else 0 end) catalog_only + ,sum(case when ssci.customer_sk is not null and csci.customer_sk is not null then 1 else 0 end) store_and_catalog +from ssci full outer join csci on (ssci.customer_sk=csci.customer_sk + and ssci.item_sk = csci.item_sk) +limit 100 +PREHOOK: type: QUERY +POSTHOOK: query: explain +with ssci as ( +select ss_customer_sk customer_sk + ,ss_item_sk item_sk +from store_sales,date_dim +where ss_sold_date_sk = d_date_sk + and d_month_seq between 1212 and 1212 + 11 +group by ss_customer_sk + ,ss_item_sk), +csci as( + select cs_bill_customer_sk customer_sk + ,cs_item_sk item_sk +from catalog_sales,date_dim +where cs_sold_date_sk = d_date_sk + and d_month_seq between 1212 and 1212 + 11 +group by cs_bill_customer_sk + ,cs_item_sk) + select sum(case when ssci.customer_sk is not null and csci.customer_sk is null then 1 else 0 end) store_only + ,sum(case when ssci.customer_sk is null and csci.customer_sk is not null then 1 else 0 end) catalog_only + ,sum(case when ssci.customer_sk is not null and csci.customer_sk is not null then 1 else 0 end) store_and_catalog +from ssci full outer join csci on (ssci.customer_sk=csci.customer_sk + and ssci.item_sk = csci.item_sk) +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 5 + 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) + 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-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: (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) + 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 (GROUP, 437) + Reducer 3 <- Reducer 2 (PARTITION-LEVEL SORT, 386), Reducer 7 (PARTITION-LEVEL SORT, 386) + Reducer 4 <- Reducer 3 (GROUP, 1) + Reducer 7 <- Map 6 (GROUP, 336) +#### 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 (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) + 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 + input vertices: + 1 Map 5 + Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE + Group By Operator + keys: _col2 (type: int), _col1 (type: int) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 633595212 Data size: 55895953508 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: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE + Local Work: + Map Reduce Local Work + Map 6 + Map Operator Tree: + TableScan + alias: catalog_sales + Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: 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_bill_customer_sk (type: int), cs_item_sk (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 287989836 Data size: 38999608952 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 + input vertices: + 1 Map 8 + Statistics: Num rows: 316788826 Data size: 42899570777 Basic stats: COMPLETE Column stats: NONE + Group By Operator + keys: _col1 (type: int), _col2 (type: int) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 316788826 Data size: 42899570777 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: 316788826 Data size: 42899570777 Basic stats: COMPLETE Column stats: NONE + Local Work: + Map Reduce Local Work + Reducer 2 + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: int), KEY._col1 (type: int) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 316797606 Data size: 27947976754 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: 316797606 Data size: 27947976754 Basic stats: COMPLETE Column stats: NONE + Reducer 3 + Reduce Operator Tree: + Join Operator + condition map: + Outer Join 0 to 1 + keys: + 0 _col0 (type: int), _col1 (type: int) + 1 _col0 (type: int), _col1 (type: int) + outputColumnNames: _col0, _col2 + Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: CASE WHEN ((_col0 is not null and _col2 is null)) THEN (1) ELSE (0) END (type: int), CASE WHEN ((_col0 is null and _col2 is not null)) THEN (1) ELSE (0) END (type: int), CASE WHEN ((_col0 is not null and _col2 is not null)) THEN (1) ELSE (0) END (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(_col0), sum(_col1), sum(_col2) + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE + TopN Hash Memory Usage: 0.1 + value expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: bigint) + Reducer 4 + Reduce Operator Tree: + Group By Operator + aggregations: sum(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Limit + Number of rows: 100 + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 24 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: + Group By Operator + keys: KEY._col0 (type: int), KEY._col1 (type: int) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 158394413 Data size: 21449785388 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: 158394413 Data size: 21449785388 Basic stats: COMPLETE Column stats: NONE + + 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/query98.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/spark/query98.q.out b/ql/src/test/results/clientpositive/perf/spark/query98.q.out new file mode 100644 index 0000000..24d7de8 --- /dev/null +++ b/ql/src/test/results/clientpositive/perf/spark/query98.q.out @@ -0,0 +1,243 @@ +PREHOOK: query: explain +select i_item_desc + ,i_category + ,i_class + ,i_current_price + ,sum(ss_ext_sales_price) as itemrevenue + ,sum(ss_ext_sales_price)*100/sum(sum(ss_ext_sales_price)) over + (partition by i_class) as revenueratio +from + store_sales + ,item + ,date_dim +where + ss_item_sk = i_item_sk + and i_category in ('Jewelry', 'Sports', 'Books') + and ss_sold_date_sk = d_date_sk + and d_date between cast('2001-01-12' as date) + and (cast('2001-01-12' as date) + 30 days) +group by + i_item_id + ,i_item_desc + ,i_category + ,i_class + ,i_current_price +order by + i_category + ,i_class + ,i_item_id + ,i_item_desc + ,revenueratio +PREHOOK: type: QUERY +POSTHOOK: query: explain +select i_item_desc + ,i_category + ,i_class + ,i_current_price + ,sum(ss_ext_sales_price) as itemrevenue + ,sum(ss_ext_sales_price)*100/sum(sum(ss_ext_sales_price)) over + (partition by i_class) as revenueratio +from + store_sales + ,item + ,date_dim +where + ss_item_sk = i_item_sk + and i_category in ('Jewelry', 'Sports', 'Books') + and ss_sold_date_sk = d_date_sk + and d_date between cast('2001-01-12' as date) + and (cast('2001-01-12' as date) + 30 days) +group by + i_item_id + ,i_item_desc + ,i_category + ,i_class + ,i_current_price +order by + i_category + ,i_class + ,i_item_id + ,i_item_desc + ,revenueratio +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 6 + 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 2001-01-12 00:00:00.0 AND 2001-02-11 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, 440), Map 7 (PARTITION-LEVEL SORT, 440) + Reducer 3 <- Reducer 2 (GROUP, 481) + Reducer 4 <- Reducer 3 (PARTITION-LEVEL SORT, 241) + 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_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_ext_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 + input vertices: + 1 Map 6 + Statistics: Num rows: 633595212 Data size: 55895953508 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: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: decimal(7,2)) + Local Work: + Map Reduce Local Work + Map 7 + Map Operator Tree: + TableScan + alias: item + Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((i_category) IN ('Jewelry', 'Sports', 'Books') and i_item_sk is not null) (type: boolean) + Statistics: Num rows: 231000 Data size: 331780228 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)), i_class (type: string), i_category (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 231000 Data size: 331780228 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: 231000 Data size: 331780228 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: decimal(7,2)), _col4 (type: string), _col5 (type: string) + Reducer 2 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col2, _col6, _col7, _col8, _col9, _col10 + Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(_col2) + keys: _col10 (type: string), _col9 (type: string), _col6 (type: string), _col7 (type: string), _col8 (type: decimal(7,2)) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 696954748 Data size: 61485550191 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: decimal(7,2)) + sort order: +++++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: decimal(7,2)) + Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE + value expressions: _col5 (type: decimal(17,2)) + Reducer 3 + Reduce Operator Tree: + Group By Operator + aggregations: sum(VALUE._col0) + keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string), KEY._col3 (type: string), KEY._col4 (type: decimal(7,2)) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col2 (type: string), _col3 (type: string), _col0 (type: string), _col1 (type: string), _col4 (type: decimal(7,2)), _col5 (type: decimal(17,2)) + 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: _col3 (type: string) + sort order: + + Map-reduce partition columns: _col3 (type: string) + Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col4 (type: decimal(7,2)), _col5 (type: decimal(17,2)) + Reducer 4 + Reduce Operator Tree: + Select Operator + expressions: VALUE._col0 (type: string), VALUE._col1 (type: string), VALUE._col2 (type: string), KEY.reducesinkkey0 (type: string), VALUE._col3 (type: decimal(7,2)), VALUE._col4 (type: decimal(17,2)) + 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: string, _col1: string, _col2: string, _col3: string, _col4: decimal(7,2), _col5: decimal(17,2) + type: WINDOWING + Windowing table definition + input alias: ptf_1 + name: windowingtablefunction + order by: _col3 ASC NULLS FIRST + partition by: _col3 + raw input shape: + window functions: + window function definition + alias: sum_window_0 + arguments: _col5 + name: sum + window function: GenericUDAFSumHiveDecimal + window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) + Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: decimal(7,2)), _col5 (type: decimal(17,2)), ((_col5 * 100) / sum_window_0) (type: decimal(38,17)), _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 + Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col1 (type: string), _col2 (type: string), _col6 (type: string), _col0 (type: string), _col5 (type: decimal(38,17)) + sort order: +++++ + Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE + value expressions: _col3 (type: decimal(7,2)), _col4 (type: decimal(17,2)) + Reducer 5 + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey3 (type: string), KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), VALUE._col0 (type: decimal(7,2)), VALUE._col1 (type: decimal(17,2)), KEY.reducesinkkey4 (type: decimal(38,17)) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 348477374 Data size: 30742775095 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: -1 + Processor Tree: + ListSink + http://git-wip-us.apache.org/repos/asf/hive/blob/bd371246/ql/src/test/results/clientpositive/perf/spark/query99.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/spark/query99.q.out b/ql/src/test/results/clientpositive/perf/spark/query99.q.out new file mode 100644 index 0000000..c0c5f13 --- /dev/null +++ b/ql/src/test/results/clientpositive/perf/spark/query99.q.out @@ -0,0 +1,270 @@ +PREHOOK: query: explain +select + substr(w_warehouse_name,1,20) + ,sm_type + ,cc_name + ,sum(case when (cs_ship_date_sk - cs_sold_date_sk <= 30 ) then 1 else 0 end) as `30 days` + ,sum(case when (cs_ship_date_sk - cs_sold_date_sk > 30) and + (cs_ship_date_sk - cs_sold_date_sk <= 60) then 1 else 0 end ) as `31-60 days` + ,sum(case when (cs_ship_date_sk - cs_sold_date_sk > 60) and + (cs_ship_date_sk - cs_sold_date_sk <= 90) then 1 else 0 end) as `61-90 days` + ,sum(case when (cs_ship_date_sk - cs_sold_date_sk > 90) and + (cs_ship_date_sk - cs_sold_date_sk <= 120) then 1 else 0 end) as `91-120 days` + ,sum(case when (cs_ship_date_sk - cs_sold_date_sk > 120) then 1 else 0 end) as `>120 days` +from + catalog_sales + ,warehouse + ,ship_mode + ,call_center + ,date_dim +where + d_month_seq between 1212 and 1212 + 11 +and cs_ship_date_sk = d_date_sk +and cs_warehouse_sk = w_warehouse_sk +and cs_ship_mode_sk = sm_ship_mode_sk +and cs_call_center_sk = cc_call_center_sk +group by + substr(w_warehouse_name,1,20) + ,sm_type + ,cc_name +order by substr(w_warehouse_name,1,20) + ,sm_type + ,cc_name +limit 100 +PREHOOK: type: QUERY +POSTHOOK: query: explain +select + substr(w_warehouse_name,1,20) + ,sm_type + ,cc_name + ,sum(case when (cs_ship_date_sk - cs_sold_date_sk <= 30 ) then 1 else 0 end) as `30 days` + ,sum(case when (cs_ship_date_sk - cs_sold_date_sk > 30) and + (cs_ship_date_sk - cs_sold_date_sk <= 60) then 1 else 0 end ) as `31-60 days` + ,sum(case when (cs_ship_date_sk - cs_sold_date_sk > 60) and + (cs_ship_date_sk - cs_sold_date_sk <= 90) then 1 else 0 end) as `61-90 days` + ,sum(case when (cs_ship_date_sk - cs_sold_date_sk > 90) and + (cs_ship_date_sk - cs_sold_date_sk <= 120) then 1 else 0 end) as `91-120 days` + ,sum(case when (cs_ship_date_sk - cs_sold_date_sk > 120) then 1 else 0 end) as `>120 days` +from + catalog_sales + ,warehouse + ,ship_mode + ,call_center + ,date_dim +where + d_month_seq between 1212 and 1212 + 11 +and cs_ship_date_sk = d_date_sk +and cs_warehouse_sk = w_warehouse_sk +and cs_ship_mode_sk = sm_ship_mode_sk +and cs_call_center_sk = cc_call_center_sk +group by + substr(w_warehouse_name,1,20) + ,sm_type + ,cc_name +order by substr(w_warehouse_name,1,20) + ,sm_type + ,cc_name +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 4 + 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) + outputColumnNames: _col0 + Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE + Spark HashTable Sink Operator + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + Local Work: + Map Reduce Local Work + Map 5 + Map Operator Tree: + TableScan + alias: call_center + Statistics: Num rows: 60 Data size: 122700 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: cc_call_center_sk is not null (type: boolean) + Statistics: Num rows: 60 Data size: 122700 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: cc_call_center_sk (type: int), cc_name (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 60 Data size: 122700 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 + Map 6 + Map Operator Tree: + TableScan + alias: warehouse + Statistics: Num rows: 27 Data size: 27802 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: w_warehouse_sk is not null (type: boolean) + Statistics: Num rows: 27 Data size: 27802 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: w_warehouse_sk (type: int), w_warehouse_name (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 27 Data size: 27802 Basic stats: COMPLETE Column stats: NONE + Spark HashTable Sink Operator + keys: + 0 _col4 (type: int) + 1 _col0 (type: int) + Local Work: + Map Reduce Local Work + Map 7 + Map Operator Tree: + TableScan + alias: ship_mode + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Filter Operator + predicate: sm_ship_mode_sk is not null (type: boolean) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Select Operator + expressions: sm_ship_mode_sk (type: int), sm_type (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Spark HashTable Sink Operator + keys: + 0 _col3 (type: int) + 1 _col0 (type: int) + Local Work: + Map Reduce Local Work + + Stage: Stage-1 + Spark + Edges: + Reducer 2 <- Map 1 (GROUP, 447) + Reducer 3 <- Reducer 2 (SORT, 1) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: catalog_sales + Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (cs_call_center_sk is not null and cs_ship_date_sk is not null and cs_ship_mode_sk is not null and cs_warehouse_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_ship_date_sk (type: int), cs_call_center_sk (type: int), cs_ship_mode_sk (type: int), cs_warehouse_sk (type: int) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + input vertices: + 1 Map 4 + 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 _col2 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0, _col1, _col3, _col4, _col8 + input vertices: + 1 Map 5 + Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col4 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0, _col1, _col3, _col8, _col10 + input vertices: + 1 Map 6 + 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: _col0, _col1, _col8, _col10, _col12 + input vertices: + 1 Map 7 + Statistics: Num rows: 421645953 Data size: 57099332415 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: substr(_col10, 1, 20) (type: string), _col12 (type: string), _col8 (type: string), CASE WHEN (((_col1 - _col0) <= 30)) THEN (1) ELSE (0) END (type: int), CASE WHEN ((((_col1 - _col0) > 30) and ((_col1 - _col0) <= 60))) THEN (1) ELSE (0) END (type: int), CASE WHEN ((((_col1 - _col0) > 60) and ((_col1 - _col0) <= 90))) THEN (1) ELSE (0) END (type: int), CASE WHEN ((((_col1 - _col0) > 90) and ((_col1 - _col0) <= 120))) THEN (1) ELSE (0) END (type: int), CASE WHEN (((_col1 - _col0) > 120)) THEN (1) ELSE (0) END (type: int) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 + Statistics: Num rows: 421645953 Data size: 57099332415 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(_col3), sum(_col4), sum(_col5), sum(_col6), sum(_col7) + keys: _col0 (type: string), _col1 (type: string), _col2 (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 + Statistics: Num rows: 421645953 Data size: 57099332415 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) + sort order: +++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string) + Statistics: Num rows: 421645953 Data size: 57099332415 Basic stats: COMPLETE Column stats: NONE + TopN Hash Memory Usage: 0.1 + value expressions: _col3 (type: bigint), _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: bigint) + Local Work: + Map Reduce Local Work + Reducer 2 + 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: string), KEY._col2 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 + Statistics: Num rows: 210822976 Data size: 28549666139 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col1 (type: string), _col2 (type: string), _col3 (type: bigint), _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: bigint), _col0 (type: string) + outputColumnNames: _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + Statistics: Num rows: 210822976 Data size: 28549666139 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col8 (type: string), _col1 (type: string), _col2 (type: string) + sort order: +++ + Statistics: Num rows: 210822976 Data size: 28549666139 Basic stats: COMPLETE Column stats: NONE + TopN Hash Memory Usage: 0.1 + value expressions: _col3 (type: bigint), _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: bigint) + Reducer 3 + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (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 + Statistics: Num rows: 210822976 Data size: 28549666139 Basic stats: COMPLETE Column stats: NONE + Limit + Number of rows: 100 + Statistics: Num rows: 100 Data size: 13500 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 100 Data size: 13500 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: -1 + Processor Tree: + ListSink +
