You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by se...@apache.org on 2017/09/29 03:36:00 UTC
[09/48] hive git commit: HIVE-17543: Enable PerfCliDriver for HoS
(Sahil Takiar, reviewed by Peter Vary)
http://git-wip-us.apache.org/repos/asf/hive/blob/bd371246/ql/src/test/results/clientpositive/perf/spark/query86.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/perf/spark/query86.q.out b/ql/src/test/results/clientpositive/perf/spark/query86.q.out
new file mode 100644
index 0000000..c5b25e8
--- /dev/null
+++ b/ql/src/test/results/clientpositive/perf/spark/query86.q.out
@@ -0,0 +1,240 @@
+PREHOOK: query: explain
+select
+ sum(ws_net_paid) as total_sum
+ ,i_category
+ ,i_class
+ ,grouping(i_category)+grouping(i_class) as lochierarchy
+ ,rank() over (
+ partition by grouping(i_category)+grouping(i_class),
+ case when grouping(i_class) = 0 then i_category end
+ order by sum(ws_net_paid) desc) as rank_within_parent
+ from
+ web_sales
+ ,date_dim d1
+ ,item
+ where
+ d1.d_month_seq between 1212 and 1212+11
+ and d1.d_date_sk = ws_sold_date_sk
+ and i_item_sk = ws_item_sk
+ group by rollup(i_category,i_class)
+ order by
+ lochierarchy desc,
+ case when lochierarchy = 0 then i_category end,
+ rank_within_parent
+ limit 100
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+select
+ sum(ws_net_paid) as total_sum
+ ,i_category
+ ,i_class
+ ,grouping(i_category)+grouping(i_class) as lochierarchy
+ ,rank() over (
+ partition by grouping(i_category)+grouping(i_class),
+ case when grouping(i_class) = 0 then i_category end
+ order by sum(ws_net_paid) desc) as rank_within_parent
+ from
+ web_sales
+ ,date_dim d1
+ ,item
+ where
+ d1.d_month_seq between 1212 and 1212+11
+ and d1.d_date_sk = ws_sold_date_sk
+ and i_item_sk = ws_item_sk
+ group by rollup(i_category,i_class)
+ order by
+ lochierarchy desc,
+ case when lochierarchy = 0 then i_category end,
+ rank_within_parent
+ 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 6
+ 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 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 (PARTITION-LEVEL SORT, 174), Map 7 (PARTITION-LEVEL SORT, 174)
+ Reducer 3 <- Reducer 2 (GROUP, 556)
+ Reducer 4 <- Reducer 3 (PARTITION-LEVEL SORT, 278)
+ Reducer 5 <- Reducer 4 (SORT, 1)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ 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_net_paid (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
+ input vertices:
+ 1 Map 6
+ 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: 158402938 Data size: 21538218500 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_item_sk is not null (type: boolean)
+ Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: i_item_sk (type: int), i_class (type: string), i_category (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 462000 Data size: 663560457 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: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: string), _col2 (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
+ Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col7 (type: string), _col6 (type: string), _col2 (type: decimal(7,2))
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: sum(_col2)
+ keys: _col0 (type: string), _col1 (type: string), 0 (type: int)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 522729705 Data size: 71076122589 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: 522729705 Data size: 71076122589 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col3 (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: int)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 261364852 Data size: 35538061226 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string), _col3 (type: decimal(17,2)), _col2 (type: int)
+ outputColumnNames: _col0, _col1, _col4, _col5
+ Statistics: Num rows: 261364852 Data size: 35538061226 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: (grouping(_col5, 1) + grouping(_col5, 0)) (type: int), CASE WHEN ((grouping(_col5, 0) = 0)) THEN (_col0) ELSE (null) END (type: string), _col4 (type: decimal(17,2))
+ sort order: ++-
+ Map-reduce partition columns: (grouping(_col5, 1) + grouping(_col5, 0)) (type: int), CASE WHEN ((grouping(_col5, 0) = 0)) THEN (_col0) ELSE (null) END (type: string)
+ Statistics: Num rows: 261364852 Data size: 35538061226 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: string), _col1 (type: string), _col5 (type: int)
+ Reducer 4
+ Reduce Operator Tree:
+ Select Operator
+ expressions: VALUE._col0 (type: string), VALUE._col1 (type: string), KEY.reducesinkkey2 (type: decimal(17,2)), VALUE._col2 (type: int)
+ outputColumnNames: _col0, _col1, _col4, _col5
+ Statistics: Num rows: 261364852 Data size: 35538061226 Basic stats: COMPLETE Column stats: NONE
+ PTF Operator
+ Function definitions:
+ Input definition
+ input alias: ptf_0
+ output shape: _col0: string, _col1: string, _col4: decimal(17,2), _col5: int
+ type: WINDOWING
+ Windowing table definition
+ input alias: ptf_1
+ name: windowingtablefunction
+ order by: _col4 DESC NULLS LAST
+ partition by: (grouping(_col5, 1) + grouping(_col5, 0)), CASE WHEN ((grouping(_col5, 0) = 0)) THEN (_col0) ELSE (null) END
+ raw input shape:
+ window functions:
+ window function definition
+ alias: rank_window_0
+ arguments: _col4
+ name: rank
+ window function: GenericUDAFRankEvaluator
+ window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX)
+ isPivotResult: true
+ Statistics: Num rows: 261364852 Data size: 35538061226 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col4 (type: decimal(17,2)), _col0 (type: string), _col1 (type: string), (grouping(_col5, 1) + grouping(_col5, 0)) (type: int), rank_window_0 (type: int), CASE WHEN (((grouping(_col5, 1) + grouping(_col5, 0)) = 0)) THEN (_col0) ELSE (null) END (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
+ Statistics: Num rows: 261364852 Data size: 35538061226 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col3 (type: int), _col5 (type: string), _col4 (type: int)
+ sort order: -++
+ Statistics: Num rows: 261364852 Data size: 35538061226 Basic stats: COMPLETE Column stats: NONE
+ TopN Hash Memory Usage: 0.1
+ value expressions: _col0 (type: decimal(17,2)), _col1 (type: string), _col2 (type: string)
+ Reducer 5
+ Reduce Operator Tree:
+ Select Operator
+ expressions: VALUE._col0 (type: decimal(17,2)), VALUE._col1 (type: string), VALUE._col2 (type: string), KEY.reducesinkkey0 (type: int), KEY.reducesinkkey2 (type: int)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Statistics: Num rows: 261364852 Data size: 35538061226 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
+
http://git-wip-us.apache.org/repos/asf/hive/blob/bd371246/ql/src/test/results/clientpositive/perf/spark/query87.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/perf/spark/query87.q.out b/ql/src/test/results/clientpositive/perf/spark/query87.q.out
new file mode 100644
index 0000000..5fe3e48
--- /dev/null
+++ b/ql/src/test/results/clientpositive/perf/spark/query87.q.out
@@ -0,0 +1,500 @@
+PREHOOK: query: explain
+select count(*)
+from ((select distinct c_last_name, c_first_name, d_date
+ from store_sales, date_dim, customer
+ where store_sales.ss_sold_date_sk = date_dim.d_date_sk
+ and store_sales.ss_customer_sk = customer.c_customer_sk
+ and d_month_seq between 1212 and 1212+11)
+ except
+ (select distinct c_last_name, c_first_name, d_date
+ from catalog_sales, date_dim, customer
+ where catalog_sales.cs_sold_date_sk = date_dim.d_date_sk
+ and catalog_sales.cs_bill_customer_sk = customer.c_customer_sk
+ and d_month_seq between 1212 and 1212+11)
+ except
+ (select distinct c_last_name, c_first_name, d_date
+ from web_sales, date_dim, customer
+ where web_sales.ws_sold_date_sk = date_dim.d_date_sk
+ and web_sales.ws_bill_customer_sk = customer.c_customer_sk
+ and d_month_seq between 1212 and 1212+11)
+) cool_cust
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+select count(*)
+from ((select distinct c_last_name, c_first_name, d_date
+ from store_sales, date_dim, customer
+ where store_sales.ss_sold_date_sk = date_dim.d_date_sk
+ and store_sales.ss_customer_sk = customer.c_customer_sk
+ and d_month_seq between 1212 and 1212+11)
+ except
+ (select distinct c_last_name, c_first_name, d_date
+ from catalog_sales, date_dim, customer
+ where catalog_sales.cs_sold_date_sk = date_dim.d_date_sk
+ and catalog_sales.cs_bill_customer_sk = customer.c_customer_sk
+ and d_month_seq between 1212 and 1212+11)
+ except
+ (select distinct c_last_name, c_first_name, d_date
+ from web_sales, date_dim, customer
+ where web_sales.ws_sold_date_sk = date_dim.d_date_sk
+ and web_sales.ws_bill_customer_sk = customer.c_customer_sk
+ and d_month_seq between 1212 and 1212+11)
+) cool_cust
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-2 is a root stage
+ Stage-3 depends on stages: Stage-2
+ Stage-4 depends on stages: Stage-3
+ Stage-1 depends on stages: Stage-4
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-2
+ Spark
+#### A masked pattern was here ####
+ Vertices:
+ Map 7
+ Map Operator Tree:
+ TableScan
+ alias: date_dim
+ Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (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 12
+ 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-4
+ Spark
+#### A masked pattern was here ####
+ Vertices:
+ Map 17
+ Map Operator Tree:
+ TableScan
+ alias: date_dim
+ Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (d_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 10 <- Map 13 (PARTITION-LEVEL SORT, 873), Map 9 (PARTITION-LEVEL SORT, 873)
+ Reducer 11 <- Reducer 10 (GROUP PARTITION-LEVEL SORT, 369)
+ Reducer 15 <- Map 13 (PARTITION-LEVEL SORT, 706), Map 14 (PARTITION-LEVEL SORT, 706)
+ Reducer 16 <- Reducer 15 (GROUP PARTITION-LEVEL SORT, 186)
+ Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 975), Map 13 (PARTITION-LEVEL SORT, 975)
+ Reducer 3 <- Reducer 2 (GROUP PARTITION-LEVEL SORT, 481)
+ Reducer 4 <- Reducer 11 (GROUP PARTITION-LEVEL SORT, 213), Reducer 3 (GROUP PARTITION-LEVEL SORT, 213)
+ Reducer 5 <- Reducer 16 (GROUP, 56), Reducer 4 (GROUP, 56)
+ Reducer 6 <- Reducer 5 (GROUP, 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_customer_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_customer_sk (type: int)
+ outputColumnNames: _col0, _col1
+ 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, _col3
+ input vertices:
+ 1 Map 7
+ 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: _col3 (type: string)
+ Local Work:
+ Map Reduce Local Work
+ Map 13
+ Map Operator Tree:
+ TableScan
+ alias: customer
+ Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: c_customer_sk is not null (type: boolean)
+ Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: c_customer_sk (type: int), c_first_name (type: string), c_last_name (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 80000000 Data size: 68801615852 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: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: string), _col2 (type: string)
+ Map 14
+ Map Operator Tree:
+ TableScan
+ alias: web_sales
+ Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (ws_bill_customer_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_bill_customer_sk (type: int)
+ outputColumnNames: _col0, _col1
+ 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, _col3
+ input vertices:
+ 1 Map 17
+ 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: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col3 (type: string)
+ Local Work:
+ Map Reduce Local Work
+ 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_bill_customer_sk is not null and cs_sold_date_sk is not null) (type: boolean)
+ Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: cs_sold_date_sk (type: int), cs_bill_customer_sk (type: int)
+ outputColumnNames: _col0, _col1
+ 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, _col3
+ input vertices:
+ 1 Map 12
+ Statistics: Num rows: 316788826 Data size: 42899570777 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: 316788826 Data size: 42899570777 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col3 (type: string)
+ Local Work:
+ Map Reduce Local Work
+ Reducer 10
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col1 (type: int)
+ 1 _col0 (type: int)
+ outputColumnNames: _col3, _col6, _col7
+ Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ keys: _col7 (type: string), _col6 (type: string), _col3 (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 348467716 Data size: 47189528877 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: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE
+ Reducer 11
+ Reduce Operator Tree:
+ Group By Operator
+ keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 174233858 Data size: 23594764438 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col1 (type: string), _col0 (type: string), _col2 (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 174233858 Data size: 23594764438 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: count()
+ keys: _col1 (type: string), _col0 (type: string), _col2 (type: string)
+ mode: complete
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 87116929 Data size: 11797382219 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), 1 (type: bigint), _col3 (type: bigint)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Statistics: Num rows: 87116929 Data size: 11797382219 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col4 (type: bigint), (_col3 * _col4) (type: bigint)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Statistics: Num rows: 261355616 Data size: 27168769766 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: sum(_col3), sum(_col4)
+ keys: _col0 (type: string), _col1 (type: string), _col2 (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Statistics: Num rows: 261355616 Data size: 27168769766 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: 261355616 Data size: 27168769766 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col3 (type: bigint), _col4 (type: bigint)
+ Reducer 15
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col1 (type: int)
+ 1 _col0 (type: int)
+ outputColumnNames: _col3, _col6, _col7
+ Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ keys: _col7 (type: string), _col6 (type: string), _col3 (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 174243235 Data size: 23692040863 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: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE
+ Reducer 16
+ Reduce Operator Tree:
+ Group By Operator
+ keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 87121617 Data size: 11846020363 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col1 (type: string), _col0 (type: string), _col2 (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 87121617 Data size: 11846020363 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: count()
+ keys: _col1 (type: string), _col0 (type: string), _col2 (type: string)
+ mode: complete
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 43560808 Data size: 5923010113 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), 1 (type: bigint), _col3 (type: bigint)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Statistics: Num rows: 43560808 Data size: 5923010113 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col4 (type: bigint), (_col3 * _col4) (type: bigint)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Statistics: Num rows: 54450625 Data size: 7055042151 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: sum(_col3), sum(_col4)
+ keys: _col0 (type: string), _col1 (type: string), _col2 (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Statistics: Num rows: 54450625 Data size: 7055042151 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: 54450625 Data size: 7055042151 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col3 (type: bigint), _col4 (type: bigint)
+ Reducer 2
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col1 (type: int)
+ 1 _col0 (type: int)
+ outputColumnNames: _col3, _col6, _col7
+ Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ keys: _col7 (type: string), _col6 (type: string), _col3 (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ 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)
+ sort order: +++
+ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string)
+ Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE
+ Reducer 3
+ Reduce Operator Tree:
+ Group By Operator
+ keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col1 (type: string), _col0 (type: string), _col2 (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: count()
+ keys: _col1 (type: string), _col0 (type: string), _col2 (type: string)
+ mode: complete
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 174238687 Data size: 15371387547 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), 2 (type: bigint), _col3 (type: bigint)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Statistics: Num rows: 174238687 Data size: 15371387547 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col4 (type: bigint), (_col3 * _col4) (type: bigint)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Statistics: Num rows: 261355616 Data size: 27168769766 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: sum(_col3), sum(_col4)
+ keys: _col0 (type: string), _col1 (type: string), _col2 (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Statistics: Num rows: 261355616 Data size: 27168769766 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: 261355616 Data size: 27168769766 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col3 (type: bigint), _col4 (type: bigint)
+ Reducer 4
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: sum(VALUE._col0), sum(VALUE._col1)
+ keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Statistics: Num rows: 130677808 Data size: 13584384883 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (((_col3 * 2) = _col4) and (_col3 > 0)) (type: boolean)
+ Statistics: Num rows: 21779634 Data size: 2264064077 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 21779634 Data size: 2264064077 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: count()
+ keys: _col0 (type: string), _col1 (type: string), _col2 (type: string)
+ mode: complete
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 10889817 Data size: 1132032038 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), 2 (type: bigint), _col3 (type: bigint)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Statistics: Num rows: 10889817 Data size: 1132032038 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col4 (type: bigint), (_col3 * _col4) (type: bigint)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Statistics: Num rows: 54450625 Data size: 7055042151 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: sum(_col3), sum(_col4)
+ keys: _col0 (type: string), _col1 (type: string), _col2 (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Statistics: Num rows: 54450625 Data size: 7055042151 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: 54450625 Data size: 7055042151 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col3 (type: bigint), _col4 (type: bigint)
+ Reducer 5
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: sum(VALUE._col0), sum(VALUE._col1)
+ keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Statistics: Num rows: 27225312 Data size: 3527521010 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col3 (type: bigint), _col4 (type: bigint)
+ outputColumnNames: _col3, _col4
+ Statistics: Num rows: 27225312 Data size: 3527521010 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (((_col3 * 2) = _col4) and (_col3 > 0)) (type: boolean)
+ Statistics: Num rows: 4537552 Data size: 587920168 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ Statistics: Num rows: 4537552 Data size: 587920168 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: count()
+ mode: hash
+ outputColumnNames: _col0
+ 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
+ value expressions: _col0 (type: bigint)
+ Reducer 6
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: count(VALUE._col0)
+ mode: mergepartial
+ outputColumnNames: _col0
+ 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
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+