http://git-wip-us.apache.org/repos/asf/hive/blob/38405c14/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_4.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_4.q.out b/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_4.q.out index 60437ec..44f792a 100644 --- a/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_4.q.out +++ b/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_4.q.out @@ -418,146 +418,10 @@ PREHOOK: type: QUERY POSTHOOK: query: explain extended select count(*) FROM bucket_big a JOIN bucket_small b ON a.key = b.key POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-2 is a root stage - Stage-1 depends on stages: Stage-2 + Stage-1 is a root stage Stage-0 depends on stages: Stage-1 STAGE PLANS: - Stage: Stage-2 - Spark -#### A masked pattern was here #### - Vertices: - Map 3 - Map Operator Tree: - TableScan - alias: b - Statistics: Num rows: 4 Data size: 452 Basic stats: COMPLETE Column stats: NONE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: key is not null (type: boolean) - Statistics: Num rows: 4 Data size: 452 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 4 Data size: 452 Basic stats: COMPLETE Column stats: NONE - Spark HashTable Sink Operator - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - Position of Big Table: 0 - Local Work: - Map Reduce Local Work - Bucket Mapjoin Context: - Alias Bucket File Name Mapping: -#### A masked pattern was here #### - Alias Bucket Output File Name Mapping: -#### A masked pattern was here #### - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: ds=2008-04-08 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2008-04-08 - properties: - bucket_count 4 - bucket_field_name key - column.name.delimiter , - columns key,value - columns.comments - columns.types string:string -#### A masked pattern was here #### - name default.bucket_small - numFiles 4 - numRows 0 - partition_columns ds - partition_columns.types string - rawDataSize 0 - serialization.ddl struct bucket_small { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 226 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - SORTBUCKETCOLSPREFIX TRUE - bucket_count 4 - bucket_field_name key - column.name.delimiter , - columns key,value - columns.comments - columns.types string:string -#### A masked pattern was here #### - name default.bucket_small - partition_columns ds - partition_columns.types string - serialization.ddl struct bucket_small { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.bucket_small - name: default.bucket_small -#### A masked pattern was here #### - Partition - base file name: ds=2008-04-09 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2008-04-09 - properties: - bucket_count 4 - bucket_field_name key - column.name.delimiter , - columns key,value - columns.comments - columns.types string:string -#### A masked pattern was here #### - name default.bucket_small - numFiles 4 - numRows 0 - partition_columns ds - partition_columns.types string - rawDataSize 0 - serialization.ddl struct bucket_small { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 226 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - SORTBUCKETCOLSPREFIX TRUE - bucket_count 4 - bucket_field_name key - column.name.delimiter , - columns key,value - columns.comments - columns.types string:string -#### A masked pattern was here #### - name default.bucket_small - partition_columns ds - partition_columns.types string - serialization.ddl struct bucket_small { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.bucket_small - name: default.bucket_small - Truncated Path -> Alias: - /bucket_small/ds=2008-04-08 [$hdt$_1:b] - /bucket_small/ds=2008-04-09 [$hdt$_1:b] - Stage: Stage-1 Spark Edges: @@ -578,14 +442,12 @@ STAGE PLANS: expressions: key (type: string) outputColumnNames: _col0 Statistics: Num rows: 27 Data size: 2750 Basic stats: COMPLETE Column stats: NONE - Map Join Operator + Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 keys: 0 _col0 (type: string) 1 _col0 (type: string) - input vertices: - 1 Map 3 Position of Big Table: 0 Statistics: Num rows: 29 Data size: 3025 Basic stats: COMPLETE Column stats: NONE BucketMapJoin: true @@ -601,13 +463,6 @@ STAGE PLANS: tag: -1 value expressions: _col0 (type: bigint) auto parallelism: false - Local Work: - Map Reduce Local Work - Bucket Mapjoin Context: - Alias Bucket File Name Mapping: -#### A masked pattern was here #### - Alias Bucket Output File Name Mapping: -#### A masked pattern was here #### Path -> Alias: #### A masked pattern was here #### Path -> Partition:
http://git-wip-us.apache.org/repos/asf/hive/blob/38405c14/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_7.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_7.q.out b/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_7.q.out index 16ecabe..73525bc 100644 --- a/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_7.q.out +++ b/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_7.q.out @@ -539,146 +539,10 @@ PREHOOK: type: QUERY POSTHOOK: query: explain extended select count(*) FROM bucket_big a JOIN bucket_small b ON a.key = b.key POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-2 is a root stage - Stage-1 depends on stages: Stage-2 + Stage-1 is a root stage Stage-0 depends on stages: Stage-1 STAGE PLANS: - Stage: Stage-2 - Spark -#### A masked pattern was here #### - Vertices: - Map 3 - Map Operator Tree: - TableScan - alias: b - Statistics: Num rows: 4 Data size: 452 Basic stats: COMPLETE Column stats: NONE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: key is not null (type: boolean) - Statistics: Num rows: 4 Data size: 452 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 4 Data size: 452 Basic stats: COMPLETE Column stats: NONE - Spark HashTable Sink Operator - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - Position of Big Table: 0 - Local Work: - Map Reduce Local Work - Bucket Mapjoin Context: - Alias Bucket File Name Mapping: -#### A masked pattern was here #### - Alias Bucket Output File Name Mapping: -#### A masked pattern was here #### - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: ds=2008-04-08 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2008-04-08 - properties: - bucket_count 4 - bucket_field_name key - column.name.delimiter , - columns key,value - columns.comments - columns.types string:string -#### A masked pattern was here #### - name default.bucket_small - numFiles 4 - numRows 0 - partition_columns ds - partition_columns.types string - rawDataSize 0 - serialization.ddl struct bucket_small { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 226 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - SORTBUCKETCOLSPREFIX TRUE - bucket_count 4 - bucket_field_name key - column.name.delimiter , - columns key,value - columns.comments - columns.types string:string -#### A masked pattern was here #### - name default.bucket_small - partition_columns ds - partition_columns.types string - serialization.ddl struct bucket_small { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.bucket_small - name: default.bucket_small -#### A masked pattern was here #### - Partition - base file name: ds=2008-04-09 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2008-04-09 - properties: - bucket_count 4 - bucket_field_name key - column.name.delimiter , - columns key,value - columns.comments - columns.types string:string -#### A masked pattern was here #### - name default.bucket_small - numFiles 4 - numRows 0 - partition_columns ds - partition_columns.types string - rawDataSize 0 - serialization.ddl struct bucket_small { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 226 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - SORTBUCKETCOLSPREFIX TRUE - bucket_count 4 - bucket_field_name key - column.name.delimiter , - columns key,value - columns.comments - columns.types string:string -#### A masked pattern was here #### - name default.bucket_small - partition_columns ds - partition_columns.types string - serialization.ddl struct bucket_small { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.bucket_small - name: default.bucket_small - Truncated Path -> Alias: - /bucket_small/ds=2008-04-08 [$hdt$_1:b] - /bucket_small/ds=2008-04-09 [$hdt$_1:b] - Stage: Stage-1 Spark Edges: @@ -699,14 +563,12 @@ STAGE PLANS: expressions: key (type: string) outputColumnNames: _col0 Statistics: Num rows: 54 Data size: 5500 Basic stats: COMPLETE Column stats: NONE - Map Join Operator + Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 keys: 0 _col0 (type: string) 1 _col0 (type: string) - input vertices: - 1 Map 3 Position of Big Table: 0 Statistics: Num rows: 59 Data size: 6050 Basic stats: COMPLETE Column stats: NONE BucketMapJoin: true @@ -722,13 +584,6 @@ STAGE PLANS: tag: -1 value expressions: _col0 (type: bigint) auto parallelism: false - Local Work: - Map Reduce Local Work - Bucket Mapjoin Context: - Alias Bucket File Name Mapping: -#### A masked pattern was here #### - Alias Bucket Output File Name Mapping: -#### A masked pattern was here #### Path -> Alias: #### A masked pattern was here #### Path -> Partition: http://git-wip-us.apache.org/repos/asf/hive/blob/38405c14/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_8.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_8.q.out b/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_8.q.out index e180471..abd6e65 100644 --- a/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_8.q.out +++ b/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_8.q.out @@ -539,146 +539,10 @@ PREHOOK: type: QUERY POSTHOOK: query: explain extended select count(*) FROM bucket_big a JOIN bucket_small b ON a.key = b.key POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-2 is a root stage - Stage-1 depends on stages: Stage-2 + Stage-1 is a root stage Stage-0 depends on stages: Stage-1 STAGE PLANS: - Stage: Stage-2 - Spark -#### A masked pattern was here #### - Vertices: - Map 3 - Map Operator Tree: - TableScan - alias: b - Statistics: Num rows: 2 Data size: 228 Basic stats: COMPLETE Column stats: NONE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: key is not null (type: boolean) - Statistics: Num rows: 2 Data size: 228 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 228 Basic stats: COMPLETE Column stats: NONE - Spark HashTable Sink Operator - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - Position of Big Table: 0 - Local Work: - Map Reduce Local Work - Bucket Mapjoin Context: - Alias Bucket File Name Mapping: -#### A masked pattern was here #### - Alias Bucket Output File Name Mapping: -#### A masked pattern was here #### - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: ds=2008-04-08 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2008-04-08 - properties: - bucket_count 2 - bucket_field_name key - column.name.delimiter , - columns key,value - columns.comments - columns.types string:string -#### A masked pattern was here #### - name default.bucket_small - numFiles 2 - numRows 0 - partition_columns ds - partition_columns.types string - rawDataSize 0 - serialization.ddl struct bucket_small { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 114 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - SORTBUCKETCOLSPREFIX TRUE - bucket_count 2 - bucket_field_name key - column.name.delimiter , - columns key,value - columns.comments - columns.types string:string -#### A masked pattern was here #### - name default.bucket_small - partition_columns ds - partition_columns.types string - serialization.ddl struct bucket_small { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.bucket_small - name: default.bucket_small -#### A masked pattern was here #### - Partition - base file name: ds=2008-04-09 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2008-04-09 - properties: - bucket_count 2 - bucket_field_name key - column.name.delimiter , - columns key,value - columns.comments - columns.types string:string -#### A masked pattern was here #### - name default.bucket_small - numFiles 2 - numRows 0 - partition_columns ds - partition_columns.types string - rawDataSize 0 - serialization.ddl struct bucket_small { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 114 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - SORTBUCKETCOLSPREFIX TRUE - bucket_count 2 - bucket_field_name key - column.name.delimiter , - columns key,value - columns.comments - columns.types string:string -#### A masked pattern was here #### - name default.bucket_small - partition_columns ds - partition_columns.types string - serialization.ddl struct bucket_small { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.bucket_small - name: default.bucket_small - Truncated Path -> Alias: - /bucket_small/ds=2008-04-08 [$hdt$_1:b] - /bucket_small/ds=2008-04-09 [$hdt$_1:b] - Stage: Stage-1 Spark Edges: @@ -699,14 +563,12 @@ STAGE PLANS: expressions: key (type: string) outputColumnNames: _col0 Statistics: Num rows: 116 Data size: 11624 Basic stats: COMPLETE Column stats: NONE - Map Join Operator + Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 keys: 0 _col0 (type: string) 1 _col0 (type: string) - input vertices: - 1 Map 3 Position of Big Table: 0 Statistics: Num rows: 127 Data size: 12786 Basic stats: COMPLETE Column stats: NONE BucketMapJoin: true @@ -722,13 +584,6 @@ STAGE PLANS: tag: -1 value expressions: _col0 (type: bigint) auto parallelism: false - Local Work: - Map Reduce Local Work - Bucket Mapjoin Context: - Alias Bucket File Name Mapping: -#### A masked pattern was here #### - Alias Bucket Output File Name Mapping: -#### A masked pattern was here #### Path -> Alias: #### A masked pattern was here #### Path -> Partition: http://git-wip-us.apache.org/repos/asf/hive/blob/38405c14/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_9.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_9.q.out b/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_9.q.out index 4d0476f..033ee04 100644 --- a/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_9.q.out +++ b/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_9.q.out @@ -387,18 +387,19 @@ join on src1.key = src2.key POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-2 is a root stage - Stage-1 depends on stages: Stage-2 + Stage-1 is a root stage Stage-0 depends on stages: Stage-1 STAGE PLANS: - Stage: Stage-2 + Stage: Stage-1 Spark Edges: - Reducer 4 <- Map 3 (GROUP, 1) + Reducer 2 <- Map 1 (GROUP, 1) + Reducer 3 <- Reducer 2 (PARTITION-LEVEL SORT, 1), Reducer 5 (PARTITION-LEVEL SORT, 1) + Reducer 5 <- Map 1 (GROUP, 1) #### A masked pattern was here #### Vertices: - Map 3 + Map 1 Map Operator Tree: TableScan alias: a @@ -430,9 +431,7 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) - Reducer 4 - Local Work: - Map Reduce Local Work + Reducer 2 Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -440,52 +439,34 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE - Spark HashTable Sink Operator - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - - Stage: Stage-1 - Spark - Edges: - Reducer 2 <- Map 1 (GROUP, 1) -#### A masked pattern was here #### - Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Sorted Merge Bucket Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - keys: _col0 (type: int) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 11 Data size: 77 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: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) - Reducer 2 - Local Work: - Map Reduce Local Work + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: bigint) + Reducer 3 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0, _col1, _col3 + Statistics: Num rows: 5 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: int), _col3 (type: bigint), _col1 (type: bigint) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 5 Data size: 38 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 5 Data size: 38 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 5 Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -493,27 +474,12 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 5 Data size: 35 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: _col0, _col1, _col3 - input vertices: - 1 Reducer 4 - Statistics: Num rows: 5 Data size: 38 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: int), _col3 (type: bigint), _col1 (type: bigint) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 5 Data size: 38 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 5 Data size: 38 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 + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: bigint) Stage: Stage-0 Fetch Operator @@ -1018,16 +984,18 @@ select count(*) from on subq1.key = subq2.key POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-2 is a root stage - Stage-1 depends on stages: Stage-2 + Stage-1 is a root stage Stage-0 depends on stages: Stage-1 STAGE PLANS: - Stage: Stage-2 + Stage: Stage-1 Spark + Edges: + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 4 (PARTITION-LEVEL SORT, 1) + Reducer 3 <- Reducer 2 (GROUP, 1) #### A masked pattern was here #### Vertices: - Map 3 + Map 1 Map Operator Tree: TableScan alias: a @@ -1039,20 +1007,12 @@ STAGE PLANS: expressions: (key + 1) (type: int) outputColumnNames: _col0 Statistics: Num rows: 10 Data size: 70 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, 1) -#### A masked pattern was here #### - Vertices: - Map 1 + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Map 4 Map Operator Tree: TableScan alias: a @@ -1064,28 +1024,31 @@ STAGE PLANS: expressions: (key + 1) (type: int) outputColumnNames: _col0 Statistics: Num rows: 10 Data size: 70 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) - input vertices: - 1 Map 3 - Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) - Local Work: - Map Reduce Local Work + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 10 Data size: 70 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) + Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) + Reducer 3 + Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial @@ -1533,34 +1496,10 @@ select count(*) from ( ) subq1 POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-2 is a root stage - Stage-1 depends on stages: Stage-2 + Stage-1 is a root stage Stage-0 depends on stages: Stage-1 STAGE PLANS: - Stage: Stage-2 - Spark -#### A masked pattern was here #### - Vertices: - Map 3 - Map Operator Tree: - TableScan - alias: b - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 70 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: @@ -1579,14 +1518,12 @@ STAGE PLANS: expressions: key (type: int) outputColumnNames: _col0 Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Map Join Operator + Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 keys: 0 _col0 (type: int) 1 _col0 (type: int) - input vertices: - 1 Map 3 Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() @@ -1597,8 +1534,6 @@ STAGE PLANS: sort order: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) - Local Work: - Map Reduce Local Work Reducer 2 Reduce Operator Tree: Group By Operator @@ -1650,34 +1585,10 @@ select key, count(*) from group by key POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-2 is a root stage - Stage-1 depends on stages: Stage-2 + Stage-1 is a root stage Stage-0 depends on stages: Stage-1 STAGE PLANS: - Stage: Stage-2 - Spark -#### A masked pattern was here #### - Vertices: - Map 3 - Map Operator Tree: - TableScan - alias: b - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 70 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: @@ -1696,15 +1607,13 @@ STAGE PLANS: expressions: key (type: int) outputColumnNames: _col0 Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Map Join Operator + Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 keys: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0 - input vertices: - 1 Map 3 Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() @@ -1718,8 +1627,6 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) - Local Work: - Map Reduce Local Work Reducer 2 Reduce Operator Tree: Group By Operator @@ -1787,34 +1694,10 @@ select count(*) from ) subq2 POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-2 is a root stage - Stage-1 depends on stages: Stage-2 + Stage-1 is a root stage 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: b - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 70 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: @@ -1834,15 +1717,13 @@ STAGE PLANS: expressions: key (type: int) outputColumnNames: _col0 Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Map Join Operator + Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 keys: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0 - input vertices: - 1 Map 4 Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: _col0 (type: int) @@ -1854,8 +1735,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE - Local Work: - Map Reduce Local Work Reducer 2 Reduce Operator Tree: Group By Operator @@ -1955,43 +1834,19 @@ join on src1.key = src2.key POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-3 is a root stage - Stage-2 depends on stages: Stage-3 - Stage-4 depends on stages: Stage-2 - Stage-1 depends on stages: Stage-4 + Stage-1 is a root stage Stage-0 depends on stages: Stage-1 STAGE PLANS: - Stage: Stage-3 - Spark -#### A masked pattern was here #### - Vertices: - Map 6 - Map Operator Tree: - TableScan - alias: b - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 70 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-2 + Stage: Stage-1 Spark Edges: - Reducer 5 <- Map 4 (GROUP, 1) + Reducer 2 <- Map 1 (GROUP, 1) + Reducer 3 <- Reducer 2 (PARTITION-LEVEL SORT, 1), Reducer 5 (PARTITION-LEVEL SORT, 1) + Reducer 5 <- Map 1 (GROUP, 1) #### A masked pattern was here #### Vertices: - Map 4 + Map 1 Map Operator Tree: TableScan alias: a @@ -2003,15 +1858,13 @@ STAGE PLANS: expressions: key (type: int) outputColumnNames: _col0 Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Map Join Operator + Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 keys: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0 - input vertices: - 1 Map 6 Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() @@ -2025,11 +1878,7 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) - Local Work: - Map Reduce Local Work - Reducer 5 - Local Work: - Map Reduce Local Work + Reducer 2 Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -2037,79 +1886,34 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE - Spark HashTable Sink Operator - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - - Stage: Stage-4 - Spark -#### A masked pattern was here #### - Vertices: - Map 3 - Map Operator Tree: - TableScan - alias: b - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 70 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, 1) -#### A masked pattern was here #### - Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 70 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: _col0 - input vertices: - 1 Map 3 - Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - keys: _col0 (type: int) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 11 Data size: 77 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: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) - Local Work: - Map Reduce Local Work - Reducer 2 - Local Work: - Map Reduce Local Work + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: bigint) + Reducer 3 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0, _col1, _col3 + Statistics: Num rows: 5 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: int), _col3 (type: bigint), _col1 (type: bigint) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 5 Data size: 38 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 5 Data size: 38 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 5 Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -2117,27 +1921,12 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 5 Data size: 35 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: _col0, _col1, _col3 - input vertices: - 1 Reducer 5 - Statistics: Num rows: 5 Data size: 38 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: int), _col3 (type: bigint), _col1 (type: bigint) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 5 Data size: 38 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 5 Data size: 38 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 + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: bigint) Stage: Stage-0 Fetch Operator @@ -2204,34 +1993,10 @@ select count(*) from on subq1.key = subq2.key POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-2 is a root stage - Stage-1 depends on stages: Stage-2 + Stage-1 is a root stage Stage-0 depends on stages: Stage-1 STAGE PLANS: - Stage: Stage-2 - Spark -#### A masked pattern was here #### - Vertices: - Map 3 - Map Operator Tree: - TableScan - alias: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 21 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: @@ -2250,14 +2015,12 @@ STAGE PLANS: expressions: key (type: int) outputColumnNames: _col0 Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Map Join Operator + Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 keys: 0 _col0 (type: int) 1 _col0 (type: int) - input vertices: - 1 Map 3 Statistics: Num rows: 3 Data size: 23 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() @@ -2268,8 +2031,6 @@ STAGE PLANS: sort order: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) - Local Work: - Map Reduce Local Work Reducer 2 Reduce Operator Tree: Group By Operator @@ -2335,34 +2096,10 @@ select count(*) from on subq2.key = b.key POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-2 is a root stage - Stage-1 depends on stages: Stage-2 + Stage-1 is a root stage Stage-0 depends on stages: Stage-1 STAGE PLANS: - Stage: Stage-2 - Spark -#### A masked pattern was here #### - Vertices: - Map 3 - Map Operator Tree: - TableScan - alias: b - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 21 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: @@ -2381,14 +2118,12 @@ STAGE PLANS: expressions: key (type: int) outputColumnNames: _col0 Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Map Join Operator + Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 keys: 0 _col0 (type: int) 1 _col0 (type: int) - input vertices: - 1 Map 3 Statistics: Num rows: 3 Data size: 23 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() @@ -2399,8 +2134,6 @@ STAGE PLANS: sort order: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) - Local Work: - Map Reduce Local Work Reducer 2 Reduce Operator Tree: Group By Operator @@ -2490,34 +2223,10 @@ select count(*) from on subq2.key = subq4.key POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-2 is a root stage - Stage-1 depends on stages: Stage-2 + Stage-1 is a root stage Stage-0 depends on stages: Stage-1 STAGE PLANS: - Stage: Stage-2 - Spark -#### A masked pattern was here #### - Vertices: - Map 3 - Map Operator Tree: - TableScan - alias: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 21 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: @@ -2536,14 +2245,12 @@ STAGE PLANS: expressions: key (type: int) outputColumnNames: _col0 Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Map Join Operator + Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 keys: 0 _col0 (type: int) 1 _col0 (type: int) - input vertices: - 1 Map 3 Statistics: Num rows: 3 Data size: 23 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() @@ -2554,8 +2261,6 @@ STAGE PLANS: sort order: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) - Local Work: - Map Reduce Local Work Reducer 2 Reduce Operator Tree: Group By Operator @@ -2633,34 +2338,10 @@ select count(*) from on subq1.key = subq2.key POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-2 is a root stage - Stage-1 depends on stages: Stage-2 + Stage-1 is a root stage Stage-0 depends on stages: Stage-1 STAGE PLANS: - Stage: Stage-2 - Spark -#### A masked pattern was here #### - Vertices: - Map 3 - Map Operator Tree: - TableScan - alias: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key < 8) (type: boolean) - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 21 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: @@ -2679,14 +2360,12 @@ STAGE PLANS: expressions: key (type: int) outputColumnNames: _col0 Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Map Join Operator + Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 keys: 0 _col0 (type: int) 1 _col0 (type: int) - input vertices: - 1 Map 3 Statistics: Num rows: 3 Data size: 23 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() @@ -2697,8 +2376,6 @@ STAGE PLANS: sort order: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) - Local Work: - Map Reduce Local Work Reducer 2 Reduce Operator Tree: Group By Operator @@ -2750,34 +2427,10 @@ select count(*) from join tbl2 a on subq1.key = a.key POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-2 is a root stage - Stage-1 depends on stages: Stage-2 + Stage-1 is a root stage Stage-0 depends on stages: Stage-1 STAGE PLANS: - Stage: Stage-2 - Spark -#### A masked pattern was here #### - Vertices: - Map 3 - Map Operator Tree: - TableScan - alias: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 21 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: @@ -2796,14 +2449,12 @@ STAGE PLANS: expressions: key (type: int) outputColumnNames: _col0 Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Map Join Operator + Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 keys: 0 _col0 (type: int) 1 _col0 (type: int) - input vertices: - 1 Map 3 Statistics: Num rows: 3 Data size: 23 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() @@ -2814,8 +2465,6 @@ STAGE PLANS: sort order: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) - Local Work: - Map Reduce Local Work Reducer 2 Reduce Operator Tree: Group By Operator @@ -2865,34 +2514,10 @@ select count(*) from tbl1 a on a.key = subq1.key POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-2 is a root stage - Stage-1 depends on stages: Stage-2 + Stage-1 is a root stage Stage-0 depends on stages: Stage-1 STAGE PLANS: - Stage: Stage-2 - Spark -#### A masked pattern was here #### - Vertices: - Map 3 - Map Operator Tree: - TableScan - alias: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 21 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: @@ -2911,14 +2536,12 @@ STAGE PLANS: expressions: key (type: int) outputColumnNames: _col0 Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Map Join Operator + Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 keys: 0 _col0 (type: int) 1 _col0 (type: int) - input vertices: - 1 Map 3 Statistics: Num rows: 3 Data size: 23 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() @@ -2929,8 +2552,6 @@ STAGE PLANS: sort order: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) - Local Work: - Map Reduce Local Work Reducer 2 Reduce Operator Tree: Group By Operator @@ -2990,54 +2611,10 @@ select count(*) from on (subq1.key = subq3.key) POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-2 is a root stage - Stage-1 depends on stages: Stage-2 + Stage-1 is a root stage Stage-0 depends on stages: Stage-1 STAGE PLANS: - Stage: Stage-2 - Spark -#### A masked pattern was here #### - Vertices: - Map 3 - Map Operator Tree: - TableScan - alias: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Spark HashTable Sink Operator - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - 2 _col0 (type: int) - Local Work: - Map Reduce Local Work - Map 4 - Map Operator Tree: - TableScan - alias: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Spark HashTable Sink Operator - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - 2 _col0 (type: int) - Local Work: - Map Reduce Local Work - Stage: Stage-1 Spark Edges: @@ -3056,7 +2633,7 @@ STAGE PLANS: expressions: key (type: int) outputColumnNames: _col0 Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Map Join Operator + Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 Inner Join 0 to 2 @@ -3064,9 +2641,6 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) 2 _col0 (type: int) - input vertices: - 1 Map 3 - 2 Map 4 Statistics: Num rows: 6 Data size: 46 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() @@ -3077,8 +2651,6 @@ STAGE PLANS: sort order: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) - Local Work: - Map Reduce Local Work Reducer 2 Reduce Operator Tree: Group By Operator @@ -3152,34 +2724,10 @@ join tbl2 b on subq2.key = b.key) a POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-2 is a root stage - Stage-1 depends on stages: Stage-2 + Stage-1 is a root stage Stage-0 depends on stages: Stage-1 STAGE PLANS: - Stage: Stage-2 - Spark -#### A masked pattern was here #### - Vertices: - Map 3 - Map Operator Tree: - TableScan - alias: b - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 21 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: @@ -3198,14 +2746,12 @@ STAGE PLANS: expressions: key (type: int) outputColumnNames: _col0 Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Map Join Operator + Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 keys: 0 _col0 (type: int) 1 _col0 (type: int) - input vertices: - 1 Map 3 Statistics: Num rows: 3 Data size: 23 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() @@ -3216,8 +2762,6 @@ STAGE PLANS: sort order: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) - Local Work: - Map Reduce Local Work Reducer 2 Reduce Operator Tree: Group By Operator
