http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/llap/bucket2.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/bucket2.q.out b/ql/src/test/results/clientpositive/llap/bucket2.q.out index 9954c2d..10fc171 100644 --- a/ql/src/test/results/clientpositive/llap/bucket2.q.out +++ b/ql/src/test/results/clientpositive/llap/bucket2.q.out @@ -140,6 +140,41 @@ STAGE PLANS: TotalFiles: 2 GatherStats: true MultiFileSpray: true + Select Operator + expressions: _col0 (type: int), _col1 (type: string) + outputColumnNames: key, value + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + mode: complete + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + columns _col0,_col1 + columns.types struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>:struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary> + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-2 Dependency Collection @@ -177,6 +212,11 @@ STAGE PLANS: Stats Work Basic Stats Work: #### A masked pattern was here #### + Column Stats Desc: + Columns: key, value + Column Types: int, string + Table: default.bucket2_1 + Is Table Level Stats: true PREHOOK: query: insert overwrite table bucket2_1 select * from src
http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/llap/bucket3.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/bucket3.q.out b/ql/src/test/results/clientpositive/llap/bucket3.q.out index 218f9b7..9ae5166 100644 --- a/ql/src/test/results/clientpositive/llap/bucket3.q.out +++ b/ql/src/test/results/clientpositive/llap/bucket3.q.out @@ -26,6 +26,7 @@ STAGE PLANS: #### A masked pattern was here #### Edges: Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 @@ -138,6 +139,61 @@ STAGE PLANS: TotalFiles: 2 GatherStats: true MultiFileSpray: true + Select Operator + expressions: _col0 (type: int), _col1 (type: string), '1' (type: string) + outputColumnNames: key, value, ds + Statistics: Num rows: 500 Data size: 90000 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + keys: ds (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 949 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: a + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 949 Basic stats: COMPLETE Column stats: COMPLETE + tag: -1 + value expressions: _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>) + auto parallelism: true + Reducer 3 + Execution mode: llap + Needs Tagging: false + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col0 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + columns _col0,_col1,_col2 + columns.types struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>:struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>:string + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-2 Dependency Collection @@ -174,6 +230,11 @@ STAGE PLANS: Stats Work Basic Stats Work: #### A masked pattern was here #### + Column Stats Desc: + Columns: key, value + Column Types: int, string + Table: default.bucket3_1 + Is Table Level Stats: false PREHOOK: query: insert overwrite table bucket3_1 partition (ds='1') select * from src http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/llap/bucket4.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/bucket4.q.out b/ql/src/test/results/clientpositive/llap/bucket4.q.out index 2115565..0a1c497 100644 --- a/ql/src/test/results/clientpositive/llap/bucket4.q.out +++ b/ql/src/test/results/clientpositive/llap/bucket4.q.out @@ -142,6 +142,41 @@ STAGE PLANS: TotalFiles: 2 GatherStats: true MultiFileSpray: true + Select Operator + expressions: _col0 (type: int), _col1 (type: string) + outputColumnNames: key, value + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + mode: complete + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + columns _col0,_col1 + columns.types struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>:struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary> + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-2 Dependency Collection @@ -180,6 +215,11 @@ STAGE PLANS: Stats Work Basic Stats Work: #### A masked pattern was here #### + Column Stats Desc: + Columns: key, value + Column Types: int, string + Table: default.bucket4_1 + Is Table Level Stats: true PREHOOK: query: insert overwrite table bucket4_1 select * from src http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/llap/bucket5.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/bucket5.q.out b/ql/src/test/results/clientpositive/llap/bucket5.q.out index 680dbd9..a679fc9 100644 --- a/ql/src/test/results/clientpositive/llap/bucket5.q.out +++ b/ql/src/test/results/clientpositive/llap/bucket5.q.out @@ -43,7 +43,9 @@ STAGE PLANS: #### A masked pattern was here #### Edges: Reducer 2 <- Map 1 (SIMPLE_EDGE) - Reducer 3 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) + Reducer 4 <- Map 1 (SIMPLE_EDGE) + Reducer 5 <- Reducer 4 (CUSTOM_SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 @@ -173,10 +175,57 @@ STAGE PLANS: TotalFiles: 1 GatherStats: true MultiFileSpray: false + Select Operator + expressions: _col0 (type: int), _col1 (type: string) + outputColumnNames: key, value + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE + tag: -1 + value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>) + auto parallelism: false Reducer 3 Execution mode: llap Needs Tagging: false Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + columns _col0,_col1 + columns.types struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>:struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary> + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + Reducer 4 + Execution mode: llap + Needs Tagging: false + Reduce Operator Tree: Select Operator expressions: UDFToInteger(KEY.reducesinkkey0) (type: int), VALUE._col0 (type: string) outputColumnNames: _col0, _col1 @@ -213,6 +262,53 @@ STAGE PLANS: TotalFiles: 1 GatherStats: true MultiFileSpray: false + Select Operator + expressions: _col0 (type: int), _col1 (type: string) + outputColumnNames: key, value + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE + tag: -1 + value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>) + auto parallelism: false + Reducer 5 + Execution mode: llap + Needs Tagging: false + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + columns _col0,_col1 + columns.types struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>:struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary> + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-3 Dependency Collection @@ -251,6 +347,11 @@ STAGE PLANS: Stats Work Basic Stats Work: #### A masked pattern was here #### + Column Stats Desc: + Columns: key, value + Column Types: int, string + Table: default.bucketed_table + Is Table Level Stats: true Stage: Stage-1 Move Operator @@ -284,6 +385,11 @@ STAGE PLANS: Stats Work Basic Stats Work: #### A masked pattern was here #### + Column Stats Desc: + Columns: key, value + Column Types: int, string + Table: default.unbucketed_table + Is Table Level Stats: true Stage: Stage-10 Conditional Operator @@ -515,7 +621,7 @@ Retention: 0 #### A masked pattern was here #### Table Type: MANAGED_TABLE Table Parameters: - COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"} + COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}} SORTBUCKETCOLSPREFIX TRUE numFiles 2 numRows 500 http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/llap/bucket6.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/bucket6.q.out b/ql/src/test/results/clientpositive/llap/bucket6.q.out index 42f062b..78c044d 100644 --- a/ql/src/test/results/clientpositive/llap/bucket6.q.out +++ b/ql/src/test/results/clientpositive/llap/bucket6.q.out @@ -24,6 +24,7 @@ STAGE PLANS: #### A masked pattern was here #### Edges: Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 @@ -58,6 +59,34 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.src_bucket + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: key, value + Statistics: Num rows: 2000 Data size: 356000 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>) + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + 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-2 Dependency Collection @@ -75,6 +104,10 @@ STAGE PLANS: Stage: Stage-3 Stats Work Basic Stats Work: + Column Stats Desc: + Columns: key, value + Column Types: string, string + Table: default.src_bucket PREHOOK: query: insert into table src_bucket select key,value from srcpart PREHOOK: type: QUERY http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/llap/bucket_groupby.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/bucket_groupby.q.out b/ql/src/test/results/clientpositive/llap/bucket_groupby.q.out index 98c1e48..e2b6002 100644 --- a/ql/src/test/results/clientpositive/llap/bucket_groupby.q.out +++ b/ql/src/test/results/clientpositive/llap/bucket_groupby.q.out @@ -62,22 +62,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: clustergroupby - Statistics: Num rows: 500 Data size: 92896 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 500 Data size: 92896 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 92896 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 92896 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: bigint) Execution mode: llap @@ -90,11 +90,11 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 46448 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 250 Data size: 46448 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: bigint) Reducer 3 @@ -103,13 +103,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 46448 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 1850 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 950 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 1850 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 950 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -189,22 +189,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: clustergroupby - Statistics: Num rows: 500 Data size: 92896 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 500 Data size: 92896 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 92896 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 92896 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: bigint) Execution mode: llap @@ -217,11 +217,11 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 46448 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 250 Data size: 46448 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: bigint) Reducer 3 @@ -230,13 +230,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 46448 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 1850 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 950 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 1850 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 950 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -290,22 +290,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: clustergroupby - Statistics: Num rows: 500 Data size: 92896 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: length(key) (type: int) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 92896 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: int) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 92896 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 3000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 500 Data size: 92896 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 3000 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: bigint) Execution mode: llap @@ -318,13 +318,13 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 46448 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 3000 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 1850 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 1850 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -371,22 +371,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: clustergroupby - Statistics: Num rows: 500 Data size: 92896 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: abs(length(key)) (type: int) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 92896 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: int) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 92896 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 3000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 500 Data size: 92896 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 3000 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: bigint) Execution mode: llap @@ -399,13 +399,13 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 46448 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 3000 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 1850 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 1850 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -453,22 +453,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: clustergroupby - Statistics: Num rows: 500 Data size: 92896 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 500 Data size: 92896 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 92896 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 92896 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: bigint) Execution mode: llap @@ -481,11 +481,11 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 46448 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 250 Data size: 46448 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: bigint) Reducer 3 @@ -494,13 +494,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 46448 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 1850 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 950 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 1850 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 950 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -555,22 +555,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: clustergroupby - Statistics: Num rows: 500 Data size: 92896 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: value (type: string) outputColumnNames: value - Statistics: Num rows: 500 Data size: 92896 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: value (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 92896 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 24750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 92896 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 24750 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: bigint) Execution mode: llap @@ -583,11 +583,11 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 46448 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 24750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 250 Data size: 46448 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 24750 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: bigint) Reducer 3 @@ -596,13 +596,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 46448 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 24750 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 1850 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 990 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 1850 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 990 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -656,22 +656,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: clustergroupby - Statistics: Num rows: 1000 Data size: 185608 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 87000 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 1000 Data size: 185608 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 87000 Basic stats: COMPLETE Column stats: PARTIAL Group By Operator aggregations: count() keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1000 Data size: 185608 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1000 Data size: 185608 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: PARTIAL value expressions: _col1 (type: bigint) Execution mode: llap LLAP IO: no inputs @@ -683,10 +683,10 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 92804 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 92804 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1041,22 +1041,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: clustergroupby - Statistics: Num rows: 1000 Data size: 185608 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 87000 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 1000 Data size: 185608 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 87000 Basic stats: COMPLETE Column stats: PARTIAL Group By Operator aggregations: count() keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1000 Data size: 185608 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1000 Data size: 185608 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: PARTIAL value expressions: _col1 (type: bigint) Execution mode: llap LLAP IO: no inputs @@ -1068,10 +1068,10 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 92804 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 92804 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1155,23 +1155,23 @@ STAGE PLANS: Map Operator Tree: TableScan alias: clustergroupby - Statistics: Num rows: 500 Data size: 92896 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 500 Data size: 92896 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() bucketGroup: true keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 92896 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 92896 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: bigint) Execution mode: llap @@ -1184,11 +1184,11 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 46448 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 250 Data size: 46448 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: bigint) Reducer 3 @@ -1197,13 +1197,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 46448 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 1850 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 950 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 1850 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 950 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1258,22 +1258,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: clustergroupby - Statistics: Num rows: 500 Data size: 92896 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: value (type: string) outputColumnNames: value - Statistics: Num rows: 500 Data size: 92896 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: value (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 92896 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 24750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 92896 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 24750 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: bigint) Execution mode: llap @@ -1286,11 +1286,11 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 46448 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 24750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 250 Data size: 46448 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 24750 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: bigint) Reducer 3 @@ -1299,13 +1299,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 46448 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 24750 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 1850 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 990 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 1850 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 990 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1460,23 +1460,23 @@ STAGE PLANS: Map Operator Tree: TableScan alias: clustergroupby - Statistics: Num rows: 500 Data size: 92896 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 500 Data size: 92896 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() bucketGroup: true keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 92896 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 92896 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: bigint) Execution mode: llap @@ -1489,11 +1489,11 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 46448 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 250 Data size: 46448 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: bigint) Reducer 3 @@ -1502,13 +1502,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 46448 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 1850 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 950 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 1850 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 950 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1563,22 +1563,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: clustergroupby - Statistics: Num rows: 500 Data size: 180480 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 180480 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 180480 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 500 Data size: 180480 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col2 (type: bigint) Execution mode: llap @@ -1591,15 +1591,15 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 90240 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col2 (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 90240 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 250 Data size: 90240 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: bigint) Reducer 3 @@ -1608,13 +1608,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 90240 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 3600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 950 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 3600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 950 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/llap/bucket_many.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/bucket_many.q.out b/ql/src/test/results/clientpositive/llap/bucket_many.q.out index 4f3bee2..2202745 100644 --- a/ql/src/test/results/clientpositive/llap/bucket_many.q.out +++ b/ql/src/test/results/clientpositive/llap/bucket_many.q.out @@ -26,6 +26,7 @@ STAGE PLANS: #### A masked pattern was here #### Edges: Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 @@ -140,6 +141,53 @@ STAGE PLANS: TotalFiles: 256 GatherStats: true MultiFileSpray: true + Select Operator + expressions: _col0 (type: int), _col1 (type: string) + outputColumnNames: key, value + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE + tag: -1 + value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>) + auto parallelism: false + Reducer 3 + Execution mode: llap + Needs Tagging: false + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + columns _col0,_col1 + columns.types struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>:struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary> + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-2 Dependency Collection @@ -177,6 +225,11 @@ STAGE PLANS: Stats Work Basic Stats Work: #### A masked pattern was here #### + Column Stats Desc: + Columns: key, value + Column Types: int, string + Table: default.bucket_many + Is Table Level Stats: true PREHOOK: query: insert overwrite table bucket_many select * from src http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/llap/bucket_map_join_tez1.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/bucket_map_join_tez1.q.out b/ql/src/test/results/clientpositive/llap/bucket_map_join_tez1.q.out index 808f4de..4df0d41 100644 --- a/ql/src/test/results/clientpositive/llap/bucket_map_join_tez1.q.out +++ b/ql/src/test/results/clientpositive/llap/bucket_map_join_tez1.q.out @@ -4132,19 +4132,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 242 Data size: 43428 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 22990 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 230 Data size: 41274 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 22990 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 230 Data size: 41274 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 22990 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 230 Data size: 41274 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 22990 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Execution mode: llap LLAP IO: no inputs @@ -4178,14 +4178,14 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 550 Data size: 52250 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 391 Data size: 72726 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 550 Data size: 52250 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 391 Data size: 72726 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 550 Data size: 52250 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 391 Data size: 72726 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -4221,19 +4221,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 242 Data size: 43428 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 22990 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 230 Data size: 41274 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 22990 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 230 Data size: 41274 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 22990 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 230 Data size: 41274 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 22990 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Execution mode: llap LLAP IO: no inputs @@ -4258,14 +4258,14 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col3 input vertices: 0 Map 1 - Statistics: Num rows: 550 Data size: 52250 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 391 Data size: 72726 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 550 Data size: 52250 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 391 Data size: 72726 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 550 Data size: 52250 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 391 Data size: 72726 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/llap/bucketmapjoin1.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/bucketmapjoin1.q.out b/ql/src/test/results/clientpositive/llap/bucketmapjoin1.q.out index fa6a2d0..480775f 100644 --- a/ql/src/test/results/clientpositive/llap/bucketmapjoin1.q.out +++ b/ql/src/test/results/clientpositive/llap/bucketmapjoin1.q.out @@ -399,7 +399,8 @@ STAGE PLANS: Tez #### A masked pattern was here #### Edges: - Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 @@ -478,7 +479,7 @@ STAGE PLANS: name: default.srcbucket_mapjoin Truncated Path -> Alias: /srcbucket_mapjoin [a] - Map 3 + Map 4 Map Operator Tree: TableScan alias: b @@ -605,6 +606,53 @@ STAGE PLANS: TotalFiles: 1 GatherStats: true MultiFileSpray: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) + outputColumnNames: key, value1, value2 + Statistics: Num rows: 58 Data size: 16921 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value1, 'hll'), compute_stats(value2, 'hll') + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + tag: -1 + value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>) + auto parallelism: false + Reducer 3 + Execution mode: llap + Needs Tagging: false + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + columns _col0,_col1,_col2 + columns.types struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>:struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>:struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary> + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-2 Dependency Collection @@ -641,6 +689,11 @@ STAGE PLANS: Stats Work Basic Stats Work: #### A masked pattern was here #### + Column Stats Desc: + Columns: key, value1, value2 + Column Types: string, string, string + Table: default.bucketmapjoin_tmp_result + Is Table Level Stats: true PREHOOK: query: insert overwrite table bucketmapjoin_tmp_result select /*+mapjoin(b)*/ a.key, a.value, b.value @@ -766,7 +819,8 @@ STAGE PLANS: Tez #### A masked pattern was here #### Edges: - Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 @@ -845,7 +899,7 @@ STAGE PLANS: name: default.srcbucket_mapjoin Truncated Path -> Alias: /srcbucket_mapjoin [a] - Map 3 + Map 4 Map Operator Tree: TableScan alias: b @@ -951,7 +1005,7 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"} + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value1":"true","value2":"true"}} bucket_count -1 column.name.delimiter , columns key,value1,value2 @@ -972,6 +1026,53 @@ STAGE PLANS: TotalFiles: 1 GatherStats: true MultiFileSpray: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) + outputColumnNames: key, value1, value2 + Statistics: Num rows: 58 Data size: 16921 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value1, 'hll'), compute_stats(value2, 'hll') + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + tag: -1 + value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>) + auto parallelism: false + Reducer 3 + Execution mode: llap + Needs Tagging: false + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + columns _col0,_col1,_col2 + columns.types struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>:struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>:struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary> + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-2 Dependency Collection @@ -985,7 +1086,7 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"} + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value1":"true","value2":"true"}} bucket_count -1 column.name.delimiter , columns key,value1,value2 @@ -1008,6 +1109,11 @@ STAGE PLANS: Stats Work Basic Stats Work: #### A masked pattern was here #### + Column Stats Desc: + Columns: key, value1, value2 + Column Types: string, string, string + Table: default.bucketmapjoin_tmp_result + Is Table Level Stats: true PREHOOK: query: insert overwrite table bucketmapjoin_tmp_result select /*+mapjoin(a)*/ a.key, a.value, b.value
