http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/llap/join1.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/join1.q.out b/ql/src/test/results/clientpositive/llap/join1.q.out index 661f55c..3c0a155 100644 --- a/ql/src/test/results/clientpositive/llap/join1.q.out +++ b/ql/src/test/results/clientpositive/llap/join1.q.out @@ -25,7 +25,8 @@ 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 @@ -47,7 +48,7 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs - Map 3 + Map 4 Map Operator Tree: TableScan alias: src2 @@ -90,6 +91,34 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.dest_j1 + Select Operator + expressions: _col0 (type: int), _col1 (type: string) + outputColumnNames: key, value + Statistics: Num rows: 809 Data size: 76855 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 + sort order: + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE + 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>) + 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 @@ -107,6 +136,10 @@ STAGE PLANS: Stage: Stage-3 Stats Work Basic Stats Work: + Column Stats Desc: + Columns: key, value + Column Types: int, string + Table: default.dest_j1 PREHOOK: query: FROM src src1 JOIN src src2 ON (src1.key = src2.key) INSERT OVERWRITE TABLE dest_j1 SELECT src1.key, src2.value
http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/llap/join32_lessSize.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/join32_lessSize.q.out b/ql/src/test/results/clientpositive/llap/join32_lessSize.q.out index 140f87e..5b5be13 100644 --- a/ql/src/test/results/clientpositive/llap/join32_lessSize.q.out +++ b/ql/src/test/results/clientpositive/llap/join32_lessSize.q.out @@ -37,8 +37,9 @@ STAGE PLANS: Tez #### A masked pattern was here #### Edges: - Map 1 <- Map 3 (BROADCAST_EDGE) - Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) + Map 1 <- Map 4 (BROADCAST_EDGE) + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 @@ -58,13 +59,13 @@ STAGE PLANS: Map Join Operator condition map: Inner Join 0 to 1 - Estimated key counts: Map 3 => 25 + Estimated key counts: Map 4 => 25 keys: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col1, _col2, _col3 input vertices: - 1 Map 3 + 1 Map 4 Position of Big Table: 0 Statistics: Num rows: 40 Data size: 10640 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator @@ -129,7 +130,7 @@ STAGE PLANS: name: default.src Truncated Path -> Alias: /src [y] - Map 3 + Map 4 Map Operator Tree: TableScan alias: x @@ -205,7 +206,7 @@ STAGE PLANS: name: default.src1 Truncated Path -> Alias: /src1 [x] - Map 4 + Map 5 Map Operator Tree: TableScan alias: z @@ -331,6 +332,53 @@ STAGE PLANS: TotalFiles: 1 GatherStats: true MultiFileSpray: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) + outputColumnNames: key, value, val2 + Statistics: Num rows: 64 Data size: 17152 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll'), compute_stats(val2, 'hll') + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE + 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: COMPLETE + 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: 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,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 @@ -367,6 +415,11 @@ STAGE PLANS: Stats Work Basic Stats Work: #### A masked pattern was here #### + Column Stats Desc: + Columns: key, value, val2 + Column Types: string, string, string + Table: default.dest_j1 + Is Table Level Stats: true PREHOOK: query: INSERT OVERWRITE TABLE dest_j1 SELECT x.key, z.value, y.value @@ -509,9 +562,10 @@ STAGE PLANS: Tez #### A masked pattern was here #### Edges: - Map 1 <- Map 4 (BROADCAST_EDGE) - Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) - Reducer 3 <- Map 6 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) + Map 1 <- Map 5 (BROADCAST_EDGE) + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 6 (SIMPLE_EDGE) + Reducer 3 <- Map 7 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) + Reducer 4 <- Reducer 3 (CUSTOM_SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 @@ -531,13 +585,13 @@ STAGE PLANS: Map Join Operator condition map: Inner Join 0 to 1 - Estimated key counts: Map 4 => 25 + Estimated key counts: Map 5 => 25 keys: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col3 input vertices: - 1 Map 4 + 1 Map 5 Position of Big Table: 0 Statistics: Num rows: 39 Data size: 10296 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator @@ -602,7 +656,7 @@ STAGE PLANS: name: default.src1 Truncated Path -> Alias: /src1 [x] - Map 4 + Map 5 Map Operator Tree: TableScan alias: z @@ -678,7 +732,7 @@ STAGE PLANS: name: default.src1 Truncated Path -> Alias: /src1 [z] - Map 5 + Map 6 Map Operator Tree: TableScan alias: w @@ -753,7 +807,7 @@ STAGE PLANS: name: default.src Truncated Path -> Alias: /src [w] - Map 6 + Map 7 Map Operator Tree: TableScan alias: y @@ -879,7 +933,7 @@ 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","val2":"true","value":"true"}} bucket_count -1 column.name.delimiter , columns key,value,val2 @@ -900,6 +954,53 @@ STAGE PLANS: TotalFiles: 1 GatherStats: true MultiFileSpray: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) + outputColumnNames: key, value, val2 + Statistics: Num rows: 101 Data size: 26866 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll'), compute_stats(val2, 'hll') + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE + 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 4 + 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: COMPLETE + 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: 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,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 @@ -913,7 +1014,7 @@ 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","val2":"true","value":"true"}} bucket_count -1 column.name.delimiter , columns key,value,val2 @@ -936,6 +1037,11 @@ STAGE PLANS: Stats Work Basic Stats Work: #### A masked pattern was here #### + Column Stats Desc: + Columns: key, value, val2 + Column Types: string, string, string + Table: default.dest_j1 + Is Table Level Stats: true PREHOOK: query: INSERT OVERWRITE TABLE dest_j1 SELECT x.key, z.value, y.value @@ -1074,8 +1180,9 @@ STAGE PLANS: Tez #### A masked pattern was here #### Edges: - Map 3 <- Map 4 (BROADCAST_EDGE) - Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) + Map 4 <- Map 5 (BROADCAST_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 @@ -1155,7 +1262,7 @@ STAGE PLANS: name: default.srcpart Truncated Path -> Alias: /srcpart/ds=2008-04-08/hr=11 [z] - Map 3 + Map 4 Map Operator Tree: TableScan alias: y @@ -1172,13 +1279,13 @@ STAGE PLANS: Map Join Operator condition map: Inner Join 0 to 1 - Estimated key counts: Map 4 => 25 + Estimated key counts: Map 5 => 25 keys: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col1, _col2 input vertices: - 1 Map 4 + 1 Map 5 Position of Big Table: 0 Statistics: Num rows: 40 Data size: 7000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator @@ -1247,7 +1354,7 @@ STAGE PLANS: name: default.src Truncated Path -> Alias: /src [y] - Map 4 + Map 5 Map Operator Tree: TableScan alias: x @@ -1372,6 +1479,53 @@ STAGE PLANS: TotalFiles: 1 GatherStats: true MultiFileSpray: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) + outputColumnNames: key, value, val2 + Statistics: Num rows: 64 Data size: 17024 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll'), compute_stats(val2, 'hll') + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE + 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: COMPLETE + 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: 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,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 @@ -1408,6 +1562,11 @@ STAGE PLANS: Stats Work Basic Stats Work: #### A masked pattern was here #### + Column Stats Desc: + Columns: key, value, val2 + Column Types: string, string, string + Table: default.dest_j2 + Is Table Level Stats: true PREHOOK: query: INSERT OVERWRITE TABLE dest_j2 SELECT res.key, z.value, res.value @@ -1548,8 +1707,9 @@ STAGE PLANS: Tez #### A masked pattern was here #### Edges: - Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) - Reducer 4 <- Map 3 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) + Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 5 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) + Reducer 5 <- Map 4 (SIMPLE_EDGE), Map 6 (SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 @@ -1629,7 +1789,7 @@ STAGE PLANS: name: default.srcpart Truncated Path -> Alias: /srcpart/ds=2008-04-08/hr=11 [z] - Map 3 + Map 4 Map Operator Tree: TableScan alias: y @@ -1700,7 +1860,7 @@ STAGE PLANS: name: default.src Truncated Path -> Alias: /src [y] - Map 5 + Map 6 Map Operator Tree: TableScan alias: x @@ -1804,7 +1964,7 @@ 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","val2":"true","value":"true"}} bucket_count -1 column.name.delimiter , columns key,value,val2 @@ -1825,7 +1985,54 @@ STAGE PLANS: TotalFiles: 1 GatherStats: true MultiFileSpray: false - Reducer 4 + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) + outputColumnNames: key, value, val2 + Statistics: Num rows: 64 Data size: 17024 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll'), compute_stats(val2, 'hll') + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE + 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: COMPLETE + 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: 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,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 + Reducer 5 Execution mode: llap Needs Tagging: false Reduce Operator Tree: @@ -1864,7 +2071,7 @@ 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","val2":"true","value":"true"}} bucket_count -1 column.name.delimiter , columns key,value,val2 @@ -1887,6 +2094,11 @@ STAGE PLANS: Stats Work Basic Stats Work: #### A masked pattern was here #### + Column Stats Desc: + Columns: key, value, val2 + Column Types: string, string, string + Table: default.dest_j2 + Is Table Level Stats: true PREHOOK: query: INSERT OVERWRITE TABLE dest_j2 SELECT res.key, z.value, res.value @@ -2039,8 +2251,9 @@ STAGE PLANS: Tez #### A masked pattern was here #### Edges: - Map 3 <- Map 4 (BROADCAST_EDGE) - Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) + Map 4 <- Map 5 (BROADCAST_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 @@ -2062,7 +2275,7 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 184500 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs - Map 3 + Map 4 Map Operator Tree: TableScan alias: y @@ -2082,7 +2295,7 @@ STAGE PLANS: 1 _col0 (type: string) outputColumnNames: _col1, _col2 input vertices: - 1 Map 4 + 1 Map 5 Statistics: Num rows: 40 Data size: 7000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string), _col2 (type: string) @@ -2096,7 +2309,7 @@ STAGE PLANS: value expressions: _col0 (type: string) Execution mode: llap LLAP IO: no inputs - Map 4 + Map 5 Map Operator Tree: TableScan alias: x @@ -2139,6 +2352,34 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.dest_j2 + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) + outputColumnNames: key, value, val2 + Statistics: Num rows: 64 Data size: 17024 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll'), compute_stats(val2, 'hll') + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 1320 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>), _col2 (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), compute_stats(VALUE._col2) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 1320 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 @@ -2156,6 +2397,10 @@ STAGE PLANS: Stage: Stage-3 Stats Work Basic Stats Work: + Column Stats Desc: + Columns: key, value, val2 + Column Types: string, string, string + Table: default.dest_j2 PREHOOK: query: INSERT OVERWRITE TABLE dest_j2 SELECT res.key, x.value, res.value @@ -2296,8 +2541,9 @@ STAGE PLANS: Tez #### A masked pattern was here #### Edges: - Map 3 <- Map 4 (BROADCAST_EDGE) - Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) + Map 4 <- Map 5 (BROADCAST_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 @@ -2319,7 +2565,7 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 184500 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs - Map 3 + Map 4 Map Operator Tree: TableScan alias: y @@ -2339,7 +2585,7 @@ STAGE PLANS: 1 _col0 (type: string) outputColumnNames: _col1, _col2 input vertices: - 1 Map 4 + 1 Map 5 Statistics: Num rows: 40 Data size: 7000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string), _col2 (type: string) @@ -2353,7 +2599,7 @@ STAGE PLANS: value expressions: _col0 (type: string) Execution mode: llap LLAP IO: no inputs - Map 4 + Map 5 Map Operator Tree: TableScan alias: x @@ -2396,6 +2642,34 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.dest_j2 + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) + outputColumnNames: key, value, val2 + Statistics: Num rows: 64 Data size: 17024 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll'), compute_stats(val2, 'hll') + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 1320 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>), _col2 (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), compute_stats(VALUE._col2) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 1320 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 @@ -2413,6 +2687,10 @@ STAGE PLANS: Stage: Stage-3 Stats Work Basic Stats Work: + Column Stats Desc: + Columns: key, value, val2 + Column Types: string, string, string + Table: default.dest_j2 PREHOOK: query: INSERT OVERWRITE TABLE dest_j2 SELECT res.key, y.value, res.value