http://git-wip-us.apache.org/repos/asf/hive/blob/f562dfb5/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 new file mode 100644 index 0000000..46d6281 --- /dev/null +++ b/ql/src/test/results/clientpositive/llap/join32_lessSize.q.out @@ -0,0 +1,2501 @@ +PREHOOK: query: -- SORT_QUERY_RESULTS + +CREATE TABLE dest_j1(key STRING, value STRING, val2 STRING) STORED AS TEXTFILE +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@dest_j1 +POSTHOOK: query: -- SORT_QUERY_RESULTS + +CREATE TABLE dest_j1(key STRING, value STRING, val2 STRING) STORED AS TEXTFILE +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@dest_j1 +PREHOOK: query: CREATE TABLE dest_j2(key STRING, value STRING, val2 STRING) STORED AS TEXTFILE +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@dest_j2 +POSTHOOK: query: CREATE TABLE dest_j2(key STRING, value STRING, val2 STRING) STORED AS TEXTFILE +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@dest_j2 +PREHOOK: query: -- Since the inputs are small, it should be automatically converted to mapjoin + +EXPLAIN EXTENDED +INSERT OVERWRITE TABLE dest_j1 +SELECT x.key, z.value, y.value +FROM src1 x JOIN src y ON (x.key = y.key) +JOIN srcpart z ON (x.value = z.value and z.ds='2008-04-08' and z.hr=11) +PREHOOK: type: QUERY +POSTHOOK: query: -- Since the inputs are small, it should be automatically converted to mapjoin + +EXPLAIN EXTENDED +INSERT OVERWRITE TABLE dest_j1 +SELECT x.key, z.value, y.value +FROM src1 x JOIN src y ON (x.key = y.key) +JOIN srcpart z ON (x.value = z.value and z.ds='2008-04-08' and z.hr=11) +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-2 depends on stages: Stage-1 + Stage-0 depends on stages: Stage-2 + Stage-3 depends on stages: Stage-0 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Map 1 <- Map 3 (BROADCAST_EDGE) + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: z + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: value is not null (type: boolean) + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: value (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 500 Data size: 184500 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + Estimated key counts: Map 3 => 25 + keys: + 0 _col0 (type: string) + 1 _col1 (type: string) + outputColumnNames: _col0, _col3 + input vertices: + 1 Map 3 + Position of Big Table: 0 + Statistics: Num rows: 58 Data size: 10266 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col3 (type: string) + null sort order: a + sort order: + + Map-reduce partition columns: _col3 (type: string) + Statistics: Num rows: 58 Data size: 10266 Basic stats: COMPLETE Column stats: COMPLETE + tag: 0 + value expressions: _col0 (type: string) + auto parallelism: true + Execution mode: llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: hr=11 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2008-04-08 + hr 11 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + numFiles 1 + numRows 500 + partition_columns ds/hr + partition_columns.types string:string + rawDataSize 5312 + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.srcpart + name: default.srcpart + Truncated Path -> Alias: + /srcpart/ds=2008-04-08/hr=11 [z] + Map 3 + Map Operator Tree: + TableScan + alias: x + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: (key is not null and value is not null) (type: boolean) + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: string) + null sort order: a + sort order: + + Map-reduce partition columns: _col1 (type: string) + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE + tag: 1 + value expressions: _col0 (type: string) + auto parallelism: true + Execution mode: llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: src1 + 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":{"key":"true","value":"true"}} + bucket_count -1 + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.src1 + numFiles 1 + numRows 25 + rawDataSize 191 + serialization.ddl struct src1 { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 216 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.src1 + numFiles 1 + numRows 25 + rawDataSize 191 + serialization.ddl struct src1 { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 216 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src1 + name: default.src1 + Truncated Path -> Alias: + /src1 [x] + Map 4 + Map Operator Tree: + TableScan + alias: y + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: key is not null (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 500 Data size: 89000 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: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + tag: 1 + value expressions: _col1 (type: string) + auto parallelism: true + Execution mode: llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: src + 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":{"key":"true","value":"true"}} + bucket_count -1 + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.src + numFiles 1 + numRows 500 + rawDataSize 5312 + serialization.ddl struct src { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.src + numFiles 1 + numRows 500 + rawDataSize 5312 + serialization.ddl struct src { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src + name: default.src + Truncated Path -> Alias: + /src [y] + Reducer 2 + Execution mode: llap + Needs Tagging: false + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col3 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col3, _col6 + Position of Big Table: 1 + Statistics: Num rows: 141 Data size: 37788 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col3 (type: string), _col0 (type: string), _col6 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 141 Data size: 37788 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + GlobalTableId: 1 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 141 Data size: 37788 Basic stats: COMPLETE Column stats: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"} + bucket_count -1 + columns key,value,val2 + columns.comments + columns.types string:string:string +#### A masked pattern was here #### + name default.dest_j1 + numFiles 0 + numRows 0 + rawDataSize 0 + serialization.ddl struct dest_j1 { string key, string value, string val2} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 0 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.dest_j1 + TotalFiles: 1 + GatherStats: true + MultiFileSpray: false + + Stage: Stage-2 + Dependency Collection + + Stage: Stage-0 + Move Operator + tables: + replace: true +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"} + bucket_count -1 + columns key,value,val2 + columns.comments + columns.types string:string:string +#### A masked pattern was here #### + name default.dest_j1 + numFiles 0 + numRows 0 + rawDataSize 0 + serialization.ddl struct dest_j1 { string key, string value, string val2} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 0 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.dest_j1 + + Stage: Stage-3 + Stats-Aggr Operator +#### A masked pattern was here #### + +PREHOOK: query: INSERT OVERWRITE TABLE dest_j1 +SELECT x.key, z.value, y.value +FROM src1 x JOIN src y ON (x.key = y.key) +JOIN srcpart z ON (x.value = z.value and z.ds='2008-04-08' and z.hr=11) +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Input: default@src1 +PREHOOK: Input: default@srcpart +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +PREHOOK: Output: default@dest_j1 +POSTHOOK: query: INSERT OVERWRITE TABLE dest_j1 +SELECT x.key, z.value, y.value +FROM src1 x JOIN src y ON (x.key = y.key) +JOIN srcpart z ON (x.value = z.value and z.ds='2008-04-08' and z.hr=11) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Input: default@src1 +POSTHOOK: Input: default@srcpart +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +POSTHOOK: Output: default@dest_j1 +POSTHOOK: Lineage: dest_j1.key SIMPLE [(src1)x.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: dest_j1.val2 SIMPLE [(src)y.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest_j1.value SIMPLE [(srcpart)z.FieldSchema(name:value, type:string, comment:default), ] +PREHOOK: query: select * from dest_j1 +PREHOOK: type: QUERY +PREHOOK: Input: default@dest_j1 +#### A masked pattern was here #### +POSTHOOK: query: select * from dest_j1 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@dest_j1 +#### A masked pattern was here #### +146 val_146 val_146 +146 val_146 val_146 +146 val_146 val_146 +146 val_146 val_146 +150 val_150 val_150 +213 val_213 val_213 +213 val_213 val_213 +213 val_213 val_213 +213 val_213 val_213 +238 val_238 val_238 +238 val_238 val_238 +238 val_238 val_238 +238 val_238 val_238 +255 val_255 val_255 +255 val_255 val_255 +255 val_255 val_255 +255 val_255 val_255 +273 val_273 val_273 +273 val_273 val_273 +273 val_273 val_273 +273 val_273 val_273 +273 val_273 val_273 +273 val_273 val_273 +273 val_273 val_273 +273 val_273 val_273 +273 val_273 val_273 +278 val_278 val_278 +278 val_278 val_278 +278 val_278 val_278 +278 val_278 val_278 +311 val_311 val_311 +311 val_311 val_311 +311 val_311 val_311 +311 val_311 val_311 +311 val_311 val_311 +311 val_311 val_311 +311 val_311 val_311 +311 val_311 val_311 +311 val_311 val_311 +401 val_401 val_401 +401 val_401 val_401 +401 val_401 val_401 +401 val_401 val_401 +401 val_401 val_401 +401 val_401 val_401 +401 val_401 val_401 +401 val_401 val_401 +401 val_401 val_401 +401 val_401 val_401 +401 val_401 val_401 +401 val_401 val_401 +401 val_401 val_401 +401 val_401 val_401 +401 val_401 val_401 +401 val_401 val_401 +401 val_401 val_401 +401 val_401 val_401 +401 val_401 val_401 +401 val_401 val_401 +401 val_401 val_401 +401 val_401 val_401 +401 val_401 val_401 +401 val_401 val_401 +401 val_401 val_401 +406 val_406 val_406 +406 val_406 val_406 +406 val_406 val_406 +406 val_406 val_406 +406 val_406 val_406 +406 val_406 val_406 +406 val_406 val_406 +406 val_406 val_406 +406 val_406 val_406 +406 val_406 val_406 +406 val_406 val_406 +406 val_406 val_406 +406 val_406 val_406 +406 val_406 val_406 +406 val_406 val_406 +406 val_406 val_406 +66 val_66 val_66 +98 val_98 val_98 +98 val_98 val_98 +98 val_98 val_98 +98 val_98 val_98 +PREHOOK: query: EXPLAIN EXTENDED +INSERT OVERWRITE TABLE dest_j1 +SELECT x.key, z.value, y.value +FROM src w JOIN src1 x ON (x.value = w.value) +JOIN src y ON (x.key = y.key) +JOIN src1 z ON (x.key = z.key) +PREHOOK: type: QUERY +POSTHOOK: query: EXPLAIN EXTENDED +INSERT OVERWRITE TABLE dest_j1 +SELECT x.key, z.value, y.value +FROM src w JOIN src1 x ON (x.value = w.value) +JOIN src y ON (x.key = y.key) +JOIN src1 z ON (x.key = z.key) +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-2 depends on stages: Stage-1 + Stage-0 depends on stages: Stage-2 + Stage-3 depends on stages: Stage-0 + +STAGE PLANS: + Stage: Stage-1 + 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) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: x + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: (value is not null and key is not null) (type: boolean) + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + Estimated key counts: Map 4 => 25 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col3 + input vertices: + 1 Map 4 + Position of Big Table: 0 + Statistics: Num rows: 44 Data size: 11616 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: string) + null sort order: a + sort order: + + Map-reduce partition columns: _col1 (type: string) + Statistics: Num rows: 44 Data size: 11616 Basic stats: COMPLETE Column stats: COMPLETE + tag: 0 + value expressions: _col0 (type: string), _col3 (type: string) + auto parallelism: true + Execution mode: llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: src1 + 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":{"key":"true","value":"true"}} + bucket_count -1 + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.src1 + numFiles 1 + numRows 25 + rawDataSize 191 + serialization.ddl struct src1 { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 216 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.src1 + numFiles 1 + numRows 25 + rawDataSize 191 + serialization.ddl struct src1 { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 216 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src1 + name: default.src1 + Truncated Path -> Alias: + /src1 [x] + Map 4 + Map Operator Tree: + TableScan + alias: z + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: key is not null (type: boolean) + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 25 Data size: 4375 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: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE + tag: 1 + value expressions: _col1 (type: string) + auto parallelism: true + Execution mode: llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: src1 + 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":{"key":"true","value":"true"}} + bucket_count -1 + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.src1 + numFiles 1 + numRows 25 + rawDataSize 191 + serialization.ddl struct src1 { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 216 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.src1 + numFiles 1 + numRows 25 + rawDataSize 191 + serialization.ddl struct src1 { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 216 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src1 + name: default.src1 + Truncated Path -> Alias: + /src1 [z] + Map 5 + Map Operator Tree: + TableScan + alias: w + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: value is not null (type: boolean) + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: value (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 500 Data size: 45500 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: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE + tag: 1 + auto parallelism: true + Execution mode: llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: src + 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":{"key":"true","value":"true"}} + bucket_count -1 + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.src + numFiles 1 + numRows 500 + rawDataSize 5312 + serialization.ddl struct src { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.src + numFiles 1 + numRows 500 + rawDataSize 5312 + serialization.ddl struct src { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src + name: default.src + Truncated Path -> Alias: + /src [w] + Map 6 + Map Operator Tree: + TableScan + alias: y + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: key is not null (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 500 Data size: 89000 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: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + tag: 1 + value expressions: _col1 (type: string) + auto parallelism: true + Execution mode: llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: src + 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":{"key":"true","value":"true"}} + bucket_count -1 + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.src + numFiles 1 + numRows 500 + rawDataSize 5312 + serialization.ddl struct src { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.src + numFiles 1 + numRows 500 + rawDataSize 5312 + serialization.ddl struct src { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src + name: default.src + Truncated Path -> Alias: + /src [y] + Reducer 2 + Execution mode: llap + Needs Tagging: false + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col3 + Position of Big Table: 1 + Statistics: Num rows: 102 Data size: 17850 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: 102 Data size: 17850 Basic stats: COMPLETE Column stats: COMPLETE + tag: 0 + value expressions: _col3 (type: string) + auto parallelism: true + Reducer 3 + Execution mode: llap + Needs Tagging: false + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col3, _col6 + Position of Big Table: 0 + Statistics: Num rows: 248 Data size: 65968 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), _col3 (type: string), _col6 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 248 Data size: 65968 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + GlobalTableId: 1 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 248 Data size: 65968 Basic stats: COMPLETE Column stats: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"} + bucket_count -1 + columns key,value,val2 + columns.comments + columns.types string:string:string +#### A masked pattern was here #### + name default.dest_j1 + numFiles 1 + numRows 85 + rawDataSize 1600 + serialization.ddl struct dest_j1 { string key, string value, string val2} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 1685 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.dest_j1 + TotalFiles: 1 + GatherStats: true + MultiFileSpray: false + + Stage: Stage-2 + Dependency Collection + + Stage: Stage-0 + Move Operator + tables: + replace: true +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"} + bucket_count -1 + columns key,value,val2 + columns.comments + columns.types string:string:string +#### A masked pattern was here #### + name default.dest_j1 + numFiles 1 + numRows 85 + rawDataSize 1600 + serialization.ddl struct dest_j1 { string key, string value, string val2} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 1685 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.dest_j1 + + Stage: Stage-3 + Stats-Aggr Operator +#### A masked pattern was here #### + +PREHOOK: query: INSERT OVERWRITE TABLE dest_j1 +SELECT x.key, z.value, y.value +FROM src w JOIN src1 x ON (x.value = w.value) +JOIN src y ON (x.key = y.key) +JOIN src1 z ON (x.key = z.key) +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Input: default@src1 +PREHOOK: Output: default@dest_j1 +POSTHOOK: query: INSERT OVERWRITE TABLE dest_j1 +SELECT x.key, z.value, y.value +FROM src w JOIN src1 x ON (x.value = w.value) +JOIN src y ON (x.key = y.key) +JOIN src1 z ON (x.key = z.key) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Input: default@src1 +POSTHOOK: Output: default@dest_j1 +POSTHOOK: Lineage: dest_j1.key SIMPLE [(src1)x.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: dest_j1.val2 SIMPLE [(src)y.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest_j1.value SIMPLE [(src1)z.FieldSchema(name:value, type:string, comment:default), ] +PREHOOK: query: select * from dest_j1 +PREHOOK: type: QUERY +PREHOOK: Input: default@dest_j1 +#### A masked pattern was here #### +POSTHOOK: query: select * from dest_j1 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@dest_j1 +#### A masked pattern was here #### +146 val_146 val_146 +146 val_146 val_146 +146 val_146 val_146 +146 val_146 val_146 +150 val_150 val_150 +213 val_213 val_213 +213 val_213 val_213 +213 val_213 val_213 +213 val_213 val_213 +238 val_238 val_238 +238 val_238 val_238 +238 val_238 val_238 +238 val_238 val_238 +255 val_255 val_255 +255 val_255 val_255 +255 val_255 val_255 +255 val_255 val_255 +273 val_273 val_273 +273 val_273 val_273 +273 val_273 val_273 +273 val_273 val_273 +273 val_273 val_273 +273 val_273 val_273 +273 val_273 val_273 +273 val_273 val_273 +273 val_273 val_273 +278 val_278 val_278 +278 val_278 val_278 +278 val_278 val_278 +278 val_278 val_278 +311 val_311 val_311 +311 val_311 val_311 +311 val_311 val_311 +311 val_311 val_311 +311 val_311 val_311 +311 val_311 val_311 +311 val_311 val_311 +311 val_311 val_311 +311 val_311 val_311 +401 val_401 val_401 +401 val_401 val_401 +401 val_401 val_401 +401 val_401 val_401 +401 val_401 val_401 +401 val_401 val_401 +401 val_401 val_401 +401 val_401 val_401 +401 val_401 val_401 +401 val_401 val_401 +401 val_401 val_401 +401 val_401 val_401 +401 val_401 val_401 +401 val_401 val_401 +401 val_401 val_401 +401 val_401 val_401 +401 val_401 val_401 +401 val_401 val_401 +401 val_401 val_401 +401 val_401 val_401 +401 val_401 val_401 +401 val_401 val_401 +401 val_401 val_401 +401 val_401 val_401 +401 val_401 val_401 +406 val_406 val_406 +406 val_406 val_406 +406 val_406 val_406 +406 val_406 val_406 +406 val_406 val_406 +406 val_406 val_406 +406 val_406 val_406 +406 val_406 val_406 +406 val_406 val_406 +406 val_406 val_406 +406 val_406 val_406 +406 val_406 val_406 +406 val_406 val_406 +406 val_406 val_406 +406 val_406 val_406 +406 val_406 val_406 +66 val_66 val_66 +98 val_98 val_98 +98 val_98 val_98 +98 val_98 val_98 +98 val_98 val_98 +PREHOOK: query: EXPLAIN EXTENDED +INSERT OVERWRITE TABLE dest_j2 +SELECT res.key, z.value, res.value +FROM (select x.key, x.value from src1 x JOIN src y ON (x.key = y.key)) res +JOIN srcpart z ON (res.value = z.value and z.ds='2008-04-08' and z.hr=11) +PREHOOK: type: QUERY +POSTHOOK: query: EXPLAIN EXTENDED +INSERT OVERWRITE TABLE dest_j2 +SELECT res.key, z.value, res.value +FROM (select x.key, x.value from src1 x JOIN src y ON (x.key = y.key)) res +JOIN srcpart z ON (res.value = z.value and z.ds='2008-04-08' and z.hr=11) +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-2 depends on stages: Stage-1 + Stage-0 depends on stages: Stage-2 + Stage-3 depends on stages: Stage-0 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Map 3 <- Map 4 (BROADCAST_EDGE) + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: z + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: value is not null (type: boolean) + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: value (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 500 Data size: 184500 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: 500 Data size: 184500 Basic stats: COMPLETE Column stats: COMPLETE + tag: 0 + auto parallelism: true + Execution mode: llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: hr=11 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2008-04-08 + hr 11 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + numFiles 1 + numRows 500 + partition_columns ds/hr + partition_columns.types string:string + rawDataSize 5312 + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.srcpart + name: default.srcpart + Truncated Path -> Alias: + /srcpart/ds=2008-04-08/hr=11 [z] + Map 3 + Map Operator Tree: + TableScan + alias: y + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: key is not null (type: boolean) + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + Estimated key counts: Map 4 => 25 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col1, _col2 + input vertices: + 1 Map 4 + Position of Big Table: 0 + Statistics: Num rows: 60 Data size: 10500 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col1 (type: string), _col2 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 60 Data size: 10500 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: string) + null sort order: a + sort order: + + Map-reduce partition columns: _col1 (type: string) + Statistics: Num rows: 60 Data size: 10500 Basic stats: COMPLETE Column stats: COMPLETE + tag: 1 + value expressions: _col0 (type: string) + auto parallelism: true + Execution mode: llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: src + 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":{"key":"true","value":"true"}} + bucket_count -1 + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.src + numFiles 1 + numRows 500 + rawDataSize 5312 + serialization.ddl struct src { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.src + numFiles 1 + numRows 500 + rawDataSize 5312 + serialization.ddl struct src { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src + name: default.src + Truncated Path -> Alias: + /src [y] + Map 4 + Map Operator Tree: + TableScan + alias: x + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: (key is not null and value is not null) (type: boolean) + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 25 Data size: 4375 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: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE + tag: 1 + value expressions: _col1 (type: string) + auto parallelism: true + Execution mode: llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: src1 + 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":{"key":"true","value":"true"}} + bucket_count -1 + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.src1 + numFiles 1 + numRows 25 + rawDataSize 191 + serialization.ddl struct src1 { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 216 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.src1 + numFiles 1 + numRows 25 + rawDataSize 191 + serialization.ddl struct src1 { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 216 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src1 + name: default.src1 + Truncated Path -> Alias: + /src1 [x] + Reducer 2 + Execution mode: llap + Needs Tagging: false + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col1 (type: string) + outputColumnNames: _col0, _col3, _col4 + Position of Big Table: 0 + Statistics: Num rows: 140 Data size: 37240 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col3 (type: string), _col0 (type: string), _col4 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 140 Data size: 37240 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + GlobalTableId: 1 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 140 Data size: 37240 Basic stats: COMPLETE Column stats: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"} + bucket_count -1 + columns key,value,val2 + columns.comments + columns.types string:string:string +#### A masked pattern was here #### + name default.dest_j2 + numFiles 0 + numRows 0 + rawDataSize 0 + serialization.ddl struct dest_j2 { string key, string value, string val2} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 0 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.dest_j2 + TotalFiles: 1 + GatherStats: true + MultiFileSpray: false + + Stage: Stage-2 + Dependency Collection + + Stage: Stage-0 + Move Operator + tables: + replace: true +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"} + bucket_count -1 + columns key,value,val2 + columns.comments + columns.types string:string:string +#### A masked pattern was here #### + name default.dest_j2 + numFiles 0 + numRows 0 + rawDataSize 0 + serialization.ddl struct dest_j2 { string key, string value, string val2} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 0 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.dest_j2 + + Stage: Stage-3 + Stats-Aggr Operator +#### A masked pattern was here #### + +PREHOOK: query: INSERT OVERWRITE TABLE dest_j2 +SELECT res.key, z.value, res.value +FROM (select x.key, x.value from src1 x JOIN src y ON (x.key = y.key)) res +JOIN srcpart z ON (res.value = z.value and z.ds='2008-04-08' and z.hr=11) +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Input: default@src1 +PREHOOK: Input: default@srcpart +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +PREHOOK: Output: default@dest_j2 +POSTHOOK: query: INSERT OVERWRITE TABLE dest_j2 +SELECT res.key, z.value, res.value +FROM (select x.key, x.value from src1 x JOIN src y ON (x.key = y.key)) res +JOIN srcpart z ON (res.value = z.value and z.ds='2008-04-08' and z.hr=11) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Input: default@src1 +POSTHOOK: Input: default@srcpart +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +POSTHOOK: Output: default@dest_j2 +POSTHOOK: Lineage: dest_j2.key SIMPLE [(src1)x.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: dest_j2.val2 SIMPLE [(src1)x.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest_j2.value SIMPLE [(srcpart)z.FieldSchema(name:value, type:string, comment:default), ] +PREHOOK: query: select * from dest_j2 +PREHOOK: type: QUERY +PREHOOK: Input: default@dest_j2 +#### A masked pattern was here #### +POSTHOOK: query: select * from dest_j2 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@dest_j2 +#### A masked pattern was here #### +146 val_146 val_146 +146 val_146 val_146 +146 val_146 val_146 +146 val_146 val_146 +150 val_150 val_150 +213 val_213 val_213 +213 val_213 val_213 +213 val_213 val_213 +213 val_213 val_213 +238 val_238 val_238 +238 val_238 val_238 +238 val_238 val_238 +238 val_238 val_238 +255 val_255 val_255 +255 val_255 val_255 +255 val_255 val_255 +255 val_255 val_255 +273 val_273 val_273 +273 val_273 val_273 +273 val_273 val_273 +273 val_273 val_273 +273 val_273 val_273 +273 val_273 val_273 +273 val_273 val_273 +273 val_273 val_273 +273 val_273 val_273 +278 val_278 val_278 +278 val_278 val_278 +278 val_278 val_278 +278 val_278 val_278 +311 val_311 val_311 +311 val_311 val_311 +311 val_311 val_311 +311 val_311 val_311 +311 val_311 val_311 +311 val_311 val_311 +311 val_311 val_311 +311 val_311 val_311 +311 val_311 val_311 +401 val_401 val_401 +401 val_401 val_401 +401 val_401 val_401 +401 val_401 val_401 +401 val_401 val_401 +401 val_401 val_401 +401 val_401 val_401 +401 val_401 val_401 +401 val_401 val_401 +401 val_401 val_401 +401 val_401 val_401 +401 val_401 val_401 +401 val_401 val_401 +401 val_401 val_401 +401 val_401 val_401 +401 val_401 val_401 +401 val_401 val_401 +401 val_401 val_401 +401 val_401 val_401 +401 val_401 val_401 +401 val_401 val_401 +401 val_401 val_401 +401 val_401 val_401 +401 val_401 val_401 +401 val_401 val_401 +406 val_406 val_406 +406 val_406 val_406 +406 val_406 val_406 +406 val_406 val_406 +406 val_406 val_406 +406 val_406 val_406 +406 val_406 val_406 +406 val_406 val_406 +406 val_406 val_406 +406 val_406 val_406 +406 val_406 val_406 +406 val_406 val_406 +406 val_406 val_406 +406 val_406 val_406 +406 val_406 val_406 +406 val_406 val_406 +66 val_66 val_66 +98 val_98 val_98 +98 val_98 val_98 +98 val_98 val_98 +98 val_98 val_98 +PREHOOK: query: EXPLAIN EXTENDED +INSERT OVERWRITE TABLE dest_j2 +SELECT res.key, z.value, res.value +FROM (select x.key, x.value from src1 x LEFT OUTER JOIN src y ON (x.key = y.key)) res +JOIN srcpart z ON (res.value = z.value and z.ds='2008-04-08' and z.hr=11) +PREHOOK: type: QUERY +POSTHOOK: query: EXPLAIN EXTENDED +INSERT OVERWRITE TABLE dest_j2 +SELECT res.key, z.value, res.value +FROM (select x.key, x.value from src1 x LEFT OUTER JOIN src y ON (x.key = y.key)) res +JOIN srcpart z ON (res.value = z.value and z.ds='2008-04-08' and z.hr=11) +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-2 depends on stages: Stage-1 + Stage-0 depends on stages: Stage-2 + Stage-3 depends on stages: Stage-0 + +STAGE PLANS: + Stage: Stage-1 + 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) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: z + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: value is not null (type: boolean) + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: value (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 500 Data size: 184500 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: 500 Data size: 184500 Basic stats: COMPLETE Column stats: COMPLETE + tag: 0 + auto parallelism: true + Execution mode: llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: hr=11 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2008-04-08 + hr 11 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + numFiles 1 + numRows 500 + partition_columns ds/hr + partition_columns.types string:string + rawDataSize 5312 + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.srcpart + name: default.srcpart + Truncated Path -> Alias: + /srcpart/ds=2008-04-08/hr=11 [z] + Map 3 + Map Operator Tree: + TableScan + alias: y + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 500 Data size: 43500 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: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + tag: 0 + auto parallelism: true + Execution mode: llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: src + 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":{"key":"true","value":"true"}} + bucket_count -1 + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.src + numFiles 1 + numRows 500 + rawDataSize 5312 + serialization.ddl struct src { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.src + numFiles 1 + numRows 500 + rawDataSize 5312 + serialization.ddl struct src { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src + name: default.src + Truncated Path -> Alias: + /src [y] + Map 5 + Map Operator Tree: + TableScan + alias: x + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: value is not null (type: boolean) + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 25 Data size: 4375 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: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE + tag: 1 + value expressions: _col1 (type: string) + auto parallelism: true + Execution mode: llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: src1 + 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":{"key":"true","value":"true"}} + bucket_count -1 + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.src1 + numFiles 1 + numRows 25 + rawDataSize 191 + serialization.ddl struct src1 { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 216 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.src1 + numFiles 1 + numRows 25 + rawDataSize 191 + serialization.ddl struct src1 { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 216 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src1 + name: default.src1 + Truncated Path -> Alias: + /src1 [x] + Reducer 2 + Execution mode: llap + Needs Tagging: false + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col1 (type: string) + outputColumnNames: _col0, _col3, _col4 + Position of Big Table: 0 + Statistics: Num rows: 140 Data size: 37240 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col3 (type: string), _col0 (type: string), _col4 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 140 Data size: 37240 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + GlobalTableId: 1 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 140 Data size: 37240 Basic stats: COMPLETE Column stats: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"} + bucket_count -1 + columns key,value,val2 + columns.comments + columns.types string:string:string +#### A masked pattern was here #### + name default.dest_j2 + numFiles 1 + numRows 85 + rawDataSize 1600 + serialization.ddl struct dest_j2 { string key, string value, string val2} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 1685 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.dest_j2 + TotalFiles: 1 + GatherStats: true + MultiFileSpray: false + Reducer 4 + Execution mode: llap + Needs Tagging: false + Reduce Operator Tree: + Merge Join Operator + condition map: + Right Outer Join0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col1, _col2 + Position of Big Table: 1 + Statistics: Num rows: 60 Data size: 10500 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col1 (type: string), _col2 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 60 Data size: 10500 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: string) + null sort order: a + sort order: + + Map-reduce partition columns: _col1 (type: string) + Statistics: Num rows: 60 Data size: 10500 Basic stats: COMPLETE Column stats: COMPLETE + tag: 1 + value expressions: _col0 (type: string) + auto parallelism: true + + Stage: Stage-2 + Dependency Collection + + Stage: Stage-0 + Move Operator + tables: + replace: true +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"} + bucket_count -1 + columns key,value,val2 + columns.comments + columns.types string:string:string +#### A masked pattern was here #### + name default.dest_j2 + numFiles 1 + numRows 85 + rawDataSize 1600 + serialization.ddl struct dest_j2 { string key, string value, string val2} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 1685 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.dest_j2 + + Stage: Stage-3 + Stats-Aggr Operator +#### A masked pattern was here #### + +PREHOOK: query: INSERT OVERWRITE TABLE dest_j2 +SELECT res.key, z.value, res.value +FROM (select x.key, x.value from src1 x LEFT OUTER JOIN src y ON (x.key = y.key)) res +JOIN srcpart z ON (res.value = z.value and z.ds='2008-04-08' and z.hr=11) +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Input: default@src1 +PREHOOK: Input: default@srcpart +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +PREHOOK: Output: default@dest_j2 +POSTHOOK: query: INSERT OVERWRITE TABLE dest_j2 +SELECT res.key, z.value, res.value +FROM (select x.key, x.value from src1 x LEFT OUTER JOIN src y ON (x.key = y.key)) res +JOIN srcpart z ON (res.value = z.value and z.ds='2008-04-08' and z.hr=11) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Input: default@src1 +POSTHOOK: Input: default@srcpart +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +POSTHOOK: Output: default@dest_j2 +POSTHOOK: Lineage: dest_j2.key SIMPLE [(src1)x.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: dest_j2.val2 SIMPLE [(src1)x.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest_j2.value SIMPLE [(srcpart)z.FieldSchema(name:value, type:string, comment:default), ] +PREHOOK: query: select * from dest_j2 +PREHOOK: type: QUERY +PREHOOK: Input: default@dest_j2 +#### A masked pattern was here #### +POSTHOOK: query: select * from dest_j2 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@dest_j2 +#### A masked pattern was here #### + val_165 val_165 + val_165 val_165 + val_193 val_193 + val_193 val_193 + val_193 val_193 + val_265 val_265 + val_265 val_265 + val_27 val_27 + val_409 val_409 + val_409 val_409 + val_409 val_409 + val_484 val_484 +146 val_146 val_146 +146 val_146 val_146 +146 val_146 val_146 +146 val_146 val_146 +150 val_150 val_150 +213 val_213 val_213 +213 val_213 val_213 +213 val_213 val_213 +213 val_213 val_213 +238 val_238 val_238 +238 val_238 val_238 +238 val_238 val_238 +238 val_238 val_238 +255 val_255 val_255 +255 val_255 val_255 +255 val_255 val_255 +255 val_255 val_255 +273 val_273 val_273 +273 val_273 val_273 +273 val_273 val_273 +273 val_273 val_273 +273 val_273 val_273 +273 val_273 val_273 +273 val_273 val_273 +273 val_273 val_273 +273 val_273 val_273 +278 val_278 val_278 +278 val_278 val_278 +278 val_278 val_278 +278 val_278 val_278 +311 val_311 val_311 +311 val_311 val_311 +311 val_311 val_311 +311 val_311 val_311 +311 val_311 val_311 +311 val_311 val_311 +311 val_311 val_311 +311 val_311 val_311 +311 val_311 val_311 +401 val_401 val_401 +401 val_401 val_401 +401 val_401 val_401 +401 val_401 val_401 +401 val_401 val_401 +401 val_401 val_401 +401 val_401 val_401 +401 val_401 val_401 +401 val_401 val_401 +401 val_401 val_401 +401 val_401 val_401 +401 val_401 val_401 +401 val_401 val_401 +401 val_401 val_401 +401 val_401 val_401 +401 val_401 val_401 +401 val_401 val_401 +401 val_401 val_401 +401 val_401 val_401 +401 val_401 val_401 +401 val_401 val_401 +401 val_401 val_401 +401 val_401 val_401 +401 val_401 val_401 +401 val_401 val_401 +406 val_406 val_406 +406 val_406 val_406 +406 val_406 val_406 +406 val_406 val_406 +406 val_406 val_406 +406 val_406 val_406 +406 val_406 val_406 +406 val_406 val_406 +406 val_406 val_406 +406 val_406 val_406 +406 val_406 val_406 +406 val_406 val_406 +406 val_406 val_406 +406 val_406 val_406 +406 val_406 val_406 +406 val_406 val_406 +66 val_66 val_66 +98 val_98 val_98 +98 val_98 val_98 +98 val_98 val_98 +98 val_98 val_98 +PREHOOK: query: EXPLAIN +INSERT OVERWRITE TABLE dest_j2 +SELECT res.key, x.value, res.value +FROM (select x.key, x.value from src1 x JOIN src y ON (x.key = y.key)) res +JOIN srcpart x ON (res.value = x.value and x.ds='2008-04-08' and x.hr=11) +PREHOOK: type: QUERY +POSTHOOK: query: EXPLAIN +INSERT OVERWRITE TABLE dest_j2 +SELECT res.key, x.value, res.value +FROM (select x.key, x.value from src1 x JOIN src y ON (x.key = y.key)) res +JOIN srcpart x ON (res.value = x.value and x.ds='2008-04-08' and x.hr=11) +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-2 depends on stages: Stage-1 + Stage-0 depends on stages: Stage-2 + Stage-3 depends on stages: Stage-0 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Map 3 <- Map 4 (BROADCAST_EDGE) + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: x + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: value is not null (type: boolean) + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: value (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 500 Data size: 184500 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: 184500 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: llap + LLAP IO: no inputs + Map 3 + Map Operator Tree: + TableScan + alias: y + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 500 Data size
<TRUNCATED>