http://git-wip-us.apache.org/repos/asf/hive/blob/f562dfb5/ql/src/test/results/clientpositive/llap/stats11.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/stats11.q.out b/ql/src/test/results/clientpositive/llap/stats11.q.out new file mode 100644 index 0000000..b4643b1 --- /dev/null +++ b/ql/src/test/results/clientpositive/llap/stats11.q.out @@ -0,0 +1,996 @@ +PREHOOK: query: CREATE TABLE srcbucket_mapjoin(key int, value string) CLUSTERED BY (key) INTO 2 BUCKETS STORED AS TEXTFILE +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@srcbucket_mapjoin +POSTHOOK: query: CREATE TABLE srcbucket_mapjoin(key int, value string) CLUSTERED BY (key) INTO 2 BUCKETS STORED AS TEXTFILE +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@srcbucket_mapjoin +PREHOOK: query: load data local inpath '../../data/files/srcbucket20.txt' INTO TABLE srcbucket_mapjoin +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@srcbucket_mapjoin +POSTHOOK: query: load data local inpath '../../data/files/srcbucket20.txt' INTO TABLE srcbucket_mapjoin +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@srcbucket_mapjoin +PREHOOK: query: load data local inpath '../../data/files/srcbucket21.txt' INTO TABLE srcbucket_mapjoin +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@srcbucket_mapjoin +POSTHOOK: query: load data local inpath '../../data/files/srcbucket21.txt' INTO TABLE srcbucket_mapjoin +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@srcbucket_mapjoin +PREHOOK: query: CREATE TABLE srcbucket_mapjoin_part (key int, value string) partitioned by (ds string) CLUSTERED BY (key) INTO 4 BUCKETS STORED AS TEXTFILE +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@srcbucket_mapjoin_part +POSTHOOK: query: CREATE TABLE srcbucket_mapjoin_part (key int, value string) partitioned by (ds string) CLUSTERED BY (key) INTO 4 BUCKETS STORED AS TEXTFILE +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@srcbucket_mapjoin_part +PREHOOK: query: explain +load data local inpath '../../data/files/srcbucket20.txt' INTO TABLE srcbucket_mapjoin_part partition(ds='2008-04-08') +PREHOOK: type: LOAD +POSTHOOK: query: explain +load data local inpath '../../data/files/srcbucket20.txt' INTO TABLE srcbucket_mapjoin_part partition(ds='2008-04-08') +POSTHOOK: type: LOAD +STAGE DEPENDENCIES: + Stage-0 is a root stage + Stage-1 depends on stages: Stage-0 + +STAGE PLANS: + Stage: Stage-0 + Move Operator + tables: + partition: + ds 2008-04-08 + replace: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.srcbucket_mapjoin_part + + Stage: Stage-1 + Stats-Aggr Operator + +PREHOOK: query: load data local inpath '../../data/files/srcbucket20.txt' INTO TABLE srcbucket_mapjoin_part partition(ds='2008-04-08') +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@srcbucket_mapjoin_part +POSTHOOK: query: load data local inpath '../../data/files/srcbucket20.txt' INTO TABLE srcbucket_mapjoin_part partition(ds='2008-04-08') +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@srcbucket_mapjoin_part +POSTHOOK: Output: default@srcbucket_mapjoin_part@ds=2008-04-08 +PREHOOK: query: desc formatted srcbucket_mapjoin_part partition(ds='2008-04-08') +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@srcbucket_mapjoin_part +POSTHOOK: query: desc formatted srcbucket_mapjoin_part partition(ds='2008-04-08') +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@srcbucket_mapjoin_part +# col_name data_type comment + +key int +value string + +# Partition Information +# col_name data_type comment + +ds string + +# Detailed Partition Information +Partition Value: [2008-04-08] +Database: default +Table: srcbucket_mapjoin_part +#### A masked pattern was here #### +Partition Parameters: + numFiles 1 + numRows 0 + rawDataSize 0 + totalSize 1358 +#### A masked pattern was here #### + +# Storage Information +SerDe Library: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +InputFormat: org.apache.hadoop.mapred.TextInputFormat +OutputFormat: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat +Compressed: No +Num Buckets: 4 +Bucket Columns: [key] +Sort Columns: [] +Storage Desc Params: + serialization.format 1 +PREHOOK: query: load data local inpath '../../data/files/srcbucket21.txt' INTO TABLE srcbucket_mapjoin_part partition(ds='2008-04-08') +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@srcbucket_mapjoin_part@ds=2008-04-08 +POSTHOOK: query: load data local inpath '../../data/files/srcbucket21.txt' INTO TABLE srcbucket_mapjoin_part partition(ds='2008-04-08') +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@srcbucket_mapjoin_part@ds=2008-04-08 +PREHOOK: query: desc formatted srcbucket_mapjoin_part partition(ds='2008-04-08') +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@srcbucket_mapjoin_part +POSTHOOK: query: desc formatted srcbucket_mapjoin_part partition(ds='2008-04-08') +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@srcbucket_mapjoin_part +# col_name data_type comment + +key int +value string + +# Partition Information +# col_name data_type comment + +ds string + +# Detailed Partition Information +Partition Value: [2008-04-08] +Database: default +Table: srcbucket_mapjoin_part +#### A masked pattern was here #### +Partition Parameters: + numFiles 2 + numRows 0 + rawDataSize 0 + totalSize 2750 +#### A masked pattern was here #### + +# Storage Information +SerDe Library: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +InputFormat: org.apache.hadoop.mapred.TextInputFormat +OutputFormat: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat +Compressed: No +Num Buckets: 4 +Bucket Columns: [key] +Sort Columns: [] +Storage Desc Params: + serialization.format 1 +PREHOOK: query: load data local inpath '../../data/files/srcbucket22.txt' INTO TABLE srcbucket_mapjoin_part partition(ds='2008-04-08') +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@srcbucket_mapjoin_part@ds=2008-04-08 +POSTHOOK: query: load data local inpath '../../data/files/srcbucket22.txt' INTO TABLE srcbucket_mapjoin_part partition(ds='2008-04-08') +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@srcbucket_mapjoin_part@ds=2008-04-08 +PREHOOK: query: desc formatted srcbucket_mapjoin_part partition(ds='2008-04-08') +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@srcbucket_mapjoin_part +POSTHOOK: query: desc formatted srcbucket_mapjoin_part partition(ds='2008-04-08') +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@srcbucket_mapjoin_part +# col_name data_type comment + +key int +value string + +# Partition Information +# col_name data_type comment + +ds string + +# Detailed Partition Information +Partition Value: [2008-04-08] +Database: default +Table: srcbucket_mapjoin_part +#### A masked pattern was here #### +Partition Parameters: + numFiles 3 + numRows 0 + rawDataSize 0 + totalSize 4200 +#### A masked pattern was here #### + +# Storage Information +SerDe Library: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +InputFormat: org.apache.hadoop.mapred.TextInputFormat +OutputFormat: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat +Compressed: No +Num Buckets: 4 +Bucket Columns: [key] +Sort Columns: [] +Storage Desc Params: + serialization.format 1 +PREHOOK: query: load data local inpath '../../data/files/srcbucket23.txt' INTO TABLE srcbucket_mapjoin_part partition(ds='2008-04-08') +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@srcbucket_mapjoin_part@ds=2008-04-08 +POSTHOOK: query: load data local inpath '../../data/files/srcbucket23.txt' INTO TABLE srcbucket_mapjoin_part partition(ds='2008-04-08') +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@srcbucket_mapjoin_part@ds=2008-04-08 +PREHOOK: query: desc formatted srcbucket_mapjoin_part partition(ds='2008-04-08') +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@srcbucket_mapjoin_part +POSTHOOK: query: desc formatted srcbucket_mapjoin_part partition(ds='2008-04-08') +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@srcbucket_mapjoin_part +# col_name data_type comment + +key int +value string + +# Partition Information +# col_name data_type comment + +ds string + +# Detailed Partition Information +Partition Value: [2008-04-08] +Database: default +Table: srcbucket_mapjoin_part +#### A masked pattern was here #### +Partition Parameters: + numFiles 4 + numRows 0 + rawDataSize 0 + totalSize 5812 +#### A masked pattern was here #### + +# Storage Information +SerDe Library: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +InputFormat: org.apache.hadoop.mapred.TextInputFormat +OutputFormat: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat +Compressed: No +Num Buckets: 4 +Bucket Columns: [key] +Sort Columns: [] +Storage Desc Params: + serialization.format 1 +PREHOOK: query: CREATE TABLE srcbucket_mapjoin_part_2 (key int, value string) partitioned by (ds string) CLUSTERED BY (key) INTO 2 BUCKETS STORED AS TEXTFILE +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@srcbucket_mapjoin_part_2 +POSTHOOK: query: CREATE TABLE srcbucket_mapjoin_part_2 (key int, value string) partitioned by (ds string) CLUSTERED BY (key) INTO 2 BUCKETS STORED AS TEXTFILE +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@srcbucket_mapjoin_part_2 +PREHOOK: query: load data local inpath '../../data/files/srcbucket22.txt' INTO TABLE srcbucket_mapjoin_part_2 partition(ds='2008-04-08') +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@srcbucket_mapjoin_part_2 +POSTHOOK: query: load data local inpath '../../data/files/srcbucket22.txt' INTO TABLE srcbucket_mapjoin_part_2 partition(ds='2008-04-08') +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@srcbucket_mapjoin_part_2 +POSTHOOK: Output: default@srcbucket_mapjoin_part_2@ds=2008-04-08 +PREHOOK: query: load data local inpath '../../data/files/srcbucket23.txt' INTO TABLE srcbucket_mapjoin_part_2 partition(ds='2008-04-08') +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@srcbucket_mapjoin_part_2@ds=2008-04-08 +POSTHOOK: query: load data local inpath '../../data/files/srcbucket23.txt' INTO TABLE srcbucket_mapjoin_part_2 partition(ds='2008-04-08') +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@srcbucket_mapjoin_part_2@ds=2008-04-08 +PREHOOK: query: create table bucketmapjoin_hash_result_1 (key bigint , value1 bigint, value2 bigint) +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@bucketmapjoin_hash_result_1 +POSTHOOK: query: create table bucketmapjoin_hash_result_1 (key bigint , value1 bigint, value2 bigint) +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@bucketmapjoin_hash_result_1 +PREHOOK: query: create table bucketmapjoin_hash_result_2 (key bigint , value1 bigint, value2 bigint) +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@bucketmapjoin_hash_result_2 +POSTHOOK: query: create table bucketmapjoin_hash_result_2 (key bigint , value1 bigint, value2 bigint) +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@bucketmapjoin_hash_result_2 +PREHOOK: query: create table bucketmapjoin_tmp_result (key string , value1 string, value2 string) +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@bucketmapjoin_tmp_result +POSTHOOK: query: create table bucketmapjoin_tmp_result (key string , value1 string, value2 string) +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@bucketmapjoin_tmp_result +PREHOOK: query: explain extended +insert overwrite table bucketmapjoin_tmp_result +select /*+mapjoin(b)*/ a.key, a.value, b.value +from srcbucket_mapjoin a join srcbucket_mapjoin_part b +on a.key=b.key where b.ds="2008-04-08" +PREHOOK: type: QUERY +POSTHOOK: query: explain extended +insert overwrite table bucketmapjoin_tmp_result +select /*+mapjoin(b)*/ a.key, a.value, b.value +from srcbucket_mapjoin a join srcbucket_mapjoin_part b +on a.key=b.key where b.ds="2008-04-08" +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), Map 3 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: a + Statistics: Num rows: 26 Data size: 2750 Basic stats: COMPLETE Column stats: NONE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: key is not null (type: boolean) + Statistics: Num rows: 26 Data size: 2750 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: key (type: int) + null sort order: a + sort order: + + Map-reduce partition columns: key (type: int) + Statistics: Num rows: 26 Data size: 2750 Basic stats: COMPLETE Column stats: NONE + tag: 0 + value expressions: value (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: srcbucket_mapjoin + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count 2 + bucket_field_name key + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.srcbucket_mapjoin + numFiles 2 + numRows 0 + rawDataSize 0 + serialization.ddl struct srcbucket_mapjoin { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 2750 +#### 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 2 + bucket_field_name key + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.srcbucket_mapjoin + numFiles 2 + numRows 0 + rawDataSize 0 + serialization.ddl struct srcbucket_mapjoin { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 2750 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.srcbucket_mapjoin + name: default.srcbucket_mapjoin + Truncated Path -> Alias: + /srcbucket_mapjoin [a] + Map 3 + Map Operator Tree: + TableScan + alias: b + Statistics: Num rows: 55 Data size: 6252 Basic stats: COMPLETE Column stats: NONE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: key is not null (type: boolean) + Statistics: Num rows: 55 Data size: 6252 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: key (type: int) + null sort order: a + sort order: + + Map-reduce partition columns: key (type: int) + Statistics: Num rows: 55 Data size: 6252 Basic stats: COMPLETE Column stats: NONE + tag: 1 + value expressions: value (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: ds=2008-04-08 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2008-04-08 + properties: + bucket_count 4 + bucket_field_name key + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.srcbucket_mapjoin_part + numFiles 4 + numRows 0 + partition_columns ds + partition_columns.types string + rawDataSize 0 + serialization.ddl struct srcbucket_mapjoin_part { i32 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 4 + bucket_field_name key + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.srcbucket_mapjoin_part + partition_columns ds + partition_columns.types string + serialization.ddl struct srcbucket_mapjoin_part { i32 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.srcbucket_mapjoin_part + name: default.srcbucket_mapjoin_part + Truncated Path -> Alias: + /srcbucket_mapjoin_part/ds=2008-04-08 [b] + Reducer 2 + Execution mode: llap + Needs Tagging: false + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 key (type: int) + 1 key (type: int) + outputColumnNames: _col0, _col1, _col6 + Position of Big Table: 1 + Statistics: Num rows: 60 Data size: 6877 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: int), _col1 (type: string), _col6 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 60 Data size: 6877 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 1 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 60 Data size: 6877 Basic stats: COMPLETE Column stats: NONE +#### 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,value1,value2 + columns.comments + columns.types string:string:string +#### A masked pattern was here #### + name default.bucketmapjoin_tmp_result + numFiles 0 + numRows 0 + rawDataSize 0 + serialization.ddl struct bucketmapjoin_tmp_result { string key, string value1, string value2} + 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.bucketmapjoin_tmp_result + 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,value1,value2 + columns.comments + columns.types string:string:string +#### A masked pattern was here #### + name default.bucketmapjoin_tmp_result + numFiles 0 + numRows 0 + rawDataSize 0 + serialization.ddl struct bucketmapjoin_tmp_result { string key, string value1, string value2} + 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.bucketmapjoin_tmp_result + + Stage: Stage-3 + Stats-Aggr Operator +#### A masked pattern was here #### + +PREHOOK: query: insert overwrite table bucketmapjoin_tmp_result +select /*+mapjoin(b)*/ a.key, a.value, b.value +from srcbucket_mapjoin a join srcbucket_mapjoin_part b +on a.key=b.key where b.ds="2008-04-08" +PREHOOK: type: QUERY +PREHOOK: Input: default@srcbucket_mapjoin +PREHOOK: Input: default@srcbucket_mapjoin_part +PREHOOK: Input: default@srcbucket_mapjoin_part@ds=2008-04-08 +PREHOOK: Output: default@bucketmapjoin_tmp_result +POSTHOOK: query: insert overwrite table bucketmapjoin_tmp_result +select /*+mapjoin(b)*/ a.key, a.value, b.value +from srcbucket_mapjoin a join srcbucket_mapjoin_part b +on a.key=b.key where b.ds="2008-04-08" +POSTHOOK: type: QUERY +POSTHOOK: Input: default@srcbucket_mapjoin +POSTHOOK: Input: default@srcbucket_mapjoin_part +POSTHOOK: Input: default@srcbucket_mapjoin_part@ds=2008-04-08 +POSTHOOK: Output: default@bucketmapjoin_tmp_result +POSTHOOK: Lineage: bucketmapjoin_tmp_result.key SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:key, type:int, comment:null), ] +POSTHOOK: Lineage: bucketmapjoin_tmp_result.value1 SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:value, type:string, comment:null), ] +POSTHOOK: Lineage: bucketmapjoin_tmp_result.value2 SIMPLE [(srcbucket_mapjoin_part)b.FieldSchema(name:value, type:string, comment:null), ] +PREHOOK: query: select count(1) from bucketmapjoin_tmp_result +PREHOOK: type: QUERY +PREHOOK: Input: default@bucketmapjoin_tmp_result +#### A masked pattern was here #### +POSTHOOK: query: select count(1) from bucketmapjoin_tmp_result +POSTHOOK: type: QUERY +POSTHOOK: Input: default@bucketmapjoin_tmp_result +#### A masked pattern was here #### +464 +PREHOOK: query: insert overwrite table bucketmapjoin_hash_result_1 +select sum(hash(key)), sum(hash(value1)), sum(hash(value2)) from bucketmapjoin_tmp_result +PREHOOK: type: QUERY +PREHOOK: Input: default@bucketmapjoin_tmp_result +PREHOOK: Output: default@bucketmapjoin_hash_result_1 +POSTHOOK: query: insert overwrite table bucketmapjoin_hash_result_1 +select sum(hash(key)), sum(hash(value1)), sum(hash(value2)) from bucketmapjoin_tmp_result +POSTHOOK: type: QUERY +POSTHOOK: Input: default@bucketmapjoin_tmp_result +POSTHOOK: Output: default@bucketmapjoin_hash_result_1 +POSTHOOK: Lineage: bucketmapjoin_hash_result_1.key EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:key, type:string, comment:null), ] +POSTHOOK: Lineage: bucketmapjoin_hash_result_1.value1 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value1, type:string, comment:null), ] +POSTHOOK: Lineage: bucketmapjoin_hash_result_1.value2 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value2, type:string, comment:null), ] +PREHOOK: query: insert overwrite table bucketmapjoin_tmp_result +select /*+mapjoin(b)*/ a.key, a.value, b.value +from srcbucket_mapjoin a join srcbucket_mapjoin_part b +on a.key=b.key where b.ds="2008-04-08" +PREHOOK: type: QUERY +PREHOOK: Input: default@srcbucket_mapjoin +PREHOOK: Input: default@srcbucket_mapjoin_part +PREHOOK: Input: default@srcbucket_mapjoin_part@ds=2008-04-08 +PREHOOK: Output: default@bucketmapjoin_tmp_result +POSTHOOK: query: insert overwrite table bucketmapjoin_tmp_result +select /*+mapjoin(b)*/ a.key, a.value, b.value +from srcbucket_mapjoin a join srcbucket_mapjoin_part b +on a.key=b.key where b.ds="2008-04-08" +POSTHOOK: type: QUERY +POSTHOOK: Input: default@srcbucket_mapjoin +POSTHOOK: Input: default@srcbucket_mapjoin_part +POSTHOOK: Input: default@srcbucket_mapjoin_part@ds=2008-04-08 +POSTHOOK: Output: default@bucketmapjoin_tmp_result +POSTHOOK: Lineage: bucketmapjoin_tmp_result.key SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:key, type:int, comment:null), ] +POSTHOOK: Lineage: bucketmapjoin_tmp_result.value1 SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:value, type:string, comment:null), ] +POSTHOOK: Lineage: bucketmapjoin_tmp_result.value2 SIMPLE [(srcbucket_mapjoin_part)b.FieldSchema(name:value, type:string, comment:null), ] +PREHOOK: query: select count(1) from bucketmapjoin_tmp_result +PREHOOK: type: QUERY +PREHOOK: Input: default@bucketmapjoin_tmp_result +#### A masked pattern was here #### +POSTHOOK: query: select count(1) from bucketmapjoin_tmp_result +POSTHOOK: type: QUERY +POSTHOOK: Input: default@bucketmapjoin_tmp_result +#### A masked pattern was here #### +464 +PREHOOK: query: insert overwrite table bucketmapjoin_hash_result_2 +select sum(hash(key)), sum(hash(value1)), sum(hash(value2)) from bucketmapjoin_tmp_result +PREHOOK: type: QUERY +PREHOOK: Input: default@bucketmapjoin_tmp_result +PREHOOK: Output: default@bucketmapjoin_hash_result_2 +POSTHOOK: query: insert overwrite table bucketmapjoin_hash_result_2 +select sum(hash(key)), sum(hash(value1)), sum(hash(value2)) from bucketmapjoin_tmp_result +POSTHOOK: type: QUERY +POSTHOOK: Input: default@bucketmapjoin_tmp_result +POSTHOOK: Output: default@bucketmapjoin_hash_result_2 +POSTHOOK: Lineage: bucketmapjoin_hash_result_2.key EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:key, type:string, comment:null), ] +POSTHOOK: Lineage: bucketmapjoin_hash_result_2.value1 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value1, type:string, comment:null), ] +POSTHOOK: Lineage: bucketmapjoin_hash_result_2.value2 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value2, type:string, comment:null), ] +PREHOOK: query: select a.key-b.key, a.value1-b.value1, a.value2-b.value2 +from bucketmapjoin_hash_result_1 a left outer join bucketmapjoin_hash_result_2 b +on a.key = b.key +PREHOOK: type: QUERY +PREHOOK: Input: default@bucketmapjoin_hash_result_1 +PREHOOK: Input: default@bucketmapjoin_hash_result_2 +#### A masked pattern was here #### +POSTHOOK: query: select a.key-b.key, a.value1-b.value1, a.value2-b.value2 +from bucketmapjoin_hash_result_1 a left outer join bucketmapjoin_hash_result_2 b +on a.key = b.key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@bucketmapjoin_hash_result_1 +POSTHOOK: Input: default@bucketmapjoin_hash_result_2 +#### A masked pattern was here #### +0 0 0 +PREHOOK: query: explain extended +insert overwrite table bucketmapjoin_tmp_result +select /*+mapjoin(a)*/ a.key, a.value, b.value +from srcbucket_mapjoin a join srcbucket_mapjoin_part b +on a.key=b.key where b.ds="2008-04-08" +PREHOOK: type: QUERY +POSTHOOK: query: explain extended +insert overwrite table bucketmapjoin_tmp_result +select /*+mapjoin(a)*/ a.key, a.value, b.value +from srcbucket_mapjoin a join srcbucket_mapjoin_part b +on a.key=b.key where b.ds="2008-04-08" +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), Map 3 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: a + Statistics: Num rows: 26 Data size: 2750 Basic stats: COMPLETE Column stats: NONE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: key is not null (type: boolean) + Statistics: Num rows: 26 Data size: 2750 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: key (type: int) + null sort order: a + sort order: + + Map-reduce partition columns: key (type: int) + Statistics: Num rows: 26 Data size: 2750 Basic stats: COMPLETE Column stats: NONE + tag: 0 + value expressions: value (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: srcbucket_mapjoin + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count 2 + bucket_field_name key + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.srcbucket_mapjoin + numFiles 2 + numRows 0 + rawDataSize 0 + serialization.ddl struct srcbucket_mapjoin { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 2750 +#### 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 2 + bucket_field_name key + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.srcbucket_mapjoin + numFiles 2 + numRows 0 + rawDataSize 0 + serialization.ddl struct srcbucket_mapjoin { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 2750 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.srcbucket_mapjoin + name: default.srcbucket_mapjoin + Truncated Path -> Alias: + /srcbucket_mapjoin [a] + Map 3 + Map Operator Tree: + TableScan + alias: b + Statistics: Num rows: 55 Data size: 6252 Basic stats: COMPLETE Column stats: NONE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: key is not null (type: boolean) + Statistics: Num rows: 55 Data size: 6252 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: key (type: int) + null sort order: a + sort order: + + Map-reduce partition columns: key (type: int) + Statistics: Num rows: 55 Data size: 6252 Basic stats: COMPLETE Column stats: NONE + tag: 1 + value expressions: value (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: ds=2008-04-08 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2008-04-08 + properties: + bucket_count 4 + bucket_field_name key + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.srcbucket_mapjoin_part + numFiles 4 + numRows 0 + partition_columns ds + partition_columns.types string + rawDataSize 0 + serialization.ddl struct srcbucket_mapjoin_part { i32 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 4 + bucket_field_name key + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.srcbucket_mapjoin_part + partition_columns ds + partition_columns.types string + serialization.ddl struct srcbucket_mapjoin_part { i32 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.srcbucket_mapjoin_part + name: default.srcbucket_mapjoin_part + Truncated Path -> Alias: + /srcbucket_mapjoin_part/ds=2008-04-08 [b] + Reducer 2 + Execution mode: llap + Needs Tagging: false + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 key (type: int) + 1 key (type: int) + outputColumnNames: _col0, _col1, _col6 + Position of Big Table: 1 + Statistics: Num rows: 60 Data size: 6877 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: int), _col1 (type: string), _col6 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 60 Data size: 6877 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 1 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 60 Data size: 6877 Basic stats: COMPLETE Column stats: NONE +#### 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,value1,value2 + columns.comments + columns.types string:string:string +#### A masked pattern was here #### + name default.bucketmapjoin_tmp_result + numFiles 1 + numRows 464 + rawDataSize 8519 + serialization.ddl struct bucketmapjoin_tmp_result { string key, string value1, string value2} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 8983 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.bucketmapjoin_tmp_result + 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,value1,value2 + columns.comments + columns.types string:string:string +#### A masked pattern was here #### + name default.bucketmapjoin_tmp_result + numFiles 1 + numRows 464 + rawDataSize 8519 + serialization.ddl struct bucketmapjoin_tmp_result { string key, string value1, string value2} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 8983 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.bucketmapjoin_tmp_result + + Stage: Stage-3 + Stats-Aggr Operator +#### A masked pattern was here #### + +PREHOOK: query: insert overwrite table bucketmapjoin_tmp_result +select /*+mapjoin(a)*/ a.key, a.value, b.value +from srcbucket_mapjoin a join srcbucket_mapjoin_part b +on a.key=b.key where b.ds="2008-04-08" +PREHOOK: type: QUERY +PREHOOK: Input: default@srcbucket_mapjoin +PREHOOK: Input: default@srcbucket_mapjoin_part +PREHOOK: Input: default@srcbucket_mapjoin_part@ds=2008-04-08 +PREHOOK: Output: default@bucketmapjoin_tmp_result +POSTHOOK: query: insert overwrite table bucketmapjoin_tmp_result +select /*+mapjoin(a)*/ a.key, a.value, b.value +from srcbucket_mapjoin a join srcbucket_mapjoin_part b +on a.key=b.key where b.ds="2008-04-08" +POSTHOOK: type: QUERY +POSTHOOK: Input: default@srcbucket_mapjoin +POSTHOOK: Input: default@srcbucket_mapjoin_part +POSTHOOK: Input: default@srcbucket_mapjoin_part@ds=2008-04-08 +POSTHOOK: Output: default@bucketmapjoin_tmp_result +POSTHOOK: Lineage: bucketmapjoin_tmp_result.key SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:key, type:int, comment:null), ] +POSTHOOK: Lineage: bucketmapjoin_tmp_result.value1 SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:value, type:string, comment:null), ] +POSTHOOK: Lineage: bucketmapjoin_tmp_result.value2 SIMPLE [(srcbucket_mapjoin_part)b.FieldSchema(name:value, type:string, comment:null), ] +PREHOOK: query: select count(1) from bucketmapjoin_tmp_result +PREHOOK: type: QUERY +PREHOOK: Input: default@bucketmapjoin_tmp_result +#### A masked pattern was here #### +POSTHOOK: query: select count(1) from bucketmapjoin_tmp_result +POSTHOOK: type: QUERY +POSTHOOK: Input: default@bucketmapjoin_tmp_result +#### A masked pattern was here #### +464 +PREHOOK: query: insert overwrite table bucketmapjoin_hash_result_1 +select sum(hash(key)), sum(hash(value1)), sum(hash(value2)) from bucketmapjoin_tmp_result +PREHOOK: type: QUERY +PREHOOK: Input: default@bucketmapjoin_tmp_result +PREHOOK: Output: default@bucketmapjoin_hash_result_1 +POSTHOOK: query: insert overwrite table bucketmapjoin_hash_result_1 +select sum(hash(key)), sum(hash(value1)), sum(hash(value2)) from bucketmapjoin_tmp_result +POSTHOOK: type: QUERY +POSTHOOK: Input: default@bucketmapjoin_tmp_result +POSTHOOK: Output: default@bucketmapjoin_hash_result_1 +POSTHOOK: Lineage: bucketmapjoin_hash_result_1.key EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:key, type:string, comment:null), ] +POSTHOOK: Lineage: bucketmapjoin_hash_result_1.value1 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value1, type:string, comment:null), ] +POSTHOOK: Lineage: bucketmapjoin_hash_result_1.value2 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value2, type:string, comment:null), ] +PREHOOK: query: insert overwrite table bucketmapjoin_tmp_result +select /*+mapjoin(a)*/ a.key, a.value, b.value +from srcbucket_mapjoin a join srcbucket_mapjoin_part b +on a.key=b.key where b.ds="2008-04-08" +PREHOOK: type: QUERY +PREHOOK: Input: default@srcbucket_mapjoin +PREHOOK: Input: default@srcbucket_mapjoin_part +PREHOOK: Input: default@srcbucket_mapjoin_part@ds=2008-04-08 +PREHOOK: Output: default@bucketmapjoin_tmp_result +POSTHOOK: query: insert overwrite table bucketmapjoin_tmp_result +select /*+mapjoin(a)*/ a.key, a.value, b.value +from srcbucket_mapjoin a join srcbucket_mapjoin_part b +on a.key=b.key where b.ds="2008-04-08" +POSTHOOK: type: QUERY +POSTHOOK: Input: default@srcbucket_mapjoin +POSTHOOK: Input: default@srcbucket_mapjoin_part +POSTHOOK: Input: default@srcbucket_mapjoin_part@ds=2008-04-08 +POSTHOOK: Output: default@bucketmapjoin_tmp_result +POSTHOOK: Lineage: bucketmapjoin_tmp_result.key SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:key, type:int, comment:null), ] +POSTHOOK: Lineage: bucketmapjoin_tmp_result.value1 SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:value, type:string, comment:null), ] +POSTHOOK: Lineage: bucketmapjoin_tmp_result.value2 SIMPLE [(srcbucket_mapjoin_part)b.FieldSchema(name:value, type:string, comment:null), ] +PREHOOK: query: select count(1) from bucketmapjoin_tmp_result +PREHOOK: type: QUERY +PREHOOK: Input: default@bucketmapjoin_tmp_result +#### A masked pattern was here #### +POSTHOOK: query: select count(1) from bucketmapjoin_tmp_result +POSTHOOK: type: QUERY +POSTHOOK: Input: default@bucketmapjoin_tmp_result +#### A masked pattern was here #### +464 +PREHOOK: query: insert overwrite table bucketmapjoin_hash_result_2 +select sum(hash(key)), sum(hash(value1)), sum(hash(value2)) from bucketmapjoin_tmp_result +PREHOOK: type: QUERY +PREHOOK: Input: default@bucketmapjoin_tmp_result +PREHOOK: Output: default@bucketmapjoin_hash_result_2 +POSTHOOK: query: insert overwrite table bucketmapjoin_hash_result_2 +select sum(hash(key)), sum(hash(value1)), sum(hash(value2)) from bucketmapjoin_tmp_result +POSTHOOK: type: QUERY +POSTHOOK: Input: default@bucketmapjoin_tmp_result +POSTHOOK: Output: default@bucketmapjoin_hash_result_2 +POSTHOOK: Lineage: bucketmapjoin_hash_result_2.key EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:key, type:string, comment:null), ] +POSTHOOK: Lineage: bucketmapjoin_hash_result_2.value1 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value1, type:string, comment:null), ] +POSTHOOK: Lineage: bucketmapjoin_hash_result_2.value2 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value2, type:string, comment:null), ] +PREHOOK: query: select a.key-b.key, a.value1-b.value1, a.value2-b.value2 +from bucketmapjoin_hash_result_1 a left outer join bucketmapjoin_hash_result_2 b +on a.key = b.key +PREHOOK: type: QUERY +PREHOOK: Input: default@bucketmapjoin_hash_result_1 +PREHOOK: Input: default@bucketmapjoin_hash_result_2 +#### A masked pattern was here #### +POSTHOOK: query: select a.key-b.key, a.value1-b.value1, a.value2-b.value2 +from bucketmapjoin_hash_result_1 a left outer join bucketmapjoin_hash_result_2 b +on a.key = b.key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@bucketmapjoin_hash_result_1 +POSTHOOK: Input: default@bucketmapjoin_hash_result_2 +#### A masked pattern was here #### +0 0 0
http://git-wip-us.apache.org/repos/asf/hive/blob/f562dfb5/ql/src/test/results/clientpositive/llap/subquery_views.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/subquery_views.q.out b/ql/src/test/results/clientpositive/llap/subquery_views.q.out new file mode 100644 index 0000000..35e80ae --- /dev/null +++ b/ql/src/test/results/clientpositive/llap/subquery_views.q.out @@ -0,0 +1,571 @@ +PREHOOK: query: -- SORT_QUERY_RESULTS + +-- exists test +create view cv1 as +select * +from src b +where exists + (select a.key + from src a + where b.value = a.value and a.key = b.key and a.value > 'val_9') +PREHOOK: type: CREATEVIEW +PREHOOK: Input: default@src +PREHOOK: Output: database:default +PREHOOK: Output: default@cv1 +POSTHOOK: query: -- SORT_QUERY_RESULTS + +-- exists test +create view cv1 as +select * +from src b +where exists + (select a.key + from src a + where b.value = a.value and a.key = b.key and a.value > 'val_9') +POSTHOOK: type: CREATEVIEW +POSTHOOK: Input: default@src +POSTHOOK: Output: database:default +POSTHOOK: Output: default@cv1 +PREHOOK: query: describe extended cv1 +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@cv1 +POSTHOOK: query: describe extended cv1 +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@cv1 +key string +value string + +#### A masked pattern was here #### +from src b +where exists + (select a.key + from src a + where b.value = a.value and a.key = b.key and a.value > 'val_9'), viewExpandedText:select `b`.`key`, `b`.`value` +from `default`.`src` `b` +where exists + (select `a`.`key` + from `default`.`src` `a` + where `b`.`value` = `a`.`value` and `a`.`key` = `b`.`key` and `a`.`value` > 'val_9'), tableType:VIRTUAL_VIEW) +PREHOOK: query: select * +from cv1 where cv1.key in (select key from cv1 c where c.key > '95') +PREHOOK: type: QUERY +PREHOOK: Input: default@cv1 +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: select * +from cv1 where cv1.key in (select key from cv1 c where c.key > '95') +POSTHOOK: type: QUERY +POSTHOOK: Input: default@cv1 +POSTHOOK: Input: default@src +#### A masked pattern was here #### +96 val_96 +97 val_97 +97 val_97 +98 val_98 +98 val_98 +PREHOOK: query: -- not in test +create view cv2 as +select * +from src b +where b.key not in + (select a.key + from src a + where b.value = a.value and a.key = b.key and a.value > 'val_11' + ) +PREHOOK: type: CREATEVIEW +PREHOOK: Input: default@src +PREHOOK: Output: database:default +PREHOOK: Output: default@cv2 +POSTHOOK: query: -- not in test +create view cv2 as +select * +from src b +where b.key not in + (select a.key + from src a + where b.value = a.value and a.key = b.key and a.value > 'val_11' + ) +POSTHOOK: type: CREATEVIEW +POSTHOOK: Input: default@src +POSTHOOK: Output: database:default +POSTHOOK: Output: default@cv2 +PREHOOK: query: describe extended cv2 +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@cv2 +POSTHOOK: query: describe extended cv2 +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@cv2 +key string +value string + +#### A masked pattern was here #### +from src b +where b.key not in + (select a.key + from src a + where b.value = a.value and a.key = b.key and a.value > 'val_11' + ), viewExpandedText:select `b`.`key`, `b`.`value` +from `default`.`src` `b` +where `b`.`key` not in + (select `a`.`key` + from `default`.`src` `a` + where `b`.`value` = `a`.`value` and `a`.`key` = `b`.`key` and `a`.`value` > 'val_11' + ), tableType:VIRTUAL_VIEW) +Warning: Shuffle Join MERGEJOIN[67][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product +Warning: Shuffle Join MERGEJOIN[69][tables = [$hdt$_1, $hdt$_2]] in Stage 'Reducer 9' is a cross product +PREHOOK: query: explain +select * +from cv2 where cv2.key in (select key from cv2 c where c.key < '11') +PREHOOK: type: QUERY +POSTHOOK: query: explain +select * +from cv2 where cv2.key in (select key from cv2 c where c.key < '11') +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 10 <- Map 13 (SIMPLE_EDGE), Reducer 9 (SIMPLE_EDGE) + Reducer 12 <- Map 11 (SIMPLE_EDGE) + Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE) + Reducer 3 <- Map 7 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) + Reducer 4 <- Reducer 10 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) + Reducer 6 <- Map 5 (SIMPLE_EDGE) + Reducer 9 <- Map 8 (SIMPLE_EDGE), Reducer 12 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: b + properties: + insideView TRUE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (key < '11') (type: boolean) + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: string), _col1 (type: string) + Execution mode: llap + LLAP IO: no inputs + Map 11 + Map Operator Tree: + TableScan + alias: a + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((value > 'val_11') and (key is null or value is null)) (type: boolean) + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: bigint) + Execution mode: llap + LLAP IO: no inputs + Map 13 + Map Operator Tree: + TableScan + alias: a + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((value > 'val_11') and (key < '11')) (type: boolean) + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string), key (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 55 Data size: 14575 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col2 (type: string), _col1 (type: string), _col0 (type: string) + sort order: +++ + Map-reduce partition columns: _col2 (type: string), _col1 (type: string), _col0 (type: string) + Statistics: Num rows: 55 Data size: 14575 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: llap + LLAP IO: no inputs + Map 5 + Map Operator Tree: + TableScan + alias: a + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((value > 'val_11') and (key is null or value is null)) (type: boolean) + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: bigint) + Execution mode: llap + LLAP IO: no inputs + Map 7 + Map Operator Tree: + TableScan + alias: a + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((value > 'val_11') and (key < '11')) (type: boolean) + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string), key (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 55 Data size: 14575 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col2 (type: string), _col1 (type: string), _col0 (type: string) + sort order: +++ + Map-reduce partition columns: _col2 (type: string), _col1 (type: string), _col0 (type: string) + Statistics: Num rows: 55 Data size: 14575 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: llap + LLAP IO: no inputs + Map 8 + Map Operator Tree: + TableScan + alias: b + properties: + insideView TRUE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (key < '11') (type: boolean) + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: string), _col1 (type: string) + Execution mode: llap + LLAP IO: no inputs + Reducer 10 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Left Outer Join0 to 1 + keys: + 0 _col0 (type: string), _col1 (type: string), _col0 (type: string) + 1 _col2 (type: string), _col1 (type: string), _col0 (type: string) + outputColumnNames: _col0, _col3 + Statistics: Num rows: 166 Data size: 28884 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: _col3 is null (type: boolean) + Statistics: Num rows: 1 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 87 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: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE + Reducer 12 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (_col0 = 0) (type: boolean) + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 + 1 + outputColumnNames: _col0, _col1 + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string), _col0 (type: string) + sort order: +++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col0 (type: string) + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Left Outer Join0 to 1 + keys: + 0 _col0 (type: string), _col1 (type: string), _col0 (type: string) + 1 _col2 (type: string), _col1 (type: string), _col0 (type: string) + outputColumnNames: _col0, _col1, _col3 + Statistics: Num rows: 166 Data size: 43990 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: _col3 is null (type: boolean) + Statistics: Num rows: 1 Data size: 265 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 178 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: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: string) + Reducer 4 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Left Semi Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 178 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 + Reducer 6 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (_col0 = 0) (type: boolean) + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Reducer 9 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 + 1 + outputColumnNames: _col0, _col1 + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string), _col0 (type: string) + sort order: +++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col0 (type: string) + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +Warning: Shuffle Join MERGEJOIN[67][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product +Warning: Shuffle Join MERGEJOIN[69][tables = [$hdt$_1, $hdt$_2]] in Stage 'Reducer 9' is a cross product +PREHOOK: query: select * +from cv2 where cv2.key in (select key from cv2 c where c.key < '11') +PREHOOK: type: QUERY +PREHOOK: Input: default@cv2 +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: select * +from cv2 where cv2.key in (select key from cv2 c where c.key < '11') +POSTHOOK: type: QUERY +POSTHOOK: Input: default@cv2 +POSTHOOK: Input: default@src +#### A masked pattern was here #### +0 val_0 +0 val_0 +0 val_0 +10 val_10 +100 val_100 +100 val_100 +103 val_103 +103 val_103 +104 val_104 +104 val_104 +105 val_105 +PREHOOK: query: -- in where + having +create view cv3 as +select key, value, count(*) +from src b +where b.key in (select key from src where src.key > '8') +group by key, value +having count(*) in (select count(*) from src s1 where s1.key > '9' group by s1.key ) +PREHOOK: type: CREATEVIEW +PREHOOK: Input: default@src +PREHOOK: Output: database:default +PREHOOK: Output: default@cv3 +POSTHOOK: query: -- in where + having +create view cv3 as +select key, value, count(*) +from src b +where b.key in (select key from src where src.key > '8') +group by key, value +having count(*) in (select count(*) from src s1 where s1.key > '9' group by s1.key ) +POSTHOOK: type: CREATEVIEW +POSTHOOK: Input: default@src +POSTHOOK: Output: database:default +POSTHOOK: Output: default@cv3 +PREHOOK: query: describe extended cv3 +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@cv3 +POSTHOOK: query: describe extended cv3 +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@cv3 +key string +value string +_c2 bigint + +#### A masked pattern was here #### +from src b +where b.key in (select key from src where src.key > '8') +group by key, value +having count(*) in (select count(*) from src s1 where s1.key > '9' group by s1.key ), viewExpandedText:select `b`.`key`, `b`.`value`, count(*) +from `default`.`src` `b` +where `b`.`key` in (select `src`.`key` from `default`.`src` where `src`.`key` > '8') +group by `b`.`key`, `b`.`value` +having count(*) in (select count(*) from `default`.`src` `s1` where `s1`.`key` > '9' group by `s1`.`key` ), tableType:VIRTUAL_VIEW) +PREHOOK: query: select * from cv3 +PREHOOK: type: QUERY +PREHOOK: Input: default@cv3 +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: select * from cv3 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@cv3 +POSTHOOK: Input: default@src +#### A masked pattern was here #### +80 val_80 1 +82 val_82 1 +83 val_83 2 +84 val_84 2 +85 val_85 1 +86 val_86 1 +87 val_87 1 +9 val_9 1 +90 val_90 3 +92 val_92 1 +95 val_95 2 +96 val_96 1 +97 val_97 2 +98 val_98 2 +PREHOOK: query: -- join of subquery views +select * +from cv3 +where cv3.key in (select key from cv1) +PREHOOK: type: QUERY +PREHOOK: Input: default@cv1 +PREHOOK: Input: default@cv3 +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: -- join of subquery views +select * +from cv3 +where cv3.key in (select key from cv1) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@cv1 +POSTHOOK: Input: default@cv3 +POSTHOOK: Input: default@src +#### A masked pattern was here #### +90 val_90 3 +92 val_92 1 +95 val_95 2 +96 val_96 1 +97 val_97 2 +98 val_98 2 +PREHOOK: query: drop table tc +PREHOOK: type: DROPTABLE +POSTHOOK: query: drop table tc +POSTHOOK: type: DROPTABLE +PREHOOK: query: create table tc (`@d` int) +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@tc +POSTHOOK: query: create table tc (`@d` int) +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@tc +PREHOOK: query: insert overwrite table tc select 1 from src limit 1 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: default@tc +POSTHOOK: query: insert overwrite table tc select 1 from src limit 1 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Output: default@tc +POSTHOOK: Lineage: tc.@d SIMPLE [] +PREHOOK: query: drop view tcv +PREHOOK: type: DROPVIEW +POSTHOOK: query: drop view tcv +POSTHOOK: type: DROPVIEW +PREHOOK: query: create view tcv as select * from tc b where exists (select a.`@d` from tc a where b.`@d`=a.`@d`) +PREHOOK: type: CREATEVIEW +PREHOOK: Input: default@tc +PREHOOK: Output: database:default +PREHOOK: Output: default@tcv +POSTHOOK: query: create view tcv as select * from tc b where exists (select a.`@d` from tc a where b.`@d`=a.`@d`) +POSTHOOK: type: CREATEVIEW +POSTHOOK: Input: default@tc +POSTHOOK: Output: database:default +POSTHOOK: Output: default@tcv +PREHOOK: query: describe extended tcv +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@tcv +POSTHOOK: query: describe extended tcv +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@tcv +@d int + +#### A masked pattern was here #### +PREHOOK: query: select * from tcv +PREHOOK: type: QUERY +PREHOOK: Input: default@tc +PREHOOK: Input: default@tcv +#### A masked pattern was here #### +POSTHOOK: query: select * from tcv +POSTHOOK: type: QUERY +POSTHOOK: Input: default@tc +POSTHOOK: Input: default@tcv +#### A masked pattern was here #### +1
