http://git-wip-us.apache.org/repos/asf/hive/blob/22541610/ql/src/test/results/clientpositive/list_bucket_dml_9.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/list_bucket_dml_9.q.out b/ql/src/test/results/clientpositive/list_bucket_dml_9.q.out new file mode 100644 index 0000000..81f3af3 --- /dev/null +++ b/ql/src/test/results/clientpositive/list_bucket_dml_9.q.out @@ -0,0 +1,811 @@ +PREHOOK: query: -- INCLUDE_HADOOP_MAJOR_VERSIONS(0.23) +-- SORT_QUERY_RESULTS + +-- list bucketing DML: static partition. multiple skewed columns. merge. +-- ds=2008-04-08/hr=11/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME: +-- 5263 000000_0 +-- 5263 000001_0 +-- ds=2008-04-08/hr=11/key=103: +-- 99 000000_0 +-- 99 000001_0 +-- after merge +-- 142 000000_0 +-- ds=2008-04-08/hr=11/key=484: +-- 87 000000_0 +-- 87 000001_0 +-- after merge +-- 118 000001_0 + +-- create a skewed table +create table list_bucketing_static_part (key String, value String) + partitioned by (ds String, hr String) + skewed by (key) on ('484','103') + stored as DIRECTORIES + STORED AS RCFILE +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@list_bucketing_static_part +POSTHOOK: query: -- INCLUDE_HADOOP_MAJOR_VERSIONS(0.23) +-- SORT_QUERY_RESULTS + +-- list bucketing DML: static partition. multiple skewed columns. merge. +-- ds=2008-04-08/hr=11/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME: +-- 5263 000000_0 +-- 5263 000001_0 +-- ds=2008-04-08/hr=11/key=103: +-- 99 000000_0 +-- 99 000001_0 +-- after merge +-- 142 000000_0 +-- ds=2008-04-08/hr=11/key=484: +-- 87 000000_0 +-- 87 000001_0 +-- after merge +-- 118 000001_0 + +-- create a skewed table +create table list_bucketing_static_part (key String, value String) + partitioned by (ds String, hr String) + skewed by (key) on ('484','103') + stored as DIRECTORIES + STORED AS RCFILE +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@list_bucketing_static_part +PREHOOK: query: -- list bucketing DML without merge. use bucketize to generate a few small files. +explain extended +insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11') +select key, value from srcpart where ds = '2008-04-08' +PREHOOK: type: QUERY +POSTHOOK: query: -- list bucketing DML without merge. use bucketize to generate a few small files. +explain extended +insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11') +select key, value from srcpart where ds = '2008-04-08' +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + Stage-2 depends on stages: Stage-0 + +STAGE PLANS: + Stage: Stage-1 + Map Reduce + Map Operator Tree: + TableScan + alias: srcpart + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + GatherStats: false + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 1 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Static Partition Specification: ds=2008-04-08/hr=11/ + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat + output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat + properties: + bucket_count -1 + columns key,value + columns.comments + columns.types string:string +#### A masked pattern was here #### + name default.list_bucketing_static_part + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct list_bucketing_static_part { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe + name: default.list_bucketing_static_part + TotalFiles: 1 + GatherStats: true + MultiFileSpray: false + 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 +#### A masked pattern was here #### + Partition + base file name: hr=12 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2008-04-08 + hr 12 + 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 [srcpart] + /srcpart/ds=2008-04-08/hr=12 [srcpart] + + Stage: Stage-0 + Move Operator + tables: + partition: + ds 2008-04-08 + hr 11 + replace: true +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat + output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat + properties: + bucket_count -1 + columns key,value + columns.comments + columns.types string:string +#### A masked pattern was here #### + name default.list_bucketing_static_part + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct list_bucketing_static_part { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe + name: default.list_bucketing_static_part + + Stage: Stage-2 + Stats-Aggr Operator +#### A masked pattern was here #### + +PREHOOK: query: insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11') +select key, value from srcpart where ds = '2008-04-08' +PREHOOK: type: QUERY +PREHOOK: Input: default@srcpart +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +PREHOOK: Output: default@list_bucketing_static_part@ds=2008-04-08/hr=11 +POSTHOOK: query: insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11') +select key, value from srcpart where ds = '2008-04-08' +POSTHOOK: type: QUERY +POSTHOOK: Input: default@srcpart +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +POSTHOOK: Output: default@list_bucketing_static_part@ds=2008-04-08/hr=11 +POSTHOOK: Lineage: list_bucketing_static_part PARTITION(ds=2008-04-08,hr=11).key SIMPLE [(srcpart)srcpart.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: list_bucketing_static_part PARTITION(ds=2008-04-08,hr=11).value SIMPLE [(srcpart)srcpart.FieldSchema(name:value, type:string, comment:default), ] +PREHOOK: query: -- check DML result +show partitions list_bucketing_static_part +PREHOOK: type: SHOWPARTITIONS +PREHOOK: Input: default@list_bucketing_static_part +POSTHOOK: query: -- check DML result +show partitions list_bucketing_static_part +POSTHOOK: type: SHOWPARTITIONS +POSTHOOK: Input: default@list_bucketing_static_part +ds=2008-04-08/hr=11 +PREHOOK: query: desc formatted list_bucketing_static_part partition (ds='2008-04-08', hr='11') +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@list_bucketing_static_part +POSTHOOK: query: desc formatted list_bucketing_static_part partition (ds='2008-04-08', hr='11') +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@list_bucketing_static_part +# col_name data_type comment + +key string +value string + +# Partition Information +# col_name data_type comment + +ds string +hr string + +# Detailed Partition Information +Partition Value: [2008-04-08, 11] +Database: default +Table: list_bucketing_static_part +#### A masked pattern was here #### +Partition Parameters: + COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"} + numFiles 6 + numRows 1000 + rawDataSize 9624 + totalSize 10898 +#### A masked pattern was here #### + +# Storage Information +SerDe Library: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe +InputFormat: org.apache.hadoop.hive.ql.io.RCFileInputFormat +OutputFormat: org.apache.hadoop.hive.ql.io.RCFileOutputFormat +Compressed: No +Num Buckets: -1 +Bucket Columns: [] +Sort Columns: [] +Stored As SubDirectories: Yes +Skewed Columns: [key] +Skewed Values: [[484], [103]] +#### A masked pattern was here #### +Skewed Value to Truncated Path: {[103]=/list_bucketing_static_part/ds=2008-04-08/hr=11/key=103, [484]=/list_bucketing_static_part/ds=2008-04-08/hr=11/key=484} +Storage Desc Params: + serialization.format 1 +PREHOOK: query: -- list bucketing DML with merge. use bucketize to generate a few small files. +explain extended +insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11') +select key, value from srcpart where ds = '2008-04-08' +PREHOOK: type: QUERY +POSTHOOK: query: -- list bucketing DML with merge. use bucketize to generate a few small files. +explain extended +insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11') +select key, value from srcpart where ds = '2008-04-08' +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-7 depends on stages: Stage-1 , consists of Stage-4, Stage-3, Stage-5 + Stage-4 + Stage-0 depends on stages: Stage-4, Stage-3, Stage-6 + Stage-2 depends on stages: Stage-0 + Stage-3 + Stage-5 + Stage-6 depends on stages: Stage-5 + +STAGE PLANS: + Stage: Stage-1 + Map Reduce + Map Operator Tree: + TableScan + alias: srcpart + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + GatherStats: false + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 1 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Static Partition Specification: ds=2008-04-08/hr=11/ + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat + output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat + properties: + bucket_count -1 + columns key,value + columns.comments + columns.types string:string +#### A masked pattern was here #### + name default.list_bucketing_static_part + partition_columns.types string:string + serialization.ddl struct list_bucketing_static_part { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe + name: default.list_bucketing_static_part + TotalFiles: 1 + GatherStats: true + MultiFileSpray: false + 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 +#### A masked pattern was here #### + Partition + base file name: hr=12 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2008-04-08 + hr 12 + 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 [srcpart] + /srcpart/ds=2008-04-08/hr=12 [srcpart] + + Stage: Stage-7 + Conditional Operator + + Stage: Stage-4 + Move Operator + files: + hdfs directory: true +#### A masked pattern was here #### + + Stage: Stage-0 + Move Operator + tables: + partition: + ds 2008-04-08 + hr 11 + replace: true +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat + output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat + properties: + bucket_count -1 + columns key,value + columns.comments + columns.types string:string +#### A masked pattern was here #### + name default.list_bucketing_static_part + partition_columns.types string:string + serialization.ddl struct list_bucketing_static_part { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe + name: default.list_bucketing_static_part + + Stage: Stage-2 + Stats-Aggr Operator +#### A masked pattern was here #### + + Stage: Stage-3 + Merge File Operator + Map Operator Tree: + RCFile Merge Operator + merge level: block + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + input format: org.apache.hadoop.hive.ql.io.rcfile.merge.RCFileBlockMergeInputFormat + output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat + properties: + bucket_count -1 + columns key,value + columns.comments + columns.types string:string +#### A masked pattern was here #### + name default.list_bucketing_static_part + partition_columns.types string:string + serialization.ddl struct list_bucketing_static_part { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe + + input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat + output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat + properties: + bucket_count -1 + columns key,value + columns.comments + columns.types string:string +#### A masked pattern was here #### + name default.list_bucketing_static_part + partition_columns.types string:string + serialization.ddl struct list_bucketing_static_part { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe + name: default.list_bucketing_static_part + name: default.list_bucketing_static_part + input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat + Truncated Path -> Alias: +#### A masked pattern was here #### + + Stage: Stage-5 + Merge File Operator + Map Operator Tree: + RCFile Merge Operator + merge level: block + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + input format: org.apache.hadoop.hive.ql.io.rcfile.merge.RCFileBlockMergeInputFormat + output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat + properties: + bucket_count -1 + columns key,value + columns.comments + columns.types string:string +#### A masked pattern was here #### + name default.list_bucketing_static_part + partition_columns.types string:string + serialization.ddl struct list_bucketing_static_part { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe + + input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat + output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat + properties: + bucket_count -1 + columns key,value + columns.comments + columns.types string:string +#### A masked pattern was here #### + name default.list_bucketing_static_part + partition_columns.types string:string + serialization.ddl struct list_bucketing_static_part { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe + name: default.list_bucketing_static_part + name: default.list_bucketing_static_part + input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat + Truncated Path -> Alias: +#### A masked pattern was here #### + + Stage: Stage-6 + Move Operator + files: + hdfs directory: true +#### A masked pattern was here #### + +PREHOOK: query: insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11') +select key, value from srcpart where ds = '2008-04-08' +PREHOOK: type: QUERY +PREHOOK: Input: default@srcpart +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +PREHOOK: Output: default@list_bucketing_static_part@ds=2008-04-08/hr=11 +POSTHOOK: query: insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11') +select key, value from srcpart where ds = '2008-04-08' +POSTHOOK: type: QUERY +POSTHOOK: Input: default@srcpart +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +POSTHOOK: Output: default@list_bucketing_static_part@ds=2008-04-08/hr=11 +POSTHOOK: Lineage: list_bucketing_static_part PARTITION(ds=2008-04-08,hr=11).key SIMPLE [(srcpart)srcpart.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: list_bucketing_static_part PARTITION(ds=2008-04-08,hr=11).value SIMPLE [(srcpart)srcpart.FieldSchema(name:value, type:string, comment:default), ] +PREHOOK: query: -- check DML result +show partitions list_bucketing_static_part +PREHOOK: type: SHOWPARTITIONS +PREHOOK: Input: default@list_bucketing_static_part +POSTHOOK: query: -- check DML result +show partitions list_bucketing_static_part +POSTHOOK: type: SHOWPARTITIONS +POSTHOOK: Input: default@list_bucketing_static_part +ds=2008-04-08/hr=11 +PREHOOK: query: desc formatted list_bucketing_static_part partition (ds='2008-04-08', hr='11') +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@list_bucketing_static_part +POSTHOOK: query: desc formatted list_bucketing_static_part partition (ds='2008-04-08', hr='11') +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@list_bucketing_static_part +# col_name data_type comment + +key string +value string + +# Partition Information +# col_name data_type comment + +ds string +hr string + +# Detailed Partition Information +Partition Value: [2008-04-08, 11] +Database: default +Table: list_bucketing_static_part +#### A masked pattern was here #### +Partition Parameters: + COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"} + numFiles 4 + numRows 1000 + rawDataSize 9624 + totalSize 10786 +#### A masked pattern was here #### + +# Storage Information +SerDe Library: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe +InputFormat: org.apache.hadoop.hive.ql.io.RCFileInputFormat +OutputFormat: org.apache.hadoop.hive.ql.io.RCFileOutputFormat +Compressed: No +Num Buckets: -1 +Bucket Columns: [] +Sort Columns: [] +Stored As SubDirectories: Yes +Skewed Columns: [key] +Skewed Values: [[484], [103]] +#### A masked pattern was here #### +Skewed Value to Truncated Path: {[103]=/list_bucketing_static_part/ds=2008-04-08/hr=11/key=103, [484]=/list_bucketing_static_part/ds=2008-04-08/hr=11/key=484} +Storage Desc Params: + serialization.format 1 +PREHOOK: query: select count(1) from srcpart where ds = '2008-04-08' +PREHOOK: type: QUERY +PREHOOK: Input: default@srcpart +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +#### A masked pattern was here #### +POSTHOOK: query: select count(1) from srcpart where ds = '2008-04-08' +POSTHOOK: type: QUERY +POSTHOOK: Input: default@srcpart +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +#### A masked pattern was here #### +1000 +PREHOOK: query: select count(*) from list_bucketing_static_part +PREHOOK: type: QUERY +PREHOOK: Input: default@list_bucketing_static_part +PREHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11 +#### A masked pattern was here #### +POSTHOOK: query: select count(*) from list_bucketing_static_part +POSTHOOK: type: QUERY +POSTHOOK: Input: default@list_bucketing_static_part +POSTHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11 +#### A masked pattern was here #### +1000 +PREHOOK: query: explain extended +select * from list_bucketing_static_part where ds = '2008-04-08' and hr = '11' and key = '484' and value = 'val_484' +PREHOOK: type: QUERY +POSTHOOK: query: explain extended +select * from list_bucketing_static_part where ds = '2008-04-08' and hr = '11' and key = '484' and value = 'val_484' +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-0 is a root stage + +STAGE PLANS: + Stage: Stage-0 + Fetch Operator + limit: -1 + Partition Description: + Partition + input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat + output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat + partition values: + ds 2008-04-08 + hr 11 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"} + bucket_count -1 + columns key,value + columns.comments + columns.types string:string +#### A masked pattern was here #### + name default.list_bucketing_static_part + numFiles 4 + numRows 1000 + partition_columns ds/hr + partition_columns.types string:string + rawDataSize 9624 + serialization.ddl struct list_bucketing_static_part { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe + totalSize 10786 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe + + input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat + output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat + properties: + bucket_count -1 + columns key,value + columns.comments + columns.types string:string +#### A masked pattern was here #### + name default.list_bucketing_static_part + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct list_bucketing_static_part { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe + name: default.list_bucketing_static_part + name: default.list_bucketing_static_part + Processor Tree: + TableScan + alias: list_bucketing_static_part + Statistics: Num rows: 1000 Data size: 9624 Basic stats: COMPLETE Column stats: NONE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: ((key = '484') and (value = 'val_484')) (type: boolean) + Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: '484' (type: string), 'val_484' (type: string), '2008-04-08' (type: string), '11' (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE + ListSink + +PREHOOK: query: select * from list_bucketing_static_part where ds = '2008-04-08' and hr = '11' and key = '484' and value = 'val_484' +PREHOOK: type: QUERY +PREHOOK: Input: default@list_bucketing_static_part +PREHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11 +#### A masked pattern was here #### +POSTHOOK: query: select * from list_bucketing_static_part where ds = '2008-04-08' and hr = '11' and key = '484' and value = 'val_484' +POSTHOOK: type: QUERY +POSTHOOK: Input: default@list_bucketing_static_part +POSTHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11 +#### A masked pattern was here #### +484 val_484 2008-04-08 11 +484 val_484 2008-04-08 11 +PREHOOK: query: select * from srcpart where ds = '2008-04-08' and key = '484' and value = 'val_484' +PREHOOK: type: QUERY +PREHOOK: Input: default@srcpart +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +#### A masked pattern was here #### +POSTHOOK: query: select * from srcpart where ds = '2008-04-08' and key = '484' and value = 'val_484' +POSTHOOK: type: QUERY +POSTHOOK: Input: default@srcpart +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +#### A masked pattern was here #### +484 val_484 2008-04-08 11 +484 val_484 2008-04-08 12 +PREHOOK: query: -- clean up +drop table list_bucketing_static_part +PREHOOK: type: DROPTABLE +PREHOOK: Input: default@list_bucketing_static_part +PREHOOK: Output: default@list_bucketing_static_part +POSTHOOK: query: -- clean up +drop table list_bucketing_static_part +POSTHOOK: type: DROPTABLE +POSTHOOK: Input: default@list_bucketing_static_part +POSTHOOK: Output: default@list_bucketing_static_part
http://git-wip-us.apache.org/repos/asf/hive/blob/22541610/ql/src/test/results/clientpositive/llap/join0.q.java1.7.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/join0.q.java1.7.out b/ql/src/test/results/clientpositive/llap/join0.q.java1.7.out deleted file mode 100644 index 5651839..0000000 --- a/ql/src/test/results/clientpositive/llap/join0.q.java1.7.out +++ /dev/null @@ -1,242 +0,0 @@ -Warning: Shuffle Join MERGEJOIN[15][tables = [src1, src2]] in Stage 'Reducer 2' is a cross product -PREHOOK: query: -- JAVA_VERSION_SPECIFIC_OUTPUT --- SORT_QUERY_RESULTS - -EXPLAIN -SELECT src1.key as k1, src1.value as v1, - src2.key as k2, src2.value as v2 FROM - (SELECT * FROM src WHERE src.key < 10) src1 - JOIN - (SELECT * FROM src WHERE src.key < 10) src2 - SORT BY k1, v1, k2, v2 -PREHOOK: type: QUERY -POSTHOOK: query: -- JAVA_VERSION_SPECIFIC_OUTPUT --- SORT_QUERY_RESULTS - -EXPLAIN -SELECT src1.key as k1, src1.value as v1, - src2.key as k2, src2.value as v2 FROM - (SELECT * FROM src WHERE src.key < 10) src1 - JOIN - (SELECT * FROM src WHERE src.key < 10) src2 - SORT BY k1, v1, k2, v2 -POSTHOOK: type: QUERY -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Tez - Edges: - Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) - Reducer 3 <- Reducer 2 (SIMPLE_EDGE) -#### A masked pattern was here #### - Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key < 10) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: string) - Execution mode: llap - Map 4 - Map Operator Tree: - TableScan - alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key < 10) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: string) - Execution mode: llap - Reducer 2 - Execution mode: llap - Reduce Operator Tree: - Merge Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 - 1 - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) - sort order: ++++ - Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE - Reducer 3 - Execution mode: uber - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE - 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 - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -Warning: Shuffle Join MERGEJOIN[15][tables = [src1, src2]] in Stage 'Reducer 2' is a cross product -PREHOOK: query: EXPLAIN FORMATTED -SELECT src1.key as k1, src1.value as v1, - src2.key as k2, src2.value as v2 FROM - (SELECT * FROM src WHERE src.key < 10) src1 - JOIN - (SELECT * FROM src WHERE src.key < 10) src2 - SORT BY k1, v1, k2, v2 -PREHOOK: type: QUERY -POSTHOOK: query: EXPLAIN FORMATTED -SELECT src1.key as k1, src1.value as v1, - src2.key as k2, src2.value as v2 FROM - (SELECT * FROM src WHERE src.key < 10) src1 - JOIN - (SELECT * FROM src WHERE src.key < 10) src2 - SORT BY k1, v1, k2, v2 -POSTHOOK: type: QUERY -#### A masked pattern was here #### -Warning: Shuffle Join MERGEJOIN[15][tables = [src1, src2]] in Stage 'Reducer 2' is a cross product -PREHOOK: query: SELECT src1.key as k1, src1.value as v1, - src2.key as k2, src2.value as v2 FROM - (SELECT * FROM src WHERE src.key < 10) src1 - JOIN - (SELECT * FROM src WHERE src.key < 10) src2 - SORT BY k1, v1, k2, v2 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: SELECT src1.key as k1, src1.value as v1, - src2.key as k2, src2.value as v2 FROM - (SELECT * FROM src WHERE src.key < 10) src1 - JOIN - (SELECT * FROM src WHERE src.key < 10) src2 - SORT BY k1, v1, k2, v2 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -0 val_0 0 val_0 -0 val_0 0 val_0 -0 val_0 0 val_0 -0 val_0 0 val_0 -0 val_0 0 val_0 -0 val_0 0 val_0 -0 val_0 0 val_0 -0 val_0 0 val_0 -0 val_0 0 val_0 -0 val_0 2 val_2 -0 val_0 2 val_2 -0 val_0 2 val_2 -0 val_0 4 val_4 -0 val_0 4 val_4 -0 val_0 4 val_4 -0 val_0 5 val_5 -0 val_0 5 val_5 -0 val_0 5 val_5 -0 val_0 5 val_5 -0 val_0 5 val_5 -0 val_0 5 val_5 -0 val_0 5 val_5 -0 val_0 5 val_5 -0 val_0 5 val_5 -0 val_0 8 val_8 -0 val_0 8 val_8 -0 val_0 8 val_8 -0 val_0 9 val_9 -0 val_0 9 val_9 -0 val_0 9 val_9 -2 val_2 0 val_0 -2 val_2 0 val_0 -2 val_2 0 val_0 -2 val_2 2 val_2 -2 val_2 4 val_4 -2 val_2 5 val_5 -2 val_2 5 val_5 -2 val_2 5 val_5 -2 val_2 8 val_8 -2 val_2 9 val_9 -4 val_4 0 val_0 -4 val_4 0 val_0 -4 val_4 0 val_0 -4 val_4 2 val_2 -4 val_4 4 val_4 -4 val_4 5 val_5 -4 val_4 5 val_5 -4 val_4 5 val_5 -4 val_4 8 val_8 -4 val_4 9 val_9 -5 val_5 0 val_0 -5 val_5 0 val_0 -5 val_5 0 val_0 -5 val_5 0 val_0 -5 val_5 0 val_0 -5 val_5 0 val_0 -5 val_5 0 val_0 -5 val_5 0 val_0 -5 val_5 0 val_0 -5 val_5 2 val_2 -5 val_5 2 val_2 -5 val_5 2 val_2 -5 val_5 4 val_4 -5 val_5 4 val_4 -5 val_5 4 val_4 -5 val_5 5 val_5 -5 val_5 5 val_5 -5 val_5 5 val_5 -5 val_5 5 val_5 -5 val_5 5 val_5 -5 val_5 5 val_5 -5 val_5 5 val_5 -5 val_5 5 val_5 -5 val_5 5 val_5 -5 val_5 8 val_8 -5 val_5 8 val_8 -5 val_5 8 val_8 -5 val_5 9 val_9 -5 val_5 9 val_9 -5 val_5 9 val_9 -8 val_8 0 val_0 -8 val_8 0 val_0 -8 val_8 0 val_0 -8 val_8 2 val_2 -8 val_8 4 val_4 -8 val_8 5 val_5 -8 val_8 5 val_5 -8 val_8 5 val_5 -8 val_8 8 val_8 -8 val_8 9 val_9 -9 val_9 0 val_0 -9 val_9 0 val_0 -9 val_9 0 val_0 -9 val_9 2 val_2 -9 val_9 4 val_4 -9 val_9 5 val_5 -9 val_9 5 val_5 -9 val_9 5 val_5 -9 val_9 8 val_8 -9 val_9 9 val_9 http://git-wip-us.apache.org/repos/asf/hive/blob/22541610/ql/src/test/results/clientpositive/llap/join0.q.java1.8.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/join0.q.java1.8.out b/ql/src/test/results/clientpositive/llap/join0.q.java1.8.out deleted file mode 100644 index 5651839..0000000 --- a/ql/src/test/results/clientpositive/llap/join0.q.java1.8.out +++ /dev/null @@ -1,242 +0,0 @@ -Warning: Shuffle Join MERGEJOIN[15][tables = [src1, src2]] in Stage 'Reducer 2' is a cross product -PREHOOK: query: -- JAVA_VERSION_SPECIFIC_OUTPUT --- SORT_QUERY_RESULTS - -EXPLAIN -SELECT src1.key as k1, src1.value as v1, - src2.key as k2, src2.value as v2 FROM - (SELECT * FROM src WHERE src.key < 10) src1 - JOIN - (SELECT * FROM src WHERE src.key < 10) src2 - SORT BY k1, v1, k2, v2 -PREHOOK: type: QUERY -POSTHOOK: query: -- JAVA_VERSION_SPECIFIC_OUTPUT --- SORT_QUERY_RESULTS - -EXPLAIN -SELECT src1.key as k1, src1.value as v1, - src2.key as k2, src2.value as v2 FROM - (SELECT * FROM src WHERE src.key < 10) src1 - JOIN - (SELECT * FROM src WHERE src.key < 10) src2 - SORT BY k1, v1, k2, v2 -POSTHOOK: type: QUERY -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Tez - Edges: - Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) - Reducer 3 <- Reducer 2 (SIMPLE_EDGE) -#### A masked pattern was here #### - Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key < 10) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: string) - Execution mode: llap - Map 4 - Map Operator Tree: - TableScan - alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key < 10) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: string) - Execution mode: llap - Reducer 2 - Execution mode: llap - Reduce Operator Tree: - Merge Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 - 1 - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) - sort order: ++++ - Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE - Reducer 3 - Execution mode: uber - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE - 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 - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -Warning: Shuffle Join MERGEJOIN[15][tables = [src1, src2]] in Stage 'Reducer 2' is a cross product -PREHOOK: query: EXPLAIN FORMATTED -SELECT src1.key as k1, src1.value as v1, - src2.key as k2, src2.value as v2 FROM - (SELECT * FROM src WHERE src.key < 10) src1 - JOIN - (SELECT * FROM src WHERE src.key < 10) src2 - SORT BY k1, v1, k2, v2 -PREHOOK: type: QUERY -POSTHOOK: query: EXPLAIN FORMATTED -SELECT src1.key as k1, src1.value as v1, - src2.key as k2, src2.value as v2 FROM - (SELECT * FROM src WHERE src.key < 10) src1 - JOIN - (SELECT * FROM src WHERE src.key < 10) src2 - SORT BY k1, v1, k2, v2 -POSTHOOK: type: QUERY -#### A masked pattern was here #### -Warning: Shuffle Join MERGEJOIN[15][tables = [src1, src2]] in Stage 'Reducer 2' is a cross product -PREHOOK: query: SELECT src1.key as k1, src1.value as v1, - src2.key as k2, src2.value as v2 FROM - (SELECT * FROM src WHERE src.key < 10) src1 - JOIN - (SELECT * FROM src WHERE src.key < 10) src2 - SORT BY k1, v1, k2, v2 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: SELECT src1.key as k1, src1.value as v1, - src2.key as k2, src2.value as v2 FROM - (SELECT * FROM src WHERE src.key < 10) src1 - JOIN - (SELECT * FROM src WHERE src.key < 10) src2 - SORT BY k1, v1, k2, v2 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -0 val_0 0 val_0 -0 val_0 0 val_0 -0 val_0 0 val_0 -0 val_0 0 val_0 -0 val_0 0 val_0 -0 val_0 0 val_0 -0 val_0 0 val_0 -0 val_0 0 val_0 -0 val_0 0 val_0 -0 val_0 2 val_2 -0 val_0 2 val_2 -0 val_0 2 val_2 -0 val_0 4 val_4 -0 val_0 4 val_4 -0 val_0 4 val_4 -0 val_0 5 val_5 -0 val_0 5 val_5 -0 val_0 5 val_5 -0 val_0 5 val_5 -0 val_0 5 val_5 -0 val_0 5 val_5 -0 val_0 5 val_5 -0 val_0 5 val_5 -0 val_0 5 val_5 -0 val_0 8 val_8 -0 val_0 8 val_8 -0 val_0 8 val_8 -0 val_0 9 val_9 -0 val_0 9 val_9 -0 val_0 9 val_9 -2 val_2 0 val_0 -2 val_2 0 val_0 -2 val_2 0 val_0 -2 val_2 2 val_2 -2 val_2 4 val_4 -2 val_2 5 val_5 -2 val_2 5 val_5 -2 val_2 5 val_5 -2 val_2 8 val_8 -2 val_2 9 val_9 -4 val_4 0 val_0 -4 val_4 0 val_0 -4 val_4 0 val_0 -4 val_4 2 val_2 -4 val_4 4 val_4 -4 val_4 5 val_5 -4 val_4 5 val_5 -4 val_4 5 val_5 -4 val_4 8 val_8 -4 val_4 9 val_9 -5 val_5 0 val_0 -5 val_5 0 val_0 -5 val_5 0 val_0 -5 val_5 0 val_0 -5 val_5 0 val_0 -5 val_5 0 val_0 -5 val_5 0 val_0 -5 val_5 0 val_0 -5 val_5 0 val_0 -5 val_5 2 val_2 -5 val_5 2 val_2 -5 val_5 2 val_2 -5 val_5 4 val_4 -5 val_5 4 val_4 -5 val_5 4 val_4 -5 val_5 5 val_5 -5 val_5 5 val_5 -5 val_5 5 val_5 -5 val_5 5 val_5 -5 val_5 5 val_5 -5 val_5 5 val_5 -5 val_5 5 val_5 -5 val_5 5 val_5 -5 val_5 5 val_5 -5 val_5 8 val_8 -5 val_5 8 val_8 -5 val_5 8 val_8 -5 val_5 9 val_9 -5 val_5 9 val_9 -5 val_5 9 val_9 -8 val_8 0 val_0 -8 val_8 0 val_0 -8 val_8 0 val_0 -8 val_8 2 val_2 -8 val_8 4 val_4 -8 val_8 5 val_5 -8 val_8 5 val_5 -8 val_8 5 val_5 -8 val_8 8 val_8 -8 val_8 9 val_9 -9 val_9 0 val_0 -9 val_9 0 val_0 -9 val_9 0 val_0 -9 val_9 2 val_2 -9 val_9 4 val_4 -9 val_9 5 val_5 -9 val_9 5 val_5 -9 val_9 5 val_5 -9 val_9 8 val_8 -9 val_9 9 val_9 http://git-wip-us.apache.org/repos/asf/hive/blob/22541610/ql/src/test/results/clientpositive/llap/join0.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/join0.q.out b/ql/src/test/results/clientpositive/llap/join0.q.out new file mode 100644 index 0000000..f177afc --- /dev/null +++ b/ql/src/test/results/clientpositive/llap/join0.q.out @@ -0,0 +1,243 @@ +Warning: Shuffle Join MERGEJOIN[15][tables = [src1, src2]] in Stage 'Reducer 2' is a cross product +PREHOOK: query: -- SORT_QUERY_RESULTS + +EXPLAIN +SELECT src1.key as k1, src1.value as v1, + src2.key as k2, src2.value as v2 FROM + (SELECT * FROM src WHERE src.key < 10) src1 + JOIN + (SELECT * FROM src WHERE src.key < 10) src2 + SORT BY k1, v1, k2, v2 +PREHOOK: type: QUERY +POSTHOOK: query: -- SORT_QUERY_RESULTS + +EXPLAIN +SELECT src1.key as k1, src1.value as v1, + src2.key as k2, src2.value as v2 FROM + (SELECT * FROM src WHERE src.key < 10) src1 + JOIN + (SELECT * FROM src WHERE src.key < 10) src2 + SORT BY k1, v1, k2, v2 +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 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (key < 10) (type: boolean) + Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: string), _col1 (type: string) + Execution mode: llap + LLAP IO: no inputs + Map 4 + Map Operator Tree: + TableScan + alias: src + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (key < 10) (type: boolean) + Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: string), _col1 (type: string) + Execution mode: llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 + 1 + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) + sort order: ++++ + Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +Warning: Shuffle Join MERGEJOIN[15][tables = [src1, src2]] in Stage 'Reducer 2' is a cross product +PREHOOK: query: EXPLAIN FORMATTED +SELECT src1.key as k1, src1.value as v1, + src2.key as k2, src2.value as v2 FROM + (SELECT * FROM src WHERE src.key < 10) src1 + JOIN + (SELECT * FROM src WHERE src.key < 10) src2 + SORT BY k1, v1, k2, v2 +PREHOOK: type: QUERY +POSTHOOK: query: EXPLAIN FORMATTED +SELECT src1.key as k1, src1.value as v1, + src2.key as k2, src2.value as v2 FROM + (SELECT * FROM src WHERE src.key < 10) src1 + JOIN + (SELECT * FROM src WHERE src.key < 10) src2 + SORT BY k1, v1, k2, v2 +POSTHOOK: type: QUERY +#### A masked pattern was here #### +Warning: Shuffle Join MERGEJOIN[15][tables = [src1, src2]] in Stage 'Reducer 2' is a cross product +PREHOOK: query: SELECT src1.key as k1, src1.value as v1, + src2.key as k2, src2.value as v2 FROM + (SELECT * FROM src WHERE src.key < 10) src1 + JOIN + (SELECT * FROM src WHERE src.key < 10) src2 + SORT BY k1, v1, k2, v2 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: SELECT src1.key as k1, src1.value as v1, + src2.key as k2, src2.value as v2 FROM + (SELECT * FROM src WHERE src.key < 10) src1 + JOIN + (SELECT * FROM src WHERE src.key < 10) src2 + SORT BY k1, v1, k2, v2 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +0 val_0 0 val_0 +0 val_0 0 val_0 +0 val_0 0 val_0 +0 val_0 0 val_0 +0 val_0 0 val_0 +0 val_0 0 val_0 +0 val_0 0 val_0 +0 val_0 0 val_0 +0 val_0 0 val_0 +0 val_0 2 val_2 +0 val_0 2 val_2 +0 val_0 2 val_2 +0 val_0 4 val_4 +0 val_0 4 val_4 +0 val_0 4 val_4 +0 val_0 5 val_5 +0 val_0 5 val_5 +0 val_0 5 val_5 +0 val_0 5 val_5 +0 val_0 5 val_5 +0 val_0 5 val_5 +0 val_0 5 val_5 +0 val_0 5 val_5 +0 val_0 5 val_5 +0 val_0 8 val_8 +0 val_0 8 val_8 +0 val_0 8 val_8 +0 val_0 9 val_9 +0 val_0 9 val_9 +0 val_0 9 val_9 +2 val_2 0 val_0 +2 val_2 0 val_0 +2 val_2 0 val_0 +2 val_2 2 val_2 +2 val_2 4 val_4 +2 val_2 5 val_5 +2 val_2 5 val_5 +2 val_2 5 val_5 +2 val_2 8 val_8 +2 val_2 9 val_9 +4 val_4 0 val_0 +4 val_4 0 val_0 +4 val_4 0 val_0 +4 val_4 2 val_2 +4 val_4 4 val_4 +4 val_4 5 val_5 +4 val_4 5 val_5 +4 val_4 5 val_5 +4 val_4 8 val_8 +4 val_4 9 val_9 +5 val_5 0 val_0 +5 val_5 0 val_0 +5 val_5 0 val_0 +5 val_5 0 val_0 +5 val_5 0 val_0 +5 val_5 0 val_0 +5 val_5 0 val_0 +5 val_5 0 val_0 +5 val_5 0 val_0 +5 val_5 2 val_2 +5 val_5 2 val_2 +5 val_5 2 val_2 +5 val_5 4 val_4 +5 val_5 4 val_4 +5 val_5 4 val_4 +5 val_5 5 val_5 +5 val_5 5 val_5 +5 val_5 5 val_5 +5 val_5 5 val_5 +5 val_5 5 val_5 +5 val_5 5 val_5 +5 val_5 5 val_5 +5 val_5 5 val_5 +5 val_5 5 val_5 +5 val_5 8 val_8 +5 val_5 8 val_8 +5 val_5 8 val_8 +5 val_5 9 val_9 +5 val_5 9 val_9 +5 val_5 9 val_9 +8 val_8 0 val_0 +8 val_8 0 val_0 +8 val_8 0 val_0 +8 val_8 2 val_2 +8 val_8 4 val_4 +8 val_8 5 val_5 +8 val_8 5 val_5 +8 val_8 5 val_5 +8 val_8 8 val_8 +8 val_8 9 val_9 +9 val_9 0 val_0 +9 val_9 0 val_0 +9 val_9 0 val_0 +9 val_9 2 val_2 +9 val_9 4 val_4 +9 val_9 5 val_5 +9 val_9 5 val_5 +9 val_9 5 val_5 +9 val_9 8 val_8 +9 val_9 9 val_9 http://git-wip-us.apache.org/repos/asf/hive/blob/22541610/ql/src/test/results/clientpositive/llap/vector_cast_constant.q.java1.7.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/vector_cast_constant.q.java1.7.out b/ql/src/test/results/clientpositive/llap/vector_cast_constant.q.java1.7.out deleted file mode 100644 index 22b5d93..0000000 --- a/ql/src/test/results/clientpositive/llap/vector_cast_constant.q.java1.7.out +++ /dev/null @@ -1,217 +0,0 @@ -PREHOOK: query: -- JAVA_VERSION_SPECIFIC_OUTPUT - -DROP TABLE over1k -PREHOOK: type: DROPTABLE -POSTHOOK: query: -- JAVA_VERSION_SPECIFIC_OUTPUT - -DROP TABLE over1k -POSTHOOK: type: DROPTABLE -PREHOOK: query: DROP TABLE over1korc -PREHOOK: type: DROPTABLE -POSTHOOK: query: DROP TABLE over1korc -POSTHOOK: type: DROPTABLE -PREHOOK: query: -- data setup -CREATE TABLE over1k(t tinyint, - si smallint, - i int, - b bigint, - f float, - d double, - bo boolean, - s string, - ts timestamp, - dec decimal(4,2), - bin binary) -ROW FORMAT DELIMITED FIELDS TERMINATED BY '|' -STORED AS TEXTFILE -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@over1k -POSTHOOK: query: -- data setup -CREATE TABLE over1k(t tinyint, - si smallint, - i int, - b bigint, - f float, - d double, - bo boolean, - s string, - ts timestamp, - dec decimal(4,2), - bin binary) -ROW FORMAT DELIMITED FIELDS TERMINATED BY '|' -STORED AS TEXTFILE -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@over1k -PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/over1k' OVERWRITE INTO TABLE over1k -PREHOOK: type: LOAD -#### A masked pattern was here #### -PREHOOK: Output: default@over1k -POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/over1k' OVERWRITE INTO TABLE over1k -POSTHOOK: type: LOAD -#### A masked pattern was here #### -POSTHOOK: Output: default@over1k -PREHOOK: query: CREATE TABLE over1korc(t tinyint, - si smallint, - i int, - b bigint, - f float, - d double, - bo boolean, - s string, - ts timestamp, - dec decimal(4,2), - bin binary) -STORED AS ORC -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@over1korc -POSTHOOK: query: CREATE TABLE over1korc(t tinyint, - si smallint, - i int, - b bigint, - f float, - d double, - bo boolean, - s string, - ts timestamp, - dec decimal(4,2), - bin binary) -STORED AS ORC -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@over1korc -PREHOOK: query: INSERT INTO TABLE over1korc SELECT * FROM over1k -PREHOOK: type: QUERY -PREHOOK: Input: default@over1k -PREHOOK: Output: default@over1korc -POSTHOOK: query: INSERT INTO TABLE over1korc SELECT * FROM over1k -POSTHOOK: type: QUERY -POSTHOOK: Input: default@over1k -POSTHOOK: Output: default@over1korc -POSTHOOK: Lineage: over1korc.b SIMPLE [(over1k)over1k.FieldSchema(name:b, type:bigint, comment:null), ] -POSTHOOK: Lineage: over1korc.bin SIMPLE [(over1k)over1k.FieldSchema(name:bin, type:binary, comment:null), ] -POSTHOOK: Lineage: over1korc.bo SIMPLE [(over1k)over1k.FieldSchema(name:bo, type:boolean, comment:null), ] -POSTHOOK: Lineage: over1korc.d SIMPLE [(over1k)over1k.FieldSchema(name:d, type:double, comment:null), ] -POSTHOOK: Lineage: over1korc.dec SIMPLE [(over1k)over1k.FieldSchema(name:dec, type:decimal(4,2), comment:null), ] -POSTHOOK: Lineage: over1korc.f SIMPLE [(over1k)over1k.FieldSchema(name:f, type:float, comment:null), ] -POSTHOOK: Lineage: over1korc.i SIMPLE [(over1k)over1k.FieldSchema(name:i, type:int, comment:null), ] -POSTHOOK: Lineage: over1korc.s SIMPLE [(over1k)over1k.FieldSchema(name:s, type:string, comment:null), ] -POSTHOOK: Lineage: over1korc.si SIMPLE [(over1k)over1k.FieldSchema(name:si, type:smallint, comment:null), ] -POSTHOOK: Lineage: over1korc.t SIMPLE [(over1k)over1k.FieldSchema(name:t, type:tinyint, comment:null), ] -POSTHOOK: Lineage: over1korc.ts SIMPLE [(over1k)over1k.FieldSchema(name:ts, type:timestamp, comment:null), ] -PREHOOK: query: EXPLAIN SELECT - i, - AVG(CAST(50 AS INT)) AS `avg_int_ok`, - AVG(CAST(50 AS DOUBLE)) AS `avg_double_ok`, - AVG(CAST(50 AS DECIMAL)) AS `avg_decimal_ok` - FROM over1korc GROUP BY i ORDER BY i LIMIT 10 -PREHOOK: type: QUERY -POSTHOOK: query: EXPLAIN SELECT - i, - AVG(CAST(50 AS INT)) AS `avg_int_ok`, - AVG(CAST(50 AS DOUBLE)) AS `avg_double_ok`, - AVG(CAST(50 AS DECIMAL)) AS `avg_decimal_ok` - FROM over1korc GROUP BY i ORDER BY i LIMIT 10 -POSTHOOK: type: QUERY -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Tez - Edges: - Reducer 2 <- Map 1 (SIMPLE_EDGE) - Reducer 3 <- Reducer 2 (SIMPLE_EDGE) -#### A masked pattern was here #### - Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: over1korc - Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: i (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: avg(50), avg(50.0), avg(50) - keys: _col0 (type: int) - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: struct<count:bigint,sum:double,input:int>), _col2 (type: struct<count:bigint,sum:double,input:double>), _col3 (type: struct<count:bigint,sum:decimal(12,0),input:decimal(10,0)>) - Execution mode: vectorized, llap - Reducer 2 - Execution mode: llap - Reduce Operator Tree: - Group By Operator - aggregations: avg(VALUE._col0), avg(VALUE._col1), avg(VALUE._col2) - keys: KEY._col0 (type: int) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 524 Data size: 155436 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Statistics: Num rows: 524 Data size: 155436 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: double), _col2 (type: double), _col3 (type: decimal(14,4)) - Reducer 3 - Execution mode: vectorized, uber - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: double), VALUE._col1 (type: double), VALUE._col2 (type: decimal(14,4)) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 524 Data size: 155436 Basic stats: COMPLETE Column stats: NONE - Limit - Number of rows: 10 - Statistics: Num rows: 10 Data size: 2960 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 10 Data size: 2960 Basic stats: COMPLETE Column stats: NONE - 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 - - Stage: Stage-0 - Fetch Operator - limit: 10 - Processor Tree: - ListSink - -PREHOOK: query: SELECT - i, - AVG(CAST(50 AS INT)) AS `avg_int_ok`, - AVG(CAST(50 AS DOUBLE)) AS `avg_double_ok`, - AVG(CAST(50 AS DECIMAL)) AS `avg_decimal_ok` - FROM over1korc GROUP BY i ORDER BY i LIMIT 10 -PREHOOK: type: QUERY -PREHOOK: Input: default@over1korc -#### A masked pattern was here #### -POSTHOOK: query: SELECT - i, - AVG(CAST(50 AS INT)) AS `avg_int_ok`, - AVG(CAST(50 AS DOUBLE)) AS `avg_double_ok`, - AVG(CAST(50 AS DECIMAL)) AS `avg_decimal_ok` - FROM over1korc GROUP BY i ORDER BY i LIMIT 10 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@over1korc -#### A masked pattern was here #### -65536 50.0 50.0 50 -65537 50.0 50.0 50 -65538 50.0 50.0 50 -65539 50.0 50.0 50 -65540 50.0 50.0 50 -65541 50.0 50.0 50 -65542 50.0 50.0 50 -65543 50.0 50.0 50 -65544 50.0 50.0 50 -65545 50.0 50.0 50 http://git-wip-us.apache.org/repos/asf/hive/blob/22541610/ql/src/test/results/clientpositive/llap/vector_cast_constant.q.java1.8.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/vector_cast_constant.q.java1.8.out b/ql/src/test/results/clientpositive/llap/vector_cast_constant.q.java1.8.out deleted file mode 100644 index 22b5d93..0000000 --- a/ql/src/test/results/clientpositive/llap/vector_cast_constant.q.java1.8.out +++ /dev/null @@ -1,217 +0,0 @@ -PREHOOK: query: -- JAVA_VERSION_SPECIFIC_OUTPUT - -DROP TABLE over1k -PREHOOK: type: DROPTABLE -POSTHOOK: query: -- JAVA_VERSION_SPECIFIC_OUTPUT - -DROP TABLE over1k -POSTHOOK: type: DROPTABLE -PREHOOK: query: DROP TABLE over1korc -PREHOOK: type: DROPTABLE -POSTHOOK: query: DROP TABLE over1korc -POSTHOOK: type: DROPTABLE -PREHOOK: query: -- data setup -CREATE TABLE over1k(t tinyint, - si smallint, - i int, - b bigint, - f float, - d double, - bo boolean, - s string, - ts timestamp, - dec decimal(4,2), - bin binary) -ROW FORMAT DELIMITED FIELDS TERMINATED BY '|' -STORED AS TEXTFILE -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@over1k -POSTHOOK: query: -- data setup -CREATE TABLE over1k(t tinyint, - si smallint, - i int, - b bigint, - f float, - d double, - bo boolean, - s string, - ts timestamp, - dec decimal(4,2), - bin binary) -ROW FORMAT DELIMITED FIELDS TERMINATED BY '|' -STORED AS TEXTFILE -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@over1k -PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/over1k' OVERWRITE INTO TABLE over1k -PREHOOK: type: LOAD -#### A masked pattern was here #### -PREHOOK: Output: default@over1k -POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/over1k' OVERWRITE INTO TABLE over1k -POSTHOOK: type: LOAD -#### A masked pattern was here #### -POSTHOOK: Output: default@over1k -PREHOOK: query: CREATE TABLE over1korc(t tinyint, - si smallint, - i int, - b bigint, - f float, - d double, - bo boolean, - s string, - ts timestamp, - dec decimal(4,2), - bin binary) -STORED AS ORC -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@over1korc -POSTHOOK: query: CREATE TABLE over1korc(t tinyint, - si smallint, - i int, - b bigint, - f float, - d double, - bo boolean, - s string, - ts timestamp, - dec decimal(4,2), - bin binary) -STORED AS ORC -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@over1korc -PREHOOK: query: INSERT INTO TABLE over1korc SELECT * FROM over1k -PREHOOK: type: QUERY -PREHOOK: Input: default@over1k -PREHOOK: Output: default@over1korc -POSTHOOK: query: INSERT INTO TABLE over1korc SELECT * FROM over1k -POSTHOOK: type: QUERY -POSTHOOK: Input: default@over1k -POSTHOOK: Output: default@over1korc -POSTHOOK: Lineage: over1korc.b SIMPLE [(over1k)over1k.FieldSchema(name:b, type:bigint, comment:null), ] -POSTHOOK: Lineage: over1korc.bin SIMPLE [(over1k)over1k.FieldSchema(name:bin, type:binary, comment:null), ] -POSTHOOK: Lineage: over1korc.bo SIMPLE [(over1k)over1k.FieldSchema(name:bo, type:boolean, comment:null), ] -POSTHOOK: Lineage: over1korc.d SIMPLE [(over1k)over1k.FieldSchema(name:d, type:double, comment:null), ] -POSTHOOK: Lineage: over1korc.dec SIMPLE [(over1k)over1k.FieldSchema(name:dec, type:decimal(4,2), comment:null), ] -POSTHOOK: Lineage: over1korc.f SIMPLE [(over1k)over1k.FieldSchema(name:f, type:float, comment:null), ] -POSTHOOK: Lineage: over1korc.i SIMPLE [(over1k)over1k.FieldSchema(name:i, type:int, comment:null), ] -POSTHOOK: Lineage: over1korc.s SIMPLE [(over1k)over1k.FieldSchema(name:s, type:string, comment:null), ] -POSTHOOK: Lineage: over1korc.si SIMPLE [(over1k)over1k.FieldSchema(name:si, type:smallint, comment:null), ] -POSTHOOK: Lineage: over1korc.t SIMPLE [(over1k)over1k.FieldSchema(name:t, type:tinyint, comment:null), ] -POSTHOOK: Lineage: over1korc.ts SIMPLE [(over1k)over1k.FieldSchema(name:ts, type:timestamp, comment:null), ] -PREHOOK: query: EXPLAIN SELECT - i, - AVG(CAST(50 AS INT)) AS `avg_int_ok`, - AVG(CAST(50 AS DOUBLE)) AS `avg_double_ok`, - AVG(CAST(50 AS DECIMAL)) AS `avg_decimal_ok` - FROM over1korc GROUP BY i ORDER BY i LIMIT 10 -PREHOOK: type: QUERY -POSTHOOK: query: EXPLAIN SELECT - i, - AVG(CAST(50 AS INT)) AS `avg_int_ok`, - AVG(CAST(50 AS DOUBLE)) AS `avg_double_ok`, - AVG(CAST(50 AS DECIMAL)) AS `avg_decimal_ok` - FROM over1korc GROUP BY i ORDER BY i LIMIT 10 -POSTHOOK: type: QUERY -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Tez - Edges: - Reducer 2 <- Map 1 (SIMPLE_EDGE) - Reducer 3 <- Reducer 2 (SIMPLE_EDGE) -#### A masked pattern was here #### - Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: over1korc - Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: i (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: avg(50), avg(50.0), avg(50) - keys: _col0 (type: int) - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: struct<count:bigint,sum:double,input:int>), _col2 (type: struct<count:bigint,sum:double,input:double>), _col3 (type: struct<count:bigint,sum:decimal(12,0),input:decimal(10,0)>) - Execution mode: vectorized, llap - Reducer 2 - Execution mode: llap - Reduce Operator Tree: - Group By Operator - aggregations: avg(VALUE._col0), avg(VALUE._col1), avg(VALUE._col2) - keys: KEY._col0 (type: int) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 524 Data size: 155436 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Statistics: Num rows: 524 Data size: 155436 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: double), _col2 (type: double), _col3 (type: decimal(14,4)) - Reducer 3 - Execution mode: vectorized, uber - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: double), VALUE._col1 (type: double), VALUE._col2 (type: decimal(14,4)) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 524 Data size: 155436 Basic stats: COMPLETE Column stats: NONE - Limit - Number of rows: 10 - Statistics: Num rows: 10 Data size: 2960 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 10 Data size: 2960 Basic stats: COMPLETE Column stats: NONE - 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 - - Stage: Stage-0 - Fetch Operator - limit: 10 - Processor Tree: - ListSink - -PREHOOK: query: SELECT - i, - AVG(CAST(50 AS INT)) AS `avg_int_ok`, - AVG(CAST(50 AS DOUBLE)) AS `avg_double_ok`, - AVG(CAST(50 AS DECIMAL)) AS `avg_decimal_ok` - FROM over1korc GROUP BY i ORDER BY i LIMIT 10 -PREHOOK: type: QUERY -PREHOOK: Input: default@over1korc -#### A masked pattern was here #### -POSTHOOK: query: SELECT - i, - AVG(CAST(50 AS INT)) AS `avg_int_ok`, - AVG(CAST(50 AS DOUBLE)) AS `avg_double_ok`, - AVG(CAST(50 AS DECIMAL)) AS `avg_decimal_ok` - FROM over1korc GROUP BY i ORDER BY i LIMIT 10 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@over1korc -#### A masked pattern was here #### -65536 50.0 50.0 50 -65537 50.0 50.0 50 -65538 50.0 50.0 50 -65539 50.0 50.0 50 -65540 50.0 50.0 50 -65541 50.0 50.0 50 -65542 50.0 50.0 50 -65543 50.0 50.0 50 -65544 50.0 50.0 50 -65545 50.0 50.0 50