http://git-wip-us.apache.org/repos/asf/hive/blob/9687dcc9/ql/src/test/results/clientpositive/list_bucket_dml_5.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/list_bucket_dml_5.q.out b/ql/src/test/results/clientpositive/list_bucket_dml_5.q.out new file mode 100644 index 0000000..09cb847 --- /dev/null +++ b/ql/src/test/results/clientpositive/list_bucket_dml_5.q.out @@ -0,0 +1,504 @@ +PREHOOK: query: -- list bucketing DML: multiple skewed columns. 2 stages + +-- INCLUDE_HADOOP_MAJOR_VERSIONS(0.23) +-- SORT_QUERY_RESULTS + +-- create a skewed table +create table list_bucketing_dynamic_part (key String, value String) +partitioned by (ds String, hr String) +skewed by (key, value) on (('484','val_484'),('51','val_14'),('103','val_103')) +stored as DIRECTORIES +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@list_bucketing_dynamic_part +POSTHOOK: query: -- list bucketing DML: multiple skewed columns. 2 stages + +-- INCLUDE_HADOOP_MAJOR_VERSIONS(0.23) +-- SORT_QUERY_RESULTS + +-- create a skewed table +create table list_bucketing_dynamic_part (key String, value String) +partitioned by (ds String, hr String) +skewed by (key, value) on (('484','val_484'),('51','val_14'),('103','val_103')) +stored as DIRECTORIES +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@list_bucketing_dynamic_part +PREHOOK: query: -- list bucketing DML +explain extended +insert overwrite table list_bucketing_dynamic_part partition (ds='2008-04-08', hr) select key, value, hr from srcpart where ds='2008-04-08' +PREHOOK: type: QUERY +POSTHOOK: query: -- list bucketing DML +explain extended +insert overwrite table list_bucketing_dynamic_part partition (ds='2008-04-08', hr) select key, value, hr 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), hr (type: string) + outputColumnNames: _col0, _col1, _col2 + 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/ + Statistics: Num rows: 1000 Data size: 10624 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: + bucket_count -1 + columns key,value + columns.comments + columns.types string:string +#### A masked pattern was here #### + name default.list_bucketing_dynamic_part + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct list_bucketing_dynamic_part { 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.list_bucketing_dynamic_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 + 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: + bucket_count -1 + columns key,value + columns.comments + columns.types string:string +#### A masked pattern was here #### + name default.list_bucketing_dynamic_part + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct list_bucketing_dynamic_part { 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.list_bucketing_dynamic_part + + Stage: Stage-2 + Stats-Aggr Operator +#### A masked pattern was here #### + +PREHOOK: query: insert overwrite table list_bucketing_dynamic_part partition (ds='2008-04-08', hr) select key, value, hr 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_dynamic_part@ds=2008-04-08 +POSTHOOK: query: insert overwrite table list_bucketing_dynamic_part partition (ds='2008-04-08', hr) select key, value, hr 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_dynamic_part@ds=2008-04-08/hr=11 +POSTHOOK: Output: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=12 +POSTHOOK: Lineage: list_bucketing_dynamic_part PARTITION(ds=2008-04-08,hr=11).key SIMPLE [(srcpart)srcpart.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: list_bucketing_dynamic_part PARTITION(ds=2008-04-08,hr=11).value SIMPLE [(srcpart)srcpart.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: list_bucketing_dynamic_part PARTITION(ds=2008-04-08,hr=12).key SIMPLE [(srcpart)srcpart.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: list_bucketing_dynamic_part PARTITION(ds=2008-04-08,hr=12).value SIMPLE [(srcpart)srcpart.FieldSchema(name:value, type:string, comment:default), ] +PREHOOK: query: -- check DML result +desc formatted list_bucketing_dynamic_part partition (ds='2008-04-08', hr='11') +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@list_bucketing_dynamic_part +POSTHOOK: query: -- check DML result +desc formatted list_bucketing_dynamic_part partition (ds='2008-04-08', hr='11') +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@list_bucketing_dynamic_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_dynamic_part +#### A masked pattern was here #### +Partition Parameters: + COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"} + numFiles 3 + numRows 500 + rawDataSize 5312 + 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: -1 +Bucket Columns: [] +Sort Columns: [] +Stored As SubDirectories: Yes +Skewed Columns: [key, value] +Skewed Values: [[484, val_484], [51, val_14], [103, val_103]] +#### A masked pattern was here #### +Skewed Value to Truncated Path: {[484, val_484]=/list_bucketing_dynamic_part/ds=2008-04-08/hr=11/key=484/value=val_484, [103, val_103]=/list_bucketing_dynamic_part/ds=2008-04-08/hr=11/key=103/value=val_103} +Storage Desc Params: + serialization.format 1 +PREHOOK: query: desc formatted list_bucketing_dynamic_part partition (ds='2008-04-08', hr='12') +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@list_bucketing_dynamic_part +POSTHOOK: query: desc formatted list_bucketing_dynamic_part partition (ds='2008-04-08', hr='12') +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@list_bucketing_dynamic_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, 12] +Database: default +Table: list_bucketing_dynamic_part +#### A masked pattern was here #### +Partition Parameters: + COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"} + numFiles 3 + numRows 500 + rawDataSize 5312 + 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: -1 +Bucket Columns: [] +Sort Columns: [] +Stored As SubDirectories: Yes +Skewed Columns: [key, value] +Skewed Values: [[484, val_484], [51, val_14], [103, val_103]] +#### A masked pattern was here #### +Skewed Value to Truncated Path: {[484, val_484]=/list_bucketing_dynamic_part/ds=2008-04-08/hr=12/key=484/value=val_484, [103, val_103]=/list_bucketing_dynamic_part/ds=2008-04-08/hr=12/key=103/value=val_103} +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(1) from list_bucketing_dynamic_part where ds='2008-04-08' +PREHOOK: type: QUERY +PREHOOK: Input: default@list_bucketing_dynamic_part +PREHOOK: Input: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=11 +PREHOOK: Input: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=12 +#### A masked pattern was here #### +POSTHOOK: query: select count(1) from list_bucketing_dynamic_part where ds='2008-04-08' +POSTHOOK: type: QUERY +POSTHOOK: Input: default@list_bucketing_dynamic_part +POSTHOOK: Input: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=11 +POSTHOOK: Input: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=12 +#### A masked pattern was here #### +1000 +PREHOOK: query: select key, value from srcpart where ds='2008-04-08' and key = "103" and value ="val_103" +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 key, value from srcpart where ds='2008-04-08' and key = "103" and value ="val_103" +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 #### +103 val_103 +103 val_103 +103 val_103 +103 val_103 +PREHOOK: query: explain extended +select key, value, ds, hr from list_bucketing_dynamic_part where ds='2008-04-08' and key = "103" and value ="val_103" +PREHOOK: type: QUERY +POSTHOOK: query: explain extended +select key, value, ds, hr from list_bucketing_dynamic_part where ds='2008-04-08' and key = "103" and value ="val_103" +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.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"} + bucket_count -1 + columns key,value + columns.comments + columns.types string:string +#### A masked pattern was here #### + name default.list_bucketing_dynamic_part + numFiles 3 + numRows 500 + partition_columns ds/hr + partition_columns.types string:string + rawDataSize 5312 + serialization.ddl struct list_bucketing_dynamic_part { 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 + columns.types string:string +#### A masked pattern was here #### + name default.list_bucketing_dynamic_part + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct list_bucketing_dynamic_part { 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.list_bucketing_dynamic_part + name: default.list_bucketing_dynamic_part + Partition + 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"} + bucket_count -1 + columns key,value + columns.comments + columns.types string:string +#### A masked pattern was here #### + name default.list_bucketing_dynamic_part + numFiles 3 + numRows 500 + partition_columns ds/hr + partition_columns.types string:string + rawDataSize 5312 + serialization.ddl struct list_bucketing_dynamic_part { 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 + columns.types string:string +#### A masked pattern was here #### + name default.list_bucketing_dynamic_part + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct list_bucketing_dynamic_part { 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.list_bucketing_dynamic_part + name: default.list_bucketing_dynamic_part + Processor Tree: + TableScan + alias: list_bucketing_dynamic_part + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: ((key = '103') and (value = 'val_103')) (type: boolean) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: '103' (type: string), 'val_103' (type: string), '2008-04-08' (type: string), hr (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + ListSink + +PREHOOK: query: select key, value, ds, hr from list_bucketing_dynamic_part where ds='2008-04-08' and key = "103" and value ="val_103" +PREHOOK: type: QUERY +PREHOOK: Input: default@list_bucketing_dynamic_part +PREHOOK: Input: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=11 +PREHOOK: Input: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=12 +#### A masked pattern was here #### +POSTHOOK: query: select key, value, ds, hr from list_bucketing_dynamic_part where ds='2008-04-08' and key = "103" and value ="val_103" +POSTHOOK: type: QUERY +POSTHOOK: Input: default@list_bucketing_dynamic_part +POSTHOOK: Input: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=11 +POSTHOOK: Input: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=12 +#### A masked pattern was here #### +103 val_103 2008-04-08 11 +103 val_103 2008-04-08 11 +103 val_103 2008-04-08 12 +103 val_103 2008-04-08 12 +PREHOOK: query: -- clean up resources +drop table list_bucketing_dynamic_part +PREHOOK: type: DROPTABLE +PREHOOK: Input: default@list_bucketing_dynamic_part +PREHOOK: Output: default@list_bucketing_dynamic_part +POSTHOOK: query: -- clean up resources +drop table list_bucketing_dynamic_part +POSTHOOK: type: DROPTABLE +POSTHOOK: Input: default@list_bucketing_dynamic_part +POSTHOOK: Output: default@list_bucketing_dynamic_part
http://git-wip-us.apache.org/repos/asf/hive/blob/9687dcc9/ql/src/test/results/clientpositive/list_bucket_dml_6.q.java1.7.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/list_bucket_dml_6.q.java1.7.out b/ql/src/test/results/clientpositive/list_bucket_dml_6.q.java1.7.out deleted file mode 100644 index c022618..0000000 --- a/ql/src/test/results/clientpositive/list_bucket_dml_6.q.java1.7.out +++ /dev/null @@ -1,1007 +0,0 @@ -PREHOOK: query: -- list bucketing DML: dynamic partition. multiple skewed columns. merge. --- The following explains merge example used in this test case --- DML will generated 2 partitions --- ds=2008-04-08/hr=a1 --- ds=2008-04-08/hr=b1 --- without merge, each partition has more files --- ds=2008-04-08/hr=a1 has 2 files --- ds=2008-04-08/hr=b1 has 6 files --- with merge each partition has more files --- ds=2008-04-08/hr=a1 has 1 files --- ds=2008-04-08/hr=b1 has 4 files --- The following shows file size and name in each directory --- hr=a1/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME: --- without merge --- 155 000000_0 --- 155 000001_0 --- with merge --- 254 000000_0 --- hr=b1/key=103/value=val_103: --- without merge --- 99 000000_0 --- 99 000001_0 --- with merge --- 142 000001_0 --- hr=b1/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME: --- without merge --- 5181 000000_0 --- 5181 000001_0 --- with merge --- 5181 000000_0 --- 5181 000001_0 --- hr=b1/key=484/value=val_484 --- without merge --- 87 000000_0 --- 87 000001_0 --- with merge --- 118 000002_0 - --- INCLUDE_HADOOP_MAJOR_VERSIONS(0.23) --- SORT_QUERY_RESULTS --- JAVA_VERSION_SPECIFIC_OUTPUT - --- create a skewed table -create table list_bucketing_dynamic_part (key String, value String) - partitioned by (ds String, hr String) - skewed by (key, value) on (('484','val_484'),('51','val_14'),('103','val_103')) - stored as DIRECTORIES - STORED AS RCFILE -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@list_bucketing_dynamic_part -POSTHOOK: query: -- list bucketing DML: dynamic partition. multiple skewed columns. merge. --- The following explains merge example used in this test case --- DML will generated 2 partitions --- ds=2008-04-08/hr=a1 --- ds=2008-04-08/hr=b1 --- without merge, each partition has more files --- ds=2008-04-08/hr=a1 has 2 files --- ds=2008-04-08/hr=b1 has 6 files --- with merge each partition has more files --- ds=2008-04-08/hr=a1 has 1 files --- ds=2008-04-08/hr=b1 has 4 files --- The following shows file size and name in each directory --- hr=a1/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME: --- without merge --- 155 000000_0 --- 155 000001_0 --- with merge --- 254 000000_0 --- hr=b1/key=103/value=val_103: --- without merge --- 99 000000_0 --- 99 000001_0 --- with merge --- 142 000001_0 --- hr=b1/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME: --- without merge --- 5181 000000_0 --- 5181 000001_0 --- with merge --- 5181 000000_0 --- 5181 000001_0 --- hr=b1/key=484/value=val_484 --- without merge --- 87 000000_0 --- 87 000001_0 --- with merge --- 118 000002_0 - --- INCLUDE_HADOOP_MAJOR_VERSIONS(0.23) --- SORT_QUERY_RESULTS --- JAVA_VERSION_SPECIFIC_OUTPUT - --- create a skewed table -create table list_bucketing_dynamic_part (key String, value String) - partitioned by (ds String, hr String) - skewed by (key, value) on (('484','val_484'),('51','val_14'),('103','val_103')) - stored as DIRECTORIES - STORED AS RCFILE -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@list_bucketing_dynamic_part -PREHOOK: query: -- list bucketing DML without merge. use bucketize to generate a few small files. -explain extended -insert overwrite table list_bucketing_dynamic_part partition (ds = '2008-04-08', hr) -select key, value, if(key % 100 == 0, 'a1', 'b1') 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_dynamic_part partition (ds = '2008-04-08', hr) -select key, value, if(key % 100 == 0, 'a1', 'b1') 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), if(((UDFToDouble(key) % 100.0) = 0.0), 'a1', 'b1') (type: string) - outputColumnNames: _col0, _col1, _col2 - 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/ - 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_dynamic_part - partition_columns ds/hr - partition_columns.types string:string - serialization.ddl struct list_bucketing_dynamic_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_dynamic_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 {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"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 {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"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 - 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_dynamic_part - partition_columns ds/hr - partition_columns.types string:string - serialization.ddl struct list_bucketing_dynamic_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_dynamic_part - - Stage: Stage-2 - Stats-Aggr Operator -#### A masked pattern was here #### - -PREHOOK: query: insert overwrite table list_bucketing_dynamic_part partition (ds = '2008-04-08', hr) -select key, value, if(key % 100 == 0, 'a1', 'b1') 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_dynamic_part@ds=2008-04-08 -POSTHOOK: query: insert overwrite table list_bucketing_dynamic_part partition (ds = '2008-04-08', hr) -select key, value, if(key % 100 == 0, 'a1', 'b1') 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_dynamic_part@ds=2008-04-08/hr=a1 -POSTHOOK: Output: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=b1 -POSTHOOK: Lineage: list_bucketing_dynamic_part PARTITION(ds=2008-04-08,hr=a1).key SIMPLE [(srcpart)srcpart.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: list_bucketing_dynamic_part PARTITION(ds=2008-04-08,hr=a1).value SIMPLE [(srcpart)srcpart.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: list_bucketing_dynamic_part PARTITION(ds=2008-04-08,hr=b1).key SIMPLE [(srcpart)srcpart.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: list_bucketing_dynamic_part PARTITION(ds=2008-04-08,hr=b1).value SIMPLE [(srcpart)srcpart.FieldSchema(name:value, type:string, comment:default), ] -PREHOOK: query: -- check DML result -show partitions list_bucketing_dynamic_part -PREHOOK: type: SHOWPARTITIONS -PREHOOK: Input: default@list_bucketing_dynamic_part -POSTHOOK: query: -- check DML result -show partitions list_bucketing_dynamic_part -POSTHOOK: type: SHOWPARTITIONS -POSTHOOK: Input: default@list_bucketing_dynamic_part -ds=2008-04-08/hr=a1 -ds=2008-04-08/hr=b1 -PREHOOK: query: desc formatted list_bucketing_dynamic_part partition (ds='2008-04-08', hr='a1') -PREHOOK: type: DESCTABLE -PREHOOK: Input: default@list_bucketing_dynamic_part -POSTHOOK: query: desc formatted list_bucketing_dynamic_part partition (ds='2008-04-08', hr='a1') -POSTHOOK: type: DESCTABLE -POSTHOOK: Input: default@list_bucketing_dynamic_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, a1] -Database: default -Table: list_bucketing_dynamic_part -#### A masked pattern was here #### -Partition Parameters: - COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"} - numFiles 2 - numRows 16 - rawDataSize 136 - totalSize 310 -#### 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, value] -Skewed Values: [[484, val_484], [51, val_14], [103, val_103]] -Storage Desc Params: - serialization.format 1 -PREHOOK: query: desc formatted list_bucketing_dynamic_part partition (ds='2008-04-08', hr='b1') -PREHOOK: type: DESCTABLE -PREHOOK: Input: default@list_bucketing_dynamic_part -POSTHOOK: query: desc formatted list_bucketing_dynamic_part partition (ds='2008-04-08', hr='b1') -POSTHOOK: type: DESCTABLE -POSTHOOK: Input: default@list_bucketing_dynamic_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, b1] -Database: default -Table: list_bucketing_dynamic_part -#### A masked pattern was here #### -Partition Parameters: - COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"} - numFiles 6 - numRows 984 - rawDataSize 9488 - totalSize 10734 -#### 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, value] -Skewed Values: [[484, val_484], [51, val_14], [103, val_103]] -#### A masked pattern was here #### -Skewed Value to Truncated Path: {[103, val_103]=/list_bucketing_dynamic_part/ds=2008-04-08/hr=b1/key=103/value=val_103, [484, val_484]=/list_bucketing_dynamic_part/ds=2008-04-08/hr=b1/key=484/value=val_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_dynamic_part partition (ds = '2008-04-08', hr) -select key, value, if(key % 100 == 0, 'a1', 'b1') 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_dynamic_part partition (ds = '2008-04-08', hr) -select key, value, if(key % 100 == 0, 'a1', 'b1') 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), if(((UDFToDouble(key) % 100.0) = 0.0), 'a1', 'b1') (type: string) - outputColumnNames: _col0, _col1, _col2 - 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/ - 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_dynamic_part - partition_columns hr - partition_columns.types string - serialization.ddl struct list_bucketing_dynamic_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_dynamic_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 {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"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 {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"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 - 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_dynamic_part - partition_columns hr - partition_columns.types string - serialization.ddl struct list_bucketing_dynamic_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_dynamic_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_dynamic_part - partition_columns hr - partition_columns.types string - serialization.ddl struct list_bucketing_dynamic_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_dynamic_part - partition_columns hr - partition_columns.types string - serialization.ddl struct list_bucketing_dynamic_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_dynamic_part - name: default.list_bucketing_dynamic_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_dynamic_part - partition_columns hr - partition_columns.types string - serialization.ddl struct list_bucketing_dynamic_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_dynamic_part - partition_columns hr - partition_columns.types string - serialization.ddl struct list_bucketing_dynamic_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_dynamic_part - name: default.list_bucketing_dynamic_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_dynamic_part partition (ds = '2008-04-08', hr) -select key, value, if(key % 100 == 0, 'a1', 'b1') 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_dynamic_part@ds=2008-04-08 -POSTHOOK: query: insert overwrite table list_bucketing_dynamic_part partition (ds = '2008-04-08', hr) -select key, value, if(key % 100 == 0, 'a1', 'b1') 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_dynamic_part@ds=2008-04-08/hr=a1 -POSTHOOK: Output: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=b1 -POSTHOOK: Lineage: list_bucketing_dynamic_part PARTITION(ds=2008-04-08,hr=a1).key SIMPLE [(srcpart)srcpart.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: list_bucketing_dynamic_part PARTITION(ds=2008-04-08,hr=a1).value SIMPLE [(srcpart)srcpart.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: list_bucketing_dynamic_part PARTITION(ds=2008-04-08,hr=b1).key SIMPLE [(srcpart)srcpart.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: list_bucketing_dynamic_part PARTITION(ds=2008-04-08,hr=b1).value SIMPLE [(srcpart)srcpart.FieldSchema(name:value, type:string, comment:default), ] -PREHOOK: query: -- check DML result -show partitions list_bucketing_dynamic_part -PREHOOK: type: SHOWPARTITIONS -PREHOOK: Input: default@list_bucketing_dynamic_part -POSTHOOK: query: -- check DML result -show partitions list_bucketing_dynamic_part -POSTHOOK: type: SHOWPARTITIONS -POSTHOOK: Input: default@list_bucketing_dynamic_part -ds=2008-04-08/hr=a1 -ds=2008-04-08/hr=b1 -PREHOOK: query: desc formatted list_bucketing_dynamic_part partition (ds='2008-04-08', hr='a1') -PREHOOK: type: DESCTABLE -PREHOOK: Input: default@list_bucketing_dynamic_part -POSTHOOK: query: desc formatted list_bucketing_dynamic_part partition (ds='2008-04-08', hr='a1') -POSTHOOK: type: DESCTABLE -POSTHOOK: Input: default@list_bucketing_dynamic_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, a1] -Database: default -Table: list_bucketing_dynamic_part -#### A masked pattern was here #### -Partition Parameters: - COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"} - numFiles 1 - numRows 16 - rawDataSize 136 - totalSize 254 -#### 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, value] -Skewed Values: [[484, val_484], [51, val_14], [103, val_103]] -Storage Desc Params: - serialization.format 1 -PREHOOK: query: desc formatted list_bucketing_dynamic_part partition (ds='2008-04-08', hr='b1') -PREHOOK: type: DESCTABLE -PREHOOK: Input: default@list_bucketing_dynamic_part -POSTHOOK: query: desc formatted list_bucketing_dynamic_part partition (ds='2008-04-08', hr='b1') -POSTHOOK: type: DESCTABLE -POSTHOOK: Input: default@list_bucketing_dynamic_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, b1] -Database: default -Table: list_bucketing_dynamic_part -#### A masked pattern was here #### -Partition Parameters: - COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"} - numFiles 4 - numRows 984 - rawDataSize 9488 - totalSize 10622 -#### 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, value] -Skewed Values: [[484, val_484], [51, val_14], [103, val_103]] -#### A masked pattern was here #### -Skewed Value to Truncated Path: {[103, val_103]=/list_bucketing_dynamic_part/ds=2008-04-08/hr=b1/key=103/value=val_103, [484, val_484]=/list_bucketing_dynamic_part/ds=2008-04-08/hr=b1/key=484/value=val_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_dynamic_part -PREHOOK: type: QUERY -PREHOOK: Input: default@list_bucketing_dynamic_part -PREHOOK: Input: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=a1 -PREHOOK: Input: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=b1 -#### A masked pattern was here #### -POSTHOOK: query: select count(*) from list_bucketing_dynamic_part -POSTHOOK: type: QUERY -POSTHOOK: Input: default@list_bucketing_dynamic_part -POSTHOOK: Input: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=a1 -POSTHOOK: Input: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=b1 -#### A masked pattern was here #### -1000 -PREHOOK: query: explain extended -select * from list_bucketing_dynamic_part where key = '484' and value = 'val_484' -PREHOOK: type: QUERY -POSTHOOK: query: explain extended -select * from list_bucketing_dynamic_part where 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 a1 - 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_dynamic_part - numFiles 1 - numRows 16 - partition_columns ds/hr - partition_columns.types string:string - rawDataSize 136 - serialization.ddl struct list_bucketing_dynamic_part { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe - totalSize 254 -#### 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_dynamic_part - partition_columns ds/hr - partition_columns.types string:string - serialization.ddl struct list_bucketing_dynamic_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_dynamic_part - name: default.list_bucketing_dynamic_part - 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 b1 - 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_dynamic_part - numFiles 4 - numRows 984 - partition_columns ds/hr - partition_columns.types string:string - rawDataSize 9488 - serialization.ddl struct list_bucketing_dynamic_part { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe - totalSize 10622 -#### 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_dynamic_part - partition_columns ds/hr - partition_columns.types string:string - serialization.ddl struct list_bucketing_dynamic_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_dynamic_part - name: default.list_bucketing_dynamic_part - Processor Tree: - TableScan - alias: list_bucketing_dynamic_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), ds (type: string), hr (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_dynamic_part where key = '484' and value = 'val_484' -PREHOOK: type: QUERY -PREHOOK: Input: default@list_bucketing_dynamic_part -PREHOOK: Input: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=a1 -PREHOOK: Input: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=b1 -#### A masked pattern was here #### -POSTHOOK: query: select * from list_bucketing_dynamic_part where key = '484' and value = 'val_484' -POSTHOOK: type: QUERY -POSTHOOK: Input: default@list_bucketing_dynamic_part -POSTHOOK: Input: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=a1 -POSTHOOK: Input: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=b1 -#### A masked pattern was here #### -484 val_484 2008-04-08 b1 -484 val_484 2008-04-08 b1 -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_dynamic_part -PREHOOK: type: DROPTABLE -PREHOOK: Input: default@list_bucketing_dynamic_part -PREHOOK: Output: default@list_bucketing_dynamic_part -POSTHOOK: query: -- clean up -drop table list_bucketing_dynamic_part -POSTHOOK: type: DROPTABLE -POSTHOOK: Input: default@list_bucketing_dynamic_part -POSTHOOK: Output: default@list_bucketing_dynamic_part
