http://git-wip-us.apache.org/repos/asf/hive/blob/9eb95813/ql/src/test/results/clientpositive/orc_analyze.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/orc_analyze.q.out b/ql/src/test/results/clientpositive/orc_analyze.q.out index b422db5..858da6c 100644 --- a/ql/src/test/results/clientpositive/orc_analyze.q.out +++ b/ql/src/test/results/clientpositive/orc_analyze.q.out @@ -71,6 +71,55 @@ POSTHOOK: Lineage: orc_create_people.last_name SIMPLE [(orc_create_people_stagin POSTHOOK: Lineage: orc_create_people.salary SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:salary, type:decimal(10,0), comment:null), ] POSTHOOK: Lineage: orc_create_people.start_date SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:start_date, type:timestamp, comment:null), ] POSTHOOK: Lineage: orc_create_people.state SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:state, type:string, comment:null), ] +PREHOOK: query: analyze table orc_create_people compute statistics +PREHOOK: type: QUERY +PREHOOK: Input: default@orc_create_people +PREHOOK: Output: default@orc_create_people +POSTHOOK: query: analyze table orc_create_people compute statistics +POSTHOOK: type: QUERY +POSTHOOK: Input: default@orc_create_people +POSTHOOK: Output: default@orc_create_people +PREHOOK: query: desc formatted orc_create_people +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@orc_create_people +POSTHOOK: query: desc formatted orc_create_people +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@orc_create_people +# col_name data_type comment + +id int +first_name string +last_name string +address string +salary decimal(10,0) +start_date timestamp +state string + +# Detailed Table Information +Database: default +#### A masked pattern was here #### +Protect Mode: None +Retention: 0 +#### A masked pattern was here #### +Table Type: MANAGED_TABLE +Table Parameters: + COLUMN_STATS_ACCURATE true + numFiles 1 + numRows 100 + rawDataSize 52600 + totalSize 3158 +#### A masked pattern was here #### + +# Storage Information +SerDe Library: org.apache.hadoop.hive.ql.io.orc.OrcSerde +InputFormat: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat +OutputFormat: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat +Compressed: No +Num Buckets: -1 +Bucket Columns: [] +Sort Columns: [] +Storage Desc Params: + serialization.format 1 PREHOOK: query: analyze table orc_create_people compute statistics partialscan PREHOOK: type: QUERY PREHOOK: Input: default@orc_create_people @@ -120,6 +169,55 @@ Bucket Columns: [] Sort Columns: [] Storage Desc Params: serialization.format 1 +PREHOOK: query: analyze table orc_create_people compute statistics noscan +PREHOOK: type: QUERY +PREHOOK: Input: default@orc_create_people +PREHOOK: Output: default@orc_create_people +POSTHOOK: query: analyze table orc_create_people compute statistics noscan +POSTHOOK: type: QUERY +POSTHOOK: Input: default@orc_create_people +POSTHOOK: Output: default@orc_create_people +PREHOOK: query: desc formatted orc_create_people +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@orc_create_people +POSTHOOK: query: desc formatted orc_create_people +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@orc_create_people +# col_name data_type comment + +id int +first_name string +last_name string +address string +salary decimal(10,0) +start_date timestamp +state string + +# Detailed Table Information +Database: default +#### A masked pattern was here #### +Protect Mode: None +Retention: 0 +#### A masked pattern was here #### +Table Type: MANAGED_TABLE +Table Parameters: + COLUMN_STATS_ACCURATE true + numFiles 1 + numRows 100 + rawDataSize 52600 + totalSize 3158 +#### A masked pattern was here #### + +# Storage Information +SerDe Library: org.apache.hadoop.hive.ql.io.orc.OrcSerde +InputFormat: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat +OutputFormat: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat +Compressed: No +Num Buckets: -1 +Bucket Columns: [] +Sort Columns: [] +Storage Desc Params: + serialization.format 1 PREHOOK: query: drop table orc_create_people PREHOOK: type: DROPTABLE PREHOOK: Input: default@orc_create_people @@ -269,13 +367,13 @@ POSTHOOK: Lineage: orc_create_people PARTITION(state=Or).id SIMPLE [(orc_create_ POSTHOOK: Lineage: orc_create_people PARTITION(state=Or).last_name SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:last_name, type:string, comment:null), ] POSTHOOK: Lineage: orc_create_people PARTITION(state=Or).salary SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:salary, type:decimal(10,0), comment:null), ] POSTHOOK: Lineage: orc_create_people PARTITION(state=Or).start_date SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:start_date, type:timestamp, comment:null), ] -PREHOOK: query: analyze table orc_create_people partition(state) compute statistics partialscan +PREHOOK: query: analyze table orc_create_people partition(state) compute statistics PREHOOK: type: QUERY PREHOOK: Input: default@orc_create_people PREHOOK: Output: default@orc_create_people PREHOOK: Output: default@orc_create_people@state=Ca PREHOOK: Output: default@orc_create_people@state=Or -POSTHOOK: query: analyze table orc_create_people partition(state) compute statistics partialscan +POSTHOOK: query: analyze table orc_create_people partition(state) compute statistics POSTHOOK: type: QUERY POSTHOOK: Input: default@orc_create_people POSTHOOK: Output: default@orc_create_people @@ -371,63 +469,18 @@ Bucket Columns: [] Sort Columns: [] Storage Desc Params: serialization.format 1 -PREHOOK: query: drop table orc_create_people -PREHOOK: type: DROPTABLE +PREHOOK: query: analyze table orc_create_people partition(state) compute statistics partialscan +PREHOOK: type: QUERY PREHOOK: Input: default@orc_create_people PREHOOK: Output: default@orc_create_people -POSTHOOK: query: drop table orc_create_people -POSTHOOK: type: DROPTABLE +PREHOOK: Output: default@orc_create_people@state=Ca +PREHOOK: Output: default@orc_create_people@state=Or +POSTHOOK: query: analyze table orc_create_people partition(state) compute statistics partialscan +POSTHOOK: type: QUERY POSTHOOK: Input: default@orc_create_people POSTHOOK: Output: default@orc_create_people -PREHOOK: query: -- auto stats gather -CREATE TABLE orc_create_people ( - id int, - first_name string, - last_name string, - address string, - salary decimal, - start_date timestamp) -PARTITIONED BY (state string) -STORED AS orc -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@orc_create_people -POSTHOOK: query: -- auto stats gather -CREATE TABLE orc_create_people ( - id int, - first_name string, - last_name string, - address string, - salary decimal, - start_date timestamp) -PARTITIONED BY (state string) -STORED AS orc -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@orc_create_people -PREHOOK: query: INSERT OVERWRITE TABLE orc_create_people PARTITION (state) - SELECT * FROM orc_create_people_staging ORDER BY id -PREHOOK: type: QUERY -PREHOOK: Input: default@orc_create_people_staging -PREHOOK: Output: default@orc_create_people -POSTHOOK: query: INSERT OVERWRITE TABLE orc_create_people PARTITION (state) - SELECT * FROM orc_create_people_staging ORDER BY id -POSTHOOK: type: QUERY -POSTHOOK: Input: default@orc_create_people_staging POSTHOOK: Output: default@orc_create_people@state=Ca POSTHOOK: Output: default@orc_create_people@state=Or -POSTHOOK: Lineage: orc_create_people PARTITION(state=Ca).address SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:address, type:string, comment:null), ] -POSTHOOK: Lineage: orc_create_people PARTITION(state=Ca).first_name SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:first_name, type:string, comment:null), ] -POSTHOOK: Lineage: orc_create_people PARTITION(state=Ca).id SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:id, type:int, comment:null), ] -POSTHOOK: Lineage: orc_create_people PARTITION(state=Ca).last_name SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:last_name, type:string, comment:null), ] -POSTHOOK: Lineage: orc_create_people PARTITION(state=Ca).salary SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:salary, type:decimal(10,0), comment:null), ] -POSTHOOK: Lineage: orc_create_people PARTITION(state=Ca).start_date SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:start_date, type:timestamp, comment:null), ] -POSTHOOK: Lineage: orc_create_people PARTITION(state=Or).address SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:address, type:string, comment:null), ] -POSTHOOK: Lineage: orc_create_people PARTITION(state=Or).first_name SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:first_name, type:string, comment:null), ] -POSTHOOK: Lineage: orc_create_people PARTITION(state=Or).id SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:id, type:int, comment:null), ] -POSTHOOK: Lineage: orc_create_people PARTITION(state=Or).last_name SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:last_name, type:string, comment:null), ] -POSTHOOK: Lineage: orc_create_people PARTITION(state=Or).salary SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:salary, type:decimal(10,0), comment:null), ] -POSTHOOK: Lineage: orc_create_people PARTITION(state=Or).start_date SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:start_date, type:timestamp, comment:null), ] PREHOOK: query: desc formatted orc_create_people partition(state="Ca") PREHOOK: type: DESCTABLE PREHOOK: Input: default@orc_create_people @@ -518,78 +571,13 @@ Bucket Columns: [] Sort Columns: [] Storage Desc Params: serialization.format 1 -PREHOOK: query: drop table orc_create_people -PREHOOK: type: DROPTABLE -PREHOOK: Input: default@orc_create_people -PREHOOK: Output: default@orc_create_people -POSTHOOK: query: drop table orc_create_people -POSTHOOK: type: DROPTABLE -POSTHOOK: Input: default@orc_create_people -POSTHOOK: Output: default@orc_create_people -PREHOOK: query: -- partitioned and bucketed table --- partial scan gather -CREATE TABLE orc_create_people ( - id int, - first_name string, - last_name string, - address string, - salary decimal, - start_date timestamp) -PARTITIONED BY (state string) -clustered by (first_name) -sorted by (last_name) -into 4 buckets -STORED AS orc -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@orc_create_people -POSTHOOK: query: -- partitioned and bucketed table --- partial scan gather -CREATE TABLE orc_create_people ( - id int, - first_name string, - last_name string, - address string, - salary decimal, - start_date timestamp) -PARTITIONED BY (state string) -clustered by (first_name) -sorted by (last_name) -into 4 buckets -STORED AS orc -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@orc_create_people -PREHOOK: query: INSERT OVERWRITE TABLE orc_create_people PARTITION (state) - SELECT * FROM orc_create_people_staging ORDER BY id -PREHOOK: type: QUERY -PREHOOK: Input: default@orc_create_people_staging -PREHOOK: Output: default@orc_create_people -POSTHOOK: query: INSERT OVERWRITE TABLE orc_create_people PARTITION (state) - SELECT * FROM orc_create_people_staging ORDER BY id -POSTHOOK: type: QUERY -POSTHOOK: Input: default@orc_create_people_staging -POSTHOOK: Output: default@orc_create_people@state=Ca -POSTHOOK: Output: default@orc_create_people@state=Or -POSTHOOK: Lineage: orc_create_people PARTITION(state=Ca).address SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:address, type:string, comment:null), ] -POSTHOOK: Lineage: orc_create_people PARTITION(state=Ca).first_name SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:first_name, type:string, comment:null), ] -POSTHOOK: Lineage: orc_create_people PARTITION(state=Ca).id SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:id, type:int, comment:null), ] -POSTHOOK: Lineage: orc_create_people PARTITION(state=Ca).last_name SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:last_name, type:string, comment:null), ] -POSTHOOK: Lineage: orc_create_people PARTITION(state=Ca).salary SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:salary, type:decimal(10,0), comment:null), ] -POSTHOOK: Lineage: orc_create_people PARTITION(state=Ca).start_date SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:start_date, type:timestamp, comment:null), ] -POSTHOOK: Lineage: orc_create_people PARTITION(state=Or).address SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:address, type:string, comment:null), ] -POSTHOOK: Lineage: orc_create_people PARTITION(state=Or).first_name SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:first_name, type:string, comment:null), ] -POSTHOOK: Lineage: orc_create_people PARTITION(state=Or).id SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:id, type:int, comment:null), ] -POSTHOOK: Lineage: orc_create_people PARTITION(state=Or).last_name SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:last_name, type:string, comment:null), ] -POSTHOOK: Lineage: orc_create_people PARTITION(state=Or).salary SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:salary, type:decimal(10,0), comment:null), ] -POSTHOOK: Lineage: orc_create_people PARTITION(state=Or).start_date SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:start_date, type:timestamp, comment:null), ] -PREHOOK: query: analyze table orc_create_people partition(state) compute statistics partialscan +PREHOOK: query: analyze table orc_create_people partition(state) compute statistics noscan PREHOOK: type: QUERY PREHOOK: Input: default@orc_create_people PREHOOK: Output: default@orc_create_people PREHOOK: Output: default@orc_create_people@state=Ca PREHOOK: Output: default@orc_create_people@state=Or -POSTHOOK: query: analyze table orc_create_people partition(state) compute statistics partialscan +POSTHOOK: query: analyze table orc_create_people partition(state) compute statistics noscan POSTHOOK: type: QUERY POSTHOOK: Input: default@orc_create_people POSTHOOK: Output: default@orc_create_people @@ -635,9 +623,9 @@ SerDe Library: org.apache.hadoop.hive.ql.io.orc.OrcSerde InputFormat: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat OutputFormat: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat Compressed: No -Num Buckets: 4 -Bucket Columns: [first_name] -Sort Columns: [Order(col:last_name, order:1)] +Num Buckets: -1 +Bucket Columns: [] +Sort Columns: [] Storage Desc Params: serialization.format 1 PREHOOK: query: desc formatted orc_create_people partition(state="Or") @@ -680,9 +668,9 @@ SerDe Library: org.apache.hadoop.hive.ql.io.orc.OrcSerde InputFormat: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat OutputFormat: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat Compressed: No -Num Buckets: 4 -Bucket Columns: [first_name] -Sort Columns: [Order(col:last_name, order:1)] +Num Buckets: -1 +Bucket Columns: [] +Sort Columns: [] Storage Desc Params: serialization.format 1 PREHOOK: query: drop table orc_create_people @@ -702,9 +690,6 @@ CREATE TABLE orc_create_people ( salary decimal, start_date timestamp) PARTITIONED BY (state string) -clustered by (first_name) -sorted by (last_name) -into 4 buckets STORED AS orc PREHOOK: type: CREATETABLE PREHOOK: Output: database:default @@ -718,9 +703,6 @@ CREATE TABLE orc_create_people ( salary decimal, start_date timestamp) PARTITIONED BY (state string) -clustered by (first_name) -sorted by (last_name) -into 4 buckets STORED AS orc POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default @@ -788,9 +770,9 @@ SerDe Library: org.apache.hadoop.hive.ql.io.orc.OrcSerde InputFormat: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat OutputFormat: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat Compressed: No -Num Buckets: 4 -Bucket Columns: [first_name] -Sort Columns: [Order(col:last_name, order:1)] +Num Buckets: -1 +Bucket Columns: [] +Sort Columns: [] Storage Desc Params: serialization.format 1 PREHOOK: query: desc formatted orc_create_people partition(state="Or") @@ -833,9 +815,9 @@ SerDe Library: org.apache.hadoop.hive.ql.io.orc.OrcSerde InputFormat: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat OutputFormat: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat Compressed: No -Num Buckets: 4 -Bucket Columns: [first_name] -Sort Columns: [Order(col:last_name, order:1)] +Num Buckets: -1 +Bucket Columns: [] +Sort Columns: [] Storage Desc Params: serialization.format 1 PREHOOK: query: drop table orc_create_people @@ -846,9 +828,8 @@ POSTHOOK: query: drop table orc_create_people POSTHOOK: type: DROPTABLE POSTHOOK: Input: default@orc_create_people POSTHOOK: Output: default@orc_create_people -PREHOOK: query: -- create table with partitions containing text and ORC files. --- ORC files implements StatsProvidingRecordReader but text files does not. --- So the partition containing text file should not have statistics. +PREHOOK: query: -- partitioned and bucketed table +-- partial scan gather CREATE TABLE orc_create_people ( id int, first_name string, @@ -857,7 +838,532 @@ CREATE TABLE orc_create_people ( salary decimal, start_date timestamp) PARTITIONED BY (state string) -STORED AS orc +clustered by (first_name) +sorted by (last_name) +into 4 buckets +STORED AS orc +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@orc_create_people +POSTHOOK: query: -- partitioned and bucketed table +-- partial scan gather +CREATE TABLE orc_create_people ( + id int, + first_name string, + last_name string, + address string, + salary decimal, + start_date timestamp) +PARTITIONED BY (state string) +clustered by (first_name) +sorted by (last_name) +into 4 buckets +STORED AS orc +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@orc_create_people +PREHOOK: query: INSERT OVERWRITE TABLE orc_create_people PARTITION (state) + SELECT * FROM orc_create_people_staging ORDER BY id +PREHOOK: type: QUERY +PREHOOK: Input: default@orc_create_people_staging +PREHOOK: Output: default@orc_create_people +POSTHOOK: query: INSERT OVERWRITE TABLE orc_create_people PARTITION (state) + SELECT * FROM orc_create_people_staging ORDER BY id +POSTHOOK: type: QUERY +POSTHOOK: Input: default@orc_create_people_staging +POSTHOOK: Output: default@orc_create_people@state=Ca +POSTHOOK: Output: default@orc_create_people@state=Or +POSTHOOK: Lineage: orc_create_people PARTITION(state=Ca).address SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:address, type:string, comment:null), ] +POSTHOOK: Lineage: orc_create_people PARTITION(state=Ca).first_name SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:first_name, type:string, comment:null), ] +POSTHOOK: Lineage: orc_create_people PARTITION(state=Ca).id SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:id, type:int, comment:null), ] +POSTHOOK: Lineage: orc_create_people PARTITION(state=Ca).last_name SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:last_name, type:string, comment:null), ] +POSTHOOK: Lineage: orc_create_people PARTITION(state=Ca).salary SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:salary, type:decimal(10,0), comment:null), ] +POSTHOOK: Lineage: orc_create_people PARTITION(state=Ca).start_date SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:start_date, type:timestamp, comment:null), ] +POSTHOOK: Lineage: orc_create_people PARTITION(state=Or).address SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:address, type:string, comment:null), ] +POSTHOOK: Lineage: orc_create_people PARTITION(state=Or).first_name SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:first_name, type:string, comment:null), ] +POSTHOOK: Lineage: orc_create_people PARTITION(state=Or).id SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:id, type:int, comment:null), ] +POSTHOOK: Lineage: orc_create_people PARTITION(state=Or).last_name SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:last_name, type:string, comment:null), ] +POSTHOOK: Lineage: orc_create_people PARTITION(state=Or).salary SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:salary, type:decimal(10,0), comment:null), ] +POSTHOOK: Lineage: orc_create_people PARTITION(state=Or).start_date SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:start_date, type:timestamp, comment:null), ] +PREHOOK: query: analyze table orc_create_people partition(state) compute statistics +PREHOOK: type: QUERY +PREHOOK: Input: default@orc_create_people +PREHOOK: Output: default@orc_create_people +PREHOOK: Output: default@orc_create_people@state=Ca +PREHOOK: Output: default@orc_create_people@state=Or +POSTHOOK: query: analyze table orc_create_people partition(state) compute statistics +POSTHOOK: type: QUERY +POSTHOOK: Input: default@orc_create_people +POSTHOOK: Output: default@orc_create_people +POSTHOOK: Output: default@orc_create_people@state=Ca +POSTHOOK: Output: default@orc_create_people@state=Or +PREHOOK: query: desc formatted orc_create_people partition(state="Ca") +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@orc_create_people +POSTHOOK: query: desc formatted orc_create_people partition(state="Ca") +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@orc_create_people +# col_name data_type comment + +id int +first_name string +last_name string +address string +salary decimal(10,0) +start_date timestamp + +# Partition Information +# col_name data_type comment + +state string + +# Detailed Partition Information +Partition Value: [Ca] +Database: default +Table: orc_create_people +#### A masked pattern was here #### +Protect Mode: None +#### A masked pattern was here #### +Partition Parameters: + COLUMN_STATS_ACCURATE true + numFiles 1 + numRows 50 + rawDataSize 21950 + totalSize 2055 +#### A masked pattern was here #### + +# Storage Information +SerDe Library: org.apache.hadoop.hive.ql.io.orc.OrcSerde +InputFormat: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat +OutputFormat: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat +Compressed: No +Num Buckets: 4 +Bucket Columns: [first_name] +Sort Columns: [Order(col:last_name, order:1)] +Storage Desc Params: + serialization.format 1 +PREHOOK: query: desc formatted orc_create_people partition(state="Or") +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@orc_create_people +POSTHOOK: query: desc formatted orc_create_people partition(state="Or") +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@orc_create_people +# col_name data_type comment + +id int +first_name string +last_name string +address string +salary decimal(10,0) +start_date timestamp + +# Partition Information +# col_name data_type comment + +state string + +# Detailed Partition Information +Partition Value: [Or] +Database: default +Table: orc_create_people +#### A masked pattern was here #### +Protect Mode: None +#### A masked pattern was here #### +Partition Parameters: + COLUMN_STATS_ACCURATE true + numFiles 1 + numRows 50 + rawDataSize 22050 + totalSize 2071 +#### A masked pattern was here #### + +# Storage Information +SerDe Library: org.apache.hadoop.hive.ql.io.orc.OrcSerde +InputFormat: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat +OutputFormat: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat +Compressed: No +Num Buckets: 4 +Bucket Columns: [first_name] +Sort Columns: [Order(col:last_name, order:1)] +Storage Desc Params: + serialization.format 1 +PREHOOK: query: analyze table orc_create_people partition(state) compute statistics partialscan +PREHOOK: type: QUERY +PREHOOK: Input: default@orc_create_people +PREHOOK: Output: default@orc_create_people +PREHOOK: Output: default@orc_create_people@state=Ca +PREHOOK: Output: default@orc_create_people@state=Or +POSTHOOK: query: analyze table orc_create_people partition(state) compute statistics partialscan +POSTHOOK: type: QUERY +POSTHOOK: Input: default@orc_create_people +POSTHOOK: Output: default@orc_create_people +POSTHOOK: Output: default@orc_create_people@state=Ca +POSTHOOK: Output: default@orc_create_people@state=Or +PREHOOK: query: desc formatted orc_create_people partition(state="Ca") +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@orc_create_people +POSTHOOK: query: desc formatted orc_create_people partition(state="Ca") +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@orc_create_people +# col_name data_type comment + +id int +first_name string +last_name string +address string +salary decimal(10,0) +start_date timestamp + +# Partition Information +# col_name data_type comment + +state string + +# Detailed Partition Information +Partition Value: [Ca] +Database: default +Table: orc_create_people +#### A masked pattern was here #### +Protect Mode: None +#### A masked pattern was here #### +Partition Parameters: + COLUMN_STATS_ACCURATE true + numFiles 1 + numRows 50 + rawDataSize 21950 + totalSize 2055 +#### A masked pattern was here #### + +# Storage Information +SerDe Library: org.apache.hadoop.hive.ql.io.orc.OrcSerde +InputFormat: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat +OutputFormat: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat +Compressed: No +Num Buckets: 4 +Bucket Columns: [first_name] +Sort Columns: [Order(col:last_name, order:1)] +Storage Desc Params: + serialization.format 1 +PREHOOK: query: desc formatted orc_create_people partition(state="Or") +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@orc_create_people +POSTHOOK: query: desc formatted orc_create_people partition(state="Or") +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@orc_create_people +# col_name data_type comment + +id int +first_name string +last_name string +address string +salary decimal(10,0) +start_date timestamp + +# Partition Information +# col_name data_type comment + +state string + +# Detailed Partition Information +Partition Value: [Or] +Database: default +Table: orc_create_people +#### A masked pattern was here #### +Protect Mode: None +#### A masked pattern was here #### +Partition Parameters: + COLUMN_STATS_ACCURATE true + numFiles 1 + numRows 50 + rawDataSize 22050 + totalSize 2071 +#### A masked pattern was here #### + +# Storage Information +SerDe Library: org.apache.hadoop.hive.ql.io.orc.OrcSerde +InputFormat: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat +OutputFormat: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat +Compressed: No +Num Buckets: 4 +Bucket Columns: [first_name] +Sort Columns: [Order(col:last_name, order:1)] +Storage Desc Params: + serialization.format 1 +PREHOOK: query: analyze table orc_create_people partition(state) compute statistics noscan +PREHOOK: type: QUERY +PREHOOK: Input: default@orc_create_people +PREHOOK: Output: default@orc_create_people +PREHOOK: Output: default@orc_create_people@state=Ca +PREHOOK: Output: default@orc_create_people@state=Or +POSTHOOK: query: analyze table orc_create_people partition(state) compute statistics noscan +POSTHOOK: type: QUERY +POSTHOOK: Input: default@orc_create_people +POSTHOOK: Output: default@orc_create_people +POSTHOOK: Output: default@orc_create_people@state=Ca +POSTHOOK: Output: default@orc_create_people@state=Or +PREHOOK: query: desc formatted orc_create_people partition(state="Ca") +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@orc_create_people +POSTHOOK: query: desc formatted orc_create_people partition(state="Ca") +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@orc_create_people +# col_name data_type comment + +id int +first_name string +last_name string +address string +salary decimal(10,0) +start_date timestamp + +# Partition Information +# col_name data_type comment + +state string + +# Detailed Partition Information +Partition Value: [Ca] +Database: default +Table: orc_create_people +#### A masked pattern was here #### +Protect Mode: None +#### A masked pattern was here #### +Partition Parameters: + COLUMN_STATS_ACCURATE true + numFiles 1 + numRows 50 + rawDataSize 21950 + totalSize 2055 +#### A masked pattern was here #### + +# Storage Information +SerDe Library: org.apache.hadoop.hive.ql.io.orc.OrcSerde +InputFormat: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat +OutputFormat: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat +Compressed: No +Num Buckets: 4 +Bucket Columns: [first_name] +Sort Columns: [Order(col:last_name, order:1)] +Storage Desc Params: + serialization.format 1 +PREHOOK: query: desc formatted orc_create_people partition(state="Or") +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@orc_create_people +POSTHOOK: query: desc formatted orc_create_people partition(state="Or") +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@orc_create_people +# col_name data_type comment + +id int +first_name string +last_name string +address string +salary decimal(10,0) +start_date timestamp + +# Partition Information +# col_name data_type comment + +state string + +# Detailed Partition Information +Partition Value: [Or] +Database: default +Table: orc_create_people +#### A masked pattern was here #### +Protect Mode: None +#### A masked pattern was here #### +Partition Parameters: + COLUMN_STATS_ACCURATE true + numFiles 1 + numRows 50 + rawDataSize 22050 + totalSize 2071 +#### A masked pattern was here #### + +# Storage Information +SerDe Library: org.apache.hadoop.hive.ql.io.orc.OrcSerde +InputFormat: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat +OutputFormat: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat +Compressed: No +Num Buckets: 4 +Bucket Columns: [first_name] +Sort Columns: [Order(col:last_name, order:1)] +Storage Desc Params: + serialization.format 1 +PREHOOK: query: drop table orc_create_people +PREHOOK: type: DROPTABLE +PREHOOK: Input: default@orc_create_people +PREHOOK: Output: default@orc_create_people +POSTHOOK: query: drop table orc_create_people +POSTHOOK: type: DROPTABLE +POSTHOOK: Input: default@orc_create_people +POSTHOOK: Output: default@orc_create_people +PREHOOK: query: -- auto stats gather +CREATE TABLE orc_create_people ( + id int, + first_name string, + last_name string, + address string, + salary decimal, + start_date timestamp) +PARTITIONED BY (state string) +clustered by (first_name) +sorted by (last_name) +into 4 buckets +STORED AS orc +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@orc_create_people +POSTHOOK: query: -- auto stats gather +CREATE TABLE orc_create_people ( + id int, + first_name string, + last_name string, + address string, + salary decimal, + start_date timestamp) +PARTITIONED BY (state string) +clustered by (first_name) +sorted by (last_name) +into 4 buckets +STORED AS orc +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@orc_create_people +PREHOOK: query: INSERT OVERWRITE TABLE orc_create_people PARTITION (state) + SELECT * FROM orc_create_people_staging ORDER BY id +PREHOOK: type: QUERY +PREHOOK: Input: default@orc_create_people_staging +PREHOOK: Output: default@orc_create_people +POSTHOOK: query: INSERT OVERWRITE TABLE orc_create_people PARTITION (state) + SELECT * FROM orc_create_people_staging ORDER BY id +POSTHOOK: type: QUERY +POSTHOOK: Input: default@orc_create_people_staging +POSTHOOK: Output: default@orc_create_people@state=Ca +POSTHOOK: Output: default@orc_create_people@state=Or +POSTHOOK: Lineage: orc_create_people PARTITION(state=Ca).address SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:address, type:string, comment:null), ] +POSTHOOK: Lineage: orc_create_people PARTITION(state=Ca).first_name SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:first_name, type:string, comment:null), ] +POSTHOOK: Lineage: orc_create_people PARTITION(state=Ca).id SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:id, type:int, comment:null), ] +POSTHOOK: Lineage: orc_create_people PARTITION(state=Ca).last_name SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:last_name, type:string, comment:null), ] +POSTHOOK: Lineage: orc_create_people PARTITION(state=Ca).salary SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:salary, type:decimal(10,0), comment:null), ] +POSTHOOK: Lineage: orc_create_people PARTITION(state=Ca).start_date SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:start_date, type:timestamp, comment:null), ] +POSTHOOK: Lineage: orc_create_people PARTITION(state=Or).address SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:address, type:string, comment:null), ] +POSTHOOK: Lineage: orc_create_people PARTITION(state=Or).first_name SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:first_name, type:string, comment:null), ] +POSTHOOK: Lineage: orc_create_people PARTITION(state=Or).id SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:id, type:int, comment:null), ] +POSTHOOK: Lineage: orc_create_people PARTITION(state=Or).last_name SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:last_name, type:string, comment:null), ] +POSTHOOK: Lineage: orc_create_people PARTITION(state=Or).salary SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:salary, type:decimal(10,0), comment:null), ] +POSTHOOK: Lineage: orc_create_people PARTITION(state=Or).start_date SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:start_date, type:timestamp, comment:null), ] +PREHOOK: query: desc formatted orc_create_people partition(state="Ca") +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@orc_create_people +POSTHOOK: query: desc formatted orc_create_people partition(state="Ca") +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@orc_create_people +# col_name data_type comment + +id int +first_name string +last_name string +address string +salary decimal(10,0) +start_date timestamp + +# Partition Information +# col_name data_type comment + +state string + +# Detailed Partition Information +Partition Value: [Ca] +Database: default +Table: orc_create_people +#### A masked pattern was here #### +Protect Mode: None +#### A masked pattern was here #### +Partition Parameters: + COLUMN_STATS_ACCURATE true + numFiles 1 + numRows 50 + rawDataSize 21950 + totalSize 2055 +#### A masked pattern was here #### + +# Storage Information +SerDe Library: org.apache.hadoop.hive.ql.io.orc.OrcSerde +InputFormat: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat +OutputFormat: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat +Compressed: No +Num Buckets: 4 +Bucket Columns: [first_name] +Sort Columns: [Order(col:last_name, order:1)] +Storage Desc Params: + serialization.format 1 +PREHOOK: query: desc formatted orc_create_people partition(state="Or") +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@orc_create_people +POSTHOOK: query: desc formatted orc_create_people partition(state="Or") +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@orc_create_people +# col_name data_type comment + +id int +first_name string +last_name string +address string +salary decimal(10,0) +start_date timestamp + +# Partition Information +# col_name data_type comment + +state string + +# Detailed Partition Information +Partition Value: [Or] +Database: default +Table: orc_create_people +#### A masked pattern was here #### +Protect Mode: None +#### A masked pattern was here #### +Partition Parameters: + COLUMN_STATS_ACCURATE true + numFiles 1 + numRows 50 + rawDataSize 22050 + totalSize 2071 +#### A masked pattern was here #### + +# Storage Information +SerDe Library: org.apache.hadoop.hive.ql.io.orc.OrcSerde +InputFormat: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat +OutputFormat: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat +Compressed: No +Num Buckets: 4 +Bucket Columns: [first_name] +Sort Columns: [Order(col:last_name, order:1)] +Storage Desc Params: + serialization.format 1 +PREHOOK: query: drop table orc_create_people +PREHOOK: type: DROPTABLE +PREHOOK: Input: default@orc_create_people +PREHOOK: Output: default@orc_create_people +POSTHOOK: query: drop table orc_create_people +POSTHOOK: type: DROPTABLE +POSTHOOK: Input: default@orc_create_people +POSTHOOK: Output: default@orc_create_people +PREHOOK: query: -- create table with partitions containing text and ORC files. +-- ORC files implements StatsProvidingRecordReader but text files does not. +-- So the partition containing text file should not have statistics. +CREATE TABLE orc_create_people ( + id int, + first_name string, + last_name string, + address string, + salary decimal, + start_date timestamp) +PARTITIONED BY (state string) +STORED AS orc PREHOOK: type: CREATETABLE PREHOOK: Output: database:default PREHOOK: Output: default@orc_create_people @@ -946,6 +1452,214 @@ POSTHOOK: query: ALTER TABLE orc_create_people SET FILEFORMAT ORC POSTHOOK: type: ALTERTABLE_FILEFORMAT POSTHOOK: Input: default@orc_create_people POSTHOOK: Output: default@orc_create_people +PREHOOK: query: analyze table orc_create_people partition(state) compute statistics +PREHOOK: type: QUERY +PREHOOK: Input: default@orc_create_people +PREHOOK: Output: default@orc_create_people +PREHOOK: Output: default@orc_create_people@state=Ca +PREHOOK: Output: default@orc_create_people@state=OH +PREHOOK: Output: default@orc_create_people@state=Or +POSTHOOK: query: analyze table orc_create_people partition(state) compute statistics +POSTHOOK: type: QUERY +POSTHOOK: Input: default@orc_create_people +POSTHOOK: Output: default@orc_create_people +POSTHOOK: Output: default@orc_create_people@state=Ca +POSTHOOK: Output: default@orc_create_people@state=OH +POSTHOOK: Output: default@orc_create_people@state=Or +PREHOOK: query: desc formatted orc_create_people partition(state="Ca") +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@orc_create_people +POSTHOOK: query: desc formatted orc_create_people partition(state="Ca") +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@orc_create_people +# col_name data_type comment + +id int +first_name string +last_name string +address string +salary decimal(10,0) +start_date timestamp + +# Partition Information +# col_name data_type comment + +state string + +# Detailed Partition Information +Partition Value: [Ca] +Database: default +Table: orc_create_people +#### A masked pattern was here #### +Protect Mode: None +#### A masked pattern was here #### +Partition Parameters: + COLUMN_STATS_ACCURATE true + numFiles 1 + numRows 50 + rawDataSize 21950 + totalSize 2055 +#### A masked pattern was here #### + +# Storage Information +SerDe Library: org.apache.hadoop.hive.ql.io.orc.OrcSerde +InputFormat: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat +OutputFormat: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat +Compressed: No +Num Buckets: -1 +Bucket Columns: [] +Sort Columns: [] +Storage Desc Params: + serialization.format 1 +PREHOOK: query: desc formatted orc_create_people partition(state="OH") +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@orc_create_people +POSTHOOK: query: desc formatted orc_create_people partition(state="OH") +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@orc_create_people +# col_name data_type comment + +id int +first_name string +last_name string +address string +salary decimal(10,0) +start_date timestamp + +# Partition Information +# col_name data_type comment + +state string + +# Detailed Partition Information +Partition Value: [OH] +Database: default +Table: orc_create_people +#### A masked pattern was here #### +Protect Mode: None +#### A masked pattern was here #### +Partition Parameters: + COLUMN_STATS_ACCURATE false + numFiles 1 + numRows -1 + rawDataSize -1 + 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.IgnoreKeyTextOutputFormat +Compressed: No +Num Buckets: -1 +Bucket Columns: [] +Sort Columns: [] +Storage Desc Params: + serialization.format 1 +PREHOOK: query: analyze table orc_create_people partition(state) compute statistics partialscan +PREHOOK: type: QUERY +PREHOOK: Input: default@orc_create_people +PREHOOK: Output: default@orc_create_people +PREHOOK: Output: default@orc_create_people@state=Ca +PREHOOK: Output: default@orc_create_people@state=OH +PREHOOK: Output: default@orc_create_people@state=Or +POSTHOOK: query: analyze table orc_create_people partition(state) compute statistics partialscan +POSTHOOK: type: QUERY +POSTHOOK: Input: default@orc_create_people +POSTHOOK: Output: default@orc_create_people +POSTHOOK: Output: default@orc_create_people@state=Ca +POSTHOOK: Output: default@orc_create_people@state=OH +POSTHOOK: Output: default@orc_create_people@state=Or +PREHOOK: query: desc formatted orc_create_people partition(state="Ca") +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@orc_create_people +POSTHOOK: query: desc formatted orc_create_people partition(state="Ca") +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@orc_create_people +# col_name data_type comment + +id int +first_name string +last_name string +address string +salary decimal(10,0) +start_date timestamp + +# Partition Information +# col_name data_type comment + +state string + +# Detailed Partition Information +Partition Value: [Ca] +Database: default +Table: orc_create_people +#### A masked pattern was here #### +Protect Mode: None +#### A masked pattern was here #### +Partition Parameters: + COLUMN_STATS_ACCURATE true + numFiles 1 + numRows 50 + rawDataSize 21950 + totalSize 2055 +#### A masked pattern was here #### + +# Storage Information +SerDe Library: org.apache.hadoop.hive.ql.io.orc.OrcSerde +InputFormat: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat +OutputFormat: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat +Compressed: No +Num Buckets: -1 +Bucket Columns: [] +Sort Columns: [] +Storage Desc Params: + serialization.format 1 +PREHOOK: query: desc formatted orc_create_people partition(state="OH") +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@orc_create_people +POSTHOOK: query: desc formatted orc_create_people partition(state="OH") +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@orc_create_people +# col_name data_type comment + +id int +first_name string +last_name string +address string +salary decimal(10,0) +start_date timestamp + +# Partition Information +# col_name data_type comment + +state string + +# Detailed Partition Information +Partition Value: [OH] +Database: default +Table: orc_create_people +#### A masked pattern was here #### +Protect Mode: None +#### A masked pattern was here #### +Partition Parameters: + COLUMN_STATS_ACCURATE false + numFiles 1 + numRows -1 + rawDataSize -1 + 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.IgnoreKeyTextOutputFormat +Compressed: No +Num Buckets: -1 +Bucket Columns: [] +Sort Columns: [] +Storage Desc Params: + serialization.format 1 PREHOOK: query: analyze table orc_create_people partition(state) compute statistics noscan PREHOOK: type: QUERY PREHOOK: Input: default@orc_create_people
http://git-wip-us.apache.org/repos/asf/hive/blob/9eb95813/ql/src/test/results/clientpositive/tez/limit_pushdown.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/tez/limit_pushdown.q.out b/ql/src/test/results/clientpositive/tez/limit_pushdown.q.out index c765ab7..af47427 100644 --- a/ql/src/test/results/clientpositive/tez/limit_pushdown.q.out +++ b/ql/src/test/results/clientpositive/tez/limit_pushdown.q.out @@ -389,21 +389,21 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cdouble (type: double) outputColumnNames: cdouble - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: cdouble (type: double) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: double) sort order: + Map-reduce partition columns: _col0 (type: double) - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.3 Reducer 2 Reduce Operator Tree: @@ -411,17 +411,17 @@ STAGE PLANS: keys: KEY._col0 (type: double) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: double) outputColumnNames: _col0 - Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 20 - Statistics: Num rows: 20 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -482,22 +482,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), cdouble (type: double) outputColumnNames: ctinyint, cdouble - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(DISTINCT cdouble) keys: ctinyint (type: tinyint), cdouble (type: double) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: tinyint), _col1 (type: double) sort order: ++ Map-reduce partition columns: _col0 (type: tinyint) - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.3 Reducer 2 Reduce Operator Tree: @@ -506,17 +506,17 @@ STAGE PLANS: keys: KEY._col0 (type: tinyint) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: tinyint), _col1 (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 20 - Statistics: Num rows: 20 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -579,22 +579,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), cstring1 (type: string), cstring2 (type: string) outputColumnNames: ctinyint, cstring1, cstring2 - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(DISTINCT cstring1), count(DISTINCT cstring2) keys: ctinyint (type: tinyint), cstring1 (type: string), cstring2 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: tinyint), _col1 (type: string), _col2 (type: string) sort order: +++ Map-reduce partition columns: _col0 (type: tinyint) - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.3 Reducer 2 Reduce Operator Tree: @@ -603,17 +603,17 @@ STAGE PLANS: keys: KEY._col0 (type: tinyint) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: tinyint), _col1 (type: bigint), _col2 (type: bigint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 20 - Statistics: Num rows: 20 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat