You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by px...@apache.org on 2015/08/14 08:16:49 UTC
[5/7] hive git commit: backport HIVE-9560: When
hive.stats.collect.rawdatasize=true, 'rawDataSize' for an ORC table will
result in value '0' after running 'analyze table TABLE_NAME compute
statistics; ' (Prasanth Jayachandran reviewed by Ashutosh Chauhan)
http://git-wip-us.apache.org/repos/asf/hive/blob/9eb95813/ql/src/test/results/clientpositive/tez/orc_analyze.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/tez/orc_analyze.q.out b/ql/src/test/results/clientpositive/tez/orc_analyze.q.out
index b422db5..858da6c 100644
--- a/ql/src/test/results/clientpositive/tez/orc_analyze.q.out
+++ b/ql/src/test/results/clientpositive/tez/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/vector_char_simple.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/tez/vector_char_simple.q.out b/ql/src/test/results/clientpositive/tez/vector_char_simple.q.out
index fe651ca..9c72edb 100644
--- a/ql/src/test/results/clientpositive/tez/vector_char_simple.q.out
+++ b/ql/src/test/results/clientpositive/tez/vector_char_simple.q.out
@@ -271,17 +271,17 @@ 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: cint (type: int)
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
Limit
Number of rows: 10
- Statistics: Num rows: 10 Data size: 300 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 2150 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
sort order:
- Statistics: Num rows: 10 Data size: 300 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 2150 Basic stats: COMPLETE Column stats: NONE
value expressions: _col0 (type: int)
Execution mode: vectorized
Reducer 2
@@ -289,17 +289,17 @@ STAGE PLANS:
Select Operator
expressions: VALUE._col0 (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 10 Data size: 300 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 2150 Basic stats: COMPLETE Column stats: NONE
Limit
Number of rows: 10
- Statistics: Num rows: 10 Data size: 300 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 2150 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: CAST( _col0 AS CHAR(12) (type: char(12))
outputColumnNames: _col0
- Statistics: Num rows: 10 Data size: 300 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 2150 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 10 Data size: 300 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 2150 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/9eb95813/ql/src/test/results/clientpositive/tez/vector_left_outer_join.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/tez/vector_left_outer_join.q.out b/ql/src/test/results/clientpositive/tez/vector_left_outer_join.q.out
index 71367c4..eabc438 100644
--- a/ql/src/test/results/clientpositive/tez/vector_left_outer_join.q.out
+++ b/ql/src/test/results/clientpositive/tez/vector_left_outer_join.q.out
@@ -32,18 +32,18 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: hd
- 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: ctinyint (type: tinyint)
sort order: +
Map-reduce partition columns: ctinyint (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
Execution mode: vectorized
Map 2
Map Operator Tree:
TableScan
alias: c
- 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
Map Join Operator
condition map:
Left Outer Join0 to 1
@@ -56,7 +56,7 @@ STAGE PLANS:
outputColumnNames: _col0
input vertices:
1 Map 4
- Statistics: Num rows: 13516 Data size: 414960 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 13516 Data size: 2906160 Basic stats: COMPLETE Column stats: NONE
Map Join Operator
condition map:
Left Outer Join0 to 1
@@ -68,9 +68,9 @@ STAGE PLANS:
1 ctinyint (type: tinyint)
input vertices:
1 Map 1
- Statistics: Num rows: 14867 Data size: 456456 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 14867 Data size: 3196776 Basic stats: COMPLETE Column stats: NONE
Select Operator
- Statistics: Num rows: 14867 Data size: 456456 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 14867 Data size: 3196776 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count()
mode: hash
@@ -85,12 +85,12 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: cd
- 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: cint (type: int)
sort order: +
Map-reduce partition columns: cint (type: int)
- 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
Execution mode: vectorized
Reducer 3
Reduce Operator Tree:
http://git-wip-us.apache.org/repos/asf/hive/blob/9eb95813/ql/src/test/results/clientpositive/tez/vector_varchar_simple.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/tez/vector_varchar_simple.q.out b/ql/src/test/results/clientpositive/tez/vector_varchar_simple.q.out
index f3d9147..e90eefa 100644
--- a/ql/src/test/results/clientpositive/tez/vector_varchar_simple.q.out
+++ b/ql/src/test/results/clientpositive/tez/vector_varchar_simple.q.out
@@ -271,17 +271,17 @@ 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: cint (type: int)
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
Limit
Number of rows: 10
- Statistics: Num rows: 10 Data size: 300 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 2150 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
sort order:
- Statistics: Num rows: 10 Data size: 300 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 2150 Basic stats: COMPLETE Column stats: NONE
value expressions: _col0 (type: int)
Execution mode: vectorized
Reducer 2
@@ -289,17 +289,17 @@ STAGE PLANS:
Select Operator
expressions: VALUE._col0 (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 10 Data size: 300 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 2150 Basic stats: COMPLETE Column stats: NONE
Limit
Number of rows: 10
- Statistics: Num rows: 10 Data size: 300 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 2150 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: CAST( _col0 AS varchar(25)) (type: varchar(25))
outputColumnNames: _col0
- Statistics: Num rows: 10 Data size: 300 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 2150 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 10 Data size: 300 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 2150 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/9eb95813/ql/src/test/results/clientpositive/tez/vectorization_0.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/tez/vectorization_0.q.out b/ql/src/test/results/clientpositive/tez/vectorization_0.q.out
index 7703158..ac72ed3 100644
--- a/ql/src/test/results/clientpositive/tez/vectorization_0.q.out
+++ b/ql/src/test/results/clientpositive/tez/vectorization_0.q.out
@@ -32,11 +32,11 @@ 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)
outputColumnNames: ctinyint
- 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: min(ctinyint), max(ctinyint), count(ctinyint), count()
mode: hash
@@ -130,11 +130,11 @@ 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)
outputColumnNames: ctinyint
- 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: sum(ctinyint)
mode: hash
@@ -237,11 +237,11 @@ 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)
outputColumnNames: ctinyint
- 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: avg(ctinyint), variance(ctinyint), var_pop(ctinyint), var_samp(ctinyint), std(ctinyint), stddev(ctinyint), stddev_pop(ctinyint), stddev_samp(ctinyint)
mode: hash
@@ -350,11 +350,11 @@ 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: cbigint (type: bigint)
outputColumnNames: cbigint
- 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: min(cbigint), max(cbigint), count(cbigint), count()
mode: hash
@@ -448,11 +448,11 @@ 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: cbigint (type: bigint)
outputColumnNames: cbigint
- 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: sum(cbigint)
mode: hash
@@ -555,11 +555,11 @@ 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: cbigint (type: bigint)
outputColumnNames: cbigint
- 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: avg(cbigint), variance(cbigint), var_pop(cbigint), var_samp(cbigint), std(cbigint), stddev(cbigint), stddev_pop(cbigint), stddev_samp(cbigint)
mode: hash
@@ -668,11 +668,11 @@ 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: cfloat (type: float)
outputColumnNames: cfloat
- 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: min(cfloat), max(cfloat), count(cfloat), count()
mode: hash
@@ -766,11 +766,11 @@ 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: cfloat (type: float)
outputColumnNames: cfloat
- 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: sum(cfloat)
mode: hash
@@ -873,11 +873,11 @@ 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: cfloat (type: float)
outputColumnNames: cfloat
- 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: avg(cfloat), variance(cfloat), var_pop(cfloat), var_samp(cfloat), std(cfloat), stddev(cfloat), stddev_pop(cfloat), stddev_samp(cfloat)
mode: hash
@@ -1024,14 +1024,14 @@ 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
Filter Operator
predicate: ((cstring2 like '%b%') or ((79.553 <> cint) or (cbigint < cdouble))) (type: boolean)
- 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: cbigint (type: bigint), cfloat (type: float), ctinyint (type: tinyint)
outputColumnNames: cbigint, cfloat, ctinyint
- 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: avg(cbigint), stddev_pop(cbigint), var_samp(cbigint), count(), sum(cfloat), min(ctinyint)
mode: hash
http://git-wip-us.apache.org/repos/asf/hive/blob/9eb95813/ql/src/test/results/clientpositive/tez/vectorization_13.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/tez/vectorization_13.q.out b/ql/src/test/results/clientpositive/tez/vectorization_13.q.out
index 3410c33..b014163 100644
--- a/ql/src/test/results/clientpositive/tez/vectorization_13.q.out
+++ b/ql/src/test/results/clientpositive/tez/vectorization_13.q.out
@@ -77,25 +77,25 @@ 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
Filter Operator
predicate: (((cfloat < 3569.0) and ((10.175 >= cdouble) and (cboolean1 <> 1))) or ((ctimestamp1 > 11) and ((ctimestamp2 <> 12) and (ctinyint < 9763215.5639)))) (type: boolean)
- Statistics: Num rows: 2730 Data size: 83809 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2730 Data size: 586959 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: cboolean1 (type: boolean), ctinyint (type: tinyint), ctimestamp1 (type: timestamp), cfloat (type: float), cstring1 (type: string)
outputColumnNames: cboolean1, ctinyint, ctimestamp1, cfloat, cstring1
- Statistics: Num rows: 2730 Data size: 83809 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2730 Data size: 586959 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: max(ctinyint), sum(cfloat), stddev_pop(cfloat), stddev_pop(ctinyint), max(cfloat), min(ctinyint)
keys: cboolean1 (type: boolean), ctinyint (type: tinyint), ctimestamp1 (type: timestamp), cfloat (type: float), cstring1 (type: string)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10
- Statistics: Num rows: 2730 Data size: 83809 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2730 Data size: 586959 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string)
sort order: +++++
Map-reduce partition columns: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string)
- Statistics: Num rows: 2730 Data size: 83809 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2730 Data size: 586959 Basic stats: COMPLETE Column stats: NONE
value expressions: _col5 (type: tinyint), _col6 (type: double), _col7 (type: struct<count:bigint,sum:double,variance:double>), _col8 (type: struct<count:bigint,sum:double,variance:double>), _col9 (type: float), _col10 (type: tinyint)
Execution mode: vectorized
Reducer 2
@@ -105,17 +105,17 @@ STAGE PLANS:
keys: KEY._col0 (type: boolean), KEY._col1 (type: tinyint), KEY._col2 (type: timestamp), KEY._col3 (type: float), KEY._col4 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10
- Statistics: Num rows: 1365 Data size: 41904 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string), (- _col1) (type: tinyint), _col5 (type: tinyint), ((- _col1) + _col5) (type: tinyint), _col6 (type: double), (_col6 * ((- _col1) + _col5)) (type: double), (- _col6) (type: double), (79.553 * _col3) (type: double), _col7 (type: double), (- _col6) (type: double), _col8 (type: double), (((- _col1) + _col5) - 10.175) (type: double), (- (- _col6)) (type: double), (-26.28 / (- (- _col6))) (type: double), _col9 (type: float), ((_col6 * ((- _col1) + _col5)) / _col1) (type: double), _col10 (type: tinyint)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20
- Statistics: Num rows: 1365 Data size: 41904 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE
Limit
Number of rows: 40
- Statistics: Num rows: 40 Data size: 1200 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 40 Data size: 8600 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 40 Data size: 1200 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 40 Data size: 8600 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -314,25 +314,25 @@ 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
Filter Operator
predicate: (((cfloat < 3569.0) and ((10.175 >= cdouble) and (cboolean1 <> 1))) or ((ctimestamp1 > -1.388) and ((ctimestamp2 <> -1.3359999999999999) and (ctinyint < 9763215.5639)))) (type: boolean)
- Statistics: Num rows: 2730 Data size: 83809 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2730 Data size: 586959 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: cboolean1 (type: boolean), ctinyint (type: tinyint), ctimestamp1 (type: timestamp), cfloat (type: float), cstring1 (type: string)
outputColumnNames: cboolean1, ctinyint, ctimestamp1, cfloat, cstring1
- Statistics: Num rows: 2730 Data size: 83809 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2730 Data size: 586959 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: max(ctinyint), sum(cfloat), stddev_pop(cfloat), stddev_pop(ctinyint), max(cfloat), min(ctinyint)
keys: cboolean1 (type: boolean), ctinyint (type: tinyint), ctimestamp1 (type: timestamp), cfloat (type: float), cstring1 (type: string)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10
- Statistics: Num rows: 2730 Data size: 83809 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2730 Data size: 586959 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string)
sort order: +++++
Map-reduce partition columns: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string)
- Statistics: Num rows: 2730 Data size: 83809 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2730 Data size: 586959 Basic stats: COMPLETE Column stats: NONE
value expressions: _col5 (type: tinyint), _col6 (type: double), _col7 (type: struct<count:bigint,sum:double,variance:double>), _col8 (type: struct<count:bigint,sum:double,variance:double>), _col9 (type: float), _col10 (type: tinyint)
Execution mode: vectorized
Reducer 2
@@ -342,17 +342,17 @@ STAGE PLANS:
keys: KEY._col0 (type: boolean), KEY._col1 (type: tinyint), KEY._col2 (type: timestamp), KEY._col3 (type: float), KEY._col4 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10
- Statistics: Num rows: 1365 Data size: 41904 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string), (- _col1) (type: tinyint), _col5 (type: tinyint), ((- _col1) + _col5) (type: tinyint), _col6 (type: double), (_col6 * ((- _col1) + _col5)) (type: double), (- _col6) (type: double), (79.553 * _col3) (type: double), _col7 (type: double), (- _col6) (type: double), _col8 (type: double), (((- _col1) + _col5) - 10.175) (type: double), (- (- _col6)) (type: double), (-26.28 / (- (- _col6))) (type: double), _col9 (type: float), ((_col6 * ((- _col1) + _col5)) / _col1) (type: double), _col10 (type: tinyint)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20
- Statistics: Num rows: 1365 Data size: 41904 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE
Limit
Number of rows: 40
- Statistics: Num rows: 40 Data size: 1200 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 40 Data size: 8600 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 40 Data size: 1200 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 40 Data size: 8600 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat