http://git-wip-us.apache.org/repos/asf/hive/blob/5f01dc42/ql/src/test/results/clientpositive/llap/orc_analyze.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/orc_analyze.q.out b/ql/src/test/results/clientpositive/llap/orc_analyze.q.out index 6eb9a93..87855fa 100644 --- a/ql/src/test/results/clientpositive/llap/orc_analyze.q.out +++ b/ql/src/test/results/clientpositive/llap/orc_analyze.q.out @@ -102,11 +102,11 @@ Retention: 0 #### A masked pattern was here #### Table Type: MANAGED_TABLE Table Parameters: - COLUMN_STATS_ACCURATE true + COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"} numFiles 1 numRows 100 rawDataSize 52600 - totalSize 3174 + totalSize 3202 #### A masked pattern was here #### # Storage Information @@ -150,11 +150,11 @@ Retention: 0 #### A masked pattern was here #### Table Type: MANAGED_TABLE Table Parameters: - COLUMN_STATS_ACCURATE true + COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"} numFiles 1 numRows 100 rawDataSize 52600 - totalSize 3174 + totalSize 3202 #### A masked pattern was here #### # Storage Information @@ -198,11 +198,11 @@ Retention: 0 #### A masked pattern was here #### Table Type: MANAGED_TABLE Table Parameters: - COLUMN_STATS_ACCURATE true + COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"} numFiles 1 numRows 100 rawDataSize 52600 - totalSize 3174 + totalSize 3202 #### A masked pattern was here #### # Storage Information @@ -287,11 +287,11 @@ Retention: 0 #### A masked pattern was here #### Table Type: MANAGED_TABLE Table Parameters: - COLUMN_STATS_ACCURATE true + COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"} numFiles 1 numRows 100 rawDataSize 52600 - totalSize 3174 + totalSize 3202 #### A masked pattern was here #### # Storage Information @@ -401,11 +401,11 @@ Database: default Table: orc_create_people #### A masked pattern was here #### Partition Parameters: - COLUMN_STATS_ACCURATE true + COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"} numFiles 1 numRows 50 rawDataSize 21950 - totalSize 2073 + totalSize 2102 #### A masked pattern was here #### # Storage Information @@ -444,11 +444,11 @@ Database: default Table: orc_create_people #### A masked pattern was here #### Partition Parameters: - COLUMN_STATS_ACCURATE true + COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"} numFiles 1 numRows 50 rawDataSize 22050 - totalSize 2088 + totalSize 2118 #### A masked pattern was here #### # Storage Information @@ -499,11 +499,11 @@ Database: default Table: orc_create_people #### A masked pattern was here #### Partition Parameters: - COLUMN_STATS_ACCURATE true + COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"} numFiles 1 numRows 50 rawDataSize 21950 - totalSize 2073 + totalSize 2102 #### A masked pattern was here #### # Storage Information @@ -542,11 +542,11 @@ Database: default Table: orc_create_people #### A masked pattern was here #### Partition Parameters: - COLUMN_STATS_ACCURATE true + COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"} numFiles 1 numRows 50 rawDataSize 22050 - totalSize 2088 + totalSize 2118 #### A masked pattern was here #### # Storage Information @@ -597,11 +597,11 @@ Database: default Table: orc_create_people #### A masked pattern was here #### Partition Parameters: - COLUMN_STATS_ACCURATE true + COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"} numFiles 1 numRows 50 rawDataSize 21950 - totalSize 2073 + totalSize 2102 #### A masked pattern was here #### # Storage Information @@ -640,11 +640,11 @@ Database: default Table: orc_create_people #### A masked pattern was here #### Partition Parameters: - COLUMN_STATS_ACCURATE true + COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"} numFiles 1 numRows 50 rawDataSize 22050 - totalSize 2088 + totalSize 2118 #### A masked pattern was here #### # Storage Information @@ -740,11 +740,11 @@ Database: default Table: orc_create_people #### A masked pattern was here #### Partition Parameters: - COLUMN_STATS_ACCURATE true + COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"} numFiles 1 numRows 50 rawDataSize 21950 - totalSize 2073 + totalSize 2102 #### A masked pattern was here #### # Storage Information @@ -783,11 +783,11 @@ Database: default Table: orc_create_people #### A masked pattern was here #### Partition Parameters: - COLUMN_STATS_ACCURATE true + COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"} numFiles 1 numRows 50 rawDataSize 22050 - totalSize 2088 + totalSize 2118 #### A masked pattern was here #### # Storage Information @@ -903,11 +903,11 @@ Database: default Table: orc_create_people #### A masked pattern was here #### Partition Parameters: - COLUMN_STATS_ACCURATE true - numFiles 1 + COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"} + numFiles 4 numRows 50 - rawDataSize 21950 - totalSize 2073 + rawDataSize 21975 + totalSize 5263 #### A masked pattern was here #### # Storage Information @@ -946,11 +946,11 @@ Database: default Table: orc_create_people #### A masked pattern was here #### Partition Parameters: - COLUMN_STATS_ACCURATE true - numFiles 1 + COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"} + numFiles 4 numRows 50 - rawDataSize 22050 - totalSize 2088 + rawDataSize 22043 + totalSize 5336 #### A masked pattern was here #### # Storage Information @@ -1001,11 +1001,11 @@ Database: default Table: orc_create_people #### A masked pattern was here #### Partition Parameters: - COLUMN_STATS_ACCURATE true - numFiles 1 + COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"} + numFiles 4 numRows 50 - rawDataSize 21950 - totalSize 2073 + rawDataSize 21975 + totalSize 5263 #### A masked pattern was here #### # Storage Information @@ -1044,11 +1044,11 @@ Database: default Table: orc_create_people #### A masked pattern was here #### Partition Parameters: - COLUMN_STATS_ACCURATE true - numFiles 1 + COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"} + numFiles 4 numRows 50 - rawDataSize 22050 - totalSize 2088 + rawDataSize 22043 + totalSize 5336 #### A masked pattern was here #### # Storage Information @@ -1099,11 +1099,11 @@ Database: default Table: orc_create_people #### A masked pattern was here #### Partition Parameters: - COLUMN_STATS_ACCURATE true - numFiles 1 + COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"} + numFiles 4 numRows 50 - rawDataSize 21950 - totalSize 2073 + rawDataSize 21975 + totalSize 5263 #### A masked pattern was here #### # Storage Information @@ -1142,11 +1142,11 @@ Database: default Table: orc_create_people #### A masked pattern was here #### Partition Parameters: - COLUMN_STATS_ACCURATE true - numFiles 1 + COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"} + numFiles 4 numRows 50 - rawDataSize 22050 - totalSize 2088 + rawDataSize 22043 + totalSize 5336 #### A masked pattern was here #### # Storage Information @@ -1248,11 +1248,11 @@ Database: default Table: orc_create_people #### A masked pattern was here #### Partition Parameters: - COLUMN_STATS_ACCURATE true - numFiles 1 + COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"} + numFiles 4 numRows 50 - rawDataSize 21950 - totalSize 2073 + rawDataSize 21975 + totalSize 5263 #### A masked pattern was here #### # Storage Information @@ -1291,11 +1291,11 @@ Database: default Table: orc_create_people #### A masked pattern was here #### Partition Parameters: - COLUMN_STATS_ACCURATE true - numFiles 1 + COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"} + numFiles 4 numRows 50 - rawDataSize 22050 - totalSize 2088 + rawDataSize 22043 + totalSize 5336 #### A masked pattern was here #### # Storage Information @@ -1369,66 +1369,17 @@ 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: -- set the table to text format -ALTER TABLE orc_create_people SET SERDE 'org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe' -PREHOOK: type: ALTERTABLE_SERIALIZER -PREHOOK: Input: default@orc_create_people -PREHOOK: Output: default@orc_create_people -POSTHOOK: query: -- set the table to text format -ALTER TABLE orc_create_people SET SERDE 'org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe' -POSTHOOK: type: ALTERTABLE_SERIALIZER -POSTHOOK: Input: default@orc_create_people -POSTHOOK: Output: default@orc_create_people -PREHOOK: query: ALTER TABLE orc_create_people SET FILEFORMAT TEXTFILE -PREHOOK: type: ALTERTABLE_FILEFORMAT -PREHOOK: Input: default@orc_create_people -PREHOOK: Output: default@orc_create_people -POSTHOOK: query: ALTER TABLE orc_create_people SET FILEFORMAT TEXTFILE -POSTHOOK: type: ALTERTABLE_FILEFORMAT -POSTHOOK: Input: default@orc_create_people -POSTHOOK: Output: default@orc_create_people -PREHOOK: query: -- load the text data into a new partition -LOAD DATA LOCAL INPATH '../../data/files/kv1.txt' OVERWRITE INTO TABLE orc_create_people PARTITION(state="OH") -PREHOOK: type: LOAD -#### A masked pattern was here #### -PREHOOK: Output: default@orc_create_people -POSTHOOK: query: -- load the text data into a new partition -LOAD DATA LOCAL INPATH '../../data/files/kv1.txt' OVERWRITE INTO TABLE orc_create_people PARTITION(state="OH") -POSTHOOK: type: LOAD -#### A masked pattern was here #### -POSTHOOK: Output: default@orc_create_people -POSTHOOK: Output: default@orc_create_people@state=OH -PREHOOK: query: -- set the table back to orc -ALTER TABLE orc_create_people SET SERDE 'org.apache.hadoop.hive.ql.io.orc.OrcSerde' -PREHOOK: type: ALTERTABLE_SERIALIZER -PREHOOK: Input: default@orc_create_people -PREHOOK: Output: default@orc_create_people -POSTHOOK: query: -- set the table back to orc -ALTER TABLE orc_create_people SET SERDE 'org.apache.hadoop.hive.ql.io.orc.OrcSerde' -POSTHOOK: type: ALTERTABLE_SERIALIZER -POSTHOOK: Input: default@orc_create_people -POSTHOOK: Output: default@orc_create_people -PREHOOK: query: ALTER TABLE orc_create_people SET FILEFORMAT ORC -PREHOOK: type: ALTERTABLE_FILEFORMAT -PREHOOK: Input: default@orc_create_people -PREHOOK: Output: default@orc_create_people -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 @@ -1456,11 +1407,11 @@ Database: default Table: orc_create_people #### A masked pattern was here #### Partition Parameters: - COLUMN_STATS_ACCURATE true + COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"} numFiles 1 numRows 50 rawDataSize 21950 - totalSize 2073 + totalSize 2102 #### A masked pattern was here #### # Storage Information @@ -1473,62 +1424,17 @@ 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 #### -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 @@ -1556,11 +1462,11 @@ Database: default Table: orc_create_people #### A masked pattern was here #### Partition Parameters: - COLUMN_STATS_ACCURATE true + COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"} numFiles 1 numRows 50 rawDataSize 21950 - totalSize 2073 + totalSize 2102 #### A masked pattern was here #### # Storage Information @@ -1573,62 +1479,17 @@ 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 #### -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 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 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=OH POSTHOOK: Output: default@orc_create_people@state=Or PREHOOK: query: desc formatted orc_create_people partition(state="Ca") PREHOOK: type: DESCTABLE @@ -1656,11 +1517,11 @@ Database: default Table: orc_create_people #### A masked pattern was here #### Partition Parameters: - COLUMN_STATS_ACCURATE true + COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"} numFiles 1 numRows 50 rawDataSize 21950 - totalSize 2073 + totalSize 2102 #### A masked pattern was here #### # Storage Information @@ -1673,49 +1534,6 @@ 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 #### -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: drop table orc_create_people PREHOOK: type: DROPTABLE PREHOOK: Input: default@orc_create_people
http://git-wip-us.apache.org/repos/asf/hive/blob/5f01dc42/ql/src/test/results/clientpositive/llap/orc_merge1.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/orc_merge1.q.out b/ql/src/test/results/clientpositive/llap/orc_merge1.q.out index 241fb05..973d5a1 100644 --- a/ql/src/test/results/clientpositive/llap/orc_merge1.q.out +++ b/ql/src/test/results/clientpositive/llap/orc_merge1.q.out @@ -71,20 +71,21 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(key) (type: int), value (type: string), (hash(key) pmod 2) (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 49500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 49500 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde name: default.orcfile_merge1 Execution mode: llap + LLAP IO: no inputs Stage: Stage-2 Dependency Collection @@ -156,20 +157,21 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(key) (type: int), value (type: string), (hash(key) pmod 2) (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 49500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 49500 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde name: default.orcfile_merge1b Execution mode: llap + LLAP IO: no inputs Stage: Stage-8 Conditional Operator @@ -286,20 +288,21 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(key) (type: int), value (type: string), (hash(key) pmod 2) (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 49500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 49500 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde name: default.orcfile_merge1c Execution mode: llap + LLAP IO: no inputs Stage: Stage-8 Conditional Operator http://git-wip-us.apache.org/repos/asf/hive/blob/5f01dc42/ql/src/test/results/clientpositive/llap/orc_merge10.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/orc_merge10.q.out b/ql/src/test/results/clientpositive/llap/orc_merge10.q.out new file mode 100644 index 0000000..164edda --- /dev/null +++ b/ql/src/test/results/clientpositive/llap/orc_merge10.q.out @@ -0,0 +1,743 @@ +PREHOOK: query: -- SORT_QUERY_RESULTS + +DROP TABLE orcfile_merge1 +PREHOOK: type: DROPTABLE +POSTHOOK: query: -- SORT_QUERY_RESULTS + +DROP TABLE orcfile_merge1 +POSTHOOK: type: DROPTABLE +PREHOOK: query: DROP TABLE orcfile_merge1b +PREHOOK: type: DROPTABLE +POSTHOOK: query: DROP TABLE orcfile_merge1b +POSTHOOK: type: DROPTABLE +PREHOOK: query: DROP TABLE orcfile_merge1c +PREHOOK: type: DROPTABLE +POSTHOOK: query: DROP TABLE orcfile_merge1c +POSTHOOK: type: DROPTABLE +PREHOOK: query: CREATE TABLE orcfile_merge1 (key INT, value STRING) + PARTITIONED BY (ds STRING, part STRING) STORED AS ORC tblproperties("orc.compress"="SNAPPY","orc.compress.size"="4096") +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@orcfile_merge1 +POSTHOOK: query: CREATE TABLE orcfile_merge1 (key INT, value STRING) + PARTITIONED BY (ds STRING, part STRING) STORED AS ORC tblproperties("orc.compress"="SNAPPY","orc.compress.size"="4096") +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@orcfile_merge1 +PREHOOK: query: CREATE TABLE orcfile_merge1b (key INT, value STRING) + PARTITIONED BY (ds STRING, part STRING) STORED AS ORC tblproperties("orc.compress"="SNAPPY","orc.compress.size"="4096") +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@orcfile_merge1b +POSTHOOK: query: CREATE TABLE orcfile_merge1b (key INT, value STRING) + PARTITIONED BY (ds STRING, part STRING) STORED AS ORC tblproperties("orc.compress"="SNAPPY","orc.compress.size"="4096") +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@orcfile_merge1b +PREHOOK: query: CREATE TABLE orcfile_merge1c (key INT, value STRING) + PARTITIONED BY (ds STRING, part STRING) STORED AS ORC tblproperties("orc.compress"="SNAPPY","orc.compress.size"="4096") +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@orcfile_merge1c +POSTHOOK: query: CREATE TABLE orcfile_merge1c (key INT, value STRING) + PARTITIONED BY (ds STRING, part STRING) STORED AS ORC tblproperties("orc.compress"="SNAPPY","orc.compress.size"="4096") +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@orcfile_merge1c +PREHOOK: query: -- merge disabled +EXPLAIN + INSERT OVERWRITE TABLE orcfile_merge1 PARTITION (ds='1', part) + SELECT key, value, PMOD(HASH(key), 2) as part + FROM src +PREHOOK: type: QUERY +POSTHOOK: query: -- merge disabled +EXPLAIN + INSERT OVERWRITE TABLE orcfile_merge1 PARTITION (ds='1', part) + SELECT key, value, PMOD(HASH(key), 2) as part + FROM src +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-2 depends on stages: Stage-1 + Stage-0 depends on stages: Stage-2 + Stage-3 depends on stages: Stage-0 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: UDFToInteger(key) (type: int), value (type: string), (hash(key) pmod 2) (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 500 Data size: 49500 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 500 Data size: 49500 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.orcfile_merge1 + Execution mode: llap + LLAP IO: no inputs + + Stage: Stage-2 + Dependency Collection + + Stage: Stage-0 + Move Operator + tables: + partition: + ds 1 + part + replace: true + table: + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.orcfile_merge1 + + Stage: Stage-3 + Stats-Aggr Operator + +PREHOOK: query: INSERT OVERWRITE TABLE orcfile_merge1 PARTITION (ds='1', part) + SELECT key, value, PMOD(HASH(key), 2) as part + FROM src +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: default@orcfile_merge1@ds=1 +POSTHOOK: query: INSERT OVERWRITE TABLE orcfile_merge1 PARTITION (ds='1', part) + SELECT key, value, PMOD(HASH(key), 2) as part + FROM src +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Output: default@orcfile_merge1@ds=1/part=0 +POSTHOOK: Output: default@orcfile_merge1@ds=1/part=1 +POSTHOOK: Lineage: orcfile_merge1 PARTITION(ds=1,part=0).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: orcfile_merge1 PARTITION(ds=1,part=0).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: orcfile_merge1 PARTITION(ds=1,part=1).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: orcfile_merge1 PARTITION(ds=1,part=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] +Found 3 items +#### A masked pattern was here #### +PREHOOK: query: -- auto-merge slow way +EXPLAIN + INSERT OVERWRITE TABLE orcfile_merge1b PARTITION (ds='1', part) + SELECT key, value, PMOD(HASH(key), 2) as part + FROM src +PREHOOK: type: QUERY +POSTHOOK: query: -- auto-merge slow way +EXPLAIN + INSERT OVERWRITE TABLE orcfile_merge1b PARTITION (ds='1', part) + SELECT key, value, PMOD(HASH(key), 2) as part + FROM src +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-8 depends on stages: Stage-1 , consists of Stage-5, Stage-4, Stage-6 + Stage-5 + Stage-2 depends on stages: Stage-5, Stage-4, Stage-7 + Stage-0 depends on stages: Stage-2 + Stage-3 depends on stages: Stage-0 + Stage-4 + Stage-6 + Stage-7 depends on stages: Stage-6 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: UDFToInteger(key) (type: int), value (type: string), (hash(key) pmod 2) (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 500 Data size: 49500 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 500 Data size: 49500 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.orcfile_merge1b + Execution mode: llap + LLAP IO: no inputs + + Stage: Stage-8 + Conditional Operator + + Stage: Stage-5 + Move Operator + files: + hdfs directory: true +#### A masked pattern was here #### + + Stage: Stage-2 + Dependency Collection + + Stage: Stage-0 + Move Operator + tables: + partition: + ds 1 + part + replace: true + table: + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.orcfile_merge1b + + Stage: Stage-3 + Stats-Aggr Operator + + Stage: Stage-4 + Tez +#### A masked pattern was here #### + Vertices: + File Merge + Map Operator Tree: + TableScan + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.orcfile_merge1b + + Stage: Stage-6 + Tez +#### A masked pattern was here #### + Vertices: + File Merge + Map Operator Tree: + TableScan + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.orcfile_merge1b + + Stage: Stage-7 + Move Operator + files: + hdfs directory: true +#### A masked pattern was here #### + +PREHOOK: query: INSERT OVERWRITE TABLE orcfile_merge1b PARTITION (ds='1', part) + SELECT key, value, PMOD(HASH(key), 2) as part + FROM src +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: default@orcfile_merge1b@ds=1 +POSTHOOK: query: INSERT OVERWRITE TABLE orcfile_merge1b PARTITION (ds='1', part) + SELECT key, value, PMOD(HASH(key), 2) as part + FROM src +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Output: default@orcfile_merge1b@ds=1/part=0 +POSTHOOK: Output: default@orcfile_merge1b@ds=1/part=1 +POSTHOOK: Lineage: orcfile_merge1b PARTITION(ds=1,part=0).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: orcfile_merge1b PARTITION(ds=1,part=0).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: orcfile_merge1b PARTITION(ds=1,part=1).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: orcfile_merge1b PARTITION(ds=1,part=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] +Found 1 items +#### A masked pattern was here #### +PREHOOK: query: -- auto-merge fast way +EXPLAIN + INSERT OVERWRITE TABLE orcfile_merge1c PARTITION (ds='1', part) + SELECT key, value, PMOD(HASH(key), 2) as part + FROM src +PREHOOK: type: QUERY +POSTHOOK: query: -- auto-merge fast way +EXPLAIN + INSERT OVERWRITE TABLE orcfile_merge1c PARTITION (ds='1', part) + SELECT key, value, PMOD(HASH(key), 2) as part + FROM src +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-8 depends on stages: Stage-1 , consists of Stage-5, Stage-4, Stage-6 + Stage-5 + Stage-2 depends on stages: Stage-5, Stage-4, Stage-7 + Stage-0 depends on stages: Stage-2 + Stage-3 depends on stages: Stage-0 + Stage-4 + Stage-6 + Stage-7 depends on stages: Stage-6 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: UDFToInteger(key) (type: int), value (type: string), (hash(key) pmod 2) (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 500 Data size: 49500 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 500 Data size: 49500 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.orcfile_merge1c + Execution mode: llap + LLAP IO: no inputs + + Stage: Stage-8 + Conditional Operator + + Stage: Stage-5 + Move Operator + files: + hdfs directory: true +#### A masked pattern was here #### + + Stage: Stage-2 + Dependency Collection + + Stage: Stage-0 + Move Operator + tables: + partition: + ds 1 + part + replace: true + table: + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.orcfile_merge1c + + Stage: Stage-3 + Stats-Aggr Operator + + Stage: Stage-4 + Tez +#### A masked pattern was here #### + Vertices: + File Merge + Merge File Operator + Map Operator Tree: + ORC File Merge Operator + merge level: stripe + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + + Stage: Stage-6 + Tez +#### A masked pattern was here #### + Vertices: + File Merge + Merge File Operator + Map Operator Tree: + ORC File Merge Operator + merge level: stripe + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + + Stage: Stage-7 + Move Operator + files: + hdfs directory: true +#### A masked pattern was here #### + +PREHOOK: query: INSERT OVERWRITE TABLE orcfile_merge1c PARTITION (ds='1', part) + SELECT key, value, PMOD(HASH(key), 2) as part + FROM src +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: default@orcfile_merge1c@ds=1 +POSTHOOK: query: INSERT OVERWRITE TABLE orcfile_merge1c PARTITION (ds='1', part) + SELECT key, value, PMOD(HASH(key), 2) as part + FROM src +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Output: default@orcfile_merge1c@ds=1/part=0 +POSTHOOK: Output: default@orcfile_merge1c@ds=1/part=1 +POSTHOOK: Lineage: orcfile_merge1c PARTITION(ds=1,part=0).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: orcfile_merge1c PARTITION(ds=1,part=0).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: orcfile_merge1c PARTITION(ds=1,part=1).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: orcfile_merge1c PARTITION(ds=1,part=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] +Found 1 items +#### A masked pattern was here #### +PREHOOK: query: -- Verify +SELECT SUM(HASH(c)) FROM ( + SELECT TRANSFORM(*) USING 'tr \t _' AS (c) + FROM orcfile_merge1 WHERE ds='1' +) t +PREHOOK: type: QUERY +PREHOOK: Input: default@orcfile_merge1 +PREHOOK: Input: default@orcfile_merge1@ds=1/part=0 +PREHOOK: Input: default@orcfile_merge1@ds=1/part=1 +#### A masked pattern was here #### +POSTHOOK: query: -- Verify +SELECT SUM(HASH(c)) FROM ( + SELECT TRANSFORM(*) USING 'tr \t _' AS (c) + FROM orcfile_merge1 WHERE ds='1' +) t +POSTHOOK: type: QUERY +POSTHOOK: Input: default@orcfile_merge1 +POSTHOOK: Input: default@orcfile_merge1@ds=1/part=0 +POSTHOOK: Input: default@orcfile_merge1@ds=1/part=1 +#### A masked pattern was here #### +-21975308766 +PREHOOK: query: SELECT SUM(HASH(c)) FROM ( + SELECT TRANSFORM(*) USING 'tr \t _' AS (c) + FROM orcfile_merge1b WHERE ds='1' +) t +PREHOOK: type: QUERY +PREHOOK: Input: default@orcfile_merge1b +PREHOOK: Input: default@orcfile_merge1b@ds=1/part=0 +PREHOOK: Input: default@orcfile_merge1b@ds=1/part=1 +#### A masked pattern was here #### +POSTHOOK: query: SELECT SUM(HASH(c)) FROM ( + SELECT TRANSFORM(*) USING 'tr \t _' AS (c) + FROM orcfile_merge1b WHERE ds='1' +) t +POSTHOOK: type: QUERY +POSTHOOK: Input: default@orcfile_merge1b +POSTHOOK: Input: default@orcfile_merge1b@ds=1/part=0 +POSTHOOK: Input: default@orcfile_merge1b@ds=1/part=1 +#### A masked pattern was here #### +-21975308766 +PREHOOK: query: select count(*) from orcfile_merge1 +PREHOOK: type: QUERY +PREHOOK: Input: default@orcfile_merge1 +PREHOOK: Input: default@orcfile_merge1@ds=1/part=0 +PREHOOK: Input: default@orcfile_merge1@ds=1/part=1 +#### A masked pattern was here #### +POSTHOOK: query: select count(*) from orcfile_merge1 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@orcfile_merge1 +POSTHOOK: Input: default@orcfile_merge1@ds=1/part=0 +POSTHOOK: Input: default@orcfile_merge1@ds=1/part=1 +#### A masked pattern was here #### +500 +PREHOOK: query: select count(*) from orcfile_merge1b +PREHOOK: type: QUERY +PREHOOK: Input: default@orcfile_merge1b +PREHOOK: Input: default@orcfile_merge1b@ds=1/part=0 +PREHOOK: Input: default@orcfile_merge1b@ds=1/part=1 +#### A masked pattern was here #### +POSTHOOK: query: select count(*) from orcfile_merge1b +POSTHOOK: type: QUERY +POSTHOOK: Input: default@orcfile_merge1b +POSTHOOK: Input: default@orcfile_merge1b@ds=1/part=0 +POSTHOOK: Input: default@orcfile_merge1b@ds=1/part=1 +#### A masked pattern was here #### +500 +PREHOOK: query: -- concatenate +explain ALTER TABLE orcfile_merge1 PARTITION (ds='1', part='0') CONCATENATE +PREHOOK: type: ALTER_PARTITION_MERGE +POSTHOOK: query: -- concatenate +explain ALTER TABLE orcfile_merge1 PARTITION (ds='1', part='0') CONCATENATE +POSTHOOK: type: ALTER_PARTITION_MERGE +STAGE DEPENDENCIES: + Stage-0 is a root stage + Stage-1 depends on stages: Stage-0 + Stage-2 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-0 + + Stage: Stage-1 + Move Operator + tables: + partition: + ds 1 + part 0 + replace: true + table: + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.orcfile_merge1 + + Stage: Stage-2 + Stats-Aggr Operator + +PREHOOK: query: ALTER TABLE orcfile_merge1 PARTITION (ds='1', part='0') CONCATENATE +PREHOOK: type: ALTER_PARTITION_MERGE +PREHOOK: Input: default@orcfile_merge1 +PREHOOK: Output: default@orcfile_merge1@ds=1/part=0 +POSTHOOK: query: ALTER TABLE orcfile_merge1 PARTITION (ds='1', part='0') CONCATENATE +POSTHOOK: type: ALTER_PARTITION_MERGE +POSTHOOK: Input: default@orcfile_merge1 +POSTHOOK: Output: default@orcfile_merge1@ds=1/part=0 +Found 1 items +#### A masked pattern was here #### +PREHOOK: query: -- Verify +SELECT SUM(HASH(c)) FROM ( + SELECT TRANSFORM(*) USING 'tr \t _' AS (c) + FROM orcfile_merge1c WHERE ds='1' +) t +PREHOOK: type: QUERY +PREHOOK: Input: default@orcfile_merge1c +PREHOOK: Input: default@orcfile_merge1c@ds=1/part=0 +PREHOOK: Input: default@orcfile_merge1c@ds=1/part=1 +#### A masked pattern was here #### +POSTHOOK: query: -- Verify +SELECT SUM(HASH(c)) FROM ( + SELECT TRANSFORM(*) USING 'tr \t _' AS (c) + FROM orcfile_merge1c WHERE ds='1' +) t +POSTHOOK: type: QUERY +POSTHOOK: Input: default@orcfile_merge1c +POSTHOOK: Input: default@orcfile_merge1c@ds=1/part=0 +POSTHOOK: Input: default@orcfile_merge1c@ds=1/part=1 +#### A masked pattern was here #### +-21975308766 +PREHOOK: query: SELECT SUM(HASH(c)) FROM ( + SELECT TRANSFORM(*) USING 'tr \t _' AS (c) + FROM orcfile_merge1 WHERE ds='1' +) t +PREHOOK: type: QUERY +PREHOOK: Input: default@orcfile_merge1 +PREHOOK: Input: default@orcfile_merge1@ds=1/part=0 +PREHOOK: Input: default@orcfile_merge1@ds=1/part=1 +#### A masked pattern was here #### +POSTHOOK: query: SELECT SUM(HASH(c)) FROM ( + SELECT TRANSFORM(*) USING 'tr \t _' AS (c) + FROM orcfile_merge1 WHERE ds='1' +) t +POSTHOOK: type: QUERY +POSTHOOK: Input: default@orcfile_merge1 +POSTHOOK: Input: default@orcfile_merge1@ds=1/part=0 +POSTHOOK: Input: default@orcfile_merge1@ds=1/part=1 +#### A masked pattern was here #### +-21975308766 +PREHOOK: query: select count(*) from orcfile_merge1 +PREHOOK: type: QUERY +PREHOOK: Input: default@orcfile_merge1 +PREHOOK: Input: default@orcfile_merge1@ds=1/part=0 +PREHOOK: Input: default@orcfile_merge1@ds=1/part=1 +#### A masked pattern was here #### +POSTHOOK: query: select count(*) from orcfile_merge1 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@orcfile_merge1 +POSTHOOK: Input: default@orcfile_merge1@ds=1/part=0 +POSTHOOK: Input: default@orcfile_merge1@ds=1/part=1 +#### A masked pattern was here #### +500 +PREHOOK: query: select count(*) from orcfile_merge1c +PREHOOK: type: QUERY +PREHOOK: Input: default@orcfile_merge1c +PREHOOK: Input: default@orcfile_merge1c@ds=1/part=0 +PREHOOK: Input: default@orcfile_merge1c@ds=1/part=1 +#### A masked pattern was here #### +POSTHOOK: query: select count(*) from orcfile_merge1c +POSTHOOK: type: QUERY +POSTHOOK: Input: default@orcfile_merge1c +POSTHOOK: Input: default@orcfile_merge1c@ds=1/part=0 +POSTHOOK: Input: default@orcfile_merge1c@ds=1/part=1 +#### A masked pattern was here #### +500 +PREHOOK: query: select * from orcfile_merge1 where ds='1' and part='0' limit 1 +PREHOOK: type: QUERY +PREHOOK: Input: default@orcfile_merge1 +PREHOOK: Input: default@orcfile_merge1@ds=1/part=0 +#### A masked pattern was here #### +-- BEGIN ORC FILE DUMP -- +#### A masked pattern was here #### +File Version: 0.12 with HIVE_13083 +Rows: 242 +Compression: SNAPPY +Compression size: 4096 +Type: struct<key:int,value:string> + +Stripe Statistics: + Stripe 1: + Column 0: count: 90 hasNull: false + Column 1: count: 90 hasNull: false min: 0 max: 495 sum: 22736 + Column 2: count: 90 hasNull: false min: val_0 max: val_86 sum: 612 + Stripe 2: + Column 0: count: 78 hasNull: false + Column 1: count: 78 hasNull: false min: 0 max: 497 sum: 18371 + Column 2: count: 78 hasNull: false min: val_0 max: val_95 sum: 529 + Stripe 3: + Column 0: count: 74 hasNull: false + Column 1: count: 74 hasNull: false min: 2 max: 493 sum: 19663 + Column 2: count: 74 hasNull: false min: val_105 max: val_97 sum: 505 + +File Statistics: + Column 0: count: 242 hasNull: false + Column 1: count: 242 hasNull: false min: 0 max: 497 sum: 60770 + Column 2: count: 242 hasNull: false min: val_0 max: val_97 sum: 1646 + +Stripes: + Stripe: offset: 3 data: 616 rows: 90 tail: 61 index: 76 + Stream: column 0 section ROW_INDEX start: 3 length 11 + Stream: column 1 section ROW_INDEX start: 14 length 27 + Stream: column 2 section ROW_INDEX start: 41 length 38 + Stream: column 1 section DATA start: 79 length 185 + Stream: column 2 section DATA start: 264 length 377 + Stream: column 2 section LENGTH start: 641 length 54 + Encoding column 0: DIRECT + Encoding column 1: DIRECT_V2 + Encoding column 2: DIRECT_V2 + Row group indices for column 0: + Entry 0: count: 90 hasNull: false positions: + Row group indices for column 1: + Entry 0: count: 90 hasNull: false min: 0 max: 495 sum: 22736 positions: 0,0,0 + Row group indices for column 2: + Entry 0: count: 90 hasNull: false min: val_0 max: val_86 sum: 612 positions: 0,0,0,0,0 + Stripe: offset: 756 data: 544 rows: 78 tail: 61 index: 76 + Stream: column 0 section ROW_INDEX start: 756 length 11 + Stream: column 1 section ROW_INDEX start: 767 length 27 + Stream: column 2 section ROW_INDEX start: 794 length 38 + Stream: column 1 section DATA start: 832 length 161 + Stream: column 2 section DATA start: 993 length 332 + Stream: column 2 section LENGTH start: 1325 length 51 + Encoding column 0: DIRECT + Encoding column 1: DIRECT_V2 + Encoding column 2: DIRECT_V2 + Row group indices for column 0: + Entry 0: count: 78 hasNull: false positions: + Row group indices for column 1: + Entry 0: count: 78 hasNull: false min: 0 max: 497 sum: 18371 positions: 0,0,0 + Row group indices for column 2: + Entry 0: count: 78 hasNull: false min: val_0 max: val_95 sum: 529 positions: 0,0,0,0,0 + Stripe: offset: 1437 data: 519 rows: 74 tail: 61 index: 78 + Stream: column 0 section ROW_INDEX start: 1437 length 11 + Stream: column 1 section ROW_INDEX start: 1448 length 27 + Stream: column 2 section ROW_INDEX start: 1475 length 40 + Stream: column 1 section DATA start: 1515 length 153 + Stream: column 2 section DATA start: 1668 length 331 + Stream: column 2 section LENGTH start: 1999 length 35 + Encoding column 0: DIRECT + Encoding column 1: DIRECT_V2 + Encoding column 2: DIRECT_V2 + Row group indices for column 0: + Entry 0: count: 74 hasNull: false positions: + Row group indices for column 1: + Entry 0: count: 74 hasNull: false min: 2 max: 493 sum: 19663 positions: 0,0,0 + Row group indices for column 2: + Entry 0: count: 74 hasNull: false min: val_105 max: val_97 sum: 505 positions: 0,0,0,0,0 + +File length: 2393 bytes +Padding length: 0 bytes +Padding ratio: 0% +________________________________________________________________________________________________________________________ + +-- END ORC FILE DUMP -- +86 val_86 1 0 +PREHOOK: query: select * from orcfile_merge1c where ds='1' and part='0' limit 1 +PREHOOK: type: QUERY +PREHOOK: Input: default@orcfile_merge1c +PREHOOK: Input: default@orcfile_merge1c@ds=1/part=0 +#### A masked pattern was here #### +-- BEGIN ORC FILE DUMP -- +#### A masked pattern was here #### +File Version: 0.12 with HIVE_13083 +Rows: 242 +Compression: SNAPPY +Compression size: 4096 +Type: struct<key:int,value:string> + +Stripe Statistics: + Stripe 1: + Column 0: count: 90 hasNull: false + Column 1: count: 90 hasNull: false min: 0 max: 495 sum: 22736 + Column 2: count: 90 hasNull: false min: val_0 max: val_86 sum: 612 + Stripe 2: + Column 0: count: 78 hasNull: false + Column 1: count: 78 hasNull: false min: 0 max: 497 sum: 18371 + Column 2: count: 78 hasNull: false min: val_0 max: val_95 sum: 529 + Stripe 3: + Column 0: count: 74 hasNull: false + Column 1: count: 74 hasNull: false min: 2 max: 493 sum: 19663 + Column 2: count: 74 hasNull: false min: val_105 max: val_97 sum: 505 + +File Statistics: + Column 0: count: 242 hasNull: false + Column 1: count: 242 hasNull: false min: 0 max: 497 sum: 60770 + Column 2: count: 242 hasNull: false min: val_0 max: val_97 sum: 1646 + +Stripes: + Stripe: offset: 3 data: 616 rows: 90 tail: 61 index: 76 + Stream: column 0 section ROW_INDEX start: 3 length 11 + Stream: column 1 section ROW_INDEX start: 14 length 27 + Stream: column 2 section ROW_INDEX start: 41 length 38 + Stream: column 1 section DATA start: 79 length 185 + Stream: column 2 section DATA start: 264 length 377 + Stream: column 2 section LENGTH start: 641 length 54 + Encoding column 0: DIRECT + Encoding column 1: DIRECT_V2 + Encoding column 2: DIRECT_V2 + Row group indices for column 0: + Entry 0: count: 90 hasNull: false positions: + Row group indices for column 1: + Entry 0: count: 90 hasNull: false min: 0 max: 495 sum: 22736 positions: 0,0,0 + Row group indices for column 2: + Entry 0: count: 90 hasNull: false min: val_0 max: val_86 sum: 612 positions: 0,0,0,0,0 + Stripe: offset: 756 data: 544 rows: 78 tail: 61 index: 76 + Stream: column 0 section ROW_INDEX start: 756 length 11 + Stream: column 1 section ROW_INDEX start: 767 length 27 + Stream: column 2 section ROW_INDEX start: 794 length 38 + Stream: column 1 section DATA start: 832 length 161 + Stream: column 2 section DATA start: 993 length 332 + Stream: column 2 section LENGTH start: 1325 length 51 + Encoding column 0: DIRECT + Encoding column 1: DIRECT_V2 + Encoding column 2: DIRECT_V2 + Row group indices for column 0: + Entry 0: count: 78 hasNull: false positions: + Row group indices for column 1: + Entry 0: count: 78 hasNull: false min: 0 max: 497 sum: 18371 positions: 0,0,0 + Row group indices for column 2: + Entry 0: count: 78 hasNull: false min: val_0 max: val_95 sum: 529 positions: 0,0,0,0,0 + Stripe: offset: 1437 data: 519 rows: 74 tail: 61 index: 78 + Stream: column 0 section ROW_INDEX start: 1437 length 11 + Stream: column 1 section ROW_INDEX start: 1448 length 27 + Stream: column 2 section ROW_INDEX start: 1475 length 40 + Stream: column 1 section DATA start: 1515 length 153 + Stream: column 2 section DATA start: 1668 length 331 + Stream: column 2 section LENGTH start: 1999 length 35 + Encoding column 0: DIRECT + Encoding column 1: DIRECT_V2 + Encoding column 2: DIRECT_V2 + Row group indices for column 0: + Entry 0: count: 74 hasNull: false positions: + Row group indices for column 1: + Entry 0: count: 74 hasNull: false min: 2 max: 493 sum: 19663 positions: 0,0,0 + Row group indices for column 2: + Entry 0: count: 74 hasNull: false min: val_105 max: val_97 sum: 505 positions: 0,0,0,0,0 + +File length: 2393 bytes +Padding length: 0 bytes +Padding ratio: 0% +________________________________________________________________________________________________________________________ + +-- END ORC FILE DUMP -- +86 val_86 1 0 +PREHOOK: query: DROP TABLE orcfile_merge1 +PREHOOK: type: DROPTABLE +PREHOOK: Input: default@orcfile_merge1 +PREHOOK: Output: default@orcfile_merge1 +PREHOOK: query: DROP TABLE orcfile_merge1b +PREHOOK: type: DROPTABLE +PREHOOK: Input: default@orcfile_merge1b +PREHOOK: Output: default@orcfile_merge1b +PREHOOK: query: DROP TABLE orcfile_merge1c +PREHOOK: type: DROPTABLE +PREHOOK: Input: default@orcfile_merge1c +PREHOOK: Output: default@orcfile_merge1c http://git-wip-us.apache.org/repos/asf/hive/blob/5f01dc42/ql/src/test/results/clientpositive/llap/orc_merge11.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/orc_merge11.q.out b/ql/src/test/results/clientpositive/llap/orc_merge11.q.out new file mode 100644 index 0000000..5143a6a --- /dev/null +++ b/ql/src/test/results/clientpositive/llap/orc_merge11.q.out @@ -0,0 +1,442 @@ +PREHOOK: query: DROP TABLE orcfile_merge1 +PREHOOK: type: DROPTABLE +POSTHOOK: query: DROP TABLE orcfile_merge1 +POSTHOOK: type: DROPTABLE +PREHOOK: query: DROP TABLE orc_split_elim +PREHOOK: type: DROPTABLE +POSTHOOK: query: DROP TABLE orc_split_elim +POSTHOOK: type: DROPTABLE +PREHOOK: query: create table orc_split_elim (userid bigint, string1 string, subtype double, decimal1 decimal, ts timestamp) stored as orc +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@orc_split_elim +POSTHOOK: query: create table orc_split_elim (userid bigint, string1 string, subtype double, decimal1 decimal, ts timestamp) stored as orc +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@orc_split_elim +PREHOOK: query: load data local inpath '../../data/files/orc_split_elim.orc' into table orc_split_elim +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@orc_split_elim +POSTHOOK: query: load data local inpath '../../data/files/orc_split_elim.orc' into table orc_split_elim +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@orc_split_elim +PREHOOK: query: load data local inpath '../../data/files/orc_split_elim.orc' into table orc_split_elim +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@orc_split_elim +POSTHOOK: query: load data local inpath '../../data/files/orc_split_elim.orc' into table orc_split_elim +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@orc_split_elim +PREHOOK: query: create table orcfile_merge1 (userid bigint, string1 string, subtype double, decimal1 decimal, ts timestamp) stored as orc tblproperties("orc.compress.size"="4096") +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@orcfile_merge1 +POSTHOOK: query: create table orcfile_merge1 (userid bigint, string1 string, subtype double, decimal1 decimal, ts timestamp) stored as orc tblproperties("orc.compress.size"="4096") +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@orcfile_merge1 +PREHOOK: query: insert overwrite table orcfile_merge1 select * from orc_split_elim +PREHOOK: type: QUERY +PREHOOK: Input: default@orc_split_elim +PREHOOK: Output: default@orcfile_merge1 +POSTHOOK: query: insert overwrite table orcfile_merge1 select * from orc_split_elim +POSTHOOK: type: QUERY +POSTHOOK: Input: default@orc_split_elim +POSTHOOK: Output: default@orcfile_merge1 +POSTHOOK: Lineage: orcfile_merge1.decimal1 SIMPLE [(orc_split_elim)orc_split_elim.FieldSchema(name:decimal1, type:decimal(10,0), comment:null), ] +POSTHOOK: Lineage: orcfile_merge1.string1 SIMPLE [(orc_split_elim)orc_split_elim.FieldSchema(name:string1, type:string, comment:null), ] +POSTHOOK: Lineage: orcfile_merge1.subtype SIMPLE [(orc_split_elim)orc_split_elim.FieldSchema(name:subtype, type:double, comment:null), ] +POSTHOOK: Lineage: orcfile_merge1.ts SIMPLE [(orc_split_elim)orc_split_elim.FieldSchema(name:ts, type:timestamp, comment:null), ] +POSTHOOK: Lineage: orcfile_merge1.userid SIMPLE [(orc_split_elim)orc_split_elim.FieldSchema(name:userid, type:bigint, comment:null), ] +PREHOOK: query: insert into table orcfile_merge1 select * from orc_split_elim +PREHOOK: type: QUERY +PREHOOK: Input: default@orc_split_elim +PREHOOK: Output: default@orcfile_merge1 +POSTHOOK: query: insert into table orcfile_merge1 select * from orc_split_elim +POSTHOOK: type: QUERY +POSTHOOK: Input: default@orc_split_elim +POSTHOOK: Output: default@orcfile_merge1 +POSTHOOK: Lineage: orcfile_merge1.decimal1 SIMPLE [(orc_split_elim)orc_split_elim.FieldSchema(name:decimal1, type:decimal(10,0), comment:null), ] +POSTHOOK: Lineage: orcfile_merge1.string1 SIMPLE [(orc_split_elim)orc_split_elim.FieldSchema(name:string1, type:string, comment:null), ] +POSTHOOK: Lineage: orcfile_merge1.subtype SIMPLE [(orc_split_elim)orc_split_elim.FieldSchema(name:subtype, type:double, comment:null), ] +POSTHOOK: Lineage: orcfile_merge1.ts SIMPLE [(orc_split_elim)orc_split_elim.FieldSchema(name:ts, type:timestamp, comment:null), ] +POSTHOOK: Lineage: orcfile_merge1.userid SIMPLE [(orc_split_elim)orc_split_elim.FieldSchema(name:userid, type:bigint, comment:null), ] +Found 2 items +#### A masked pattern was here #### +PREHOOK: query: select * from orcfile_merge1 limit 1 +PREHOOK: type: QUERY +PREHOOK: Input: default@orcfile_merge1 +#### A masked pattern was here #### +-- BEGIN ORC FILE DUMP -- +#### A masked pattern was here #### +File Version: 0.12 with HIVE_13083 +Rows: 50000 +Compression: ZLIB +Compression size: 4096 +Type: struct<userid:bigint,string1:string,subtype:double,decimal1:decimal(10,0),ts:timestamp> + +Stripe Statistics: + Stripe 1: + Column 0: count: 50000 hasNull: false + Column 1: count: 50000 hasNull: false min: 2 max: 100 sum: 4999238 + Column 2: count: 50000 hasNull: false min: bar max: zebra sum: 249980 + Column 3: count: 50000 hasNull: false min: 0.8 max: 80.0 sum: 400102.80000000005 + Column 4: count: 50000 hasNull: false min: 0 max: 6 sum: 32 + Column 5: count: 50000 hasNull: false min: 1969-12-31 16:00:00.0 max: 1969-12-31 16:04:10.0 + +File Statistics: + Column 0: count: 50000 hasNull: false + Column 1: count: 50000 hasNull: false min: 2 max: 100 sum: 4999238 + Column 2: count: 50000 hasNull: false min: bar max: zebra sum: 249980 + Column 3: count: 50000 hasNull: false min: 0.8 max: 80.0 sum: 400102.80000000005 + Column 4: count: 50000 hasNull: false min: 0 max: 6 sum: 32 + Column 5: count: 50000 hasNull: false min: 1969-12-31 16:00:00.0 max: 1969-12-31 16:04:10.0 + +Stripes: + Stripe: offset: 3 data: 5897 rows: 50000 tail: 113 index: 498 + Stream: column 0 section ROW_INDEX start: 3 length 17 + Stream: column 1 section ROW_INDEX start: 20 length 83 + Stream: column 2 section ROW_INDEX start: 103 length 81 + Stream: column 3 section ROW_INDEX start: 184 length 111 + Stream: column 4 section ROW_INDEX start: 295 length 110 + Stream: column 5 section ROW_INDEX start: 405 length 96 + Stream: column 1 section DATA start: 501 length 45 + Stream: column 2 section DATA start: 546 length 41 + Stream: column 2 section LENGTH start: 587 length 8 + Stream: column 2 section DICTIONARY_DATA start: 595 length 23 + Stream: column 3 section DATA start: 618 length 5167 + Stream: column 4 section DATA start: 5785 length 524 + Stream: column 4 section SECONDARY start: 6309 length 18 + Stream: column 5 section DATA start: 6327 length 53 + Stream: column 5 section SECONDARY start: 6380 length 18 + Encoding column 0: DIRECT + Encoding column 1: DIRECT_V2 + Encoding column 2: DICTIONARY_V2[6] + Encoding column 3: DIRECT + Encoding column 4: DIRECT_V2 + Encoding column 5: DIRECT_V2 + Row group indices for column 0: + Entry 0: count: 10000 hasNull: false positions: + Entry 1: count: 10000 hasNull: false positions: + Entry 2: count: 10000 hasNull: false positions: + Entry 3: count: 10000 hasNull: false positions: + Entry 4: count: 10000 hasNull: false positions: + Row group indices for column 1: + Entry 0: count: 10000 hasNull: false min: 2 max: 100 sum: 999815 positions: 0,0,0 + Entry 1: count: 10000 hasNull: false min: 29 max: 100 sum: 999899 positions: 0,101,391 + Entry 2: count: 10000 hasNull: false min: 2 max: 100 sum: 999807 positions: 0,207,391 + Entry 3: count: 10000 hasNull: false min: 13 max: 100 sum: 999842 positions: 0,313,391 + Entry 4: count: 10000 hasNull: false min: 5 max: 100 sum: 999875 positions: 0,419,391 + Row group indices for column 2: + Entry 0: count: 10000 hasNull: false min: bar max: zebra sum: 49996 positions: 0,0,0 + Entry 1: count: 10000 hasNull: false min: cat max: zebra sum: 49996 positions: 0,82,391 + Entry 2: count: 10000 hasNull: false min: eat max: zebra sum: 49996 positions: 0,168,391 + Entry 3: count: 10000 hasNull: false min: bar max: zebra sum: 49996 positions: 0,254,391 + Entry 4: count: 10000 hasNull: false min: dog max: zebra sum: 49996 positions: 0,340,391 + Row group indices for column 3: + Entry 0: count: 10000 hasNull: false min: 0.8 max: 80.0 sum: 80064.8 positions: 0,0 + Entry 1: count: 10000 hasNull: false min: 1.8 max: 8.0 sum: 79993.8 positions: 1002,2176 + Entry 2: count: 10000 hasNull: false min: 0.8 max: 8.0 sum: 79985.6 positions: 2053,256 + Entry 3: count: 10000 hasNull: false min: 8.0 max: 80.0 sum: 80072.0 positions: 3067,2432 + Entry 4: count: 10000 hasNull: false min: 0.8 max: 8.0 sum: 79986.6 positions: 4117,512 + Row group indices for column 4: + Entry 0: count: 10000 hasNull: false min: 0 max: 2 sum: 3 positions: 0,0,0,0,0 + Entry 1: count: 10000 hasNull: false min: 0 max: 4 sum: 7 positions: 83,1808,0,76,272 + Entry 2: count: 10000 hasNull: false min: 0 max: 6 sum: 7 positions: 167,3616,0,156,32 + Entry 3: count: 10000 hasNull: false min: 0 max: 3 sum: 5 positions: 290,1328,0,232,304 + Entry 4: count: 10000 hasNull: false min: 0 max: 6 sum: 10 positions: 380,3136,0,312,64 + Row group indices for column 5: + Entry 0: count: 10000 hasNull: false min: 1969-12-31 16:00:00.0 max: 1969-12-31 16:04:10.0 positions: 0,0,0,0,0,0 + Entry 1: count: 10000 hasNull: false min: 1969-12-31 16:00:10.0 max: 1969-12-31 16:04:10.0 positions: 0,164,391,0,76,272 + Entry 2: count: 10000 hasNull: false min: 1969-12-31 16:00:00.0 max: 1969-12-31 16:04:10.0 positions: 0,336,391,0,156,32 + Entry 3: count: 10000 hasNull: false min: 1969-12-31 16:00:05.0 max: 1969-12-31 16:04:10.0 positions: 0,508,391,0,232,304 + Entry 4: count: 10000 hasNull: false min: 1969-12-31 16:00:15.0 max: 1969-12-31 16:04:10.0 positions: 0,680,391,0,312,64 + +File length: 6849 bytes +Padding length: 0 bytes +Padding ratio: 0% +________________________________________________________________________________________________________________________ + +-- END ORC FILE DUMP -- +-- BEGIN ORC FILE DUMP -- +#### A masked pattern was here #### +File Version: 0.12 with HIVE_13083 +Rows: 50000 +Compression: ZLIB +Compression size: 4096 +Type: struct<userid:bigint,string1:string,subtype:double,decimal1:decimal(10,0),ts:timestamp> + +Stripe Statistics: + Stripe 1: + Column 0: count: 50000 hasNull: false + Column 1: count: 50000 hasNull: false min: 2 max: 100 sum: 4999238 + Column 2: count: 50000 hasNull: false min: bar max: zebra sum: 249980 + Column 3: count: 50000 hasNull: false min: 0.8 max: 80.0 sum: 400102.80000000005 + Column 4: count: 50000 hasNull: false min: 0 max: 6 sum: 32 + Column 5: count: 50000 hasNull: false min: 1969-12-31 16:00:00.0 max: 1969-12-31 16:04:10.0 + +File Statistics: + Column 0: count: 50000 hasNull: false + Column 1: count: 50000 hasNull: false min: 2 max: 100 sum: 4999238 + Column 2: count: 50000 hasNull: false min: bar max: zebra sum: 249980 + Column 3: count: 50000 hasNull: false min: 0.8 max: 80.0 sum: 400102.80000000005 + Column 4: count: 50000 hasNull: false min: 0 max: 6 sum: 32 + Column 5: count: 50000 hasNull: false min: 1969-12-31 16:00:00.0 max: 1969-12-31 16:04:10.0 + +Stripes: + Stripe: offset: 3 data: 5897 rows: 50000 tail: 113 index: 498 + Stream: column 0 section ROW_INDEX start: 3 length 17 + Stream: column 1 section ROW_INDEX start: 20 length 83 + Stream: column 2 section ROW_INDEX start: 103 length 81 + Stream: column 3 section ROW_INDEX start: 184 length 111 + Stream: column 4 section ROW_INDEX start: 295 length 110 + Stream: column 5 section ROW_INDEX start: 405 length 96 + Stream: column 1 section DATA start: 501 length 45 + Stream: column 2 section DATA start: 546 length 41 + Stream: column 2 section LENGTH start: 587 length 8 + Stream: column 2 section DICTIONARY_DATA start: 595 length 23 + Stream: column 3 section DATA start: 618 length 5167 + Stream: column 4 section DATA start: 5785 length 524 + Stream: column 4 section SECONDARY start: 6309 length 18 + Stream: column 5 section DATA start: 6327 length 53 + Stream: column 5 section SECONDARY start: 6380 length 18 + Encoding column 0: DIRECT + Encoding column 1: DIRECT_V2 + Encoding column 2: DICTIONARY_V2[6] + Encoding column 3: DIRECT + Encoding column 4: DIRECT_V2 + Encoding column 5: DIRECT_V2 + Row group indices for column 0: + Entry 0: count: 10000 hasNull: false positions: + Entry 1: count: 10000 hasNull: false positions: + Entry 2: count: 10000 hasNull: false positions: + Entry 3: count: 10000 hasNull: false positions: + Entry 4: count: 10000 hasNull: false positions: + Row group indices for column 1: + Entry 0: count: 10000 hasNull: false min: 2 max: 100 sum: 999815 positions: 0,0,0 + Entry 1: count: 10000 hasNull: false min: 29 max: 100 sum: 999899 positions: 0,101,391 + Entry 2: count: 10000 hasNull: false min: 2 max: 100 sum: 999807 positions: 0,207,391 + Entry 3: count: 10000 hasNull: false min: 13 max: 100 sum: 999842 positions: 0,313,391 + Entry 4: count: 10000 hasNull: false min: 5 max: 100 sum: 999875 positions: 0,419,391 + Row group indices for column 2: + Entry 0: count: 10000 hasNull: false min: bar max: zebra sum: 49996 positions: 0,0,0 + Entry 1: count: 10000 hasNull: false min: cat max: zebra sum: 49996 positions: 0,82,391 + Entry 2: count: 10000 hasNull: false min: eat max: zebra sum: 49996 positions: 0,168,391 + Entry 3: count: 10000 hasNull: false min: bar max: zebra sum: 49996 positions: 0,254,391 + Entry 4: count: 10000 hasNull: false min: dog max: zebra sum: 49996 positions: 0,340,391 + Row group indices for column 3: + Entry 0: count: 10000 hasNull: false min: 0.8 max: 80.0 sum: 80064.8 positions: 0,0 + Entry 1: count: 10000 hasNull: false min: 1.8 max: 8.0 sum: 79993.8 positions: 1002,2176 + Entry 2: count: 10000 hasNull: false min: 0.8 max: 8.0 sum: 79985.6 positions: 2053,256 + Entry 3: count: 10000 hasNull: false min: 8.0 max: 80.0 sum: 80072.0 positions: 3067,2432 + Entry 4: count: 10000 hasNull: false min: 0.8 max: 8.0 sum: 79986.6 positions: 4117,512 + Row group indices for column 4: + Entry 0: count: 10000 hasNull: false min: 0 max: 2 sum: 3 positions: 0,0,0,0,0 + Entry 1: count: 10000 hasNull: false min: 0 max: 4 sum: 7 positions: 83,1808,0,76,272 + Entry 2: count: 10000 hasNull: false min: 0 max: 6 sum: 7 positions: 167,3616,0,156,32 + Entry 3: count: 10000 hasNull: false min: 0 max: 3 sum: 5 positions: 290,1328,0,232,304 + Entry 4: count: 10000 hasNull: false min: 0 max: 6 sum: 10 positions: 380,3136,0,312,64 + Row group indices for column 5: + Entry 0: count: 10000 hasNull: false min: 1969-12-31 16:00:00.0 max: 1969-12-31 16:04:10.0 positions: 0,0,0,0,0,0 + Entry 1: count: 10000 hasNull: false min: 1969-12-31 16:00:10.0 max: 1969-12-31 16:04:10.0 positions: 0,164,391,0,76,272 + Entry 2: count: 10000 hasNull: false min: 1969-12-31 16:00:00.0 max: 1969-12-31 16:04:10.0 positions: 0,336,391,0,156,32 + Entry 3: count: 10000 hasNull: false min: 1969-12-31 16:00:05.0 max: 1969-12-31 16:04:10.0 positions: 0,508,391,0,232,304 + Entry 4: count: 10000 hasNull: false min: 1969-12-31 16:00:15.0 max: 1969-12-31 16:04:10.0 positions: 0,680,391,0,312,64 + +File length: 6849 bytes +Padding length: 0 bytes +Padding ratio: 0% +________________________________________________________________________________________________________________________ + +-- END ORC FILE DUMP -- +2 foo 0.8 1 1969-12-31 16:00:00 +PREHOOK: query: -- concatenate +ALTER TABLE orcfile_merge1 CONCATENATE +PREHOOK: type: ALTER_TABLE_MERGE +PREHOOK: Input: default@orcfile_merge1 +PREHOOK: Output: default@orcfile_merge1 +Found 1 items +#### A masked pattern was here #### +PREHOOK: query: select count(*) from orc_split_elim +PREHOOK: type: QUERY +PREHOOK: Input: default@orc_split_elim +#### A masked pattern was here #### +50000 +PREHOOK: query: -- will have double the number of rows +select count(*) from orcfile_merge1 +PREHOOK: type: QUERY +PREHOOK: Input: default@orcfile_merge1 +#### A masked pattern was here #### +100000 +PREHOOK: query: select * from orcfile_merge1 limit 1 +PREHOOK: type: QUERY +PREHOOK: Input: default@orcfile_merge1 +#### A masked pattern was here #### +-- BEGIN ORC FILE DUMP -- +#### A masked pattern was here #### +File Version: 0.12 with HIVE_13083 +Rows: 100000 +Compression: ZLIB +Compression size: 4096 +Type: struct<userid:bigint,string1:string,subtype:double,decimal1:decimal(10,0),ts:timestamp> + +Stripe Statistics: + Stripe 1: + Column 0: count: 50000 hasNull: false + Column 1: count: 50000 hasNull: false min: 2 max: 100 sum: 4999238 + Column 2: count: 50000 hasNull: false min: bar max: zebra sum: 249980 + Column 3: count: 50000 hasNull: false min: 0.8 max: 80.0 sum: 400102.80000000005 + Column 4: count: 50000 hasNull: false min: 0 max: 6 sum: 32 + Column 5: count: 50000 hasNull: false min: 1969-12-31 16:00:00.0 max: 1969-12-31 16:04:10.0 + Stripe 2: + Column 0: count: 50000 hasNull: false + Column 1: count: 50000 hasNull: false min: 2 max: 100 sum: 4999238 + Column 2: count: 50000 hasNull: false min: bar max: zebra sum: 249980 + Column 3: count: 50000 hasNull: false min: 0.8 max: 80.0 sum: 400102.80000000005 + Column 4: count: 50000 hasNull: false min: 0 max: 6 sum: 32 + Column 5: count: 50000 hasNull: false min: 1969-12-31 16:00:00.0 max: 1969-12-31 16:04:10.0 + +File Statistics: + Column 0: count: 100000 hasNull: false + Column 1: count: 100000 hasNull: false min: 2 max: 100 sum: 9998476 + Column 2: count: 100000 hasNull: false min: bar max: zebra sum: 499960 + Column 3: count: 100000 hasNull: false min: 0.8 max: 80.0 sum: 800205.6000000001 + Column 4: count: 100000 hasNull: false min: 0 max: 6 sum: 64 + Column 5: count: 100000 hasNull: false min: 1969-12-31 16:00:00.0 max: 1969-12-31 16:04:10.0 + +Stripes: + Stripe: offset: 3 data: 5897 rows: 50000 tail: 113 index: 498 + Stream: column 0 section ROW_INDEX start: 3 length 17 + Stream: column 1 section ROW_INDEX start: 20 length 83 + Stream: column 2 section ROW_INDEX start: 103 length 81 + Stream: column 3 section ROW_INDEX start: 184 length 111 + Stream: column 4 section ROW_INDEX start: 295 length 110 + Stream: column 5 section ROW_INDEX start: 405 length 96 + Stream: column 1 section DATA start: 501 length 45 + Stream: column 2 section DATA start: 546 length 41 + Stream: column 2 section LENGTH start: 587 length 8 + Stream: column 2 section DICTIONARY_DATA start: 595 length 23 + Stream: column 3 section DATA start: 618 length 5167 + Stream: column 4 section DATA start: 5785 length 524 + Stream: column 4 section SECONDARY start: 6309 length 18 + Stream: column 5 section DATA start: 6327 length 53 + Stream: column 5 section SECONDARY start: 6380 length 18 + Encoding column 0: DIRECT + Encoding column 1: DIRECT_V2 + Encoding column 2: DICTIONARY_V2[6] + Encoding column 3: DIRECT + Encoding column 4: DIRECT_V2 + Encoding column 5: DIRECT_V2 + Row group indices for column 0: + Entry 0: count: 10000 hasNull: false positions: + Entry 1: count: 10000 hasNull: false positions: + Entry 2: count: 10000 hasNull: false positions: + Entry 3: count: 10000 hasNull: false positions: + Entry 4: count: 10000 hasNull: false positions: + Row group indices for column 1: + Entry 0: count: 10000 hasNull: false min: 2 max: 100 sum: 999815 positions: 0,0,0 + Entry 1: count: 10000 hasNull: false min: 29 max: 100 sum: 999899 positions: 0,101,391 + Entry 2: count: 10000 hasNull: false min: 2 max: 100 sum: 999807 positions: 0,207,391 + Entry 3: count: 10000 hasNull: false min: 13 max: 100 sum: 999842 positions: 0,313,391 + Entry 4: count: 10000 hasNull: false min: 5 max: 100 sum: 999875 positions: 0,419,391 + Row group indices for column 2: + Entry 0: count: 10000 hasNull: false min: bar max: zebra sum: 49996 positions: 0,0,0 + Entry 1: count: 10000 hasNull: false min: cat max: zebra sum: 49996 positions: 0,82,391 + Entry 2: count: 10000 hasNull: false min: eat max: zebra sum: 49996 positions: 0,168,391 + Entry 3: count: 10000 hasNull: false min: bar max: zebra sum: 49996 positions: 0,254,391 + Entry 4: count: 10000 hasNull: false min: dog max: zebra sum: 49996 positions: 0,340,391 + Row group indices for column 3: + Entry 0: count: 10000 hasNull: false min: 0.8 max: 80.0 sum: 80064.8 positions: 0,0 + Entry 1: count: 10000 hasNull: false min: 1.8 max: 8.0 sum: 79993.8 positions: 1002,2176 + Entry 2: count: 10000 hasNull: false min: 0.8 max: 8.0 sum: 79985.6 positions: 2053,256 + Entry 3: count: 10000 hasNull: false min: 8.0 max: 80.0 sum: 80072.0 positions: 3067,2432 + Entry 4: count: 10000 hasNull: false min: 0.8 max: 8.0 sum: 79986.6 positions: 4117,512 + Row group indices for column 4: + Entry 0: count: 10000 hasNull: false min: 0 max: 2 sum: 3 positions: 0,0,0,0,0 + Entry 1: count: 10000 hasNull: false min: 0 max: 4 sum: 7 positions: 83,1808,0,76,272 + Entry 2: count: 10000 hasNull: false min: 0 max: 6 sum: 7 positions: 167,3616,0,156,32 + Entry 3: count: 10000 hasNull: false min: 0 max: 3 sum: 5 positions: 290,1328,0,232,304 + Entry 4: count: 10000 hasNull: false min: 0 max: 6 sum: 10 positions: 380,3136,0,312,64 + Row group indices for column 5: + Entry 0: count: 10000 hasNull: false min: 1969-12-31 16:00:00.0 max: 1969-12-31 16:04:10.0 positions: 0,0,0,0,0,0 + Entry 1: count: 10000 hasNull: false min: 1969-12-31 16:00:10.0 max: 1969-12-31 16:04:10.0 positions: 0,164,391,0,76,272 + Entry 2: count: 10000 hasNull: false min: 1969-12-31 16:00:00.0 max: 1969-12-31 16:04:10.0 positions: 0,336,391,0,156,32 + Entry 3: count: 10000 hasNull: false min: 1969-12-31 16:00:05.0 max: 1969-12-31 16:04:10.0 positions: 0,508,391,0,232,304 + Entry 4: count: 10000 hasNull: false min: 1969-12-31 16:00:15.0 max: 1969-12-31 16:04:10.0 positions: 0,680,391,0,312,64 + Stripe: offset: 6511 data: 5897 rows: 50000 tail: 113 index: 498 + Stream: column 0 section ROW_INDEX start: 6511 length 17 + Stream: column 1 section ROW_INDEX start: 6528 length 83 + Stream: column 2 section ROW_INDEX start: 6611 length 81 + Stream: column 3 section ROW_INDEX start: 6692 length 111 + Stream: column 4 section ROW_INDEX start: 6803 length 110 + Stream: column 5 section ROW_INDEX start: 6913 length 96 + Stream: column 1 section DATA start: 7009 length 45 + Stream: column 2 section DATA start: 7054 length 41 + Stream: column 2 section LENGTH start: 7095 length 8 + Stream: column 2 section DICTIONARY_DATA start: 7103 length 23 + Stream: column 3 section DATA start: 7126 length 5167 + Stream: column 4 section DATA start: 12293 length 524 + Stream: column 4 section SECONDARY start: 12817 length 18 + Stream: column 5 section DATA start: 12835 length 53 + Stream: column 5 section SECONDARY start: 12888 length 18 + Encoding column 0: DIRECT + Encoding column 1: DIRECT_V2 + Encoding column 2: DICTIONARY_V2[6] + Encoding column 3: DIRECT + Encoding column 4: DIRECT_V2 + Encoding column 5: DIRECT_V2 + Row group indices for column 0: + Entry 0: count: 10000 hasNull: false positions: + Entry 1: count: 10000 hasNull: false positions: + Entry 2: count: 10000 hasNull: false positions: + Entry 3: count: 10000 hasNull: false positions: + Entry 4: count: 10000 hasNull: false positions: + Row group indices for column 1: + Entry 0: count: 10000 hasNull: false min: 2 max: 100 sum: 999815 positions: 0,0,0 + Entry 1: count: 10000 hasNull: false min: 29 max: 100 sum: 999899 positions: 0,101,391 + Entry 2: count: 10000 hasNull: false min: 2 max: 100 sum: 999807 positions: 0,207,391 + Entry 3: count: 10000 hasNull: false min: 13 max: 100 sum: 999842 positions: 0,313,391 + Entry 4: count: 10000 hasNull: false min: 5 max: 100 sum: 999875 positions: 0,419,391 + Row group indices for column 2: + Entry 0: count: 10000 hasNull: false min: bar max: zebra sum: 49996 positions: 0,0,0 + Entry 1: count: 10000 hasNull: false min: cat max: zebra sum: 49996 positions: 0,82,391 + Entry 2: count: 10000 hasNull: false min: eat max: zebra sum: 49996 positions: 0,168,391 + Entry 3: count: 10000 hasNull: false min: bar max: zebra sum: 49996 positions: 0,254,391 + Entry 4: count: 10000 hasNull: false min: dog max: zebra sum: 49996 positions: 0,340,391 + Row group indices for column 3: + Entry 0: count: 10000 hasNull: false min: 0.8 max: 80.0 sum: 80064.8 positions: 0,0 + Entry 1: count: 10000 hasNull: false min: 1.8 max: 8.0 sum: 79993.8 positions: 1002,2176 + Entry 2: count: 10000 hasNull: false min: 0.8 max: 8.0 sum: 79985.6 positions: 2053,256 + Entry 3: count: 10000 hasNull: false min: 8.0 max: 80.0 sum: 80072.0 positions: 3067,2432 + Entry 4: count: 10000 hasNull: false min: 0.8 max: 8.0 sum: 79986.6 positions: 4117,512 + Row group indices for column 4: + Entry 0: count: 10000 hasNull: false min: 0 max: 2 sum: 3 positions: 0,0,0,0,0 + Entry 1: count: 10000 hasNull: false min: 0 max: 4 sum: 7 positions: 83,1808,0,76,272 + Entry 2: count: 10000 hasNull: false min: 0 max: 6 sum: 7 positions: 167,3616,0,156,32 + Entry 3: count: 10000 hasNull: false min: 0 max: 3 sum: 5 positions: 290,1328,0,232,304 + Entry 4: count: 10000 hasNull: false min: 0 max: 6 sum: 10 positions: 380,3136,0,312,64 + Row group indices for column 5: + Entry 0: count: 10000 hasNull: false min: 1969-12-31 16:00:00.0 max: 1969-12-31 16:04:10.0 positions: 0,0,0,0,0,0 + Entry 1: count: 10000 hasNull: false min: 1969-12-31 16:00:10.0 max: 1969-12-31 16:04:10.0 positions: 0,164,391,0,76,272 + Entry 2: count: 10000 hasNull: false min: 1969-12-31 16:00:00.0 max: 1969-12-31 16:04:10.0 positions: 0,336,391,0,156,32 + Entry 3: count: 10000 hasNull: false min: 1969-12-31 16:00:05.0 max: 1969-12-31 16:04:10.0 positions: 0,508,391,0,232,304 + Entry 4: count: 10000 hasNull: false min: 1969-12-31 16:00:15.0 max: 1969-12-31 16:04:10.0 positions: 0,680,391,0,312,64 + +File length: 13369 bytes +Padding length: 0 bytes +Padding ratio: 0% +________________________________________________________________________________________________________________________ + +-- END ORC FILE DUMP -- +2 foo 0.8 1 1969-12-31 16:00:00 +PREHOOK: query: DROP TABLE orc_split_elim +PREHOOK: type: DROPTABLE +PREHOOK: Input: default@orc_split_elim +PREHOOK: Output: default@orc_split_elim +PREHOOK: query: DROP TABLE orcfile_merge1 +PREHOOK: type: DROPTABLE +PREHOOK: Input: default@orcfile_merge1 +PREHOOK: Output: default@orcfile_merge1
