You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by jc...@apache.org on 2018/04/10 09:30:00 UTC
[22/24] hive git commit: HIVE-18839: Implement incremental rebuild
for materialized views (only insert operations in source tables) (Jesus
Camacho Rodriguez, reviewed by Ashutosh Chauhan)
http://git-wip-us.apache.org/repos/asf/hive/blob/be420098/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_4.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_4.q.out b/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_4.q.out
new file mode 100644
index 0000000..2f88037
--- /dev/null
+++ b/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_4.q.out
@@ -0,0 +1,1784 @@
+PREHOOK: query: create table cmv_basetable (a int, b varchar(256), c decimal(10,2), d int) stored as orc TBLPROPERTIES ('transactional'='true')
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@cmv_basetable
+POSTHOOK: query: create table cmv_basetable (a int, b varchar(256), c decimal(10,2), d int) stored as orc TBLPROPERTIES ('transactional'='true')
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@cmv_basetable
+PREHOOK: query: insert into cmv_basetable values
+ (1, 'alfred', 10.30, 2),
+ (2, 'bob', 3.14, 3),
+ (2, 'bonnie', 172342.2, 3),
+ (3, 'calvin', 978.76, 3),
+ (3, 'charlie', 9.8, 1)
+PREHOOK: type: QUERY
+PREHOOK: Input: _dummy_database@_dummy_table
+PREHOOK: Output: default@cmv_basetable
+POSTHOOK: query: insert into cmv_basetable values
+ (1, 'alfred', 10.30, 2),
+ (2, 'bob', 3.14, 3),
+ (2, 'bonnie', 172342.2, 3),
+ (3, 'calvin', 978.76, 3),
+ (3, 'charlie', 9.8, 1)
+POSTHOOK: type: QUERY
+POSTHOOK: Input: _dummy_database@_dummy_table
+POSTHOOK: Output: default@cmv_basetable
+POSTHOOK: Lineage: cmv_basetable.a SCRIPT []
+POSTHOOK: Lineage: cmv_basetable.b SCRIPT []
+POSTHOOK: Lineage: cmv_basetable.c SCRIPT []
+POSTHOOK: Lineage: cmv_basetable.d SCRIPT []
+PREHOOK: query: analyze table cmv_basetable compute statistics for columns
+PREHOOK: type: QUERY
+PREHOOK: Input: default@cmv_basetable
+PREHOOK: Output: default@cmv_basetable
+#### A masked pattern was here ####
+POSTHOOK: query: analyze table cmv_basetable compute statistics for columns
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@cmv_basetable
+POSTHOOK: Output: default@cmv_basetable
+#### A masked pattern was here ####
+PREHOOK: query: create table cmv_basetable_2 (a int, b varchar(256), c decimal(10,2), d int) stored as orc TBLPROPERTIES ('transactional'='true')
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@cmv_basetable_2
+POSTHOOK: query: create table cmv_basetable_2 (a int, b varchar(256), c decimal(10,2), d int) stored as orc TBLPROPERTIES ('transactional'='true')
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@cmv_basetable_2
+PREHOOK: query: insert into cmv_basetable_2 values
+ (1, 'alfred', 10.30, 2),
+ (3, 'calvin', 978.76, 3)
+PREHOOK: type: QUERY
+PREHOOK: Input: _dummy_database@_dummy_table
+PREHOOK: Output: default@cmv_basetable_2
+POSTHOOK: query: insert into cmv_basetable_2 values
+ (1, 'alfred', 10.30, 2),
+ (3, 'calvin', 978.76, 3)
+POSTHOOK: type: QUERY
+POSTHOOK: Input: _dummy_database@_dummy_table
+POSTHOOK: Output: default@cmv_basetable_2
+POSTHOOK: Lineage: cmv_basetable_2.a SCRIPT []
+POSTHOOK: Lineage: cmv_basetable_2.b SCRIPT []
+POSTHOOK: Lineage: cmv_basetable_2.c SCRIPT []
+POSTHOOK: Lineage: cmv_basetable_2.d SCRIPT []
+PREHOOK: query: analyze table cmv_basetable_2 compute statistics for columns
+PREHOOK: type: QUERY
+PREHOOK: Input: default@cmv_basetable_2
+PREHOOK: Output: default@cmv_basetable_2
+#### A masked pattern was here ####
+POSTHOOK: query: analyze table cmv_basetable_2 compute statistics for columns
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@cmv_basetable_2
+POSTHOOK: Output: default@cmv_basetable_2
+#### A masked pattern was here ####
+PREHOOK: query: EXPLAIN
+CREATE MATERIALIZED VIEW cmv_mat_view TBLPROPERTIES ('transactional'='true') AS
+ SELECT cmv_basetable.a, cmv_basetable_2.c, sum(cmv_basetable_2.d)
+ FROM cmv_basetable JOIN cmv_basetable_2 ON (cmv_basetable.a = cmv_basetable_2.a)
+ WHERE cmv_basetable_2.c > 10.0
+ GROUP BY cmv_basetable.a, cmv_basetable_2.c
+PREHOOK: type: CREATE_MATERIALIZED_VIEW
+POSTHOOK: query: EXPLAIN
+CREATE MATERIALIZED VIEW cmv_mat_view TBLPROPERTIES ('transactional'='true') AS
+ SELECT cmv_basetable.a, cmv_basetable_2.c, sum(cmv_basetable_2.d)
+ FROM cmv_basetable JOIN cmv_basetable_2 ON (cmv_basetable.a = cmv_basetable_2.a)
+ WHERE cmv_basetable_2.c > 10.0
+ GROUP BY cmv_basetable.a, cmv_basetable_2.c
+POSTHOOK: type: CREATE_MATERIALIZED_VIEW
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1
+ Stage-4 depends on stages: Stage-2, Stage-0
+ Stage-3 depends on stages: Stage-4
+ Stage-5 depends on stages: Stage-3
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Tez
+#### A masked pattern was here ####
+ Edges:
+ Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE)
+ Reducer 3 <- Reducer 2 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: cmv_basetable
+ Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: a is not null (type: boolean)
+ Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: a (type: int)
+ outputColumnNames: _col0
+ Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE
+ Execution mode: llap
+ LLAP IO: may be used (ACID table)
+ Map 4
+ Map Operator Tree:
+ TableScan
+ alias: cmv_basetable_2
+ Statistics: Num rows: 2 Data size: 240 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: ((c > 10) and a is not null) (type: boolean)
+ Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: a (type: int), c (type: decimal(10,2)), d (type: int)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col1 (type: decimal(10,2)), _col2 (type: int)
+ Execution mode: llap
+ LLAP IO: may be used (ACID table)
+ Reducer 2
+ Execution mode: llap
+ Reduce Operator Tree:
+ Merge Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: int)
+ 1 _col0 (type: int)
+ outputColumnNames: _col0, _col2, _col3
+ Statistics: Num rows: 3 Data size: 360 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: sum(_col3)
+ keys: _col0 (type: int), _col2 (type: decimal(10,2))
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 124 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: int), _col1 (type: decimal(10,2))
+ sort order: ++
+ Map-reduce partition columns: _col0 (type: int), _col1 (type: decimal(10,2))
+ Statistics: Num rows: 1 Data size: 124 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col2 (type: bigint)
+ Reducer 3
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: sum(VALUE._col0)
+ keys: KEY._col0 (type: int), KEY._col1 (type: decimal(10,2))
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 124 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 124 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.cmv_mat_view
+
+ Stage: Stage-2
+ Dependency Collection
+
+ Stage: Stage-4
+ Create View Operator:
+ Create View
+ columns: a int, c decimal(10,2), _c2 bigint
+ table properties:
+ transactional true
+ expanded text: SELECT `cmv_basetable`.`a`, `cmv_basetable_2`.`c`, sum(`cmv_basetable_2`.`d`)
+ FROM `default`.`cmv_basetable` JOIN `default`.`cmv_basetable_2` ON (`cmv_basetable`.`a` = `cmv_basetable_2`.`a`)
+ WHERE `cmv_basetable_2`.`c` > 10.0
+ GROUP BY `cmv_basetable`.`a`, `cmv_basetable_2`.`c`
+ name: default.cmv_mat_view
+ original text: SELECT cmv_basetable.a, cmv_basetable_2.c, sum(cmv_basetable_2.d)
+ FROM cmv_basetable JOIN cmv_basetable_2 ON (cmv_basetable.a = cmv_basetable_2.a)
+ WHERE cmv_basetable_2.c > 10.0
+ GROUP BY cmv_basetable.a, cmv_basetable_2.c
+
+ Stage: Stage-3
+ Stats Work
+ Basic Stats Work:
+
+ Stage: Stage-5
+ Materialized View Work
+
+ Stage: Stage-0
+ Move Operator
+ files:
+ hdfs directory: true
+#### A masked pattern was here ####
+
+PREHOOK: query: CREATE MATERIALIZED VIEW cmv_mat_view TBLPROPERTIES ('transactional'='true') AS
+ SELECT cmv_basetable.a, cmv_basetable_2.c, sum(cmv_basetable_2.d)
+ FROM cmv_basetable JOIN cmv_basetable_2 ON (cmv_basetable.a = cmv_basetable_2.a)
+ WHERE cmv_basetable_2.c > 10.0
+ GROUP BY cmv_basetable.a, cmv_basetable_2.c
+PREHOOK: type: CREATE_MATERIALIZED_VIEW
+PREHOOK: Input: default@cmv_basetable
+PREHOOK: Input: default@cmv_basetable_2
+PREHOOK: Output: database:default
+PREHOOK: Output: default@cmv_mat_view
+POSTHOOK: query: CREATE MATERIALIZED VIEW cmv_mat_view TBLPROPERTIES ('transactional'='true') AS
+ SELECT cmv_basetable.a, cmv_basetable_2.c, sum(cmv_basetable_2.d)
+ FROM cmv_basetable JOIN cmv_basetable_2 ON (cmv_basetable.a = cmv_basetable_2.a)
+ WHERE cmv_basetable_2.c > 10.0
+ GROUP BY cmv_basetable.a, cmv_basetable_2.c
+POSTHOOK: type: CREATE_MATERIALIZED_VIEW
+POSTHOOK: Input: default@cmv_basetable
+POSTHOOK: Input: default@cmv_basetable_2
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@cmv_mat_view
+PREHOOK: query: analyze table cmv_mat_view compute statistics for columns
+PREHOOK: type: QUERY
+PREHOOK: Input: default@cmv_mat_view
+PREHOOK: Output: default@cmv_mat_view
+#### A masked pattern was here ####
+POSTHOOK: query: analyze table cmv_mat_view compute statistics for columns
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@cmv_mat_view
+POSTHOOK: Output: default@cmv_mat_view
+#### A masked pattern was here ####
+PREHOOK: query: DESCRIBE FORMATTED cmv_mat_view
+PREHOOK: type: DESCTABLE
+PREHOOK: Input: default@cmv_mat_view
+POSTHOOK: query: DESCRIBE FORMATTED cmv_mat_view
+POSTHOOK: type: DESCTABLE
+POSTHOOK: Input: default@cmv_mat_view
+# col_name data_type comment
+a int
+c decimal(10,2)
+_c2 bigint
+
+# Detailed Table Information
+Database: default
+#### A masked pattern was here ####
+Retention: 0
+#### A masked pattern was here ####
+Table Type: MATERIALIZED_VIEW
+Table Parameters:
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"_c2\":\"true\",\"a\":\"true\",\"c\":\"true\"}}
+ numFiles 2
+ numRows 2
+ rawDataSize 248
+ totalSize 706
+ transactional true
+ transactional_properties default
+#### 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: []
+
+# View Information
+View Original Text: SELECT cmv_basetable.a, cmv_basetable_2.c, sum(cmv_basetable_2.d)
+ FROM cmv_basetable JOIN cmv_basetable_2 ON (cmv_basetable.a = cmv_basetable_2.a)
+ WHERE cmv_basetable_2.c > 10.0
+ GROUP BY cmv_basetable.a, cmv_basetable_2.c
+View Expanded Text: SELECT `cmv_basetable`.`a`, `cmv_basetable_2`.`c`, sum(`cmv_basetable_2`.`d`)
+ FROM `default`.`cmv_basetable` JOIN `default`.`cmv_basetable_2` ON (`cmv_basetable`.`a` = `cmv_basetable_2`.`a`)
+ WHERE `cmv_basetable_2`.`c` > 10.0
+ GROUP BY `cmv_basetable`.`a`, `cmv_basetable_2`.`c`
+View Rewrite Enabled: No
+PREHOOK: query: EXPLAIN
+SELECT cmv_basetable.a, sum(cmv_basetable_2.d)
+FROM cmv_basetable join cmv_basetable_2 ON (cmv_basetable.a = cmv_basetable_2.a)
+WHERE cmv_basetable_2.c > 10.10
+GROUP BY cmv_basetable.a, cmv_basetable_2.c
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN
+SELECT cmv_basetable.a, sum(cmv_basetable_2.d)
+FROM cmv_basetable join cmv_basetable_2 ON (cmv_basetable.a = cmv_basetable_2.a)
+WHERE cmv_basetable_2.c > 10.10
+GROUP BY cmv_basetable.a, cmv_basetable_2.c
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Tez
+#### A masked pattern was here ####
+ Edges:
+ Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE)
+ Reducer 3 <- Reducer 2 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: cmv_basetable
+ Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: a is not null (type: boolean)
+ Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: a (type: int)
+ outputColumnNames: _col0
+ Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE
+ Execution mode: llap
+ LLAP IO: may be used (ACID table)
+ Map 4
+ Map Operator Tree:
+ TableScan
+ alias: cmv_basetable_2
+ Statistics: Num rows: 2 Data size: 240 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: ((c > 10.1) and a is not null) (type: boolean)
+ Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: a (type: int), c (type: decimal(10,2)), d (type: int)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col1 (type: decimal(10,2)), _col2 (type: int)
+ Execution mode: llap
+ LLAP IO: may be used (ACID table)
+ Reducer 2
+ Execution mode: llap
+ Reduce Operator Tree:
+ Merge Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: int)
+ 1 _col0 (type: int)
+ outputColumnNames: _col0, _col2, _col3
+ Statistics: Num rows: 3 Data size: 360 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: sum(_col3)
+ keys: _col0 (type: int), _col2 (type: decimal(10,2))
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 124 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: int), _col1 (type: decimal(10,2))
+ sort order: ++
+ Map-reduce partition columns: _col0 (type: int), _col1 (type: decimal(10,2))
+ Statistics: Num rows: 1 Data size: 124 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col2 (type: bigint)
+ Reducer 3
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: sum(VALUE._col0)
+ keys: KEY._col0 (type: int), KEY._col1 (type: decimal(10,2))
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 124 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col0 (type: int), _col2 (type: bigint)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: SELECT cmv_basetable.a, sum(cmv_basetable_2.d)
+FROM cmv_basetable JOIN cmv_basetable_2 ON (cmv_basetable.a = cmv_basetable_2.a)
+WHERE cmv_basetable_2.c > 10.10
+GROUP BY cmv_basetable.a, cmv_basetable_2.c
+PREHOOK: type: QUERY
+PREHOOK: Input: default@cmv_basetable
+PREHOOK: Input: default@cmv_basetable_2
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT cmv_basetable.a, sum(cmv_basetable_2.d)
+FROM cmv_basetable JOIN cmv_basetable_2 ON (cmv_basetable.a = cmv_basetable_2.a)
+WHERE cmv_basetable_2.c > 10.10
+GROUP BY cmv_basetable.a, cmv_basetable_2.c
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@cmv_basetable
+POSTHOOK: Input: default@cmv_basetable_2
+#### A masked pattern was here ####
+3 6
+1 2
+PREHOOK: query: insert into cmv_basetable_2 values
+ (3, 'charlie', 15.8, 1)
+PREHOOK: type: QUERY
+PREHOOK: Input: _dummy_database@_dummy_table
+PREHOOK: Output: default@cmv_basetable_2
+POSTHOOK: query: insert into cmv_basetable_2 values
+ (3, 'charlie', 15.8, 1)
+POSTHOOK: type: QUERY
+POSTHOOK: Input: _dummy_database@_dummy_table
+POSTHOOK: Output: default@cmv_basetable_2
+POSTHOOK: Lineage: cmv_basetable_2.a SCRIPT []
+POSTHOOK: Lineage: cmv_basetable_2.b SCRIPT []
+POSTHOOK: Lineage: cmv_basetable_2.c SCRIPT []
+POSTHOOK: Lineage: cmv_basetable_2.d SCRIPT []
+PREHOOK: query: analyze table cmv_basetable_2 compute statistics for columns
+PREHOOK: type: QUERY
+PREHOOK: Input: default@cmv_basetable_2
+PREHOOK: Output: default@cmv_basetable_2
+#### A masked pattern was here ####
+POSTHOOK: query: analyze table cmv_basetable_2 compute statistics for columns
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@cmv_basetable_2
+POSTHOOK: Output: default@cmv_basetable_2
+#### A masked pattern was here ####
+PREHOOK: query: EXPLAIN
+ALTER MATERIALIZED VIEW cmv_mat_view ENABLE REWRITE
+PREHOOK: type: ALTER_MATERIALIZED_VIEW_REWRITE
+POSTHOOK: query: EXPLAIN
+ALTER MATERIALIZED VIEW cmv_mat_view ENABLE REWRITE
+POSTHOOK: type: ALTER_MATERIALIZED_VIEW_REWRITE
+STAGE DEPENDENCIES:
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-0
+ Alter Materialized View Operator:
+ Alter Materialized View
+ name: default.cmv_mat_view
+ operation: UPDATE_REWRITE_FLAG
+
+PREHOOK: query: ALTER MATERIALIZED VIEW cmv_mat_view ENABLE REWRITE
+PREHOOK: type: ALTER_MATERIALIZED_VIEW_REWRITE
+PREHOOK: Input: default@cmv_mat_view
+PREHOOK: Output: default@cmv_mat_view
+POSTHOOK: query: ALTER MATERIALIZED VIEW cmv_mat_view ENABLE REWRITE
+POSTHOOK: type: ALTER_MATERIALIZED_VIEW_REWRITE
+POSTHOOK: Input: default@cmv_mat_view
+POSTHOOK: Output: default@cmv_mat_view
+PREHOOK: query: DESCRIBE FORMATTED cmv_mat_view
+PREHOOK: type: DESCTABLE
+PREHOOK: Input: default@cmv_mat_view
+POSTHOOK: query: DESCRIBE FORMATTED cmv_mat_view
+POSTHOOK: type: DESCTABLE
+POSTHOOK: Input: default@cmv_mat_view
+# col_name data_type comment
+a int
+c decimal(10,2)
+_c2 bigint
+
+# Detailed Table Information
+Database: default
+#### A masked pattern was here ####
+Retention: 0
+#### A masked pattern was here ####
+Table Type: MATERIALIZED_VIEW
+Table Parameters:
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"_c2\":\"true\",\"a\":\"true\",\"c\":\"true\"}}
+ numFiles 2
+ numRows 2
+ rawDataSize 248
+ totalSize 706
+ transactional true
+ transactional_properties default
+#### 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: []
+
+# View Information
+View Original Text: SELECT cmv_basetable.a, cmv_basetable_2.c, sum(cmv_basetable_2.d)
+ FROM cmv_basetable JOIN cmv_basetable_2 ON (cmv_basetable.a = cmv_basetable_2.a)
+ WHERE cmv_basetable_2.c > 10.0
+ GROUP BY cmv_basetable.a, cmv_basetable_2.c
+View Expanded Text: SELECT `cmv_basetable`.`a`, `cmv_basetable_2`.`c`, sum(`cmv_basetable_2`.`d`)
+ FROM `default`.`cmv_basetable` JOIN `default`.`cmv_basetable_2` ON (`cmv_basetable`.`a` = `cmv_basetable_2`.`a`)
+ WHERE `cmv_basetable_2`.`c` > 10.0
+ GROUP BY `cmv_basetable`.`a`, `cmv_basetable_2`.`c`
+View Rewrite Enabled: Yes
+PREHOOK: query: EXPLAIN
+SELECT cmv_basetable.a, sum(cmv_basetable_2.d)
+FROM cmv_basetable join cmv_basetable_2 ON (cmv_basetable.a = cmv_basetable_2.a)
+WHERE cmv_basetable_2.c > 10.10
+GROUP BY cmv_basetable.a, cmv_basetable_2.c
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN
+SELECT cmv_basetable.a, sum(cmv_basetable_2.d)
+FROM cmv_basetable join cmv_basetable_2 ON (cmv_basetable.a = cmv_basetable_2.a)
+WHERE cmv_basetable_2.c > 10.10
+GROUP BY cmv_basetable.a, cmv_basetable_2.c
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Tez
+#### A masked pattern was here ####
+ Edges:
+ Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE)
+ Reducer 3 <- Reducer 2 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: cmv_basetable
+ Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: a is not null (type: boolean)
+ Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: a (type: int)
+ outputColumnNames: _col0
+ Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE
+ Execution mode: llap
+ LLAP IO: may be used (ACID table)
+ Map 4
+ Map Operator Tree:
+ TableScan
+ alias: cmv_basetable_2
+ Statistics: Num rows: 3 Data size: 360 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: ((c > 10.1) and a is not null) (type: boolean)
+ Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: a (type: int), c (type: decimal(10,2)), d (type: int)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col1 (type: decimal(10,2)), _col2 (type: int)
+ Execution mode: llap
+ LLAP IO: may be used (ACID table)
+ Reducer 2
+ Execution mode: llap
+ Reduce Operator Tree:
+ Merge Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: int)
+ 1 _col0 (type: int)
+ outputColumnNames: _col0, _col2, _col3
+ Statistics: Num rows: 2 Data size: 240 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: sum(_col3)
+ keys: _col0 (type: int), _col2 (type: decimal(10,2))
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 124 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: int), _col1 (type: decimal(10,2))
+ sort order: ++
+ Map-reduce partition columns: _col0 (type: int), _col1 (type: decimal(10,2))
+ Statistics: Num rows: 1 Data size: 124 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col2 (type: bigint)
+ Reducer 3
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: sum(VALUE._col0)
+ keys: KEY._col0 (type: int), KEY._col1 (type: decimal(10,2))
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 124 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col0 (type: int), _col2 (type: bigint)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: SELECT cmv_basetable.a, sum(cmv_basetable_2.d)
+FROM cmv_basetable JOIN cmv_basetable_2 ON (cmv_basetable.a = cmv_basetable_2.a)
+WHERE cmv_basetable_2.c > 10.10
+GROUP BY cmv_basetable.a, cmv_basetable_2.c
+PREHOOK: type: QUERY
+PREHOOK: Input: default@cmv_basetable
+PREHOOK: Input: default@cmv_basetable_2
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT cmv_basetable.a, sum(cmv_basetable_2.d)
+FROM cmv_basetable JOIN cmv_basetable_2 ON (cmv_basetable.a = cmv_basetable_2.a)
+WHERE cmv_basetable_2.c > 10.10
+GROUP BY cmv_basetable.a, cmv_basetable_2.c
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@cmv_basetable
+POSTHOOK: Input: default@cmv_basetable_2
+#### A masked pattern was here ####
+3 2
+3 6
+1 2
+PREHOOK: query: EXPLAIN
+ALTER MATERIALIZED VIEW cmv_mat_view REBUILD
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN
+ALTER MATERIALIZED VIEW cmv_mat_view REBUILD
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-2 is a root stage
+ Stage-3 depends on stages: Stage-2
+ Stage-0 depends on stages: Stage-3
+ Stage-4 depends on stages: Stage-0
+ Stage-6 depends on stages: Stage-4, Stage-5
+ Stage-1 depends on stages: Stage-3
+ Stage-5 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-2
+ Tez
+#### A masked pattern was here ####
+ Edges:
+ Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 7 (ONE_TO_ONE_EDGE)
+ Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE)
+ Reducer 4 <- Reducer 2 (SIMPLE_EDGE)
+ Reducer 6 <- Map 5 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE)
+ Reducer 7 <- Reducer 6 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: default.cmv_mat_view
+ Statistics: Num rows: 2 Data size: 248 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: ((c > 10) and a is not null) (type: boolean)
+ Statistics: Num rows: 1 Data size: 124 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: a (type: int), c (type: decimal(10,2)), _c2 (type: bigint), ROW__ID (type: struct<writeid:bigint,bucketid:int,rowid:bigint>)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: int), _col1 (type: decimal(10,2))
+ sort order: ++
+ Map-reduce partition columns: _col0 (type: int), _col1 (type: decimal(10,2))
+ Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col2 (type: bigint), _col3 (type: struct<writeid:bigint,bucketid:int,rowid:bigint>)
+ Execution mode: llap
+ LLAP IO: may be used (ACID table)
+ Map 5
+ Map Operator Tree:
+ TableScan
+ alias: cmv_basetable
+ Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: a is not null (type: boolean)
+ Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: a (type: int)
+ outputColumnNames: _col0
+ Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE
+ Execution mode: llap
+ LLAP IO: may be used (ACID table)
+ Map 8
+ Map Operator Tree:
+ TableScan
+ alias: cmv_basetable_2
+ Statistics: Num rows: 3 Data size: 360 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: ((ROW__ID.writeid > 1) and (c > 10) and a is not null) (type: boolean)
+ Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: a (type: int), c (type: decimal(10,2)), d (type: int)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 196 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 1 Data size: 196 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col1 (type: decimal(10,2)), _col2 (type: int)
+ Execution mode: llap
+ LLAP IO: may be used (ACID table)
+ Reducer 2
+ Execution mode: llap
+ Reduce Operator Tree:
+ Merge Join Operator
+ condition map:
+ Right Outer Join 0 to 1
+ keys:
+ 0 _col0 (type: int), _col1 (type: decimal(10,2))
+ 1 _col0 (type: int), _col1 (type: decimal(10,2))
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6
+ Statistics: Num rows: 1 Data size: 324 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: (_col0 is null and _col1 is null) (type: boolean)
+ Statistics: Num rows: 1 Data size: 324 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col4 (type: int), _col5 (type: decimal(10,2)), CASE WHEN ((_col0 is null and _col1 is null)) THEN (_col6) ELSE ((_col6 + _col2)) END (type: bigint)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 124 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 124 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.cmv_mat_view
+ Write Type: INSERT
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: decimal(10,2)), _col2 (type: bigint)
+ outputColumnNames: a, c, _c2
+ Statistics: Num rows: 1 Data size: 124 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: compute_stats(a, 'hll'), compute_stats(c, 'hll'), compute_stats(_c2, 'hll')
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 1480 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 1480 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,min:decimal(10,2),max:decimal(10,2),countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>)
+ Filter Operator
+ predicate: ((_col0 = _col4) and (_col1 = _col5)) (type: boolean)
+ Statistics: Num rows: 1 Data size: 324 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col3 (type: struct<writeid:bigint,bucketid:int,rowid:bigint>), _col4 (type: int), _col5 (type: decimal(10,2)), CASE WHEN ((_col0 is null and _col1 is null)) THEN (_col6) ELSE ((_col6 + _col2)) END (type: bigint)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: struct<writeid:bigint,bucketid:int,rowid:bigint>)
+ sort order: +
+ Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col1 (type: int), _col2 (type: decimal(10,2)), _col3 (type: bigint)
+ Reducer 3
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 1528 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 1528 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ Reducer 4
+ Execution mode: llap
+ Reduce Operator Tree:
+ Select Operator
+ expressions: KEY.reducesinkkey0 (type: struct<writeid:bigint,bucketid:int,rowid:bigint>), VALUE._col0 (type: int), VALUE._col1 (type: decimal(10,2)), VALUE._col2 (type: bigint)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 200 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.cmv_mat_view
+ Write Type: UPDATE
+ Reducer 6
+ Execution mode: llap
+ Reduce Operator Tree:
+ Merge Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: int)
+ 1 _col0 (type: int)
+ outputColumnNames: _col0, _col2, _col3
+ Statistics: Num rows: 2 Data size: 240 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: sum(_col3)
+ keys: _col0 (type: int), _col2 (type: decimal(10,2))
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 124 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: int), _col1 (type: decimal(10,2))
+ sort order: ++
+ Map-reduce partition columns: _col0 (type: int), _col1 (type: decimal(10,2))
+ Statistics: Num rows: 1 Data size: 124 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col2 (type: bigint)
+ Reducer 7
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: sum(VALUE._col0)
+ keys: KEY._col0 (type: int), KEY._col1 (type: decimal(10,2))
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 124 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: int), _col1 (type: decimal(10,2))
+ sort order: ++
+ Map-reduce partition columns: _col0 (type: int), _col1 (type: decimal(10,2))
+ Statistics: Num rows: 1 Data size: 124 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col2 (type: bigint)
+
+ Stage: Stage-3
+ Dependency Collection
+
+ Stage: Stage-0
+ Move Operator
+ tables:
+ replace: 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.cmv_mat_view
+ Write Type: INSERT
+
+ Stage: Stage-4
+ Stats Work
+ Basic Stats Work:
+
+ Stage: Stage-6
+ Materialized View Work
+
+ Stage: Stage-1
+ Move Operator
+ tables:
+ replace: 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.cmv_mat_view
+ Write Type: UPDATE
+
+ Stage: Stage-5
+ Stats Work
+ Basic Stats Work:
+ Column Stats Desc:
+ Columns: a, c, _c2
+ Column Types: int, decimal(10,2), bigint
+ Table: default.cmv_mat_view
+
+PREHOOK: query: ALTER MATERIALIZED VIEW cmv_mat_view REBUILD
+PREHOOK: type: QUERY
+PREHOOK: Input: default@cmv_basetable
+PREHOOK: Input: default@cmv_basetable_2
+PREHOOK: Input: default@cmv_mat_view
+PREHOOK: Output: default@cmv_mat_view
+PREHOOK: Output: default@cmv_mat_view
+POSTHOOK: query: ALTER MATERIALIZED VIEW cmv_mat_view REBUILD
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@cmv_basetable
+POSTHOOK: Input: default@cmv_basetable_2
+POSTHOOK: Input: default@cmv_mat_view
+POSTHOOK: Output: default@cmv_mat_view
+POSTHOOK: Output: default@cmv_mat_view
+POSTHOOK: Lineage: cmv_mat_view._c2 EXPRESSION [(cmv_mat_view)default.cmv_mat_view.FieldSchema(name:a, type:int, comment:null), (cmv_mat_view)default.cmv_mat_view.FieldSchema(name:c, type:decimal(10,2), comment:null), (cmv_basetable_2)cmv_basetable_2.FieldSchema(name:d, type:int, comment:null), (cmv_mat_view)default.cmv_mat_view.FieldSchema(name:_c2, type:bigint, comment:null), ]
+POSTHOOK: Lineage: cmv_mat_view.a SIMPLE [(cmv_basetable)cmv_basetable.FieldSchema(name:a, type:int, comment:null), ]
+POSTHOOK: Lineage: cmv_mat_view.c SIMPLE [(cmv_basetable_2)cmv_basetable_2.FieldSchema(name:c, type:decimal(10,2), comment:null), ]
+PREHOOK: query: DESCRIBE FORMATTED cmv_mat_view
+PREHOOK: type: DESCTABLE
+PREHOOK: Input: default@cmv_mat_view
+POSTHOOK: query: DESCRIBE FORMATTED cmv_mat_view
+POSTHOOK: type: DESCTABLE
+POSTHOOK: Input: default@cmv_mat_view
+# col_name data_type comment
+a int
+c decimal(10,2)
+_c2 bigint
+
+# Detailed Table Information
+Database: default
+#### A masked pattern was here ####
+Retention: 0
+#### A masked pattern was here ####
+Table Type: MATERIALIZED_VIEW
+Table Parameters:
+ numFiles 3
+ totalSize 1453
+ transactional true
+ transactional_properties default
+#### 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: []
+
+# View Information
+View Original Text: SELECT cmv_basetable.a, cmv_basetable_2.c, sum(cmv_basetable_2.d)
+ FROM cmv_basetable JOIN cmv_basetable_2 ON (cmv_basetable.a = cmv_basetable_2.a)
+ WHERE cmv_basetable_2.c > 10.0
+ GROUP BY cmv_basetable.a, cmv_basetable_2.c
+View Expanded Text: SELECT `cmv_basetable`.`a`, `cmv_basetable_2`.`c`, sum(`cmv_basetable_2`.`d`)
+ FROM `default`.`cmv_basetable` JOIN `default`.`cmv_basetable_2` ON (`cmv_basetable`.`a` = `cmv_basetable_2`.`a`)
+ WHERE `cmv_basetable_2`.`c` > 10.0
+ GROUP BY `cmv_basetable`.`a`, `cmv_basetable_2`.`c`
+View Rewrite Enabled: Yes
+PREHOOK: query: EXPLAIN
+SELECT cmv_basetable.a, sum(cmv_basetable_2.d)
+FROM cmv_basetable join cmv_basetable_2 ON (cmv_basetable.a = cmv_basetable_2.a)
+WHERE cmv_basetable_2.c > 10.10
+GROUP BY cmv_basetable.a, cmv_basetable_2.c
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN
+SELECT cmv_basetable.a, sum(cmv_basetable_2.d)
+FROM cmv_basetable join cmv_basetable_2 ON (cmv_basetable.a = cmv_basetable_2.a)
+WHERE cmv_basetable_2.c > 10.10
+GROUP BY cmv_basetable.a, cmv_basetable_2.c
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ TableScan
+ alias: default.cmv_mat_view
+ Filter Operator
+ predicate: (c > 10.1) (type: boolean)
+ Select Operator
+ expressions: a (type: int), _c2 (type: bigint)
+ outputColumnNames: _col0, _col1
+ ListSink
+
+PREHOOK: query: SELECT cmv_basetable.a, sum(cmv_basetable_2.d)
+FROM cmv_basetable JOIN cmv_basetable_2 ON (cmv_basetable.a = cmv_basetable_2.a)
+WHERE cmv_basetable_2.c > 10.10
+GROUP BY cmv_basetable.a, cmv_basetable_2.c
+PREHOOK: type: QUERY
+PREHOOK: Input: default@cmv_basetable
+PREHOOK: Input: default@cmv_basetable_2
+PREHOOK: Input: default@cmv_mat_view
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT cmv_basetable.a, sum(cmv_basetable_2.d)
+FROM cmv_basetable JOIN cmv_basetable_2 ON (cmv_basetable.a = cmv_basetable_2.a)
+WHERE cmv_basetable_2.c > 10.10
+GROUP BY cmv_basetable.a, cmv_basetable_2.c
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@cmv_basetable
+POSTHOOK: Input: default@cmv_basetable_2
+POSTHOOK: Input: default@cmv_mat_view
+#### A masked pattern was here ####
+3 6
+1 2
+3 2
+PREHOOK: query: UPDATE cmv_basetable_2 SET a=2 WHERE a=1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@cmv_basetable_2
+PREHOOK: Output: default@cmv_basetable_2
+POSTHOOK: query: UPDATE cmv_basetable_2 SET a=2 WHERE a=1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@cmv_basetable_2
+POSTHOOK: Output: default@cmv_basetable_2
+PREHOOK: query: EXPLAIN
+ALTER MATERIALIZED VIEW cmv_mat_view REBUILD
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN
+ALTER MATERIALIZED VIEW cmv_mat_view REBUILD
+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-4 depends on stages: Stage-3
+
+STAGE PLANS:
+ Stage: Stage-1
+ Tez
+#### A masked pattern was here ####
+ Edges:
+ Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE)
+ Reducer 3 <- Reducer 2 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: cmv_basetable
+ Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: a is not null (type: boolean)
+ Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: a (type: int)
+ outputColumnNames: _col0
+ Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE
+ Execution mode: llap
+ LLAP IO: may be used (ACID table)
+ Map 4
+ Map Operator Tree:
+ TableScan
+ alias: cmv_basetable_2
+ Statistics: Num rows: 60 Data size: 7200 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: ((c > 10) and a is not null) (type: boolean)
+ Statistics: Num rows: 20 Data size: 2400 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: a (type: int), c (type: decimal(10,2)), d (type: int)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 20 Data size: 2400 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 20 Data size: 2400 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col1 (type: decimal(10,2)), _col2 (type: int)
+ Execution mode: llap
+ LLAP IO: may be used (ACID table)
+ Reducer 2
+ Execution mode: llap
+ Reduce Operator Tree:
+ Merge Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: int)
+ 1 _col0 (type: int)
+ outputColumnNames: _col0, _col2, _col3
+ Statistics: Num rows: 33 Data size: 3960 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: sum(_col3)
+ keys: _col0 (type: int), _col2 (type: decimal(10,2))
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 124 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: int), _col1 (type: decimal(10,2))
+ sort order: ++
+ Map-reduce partition columns: _col0 (type: int), _col1 (type: decimal(10,2))
+ Statistics: Num rows: 1 Data size: 124 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col2 (type: bigint)
+ Reducer 3
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: sum(VALUE._col0)
+ keys: KEY._col0 (type: int), KEY._col1 (type: decimal(10,2))
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 124 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 124 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.cmv_mat_view
+ Write Type: INSERT
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: decimal(10,2)), _col2 (type: bigint)
+ outputColumnNames: a, c, _c2
+ Statistics: Num rows: 1 Data size: 124 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: compute_stats(a, 'hll'), compute_stats(c, 'hll'), compute_stats(_c2, 'hll')
+ mode: complete
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 1480 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col1 (type: struct<columntype:string,min:decimal(10,2),max:decimal(10,2),countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col2 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 1480 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 1480 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-2
+ Dependency Collection
+
+ Stage: Stage-0
+ Move Operator
+ tables:
+ replace: 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.cmv_mat_view
+ Write Type: INSERT
+
+ Stage: Stage-3
+ Stats Work
+ Basic Stats Work:
+ Column Stats Desc:
+ Columns: a, c, _c2
+ Column Types: int, decimal(10,2), bigint
+ Table: default.cmv_mat_view
+
+ Stage: Stage-4
+ Materialized View Work
+
+PREHOOK: query: ALTER MATERIALIZED VIEW cmv_mat_view REBUILD
+PREHOOK: type: QUERY
+PREHOOK: Input: default@cmv_basetable
+PREHOOK: Input: default@cmv_basetable_2
+PREHOOK: Output: default@cmv_mat_view
+POSTHOOK: query: ALTER MATERIALIZED VIEW cmv_mat_view REBUILD
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@cmv_basetable
+POSTHOOK: Input: default@cmv_basetable_2
+POSTHOOK: Output: default@cmv_mat_view
+POSTHOOK: Lineage: cmv_mat_view._c2 EXPRESSION [(cmv_basetable_2)cmv_basetable_2.FieldSchema(name:d, type:int, comment:null), ]
+POSTHOOK: Lineage: cmv_mat_view.a SIMPLE [(cmv_basetable)cmv_basetable.FieldSchema(name:a, type:int, comment:null), ]
+POSTHOOK: Lineage: cmv_mat_view.c SIMPLE [(cmv_basetable_2)cmv_basetable_2.FieldSchema(name:c, type:decimal(10,2), comment:null), ]
+PREHOOK: query: EXPLAIN
+SELECT cmv_basetable.a, sum(cmv_basetable_2.d)
+FROM cmv_basetable join cmv_basetable_2 ON (cmv_basetable.a = cmv_basetable_2.a)
+WHERE cmv_basetable_2.c > 10.10
+GROUP BY cmv_basetable.a, cmv_basetable_2.c
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN
+SELECT cmv_basetable.a, sum(cmv_basetable_2.d)
+FROM cmv_basetable join cmv_basetable_2 ON (cmv_basetable.a = cmv_basetable_2.a)
+WHERE cmv_basetable_2.c > 10.10
+GROUP BY cmv_basetable.a, cmv_basetable_2.c
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ TableScan
+ alias: default.cmv_mat_view
+ Filter Operator
+ predicate: (c > 10.1) (type: boolean)
+ Select Operator
+ expressions: a (type: int), _c2 (type: bigint)
+ outputColumnNames: _col0, _col1
+ ListSink
+
+PREHOOK: query: SELECT cmv_basetable.a, sum(cmv_basetable_2.d)
+FROM cmv_basetable JOIN cmv_basetable_2 ON (cmv_basetable.a = cmv_basetable_2.a)
+WHERE cmv_basetable_2.c > 10.10
+GROUP BY cmv_basetable.a, cmv_basetable_2.c
+PREHOOK: type: QUERY
+PREHOOK: Input: default@cmv_basetable
+PREHOOK: Input: default@cmv_basetable_2
+PREHOOK: Input: default@cmv_mat_view
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT cmv_basetable.a, sum(cmv_basetable_2.d)
+FROM cmv_basetable JOIN cmv_basetable_2 ON (cmv_basetable.a = cmv_basetable_2.a)
+WHERE cmv_basetable_2.c > 10.10
+GROUP BY cmv_basetable.a, cmv_basetable_2.c
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@cmv_basetable
+POSTHOOK: Input: default@cmv_basetable_2
+POSTHOOK: Input: default@cmv_mat_view
+#### A masked pattern was here ####
+2 4
+3 2
+3 6
+PREHOOK: query: DELETE FROM cmv_basetable_2 WHERE a=2
+PREHOOK: type: QUERY
+PREHOOK: Input: default@cmv_basetable_2
+PREHOOK: Output: default@cmv_basetable_2
+POSTHOOK: query: DELETE FROM cmv_basetable_2 WHERE a=2
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@cmv_basetable_2
+POSTHOOK: Output: default@cmv_basetable_2
+PREHOOK: query: EXPLAIN
+ALTER MATERIALIZED VIEW cmv_mat_view REBUILD
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN
+ALTER MATERIALIZED VIEW cmv_mat_view REBUILD
+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-4 depends on stages: Stage-3
+
+STAGE PLANS:
+ Stage: Stage-1
+ Tez
+#### A masked pattern was here ####
+ Edges:
+ Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE)
+ Reducer 3 <- Reducer 2 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: cmv_basetable
+ Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: a is not null (type: boolean)
+ Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: a (type: int)
+ outputColumnNames: _col0
+ Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE
+ Execution mode: llap
+ LLAP IO: may be used (ACID table)
+ Map 4
+ Map Operator Tree:
+ TableScan
+ alias: cmv_basetable_2
+ Statistics: Num rows: 70 Data size: 8400 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: ((c > 10) and a is not null) (type: boolean)
+ Statistics: Num rows: 23 Data size: 2760 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: a (type: int), c (type: decimal(10,2)), d (type: int)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 23 Data size: 2760 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 23 Data size: 2760 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col1 (type: decimal(10,2)), _col2 (type: int)
+ Execution mode: llap
+ LLAP IO: may be used (ACID table)
+ Reducer 2
+ Execution mode: llap
+ Reduce Operator Tree:
+ Merge Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: int)
+ 1 _col0 (type: int)
+ outputColumnNames: _col0, _col2, _col3
+ Statistics: Num rows: 38 Data size: 4560 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: sum(_col3)
+ keys: _col0 (type: int), _col2 (type: decimal(10,2))
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 124 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: int), _col1 (type: decimal(10,2))
+ sort order: ++
+ Map-reduce partition columns: _col0 (type: int), _col1 (type: decimal(10,2))
+ Statistics: Num rows: 1 Data size: 124 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col2 (type: bigint)
+ Reducer 3
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: sum(VALUE._col0)
+ keys: KEY._col0 (type: int), KEY._col1 (type: decimal(10,2))
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 124 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 124 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.cmv_mat_view
+ Write Type: INSERT
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: decimal(10,2)), _col2 (type: bigint)
+ outputColumnNames: a, c, _c2
+ Statistics: Num rows: 1 Data size: 124 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: compute_stats(a, 'hll'), compute_stats(c, 'hll'), compute_stats(_c2, 'hll')
+ mode: complete
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 1480 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col1 (type: struct<columntype:string,min:decimal(10,2),max:decimal(10,2),countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col2 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 1480 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 1480 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-2
+ Dependency Collection
+
+ Stage: Stage-0
+ Move Operator
+ tables:
+ replace: 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.cmv_mat_view
+ Write Type: INSERT
+
+ Stage: Stage-3
+ Stats Work
+ Basic Stats Work:
+ Column Stats Desc:
+ Columns: a, c, _c2
+ Column Types: int, decimal(10,2), bigint
+ Table: default.cmv_mat_view
+
+ Stage: Stage-4
+ Materialized View Work
+
+PREHOOK: query: ALTER MATERIALIZED VIEW cmv_mat_view REBUILD
+PREHOOK: type: QUERY
+PREHOOK: Input: default@cmv_basetable
+PREHOOK: Input: default@cmv_basetable_2
+PREHOOK: Output: default@cmv_mat_view
+POSTHOOK: query: ALTER MATERIALIZED VIEW cmv_mat_view REBUILD
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@cmv_basetable
+POSTHOOK: Input: default@cmv_basetable_2
+POSTHOOK: Output: default@cmv_mat_view
+POSTHOOK: Lineage: cmv_mat_view._c2 EXPRESSION [(cmv_basetable_2)cmv_basetable_2.FieldSchema(name:d, type:int, comment:null), ]
+POSTHOOK: Lineage: cmv_mat_view.a SIMPLE [(cmv_basetable)cmv_basetable.FieldSchema(name:a, type:int, comment:null), ]
+POSTHOOK: Lineage: cmv_mat_view.c SIMPLE [(cmv_basetable_2)cmv_basetable_2.FieldSchema(name:c, type:decimal(10,2), comment:null), ]
+PREHOOK: query: EXPLAIN
+SELECT cmv_basetable.a, sum(cmv_basetable_2.d)
+FROM cmv_basetable join cmv_basetable_2 ON (cmv_basetable.a = cmv_basetable_2.a)
+WHERE cmv_basetable_2.c > 10.10
+GROUP BY cmv_basetable.a, cmv_basetable_2.c
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN
+SELECT cmv_basetable.a, sum(cmv_basetable_2.d)
+FROM cmv_basetable join cmv_basetable_2 ON (cmv_basetable.a = cmv_basetable_2.a)
+WHERE cmv_basetable_2.c > 10.10
+GROUP BY cmv_basetable.a, cmv_basetable_2.c
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ TableScan
+ alias: default.cmv_mat_view
+ Filter Operator
+ predicate: (c > 10.1) (type: boolean)
+ Select Operator
+ expressions: a (type: int), _c2 (type: bigint)
+ outputColumnNames: _col0, _col1
+ ListSink
+
+PREHOOK: query: SELECT cmv_basetable.a, sum(cmv_basetable_2.d)
+FROM cmv_basetable JOIN cmv_basetable_2 ON (cmv_basetable.a = cmv_basetable_2.a)
+WHERE cmv_basetable_2.c > 10.10
+GROUP BY cmv_basetable.a, cmv_basetable_2.c
+PREHOOK: type: QUERY
+PREHOOK: Input: default@cmv_basetable
+PREHOOK: Input: default@cmv_basetable_2
+PREHOOK: Input: default@cmv_mat_view
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT cmv_basetable.a, sum(cmv_basetable_2.d)
+FROM cmv_basetable JOIN cmv_basetable_2 ON (cmv_basetable.a = cmv_basetable_2.a)
+WHERE cmv_basetable_2.c > 10.10
+GROUP BY cmv_basetable.a, cmv_basetable_2.c
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@cmv_basetable
+POSTHOOK: Input: default@cmv_basetable_2
+POSTHOOK: Input: default@cmv_mat_view
+#### A masked pattern was here ####
+3 2
+3 6
+PREHOOK: query: insert into cmv_basetable_2 values
+ (1, 'charlie', 15.8, 1)
+PREHOOK: type: QUERY
+PREHOOK: Input: _dummy_database@_dummy_table
+PREHOOK: Output: default@cmv_basetable_2
+POSTHOOK: query: insert into cmv_basetable_2 values
+ (1, 'charlie', 15.8, 1)
+POSTHOOK: type: QUERY
+POSTHOOK: Input: _dummy_database@_dummy_table
+POSTHOOK: Output: default@cmv_basetable_2
+POSTHOOK: Lineage: cmv_basetable_2.a SCRIPT []
+POSTHOOK: Lineage: cmv_basetable_2.b SCRIPT []
+POSTHOOK: Lineage: cmv_basetable_2.c SCRIPT []
+POSTHOOK: Lineage: cmv_basetable_2.d SCRIPT []
+PREHOOK: query: EXPLAIN
+ALTER MATERIALIZED VIEW cmv_mat_view REBUILD
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN
+ALTER MATERIALIZED VIEW cmv_mat_view REBUILD
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-2 is a root stage
+ Stage-3 depends on stages: Stage-2
+ Stage-0 depends on stages: Stage-3
+ Stage-4 depends on stages: Stage-0
+ Stage-6 depends on stages: Stage-4, Stage-5
+ Stage-1 depends on stages: Stage-3
+ Stage-5 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-2
+ Tez
+#### A masked pattern was here ####
+ Edges:
+ Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 7 (ONE_TO_ONE_EDGE)
+ Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE)
+ Reducer 4 <- Reducer 2 (SIMPLE_EDGE)
+ Reducer 6 <- Map 5 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE)
+ Reducer 7 <- Reducer 6 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: default.cmv_mat_view
+ Statistics: Num rows: 2 Data size: 248 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: ((c > 10) and a is not null) (type: boolean)
+ Statistics: Num rows: 1 Data size: 124 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: a (type: int), c (type: decimal(10,2)), _c2 (type: bigint), ROW__ID (type: struct<writeid:bigint,bucketid:int,rowid:bigint>)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: int), _col1 (type: decimal(10,2))
+ sort order: ++
+ Map-reduce partition columns: _col0 (type: int), _col1 (type: decimal(10,2))
+ Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col2 (type: bigint), _col3 (type: struct<writeid:bigint,bucketid:int,rowid:bigint>)
+ Execution mode: llap
+ LLAP IO: may be used (ACID table)
+ Map 5
+ Map Operator Tree:
+ TableScan
+ alias: cmv_basetable
+ Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: a is not null (type: boolean)
+ Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: a (type: int)
+ outputColumnNames: _col0
+ Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE
+ Execution mode: llap
+ LLAP IO: may be used (ACID table)
+ Map 8
+ Map Operator Tree:
+ TableScan
+ alias: cmv_basetable_2
+ Statistics: Num rows: 85 Data size: 10200 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: ((ROW__ID.writeid > 4) and (c > 10) and a is not null) (type: boolean)
+ Statistics: Num rows: 9 Data size: 1080 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: a (type: int), c (type: decimal(10,2)), d (type: int)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 9 Data size: 1764 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 9 Data size: 1764 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col1 (type: decimal(10,2)), _col2 (type: int)
+ Execution mode: llap
+ LLAP IO: may be used (ACID table)
+ Reducer 2
+ Execution mode: llap
+ Reduce Operator Tree:
+ Merge Join Operator
+ condition map:
+ Right Outer Join 0 to 1
+ keys:
+ 0 _col0 (type: int), _col1 (type: decimal(10,2))
+ 1 _col0 (type: int), _col1 (type: decimal(10,2))
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6
+ Statistics: Num rows: 1 Data size: 324 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: (_col0 is null and _col1 is null) (type: boolean)
+ Statistics: Num rows: 1 Data size: 324 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col4 (type: int), _col5 (type: decimal(10,2)), CASE WHEN ((_col0 is null and _col1 is null)) THEN (_col6) ELSE ((_col6 + _col2)) END (type: bigint)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 124 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 124 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.cmv_mat_view
+ Write Type: INSERT
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: decimal(10,2)), _col2 (type: bigint)
+ outputColumnNames: a, c, _c2
+ Statistics: Num rows: 1 Data size: 124 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: compute_stats(a, 'hll'), compute_stats(c, 'hll'), compute_stats(_c2, 'hll')
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 1480 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 1480 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,min:decimal(10,2),max:decimal(10,2),countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>)
+ Filter Operator
+ predicate: ((_col0 = _col4) and (_col1 = _col5)) (type: boolean)
+ Statistics: Num rows: 1 Data size: 324 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col3 (type: struct<writeid:bigint,bucketid:int,rowid:bigint>), _col4 (type: int), _col5 (type: decimal(10,2)), CASE WHEN ((_col0 is null and _col1 is null)) THEN (_col6) ELSE ((_col6 + _col2)) END (type: bigint)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: struct<writeid:bigint,bucketid:int,rowid:bigint>)
+ sort order: +
+ Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col1 (type: int), _col2 (type: decimal(10,2)), _col3 (type: bigint)
+ Reducer 3
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 1528 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 1528 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ Reducer 4
+ Execution mode: llap
+ Reduce Operator Tree:
+ Select Operator
+ expressions: KEY.reducesinkkey0 (type: struct<writeid:bigint,bucketid:int,rowid:bigint>), VALUE._col0 (type: int), VALUE._col1 (type: decimal(10,2)), VALUE._col2 (type: bigint)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 200 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.cmv_mat_view
+ Write Type: UPDATE
+ Reducer 6
+ Execution mode: llap
+ Reduce Operator Tree:
+ Merge Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: int)
+ 1 _col0 (type: int)
+ outputColumnNames: _col0, _col2, _col3
+ Statistics: Num rows: 15 Data size: 1800 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: sum(_col3)
+ keys: _col0 (type: int), _col2 (type: decimal(10,2))
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 124 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: int), _col1 (type: decimal(10,2))
+ sort order: ++
+ Map-reduce partition columns: _col0 (type: int), _col1 (type: decimal(10,2))
+ Statistics: Num rows: 1 Data size: 124 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col2 (type: bigint)
+ Reducer 7
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: sum(VALUE._col0)
+ keys: KEY._col0 (type: int), KEY._col1 (type: decimal(10,2))
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 124 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: int), _col1 (type: decimal(10,2))
+ sort order: ++
+ Map-reduce partition columns: _col0 (type: int), _col1 (type: decimal(10,2))
+ Statistics: Num rows: 1 Data size: 124 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col2 (type: bigint)
+
+ Stage: Stage-3
+ Dependency Collection
+
+ Stage: Stage-0
+ Move Operator
+ tables:
+ replace: 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.cmv_mat_view
+ Write Type: INSERT
+
+ Stage: Stage-4
+ Stats Work
+ Basic Stats Work:
+
+ Stage: Stage-6
+ Materialized View Work
+
+ Stage: Stage-1
+ Move Operator
+ tables:
+ replace: 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.cmv_mat_view
+ Write Type: UPDATE
+
+ Stage: Stage-5
+ Stats Work
+ Basic Stats Work:
+ Column Stats Desc:
+ Columns: a, c, _c2
+ Column Types: int, decimal(10,2), bigint
+ Table: default.cmv_mat_view
+
+PREHOOK: query: ALTER MATERIALIZED VIEW cmv_mat_view REBUILD
+PREHOOK: type: QUERY
+PREHOOK: Input: default@cmv_basetable
+PREHOOK: Input: default@cmv_basetable_2
+PREHOOK: Input: default@cmv_mat_view
+PREHOOK: Output: default@cmv_mat_view
+PREHOOK: Output: default@cmv_mat_view
+POSTHOOK: query: ALTER MATERIALIZED VIEW cmv_mat_view REBUILD
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@cmv_basetable
+POSTHOOK: Input: default@cmv_basetable_2
+POSTHOOK: Input: default@cmv_mat_view
+POSTHOOK: Output: default@cmv_mat_view
+POSTHOOK: Output: default@cmv_mat_view
+POSTHOOK: Lineage: cmv_mat_view._c2 EXPRESSION [(cmv_mat_view)default.cmv_mat_view.FieldSchema(name:a, type:int, comment:null), (cmv_mat_view)default.cmv_mat_view.FieldSchema(name:c, type:decimal(10,2), comment:null), (cmv_basetable_2)cmv_basetable_2.FieldSchema(name:d, type:int, comment:null), (cmv_mat_view)default.cmv_mat_view.FieldSchema(name:_c2, type:bigint, comment:null), ]
+POSTHOOK: Lineage: cmv_mat_view.a SIMPLE [(cmv_basetable)cmv_basetable.FieldSchema(name:a, type:int, comment:null), ]
+POSTHOOK: Lineage: cmv_mat_view.c SIMPLE [(cmv_basetable_2)cmv_basetable_2.FieldSchema(name:c, type:decimal(10,2), comment:null), ]
+PREHOOK: query: EXPLAIN
+SELECT cmv_basetable.a, sum(cmv_basetable_2.d)
+FROM cmv_basetable join cmv_basetable_2 ON (cmv_basetable.a = cmv_basetable_2.a)
+WHERE cmv_basetable_2.c > 10.10
+GROUP BY cmv_basetable.a, cmv_basetable_2.c
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN
+SELECT cmv_basetable.a, sum(cmv_basetable_2.d)
+FROM cmv_basetable join cmv_basetable_2 ON (cmv_basetable.a = cmv_basetable_2.a)
+WHERE cmv_basetable_2.c > 10.10
+GROUP BY cmv_basetable.a, cmv_basetable_2.c
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ TableScan
+ alias: default.cmv_mat_view
+ Filter Operator
+ predicate: (c > 10.1) (type: boolean)
+ Select Operator
+ expressions: a (type: int), _c2 (type: bigint)
+ outputColumnNames: _col0, _col1
+ ListSink
+
+PREHOOK: query: SELECT cmv_basetable.a, sum(cmv_basetable_2.d)
+FROM cmv_basetable JOIN cmv_basetable_2 ON (cmv_basetable.a = cmv_basetable_2.a)
+WHERE cmv_basetable_2.c > 10.10
+GROUP BY cmv_basetable.a, cmv_basetable_2.c
+PREHOOK: type: QUERY
+PREHOOK: Input: default@cmv_basetable
+PREHOOK: Input: default@cmv_basetable_2
+PREHOOK: Input: default@cmv_mat_view
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT cmv_basetable.a, sum(cmv_basetable_2.d)
+FROM cmv_basetable JOIN cmv_basetable_2 ON (cmv_basetable.a = cmv_basetable_2.a)
+WHERE cmv_basetable_2.c > 10.10
+GROUP BY cmv_basetable.a, cmv_basetable_2.c
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@cmv_basetable
+POSTHOOK: Input: default@cmv_basetable_2
+POSTHOOK: Input: default@cmv_mat_view
+#### A masked pattern was here ####
+3 2
+3 6
+1 1
+PREHOOK: query: drop materialized view cmv_mat_view
+PREHOOK: type: DROP_MATERIALIZED_VIEW
+PREHOOK: Input: default@cmv_mat_view
+PREHOOK: Output: default@cmv_mat_view
+POSTHOOK: query: drop materialized view cmv_mat_view
+POSTHOOK: type: DROP_MATERIALIZED_VIEW
+POSTHOOK: Input: default@cmv_mat_view
+POSTHOOK: Output: default@cmv_mat_view