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 2019/01/04 00:24:26 UTC
[27/35] hive git commit: HIVE-16957: Support CTAS for auto gather
column stats (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan)
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_2.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_2.q.out b/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_2.q.out
index ce57ec1..82415de 100644
--- a/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_2.q.out
+++ b/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_2.q.out
@@ -28,16 +28,6 @@ POSTHOOK: Lineage: cmv_basetable_n9.a SCRIPT []
POSTHOOK: Lineage: cmv_basetable_n9.b SCRIPT []
POSTHOOK: Lineage: cmv_basetable_n9.c SCRIPT []
POSTHOOK: Lineage: cmv_basetable_n9.d SCRIPT []
-PREHOOK: query: analyze table cmv_basetable_n9 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@cmv_basetable_n9
-PREHOOK: Output: default@cmv_basetable_n9
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table cmv_basetable_n9 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@cmv_basetable_n9
-POSTHOOK: Output: default@cmv_basetable_n9
-#### A masked pattern was here ####
PREHOOK: query: create materialized view cmv_mat_view_n9
as select b from cmv_basetable_n9 where c > 10.0 group by a, b, c
PREHOOK: type: CREATE_MATERIALIZED_VIEW
@@ -269,24 +259,24 @@ STAGE PLANS:
TableScan
alias: default.cmv_mat_view_3
filterExpr: (c > 20) (type: boolean)
- Statistics: Num rows: 3 Data size: 1368 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 618 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: (c > 20) (type: boolean)
- Statistics: Num rows: 1 Data size: 456 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: a (type: int), b (type: varchar(256))
outputColumnNames: a, b
- Statistics: Num rows: 1 Data size: 456 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: a (type: int), b (type: varchar(256))
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 456 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: varchar(256))
sort order: ++
Map-reduce partition columns: _col0 (type: int), _col1 (type: varchar(256))
- Statistics: Num rows: 1 Data size: 456 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: all inputs
Reducer 2
@@ -296,14 +286,14 @@ STAGE PLANS:
keys: KEY._col0 (type: int), KEY._col1 (type: varchar(256))
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 456 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col1 (type: varchar(256))
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 456 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 90 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 456 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 90 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -367,21 +357,21 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: default.cmv_mat_view_4
- Statistics: Num rows: 5 Data size: 1700 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 450 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: b (type: varchar(256))
outputColumnNames: b
- Statistics: Num rows: 5 Data size: 1700 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 450 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: b (type: varchar(256))
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 5 Data size: 1700 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: varchar(256))
sort order: +
Map-reduce partition columns: _col0 (type: varchar(256))
- Statistics: Num rows: 5 Data size: 1700 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: all inputs
Reducer 2
@@ -391,10 +381,10 @@ STAGE PLANS:
keys: KEY._col0 (type: varchar(256))
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 2 Data size: 680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 2 Data size: 680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -445,16 +435,6 @@ POSTHOOK: Lineage: cmv_basetable_2_n4.a SCRIPT []
POSTHOOK: Lineage: cmv_basetable_2_n4.b SCRIPT []
POSTHOOK: Lineage: cmv_basetable_2_n4.c SCRIPT []
POSTHOOK: Lineage: cmv_basetable_2_n4.d SCRIPT []
-PREHOOK: query: analyze table cmv_basetable_2_n4 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@cmv_basetable_2_n4
-PREHOOK: Output: default@cmv_basetable_2_n4
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table cmv_basetable_2_n4 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@cmv_basetable_2_n4
-POSTHOOK: Output: default@cmv_basetable_2_n4
-#### A masked pattern was here ####
PREHOOK: query: create materialized view cmv_mat_view_5
as select cmv_basetable_n9.a, cmv_basetable_2_n4.c
from cmv_basetable_n9 join cmv_basetable_2_n4 on (cmv_basetable_n9.a = cmv_basetable_2_n4.a)
@@ -570,24 +550,24 @@ STAGE PLANS:
TableScan
alias: default.cmv_mat_view_5
filterExpr: (c > 10.1) (type: boolean)
- Statistics: Num rows: 2 Data size: 232 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 232 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: (c > 10.1) (type: boolean)
- Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: a (type: int)
outputColumnNames: a
- Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: a (type: int)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 4 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: 116 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: all inputs
Reducer 2
@@ -597,10 +577,10 @@ STAGE PLANS:
keys: KEY._col0 (type: int)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_3.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_3.q.out b/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_3.q.out
index 8fcab1f..e8d0657 100644
--- a/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_3.q.out
+++ b/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_3.q.out
@@ -28,16 +28,6 @@ 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: ANALYZE_TABLE
-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: ANALYZE_TABLE
-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
@@ -62,16 +52,6 @@ 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: ANALYZE_TABLE
-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: ANALYZE_TABLE
-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 AS
SELECT cmv_basetable.a, cmv_basetable_2.c
@@ -97,7 +77,7 @@ POSTHOOK: Output: default@cmv_mat_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-4 depends on stages: Stage-0, Stage-2
Stage-3 depends on stages: Stage-4
Stage-5 depends on stages: Stage-3
Stage-0 depends on stages: Stage-1
@@ -107,8 +87,9 @@ STAGE PLANS:
Tez
#### A masked pattern was here ####
Edges:
- Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE)
+ Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE)
Reducer 3 <- Reducer 2 (SIMPLE_EDGE)
+ Reducer 4 <- Reducer 3 (CUSTOM_SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -131,7 +112,7 @@ STAGE PLANS:
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 5
Map Operator Tree:
TableScan
alias: cmv_basetable_2
@@ -189,6 +170,34 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde
name: default.cmv_mat_view
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: decimal(10,2))
+ outputColumnNames: col1, col2
+ Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: compute_stats(col1, 'hll'), compute_stats(col2, 'hll')
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 1056 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 1056 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>)
+ Reducer 4
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 1088 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 1088 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
@@ -211,6 +220,10 @@ STAGE PLANS:
Stage: Stage-3
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: a, c
+ Column Types: int, decimal(10,2)
+ Table: default.cmv_mat_view
Stage: Stage-5
Materialized View Work
@@ -313,16 +326,6 @@ 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: ANALYZE_TABLE
-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: ANALYZE_TABLE
-POSTHOOK: Input: default@cmv_basetable_2
-POSTHOOK: Output: default@cmv_basetable_2
-#### A masked pattern was here ####
PREHOOK: query: EXPLAIN
SELECT cmv_basetable.a
FROM cmv_basetable join cmv_basetable_2 ON (cmv_basetable.a = cmv_basetable_2.a)
@@ -518,10 +521,10 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: cmv_basetable_2
- filterExpr: ((c > 10) and (ROW__ID.writeid > 2) and a is not null) (type: boolean)
+ filterExpr: ((c > 10) and (ROW__ID.writeid > 1) and a is not null) (type: boolean)
Statistics: Num rows: 3 Data size: 348 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: ((ROW__ID.writeid > 2) and (c > 10) and a is not null) (type: boolean)
+ predicate: ((ROW__ID.writeid > 1) and (c > 10) and a is not null) (type: boolean)
Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: a (type: int), c (type: decimal(10,2))
@@ -539,21 +542,21 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: default.cmv_mat_view
- Statistics: Num rows: 2 Data size: 232 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 232 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: a (type: int), c (type: decimal(10,2))
outputColumnNames: _col0, _col1
- Statistics: Num rows: 2 Data size: 232 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 232 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: int), _col1 (type: decimal(10,2))
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 1 Data size: 116 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: 116 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: all inputs
Reducer 2
@@ -589,12 +592,12 @@ STAGE PLANS:
keys: _col0 (type: int), _col1 (type: decimal(10,2))
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 1 Data size: 116 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: 116 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: COMPLETE
Reducer 5
Execution mode: llap
Reduce Operator Tree:
@@ -602,10 +605,10 @@ STAGE PLANS:
keys: KEY._col0 (type: int), KEY._col1 (type: decimal(10,2))
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 1 Data size: 116 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
@@ -614,15 +617,15 @@ STAGE PLANS:
Select Operator
expressions: _col0 (type: int), _col1 (type: decimal(10,2))
outputColumnNames: a, c
- Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: compute_stats(a, 'hll'), compute_stats(c, 'hll')
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 1056 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 1 Data size: 1056 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 1056 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 1 Data size: 1056 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>)
Reducer 6
Execution mode: llap
@@ -631,10 +634,10 @@ STAGE PLANS:
aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 1088 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 1 Data size: 1088 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 1088 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 1 Data size: 1088 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -976,16 +979,6 @@ POSTHOOK: Lineage: cmv_irrelevant_table.a SCRIPT []
POSTHOOK: Lineage: cmv_irrelevant_table.b SCRIPT []
POSTHOOK: Lineage: cmv_irrelevant_table.c SCRIPT []
POSTHOOK: Lineage: cmv_irrelevant_table.d SCRIPT []
-PREHOOK: query: analyze table cmv_irrelevant_table compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@cmv_irrelevant_table
-PREHOOK: Output: default@cmv_irrelevant_table
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table cmv_irrelevant_table compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@cmv_irrelevant_table
-POSTHOOK: Output: default@cmv_irrelevant_table
-#### A masked pattern was here ####
PREHOOK: query: EXPLAIN
SELECT cmv_basetable.a
FROM cmv_basetable join cmv_basetable_2 ON (cmv_basetable.a = cmv_basetable_2.a)
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/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
index 8fe194e..1b42330 100644
--- 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
@@ -28,16 +28,6 @@ POSTHOOK: Lineage: cmv_basetable_n5.a SCRIPT []
POSTHOOK: Lineage: cmv_basetable_n5.b SCRIPT []
POSTHOOK: Lineage: cmv_basetable_n5.c SCRIPT []
POSTHOOK: Lineage: cmv_basetable_n5.d SCRIPT []
-PREHOOK: query: analyze table cmv_basetable_n5 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@cmv_basetable_n5
-PREHOOK: Output: default@cmv_basetable_n5
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table cmv_basetable_n5 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@cmv_basetable_n5
-POSTHOOK: Output: default@cmv_basetable_n5
-#### A masked pattern was here ####
PREHOOK: query: create table cmv_basetable_2_n2 (a int, b varchar(256), c decimal(10,2), d int) stored as orc TBLPROPERTIES ('transactional'='true')
PREHOOK: type: CREATETABLE
PREHOOK: Output: database:default
@@ -62,16 +52,6 @@ POSTHOOK: Lineage: cmv_basetable_2_n2.a SCRIPT []
POSTHOOK: Lineage: cmv_basetable_2_n2.b SCRIPT []
POSTHOOK: Lineage: cmv_basetable_2_n2.c SCRIPT []
POSTHOOK: Lineage: cmv_basetable_2_n2.d SCRIPT []
-PREHOOK: query: analyze table cmv_basetable_2_n2 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@cmv_basetable_2_n2
-PREHOOK: Output: default@cmv_basetable_2_n2
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table cmv_basetable_2_n2 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@cmv_basetable_2_n2
-POSTHOOK: Output: default@cmv_basetable_2_n2
-#### A masked pattern was here ####
PREHOOK: query: EXPLAIN
CREATE MATERIALIZED VIEW cmv_mat_view_n5 DISABLE REWRITE TBLPROPERTIES ('transactional'='true') AS
SELECT cmv_basetable_n5.a, cmv_basetable_2_n2.c, sum(cmv_basetable_2_n2.d)
@@ -97,7 +77,7 @@ POSTHOOK: Output: default@cmv_mat_view_n5
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-4 depends on stages: Stage-0, Stage-2
Stage-3 depends on stages: Stage-4
Stage-5 depends on stages: Stage-3
Stage-0 depends on stages: Stage-1
@@ -192,6 +172,27 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde
name: default.cmv_mat_view_n5
+ Write Type: INSERT
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: decimal(10,2)), _col2 (type: bigint)
+ outputColumnNames: col1, col2, col3
+ Statistics: Num rows: 1 Data size: 124 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: compute_stats(col1, 'hll'), compute_stats(col2, 'hll'), compute_stats(col3, '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
@@ -215,6 +216,10 @@ STAGE PLANS:
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_n5
Stage: Stage-5
Materialized View Work
@@ -224,6 +229,7 @@ STAGE PLANS:
files:
hdfs directory: true
#### A masked pattern was here ####
+ Write Type: INSERT
PREHOOK: query: CREATE MATERIALIZED VIEW cmv_mat_view_n5 DISABLE REWRITE TBLPROPERTIES ('transactional'='true') AS
SELECT cmv_basetable_n5.a, cmv_basetable_2_n2.c, sum(cmv_basetable_2_n2.d)
@@ -245,16 +251,6 @@ POSTHOOK: Input: default@cmv_basetable_2_n2
POSTHOOK: Input: default@cmv_basetable_n5
POSTHOOK: Output: database:default
POSTHOOK: Output: default@cmv_mat_view_n5
-PREHOOK: query: analyze table cmv_mat_view_n5 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@cmv_mat_view_n5
-PREHOOK: Output: default@cmv_mat_view_n5
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table cmv_mat_view_n5 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@cmv_mat_view_n5
-POSTHOOK: Output: default@cmv_mat_view_n5
-#### A masked pattern was here ####
PREHOOK: query: DESCRIBE FORMATTED cmv_mat_view_n5
PREHOOK: type: DESCTABLE
PREHOOK: Input: default@cmv_mat_view_n5
@@ -275,10 +271,10 @@ Table Type: MATERIALIZED_VIEW
Table Parameters:
COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"_c2\":\"true\",\"a\":\"true\",\"c\":\"true\"}}
bucketing_version 2
- numFiles 2
+ numFiles 1
numRows 2
rawDataSize 0
- totalSize 736
+ totalSize 809
transactional true
transactional_properties default
#### A masked pattern was here ####
@@ -457,16 +453,6 @@ POSTHOOK: Lineage: cmv_basetable_2_n2.a SCRIPT []
POSTHOOK: Lineage: cmv_basetable_2_n2.b SCRIPT []
POSTHOOK: Lineage: cmv_basetable_2_n2.c SCRIPT []
POSTHOOK: Lineage: cmv_basetable_2_n2.d SCRIPT []
-PREHOOK: query: analyze table cmv_basetable_2_n2 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@cmv_basetable_2_n2
-PREHOOK: Output: default@cmv_basetable_2_n2
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table cmv_basetable_2_n2 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@cmv_basetable_2_n2
-POSTHOOK: Output: default@cmv_basetable_2_n2
-#### A masked pattern was here ####
PREHOOK: query: EXPLAIN
ALTER MATERIALIZED VIEW cmv_mat_view_n5 ENABLE REWRITE
PREHOOK: type: ALTER_MATERIALIZED_VIEW_REWRITE
@@ -515,10 +501,10 @@ Table Type: MATERIALIZED_VIEW
Table Parameters:
COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"_c2\":\"true\",\"a\":\"true\",\"c\":\"true\"}}
bucketing_version 2
- numFiles 2
+ numFiles 1
numRows 2
rawDataSize 0
- totalSize 736
+ totalSize 809
transactional true
transactional_properties default
#### A masked pattern was here ####
@@ -766,10 +752,10 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: cmv_basetable_2_n2
- filterExpr: ((c > 10) and (ROW__ID.writeid > 2) and a is not null) (type: boolean)
+ filterExpr: ((c > 10) and (ROW__ID.writeid > 1) and a is not null) (type: boolean)
Statistics: Num rows: 3 Data size: 360 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: ((ROW__ID.writeid > 2) and (c > 10) and a is not null) (type: boolean)
+ 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)
@@ -983,10 +969,10 @@ Table Type: MATERIALIZED_VIEW
Table Parameters:
COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
bucketing_version 2
- numFiles 3
+ numFiles 2
numRows 3
rawDataSize 0
- totalSize 1500
+ totalSize 1573
transactional true
transactional_properties default
#### A masked pattern was here ####
@@ -1247,6 +1233,54 @@ POSTHOOK: Output: default@cmv_mat_view_n5
POSTHOOK: Lineage: cmv_mat_view_n5._c2 EXPRESSION [(cmv_basetable_2_n2)cmv_basetable_2_n2.FieldSchema(name:d, type:int, comment:null), ]
POSTHOOK: Lineage: cmv_mat_view_n5.a SIMPLE [(cmv_basetable_n5)cmv_basetable_n5.FieldSchema(name:a, type:int, comment:null), ]
POSTHOOK: Lineage: cmv_mat_view_n5.c SIMPLE [(cmv_basetable_2_n2)cmv_basetable_2_n2.FieldSchema(name:c, type:decimal(10,2), comment:null), ]
+PREHOOK: query: DESCRIBE FORMATTED cmv_mat_view_n5
+PREHOOK: type: DESCTABLE
+PREHOOK: Input: default@cmv_mat_view_n5
+POSTHOOK: query: DESCRIBE FORMATTED cmv_mat_view_n5
+POSTHOOK: type: DESCTABLE
+POSTHOOK: Input: default@cmv_mat_view_n5
+# 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\"}}
+ bucketing_version 2
+ numFiles 1
+ numRows 3
+ rawDataSize 0
+ totalSize 814
+ 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: []
+
+# Materialized View Information
+Original Query: SELECT cmv_basetable_n5.a, cmv_basetable_2_n2.c, sum(cmv_basetable_2_n2.d)
+ FROM cmv_basetable_n5 JOIN cmv_basetable_2_n2 ON (cmv_basetable_n5.a = cmv_basetable_2_n2.a)
+ WHERE cmv_basetable_2_n2.c > 10.0
+ GROUP BY cmv_basetable_n5.a, cmv_basetable_2_n2.c
+Expanded Query: SELECT `cmv_basetable_n5`.`a`, `cmv_basetable_2_n2`.`c`, sum(`cmv_basetable_2_n2`.`d`)
+ FROM `default`.`cmv_basetable_n5` JOIN `default`.`cmv_basetable_2_n2` ON (`cmv_basetable_n5`.`a` = `cmv_basetable_2_n2`.`a`)
+ WHERE `cmv_basetable_2_n2`.`c` > 10.0
+ GROUP BY `cmv_basetable_n5`.`a`, `cmv_basetable_2_n2`.`c`
+Rewrite Enabled: Yes
+Outdated for Rewriting: No
PREHOOK: query: EXPLAIN
SELECT cmv_basetable_n5.a, sum(cmv_basetable_2_n2.d)
FROM cmv_basetable_n5 join cmv_basetable_2_n2 ON (cmv_basetable_n5.a = cmv_basetable_2_n2.a)
@@ -1483,6 +1517,54 @@ POSTHOOK: Output: default@cmv_mat_view_n5
POSTHOOK: Lineage: cmv_mat_view_n5._c2 EXPRESSION [(cmv_basetable_2_n2)cmv_basetable_2_n2.FieldSchema(name:d, type:int, comment:null), ]
POSTHOOK: Lineage: cmv_mat_view_n5.a SIMPLE [(cmv_basetable_n5)cmv_basetable_n5.FieldSchema(name:a, type:int, comment:null), ]
POSTHOOK: Lineage: cmv_mat_view_n5.c SIMPLE [(cmv_basetable_2_n2)cmv_basetable_2_n2.FieldSchema(name:c, type:decimal(10,2), comment:null), ]
+PREHOOK: query: DESCRIBE FORMATTED cmv_mat_view_n5
+PREHOOK: type: DESCTABLE
+PREHOOK: Input: default@cmv_mat_view_n5
+POSTHOOK: query: DESCRIBE FORMATTED cmv_mat_view_n5
+POSTHOOK: type: DESCTABLE
+POSTHOOK: Input: default@cmv_mat_view_n5
+# 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\"}}
+ bucketing_version 2
+ numFiles 1
+ numRows 2
+ rawDataSize 0
+ totalSize 812
+ 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: []
+
+# Materialized View Information
+Original Query: SELECT cmv_basetable_n5.a, cmv_basetable_2_n2.c, sum(cmv_basetable_2_n2.d)
+ FROM cmv_basetable_n5 JOIN cmv_basetable_2_n2 ON (cmv_basetable_n5.a = cmv_basetable_2_n2.a)
+ WHERE cmv_basetable_2_n2.c > 10.0
+ GROUP BY cmv_basetable_n5.a, cmv_basetable_2_n2.c
+Expanded Query: SELECT `cmv_basetable_n5`.`a`, `cmv_basetable_2_n2`.`c`, sum(`cmv_basetable_2_n2`.`d`)
+ FROM `default`.`cmv_basetable_n5` JOIN `default`.`cmv_basetable_2_n2` ON (`cmv_basetable_n5`.`a` = `cmv_basetable_2_n2`.`a`)
+ WHERE `cmv_basetable_2_n2`.`c` > 10.0
+ GROUP BY `cmv_basetable_n5`.`a`, `cmv_basetable_2_n2`.`c`
+Rewrite Enabled: Yes
+Outdated for Rewriting: No
PREHOOK: query: EXPLAIN
SELECT cmv_basetable_n5.a, sum(cmv_basetable_2_n2.d)
FROM cmv_basetable_n5 join cmv_basetable_2_n2 ON (cmv_basetable_n5.a = cmv_basetable_2_n2.a)
@@ -1637,10 +1719,10 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: cmv_basetable_2_n2
- filterExpr: ((c > 10) and (ROW__ID.writeid > 6) and a is not null) (type: boolean)
+ filterExpr: ((c > 10) and (ROW__ID.writeid > 4) and a is not null) (type: boolean)
Statistics: Num rows: 3 Data size: 360 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: ((ROW__ID.writeid > 6) and (c > 10) and a is not null) (type: boolean)
+ predicate: ((ROW__ID.writeid > 4) 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)
@@ -1834,6 +1916,54 @@ POSTHOOK: Output: default@cmv_mat_view_n5
POSTHOOK: Lineage: cmv_mat_view_n5._c2 EXPRESSION [(cmv_mat_view_n5)default.cmv_mat_view_n5.FieldSchema(name:a, type:int, comment:null), (cmv_mat_view_n5)default.cmv_mat_view_n5.FieldSchema(name:c, type:decimal(10,2), comment:null), (cmv_basetable_2_n2)cmv_basetable_2_n2.FieldSchema(name:d, type:int, comment:null), (cmv_mat_view_n5)default.cmv_mat_view_n5.FieldSchema(name:_c2, type:bigint, comment:null), ]
POSTHOOK: Lineage: cmv_mat_view_n5.a SIMPLE [(cmv_basetable_n5)cmv_basetable_n5.FieldSchema(name:a, type:int, comment:null), ]
POSTHOOK: Lineage: cmv_mat_view_n5.c SIMPLE [(cmv_basetable_2_n2)cmv_basetable_2_n2.FieldSchema(name:c, type:decimal(10,2), comment:null), ]
+PREHOOK: query: DESCRIBE FORMATTED cmv_mat_view_n5
+PREHOOK: type: DESCTABLE
+PREHOOK: Input: default@cmv_mat_view_n5
+POSTHOOK: query: DESCRIBE FORMATTED cmv_mat_view_n5
+POSTHOOK: type: DESCTABLE
+POSTHOOK: Input: default@cmv_mat_view_n5
+# 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\"}
+ bucketing_version 2
+ numFiles 2
+ numRows 3
+ rawDataSize 0
+ totalSize 1573
+ 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: []
+
+# Materialized View Information
+Original Query: SELECT cmv_basetable_n5.a, cmv_basetable_2_n2.c, sum(cmv_basetable_2_n2.d)
+ FROM cmv_basetable_n5 JOIN cmv_basetable_2_n2 ON (cmv_basetable_n5.a = cmv_basetable_2_n2.a)
+ WHERE cmv_basetable_2_n2.c > 10.0
+ GROUP BY cmv_basetable_n5.a, cmv_basetable_2_n2.c
+Expanded Query: SELECT `cmv_basetable_n5`.`a`, `cmv_basetable_2_n2`.`c`, sum(`cmv_basetable_2_n2`.`d`)
+ FROM `default`.`cmv_basetable_n5` JOIN `default`.`cmv_basetable_2_n2` ON (`cmv_basetable_n5`.`a` = `cmv_basetable_2_n2`.`a`)
+ WHERE `cmv_basetable_2_n2`.`c` > 10.0
+ GROUP BY `cmv_basetable_n5`.`a`, `cmv_basetable_2_n2`.`c`
+Rewrite Enabled: Yes
+Outdated for Rewriting: No
PREHOOK: query: EXPLAIN
SELECT cmv_basetable_n5.a, sum(cmv_basetable_2_n2.d)
FROM cmv_basetable_n5 join cmv_basetable_2_n2 ON (cmv_basetable_n5.a = cmv_basetable_2_n2.a)
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_5.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_5.q.out b/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_5.q.out
index 117593e..1b0d9e0 100644
--- a/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_5.q.out
+++ b/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_5.q.out
@@ -28,16 +28,6 @@ POSTHOOK: Lineage: cmv_basetable_n6.a SCRIPT []
POSTHOOK: Lineage: cmv_basetable_n6.b SCRIPT []
POSTHOOK: Lineage: cmv_basetable_n6.c SCRIPT []
POSTHOOK: Lineage: cmv_basetable_n6.d SCRIPT []
-PREHOOK: query: analyze table cmv_basetable_n6 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@cmv_basetable_n6
-PREHOOK: Output: default@cmv_basetable_n6
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table cmv_basetable_n6 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@cmv_basetable_n6
-POSTHOOK: Output: default@cmv_basetable_n6
-#### A masked pattern was here ####
PREHOOK: query: create table cmv_basetable_2_n3 (a int, b varchar(256), c decimal(10,2), d int) stored as orc TBLPROPERTIES ('transactional'='true')
PREHOOK: type: CREATETABLE
PREHOOK: Output: database:default
@@ -62,16 +52,6 @@ POSTHOOK: Lineage: cmv_basetable_2_n3.a SCRIPT []
POSTHOOK: Lineage: cmv_basetable_2_n3.b SCRIPT []
POSTHOOK: Lineage: cmv_basetable_2_n3.c SCRIPT []
POSTHOOK: Lineage: cmv_basetable_2_n3.d SCRIPT []
-PREHOOK: query: analyze table cmv_basetable_2_n3 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@cmv_basetable_2_n3
-PREHOOK: Output: default@cmv_basetable_2_n3
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table cmv_basetable_2_n3 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@cmv_basetable_2_n3
-POSTHOOK: Output: default@cmv_basetable_2_n3
-#### A masked pattern was here ####
PREHOOK: query: CREATE MATERIALIZED VIEW cmv_mat_view_n6
TBLPROPERTIES ('transactional'='true') AS
SELECT cmv_basetable_n6.a, cmv_basetable_2_n3.c
@@ -92,16 +72,6 @@ POSTHOOK: Input: default@cmv_basetable_2_n3
POSTHOOK: Input: default@cmv_basetable_n6
POSTHOOK: Output: database:default
POSTHOOK: Output: default@cmv_mat_view_n6
-PREHOOK: query: analyze table cmv_mat_view_n6 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@cmv_mat_view_n6
-PREHOOK: Output: default@cmv_mat_view_n6
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table cmv_mat_view_n6 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@cmv_mat_view_n6
-POSTHOOK: Output: default@cmv_mat_view_n6
-#### A masked pattern was here ####
PREHOOK: query: insert into cmv_basetable_2_n3 values
(3, 'charlie', 15.8, 1)
PREHOOK: type: QUERY
@@ -116,16 +86,6 @@ POSTHOOK: Lineage: cmv_basetable_2_n3.a SCRIPT []
POSTHOOK: Lineage: cmv_basetable_2_n3.b SCRIPT []
POSTHOOK: Lineage: cmv_basetable_2_n3.c SCRIPT []
POSTHOOK: Lineage: cmv_basetable_2_n3.d SCRIPT []
-PREHOOK: query: analyze table cmv_basetable_2_n3 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@cmv_basetable_2_n3
-PREHOOK: Output: default@cmv_basetable_2_n3
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table cmv_basetable_2_n3 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@cmv_basetable_2_n3
-POSTHOOK: Output: default@cmv_basetable_2_n3
-#### A masked pattern was here ####
PREHOOK: query: EXPLAIN
SELECT cmv_basetable_n6.a
FROM cmv_basetable_n6 join cmv_basetable_2_n3 ON (cmv_basetable_n6.a = cmv_basetable_2_n3.a)
@@ -290,10 +250,10 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: cmv_basetable_2_n3
- filterExpr: ((c > 10) and (ROW__ID.writeid > 2) and a is not null) (type: boolean)
+ filterExpr: ((c > 10) and (ROW__ID.writeid > 1) and a is not null) (type: boolean)
Statistics: Num rows: 3 Data size: 348 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: ((ROW__ID.writeid > 2) and (c > 10) and a is not null) (type: boolean)
+ predicate: ((ROW__ID.writeid > 1) and (c > 10) and a is not null) (type: boolean)
Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: a (type: int), c (type: decimal(10,2))
@@ -419,7 +379,7 @@ Table Parameters:
numFiles 2
numRows 5
rawDataSize 0
- totalSize 1071
+ totalSize 1498
transactional true
transactional_properties default
#### A masked pattern was here ####
@@ -1013,10 +973,10 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: cmv_basetable_2_n3
- filterExpr: ((c > 10) and (ROW__ID.writeid > 6) and a is not null) (type: boolean)
+ filterExpr: ((c > 10) and (ROW__ID.writeid > 4) and a is not null) (type: boolean)
Statistics: Num rows: 3 Data size: 348 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: ((ROW__ID.writeid > 6) and (c > 10) and a is not null) (type: boolean)
+ predicate: ((ROW__ID.writeid > 4) and (c > 10) and a is not null) (type: boolean)
Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: a (type: int), c (type: decimal(10,2))
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_dummy.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_dummy.q.out b/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_dummy.q.out
index 485a32e..734ae68 100644
--- a/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_dummy.q.out
+++ b/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_dummy.q.out
@@ -28,16 +28,6 @@ POSTHOOK: Lineage: cmv_basetable_n0.a SCRIPT []
POSTHOOK: Lineage: cmv_basetable_n0.b SCRIPT []
POSTHOOK: Lineage: cmv_basetable_n0.c SCRIPT []
POSTHOOK: Lineage: cmv_basetable_n0.d SCRIPT []
-PREHOOK: query: analyze table cmv_basetable_n0 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@cmv_basetable_n0
-PREHOOK: Output: default@cmv_basetable_n0
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table cmv_basetable_n0 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@cmv_basetable_n0
-POSTHOOK: Output: default@cmv_basetable_n0
-#### A masked pattern was here ####
PREHOOK: query: create materialized view cmv_mat_view_n0
as select a, b, c from cmv_basetable_n0 where a = 2
PREHOOK: type: CREATE_MATERIALIZED_VIEW
@@ -64,7 +54,7 @@ PREHOOK: query: show tblproperties cmv_mat_view_n0
PREHOOK: type: SHOW_TBLPROPERTIES
POSTHOOK: query: show tblproperties cmv_mat_view_n0
POSTHOOK: type: SHOW_TBLPROPERTIES
-COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
+COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"a":"true","b":"true","c":"true"}}
bucketing_version 2
numFiles 1
numFilesErasureCoded 0
@@ -98,7 +88,7 @@ PREHOOK: query: show tblproperties cmv_mat_view2
PREHOOK: type: SHOW_TBLPROPERTIES
POSTHOOK: query: show tblproperties cmv_mat_view2
POSTHOOK: type: SHOW_TBLPROPERTIES
-COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
+COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"a":"true","c":"true"}}
bucketing_version 2
numFiles 1
numFilesErasureCoded 0
@@ -354,10 +344,10 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: default.cmv_mat_view2
- Statistics: Num rows: 2 Data size: 232 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 232 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 2 Data size: 232 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 232 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: a (type: int), c (type: decimal(10,2))
Execution mode: llap
LLAP IO: all inputs
@@ -371,14 +361,14 @@ STAGE PLANS:
0
1
outputColumnNames: _col0, _col1, _col5
- Statistics: Num rows: 2 Data size: 458 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 456 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: int), _col1 (type: decimal(10,2)), _col0 (type: int), _col5 (type: decimal(10,2))
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 2 Data size: 458 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 464 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 2 Data size: 458 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 464 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_multi_db.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_multi_db.q.out b/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_multi_db.q.out
index ecaefad..4bf5c2f 100644
--- a/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_multi_db.q.out
+++ b/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_multi_db.q.out
@@ -40,16 +40,6 @@ POSTHOOK: Lineage: cmv_basetable_n7.a SCRIPT []
POSTHOOK: Lineage: cmv_basetable_n7.b SCRIPT []
POSTHOOK: Lineage: cmv_basetable_n7.c SCRIPT []
POSTHOOK: Lineage: cmv_basetable_n7.d SCRIPT []
-PREHOOK: query: analyze table cmv_basetable_n7 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: db1@cmv_basetable_n7
-PREHOOK: Output: db1@cmv_basetable_n7
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table cmv_basetable_n7 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: db1@cmv_basetable_n7
-POSTHOOK: Output: db1@cmv_basetable_n7
-#### A masked pattern was here ####
PREHOOK: query: create database db2
PREHOOK: type: CREATEDATABASE
PREHOOK: Output: database:db2
@@ -88,7 +78,7 @@ PREHOOK: query: show tblproperties cmv_mat_view_n7
PREHOOK: type: SHOW_TBLPROPERTIES
POSTHOOK: query: show tblproperties cmv_mat_view_n7
POSTHOOK: type: SHOW_TBLPROPERTIES
-COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
+COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"a":"true","b":"true","c":"true"}}
bucketing_version 2
numFiles 1
numFilesErasureCoded 0
@@ -122,7 +112,7 @@ PREHOOK: query: show tblproperties cmv_mat_view2_n2
PREHOOK: type: SHOW_TBLPROPERTIES
POSTHOOK: query: show tblproperties cmv_mat_view2_n2
POSTHOOK: type: SHOW_TBLPROPERTIES
-COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
+COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"a":"true","c":"true"}}
bucketing_version 2
numFiles 1
numFilesErasureCoded 0
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_rebuild_dummy.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_rebuild_dummy.q.out b/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_rebuild_dummy.q.out
index 32befa5..261cc5f 100644
--- a/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_rebuild_dummy.q.out
+++ b/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_rebuild_dummy.q.out
@@ -28,16 +28,6 @@ POSTHOOK: Lineage: cmv_basetable_n1.a SCRIPT []
POSTHOOK: Lineage: cmv_basetable_n1.b SCRIPT []
POSTHOOK: Lineage: cmv_basetable_n1.c SCRIPT []
POSTHOOK: Lineage: cmv_basetable_n1.d SCRIPT []
-PREHOOK: query: analyze table cmv_basetable_n1 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@cmv_basetable_n1
-PREHOOK: Output: default@cmv_basetable_n1
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table cmv_basetable_n1 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@cmv_basetable_n1
-POSTHOOK: Output: default@cmv_basetable_n1
-#### A masked pattern was here ####
PREHOOK: query: create table cmv_basetable_2_n0 (a int, b varchar(256), c decimal(10,2), d int) stored as orc TBLPROPERTIES ('transactional'='true')
PREHOOK: type: CREATETABLE
PREHOOK: Output: database:default
@@ -62,16 +52,6 @@ POSTHOOK: Lineage: cmv_basetable_2_n0.a SCRIPT []
POSTHOOK: Lineage: cmv_basetable_2_n0.b SCRIPT []
POSTHOOK: Lineage: cmv_basetable_2_n0.c SCRIPT []
POSTHOOK: Lineage: cmv_basetable_2_n0.d SCRIPT []
-PREHOOK: query: analyze table cmv_basetable_2_n0 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@cmv_basetable_2_n0
-PREHOOK: Output: default@cmv_basetable_2_n0
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table cmv_basetable_2_n0 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@cmv_basetable_2_n0
-POSTHOOK: Output: default@cmv_basetable_2_n0
-#### A masked pattern was here ####
PREHOOK: query: EXPLAIN
CREATE MATERIALIZED VIEW cmv_mat_view_n1 AS
SELECT cmv_basetable_n1.a, cmv_basetable_2_n0.c
@@ -97,7 +77,7 @@ POSTHOOK: Output: default@cmv_mat_view_n1
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-4 depends on stages: Stage-0, Stage-2
Stage-3 depends on stages: Stage-4
Stage-5 depends on stages: Stage-3
Stage-0 depends on stages: Stage-1
@@ -107,8 +87,9 @@ STAGE PLANS:
Tez
#### A masked pattern was here ####
Edges:
- Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE)
+ Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE)
Reducer 3 <- Reducer 2 (SIMPLE_EDGE)
+ Reducer 4 <- Reducer 3 (CUSTOM_SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -131,7 +112,7 @@ STAGE PLANS:
Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: may be used (ACID table)
- Map 4
+ Map 5
Map Operator Tree:
TableScan
alias: cmv_basetable_2_n0
@@ -174,7 +155,7 @@ STAGE PLANS:
Map-reduce partition columns: _col0 (type: int), _col1 (type: decimal(10,2))
Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: COMPLETE
Reducer 3
- Execution mode: vectorized, llap
+ Execution mode: llap
Reduce Operator Tree:
Group By Operator
keys: KEY._col0 (type: int), KEY._col1 (type: decimal(10,2))
@@ -189,6 +170,34 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde
name: default.cmv_mat_view_n1
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: decimal(10,2))
+ outputColumnNames: col1, col2
+ Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: compute_stats(col1, 'hll'), compute_stats(col2, 'hll')
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 1056 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 1056 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>)
+ Reducer 4
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 1088 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 1088 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
@@ -211,6 +220,10 @@ STAGE PLANS:
Stage: Stage-3
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: a, c
+ Column Types: int, decimal(10,2)
+ Table: default.cmv_mat_view_n1
Stage: Stage-5
Materialized View Work
@@ -313,16 +326,6 @@ POSTHOOK: Lineage: cmv_basetable_2_n0.a SCRIPT []
POSTHOOK: Lineage: cmv_basetable_2_n0.b SCRIPT []
POSTHOOK: Lineage: cmv_basetable_2_n0.c SCRIPT []
POSTHOOK: Lineage: cmv_basetable_2_n0.d SCRIPT []
-PREHOOK: query: analyze table cmv_basetable_2_n0 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@cmv_basetable_2_n0
-PREHOOK: Output: default@cmv_basetable_2_n0
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table cmv_basetable_2_n0 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@cmv_basetable_2_n0
-POSTHOOK: Output: default@cmv_basetable_2_n0
-#### A masked pattern was here ####
PREHOOK: query: EXPLAIN
SELECT cmv_basetable_n1.a
FROM cmv_basetable_n1 join cmv_basetable_2_n0 ON (cmv_basetable_n1.a = cmv_basetable_2_n0.a)
@@ -518,10 +521,10 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: cmv_basetable_2_n0
- filterExpr: ((c > 10) and (ROW__ID.writeid > 2) and a is not null) (type: boolean)
+ filterExpr: ((c > 10) and (ROW__ID.writeid > 1) and a is not null) (type: boolean)
Statistics: Num rows: 3 Data size: 348 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: ((ROW__ID.writeid > 2) and (c > 10) and a is not null) (type: boolean)
+ predicate: ((ROW__ID.writeid > 1) and (c > 10) and a is not null) (type: boolean)
Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: a (type: int), c (type: decimal(10,2))
@@ -539,21 +542,21 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: default.cmv_mat_view_n1
- Statistics: Num rows: 2 Data size: 232 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 232 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: a (type: int), c (type: decimal(10,2))
outputColumnNames: _col0, _col1
- Statistics: Num rows: 2 Data size: 232 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 232 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: int), _col1 (type: decimal(10,2))
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 1 Data size: 116 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: 116 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Reducer 2
@@ -589,12 +592,12 @@ STAGE PLANS:
keys: _col0 (type: int), _col1 (type: decimal(10,2))
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 1 Data size: 116 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: 116 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: COMPLETE
Reducer 5
Execution mode: llap
Reduce Operator Tree:
@@ -602,10 +605,10 @@ STAGE PLANS:
keys: KEY._col0 (type: int), KEY._col1 (type: decimal(10,2))
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 1 Data size: 116 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
@@ -614,15 +617,15 @@ STAGE PLANS:
Select Operator
expressions: _col0 (type: int), _col1 (type: decimal(10,2))
outputColumnNames: a, c
- Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: compute_stats(a, 'hll'), compute_stats(c, 'hll')
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 1056 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 1 Data size: 1056 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 1056 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 1 Data size: 1056 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>)
Reducer 6
Execution mode: llap
@@ -631,10 +634,10 @@ STAGE PLANS:
aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 1088 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 1 Data size: 1088 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 1088 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 1 Data size: 1088 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -976,16 +979,6 @@ POSTHOOK: Lineage: cmv_irrelevant_table_n0.a SCRIPT []
POSTHOOK: Lineage: cmv_irrelevant_table_n0.b SCRIPT []
POSTHOOK: Lineage: cmv_irrelevant_table_n0.c SCRIPT []
POSTHOOK: Lineage: cmv_irrelevant_table_n0.d SCRIPT []
-PREHOOK: query: analyze table cmv_irrelevant_table_n0 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@cmv_irrelevant_table_n0
-PREHOOK: Output: default@cmv_irrelevant_table_n0
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table cmv_irrelevant_table_n0 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@cmv_irrelevant_table_n0
-POSTHOOK: Output: default@cmv_irrelevant_table_n0
-#### A masked pattern was here ####
PREHOOK: query: EXPLAIN
SELECT cmv_basetable_n1.a
FROM cmv_basetable_n1 join cmv_basetable_2_n0 ON (cmv_basetable_n1.a = cmv_basetable_2_n0.a)
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_time_window.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_time_window.q.out b/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_time_window.q.out
index 06835a1..51be03e 100644
--- a/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_time_window.q.out
+++ b/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_time_window.q.out
@@ -28,16 +28,6 @@ POSTHOOK: Lineage: cmv_basetable_n3.a SCRIPT []
POSTHOOK: Lineage: cmv_basetable_n3.b SCRIPT []
POSTHOOK: Lineage: cmv_basetable_n3.c SCRIPT []
POSTHOOK: Lineage: cmv_basetable_n3.d SCRIPT []
-PREHOOK: query: analyze table cmv_basetable_n3 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@cmv_basetable_n3
-PREHOOK: Output: default@cmv_basetable_n3
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table cmv_basetable_n3 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@cmv_basetable_n3
-POSTHOOK: Output: default@cmv_basetable_n3
-#### A masked pattern was here ####
PREHOOK: query: create table cmv_basetable_2_n1 (a int, b varchar(256), c decimal(10,2), d int) stored as orc TBLPROPERTIES ('transactional'='true')
PREHOOK: type: CREATETABLE
PREHOOK: Output: database:default
@@ -62,16 +52,6 @@ POSTHOOK: Lineage: cmv_basetable_2_n1.a SCRIPT []
POSTHOOK: Lineage: cmv_basetable_2_n1.b SCRIPT []
POSTHOOK: Lineage: cmv_basetable_2_n1.c SCRIPT []
POSTHOOK: Lineage: cmv_basetable_2_n1.d SCRIPT []
-PREHOOK: query: analyze table cmv_basetable_2_n1 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@cmv_basetable_2_n1
-PREHOOK: Output: default@cmv_basetable_2_n1
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table cmv_basetable_2_n1 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@cmv_basetable_2_n1
-POSTHOOK: Output: default@cmv_basetable_2_n1
-#### A masked pattern was here ####
PREHOOK: query: EXPLAIN
CREATE MATERIALIZED VIEW cmv_mat_view_n3 DISABLE REWRITE TBLPROPERTIES('rewriting.time.window'='5min') AS
SELECT cmv_basetable_n3.a, cmv_basetable_2_n1.c
@@ -97,7 +77,7 @@ POSTHOOK: Output: default@cmv_mat_view_n3
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-4 depends on stages: Stage-0, Stage-2
Stage-3 depends on stages: Stage-4
Stage-5 depends on stages: Stage-3
Stage-0 depends on stages: Stage-1
@@ -107,8 +87,9 @@ STAGE PLANS:
Tez
#### A masked pattern was here ####
Edges:
- Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE)
+ Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE)
Reducer 3 <- Reducer 2 (SIMPLE_EDGE)
+ Reducer 4 <- Reducer 3 (CUSTOM_SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -131,7 +112,7 @@ STAGE PLANS:
Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: may be used (ACID table)
- Map 4
+ Map 5
Map Operator Tree:
TableScan
alias: cmv_basetable_2_n1
@@ -174,7 +155,7 @@ STAGE PLANS:
Map-reduce partition columns: _col0 (type: int), _col1 (type: decimal(10,2))
Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: COMPLETE
Reducer 3
- Execution mode: vectorized, llap
+ Execution mode: llap
Reduce Operator Tree:
Group By Operator
keys: KEY._col0 (type: int), KEY._col1 (type: decimal(10,2))
@@ -189,6 +170,34 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde
name: default.cmv_mat_view_n3
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: decimal(10,2))
+ outputColumnNames: col1, col2
+ Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: compute_stats(col1, 'hll'), compute_stats(col2, 'hll')
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 1056 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 1056 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>)
+ Reducer 4
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 1088 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 1088 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
@@ -212,6 +221,10 @@ STAGE PLANS:
Stage: Stage-3
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: a, c
+ Column Types: int, decimal(10,2)
+ Table: default.cmv_mat_view_n3
Stage: Stage-5
Materialized View Work
@@ -259,7 +272,7 @@ Retention: 0
#### A masked pattern was here ####
Table Type: MATERIALIZED_VIEW
Table Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"a\":\"true\",\"c\":\"true\"}}
bucketing_version 2
numFiles 2
numRows 2
@@ -439,16 +452,6 @@ POSTHOOK: Lineage: cmv_basetable_2_n1.a SCRIPT []
POSTHOOK: Lineage: cmv_basetable_2_n1.b SCRIPT []
POSTHOOK: Lineage: cmv_basetable_2_n1.c SCRIPT []
POSTHOOK: Lineage: cmv_basetable_2_n1.d SCRIPT []
-PREHOOK: query: analyze table cmv_basetable_2_n1 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@cmv_basetable_2_n1
-PREHOOK: Output: default@cmv_basetable_2_n1
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table cmv_basetable_2_n1 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@cmv_basetable_2_n1
-POSTHOOK: Output: default@cmv_basetable_2_n1
-#### A masked pattern was here ####
PREHOOK: query: EXPLAIN
ALTER MATERIALIZED VIEW cmv_mat_view_n3 ENABLE REWRITE
PREHOOK: type: ALTER_MATERIALIZED_VIEW_REWRITE
@@ -494,7 +497,7 @@ Retention: 0
#### A masked pattern was here ####
Table Type: MATERIALIZED_VIEW
Table Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"a\":\"true\",\"c\":\"true\"}}
bucketing_version 2
numFiles 2
numRows 2
@@ -638,10 +641,10 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: cmv_basetable_2_n1
- filterExpr: ((c > 10) and (ROW__ID.writeid > 2) and a is not null) (type: boolean)
+ filterExpr: ((c > 10) and (ROW__ID.writeid > 1) and a is not null) (type: boolean)
Statistics: Num rows: 3 Data size: 348 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: ((ROW__ID.writeid > 2) and (c > 10) and a is not null) (type: boolean)
+ predicate: ((ROW__ID.writeid > 1) and (c > 10) and a is not null) (type: boolean)
Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: a (type: int), c (type: decimal(10,2))
@@ -659,21 +662,21 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: default.cmv_mat_view_n3
- Statistics: Num rows: 2 Data size: 232 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 232 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: a (type: int), c (type: decimal(10,2))
outputColumnNames: _col0, _col1
- Statistics: Num rows: 2 Data size: 232 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 232 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: int), _col1 (type: decimal(10,2))
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 1 Data size: 116 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: 116 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Reducer 2
@@ -709,12 +712,12 @@ STAGE PLANS:
keys: _col0 (type: int), _col1 (type: decimal(10,2))
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 1 Data size: 116 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: 116 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: COMPLETE
Reducer 5
Execution mode: llap
Reduce Operator Tree:
@@ -722,10 +725,10 @@ STAGE PLANS:
keys: KEY._col0 (type: int), KEY._col1 (type: decimal(10,2))
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 1 Data size: 116 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
@@ -734,15 +737,15 @@ STAGE PLANS:
Select Operator
expressions: _col0 (type: int), _col1 (type: decimal(10,2))
outputColumnNames: a, c
- Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: compute_stats(a, 'hll'), compute_stats(c, 'hll')
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 1056 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 1 Data size: 1056 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 1056 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 1 Data size: 1056 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>)
Reducer 6
Execution mode: llap
@@ -751,10 +754,10 @@ STAGE PLANS:
aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 1088 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 1 Data size: 1088 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 1088 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 1 Data size: 1088 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat