You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by vg...@apache.org on 2018/08/06 17:27:10 UTC
[6/7] hive git commit: HIVE-20292: Bad join ordering in tpcds query93
with primary constraint defined (Vineet Garg, reviewed by Ashutosh Chauhan)
http://git-wip-us.apache.org/repos/asf/hive/blob/30c17911/ql/src/test/results/clientpositive/llap/dynamic_semijoin_reduction_sw.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/dynamic_semijoin_reduction_sw.q.out b/ql/src/test/results/clientpositive/llap/dynamic_semijoin_reduction_sw.q.out
index 6056865..e85fd5e 100644
--- a/ql/src/test/results/clientpositive/llap/dynamic_semijoin_reduction_sw.q.out
+++ b/ql/src/test/results/clientpositive/llap/dynamic_semijoin_reduction_sw.q.out
@@ -148,7 +148,7 @@ POSTHOOK: Output: default@srcpart_small_n2
POSTHOOK: Output: default@srcpart_small_n2@ds1=2008-04-08
POSTHOOK: Output: default@srcpart_small_n2@ds1=2008-04-09
#### A masked pattern was here ####
-Warning: Shuffle Join MERGEJOIN[93][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 3' is a cross product
+Warning: Shuffle Join MERGEJOIN[92][tables = [$hdt$_1, $hdt$_2, $hdt$_0, $hdt$_3]] in Stage 'Reducer 3' is a cross product
PREHOOK: query: EXPLAIN
SELECT count(*)
FROM (
@@ -212,10 +212,10 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: srcpart_date_n6
- filterExpr: (key is not null and (key BETWEEN DynamicValue(RS_10_srcpart_small_n2_key1_min) AND DynamicValue(RS_10_srcpart_small_n2_key1_max) and in_bloom_filter(key, DynamicValue(RS_10_srcpart_small_n2_key1_bloom_filter)))) (type: boolean)
+ filterExpr: (key is not null and (key BETWEEN DynamicValue(RS_24_srcpart_small_n2_key1_min) AND DynamicValue(RS_24_srcpart_small_n2_key1_max) and in_bloom_filter(key, DynamicValue(RS_24_srcpart_small_n2_key1_bloom_filter)))) (type: boolean)
Statistics: Num rows: 1000 Data size: 87000 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: ((key BETWEEN DynamicValue(RS_10_srcpart_small_n2_key1_min) AND DynamicValue(RS_10_srcpart_small_n2_key1_max) and in_bloom_filter(key, DynamicValue(RS_10_srcpart_small_n2_key1_bloom_filter))) and key is not null) (type: boolean)
+ predicate: ((key BETWEEN DynamicValue(RS_24_srcpart_small_n2_key1_min) AND DynamicValue(RS_24_srcpart_small_n2_key1_max) and in_bloom_filter(key, DynamicValue(RS_24_srcpart_small_n2_key1_bloom_filter))) and key is not null) (type: boolean)
Statistics: Num rows: 1000 Data size: 87000 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string)
@@ -245,10 +245,10 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc_int_n0
- filterExpr: (cstring is not null and (cstring BETWEEN DynamicValue(RS_9_srcpart_date_n6_key_min) AND DynamicValue(RS_9_srcpart_date_n6_key_max) and in_bloom_filter(cstring, DynamicValue(RS_9_srcpart_date_n6_key_bloom_filter))) and (cstring BETWEEN DynamicValue(RS_10_srcpart_small_n2_key1_min) AND DynamicValue(RS_10_srcpart_small_n2_key1_max) and in_bloom_filter(cstring, DynamicValue(RS_10_srcpart_small_n2_key1_bloom_filter)))) (type: boolean)
+ filterExpr: (cstring is not null and (cstring BETWEEN DynamicValue(RS_23_srcpart_date_n6_key_min) AND DynamicValue(RS_23_srcpart_date_n6_key_max) and in_bloom_filter(cstring, DynamicValue(RS_23_srcpart_date_n6_key_bloom_filter))) and (cstring BETWEEN DynamicValue(RS_24_srcpart_small_n2_key1_min) AND DynamicValue(RS_24_srcpart_small_n2_key1_max) and in_bloom_filter(cstring, DynamicValue(RS_24_srcpart_small_n2_key1_bloom_filter)))) (type: boolean)
Statistics: Num rows: 12288 Data size: 862450 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: ((cstring BETWEEN DynamicValue(RS_10_srcpart_small_n2_key1_min) AND DynamicValue(RS_10_srcpart_small_n2_key1_max) and in_bloom_filter(cstring, DynamicValue(RS_10_srcpart_small_n2_key1_bloom_filter))) and (cstring BETWEEN DynamicValue(RS_9_srcpart_date_n6_key_min) AND DynamicValue(RS_9_srcpart_date_n6_key_max) and in_bloom_filter(cstring, DynamicValue(RS_9_srcpart_date_n6_key_bloom_filter))) and cstring is not null) (type: boolean)
+ predicate: ((cstring BETWEEN DynamicValue(RS_23_srcpart_date_n6_key_min) AND DynamicValue(RS_23_srcpart_date_n6_key_max) and in_bloom_filter(cstring, DynamicValue(RS_23_srcpart_date_n6_key_bloom_filter))) and (cstring BETWEEN DynamicValue(RS_24_srcpart_small_n2_key1_min) AND DynamicValue(RS_24_srcpart_small_n2_key1_max) and in_bloom_filter(cstring, DynamicValue(RS_24_srcpart_small_n2_key1_bloom_filter))) and cstring is not null) (type: boolean)
Statistics: Num rows: 9174 Data size: 643900 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: cstring (type: string)
@@ -265,10 +265,10 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: srcpart_date_n6
- filterExpr: (key is not null and (key BETWEEN DynamicValue(RS_24_srcpart_small_n2_key1_min) AND DynamicValue(RS_24_srcpart_small_n2_key1_max) and in_bloom_filter(key, DynamicValue(RS_24_srcpart_small_n2_key1_bloom_filter)))) (type: boolean)
+ filterExpr: (key is not null and (key BETWEEN DynamicValue(RS_19_srcpart_small_n2_key1_min) AND DynamicValue(RS_19_srcpart_small_n2_key1_max) and in_bloom_filter(key, DynamicValue(RS_19_srcpart_small_n2_key1_bloom_filter)))) (type: boolean)
Statistics: Num rows: 1000 Data size: 87000 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: ((key BETWEEN DynamicValue(RS_24_srcpart_small_n2_key1_min) AND DynamicValue(RS_24_srcpart_small_n2_key1_max) and in_bloom_filter(key, DynamicValue(RS_24_srcpart_small_n2_key1_bloom_filter))) and key is not null) (type: boolean)
+ predicate: ((key BETWEEN DynamicValue(RS_19_srcpart_small_n2_key1_min) AND DynamicValue(RS_19_srcpart_small_n2_key1_max) and in_bloom_filter(key, DynamicValue(RS_19_srcpart_small_n2_key1_bloom_filter))) and key is not null) (type: boolean)
Statistics: Num rows: 1000 Data size: 87000 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string)
@@ -298,10 +298,10 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc_int_n0
- filterExpr: (cstring is not null and (cstring BETWEEN DynamicValue(RS_23_srcpart_date_n6_key_min) AND DynamicValue(RS_23_srcpart_date_n6_key_max) and in_bloom_filter(cstring, DynamicValue(RS_23_srcpart_date_n6_key_bloom_filter))) and (cstring BETWEEN DynamicValue(RS_24_srcpart_small_n2_key1_min) AND DynamicValue(RS_24_srcpart_small_n2_key1_max) and in_bloom_filter(cstring, DynamicValue(RS_24_srcpart_small_n2_key1_bloom_filter)))) (type: boolean)
+ filterExpr: (cstring is not null and (cstring BETWEEN DynamicValue(RS_18_srcpart_date_n6_key_min) AND DynamicValue(RS_18_srcpart_date_n6_key_max) and in_bloom_filter(cstring, DynamicValue(RS_18_srcpart_date_n6_key_bloom_filter))) and (cstring BETWEEN DynamicValue(RS_19_srcpart_small_n2_key1_min) AND DynamicValue(RS_19_srcpart_small_n2_key1_max) and in_bloom_filter(cstring, DynamicValue(RS_19_srcpart_small_n2_key1_bloom_filter)))) (type: boolean)
Statistics: Num rows: 12288 Data size: 862450 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: ((cstring BETWEEN DynamicValue(RS_23_srcpart_date_n6_key_min) AND DynamicValue(RS_23_srcpart_date_n6_key_max) and in_bloom_filter(cstring, DynamicValue(RS_23_srcpart_date_n6_key_bloom_filter))) and (cstring BETWEEN DynamicValue(RS_24_srcpart_small_n2_key1_min) AND DynamicValue(RS_24_srcpart_small_n2_key1_max) and in_bloom_filter(cstring, DynamicValue(RS_24_srcpart_small_n2_key1_bloom_filter))) and cstring is not null) (type: boolean)
+ predicate: ((cstring BETWEEN DynamicValue(RS_18_srcpart_date_n6_key_min) AND DynamicValue(RS_18_srcpart_date_n6_key_max) and in_bloom_filter(cstring, DynamicValue(RS_18_srcpart_date_n6_key_bloom_filter))) and (cstring BETWEEN DynamicValue(RS_19_srcpart_small_n2_key1_min) AND DynamicValue(RS_19_srcpart_small_n2_key1_max) and in_bloom_filter(cstring, DynamicValue(RS_19_srcpart_small_n2_key1_bloom_filter))) and cstring is not null) (type: boolean)
Statistics: Num rows: 9174 Data size: 643900 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: cstring (type: string)
http://git-wip-us.apache.org/repos/asf/hive/blob/30c17911/ql/src/test/results/clientpositive/llap/join32_lessSize.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/join32_lessSize.q.out b/ql/src/test/results/clientpositive/llap/join32_lessSize.q.out
index f1b4fb2..70ea9ac 100644
--- a/ql/src/test/results/clientpositive/llap/join32_lessSize.q.out
+++ b/ql/src/test/results/clientpositive/llap/join32_lessSize.q.out
@@ -1205,17 +1205,16 @@ SELECT res.key, z.value, res.value
FROM (select x.key, x.value from src1 x JOIN src y ON (x.key = y.key)) res
JOIN srcpart z ON (res.value = z.value and z.ds='2008-04-08' and z.hr=11)
POSTHOOK: type: QUERY
-OPTIMIZED SQL: SELECT `t5`.`key`, `t0`.`value`, `t5`.`value` AS `value1`
+OPTIMIZED SQL: SELECT `t4`.`key`, `t0`.`value`, `t4`.`value` AS `value1`
FROM (SELECT `value`, CAST('2008-04-08' AS STRING) AS `ds`, `hr`
FROM `default`.`srcpart`
WHERE `ds` = '2008-04-08' AND `hr` = 11 AND `value` IS NOT NULL) AS `t0`
-INNER JOIN (SELECT `t4`.`key`, `t4`.`value`
-FROM (SELECT `key`
+INNER JOIN ((SELECT `key`
FROM `default`.`src`
WHERE `key` IS NOT NULL) AS `t2`
INNER JOIN (SELECT `key`, `value`
FROM `default`.`src1`
-WHERE `key` IS NOT NULL AND `value` IS NOT NULL) AS `t4` ON `t2`.`key` = `t4`.`key`) AS `t5` ON `t0`.`value` = `t5`.`value`
+WHERE `key` IS NOT NULL AND `value` IS NOT NULL) AS `t4` ON `t2`.`key` = `t4`.`key`) ON `t0`.`value` = `t4`.`value`
STAGE DEPENDENCIES:
Stage-1 is a root stage
Stage-2 depends on stages: Stage-1
@@ -1227,93 +1226,14 @@ STAGE PLANS:
Tez
#### A masked pattern was here ####
Edges:
- Map 4 <- Map 5 (BROADCAST_EDGE)
- Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE)
+ Map 1 <- Map 4 (BROADCAST_EDGE)
+ Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE)
Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
Map Operator Tree:
TableScan
- alias: z
- filterExpr: value is not null (type: boolean)
- Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE
- GatherStats: false
- Filter Operator
- isSamplingPred: false
- predicate: value is not null (type: boolean)
- Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: value (type: string)
- outputColumnNames: _col0
- Statistics: Num rows: 500 Data size: 184500 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- null sort order: a
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 500 Data size: 184500 Basic stats: COMPLETE Column stats: COMPLETE
- tag: 0
- auto parallelism: true
- Execution mode: vectorized, llap
- LLAP IO: no inputs
- Path -> Alias:
-#### A masked pattern was here ####
- Path -> Partition:
-#### A masked pattern was here ####
- Partition
- base file name: hr=11
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-08
- hr 11
- properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
- bucket_count -1
- column.name.delimiter ,
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- numFiles 1
- numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 5312
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- bucketing_version 2
- column.name.delimiter ,
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcpart
- name: default.srcpart
- Truncated Path -> Alias:
- /srcpart/ds=2008-04-08/hr=11 [z]
- Map 4
- Map Operator Tree:
- TableScan
alias: y
filterExpr: key is not null (type: boolean)
Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
@@ -1329,28 +1249,24 @@ STAGE PLANS:
Map Join Operator
condition map:
Inner Join 0 to 1
- Estimated key counts: Map 5 => 25
+ Estimated key counts: Map 4 => 25
keys:
0 _col0 (type: string)
1 _col0 (type: string)
outputColumnNames: _col1, _col2
input vertices:
- 1 Map 5
+ 1 Map 4
Position of Big Table: 0
Statistics: Num rows: 39 Data size: 6825 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: _col1 (type: string), _col2 (type: string)
- outputColumnNames: _col0, _col1
+ Reduce Output Operator
+ key expressions: _col2 (type: string)
+ null sort order: a
+ sort order: +
+ Map-reduce partition columns: _col2 (type: string)
Statistics: Num rows: 39 Data size: 6825 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- key expressions: _col1 (type: string)
- null sort order: a
- sort order: +
- Map-reduce partition columns: _col1 (type: string)
- Statistics: Num rows: 39 Data size: 6825 Basic stats: COMPLETE Column stats: COMPLETE
- tag: 1
- value expressions: _col0 (type: string)
- auto parallelism: true
+ tag: 0
+ value expressions: _col1 (type: string)
+ auto parallelism: true
Execution mode: vectorized, llap
LLAP IO: no inputs
Path -> Alias:
@@ -1406,7 +1322,7 @@ STAGE PLANS:
name: default.src
Truncated Path -> Alias:
/src [y]
- Map 5
+ Map 4
Map Operator Tree:
TableScan
alias: x
@@ -1485,6 +1401,85 @@ STAGE PLANS:
name: default.src1
Truncated Path -> Alias:
/src1 [x]
+ Map 5
+ Map Operator Tree:
+ TableScan
+ alias: z
+ filterExpr: value is not null (type: boolean)
+ Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE
+ GatherStats: false
+ Filter Operator
+ isSamplingPred: false
+ predicate: value is not null (type: boolean)
+ Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: value (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 500 Data size: 184500 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ null sort order: a
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 500 Data size: 184500 Basic stats: COMPLETE Column stats: COMPLETE
+ tag: 1
+ auto parallelism: true
+ Execution mode: vectorized, llap
+ LLAP IO: no inputs
+ Path -> Alias:
+#### A masked pattern was here ####
+ Path -> Partition:
+#### A masked pattern was here ####
+ Partition
+ base file name: hr=11
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ partition values:
+ ds 2008-04-08
+ hr 11
+ properties:
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
+ bucket_count -1
+ column.name.delimiter ,
+ columns key,value
+ columns.comments 'default','default'
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.srcpart
+ numFiles 1
+ numRows 500
+ partition_columns ds/hr
+ partition_columns.types string:string
+ rawDataSize 5312
+ serialization.ddl struct srcpart { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 5812
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ bucket_count -1
+ bucketing_version 2
+ column.name.delimiter ,
+ columns key,value
+ columns.comments 'default','default'
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.srcpart
+ partition_columns ds/hr
+ partition_columns.types string:string
+ serialization.ddl struct srcpart { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.srcpart
+ name: default.srcpart
+ Truncated Path -> Alias:
+ /srcpart/ds=2008-04-08/hr=11 [z]
Reducer 2
Execution mode: llap
Needs Tagging: false
@@ -1493,13 +1488,13 @@ STAGE PLANS:
condition map:
Inner Join 0 to 1
keys:
- 0 _col0 (type: string)
- 1 _col1 (type: string)
- outputColumnNames: _col0, _col3, _col4
- Position of Big Table: 0
+ 0 _col2 (type: string)
+ 1 _col0 (type: string)
+ outputColumnNames: _col1, _col2, _col3
+ Position of Big Table: 1
Statistics: Num rows: 63 Data size: 16758 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
- expressions: _col3 (type: string), _col0 (type: string), _col4 (type: string)
+ expressions: _col1 (type: string), _col3 (type: string), _col2 (type: string)
outputColumnNames: _col0, _col1, _col2
Statistics: Num rows: 63 Data size: 16758 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
@@ -1753,16 +1748,15 @@ SELECT res.key, z.value, res.value
FROM (select x.key, x.value from src1 x LEFT OUTER JOIN src y ON (x.key = y.key)) res
JOIN srcpart z ON (res.value = z.value and z.ds='2008-04-08' and z.hr=11)
POSTHOOK: type: QUERY
-OPTIMIZED SQL: SELECT `t4`.`key`, `t0`.`value`, `t4`.`value` AS `value1`
+OPTIMIZED SQL: SELECT `t2`.`key`, `t0`.`value`, `t2`.`value` AS `value1`
FROM (SELECT `value`, CAST('2008-04-08' AS STRING) AS `ds`, `hr`
FROM `default`.`srcpart`
WHERE `ds` = '2008-04-08' AND `hr` = 11 AND `value` IS NOT NULL) AS `t0`
-INNER JOIN (SELECT `t3`.`key`, `t3`.`value`
-FROM (SELECT `key`
-FROM `default`.`src`) AS `t1`
-RIGHT JOIN (SELECT `key`, `value`
+INNER JOIN ((SELECT `key`, `value`
FROM `default`.`src1`
-WHERE `value` IS NOT NULL) AS `t3` ON `t1`.`key` = `t3`.`key`) AS `t4` ON `t0`.`value` = `t4`.`value`
+WHERE `value` IS NOT NULL) AS `t2`
+LEFT JOIN (SELECT `key`
+FROM `default`.`src`) AS `t3` ON `t2`.`key` = `t3`.`key`) ON `t0`.`value` = `t2`.`value`
STAGE DEPENDENCIES:
Stage-1 is a root stage
Stage-2 depends on stages: Stage-1
@@ -1774,33 +1768,34 @@ STAGE PLANS:
Tez
#### A masked pattern was here ####
Edges:
- Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 5 (SIMPLE_EDGE)
- Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE)
- Reducer 5 <- Map 4 (SIMPLE_EDGE), Map 6 (SIMPLE_EDGE)
+ Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE)
+ Reducer 3 <- Map 6 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE)
+ Reducer 4 <- Reducer 3 (CUSTOM_SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
Map Operator Tree:
TableScan
- alias: z
+ alias: x
filterExpr: value is not null (type: boolean)
- Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE
GatherStats: false
Filter Operator
isSamplingPred: false
predicate: value is not null (type: boolean)
- Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
- expressions: value (type: string)
- outputColumnNames: _col0
- Statistics: Num rows: 500 Data size: 184500 Basic stats: COMPLETE Column stats: COMPLETE
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
null sort order: a
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 500 Data size: 184500 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE
tag: 0
+ value expressions: _col1 (type: string)
auto parallelism: true
Execution mode: vectorized, llap
LLAP IO: no inputs
@@ -1809,36 +1804,33 @@ STAGE PLANS:
Path -> Partition:
#### A masked pattern was here ####
Partition
- base file name: hr=11
+ base file name: src1
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-08
- hr 11
properties:
COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
+ bucketing_version 2
column.name.delimiter ,
columns key,value
columns.comments 'default','default'
columns.types string:string
#### A masked pattern was here ####
- name default.srcpart
+ name default.src1
numFiles 1
- numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 5312
- serialization.ddl struct srcpart { string key, string value}
+ numRows 25
+ rawDataSize 191
+ serialization.ddl struct src1 { string key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
+ totalSize 216
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
bucketing_version 2
column.name.delimiter ,
@@ -1846,19 +1838,21 @@ STAGE PLANS:
columns.comments 'default','default'
columns.types string:string
#### A masked pattern was here ####
- name default.srcpart
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct srcpart { string key, string value}
+ name default.src1
+ numFiles 1
+ numRows 25
+ rawDataSize 191
+ serialization.ddl struct src1 { string key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 216
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcpart
- name: default.srcpart
+ name: default.src1
+ name: default.src1
Truncated Path -> Alias:
- /srcpart/ds=2008-04-08/hr=11 [z]
- Map 4
+ /src1 [x]
+ Map 5
Map Operator Tree:
TableScan
alias: y
@@ -1874,7 +1868,7 @@ STAGE PLANS:
sort order: +
Map-reduce partition columns: _col0 (type: string)
Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
- tag: 0
+ tag: 1
auto parallelism: true
Execution mode: vectorized, llap
LLAP IO: no inputs
@@ -1934,26 +1928,25 @@ STAGE PLANS:
Map 6
Map Operator Tree:
TableScan
- alias: x
+ alias: z
filterExpr: value is not null (type: boolean)
- Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE
GatherStats: false
Filter Operator
isSamplingPred: false
predicate: value is not null (type: boolean)
- Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
- expressions: key (type: string), value (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE
+ expressions: value (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 500 Data size: 184500 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
null sort order: a
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 500 Data size: 184500 Basic stats: COMPLETE Column stats: COMPLETE
tag: 1
- value expressions: _col1 (type: string)
auto parallelism: true
Execution mode: vectorized, llap
LLAP IO: no inputs
@@ -1962,33 +1955,36 @@ STAGE PLANS:
Path -> Partition:
#### A masked pattern was here ####
Partition
- base file name: src1
+ base file name: hr=11
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ partition values:
+ ds 2008-04-08
+ hr 11
properties:
COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
- bucketing_version 2
column.name.delimiter ,
columns key,value
columns.comments 'default','default'
columns.types string:string
#### A masked pattern was here ####
- name default.src1
+ name default.srcpart
numFiles 1
- numRows 25
- rawDataSize 191
- serialization.ddl struct src1 { string key, string value}
+ numRows 500
+ partition_columns ds/hr
+ partition_columns.types string:string
+ rawDataSize 5312
+ serialization.ddl struct srcpart { string key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 216
+ totalSize 5812
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
bucketing_version 2
column.name.delimiter ,
@@ -1996,35 +1992,55 @@ STAGE PLANS:
columns.comments 'default','default'
columns.types string:string
#### A masked pattern was here ####
- name default.src1
- numFiles 1
- numRows 25
- rawDataSize 191
- serialization.ddl struct src1 { string key, string value}
+ name default.srcpart
+ partition_columns ds/hr
+ partition_columns.types string:string
+ serialization.ddl struct srcpart { string key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 216
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.src1
- name: default.src1
+ name: default.srcpart
+ name: default.srcpart
Truncated Path -> Alias:
- /src1 [x]
+ /srcpart/ds=2008-04-08/hr=11 [z]
Reducer 2
Execution mode: llap
Needs Tagging: false
Reduce Operator Tree:
Merge Join Operator
condition map:
- Inner Join 0 to 1
+ Left Outer Join 0 to 1
keys:
0 _col0 (type: string)
- 1 _col1 (type: string)
- outputColumnNames: _col0, _col3, _col4
- Position of Big Table: 1
+ 1 _col0 (type: string)
+ outputColumnNames: _col0, _col1
+ Position of Big Table: 0
+ Statistics: Num rows: 39 Data size: 6825 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col1 (type: string)
+ null sort order: a
+ sort order: +
+ Map-reduce partition columns: _col1 (type: string)
+ Statistics: Num rows: 39 Data size: 6825 Basic stats: COMPLETE Column stats: COMPLETE
+ tag: 0
+ value expressions: _col0 (type: string)
+ auto parallelism: true
+ Reducer 3
+ Execution mode: llap
+ Needs Tagging: false
+ Reduce Operator Tree:
+ Merge Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col1 (type: string)
+ 1 _col0 (type: string)
+ outputColumnNames: _col0, _col1, _col3
+ Position of Big Table: 0
Statistics: Num rows: 63 Data size: 16758 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
- expressions: _col3 (type: string), _col0 (type: string), _col4 (type: string)
+ expressions: _col0 (type: string), _col3 (type: string), _col1 (type: string)
outputColumnNames: _col0, _col1, _col2
Statistics: Num rows: 63 Data size: 16758 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
@@ -2076,7 +2092,7 @@ STAGE PLANS:
tag: -1
value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
auto parallelism: false
- Reducer 3
+ Reducer 4
Execution mode: llap
Needs Tagging: false
Reduce Operator Tree:
@@ -2107,32 +2123,6 @@ STAGE PLANS:
TotalFiles: 1
GatherStats: false
MultiFileSpray: false
- Reducer 5
- Execution mode: llap
- Needs Tagging: false
- Reduce Operator Tree:
- Merge Join Operator
- condition map:
- Right Outer Join 0 to 1
- keys:
- 0 _col0 (type: string)
- 1 _col0 (type: string)
- outputColumnNames: _col1, _col2
- Position of Big Table: 1
- Statistics: Num rows: 39 Data size: 6825 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: _col1 (type: string), _col2 (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 39 Data size: 6825 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- key expressions: _col1 (type: string)
- null sort order: a
- sort order: +
- Map-reduce partition columns: _col1 (type: string)
- Statistics: Num rows: 39 Data size: 6825 Basic stats: COMPLETE Column stats: COMPLETE
- tag: 1
- value expressions: _col0 (type: string)
- auto parallelism: true
Stage: Stage-2
Dependency Collection
@@ -2327,34 +2317,14 @@ STAGE PLANS:
Tez
#### A masked pattern was here ####
Edges:
- Map 4 <- Map 5 (BROADCAST_EDGE)
- Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE)
+ Map 1 <- Map 4 (BROADCAST_EDGE)
+ Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE)
Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
Map Operator Tree:
TableScan
- alias: x
- filterExpr: value is not null (type: boolean)
- Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE
- Filter Operator
- predicate: value is not null (type: boolean)
- Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: value (type: string)
- outputColumnNames: _col0
- Statistics: Num rows: 500 Data size: 184500 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 500 Data size: 184500 Basic stats: COMPLETE Column stats: COMPLETE
- Execution mode: vectorized, llap
- LLAP IO: no inputs
- Map 4
- Map Operator Tree:
- TableScan
alias: y
filterExpr: key is not null (type: boolean)
Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
@@ -2373,21 +2343,17 @@ STAGE PLANS:
1 _col0 (type: string)
outputColumnNames: _col1, _col2
input vertices:
- 1 Map 5
+ 1 Map 4
Statistics: Num rows: 39 Data size: 6825 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: _col1 (type: string), _col2 (type: string)
- outputColumnNames: _col0, _col1
+ Reduce Output Operator
+ key expressions: _col2 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col2 (type: string)
Statistics: Num rows: 39 Data size: 6825 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- key expressions: _col1 (type: string)
- sort order: +
- Map-reduce partition columns: _col1 (type: string)
- Statistics: Num rows: 39 Data size: 6825 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: _col0 (type: string)
+ value expressions: _col1 (type: string)
Execution mode: vectorized, llap
LLAP IO: no inputs
- Map 5
+ Map 4
Map Operator Tree:
TableScan
alias: x
@@ -2408,6 +2374,26 @@ STAGE PLANS:
value expressions: _col1 (type: string)
Execution mode: vectorized, llap
LLAP IO: no inputs
+ Map 5
+ Map Operator Tree:
+ TableScan
+ alias: x
+ filterExpr: value is not null (type: boolean)
+ Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: value is not null (type: boolean)
+ Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: value (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 500 Data size: 184500 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 500 Data size: 184500 Basic stats: COMPLETE Column stats: COMPLETE
+ Execution mode: vectorized, llap
+ LLAP IO: no inputs
Reducer 2
Execution mode: llap
Reduce Operator Tree:
@@ -2415,12 +2401,12 @@ STAGE PLANS:
condition map:
Inner Join 0 to 1
keys:
- 0 _col0 (type: string)
- 1 _col1 (type: string)
- outputColumnNames: _col0, _col3, _col4
+ 0 _col2 (type: string)
+ 1 _col0 (type: string)
+ outputColumnNames: _col1, _col2, _col3
Statistics: Num rows: 63 Data size: 16758 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
- expressions: _col3 (type: string), _col0 (type: string), _col4 (type: string)
+ expressions: _col1 (type: string), _col3 (type: string), _col2 (type: string)
outputColumnNames: _col0, _col1, _col2
Statistics: Num rows: 63 Data size: 16758 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
@@ -2620,8 +2606,8 @@ STAGE PLANS:
Tez
#### A masked pattern was here ####
Edges:
- Map 4 <- Map 5 (BROADCAST_EDGE)
- Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE)
+ Map 1 <- Map 4 (BROADCAST_EDGE)
+ Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE)
Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
@@ -2629,26 +2615,6 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: y
- filterExpr: value is not null (type: boolean)
- Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE
- Filter Operator
- predicate: value is not null (type: boolean)
- Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: value (type: string)
- outputColumnNames: _col0
- Statistics: Num rows: 500 Data size: 184500 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 500 Data size: 184500 Basic stats: COMPLETE Column stats: COMPLETE
- Execution mode: vectorized, llap
- LLAP IO: no inputs
- Map 4
- Map Operator Tree:
- TableScan
- alias: y
filterExpr: key is not null (type: boolean)
Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
@@ -2666,21 +2632,17 @@ STAGE PLANS:
1 _col0 (type: string)
outputColumnNames: _col1, _col2
input vertices:
- 1 Map 5
+ 1 Map 4
Statistics: Num rows: 39 Data size: 6825 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: _col1 (type: string), _col2 (type: string)
- outputColumnNames: _col0, _col1
+ Reduce Output Operator
+ key expressions: _col2 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col2 (type: string)
Statistics: Num rows: 39 Data size: 6825 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- key expressions: _col1 (type: string)
- sort order: +
- Map-reduce partition columns: _col1 (type: string)
- Statistics: Num rows: 39 Data size: 6825 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: _col0 (type: string)
+ value expressions: _col1 (type: string)
Execution mode: vectorized, llap
LLAP IO: no inputs
- Map 5
+ Map 4
Map Operator Tree:
TableScan
alias: x
@@ -2701,6 +2663,26 @@ STAGE PLANS:
value expressions: _col1 (type: string)
Execution mode: vectorized, llap
LLAP IO: no inputs
+ Map 5
+ Map Operator Tree:
+ TableScan
+ alias: y
+ filterExpr: value is not null (type: boolean)
+ Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: value is not null (type: boolean)
+ Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: value (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 500 Data size: 184500 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 500 Data size: 184500 Basic stats: COMPLETE Column stats: COMPLETE
+ Execution mode: vectorized, llap
+ LLAP IO: no inputs
Reducer 2
Execution mode: llap
Reduce Operator Tree:
@@ -2708,12 +2690,12 @@ STAGE PLANS:
condition map:
Inner Join 0 to 1
keys:
- 0 _col0 (type: string)
- 1 _col1 (type: string)
- outputColumnNames: _col0, _col3, _col4
+ 0 _col2 (type: string)
+ 1 _col0 (type: string)
+ outputColumnNames: _col1, _col2, _col3
Statistics: Num rows: 63 Data size: 16758 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
- expressions: _col3 (type: string), _col0 (type: string), _col4 (type: string)
+ expressions: _col1 (type: string), _col3 (type: string), _col2 (type: string)
outputColumnNames: _col0, _col1, _col2
Statistics: Num rows: 63 Data size: 16758 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
http://git-wip-us.apache.org/repos/asf/hive/blob/30c17911/ql/src/test/results/clientpositive/llap/llap_smb_ptf.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/llap_smb_ptf.q.out b/ql/src/test/results/clientpositive/llap/llap_smb_ptf.q.out
index 33da686..8ac21ff 100644
--- a/ql/src/test/results/clientpositive/llap/llap_smb_ptf.q.out
+++ b/ql/src/test/results/clientpositive/llap/llap_smb_ptf.q.out
@@ -644,15 +644,15 @@ STAGE PLANS:
outputColumnNames: _col0, _col1, _col2, _col3, _col5, _col6, _col7, _col9, _col10, _col11, _col12, _col13
Statistics: Num rows: 1 Data size: 504 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
- expressions: _col7 (type: int), _col0 (type: smallint), _col1 (type: string), _col2 (type: smallint), _col3 (type: string), _col5 (type: smallint), _col6 (type: string), _col9 (type: smallint), _col10 (type: smallint), _col12 (type: string), _col13 (type: string), _col11 (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11
+ expressions: _col7 (type: int), _col0 (type: smallint), _col1 (type: string), _col2 (type: smallint), _col3 (type: string), _col5 (type: smallint), _col6 (type: string), _col9 (type: smallint), _col10 (type: smallint), _col11 (type: string), _col12 (type: string), _col13 (type: string)
+ outputColumnNames: _col0, _col2, _col3, _col4, _col5, _col7, _col8, _col9, _col10, _col11, _col12, _col13
Statistics: Num rows: 1 Data size: 504 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: 504 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: _col1 (type: smallint), _col2 (type: string), _col3 (type: smallint), _col4 (type: string), _col5 (type: smallint), _col6 (type: string), _col7 (type: smallint), _col8 (type: smallint), _col9 (type: string), _col10 (type: string), _col11 (type: string)
+ value expressions: _col2 (type: smallint), _col3 (type: string), _col4 (type: smallint), _col5 (type: string), _col7 (type: smallint), _col8 (type: string), _col9 (type: smallint), _col10 (type: smallint), _col11 (type: string), _col12 (type: string), _col13 (type: string)
Reducer 5
Execution mode: llap
Reduce Operator Tree:
@@ -662,22 +662,26 @@ STAGE PLANS:
keys:
0 _col0 (type: int)
1 _col0 (type: int)
- outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12
+ outputColumnNames: _col0, _col2, _col3, _col4, _col5, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col15
Statistics: Num rows: 1 Data size: 504 Basic stats: COMPLETE Column stats: COMPLETE
- Filter Operator
- predicate: _col12 is null (type: boolean)
+ Select Operator
+ expressions: _col0 (type: int), _col2 (type: smallint), _col3 (type: string), _col4 (type: smallint), _col5 (type: string), _col7 (type: smallint), _col8 (type: string), _col9 (type: smallint), _col10 (type: smallint), _col12 (type: string), _col13 (type: string), _col11 (type: string), _col15 (type: int)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12
Statistics: Num rows: 1 Data size: 504 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: _col0 (type: int), _col1 (type: smallint), _col2 (type: string), _col3 (type: smallint), _col4 (type: string), _col5 (type: smallint), _col6 (type: string), _col7 (type: smallint), _col8 (type: smallint), _col9 (type: string), _col10 (type: string), _col11 (type: string), '201611160940' (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12
- Statistics: Num rows: 1 Data size: 600 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: false
+ Filter Operator
+ predicate: _col12 is null (type: boolean)
+ Statistics: Num rows: 1 Data size: 504 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: smallint), _col2 (type: string), _col3 (type: smallint), _col4 (type: string), _col5 (type: smallint), _col6 (type: string), _col7 (type: smallint), _col8 (type: smallint), _col9 (type: string), _col10 (type: string), _col11 (type: string), '201611160940' (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12
Statistics: Num rows: 1 Data size: 600 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
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 600 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 7
Execution mode: vectorized, llap
Reduce Operator Tree: