You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by xu...@apache.org on 2014/10/27 20:57:03 UTC
svn commit: r1634671 [12/46] - in /hive/branches/spark:
itests/src/test/resources/ ql/src/test/results/clientpositive/spark/
Added: hive/branches/spark/ql/src/test/results/clientpositive/spark/avro_joins.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/avro_joins.q.out?rev=1634671&view=auto
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/avro_joins.q.out (added)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/avro_joins.q.out Mon Oct 27 19:56:58 2014
@@ -0,0 +1,199 @@
+PREHOOK: query: -- SORT_QUERY_RESULTS
+
+-- verify that new joins bring in correct schemas (including evolved schemas)
+
+CREATE TABLE doctors4
+ROW FORMAT
+SERDE 'org.apache.hadoop.hive.serde2.avro.AvroSerDe'
+STORED AS
+INPUTFORMAT 'org.apache.hadoop.hive.ql.io.avro.AvroContainerInputFormat'
+OUTPUTFORMAT 'org.apache.hadoop.hive.ql.io.avro.AvroContainerOutputFormat'
+TBLPROPERTIES ('avro.schema.literal'='{
+ "namespace": "testing.hive.avro.serde",
+ "name": "doctors",
+ "type": "record",
+ "fields": [
+ {
+ "name":"number",
+ "type":"int",
+ "doc":"Order of playing the role"
+ },
+ {
+ "name":"first_name",
+ "type":"string",
+ "doc":"first name of actor playing role"
+ },
+ {
+ "name":"last_name",
+ "type":"string",
+ "doc":"last name of actor playing role"
+ },
+ {
+ "name":"extra_field",
+ "type":"string",
+ "doc:":"an extra field not in the original file",
+ "default":"fishfingers and custard"
+ }
+ ]
+}')
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@doctors4
+POSTHOOK: query: -- SORT_QUERY_RESULTS
+
+-- verify that new joins bring in correct schemas (including evolved schemas)
+
+CREATE TABLE doctors4
+ROW FORMAT
+SERDE 'org.apache.hadoop.hive.serde2.avro.AvroSerDe'
+STORED AS
+INPUTFORMAT 'org.apache.hadoop.hive.ql.io.avro.AvroContainerInputFormat'
+OUTPUTFORMAT 'org.apache.hadoop.hive.ql.io.avro.AvroContainerOutputFormat'
+TBLPROPERTIES ('avro.schema.literal'='{
+ "namespace": "testing.hive.avro.serde",
+ "name": "doctors",
+ "type": "record",
+ "fields": [
+ {
+ "name":"number",
+ "type":"int",
+ "doc":"Order of playing the role"
+ },
+ {
+ "name":"first_name",
+ "type":"string",
+ "doc":"first name of actor playing role"
+ },
+ {
+ "name":"last_name",
+ "type":"string",
+ "doc":"last name of actor playing role"
+ },
+ {
+ "name":"extra_field",
+ "type":"string",
+ "doc:":"an extra field not in the original file",
+ "default":"fishfingers and custard"
+ }
+ ]
+}')
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@doctors4
+PREHOOK: query: DESCRIBE doctors4
+PREHOOK: type: DESCTABLE
+PREHOOK: Input: default@doctors4
+POSTHOOK: query: DESCRIBE doctors4
+POSTHOOK: type: DESCTABLE
+POSTHOOK: Input: default@doctors4
+number int from deserializer
+first_name string from deserializer
+last_name string from deserializer
+extra_field string from deserializer
+PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/doctors.avro' INTO TABLE doctors4
+PREHOOK: type: LOAD
+#### A masked pattern was here ####
+PREHOOK: Output: default@doctors4
+POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/doctors.avro' INTO TABLE doctors4
+POSTHOOK: type: LOAD
+#### A masked pattern was here ####
+POSTHOOK: Output: default@doctors4
+PREHOOK: query: CREATE TABLE episodes
+ROW FORMAT
+SERDE 'org.apache.hadoop.hive.serde2.avro.AvroSerDe'
+STORED AS
+INPUTFORMAT 'org.apache.hadoop.hive.ql.io.avro.AvroContainerInputFormat'
+OUTPUTFORMAT 'org.apache.hadoop.hive.ql.io.avro.AvroContainerOutputFormat'
+TBLPROPERTIES ('avro.schema.literal'='{
+ "namespace": "testing.hive.avro.serde",
+ "name": "episodes",
+ "type": "record",
+ "fields": [
+ {
+ "name":"title",
+ "type":"string",
+ "doc":"episode title"
+ },
+ {
+ "name":"air_date",
+ "type":"string",
+ "doc":"initial date"
+ },
+ {
+ "name":"doctor",
+ "type":"int",
+ "doc":"main actor playing the Doctor in episode"
+ }
+ ]
+}')
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@episodes
+POSTHOOK: query: CREATE TABLE episodes
+ROW FORMAT
+SERDE 'org.apache.hadoop.hive.serde2.avro.AvroSerDe'
+STORED AS
+INPUTFORMAT 'org.apache.hadoop.hive.ql.io.avro.AvroContainerInputFormat'
+OUTPUTFORMAT 'org.apache.hadoop.hive.ql.io.avro.AvroContainerOutputFormat'
+TBLPROPERTIES ('avro.schema.literal'='{
+ "namespace": "testing.hive.avro.serde",
+ "name": "episodes",
+ "type": "record",
+ "fields": [
+ {
+ "name":"title",
+ "type":"string",
+ "doc":"episode title"
+ },
+ {
+ "name":"air_date",
+ "type":"string",
+ "doc":"initial date"
+ },
+ {
+ "name":"doctor",
+ "type":"int",
+ "doc":"main actor playing the Doctor in episode"
+ }
+ ]
+}')
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@episodes
+PREHOOK: query: DESCRIBE episodes
+PREHOOK: type: DESCTABLE
+PREHOOK: Input: default@episodes
+POSTHOOK: query: DESCRIBE episodes
+POSTHOOK: type: DESCTABLE
+POSTHOOK: Input: default@episodes
+title string from deserializer
+air_date string from deserializer
+doctor int from deserializer
+PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/episodes.avro' INTO TABLE episodes
+PREHOOK: type: LOAD
+#### A masked pattern was here ####
+PREHOOK: Output: default@episodes
+POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/episodes.avro' INTO TABLE episodes
+POSTHOOK: type: LOAD
+#### A masked pattern was here ####
+POSTHOOK: Output: default@episodes
+PREHOOK: query: SELECT e.title, e.air_date, d.first_name, d.last_name, d.extra_field, e.air_date
+FROM doctors4 d JOIN episodes e ON (d.number=e.doctor)
+PREHOOK: type: QUERY
+PREHOOK: Input: default@doctors4
+PREHOOK: Input: default@episodes
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT e.title, e.air_date, d.first_name, d.last_name, d.extra_field, e.air_date
+FROM doctors4 d JOIN episodes e ON (d.number=e.doctor)
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@doctors4
+POSTHOOK: Input: default@episodes
+#### A masked pattern was here ####
+An Unearthly Child 23 November 1963 William Hartnell fishfingers and custard 23 November 1963
+Castrolava 4 January 1982 Peter Davison fishfingers and custard 4 January 1982
+Horror of Fang Rock 3 September 1977 Tom Baker fishfingers and custard 3 September 1977
+Rose 26 March 2005 Christopher Eccleston fishfingers and custard 26 March 2005
+The Doctor's Wife 14 May 2011 Matt Smith fishfingers and custard 14 May 2011
+The Eleventh Hour 3 April 2010 Matt Smith fishfingers and custard 3 April 2010
+The Mysterious Planet 6 September 1986 Colin Baker fishfingers and custard 6 September 1986
+The Power of the Daleks 5 November 1966 Patrick Troughton fishfingers and custard 5 November 1966
Added: hive/branches/spark/ql/src/test/results/clientpositive/spark/avro_joins_native.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/avro_joins_native.q.out?rev=1634671&view=auto
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/avro_joins_native.q.out (added)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/avro_joins_native.q.out Mon Oct 27 19:56:58 2014
@@ -0,0 +1,94 @@
+PREHOOK: query: -- SORT_QUERY_RESULTS
+
+-- verify that new joins bring in correct schemas (including evolved schemas)
+
+CREATE TABLE doctors4 (
+ number int COMMENT "Order of playing the role",
+ first_name string COMMENT "first name of actor playing role",
+ last_name string COMMENT "last name of actor playing role")
+STORED AS AVRO
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@doctors4
+POSTHOOK: query: -- SORT_QUERY_RESULTS
+
+-- verify that new joins bring in correct schemas (including evolved schemas)
+
+CREATE TABLE doctors4 (
+ number int COMMENT "Order of playing the role",
+ first_name string COMMENT "first name of actor playing role",
+ last_name string COMMENT "last name of actor playing role")
+STORED AS AVRO
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@doctors4
+PREHOOK: query: DESCRIBE doctors4
+PREHOOK: type: DESCTABLE
+PREHOOK: Input: default@doctors4
+POSTHOOK: query: DESCRIBE doctors4
+POSTHOOK: type: DESCTABLE
+POSTHOOK: Input: default@doctors4
+number int from deserializer
+first_name string from deserializer
+last_name string from deserializer
+PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/doctors.avro' INTO TABLE doctors4
+PREHOOK: type: LOAD
+#### A masked pattern was here ####
+PREHOOK: Output: default@doctors4
+POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/doctors.avro' INTO TABLE doctors4
+POSTHOOK: type: LOAD
+#### A masked pattern was here ####
+POSTHOOK: Output: default@doctors4
+PREHOOK: query: CREATE TABLE episodes (
+ title string COMMENT "episode title",
+ air_date string COMMENT "initial date",
+ doctor int COMMENT "main actor playing the Doctor in episode")
+STORED AS AVRO
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@episodes
+POSTHOOK: query: CREATE TABLE episodes (
+ title string COMMENT "episode title",
+ air_date string COMMENT "initial date",
+ doctor int COMMENT "main actor playing the Doctor in episode")
+STORED AS AVRO
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@episodes
+PREHOOK: query: DESCRIBE episodes
+PREHOOK: type: DESCTABLE
+PREHOOK: Input: default@episodes
+POSTHOOK: query: DESCRIBE episodes
+POSTHOOK: type: DESCTABLE
+POSTHOOK: Input: default@episodes
+title string from deserializer
+air_date string from deserializer
+doctor int from deserializer
+PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/episodes.avro' INTO TABLE episodes
+PREHOOK: type: LOAD
+#### A masked pattern was here ####
+PREHOOK: Output: default@episodes
+POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/episodes.avro' INTO TABLE episodes
+POSTHOOK: type: LOAD
+#### A masked pattern was here ####
+POSTHOOK: Output: default@episodes
+PREHOOK: query: SELECT e.title, e.air_date, d.first_name, d.last_name, e.air_date
+FROM doctors4 d JOIN episodes e ON (d.number=e.doctor)
+PREHOOK: type: QUERY
+PREHOOK: Input: default@doctors4
+PREHOOK: Input: default@episodes
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT e.title, e.air_date, d.first_name, d.last_name, e.air_date
+FROM doctors4 d JOIN episodes e ON (d.number=e.doctor)
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@doctors4
+POSTHOOK: Input: default@episodes
+#### A masked pattern was here ####
+An Unearthly Child 23 November 1963 William Hartnell 23 November 1963
+Castrolava 4 January 1982 Peter Davison 4 January 1982
+Horror of Fang Rock 3 September 1977 Tom Baker 3 September 1977
+Rose 26 March 2005 Christopher Eccleston 26 March 2005
+The Doctor's Wife 14 May 2011 Matt Smith 14 May 2011
+The Eleventh Hour 3 April 2010 Matt Smith 3 April 2010
+The Mysterious Planet 6 September 1986 Colin Baker 6 September 1986
+The Power of the Daleks 5 November 1966 Patrick Troughton 5 November 1966
Added: hive/branches/spark/ql/src/test/results/clientpositive/spark/bucket_map_join_1.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/bucket_map_join_1.q.out?rev=1634671&view=auto
==============================================================================
Files hive/branches/spark/ql/src/test/results/clientpositive/spark/bucket_map_join_1.q.out (added) and hive/branches/spark/ql/src/test/results/clientpositive/spark/bucket_map_join_1.q.out Mon Oct 27 19:56:58 2014 differ
Added: hive/branches/spark/ql/src/test/results/clientpositive/spark/bucket_map_join_2.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/bucket_map_join_2.q.out?rev=1634671&view=auto
==============================================================================
Files hive/branches/spark/ql/src/test/results/clientpositive/spark/bucket_map_join_2.q.out (added) and hive/branches/spark/ql/src/test/results/clientpositive/spark/bucket_map_join_2.q.out Mon Oct 27 19:56:58 2014 differ
Added: hive/branches/spark/ql/src/test/results/clientpositive/spark/bucket_map_join_tez1.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/bucket_map_join_tez1.q.out?rev=1634671&view=auto
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/bucket_map_join_tez1.q.out (added)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/bucket_map_join_tez1.q.out Mon Oct 27 19:56:58 2014
@@ -0,0 +1,1253 @@
+PREHOOK: query: CREATE TABLE srcbucket_mapjoin(key int, value string) partitioned by (ds string) CLUSTERED BY (key) INTO 2 BUCKETS STORED AS TEXTFILE
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@srcbucket_mapjoin
+POSTHOOK: query: CREATE TABLE srcbucket_mapjoin(key int, value string) partitioned by (ds string) CLUSTERED BY (key) INTO 2 BUCKETS STORED AS TEXTFILE
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@srcbucket_mapjoin
+PREHOOK: query: CREATE TABLE tab_part (key int, value string) PARTITIONED BY(ds STRING) CLUSTERED BY (key) INTO 4 BUCKETS STORED AS TEXTFILE
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@tab_part
+POSTHOOK: query: CREATE TABLE tab_part (key int, value string) PARTITIONED BY(ds STRING) CLUSTERED BY (key) INTO 4 BUCKETS STORED AS TEXTFILE
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@tab_part
+PREHOOK: query: CREATE TABLE srcbucket_mapjoin_part (key int, value string) partitioned by (ds string) CLUSTERED BY (key) INTO 4 BUCKETS STORED AS TEXTFILE
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@srcbucket_mapjoin_part
+POSTHOOK: query: CREATE TABLE srcbucket_mapjoin_part (key int, value string) partitioned by (ds string) CLUSTERED BY (key) INTO 4 BUCKETS STORED AS TEXTFILE
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@srcbucket_mapjoin_part
+PREHOOK: query: load data local inpath '../../data/files/srcbucket20.txt' INTO TABLE srcbucket_mapjoin partition(ds='2008-04-08')
+PREHOOK: type: LOAD
+#### A masked pattern was here ####
+PREHOOK: Output: default@srcbucket_mapjoin
+POSTHOOK: query: load data local inpath '../../data/files/srcbucket20.txt' INTO TABLE srcbucket_mapjoin partition(ds='2008-04-08')
+POSTHOOK: type: LOAD
+#### A masked pattern was here ####
+POSTHOOK: Output: default@srcbucket_mapjoin
+POSTHOOK: Output: default@srcbucket_mapjoin@ds=2008-04-08
+PREHOOK: query: load data local inpath '../../data/files/srcbucket22.txt' INTO TABLE srcbucket_mapjoin partition(ds='2008-04-08')
+PREHOOK: type: LOAD
+#### A masked pattern was here ####
+PREHOOK: Output: default@srcbucket_mapjoin@ds=2008-04-08
+POSTHOOK: query: load data local inpath '../../data/files/srcbucket22.txt' INTO TABLE srcbucket_mapjoin partition(ds='2008-04-08')
+POSTHOOK: type: LOAD
+#### A masked pattern was here ####
+POSTHOOK: Output: default@srcbucket_mapjoin@ds=2008-04-08
+PREHOOK: query: load data local inpath '../../data/files/srcbucket20.txt' INTO TABLE srcbucket_mapjoin_part partition(ds='2008-04-08')
+PREHOOK: type: LOAD
+#### A masked pattern was here ####
+PREHOOK: Output: default@srcbucket_mapjoin_part
+POSTHOOK: query: load data local inpath '../../data/files/srcbucket20.txt' INTO TABLE srcbucket_mapjoin_part partition(ds='2008-04-08')
+POSTHOOK: type: LOAD
+#### A masked pattern was here ####
+POSTHOOK: Output: default@srcbucket_mapjoin_part
+POSTHOOK: Output: default@srcbucket_mapjoin_part@ds=2008-04-08
+PREHOOK: query: load data local inpath '../../data/files/srcbucket21.txt' INTO TABLE srcbucket_mapjoin_part partition(ds='2008-04-08')
+PREHOOK: type: LOAD
+#### A masked pattern was here ####
+PREHOOK: Output: default@srcbucket_mapjoin_part@ds=2008-04-08
+POSTHOOK: query: load data local inpath '../../data/files/srcbucket21.txt' INTO TABLE srcbucket_mapjoin_part partition(ds='2008-04-08')
+POSTHOOK: type: LOAD
+#### A masked pattern was here ####
+POSTHOOK: Output: default@srcbucket_mapjoin_part@ds=2008-04-08
+PREHOOK: query: load data local inpath '../../data/files/srcbucket22.txt' INTO TABLE srcbucket_mapjoin_part partition(ds='2008-04-08')
+PREHOOK: type: LOAD
+#### A masked pattern was here ####
+PREHOOK: Output: default@srcbucket_mapjoin_part@ds=2008-04-08
+POSTHOOK: query: load data local inpath '../../data/files/srcbucket22.txt' INTO TABLE srcbucket_mapjoin_part partition(ds='2008-04-08')
+POSTHOOK: type: LOAD
+#### A masked pattern was here ####
+POSTHOOK: Output: default@srcbucket_mapjoin_part@ds=2008-04-08
+PREHOOK: query: load data local inpath '../../data/files/srcbucket23.txt' INTO TABLE srcbucket_mapjoin_part partition(ds='2008-04-08')
+PREHOOK: type: LOAD
+#### A masked pattern was here ####
+PREHOOK: Output: default@srcbucket_mapjoin_part@ds=2008-04-08
+POSTHOOK: query: load data local inpath '../../data/files/srcbucket23.txt' INTO TABLE srcbucket_mapjoin_part partition(ds='2008-04-08')
+POSTHOOK: type: LOAD
+#### A masked pattern was here ####
+POSTHOOK: Output: default@srcbucket_mapjoin_part@ds=2008-04-08
+PREHOOK: query: insert overwrite table tab_part partition (ds='2008-04-08')
+select key,value from srcbucket_mapjoin_part
+PREHOOK: type: QUERY
+PREHOOK: Input: default@srcbucket_mapjoin_part
+PREHOOK: Input: default@srcbucket_mapjoin_part@ds=2008-04-08
+PREHOOK: Output: default@tab_part@ds=2008-04-08
+[Error 30017]: Skipping stats aggregation by error org.apache.hadoop.hive.ql.metadata.HiveException: [Error 30015]: Stats aggregator of type counter cannot be connected to
+POSTHOOK: query: insert overwrite table tab_part partition (ds='2008-04-08')
+select key,value from srcbucket_mapjoin_part
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@srcbucket_mapjoin_part
+POSTHOOK: Input: default@srcbucket_mapjoin_part@ds=2008-04-08
+POSTHOOK: Output: default@tab_part@ds=2008-04-08
+POSTHOOK: Lineage: tab_part PARTITION(ds=2008-04-08).key SIMPLE [(srcbucket_mapjoin_part)srcbucket_mapjoin_part.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: tab_part PARTITION(ds=2008-04-08).value SIMPLE [(srcbucket_mapjoin_part)srcbucket_mapjoin_part.FieldSchema(name:value, type:string, comment:null), ]
+PREHOOK: query: CREATE TABLE tab(key int, value string) PARTITIONED BY(ds STRING) CLUSTERED BY (key) INTO 2 BUCKETS STORED AS TEXTFILE
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@tab
+POSTHOOK: query: CREATE TABLE tab(key int, value string) PARTITIONED BY(ds STRING) CLUSTERED BY (key) INTO 2 BUCKETS STORED AS TEXTFILE
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@tab
+PREHOOK: query: insert overwrite table tab partition (ds='2008-04-08')
+select key,value from srcbucket_mapjoin
+PREHOOK: type: QUERY
+PREHOOK: Input: default@srcbucket_mapjoin
+PREHOOK: Input: default@srcbucket_mapjoin@ds=2008-04-08
+PREHOOK: Output: default@tab@ds=2008-04-08
+[Error 30017]: Skipping stats aggregation by error org.apache.hadoop.hive.ql.metadata.HiveException: [Error 30015]: Stats aggregator of type counter cannot be connected to
+POSTHOOK: query: insert overwrite table tab partition (ds='2008-04-08')
+select key,value from srcbucket_mapjoin
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@srcbucket_mapjoin
+POSTHOOK: Input: default@srcbucket_mapjoin@ds=2008-04-08
+POSTHOOK: Output: default@tab@ds=2008-04-08
+POSTHOOK: Lineage: tab PARTITION(ds=2008-04-08).key SIMPLE [(srcbucket_mapjoin)srcbucket_mapjoin.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: tab PARTITION(ds=2008-04-08).value SIMPLE [(srcbucket_mapjoin)srcbucket_mapjoin.FieldSchema(name:value, type:string, comment:null), ]
+PREHOOK: query: explain
+select a.key, a.value, b.value
+from tab a join tab_part b on a.key = b.key
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+select a.key, a.value, b.value
+from tab a join tab_part b on a.key = b.key
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Spark
+ Edges:
+ Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 1), Map 3 (GROUP PARTITION-LEVEL SORT, 1)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: b
+ Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 28 Data size: 2958 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: int)
+ sort order: +
+ Map-reduce partition columns: key (type: int)
+ Statistics: Num rows: 28 Data size: 2958 Basic stats: COMPLETE Column stats: NONE
+ value expressions: value (type: string)
+ Map 3
+ Map Operator Tree:
+ TableScan
+ alias: a
+ Statistics: Num rows: 27 Data size: 2808 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 14 Data size: 1456 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: int)
+ sort order: +
+ Map-reduce partition columns: key (type: int)
+ Statistics: Num rows: 14 Data size: 1456 Basic stats: COMPLETE Column stats: NONE
+ value expressions: value (type: string)
+ Reducer 2
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {KEY.reducesinkkey0} {VALUE._col0}
+ 1 {VALUE._col0}
+ outputColumnNames: _col0, _col1, _col7
+ Statistics: Num rows: 30 Data size: 3253 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string), _col7 (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 30 Data size: 3253 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 30 Data size: 3253 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: -- one side is really bucketed. srcbucket_mapjoin is not really a bucketed table.
+-- In this case the sub-query is chosen as the big table.
+explain
+select a.k1, a.v1, b.value
+from (select sum(substr(srcbucket_mapjoin.value,5)) as v1, key as k1 from srcbucket_mapjoin GROUP BY srcbucket_mapjoin.key) a
+join tab b on a.k1 = b.key
+PREHOOK: type: QUERY
+POSTHOOK: query: -- one side is really bucketed. srcbucket_mapjoin is not really a bucketed table.
+-- In this case the sub-query is chosen as the big table.
+explain
+select a.k1, a.v1, b.value
+from (select sum(substr(srcbucket_mapjoin.value,5)) as v1, key as k1 from srcbucket_mapjoin GROUP BY srcbucket_mapjoin.key) a
+join tab b on a.k1 = b.key
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Spark
+ Edges:
+ Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 1), Reducer 4 (GROUP PARTITION-LEVEL SORT, 1)
+ Reducer 4 <- Map 3 (GROUP, 1)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: b
+ Statistics: Num rows: 27 Data size: 2808 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 14 Data size: 1456 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: int)
+ sort order: +
+ Map-reduce partition columns: key (type: int)
+ Statistics: Num rows: 14 Data size: 1456 Basic stats: COMPLETE Column stats: NONE
+ value expressions: value (type: string)
+ Map 3
+ Map Operator Tree:
+ TableScan
+ alias: srcbucket_mapjoin
+ Statistics: Num rows: 27 Data size: 2808 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 14 Data size: 1456 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: int), value (type: string)
+ outputColumnNames: key, value
+ Statistics: Num rows: 14 Data size: 1456 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: sum(substr(value, 5))
+ keys: key (type: int)
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 14 Data size: 1456 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 14 Data size: 1456 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: double)
+ Reducer 2
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {VALUE._col0} {KEY.reducesinkkey0}
+ 1 {VALUE._col0}
+ outputColumnNames: _col0, _col1, _col3
+ Statistics: Num rows: 15 Data size: 1601 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col1 (type: int), _col0 (type: double), _col3 (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 15 Data size: 1601 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 15 Data size: 1601 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ Reducer 4
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: sum(VALUE._col0)
+ keys: KEY._col0 (type: int)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 7 Data size: 728 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col1 (type: double), _col0 (type: int)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 7 Data size: 728 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col1 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col1 (type: int)
+ Statistics: Num rows: 7 Data size: 728 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: double)
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: explain
+select a.k1, a.v1, b.value
+from (select sum(substr(tab.value,5)) as v1, key as k1 from tab_part join tab on tab_part.key = tab.key GROUP BY tab.key) a
+join tab b on a.k1 = b.key
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+select a.k1, a.v1, b.value
+from (select sum(substr(tab.value,5)) as v1, key as k1 from tab_part join tab on tab_part.key = tab.key GROUP BY tab.key) a
+join tab b on a.k1 = b.key
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Spark
+ Edges:
+ Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 1), Reducer 5 (GROUP PARTITION-LEVEL SORT, 1)
+ Reducer 4 <- Map 3 (GROUP PARTITION-LEVEL SORT, 1), Map 6 (GROUP PARTITION-LEVEL SORT, 1)
+ Reducer 5 <- Reducer 4 (GROUP, 1)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: b
+ Statistics: Num rows: 27 Data size: 2808 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 14 Data size: 1456 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: int)
+ sort order: +
+ Map-reduce partition columns: key (type: int)
+ Statistics: Num rows: 14 Data size: 1456 Basic stats: COMPLETE Column stats: NONE
+ value expressions: value (type: string)
+ Map 3
+ Map Operator Tree:
+ TableScan
+ alias: tab_part
+ Statistics: Num rows: 1453 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 727 Data size: 2908 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: int)
+ sort order: +
+ Map-reduce partition columns: key (type: int)
+ Statistics: Num rows: 727 Data size: 2908 Basic stats: COMPLETE Column stats: NONE
+ Map 6
+ Map Operator Tree:
+ TableScan
+ alias: tab
+ Statistics: Num rows: 27 Data size: 2808 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 14 Data size: 1456 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: int)
+ sort order: +
+ Map-reduce partition columns: key (type: int)
+ Statistics: Num rows: 14 Data size: 1456 Basic stats: COMPLETE Column stats: NONE
+ value expressions: value (type: string)
+ Reducer 2
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {VALUE._col0} {KEY.reducesinkkey0}
+ 1 {VALUE._col0}
+ outputColumnNames: _col0, _col1, _col3
+ Statistics: Num rows: 438 Data size: 1755 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col1 (type: int), _col0 (type: double), _col3 (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 438 Data size: 1755 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 438 Data size: 1755 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ Reducer 4
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0
+ 1 {KEY.reducesinkkey0} {VALUE._col0}
+ outputColumnNames: _col6, _col7
+ Statistics: Num rows: 799 Data size: 3198 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col6 (type: int), _col7 (type: string)
+ outputColumnNames: _col6, _col7
+ Statistics: Num rows: 799 Data size: 3198 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: sum(substr(_col7, 5))
+ keys: _col6 (type: int)
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 799 Data size: 3198 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 799 Data size: 3198 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: double)
+ Reducer 5
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: sum(VALUE._col0)
+ keys: KEY._col0 (type: int)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 399 Data size: 1596 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col1 (type: double), _col0 (type: int)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 399 Data size: 1596 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col1 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col1 (type: int)
+ Statistics: Num rows: 399 Data size: 1596 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: double)
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: explain
+select a.k1, a.v1, b.value
+from (select sum(substr(x.value,5)) as v1, x.key as k1 from tab x join tab y on x.key = y.key GROUP BY x.key) a
+join tab_part b on a.k1 = b.key
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+select a.k1, a.v1, b.value
+from (select sum(substr(x.value,5)) as v1, x.key as k1 from tab x join tab y on x.key = y.key GROUP BY x.key) a
+join tab_part b on a.k1 = b.key
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Spark
+ Edges:
+ Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 1), Reducer 5 (GROUP PARTITION-LEVEL SORT, 1)
+ Reducer 4 <- Map 3 (GROUP PARTITION-LEVEL SORT, 1), Map 6 (GROUP PARTITION-LEVEL SORT, 1)
+ Reducer 5 <- Reducer 4 (GROUP, 1)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: b
+ Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 28 Data size: 2958 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: int)
+ sort order: +
+ Map-reduce partition columns: key (type: int)
+ Statistics: Num rows: 28 Data size: 2958 Basic stats: COMPLETE Column stats: NONE
+ value expressions: value (type: string)
+ Map 3
+ Map Operator Tree:
+ TableScan
+ alias: x
+ Statistics: Num rows: 27 Data size: 2808 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 14 Data size: 1456 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: int)
+ sort order: +
+ Map-reduce partition columns: key (type: int)
+ Statistics: Num rows: 14 Data size: 1456 Basic stats: COMPLETE Column stats: NONE
+ value expressions: value (type: string)
+ Map 6
+ Map Operator Tree:
+ TableScan
+ alias: y
+ Statistics: Num rows: 702 Data size: 2808 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 351 Data size: 1404 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: int)
+ sort order: +
+ Map-reduce partition columns: key (type: int)
+ Statistics: Num rows: 351 Data size: 1404 Basic stats: COMPLETE Column stats: NONE
+ Reducer 2
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {VALUE._col0} {KEY.reducesinkkey0}
+ 1 {VALUE._col0}
+ outputColumnNames: _col0, _col1, _col3
+ Statistics: Num rows: 212 Data size: 849 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col1 (type: int), _col0 (type: double), _col3 (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 212 Data size: 849 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 212 Data size: 849 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ Reducer 4
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {KEY.reducesinkkey0} {VALUE._col0}
+ 1
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 386 Data size: 1544 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 386 Data size: 1544 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: sum(substr(_col1, 5))
+ keys: _col0 (type: int)
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 386 Data size: 1544 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 386 Data size: 1544 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: double)
+ Reducer 5
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: sum(VALUE._col0)
+ keys: KEY._col0 (type: int)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 193 Data size: 772 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col1 (type: double), _col0 (type: int)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 193 Data size: 772 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col1 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col1 (type: int)
+ Statistics: Num rows: 193 Data size: 772 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: double)
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: -- multi-way join
+explain
+select a.key, a.value, b.value
+from tab_part a join tab b on a.key = b.key join tab c on a.key = c.key
+PREHOOK: type: QUERY
+POSTHOOK: query: -- multi-way join
+explain
+select a.key, a.value, b.value
+from tab_part a join tab b on a.key = b.key join tab c on a.key = c.key
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Spark
+ Edges:
+ Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 1), Map 3 (GROUP PARTITION-LEVEL SORT, 1), Map 4 (GROUP PARTITION-LEVEL SORT, 1)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: b
+ Statistics: Num rows: 27 Data size: 2808 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 14 Data size: 1456 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: int)
+ sort order: +
+ Map-reduce partition columns: key (type: int)
+ Statistics: Num rows: 14 Data size: 1456 Basic stats: COMPLETE Column stats: NONE
+ value expressions: value (type: string)
+ Map 3
+ Map Operator Tree:
+ TableScan
+ alias: c
+ Statistics: Num rows: 702 Data size: 2808 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 351 Data size: 1404 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: int)
+ sort order: +
+ Map-reduce partition columns: key (type: int)
+ Statistics: Num rows: 351 Data size: 1404 Basic stats: COMPLETE Column stats: NONE
+ Map 4
+ Map Operator Tree:
+ TableScan
+ alias: a
+ Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 28 Data size: 2958 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: int)
+ sort order: +
+ Map-reduce partition columns: key (type: int)
+ Statistics: Num rows: 28 Data size: 2958 Basic stats: COMPLETE Column stats: NONE
+ value expressions: value (type: string)
+ Reducer 2
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ Inner Join 0 to 2
+ condition expressions:
+ 0 {KEY.reducesinkkey0} {VALUE._col0}
+ 1 {VALUE._col0}
+ 2
+ outputColumnNames: _col0, _col1, _col7
+ Statistics: Num rows: 772 Data size: 3088 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string), _col7 (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 772 Data size: 3088 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 772 Data size: 3088 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: explain
+select a.key, a.value, c.value
+from (select x.key, x.value from tab_part x join tab y on x.key = y.key) a join tab c on a.key = c.key
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+select a.key, a.value, c.value
+from (select x.key, x.value from tab_part x join tab y on x.key = y.key) a join tab c on a.key = c.key
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Spark
+ Edges:
+ Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 1), Reducer 4 (GROUP PARTITION-LEVEL SORT, 1)
+ Reducer 4 <- Map 3 (GROUP PARTITION-LEVEL SORT, 1), Map 5 (GROUP PARTITION-LEVEL SORT, 1)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: c
+ Statistics: Num rows: 27 Data size: 2808 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 14 Data size: 1456 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: int)
+ sort order: +
+ Map-reduce partition columns: key (type: int)
+ Statistics: Num rows: 14 Data size: 1456 Basic stats: COMPLETE Column stats: NONE
+ value expressions: value (type: string)
+ Map 3
+ Map Operator Tree:
+ TableScan
+ alias: x
+ Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 28 Data size: 2958 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: int)
+ sort order: +
+ Map-reduce partition columns: key (type: int)
+ Statistics: Num rows: 28 Data size: 2958 Basic stats: COMPLETE Column stats: NONE
+ value expressions: value (type: string)
+ Map 5
+ Map Operator Tree:
+ TableScan
+ alias: y
+ Statistics: Num rows: 702 Data size: 2808 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 351 Data size: 1404 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: int)
+ sort order: +
+ Map-reduce partition columns: key (type: int)
+ Statistics: Num rows: 351 Data size: 1404 Basic stats: COMPLETE Column stats: NONE
+ Reducer 2
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {KEY.reducesinkkey0} {VALUE._col0}
+ 1 {VALUE._col0}
+ outputColumnNames: _col0, _col1, _col3
+ Statistics: Num rows: 424 Data size: 1698 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 424 Data size: 1698 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 424 Data size: 1698 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ Reducer 4
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {KEY.reducesinkkey0} {VALUE._col0}
+ 1
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 386 Data size: 1544 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 386 Data size: 1544 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 386 Data size: 1544 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: string)
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: -- in this case sub-query is the small table
+explain
+select a.key, a.value, b.value
+from (select key, sum(substr(srcbucket_mapjoin.value,5)) as value from srcbucket_mapjoin GROUP BY srcbucket_mapjoin.key) a
+join tab_part b on a.key = b.key
+PREHOOK: type: QUERY
+POSTHOOK: query: -- in this case sub-query is the small table
+explain
+select a.key, a.value, b.value
+from (select key, sum(substr(srcbucket_mapjoin.value,5)) as value from srcbucket_mapjoin GROUP BY srcbucket_mapjoin.key) a
+join tab_part b on a.key = b.key
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Spark
+ Edges:
+ Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 1), Reducer 4 (GROUP PARTITION-LEVEL SORT, 1)
+ Reducer 4 <- Map 3 (GROUP, 1)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: b
+ Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 28 Data size: 2958 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: int)
+ sort order: +
+ Map-reduce partition columns: key (type: int)
+ Statistics: Num rows: 28 Data size: 2958 Basic stats: COMPLETE Column stats: NONE
+ value expressions: value (type: string)
+ Map 3
+ Map Operator Tree:
+ TableScan
+ alias: srcbucket_mapjoin
+ Statistics: Num rows: 27 Data size: 2808 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 14 Data size: 1456 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: int), value (type: string)
+ outputColumnNames: key, value
+ Statistics: Num rows: 14 Data size: 1456 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: sum(substr(value, 5))
+ keys: key (type: int)
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 14 Data size: 1456 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 14 Data size: 1456 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: double)
+ Reducer 2
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {KEY.reducesinkkey0} {VALUE._col0}
+ 1 {VALUE._col0}
+ outputColumnNames: _col0, _col1, _col3
+ Statistics: Num rows: 30 Data size: 3253 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: double), _col3 (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 30 Data size: 3253 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 30 Data size: 3253 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ Reducer 4
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: sum(VALUE._col0)
+ keys: KEY._col0 (type: int)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 7 Data size: 728 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: double)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 7 Data size: 728 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 7 Data size: 728 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: double)
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: explain
+select a.key, a.value, b.value
+from (select key, sum(substr(srcbucket_mapjoin.value,5)) as value from srcbucket_mapjoin GROUP BY srcbucket_mapjoin.key) a
+join tab_part b on a.key = b.key
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+select a.key, a.value, b.value
+from (select key, sum(substr(srcbucket_mapjoin.value,5)) as value from srcbucket_mapjoin GROUP BY srcbucket_mapjoin.key) a
+join tab_part b on a.key = b.key
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Spark
+ Edges:
+ Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 1), Reducer 4 (GROUP PARTITION-LEVEL SORT, 1)
+ Reducer 4 <- Map 3 (GROUP, 1)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: b
+ Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 28 Data size: 2958 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: int)
+ sort order: +
+ Map-reduce partition columns: key (type: int)
+ Statistics: Num rows: 28 Data size: 2958 Basic stats: COMPLETE Column stats: NONE
+ value expressions: value (type: string)
+ Map 3
+ Map Operator Tree:
+ TableScan
+ alias: srcbucket_mapjoin
+ Statistics: Num rows: 27 Data size: 2808 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 14 Data size: 1456 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: int), value (type: string)
+ outputColumnNames: key, value
+ Statistics: Num rows: 14 Data size: 1456 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: int)
+ sort order: +
+ Map-reduce partition columns: key (type: int)
+ Statistics: Num rows: 14 Data size: 1456 Basic stats: COMPLETE Column stats: NONE
+ value expressions: substr(value, 5) (type: string)
+ Reducer 2
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {KEY.reducesinkkey0} {VALUE._col0}
+ 1 {VALUE._col0}
+ outputColumnNames: _col0, _col1, _col3
+ Statistics: Num rows: 30 Data size: 3253 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: double), _col3 (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 30 Data size: 3253 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 30 Data size: 3253 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ Reducer 4
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: sum(VALUE._col0)
+ keys: KEY._col0 (type: int)
+ mode: complete
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 7 Data size: 728 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: double)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 7 Data size: 728 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 7 Data size: 728 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: double)
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: -- join on non-bucketed column results in broadcast join.
+explain
+select a.key, a.value, b.value
+from tab a join tab_part b on a.value = b.value
+PREHOOK: type: QUERY
+POSTHOOK: query: -- join on non-bucketed column results in broadcast join.
+explain
+select a.key, a.value, b.value
+from tab a join tab_part b on a.value = b.value
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Spark
+ Edges:
+ Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 1), Map 3 (GROUP PARTITION-LEVEL SORT, 1)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: b
+ Statistics: Num rows: 58 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: value is not null (type: boolean)
+ Statistics: Num rows: 29 Data size: 2906 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: value (type: string)
+ sort order: +
+ Map-reduce partition columns: value (type: string)
+ Statistics: Num rows: 29 Data size: 2906 Basic stats: COMPLETE Column stats: NONE
+ Map 3
+ Map Operator Tree:
+ TableScan
+ alias: a
+ Statistics: Num rows: 27 Data size: 2808 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: value is not null (type: boolean)
+ Statistics: Num rows: 14 Data size: 1456 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: value (type: string)
+ sort order: +
+ Map-reduce partition columns: value (type: string)
+ Statistics: Num rows: 14 Data size: 1456 Basic stats: COMPLETE Column stats: NONE
+ value expressions: key (type: int)
+ Reducer 2
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {VALUE._col0} {KEY.reducesinkkey0}
+ 1 {KEY.reducesinkkey0}
+ outputColumnNames: _col0, _col1, _col7
+ Statistics: Num rows: 31 Data size: 3196 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string), _col7 (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 31 Data size: 3196 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 31 Data size: 3196 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: CREATE TABLE tab1(key int, value string) CLUSTERED BY (key) INTO 2 BUCKETS STORED AS TEXTFILE
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@tab1
+POSTHOOK: query: CREATE TABLE tab1(key int, value string) CLUSTERED BY (key) INTO 2 BUCKETS STORED AS TEXTFILE
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@tab1
+PREHOOK: query: insert overwrite table tab1
+select key,value from srcbucket_mapjoin
+PREHOOK: type: QUERY
+PREHOOK: Input: default@srcbucket_mapjoin
+PREHOOK: Input: default@srcbucket_mapjoin@ds=2008-04-08
+PREHOOK: Output: default@tab1
+[Error 30017]: Skipping stats aggregation by error org.apache.hadoop.hive.ql.metadata.HiveException: [Error 30015]: Stats aggregator of type counter cannot be connected to
+POSTHOOK: query: insert overwrite table tab1
+select key,value from srcbucket_mapjoin
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@srcbucket_mapjoin
+POSTHOOK: Input: default@srcbucket_mapjoin@ds=2008-04-08
+POSTHOOK: Output: default@tab1
+POSTHOOK: Lineage: tab1.key SIMPLE [(srcbucket_mapjoin)srcbucket_mapjoin.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: tab1.value SIMPLE [(srcbucket_mapjoin)srcbucket_mapjoin.FieldSchema(name:value, type:string, comment:null), ]
+PREHOOK: query: explain
+select a.key, a.value, b.value
+from tab1 a join tab_part b on a.key = b.key
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+select a.key, a.value, b.value
+from tab1 a join tab_part b on a.key = b.key
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Spark
+ Edges:
+ Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 1), Map 3 (GROUP PARTITION-LEVEL SORT, 1)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: b
+ Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 28 Data size: 2958 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: int)
+ sort order: +
+ Map-reduce partition columns: key (type: int)
+ Statistics: Num rows: 28 Data size: 2958 Basic stats: COMPLETE Column stats: NONE
+ value expressions: value (type: string)
+ Map 3
+ Map Operator Tree:
+ TableScan
+ alias: a
+ Statistics: Num rows: 27 Data size: 2808 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 14 Data size: 1456 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: int)
+ sort order: +
+ Map-reduce partition columns: key (type: int)
+ Statistics: Num rows: 14 Data size: 1456 Basic stats: COMPLETE Column stats: NONE
+ value expressions: value (type: string)
+ Reducer 2
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {KEY.reducesinkkey0} {VALUE._col0}
+ 1 {VALUE._col0}
+ outputColumnNames: _col0, _col1, _col6
+ Statistics: Num rows: 30 Data size: 3253 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string), _col6 (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 30 Data size: 3253 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 30 Data size: 3253 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: explain select a.key, b.key from tab_part a join tab_part c on a.key = c.key join tab_part b on a.value = b.value
+PREHOOK: type: QUERY
+POSTHOOK: query: explain select a.key, b.key from tab_part a join tab_part c on a.key = c.key join tab_part b on a.value = b.value
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Spark
+ Edges:
+ Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 1), Reducer 4 (GROUP PARTITION-LEVEL SORT, 1)
+ Reducer 4 <- Map 3 (GROUP PARTITION-LEVEL SORT, 1), Map 5 (GROUP PARTITION-LEVEL SORT, 1)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: b
+ Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: value is not null (type: boolean)
+ Statistics: Num rows: 28 Data size: 2958 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: value (type: string)
+ sort order: +
+ Map-reduce partition columns: value (type: string)
+ Statistics: Num rows: 28 Data size: 2958 Basic stats: COMPLETE Column stats: NONE
+ value expressions: key (type: int)
+ Map 3
+ Map Operator Tree:
+ TableScan
+ alias: c
+ Statistics: Num rows: 1453 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 727 Data size: 2908 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: int)
+ sort order: +
+ Map-reduce partition columns: key (type: int)
+ Statistics: Num rows: 727 Data size: 2908 Basic stats: COMPLETE Column stats: NONE
+ Map 5
+ Map Operator Tree:
+ TableScan
+ alias: a
+ Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (key is not null and value is not null) (type: boolean)
+ Statistics: Num rows: 14 Data size: 1479 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: int)
+ sort order: +
+ Map-reduce partition columns: key (type: int)
+ Statistics: Num rows: 14 Data size: 1479 Basic stats: COMPLETE Column stats: NONE
+ value expressions: value (type: string)
+ Reducer 2
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {VALUE._col0}
+ 1 {VALUE._col0}
+ outputColumnNames: _col0, _col12
+ Statistics: Num rows: 878 Data size: 3517 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: int), _col12 (type: int)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 878 Data size: 3517 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 878 Data size: 3517 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ Reducer 4
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {KEY.reducesinkkey0} {VALUE._col0}
+ 1
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 799 Data size: 3198 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col1 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col1 (type: string)
+ Statistics: Num rows: 799 Data size: 3198 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: int)
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+