You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by gu...@apache.org on 2014/10/30 00:28:30 UTC
svn commit: r1635338 - in /hive/trunk: itests/src/test/resources/
ql/src/java/org/apache/hadoop/hive/ql/optimizer/
ql/src/java/org/apache/hadoop/hive/ql/parse/
ql/src/test/results/clientpositive/tez/
Author: gunther
Date: Wed Oct 29 23:28:30 2014
New Revision: 1635338
URL: http://svn.apache.org/r1635338
Log:
HIVE-8641: Disable skew joins in tez. (Vikram Dixit K via Gunther Hagleitner)
Added:
hive/trunk/ql/src/test/results/clientpositive/tez/skewjoin.q.out
Modified:
hive/trunk/itests/src/test/resources/testconfiguration.properties
hive/trunk/ql/src/java/org/apache/hadoop/hive/ql/optimizer/Optimizer.java
hive/trunk/ql/src/java/org/apache/hadoop/hive/ql/parse/SemanticAnalyzer.java
Modified: hive/trunk/itests/src/test/resources/testconfiguration.properties
URL: http://svn.apache.org/viewvc/hive/trunk/itests/src/test/resources/testconfiguration.properties?rev=1635338&r1=1635337&r2=1635338&view=diff
==============================================================================
--- hive/trunk/itests/src/test/resources/testconfiguration.properties (original)
+++ hive/trunk/itests/src/test/resources/testconfiguration.properties Wed Oct 29 23:28:30 2014
@@ -127,6 +127,7 @@ minitez.query.files.shared=alter_merge_2
script_pipe.q,\
scriptfile1.q,\
select_dummy_source.q,\
+ skewjoin.q,\
stats_counter.q,\
stats_counter_partitioned.q,\
stats_noscan_1.q,\
Modified: hive/trunk/ql/src/java/org/apache/hadoop/hive/ql/optimizer/Optimizer.java
URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/java/org/apache/hadoop/hive/ql/optimizer/Optimizer.java?rev=1635338&r1=1635337&r2=1635338&view=diff
==============================================================================
--- hive/trunk/ql/src/java/org/apache/hadoop/hive/ql/optimizer/Optimizer.java (original)
+++ hive/trunk/ql/src/java/org/apache/hadoop/hive/ql/optimizer/Optimizer.java Wed Oct 29 23:28:30 2014
@@ -21,6 +21,8 @@ package org.apache.hadoop.hive.ql.optimi
import java.util.ArrayList;
import java.util.List;
+import org.apache.commons.logging.Log;
+import org.apache.commons.logging.LogFactory;
import org.apache.hadoop.hive.conf.HiveConf;
import org.apache.hadoop.hive.ql.optimizer.correlation.CorrelationOptimizer;
import org.apache.hadoop.hive.ql.optimizer.correlation.ReduceSinkDeDuplication;
@@ -44,6 +46,7 @@ import org.apache.hadoop.hive.ql.ppd.Syn
public class Optimizer {
private ParseContext pctx;
private List<Transform> transformations;
+ private static final Log LOG = LogFactory.getLog(Optimizer.class.getName());
/**
* Create the list of transformations.
@@ -87,7 +90,11 @@ public class Optimizer {
}
transformations.add(new ColumnPruner());
if (HiveConf.getBoolVar(hiveConf, HiveConf.ConfVars.HIVE_OPTIMIZE_SKEWJOIN_COMPILETIME)) {
- transformations.add(new SkewJoinOptimizer());
+ if (!isTezExecEngine) {
+ transformations.add(new SkewJoinOptimizer());
+ } else {
+ LOG.warn("Skew join is currently not supported in tez! Disabling the skew join optimization.");
+ }
}
if (HiveConf.getBoolVar(hiveConf, HiveConf.ConfVars.HIVEOPTGBYUSINGINDEX)) {
transformations.add(new RewriteGBUsingIndex());
Modified: hive/trunk/ql/src/java/org/apache/hadoop/hive/ql/parse/SemanticAnalyzer.java
URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/java/org/apache/hadoop/hive/ql/parse/SemanticAnalyzer.java?rev=1635338&r1=1635337&r2=1635338&view=diff
==============================================================================
--- hive/trunk/ql/src/java/org/apache/hadoop/hive/ql/parse/SemanticAnalyzer.java (original)
+++ hive/trunk/ql/src/java/org/apache/hadoop/hive/ql/parse/SemanticAnalyzer.java Wed Oct 29 23:28:30 2014
@@ -383,7 +383,7 @@ public class SemanticAnalyzer extends Ba
private ArrayList<String> ctesExpanded;
/** Not thread-safe. */
- private ASTSearcher astSearcher = new ASTSearcher();
+ private final ASTSearcher astSearcher = new ASTSearcher();
private static class Phase1Ctx {
String dest;
@@ -7760,7 +7760,9 @@ public class SemanticAnalyzer extends Ba
}
joinTree.setJoinCond(condn);
- if (qb.getParseInfo().getHints() != null) {
+ if ((qb.getParseInfo().getHints() != null)
+ && !(conf.getVar(HiveConf.ConfVars.HIVE_EXECUTION_ENGINE).equals("tez"))) {
+ LOG.info("STREAMTABLE hint honored.");
parseStreamTables(joinTree, qb);
}
@@ -8043,7 +8045,9 @@ public class SemanticAnalyzer extends Ba
joinTree.setMapAliases(mapAliases);
- parseStreamTables(joinTree, qb);
+ if ((conf.getVar(HiveConf.ConfVars.HIVE_EXECUTION_ENGINE).equals("tez")) == false) {
+ parseStreamTables(joinTree, qb);
+ }
}
return joinTree;
Added: hive/trunk/ql/src/test/results/clientpositive/tez/skewjoin.q.out
URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/test/results/clientpositive/tez/skewjoin.q.out?rev=1635338&view=auto
==============================================================================
--- hive/trunk/ql/src/test/results/clientpositive/tez/skewjoin.q.out (added)
+++ hive/trunk/ql/src/test/results/clientpositive/tez/skewjoin.q.out Wed Oct 29 23:28:30 2014
@@ -0,0 +1,1161 @@
+PREHOOK: query: CREATE TABLE T1(key STRING, val STRING) STORED AS TEXTFILE
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@T1
+POSTHOOK: query: CREATE TABLE T1(key STRING, val STRING) STORED AS TEXTFILE
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@T1
+PREHOOK: query: CREATE TABLE T2(key STRING, val STRING) STORED AS TEXTFILE
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@T2
+POSTHOOK: query: CREATE TABLE T2(key STRING, val STRING) STORED AS TEXTFILE
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@T2
+PREHOOK: query: CREATE TABLE T3(key STRING, val STRING) STORED AS TEXTFILE
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@T3
+POSTHOOK: query: CREATE TABLE T3(key STRING, val STRING) STORED AS TEXTFILE
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@T3
+PREHOOK: query: CREATE TABLE T4(key STRING, val STRING) STORED AS TEXTFILE
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@T4
+POSTHOOK: query: CREATE TABLE T4(key STRING, val STRING) STORED AS TEXTFILE
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@T4
+PREHOOK: query: CREATE TABLE dest_j1(key INT, value STRING) STORED AS TEXTFILE
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@dest_j1
+POSTHOOK: query: CREATE TABLE dest_j1(key INT, value STRING) STORED AS TEXTFILE
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@dest_j1
+PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T1.txt' INTO TABLE T1
+PREHOOK: type: LOAD
+#### A masked pattern was here ####
+PREHOOK: Output: default@t1
+POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T1.txt' INTO TABLE T1
+POSTHOOK: type: LOAD
+#### A masked pattern was here ####
+POSTHOOK: Output: default@t1
+PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T2.txt' INTO TABLE T2
+PREHOOK: type: LOAD
+#### A masked pattern was here ####
+PREHOOK: Output: default@t2
+POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T2.txt' INTO TABLE T2
+POSTHOOK: type: LOAD
+#### A masked pattern was here ####
+POSTHOOK: Output: default@t2
+PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T3.txt' INTO TABLE T3
+PREHOOK: type: LOAD
+#### A masked pattern was here ####
+PREHOOK: Output: default@t3
+POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T3.txt' INTO TABLE T3
+POSTHOOK: type: LOAD
+#### A masked pattern was here ####
+POSTHOOK: Output: default@t3
+PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T1.txt' INTO TABLE T4
+PREHOOK: type: LOAD
+#### A masked pattern was here ####
+PREHOOK: Output: default@t4
+POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T1.txt' INTO TABLE T4
+POSTHOOK: type: LOAD
+#### A masked pattern was here ####
+POSTHOOK: Output: default@t4
+PREHOOK: query: EXPLAIN
+FROM src src1 JOIN src src2 ON (src1.key = src2.key)
+INSERT OVERWRITE TABLE dest_j1 SELECT src1.key, src2.value
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN
+FROM src src1 JOIN src src2 ON (src1.key = src2.key)
+INSERT OVERWRITE TABLE dest_j1 SELECT src1.key, src2.value
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1
+ Stage-0 depends on stages: Stage-2
+ Stage-3 depends on stages: Stage-0
+
+STAGE PLANS:
+ Stage: Stage-1
+ Tez
+ Edges:
+ Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: src2
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: string)
+ sort order: +
+ Map-reduce partition columns: key (type: string)
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ value expressions: value (type: string)
+ Map 3
+ Map Operator Tree:
+ TableScan
+ alias: src1
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: string)
+ sort order: +
+ Map-reduce partition columns: key (type: string)
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Reducer 2
+ Reduce Operator Tree:
+ Merge Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {KEY.reducesinkkey0}
+ 1 {VALUE._col0}
+ outputColumnNames: _col0, _col6
+ Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: UDFToInteger(_col0) (type: int), _col6 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 275 Data size: 2921 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
+ name: default.dest_j1
+
+ Stage: Stage-2
+ Dependency Collection
+
+ Stage: Stage-0
+ Move Operator
+ tables:
+ replace: true
+ 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
+ name: default.dest_j1
+
+ Stage: Stage-3
+ Stats-Aggr Operator
+
+PREHOOK: query: FROM src src1 JOIN src src2 ON (src1.key = src2.key)
+INSERT OVERWRITE TABLE dest_j1 SELECT src1.key, src2.value
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Output: default@dest_j1
+POSTHOOK: query: FROM src src1 JOIN src src2 ON (src1.key = src2.key)
+INSERT OVERWRITE TABLE dest_j1 SELECT src1.key, src2.value
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Output: default@dest_j1
+POSTHOOK: Lineage: dest_j1.key EXPRESSION [(src)src1.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: dest_j1.value SIMPLE [(src)src2.FieldSchema(name:value, type:string, comment:default), ]
+PREHOOK: query: SELECT sum(hash(key)), sum(hash(value)) FROM dest_j1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@dest_j1
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT sum(hash(key)), sum(hash(value)) FROM dest_j1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@dest_j1
+#### A masked pattern was here ####
+278697 101852390308
+PREHOOK: query: EXPLAIN
+SELECT /*+ STREAMTABLE(a) */ *
+FROM T1 a JOIN T2 b ON a.key = b.key
+ JOIN T3 c ON b.key = c.key
+ JOIN T4 d ON c.key = d.key
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN
+SELECT /*+ STREAMTABLE(a) */ *
+FROM T1 a JOIN T2 b ON a.key = b.key
+ JOIN T3 c ON b.key = c.key
+ JOIN T4 d ON c.key = d.key
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Tez
+ Edges:
+ Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: d
+ Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: string)
+ sort order: +
+ Map-reduce partition columns: key (type: string)
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ value expressions: val (type: string)
+ Map 3
+ Map Operator Tree:
+ TableScan
+ alias: b
+ Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: string)
+ sort order: +
+ Map-reduce partition columns: key (type: string)
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ value expressions: val (type: string)
+ Map 4
+ Map Operator Tree:
+ TableScan
+ alias: c
+ Statistics: Num rows: 0 Data size: 20 Basic stats: PARTIAL Column stats: NONE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: string)
+ sort order: +
+ Map-reduce partition columns: key (type: string)
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ value expressions: val (type: string)
+ Map 5
+ Map Operator Tree:
+ TableScan
+ alias: a
+ Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: string)
+ sort order: +
+ Map-reduce partition columns: key (type: string)
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ value expressions: val (type: string)
+ Reducer 2
+ Reduce Operator Tree:
+ Merge Join Operator
+ condition map:
+ Inner Join 0 to 1
+ Inner Join 1 to 2
+ Inner Join 2 to 3
+ condition expressions:
+ 0 {KEY.reducesinkkey0} {VALUE._col0}
+ 1 {KEY.reducesinkkey0} {VALUE._col0}
+ 2 {KEY.reducesinkkey0} {VALUE._col0}
+ 3 {KEY.reducesinkkey0} {VALUE._col0}
+ outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11, _col15, _col16
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string), _col15 (type: string), _col16 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE 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: SELECT /*+ STREAMTABLE(a) */ *
+FROM T1 a JOIN T2 b ON a.key = b.key
+ JOIN T3 c ON b.key = c.key
+ JOIN T4 d ON c.key = d.key
+PREHOOK: type: QUERY
+PREHOOK: Input: default@t1
+PREHOOK: Input: default@t2
+PREHOOK: Input: default@t3
+PREHOOK: Input: default@t4
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT /*+ STREAMTABLE(a) */ *
+FROM T1 a JOIN T2 b ON a.key = b.key
+ JOIN T3 c ON b.key = c.key
+ JOIN T4 d ON c.key = d.key
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@t1
+POSTHOOK: Input: default@t2
+POSTHOOK: Input: default@t3
+POSTHOOK: Input: default@t4
+#### A masked pattern was here ####
+2 12 2 22 2 12 2 12
+PREHOOK: query: EXPLAIN
+SELECT /*+ STREAMTABLE(a,c) */ *
+FROM T1 a JOIN T2 b ON a.key = b.key
+ JOIN T3 c ON b.key = c.key
+ JOIN T4 d ON c.key = d.key
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN
+SELECT /*+ STREAMTABLE(a,c) */ *
+FROM T1 a JOIN T2 b ON a.key = b.key
+ JOIN T3 c ON b.key = c.key
+ JOIN T4 d ON c.key = d.key
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Tez
+ Edges:
+ Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: d
+ Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: string)
+ sort order: +
+ Map-reduce partition columns: key (type: string)
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ value expressions: val (type: string)
+ Map 3
+ Map Operator Tree:
+ TableScan
+ alias: b
+ Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: string)
+ sort order: +
+ Map-reduce partition columns: key (type: string)
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ value expressions: val (type: string)
+ Map 4
+ Map Operator Tree:
+ TableScan
+ alias: c
+ Statistics: Num rows: 0 Data size: 20 Basic stats: PARTIAL Column stats: NONE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: string)
+ sort order: +
+ Map-reduce partition columns: key (type: string)
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ value expressions: val (type: string)
+ Map 5
+ Map Operator Tree:
+ TableScan
+ alias: a
+ Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: string)
+ sort order: +
+ Map-reduce partition columns: key (type: string)
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ value expressions: val (type: string)
+ Reducer 2
+ Reduce Operator Tree:
+ Merge Join Operator
+ condition map:
+ Inner Join 0 to 1
+ Inner Join 1 to 2
+ Inner Join 2 to 3
+ condition expressions:
+ 0 {KEY.reducesinkkey0} {VALUE._col0}
+ 1 {KEY.reducesinkkey0} {VALUE._col0}
+ 2 {KEY.reducesinkkey0} {VALUE._col0}
+ 3 {KEY.reducesinkkey0} {VALUE._col0}
+ outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11, _col15, _col16
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string), _col15 (type: string), _col16 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE 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: SELECT /*+ STREAMTABLE(a,c) */ *
+FROM T1 a JOIN T2 b ON a.key = b.key
+ JOIN T3 c ON b.key = c.key
+ JOIN T4 d ON c.key = d.key
+PREHOOK: type: QUERY
+PREHOOK: Input: default@t1
+PREHOOK: Input: default@t2
+PREHOOK: Input: default@t3
+PREHOOK: Input: default@t4
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT /*+ STREAMTABLE(a,c) */ *
+FROM T1 a JOIN T2 b ON a.key = b.key
+ JOIN T3 c ON b.key = c.key
+ JOIN T4 d ON c.key = d.key
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@t1
+POSTHOOK: Input: default@t2
+POSTHOOK: Input: default@t3
+POSTHOOK: Input: default@t4
+#### A masked pattern was here ####
+2 12 2 22 2 12 2 12
+PREHOOK: query: EXPLAIN FROM T1 a JOIN src c ON c.key+1=a.key SELECT /*+ STREAMTABLE(a) */ sum(hash(a.key)), sum(hash(a.val)), sum(hash(c.key))
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN FROM T1 a JOIN src c ON c.key+1=a.key SELECT /*+ STREAMTABLE(a) */ sum(hash(a.key)), sum(hash(a.val)), sum(hash(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
+ Tez
+ Edges:
+ Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE)
+ Reducer 3 <- Reducer 2 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: c
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (key + 1) is not null (type: boolean)
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: (key + 1) (type: double)
+ sort order: +
+ Map-reduce partition columns: (key + 1) (type: double)
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ value expressions: key (type: string)
+ Map 4
+ Map Operator Tree:
+ TableScan
+ alias: a
+ Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
+ Filter Operator
+ predicate: UDFToDouble(key) is not null (type: boolean)
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ Reduce Output Operator
+ key expressions: UDFToDouble(key) (type: double)
+ sort order: +
+ Map-reduce partition columns: UDFToDouble(key) (type: double)
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ value expressions: key (type: string), val (type: string)
+ Reducer 2
+ Reduce Operator Tree:
+ Merge Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {VALUE._col0} {VALUE._col1}
+ 1 {VALUE._col0}
+ outputColumnNames: _col0, _col1, _col5
+ Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string)
+ outputColumnNames: _col0, _col1, _col5
+ Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: sum(hash(_col0)), sum(hash(_col1)), sum(hash(_col5))
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: bigint)
+ Reducer 3
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: sum(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: bigint)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 24 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: FROM T1 a JOIN src c ON c.key+1=a.key SELECT /*+ STREAMTABLE(a) */ sum(hash(a.key)), sum(hash(a.val)), sum(hash(c.key))
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Input: default@t1
+#### A masked pattern was here ####
+POSTHOOK: query: FROM T1 a JOIN src c ON c.key+1=a.key SELECT /*+ STREAMTABLE(a) */ sum(hash(a.key)), sum(hash(a.val)), sum(hash(c.key))
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Input: default@t1
+#### A masked pattern was here ####
+198 6274 194
+PREHOOK: query: EXPLAIN FROM
+(SELECT src.* FROM src) x
+JOIN
+(SELECT src.* FROM src) Y
+ON (x.key = Y.key)
+SELECT sum(hash(Y.key)), sum(hash(Y.value))
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN FROM
+(SELECT src.* FROM src) x
+JOIN
+(SELECT src.* FROM src) Y
+ON (x.key = Y.key)
+SELECT sum(hash(Y.key)), sum(hash(Y.value))
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Tez
+ Edges:
+ Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE)
+ Reducer 3 <- Reducer 2 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Map 4
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: string)
+ Reducer 2
+ Reduce Operator Tree:
+ Merge Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0
+ 1 {KEY.reducesinkkey0} {VALUE._col0}
+ outputColumnNames: _col2, _col3
+ Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col2 (type: string), _col3 (type: string)
+ outputColumnNames: _col2, _col3
+ Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: sum(hash(_col2)), sum(hash(_col3))
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: bigint), _col1 (type: bigint)
+ Reducer 3
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: sum(VALUE._col0), sum(VALUE._col1)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: bigint), _col1 (type: bigint)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 16 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: FROM
+(SELECT src.* FROM src) x
+JOIN
+(SELECT src.* FROM src) Y
+ON (x.key = Y.key)
+SELECT sum(hash(Y.key)), sum(hash(Y.value))
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+#### A masked pattern was here ####
+POSTHOOK: query: FROM
+(SELECT src.* FROM src) x
+JOIN
+(SELECT src.* FROM src) Y
+ON (x.key = Y.key)
+SELECT sum(hash(Y.key)), sum(hash(Y.value))
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+#### A masked pattern was here ####
+44481300 101852390308
+PREHOOK: query: EXPLAIN FROM
+(SELECT src.* FROM src) x
+JOIN
+(SELECT src.* FROM src) Y
+ON (x.key = Y.key and substring(x.value, 5)=substring(y.value, 5)+1)
+SELECT sum(hash(Y.key)), sum(hash(Y.value))
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN FROM
+(SELECT src.* FROM src) x
+JOIN
+(SELECT src.* FROM src) Y
+ON (x.key = Y.key and substring(x.value, 5)=substring(y.value, 5)+1)
+SELECT sum(hash(Y.key)), sum(hash(Y.value))
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Tez
+ Edges:
+ Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE)
+ Reducer 3 <- Reducer 2 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (key is not null and UDFToDouble(substring(value, 5)) is not null) (type: boolean)
+ Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string), UDFToDouble(substring(_col1, 5)) (type: double)
+ sort order: ++
+ Map-reduce partition columns: _col0 (type: string), UDFToDouble(substring(_col1, 5)) (type: double)
+ Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE
+ Map 4
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (key is not null and (substring(value, 5) + 1) is not null) (type: boolean)
+ Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string), (substring(_col1, 5) + 1) (type: double)
+ sort order: ++
+ Map-reduce partition columns: _col0 (type: string), (substring(_col1, 5) + 1) (type: double)
+ Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: string)
+ Reducer 2
+ Reduce Operator Tree:
+ Merge Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0
+ 1 {KEY.reducesinkkey0} {VALUE._col0}
+ outputColumnNames: _col2, _col3
+ Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col2 (type: string), _col3 (type: string)
+ outputColumnNames: _col2, _col3
+ Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: sum(hash(_col2)), sum(hash(_col3))
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: bigint), _col1 (type: bigint)
+ Reducer 3
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: sum(VALUE._col0), sum(VALUE._col1)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: bigint), _col1 (type: bigint)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 16 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: FROM
+(SELECT src.* FROM src) x
+JOIN
+(SELECT src.* FROM src) Y
+ON (x.key = Y.key and substring(x.value, 5)=substring(y.value, 5)+1)
+SELECT sum(hash(Y.key)), sum(hash(Y.value))
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+#### A masked pattern was here ####
+POSTHOOK: query: FROM
+(SELECT src.* FROM src) x
+JOIN
+(SELECT src.* FROM src) Y
+ON (x.key = Y.key and substring(x.value, 5)=substring(y.value, 5)+1)
+SELECT sum(hash(Y.key)), sum(hash(Y.value))
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+#### A masked pattern was here ####
+NULL NULL
+PREHOOK: query: EXPLAIN
+SELECT sum(hash(src1.c1)), sum(hash(src2.c4))
+FROM
+(SELECT src.key as c1, src.value as c2 from src) src1
+JOIN
+(SELECT src.key as c3, src.value as c4 from src) src2
+ON src1.c1 = src2.c3 AND src1.c1 < 100
+JOIN
+(SELECT src.key as c5, src.value as c6 from src) src3
+ON src1.c1 = src3.c5 AND src3.c5 < 80
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN
+SELECT sum(hash(src1.c1)), sum(hash(src2.c4))
+FROM
+(SELECT src.key as c1, src.value as c2 from src) src1
+JOIN
+(SELECT src.key as c3, src.value as c4 from src) src2
+ON src1.c1 = src2.c3 AND src1.c1 < 100
+JOIN
+(SELECT src.key as c5, src.value as c6 from src) src3
+ON src1.c1 = src3.c5 AND src3.c5 < 80
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Tez
+ Edges:
+ Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE)
+ Reducer 3 <- Reducer 2 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (((key < 100) and (key < 80)) and key is not null) (type: boolean)
+ Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: string)
+ Map 4
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: ((key < 80) and (key < 100)) (type: boolean)
+ Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+ Map 5
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: ((key < 100) and (key < 80)) (type: boolean)
+ Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+ Reducer 2
+ Reduce Operator Tree:
+ Merge Join Operator
+ condition map:
+ Inner Join 0 to 1
+ Inner Join 0 to 2
+ condition expressions:
+ 0 {KEY.reducesinkkey0}
+ 1 {VALUE._col0}
+ 2
+ outputColumnNames: _col0, _col3
+ Statistics: Num rows: 121 Data size: 1284 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col3 (type: string)
+ outputColumnNames: _col0, _col3
+ Statistics: Num rows: 121 Data size: 1284 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: sum(hash(_col0)), sum(hash(_col3))
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: bigint), _col1 (type: bigint)
+ Reducer 3
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: sum(VALUE._col0), sum(VALUE._col1)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: bigint), _col1 (type: bigint)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 16 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: SELECT sum(hash(src1.c1)), sum(hash(src2.c4))
+FROM
+(SELECT src.key as c1, src.value as c2 from src) src1
+JOIN
+(SELECT src.key as c3, src.value as c4 from src) src2
+ON src1.c1 = src2.c3 AND src1.c1 < 100
+JOIN
+(SELECT src.key as c5, src.value as c6 from src) src3
+ON src1.c1 = src3.c5 AND src3.c5 < 80
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT sum(hash(src1.c1)), sum(hash(src2.c4))
+FROM
+(SELECT src.key as c1, src.value as c2 from src) src1
+JOIN
+(SELECT src.key as c3, src.value as c4 from src) src2
+ON src1.c1 = src2.c3 AND src1.c1 < 100
+JOIN
+(SELECT src.key as c5, src.value as c6 from src) src3
+ON src1.c1 = src3.c5 AND src3.c5 < 80
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+#### A masked pattern was here ####
+293143 -136853010385
+PREHOOK: query: EXPLAIN
+SELECT /*+ mapjoin(v)*/ sum(hash(k.key)), sum(hash(v.val)) FROM T1 k LEFT OUTER JOIN T1 v ON k.key+1=v.key
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN
+SELECT /*+ mapjoin(v)*/ sum(hash(k.key)), sum(hash(v.val)) FROM T1 k LEFT OUTER JOIN T1 v ON k.key+1=v.key
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Tez
+ Edges:
+ Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE)
+ Reducer 3 <- Reducer 2 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: v
+ Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
+ Reduce Output Operator
+ key expressions: UDFToDouble(key) (type: double)
+ sort order: +
+ Map-reduce partition columns: UDFToDouble(key) (type: double)
+ Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
+ value expressions: val (type: string)
+ Map 4
+ Map Operator Tree:
+ TableScan
+ alias: k
+ Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
+ Reduce Output Operator
+ key expressions: (key + 1) (type: double)
+ sort order: +
+ Map-reduce partition columns: (key + 1) (type: double)
+ Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
+ value expressions: key (type: string)
+ Reducer 2
+ Reduce Operator Tree:
+ Merge Join Operator
+ condition map:
+ Left Outer Join0 to 1
+ condition expressions:
+ 0 {VALUE._col0}
+ 1 {VALUE._col1}
+ outputColumnNames: _col0, _col6
+ Statistics: Num rows: 0 Data size: 33 Basic stats: PARTIAL Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col6 (type: string)
+ outputColumnNames: _col0, _col6
+ Statistics: Num rows: 0 Data size: 33 Basic stats: PARTIAL Column stats: NONE
+ Group By Operator
+ aggregations: sum(hash(_col0)), sum(hash(_col6))
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: bigint), _col1 (type: bigint)
+ Reducer 3
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: sum(VALUE._col0), sum(VALUE._col1)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: bigint), _col1 (type: bigint)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 16 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: SELECT /*+ mapjoin(v)*/ sum(hash(k.key)), sum(hash(v.val)) FROM T1 k LEFT OUTER JOIN T1 v ON k.key+1=v.key
+PREHOOK: type: QUERY
+PREHOOK: Input: default@t1
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT /*+ mapjoin(v)*/ sum(hash(k.key)), sum(hash(v.val)) FROM T1 k LEFT OUTER JOIN T1 v ON k.key+1=v.key
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@t1
+#### A masked pattern was here ####
+372 6320
+PREHOOK: query: select /*+ mapjoin(k)*/ sum(hash(k.key)), sum(hash(v.val)) from T1 k join T1 v on k.key=v.val
+PREHOOK: type: QUERY
+PREHOOK: Input: default@t1
+#### A masked pattern was here ####
+POSTHOOK: query: select /*+ mapjoin(k)*/ sum(hash(k.key)), sum(hash(v.val)) from T1 k join T1 v on k.key=v.val
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@t1
+#### A masked pattern was here ####
+NULL NULL
+PREHOOK: query: select /*+ mapjoin(k)*/ sum(hash(k.key)), sum(hash(v.val)) from T1 k join T1 v on k.key=v.key
+PREHOOK: type: QUERY
+PREHOOK: Input: default@t1
+#### A masked pattern was here ####
+POSTHOOK: query: select /*+ mapjoin(k)*/ sum(hash(k.key)), sum(hash(v.val)) from T1 k join T1 v on k.key=v.key
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@t1
+#### A masked pattern was here ####
+429 12643
+PREHOOK: query: select sum(hash(k.key)), sum(hash(v.val)) from T1 k join T1 v on k.key=v.key
+PREHOOK: type: QUERY
+PREHOOK: Input: default@t1
+#### A masked pattern was here ####
+POSTHOOK: query: select sum(hash(k.key)), sum(hash(v.val)) from T1 k join T1 v on k.key=v.key
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@t1
+#### A masked pattern was here ####
+429 12643
+PREHOOK: query: select count(1) from T1 a join T1 b on a.key = b.key
+PREHOOK: type: QUERY
+PREHOOK: Input: default@t1
+#### A masked pattern was here ####
+POSTHOOK: query: select count(1) from T1 a join T1 b on a.key = b.key
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@t1
+#### A masked pattern was here ####
+8
+PREHOOK: query: FROM T1 a LEFT OUTER JOIN T2 c ON c.key+1=a.key SELECT sum(hash(a.key)), sum(hash(a.val)), sum(hash(c.key))
+PREHOOK: type: QUERY
+PREHOOK: Input: default@t1
+PREHOOK: Input: default@t2
+#### A masked pattern was here ####
+POSTHOOK: query: FROM T1 a LEFT OUTER JOIN T2 c ON c.key+1=a.key SELECT sum(hash(a.key)), sum(hash(a.val)), sum(hash(c.key))
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@t1
+POSTHOOK: Input: default@t2
+#### A masked pattern was here ####
+317 9462 50
+PREHOOK: query: FROM T1 a RIGHT OUTER JOIN T2 c ON c.key+1=a.key SELECT /*+ STREAMTABLE(a) */ sum(hash(a.key)), sum(hash(a.val)), sum(hash(c.key))
+PREHOOK: type: QUERY
+PREHOOK: Input: default@t1
+PREHOOK: Input: default@t2
+#### A masked pattern was here ####
+POSTHOOK: query: FROM T1 a RIGHT OUTER JOIN T2 c ON c.key+1=a.key SELECT /*+ STREAMTABLE(a) */ sum(hash(a.key)), sum(hash(a.val)), sum(hash(c.key))
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@t1
+POSTHOOK: Input: default@t2
+#### A masked pattern was here ####
+51 1570 318
+PREHOOK: query: FROM T1 a FULL OUTER JOIN T2 c ON c.key+1=a.key SELECT /*+ STREAMTABLE(a) */ sum(hash(a.key)), sum(hash(a.val)), sum(hash(c.key))
+PREHOOK: type: QUERY
+PREHOOK: Input: default@t1
+PREHOOK: Input: default@t2
+#### A masked pattern was here ####
+POSTHOOK: query: FROM T1 a FULL OUTER JOIN T2 c ON c.key+1=a.key SELECT /*+ STREAMTABLE(a) */ sum(hash(a.key)), sum(hash(a.val)), sum(hash(c.key))
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@t1
+POSTHOOK: Input: default@t2
+#### A masked pattern was here ####
+317 9462 318
+PREHOOK: query: SELECT sum(hash(src1.key)), sum(hash(src1.val)), sum(hash(src2.key)) FROM T1 src1 LEFT OUTER JOIN T2 src2 ON src1.key+1 = src2.key RIGHT OUTER JOIN T2 src3 ON src2.key = src3.key
+PREHOOK: type: QUERY
+PREHOOK: Input: default@t1
+PREHOOK: Input: default@t2
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT sum(hash(src1.key)), sum(hash(src1.val)), sum(hash(src2.key)) FROM T1 src1 LEFT OUTER JOIN T2 src2 ON src1.key+1 = src2.key RIGHT OUTER JOIN T2 src3 ON src2.key = src3.key
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@t1
+POSTHOOK: Input: default@t2
+#### A masked pattern was here ####
+370 11003 377
+PREHOOK: query: SELECT sum(hash(src1.key)), sum(hash(src1.val)), sum(hash(src2.key)) FROM T1 src1 JOIN T2 src2 ON src1.key+1 = src2.key JOIN T2 src3 ON src2.key = src3.key
+PREHOOK: type: QUERY
+PREHOOK: Input: default@t1
+PREHOOK: Input: default@t2
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT sum(hash(src1.key)), sum(hash(src1.val)), sum(hash(src2.key)) FROM T1 src1 JOIN T2 src2 ON src1.key+1 = src2.key JOIN T2 src3 ON src2.key = src3.key
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@t1
+POSTHOOK: Input: default@t2
+#### A masked pattern was here ####
+370 11003 377
+PREHOOK: query: select /*+ mapjoin(v)*/ sum(hash(k.key)), sum(hash(v.val)) from T1 k left outer join T1 v on k.key+1=v.key
+PREHOOK: type: QUERY
+PREHOOK: Input: default@t1
+#### A masked pattern was here ####
+POSTHOOK: query: select /*+ mapjoin(v)*/ sum(hash(k.key)), sum(hash(v.val)) from T1 k left outer join T1 v on k.key+1=v.key
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@t1
+#### A masked pattern was here ####
+372 6320