hive-commits mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From mmccl...@apache.org
Subject hive git commit: HIVE-13818: Fast Vector MapJoin Long hashtable has to handle all integral types (Gopal Vijayaraghavan, reviewed by Matt McCline)
Date Mon, 30 May 2016 23:52:30 GMT
Repository: hive
Updated Branches:
  refs/heads/branch-2.1 dc455d76a -> 8e664dca0


HIVE-13818: Fast Vector MapJoin Long hashtable has to handle all integral types (Gopal Vijayaraghavan,
reviewed by Matt McCline)


Project: http://git-wip-us.apache.org/repos/asf/hive/repo
Commit: http://git-wip-us.apache.org/repos/asf/hive/commit/8e664dca
Tree: http://git-wip-us.apache.org/repos/asf/hive/tree/8e664dca
Diff: http://git-wip-us.apache.org/repos/asf/hive/diff/8e664dca

Branch: refs/heads/branch-2.1
Commit: 8e664dca0957a9f5ab08645cb1fdad62a93cf178
Parents: dc455d7
Author: Matt McCline <mmccline@hortonworks.com>
Authored: Mon May 30 16:46:28 2016 -0700
Committer: Matt McCline <mmccline@hortonworks.com>
Committed: Mon May 30 16:51:41 2016 -0700

----------------------------------------------------------------------
 .../fast/VectorMapJoinFastLongHashTable.java    |   2 +-
 .../VectorMapJoinOptimizedLongCommon.java       |   2 +-
 .../hadoop/hive/ql/plan/VectorMapJoinDesc.java  |  27 +++-
 .../clientpositive/vectorized_mapjoin2.q        |  21 +++
 .../tez/vectorized_mapjoin2.q.out               | 135 +++++++++++++++++++
 .../clientpositive/vectorized_mapjoin2.q.out    | 132 ++++++++++++++++++
 6 files changed, 316 insertions(+), 3 deletions(-)
----------------------------------------------------------------------


http://git-wip-us.apache.org/repos/asf/hive/blob/8e664dca/ql/src/java/org/apache/hadoop/hive/ql/exec/vector/mapjoin/fast/VectorMapJoinFastLongHashTable.java
----------------------------------------------------------------------
diff --git a/ql/src/java/org/apache/hadoop/hive/ql/exec/vector/mapjoin/fast/VectorMapJoinFastLongHashTable.java
b/ql/src/java/org/apache/hadoop/hive/ql/exec/vector/mapjoin/fast/VectorMapJoinFastLongHashTable.java
index 0a502e0..78b55a1 100644
--- a/ql/src/java/org/apache/hadoop/hive/ql/exec/vector/mapjoin/fast/VectorMapJoinFastLongHashTable.java
+++ b/ql/src/java/org/apache/hadoop/hive/ql/exec/vector/mapjoin/fast/VectorMapJoinFastLongHashTable.java
@@ -259,7 +259,7 @@ public abstract class VectorMapJoinFastLongHashTable
     super(initialCapacity, loadFactor, writeBuffersSize);
     this.isOuterJoin = isOuterJoin;
     this.hashTableKeyType = hashTableKeyType;
-    PrimitiveTypeInfo[] primitiveTypeInfos = { TypeInfoFactory.longTypeInfo };
+    PrimitiveTypeInfo[] primitiveTypeInfos = { hashTableKeyType.getPrimitiveTypeInfo() };
     keyBinarySortableDeserializeRead = new BinarySortableDeserializeRead(primitiveTypeInfos);
     allocateBucketArray();
     useMinMax = minMaxEnabled;

http://git-wip-us.apache.org/repos/asf/hive/blob/8e664dca/ql/src/java/org/apache/hadoop/hive/ql/exec/vector/mapjoin/optimized/VectorMapJoinOptimizedLongCommon.java
----------------------------------------------------------------------
diff --git a/ql/src/java/org/apache/hadoop/hive/ql/exec/vector/mapjoin/optimized/VectorMapJoinOptimizedLongCommon.java
b/ql/src/java/org/apache/hadoop/hive/ql/exec/vector/mapjoin/optimized/VectorMapJoinOptimizedLongCommon.java
index a84de89..0eabc44 100644
--- a/ql/src/java/org/apache/hadoop/hive/ql/exec/vector/mapjoin/optimized/VectorMapJoinOptimizedLongCommon.java
+++ b/ql/src/java/org/apache/hadoop/hive/ql/exec/vector/mapjoin/optimized/VectorMapJoinOptimizedLongCommon.java
@@ -161,7 +161,7 @@ public class VectorMapJoinOptimizedLongCommon {
     min = Long.MAX_VALUE;
     max = Long.MIN_VALUE;
     this.hashTableKeyType = hashTableKeyType;
-    // PrimitiveTypeInfo[] primitiveTypeInfos = { TypeInfoFactory.longTypeInfo };
+    // PrimitiveTypeInfo[] primitiveTypeInfos = { hashTableKeyType.getPrimitiveTypeInfo()
};
     // keyBinarySortableDeserializeRead = new BinarySortableDeserializeRead(primitiveTypeInfos);
     keyBinarySortableSerializeWrite = new BinarySortableSerializeWrite(1);
     output = new Output();

http://git-wip-us.apache.org/repos/asf/hive/blob/8e664dca/ql/src/java/org/apache/hadoop/hive/ql/plan/VectorMapJoinDesc.java
----------------------------------------------------------------------
diff --git a/ql/src/java/org/apache/hadoop/hive/ql/plan/VectorMapJoinDesc.java b/ql/src/java/org/apache/hadoop/hive/ql/plan/VectorMapJoinDesc.java
index e1bf1f4..8ea230f 100644
--- a/ql/src/java/org/apache/hadoop/hive/ql/plan/VectorMapJoinDesc.java
+++ b/ql/src/java/org/apache/hadoop/hive/ql/plan/VectorMapJoinDesc.java
@@ -18,6 +18,9 @@
 
 package org.apache.hadoop.hive.ql.plan;
 
+import org.apache.hadoop.hive.serde2.typeinfo.PrimitiveTypeInfo;
+import org.apache.hadoop.hive.serde2.typeinfo.TypeInfoFactory;
+
 /**
  * VectorGroupByDesc.
  *
@@ -51,7 +54,29 @@ public class VectorMapJoinDesc extends AbstractVectorDesc  {
     INT,
     LONG,
     STRING,
-    MULTI_KEY
+    MULTI_KEY;
+
+    public PrimitiveTypeInfo getPrimitiveTypeInfo() {
+      switch (this) {
+      case BOOLEAN:
+        return TypeInfoFactory.booleanTypeInfo;
+      case BYTE:
+        return TypeInfoFactory.byteTypeInfo;
+      case INT:
+        return TypeInfoFactory.intTypeInfo;
+      case LONG:
+        return TypeInfoFactory.longTypeInfo;
+      case NONE:
+        return TypeInfoFactory.voidTypeInfo;
+      case SHORT:
+        return TypeInfoFactory.shortTypeInfo;
+      case STRING:
+        return TypeInfoFactory.stringTypeInfo;
+      case MULTI_KEY:
+      default:
+        return null;
+      }
+    }
   }
 
   private HashTableImplementationType hashTableImplementationType;

http://git-wip-us.apache.org/repos/asf/hive/blob/8e664dca/ql/src/test/queries/clientpositive/vectorized_mapjoin2.q
----------------------------------------------------------------------
diff --git a/ql/src/test/queries/clientpositive/vectorized_mapjoin2.q b/ql/src/test/queries/clientpositive/vectorized_mapjoin2.q
new file mode 100644
index 0000000..137acbc
--- /dev/null
+++ b/ql/src/test/queries/clientpositive/vectorized_mapjoin2.q
@@ -0,0 +1,21 @@
+set hive.explain.user=false;
+SET hive.vectorized.execution.enabled=true;
+SET hive.vectorized.execution.mapjoin.native.enabled=true;
+set hive.cbo.enable=true;
+set hive.fetch.task.conversion=none;
+SET hive.auto.convert.join=true;
+SET hive.auto.convert.join.noconditionaltask=true;
+SET hive.auto.convert.join.noconditionaltask.size=1000000000;
+set hive.exec.dynamic.partition.mode=nonstrict;
+set hive.mapjoin.hybridgrace.hashtable=false;
+set hive.vectorized.execution.mapjoin.native.fast.hashtable.enabled=true;
+
+create temporary table x (a int) stored as orc;
+create temporary table y (b int) stored as orc;
+insert into x values(1);
+insert into y values(1);
+
+explain
+select count(1) from x, y where a = b;
+
+select count(1) from x, y where a = b;

http://git-wip-us.apache.org/repos/asf/hive/blob/8e664dca/ql/src/test/results/clientpositive/tez/vectorized_mapjoin2.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/tez/vectorized_mapjoin2.q.out b/ql/src/test/results/clientpositive/tez/vectorized_mapjoin2.q.out
new file mode 100644
index 0000000..a3c0b31
--- /dev/null
+++ b/ql/src/test/results/clientpositive/tez/vectorized_mapjoin2.q.out
@@ -0,0 +1,135 @@
+PREHOOK: query: create temporary table x (a int) stored as orc
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@x
+POSTHOOK: query: create temporary table x (a int) stored as orc
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@x
+PREHOOK: query: create temporary table y (b int) stored as orc
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@y
+POSTHOOK: query: create temporary table y (b int) stored as orc
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@y
+PREHOOK: query: insert into x values(1)
+PREHOOK: type: QUERY
+PREHOOK: Input: default@values__tmp__table__1
+PREHOOK: Output: default@x
+POSTHOOK: query: insert into x values(1)
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@values__tmp__table__1
+POSTHOOK: Output: default@x
+POSTHOOK: Lineage: x.a EXPRESSION [(values__tmp__table__1)values__tmp__table__1.FieldSchema(name:tmp_values_col1,
type:string, comment:), ]
+PREHOOK: query: insert into y values(1)
+PREHOOK: type: QUERY
+PREHOOK: Input: default@values__tmp__table__2
+PREHOOK: Output: default@y
+POSTHOOK: query: insert into y values(1)
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@values__tmp__table__2
+POSTHOOK: Output: default@y
+POSTHOOK: Lineage: y.b EXPRESSION [(values__tmp__table__2)values__tmp__table__2.FieldSchema(name:tmp_values_col1,
type:string, comment:), ]
+PREHOOK: query: explain
+select count(1) from x, y where a = b
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+select count(1) from x, y where a = b
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+  Stage-1 is a root stage
+  Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+  Stage: Stage-1
+    Tez
+#### A masked pattern was here ####
+      Edges:
+        Map 1 <- Map 3 (BROADCAST_EDGE)
+        Reducer 2 <- Map 1 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+      Vertices:
+        Map 1 
+            Map Operator Tree:
+                TableScan
+                  alias: x
+                  Statistics: Num rows: 45 Data size: 181 Basic stats: COMPLETE Column stats:
NONE
+                  Filter Operator
+                    predicate: a is not null (type: boolean)
+                    Statistics: Num rows: 45 Data size: 181 Basic stats: COMPLETE Column
stats: NONE
+                    Select Operator
+                      expressions: a (type: int)
+                      outputColumnNames: _col0
+                      Statistics: Num rows: 45 Data size: 181 Basic stats: COMPLETE Column
stats: NONE
+                      Map Join Operator
+                        condition map:
+                             Inner Join 0 to 1
+                        keys:
+                          0 _col0 (type: int)
+                          1 _col0 (type: int)
+                        input vertices:
+                          1 Map 3
+                        Statistics: Num rows: 49 Data size: 199 Basic stats: COMPLETE Column
stats: NONE
+                        Group By Operator
+                          aggregations: count(1)
+                          mode: hash
+                          outputColumnNames: _col0
+                          Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column
stats: NONE
+                          Reduce Output Operator
+                            sort order: 
+                            Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column
stats: NONE
+                            value expressions: _col0 (type: bigint)
+            Execution mode: vectorized
+        Map 3 
+            Map Operator Tree:
+                TableScan
+                  alias: y
+                  Statistics: Num rows: 45 Data size: 181 Basic stats: COMPLETE Column stats:
NONE
+                  Filter Operator
+                    predicate: b is not null (type: boolean)
+                    Statistics: Num rows: 45 Data size: 181 Basic stats: COMPLETE Column
stats: NONE
+                    Select Operator
+                      expressions: b (type: int)
+                      outputColumnNames: _col0
+                      Statistics: Num rows: 45 Data size: 181 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: 45 Data size: 181 Basic stats: COMPLETE Column
stats: NONE
+            Execution mode: vectorized
+        Reducer 2 
+            Execution mode: vectorized
+            Reduce Operator Tree:
+              Group By Operator
+                aggregations: count(VALUE._col0)
+                mode: mergepartial
+                outputColumnNames: _col0
+                Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats:
NONE
+                File Output Operator
+                  compressed: false
+                  Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats:
NONE
+                  table:
+                      input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+                      output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+                      serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+  Stage: Stage-0
+    Fetch Operator
+      limit: -1
+      Processor Tree:
+        ListSink
+
+PREHOOK: query: select count(1) from x, y where a = b
+PREHOOK: type: QUERY
+PREHOOK: Input: default@x
+PREHOOK: Input: default@y
+#### A masked pattern was here ####
+POSTHOOK: query: select count(1) from x, y where a = b
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@x
+POSTHOOK: Input: default@y
+#### A masked pattern was here ####
+1

http://git-wip-us.apache.org/repos/asf/hive/blob/8e664dca/ql/src/test/results/clientpositive/vectorized_mapjoin2.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/vectorized_mapjoin2.q.out b/ql/src/test/results/clientpositive/vectorized_mapjoin2.q.out
new file mode 100644
index 0000000..73b61a2
--- /dev/null
+++ b/ql/src/test/results/clientpositive/vectorized_mapjoin2.q.out
@@ -0,0 +1,132 @@
+PREHOOK: query: create temporary table x (a int) stored as orc
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@x
+POSTHOOK: query: create temporary table x (a int) stored as orc
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@x
+PREHOOK: query: create temporary table y (b int) stored as orc
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@y
+POSTHOOK: query: create temporary table y (b int) stored as orc
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@y
+PREHOOK: query: insert into x values(1)
+PREHOOK: type: QUERY
+PREHOOK: Input: default@values__tmp__table__1
+PREHOOK: Output: default@x
+POSTHOOK: query: insert into x values(1)
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@values__tmp__table__1
+POSTHOOK: Output: default@x
+POSTHOOK: Lineage: x.a EXPRESSION [(values__tmp__table__1)values__tmp__table__1.FieldSchema(name:tmp_values_col1,
type:string, comment:), ]
+PREHOOK: query: insert into y values(1)
+PREHOOK: type: QUERY
+PREHOOK: Input: default@values__tmp__table__2
+PREHOOK: Output: default@y
+POSTHOOK: query: insert into y values(1)
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@values__tmp__table__2
+POSTHOOK: Output: default@y
+POSTHOOK: Lineage: y.b EXPRESSION [(values__tmp__table__2)values__tmp__table__2.FieldSchema(name:tmp_values_col1,
type:string, comment:), ]
+PREHOOK: query: explain
+select count(1) from x, y where a = b
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+select count(1) from x, y where a = b
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+  Stage-5 is a root stage
+  Stage-2 depends on stages: Stage-5
+  Stage-0 depends on stages: Stage-2
+
+STAGE PLANS:
+  Stage: Stage-5
+    Map Reduce Local Work
+      Alias -> Map Local Tables:
+        $hdt$_0:$hdt$_0:x 
+          Fetch Operator
+            limit: -1
+      Alias -> Map Local Operator Tree:
+        $hdt$_0:$hdt$_0:x 
+          TableScan
+            alias: x
+            Statistics: Num rows: 45 Data size: 181 Basic stats: COMPLETE Column stats: NONE
+            Filter Operator
+              predicate: a is not null (type: boolean)
+              Statistics: Num rows: 45 Data size: 181 Basic stats: COMPLETE Column stats:
NONE
+              Select Operator
+                expressions: a (type: int)
+                outputColumnNames: _col0
+                Statistics: Num rows: 45 Data size: 181 Basic stats: COMPLETE Column stats:
NONE
+                HashTable Sink Operator
+                  keys:
+                    0 _col0 (type: int)
+                    1 _col0 (type: int)
+
+  Stage: Stage-2
+    Map Reduce
+      Map Operator Tree:
+          TableScan
+            alias: y
+            Statistics: Num rows: 45 Data size: 181 Basic stats: COMPLETE Column stats: NONE
+            Filter Operator
+              predicate: b is not null (type: boolean)
+              Statistics: Num rows: 45 Data size: 181 Basic stats: COMPLETE Column stats:
NONE
+              Select Operator
+                expressions: b (type: int)
+                outputColumnNames: _col0
+                Statistics: Num rows: 45 Data size: 181 Basic stats: COMPLETE Column stats:
NONE
+                Map Join Operator
+                  condition map:
+                       Inner Join 0 to 1
+                  keys:
+                    0 _col0 (type: int)
+                    1 _col0 (type: int)
+                  Statistics: Num rows: 49 Data size: 199 Basic stats: COMPLETE Column stats:
NONE
+                  Group By Operator
+                    aggregations: count(1)
+                    mode: hash
+                    outputColumnNames: _col0
+                    Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats:
NONE
+                    Reduce Output Operator
+                      sort order: 
+                      Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats:
NONE
+                      value expressions: _col0 (type: bigint)
+      Execution mode: vectorized
+      Local Work:
+        Map Reduce Local Work
+      Reduce Operator Tree:
+        Group By Operator
+          aggregations: count(VALUE._col0)
+          mode: mergepartial
+          outputColumnNames: _col0
+          Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+          File Output Operator
+            compressed: false
+            Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+            table:
+                input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+                output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+                serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+  Stage: Stage-0
+    Fetch Operator
+      limit: -1
+      Processor Tree:
+        ListSink
+
+PREHOOK: query: select count(1) from x, y where a = b
+PREHOOK: type: QUERY
+PREHOOK: Input: default@x
+PREHOOK: Input: default@y
+#### A masked pattern was here ####
+POSTHOOK: query: select count(1) from x, y where a = b
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@x
+POSTHOOK: Input: default@y
+#### A masked pattern was here ####
+1


Mime
View raw message