You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by mm...@apache.org on 2017/07/20 10:16:57 UTC
[31/36] hive git commit: HIVE-16369: Vectorization: Support PTF (Part
1: No Custom Window Framing -- Default Only) (Matt McCline,
reviewed by Ashutosh Chauhan)
http://git-wip-us.apache.org/repos/asf/hive/blob/a0df0ace/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_id1.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_id1.q.out b/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_id1.q.out
index 81b921c..aabe7d6 100644
--- a/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_id1.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_id1.q.out
@@ -27,6 +27,139 @@ POSTHOOK: Output: default@T1
POSTHOOK: Lineage: t1.key SIMPLE [(t1_text)t1_text.FieldSchema(name:key, type:string, comment:null), ]
POSTHOOK: Lineage: t1.val SIMPLE [(t1_text)t1_text.FieldSchema(name:val, type:string, comment:null), ]
t1_text.key t1_text.val
+PREHOOK: query: EXPLAIN VECTORIZATION DETAIL
+SELECT key, val, GROUPING__ID from T1 group by key, val with cube
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN VECTORIZATION DETAIL
+SELECT key, val, GROUPING__ID from T1 group by key, val with cube
+POSTHOOK: type: QUERY
+Explain
+PLAN VECTORIZATION:
+ enabled: true
+ enabledConditionsMet: [hive.vectorized.execution.enabled IS true]
+
+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:
+ Reducer 2 <- Map 1 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: t1
+ Statistics: Num rows: 6 Data size: 1026 Basic stats: COMPLETE Column stats: NONE
+ TableScan Vectorization:
+ native: true
+ projectedOutputColumns: [0, 1]
+ Select Operator
+ expressions: key (type: string), val (type: string)
+ outputColumnNames: _col0, _col1
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumns: [0, 1]
+ Statistics: Num rows: 6 Data size: 1026 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ Group By Vectorization:
+ className: VectorGroupByOperator
+ groupByMode: HASH
+ vectorOutput: true
+ keyExpressions: col 0, col 1, ConstantVectorExpression(val 0) -> 2:long
+ native: false
+ vectorProcessingMode: HASH
+ projectedOutputColumns: []
+ keys: _col0 (type: string), _col1 (type: string), 0 (type: int)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 24 Data size: 4104 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: int)
+ sort order: +++
+ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: int)
+ Reduce Sink Vectorization:
+ className: VectorReduceSinkMultiKeyOperator
+ keyColumns: [0, 1, 2]
+ native: true
+ nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
+ valueColumns: []
+ Statistics: Num rows: 24 Data size: 4104 Basic stats: COMPLETE Column stats: NONE
+ Execution mode: vectorized, llap
+ LLAP IO: all inputs
+ Map Vectorization:
+ enabled: true
+ enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
+ groupByVectorOutput: true
+ inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+ allNative: false
+ usesVectorUDFAdaptor: false
+ vectorized: true
+ rowBatchContext:
+ dataColumnCount: 2
+ includeColumns: [0, 1]
+ dataColumns: key:string, val:string
+ partitionColumnCount: 0
+ scratchColumnTypeNames: bigint
+ Reducer 2
+ Execution mode: vectorized, llap
+ Reduce Vectorization:
+ enabled: true
+ enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true
+ reduceColumnNullOrder: aaa
+ reduceColumnSortOrder: +++
+ groupByVectorOutput: true
+ allNative: false
+ usesVectorUDFAdaptor: false
+ vectorized: true
+ rowBatchContext:
+ dataColumnCount: 3
+ dataColumns: KEY._col0:string, KEY._col1:string, KEY._col2:int
+ partitionColumnCount: 0
+ Reduce Operator Tree:
+ Group By Operator
+ Group By Vectorization:
+ className: VectorGroupByOperator
+ groupByMode: MERGEPARTIAL
+ vectorOutput: true
+ keyExpressions: col 0, col 1, col 2
+ native: false
+ vectorProcessingMode: MERGE_PARTIAL
+ projectedOutputColumns: []
+ keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: int)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 12 Data size: 2052 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string), _col2 (type: int)
+ outputColumnNames: _col0, _col1, _col2
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumns: [0, 1, 2]
+ Statistics: Num rows: 12 Data size: 2052 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ File Sink Vectorization:
+ className: VectorFileSinkOperator
+ native: false
+ Statistics: Num rows: 12 Data size: 2052 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 key, val, GROUPING__ID from T1 group by key, val with cube
PREHOOK: type: QUERY
PREHOOK: Input: default@t1
@@ -54,6 +187,139 @@ NULL 17 2
NULL 18 2
NULL 28 2
NULL NULL 3
+PREHOOK: query: EXPLAIN VECTORIZATION DETAIL
+SELECT key, val, GROUPING__ID from T1 group by cube(key, val)
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN VECTORIZATION DETAIL
+SELECT key, val, GROUPING__ID from T1 group by cube(key, val)
+POSTHOOK: type: QUERY
+Explain
+PLAN VECTORIZATION:
+ enabled: true
+ enabledConditionsMet: [hive.vectorized.execution.enabled IS true]
+
+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:
+ Reducer 2 <- Map 1 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: t1
+ Statistics: Num rows: 6 Data size: 1026 Basic stats: COMPLETE Column stats: NONE
+ TableScan Vectorization:
+ native: true
+ projectedOutputColumns: [0, 1]
+ Select Operator
+ expressions: key (type: string), val (type: string)
+ outputColumnNames: _col0, _col1
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumns: [0, 1]
+ Statistics: Num rows: 6 Data size: 1026 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ Group By Vectorization:
+ className: VectorGroupByOperator
+ groupByMode: HASH
+ vectorOutput: true
+ keyExpressions: col 0, col 1, ConstantVectorExpression(val 0) -> 2:long
+ native: false
+ vectorProcessingMode: HASH
+ projectedOutputColumns: []
+ keys: _col0 (type: string), _col1 (type: string), 0 (type: int)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 24 Data size: 4104 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: int)
+ sort order: +++
+ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: int)
+ Reduce Sink Vectorization:
+ className: VectorReduceSinkMultiKeyOperator
+ keyColumns: [0, 1, 2]
+ native: true
+ nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
+ valueColumns: []
+ Statistics: Num rows: 24 Data size: 4104 Basic stats: COMPLETE Column stats: NONE
+ Execution mode: vectorized, llap
+ LLAP IO: all inputs
+ Map Vectorization:
+ enabled: true
+ enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
+ groupByVectorOutput: true
+ inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+ allNative: false
+ usesVectorUDFAdaptor: false
+ vectorized: true
+ rowBatchContext:
+ dataColumnCount: 2
+ includeColumns: [0, 1]
+ dataColumns: key:string, val:string
+ partitionColumnCount: 0
+ scratchColumnTypeNames: bigint
+ Reducer 2
+ Execution mode: vectorized, llap
+ Reduce Vectorization:
+ enabled: true
+ enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true
+ reduceColumnNullOrder: aaa
+ reduceColumnSortOrder: +++
+ groupByVectorOutput: true
+ allNative: false
+ usesVectorUDFAdaptor: false
+ vectorized: true
+ rowBatchContext:
+ dataColumnCount: 3
+ dataColumns: KEY._col0:string, KEY._col1:string, KEY._col2:int
+ partitionColumnCount: 0
+ Reduce Operator Tree:
+ Group By Operator
+ Group By Vectorization:
+ className: VectorGroupByOperator
+ groupByMode: MERGEPARTIAL
+ vectorOutput: true
+ keyExpressions: col 0, col 1, col 2
+ native: false
+ vectorProcessingMode: MERGE_PARTIAL
+ projectedOutputColumns: []
+ keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: int)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 12 Data size: 2052 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string), _col2 (type: int)
+ outputColumnNames: _col0, _col1, _col2
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumns: [0, 1, 2]
+ Statistics: Num rows: 12 Data size: 2052 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ File Sink Vectorization:
+ className: VectorFileSinkOperator
+ native: false
+ Statistics: Num rows: 12 Data size: 2052 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 key, val, GROUPING__ID from T1 group by cube(key, val)
PREHOOK: type: QUERY
PREHOOK: Input: default@t1
@@ -81,6 +347,139 @@ NULL 17 2
NULL 18 2
NULL 28 2
NULL NULL 3
+PREHOOK: query: EXPLAIN VECTORIZATION DETAIL
+SELECT GROUPING__ID, key, val from T1 group by key, val with rollup
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN VECTORIZATION DETAIL
+SELECT GROUPING__ID, key, val from T1 group by key, val with rollup
+POSTHOOK: type: QUERY
+Explain
+PLAN VECTORIZATION:
+ enabled: true
+ enabledConditionsMet: [hive.vectorized.execution.enabled IS true]
+
+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:
+ Reducer 2 <- Map 1 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: t1
+ Statistics: Num rows: 6 Data size: 1026 Basic stats: COMPLETE Column stats: NONE
+ TableScan Vectorization:
+ native: true
+ projectedOutputColumns: [0, 1]
+ Select Operator
+ expressions: key (type: string), val (type: string)
+ outputColumnNames: _col0, _col1
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumns: [0, 1]
+ Statistics: Num rows: 6 Data size: 1026 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ Group By Vectorization:
+ className: VectorGroupByOperator
+ groupByMode: HASH
+ vectorOutput: true
+ keyExpressions: col 0, col 1, ConstantVectorExpression(val 0) -> 2:long
+ native: false
+ vectorProcessingMode: HASH
+ projectedOutputColumns: []
+ keys: _col0 (type: string), _col1 (type: string), 0 (type: int)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 18 Data size: 3078 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: int)
+ sort order: +++
+ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: int)
+ Reduce Sink Vectorization:
+ className: VectorReduceSinkMultiKeyOperator
+ keyColumns: [0, 1, 2]
+ native: true
+ nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
+ valueColumns: []
+ Statistics: Num rows: 18 Data size: 3078 Basic stats: COMPLETE Column stats: NONE
+ Execution mode: vectorized, llap
+ LLAP IO: all inputs
+ Map Vectorization:
+ enabled: true
+ enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
+ groupByVectorOutput: true
+ inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+ allNative: false
+ usesVectorUDFAdaptor: false
+ vectorized: true
+ rowBatchContext:
+ dataColumnCount: 2
+ includeColumns: [0, 1]
+ dataColumns: key:string, val:string
+ partitionColumnCount: 0
+ scratchColumnTypeNames: bigint
+ Reducer 2
+ Execution mode: vectorized, llap
+ Reduce Vectorization:
+ enabled: true
+ enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true
+ reduceColumnNullOrder: aaa
+ reduceColumnSortOrder: +++
+ groupByVectorOutput: true
+ allNative: false
+ usesVectorUDFAdaptor: false
+ vectorized: true
+ rowBatchContext:
+ dataColumnCount: 3
+ dataColumns: KEY._col0:string, KEY._col1:string, KEY._col2:int
+ partitionColumnCount: 0
+ Reduce Operator Tree:
+ Group By Operator
+ Group By Vectorization:
+ className: VectorGroupByOperator
+ groupByMode: MERGEPARTIAL
+ vectorOutput: true
+ keyExpressions: col 0, col 1, col 2
+ native: false
+ vectorProcessingMode: MERGE_PARTIAL
+ projectedOutputColumns: []
+ keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: int)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 9 Data size: 1539 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col2 (type: int), _col0 (type: string), _col1 (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumns: [2, 0, 1]
+ Statistics: Num rows: 9 Data size: 1539 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ File Sink Vectorization:
+ className: VectorFileSinkOperator
+ native: false
+ Statistics: Num rows: 9 Data size: 1539 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 GROUPING__ID, key, val from T1 group by key, val with rollup
PREHOOK: type: QUERY
PREHOOK: Input: default@t1
@@ -102,6 +501,139 @@ grouping__id key val
1 7 NULL
1 8 NULL
3 NULL NULL
+PREHOOK: query: EXPLAIN VECTORIZATION DETAIL
+SELECT GROUPING__ID, key, val from T1 group by rollup (key, val)
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN VECTORIZATION DETAIL
+SELECT GROUPING__ID, key, val from T1 group by rollup (key, val)
+POSTHOOK: type: QUERY
+Explain
+PLAN VECTORIZATION:
+ enabled: true
+ enabledConditionsMet: [hive.vectorized.execution.enabled IS true]
+
+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:
+ Reducer 2 <- Map 1 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: t1
+ Statistics: Num rows: 6 Data size: 1026 Basic stats: COMPLETE Column stats: NONE
+ TableScan Vectorization:
+ native: true
+ projectedOutputColumns: [0, 1]
+ Select Operator
+ expressions: key (type: string), val (type: string)
+ outputColumnNames: _col0, _col1
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumns: [0, 1]
+ Statistics: Num rows: 6 Data size: 1026 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ Group By Vectorization:
+ className: VectorGroupByOperator
+ groupByMode: HASH
+ vectorOutput: true
+ keyExpressions: col 0, col 1, ConstantVectorExpression(val 0) -> 2:long
+ native: false
+ vectorProcessingMode: HASH
+ projectedOutputColumns: []
+ keys: _col0 (type: string), _col1 (type: string), 0 (type: int)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 18 Data size: 3078 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: int)
+ sort order: +++
+ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: int)
+ Reduce Sink Vectorization:
+ className: VectorReduceSinkMultiKeyOperator
+ keyColumns: [0, 1, 2]
+ native: true
+ nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
+ valueColumns: []
+ Statistics: Num rows: 18 Data size: 3078 Basic stats: COMPLETE Column stats: NONE
+ Execution mode: vectorized, llap
+ LLAP IO: all inputs
+ Map Vectorization:
+ enabled: true
+ enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
+ groupByVectorOutput: true
+ inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+ allNative: false
+ usesVectorUDFAdaptor: false
+ vectorized: true
+ rowBatchContext:
+ dataColumnCount: 2
+ includeColumns: [0, 1]
+ dataColumns: key:string, val:string
+ partitionColumnCount: 0
+ scratchColumnTypeNames: bigint
+ Reducer 2
+ Execution mode: vectorized, llap
+ Reduce Vectorization:
+ enabled: true
+ enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true
+ reduceColumnNullOrder: aaa
+ reduceColumnSortOrder: +++
+ groupByVectorOutput: true
+ allNative: false
+ usesVectorUDFAdaptor: false
+ vectorized: true
+ rowBatchContext:
+ dataColumnCount: 3
+ dataColumns: KEY._col0:string, KEY._col1:string, KEY._col2:int
+ partitionColumnCount: 0
+ Reduce Operator Tree:
+ Group By Operator
+ Group By Vectorization:
+ className: VectorGroupByOperator
+ groupByMode: MERGEPARTIAL
+ vectorOutput: true
+ keyExpressions: col 0, col 1, col 2
+ native: false
+ vectorProcessingMode: MERGE_PARTIAL
+ projectedOutputColumns: []
+ keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: int)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 9 Data size: 1539 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col2 (type: int), _col0 (type: string), _col1 (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumns: [2, 0, 1]
+ Statistics: Num rows: 9 Data size: 1539 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ File Sink Vectorization:
+ className: VectorFileSinkOperator
+ native: false
+ Statistics: Num rows: 9 Data size: 1539 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 GROUPING__ID, key, val from T1 group by rollup (key, val)
PREHOOK: type: QUERY
PREHOOK: Input: default@t1
@@ -123,6 +655,140 @@ grouping__id key val
1 7 NULL
1 8 NULL
3 NULL NULL
+PREHOOK: query: EXPLAIN VECTORIZATION DETAIL
+SELECT key, val, GROUPING__ID, CASE WHEN GROUPING__ID == 0 THEN "0" WHEN GROUPING__ID == 1 THEN "1" WHEN GROUPING__ID == 2 THEN "2" WHEN GROUPING__ID == 3 THEN "3" ELSE "nothing" END from T1 group by key, val with cube
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN VECTORIZATION DETAIL
+SELECT key, val, GROUPING__ID, CASE WHEN GROUPING__ID == 0 THEN "0" WHEN GROUPING__ID == 1 THEN "1" WHEN GROUPING__ID == 2 THEN "2" WHEN GROUPING__ID == 3 THEN "3" ELSE "nothing" END from T1 group by key, val with cube
+POSTHOOK: type: QUERY
+Explain
+PLAN VECTORIZATION:
+ enabled: true
+ enabledConditionsMet: [hive.vectorized.execution.enabled IS true]
+
+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:
+ Reducer 2 <- Map 1 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: t1
+ Statistics: Num rows: 6 Data size: 1026 Basic stats: COMPLETE Column stats: NONE
+ TableScan Vectorization:
+ native: true
+ projectedOutputColumns: [0, 1]
+ Select Operator
+ expressions: key (type: string), val (type: string)
+ outputColumnNames: _col0, _col1
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumns: [0, 1]
+ Statistics: Num rows: 6 Data size: 1026 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ Group By Vectorization:
+ className: VectorGroupByOperator
+ groupByMode: HASH
+ vectorOutput: true
+ keyExpressions: col 0, col 1, ConstantVectorExpression(val 0) -> 2:long
+ native: false
+ vectorProcessingMode: HASH
+ projectedOutputColumns: []
+ keys: _col0 (type: string), _col1 (type: string), 0 (type: int)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 24 Data size: 4104 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: int)
+ sort order: +++
+ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: int)
+ Reduce Sink Vectorization:
+ className: VectorReduceSinkMultiKeyOperator
+ keyColumns: [0, 1, 2]
+ native: true
+ nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
+ valueColumns: []
+ Statistics: Num rows: 24 Data size: 4104 Basic stats: COMPLETE Column stats: NONE
+ Execution mode: vectorized, llap
+ LLAP IO: all inputs
+ Map Vectorization:
+ enabled: true
+ enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
+ groupByVectorOutput: true
+ inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+ allNative: false
+ usesVectorUDFAdaptor: false
+ vectorized: true
+ rowBatchContext:
+ dataColumnCount: 2
+ includeColumns: [0, 1]
+ dataColumns: key:string, val:string
+ partitionColumnCount: 0
+ scratchColumnTypeNames: bigint
+ Reducer 2
+ Execution mode: vectorized, llap
+ Reduce Vectorization:
+ enabled: true
+ enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true
+ reduceColumnNullOrder: aaa
+ reduceColumnSortOrder: +++
+ groupByVectorOutput: true
+ allNative: false
+ usesVectorUDFAdaptor: false
+ vectorized: true
+ rowBatchContext:
+ dataColumnCount: 3
+ dataColumns: KEY._col0:string, KEY._col1:string, KEY._col2:int
+ partitionColumnCount: 0
+ Reduce Operator Tree:
+ Group By Operator
+ Group By Vectorization:
+ className: VectorGroupByOperator
+ groupByMode: MERGEPARTIAL
+ vectorOutput: true
+ keyExpressions: col 0, col 1, col 2
+ native: false
+ vectorProcessingMode: MERGE_PARTIAL
+ projectedOutputColumns: []
+ keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: int)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 12 Data size: 2052 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string), _col2 (type: int), CASE WHEN ((_col2 = 0)) THEN ('0') WHEN ((_col2 = 1)) THEN ('1') WHEN ((_col2 = 2)) THEN ('2') WHEN ((_col2 = 3)) THEN ('3') ELSE ('nothing') END (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumns: [0, 1, 2, 8]
+ selectExpressions: IfExprStringScalarStringGroupColumn(col 3, val 0, col 7)(children: LongColEqualLongScalar(col 2, val 0) -> 3:long, IfExprStringScalarStringGroupColumn(col 4, val 1, col 8)(children: LongColEqualLongScalar(col 2, val 1) -> 4:long, IfExprStringScalarStringGroupColumn(col 5, val 2, col 7)(children: LongColEqualLongScalar(col 2, val 2) -> 5:long, IfExprStringScalarStringScalar(col 6, val 3, val nothing)(children: LongColEqualLongScalar(col 2, val 3) -> 6:long) -> 7:String) -> 8:String) -> 7:String) -> 8:String
+ Statistics: Num rows: 12 Data size: 2052 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ File Sink Vectorization:
+ className: VectorFileSinkOperator
+ native: false
+ Statistics: Num rows: 12 Data size: 2052 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 key, val, GROUPING__ID, CASE WHEN GROUPING__ID == 0 THEN "0" WHEN GROUPING__ID == 1 THEN "1" WHEN GROUPING__ID == 2 THEN "2" WHEN GROUPING__ID == 3 THEN "3" ELSE "nothing" END from T1 group by key, val with cube
PREHOOK: type: QUERY
PREHOOK: Input: default@t1
@@ -150,6 +816,140 @@ NULL 17 2 2
NULL 18 2 2
NULL 28 2 2
NULL NULL 3 3
+PREHOOK: query: EXPLAIN VECTORIZATION DETAIL
+SELECT key, val, GROUPING__ID, CASE WHEN GROUPING__ID == 0 THEN "0" WHEN GROUPING__ID == 1 THEN "1" WHEN GROUPING__ID == 2 THEN "2" WHEN GROUPING__ID == 3 THEN "3" ELSE "nothing" END from T1 group by cube(key, val)
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN VECTORIZATION DETAIL
+SELECT key, val, GROUPING__ID, CASE WHEN GROUPING__ID == 0 THEN "0" WHEN GROUPING__ID == 1 THEN "1" WHEN GROUPING__ID == 2 THEN "2" WHEN GROUPING__ID == 3 THEN "3" ELSE "nothing" END from T1 group by cube(key, val)
+POSTHOOK: type: QUERY
+Explain
+PLAN VECTORIZATION:
+ enabled: true
+ enabledConditionsMet: [hive.vectorized.execution.enabled IS true]
+
+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:
+ Reducer 2 <- Map 1 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: t1
+ Statistics: Num rows: 6 Data size: 1026 Basic stats: COMPLETE Column stats: NONE
+ TableScan Vectorization:
+ native: true
+ projectedOutputColumns: [0, 1]
+ Select Operator
+ expressions: key (type: string), val (type: string)
+ outputColumnNames: _col0, _col1
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumns: [0, 1]
+ Statistics: Num rows: 6 Data size: 1026 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ Group By Vectorization:
+ className: VectorGroupByOperator
+ groupByMode: HASH
+ vectorOutput: true
+ keyExpressions: col 0, col 1, ConstantVectorExpression(val 0) -> 2:long
+ native: false
+ vectorProcessingMode: HASH
+ projectedOutputColumns: []
+ keys: _col0 (type: string), _col1 (type: string), 0 (type: int)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 24 Data size: 4104 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: int)
+ sort order: +++
+ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: int)
+ Reduce Sink Vectorization:
+ className: VectorReduceSinkMultiKeyOperator
+ keyColumns: [0, 1, 2]
+ native: true
+ nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
+ valueColumns: []
+ Statistics: Num rows: 24 Data size: 4104 Basic stats: COMPLETE Column stats: NONE
+ Execution mode: vectorized, llap
+ LLAP IO: all inputs
+ Map Vectorization:
+ enabled: true
+ enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
+ groupByVectorOutput: true
+ inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+ allNative: false
+ usesVectorUDFAdaptor: false
+ vectorized: true
+ rowBatchContext:
+ dataColumnCount: 2
+ includeColumns: [0, 1]
+ dataColumns: key:string, val:string
+ partitionColumnCount: 0
+ scratchColumnTypeNames: bigint
+ Reducer 2
+ Execution mode: vectorized, llap
+ Reduce Vectorization:
+ enabled: true
+ enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true
+ reduceColumnNullOrder: aaa
+ reduceColumnSortOrder: +++
+ groupByVectorOutput: true
+ allNative: false
+ usesVectorUDFAdaptor: false
+ vectorized: true
+ rowBatchContext:
+ dataColumnCount: 3
+ dataColumns: KEY._col0:string, KEY._col1:string, KEY._col2:int
+ partitionColumnCount: 0
+ Reduce Operator Tree:
+ Group By Operator
+ Group By Vectorization:
+ className: VectorGroupByOperator
+ groupByMode: MERGEPARTIAL
+ vectorOutput: true
+ keyExpressions: col 0, col 1, col 2
+ native: false
+ vectorProcessingMode: MERGE_PARTIAL
+ projectedOutputColumns: []
+ keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: int)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 12 Data size: 2052 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string), _col2 (type: int), CASE WHEN ((_col2 = 0)) THEN ('0') WHEN ((_col2 = 1)) THEN ('1') WHEN ((_col2 = 2)) THEN ('2') WHEN ((_col2 = 3)) THEN ('3') ELSE ('nothing') END (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumns: [0, 1, 2, 8]
+ selectExpressions: IfExprStringScalarStringGroupColumn(col 3, val 0, col 7)(children: LongColEqualLongScalar(col 2, val 0) -> 3:long, IfExprStringScalarStringGroupColumn(col 4, val 1, col 8)(children: LongColEqualLongScalar(col 2, val 1) -> 4:long, IfExprStringScalarStringGroupColumn(col 5, val 2, col 7)(children: LongColEqualLongScalar(col 2, val 2) -> 5:long, IfExprStringScalarStringScalar(col 6, val 3, val nothing)(children: LongColEqualLongScalar(col 2, val 3) -> 6:long) -> 7:String) -> 8:String) -> 7:String) -> 8:String
+ Statistics: Num rows: 12 Data size: 2052 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ File Sink Vectorization:
+ className: VectorFileSinkOperator
+ native: false
+ Statistics: Num rows: 12 Data size: 2052 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 key, val, GROUPING__ID, CASE WHEN GROUPING__ID == 0 THEN "0" WHEN GROUPING__ID == 1 THEN "1" WHEN GROUPING__ID == 2 THEN "2" WHEN GROUPING__ID == 3 THEN "3" ELSE "nothing" END from T1 group by cube(key, val)
PREHOOK: type: QUERY
PREHOOK: Input: default@t1