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 2017/02/03 20:03:48 UTC
[23/51] [partial] hive git commit: HIVE-11394: Enhance EXPLAIN
display for vectorization (Matt McCline, reviewed by Gopal Vijayaraghavan)
http://git-wip-us.apache.org/repos/asf/hive/blob/fcb57100/ql/src/test/results/clientpositive/llap/vector_interval_arithmetic.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vector_interval_arithmetic.q.out b/ql/src/test/results/clientpositive/llap/vector_interval_arithmetic.q.out
index 391c775..ee8aa0c 100644
--- a/ql/src/test/results/clientpositive/llap/vector_interval_arithmetic.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_interval_arithmetic.q.out
@@ -35,7 +35,7 @@ POSTHOOK: Output: default@interval_arithmetic_1
POSTHOOK: Lineage: interval_arithmetic_1.dateval EXPRESSION [(unique_timestamps)unique_timestamps.FieldSchema(name:tsval, type:timestamp, comment:null), ]
POSTHOOK: Lineage: interval_arithmetic_1.tsval SIMPLE [(unique_timestamps)unique_timestamps.FieldSchema(name:tsval, type:timestamp, comment:null), ]
tsval tsval
-PREHOOK: query: explain
+PREHOOK: query: explain vectorization expression
select
dateval,
dateval - interval '2-2' year to month,
@@ -47,7 +47,7 @@ select
from interval_arithmetic_1
order by dateval
PREHOOK: type: QUERY
-POSTHOOK: query: explain
+POSTHOOK: query: explain vectorization expression
select
dateval,
dateval - interval '2-2' year to month,
@@ -60,6 +60,10 @@ from interval_arithmetic_1
order by dateval
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
@@ -77,26 +81,61 @@ STAGE PLANS:
TableScan
alias: interval_arithmetic_1
Statistics: Num rows: 50 Data size: 4800 Basic stats: COMPLETE Column stats: NONE
+ TableScan Vectorization:
+ native: true
+ projectedOutputColumns: [0, 1]
Select Operator
expressions: dateval (type: date), (dateval - 2-2) (type: date), (dateval - -2-2) (type: date), (dateval + 2-2) (type: date), (dateval + -2-2) (type: date), (-2-2 + dateval) (type: date), (2-2 + dateval) (type: date)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumns: [0, 2, 3, 4, 5, 6, 7]
+ selectExpressions: DateColSubtractIntervalYearMonthScalar(col 0, val 2-2) -> 2:long, DateColSubtractIntervalYearMonthScalar(col 0, val -2-2) -> 3:long, DateColAddIntervalYearMonthScalar(col 0, val 2-2) -> 4:long, DateColAddIntervalYearMonthScalar(col 0, val -2-2) -> 5:long, IntervalYearMonthScalarAddDateColumn(val -2-2, col 0) -> 6:long, IntervalYearMonthScalarAddDateColumn(val 2-2, col 0) -> 7:long
Statistics: Num rows: 50 Data size: 4800 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: date)
sort order: +
+ Reduce Sink Vectorization:
+ className: VectorReduceSinkOperator
+ native: false
+ nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, Not ACID UPDATE or DELETE IS true, No buckets IS true, No TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
+ nativeConditionsNotMet: Uniform Hash IS false
Statistics: Num rows: 50 Data size: 4800 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: date), _col2 (type: date), _col3 (type: date), _col4 (type: date), _col5 (type: date), _col6 (type: date)
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
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
+ groupByVectorOutput: true
+ allNative: false
+ usesVectorUDFAdaptor: false
+ vectorized: true
Reduce Operator Tree:
Select Operator
expressions: KEY.reducesinkkey0 (type: date), VALUE._col0 (type: date), VALUE._col1 (type: date), VALUE._col2 (type: date), VALUE._col3 (type: date), VALUE._col4 (type: date), VALUE._col5 (type: date)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6]
Statistics: Num rows: 50 Data size: 4800 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
+ File Sink Vectorization:
+ className: VectorFileSinkOperator
+ native: false
Statistics: Num rows: 50 Data size: 4800 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
@@ -186,7 +225,7 @@ dateval _c1 _c2 _c3 _c4 _c5 _c6
9075-06-13 9073-04-13 9077-08-13 9077-08-13 9073-04-13 9073-04-13 9077-08-13
9209-11-11 9207-09-11 9212-01-11 9212-01-11 9207-09-11 9207-09-11 9212-01-11
9403-01-09 9400-11-09 9405-03-09 9405-03-09 9400-11-09 9400-11-09 9405-03-09
-PREHOOK: query: explain
+PREHOOK: query: explain vectorization expression
select
dateval,
dateval - date '1999-06-07',
@@ -195,7 +234,7 @@ select
from interval_arithmetic_1
order by dateval
PREHOOK: type: QUERY
-POSTHOOK: query: explain
+POSTHOOK: query: explain vectorization expression
select
dateval,
dateval - date '1999-06-07',
@@ -205,6 +244,10 @@ from interval_arithmetic_1
order by dateval
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
@@ -222,26 +265,61 @@ STAGE PLANS:
TableScan
alias: interval_arithmetic_1
Statistics: Num rows: 50 Data size: 4800 Basic stats: COMPLETE Column stats: NONE
+ TableScan Vectorization:
+ native: true
+ projectedOutputColumns: [0, 1]
Select Operator
expressions: dateval (type: date), (dateval - 1999-06-07) (type: interval_day_time), (1999-06-07 - dateval) (type: interval_day_time), (dateval - dateval) (type: interval_day_time)
outputColumnNames: _col0, _col1, _col2, _col3
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumns: [0, 2, 3, 4]
+ selectExpressions: DateColSubtractDateScalar(col 0, val 1999-06-07 00:00:00.0) -> 2:timestamp, DateScalarSubtractDateColumn(val 1999-06-07 00:00:00.0, col 0) -> 3:timestamp, DateColSubtractDateColumn(col 0, col 0) -> 4:timestamp
Statistics: Num rows: 50 Data size: 4800 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: date)
sort order: +
+ Reduce Sink Vectorization:
+ className: VectorReduceSinkOperator
+ native: false
+ nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, Not ACID UPDATE or DELETE IS true, No buckets IS true, No TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
+ nativeConditionsNotMet: Uniform Hash IS false
Statistics: Num rows: 50 Data size: 4800 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: interval_day_time), _col2 (type: interval_day_time), _col3 (type: interval_day_time)
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
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
+ groupByVectorOutput: true
+ allNative: false
+ usesVectorUDFAdaptor: false
+ vectorized: true
Reduce Operator Tree:
Select Operator
expressions: KEY.reducesinkkey0 (type: date), VALUE._col0 (type: interval_day_time), VALUE._col1 (type: interval_day_time), VALUE._col2 (type: interval_day_time)
outputColumnNames: _col0, _col1, _col2, _col3
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumns: [0, 1, 2, 3]
Statistics: Num rows: 50 Data size: 4800 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
+ File Sink Vectorization:
+ className: VectorFileSinkOperator
+ native: false
Statistics: Num rows: 50 Data size: 4800 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
@@ -325,7 +403,7 @@ dateval _c1 _c2 _c3
9075-06-13 2584462 00:00:00.000000000 -2584462 00:00:00.000000000 0 00:00:00.000000000
9209-11-11 2633556 01:00:00.000000000 -2633556 01:00:00.000000000 0 00:00:00.000000000
9403-01-09 2704106 01:00:00.000000000 -2704106 01:00:00.000000000 0 00:00:00.000000000
-PREHOOK: query: explain
+PREHOOK: query: explain vectorization expression
select
tsval,
tsval - interval '2-2' year to month,
@@ -337,7 +415,7 @@ select
from interval_arithmetic_1
order by tsval
PREHOOK: type: QUERY
-POSTHOOK: query: explain
+POSTHOOK: query: explain vectorization expression
select
tsval,
tsval - interval '2-2' year to month,
@@ -350,6 +428,10 @@ from interval_arithmetic_1
order by tsval
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
@@ -367,26 +449,61 @@ STAGE PLANS:
TableScan
alias: interval_arithmetic_1
Statistics: Num rows: 50 Data size: 4800 Basic stats: COMPLETE Column stats: NONE
+ TableScan Vectorization:
+ native: true
+ projectedOutputColumns: [0, 1]
Select Operator
expressions: tsval (type: timestamp), (tsval - 2-2) (type: timestamp), (tsval - -2-2) (type: timestamp), (tsval + 2-2) (type: timestamp), (tsval + -2-2) (type: timestamp), (-2-2 + tsval) (type: timestamp), (2-2 + tsval) (type: timestamp)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumns: [1, 2, 3, 4, 5, 6, 7]
+ selectExpressions: TimestampColSubtractIntervalYearMonthScalar(col 1, val 2-2) -> 2:timestamp, TimestampColSubtractIntervalYearMonthScalar(col 1, val -2-2) -> 3:timestamp, TimestampColAddIntervalYearMonthScalar(col 1, val 2-2) -> 4:timestamp, TimestampColAddIntervalYearMonthScalar(col 1, val -2-2) -> 5:timestamp, IntervalYearMonthScalarAddTimestampColumn(val -2-2, col 1) -> 6:timestamp, IntervalYearMonthScalarAddTimestampColumn(val 2-2, col 1) -> 7:timestamp
Statistics: Num rows: 50 Data size: 4800 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: timestamp)
sort order: +
+ Reduce Sink Vectorization:
+ className: VectorReduceSinkOperator
+ native: false
+ nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, Not ACID UPDATE or DELETE IS true, No buckets IS true, No TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
+ nativeConditionsNotMet: Uniform Hash IS false
Statistics: Num rows: 50 Data size: 4800 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: timestamp), _col2 (type: timestamp), _col3 (type: timestamp), _col4 (type: timestamp), _col5 (type: timestamp), _col6 (type: timestamp)
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
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
+ groupByVectorOutput: true
+ allNative: false
+ usesVectorUDFAdaptor: false
+ vectorized: true
Reduce Operator Tree:
Select Operator
expressions: KEY.reducesinkkey0 (type: timestamp), VALUE._col0 (type: timestamp), VALUE._col1 (type: timestamp), VALUE._col2 (type: timestamp), VALUE._col3 (type: timestamp), VALUE._col4 (type: timestamp), VALUE._col5 (type: timestamp)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6]
Statistics: Num rows: 50 Data size: 4800 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
+ File Sink Vectorization:
+ className: VectorFileSinkOperator
+ native: false
Statistics: Num rows: 50 Data size: 4800 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
@@ -476,7 +593,7 @@ tsval _c1 _c2 _c3 _c4 _c5 _c6
9075-06-13 16:20:09.218517797 9073-04-13 16:20:09.218517797 9077-08-13 16:20:09.218517797 9077-08-13 16:20:09.218517797 9073-04-13 16:20:09.218517797 9073-04-13 16:20:09.218517797 9077-08-13 16:20:09.218517797
9209-11-11 04:08:58.223768453 9207-09-11 05:08:58.223768453 9212-01-11 04:08:58.223768453 9212-01-11 04:08:58.223768453 9207-09-11 05:08:58.223768453 9207-09-11 05:08:58.223768453 9212-01-11 04:08:58.223768453
9403-01-09 18:12:33.547 9400-11-09 18:12:33.547 9405-03-09 18:12:33.547 9405-03-09 18:12:33.547 9400-11-09 18:12:33.547 9400-11-09 18:12:33.547 9405-03-09 18:12:33.547
-PREHOOK: query: explain
+PREHOOK: query: explain vectorization expression
select
interval '2-2' year to month + interval '3-3' year to month,
interval '2-2' year to month - interval '3-3' year to month
@@ -484,7 +601,7 @@ from interval_arithmetic_1
order by interval '2-2' year to month + interval '3-3' year to month
limit 2
PREHOOK: type: QUERY
-POSTHOOK: query: explain
+POSTHOOK: query: explain vectorization expression
select
interval '2-2' year to month + interval '3-3' year to month,
interval '2-2' year to month - interval '3-3' year to month
@@ -493,6 +610,10 @@ order by interval '2-2' year to month + interval '3-3' year to month
limit 2
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
@@ -510,27 +631,65 @@ STAGE PLANS:
TableScan
alias: interval_arithmetic_1
Statistics: Num rows: 50 Data size: 4800 Basic stats: COMPLETE Column stats: COMPLETE
+ TableScan Vectorization:
+ native: true
+ projectedOutputColumns: [0, 1]
Select Operator
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumns: []
Statistics: Num rows: 50 Data size: 800 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: CAST( 5-5 AS INTERVAL YEAR TO MONTH) (type: interval_year_month)
sort order: +
+ Reduce Sink Vectorization:
+ className: VectorReduceSinkOperator
+ native: false
+ nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, Not ACID UPDATE or DELETE IS true, No buckets IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
+ nativeConditionsNotMet: No TopN IS false, Uniform Hash IS false
Statistics: Num rows: 50 Data size: 800 Basic stats: COMPLETE Column stats: COMPLETE
TopN Hash Memory Usage: 0.1
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
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
+ groupByVectorOutput: true
+ allNative: false
+ usesVectorUDFAdaptor: false
+ vectorized: true
Reduce Operator Tree:
Select Operator
expressions: 5-5 (type: interval_year_month), -1-1 (type: interval_year_month)
outputColumnNames: _col0, _col1
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumns: [1, 2]
+ selectExpressions: ConstantVectorExpression(val 65) -> 1:long, ConstantVectorExpression(val -13) -> 2:long
Statistics: Num rows: 50 Data size: 800 Basic stats: COMPLETE Column stats: COMPLETE
Limit
Number of rows: 2
+ Limit Vectorization:
+ className: VectorLimitOperator
+ native: true
Statistics: Num rows: 2 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
+ File Sink Vectorization:
+ className: VectorFileSinkOperator
+ native: false
Statistics: Num rows: 2 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
@@ -564,7 +723,7 @@ POSTHOOK: Input: default@interval_arithmetic_1
_c0 _c1
5-5 -1-1
5-5 -1-1
-PREHOOK: query: explain
+PREHOOK: query: explain vectorization expression
select
dateval,
dateval - interval '99 11:22:33.123456789' day to second,
@@ -576,7 +735,7 @@ select
from interval_arithmetic_1
order by dateval
PREHOOK: type: QUERY
-POSTHOOK: query: explain
+POSTHOOK: query: explain vectorization expression
select
dateval,
dateval - interval '99 11:22:33.123456789' day to second,
@@ -589,6 +748,10 @@ from interval_arithmetic_1
order by dateval
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
@@ -606,26 +769,61 @@ STAGE PLANS:
TableScan
alias: interval_arithmetic_1
Statistics: Num rows: 50 Data size: 4800 Basic stats: COMPLETE Column stats: NONE
+ TableScan Vectorization:
+ native: true
+ projectedOutputColumns: [0, 1]
Select Operator
expressions: dateval (type: date), (dateval - 99 11:22:33.123456789) (type: timestamp), (dateval - -99 11:22:33.123456789) (type: timestamp), (dateval + 99 11:22:33.123456789) (type: timestamp), (dateval + -99 11:22:33.123456789) (type: timestamp), (-99 11:22:33.123456789 + dateval) (type: timestamp), (99 11:22:33.123456789 + dateval) (type: timestamp)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumns: [0, 2, 3, 4, 5, 6, 7]
+ selectExpressions: DateColSubtractIntervalDayTimeScalar(col 0, val 99 11:22:33.123456789) -> 2:timestamp, DateColSubtractIntervalDayTimeScalar(col 0, val -99 11:22:33.123456789) -> 3:timestamp, DateColAddIntervalDayTimeScalar(col 0, val 99 11:22:33.123456789) -> 4:timestamp, DateColAddIntervalDayTimeScalar(col 0, val -99 11:22:33.123456789) -> 5:timestamp, IntervalDayTimeScalarAddDateColumn(val -99 11:22:33.123456789, col 0) -> 6:timestamp, IntervalDayTimeScalarAddDateColumn(val 99 11:22:33.123456789, col 0) -> 7:timestamp
Statistics: Num rows: 50 Data size: 4800 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: date)
sort order: +
+ Reduce Sink Vectorization:
+ className: VectorReduceSinkOperator
+ native: false
+ nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, Not ACID UPDATE or DELETE IS true, No buckets IS true, No TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
+ nativeConditionsNotMet: Uniform Hash IS false
Statistics: Num rows: 50 Data size: 4800 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: timestamp), _col2 (type: timestamp), _col3 (type: timestamp), _col4 (type: timestamp), _col5 (type: timestamp), _col6 (type: timestamp)
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
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
+ groupByVectorOutput: true
+ allNative: false
+ usesVectorUDFAdaptor: false
+ vectorized: true
Reduce Operator Tree:
Select Operator
expressions: KEY.reducesinkkey0 (type: date), VALUE._col0 (type: timestamp), VALUE._col1 (type: timestamp), VALUE._col2 (type: timestamp), VALUE._col3 (type: timestamp), VALUE._col4 (type: timestamp), VALUE._col5 (type: timestamp)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6]
Statistics: Num rows: 50 Data size: 4800 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
+ File Sink Vectorization:
+ className: VectorFileSinkOperator
+ native: false
Statistics: Num rows: 50 Data size: 4800 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
@@ -715,7 +913,7 @@ dateval _c1 _c2 _c3 _c4 _c5 _c6
9075-06-13 9075-03-05 11:37:26.876543211 9075-09-20 11:22:33.123456789 9075-09-20 11:22:33.123456789 9075-03-05 11:37:26.876543211 9075-03-05 11:37:26.876543211 9075-09-20 11:22:33.123456789
9209-11-11 9209-08-03 13:37:26.876543211 9210-02-18 11:22:33.123456789 9210-02-18 11:22:33.123456789 9209-08-03 13:37:26.876543211 9209-08-03 13:37:26.876543211 9210-02-18 11:22:33.123456789
9403-01-09 9402-10-01 13:37:26.876543211 9403-04-18 12:22:33.123456789 9403-04-18 12:22:33.123456789 9402-10-01 13:37:26.876543211 9402-10-01 13:37:26.876543211 9403-04-18 12:22:33.123456789
-PREHOOK: query: explain
+PREHOOK: query: explain vectorization expression
select
dateval,
tsval,
@@ -725,7 +923,7 @@ select
from interval_arithmetic_1
order by dateval
PREHOOK: type: QUERY
-POSTHOOK: query: explain
+POSTHOOK: query: explain vectorization expression
select
dateval,
tsval,
@@ -736,6 +934,10 @@ from interval_arithmetic_1
order by dateval
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
@@ -753,26 +955,61 @@ STAGE PLANS:
TableScan
alias: interval_arithmetic_1
Statistics: Num rows: 50 Data size: 4800 Basic stats: COMPLETE Column stats: NONE
+ TableScan Vectorization:
+ native: true
+ projectedOutputColumns: [0, 1]
Select Operator
expressions: dateval (type: date), tsval (type: timestamp), (dateval - tsval) (type: interval_day_time), (tsval - dateval) (type: interval_day_time), (tsval - tsval) (type: interval_day_time)
outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumns: [0, 1, 2, 3, 4]
+ selectExpressions: DateColSubtractTimestampColumn(col 0, col 1) -> 2:interval_day_time, TimestampColSubtractDateColumn(col 1, col 0) -> 3:interval_day_time, TimestampColSubtractTimestampColumn(col 1, col 1) -> 4:interval_day_time
Statistics: Num rows: 50 Data size: 4800 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: date)
sort order: +
+ Reduce Sink Vectorization:
+ className: VectorReduceSinkOperator
+ native: false
+ nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, Not ACID UPDATE or DELETE IS true, No buckets IS true, No TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
+ nativeConditionsNotMet: Uniform Hash IS false
Statistics: Num rows: 50 Data size: 4800 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: timestamp), _col2 (type: interval_day_time), _col3 (type: interval_day_time), _col4 (type: interval_day_time)
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
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
+ groupByVectorOutput: true
+ allNative: false
+ usesVectorUDFAdaptor: false
+ vectorized: true
Reduce Operator Tree:
Select Operator
expressions: KEY.reducesinkkey0 (type: date), VALUE._col0 (type: timestamp), VALUE._col1 (type: interval_day_time), VALUE._col2 (type: interval_day_time), VALUE._col3 (type: interval_day_time)
outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumns: [0, 1, 2, 3, 4]
Statistics: Num rows: 50 Data size: 4800 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
+ File Sink Vectorization:
+ className: VectorFileSinkOperator
+ native: false
Statistics: Num rows: 50 Data size: 4800 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
@@ -858,7 +1095,7 @@ dateval tsval _c2 _c3 _c4
9075-06-13 9075-06-13 16:20:09.218517797 -0 16:20:09.218517797 0 16:20:09.218517797 0 00:00:00.000000000
9209-11-11 9209-11-11 04:08:58.223768453 -0 04:08:58.223768453 0 04:08:58.223768453 0 00:00:00.000000000
9403-01-09 9403-01-09 18:12:33.547 -0 18:12:33.547000000 0 18:12:33.547000000 0 00:00:00.000000000
-PREHOOK: query: explain
+PREHOOK: query: explain vectorization expression
select
tsval,
tsval - interval '99 11:22:33.123456789' day to second,
@@ -870,7 +1107,7 @@ select
from interval_arithmetic_1
order by tsval
PREHOOK: type: QUERY
-POSTHOOK: query: explain
+POSTHOOK: query: explain vectorization expression
select
tsval,
tsval - interval '99 11:22:33.123456789' day to second,
@@ -883,6 +1120,10 @@ from interval_arithmetic_1
order by tsval
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
@@ -900,26 +1141,61 @@ STAGE PLANS:
TableScan
alias: interval_arithmetic_1
Statistics: Num rows: 50 Data size: 4800 Basic stats: COMPLETE Column stats: NONE
+ TableScan Vectorization:
+ native: true
+ projectedOutputColumns: [0, 1]
Select Operator
expressions: tsval (type: timestamp), (tsval - 99 11:22:33.123456789) (type: timestamp), (tsval - -99 11:22:33.123456789) (type: timestamp), (tsval + 99 11:22:33.123456789) (type: timestamp), (tsval + -99 11:22:33.123456789) (type: timestamp), (-99 11:22:33.123456789 + tsval) (type: timestamp), (99 11:22:33.123456789 + tsval) (type: timestamp)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumns: [1, 2, 3, 4, 5, 6, 7]
+ selectExpressions: TimestampColSubtractIntervalDayTimeScalar(col 1, val 99 11:22:33.123456789) -> 2:timestamp, TimestampColSubtractIntervalDayTimeScalar(col 1, val -99 11:22:33.123456789) -> 3:timestamp, TimestampColAddIntervalDayTimeScalar(col 1, val 99 11:22:33.123456789) -> 4:timestamp, TimestampColAddIntervalDayTimeScalar(col 1, val -99 11:22:33.123456789) -> 5:timestamp, IntervalDayTimeScalarAddTimestampColumn(val -99 11:22:33.123456789, col 1) -> 6:timestamp, IntervalDayTimeScalarAddTimestampColumn(val 99 11:22:33.123456789, col 1) -> 7:timestamp
Statistics: Num rows: 50 Data size: 4800 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: timestamp)
sort order: +
+ Reduce Sink Vectorization:
+ className: VectorReduceSinkOperator
+ native: false
+ nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, Not ACID UPDATE or DELETE IS true, No buckets IS true, No TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
+ nativeConditionsNotMet: Uniform Hash IS false
Statistics: Num rows: 50 Data size: 4800 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: timestamp), _col2 (type: timestamp), _col3 (type: timestamp), _col4 (type: timestamp), _col5 (type: timestamp), _col6 (type: timestamp)
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
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
+ groupByVectorOutput: true
+ allNative: false
+ usesVectorUDFAdaptor: false
+ vectorized: true
Reduce Operator Tree:
Select Operator
expressions: KEY.reducesinkkey0 (type: timestamp), VALUE._col0 (type: timestamp), VALUE._col1 (type: timestamp), VALUE._col2 (type: timestamp), VALUE._col3 (type: timestamp), VALUE._col4 (type: timestamp), VALUE._col5 (type: timestamp)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6]
Statistics: Num rows: 50 Data size: 4800 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
+ File Sink Vectorization:
+ className: VectorFileSinkOperator
+ native: false
Statistics: Num rows: 50 Data size: 4800 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
@@ -1009,14 +1285,14 @@ tsval _c1 _c2 _c3 _c4 _c5 _c6
9075-06-13 16:20:09.218517797 9075-03-06 03:57:36.095061008 9075-09-21 03:42:42.341974586 9075-09-21 03:42:42.341974586 9075-03-06 03:57:36.095061008 9075-03-06 03:57:36.095061008 9075-09-21 03:42:42.341974586
9209-11-11 04:08:58.223768453 9209-08-03 17:46:25.100311664 9210-02-18 15:31:31.347225242 9210-02-18 15:31:31.347225242 9209-08-03 17:46:25.100311664 9209-08-03 17:46:25.100311664 9210-02-18 15:31:31.347225242
9403-01-09 18:12:33.547 9402-10-02 07:50:00.423543211 9403-04-19 06:35:06.670456789 9403-04-19 06:35:06.670456789 9402-10-02 07:50:00.423543211 9402-10-02 07:50:00.423543211 9403-04-19 06:35:06.670456789
-PREHOOK: query: explain
+PREHOOK: query: explain vectorization expression
select
interval '99 11:22:33.123456789' day to second + interval '10 9:8:7.123456789' day to second,
interval '99 11:22:33.123456789' day to second - interval '10 9:8:7.123456789' day to second
from interval_arithmetic_1
limit 2
PREHOOK: type: QUERY
-POSTHOOK: query: explain
+POSTHOOK: query: explain vectorization expression
select
interval '99 11:22:33.123456789' day to second + interval '10 9:8:7.123456789' day to second,
interval '99 11:22:33.123456789' day to second - interval '10 9:8:7.123456789' day to second
@@ -1024,6 +1300,10 @@ from interval_arithmetic_1
limit 2
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
@@ -1038,15 +1318,29 @@ STAGE PLANS:
TableScan
alias: interval_arithmetic_1
Statistics: Num rows: 50 Data size: 4800 Basic stats: COMPLETE Column stats: COMPLETE
+ TableScan Vectorization:
+ native: true
+ projectedOutputColumns: [0, 1]
Select Operator
expressions: 109 20:30:40.246913578 (type: interval_day_time), 89 02:14:26.000000000 (type: interval_day_time)
outputColumnNames: _col0, _col1
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumns: [2, 3]
+ selectExpressions: ConstantVectorExpression(val 109 20:30:40.246913578) -> 2:interval_day_time, ConstantVectorExpression(val 89 02:14:26.000000000) -> 3:interval_day_time
Statistics: Num rows: 50 Data size: 1200 Basic stats: COMPLETE Column stats: COMPLETE
Limit
Number of rows: 2
+ Limit Vectorization:
+ className: VectorLimitOperator
+ native: true
Statistics: Num rows: 2 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
+ File Sink Vectorization:
+ className: VectorFileSinkOperator
+ native: false
Statistics: Num rows: 2 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
@@ -1054,6 +1348,14 @@ STAGE PLANS:
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
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
Stage: Stage-0
Fetch Operator
http://git-wip-us.apache.org/repos/asf/hive/blob/fcb57100/ql/src/test/results/clientpositive/llap/vector_interval_mapjoin.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vector_interval_mapjoin.q.out b/ql/src/test/results/clientpositive/llap/vector_interval_mapjoin.q.out
index 0bc0e4c..53c728b 100644
--- a/ql/src/test/results/clientpositive/llap/vector_interval_mapjoin.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_interval_mapjoin.q.out
@@ -136,7 +136,7 @@ POSTHOOK: Lineage: vectortab_b_1korc.si SIMPLE [(vectortab_b_1k)vectortab_b_1k.F
POSTHOOK: Lineage: vectortab_b_1korc.t SIMPLE [(vectortab_b_1k)vectortab_b_1k.FieldSchema(name:t, type:tinyint, comment:null), ]
POSTHOOK: Lineage: vectortab_b_1korc.ts SIMPLE [(vectortab_b_1k)vectortab_b_1k.FieldSchema(name:ts, type:timestamp, comment:null), ]
POSTHOOK: Lineage: vectortab_b_1korc.ts2 SIMPLE [(vectortab_b_1k)vectortab_b_1k.FieldSchema(name:ts2, type:timestamp, comment:null), ]
-PREHOOK: query: explain
+PREHOOK: query: explain vectorization expression
select
v1.s,
v2.s,
@@ -158,7 +158,7 @@ join
on v1.intrvl1 = v2.intrvl2
and v1.s = v2.s
PREHOOK: type: QUERY
-POSTHOOK: query: explain
+POSTHOOK: query: explain vectorization expression
select
v1.s,
v2.s,
@@ -180,6 +180,10 @@ join
on v1.intrvl1 = v2.intrvl2
and v1.s = v2.s
POSTHOOK: type: QUERY
+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
@@ -197,12 +201,24 @@ STAGE PLANS:
TableScan
alias: vectortab_a_1korc
Statistics: Num rows: 1000 Data size: 460264 Basic stats: COMPLETE Column stats: NONE
+ TableScan Vectorization:
+ native: true
+ projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12]
Filter Operator
+ Filter Vectorization:
+ className: VectorFilterOperator
+ native: true
+ predicateExpression: FilterExprAndExpr(children: SelectColumnIsNotNull(col 8) -> boolean, SelectColumnIsNotNull(col 14)(children: DateColSubtractDateColumn(col 12, col 13)(children: CastTimestampToDate(col 10) -> 13:date) -> 14:timestamp) -> boolean) -> boolean
predicate: (s is not null and (dt - CAST( ts AS DATE)) is not null) (type: boolean)
Statistics: Num rows: 1000 Data size: 460264 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: s (type: string), (dt - CAST( ts AS DATE)) (type: interval_day_time)
outputColumnNames: _col0, _col1
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumns: [8, 14]
+ selectExpressions: DateColSubtractDateColumn(col 12, col 13)(children: CastTimestampToDate(col 10) -> 13:date) -> 14:timestamp
Statistics: Num rows: 1000 Data size: 460264 Basic stats: COMPLETE Column stats: NONE
Map Join Operator
condition map:
@@ -210,6 +226,10 @@ STAGE PLANS:
keys:
0 _col0 (type: string), _col1 (type: interval_day_time)
1 _col0 (type: string), _col1 (type: interval_day_time)
+ Map Join Vectorization:
+ className: VectorMapJoinInnerBigOnlyMultiKeyOperator
+ native: true
+ nativeConditionsMet: hive.mapjoin.optimized.hashtable IS true, hive.vectorized.execution.mapjoin.native.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, One MapJoin Condition IS true, No nullsafe IS true, Small table vectorizes IS true, Optimized Table and Supports Key Types IS true
outputColumnNames: _col0, _col1, _col2
input vertices:
1 Map 2
@@ -217,9 +237,16 @@ STAGE PLANS:
Select Operator
expressions: _col0 (type: string), _col2 (type: string), _col1 (type: interval_day_time)
outputColumnNames: _col0, _col1, _col2
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumns: [8, 8, 14]
Statistics: Num rows: 1100 Data size: 506290 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
+ File Sink Vectorization:
+ className: VectorFileSinkOperator
+ native: false
Statistics: Num rows: 1100 Data size: 506290 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
@@ -227,25 +254,57 @@ STAGE PLANS:
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
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
Map 2
Map Operator Tree:
TableScan
alias: vectortab_b_1korc
Statistics: Num rows: 1000 Data size: 458448 Basic stats: COMPLETE Column stats: NONE
+ TableScan Vectorization:
+ native: true
+ projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12]
Filter Operator
+ Filter Vectorization:
+ className: VectorFilterOperator
+ native: true
+ predicateExpression: FilterExprAndExpr(children: SelectColumnIsNotNull(col 8) -> boolean, SelectColumnIsNotNull(col 14)(children: DateColSubtractDateColumn(col 12, col 13)(children: CastTimestampToDate(col 10) -> 13:date) -> 14:timestamp) -> boolean) -> boolean
predicate: (s is not null and (dt - CAST( ts AS DATE)) is not null) (type: boolean)
Statistics: Num rows: 1000 Data size: 458448 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: s (type: string), (dt - CAST( ts AS DATE)) (type: interval_day_time)
outputColumnNames: _col0, _col1
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumns: [8, 14]
+ selectExpressions: DateColSubtractDateColumn(col 12, col 13)(children: CastTimestampToDate(col 10) -> 13:date) -> 14:timestamp
Statistics: Num rows: 1000 Data size: 458448 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: interval_day_time)
sort order: ++
Map-reduce partition columns: _col0 (type: string), _col1 (type: interval_day_time)
+ Reduce Sink Vectorization:
+ className: VectorReduceSinkMultiKeyOperator
+ native: true
+ nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, Not ACID UPDATE or DELETE IS true, No buckets IS true, No TopN IS true, Uniform Hash IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
Statistics: Num rows: 1000 Data size: 458448 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: true
+ usesVectorUDFAdaptor: false
+ vectorized: true
Stage: Stage-0
Fetch Operator
http://git-wip-us.apache.org/repos/asf/hive/blob/fcb57100/ql/src/test/results/clientpositive/llap/vector_join.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vector_join.q.out b/ql/src/test/results/clientpositive/llap/vector_join.q.out
new file mode 100644
index 0000000..94c0290
--- /dev/null
+++ b/ql/src/test/results/clientpositive/llap/vector_join.q.out
@@ -0,0 +1,104 @@
+PREHOOK: query: DROP TABLE IF EXISTS test1_vc
+PREHOOK: type: DROPTABLE
+POSTHOOK: query: DROP TABLE IF EXISTS test1_vc
+POSTHOOK: type: DROPTABLE
+PREHOOK: query: DROP TABLE IF EXISTS test2_vc
+PREHOOK: type: DROPTABLE
+POSTHOOK: query: DROP TABLE IF EXISTS test2_vc
+POSTHOOK: type: DROPTABLE
+PREHOOK: query: CREATE TABLE test1_vc
+ (
+ id string)
+ PARTITIONED BY (
+ cr_year bigint,
+ cr_month bigint)
+ ROW FORMAT SERDE
+ 'org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe'
+STORED AS INPUTFORMAT
+ 'org.apache.hadoop.hive.ql.io.RCFileInputFormat'
+OUTPUTFORMAT
+ 'org.apache.hadoop.hive.ql.io.RCFileOutputFormat'
+TBLPROPERTIES (
+ 'serialization.null.format'='' )
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@test1_vc
+POSTHOOK: query: CREATE TABLE test1_vc
+ (
+ id string)
+ PARTITIONED BY (
+ cr_year bigint,
+ cr_month bigint)
+ ROW FORMAT SERDE
+ 'org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe'
+STORED AS INPUTFORMAT
+ 'org.apache.hadoop.hive.ql.io.RCFileInputFormat'
+OUTPUTFORMAT
+ 'org.apache.hadoop.hive.ql.io.RCFileOutputFormat'
+TBLPROPERTIES (
+ 'serialization.null.format'='' )
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@test1_vc
+PREHOOK: query: CREATE TABLE test2_vc(
+ id string
+ )
+ PARTITIONED BY (
+ cr_year bigint,
+ cr_month bigint)
+ROW FORMAT SERDE
+ 'org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe'
+STORED AS INPUTFORMAT
+ 'org.apache.hadoop.hive.ql.io.RCFileInputFormat'
+OUTPUTFORMAT
+ 'org.apache.hadoop.hive.ql.io.RCFileOutputFormat'
+TBLPROPERTIES (
+ 'serialization.null.format'=''
+ )
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@test2_vc
+POSTHOOK: query: CREATE TABLE test2_vc(
+ id string
+ )
+ PARTITIONED BY (
+ cr_year bigint,
+ cr_month bigint)
+ROW FORMAT SERDE
+ 'org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe'
+STORED AS INPUTFORMAT
+ 'org.apache.hadoop.hive.ql.io.RCFileInputFormat'
+OUTPUTFORMAT
+ 'org.apache.hadoop.hive.ql.io.RCFileOutputFormat'
+TBLPROPERTIES (
+ 'serialization.null.format'=''
+ )
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@test2_vc
+PREHOOK: query: SELECT cr.id1 ,
+cr.id2
+FROM
+(SELECT t1.id id1,
+ t2.id id2
+ from
+ (select * from test1_vc ) t1
+ left outer join test2_vc t2
+ on t1.id=t2.id) cr
+PREHOOK: type: QUERY
+PREHOOK: Input: default@test1_vc
+PREHOOK: Input: default@test2_vc
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT cr.id1 ,
+cr.id2
+FROM
+(SELECT t1.id id1,
+ t2.id id2
+ from
+ (select * from test1_vc ) t1
+ left outer join test2_vc t2
+ on t1.id=t2.id) cr
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@test1_vc
+POSTHOOK: Input: default@test2_vc
+#### A masked pattern was here ####