[14/51] [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_partitioned_date_time.q.out -- diff --git a/ql/src/test/results/clientpositive/llap/vector_partitioned_date_time.q.out b/ql/src/test/results/clientpositive/llap/vector_partitioned_date_time.q.out index 2703aff..4cc6b81 100644 --- a/ql/src/test/results/clientpositive/llap/vector_partitioned_date_time.q.out +++ b/ql/src/test/results/clientpositive/llap/vector_partitioned_date_time.q.out @@ -244,12 +244,16 @@ POSTHOOK: Input: default@flights_tiny_orc 2010-10-29 12 2010-10-30 11 2010-10-31 8 -PREHOOK: query: explain +PREHOOK: query: explain vectorization expression select * from flights_tiny_orc sort by fl_num, fl_date limit 25 PREHOOK: type: QUERY -POSTHOOK: query: explain +POSTHOOK: query: explain vectorization expression select * from flights_tiny_orc sort by fl_num, fl_date limit 25 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 @@ -268,46 +272,102 @@ STAGE PLANS: TableScan alias: flights_tiny_orc Statistics: Num rows: 137 Data size: 39456 Basic stats: COMPLETE Column stats: NONE + TableScan Vectorization: + native: true + projectedOutputColumns: [0, 1, 2, 3, 4, 5] Select Operator expressions: origin_city_name (type: string), dest_city_name (type: string), fl_date (type: date), fl_time (type: timestamp), arr_delay (type: float), fl_num (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 +Select Vectorization: +className: VectorSelectOperator +native: true +projectedOutputColumns: [0, 1, 2, 3, 4, 5] Statistics: Num rows: 137 Data size: 39456 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col5 (type: int), _col2 (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 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: 137 Data size: 39456 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.1 value expressions: _col0 (type: string), _col1 (type: string), _col3 (type: timestamp), _col4 (type: float) 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: VALUE._col0 (type: string), VALUE._col1 (type: string), KEY.reducesinkkey1 (type: date), VALUE._col2 (type: timestamp), VALUE._col3 (type: float), KEY.reducesinkkey0 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 +Select Vectorization: +className: VectorSelectOperator +native: true +projectedOutputColumns: [2, 3, 1, 4, 5, 0] Statistics: Num rows: 137 Data size: 39456 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 25 + Limit Vectorization: + className: VectorLimitOperator + native: true Statistics: Num rows: 25 Data size: 7200
[14/51] [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/f923db0b/ql/src/test/results/clientpositive/llap/vector_varchar_simple.q.out -- diff --git a/ql/src/test/results/clientpositive/llap/vector_varchar_simple.q.out b/ql/src/test/results/clientpositive/llap/vector_varchar_simple.q.out index edb67f1..911a962 100644 --- a/ql/src/test/results/clientpositive/llap/vector_varchar_simple.q.out +++ b/ql/src/test/results/clientpositive/llap/vector_varchar_simple.q.out @@ -45,16 +45,20 @@ POSTHOOK: Input: default@src 0 val_0 10 val_10 100val_100 -PREHOOK: query: explain select key, value +PREHOOK: query: explain vectorization select key, value from varchar_2 order by key asc limit 5 PREHOOK: type: QUERY -POSTHOOK: query: explain select key, value +POSTHOOK: query: explain vectorization select key, value from varchar_2 order by key asc limit 5 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 @@ -84,8 +88,23 @@ STAGE PLANS: value expressions: _col1 (type: varchar(20)) 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: varchar(10)), VALUE._col0 (type: varchar(20)) @@ -148,16 +167,20 @@ POSTHOOK: Input: default@src 97 val_97 97 val_97 96 val_96 -PREHOOK: query: explain select key, value +PREHOOK: query: explain vectorization select key, value from varchar_2 order by key desc limit 5 PREHOOK: type: QUERY -POSTHOOK: query: explain select key, value +POSTHOOK: query: explain vectorization select key, value from varchar_2 order by key desc limit 5 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 @@ -187,8 +210,23 @@ STAGE PLANS: value expressions: _col1 (type: varchar(20)) 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: varchar(10)), VALUE._col0 (type: varchar(20)) @@ -254,12 +292,16 @@ create table varchar_3 ( POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default POSTHOOK: Output: default@varchar_3 -PREHOOK: query: explain +PREHOOK: query: explain vectorization expression insert into table varchar_3 select cint from alltypesorc limit 10 PREHOOK: type: QUERY -POSTHOOK: query: explain +POSTHOOK: query: explain vectorization expression insert into table varchar_3 select cint from alltypesorc limit 10 POSTHOOK: type: QUERY +PLAN VECTORIZATION: + enabled: true + enabledConditionsMet: [hive.vectorized.execution.enabled IS true] + STAGE DEPENDENCIES: Stage-1 is a root stage Stage-2 depends on stages: Stage-1 @@ -279,36 +321,81 @@ STAGE PLANS: TableScan alias: alltypesorc Statistics: Num rows: 12288 Data size: 36696 Basic stats: COMPLETE Column stats:
