[27/51] [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_groupby_reduce.q.out -- diff --git a/ql/src/test/results/clientpositive/llap/vector_groupby_reduce.q.out b/ql/src/test/results/clientpositive/llap/vector_groupby_reduce.q.out index c4bcbab..8599e97 100644 --- a/ql/src/test/results/clientpositive/llap/vector_groupby_reduce.q.out +++ b/ql/src/test/results/clientpositive/llap/vector_groupby_reduce.q.out @@ -211,7 +211,7 @@ POSTHOOK: Lineage: store_sales.ss_sold_time_sk SIMPLE [(store_sales_txt)store_sa POSTHOOK: Lineage: store_sales.ss_store_sk SIMPLE [(store_sales_txt)store_sales_txt.FieldSchema(name:ss_store_sk, type:int, comment:null), ] POSTHOOK: Lineage: store_sales.ss_ticket_number SIMPLE [(store_sales_txt)store_sales_txt.FieldSchema(name:ss_ticket_number, type:int, comment:null), ] POSTHOOK: Lineage: store_sales.ss_wholesale_cost SIMPLE [(store_sales_txt)store_sales_txt.FieldSchema(name:ss_wholesale_cost, type:float, comment:null), ] -PREHOOK: query: explain +PREHOOK: query: explain vectorization expression select ss_ticket_number from @@ -219,7 +219,7 @@ from group by ss_ticket_number limit 20 PREHOOK: type: QUERY -POSTHOOK: query: explain +POSTHOOK: query: explain vectorization expression select ss_ticket_number from @@ -227,6 +227,10 @@ from group by ss_ticket_number limit 20 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 @@ -244,11 +248,24 @@ STAGE PLANS: TableScan alias: store_sales Statistics: Num rows: 1000 Data size: 88276 Basic stats: COMPLETE Column stats: NONE + TableScan Vectorization: + native: true + projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22] Select Operator expressions: ss_ticket_number (type: int) outputColumnNames: ss_ticket_number +Select Vectorization: +className: VectorSelectOperator +native: true +projectedOutputColumns: [9] Statistics: Num rows: 1000 Data size: 88276 Basic stats: COMPLETE Column stats: NONE Group By Operator + Group By Vectorization: + className: VectorGroupByOperator + vectorOutput: true + keyExpressions: col 9 + native: false + projectedOutputColumns: [] keys: ss_ticket_number (type: int) mode: hash outputColumnNames: _col0 @@ -257,23 +274,55 @@ STAGE PLANS: key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) +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, Uniform Hash IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true +nativeConditionsNotMet: No TopN IS false Statistics: Num rows: 1000 Data size: 88276 Basic stats: COMPLETE Column stats: NONE 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: Group By Operator +Group By Vectorization: +
[27/51] [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_interval_1.q.out -- diff --git a/ql/src/test/results/clientpositive/llap/vector_interval_1.q.out b/ql/src/test/results/clientpositive/llap/vector_interval_1.q.out index d8003ba..e7d1963 100644 --- a/ql/src/test/results/clientpositive/llap/vector_interval_1.q.out +++ b/ql/src/test/results/clientpositive/llap/vector_interval_1.q.out @@ -39,7 +39,7 @@ POSTHOOK: Lineage: vector_interval_1.str1 EXPRESSION [] POSTHOOK: Lineage: vector_interval_1.str2 EXPRESSION [] POSTHOOK: Lineage: vector_interval_1.ts EXPRESSION [] PREHOOK: query: -- constants/cast from string -explain +explain vectorization expression select str1, interval '1-2' year to month, interval_year_month(str1), @@ -47,13 +47,17 @@ select from vector_interval_1 order by str1 PREHOOK: type: QUERY POSTHOOK: query: -- constants/cast from string -explain +explain vectorization expression select str1, interval '1-2' year to month, interval_year_month(str1), interval '1 2:3:4' day to second, interval_day_time(str2) from vector_interval_1 order by str1 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 @@ -71,26 +75,62 @@ STAGE PLANS: TableScan alias: vector_interval_1 Statistics: Num rows: 2 Data size: 442 Basic stats: COMPLETE Column stats: NONE + TableScan Vectorization: + native: true + projectedOutputColumns: [0, 1, 2, 3] Select Operator expressions: str1 (type: string), CAST( str1 AS INTERVAL YEAR TO MONTH) (type: interval_year_month), CAST( str2 AS INTERVAL DAY TO SECOND) (type: interval_day_time) outputColumnNames: _col0, _col2, _col4 +Select Vectorization: +className: VectorSelectOperator +native: true +projectedOutputColumns: [2, 4, 5] +selectExpressions: CastStringToIntervalYearMonth(col 2) -> 4:interval_year_month, CastStringToIntervalDayTime(col 3) -> 5:interval_day_time Statistics: Num rows: 2 Data size: 442 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) 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: 2 Data size: 442 Basic stats: COMPLETE Column stats: NONE value expressions: _col2 (type: interval_year_month), _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: string), 1-2 (type: interval_year_month), VALUE._col0 (type: interval_year_month), 1 02:03:04.0 (type: interval_day_time), VALUE._col1 (type: interval_day_time) outputColumnNames: _col0, _col1, _col2, _col3, _col4 +Select Vectorization: +className: VectorSelectOperator +native: true +projectedOutputColumns: [0, 3, 1, 4, 2] +selectExpressions: ConstantVectorExpression(val 14) -> 3:long,