http://git-wip-us.apache.org/repos/asf/hive/blob/470ba3e2/ql/src/test/results/clientpositive/perf/spark/query47.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/spark/query47.q.out b/ql/src/test/results/clientpositive/perf/spark/query47.q.out index 690b105..a2387e8 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query47.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query47.q.out @@ -1,4 +1,4 @@ -PREHOOK: query: explain +PREHOOK: query: explain vectorization expression with v1 as( select i_category, i_brand, s_store_name, s_company_name, @@ -48,7 +48,7 @@ with v1 as( order by sum_sales - avg_monthly_sales, 3 limit 100 PREHOOK: type: QUERY -POSTHOOK: query: explain +POSTHOOK: query: explain vectorization expression with v1 as( select i_category, i_brand, s_store_name, s_company_name, @@ -98,6 +98,10 @@ with v1 as( order by sum_sales - avg_monthly_sales, 3 limit 100 POSTHOOK: type: QUERY +PLAN VECTORIZATION: + enabled: true + enabledConditionsMet: [hive.vectorized.execution.enabled IS true] + STAGE DEPENDENCIES: Stage-2 is a root stage Stage-3 depends on stages: Stage-2 @@ -116,18 +120,40 @@ STAGE PLANS: alias: store filterExpr: (s_store_sk is not null and s_store_name is not null and s_company_name is not null) (type: boolean) Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + TableScan Vectorization: + native: true Filter Operator + Filter Vectorization: + className: VectorFilterOperator + native: true + predicateExpression: FilterExprAndExpr(children: SelectColumnIsNotNull(col 0:int), SelectColumnIsNotNull(col 5:string), SelectColumnIsNotNull(col 17:string)) predicate: (s_company_name is not null and s_store_name is not null and s_store_sk is not null) (type: boolean) Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: s_store_sk (type: int), s_store_name (type: string), s_company_name (type: string) outputColumnNames: _col0, _col1, _col2 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [0, 5, 17] Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE Spark HashTable Sink Operator + Spark Hash Table Sink Vectorization: + className: VectorSparkHashTableSinkOperator + native: true keys: 0 _col2 (type: int) 1 _col0 (type: int) Execution mode: vectorized + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + inputFormatFeatureSupport: [DECIMAL_64] + featureSupportInUse: [DECIMAL_64] + inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + allNative: true + usesVectorUDFAdaptor: false + vectorized: true Local Work: Map Reduce Local Work @@ -141,18 +167,40 @@ STAGE PLANS: alias: store filterExpr: (s_store_sk is not null and s_store_name is not null and s_company_name is not null) (type: boolean) Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + TableScan Vectorization: + native: true Filter Operator + Filter Vectorization: + className: VectorFilterOperator + native: true + predicateExpression: FilterExprAndExpr(children: SelectColumnIsNotNull(col 0:int), SelectColumnIsNotNull(col 5:string), SelectColumnIsNotNull(col 17:string)) predicate: (s_company_name is not null and s_store_name is not null and s_store_sk is not null) (type: boolean) Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: s_store_sk (type: int), s_store_name (type: string), s_company_name (type: string) outputColumnNames: _col0, _col1, _col2 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [0, 5, 17] Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE Spark HashTable Sink Operator + Spark Hash Table Sink Vectorization: + className: VectorSparkHashTableSinkOperator + native: true keys: 0 _col2 (type: int) 1 _col0 (type: int) Execution mode: vectorized + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + inputFormatFeatureSupport: [DECIMAL_64] + featureSupportInUse: [DECIMAL_64] + inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + allNative: true + usesVectorUDFAdaptor: false + vectorized: true Local Work: Map Reduce Local Work @@ -166,18 +214,40 @@ STAGE PLANS: alias: store filterExpr: (s_store_sk is not null and s_store_name is not null and s_company_name is not null) (type: boolean) Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + TableScan Vectorization: + native: true Filter Operator + Filter Vectorization: + className: VectorFilterOperator + native: true + predicateExpression: FilterExprAndExpr(children: SelectColumnIsNotNull(col 0:int), SelectColumnIsNotNull(col 5:string), SelectColumnIsNotNull(col 17:string)) predicate: (s_company_name is not null and s_store_name is not null and s_store_sk is not null) (type: boolean) Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: s_store_sk (type: int), s_store_name (type: string), s_company_name (type: string) outputColumnNames: _col0, _col1, _col2 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [0, 5, 17] Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE Spark HashTable Sink Operator + Spark Hash Table Sink Vectorization: + className: VectorSparkHashTableSinkOperator + native: true keys: 0 _col2 (type: int) 1 _col0 (type: int) Execution mode: vectorized + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + inputFormatFeatureSupport: [DECIMAL_64] + featureSupportInUse: [DECIMAL_64] + inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + allNative: true + usesVectorUDFAdaptor: false + vectorized: true Local Work: Map Reduce Local Work @@ -207,181 +277,393 @@ STAGE PLANS: alias: store_sales filterExpr: (ss_item_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null) (type: boolean) Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + TableScan Vectorization: + native: true Filter Operator + Filter Vectorization: + className: VectorFilterOperator + native: true + predicateExpression: FilterExprAndExpr(children: SelectColumnIsNotNull(col 2:int), SelectColumnIsNotNull(col 0:int), SelectColumnIsNotNull(col 7:int)) predicate: (ss_item_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null) (type: boolean) Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ss_sold_date_sk (type: int), ss_item_sk (type: int), ss_store_sk (type: int), ss_sales_price (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col3 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [0, 2, 7, 13] Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) + Reduce Sink Vectorization: + className: VectorReduceSinkLongOperator + native: true + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine spark 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 Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: decimal(7,2)) Execution mode: vectorized + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + inputFormatFeatureSupport: [DECIMAL_64] + featureSupportInUse: [DECIMAL_64] + inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + allNative: true + usesVectorUDFAdaptor: false + vectorized: true Map 11 Map Operator Tree: TableScan alias: store_sales filterExpr: (ss_item_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null) (type: boolean) Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + TableScan Vectorization: + native: true Filter Operator + Filter Vectorization: + className: VectorFilterOperator + native: true + predicateExpression: FilterExprAndExpr(children: SelectColumnIsNotNull(col 2:int), SelectColumnIsNotNull(col 0:int), SelectColumnIsNotNull(col 7:int)) predicate: (ss_item_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null) (type: boolean) Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ss_sold_date_sk (type: int), ss_item_sk (type: int), ss_store_sk (type: int), ss_sales_price (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col3 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [0, 2, 7, 13] Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) + Reduce Sink Vectorization: + className: VectorReduceSinkLongOperator + native: true + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine spark 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 Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: decimal(7,2)) Execution mode: vectorized + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + inputFormatFeatureSupport: [DECIMAL_64] + featureSupportInUse: [DECIMAL_64] + inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + allNative: true + usesVectorUDFAdaptor: false + vectorized: true Map 17 Map Operator Tree: TableScan alias: date_dim filterExpr: (((d_year = 2000) or ((d_year = 1999) and (d_moy = 12)) or ((d_year = 2001) and (d_moy = 1))) and d_date_sk is not null) (type: boolean) Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + TableScan Vectorization: + native: true Filter Operator + Filter Vectorization: + className: VectorFilterOperator + native: true + predicateExpression: FilterExprAndExpr(children: FilterExprOrExpr(children: FilterLongColEqualLongScalar(col 6:int, val 2000), FilterExprAndExpr(children: FilterLongColEqualLongScalar(col 6:int, val 1999), FilterLongColEqualLongScalar(col 8:int, val 12)), FilterExprAndExpr(children: FilterLongColEqualLongScalar(col 6:int, val 2001), FilterLongColEqualLongScalar(col 8:int, val 1))), SelectColumnIsNotNull(col 0:int)) predicate: (((d_year = 2000) or ((d_year = 1999) and (d_moy = 12)) or ((d_year = 2001) and (d_moy = 1))) and d_date_sk is not null) (type: boolean) Statistics: Num rows: 73048 Data size: 81740712 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: d_date_sk (type: int), d_year (type: int), d_moy (type: int) outputColumnNames: _col0, _col1, _col2 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [0, 6, 8] Statistics: Num rows: 73048 Data size: 81740712 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) + Reduce Sink Vectorization: + className: VectorReduceSinkLongOperator + native: true + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine spark 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 Statistics: Num rows: 73048 Data size: 81740712 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: int), _col2 (type: int) Execution mode: vectorized + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + inputFormatFeatureSupport: [DECIMAL_64] + featureSupportInUse: [DECIMAL_64] + inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + allNative: true + usesVectorUDFAdaptor: false + vectorized: true Map 18 Map Operator Tree: TableScan alias: item filterExpr: (i_item_sk is not null and i_category is not null and i_brand is not null) (type: boolean) Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + TableScan Vectorization: + native: true Filter Operator + Filter Vectorization: + className: VectorFilterOperator + native: true + predicateExpression: FilterExprAndExpr(children: SelectColumnIsNotNull(col 0:int), SelectColumnIsNotNull(col 12:string), SelectColumnIsNotNull(col 8:string)) predicate: (i_brand is not null and i_category is not null and i_item_sk is not null) (type: boolean) Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: i_item_sk (type: int), i_brand (type: string), i_category (type: string) outputColumnNames: _col0, _col1, _col2 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [0, 8, 12] Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) + Reduce Sink Vectorization: + className: VectorReduceSinkLongOperator + native: true + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine spark 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 Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string), _col2 (type: string) Execution mode: vectorized + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + inputFormatFeatureSupport: [DECIMAL_64] + featureSupportInUse: [DECIMAL_64] + inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + allNative: true + usesVectorUDFAdaptor: false + vectorized: true Map 20 Map Operator Tree: TableScan alias: store_sales filterExpr: (ss_item_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null) (type: boolean) Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + TableScan Vectorization: + native: true Filter Operator + Filter Vectorization: + className: VectorFilterOperator + native: true + predicateExpression: FilterExprAndExpr(children: SelectColumnIsNotNull(col 2:int), SelectColumnIsNotNull(col 0:int), SelectColumnIsNotNull(col 7:int)) predicate: (ss_item_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null) (type: boolean) Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ss_sold_date_sk (type: int), ss_item_sk (type: int), ss_store_sk (type: int), ss_sales_price (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col3 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [0, 2, 7, 13] Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) + Reduce Sink Vectorization: + className: VectorReduceSinkLongOperator + native: true + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine spark 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 Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: decimal(7,2)) Execution mode: vectorized + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + inputFormatFeatureSupport: [DECIMAL_64] + featureSupportInUse: [DECIMAL_64] + inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + allNative: true + usesVectorUDFAdaptor: false + vectorized: true Map 25 Map Operator Tree: TableScan alias: date_dim filterExpr: (((d_year = 2000) or ((d_year = 1999) and (d_moy = 12)) or ((d_year = 2001) and (d_moy = 1))) and d_date_sk is not null) (type: boolean) Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + TableScan Vectorization: + native: true Filter Operator + Filter Vectorization: + className: VectorFilterOperator + native: true + predicateExpression: FilterExprAndExpr(children: FilterExprOrExpr(children: FilterLongColEqualLongScalar(col 6:int, val 2000), FilterExprAndExpr(children: FilterLongColEqualLongScalar(col 6:int, val 1999), FilterLongColEqualLongScalar(col 8:int, val 12)), FilterExprAndExpr(children: FilterLongColEqualLongScalar(col 6:int, val 2001), FilterLongColEqualLongScalar(col 8:int, val 1))), SelectColumnIsNotNull(col 0:int)) predicate: (((d_year = 2000) or ((d_year = 1999) and (d_moy = 12)) or ((d_year = 2001) and (d_moy = 1))) and d_date_sk is not null) (type: boolean) Statistics: Num rows: 73048 Data size: 81740712 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: d_date_sk (type: int), d_year (type: int), d_moy (type: int) outputColumnNames: _col0, _col1, _col2 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [0, 6, 8] Statistics: Num rows: 73048 Data size: 81740712 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) + Reduce Sink Vectorization: + className: VectorReduceSinkLongOperator + native: true + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine spark 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 Statistics: Num rows: 73048 Data size: 81740712 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: int), _col2 (type: int) Execution mode: vectorized + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + inputFormatFeatureSupport: [DECIMAL_64] + featureSupportInUse: [DECIMAL_64] + inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + allNative: true + usesVectorUDFAdaptor: false + vectorized: true Map 26 Map Operator Tree: TableScan alias: item filterExpr: (i_item_sk is not null and i_category is not null and i_brand is not null) (type: boolean) Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + TableScan Vectorization: + native: true Filter Operator + Filter Vectorization: + className: VectorFilterOperator + native: true + predicateExpression: FilterExprAndExpr(children: SelectColumnIsNotNull(col 0:int), SelectColumnIsNotNull(col 12:string), SelectColumnIsNotNull(col 8:string)) predicate: (i_brand is not null and i_category is not null and i_item_sk is not null) (type: boolean) Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: i_item_sk (type: int), i_brand (type: string), i_category (type: string) outputColumnNames: _col0, _col1, _col2 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [0, 8, 12] Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) + Reduce Sink Vectorization: + className: VectorReduceSinkLongOperator + native: true + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine spark 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 Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string), _col2 (type: string) Execution mode: vectorized + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + inputFormatFeatureSupport: [DECIMAL_64] + featureSupportInUse: [DECIMAL_64] + inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + allNative: true + usesVectorUDFAdaptor: false + vectorized: true Map 8 Map Operator Tree: TableScan alias: date_dim filterExpr: (((d_year = 2000) or ((d_year = 1999) and (d_moy = 12)) or ((d_year = 2001) and (d_moy = 1))) and d_date_sk is not null) (type: boolean) Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + TableScan Vectorization: + native: true Filter Operator + Filter Vectorization: + className: VectorFilterOperator + native: true + predicateExpression: FilterExprAndExpr(children: FilterExprOrExpr(children: FilterLongColEqualLongScalar(col 6:int, val 2000), FilterExprAndExpr(children: FilterLongColEqualLongScalar(col 6:int, val 1999), FilterLongColEqualLongScalar(col 8:int, val 12)), FilterExprAndExpr(children: FilterLongColEqualLongScalar(col 6:int, val 2001), FilterLongColEqualLongScalar(col 8:int, val 1))), SelectColumnIsNotNull(col 0:int)) predicate: (((d_year = 2000) or ((d_year = 1999) and (d_moy = 12)) or ((d_year = 2001) and (d_moy = 1))) and d_date_sk is not null) (type: boolean) Statistics: Num rows: 73048 Data size: 81740712 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: d_date_sk (type: int), d_year (type: int), d_moy (type: int) outputColumnNames: _col0, _col1, _col2 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [0, 6, 8] Statistics: Num rows: 73048 Data size: 81740712 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) + Reduce Sink Vectorization: + className: VectorReduceSinkLongOperator + native: true + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine spark 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 Statistics: Num rows: 73048 Data size: 81740712 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: int), _col2 (type: int) Execution mode: vectorized + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + inputFormatFeatureSupport: [DECIMAL_64] + featureSupportInUse: [DECIMAL_64] + inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + allNative: true + usesVectorUDFAdaptor: false + vectorized: true Map 9 Map Operator Tree: TableScan alias: item filterExpr: (i_item_sk is not null and i_category is not null and i_brand is not null) (type: boolean) Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + TableScan Vectorization: + native: true Filter Operator + Filter Vectorization: + className: VectorFilterOperator + native: true + predicateExpression: FilterExprAndExpr(children: SelectColumnIsNotNull(col 0:int), SelectColumnIsNotNull(col 12:string), SelectColumnIsNotNull(col 8:string)) predicate: (i_brand is not null and i_category is not null and i_item_sk is not null) (type: boolean) Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: i_item_sk (type: int), i_brand (type: string), i_category (type: string) outputColumnNames: _col0, _col1, _col2 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [0, 8, 12] Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) + Reduce Sink Vectorization: + className: VectorReduceSinkLongOperator + native: true + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine spark 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 Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string), _col2 (type: string) Execution mode: vectorized + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + inputFormatFeatureSupport: [DECIMAL_64] + featureSupportInUse: [DECIMAL_64] + inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + allNative: true + usesVectorUDFAdaptor: false + vectorized: true Reducer 12 + Reduce Vectorization: + enabled: true + enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true + notVectorizedReason: Tagging not supported + vectorized: false Reduce Operator Tree: Join Operator condition map: @@ -400,6 +682,11 @@ STAGE PLANS: Reducer 13 Local Work: Map Reduce Local Work + Reduce Vectorization: + enabled: true + enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true + notVectorizedReason: Tagging not supported + vectorized: false Reduce Operator Tree: Join Operator condition map: @@ -433,9 +720,23 @@ STAGE PLANS: value expressions: _col6 (type: decimal(17,2)) Reducer 14 Execution mode: vectorized + Reduce Vectorization: + enabled: true + enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true + allNative: false + usesVectorUDFAdaptor: false + vectorized: true Reduce Operator Tree: Group By Operator aggregations: sum(VALUE._col0) + Group By Vectorization: + aggregators: VectorUDAFSumDecimal(col 6:decimal(17,2)) -> decimal(17,2) + className: VectorGroupByOperator + groupByMode: MERGEPARTIAL + keyExpressions: col 0:int, col 1:int, col 2:string, col 3:string, col 4:string, col 5:string + native: false + vectorProcessingMode: MERGE_PARTIAL + projectedOutputColumnNums: [0] keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: string), KEY._col3 (type: string), KEY._col4 (type: string), KEY._col5 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 @@ -444,14 +745,28 @@ STAGE PLANS: key expressions: _col3 (type: string), _col2 (type: string), _col4 (type: string), _col5 (type: string), _col0 (type: int) sort order: +++++ Map-reduce partition columns: _col3 (type: string), _col2 (type: string), _col4 (type: string), _col5 (type: string), _col0 (type: int) + Reduce Sink Vectorization: + className: VectorReduceSinkMultiKeyOperator + native: true + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine spark 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 Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: int), _col6 (type: decimal(17,2)) Reducer 15 Execution mode: vectorized + Reduce Vectorization: + enabled: true + enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true + allNative: true + usesVectorUDFAdaptor: false + vectorized: true Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey4 (type: int), VALUE._col0 (type: int), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string), VALUE._col1 (type: decimal(17,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [4, 5, 1, 0, 2, 3, 6] Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: @@ -472,18 +787,38 @@ STAGE PLANS: name: avg window function: GenericUDAFAverageEvaluatorDecimal window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) + PTF Vectorization: + className: VectorPTFOperator + evaluatorClasses: [VectorPTFEvaluatorDecimalAvg] + functionInputExpressions: [col 6:decimal(17,2)] + functionNames: [avg] + native: true + orderExpressions: [col 0:string, col 1:string, col 2:string, col 3:string, col 4:int] Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: avg_window_0 (type: decimal(21,6)), _col0 (type: int), _col1 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: decimal(17,2)) outputColumnNames: avg_window_0, _col0, _col1, _col2, _col3, _col4, _col5, _col6 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [7, 4, 5, 1, 0, 2, 3, 6] Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col3 (type: string), _col2 (type: string), _col4 (type: string), _col5 (type: string), _col0 (type: int), _col1 (type: int) sort order: ++++++ Map-reduce partition columns: _col3 (type: string), _col2 (type: string), _col4 (type: string), _col5 (type: string) + Reduce Sink Vectorization: + className: VectorReduceSinkObjectHashOperator + native: true + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine spark 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 Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE value expressions: avg_window_0 (type: decimal(21,6)), _col6 (type: decimal(17,2)) Reducer 16 + Reduce Vectorization: + enabled: true + enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true + notVectorizedReason: PTF operator: More than 1 argument expression of aggregation function rank + vectorized: false Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: decimal(21,6)), KEY.reducesinkkey4 (type: int), KEY.reducesinkkey5 (type: int), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string), VALUE._col1 (type: decimal(17,2)) @@ -531,6 +866,11 @@ STAGE PLANS: Statistics: Num rows: 31943759 Data size: 2818087693 Basic stats: COMPLETE Column stats: NONE value expressions: _col4 (type: int), _col5 (type: int), _col6 (type: decimal(17,2)), _col7 (type: decimal(21,6)) Reducer 2 + Reduce Vectorization: + enabled: true + enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true + notVectorizedReason: Tagging not supported + vectorized: false Reduce Operator Tree: Join Operator condition map: @@ -547,6 +887,11 @@ STAGE PLANS: Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE value expressions: _col2 (type: int), _col3 (type: decimal(7,2)), _col5 (type: int), _col6 (type: int) Reducer 21 + Reduce Vectorization: + enabled: true + enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true + notVectorizedReason: Tagging not supported + vectorized: false Reduce Operator Tree: Join Operator condition map: @@ -565,6 +910,11 @@ STAGE PLANS: Reducer 22 Local Work: Map Reduce Local Work + Reduce Vectorization: + enabled: true + enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true + notVectorizedReason: Tagging not supported + vectorized: false Reduce Operator Tree: Join Operator condition map: @@ -598,9 +948,23 @@ STAGE PLANS: value expressions: _col6 (type: decimal(17,2)) Reducer 23 Execution mode: vectorized + Reduce Vectorization: + enabled: true + enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true + allNative: false + usesVectorUDFAdaptor: false + vectorized: true Reduce Operator Tree: Group By Operator aggregations: sum(VALUE._col0) + Group By Vectorization: + aggregators: VectorUDAFSumDecimal(col 6:decimal(17,2)) -> decimal(17,2) + className: VectorGroupByOperator + groupByMode: MERGEPARTIAL + keyExpressions: col 0:int, col 1:int, col 2:string, col 3:string, col 4:string, col 5:string + native: false + vectorProcessingMode: MERGE_PARTIAL + projectedOutputColumnNums: [0] keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: string), KEY._col3 (type: string), KEY._col4 (type: string), KEY._col5 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 @@ -609,9 +973,18 @@ STAGE PLANS: key expressions: _col3 (type: string), _col2 (type: string), _col4 (type: string), _col5 (type: string), _col0 (type: int), _col1 (type: int) sort order: ++++++ Map-reduce partition columns: _col3 (type: string), _col2 (type: string), _col4 (type: string), _col5 (type: string) + Reduce Sink Vectorization: + className: VectorReduceSinkObjectHashOperator + native: true + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine spark 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 Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE value expressions: _col6 (type: decimal(17,2)) Reducer 24 + Reduce Vectorization: + enabled: true + enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true + notVectorizedReason: PTF operator: More than 1 argument expression of aggregation function rank + vectorized: false Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey4 (type: int), KEY.reducesinkkey5 (type: int), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string), VALUE._col0 (type: decimal(17,2)) @@ -654,6 +1027,11 @@ STAGE PLANS: Reducer 3 Local Work: Map Reduce Local Work + Reduce Vectorization: + enabled: true + enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true + notVectorizedReason: Tagging not supported + vectorized: false Reduce Operator Tree: Join Operator condition map: @@ -687,9 +1065,23 @@ STAGE PLANS: value expressions: _col6 (type: decimal(17,2)) Reducer 4 Execution mode: vectorized + Reduce Vectorization: + enabled: true + enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true + allNative: false + usesVectorUDFAdaptor: false + vectorized: true Reduce Operator Tree: Group By Operator aggregations: sum(VALUE._col0) + Group By Vectorization: + aggregators: VectorUDAFSumDecimal(col 6:decimal(17,2)) -> decimal(17,2) + className: VectorGroupByOperator + groupByMode: MERGEPARTIAL + keyExpressions: col 0:int, col 1:int, col 2:string, col 3:string, col 4:string, col 5:string + native: false + vectorProcessingMode: MERGE_PARTIAL + projectedOutputColumnNums: [0] keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: string), KEY._col3 (type: string), KEY._col4 (type: string), KEY._col5 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 @@ -698,9 +1090,18 @@ STAGE PLANS: key expressions: _col3 (type: string), _col2 (type: string), _col4 (type: string), _col5 (type: string), _col0 (type: int), _col1 (type: int) sort order: ++++++ Map-reduce partition columns: _col3 (type: string), _col2 (type: string), _col4 (type: string), _col5 (type: string) + Reduce Sink Vectorization: + className: VectorReduceSinkObjectHashOperator + native: true + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine spark 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 Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE value expressions: _col6 (type: decimal(17,2)) Reducer 5 + Reduce Vectorization: + enabled: true + enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true + notVectorizedReason: PTF operator: More than 1 argument expression of aggregation function rank + vectorized: false Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey4 (type: int), KEY.reducesinkkey5 (type: int), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string), VALUE._col0 (type: decimal(17,2)) @@ -741,6 +1142,11 @@ STAGE PLANS: Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE value expressions: _col4 (type: decimal(17,2)) Reducer 6 + Reduce Vectorization: + enabled: true + enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true + notVectorizedReason: Tagging not supported + vectorized: false Reduce Operator Tree: Join Operator condition map: @@ -764,16 +1170,32 @@ STAGE PLANS: value expressions: _col0 (type: string), _col1 (type: int), _col3 (type: decimal(21,6)), _col4 (type: decimal(17,2)), _col5 (type: decimal(17,2)), _col6 (type: decimal(17,2)) Reducer 7 Execution mode: vectorized + Reduce Vectorization: + enabled: true + enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true + allNative: false + usesVectorUDFAdaptor: false + vectorized: true Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: string), VALUE._col1 (type: int), KEY.reducesinkkey1 (type: int), VALUE._col2 (type: decimal(21,6)), VALUE._col3 (type: decimal(17,2)), VALUE._col4 (type: decimal(17,2)), VALUE._col5 (type: decimal(17,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [2, 3, 1, 4, 5, 6, 7] Statistics: Num rows: 843315280 Data size: 74397518857 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 100 + Limit Vectorization: + className: VectorLimitOperator + native: true Statistics: Num rows: 100 Data size: 8800 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false + File Sink Vectorization: + className: VectorFileSinkOperator + native: false Statistics: Num rows: 100 Data size: 8800 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/470ba3e2/ql/src/test/results/clientpositive/perf/spark/query48.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/spark/query48.q.out b/ql/src/test/results/clientpositive/perf/spark/query48.q.out index 38ccff2..ba3a819 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query48.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query48.q.out @@ -1,4 +1,4 @@ -PREHOOK: query: explain +PREHOOK: query: explain vectorization expression select sum (ss_quantity) from store_sales, store, customer_demographics, customer_address, date_dim where s_store_sk = ss_store_sk @@ -63,7 +63,7 @@ select sum (ss_quantity) ) ) PREHOOK: type: QUERY -POSTHOOK: query: explain +POSTHOOK: query: explain vectorization expression select sum (ss_quantity) from store_sales, store, customer_demographics, customer_address, date_dim where s_store_sk = ss_store_sk @@ -128,6 +128,10 @@ select sum (ss_quantity) ) ) POSTHOOK: type: QUERY +PLAN VECTORIZATION: + enabled: true + enabledConditionsMet: [hive.vectorized.execution.enabled IS true] + STAGE DEPENDENCIES: Stage-2 is a root stage Stage-1 depends on stages: Stage-2 @@ -144,18 +148,40 @@ STAGE PLANS: alias: store filterExpr: s_store_sk is not null (type: boolean) Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + TableScan Vectorization: + native: true Filter Operator + Filter Vectorization: + className: VectorFilterOperator + native: true + predicateExpression: SelectColumnIsNotNull(col 0:int) predicate: s_store_sk is not null (type: boolean) Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: s_store_sk (type: int) outputColumnNames: _col0 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [0] Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE Spark HashTable Sink Operator + Spark Hash Table Sink Vectorization: + className: VectorSparkHashTableSinkOperator + native: true keys: 0 _col3 (type: int) 1 _col0 (type: int) Execution mode: vectorized + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + inputFormatFeatureSupport: [DECIMAL_64] + featureSupportInUse: [DECIMAL_64] + inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + allNative: true + usesVectorUDFAdaptor: false + vectorized: true Local Work: Map Reduce Local Work @@ -174,79 +200,176 @@ STAGE PLANS: alias: store_sales filterExpr: ((ss_sales_price BETWEEN 100 AND 150 or ss_sales_price BETWEEN 50 AND 100 or ss_sales_price BETWEEN 150 AND 200) and ss_store_sk is not null and ss_cdemo_sk is not null and ss_addr_sk is not null and ss_sold_date_sk is not null) (type: boolean) Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + TableScan Vectorization: + native: true Filter Operator + Filter Vectorization: + className: VectorFilterOperator + native: true + predicateExpression: FilterExprAndExpr(children: FilterExprOrExpr(children: FilterDecimal64ColumnBetween(col 13:decimal(7,2)/DECIMAL_64, decimal64LeftVal 10000, decimalLeftVal 10000, decimal64RightVal 15000, decimalRightVal 15000), FilterDecimal64ColumnBetween(col 13:decimal(7,2)/DECIMAL_64, decimal64LeftVal 5000, decimalLeftVal 5000, decimal64RightVal 10000, decimalRightVal 10000), FilterDecimal64ColumnBetween(col 13:decimal(7,2)/DECIMAL_64, decimal64LeftVal 15000, decimalLeftVal 15000, decimal64RightVal 20000, decimalRightVal 20000)), SelectColumnIsNotNull(col 7:int), SelectColumnIsNotNull(col 4:int), SelectColumnIsNotNull(col 6:int), SelectColumnIsNotNull(col 0:int)) predicate: ((ss_sales_price BETWEEN 100 AND 150 or ss_sales_price BETWEEN 50 AND 100 or ss_sales_price BETWEEN 150 AND 200) and ss_addr_sk is not null and ss_cdemo_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null) (type: boolean) Statistics: Num rows: 191998545 Data size: 16938167362 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ss_sold_date_sk (type: int), ss_cdemo_sk (type: int), ss_addr_sk (type: int), ss_store_sk (type: int), ss_quantity (type: int), ss_net_profit (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col6 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [0, 4, 6, 7, 10, 22] Statistics: Num rows: 191998545 Data size: 16938167362 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) + Reduce Sink Vectorization: + className: VectorReduceSinkLongOperator + native: true + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine spark 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 Statistics: Num rows: 191998545 Data size: 16938167362 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: int), _col6 (type: decimal(7,2)) Execution mode: vectorized + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + inputFormatFeatureSupport: [DECIMAL_64] + featureSupportInUse: [DECIMAL_64] + inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + allNative: true + usesVectorUDFAdaptor: false + vectorized: true Map 6 Map Operator Tree: TableScan alias: date_dim filterExpr: ((d_year = 1998) and d_date_sk is not null) (type: boolean) Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + TableScan Vectorization: + native: true Filter Operator + Filter Vectorization: + className: VectorFilterOperator + native: true + predicateExpression: FilterExprAndExpr(children: FilterLongColEqualLongScalar(col 6:int, val 1998), SelectColumnIsNotNull(col 0:int)) predicate: ((d_year = 1998) and d_date_sk is not null) (type: boolean) Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: d_date_sk (type: int) outputColumnNames: _col0 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [0] Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) + Reduce Sink Vectorization: + className: VectorReduceSinkLongOperator + native: true + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine spark 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 Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + inputFormatFeatureSupport: [DECIMAL_64] + featureSupportInUse: [DECIMAL_64] + inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + allNative: true + usesVectorUDFAdaptor: false + vectorized: true Map 7 Map Operator Tree: TableScan alias: customer_demographics filterExpr: ((cd_marital_status = 'M') and (cd_education_status = '4 yr Degree') and cd_demo_sk is not null) (type: boolean) Statistics: Num rows: 1861800 Data size: 717186159 Basic stats: COMPLETE Column stats: NONE + TableScan Vectorization: + native: true Filter Operator + Filter Vectorization: + className: VectorFilterOperator + native: true + predicateExpression: FilterExprAndExpr(children: FilterStringGroupColEqualStringScalar(col 2:string, val M), FilterStringGroupColEqualStringScalar(col 3:string, val 4 yr Degree), SelectColumnIsNotNull(col 0:int)) predicate: ((cd_education_status = '4 yr Degree') and (cd_marital_status = 'M') and cd_demo_sk is not null) (type: boolean) Statistics: Num rows: 465450 Data size: 179296539 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cd_demo_sk (type: int) outputColumnNames: _col0 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [0] Statistics: Num rows: 465450 Data size: 179296539 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) + Reduce Sink Vectorization: + className: VectorReduceSinkLongOperator + native: true + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine spark 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 Statistics: Num rows: 465450 Data size: 179296539 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + inputFormatFeatureSupport: [DECIMAL_64] + featureSupportInUse: [DECIMAL_64] + inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + allNative: true + usesVectorUDFAdaptor: false + vectorized: true Map 8 Map Operator Tree: TableScan alias: customer_address filterExpr: ((ca_country = 'United States') and ca_address_sk is not null) (type: boolean) Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + TableScan Vectorization: + native: true Filter Operator + Filter Vectorization: + className: VectorFilterOperator + native: true + predicateExpression: FilterExprAndExpr(children: FilterStringGroupColEqualStringScalar(col 10:string, val United States), SelectColumnIsNotNull(col 0:int)) predicate: ((ca_country = 'United States') and ca_address_sk is not null) (type: boolean) Statistics: Num rows: 20000000 Data size: 20297597642 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ca_address_sk (type: int), ca_state (type: string) outputColumnNames: _col0, _col1 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [0, 8] Statistics: Num rows: 20000000 Data size: 20297597642 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) + Reduce Sink Vectorization: + className: VectorReduceSinkLongOperator + native: true + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine spark 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 Statistics: Num rows: 20000000 Data size: 20297597642 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Execution mode: vectorized + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + inputFormatFeatureSupport: [DECIMAL_64] + featureSupportInUse: [DECIMAL_64] + inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + allNative: true + usesVectorUDFAdaptor: false + vectorized: true Reducer 2 + Reduce Vectorization: + enabled: true + enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true + notVectorizedReason: Tagging not supported + vectorized: false Reduce Operator Tree: Join Operator condition map: @@ -263,6 +386,11 @@ STAGE PLANS: Statistics: Num rows: 211198404 Data size: 18631984502 Basic stats: COMPLETE Column stats: NONE value expressions: _col2 (type: int), _col3 (type: int), _col4 (type: int), _col6 (type: decimal(7,2)) Reducer 3 + Reduce Vectorization: + enabled: true + enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true + notVectorizedReason: Tagging not supported + vectorized: false Reduce Operator Tree: Join Operator condition map: @@ -281,6 +409,11 @@ STAGE PLANS: Reducer 4 Local Work: Map Reduce Local Work + Reduce Vectorization: + enabled: true + enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true + notVectorizedReason: Tagging not supported + vectorized: false Reduce Operator Tree: Join Operator condition map: @@ -314,14 +447,30 @@ STAGE PLANS: value expressions: _col0 (type: bigint) Reducer 5 Execution mode: vectorized + Reduce Vectorization: + enabled: true + enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true + allNative: false + usesVectorUDFAdaptor: false + vectorized: true Reduce Operator Tree: Group By Operator aggregations: sum(VALUE._col0) + Group By Vectorization: + aggregators: VectorUDAFSumLong(col 0:bigint) -> bigint + className: VectorGroupByOperator + groupByMode: MERGEPARTIAL + native: false + vectorProcessingMode: GLOBAL + projectedOutputColumnNums: [0] mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false + File Sink Vectorization: + className: VectorFileSinkOperator + native: false Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat
