http://git-wip-us.apache.org/repos/asf/hive/blob/142367d9/ql/src/test/results/clientpositive/perf/spark/query34.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/spark/query34.q.out b/ql/src/test/results/clientpositive/perf/spark/query34.q.out index 371d94f..88279a3 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query34.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query34.q.out @@ -1,4 +1,4 @@ -PREHOOK: query: explain vectorization expression +PREHOOK: query: explain select c_last_name ,c_first_name ,c_salutation @@ -28,7 +28,7 @@ select c_last_name and cnt between 15 and 20 order by c_last_name,c_first_name,c_salutation,c_preferred_cust_flag desc PREHOOK: type: QUERY -POSTHOOK: query: explain vectorization expression +POSTHOOK: query: explain select c_last_name ,c_first_name ,c_salutation @@ -58,10 +58,6 @@ select c_last_name and cnt between 15 and 20 order by c_last_name,c_first_name,c_salutation,c_preferred_cust_flag desc 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 @@ -78,40 +74,18 @@ STAGE PLANS: alias: household_demographics filterExpr: ((hd_buy_potential) IN ('>10000', 'unknown') and (hd_vehicle_count > 0) and CASE WHEN ((hd_vehicle_count > 0)) THEN (((UDFToDouble(hd_dep_count) / UDFToDouble(hd_vehicle_count)) > 1.2D)) ELSE (null) END and hd_demo_sk is not null) (type: boolean) Statistics: Num rows: 7200 Data size: 770400 Basic stats: COMPLETE Column stats: NONE - TableScan Vectorization: - native: true Filter Operator - Filter Vectorization: - className: VectorFilterOperator - native: true - predicateExpression: FilterExprAndExpr(children: FilterStringColumnInList(col 2, values >10000, unknown), FilterLongColGreaterLongScalar(col 4:int, val 0), SelectColumnIsTrue(col 11:boolean)(children: IfExprCondExprNull(col 6:boolean, col 10:boolean, null)(children: LongColGreaterLongScalar(col 4:int, val 0) -> 6:boolean, DoubleColGreaterDoubleScalar(col 9:double, val 1.2)(children: DoubleColDivideDoubleColumn(col 7:double, col 8:double)(children: CastLongToDouble(col 3:int) -> 7:double, CastLongToDouble(col 4:int) -> 8:double) -> 9:double) -> 10:boolean) -> 11:boolean), SelectColumnIsNotNull(col 0:int)) predicate: ((hd_buy_potential) IN ('>10000', 'unknown') and (hd_vehicle_count > 0) and CASE WHEN ((hd_vehicle_count > 0)) THEN (((UDFToDouble(hd_dep_count) / UDFToDouble(hd_vehicle_count)) > 1.2D)) ELSE (null) END and hd_demo_sk is not null) (type: boolean) Statistics: Num rows: 1200 Data size: 128400 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: hd_demo_sk (type: int) outputColumnNames: _col0 - Select Vectorization: - className: VectorSelectOperator - native: true - projectedOutputColumnNums: [0] Statistics: Num rows: 1200 Data size: 128400 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 Map 9 @@ -120,40 +94,18 @@ STAGE PLANS: alias: store filterExpr: ((s_county) IN ('Mobile County', 'Maverick County', 'Huron County', 'Kittitas County', 'Fairfield County', 'Jackson County', 'Barrow County', 'Pennington County') and 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: FilterExprAndExpr(children: FilterStringColumnInList(col 23, values Mobile County, Maverick County, Huron County, Kittitas County, Fairfield County, Jackson County, Barrow County, Pennington County), SelectColumnIsNotNull(col 0:int)) predicate: ((s_county) IN ('Mobile County', 'Maverick County', 'Huron County', 'Kittitas County', 'Fairfield County', 'Jackson County', 'Barrow County', 'Pennington County') 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) 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 @@ -172,134 +124,60 @@ STAGE PLANS: alias: customer filterExpr: c_customer_sk is not null (type: boolean) Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE - TableScan Vectorization: - native: true Filter Operator - Filter Vectorization: - className: VectorFilterOperator - native: true - predicateExpression: SelectColumnIsNotNull(col 0:int) predicate: c_customer_sk is not null (type: boolean) Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: c_customer_sk (type: int), c_salutation (type: string), c_first_name (type: string), c_last_name (type: string), c_preferred_cust_flag (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Select Vectorization: - className: VectorSelectOperator - native: true - projectedOutputColumnNums: [0, 7, 8, 9, 10] Statistics: Num rows: 80000000 Data size: 68801615852 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: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (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 4 Map Operator Tree: TableScan alias: store_sales filterExpr: (ss_sold_date_sk is not null and ss_store_sk is not null and ss_hdemo_sk is not null and ss_customer_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 0:int), SelectColumnIsNotNull(col 7:int), SelectColumnIsNotNull(col 5:int), SelectColumnIsNotNull(col 3:int)) predicate: (ss_customer_sk is not null and ss_hdemo_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_customer_sk (type: int), ss_hdemo_sk (type: int), ss_store_sk (type: int), ss_ticket_number (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Select Vectorization: - className: VectorSelectOperator - native: true - projectedOutputColumnNums: [0, 3, 5, 7, 9] 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: int), _col4 (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 7 Map Operator Tree: TableScan alias: date_dim filterExpr: ((d_year) IN (2000, 2001, 2002) and (d_dom BETWEEN 1 AND 3 or d_dom BETWEEN 25 AND 28) 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: FilterLongColumnInList(col 6:int, values [2000, 2001, 2002]), FilterExprOrExpr(children: FilterLongColumnBetween(col 9:int, left 1, right 3), FilterLongColumnBetween(col 9:int, left 25, right 28)), SelectColumnIsNotNull(col 0:int)) predicate: ((d_dom BETWEEN 1 AND 3 or d_dom BETWEEN 25 AND 28) and (d_year) IN (2000, 2001, 2002) and d_date_sk is not null) (type: boolean) Statistics: Num rows: 16232 Data size: 18163608 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: 16232 Data size: 18163608 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: 16232 Data size: 18163608 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 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: @@ -320,26 +198,13 @@ STAGE PLANS: value expressions: _col4 (type: int), _col5 (type: bigint) Reducer 3 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: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string), VALUE._col0 (type: int), VALUE._col1 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Select Vectorization: - className: VectorSelectOperator - native: true - projectedOutputColumnNums: [0, 1, 2, 3, 4, 5] Statistics: Num rows: 88000001 Data size: 75681779077 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - File Sink Vectorization: - className: VectorFileSinkOperator - native: false Statistics: Num rows: 88000001 Data size: 75681779077 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -348,11 +213,6 @@ STAGE PLANS: Reducer 5 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: @@ -396,23 +256,9 @@ STAGE PLANS: value expressions: _col2 (type: bigint) Reducer 6 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: count(VALUE._col0) - Group By Vectorization: - aggregators: VectorUDAFCountMerge(col 2:bigint) -> bigint - className: VectorGroupByOperator - groupByMode: MERGEPARTIAL - keyExpressions: col 0:int, col 1:int - native: false - vectorProcessingMode: MERGE_PARTIAL - projectedOutputColumnNums: [0] keys: KEY._col0 (type: int), KEY._col1 (type: int) mode: mergepartial outputColumnNames: _col0, _col1, _col2 @@ -420,26 +266,14 @@ STAGE PLANS: Select Operator expressions: _col1 (type: int), _col0 (type: int), _col2 (type: bigint) outputColumnNames: _col0, _col1, _col2 - Select Vectorization: - className: VectorSelectOperator - native: true - projectedOutputColumnNums: [1, 0, 2] Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE Filter Operator - Filter Vectorization: - className: VectorFilterOperator - native: true - predicateExpression: FilterLongColumnBetween(col 2:bigint, left 15, right 20) predicate: _col2 BETWEEN 15 AND 20 (type: boolean) Statistics: Num rows: 42591679 Data size: 3757450287 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (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: 42591679 Data size: 3757450287 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int), _col2 (type: bigint)
http://git-wip-us.apache.org/repos/asf/hive/blob/142367d9/ql/src/test/results/clientpositive/perf/spark/query35.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/spark/query35.q.out b/ql/src/test/results/clientpositive/perf/spark/query35.q.out index 3ab2559..6d1ea9b 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query35.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query35.q.out @@ -1,4 +1,4 @@ -PREHOOK: query: explain vectorization expression +PREHOOK: query: explain select ca_state, cd_gender, @@ -54,7 +54,7 @@ select cd_dep_college_count limit 100 PREHOOK: type: QUERY -POSTHOOK: query: explain vectorization expression +POSTHOOK: query: explain select ca_state, cd_gender, @@ -110,10 +110,6 @@ select cd_dep_college_count limit 100 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 @@ -140,390 +136,178 @@ STAGE PLANS: alias: c filterExpr: (c_current_addr_sk is not null and c_current_cdemo_sk is not null and c_customer_sk is not null) (type: boolean) Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE - TableScan Vectorization: - native: true Filter Operator - Filter Vectorization: - className: VectorFilterOperator - native: true - predicateExpression: FilterExprAndExpr(children: SelectColumnIsNotNull(col 4:int), SelectColumnIsNotNull(col 2:int), SelectColumnIsNotNull(col 0:int)) predicate: (c_current_addr_sk is not null and c_current_cdemo_sk is not null and c_customer_sk is not null) (type: boolean) Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: c_customer_sk (type: int), c_current_cdemo_sk (type: int), c_current_addr_sk (type: int) outputColumnNames: _col0, _col1, _col2 - Select Vectorization: - className: VectorSelectOperator - native: true - projectedOutputColumnNums: [0, 2, 4] Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col2 (type: int) sort order: + Map-reduce partition columns: _col2 (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: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int), _col1 (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 11 Map Operator Tree: TableScan alias: date_dim filterExpr: ((d_year = 1999) and (d_qoy < 4) 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 1999), FilterLongColLessLongScalar(col 10:int, val 4), SelectColumnIsNotNull(col 0:int)) predicate: ((d_qoy < 4) and (d_year = 1999) and d_date_sk is not null) (type: boolean) Statistics: Num rows: 12174 Data size: 13622706 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: 12174 Data size: 13622706 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: 12174 Data size: 13622706 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 12 Map Operator Tree: TableScan alias: web_sales filterExpr: (ws_bill_customer_sk is not null and ws_sold_date_sk is not null) (type: boolean) Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE - TableScan Vectorization: - native: true Filter Operator - Filter Vectorization: - className: VectorFilterOperator - native: true - predicateExpression: FilterExprAndExpr(children: SelectColumnIsNotNull(col 4:int), SelectColumnIsNotNull(col 0:int)) predicate: (ws_bill_customer_sk is not null and ws_sold_date_sk is not null) (type: boolean) Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ws_sold_date_sk (type: int), ws_bill_customer_sk (type: int) outputColumnNames: _col0, _col1 - Select Vectorization: - className: VectorSelectOperator - native: true - projectedOutputColumnNums: [0, 4] Statistics: Num rows: 144002668 Data size: 19580198212 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: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (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 15 Map Operator Tree: TableScan alias: date_dim filterExpr: ((d_year = 1999) and (d_qoy < 4) 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 1999), FilterLongColLessLongScalar(col 10:int, val 4), SelectColumnIsNotNull(col 0:int)) predicate: ((d_qoy < 4) and (d_year = 1999) and d_date_sk is not null) (type: boolean) Statistics: Num rows: 12174 Data size: 13622706 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: 12174 Data size: 13622706 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: 12174 Data size: 13622706 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 16 Map Operator Tree: TableScan alias: catalog_sales filterExpr: (cs_ship_customer_sk is not null and cs_sold_date_sk is not null) (type: boolean) Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE - TableScan Vectorization: - native: true Filter Operator - Filter Vectorization: - className: VectorFilterOperator - native: true - predicateExpression: FilterExprAndExpr(children: SelectColumnIsNotNull(col 7:int), SelectColumnIsNotNull(col 0:int)) predicate: (cs_ship_customer_sk is not null and cs_sold_date_sk is not null) (type: boolean) Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cs_sold_date_sk (type: int), cs_ship_customer_sk (type: int) outputColumnNames: _col0, _col1 - Select Vectorization: - className: VectorSelectOperator - native: true - projectedOutputColumnNums: [0, 7] Statistics: Num rows: 287989836 Data size: 38999608952 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: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (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 19 Map Operator Tree: TableScan alias: date_dim filterExpr: ((d_year = 1999) and (d_qoy < 4) 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 1999), FilterLongColLessLongScalar(col 10:int, val 4), SelectColumnIsNotNull(col 0:int)) predicate: ((d_qoy < 4) and (d_year = 1999) and d_date_sk is not null) (type: boolean) Statistics: Num rows: 12174 Data size: 13622706 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: 12174 Data size: 13622706 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: 12174 Data size: 13622706 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: ca filterExpr: 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: SelectColumnIsNotNull(col 0:int) predicate: ca_address_sk is not null (type: boolean) Statistics: Num rows: 40000000 Data size: 40595195284 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: 40000000 Data size: 40595195284 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: 40000000 Data size: 40595195284 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 Map 8 Map Operator Tree: TableScan alias: customer_demographics filterExpr: 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: SelectColumnIsNotNull(col 0:int) predicate: cd_demo_sk is not null (type: boolean) Statistics: Num rows: 1861800 Data size: 717186159 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cd_demo_sk (type: int), cd_gender (type: string), cd_marital_status (type: string), cd_dep_count (type: int), cd_dep_employed_count (type: int), cd_dep_college_count (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Select Vectorization: - className: VectorSelectOperator - native: true - projectedOutputColumnNums: [0, 1, 2, 6, 7, 8] Statistics: Num rows: 1861800 Data size: 717186159 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: 1861800 Data size: 717186159 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: int), _col4 (type: int), _col5 (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: store_sales filterExpr: (ss_customer_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: SelectColumnIsNotNull(col 3:int), SelectColumnIsNotNull(col 0:int)) predicate: (ss_customer_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 Select Operator expressions: ss_sold_date_sk (type: int), ss_customer_sk (type: int) outputColumnNames: _col0, _col1 - Select Vectorization: - className: VectorSelectOperator - native: true - projectedOutputColumnNums: [0, 3] 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) 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 10 - 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: @@ -548,11 +332,6 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE Reducer 13 - 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: @@ -574,21 +353,8 @@ STAGE PLANS: Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE 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 - Group By Vectorization: - className: VectorGroupByOperator - groupByMode: MERGEPARTIAL - keyExpressions: col 0:int - native: false - vectorProcessingMode: MERGE_PARTIAL - projectedOutputColumnNums: [] keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0 @@ -596,28 +362,14 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), true (type: boolean) outputColumnNames: _col0, _col1 - Select Vectorization: - className: VectorSelectOperator - native: true - projectedOutputColumnNums: [0, 1] - selectExpressions: ConstantVectorExpression(val 1) -> 1:boolean Statistics: Num rows: 79201469 Data size: 10769109250 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: 79201469 Data size: 10769109250 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: boolean) Reducer 17 - 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: @@ -639,21 +391,8 @@ STAGE PLANS: Statistics: Num rows: 316788826 Data size: 42899570777 Basic stats: COMPLETE Column stats: NONE Reducer 18 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 - Group By Vectorization: - className: VectorGroupByOperator - groupByMode: MERGEPARTIAL - keyExpressions: col 0:int - native: false - vectorProcessingMode: MERGE_PARTIAL - projectedOutputColumnNums: [] keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0 @@ -661,28 +400,14 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), true (type: boolean) outputColumnNames: _col0, _col1 - Select Vectorization: - className: VectorSelectOperator - native: true - projectedOutputColumnNums: [0, 1] - selectExpressions: ConstantVectorExpression(val 1) -> 1:boolean Statistics: Num rows: 158394413 Data size: 21449785388 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: 158394413 Data size: 21449785388 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: boolean) 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: @@ -699,11 +424,6 @@ STAGE PLANS: Statistics: Num rows: 88000001 Data size: 75681779077 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int), _col4 (type: string) 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: @@ -720,11 +440,6 @@ STAGE PLANS: Statistics: Num rows: 96800003 Data size: 83249958789 Basic stats: COMPLETE Column stats: NONE value expressions: _col4 (type: string), _col6 (type: string), _col7 (type: string), _col8 (type: int), _col9 (type: int), _col10 (type: int) Reducer 4 - 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: @@ -760,23 +475,9 @@ STAGE PLANS: value expressions: _col6 (type: bigint), _col7 (type: bigint), _col8 (type: bigint), _col9 (type: int), _col10 (type: bigint), _col11 (type: bigint), _col12 (type: int), _col13 (type: bigint), _col14 (type: bigint), _col15 (type: int) 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: count(VALUE._col0), sum(VALUE._col1), count(VALUE._col2), max(VALUE._col3), sum(VALUE._col4), count(VALUE._col5), max(VALUE._col6), sum(VALUE._col7), count(VALUE._col8), max(VALUE._col9) - Group By Vectorization: - aggregators: VectorUDAFCountMerge(col 6:bigint) -> bigint, VectorUDAFSumLong(col 7:bigint) -> bigint, VectorUDAFCountMerge(col 8:bigint) -> bigint, VectorUDAFMaxLong(col 9:int) -> int, VectorUDAFSumLong(col 10:bigint) -> bigint, VectorUDAFCountMerge(col 11:bigint) -> bigint, VectorUDAFMaxLong(col 12:int) -> int, VectorUDAFSumLong(col 13:bigint) -> bigint, VectorUDAFCountMerge(col 14:bigint) -> bigint, VectorUDAFMaxLong(col 15:int) -> int - className: VectorGroupByOperator - groupByMode: MERGEPARTIAL - keyExpressions: col 0:string, col 1:string, col 2:string, col 3:int, col 4:int, col 5:int - native: false - vectorProcessingMode: MERGE_PARTIAL - projectedOutputColumnNums: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9] keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string), KEY._col3 (type: int), KEY._col4 (type: int), KEY._col5 (type: int) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15 @@ -784,50 +485,25 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col6 (type: bigint), (_col7 / _col8) (type: double), _col9 (type: int), _col7 (type: bigint), _col4 (type: int), (_col10 / _col11) (type: double), _col12 (type: int), _col10 (type: bigint), _col5 (type: int), (_col13 / _col14) (type: double), _col15 (type: int), _col13 (type: bigint), _col3 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col9, _col10, _col11, _col12, _col14, _col15, _col16, _col17 - Select Vectorization: - className: VectorSelectOperator - native: true - projectedOutputColumnNums: [0, 1, 2, 6, 16, 9, 7, 4, 17, 12, 10, 5, 18, 15, 13, 3] - selectExpressions: LongColDivideLongColumn(col 7:bigint, col 8:bigint) -> 16:double, LongColDivideLongColumn(col 10:bigint, col 11:bigint) -> 17:double, LongColDivideLongColumn(col 13:bigint, col 14:bigint) -> 18:double Statistics: Num rows: 1045432122 Data size: 92228325287 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col17 (type: int), _col7 (type: int), _col12 (type: int) sort order: ++++++ - 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: 1045432122 Data size: 92228325287 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.1 value expressions: _col3 (type: bigint), _col4 (type: double), _col5 (type: int), _col6 (type: bigint), _col9 (type: double), _col10 (type: int), _col11 (type: bigint), _col14 (type: double), _col15 (type: int), _col16 (type: bigint) Reducer 6 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: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), VALUE._col0 (type: bigint), VALUE._col1 (type: double), VALUE._col2 (type: int), VALUE._col3 (type: bigint), KEY.reducesinkkey4 (type: int), VALUE._col0 (type: bigint), VALUE._col4 (type: double), VALUE._col5 (type: int), VALUE._col6 (type: bigint), KEY.reducesinkkey5 (type: int), VALUE._col0 (type: bigint), VALUE._col7 (type: double), VALUE._col8 (type: int), VALUE._col9 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16 - Select Vectorization: - className: VectorSelectOperator - native: true - projectedOutputColumnNums: [0, 1, 2, 6, 7, 8, 9, 4, 6, 10, 11, 12, 5, 6, 13, 14, 15] Statistics: Num rows: 1045432122 Data size: 92228325287 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/142367d9/ql/src/test/results/clientpositive/perf/spark/query36.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/spark/query36.q.out b/ql/src/test/results/clientpositive/perf/spark/query36.q.out index 5ff3d9d..694e579 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query36.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query36.q.out @@ -1,4 +1,4 @@ -PREHOOK: query: explain vectorization expression +PREHOOK: query: explain select sum(ss_net_profit)/sum(ss_ext_sales_price) as gross_margin ,i_category @@ -27,7 +27,7 @@ select ,rank_within_parent limit 100 PREHOOK: type: QUERY -POSTHOOK: query: explain vectorization expression +POSTHOOK: query: explain select sum(ss_net_profit)/sum(ss_ext_sales_price) as gross_margin ,i_category @@ -56,10 +56,6 @@ select ,rank_within_parent 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-1 depends on stages: Stage-2 @@ -76,40 +72,18 @@ STAGE PLANS: alias: store filterExpr: ((s_state) IN ('SD', 'FL', 'MI', 'LA', 'MO', 'SC', 'AL', 'GA') and 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: FilterExprAndExpr(children: FilterStringColumnInList(col 24, values SD, FL, MI, LA, MO, SC, AL, GA), SelectColumnIsNotNull(col 0:int)) predicate: ((s_state) IN ('SD', 'FL', 'MI', 'LA', 'MO', 'SC', 'AL', 'GA') 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) 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 _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 @@ -129,136 +103,62 @@ STAGE PLANS: alias: store_sales filterExpr: (ss_sold_date_sk is not null and ss_item_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 0:int), SelectColumnIsNotNull(col 2: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_ext_sales_price (type: decimal(7,2)), ss_net_profit (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Select Vectorization: - className: VectorSelectOperator - native: true - projectedOutputColumnNums: [0, 2, 7, 15, 22] 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)), _col4 (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 7 Map Operator Tree: TableScan alias: d1 filterExpr: ((d_year = 1999) 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 1999), SelectColumnIsNotNull(col 0:int)) predicate: ((d_year = 1999) 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 9 Map Operator Tree: TableScan alias: item filterExpr: i_item_sk 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: SelectColumnIsNotNull(col 0:int) predicate: 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_class (type: string), i_category (type: string) outputColumnNames: _col0, _col1, _col2 - Select Vectorization: - className: VectorSelectOperator - native: true - projectedOutputColumnNums: [0, 10, 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 2 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: @@ -285,11 +185,6 @@ STAGE PLANS: Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE value expressions: _col3 (type: decimal(7,2)), _col4 (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: @@ -317,23 +212,9 @@ STAGE PLANS: value expressions: _col3 (type: decimal(17,2)), _col4 (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: true - vectorized: true Reduce Operator Tree: Group By Operator aggregations: sum(VALUE._col0), sum(VALUE._col1) - Group By Vectorization: - aggregators: VectorUDAFSumDecimal(col 3:decimal(17,2)) -> decimal(17,2), VectorUDAFSumDecimal(col 4:decimal(17,2)) -> decimal(17,2) - className: VectorGroupByOperator - groupByMode: MERGEPARTIAL - keyExpressions: col 0:string, col 1:string, col 2:bigint - native: false - vectorProcessingMode: MERGE_PARTIAL - projectedOutputColumnNums: [0, 1] keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4 @@ -341,38 +222,19 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), _col3 (type: decimal(17,2)), _col4 (type: decimal(17,2)), _col2 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Select Vectorization: - className: VectorSelectOperator - native: true - projectedOutputColumnNums: [0, 1, 3, 4, 2] Statistics: Num rows: 1149975358 Data size: 101451159969 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: (grouping(_col4, 1) + grouping(_col4, 0)) (type: bigint), CASE WHEN ((grouping(_col4, 0) = 0)) THEN (_col0) ELSE (CAST( null AS STRING)) END (type: string), (_col2 / _col3) (type: decimal(37,20)) sort order: +++ Map-reduce partition columns: (grouping(_col4, 1) + grouping(_col4, 0)) (type: bigint), CASE WHEN ((grouping(_col4, 0) = 0)) THEN (_col0) ELSE (CAST( null AS STRING)) END (type: string) - Reduce Sink Vectorization: - className: VectorReduceSinkObjectHashOperator - keyExpressions: LongColAddLongColumn(col 5:bigint, col 6:bigint)(children: VectorUDFAdaptor(grouping(_col4, 1)) -> 5:bigint, VectorUDFAdaptor(grouping(_col4, 0)) -> 6:bigint) -> 7:bigint, IfExprColumnNull(col 6:boolean, col 0:string, null)(children: LongColEqualLongScalar(col 5:bigint, val 0)(children: VectorUDFAdaptor(grouping(_col4, 0)) -> 5:bigint) -> 6:boolean, col 0:string) -> 8:string, DecimalColDivideDecimalColumn(col 3:decimal(17,2), col 4:decimal(17,2)) -> 9:decimal(37,20) - 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: 1149975358 Data size: 101451159969 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: decimal(17,2)), _col3 (type: decimal(17,2)), _col4 (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: true - usesVectorUDFAdaptor: true - vectorized: true Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: string), VALUE._col1 (type: string), VALUE._col2 (type: decimal(17,2)), VALUE._col3 (type: decimal(17,2)), VALUE._col4 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Select Vectorization: - className: VectorSelectOperator - native: true - projectedOutputColumnNums: [3, 4, 5, 6, 7] Statistics: Num rows: 1149975358 Data size: 101451159969 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: @@ -394,62 +256,29 @@ STAGE PLANS: window function: GenericUDAFRankEvaluator window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true - PTF Vectorization: - className: VectorPTFOperator - evaluatorClasses: [VectorPTFEvaluatorRank] - functionInputExpressions: [DecimalColDivideDecimalColumn(col 5:decimal(17,2), col 6:decimal(17,2)) -> 14:decimal(37,20)] - functionNames: [rank] - native: true - orderExpressions: [DecimalColDivideDecimalColumn(col 5:decimal(17,2), col 6:decimal(17,2)) -> 13:decimal(37,20)] - partitionExpressions: [LongColAddLongColumn(col 9:bigint, col 10:bigint)(children: VectorUDFAdaptor(grouping(_col4, 1)) -> 9:bigint, VectorUDFAdaptor(grouping(_col4, 0)) -> 10:bigint) -> 11:bigint, IfExprColumnNull(col 10:boolean, col 3:string, null)(children: LongColEqualLongScalar(col 9:bigint, val 0)(children: VectorUDFAdaptor(grouping(_col4, 0)) -> 9:bigint) -> 10:boolean, col 3:string) -> 12:string] Statistics: Num rows: 1149975358 Data size: 101451159969 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: (_col2 / _col3) (type: decimal(37,20)), _col0 (type: string), _col1 (type: string), (grouping(_col4, 1) + grouping(_col4, 0)) (type: bigint), rank_window_0 (type: int), CASE WHEN (((grouping(_col4, 1) + grouping(_col4, 0)) = 0)) THEN (_col0) ELSE (null) END (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Select Vectorization: - className: VectorSelectOperator - native: true - projectedOutputColumnNums: [15, 3, 4, 17, 8, 19] - selectExpressions: DecimalColDivideDecimalColumn(col 5:decimal(17,2), col 6:decimal(17,2)) -> 15:decimal(37,20), LongColAddLongColumn(col 9:bigint, col 16:bigint)(children: VectorUDFAdaptor(grouping(_col4, 1)) -> 9:bigint, VectorUDFAdaptor(grouping(_col4, 0)) -> 16:bigint) -> 17:bigint, IfExprColumnNull(col 9:boolean, col 3:string, null)(children: LongColEqualLongScalar(col 18:bigint, val 0)(children: LongColAddLongColumn(col 9:bigint, col 16:bigint)(children: VectorUDFAdaptor(grouping(_col4, 1)) -> 9:bigint, VectorUDFAdaptor(grouping(_col4, 0)) -> 16:bigint) -> 18:bigint) -> 9:boolean, col 3:string) -> 19:string Statistics: Num rows: 1149975358 Data size: 101451159969 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col3 (type: bigint), _col5 (type: string), _col4 (type: int) sort order: -++ - 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: 1149975358 Data size: 101451159969 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.1 value expressions: _col0 (type: decimal(37,20)), _col1 (type: string), _col2 (type: string) Reducer 6 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: decimal(37,20)), VALUE._col1 (type: string), VALUE._col2 (type: string), KEY.reducesinkkey0 (type: bigint), KEY.reducesinkkey2 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Select Vectorization: - className: VectorSelectOperator - native: true - projectedOutputColumnNums: [3, 4, 5, 0, 2] Statistics: Num rows: 1149975358 Data size: 101451159969 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