http://git-wip-us.apache.org/repos/asf/hive/blob/aed21d0b/ql/src/test/results/clientpositive/llap/vectorized_dynamic_partition_pruning.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/vectorized_dynamic_partition_pruning.q.out b/ql/src/test/results/clientpositive/llap/vectorized_dynamic_partition_pruning.q.out index c2e1dfd..76c8404 100644 --- a/ql/src/test/results/clientpositive/llap/vectorized_dynamic_partition_pruning.q.out +++ b/ql/src/test/results/clientpositive/llap/vectorized_dynamic_partition_pruning.q.out @@ -34,14 +34,10 @@ POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 #### A masked pattern was here #### 11 12 -PREHOOK: query: EXPLAIN VECTORIZATION create table srcpart_date as select ds as ds, ds as `date` from srcpart group by ds +PREHOOK: query: EXPLAIN create table srcpart_date as select ds as ds, ds as `date` from srcpart group by ds PREHOOK: type: CREATETABLE_AS_SELECT -POSTHOOK: query: EXPLAIN VECTORIZATION create table srcpart_date as select ds as ds, ds as `date` from srcpart group by ds +POSTHOOK: query: EXPLAIN create table srcpart_date as select ds as ds, ds as `date` from srcpart group by ds POSTHOOK: type: CREATETABLE_AS_SELECT -PLAN VECTORIZATION: - enabled: true - enabledConditionsMet: [hive.vectorized.execution.enabled IS true] - STAGE DEPENDENCIES: Stage-1 is a root stage Stage-2 depends on stages: Stage-1 @@ -78,19 +74,8 @@ STAGE PLANS: Statistics: Num rows: 2 Data size: 368 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs - Map Vectorization: - enabled: false - enabledConditionsNotMet: hive.vectorized.use.vector.serde.deserialize IS false - inputFileFormats: org.apache.hadoop.mapred.TextInputFormat Reducer 2 Execution mode: vectorized, llap - Reduce Vectorization: - enabled: true - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true - groupByVectorOutput: true - allNative: false - usesVectorUDFAdaptor: false - vectorized: true Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string) @@ -214,15 +199,11 @@ POSTHOOK: Output: default@srcpart_double_hour POSTHOOK: Lineage: srcpart_double_hour.hour SIMPLE [(srcpart)srcpart.FieldSchema(name:hr, type:string, comment:null), ] POSTHOOK: Lineage: srcpart_double_hour.hr EXPRESSION [(srcpart)srcpart.FieldSchema(name:hr, type:string, comment:null), ] PREHOOK: query: -- single column, single key -EXPLAIN VECTORIZATION select count(*) from srcpart join srcpart_date on (srcpart.ds = srcpart_date.ds) where srcpart_date.`date` = '2008-04-08' +EXPLAIN select count(*) from srcpart join srcpart_date on (srcpart.ds = srcpart_date.ds) where srcpart_date.`date` = '2008-04-08' PREHOOK: type: QUERY POSTHOOK: query: -- single column, single key -EXPLAIN VECTORIZATION select count(*) from srcpart join srcpart_date on (srcpart.ds = srcpart_date.ds) where srcpart_date.`date` = '2008-04-08' +EXPLAIN select count(*) from srcpart join srcpart_date on (srcpart.ds = srcpart_date.ds) where srcpart_date.`date` = '2008-04-08' 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 @@ -253,10 +234,6 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 368000 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs - Map Vectorization: - enabled: false - enabledConditionsNotMet: hive.vectorized.use.vector.serde.deserialize IS false - inputFileFormats: org.apache.hadoop.mapred.TextInputFormat Map 4 Map Operator Tree: TableScan @@ -292,14 +269,6 @@ STAGE PLANS: Target Vertex: Map 1 Execution mode: vectorized, llap LLAP IO: all inputs - Map Vectorization: - enabled: true - enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true - groupByVectorOutput: true - inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat - allNative: false - usesVectorUDFAdaptor: false - vectorized: true Reducer 2 Execution mode: llap Reduce Operator Tree: @@ -321,13 +290,6 @@ STAGE PLANS: value expressions: _col0 (type: bigint) Reducer 3 Execution mode: vectorized, llap - Reduce Vectorization: - enabled: true - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true - groupByVectorOutput: true - allNative: false - usesVectorUDFAdaptor: false - vectorized: true Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -367,14 +329,10 @@ POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 POSTHOOK: Input: default@srcpart_date #### A masked pattern was here #### 1000 -PREHOOK: query: EXPLAIN VECTORIZATION select count(*) from srcpart join srcpart_date on (srcpart.ds = srcpart_date.ds) where srcpart_date.`date` = '2008-04-08' +PREHOOK: query: EXPLAIN select count(*) from srcpart join srcpart_date on (srcpart.ds = srcpart_date.ds) where srcpart_date.`date` = '2008-04-08' PREHOOK: type: QUERY -POSTHOOK: query: EXPLAIN VECTORIZATION select count(*) from srcpart join srcpart_date on (srcpart.ds = srcpart_date.ds) where srcpart_date.`date` = '2008-04-08' +POSTHOOK: query: EXPLAIN select count(*) from srcpart join srcpart_date on (srcpart.ds = srcpart_date.ds) where srcpart_date.`date` = '2008-04-08' 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 @@ -405,10 +363,6 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 368000 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs - Map Vectorization: - enabled: false - enabledConditionsNotMet: hive.vectorized.use.vector.serde.deserialize IS false - inputFileFormats: org.apache.hadoop.mapred.TextInputFormat Map 4 Map Operator Tree: TableScan @@ -429,14 +383,6 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized, llap LLAP IO: all inputs - Map Vectorization: - enabled: true - enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true - groupByVectorOutput: true - inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat - allNative: true - usesVectorUDFAdaptor: false - vectorized: true Reducer 2 Execution mode: llap Reduce Operator Tree: @@ -458,13 +404,6 @@ STAGE PLANS: value expressions: _col0 (type: bigint) Reducer 3 Execution mode: vectorized, llap - Reduce Vectorization: - enabled: true - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true - groupByVectorOutput: true - allNative: false - usesVectorUDFAdaptor: false - vectorized: true Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -518,17 +457,13 @@ POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 #### A masked pattern was here #### 1000 PREHOOK: query: -- multiple sources, single key -EXPLAIN VECTORIZATION select count(*) from srcpart join srcpart_date on (srcpart.ds = srcpart_date.ds) join srcpart_hour on (srcpart.hr = srcpart_hour.hr) +EXPLAIN select count(*) from srcpart join srcpart_date on (srcpart.ds = srcpart_date.ds) join srcpart_hour on (srcpart.hr = srcpart_hour.hr) where srcpart_date.`date` = '2008-04-08' and srcpart_hour.hour = 11 PREHOOK: type: QUERY POSTHOOK: query: -- multiple sources, single key -EXPLAIN VECTORIZATION select count(*) from srcpart join srcpart_date on (srcpart.ds = srcpart_date.ds) join srcpart_hour on (srcpart.hr = srcpart_hour.hr) +EXPLAIN select count(*) from srcpart join srcpart_date on (srcpart.ds = srcpart_date.ds) join srcpart_hour on (srcpart.hr = srcpart_hour.hr) where srcpart_date.`date` = '2008-04-08' and srcpart_hour.hour = 11 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 @@ -560,10 +495,6 @@ STAGE PLANS: value expressions: _col1 (type: string) Execution mode: llap LLAP IO: no inputs - Map Vectorization: - enabled: false - enabledConditionsNotMet: hive.vectorized.use.vector.serde.deserialize IS false - inputFileFormats: org.apache.hadoop.mapred.TextInputFormat Map 5 Map Operator Tree: TableScan @@ -599,14 +530,6 @@ STAGE PLANS: Target Vertex: Map 1 Execution mode: vectorized, llap LLAP IO: all inputs - Map Vectorization: - enabled: true - enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true - groupByVectorOutput: true - inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat - allNative: false - usesVectorUDFAdaptor: false - vectorized: true Map 6 Map Operator Tree: TableScan @@ -642,14 +565,6 @@ STAGE PLANS: Target Vertex: Map 1 Execution mode: vectorized, llap LLAP IO: all inputs - Map Vectorization: - enabled: true - enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true - groupByVectorOutput: true - inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat - allNative: false - usesVectorUDFAdaptor: true - vectorized: true Reducer 2 Execution mode: llap Reduce Operator Tree: @@ -687,13 +602,6 @@ STAGE PLANS: value expressions: _col0 (type: bigint) Reducer 4 Execution mode: vectorized, llap - Reduce Vectorization: - enabled: true - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true - groupByVectorOutput: true - allNative: false - usesVectorUDFAdaptor: false - vectorized: true Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -737,16 +645,12 @@ POSTHOOK: Input: default@srcpart_date POSTHOOK: Input: default@srcpart_hour #### A masked pattern was here #### 500 -PREHOOK: query: EXPLAIN VECTORIZATION select count(*) from srcpart join srcpart_date on (srcpart.ds = srcpart_date.ds) join srcpart_hour on (srcpart.hr = srcpart_hour.hr) +PREHOOK: query: EXPLAIN select count(*) from srcpart join srcpart_date on (srcpart.ds = srcpart_date.ds) join srcpart_hour on (srcpart.hr = srcpart_hour.hr) where srcpart_date.`date` = '2008-04-08' and srcpart_hour.hour = 11 PREHOOK: type: QUERY -POSTHOOK: query: EXPLAIN VECTORIZATION select count(*) from srcpart join srcpart_date on (srcpart.ds = srcpart_date.ds) join srcpart_hour on (srcpart.hr = srcpart_hour.hr) +POSTHOOK: query: EXPLAIN select count(*) from srcpart join srcpart_date on (srcpart.ds = srcpart_date.ds) join srcpart_hour on (srcpart.hr = srcpart_hour.hr) where srcpart_date.`date` = '2008-04-08' and srcpart_hour.hour = 11 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 @@ -779,10 +683,6 @@ STAGE PLANS: value expressions: _col1 (type: string) Execution mode: llap LLAP IO: no inputs - Map Vectorization: - enabled: false - enabledConditionsNotMet: hive.vectorized.use.vector.serde.deserialize IS false - inputFileFormats: org.apache.hadoop.mapred.TextInputFormat Map 5 Map Operator Tree: TableScan @@ -803,14 +703,6 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized, llap LLAP IO: all inputs - Map Vectorization: - enabled: true - enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true - groupByVectorOutput: true - inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat - allNative: true - usesVectorUDFAdaptor: false - vectorized: true Map 6 Map Operator Tree: TableScan @@ -831,14 +723,6 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized, llap LLAP IO: all inputs - Map Vectorization: - enabled: true - enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true - groupByVectorOutput: true - inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat - allNative: true - usesVectorUDFAdaptor: true - vectorized: true Reducer 2 Execution mode: llap Reduce Operator Tree: @@ -876,13 +760,6 @@ STAGE PLANS: value expressions: _col0 (type: bigint) Reducer 4 Execution mode: vectorized, llap - Reduce Vectorization: - enabled: true - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true - groupByVectorOutput: true - allNative: false - usesVectorUDFAdaptor: false - vectorized: true Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -938,15 +815,11 @@ POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 #### A masked pattern was here #### 500 PREHOOK: query: -- multiple columns single source -EXPLAIN VECTORIZATION select count(*) from srcpart join srcpart_date_hour on (srcpart.ds = srcpart_date_hour.ds and srcpart.hr = srcpart_date_hour.hr) where srcpart_date_hour.`date` = '2008-04-08' and srcpart_date_hour.hour = 11 +EXPLAIN select count(*) from srcpart join srcpart_date_hour on (srcpart.ds = srcpart_date_hour.ds and srcpart.hr = srcpart_date_hour.hr) where srcpart_date_hour.`date` = '2008-04-08' and srcpart_date_hour.hour = 11 PREHOOK: type: QUERY POSTHOOK: query: -- multiple columns single source -EXPLAIN VECTORIZATION select count(*) from srcpart join srcpart_date_hour on (srcpart.ds = srcpart_date_hour.ds and srcpart.hr = srcpart_date_hour.hr) where srcpart_date_hour.`date` = '2008-04-08' and srcpart_date_hour.hour = 11 +EXPLAIN select count(*) from srcpart join srcpart_date_hour on (srcpart.ds = srcpart_date_hour.ds and srcpart.hr = srcpart_date_hour.hr) where srcpart_date_hour.`date` = '2008-04-08' and srcpart_date_hour.hour = 11 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 @@ -976,10 +849,6 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 736000 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs - Map Vectorization: - enabled: false - enabledConditionsNotMet: hive.vectorized.use.vector.serde.deserialize IS false - inputFileFormats: org.apache.hadoop.mapred.TextInputFormat Map 4 Map Operator Tree: TableScan @@ -1030,14 +899,6 @@ STAGE PLANS: Target Vertex: Map 1 Execution mode: vectorized, llap LLAP IO: all inputs - Map Vectorization: - enabled: true - enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true - groupByVectorOutput: true - inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat - allNative: false - usesVectorUDFAdaptor: true - vectorized: true Reducer 2 Execution mode: llap Reduce Operator Tree: @@ -1059,13 +920,6 @@ STAGE PLANS: value expressions: _col0 (type: bigint) Reducer 3 Execution mode: vectorized, llap - Reduce Vectorization: - enabled: true - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true - groupByVectorOutput: true - allNative: false - usesVectorUDFAdaptor: false - vectorized: true Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -1105,14 +959,10 @@ POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 POSTHOOK: Input: default@srcpart_date_hour #### A masked pattern was here #### 500 -PREHOOK: query: EXPLAIN VECTORIZATION select count(*) from srcpart join srcpart_date_hour on (srcpart.ds = srcpart_date_hour.ds and srcpart.hr = srcpart_date_hour.hr) where srcpart_date_hour.`date` = '2008-04-08' and srcpart_date_hour.hour = 11 +PREHOOK: query: EXPLAIN select count(*) from srcpart join srcpart_date_hour on (srcpart.ds = srcpart_date_hour.ds and srcpart.hr = srcpart_date_hour.hr) where srcpart_date_hour.`date` = '2008-04-08' and srcpart_date_hour.hour = 11 PREHOOK: type: QUERY -POSTHOOK: query: EXPLAIN VECTORIZATION select count(*) from srcpart join srcpart_date_hour on (srcpart.ds = srcpart_date_hour.ds and srcpart.hr = srcpart_date_hour.hr) where srcpart_date_hour.`date` = '2008-04-08' and srcpart_date_hour.hour = 11 +POSTHOOK: query: EXPLAIN select count(*) from srcpart join srcpart_date_hour on (srcpart.ds = srcpart_date_hour.ds and srcpart.hr = srcpart_date_hour.hr) where srcpart_date_hour.`date` = '2008-04-08' and srcpart_date_hour.hour = 11 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 @@ -1143,10 +993,6 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 736000 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs - Map Vectorization: - enabled: false - enabledConditionsNotMet: hive.vectorized.use.vector.serde.deserialize IS false - inputFileFormats: org.apache.hadoop.mapred.TextInputFormat Map 4 Map Operator Tree: TableScan @@ -1167,14 +1013,6 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized, llap LLAP IO: all inputs - Map Vectorization: - enabled: true - enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true - groupByVectorOutput: true - inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat - allNative: true - usesVectorUDFAdaptor: true - vectorized: true Reducer 2 Execution mode: llap Reduce Operator Tree: @@ -1196,13 +1034,6 @@ STAGE PLANS: value expressions: _col0 (type: bigint) Reducer 3 Execution mode: vectorized, llap - Reduce Vectorization: - enabled: true - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true - groupByVectorOutput: true - allNative: false - usesVectorUDFAdaptor: false - vectorized: true Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -1254,15 +1085,11 @@ POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 #### A masked pattern was here #### 500 PREHOOK: query: -- empty set -EXPLAIN VECTORIZATION select count(*) from srcpart join srcpart_date on (srcpart.ds = srcpart_date.ds) where srcpart_date.`date` = 'I DONT EXIST' +EXPLAIN select count(*) from srcpart join srcpart_date on (srcpart.ds = srcpart_date.ds) where srcpart_date.`date` = 'I DONT EXIST' PREHOOK: type: QUERY POSTHOOK: query: -- empty set -EXPLAIN VECTORIZATION select count(*) from srcpart join srcpart_date on (srcpart.ds = srcpart_date.ds) where srcpart_date.`date` = 'I DONT EXIST' +EXPLAIN select count(*) from srcpart join srcpart_date on (srcpart.ds = srcpart_date.ds) where srcpart_date.`date` = 'I DONT EXIST' 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 @@ -1293,10 +1120,6 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 368000 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs - Map Vectorization: - enabled: false - enabledConditionsNotMet: hive.vectorized.use.vector.serde.deserialize IS false - inputFileFormats: org.apache.hadoop.mapred.TextInputFormat Map 4 Map Operator Tree: TableScan @@ -1332,14 +1155,6 @@ STAGE PLANS: Target Vertex: Map 1 Execution mode: vectorized, llap LLAP IO: all inputs - Map Vectorization: - enabled: true - enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true - groupByVectorOutput: true - inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat - allNative: false - usesVectorUDFAdaptor: false - vectorized: true Reducer 2 Execution mode: llap Reduce Operator Tree: @@ -1361,13 +1176,6 @@ STAGE PLANS: value expressions: _col0 (type: bigint) Reducer 3 Execution mode: vectorized, llap - Reduce Vectorization: - enabled: true - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true - groupByVectorOutput: true - allNative: false - usesVectorUDFAdaptor: false - vectorized: true Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -1407,14 +1215,10 @@ POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 POSTHOOK: Input: default@srcpart_date #### A masked pattern was here #### 0 -PREHOOK: query: EXPLAIN VECTORIZATION select count(*) from srcpart join srcpart_date on (srcpart.ds = srcpart_date.ds) where srcpart_date.`date` = 'I DONT EXIST' +PREHOOK: query: EXPLAIN select count(*) from srcpart join srcpart_date on (srcpart.ds = srcpart_date.ds) where srcpart_date.`date` = 'I DONT EXIST' PREHOOK: type: QUERY -POSTHOOK: query: EXPLAIN VECTORIZATION select count(*) from srcpart join srcpart_date on (srcpart.ds = srcpart_date.ds) where srcpart_date.`date` = 'I DONT EXIST' +POSTHOOK: query: EXPLAIN select count(*) from srcpart join srcpart_date on (srcpart.ds = srcpart_date.ds) where srcpart_date.`date` = 'I DONT EXIST' 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 @@ -1445,10 +1249,6 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 368000 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs - Map Vectorization: - enabled: false - enabledConditionsNotMet: hive.vectorized.use.vector.serde.deserialize IS false - inputFileFormats: org.apache.hadoop.mapred.TextInputFormat Map 4 Map Operator Tree: TableScan @@ -1469,14 +1269,6 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized, llap LLAP IO: all inputs - Map Vectorization: - enabled: true - enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true - groupByVectorOutput: true - inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat - allNative: true - usesVectorUDFAdaptor: false - vectorized: true Reducer 2 Execution mode: llap Reduce Operator Tree: @@ -1498,13 +1290,6 @@ STAGE PLANS: value expressions: _col0 (type: bigint) Reducer 3 Execution mode: vectorized, llap - Reduce Vectorization: - enabled: true - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true - groupByVectorOutput: true - allNative: false - usesVectorUDFAdaptor: false - vectorized: true Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -1554,15 +1339,11 @@ POSTHOOK: Input: default@srcpart #### A masked pattern was here #### 0 PREHOOK: query: -- expressions -EXPLAIN VECTORIZATION select count(*) from srcpart join srcpart_double_hour on (srcpart.hr = cast(srcpart_double_hour.hr/2 as int)) where srcpart_double_hour.hour = 11 +EXPLAIN select count(*) from srcpart join srcpart_double_hour on (srcpart.hr = cast(srcpart_double_hour.hr/2 as int)) where srcpart_double_hour.hour = 11 PREHOOK: type: QUERY POSTHOOK: query: -- expressions -EXPLAIN VECTORIZATION select count(*) from srcpart join srcpart_double_hour on (srcpart.hr = cast(srcpart_double_hour.hr/2 as int)) where srcpart_double_hour.hour = 11 +EXPLAIN select count(*) from srcpart join srcpart_double_hour on (srcpart.hr = cast(srcpart_double_hour.hr/2 as int)) where srcpart_double_hour.hour = 11 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 @@ -1593,10 +1374,6 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 368000 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs - Map Vectorization: - enabled: false - enabledConditionsNotMet: hive.vectorized.use.vector.serde.deserialize IS false - inputFileFormats: org.apache.hadoop.mapred.TextInputFormat Map 4 Map Operator Tree: TableScan @@ -1632,14 +1409,6 @@ STAGE PLANS: Target Vertex: Map 1 Execution mode: vectorized, llap LLAP IO: all inputs - Map Vectorization: - enabled: true - enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true - groupByVectorOutput: true - inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat - allNative: false - usesVectorUDFAdaptor: true - vectorized: true Reducer 2 Execution mode: llap Reduce Operator Tree: @@ -1661,13 +1430,6 @@ STAGE PLANS: value expressions: _col0 (type: bigint) Reducer 3 Execution mode: vectorized, llap - Reduce Vectorization: - enabled: true - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true - groupByVectorOutput: true - allNative: false - usesVectorUDFAdaptor: false - vectorized: true Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -1707,14 +1469,10 @@ POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 POSTHOOK: Input: default@srcpart_double_hour #### A masked pattern was here #### 1000 -PREHOOK: query: EXPLAIN VECTORIZATION select count(*) from srcpart join srcpart_double_hour on (srcpart.hr*2 = srcpart_double_hour.hr) where srcpart_double_hour.hour = 11 +PREHOOK: query: EXPLAIN select count(*) from srcpart join srcpart_double_hour on (srcpart.hr*2 = srcpart_double_hour.hr) where srcpart_double_hour.hour = 11 PREHOOK: type: QUERY -POSTHOOK: query: EXPLAIN VECTORIZATION select count(*) from srcpart join srcpart_double_hour on (srcpart.hr*2 = srcpart_double_hour.hr) where srcpart_double_hour.hour = 11 +POSTHOOK: query: EXPLAIN select count(*) from srcpart join srcpart_double_hour on (srcpart.hr*2 = srcpart_double_hour.hr) where srcpart_double_hour.hour = 11 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 @@ -1745,10 +1503,6 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 368000 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs - Map Vectorization: - enabled: false - enabledConditionsNotMet: hive.vectorized.use.vector.serde.deserialize IS false - inputFileFormats: org.apache.hadoop.mapred.TextInputFormat Map 4 Map Operator Tree: TableScan @@ -1784,14 +1538,6 @@ STAGE PLANS: Target Vertex: Map 1 Execution mode: vectorized, llap LLAP IO: all inputs - Map Vectorization: - enabled: true - enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true - groupByVectorOutput: true - inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat - allNative: false - usesVectorUDFAdaptor: true - vectorized: true Reducer 2 Execution mode: llap Reduce Operator Tree: @@ -1813,13 +1559,6 @@ STAGE PLANS: value expressions: _col0 (type: bigint) Reducer 3 Execution mode: vectorized, llap - Reduce Vectorization: - enabled: true - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true - groupByVectorOutput: true - allNative: false - usesVectorUDFAdaptor: false - vectorized: true Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -1859,14 +1598,10 @@ POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 POSTHOOK: Input: default@srcpart_double_hour #### A masked pattern was here #### 1000 -PREHOOK: query: EXPLAIN VECTORIZATION select count(*) from srcpart join srcpart_double_hour on (srcpart.hr = cast(srcpart_double_hour.hr/2 as int)) where srcpart_double_hour.hour = 11 +PREHOOK: query: EXPLAIN select count(*) from srcpart join srcpart_double_hour on (srcpart.hr = cast(srcpart_double_hour.hr/2 as int)) where srcpart_double_hour.hour = 11 PREHOOK: type: QUERY -POSTHOOK: query: EXPLAIN VECTORIZATION select count(*) from srcpart join srcpart_double_hour on (srcpart.hr = cast(srcpart_double_hour.hr/2 as int)) where srcpart_double_hour.hour = 11 +POSTHOOK: query: EXPLAIN select count(*) from srcpart join srcpart_double_hour on (srcpart.hr = cast(srcpart_double_hour.hr/2 as int)) where srcpart_double_hour.hour = 11 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 @@ -1897,10 +1632,6 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 368000 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs - Map Vectorization: - enabled: false - enabledConditionsNotMet: hive.vectorized.use.vector.serde.deserialize IS false - inputFileFormats: org.apache.hadoop.mapred.TextInputFormat Map 4 Map Operator Tree: TableScan @@ -1921,14 +1652,6 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized, llap LLAP IO: all inputs - Map Vectorization: - enabled: true - enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true - groupByVectorOutput: true - inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat - allNative: true - usesVectorUDFAdaptor: true - vectorized: true Reducer 2 Execution mode: llap Reduce Operator Tree: @@ -1950,13 +1673,6 @@ STAGE PLANS: value expressions: _col0 (type: bigint) Reducer 3 Execution mode: vectorized, llap - Reduce Vectorization: - enabled: true - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true - groupByVectorOutput: true - allNative: false - usesVectorUDFAdaptor: false - vectorized: true Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -1996,14 +1712,10 @@ POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 POSTHOOK: Input: default@srcpart_double_hour #### A masked pattern was here #### 1000 -PREHOOK: query: EXPLAIN VECTORIZATION select count(*) from srcpart join srcpart_double_hour on (srcpart.hr*2 = srcpart_double_hour.hr) where srcpart_double_hour.hour = 11 +PREHOOK: query: EXPLAIN select count(*) from srcpart join srcpart_double_hour on (srcpart.hr*2 = srcpart_double_hour.hr) where srcpart_double_hour.hour = 11 PREHOOK: type: QUERY -POSTHOOK: query: EXPLAIN VECTORIZATION select count(*) from srcpart join srcpart_double_hour on (srcpart.hr*2 = srcpart_double_hour.hr) where srcpart_double_hour.hour = 11 +POSTHOOK: query: EXPLAIN select count(*) from srcpart join srcpart_double_hour on (srcpart.hr*2 = srcpart_double_hour.hr) where srcpart_double_hour.hour = 11 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 @@ -2034,10 +1746,6 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 368000 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs - Map Vectorization: - enabled: false - enabledConditionsNotMet: hive.vectorized.use.vector.serde.deserialize IS false - inputFileFormats: org.apache.hadoop.mapred.TextInputFormat Map 4 Map Operator Tree: TableScan @@ -2058,14 +1766,6 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized, llap LLAP IO: all inputs - Map Vectorization: - enabled: true - enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true - groupByVectorOutput: true - inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat - allNative: true - usesVectorUDFAdaptor: true - vectorized: true Reducer 2 Execution mode: llap Reduce Operator Tree: @@ -2087,13 +1787,6 @@ STAGE PLANS: value expressions: _col0 (type: bigint) Reducer 3 Execution mode: vectorized, llap - Reduce Vectorization: - enabled: true - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true - groupByVectorOutput: true - allNative: false - usesVectorUDFAdaptor: false - vectorized: true Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -2146,14 +1839,10 @@ POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 #### A masked pattern was here #### 1000 -PREHOOK: query: EXPLAIN VECTORIZATION select count(*) from srcpart join srcpart_double_hour on (cast(srcpart.hr*2 as string) = cast(srcpart_double_hour.hr as string)) where srcpart_double_hour.hour = 11 +PREHOOK: query: EXPLAIN select count(*) from srcpart join srcpart_double_hour on (cast(srcpart.hr*2 as string) = cast(srcpart_double_hour.hr as string)) where srcpart_double_hour.hour = 11 PREHOOK: type: QUERY -POSTHOOK: query: EXPLAIN VECTORIZATION select count(*) from srcpart join srcpart_double_hour on (cast(srcpart.hr*2 as string) = cast(srcpart_double_hour.hr as string)) where srcpart_double_hour.hour = 11 +POSTHOOK: query: EXPLAIN select count(*) from srcpart join srcpart_double_hour on (cast(srcpart.hr*2 as string) = cast(srcpart_double_hour.hr as string)) where srcpart_double_hour.hour = 11 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 @@ -2184,10 +1873,6 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 368000 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs - Map Vectorization: - enabled: false - enabledConditionsNotMet: hive.vectorized.use.vector.serde.deserialize IS false - inputFileFormats: org.apache.hadoop.mapred.TextInputFormat Map 4 Map Operator Tree: TableScan @@ -2223,14 +1908,6 @@ STAGE PLANS: Target Vertex: Map 1 Execution mode: vectorized, llap LLAP IO: all inputs - Map Vectorization: - enabled: true - enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true - groupByVectorOutput: true - inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat - allNative: false - usesVectorUDFAdaptor: true - vectorized: true Reducer 2 Execution mode: llap Reduce Operator Tree: @@ -2252,13 +1929,6 @@ STAGE PLANS: value expressions: _col0 (type: bigint) Reducer 3 Execution mode: vectorized, llap - Reduce Vectorization: - enabled: true - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true - groupByVectorOutput: true - allNative: false - usesVectorUDFAdaptor: false - vectorized: true Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -2313,15 +1983,11 @@ POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 1000 Warning: Shuffle Join MERGEJOIN[22][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product PREHOOK: query: -- parent is reduce tasks -EXPLAIN VECTORIZATION select count(*) from srcpart join (select ds as ds, ds as `date` from srcpart group by ds) s on (srcpart.ds = s.ds) where s.`date` = '2008-04-08' +EXPLAIN select count(*) from srcpart join (select ds as ds, ds as `date` from srcpart group by ds) s on (srcpart.ds = s.ds) where s.`date` = '2008-04-08' PREHOOK: type: QUERY POSTHOOK: query: -- parent is reduce tasks -EXPLAIN VECTORIZATION select count(*) from srcpart join (select ds as ds, ds as `date` from srcpart group by ds) s on (srcpart.ds = s.ds) where s.`date` = '2008-04-08' +EXPLAIN select count(*) from srcpart join (select ds as ds, ds as `date` from srcpart group by ds) s on (srcpart.ds = s.ds) where s.`date` = '2008-04-08' 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 @@ -2349,10 +2015,6 @@ STAGE PLANS: Statistics: Num rows: 1000 Data size: 94000 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs - Map Vectorization: - enabled: false - enabledConditionsNotMet: hive.vectorized.use.vector.serde.deserialize IS false - inputFileFormats: org.apache.hadoop.mapred.TextInputFormat Map 4 Map Operator Tree: TableScan @@ -2373,10 +2035,6 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs - Map Vectorization: - enabled: false - enabledConditionsNotMet: hive.vectorized.use.vector.serde.deserialize IS false - inputFileFormats: org.apache.hadoop.mapred.TextInputFormat Reducer 2 Execution mode: llap Reduce Operator Tree: @@ -2398,13 +2056,6 @@ STAGE PLANS: value expressions: _col0 (type: bigint) Reducer 3 Execution mode: vectorized, llap - Reduce Vectorization: - enabled: true - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true - groupByVectorOutput: true - allNative: false - usesVectorUDFAdaptor: false - vectorized: true Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -2420,13 +2071,6 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Reducer 5 Execution mode: vectorized, llap - Reduce Vectorization: - enabled: true - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true - groupByVectorOutput: true - allNative: false - usesVectorUDFAdaptor: false - vectorized: true Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string) @@ -2474,15 +2118,11 @@ POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 1000 Warning: Shuffle Join MERGEJOIN[16][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product PREHOOK: query: -- non-equi join -EXPLAIN VECTORIZATION select count(*) from srcpart, srcpart_date_hour where (srcpart_date_hour.`date` = '2008-04-08' and srcpart_date_hour.hour = 11) and (srcpart.ds = srcpart_date_hour.ds or srcpart.hr = srcpart_date_hour.hr) +EXPLAIN select count(*) from srcpart, srcpart_date_hour where (srcpart_date_hour.`date` = '2008-04-08' and srcpart_date_hour.hour = 11) and (srcpart.ds = srcpart_date_hour.ds or srcpart.hr = srcpart_date_hour.hr) PREHOOK: type: QUERY POSTHOOK: query: -- non-equi join -EXPLAIN VECTORIZATION select count(*) from srcpart, srcpart_date_hour where (srcpart_date_hour.`date` = '2008-04-08' and srcpart_date_hour.hour = 11) and (srcpart.ds = srcpart_date_hour.ds or srcpart.hr = srcpart_date_hour.hr) +EXPLAIN select count(*) from srcpart, srcpart_date_hour where (srcpart_date_hour.`date` = '2008-04-08' and srcpart_date_hour.hour = 11) and (srcpart.ds = srcpart_date_hour.ds or srcpart.hr = srcpart_date_hour.hr) 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 @@ -2511,10 +2151,6 @@ STAGE PLANS: value expressions: _col0 (type: string), _col1 (type: string) Execution mode: llap LLAP IO: no inputs - Map Vectorization: - enabled: false - enabledConditionsNotMet: hive.vectorized.use.vector.serde.deserialize IS false - inputFileFormats: org.apache.hadoop.mapred.TextInputFormat Map 4 Map Operator Tree: TableScan @@ -2534,14 +2170,6 @@ STAGE PLANS: value expressions: _col0 (type: string), _col2 (type: string) Execution mode: vectorized, llap LLAP IO: all inputs - Map Vectorization: - enabled: true - enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true - groupByVectorOutput: true - inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat - allNative: false - usesVectorUDFAdaptor: true - vectorized: true Reducer 2 Execution mode: llap Reduce Operator Tree: @@ -2569,13 +2197,6 @@ STAGE PLANS: value expressions: _col0 (type: bigint) Reducer 3 Execution mode: vectorized, llap - Reduce Vectorization: - enabled: true - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true - groupByVectorOutput: true - allNative: false - usesVectorUDFAdaptor: false - vectorized: true Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -2617,15 +2238,11 @@ POSTHOOK: Input: default@srcpart_date_hour #### A masked pattern was here #### 1500 PREHOOK: query: -- old style join syntax -EXPLAIN VECTORIZATION select count(*) from srcpart, srcpart_date_hour where srcpart_date_hour.`date` = '2008-04-08' and srcpart_date_hour.hour = 11 and srcpart.ds = srcpart_date_hour.ds and srcpart.hr = srcpart_date_hour.hr +EXPLAIN select count(*) from srcpart, srcpart_date_hour where srcpart_date_hour.`date` = '2008-04-08' and srcpart_date_hour.hour = 11 and srcpart.ds = srcpart_date_hour.ds and srcpart.hr = srcpart_date_hour.hr PREHOOK: type: QUERY POSTHOOK: query: -- old style join syntax -EXPLAIN VECTORIZATION select count(*) from srcpart, srcpart_date_hour where srcpart_date_hour.`date` = '2008-04-08' and srcpart_date_hour.hour = 11 and srcpart.ds = srcpart_date_hour.ds and srcpart.hr = srcpart_date_hour.hr +EXPLAIN select count(*) from srcpart, srcpart_date_hour where srcpart_date_hour.`date` = '2008-04-08' and srcpart_date_hour.hour = 11 and srcpart.ds = srcpart_date_hour.ds and srcpart.hr = srcpart_date_hour.hr 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 @@ -2655,10 +2272,6 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 736000 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs - Map Vectorization: - enabled: false - enabledConditionsNotMet: hive.vectorized.use.vector.serde.deserialize IS false - inputFileFormats: org.apache.hadoop.mapred.TextInputFormat Map 4 Map Operator Tree: TableScan @@ -2709,14 +2322,6 @@ STAGE PLANS: Target Vertex: Map 1 Execution mode: vectorized, llap LLAP IO: all inputs - Map Vectorization: - enabled: true - enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true - groupByVectorOutput: true - inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat - allNative: false - usesVectorUDFAdaptor: true - vectorized: true Reducer 2 Execution mode: llap Reduce Operator Tree: @@ -2738,13 +2343,6 @@ STAGE PLANS: value expressions: _col0 (type: bigint) Reducer 3 Execution mode: vectorized, llap - Reduce Vectorization: - enabled: true - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true - groupByVectorOutput: true - allNative: false - usesVectorUDFAdaptor: false - vectorized: true Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -2785,15 +2383,11 @@ POSTHOOK: Input: default@srcpart_date_hour #### A masked pattern was here #### 500 PREHOOK: query: -- left join -EXPLAIN VECTORIZATION select count(*) from srcpart left join srcpart_date on (srcpart.ds = srcpart_date.ds) where srcpart_date.`date` = '2008-04-08' +EXPLAIN select count(*) from srcpart left join srcpart_date on (srcpart.ds = srcpart_date.ds) where srcpart_date.`date` = '2008-04-08' PREHOOK: type: QUERY POSTHOOK: query: -- left join -EXPLAIN VECTORIZATION select count(*) from srcpart left join srcpart_date on (srcpart.ds = srcpart_date.ds) where srcpart_date.`date` = '2008-04-08' +EXPLAIN select count(*) from srcpart left join srcpart_date on (srcpart.ds = srcpart_date.ds) where srcpart_date.`date` = '2008-04-08' 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 @@ -2824,10 +2418,6 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 368000 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs - Map Vectorization: - enabled: false - enabledConditionsNotMet: hive.vectorized.use.vector.serde.deserialize IS false - inputFileFormats: org.apache.hadoop.mapred.TextInputFormat Map 4 Map Operator Tree: TableScan @@ -2863,14 +2453,6 @@ STAGE PLANS: Target Vertex: Map 1 Execution mode: vectorized, llap LLAP IO: all inputs - Map Vectorization: - enabled: true - enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true - groupByVectorOutput: true - inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat - allNative: false - usesVectorUDFAdaptor: false - vectorized: true Reducer 2 Execution mode: llap Reduce Operator Tree: @@ -2892,13 +2474,6 @@ STAGE PLANS: value expressions: _col0 (type: bigint) Reducer 3 Execution mode: vectorized, llap - Reduce Vectorization: - enabled: true - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true - groupByVectorOutput: true - allNative: false - usesVectorUDFAdaptor: false - vectorized: true Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -2919,14 +2494,10 @@ STAGE PLANS: Processor Tree: ListSink -PREHOOK: query: EXPLAIN VECTORIZATION select count(*) from srcpart_date left join srcpart on (srcpart.ds = srcpart_date.ds) where srcpart_date.`date` = '2008-04-08' +PREHOOK: query: EXPLAIN select count(*) from srcpart_date left join srcpart on (srcpart.ds = srcpart_date.ds) where srcpart_date.`date` = '2008-04-08' PREHOOK: type: QUERY -POSTHOOK: query: EXPLAIN VECTORIZATION select count(*) from srcpart_date left join srcpart on (srcpart.ds = srcpart_date.ds) where srcpart_date.`date` = '2008-04-08' +POSTHOOK: query: EXPLAIN select count(*) from srcpart_date left join srcpart on (srcpart.ds = srcpart_date.ds) where srcpart_date.`date` = '2008-04-08' 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 @@ -2975,14 +2546,6 @@ STAGE PLANS: Target Vertex: Map 4 Execution mode: vectorized, llap LLAP IO: all inputs - Map Vectorization: - enabled: true - enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true - groupByVectorOutput: true - inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat - allNative: false - usesVectorUDFAdaptor: false - vectorized: true Map 4 Map Operator Tree: TableScan @@ -2999,10 +2562,6 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 368000 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs - Map Vectorization: - enabled: false - enabledConditionsNotMet: hive.vectorized.use.vector.serde.deserialize IS false - inputFileFormats: org.apache.hadoop.mapred.TextInputFormat Reducer 2 Execution mode: llap Reduce Operator Tree: @@ -3024,13 +2583,6 @@ STAGE PLANS: value expressions: _col0 (type: bigint) Reducer 3 Execution mode: vectorized, llap - Reduce Vectorization: - enabled: true - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true - groupByVectorOutput: true - allNative: false - usesVectorUDFAdaptor: false - vectorized: true Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -3052,15 +2604,11 @@ STAGE PLANS: ListSink PREHOOK: query: -- full outer -EXPLAIN VECTORIZATION select count(*) from srcpart full outer join srcpart_date on (srcpart.ds = srcpart_date.ds) where srcpart_date.`date` = '2008-04-08' +EXPLAIN select count(*) from srcpart full outer join srcpart_date on (srcpart.ds = srcpart_date.ds) where srcpart_date.`date` = '2008-04-08' PREHOOK: type: QUERY POSTHOOK: query: -- full outer -EXPLAIN VECTORIZATION select count(*) from srcpart full outer join srcpart_date on (srcpart.ds = srcpart_date.ds) where srcpart_date.`date` = '2008-04-08' +EXPLAIN select count(*) from srcpart full outer join srcpart_date on (srcpart.ds = srcpart_date.ds) where srcpart_date.`date` = '2008-04-08' 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 @@ -3090,10 +2638,6 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 368000 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs - Map Vectorization: - enabled: false - enabledConditionsNotMet: hive.vectorized.use.vector.serde.deserialize IS false - inputFileFormats: org.apache.hadoop.mapred.TextInputFormat Map 4 Map Operator Tree: TableScan @@ -3129,14 +2673,6 @@ STAGE PLANS: Target Vertex: Map 1 Execution mode: vectorized, llap LLAP IO: all inputs - Map Vectorization: - enabled: true - enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true - groupByVectorOutput: true - inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat - allNative: false - usesVectorUDFAdaptor: false - vectorized: true Reducer 2 Execution mode: llap Reduce Operator Tree: @@ -3158,13 +2694,6 @@ STAGE PLANS: value expressions: _col0 (type: bigint) Reducer 3 Execution mode: vectorized, llap - Reduce Vectorization: - enabled: true - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true - groupByVectorOutput: true - allNative: false - usesVectorUDFAdaptor: false - vectorized: true Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -3186,17 +2715,13 @@ STAGE PLANS: ListSink PREHOOK: query: -- with static pruning -EXPLAIN VECTORIZATION select count(*) from srcpart join srcpart_date on (srcpart.ds = srcpart_date.ds) join srcpart_hour on (srcpart.hr = srcpart_hour.hr) +EXPLAIN select count(*) from srcpart join srcpart_date on (srcpart.ds = srcpart_date.ds) join srcpart_hour on (srcpart.hr = srcpart_hour.hr) where srcpart_date.`date` = '2008-04-08' and srcpart_hour.hour = 11 and srcpart.hr = 11 PREHOOK: type: QUERY POSTHOOK: query: -- with static pruning -EXPLAIN VECTORIZATION select count(*) from srcpart join srcpart_date on (srcpart.ds = srcpart_date.ds) join srcpart_hour on (srcpart.hr = srcpart_hour.hr) +EXPLAIN select count(*) from srcpart join srcpart_date on (srcpart.ds = srcpart_date.ds) join srcpart_hour on (srcpart.hr = srcpart_hour.hr) where srcpart_date.`date` = '2008-04-08' and srcpart_hour.hour = 11 and srcpart.hr = 11 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 @@ -3228,10 +2753,6 @@ STAGE PLANS: value expressions: _col1 (type: string) Execution mode: llap LLAP IO: no inputs - Map Vectorization: - enabled: false - enabledConditionsNotMet: hive.vectorized.use.vector.serde.deserialize IS false - inputFileFormats: org.apache.hadoop.mapred.TextInputFormat Map 5 Map Operator Tree: TableScan @@ -3267,14 +2788,6 @@ STAGE PLANS: Target Vertex: Map 1 Execution mode: vectorized, llap LLAP IO: all inputs - Map Vectorization: - enabled: true - enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true - groupByVectorOutput: true - inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat - allNative: false - usesVectorUDFAdaptor: false - vectorized: true Map 6 Map Operator Tree: TableScan @@ -3295,14 +2808,6 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized, llap LLAP IO: all inputs - Map Vectorization: - enabled: true - enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true - groupByVectorOutput: true - inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat - allNative: true - usesVectorUDFAdaptor: true - vectorized: true Reducer 2 Execution mode: llap Reduce Operator Tree: @@ -3340,13 +2845,6 @@ STAGE PLANS: value expressions: _col0 (type: bigint) Reducer 4 Execution mode: vectorized, llap - Reduce Vectorization: - enabled: true - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true - groupByVectorOutput: true - allNative: false - usesVectorUDFAdaptor: false - vectorized: true Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -3386,16 +2884,12 @@ POSTHOOK: Input: default@srcpart_date POSTHOOK: Input: default@srcpart_hour #### A masked pattern was here #### 500 -PREHOOK: query: EXPLAIN VECTORIZATION select count(*) from srcpart join srcpart_date on (srcpart.ds = srcpart_date.ds) join srcpart_hour on (srcpart.hr = srcpart_hour.hr) +PREHOOK: query: EXPLAIN select count(*) from srcpart join srcpart_date on (srcpart.ds = srcpart_date.ds) join srcpart_hour on (srcpart.hr = srcpart_hour.hr) where srcpart_date.`date` = '2008-04-08' and srcpart.hr = 13 PREHOOK: type: QUERY -POSTHOOK: query: EXPLAIN VECTORIZATION select count(*) from srcpart join srcpart_date on (srcpart.ds = srcpart_date.ds) join srcpart_hour on (srcpart.hr = srcpart_hour.hr) +POSTHOOK: query: EXPLAIN select count(*) from srcpart join srcpart_date on (srcpart.ds = srcpart_date.ds) join srcpart_hour on (srcpart.hr = srcpart_hour.hr) where srcpart_date.`date` = '2008-04-08' and srcpart.hr = 13 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 @@ -3431,12 +2925,6 @@ STAGE PLANS: value expressions: _col1 (type: string) Execution mode: vectorized, llap LLAP IO: unknown - Map Vectorization: - enabled: true - groupByVectorOutput: true - allNative: true - usesVectorUDFAdaptor: true - vectorized: true Map 5 Map Operator Tree: TableScan @@ -3457,14 +2945,6 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized, llap LLAP IO: all inputs - Map Vectorization: - enabled: true - enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true - groupByVectorOutput: true - inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat - allNative: true - usesVectorUDFAdaptor: false - vectorized: true Map 6 Map Operator Tree: TableScan @@ -3485,14 +2965,6 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized, llap LLAP IO: all inputs - Map Vectorization: - enabled: true - enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true - groupByVectorOutput: true - inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat - allNative: true - usesVectorUDFAdaptor: true - vectorized: true Reducer 2 Execution mode: llap Reduce Operator Tree: @@ -3530,13 +3002,6 @@ STAGE PLANS: value expressions: _col0 (type: bigint) Reducer 4 Execution mode: vectorized, llap - Reduce Vectorization: - enabled: true - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true - groupByVectorOutput: true - allNative: false - usesVectorUDFAdaptor: false - vectorized: true Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -3573,15 +3038,11 @@ POSTHOOK: Input: default@srcpart_hour #### A masked pattern was here #### 0 PREHOOK: query: -- union + subquery -EXPLAIN VECTORIZATION select count(*) from srcpart where srcpart.ds in (select max(srcpart.ds) from srcpart union all select min(srcpart.ds) from srcpart) +EXPLAIN select count(*) from srcpart where srcpart.ds in (select max(srcpart.ds) from srcpart union all select min(srcpart.ds) from srcpart) PREHOOK: type: QUERY POSTHOOK: query: -- union + subquery -EXPLAIN VECTORIZATION select count(*) from srcpart where srcpart.ds in (select max(srcpart.ds) from srcpart union all select min(srcpart.ds) from srcpart) +EXPLAIN select count(*) from srcpart where srcpart.ds in (select max(srcpart.ds) from srcpart union all select min(srcpart.ds) from srcpart) 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 @@ -3614,10 +3075,6 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 368000 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs - Map Vectorization: - enabled: false - enabledConditionsNotMet: hive.vectorized.use.vector.serde.deserialize IS false - inputFileFormats: org.apache.hadoop.mapred.TextInputFormat Map 4 Map Operator Tree: TableScan @@ -3638,10 +3095,6 @@ STAGE PLANS: value expressions: _col0 (type: string) Execution mode: llap LLAP IO: no inputs - Map Vectorization: - enabled: false - enabledConditionsNotMet: hive.vectorized.use.vector.serde.deserialize IS false - inputFileFormats: org.apache.hadoop.mapred.TextInputFormat Map 7 Map Operator Tree: TableScan @@ -3662,10 +3115,6 @@ STAGE PLANS: value expressions: _col0 (type: string) Execution mode: llap LLAP IO: no inputs - Map Vectorization: - enabled: false - enabledConditionsNotMet: hive.vectorized.use.vector.serde.deserialize IS false - inputFileFormats: org.apache.hadoop.mapred.TextInputFormat Reducer 2 Execution mode: llap Reduce Operator Tree: @@ -3687,13 +3136,6 @@ STAGE PLANS: value expressions: _col0 (type: bigint) Reducer 3 Execution mode: vectorized, llap - Reduce Vectorization: - enabled: true - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true - groupByVectorOutput: true - allNative: false - usesVectorUDFAdaptor: false - vectorized: true Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -3709,13 +3151,6 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Reducer 5 Execution mode: vectorized, llap - Reduce Vectorization: - enabled: true - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true - groupByVectorOutput: true - allNative: false - usesVectorUDFAdaptor: false - vectorized: true Reduce Operator Tree: Group By Operator aggregations: max(VALUE._col0) @@ -3752,13 +3187,6 @@ STAGE PLANS: Target Vertex: Map 1 Reducer 8 Execution mode: vectorized, llap - Reduce Vectorization: - enabled: true - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true - groupByVectorOutput: true - allNative: false - usesVectorUDFAdaptor: false - vectorized: true Reduce Operator Tree: Group By Operator aggregations: min(VALUE._col0) @@ -3819,14 +3247,10 @@ POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 #### A masked pattern was here #### 2000 -PREHOOK: query: EXPLAIN VECTORIZATION select distinct(ds) from srcpart where srcpart.ds in (select max(srcpart.ds) from srcpart union all select min(srcpart.ds) from srcpart) +PREHOOK: query: EXPLAIN select distinct(ds) from srcpart where srcpart.ds in (select max(srcpart.ds) from srcpart union all select min(srcpart.ds) from srcpart) PREHOOK: type: QUERY -POSTHOOK: query: EXPLAIN VECTORIZATION select distinct(ds) from srcpart where srcpart.ds in (select max(srcpart.ds) from srcpart union all select min(srcpart.ds) from srcpart) +POSTHOOK: query: EXPLAIN select distinct(ds) from srcpart where srcpart.ds in (select max(srcpart.ds) from srcpart union all select min(srcpart.ds) from srcpart) 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 @@ -3859,10 +3283,6 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 368000 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs - Map Vectorization: - enabled: false - enabledConditionsNotMet: hive.vectorized.use.vector.serde.deserialize IS false - inputFileFormats: org.apache.hadoop.mapred.TextInputFormat Map 4 Map Operator Tree: TableScan @@ -3883,10 +3303,6 @@ STAGE PLANS: value expressions: _col0 (type: string) Execution mode: llap LLAP IO: no inputs - Map Vectorization: - enabled: false - enabledConditionsNotMet: hive.vectorized.use.vector.serde.deserialize IS false - inputFileFormats: org.apache.hadoop.mapred.TextInputFormat Map 7 Map Operator Tree: TableScan @@ -3907,10 +3323,6 @@ STAGE PLANS: value expressions: _col0 (type: string) Execution mode: llap LLAP IO: no inputs - Map Vectorization: - enabled: false - enabledConditionsNotMet: hive.vectorized.use.vector.serde.deserialize IS false - inputFileFormats: org.apache.hadoop.mapred.TextInputFormat Reducer 2 Execution mode: llap Reduce Operator Tree: @@ -3934,13 +3346,6 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE Reducer 3 Execution mode: vectorized, llap - Reduce Vectorization: - enabled: true - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true - groupByVectorOutput: true - allNative: false - usesVectorUDFAdaptor: false - vectorized: true Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string) @@ -3956,13 +3361,6 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Reducer 5 Execution mode: vectorized, llap - Reduce Vectorization: - enabled: true - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true - groupByVectorOutput: true - allNative: false - usesVectorUDFAdaptor: false - vectorized: true Reduce Operator Tree: Group By Operator aggregations: max(VALUE._col0) @@ -3999,13 +3397,6 @@ STAGE PLANS: Target Vertex: Map 1 Reducer 8 Execution mode: vectorized, llap - Reduce Vectorization: - enabled: true - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true - groupByVectorOutput: true - allNative: false - usesVectorUDFAdaptor: false - vectorized: true Reduce Operator Tree: Group By Operator aggregations: min(VALUE._col0) @@ -4067,14 +3458,10 @@ POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 #### A masked pattern was here #### 2008-04-08 2008-04-09 -PREHOOK: query: EXPLAIN VECTORIZATION select ds from (select distinct(ds) as ds from srcpart union all select distinct(ds) as ds from srcpart) s where s.ds in (select max(srcpart.ds) from srcpart union all select min(srcpart.ds) from srcpart) +PREHOOK: query: EXPLAIN select ds from (select distinct(ds) as ds from srcpart union all select distinct(ds) as ds from srcpart) s where s.ds in (select max(srcpart.ds) from srcpart union all select min(srcpart.ds) from srcpart) PREHOOK: type: QUERY -POSTHOOK: query: EXPLAIN VECTORIZATION select ds from (select distinct(ds) as ds from srcpart union all select distinct(ds) as ds from srcpart) s where s.ds in (select max(srcpart.ds) from srcpart union all select min(srcpart.ds) from srcpart) +POSTHOOK: query: EXPLAIN select ds from (select distinct(ds) as ds from srcpart union all select distinct(ds) as ds from srcpart) s where s.ds in (select max(srcpart.ds) from srcpart union all select min(srcpart.ds) from srcpart) 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 @@ -4109,10 +3496,6 @@ STAGE PLANS: Statistics: Num rows: 2 Data size: 368 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs - Map Vectorization: - enabled: false - enabledConditionsNotMet: hive.vectorized.use.vector.serde.deserialize IS false - inputFileFormats: org.apache.hadoop.mapred.TextInputFormat Map 10 Map Operator Tree: TableScan @@ -4133,10 +3516,6 @@ STAGE PLANS: value expressions: _col0 (type: string) Execution mode: llap LLAP IO: no inputs - Map Vectorization: - enabled: false - enabledConditionsNotMet: hive.vectorized.use.vector.serde.deserialize IS false - inputFileFormats: org.apache.hadoop.mapred.TextInputFormat Map 5 Map Operator Tree: TableScan @@ -4155,10 +3534,6 @@ STAGE PLANS: Statistics: Num rows: 2 Data size: 368 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs - Map Vectorization: - enabled: false - enabledConditionsNotMet: hive.vectorized.use.vector.serde.deserialize IS false - inputFileFormats: org.apache.hadoop.mapred.TextInputFormat Map 7 Map Operator Tree: TableScan @@ -4179,19 +3554,8 @@ STAGE PLANS: value expressions: _col0 (type: string) Execution mode: llap LLAP IO: no inputs - Map Vectorization: - enabled: false - enabledConditionsNotMet: hive.vectorized.use.vector.serde.deserialize IS false - inputFileFormats: org.apache.hadoop.mapred.TextInputFormat Reducer 11 Execution mode: vectorized, llap - Reduce Vectorization: - enabled: true - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true - groupByVectorOutput: true - allNative: false - usesVectorUDFAdaptor: false - vectorized: true Reduce Operator Tree: Group By Operator aggregations: min(VALUE._col0) @@ -4243,13 +3607,6 @@ STAGE PLANS: Target Vertex: Map 5 Reducer 2 Execution mode: vectorized, llap - Reduce Vectorization: - enabled: true - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true - groupByVectorOutput: true - allNative: false - usesVectorUDFAdaptor: false - vectorized: true Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string) @@ -4281,13 +3638,6 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Reducer 6 Execution mode: vectorized, llap - Reduce Vectorization: - enabled: true - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true - groupByVectorOutput: true - allNative: false - usesVectorUDFAdaptor: false - vectorized: true Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string) @@ -4301,13 +3651,6 @@ STAGE PLANS: Statistics: Num rows: 4 Data size: 736 Basic stats: COMPLETE Column stats: COMPLETE Reducer 8 Execution mode: vectorized, llap - Reduce Vectorization: - enabled: true - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true - groupByVectorOutput: true - allNative: false - usesVectorUDFAdaptor: false - vectorized: true Reduce Operator Tree: Group By Operator aggregations: max(VALUE._col0) @@ -4389,15 +3732,11 @@ POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 2008-04-09 2008-04-09 PREHOOK: query: -- single column, single key -EXPLAIN VECTORIZATION select count(*) from srcpart join srcpart_date on (srcpart.ds = srcpart_date.ds) where srcpart_date.`date` = '2008-04-08' +EXPLAIN select count(*) from srcpart join srcpart_date on (srcpart.ds = srcpart_date.ds) where srcpart_date.`date` = '2008-04-08' PREHOOK: type: QUERY POSTHOOK: query: -- single column, single key -EXPLAIN VECTORIZATION select count(*) from srcpart join srcpart_date on (srcpart.ds = srcpart_date.ds) where srcpart_date.`date` = '2008-04-08' +EXPLAIN select count(*) from srcpart join srcpart_date on (srcpart.ds = srcpart_date.ds) where srcpart_date.`date` = '2008-04-08' 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 @@ -4441,10 +3780,6 @@ STAGE PLANS: value expressions: _col0 (type: bigint) Execution mode: llap LLAP IO: no inputs - Map Vectorization: - enabled: false - enabledConditionsNotMet: hive.vectorized.use.vector.serde.deserialize IS false - inputFileFormats: org.apache.hadoop.mapred.TextInputFormat Map 3 Map Operator Tree: TableScan @@ -4480,23 +3815,8 @@ STAGE PLANS: Target Vertex: Map 1 Execution mode: vectorized, llap LLAP IO: all inputs - Map Vectorization: - enabled: true - enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true - groupByVectorOutput: true - inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat - allNative: false - usesVectorUDFAdaptor: false - vectorized: true Reducer 2 Execution mode: vectorized, llap - Reduce Vectorization: - enabled: true - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true - groupByVectorOutput: true - allNative: false - usesVectorUDFAdaptor: false - vectorized: true Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -4550,17 +3870,13 @@ POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 #### A masked pattern was here #### 1000 PREHOOK: query: -- multiple sources, single key -EXPLAIN VECTORIZATION select count(*) from srcpart join srcpart_date on (srcpart.ds = srcpart_date.ds) join srcpart_hour on (srcpart.hr = srcpart_hour.hr) +EXPLAIN select count(*) from srcpart join srcpart_date on (srcpart.ds = srcpart_date.ds) join srcpart_hour on (srcpart.hr = srcpart_hour.hr) where srcpart_date.`date` = '2008-04-08' and srcpart_hour.hour = 11 PREHOOK: type: QUERY POSTHOOK: query: -- multiple sources, single key -EXPLAIN VECTORIZATION select count(*) from srcpart join srcpart_date on (srcpart.ds = srcpart_date.ds) join srcpart_hour on (srcpart.hr = srcpart_hour.hr) +EXPLAIN select count(*) from srcpart join srcpart_date on (srcpart.ds = srcpart_date.ds) join srcpart_hour on (srcpart.hr = srcpart_hour.hr) where srcpart_date.`date` = '2008-04-08' and srcpart_hour.hour = 11 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 @@ -4613,10 +3929,6 @@ STAGE PLANS: value expressions: _col0 (type: bigint) Execution mode: llap LLAP IO: no inputs - Map Vectorization: - enabled: false - enabledConditionsNotMet: hive.vectorized.use.vector.serde.deserialize IS false - inputFileFormats: org.apache.hadoop.mapred.TextInputFormat Map 3 Map Operator Tree: TableScan @@ -4652,14 +3964,6 @@ STAGE PLANS: Target Vertex: Map 1 Execution mode: vectorized, llap LLAP IO: all inputs - Map Vectorization: - enabled: true - enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true - groupByVectorOutput: true - inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat - allNative: false - usesVectorUDFAdaptor: false - vectorized: true Map 4 Map Operator Tree: TableScan @@ -4695,23 +3999,8 @@ STAGE PLANS: Target Vertex: Map 1 Execution mode: vectorized, llap LLAP IO: all inputs - Map Vectorization: - enabled: true - enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true - groupByVectorOutput: true - inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat - allNative: false - usesVectorUDFAdaptor: true - vectorized: true Reducer 2 Execution mode: vectorized, llap - Reduce Vectorization: - enabled: true - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true - groupByVectorOutput: true - allNative: false - usesVectorUDFAdaptor: false - vectorized: true Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -4767,15 +4056,11 @@ POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 #### A masked pattern was here #### 500 PREHOOK: query: -- multiple columns single source -EXPLAIN VECTORIZATION select count(*) from srcpart join srcpart_date_hour on (srcpart.ds = srcpart_date_hour.ds and srcpart.hr = srcpart_date_hour.hr) where srcpart_date_hour.`date` = '2008-04-08' and srcpart_date_hour.hour = 11 +EXPLAIN select count(*) from srcpart join srcpart_date_hour on (srcpart.ds = srcpart_date_hour.ds and srcpart.hr = srcpart_date_hour.hr) where srcpart_date_hour.`date` = '2008-04-08' and srcpart_date_hour.hour = 11 PREHOOK: type: QUERY POSTHOOK: query: -- multiple columns single source -EXPLAIN VECTORIZATION select count(*) from srcpart join srcpart_date_hour on (srcpart.ds = srcpart_date_hour.ds and srcpart.hr = srcpart_date_hour.hr) where srcpart_date_hour.`date` = '2008-04-08' and srcpart_date_hour.hour = 11 +EXPLAIN select count(*) from s
<TRUNCATED>