diff --git a/pom.xml b/pom.xml index 9f6ff46225b0..319a9680b823 100644 --- a/pom.xml +++ b/pom.xml @@ -117,7 +117,7 @@ 1.12.0 4.2.1 1.84 - 1.42.0 + 1.43.0-SNAPSHOT 6.0.5 6.0.11 3.2.0-release @@ -273,6 +273,20 @@ false + diff --git a/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/HiveRelShuttleImpl.java b/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/HiveRelShuttleImpl.java index 6f74664c0bd7..eb7176897dfa 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/HiveRelShuttleImpl.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/HiveRelShuttleImpl.java @@ -22,8 +22,17 @@ import java.util.Deque; import org.apache.calcite.linq4j.Ord; import org.apache.calcite.rel.RelNode; +import org.apache.calcite.rel.core.Collect; +import org.apache.calcite.rel.core.Combine; +import org.apache.calcite.rel.core.ConditionalCorrelate; +import org.apache.calcite.rel.core.Sample; +import org.apache.calcite.rel.core.Snapshot; +import org.apache.calcite.rel.core.SortExchange; import org.apache.calcite.rel.core.TableFunctionScan; import org.apache.calcite.rel.core.TableScan; +import org.apache.calcite.rel.core.TableSpool; +import org.apache.calcite.rel.core.Uncollect; +import org.apache.calcite.rel.core.Window; import org.apache.calcite.rel.logical.LogicalAggregate; import org.apache.calcite.rel.logical.LogicalAsofJoin; import org.apache.calcite.rel.logical.LogicalCalc; @@ -190,6 +199,51 @@ public RelNode visit(LogicalAsofJoin logicalAsofJoin) { public RelNode visit(LogicalRepeatUnion logicalRepeatUnion) { return visitChildren(logicalRepeatUnion); } + + @Override + public RelNode visit(Window window) { + return visitChildren(window); + } + + @Override + public RelNode visit(Snapshot snapshot) { + return visitChildren(snapshot); + } + + @Override + public RelNode visit(Collect collect) { + return visitChildren(collect); + } + + @Override + public RelNode visit(Sample sample) { + return visitChildren(sample); + } + + @Override + public RelNode visit(Uncollect uncollect) { + return visitChildren(uncollect); + } + + @Override + public RelNode visit(Combine combine) { + return visitChildren(combine); + } + + @Override + public RelNode visit(ConditionalCorrelate conditionalCorrelate) { + return visitChildren(conditionalCorrelate); + } + + @Override + public RelNode visit(SortExchange sortExchange) { + return visitChildren(sortExchange); + } + + @Override + public RelNode visit(TableSpool tableSpool) { + return visitChildren(tableSpool); + } } // End RelShuttleImpl.java diff --git a/ql/src/test/results/clientpositive/llap/allcolref_in_udf.q.out b/ql/src/test/results/clientpositive/llap/allcolref_in_udf.q.out index 9b6626ad5dc7..236d52a2ded5 100644 --- a/ql/src/test/results/clientpositive/llap/allcolref_in_udf.q.out +++ b/ql/src/test/results/clientpositive/llap/allcolref_in_udf.q.out @@ -76,10 +76,10 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - filterExpr: ((UDFToDouble(key) < 100.0D) and (UDFToDouble(key) + 1.0D) is not null) (type: boolean) + filterExpr: (UDFToDouble(key) < 100.0D) (type: boolean) Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: ((UDFToDouble(key) < 100.0D) and (UDFToDouble(key) + 1.0D) is not null) (type: boolean) + predicate: (UDFToDouble(key) < 100.0D) (type: boolean) Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string), concat(key, value) (type: string), (UDFToDouble(key) + 1.0D) (type: double) diff --git a/ql/src/test/results/clientpositive/llap/auto_join13.q.out b/ql/src/test/results/clientpositive/llap/auto_join13.q.out index 55352923f3e6..8d7b32361f23 100644 --- a/ql/src/test/results/clientpositive/llap/auto_join13.q.out +++ b/ql/src/test/results/clientpositive/llap/auto_join13.q.out @@ -61,7 +61,6 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2 input vertices: 1 Reducer 4 - residual filter predicates: {(UDFToDouble(_col2) + UDFToDouble(_col0)) is not null} Statistics: Num rows: 166 Data size: 43990 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: @@ -88,7 +87,7 @@ STAGE PLANS: sort order: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) - Execution mode: llap + Execution mode: vectorized, llap LLAP IO: all inputs Map 3 Map Operator Tree: diff --git a/ql/src/test/results/clientpositive/llap/auto_join2.q.out b/ql/src/test/results/clientpositive/llap/auto_join2.q.out index bc77780295e2..4ff363c6a7f1 100644 --- a/ql/src/test/results/clientpositive/llap/auto_join2.q.out +++ b/ql/src/test/results/clientpositive/llap/auto_join2.q.out @@ -38,73 +38,70 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src1 - filterExpr: key is not null (type: boolean) - probeDecodeDetails: cacheKey:HASH_MAP_MAPJOIN_49_container, bigKeyColName:key, smallTablePos:1, keyRatio:0.632 + filterExpr: (key is not null and UDFToDouble(key) is not null) (type: boolean) + probeDecodeDetails: cacheKey:HASH_MAP_MAPJOIN_45_container, bigKeyColName:key, smallTablePos:1, keyRatio:0.632 Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: key is not null (type: boolean) + predicate: (key is not null and UDFToDouble(key) is not null) (type: boolean) Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), UDFToDouble(key) (type: double) outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: _col1 is not null (type: boolean) - Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col3 + input vertices: + 1 Reducer 4 + Statistics: Num rows: 791 Data size: 81473 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col3 + 0 (_col1 + _col3) (type: double) + 1 _col1 (type: double) + outputColumnNames: _col0, _col4 input vertices: - 1 Reducer 4 - Statistics: Num rows: 791 Data size: 81473 Basic stats: COMPLETE Column stats: COMPLETE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 (_col1 + _col3) (type: double) - 1 _col1 (type: double) - outputColumnNames: _col0, _col4 - input vertices: - 1 Map 3 - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + 1 Map 3 + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: UDFToInteger(_col0) (type: int), _col4 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.dest_j2 Select Operator - expressions: UDFToInteger(_col0) (type: int), _col4 (type: string) - outputColumnNames: _col0, _col1 + expressions: _col0 (type: int), _col1 (type: string) + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest_j2 - Select Operator - expressions: _col0 (type: int), _col1 (type: string) - outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: min(key), max(key), count(1), count(key), compute_bit_vector_hll(key), max(length(value)), avg(COALESCE(length(value),0)), count(value), compute_bit_vector_hll(value) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + Group By Operator + aggregations: min(key), max(key), count(1), count(key), compute_bit_vector_hll(key), max(length(value)), avg(COALESCE(length(value),0)), count(value), compute_bit_vector_hll(value) + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + Statistics: Num rows: 1 Data size: 400 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: Statistics: Num rows: 1 Data size: 400 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 400 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint), _col3 (type: bigint), _col4 (type: binary), _col5 (type: int), _col6 (type: struct), _col7 (type: bigint), _col8 (type: binary) + value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint), _col3 (type: bigint), _col4 (type: binary), _col5 (type: int), _col6 (type: struct), _col7 (type: bigint), _col8 (type: binary) Execution mode: vectorized, llap LLAP IO: all inputs Map 3 Map Operator Tree: TableScan alias: src3 - filterExpr: (UDFToDouble(key) is not null or key is not null) (type: boolean) + filterExpr: (UDFToDouble(key) is not null or (key is not null and UDFToDouble(key) is not null)) (type: boolean) Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: UDFToDouble(key) is not null (type: boolean) @@ -121,22 +118,19 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 49500 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string) Filter Operator - predicate: key is not null (type: boolean) + predicate: (key is not null and UDFToDouble(key) is not null) (type: boolean) Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), UDFToDouble(key) (type: double) outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: _col1 is not null (type: boolean) + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: double) + value expressions: _col1 (type: double) Execution mode: vectorized, llap LLAP IO: all inputs Reducer 2 diff --git a/ql/src/test/results/clientpositive/llap/auto_join_stats.q.out b/ql/src/test/results/clientpositive/llap/auto_join_stats.q.out index e4c590dda7e5..8ed693529f7c 100644 --- a/ql/src/test/results/clientpositive/llap/auto_join_stats.q.out +++ b/ql/src/test/results/clientpositive/llap/auto_join_stats.q.out @@ -48,50 +48,44 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src1 - filterExpr: key is not null (type: boolean) + filterExpr: (key is not null and UDFToDouble(key) is not null) (type: boolean) Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: key is not null (type: boolean) + predicate: (key is not null and UDFToDouble(key) is not null) (type: boolean) Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), UDFToDouble(key) (type: double) outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: _col1 is not null (type: boolean) + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: double) + value expressions: _col1 (type: double) Execution mode: vectorized, llap LLAP IO: all inputs Map 3 Map Operator Tree: TableScan alias: src2 - filterExpr: key is not null (type: boolean) + filterExpr: (key is not null and UDFToDouble(key) is not null) (type: boolean) Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: key is not null (type: boolean) + predicate: (key is not null and UDFToDouble(key) is not null) (type: boolean) Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), UDFToDouble(key) (type: double) outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: _col1 is not null (type: boolean) + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: double) + value expressions: _col1 (type: double) Execution mode: vectorized, llap LLAP IO: all inputs Map 4 @@ -219,50 +213,44 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src1 - filterExpr: key is not null (type: boolean) + filterExpr: (key is not null and UDFToDouble(key) is not null) (type: boolean) Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: key is not null (type: boolean) + predicate: (key is not null and UDFToDouble(key) is not null) (type: boolean) Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), UDFToDouble(key) (type: double) outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: _col1 is not null (type: boolean) + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: double) + value expressions: _col1 (type: double) Execution mode: vectorized, llap LLAP IO: all inputs Map 3 Map Operator Tree: TableScan alias: src2 - filterExpr: key is not null (type: boolean) + filterExpr: (key is not null and UDFToDouble(key) is not null) (type: boolean) Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: key is not null (type: boolean) + predicate: (key is not null and UDFToDouble(key) is not null) (type: boolean) Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), UDFToDouble(key) (type: double) outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: _col1 is not null (type: boolean) + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: double) + value expressions: _col1 (type: double) Execution mode: vectorized, llap LLAP IO: all inputs Map 4 diff --git a/ql/src/test/results/clientpositive/llap/auto_join_stats2.q.out b/ql/src/test/results/clientpositive/llap/auto_join_stats2.q.out index 6b775c286e7b..f1a52ab82b0c 100644 --- a/ql/src/test/results/clientpositive/llap/auto_join_stats2.q.out +++ b/ql/src/test/results/clientpositive/llap/auto_join_stats2.q.out @@ -14,7 +14,7 @@ POSTHOOK: query: load data local inpath '../../data/files/T1.txt' into table sma POSTHOOK: type: LOAD #### A masked pattern was here #### POSTHOOK: Output: default@smalltable -Warning: Map Join MAPJOIN[37][bigTable=?] in task 'Map 1' is a cross product +Warning: Map Join MAPJOIN[33][bigTable=?] in task 'Map 1' is a cross product PREHOOK: query: explain select src1.key, src2.key, smalltable.key from src src1 JOIN src src2 ON (src1.key = src2.key) JOIN smalltable ON (src1.key + src2.key = smalltable.key) PREHOOK: type: QUERY PREHOOK: Input: default@smalltable @@ -41,50 +41,47 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src2 - filterExpr: key is not null (type: boolean) + filterExpr: (key is not null and UDFToDouble(key) is not null) (type: boolean) Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: key is not null (type: boolean) + predicate: (key is not null and UDFToDouble(key) is not null) (type: boolean) Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), UDFToDouble(key) (type: double) outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: _col1 is not null (type: boolean) - Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 + 1 + outputColumnNames: _col0, _col1, _col2, _col3 + input vertices: + 1 Map 2 + Statistics: Num rows: 500 Data size: 140000 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 - 1 - outputColumnNames: _col0, _col1, _col2, _col3 + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 input vertices: - 1 Map 2 - Statistics: Num rows: 500 Data size: 140000 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - input vertices: - 1 Map 3 - residual filter predicates: {((_col5 + _col1) = _col3)} + 1 Map 3 + residual filter predicates: {((_col5 + _col1) = _col3)} + Statistics: Num rows: 275 Data size: 77000 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col4 (type: string), _col0 (type: string), _col2 (type: string) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 275 Data size: 77000 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col4 (type: string), _col0 (type: string), _col2 (type: string) - outputColumnNames: _col0, _col1, _col2 + File Output Operator + compressed: false Statistics: Num rows: 275 Data size: 77000 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 275 Data size: 77000 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Execution mode: llap LLAP IO: all inputs Map 2 @@ -111,25 +108,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src1 - filterExpr: key is not null (type: boolean) + filterExpr: (key is not null and UDFToDouble(key) is not null) (type: boolean) Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: key is not null (type: boolean) + predicate: (key is not null and UDFToDouble(key) is not null) (type: boolean) Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), UDFToDouble(key) (type: double) outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: _col1 is not null (type: boolean) + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: double) + value expressions: _col1 (type: double) Execution mode: vectorized, llap LLAP IO: all inputs @@ -139,7 +133,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Map Join MAPJOIN[37][bigTable=?] in task 'Map 1' is a cross product +Warning: Map Join MAPJOIN[33][bigTable=?] in task 'Map 1' is a cross product PREHOOK: query: select src1.key, src2.key, smalltable.key from src src1 JOIN src src2 ON (src1.key = src2.key) JOIN smalltable ON (src1.key + src2.key = smalltable.key) PREHOOK: type: QUERY PREHOOK: Input: default@smalltable @@ -204,85 +198,79 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src1 - filterExpr: key is not null (type: boolean) - probeDecodeDetails: cacheKey:HASH_MAP_MAPJOIN_55_container, bigKeyColName:key, smallTablePos:1, keyRatio:0.632 + filterExpr: (key is not null and UDFToDouble(key) is not null) (type: boolean) + probeDecodeDetails: cacheKey:HASH_MAP_MAPJOIN_51_container, bigKeyColName:key, smallTablePos:1, keyRatio:0.632 Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: key is not null (type: boolean) + predicate: (key is not null and UDFToDouble(key) is not null) (type: boolean) Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), UDFToDouble(key) (type: double) outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: _col1 is not null (type: boolean) - Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + input vertices: + 1 Map 2 + Statistics: Num rows: 791 Data size: 150290 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) + 0 (_col1 + _col3) (type: double) + 1 _col0 (type: double) outputColumnNames: _col0, _col1, _col2, _col3 input vertices: - 1 Map 2 - Statistics: Num rows: 791 Data size: 150290 Basic stats: COMPLETE Column stats: COMPLETE + 1 Map 3 + Statistics: Num rows: 870 Data size: 165319 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: 0 (_col1 + _col3) (type: double) - 1 _col0 (type: double) - outputColumnNames: _col0, _col1, _col2, _col3 + 1 _col1 (type: double) + outputColumnNames: _col0, _col2, _col5 input vertices: - 1 Map 3 - Statistics: Num rows: 870 Data size: 165319 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 (_col1 + _col3) (type: double) - 1 _col1 (type: double) - outputColumnNames: _col0, _col2, _col5 - input vertices: - 1 Map 4 + 1 Map 4 + Statistics: Num rows: 957 Data size: 181850 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: string), _col2 (type: string), _col5 (type: string) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 957 Data size: 181850 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col2 (type: string), _col5 (type: string) - outputColumnNames: _col0, _col1, _col2 + File Output Operator + compressed: false Statistics: Num rows: 957 Data size: 181850 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 957 Data size: 181850 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Execution mode: vectorized, llap LLAP IO: all inputs Map 2 Map Operator Tree: TableScan alias: src2 - filterExpr: key is not null (type: boolean) + filterExpr: (key is not null and UDFToDouble(key) is not null) (type: boolean) Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: key is not null (type: boolean) + predicate: (key is not null and UDFToDouble(key) is not null) (type: boolean) Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), UDFToDouble(key) (type: double) outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: _col1 is not null (type: boolean) + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: double) + value expressions: _col1 (type: double) Execution mode: vectorized, llap LLAP IO: all inputs Map 3 diff --git a/ql/src/test/results/clientpositive/llap/interval_3.q.out b/ql/src/test/results/clientpositive/llap/interval_3.q.out index 40a8a3df742b..f004b3e990a2 100644 --- a/ql/src/test/results/clientpositive/llap/interval_3.q.out +++ b/ql/src/test/results/clientpositive/llap/interval_3.q.out @@ -159,10 +159,10 @@ STAGE PLANS: Map Operator Tree: TableScan alias: d1 - filterExpr: (((((((CAST( d_date AS DATE) + INTERVAL'1-0') + INTERVAL'0-2') + INTERVAL'5 00:00:00.000000000') + INTERVAL'0 04:00:00.000000000') + INTERVAL'0 00:10:00.000000000') + INTERVAL'0 00:00:09.000000000') is not null and (CAST( d_date AS DATE) + INTERVAL'1-2') is not null) (type: boolean) + filterExpr: CAST( d_date AS DATE) is not null (type: boolean) Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((((((CAST( d_date AS DATE) + INTERVAL'1-0') + INTERVAL'0-2') + INTERVAL'5 00:00:00.000000000') + INTERVAL'0 04:00:00.000000000') + INTERVAL'0 00:10:00.000000000') + INTERVAL'0 00:00:09.000000000') is not null and (CAST( d_date AS DATE) + INTERVAL'1-2') is not null) (type: boolean) + predicate: CAST( d_date AS DATE) is not null (type: boolean) Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: d_week_seq (type: int), ((((((CAST( d_date AS DATE) + INTERVAL'1-0') + INTERVAL'0-2') + INTERVAL'5 00:00:00.000000000') + INTERVAL'0 04:00:00.000000000') + INTERVAL'0 00:10:00.000000000') + INTERVAL'0 00:00:09.000000000') (type: timestamp), (CAST( d_date AS DATE) + INTERVAL'1-2') (type: date) diff --git a/ql/src/test/results/clientpositive/llap/join13.q.out b/ql/src/test/results/clientpositive/llap/join13.q.out index 0bc700cd4561..dc395305938d 100644 --- a/ql/src/test/results/clientpositive/llap/join13.q.out +++ b/ql/src/test/results/clientpositive/llap/join13.q.out @@ -103,7 +103,6 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2 - residual filter predicates: {(UDFToDouble(_col2) + UDFToDouble(_col0)) is not null} Statistics: Num rows: 166 Data size: 43990 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: (UDFToDouble(_col2) + UDFToDouble(_col0)) (type: double) diff --git a/ql/src/test/results/clientpositive/llap/join2.q.out b/ql/src/test/results/clientpositive/llap/join2.q.out index 32912e401227..3b46b489faa3 100644 --- a/ql/src/test/results/clientpositive/llap/join2.q.out +++ b/ql/src/test/results/clientpositive/llap/join2.q.out @@ -37,32 +37,29 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src1 - filterExpr: key is not null (type: boolean) + filterExpr: (key is not null and UDFToDouble(key) is not null) (type: boolean) Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: key is not null (type: boolean) + predicate: (key is not null and UDFToDouble(key) is not null) (type: boolean) Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), UDFToDouble(key) (type: double) outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: _col1 is not null (type: boolean) + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: double) + value expressions: _col1 (type: double) Execution mode: vectorized, llap LLAP IO: all inputs Map 4 Map Operator Tree: TableScan alias: src3 - filterExpr: (UDFToDouble(key) is not null or key is not null) (type: boolean) + filterExpr: (UDFToDouble(key) is not null or (key is not null and UDFToDouble(key) is not null)) (type: boolean) Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: UDFToDouble(key) is not null (type: boolean) @@ -79,22 +76,19 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 49500 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string) Filter Operator - predicate: key is not null (type: boolean) + predicate: (key is not null and UDFToDouble(key) is not null) (type: boolean) Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), UDFToDouble(key) (type: double) outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: _col1 is not null (type: boolean) + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: double) + value expressions: _col1 (type: double) Execution mode: vectorized, llap LLAP IO: all inputs Reducer 2 diff --git a/ql/src/test/results/clientpositive/llap/materialized_view_cluster.q.out b/ql/src/test/results/clientpositive/llap/materialized_view_cluster.q.out index 2f57559da121..afb6063bf899 100644 --- a/ql/src/test/results/clientpositive/llap/materialized_view_cluster.q.out +++ b/ql/src/test/results/clientpositive/llap/materialized_view_cluster.q.out @@ -490,18 +490,18 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src_txn - filterExpr: ((ROW__ID.writeid > 1L) and (UDFToDouble(key) > 200.0D) and (UDFToDouble(key) < 250.0D)) (type: boolean) + filterExpr: ((UDFToDouble(key) > 200.0D) and (UDFToDouble(key) < 250.0D) and (ROW__ID.writeid <= 1L) is not true) (type: boolean) Statistics: Num rows: 501 Data size: 90180 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: ((ROW__ID.writeid > 1L) and (UDFToDouble(key) > 200.0D) and (UDFToDouble(key) < 250.0D)) (type: boolean) - Statistics: Num rows: 18 Data size: 3240 Basic stats: COMPLETE Column stats: COMPLETE + predicate: ((UDFToDouble(key) > 200.0D) and (UDFToDouble(key) < 250.0D) and (ROW__ID.writeid <= 1L) is not true) (type: boolean) + Statistics: Num rows: 27 Data size: 4860 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: value (type: string), key (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 18 Data size: 3240 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 27 Data size: 4860 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 18 Data size: 3240 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 27 Data size: 4860 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -510,10 +510,10 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: value, key - Statistics: Num rows: 18 Data size: 3240 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 27 Data size: 4860 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: max(length(value)), avg(COALESCE(length(value),0)), count(1), count(value), compute_bit_vector_hll(value), max(length(key)), avg(COALESCE(length(key),0)), count(key), compute_bit_vector_hll(key) - minReductionHashAggr: 0.9444444 + minReductionHashAggr: 0.962963 mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 Statistics: Num rows: 1 Data size: 472 Basic stats: COMPLETE Column stats: COMPLETE @@ -796,21 +796,21 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src_txn - filterExpr: ((ROW__ID.writeid > 2L) and (UDFToDouble(key) > 200.0D) and (UDFToDouble(key) < 250.0D)) (type: boolean) + filterExpr: ((UDFToDouble(key) > 200.0D) and (UDFToDouble(key) < 250.0D) and (ROW__ID.writeid <= 2L) is not true) (type: boolean) Statistics: Num rows: 502 Data size: 90862 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: ((ROW__ID.writeid > 2L) and (UDFToDouble(key) > 200.0D) and (UDFToDouble(key) < 250.0D)) (type: boolean) - Statistics: Num rows: 18 Data size: 3258 Basic stats: COMPLETE Column stats: COMPLETE + predicate: ((UDFToDouble(key) > 200.0D) and (UDFToDouble(key) < 250.0D) and (ROW__ID.writeid <= 2L) is not true) (type: boolean) + Statistics: Num rows: 27 Data size: 4887 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 18 Data size: 3258 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 27 Data size: 4887 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) null sort order: z sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 18 Data size: 3258 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 27 Data size: 4887 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Execution mode: vectorized, llap LLAP IO: may be used (ACID table) @@ -845,14 +845,14 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 18 Data size: 3258 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 27 Data size: 4887 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string), _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 18 Data size: 3258 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 27 Data size: 4887 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 18 Data size: 3258 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 27 Data size: 4887 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -861,10 +861,10 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: value, key - Statistics: Num rows: 18 Data size: 3258 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 27 Data size: 4887 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: max(length(value)), avg(COALESCE(length(value),0)), count(1), count(value), compute_bit_vector_hll(value), max(length(key)), avg(COALESCE(length(key),0)), count(key), compute_bit_vector_hll(key) - minReductionHashAggr: 0.9444444 + minReductionHashAggr: 0.962963 mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 Statistics: Num rows: 1 Data size: 472 Basic stats: COMPLETE Column stats: COMPLETE diff --git a/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_3.q.out b/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_3.q.out index e0718e569551..8b820b73a3db 100644 --- a/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_3.q.out +++ b/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_3.q.out @@ -542,10 +542,10 @@ STAGE PLANS: Map Operator Tree: TableScan alias: cmv_basetable_2 - filterExpr: ((ROW__ID.writeid > 1L) and (c > 10) and a is not null) (type: boolean) + filterExpr: ((c > 10) and (ROW__ID.writeid <= 1L) is not true and a is not null) (type: boolean) Statistics: Num rows: 3 Data size: 348 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: ((ROW__ID.writeid > 1L) and (c > 10) and a is not null) (type: boolean) + predicate: ((c > 10) and (ROW__ID.writeid <= 1L) is not true and a is not null) (type: boolean) Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: a (type: int), c (type: decimal(10,2)) diff --git a/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_4.q.out b/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_4.q.out index 3b05f9b86341..b439c1f21135 100644 --- a/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_4.q.out +++ b/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_4.q.out @@ -801,10 +801,10 @@ STAGE PLANS: Map Operator Tree: TableScan alias: cmv_basetable_2_n2 - filterExpr: ((ROW__ID.writeid > 1L) and (c > 10) and a is not null) (type: boolean) + filterExpr: ((c > 10) and (ROW__ID.writeid <= 1L) is not true and a is not null) (type: boolean) Statistics: Num rows: 3 Data size: 360 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: ((ROW__ID.writeid > 1L) and (c > 10) and a is not null) (type: boolean) + predicate: ((c > 10) and (ROW__ID.writeid <= 1L) is not true and a is not null) (type: boolean) Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: a (type: int), c (type: decimal(10,2)), d (type: int) @@ -1913,10 +1913,10 @@ STAGE PLANS: Map Operator Tree: TableScan alias: cmv_basetable_2_n2 - filterExpr: ((ROW__ID.writeid > 4L) and (c > 10) and a is not null) (type: boolean) + filterExpr: ((c > 10) and (ROW__ID.writeid <= 4L) is not true and a is not null) (type: boolean) Statistics: Num rows: 3 Data size: 360 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: ((ROW__ID.writeid > 4L) and (c > 10) and a is not null) (type: boolean) + predicate: ((c > 10) and (ROW__ID.writeid <= 4L) is not true and a is not null) (type: boolean) Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: a (type: int), c (type: decimal(10,2)), d (type: int) diff --git a/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_5.q.out b/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_5.q.out index bb85ddc371db..1dddc405cff5 100644 --- a/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_5.q.out +++ b/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_5.q.out @@ -266,21 +266,21 @@ STAGE PLANS: Map Operator Tree: TableScan alias: cmv_basetable_2_n3 - filterExpr: ((ROW__ID.writeid > 1L) and (c > 10) and a is not null) (type: boolean) + filterExpr: ((c > 10) and (ROW__ID.writeid <= 1L) is not true and a is not null) (type: boolean) Statistics: Num rows: 4 Data size: 464 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: ((ROW__ID.writeid > 1L) and (c > 10) and a is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: COMPLETE + predicate: ((c > 10) and (ROW__ID.writeid <= 1L) is not true and a is not null) (type: boolean) + Statistics: Num rows: 2 Data size: 232 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: a (type: int), c (type: decimal(10,2)) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 232 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) null sort order: z sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 232 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: decimal(10,2)) Execution mode: llap LLAP IO: may be used (ACID table) @@ -294,14 +294,14 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col2 - Statistics: Num rows: 2 Data size: 232 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 464 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col2 (type: decimal(10,2)) outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 232 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 464 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 232 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 464 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat @@ -311,10 +311,10 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: decimal(10,2)) outputColumnNames: a, c - Statistics: Num rows: 2 Data size: 232 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 464 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: min(a), max(a), count(1), count(a), compute_bit_vector_hll(a), min(c), max(c), count(c), compute_bit_vector_hll(c) - minReductionHashAggr: 0.5 + minReductionHashAggr: 0.75 mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 Statistics: Num rows: 1 Data size: 544 Basic stats: COMPLETE Column stats: COMPLETE @@ -1037,10 +1037,10 @@ STAGE PLANS: Map Operator Tree: TableScan alias: cmv_basetable_2_n3 - filterExpr: ((ROW__ID.writeid > 4L) and (c > 10) and a is not null) (type: boolean) + filterExpr: ((c > 10) and (ROW__ID.writeid <= 4L) is not true and a is not null) (type: boolean) Statistics: Num rows: 3 Data size: 348 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: ((ROW__ID.writeid > 4L) and (c > 10) and a is not null) (type: boolean) + predicate: ((c > 10) and (ROW__ID.writeid <= 4L) is not true and a is not null) (type: boolean) Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: a (type: int), c (type: decimal(10,2)) diff --git a/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_7.q.out b/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_7.q.out index 7c3ba78c396f..e74fcae7002a 100644 --- a/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_7.q.out +++ b/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_7.q.out @@ -108,7 +108,7 @@ HiveProject(t1.a=[$3], _c1=[CASE(IS NULL($1), $4, IS NULL($4), $1, +($4, $1))]) HiveTableScan(table=[[default, mat1]], table:alias=[default.mat1]) HiveProject(a=[$0], $f1=[$1]) HiveAggregate(group=[{0}], agg#0=[count()]) - HiveFilter(condition=[<(2, $5.writeid)]) + HiveFilter(condition=[IS NOT TRUE(>=(2, $5.writeid))]) HiveTableScan(table=[[default, t1]], table:alias=[t1]) PREHOOK: query: explain @@ -170,28 +170,28 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1 - filterExpr: (ROW__ID.writeid > 2L) (type: boolean) + filterExpr: (ROW__ID.writeid <= 2L) is not true (type: boolean) Statistics: Num rows: 11 Data size: 900 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: (ROW__ID.writeid > 2L) (type: boolean) - Statistics: Num rows: 3 Data size: 270 Basic stats: COMPLETE Column stats: COMPLETE + predicate: (ROW__ID.writeid <= 2L) is not true (type: boolean) + Statistics: Num rows: 5 Data size: 450 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: a (type: char(15)) outputColumnNames: a - Statistics: Num rows: 3 Data size: 270 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 450 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: a (type: char(15)) minReductionHashAggr: 0.4 mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 294 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 392 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: char(15)) null sort order: z sort order: + Map-reduce partition columns: _col0 (type: char(15)) - Statistics: Num rows: 3 Data size: 294 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 392 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized, llap LLAP IO: may be used (ACID table) @@ -206,7 +206,7 @@ STAGE PLANS: 1 _col0 (type: char(15)) nullSafes: [true] outputColumnNames: _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 4 Data size: 744 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 6 Data size: 1028 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: _col2 (type: boolean) Statistics: Num rows: 1 Data size: 186 Basic stats: COMPLETE Column stats: COMPLETE @@ -253,14 +253,14 @@ STAGE PLANS: value expressions: _col0 (type: int), _col1 (type: struct), _col2 (type: bigint), _col3 (type: bigint), _col4 (type: binary), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: bigint), _col8 (type: binary) Filter Operator predicate: _col2 is null (type: boolean) - Statistics: Num rows: 1 Data size: 186 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 372 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col4 (type: char(15)), CASE WHEN (_col1 is null) THEN (_col5) WHEN (_col5 is null) THEN (_col1) ELSE ((_col5 + _col1)) END (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 98 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 196 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 98 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 196 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat @@ -270,10 +270,10 @@ STAGE PLANS: Select Operator expressions: _col0 (type: char(15)), _col1 (type: bigint) outputColumnNames: a, _c1 - Statistics: Num rows: 1 Data size: 98 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 196 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: max(length(a)), avg(COALESCE(length(a),0)), count(1), count(a), compute_bit_vector_hll(a), min(_c1), max(_c1), count(_c1), compute_bit_vector_hll(_c1) - minReductionHashAggr: 0.4 + minReductionHashAggr: 0.5 mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 Statistics: Num rows: 1 Data size: 408 Basic stats: COMPLETE Column stats: COMPLETE @@ -344,13 +344,13 @@ STAGE PLANS: keys: KEY._col0 (type: char(15)) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 294 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 392 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: char(15)) null sort order: z sort order: + Map-reduce partition columns: _col0 (type: char(15)) - Statistics: Num rows: 3 Data size: 294 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 392 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Stage: Stage-4 diff --git a/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_8.q.out b/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_8.q.out index 68eba9e63600..81e00f3b3971 100644 --- a/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_8.q.out +++ b/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_8.q.out @@ -197,23 +197,23 @@ STAGE PLANS: Map Operator Tree: TableScan alias: cmv_basetable_2_n3 - filterExpr: ((ROW__ID.writeid > 1L) and (c > 10) and a is not null) (type: boolean) + filterExpr: ((c > 10) and (ROW__ID.writeid <= 1L) is not true and a is not null) (type: boolean) properties: insertonly.fetch.bucketid TRUE Statistics: Num rows: 4 Data size: 464 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: ((ROW__ID.writeid > 1L) and (c > 10) and a is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: COMPLETE + predicate: ((c > 10) and (ROW__ID.writeid <= 1L) is not true and a is not null) (type: boolean) + Statistics: Num rows: 2 Data size: 232 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: a (type: int), c (type: decimal(10,2)) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 232 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) null sort order: z sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 232 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: decimal(10,2)) Execution mode: vectorized, llap LLAP IO: may be used (ACID table) @@ -227,14 +227,14 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col2 - Statistics: Num rows: 2 Data size: 232 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 464 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col2 (type: decimal(10,2)) outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 232 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 464 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 232 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 464 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat @@ -244,10 +244,10 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: decimal(10,2)) outputColumnNames: a, c - Statistics: Num rows: 2 Data size: 232 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 464 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: min(a), max(a), count(1), count(a), compute_bit_vector_hll(a), min(c), max(c), count(c), compute_bit_vector_hll(c) - minReductionHashAggr: 0.5 + minReductionHashAggr: 0.75 mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 Statistics: Num rows: 1 Data size: 544 Basic stats: COMPLETE Column stats: COMPLETE diff --git a/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_nulls.q.out b/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_nulls.q.out index adf42999c5f7..a06845287444 100644 --- a/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_nulls.q.out +++ b/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_nulls.q.out @@ -123,7 +123,7 @@ HiveProject(t1.a=[$6], t1.b=[$7], _c2=[CASE(IS NULL($2), $8, IS NULL($8), $2, +( HiveTableScan(table=[[default, mat1]], table:alias=[default.mat1]) HiveProject(a=[$0], b=[$1], $f2=[$2], $f3=[$3], $f4=[$4]) HiveAggregate(group=[{0, 1}], agg#0=[sum($3)], agg#1=[min($3)], agg#2=[max($3)]) - HiveFilter(condition=[AND(<(1, $6.writeid), >($2, 10:DECIMAL(2, 0)))]) + HiveFilter(condition=[AND(>($2, 10:DECIMAL(2, 0)), IS NOT TRUE(>=(1, $6.writeid)))]) HiveTableScan(table=[[default, t1]], table:alias=[t1]) PREHOOK: query: explain @@ -186,28 +186,28 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1 - filterExpr: ((ROW__ID.writeid > 1L) and (c > 10)) (type: boolean) + filterExpr: ((c > 10) and (ROW__ID.writeid <= 1L) is not true) (type: boolean) Statistics: Num rows: 22 Data size: 4986 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: ((ROW__ID.writeid > 1L) and (c > 10)) (type: boolean) - Statistics: Num rows: 7 Data size: 1626 Basic stats: COMPLETE Column stats: COMPLETE + predicate: ((c > 10) and (ROW__ID.writeid <= 1L) is not true) (type: boolean) + Statistics: Num rows: 11 Data size: 2554 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: a (type: int), b (type: varchar(256)), d (type: int) outputColumnNames: a, b, d - Statistics: Num rows: 7 Data size: 1626 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11 Data size: 2554 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(d), min(d), max(d) keys: a (type: int), b (type: varchar(256)) minReductionHashAggr: 0.4 mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 7 Data size: 930 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11 Data size: 1462 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: varchar(256)) null sort order: zz sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: varchar(256)) - Statistics: Num rows: 7 Data size: 930 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11 Data size: 1462 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: bigint), _col3 (type: int), _col4 (type: int) Execution mode: llap LLAP IO: may be used (ACID table) @@ -222,7 +222,7 @@ STAGE PLANS: 1 _col0 (type: int), _col1 (type: varchar(256)) nullSafes: [true, true] outputColumnNames: _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 10 Data size: 2052 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 20 Data size: 3580 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: _col5 (type: boolean) Statistics: Num rows: 1 Data size: 230 Basic stats: COMPLETE Column stats: COMPLETE @@ -269,14 +269,14 @@ STAGE PLANS: value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint), _col3 (type: bigint), _col4 (type: binary), _col5 (type: int), _col6 (type: struct), _col7 (type: bigint), _col8 (type: binary), _col9 (type: bigint), _col10 (type: bigint), _col11 (type: bigint), _col12 (type: binary), _col13 (type: int), _col14 (type: int), _col15 (type: bigint), _col16 (type: binary), _col17 (type: int), _col18 (type: int), _col19 (type: bigint), _col20 (type: binary) Filter Operator predicate: _col5 is null (type: boolean) - Statistics: Num rows: 3 Data size: 674 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11 Data size: 2014 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col7 (type: int), _col8 (type: varchar(256)), CASE WHEN (_col2 is null) THEN (_col9) WHEN (_col9 is null) THEN (_col2) ELSE ((_col9 + _col2)) END (type: bigint), CASE WHEN (_col3 is null) THEN (_col10) WHEN (_col10 is null) THEN (_col3) ELSE (if((_col10 < _col3), _col10, _col3)) END (type: int), CASE WHEN (_col4 is null) THEN (_col11) WHEN (_col11 is null) THEN (_col4) ELSE (if((_col11 > _col4), _col11, _col4)) END (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 3 Data size: 386 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11 Data size: 1358 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 3 Data size: 386 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11 Data size: 1358 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat @@ -286,10 +286,10 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: varchar(256)), _col2 (type: bigint), _col3 (type: int), _col4 (type: int) outputColumnNames: a, b, _c2, _c3, _c4 - Statistics: Num rows: 3 Data size: 386 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11 Data size: 1358 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: min(a), max(a), count(1), count(a), compute_bit_vector_hll(a), max(length(b)), avg(COALESCE(length(b),0)), count(b), compute_bit_vector_hll(b), min(_c2), max(_c2), count(_c2), compute_bit_vector_hll(_c2), min(_c3), max(_c3), count(_c3), compute_bit_vector_hll(_c3), min(_c4), max(_c4), count(_c4), compute_bit_vector_hll(_c4) - minReductionHashAggr: 0.6666666 + minReductionHashAggr: 0.9090909 mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20 Statistics: Num rows: 1 Data size: 888 Basic stats: COMPLETE Column stats: COMPLETE @@ -360,13 +360,13 @@ STAGE PLANS: keys: KEY._col0 (type: int), KEY._col1 (type: varchar(256)) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 7 Data size: 930 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11 Data size: 1462 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: varchar(256)) null sort order: zz sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: varchar(256)) - Statistics: Num rows: 7 Data size: 930 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11 Data size: 1462 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: bigint), _col3 (type: int), _col4 (type: int) Stage: Stage-4 diff --git a/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_one_key_gby.q.out b/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_one_key_gby.q.out index 25fe6711ccc5..c869be4b56e9 100644 --- a/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_one_key_gby.q.out +++ b/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_one_key_gby.q.out @@ -171,10 +171,10 @@ STAGE PLANS: Map Operator Tree: TableScan alias: cmv_basetable_2_n2 - filterExpr: ((ROW__ID.writeid > 1L) and (c > 10) and a is not null) (type: boolean) + filterExpr: ((c > 10) and (ROW__ID.writeid <= 1L) is not true and a is not null) (type: boolean) Statistics: Num rows: 3 Data size: 360 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: ((ROW__ID.writeid > 1L) and (c > 10) and a is not null) (type: boolean) + predicate: ((c > 10) and (ROW__ID.writeid <= 1L) is not true and a is not null) (type: boolean) Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: a (type: int), d (type: int) diff --git a/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_rebuild_dummy.q.out b/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_rebuild_dummy.q.out index 7e951ad1c638..246a0f48163b 100644 --- a/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_rebuild_dummy.q.out +++ b/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_rebuild_dummy.q.out @@ -542,10 +542,10 @@ STAGE PLANS: Map Operator Tree: TableScan alias: cmv_basetable_2_n0 - filterExpr: ((ROW__ID.writeid > 1L) and (c > 10) and a is not null) (type: boolean) + filterExpr: ((c > 10) and (ROW__ID.writeid <= 1L) is not true and a is not null) (type: boolean) Statistics: Num rows: 3 Data size: 348 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: ((ROW__ID.writeid > 1L) and (c > 10) and a is not null) (type: boolean) + predicate: ((c > 10) and (ROW__ID.writeid <= 1L) is not true and a is not null) (type: boolean) Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: a (type: int), c (type: decimal(10,2)) diff --git a/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_time_window.q.out b/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_time_window.q.out index 4ebaf7f33a97..6703c4c0b044 100644 --- a/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_time_window.q.out +++ b/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_time_window.q.out @@ -676,10 +676,10 @@ STAGE PLANS: Map Operator Tree: TableScan alias: cmv_basetable_2_n1 - filterExpr: ((ROW__ID.writeid > 1L) and (c > 10) and a is not null) (type: boolean) + filterExpr: ((c > 10) and (ROW__ID.writeid <= 1L) is not true and a is not null) (type: boolean) Statistics: Num rows: 3 Data size: 348 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: ((ROW__ID.writeid > 1L) and (c > 10) and a is not null) (type: boolean) + predicate: ((c > 10) and (ROW__ID.writeid <= 1L) is not true and a is not null) (type: boolean) Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: a (type: int), c (type: decimal(10,2)) diff --git a/ql/src/test/results/clientpositive/llap/materialized_view_distribute_sort.q.out b/ql/src/test/results/clientpositive/llap/materialized_view_distribute_sort.q.out index c86001ada212..26c15292f9f6 100644 --- a/ql/src/test/results/clientpositive/llap/materialized_view_distribute_sort.q.out +++ b/ql/src/test/results/clientpositive/llap/materialized_view_distribute_sort.q.out @@ -672,18 +672,18 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src_txn - filterExpr: ((ROW__ID.writeid > 1L) and (UDFToDouble(key) > 200.0D) and (UDFToDouble(key) < 250.0D)) (type: boolean) + filterExpr: ((UDFToDouble(key) > 200.0D) and (UDFToDouble(key) < 250.0D) and (ROW__ID.writeid <= 1L) is not true) (type: boolean) Statistics: Num rows: 501 Data size: 90180 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: ((ROW__ID.writeid > 1L) and (UDFToDouble(key) > 200.0D) and (UDFToDouble(key) < 250.0D)) (type: boolean) - Statistics: Num rows: 18 Data size: 3240 Basic stats: COMPLETE Column stats: COMPLETE + predicate: ((UDFToDouble(key) > 200.0D) and (UDFToDouble(key) < 250.0D) and (ROW__ID.writeid <= 1L) is not true) (type: boolean) + Statistics: Num rows: 27 Data size: 4860 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: value (type: string), key (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 18 Data size: 3240 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 27 Data size: 4860 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 18 Data size: 3240 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 27 Data size: 4860 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -692,10 +692,10 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: value, key - Statistics: Num rows: 18 Data size: 3240 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 27 Data size: 4860 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: max(length(value)), avg(COALESCE(length(value),0)), count(1), count(value), compute_bit_vector_hll(value), max(length(key)), avg(COALESCE(length(key),0)), count(key), compute_bit_vector_hll(key) - minReductionHashAggr: 0.9444444 + minReductionHashAggr: 0.962963 mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 Statistics: Num rows: 1 Data size: 472 Basic stats: COMPLETE Column stats: COMPLETE @@ -1219,21 +1219,21 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src_txn - filterExpr: ((ROW__ID.writeid > 2L) and (UDFToDouble(key) > 200.0D) and (UDFToDouble(key) < 250.0D)) (type: boolean) + filterExpr: ((UDFToDouble(key) > 200.0D) and (UDFToDouble(key) < 250.0D) and (ROW__ID.writeid <= 2L) is not true) (type: boolean) Statistics: Num rows: 502 Data size: 90862 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: ((ROW__ID.writeid > 2L) and (UDFToDouble(key) > 200.0D) and (UDFToDouble(key) < 250.0D)) (type: boolean) - Statistics: Num rows: 18 Data size: 3258 Basic stats: COMPLETE Column stats: COMPLETE + predicate: ((UDFToDouble(key) > 200.0D) and (UDFToDouble(key) < 250.0D) and (ROW__ID.writeid <= 2L) is not true) (type: boolean) + Statistics: Num rows: 27 Data size: 4887 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 18 Data size: 3258 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 27 Data size: 4887 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) null sort order: z sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 18 Data size: 3258 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 27 Data size: 4887 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Execution mode: vectorized, llap LLAP IO: may be used (ACID table) @@ -1268,14 +1268,14 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 18 Data size: 3258 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 27 Data size: 4887 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string), _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 18 Data size: 3258 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 27 Data size: 4887 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 18 Data size: 3258 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 27 Data size: 4887 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -1284,10 +1284,10 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: value, key - Statistics: Num rows: 18 Data size: 3258 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 27 Data size: 4887 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: max(length(value)), avg(COALESCE(length(value),0)), count(1), count(value), compute_bit_vector_hll(value), max(length(key)), avg(COALESCE(length(key),0)), count(key), compute_bit_vector_hll(key) - minReductionHashAggr: 0.9444444 + minReductionHashAggr: 0.962963 mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 Statistics: Num rows: 1 Data size: 472 Basic stats: COMPLETE Column stats: COMPLETE diff --git a/ql/src/test/results/clientpositive/llap/materialized_view_parquet.q.out b/ql/src/test/results/clientpositive/llap/materialized_view_parquet.q.out index 84c858d69f7b..dabe42d7828e 100644 --- a/ql/src/test/results/clientpositive/llap/materialized_view_parquet.q.out +++ b/ql/src/test/results/clientpositive/llap/materialized_view_parquet.q.out @@ -849,30 +849,30 @@ STAGE PLANS: Map Operator Tree: TableScan alias: emps_parquet_n3 - filterExpr: (ROW__ID.writeid > 3L) (type: boolean) + filterExpr: (ROW__ID.writeid <= 3L) is not true (type: boolean) properties: insertonly.fetch.bucketid TRUE Statistics: Num rows: 6 Data size: 588 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: (ROW__ID.writeid > 3L) (type: boolean) - Statistics: Num rows: 2 Data size: 196 Basic stats: COMPLETE Column stats: COMPLETE + predicate: (ROW__ID.writeid <= 3L) is not true (type: boolean) + Statistics: Num rows: 3 Data size: 294 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: empid (type: int), name (type: varchar(256)), salary (type: float) outputColumnNames: empid, name, salary - Statistics: Num rows: 2 Data size: 196 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3 Data size: 294 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(), sum(empid) keys: name (type: varchar(256)), salary (type: float) minReductionHashAggr: 0.4 mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2 Data size: 220 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3 Data size: 330 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: varchar(256)), _col1 (type: float) null sort order: zz sort order: ++ Map-reduce partition columns: _col0 (type: varchar(256)), _col1 (type: float) - Statistics: Num rows: 2 Data size: 220 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3 Data size: 330 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: bigint), _col3 (type: bigint) Execution mode: vectorized, llap LLAP IO: all inputs (cache only) @@ -909,7 +909,7 @@ STAGE PLANS: keys: KEY._col0 (type: varchar(256)), KEY._col1 (type: float) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2 Data size: 220 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3 Data size: 330 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col2), sum(_col3) keys: _col0 (type: varchar(256)), _col1 (type: float) diff --git a/ql/src/test/results/clientpositive/llap/materialized_view_partition_cluster.q.out b/ql/src/test/results/clientpositive/llap/materialized_view_partition_cluster.q.out index 2a59f7983fa3..2f09d060782c 100644 --- a/ql/src/test/results/clientpositive/llap/materialized_view_partition_cluster.q.out +++ b/ql/src/test/results/clientpositive/llap/materialized_view_partition_cluster.q.out @@ -978,18 +978,18 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src_txn - filterExpr: ((ROW__ID.writeid > 1L) and (UDFToDouble(key) > 200.0D) and (UDFToDouble(key) < 250.0D)) (type: boolean) + filterExpr: ((UDFToDouble(key) > 200.0D) and (UDFToDouble(key) < 250.0D) and (ROW__ID.writeid <= 1L) is not true) (type: boolean) Statistics: Num rows: 501 Data size: 90180 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: ((ROW__ID.writeid > 1L) and (UDFToDouble(key) > 200.0D) and (UDFToDouble(key) < 250.0D)) (type: boolean) - Statistics: Num rows: 18 Data size: 3240 Basic stats: COMPLETE Column stats: COMPLETE + predicate: ((UDFToDouble(key) > 200.0D) and (UDFToDouble(key) < 250.0D) and (ROW__ID.writeid <= 1L) is not true) (type: boolean) + Statistics: Num rows: 27 Data size: 4860 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: value (type: string), key (type: string), (UDFToDouble(key) + 100.0D) (type: double) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 18 Data size: 3384 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 27 Data size: 5076 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 18 Data size: 3384 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 27 Data size: 5076 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat @@ -998,20 +998,20 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: double) outputColumnNames: value, key, partkey - Statistics: Num rows: 18 Data size: 3384 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 27 Data size: 5076 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: max(length(value)), avg(COALESCE(length(value),0)), count(1), count(value), compute_bit_vector_hll(value), max(length(key)), avg(COALESCE(length(key),0)), count(key), compute_bit_vector_hll(key) keys: partkey (type: double) minReductionHashAggr: 0.4 mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 - Statistics: Num rows: 18 Data size: 8640 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 27 Data size: 12960 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: double) null sort order: z sort order: + Map-reduce partition columns: _col0 (type: double) - Statistics: Num rows: 18 Data size: 8640 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 27 Data size: 12960 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: int), _col2 (type: struct), _col3 (type: bigint), _col4 (type: bigint), _col5 (type: binary), _col6 (type: int), _col7 (type: struct), _col8 (type: bigint), _col9 (type: binary) Execution mode: vectorized, llap LLAP IO: may be used (ACID table) @@ -1023,14 +1023,14 @@ STAGE PLANS: keys: KEY._col0 (type: double) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 - Statistics: Num rows: 18 Data size: 6192 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 27 Data size: 9288 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 'STRING' (type: string), UDFToLong(COALESCE(_col1,0)) (type: bigint), COALESCE(_col2,0) (type: double), (_col3 - _col4) (type: bigint), COALESCE(ndv_compute_bit_vector(_col5),0) (type: bigint), _col5 (type: binary), 'STRING' (type: string), UDFToLong(COALESCE(_col6,0)) (type: bigint), COALESCE(_col7,0) (type: double), (_col3 - _col8) (type: bigint), COALESCE(ndv_compute_bit_vector(_col9),0) (type: bigint), _col9 (type: binary), _col0 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 - Statistics: Num rows: 18 Data size: 9720 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 27 Data size: 14580 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 18 Data size: 9720 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 27 Data size: 14580 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1400,21 +1400,21 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src_txn - filterExpr: ((ROW__ID.writeid > 2L) and (UDFToDouble(key) > 200.0D) and (UDFToDouble(key) < 250.0D)) (type: boolean) + filterExpr: ((UDFToDouble(key) > 200.0D) and (UDFToDouble(key) < 250.0D) and (ROW__ID.writeid <= 2L) is not true) (type: boolean) Statistics: Num rows: 502 Data size: 90862 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: ((ROW__ID.writeid > 2L) and (UDFToDouble(key) > 200.0D) and (UDFToDouble(key) < 250.0D)) (type: boolean) - Statistics: Num rows: 18 Data size: 3258 Basic stats: COMPLETE Column stats: COMPLETE + predicate: ((UDFToDouble(key) > 200.0D) and (UDFToDouble(key) < 250.0D) and (ROW__ID.writeid <= 2L) is not true) (type: boolean) + Statistics: Num rows: 27 Data size: 4887 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string), (UDFToDouble(key) + 100.0D) (type: double) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 18 Data size: 3402 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 27 Data size: 5103 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) null sort order: z sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 18 Data size: 3402 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 27 Data size: 5103 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col2 (type: double) Execution mode: vectorized, llap LLAP IO: may be used (ACID table) @@ -1449,14 +1449,14 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 18 Data size: 3402 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 27 Data size: 5103 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string), _col0 (type: string), _col2 (type: double) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 18 Data size: 3402 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 27 Data size: 5103 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 18 Data size: 3402 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 27 Data size: 5103 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat @@ -1465,20 +1465,20 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: double) outputColumnNames: value, key, partkey - Statistics: Num rows: 18 Data size: 3402 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 27 Data size: 5103 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: max(length(value)), avg(COALESCE(length(value),0)), count(1), count(value), compute_bit_vector_hll(value), max(length(key)), avg(COALESCE(length(key),0)), count(key), compute_bit_vector_hll(key) keys: partkey (type: double) minReductionHashAggr: 0.4 mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 - Statistics: Num rows: 18 Data size: 8640 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 27 Data size: 12960 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: double) null sort order: z sort order: + Map-reduce partition columns: _col0 (type: double) - Statistics: Num rows: 18 Data size: 8640 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 27 Data size: 12960 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: int), _col2 (type: struct), _col3 (type: bigint), _col4 (type: bigint), _col5 (type: binary), _col6 (type: int), _col7 (type: struct), _col8 (type: bigint), _col9 (type: binary) Reducer 3 Execution mode: vectorized, llap @@ -1488,14 +1488,14 @@ STAGE PLANS: keys: KEY._col0 (type: double) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 - Statistics: Num rows: 18 Data size: 6192 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 27 Data size: 9288 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 'STRING' (type: string), UDFToLong(COALESCE(_col1,0)) (type: bigint), COALESCE(_col2,0) (type: double), (_col3 - _col4) (type: bigint), COALESCE(ndv_compute_bit_vector(_col5),0) (type: bigint), _col5 (type: binary), 'STRING' (type: string), UDFToLong(COALESCE(_col6,0)) (type: bigint), COALESCE(_col7,0) (type: double), (_col3 - _col8) (type: bigint), COALESCE(ndv_compute_bit_vector(_col9),0) (type: bigint), _col9 (type: binary), _col0 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 - Statistics: Num rows: 18 Data size: 9720 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 27 Data size: 14580 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 18 Data size: 9720 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 27 Data size: 14580 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/materialized_view_partitioned.q.out b/ql/src/test/results/clientpositive/llap/materialized_view_partitioned.q.out index b264b6acbd9a..c57c4817c7c8 100644 --- a/ql/src/test/results/clientpositive/llap/materialized_view_partitioned.q.out +++ b/ql/src/test/results/clientpositive/llap/materialized_view_partitioned.q.out @@ -652,39 +652,39 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src_txn - filterExpr: ((ROW__ID.writeid > 1L) and (UDFToDouble(key) > 200.0D) and (UDFToDouble(key) < 250.0D)) (type: boolean) + filterExpr: ((UDFToDouble(key) > 200.0D) and (UDFToDouble(key) < 250.0D) and (ROW__ID.writeid <= 1L) is not true) (type: boolean) Statistics: Num rows: 501 Data size: 90180 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: ((ROW__ID.writeid > 1L) and (UDFToDouble(key) > 200.0D) and (UDFToDouble(key) < 250.0D)) (type: boolean) - Statistics: Num rows: 18 Data size: 3240 Basic stats: COMPLETE Column stats: COMPLETE + predicate: ((UDFToDouble(key) > 200.0D) and (UDFToDouble(key) < 250.0D) and (ROW__ID.writeid <= 1L) is not true) (type: boolean) + Statistics: Num rows: 27 Data size: 4860 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: value (type: string), key (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 18 Data size: 3240 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 27 Data size: 4860 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) null sort order: z sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 18 Data size: 3240 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 27 Data size: 4860 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string) Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: value, key - Statistics: Num rows: 18 Data size: 3240 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 27 Data size: 4860 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: max(length(value)), avg(COALESCE(length(value),0)), count(1), count(value), compute_bit_vector_hll(value) keys: key (type: string) minReductionHashAggr: 0.4 mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 18 Data size: 5886 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 27 Data size: 8829 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) null sort order: z sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 18 Data size: 5886 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 27 Data size: 8829 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: int), _col2 (type: struct), _col3 (type: bigint), _col4 (type: bigint), _col5 (type: binary) Execution mode: vectorized, llap LLAP IO: may be used (ACID table) @@ -697,7 +697,7 @@ STAGE PLANS: File Output Operator compressed: false Dp Sort State: PARTITION_SORTED - Statistics: Num rows: 18 Data size: 3240 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 27 Data size: 4860 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat @@ -711,14 +711,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 18 Data size: 4662 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 27 Data size: 6993 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 'STRING' (type: string), UDFToLong(COALESCE(_col1,0)) (type: bigint), COALESCE(_col2,0) (type: double), (_col3 - _col4) (type: bigint), COALESCE(ndv_compute_bit_vector(_col5),0) (type: bigint), _col5 (type: binary), _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 18 Data size: 6354 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 27 Data size: 9531 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 18 Data size: 6354 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 27 Data size: 9531 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -991,21 +991,21 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src_txn - filterExpr: ((ROW__ID.writeid > 2L) and (UDFToDouble(key) > 200.0D) and (UDFToDouble(key) < 250.0D)) (type: boolean) + filterExpr: ((UDFToDouble(key) > 200.0D) and (UDFToDouble(key) < 250.0D) and (ROW__ID.writeid <= 2L) is not true) (type: boolean) Statistics: Num rows: 502 Data size: 90862 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: ((ROW__ID.writeid > 2L) and (UDFToDouble(key) > 200.0D) and (UDFToDouble(key) < 250.0D)) (type: boolean) - Statistics: Num rows: 18 Data size: 3258 Basic stats: COMPLETE Column stats: COMPLETE + predicate: ((UDFToDouble(key) > 200.0D) and (UDFToDouble(key) < 250.0D) and (ROW__ID.writeid <= 2L) is not true) (type: boolean) + Statistics: Num rows: 27 Data size: 4887 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 18 Data size: 3258 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 27 Data size: 4887 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) null sort order: z sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 18 Data size: 3258 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 27 Data size: 4887 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Execution mode: vectorized, llap LLAP IO: may be used (ACID table) @@ -1040,35 +1040,35 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 18 Data size: 3258 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 27 Data size: 4887 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string), _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 18 Data size: 3258 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 27 Data size: 4887 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) null sort order: z sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 18 Data size: 3258 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 27 Data size: 4887 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string) Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: value, key - Statistics: Num rows: 18 Data size: 3258 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 27 Data size: 4887 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: max(length(value)), avg(COALESCE(length(value),0)), count(1), count(value), compute_bit_vector_hll(value) keys: key (type: string) minReductionHashAggr: 0.4 mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 18 Data size: 5886 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 27 Data size: 8829 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) null sort order: z sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 18 Data size: 5886 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 27 Data size: 8829 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: int), _col2 (type: struct), _col3 (type: bigint), _col4 (type: bigint), _col5 (type: binary) Reducer 3 Execution mode: vectorized, llap @@ -1079,7 +1079,7 @@ STAGE PLANS: File Output Operator compressed: false Dp Sort State: PARTITION_SORTED - Statistics: Num rows: 18 Data size: 3258 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 27 Data size: 4887 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat @@ -1093,14 +1093,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 18 Data size: 4662 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 27 Data size: 6993 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 'STRING' (type: string), UDFToLong(COALESCE(_col1,0)) (type: bigint), COALESCE(_col2,0) (type: double), (_col3 - _col4) (type: bigint), COALESCE(ndv_compute_bit_vector(_col5),0) (type: bigint), _col5 (type: binary), _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 18 Data size: 6354 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 27 Data size: 9531 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 18 Data size: 6354 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 27 Data size: 9531 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/materialized_view_partitioned_2.q.out b/ql/src/test/results/clientpositive/llap/materialized_view_partitioned_2.q.out index 9d222fc5bd34..21bceb01fde5 100644 --- a/ql/src/test/results/clientpositive/llap/materialized_view_partitioned_2.q.out +++ b/ql/src/test/results/clientpositive/llap/materialized_view_partitioned_2.q.out @@ -549,137 +549,13 @@ POSTHOOK: Output: default@partition_mv_4 PREHOOK: query: EXPLAIN SELECT * FROM src_txn_2 where key > 224 and key < 226 PREHOOK: type: QUERY -PREHOOK: Input: default@partition_mv_2 -PREHOOK: Input: default@partition_mv_2@value=val_201 -PREHOOK: Input: default@partition_mv_2@value=val_202 -PREHOOK: Input: default@partition_mv_2@value=val_203 -PREHOOK: Input: default@partition_mv_2@value=val_205 -PREHOOK: Input: default@partition_mv_2@value=val_207 -PREHOOK: Input: default@partition_mv_2@value=val_208 -PREHOOK: Input: default@partition_mv_2@value=val_209 -PREHOOK: Input: default@partition_mv_2@value=val_213 -PREHOOK: Input: default@partition_mv_2@value=val_214 -PREHOOK: Input: default@partition_mv_2@value=val_216 -PREHOOK: Input: default@partition_mv_2@value=val_217 -PREHOOK: Input: default@partition_mv_2@value=val_218 -PREHOOK: Input: default@partition_mv_2@value=val_219 -PREHOOK: Input: default@partition_mv_2@value=val_221 -PREHOOK: Input: default@partition_mv_2@value=val_222 -PREHOOK: Input: default@partition_mv_2@value=val_223 -PREHOOK: Input: default@partition_mv_2@value=val_224 -PREHOOK: Input: default@partition_mv_2@value=val_226 -PREHOOK: Input: default@partition_mv_2@value=val_228 -PREHOOK: Input: default@partition_mv_2@value=val_229 -PREHOOK: Input: default@partition_mv_2@value=val_230 -PREHOOK: Input: default@partition_mv_2@value=val_233 -PREHOOK: Input: default@partition_mv_2@value=val_235 -PREHOOK: Input: default@partition_mv_2@value=val_237 -PREHOOK: Input: default@partition_mv_2@value=val_238 -PREHOOK: Input: default@partition_mv_2@value=val_239 -PREHOOK: Input: default@partition_mv_2@value=val_241 -PREHOOK: Input: default@partition_mv_2@value=val_242 -PREHOOK: Input: default@partition_mv_2@value=val_244 -PREHOOK: Input: default@partition_mv_2@value=val_247 -PREHOOK: Input: default@partition_mv_2@value=val_248 -PREHOOK: Input: default@partition_mv_2@value=val_249 -PREHOOK: Input: default@partition_mv_2@value=val_252 -PREHOOK: Input: default@partition_mv_2@value=val_255 -PREHOOK: Input: default@partition_mv_2@value=val_256 -PREHOOK: Input: default@partition_mv_2@value=val_257 -PREHOOK: Input: default@partition_mv_2@value=val_258 -PREHOOK: Input: default@partition_mv_2@value=val_260 -PREHOOK: Input: default@partition_mv_2@value=val_262 -PREHOOK: Input: default@partition_mv_2@value=val_263 -PREHOOK: Input: default@partition_mv_2@value=val_265 -PREHOOK: Input: default@partition_mv_2@value=val_266 -PREHOOK: Input: default@partition_mv_2@value=val_272 -PREHOOK: Input: default@partition_mv_2@value=val_273 -PREHOOK: Input: default@partition_mv_2@value=val_274 -PREHOOK: Input: default@partition_mv_2@value=val_275 -PREHOOK: Input: default@partition_mv_2@value=val_277 -PREHOOK: Input: default@partition_mv_2@value=val_278 -PREHOOK: Input: default@partition_mv_2@value=val_280 -PREHOOK: Input: default@partition_mv_2@value=val_281 -PREHOOK: Input: default@partition_mv_2@value=val_282 -PREHOOK: Input: default@partition_mv_2@value=val_283 -PREHOOK: Input: default@partition_mv_2@value=val_284 -PREHOOK: Input: default@partition_mv_2@value=val_285 -PREHOOK: Input: default@partition_mv_2@value=val_286 -PREHOOK: Input: default@partition_mv_2@value=val_287 -PREHOOK: Input: default@partition_mv_2@value=val_288 -PREHOOK: Input: default@partition_mv_2@value=val_289 -PREHOOK: Input: default@partition_mv_2@value=val_291 -PREHOOK: Input: default@partition_mv_2@value=val_292 -PREHOOK: Input: default@partition_mv_2@value=val_296 -PREHOOK: Input: default@partition_mv_2@value=val_298 +PREHOOK: Input: default@partition_mv_3 PREHOOK: Input: default@src_txn_2 #### A masked pattern was here #### POSTHOOK: query: EXPLAIN SELECT * FROM src_txn_2 where key > 224 and key < 226 POSTHOOK: type: QUERY -POSTHOOK: Input: default@partition_mv_2 -POSTHOOK: Input: default@partition_mv_2@value=val_201 -POSTHOOK: Input: default@partition_mv_2@value=val_202 -POSTHOOK: Input: default@partition_mv_2@value=val_203 -POSTHOOK: Input: default@partition_mv_2@value=val_205 -POSTHOOK: Input: default@partition_mv_2@value=val_207 -POSTHOOK: Input: default@partition_mv_2@value=val_208 -POSTHOOK: Input: default@partition_mv_2@value=val_209 -POSTHOOK: Input: default@partition_mv_2@value=val_213 -POSTHOOK: Input: default@partition_mv_2@value=val_214 -POSTHOOK: Input: default@partition_mv_2@value=val_216 -POSTHOOK: Input: default@partition_mv_2@value=val_217 -POSTHOOK: Input: default@partition_mv_2@value=val_218 -POSTHOOK: Input: default@partition_mv_2@value=val_219 -POSTHOOK: Input: default@partition_mv_2@value=val_221 -POSTHOOK: Input: default@partition_mv_2@value=val_222 -POSTHOOK: Input: default@partition_mv_2@value=val_223 -POSTHOOK: Input: default@partition_mv_2@value=val_224 -POSTHOOK: Input: default@partition_mv_2@value=val_226 -POSTHOOK: Input: default@partition_mv_2@value=val_228 -POSTHOOK: Input: default@partition_mv_2@value=val_229 -POSTHOOK: Input: default@partition_mv_2@value=val_230 -POSTHOOK: Input: default@partition_mv_2@value=val_233 -POSTHOOK: Input: default@partition_mv_2@value=val_235 -POSTHOOK: Input: default@partition_mv_2@value=val_237 -POSTHOOK: Input: default@partition_mv_2@value=val_238 -POSTHOOK: Input: default@partition_mv_2@value=val_239 -POSTHOOK: Input: default@partition_mv_2@value=val_241 -POSTHOOK: Input: default@partition_mv_2@value=val_242 -POSTHOOK: Input: default@partition_mv_2@value=val_244 -POSTHOOK: Input: default@partition_mv_2@value=val_247 -POSTHOOK: Input: default@partition_mv_2@value=val_248 -POSTHOOK: Input: default@partition_mv_2@value=val_249 -POSTHOOK: Input: default@partition_mv_2@value=val_252 -POSTHOOK: Input: default@partition_mv_2@value=val_255 -POSTHOOK: Input: default@partition_mv_2@value=val_256 -POSTHOOK: Input: default@partition_mv_2@value=val_257 -POSTHOOK: Input: default@partition_mv_2@value=val_258 -POSTHOOK: Input: default@partition_mv_2@value=val_260 -POSTHOOK: Input: default@partition_mv_2@value=val_262 -POSTHOOK: Input: default@partition_mv_2@value=val_263 -POSTHOOK: Input: default@partition_mv_2@value=val_265 -POSTHOOK: Input: default@partition_mv_2@value=val_266 -POSTHOOK: Input: default@partition_mv_2@value=val_272 -POSTHOOK: Input: default@partition_mv_2@value=val_273 -POSTHOOK: Input: default@partition_mv_2@value=val_274 -POSTHOOK: Input: default@partition_mv_2@value=val_275 -POSTHOOK: Input: default@partition_mv_2@value=val_277 -POSTHOOK: Input: default@partition_mv_2@value=val_278 -POSTHOOK: Input: default@partition_mv_2@value=val_280 -POSTHOOK: Input: default@partition_mv_2@value=val_281 -POSTHOOK: Input: default@partition_mv_2@value=val_282 -POSTHOOK: Input: default@partition_mv_2@value=val_283 -POSTHOOK: Input: default@partition_mv_2@value=val_284 -POSTHOOK: Input: default@partition_mv_2@value=val_285 -POSTHOOK: Input: default@partition_mv_2@value=val_286 -POSTHOOK: Input: default@partition_mv_2@value=val_287 -POSTHOOK: Input: default@partition_mv_2@value=val_288 -POSTHOOK: Input: default@partition_mv_2@value=val_289 -POSTHOOK: Input: default@partition_mv_2@value=val_291 -POSTHOOK: Input: default@partition_mv_2@value=val_292 -POSTHOOK: Input: default@partition_mv_2@value=val_296 -POSTHOOK: Input: default@partition_mv_2@value=val_298 +POSTHOOK: Input: default@partition_mv_3 POSTHOOK: Input: default@src_txn_2 #### A masked pattern was here #### STAGE DEPENDENCIES: @@ -691,7 +567,7 @@ STAGE PLANS: limit: -1 Processor Tree: TableScan - alias: default.partition_mv_2 + alias: default.partition_mv_3 filterExpr: ((UDFToDouble(key) > 224.0D) and (UDFToDouble(key) < 226.0D)) (type: boolean) Filter Operator predicate: ((UDFToDouble(key) > 224.0D) and (UDFToDouble(key) < 226.0D)) (type: boolean) @@ -702,136 +578,14 @@ STAGE PLANS: PREHOOK: query: SELECT * FROM src_txn_2 where key > 223 and key < 225 PREHOOK: type: QUERY -PREHOOK: Input: default@partition_mv_2 -PREHOOK: Input: default@partition_mv_2@value=val_201 -PREHOOK: Input: default@partition_mv_2@value=val_202 -PREHOOK: Input: default@partition_mv_2@value=val_203 -PREHOOK: Input: default@partition_mv_2@value=val_205 -PREHOOK: Input: default@partition_mv_2@value=val_207 -PREHOOK: Input: default@partition_mv_2@value=val_208 -PREHOOK: Input: default@partition_mv_2@value=val_209 -PREHOOK: Input: default@partition_mv_2@value=val_213 -PREHOOK: Input: default@partition_mv_2@value=val_214 -PREHOOK: Input: default@partition_mv_2@value=val_216 -PREHOOK: Input: default@partition_mv_2@value=val_217 -PREHOOK: Input: default@partition_mv_2@value=val_218 -PREHOOK: Input: default@partition_mv_2@value=val_219 -PREHOOK: Input: default@partition_mv_2@value=val_221 -PREHOOK: Input: default@partition_mv_2@value=val_222 -PREHOOK: Input: default@partition_mv_2@value=val_223 -PREHOOK: Input: default@partition_mv_2@value=val_224 -PREHOOK: Input: default@partition_mv_2@value=val_226 -PREHOOK: Input: default@partition_mv_2@value=val_228 -PREHOOK: Input: default@partition_mv_2@value=val_229 -PREHOOK: Input: default@partition_mv_2@value=val_230 -PREHOOK: Input: default@partition_mv_2@value=val_233 -PREHOOK: Input: default@partition_mv_2@value=val_235 -PREHOOK: Input: default@partition_mv_2@value=val_237 -PREHOOK: Input: default@partition_mv_2@value=val_238 -PREHOOK: Input: default@partition_mv_2@value=val_239 -PREHOOK: Input: default@partition_mv_2@value=val_241 -PREHOOK: Input: default@partition_mv_2@value=val_242 -PREHOOK: Input: default@partition_mv_2@value=val_244 -PREHOOK: Input: default@partition_mv_2@value=val_247 -PREHOOK: Input: default@partition_mv_2@value=val_248 -PREHOOK: Input: default@partition_mv_2@value=val_249 -PREHOOK: Input: default@partition_mv_2@value=val_252 -PREHOOK: Input: default@partition_mv_2@value=val_255 -PREHOOK: Input: default@partition_mv_2@value=val_256 -PREHOOK: Input: default@partition_mv_2@value=val_257 -PREHOOK: Input: default@partition_mv_2@value=val_258 -PREHOOK: Input: default@partition_mv_2@value=val_260 -PREHOOK: Input: default@partition_mv_2@value=val_262 -PREHOOK: Input: default@partition_mv_2@value=val_263 -PREHOOK: Input: default@partition_mv_2@value=val_265 -PREHOOK: Input: default@partition_mv_2@value=val_266 -PREHOOK: Input: default@partition_mv_2@value=val_272 -PREHOOK: Input: default@partition_mv_2@value=val_273 -PREHOOK: Input: default@partition_mv_2@value=val_274 -PREHOOK: Input: default@partition_mv_2@value=val_275 -PREHOOK: Input: default@partition_mv_2@value=val_277 -PREHOOK: Input: default@partition_mv_2@value=val_278 -PREHOOK: Input: default@partition_mv_2@value=val_280 -PREHOOK: Input: default@partition_mv_2@value=val_281 -PREHOOK: Input: default@partition_mv_2@value=val_282 -PREHOOK: Input: default@partition_mv_2@value=val_283 -PREHOOK: Input: default@partition_mv_2@value=val_284 -PREHOOK: Input: default@partition_mv_2@value=val_285 -PREHOOK: Input: default@partition_mv_2@value=val_286 -PREHOOK: Input: default@partition_mv_2@value=val_287 -PREHOOK: Input: default@partition_mv_2@value=val_288 -PREHOOK: Input: default@partition_mv_2@value=val_289 -PREHOOK: Input: default@partition_mv_2@value=val_291 -PREHOOK: Input: default@partition_mv_2@value=val_292 -PREHOOK: Input: default@partition_mv_2@value=val_296 -PREHOOK: Input: default@partition_mv_2@value=val_298 +PREHOOK: Input: default@partition_mv_3 +PREHOOK: Input: default@partition_mv_3@key=224 PREHOOK: Input: default@src_txn_2 #### A masked pattern was here #### POSTHOOK: query: SELECT * FROM src_txn_2 where key > 223 and key < 225 POSTHOOK: type: QUERY -POSTHOOK: Input: default@partition_mv_2 -POSTHOOK: Input: default@partition_mv_2@value=val_201 -POSTHOOK: Input: default@partition_mv_2@value=val_202 -POSTHOOK: Input: default@partition_mv_2@value=val_203 -POSTHOOK: Input: default@partition_mv_2@value=val_205 -POSTHOOK: Input: default@partition_mv_2@value=val_207 -POSTHOOK: Input: default@partition_mv_2@value=val_208 -POSTHOOK: Input: default@partition_mv_2@value=val_209 -POSTHOOK: Input: default@partition_mv_2@value=val_213 -POSTHOOK: Input: default@partition_mv_2@value=val_214 -POSTHOOK: Input: default@partition_mv_2@value=val_216 -POSTHOOK: Input: default@partition_mv_2@value=val_217 -POSTHOOK: Input: default@partition_mv_2@value=val_218 -POSTHOOK: Input: default@partition_mv_2@value=val_219 -POSTHOOK: Input: default@partition_mv_2@value=val_221 -POSTHOOK: Input: default@partition_mv_2@value=val_222 -POSTHOOK: Input: default@partition_mv_2@value=val_223 -POSTHOOK: Input: default@partition_mv_2@value=val_224 -POSTHOOK: Input: default@partition_mv_2@value=val_226 -POSTHOOK: Input: default@partition_mv_2@value=val_228 -POSTHOOK: Input: default@partition_mv_2@value=val_229 -POSTHOOK: Input: default@partition_mv_2@value=val_230 -POSTHOOK: Input: default@partition_mv_2@value=val_233 -POSTHOOK: Input: default@partition_mv_2@value=val_235 -POSTHOOK: Input: default@partition_mv_2@value=val_237 -POSTHOOK: Input: default@partition_mv_2@value=val_238 -POSTHOOK: Input: default@partition_mv_2@value=val_239 -POSTHOOK: Input: default@partition_mv_2@value=val_241 -POSTHOOK: Input: default@partition_mv_2@value=val_242 -POSTHOOK: Input: default@partition_mv_2@value=val_244 -POSTHOOK: Input: default@partition_mv_2@value=val_247 -POSTHOOK: Input: default@partition_mv_2@value=val_248 -POSTHOOK: Input: default@partition_mv_2@value=val_249 -POSTHOOK: Input: default@partition_mv_2@value=val_252 -POSTHOOK: Input: default@partition_mv_2@value=val_255 -POSTHOOK: Input: default@partition_mv_2@value=val_256 -POSTHOOK: Input: default@partition_mv_2@value=val_257 -POSTHOOK: Input: default@partition_mv_2@value=val_258 -POSTHOOK: Input: default@partition_mv_2@value=val_260 -POSTHOOK: Input: default@partition_mv_2@value=val_262 -POSTHOOK: Input: default@partition_mv_2@value=val_263 -POSTHOOK: Input: default@partition_mv_2@value=val_265 -POSTHOOK: Input: default@partition_mv_2@value=val_266 -POSTHOOK: Input: default@partition_mv_2@value=val_272 -POSTHOOK: Input: default@partition_mv_2@value=val_273 -POSTHOOK: Input: default@partition_mv_2@value=val_274 -POSTHOOK: Input: default@partition_mv_2@value=val_275 -POSTHOOK: Input: default@partition_mv_2@value=val_277 -POSTHOOK: Input: default@partition_mv_2@value=val_278 -POSTHOOK: Input: default@partition_mv_2@value=val_280 -POSTHOOK: Input: default@partition_mv_2@value=val_281 -POSTHOOK: Input: default@partition_mv_2@value=val_282 -POSTHOOK: Input: default@partition_mv_2@value=val_283 -POSTHOOK: Input: default@partition_mv_2@value=val_284 -POSTHOOK: Input: default@partition_mv_2@value=val_285 -POSTHOOK: Input: default@partition_mv_2@value=val_286 -POSTHOOK: Input: default@partition_mv_2@value=val_287 -POSTHOOK: Input: default@partition_mv_2@value=val_288 -POSTHOOK: Input: default@partition_mv_2@value=val_289 -POSTHOOK: Input: default@partition_mv_2@value=val_291 -POSTHOOK: Input: default@partition_mv_2@value=val_292 -POSTHOOK: Input: default@partition_mv_2@value=val_296 -POSTHOOK: Input: default@partition_mv_2@value=val_298 +POSTHOOK: Input: default@partition_mv_3 +POSTHOOK: Input: default@partition_mv_3@key=224 POSTHOOK: Input: default@src_txn_2 #### A masked pattern was here #### 224 val_224 diff --git a/ql/src/test/results/clientpositive/llap/materialized_view_partitioned_create_rewrite_agg.q.out b/ql/src/test/results/clientpositive/llap/materialized_view_partitioned_create_rewrite_agg.q.out index 54aa1228203c..8a32a9321f76 100644 --- a/ql/src/test/results/clientpositive/llap/materialized_view_partitioned_create_rewrite_agg.q.out +++ b/ql/src/test/results/clientpositive/llap/materialized_view_partitioned_create_rewrite_agg.q.out @@ -136,11 +136,11 @@ HiveProject(b=[$0], sumc=[$2], a=[$1]) HiveTableScan(table=[[default, mat1]], table:alias=[default.mat1]) HiveProject(b=[$1], a=[$0]) HiveAggregate(group=[{0, 1}]) - HiveFilter(condition=[<(1, $5.writeid)]) + HiveFilter(condition=[IS NOT TRUE(>=(1, $5.writeid))]) HiveTableScan(table=[[default, t1]], table:alias=[t1]) HiveProject(b=[$1], a=[$0], $f2=[$2]) HiveAggregate(group=[{0, 1}], agg#0=[sum($2)]) - HiveFilter(condition=[<(1, $5.writeid)]) + HiveFilter(condition=[IS NOT TRUE(>=(1, $5.writeid))]) HiveTableScan(table=[[default, t1]], table:alias=[t1]) PREHOOK: query: EXPLAIN @@ -202,44 +202,44 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1 - filterExpr: (ROW__ID.writeid > 1L) (type: boolean) + filterExpr: (ROW__ID.writeid <= 1L) is not true (type: boolean) Statistics: Num rows: 10 Data size: 76 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: (ROW__ID.writeid > 1L) (type: boolean) - Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + predicate: (ROW__ID.writeid <= 1L) is not true (type: boolean) + Statistics: Num rows: 5 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: a (type: int), b (type: int) outputColumnNames: a, b - Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: a (type: int), b (type: int) minReductionHashAggr: 0.4 mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int) null sort order: zz sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: int) - Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: a (type: int), b (type: int), c (type: int) outputColumnNames: a, b, c - Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(c) keys: b (type: int), a (type: int) minReductionHashAggr: 0.4 mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int) null sort order: zz sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: int) - Statistics: Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: bigint) Execution mode: vectorized, llap LLAP IO: may be used (ACID table) @@ -258,16 +258,16 @@ STAGE PLANS: Group By Operator aggregations: sum(_col2) keys: _col0 (type: int), _col1 (type: int) - minReductionHashAggr: 0.4285714 + minReductionHashAggr: 0.4 mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int) null sort order: zz sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: int) - Statistics: Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: bigint) Reducer 4 Execution mode: vectorized, llap @@ -277,14 +277,14 @@ STAGE PLANS: keys: KEY._col0 (type: int), KEY._col1 (type: int) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col2 (type: bigint), _col1 (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat @@ -294,7 +294,7 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: bigint), _col2 (type: int) outputColumnNames: b, sumc, a - Statistics: Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: min(b), max(b), count(1), count(b), compute_bit_vector_hll(b), min(sumc), max(sumc), count(sumc), compute_bit_vector_hll(sumc) keys: a (type: int) @@ -336,11 +336,11 @@ STAGE PLANS: keys: KEY._col0 (type: int), KEY._col1 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: int) minReductionHashAggr: 0.4 @@ -361,20 +361,20 @@ STAGE PLANS: keys: KEY._col0 (type: int), KEY._col1 (type: int) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col2) keys: _col0 (type: int), _col1 (type: int) - minReductionHashAggr: 0.4285714 + minReductionHashAggr: 0.4 mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int) null sort order: zz sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: int) - Statistics: Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: bigint) Union 3 Vertex: Union 3 diff --git a/ql/src/test/results/clientpositive/llap/materialized_view_partitioned_create_rewrite_agg_2.q.out b/ql/src/test/results/clientpositive/llap/materialized_view_partitioned_create_rewrite_agg_2.q.out index 4e02cb3ed46e..51ba08208bb8 100644 --- a/ql/src/test/results/clientpositive/llap/materialized_view_partitioned_create_rewrite_agg_2.q.out +++ b/ql/src/test/results/clientpositive/llap/materialized_view_partitioned_create_rewrite_agg_2.q.out @@ -113,11 +113,11 @@ HiveProject(sumb=[$3], sume=[$4], a=[$0], c=[$1], d=[$2]) HiveTableScan(table=[[default, mat1]], table:alias=[default.mat1]) HiveProject(a=[$0], c=[$1], d=[$2]) HiveAggregate(group=[{0, 2, 3}]) - HiveFilter(condition=[<(1, $7.writeid)]) + HiveFilter(condition=[IS NOT TRUE(>=(1, $7.writeid))]) HiveTableScan(table=[[default, t1]], table:alias=[t1]) HiveProject(a=[$0], c=[$1], d=[$2], $f3=[$3], $f4=[$4]) HiveAggregate(group=[{0, 2, 3}], agg#0=[sum($1)], agg#1=[sum($4)]) - HiveFilter(condition=[<(1, $7.writeid)]) + HiveFilter(condition=[IS NOT TRUE(>=(1, $7.writeid))]) HiveTableScan(table=[[default, t1]], table:alias=[t1]) PREHOOK: query: EXPLAIN @@ -180,15 +180,15 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1 - filterExpr: (ROW__ID.writeid > 1L) (type: boolean) + filterExpr: (ROW__ID.writeid <= 1L) is not true (type: boolean) Statistics: Num rows: 11 Data size: 1044 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: (ROW__ID.writeid > 1L) (type: boolean) - Statistics: Num rows: 3 Data size: 288 Basic stats: COMPLETE Column stats: COMPLETE + predicate: (ROW__ID.writeid <= 1L) is not true (type: boolean) + Statistics: Num rows: 5 Data size: 480 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: a (type: int), c (type: int), d (type: string) outputColumnNames: a, c, d - Statistics: Num rows: 3 Data size: 288 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 480 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: a (type: int), c (type: int), d (type: string) minReductionHashAggr: 0.4 @@ -204,7 +204,7 @@ STAGE PLANS: Select Operator expressions: a (type: int), b (type: int), c (type: int), d (type: string), e (type: float) outputColumnNames: a, b, c, d, e - Statistics: Num rows: 3 Data size: 312 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 520 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(b), sum(e) keys: a (type: int), c (type: int), d (type: string) diff --git a/ql/src/test/results/clientpositive/llap/materialized_view_partitioned_create_rewrite_agg_3.q.out b/ql/src/test/results/clientpositive/llap/materialized_view_partitioned_create_rewrite_agg_3.q.out index 9c3897d016e6..136129351815 100644 --- a/ql/src/test/results/clientpositive/llap/materialized_view_partitioned_create_rewrite_agg_3.q.out +++ b/ql/src/test/results/clientpositive/llap/materialized_view_partitioned_create_rewrite_agg_3.q.out @@ -132,11 +132,11 @@ HiveProject(b=[$0], sumc=[$2], a=[$1]) HiveTableScan(table=[[default, mat1]], table:alias=[default.mat1]) HiveProject(b=[$1], a=[$0]) HiveAggregate(group=[{0, 1}]) - HiveFilter(condition=[<(1, $5.writeid)]) + HiveFilter(condition=[IS NOT TRUE(>=(1, $5.writeid))]) HiveTableScan(table=[[default, t1]], table:alias=[t1]) HiveProject(b=[$1], a=[$0], $f2=[$2]) HiveAggregate(group=[{0, 1}], agg#0=[sum($2)]) - HiveFilter(condition=[<(1, $5.writeid)]) + HiveFilter(condition=[IS NOT TRUE(>=(1, $5.writeid))]) HiveTableScan(table=[[default, t1]], table:alias=[t1]) PREHOOK: query: EXPLAIN @@ -198,46 +198,46 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1 - filterExpr: (ROW__ID.writeid > 1L) (type: boolean) + filterExpr: (ROW__ID.writeid <= 1L) is not true (type: boolean) properties: insertonly.fetch.bucketid TRUE Statistics: Num rows: 10 Data size: 76 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: (ROW__ID.writeid > 1L) (type: boolean) - Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + predicate: (ROW__ID.writeid <= 1L) is not true (type: boolean) + Statistics: Num rows: 5 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: a (type: int), b (type: int) outputColumnNames: a, b - Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: a (type: int), b (type: int) minReductionHashAggr: 0.4 mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int) null sort order: zz sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: int) - Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: a (type: int), b (type: int), c (type: int) outputColumnNames: a, b, c - Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(c) keys: b (type: int), a (type: int) minReductionHashAggr: 0.4 mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int) null sort order: zz sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: int) - Statistics: Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: bigint) Execution mode: vectorized, llap LLAP IO: may be used (ACID table) @@ -256,16 +256,16 @@ STAGE PLANS: Group By Operator aggregations: sum(_col2) keys: _col0 (type: int), _col1 (type: int) - minReductionHashAggr: 0.4285714 + minReductionHashAggr: 0.4 mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int) null sort order: zz sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: int) - Statistics: Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: bigint) Reducer 4 Execution mode: vectorized, llap @@ -275,14 +275,14 @@ STAGE PLANS: keys: KEY._col0 (type: int), KEY._col1 (type: int) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col2 (type: bigint), _col1 (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat @@ -292,7 +292,7 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: bigint), _col2 (type: int) outputColumnNames: b, sumc, a - Statistics: Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: min(b), max(b), count(1), count(b), compute_bit_vector_hll(b), min(sumc), max(sumc), count(sumc), compute_bit_vector_hll(sumc) keys: a (type: int) @@ -334,11 +334,11 @@ STAGE PLANS: keys: KEY._col0 (type: int), KEY._col1 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: int) minReductionHashAggr: 0.4 @@ -359,20 +359,20 @@ STAGE PLANS: keys: KEY._col0 (type: int), KEY._col1 (type: int) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col2) keys: _col0 (type: int), _col1 (type: int) - minReductionHashAggr: 0.4285714 + minReductionHashAggr: 0.4 mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int) null sort order: zz sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: int) - Statistics: Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: bigint) Union 3 Vertex: Union 3 diff --git a/ql/src/test/results/clientpositive/llap/materialized_view_rebuild_2.q.out b/ql/src/test/results/clientpositive/llap/materialized_view_rebuild_2.q.out index 454c2c0af07a..4cf06e98da70 100644 --- a/ql/src/test/results/clientpositive/llap/materialized_view_rebuild_2.q.out +++ b/ql/src/test/results/clientpositive/llap/materialized_view_rebuild_2.q.out @@ -92,10 +92,10 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1 - filterExpr: ((ROW__ID.writeid > 1L) and (col0 = 1)) (type: boolean) + filterExpr: ((ROW__ID.writeid <= 1L) is not true and (col0 = 1)) (type: boolean) Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: ((ROW__ID.writeid > 1L) and (col0 = 1)) (type: boolean) + predicate: ((ROW__ID.writeid <= 1L) is not true and (col0 = 1)) (type: boolean) Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 1 (type: int) diff --git a/ql/src/test/results/clientpositive/llap/materialized_view_rebuild_3.q.out b/ql/src/test/results/clientpositive/llap/materialized_view_rebuild_3.q.out index 2ef598e2d963..82b9c4fe5fce 100644 --- a/ql/src/test/results/clientpositive/llap/materialized_view_rebuild_3.q.out +++ b/ql/src/test/results/clientpositive/llap/materialized_view_rebuild_3.q.out @@ -95,28 +95,28 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1 - filterExpr: (ROW__ID.writeid > 1L) (type: boolean) + filterExpr: (ROW__ID.writeid <= 1L) is not true (type: boolean) Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: (ROW__ID.writeid > 1L) (type: boolean) - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + predicate: (ROW__ID.writeid <= 1L) is not true (type: boolean) + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: col0 (type: int), col1 (type: int) outputColumnNames: col0, col1 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(col1) keys: col0 (type: int) minReductionHashAggr: 0.4 mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) null sort order: z sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized, llap LLAP IO: may be used (ACID table) @@ -132,7 +132,7 @@ STAGE PLANS: Group By Operator aggregations: sum(_col1) keys: _col0 (type: int) - minReductionHashAggr: 0.4 + minReductionHashAggr: 0.5 mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE @@ -153,11 +153,11 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col1) keys: _col0 (type: int) - minReductionHashAggr: 0.4 + minReductionHashAggr: 0.5 mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE diff --git a/ql/src/test/results/clientpositive/llap/sketches_materialized_view_cume_dist.q.out b/ql/src/test/results/clientpositive/llap/sketches_materialized_view_cume_dist.q.out index b09f1fbfb2a9..060704583885 100644 --- a/ql/src/test/results/clientpositive/llap/sketches_materialized_view_cume_dist.q.out +++ b/ql/src/test/results/clientpositive/llap/sketches_materialized_view_cume_dist.q.out @@ -544,19 +544,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: sketch_input - filterExpr: (ROW__ID.writeid > 1L) (type: boolean) + filterExpr: (ROW__ID.writeid <= 1L) is not true (type: boolean) Statistics: Num rows: 44 Data size: 3916 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: (ROW__ID.writeid > 1L) (type: boolean) - Statistics: Num rows: 14 Data size: 1246 Basic stats: COMPLETE Column stats: COMPLETE + predicate: (ROW__ID.writeid <= 1L) is not true (type: boolean) + Statistics: Num rows: 22 Data size: 1958 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: category (type: char(1)), UDFToFloat(id) (type: float) outputColumnNames: _col0, _col1 - Statistics: Num rows: 14 Data size: 1246 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 22 Data size: 1958 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: ds_kll_sketch(_col1) keys: _col0 (type: char(1)) - minReductionHashAggr: 0.85714287 + minReductionHashAggr: 0.9090909 mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 2 Data size: 458 Basic stats: COMPLETE Column stats: COMPLETE diff --git a/ql/src/test/results/clientpositive/llap/sketches_materialized_view_ntile.q.out b/ql/src/test/results/clientpositive/llap/sketches_materialized_view_ntile.q.out index eed5ef3f6ae3..26af84ab6b5c 100644 --- a/ql/src/test/results/clientpositive/llap/sketches_materialized_view_ntile.q.out +++ b/ql/src/test/results/clientpositive/llap/sketches_materialized_view_ntile.q.out @@ -548,19 +548,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: sketch_input - filterExpr: (ROW__ID.writeid > 1L) (type: boolean) + filterExpr: (ROW__ID.writeid <= 1L) is not true (type: boolean) Statistics: Num rows: 44 Data size: 3916 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: (ROW__ID.writeid > 1L) (type: boolean) - Statistics: Num rows: 14 Data size: 1246 Basic stats: COMPLETE Column stats: COMPLETE + predicate: (ROW__ID.writeid <= 1L) is not true (type: boolean) + Statistics: Num rows: 22 Data size: 1958 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: category (type: char(1)), UDFToFloat(id) (type: float) outputColumnNames: _col0, _col1 - Statistics: Num rows: 14 Data size: 1246 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 22 Data size: 1958 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: ds_kll_sketch(_col1) keys: _col0 (type: char(1)) - minReductionHashAggr: 0.85714287 + minReductionHashAggr: 0.9090909 mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 2 Data size: 458 Basic stats: COMPLETE Column stats: COMPLETE diff --git a/ql/src/test/results/clientpositive/llap/sketches_materialized_view_percentile_disc.q.out b/ql/src/test/results/clientpositive/llap/sketches_materialized_view_percentile_disc.q.out index e9452e24cfc7..91145a4bfbce 100644 --- a/ql/src/test/results/clientpositive/llap/sketches_materialized_view_percentile_disc.q.out +++ b/ql/src/test/results/clientpositive/llap/sketches_materialized_view_percentile_disc.q.out @@ -312,19 +312,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: sketch_input - filterExpr: (ROW__ID.writeid > 1L) (type: boolean) + filterExpr: (ROW__ID.writeid <= 1L) is not true (type: boolean) Statistics: Num rows: 44 Data size: 3916 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: (ROW__ID.writeid > 1L) (type: boolean) - Statistics: Num rows: 14 Data size: 1246 Basic stats: COMPLETE Column stats: COMPLETE + predicate: (ROW__ID.writeid <= 1L) is not true (type: boolean) + Statistics: Num rows: 22 Data size: 1958 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: category (type: char(1)), UDFToFloat(id) (type: float) outputColumnNames: _col0, _col1 - Statistics: Num rows: 14 Data size: 1246 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 22 Data size: 1958 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: ds_kll_sketch(_col1) keys: _col0 (type: char(1)) - minReductionHashAggr: 0.85714287 + minReductionHashAggr: 0.9090909 mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 2 Data size: 458 Basic stats: COMPLETE Column stats: COMPLETE diff --git a/ql/src/test/results/clientpositive/llap/sketches_materialized_view_rank.q.out b/ql/src/test/results/clientpositive/llap/sketches_materialized_view_rank.q.out index bfc3ac7dfd61..45bd756f9ec8 100644 --- a/ql/src/test/results/clientpositive/llap/sketches_materialized_view_rank.q.out +++ b/ql/src/test/results/clientpositive/llap/sketches_materialized_view_rank.q.out @@ -548,19 +548,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: sketch_input - filterExpr: (ROW__ID.writeid > 1L) (type: boolean) + filterExpr: (ROW__ID.writeid <= 1L) is not true (type: boolean) Statistics: Num rows: 44 Data size: 3916 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: (ROW__ID.writeid > 1L) (type: boolean) - Statistics: Num rows: 14 Data size: 1246 Basic stats: COMPLETE Column stats: COMPLETE + predicate: (ROW__ID.writeid <= 1L) is not true (type: boolean) + Statistics: Num rows: 22 Data size: 1958 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: category (type: char(1)), UDFToFloat(id) (type: float) outputColumnNames: _col0, _col1 - Statistics: Num rows: 14 Data size: 1246 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 22 Data size: 1958 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: ds_kll_sketch(_col1) keys: _col0 (type: char(1)) - minReductionHashAggr: 0.85714287 + minReductionHashAggr: 0.9090909 mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 2 Data size: 458 Basic stats: COMPLETE Column stats: COMPLETE diff --git a/ql/src/test/results/clientpositive/llap/sketches_materialized_view_rollup2.q.out b/ql/src/test/results/clientpositive/llap/sketches_materialized_view_rollup2.q.out index 96f517f59b5b..559ed289e9ec 100644 --- a/ql/src/test/results/clientpositive/llap/sketches_materialized_view_rollup2.q.out +++ b/ql/src/test/results/clientpositive/llap/sketches_materialized_view_rollup2.q.out @@ -320,19 +320,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: sketch_input - filterExpr: (ROW__ID.writeid > 1L) (type: boolean) + filterExpr: (ROW__ID.writeid <= 1L) is not true (type: boolean) Statistics: Num rows: 44 Data size: 3916 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: (ROW__ID.writeid > 1L) (type: boolean) - Statistics: Num rows: 14 Data size: 1246 Basic stats: COMPLETE Column stats: COMPLETE + predicate: (ROW__ID.writeid <= 1L) is not true (type: boolean) + Statistics: Num rows: 22 Data size: 1958 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: id (type: int), category (type: char(1)) outputColumnNames: id, category - Statistics: Num rows: 14 Data size: 1246 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 22 Data size: 1958 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: ds_hll_sketch(id), count(id) keys: category (type: char(1)) - minReductionHashAggr: 0.85714287 + minReductionHashAggr: 0.9090909 mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 2 Data size: 962 Basic stats: COMPLETE Column stats: COMPLETE diff --git a/ql/src/test/results/clientpositive/llap/subquery_notin.q.out b/ql/src/test/results/clientpositive/llap/subquery_notin.q.out index bfbc465981bc..f59a519ae615 100644 --- a/ql/src/test/results/clientpositive/llap/subquery_notin.q.out +++ b/ql/src/test/results/clientpositive/llap/subquery_notin.q.out @@ -3145,7 +3145,7 @@ STAGE PLANS: Statistics: Num rows: 16 Data size: 1728 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint), _col2 (type: bigint) Filter Operator - predicate: (p_brand is not null and (UDFToDouble(p_type) + 2.0D) is not null) (type: boolean) + predicate: (p_brand is not null and UDFToDouble(p_type) is not null) (type: boolean) Statistics: Num rows: 26 Data size: 5096 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: (UDFToDouble(p_type) + 2.0D) (type: double), p_brand (type: string) diff --git a/ql/src/test/results/clientpositive/llap/vector_interval_2.q.out b/ql/src/test/results/clientpositive/llap/vector_interval_2.q.out index 91f4610f0508..7529209b4812 100644 --- a/ql/src/test/results/clientpositive/llap/vector_interval_2.q.out +++ b/ql/src/test/results/clientpositive/llap/vector_interval_2.q.out @@ -962,7 +962,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: vector_interval_2 - filterExpr: ((CAST( str2 AS INTERVAL YEAR TO MONTH) > INTERVAL'1-2') and (CAST( str1 AS INTERVAL YEAR TO MONTH) <= CAST( str2 AS INTERVAL YEAR TO MONTH)) and (CAST( str1 AS INTERVAL YEAR TO MONTH) < CAST( str2 AS INTERVAL YEAR TO MONTH)) and (CAST( str2 AS INTERVAL YEAR TO MONTH) >= CAST( str1 AS INTERVAL YEAR TO MONTH)) and (CAST( str2 AS INTERVAL YEAR TO MONTH) > CAST( str1 AS INTERVAL YEAR TO MONTH)) and (CAST( str1 AS INTERVAL YEAR TO MONTH) <> CAST( str2 AS INTERVAL YEAR TO MONTH)) and (CAST( str1 AS INTERVAL YEAR TO MONTH) = INTERVAL'1-2')) (type: boolean) + filterExpr: ((CAST( str2 AS INTERVAL YEAR TO MONTH) > INTERVAL'1-2') and (CAST( str1 AS INTERVAL YEAR TO MONTH) <= CAST( str2 AS INTERVAL YEAR TO MONTH)) and (CAST( str1 AS INTERVAL YEAR TO MONTH) < CAST( str2 AS INTERVAL YEAR TO MONTH)) and (CAST( str2 AS INTERVAL YEAR TO MONTH) >= CAST( str1 AS INTERVAL YEAR TO MONTH)) and (CAST( str2 AS INTERVAL YEAR TO MONTH) > CAST( str1 AS INTERVAL YEAR TO MONTH)) and (CAST( str1 AS INTERVAL YEAR TO MONTH) = INTERVAL'1-2') and (CAST( str1 AS INTERVAL YEAR TO MONTH) <> CAST( str2 AS INTERVAL YEAR TO MONTH))) (type: boolean) Statistics: Num rows: 2 Data size: 428 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true @@ -970,8 +970,8 @@ STAGE PLANS: Filter Vectorization: className: VectorFilterOperator native: true - predicateExpression: FilterExprAndExpr(children: FilterIntervalYearMonthColGreaterIntervalYearMonthScalar(col 8:interval_year_month, val 14)(children: CastStringToIntervalYearMonth(col 3:string) -> 8:interval_year_month), FilterLongColLessEqualLongColumn(col 9:interval_year_month, col 10:interval_year_month)(children: CastStringToIntervalYearMonth(col 2:string) -> 9:interval_year_month, CastStringToIntervalYearMonth(col 3:string) -> 10:interval_year_month), FilterLongColLessLongColumn(col 11:interval_year_month, col 12:interval_year_month)(children: CastStringToIntervalYearMonth(col 2:string) -> 11:interval_year_month, CastStringToIntervalYearMonth(col 3:string) -> 12:interval_year_month), FilterLongColGreaterEqualLongColumn(col 13:interval_year_month, col 14:interval_year_month)(children: CastStringToIntervalYearMonth(col 3:string) -> 13:interval_year_month, CastStringToIntervalYearMonth(col 2:string) -> 14:interval_year_month), FilterLongColGreaterLongColumn(col 15:interval_year_month, col 16:interval_year_month)(children: CastStringToIntervalYearMonth(col 3:string) -> 15:interval_year_month, CastStringToIntervalYearMonth(col 2:string) -> 16:interval_year_month), FilterLongColNotEqualLongColumn(col 17:interval_year_month, col 18:interval_year_month)(children: CastStringToIntervalYearMonth(col 2:string) -> 17:interval_year_month, CastStringToIntervalYearMonth(col 3:string) -> 18:interval_year_month), FilterIntervalYearMonthColEqualIntervalYearMonthScalar(col 19:interval_year_month, val 14)(children: CastStringToIntervalYearMonth(col 2:string) -> 19:interval_year_month)) - predicate: ((CAST( str2 AS INTERVAL YEAR TO MONTH) > INTERVAL'1-2') and (CAST( str1 AS INTERVAL YEAR TO MONTH) <= CAST( str2 AS INTERVAL YEAR TO MONTH)) and (CAST( str1 AS INTERVAL YEAR TO MONTH) < CAST( str2 AS INTERVAL YEAR TO MONTH)) and (CAST( str2 AS INTERVAL YEAR TO MONTH) >= CAST( str1 AS INTERVAL YEAR TO MONTH)) and (CAST( str2 AS INTERVAL YEAR TO MONTH) > CAST( str1 AS INTERVAL YEAR TO MONTH)) and (CAST( str1 AS INTERVAL YEAR TO MONTH) <> CAST( str2 AS INTERVAL YEAR TO MONTH)) and (CAST( str1 AS INTERVAL YEAR TO MONTH) = INTERVAL'1-2')) (type: boolean) + predicateExpression: FilterExprAndExpr(children: FilterIntervalYearMonthColGreaterIntervalYearMonthScalar(col 8:interval_year_month, val 14)(children: CastStringToIntervalYearMonth(col 3:string) -> 8:interval_year_month), FilterLongColLessEqualLongColumn(col 9:interval_year_month, col 10:interval_year_month)(children: CastStringToIntervalYearMonth(col 2:string) -> 9:interval_year_month, CastStringToIntervalYearMonth(col 3:string) -> 10:interval_year_month), FilterLongColLessLongColumn(col 11:interval_year_month, col 12:interval_year_month)(children: CastStringToIntervalYearMonth(col 2:string) -> 11:interval_year_month, CastStringToIntervalYearMonth(col 3:string) -> 12:interval_year_month), FilterLongColGreaterEqualLongColumn(col 13:interval_year_month, col 14:interval_year_month)(children: CastStringToIntervalYearMonth(col 3:string) -> 13:interval_year_month, CastStringToIntervalYearMonth(col 2:string) -> 14:interval_year_month), FilterLongColGreaterLongColumn(col 15:interval_year_month, col 16:interval_year_month)(children: CastStringToIntervalYearMonth(col 3:string) -> 15:interval_year_month, CastStringToIntervalYearMonth(col 2:string) -> 16:interval_year_month), FilterIntervalYearMonthColEqualIntervalYearMonthScalar(col 17:interval_year_month, val 14)(children: CastStringToIntervalYearMonth(col 2:string) -> 17:interval_year_month), FilterLongColNotEqualLongColumn(col 18:interval_year_month, col 19:interval_year_month)(children: CastStringToIntervalYearMonth(col 2:string) -> 18:interval_year_month, CastStringToIntervalYearMonth(col 3:string) -> 19:interval_year_month)) + predicate: ((CAST( str2 AS INTERVAL YEAR TO MONTH) > INTERVAL'1-2') and (CAST( str1 AS INTERVAL YEAR TO MONTH) <= CAST( str2 AS INTERVAL YEAR TO MONTH)) and (CAST( str1 AS INTERVAL YEAR TO MONTH) < CAST( str2 AS INTERVAL YEAR TO MONTH)) and (CAST( str2 AS INTERVAL YEAR TO MONTH) >= CAST( str1 AS INTERVAL YEAR TO MONTH)) and (CAST( str2 AS INTERVAL YEAR TO MONTH) > CAST( str1 AS INTERVAL YEAR TO MONTH)) and (CAST( str1 AS INTERVAL YEAR TO MONTH) = INTERVAL'1-2') and (CAST( str1 AS INTERVAL YEAR TO MONTH) <> CAST( str2 AS INTERVAL YEAR TO MONTH))) (type: boolean) Statistics: Num rows: 1 Data size: 214 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ts (type: timestamp) @@ -1162,7 +1162,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: vector_interval_2 - filterExpr: ((CAST( str4 AS INTERVAL DAY TO SECOND) > INTERVAL'1 02:03:04.000000000') and (CAST( str3 AS INTERVAL DAY TO SECOND) <= CAST( str4 AS INTERVAL DAY TO SECOND)) and (CAST( str3 AS INTERVAL DAY TO SECOND) < CAST( str4 AS INTERVAL DAY TO SECOND)) and (CAST( str4 AS INTERVAL DAY TO SECOND) >= CAST( str3 AS INTERVAL DAY TO SECOND)) and (CAST( str4 AS INTERVAL DAY TO SECOND) > CAST( str3 AS INTERVAL DAY TO SECOND)) and (CAST( str3 AS INTERVAL DAY TO SECOND) <> CAST( str4 AS INTERVAL DAY TO SECOND)) and (CAST( str3 AS INTERVAL DAY TO SECOND) = INTERVAL'1 02:03:04.000000000')) (type: boolean) + filterExpr: ((CAST( str4 AS INTERVAL DAY TO SECOND) > INTERVAL'1 02:03:04.000000000') and (CAST( str3 AS INTERVAL DAY TO SECOND) <= CAST( str4 AS INTERVAL DAY TO SECOND)) and (CAST( str3 AS INTERVAL DAY TO SECOND) < CAST( str4 AS INTERVAL DAY TO SECOND)) and (CAST( str4 AS INTERVAL DAY TO SECOND) >= CAST( str3 AS INTERVAL DAY TO SECOND)) and (CAST( str4 AS INTERVAL DAY TO SECOND) > CAST( str3 AS INTERVAL DAY TO SECOND)) and (CAST( str3 AS INTERVAL DAY TO SECOND) = INTERVAL'1 02:03:04.000000000') and (CAST( str3 AS INTERVAL DAY TO SECOND) <> CAST( str4 AS INTERVAL DAY TO SECOND))) (type: boolean) Statistics: Num rows: 2 Data size: 444 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true @@ -1170,8 +1170,8 @@ STAGE PLANS: Filter Vectorization: className: VectorFilterOperator native: true - predicateExpression: FilterExprAndExpr(children: FilterIntervalDayTimeColGreaterIntervalDayTimeScalar(col 8:interval_day_time, val 1 02:03:04.000000000)(children: CastStringToIntervalDayTime(col 5:string) -> 8:interval_day_time), FilterIntervalDayTimeColLessEqualIntervalDayTimeColumn(col 9:interval_day_time, col 10:interval_day_time)(children: CastStringToIntervalDayTime(col 4:string) -> 9:interval_day_time, CastStringToIntervalDayTime(col 5:string) -> 10:interval_day_time), FilterIntervalDayTimeColLessIntervalDayTimeColumn(col 11:interval_day_time, col 12:interval_day_time)(children: CastStringToIntervalDayTime(col 4:string) -> 11:interval_day_time, CastStringToIntervalDayTime(col 5:string) -> 12:interval_day_time), FilterIntervalDayTimeColGreaterEqualIntervalDayTimeColumn(col 13:interval_day_time, col 14:interval_day_time)(children: CastStringToIntervalDayTime(col 5:string) -> 13:interval_day_time, CastStringToIntervalDayTime(col 4:string) -> 14:interval_day_time), FilterIntervalDayTimeColGreaterIntervalDayTimeColumn(col 15:interval_day_time, col 16:interval_day_time)(children: CastStringToIntervalDayTime(col 5:string) -> 15:interval_day_time, CastStringToIntervalDayTime(col 4:string) -> 16:interval_day_time), FilterIntervalDayTimeColNotEqualIntervalDayTimeColumn(col 17:interval_day_time, col 18:interval_day_time)(children: CastStringToIntervalDayTime(col 4:string) -> 17:interval_day_time, CastStringToIntervalDayTime(col 5:string) -> 18:interval_day_time), FilterIntervalDayTimeColEqualIntervalDayTimeScalar(col 19:interval_day_time, val 1 02:03:04.000000000)(children: CastStringToIntervalDayTime(col 4:string) -> 19:interval_day_time)) - predicate: ((CAST( str4 AS INTERVAL DAY TO SECOND) > INTERVAL'1 02:03:04.000000000') and (CAST( str3 AS INTERVAL DAY TO SECOND) <= CAST( str4 AS INTERVAL DAY TO SECOND)) and (CAST( str3 AS INTERVAL DAY TO SECOND) < CAST( str4 AS INTERVAL DAY TO SECOND)) and (CAST( str4 AS INTERVAL DAY TO SECOND) >= CAST( str3 AS INTERVAL DAY TO SECOND)) and (CAST( str4 AS INTERVAL DAY TO SECOND) > CAST( str3 AS INTERVAL DAY TO SECOND)) and (CAST( str3 AS INTERVAL DAY TO SECOND) <> CAST( str4 AS INTERVAL DAY TO SECOND)) and (CAST( str3 AS INTERVAL DAY TO SECOND) = INTERVAL'1 02:03:04.000000000')) (type: boolean) + predicateExpression: FilterExprAndExpr(children: FilterIntervalDayTimeColGreaterIntervalDayTimeScalar(col 8:interval_day_time, val 1 02:03:04.000000000)(children: CastStringToIntervalDayTime(col 5:string) -> 8:interval_day_time), FilterIntervalDayTimeColLessEqualIntervalDayTimeColumn(col 9:interval_day_time, col 10:interval_day_time)(children: CastStringToIntervalDayTime(col 4:string) -> 9:interval_day_time, CastStringToIntervalDayTime(col 5:string) -> 10:interval_day_time), FilterIntervalDayTimeColLessIntervalDayTimeColumn(col 11:interval_day_time, col 12:interval_day_time)(children: CastStringToIntervalDayTime(col 4:string) -> 11:interval_day_time, CastStringToIntervalDayTime(col 5:string) -> 12:interval_day_time), FilterIntervalDayTimeColGreaterEqualIntervalDayTimeColumn(col 13:interval_day_time, col 14:interval_day_time)(children: CastStringToIntervalDayTime(col 5:string) -> 13:interval_day_time, CastStringToIntervalDayTime(col 4:string) -> 14:interval_day_time), FilterIntervalDayTimeColGreaterIntervalDayTimeColumn(col 15:interval_day_time, col 16:interval_day_time)(children: CastStringToIntervalDayTime(col 5:string) -> 15:interval_day_time, CastStringToIntervalDayTime(col 4:string) -> 16:interval_day_time), FilterIntervalDayTimeColEqualIntervalDayTimeScalar(col 17:interval_day_time, val 1 02:03:04.000000000)(children: CastStringToIntervalDayTime(col 4:string) -> 17:interval_day_time), FilterIntervalDayTimeColNotEqualIntervalDayTimeColumn(col 18:interval_day_time, col 19:interval_day_time)(children: CastStringToIntervalDayTime(col 4:string) -> 18:interval_day_time, CastStringToIntervalDayTime(col 5:string) -> 19:interval_day_time)) + predicate: ((CAST( str4 AS INTERVAL DAY TO SECOND) > INTERVAL'1 02:03:04.000000000') and (CAST( str3 AS INTERVAL DAY TO SECOND) <= CAST( str4 AS INTERVAL DAY TO SECOND)) and (CAST( str3 AS INTERVAL DAY TO SECOND) < CAST( str4 AS INTERVAL DAY TO SECOND)) and (CAST( str4 AS INTERVAL DAY TO SECOND) >= CAST( str3 AS INTERVAL DAY TO SECOND)) and (CAST( str4 AS INTERVAL DAY TO SECOND) > CAST( str3 AS INTERVAL DAY TO SECOND)) and (CAST( str3 AS INTERVAL DAY TO SECOND) = INTERVAL'1 02:03:04.000000000') and (CAST( str3 AS INTERVAL DAY TO SECOND) <> CAST( str4 AS INTERVAL DAY TO SECOND))) (type: boolean) Statistics: Num rows: 1 Data size: 222 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ts (type: timestamp) @@ -1352,7 +1352,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: vector_interval_2 - filterExpr: (((dt + CAST( str1 AS INTERVAL YEAR TO MONTH)) = DATE'2002-03-01') and (dt <> (dt + CAST( str1 AS INTERVAL YEAR TO MONTH))) and ((dt + INTERVAL'1-2') = DATE'2002-03-01') and (dt <> (dt + INTERVAL'1-2'))) (type: boolean) + filterExpr: ((DATE'2002-03-01' = (dt + CAST( str1 AS INTERVAL YEAR TO MONTH))) and (dt <> (dt + CAST( str1 AS INTERVAL YEAR TO MONTH))) and (DATE'2002-03-01' = (dt + INTERVAL'1-2')) and (dt <> (dt + INTERVAL'1-2'))) (type: boolean) Statistics: Num rows: 2 Data size: 366 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true @@ -1360,8 +1360,8 @@ STAGE PLANS: Filter Vectorization: className: VectorFilterOperator native: true - predicateExpression: FilterExprAndExpr(children: FilterDateColEqualDateScalar(col 9:date, val 11747)(children: DateColAddIntervalYearMonthColumn(col 1:date, col 8:interval_year_month)(children: CastStringToIntervalYearMonth(col 2:string) -> 8:interval_year_month) -> 9:date), FilterLongColNotEqualLongColumn(col 1:date, col 11:date)(children: DateColAddIntervalYearMonthColumn(col 1:date, col 10:interval_year_month)(children: CastStringToIntervalYearMonth(col 2:string) -> 10:interval_year_month) -> 11:date), FilterDateColEqualDateScalar(col 12:date, val 11747)(children: DateColAddIntervalYearMonthScalar(col 1:date, val 1-2) -> 12:date), FilterLongColNotEqualLongColumn(col 1:date, col 13:date)(children: DateColAddIntervalYearMonthScalar(col 1:date, val 1-2) -> 13:date)) - predicate: (((dt + CAST( str1 AS INTERVAL YEAR TO MONTH)) = DATE'2002-03-01') and (dt <> (dt + CAST( str1 AS INTERVAL YEAR TO MONTH))) and ((dt + INTERVAL'1-2') = DATE'2002-03-01') and (dt <> (dt + INTERVAL'1-2'))) (type: boolean) + predicateExpression: FilterExprAndExpr(children: FilterDateScalarEqualDateColumn(val 11747, col 9:date)(children: DateColAddIntervalYearMonthColumn(col 1:date, col 8:interval_year_month)(children: CastStringToIntervalYearMonth(col 2:string) -> 8:interval_year_month) -> 9:date), FilterLongColNotEqualLongColumn(col 1:date, col 11:date)(children: DateColAddIntervalYearMonthColumn(col 1:date, col 10:interval_year_month)(children: CastStringToIntervalYearMonth(col 2:string) -> 10:interval_year_month) -> 11:date), FilterDateScalarEqualDateColumn(val 11747, col 12:date)(children: DateColAddIntervalYearMonthScalar(col 1:date, val 1-2) -> 12:date), FilterLongColNotEqualLongColumn(col 1:date, col 13:date)(children: DateColAddIntervalYearMonthScalar(col 1:date, val 1-2) -> 13:date)) + predicate: ((DATE'2002-03-01' = (dt + CAST( str1 AS INTERVAL YEAR TO MONTH))) and (dt <> (dt + CAST( str1 AS INTERVAL YEAR TO MONTH))) and (DATE'2002-03-01' = (dt + INTERVAL'1-2')) and (dt <> (dt + INTERVAL'1-2'))) (type: boolean) Statistics: Num rows: 1 Data size: 183 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ts (type: timestamp) diff --git a/ql/src/test/results/clientpositive/llap/vector_interval_mapjoin.q.out b/ql/src/test/results/clientpositive/llap/vector_interval_mapjoin.q.out index 76f4387f95ee..2bbf69ab5033 100644 --- a/ql/src/test/results/clientpositive/llap/vector_interval_mapjoin.q.out +++ b/ql/src/test/results/clientpositive/llap/vector_interval_mapjoin.q.out @@ -206,7 +206,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: vectortab_a_1korc - filterExpr: ((dt - CAST( ts AS DATE)) is not null and s is not null) (type: boolean) + filterExpr: (dt is not null and CAST( ts AS DATE) is not null and s is not null) (type: boolean) Statistics: Num rows: 1000 Data size: 185480 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true @@ -214,18 +214,18 @@ STAGE PLANS: Filter Vectorization: className: VectorFilterOperator native: true - predicateExpression: FilterExprAndExpr(children: SelectColumnIsNotNull(col 16:interval_day_time)(children: DateColSubtractDateColumn(col 12:date, col 15:date)(children: CastTimestampToDate(col 10:timestamp) -> 15:date) -> 16:interval_day_time), SelectColumnIsNotNull(col 8:string)) - predicate: ((dt - CAST( ts AS DATE)) is not null and s is not null) (type: boolean) - Statistics: Num rows: 949 Data size: 176022 Basic stats: COMPLETE Column stats: COMPLETE + predicateExpression: FilterExprAndExpr(children: SelectColumnIsNotNull(col 12:date), SelectColumnIsNotNull(col 15:date)(children: CastTimestampToDate(col 10:timestamp) -> 15:date), SelectColumnIsNotNull(col 8:string)) + predicate: (dt is not null and CAST( ts AS DATE) is not null and s is not null) (type: boolean) + Statistics: Num rows: 905 Data size: 167854 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: s (type: string), (dt - CAST( ts AS DATE)) (type: interval_day_time) outputColumnNames: _col0, _col1 Select Vectorization: className: VectorSelectOperator native: true - projectedOutputColumnNums: [8, 18] - selectExpressions: DateColSubtractDateColumn(col 12:date, col 17:date)(children: CastTimestampToDate(col 10:timestamp) -> 17:date) -> 18:interval_day_time - Statistics: Num rows: 949 Data size: 100594 Basic stats: COMPLETE Column stats: COMPLETE + projectedOutputColumnNums: [8, 17] + selectExpressions: DateColSubtractDateColumn(col 12:date, col 16:date)(children: CastTimestampToDate(col 10:timestamp) -> 16:date) -> 17:interval_day_time + Statistics: Num rows: 905 Data size: 95930 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -240,21 +240,21 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2 input vertices: 1 Map 2 - Statistics: Num rows: 943 Data size: 188600 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 890 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col2 (type: string), _col1 (type: interval_day_time) outputColumnNames: _col0, _col1, _col2 Select Vectorization: className: VectorSelectOperator native: true - projectedOutputColumnNums: [8, 8, 18] - Statistics: Num rows: 943 Data size: 188600 Basic stats: COMPLETE Column stats: COMPLETE + projectedOutputColumnNums: [8, 8, 17] + Statistics: Num rows: 890 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 943 Data size: 188600 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 890 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -274,7 +274,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: vectortab_b_1korc - filterExpr: ((dt - CAST( ts AS DATE)) is not null and s is not null) (type: boolean) + filterExpr: (dt is not null and CAST( ts AS DATE) is not null and s is not null) (type: boolean) Statistics: Num rows: 1000 Data size: 184664 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true @@ -282,18 +282,18 @@ STAGE PLANS: Filter Vectorization: className: VectorFilterOperator native: true - predicateExpression: FilterExprAndExpr(children: SelectColumnIsNotNull(col 16:interval_day_time)(children: DateColSubtractDateColumn(col 12:date, col 15:date)(children: CastTimestampToDate(col 10:timestamp) -> 15:date) -> 16:interval_day_time), SelectColumnIsNotNull(col 8:string)) - predicate: ((dt - CAST( ts AS DATE)) is not null and s is not null) (type: boolean) - Statistics: Num rows: 943 Data size: 174122 Basic stats: COMPLETE Column stats: COMPLETE + predicateExpression: FilterExprAndExpr(children: SelectColumnIsNotNull(col 12:date), SelectColumnIsNotNull(col 15:date)(children: CastTimestampToDate(col 10:timestamp) -> 15:date), SelectColumnIsNotNull(col 8:string)) + predicate: (dt is not null and CAST( ts AS DATE) is not null and s is not null) (type: boolean) + Statistics: Num rows: 890 Data size: 164340 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: s (type: string), (dt - CAST( ts AS DATE)) (type: interval_day_time) outputColumnNames: _col0, _col1 Select Vectorization: className: VectorSelectOperator native: true - projectedOutputColumnNums: [8, 18] - selectExpressions: DateColSubtractDateColumn(col 12:date, col 17:date)(children: CastTimestampToDate(col 10:timestamp) -> 17:date) -> 18:interval_day_time - Statistics: Num rows: 943 Data size: 99958 Basic stats: COMPLETE Column stats: COMPLETE + projectedOutputColumnNums: [8, 17] + selectExpressions: DateColSubtractDateColumn(col 12:date, col 16:date)(children: CastTimestampToDate(col 10:timestamp) -> 16:date) -> 17:interval_day_time + Statistics: Num rows: 890 Data size: 94340 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: interval_day_time) null sort order: zz @@ -303,7 +303,7 @@ STAGE PLANS: className: VectorReduceSinkMultiKeyOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez] 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: 943 Data size: 99958 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 890 Data size: 94340 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs Map Vectorization: