Repository: hive Updated Branches: refs/heads/master c392bccdb -> 2b882d5b1
HIVE-20944: Not validate stats during query compilation (Daniel Dai, reviewed by Ashutosh Chauhan) Signed-off-by: Ashutosh Chauhan <hashut...@apache.org> Project: http://git-wip-us.apache.org/repos/asf/hive/repo Commit: http://git-wip-us.apache.org/repos/asf/hive/commit/2b882d5b Tree: http://git-wip-us.apache.org/repos/asf/hive/tree/2b882d5b Diff: http://git-wip-us.apache.org/repos/asf/hive/diff/2b882d5b Branch: refs/heads/master Commit: 2b882d5b1cb40082dd13eb88147e7ffc97c7b314 Parents: c392bcc Author: Daniel Dai <dai...@gmail.com> Authored: Tue Nov 20 21:16:26 2018 -0800 Committer: Daniel Dai <dai...@gmail.com> Committed: Tue Nov 20 21:16:43 2018 -0800 ---------------------------------------------------------------------- .../apache/hadoop/hive/ql/stats/StatsUtils.java | 4 +- .../results/clientpositive/acid_stats4.q.out | 12 +- .../results/clientpositive/acid_stats5.q.out | 18 +-- .../llap/dynpart_sort_optimization_acid.q.out | 60 ++++----- .../clientpositive/llap/tez_nway_join.q.out | 122 +++++++++---------- .../clientpositive/llap/vector_if_expr_2.q.out | 10 +- .../clientpositive/llap/vector_like_2.q.out | 10 +- .../clientpositive/llap/vector_udf2.q.out | 16 +-- .../llap/vectorized_mapjoin3.q.out | 72 +++++------ .../clientpositive/stats_partial_size.q.out | 12 +- 10 files changed, 168 insertions(+), 168 deletions(-) ---------------------------------------------------------------------- http://git-wip-us.apache.org/repos/asf/hive/blob/2b882d5b/ql/src/java/org/apache/hadoop/hive/ql/stats/StatsUtils.java ---------------------------------------------------------------------- diff --git a/ql/src/java/org/apache/hadoop/hive/ql/stats/StatsUtils.java b/ql/src/java/org/apache/hadoop/hive/ql/stats/StatsUtils.java index b7adc48..bb4196f 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/stats/StatsUtils.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/stats/StatsUtils.java @@ -385,7 +385,7 @@ public class StatsUtils { // skip the step to connect to the metastore. if (neededColsToRetrieve.size() > 0 && partNames.size() > 0) { aggrStats = Hive.get().getAggrColStatsFor(table.getDbName(), table.getTableName(), - neededColsToRetrieve, partNames, true); + neededColsToRetrieve, partNames, false); } boolean statsRetrieved = aggrStats != null && @@ -1025,7 +1025,7 @@ public class StatsUtils { List<ColStatistics> stats = null; try { List<ColumnStatisticsObj> colStat = Hive.get().getTableColumnStatistics( - dbName, tabName, colStatsToRetrieve, true); + dbName, tabName, colStatsToRetrieve, false); stats = convertColStats(colStat, tabName); } catch (HiveException e) { LOG.error("Failed to retrieve table statistics: ", e); http://git-wip-us.apache.org/repos/asf/hive/blob/2b882d5b/ql/src/test/results/clientpositive/acid_stats4.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/acid_stats4.q.out b/ql/src/test/results/clientpositive/acid_stats4.q.out index d317ed0..b36aa4a 100644 --- a/ql/src/test/results/clientpositive/acid_stats4.q.out +++ b/ql/src/test/results/clientpositive/acid_stats4.q.out @@ -265,19 +265,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: stats_nonpart2 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key2 (type: int) outputColumnNames: key2 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(key2) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -285,10 +285,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat http://git-wip-us.apache.org/repos/asf/hive/blob/2b882d5b/ql/src/test/results/clientpositive/acid_stats5.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/acid_stats5.q.out b/ql/src/test/results/clientpositive/acid_stats5.q.out index 21d891a..f9509f2 100644 --- a/ql/src/test/results/clientpositive/acid_stats5.q.out +++ b/ql/src/test/results/clientpositive/acid_stats5.q.out @@ -196,33 +196,33 @@ STAGE PLANS: Map Operator Tree: TableScan alias: stats2 - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: key - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: key (type: int) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: int) mode: partial2 outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(_col0) mode: partial2 outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -236,7 +236,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -244,10 +244,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat http://git-wip-us.apache.org/repos/asf/hive/blob/2b882d5b/ql/src/test/results/clientpositive/llap/dynpart_sort_optimization_acid.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/dynpart_sort_optimization_acid.q.out b/ql/src/test/results/clientpositive/llap/dynpart_sort_optimization_acid.q.out index a52d939..4542b5c 100644 --- a/ql/src/test/results/clientpositive/llap/dynpart_sort_optimization_acid.q.out +++ b/ql/src/test/results/clientpositive/llap/dynpart_sort_optimization_acid.q.out @@ -101,19 +101,19 @@ STAGE PLANS: TableScan alias: acid_part filterExpr: ((key = 'foo') and (ds = '2008-04-08')) (type: boolean) - Statistics: Num rows: 1601 Data size: 150414 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1601 Data size: 139287 Basic stats: COMPLETE Column stats: PARTIAL Filter Operator predicate: (key = 'foo') (type: boolean) - Statistics: Num rows: 5 Data size: 469 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 435 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: ROW__ID (type: struct<writeid:bigint,bucketid:int,rowid:bigint>) outputColumnNames: _col0 - Statistics: Num rows: 5 Data size: 469 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 1720 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator key expressions: _col0 (type: struct<writeid:bigint,bucketid:int,rowid:bigint>) sort order: + Map-reduce partition columns: UDFToInteger(_col0) (type: int) - Statistics: Num rows: 5 Data size: 469 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 1720 Basic stats: COMPLETE Column stats: PARTIAL Execution mode: llap LLAP IO: may be used (ACID table) Reducer 2 @@ -122,10 +122,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: struct<writeid:bigint,bucketid:int,rowid:bigint>), 'foo' (type: string), 'bar' (type: string), '2008-04-08' (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 5 Data size: 469 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 1720 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 5 Data size: 469 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 1720 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat @@ -203,19 +203,19 @@ STAGE PLANS: TableScan alias: acid_part filterExpr: ((key = 'foo') and (ds = '2008-04-08')) (type: boolean) - Statistics: Num rows: 1601 Data size: 150414 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1601 Data size: 139287 Basic stats: COMPLETE Column stats: PARTIAL Filter Operator predicate: (key = 'foo') (type: boolean) - Statistics: Num rows: 5 Data size: 469 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 435 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: ROW__ID (type: struct<writeid:bigint,bucketid:int,rowid:bigint>) outputColumnNames: _col0 - Statistics: Num rows: 5 Data size: 469 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 1720 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator key expressions: _col0 (type: struct<writeid:bigint,bucketid:int,rowid:bigint>) sort order: + Map-reduce partition columns: UDFToInteger(_col0) (type: int) - Statistics: Num rows: 5 Data size: 469 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 1720 Basic stats: COMPLETE Column stats: PARTIAL Execution mode: llap LLAP IO: may be used (ACID table) Reducer 2 @@ -224,10 +224,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: struct<writeid:bigint,bucketid:int,rowid:bigint>), 'foo' (type: string), 'bar' (type: string), '2008-04-08' (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 5 Data size: 469 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 1720 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 5 Data size: 469 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 1720 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat @@ -708,19 +708,19 @@ STAGE PLANS: TableScan alias: acid_2l_part filterExpr: ((key = 'foo') and (ds = '2008-04-08') and (hr = 11)) (type: boolean) - Statistics: Num rows: 1601 Data size: 150414 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1601 Data size: 139287 Basic stats: COMPLETE Column stats: PARTIAL Filter Operator predicate: (key = 'foo') (type: boolean) - Statistics: Num rows: 5 Data size: 469 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 435 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: ROW__ID (type: struct<writeid:bigint,bucketid:int,rowid:bigint>) outputColumnNames: _col0 - Statistics: Num rows: 5 Data size: 469 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 1740 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator key expressions: _col0 (type: struct<writeid:bigint,bucketid:int,rowid:bigint>) sort order: + Map-reduce partition columns: UDFToInteger(_col0) (type: int) - Statistics: Num rows: 5 Data size: 469 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 1740 Basic stats: COMPLETE Column stats: PARTIAL Execution mode: llap LLAP IO: may be used (ACID table) Reducer 2 @@ -729,10 +729,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: struct<writeid:bigint,bucketid:int,rowid:bigint>), 'foo' (type: string), 'bar' (type: string), '2008-04-08' (type: string), 11 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 5 Data size: 469 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 1740 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 5 Data size: 469 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 1740 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat @@ -815,19 +815,19 @@ STAGE PLANS: TableScan alias: acid_2l_part filterExpr: ((key = 'foo') and (ds = '2008-04-08') and (hr >= 11)) (type: boolean) - Statistics: Num rows: 3201 Data size: 313458 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 3201 Data size: 291291 Basic stats: COMPLETE Column stats: PARTIAL Filter Operator predicate: (key = 'foo') (type: boolean) - Statistics: Num rows: 5 Data size: 455 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 10 Data size: 910 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: ROW__ID (type: struct<writeid:bigint,bucketid:int,rowid:bigint>), hr (type: int) outputColumnNames: _col0, _col4 - Statistics: Num rows: 5 Data size: 1740 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 10 Data size: 3480 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator key expressions: _col0 (type: struct<writeid:bigint,bucketid:int,rowid:bigint>) sort order: + Map-reduce partition columns: UDFToInteger(_col0) (type: int) - Statistics: Num rows: 5 Data size: 1740 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 10 Data size: 3480 Basic stats: COMPLETE Column stats: PARTIAL value expressions: _col4 (type: int) Execution mode: llap LLAP IO: may be used (ACID table) @@ -837,10 +837,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: struct<writeid:bigint,bucketid:int,rowid:bigint>), 'foo' (type: string), 'bar' (type: string), '2008-04-08' (type: string), VALUE._col2 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 5 Data size: 1740 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 10 Data size: 3480 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 5 Data size: 1740 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 10 Data size: 3480 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat @@ -960,19 +960,19 @@ STAGE PLANS: TableScan alias: acid_2l_part filterExpr: (value = 'bar') (type: boolean) - Statistics: Num rows: 4200 Data size: 1253037 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 4200 Data size: 1171800 Basic stats: COMPLETE Column stats: PARTIAL Filter Operator predicate: (value = 'bar') (type: boolean) - Statistics: Num rows: 5 Data size: 1375 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 14 Data size: 3906 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: ROW__ID (type: struct<writeid:bigint,bucketid:int,rowid:bigint>), ds (type: string), hr (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 5 Data size: 1320 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 14 Data size: 3696 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator key expressions: _col0 (type: struct<writeid:bigint,bucketid:int,rowid:bigint>) sort order: + Map-reduce partition columns: UDFToInteger(_col0) (type: int) - Statistics: Num rows: 5 Data size: 1320 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 14 Data size: 3696 Basic stats: COMPLETE Column stats: PARTIAL value expressions: _col1 (type: string), _col2 (type: int) Execution mode: llap LLAP IO: may be used (ACID table) @@ -982,10 +982,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: struct<writeid:bigint,bucketid:int,rowid:bigint>), VALUE._col0 (type: string), VALUE._col1 (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 5 Data size: 1320 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 14 Data size: 3696 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 5 Data size: 1320 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 14 Data size: 3696 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat http://git-wip-us.apache.org/repos/asf/hive/blob/2b882d5b/ql/src/test/results/clientpositive/llap/tez_nway_join.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/tez_nway_join.q.out b/ql/src/test/results/clientpositive/llap/tez_nway_join.q.out index 288f64c..0bf2796 100644 --- a/ql/src/test/results/clientpositive/llap/tez_nway_join.q.out +++ b/ql/src/test/results/clientpositive/llap/tez_nway_join.q.out @@ -60,14 +60,14 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -79,15 +79,15 @@ STAGE PLANS: input vertices: 1 Map 3 2 Map 4 - Statistics: Num rows: 6 Data size: 26 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: vectorized, llap LLAP IO: all inputs @@ -96,19 +96,19 @@ STAGE PLANS: TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs Map 4 @@ -116,19 +116,19 @@ STAGE PLANS: TableScan alias: c filterExpr: key is not null (type: boolean) - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs Reducer 2 @@ -138,10 +138,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -181,14 +181,14 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -198,7 +198,7 @@ STAGE PLANS: outputColumnNames: _col0 input vertices: 1 Map 3 - Statistics: Num rows: 3 Data size: 13 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -207,15 +207,15 @@ STAGE PLANS: 1 _col0 (type: int) input vertices: 1 Map 4 - Statistics: Num rows: 3 Data size: 14 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: vectorized, llap LLAP IO: all inputs @@ -224,19 +224,19 @@ STAGE PLANS: TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs Map 4 @@ -244,19 +244,19 @@ STAGE PLANS: TableScan alias: c filterExpr: key is not null (type: boolean) - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs Reducer 2 @@ -266,10 +266,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -330,48 +330,48 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs Map 4 Map Operator Tree: TableScan alias: b - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs Map 5 Map Operator Tree: TableScan alias: c - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs Reducer 2 @@ -385,15 +385,15 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) 2 _col0 (type: int) - Statistics: Num rows: 6 Data size: 26 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Reducer 3 Execution mode: vectorized, llap @@ -402,10 +402,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -444,11 +444,11 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Left Outer Join 0 to 1 @@ -458,7 +458,7 @@ STAGE PLANS: outputColumnNames: _col0 input vertices: 1 Map 3 - Statistics: Num rows: 3 Data size: 13 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Left Outer Join 0 to 1 @@ -467,15 +467,15 @@ STAGE PLANS: 1 _col0 (type: int) input vertices: 1 Map 4 - Statistics: Num rows: 3 Data size: 14 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: vectorized, llap LLAP IO: all inputs @@ -483,32 +483,32 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs Map 4 Map Operator Tree: TableScan alias: c - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs Reducer 2 @@ -518,10 +518,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat http://git-wip-us.apache.org/repos/asf/hive/blob/2b882d5b/ql/src/test/results/clientpositive/llap/vector_if_expr_2.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/vector_if_expr_2.q.out b/ql/src/test/results/clientpositive/llap/vector_if_expr_2.q.out index 8bf3016..e9e82d6 100644 --- a/ql/src/test/results/clientpositive/llap/vector_if_expr_2.q.out +++ b/ql/src/test/results/clientpositive/llap/vector_if_expr_2.q.out @@ -50,7 +50,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: foo - Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true Select Operator @@ -61,7 +61,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [0, 4] selectExpressions: IfExprLongColumnLongScalar(col 3:boolean, col 1:int, val 0)(children: LongColGreaterLongScalar(col 0:int, val 0) -> 3:boolean) -> 4:int - Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + @@ -69,7 +69,7 @@ STAGE PLANS: className: VectorReduceSinkObjectHashOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: int) Execution mode: vectorized, llap LLAP IO: all inputs @@ -98,13 +98,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 1] - Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat http://git-wip-us.apache.org/repos/asf/hive/blob/2b882d5b/ql/src/test/results/clientpositive/llap/vector_like_2.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/vector_like_2.q.out b/ql/src/test/results/clientpositive/llap/vector_like_2.q.out index ec80136..99ca5d6 100644 --- a/ql/src/test/results/clientpositive/llap/vector_like_2.q.out +++ b/ql/src/test/results/clientpositive/llap/vector_like_2.q.out @@ -49,7 +49,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: foo - Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 267 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:a:string, 1:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>] @@ -61,7 +61,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [0, 2] selectExpressions: SelectStringColLikeStringScalar(col 0:string) -> 2:boolean - Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + @@ -71,7 +71,7 @@ STAGE PLANS: native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true valueColumns: 2:boolean - Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: boolean) Execution mode: vectorized, llap LLAP IO: all inputs @@ -113,13 +113,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 1] - Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat http://git-wip-us.apache.org/repos/asf/hive/blob/2b882d5b/ql/src/test/results/clientpositive/llap/vector_udf2.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/vector_udf2.q.out b/ql/src/test/results/clientpositive/llap/vector_udf2.q.out index 266211c..0e1ab60 100644 --- a/ql/src/test/results/clientpositive/llap/vector_udf2.q.out +++ b/ql/src/test/results/clientpositive/llap/vector_udf2.q.out @@ -187,7 +187,7 @@ STAGE PLANS: TableScan alias: hive_14349 filterExpr: (a like 'XYZ%a%') (type: boolean) - Statistics: Num rows: 2 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true Filter Operator @@ -196,7 +196,7 @@ STAGE PLANS: native: true predicateExpression: FilterStringColLikeStringScalar(col 0:string, pattern XYZ%a%) predicate: (a like 'XYZ%a%') (type: boolean) - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 90 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: a (type: string) outputColumnNames: _col0 @@ -204,13 +204,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0] - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 90 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 90 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -279,7 +279,7 @@ STAGE PLANS: TableScan alias: hive_14349 filterExpr: (a like 'XYZ%a_') (type: boolean) - Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true Filter Operator @@ -288,7 +288,7 @@ STAGE PLANS: native: true predicateExpression: FilterStringColLikeStringScalar(col 0:string, pattern XYZ%a_) predicate: (a like 'XYZ%a_') (type: boolean) - Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: a (type: string) outputColumnNames: _col0 @@ -296,13 +296,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0] - Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat http://git-wip-us.apache.org/repos/asf/hive/blob/2b882d5b/ql/src/test/results/clientpositive/llap/vectorized_mapjoin3.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/vectorized_mapjoin3.q.out b/ql/src/test/results/clientpositive/llap/vectorized_mapjoin3.q.out index 4013b36..fa9103f 100644 --- a/ql/src/test/results/clientpositive/llap/vectorized_mapjoin3.q.out +++ b/ql/src/test/results/clientpositive/llap/vectorized_mapjoin3.q.out @@ -126,7 +126,7 @@ STAGE PLANS: TableScan alias: t1 filterExpr: (decimal0801_col is not null and int_col_1 is not null) (type: boolean) - Statistics: Num rows: 5 Data size: 580 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 580 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:decimal0801_col:decimal(8,1)/DECIMAL_64, 1:int_col_1:int, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>] @@ -136,7 +136,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprAndExpr(children: SelectColumnIsNotNull(col 0:decimal(8,1)/DECIMAL_64), SelectColumnIsNotNull(col 1:int)) predicate: (decimal0801_col is not null and int_col_1 is not null) (type: boolean) - Statistics: Num rows: 5 Data size: 580 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 464 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: decimal0801_col (type: decimal(8,1)), int_col_1 (type: int) outputColumnNames: _col0, _col1 @@ -144,7 +144,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 1] - Statistics: Num rows: 5 Data size: 580 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 464 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -165,13 +165,13 @@ STAGE PLANS: outputColumnNames: _col0 input vertices: 1 Reducer 3 - Statistics: Num rows: 5 Data size: 638 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 5 Data size: 638 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -197,7 +197,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: tt1 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:int_col_0:int, 1:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>] @@ -208,7 +208,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0] - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: max(int_col_0) Group By Vectorization: @@ -220,7 +220,7 @@ STAGE PLANS: projectedOutputColumnNums: [0] mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: Reduce Sink Vectorization: @@ -228,7 +228,7 @@ STAGE PLANS: native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true valueColumns: 0:int - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int) Execution mode: vectorized, llap LLAP IO: all inputs @@ -274,14 +274,14 @@ STAGE PLANS: projectedOutputColumnNums: [0] mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator Filter Vectorization: className: VectorFilterOperator native: true predicateExpression: SelectColumnIsNotNull(col 0:int) predicate: _col0 is not null (type: boolean) - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + @@ -291,7 +291,7 @@ STAGE PLANS: keyColumns: 0:int native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Stage: Stage-0 Fetch Operator @@ -337,7 +337,7 @@ STAGE PLANS: TableScan alias: t1 filterExpr: (int_col_1 is not null and decimal0801_col is not null) (type: boolean) - Statistics: Num rows: 5 Data size: 580 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 580 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:decimal0801_col:decimal(8,1)/DECIMAL_64, 1:int_col_1:int, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>] @@ -347,7 +347,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprAndExpr(children: SelectColumnIsNotNull(col 1:int), SelectColumnIsNotNull(col 0:decimal(8,1)/DECIMAL_64)) predicate: (decimal0801_col is not null and int_col_1 is not null) (type: boolean) - Statistics: Num rows: 5 Data size: 580 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 464 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: decimal0801_col (type: decimal(8,1)), int_col_1 (type: int) outputColumnNames: _col0, _col1 @@ -355,7 +355,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 1] - Statistics: Num rows: 5 Data size: 580 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 464 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -376,13 +376,13 @@ STAGE PLANS: outputColumnNames: _col0 input vertices: 1 Reducer 3 - Statistics: Num rows: 5 Data size: 638 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 5 Data size: 638 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -408,7 +408,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: tt1 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:int_col_0:int, 1:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>] @@ -419,7 +419,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0] - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: max(int_col_0) Group By Vectorization: @@ -431,7 +431,7 @@ STAGE PLANS: projectedOutputColumnNums: [0] mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: Reduce Sink Vectorization: @@ -439,7 +439,7 @@ STAGE PLANS: native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true valueColumns: 0:int - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int) Execution mode: vectorized, llap LLAP IO: all inputs @@ -485,14 +485,14 @@ STAGE PLANS: projectedOutputColumnNums: [0] mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator Filter Vectorization: className: VectorFilterOperator native: true predicateExpression: SelectColumnIsNotNull(col 0:int) predicate: _col0 is not null (type: boolean) - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + @@ -502,7 +502,7 @@ STAGE PLANS: keyColumns: 0:int native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Stage: Stage-0 Fetch Operator @@ -548,7 +548,7 @@ STAGE PLANS: TableScan alias: t1 filterExpr: (decimal0801_col is not null and int_col_1 is not null) (type: boolean) - Statistics: Num rows: 5 Data size: 580 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 580 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:decimal0801_col:decimal(8,1)/DECIMAL_64, 1:int_col_1:int, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>] @@ -558,7 +558,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprAndExpr(children: SelectColumnIsNotNull(col 0:decimal(8,1)/DECIMAL_64), SelectColumnIsNotNull(col 1:int)) predicate: (decimal0801_col is not null and int_col_1 is not null) (type: boolean) - Statistics: Num rows: 5 Data size: 580 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 464 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: decimal0801_col (type: decimal(8,1)), int_col_1 (type: int) outputColumnNames: _col0, _col1 @@ -566,7 +566,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 1] - Statistics: Num rows: 5 Data size: 580 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 464 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -587,13 +587,13 @@ STAGE PLANS: outputColumnNames: _col0 input vertices: 1 Reducer 3 - Statistics: Num rows: 5 Data size: 638 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 5 Data size: 638 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -619,7 +619,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: tt1 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:int_col_0:int, 1:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>] @@ -630,7 +630,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0] - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: max(int_col_0) Group By Vectorization: @@ -642,7 +642,7 @@ STAGE PLANS: projectedOutputColumnNums: [0] mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: Reduce Sink Vectorization: @@ -650,7 +650,7 @@ STAGE PLANS: native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true valueColumns: 0:int - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int) Execution mode: vectorized, llap LLAP IO: all inputs @@ -696,14 +696,14 @@ STAGE PLANS: projectedOutputColumnNums: [0] mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator Filter Vectorization: className: VectorFilterOperator native: true predicateExpression: SelectColumnIsNotNull(col 0:int) predicate: _col0 is not null (type: boolean) - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + @@ -713,7 +713,7 @@ STAGE PLANS: keyColumns: 0:int native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Stage: Stage-0 Fetch Operator http://git-wip-us.apache.org/repos/asf/hive/blob/2b882d5b/ql/src/test/results/clientpositive/stats_partial_size.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/stats_partial_size.q.out b/ql/src/test/results/clientpositive/stats_partial_size.q.out index a1bf375..824dd19 100644 --- a/ql/src/test/results/clientpositive/stats_partial_size.q.out +++ b/ql/src/test/results/clientpositive/stats_partial_size.q.out @@ -74,19 +74,19 @@ STAGE PLANS: TableScan alias: sample filterExpr: y is not null (type: boolean) - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: y is not null (type: boolean) - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: y (type: int) outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -95,10 +95,10 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col0 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 17 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 17 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
