HIVE-15784: Vectorization: Turn on text vectorization by default (vector serde) (Matt McCline, reviewed by Sergey Shelukhin)
Project: http://git-wip-us.apache.org/repos/asf/hive/repo Commit: http://git-wip-us.apache.org/repos/asf/hive/commit/ce695b5d Tree: http://git-wip-us.apache.org/repos/asf/hive/tree/ce695b5d Diff: http://git-wip-us.apache.org/repos/asf/hive/diff/ce695b5d Branch: refs/heads/master Commit: ce695b5d4ae07d0bfc79fb88fcb09cb99e9e4706 Parents: 9f5a3e3 Author: Matt McCline <mmccl...@hortonworks.com> Authored: Wed Mar 22 03:06:34 2017 -0500 Committer: Matt McCline <mmccl...@hortonworks.com> Committed: Wed Mar 22 03:06:34 2017 -0500 ---------------------------------------------------------------------- .../org/apache/hadoop/hive/conf/HiveConf.java | 4 +- .../hive/ql/optimizer/physical/Vectorizer.java | 1 + .../clientpositive/vector_groupby_mapjoin.q | 14 + .../clientpositive/vectorized_parquet_types.q | 5 +- .../llap/dynpart_sort_opt_vectorization.q.out | 4 +- .../llap/dynpart_sort_optimization2.q.out | 4 +- .../results/clientpositive/llap/mergejoin.q.out | 8 +- .../clientpositive/llap/tez_join_hash.q.out | 10 +- .../llap/tez_vector_dynpart_hashjoin_2.q.out | 8 +- .../clientpositive/llap/vector_bucket.q.out | 21 +- .../llap/vector_decimal_round.q.out | 44 +- .../llap/vector_groupby_mapjoin.q.out | 133 +++++- .../llap/vector_mapjoin_reduce.q.out | 167 ++++++- .../llap/vector_udf_character_length.q.out | 2 +- .../llap/vector_udf_octet_length.q.out | 2 +- .../llap/vectorized_bucketmapjoin1.q.out | 21 +- .../vectorized_dynamic_partition_pruning.q.out | 470 +++++++++++++------ .../clientpositive/llap/vectorized_join46.q.out | 58 +-- .../llap/vectorized_parquet_types.q.out | 189 ++++++-- .../test/results/clientpositive/mergejoin.q.out | 11 + .../spark/vector_mapjoin_reduce.q.out | 157 ++++++- .../test/results/clientpositive/structin.q.out | 1 + .../clientpositive/tez/explainuser_3.q.out | 20 +- .../results/clientpositive/tez_join_hash.q.out | 5 + .../results/clientpositive/vector_bucket.q.out | 21 +- .../clientpositive/vector_cast_constant.q.out | 17 +- .../results/clientpositive/vector_char_2.q.out | 34 +- .../clientpositive/vector_decimal_round.q.out | 43 +- .../clientpositive/vector_groupby4.q.out | 17 +- .../clientpositive/vector_groupby6.q.out | 17 +- .../clientpositive/vector_groupby_mapjoin.q.out | 165 ++++++- .../clientpositive/vector_groupby_reduce.q.out | 51 +- .../clientpositive/vector_mapjoin_reduce.q.out | 112 ++++- .../vector_mr_diff_schema_alias.q.out | 18 +- .../clientpositive/vector_orderby_5.q.out | 17 +- .../vector_reduce_groupby_decimal.q.out | 17 +- .../clientpositive/vector_string_concat.q.out | 17 +- .../vector_tablesample_rows.q.out | 17 +- .../vector_udf_character_length.q.out | 1 + .../vector_udf_octet_length.q.out | 1 + .../clientpositive/vectorization_13.q.out | 34 +- .../clientpositive/vectorization_14.q.out | 9 +- .../clientpositive/vectorization_15.q.out | 9 +- .../clientpositive/vectorization_limit.q.out | 17 +- .../clientpositive/vectorized_date_funcs.q.out | 17 +- .../vectorized_parquet_types.q.out | 17 +- .../clientpositive/vectorized_shufflejoin.q.out | 23 +- 47 files changed, 1658 insertions(+), 392 deletions(-) ---------------------------------------------------------------------- http://git-wip-us.apache.org/repos/asf/hive/blob/ce695b5d/common/src/java/org/apache/hadoop/hive/conf/HiveConf.java ---------------------------------------------------------------------- diff --git a/common/src/java/org/apache/hadoop/hive/conf/HiveConf.java b/common/src/java/org/apache/hadoop/hive/conf/HiveConf.java index 62908f9..1b186f7 100644 --- a/common/src/java/org/apache/hadoop/hive/conf/HiveConf.java +++ b/common/src/java/org/apache/hadoop/hive/conf/HiveConf.java @@ -2751,9 +2751,9 @@ public class HiveConf extends Configuration { HIVE_VECTORIZATION_USE_VECTORIZED_INPUT_FILE_FORMAT("hive.vectorized.use.vectorized.input.format", true, "This flag should be set to true to enable vectorizing with vectorized input file format capable SerDe.\n" + "The default value is true."), - HIVE_VECTORIZATION_USE_VECTOR_DESERIALIZE("hive.vectorized.use.vector.serde.deserialize", false, + HIVE_VECTORIZATION_USE_VECTOR_DESERIALIZE("hive.vectorized.use.vector.serde.deserialize", true, "This flag should be set to true to enable vectorizing rows using vector deserialize.\n" + - "The default value is false."), + "The default value is true."), HIVE_VECTORIZATION_USE_ROW_DESERIALIZE("hive.vectorized.use.row.serde.deserialize", false, "This flag should be set to true to enable vectorizing using row deserialize.\n" + "The default value is false."), http://git-wip-us.apache.org/repos/asf/hive/blob/ce695b5d/ql/src/java/org/apache/hadoop/hive/ql/optimizer/physical/Vectorizer.java ---------------------------------------------------------------------- diff --git a/ql/src/java/org/apache/hadoop/hive/ql/optimizer/physical/Vectorizer.java b/ql/src/java/org/apache/hadoop/hive/ql/optimizer/physical/Vectorizer.java index bf60c10..2f85379 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/optimizer/physical/Vectorizer.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/optimizer/physical/Vectorizer.java @@ -749,6 +749,7 @@ public class Vectorizer implements PhysicalPlanResolver { if (!isSchemaEvolution) { enabledConditionsNotMetList.add( "Vectorizing tables without Schema Evolution requires " + HiveConf.ConfVars.HIVE_VECTORIZATION_USE_VECTORIZED_INPUT_FILE_FORMAT.varname); + return false; } String deserializerClassName = pd.getDeserializerClassName(); http://git-wip-us.apache.org/repos/asf/hive/blob/ce695b5d/ql/src/test/queries/clientpositive/vector_groupby_mapjoin.q ---------------------------------------------------------------------- diff --git a/ql/src/test/queries/clientpositive/vector_groupby_mapjoin.q b/ql/src/test/queries/clientpositive/vector_groupby_mapjoin.q index c692182..0c24441 100644 --- a/ql/src/test/queries/clientpositive/vector_groupby_mapjoin.q +++ b/ql/src/test/queries/clientpositive/vector_groupby_mapjoin.q @@ -20,3 +20,17 @@ from src where not key in (select key from src) order by key; + +CREATE TABLE orcsrc STORED AS ORC AS SELECT * FROM src; + +select * +from orcsrc +where not key in +(select key from orcsrc) +order by key; + +select * +from orcsrc +where not key in +(select key from orcsrc) +order by key; http://git-wip-us.apache.org/repos/asf/hive/blob/ce695b5d/ql/src/test/queries/clientpositive/vectorized_parquet_types.q ---------------------------------------------------------------------- diff --git a/ql/src/test/queries/clientpositive/vectorized_parquet_types.q b/ql/src/test/queries/clientpositive/vectorized_parquet_types.q index 68761b6..7467cb3 100644 --- a/ql/src/test/queries/clientpositive/vectorized_parquet_types.q +++ b/ql/src/test/queries/clientpositive/vectorized_parquet_types.q @@ -1,6 +1,5 @@ set hive.mapred.mode=nonstrict; -SET hive.vectorized.execution.enabled=true; -set hive.explain.user=true; +set hive.explain.user=false; DROP TABLE parquet_types_staging; DROP TABLE parquet_types; @@ -47,6 +46,8 @@ INSERT OVERWRITE TABLE parquet_types SELECT cint, ctinyint, csmallint, cfloat, cdouble, cstring1, t, cchar, cvarchar, unhex(cbinary), cdecimal FROM parquet_types_staging; +SET hive.vectorized.execution.enabled=true; + -- select explain vectorization expression SELECT cint, ctinyint, csmallint, cfloat, cdouble, cstring1, t, cchar, cvarchar, http://git-wip-us.apache.org/repos/asf/hive/blob/ce695b5d/ql/src/test/results/clientpositive/llap/dynpart_sort_opt_vectorization.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/dynpart_sort_opt_vectorization.q.out b/ql/src/test/results/clientpositive/llap/dynpart_sort_opt_vectorization.q.out index 85d65d6..ea98417 100644 --- a/ql/src/test/results/clientpositive/llap/dynpart_sort_opt_vectorization.q.out +++ b/ql/src/test/results/clientpositive/llap/dynpart_sort_opt_vectorization.q.out @@ -2351,7 +2351,7 @@ 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: no inputs Reducer 2 Execution mode: vectorized, llap @@ -2567,7 +2567,7 @@ 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: no inputs Reducer 2 Execution mode: vectorized, llap http://git-wip-us.apache.org/repos/asf/hive/blob/ce695b5d/ql/src/test/results/clientpositive/llap/dynpart_sort_optimization2.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/dynpart_sort_optimization2.q.out b/ql/src/test/results/clientpositive/llap/dynpart_sort_optimization2.q.out index 667d980..d4811d6 100644 --- a/ql/src/test/results/clientpositive/llap/dynpart_sort_optimization2.q.out +++ b/ql/src/test/results/clientpositive/llap/dynpart_sort_optimization2.q.out @@ -1631,7 +1631,7 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 205 Data size: 19475 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) - Execution mode: llap + Execution mode: vectorized, llap LLAP IO: no inputs Reducer 2 Execution mode: vectorized, llap @@ -1761,7 +1761,7 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 205 Data size: 19475 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) - Execution mode: llap + Execution mode: vectorized, llap LLAP IO: no inputs Reducer 2 Execution mode: vectorized, llap http://git-wip-us.apache.org/repos/asf/hive/blob/ce695b5d/ql/src/test/results/clientpositive/llap/mergejoin.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/mergejoin.q.out b/ql/src/test/results/clientpositive/llap/mergejoin.q.out index ae99e66..186600b 100644 --- a/ql/src/test/results/clientpositive/llap/mergejoin.q.out +++ b/ql/src/test/results/clientpositive/llap/mergejoin.q.out @@ -37,7 +37,7 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) - Execution mode: llap + Execution mode: vectorized, llap LLAP IO: no inputs Map 3 Map Operator Tree: @@ -71,7 +71,7 @@ STAGE PLANS: sort order: Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: binary) - Execution mode: llap + Execution mode: vectorized, llap LLAP IO: no inputs Reducer 2 Execution mode: llap @@ -1884,7 +1884,7 @@ STAGE PLANS: sort order: Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: binary) - Execution mode: llap + Execution mode: vectorized, llap LLAP IO: no inputs Reducer 2 Execution mode: llap @@ -2577,7 +2577,7 @@ STAGE PLANS: sort order: Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: binary) - Execution mode: llap + Execution mode: vectorized, llap LLAP IO: no inputs Reducer 2 Execution mode: llap http://git-wip-us.apache.org/repos/asf/hive/blob/ce695b5d/ql/src/test/results/clientpositive/llap/tez_join_hash.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/tez_join_hash.q.out b/ql/src/test/results/clientpositive/llap/tez_join_hash.q.out index ef4556a..92a188e 100644 --- a/ql/src/test/results/clientpositive/llap/tez_join_hash.q.out +++ b/ql/src/test/results/clientpositive/llap/tez_join_hash.q.out @@ -52,7 +52,7 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: llap + Execution mode: vectorized, llap LLAP IO: no inputs Map 4 Map Operator Tree: @@ -170,7 +170,7 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 2000 Data size: 356000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) - Execution mode: llap + Execution mode: vectorized, llap LLAP IO: no inputs Map 6 Map Operator Tree: @@ -189,7 +189,7 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 2000 Data size: 174000 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: llap + Execution mode: vectorized, llap LLAP IO: no inputs Map 7 Map Operator Tree: @@ -209,7 +209,7 @@ STAGE PLANS: Map-reduce partition columns: _col1 (type: string) Statistics: Num rows: 21512 Data size: 3829136 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string) - Execution mode: llap + Execution mode: vectorized, llap LLAP IO: no inputs Map 8 Map Operator Tree: @@ -228,7 +228,7 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: llap + Execution mode: vectorized, llap LLAP IO: no inputs Reducer 2 Execution mode: llap http://git-wip-us.apache.org/repos/asf/hive/blob/ce695b5d/ql/src/test/results/clientpositive/llap/tez_vector_dynpart_hashjoin_2.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/tez_vector_dynpart_hashjoin_2.q.out b/ql/src/test/results/clientpositive/llap/tez_vector_dynpart_hashjoin_2.q.out index 9c1b3af..6eba119 100644 --- a/ql/src/test/results/clientpositive/llap/tez_vector_dynpart_hashjoin_2.q.out +++ b/ql/src/test/results/clientpositive/llap/tez_vector_dynpart_hashjoin_2.q.out @@ -263,7 +263,7 @@ STAGE PLANS: sort order: + Map-reduce partition columns: UDFToInteger(_col0) (type: int) Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: llap + Execution mode: vectorized, llap LLAP IO: no inputs Map 5 Map Operator Tree: @@ -282,7 +282,7 @@ STAGE PLANS: sort order: + Map-reduce partition columns: (UDFToInteger(_col0) + 0) (type: int) Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: llap + Execution mode: vectorized, llap LLAP IO: no inputs Reducer 2 Execution mode: llap @@ -454,7 +454,7 @@ STAGE PLANS: sort order: + Map-reduce partition columns: UDFToInteger(_col0) (type: int) Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: llap + Execution mode: vectorized, llap LLAP IO: no inputs Map 5 Map Operator Tree: @@ -473,7 +473,7 @@ STAGE PLANS: sort order: + Map-reduce partition columns: (UDFToInteger(_col0) + 0) (type: int) Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: llap + Execution mode: vectorized, llap LLAP IO: no inputs Reducer 2 Execution mode: llap http://git-wip-us.apache.org/repos/asf/hive/blob/ce695b5d/ql/src/test/results/clientpositive/llap/vector_bucket.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/vector_bucket.q.out b/ql/src/test/results/clientpositive/llap/vector_bucket.q.out index 18dcce2..7b57223 100644 --- a/ql/src/test/results/clientpositive/llap/vector_bucket.q.out +++ b/ql/src/test/results/clientpositive/llap/vector_bucket.q.out @@ -35,21 +35,36 @@ STAGE PLANS: TableScan alias: values__tmp__table__1 Statistics: Num rows: 1 Data size: 26 Basic stats: COMPLETE Column stats: NONE + TableScan Vectorization: + native: true + projectedOutputColumns: [0, 1] Select Operator expressions: tmp_values_col1 (type: string), tmp_values_col2 (type: string) outputColumnNames: _col0, _col1 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumns: [0, 1] Statistics: Num rows: 1 Data size: 26 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: Map-reduce partition columns: UDFToInteger(_col0) (type: int) + Reduce Sink Vectorization: + className: VectorReduceSinkObjectHashOperator + native: true + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true Statistics: Num rows: 1 Data size: 26 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: string), _col1 (type: string) - Execution mode: llap + Execution mode: vectorized, llap LLAP IO: no inputs Map Vectorization: - enabled: false - enabledConditionsNotMet: hive.vectorized.use.vector.serde.deserialize IS false + enabled: true + enabledConditionsMet: hive.vectorized.use.vector.serde.deserialize IS true + groupByVectorOutput: true inputFileFormats: org.apache.hadoop.mapred.TextInputFormat + allNative: true + usesVectorUDFAdaptor: false + vectorized: true Reducer 2 Execution mode: vectorized, llap Reduce Vectorization: http://git-wip-us.apache.org/repos/asf/hive/blob/ce695b5d/ql/src/test/results/clientpositive/llap/vector_decimal_round.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/vector_decimal_round.q.out b/ql/src/test/results/clientpositive/llap/vector_decimal_round.q.out index 2a5e515..07a7433 100644 --- a/ql/src/test/results/clientpositive/llap/vector_decimal_round.q.out +++ b/ql/src/test/results/clientpositive/llap/vector_decimal_round.q.out @@ -55,21 +55,37 @@ STAGE PLANS: TableScan alias: decimal_tbl_txt Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE + TableScan Vectorization: + native: true + projectedOutputColumns: [0] Select Operator expressions: dec (type: decimal(10,0)), round(dec, -1) (type: decimal(11,0)) outputColumnNames: _col0, _col1 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumns: [0, 1] + selectExpressions: FuncRoundWithNumDigitsDecimalToDecimal(col 0, decimalPlaces -1) -> 1:decimal(11,0) Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: decimal(10,0)) sort order: + + Reduce Sink Vectorization: + className: VectorReduceSinkObjectHashOperator + native: true + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: decimal(11,0)) - Execution mode: llap + Execution mode: vectorized, llap LLAP IO: no inputs Map Vectorization: - enabled: false - enabledConditionsNotMet: hive.vectorized.use.vector.serde.deserialize IS false + enabled: true + enabledConditionsMet: hive.vectorized.use.vector.serde.deserialize IS true + groupByVectorOutput: true inputFileFormats: org.apache.hadoop.mapred.TextInputFormat + allNative: true + usesVectorUDFAdaptor: false + vectorized: true Reducer 2 Execution mode: vectorized, llap Reduce Vectorization: @@ -141,21 +157,37 @@ STAGE PLANS: TableScan alias: decimal_tbl_txt Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE + TableScan Vectorization: + native: true + projectedOutputColumns: [0] Select Operator expressions: dec (type: decimal(10,0)) outputColumnNames: _col0 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumns: [0] Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: round(_col0, -1) (type: decimal(11,0)) sort order: + + Reduce Sink Vectorization: + className: VectorReduceSinkObjectHashOperator + keyExpressions: FuncRoundWithNumDigitsDecimalToDecimal(col 0, decimalPlaces -1) -> 1:decimal(11,0) + native: true + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: decimal(10,0)) - Execution mode: llap + Execution mode: vectorized, llap LLAP IO: no inputs Map Vectorization: - enabled: false - enabledConditionsNotMet: hive.vectorized.use.vector.serde.deserialize IS false + enabled: true + enabledConditionsMet: hive.vectorized.use.vector.serde.deserialize IS true + groupByVectorOutput: true inputFileFormats: org.apache.hadoop.mapred.TextInputFormat + allNative: true + usesVectorUDFAdaptor: false + vectorized: true Reducer 2 Execution mode: vectorized, llap Reduce Vectorization: http://git-wip-us.apache.org/repos/asf/hive/blob/ce695b5d/ql/src/test/results/clientpositive/llap/vector_groupby_mapjoin.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/vector_groupby_mapjoin.q.out b/ql/src/test/results/clientpositive/llap/vector_groupby_mapjoin.q.out index af5a5ab..1b1ec9e 100644 --- a/ql/src/test/results/clientpositive/llap/vector_groupby_mapjoin.q.out +++ b/ql/src/test/results/clientpositive/llap/vector_groupby_mapjoin.q.out @@ -37,9 +37,16 @@ STAGE PLANS: TableScan alias: src Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + TableScan Vectorization: + native: true + projectedOutputColumns: [0, 1] Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumns: [0, 1] Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: @@ -47,6 +54,10 @@ STAGE PLANS: keys: 0 1 + Map Join Vectorization: + className: VectorMapJoinInnerMultiKeyOperator + native: true + nativeConditionsMet: hive.mapjoin.optimized.hashtable IS true, hive.vectorized.execution.mapjoin.native.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, One MapJoin Condition IS true, No nullsafe IS true, Small table vectorizes IS true, Optimized Table and Supports Key Types IS true outputColumnNames: _col0, _col1, _col2, _col3 input vertices: 1 Reducer 4 @@ -57,66 +68,108 @@ STAGE PLANS: keys: 0 _col0 (type: string) 1 _col0 (type: string) + Map Join Vectorization: + className: VectorMapJoinOuterStringOperator + native: true + nativeConditionsMet: hive.mapjoin.optimized.hashtable IS true, hive.vectorized.execution.mapjoin.native.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, One MapJoin Condition IS true, No nullsafe IS true, Small table vectorizes IS true, Optimized Table and Supports Key Types IS true outputColumnNames: _col0, _col1, _col2, _col3, _col5 input vertices: 1 Reducer 6 Statistics: Num rows: 500 Data size: 99000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator + Filter Vectorization: + className: VectorFilterOperator + native: true + predicateExpression: FilterExprOrExpr(children: FilterLongColEqualLongScalar(col 2, val 0) -> boolean, FilterExprAndExpr(children: SelectColumnIsNull(col 4) -> boolean, SelectColumnIsNotNull(col 0) -> boolean, FilterLongColGreaterEqualLongColumn(col 3, col 2) -> boolean) -> boolean) -> boolean predicate: ((_col2 = 0) or (_col5 is null and _col0 is not null and (_col3 >= _col2))) (type: boolean) Statistics: Num rows: 500 Data size: 99000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumns: [0, 1] Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + + Reduce Sink Vectorization: + className: VectorReduceSinkObjectHashOperator + native: true + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) - Execution mode: llap + Execution mode: vectorized, llap LLAP IO: no inputs Map Vectorization: - enabled: false - enabledConditionsNotMet: hive.vectorized.use.vector.serde.deserialize IS false + enabled: true + enabledConditionsMet: hive.vectorized.use.vector.serde.deserialize IS true + groupByVectorOutput: true inputFileFormats: org.apache.hadoop.mapred.TextInputFormat + allNative: true + usesVectorUDFAdaptor: false + vectorized: true Map 3 Map Operator Tree: TableScan alias: src Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + TableScan Vectorization: + native: true + projectedOutputColumns: [0, 1] Select Operator expressions: key (type: string) outputColumnNames: key + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumns: [0] Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(), count(key) Group By Vectorization: - vectorOutput: false + aggregators: VectorUDAFCountStar(*) -> bigint, VectorUDAFCount(col 0) -> bigint + className: VectorGroupByOperator + vectorOutput: true native: false - projectedOutputColumns: null + projectedOutputColumns: [0, 1] mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: + Reduce Sink Vectorization: + className: VectorReduceSinkObjectHashOperator + native: true + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint), _col1 (type: bigint) - Execution mode: llap + Execution mode: vectorized, llap LLAP IO: no inputs Map Vectorization: - enabled: false - enabledConditionsNotMet: hive.vectorized.use.vector.serde.deserialize IS false + enabled: true + enabledConditionsMet: hive.vectorized.use.vector.serde.deserialize IS true + groupByVectorOutput: true inputFileFormats: org.apache.hadoop.mapred.TextInputFormat + allNative: false + usesVectorUDFAdaptor: false + vectorized: true Map 5 Map Operator Tree: TableScan alias: src Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + TableScan Vectorization: + native: true + projectedOutputColumns: [0, 1] Group By Operator Group By Vectorization: - vectorOutput: false + className: VectorGroupByOperator + vectorOutput: true + keyExpressions: col 0 native: false - projectedOutputColumns: null + projectedOutputColumns: [] keys: key (type: string) mode: hash outputColumnNames: _col0 @@ -125,13 +178,21 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) + Reduce Sink Vectorization: + className: VectorReduceSinkStringOperator + native: true + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true Statistics: Num rows: 205 Data size: 17835 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: llap + Execution mode: vectorized, llap LLAP IO: no inputs Map Vectorization: - enabled: false - enabledConditionsNotMet: hive.vectorized.use.vector.serde.deserialize IS false + enabled: true + enabledConditionsMet: hive.vectorized.use.vector.serde.deserialize IS true + groupByVectorOutput: true inputFileFormats: org.apache.hadoop.mapred.TextInputFormat + allNative: false + usesVectorUDFAdaptor: false + vectorized: true Reducer 2 Execution mode: vectorized, llap Reduce Vectorization: @@ -253,3 +314,49 @@ order by key POSTHOOK: type: QUERY POSTHOOK: Input: default@src #### A masked pattern was here #### +PREHOOK: query: CREATE TABLE orcsrc STORED AS ORC AS SELECT * FROM src +PREHOOK: type: CREATETABLE_AS_SELECT +PREHOOK: Input: default@src +PREHOOK: Output: database:default +PREHOOK: Output: default@orcsrc +POSTHOOK: query: CREATE TABLE orcsrc STORED AS ORC AS SELECT * FROM src +POSTHOOK: type: CREATETABLE_AS_SELECT +POSTHOOK: Input: default@src +POSTHOOK: Output: database:default +POSTHOOK: Output: default@orcsrc +POSTHOOK: Lineage: orcsrc.key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: orcsrc.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] +Warning: Map Join MAPJOIN[27][bigTable=?] in task 'Map 1' is a cross product +PREHOOK: query: select * +from orcsrc +where not key in +(select key from orcsrc) +order by key +PREHOOK: type: QUERY +PREHOOK: Input: default@orcsrc +#### A masked pattern was here #### +POSTHOOK: query: select * +from orcsrc +where not key in +(select key from orcsrc) +order by key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@orcsrc +#### A masked pattern was here #### +Warning: Map Join MAPJOIN[27][bigTable=?] in task 'Map 1' is a cross product +PREHOOK: query: select * +from orcsrc +where not key in +(select key from orcsrc) +order by key +PREHOOK: type: QUERY +PREHOOK: Input: default@orcsrc +#### A masked pattern was here #### +POSTHOOK: query: select * +from orcsrc +where not key in +(select key from orcsrc) +order by key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@orcsrc +#### A masked pattern was here #### http://git-wip-us.apache.org/repos/asf/hive/blob/ce695b5d/ql/src/test/results/clientpositive/llap/vector_mapjoin_reduce.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/vector_mapjoin_reduce.q.out b/ql/src/test/results/clientpositive/llap/vector_mapjoin_reduce.q.out index 48deecf..ef67ec2 100644 --- a/ql/src/test/results/clientpositive/llap/vector_mapjoin_reduce.q.out +++ b/ql/src/test/results/clientpositive/llap/vector_mapjoin_reduce.q.out @@ -31,14 +31,23 @@ STAGE PLANS: TableScan alias: lineitem Statistics: Num rows: 100 Data size: 400 Basic stats: COMPLETE Column stats: COMPLETE + TableScan Vectorization: + native: true + projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15] Filter Operator + Filter Vectorization: + className: VectorFilterOperator + native: true + predicateExpression: SelectColumnIsNotNull(col 1) -> boolean predicate: l_partkey is not null (type: boolean) Statistics: Num rows: 100 Data size: 400 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator Group By Vectorization: - vectorOutput: false + className: VectorGroupByOperator + vectorOutput: true + keyExpressions: col 1 native: false - projectedOutputColumns: null + projectedOutputColumns: [] keys: l_partkey (type: int) mode: hash outputColumnNames: _col0 @@ -47,54 +56,94 @@ STAGE PLANS: key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) + Reduce Sink Vectorization: + className: VectorReduceSinkLongOperator + native: true + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true Statistics: Num rows: 50 Data size: 200 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: llap + Execution mode: vectorized, llap LLAP IO: no inputs Map Vectorization: - enabled: false - enabledConditionsNotMet: hive.vectorized.use.vector.serde.deserialize IS false + enabled: true + enabledConditionsMet: hive.vectorized.use.vector.serde.deserialize IS true + groupByVectorOutput: true inputFileFormats: org.apache.hadoop.mapred.TextInputFormat + allNative: false + usesVectorUDFAdaptor: false + vectorized: true Map 3 Map Operator Tree: TableScan alias: li Statistics: Num rows: 100 Data size: 1600 Basic stats: COMPLETE Column stats: COMPLETE + TableScan Vectorization: + native: true + projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15] Filter Operator + Filter Vectorization: + className: VectorFilterOperator + native: true + predicateExpression: FilterExprAndExpr(children: FilterLongColEqualLongScalar(col 3, val 1) -> boolean, SelectColumnIsNotNull(col 1) -> boolean, SelectColumnIsNotNull(col 0) -> boolean) -> boolean predicate: ((l_linenumber = 1) and l_partkey is not null and l_orderkey is not null) (type: boolean) Statistics: Num rows: 17 Data size: 272 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: l_orderkey (type: int), l_partkey (type: int), l_suppkey (type: int) outputColumnNames: _col0, _col1, _col2 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumns: [0, 1, 2] Statistics: Num rows: 17 Data size: 272 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) + Reduce Sink Vectorization: + className: VectorReduceSinkLongOperator + native: true + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true Statistics: Num rows: 17 Data size: 272 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col2 (type: int) - Execution mode: llap + Execution mode: vectorized, llap LLAP IO: no inputs Map Vectorization: - enabled: false - enabledConditionsNotMet: hive.vectorized.use.vector.serde.deserialize IS false + enabled: true + enabledConditionsMet: hive.vectorized.use.vector.serde.deserialize IS true + groupByVectorOutput: true inputFileFormats: org.apache.hadoop.mapred.TextInputFormat + allNative: true + usesVectorUDFAdaptor: false + vectorized: true Map 4 Map Operator Tree: TableScan alias: lineitem Statistics: Num rows: 100 Data size: 9200 Basic stats: COMPLETE Column stats: COMPLETE + TableScan Vectorization: + native: true + projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15] Filter Operator + Filter Vectorization: + className: VectorFilterOperator + native: true + predicateExpression: FilterExprAndExpr(children: FilterStringGroupColEqualStringScalar(col 14, val AIR) -> boolean, SelectColumnIsNotNull(col 0) -> boolean) -> boolean predicate: ((l_shipmode = 'AIR') and l_orderkey is not null) (type: boolean) Statistics: Num rows: 14 Data size: 1288 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: l_orderkey (type: int) outputColumnNames: _col0 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumns: [0] Statistics: Num rows: 14 Data size: 56 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator Group By Vectorization: - vectorOutput: false + className: VectorGroupByOperator + vectorOutput: true + keyExpressions: col 0 native: false - projectedOutputColumns: null + projectedOutputColumns: [] keys: _col0 (type: int) mode: hash outputColumnNames: _col0 @@ -103,13 +152,21 @@ STAGE PLANS: key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) + Reduce Sink Vectorization: + className: VectorReduceSinkLongOperator + native: true + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: llap + Execution mode: vectorized, llap LLAP IO: no inputs Map Vectorization: - enabled: false - enabledConditionsNotMet: hive.vectorized.use.vector.serde.deserialize IS false + enabled: true + enabledConditionsMet: hive.vectorized.use.vector.serde.deserialize IS true + groupByVectorOutput: true inputFileFormats: org.apache.hadoop.mapred.TextInputFormat + allNative: false + usesVectorUDFAdaptor: false + vectorized: true Reducer 2 Execution mode: vectorized, llap Reduce Vectorization: @@ -241,14 +298,23 @@ STAGE PLANS: TableScan alias: lineitem Statistics: Num rows: 100 Data size: 400 Basic stats: COMPLETE Column stats: COMPLETE + TableScan Vectorization: + native: true + projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15] Filter Operator + Filter Vectorization: + className: VectorFilterOperator + native: true + predicateExpression: SelectColumnIsNotNull(col 1) -> boolean predicate: l_partkey is not null (type: boolean) Statistics: Num rows: 100 Data size: 400 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator Group By Vectorization: - vectorOutput: false + className: VectorGroupByOperator + vectorOutput: true + keyExpressions: col 1 native: false - projectedOutputColumns: null + projectedOutputColumns: [] keys: l_partkey (type: int) mode: hash outputColumnNames: _col0 @@ -257,54 +323,95 @@ STAGE PLANS: key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) + Reduce Sink Vectorization: + className: VectorReduceSinkLongOperator + native: true + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true Statistics: Num rows: 50 Data size: 200 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: llap + Execution mode: vectorized, llap LLAP IO: no inputs Map Vectorization: - enabled: false - enabledConditionsNotMet: hive.vectorized.use.vector.serde.deserialize IS false + enabled: true + enabledConditionsMet: hive.vectorized.use.vector.serde.deserialize IS true + groupByVectorOutput: true inputFileFormats: org.apache.hadoop.mapred.TextInputFormat + allNative: false + usesVectorUDFAdaptor: false + vectorized: true Map 3 Map Operator Tree: TableScan alias: li Statistics: Num rows: 100 Data size: 1600 Basic stats: COMPLETE Column stats: COMPLETE + TableScan Vectorization: + native: true + projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15] Filter Operator + Filter Vectorization: + className: VectorFilterOperator + native: true + predicateExpression: FilterExprAndExpr(children: FilterLongColEqualLongScalar(col 3, val 1) -> boolean, SelectColumnIsNotNull(col 1) -> boolean) -> boolean predicate: ((l_linenumber = 1) and l_partkey is not null) (type: boolean) Statistics: Num rows: 17 Data size: 272 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: l_orderkey (type: int), l_partkey (type: int), l_suppkey (type: int), 1 (type: int) outputColumnNames: _col0, _col1, _col2, _col3 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumns: [0, 1, 2, 16] + selectExpressions: ConstantVectorExpression(val 1) -> 16:long Statistics: Num rows: 17 Data size: 272 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) + Reduce Sink Vectorization: + className: VectorReduceSinkLongOperator + native: true + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true Statistics: Num rows: 17 Data size: 272 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col2 (type: int), _col3 (type: int) - Execution mode: llap + Execution mode: vectorized, llap LLAP IO: no inputs Map Vectorization: - enabled: false - enabledConditionsNotMet: hive.vectorized.use.vector.serde.deserialize IS false + enabled: true + enabledConditionsMet: hive.vectorized.use.vector.serde.deserialize IS true + groupByVectorOutput: true inputFileFormats: org.apache.hadoop.mapred.TextInputFormat + allNative: true + usesVectorUDFAdaptor: false + vectorized: true Map 4 Map Operator Tree: TableScan alias: lineitem Statistics: Num rows: 100 Data size: 9600 Basic stats: COMPLETE Column stats: COMPLETE + TableScan Vectorization: + native: true + projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15] Filter Operator + Filter Vectorization: + className: VectorFilterOperator + native: true + predicateExpression: FilterExprAndExpr(children: FilterStringGroupColEqualStringScalar(col 14, val AIR) -> boolean, FilterLongColEqualLongColumn(col 3, col 3) -> boolean) -> boolean predicate: ((l_shipmode = 'AIR') and (l_linenumber = l_linenumber)) (type: boolean) Statistics: Num rows: 7 Data size: 672 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: l_orderkey (type: int), l_linenumber (type: int) outputColumnNames: _col0, _col1 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumns: [0, 3] Statistics: Num rows: 7 Data size: 56 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator Group By Vectorization: - vectorOutput: false + className: VectorGroupByOperator + vectorOutput: true + keyExpressions: col 0, col 3 native: false - projectedOutputColumns: null + projectedOutputColumns: [] keys: _col0 (type: int), _col1 (type: int) mode: hash outputColumnNames: _col0, _col1 @@ -313,13 +420,21 @@ STAGE PLANS: key expressions: _col0 (type: int), _col1 (type: int) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: int) + Reduce Sink Vectorization: + className: VectorReduceSinkMultiKeyOperator + native: true + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: llap + Execution mode: vectorized, llap LLAP IO: no inputs Map Vectorization: - enabled: false - enabledConditionsNotMet: hive.vectorized.use.vector.serde.deserialize IS false + enabled: true + enabledConditionsMet: hive.vectorized.use.vector.serde.deserialize IS true + groupByVectorOutput: true inputFileFormats: org.apache.hadoop.mapred.TextInputFormat + allNative: false + usesVectorUDFAdaptor: false + vectorized: true Reducer 2 Execution mode: vectorized, llap Reduce Vectorization: http://git-wip-us.apache.org/repos/asf/hive/blob/ce695b5d/ql/src/test/results/clientpositive/llap/vector_udf_character_length.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/vector_udf_character_length.q.out b/ql/src/test/results/clientpositive/llap/vector_udf_character_length.q.out index b26db2d..559a82b 100644 --- a/ql/src/test/results/clientpositive/llap/vector_udf_character_length.q.out +++ b/ql/src/test/results/clientpositive/llap/vector_udf_character_length.q.out @@ -70,7 +70,7 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.dest1 - Execution mode: llap + Execution mode: vectorized, llap LLAP IO: no inputs Stage: Stage-2 http://git-wip-us.apache.org/repos/asf/hive/blob/ce695b5d/ql/src/test/results/clientpositive/llap/vector_udf_octet_length.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/vector_udf_octet_length.q.out b/ql/src/test/results/clientpositive/llap/vector_udf_octet_length.q.out index 10ace12..cee8322 100644 --- a/ql/src/test/results/clientpositive/llap/vector_udf_octet_length.q.out +++ b/ql/src/test/results/clientpositive/llap/vector_udf_octet_length.q.out @@ -53,7 +53,7 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.dest1 - Execution mode: llap + Execution mode: vectorized, llap LLAP IO: no inputs Stage: Stage-2 http://git-wip-us.apache.org/repos/asf/hive/blob/ce695b5d/ql/src/test/results/clientpositive/llap/vectorized_bucketmapjoin1.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/vectorized_bucketmapjoin1.q.out b/ql/src/test/results/clientpositive/llap/vectorized_bucketmapjoin1.q.out index 9d2d8a6..3f0afcb 100644 --- a/ql/src/test/results/clientpositive/llap/vectorized_bucketmapjoin1.q.out +++ b/ql/src/test/results/clientpositive/llap/vectorized_bucketmapjoin1.q.out @@ -411,21 +411,36 @@ STAGE PLANS: TableScan alias: b Statistics: Num rows: 2 Data size: 52 Basic stats: COMPLETE Column stats: NONE + TableScan Vectorization: + native: true + projectedOutputColumns: [0, 1] Filter Operator + Filter Vectorization: + className: VectorFilterOperator + native: true + predicateExpression: SelectColumnIsNotNull(col 0) -> boolean predicate: key is not null (type: boolean) Statistics: Num rows: 2 Data size: 52 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key (type: int) sort order: + Map-reduce partition columns: key (type: int) + Reduce Sink Vectorization: + className: VectorReduceSinkLongOperator + native: true + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true Statistics: Num rows: 2 Data size: 52 Basic stats: COMPLETE Column stats: NONE value expressions: value (type: string) - Execution mode: llap + Execution mode: vectorized, llap LLAP IO: no inputs Map Vectorization: - enabled: false - enabledConditionsNotMet: hive.vectorized.use.vector.serde.deserialize IS false + enabled: true + enabledConditionsMet: hive.vectorized.use.vector.serde.deserialize IS true + groupByVectorOutput: true inputFileFormats: org.apache.hadoop.mapred.TextInputFormat + allNative: true + usesVectorUDFAdaptor: false + vectorized: true Reducer 2 Execution mode: llap Reduce Operator Tree:
