Repository: hive Updated Branches: refs/heads/master f80f65da9 -> a5502b26f
HIVE-13744: LLAP IO - add complex types support (Prasanth Jayachandran 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/a5502b26 Tree: http://git-wip-us.apache.org/repos/asf/hive/tree/a5502b26 Diff: http://git-wip-us.apache.org/repos/asf/hive/diff/a5502b26 Branch: refs/heads/master Commit: a5502b26f234ed76966b2e13c7713fdbb7d8be95 Parents: f80f65d Author: Prasanth Jayachandran <[email protected]> Authored: Wed Jun 22 11:16:28 2016 -0700 Committer: Prasanth Jayachandran <[email protected]> Committed: Wed Jun 22 11:16:32 2016 -0700 ---------------------------------------------------------------------- .../test/resources/testconfiguration.properties | 2 + .../llap/io/decode/OrcEncodedDataConsumer.java | 37 ++- .../llap/vector_complex_all.q.out | 258 +++++++++++++++++++ .../llap/vector_complex_join.q.out | 233 +++++++++++++++++ 4 files changed, 525 insertions(+), 5 deletions(-) ---------------------------------------------------------------------- http://git-wip-us.apache.org/repos/asf/hive/blob/a5502b26/itests/src/test/resources/testconfiguration.properties ---------------------------------------------------------------------- diff --git a/itests/src/test/resources/testconfiguration.properties b/itests/src/test/resources/testconfiguration.properties index 46350a3..2b40cd9 100644 --- a/itests/src/test/resources/testconfiguration.properties +++ b/itests/src/test/resources/testconfiguration.properties @@ -515,6 +515,8 @@ minillap.shared.query.files=bucket_map_join_tez1.q,\ tez_union_group_by.q,\ tez_smb_main.q,\ tez_smb_1.q,\ + vector_complex_all.q,\ + vector_complex_join.q,\ vector_join_part_col_char.q,\ vectorized_dynamic_partition_pruning.q,\ tez_multi_union.q,\ http://git-wip-us.apache.org/repos/asf/hive/blob/a5502b26/llap-server/src/java/org/apache/hadoop/hive/llap/io/decode/OrcEncodedDataConsumer.java ---------------------------------------------------------------------- diff --git a/llap-server/src/java/org/apache/hadoop/hive/llap/io/decode/OrcEncodedDataConsumer.java b/llap-server/src/java/org/apache/hadoop/hive/llap/io/decode/OrcEncodedDataConsumer.java index 619d1a4..3dfab63 100644 --- a/llap-server/src/java/org/apache/hadoop/hive/llap/io/decode/OrcEncodedDataConsumer.java +++ b/llap-server/src/java/org/apache/hadoop/hive/llap/io/decode/OrcEncodedDataConsumer.java @@ -32,8 +32,12 @@ import org.apache.hadoop.hive.ql.exec.vector.BytesColumnVector; import org.apache.hadoop.hive.ql.exec.vector.ColumnVector; import org.apache.hadoop.hive.ql.exec.vector.DecimalColumnVector; import org.apache.hadoop.hive.ql.exec.vector.DoubleColumnVector; +import org.apache.hadoop.hive.ql.exec.vector.ListColumnVector; import org.apache.hadoop.hive.ql.exec.vector.LongColumnVector; +import org.apache.hadoop.hive.ql.exec.vector.MapColumnVector; +import org.apache.hadoop.hive.ql.exec.vector.StructColumnVector; import org.apache.hadoop.hive.ql.exec.vector.TimestampColumnVector; +import org.apache.hadoop.hive.ql.exec.vector.UnionColumnVector; import org.apache.hadoop.hive.ql.exec.vector.VectorizedRowBatch; import org.apache.orc.CompressionCodec; import org.apache.hadoop.hive.ql.io.orc.encoded.Consumer; @@ -77,8 +81,9 @@ public class OrcEncodedDataConsumer stripes[m.getStripeIx()] = m; } - private static ColumnVector createColumn(OrcProto.Type type, - int batchSize) { + private static ColumnVector createColumn(List<OrcProto.Type> types, + final int columnId, int batchSize) { + OrcProto.Type type = types.get(columnId); switch (type.getKind()) { case BOOLEAN: case BYTE: @@ -100,6 +105,28 @@ public class OrcEncodedDataConsumer case DECIMAL: return new DecimalColumnVector(batchSize, type.getPrecision(), type.getScale()); + case STRUCT: { + List<Integer> subtypeIdxs = type.getSubtypesList(); + ColumnVector[] fieldVector = new ColumnVector[subtypeIdxs.size()]; + for(int i=0; i < fieldVector.length; ++i) { + fieldVector[i] = createColumn(types, subtypeIdxs.get(i), batchSize); + } + return new StructColumnVector(batchSize, fieldVector); + } + case UNION: { + List<Integer> subtypeIdxs = type.getSubtypesList(); + ColumnVector[] fieldVector = new ColumnVector[subtypeIdxs.size()]; + for(int i=0; i < fieldVector.length; ++i) { + fieldVector[i] = createColumn(types, subtypeIdxs.get(i), batchSize); + } + return new UnionColumnVector(batchSize, fieldVector); + } + case LIST: + return new ListColumnVector(batchSize, createColumn(types, type.getSubtypes(0), batchSize)); + case MAP: + return new MapColumnVector(batchSize, + createColumn(types, type.getSubtypes(0), batchSize), + createColumn(types, type.getSubtypes(1), batchSize)); default: throw new IllegalArgumentException("LLAP does not support " + type.getKind()); @@ -151,9 +178,9 @@ public class OrcEncodedDataConsumer int[] columnMapping = batch.getColumnIxs(); for (int idx = 0; idx < batch.getColumnIxs().length; idx++) { if (cvb.cols[idx] == null) { - // skip over the top level struct, but otherwise assume no complex - // types - cvb.cols[idx] = createColumn(types.get(columnMapping[idx]), batchSize); + // Orc store rows inside a root struct (hive writes it this way). + // When we populate column vectors we skip over the root struct. + cvb.cols[idx] = createColumn(types, columnMapping[idx], batchSize); } cvb.cols[idx].ensureSize(batchSize, false); columnReaders[idx].nextVector(cvb.cols[idx], null, batchSize); http://git-wip-us.apache.org/repos/asf/hive/blob/a5502b26/ql/src/test/results/clientpositive/llap/vector_complex_all.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/vector_complex_all.q.out b/ql/src/test/results/clientpositive/llap/vector_complex_all.q.out new file mode 100644 index 0000000..08d49bc --- /dev/null +++ b/ql/src/test/results/clientpositive/llap/vector_complex_all.q.out @@ -0,0 +1,258 @@ +PREHOOK: query: CREATE TABLE orc_create_staging ( + str STRING, + mp MAP<STRING,STRING>, + lst ARRAY<STRING>, + strct STRUCT<A:STRING,B:STRING> +) ROW FORMAT DELIMITED + FIELDS TERMINATED BY '|' + COLLECTION ITEMS TERMINATED BY ',' + MAP KEYS TERMINATED BY ':' +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@orc_create_staging +POSTHOOK: query: CREATE TABLE orc_create_staging ( + str STRING, + mp MAP<STRING,STRING>, + lst ARRAY<STRING>, + strct STRUCT<A:STRING,B:STRING> +) ROW FORMAT DELIMITED + FIELDS TERMINATED BY '|' + COLLECTION ITEMS TERMINATED BY ',' + MAP KEYS TERMINATED BY ':' +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@orc_create_staging +PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/orc_create.txt' OVERWRITE INTO TABLE orc_create_staging +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@orc_create_staging +POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/orc_create.txt' OVERWRITE INTO TABLE orc_create_staging +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@orc_create_staging +PREHOOK: query: CREATE TABLE orc_create_complex ( + str STRING, + mp MAP<STRING,STRING>, + lst ARRAY<STRING>, + strct STRUCT<A:STRING,B:STRING> +) STORED AS ORC +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@orc_create_complex +POSTHOOK: query: CREATE TABLE orc_create_complex ( + str STRING, + mp MAP<STRING,STRING>, + lst ARRAY<STRING>, + strct STRUCT<A:STRING,B:STRING> +) STORED AS ORC +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@orc_create_complex +PREHOOK: query: INSERT OVERWRITE TABLE orc_create_complex SELECT * FROM orc_create_staging +PREHOOK: type: QUERY +PREHOOK: Input: default@orc_create_staging +PREHOOK: Output: default@orc_create_complex +POSTHOOK: query: INSERT OVERWRITE TABLE orc_create_complex SELECT * FROM orc_create_staging +POSTHOOK: type: QUERY +POSTHOOK: Input: default@orc_create_staging +POSTHOOK: Output: default@orc_create_complex +POSTHOOK: Lineage: orc_create_complex.lst SIMPLE [(orc_create_staging)orc_create_staging.FieldSchema(name:lst, type:array<string>, comment:null), ] +POSTHOOK: Lineage: orc_create_complex.mp SIMPLE [(orc_create_staging)orc_create_staging.FieldSchema(name:mp, type:map<string,string>, comment:null), ] +POSTHOOK: Lineage: orc_create_complex.str SIMPLE [(orc_create_staging)orc_create_staging.FieldSchema(name:str, type:string, comment:null), ] +POSTHOOK: Lineage: orc_create_complex.strct SIMPLE [(orc_create_staging)orc_create_staging.FieldSchema(name:strct, type:struct<A:string,B:string>, comment:null), ] +orc_create_staging.str orc_create_staging.mp orc_create_staging.lst orc_create_staging.strct +PREHOOK: query: -- Since complex types are not supported, this query should not vectorize. +EXPLAIN +SELECT * FROM orc_create_complex +PREHOOK: type: QUERY +POSTHOOK: query: -- Since complex types are not supported, this query should not vectorize. +EXPLAIN +SELECT * FROM orc_create_complex +POSTHOOK: type: QUERY +Explain +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: orc_create_complex + Statistics: Num rows: 3 Data size: 3177 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: str (type: string), mp (type: map<string,string>), lst (type: array<string>), strct (type: struct<a:string,b:string>) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 3 Data size: 3177 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 3 Data size: 3177 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Execution mode: llap + LLAP IO: no inputs + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT * FROM orc_create_complex +PREHOOK: type: QUERY +PREHOOK: Input: default@orc_create_complex +#### A masked pattern was here #### +POSTHOOK: query: SELECT * FROM orc_create_complex +POSTHOOK: type: QUERY +POSTHOOK: Input: default@orc_create_complex +#### A masked pattern was here #### +orc_create_complex.str orc_create_complex.mp orc_create_complex.lst orc_create_complex.strct +line1 {"key13":"value13","key11":"value11","key12":"value12"} ["a","b","c"] {"a":"one","b":"two"} +line2 {"key21":"value21","key22":"value22","key23":"value23"} ["d","e","f"] {"a":"three","b":"four"} +line3 {"key31":"value31","key32":"value32","key33":"value33"} ["g","h","i"] {"a":"five","b":"six"} +PREHOOK: query: -- However, since this query is not referencing the complex fields, it should vectorize. +EXPLAIN +SELECT COUNT(*) FROM orc_create_complex +PREHOOK: type: QUERY +POSTHOOK: query: -- However, since this query is not referencing the complex fields, it should vectorize. +EXPLAIN +SELECT COUNT(*) FROM orc_create_complex +POSTHOOK: type: QUERY +Explain +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: orc_create_complex + Statistics: Num rows: 3 Data size: 3177 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + Statistics: Num rows: 3 Data size: 3177 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: COMPLETE + Reduce Output Operator + sort order: + 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 + Reducer 2 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + mode: mergepartial + outputColumnNames: _col0 + 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: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT COUNT(*) FROM orc_create_complex +PREHOOK: type: QUERY +PREHOOK: Input: default@orc_create_complex +#### A masked pattern was here #### +POSTHOOK: query: SELECT COUNT(*) FROM orc_create_complex +POSTHOOK: type: QUERY +POSTHOOK: Input: default@orc_create_complex +#### A masked pattern was here #### +c0 +3 +PREHOOK: query: -- Also, since this query is not referencing the complex fields, it should vectorize. +EXPLAIN +SELECT str FROM orc_create_complex ORDER BY str +PREHOOK: type: QUERY +POSTHOOK: query: -- Also, since this query is not referencing the complex fields, it should vectorize. +EXPLAIN +SELECT str FROM orc_create_complex ORDER BY str +POSTHOOK: type: QUERY +Explain +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: orc_create_complex + Statistics: Num rows: 3 Data size: 3177 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: str (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 3 Data size: 3177 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Statistics: Num rows: 3 Data size: 3177 Basic stats: COMPLETE Column stats: NONE + Execution mode: vectorized, llap + LLAP IO: all inputs + Reducer 2 + Execution mode: vectorized, llap + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 3 Data size: 3177 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 3 Data size: 3177 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT str FROM orc_create_complex ORDER BY str +PREHOOK: type: QUERY +PREHOOK: Input: default@orc_create_complex +#### A masked pattern was here #### +POSTHOOK: query: SELECT str FROM orc_create_complex ORDER BY str +POSTHOOK: type: QUERY +POSTHOOK: Input: default@orc_create_complex +#### A masked pattern was here #### +str +line1 +line2 +line3 http://git-wip-us.apache.org/repos/asf/hive/blob/a5502b26/ql/src/test/results/clientpositive/llap/vector_complex_join.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/vector_complex_join.q.out b/ql/src/test/results/clientpositive/llap/vector_complex_join.q.out new file mode 100644 index 0000000..480627f --- /dev/null +++ b/ql/src/test/results/clientpositive/llap/vector_complex_join.q.out @@ -0,0 +1,233 @@ +PREHOOK: query: -- From HIVE-10729. Not expected to vectorize this query. +-- +CREATE TABLE test (a INT, b MAP<INT, STRING>) STORED AS ORC +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@test +POSTHOOK: query: -- From HIVE-10729. Not expected to vectorize this query. +-- +CREATE TABLE test (a INT, b MAP<INT, STRING>) STORED AS ORC +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@test +PREHOOK: query: INSERT OVERWRITE TABLE test SELECT 199408978, MAP(1, "val_1", 2, "val_2") FROM src LIMIT 1 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: default@test +POSTHOOK: query: INSERT OVERWRITE TABLE test SELECT 199408978, MAP(1, "val_1", 2, "val_2") FROM src LIMIT 1 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Output: default@test +POSTHOOK: Lineage: test.a SIMPLE [] +POSTHOOK: Lineage: test.b EXPRESSION [] +c0 c1 +PREHOOK: query: explain +select * from alltypesorc join test where alltypesorc.cint=test.a +PREHOOK: type: QUERY +POSTHOOK: query: explain +select * from alltypesorc join test where alltypesorc.cint=test.a +POSTHOOK: type: QUERY +Explain +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Map 1 <- Map 2 (BROADCAST_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: alltypesorc + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: cint is not null (type: boolean) + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cbigint (type: bigint), cfloat (type: float), cdouble (type: double), cstring1 (type: string), cstring2 (type: string), ctimestamp1 (type: timestamp), ctimestamp2 (type: timestamp), cboolean1 (type: boolean), cboolean2 (type: boolean) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col2 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 + input vertices: + 1 Map 2 + Statistics: Num rows: 13516 Data size: 2906160 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 13516 Data size: 2906160 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Execution mode: llap + LLAP IO: no inputs + Map 2 + Map Operator Tree: + TableScan + alias: test + Statistics: Num rows: 1 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: a is not null (type: boolean) + Statistics: Num rows: 1 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: a (type: int), b (type: map<int,string>) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 1 Data size: 190 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: map<int,string>) + Execution mode: llap + LLAP IO: no inputs + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select * from alltypesorc join test where alltypesorc.cint=test.a +PREHOOK: type: QUERY +PREHOOK: Input: default@alltypesorc +PREHOOK: Input: default@test +#### A masked pattern was here #### +POSTHOOK: query: select * from alltypesorc join test where alltypesorc.cint=test.a +POSTHOOK: type: QUERY +POSTHOOK: Input: default@alltypesorc +POSTHOOK: Input: default@test +#### A masked pattern was here #### +alltypesorc.ctinyint alltypesorc.csmallint alltypesorc.cint alltypesorc.cbigint alltypesorc.cfloat alltypesorc.cdouble alltypesorc.cstring1 alltypesorc.cstring2 alltypesorc.ctimestamp1 alltypesorc.ctimestamp2 alltypesorc.cboolean1 alltypesorc.cboolean2 test.a test.b +-51 NULL 199408978 -1800989684 -51.0 NULL 34N4EY63M1GFWuW0boW P4PL5h1eXR4mMLr2 1969-12-31 16:00:08.451 NULL false true 199408978 {1:"val_1",2:"val_2"} +PREHOOK: query: CREATE TABLE test2a (a ARRAY<INT>) STORED AS ORC +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@test2a +POSTHOOK: query: CREATE TABLE test2a (a ARRAY<INT>) STORED AS ORC +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@test2a +PREHOOK: query: INSERT OVERWRITE TABLE test2a SELECT ARRAY(1, 2) FROM src LIMIT 1 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: default@test2a +POSTHOOK: query: INSERT OVERWRITE TABLE test2a SELECT ARRAY(1, 2) FROM src LIMIT 1 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Output: default@test2a +POSTHOOK: Lineage: test2a.a EXPRESSION [] +c0 +PREHOOK: query: CREATE TABLE test2b (a INT) STORED AS ORC +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@test2b +POSTHOOK: query: CREATE TABLE test2b (a INT) STORED AS ORC +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@test2b +PREHOOK: query: INSERT OVERWRITE TABLE test2b VALUES (2), (3), (4) +PREHOOK: type: QUERY +PREHOOK: Input: default@values__tmp__table__1 +PREHOOK: Output: default@test2b +POSTHOOK: query: INSERT OVERWRITE TABLE test2b VALUES (2), (3), (4) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@values__tmp__table__1 +POSTHOOK: Output: default@test2b +POSTHOOK: Lineage: test2b.a EXPRESSION [(values__tmp__table__1)values__tmp__table__1.FieldSchema(name:tmp_values_col1, type:string, comment:), ] +_col0 +PREHOOK: query: explain +select * from test2b join test2a on test2b.a = test2a.a[1] +PREHOOK: type: QUERY +POSTHOOK: query: explain +select * from test2b join test2a on test2b.a = test2a.a[1] +POSTHOOK: type: QUERY +Explain +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Map 1 <- Map 2 (BROADCAST_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: test2b + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: a is not null (type: boolean) + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 a (type: int) + 1 a[1] (type: int) + outputColumnNames: _col0, _col4 + input vertices: + 1 Map 2 + Statistics: Num rows: 3 Data size: 13 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: int), _col4 (type: array<int>) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 3 Data size: 13 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 3 Data size: 13 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Execution mode: llap + LLAP IO: no inputs + Map 2 + Map Operator Tree: + TableScan + alias: test2a + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: a[1] is not null (type: boolean) + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: a[1] (type: int) + sort order: + + Map-reduce partition columns: a[1] (type: int) + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: a (type: array<int>) + Execution mode: llap + LLAP IO: no inputs + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select * from test2b join test2a on test2b.a = test2a.a[1] +PREHOOK: type: QUERY +PREHOOK: Input: default@test2a +PREHOOK: Input: default@test2b +#### A masked pattern was here #### +POSTHOOK: query: select * from test2b join test2a on test2b.a = test2a.a[1] +POSTHOOK: type: QUERY +POSTHOOK: Input: default@test2a +POSTHOOK: Input: default@test2b +#### A masked pattern was here #### +test2b.a test2a.a +2 [1,2]
