HIVE-11614: CBO: Calcite Operator To Hive Operator (Calcite Return Path): ctas after order by has problem (Pengcheng Xiong, reviewd by Laljo John Pullokkaran)
Project: http://git-wip-us.apache.org/repos/asf/hive/repo Commit: http://git-wip-us.apache.org/repos/asf/hive/commit/bbb91292 Tree: http://git-wip-us.apache.org/repos/asf/hive/tree/bbb91292 Diff: http://git-wip-us.apache.org/repos/asf/hive/diff/bbb91292 Branch: refs/heads/llap Commit: bbb912927a1457daf283f3030cd873d55b93c8c3 Parents: ff1f5b1 Author: Pengcheng Xiong <pxi...@apache.org> Authored: Sat Sep 12 20:27:16 2015 -0700 Committer: Pengcheng Xiong <pxi...@apache.org> Committed: Sat Sep 12 20:27:16 2015 -0700 ---------------------------------------------------------------------- .../translator/PlanModifierForReturnPath.java | 4 - .../hadoop/hive/ql/parse/CalcitePlanner.java | 7 +- .../hadoop/hive/ql/parse/SemanticAnalyzer.java | 2 +- .../queries/clientpositive/cbo_rp_auto_join17.q | 14 + .../cbo_rp_cross_product_check_2.q | 31 + .../clientpositive/cbo_rp_auto_join17.q.out | 118 ++++ .../cbo_rp_cross_product_check_2.q.out | 699 +++++++++++++++++++ 7 files changed, 866 insertions(+), 9 deletions(-) ---------------------------------------------------------------------- http://git-wip-us.apache.org/repos/asf/hive/blob/bbb91292/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/translator/PlanModifierForReturnPath.java ---------------------------------------------------------------------- diff --git a/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/translator/PlanModifierForReturnPath.java b/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/translator/PlanModifierForReturnPath.java index 81cc474..95d692c 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/translator/PlanModifierForReturnPath.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/translator/PlanModifierForReturnPath.java @@ -34,10 +34,6 @@ public class PlanModifierForReturnPath { Pair<RelNode, RelNode> topSelparentPair = HiveCalciteUtil.getTopLevelSelect(newTopNode); PlanModifierUtil.fixTopOBSchema(newTopNode, topSelparentPair, resultSchema, false); - if (isCTAS) { - newTopNode = PlanModifierForASTConv.renameTopLevelSelectInResultSchema(newTopNode, - topSelparentPair, resultSchema); - } return newTopNode; } http://git-wip-us.apache.org/repos/asf/hive/blob/bbb91292/ql/src/java/org/apache/hadoop/hive/ql/parse/CalcitePlanner.java ---------------------------------------------------------------------- diff --git a/ql/src/java/org/apache/hadoop/hive/ql/parse/CalcitePlanner.java b/ql/src/java/org/apache/hadoop/hive/ql/parse/CalcitePlanner.java index 86bdf7e..8e992da 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/parse/CalcitePlanner.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/parse/CalcitePlanner.java @@ -193,7 +193,6 @@ import com.google.common.collect.Lists; public class CalcitePlanner extends SemanticAnalyzer { private final AtomicInteger noColsMissingStats = new AtomicInteger(0); - private List<FieldSchema> topLevelFieldSchema; private SemanticException semanticException; private boolean runCBO = true; @@ -620,7 +619,7 @@ public class CalcitePlanner extends SemanticAnalyzer { rethrowCalciteException(e); throw new AssertionError("rethrowCalciteException didn't throw for " + e.getMessage()); } - optiqOptimizedAST = ASTConverter.convert(optimizedOptiqPlan, topLevelFieldSchema); + optiqOptimizedAST = ASTConverter.convert(optimizedOptiqPlan, resultSchema); return optiqOptimizedAST; } @@ -644,7 +643,7 @@ public class CalcitePlanner extends SemanticAnalyzer { } RelNode modifiedOptimizedOptiqPlan = PlanModifierForReturnPath.convertOpTree( - introduceProjectIfNeeded(optimizedOptiqPlan), topLevelFieldSchema, this.getQB() + introduceProjectIfNeeded(optimizedOptiqPlan), resultSchema, this.getQB() .getTableDesc() != null); LOG.debug("Translating the following plan:\n" + RelOptUtil.toString(modifiedOptimizedOptiqPlan)); @@ -851,7 +850,7 @@ public class CalcitePlanner extends SemanticAnalyzer { // 1. Gen Calcite Plan try { calciteGenPlan = genLogicalPlan(getQB(), true); - topLevelFieldSchema = SemanticAnalyzer.convertRowSchemaToResultSetSchema( + resultSchema = SemanticAnalyzer.convertRowSchemaToResultSetSchema( relToHiveRR.get(calciteGenPlan), HiveConf.getBoolVar(conf, HiveConf.ConfVars.HIVE_RESULTSET_USE_UNIQUE_COLUMN_NAMES)); } catch (SemanticException e) { http://git-wip-us.apache.org/repos/asf/hive/blob/bbb91292/ql/src/java/org/apache/hadoop/hive/ql/parse/SemanticAnalyzer.java ---------------------------------------------------------------------- diff --git a/ql/src/java/org/apache/hadoop/hive/ql/parse/SemanticAnalyzer.java b/ql/src/java/org/apache/hadoop/hive/ql/parse/SemanticAnalyzer.java index f6052e3..16957b6 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/parse/SemanticAnalyzer.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/parse/SemanticAnalyzer.java @@ -261,7 +261,7 @@ public class SemanticAnalyzer extends BaseSemanticAnalyzer { private final HashMap<String, SplitSample> nameToSplitSample; Map<GroupByOperator, Set<String>> groupOpToInputTables; Map<String, PrunedPartitionList> prunedPartitions; - private List<FieldSchema> resultSchema; + protected List<FieldSchema> resultSchema; private CreateViewDesc createVwDesc; private ArrayList<String> viewsExpanded; private ASTNode viewSelect; http://git-wip-us.apache.org/repos/asf/hive/blob/bbb91292/ql/src/test/queries/clientpositive/cbo_rp_auto_join17.q ---------------------------------------------------------------------- diff --git a/ql/src/test/queries/clientpositive/cbo_rp_auto_join17.q b/ql/src/test/queries/clientpositive/cbo_rp_auto_join17.q new file mode 100644 index 0000000..7e2f068 --- /dev/null +++ b/ql/src/test/queries/clientpositive/cbo_rp_auto_join17.q @@ -0,0 +1,14 @@ +set hive.cbo.returnpath.hiveop=true; +set hive.auto.convert.join = true; + +CREATE TABLE dest1(key1 INT, value1 STRING, key2 INT, value2 STRING) STORED AS TEXTFILE; + +explain +FROM src src1 JOIN src src2 ON (src1.key = src2.key) +INSERT OVERWRITE TABLE dest1 SELECT src1.*, src2.*; + + +FROM src src1 JOIN src src2 ON (src1.key = src2.key) +INSERT OVERWRITE TABLE dest1 SELECT src1.*, src2.*; + +SELECT sum(hash(dest1.key1,dest1.value1,dest1.key2,dest1.value2)) FROM dest1; \ No newline at end of file http://git-wip-us.apache.org/repos/asf/hive/blob/bbb91292/ql/src/test/queries/clientpositive/cbo_rp_cross_product_check_2.q ---------------------------------------------------------------------- diff --git a/ql/src/test/queries/clientpositive/cbo_rp_cross_product_check_2.q b/ql/src/test/queries/clientpositive/cbo_rp_cross_product_check_2.q new file mode 100644 index 0000000..6c35548 --- /dev/null +++ b/ql/src/test/queries/clientpositive/cbo_rp_cross_product_check_2.q @@ -0,0 +1,31 @@ +set hive.cbo.returnpath.hiveop=true; +set hive.explain.user=false; +-- SORT_QUERY_RESULTS + +create table A as +select * from src; + +create table B as +select * from src order by key +limit 10; + +set hive.auto.convert.join=true; +set hive.auto.convert.join.noconditionaltask=true; +set hive.auto.convert.join.noconditionaltask.size=10000000; + +explain select * from A join B; + +explain select * from B d1 join B d2 on d1.key = d2.key join A; + +explain select * from A join + (select d1.key + from B d1 join B d2 on d1.key = d2.key + where 1 = 1 group by d1.key) od1; + +explain select * from A join (select d1.key from B d1 join B d2 where 1 = 1 group by d1.key) od1; + +explain select * from +(select A.key from A group by key) ss join +(select d1.key from B d1 join B d2 on d1.key = d2.key where 1 = 1 group by d1.key) od1; + + http://git-wip-us.apache.org/repos/asf/hive/blob/bbb91292/ql/src/test/results/clientpositive/cbo_rp_auto_join17.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/cbo_rp_auto_join17.q.out b/ql/src/test/results/clientpositive/cbo_rp_auto_join17.q.out new file mode 100644 index 0000000..351699d --- /dev/null +++ b/ql/src/test/results/clientpositive/cbo_rp_auto_join17.q.out @@ -0,0 +1,118 @@ +PREHOOK: query: CREATE TABLE dest1(key1 INT, value1 STRING, key2 INT, value2 STRING) STORED AS TEXTFILE +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@dest1 +POSTHOOK: query: CREATE TABLE dest1(key1 INT, value1 STRING, key2 INT, value2 STRING) STORED AS TEXTFILE +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@dest1 +PREHOOK: query: explain +FROM src src1 JOIN src src2 ON (src1.key = src2.key) +INSERT OVERWRITE TABLE dest1 SELECT src1.*, src2.* +PREHOOK: type: QUERY +POSTHOOK: query: explain +FROM src src1 JOIN src src2 ON (src1.key = src2.key) +INSERT OVERWRITE TABLE dest1 SELECT src1.*, src2.* +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-5 is a root stage + Stage-4 depends on stages: Stage-5 + Stage-0 depends on stages: Stage-4 + Stage-2 depends on stages: Stage-0 + +STAGE PLANS: + Stage: Stage-5 + Map Reduce Local Work + Alias -> Map Local Tables: + src1 + Fetch Operator + limit: -1 + Alias -> Map Local Operator Tree: + src1 + TableScan + alias: src1 + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + HashTable Sink Operator + keys: + 0 key (type: string) + 1 key (type: string) + + Stage: Stage-4 + Map Reduce + Map Operator Tree: + TableScan + alias: src2 + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, value, key0, value0 + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: UDFToInteger(key) (type: int), value (type: string), UDFToInteger(key0) (type: int), value0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.dest1 + Local Work: + Map Reduce Local Work + + Stage: Stage-0 + Move Operator + tables: + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.dest1 + + Stage: Stage-2 + Stats-Aggr Operator + +PREHOOK: query: FROM src src1 JOIN src src2 ON (src1.key = src2.key) +INSERT OVERWRITE TABLE dest1 SELECT src1.*, src2.* +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: default@dest1 +POSTHOOK: query: FROM src src1 JOIN src src2 ON (src1.key = src2.key) +INSERT OVERWRITE TABLE dest1 SELECT src1.*, src2.* +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Output: default@dest1 +POSTHOOK: Lineage: dest1.key1 EXPRESSION [(src)src1.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: dest1.key2 EXPRESSION [(src)src2.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: dest1.value1 SIMPLE [(src)src1.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest1.value2 SIMPLE [(src)src2.FieldSchema(name:value, type:string, comment:default), ] +PREHOOK: query: SELECT sum(hash(dest1.key1,dest1.value1,dest1.key2,dest1.value2)) FROM dest1 +PREHOOK: type: QUERY +PREHOOK: Input: default@dest1 +#### A masked pattern was here #### +POSTHOOK: query: SELECT sum(hash(dest1.key1,dest1.value1,dest1.key2,dest1.value2)) FROM dest1 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@dest1 +#### A masked pattern was here #### +-793937029770 http://git-wip-us.apache.org/repos/asf/hive/blob/bbb91292/ql/src/test/results/clientpositive/cbo_rp_cross_product_check_2.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/cbo_rp_cross_product_check_2.q.out b/ql/src/test/results/clientpositive/cbo_rp_cross_product_check_2.q.out new file mode 100644 index 0000000..cdd47b6 --- /dev/null +++ b/ql/src/test/results/clientpositive/cbo_rp_cross_product_check_2.q.out @@ -0,0 +1,699 @@ +PREHOOK: query: -- SORT_QUERY_RESULTS + +create table A as +select * from src +PREHOOK: type: CREATETABLE_AS_SELECT +PREHOOK: Input: default@src +PREHOOK: Output: database:default +PREHOOK: Output: default@A +POSTHOOK: query: -- SORT_QUERY_RESULTS + +create table A as +select * from src +POSTHOOK: type: CREATETABLE_AS_SELECT +POSTHOOK: Input: default@src +POSTHOOK: Output: database:default +POSTHOOK: Output: default@A +PREHOOK: query: create table B as +select * from src order by key +limit 10 +PREHOOK: type: CREATETABLE_AS_SELECT +PREHOOK: Input: default@src +PREHOOK: Output: database:default +PREHOOK: Output: default@B +POSTHOOK: query: create table B as +select * from src order by key +limit 10 +POSTHOOK: type: CREATETABLE_AS_SELECT +POSTHOOK: Input: default@src +POSTHOOK: Output: database:default +POSTHOOK: Output: default@B +Warning: Map Join MAPJOIN[9][bigTable=?] in task 'Stage-3:MAPRED' is a cross product +PREHOOK: query: explain select * from A join B +PREHOOK: type: QUERY +POSTHOOK: query: explain select * from A join B +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-4 is a root stage + Stage-3 depends on stages: Stage-4 + Stage-0 depends on stages: Stage-3 + +STAGE PLANS: + Stage: Stage-4 + Map Reduce Local Work + Alias -> Map Local Tables: + b + Fetch Operator + limit: -1 + Alias -> Map Local Operator Tree: + b + TableScan + alias: b + Statistics: Num rows: 10 Data size: 96 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 10 Data size: 96 Basic stats: COMPLETE Column stats: NONE + HashTable Sink Operator + keys: + 0 + 1 + + Stage: Stage-3 + Map Reduce + Map Operator Tree: + TableScan + alias: a + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 + 1 + outputColumnNames: key, value, key0, value0 + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string), key0 (type: string), value0 (type: string) + outputColumnNames: key, value, key0, value0 + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Local Work: + Map Reduce Local Work + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +Warning: Map Join MAPJOIN[17][bigTable=?] in task 'Stage-5:MAPRED' is a cross product +PREHOOK: query: explain select * from B d1 join B d2 on d1.key = d2.key join A +PREHOOK: type: QUERY +POSTHOOK: query: explain select * from B d1 join B d2 on d1.key = d2.key join A +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-7 is a root stage + Stage-5 depends on stages: Stage-7 + Stage-0 depends on stages: Stage-5 + +STAGE PLANS: + Stage: Stage-7 + Map Reduce Local Work + Alias -> Map Local Tables: + a + Fetch Operator + limit: -1 + d1 + Fetch Operator + limit: -1 + Alias -> Map Local Operator Tree: + a + TableScan + alias: a + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + HashTable Sink Operator + keys: + 0 + 1 + d1 + TableScan + alias: d1 + Statistics: Num rows: 10 Data size: 96 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 5 Data size: 48 Basic stats: COMPLETE Column stats: NONE + HashTable Sink Operator + keys: + 0 key (type: string) + 1 key (type: string) + + Stage: Stage-5 + Map Reduce + Map Operator Tree: + TableScan + alias: d2 + Statistics: Num rows: 10 Data size: 96 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 5 Data size: 48 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 key (type: string) + 1 key (type: string) + outputColumnNames: _col0, _col1, _col5, _col6 + Statistics: Num rows: 5 Data size: 52 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 + 1 + outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11 + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Local Work: + Map Reduce Local Work + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +Warning: Map Join MAPJOIN[25][bigTable=?] in task 'Stage-6:MAPRED' is a cross product +PREHOOK: query: explain select * from A join + (select d1.key + from B d1 join B d2 on d1.key = d2.key + where 1 = 1 group by d1.key) od1 +PREHOOK: type: QUERY +POSTHOOK: query: explain select * from A join + (select d1.key + from B d1 join B d2 on d1.key = d2.key + where 1 = 1 group by d1.key) od1 +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-9 is a root stage + Stage-2 depends on stages: Stage-9 + Stage-8 depends on stages: Stage-2 + Stage-6 depends on stages: Stage-8 + Stage-0 depends on stages: Stage-6 + +STAGE PLANS: + Stage: Stage-9 + Map Reduce Local Work + Alias -> Map Local Tables: + od1:d1 + Fetch Operator + limit: -1 + Alias -> Map Local Operator Tree: + od1:d1 + TableScan + alias: d1 + Statistics: Num rows: 10 Data size: 96 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 5 Data size: 48 Basic stats: COMPLETE Column stats: NONE + HashTable Sink Operator + keys: + 0 key (type: string) + 1 key (type: string) + + Stage: Stage-2 + Map Reduce + Map Operator Tree: + TableScan + alias: d2 + Statistics: Num rows: 10 Data size: 96 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 5 Data size: 48 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 key (type: string) + 1 key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 5 Data size: 52 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 5 Data size: 52 Basic stats: COMPLETE Column stats: NONE + Group By Operator + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 5 Data size: 52 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 5 Data size: 52 Basic stats: COMPLETE Column stats: NONE + Local Work: + Map Reduce Local Work + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 2 Data size: 20 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 2 Data size: 20 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + + Stage: Stage-8 + Map Reduce Local Work + Alias -> Map Local Tables: + a + Fetch Operator + limit: -1 + Alias -> Map Local Operator Tree: + a + TableScan + alias: a + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + HashTable Sink Operator + keys: + 0 + 1 + + Stage: Stage-6 + Map Reduce + Map Operator Tree: + TableScan + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 + 1 + outputColumnNames: _col0, _col1, _col5 + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Local Work: + Map Reduce Local Work + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +Warning: Map Join MAPJOIN[21][bigTable=?] in task 'Stage-6:MAPRED' is a cross product +Warning: Map Join MAPJOIN[22][bigTable=d2] in task 'Stage-2:MAPRED' is a cross product +PREHOOK: query: explain select * from A join (select d1.key from B d1 join B d2 where 1 = 1 group by d1.key) od1 +PREHOOK: type: QUERY +POSTHOOK: query: explain select * from A join (select d1.key from B d1 join B d2 where 1 = 1 group by d1.key) od1 +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-9 is a root stage + Stage-2 depends on stages: Stage-9 + Stage-8 depends on stages: Stage-2 + Stage-6 depends on stages: Stage-8 + Stage-0 depends on stages: Stage-6 + +STAGE PLANS: + Stage: Stage-9 + Map Reduce Local Work + Alias -> Map Local Tables: + od1:d1 + Fetch Operator + limit: -1 + Alias -> Map Local Operator Tree: + od1:d1 + TableScan + alias: d1 + Statistics: Num rows: 10 Data size: 96 Basic stats: COMPLETE Column stats: NONE + HashTable Sink Operator + keys: + 0 + 1 + + Stage: Stage-2 + Map Reduce + Map Operator Tree: + TableScan + alias: d2 + Statistics: Num rows: 10 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 + 1 + outputColumnNames: _col0 + Statistics: Num rows: 11 Data size: 105 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 11 Data size: 105 Basic stats: COMPLETE Column stats: NONE + Group By Operator + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 11 Data size: 105 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 11 Data size: 105 Basic stats: COMPLETE Column stats: NONE + Local Work: + Map Reduce Local Work + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 5 Data size: 47 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 5 Data size: 47 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + + Stage: Stage-8 + Map Reduce Local Work + Alias -> Map Local Tables: + a + Fetch Operator + limit: -1 + Alias -> Map Local Operator Tree: + a + TableScan + alias: a + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + HashTable Sink Operator + keys: + 0 + 1 + + Stage: Stage-6 + Map Reduce + Map Operator Tree: + TableScan + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 + 1 + outputColumnNames: _col0, _col1, _col5 + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Local Work: + Map Reduce Local Work + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +Warning: Map Join MAPJOIN[47][bigTable=?] in task 'Stage-7:MAPRED' is a cross product +Warning: Map Join MAPJOIN[39][bigTable=?] in task 'Stage-6:MAPRED' is a cross product +Warning: Shuffle Join JOIN[21][tables = [ss, od1]] in Stage 'Stage-2:MAPRED' is a cross product +PREHOOK: query: explain select * from +(select A.key from A group by key) ss join +(select d1.key from B d1 join B d2 on d1.key = d2.key where 1 = 1 group by d1.key) od1 +PREHOOK: type: QUERY +POSTHOOK: query: explain select * from +(select A.key from A group by key) ss join +(select d1.key from B d1 join B d2 on d1.key = d2.key where 1 = 1 group by d1.key) od1 +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-8 depends on stages: Stage-1, Stage-4 , consists of Stage-10, Stage-11, Stage-2 + Stage-10 has a backup stage: Stage-2 + Stage-6 depends on stages: Stage-10 + Stage-11 has a backup stage: Stage-2 + Stage-7 depends on stages: Stage-11 + Stage-2 + Stage-12 is a root stage + Stage-4 depends on stages: Stage-12 + Stage-0 depends on stages: Stage-6, Stage-7, Stage-2 + +STAGE PLANS: + Stage: Stage-1 + Map Reduce + Map Operator Tree: + TableScan + alias: a + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string) + outputColumnNames: key + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Group By Operator + keys: key (type: string) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + + Stage: Stage-8 + Conditional Operator + + Stage: Stage-10 + Map Reduce Local Work + Alias -> Map Local Tables: + $INTNAME1 + Fetch Operator + limit: -1 + Alias -> Map Local Operator Tree: + $INTNAME1 + TableScan + HashTable Sink Operator + keys: + 0 + 1 + + Stage: Stage-6 + Map Reduce + Map Operator Tree: + TableScan + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 + 1 + outputColumnNames: _col0, _col1 + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Local Work: + Map Reduce Local Work + + Stage: Stage-11 + Map Reduce Local Work + Alias -> Map Local Tables: + $INTNAME + Fetch Operator + limit: -1 + Alias -> Map Local Operator Tree: + $INTNAME + TableScan + HashTable Sink Operator + keys: + 0 + 1 + + Stage: Stage-7 + Map Reduce + Map Operator Tree: + TableScan + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 + 1 + outputColumnNames: _col0, _col1 + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Local Work: + Map Reduce Local Work + + Stage: Stage-2 + Map Reduce + Map Operator Tree: + TableScan + Reduce Output Operator + sort order: + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: string) + TableScan + Reduce Output Operator + sort order: + Statistics: Num rows: 2 Data size: 20 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: string) + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 + 1 + outputColumnNames: _col0, _col1 + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-12 + Map Reduce Local Work + Alias -> Map Local Tables: + od1:d1 + Fetch Operator + limit: -1 + Alias -> Map Local Operator Tree: + od1:d1 + TableScan + alias: d1 + Statistics: Num rows: 10 Data size: 96 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 5 Data size: 48 Basic stats: COMPLETE Column stats: NONE + HashTable Sink Operator + keys: + 0 key (type: string) + 1 key (type: string) + + Stage: Stage-4 + Map Reduce + Map Operator Tree: + TableScan + alias: d2 + Statistics: Num rows: 10 Data size: 96 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 5 Data size: 48 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 key (type: string) + 1 key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 5 Data size: 52 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 5 Data size: 52 Basic stats: COMPLETE Column stats: NONE + Group By Operator + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 5 Data size: 52 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 5 Data size: 52 Basic stats: COMPLETE Column stats: NONE + Local Work: + Map Reduce Local Work + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 2 Data size: 20 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 2 Data size: 20 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink +
