diff --git a/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/HiveJoinProjectTransposeRule.java b/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/HiveJoinProjectTransposeRule.java index e684432606..b163052c3b 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/HiveJoinProjectTransposeRule.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/HiveJoinProjectTransposeRule.java @@ -27,13 +27,14 @@ public class HiveJoinProjectTransposeRule extends JoinProjectTransposeRule { - public static final HiveJoinProjectTransposeRule LEFF_PROJECT_BTW_JOIN = + public static final HiveJoinProjectTransposeRule LEFT_PROJECT_BTW_JOIN = new HiveJoinProjectTransposeRule( operand(HiveJoin.class, operand(HiveProject.class, operand(HiveJoin.class, any())), operand(RelNode.class, any())), "JoinProjectTransposeRule(Project-Join-Other)", false, HiveRelFactories.HIVE_BUILDER); + public static final HiveJoinProjectTransposeRule RIGHT_PROJECT_BTW_JOIN = new HiveJoinProjectTransposeRule( operand(HiveJoin.class, 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 22f3266c87..108584526a 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 @@ -1785,16 +1785,15 @@ public RelNode apply(RelOptCluster cluster, RelOptSchema relOptSchema, SchemaPlu calcitePreCboPlan = hepPlan(calcitePreCboPlan, false, mdProvider.getMetadataProvider(), null, HiveRemoveSqCountCheck.INSTANCE); - perfLogger.PerfLogEnd(this.getClass().getName(), PerfLogger.OPTIMIZER, - "Calcite: Removing sq_count_check UDF "); + perfLogger.PerfLogEnd(this.getClass().getName(), PerfLogger.OPTIMIZER, "Calcite: Removing sq_count_check UDF "); } - // 4.1 Remove Projects between Joins so that JoinToMultiJoinRule can merge them to MultiJoin. - // Don't run this rule if hive is to remove sq_count_check since that rule expects to have project b/w join. + + // Remove Projects between Joins so that JoinToMultiJoinRule can merge them to MultiJoin calcitePreCboPlan = hepPlan(calcitePreCboPlan, true, mdProvider.getMetadataProvider(), executorProvider, - HepMatchOrder.BOTTOM_UP, HiveJoinProjectTransposeRule.LEFF_PROJECT_BTW_JOIN, - HiveJoinProjectTransposeRule.RIGHT_PROJECT_BTW_JOIN); + HepMatchOrder.BOTTOM_UP, HiveJoinProjectTransposeRule.LEFT_PROJECT_BTW_JOIN, + HiveJoinProjectTransposeRule.RIGHT_PROJECT_BTW_JOIN, HiveProjectMergeRule.INSTANCE); - // 4.2 Apply join order optimizations: reordering MST algorithm + // 4. Apply join order optimizations: reordering MST algorithm // If join optimizations failed because of missing stats, we continue with // the rest of optimizations if (profilesCBO.contains(ExtendedCBOProfile.JOIN_REORDERING)) { diff --git a/ql/src/test/results/clientpositive/llap/lineage2.q.out b/ql/src/test/results/clientpositive/llap/lineage2.q.out index d32f490a70..1cb0cc76fa 100644 --- a/ql/src/test/results/clientpositive/llap/lineage2.q.out +++ b/ql/src/test/results/clientpositive/llap/lineage2.q.out @@ -593,7 +593,7 @@ PREHOOK: Input: default@dept_n10 PREHOOK: Input: default@emp PREHOOK: Input: default@project_n10 PREHOOK: Output: default@tgt_n10 -{"version":"1.0","engine":"tez","database":"default","hash":"bd297ef302d63c60b0bfb692af732b04","queryText":"INSERT INTO TABLE tgt_n10\nSELECT emd.dept_name, emd.name, emd.emp_id, emd.mgr_id, p.project_id, p.project_name\nFROM (\n SELECT d.dept_name, em.name, em.emp_id, em.mgr_id, em.dept_id\n FROM (\n SELECT e.name, e.dept_id, e.emp_id emp_id, m.emp_id mgr_id\n FROM emp e JOIN emp m ON e.emp_id = m.emp_id\n ) em\n JOIN dept_n10 d ON d.dept_id = em.dept_id\n ) emd JOIN project_n10 p ON emd.dept_id = p.project_id","edges":[{"sources":[6],"targets":[0],"edgeType":"PROJECTION"},{"sources":[7],"targets":[1],"edgeType":"PROJECTION"},{"sources":[8],"targets":[2,3],"edgeType":"PROJECTION"},{"sources":[9],"targets":[4],"edgeType":"PROJECTION"},{"sources":[10],"targets":[5],"edgeType":"PROJECTION"},{"sources":[8,11],"targets":[0,1,2,3,4,5],"expression":"(e.emp_id is not null and e.dept_id is not null)","edgeType":"PREDICATE"},{"sources":[8],"targets":[0,1,2,3,4,5],"expression":"(e.emp_id = m.emp_id)","edgeType":"PREDICATE"},{"sources":[8],"targets":[0,1,2,3,4,5],"expression":"m.emp_id is not null","edgeType":"PREDICATE"},{"sources":[11,12],"targets":[0,1,2,3,4,5],"expression":"(e.dept_id = d.dept_id)","edgeType":"PREDICATE"},{"sources":[12],"targets":[0,1,2,3,4,5],"expression":"d.dept_id is not null","edgeType":"PREDICATE"},{"sources":[11,9],"targets":[0,1,2,3,4,5],"expression":"(e.dept_id = p.project_id)","edgeType":"PREDICATE"},{"sources":[9],"targets":[0,1,2,3,4,5],"expression":"p.project_id is not null","edgeType":"PREDICATE"},{"sources":[6],"targets":[0],"expression":"compute_stats(default.dept_n10.dept_name, 'hll')","edgeType":"PROJECTION"},{"sources":[7],"targets":[1],"expression":"compute_stats(default.emp.name, 'hll')","edgeType":"PROJECTION"},{"sources":[8],"targets":[2,3],"expression":"compute_stats(default.emp.emp_id, 'hll')","edgeType":"PROJECTION"},{"sources":[9],"targets":[4],"expression":"compute_stats(default.project_n10.project_id, 'hll')","edgeType":"PROJECTION"},{"sources":[10],"targets":[5],"expression":"compute_stats(default.project_n10.project_name, 'hll')","edgeType":"PROJECTION"}],"vertices":[{"id":0,"vertexType":"COLUMN","vertexId":"default.tgt_n10.dept_name"},{"id":1,"vertexType":"COLUMN","vertexId":"default.tgt_n10.name"},{"id":2,"vertexType":"COLUMN","vertexId":"default.tgt_n10.emp_id"},{"id":3,"vertexType":"COLUMN","vertexId":"default.tgt_n10.mgr_id"},{"id":4,"vertexType":"COLUMN","vertexId":"default.tgt_n10.proj_id"},{"id":5,"vertexType":"COLUMN","vertexId":"default.tgt_n10.proj_name"},{"id":6,"vertexType":"COLUMN","vertexId":"default.dept_n10.dept_name"},{"id":7,"vertexType":"COLUMN","vertexId":"default.emp.name"},{"id":8,"vertexType":"COLUMN","vertexId":"default.emp.emp_id"},{"id":9,"vertexType":"COLUMN","vertexId":"default.project_n10.project_id"},{"id":10,"vertexType":"COLUMN","vertexId":"default.project_n10.project_name"},{"id":11,"vertexType":"COLUMN","vertexId":"default.emp.dept_id"},{"id":12,"vertexType":"COLUMN","vertexId":"default.dept_n10.dept_id"}]} +{"version":"1.0","engine":"tez","database":"default","hash":"bd297ef302d63c60b0bfb692af732b04","queryText":"INSERT INTO TABLE tgt_n10\nSELECT emd.dept_name, emd.name, emd.emp_id, emd.mgr_id, p.project_id, p.project_name\nFROM (\n SELECT d.dept_name, em.name, em.emp_id, em.mgr_id, em.dept_id\n FROM (\n SELECT e.name, e.dept_id, e.emp_id emp_id, m.emp_id mgr_id\n FROM emp e JOIN emp m ON e.emp_id = m.emp_id\n ) em\n JOIN dept_n10 d ON d.dept_id = em.dept_id\n ) emd JOIN project_n10 p ON emd.dept_id = p.project_id","edges":[{"sources":[6],"targets":[0],"edgeType":"PROJECTION"},{"sources":[7],"targets":[1],"edgeType":"PROJECTION"},{"sources":[8],"targets":[2,3],"edgeType":"PROJECTION"},{"sources":[9],"targets":[4],"edgeType":"PROJECTION"},{"sources":[10],"targets":[5],"edgeType":"PROJECTION"},{"sources":[8,11],"targets":[0,1,2,3,4,5],"expression":"(e.emp_id is not null and e.dept_id is not null)","edgeType":"PREDICATE"},{"sources":[8],"targets":[0,1,2,3,4,5],"expression":"(e.emp_id = m.emp_id)","edgeType":"PREDICATE"},{"sources":[8],"targets":[0,1,2,3,4,5],"expression":"m.emp_id is not null","edgeType":"PREDICATE"},{"sources":[11,12,9],"targets":[0,1,2,3,4,5],"expression":"(e.dept_id = d.dept_id AND e.dept_id = p.project_id)","edgeType":"PREDICATE"},{"sources":[12],"targets":[0,1,2,3,4,5],"expression":"d.dept_id is not null","edgeType":"PREDICATE"},{"sources":[9],"targets":[0,1,2,3,4,5],"expression":"p.project_id is not null","edgeType":"PREDICATE"},{"sources":[6],"targets":[0],"expression":"compute_stats(default.dept_n10.dept_name, 'hll')","edgeType":"PROJECTION"},{"sources":[7],"targets":[1],"expression":"compute_stats(default.emp.name, 'hll')","edgeType":"PROJECTION"},{"sources":[8],"targets":[2,3],"expression":"compute_stats(default.emp.emp_id, 'hll')","edgeType":"PROJECTION"},{"sources":[9],"targets":[4],"expression":"compute_stats(default.project_n10.project_id, 'hll')","edgeType":"PROJECTION"},{"sources":[10],"targets":[5],"expression":"compute_stats(default.project_n10.project_name, 'hll')","edgeType":"PROJECTION"}],"vertices":[{"id":0,"vertexType":"COLUMN","vertexId":"default.tgt_n10.dept_name"},{"id":1,"vertexType":"COLUMN","vertexId":"default.tgt_n10.name"},{"id":2,"vertexType":"COLUMN","vertexId":"default.tgt_n10.emp_id"},{"id":3,"vertexType":"COLUMN","vertexId":"default.tgt_n10.mgr_id"},{"id":4,"vertexType":"COLUMN","vertexId":"default.tgt_n10.proj_id"},{"id":5,"vertexType":"COLUMN","vertexId":"default.tgt_n10.proj_name"},{"id":6,"vertexType":"COLUMN","vertexId":"default.dept_n10.dept_name"},{"id":7,"vertexType":"COLUMN","vertexId":"default.emp.name"},{"id":8,"vertexType":"COLUMN","vertexId":"default.emp.emp_id"},{"id":9,"vertexType":"COLUMN","vertexId":"default.project_n10.project_id"},{"id":10,"vertexType":"COLUMN","vertexId":"default.project_n10.project_name"},{"id":11,"vertexType":"COLUMN","vertexId":"default.emp.dept_id"},{"id":12,"vertexType":"COLUMN","vertexId":"default.dept_n10.dept_id"}]} PREHOOK: query: drop table if exists dest_l2 PREHOOK: type: DROPTABLE PREHOOK: query: create table dest_l2 (id int, c1 tinyint, c2 int, c3 bigint) stored as textfile diff --git a/ql/src/test/results/clientpositive/llap/materialized_view_rewrite_7.q.out b/ql/src/test/results/clientpositive/llap/materialized_view_rewrite_7.q.out index 6f00a5c82b..d6685c863d 100644 --- a/ql/src/test/results/clientpositive/llap/materialized_view_rewrite_7.q.out +++ b/ql/src/test/results/clientpositive/llap/materialized_view_rewrite_7.q.out @@ -267,11 +267,11 @@ STAGE PLANS: Tez #### A masked pattern was here #### Edges: - Map 10 <- Union 5 (CONTAINS) - Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 7 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) - Reducer 3 <- Map 9 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) - Reducer 4 <- Reducer 3 (SIMPLE_EDGE), Union 5 (CONTAINS) - Reducer 6 <- Union 5 (SIMPLE_EDGE) + Map 10 <- Union 4 (CONTAINS) + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 6 (SIMPLE_EDGE), Reducer 8 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE), Union 4 (CONTAINS) + Reducer 5 <- Union 4 (SIMPLE_EDGE) + Reducer 8 <- Map 7 (SIMPLE_EDGE), Map 9 (SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 @@ -316,28 +316,7 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs - Map 7 - Map Operator Tree: - TableScan - alias: depts_n6 - filterExpr: ((deptno > 10) and (deptno <= 11) and name is not null) (type: boolean) - Statistics: Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((deptno <= 11) and (deptno > 10) and name is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: deptno (type: int), name (type: varchar(256)) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col1 (type: varchar(256)) - sort order: + - Map-reduce partition columns: _col1 (type: varchar(256)) - Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: int) - Execution mode: vectorized, llap - LLAP IO: may be used (ACID table) - Map 8 + Map 6 Map Operator Tree: TableScan alias: locations_n4 @@ -357,6 +336,27 @@ STAGE PLANS: Statistics: Num rows: 2 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: may be used (ACID table) + Map 7 + Map Operator Tree: + TableScan + alias: depts_n6 + filterExpr: ((deptno > 10) and (deptno <= 11) and name is not null) (type: boolean) + Statistics: Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((deptno <= 11) and (deptno > 10) and name is not null) (type: boolean) + Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: deptno (type: int), name (type: varchar(256)) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: varchar(256)) + Execution mode: vectorized, llap + LLAP IO: may be used (ACID table) Map 9 Map Operator Tree: TableScan @@ -386,33 +386,12 @@ STAGE PLANS: Inner Join 0 to 2 keys: 0 _col1 (type: varchar(256)) - 1 _col1 (type: varchar(256)) - 2 _col0 (type: varchar(256)) - outputColumnNames: _col0, _col2 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col2 (type: int), _col0 (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: int) - Reducer 3 - Execution mode: llap - Reduce Operator Tree: - Merge Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1 + 1 _col0 (type: varchar(256)) + 2 _col1 (type: varchar(256)) + outputColumnNames: _col0, _col3 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - keys: _col1 (type: int), _col0 (type: int) + keys: _col0 (type: int), _col3 (type: int) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -421,7 +400,7 @@ STAGE PLANS: sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: int) Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reducer 4 + Reducer 3 Execution mode: vectorized, llap Reduce Operator Tree: Group By Operator @@ -439,7 +418,7 @@ STAGE PLANS: sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: int) Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reducer 6 + Reducer 5 Execution mode: vectorized, llap Reduce Operator Tree: Group By Operator @@ -454,8 +433,25 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Union 5 - Vertex: Union 5 + Reducer 8 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: varchar(256)) + sort order: + + Map-reduce partition columns: _col1 (type: varchar(256)) + Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: int) + Union 4 + Vertex: Union 4 Stage: Stage-0 Fetch Operator @@ -578,11 +574,11 @@ STAGE PLANS: Tez #### A masked pattern was here #### Edges: - Reducer 11 <- Map 10 (SIMPLE_EDGE), Union 5 (CONTAINS) - Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 7 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) - Reducer 3 <- Map 9 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) - Reducer 4 <- Reducer 3 (SIMPLE_EDGE), Union 5 (CONTAINS) - Reducer 6 <- Union 5 (SIMPLE_EDGE) + Reducer 11 <- Map 10 (SIMPLE_EDGE), Union 4 (CONTAINS) + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 6 (SIMPLE_EDGE), Reducer 8 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE), Union 4 (CONTAINS) + Reducer 5 <- Union 4 (SIMPLE_EDGE) + Reducer 8 <- Map 7 (SIMPLE_EDGE), Map 9 (SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 @@ -629,28 +625,7 @@ STAGE PLANS: value expressions: _col1 (type: bigint) Execution mode: llap LLAP IO: all inputs - Map 7 - Map Operator Tree: - TableScan - alias: depts_n6 - filterExpr: ((deptno > 10) and (deptno < 20) and ((deptno <= 11) or (deptno >= 19)) and name is not null) (type: boolean) - Statistics: Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (((deptno <= 11) or (deptno >= 19)) and (deptno < 20) and (deptno > 10) and name is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: deptno (type: int), name (type: varchar(256)) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col1 (type: varchar(256)) - sort order: + - Map-reduce partition columns: _col1 (type: varchar(256)) - Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: int) - Execution mode: vectorized, llap - LLAP IO: may be used (ACID table) - Map 8 + Map 6 Map Operator Tree: TableScan alias: locations_n4 @@ -670,7 +645,7 @@ STAGE PLANS: Statistics: Num rows: 2 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: may be used (ACID table) - Map 9 + Map 7 Map Operator Tree: TableScan alias: emps_n8 @@ -691,6 +666,27 @@ STAGE PLANS: value expressions: _col1 (type: float) Execution mode: vectorized, llap LLAP IO: may be used (ACID table) + Map 9 + Map Operator Tree: + TableScan + alias: depts_n6 + filterExpr: ((deptno > 10) and (deptno < 20) and ((deptno <= 11) or (deptno >= 19)) and name is not null) (type: boolean) + Statistics: Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (((deptno <= 11) or (deptno >= 19)) and (deptno < 20) and (deptno > 10) and name is not null) (type: boolean) + Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: deptno (type: int), name (type: varchar(256)) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: varchar(256)) + Execution mode: vectorized, llap + LLAP IO: may be used (ACID table) Reducer 11 Execution mode: llap Reduce Operator Tree: @@ -721,34 +717,13 @@ STAGE PLANS: Inner Join 0 to 2 keys: 0 _col1 (type: varchar(256)) - 1 _col1 (type: varchar(256)) - 2 _col0 (type: varchar(256)) - outputColumnNames: _col0, _col2 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col2 (type: int), _col0 (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: int) - Reducer 3 - Execution mode: llap - Reduce Operator Tree: - Merge Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col3 + 1 _col0 (type: varchar(256)) + 2 _col3 (type: varchar(256)) + outputColumnNames: _col0, _col4 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(_col3) - keys: _col1 (type: int) + aggregations: count(_col4) + keys: _col0 (type: int) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE @@ -758,7 +733,7 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) - Reducer 4 + Reducer 3 Execution mode: llap Reduce Operator Tree: Group By Operator @@ -779,7 +754,7 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) - Reducer 6 + Reducer 5 Execution mode: llap Reduce Operator Tree: Group By Operator @@ -799,8 +774,25 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Union 5 - Vertex: Union 5 + Reducer 8 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col3 + Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col3 (type: varchar(256)) + sort order: + + Map-reduce partition columns: _col3 (type: varchar(256)) + Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: float) + Union 4 + Vertex: Union 4 Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/llap/multiMapJoin1.q.out b/ql/src/test/results/clientpositive/llap/multiMapJoin1.q.out index ae821f600b..540ff08acc 100644 --- a/ql/src/test/results/clientpositive/llap/multiMapJoin1.q.out +++ b/ql/src/test/results/clientpositive/llap/multiMapJoin1.q.out @@ -881,49 +881,45 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col2 (type: string) - 1 _col1 (type: string) + 0 _col1 (type: string) + 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4 input vertices: 1 Map 4 Statistics: Num rows: 5142 Data size: 2697293 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string), _col4 (type: string), _col2 (type: string), _col2 (type: string) + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col2 (type: string) + 1 _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 5142 Data size: 2697293 Basic stats: COMPLETE Column stats: NONE + input vertices: + 1 Map 5 + Statistics: Num rows: 5656 Data size: 2967022 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col1 (type: string) + 0 _col3 (type: string) 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col7 input vertices: - 1 Map 5 - Statistics: Num rows: 5656 Data size: 2967022 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col2 (type: string) - 1 _col0 (type: string) + 1 Map 6 + Statistics: Num rows: 6221 Data size: 3263724 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: hash(_col0) (type: int), hash(_col1) (type: int), hash(_col3) (type: int), hash(_col5) (type: int), hash(_col4) (type: int), hash(_col7) (type: int), hash(_col2) (type: int), hash(_col2) (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - input vertices: - 1 Map 6 Statistics: Num rows: 6221 Data size: 3263724 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: hash(_col0) (type: int), hash(_col1) (type: int), hash(_col2) (type: int), hash(_col3) (type: int), hash(_col6) (type: int), hash(_col7) (type: int), hash(_col4) (type: int), hash(_col5) (type: int) + Group By Operator + aggregations: sum(_col0), sum(_col1), sum(_col2), sum(_col3), sum(_col4), sum(_col5), sum(_col6), sum(_col7) + mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 6221 Data size: 3263724 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col0), sum(_col1), sum(_col2), sum(_col3), sum(_col4), sum(_col5), sum(_col6), sum(_col7) - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 + Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: bigint), _col3 (type: bigint), _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: bigint) + value expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: bigint), _col3 (type: bigint), _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: bigint) Execution mode: vectorized, llap LLAP IO: no inputs Map 3 @@ -947,6 +943,26 @@ STAGE PLANS: Execution mode: vectorized, llap LLAP IO: no inputs Map 4 + Map Operator Tree: + TableScan + alias: smalltbl3 + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 10 Data size: 1840 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: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 5 Map Operator Tree: TableScan alias: smalltbl2 @@ -967,26 +983,6 @@ STAGE PLANS: value expressions: _col0 (type: string) Execution mode: vectorized, llap LLAP IO: no inputs - Map 5 - Map Operator Tree: - TableScan - alias: smalltbl3 - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 1840 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: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE - Execution mode: vectorized, llap - LLAP IO: no inputs Map 6 Map Operator Tree: TableScan @@ -1225,49 +1221,45 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col2 (type: string) - 1 _col1 (type: string) + 0 _col1 (type: string) + 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4 input vertices: 1 Map 4 Statistics: Num rows: 5142 Data size: 2697293 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string), _col4 (type: string), _col2 (type: string), _col2 (type: string) + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col2 (type: string) + 1 _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 5142 Data size: 2697293 Basic stats: COMPLETE Column stats: NONE + input vertices: + 1 Map 5 + Statistics: Num rows: 5656 Data size: 2967022 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col1 (type: string) + 0 _col3 (type: string) 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col7 input vertices: - 1 Map 5 - Statistics: Num rows: 5656 Data size: 2967022 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col2 (type: string) - 1 _col0 (type: string) + 1 Map 6 + Statistics: Num rows: 6221 Data size: 3263724 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: hash(_col0) (type: int), hash(_col1) (type: int), hash(_col3) (type: int), hash(_col5) (type: int), hash(_col4) (type: int), hash(_col7) (type: int), hash(_col2) (type: int), hash(_col2) (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - input vertices: - 1 Map 6 Statistics: Num rows: 6221 Data size: 3263724 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: hash(_col0) (type: int), hash(_col1) (type: int), hash(_col2) (type: int), hash(_col3) (type: int), hash(_col6) (type: int), hash(_col7) (type: int), hash(_col4) (type: int), hash(_col5) (type: int) + Group By Operator + aggregations: sum(_col0), sum(_col1), sum(_col2), sum(_col3), sum(_col4), sum(_col5), sum(_col6), sum(_col7) + mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 6221 Data size: 3263724 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col0), sum(_col1), sum(_col2), sum(_col3), sum(_col4), sum(_col5), sum(_col6), sum(_col7) - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 + Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: bigint), _col3 (type: bigint), _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: bigint) + value expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: bigint), _col3 (type: bigint), _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: bigint) Execution mode: vectorized, llap LLAP IO: no inputs Map 3 @@ -1291,6 +1283,26 @@ STAGE PLANS: Execution mode: vectorized, llap LLAP IO: no inputs Map 4 + Map Operator Tree: + TableScan + alias: smalltbl3 + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 10 Data size: 1840 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: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 5 Map Operator Tree: TableScan alias: smalltbl2 @@ -1311,26 +1323,6 @@ STAGE PLANS: value expressions: _col0 (type: string) Execution mode: vectorized, llap LLAP IO: no inputs - Map 5 - Map Operator Tree: - TableScan - alias: smalltbl3 - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 1840 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: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE - Execution mode: vectorized, llap - LLAP IO: no inputs Map 6 Map Operator Tree: TableScan @@ -1607,6 +1599,26 @@ STAGE PLANS: Execution mode: vectorized, llap LLAP IO: no inputs Map 8 + Map Operator Tree: + TableScan + alias: smalltbl3 + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 10 Data size: 1840 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: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 9 Map Operator Tree: TableScan alias: smalltbl2 @@ -1627,26 +1639,6 @@ STAGE PLANS: value expressions: _col0 (type: string) Execution mode: vectorized, llap LLAP IO: no inputs - Map 9 - Map Operator Tree: - TableScan - alias: smalltbl3 - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 1840 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: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE - Execution mode: vectorized, llap - LLAP IO: no inputs Reducer 2 Execution mode: llap Reduce Operator Tree: @@ -1659,11 +1651,11 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 4675 Data size: 2452085 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col2 (type: string) + key expressions: _col1 (type: string) sort order: + - Map-reduce partition columns: _col2 (type: string) + Map-reduce partition columns: _col1 (type: string) Statistics: Num rows: 4675 Data size: 2452085 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string) + value expressions: _col0 (type: string), _col2 (type: string), _col3 (type: string) Reducer 3 Execution mode: llap Reduce Operator Tree: @@ -1671,20 +1663,16 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col2 (type: string) - 1 _col1 (type: string) + 0 _col1 (type: string) + 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 5142 Data size: 2697293 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string), _col4 (type: string), _col2 (type: string), _col2 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Reduce Output Operator + key expressions: _col2 (type: string) + sort order: + + Map-reduce partition columns: _col2 (type: string) Statistics: Num rows: 5142 Data size: 2697293 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: string) - sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 5142 Data size: 2697293 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) + value expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string), _col4 (type: string) Reducer 4 Execution mode: llap Reduce Operator Tree: @@ -1692,16 +1680,16 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col1 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 + 0 _col2 (type: string) + 1 _col1 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 5656 Data size: 2967022 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col2 (type: string) + key expressions: _col3 (type: string) sort order: + - Map-reduce partition columns: _col2 (type: string) + Map-reduce partition columns: _col3 (type: string) Statistics: Num rows: 5656 Data size: 2967022 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string) + value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col4 (type: string), _col5 (type: string) Reducer 5 Execution mode: llap Reduce Operator Tree: @@ -1709,12 +1697,12 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col2 (type: string) + 0 _col3 (type: string) 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col7 Statistics: Num rows: 6221 Data size: 3263724 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: hash(_col0) (type: int), hash(_col1) (type: int), hash(_col2) (type: int), hash(_col3) (type: int), hash(_col6) (type: int), hash(_col7) (type: int), hash(_col4) (type: int), hash(_col5) (type: int) + expressions: hash(_col0) (type: int), hash(_col1) (type: int), hash(_col3) (type: int), hash(_col5) (type: int), hash(_col4) (type: int), hash(_col7) (type: int), hash(_col2) (type: int), hash(_col2) (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 Statistics: Num rows: 6221 Data size: 3263724 Basic stats: COMPLETE Column stats: NONE Group By Operator @@ -1982,6 +1970,26 @@ STAGE PLANS: Execution mode: vectorized, llap LLAP IO: no inputs Map 8 + Map Operator Tree: + TableScan + alias: smalltbl3 + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 10 Data size: 1840 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: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 9 Map Operator Tree: TableScan alias: smalltbl2 @@ -2002,26 +2010,6 @@ STAGE PLANS: value expressions: _col0 (type: string) Execution mode: vectorized, llap LLAP IO: no inputs - Map 9 - Map Operator Tree: - TableScan - alias: smalltbl3 - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 1840 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: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE - Execution mode: vectorized, llap - LLAP IO: no inputs Reducer 2 Execution mode: llap Reduce Operator Tree: @@ -2034,11 +2022,11 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 4675 Data size: 2452085 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col2 (type: string) + key expressions: _col1 (type: string) sort order: + - Map-reduce partition columns: _col2 (type: string) + Map-reduce partition columns: _col1 (type: string) Statistics: Num rows: 4675 Data size: 2452085 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string) + value expressions: _col0 (type: string), _col2 (type: string), _col3 (type: string) Reducer 3 Execution mode: llap Reduce Operator Tree: @@ -2046,20 +2034,16 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col2 (type: string) - 1 _col1 (type: string) + 0 _col1 (type: string) + 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 5142 Data size: 2697293 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string), _col4 (type: string), _col2 (type: string), _col2 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Reduce Output Operator + key expressions: _col2 (type: string) + sort order: + + Map-reduce partition columns: _col2 (type: string) Statistics: Num rows: 5142 Data size: 2697293 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: string) - sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 5142 Data size: 2697293 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) + value expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string), _col4 (type: string) Reducer 4 Execution mode: llap Reduce Operator Tree: @@ -2067,16 +2051,16 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col1 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 + 0 _col2 (type: string) + 1 _col1 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 5656 Data size: 2967022 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col2 (type: string) + key expressions: _col3 (type: string) sort order: + - Map-reduce partition columns: _col2 (type: string) + Map-reduce partition columns: _col3 (type: string) Statistics: Num rows: 5656 Data size: 2967022 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string) + value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col4 (type: string), _col5 (type: string) Reducer 5 Execution mode: llap Reduce Operator Tree: @@ -2084,12 +2068,12 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col2 (type: string) + 0 _col3 (type: string) 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col7 Statistics: Num rows: 6221 Data size: 3263724 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: hash(_col0) (type: int), hash(_col1) (type: int), hash(_col2) (type: int), hash(_col3) (type: int), hash(_col6) (type: int), hash(_col7) (type: int), hash(_col4) (type: int), hash(_col5) (type: int) + expressions: hash(_col0) (type: int), hash(_col1) (type: int), hash(_col3) (type: int), hash(_col5) (type: int), hash(_col4) (type: int), hash(_col7) (type: int), hash(_col2) (type: int), hash(_col2) (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 Statistics: Num rows: 6221 Data size: 3263724 Basic stats: COMPLETE Column stats: NONE Group By Operator diff --git a/ql/src/test/results/clientpositive/perf/spark/query54.q.out b/ql/src/test/results/clientpositive/perf/spark/query54.q.out index f10250f307..7d488f9b75 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query54.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query54.q.out @@ -1,6 +1,6 @@ -Warning: Shuffle Join JOIN[84][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3, $hdt$_4]] in Work 'Reducer 4' is a cross product -Warning: Shuffle Join JOIN[115][tables = [$hdt$_0, $hdt$_1]] in Work 'Reducer 5' is a cross product -Warning: Map Join MAPJOIN[145][bigTable=?] in task 'Stage-1:MAPRED' is a cross product +Warning: Shuffle Join JOIN[111][tables = [$hdt$_1, $hdt$_2]] in Work 'Reducer 3' is a cross product +Warning: Shuffle Join JOIN[107][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3, $hdt$_4]] in Work 'Reducer 14' is a cross product +Warning: Shuffle Join JOIN[114][tables = [$hdt$_1, $hdt$_2, $hdt$_0]] in Work 'Reducer 4' is a cross product Warning: Map Join MAPJOIN[144][bigTable=?] in task 'Stage-1:MAPRED' is a cross product PREHOOK: query: explain with my_customers as ( @@ -133,89 +133,18 @@ POSTHOOK: Input: default@web_sales STAGE DEPENDENCIES: Stage-2 is a root stage Stage-3 depends on stages: Stage-2 - Stage-4 depends on stages: Stage-3 - Stage-1 depends on stages: Stage-4 + Stage-1 depends on stages: Stage-3 Stage-0 depends on stages: Stage-1 STAGE PLANS: Stage: Stage-2 Spark Edges: - Reducer 28 <- Map 27 (GROUP, 2) - Reducer 29 <- Reducer 28 (GROUP, 1) + Reducer 29 <- Map 28 (GROUP, 2) + Reducer 30 <- Reducer 29 (GROUP, 1) #### A masked pattern was here #### Vertices: - Map 27 - Map Operator Tree: - TableScan - alias: date_dim - filterExpr: ((d_year = 1999) and (d_moy = 3)) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((d_moy = 3) and (d_year = 1999)) (type: boolean) - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: (d_month_seq + 3) (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: int) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 18262 Data size: 20435178 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: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE - Execution mode: vectorized - Reducer 28 - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - keys: KEY._col0 (type: int) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 9131 Data size: 10217589 Basic stats: COMPLETE Column stats: NONE - Select Operator - Statistics: Num rows: 9131 Data size: 10217589 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) - Reducer 29 - Execution mode: vectorized - Local Work: - Map Reduce Local Work - 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: NONE - Filter Operator - predicate: (sq_count_check(_col0) <= 1) (type: boolean) - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Select Operator - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Spark HashTable Sink Operator - keys: - 0 - 1 - - Stage: Stage-3 - Spark - Edges: - Reducer 23 <- Map 22 (GROUP, 2) - Reducer 24 <- Reducer 23 (GROUP, 1) -#### A masked pattern was here #### - Vertices: - Map 22 + Map 28 Map Operator Tree: TableScan alias: date_dim @@ -239,7 +168,7 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized - Reducer 23 + Reducer 29 Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -258,7 +187,7 @@ STAGE PLANS: sort order: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) - Reducer 24 + Reducer 30 Execution mode: vectorized Local Work: Map Reduce Local Work @@ -278,11 +207,11 @@ STAGE PLANS: 0 1 - Stage: Stage-4 + Stage: Stage-3 Spark #### A masked pattern was here #### Vertices: - Map 12 + Map 18 Map Operator Tree: TableScan alias: store @@ -306,23 +235,50 @@ STAGE PLANS: Stage: Stage-1 Spark Edges: - Reducer 11 <- Map 10 (PARTITION-LEVEL SORT, 654), Reducer 17 (PARTITION-LEVEL SORT, 654) - Reducer 14 <- Map 13 (PARTITION-LEVEL SORT, 458), Map 18 (PARTITION-LEVEL SORT, 458), Map 19 (PARTITION-LEVEL SORT, 458) - Reducer 15 <- Map 20 (PARTITION-LEVEL SORT, 505), Reducer 14 (PARTITION-LEVEL SORT, 505) - Reducer 16 <- Map 21 (PARTITION-LEVEL SORT, 1009), Reducer 15 (PARTITION-LEVEL SORT, 1009) - Reducer 17 <- Reducer 16 (GROUP, 610) - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 398), Map 9 (PARTITION-LEVEL SORT, 398) - Reducer 26 <- Map 25 (GROUP, 2) - Reducer 3 <- Reducer 11 (PARTITION-LEVEL SORT, 772), Reducer 2 (PARTITION-LEVEL SORT, 772) - Reducer 31 <- Map 30 (GROUP, 2) - Reducer 4 <- Reducer 26 (PARTITION-LEVEL SORT, 1), Reducer 3 (PARTITION-LEVEL SORT, 1) - Reducer 5 <- Reducer 31 (PARTITION-LEVEL SORT, 1), Reducer 4 (PARTITION-LEVEL SORT, 1) + Reducer 10 <- Reducer 9 (GROUP, 1) + Reducer 12 <- Map 11 (PARTITION-LEVEL SORT, 398), Map 15 (PARTITION-LEVEL SORT, 398) + Reducer 13 <- Reducer 12 (PARTITION-LEVEL SORT, 772), Reducer 17 (PARTITION-LEVEL SORT, 772) + Reducer 14 <- Reducer 13 (PARTITION-LEVEL SORT, 1), Reducer 32 (PARTITION-LEVEL SORT, 1) + Reducer 17 <- Map 16 (PARTITION-LEVEL SORT, 654), Reducer 23 (PARTITION-LEVEL SORT, 654) + Reducer 2 <- Map 1 (GROUP, 2) + Reducer 20 <- Map 19 (PARTITION-LEVEL SORT, 458), Map 24 (PARTITION-LEVEL SORT, 458), Map 25 (PARTITION-LEVEL SORT, 458) + Reducer 21 <- Map 26 (PARTITION-LEVEL SORT, 505), Reducer 20 (PARTITION-LEVEL SORT, 505) + Reducer 22 <- Map 27 (PARTITION-LEVEL SORT, 1009), Reducer 21 (PARTITION-LEVEL SORT, 1009) + Reducer 23 <- Reducer 22 (GROUP, 610) + Reducer 3 <- Reducer 10 (PARTITION-LEVEL SORT, 1), Reducer 2 (PARTITION-LEVEL SORT, 1) + Reducer 32 <- Map 31 (GROUP, 2) + Reducer 4 <- Reducer 14 (PARTITION-LEVEL SORT, 1), Reducer 3 (PARTITION-LEVEL SORT, 1) + Reducer 5 <- Reducer 4 (GROUP, 1009) Reducer 6 <- Reducer 5 (GROUP, 1009) - Reducer 7 <- Reducer 6 (GROUP, 1009) - Reducer 8 <- Reducer 7 (SORT, 1) + Reducer 7 <- Reducer 6 (SORT, 1) + Reducer 9 <- Map 1 (GROUP, 2) #### A masked pattern was here #### Vertices: Map 1 + Map Operator Tree: + TableScan + alias: date_dim + filterExpr: ((d_year = 1999) and (d_moy = 3)) (type: boolean) + Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((d_moy = 3) and (d_year = 1999)) (type: boolean) + Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: (d_month_seq + 3) (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE + Group By Operator + keys: _col0 (type: int) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 18262 Data size: 20435178 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: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE + Execution mode: vectorized + Map 11 Map Operator Tree: TableScan alias: store_sales @@ -342,7 +298,27 @@ STAGE PLANS: Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: int), _col2 (type: decimal(7,2)) Execution mode: vectorized - Map 10 + Map 15 + Map Operator Tree: + TableScan + alias: date_dim + filterExpr: d_date_sk is not null (type: boolean) + Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: d_date_sk is not null (type: boolean) + Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: d_date_sk (type: int), d_month_seq (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 73049 Data size: 81741831 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: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: int) + Execution mode: vectorized + Map 16 Map Operator Tree: TableScan alias: customer_address @@ -363,7 +339,7 @@ STAGE PLANS: 1 _col0 (type: string), _col1 (type: string) outputColumnNames: _col0 input vertices: - 1 Map 12 + 1 Map 18 Statistics: Num rows: 44000000 Data size: 44654715780 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) @@ -373,7 +349,7 @@ STAGE PLANS: Execution mode: vectorized Local Work: Map Reduce Local Work - Map 13 + Map 19 Map Operator Tree: TableScan alias: catalog_sales @@ -393,7 +369,7 @@ STAGE PLANS: Statistics: Num rows: 431992504 Data size: 58579807164 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: int), _col2 (type: int) Execution mode: vectorized - Map 18 + Map 24 Map Operator Tree: TableScan alias: web_sales @@ -413,7 +389,7 @@ STAGE PLANS: Statistics: Num rows: 431992504 Data size: 58579807164 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: int), _col2 (type: int) Execution mode: vectorized - Map 19 + Map 25 Map Operator Tree: TableScan alias: date_dim @@ -432,7 +408,7 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized - Map 20 + Map 26 Map Operator Tree: TableScan alias: item @@ -451,7 +427,7 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 115500 Data size: 165890114 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized - Map 21 + Map 27 Map Operator Tree: TableScan alias: customer @@ -471,7 +447,7 @@ STAGE PLANS: Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: int) Execution mode: vectorized - Map 25 + Map 31 Map Operator Tree: TableScan alias: date_dim @@ -495,51 +471,83 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized - Map 30 - Map Operator Tree: - TableScan - alias: date_dim - filterExpr: ((d_year = 1999) and (d_moy = 3)) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((d_moy = 3) and (d_year = 1999)) (type: boolean) - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: (d_month_seq + 3) (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: int) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 18262 Data size: 20435178 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: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE - Execution mode: vectorized - Map 9 - Map Operator Tree: - TableScan - alias: date_dim - filterExpr: d_date_sk is not null (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: d_date_sk is not null (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: d_date_sk (type: int), d_month_seq (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 73049 Data size: 81741831 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: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int) + Reducer 10 Execution mode: vectorized - Reducer 11 + 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: NONE + Filter Operator + predicate: (sq_count_check(_col0) <= 1) (type: boolean) + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Select Operator + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Reducer 12 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col4 + Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col1 (type: int) + sort order: + + Map-reduce partition columns: _col1 (type: int) + Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: decimal(7,2)), _col4 (type: int) + Reducer 13 + Local Work: + Map Reduce Local Work + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col5 (type: int) + outputColumnNames: _col2, _col4, _col10 + Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 + 1 + outputColumnNames: _col2, _col4, _col10 + input vertices: + 1 Reducer 30 + Statistics: Num rows: 696954748 Data size: 67758142923 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 696954748 Data size: 67758142923 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: decimal(7,2)), _col4 (type: int), _col10 (type: int) + Reducer 14 + Reduce Operator Tree: + Join Operator + condition map: + Left Outer Join 0 to 1 + keys: + 0 + 1 + outputColumnNames: _col2, _col4, _col10, _col13 + Statistics: Num rows: 6363893803988 Data size: 7746260663496473 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col10 (type: int), _col2 (type: decimal(7,2)), _col4 (type: int), _col13 (type: int) + outputColumnNames: _col0, _col4, _col11, _col13 + Statistics: Num rows: 6363893803988 Data size: 7746260663496473 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 6363893803988 Data size: 7746260663496473 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int), _col4 (type: decimal(7,2)), _col11 (type: int), _col13 (type: int) + Reducer 17 Reduce Operator Tree: Join Operator condition map: @@ -554,7 +562,19 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col5 (type: int) Statistics: Num rows: 316240138 Data size: 42883351551 Basic stats: COMPLETE Column stats: NONE - Reducer 14 + Reducer 2 + Execution mode: vectorized + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: int) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 9131 Data size: 10217589 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 9131 Data size: 10217589 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int) + Reducer 20 Reduce Operator Tree: Join Operator condition map: @@ -570,7 +590,7 @@ STAGE PLANS: Map-reduce partition columns: _col2 (type: int) Statistics: Num rows: 475191764 Data size: 64437789277 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: int) - Reducer 15 + Reducer 21 Reduce Operator Tree: Join Operator condition map: @@ -585,7 +605,7 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col1 (type: int) Statistics: Num rows: 522710951 Data size: 70881569741 Basic stats: COMPLETE Column stats: NONE - Reducer 16 + Reducer 22 Reduce Operator Tree: Join Operator condition map: @@ -605,7 +625,7 @@ STAGE PLANS: sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: int) Statistics: Num rows: 574982058 Data size: 77969728405 Basic stats: COMPLETE Column stats: NONE - Reducer 17 + Reducer 23 Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -623,61 +643,24 @@ STAGE PLANS: Map-reduce partition columns: _col1 (type: int) Statistics: Num rows: 287491029 Data size: 38984864202 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int) - Reducer 2 + Reducer 3 Reduce Operator Tree: Join Operator condition map: - Inner Join 0 to 1 + Right Outer Join 0 to 1 + filter predicates: + 0 + 1 {true} keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2, _col4 - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: decimal(7,2)), _col4 (type: int) - Reducer 26 - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - keys: KEY._col0 (type: int) - mode: mergepartial + 0 + 1 outputColumnNames: _col0 - Statistics: Num rows: 9131 Data size: 10217589 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9131 Data size: 10299768 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 9131 Data size: 10217589 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9131 Data size: 10299768 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int) - Reducer 3 - Local Work: - Map Reduce Local Work - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: int) - 1 _col5 (type: int) - outputColumnNames: _col2, _col4, _col10 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 - 1 - outputColumnNames: _col2, _col4, _col10 - input vertices: - 1 Reducer 24 - Statistics: Num rows: 696954748 Data size: 67758142923 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 696954748 Data size: 67758142923 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: decimal(7,2)), _col4 (type: int), _col10 (type: int) - Reducer 31 + Reducer 32 Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -690,69 +673,39 @@ STAGE PLANS: Statistics: Num rows: 9131 Data size: 10217589 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int) Reducer 4 - Local Work: - Map Reduce Local Work - Reduce Operator Tree: - Join Operator - condition map: - Left Outer Join 0 to 1 - keys: - 0 - 1 - outputColumnNames: _col2, _col4, _col10, _col13 - Statistics: Num rows: 6363893803988 Data size: 7746260663496473 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col10 (type: int), _col2 (type: decimal(7,2)), _col4 (type: int), _col13 (type: int) - outputColumnNames: _col0, _col4, _col11, _col13 - Statistics: Num rows: 6363893803988 Data size: 7746260663496473 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 - 1 - outputColumnNames: _col0, _col4, _col11, _col13 - input vertices: - 1 Reducer 29 - Statistics: Num rows: 6363893803988 Data size: 7803535707732365 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: int), _col4 (type: decimal(7,2)), _col11 (type: int), _col13 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 6363893803988 Data size: 7803535707732365 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 6363893803988 Data size: 7803535707732365 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: decimal(7,2)), _col2 (type: int), _col3 (type: int) - Reducer 5 Reduce Operator Tree: Join Operator condition map: - Left Outer Join 0 to 1 + Inner Join 0 to 1 keys: 0 1 - outputColumnNames: _col0, _col1, _col2, _col3, _col4 + outputColumnNames: _col0, _col2, _col6, _col13, _col15 Statistics: Num rows: 58108714324214428 Data size: 9223372036854775807 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col2 BETWEEN _col3 AND _col4 (type: boolean) - Statistics: Num rows: 6456523813801603 Data size: 1024819115206086144 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: int), _col1 (type: decimal(7,2)) - outputColumnNames: _col0, _col1 + Select Operator + expressions: _col2 (type: int), _col6 (type: decimal(7,2)), _col13 (type: int), _col15 (type: int), _col0 (type: int) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 58108714324214428 Data size: 9223372036854775807 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: _col2 BETWEEN _col3 AND _col4 (type: boolean) Statistics: Num rows: 6456523813801603 Data size: 1024819115206086144 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col1) - keys: _col0 (type: int) - mode: hash + Select Operator + expressions: _col0 (type: int), _col1 (type: decimal(7,2)) outputColumnNames: _col0, _col1 Statistics: Num rows: 6456523813801603 Data size: 1024819115206086144 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) + Group By Operator + aggregations: sum(_col1) + keys: _col0 (type: int) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 6456523813801603 Data size: 1024819115206086144 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: decimal(17,2)) - Reducer 6 + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 6456523813801603 Data size: 1024819115206086144 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: decimal(17,2)) + Reducer 5 Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -777,7 +730,7 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 3228261906900801 Data size: 512409557603043008 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) - Reducer 7 + Reducer 6 Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -796,7 +749,7 @@ STAGE PLANS: Statistics: Num rows: 1614130953450400 Data size: 256204778801521408 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.1 value expressions: _col2 (type: int) - Reducer 8 + Reducer 7 Execution mode: vectorized Reduce Operator Tree: Select Operator @@ -813,6 +766,25 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 9 + Execution mode: vectorized + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: int) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 9131 Data size: 10217589 Basic stats: COMPLETE Column stats: NONE + Select Operator + Statistics: Num rows: 9131 Data size: 10217589 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/perf/tez/query54.q.out b/ql/src/test/results/clientpositive/perf/tez/query54.q.out index 1c17d2a53a..0fd1b429d4 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query54.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query54.q.out @@ -1,7 +1,7 @@ -Warning: Shuffle Join MERGEJOIN[270][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3]] in Stage 'Reducer 4' is a cross product -Warning: Shuffle Join MERGEJOIN[271][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3, $hdt$_4]] in Stage 'Reducer 5' is a cross product -Warning: Shuffle Join MERGEJOIN[272][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 6' is a cross product -Warning: Shuffle Join MERGEJOIN[273][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 7' is a cross product +Warning: Shuffle Join MERGEJOIN[271][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3]] in Stage 'Reducer 4' is a cross product +Warning: Shuffle Join MERGEJOIN[272][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3, $hdt$_4]] in Stage 'Reducer 5' is a cross product +Warning: Shuffle Join MERGEJOIN[270][tables = [$hdt$_1, $hdt$_2]] in Stage 'Reducer 33' is a cross product +Warning: Shuffle Join MERGEJOIN[273][tables = [$hdt$_1, $hdt$_2, $hdt$_0]] in Stage 'Reducer 6' is a cross product PREHOOK: query: explain with my_customers as ( select distinct c_customer_sk @@ -133,31 +133,31 @@ POSTHOOK: Output: hdfs://### HDFS PATH ### Plan optimized by CBO. Vertex dependency in root stage -Map 1 <- Reducer 12 (BROADCAST_EDGE) -Map 17 <- Reducer 25 (BROADCAST_EDGE), Reducer 27 (BROADCAST_EDGE), Reducer 29 (BROADCAST_EDGE), Union 18 (CONTAINS) -Map 23 <- Reducer 25 (BROADCAST_EDGE), Reducer 27 (BROADCAST_EDGE), Union 18 (CONTAINS) -Reducer 10 <- Reducer 9 (SIMPLE_EDGE) -Reducer 12 <- Map 11 (CUSTOM_SIMPLE_EDGE) -Reducer 14 <- Map 13 (SIMPLE_EDGE), Map 16 (SIMPLE_EDGE) -Reducer 15 <- Reducer 14 (SIMPLE_EDGE), Reducer 22 (SIMPLE_EDGE) -Reducer 19 <- Map 24 (SIMPLE_EDGE), Union 18 (SIMPLE_EDGE) -Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 11 (SIMPLE_EDGE) -Reducer 20 <- Map 26 (SIMPLE_EDGE), Reducer 19 (SIMPLE_EDGE) -Reducer 21 <- Map 28 (SIMPLE_EDGE), Reducer 20 (SIMPLE_EDGE) -Reducer 22 <- Reducer 21 (SIMPLE_EDGE) -Reducer 25 <- Map 24 (CUSTOM_SIMPLE_EDGE) -Reducer 27 <- Map 26 (CUSTOM_SIMPLE_EDGE) -Reducer 29 <- Map 28 (CUSTOM_SIMPLE_EDGE) -Reducer 3 <- Reducer 15 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) -Reducer 31 <- Map 30 (SIMPLE_EDGE) -Reducer 32 <- Reducer 31 (CUSTOM_SIMPLE_EDGE) -Reducer 33 <- Map 30 (SIMPLE_EDGE) -Reducer 34 <- Reducer 33 (CUSTOM_SIMPLE_EDGE) -Reducer 35 <- Map 30 (SIMPLE_EDGE) -Reducer 4 <- Reducer 3 (CUSTOM_SIMPLE_EDGE), Reducer 32 (CUSTOM_SIMPLE_EDGE) -Reducer 5 <- Reducer 31 (CUSTOM_SIMPLE_EDGE), Reducer 4 (CUSTOM_SIMPLE_EDGE) -Reducer 6 <- Reducer 34 (CUSTOM_SIMPLE_EDGE), Reducer 5 (CUSTOM_SIMPLE_EDGE) -Reducer 7 <- Reducer 35 (CUSTOM_SIMPLE_EDGE), Reducer 6 (CUSTOM_SIMPLE_EDGE) +Map 1 <- Reducer 11 (BROADCAST_EDGE) +Map 16 <- Reducer 24 (BROADCAST_EDGE), Reducer 26 (BROADCAST_EDGE), Reducer 28 (BROADCAST_EDGE), Union 17 (CONTAINS) +Map 22 <- Reducer 24 (BROADCAST_EDGE), Reducer 26 (BROADCAST_EDGE), Union 17 (CONTAINS) +Reducer 11 <- Map 10 (CUSTOM_SIMPLE_EDGE) +Reducer 13 <- Map 12 (SIMPLE_EDGE), Map 15 (SIMPLE_EDGE) +Reducer 14 <- Reducer 13 (SIMPLE_EDGE), Reducer 21 (SIMPLE_EDGE) +Reducer 18 <- Map 23 (SIMPLE_EDGE), Union 17 (SIMPLE_EDGE) +Reducer 19 <- Map 25 (SIMPLE_EDGE), Reducer 18 (SIMPLE_EDGE) +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 10 (SIMPLE_EDGE) +Reducer 20 <- Map 27 (SIMPLE_EDGE), Reducer 19 (SIMPLE_EDGE) +Reducer 21 <- Reducer 20 (SIMPLE_EDGE) +Reducer 24 <- Map 23 (CUSTOM_SIMPLE_EDGE) +Reducer 26 <- Map 25 (CUSTOM_SIMPLE_EDGE) +Reducer 28 <- Map 27 (CUSTOM_SIMPLE_EDGE) +Reducer 3 <- Reducer 14 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) +Reducer 30 <- Map 29 (SIMPLE_EDGE) +Reducer 31 <- Reducer 30 (CUSTOM_SIMPLE_EDGE) +Reducer 32 <- Map 29 (SIMPLE_EDGE) +Reducer 33 <- Reducer 32 (CUSTOM_SIMPLE_EDGE), Reducer 35 (CUSTOM_SIMPLE_EDGE) +Reducer 34 <- Map 29 (SIMPLE_EDGE) +Reducer 35 <- Reducer 34 (CUSTOM_SIMPLE_EDGE) +Reducer 4 <- Reducer 3 (CUSTOM_SIMPLE_EDGE), Reducer 31 (CUSTOM_SIMPLE_EDGE) +Reducer 5 <- Reducer 30 (CUSTOM_SIMPLE_EDGE), Reducer 4 (CUSTOM_SIMPLE_EDGE) +Reducer 6 <- Reducer 33 (CUSTOM_SIMPLE_EDGE), Reducer 5 (CUSTOM_SIMPLE_EDGE) +Reducer 7 <- Reducer 6 (SIMPLE_EDGE) Reducer 8 <- Reducer 7 (SIMPLE_EDGE) Reducer 9 <- Reducer 8 (SIMPLE_EDGE) @@ -165,19 +165,19 @@ Stage-0 Fetch Operator limit:100 Stage-1 - Reducer 10 vectorized + Reducer 9 vectorized File Output Operator [FS_360] Limit [LIM_359] (rows=100 width=158) Number of rows:100 Select Operator [SEL_358] (rows=1614130953450400 width=158) Output:["_col0","_col1","_col2"] - <-Reducer 9 [SIMPLE_EDGE] vectorized + <-Reducer 8 [SIMPLE_EDGE] vectorized SHUFFLE [RS_357] Select Operator [SEL_356] (rows=1614130953450400 width=158) Output:["_col0","_col1","_col2"] Group By Operator [GBY_355] (rows=1614130953450400 width=158) Output:["_col0","_col1"],aggregations:["count(VALUE._col0)"],keys:KEY._col0 - <-Reducer 8 [SIMPLE_EDGE] vectorized + <-Reducer 7 [SIMPLE_EDGE] vectorized SHUFFLE [RS_354] PartitionCols:_col0 Group By Operator [GBY_353] (rows=3228261906900801 width=158) @@ -186,7 +186,7 @@ Stage-0 Output:["_col0"] Group By Operator [GBY_351] (rows=3228261906900801 width=158) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 - <-Reducer 7 [SIMPLE_EDGE] + <-Reducer 6 [SIMPLE_EDGE] SHUFFLE [RS_119] PartitionCols:_col0 Group By Operator [GBY_118] (rows=6456523813801603 width=158) @@ -195,259 +195,259 @@ Stage-0 Output:["_col0","_col1"] Filter Operator [FIL_116] (rows=6456523813801603 width=158) predicate:_col2 BETWEEN _col3 AND _col4 - Merge Join Operator [MERGEJOIN_273] (rows=58108714324214428 width=158) - Conds:(Left Outer),Output:["_col0","_col1","_col2","_col3","_col4"] - <-Reducer 35 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_350] - Group By Operator [GBY_349] (rows=9131 width=1119) - Output:["_col0"],keys:KEY._col0 - <-Map 30 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_331] - PartitionCols:_col0 - Group By Operator [GBY_328] (rows=18262 width=1119) - Output:["_col0"],keys:_col0 - Select Operator [SEL_325] (rows=18262 width=1119) - Output:["_col0"] - Filter Operator [FIL_322] (rows=18262 width=1119) - predicate:((d_moy = 3) and (d_year = 1999)) - TableScan [TS_50] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_month_seq","d_year","d_moy"] - <-Reducer 6 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_113] - Select Operator [SEL_104] (rows=6363893803988 width=1226) - Output:["_col0","_col1","_col2","_col3"] - Merge Join Operator [MERGEJOIN_272] (rows=6363893803988 width=1226) - Conds:(Inner),Output:["_col0","_col4","_col11","_col13"] - <-Reducer 34 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_348] - Select Operator [SEL_347] (rows=1 width=8) - Filter Operator [FIL_346] (rows=1 width=8) + Select Operator [SEL_115] (rows=58108714324214428 width=158) + Output:["_col0","_col1","_col2","_col3","_col4"] + Merge Join Operator [MERGEJOIN_273] (rows=58108714324214428 width=158) + Conds:(Inner),Output:["_col0","_col2","_col6","_col13","_col15"] + <-Reducer 33 [CUSTOM_SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_112] + Merge Join Operator [MERGEJOIN_270] (rows=9131 width=1128) + Conds:(Right Outer),Output:["_col0"] + <-Reducer 32 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_342] + Group By Operator [GBY_341] (rows=9131 width=1119) + Output:["_col0"],keys:KEY._col0 + <-Map 29 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_330] + PartitionCols:_col0 + Group By Operator [GBY_327] (rows=18262 width=1119) + Output:["_col0"],keys:_col0 + Select Operator [SEL_324] (rows=18262 width=1119) + Output:["_col0"] + Filter Operator [FIL_322] (rows=18262 width=1119) + predicate:((d_moy = 3) and (d_year = 1999)) + TableScan [TS_73] (rows=73049 width=1119) + default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_month_seq","d_year","d_moy"] + <-Reducer 35 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_350] + Select Operator [SEL_349] (rows=1 width=8) + Filter Operator [FIL_348] (rows=1 width=8) predicate:(sq_count_check(_col0) <= 1) - Group By Operator [GBY_345] (rows=1 width=8) + Group By Operator [GBY_347] (rows=1 width=8) Output:["_col0"],aggregations:["count(VALUE._col0)"] - <-Reducer 33 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_344] - Group By Operator [GBY_343] (rows=1 width=8) + <-Reducer 34 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_346] + Group By Operator [GBY_345] (rows=1 width=8) Output:["_col0"],aggregations:["count()"] - Select Operator [SEL_342] (rows=9131 width=1119) - Group By Operator [GBY_341] (rows=9131 width=1119) + Select Operator [SEL_344] (rows=9131 width=1119) + Group By Operator [GBY_343] (rows=9131 width=1119) Output:["_col0"],keys:KEY._col0 - <-Map 30 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_330] + <-Map 29 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_331] PartitionCols:_col0 - Group By Operator [GBY_327] (rows=18262 width=1119) + Group By Operator [GBY_328] (rows=18262 width=1119) Output:["_col0"],keys:_col0 - Select Operator [SEL_324] (rows=18262 width=1119) + Select Operator [SEL_325] (rows=18262 width=1119) Output:["_col0"] Please refer to the previous Filter Operator [FIL_322] - <-Reducer 5 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_101] - Select Operator [SEL_85] (rows=6363893803988 width=1217) - Output:["_col0","_col4","_col11","_col13"] - Merge Join Operator [MERGEJOIN_271] (rows=6363893803988 width=1217) - Conds:(Left Outer),Output:["_col2","_col4","_col10","_col13"] - <-Reducer 31 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_334] - Group By Operator [GBY_332] (rows=9131 width=1119) - Output:["_col0"],keys:KEY._col0 - <-Map 30 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_329] - PartitionCols:_col0 - Group By Operator [GBY_326] (rows=18262 width=1119) - Output:["_col0"],keys:_col0 - Select Operator [SEL_323] (rows=18262 width=1119) - Output:["_col0"] - Please refer to the previous Filter Operator [FIL_322] - <-Reducer 4 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_82] - Merge Join Operator [MERGEJOIN_270] (rows=696954748 width=97) - Conds:(Inner),Output:["_col2","_col4","_col10"] - <-Reducer 3 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_79] - Merge Join Operator [MERGEJOIN_269] (rows=696954748 width=88) - Conds:RS_76._col1=RS_77._col5(Inner),Output:["_col2","_col4","_col10"] - <-Reducer 15 [SIMPLE_EDGE] - SHUFFLE [RS_77] - PartitionCols:_col5 - Merge Join Operator [MERGEJOIN_268] (rows=316240138 width=135) - Conds:RS_46._col0=RS_321._col1(Inner),Output:["_col5"] - <-Reducer 14 [SIMPLE_EDGE] - SHUFFLE [RS_46] - PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_264] (rows=44000000 width=1014) - Conds:RS_297._col1, _col2=RS_300._col0, _col1(Inner),Output:["_col0"] - <-Map 13 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_297] - PartitionCols:_col1, _col2 - Select Operator [SEL_296] (rows=40000000 width=1014) - Output:["_col0","_col1","_col2"] - Filter Operator [FIL_295] (rows=40000000 width=1014) - predicate:(ca_address_sk is not null and ca_county is not null and ca_state is not null) - TableScan [TS_6] (rows=40000000 width=1014) - default@customer_address,customer_address,Tbl:COMPLETE,Col:NONE,Output:["ca_address_sk","ca_county","ca_state"] - <-Map 16 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_300] - PartitionCols:_col0, _col1 - Select Operator [SEL_299] (rows=1704 width=1910) - Output:["_col0","_col1"] - Filter Operator [FIL_298] (rows=1704 width=1910) - predicate:(s_county is not null and s_state is not null) - TableScan [TS_9] (rows=1704 width=1910) - default@store,store,Tbl:COMPLETE,Col:NONE,Output:["s_county","s_state"] - <-Reducer 22 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_321] - PartitionCols:_col1 - Select Operator [SEL_320] (rows=287491029 width=135) + <-Reducer 5 [CUSTOM_SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_113] + Select Operator [SEL_108] (rows=6363893803988 width=1217) + Output:["_col0","_col4","_col11","_col13"] + Merge Join Operator [MERGEJOIN_272] (rows=6363893803988 width=1217) + Conds:(Left Outer),Output:["_col2","_col4","_col10","_col13"] + <-Reducer 30 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_334] + Group By Operator [GBY_332] (rows=9131 width=1119) + Output:["_col0"],keys:KEY._col0 + <-Map 29 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_329] + PartitionCols:_col0 + Group By Operator [GBY_326] (rows=18262 width=1119) + Output:["_col0"],keys:_col0 + Select Operator [SEL_323] (rows=18262 width=1119) + Output:["_col0"] + Please refer to the previous Filter Operator [FIL_322] + <-Reducer 4 [CUSTOM_SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_105] + Merge Join Operator [MERGEJOIN_271] (rows=696954748 width=97) + Conds:(Inner),Output:["_col2","_col4","_col10"] + <-Reducer 3 [CUSTOM_SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_102] + Merge Join Operator [MERGEJOIN_269] (rows=696954748 width=88) + Conds:RS_99._col1=RS_100._col5(Inner),Output:["_col2","_col4","_col10"] + <-Reducer 14 [SIMPLE_EDGE] + SHUFFLE [RS_100] + PartitionCols:_col5 + Merge Join Operator [MERGEJOIN_268] (rows=316240138 width=135) + Conds:RS_69._col0=RS_321._col1(Inner),Output:["_col5"] + <-Reducer 13 [SIMPLE_EDGE] + SHUFFLE [RS_69] + PartitionCols:_col0 + Merge Join Operator [MERGEJOIN_264] (rows=44000000 width=1014) + Conds:RS_297._col1, _col2=RS_300._col0, _col1(Inner),Output:["_col0"] + <-Map 12 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_297] + PartitionCols:_col1, _col2 + Select Operator [SEL_296] (rows=40000000 width=1014) + Output:["_col0","_col1","_col2"] + Filter Operator [FIL_295] (rows=40000000 width=1014) + predicate:(ca_address_sk is not null and ca_county is not null and ca_state is not null) + TableScan [TS_29] (rows=40000000 width=1014) + default@customer_address,customer_address,Tbl:COMPLETE,Col:NONE,Output:["ca_address_sk","ca_county","ca_state"] + <-Map 15 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_300] + PartitionCols:_col0, _col1 + Select Operator [SEL_299] (rows=1704 width=1910) Output:["_col0","_col1"] - Group By Operator [GBY_319] (rows=287491029 width=135) - Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 - <-Reducer 21 [SIMPLE_EDGE] - SHUFFLE [RS_40] - PartitionCols:_col0, _col1 - Group By Operator [GBY_39] (rows=574982058 width=135) - Output:["_col0","_col1"],keys:_col10, _col9 - Merge Join Operator [MERGEJOIN_267] (rows=574982058 width=135) - Conds:RS_35._col1=RS_315._col0(Inner),Output:["_col9","_col10"] - <-Map 28 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_315] + Filter Operator [FIL_298] (rows=1704 width=1910) + predicate:(s_county is not null and s_state is not null) + TableScan [TS_32] (rows=1704 width=1910) + default@store,store,Tbl:COMPLETE,Col:NONE,Output:["s_county","s_state"] + <-Reducer 21 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_321] + PartitionCols:_col1 + Select Operator [SEL_320] (rows=287491029 width=135) + Output:["_col0","_col1"] + Group By Operator [GBY_319] (rows=287491029 width=135) + Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 + <-Reducer 20 [SIMPLE_EDGE] + SHUFFLE [RS_63] + PartitionCols:_col0, _col1 + Group By Operator [GBY_62] (rows=574982058 width=135) + Output:["_col0","_col1"],keys:_col10, _col9 + Merge Join Operator [MERGEJOIN_267] (rows=574982058 width=135) + Conds:RS_58._col1=RS_315._col0(Inner),Output:["_col9","_col10"] + <-Map 27 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_315] + PartitionCols:_col0 + Select Operator [SEL_314] (rows=80000000 width=860) + Output:["_col0","_col1"] + Filter Operator [FIL_313] (rows=80000000 width=860) + predicate:(c_current_addr_sk is not null and c_customer_sk is not null) + TableScan [TS_49] (rows=80000000 width=860) + default@customer,customer,Tbl:COMPLETE,Col:NONE,Output:["c_customer_sk","c_current_addr_sk"] + <-Reducer 19 [SIMPLE_EDGE] + SHUFFLE [RS_58] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_266] (rows=522710951 width=135) + Conds:RS_55._col2=RS_309._col0(Inner),Output:["_col1"] + <-Map 25 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_309] PartitionCols:_col0 - Select Operator [SEL_314] (rows=80000000 width=860) - Output:["_col0","_col1"] - Filter Operator [FIL_313] (rows=80000000 width=860) - predicate:(c_current_addr_sk is not null and c_customer_sk is not null) - TableScan [TS_26] (rows=80000000 width=860) - default@customer,customer,Tbl:COMPLETE,Col:NONE,Output:["c_customer_sk","c_current_addr_sk"] - <-Reducer 20 [SIMPLE_EDGE] - SHUFFLE [RS_35] - PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_266] (rows=522710951 width=135) - Conds:RS_32._col2=RS_309._col0(Inner),Output:["_col1"] - <-Map 26 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_309] + Select Operator [SEL_308] (rows=115500 width=1436) + Output:["_col0"] + Filter Operator [FIL_307] (rows=115500 width=1436) + predicate:((i_category = 'Jewelry') and (i_class = 'consignment') and i_item_sk is not null) + TableScan [TS_46] (rows=462000 width=1436) + default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_class","i_category"] + <-Reducer 18 [SIMPLE_EDGE] + SHUFFLE [RS_55] + PartitionCols:_col2 + Merge Join Operator [MERGEJOIN_265] (rows=475191764 width=135) + Conds:Union 17._col0=RS_303._col0(Inner),Output:["_col1","_col2"] + <-Map 23 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_303] PartitionCols:_col0 - Select Operator [SEL_308] (rows=115500 width=1436) + Select Operator [SEL_302] (rows=18262 width=1119) Output:["_col0"] - Filter Operator [FIL_307] (rows=115500 width=1436) - predicate:((i_category = 'Jewelry') and (i_class = 'consignment') and i_item_sk is not null) - TableScan [TS_23] (rows=462000 width=1436) - default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_class","i_category"] - <-Reducer 19 [SIMPLE_EDGE] - SHUFFLE [RS_32] - PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_265] (rows=475191764 width=135) - Conds:Union 18._col0=RS_303._col0(Inner),Output:["_col1","_col2"] - <-Map 24 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_303] - PartitionCols:_col0 - Select Operator [SEL_302] (rows=18262 width=1119) - Output:["_col0"] - Filter Operator [FIL_301] (rows=18262 width=1119) - predicate:((d_moy = 3) and (d_year = 1999) and d_date_sk is not null) - TableScan [TS_20] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year","d_moy"] - <-Union 18 [SIMPLE_EDGE] - <-Map 17 [CONTAINS] vectorized - Reduce Output Operator [RS_371] - PartitionCols:_col0 - Select Operator [SEL_370] (rows=287989836 width=135) - Output:["_col0","_col1","_col2"] - Filter Operator [FIL_369] (rows=287989836 width=135) - predicate:((cs_bill_customer_sk BETWEEN DynamicValue(RS_36_customer_c_customer_sk_min) AND DynamicValue(RS_36_customer_c_customer_sk_max) and in_bloom_filter(cs_bill_customer_sk, DynamicValue(RS_36_customer_c_customer_sk_bloom_filter))) and (cs_item_sk BETWEEN DynamicValue(RS_33_item_i_item_sk_min) AND DynamicValue(RS_33_item_i_item_sk_max) and in_bloom_filter(cs_item_sk, DynamicValue(RS_33_item_i_item_sk_bloom_filter))) and (cs_sold_date_sk BETWEEN DynamicValue(RS_30_date_dim_d_date_sk_min) AND DynamicValue(RS_30_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_30_date_dim_d_date_sk_bloom_filter))) and cs_bill_customer_sk is not null and cs_item_sk is not null and cs_sold_date_sk is not null) - TableScan [TS_274] (rows=287989836 width=135) - Output:["cs_sold_date_sk","cs_bill_customer_sk","cs_item_sk"] - <-Reducer 25 [BROADCAST_EDGE] vectorized - BROADCAST [RS_362] - Group By Operator [GBY_361] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 24 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_306] - Group By Operator [GBY_305] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_304] (rows=18262 width=1119) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_302] - <-Reducer 27 [BROADCAST_EDGE] vectorized - BROADCAST [RS_365] - Group By Operator [GBY_364] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 26 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_312] - Group By Operator [GBY_311] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_310] (rows=115500 width=1436) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_308] - <-Reducer 29 [BROADCAST_EDGE] vectorized - BROADCAST [RS_368] - Group By Operator [GBY_367] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=80000000)"] - <-Map 28 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_318] - Group By Operator [GBY_317] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=80000000)"] - Select Operator [SEL_316] (rows=80000000 width=860) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_314] - <-Map 23 [CONTAINS] vectorized - Reduce Output Operator [RS_374] - PartitionCols:_col0 - Select Operator [SEL_373] (rows=144002668 width=135) - Output:["_col0","_col1","_col2"] - Filter Operator [FIL_372] (rows=144002668 width=135) - predicate:((ws_item_sk BETWEEN DynamicValue(RS_33_item_i_item_sk_min) AND DynamicValue(RS_33_item_i_item_sk_max) and in_bloom_filter(ws_item_sk, DynamicValue(RS_33_item_i_item_sk_bloom_filter))) and (ws_sold_date_sk BETWEEN DynamicValue(RS_30_date_dim_d_date_sk_min) AND DynamicValue(RS_30_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_30_date_dim_d_date_sk_bloom_filter))) and ws_bill_customer_sk is not null and ws_item_sk is not null and ws_sold_date_sk is not null) - TableScan [TS_279] (rows=144002668 width=135) - Output:["ws_sold_date_sk","ws_item_sk","ws_bill_customer_sk"] - <-Reducer 25 [BROADCAST_EDGE] vectorized - BROADCAST [RS_363] - Please refer to the previous Group By Operator [GBY_361] - <-Reducer 27 [BROADCAST_EDGE] vectorized - BROADCAST [RS_366] - Please refer to the previous Group By Operator [GBY_364] - <-Reducer 2 [SIMPLE_EDGE] - SHUFFLE [RS_76] - PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_263] (rows=633595212 width=88) - Conds:RS_294._col0=RS_286._col0(Inner),Output:["_col1","_col2","_col4"] - <-Map 11 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_286] - PartitionCols:_col0 - Select Operator [SEL_285] (rows=73049 width=1119) - Output:["_col0","_col1"] - Filter Operator [FIL_284] (rows=73049 width=1119) - predicate:d_date_sk is not null - TableScan [TS_3] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_month_seq"] - <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_294] - PartitionCols:_col0 - Select Operator [SEL_293] (rows=575995635 width=88) - Output:["_col0","_col1","_col2"] - Filter Operator [FIL_292] (rows=575995635 width=88) - predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_74_date_dim_d_date_sk_min) AND DynamicValue(RS_74_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_74_date_dim_d_date_sk_bloom_filter))) and ss_customer_sk is not null and ss_sold_date_sk is not null) - TableScan [TS_0] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_customer_sk","ss_ext_sales_price"] - <-Reducer 12 [BROADCAST_EDGE] vectorized - BROADCAST [RS_291] - Group By Operator [GBY_290] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 11 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_289] - Group By Operator [GBY_288] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_287] (rows=73049 width=1119) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_285] - <-Reducer 32 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_340] - Select Operator [SEL_339] (rows=1 width=8) - Filter Operator [FIL_338] (rows=1 width=8) - predicate:(sq_count_check(_col0) <= 1) - Group By Operator [GBY_337] (rows=1 width=8) - Output:["_col0"],aggregations:["count(VALUE._col0)"] - <-Reducer 31 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_336] - Group By Operator [GBY_335] (rows=1 width=8) - Output:["_col0"],aggregations:["count()"] - Select Operator [SEL_333] (rows=9131 width=1119) - Please refer to the previous Group By Operator [GBY_332] + Filter Operator [FIL_301] (rows=18262 width=1119) + predicate:((d_moy = 3) and (d_year = 1999) and d_date_sk is not null) + TableScan [TS_43] (rows=73049 width=1119) + default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year","d_moy"] + <-Union 17 [SIMPLE_EDGE] + <-Map 16 [CONTAINS] vectorized + Reduce Output Operator [RS_371] + PartitionCols:_col0 + Select Operator [SEL_370] (rows=287989836 width=135) + Output:["_col0","_col1","_col2"] + Filter Operator [FIL_369] (rows=287989836 width=135) + predicate:((cs_bill_customer_sk BETWEEN DynamicValue(RS_59_customer_c_customer_sk_min) AND DynamicValue(RS_59_customer_c_customer_sk_max) and in_bloom_filter(cs_bill_customer_sk, DynamicValue(RS_59_customer_c_customer_sk_bloom_filter))) and (cs_item_sk BETWEEN DynamicValue(RS_56_item_i_item_sk_min) AND DynamicValue(RS_56_item_i_item_sk_max) and in_bloom_filter(cs_item_sk, DynamicValue(RS_56_item_i_item_sk_bloom_filter))) and (cs_sold_date_sk BETWEEN DynamicValue(RS_53_date_dim_d_date_sk_min) AND DynamicValue(RS_53_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_53_date_dim_d_date_sk_bloom_filter))) and cs_bill_customer_sk is not null and cs_item_sk is not null and cs_sold_date_sk is not null) + TableScan [TS_274] (rows=287989836 width=135) + Output:["cs_sold_date_sk","cs_bill_customer_sk","cs_item_sk"] + <-Reducer 24 [BROADCAST_EDGE] vectorized + BROADCAST [RS_362] + Group By Operator [GBY_361] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 23 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_306] + Group By Operator [GBY_305] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_304] (rows=18262 width=1119) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_302] + <-Reducer 26 [BROADCAST_EDGE] vectorized + BROADCAST [RS_365] + Group By Operator [GBY_364] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 25 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_312] + Group By Operator [GBY_311] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_310] (rows=115500 width=1436) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_308] + <-Reducer 28 [BROADCAST_EDGE] vectorized + BROADCAST [RS_368] + Group By Operator [GBY_367] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=80000000)"] + <-Map 27 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_318] + Group By Operator [GBY_317] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=80000000)"] + Select Operator [SEL_316] (rows=80000000 width=860) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_314] + <-Map 22 [CONTAINS] vectorized + Reduce Output Operator [RS_374] + PartitionCols:_col0 + Select Operator [SEL_373] (rows=144002668 width=135) + Output:["_col0","_col1","_col2"] + Filter Operator [FIL_372] (rows=144002668 width=135) + predicate:((ws_item_sk BETWEEN DynamicValue(RS_56_item_i_item_sk_min) AND DynamicValue(RS_56_item_i_item_sk_max) and in_bloom_filter(ws_item_sk, DynamicValue(RS_56_item_i_item_sk_bloom_filter))) and (ws_sold_date_sk BETWEEN DynamicValue(RS_53_date_dim_d_date_sk_min) AND DynamicValue(RS_53_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_53_date_dim_d_date_sk_bloom_filter))) and ws_bill_customer_sk is not null and ws_item_sk is not null and ws_sold_date_sk is not null) + TableScan [TS_279] (rows=144002668 width=135) + Output:["ws_sold_date_sk","ws_item_sk","ws_bill_customer_sk"] + <-Reducer 24 [BROADCAST_EDGE] vectorized + BROADCAST [RS_363] + Please refer to the previous Group By Operator [GBY_361] + <-Reducer 26 [BROADCAST_EDGE] vectorized + BROADCAST [RS_366] + Please refer to the previous Group By Operator [GBY_364] + <-Reducer 2 [SIMPLE_EDGE] + SHUFFLE [RS_99] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_263] (rows=633595212 width=88) + Conds:RS_294._col0=RS_286._col0(Inner),Output:["_col1","_col2","_col4"] + <-Map 10 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_286] + PartitionCols:_col0 + Select Operator [SEL_285] (rows=73049 width=1119) + Output:["_col0","_col1"] + Filter Operator [FIL_284] (rows=73049 width=1119) + predicate:d_date_sk is not null + TableScan [TS_26] (rows=73049 width=1119) + default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_month_seq"] + <-Map 1 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_294] + PartitionCols:_col0 + Select Operator [SEL_293] (rows=575995635 width=88) + Output:["_col0","_col1","_col2"] + Filter Operator [FIL_292] (rows=575995635 width=88) + predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_97_date_dim_d_date_sk_min) AND DynamicValue(RS_97_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_97_date_dim_d_date_sk_bloom_filter))) and ss_customer_sk is not null and ss_sold_date_sk is not null) + TableScan [TS_23] (rows=575995635 width=88) + default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_customer_sk","ss_ext_sales_price"] + <-Reducer 11 [BROADCAST_EDGE] vectorized + BROADCAST [RS_291] + Group By Operator [GBY_290] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 10 [CUSTOM_SIMPLE_EDGE] vectorized + SHUFFLE [RS_289] + Group By Operator [GBY_288] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_287] (rows=73049 width=1119) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_285] + <-Reducer 31 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_340] + Select Operator [SEL_339] (rows=1 width=8) + Filter Operator [FIL_338] (rows=1 width=8) + predicate:(sq_count_check(_col0) <= 1) + Group By Operator [GBY_337] (rows=1 width=8) + Output:["_col0"],aggregations:["count(VALUE._col0)"] + <-Reducer 30 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_336] + Group By Operator [GBY_335] (rows=1 width=8) + Output:["_col0"],aggregations:["count()"] + Select Operator [SEL_333] (rows=9131 width=1119) + Please refer to the previous Group By Operator [GBY_332]