diff --git itests/src/test/resources/testconfiguration.properties itests/src/test/resources/testconfiguration.properties index da2091ac5d2..eeca1c9d4ef 100644 --- itests/src/test/resources/testconfiguration.properties +++ itests/src/test/resources/testconfiguration.properties @@ -1731,6 +1731,8 @@ spark.only.query.negative.files=spark_job_max_tasks.q,\ spark_submit_negative_executor_cores.q,\ spark_submit_negative_executor_memory.q +tez.perf.disabled.query.files=mv_query44.q + spark.perf.disabled.query.files=query14.q,\ query64.q,\ cbo_query1.q,\ @@ -1829,7 +1831,8 @@ spark.perf.disabled.query.files=query14.q,\ cbo_query96.q,\ cbo_query97.q,\ cbo_query98.q,\ - cbo_query99.q + cbo_query99.q,\ + mv_query44.q druid.query.files=druidmini_test1.q,\ druidmini_test_ts.q,\ diff --git itests/util/src/main/java/org/apache/hadoop/hive/cli/control/CliConfigs.java itests/util/src/main/java/org/apache/hadoop/hive/cli/control/CliConfigs.java index afff0df759a..df058eaf6d3 100644 --- itests/util/src/main/java/org/apache/hadoop/hive/cli/control/CliConfigs.java +++ itests/util/src/main/java/org/apache/hadoop/hive/cli/control/CliConfigs.java @@ -285,6 +285,12 @@ public TezPerfCliConfig(boolean useConstraints) { try { setQueryDir("ql/src/test/queries/clientpositive/perf"); + if (useConstraints) { + excludesFrom(testConfigProps, "tez.perf.constraints.disabled.query.files"); + } else { + excludesFrom(testConfigProps, "tez.perf.disabled.query.files"); + } + excludesFrom(testConfigProps, "minimr.query.files"); excludesFrom(testConfigProps, "minitez.query.files"); excludesFrom(testConfigProps, "encrypted.query.files"); diff --git ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/HiveProjectJoinTransposeRule.java ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/HiveProjectJoinTransposeRule.java index 43c78968d0f..38759c0525d 100644 --- ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/HiveProjectJoinTransposeRule.java +++ ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/HiveProjectJoinTransposeRule.java @@ -17,17 +17,131 @@ */ package org.apache.hadoop.hive.ql.optimizer.calcite.rules; -import org.apache.calcite.rel.rules.ProjectJoinTransposeRule; +import java.util.ArrayList; +import java.util.List; +import org.apache.calcite.plan.RelOptRule; +import org.apache.calcite.plan.RelOptRuleCall; +import org.apache.calcite.rel.RelNode; +import org.apache.calcite.rel.core.Join; +import org.apache.calcite.rel.core.Project; +import org.apache.calcite.rel.core.SemiJoin; +import org.apache.calcite.rel.rules.PushProjector; +import org.apache.calcite.rel.type.RelDataTypeField; +import org.apache.calcite.rex.RexNode; import org.apache.calcite.tools.RelBuilderFactory; import org.apache.hadoop.hive.ql.optimizer.calcite.HiveRelFactories; -public class HiveProjectJoinTransposeRule extends ProjectJoinTransposeRule { +/** + * Planner rule that pushes a {@link org.apache.calcite.rel.core.Project} + * past a {@link org.apache.calcite.rel.core.Join} + * by splitting the projection into a projection on top of each child of + * the join. + * TODO: Use Calcite rule once we can pass the matching operand as a parameter + */ +public class HiveProjectJoinTransposeRule extends RelOptRule { public static final HiveProjectJoinTransposeRule INSTANCE = new HiveProjectJoinTransposeRule(HiveRelFactories.HIVE_BUILDER); + /** + * Condition for expressions that should be preserved in the projection. + */ + private final PushProjector.ExprCondition preserveExprCondition; + private HiveProjectJoinTransposeRule(RelBuilderFactory relBuilderFactory) { - super(expr -> true, relBuilderFactory); + super( + operand(Project.class, + operand(Join.class, + operand(RelNode.class, any()), + operand(RelNode.class, any()))), + relBuilderFactory, "HiveProjectJoinTransposeRule"); + this.preserveExprCondition = expr -> true; + } + + @Override + public boolean matches(RelOptRuleCall call) { + final RelNode leftInput = call.rel(2); + final RelNode rightInput = call.rel(3); + + if (leftInput instanceof Project && rightInput instanceof Project) { + return false; + } + + return true; + } + + //~ Methods ---------------------------------------------------------------- + + // implement RelOptRule + public void onMatch(RelOptRuleCall call) { + Project origProj = call.rel(0); + final Join join = call.rel(1); + + if (join instanceof SemiJoin) { + return; // TODO: support SemiJoin + } + // locate all fields referenced in the projection and join condition; + // determine which inputs are referenced in the projection and + // join condition; if all fields are being referenced and there are no + // special expressions, no point in proceeding any further + PushProjector pushProject = + new PushProjector( + origProj, + join.getCondition(), + join, + preserveExprCondition, + call.builder()); + if (pushProject.locateAllRefs()) { + return; + } + + // create left and right projections, projecting only those + // fields referenced on each side + RelNode leftProjRel = + pushProject.createProjectRefsAndExprs( + join.getLeft(), + true, + false); + RelNode rightProjRel = + pushProject.createProjectRefsAndExprs( + join.getRight(), + true, + true); + + // convert the join condition to reference the projected columns + RexNode newJoinFilter = null; + int[] adjustments = pushProject.getAdjustments(); + if (join.getCondition() != null) { + List projJoinFieldList = new ArrayList<>(); + projJoinFieldList.addAll( + join.getSystemFieldList()); + projJoinFieldList.addAll( + leftProjRel.getRowType().getFieldList()); + projJoinFieldList.addAll( + rightProjRel.getRowType().getFieldList()); + newJoinFilter = + pushProject.convertRefsAndExprs( + join.getCondition(), + projJoinFieldList, + adjustments); + } + + // create a new join with the projected children + Join newJoinRel = + join.copy( + join.getTraitSet(), + newJoinFilter, + leftProjRel, + rightProjRel, + join.getJoinType(), + join.isSemiJoinDone()); + + // put the original project on top of the join, converting it to + // reference the modified projection list + RelNode topProject = + pushProject.createNewProject(newJoinRel, adjustments); + + call.transformTo(topProject); } } diff --git ql/src/java/org/apache/hadoop/hive/ql/parse/CalcitePlanner.java ql/src/java/org/apache/hadoop/hive/ql/parse/CalcitePlanner.java index 82e975a50de..8e3ef3f7c8e 100644 --- ql/src/java/org/apache/hadoop/hive/ql/parse/CalcitePlanner.java +++ ql/src/java/org/apache/hadoop/hive/ql/parse/CalcitePlanner.java @@ -2065,9 +2065,9 @@ private RelNode applyPreJoinOrderingTransforms(RelNode basePlan, RelMetadataProv rules.add(new HivePointLookupOptimizerRule.FilterCondition(minNumORClauses)); rules.add(new HivePointLookupOptimizerRule.JoinCondition(minNumORClauses)); } + rules.add(HiveProjectJoinTransposeRule.INSTANCE); if (conf.getBoolVar(HiveConf.ConfVars.HIVE_OPTIMIZE_CONSTRAINTS_JOIN) && profilesCBO.contains(ExtendedCBOProfile.REFERENTIAL_CONSTRAINTS)) { - rules.add(HiveProjectJoinTransposeRule.INSTANCE); rules.add(HiveJoinConstraintsRule.INSTANCE); } rules.add(HiveJoinAddNotNullRule.INSTANCE_JOIN); @@ -2246,7 +2246,7 @@ private RelNode copyNodeScan(RelNode scan) { perfLogger.PerfLogEnd(this.getClass().getName(), PerfLogger.OPTIMIZER, "Calcite: View-based rewriting"); - if (calcitePreMVRewritingPlan != basePlan) { + if (!RelOptUtil.toString(calcitePreMVRewritingPlan).equals(RelOptUtil.toString(basePlan))) { // A rewriting was produced, we will check whether it was part of an incremental rebuild // to try to replace INSERT OVERWRITE by INSERT if (mvRebuildMode == MaterializationRebuildMode.INSERT_OVERWRITE_REBUILD && diff --git ql/src/test/queries/clientpositive/perf/mv_query44.q ql/src/test/queries/clientpositive/perf/mv_query44.q new file mode 100644 index 00000000000..7415f5e5e1b --- /dev/null +++ ql/src/test/queries/clientpositive/perf/mv_query44.q @@ -0,0 +1,47 @@ +set hive.mapred.mode=nonstrict; +set hive.materializedview.rewriting.time.window=-1; + +-- start query 1 in stream 0 using template query44.tpl and seed 1819994127 + +CREATE MATERIALIZED VIEW mv_store_sales_item_customer PARTITIONED ON (ss_sold_date_sk) +AS + select ss_item_sk, ss_store_sk, ss_customer_sk, ss_sold_date_sk, count(*) cnt, sum(ss_quantity) as ss_quantity, sum(ss_ext_wholesale_cost) as ss_ext_wholesale_cost,sum(ss_net_paid) as ss_net_paid,sum(ss_net_profit) as ss_net_profit, sum(ss_ext_sales_price) as ss_ext_sales_price, sum(ss_coupon_amt) amt, sum(ss_sales_price) ss_sales_price, sum(ss_quantity*ss_sales_price) ssales + from store_sales + group by ss_store_sk, + ss_item_sk, ss_customer_sk, ss_sold_date_sk; + +explain +select asceding.rnk, i1.i_product_name best_performing, i2.i_product_name worst_performing +from(select * + from (select item_sk,rank() over (order by rank_col asc) rnk + from (select ss_item_sk item_sk,avg(ss_net_profit) rank_col + from store_sales ss1 + where ss_store_sk = 410 + group by ss_item_sk + having avg(ss_net_profit) > 0.9*(select avg(ss_net_profit) rank_col + from store_sales + where ss_store_sk = 410 + and ss_hdemo_sk is null + group by ss_store_sk))V1)V11 + where rnk < 11) asceding, + (select * + from (select item_sk,rank() over (order by rank_col desc) rnk + from (select ss_item_sk item_sk,avg(ss_net_profit) rank_col + from store_sales ss1 + where ss_store_sk = 410 + group by ss_item_sk + having avg(ss_net_profit) > 0.9*(select avg(ss_net_profit) rank_col + from store_sales + where ss_store_sk = 410 + and ss_hdemo_sk is null + group by ss_store_sk))V2)V21 + where rnk < 11) descending, +item i1, +item i2 +where asceding.rnk = descending.rnk + and i1.i_item_sk=asceding.item_sk + and i2.i_item_sk=descending.item_sk +order by asceding.rnk +limit 100; + +-- end query 1 in stream 0 using template query44.tpl diff --git ql/src/test/results/clientpositive/perf/tez/cbo_query1.q.out ql/src/test/results/clientpositive/perf/tez/cbo_query1.q.out index 295ba99d533..9d0fa3a1095 100644 --- ql/src/test/results/clientpositive/perf/tez/cbo_query1.q.out +++ ql/src/test/results/clientpositive/perf/tez/cbo_query1.q.out @@ -59,7 +59,7 @@ POSTHOOK: Output: hdfs://### HDFS PATH ### CBO PLAN: HiveSortLimit(sort0=[$0], dir0=[ASC], fetch=[100]) HiveProject(c_customer_id=[$1]) - HiveJoin(condition=[AND(=($3, $8), >($4, $7))], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[AND(=($3, $7), >($4, $6))], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($2, $0)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(c_customer_sk=[$0], c_customer_id=[$1]) HiveFilter(condition=[IS NOT NULL($0)]) @@ -71,10 +71,10 @@ HiveSortLimit(sort0=[$0], dir0=[ASC], fetch=[100]) HiveProject(sr_returned_date_sk=[$0], sr_customer_sk=[$3], sr_store_sk=[$7], sr_fee=[$14]) HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($7), IS NOT NULL($3))]) HiveTableScan(table=[[default, store_returns]], table:alias=[store_returns]) - HiveProject(d_date_sk=[$0], d_year=[CAST(2000):INTEGER]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(=($6, 2000), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) - HiveProject(s_store_sk=[$0], s_state=[CAST(_UTF-16LE'NM'):VARCHAR(2147483647) CHARACTER SET "UTF-16LE" COLLATE "ISO-8859-1$en_US$primary"]) + HiveProject(s_store_sk=[$0]) HiveFilter(condition=[AND(=($24, _UTF-16LE'NM'), IS NOT NULL($0))]) HiveTableScan(table=[[default, store]], table:alias=[store]) HiveProject(_o__c0=[*(/($1, $2), 1.2)], ctr_store_sk=[$0]) @@ -85,7 +85,7 @@ HiveSortLimit(sort0=[$0], dir0=[ASC], fetch=[100]) HiveProject(sr_returned_date_sk=[$0], sr_customer_sk=[$3], sr_store_sk=[$7], sr_fee=[$14]) HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($7))]) HiveTableScan(table=[[default, store_returns]], table:alias=[store_returns]) - HiveProject(d_date_sk=[$0], d_year=[CAST(2000):INTEGER]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(=($6, 2000), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) diff --git ql/src/test/results/clientpositive/perf/tez/cbo_query10.q.out ql/src/test/results/clientpositive/perf/tez/cbo_query10.q.out index b226905d4eb..ccad67d5a76 100644 --- ql/src/test/results/clientpositive/perf/tez/cbo_query10.q.out +++ ql/src/test/results/clientpositive/perf/tez/cbo_query10.q.out @@ -154,7 +154,7 @@ HiveSortLimit(sort0=[$0], sort1=[$1], sort2=[$2], sort3=[$4], sort4=[$6], sort5= HiveProject(ss_sold_date_sk=[$0], ss_customer_sk=[$3]) HiveFilter(condition=[AND(IS NOT NULL($3), IS NOT NULL($0))]) HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) - HiveProject(d_date_sk=[$0], d_year=[CAST(2002):INTEGER], d_moy=[$8]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(=($6, 2002), BETWEEN(false, $8, 4, 7), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) HiveProject(ws_bill_customer_sk0=[$0], $f1=[true]) @@ -163,7 +163,7 @@ HiveSortLimit(sort0=[$0], sort1=[$1], sort2=[$2], sort3=[$4], sort4=[$6], sort5= HiveProject(ws_sold_date_sk=[$0], ws_bill_customer_sk=[$4]) HiveFilter(condition=[AND(IS NOT NULL($4), IS NOT NULL($0))]) HiveTableScan(table=[[default, web_sales]], table:alias=[web_sales]) - HiveProject(d_date_sk=[$0], d_year=[CAST(2002):INTEGER], d_moy=[$8]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(=($6, 2002), BETWEEN(false, $8, 4, 7), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) HiveProject(cs_ship_customer_sk0=[$0], $f1=[true]) @@ -172,7 +172,7 @@ HiveSortLimit(sort0=[$0], sort1=[$1], sort2=[$2], sort3=[$4], sort4=[$6], sort5= HiveProject(cs_sold_date_sk=[$0], cs_ship_customer_sk=[$7]) HiveFilter(condition=[AND(IS NOT NULL($7), IS NOT NULL($0))]) HiveTableScan(table=[[default, catalog_sales]], table:alias=[catalog_sales]) - HiveProject(d_date_sk=[$0], d_year=[CAST(2002):INTEGER], d_moy=[$8]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(=($6, 2002), BETWEEN(false, $8, 4, 7), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) diff --git ql/src/test/results/clientpositive/perf/tez/cbo_query11.q.out ql/src/test/results/clientpositive/perf/tez/cbo_query11.q.out index e09f7ecf7bc..de0783be165 100644 --- ql/src/test/results/clientpositive/perf/tez/cbo_query11.q.out +++ ql/src/test/results/clientpositive/perf/tez/cbo_query11.q.out @@ -159,65 +159,61 @@ POSTHOOK: Output: hdfs://### HDFS PATH ### CBO PLAN: HiveSortLimit(sort0=[$0], dir0=[ASC], fetch=[100]) HiveProject(c_preferred_cust_flag=[$1]) - HiveJoin(condition=[AND(=($0, $5), CASE(CAST(IS NOT NULL($6)):BOOLEAN, CASE(CAST(IS NOT NULL($8)):BOOLEAN, >(/($4, $8), /($2, $6)), >(null, /($2, $6))), CASE(CAST(IS NOT NULL($8)):BOOLEAN, >(/($4, $8), null), null)))], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[AND(=($0, $5), CASE(CAST(IS NOT NULL($6)):BOOLEAN, CASE($9, >(/($4, $8), /($2, $6)), >(null, /($2, $6))), CASE($9, >(/($4, $8), null), null)))], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject($f0=[$0], $f4=[$3], $f9=[$7]) - HiveAggregate(group=[{0, 1, 2, 3, 4, 5, 6}], agg#0=[sum($7)]) - HiveProject($f0=[$1], $f1=[$2], $f2=[$3], $f4=[$4], $f5=[$5], $f6=[$6], $f7=[$7], $f9=[-($11, $10)]) - HiveJoin(condition=[=($0, $9)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(c_customer_sk=[$0], c_customer_id=[$1], c_first_name=[$8], c_last_name=[$9], c_preferred_cust_flag=[$10], c_birth_country=[$14], c_login=[$15], c_email_address=[$16]) - HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($1))]) - HiveTableScan(table=[[default, customer]], table:alias=[customer]) - HiveJoin(condition=[=($0, $4)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(ss_sold_date_sk=[$0], ss_customer_sk=[$3], ss_ext_discount_amt=[$14], ss_ext_list_price=[$17]) - HiveFilter(condition=[AND(IS NOT NULL($3), IS NOT NULL($0))]) - HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) - HiveProject(d_date_sk=[$0], d_year=[CAST(2002):INTEGER]) - HiveFilter(condition=[AND(=($6, 2002), IS NOT NULL($0))]) - HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) + HiveAggregate(group=[{1, 2, 3, 4, 5, 6, 7}], agg#0=[sum($10)]) + HiveJoin(condition=[=($0, $9)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(c_customer_sk=[$0], c_customer_id=[$1], c_first_name=[$8], c_last_name=[$9], c_preferred_cust_flag=[$10], c_birth_country=[$14], c_login=[$15], c_email_address=[$16]) + HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($1))]) + HiveTableScan(table=[[default, customer]], table:alias=[customer]) + HiveJoin(condition=[=($0, $3)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(ss_sold_date_sk=[$0], ss_customer_sk=[$3], -=[-($17, $14)]) + HiveFilter(condition=[AND(IS NOT NULL($3), IS NOT NULL($0))]) + HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) + HiveProject(d_date_sk=[$0]) + HiveFilter(condition=[AND(=($6, 2002), IS NOT NULL($0))]) + HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) HiveJoin(condition=[=($2, $4)], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($2, $0)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject($f0=[$0], $f8=[$7]) - HiveAggregate(group=[{0, 1, 2, 3, 4, 5, 6}], agg#0=[sum($7)]) - HiveProject($f0=[$1], $f1=[$2], $f2=[$3], $f3=[$4], $f4=[$5], $f5=[$6], $f6=[$7], $f8=[-($11, $10)]) - HiveJoin(condition=[=($0, $9)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(c_customer_sk=[$0], c_customer_id=[$1], c_first_name=[$8], c_last_name=[$9], c_preferred_cust_flag=[$10], c_birth_country=[$14], c_login=[$15], c_email_address=[$16]) - HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($1))]) - HiveTableScan(table=[[default, customer]], table:alias=[customer]) - HiveJoin(condition=[=($0, $4)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(ws_sold_date_sk=[$0], ws_bill_customer_sk=[$4], ws_ext_discount_amt=[$22], ws_ext_list_price=[$25]) - HiveFilter(condition=[AND(IS NOT NULL($4), IS NOT NULL($0))]) - HiveTableScan(table=[[default, web_sales]], table:alias=[web_sales]) - HiveProject(d_date_sk=[$0], d_year=[CAST(2002):INTEGER]) - HiveFilter(condition=[AND(=($6, 2002), IS NOT NULL($0))]) - HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) + HiveAggregate(group=[{1, 2, 3, 4, 5, 6, 7}], agg#0=[sum($10)]) + HiveJoin(condition=[=($0, $9)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(c_customer_sk=[$0], c_customer_id=[$1], c_first_name=[$8], c_last_name=[$9], c_preferred_cust_flag=[$10], c_birth_country=[$14], c_login=[$15], c_email_address=[$16]) + HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($1))]) + HiveTableScan(table=[[default, customer]], table:alias=[customer]) + HiveJoin(condition=[=($0, $3)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(ws_sold_date_sk=[$0], ws_bill_customer_sk=[$4], -=[-($25, $22)]) + HiveFilter(condition=[AND(IS NOT NULL($4), IS NOT NULL($0))]) + HiveTableScan(table=[[default, web_sales]], table:alias=[web_sales]) + HiveProject(d_date_sk=[$0]) + HiveFilter(condition=[AND(=($6, 2002), IS NOT NULL($0))]) + HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) HiveProject($f0=[$0], $f9=[$7]) HiveFilter(condition=[>($7, 0)]) - HiveAggregate(group=[{0, 1, 2, 3, 4, 5, 6}], agg#0=[sum($7)]) - HiveProject($f0=[$1], $f1=[$2], $f2=[$3], $f4=[$4], $f5=[$5], $f6=[$6], $f7=[$7], $f9=[-($11, $10)]) - HiveJoin(condition=[=($0, $9)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(c_customer_sk=[$0], c_customer_id=[$1], c_first_name=[$8], c_last_name=[$9], c_preferred_cust_flag=[$10], c_birth_country=[$14], c_login=[$15], c_email_address=[$16]) - HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($1))]) - HiveTableScan(table=[[default, customer]], table:alias=[customer]) - HiveJoin(condition=[=($0, $4)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(ss_sold_date_sk=[$0], ss_customer_sk=[$3], ss_ext_discount_amt=[$14], ss_ext_list_price=[$17]) - HiveFilter(condition=[AND(IS NOT NULL($3), IS NOT NULL($0))]) - HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) - HiveProject(d_date_sk=[$0], d_year=[CAST(2001):INTEGER]) - HiveFilter(condition=[AND(=($6, 2001), IS NOT NULL($0))]) - HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) - HiveProject($f0=[$0], $f8=[$7]) - HiveFilter(condition=[>($7, 0)]) - HiveAggregate(group=[{0, 1, 2, 3, 4, 5, 6}], agg#0=[sum($7)]) - HiveProject($f0=[$1], $f1=[$2], $f2=[$3], $f3=[$4], $f4=[$5], $f5=[$6], $f6=[$7], $f8=[-($11, $10)]) + HiveAggregate(group=[{1, 2, 3, 4, 5, 6, 7}], agg#0=[sum($10)]) HiveJoin(condition=[=($0, $9)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(c_customer_sk=[$0], c_customer_id=[$1], c_first_name=[$8], c_last_name=[$9], c_preferred_cust_flag=[$10], c_birth_country=[$14], c_login=[$15], c_email_address=[$16]) HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($1))]) HiveTableScan(table=[[default, customer]], table:alias=[customer]) - HiveJoin(condition=[=($0, $4)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(ws_sold_date_sk=[$0], ws_bill_customer_sk=[$4], ws_ext_discount_amt=[$22], ws_ext_list_price=[$25]) - HiveFilter(condition=[AND(IS NOT NULL($4), IS NOT NULL($0))]) - HiveTableScan(table=[[default, web_sales]], table:alias=[web_sales]) - HiveProject(d_date_sk=[$0], d_year=[CAST(2001):INTEGER]) + HiveJoin(condition=[=($0, $3)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(ss_sold_date_sk=[$0], ss_customer_sk=[$3], -=[-($17, $14)]) + HiveFilter(condition=[AND(IS NOT NULL($3), IS NOT NULL($0))]) + HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(=($6, 2001), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) + HiveProject(customer_id=[$0], year_total=[$7], CAST=[CAST(IS NOT NULL($7)):BOOLEAN]) + HiveFilter(condition=[>($7, 0)]) + HiveAggregate(group=[{1, 2, 3, 4, 5, 6, 7}], agg#0=[sum($10)]) + HiveJoin(condition=[=($0, $9)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(c_customer_sk=[$0], c_customer_id=[$1], c_first_name=[$8], c_last_name=[$9], c_preferred_cust_flag=[$10], c_birth_country=[$14], c_login=[$15], c_email_address=[$16]) + HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($1))]) + HiveTableScan(table=[[default, customer]], table:alias=[customer]) + HiveJoin(condition=[=($0, $3)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(ws_sold_date_sk=[$0], ws_bill_customer_sk=[$4], -=[-($25, $22)]) + HiveFilter(condition=[AND(IS NOT NULL($4), IS NOT NULL($0))]) + HiveTableScan(table=[[default, web_sales]], table:alias=[web_sales]) + HiveProject(d_date_sk=[$0]) + HiveFilter(condition=[AND(=($6, 2001), IS NOT NULL($0))]) + HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) diff --git ql/src/test/results/clientpositive/perf/tez/cbo_query12.q.out ql/src/test/results/clientpositive/perf/tez/cbo_query12.q.out index dbfe6e72b41..cda7aa302e5 100644 --- ql/src/test/results/clientpositive/perf/tez/cbo_query12.q.out +++ ql/src/test/results/clientpositive/perf/tez/cbo_query12.q.out @@ -83,7 +83,7 @@ HiveProject(i_item_desc=[$0], i_category=[$1], i_class=[$2], i_current_price=[$3 HiveProject(ws_sold_date_sk=[$0], ws_item_sk=[$3], ws_ext_sales_price=[$23]) HiveFilter(condition=[AND(IS NOT NULL($3), IS NOT NULL($0))]) HiveTableScan(table=[[default, web_sales]], table:alias=[web_sales]) - HiveProject(d_date_sk=[$0], d_date=[$2]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(BETWEEN(false, CAST($2):TIMESTAMP(9), 2001-01-12 00:00:00, 2001-02-11 00:00:00), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) diff --git ql/src/test/results/clientpositive/perf/tez/cbo_query13.q.out ql/src/test/results/clientpositive/perf/tez/cbo_query13.q.out index ccad0880c4b..19f30397814 100644 --- ql/src/test/results/clientpositive/perf/tez/cbo_query13.q.out +++ ql/src/test/results/clientpositive/perf/tez/cbo_query13.q.out @@ -114,28 +114,28 @@ POSTHOOK: Input: default@store_sales POSTHOOK: Output: hdfs://### HDFS PATH ### CBO PLAN: HiveProject($f0=[/(CAST($0):DOUBLE, $1)], $f1=[/($2, $3)], $f2=[/($4, $5)], $f3=[CAST($4):DECIMAL(17, 2)]) - HiveAggregate(group=[{}], agg#0=[sum($16)], agg#1=[count($16)], agg#2=[sum($18)], agg#3=[count($18)], agg#4=[sum($19)], agg#5=[count($19)]) - HiveJoin(condition=[AND(=($0, $12), OR(AND(=($1, _UTF-16LE'M'), =($2, _UTF-16LE'4 yr Degree'), BETWEEN(false, $17, 100, 150), =($7, 3)), AND(=($1, _UTF-16LE'D'), =($2, _UTF-16LE'Primary'), BETWEEN(false, $17, 50, 100), =($7, 1)), AND(=($1, _UTF-16LE'U'), =($2, _UTF-16LE'Advanced Degree'), BETWEEN(false, $17, 150, 200), =($7, 1))))], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(cd_demo_sk=[$0], cd_marital_status=[$2], cd_education_status=[$3]) + HiveAggregate(group=[{}], agg#0=[sum($21)], agg#1=[count($21)], agg#2=[sum($22)], agg#3=[count($22)], agg#4=[sum($23)], agg#5=[count($23)]) + HiveJoin(condition=[AND(=($0, $17), OR(AND($1, $2, $27, $12), AND($3, $4, $28, $13), AND($5, $6, $29, $13)))], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(cd_demo_sk=[$0], ==[=($2, _UTF-16LE'M')], =2=[=($3, _UTF-16LE'4 yr Degree')], =3=[=($2, _UTF-16LE'D')], =4=[=($3, _UTF-16LE'Primary')], =5=[=($2, _UTF-16LE'U')], =6=[=($3, _UTF-16LE'Advanced Degree')]) HiveFilter(condition=[AND(IN($2, _UTF-16LE'M', _UTF-16LE'D', _UTF-16LE'U'), IN($3, _UTF-16LE'4 yr Degree', _UTF-16LE'Primary', _UTF-16LE'Advanced Degree'), IS NOT NULL($0))]) HiveTableScan(table=[[default, customer_demographics]], table:alias=[customer_demographics]) - HiveJoin(condition=[AND(=($11, $0), OR(AND(IN($1, _UTF-16LE'KY', _UTF-16LE'GA', _UTF-16LE'NM'), BETWEEN(false, $17, 100, 200)), AND(IN($1, _UTF-16LE'MT', _UTF-16LE'OR', _UTF-16LE'IN'), BETWEEN(false, $17, 150, 300)), AND(IN($1, _UTF-16LE'WI', _UTF-16LE'MO', _UTF-16LE'WV'), BETWEEN(false, $17, 50, 250))))], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(ca_address_sk=[$0], ca_state=[$8], ca_country=[CAST(_UTF-16LE'United States'):VARCHAR(2147483647) CHARACTER SET "UTF-16LE" COLLATE "ISO-8859-1$en_US$primary"]) + HiveJoin(condition=[AND(=($12, $0), OR(AND($1, $17), AND($2, $18), AND($3, $19)))], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(ca_address_sk=[$0], IN=[IN($8, _UTF-16LE'KY', _UTF-16LE'GA', _UTF-16LE'NM')], IN2=[IN($8, _UTF-16LE'MT', _UTF-16LE'OR', _UTF-16LE'IN')], IN3=[IN($8, _UTF-16LE'WI', _UTF-16LE'MO', _UTF-16LE'WV')]) HiveFilter(condition=[AND(IN($8, _UTF-16LE'KY', _UTF-16LE'GA', _UTF-16LE'NM', _UTF-16LE'MT', _UTF-16LE'OR', _UTF-16LE'IN', _UTF-16LE'WI', _UTF-16LE'MO', _UTF-16LE'WV'), =($10, _UTF-16LE'United States'), IS NOT NULL($0))]) HiveTableScan(table=[[default, customer_address]], table:alias=[customer_address]) HiveJoin(condition=[=($7, $0)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(hd_demo_sk=[$0], hd_dep_count=[$3]) + HiveProject(hd_demo_sk=[$0], ==[=($3, 3)], =2=[=($3, 1)]) HiveFilter(condition=[AND(IN($3, 3, 1), IS NOT NULL($0))]) HiveTableScan(table=[[default, household_demographics]], table:alias=[household_demographics]) - HiveJoin(condition=[=($3, $0)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(d_date_sk=[$0], d_year=[CAST(2001):INTEGER]) - HiveFilter(condition=[AND(=($6, 2001), IS NOT NULL($0))]) - HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) - HiveJoin(condition=[=($0, $5)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(s_store_sk=[$0]) - HiveFilter(condition=[IS NOT NULL($0)]) - HiveTableScan(table=[[default, store]], table:alias=[store]) - HiveProject(ss_sold_date_sk=[$0], ss_cdemo_sk=[$4], ss_hdemo_sk=[$5], ss_addr_sk=[$6], ss_store_sk=[$7], ss_quantity=[$10], ss_sales_price=[$13], ss_ext_sales_price=[$15], ss_ext_wholesale_cost=[$16], ss_net_profit=[$22]) + HiveJoin(condition=[=($0, $6)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(s_store_sk=[$0]) + HiveFilter(condition=[IS NOT NULL($0)]) + HiveTableScan(table=[[default, store]], table:alias=[store]) + HiveJoin(condition=[=($1, $0)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(d_date_sk=[$0]) + HiveFilter(condition=[AND(=($6, 2001), IS NOT NULL($0))]) + HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) + HiveProject(ss_sold_date_sk=[$0], ss_cdemo_sk=[$4], ss_hdemo_sk=[$5], ss_addr_sk=[$6], ss_store_sk=[$7], ss_quantity=[$10], ss_ext_sales_price=[$15], ss_ext_wholesale_cost=[$16], BETWEEN=[BETWEEN(false, $22, 100, 200)], BETWEEN9=[BETWEEN(false, $22, 150, 300)], BETWEEN10=[BETWEEN(false, $22, 50, 250)], BETWEEN11=[BETWEEN(false, $13, 100, 150)], BETWEEN12=[BETWEEN(false, $13, 50, 100)], BETWEEN13=[BETWEEN(false, $13, 150, 200)]) HiveFilter(condition=[AND(OR(BETWEEN(false, $13, 100, 150), BETWEEN(false, $13, 50, 100), BETWEEN(false, $13, 150, 200)), OR(BETWEEN(false, $22, 100, 200), BETWEEN(false, $22, 150, 300), BETWEEN(false, $22, 50, 250)), IS NOT NULL($7), IS NOT NULL($4), IS NOT NULL($5), IS NOT NULL($6), IS NOT NULL($0))]) HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) diff --git ql/src/test/results/clientpositive/perf/tez/cbo_query14.q.out ql/src/test/results/clientpositive/perf/tez/cbo_query14.q.out index 9bb4f2e7f28..e75609ba262 100644 --- ql/src/test/results/clientpositive/perf/tez/cbo_query14.q.out +++ ql/src/test/results/clientpositive/perf/tez/cbo_query14.q.out @@ -246,39 +246,39 @@ HiveSortLimit(sort0=[$0], sort1=[$1], sort2=[$2], sort3=[$3], dir0=[ASC], dir1=[ HiveProject(i_brand_id=[$0], i_class_id=[$1], i_category_id=[$2], $f3=[$3]) HiveUnion(all=[true]) HiveProject(i_brand_id=[$0], i_class_id=[$1], i_category_id=[$2], $f3=[$3]) - HiveAggregate(group=[{5, 6, 7}], agg#0=[count()]) - HiveJoin(condition=[=($1, $4)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveAggregate(group=[{4, 5, 6}], agg#0=[count()]) + HiveJoin(condition=[=($1, $3)], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($0, $2)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(ss_sold_date_sk=[$0], ss_item_sk=[$2]) HiveFilter(condition=[AND(IS NOT NULL($2), IS NOT NULL($0))]) HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) - HiveProject(d_date_sk=[$0], d_year=[$6]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(BETWEEN(false, $6, 1999, 2001), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[d1]) HiveProject(i_item_sk=[$0], i_brand_id=[$7], i_class_id=[$9], i_category_id=[$11]) HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($7), IS NOT NULL($9), IS NOT NULL($11))]) HiveTableScan(table=[[default, item]], table:alias=[iss]) HiveProject(i_brand_id=[$0], i_class_id=[$1], i_category_id=[$2], $f3=[$3]) - HiveAggregate(group=[{5, 6, 7}], agg#0=[count()]) - HiveJoin(condition=[=($1, $4)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveAggregate(group=[{4, 5, 6}], agg#0=[count()]) + HiveJoin(condition=[=($1, $3)], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($0, $2)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(cs_sold_date_sk=[$0], cs_item_sk=[$15]) HiveFilter(condition=[AND(IS NOT NULL($15), IS NOT NULL($0))]) HiveTableScan(table=[[default, catalog_sales]], table:alias=[catalog_sales]) - HiveProject(d_date_sk=[$0], d_year=[$6]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(BETWEEN(false, $6, 1999, 2001), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[d2]) HiveProject(i_item_sk=[$0], i_brand_id=[$7], i_class_id=[$9], i_category_id=[$11]) HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($7), IS NOT NULL($9), IS NOT NULL($11))]) HiveTableScan(table=[[default, item]], table:alias=[ics]) HiveProject(i_brand_id=[$0], i_class_id=[$1], i_category_id=[$2], $f3=[$3]) - HiveAggregate(group=[{5, 6, 7}], agg#0=[count()]) - HiveJoin(condition=[=($1, $4)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveAggregate(group=[{4, 5, 6}], agg#0=[count()]) + HiveJoin(condition=[=($1, $3)], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($0, $2)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(ws_sold_date_sk=[$0], ws_item_sk=[$3]) HiveFilter(condition=[AND(IS NOT NULL($3), IS NOT NULL($0))]) HiveTableScan(table=[[default, web_sales]], table:alias=[web_sales]) - HiveProject(d_date_sk=[$0], d_year=[$6]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(BETWEEN(false, $6, 1999, 2001), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[d3]) HiveProject(i_item_sk=[$0], i_brand_id=[$7], i_class_id=[$9], i_category_id=[$11]) @@ -292,7 +292,7 @@ HiveSortLimit(sort0=[$0], sort1=[$1], sort2=[$2], sort3=[$3], dir0=[ASC], dir1=[ HiveProject(ss_sold_date_sk=[$0], ss_item_sk=[$2], ss_quantity=[$10], ss_list_price=[$12]) HiveFilter(condition=[AND(IS NOT NULL($2), IS NOT NULL($0))]) HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) - HiveProject(d_date_sk=[$0], d_year=[CAST(2000):INTEGER], d_moy=[CAST(11):INTEGER]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(=($6, 2000), =($8, 11), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) HiveJoin(condition=[true], joinType=[inner], algorithm=[none], cost=[not available]) @@ -310,7 +310,7 @@ HiveSortLimit(sort0=[$0], sort1=[$1], sort2=[$2], sort3=[$3], dir0=[ASC], dir1=[ HiveProject(ss_sold_date_sk=[$0], ss_quantity=[$10], ss_list_price=[$12]) HiveFilter(condition=[IS NOT NULL($0)]) HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) - HiveProject(d_date_sk=[$0], d_year=[$6]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(BETWEEN(false, $6, 1999, 2001), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) HiveProject(quantity=[$1], list_price=[$2]) @@ -318,7 +318,7 @@ HiveSortLimit(sort0=[$0], sort1=[$1], sort2=[$2], sort3=[$3], dir0=[ASC], dir1=[ HiveProject(cs_sold_date_sk=[$0], cs_quantity=[$18], cs_list_price=[$20]) HiveFilter(condition=[IS NOT NULL($0)]) HiveTableScan(table=[[default, catalog_sales]], table:alias=[catalog_sales]) - HiveProject(d_date_sk=[$0], d_year=[$6]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(BETWEEN(false, $6, 1998, 2000), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) HiveProject(quantity=[$1], list_price=[$2]) @@ -326,7 +326,7 @@ HiveSortLimit(sort0=[$0], sort1=[$1], sort2=[$2], sort3=[$3], dir0=[ASC], dir1=[ HiveProject(ws_sold_date_sk=[$0], ws_quantity=[$18], ws_list_price=[$20]) HiveFilter(condition=[IS NOT NULL($0)]) HiveTableScan(table=[[default, web_sales]], table:alias=[web_sales]) - HiveProject(d_date_sk=[$0], d_year=[$6]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(BETWEEN(false, $6, 1998, 2000), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) HiveProject($f0=[/($0, $1)]) @@ -338,7 +338,7 @@ HiveSortLimit(sort0=[$0], sort1=[$1], sort2=[$2], sort3=[$3], dir0=[ASC], dir1=[ HiveProject(ss_sold_date_sk=[$0], ss_quantity=[$10], ss_list_price=[$12]) HiveFilter(condition=[IS NOT NULL($0)]) HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) - HiveProject(d_date_sk=[$0], d_year=[$6]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(BETWEEN(false, $6, 1999, 2001), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) HiveProject(quantity=[$1], list_price=[$2]) @@ -346,7 +346,7 @@ HiveSortLimit(sort0=[$0], sort1=[$1], sort2=[$2], sort3=[$3], dir0=[ASC], dir1=[ HiveProject(cs_sold_date_sk=[$0], cs_quantity=[$18], cs_list_price=[$20]) HiveFilter(condition=[IS NOT NULL($0)]) HiveTableScan(table=[[default, catalog_sales]], table:alias=[catalog_sales]) - HiveProject(d_date_sk=[$0], d_year=[$6]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(BETWEEN(false, $6, 1998, 2000), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) HiveProject(quantity=[$1], list_price=[$2]) @@ -354,7 +354,7 @@ HiveSortLimit(sort0=[$0], sort1=[$1], sort2=[$2], sort3=[$3], dir0=[ASC], dir1=[ HiveProject(ws_sold_date_sk=[$0], ws_quantity=[$18], ws_list_price=[$20]) HiveFilter(condition=[IS NOT NULL($0)]) HiveTableScan(table=[[default, web_sales]], table:alias=[web_sales]) - HiveProject(d_date_sk=[$0], d_year=[$6]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(BETWEEN(false, $6, 1998, 2000), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) HiveProject(channel=[_UTF-16LE'catalog'], i_brand_id=[$0], i_class_id=[$1], i_category_id=[$2], sales=[$3], number_sales=[$4]) @@ -375,39 +375,39 @@ HiveSortLimit(sort0=[$0], sort1=[$1], sort2=[$2], sort3=[$3], dir0=[ASC], dir1=[ HiveProject(i_brand_id=[$0], i_class_id=[$1], i_category_id=[$2], $f3=[$3]) HiveUnion(all=[true]) HiveProject(i_brand_id=[$0], i_class_id=[$1], i_category_id=[$2], $f3=[$3]) - HiveAggregate(group=[{5, 6, 7}], agg#0=[count()]) - HiveJoin(condition=[=($1, $4)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveAggregate(group=[{4, 5, 6}], agg#0=[count()]) + HiveJoin(condition=[=($1, $3)], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($0, $2)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(ss_sold_date_sk=[$0], ss_item_sk=[$2]) HiveFilter(condition=[AND(IS NOT NULL($2), IS NOT NULL($0))]) HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) - HiveProject(d_date_sk=[$0], d_year=[$6]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(BETWEEN(false, $6, 1999, 2001), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[d1]) HiveProject(i_item_sk=[$0], i_brand_id=[$7], i_class_id=[$9], i_category_id=[$11]) HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($7), IS NOT NULL($9), IS NOT NULL($11))]) HiveTableScan(table=[[default, item]], table:alias=[iss]) HiveProject(i_brand_id=[$0], i_class_id=[$1], i_category_id=[$2], $f3=[$3]) - HiveAggregate(group=[{5, 6, 7}], agg#0=[count()]) - HiveJoin(condition=[=($1, $4)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveAggregate(group=[{4, 5, 6}], agg#0=[count()]) + HiveJoin(condition=[=($1, $3)], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($0, $2)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(cs_sold_date_sk=[$0], cs_item_sk=[$15]) HiveFilter(condition=[AND(IS NOT NULL($15), IS NOT NULL($0))]) HiveTableScan(table=[[default, catalog_sales]], table:alias=[catalog_sales]) - HiveProject(d_date_sk=[$0], d_year=[$6]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(BETWEEN(false, $6, 1999, 2001), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[d2]) HiveProject(i_item_sk=[$0], i_brand_id=[$7], i_class_id=[$9], i_category_id=[$11]) HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($7), IS NOT NULL($9), IS NOT NULL($11))]) HiveTableScan(table=[[default, item]], table:alias=[ics]) HiveProject(i_brand_id=[$0], i_class_id=[$1], i_category_id=[$2], $f3=[$3]) - HiveAggregate(group=[{5, 6, 7}], agg#0=[count()]) - HiveJoin(condition=[=($1, $4)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveAggregate(group=[{4, 5, 6}], agg#0=[count()]) + HiveJoin(condition=[=($1, $3)], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($0, $2)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(ws_sold_date_sk=[$0], ws_item_sk=[$3]) HiveFilter(condition=[AND(IS NOT NULL($3), IS NOT NULL($0))]) HiveTableScan(table=[[default, web_sales]], table:alias=[web_sales]) - HiveProject(d_date_sk=[$0], d_year=[$6]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(BETWEEN(false, $6, 1999, 2001), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[d3]) HiveProject(i_item_sk=[$0], i_brand_id=[$7], i_class_id=[$9], i_category_id=[$11]) @@ -421,7 +421,7 @@ HiveSortLimit(sort0=[$0], sort1=[$1], sort2=[$2], sort3=[$3], dir0=[ASC], dir1=[ HiveProject(cs_sold_date_sk=[$0], cs_item_sk=[$15], cs_quantity=[$18], cs_list_price=[$20]) HiveFilter(condition=[AND(IS NOT NULL($15), IS NOT NULL($0))]) HiveTableScan(table=[[default, catalog_sales]], table:alias=[catalog_sales]) - HiveProject(d_date_sk=[$0], d_year=[CAST(2000):INTEGER], d_moy=[CAST(11):INTEGER]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(=($6, 2000), =($8, 11), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) HiveJoin(condition=[true], joinType=[inner], algorithm=[none], cost=[not available]) @@ -439,7 +439,7 @@ HiveSortLimit(sort0=[$0], sort1=[$1], sort2=[$2], sort3=[$3], dir0=[ASC], dir1=[ HiveProject(ss_sold_date_sk=[$0], ss_quantity=[$10], ss_list_price=[$12]) HiveFilter(condition=[IS NOT NULL($0)]) HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) - HiveProject(d_date_sk=[$0], d_year=[$6]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(BETWEEN(false, $6, 1999, 2001), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) HiveProject(quantity=[$1], list_price=[$2]) @@ -447,7 +447,7 @@ HiveSortLimit(sort0=[$0], sort1=[$1], sort2=[$2], sort3=[$3], dir0=[ASC], dir1=[ HiveProject(cs_sold_date_sk=[$0], cs_quantity=[$18], cs_list_price=[$20]) HiveFilter(condition=[IS NOT NULL($0)]) HiveTableScan(table=[[default, catalog_sales]], table:alias=[catalog_sales]) - HiveProject(d_date_sk=[$0], d_year=[$6]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(BETWEEN(false, $6, 1998, 2000), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) HiveProject(quantity=[$1], list_price=[$2]) @@ -455,7 +455,7 @@ HiveSortLimit(sort0=[$0], sort1=[$1], sort2=[$2], sort3=[$3], dir0=[ASC], dir1=[ HiveProject(ws_sold_date_sk=[$0], ws_quantity=[$18], ws_list_price=[$20]) HiveFilter(condition=[IS NOT NULL($0)]) HiveTableScan(table=[[default, web_sales]], table:alias=[web_sales]) - HiveProject(d_date_sk=[$0], d_year=[$6]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(BETWEEN(false, $6, 1998, 2000), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) HiveProject($f0=[/($0, $1)]) @@ -467,7 +467,7 @@ HiveSortLimit(sort0=[$0], sort1=[$1], sort2=[$2], sort3=[$3], dir0=[ASC], dir1=[ HiveProject(ss_sold_date_sk=[$0], ss_quantity=[$10], ss_list_price=[$12]) HiveFilter(condition=[IS NOT NULL($0)]) HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) - HiveProject(d_date_sk=[$0], d_year=[$6]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(BETWEEN(false, $6, 1999, 2001), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) HiveProject(quantity=[$1], list_price=[$2]) @@ -475,7 +475,7 @@ HiveSortLimit(sort0=[$0], sort1=[$1], sort2=[$2], sort3=[$3], dir0=[ASC], dir1=[ HiveProject(cs_sold_date_sk=[$0], cs_quantity=[$18], cs_list_price=[$20]) HiveFilter(condition=[IS NOT NULL($0)]) HiveTableScan(table=[[default, catalog_sales]], table:alias=[catalog_sales]) - HiveProject(d_date_sk=[$0], d_year=[$6]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(BETWEEN(false, $6, 1998, 2000), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) HiveProject(quantity=[$1], list_price=[$2]) @@ -483,7 +483,7 @@ HiveSortLimit(sort0=[$0], sort1=[$1], sort2=[$2], sort3=[$3], dir0=[ASC], dir1=[ HiveProject(ws_sold_date_sk=[$0], ws_quantity=[$18], ws_list_price=[$20]) HiveFilter(condition=[IS NOT NULL($0)]) HiveTableScan(table=[[default, web_sales]], table:alias=[web_sales]) - HiveProject(d_date_sk=[$0], d_year=[$6]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(BETWEEN(false, $6, 1998, 2000), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) HiveProject(channel=[_UTF-16LE'web'], i_brand_id=[$0], i_class_id=[$1], i_category_id=[$2], sales=[$3], number_sales=[$4]) @@ -504,39 +504,39 @@ HiveSortLimit(sort0=[$0], sort1=[$1], sort2=[$2], sort3=[$3], dir0=[ASC], dir1=[ HiveProject(i_brand_id=[$0], i_class_id=[$1], i_category_id=[$2], $f3=[$3]) HiveUnion(all=[true]) HiveProject(i_brand_id=[$0], i_class_id=[$1], i_category_id=[$2], $f3=[$3]) - HiveAggregate(group=[{5, 6, 7}], agg#0=[count()]) - HiveJoin(condition=[=($1, $4)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveAggregate(group=[{4, 5, 6}], agg#0=[count()]) + HiveJoin(condition=[=($1, $3)], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($0, $2)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(ss_sold_date_sk=[$0], ss_item_sk=[$2]) HiveFilter(condition=[AND(IS NOT NULL($2), IS NOT NULL($0))]) HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) - HiveProject(d_date_sk=[$0], d_year=[$6]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(BETWEEN(false, $6, 1999, 2001), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[d1]) HiveProject(i_item_sk=[$0], i_brand_id=[$7], i_class_id=[$9], i_category_id=[$11]) HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($7), IS NOT NULL($9), IS NOT NULL($11))]) HiveTableScan(table=[[default, item]], table:alias=[iss]) HiveProject(i_brand_id=[$0], i_class_id=[$1], i_category_id=[$2], $f3=[$3]) - HiveAggregate(group=[{5, 6, 7}], agg#0=[count()]) - HiveJoin(condition=[=($1, $4)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveAggregate(group=[{4, 5, 6}], agg#0=[count()]) + HiveJoin(condition=[=($1, $3)], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($0, $2)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(cs_sold_date_sk=[$0], cs_item_sk=[$15]) HiveFilter(condition=[AND(IS NOT NULL($15), IS NOT NULL($0))]) HiveTableScan(table=[[default, catalog_sales]], table:alias=[catalog_sales]) - HiveProject(d_date_sk=[$0], d_year=[$6]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(BETWEEN(false, $6, 1999, 2001), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[d2]) HiveProject(i_item_sk=[$0], i_brand_id=[$7], i_class_id=[$9], i_category_id=[$11]) HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($7), IS NOT NULL($9), IS NOT NULL($11))]) HiveTableScan(table=[[default, item]], table:alias=[ics]) HiveProject(i_brand_id=[$0], i_class_id=[$1], i_category_id=[$2], $f3=[$3]) - HiveAggregate(group=[{5, 6, 7}], agg#0=[count()]) - HiveJoin(condition=[=($1, $4)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveAggregate(group=[{4, 5, 6}], agg#0=[count()]) + HiveJoin(condition=[=($1, $3)], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($0, $2)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(ws_sold_date_sk=[$0], ws_item_sk=[$3]) HiveFilter(condition=[AND(IS NOT NULL($3), IS NOT NULL($0))]) HiveTableScan(table=[[default, web_sales]], table:alias=[web_sales]) - HiveProject(d_date_sk=[$0], d_year=[$6]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(BETWEEN(false, $6, 1999, 2001), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[d3]) HiveProject(i_item_sk=[$0], i_brand_id=[$7], i_class_id=[$9], i_category_id=[$11]) @@ -550,7 +550,7 @@ HiveSortLimit(sort0=[$0], sort1=[$1], sort2=[$2], sort3=[$3], dir0=[ASC], dir1=[ HiveProject(ws_sold_date_sk=[$0], ws_item_sk=[$3], ws_quantity=[$18], ws_list_price=[$20]) HiveFilter(condition=[AND(IS NOT NULL($3), IS NOT NULL($0))]) HiveTableScan(table=[[default, web_sales]], table:alias=[web_sales]) - HiveProject(d_date_sk=[$0], d_year=[CAST(2000):INTEGER], d_moy=[CAST(11):INTEGER]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(=($6, 2000), =($8, 11), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) HiveJoin(condition=[true], joinType=[inner], algorithm=[none], cost=[not available]) @@ -568,7 +568,7 @@ HiveSortLimit(sort0=[$0], sort1=[$1], sort2=[$2], sort3=[$3], dir0=[ASC], dir1=[ HiveProject(ss_sold_date_sk=[$0], ss_quantity=[$10], ss_list_price=[$12]) HiveFilter(condition=[IS NOT NULL($0)]) HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) - HiveProject(d_date_sk=[$0], d_year=[$6]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(BETWEEN(false, $6, 1999, 2001), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) HiveProject(quantity=[$1], list_price=[$2]) @@ -576,7 +576,7 @@ HiveSortLimit(sort0=[$0], sort1=[$1], sort2=[$2], sort3=[$3], dir0=[ASC], dir1=[ HiveProject(cs_sold_date_sk=[$0], cs_quantity=[$18], cs_list_price=[$20]) HiveFilter(condition=[IS NOT NULL($0)]) HiveTableScan(table=[[default, catalog_sales]], table:alias=[catalog_sales]) - HiveProject(d_date_sk=[$0], d_year=[$6]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(BETWEEN(false, $6, 1998, 2000), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) HiveProject(quantity=[$1], list_price=[$2]) @@ -584,7 +584,7 @@ HiveSortLimit(sort0=[$0], sort1=[$1], sort2=[$2], sort3=[$3], dir0=[ASC], dir1=[ HiveProject(ws_sold_date_sk=[$0], ws_quantity=[$18], ws_list_price=[$20]) HiveFilter(condition=[IS NOT NULL($0)]) HiveTableScan(table=[[default, web_sales]], table:alias=[web_sales]) - HiveProject(d_date_sk=[$0], d_year=[$6]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(BETWEEN(false, $6, 1998, 2000), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) HiveProject($f0=[/($0, $1)]) @@ -596,7 +596,7 @@ HiveSortLimit(sort0=[$0], sort1=[$1], sort2=[$2], sort3=[$3], dir0=[ASC], dir1=[ HiveProject(ss_sold_date_sk=[$0], ss_quantity=[$10], ss_list_price=[$12]) HiveFilter(condition=[IS NOT NULL($0)]) HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) - HiveProject(d_date_sk=[$0], d_year=[$6]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(BETWEEN(false, $6, 1999, 2001), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) HiveProject(quantity=[$1], list_price=[$2]) @@ -604,7 +604,7 @@ HiveSortLimit(sort0=[$0], sort1=[$1], sort2=[$2], sort3=[$3], dir0=[ASC], dir1=[ HiveProject(cs_sold_date_sk=[$0], cs_quantity=[$18], cs_list_price=[$20]) HiveFilter(condition=[IS NOT NULL($0)]) HiveTableScan(table=[[default, catalog_sales]], table:alias=[catalog_sales]) - HiveProject(d_date_sk=[$0], d_year=[$6]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(BETWEEN(false, $6, 1998, 2000), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) HiveProject(quantity=[$1], list_price=[$2]) @@ -612,7 +612,7 @@ HiveSortLimit(sort0=[$0], sort1=[$1], sort2=[$2], sort3=[$3], dir0=[ASC], dir1=[ HiveProject(ws_sold_date_sk=[$0], ws_quantity=[$18], ws_list_price=[$20]) HiveFilter(condition=[IS NOT NULL($0)]) HiveTableScan(table=[[default, web_sales]], table:alias=[web_sales]) - HiveProject(d_date_sk=[$0], d_year=[$6]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(BETWEEN(false, $6, 1998, 2000), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) diff --git ql/src/test/results/clientpositive/perf/tez/cbo_query15.q.out ql/src/test/results/clientpositive/perf/tez/cbo_query15.q.out index 02ad7c207c0..0ab0f5de29a 100644 --- ql/src/test/results/clientpositive/perf/tez/cbo_query15.q.out +++ ql/src/test/results/clientpositive/perf/tez/cbo_query15.q.out @@ -49,21 +49,21 @@ POSTHOOK: Output: hdfs://### HDFS PATH ### CBO PLAN: HiveSortLimit(sort0=[$0], dir0=[ASC], fetch=[100]) HiveProject(ca_zip=[$0], $f1=[$1]) - HiveAggregate(group=[{4}], agg#0=[sum($7)]) - HiveJoin(condition=[AND(=($6, $0), OR(IN(substr($4, 1, 5), _UTF-16LE'85669', _UTF-16LE'86197', _UTF-16LE'88274', _UTF-16LE'83405', _UTF-16LE'86475', _UTF-16LE'85392', _UTF-16LE'85460', _UTF-16LE'80348', _UTF-16LE'81792'), >($7, 500), IN($3, _UTF-16LE'CA', _UTF-16LE'WA', _UTF-16LE'GA')))], joinType=[inner], algorithm=[none], cost=[not available]) + HiveAggregate(group=[{3}], agg#0=[sum($8)]) + HiveJoin(condition=[AND(=($7, $0), OR($4, $9, $5))], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($1, $2)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(c_customer_sk=[$0], c_current_addr_sk=[$4]) HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($4))]) HiveTableScan(table=[[default, customer]], table:alias=[customer]) - HiveProject(ca_address_sk=[$0], ca_state=[$8], ca_zip=[$9]) + HiveProject(ca_address_sk=[$0], ca_zip=[$9], IN=[IN(substr($9, 1, 5), _UTF-16LE'85669', _UTF-16LE'86197', _UTF-16LE'88274', _UTF-16LE'83405', _UTF-16LE'86475', _UTF-16LE'85392', _UTF-16LE'85460', _UTF-16LE'80348', _UTF-16LE'81792')], IN3=[IN($8, _UTF-16LE'CA', _UTF-16LE'WA', _UTF-16LE'GA')]) HiveFilter(condition=[IS NOT NULL($0)]) HiveTableScan(table=[[default, customer_address]], table:alias=[customer_address]) - HiveProject(cs_sold_date_sk=[$0], cs_bill_customer_sk=[$1], cs_sales_price=[$2], d_date_sk=[$3], d_year=[$4], d_qoy=[$5]) - HiveJoin(condition=[=($0, $3)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(cs_sold_date_sk=[$0], cs_bill_customer_sk=[$3], cs_sales_price=[$21]) + HiveProject(cs_sold_date_sk=[$0], cs_bill_customer_sk=[$1], cs_sales_price=[$2], >=[$3], d_date_sk=[$4]) + HiveJoin(condition=[=($0, $4)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(cs_sold_date_sk=[$0], cs_bill_customer_sk=[$3], cs_sales_price=[$21], >=[>($21, 500)]) HiveFilter(condition=[AND(IS NOT NULL($3), IS NOT NULL($0))]) HiveTableScan(table=[[default, catalog_sales]], table:alias=[catalog_sales]) - HiveProject(d_date_sk=[$0], d_year=[CAST(2000):INTEGER], d_qoy=[CAST(2):INTEGER]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(=($10, 2), =($6, 2000), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) diff --git ql/src/test/results/clientpositive/perf/tez/cbo_query17.q.out ql/src/test/results/clientpositive/perf/tez/cbo_query17.q.out index 6c5b48033c0..84832a4b4d2 100644 --- ql/src/test/results/clientpositive/perf/tez/cbo_query17.q.out +++ ql/src/test/results/clientpositive/perf/tez/cbo_query17.q.out @@ -104,35 +104,35 @@ CBO PLAN: HiveSortLimit(sort0=[$0], sort1=[$1], sort2=[$2], dir0=[ASC], dir1=[ASC], dir2=[ASC], fetch=[100]) HiveProject(i_item_id=[$0], i_item_desc=[$1], s_state=[$2], store_sales_quantitycount=[$3], store_sales_quantityave=[/(CAST($4):DOUBLE, $3)], store_sales_quantitystdev=[POWER(/(-($5, /(*($6, $6), $3)), CASE(=($3, 1), null, -($3, 1))), 0.5)], store_sales_quantitycov=[/(POWER(/(-($5, /(*($6, $6), $3)), CASE(=($3, 1), null, -($3, 1))), 0.5), /(CAST($4):DOUBLE, $3))], as_store_returns_quantitycount=[$7], as_store_returns_quantityave=[/(CAST($8):DOUBLE, $7)], as_store_returns_quantitystdev=[POWER(/(-($9, /(*($10, $10), $7)), CASE(=($7, 1), null, -($7, 1))), 0.5)], store_returns_quantitycov=[/(POWER(/(-($9, /(*($10, $10), $7)), CASE(=($7, 1), null, -($7, 1))), 0.5), /(CAST($8):DOUBLE, $7))], catalog_sales_quantitycount=[$11], catalog_sales_quantityave=[/(CAST($12):DOUBLE, $11)], catalog_sales_quantitystdev=[/(POWER(/(-($13, /(*($14, $14), $11)), CASE(=($11, 1), null, -($11, 1))), 0.5), /(CAST($12):DOUBLE, $11))], catalog_sales_quantitycov=[/(POWER(/(-($13, /(*($14, $14), $11)), CASE(=($11, 1), null, -($11, 1))), 0.5), /(CAST($12):DOUBLE, $11))]) HiveAggregate(group=[{0, 1, 2}], agg#0=[count($3)], agg#1=[sum($3)], agg#2=[sum($7)], agg#3=[sum($6)], agg#4=[count($4)], agg#5=[sum($4)], agg#6=[sum($9)], agg#7=[sum($8)], agg#8=[count($5)], agg#9=[sum($5)], agg#10=[sum($11)], agg#11=[sum($10)]) - HiveProject($f0=[$9], $f1=[$10], $f2=[$25], $f3=[$5], $f4=[$21], $f5=[$14], $f30=[CAST($5):DOUBLE], $f7=[*(CAST($5):DOUBLE, CAST($5):DOUBLE)], $f40=[CAST($21):DOUBLE], $f9=[*(CAST($21):DOUBLE, CAST($21):DOUBLE)], $f50=[CAST($14):DOUBLE], $f11=[*(CAST($14):DOUBLE, CAST($14):DOUBLE)]) - HiveJoin(condition=[=($24, $3)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveJoin(condition=[AND(AND(=($2, $19), =($1, $18)), =($4, $20))], joinType=[inner], algorithm=[none], cost=[not available]) - HiveJoin(condition=[=($8, $1)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject($f0=[$8], $f1=[$9], $f2=[$22], $f3=[$5], $f4=[$19], $f5=[$13], $f30=[CAST($5):DOUBLE], $f7=[*(CAST($5):DOUBLE, CAST($5):DOUBLE)], $f40=[CAST($19):DOUBLE], $f9=[*(CAST($19):DOUBLE, CAST($19):DOUBLE)], $f50=[CAST($13):DOUBLE], $f11=[*(CAST($13):DOUBLE, CAST($13):DOUBLE)]) + HiveJoin(condition=[=($21, $3)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[AND(AND(=($2, $17), =($1, $16)), =($4, $18))], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($7, $1)], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($6, $0)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(ss_sold_date_sk=[$0], ss_item_sk=[$2], ss_customer_sk=[$3], ss_store_sk=[$7], ss_ticket_number=[$9], ss_quantity=[$10]) HiveFilter(condition=[AND(IS NOT NULL($3), IS NOT NULL($2), IS NOT NULL($9), IS NOT NULL($0), IS NOT NULL($7))]) HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) - HiveProject(d_date_sk=[$0], d_quarter_name=[CAST(_UTF-16LE'2000Q1'):VARCHAR(2147483647) CHARACTER SET "UTF-16LE" COLLATE "ISO-8859-1$en_US$primary"]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(=($15, _UTF-16LE'2000Q1'), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[d1]) HiveProject(i_item_sk=[$0], i_item_id=[$1], i_item_desc=[$4]) HiveFilter(condition=[IS NOT NULL($0)]) HiveTableScan(table=[[default, item]], table:alias=[item]) - HiveProject(cs_sold_date_sk=[$0], cs_bill_customer_sk=[$1], cs_item_sk=[$2], cs_quantity=[$3], d_date_sk=[$4], d_quarter_name=[$5], sr_returned_date_sk=[$6], sr_item_sk=[$7], sr_customer_sk=[$8], sr_ticket_number=[$9], sr_return_quantity=[$10], d_date_sk0=[$11], d_quarter_name0=[$12]) - HiveJoin(condition=[AND(=($8, $1), =($7, $2))], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(cs_sold_date_sk=[$0], cs_bill_customer_sk=[$1], cs_item_sk=[$2], cs_quantity=[$3], d_date_sk=[$4], sr_returned_date_sk=[$5], sr_item_sk=[$6], sr_customer_sk=[$7], sr_ticket_number=[$8], sr_return_quantity=[$9], d_date_sk0=[$10]) + HiveJoin(condition=[AND(=($7, $1), =($6, $2))], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($0, $4)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(cs_sold_date_sk=[$0], cs_bill_customer_sk=[$3], cs_item_sk=[$15], cs_quantity=[$18]) HiveFilter(condition=[AND(IS NOT NULL($3), IS NOT NULL($15), IS NOT NULL($0))]) HiveTableScan(table=[[default, catalog_sales]], table:alias=[catalog_sales]) - HiveProject(d_date_sk=[$0], d_quarter_name=[$15]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(IN($15, _UTF-16LE'2000Q1', _UTF-16LE'2000Q2', _UTF-16LE'2000Q3'), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[d3]) - HiveProject(sr_returned_date_sk=[$0], sr_item_sk=[$1], sr_customer_sk=[$2], sr_ticket_number=[$3], sr_return_quantity=[$4], d_date_sk=[$5], d_quarter_name=[$6]) + HiveProject(sr_returned_date_sk=[$0], sr_item_sk=[$1], sr_customer_sk=[$2], sr_ticket_number=[$3], sr_return_quantity=[$4], d_date_sk=[$5]) HiveJoin(condition=[=($0, $5)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(sr_returned_date_sk=[$0], sr_item_sk=[$2], sr_customer_sk=[$3], sr_ticket_number=[$9], sr_return_quantity=[$10]) HiveFilter(condition=[AND(IS NOT NULL($3), IS NOT NULL($2), IS NOT NULL($9), IS NOT NULL($0))]) HiveTableScan(table=[[default, store_returns]], table:alias=[store_returns]) - HiveProject(d_date_sk=[$0], d_quarter_name=[$15]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(IN($15, _UTF-16LE'2000Q1', _UTF-16LE'2000Q2', _UTF-16LE'2000Q3'), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[d2]) HiveProject(s_store_sk=[$0], s_state=[$24]) diff --git ql/src/test/results/clientpositive/perf/tez/cbo_query18.q.out ql/src/test/results/clientpositive/perf/tez/cbo_query18.q.out index 7e931c5141a..ebeb13b0ee9 100644 --- ql/src/test/results/clientpositive/perf/tez/cbo_query18.q.out +++ ql/src/test/results/clientpositive/perf/tez/cbo_query18.q.out @@ -80,35 +80,34 @@ POSTHOOK: Input: default@item POSTHOOK: Output: hdfs://### HDFS PATH ### CBO PLAN: HiveSortLimit(sort0=[$1], sort1=[$2], sort2=[$3], sort3=[$0], dir0=[ASC], dir1=[ASC], dir2=[ASC], dir3=[ASC], fetch=[100]) - HiveProject($f0=[$0], $f1=[$1], $f2=[$2], $f3=[$3], $f4=[/($4, $5)], $f5=[/($6, $7)], $f6=[/($8, $9)], $f7=[/($10, $11)], $f8=[/($12, $13)], $f9=[/($14, $15)], $f10=[/($16, $17)]) - HiveAggregate(group=[{0, 1, 2, 3}], groups=[[{0, 1, 2, 3}, {0, 1, 2}, {0, 1}, {0}, {}]], agg#0=[sum($4)], agg#1=[count($4)], agg#2=[sum($5)], agg#3=[count($5)], agg#4=[sum($6)], agg#5=[count($6)], agg#6=[sum($7)], agg#7=[count($7)], agg#8=[sum($8)], agg#9=[count($8)], agg#10=[sum($9)], agg#11=[count($9)], agg#12=[sum($10)], agg#13=[count($10)]) - HiveProject($f0=[$11], $f1=[$8], $f2=[$7], $f3=[$6], $f4=[CAST($16):DECIMAL(12, 2)], $f5=[CAST($17):DECIMAL(12, 2)], $f6=[CAST($19):DECIMAL(12, 2)], $f7=[CAST($18):DECIMAL(12, 2)], $f8=[CAST($20):DECIMAL(12, 2)], $f9=[CAST($4):DECIMAL(12, 2)], $f10=[CAST($26):DECIMAL(12, 2)]) - HiveJoin(condition=[=($13, $0)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveJoin(condition=[=($1, $9)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveJoin(condition=[=($2, $5)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(c_customer_sk=[$0], c_current_cdemo_sk=[$2], c_current_addr_sk=[$4], c_birth_month=[$12], c_birth_year=[$13]) - HiveFilter(condition=[AND(IN($12, 9, 5, 12, 4, 1, 10), IS NOT NULL($0), IS NOT NULL($2), IS NOT NULL($4))]) - HiveTableScan(table=[[default, customer]], table:alias=[customer]) - HiveProject(ca_address_sk=[$0], ca_county=[$7], ca_state=[$8], ca_country=[$10]) - HiveFilter(condition=[AND(IN($8, _UTF-16LE'ND', _UTF-16LE'WI', _UTF-16LE'AL', _UTF-16LE'NC', _UTF-16LE'OK', _UTF-16LE'MS', _UTF-16LE'TN'), IS NOT NULL($0))]) - HiveTableScan(table=[[default, customer_address]], table:alias=[customer_address]) - HiveProject(cd_demo_sk=[$0]) + HiveProject($f0=[$3], $f1=[$2], $f2=[$1], $f3=[$0], $f4=[/($4, $5)], $f5=[/($6, $7)], $f6=[/($8, $9)], $f7=[/($10, $11)], $f8=[/($12, $13)], $f9=[/($14, $15)], $f10=[/($16, $17)]) + HiveAggregate(group=[{5, 6, 7, 10}], groups=[[{5, 6, 7, 10}, {6, 7, 10}, {7, 10}, {10}, {}]], agg#0=[sum($15)], agg#1=[count($15)], agg#2=[sum($16)], agg#3=[count($16)], agg#4=[sum($17)], agg#5=[count($17)], agg#6=[sum($18)], agg#7=[count($18)], agg#8=[sum($19)], agg#9=[count($19)], agg#10=[sum($3)], agg#11=[count($3)], agg#12=[sum($22)], agg#13=[count($22)]) + HiveJoin(condition=[=($12, $0)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($1, $8)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($2, $4)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(c_customer_sk=[$0], c_current_cdemo_sk=[$2], c_current_addr_sk=[$4], CAST=[CAST($13):DECIMAL(12, 2)]) + HiveFilter(condition=[AND(IN($12, 9, 5, 12, 4, 1, 10), IS NOT NULL($0), IS NOT NULL($2), IS NOT NULL($4))]) + HiveTableScan(table=[[default, customer]], table:alias=[customer]) + HiveProject(ca_address_sk=[$0], ca_county=[$7], ca_state=[$8], ca_country=[$10]) + HiveFilter(condition=[AND(IN($8, _UTF-16LE'ND', _UTF-16LE'WI', _UTF-16LE'AL', _UTF-16LE'NC', _UTF-16LE'OK', _UTF-16LE'MS', _UTF-16LE'TN'), IS NOT NULL($0))]) + HiveTableScan(table=[[default, customer_address]], table:alias=[customer_address]) + HiveProject(cd_demo_sk=[$0]) + HiveFilter(condition=[IS NOT NULL($0)]) + HiveTableScan(table=[[default, customer_demographics]], table:alias=[cd2]) + HiveProject(i_item_sk=[$0], i_item_id=[$1], cs_sold_date_sk=[$2], cs_bill_customer_sk=[$3], cs_bill_cdemo_sk=[$4], cs_item_sk=[$5], CAST=[$6], CAST5=[$7], CAST6=[$8], CAST7=[$9], CAST8=[$10], d_date_sk=[$11], cd_demo_sk=[$12], CAST0=[$13]) + HiveJoin(condition=[=($5, $0)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(i_item_sk=[$0], i_item_id=[$1]) HiveFilter(condition=[IS NOT NULL($0)]) - HiveTableScan(table=[[default, customer_demographics]], table:alias=[cd2]) - HiveProject(i_item_sk=[$0], i_item_id=[$1], cs_sold_date_sk=[$2], cs_bill_customer_sk=[$3], cs_bill_cdemo_sk=[$4], cs_item_sk=[$5], cs_quantity=[$6], cs_list_price=[$7], cs_sales_price=[$8], cs_coupon_amt=[$9], cs_net_profit=[$10], d_date_sk=[$11], d_year=[$12], cd_demo_sk=[$13], cd_gender=[$14], cd_education_status=[$15], cd_dep_count=[$16]) - HiveJoin(condition=[=($5, $0)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(i_item_sk=[$0], i_item_id=[$1]) - HiveFilter(condition=[IS NOT NULL($0)]) - HiveTableScan(table=[[default, item]], table:alias=[item]) - HiveJoin(condition=[=($2, $11)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveJoin(condition=[=($0, $9)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(cs_sold_date_sk=[$0], cs_bill_customer_sk=[$3], cs_bill_cdemo_sk=[$4], cs_item_sk=[$15], cs_quantity=[$18], cs_list_price=[$20], cs_sales_price=[$21], cs_coupon_amt=[$27], cs_net_profit=[$33]) - HiveFilter(condition=[AND(IS NOT NULL($4), IS NOT NULL($3), IS NOT NULL($0), IS NOT NULL($15))]) - HiveTableScan(table=[[default, catalog_sales]], table:alias=[catalog_sales]) - HiveProject(d_date_sk=[$0], d_year=[CAST(2001):INTEGER]) - HiveFilter(condition=[AND(=($6, 2001), IS NOT NULL($0))]) - HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) - HiveProject(cd_demo_sk=[$0], cd_gender=[CAST(_UTF-16LE'M'):VARCHAR(2147483647) CHARACTER SET "UTF-16LE" COLLATE "ISO-8859-1$en_US$primary"], cd_education_status=[CAST(_UTF-16LE'College'):VARCHAR(2147483647) CHARACTER SET "UTF-16LE" COLLATE "ISO-8859-1$en_US$primary"], cd_dep_count=[$6]) - HiveFilter(condition=[AND(=($1, _UTF-16LE'M'), =($3, _UTF-16LE'College'), IS NOT NULL($0))]) - HiveTableScan(table=[[default, customer_demographics]], table:alias=[cd1]) + HiveTableScan(table=[[default, item]], table:alias=[item]) + HiveJoin(condition=[=($2, $10)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($0, $9)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(cs_sold_date_sk=[$0], cs_bill_customer_sk=[$3], cs_bill_cdemo_sk=[$4], cs_item_sk=[$15], CAST=[CAST($18):DECIMAL(12, 2)], CAST5=[CAST($20):DECIMAL(12, 2)], CAST6=[CAST($27):DECIMAL(12, 2)], CAST7=[CAST($21):DECIMAL(12, 2)], CAST8=[CAST($33):DECIMAL(12, 2)]) + HiveFilter(condition=[AND(IS NOT NULL($4), IS NOT NULL($3), IS NOT NULL($0), IS NOT NULL($15))]) + HiveTableScan(table=[[default, catalog_sales]], table:alias=[catalog_sales]) + HiveProject(d_date_sk=[$0]) + HiveFilter(condition=[AND(=($6, 2001), IS NOT NULL($0))]) + HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) + HiveProject(cd_demo_sk=[$0], CAST=[CAST($6):DECIMAL(12, 2)]) + HiveFilter(condition=[AND(=($1, _UTF-16LE'M'), =($3, _UTF-16LE'College'), IS NOT NULL($0))]) + HiveTableScan(table=[[default, customer_demographics]], table:alias=[cd1]) diff --git ql/src/test/results/clientpositive/perf/tez/cbo_query19.q.out ql/src/test/results/clientpositive/perf/tez/cbo_query19.q.out index c24d76f1c18..be19babca61 100644 --- ql/src/test/results/clientpositive/perf/tez/cbo_query19.q.out +++ ql/src/test/results/clientpositive/perf/tez/cbo_query19.q.out @@ -64,29 +64,29 @@ CBO PLAN: HiveProject(brand_id=[$0], brand=[$1], i_manufact_id=[$2], i_manufact=[$3], ext_price=[$4]) HiveSortLimit(sort0=[$4], sort1=[$5], sort2=[$6], sort3=[$2], sort4=[$3], dir0=[DESC-nulls-last], dir1=[ASC], dir2=[ASC], dir3=[ASC], dir4=[ASC], fetch=[100]) HiveProject(brand_id=[$0], brand=[$1], i_manufact_id=[$2], i_manufact=[$3], ext_price=[$4], (tok_table_or_col i_brand)=[$1], (tok_table_or_col i_brand_id)=[$0]) - HiveAggregate(group=[{13, 14, 15, 16}], agg#0=[sum($8)]) - HiveJoin(condition=[AND(<>(substr($3, 1, 5), substr($19, 1, 5)), =($7, $18))], joinType=[inner], algorithm=[none], cost=[not available]) + HiveAggregate(group=[{11, 12, 13, 14}], agg#0=[sum($8)]) + HiveJoin(condition=[AND(<>($3, $16), =($7, $15))], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($6, $0)], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($1, $2)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(c_customer_sk=[$0], c_current_addr_sk=[$4]) HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($4))]) HiveTableScan(table=[[default, customer]], table:alias=[customer]) - HiveProject(ca_address_sk=[$0], ca_zip=[$9]) + HiveProject(ca_address_sk=[$0], substr=[substr($9, 1, 5)]) HiveFilter(condition=[IS NOT NULL($0)]) HiveTableScan(table=[[default, customer_address]], table:alias=[customer_address]) - HiveProject(ss_sold_date_sk=[$0], ss_item_sk=[$1], ss_customer_sk=[$2], ss_store_sk=[$3], ss_ext_sales_price=[$4], d_date_sk=[$5], d_year=[$6], d_moy=[$7], i_item_sk=[$8], i_brand_id=[$9], i_brand=[$10], i_manufact_id=[$11], i_manufact=[$12], i_manager_id=[$13]) - HiveJoin(condition=[=($1, $8)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(ss_sold_date_sk=[$0], ss_item_sk=[$1], ss_customer_sk=[$2], ss_store_sk=[$3], ss_ext_sales_price=[$4], d_date_sk=[$5], i_item_sk=[$6], i_brand_id=[$7], i_brand=[$8], i_manufact_id=[$9], i_manufact=[$10]) + HiveJoin(condition=[=($1, $6)], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($5, $0)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(ss_sold_date_sk=[$0], ss_item_sk=[$2], ss_customer_sk=[$3], ss_store_sk=[$7], ss_ext_sales_price=[$15]) HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($2), IS NOT NULL($3), IS NOT NULL($7))]) HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) - HiveProject(d_date_sk=[$0], d_year=[CAST(1999):INTEGER], d_moy=[CAST(11):INTEGER]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(=($8, 11), =($6, 1999), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) - HiveProject(i_item_sk=[$0], i_brand_id=[$7], i_brand=[$8], i_manufact_id=[$13], i_manufact=[$14], i_manager_id=[CAST(7):INTEGER]) + HiveProject(i_item_sk=[$0], i_brand_id=[$7], i_brand=[$8], i_manufact_id=[$13], i_manufact=[$14]) HiveFilter(condition=[AND(=($20, 7), IS NOT NULL($0))]) HiveTableScan(table=[[default, item]], table:alias=[item]) - HiveProject(s_store_sk=[$0], s_zip=[$25]) + HiveProject(s_store_sk=[$0], substr=[substr($25, 1, 5)]) HiveFilter(condition=[IS NOT NULL($0)]) HiveTableScan(table=[[default, store]], table:alias=[store]) diff --git ql/src/test/results/clientpositive/perf/tez/cbo_query2.q.out ql/src/test/results/clientpositive/perf/tez/cbo_query2.q.out index cca252eb3b7..7b14ad3358a 100644 --- ql/src/test/results/clientpositive/perf/tez/cbo_query2.q.out +++ ql/src/test/results/clientpositive/perf/tez/cbo_query2.q.out @@ -126,12 +126,12 @@ POSTHOOK: Input: default@web_sales POSTHOOK: Output: hdfs://### HDFS PATH ### CBO PLAN: HiveSortLimit(sort0=[$0], dir0=[ASC]) - HiveProject(d_week_seq1=[$0], _o__c1=[round(/($1, $11), 2)], _o__c2=[round(/($2, $12), 2)], _o__c3=[round(/($3, $13), 2)], _o__c4=[round(/($4, $14), 2)], _o__c5=[round(/($5, $15), 2)], _o__c6=[round(/($6, $16), 2)], _o__c7=[round(/($7, $17), 2)]) - HiveJoin(condition=[=($0, -($10, 53))], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(d_week_seq1=[$0], _o__c1=[round(/($1, $10), 2)], _o__c2=[round(/($2, $11), 2)], _o__c3=[round(/($3, $12), 2)], _o__c4=[round(/($4, $13), 2)], _o__c5=[round(/($5, $14), 2)], _o__c6=[round(/($6, $15), 2)], _o__c7=[round(/($7, $16), 2)]) + HiveJoin(condition=[=($0, -($9, 53))], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($8, $0)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject($f0=[$0], $f1=[$1], $f2=[$2], $f3=[$3], $f4=[$4], $f5=[$5], $f6=[$6], $f7=[$7]) HiveAggregate(group=[{0}], agg#0=[sum($1)], agg#1=[sum($2)], agg#2=[sum($3)], agg#3=[sum($4)], agg#4=[sum($5)], agg#5=[sum($6)], agg#6=[sum($7)]) - HiveProject($f0=[$3], $f1=[CASE(=($4, _UTF-16LE'Sunday'), $1, null)], $f2=[CASE(=($4, _UTF-16LE'Monday'), $1, null)], $f3=[CASE(=($4, _UTF-16LE'Tuesday'), $1, null)], $f4=[CASE(=($4, _UTF-16LE'Wednesday'), $1, null)], $f5=[CASE(=($4, _UTF-16LE'Thursday'), $1, null)], $f6=[CASE(=($4, _UTF-16LE'Friday'), $1, null)], $f7=[CASE(=($4, _UTF-16LE'Saturday'), $1, null)]) + HiveProject($f0=[$3], $f1=[CASE($4, $1, null)], $f2=[CASE($5, $1, null)], $f3=[CASE($6, $1, null)], $f4=[CASE($7, $1, null)], $f5=[CASE($8, $1, null)], $f6=[CASE($9, $1, null)], $f7=[CASE($10, $1, null)]) HiveJoin(condition=[=($2, $0)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(ws_sold_date_sk=[$0], ws_ext_sales_price=[$1]) HiveUnion(all=[true]) @@ -141,17 +141,17 @@ HiveSortLimit(sort0=[$0], dir0=[ASC]) HiveProject(cs_sold_date_sk=[$0], cs_ext_sales_price=[$23]) HiveFilter(condition=[IS NOT NULL($0)]) HiveTableScan(table=[[default, catalog_sales]], table:alias=[catalog_sales]) - HiveProject(d_date_sk=[$0], d_week_seq=[$4], d_day_name=[$14]) + HiveProject(d_date_sk=[$0], d_week_seq=[$4], ==[=($14, _UTF-16LE'Sunday')], =3=[=($14, _UTF-16LE'Monday')], =4=[=($14, _UTF-16LE'Tuesday')], =5=[=($14, _UTF-16LE'Wednesday')], =6=[=($14, _UTF-16LE'Thursday')], =7=[=($14, _UTF-16LE'Friday')], =8=[=($14, _UTF-16LE'Saturday')]) HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($4))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) - HiveProject(d_week_seq=[$4], d_year=[CAST(2001):INTEGER]) + HiveProject(d_week_seq=[$4]) HiveFilter(condition=[AND(=($6, 2001), IS NOT NULL($4))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) HiveProject(d_week_seq2=[$0], sun_sales2=[$1], mon_sales2=[$2], tue_sales2=[$3], wed_sales2=[$4], thu_sales2=[$5], fri_sales2=[$6], sat_sales2=[$7]) HiveJoin(condition=[=($8, $0)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject($f0=[$0], $f1=[$1], $f2=[$2], $f3=[$3], $f4=[$4], $f5=[$5], $f6=[$6], $f7=[$7]) HiveAggregate(group=[{0}], agg#0=[sum($1)], agg#1=[sum($2)], agg#2=[sum($3)], agg#3=[sum($4)], agg#4=[sum($5)], agg#5=[sum($6)], agg#6=[sum($7)]) - HiveProject($f0=[$3], $f1=[CASE(=($4, _UTF-16LE'Sunday'), $1, null)], $f2=[CASE(=($4, _UTF-16LE'Monday'), $1, null)], $f3=[CASE(=($4, _UTF-16LE'Tuesday'), $1, null)], $f4=[CASE(=($4, _UTF-16LE'Wednesday'), $1, null)], $f5=[CASE(=($4, _UTF-16LE'Thursday'), $1, null)], $f6=[CASE(=($4, _UTF-16LE'Friday'), $1, null)], $f7=[CASE(=($4, _UTF-16LE'Saturday'), $1, null)]) + HiveProject($f0=[$3], $f1=[CASE($4, $1, null)], $f2=[CASE($5, $1, null)], $f3=[CASE($6, $1, null)], $f4=[CASE($7, $1, null)], $f5=[CASE($8, $1, null)], $f6=[CASE($9, $1, null)], $f7=[CASE($10, $1, null)]) HiveJoin(condition=[=($2, $0)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(ws_sold_date_sk=[$0], ws_ext_sales_price=[$1]) HiveUnion(all=[true]) @@ -161,10 +161,10 @@ HiveSortLimit(sort0=[$0], dir0=[ASC]) HiveProject(cs_sold_date_sk=[$0], cs_ext_sales_price=[$23]) HiveFilter(condition=[IS NOT NULL($0)]) HiveTableScan(table=[[default, catalog_sales]], table:alias=[catalog_sales]) - HiveProject(d_date_sk=[$0], d_week_seq=[$4], d_day_name=[$14]) + HiveProject(d_date_sk=[$0], d_week_seq=[$4], ==[=($14, _UTF-16LE'Sunday')], =3=[=($14, _UTF-16LE'Monday')], =4=[=($14, _UTF-16LE'Tuesday')], =5=[=($14, _UTF-16LE'Wednesday')], =6=[=($14, _UTF-16LE'Thursday')], =7=[=($14, _UTF-16LE'Friday')], =8=[=($14, _UTF-16LE'Saturday')]) HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($4))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) - HiveProject(d_week_seq=[$4], d_year=[CAST(2002):INTEGER]) + HiveProject(d_week_seq=[$4]) HiveFilter(condition=[AND(=($6, 2002), IS NOT NULL($4))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) diff --git ql/src/test/results/clientpositive/perf/tez/cbo_query20.q.out ql/src/test/results/clientpositive/perf/tez/cbo_query20.q.out index 834c804dd7e..ba354b67387 100644 --- ql/src/test/results/clientpositive/perf/tez/cbo_query20.q.out +++ ql/src/test/results/clientpositive/perf/tez/cbo_query20.q.out @@ -75,7 +75,7 @@ HiveProject(i_item_desc=[$0], i_category=[$1], i_class=[$2], i_current_price=[$3 HiveProject(cs_sold_date_sk=[$0], cs_item_sk=[$15], cs_ext_sales_price=[$23]) HiveFilter(condition=[AND(IS NOT NULL($15), IS NOT NULL($0))]) HiveTableScan(table=[[default, catalog_sales]], table:alias=[catalog_sales]) - HiveProject(d_date_sk=[$0], d_date=[$2]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(BETWEEN(false, CAST($2):TIMESTAMP(9), 2001-01-12 00:00:00, 2001-02-11 00:00:00), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) diff --git ql/src/test/results/clientpositive/perf/tez/cbo_query21.q.out ql/src/test/results/clientpositive/perf/tez/cbo_query21.q.out index a54a085ed0f..3a675034ef6 100644 --- ql/src/test/results/clientpositive/perf/tez/cbo_query21.q.out +++ ql/src/test/results/clientpositive/perf/tez/cbo_query21.q.out @@ -71,20 +71,20 @@ HiveSortLimit(sort0=[$0], sort1=[$1], dir0=[ASC], dir1=[ASC], fetch=[100]) HiveProject($f0=[$0], $f1=[$1], $f2=[$2], $f3=[$3]) HiveFilter(condition=[CASE(>($2, 0), BETWEEN(false, /(CAST($3):DOUBLE, CAST($2):DOUBLE), 6.66667E-1, 1.5E0), null)]) HiveAggregate(group=[{0, 1}], agg#0=[sum($2)], agg#1=[sum($3)]) - HiveProject($f0=[$1], $f1=[$9], $f2=[CASE(<(CAST($7):DATE, 1998-04-08), $5, 0)], $f3=[CASE(>=(CAST($7):DATE, 1998-04-08), $5, 0)]) + HiveProject($f0=[$1], $f1=[$10], $f2=[CASE($7, $5, 0)], $f3=[CASE($8, $5, 0)]) HiveJoin(condition=[=($4, $0)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(w_warehouse_sk=[$0], w_warehouse_name=[$2]) HiveFilter(condition=[IS NOT NULL($0)]) HiveTableScan(table=[[default, warehouse]], table:alias=[warehouse]) - HiveJoin(condition=[=($6, $1)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($7, $1)], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($0, $4)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(inv_date_sk=[$0], inv_item_sk=[$1], inv_warehouse_sk=[$2], inv_quantity_on_hand=[$3]) HiveFilter(condition=[AND(IS NOT NULL($2), IS NOT NULL($1), IS NOT NULL($0))]) HiveTableScan(table=[[default, inventory]], table:alias=[inventory]) - HiveProject(d_date_sk=[$0], d_date=[$2]) + HiveProject(d_date_sk=[$0], <=[<(CAST($2):DATE, 1998-04-08)], >==[>=(CAST($2):DATE, 1998-04-08)]) HiveFilter(condition=[AND(BETWEEN(false, CAST($2):TIMESTAMP(9), 1998-03-09 00:00:00, 1998-05-08 00:00:00), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) - HiveProject(i_item_sk=[$0], i_item_id=[$1], i_current_price=[$5]) + HiveProject(i_item_sk=[$0], i_item_id=[$1]) HiveFilter(condition=[AND(BETWEEN(false, $5, 0.99, 1.49), IS NOT NULL($0))]) HiveTableScan(table=[[default, item]], table:alias=[item]) diff --git ql/src/test/results/clientpositive/perf/tez/cbo_query22.q.out ql/src/test/results/clientpositive/perf/tez/cbo_query22.q.out index c5118ee62fa..7231d6e16dd 100644 --- ql/src/test/results/clientpositive/perf/tez/cbo_query22.q.out +++ ql/src/test/results/clientpositive/perf/tez/cbo_query22.q.out @@ -58,12 +58,12 @@ HiveSortLimit(sort0=[$4], sort1=[$0], sort2=[$1], sort3=[$2], sort4=[$3], dir0=[ HiveProject(i_item_sk=[$0], i_brand=[$8], i_class=[$10], i_category=[$12], i_product_name=[$21]) HiveFilter(condition=[IS NOT NULL($0)]) HiveTableScan(table=[[default, item]], table:alias=[item]) - HiveJoin(condition=[=($2, $6)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($2, $5)], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($0, $4)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(inv_date_sk=[$0], inv_item_sk=[$1], inv_warehouse_sk=[$2], inv_quantity_on_hand=[$3]) HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($1), IS NOT NULL($2))]) HiveTableScan(table=[[default, inventory]], table:alias=[inventory]) - HiveProject(d_date_sk=[$0], d_month_seq=[$3]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(BETWEEN(false, $3, 1212, 1223), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) HiveProject(w_warehouse_sk=[$0]) diff --git ql/src/test/results/clientpositive/perf/tez/cbo_query23.q.out ql/src/test/results/clientpositive/perf/tez/cbo_query23.q.out index ace7cf5b791..b55f2c17ec3 100644 --- ql/src/test/results/clientpositive/perf/tez/cbo_query23.q.out +++ ql/src/test/results/clientpositive/perf/tez/cbo_query23.q.out @@ -1,7 +1,7 @@ -Warning: Shuffle Join MERGEJOIN[593][tables = [$hdt$_1, $hdt$_2]] in Stage 'Reducer 29' is a cross product -Warning: Shuffle Join MERGEJOIN[594][tables = [$hdt$_1, $hdt$_2, $hdt$_0]] in Stage 'Reducer 30' is a cross product -Warning: Shuffle Join MERGEJOIN[596][tables = [$hdt$_1, $hdt$_2]] in Stage 'Reducer 33' is a cross product -Warning: Shuffle Join MERGEJOIN[597][tables = [$hdt$_1, $hdt$_2, $hdt$_0]] in Stage 'Reducer 34' is a cross product +Warning: Shuffle Join MERGEJOIN[583][tables = [$hdt$_1, $hdt$_2]] in Stage 'Reducer 29' is a cross product +Warning: Shuffle Join MERGEJOIN[584][tables = [$hdt$_1, $hdt$_2, $hdt$_0]] in Stage 'Reducer 30' is a cross product +Warning: Shuffle Join MERGEJOIN[586][tables = [$hdt$_1, $hdt$_2]] in Stage 'Reducer 33' is a cross product +Warning: Shuffle Join MERGEJOIN[587][tables = [$hdt$_1, $hdt$_2, $hdt$_0]] in Stage 'Reducer 34' is a cross product PREHOOK: query: explain cbo with frequent_ss_items as (select substr(i_item_desc,1,30) itemdesc,i_item_sk item_sk,d_date solddate,count(*) cnt @@ -128,16 +128,15 @@ HiveSortLimit(fetch=[100]) HiveJoin(condition=[=($3, $0)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject($f0=[$0]) HiveJoin(condition=[>($1, *(0.95, $3))], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject($f0=[$0], $f1=[$1]) - HiveAggregate(group=[{0}], agg#0=[sum($1)]) - HiveProject($f0=[$3], $f1=[*(CAST($1):DECIMAL(10, 0), $2)]) - HiveJoin(condition=[=($0, $3)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(ss_customer_sk=[$3], ss_quantity=[$10], ss_sales_price=[$13]) - HiveFilter(condition=[IS NOT NULL($3)]) - HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) - HiveProject(c_customer_sk=[$0]) - HiveFilter(condition=[IS NOT NULL($0)]) - HiveTableScan(table=[[default, customer]], table:alias=[customer]) + HiveProject(c_customer_sk=[$0], $f1=[$1]) + HiveAggregate(group=[{2}], agg#0=[sum($1)]) + HiveJoin(condition=[=($0, $2)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(ss_customer_sk=[$3], *=[*(CAST($10):DECIMAL(10, 0), $13)]) + HiveFilter(condition=[IS NOT NULL($3)]) + HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) + HiveProject(c_customer_sk=[$0]) + HiveFilter(condition=[IS NOT NULL($0)]) + HiveTableScan(table=[[default, customer]], table:alias=[customer]) HiveJoin(condition=[true], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(cnt=[$0]) HiveFilter(condition=[<=(sq_count_check($0), 1)]) @@ -146,75 +145,71 @@ HiveSortLimit(fetch=[100]) HiveProject HiveProject($f0=[$0]) HiveAggregate(group=[{}], agg#0=[count($0)]) - HiveProject($f0=[$0], $f1=[$1]) - HiveAggregate(group=[{0}], agg#0=[sum($1)]) - HiveProject($f0=[$0], $f1=[*(CAST($3):DECIMAL(10, 0), $4)]) - HiveJoin(condition=[=($2, $0)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(c_customer_sk=[$0]) - HiveFilter(condition=[IS NOT NULL($0)]) - HiveTableScan(table=[[default, customer]], table:alias=[customer]) - HiveJoin(condition=[=($0, $4)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(ss_sold_date_sk=[$0], ss_customer_sk=[$3], ss_quantity=[$10], ss_sales_price=[$13]) - HiveFilter(condition=[AND(IS NOT NULL($3), IS NOT NULL($0))]) - HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) - HiveProject(d_date_sk=[$0], d_year=[$6]) - HiveFilter(condition=[AND(IN($6, 1999, 2000, 2001, 2002), IS NOT NULL($0))]) - HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) + HiveProject(c_customer_sk=[$0], $f1=[$1]) + HiveAggregate(group=[{0}], agg#0=[sum($3)]) + HiveJoin(condition=[=($2, $0)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(c_customer_sk=[$0]) + HiveFilter(condition=[IS NOT NULL($0)]) + HiveTableScan(table=[[default, customer]], table:alias=[customer]) + HiveJoin(condition=[=($0, $3)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(ss_sold_date_sk=[$0], ss_customer_sk=[$3], *=[*(CAST($10):DECIMAL(10, 0), $13)]) + HiveFilter(condition=[AND(IS NOT NULL($3), IS NOT NULL($0))]) + HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) + HiveProject(d_date_sk=[$0]) + HiveFilter(condition=[AND(IN($6, 1999, 2000, 2001, 2002), IS NOT NULL($0))]) + HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) HiveProject($f0=[$0]) HiveAggregate(group=[{}], agg#0=[max($1)]) - HiveProject($f0=[$0], $f1=[$1]) - HiveAggregate(group=[{0}], agg#0=[sum($1)]) - HiveProject($f0=[$0], $f1=[*(CAST($3):DECIMAL(10, 0), $4)]) - HiveJoin(condition=[=($2, $0)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(c_customer_sk=[$0]) - HiveFilter(condition=[IS NOT NULL($0)]) - HiveTableScan(table=[[default, customer]], table:alias=[customer]) - HiveJoin(condition=[=($0, $4)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(ss_sold_date_sk=[$0], ss_customer_sk=[$3], ss_quantity=[$10], ss_sales_price=[$13]) - HiveFilter(condition=[AND(IS NOT NULL($3), IS NOT NULL($0))]) - HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) - HiveProject(d_date_sk=[$0], d_year=[$6]) - HiveFilter(condition=[AND(IN($6, 1999, 2000, 2001, 2002), IS NOT NULL($0))]) - HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) - HiveJoin(condition=[=($3, $0)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject($f1=[$0]) - HiveAggregate(group=[{1}]) - HiveProject($f0=[$0], $f1=[$1], $f2=[$2], $f3=[$3]) - HiveFilter(condition=[>($3, 4)]) - HiveAggregate(group=[{0, 1, 2}], agg#0=[count()]) - HiveProject($f0=[substr($6, 1, 30)], $f1=[$5], $f2=[$3]) - HiveJoin(condition=[=($1, $5)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveJoin(condition=[=($0, $2)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(ss_sold_date_sk=[$0], ss_item_sk=[$2]) - HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($2))]) + HiveProject(c_customer_sk=[$0], $f1=[$1]) + HiveAggregate(group=[{0}], agg#0=[sum($3)]) + HiveJoin(condition=[=($2, $0)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(c_customer_sk=[$0]) + HiveFilter(condition=[IS NOT NULL($0)]) + HiveTableScan(table=[[default, customer]], table:alias=[customer]) + HiveJoin(condition=[=($0, $3)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(ss_sold_date_sk=[$0], ss_customer_sk=[$3], *=[*(CAST($10):DECIMAL(10, 0), $13)]) + HiveFilter(condition=[AND(IS NOT NULL($3), IS NOT NULL($0))]) HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) - HiveProject(d_date_sk=[$0], d_date=[$2], d_year=[$6]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(IN($6, 1999, 2000, 2001, 2002), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) - HiveProject(i_item_sk=[$0], i_item_desc=[$4]) - HiveFilter(condition=[IS NOT NULL($0)]) - HiveTableScan(table=[[default, item]], table:alias=[item]) + HiveJoin(condition=[=($3, $0)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(i_item_sk=[$0]) + HiveAggregate(group=[{1}]) + HiveFilter(condition=[>($3, 4)]) + HiveProject(substr=[$2], i_item_sk=[$1], d_date=[$0], $f3=[$3]) + HiveAggregate(group=[{3, 4, 5}], agg#0=[count()]) + HiveJoin(condition=[=($1, $4)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($0, $2)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(ss_sold_date_sk=[$0], ss_item_sk=[$2]) + HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($2))]) + HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) + HiveProject(d_date_sk=[$0], d_date=[$2]) + HiveFilter(condition=[AND(IN($6, 1999, 2000, 2001, 2002), IS NOT NULL($0))]) + HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) + HiveProject(i_item_sk=[$0], substr=[substr($4, 1, 30)]) + HiveFilter(condition=[IS NOT NULL($0)]) + HiveTableScan(table=[[default, item]], table:alias=[item]) HiveJoin(condition=[=($0, $5)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(cs_sold_date_sk=[$0], cs_bill_customer_sk=[$3], cs_item_sk=[$15], cs_quantity=[$18], cs_list_price=[$20]) HiveFilter(condition=[AND(IS NOT NULL($15), IS NOT NULL($3), IS NOT NULL($0))]) HiveTableScan(table=[[default, catalog_sales]], table:alias=[catalog_sales]) - HiveProject(d_date_sk=[$0], d_year=[CAST(1999):INTEGER], d_moy=[CAST(1):INTEGER]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(=($6, 1999), =($8, 1), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) HiveProject(sales=[*(CAST($5):DECIMAL(10, 0), $6)]) HiveJoin(condition=[=($4, $0)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject($f0=[$0]) HiveJoin(condition=[>($1, *(0.95, $3))], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject($f0=[$0], $f1=[$1]) - HiveAggregate(group=[{0}], agg#0=[sum($1)]) - HiveProject($f0=[$3], $f1=[*(CAST($1):DECIMAL(10, 0), $2)]) - HiveJoin(condition=[=($0, $3)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(ss_customer_sk=[$3], ss_quantity=[$10], ss_sales_price=[$13]) - HiveFilter(condition=[IS NOT NULL($3)]) - HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) - HiveProject(c_customer_sk=[$0]) - HiveFilter(condition=[IS NOT NULL($0)]) - HiveTableScan(table=[[default, customer]], table:alias=[customer]) + HiveProject(c_customer_sk=[$0], $f1=[$1]) + HiveAggregate(group=[{2}], agg#0=[sum($1)]) + HiveJoin(condition=[=($0, $2)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(ss_customer_sk=[$3], *=[*(CAST($10):DECIMAL(10, 0), $13)]) + HiveFilter(condition=[IS NOT NULL($3)]) + HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) + HiveProject(c_customer_sk=[$0]) + HiveFilter(condition=[IS NOT NULL($0)]) + HiveTableScan(table=[[default, customer]], table:alias=[customer]) HiveJoin(condition=[true], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(cnt=[$0]) HiveFilter(condition=[<=(sq_count_check($0), 1)]) @@ -223,59 +218,56 @@ HiveSortLimit(fetch=[100]) HiveProject HiveProject($f0=[$0]) HiveAggregate(group=[{}], agg#0=[count($0)]) - HiveProject($f0=[$0], $f1=[$1]) - HiveAggregate(group=[{0}], agg#0=[sum($1)]) - HiveProject($f0=[$0], $f1=[*(CAST($3):DECIMAL(10, 0), $4)]) - HiveJoin(condition=[=($2, $0)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(c_customer_sk=[$0]) - HiveFilter(condition=[IS NOT NULL($0)]) - HiveTableScan(table=[[default, customer]], table:alias=[customer]) - HiveJoin(condition=[=($0, $4)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(ss_sold_date_sk=[$0], ss_customer_sk=[$3], ss_quantity=[$10], ss_sales_price=[$13]) - HiveFilter(condition=[AND(IS NOT NULL($3), IS NOT NULL($0))]) - HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) - HiveProject(d_date_sk=[$0], d_year=[$6]) - HiveFilter(condition=[AND(IN($6, 1999, 2000, 2001, 2002), IS NOT NULL($0))]) - HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) + HiveProject(c_customer_sk=[$0], $f1=[$1]) + HiveAggregate(group=[{0}], agg#0=[sum($3)]) + HiveJoin(condition=[=($2, $0)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(c_customer_sk=[$0]) + HiveFilter(condition=[IS NOT NULL($0)]) + HiveTableScan(table=[[default, customer]], table:alias=[customer]) + HiveJoin(condition=[=($0, $3)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(ss_sold_date_sk=[$0], ss_customer_sk=[$3], *=[*(CAST($10):DECIMAL(10, 0), $13)]) + HiveFilter(condition=[AND(IS NOT NULL($3), IS NOT NULL($0))]) + HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) + HiveProject(d_date_sk=[$0]) + HiveFilter(condition=[AND(IN($6, 1999, 2000, 2001, 2002), IS NOT NULL($0))]) + HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) HiveProject($f0=[$0]) HiveAggregate(group=[{}], agg#0=[max($1)]) - HiveProject($f0=[$0], $f1=[$1]) - HiveAggregate(group=[{0}], agg#0=[sum($1)]) - HiveProject($f0=[$0], $f1=[*(CAST($3):DECIMAL(10, 0), $4)]) - HiveJoin(condition=[=($2, $0)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(c_customer_sk=[$0]) - HiveFilter(condition=[IS NOT NULL($0)]) - HiveTableScan(table=[[default, customer]], table:alias=[customer]) - HiveJoin(condition=[=($0, $4)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(ss_sold_date_sk=[$0], ss_customer_sk=[$3], ss_quantity=[$10], ss_sales_price=[$13]) - HiveFilter(condition=[AND(IS NOT NULL($3), IS NOT NULL($0))]) - HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) - HiveProject(d_date_sk=[$0], d_year=[$6]) - HiveFilter(condition=[AND(IN($6, 1999, 2000, 2001, 2002), IS NOT NULL($0))]) - HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) - HiveJoin(condition=[=($2, $0)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject($f1=[$0]) - HiveAggregate(group=[{1}]) - HiveProject($f0=[$0], $f1=[$1], $f2=[$2], $f3=[$3]) - HiveFilter(condition=[>($3, 4)]) - HiveAggregate(group=[{0, 1, 2}], agg#0=[count()]) - HiveProject($f0=[substr($6, 1, 30)], $f1=[$5], $f2=[$3]) - HiveJoin(condition=[=($1, $5)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveJoin(condition=[=($0, $2)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(ss_sold_date_sk=[$0], ss_item_sk=[$2]) - HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($2))]) + HiveProject(c_customer_sk=[$0], $f1=[$1]) + HiveAggregate(group=[{0}], agg#0=[sum($3)]) + HiveJoin(condition=[=($2, $0)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(c_customer_sk=[$0]) + HiveFilter(condition=[IS NOT NULL($0)]) + HiveTableScan(table=[[default, customer]], table:alias=[customer]) + HiveJoin(condition=[=($0, $3)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(ss_sold_date_sk=[$0], ss_customer_sk=[$3], *=[*(CAST($10):DECIMAL(10, 0), $13)]) + HiveFilter(condition=[AND(IS NOT NULL($3), IS NOT NULL($0))]) HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) - HiveProject(d_date_sk=[$0], d_date=[$2], d_year=[$6]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(IN($6, 1999, 2000, 2001, 2002), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) - HiveProject(i_item_sk=[$0], i_item_desc=[$4]) - HiveFilter(condition=[IS NOT NULL($0)]) - HiveTableScan(table=[[default, item]], table:alias=[item]) + HiveJoin(condition=[=($2, $0)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(i_item_sk=[$0]) + HiveAggregate(group=[{1}]) + HiveFilter(condition=[>($3, 4)]) + HiveProject(substr=[$2], i_item_sk=[$1], d_date=[$0], $f3=[$3]) + HiveAggregate(group=[{3, 4, 5}], agg#0=[count()]) + HiveJoin(condition=[=($1, $4)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($0, $2)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(ss_sold_date_sk=[$0], ss_item_sk=[$2]) + HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($2))]) + HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) + HiveProject(d_date_sk=[$0], d_date=[$2]) + HiveFilter(condition=[AND(IN($6, 1999, 2000, 2001, 2002), IS NOT NULL($0))]) + HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) + HiveProject(i_item_sk=[$0], substr=[substr($4, 1, 30)]) + HiveFilter(condition=[IS NOT NULL($0)]) + HiveTableScan(table=[[default, item]], table:alias=[item]) HiveJoin(condition=[=($0, $5)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(ws_sold_date_sk=[$0], ws_item_sk=[$3], ws_bill_customer_sk=[$4], ws_quantity=[$18], ws_list_price=[$20]) HiveFilter(condition=[AND(IS NOT NULL($3), IS NOT NULL($4), IS NOT NULL($0))]) HiveTableScan(table=[[default, web_sales]], table:alias=[web_sales]) - HiveProject(d_date_sk=[$0], d_year=[CAST(1999):INTEGER], d_moy=[CAST(1):INTEGER]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(=($6, 1999), =($8, 1), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) diff --git ql/src/test/results/clientpositive/perf/tez/cbo_query24.q.out ql/src/test/results/clientpositive/perf/tez/cbo_query24.q.out index 1d005b86e1b..3add88ad254 100644 --- ql/src/test/results/clientpositive/perf/tez/cbo_query24.q.out +++ ql/src/test/results/clientpositive/perf/tez/cbo_query24.q.out @@ -119,50 +119,50 @@ HiveProject($f0=[$0], $f1=[$1], $f2=[$2], $f3=[$3]) HiveProject(c_last_name=[$1], c_first_name=[$0], s_store_name=[$2], $f3=[$3]) HiveAggregate(group=[{4, 5, 7}], agg#0=[sum($9)]) HiveProject(i_current_price=[$0], i_size=[$1], i_units=[$2], i_manager_id=[$3], c_first_name=[$4], c_last_name=[$5], ca_state=[$6], s_store_name=[$7], s_state=[$8], $f9=[$9]) - HiveAggregate(group=[{8, 9, 11, 12, 15, 16, 19, 23, 25}], agg#0=[sum($6)]) + HiveAggregate(group=[{8, 9, 10, 11, 14, 15, 18, 22, 23}], agg#0=[sum($6)]) HiveJoin(condition=[AND(=($5, $1), =($2, $0))], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(sr_item_sk=[$2], sr_ticket_number=[$9]) HiveFilter(condition=[AND(IS NOT NULL($9), IS NOT NULL($2))]) HiveTableScan(table=[[default, store_returns]], table:alias=[store_returns]) - HiveJoin(condition=[AND(=($1, $11), =($2, $20))], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[AND(=($1, $10), =($2, $19))], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($0, $5)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(ss_item_sk=[$2], ss_customer_sk=[$3], ss_store_sk=[$7], ss_ticket_number=[$9], ss_sales_price=[$13]) HiveFilter(condition=[AND(IS NOT NULL($9), IS NOT NULL($2), IS NOT NULL($7), IS NOT NULL($3))]) HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) - HiveProject(i_item_sk=[$0], i_current_price=[$5], i_size=[$15], i_color=[CAST(_UTF-16LE'orchid'):VARCHAR(2147483647) CHARACTER SET "UTF-16LE" COLLATE "ISO-8859-1$en_US$primary"], i_units=[$18], i_manager_id=[$20]) + HiveProject(i_item_sk=[$0], i_current_price=[$5], i_size=[$15], i_units=[$18], i_manager_id=[$20]) HiveFilter(condition=[AND(=($17, _UTF-16LE'orchid'), IS NOT NULL($0))]) HiveTableScan(table=[[default, item]], table:alias=[item]) - HiveProject(c_customer_sk=[$0], c_current_addr_sk=[$1], c_first_name=[$2], c_last_name=[$3], c_birth_country=[$4], ca_address_sk=[$5], ca_state=[$6], ca_zip=[$7], ca_country=[$8], s_store_sk=[$9], s_store_name=[$10], s_market_id=[$11], s_state=[$12], s_zip=[$13]) - HiveJoin(condition=[AND(=($1, $5), <>($4, UPPER($8)))], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(c_customer_sk=[$0], c_current_addr_sk=[$1], c_first_name=[$2], c_last_name=[$3], c_birth_country=[$4], ca_address_sk=[$5], ca_state=[$6], ca_zip=[$7], UPPER=[$8], s_store_sk=[$9], s_store_name=[$10], s_state=[$11], s_zip=[$12]) + HiveJoin(condition=[AND(=($1, $5), <>($4, $8))], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(c_customer_sk=[$0], c_current_addr_sk=[$4], c_first_name=[$8], c_last_name=[$9], c_birth_country=[$14]) HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($4))]) HiveTableScan(table=[[default, customer]], table:alias=[customer]) - HiveJoin(condition=[=($8, $2)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(ca_address_sk=[$0], ca_state=[$8], ca_zip=[$9], ca_country=[$10]) + HiveJoin(condition=[=($7, $2)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(ca_address_sk=[$0], ca_state=[$8], ca_zip=[$9], UPPER=[UPPER($10)]) HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($9))]) HiveTableScan(table=[[default, customer_address]], table:alias=[customer_address]) - HiveProject(s_store_sk=[$0], s_store_name=[$5], s_market_id=[CAST(7):INTEGER], s_state=[$24], s_zip=[$25]) + HiveProject(s_store_sk=[$0], s_store_name=[$5], s_state=[$24], s_zip=[$25]) HiveFilter(condition=[AND(=($10, 7), IS NOT NULL($0), IS NOT NULL($25))]) HiveTableScan(table=[[default, store]], table:alias=[store]) HiveProject(_o__c0=[*(0.05, /($0, $1))]) HiveAggregate(group=[{}], agg#0=[sum($10)], agg#1=[count($10)]) HiveProject(c_first_name=[$0], c_last_name=[$1], ca_state=[$2], s_store_name=[$3], s_state=[$4], i_current_price=[$5], i_size=[$6], i_color=[$7], i_units=[$8], i_manager_id=[$9], $f10=[$10]) - HiveAggregate(group=[{7, 8, 11, 15, 17, 20, 21, 22, 23, 24}], agg#0=[sum($4)]) - HiveJoin(condition=[AND(=($3, $26), =($0, $25))], joinType=[inner], algorithm=[none], cost=[not available]) - HiveJoin(condition=[=($0, $19)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveAggregate(group=[{7, 8, 11, 15, 16, 19, 20, 21, 22, 23}], agg#0=[sum($4)]) + HiveJoin(condition=[AND(=($3, $25), =($0, $24))], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($0, $18)], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[AND(=($1, $5), =($2, $14))], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(ss_item_sk=[$2], ss_customer_sk=[$3], ss_store_sk=[$7], ss_ticket_number=[$9], ss_sales_price=[$13]) HiveFilter(condition=[AND(IS NOT NULL($9), IS NOT NULL($2), IS NOT NULL($7), IS NOT NULL($3))]) HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) - HiveJoin(condition=[AND(=($1, $5), <>($4, UPPER($8)))], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[AND(=($1, $5), <>($4, $8))], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(c_customer_sk=[$0], c_current_addr_sk=[$4], c_first_name=[$8], c_last_name=[$9], c_birth_country=[$14]) HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($4))]) HiveTableScan(table=[[default, customer]], table:alias=[customer]) - HiveJoin(condition=[=($8, $2)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(ca_address_sk=[$0], ca_state=[$8], ca_zip=[$9], ca_country=[$10]) + HiveJoin(condition=[=($7, $2)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(ca_address_sk=[$0], ca_state=[$8], ca_zip=[$9], UPPER=[UPPER($10)]) HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($9))]) HiveTableScan(table=[[default, customer_address]], table:alias=[customer_address]) - HiveProject(s_store_sk=[$0], s_store_name=[$5], s_market_id=[CAST(7):INTEGER], s_state=[$24], s_zip=[$25]) + HiveProject(s_store_sk=[$0], s_store_name=[$5], s_state=[$24], s_zip=[$25]) HiveFilter(condition=[AND(=($10, 7), IS NOT NULL($0), IS NOT NULL($25))]) HiveTableScan(table=[[default, store]], table:alias=[store]) HiveProject(i_item_sk=[$0], i_current_price=[$5], i_size=[$15], i_color=[$17], i_units=[$18], i_manager_id=[$20]) diff --git ql/src/test/results/clientpositive/perf/tez/cbo_query25.q.out ql/src/test/results/clientpositive/perf/tez/cbo_query25.q.out index 88e0cf025ea..db13a5d30a9 100644 --- ql/src/test/results/clientpositive/perf/tez/cbo_query25.q.out +++ ql/src/test/results/clientpositive/perf/tez/cbo_query25.q.out @@ -109,35 +109,35 @@ POSTHOOK: Output: hdfs://### HDFS PATH ### CBO PLAN: HiveSortLimit(sort0=[$0], sort1=[$1], sort2=[$2], sort3=[$3], dir0=[ASC], dir1=[ASC], dir2=[ASC], dir3=[ASC], fetch=[100]) HiveProject(i_item_id=[$0], i_item_desc=[$1], s_store_id=[$2], s_store_name=[$3], $f4=[$4], $f5=[$5], $f6=[$6]) - HiveAggregate(group=[{1, 2, 28, 29}], agg#0=[sum($8)], agg#1=[sum($23)], agg#2=[sum($15)]) - HiveJoin(condition=[=($27, $6)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveAggregate(group=[{1, 2, 22, 23}], agg#0=[sum($8)], agg#1=[sum($19)], agg#2=[sum($13)]) + HiveJoin(condition=[=($21, $6)], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($0, $4)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(i_item_sk=[$0], i_item_id=[$1], i_item_desc=[$4]) HiveFilter(condition=[IS NOT NULL($0)]) HiveTableScan(table=[[default, item]], table:alias=[item]) - HiveJoin(condition=[AND(AND(=($2, $18), =($1, $17)), =($4, $19))], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[AND(AND(=($2, $14), =($1, $13)), =($4, $15))], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($6, $0)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(ss_sold_date_sk=[$0], ss_item_sk=[$2], ss_customer_sk=[$3], ss_store_sk=[$7], ss_ticket_number=[$9], ss_net_profit=[$22]) HiveFilter(condition=[AND(IS NOT NULL($3), IS NOT NULL($2), IS NOT NULL($9), IS NOT NULL($0), IS NOT NULL($7))]) HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) - HiveProject(d_date_sk=[$0], d_year=[CAST(2000):INTEGER], d_moy=[CAST(4):INTEGER]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(=($8, 4), =($6, 2000), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[d1]) - HiveProject(cs_sold_date_sk=[$0], cs_bill_customer_sk=[$1], cs_item_sk=[$2], cs_net_profit=[$3], d_date_sk=[$4], d_year=[$5], d_moy=[$6], sr_returned_date_sk=[$7], sr_item_sk=[$8], sr_customer_sk=[$9], sr_ticket_number=[$10], sr_net_loss=[$11], d_date_sk0=[$12], d_year0=[$13], d_moy0=[$14]) - HiveJoin(condition=[AND(=($9, $1), =($8, $2))], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(cs_sold_date_sk=[$0], cs_bill_customer_sk=[$1], cs_item_sk=[$2], cs_net_profit=[$3], d_date_sk=[$4], sr_returned_date_sk=[$5], sr_item_sk=[$6], sr_customer_sk=[$7], sr_ticket_number=[$8], sr_net_loss=[$9], d_date_sk0=[$10]) + HiveJoin(condition=[AND(=($7, $1), =($6, $2))], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($0, $4)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(cs_sold_date_sk=[$0], cs_bill_customer_sk=[$3], cs_item_sk=[$15], cs_net_profit=[$33]) HiveFilter(condition=[AND(IS NOT NULL($3), IS NOT NULL($15), IS NOT NULL($0))]) HiveTableScan(table=[[default, catalog_sales]], table:alias=[catalog_sales]) - HiveProject(d_date_sk=[$0], d_year=[CAST(2000):INTEGER], d_moy=[$8]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(BETWEEN(false, $8, 4, 10), =($6, 2000), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[d3]) - HiveProject(sr_returned_date_sk=[$0], sr_item_sk=[$1], sr_customer_sk=[$2], sr_ticket_number=[$3], sr_net_loss=[$4], d_date_sk=[$5], d_year=[$6], d_moy=[$7]) + HiveProject(sr_returned_date_sk=[$0], sr_item_sk=[$1], sr_customer_sk=[$2], sr_ticket_number=[$3], sr_net_loss=[$4], d_date_sk=[$5]) HiveJoin(condition=[=($0, $5)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(sr_returned_date_sk=[$0], sr_item_sk=[$2], sr_customer_sk=[$3], sr_ticket_number=[$9], sr_net_loss=[$19]) HiveFilter(condition=[AND(IS NOT NULL($3), IS NOT NULL($2), IS NOT NULL($9), IS NOT NULL($0))]) HiveTableScan(table=[[default, store_returns]], table:alias=[store_returns]) - HiveProject(d_date_sk=[$0], d_year=[CAST(2000):INTEGER], d_moy=[$8]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(BETWEEN(false, $8, 4, 10), =($6, 2000), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[d2]) HiveProject(s_store_sk=[$0], s_store_id=[$1], s_store_name=[$5]) diff --git ql/src/test/results/clientpositive/perf/tez/cbo_query26.q.out ql/src/test/results/clientpositive/perf/tez/cbo_query26.q.out index 8b36aed6173..9f51402caff 100644 --- ql/src/test/results/clientpositive/perf/tez/cbo_query26.q.out +++ ql/src/test/results/clientpositive/perf/tez/cbo_query26.q.out @@ -58,19 +58,19 @@ HiveSortLimit(sort0=[$0], dir0=[ASC], fetch=[100]) HiveProject(i_item_sk=[$0], i_item_id=[$1]) HiveFilter(condition=[IS NOT NULL($0)]) HiveTableScan(table=[[default, item]], table:alias=[item]) - HiveJoin(condition=[=($3, $14)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveJoin(condition=[=($0, $12)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($3, $10)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($0, $9)], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($1, $8)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(cs_sold_date_sk=[$0], cs_bill_cdemo_sk=[$4], cs_item_sk=[$15], cs_promo_sk=[$16], cs_quantity=[$18], cs_list_price=[$20], cs_sales_price=[$21], cs_coupon_amt=[$27]) HiveFilter(condition=[AND(IS NOT NULL($4), IS NOT NULL($0), IS NOT NULL($15), IS NOT NULL($16))]) HiveTableScan(table=[[default, catalog_sales]], table:alias=[catalog_sales]) - HiveProject(cd_demo_sk=[$0], cd_gender=[CAST(_UTF-16LE'F'):VARCHAR(2147483647) CHARACTER SET "UTF-16LE" COLLATE "ISO-8859-1$en_US$primary"], cd_marital_status=[CAST(_UTF-16LE'W'):VARCHAR(2147483647) CHARACTER SET "UTF-16LE" COLLATE "ISO-8859-1$en_US$primary"], cd_education_status=[CAST(_UTF-16LE'Primary'):VARCHAR(2147483647) CHARACTER SET "UTF-16LE" COLLATE "ISO-8859-1$en_US$primary"]) + HiveProject(cd_demo_sk=[$0]) HiveFilter(condition=[AND(=($1, _UTF-16LE'F'), =($2, _UTF-16LE'W'), =($3, _UTF-16LE'Primary'), IS NOT NULL($0))]) HiveTableScan(table=[[default, customer_demographics]], table:alias=[customer_demographics]) - HiveProject(d_date_sk=[$0], d_year=[CAST(1998):INTEGER]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(=($6, 1998), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) - HiveProject(p_promo_sk=[$0], p_channel_email=[$9], p_channel_event=[$14]) + HiveProject(p_promo_sk=[$0]) HiveFilter(condition=[AND(OR(=($9, _UTF-16LE'N'), =($14, _UTF-16LE'N')), IS NOT NULL($0))]) HiveTableScan(table=[[default, promotion]], table:alias=[promotion]) diff --git ql/src/test/results/clientpositive/perf/tez/cbo_query27.q.out ql/src/test/results/clientpositive/perf/tez/cbo_query27.q.out index 9a6718af9bc..e072692b33f 100644 --- ql/src/test/results/clientpositive/perf/tez/cbo_query27.q.out +++ ql/src/test/results/clientpositive/perf/tez/cbo_query27.q.out @@ -58,21 +58,21 @@ CBO PLAN: HiveSortLimit(sort0=[$0], sort1=[$1], dir0=[ASC], dir1=[ASC], fetch=[100]) HiveProject(i_item_id=[$0], s_state=[$1], g_state=[grouping($10, 0)], agg1=[/(CAST($2):DOUBLE, $3)], agg2=[/($4, $5)], agg3=[/($6, $7)], agg4=[/($8, $9)]) HiveAggregate(group=[{0, 1}], groups=[[{0, 1}, {0}, {}]], agg#0=[sum($2)], agg#1=[count($2)], agg#2=[sum($3)], agg#3=[count($3)], agg#4=[sum($4)], agg#5=[count($4)], agg#6=[sum($5)], agg#7=[count($5)], GROUPING__ID=[GROUPING__ID()]) - HiveProject($f0=[$1], $f1=[$17], $f2=[$6], $f3=[$7], $f4=[$9], $f5=[$8]) + HiveProject($f0=[$1], $f1=[$13], $f2=[$6], $f3=[$7], $f4=[$9], $f5=[$8]) HiveJoin(condition=[=($3, $0)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(i_item_sk=[$0], i_item_id=[$1]) HiveFilter(condition=[IS NOT NULL($0)]) HiveTableScan(table=[[default, item]], table:alias=[item]) - HiveJoin(condition=[=($3, $14)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveJoin(condition=[=($0, $12)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($3, $10)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($0, $9)], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($2, $8)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(ss_sold_date_sk=[$0], ss_item_sk=[$2], ss_cdemo_sk=[$4], ss_store_sk=[$7], ss_quantity=[$10], ss_list_price=[$12], ss_sales_price=[$13], ss_coupon_amt=[$19]) HiveFilter(condition=[AND(IS NOT NULL($4), IS NOT NULL($0), IS NOT NULL($7), IS NOT NULL($2))]) HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) - HiveProject(cd_demo_sk=[$0], cd_gender=[CAST(_UTF-16LE'M'):VARCHAR(2147483647) CHARACTER SET "UTF-16LE" COLLATE "ISO-8859-1$en_US$primary"], cd_marital_status=[CAST(_UTF-16LE'U'):VARCHAR(2147483647) CHARACTER SET "UTF-16LE" COLLATE "ISO-8859-1$en_US$primary"], cd_education_status=[CAST(_UTF-16LE'2 yr Degree'):VARCHAR(2147483647) CHARACTER SET "UTF-16LE" COLLATE "ISO-8859-1$en_US$primary"]) + HiveProject(cd_demo_sk=[$0]) HiveFilter(condition=[AND(=($1, _UTF-16LE'M'), =($2, _UTF-16LE'U'), =($3, _UTF-16LE'2 yr Degree'), IS NOT NULL($0))]) HiveTableScan(table=[[default, customer_demographics]], table:alias=[customer_demographics]) - HiveProject(d_date_sk=[$0], d_year=[CAST(2001):INTEGER]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(=($6, 2001), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) HiveProject(s_store_sk=[$0], s_state=[$24]) diff --git ql/src/test/results/clientpositive/perf/tez/cbo_query29.q.out ql/src/test/results/clientpositive/perf/tez/cbo_query29.q.out index 9f9ffe50cd1..82a914b616e 100644 --- ql/src/test/results/clientpositive/perf/tez/cbo_query29.q.out +++ ql/src/test/results/clientpositive/perf/tez/cbo_query29.q.out @@ -107,35 +107,35 @@ POSTHOOK: Output: hdfs://### HDFS PATH ### CBO PLAN: HiveSortLimit(sort0=[$0], sort1=[$1], sort2=[$2], sort3=[$3], dir0=[ASC], dir1=[ASC], dir2=[ASC], dir3=[ASC], fetch=[100]) HiveProject(i_item_id=[$0], i_item_desc=[$1], s_store_id=[$2], s_store_name=[$3], $f4=[$4], $f5=[$5], $f6=[$6]) - HiveAggregate(group=[{7, 8, 27, 28}], agg#0=[sum($14)], agg#1=[sum($22)], agg#2=[sum($3)]) - HiveJoin(condition=[AND(=($20, $1), =($19, $2))], joinType=[inner], algorithm=[none], cost=[not available]) + HiveAggregate(group=[{6, 7, 22, 23}], agg#0=[sum($13)], agg#1=[sum($19)], agg#2=[sum($3)]) + HiveJoin(condition=[AND(=($17, $1), =($16, $2))], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($0, $4)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(cs_sold_date_sk=[$0], cs_bill_customer_sk=[$3], cs_item_sk=[$15], cs_quantity=[$18]) HiveFilter(condition=[AND(IS NOT NULL($3), IS NOT NULL($15), IS NOT NULL($0))]) HiveTableScan(table=[[default, catalog_sales]], table:alias=[catalog_sales]) - HiveProject(d_date_sk=[$0], d_year=[$6]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(IN($6, 1999, 2000, 2001), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[d3]) - HiveProject(i_item_sk=[$0], i_item_id=[$1], i_item_desc=[$2], ss_sold_date_sk=[$3], ss_item_sk=[$4], ss_customer_sk=[$5], ss_store_sk=[$6], ss_ticket_number=[$7], ss_quantity=[$8], d_date_sk=[$9], d_year=[$10], d_moy=[$11], sr_returned_date_sk=[$12], sr_item_sk=[$13], sr_customer_sk=[$14], sr_ticket_number=[$15], sr_return_quantity=[$16], d_date_sk0=[$17], d_year0=[$18], d_moy0=[$19], s_store_sk=[$20], s_store_id=[$21], s_store_name=[$22]) - HiveJoin(condition=[=($20, $6)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(i_item_sk=[$0], i_item_id=[$1], i_item_desc=[$2], ss_sold_date_sk=[$3], ss_item_sk=[$4], ss_customer_sk=[$5], ss_store_sk=[$6], ss_ticket_number=[$7], ss_quantity=[$8], d_date_sk=[$9], sr_returned_date_sk=[$10], sr_item_sk=[$11], sr_customer_sk=[$12], sr_ticket_number=[$13], sr_return_quantity=[$14], d_date_sk0=[$15], s_store_sk=[$16], s_store_id=[$17], s_store_name=[$18]) + HiveJoin(condition=[=($16, $6)], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($0, $4)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(i_item_sk=[$0], i_item_id=[$1], i_item_desc=[$4]) HiveFilter(condition=[IS NOT NULL($0)]) HiveTableScan(table=[[default, item]], table:alias=[item]) - HiveJoin(condition=[AND(AND(=($2, $11), =($1, $10)), =($4, $12))], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[AND(AND(=($2, $9), =($1, $8)), =($4, $10))], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($6, $0)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(ss_sold_date_sk=[$0], ss_item_sk=[$2], ss_customer_sk=[$3], ss_store_sk=[$7], ss_ticket_number=[$9], ss_quantity=[$10]) HiveFilter(condition=[AND(IS NOT NULL($3), IS NOT NULL($2), IS NOT NULL($9), IS NOT NULL($0), IS NOT NULL($7))]) HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) - HiveProject(d_date_sk=[$0], d_year=[CAST(1999):INTEGER], d_moy=[CAST(4):INTEGER]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(=($8, 4), =($6, 1999), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[d1]) - HiveProject(sr_returned_date_sk=[$0], sr_item_sk=[$1], sr_customer_sk=[$2], sr_ticket_number=[$3], sr_return_quantity=[$4], d_date_sk=[$5], d_year=[$6], d_moy=[$7]) + HiveProject(sr_returned_date_sk=[$0], sr_item_sk=[$1], sr_customer_sk=[$2], sr_ticket_number=[$3], sr_return_quantity=[$4], d_date_sk=[$5]) HiveJoin(condition=[=($0, $5)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(sr_returned_date_sk=[$0], sr_item_sk=[$2], sr_customer_sk=[$3], sr_ticket_number=[$9], sr_return_quantity=[$10]) HiveFilter(condition=[AND(IS NOT NULL($3), IS NOT NULL($2), IS NOT NULL($9), IS NOT NULL($0))]) HiveTableScan(table=[[default, store_returns]], table:alias=[store_returns]) - HiveProject(d_date_sk=[$0], d_year=[CAST(1999):INTEGER], d_moy=[$8]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(BETWEEN(false, $8, 4, 7), =($6, 1999), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[d2]) HiveProject(s_store_sk=[$0], s_store_id=[$1], s_store_name=[$5]) diff --git ql/src/test/results/clientpositive/perf/tez/cbo_query3.q.out ql/src/test/results/clientpositive/perf/tez/cbo_query3.q.out index 09c9bb78fe0..b3688f38fe1 100644 --- ql/src/test/results/clientpositive/perf/tez/cbo_query3.q.out +++ ql/src/test/results/clientpositive/perf/tez/cbo_query3.q.out @@ -49,16 +49,16 @@ POSTHOOK: Output: hdfs://### HDFS PATH ### CBO PLAN: HiveSortLimit(sort0=[$0], sort1=[$3], sort2=[$1], dir0=[ASC], dir1=[DESC-nulls-last], dir2=[ASC], fetch=[100]) HiveProject(d_year=[$2], i_brand_id=[$0], i_brand=[$1], $f3=[$3]) - HiveAggregate(group=[{4, 5, 8}], agg#0=[sum($2)]) - HiveJoin(condition=[=($7, $0)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveAggregate(group=[{4, 5, 7}], agg#0=[sum($2)]) + HiveJoin(condition=[=($6, $0)], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($1, $3)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(ss_sold_date_sk=[$0], ss_item_sk=[$2], ss_ext_sales_price=[$15]) HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($2))]) HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) - HiveProject(i_item_sk=[$0], i_brand_id=[$7], i_brand=[$8], i_manufact_id=[CAST(436):INTEGER]) + HiveProject(i_item_sk=[$0], i_brand_id=[$7], i_brand=[$8]) HiveFilter(condition=[AND(=($13, 436), IS NOT NULL($0))]) HiveTableScan(table=[[default, item]], table:alias=[item]) - HiveProject(d_date_sk=[$0], d_year=[$6], d_moy=[CAST(12):INTEGER]) + HiveProject(d_date_sk=[$0], d_year=[$6]) HiveFilter(condition=[AND(=($8, 12), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[dt]) diff --git ql/src/test/results/clientpositive/perf/tez/cbo_query30.q.out ql/src/test/results/clientpositive/perf/tez/cbo_query30.q.out index 067b2bc8a32..02e26a7c101 100644 --- ql/src/test/results/clientpositive/perf/tez/cbo_query30.q.out +++ ql/src/test/results/clientpositive/perf/tez/cbo_query30.q.out @@ -70,13 +70,13 @@ POSTHOOK: Input: default@web_returns POSTHOOK: Output: hdfs://### HDFS PATH ### CBO PLAN: HiveSortLimit(sort0=[$0], sort1=[$1], sort2=[$2], sort3=[$3], sort4=[$4], sort5=[$5], sort6=[$6], sort7=[$7], sort8=[$8], sort9=[$9], sort10=[$10], sort11=[$11], sort12=[$12], dir0=[ASC], dir1=[ASC], dir2=[ASC], dir3=[ASC], dir4=[ASC], dir5=[ASC], dir6=[ASC], dir7=[ASC], dir8=[ASC], dir9=[ASC], dir10=[ASC], dir11=[ASC], dir12=[ASC], fetch=[100]) - HiveProject(c_customer_id=[$1], c_salutation=[$3], c_first_name=[$4], c_last_name=[$5], c_preferred_cust_flag=[$6], c_birth_day=[$7], c_birth_month=[$8], c_birth_year=[$9], c_birth_country=[$10], c_login=[$11], c_email_address=[$12], c_last_review_date=[$13], ctr_total_return=[$18]) - HiveJoin(condition=[=($16, $0)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(c_customer_id=[$1], c_salutation=[$3], c_first_name=[$4], c_last_name=[$5], c_preferred_cust_flag=[$6], c_birth_day=[$7], c_birth_month=[$8], c_birth_year=[$9], c_birth_country=[$10], c_login=[$11], c_email_address=[$12], c_last_review_date=[$13], ctr_total_return=[$17]) + HiveJoin(condition=[=($15, $0)], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($14, $2)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(c_customer_sk=[$0], c_customer_id=[$1], c_current_addr_sk=[$4], c_salutation=[$7], c_first_name=[$8], c_last_name=[$9], c_preferred_cust_flag=[$10], c_birth_day=[$11], c_birth_month=[$12], c_birth_year=[$13], c_birth_country=[$14], c_login=[$15], c_email_address=[$16], c_last_review_date=[$17]) HiveFilter(condition=[AND(IS NOT NULL($4), IS NOT NULL($0))]) HiveTableScan(table=[[default, customer]], table:alias=[customer]) - HiveProject(ca_address_sk=[$0], ca_state=[CAST(_UTF-16LE'IL'):VARCHAR(2147483647) CHARACTER SET "UTF-16LE" COLLATE "ISO-8859-1$en_US$primary"]) + HiveProject(ca_address_sk=[$0]) HiveFilter(condition=[AND(=($8, _UTF-16LE'IL'), IS NOT NULL($0))]) HiveTableScan(table=[[default, customer_address]], table:alias=[customer_address]) HiveProject(wr_returning_customer_sk=[$0], ca_state=[$1], $f2=[$2], _o__c0=[$3], ctr_state=[$4]) @@ -91,7 +91,7 @@ HiveSortLimit(sort0=[$0], sort1=[$1], sort2=[$2], sort3=[$3], sort4=[$4], sort5= HiveProject(wr_returned_date_sk=[$0], wr_returning_customer_sk=[$7], wr_returning_addr_sk=[$10], wr_return_amt=[$15]) HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($10), IS NOT NULL($7))]) HiveTableScan(table=[[default, web_returns]], table:alias=[web_returns]) - HiveProject(d_date_sk=[$0], d_year=[CAST(2002):INTEGER]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(=($6, 2002), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) HiveProject(_o__c0=[*(/($1, $2), 1.2)], ctr_state=[$0]) @@ -106,7 +106,7 @@ HiveSortLimit(sort0=[$0], sort1=[$1], sort2=[$2], sort3=[$3], sort4=[$4], sort5= HiveProject(wr_returned_date_sk=[$0], wr_returning_customer_sk=[$7], wr_returning_addr_sk=[$10], wr_return_amt=[$15]) HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($10))]) HiveTableScan(table=[[default, web_returns]], table:alias=[web_returns]) - HiveProject(d_date_sk=[$0], d_year=[CAST(2002):INTEGER]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(=($6, 2002), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) diff --git ql/src/test/results/clientpositive/perf/tez/cbo_query31.q.out ql/src/test/results/clientpositive/perf/tez/cbo_query31.q.out index 5143053673d..8907b8d6cd5 100644 --- ql/src/test/results/clientpositive/perf/tez/cbo_query31.q.out +++ ql/src/test/results/clientpositive/perf/tez/cbo_query31.q.out @@ -111,22 +111,22 @@ POSTHOOK: Input: default@store_sales POSTHOOK: Input: default@web_sales POSTHOOK: Output: hdfs://### HDFS PATH ### CBO PLAN: -HiveProject(ca_county=[$0], d_year=[CAST(2000):INTEGER], web_q1_q2_increase=[/($9, $7)], store_q1_q2_increase=[/($1, $3)], web_q2_q3_increase=[/($11, $9)], store_q2_q3_increase=[/($5, $1)]) - HiveJoin(condition=[AND(AND(=($0, $6), CASE(>($3, 0), CASE(>($7, 0), >(/($9, $7), /($1, $3)), >(null, /($1, $3))), CASE(>($7, 0), >(/($9, $7), null), null))), CASE(>($1, 0), CASE(>($9, 0), >(/($11, $9), /($5, $1)), >(null, /($5, $1))), CASE(>($9, 0), >(/($11, $9), null), null)))], joinType=[inner], algorithm=[none], cost=[not available]) - HiveJoin(condition=[=($0, $4)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveJoin(condition=[=($2, $0)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(ca_county=[$0], $f1=[$1]) +HiveProject(ca_county=[$8], d_year=[CAST(2000):INTEGER], web_q1_q2_increase=[/($6, $1)], store_q1_q2_increase=[/($9, $11)], web_q2_q3_increase=[/($4, $6)], store_q2_q3_increase=[/($13, $9)]) + HiveJoin(condition=[AND(AND(=($8, $0), CASE(>($11, 0), CASE($2, >(/($6, $1), /($9, $11)), >(null, /($9, $11))), CASE($2, >(/($6, $1), null), null))), CASE(>($9, 0), CASE($7, >(/($4, $6), /($13, $9)), >(null, /($13, $9))), CASE($7, >(/($4, $6), null), null)))], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($0, $5)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($0, $3)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject($f0=[$0], $f3=[$1], >=[>($1, 0)]) HiveAggregate(group=[{1}], agg#0=[sum($4)]) HiveJoin(condition=[=($3, $0)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(ca_address_sk=[$0], ca_county=[$7]) HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($7))]) HiveTableScan(table=[[default, customer_address]], table:alias=[customer_address]) HiveJoin(condition=[=($0, $3)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(ss_sold_date_sk=[$0], ss_addr_sk=[$6], ss_ext_sales_price=[$15]) - HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($6))]) - HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) - HiveProject(d_date_sk=[$0], d_year=[CAST(2000):INTEGER], d_qoy=[CAST(2):INTEGER]) - HiveFilter(condition=[AND(=($10, 2), =($6, 2000), IS NOT NULL($0))]) + HiveProject(ws_sold_date_sk=[$0], ws_bill_addr_sk=[$7], ws_ext_sales_price=[$23]) + HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($7))]) + HiveTableScan(table=[[default, web_sales]], table:alias=[web_sales]) + HiveProject(d_date_sk=[$0]) + HiveFilter(condition=[AND(=($10, 1), =($6, 2000), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) HiveProject(ca_county=[$0], $f1=[$1]) HiveAggregate(group=[{1}], agg#0=[sum($4)]) @@ -135,28 +135,28 @@ HiveProject(ca_county=[$0], d_year=[CAST(2000):INTEGER], web_q1_q2_increase=[/($ HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($7))]) HiveTableScan(table=[[default, customer_address]], table:alias=[customer_address]) HiveJoin(condition=[=($0, $3)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(ss_sold_date_sk=[$0], ss_addr_sk=[$6], ss_ext_sales_price=[$15]) - HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($6))]) - HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) - HiveProject(d_date_sk=[$0], d_year=[CAST(2000):INTEGER], d_qoy=[CAST(1):INTEGER]) - HiveFilter(condition=[AND(=($10, 1), =($6, 2000), IS NOT NULL($0))]) + HiveProject(ws_sold_date_sk=[$0], ws_bill_addr_sk=[$7], ws_ext_sales_price=[$23]) + HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($7))]) + HiveTableScan(table=[[default, web_sales]], table:alias=[web_sales]) + HiveProject(d_date_sk=[$0]) + HiveFilter(condition=[AND(=($10, 3), =($6, 2000), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) - HiveProject(ca_county=[$0], $f1=[$1]) + HiveProject($f0=[$0], $f3=[$1], >=[>($1, 0)]) HiveAggregate(group=[{1}], agg#0=[sum($4)]) HiveJoin(condition=[=($3, $0)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(ca_address_sk=[$0], ca_county=[$7]) HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($7))]) HiveTableScan(table=[[default, customer_address]], table:alias=[customer_address]) HiveJoin(condition=[=($0, $3)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(ss_sold_date_sk=[$0], ss_addr_sk=[$6], ss_ext_sales_price=[$15]) - HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($6))]) - HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) - HiveProject(d_date_sk=[$0], d_year=[CAST(2000):INTEGER], d_qoy=[CAST(3):INTEGER]) - HiveFilter(condition=[AND(=($10, 3), =($6, 2000), IS NOT NULL($0))]) + HiveProject(ws_sold_date_sk=[$0], ws_bill_addr_sk=[$7], ws_ext_sales_price=[$23]) + HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($7))]) + HiveTableScan(table=[[default, web_sales]], table:alias=[web_sales]) + HiveProject(d_date_sk=[$0]) + HiveFilter(condition=[AND(=($10, 2), =($6, 2000), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) HiveProject(ca_county=[$0], $f1=[$1], ca_county0=[$2], $f10=[$3], ca_county1=[$4], $f11=[$5]) HiveJoin(condition=[=($0, $4)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveJoin(condition=[=($0, $2)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($2, $0)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(ca_county=[$0], $f1=[$1]) HiveAggregate(group=[{1}], agg#0=[sum($4)]) HiveJoin(condition=[=($3, $0)], joinType=[inner], algorithm=[none], cost=[not available]) @@ -164,11 +164,11 @@ HiveProject(ca_county=[$0], d_year=[CAST(2000):INTEGER], web_q1_q2_increase=[/($ HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($7))]) HiveTableScan(table=[[default, customer_address]], table:alias=[customer_address]) HiveJoin(condition=[=($0, $3)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(ws_sold_date_sk=[$0], ws_bill_addr_sk=[$7], ws_ext_sales_price=[$23]) - HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($7))]) - HiveTableScan(table=[[default, web_sales]], table:alias=[web_sales]) - HiveProject(d_date_sk=[$0], d_year=[CAST(2000):INTEGER], d_qoy=[CAST(1):INTEGER]) - HiveFilter(condition=[AND(=($10, 1), =($6, 2000), IS NOT NULL($0))]) + HiveProject(ss_sold_date_sk=[$0], ss_addr_sk=[$6], ss_ext_sales_price=[$15]) + HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($6))]) + HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) + HiveProject(d_date_sk=[$0]) + HiveFilter(condition=[AND(=($10, 2), =($6, 2000), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) HiveProject(ca_county=[$0], $f1=[$1]) HiveAggregate(group=[{1}], agg#0=[sum($4)]) @@ -177,11 +177,11 @@ HiveProject(ca_county=[$0], d_year=[CAST(2000):INTEGER], web_q1_q2_increase=[/($ HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($7))]) HiveTableScan(table=[[default, customer_address]], table:alias=[customer_address]) HiveJoin(condition=[=($0, $3)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(ws_sold_date_sk=[$0], ws_bill_addr_sk=[$7], ws_ext_sales_price=[$23]) - HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($7))]) - HiveTableScan(table=[[default, web_sales]], table:alias=[web_sales]) - HiveProject(d_date_sk=[$0], d_year=[CAST(2000):INTEGER], d_qoy=[CAST(2):INTEGER]) - HiveFilter(condition=[AND(=($10, 2), =($6, 2000), IS NOT NULL($0))]) + HiveProject(ss_sold_date_sk=[$0], ss_addr_sk=[$6], ss_ext_sales_price=[$15]) + HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($6))]) + HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) + HiveProject(d_date_sk=[$0]) + HiveFilter(condition=[AND(=($10, 1), =($6, 2000), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) HiveProject(ca_county=[$0], $f1=[$1]) HiveAggregate(group=[{1}], agg#0=[sum($4)]) @@ -190,10 +190,10 @@ HiveProject(ca_county=[$0], d_year=[CAST(2000):INTEGER], web_q1_q2_increase=[/($ HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($7))]) HiveTableScan(table=[[default, customer_address]], table:alias=[customer_address]) HiveJoin(condition=[=($0, $3)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(ws_sold_date_sk=[$0], ws_bill_addr_sk=[$7], ws_ext_sales_price=[$23]) - HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($7))]) - HiveTableScan(table=[[default, web_sales]], table:alias=[web_sales]) - HiveProject(d_date_sk=[$0], d_year=[CAST(2000):INTEGER], d_qoy=[CAST(3):INTEGER]) + HiveProject(ss_sold_date_sk=[$0], ss_addr_sk=[$6], ss_ext_sales_price=[$15]) + HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($6))]) + HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(=($10, 3), =($6, 2000), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) diff --git ql/src/test/results/clientpositive/perf/tez/cbo_query32.q.out ql/src/test/results/clientpositive/perf/tez/cbo_query32.q.out index 981d478d483..837a743154f 100644 --- ql/src/test/results/clientpositive/perf/tez/cbo_query32.q.out +++ ql/src/test/results/clientpositive/perf/tez/cbo_query32.q.out @@ -64,26 +64,26 @@ CBO PLAN: HiveSortLimit(fetch=[100]) HiveProject($f0=[$0]) HiveAggregate(group=[{}], agg#0=[sum($2)]) - HiveJoin(condition=[AND(>($2, CAST(*(1.3, $6)):DECIMAL(14, 7)), =($7, $1))], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[AND(>($2, $5), =($6, $1))], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($3, $0)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(cs_sold_date_sk=[$0], cs_item_sk=[$15], cs_ext_discount_amt=[$22]) HiveFilter(condition=[AND(IS NOT NULL($15), IS NOT NULL($0))]) HiveTableScan(table=[[default, catalog_sales]], table:alias=[catalog_sales]) - HiveProject(d_date_sk=[$0], d_date=[$2]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(BETWEEN(false, CAST($2):TIMESTAMP(9), 1998-03-18 00:00:00, 1998-06-16 00:00:00), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) - HiveProject(cs_item_sk=[$0], $f1=[$1], i_item_sk=[$2], i_manufact_id=[$3]) + HiveProject(cs_item_sk=[$0], CAST=[$1], i_item_sk=[$2]) HiveJoin(condition=[=($0, $2)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(cs_item_sk=[$0], $f1=[/($1, $2)]) + HiveProject(cs_item_sk=[$0], CAST=[CAST(*(1.3, /($1, $2))):DECIMAL(14, 7)]) HiveAggregate(group=[{1}], agg#0=[sum($2)], agg#1=[count($2)]) HiveJoin(condition=[=($3, $0)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(cs_sold_date_sk=[$0], cs_item_sk=[$15], cs_ext_discount_amt=[$22]) HiveFilter(condition=[AND(IS NOT NULL($15), IS NOT NULL($0))]) HiveTableScan(table=[[default, catalog_sales]], table:alias=[catalog_sales]) - HiveProject(d_date_sk=[$0], d_date=[$2]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(BETWEEN(false, CAST($2):TIMESTAMP(9), 1998-03-18 00:00:00, 1998-06-16 00:00:00), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) - HiveProject(i_item_sk=[$0], i_manufact_id=[CAST(269):INTEGER]) + HiveProject(i_item_sk=[$0]) HiveFilter(condition=[AND(=($13, 269), IS NOT NULL($0))]) HiveTableScan(table=[[default, item]], table:alias=[item]) diff --git ql/src/test/results/clientpositive/perf/tez/cbo_query33.q.out ql/src/test/results/clientpositive/perf/tez/cbo_query33.q.out index b5c7f114116..85349974883 100644 --- ql/src/test/results/clientpositive/perf/tez/cbo_query33.q.out +++ ql/src/test/results/clientpositive/perf/tez/cbo_query33.q.out @@ -167,8 +167,8 @@ HiveSortLimit(sort0=[$1], dir0=[ASC], fetch=[100]) HiveProject(i_manufact_id=[$0], $f1=[$1]) HiveUnion(all=[true]) HiveProject(i_manufact_id=[$0], $f1=[$1]) - HiveAggregate(group=[{1}], agg#0=[sum($8)]) - HiveJoin(condition=[=($6, $0)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveAggregate(group=[{1}], agg#0=[sum($7)]) + HiveJoin(condition=[=($5, $0)], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($1, $2)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(i_item_sk=[$0], i_manufact_id=[$13]) HiveFilter(condition=[AND(IS NOT NULL($13), IS NOT NULL($0))]) @@ -177,21 +177,21 @@ HiveSortLimit(sort0=[$1], dir0=[ASC], fetch=[100]) HiveAggregate(group=[{13}]) HiveFilter(condition=[AND(=($12, _UTF-16LE'Books'), IS NOT NULL($13))]) HiveTableScan(table=[[default, item]], table:alias=[item]) - HiveProject(ca_address_sk=[$0], ca_gmt_offset=[$1], ss_sold_date_sk=[$2], ss_item_sk=[$3], ss_addr_sk=[$4], ss_ext_sales_price=[$5], d_date_sk=[$6], d_year=[$7], d_moy=[$8]) - HiveJoin(condition=[=($4, $0)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(ca_address_sk=[$0], ca_gmt_offset=[CAST(-6):DECIMAL(5, 2)]) + HiveProject(ca_address_sk=[$0], ss_sold_date_sk=[$1], ss_item_sk=[$2], ss_addr_sk=[$3], ss_ext_sales_price=[$4], d_date_sk=[$5]) + HiveJoin(condition=[=($3, $0)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(ca_address_sk=[$0]) HiveFilter(condition=[AND(=($11, -6), IS NOT NULL($0))]) HiveTableScan(table=[[default, customer_address]], table:alias=[customer_address]) HiveJoin(condition=[=($0, $4)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(ss_sold_date_sk=[$0], ss_item_sk=[$2], ss_addr_sk=[$6], ss_ext_sales_price=[$15]) HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($6), IS NOT NULL($2))]) HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) - HiveProject(d_date_sk=[$0], d_year=[CAST(1999):INTEGER], d_moy=[CAST(3):INTEGER]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(=($6, 1999), =($8, 3), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) HiveProject(i_manufact_id=[$0], $f1=[$1]) - HiveAggregate(group=[{1}], agg#0=[sum($8)]) - HiveJoin(condition=[=($7, $0)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveAggregate(group=[{1}], agg#0=[sum($7)]) + HiveJoin(condition=[=($6, $0)], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($1, $2)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(i_item_sk=[$0], i_manufact_id=[$13]) HiveFilter(condition=[AND(IS NOT NULL($13), IS NOT NULL($0))]) @@ -200,21 +200,21 @@ HiveSortLimit(sort0=[$1], dir0=[ASC], fetch=[100]) HiveAggregate(group=[{13}]) HiveFilter(condition=[AND(=($12, _UTF-16LE'Books'), IS NOT NULL($13))]) HiveTableScan(table=[[default, item]], table:alias=[item]) - HiveProject(ca_address_sk=[$0], ca_gmt_offset=[$1], cs_sold_date_sk=[$2], cs_bill_addr_sk=[$3], cs_item_sk=[$4], cs_ext_sales_price=[$5], d_date_sk=[$6], d_year=[$7], d_moy=[$8]) - HiveJoin(condition=[=($3, $0)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(ca_address_sk=[$0], ca_gmt_offset=[CAST(-6):DECIMAL(5, 2)]) + HiveProject(ca_address_sk=[$0], cs_sold_date_sk=[$1], cs_bill_addr_sk=[$2], cs_item_sk=[$3], cs_ext_sales_price=[$4], d_date_sk=[$5]) + HiveJoin(condition=[=($2, $0)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(ca_address_sk=[$0]) HiveFilter(condition=[AND(=($11, -6), IS NOT NULL($0))]) HiveTableScan(table=[[default, customer_address]], table:alias=[customer_address]) HiveJoin(condition=[=($0, $4)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(cs_sold_date_sk=[$0], cs_bill_addr_sk=[$6], cs_item_sk=[$15], cs_ext_sales_price=[$23]) HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($6), IS NOT NULL($15))]) HiveTableScan(table=[[default, catalog_sales]], table:alias=[catalog_sales]) - HiveProject(d_date_sk=[$0], d_year=[CAST(1999):INTEGER], d_moy=[CAST(3):INTEGER]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(=($6, 1999), =($8, 3), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) HiveProject(i_manufact_id=[$0], $f1=[$1]) - HiveAggregate(group=[{1}], agg#0=[sum($8)]) - HiveJoin(condition=[=($6, $0)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveAggregate(group=[{1}], agg#0=[sum($7)]) + HiveJoin(condition=[=($5, $0)], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($1, $2)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(i_item_sk=[$0], i_manufact_id=[$13]) HiveFilter(condition=[AND(IS NOT NULL($13), IS NOT NULL($0))]) @@ -223,16 +223,16 @@ HiveSortLimit(sort0=[$1], dir0=[ASC], fetch=[100]) HiveAggregate(group=[{13}]) HiveFilter(condition=[AND(=($12, _UTF-16LE'Books'), IS NOT NULL($13))]) HiveTableScan(table=[[default, item]], table:alias=[item]) - HiveProject(ca_address_sk=[$0], ca_gmt_offset=[$1], ws_sold_date_sk=[$2], ws_item_sk=[$3], ws_bill_addr_sk=[$4], ws_ext_sales_price=[$5], d_date_sk=[$6], d_year=[$7], d_moy=[$8]) - HiveJoin(condition=[=($4, $0)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(ca_address_sk=[$0], ca_gmt_offset=[CAST(-6):DECIMAL(5, 2)]) + HiveProject(ca_address_sk=[$0], ws_sold_date_sk=[$1], ws_item_sk=[$2], ws_bill_addr_sk=[$3], ws_ext_sales_price=[$4], d_date_sk=[$5]) + HiveJoin(condition=[=($3, $0)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(ca_address_sk=[$0]) HiveFilter(condition=[AND(=($11, -6), IS NOT NULL($0))]) HiveTableScan(table=[[default, customer_address]], table:alias=[customer_address]) HiveJoin(condition=[=($0, $4)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(ws_sold_date_sk=[$0], ws_item_sk=[$3], ws_bill_addr_sk=[$7], ws_ext_sales_price=[$23]) HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($7), IS NOT NULL($3))]) HiveTableScan(table=[[default, web_sales]], table:alias=[web_sales]) - HiveProject(d_date_sk=[$0], d_year=[CAST(1999):INTEGER], d_moy=[CAST(3):INTEGER]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(=($6, 1999), =($8, 3), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) diff --git ql/src/test/results/clientpositive/perf/tez/cbo_query34.q.out ql/src/test/results/clientpositive/perf/tez/cbo_query34.q.out index 4e50a1ce372..9299409a899 100644 --- ql/src/test/results/clientpositive/perf/tez/cbo_query34.q.out +++ ql/src/test/results/clientpositive/perf/tez/cbo_query34.q.out @@ -81,19 +81,19 @@ HiveSortLimit(sort0=[$0], sort1=[$1], sort2=[$2], sort3=[$3], dir0=[ASC], dir1=[ HiveFilter(condition=[BETWEEN(false, $2, 15, 20)]) HiveProject(ss_ticket_number=[$1], ss_customer_sk=[$0], $f2=[$2]) HiveAggregate(group=[{1, 4}], agg#0=[count()]) - HiveJoin(condition=[=($3, $12)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveJoin(condition=[=($2, $8)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($3, $7)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($2, $6)], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($0, $5)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(ss_sold_date_sk=[$0], ss_customer_sk=[$3], ss_hdemo_sk=[$5], ss_store_sk=[$7], ss_ticket_number=[$9]) HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($7), IS NOT NULL($5), IS NOT NULL($3))]) HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) - HiveProject(d_date_sk=[$0], d_year=[$6], d_dom=[$9]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(IN($6, 2000, 2001, 2002), OR(BETWEEN(false, $9, 1, 3), BETWEEN(false, $9, 25, 28)), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) - HiveProject(hd_demo_sk=[$0], hd_buy_potential=[$2], hd_dep_count=[$3], hd_vehicle_count=[$4]) + HiveProject(hd_demo_sk=[$0]) HiveFilter(condition=[AND(IN($2, _UTF-16LE'>10000', _UTF-16LE'unknown'), >($4, 0), CASE(>($4, 0), >(/(CAST($3):DOUBLE, CAST($4):DOUBLE), 1.2), null), IS NOT NULL($0))]) HiveTableScan(table=[[default, household_demographics]], table:alias=[household_demographics]) - HiveProject(s_store_sk=[$0], s_county=[$23]) + HiveProject(s_store_sk=[$0]) HiveFilter(condition=[AND(IN($23, _UTF-16LE'Mobile County', _UTF-16LE'Maverick County', _UTF-16LE'Huron County', _UTF-16LE'Kittitas County', _UTF-16LE'Fairfield County', _UTF-16LE'Jackson County', _UTF-16LE'Barrow County', _UTF-16LE'Pennington County'), IS NOT NULL($0))]) HiveTableScan(table=[[default, store]], table:alias=[store]) diff --git ql/src/test/results/clientpositive/perf/tez/cbo_query35.q.out ql/src/test/results/clientpositive/perf/tez/cbo_query35.q.out index 2b8a4531b2e..f14a2bd8f30 100644 --- ql/src/test/results/clientpositive/perf/tez/cbo_query35.q.out +++ ql/src/test/results/clientpositive/perf/tez/cbo_query35.q.out @@ -151,7 +151,7 @@ HiveProject(ca_state=[$0], cd_gender=[$1], cd_marital_status=[$2], cnt1=[$3], _o HiveProject(ss_sold_date_sk=[$0], ss_customer_sk=[$3]) HiveFilter(condition=[AND(IS NOT NULL($3), IS NOT NULL($0))]) HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) - HiveProject(d_date_sk=[$0], d_year=[CAST(1999):INTEGER], d_qoy=[$10]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(=($6, 1999), <($10, 4), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) HiveProject(ws_bill_customer_sk0=[$0], $f1=[true]) @@ -160,7 +160,7 @@ HiveProject(ca_state=[$0], cd_gender=[$1], cd_marital_status=[$2], cnt1=[$3], _o HiveProject(ws_sold_date_sk=[$0], ws_bill_customer_sk=[$4]) HiveFilter(condition=[AND(IS NOT NULL($4), IS NOT NULL($0))]) HiveTableScan(table=[[default, web_sales]], table:alias=[web_sales]) - HiveProject(d_date_sk=[$0], d_year=[CAST(1999):INTEGER], d_qoy=[$10]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(=($6, 1999), <($10, 4), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) HiveProject(cs_ship_customer_sk0=[$0], $f1=[true]) @@ -169,7 +169,7 @@ HiveProject(ca_state=[$0], cd_gender=[$1], cd_marital_status=[$2], cnt1=[$3], _o HiveProject(cs_sold_date_sk=[$0], cs_ship_customer_sk=[$7]) HiveFilter(condition=[AND(IS NOT NULL($7), IS NOT NULL($0))]) HiveTableScan(table=[[default, catalog_sales]], table:alias=[catalog_sales]) - HiveProject(d_date_sk=[$0], d_year=[CAST(1999):INTEGER], d_qoy=[$10]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(=($6, 1999), <($10, 4), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) diff --git ql/src/test/results/clientpositive/perf/tez/cbo_query36.q.out ql/src/test/results/clientpositive/perf/tez/cbo_query36.q.out index b2a713f5c1a..9a74bed4705 100644 --- ql/src/test/results/clientpositive/perf/tez/cbo_query36.q.out +++ ql/src/test/results/clientpositive/perf/tez/cbo_query36.q.out @@ -72,17 +72,17 @@ HiveProject(gross_margin=[$0], i_category=[$1], i_class=[$2], lochierarchy=[$3], HiveProject(gross_margin=[/($2, $3)], i_category=[$0], i_class=[$1], lochierarchy=[+(grouping($4, 1), grouping($4, 0))], rank_within_parent=[rank() OVER (PARTITION BY +(grouping($4, 1), grouping($4, 0)), CASE(=(grouping($4, 0), 0), $0, null) ORDER BY /($2, $3) NULLS FIRST ROWS BETWEEN 2147483647 FOLLOWING AND 2147483647 PRECEDING)], (tok_function when (= (tok_table_or_col lochierarchy) 0) (tok_table_or_col i_category))=[CASE(=(+(grouping($4, 1), grouping($4, 0)), 0), $0, null)]) HiveProject($f0=[$0], $f1=[$1], $f2=[$2], $f3=[$3], GROUPING__ID=[$4]) HiveAggregate(group=[{0, 1}], groups=[[{0, 1}, {0}, {}]], agg#0=[sum($2)], agg#1=[sum($3)], GROUPING__ID=[GROUPING__ID()]) - HiveProject($f0=[$11], $f1=[$10], $f2=[$4], $f3=[$3]) - HiveJoin(condition=[=($9, $1)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveJoin(condition=[=($7, $2)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject($f0=[$9], $f1=[$8], $f2=[$4], $f3=[$3]) + HiveJoin(condition=[=($7, $1)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($6, $2)], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($5, $0)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(ss_sold_date_sk=[$0], ss_item_sk=[$2], ss_store_sk=[$7], ss_ext_sales_price=[$15], ss_net_profit=[$22]) HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($2), IS NOT NULL($7))]) HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) - HiveProject(d_date_sk=[$0], d_year=[CAST(1999):INTEGER]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(=($6, 1999), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[d1]) - HiveProject(s_store_sk=[$0], s_state=[$24]) + HiveProject(s_store_sk=[$0]) HiveFilter(condition=[AND(IN($24, _UTF-16LE'SD', _UTF-16LE'FL', _UTF-16LE'MI', _UTF-16LE'LA', _UTF-16LE'MO', _UTF-16LE'SC', _UTF-16LE'AL', _UTF-16LE'GA'), IS NOT NULL($0))]) HiveTableScan(table=[[default, store]], table:alias=[store]) HiveProject(i_item_sk=[$0], i_class=[$10], i_category=[$12]) diff --git ql/src/test/results/clientpositive/perf/tez/cbo_query37.q.out ql/src/test/results/clientpositive/perf/tez/cbo_query37.q.out index 0edc78b8713..07b99015206 100644 --- ql/src/test/results/clientpositive/perf/tez/cbo_query37.q.out +++ ql/src/test/results/clientpositive/perf/tez/cbo_query37.q.out @@ -44,20 +44,20 @@ CBO PLAN: HiveSortLimit(sort0=[$0], dir0=[ASC], fetch=[100]) HiveProject(i_item_id=[$0], i_item_desc=[$1], i_current_price=[$2]) HiveAggregate(group=[{2, 3, 4}]) - HiveJoin(condition=[=($7, $1)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($6, $1)], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($0, $1)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(cs_item_sk=[$15]) HiveFilter(condition=[IS NOT NULL($15)]) HiveTableScan(table=[[default, catalog_sales]], table:alias=[catalog_sales]) - HiveProject(i_item_sk=[$0], i_item_id=[$1], i_item_desc=[$4], i_current_price=[$5], i_manufact_id=[$13]) + HiveProject(i_item_sk=[$0], i_item_id=[$1], i_item_desc=[$4], i_current_price=[$5]) HiveFilter(condition=[AND(IN($13, 678, 964, 918, 849), BETWEEN(false, $5, 22, 52), IS NOT NULL($0))]) HiveTableScan(table=[[default, item]], table:alias=[item]) - HiveProject(inv_date_sk=[$0], inv_item_sk=[$1], inv_quantity_on_hand=[$2], d_date_sk=[$3], d_date=[$4]) - HiveJoin(condition=[=($3, $0)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(inv_date_sk=[$0], inv_item_sk=[$1], inv_quantity_on_hand=[$3]) + HiveProject(inv_date_sk=[$0], inv_item_sk=[$1], d_date_sk=[$2]) + HiveJoin(condition=[=($2, $0)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(inv_date_sk=[$0], inv_item_sk=[$1]) HiveFilter(condition=[AND(BETWEEN(false, $3, 100, 500), IS NOT NULL($1), IS NOT NULL($0))]) HiveTableScan(table=[[default, inventory]], table:alias=[inventory]) - HiveProject(d_date_sk=[$0], d_date=[$2]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(BETWEEN(false, CAST($2):TIMESTAMP(9), 2001-06-02 00:00:00, 2001-08-01 00:00:00), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) diff --git ql/src/test/results/clientpositive/perf/tez/cbo_query38.q.out ql/src/test/results/clientpositive/perf/tez/cbo_query38.q.out index 9633df11a14..cbf9bca0715 100644 --- ql/src/test/results/clientpositive/perf/tez/cbo_query38.q.out +++ ql/src/test/results/clientpositive/perf/tez/cbo_query38.q.out @@ -75,7 +75,7 @@ HiveSortLimit(fetch=[100]) HiveProject(ss_sold_date_sk=[$0], ss_customer_sk=[$3]) HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($3))]) HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) - HiveProject(d_date_sk=[$0], d_date=[$2], d_month_seq=[$3]) + HiveProject(d_date_sk=[$0], d_date=[$2]) HiveFilter(condition=[AND(BETWEEN(false, $3, 1212, 1223), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) HiveProject(c_last_name=[$1], c_first_name=[$0], d_date=[$2], $f3=[$3]) @@ -90,7 +90,7 @@ HiveSortLimit(fetch=[100]) HiveProject(cs_sold_date_sk=[$0], cs_bill_customer_sk=[$3]) HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($3))]) HiveTableScan(table=[[default, catalog_sales]], table:alias=[catalog_sales]) - HiveProject(d_date_sk=[$0], d_date=[$2], d_month_seq=[$3]) + HiveProject(d_date_sk=[$0], d_date=[$2]) HiveFilter(condition=[AND(BETWEEN(false, $3, 1212, 1223), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) HiveProject(c_last_name=[$1], c_first_name=[$0], d_date=[$2], $f3=[$3]) @@ -105,7 +105,7 @@ HiveSortLimit(fetch=[100]) HiveProject(ws_sold_date_sk=[$0], ws_bill_customer_sk=[$4]) HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($4))]) HiveTableScan(table=[[default, web_sales]], table:alias=[web_sales]) - HiveProject(d_date_sk=[$0], d_date=[$2], d_month_seq=[$3]) + HiveProject(d_date_sk=[$0], d_date=[$2]) HiveFilter(condition=[AND(BETWEEN(false, $3, 1212, 1223), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) diff --git ql/src/test/results/clientpositive/perf/tez/cbo_query39.q.out ql/src/test/results/clientpositive/perf/tez/cbo_query39.q.out index fd3038e37c4..51bb90101de 100644 --- ql/src/test/results/clientpositive/perf/tez/cbo_query39.q.out +++ ql/src/test/results/clientpositive/perf/tez/cbo_query39.q.out @@ -68,8 +68,8 @@ HiveProject(w_warehouse_sk=[$0], i_item_sk=[$1], d_moy=[CAST(4):INTEGER], mean=[ HiveProject(w_warehouse_sk=[$1], i_item_sk=[$2], mean=[/(CAST($6):DOUBLE, $5)], cov=[CASE(=(/(CAST($6):DOUBLE, $5), 0), null, /(POWER(/(-($3, /(*($4, $4), $5)), CASE(=($5, 1), null, -($5, 1))), 0.5), /(CAST($6):DOUBLE, $5)))]) HiveFilter(condition=[CASE(=(/(CAST($6):DOUBLE, $5), 0), false, >(/(POWER(/(-($3, /(*($4, $4), $5)), CASE(=($5, 1), null, -($5, 1))), 0.5), /(CAST($6):DOUBLE, $5)), 1))]) HiveAggregate(group=[{0, 1, 2}], agg#0=[sum($5)], agg#1=[sum($4)], agg#2=[count($3)], agg#3=[sum($3)]) - HiveProject($f0=[$9], $f1=[$8], $f2=[$0], $f4=[$4], $f40=[CAST($4):DOUBLE], $f6=[*(CAST($4):DOUBLE, CAST($4):DOUBLE)]) - HiveJoin(condition=[=($3, $8)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject($f0=[$7], $f1=[$6], $f2=[$0], $f4=[$4], $f40=[CAST($4):DOUBLE], $f6=[*(CAST($4):DOUBLE, CAST($4):DOUBLE)]) + HiveJoin(condition=[=($3, $6)], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($2, $0)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(i_item_sk=[$0]) HiveFilter(condition=[IS NOT NULL($0)]) @@ -78,7 +78,7 @@ HiveProject(w_warehouse_sk=[$0], i_item_sk=[$1], d_moy=[CAST(4):INTEGER], mean=[ HiveProject(inv_date_sk=[$0], inv_item_sk=[$1], inv_warehouse_sk=[$2], inv_quantity_on_hand=[$3]) HiveFilter(condition=[AND(IS NOT NULL($1), IS NOT NULL($2), IS NOT NULL($0))]) HiveTableScan(table=[[default, inventory]], table:alias=[inventory]) - HiveProject(d_date_sk=[$0], d_year=[CAST(1999):INTEGER], d_moy=[CAST(4):INTEGER]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(=($6, 1999), =($8, 4), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) HiveProject(w_warehouse_sk=[$0], w_warehouse_name=[$2]) @@ -87,8 +87,8 @@ HiveProject(w_warehouse_sk=[$0], i_item_sk=[$1], d_moy=[CAST(4):INTEGER], mean=[ HiveProject(w_warehouse_sk=[$1], i_item_sk=[$2], mean=[/(CAST($6):DOUBLE, $5)], cov=[CASE(=(/(CAST($6):DOUBLE, $5), 0), null, /(POWER(/(-($3, /(*($4, $4), $5)), CASE(=($5, 1), null, -($5, 1))), 0.5), /(CAST($6):DOUBLE, $5)))]) HiveFilter(condition=[CASE(=(/(CAST($6):DOUBLE, $5), 0), false, >(/(POWER(/(-($3, /(*($4, $4), $5)), CASE(=($5, 1), null, -($5, 1))), 0.5), /(CAST($6):DOUBLE, $5)), 1))]) HiveAggregate(group=[{0, 1, 2}], agg#0=[sum($5)], agg#1=[sum($4)], agg#2=[count($3)], agg#3=[sum($3)]) - HiveProject($f0=[$9], $f1=[$8], $f2=[$0], $f4=[$4], $f40=[CAST($4):DOUBLE], $f6=[*(CAST($4):DOUBLE, CAST($4):DOUBLE)]) - HiveJoin(condition=[=($3, $8)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject($f0=[$7], $f1=[$6], $f2=[$0], $f4=[$4], $f40=[CAST($4):DOUBLE], $f6=[*(CAST($4):DOUBLE, CAST($4):DOUBLE)]) + HiveJoin(condition=[=($3, $6)], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($2, $0)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(i_item_sk=[$0]) HiveFilter(condition=[IS NOT NULL($0)]) @@ -97,7 +97,7 @@ HiveProject(w_warehouse_sk=[$0], i_item_sk=[$1], d_moy=[CAST(4):INTEGER], mean=[ HiveProject(inv_date_sk=[$0], inv_item_sk=[$1], inv_warehouse_sk=[$2], inv_quantity_on_hand=[$3]) HiveFilter(condition=[AND(IS NOT NULL($1), IS NOT NULL($2), IS NOT NULL($0))]) HiveTableScan(table=[[default, inventory]], table:alias=[inventory]) - HiveProject(d_date_sk=[$0], d_year=[CAST(1999):INTEGER], d_moy=[CAST(5):INTEGER]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(=($6, 1999), =($8, 5), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) HiveProject(w_warehouse_sk=[$0], w_warehouse_name=[$2]) diff --git ql/src/test/results/clientpositive/perf/tez/cbo_query4.q.out ql/src/test/results/clientpositive/perf/tez/cbo_query4.q.out index d796f8622c1..4b388653aee 100644 --- ql/src/test/results/clientpositive/perf/tez/cbo_query4.q.out +++ ql/src/test/results/clientpositive/perf/tez/cbo_query4.q.out @@ -229,96 +229,90 @@ POSTHOOK: Output: hdfs://### HDFS PATH ### CBO PLAN: HiveSortLimit(sort0=[$0], dir0=[ASC], fetch=[100]) HiveProject(customer_preferred_cust_flag=[$1]) - HiveJoin(condition=[AND(=($0, $7), CASE(CAST(IS NOT NULL($8)):BOOLEAN, CASE(CAST(IS NOT NULL($10)):BOOLEAN, >(/($4, $10), /($2, $8)), >(null, /($2, $8))), CASE(CAST(IS NOT NULL($10)):BOOLEAN, >(/($4, $10), null), null)))], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[AND(=($0, $7), CASE(CAST(IS NOT NULL($8)):BOOLEAN, CASE($14, >(/($4, $13), /($2, $8)), >(null, /($2, $8))), CASE($14, >(/($4, $13), null), null)))], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject($f0=[$0], $f3=[$3], $f8=[$7]) - HiveAggregate(group=[{0, 1, 2, 3, 4, 5, 6}], agg#0=[sum($7)]) - HiveProject($f0=[$1], $f1=[$2], $f2=[$3], $f3=[$4], $f4=[$5], $f5=[$6], $f6=[$7], $f8=[/(+(-(-($13, $12), $10), $11), CAST(2):DECIMAL(10, 0))]) + HiveAggregate(group=[{1, 2, 3, 4, 5, 6, 7}], agg#0=[sum($10)]) + HiveJoin(condition=[=($0, $9)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(c_customer_sk=[$0], c_customer_id=[$1], c_first_name=[$8], c_last_name=[$9], c_preferred_cust_flag=[$10], c_birth_country=[$14], c_login=[$15], c_email_address=[$16]) + HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($1))]) + HiveTableScan(table=[[default, customer]], table:alias=[customer]) + HiveJoin(condition=[=($0, $3)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(ss_sold_date_sk=[$0], ss_customer_sk=[$3], /=[/(+(-(-($17, $16), $14), $15), CAST(2):DECIMAL(10, 0))]) + HiveFilter(condition=[AND(IS NOT NULL($3), IS NOT NULL($0))]) + HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) + HiveProject(d_date_sk=[$0]) + HiveFilter(condition=[AND(=($6, 2002), IS NOT NULL($0))]) + HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) + HiveJoin(condition=[AND(=($4, $0), CASE($8, CASE($11, >(/($1, $10), /($3, $7)), >(null, /($3, $7))), CASE($11, >(/($1, $10), null), null)))], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject($f0=[$0], $f8=[$7]) + HiveAggregate(group=[{1, 2, 3, 4, 5, 6, 7}], agg#0=[sum($10)]) HiveJoin(condition=[=($0, $9)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(c_customer_sk=[$0], c_customer_id=[$1], c_first_name=[$8], c_last_name=[$9], c_preferred_cust_flag=[$10], c_birth_country=[$14], c_login=[$15], c_email_address=[$16]) HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($1))]) HiveTableScan(table=[[default, customer]], table:alias=[customer]) - HiveJoin(condition=[=($0, $6)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(ss_sold_date_sk=[$0], ss_customer_sk=[$3], ss_ext_discount_amt=[$14], ss_ext_sales_price=[$15], ss_ext_wholesale_cost=[$16], ss_ext_list_price=[$17]) + HiveJoin(condition=[=($0, $3)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(cs_sold_date_sk=[$0], cs_bill_customer_sk=[$3], /=[/(+(-(-($25, $24), $22), $23), CAST(2):DECIMAL(10, 0))]) HiveFilter(condition=[AND(IS NOT NULL($3), IS NOT NULL($0))]) - HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) - HiveProject(d_date_sk=[$0], d_year=[CAST(2002):INTEGER]) + HiveTableScan(table=[[default, catalog_sales]], table:alias=[catalog_sales]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(=($6, 2002), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) - HiveJoin(condition=[AND(=($4, $0), CASE(CAST(IS NOT NULL($9)):BOOLEAN, CASE(CAST(IS NOT NULL($7)):BOOLEAN, >(/($1, $7), /($3, $9)), >(null, /($3, $9))), CASE(CAST(IS NOT NULL($7)):BOOLEAN, >(/($1, $7), null), null)))], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject($f0=[$0], $f8=[$7]) - HiveAggregate(group=[{0, 1, 2, 3, 4, 5, 6}], agg#0=[sum($7)]) - HiveProject($f0=[$1], $f1=[$2], $f2=[$3], $f3=[$4], $f4=[$5], $f5=[$6], $f6=[$7], $f8=[/(+(-(-($13, $12), $10), $11), CAST(2):DECIMAL(10, 0))]) - HiveJoin(condition=[=($0, $9)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(c_customer_sk=[$0], c_customer_id=[$1], c_first_name=[$8], c_last_name=[$9], c_preferred_cust_flag=[$10], c_birth_country=[$14], c_login=[$15], c_email_address=[$16]) - HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($1))]) - HiveTableScan(table=[[default, customer]], table:alias=[customer]) - HiveJoin(condition=[=($0, $6)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(cs_sold_date_sk=[$0], cs_bill_customer_sk=[$3], cs_ext_discount_amt=[$22], cs_ext_sales_price=[$23], cs_ext_wholesale_cost=[$24], cs_ext_list_price=[$25]) - HiveFilter(condition=[AND(IS NOT NULL($3), IS NOT NULL($0))]) - HiveTableScan(table=[[default, catalog_sales]], table:alias=[catalog_sales]) - HiveProject(d_date_sk=[$0], d_year=[CAST(2002):INTEGER]) - HiveFilter(condition=[AND(=($6, 2002), IS NOT NULL($0))]) - HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) - HiveJoin(condition=[=($2, $6)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($2, $7)], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($2, $4)], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($2, $0)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject($f0=[$0], $f8=[$7]) - HiveAggregate(group=[{0, 1, 2, 3, 4, 5, 6}], agg#0=[sum($7)]) - HiveProject($f0=[$1], $f1=[$2], $f2=[$3], $f3=[$4], $f4=[$5], $f5=[$6], $f6=[$7], $f8=[/(+(-(-($13, $12), $10), $11), CAST(2):DECIMAL(10, 0))]) - HiveJoin(condition=[=($0, $9)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(c_customer_sk=[$0], c_customer_id=[$1], c_first_name=[$8], c_last_name=[$9], c_preferred_cust_flag=[$10], c_birth_country=[$14], c_login=[$15], c_email_address=[$16]) - HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($1))]) - HiveTableScan(table=[[default, customer]], table:alias=[customer]) - HiveJoin(condition=[=($0, $6)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(ws_sold_date_sk=[$0], ws_bill_customer_sk=[$4], ws_ext_discount_amt=[$22], ws_ext_sales_price=[$23], ws_ext_wholesale_cost=[$24], ws_ext_list_price=[$25]) - HiveFilter(condition=[AND(IS NOT NULL($4), IS NOT NULL($0))]) - HiveTableScan(table=[[default, web_sales]], table:alias=[web_sales]) - HiveProject(d_date_sk=[$0], d_year=[CAST(2002):INTEGER]) - HiveFilter(condition=[AND(=($6, 2002), IS NOT NULL($0))]) - HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) + HiveAggregate(group=[{1, 2, 3, 4, 5, 6, 7}], agg#0=[sum($10)]) + HiveJoin(condition=[=($0, $9)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(c_customer_sk=[$0], c_customer_id=[$1], c_first_name=[$8], c_last_name=[$9], c_preferred_cust_flag=[$10], c_birth_country=[$14], c_login=[$15], c_email_address=[$16]) + HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($1))]) + HiveTableScan(table=[[default, customer]], table:alias=[customer]) + HiveJoin(condition=[=($0, $3)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(ws_sold_date_sk=[$0], ws_bill_customer_sk=[$4], /=[/(+(-(-($25, $24), $22), $23), CAST(2):DECIMAL(10, 0))]) + HiveFilter(condition=[AND(IS NOT NULL($4), IS NOT NULL($0))]) + HiveTableScan(table=[[default, web_sales]], table:alias=[web_sales]) + HiveProject(d_date_sk=[$0]) + HiveFilter(condition=[AND(=($6, 2002), IS NOT NULL($0))]) + HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) HiveProject($f0=[$0], $f8=[$7]) HiveFilter(condition=[>($7, 0)]) - HiveAggregate(group=[{0, 1, 2, 3, 4, 5, 6}], agg#0=[sum($7)]) - HiveProject($f0=[$1], $f1=[$2], $f2=[$3], $f3=[$4], $f4=[$5], $f5=[$6], $f6=[$7], $f8=[/(+(-(-($13, $12), $10), $11), CAST(2):DECIMAL(10, 0))]) - HiveJoin(condition=[=($0, $9)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(c_customer_sk=[$0], c_customer_id=[$1], c_first_name=[$8], c_last_name=[$9], c_preferred_cust_flag=[$10], c_birth_country=[$14], c_login=[$15], c_email_address=[$16]) - HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($1))]) - HiveTableScan(table=[[default, customer]], table:alias=[customer]) - HiveJoin(condition=[=($0, $6)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(ss_sold_date_sk=[$0], ss_customer_sk=[$3], ss_ext_discount_amt=[$14], ss_ext_sales_price=[$15], ss_ext_wholesale_cost=[$16], ss_ext_list_price=[$17]) - HiveFilter(condition=[AND(IS NOT NULL($3), IS NOT NULL($0))]) - HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) - HiveProject(d_date_sk=[$0], d_year=[CAST(2001):INTEGER]) - HiveFilter(condition=[AND(=($6, 2001), IS NOT NULL($0))]) - HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) - HiveProject($f0=[$0], $f8=[$7]) - HiveFilter(condition=[>($7, 0)]) - HiveAggregate(group=[{0, 1, 2, 3, 4, 5, 6}], agg#0=[sum($7)]) - HiveProject($f0=[$1], $f1=[$2], $f2=[$3], $f3=[$4], $f4=[$5], $f5=[$6], $f6=[$7], $f8=[/(+(-(-($13, $12), $10), $11), CAST(2):DECIMAL(10, 0))]) + HiveAggregate(group=[{1, 2, 3, 4, 5, 6, 7}], agg#0=[sum($10)]) HiveJoin(condition=[=($0, $9)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(c_customer_sk=[$0], c_customer_id=[$1], c_first_name=[$8], c_last_name=[$9], c_preferred_cust_flag=[$10], c_birth_country=[$14], c_login=[$15], c_email_address=[$16]) HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($1))]) HiveTableScan(table=[[default, customer]], table:alias=[customer]) - HiveJoin(condition=[=($0, $6)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(cs_sold_date_sk=[$0], cs_bill_customer_sk=[$3], cs_ext_discount_amt=[$22], cs_ext_sales_price=[$23], cs_ext_wholesale_cost=[$24], cs_ext_list_price=[$25]) + HiveJoin(condition=[=($0, $3)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(ss_sold_date_sk=[$0], ss_customer_sk=[$3], /=[/(+(-(-($17, $16), $14), $15), CAST(2):DECIMAL(10, 0))]) HiveFilter(condition=[AND(IS NOT NULL($3), IS NOT NULL($0))]) - HiveTableScan(table=[[default, catalog_sales]], table:alias=[catalog_sales]) - HiveProject(d_date_sk=[$0], d_year=[CAST(2001):INTEGER]) + HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(=($6, 2001), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) - HiveProject($f0=[$0], $f8=[$7]) - HiveFilter(condition=[>($7, 0)]) - HiveAggregate(group=[{0, 1, 2, 3, 4, 5, 6}], agg#0=[sum($7)]) - HiveProject($f0=[$1], $f1=[$2], $f2=[$3], $f3=[$4], $f4=[$5], $f5=[$6], $f6=[$7], $f8=[/(+(-(-($13, $12), $10), $11), CAST(2):DECIMAL(10, 0))]) + HiveProject(customer_id=[$0], year_total=[$7], CAST=[CAST(IS NOT NULL($7)):BOOLEAN]) + HiveFilter(condition=[>($7, 0)]) + HiveAggregate(group=[{1, 2, 3, 4, 5, 6, 7}], agg#0=[sum($10)]) HiveJoin(condition=[=($0, $9)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(c_customer_sk=[$0], c_customer_id=[$1], c_first_name=[$8], c_last_name=[$9], c_preferred_cust_flag=[$10], c_birth_country=[$14], c_login=[$15], c_email_address=[$16]) HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($1))]) HiveTableScan(table=[[default, customer]], table:alias=[customer]) - HiveJoin(condition=[=($0, $6)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(ws_sold_date_sk=[$0], ws_bill_customer_sk=[$4], ws_ext_discount_amt=[$22], ws_ext_sales_price=[$23], ws_ext_wholesale_cost=[$24], ws_ext_list_price=[$25]) + HiveJoin(condition=[=($0, $3)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(ws_sold_date_sk=[$0], ws_bill_customer_sk=[$4], /=[/(+(-(-($25, $24), $22), $23), CAST(2):DECIMAL(10, 0))]) HiveFilter(condition=[AND(IS NOT NULL($4), IS NOT NULL($0))]) HiveTableScan(table=[[default, web_sales]], table:alias=[web_sales]) - HiveProject(d_date_sk=[$0], d_year=[CAST(2001):INTEGER]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(=($6, 2001), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) + HiveProject(customer_id=[$0], year_total=[$7], CAST=[CAST(IS NOT NULL($7)):BOOLEAN]) + HiveFilter(condition=[>($7, 0)]) + HiveAggregate(group=[{1, 2, 3, 4, 5, 6, 7}], agg#0=[sum($10)]) + HiveJoin(condition=[=($0, $9)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(c_customer_sk=[$0], c_customer_id=[$1], c_first_name=[$8], c_last_name=[$9], c_preferred_cust_flag=[$10], c_birth_country=[$14], c_login=[$15], c_email_address=[$16]) + HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($1))]) + HiveTableScan(table=[[default, customer]], table:alias=[customer]) + HiveJoin(condition=[=($0, $3)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(cs_sold_date_sk=[$0], cs_bill_customer_sk=[$3], /=[/(+(-(-($25, $24), $22), $23), CAST(2):DECIMAL(10, 0))]) + HiveFilter(condition=[AND(IS NOT NULL($3), IS NOT NULL($0))]) + HiveTableScan(table=[[default, catalog_sales]], table:alias=[catalog_sales]) + HiveProject(d_date_sk=[$0]) + HiveFilter(condition=[AND(=($6, 2001), IS NOT NULL($0))]) + HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) diff --git ql/src/test/results/clientpositive/perf/tez/cbo_query40.q.out ql/src/test/results/clientpositive/perf/tez/cbo_query40.q.out index 7d8fc9b18d6..1f834b56477 100644 --- ql/src/test/results/clientpositive/perf/tez/cbo_query40.q.out +++ ql/src/test/results/clientpositive/perf/tez/cbo_query40.q.out @@ -68,12 +68,12 @@ CBO PLAN: HiveSortLimit(sort0=[$0], sort1=[$1], dir0=[ASC], dir1=[ASC], fetch=[100]) HiveProject($f0=[$0], $f1=[$1], $f2=[$2], $f3=[$3]) HiveAggregate(group=[{0, 1}], agg#0=[sum($2)], agg#1=[sum($3)]) - HiveProject($f0=[$1], $f1=[$13], $f2=[CASE(<(CAST($11):DATE, 1998-04-08), -($6, CASE(IS NOT NULL($9), $9, 0)), 0)], $f3=[CASE(>=(CAST($11):DATE, 1998-04-08), -($6, CASE(IS NOT NULL($9), $9, 0)), 0)]) + HiveProject($f0=[$1], $f1=[$14], $f2=[CASE($11, -($6, CASE(IS NOT NULL($9), $9, 0)), 0)], $f3=[CASE($12, -($6, CASE(IS NOT NULL($9), $9, 0)), 0)]) HiveJoin(condition=[=($3, $0)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(w_warehouse_sk=[$0], w_state=[$10]) HiveFilter(condition=[IS NOT NULL($0)]) HiveTableScan(table=[[default, warehouse]], table:alias=[warehouse]) - HiveJoin(condition=[=($10, $2)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($11, $2)], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($0, $8)], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[AND(=($3, $6), =($2, $5))], joinType=[left], algorithm=[none], cost=[not available]) HiveProject(cs_sold_date_sk=[$0], cs_warehouse_sk=[$14], cs_item_sk=[$15], cs_order_number=[$17], cs_sales_price=[$21]) @@ -82,10 +82,10 @@ HiveSortLimit(sort0=[$0], sort1=[$1], dir0=[ASC], dir1=[ASC], fetch=[100]) HiveProject(cr_item_sk=[$2], cr_order_number=[$16], cr_refunded_cash=[$23]) HiveFilter(condition=[IS NOT NULL($2)]) HiveTableScan(table=[[default, catalog_returns]], table:alias=[catalog_returns]) - HiveProject(d_date_sk=[$0], d_date=[$2]) + HiveProject(d_date_sk=[$0], <=[<(CAST($2):DATE, 1998-04-08)], >==[>=(CAST($2):DATE, 1998-04-08)]) HiveFilter(condition=[AND(BETWEEN(false, CAST($2):TIMESTAMP(9), 1998-03-09 00:00:00, 1998-05-08 00:00:00), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) - HiveProject(i_item_sk=[$0], i_item_id=[$1], i_current_price=[$5]) + HiveProject(i_item_sk=[$0], i_item_id=[$1]) HiveFilter(condition=[AND(BETWEEN(false, $5, 0.99, 1.49), IS NOT NULL($0))]) HiveTableScan(table=[[default, item]], table:alias=[item]) diff --git ql/src/test/results/clientpositive/perf/tez/cbo_query42.q.out ql/src/test/results/clientpositive/perf/tez/cbo_query42.q.out index ddb32232e97..0a7dac0336a 100644 --- ql/src/test/results/clientpositive/perf/tez/cbo_query42.q.out +++ ql/src/test/results/clientpositive/perf/tez/cbo_query42.q.out @@ -53,16 +53,16 @@ HiveSortLimit(fetch=[100]) HiveProject(d_year=[CAST(1998):INTEGER], i_category_id=[$0], i_category=[$1], _o__c3=[$2]) HiveSortLimit(sort0=[$3], sort1=[$0], sort2=[$1], dir0=[DESC-nulls-last], dir1=[ASC], dir2=[ASC]) HiveProject(i_category_id=[$0], i_category=[$1], _o__c3=[$2], (tok_function sum (tok_table_or_col ss_ext_sales_price))=[$2]) - HiveAggregate(group=[{7, 8}], agg#0=[sum($2)]) - HiveJoin(condition=[=($1, $6)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveAggregate(group=[{5, 6}], agg#0=[sum($2)]) + HiveJoin(condition=[=($1, $4)], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($3, $0)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(ss_sold_date_sk=[$0], ss_item_sk=[$2], ss_ext_sales_price=[$15]) HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($2))]) HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) - HiveProject(d_date_sk=[$0], d_year=[CAST(1998):INTEGER], d_moy=[CAST(12):INTEGER]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(=($8, 12), =($6, 1998), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[dt]) - HiveProject(i_item_sk=[$0], i_category_id=[$11], i_category=[$12], i_manager_id=[CAST(1):INTEGER]) + HiveProject(i_item_sk=[$0], i_category_id=[$11], i_category=[$12]) HiveFilter(condition=[AND(=($20, 1), IS NOT NULL($0))]) HiveTableScan(table=[[default, item]], table:alias=[item]) diff --git ql/src/test/results/clientpositive/perf/tez/cbo_query43.q.out ql/src/test/results/clientpositive/perf/tez/cbo_query43.q.out index f6eeae33ed9..1d86c8bd07d 100644 --- ql/src/test/results/clientpositive/perf/tez/cbo_query43.q.out +++ ql/src/test/results/clientpositive/perf/tez/cbo_query43.q.out @@ -46,16 +46,16 @@ CBO PLAN: HiveSortLimit(sort0=[$0], sort1=[$1], sort2=[$2], sort3=[$3], sort4=[$4], sort5=[$5], sort6=[$6], sort7=[$7], sort8=[$8], dir0=[ASC], dir1=[ASC], dir2=[ASC], dir3=[ASC], dir4=[ASC], dir5=[ASC], dir6=[ASC], dir7=[ASC], dir8=[ASC], fetch=[100]) HiveProject($f0=[$0], $f1=[$1], $f2=[$2], $f3=[$3], $f4=[$4], $f5=[$5], $f6=[$6], $f7=[$7], $f8=[$8]) HiveAggregate(group=[{0, 1}], agg#0=[sum($2)], agg#1=[sum($3)], agg#2=[sum($4)], agg#3=[sum($5)], agg#4=[sum($6)], agg#5=[sum($7)], agg#6=[sum($8)]) - HiveProject($f0=[$8], $f1=[$7], $f2=[CASE(=($5, _UTF-16LE'Sunday'), $2, null)], $f3=[CASE(=($5, _UTF-16LE'Monday'), $2, null)], $f4=[CASE(=($5, _UTF-16LE'Tuesday'), $2, null)], $f5=[CASE(=($5, _UTF-16LE'Wednesday'), $2, null)], $f6=[CASE(=($5, _UTF-16LE'Thursday'), $2, null)], $f7=[CASE(=($5, _UTF-16LE'Friday'), $2, null)], $f8=[CASE(=($5, _UTF-16LE'Saturday'), $2, null)]) - HiveJoin(condition=[=($6, $1)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject($f0=[$13], $f1=[$12], $f2=[CASE($4, $2, null)], $f3=[CASE($5, $2, null)], $f4=[CASE($6, $2, null)], $f5=[CASE($7, $2, null)], $f6=[CASE($8, $2, null)], $f7=[CASE($9, $2, null)], $f8=[CASE($10, $2, null)]) + HiveJoin(condition=[=($11, $1)], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($3, $0)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(ss_sold_date_sk=[$0], ss_store_sk=[$7], ss_sales_price=[$13]) HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($7))]) HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) - HiveProject(d_date_sk=[$0], d_year=[CAST(1998):INTEGER], d_day_name=[$14]) + HiveProject(d_date_sk=[$0], ==[=($14, _UTF-16LE'Sunday')], =2=[=($14, _UTF-16LE'Monday')], =3=[=($14, _UTF-16LE'Tuesday')], =4=[=($14, _UTF-16LE'Wednesday')], =5=[=($14, _UTF-16LE'Thursday')], =6=[=($14, _UTF-16LE'Friday')], =7=[=($14, _UTF-16LE'Saturday')]) HiveFilter(condition=[AND(=($6, 1998), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) - HiveProject(s_store_sk=[$0], s_store_id=[$1], s_store_name=[$5], s_gmt_offset=[CAST(-6):DECIMAL(5, 2)]) + HiveProject(s_store_sk=[$0], s_store_id=[$1], s_store_name=[$5]) HiveFilter(condition=[AND(=($27, -6), IS NOT NULL($0))]) HiveTableScan(table=[[default, store]], table:alias=[store]) diff --git ql/src/test/results/clientpositive/perf/tez/cbo_query46.q.out ql/src/test/results/clientpositive/perf/tez/cbo_query46.q.out index 0728056fe69..89218b861ec 100644 --- ql/src/test/results/clientpositive/perf/tez/cbo_query46.q.out +++ ql/src/test/results/clientpositive/perf/tez/cbo_query46.q.out @@ -97,19 +97,19 @@ HiveSortLimit(sort0=[$0], sort1=[$1], sort2=[$2], sort3=[$3], sort4=[$4], dir0=[ HiveProject(ca_address_sk=[$0], ca_city=[$6]) HiveFilter(condition=[IS NOT NULL($0)]) HiveTableScan(table=[[default, customer_address]], table:alias=[customer_address]) - HiveJoin(condition=[=($2, $13)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveJoin(condition=[=($4, $11)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($2, $10)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($4, $9)], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($0, $8)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(ss_sold_date_sk=[$0], ss_customer_sk=[$3], ss_hdemo_sk=[$5], ss_addr_sk=[$6], ss_store_sk=[$7], ss_ticket_number=[$9], ss_coupon_amt=[$19], ss_net_profit=[$22]) HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($7), IS NOT NULL($5), IS NOT NULL($6), IS NOT NULL($3))]) HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) - HiveProject(d_date_sk=[$0], d_year=[$6], d_dow=[$7]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(IN($7, 6, 0), IN($6, 1998, 1999, 2000), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) - HiveProject(s_store_sk=[$0], s_city=[$22]) + HiveProject(s_store_sk=[$0]) HiveFilter(condition=[AND(IN($22, _UTF-16LE'Cedar Grove', _UTF-16LE'Wildwood', _UTF-16LE'Union', _UTF-16LE'Salem', _UTF-16LE'Highland Park'), IS NOT NULL($0))]) HiveTableScan(table=[[default, store]], table:alias=[store]) - HiveProject(hd_demo_sk=[$0], hd_dep_count=[$3], hd_vehicle_count=[$4]) + HiveProject(hd_demo_sk=[$0]) HiveFilter(condition=[AND(OR(=($3, 2), =($4, 1)), IS NOT NULL($0))]) HiveTableScan(table=[[default, household_demographics]], table:alias=[household_demographics]) diff --git ql/src/test/results/clientpositive/perf/tez/cbo_query47.q.out ql/src/test/results/clientpositive/perf/tez/cbo_query47.q.out index 11fd5773e9d..8dff4677bad 100644 --- ql/src/test/results/clientpositive/perf/tez/cbo_query47.q.out +++ ql/src/test/results/clientpositive/perf/tez/cbo_query47.q.out @@ -112,8 +112,8 @@ CBO PLAN: HiveProject(i_category=[$0], d_year=[$1], d_moy=[$2], avg_monthly_sales=[$3], sum_sales=[$4], psum=[$5], nsum=[$6]) HiveSortLimit(sort0=[$7], sort1=[$2], dir0=[ASC], dir1=[ASC], fetch=[100]) HiveProject(i_category=[$12], d_year=[$16], d_moy=[$17], avg_monthly_sales=[$19], sum_sales=[$18], psum=[$10], nsum=[$4], (- (tok_table_or_col sum_sales) (tok_table_or_col avg_monthly_sales))=[-($18, $19)]) - HiveJoin(condition=[AND(AND(AND(AND(=($12, $0), =($13, $1)), =($14, $2)), =($15, $3)), =($20, -($5, 1)))], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject((tok_table_or_col i_category)=[$0], (tok_table_or_col i_brand)=[$1], (tok_table_or_col s_store_name)=[$2], (tok_table_or_col s_company_name)=[$3], (tok_function sum (tok_table_or_col ss_sales_price))=[$4], rank_window_1=[$5]) + HiveJoin(condition=[AND(AND(AND(AND(=($12, $0), =($13, $1)), =($14, $2)), =($15, $3)), =($20, $5))], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject((tok_table_or_col i_category)=[$0], (tok_table_or_col i_brand)=[$1], (tok_table_or_col s_store_name)=[$2], (tok_table_or_col s_company_name)=[$3], (tok_function sum (tok_table_or_col ss_sales_price))=[$4], -=[-($5, 1)]) HiveFilter(condition=[IS NOT NULL($5)]) HiveProject((tok_table_or_col i_category)=[$1], (tok_table_or_col i_brand)=[$0], (tok_table_or_col s_store_name)=[$4], (tok_table_or_col s_company_name)=[$5], (tok_function sum (tok_table_or_col ss_sales_price))=[$6], rank_window_1=[rank() OVER (PARTITION BY $1, $0, $4, $5 ORDER BY $2 NULLS LAST, $3 NULLS LAST ROWS BETWEEN 2147483647 FOLLOWING AND 2147483647 PRECEDING)]) HiveProject(i_brand=[$0], i_category=[$1], d_year=[$2], d_moy=[$3], s_store_name=[$4], s_company_name=[$5], $f6=[$6]) @@ -133,8 +133,8 @@ HiveProject(i_category=[$0], d_year=[$1], d_moy=[$2], avg_monthly_sales=[$3], su HiveProject(s_store_sk=[$0], s_store_name=[$5], s_company_name=[$17]) HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($5), IS NOT NULL($17))]) HiveTableScan(table=[[default, store]], table:alias=[store]) - HiveJoin(condition=[AND(AND(AND(AND(=($6, $0), =($7, $1)), =($8, $2)), =($9, $3)), =($14, +($5, 1)))], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject((tok_table_or_col i_category)=[$0], (tok_table_or_col i_brand)=[$1], (tok_table_or_col s_store_name)=[$2], (tok_table_or_col s_company_name)=[$3], (tok_function sum (tok_table_or_col ss_sales_price))=[$4], rank_window_1=[$5]) + HiveJoin(condition=[AND(AND(AND(AND(=($6, $0), =($7, $1)), =($8, $2)), =($9, $3)), =($14, $5))], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject((tok_table_or_col i_category)=[$0], (tok_table_or_col i_brand)=[$1], (tok_table_or_col s_store_name)=[$2], (tok_table_or_col s_company_name)=[$3], (tok_function sum (tok_table_or_col ss_sales_price))=[$4], +=[+($5, 1)]) HiveFilter(condition=[IS NOT NULL($5)]) HiveProject((tok_table_or_col i_category)=[$1], (tok_table_or_col i_brand)=[$0], (tok_table_or_col s_store_name)=[$4], (tok_table_or_col s_company_name)=[$5], (tok_function sum (tok_table_or_col ss_sales_price))=[$6], rank_window_1=[rank() OVER (PARTITION BY $1, $0, $4, $5 ORDER BY $2 NULLS LAST, $3 NULLS LAST ROWS BETWEEN 2147483647 FOLLOWING AND 2147483647 PRECEDING)]) HiveProject(i_brand=[$0], i_category=[$1], d_year=[$2], d_moy=[$3], s_store_name=[$4], s_company_name=[$5], $f6=[$6]) diff --git ql/src/test/results/clientpositive/perf/tez/cbo_query48.q.out ql/src/test/results/clientpositive/perf/tez/cbo_query48.q.out index feb4012a377..079556ec993 100644 --- ql/src/test/results/clientpositive/perf/tez/cbo_query48.q.out +++ ql/src/test/results/clientpositive/perf/tez/cbo_query48.q.out @@ -141,24 +141,24 @@ POSTHOOK: Input: default@store POSTHOOK: Input: default@store_sales POSTHOOK: Output: hdfs://### HDFS PATH ### CBO PLAN: -HiveAggregate(group=[{}], agg#0=[sum($13)]) - HiveJoin(condition=[AND(=($11, $0), OR(AND(IN($1, _UTF-16LE'KY', _UTF-16LE'GA', _UTF-16LE'NM'), BETWEEN(false, $15, 0, 2000)), AND(IN($1, _UTF-16LE'MT', _UTF-16LE'OR', _UTF-16LE'IN'), BETWEEN(false, $15, 150, 3000)), AND(IN($1, _UTF-16LE'WI', _UTF-16LE'MO', _UTF-16LE'WV'), BETWEEN(false, $15, 50, 25000))))], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(ca_address_sk=[$0], ca_state=[$8], ca_country=[CAST(_UTF-16LE'United States'):VARCHAR(2147483647) CHARACTER SET "UTF-16LE" COLLATE "ISO-8859-1$en_US$primary"]) +HiveAggregate(group=[{}], agg#0=[sum($11)]) + HiveJoin(condition=[AND(=($9, $0), OR(AND($1, $12), AND($2, $13), AND($3, $14)))], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(ca_address_sk=[$0], IN=[IN($8, _UTF-16LE'KY', _UTF-16LE'GA', _UTF-16LE'NM')], IN2=[IN($8, _UTF-16LE'MT', _UTF-16LE'OR', _UTF-16LE'IN')], IN3=[IN($8, _UTF-16LE'WI', _UTF-16LE'MO', _UTF-16LE'WV')]) HiveFilter(condition=[AND(IN($8, _UTF-16LE'KY', _UTF-16LE'GA', _UTF-16LE'NM', _UTF-16LE'MT', _UTF-16LE'OR', _UTF-16LE'IN', _UTF-16LE'WI', _UTF-16LE'MO', _UTF-16LE'WV'), =($10, _UTF-16LE'United States'), IS NOT NULL($0))]) HiveTableScan(table=[[default, customer_address]], table:alias=[customer_address]) - HiveJoin(condition=[=($0, $7)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(cd_demo_sk=[$0], cd_marital_status=[CAST(_UTF-16LE'M'):VARCHAR(2147483647) CHARACTER SET "UTF-16LE" COLLATE "ISO-8859-1$en_US$primary"], cd_education_status=[CAST(_UTF-16LE'4 yr Degree'):VARCHAR(2147483647) CHARACTER SET "UTF-16LE" COLLATE "ISO-8859-1$en_US$primary"]) - HiveFilter(condition=[AND(=($2, _UTF-16LE'M'), =($3, _UTF-16LE'4 yr Degree'), IS NOT NULL($0))]) - HiveTableScan(table=[[default, customer_demographics]], table:alias=[customer_demographics]) - HiveJoin(condition=[=($3, $0)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(d_date_sk=[$0], d_year=[CAST(1998):INTEGER]) + HiveJoin(condition=[=($0, $6)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(s_store_sk=[$0]) + HiveFilter(condition=[IS NOT NULL($0)]) + HiveTableScan(table=[[default, store]], table:alias=[store]) + HiveJoin(condition=[=($2, $0)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(=($6, 1998), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) - HiveJoin(condition=[=($0, $4)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(s_store_sk=[$0]) - HiveFilter(condition=[IS NOT NULL($0)]) - HiveTableScan(table=[[default, store]], table:alias=[store]) - HiveProject(ss_sold_date_sk=[$0], ss_cdemo_sk=[$4], ss_addr_sk=[$6], ss_store_sk=[$7], ss_quantity=[$10], ss_sales_price=[$13], ss_net_profit=[$22]) + HiveJoin(condition=[=($0, $2)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(cd_demo_sk=[$0]) + HiveFilter(condition=[AND(=($2, _UTF-16LE'M'), =($3, _UTF-16LE'4 yr Degree'), IS NOT NULL($0))]) + HiveTableScan(table=[[default, customer_demographics]], table:alias=[customer_demographics]) + HiveProject(ss_sold_date_sk=[$0], ss_cdemo_sk=[$4], ss_addr_sk=[$6], ss_store_sk=[$7], ss_quantity=[$10], BETWEEN=[BETWEEN(false, $22, 0, 2000)], BETWEEN6=[BETWEEN(false, $22, 150, 3000)], BETWEEN7=[BETWEEN(false, $22, 50, 25000)]) HiveFilter(condition=[AND(OR(BETWEEN(false, $13, 100, 150), BETWEEN(false, $13, 50, 100), BETWEEN(false, $13, 150, 200)), OR(BETWEEN(false, $22, 0, 2000), BETWEEN(false, $22, 150, 3000), BETWEEN(false, $22, 50, 25000)), IS NOT NULL($7), IS NOT NULL($4), IS NOT NULL($6), IS NOT NULL($0))]) HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) diff --git ql/src/test/results/clientpositive/perf/tez/cbo_query49.q.out ql/src/test/results/clientpositive/perf/tez/cbo_query49.q.out index 9c31d615f91..1300dd92af7 100644 --- ql/src/test/results/clientpositive/perf/tez/cbo_query49.q.out +++ ql/src/test/results/clientpositive/perf/tez/cbo_query49.q.out @@ -279,52 +279,49 @@ HiveSortLimit(sort0=[$0], sort1=[$3], sort2=[$4], dir0=[ASC], dir1=[ASC], dir2=[ HiveProject(channel=[_UTF-16LE'web'], item=[$0], return_ratio=[$1], return_rank=[$2], currency_rank=[$3]) HiveFilter(condition=[OR(<=($2, 10), <=($3, 10))]) HiveProject(item=[$0], return_ratio=[/(CAST($1):DECIMAL(15, 4), CAST($2):DECIMAL(15, 4))], rank_window_0=[rank() OVER (PARTITION BY 0 ORDER BY /(CAST($1):DECIMAL(15, 4), CAST($2):DECIMAL(15, 4)) NULLS LAST ROWS BETWEEN 2147483647 FOLLOWING AND 2147483647 PRECEDING)], rank_window_1=[rank() OVER (PARTITION BY 0 ORDER BY /(CAST($3):DECIMAL(15, 4), CAST($4):DECIMAL(15, 4)) NULLS LAST ROWS BETWEEN 2147483647 FOLLOWING AND 2147483647 PRECEDING)]) - HiveProject($f0=[$0], $f1=[$1], $f2=[$2], $f3=[$3], $f4=[$4]) - HiveAggregate(group=[{0}], agg#0=[sum($1)], agg#1=[sum($2)], agg#2=[sum($3)], agg#3=[sum($4)]) - HiveProject($f0=[$5], $f1=[CASE(IS NOT NULL($2), $2, 0)], $f2=[CASE(IS NOT NULL($7), $7, 0)], $f3=[CASE(IS NOT NULL($3), $3, 0)], $f4=[CASE(IS NOT NULL($8), $8, 0)]) - HiveJoin(condition=[AND(=($6, $1), =($5, $0))], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(wr_item_sk=[$2], wr_order_number=[$13], wr_return_quantity=[$14], wr_return_amt=[$15]) - HiveFilter(condition=[AND(>($15, 10000), IS NOT NULL($13), IS NOT NULL($2))]) - HiveTableScan(table=[[default, web_returns]], table:alias=[wr]) - HiveJoin(condition=[=($0, $6)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(ws_sold_date_sk=[$0], ws_item_sk=[$3], ws_order_number=[$17], ws_quantity=[$18], ws_net_paid=[$29], ws_net_profit=[$33]) - HiveFilter(condition=[AND(>($33, 1), >($29, 0), >($18, 0), IS NOT NULL($17), IS NOT NULL($3), IS NOT NULL($0))]) - HiveTableScan(table=[[default, web_sales]], table:alias=[ws]) - HiveProject(d_date_sk=[$0], d_year=[CAST(2000):INTEGER], d_moy=[CAST(12):INTEGER]) - HiveFilter(condition=[AND(=($6, 2000), =($8, 12), IS NOT NULL($0))]) - HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) + HiveProject(ws_item_sk=[$0], $f1=[$1], $f2=[$2], $f3=[$3], $f4=[$4]) + HiveAggregate(group=[{5}], agg#0=[sum($2)], agg#1=[sum($7)], agg#2=[sum($3)], agg#3=[sum($8)]) + HiveJoin(condition=[AND(=($6, $1), =($5, $0))], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(wr_item_sk=[$2], wr_order_number=[$13], CASE=[CASE(IS NOT NULL($14), $14, 0)], CASE3=[CASE(IS NOT NULL($15), $15, 0)]) + HiveFilter(condition=[AND(>($15, 10000), IS NOT NULL($13), IS NOT NULL($2))]) + HiveTableScan(table=[[default, web_returns]], table:alias=[wr]) + HiveJoin(condition=[=($0, $5)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(ws_sold_date_sk=[$0], ws_item_sk=[$3], ws_order_number=[$17], CASE=[CASE(IS NOT NULL($18), $18, 0)], CASE4=[CASE(IS NOT NULL($29), $29, 0)]) + HiveFilter(condition=[AND(>($33, 1), >($29, 0), >($18, 0), IS NOT NULL($17), IS NOT NULL($3), IS NOT NULL($0))]) + HiveTableScan(table=[[default, web_sales]], table:alias=[ws]) + HiveProject(d_date_sk=[$0]) + HiveFilter(condition=[AND(=($6, 2000), =($8, 12), IS NOT NULL($0))]) + HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) HiveProject(channel=[_UTF-16LE'catalog'], item=[$0], return_ratio=[$1], return_rank=[$2], currency_rank=[$3]) HiveFilter(condition=[OR(<=($2, 10), <=($3, 10))]) HiveProject(item=[$0], return_ratio=[/(CAST($1):DECIMAL(15, 4), CAST($2):DECIMAL(15, 4))], rank_window_0=[rank() OVER (PARTITION BY 0 ORDER BY /(CAST($1):DECIMAL(15, 4), CAST($2):DECIMAL(15, 4)) NULLS LAST ROWS BETWEEN 2147483647 FOLLOWING AND 2147483647 PRECEDING)], rank_window_1=[rank() OVER (PARTITION BY 0 ORDER BY /(CAST($3):DECIMAL(15, 4), CAST($4):DECIMAL(15, 4)) NULLS LAST ROWS BETWEEN 2147483647 FOLLOWING AND 2147483647 PRECEDING)]) - HiveProject($f0=[$0], $f1=[$1], $f2=[$2], $f3=[$3], $f4=[$4]) - HiveAggregate(group=[{0}], agg#0=[sum($1)], agg#1=[sum($2)], agg#2=[sum($3)], agg#3=[sum($4)]) - HiveProject($f0=[$5], $f1=[CASE(IS NOT NULL($2), $2, 0)], $f2=[CASE(IS NOT NULL($7), $7, 0)], $f3=[CASE(IS NOT NULL($3), $3, 0)], $f4=[CASE(IS NOT NULL($8), $8, 0)]) - HiveJoin(condition=[AND(=($6, $1), =($5, $0))], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(cr_item_sk=[$2], cr_order_number=[$16], cr_return_quantity=[$17], cr_return_amount=[$18]) - HiveFilter(condition=[AND(>($18, 10000), IS NOT NULL($16), IS NOT NULL($2))]) - HiveTableScan(table=[[default, catalog_returns]], table:alias=[cr]) - HiveJoin(condition=[=($0, $6)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(cs_sold_date_sk=[$0], cs_item_sk=[$15], cs_order_number=[$17], cs_quantity=[$18], cs_net_paid=[$29], cs_net_profit=[$33]) - HiveFilter(condition=[AND(>($33, 1), >($29, 0), >($18, 0), IS NOT NULL($17), IS NOT NULL($15), IS NOT NULL($0))]) - HiveTableScan(table=[[default, catalog_sales]], table:alias=[cs]) - HiveProject(d_date_sk=[$0], d_year=[CAST(2000):INTEGER], d_moy=[CAST(12):INTEGER]) - HiveFilter(condition=[AND(=($6, 2000), =($8, 12), IS NOT NULL($0))]) - HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) + HiveProject(cs_item_sk=[$0], $f1=[$1], $f2=[$2], $f3=[$3], $f4=[$4]) + HiveAggregate(group=[{5}], agg#0=[sum($2)], agg#1=[sum($7)], agg#2=[sum($3)], agg#3=[sum($8)]) + HiveJoin(condition=[AND(=($6, $1), =($5, $0))], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(cr_item_sk=[$2], cr_order_number=[$16], CASE=[CASE(IS NOT NULL($17), $17, 0)], CASE3=[CASE(IS NOT NULL($18), $18, 0)]) + HiveFilter(condition=[AND(>($18, 10000), IS NOT NULL($16), IS NOT NULL($2))]) + HiveTableScan(table=[[default, catalog_returns]], table:alias=[cr]) + HiveJoin(condition=[=($0, $5)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(cs_sold_date_sk=[$0], cs_item_sk=[$15], cs_order_number=[$17], CASE=[CASE(IS NOT NULL($18), $18, 0)], CASE4=[CASE(IS NOT NULL($29), $29, 0)]) + HiveFilter(condition=[AND(>($33, 1), >($29, 0), >($18, 0), IS NOT NULL($17), IS NOT NULL($15), IS NOT NULL($0))]) + HiveTableScan(table=[[default, catalog_sales]], table:alias=[cs]) + HiveProject(d_date_sk=[$0]) + HiveFilter(condition=[AND(=($6, 2000), =($8, 12), IS NOT NULL($0))]) + HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) HiveProject(channel=[_UTF-16LE'store'], item=[$0], return_ratio=[$1], return_rank=[$2], currency_rank=[$3]) HiveFilter(condition=[OR(<=($2, 10), <=($3, 10))]) HiveProject(item=[$0], return_ratio=[/(CAST($1):DECIMAL(15, 4), CAST($2):DECIMAL(15, 4))], rank_window_0=[rank() OVER (PARTITION BY 0 ORDER BY /(CAST($1):DECIMAL(15, 4), CAST($2):DECIMAL(15, 4)) NULLS LAST ROWS BETWEEN 2147483647 FOLLOWING AND 2147483647 PRECEDING)], rank_window_1=[rank() OVER (PARTITION BY 0 ORDER BY /(CAST($3):DECIMAL(15, 4), CAST($4):DECIMAL(15, 4)) NULLS LAST ROWS BETWEEN 2147483647 FOLLOWING AND 2147483647 PRECEDING)]) - HiveProject($f0=[$0], $f1=[$1], $f2=[$2], $f3=[$3], $f4=[$4]) - HiveAggregate(group=[{0}], agg#0=[sum($1)], agg#1=[sum($2)], agg#2=[sum($3)], agg#3=[sum($4)]) - HiveProject($f0=[$5], $f1=[CASE(IS NOT NULL($2), $2, 0)], $f2=[CASE(IS NOT NULL($7), $7, 0)], $f3=[CASE(IS NOT NULL($3), $3, 0)], $f4=[CASE(IS NOT NULL($8), $8, 0)]) - HiveJoin(condition=[AND(=($6, $1), =($5, $0))], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(sr_item_sk=[$2], sr_ticket_number=[$9], sr_return_quantity=[$10], sr_return_amt=[$11]) - HiveFilter(condition=[AND(>($11, 10000), IS NOT NULL($9), IS NOT NULL($2))]) - HiveTableScan(table=[[default, store_returns]], table:alias=[sr]) - HiveJoin(condition=[=($0, $6)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(ss_sold_date_sk=[$0], ss_item_sk=[$2], ss_ticket_number=[$9], ss_quantity=[$10], ss_net_paid=[$20], ss_net_profit=[$22]) - HiveFilter(condition=[AND(>($22, 1), >($20, 0), >($10, 0), IS NOT NULL($9), IS NOT NULL($2), IS NOT NULL($0))]) - HiveTableScan(table=[[default, store_sales]], table:alias=[sts]) - HiveProject(d_date_sk=[$0], d_year=[CAST(2000):INTEGER], d_moy=[CAST(12):INTEGER]) - HiveFilter(condition=[AND(=($6, 2000), =($8, 12), IS NOT NULL($0))]) - HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) + HiveProject(ss_item_sk=[$0], $f1=[$1], $f2=[$2], $f3=[$3], $f4=[$4]) + HiveAggregate(group=[{5}], agg#0=[sum($2)], agg#1=[sum($7)], agg#2=[sum($3)], agg#3=[sum($8)]) + HiveJoin(condition=[AND(=($6, $1), =($5, $0))], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(sr_item_sk=[$2], sr_ticket_number=[$9], CASE=[CASE(IS NOT NULL($10), $10, 0)], CASE3=[CASE(IS NOT NULL($11), $11, 0)]) + HiveFilter(condition=[AND(>($11, 10000), IS NOT NULL($9), IS NOT NULL($2))]) + HiveTableScan(table=[[default, store_returns]], table:alias=[sr]) + HiveJoin(condition=[=($0, $5)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(ss_sold_date_sk=[$0], ss_item_sk=[$2], ss_ticket_number=[$9], CASE=[CASE(IS NOT NULL($10), $10, 0)], CASE4=[CASE(IS NOT NULL($20), $20, 0)]) + HiveFilter(condition=[AND(>($22, 1), >($20, 0), >($10, 0), IS NOT NULL($9), IS NOT NULL($2), IS NOT NULL($0))]) + HiveTableScan(table=[[default, store_sales]], table:alias=[sts]) + HiveProject(d_date_sk=[$0]) + HiveFilter(condition=[AND(=($6, 2000), =($8, 12), IS NOT NULL($0))]) + HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) diff --git ql/src/test/results/clientpositive/perf/tez/cbo_query5.q.out ql/src/test/results/clientpositive/perf/tez/cbo_query5.q.out index a82f0119a23..e78c3e59171 100644 --- ql/src/test/results/clientpositive/perf/tez/cbo_query5.q.out +++ ql/src/test/results/clientpositive/perf/tez/cbo_query5.q.out @@ -281,8 +281,8 @@ HiveSortLimit(sort0=[$0], sort1=[$1], dir0=[ASC], dir1=[ASC], fetch=[100]) HiveProject(channel=[$0], id=[$1], sales=[$2], returns=[$3], profit=[$4]) HiveUnion(all=[true]) HiveProject(channel=[_UTF-16LE'store channel'], id=[||(_UTF-16LE'store', $0)], sales=[$1], returns=[$3], profit=[-($2, $4)]) - HiveAggregate(group=[{9}], agg#0=[sum($2)], agg#1=[sum($3)], agg#2=[sum($4)], agg#3=[sum($5)]) - HiveJoin(condition=[=($0, $8)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveAggregate(group=[{8}], agg#0=[sum($2)], agg#1=[sum($3)], agg#2=[sum($4)], agg#3=[sum($5)]) + HiveJoin(condition=[=($0, $7)], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($1, $6)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(store_sk=[$0], date_sk=[$1], sales_price=[$2], profit=[$3], return_amt=[$4], net_loss=[$5]) HiveUnion(all=[true]) @@ -292,7 +292,7 @@ HiveSortLimit(sort0=[$0], sort1=[$1], dir0=[ASC], dir1=[ASC], fetch=[100]) HiveProject(store_sk=[$7], date_sk=[$0], sales_price=[CAST(0):DECIMAL(7, 2)], profit=[CAST(0):DECIMAL(7, 2)], return_amt=[$11], net_loss=[$19]) HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($7))]) HiveTableScan(table=[[default, store_returns]], table:alias=[store_returns]) - HiveProject(d_date_sk=[$0], d_date=[$2]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(BETWEEN(false, CAST($2):TIMESTAMP(9), 1998-08-04 00:00:00, 1998-08-18 00:00:00), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) HiveProject(s_store_sk=[$0], s_store_id=[$1]) @@ -313,12 +313,12 @@ HiveSortLimit(sort0=[$0], sort1=[$1], dir0=[ASC], dir1=[ASC], fetch=[100]) HiveProject(page_sk=[$12], date_sk=[$0], sales_price=[CAST(0):DECIMAL(7, 2)], profit=[CAST(0):DECIMAL(7, 2)], return_amt=[$18], net_loss=[$26]) HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($12))]) HiveTableScan(table=[[default, catalog_returns]], table:alias=[catalog_returns]) - HiveProject(d_date_sk=[$0], d_date=[$2]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(BETWEEN(false, CAST($2):TIMESTAMP(9), 1998-08-04 00:00:00, 1998-08-18 00:00:00), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) HiveProject(channel=[_UTF-16LE'web channel'], id=[||(_UTF-16LE'web_site', $0)], sales=[$1], returns=[$3], profit=[-($2, $4)]) - HiveAggregate(group=[{9}], agg#0=[sum($2)], agg#1=[sum($3)], agg#2=[sum($4)], agg#3=[sum($5)]) - HiveJoin(condition=[=($0, $8)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveAggregate(group=[{8}], agg#0=[sum($2)], agg#1=[sum($3)], agg#2=[sum($4)], agg#3=[sum($5)]) + HiveJoin(condition=[=($0, $7)], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($1, $6)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(wsr_web_site_sk=[$0], date_sk=[$1], sales_price=[$2], profit=[$3], return_amt=[$4], net_loss=[$5]) HiveUnion(all=[true]) @@ -333,7 +333,7 @@ HiveSortLimit(sort0=[$0], sort1=[$1], dir0=[ASC], dir1=[ASC], fetch=[100]) HiveProject(wr_returned_date_sk=[$0], wr_item_sk=[$2], wr_order_number=[$13], wr_return_amt=[$15], wr_net_loss=[$23]) HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($2), IS NOT NULL($13))]) HiveTableScan(table=[[default, web_returns]], table:alias=[web_returns]) - HiveProject(d_date_sk=[$0], d_date=[$2]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(BETWEEN(false, CAST($2):TIMESTAMP(9), 1998-08-04 00:00:00, 1998-08-18 00:00:00), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) HiveProject(web_site_sk=[$0], web_site_id=[$1]) diff --git ql/src/test/results/clientpositive/perf/tez/cbo_query50.q.out ql/src/test/results/clientpositive/perf/tez/cbo_query50.q.out index 2be59c1d4e3..becffde8202 100644 --- ql/src/test/results/clientpositive/perf/tez/cbo_query50.q.out +++ ql/src/test/results/clientpositive/perf/tez/cbo_query50.q.out @@ -128,9 +128,9 @@ CBO PLAN: HiveSortLimit(sort0=[$0], sort1=[$1], sort2=[$2], sort3=[$3], sort4=[$4], sort5=[$5], sort6=[$6], sort7=[$7], sort8=[$8], sort9=[$9], dir0=[ASC], dir1=[ASC], dir2=[ASC], dir3=[ASC], dir4=[ASC], dir5=[ASC], dir6=[ASC], dir7=[ASC], dir8=[ASC], dir9=[ASC], fetch=[100]) HiveProject($f0=[$0], $f1=[$1], $f2=[$2], $f3=[$3], $f4=[$4], $f5=[$5], $f6=[$6], $f7=[$7], $f8=[$8], $f9=[$9], $f10=[$10], $f11=[$11], $f12=[$12], $f13=[$13], $f14=[$14]) HiveAggregate(group=[{0, 1, 2, 3, 4, 5, 6, 7, 8, 9}], agg#0=[sum($10)], agg#1=[sum($11)], agg#2=[sum($12)], agg#3=[sum($13)], agg#4=[sum($14)]) - HiveProject($f0=[$14], $f1=[$15], $f2=[$16], $f3=[$17], $f4=[$18], $f5=[$19], $f6=[$20], $f7=[$21], $f8=[$22], $f9=[$23], $f10=[CASE(<=(-($5, $0), 30), 1, 0)], $f11=[CASE(AND(>(-($5, $0), 30), <=(-($5, $0), 60)), 1, 0)], $f12=[CASE(AND(>(-($5, $0), 60), <=(-($5, $0), 90)), 1, 0)], $f13=[CASE(AND(>(-($5, $0), 90), <=(-($5, $0), 120)), 1, 0)], $f14=[CASE(>(-($5, $0), 120), 1, 0)]) - HiveJoin(condition=[=($3, $13)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveJoin(condition=[=($0, $12)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject($f0=[$12], $f1=[$13], $f2=[$14], $f3=[$15], $f4=[$16], $f5=[$17], $f6=[$18], $f7=[$19], $f8=[$20], $f9=[$21], $f10=[CASE(<=(-($5, $0), 30), 1, 0)], $f11=[CASE(AND(>(-($5, $0), 30), <=(-($5, $0), 60)), 1, 0)], $f12=[CASE(AND(>(-($5, $0), 60), <=(-($5, $0), 90)), 1, 0)], $f13=[CASE(AND(>(-($5, $0), 90), <=(-($5, $0), 120)), 1, 0)], $f14=[CASE(>(-($5, $0), 120), 1, 0)]) + HiveJoin(condition=[=($3, $11)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($0, $10)], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[AND(AND(=($4, $8), =($1, $6)), =($2, $7))], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(ss_sold_date_sk=[$0], ss_item_sk=[$2], ss_customer_sk=[$3], ss_store_sk=[$7], ss_ticket_number=[$9]) HiveFilter(condition=[AND(IS NOT NULL($9), IS NOT NULL($2), IS NOT NULL($3), IS NOT NULL($7), IS NOT NULL($0))]) @@ -139,7 +139,7 @@ HiveSortLimit(sort0=[$0], sort1=[$1], sort2=[$2], sort3=[$3], sort4=[$4], sort5= HiveProject(sr_returned_date_sk=[$0], sr_item_sk=[$2], sr_customer_sk=[$3], sr_ticket_number=[$9]) HiveFilter(condition=[AND(IS NOT NULL($9), IS NOT NULL($2), IS NOT NULL($3), IS NOT NULL($0))]) HiveTableScan(table=[[default, store_returns]], table:alias=[store_returns]) - HiveProject(d_date_sk=[$0], d_year=[CAST(2000):INTEGER], d_moy=[CAST(9):INTEGER]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(=($6, 2000), =($8, 9), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[d2]) HiveProject(d_date_sk=[$0]) diff --git ql/src/test/results/clientpositive/perf/tez/cbo_query51.q.out ql/src/test/results/clientpositive/perf/tez/cbo_query51.q.out index fed86777370..79c5f992ce8 100644 --- ql/src/test/results/clientpositive/perf/tez/cbo_query51.q.out +++ ql/src/test/results/clientpositive/perf/tez/cbo_query51.q.out @@ -108,7 +108,7 @@ HiveSortLimit(sort0=[$0], sort1=[$1], dir0=[ASC], dir1=[ASC], fetch=[100]) HiveProject(ss_sold_date_sk=[$0], ss_item_sk=[$2], ss_sales_price=[$13]) HiveFilter(condition=[AND(IS NOT NULL($2), IS NOT NULL($0))]) HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) - HiveProject(d_date_sk=[$0], d_date=[$2], d_month_seq=[$3]) + HiveProject(d_date_sk=[$0], d_date=[$2]) HiveFilter(condition=[AND(BETWEEN(false, $3, 1212, 1223), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) HiveProject((tok_table_or_col ws_item_sk)=[$0], (tok_table_or_col d_date)=[$1], sum_window_0=[$2]) @@ -119,7 +119,7 @@ HiveSortLimit(sort0=[$0], sort1=[$1], dir0=[ASC], dir1=[ASC], fetch=[100]) HiveProject(ws_sold_date_sk=[$0], ws_item_sk=[$3], ws_sales_price=[$21]) HiveFilter(condition=[AND(IS NOT NULL($3), IS NOT NULL($0))]) HiveTableScan(table=[[default, web_sales]], table:alias=[web_sales]) - HiveProject(d_date_sk=[$0], d_date=[$2], d_month_seq=[$3]) + HiveProject(d_date_sk=[$0], d_date=[$2]) HiveFilter(condition=[AND(BETWEEN(false, $3, 1212, 1223), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) diff --git ql/src/test/results/clientpositive/perf/tez/cbo_query52.q.out ql/src/test/results/clientpositive/perf/tez/cbo_query52.q.out index 627b8b05d1d..27cb4eb3c0c 100644 --- ql/src/test/results/clientpositive/perf/tez/cbo_query52.q.out +++ ql/src/test/results/clientpositive/perf/tez/cbo_query52.q.out @@ -52,16 +52,16 @@ CBO PLAN: HiveProject(d_year=[CAST(1998):INTEGER], brand_id=[$0], brand=[$1], ext_price=[$2]) HiveSortLimit(sort0=[$2], sort1=[$0], dir0=[DESC-nulls-last], dir1=[ASC], fetch=[100]) HiveProject(i_brand_id=[$0], i_brand=[$1], $f2=[$2]) - HiveAggregate(group=[{7, 8}], agg#0=[sum($2)]) - HiveJoin(condition=[=($1, $6)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveAggregate(group=[{5, 6}], agg#0=[sum($2)]) + HiveJoin(condition=[=($1, $4)], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($3, $0)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(ss_sold_date_sk=[$0], ss_item_sk=[$2], ss_ext_sales_price=[$15]) HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($2))]) HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) - HiveProject(d_date_sk=[$0], d_year=[CAST(1998):INTEGER], d_moy=[CAST(12):INTEGER]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(=($8, 12), =($6, 1998), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[dt]) - HiveProject(i_item_sk=[$0], i_brand_id=[$7], i_brand=[$8], i_manager_id=[CAST(1):INTEGER]) + HiveProject(i_item_sk=[$0], i_brand_id=[$7], i_brand=[$8]) HiveFilter(condition=[AND(=($20, 1), IS NOT NULL($0))]) HiveTableScan(table=[[default, item]], table:alias=[item]) diff --git ql/src/test/results/clientpositive/perf/tez/cbo_query53.q.out ql/src/test/results/clientpositive/perf/tez/cbo_query53.q.out index 56b1ba286d1..9b424280971 100644 --- ql/src/test/results/clientpositive/perf/tez/cbo_query53.q.out +++ ql/src/test/results/clientpositive/perf/tez/cbo_query53.q.out @@ -68,20 +68,20 @@ HiveSortLimit(sort0=[$2], sort1=[$1], sort2=[$0], dir0=[ASC], dir1=[ASC], dir2=[ HiveFilter(condition=[CASE(>($2, 0), >(/(ABS(-($1, $2)), $2), 0.1), null)]) HiveProject((tok_table_or_col i_manufact_id)=[$0], (tok_function sum (tok_table_or_col ss_sales_price))=[$2], avg_window_0=[avg($2) OVER (PARTITION BY $0 ORDER BY $0 NULLS FIRST ROWS BETWEEN 2147483647 FOLLOWING AND 2147483647 PRECEDING)]) HiveProject(i_manufact_id=[$0], d_qoy=[$1], $f2=[$2]) - HiveAggregate(group=[{9, 12}], agg#0=[sum($4)]) + HiveAggregate(group=[{6, 8}], agg#0=[sum($4)]) HiveJoin(condition=[=($3, $0)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(s_store_sk=[$0]) HiveFilter(condition=[IS NOT NULL($0)]) HiveTableScan(table=[[default, store]], table:alias=[store]) - HiveJoin(condition=[=($0, $9)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($0, $6)], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($1, $4)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(ss_sold_date_sk=[$0], ss_item_sk=[$2], ss_store_sk=[$7], ss_sales_price=[$13]) HiveFilter(condition=[AND(IS NOT NULL($2), IS NOT NULL($0), IS NOT NULL($7))]) HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) - HiveProject(i_item_sk=[$0], i_brand=[$8], i_class=[$10], i_category=[$12], i_manufact_id=[$13]) + HiveProject(i_item_sk=[$0], i_manufact_id=[$13]) HiveFilter(condition=[AND(IN($10, _UTF-16LE'personal', _UTF-16LE'portable', _UTF-16LE'reference', _UTF-16LE'self-help', _UTF-16LE'accessories', _UTF-16LE'classical', _UTF-16LE'fragrances', _UTF-16LE'pants'), IN($8, _UTF-16LE'scholaramalgamalg #14', _UTF-16LE'scholaramalgamalg #7', _UTF-16LE'exportiunivamalg #9', _UTF-16LE'scholaramalgamalg #9', _UTF-16LE'amalgimporto #1', _UTF-16LE'edu packscholar #1', _UTF-16LE'exportiimporto #1', _UTF-16LE'importoamalg #1'), IN($12, _UTF-16LE'Books', _UTF-16LE'Children', _UTF-16LE'Electronics', _UTF-16LE'Women', _UTF-16LE'Music', _UTF-16LE'Men'), OR(AND(IN($12, _UTF-16LE'Books', _UTF-16LE'Children', _UTF-16LE'Electronics'), IN($10, _UTF-16LE'personal', _UTF-16LE'portable', _UTF-16LE'reference', _UTF-16LE'self-help'), IN($8, _UTF-16LE'scholaramalgamalg #14', _UTF-16LE'scholaramalgamalg #7', _UTF-16LE'exportiunivamalg #9', _UTF-16LE'scholaramalgamalg #9')), AND(IN($12, _UTF-16LE'Women', _UTF-16LE'Music', _UTF-16LE'Men'), IN($10, _UTF-16LE'accessories', _UTF-16LE'classical', _UTF-16LE'fragrances', _UTF-16LE'pants'), IN($8, _UTF-16LE'amalgimporto #1', _UTF-16LE'edu packscholar #1', _UTF-16LE'exportiimporto #1', _UTF-16LE'importoamalg #1'))), IS NOT NULL($0))]) HiveTableScan(table=[[default, item]], table:alias=[item]) - HiveProject(d_date_sk=[$0], d_month_seq=[$3], d_qoy=[$10]) + HiveProject(d_date_sk=[$0], d_qoy=[$10]) HiveFilter(condition=[AND(IN($3, 1212, 1213, 1214, 1215, 1216, 1217, 1218, 1219, 1220, 1221, 1222, 1223), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) diff --git ql/src/test/results/clientpositive/perf/tez/cbo_query54.q.out ql/src/test/results/clientpositive/perf/tez/cbo_query54.q.out index eaf25363b16..6d3d037c481 100644 --- ql/src/test/results/clientpositive/perf/tez/cbo_query54.q.out +++ ql/src/test/results/clientpositive/perf/tez/cbo_query54.q.out @@ -165,7 +165,7 @@ HiveSortLimit(sort0=[$0], sort1=[$1], dir0=[ASC], dir1=[ASC], fetch=[100]) HiveProject(c_customer_sk=[$0], c_current_addr_sk=[$4]) HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($4))]) HiveTableScan(table=[[default, customer]], table:alias=[customer]) - HiveJoin(condition=[=($2, $6)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($2, $4)], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($0, $3)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(cs_sold_date_sk=[$0], cs_bill_customer_sk=[$1], cs_item_sk=[$2]) HiveUnion(all=[true]) @@ -175,10 +175,10 @@ HiveSortLimit(sort0=[$0], sort1=[$1], dir0=[ASC], dir1=[ASC], fetch=[100]) HiveProject(sold_date_sk=[$0], customer_sk=[$4], item_sk=[$3]) HiveFilter(condition=[AND(IS NOT NULL($3), IS NOT NULL($0), IS NOT NULL($4))]) HiveTableScan(table=[[default, web_sales]], table:alias=[web_sales]) - HiveProject(d_date_sk=[$0], d_year=[CAST(1999):INTEGER], d_moy=[CAST(3):INTEGER]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(=($8, 3), =($6, 1999), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) - HiveProject(i_item_sk=[$0], i_class=[CAST(_UTF-16LE'consignment'):VARCHAR(2147483647) CHARACTER SET "UTF-16LE" COLLATE "ISO-8859-1$en_US$primary"], i_category=[CAST(_UTF-16LE'Jewelry'):VARCHAR(2147483647) CHARACTER SET "UTF-16LE" COLLATE "ISO-8859-1$en_US$primary"]) + HiveProject(i_item_sk=[$0]) HiveFilter(condition=[AND(=($12, _UTF-16LE'Jewelry'), =($10, _UTF-16LE'consignment'), IS NOT NULL($0))]) HiveTableScan(table=[[default, item]], table:alias=[item]) HiveProject(cnt=[$0]) diff --git ql/src/test/results/clientpositive/perf/tez/cbo_query55.q.out ql/src/test/results/clientpositive/perf/tez/cbo_query55.q.out index 4182de0b576..24c93f6adcb 100644 --- ql/src/test/results/clientpositive/perf/tez/cbo_query55.q.out +++ ql/src/test/results/clientpositive/perf/tez/cbo_query55.q.out @@ -36,16 +36,16 @@ CBO PLAN: HiveProject(brand_id=[$0], brand=[$1], ext_price=[$2]) HiveSortLimit(sort0=[$2], sort1=[$3], dir0=[DESC-nulls-last], dir1=[ASC], fetch=[100]) HiveProject(brand_id=[$0], brand=[$1], ext_price=[$2], (tok_table_or_col i_brand_id)=[$0]) - HiveAggregate(group=[{7, 8}], agg#0=[sum($2)]) - HiveJoin(condition=[=($1, $6)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveAggregate(group=[{5, 6}], agg#0=[sum($2)]) + HiveJoin(condition=[=($1, $4)], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($3, $0)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(ss_sold_date_sk=[$0], ss_item_sk=[$2], ss_ext_sales_price=[$15]) HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($2))]) HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) - HiveProject(d_date_sk=[$0], d_year=[CAST(2001):INTEGER], d_moy=[CAST(12):INTEGER]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(=($8, 12), =($6, 2001), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) - HiveProject(i_item_sk=[$0], i_brand_id=[$7], i_brand=[$8], i_manager_id=[CAST(36):INTEGER]) + HiveProject(i_item_sk=[$0], i_brand_id=[$7], i_brand=[$8]) HiveFilter(condition=[AND(=($20, 36), IS NOT NULL($0))]) HiveTableScan(table=[[default, item]], table:alias=[item]) diff --git ql/src/test/results/clientpositive/perf/tez/cbo_query56.q.out ql/src/test/results/clientpositive/perf/tez/cbo_query56.q.out index 579d06a203b..d01dbcd1540 100644 --- ql/src/test/results/clientpositive/perf/tez/cbo_query56.q.out +++ ql/src/test/results/clientpositive/perf/tez/cbo_query56.q.out @@ -153,8 +153,8 @@ HiveSortLimit(sort0=[$1], dir0=[ASC], fetch=[100]) HiveProject(i_item_id=[$0], $f1=[$1]) HiveUnion(all=[true]) HiveProject(i_item_id=[$0], $f1=[$1]) - HiveAggregate(group=[{1}], agg#0=[sum($8)]) - HiveJoin(condition=[=($6, $0)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveAggregate(group=[{1}], agg#0=[sum($7)]) + HiveJoin(condition=[=($5, $0)], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($1, $2)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(i_item_sk=[$0], i_item_id=[$1]) HiveFilter(condition=[AND(IS NOT NULL($1), IS NOT NULL($0))]) @@ -163,21 +163,21 @@ HiveSortLimit(sort0=[$1], dir0=[ASC], fetch=[100]) HiveAggregate(group=[{1}]) HiveFilter(condition=[AND(IN($17, _UTF-16LE'orchid', _UTF-16LE'chiffon', _UTF-16LE'lace'), IS NOT NULL($1))]) HiveTableScan(table=[[default, item]], table:alias=[item]) - HiveProject(ca_address_sk=[$0], ca_gmt_offset=[$1], ss_sold_date_sk=[$2], ss_item_sk=[$3], ss_addr_sk=[$4], ss_ext_sales_price=[$5], d_date_sk=[$6], d_year=[$7], d_moy=[$8]) - HiveJoin(condition=[=($4, $0)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(ca_address_sk=[$0], ca_gmt_offset=[CAST(-8):DECIMAL(5, 2)]) + HiveProject(ca_address_sk=[$0], ss_sold_date_sk=[$1], ss_item_sk=[$2], ss_addr_sk=[$3], ss_ext_sales_price=[$4], d_date_sk=[$5]) + HiveJoin(condition=[=($3, $0)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(ca_address_sk=[$0]) HiveFilter(condition=[AND(=($11, -8), IS NOT NULL($0))]) HiveTableScan(table=[[default, customer_address]], table:alias=[customer_address]) HiveJoin(condition=[=($0, $4)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(ss_sold_date_sk=[$0], ss_item_sk=[$2], ss_addr_sk=[$6], ss_ext_sales_price=[$15]) HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($6), IS NOT NULL($2))]) HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) - HiveProject(d_date_sk=[$0], d_year=[CAST(2000):INTEGER], d_moy=[CAST(1):INTEGER]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(=($6, 2000), =($8, 1), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) HiveProject(i_item_id=[$0], $f1=[$1]) - HiveAggregate(group=[{1}], agg#0=[sum($8)]) - HiveJoin(condition=[=($7, $0)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveAggregate(group=[{1}], agg#0=[sum($7)]) + HiveJoin(condition=[=($6, $0)], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($1, $2)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(i_item_sk=[$0], i_item_id=[$1]) HiveFilter(condition=[AND(IS NOT NULL($1), IS NOT NULL($0))]) @@ -186,21 +186,21 @@ HiveSortLimit(sort0=[$1], dir0=[ASC], fetch=[100]) HiveAggregate(group=[{1}]) HiveFilter(condition=[AND(IN($17, _UTF-16LE'orchid', _UTF-16LE'chiffon', _UTF-16LE'lace'), IS NOT NULL($1))]) HiveTableScan(table=[[default, item]], table:alias=[item]) - HiveProject(ca_address_sk=[$0], ca_gmt_offset=[$1], cs_sold_date_sk=[$2], cs_bill_addr_sk=[$3], cs_item_sk=[$4], cs_ext_sales_price=[$5], d_date_sk=[$6], d_year=[$7], d_moy=[$8]) - HiveJoin(condition=[=($3, $0)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(ca_address_sk=[$0], ca_gmt_offset=[CAST(-8):DECIMAL(5, 2)]) + HiveProject(ca_address_sk=[$0], cs_sold_date_sk=[$1], cs_bill_addr_sk=[$2], cs_item_sk=[$3], cs_ext_sales_price=[$4], d_date_sk=[$5]) + HiveJoin(condition=[=($2, $0)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(ca_address_sk=[$0]) HiveFilter(condition=[AND(=($11, -8), IS NOT NULL($0))]) HiveTableScan(table=[[default, customer_address]], table:alias=[customer_address]) HiveJoin(condition=[=($0, $4)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(cs_sold_date_sk=[$0], cs_bill_addr_sk=[$6], cs_item_sk=[$15], cs_ext_sales_price=[$23]) HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($6), IS NOT NULL($15))]) HiveTableScan(table=[[default, catalog_sales]], table:alias=[catalog_sales]) - HiveProject(d_date_sk=[$0], d_year=[CAST(2000):INTEGER], d_moy=[CAST(1):INTEGER]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(=($6, 2000), =($8, 1), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) HiveProject(i_item_id=[$0], $f1=[$1]) - HiveAggregate(group=[{1}], agg#0=[sum($8)]) - HiveJoin(condition=[=($6, $0)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveAggregate(group=[{1}], agg#0=[sum($7)]) + HiveJoin(condition=[=($5, $0)], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($1, $2)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(i_item_sk=[$0], i_item_id=[$1]) HiveFilter(condition=[AND(IS NOT NULL($1), IS NOT NULL($0))]) @@ -209,16 +209,16 @@ HiveSortLimit(sort0=[$1], dir0=[ASC], fetch=[100]) HiveAggregate(group=[{1}]) HiveFilter(condition=[AND(IN($17, _UTF-16LE'orchid', _UTF-16LE'chiffon', _UTF-16LE'lace'), IS NOT NULL($1))]) HiveTableScan(table=[[default, item]], table:alias=[item]) - HiveProject(ca_address_sk=[$0], ca_gmt_offset=[$1], ws_sold_date_sk=[$2], ws_item_sk=[$3], ws_bill_addr_sk=[$4], ws_ext_sales_price=[$5], d_date_sk=[$6], d_year=[$7], d_moy=[$8]) - HiveJoin(condition=[=($4, $0)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(ca_address_sk=[$0], ca_gmt_offset=[CAST(-8):DECIMAL(5, 2)]) + HiveProject(ca_address_sk=[$0], ws_sold_date_sk=[$1], ws_item_sk=[$2], ws_bill_addr_sk=[$3], ws_ext_sales_price=[$4], d_date_sk=[$5]) + HiveJoin(condition=[=($3, $0)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(ca_address_sk=[$0]) HiveFilter(condition=[AND(=($11, -8), IS NOT NULL($0))]) HiveTableScan(table=[[default, customer_address]], table:alias=[customer_address]) HiveJoin(condition=[=($0, $4)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(ws_sold_date_sk=[$0], ws_item_sk=[$3], ws_bill_addr_sk=[$7], ws_ext_sales_price=[$23]) HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($7), IS NOT NULL($3))]) HiveTableScan(table=[[default, web_sales]], table:alias=[web_sales]) - HiveProject(d_date_sk=[$0], d_year=[CAST(2000):INTEGER], d_moy=[CAST(1):INTEGER]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(=($6, 2000), =($8, 1), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) diff --git ql/src/test/results/clientpositive/perf/tez/cbo_query57.q.out ql/src/test/results/clientpositive/perf/tez/cbo_query57.q.out index e0480e415b3..6c8ef17bc62 100644 --- ql/src/test/results/clientpositive/perf/tez/cbo_query57.q.out +++ ql/src/test/results/clientpositive/perf/tez/cbo_query57.q.out @@ -106,8 +106,8 @@ CBO PLAN: HiveProject(i_category=[$0], i_brand=[$1], d_year=[$2], d_moy=[$3], avg_monthly_sales=[$4], sum_sales=[$5], psum=[$6], nsum=[$7]) HiveSortLimit(sort0=[$8], sort1=[$2], dir0=[ASC], dir1=[ASC], fetch=[100]) HiveProject(i_category=[$10], i_brand=[$11], d_year=[$13], d_moy=[$14], avg_monthly_sales=[$16], sum_sales=[$15], psum=[$8], nsum=[$3], (- (tok_table_or_col sum_sales) (tok_table_or_col avg_monthly_sales))=[-($15, $16)]) - HiveJoin(condition=[AND(AND(AND(=($10, $0), =($11, $1)), =($12, $2)), =($17, -($4, 1)))], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject((tok_table_or_col i_category)=[$0], (tok_table_or_col i_brand)=[$1], (tok_table_or_col cc_name)=[$2], (tok_function sum (tok_table_or_col cs_sales_price))=[$3], rank_window_1=[$4]) + HiveJoin(condition=[AND(AND(AND(=($10, $0), =($11, $1)), =($12, $2)), =($17, $4))], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject((tok_table_or_col i_category)=[$0], (tok_table_or_col i_brand)=[$1], (tok_table_or_col cc_name)=[$2], (tok_function sum (tok_table_or_col cs_sales_price))=[$3], -=[-($4, 1)]) HiveFilter(condition=[IS NOT NULL($4)]) HiveProject((tok_table_or_col i_category)=[$1], (tok_table_or_col i_brand)=[$0], (tok_table_or_col cc_name)=[$4], (tok_function sum (tok_table_or_col cs_sales_price))=[$5], rank_window_1=[rank() OVER (PARTITION BY $1, $0, $4 ORDER BY $2 NULLS LAST, $3 NULLS LAST ROWS BETWEEN 2147483647 FOLLOWING AND 2147483647 PRECEDING)]) HiveProject(i_brand=[$0], i_category=[$1], d_year=[$2], d_moy=[$3], cc_name=[$4], $f5=[$5]) @@ -127,8 +127,8 @@ HiveProject(i_category=[$0], i_brand=[$1], d_year=[$2], d_moy=[$3], avg_monthly_ HiveProject(cc_call_center_sk=[$0], cc_name=[$6]) HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($6))]) HiveTableScan(table=[[default, call_center]], table:alias=[call_center]) - HiveJoin(condition=[AND(AND(AND(=($5, $0), =($6, $1)), =($7, $2)), =($12, +($4, 1)))], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject((tok_table_or_col i_category)=[$0], (tok_table_or_col i_brand)=[$1], (tok_table_or_col cc_name)=[$2], (tok_function sum (tok_table_or_col cs_sales_price))=[$3], rank_window_1=[$4]) + HiveJoin(condition=[AND(AND(AND(=($5, $0), =($6, $1)), =($7, $2)), =($12, $4))], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject((tok_table_or_col i_category)=[$0], (tok_table_or_col i_brand)=[$1], (tok_table_or_col cc_name)=[$2], (tok_function sum (tok_table_or_col cs_sales_price))=[$3], +=[+($4, 1)]) HiveFilter(condition=[IS NOT NULL($4)]) HiveProject((tok_table_or_col i_category)=[$1], (tok_table_or_col i_brand)=[$0], (tok_table_or_col cc_name)=[$4], (tok_function sum (tok_table_or_col cs_sales_price))=[$5], rank_window_1=[rank() OVER (PARTITION BY $1, $0, $4 ORDER BY $2 NULLS LAST, $3 NULLS LAST ROWS BETWEEN 2147483647 FOLLOWING AND 2147483647 PRECEDING)]) HiveProject(i_brand=[$0], i_category=[$1], d_year=[$2], d_moy=[$3], cc_name=[$4], $f5=[$5]) diff --git ql/src/test/results/clientpositive/perf/tez/cbo_query58.q.out ql/src/test/results/clientpositive/perf/tez/cbo_query58.q.out index 2504d783802..b4410ff07a2 100644 --- ql/src/test/results/clientpositive/perf/tez/cbo_query58.q.out +++ ql/src/test/results/clientpositive/perf/tez/cbo_query58.q.out @@ -141,10 +141,10 @@ POSTHOOK: Input: default@web_sales POSTHOOK: Output: hdfs://### HDFS PATH ### CBO PLAN: HiveSortLimit(sort0=[$0], sort1=[$1], dir0=[ASC], dir1=[ASC], fetch=[100]) - HiveProject(item_id=[$0], ss_item_rev=[$3], ss_dev=[*(/(/($3, +(+($3, $1), $5)), CAST(3):DECIMAL(10, 0)), CAST(100):DECIMAL(10, 0))], cs_item_rev=[$1], cs_dev=[*(/(/($1, +(+($3, $1), $5)), CAST(3):DECIMAL(10, 0)), CAST(100):DECIMAL(10, 0))], ws_item_rev=[$5], ws_dev=[*(/(/($5, +(+($3, $1), $5)), CAST(3):DECIMAL(10, 0)), CAST(100):DECIMAL(10, 0))], average=[/(+(+($3, $1), $5), CAST(3):DECIMAL(10, 0))]) - HiveJoin(condition=[AND(AND(AND(AND(=($0, $4), BETWEEN(false, $3, *(0.9, $5), *(1.1, $5))), BETWEEN(false, $1, *(0.9, $5), *(1.1, $5))), BETWEEN(false, $5, *(0.9, $3), *(1.1, $3))), BETWEEN(false, $5, *(0.9, $1), *(1.1, $1)))], joinType=[inner], algorithm=[none], cost=[not available]) - HiveJoin(condition=[AND(AND(=($2, $0), BETWEEN(false, $3, *(0.9, $1), *(1.1, $1))), BETWEEN(false, $1, *(0.9, $3), *(1.1, $3)))], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(i_item_id=[$0], $f1=[$1]) + HiveProject(item_id=[$0], ss_item_rev=[$5], ss_dev=[*(/(/($5, +(+($5, $1), $9)), CAST(3):DECIMAL(10, 0)), CAST(100):DECIMAL(10, 0))], cs_item_rev=[$1], cs_dev=[*(/(/($1, +(+($5, $1), $9)), CAST(3):DECIMAL(10, 0)), CAST(100):DECIMAL(10, 0))], ws_item_rev=[$9], ws_dev=[*(/(/($9, +(+($5, $1), $9)), CAST(3):DECIMAL(10, 0)), CAST(100):DECIMAL(10, 0))], average=[/(+(+($5, $1), $9), CAST(3):DECIMAL(10, 0))]) + HiveJoin(condition=[AND(AND(AND(AND(=($0, $8), BETWEEN(false, $5, $10, $11)), BETWEEN(false, $1, $10, $11)), BETWEEN(false, $9, $6, $7)), BETWEEN(false, $9, $2, $3))], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[AND(AND(=($4, $0), BETWEEN(false, $5, $2, $3)), BETWEEN(false, $1, $6, $7))], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject($f0=[$0], $f1=[$1], *=[*(0.9, $1)], *3=[*(1.1, $1)]) HiveAggregate(group=[{4}], agg#0=[sum($2)]) HiveJoin(condition=[=($0, $5)], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($1, $3)], joinType=[inner], algorithm=[none], cost=[not available]) @@ -175,7 +175,7 @@ HiveSortLimit(sort0=[$0], sort1=[$1], dir0=[ASC], dir1=[ASC], fetch=[100]) HiveProject(d_week_seq=[$4]) HiveFilter(condition=[AND(=($2, _UTF-16LE'1998-02-19'), IS NOT NULL($4))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) - HiveProject(i_item_id=[$0], $f1=[$1]) + HiveProject($f0=[$0], $f1=[$1], *=[*(0.9, $1)], *3=[*(1.1, $1)]) HiveAggregate(group=[{4}], agg#0=[sum($2)]) HiveJoin(condition=[=($0, $5)], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($1, $3)], joinType=[inner], algorithm=[none], cost=[not available]) @@ -206,7 +206,7 @@ HiveSortLimit(sort0=[$0], sort1=[$1], dir0=[ASC], dir1=[ASC], fetch=[100]) HiveProject(d_week_seq=[$4]) HiveFilter(condition=[AND(=($2, _UTF-16LE'1998-02-19'), IS NOT NULL($4))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) - HiveProject(i_item_id=[$0], $f1=[$1]) + HiveProject($f0=[$0], $f1=[$1], *=[*(0.9, $1)], *3=[*(1.1, $1)]) HiveAggregate(group=[{4}], agg#0=[sum($2)]) HiveJoin(condition=[=($0, $5)], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($1, $3)], joinType=[inner], algorithm=[none], cost=[not available]) diff --git ql/src/test/results/clientpositive/perf/tez/cbo_query59.q.out ql/src/test/results/clientpositive/perf/tez/cbo_query59.q.out index bb92a1fcf7b..8674a8a6c6d 100644 --- ql/src/test/results/clientpositive/perf/tez/cbo_query59.q.out +++ ql/src/test/results/clientpositive/perf/tez/cbo_query59.q.out @@ -94,24 +94,24 @@ POSTHOOK: Input: default@store_sales POSTHOOK: Output: hdfs://### HDFS PATH ### CBO PLAN: HiveSortLimit(sort0=[$0], sort1=[$1], sort2=[$2], dir0=[ASC], dir1=[ASC], dir2=[ASC], fetch=[100]) - HiveProject(s_store_name1=[$2], s_store_id1=[$1], d_week_seq1=[$3], _o__c3=[/($5, $16)], _o__c4=[/($6, $17)], _o__c5=[/($7, $7)], _o__c6=[/($8, $18)], _o__c7=[/($9, $19)], _o__c8=[/($10, $20)], _o__c9=[/($11, $21)]) - HiveJoin(condition=[AND(=($1, $15), =($3, -($14, 52)))], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(s_store_name1=[$2], s_store_id1=[$1], d_week_seq1=[$3], _o__c3=[/($5, $15)], _o__c4=[/($6, $16)], _o__c5=[/($7, $7)], _o__c6=[/($8, $17)], _o__c7=[/($9, $18)], _o__c8=[/($10, $19)], _o__c9=[/($11, $20)]) + HiveJoin(condition=[AND(=($1, $14), =($3, -($13, 52)))], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($4, $0)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(s_store_sk=[$0], s_store_id=[$1], s_store_name=[$5]) HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($1))]) HiveTableScan(table=[[default, store]], table:alias=[store]) - HiveJoin(condition=[=($10, $0)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($9, $0)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject($f0=[$0], $f1=[$1], $f2=[$2], $f3=[$3], $f4=[$4], $f5=[$5], $f6=[$6], $f7=[$7], $f8=[$8]) HiveAggregate(group=[{0, 1}], agg#0=[sum($2)], agg#1=[sum($3)], agg#2=[sum($4)], agg#3=[sum($5)], agg#4=[sum($6)], agg#5=[sum($7)], agg#6=[sum($8)]) - HiveProject($f0=[$4], $f1=[$1], $f2=[CASE(=($5, _UTF-16LE'Sunday'), $2, null)], $f3=[CASE(=($5, _UTF-16LE'Monday'), $2, null)], $f4=[CASE(=($5, _UTF-16LE'Tuesday'), $2, null)], $f5=[CASE(=($5, _UTF-16LE'Wednesday'), $2, null)], $f6=[CASE(=($5, _UTF-16LE'Thursday'), $2, null)], $f7=[CASE(=($5, _UTF-16LE'Friday'), $2, null)], $f8=[CASE(=($5, _UTF-16LE'Saturday'), $2, null)]) + HiveProject($f0=[$4], $f1=[$1], $f2=[CASE($5, $2, null)], $f3=[CASE($6, $2, null)], $f4=[CASE($7, $2, null)], $f5=[CASE($8, $2, null)], $f6=[CASE($9, $2, null)], $f7=[CASE($10, $2, null)], $f8=[CASE($11, $2, null)]) HiveJoin(condition=[=($3, $0)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(ss_sold_date_sk=[$0], ss_store_sk=[$7], ss_sales_price=[$13]) HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($7))]) HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) - HiveProject(d_date_sk=[$0], d_week_seq=[$4], d_day_name=[$14]) + HiveProject(d_date_sk=[$0], d_week_seq=[$4], ==[=($14, _UTF-16LE'Sunday')], =3=[=($14, _UTF-16LE'Monday')], =4=[=($14, _UTF-16LE'Tuesday')], =5=[=($14, _UTF-16LE'Wednesday')], =6=[=($14, _UTF-16LE'Thursday')], =7=[=($14, _UTF-16LE'Friday')], =8=[=($14, _UTF-16LE'Saturday')]) HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($4))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) - HiveProject(d_month_seq=[$3], d_week_seq=[$4]) + HiveProject(d_week_seq=[$4]) HiveFilter(condition=[AND(BETWEEN(false, $3, 1185, 1196), IS NOT NULL($4))]) HiveTableScan(table=[[default, date_dim]], table:alias=[d]) HiveProject(d_week_seq2=[$2], s_store_id2=[$1], sun_sales2=[$4], mon_sales2=[$5], wed_sales2=[$6], thu_sales2=[$7], fri_sales2=[$8], sat_sales2=[$9]) @@ -119,18 +119,18 @@ HiveSortLimit(sort0=[$0], sort1=[$1], sort2=[$2], dir0=[ASC], dir1=[ASC], dir2=[ HiveProject(s_store_sk=[$0], s_store_id=[$1]) HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($1))]) HiveTableScan(table=[[default, store]], table:alias=[store]) - HiveJoin(condition=[=($9, $0)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($8, $0)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject($f0=[$0], $f1=[$1], $f2=[$2], $f3=[$3], $f4=[$4], $f5=[$5], $f6=[$6], $f7=[$7]) HiveAggregate(group=[{0, 1}], agg#0=[sum($2)], agg#1=[sum($3)], agg#2=[sum($5)], agg#3=[sum($6)], agg#4=[sum($7)], agg#5=[sum($8)]) - HiveProject($f0=[$4], $f1=[$1], $f2=[CASE(=($5, _UTF-16LE'Sunday'), $2, null)], $f3=[CASE(=($5, _UTF-16LE'Monday'), $2, null)], $f4=[CASE(=($5, _UTF-16LE'Tuesday'), $2, null)], $f5=[CASE(=($5, _UTF-16LE'Wednesday'), $2, null)], $f6=[CASE(=($5, _UTF-16LE'Thursday'), $2, null)], $f7=[CASE(=($5, _UTF-16LE'Friday'), $2, null)], $f8=[CASE(=($5, _UTF-16LE'Saturday'), $2, null)]) + HiveProject($f0=[$4], $f1=[$1], $f2=[CASE($5, $2, null)], $f3=[CASE($6, $2, null)], $f4=[CASE($7, $2, null)], $f5=[CASE($8, $2, null)], $f6=[CASE($9, $2, null)], $f7=[CASE($10, $2, null)], $f8=[CASE($11, $2, null)]) HiveJoin(condition=[=($3, $0)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(ss_sold_date_sk=[$0], ss_store_sk=[$7], ss_sales_price=[$13]) HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($7))]) HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) - HiveProject(d_date_sk=[$0], d_week_seq=[$4], d_day_name=[$14]) + HiveProject(d_date_sk=[$0], d_week_seq=[$4], ==[=($14, _UTF-16LE'Sunday')], =3=[=($14, _UTF-16LE'Monday')], =4=[=($14, _UTF-16LE'Tuesday')], =5=[=($14, _UTF-16LE'Wednesday')], =6=[=($14, _UTF-16LE'Thursday')], =7=[=($14, _UTF-16LE'Friday')], =8=[=($14, _UTF-16LE'Saturday')]) HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($4))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) - HiveProject(d_month_seq=[$3], d_week_seq=[$4]) + HiveProject(d_week_seq=[$4]) HiveFilter(condition=[AND(BETWEEN(false, $3, 1197, 1208), IS NOT NULL($4))]) HiveTableScan(table=[[default, date_dim]], table:alias=[d]) diff --git ql/src/test/results/clientpositive/perf/tez/cbo_query6.q.out ql/src/test/results/clientpositive/perf/tez/cbo_query6.q.out index 02149e760df..f502c004cfc 100644 --- ql/src/test/results/clientpositive/perf/tez/cbo_query6.q.out +++ ql/src/test/results/clientpositive/perf/tez/cbo_query6.q.out @@ -88,13 +88,13 @@ HiveSortLimit(sort0=[$1], dir0=[ASC], fetch=[100]) HiveProject(ca_address_sk=[$0], ca_state=[$8]) HiveFilter(condition=[IS NOT NULL($0)]) HiveTableScan(table=[[default, customer_address]], table:alias=[a]) - HiveProject(i_item_sk=[$0], i_current_price=[$1], i_category=[$2], _o__c0=[$3], i_category0=[$4], cnt=[$5]) - HiveJoin(condition=[AND(=($4, $2), >($1, *(1.2, CAST($3):DECIMAL(16, 6))))], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(i_item_sk=[$0], i_current_price=[$1], i_category=[$2], i_category0=[$3], *=[$4], cnt=[$5]) + HiveJoin(condition=[AND(=($3, $2), >($1, $4))], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(i_item_sk=[$0], i_current_price=[$5], i_category=[$12]) HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($12))]) HiveTableScan(table=[[default, item]], table:alias=[i]) HiveJoin(condition=[true], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(_o__c0=[/($1, $2)], i_category=[$0]) + HiveProject(i_category=[$0], *=[*(1.2, CAST(/($1, $2)):DECIMAL(16, 6))]) HiveAggregate(group=[{12}], agg#0=[sum($5)], agg#1=[count($5)]) HiveFilter(condition=[IS NOT NULL($12)]) HiveTableScan(table=[[default, item]], table:alias=[j]) diff --git ql/src/test/results/clientpositive/perf/tez/cbo_query60.q.out ql/src/test/results/clientpositive/perf/tez/cbo_query60.q.out index 81dfec798be..acda9301979 100644 --- ql/src/test/results/clientpositive/perf/tez/cbo_query60.q.out +++ ql/src/test/results/clientpositive/perf/tez/cbo_query60.q.out @@ -173,8 +173,8 @@ HiveSortLimit(sort0=[$0], sort1=[$1], dir0=[ASC], dir1=[ASC], fetch=[100]) HiveProject(i_item_id=[$0], $f1=[$1]) HiveUnion(all=[true]) HiveProject(i_item_id=[$0], $f1=[$1]) - HiveAggregate(group=[{1}], agg#0=[sum($8)]) - HiveJoin(condition=[=($6, $0)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveAggregate(group=[{1}], agg#0=[sum($7)]) + HiveJoin(condition=[=($5, $0)], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($1, $2)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(i_item_sk=[$0], i_item_id=[$1]) HiveFilter(condition=[AND(IS NOT NULL($1), IS NOT NULL($0))]) @@ -183,21 +183,21 @@ HiveSortLimit(sort0=[$0], sort1=[$1], dir0=[ASC], dir1=[ASC], fetch=[100]) HiveAggregate(group=[{1}]) HiveFilter(condition=[AND(=($12, _UTF-16LE'Children'), IS NOT NULL($1))]) HiveTableScan(table=[[default, item]], table:alias=[item]) - HiveProject(ca_address_sk=[$0], ca_gmt_offset=[$1], ss_sold_date_sk=[$2], ss_item_sk=[$3], ss_addr_sk=[$4], ss_ext_sales_price=[$5], d_date_sk=[$6], d_year=[$7], d_moy=[$8]) - HiveJoin(condition=[=($4, $0)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(ca_address_sk=[$0], ca_gmt_offset=[CAST(-6):DECIMAL(5, 2)]) + HiveProject(ca_address_sk=[$0], ss_sold_date_sk=[$1], ss_item_sk=[$2], ss_addr_sk=[$3], ss_ext_sales_price=[$4], d_date_sk=[$5]) + HiveJoin(condition=[=($3, $0)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(ca_address_sk=[$0]) HiveFilter(condition=[AND(=($11, -6), IS NOT NULL($0))]) HiveTableScan(table=[[default, customer_address]], table:alias=[customer_address]) HiveJoin(condition=[=($0, $4)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(ss_sold_date_sk=[$0], ss_item_sk=[$2], ss_addr_sk=[$6], ss_ext_sales_price=[$15]) HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($6), IS NOT NULL($2))]) HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) - HiveProject(d_date_sk=[$0], d_year=[CAST(1999):INTEGER], d_moy=[CAST(9):INTEGER]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(=($6, 1999), =($8, 9), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) HiveProject(i_item_id=[$0], $f1=[$1]) - HiveAggregate(group=[{1}], agg#0=[sum($8)]) - HiveJoin(condition=[=($7, $0)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveAggregate(group=[{1}], agg#0=[sum($7)]) + HiveJoin(condition=[=($6, $0)], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($1, $2)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(i_item_sk=[$0], i_item_id=[$1]) HiveFilter(condition=[AND(IS NOT NULL($1), IS NOT NULL($0))]) @@ -206,21 +206,21 @@ HiveSortLimit(sort0=[$0], sort1=[$1], dir0=[ASC], dir1=[ASC], fetch=[100]) HiveAggregate(group=[{1}]) HiveFilter(condition=[AND(=($12, _UTF-16LE'Children'), IS NOT NULL($1))]) HiveTableScan(table=[[default, item]], table:alias=[item]) - HiveProject(ca_address_sk=[$0], ca_gmt_offset=[$1], cs_sold_date_sk=[$2], cs_bill_addr_sk=[$3], cs_item_sk=[$4], cs_ext_sales_price=[$5], d_date_sk=[$6], d_year=[$7], d_moy=[$8]) - HiveJoin(condition=[=($3, $0)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(ca_address_sk=[$0], ca_gmt_offset=[CAST(-6):DECIMAL(5, 2)]) + HiveProject(ca_address_sk=[$0], cs_sold_date_sk=[$1], cs_bill_addr_sk=[$2], cs_item_sk=[$3], cs_ext_sales_price=[$4], d_date_sk=[$5]) + HiveJoin(condition=[=($2, $0)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(ca_address_sk=[$0]) HiveFilter(condition=[AND(=($11, -6), IS NOT NULL($0))]) HiveTableScan(table=[[default, customer_address]], table:alias=[customer_address]) HiveJoin(condition=[=($0, $4)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(cs_sold_date_sk=[$0], cs_bill_addr_sk=[$6], cs_item_sk=[$15], cs_ext_sales_price=[$23]) HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($6), IS NOT NULL($15))]) HiveTableScan(table=[[default, catalog_sales]], table:alias=[catalog_sales]) - HiveProject(d_date_sk=[$0], d_year=[CAST(1999):INTEGER], d_moy=[CAST(9):INTEGER]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(=($6, 1999), =($8, 9), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) HiveProject(i_item_id=[$0], $f1=[$1]) - HiveAggregate(group=[{1}], agg#0=[sum($8)]) - HiveJoin(condition=[=($6, $0)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveAggregate(group=[{1}], agg#0=[sum($7)]) + HiveJoin(condition=[=($5, $0)], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($1, $2)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(i_item_sk=[$0], i_item_id=[$1]) HiveFilter(condition=[AND(IS NOT NULL($1), IS NOT NULL($0))]) @@ -229,16 +229,16 @@ HiveSortLimit(sort0=[$0], sort1=[$1], dir0=[ASC], dir1=[ASC], fetch=[100]) HiveAggregate(group=[{1}]) HiveFilter(condition=[AND(=($12, _UTF-16LE'Children'), IS NOT NULL($1))]) HiveTableScan(table=[[default, item]], table:alias=[item]) - HiveProject(ca_address_sk=[$0], ca_gmt_offset=[$1], ws_sold_date_sk=[$2], ws_item_sk=[$3], ws_bill_addr_sk=[$4], ws_ext_sales_price=[$5], d_date_sk=[$6], d_year=[$7], d_moy=[$8]) - HiveJoin(condition=[=($4, $0)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(ca_address_sk=[$0], ca_gmt_offset=[CAST(-6):DECIMAL(5, 2)]) + HiveProject(ca_address_sk=[$0], ws_sold_date_sk=[$1], ws_item_sk=[$2], ws_bill_addr_sk=[$3], ws_ext_sales_price=[$4], d_date_sk=[$5]) + HiveJoin(condition=[=($3, $0)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(ca_address_sk=[$0]) HiveFilter(condition=[AND(=($11, -6), IS NOT NULL($0))]) HiveTableScan(table=[[default, customer_address]], table:alias=[customer_address]) HiveJoin(condition=[=($0, $4)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(ws_sold_date_sk=[$0], ws_item_sk=[$3], ws_bill_addr_sk=[$7], ws_ext_sales_price=[$23]) HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($7), IS NOT NULL($3))]) HiveTableScan(table=[[default, web_sales]], table:alias=[web_sales]) - HiveProject(d_date_sk=[$0], d_year=[CAST(1999):INTEGER], d_moy=[CAST(9):INTEGER]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(=($6, 1999), =($8, 9), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) diff --git ql/src/test/results/clientpositive/perf/tez/cbo_query61.q.out ql/src/test/results/clientpositive/perf/tez/cbo_query61.q.out index c5356dfe637..8e8cf270780 100644 --- ql/src/test/results/clientpositive/perf/tez/cbo_query61.q.out +++ ql/src/test/results/clientpositive/perf/tez/cbo_query61.q.out @@ -106,59 +106,59 @@ HiveSortLimit(sort0=[$0], sort1=[$1], dir0=[ASC], dir1=[ASC], fetch=[100]) HiveProject(promotions=[$0], total=[$1], _o__c2=[*(/(CAST($0):DECIMAL(15, 4), CAST($1):DECIMAL(15, 4)), CAST(100):DECIMAL(10, 0))]) HiveJoin(condition=[true], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject($f0=[$0]) - HiveAggregate(group=[{}], agg#0=[sum($9)]) - HiveJoin(condition=[=($6, $0)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveAggregate(group=[{}], agg#0=[sum($8)]) + HiveJoin(condition=[=($5, $0)], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($2, $1)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(c_customer_sk=[$0], c_current_addr_sk=[$4]) HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($4))]) HiveTableScan(table=[[default, customer]], table:alias=[customer]) - HiveProject(ca_address_sk=[$0], ca_gmt_offset=[CAST(-7):DECIMAL(5, 2)]) + HiveProject(ca_address_sk=[$0]) HiveFilter(condition=[AND(=($11, -7), IS NOT NULL($0))]) HiveTableScan(table=[[default, customer_address]], table:alias=[customer_address]) - HiveProject(ss_sold_date_sk=[$0], ss_item_sk=[$1], ss_customer_sk=[$2], ss_store_sk=[$3], ss_promo_sk=[$4], ss_ext_sales_price=[$5], d_date_sk=[$6], d_year=[$7], d_moy=[$8], i_item_sk=[$9], i_category=[$10], s_store_sk=[$11], s_gmt_offset=[$12], p_promo_sk=[$13], p_channel_dmail=[$14], p_channel_email=[$15], p_channel_tv=[$16]) - HiveJoin(condition=[=($4, $13)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveJoin(condition=[=($3, $11)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveJoin(condition=[=($1, $9)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(ss_sold_date_sk=[$0], ss_item_sk=[$1], ss_customer_sk=[$2], ss_store_sk=[$3], ss_promo_sk=[$4], ss_ext_sales_price=[$5], d_date_sk=[$6], i_item_sk=[$7], s_store_sk=[$8], p_promo_sk=[$9]) + HiveJoin(condition=[=($4, $9)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($3, $8)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($1, $7)], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($0, $6)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(ss_sold_date_sk=[$0], ss_item_sk=[$2], ss_customer_sk=[$3], ss_store_sk=[$7], ss_promo_sk=[$8], ss_ext_sales_price=[$15]) HiveFilter(condition=[AND(IS NOT NULL($7), IS NOT NULL($8), IS NOT NULL($0), IS NOT NULL($3), IS NOT NULL($2))]) HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) - HiveProject(d_date_sk=[$0], d_year=[CAST(1999):INTEGER], d_moy=[CAST(11):INTEGER]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(=($6, 1999), =($8, 11), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) - HiveProject(i_item_sk=[$0], i_category=[CAST(_UTF-16LE'Electronics'):VARCHAR(2147483647) CHARACTER SET "UTF-16LE" COLLATE "ISO-8859-1$en_US$primary"]) + HiveProject(i_item_sk=[$0]) HiveFilter(condition=[AND(=($12, _UTF-16LE'Electronics'), IS NOT NULL($0))]) HiveTableScan(table=[[default, item]], table:alias=[item]) - HiveProject(s_store_sk=[$0], s_gmt_offset=[CAST(-7):DECIMAL(5, 2)]) + HiveProject(s_store_sk=[$0]) HiveFilter(condition=[AND(=($27, -7), IS NOT NULL($0))]) HiveTableScan(table=[[default, store]], table:alias=[store]) - HiveProject(p_promo_sk=[$0], p_channel_dmail=[$8], p_channel_email=[$9], p_channel_tv=[$11]) + HiveProject(p_promo_sk=[$0]) HiveFilter(condition=[AND(OR(=($8, _UTF-16LE'Y'), =($9, _UTF-16LE'Y'), =($11, _UTF-16LE'Y')), IS NOT NULL($0))]) HiveTableScan(table=[[default, promotion]], table:alias=[promotion]) HiveProject($f0=[$0]) - HiveAggregate(group=[{}], agg#0=[sum($8)]) - HiveJoin(condition=[=($6, $0)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveAggregate(group=[{}], agg#0=[sum($7)]) + HiveJoin(condition=[=($5, $0)], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($2, $1)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(c_customer_sk=[$0], c_current_addr_sk=[$4]) HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($4))]) HiveTableScan(table=[[default, customer]], table:alias=[customer]) - HiveProject(ca_address_sk=[$0], ca_gmt_offset=[CAST(-7):DECIMAL(5, 2)]) + HiveProject(ca_address_sk=[$0]) HiveFilter(condition=[AND(=($11, -7), IS NOT NULL($0))]) HiveTableScan(table=[[default, customer_address]], table:alias=[customer_address]) - HiveProject(ss_sold_date_sk=[$0], ss_item_sk=[$1], ss_customer_sk=[$2], ss_store_sk=[$3], ss_ext_sales_price=[$4], d_date_sk=[$5], d_year=[$6], d_moy=[$7], i_item_sk=[$8], i_category=[$9], s_store_sk=[$10], s_gmt_offset=[$11]) - HiveJoin(condition=[=($3, $10)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveJoin(condition=[=($1, $8)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(ss_sold_date_sk=[$0], ss_item_sk=[$1], ss_customer_sk=[$2], ss_store_sk=[$3], ss_ext_sales_price=[$4], d_date_sk=[$5], i_item_sk=[$6], s_store_sk=[$7]) + HiveJoin(condition=[=($3, $7)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($1, $6)], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($0, $5)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(ss_sold_date_sk=[$0], ss_item_sk=[$2], ss_customer_sk=[$3], ss_store_sk=[$7], ss_ext_sales_price=[$15]) HiveFilter(condition=[AND(IS NOT NULL($7), IS NOT NULL($0), IS NOT NULL($3), IS NOT NULL($2))]) HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) - HiveProject(d_date_sk=[$0], d_year=[CAST(1999):INTEGER], d_moy=[CAST(11):INTEGER]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(=($6, 1999), =($8, 11), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) - HiveProject(i_item_sk=[$0], i_category=[CAST(_UTF-16LE'Electronics'):VARCHAR(2147483647) CHARACTER SET "UTF-16LE" COLLATE "ISO-8859-1$en_US$primary"]) + HiveProject(i_item_sk=[$0]) HiveFilter(condition=[AND(=($12, _UTF-16LE'Electronics'), IS NOT NULL($0))]) HiveTableScan(table=[[default, item]], table:alias=[item]) - HiveProject(s_store_sk=[$0], s_gmt_offset=[CAST(-7):DECIMAL(5, 2)]) + HiveProject(s_store_sk=[$0]) HiveFilter(condition=[AND(=($27, -7), IS NOT NULL($0))]) HiveTableScan(table=[[default, store]], table:alias=[store]) diff --git ql/src/test/results/clientpositive/perf/tez/cbo_query63.q.out ql/src/test/results/clientpositive/perf/tez/cbo_query63.q.out index a0809895ebe..78c9b131114 100644 --- ql/src/test/results/clientpositive/perf/tez/cbo_query63.q.out +++ ql/src/test/results/clientpositive/perf/tez/cbo_query63.q.out @@ -70,20 +70,20 @@ HiveSortLimit(sort0=[$0], sort1=[$2], sort2=[$1], dir0=[ASC], dir1=[ASC], dir2=[ HiveFilter(condition=[CASE(>($2, 0), >(/(ABS(-($1, $2)), $2), 0.1), null)]) HiveProject((tok_table_or_col i_manager_id)=[$0], (tok_function sum (tok_table_or_col ss_sales_price))=[$2], avg_window_0=[avg($2) OVER (PARTITION BY $0 ORDER BY $0 NULLS FIRST ROWS BETWEEN 2147483647 FOLLOWING AND 2147483647 PRECEDING)]) HiveProject(i_manager_id=[$0], d_moy=[$1], $f2=[$2]) - HiveAggregate(group=[{9, 12}], agg#0=[sum($4)]) + HiveAggregate(group=[{6, 8}], agg#0=[sum($4)]) HiveJoin(condition=[=($3, $0)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(s_store_sk=[$0]) HiveFilter(condition=[IS NOT NULL($0)]) HiveTableScan(table=[[default, store]], table:alias=[store]) - HiveJoin(condition=[=($0, $9)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($0, $6)], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($1, $4)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(ss_sold_date_sk=[$0], ss_item_sk=[$2], ss_store_sk=[$7], ss_sales_price=[$13]) HiveFilter(condition=[AND(IS NOT NULL($2), IS NOT NULL($0), IS NOT NULL($7))]) HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) - HiveProject(i_item_sk=[$0], i_brand=[$8], i_class=[$10], i_category=[$12], i_manager_id=[$20]) + HiveProject(i_item_sk=[$0], i_manager_id=[$20]) HiveFilter(condition=[AND(IN($10, _UTF-16LE'personal', _UTF-16LE'portable', _UTF-16LE'refernece', _UTF-16LE'self-help', _UTF-16LE'accessories', _UTF-16LE'classical', _UTF-16LE'fragrances', _UTF-16LE'pants'), IN($8, _UTF-16LE'scholaramalgamalg #14', _UTF-16LE'scholaramalgamalg #7', _UTF-16LE'exportiunivamalg #9', _UTF-16LE'scholaramalgamalg #9', _UTF-16LE'amalgimporto #1', _UTF-16LE'edu packscholar #1', _UTF-16LE'exportiimporto #1', _UTF-16LE'importoamalg #1'), IN($12, _UTF-16LE'Books', _UTF-16LE'Children', _UTF-16LE'Electronics', _UTF-16LE'Women', _UTF-16LE'Music', _UTF-16LE'Men'), OR(AND(IN($12, _UTF-16LE'Books', _UTF-16LE'Children', _UTF-16LE'Electronics'), IN($10, _UTF-16LE'personal', _UTF-16LE'portable', _UTF-16LE'refernece', _UTF-16LE'self-help'), IN($8, _UTF-16LE'scholaramalgamalg #14', _UTF-16LE'scholaramalgamalg #7', _UTF-16LE'exportiunivamalg #9', _UTF-16LE'scholaramalgamalg #9')), AND(IN($12, _UTF-16LE'Women', _UTF-16LE'Music', _UTF-16LE'Men'), IN($10, _UTF-16LE'accessories', _UTF-16LE'classical', _UTF-16LE'fragrances', _UTF-16LE'pants'), IN($8, _UTF-16LE'amalgimporto #1', _UTF-16LE'edu packscholar #1', _UTF-16LE'exportiimporto #1', _UTF-16LE'importoamalg #1'))), IS NOT NULL($0))]) HiveTableScan(table=[[default, item]], table:alias=[item]) - HiveProject(d_date_sk=[$0], d_month_seq=[$3], d_moy=[$8]) + HiveProject(d_date_sk=[$0], d_moy=[$8]) HiveFilter(condition=[AND(IN($3, 1212, 1213, 1214, 1215, 1216, 1217, 1218, 1219, 1220, 1221, 1222, 1223), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) diff --git ql/src/test/results/clientpositive/perf/tez/cbo_query64.q.out ql/src/test/results/clientpositive/perf/tez/cbo_query64.q.out index 3b59bd89997..5a5bb797a1f 100644 --- ql/src/test/results/clientpositive/perf/tez/cbo_query64.q.out +++ ql/src/test/results/clientpositive/perf/tez/cbo_query64.q.out @@ -268,7 +268,7 @@ HiveProject(product_name=[$0], store_name=[$1], store_zip=[$2], b_street_number= HiveProject(product_name=[$0], store_name=[$2], store_zip=[$3], b_street_number=[$4], b_streen_name=[$5], b_city=[$6], b_zip=[$7], c_street_number=[$8], c_street_name=[$9], c_city=[$10], c_zip=[$11], cnt=[$12], s1=[$13], s2=[$14], s3=[$15], s11=[$20], s21=[$21], s31=[$22], cnt1=[$19]) HiveJoin(condition=[AND(AND(AND(=($1, $16), <=($19, $12)), =($2, $17)), =($3, $18))], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject($f0=[$13], $f1=[$12], $f2=[$10], $f3=[$11], $f4=[$6], $f5=[$7], $f6=[$8], $f7=[$9], $f8=[$2], $f9=[$3], $f10=[$4], $f11=[$5], $f15=[$14], $f16=[$15], $f17=[$16], $f18=[$17]) - HiveAggregate(group=[{9, 11, 16, 17, 18, 19, 25, 26, 27, 28, 30, 31, 48, 51}], agg#0=[count()], agg#1=[sum($45)], agg#2=[sum($46)], agg#3=[sum($47)]) + HiveAggregate(group=[{9, 11, 16, 17, 18, 19, 25, 26, 27, 28, 30, 31, 48, 49}], agg#0=[count()], agg#1=[sum($45)], agg#2=[sum($46)], agg#3=[sum($47)]) HiveJoin(condition=[AND(<>($1, $21), =($39, $0))], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(cd_demo_sk=[$0], cd_marital_status=[$2]) HiveFilter(condition=[IS NOT NULL($0)]) @@ -302,7 +302,7 @@ HiveProject(product_name=[$0], store_name=[$1], store_zip=[$2], b_street_number= HiveProject(cd_demo_sk=[$0], cd_marital_status=[$2]) HiveFilter(condition=[IS NOT NULL($0)]) HiveTableScan(table=[[default, customer_demographics]], table:alias=[cd2]) - HiveProject(sr_item_sk=[$0], sr_ticket_number=[$1], ca_address_sk=[$2], ca_street_number=[$3], ca_street_name=[$4], ca_city=[$5], ca_zip=[$6], s_store_sk=[$7], s_store_name=[$8], s_zip=[$9], hd_demo_sk=[$10], hd_income_band_sk=[$11], ib_income_band_sk=[$12], p_promo_sk=[$13], ss_sold_date_sk=[$14], ss_item_sk=[$15], ss_customer_sk=[$16], ss_cdemo_sk=[$17], ss_hdemo_sk=[$18], ss_addr_sk=[$19], ss_store_sk=[$20], ss_promo_sk=[$21], ss_ticket_number=[$22], ss_wholesale_cost=[$23], ss_list_price=[$24], ss_coupon_amt=[$25], i_item_sk=[$26], i_current_price=[$27], i_color=[$28], i_product_name=[$29], d_date_sk=[$30], d_year=[$31], $f0=[$32], $f1=[$33], $f2=[$34]) + HiveProject(sr_item_sk=[$0], sr_ticket_number=[$1], ca_address_sk=[$2], ca_street_number=[$3], ca_street_name=[$4], ca_city=[$5], ca_zip=[$6], s_store_sk=[$7], s_store_name=[$8], s_zip=[$9], hd_demo_sk=[$10], hd_income_band_sk=[$11], ib_income_band_sk=[$12], p_promo_sk=[$13], ss_sold_date_sk=[$14], ss_item_sk=[$15], ss_customer_sk=[$16], ss_cdemo_sk=[$17], ss_hdemo_sk=[$18], ss_addr_sk=[$19], ss_store_sk=[$20], ss_promo_sk=[$21], ss_ticket_number=[$22], ss_wholesale_cost=[$23], ss_list_price=[$24], ss_coupon_amt=[$25], i_item_sk=[$26], i_product_name=[$27], d_date_sk=[$28], $f0=[$29]) HiveJoin(condition=[AND(=($15, $0), =($22, $1))], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(sr_item_sk=[$2], sr_ticket_number=[$9]) HiveFilter(condition=[AND(IS NOT NULL($2), IS NOT NULL($9))]) @@ -315,44 +315,43 @@ HiveProject(product_name=[$0], store_name=[$1], store_zip=[$2], b_street_number= HiveProject(s_store_sk=[$0], s_store_name=[$5], s_zip=[$25]) HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($5), IS NOT NULL($25))]) HiveTableScan(table=[[default, store]], table:alias=[store]) - HiveJoin(condition=[=($5, $22)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveJoin(condition=[=($8, $0)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveJoin(condition=[=($1, $2)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(hd_demo_sk=[$0], hd_income_band_sk=[$1]) - HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($1))]) - HiveTableScan(table=[[default, household_demographics]], table:alias=[hd1]) - HiveProject(ib_income_band_sk=[$0]) + HiveJoin(condition=[=($8, $0)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($1, $2)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(hd_demo_sk=[$0], hd_income_band_sk=[$1]) + HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($1))]) + HiveTableScan(table=[[default, household_demographics]], table:alias=[hd1]) + HiveProject(ib_income_band_sk=[$0]) + HiveFilter(condition=[IS NOT NULL($0)]) + HiveTableScan(table=[[default, income_band]], table:alias=[ib1]) + HiveProject(p_promo_sk=[$0], ss_sold_date_sk=[$1], ss_item_sk=[$2], ss_customer_sk=[$3], ss_cdemo_sk=[$4], ss_hdemo_sk=[$5], ss_addr_sk=[$6], ss_store_sk=[$7], ss_promo_sk=[$8], ss_ticket_number=[$9], ss_wholesale_cost=[$10], ss_list_price=[$11], ss_coupon_amt=[$12], i_item_sk=[$13], i_product_name=[$14], d_date_sk=[$15], $f0=[$16]) + HiveJoin(condition=[=($8, $0)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(p_promo_sk=[$0]) HiveFilter(condition=[IS NOT NULL($0)]) - HiveTableScan(table=[[default, income_band]], table:alias=[ib1]) - HiveProject(p_promo_sk=[$0], ss_sold_date_sk=[$1], ss_item_sk=[$2], ss_customer_sk=[$3], ss_cdemo_sk=[$4], ss_hdemo_sk=[$5], ss_addr_sk=[$6], ss_store_sk=[$7], ss_promo_sk=[$8], ss_ticket_number=[$9], ss_wholesale_cost=[$10], ss_list_price=[$11], ss_coupon_amt=[$12], i_item_sk=[$13], i_current_price=[$14], i_color=[$15], i_product_name=[$16], d_date_sk=[$17], d_year=[$18]) - HiveJoin(condition=[=($8, $0)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(p_promo_sk=[$0]) - HiveFilter(condition=[IS NOT NULL($0)]) - HiveTableScan(table=[[default, promotion]], table:alias=[promotion]) - HiveJoin(condition=[=($0, $16)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveTableScan(table=[[default, promotion]], table:alias=[promotion]) + HiveJoin(condition=[=($1, $15)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($0, $14)], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($1, $12)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(ss_sold_date_sk=[$0], ss_item_sk=[$2], ss_customer_sk=[$3], ss_cdemo_sk=[$4], ss_hdemo_sk=[$5], ss_addr_sk=[$6], ss_store_sk=[$7], ss_promo_sk=[$8], ss_ticket_number=[$9], ss_wholesale_cost=[$11], ss_list_price=[$12], ss_coupon_amt=[$19]) HiveFilter(condition=[AND(IS NOT NULL($2), IS NOT NULL($9), IS NOT NULL($0), IS NOT NULL($7), IS NOT NULL($3), IS NOT NULL($4), IS NOT NULL($8), IS NOT NULL($5), IS NOT NULL($6))]) HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) - HiveProject(i_item_sk=[$0], i_current_price=[$5], i_color=[$17], i_product_name=[$21]) + HiveProject(i_item_sk=[$0], i_product_name=[$21]) HiveFilter(condition=[AND(IN($17, _UTF-16LE'maroon', _UTF-16LE'burnished', _UTF-16LE'dim', _UTF-16LE'steel', _UTF-16LE'navajo', _UTF-16LE'chocolate'), BETWEEN(false, $5, 35, 45), BETWEEN(false, $5, 36, 50), IS NOT NULL($0))]) HiveTableScan(table=[[default, item]], table:alias=[item]) - HiveProject(d_date_sk=[$0], d_year=[CAST(2000):INTEGER]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(=($6, 2000), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[d1]) - HiveProject($f0=[$0], $f1=[$1], $f2=[$2]) - HiveFilter(condition=[>($1, *(2, $2))]) - HiveAggregate(group=[{0}], agg#0=[sum($1)], agg#1=[sum($2)]) - HiveProject($f0=[$0], $f1=[$2], $f2=[+(+($5, $6), $7)]) - HiveJoin(condition=[AND(=($0, $3), =($1, $4))], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(cs_item_sk=[$15], cs_order_number=[$17], cs_ext_list_price=[$25]) - HiveFilter(condition=[AND(IS NOT NULL($15), IS NOT NULL($17))]) - HiveTableScan(table=[[default, catalog_sales]], table:alias=[catalog_sales]) - HiveProject(cr_item_sk=[$2], cr_order_number=[$16], cr_refunded_cash=[$23], cr_reversed_charge=[$24], cr_store_credit=[$25]) - HiveFilter(condition=[AND(IS NOT NULL($2), IS NOT NULL($16))]) - HiveTableScan(table=[[default, catalog_returns]], table:alias=[catalog_returns]) + HiveProject($f0=[$0]) + HiveFilter(condition=[>($1, *(2, $2))]) + HiveAggregate(group=[{0}], agg#0=[sum($2)], agg#1=[sum($5)]) + HiveJoin(condition=[AND(=($0, $3), =($1, $4))], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(cs_item_sk=[$15], cs_order_number=[$17], cs_ext_list_price=[$25]) + HiveFilter(condition=[AND(IS NOT NULL($15), IS NOT NULL($17))]) + HiveTableScan(table=[[default, catalog_sales]], table:alias=[catalog_sales]) + HiveProject(cr_item_sk=[$2], cr_order_number=[$16], +=[+(+($23, $24), $25)]) + HiveFilter(condition=[AND(IS NOT NULL($2), IS NOT NULL($16))]) + HiveTableScan(table=[[default, catalog_returns]], table:alias=[catalog_returns]) HiveProject($f1=[$12], $f2=[$10], $f3=[$11], $f15=[$14], $f16=[$15], $f17=[$16], $f18=[$17]) - HiveAggregate(group=[{9, 11, 16, 17, 18, 19, 25, 26, 27, 28, 30, 31, 48, 51}], agg#0=[count()], agg#1=[sum($45)], agg#2=[sum($46)], agg#3=[sum($47)]) + HiveAggregate(group=[{9, 11, 16, 17, 18, 19, 25, 26, 27, 28, 30, 31, 48, 49}], agg#0=[count()], agg#1=[sum($45)], agg#2=[sum($46)], agg#3=[sum($47)]) HiveJoin(condition=[AND(<>($1, $21), =($39, $0))], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(cd_demo_sk=[$0], cd_marital_status=[$2]) HiveFilter(condition=[IS NOT NULL($0)]) @@ -386,7 +385,7 @@ HiveProject(product_name=[$0], store_name=[$1], store_zip=[$2], b_street_number= HiveProject(cd_demo_sk=[$0], cd_marital_status=[$2]) HiveFilter(condition=[IS NOT NULL($0)]) HiveTableScan(table=[[default, customer_demographics]], table:alias=[cd2]) - HiveProject(sr_item_sk=[$0], sr_ticket_number=[$1], ca_address_sk=[$2], ca_street_number=[$3], ca_street_name=[$4], ca_city=[$5], ca_zip=[$6], s_store_sk=[$7], s_store_name=[$8], s_zip=[$9], hd_demo_sk=[$10], hd_income_band_sk=[$11], ib_income_band_sk=[$12], p_promo_sk=[$13], ss_sold_date_sk=[$14], ss_item_sk=[$15], ss_customer_sk=[$16], ss_cdemo_sk=[$17], ss_hdemo_sk=[$18], ss_addr_sk=[$19], ss_store_sk=[$20], ss_promo_sk=[$21], ss_ticket_number=[$22], ss_wholesale_cost=[$23], ss_list_price=[$24], ss_coupon_amt=[$25], i_item_sk=[$26], i_current_price=[$27], i_color=[$28], i_product_name=[$29], d_date_sk=[$30], d_year=[$31], $f0=[$32], $f1=[$33], $f2=[$34]) + HiveProject(sr_item_sk=[$0], sr_ticket_number=[$1], ca_address_sk=[$2], ca_street_number=[$3], ca_street_name=[$4], ca_city=[$5], ca_zip=[$6], s_store_sk=[$7], s_store_name=[$8], s_zip=[$9], hd_demo_sk=[$10], hd_income_band_sk=[$11], ib_income_band_sk=[$12], p_promo_sk=[$13], ss_sold_date_sk=[$14], ss_item_sk=[$15], ss_customer_sk=[$16], ss_cdemo_sk=[$17], ss_hdemo_sk=[$18], ss_addr_sk=[$19], ss_store_sk=[$20], ss_promo_sk=[$21], ss_ticket_number=[$22], ss_wholesale_cost=[$23], ss_list_price=[$24], ss_coupon_amt=[$25], i_item_sk=[$26], i_product_name=[$27], d_date_sk=[$28], $f0=[$29]) HiveJoin(condition=[AND(=($15, $0), =($22, $1))], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(sr_item_sk=[$2], sr_ticket_number=[$9]) HiveFilter(condition=[AND(IS NOT NULL($2), IS NOT NULL($9))]) @@ -399,40 +398,39 @@ HiveProject(product_name=[$0], store_name=[$1], store_zip=[$2], b_street_number= HiveProject(s_store_sk=[$0], s_store_name=[$5], s_zip=[$25]) HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($5), IS NOT NULL($25))]) HiveTableScan(table=[[default, store]], table:alias=[store]) - HiveJoin(condition=[=($5, $22)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveJoin(condition=[=($8, $0)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveJoin(condition=[=($1, $2)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(hd_demo_sk=[$0], hd_income_band_sk=[$1]) - HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($1))]) - HiveTableScan(table=[[default, household_demographics]], table:alias=[hd1]) - HiveProject(ib_income_band_sk=[$0]) + HiveJoin(condition=[=($8, $0)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($1, $2)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(hd_demo_sk=[$0], hd_income_band_sk=[$1]) + HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($1))]) + HiveTableScan(table=[[default, household_demographics]], table:alias=[hd1]) + HiveProject(ib_income_band_sk=[$0]) + HiveFilter(condition=[IS NOT NULL($0)]) + HiveTableScan(table=[[default, income_band]], table:alias=[ib1]) + HiveProject(p_promo_sk=[$0], ss_sold_date_sk=[$1], ss_item_sk=[$2], ss_customer_sk=[$3], ss_cdemo_sk=[$4], ss_hdemo_sk=[$5], ss_addr_sk=[$6], ss_store_sk=[$7], ss_promo_sk=[$8], ss_ticket_number=[$9], ss_wholesale_cost=[$10], ss_list_price=[$11], ss_coupon_amt=[$12], i_item_sk=[$13], i_product_name=[$14], d_date_sk=[$15], $f0=[$16]) + HiveJoin(condition=[=($8, $0)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(p_promo_sk=[$0]) HiveFilter(condition=[IS NOT NULL($0)]) - HiveTableScan(table=[[default, income_band]], table:alias=[ib1]) - HiveProject(p_promo_sk=[$0], ss_sold_date_sk=[$1], ss_item_sk=[$2], ss_customer_sk=[$3], ss_cdemo_sk=[$4], ss_hdemo_sk=[$5], ss_addr_sk=[$6], ss_store_sk=[$7], ss_promo_sk=[$8], ss_ticket_number=[$9], ss_wholesale_cost=[$10], ss_list_price=[$11], ss_coupon_amt=[$12], i_item_sk=[$13], i_current_price=[$14], i_color=[$15], i_product_name=[$16], d_date_sk=[$17], d_year=[$18]) - HiveJoin(condition=[=($8, $0)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(p_promo_sk=[$0]) - HiveFilter(condition=[IS NOT NULL($0)]) - HiveTableScan(table=[[default, promotion]], table:alias=[promotion]) - HiveJoin(condition=[=($0, $16)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveTableScan(table=[[default, promotion]], table:alias=[promotion]) + HiveJoin(condition=[=($1, $15)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($0, $14)], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($1, $12)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(ss_sold_date_sk=[$0], ss_item_sk=[$2], ss_customer_sk=[$3], ss_cdemo_sk=[$4], ss_hdemo_sk=[$5], ss_addr_sk=[$6], ss_store_sk=[$7], ss_promo_sk=[$8], ss_ticket_number=[$9], ss_wholesale_cost=[$11], ss_list_price=[$12], ss_coupon_amt=[$19]) HiveFilter(condition=[AND(IS NOT NULL($2), IS NOT NULL($9), IS NOT NULL($0), IS NOT NULL($7), IS NOT NULL($3), IS NOT NULL($4), IS NOT NULL($8), IS NOT NULL($5), IS NOT NULL($6))]) HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) - HiveProject(i_item_sk=[$0], i_current_price=[$5], i_color=[$17], i_product_name=[$21]) + HiveProject(i_item_sk=[$0], i_product_name=[$21]) HiveFilter(condition=[AND(IN($17, _UTF-16LE'maroon', _UTF-16LE'burnished', _UTF-16LE'dim', _UTF-16LE'steel', _UTF-16LE'navajo', _UTF-16LE'chocolate'), BETWEEN(false, $5, 35, 45), BETWEEN(false, $5, 36, 50), IS NOT NULL($0))]) HiveTableScan(table=[[default, item]], table:alias=[item]) - HiveProject(d_date_sk=[$0], d_year=[CAST(2001):INTEGER]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(=($6, 2001), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[d1]) - HiveProject($f0=[$0], $f1=[$1], $f2=[$2]) - HiveFilter(condition=[>($1, *(2, $2))]) - HiveAggregate(group=[{0}], agg#0=[sum($1)], agg#1=[sum($2)]) - HiveProject($f0=[$0], $f1=[$2], $f2=[+(+($5, $6), $7)]) - HiveJoin(condition=[AND(=($0, $3), =($1, $4))], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(cs_item_sk=[$15], cs_order_number=[$17], cs_ext_list_price=[$25]) - HiveFilter(condition=[AND(IS NOT NULL($15), IS NOT NULL($17))]) - HiveTableScan(table=[[default, catalog_sales]], table:alias=[catalog_sales]) - HiveProject(cr_item_sk=[$2], cr_order_number=[$16], cr_refunded_cash=[$23], cr_reversed_charge=[$24], cr_store_credit=[$25]) - HiveFilter(condition=[AND(IS NOT NULL($2), IS NOT NULL($16))]) - HiveTableScan(table=[[default, catalog_returns]], table:alias=[catalog_returns]) + HiveProject($f0=[$0]) + HiveFilter(condition=[>($1, *(2, $2))]) + HiveAggregate(group=[{0}], agg#0=[sum($2)], agg#1=[sum($5)]) + HiveJoin(condition=[AND(=($0, $3), =($1, $4))], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(cs_item_sk=[$15], cs_order_number=[$17], cs_ext_list_price=[$25]) + HiveFilter(condition=[AND(IS NOT NULL($15), IS NOT NULL($17))]) + HiveTableScan(table=[[default, catalog_sales]], table:alias=[catalog_sales]) + HiveProject(cr_item_sk=[$2], cr_order_number=[$16], +=[+(+($23, $24), $25)]) + HiveFilter(condition=[AND(IS NOT NULL($2), IS NOT NULL($16))]) + HiveTableScan(table=[[default, catalog_returns]], table:alias=[catalog_returns]) diff --git ql/src/test/results/clientpositive/perf/tez/cbo_query65.q.out ql/src/test/results/clientpositive/perf/tez/cbo_query65.q.out index 1b154a434f3..25cb9ccc6b0 100644 --- ql/src/test/results/clientpositive/perf/tez/cbo_query65.q.out +++ ql/src/test/results/clientpositive/perf/tez/cbo_query65.q.out @@ -72,17 +72,17 @@ HiveSortLimit(sort0=[$0], sort1=[$1], dir0=[ASC], dir1=[ASC], fetch=[100]) HiveFilter(condition=[IS NOT NULL($0)]) HiveTableScan(table=[[default, item]], table:alias=[item]) HiveJoin(condition=[=($5, $0)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveJoin(condition=[AND(=($3, $0), <=($2, *(0.1, $4)))], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[AND(=($3, $0), <=($2, $4))], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(ss_store_sk=[$1], ss_item_sk=[$0], $f2=[$2]) HiveAggregate(group=[{1, 2}], agg#0=[sum($3)]) HiveJoin(condition=[=($0, $4)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(ss_sold_date_sk=[$0], ss_item_sk=[$2], ss_store_sk=[$7], ss_sales_price=[$13]) HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($7), IS NOT NULL($2))]) HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) - HiveProject(d_date_sk=[$0], d_month_seq=[$3]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(BETWEEN(false, $3, 1212, 1223), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) - HiveProject($f0=[$0], $f1=[/($1, $2)]) + HiveProject($f0=[$0], *=[*(0.1, /($1, $2))]) HiveAggregate(group=[{1}], agg#0=[sum($2)], agg#1=[count($2)]) HiveProject(ss_item_sk=[$0], ss_store_sk=[$1], $f2=[$2]) HiveAggregate(group=[{1, 2}], agg#0=[sum($3)]) @@ -90,7 +90,7 @@ HiveSortLimit(sort0=[$0], sort1=[$1], dir0=[ASC], dir1=[ASC], fetch=[100]) HiveProject(ss_sold_date_sk=[$0], ss_item_sk=[$2], ss_store_sk=[$7], ss_sales_price=[$13]) HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($7))]) HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) - HiveProject(d_date_sk=[$0], d_month_seq=[$3]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(BETWEEN(false, $3, 1212, 1223), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) HiveProject(s_store_sk=[$0], s_store_name=[$5]) diff --git ql/src/test/results/clientpositive/perf/tez/cbo_query66.q.out ql/src/test/results/clientpositive/perf/tez/cbo_query66.q.out index d97f351c4d8..e2409a9d82c 100644 --- ql/src/test/results/clientpositive/perf/tez/cbo_query66.q.out +++ ql/src/test/results/clientpositive/perf/tez/cbo_query66.q.out @@ -463,43 +463,43 @@ HiveProject(w_warehouse_name=[$0], w_warehouse_sq_ft=[$1], w_city=[$2], w_county HiveUnion(all=[true]) HiveProject($f0=[$0], $f1=[$1], $f2=[$2], $f3=[$3], $f4=[$4], $f5=[$5], $f6=[$6], $f7=[$7], $f8=[$8], $f9=[$9], $f10=[$10], $f11=[$11], $f12=[$12], $f13=[$13], $f14=[$14], $f15=[$15], $f16=[$16], $f17=[$17], $f18=[$18], $f19=[$19], $f20=[$20], $f21=[$21], $f22=[$22], $f23=[$23], $f24=[$24], $f25=[$25], $f26=[$26], $f27=[$27], $f28=[$28], $f29=[$29]) HiveAggregate(group=[{0, 1, 2, 3, 4, 5}], agg#0=[sum($6)], agg#1=[sum($7)], agg#2=[sum($8)], agg#3=[sum($9)], agg#4=[sum($10)], agg#5=[sum($11)], agg#6=[sum($12)], agg#7=[sum($13)], agg#8=[sum($14)], agg#9=[sum($15)], agg#10=[sum($16)], agg#11=[sum($17)], agg#12=[sum($18)], agg#13=[sum($19)], agg#14=[sum($20)], agg#15=[sum($21)], agg#16=[sum($22)], agg#17=[sum($23)], agg#18=[sum($24)], agg#19=[sum($25)], agg#20=[sum($26)], agg#21=[sum($27)], agg#22=[sum($28)], agg#23=[sum($29)]) - HiveProject($f0=[$1], $f1=[$2], $f2=[$3], $f3=[$4], $f4=[$5], $f5=[$6], $f7=[CASE(=($18, 1), *($12, CAST($11):DECIMAL(10, 0)), 0)], $f8=[CASE(=($18, 2), *($12, CAST($11):DECIMAL(10, 0)), 0)], $f9=[CASE(=($18, 3), *($12, CAST($11):DECIMAL(10, 0)), 0)], $f10=[CASE(=($18, 4), *($12, CAST($11):DECIMAL(10, 0)), 0)], $f11=[CASE(=($18, 5), *($12, CAST($11):DECIMAL(10, 0)), 0)], $f12=[CASE(=($18, 6), *($12, CAST($11):DECIMAL(10, 0)), 0)], $f13=[CASE(=($18, 7), *($12, CAST($11):DECIMAL(10, 0)), 0)], $f14=[CASE(=($18, 8), *($12, CAST($11):DECIMAL(10, 0)), 0)], $f15=[CASE(=($18, 9), *($12, CAST($11):DECIMAL(10, 0)), 0)], $f16=[CASE(=($18, 10), *($12, CAST($11):DECIMAL(10, 0)), 0)], $f17=[CASE(=($18, 11), *($12, CAST($11):DECIMAL(10, 0)), 0)], $f18=[CASE(=($18, 12), *($12, CAST($11):DECIMAL(10, 0)), 0)], $f19=[CASE(=($18, 1), *($13, CAST($11):DECIMAL(10, 0)), 0)], $f20=[CASE(=($18, 2), *($13, CAST($11):DECIMAL(10, 0)), 0)], $f21=[CASE(=($18, 3), *($13, CAST($11):DECIMAL(10, 0)), 0)], $f22=[CASE(=($18, 4), *($13, CAST($11):DECIMAL(10, 0)), 0)], $f23=[CASE(=($18, 5), *($13, CAST($11):DECIMAL(10, 0)), 0)], $f24=[CASE(=($18, 6), *($13, CAST($11):DECIMAL(10, 0)), 0)], $f25=[CASE(=($18, 7), *($13, CAST($11):DECIMAL(10, 0)), 0)], $f26=[CASE(=($18, 8), *($13, CAST($11):DECIMAL(10, 0)), 0)], $f27=[CASE(=($18, 9), *($13, CAST($11):DECIMAL(10, 0)), 0)], $f28=[CASE(=($18, 10), *($13, CAST($11):DECIMAL(10, 0)), 0)], $f29=[CASE(=($18, 11), *($13, CAST($11):DECIMAL(10, 0)), 0)], $f30=[CASE(=($18, 12), *($13, CAST($11):DECIMAL(10, 0)), 0)]) + HiveProject($f0=[$1], $f1=[$2], $f2=[$3], $f3=[$4], $f4=[$5], $f5=[$6], $f7=[CASE($15, $11, 0)], $f8=[CASE($16, $11, 0)], $f9=[CASE($17, $11, 0)], $f10=[CASE($18, $11, 0)], $f11=[CASE($19, $11, 0)], $f12=[CASE($20, $11, 0)], $f13=[CASE($21, $11, 0)], $f14=[CASE($22, $11, 0)], $f15=[CASE($23, $11, 0)], $f16=[CASE($24, $11, 0)], $f17=[CASE($25, $11, 0)], $f18=[CASE($26, $11, 0)], $f19=[CASE($15, $12, 0)], $f20=[CASE($16, $12, 0)], $f21=[CASE($17, $12, 0)], $f22=[CASE($18, $12, 0)], $f23=[CASE($19, $12, 0)], $f24=[CASE($20, $12, 0)], $f25=[CASE($21, $12, 0)], $f26=[CASE($22, $12, 0)], $f27=[CASE($23, $12, 0)], $f28=[CASE($24, $12, 0)], $f29=[CASE($25, $12, 0)], $f30=[CASE($26, $12, 0)]) HiveJoin(condition=[=($10, $0)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(w_warehouse_sk=[$0], w_warehouse_name=[$2], w_warehouse_sq_ft=[$3], w_city=[$8], w_county=[$9], w_state=[$10], w_country=[$12]) HiveFilter(condition=[IS NOT NULL($0)]) HiveTableScan(table=[[default, warehouse]], table:alias=[warehouse]) - HiveJoin(condition=[=($2, $12)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveJoin(condition=[=($0, $9)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveJoin(condition=[=($1, $7)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(ws_sold_date_sk=[$0], ws_sold_time_sk=[$1], ws_ship_mode_sk=[$14], ws_warehouse_sk=[$15], ws_quantity=[$18], ws_sales_price=[$21], ws_net_paid_inc_tax=[$30]) + HiveJoin(condition=[=($2, $20)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($0, $7)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($1, $6)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(ws_sold_date_sk=[$0], ws_sold_time_sk=[$1], ws_ship_mode_sk=[$14], ws_warehouse_sk=[$15], *=[*($21, CAST($18):DECIMAL(10, 0))], *5=[*($30, CAST($18):DECIMAL(10, 0))]) HiveFilter(condition=[AND(IS NOT NULL($15), IS NOT NULL($0), IS NOT NULL($1), IS NOT NULL($14))]) HiveTableScan(table=[[default, web_sales]], table:alias=[web_sales]) - HiveProject(t_time_sk=[$0], t_time=[$2]) + HiveProject(t_time_sk=[$0]) HiveFilter(condition=[AND(BETWEEN(false, $2, 49530, 78330), IS NOT NULL($0))]) HiveTableScan(table=[[default, time_dim]], table:alias=[time_dim]) - HiveProject(d_date_sk=[$0], d_year=[CAST(2002):INTEGER], d_moy=[$8]) + HiveProject(d_date_sk=[$0], ==[=($8, 1)], =2=[=($8, 2)], =3=[=($8, 3)], =4=[=($8, 4)], =5=[=($8, 5)], =6=[=($8, 6)], =7=[=($8, 7)], =8=[=($8, 8)], =9=[=($8, 9)], =10=[=($8, 10)], =11=[=($8, 11)], =12=[=($8, 12)]) HiveFilter(condition=[AND(=($6, 2002), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) - HiveProject(sm_ship_mode_sk=[$0], sm_carrier=[$4]) + HiveProject(sm_ship_mode_sk=[$0]) HiveFilter(condition=[AND(IN($4, _UTF-16LE'DIAMOND', _UTF-16LE'AIRBORNE'), IS NOT NULL($0))]) HiveTableScan(table=[[default, ship_mode]], table:alias=[ship_mode]) HiveProject($f0=[$0], $f1=[$1], $f2=[$2], $f3=[$3], $f4=[$4], $f5=[$5], $f6=[$6], $f7=[$7], $f8=[$8], $f9=[$9], $f10=[$10], $f11=[$11], $f12=[$12], $f13=[$13], $f14=[$14], $f15=[$15], $f16=[$16], $f17=[$17], $f18=[$18], $f19=[$19], $f20=[$20], $f21=[$21], $f22=[$22], $f23=[$23], $f24=[$24], $f25=[$25], $f26=[$26], $f27=[$27], $f28=[$28], $f29=[$29]) HiveAggregate(group=[{0, 1, 2, 3, 4, 5}], agg#0=[sum($6)], agg#1=[sum($7)], agg#2=[sum($8)], agg#3=[sum($9)], agg#4=[sum($10)], agg#5=[sum($11)], agg#6=[sum($12)], agg#7=[sum($13)], agg#8=[sum($14)], agg#9=[sum($15)], agg#10=[sum($16)], agg#11=[sum($17)], agg#12=[sum($18)], agg#13=[sum($19)], agg#14=[sum($20)], agg#15=[sum($21)], agg#16=[sum($22)], agg#17=[sum($23)], agg#18=[sum($24)], agg#19=[sum($25)], agg#20=[sum($26)], agg#21=[sum($27)], agg#22=[sum($28)], agg#23=[sum($29)]) - HiveProject($f0=[$15], $f1=[$16], $f2=[$17], $f3=[$18], $f4=[$19], $f5=[$20], $f7=[CASE(=($11, 1), *($5, CAST($4):DECIMAL(10, 0)), 0)], $f8=[CASE(=($11, 2), *($5, CAST($4):DECIMAL(10, 0)), 0)], $f9=[CASE(=($11, 3), *($5, CAST($4):DECIMAL(10, 0)), 0)], $f10=[CASE(=($11, 4), *($5, CAST($4):DECIMAL(10, 0)), 0)], $f11=[CASE(=($11, 5), *($5, CAST($4):DECIMAL(10, 0)), 0)], $f12=[CASE(=($11, 6), *($5, CAST($4):DECIMAL(10, 0)), 0)], $f13=[CASE(=($11, 7), *($5, CAST($4):DECIMAL(10, 0)), 0)], $f14=[CASE(=($11, 8), *($5, CAST($4):DECIMAL(10, 0)), 0)], $f15=[CASE(=($11, 9), *($5, CAST($4):DECIMAL(10, 0)), 0)], $f16=[CASE(=($11, 10), *($5, CAST($4):DECIMAL(10, 0)), 0)], $f17=[CASE(=($11, 11), *($5, CAST($4):DECIMAL(10, 0)), 0)], $f18=[CASE(=($11, 12), *($5, CAST($4):DECIMAL(10, 0)), 0)], $f19=[CASE(=($11, 1), *($6, CAST($4):DECIMAL(10, 0)), 0)], $f20=[CASE(=($11, 2), *($6, CAST($4):DECIMAL(10, 0)), 0)], $f21=[CASE(=($11, 3), *($6, CAST($4):DECIMAL(10, 0)), 0)], $f22=[CASE(=($11, 4), *($6, CAST($4):DECIMAL(10, 0)), 0)], $f23=[CASE(=($11, 5), *($6, CAST($4):DECIMAL(10, 0)), 0)], $f24=[CASE(=($11, 6), *($6, CAST($4):DECIMAL(10, 0)), 0)], $f25=[CASE(=($11, 7), *($6, CAST($4):DECIMAL(10, 0)), 0)], $f26=[CASE(=($11, 8), *($6, CAST($4):DECIMAL(10, 0)), 0)], $f27=[CASE(=($11, 9), *($6, CAST($4):DECIMAL(10, 0)), 0)], $f28=[CASE(=($11, 10), *($6, CAST($4):DECIMAL(10, 0)), 0)], $f29=[CASE(=($11, 11), *($6, CAST($4):DECIMAL(10, 0)), 0)], $f30=[CASE(=($11, 12), *($6, CAST($4):DECIMAL(10, 0)), 0)]) - HiveJoin(condition=[=($3, $14)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveJoin(condition=[=($2, $12)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveJoin(condition=[=($0, $9)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveJoin(condition=[=($1, $7)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(cs_sold_date_sk=[$0], cs_sold_time_sk=[$1], cs_ship_mode_sk=[$13], cs_warehouse_sk=[$14], cs_quantity=[$18], cs_ext_sales_price=[$23], cs_net_paid_inc_ship_tax=[$32]) + HiveProject($f0=[$22], $f1=[$23], $f2=[$24], $f3=[$25], $f4=[$26], $f5=[$27], $f7=[CASE($8, $4, 0)], $f8=[CASE($9, $4, 0)], $f9=[CASE($10, $4, 0)], $f10=[CASE($11, $4, 0)], $f11=[CASE($12, $4, 0)], $f12=[CASE($13, $4, 0)], $f13=[CASE($14, $4, 0)], $f14=[CASE($15, $4, 0)], $f15=[CASE($16, $4, 0)], $f16=[CASE($17, $4, 0)], $f17=[CASE($18, $4, 0)], $f18=[CASE($19, $4, 0)], $f19=[CASE($8, $5, 0)], $f20=[CASE($9, $5, 0)], $f21=[CASE($10, $5, 0)], $f22=[CASE($11, $5, 0)], $f23=[CASE($12, $5, 0)], $f24=[CASE($13, $5, 0)], $f25=[CASE($14, $5, 0)], $f26=[CASE($15, $5, 0)], $f27=[CASE($16, $5, 0)], $f28=[CASE($17, $5, 0)], $f29=[CASE($18, $5, 0)], $f30=[CASE($19, $5, 0)]) + HiveJoin(condition=[=($3, $21)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($2, $20)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($0, $7)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($1, $6)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(cs_sold_date_sk=[$0], cs_sold_time_sk=[$1], cs_ship_mode_sk=[$13], cs_warehouse_sk=[$14], *=[*($23, CAST($18):DECIMAL(10, 0))], *5=[*($32, CAST($18):DECIMAL(10, 0))]) HiveFilter(condition=[AND(IS NOT NULL($14), IS NOT NULL($0), IS NOT NULL($1), IS NOT NULL($13))]) HiveTableScan(table=[[default, catalog_sales]], table:alias=[catalog_sales]) - HiveProject(t_time_sk=[$0], t_time=[$2]) + HiveProject(t_time_sk=[$0]) HiveFilter(condition=[AND(BETWEEN(false, $2, 49530, 78330), IS NOT NULL($0))]) HiveTableScan(table=[[default, time_dim]], table:alias=[time_dim]) - HiveProject(d_date_sk=[$0], d_year=[CAST(2002):INTEGER], d_moy=[$8]) + HiveProject(d_date_sk=[$0], ==[=($8, 1)], =2=[=($8, 2)], =3=[=($8, 3)], =4=[=($8, 4)], =5=[=($8, 5)], =6=[=($8, 6)], =7=[=($8, 7)], =8=[=($8, 8)], =9=[=($8, 9)], =10=[=($8, 10)], =11=[=($8, 11)], =12=[=($8, 12)]) HiveFilter(condition=[AND(=($6, 2002), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) - HiveProject(sm_ship_mode_sk=[$0], sm_carrier=[$4]) + HiveProject(sm_ship_mode_sk=[$0]) HiveFilter(condition=[AND(IN($4, _UTF-16LE'DIAMOND', _UTF-16LE'AIRBORNE'), IS NOT NULL($0))]) HiveTableScan(table=[[default, ship_mode]], table:alias=[ship_mode]) HiveProject(w_warehouse_sk=[$0], w_warehouse_name=[$2], w_warehouse_sq_ft=[$3], w_city=[$8], w_county=[$9], w_state=[$10], w_country=[$12]) diff --git ql/src/test/results/clientpositive/perf/tez/cbo_query68.q.out ql/src/test/results/clientpositive/perf/tez/cbo_query68.q.out index cd71cda18dd..f14338cd8ae 100644 --- ql/src/test/results/clientpositive/perf/tez/cbo_query68.q.out +++ ql/src/test/results/clientpositive/perf/tez/cbo_query68.q.out @@ -111,19 +111,19 @@ HiveSortLimit(sort0=[$0], sort1=[$4], dir0=[ASC], dir1=[ASC], fetch=[100]) HiveProject(ca_address_sk=[$0], ca_city=[$6]) HiveFilter(condition=[IS NOT NULL($0)]) HiveTableScan(table=[[default, customer_address]], table:alias=[customer_address]) - HiveJoin(condition=[=($2, $14)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveJoin(condition=[=($4, $12)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($2, $11)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($4, $10)], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($0, $9)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(ss_sold_date_sk=[$0], ss_customer_sk=[$3], ss_hdemo_sk=[$5], ss_addr_sk=[$6], ss_store_sk=[$7], ss_ticket_number=[$9], ss_ext_sales_price=[$15], ss_ext_list_price=[$17], ss_ext_tax=[$18]) HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($7), IS NOT NULL($5), IS NOT NULL($6), IS NOT NULL($3))]) HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) - HiveProject(d_date_sk=[$0], d_year=[$6], d_dom=[$9]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(IN($6, 1998, 1999, 2000), BETWEEN(false, $9, 1, 2), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) - HiveProject(s_store_sk=[$0], s_city=[$22]) + HiveProject(s_store_sk=[$0]) HiveFilter(condition=[AND(IN($22, _UTF-16LE'Cedar Grove', _UTF-16LE'Wildwood'), IS NOT NULL($0))]) HiveTableScan(table=[[default, store]], table:alias=[store]) - HiveProject(hd_demo_sk=[$0], hd_dep_count=[$3], hd_vehicle_count=[$4]) + HiveProject(hd_demo_sk=[$0]) HiveFilter(condition=[AND(OR(=($3, 2), =($4, 1)), IS NOT NULL($0))]) HiveTableScan(table=[[default, household_demographics]], table:alias=[household_demographics]) diff --git ql/src/test/results/clientpositive/perf/tez/cbo_query69.q.out ql/src/test/results/clientpositive/perf/tez/cbo_query69.q.out index 9089fc8e33e..0cc24d321ef 100644 --- ql/src/test/results/clientpositive/perf/tez/cbo_query69.q.out +++ ql/src/test/results/clientpositive/perf/tez/cbo_query69.q.out @@ -132,7 +132,7 @@ HiveSortLimit(sort0=[$0], sort1=[$1], sort2=[$2], sort3=[$4], sort4=[$6], dir0=[ HiveProject(ss_sold_date_sk=[$0], ss_customer_sk=[$3]) HiveFilter(condition=[AND(IS NOT NULL($3), IS NOT NULL($0))]) HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) - HiveProject(d_date_sk=[$0], d_year=[CAST(1999):INTEGER], d_moy=[$8]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(=($6, 1999), BETWEEN(false, $8, 1, 3), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) HiveProject(ws_bill_customer_sk0=[$0], $f1=[true]) @@ -141,7 +141,7 @@ HiveSortLimit(sort0=[$0], sort1=[$1], sort2=[$2], sort3=[$4], sort4=[$6], dir0=[ HiveProject(ws_sold_date_sk=[$0], ws_bill_customer_sk=[$4]) HiveFilter(condition=[AND(IS NOT NULL($4), IS NOT NULL($0))]) HiveTableScan(table=[[default, web_sales]], table:alias=[web_sales]) - HiveProject(d_date_sk=[$0], d_year=[CAST(1999):INTEGER], d_moy=[$8]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(=($6, 1999), BETWEEN(false, $8, 1, 3), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) HiveProject(cs_ship_customer_sk0=[$0], $f1=[true]) @@ -150,7 +150,7 @@ HiveSortLimit(sort0=[$0], sort1=[$1], sort2=[$2], sort3=[$4], sort4=[$6], dir0=[ HiveProject(cs_sold_date_sk=[$0], cs_ship_customer_sk=[$7]) HiveFilter(condition=[AND(IS NOT NULL($7), IS NOT NULL($0))]) HiveTableScan(table=[[default, catalog_sales]], table:alias=[catalog_sales]) - HiveProject(d_date_sk=[$0], d_year=[CAST(1999):INTEGER], d_moy=[$8]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(=($6, 1999), BETWEEN(false, $8, 1, 3), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) diff --git ql/src/test/results/clientpositive/perf/tez/cbo_query7.q.out ql/src/test/results/clientpositive/perf/tez/cbo_query7.q.out index 29415ca75f7..d4c3ac61c1e 100644 --- ql/src/test/results/clientpositive/perf/tez/cbo_query7.q.out +++ ql/src/test/results/clientpositive/perf/tez/cbo_query7.q.out @@ -58,19 +58,19 @@ HiveSortLimit(sort0=[$0], dir0=[ASC], fetch=[100]) HiveProject(i_item_sk=[$0], i_item_id=[$1]) HiveFilter(condition=[IS NOT NULL($0)]) HiveTableScan(table=[[default, item]], table:alias=[item]) - HiveJoin(condition=[=($3, $14)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveJoin(condition=[=($0, $12)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($3, $10)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($0, $9)], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($2, $8)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(ss_sold_date_sk=[$0], ss_item_sk=[$2], ss_cdemo_sk=[$4], ss_promo_sk=[$8], ss_quantity=[$10], ss_list_price=[$12], ss_sales_price=[$13], ss_coupon_amt=[$19]) HiveFilter(condition=[AND(IS NOT NULL($4), IS NOT NULL($0), IS NOT NULL($2), IS NOT NULL($8))]) HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) - HiveProject(cd_demo_sk=[$0], cd_gender=[CAST(_UTF-16LE'F'):VARCHAR(2147483647) CHARACTER SET "UTF-16LE" COLLATE "ISO-8859-1$en_US$primary"], cd_marital_status=[CAST(_UTF-16LE'W'):VARCHAR(2147483647) CHARACTER SET "UTF-16LE" COLLATE "ISO-8859-1$en_US$primary"], cd_education_status=[CAST(_UTF-16LE'Primary'):VARCHAR(2147483647) CHARACTER SET "UTF-16LE" COLLATE "ISO-8859-1$en_US$primary"]) + HiveProject(cd_demo_sk=[$0]) HiveFilter(condition=[AND(=($1, _UTF-16LE'F'), =($2, _UTF-16LE'W'), =($3, _UTF-16LE'Primary'), IS NOT NULL($0))]) HiveTableScan(table=[[default, customer_demographics]], table:alias=[customer_demographics]) - HiveProject(d_date_sk=[$0], d_year=[CAST(1998):INTEGER]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(=($6, 1998), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) - HiveProject(p_promo_sk=[$0], p_channel_email=[$9], p_channel_event=[$14]) + HiveProject(p_promo_sk=[$0]) HiveFilter(condition=[AND(OR(=($9, _UTF-16LE'N'), =($14, _UTF-16LE'N')), IS NOT NULL($0))]) HiveTableScan(table=[[default, promotion]], table:alias=[promotion]) diff --git ql/src/test/results/clientpositive/perf/tez/cbo_query71.q.out ql/src/test/results/clientpositive/perf/tez/cbo_query71.q.out index 4e52893255e..20444c6616c 100644 --- ql/src/test/results/clientpositive/perf/tez/cbo_query71.q.out +++ ql/src/test/results/clientpositive/perf/tez/cbo_query71.q.out @@ -92,9 +92,9 @@ CBO PLAN: HiveProject(brand_id=[$0], brand=[$1], t_hour=[$2], t_minute=[$3], ext_price=[$4]) HiveSortLimit(sort0=[$4], sort1=[$5], dir0=[DESC-nulls-last], dir1=[ASC]) HiveProject(brand_id=[$2], brand=[$3], t_hour=[$0], t_minute=[$1], ext_price=[$4], (tok_table_or_col i_brand_id)=[$2]) - HiveAggregate(group=[{1, 2, 8, 9}], agg#0=[sum($4)]) - HiveJoin(condition=[=($6, $0)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(t_time_sk=[$0], t_hour=[$3], t_minute=[$4], t_meal_time=[$9]) + HiveAggregate(group=[{1, 2, 7, 8}], agg#0=[sum($3)]) + HiveJoin(condition=[=($5, $0)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(t_time_sk=[$0], t_hour=[$3], t_minute=[$4]) HiveFilter(condition=[AND(IN($9, _UTF-16LE'breakfast', _UTF-16LE'dinner'), IS NOT NULL($0))]) HiveTableScan(table=[[default, time_dim]], table:alias=[time_dim]) HiveJoin(condition=[=($1, $3)], joinType=[inner], algorithm=[none], cost=[not available]) @@ -105,7 +105,7 @@ HiveProject(brand_id=[$0], brand=[$1], t_hour=[$2], t_minute=[$3], ext_price=[$4 HiveProject(ws_sold_date_sk=[$0], ws_sold_time_sk=[$1], ws_item_sk=[$3], ws_ext_sales_price=[$23]) HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($3), IS NOT NULL($1))]) HiveTableScan(table=[[default, web_sales]], table:alias=[web_sales]) - HiveProject(d_date_sk=[$0], d_year=[CAST(2001):INTEGER], d_moy=[CAST(12):INTEGER]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(=($8, 12), =($6, 2001), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) HiveProject(ext_price=[$3], sold_item_sk=[$2], time_sk=[$1]) @@ -113,7 +113,7 @@ HiveProject(brand_id=[$0], brand=[$1], t_hour=[$2], t_minute=[$3], ext_price=[$4 HiveProject(cs_sold_date_sk=[$0], cs_sold_time_sk=[$1], cs_item_sk=[$15], cs_ext_sales_price=[$23]) HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($15), IS NOT NULL($1))]) HiveTableScan(table=[[default, catalog_sales]], table:alias=[catalog_sales]) - HiveProject(d_date_sk=[$0], d_year=[CAST(2001):INTEGER], d_moy=[CAST(12):INTEGER]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(=($8, 12), =($6, 2001), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) HiveProject(ext_price=[$3], sold_item_sk=[$2], time_sk=[$1]) @@ -121,10 +121,10 @@ HiveProject(brand_id=[$0], brand=[$1], t_hour=[$2], t_minute=[$3], ext_price=[$4 HiveProject(ss_sold_date_sk=[$0], ss_sold_time_sk=[$1], ss_item_sk=[$2], ss_ext_sales_price=[$15]) HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($2), IS NOT NULL($1))]) HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) - HiveProject(d_date_sk=[$0], d_year=[CAST(2001):INTEGER], d_moy=[CAST(12):INTEGER]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(=($8, 12), =($6, 2001), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) - HiveProject(i_item_sk=[$0], i_brand_id=[$7], i_brand=[$8], i_manager_id=[CAST(1):INTEGER]) + HiveProject(i_item_sk=[$0], i_brand_id=[$7], i_brand=[$8]) HiveFilter(condition=[AND(=($20, 1), IS NOT NULL($0))]) HiveTableScan(table=[[default, item]], table:alias=[item]) diff --git ql/src/test/results/clientpositive/perf/tez/cbo_query72.q.out ql/src/test/results/clientpositive/perf/tez/cbo_query72.q.out index fca31efa448..e49b44bf32d 100644 --- ql/src/test/results/clientpositive/perf/tez/cbo_query72.q.out +++ ql/src/test/results/clientpositive/perf/tez/cbo_query72.q.out @@ -82,10 +82,10 @@ CBO PLAN: HiveSortLimit(sort0=[$5], sort1=[$0], sort2=[$1], sort3=[$2], dir0=[DESC-nulls-last], dir1=[ASC], dir2=[ASC], dir3=[ASC], fetch=[100]) HiveProject($f0=[$0], $f1=[$1], $f2=[$2], $f3=[$3], $f4=[$4], $f5=[$5]) HiveAggregate(group=[{0, 1, 2}], agg#0=[count($3)], agg#1=[count($4)], agg#2=[count()]) - HiveProject($f0=[$15], $f1=[$13], $f2=[$22], $f3=[CASE(IS NULL($28), 1, 0)], $f4=[CASE(IS NOT NULL($28), 1, 0)]) - HiveJoin(condition=[AND(=($29, $4), =($30, $6))], joinType=[left], algorithm=[none], cost=[not available]) - HiveProject(cs_sold_date_sk=[$10], cs_ship_date_sk=[$11], cs_bill_cdemo_sk=[$12], cs_bill_hdemo_sk=[$13], cs_item_sk=[$14], cs_promo_sk=[$15], cs_order_number=[$16], cs_quantity=[$17], inv_date_sk=[$0], inv_item_sk=[$1], inv_warehouse_sk=[$2], inv_quantity_on_hand=[$3], w_warehouse_sk=[$4], w_warehouse_name=[$5], i_item_sk=[$8], i_item_desc=[$9], cd_demo_sk=[$22], cd_marital_status=[$23], hd_demo_sk=[$24], hd_buy_potential=[$25], d_date_sk=[$18], d_date=[$19], d_week_seq=[$20], d_year=[$21], d_date_sk0=[$27], d_week_seq0=[$28], d_date_sk1=[$6], d_date0=[$7], p_promo_sk=[$26]) - HiveJoin(condition=[AND(=($0, $27), =($20, $28))], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject($f0=[$15], $f1=[$13], $f2=[$19], $f3=[CASE(IS NULL($25), 1, 0)], $f4=[CASE(IS NOT NULL($25), 1, 0)]) + HiveJoin(condition=[AND(=($26, $4), =($27, $6))], joinType=[left], algorithm=[none], cost=[not available]) + HiveProject(cs_sold_date_sk=[$10], cs_ship_date_sk=[$11], cs_bill_cdemo_sk=[$12], cs_bill_hdemo_sk=[$13], cs_item_sk=[$14], cs_promo_sk=[$15], cs_order_number=[$16], cs_quantity=[$17], inv_date_sk=[$0], inv_item_sk=[$1], inv_warehouse_sk=[$2], inv_quantity_on_hand=[$3], w_warehouse_sk=[$4], w_warehouse_name=[$5], i_item_sk=[$8], i_item_desc=[$9], cd_demo_sk=[$21], hd_demo_sk=[$22], d_date_sk=[$18], d_week_seq=[$19], +=[$20], d_date_sk0=[$24], d_week_seq0=[$25], d_date_sk1=[$6], CAST=[$7], p_promo_sk=[$23]) + HiveJoin(condition=[AND(=($0, $24), =($19, $25))], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[AND(=($14, $1), <($3, $17))], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($4, $2)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(inv_date_sk=[$0], inv_item_sk=[$1], inv_warehouse_sk=[$2], inv_quantity_on_hand=[$3]) @@ -94,29 +94,29 @@ HiveSortLimit(sort0=[$5], sort1=[$0], sort2=[$1], sort3=[$2], dir0=[DESC-nulls-l HiveProject(w_warehouse_sk=[$0], w_warehouse_name=[$2]) HiveFilter(condition=[IS NOT NULL($0)]) HiveTableScan(table=[[default, warehouse]], table:alias=[warehouse]) - HiveProject(d_date_sk=[$0], d_date=[$1], i_item_sk=[$2], i_item_desc=[$3], cs_sold_date_sk=[$4], cs_ship_date_sk=[$5], cs_bill_cdemo_sk=[$6], cs_bill_hdemo_sk=[$7], cs_item_sk=[$8], cs_promo_sk=[$9], cs_order_number=[$10], cs_quantity=[$11], d_date_sk0=[$12], d_date0=[$13], d_week_seq=[$14], d_year=[$15], cd_demo_sk=[$16], cd_marital_status=[$17], hd_demo_sk=[$18], hd_buy_potential=[$19], p_promo_sk=[$20]) - HiveJoin(condition=[AND(=($5, $0), >(CAST($1):DOUBLE, +(CAST($13):DOUBLE, 5)))], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(d_date_sk=[$0], d_date=[$2]) + HiveProject(d_date_sk=[$0], CAST=[$1], i_item_sk=[$2], i_item_desc=[$3], cs_sold_date_sk=[$4], cs_ship_date_sk=[$5], cs_bill_cdemo_sk=[$6], cs_bill_hdemo_sk=[$7], cs_item_sk=[$8], cs_promo_sk=[$9], cs_order_number=[$10], cs_quantity=[$11], d_date_sk0=[$12], d_week_seq=[$13], +=[$14], cd_demo_sk=[$15], hd_demo_sk=[$16], p_promo_sk=[$17]) + HiveJoin(condition=[AND(=($5, $0), >($1, $14))], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(d_date_sk=[$0], CAST=[CAST($2):DOUBLE]) HiveFilter(condition=[IS NOT NULL($0)]) HiveTableScan(table=[[default, date_dim]], table:alias=[d3]) HiveJoin(condition=[=($0, $6)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(i_item_sk=[$0], i_item_desc=[$4]) HiveFilter(condition=[IS NOT NULL($0)]) HiveTableScan(table=[[default, item]], table:alias=[item]) - HiveJoin(condition=[=($5, $16)], joinType=[left], algorithm=[none], cost=[not available]) - HiveJoin(condition=[=($3, $14)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveJoin(condition=[=($2, $12)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($5, $13)], joinType=[left], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($3, $12)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($2, $11)], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($0, $8)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(cs_sold_date_sk=[$0], cs_ship_date_sk=[$2], cs_bill_cdemo_sk=[$4], cs_bill_hdemo_sk=[$5], cs_item_sk=[$15], cs_promo_sk=[$16], cs_order_number=[$17], cs_quantity=[$18]) HiveFilter(condition=[AND(IS NOT NULL($15), IS NOT NULL($4), IS NOT NULL($5), IS NOT NULL($0), IS NOT NULL($2))]) HiveTableScan(table=[[default, catalog_sales]], table:alias=[catalog_sales]) - HiveProject(d_date_sk=[$0], d_date=[$2], d_week_seq=[$4], d_year=[CAST(2001):INTEGER]) + HiveProject(d_date_sk=[$0], d_week_seq=[$4], +=[+(CAST($2):DOUBLE, 5)]) HiveFilter(condition=[AND(=($6, 2001), IS NOT NULL($0), IS NOT NULL($4))]) HiveTableScan(table=[[default, date_dim]], table:alias=[d1]) - HiveProject(cd_demo_sk=[$0], cd_marital_status=[CAST(_UTF-16LE'M'):VARCHAR(2147483647) CHARACTER SET "UTF-16LE" COLLATE "ISO-8859-1$en_US$primary"]) + HiveProject(cd_demo_sk=[$0]) HiveFilter(condition=[AND(=($2, _UTF-16LE'M'), IS NOT NULL($0))]) HiveTableScan(table=[[default, customer_demographics]], table:alias=[customer_demographics]) - HiveProject(hd_demo_sk=[$0], hd_buy_potential=[CAST(_UTF-16LE'1001-5000'):VARCHAR(2147483647) CHARACTER SET "UTF-16LE" COLLATE "ISO-8859-1$en_US$primary"]) + HiveProject(hd_demo_sk=[$0]) HiveFilter(condition=[AND(=($2, _UTF-16LE'1001-5000'), IS NOT NULL($0))]) HiveTableScan(table=[[default, household_demographics]], table:alias=[household_demographics]) HiveProject(p_promo_sk=[$0]) diff --git ql/src/test/results/clientpositive/perf/tez/cbo_query73.q.out ql/src/test/results/clientpositive/perf/tez/cbo_query73.q.out index d28a896fd7f..2639cf22b47 100644 --- ql/src/test/results/clientpositive/perf/tez/cbo_query73.q.out +++ ql/src/test/results/clientpositive/perf/tez/cbo_query73.q.out @@ -75,19 +75,19 @@ HiveSortLimit(sort0=[$5], dir0=[DESC-nulls-last]) HiveFilter(condition=[BETWEEN(false, $2, 1, 5)]) HiveProject(ss_ticket_number=[$1], ss_customer_sk=[$0], $f2=[$2]) HiveAggregate(group=[{1, 4}], agg#0=[count()]) - HiveJoin(condition=[=($3, $12)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveJoin(condition=[=($2, $8)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($3, $7)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($2, $6)], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($0, $5)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(ss_sold_date_sk=[$0], ss_customer_sk=[$3], ss_hdemo_sk=[$5], ss_store_sk=[$7], ss_ticket_number=[$9]) HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($7), IS NOT NULL($5), IS NOT NULL($3))]) HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) - HiveProject(d_date_sk=[$0], d_year=[$6], d_dom=[$9]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(IN($6, 2000, 2001, 2002), BETWEEN(false, $9, 1, 2), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) - HiveProject(hd_demo_sk=[$0], hd_buy_potential=[$2], hd_dep_count=[$3], hd_vehicle_count=[$4]) + HiveProject(hd_demo_sk=[$0]) HiveFilter(condition=[AND(IN($2, _UTF-16LE'>10000', _UTF-16LE'unknown'), >($4, 0), CASE(>($4, 0), >(/(CAST($3):DOUBLE, CAST($4):DOUBLE), 1), null), IS NOT NULL($0))]) HiveTableScan(table=[[default, household_demographics]], table:alias=[household_demographics]) - HiveProject(s_store_sk=[$0], s_county=[$23]) + HiveProject(s_store_sk=[$0]) HiveFilter(condition=[AND(IN($23, _UTF-16LE'Mobile County', _UTF-16LE'Maverick County', _UTF-16LE'Huron County', _UTF-16LE'Kittitas County'), IS NOT NULL($0))]) HiveTableScan(table=[[default, store]], table:alias=[store]) diff --git ql/src/test/results/clientpositive/perf/tez/cbo_query74.q.out ql/src/test/results/clientpositive/perf/tez/cbo_query74.q.out index 32d6e03706e..4a9a1127b30 100644 --- ql/src/test/results/clientpositive/perf/tez/cbo_query74.q.out +++ ql/src/test/results/clientpositive/perf/tez/cbo_query74.q.out @@ -131,9 +131,9 @@ POSTHOOK: Output: hdfs://### HDFS PATH ### CBO PLAN: HiveSortLimit(sort0=[$1], sort1=[$0], sort2=[$2], dir0=[ASC], dir1=[ASC], dir2=[ASC], fetch=[100]) HiveProject(customer_id=[$0], customer_first_name=[$1], customer_last_name=[$2]) - HiveJoin(condition=[AND(=($0, $6), CASE(CAST(IS NOT NULL($7)):BOOLEAN, CASE(CAST(IS NOT NULL($9)):BOOLEAN, >(/($5, $9), /($3, $7)), >(null, /($3, $7))), CASE(CAST(IS NOT NULL($9)):BOOLEAN, >(/($5, $9), null), null)))], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(customer_id=[$0], customer_first_name=[$1], customer_last_name=[$2], year_total=[$4]) - HiveAggregate(group=[{1, 2, 3, 8}], agg#0=[max($6)]) + HiveJoin(condition=[AND(=($0, $6), CASE(CAST(IS NOT NULL($7)):BOOLEAN, CASE($10, >(/($5, $9), /($3, $7)), >(null, /($3, $7))), CASE($10, >(/($5, $9), null), null)))], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(c_customer_id=[$0], c_first_name=[$1], c_last_name=[$2], $f3=[$3]) + HiveAggregate(group=[{1, 2, 3}], agg#0=[max($6)]) HiveJoin(condition=[=($0, $5)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(c_customer_sk=[$0], c_customer_id=[$1], c_first_name=[$8], c_last_name=[$9]) HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($1))]) @@ -142,13 +142,13 @@ HiveSortLimit(sort0=[$1], sort1=[$0], sort2=[$2], dir0=[ASC], dir1=[ASC], dir2=[ HiveProject(ss_sold_date_sk=[$0], ss_customer_sk=[$3], ss_net_paid=[$20]) HiveFilter(condition=[AND(IS NOT NULL($3), IS NOT NULL($0))]) HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) - HiveProject(d_date_sk=[$0], d_year=[CAST(2002):INTEGER]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(IN($6, 2001, 2002), =($6, 2002), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) HiveJoin(condition=[=($2, $4)], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($2, $0)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(customer_id=[$0], year_total=[$4]) - HiveAggregate(group=[{1, 2, 3, 8}], agg#0=[max($6)]) + HiveProject($f0=[$0], $f4=[$3]) + HiveAggregate(group=[{1, 2, 3}], agg#0=[max($6)]) HiveJoin(condition=[=($0, $5)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(c_customer_sk=[$0], c_customer_id=[$1], c_first_name=[$8], c_last_name=[$9]) HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($1))]) @@ -157,12 +157,12 @@ HiveSortLimit(sort0=[$1], sort1=[$0], sort2=[$2], dir0=[ASC], dir1=[ASC], dir2=[ HiveProject(ws_sold_date_sk=[$0], ws_bill_customer_sk=[$4], ws_net_paid=[$29]) HiveFilter(condition=[AND(IS NOT NULL($4), IS NOT NULL($0))]) HiveTableScan(table=[[default, web_sales]], table:alias=[web_sales]) - HiveProject(d_date_sk=[$0], d_year=[CAST(2002):INTEGER]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(IN($6, 2001, 2002), =($6, 2002), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) - HiveProject(customer_id=[$0], year_total=[$4]) - HiveFilter(condition=[>($4, 0)]) - HiveAggregate(group=[{1, 2, 3, 8}], agg#0=[max($6)]) + HiveProject($f0=[$0], $f4=[$3]) + HiveFilter(condition=[>($3, 0)]) + HiveAggregate(group=[{1, 2, 3}], agg#0=[max($6)]) HiveJoin(condition=[=($0, $5)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(c_customer_sk=[$0], c_customer_id=[$1], c_first_name=[$8], c_last_name=[$9]) HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($1))]) @@ -171,12 +171,12 @@ HiveSortLimit(sort0=[$1], sort1=[$0], sort2=[$2], dir0=[ASC], dir1=[ASC], dir2=[ HiveProject(ss_sold_date_sk=[$0], ss_customer_sk=[$3], ss_net_paid=[$20]) HiveFilter(condition=[AND(IS NOT NULL($3), IS NOT NULL($0))]) HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) - HiveProject(d_date_sk=[$0], d_year=[CAST(2001):INTEGER]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(IN($6, 2001, 2002), =($6, 2001), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) - HiveProject(customer_id=[$0], year_total=[$4]) - HiveFilter(condition=[>($4, 0)]) - HiveAggregate(group=[{1, 2, 3, 8}], agg#0=[max($6)]) + HiveProject(customer_id=[$0], year_total=[$3], CAST=[CAST(IS NOT NULL($3)):BOOLEAN]) + HiveFilter(condition=[>($3, 0)]) + HiveAggregate(group=[{1, 2, 3}], agg#0=[max($6)]) HiveJoin(condition=[=($0, $5)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(c_customer_sk=[$0], c_customer_id=[$1], c_first_name=[$8], c_last_name=[$9]) HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($1))]) @@ -185,7 +185,7 @@ HiveSortLimit(sort0=[$1], sort1=[$0], sort2=[$2], dir0=[ASC], dir1=[ASC], dir2=[ HiveProject(ws_sold_date_sk=[$0], ws_bill_customer_sk=[$4], ws_net_paid=[$29]) HiveFilter(condition=[AND(IS NOT NULL($4), IS NOT NULL($0))]) HiveTableScan(table=[[default, web_sales]], table:alias=[web_sales]) - HiveProject(d_date_sk=[$0], d_year=[CAST(2001):INTEGER]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(IN($6, 2001, 2002), =($6, 2001), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) diff --git ql/src/test/results/clientpositive/perf/tez/cbo_query75.q.out ql/src/test/results/clientpositive/perf/tez/cbo_query75.q.out index 3d87d1b088e..8c445d9de51 100644 --- ql/src/test/results/clientpositive/perf/tez/cbo_query75.q.out +++ ql/src/test/results/clientpositive/perf/tez/cbo_query75.q.out @@ -169,52 +169,52 @@ HiveProject(prev_year=[CAST(2001):INTEGER], year=[CAST(2002):INTEGER], i_brand_i HiveAggregate(group=[{0, 1, 2, 3, 4, 5}]) HiveProject(i_brand_id=[$0], i_class_id=[$1], i_category_id=[$2], i_manufact_id=[$3], sales_cnt=[$4], sales_amt=[$5]) HiveUnion(all=[true]) - HiveProject(i_brand_id=[$12], i_class_id=[$13], i_category_id=[$14], i_manufact_id=[$16], sales_cnt=[-($7, CASE(IS NOT NULL($2), $2, 0))], sales_amt=[-($8, CASE(IS NOT NULL($3), $3, 0))]) + HiveProject(i_brand_id=[$11], i_class_id=[$12], i_category_id=[$13], i_manufact_id=[$14], sales_cnt=[-($7, CASE(IS NOT NULL($2), $2, 0))], sales_amt=[-($8, CASE(IS NOT NULL($3), $3, 0))]) HiveJoin(condition=[AND(=($6, $1), =($5, $0))], joinType=[right], algorithm=[none], cost=[not available]) HiveProject(cr_item_sk=[$2], cr_order_number=[$16], cr_return_quantity=[$17], cr_return_amount=[$18]) HiveFilter(condition=[IS NOT NULL($2)]) HiveTableScan(table=[[default, catalog_returns]], table:alias=[catalog_returns]) - HiveJoin(condition=[=($7, $1)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($6, $1)], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($5, $0)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(cs_sold_date_sk=[$0], cs_item_sk=[$15], cs_order_number=[$17], cs_quantity=[$18], cs_ext_sales_price=[$23]) HiveFilter(condition=[AND(IS NOT NULL($15), IS NOT NULL($0))]) HiveTableScan(table=[[default, catalog_sales]], table:alias=[catalog_sales]) - HiveProject(d_date_sk=[$0], d_year=[CAST(2001):INTEGER]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(=($6, 2001), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) - HiveProject(i_item_sk=[$0], i_brand_id=[$7], i_class_id=[$9], i_category_id=[$11], i_category=[CAST(_UTF-16LE'Sports'):VARCHAR(2147483647) CHARACTER SET "UTF-16LE" COLLATE "ISO-8859-1$en_US$primary"], i_manufact_id=[$13]) + HiveProject(i_item_sk=[$0], i_brand_id=[$7], i_class_id=[$9], i_category_id=[$11], i_manufact_id=[$13]) HiveFilter(condition=[AND(=($12, _UTF-16LE'Sports'), IS NOT NULL($0), IS NOT NULL($7), IS NOT NULL($9), IS NOT NULL($11), IS NOT NULL($13))]) HiveTableScan(table=[[default, item]], table:alias=[item]) - HiveProject(i_brand_id=[$12], i_class_id=[$13], i_category_id=[$14], i_manufact_id=[$16], sales_cnt=[-($7, CASE(IS NOT NULL($2), $2, 0))], sales_amt=[-($8, CASE(IS NOT NULL($3), $3, 0))]) + HiveProject(i_brand_id=[$11], i_class_id=[$12], i_category_id=[$13], i_manufact_id=[$14], sales_cnt=[-($7, CASE(IS NOT NULL($2), $2, 0))], sales_amt=[-($8, CASE(IS NOT NULL($3), $3, 0))]) HiveJoin(condition=[AND(=($6, $1), =($5, $0))], joinType=[right], algorithm=[none], cost=[not available]) HiveProject(sr_item_sk=[$2], sr_ticket_number=[$9], sr_return_quantity=[$10], sr_return_amt=[$11]) HiveFilter(condition=[IS NOT NULL($2)]) HiveTableScan(table=[[default, store_returns]], table:alias=[store_returns]) - HiveJoin(condition=[=($7, $1)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($6, $1)], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($5, $0)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(ss_sold_date_sk=[$0], ss_item_sk=[$2], ss_ticket_number=[$9], ss_quantity=[$10], ss_ext_sales_price=[$15]) HiveFilter(condition=[AND(IS NOT NULL($2), IS NOT NULL($0))]) HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) - HiveProject(d_date_sk=[$0], d_year=[CAST(2001):INTEGER]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(=($6, 2001), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) - HiveProject(i_item_sk=[$0], i_brand_id=[$7], i_class_id=[$9], i_category_id=[$11], i_category=[CAST(_UTF-16LE'Sports'):VARCHAR(2147483647) CHARACTER SET "UTF-16LE" COLLATE "ISO-8859-1$en_US$primary"], i_manufact_id=[$13]) + HiveProject(i_item_sk=[$0], i_brand_id=[$7], i_class_id=[$9], i_category_id=[$11], i_manufact_id=[$13]) HiveFilter(condition=[AND(=($12, _UTF-16LE'Sports'), IS NOT NULL($0), IS NOT NULL($7), IS NOT NULL($9), IS NOT NULL($11), IS NOT NULL($13))]) HiveTableScan(table=[[default, item]], table:alias=[item]) - HiveProject(i_brand_id=[$12], i_class_id=[$13], i_category_id=[$14], i_manufact_id=[$16], sales_cnt=[-($7, CASE(IS NOT NULL($2), $2, 0))], sales_amt=[-($8, CASE(IS NOT NULL($3), $3, 0))]) + HiveProject(i_brand_id=[$11], i_class_id=[$12], i_category_id=[$13], i_manufact_id=[$14], sales_cnt=[-($7, CASE(IS NOT NULL($2), $2, 0))], sales_amt=[-($8, CASE(IS NOT NULL($3), $3, 0))]) HiveJoin(condition=[AND(=($6, $1), =($5, $0))], joinType=[right], algorithm=[none], cost=[not available]) HiveProject(wr_item_sk=[$2], wr_order_number=[$13], wr_return_quantity=[$14], wr_return_amt=[$15]) HiveFilter(condition=[IS NOT NULL($2)]) HiveTableScan(table=[[default, web_returns]], table:alias=[web_returns]) - HiveJoin(condition=[=($7, $1)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($6, $1)], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($5, $0)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(ws_sold_date_sk=[$0], ws_item_sk=[$3], ws_order_number=[$17], ws_quantity=[$18], ws_ext_sales_price=[$23]) HiveFilter(condition=[AND(IS NOT NULL($3), IS NOT NULL($0))]) HiveTableScan(table=[[default, web_sales]], table:alias=[web_sales]) - HiveProject(d_date_sk=[$0], d_year=[CAST(2001):INTEGER]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(=($6, 2001), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) - HiveProject(i_item_sk=[$0], i_brand_id=[$7], i_class_id=[$9], i_category_id=[$11], i_category=[CAST(_UTF-16LE'Sports'):VARCHAR(2147483647) CHARACTER SET "UTF-16LE" COLLATE "ISO-8859-1$en_US$primary"], i_manufact_id=[$13]) + HiveProject(i_item_sk=[$0], i_brand_id=[$7], i_class_id=[$9], i_category_id=[$11], i_manufact_id=[$13]) HiveFilter(condition=[AND(=($12, _UTF-16LE'Sports'), IS NOT NULL($0), IS NOT NULL($7), IS NOT NULL($9), IS NOT NULL($11), IS NOT NULL($13))]) HiveTableScan(table=[[default, item]], table:alias=[item]) HiveProject(i_brand_id=[$0], i_class_id=[$1], i_category_id=[$2], i_manufact_id=[$3], $f4=[$4], $f5=[$5]) @@ -227,52 +227,52 @@ HiveProject(prev_year=[CAST(2001):INTEGER], year=[CAST(2002):INTEGER], i_brand_i HiveAggregate(group=[{0, 1, 2, 3, 4, 5}]) HiveProject(i_brand_id=[$0], i_class_id=[$1], i_category_id=[$2], i_manufact_id=[$3], sales_cnt=[$4], sales_amt=[$5]) HiveUnion(all=[true]) - HiveProject(i_brand_id=[$12], i_class_id=[$13], i_category_id=[$14], i_manufact_id=[$16], sales_cnt=[-($7, CASE(IS NOT NULL($2), $2, 0))], sales_amt=[-($8, CASE(IS NOT NULL($3), $3, 0))]) + HiveProject(i_brand_id=[$11], i_class_id=[$12], i_category_id=[$13], i_manufact_id=[$14], sales_cnt=[-($7, CASE(IS NOT NULL($2), $2, 0))], sales_amt=[-($8, CASE(IS NOT NULL($3), $3, 0))]) HiveJoin(condition=[AND(=($6, $1), =($5, $0))], joinType=[right], algorithm=[none], cost=[not available]) HiveProject(cr_item_sk=[$2], cr_order_number=[$16], cr_return_quantity=[$17], cr_return_amount=[$18]) HiveFilter(condition=[IS NOT NULL($2)]) HiveTableScan(table=[[default, catalog_returns]], table:alias=[catalog_returns]) - HiveJoin(condition=[=($7, $1)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($6, $1)], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($5, $0)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(cs_sold_date_sk=[$0], cs_item_sk=[$15], cs_order_number=[$17], cs_quantity=[$18], cs_ext_sales_price=[$23]) HiveFilter(condition=[AND(IS NOT NULL($15), IS NOT NULL($0))]) HiveTableScan(table=[[default, catalog_sales]], table:alias=[catalog_sales]) - HiveProject(d_date_sk=[$0], d_year=[CAST(2002):INTEGER]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(=($6, 2002), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) - HiveProject(i_item_sk=[$0], i_brand_id=[$7], i_class_id=[$9], i_category_id=[$11], i_category=[CAST(_UTF-16LE'Sports'):VARCHAR(2147483647) CHARACTER SET "UTF-16LE" COLLATE "ISO-8859-1$en_US$primary"], i_manufact_id=[$13]) + HiveProject(i_item_sk=[$0], i_brand_id=[$7], i_class_id=[$9], i_category_id=[$11], i_manufact_id=[$13]) HiveFilter(condition=[AND(=($12, _UTF-16LE'Sports'), IS NOT NULL($0), IS NOT NULL($7), IS NOT NULL($9), IS NOT NULL($11), IS NOT NULL($13))]) HiveTableScan(table=[[default, item]], table:alias=[item]) - HiveProject(i_brand_id=[$12], i_class_id=[$13], i_category_id=[$14], i_manufact_id=[$16], sales_cnt=[-($7, CASE(IS NOT NULL($2), $2, 0))], sales_amt=[-($8, CASE(IS NOT NULL($3), $3, 0))]) + HiveProject(i_brand_id=[$11], i_class_id=[$12], i_category_id=[$13], i_manufact_id=[$14], sales_cnt=[-($7, CASE(IS NOT NULL($2), $2, 0))], sales_amt=[-($8, CASE(IS NOT NULL($3), $3, 0))]) HiveJoin(condition=[AND(=($6, $1), =($5, $0))], joinType=[right], algorithm=[none], cost=[not available]) HiveProject(sr_item_sk=[$2], sr_ticket_number=[$9], sr_return_quantity=[$10], sr_return_amt=[$11]) HiveFilter(condition=[IS NOT NULL($2)]) HiveTableScan(table=[[default, store_returns]], table:alias=[store_returns]) - HiveJoin(condition=[=($7, $1)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($6, $1)], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($5, $0)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(ss_sold_date_sk=[$0], ss_item_sk=[$2], ss_ticket_number=[$9], ss_quantity=[$10], ss_ext_sales_price=[$15]) HiveFilter(condition=[AND(IS NOT NULL($2), IS NOT NULL($0))]) HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) - HiveProject(d_date_sk=[$0], d_year=[CAST(2002):INTEGER]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(=($6, 2002), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) - HiveProject(i_item_sk=[$0], i_brand_id=[$7], i_class_id=[$9], i_category_id=[$11], i_category=[CAST(_UTF-16LE'Sports'):VARCHAR(2147483647) CHARACTER SET "UTF-16LE" COLLATE "ISO-8859-1$en_US$primary"], i_manufact_id=[$13]) + HiveProject(i_item_sk=[$0], i_brand_id=[$7], i_class_id=[$9], i_category_id=[$11], i_manufact_id=[$13]) HiveFilter(condition=[AND(=($12, _UTF-16LE'Sports'), IS NOT NULL($0), IS NOT NULL($7), IS NOT NULL($9), IS NOT NULL($11), IS NOT NULL($13))]) HiveTableScan(table=[[default, item]], table:alias=[item]) - HiveProject(i_brand_id=[$12], i_class_id=[$13], i_category_id=[$14], i_manufact_id=[$16], sales_cnt=[-($7, CASE(IS NOT NULL($2), $2, 0))], sales_amt=[-($8, CASE(IS NOT NULL($3), $3, 0))]) + HiveProject(i_brand_id=[$11], i_class_id=[$12], i_category_id=[$13], i_manufact_id=[$14], sales_cnt=[-($7, CASE(IS NOT NULL($2), $2, 0))], sales_amt=[-($8, CASE(IS NOT NULL($3), $3, 0))]) HiveJoin(condition=[AND(=($6, $1), =($5, $0))], joinType=[right], algorithm=[none], cost=[not available]) HiveProject(wr_item_sk=[$2], wr_order_number=[$13], wr_return_quantity=[$14], wr_return_amt=[$15]) HiveFilter(condition=[IS NOT NULL($2)]) HiveTableScan(table=[[default, web_returns]], table:alias=[web_returns]) - HiveJoin(condition=[=($7, $1)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($6, $1)], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($5, $0)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(ws_sold_date_sk=[$0], ws_item_sk=[$3], ws_order_number=[$17], ws_quantity=[$18], ws_ext_sales_price=[$23]) HiveFilter(condition=[AND(IS NOT NULL($3), IS NOT NULL($0))]) HiveTableScan(table=[[default, web_sales]], table:alias=[web_sales]) - HiveProject(d_date_sk=[$0], d_year=[CAST(2002):INTEGER]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(=($6, 2002), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) - HiveProject(i_item_sk=[$0], i_brand_id=[$7], i_class_id=[$9], i_category_id=[$11], i_category=[CAST(_UTF-16LE'Sports'):VARCHAR(2147483647) CHARACTER SET "UTF-16LE" COLLATE "ISO-8859-1$en_US$primary"], i_manufact_id=[$13]) + HiveProject(i_item_sk=[$0], i_brand_id=[$7], i_class_id=[$9], i_category_id=[$11], i_manufact_id=[$13]) HiveFilter(condition=[AND(=($12, _UTF-16LE'Sports'), IS NOT NULL($0), IS NOT NULL($7), IS NOT NULL($9), IS NOT NULL($11), IS NOT NULL($13))]) HiveTableScan(table=[[default, item]], table:alias=[item]) diff --git ql/src/test/results/clientpositive/perf/tez/cbo_query76.q.out ql/src/test/results/clientpositive/perf/tez/cbo_query76.q.out index 74f888cffaf..740d03818ef 100644 --- ql/src/test/results/clientpositive/perf/tez/cbo_query76.q.out +++ ql/src/test/results/clientpositive/perf/tez/cbo_query76.q.out @@ -62,7 +62,7 @@ HiveSortLimit(sort0=[$0], sort1=[$1], sort2=[$2], sort3=[$3], sort4=[$4], dir0=[ HiveAggregate(group=[{0, 1, 2, 3, 4}], agg#0=[count()], agg#1=[sum($5)]) HiveProject(channel=[$0], col_name=[$1], d_year=[$2], d_qoy=[$3], i_category=[$4], ext_sales_price=[$5]) HiveUnion(all=[true]) - HiveProject(channel=[_UTF-16LE'store'], col_name=[_UTF-16LE'ss_addr_sk'], d_year=[$1], d_qoy=[$2], i_category=[$4], ext_sales_price=[$8]) + HiveProject(channel=[_UTF-16LE'store'], col_name=[_UTF-16LE'ss_addr_sk'], d_year=[$1], d_qoy=[$2], i_category=[$4], ext_sales_price=[$7]) HiveJoin(condition=[=($5, $0)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(d_date_sk=[$0], d_year=[$6], d_qoy=[$10]) HiveFilter(condition=[IS NOT NULL($0)]) @@ -71,13 +71,13 @@ HiveSortLimit(sort0=[$0], sort1=[$1], sort2=[$2], sort3=[$3], sort4=[$4], dir0=[ HiveProject(i_item_sk=[$0], i_category=[$12]) HiveFilter(condition=[IS NOT NULL($0)]) HiveTableScan(table=[[default, item]], table:alias=[item]) - HiveProject(ss_sold_date_sk=[$0], ss_item_sk=[$2], ss_addr_sk=[null], ss_ext_sales_price=[$15]) + HiveProject(ss_sold_date_sk=[$0], ss_item_sk=[$2], ss_ext_sales_price=[$15]) HiveFilter(condition=[AND(IS NULL($6), IS NOT NULL($2), IS NOT NULL($0))]) HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) - HiveProject(channel=[_UTF-16LE'web'], col_name=[_UTF-16LE'ws_web_page_sk'], d_year=[$7], d_qoy=[$8], i_category=[$5], ext_sales_price=[$3]) - HiveJoin(condition=[=($0, $6)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveJoin(condition=[=($1, $4)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(ws_sold_date_sk=[$0], ws_item_sk=[$3], ws_web_page_sk=[null], ws_ext_sales_price=[$23]) + HiveProject(channel=[_UTF-16LE'web'], col_name=[_UTF-16LE'ws_web_page_sk'], d_year=[$6], d_qoy=[$7], i_category=[$4], ext_sales_price=[$2]) + HiveJoin(condition=[=($0, $5)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($1, $3)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(ws_sold_date_sk=[$0], ws_item_sk=[$3], ws_ext_sales_price=[$23]) HiveFilter(condition=[AND(IS NULL($12), IS NOT NULL($3), IS NOT NULL($0))]) HiveTableScan(table=[[default, web_sales]], table:alias=[web_sales]) HiveProject(i_item_sk=[$0], i_category=[$12]) @@ -86,10 +86,10 @@ HiveSortLimit(sort0=[$0], sort1=[$1], sort2=[$2], sort3=[$3], sort4=[$4], dir0=[ HiveProject(d_date_sk=[$0], d_year=[$6], d_qoy=[$10]) HiveFilter(condition=[IS NOT NULL($0)]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) - HiveProject(channel=[_UTF-16LE'catalog'], col_name=[_UTF-16LE'cs_warehouse_sk'], d_year=[$7], d_qoy=[$8], i_category=[$5], ext_sales_price=[$3]) - HiveJoin(condition=[=($0, $6)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveJoin(condition=[=($2, $4)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(cs_sold_date_sk=[$0], cs_warehouse_sk=[null], cs_item_sk=[$15], cs_ext_sales_price=[$23]) + HiveProject(channel=[_UTF-16LE'catalog'], col_name=[_UTF-16LE'cs_warehouse_sk'], d_year=[$6], d_qoy=[$7], i_category=[$4], ext_sales_price=[$2]) + HiveJoin(condition=[=($0, $5)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($1, $3)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(cs_sold_date_sk=[$0], cs_item_sk=[$15], cs_ext_sales_price=[$23]) HiveFilter(condition=[AND(IS NULL($14), IS NOT NULL($15), IS NOT NULL($0))]) HiveTableScan(table=[[default, catalog_sales]], table:alias=[catalog_sales]) HiveProject(i_item_sk=[$0], i_category=[$12]) diff --git ql/src/test/results/clientpositive/perf/tez/cbo_query77.q.out ql/src/test/results/clientpositive/perf/tez/cbo_query77.q.out index 2c42995747f..91ad054e660 100644 --- ql/src/test/results/clientpositive/perf/tez/cbo_query77.q.out +++ ql/src/test/results/clientpositive/perf/tez/cbo_query77.q.out @@ -240,13 +240,13 @@ HiveSortLimit(sort0=[$0], sort1=[$1], dir0=[ASC], dir1=[ASC], fetch=[100]) HiveProject(channel=[_UTF-16LE'store channel'], id=[$0], sales=[$1], returns=[CASE(IS NOT NULL($4), $4, 0)], profit=[-($2, CASE(IS NOT NULL($5), $5, 0))]) HiveJoin(condition=[=($0, $3)], joinType=[left], algorithm=[none], cost=[not available]) HiveProject(s_store_sk=[$0], $f1=[$1], $f2=[$2]) - HiveAggregate(group=[{6}], agg#0=[sum($2)], agg#1=[sum($3)]) - HiveJoin(condition=[=($1, $6)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveAggregate(group=[{5}], agg#0=[sum($2)], agg#1=[sum($3)]) + HiveJoin(condition=[=($1, $5)], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($0, $4)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(ss_sold_date_sk=[$0], ss_store_sk=[$7], ss_ext_sales_price=[$15], ss_net_profit=[$22]) HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($7))]) HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) - HiveProject(d_date_sk=[$0], d_date=[$2]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(BETWEEN(false, CAST($2):TIMESTAMP(9), 1998-08-04 00:00:00, 1998-09-03 00:00:00), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) HiveProject(s_store_sk=[$0]) @@ -262,7 +262,7 @@ HiveSortLimit(sort0=[$0], sort1=[$1], dir0=[ASC], dir1=[ASC], fetch=[100]) HiveProject(sr_returned_date_sk=[$0], sr_store_sk=[$7], sr_return_amt=[$11], sr_net_loss=[$19]) HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($7))]) HiveTableScan(table=[[default, store_returns]], table:alias=[store_returns]) - HiveProject(d_date_sk=[$0], d_date=[$2]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(BETWEEN(false, CAST($2):TIMESTAMP(9), 1998-08-04 00:00:00, 1998-09-03 00:00:00), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) HiveProject(channel=[_UTF-16LE'catalog channel'], id=[$0], sales=[$1], returns=[$3], profit=[-($2, $4)]) @@ -273,7 +273,7 @@ HiveSortLimit(sort0=[$0], sort1=[$1], dir0=[ASC], dir1=[ASC], fetch=[100]) HiveProject(cs_sold_date_sk=[$0], cs_call_center_sk=[$11], cs_ext_sales_price=[$23], cs_net_profit=[$33]) HiveFilter(condition=[IS NOT NULL($0)]) HiveTableScan(table=[[default, catalog_sales]], table:alias=[catalog_sales]) - HiveProject(d_date_sk=[$0], d_date=[$2]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(BETWEEN(false, CAST($2):TIMESTAMP(9), 1998-08-04 00:00:00, 1998-09-03 00:00:00), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) HiveProject($f0=[$0], $f1=[$1]) @@ -282,7 +282,7 @@ HiveSortLimit(sort0=[$0], sort1=[$1], dir0=[ASC], dir1=[ASC], fetch=[100]) HiveProject(cr_returned_date_sk=[$0], cr_return_amount=[$18], cr_net_loss=[$26]) HiveFilter(condition=[IS NOT NULL($0)]) HiveTableScan(table=[[default, catalog_returns]], table:alias=[catalog_returns]) - HiveProject(d_date_sk=[$0], d_date=[$2]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(BETWEEN(false, CAST($2):TIMESTAMP(9), 1998-08-04 00:00:00, 1998-09-03 00:00:00), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) HiveProject(channel=[_UTF-16LE'web channel'], id=[$0], sales=[$1], returns=[CASE(IS NOT NULL($4), $4, 0)], profit=[-($2, CASE(IS NOT NULL($5), $5, 0))]) @@ -297,7 +297,7 @@ HiveSortLimit(sort0=[$0], sort1=[$1], dir0=[ASC], dir1=[ASC], fetch=[100]) HiveProject(ws_sold_date_sk=[$0], ws_web_page_sk=[$12], ws_ext_sales_price=[$23], ws_net_profit=[$33]) HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($12))]) HiveTableScan(table=[[default, web_sales]], table:alias=[web_sales]) - HiveProject(d_date_sk=[$0], d_date=[$2]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(BETWEEN(false, CAST($2):TIMESTAMP(9), 1998-08-04 00:00:00, 1998-09-03 00:00:00), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) HiveProject(wp_web_page_sk=[$0], $f1=[$1], $f2=[$2]) @@ -310,7 +310,7 @@ HiveSortLimit(sort0=[$0], sort1=[$1], dir0=[ASC], dir1=[ASC], fetch=[100]) HiveProject(wr_returned_date_sk=[$0], wr_web_page_sk=[$11], wr_return_amt=[$15], wr_net_loss=[$23]) HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($11))]) HiveTableScan(table=[[default, web_returns]], table:alias=[web_returns]) - HiveProject(d_date_sk=[$0], d_date=[$2]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(BETWEEN(false, CAST($2):TIMESTAMP(9), 1998-08-04 00:00:00, 1998-09-03 00:00:00), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) diff --git ql/src/test/results/clientpositive/perf/tez/cbo_query78.q.out ql/src/test/results/clientpositive/perf/tez/cbo_query78.q.out index 66b345ce689..02635826f03 100644 --- ql/src/test/results/clientpositive/perf/tez/cbo_query78.q.out +++ ql/src/test/results/clientpositive/perf/tez/cbo_query78.q.out @@ -139,12 +139,12 @@ HiveSortLimit(fetch=[100]) HiveFilter(condition=[CASE(IS NOT NULL($7), >($7, 0), false)]) HiveJoin(condition=[AND(=($5, $0), =($6, $1))], joinType=[left], algorithm=[none], cost=[not available]) HiveProject(ss_item_sk=[$0], ss_customer_sk=[$1], $f2=[$2], $f3=[$3], $f4=[$4]) - HiveAggregate(group=[{3, 4}], agg#0=[sum($6)], agg#1=[sum($7)], agg#2=[sum($8)]) - HiveJoin(condition=[=($2, $0)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(d_date_sk=[$0], d_year=[CAST(2000):INTEGER]) + HiveAggregate(group=[{2, 3}], agg#0=[sum($4)], agg#1=[sum($5)], agg#2=[sum($6)]) + HiveJoin(condition=[=($1, $0)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(=($6, 2000), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) - HiveProject(ss_sold_date_sk=[$0], ss_item_sk=[$1], ss_customer_sk=[$2], ss_ticket_number=[$3], ss_quantity=[$4], ss_wholesale_cost=[$5], ss_sales_price=[$6], sr_item_sk=[$7], sr_ticket_number=[$8]) + HiveProject(ss_sold_date_sk=[$0], ss_item_sk=[$1], ss_customer_sk=[$2], ss_quantity=[$4], ss_wholesale_cost=[$5], ss_sales_price=[$6]) HiveFilter(condition=[IS NULL($8)]) HiveJoin(condition=[AND(=($8, $3), =($1, $7))], joinType=[left], algorithm=[none], cost=[not available]) HiveProject(ss_sold_date_sk=[$0], ss_item_sk=[$2], ss_customer_sk=[$3], ss_ticket_number=[$9], ss_quantity=[$10], ss_wholesale_cost=[$11], ss_sales_price=[$13]) @@ -153,12 +153,12 @@ HiveSortLimit(fetch=[100]) HiveProject(sr_item_sk=[$2], sr_ticket_number=[$9]) HiveTableScan(table=[[default, store_returns]], table:alias=[store_returns]) HiveProject(ws_item_sk=[$0], ws_bill_customer_sk=[$1], $f2=[$2], $f3=[$3], $f4=[$4]) - HiveAggregate(group=[{3, 4}], agg#0=[sum($6)], agg#1=[sum($7)], agg#2=[sum($8)]) - HiveJoin(condition=[=($2, $0)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(d_date_sk=[$0], d_year=[CAST(2000):INTEGER]) + HiveAggregate(group=[{2, 3}], agg#0=[sum($4)], agg#1=[sum($5)], agg#2=[sum($6)]) + HiveJoin(condition=[=($1, $0)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(=($6, 2000), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) - HiveProject(ws_sold_date_sk=[$0], ws_item_sk=[$1], ws_bill_customer_sk=[$2], ws_order_number=[$3], ws_quantity=[$4], ws_wholesale_cost=[$5], ws_sales_price=[$6], wr_item_sk=[$7], wr_order_number=[$8]) + HiveProject(ws_sold_date_sk=[$0], ws_item_sk=[$1], ws_bill_customer_sk=[$2], ws_quantity=[$4], ws_wholesale_cost=[$5], ws_sales_price=[$6]) HiveFilter(condition=[IS NULL($8)]) HiveJoin(condition=[AND(=($8, $3), =($1, $7))], joinType=[left], algorithm=[none], cost=[not available]) HiveProject(ws_sold_date_sk=[$0], ws_item_sk=[$3], ws_bill_customer_sk=[$4], ws_order_number=[$17], ws_quantity=[$18], ws_wholesale_cost=[$19], ws_sales_price=[$21]) @@ -167,12 +167,12 @@ HiveSortLimit(fetch=[100]) HiveProject(wr_item_sk=[$2], wr_order_number=[$13]) HiveTableScan(table=[[default, web_returns]], table:alias=[web_returns]) HiveProject($f2=[$0], $f3=[$2], $f4=[$3], $f5=[$4]) - HiveAggregate(group=[{3, 4}], agg#0=[sum($6)], agg#1=[sum($7)], agg#2=[sum($8)]) - HiveJoin(condition=[=($2, $0)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(d_date_sk=[$0], d_year=[CAST(2000):INTEGER]) + HiveAggregate(group=[{2, 3}], agg#0=[sum($4)], agg#1=[sum($5)], agg#2=[sum($6)]) + HiveJoin(condition=[=($1, $0)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(=($6, 2000), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) - HiveProject(cs_sold_date_sk=[$0], cs_bill_customer_sk=[$1], cs_item_sk=[$2], cs_order_number=[$3], cs_quantity=[$4], cs_wholesale_cost=[$5], cs_sales_price=[$6], cr_item_sk=[$7], cr_order_number=[$8]) + HiveProject(cs_sold_date_sk=[$0], cs_bill_customer_sk=[$1], cs_item_sk=[$2], cs_quantity=[$4], cs_wholesale_cost=[$5], cs_sales_price=[$6]) HiveFilter(condition=[IS NULL($8)]) HiveJoin(condition=[AND(=($8, $3), =($2, $7))], joinType=[left], algorithm=[none], cost=[not available]) HiveProject(cs_sold_date_sk=[$0], cs_bill_customer_sk=[$3], cs_item_sk=[$15], cs_order_number=[$17], cs_quantity=[$18], cs_wholesale_cost=[$19], cs_sales_price=[$21]) diff --git ql/src/test/results/clientpositive/perf/tez/cbo_query79.q.out ql/src/test/results/clientpositive/perf/tez/cbo_query79.q.out index 6da8ac2300e..4317c1b7641 100644 --- ql/src/test/results/clientpositive/perf/tez/cbo_query79.q.out +++ ql/src/test/results/clientpositive/perf/tez/cbo_query79.q.out @@ -57,26 +57,26 @@ POSTHOOK: Output: hdfs://### HDFS PATH ### CBO PLAN: HiveProject(c_last_name=[$0], c_first_name=[$1], _o__c2=[$2], ss_ticket_number=[$3], amt=[$4], profit=[$5]) HiveSortLimit(sort0=[$0], sort1=[$1], sort2=[$6], sort3=[$5], dir0=[ASC], dir1=[ASC], dir2=[ASC], dir3=[ASC], fetch=[100]) - HiveProject(c_last_name=[$2], c_first_name=[$1], _o__c2=[substr($5, 1, 30)], ss_ticket_number=[$3], amt=[$6], profit=[$7], (tok_function substr (tok_table_or_col s_city) 1 30)=[substr($5, 1, 30)]) + HiveProject(c_last_name=[$2], c_first_name=[$1], _o__c2=[$8], ss_ticket_number=[$3], amt=[$6], profit=[$7], (tok_function substr (tok_table_or_col s_city) 1 30)=[substr($5, 1, 30)]) HiveJoin(condition=[=($4, $0)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(c_customer_sk=[$0], c_first_name=[$8], c_last_name=[$9]) HiveFilter(condition=[IS NOT NULL($0)]) HiveTableScan(table=[[default, customer]], table:alias=[customer]) - HiveProject(ss_ticket_number=[$2], ss_customer_sk=[$0], s_city=[$3], amt=[$4], profit=[$5]) - HiveAggregate(group=[{1, 3, 5, 13}], agg#0=[sum($6)], agg#1=[sum($7)]) - HiveJoin(condition=[=($2, $14)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveJoin(condition=[=($4, $11)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(ss_ticket_number=[$2], ss_customer_sk=[$0], s_city=[$3], amt=[$4], profit=[$5], substr=[substr($3, 1, 30)]) + HiveAggregate(group=[{1, 3, 5, 10}], agg#0=[sum($6)], agg#1=[sum($7)]) + HiveJoin(condition=[=($2, $11)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($4, $9)], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($0, $8)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(ss_sold_date_sk=[$0], ss_customer_sk=[$3], ss_hdemo_sk=[$5], ss_addr_sk=[$6], ss_store_sk=[$7], ss_ticket_number=[$9], ss_coupon_amt=[$19], ss_net_profit=[$22]) HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($7), IS NOT NULL($5), IS NOT NULL($3))]) HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) - HiveProject(d_date_sk=[$0], d_year=[$6], d_dow=[CAST(1):INTEGER]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(IN($6, 1998, 1999, 2000), =($7, 1), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) - HiveProject(s_store_sk=[$0], s_number_employees=[$6], s_city=[$22]) + HiveProject(s_store_sk=[$0], s_city=[$22]) HiveFilter(condition=[AND(BETWEEN(false, $6, 200, 295), IS NOT NULL($0))]) HiveTableScan(table=[[default, store]], table:alias=[store]) - HiveProject(hd_demo_sk=[$0], hd_dep_count=[$3], hd_vehicle_count=[$4]) + HiveProject(hd_demo_sk=[$0]) HiveFilter(condition=[AND(OR(=($3, 8), >($4, 0)), IS NOT NULL($0))]) HiveTableScan(table=[[default, household_demographics]], table:alias=[household_demographics]) diff --git ql/src/test/results/clientpositive/perf/tez/cbo_query8.q.out ql/src/test/results/clientpositive/perf/tez/cbo_query8.q.out index 5c4f7a26ff5..d80d3365d97 100644 --- ql/src/test/results/clientpositive/perf/tez/cbo_query8.q.out +++ ql/src/test/results/clientpositive/perf/tez/cbo_query8.q.out @@ -227,18 +227,18 @@ POSTHOOK: Output: hdfs://### HDFS PATH ### CBO PLAN: HiveSortLimit(sort0=[$0], dir0=[ASC], fetch=[100]) HiveProject(s_store_name=[$0], $f1=[$1]) - HiveAggregate(group=[{8}], agg#0=[sum($2)]) - HiveJoin(condition=[=($1, $7)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveAggregate(group=[{6}], agg#0=[sum($2)]) + HiveJoin(condition=[=($1, $5)], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($0, $3)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(ss_sold_date_sk=[$0], ss_store_sk=[$7], ss_net_profit=[$22]) HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($7))]) HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) - HiveProject(d_date_sk=[$0], d_year=[CAST(2002):INTEGER], d_qoy=[CAST(1):INTEGER]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(=($10, 1), =($6, 2002), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) - HiveProject($f0=[$0], s_store_sk=[$1], s_store_name=[$2], s_zip=[$3]) - HiveJoin(condition=[=(substr($3, 1, 2), substr($0, 1, 2))], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject($f0=[$0]) + HiveProject(substr=[$0], s_store_sk=[$1], s_store_name=[$2], substr0=[$3]) + HiveJoin(condition=[=($3, $0)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(substr=[substr($0, 1, 2)]) HiveFilter(condition=[=($1, 2)]) HiveAggregate(group=[{0}], agg#0=[count($1)]) HiveProject(ca_zip=[$0], $f1=[$1]) @@ -257,10 +257,10 @@ HiveSortLimit(sort0=[$0], dir0=[ASC], fetch=[100]) HiveProject(ca_address_sk=[$0], ca_zip=[$9]) HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL(substr(substr($9, 1, 5), 1, 2)))]) HiveTableScan(table=[[default, customer_address]], table:alias=[customer_address]) - HiveProject(c_current_addr_sk=[$4], c_preferred_cust_flag=[CAST(_UTF-16LE'Y'):VARCHAR(2147483647) CHARACTER SET "UTF-16LE" COLLATE "ISO-8859-1$en_US$primary"]) + HiveProject(c_current_addr_sk=[$4]) HiveFilter(condition=[AND(=($10, _UTF-16LE'Y'), IS NOT NULL($4))]) HiveTableScan(table=[[default, customer]], table:alias=[customer]) - HiveProject(s_store_sk=[$0], s_store_name=[$5], s_zip=[$25]) + HiveProject(s_store_sk=[$0], s_store_name=[$5], substr=[substr($25, 1, 2)]) HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL(substr($25, 1, 2)))]) HiveTableScan(table=[[default, store]], table:alias=[store]) diff --git ql/src/test/results/clientpositive/perf/tez/cbo_query80.q.out ql/src/test/results/clientpositive/perf/tez/cbo_query80.q.out index 9c4329473d5..334f09cc33d 100644 --- ql/src/test/results/clientpositive/perf/tez/cbo_query80.q.out +++ ql/src/test/results/clientpositive/perf/tez/cbo_query80.q.out @@ -222,14 +222,14 @@ HiveSortLimit(sort0=[$0], sort1=[$1], dir0=[ASC], dir1=[ASC], fetch=[100]) HiveUnion(all=[true]) HiveProject(channel=[_UTF-16LE'store channel'], id=[||(_UTF-16LE'store', $0)], sales=[$1], returns=[$2], profit=[$3]) HiveAggregate(group=[{0}], agg#0=[sum($1)], agg#1=[sum($2)], agg#2=[sum($3)]) - HiveProject($f0=[$1], $f1=[$9], $f2=[CASE(IS NOT NULL($13), $13, 0)], $f3=[-($10, CASE(IS NOT NULL($14), $14, 0))]) - HiveJoin(condition=[=($6, $0)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject($f0=[$1], $f1=[$8], $f2=[CASE(IS NOT NULL($12), $12, 0)], $f3=[-($9, CASE(IS NOT NULL($13), $13, 0))]) + HiveJoin(condition=[=($5, $0)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(s_store_sk=[$0], s_store_id=[$1]) HiveFilter(condition=[IS NOT NULL($0)]) HiveTableScan(table=[[default, store]], table:alias=[store]) - HiveJoin(condition=[=($5, $15)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveJoin(condition=[=($3, $0)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(i_item_sk=[$0], i_current_price=[$5]) + HiveJoin(condition=[=($4, $13)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($2, $0)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(i_item_sk=[$0]) HiveFilter(condition=[AND(>($5, 50), IS NOT NULL($0))]) HiveTableScan(table=[[default, item]], table:alias=[item]) HiveJoin(condition=[=($0, $11)], joinType=[inner], algorithm=[none], cost=[not available]) @@ -240,22 +240,22 @@ HiveSortLimit(sort0=[$0], sort1=[$1], dir0=[ASC], dir1=[ASC], fetch=[100]) HiveProject(sr_item_sk=[$2], sr_ticket_number=[$9], sr_return_amt=[$11], sr_net_loss=[$19]) HiveFilter(condition=[IS NOT NULL($2)]) HiveTableScan(table=[[default, store_returns]], table:alias=[store_returns]) - HiveProject(d_date_sk=[$0], d_date=[$2]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(BETWEEN(false, CAST($2):TIMESTAMP(9), 1998-08-04 00:00:00, 1998-09-03 00:00:00), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) - HiveProject(p_promo_sk=[$0], p_channel_tv=[CAST(_UTF-16LE'N'):VARCHAR(2147483647) CHARACTER SET "UTF-16LE" COLLATE "ISO-8859-1$en_US$primary"]) + HiveProject(p_promo_sk=[$0]) HiveFilter(condition=[AND(=($11, _UTF-16LE'N'), IS NOT NULL($0))]) HiveTableScan(table=[[default, promotion]], table:alias=[promotion]) HiveProject(channel=[_UTF-16LE'catalog channel'], id=[||(_UTF-16LE'catalog_page', $0)], sales=[$1], returns=[$2], profit=[$3]) HiveAggregate(group=[{0}], agg#0=[sum($1)], agg#1=[sum($2)], agg#2=[sum($3)]) - HiveProject($f0=[$1], $f1=[$9], $f2=[CASE(IS NOT NULL($13), $13, 0)], $f3=[-($10, CASE(IS NOT NULL($14), $14, 0))]) - HiveJoin(condition=[=($5, $0)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject($f0=[$1], $f1=[$8], $f2=[CASE(IS NOT NULL($12), $12, 0)], $f3=[-($9, CASE(IS NOT NULL($13), $13, 0))]) + HiveJoin(condition=[=($4, $0)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(cp_catalog_page_sk=[$0], cp_catalog_page_id=[$1]) HiveFilter(condition=[IS NOT NULL($0)]) HiveTableScan(table=[[default, catalog_page]], table:alias=[catalog_page]) - HiveJoin(condition=[=($5, $15)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveJoin(condition=[=($4, $0)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(i_item_sk=[$0], i_current_price=[$5]) + HiveJoin(condition=[=($4, $13)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($3, $0)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(i_item_sk=[$0]) HiveFilter(condition=[AND(>($5, 50), IS NOT NULL($0))]) HiveTableScan(table=[[default, item]], table:alias=[item]) HiveJoin(condition=[=($0, $11)], joinType=[inner], algorithm=[none], cost=[not available]) @@ -266,22 +266,22 @@ HiveSortLimit(sort0=[$0], sort1=[$1], dir0=[ASC], dir1=[ASC], fetch=[100]) HiveProject(cr_item_sk=[$2], cr_order_number=[$16], cr_return_amount=[$18], cr_net_loss=[$26]) HiveFilter(condition=[IS NOT NULL($2)]) HiveTableScan(table=[[default, catalog_returns]], table:alias=[catalog_returns]) - HiveProject(d_date_sk=[$0], d_date=[$2]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(BETWEEN(false, CAST($2):TIMESTAMP(9), 1998-08-04 00:00:00, 1998-09-03 00:00:00), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) - HiveProject(p_promo_sk=[$0], p_channel_tv=[CAST(_UTF-16LE'N'):VARCHAR(2147483647) CHARACTER SET "UTF-16LE" COLLATE "ISO-8859-1$en_US$primary"]) + HiveProject(p_promo_sk=[$0]) HiveFilter(condition=[AND(=($11, _UTF-16LE'N'), IS NOT NULL($0))]) HiveTableScan(table=[[default, promotion]], table:alias=[promotion]) HiveProject(channel=[_UTF-16LE'web channel'], id=[||(_UTF-16LE'web_site', $0)], sales=[$1], returns=[$2], profit=[$3]) HiveAggregate(group=[{0}], agg#0=[sum($1)], agg#1=[sum($2)], agg#2=[sum($3)]) - HiveProject($f0=[$18], $f1=[$9], $f2=[CASE(IS NOT NULL($13), $13, 0)], $f3=[-($10, CASE(IS NOT NULL($14), $14, 0))]) - HiveJoin(condition=[=($6, $17)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveJoin(condition=[=($7, $0)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(p_promo_sk=[$0], p_channel_tv=[CAST(_UTF-16LE'N'):VARCHAR(2147483647) CHARACTER SET "UTF-16LE" COLLATE "ISO-8859-1$en_US$primary"]) + HiveProject($f0=[$15], $f1=[$7], $f2=[CASE(IS NOT NULL($11), $11, 0)], $f3=[-($8, CASE(IS NOT NULL($12), $12, 0))]) + HiveJoin(condition=[=($4, $14)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($5, $0)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(p_promo_sk=[$0]) HiveFilter(condition=[AND(=($11, _UTF-16LE'N'), IS NOT NULL($0))]) HiveTableScan(table=[[default, promotion]], table:alias=[promotion]) - HiveJoin(condition=[=($3, $0)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(i_item_sk=[$0], i_current_price=[$5]) + HiveJoin(condition=[=($2, $0)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(i_item_sk=[$0]) HiveFilter(condition=[AND(>($5, 50), IS NOT NULL($0))]) HiveTableScan(table=[[default, item]], table:alias=[item]) HiveJoin(condition=[=($0, $11)], joinType=[inner], algorithm=[none], cost=[not available]) @@ -292,7 +292,7 @@ HiveSortLimit(sort0=[$0], sort1=[$1], dir0=[ASC], dir1=[ASC], fetch=[100]) HiveProject(wr_item_sk=[$2], wr_order_number=[$13], wr_return_amt=[$15], wr_net_loss=[$23]) HiveFilter(condition=[IS NOT NULL($2)]) HiveTableScan(table=[[default, web_returns]], table:alias=[web_returns]) - HiveProject(d_date_sk=[$0], d_date=[$2]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(BETWEEN(false, CAST($2):TIMESTAMP(9), 1998-08-04 00:00:00, 1998-09-03 00:00:00), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) HiveProject(web_site_sk=[$0], web_site_id=[$1]) diff --git ql/src/test/results/clientpositive/perf/tez/cbo_query81.q.out ql/src/test/results/clientpositive/perf/tez/cbo_query81.q.out index e13017f61dc..0adb5551da0 100644 --- ql/src/test/results/clientpositive/perf/tez/cbo_query81.q.out +++ ql/src/test/results/clientpositive/perf/tez/cbo_query81.q.out @@ -71,13 +71,13 @@ POSTHOOK: Output: hdfs://### HDFS PATH ### CBO PLAN: HiveProject(c_customer_id=[$0], c_salutation=[$1], c_first_name=[$2], c_last_name=[$3], ca_street_number=[$4], ca_street_name=[$5], ca_street_type=[$6], ca_suite_number=[$7], ca_city=[$8], ca_county=[$9], ca_state=[CAST(_UTF-16LE'IL'):VARCHAR(2147483647) CHARACTER SET "UTF-16LE" COLLATE "ISO-8859-1$en_US$primary"], ca_zip=[$10], ca_country=[$11], ca_gmt_offset=[$12], ca_location_type=[$13], ctr_total_return=[$14]) HiveSortLimit(sort0=[$0], sort1=[$1], sort2=[$2], sort3=[$3], sort4=[$4], sort5=[$5], sort6=[$6], sort7=[$7], sort8=[$8], sort9=[$9], sort10=[$10], sort11=[$11], sort12=[$12], sort13=[$13], sort14=[$14], dir0=[ASC], dir1=[ASC], dir2=[ASC], dir3=[ASC], dir4=[ASC], dir5=[ASC], dir6=[ASC], dir7=[ASC], dir8=[ASC], dir9=[ASC], dir10=[ASC], dir11=[ASC], dir12=[ASC], dir13=[ASC], dir14=[ASC], fetch=[100]) - HiveProject(c_customer_id=[$1], c_salutation=[$3], c_first_name=[$4], c_last_name=[$5], ca_street_number=[$7], ca_street_name=[$8], ca_street_type=[$9], ca_suite_number=[$10], ca_city=[$11], ca_county=[$12], ca_zip=[$14], ca_country=[$15], ca_gmt_offset=[$16], ca_location_type=[$17], ctr_total_return=[$20]) - HiveJoin(condition=[=($18, $0)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(c_customer_id=[$1], c_salutation=[$3], c_first_name=[$4], c_last_name=[$5], ca_street_number=[$7], ca_street_name=[$8], ca_street_type=[$9], ca_suite_number=[$10], ca_city=[$11], ca_county=[$12], ca_zip=[$13], ca_country=[$14], ca_gmt_offset=[$15], ca_location_type=[$16], ctr_total_return=[$19]) + HiveJoin(condition=[=($17, $0)], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($6, $2)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(c_customer_sk=[$0], c_customer_id=[$1], c_current_addr_sk=[$4], c_salutation=[$7], c_first_name=[$8], c_last_name=[$9]) HiveFilter(condition=[AND(IS NOT NULL($4), IS NOT NULL($0))]) HiveTableScan(table=[[default, customer]], table:alias=[customer]) - HiveProject(ca_address_sk=[$0], ca_street_number=[$2], ca_street_name=[$3], ca_street_type=[$4], ca_suite_number=[$5], ca_city=[$6], ca_county=[$7], ca_state=[CAST(_UTF-16LE'IL'):VARCHAR(2147483647) CHARACTER SET "UTF-16LE" COLLATE "ISO-8859-1$en_US$primary"], ca_zip=[$9], ca_country=[$10], ca_gmt_offset=[$11], ca_location_type=[$12]) + HiveProject(ca_address_sk=[$0], ca_street_number=[$2], ca_street_name=[$3], ca_street_type=[$4], ca_suite_number=[$5], ca_city=[$6], ca_county=[$7], ca_zip=[$9], ca_country=[$10], ca_gmt_offset=[$11], ca_location_type=[$12]) HiveFilter(condition=[AND(=($8, _UTF-16LE'IL'), IS NOT NULL($0))]) HiveTableScan(table=[[default, customer_address]], table:alias=[customer_address]) HiveProject(cr_returning_customer_sk=[$0], ca_state=[$1], $f2=[$2], _o__c0=[$3], ctr_state=[$4]) @@ -92,7 +92,7 @@ HiveProject(c_customer_id=[$0], c_salutation=[$1], c_first_name=[$2], c_last_nam HiveProject(cr_returned_date_sk=[$0], cr_returning_customer_sk=[$7], cr_returning_addr_sk=[$10], cr_return_amt_inc_tax=[$20]) HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($10), IS NOT NULL($7))]) HiveTableScan(table=[[default, catalog_returns]], table:alias=[catalog_returns]) - HiveProject(d_date_sk=[$0], d_year=[CAST(1998):INTEGER]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(=($6, 1998), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) HiveProject(_o__c0=[*(/($1, $2), 1.2)], ctr_state=[$0]) @@ -107,7 +107,7 @@ HiveProject(c_customer_id=[$0], c_salutation=[$1], c_first_name=[$2], c_last_nam HiveProject(cr_returned_date_sk=[$0], cr_returning_customer_sk=[$7], cr_returning_addr_sk=[$10], cr_return_amt_inc_tax=[$20]) HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($10))]) HiveTableScan(table=[[default, catalog_returns]], table:alias=[catalog_returns]) - HiveProject(d_date_sk=[$0], d_year=[CAST(1998):INTEGER]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(=($6, 1998), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) diff --git ql/src/test/results/clientpositive/perf/tez/cbo_query82.q.out ql/src/test/results/clientpositive/perf/tez/cbo_query82.q.out index 08d99929973..a60312f11bd 100644 --- ql/src/test/results/clientpositive/perf/tez/cbo_query82.q.out +++ ql/src/test/results/clientpositive/perf/tez/cbo_query82.q.out @@ -44,20 +44,20 @@ CBO PLAN: HiveSortLimit(sort0=[$0], dir0=[ASC], fetch=[100]) HiveProject(i_item_id=[$0], i_item_desc=[$1], i_current_price=[$2]) HiveAggregate(group=[{2, 3, 4}]) - HiveJoin(condition=[=($7, $1)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($6, $1)], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($0, $1)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(ss_item_sk=[$2]) HiveFilter(condition=[IS NOT NULL($2)]) HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) - HiveProject(i_item_sk=[$0], i_item_id=[$1], i_item_desc=[$4], i_current_price=[$5], i_manufact_id=[$13]) + HiveProject(i_item_sk=[$0], i_item_id=[$1], i_item_desc=[$4], i_current_price=[$5]) HiveFilter(condition=[AND(IN($13, 437, 129, 727, 663), BETWEEN(false, $5, 30, 60), IS NOT NULL($0))]) HiveTableScan(table=[[default, item]], table:alias=[item]) - HiveProject(inv_date_sk=[$0], inv_item_sk=[$1], inv_quantity_on_hand=[$2], d_date_sk=[$3], d_date=[$4]) - HiveJoin(condition=[=($3, $0)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(inv_date_sk=[$0], inv_item_sk=[$1], inv_quantity_on_hand=[$3]) + HiveProject(inv_date_sk=[$0], inv_item_sk=[$1], d_date_sk=[$2]) + HiveJoin(condition=[=($2, $0)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(inv_date_sk=[$0], inv_item_sk=[$1]) HiveFilter(condition=[AND(BETWEEN(false, $3, 100, 500), IS NOT NULL($1), IS NOT NULL($0))]) HiveTableScan(table=[[default, inventory]], table:alias=[inventory]) - HiveProject(d_date_sk=[$0], d_date=[$2]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(BETWEEN(false, CAST($2):TIMESTAMP(9), 2002-05-30 00:00:00, 2002-07-29 00:00:00), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) diff --git ql/src/test/results/clientpositive/perf/tez/cbo_query83.q.out ql/src/test/results/clientpositive/perf/tez/cbo_query83.q.out index d5a3d667eaf..0e61e45ad54 100644 --- ql/src/test/results/clientpositive/perf/tez/cbo_query83.q.out +++ ql/src/test/results/clientpositive/perf/tez/cbo_query83.q.out @@ -144,10 +144,10 @@ POSTHOOK: Input: default@web_returns POSTHOOK: Output: hdfs://### HDFS PATH ### CBO PLAN: HiveSortLimit(sort0=[$0], sort1=[$1], dir0=[ASC], dir1=[ASC], fetch=[100]) - HiveProject(item_id=[$0], sr_item_qty=[$3], sr_dev=[*(/(/(CAST($3):DOUBLE, CAST(+(+($3, $1), $5)):DOUBLE), CAST(3):DOUBLE), CAST(100):DOUBLE)], cr_item_qty=[$1], cr_dev=[*(/(/(CAST($1):DOUBLE, CAST(+(+($3, $1), $5)):DOUBLE), CAST(3):DOUBLE), CAST(100):DOUBLE)], wr_item_qty=[$5], wr_dev=[*(/(/(CAST($5):DOUBLE, CAST(+(+($3, $1), $5)):DOUBLE), CAST(3):DOUBLE), CAST(100):DOUBLE)], average=[/(CAST(+(+($3, $1), $5)):DECIMAL(19, 0), 3)]) - HiveJoin(condition=[=($0, $4)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveJoin(condition=[=($2, $0)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(i_item_id=[$0], $f1=[$1]) + HiveProject(item_id=[$0], sr_item_qty=[$4], sr_dev=[*(/(/($5, CAST(+(+($4, $1), $7)):DOUBLE), CAST(3):DOUBLE), CAST(100):DOUBLE)], cr_item_qty=[$1], cr_dev=[*(/(/($2, CAST(+(+($4, $1), $7)):DOUBLE), CAST(3):DOUBLE), CAST(100):DOUBLE)], wr_item_qty=[$7], wr_dev=[*(/(/($8, CAST(+(+($4, $1), $7)):DOUBLE), CAST(3):DOUBLE), CAST(100):DOUBLE)], average=[/(CAST(+(+($4, $1), $7)):DECIMAL(19, 0), 3)]) + HiveJoin(condition=[=($0, $6)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($3, $0)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject($f0=[$0], $f1=[$1], CAST=[CAST($1):DOUBLE]) HiveAggregate(group=[{4}], agg#0=[sum($2)]) HiveJoin(condition=[=($0, $5)], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($1, $3)], joinType=[inner], algorithm=[none], cost=[not available]) @@ -171,7 +171,7 @@ HiveSortLimit(sort0=[$0], sort1=[$1], dir0=[ASC], dir1=[ASC], fetch=[100]) HiveProject(d_date_sk=[$0], d_date_id=[$1], d_date=[$2], d_month_seq=[$3], d_week_seq=[$4], d_quarter_seq=[$5], d_year=[$6], d_dow=[$7], d_moy=[$8], d_dom=[$9], d_qoy=[$10], d_fy_year=[$11], d_fy_quarter_seq=[$12], d_fy_week_seq=[$13], d_day_name=[$14], d_quarter_name=[$15], d_holiday=[$16], d_weekend=[$17], d_following_holiday=[$18], d_first_dom=[$19], d_last_dom=[$20], d_same_day_ly=[$21], d_same_day_lq=[$22], d_current_day=[$23], d_current_week=[$24], d_current_month=[$25], d_current_quarter=[$26], d_current_year=[$27], BLOCK__OFFSET__INSIDE__FILE=[$28], INPUT__FILE__NAME=[$29], ROW__ID=[$30]) HiveFilter(condition=[AND(IN($2, _UTF-16LE'1998-01-02', _UTF-16LE'1998-10-15', _UTF-16LE'1998-11-10'), IS NOT NULL($4))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) - HiveProject(i_item_id=[$0], $f1=[$1]) + HiveProject($f0=[$0], $f1=[$1], CAST=[CAST($1):DOUBLE]) HiveAggregate(group=[{4}], agg#0=[sum($2)]) HiveJoin(condition=[=($0, $5)], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($1, $3)], joinType=[inner], algorithm=[none], cost=[not available]) @@ -195,7 +195,7 @@ HiveSortLimit(sort0=[$0], sort1=[$1], dir0=[ASC], dir1=[ASC], fetch=[100]) HiveProject(d_date_sk=[$0], d_date_id=[$1], d_date=[$2], d_month_seq=[$3], d_week_seq=[$4], d_quarter_seq=[$5], d_year=[$6], d_dow=[$7], d_moy=[$8], d_dom=[$9], d_qoy=[$10], d_fy_year=[$11], d_fy_quarter_seq=[$12], d_fy_week_seq=[$13], d_day_name=[$14], d_quarter_name=[$15], d_holiday=[$16], d_weekend=[$17], d_following_holiday=[$18], d_first_dom=[$19], d_last_dom=[$20], d_same_day_ly=[$21], d_same_day_lq=[$22], d_current_day=[$23], d_current_week=[$24], d_current_month=[$25], d_current_quarter=[$26], d_current_year=[$27], BLOCK__OFFSET__INSIDE__FILE=[$28], INPUT__FILE__NAME=[$29], ROW__ID=[$30]) HiveFilter(condition=[AND(IN($2, _UTF-16LE'1998-01-02', _UTF-16LE'1998-10-15', _UTF-16LE'1998-11-10'), IS NOT NULL($4))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) - HiveProject(i_item_id=[$0], $f1=[$1]) + HiveProject($f0=[$0], $f1=[$1], CAST=[CAST($1):DOUBLE]) HiveAggregate(group=[{4}], agg#0=[sum($2)]) HiveJoin(condition=[=($0, $5)], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($1, $3)], joinType=[inner], algorithm=[none], cost=[not available]) diff --git ql/src/test/results/clientpositive/perf/tez/cbo_query84.q.out ql/src/test/results/clientpositive/perf/tez/cbo_query84.q.out index de765ab8367..006f70365eb 100644 --- ql/src/test/results/clientpositive/perf/tez/cbo_query84.q.out +++ ql/src/test/results/clientpositive/perf/tez/cbo_query84.q.out @@ -55,7 +55,7 @@ POSTHOOK: Output: hdfs://### HDFS PATH ### CBO PLAN: HiveProject(customer_id=[$0], customername=[$1]) HiveSortLimit(sort0=[$2], dir0=[ASC], fetch=[100]) - HiveProject(customer_id=[$2], customername=[||(||($7, _UTF-16LE', '), $6)], c_customer_id=[$2]) + HiveProject(customer_id=[$2], customername=[$6], c_customer_id=[$2]) HiveJoin(condition=[=($1, $3)], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($0, $1)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(sr_cdemo_sk=[$4]) @@ -64,21 +64,21 @@ HiveProject(customer_id=[$0], customername=[$1]) HiveProject(cd_demo_sk=[$0]) HiveFilter(condition=[IS NOT NULL($0)]) HiveTableScan(table=[[default, customer_demographics]], table:alias=[customer_demographics]) - HiveProject(c_customer_id=[$0], c_current_cdemo_sk=[$1], c_current_hdemo_sk=[$2], c_current_addr_sk=[$3], c_first_name=[$4], c_last_name=[$5], ca_address_sk=[$6], ca_city=[$7], hd_demo_sk=[$8], hd_income_band_sk=[$9], ib_income_band_sk=[$10], ib_lower_bound=[$11], ib_upper_bound=[$12]) - HiveJoin(condition=[=($8, $2)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveJoin(condition=[=($3, $6)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(c_customer_id=[$1], c_current_cdemo_sk=[$2], c_current_hdemo_sk=[$3], c_current_addr_sk=[$4], c_first_name=[$8], c_last_name=[$9]) + HiveProject(c_customer_id=[$0], c_current_cdemo_sk=[$1], c_current_hdemo_sk=[$2], c_current_addr_sk=[$3], ||=[$4], ca_address_sk=[$5], hd_demo_sk=[$6], hd_income_band_sk=[$7], ib_income_band_sk=[$8]) + HiveJoin(condition=[=($6, $2)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($3, $5)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(c_customer_id=[$1], c_current_cdemo_sk=[$2], c_current_hdemo_sk=[$3], c_current_addr_sk=[$4], ||=[||(||($9, _UTF-16LE', '), $8)]) HiveFilter(condition=[AND(IS NOT NULL($4), IS NOT NULL($2), IS NOT NULL($3))]) HiveTableScan(table=[[default, customer]], table:alias=[customer]) - HiveProject(ca_address_sk=[$0], ca_city=[CAST(_UTF-16LE'Hopewell'):VARCHAR(2147483647) CHARACTER SET "UTF-16LE" COLLATE "ISO-8859-1$en_US$primary"]) + HiveProject(ca_address_sk=[$0]) HiveFilter(condition=[AND(=($6, _UTF-16LE'Hopewell'), IS NOT NULL($0))]) HiveTableScan(table=[[default, customer_address]], table:alias=[customer_address]) - HiveProject(hd_demo_sk=[$0], hd_income_band_sk=[$1], ib_income_band_sk=[$2], ib_lower_bound=[$3], ib_upper_bound=[$4]) + HiveProject(hd_demo_sk=[$0], hd_income_band_sk=[$1], ib_income_band_sk=[$2]) HiveJoin(condition=[=($2, $1)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(hd_demo_sk=[$0], hd_income_band_sk=[$1]) HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($1))]) HiveTableScan(table=[[default, household_demographics]], table:alias=[household_demographics]) - HiveProject(ib_income_band_sk=[$0], ib_lower_bound=[$1], ib_upper_bound=[$2]) + HiveProject(ib_income_band_sk=[$0]) HiveFilter(condition=[AND(>=($1, 32287), <=($2, 82287), IS NOT NULL($0))]) HiveTableScan(table=[[default, income_band]], table:alias=[income_band]) diff --git ql/src/test/results/clientpositive/perf/tez/cbo_query85.q.out ql/src/test/results/clientpositive/perf/tez/cbo_query85.q.out index 50474bc2698..f5a71b422bd 100644 --- ql/src/test/results/clientpositive/perf/tez/cbo_query85.q.out +++ ql/src/test/results/clientpositive/perf/tez/cbo_query85.q.out @@ -184,36 +184,36 @@ CBO PLAN: HiveProject(_o__c0=[$0], _o__c1=[$1], _o__c2=[$2], _o__c3=[$3]) HiveSortLimit(sort0=[$7], sort1=[$4], sort2=[$5], sort3=[$6], dir0=[ASC], dir1=[ASC], dir2=[ASC], dir3=[ASC], fetch=[100]) HiveProject(_o__c0=[substr($0, 1, 20)], _o__c1=[/(CAST($1):DOUBLE, $2)], _o__c2=[/($3, $4)], _o__c3=[/($5, $6)], (tok_function avg (tok_table_or_col ws_quantity))=[/(CAST($1):DOUBLE, $2)], (tok_function avg (tok_table_or_col wr_refunded_cash))=[/($3, $4)], (tok_function avg (tok_table_or_col wr_fee))=[/($5, $6)], (tok_function substr (tok_table_or_col r_reason_desc) 1 20)=[substr($0, 1, 20)]) - HiveAggregate(group=[{7}], agg#0=[sum($26)], agg#1=[count($26)], agg#2=[sum($21)], agg#3=[count($21)], agg#4=[sum($20)], agg#5=[count($20)]) - HiveJoin(condition=[AND(AND(=($0, $17), =($4, $1)), =($5, $2))], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(cd_demo_sk=[$0], cd_marital_status=[$2], cd_education_status=[$3]) + HiveAggregate(group=[{14}], agg#0=[sum($32)], agg#1=[count($32)], agg#2=[sum($27)], agg#3=[count($27)], agg#4=[sum($26)], agg#5=[count($26)]) + HiveJoin(condition=[AND(AND(AND(=($1, $18), =($2, $19)), =($0, $21)), OR(AND($3, $4, $36), AND($5, $6, $37), AND($7, $8, $38)))], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(cd_demo_sk=[$0], cd_marital_status=[$2], cd_education_status=[$3], ==[=($2, _UTF-16LE'M')], =4=[=($3, _UTF-16LE'4 yr Degree')], =5=[=($2, _UTF-16LE'D')], =6=[=($3, _UTF-16LE'Primary')], =7=[=($2, _UTF-16LE'U')], =8=[=($3, _UTF-16LE'Advanced Degree')]) HiveFilter(condition=[AND(IN($3, _UTF-16LE'4 yr Degree', _UTF-16LE'Primary', _UTF-16LE'Advanced Degree'), IN($2, _UTF-16LE'M', _UTF-16LE'D', _UTF-16LE'U'), IS NOT NULL($0))]) - HiveTableScan(table=[[default, customer_demographics]], table:alias=[cd2]) - HiveJoin(condition=[AND(=($0, $12), OR(AND(=($1, _UTF-16LE'M'), =($2, _UTF-16LE'4 yr Degree'), BETWEEN(false, $24, 100, 150)), AND(=($1, _UTF-16LE'D'), =($2, _UTF-16LE'Primary'), BETWEEN(false, $24, 50, 100)), AND(=($1, _UTF-16LE'U'), =($2, _UTF-16LE'Advanced Degree'), BETWEEN(false, $24, 150, 200))))], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(cd_demo_sk=[$0], cd_marital_status=[$2], cd_education_status=[$3]) - HiveFilter(condition=[AND(IN($3, _UTF-16LE'4 yr Degree', _UTF-16LE'Primary', _UTF-16LE'Advanced Degree'), IN($2, _UTF-16LE'M', _UTF-16LE'D', _UTF-16LE'U'), IS NOT NULL($0))]) - HiveTableScan(table=[[default, customer_demographics]], table:alias=[cd1]) - HiveJoin(condition=[=($0, $12)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveTableScan(table=[[default, customer_demographics]], table:alias=[cd1]) + HiveJoin(condition=[AND(=($0, $13), OR(AND($1, $24), AND($2, $25), AND($3, $26)))], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(ca_address_sk=[$0], IN=[IN($8, _UTF-16LE'KY', _UTF-16LE'GA', _UTF-16LE'NM')], IN2=[IN($8, _UTF-16LE'MT', _UTF-16LE'OR', _UTF-16LE'IN')], IN3=[IN($8, _UTF-16LE'WI', _UTF-16LE'MO', _UTF-16LE'WV')]) + HiveFilter(condition=[AND(IN($8, _UTF-16LE'KY', _UTF-16LE'GA', _UTF-16LE'NM', _UTF-16LE'MT', _UTF-16LE'OR', _UTF-16LE'IN', _UTF-16LE'WI', _UTF-16LE'MO', _UTF-16LE'WV'), =($10, _UTF-16LE'United States'), IS NOT NULL($0))]) + HiveTableScan(table=[[default, customer_address]], table:alias=[customer_address]) + HiveJoin(condition=[=($0, $11)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(r_reason_sk=[$0], r_reason_desc=[$2]) HiveFilter(condition=[IS NOT NULL($0)]) HiveTableScan(table=[[default, reason]], table:alias=[reason]) - HiveJoin(condition=[=($14, $0)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(d_date_sk=[$0], d_year=[CAST(1998):INTEGER]) - HiveFilter(condition=[AND(=($6, 1998), IS NOT NULL($0))]) - HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) - HiveJoin(condition=[=($14, $0)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(wp_web_page_sk=[$0]) - HiveFilter(condition=[IS NOT NULL($0)]) - HiveTableScan(table=[[default, web_page]], table:alias=[web_page]) - HiveJoin(condition=[AND(=($0, $5), OR(AND(IN($1, _UTF-16LE'KY', _UTF-16LE'GA', _UTF-16LE'NM'), BETWEEN(false, $17, 100, 200)), AND(IN($1, _UTF-16LE'MT', _UTF-16LE'OR', _UTF-16LE'IN'), BETWEEN(false, $17, 150, 300)), AND(IN($1, _UTF-16LE'WI', _UTF-16LE'MO', _UTF-16LE'WV'), BETWEEN(false, $17, 50, 250))))], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(ca_address_sk=[$0], ca_state=[$8], ca_country=[CAST(_UTF-16LE'United States'):VARCHAR(2147483647) CHARACTER SET "UTF-16LE" COLLATE "ISO-8859-1$en_US$primary"]) - HiveFilter(condition=[AND(IN($8, _UTF-16LE'KY', _UTF-16LE'GA', _UTF-16LE'NM', _UTF-16LE'MT', _UTF-16LE'OR', _UTF-16LE'IN', _UTF-16LE'WI', _UTF-16LE'MO', _UTF-16LE'WV'), =($10, _UTF-16LE'United States'), IS NOT NULL($0))]) - HiveTableScan(table=[[default, customer_address]], table:alias=[customer_address]) + HiveJoin(condition=[=($15, $0)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(wp_web_page_sk=[$0]) + HiveFilter(condition=[IS NOT NULL($0)]) + HiveTableScan(table=[[default, web_page]], table:alias=[web_page]) + HiveJoin(condition=[=($12, $0)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(d_date_sk=[$0]) + HiveFilter(condition=[AND(=($6, 1998), IS NOT NULL($0))]) + HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) + HiveJoin(condition=[=($0, $6)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(cd_demo_sk=[$0], cd_marital_status=[$2], cd_education_status=[$3]) + HiveFilter(condition=[AND(IN($3, _UTF-16LE'4 yr Degree', _UTF-16LE'Primary', _UTF-16LE'Advanced Degree'), IN($2, _UTF-16LE'M', _UTF-16LE'D', _UTF-16LE'U'), IS NOT NULL($0))]) + HiveTableScan(table=[[default, customer_demographics]], table:alias=[cd2]) HiveJoin(condition=[AND(=($9, $0), =($11, $5))], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(wr_item_sk=[$2], wr_refunded_cdemo_sk=[$4], wr_refunded_addr_sk=[$6], wr_returning_cdemo_sk=[$8], wr_reason_sk=[$12], wr_order_number=[$13], wr_fee=[$18], wr_refunded_cash=[$20]) HiveFilter(condition=[AND(IS NOT NULL($2), IS NOT NULL($13), IS NOT NULL($4), IS NOT NULL($8), IS NOT NULL($6), IS NOT NULL($12))]) HiveTableScan(table=[[default, web_returns]], table:alias=[web_returns]) - HiveProject(ws_sold_date_sk=[$0], ws_item_sk=[$3], ws_web_page_sk=[$12], ws_order_number=[$17], ws_quantity=[$18], ws_sales_price=[$21], ws_net_profit=[$33]) + HiveProject(ws_sold_date_sk=[$0], ws_item_sk=[$3], ws_web_page_sk=[$12], ws_order_number=[$17], ws_quantity=[$18], BETWEEN=[BETWEEN(false, $33, 100, 200)], BETWEEN6=[BETWEEN(false, $33, 150, 300)], BETWEEN7=[BETWEEN(false, $33, 50, 250)], BETWEEN8=[BETWEEN(false, $21, 100, 150)], BETWEEN9=[BETWEEN(false, $21, 50, 100)], BETWEEN10=[BETWEEN(false, $21, 150, 200)]) HiveFilter(condition=[AND(OR(BETWEEN(false, $21, 100, 150), BETWEEN(false, $21, 50, 100), BETWEEN(false, $21, 150, 200)), OR(BETWEEN(false, $33, 100, 200), BETWEEN(false, $33, 150, 300), BETWEEN(false, $33, 50, 250)), IS NOT NULL($3), IS NOT NULL($17), IS NOT NULL($12), IS NOT NULL($0))]) HiveTableScan(table=[[default, web_sales]], table:alias=[web_sales]) diff --git ql/src/test/results/clientpositive/perf/tez/cbo_query87.q.out ql/src/test/results/clientpositive/perf/tez/cbo_query87.q.out index 35f319d9537..e030b3eb2c2 100644 --- ql/src/test/results/clientpositive/perf/tez/cbo_query87.q.out +++ ql/src/test/results/clientpositive/perf/tez/cbo_query87.q.out @@ -78,7 +78,7 @@ HiveAggregate(group=[{}], agg#0=[count()]) HiveProject(ss_sold_date_sk=[$0], ss_customer_sk=[$3]) HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($3))]) HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) - HiveProject(d_date_sk=[$0], d_date=[$2], d_month_seq=[$3]) + HiveProject(d_date_sk=[$0], d_date=[$2]) HiveFilter(condition=[AND(BETWEEN(false, $3, 1212, 1223), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) HiveProject($f0=[$1], $f1=[$0], $f2=[$2], $f3=[1], $f4=[$3]) @@ -93,7 +93,7 @@ HiveAggregate(group=[{}], agg#0=[count()]) HiveProject(cs_sold_date_sk=[$0], cs_bill_customer_sk=[$3]) HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($3))]) HiveTableScan(table=[[default, catalog_sales]], table:alias=[catalog_sales]) - HiveProject(d_date_sk=[$0], d_date=[$2], d_month_seq=[$3]) + HiveProject(d_date_sk=[$0], d_date=[$2]) HiveFilter(condition=[AND(BETWEEN(false, $3, 1212, 1223), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) HiveProject($f0=[$1], $f1=[$0], $f2=[$2], $f3=[1], $f4=[$3]) @@ -108,7 +108,7 @@ HiveAggregate(group=[{}], agg#0=[count()]) HiveProject(ws_sold_date_sk=[$0], ws_bill_customer_sk=[$4]) HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($4))]) HiveTableScan(table=[[default, web_sales]], table:alias=[web_sales]) - HiveProject(d_date_sk=[$0], d_date=[$2], d_month_seq=[$3]) + HiveProject(d_date_sk=[$0], d_date=[$2]) HiveFilter(condition=[AND(BETWEEN(false, $3, 1212, 1223), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) diff --git ql/src/test/results/clientpositive/perf/tez/cbo_query88.q.out ql/src/test/results/clientpositive/perf/tez/cbo_query88.q.out index 1f86e3ab46e..1f4471e8ae6 100644 --- ql/src/test/results/clientpositive/perf/tez/cbo_query88.q.out +++ ql/src/test/results/clientpositive/perf/tez/cbo_query88.q.out @@ -210,138 +210,138 @@ HiveProject($f0=[$0], $f00=[$7], $f01=[$6], $f02=[$5], $f03=[$4], $f04=[$3], $f0 HiveJoin(condition=[true], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject($f0=[$0]) HiveAggregate(group=[{}], agg#0=[count()]) - HiveJoin(condition=[=($2, $9)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveJoin(condition=[=($0, $6)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($2, $5)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($0, $4)], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($1, $3)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(ss_sold_time_sk=[$1], ss_hdemo_sk=[$5], ss_store_sk=[$7]) HiveFilter(condition=[AND(IS NOT NULL($5), IS NOT NULL($1), IS NOT NULL($7))]) HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) - HiveProject(hd_demo_sk=[$0], hd_dep_count=[$3], hd_vehicle_count=[$4]) + HiveProject(hd_demo_sk=[$0]) HiveFilter(condition=[AND(IN($3, 3, 0, 1), <=($4, 5), OR(AND(=($3, 3), IS NOT NULL($4)), AND(=($3, 0), <=($4, 2)), AND(=($3, 1), <=($4, 3))), IS NOT NULL($0))]) HiveTableScan(table=[[default, household_demographics]], table:alias=[household_demographics]) - HiveProject(t_time_sk=[$0], t_hour=[CAST(8):INTEGER], t_minute=[$4]) + HiveProject(t_time_sk=[$0]) HiveFilter(condition=[AND(=($3, 8), >=($4, 30), IS NOT NULL($0))]) HiveTableScan(table=[[default, time_dim]], table:alias=[time_dim]) - HiveProject(s_store_sk=[$0], s_store_name=[CAST(_UTF-16LE'ese'):VARCHAR(2147483647) CHARACTER SET "UTF-16LE" COLLATE "ISO-8859-1$en_US$primary"]) + HiveProject(s_store_sk=[$0]) HiveFilter(condition=[AND(=($5, _UTF-16LE'ese'), IS NOT NULL($0))]) HiveTableScan(table=[[default, store]], table:alias=[store]) HiveProject($f0=[$0]) HiveAggregate(group=[{}], agg#0=[count()]) - HiveJoin(condition=[=($2, $9)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveJoin(condition=[=($0, $6)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($2, $5)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($0, $4)], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($1, $3)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(ss_sold_time_sk=[$1], ss_hdemo_sk=[$5], ss_store_sk=[$7]) HiveFilter(condition=[AND(IS NOT NULL($5), IS NOT NULL($1), IS NOT NULL($7))]) HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) - HiveProject(hd_demo_sk=[$0], hd_dep_count=[$3], hd_vehicle_count=[$4]) + HiveProject(hd_demo_sk=[$0]) HiveFilter(condition=[AND(IN($3, 3, 0, 1), <=($4, 5), OR(AND(=($3, 3), IS NOT NULL($4)), AND(=($3, 0), <=($4, 2)), AND(=($3, 1), <=($4, 3))), IS NOT NULL($0))]) HiveTableScan(table=[[default, household_demographics]], table:alias=[household_demographics]) - HiveProject(t_time_sk=[$0], t_hour=[CAST(12):INTEGER], t_minute=[$4]) + HiveProject(t_time_sk=[$0]) HiveFilter(condition=[AND(=($3, 12), <($4, 30), IS NOT NULL($0))]) HiveTableScan(table=[[default, time_dim]], table:alias=[time_dim]) - HiveProject(s_store_sk=[$0], s_store_name=[CAST(_UTF-16LE'ese'):VARCHAR(2147483647) CHARACTER SET "UTF-16LE" COLLATE "ISO-8859-1$en_US$primary"]) + HiveProject(s_store_sk=[$0]) HiveFilter(condition=[AND(=($5, _UTF-16LE'ese'), IS NOT NULL($0))]) HiveTableScan(table=[[default, store]], table:alias=[store]) HiveProject($f0=[$0]) HiveAggregate(group=[{}], agg#0=[count()]) - HiveJoin(condition=[=($2, $9)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveJoin(condition=[=($0, $6)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($2, $5)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($0, $4)], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($1, $3)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(ss_sold_time_sk=[$1], ss_hdemo_sk=[$5], ss_store_sk=[$7]) HiveFilter(condition=[AND(IS NOT NULL($5), IS NOT NULL($1), IS NOT NULL($7))]) HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) - HiveProject(hd_demo_sk=[$0], hd_dep_count=[$3], hd_vehicle_count=[$4]) + HiveProject(hd_demo_sk=[$0]) HiveFilter(condition=[AND(IN($3, 3, 0, 1), <=($4, 5), OR(AND(=($3, 3), IS NOT NULL($4)), AND(=($3, 0), <=($4, 2)), AND(=($3, 1), <=($4, 3))), IS NOT NULL($0))]) HiveTableScan(table=[[default, household_demographics]], table:alias=[household_demographics]) - HiveProject(t_time_sk=[$0], t_hour=[CAST(11):INTEGER], t_minute=[$4]) + HiveProject(t_time_sk=[$0]) HiveFilter(condition=[AND(=($3, 11), >=($4, 30), IS NOT NULL($0))]) HiveTableScan(table=[[default, time_dim]], table:alias=[time_dim]) - HiveProject(s_store_sk=[$0], s_store_name=[CAST(_UTF-16LE'ese'):VARCHAR(2147483647) CHARACTER SET "UTF-16LE" COLLATE "ISO-8859-1$en_US$primary"]) + HiveProject(s_store_sk=[$0]) HiveFilter(condition=[AND(=($5, _UTF-16LE'ese'), IS NOT NULL($0))]) HiveTableScan(table=[[default, store]], table:alias=[store]) HiveProject($f0=[$0]) HiveAggregate(group=[{}], agg#0=[count()]) - HiveJoin(condition=[=($2, $9)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveJoin(condition=[=($0, $6)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($2, $5)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($0, $4)], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($1, $3)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(ss_sold_time_sk=[$1], ss_hdemo_sk=[$5], ss_store_sk=[$7]) HiveFilter(condition=[AND(IS NOT NULL($5), IS NOT NULL($1), IS NOT NULL($7))]) HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) - HiveProject(hd_demo_sk=[$0], hd_dep_count=[$3], hd_vehicle_count=[$4]) + HiveProject(hd_demo_sk=[$0]) HiveFilter(condition=[AND(IN($3, 3, 0, 1), <=($4, 5), OR(AND(=($3, 3), IS NOT NULL($4)), AND(=($3, 0), <=($4, 2)), AND(=($3, 1), <=($4, 3))), IS NOT NULL($0))]) HiveTableScan(table=[[default, household_demographics]], table:alias=[household_demographics]) - HiveProject(t_time_sk=[$0], t_hour=[CAST(11):INTEGER], t_minute=[$4]) + HiveProject(t_time_sk=[$0]) HiveFilter(condition=[AND(=($3, 11), <($4, 30), IS NOT NULL($0))]) HiveTableScan(table=[[default, time_dim]], table:alias=[time_dim]) - HiveProject(s_store_sk=[$0], s_store_name=[CAST(_UTF-16LE'ese'):VARCHAR(2147483647) CHARACTER SET "UTF-16LE" COLLATE "ISO-8859-1$en_US$primary"]) + HiveProject(s_store_sk=[$0]) HiveFilter(condition=[AND(=($5, _UTF-16LE'ese'), IS NOT NULL($0))]) HiveTableScan(table=[[default, store]], table:alias=[store]) HiveProject($f0=[$0]) HiveAggregate(group=[{}], agg#0=[count()]) - HiveJoin(condition=[=($2, $9)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveJoin(condition=[=($0, $6)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($2, $5)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($0, $4)], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($1, $3)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(ss_sold_time_sk=[$1], ss_hdemo_sk=[$5], ss_store_sk=[$7]) HiveFilter(condition=[AND(IS NOT NULL($5), IS NOT NULL($1), IS NOT NULL($7))]) HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) - HiveProject(hd_demo_sk=[$0], hd_dep_count=[$3], hd_vehicle_count=[$4]) + HiveProject(hd_demo_sk=[$0]) HiveFilter(condition=[AND(IN($3, 3, 0, 1), <=($4, 5), OR(AND(=($3, 3), IS NOT NULL($4)), AND(=($3, 0), <=($4, 2)), AND(=($3, 1), <=($4, 3))), IS NOT NULL($0))]) HiveTableScan(table=[[default, household_demographics]], table:alias=[household_demographics]) - HiveProject(t_time_sk=[$0], t_hour=[CAST(10):INTEGER], t_minute=[$4]) + HiveProject(t_time_sk=[$0]) HiveFilter(condition=[AND(=($3, 10), >=($4, 30), IS NOT NULL($0))]) HiveTableScan(table=[[default, time_dim]], table:alias=[time_dim]) - HiveProject(s_store_sk=[$0], s_store_name=[CAST(_UTF-16LE'ese'):VARCHAR(2147483647) CHARACTER SET "UTF-16LE" COLLATE "ISO-8859-1$en_US$primary"]) + HiveProject(s_store_sk=[$0]) HiveFilter(condition=[AND(=($5, _UTF-16LE'ese'), IS NOT NULL($0))]) HiveTableScan(table=[[default, store]], table:alias=[store]) HiveProject($f0=[$0]) HiveAggregate(group=[{}], agg#0=[count()]) - HiveJoin(condition=[=($2, $9)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveJoin(condition=[=($0, $6)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($2, $5)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($0, $4)], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($1, $3)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(ss_sold_time_sk=[$1], ss_hdemo_sk=[$5], ss_store_sk=[$7]) HiveFilter(condition=[AND(IS NOT NULL($5), IS NOT NULL($1), IS NOT NULL($7))]) HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) - HiveProject(hd_demo_sk=[$0], hd_dep_count=[$3], hd_vehicle_count=[$4]) + HiveProject(hd_demo_sk=[$0]) HiveFilter(condition=[AND(IN($3, 3, 0, 1), <=($4, 5), OR(AND(=($3, 3), IS NOT NULL($4)), AND(=($3, 0), <=($4, 2)), AND(=($3, 1), <=($4, 3))), IS NOT NULL($0))]) HiveTableScan(table=[[default, household_demographics]], table:alias=[household_demographics]) - HiveProject(t_time_sk=[$0], t_hour=[CAST(10):INTEGER], t_minute=[$4]) + HiveProject(t_time_sk=[$0]) HiveFilter(condition=[AND(=($3, 10), <($4, 30), IS NOT NULL($0))]) HiveTableScan(table=[[default, time_dim]], table:alias=[time_dim]) - HiveProject(s_store_sk=[$0], s_store_name=[CAST(_UTF-16LE'ese'):VARCHAR(2147483647) CHARACTER SET "UTF-16LE" COLLATE "ISO-8859-1$en_US$primary"]) + HiveProject(s_store_sk=[$0]) HiveFilter(condition=[AND(=($5, _UTF-16LE'ese'), IS NOT NULL($0))]) HiveTableScan(table=[[default, store]], table:alias=[store]) HiveProject($f0=[$0]) HiveAggregate(group=[{}], agg#0=[count()]) - HiveJoin(condition=[=($2, $9)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveJoin(condition=[=($0, $6)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($2, $5)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($0, $4)], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($1, $3)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(ss_sold_time_sk=[$1], ss_hdemo_sk=[$5], ss_store_sk=[$7]) HiveFilter(condition=[AND(IS NOT NULL($5), IS NOT NULL($1), IS NOT NULL($7))]) HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) - HiveProject(hd_demo_sk=[$0], hd_dep_count=[$3], hd_vehicle_count=[$4]) + HiveProject(hd_demo_sk=[$0]) HiveFilter(condition=[AND(IN($3, 3, 0, 1), <=($4, 5), OR(AND(=($3, 3), IS NOT NULL($4)), AND(=($3, 0), <=($4, 2)), AND(=($3, 1), <=($4, 3))), IS NOT NULL($0))]) HiveTableScan(table=[[default, household_demographics]], table:alias=[household_demographics]) - HiveProject(t_time_sk=[$0], t_hour=[CAST(9):INTEGER], t_minute=[$4]) + HiveProject(t_time_sk=[$0]) HiveFilter(condition=[AND(=($3, 9), >=($4, 30), IS NOT NULL($0))]) HiveTableScan(table=[[default, time_dim]], table:alias=[time_dim]) - HiveProject(s_store_sk=[$0], s_store_name=[CAST(_UTF-16LE'ese'):VARCHAR(2147483647) CHARACTER SET "UTF-16LE" COLLATE "ISO-8859-1$en_US$primary"]) + HiveProject(s_store_sk=[$0]) HiveFilter(condition=[AND(=($5, _UTF-16LE'ese'), IS NOT NULL($0))]) HiveTableScan(table=[[default, store]], table:alias=[store]) HiveProject($f0=[$0]) HiveAggregate(group=[{}], agg#0=[count()]) - HiveJoin(condition=[=($2, $9)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveJoin(condition=[=($0, $6)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($2, $5)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($0, $4)], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($1, $3)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(ss_sold_time_sk=[$1], ss_hdemo_sk=[$5], ss_store_sk=[$7]) HiveFilter(condition=[AND(IS NOT NULL($5), IS NOT NULL($1), IS NOT NULL($7))]) HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) - HiveProject(hd_demo_sk=[$0], hd_dep_count=[$3], hd_vehicle_count=[$4]) + HiveProject(hd_demo_sk=[$0]) HiveFilter(condition=[AND(IN($3, 3, 0, 1), <=($4, 5), OR(AND(=($3, 3), IS NOT NULL($4)), AND(=($3, 0), <=($4, 2)), AND(=($3, 1), <=($4, 3))), IS NOT NULL($0))]) HiveTableScan(table=[[default, household_demographics]], table:alias=[household_demographics]) - HiveProject(t_time_sk=[$0], t_hour=[CAST(9):INTEGER], t_minute=[$4]) + HiveProject(t_time_sk=[$0]) HiveFilter(condition=[AND(=($3, 9), <($4, 30), IS NOT NULL($0))]) HiveTableScan(table=[[default, time_dim]], table:alias=[time_dim]) - HiveProject(s_store_sk=[$0], s_store_name=[CAST(_UTF-16LE'ese'):VARCHAR(2147483647) CHARACTER SET "UTF-16LE" COLLATE "ISO-8859-1$en_US$primary"]) + HiveProject(s_store_sk=[$0]) HiveFilter(condition=[AND(=($5, _UTF-16LE'ese'), IS NOT NULL($0))]) HiveTableScan(table=[[default, store]], table:alias=[store]) diff --git ql/src/test/results/clientpositive/perf/tez/cbo_query89.q.out ql/src/test/results/clientpositive/perf/tez/cbo_query89.q.out index 72f22b64c52..7cfb3ecdecc 100644 --- ql/src/test/results/clientpositive/perf/tez/cbo_query89.q.out +++ ql/src/test/results/clientpositive/perf/tez/cbo_query89.q.out @@ -69,8 +69,8 @@ HiveProject(i_category=[$0], i_class=[$1], i_brand=[$2], s_store_name=[$3], s_co HiveFilter(condition=[CASE(<>($7, 0), >(/(ABS(-($6, $7)), $7), 0.1), null)]) HiveProject((tok_table_or_col i_category)=[$2], (tok_table_or_col i_class)=[$1], (tok_table_or_col i_brand)=[$0], (tok_table_or_col s_store_name)=[$4], (tok_table_or_col s_company_name)=[$5], (tok_table_or_col d_moy)=[$3], (tok_function sum (tok_table_or_col ss_sales_price))=[$6], avg_window_0=[avg($6) OVER (PARTITION BY $2, $0, $4, $5 ORDER BY $2 NULLS FIRST, $0 NULLS FIRST, $4 NULLS FIRST, $5 NULLS FIRST ROWS BETWEEN 2147483647 FOLLOWING AND 2147483647 PRECEDING)]) HiveProject(i_brand=[$0], i_class=[$1], i_category=[$2], d_moy=[$3], s_store_name=[$4], s_company_name=[$5], $f6=[$6]) - HiveAggregate(group=[{5, 6, 7, 10, 12, 13}], agg#0=[sum($3)]) - HiveJoin(condition=[=($2, $11)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveAggregate(group=[{5, 6, 7, 9, 11, 12}], agg#0=[sum($3)]) + HiveJoin(condition=[=($2, $10)], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($0, $8)], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($1, $4)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(ss_sold_date_sk=[$0], ss_item_sk=[$2], ss_store_sk=[$7], ss_sales_price=[$13]) @@ -79,7 +79,7 @@ HiveProject(i_category=[$0], i_class=[$1], i_brand=[$2], s_store_name=[$3], s_co HiveProject(i_item_sk=[$0], i_brand=[$8], i_class=[$10], i_category=[$12]) HiveFilter(condition=[AND(IN($10, _UTF-16LE'wallpaper', _UTF-16LE'parenting', _UTF-16LE'musical', _UTF-16LE'womens', _UTF-16LE'birdal', _UTF-16LE'pants'), IN($12, _UTF-16LE'Home', _UTF-16LE'Books', _UTF-16LE'Electronics', _UTF-16LE'Shoes', _UTF-16LE'Jewelry', _UTF-16LE'Men'), OR(AND(IN($12, _UTF-16LE'Home', _UTF-16LE'Books', _UTF-16LE'Electronics'), IN($10, _UTF-16LE'wallpaper', _UTF-16LE'parenting', _UTF-16LE'musical')), AND(IN($12, _UTF-16LE'Shoes', _UTF-16LE'Jewelry', _UTF-16LE'Men'), IN($10, _UTF-16LE'womens', _UTF-16LE'birdal', _UTF-16LE'pants'))), IS NOT NULL($0))]) HiveTableScan(table=[[default, item]], table:alias=[item]) - HiveProject(d_date_sk=[$0], d_year=[CAST(2000):INTEGER], d_moy=[$8]) + HiveProject(d_date_sk=[$0], d_moy=[$8]) HiveFilter(condition=[AND(=($6, 2000), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) HiveProject(s_store_sk=[$0], s_store_name=[$5], s_company_name=[$17]) diff --git ql/src/test/results/clientpositive/perf/tez/cbo_query9.q.out ql/src/test/results/clientpositive/perf/tez/cbo_query9.q.out index 3ec19162627..3a1e1990efc 100644 --- ql/src/test/results/clientpositive/perf/tez/cbo_query9.q.out +++ ql/src/test/results/clientpositive/perf/tez/cbo_query9.q.out @@ -118,7 +118,7 @@ POSTHOOK: Input: default@reason POSTHOOK: Input: default@store_sales POSTHOOK: Output: hdfs://### HDFS PATH ### CBO PLAN: -HiveProject(bucket1=[CASE(>($1, 409437), $2, $3)], bucket2=[CASE(>($4, 4595804), $5, $6)], bucket3=[CASE(>($7, 7887297), $8, $9)], bucket4=[CASE(>($10, 10872978), $11, $12)], bucket5=[CASE(>($13, 43571537), $14, $15)]) +HiveProject(bucket1=[CASE($1, $2, $3)], bucket2=[CASE($4, $5, $6)], bucket3=[CASE($7, $8, $9)], bucket4=[CASE($10, $11, $12)], bucket5=[CASE($13, $14, $15)]) HiveJoin(condition=[true], joinType=[left], algorithm=[none], cost=[not available]) HiveJoin(condition=[true], joinType=[left], algorithm=[none], cost=[not available]) HiveJoin(condition=[true], joinType=[left], algorithm=[none], cost=[not available]) @@ -137,7 +137,7 @@ HiveProject(bucket1=[CASE(>($1, 409437), $2, $3)], bucket2=[CASE(>($4, 4595804), HiveProject(r_reason_sk=[CAST(1):INTEGER]) HiveFilter(condition=[=($0, 1)]) HiveTableScan(table=[[default, reason]], table:alias=[reason]) - HiveProject($f0=[$0]) + HiveProject(>=[>($0, 409437)]) HiveAggregate(group=[{}], agg#0=[count()]) HiveFilter(condition=[BETWEEN(false, $10, 1, 20)]) HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) @@ -149,7 +149,7 @@ HiveProject(bucket1=[CASE(>($1, 409437), $2, $3)], bucket2=[CASE(>($4, 4595804), HiveAggregate(group=[{}], agg#0=[sum($21)], agg#1=[count($21)]) HiveFilter(condition=[BETWEEN(false, $10, 1, 20)]) HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) - HiveProject($f0=[$0]) + HiveProject(>=[>($0, 4595804)]) HiveAggregate(group=[{}], agg#0=[count()]) HiveFilter(condition=[BETWEEN(false, $10, 21, 40)]) HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) @@ -161,7 +161,7 @@ HiveProject(bucket1=[CASE(>($1, 409437), $2, $3)], bucket2=[CASE(>($4, 4595804), HiveAggregate(group=[{}], agg#0=[sum($21)], agg#1=[count($21)]) HiveFilter(condition=[BETWEEN(false, $10, 21, 40)]) HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) - HiveProject($f0=[$0]) + HiveProject(>=[>($0, 7887297)]) HiveAggregate(group=[{}], agg#0=[count()]) HiveFilter(condition=[BETWEEN(false, $10, 41, 60)]) HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) @@ -173,7 +173,7 @@ HiveProject(bucket1=[CASE(>($1, 409437), $2, $3)], bucket2=[CASE(>($4, 4595804), HiveAggregate(group=[{}], agg#0=[sum($21)], agg#1=[count($21)]) HiveFilter(condition=[BETWEEN(false, $10, 41, 60)]) HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) - HiveProject($f0=[$0]) + HiveProject(>=[>($0, 10872978)]) HiveAggregate(group=[{}], agg#0=[count()]) HiveFilter(condition=[BETWEEN(false, $10, 61, 80)]) HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) @@ -185,7 +185,7 @@ HiveProject(bucket1=[CASE(>($1, 409437), $2, $3)], bucket2=[CASE(>($4, 4595804), HiveAggregate(group=[{}], agg#0=[sum($21)], agg#1=[count($21)]) HiveFilter(condition=[BETWEEN(false, $10, 61, 80)]) HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) - HiveProject($f0=[$0]) + HiveProject(>=[>($0, 43571537)]) HiveAggregate(group=[{}], agg#0=[count()]) HiveFilter(condition=[BETWEEN(false, $10, 81, 100)]) HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) diff --git ql/src/test/results/clientpositive/perf/tez/cbo_query90.q.out ql/src/test/results/clientpositive/perf/tez/cbo_query90.q.out index c1567c7f61d..123b3c20db0 100644 --- ql/src/test/results/clientpositive/perf/tez/cbo_query90.q.out +++ ql/src/test/results/clientpositive/perf/tez/cbo_query90.q.out @@ -57,36 +57,36 @@ HiveSortLimit(sort0=[$0], dir0=[ASC], fetch=[100]) HiveJoin(condition=[true], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject($f0=[$0]) HiveAggregate(group=[{}], agg#0=[count()]) - HiveJoin(condition=[=($1, $7)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveJoin(condition=[=($0, $5)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($1, $5)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($0, $4)], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($2, $3)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(ws_sold_time_sk=[$1], ws_ship_hdemo_sk=[$10], ws_web_page_sk=[$12]) HiveFilter(condition=[AND(IS NOT NULL($10), IS NOT NULL($1), IS NOT NULL($12))]) HiveTableScan(table=[[default, web_sales]], table:alias=[web_sales]) - HiveProject(wp_web_page_sk=[$0], wp_char_count=[$10]) + HiveProject(wp_web_page_sk=[$0]) HiveFilter(condition=[AND(BETWEEN(false, $10, 5000, 5200), IS NOT NULL($0))]) HiveTableScan(table=[[default, web_page]], table:alias=[web_page]) - HiveProject(t_time_sk=[$0], t_hour=[$3]) + HiveProject(t_time_sk=[$0]) HiveFilter(condition=[AND(BETWEEN(false, $3, 6, 7), IS NOT NULL($0))]) HiveTableScan(table=[[default, time_dim]], table:alias=[time_dim]) - HiveProject(hd_demo_sk=[$0], hd_dep_count=[CAST(8):INTEGER]) + HiveProject(hd_demo_sk=[$0]) HiveFilter(condition=[AND(=($3, 8), IS NOT NULL($0))]) HiveTableScan(table=[[default, household_demographics]], table:alias=[household_demographics]) HiveProject($f0=[$0]) HiveAggregate(group=[{}], agg#0=[count()]) - HiveJoin(condition=[=($1, $7)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveJoin(condition=[=($0, $5)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($1, $5)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($0, $4)], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($2, $3)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(ws_sold_time_sk=[$1], ws_ship_hdemo_sk=[$10], ws_web_page_sk=[$12]) HiveFilter(condition=[AND(IS NOT NULL($10), IS NOT NULL($1), IS NOT NULL($12))]) HiveTableScan(table=[[default, web_sales]], table:alias=[web_sales]) - HiveProject(wp_web_page_sk=[$0], wp_char_count=[$10]) + HiveProject(wp_web_page_sk=[$0]) HiveFilter(condition=[AND(BETWEEN(false, $10, 5000, 5200), IS NOT NULL($0))]) HiveTableScan(table=[[default, web_page]], table:alias=[web_page]) - HiveProject(t_time_sk=[$0], t_hour=[$3]) + HiveProject(t_time_sk=[$0]) HiveFilter(condition=[AND(BETWEEN(false, $3, 14, 15), IS NOT NULL($0))]) HiveTableScan(table=[[default, time_dim]], table:alias=[time_dim]) - HiveProject(hd_demo_sk=[$0], hd_dep_count=[CAST(8):INTEGER]) + HiveProject(hd_demo_sk=[$0]) HiveFilter(condition=[AND(=($3, 8), IS NOT NULL($0))]) HiveTableScan(table=[[default, household_demographics]], table:alias=[household_demographics]) diff --git ql/src/test/results/clientpositive/perf/tez/cbo_query91.q.out ql/src/test/results/clientpositive/perf/tez/cbo_query91.q.out index 6b58ccc61ed..e6fe23fb5b8 100644 --- ql/src/test/results/clientpositive/perf/tez/cbo_query91.q.out +++ ql/src/test/results/clientpositive/perf/tez/cbo_query91.q.out @@ -78,11 +78,11 @@ CBO PLAN: HiveProject(call_center=[$0], call_center_name=[$1], manager=[$2], returns_loss=[$3]) HiveSortLimit(sort0=[$4], dir0=[DESC-nulls-last]) HiveProject(call_center=[$2], call_center_name=[$3], manager=[$4], returns_loss=[$5], (tok_function sum (tok_table_or_col cr_net_loss))=[$5]) - HiveAggregate(group=[{7, 8, 17, 18, 19}], agg#0=[sum($12)]) - HiveJoin(condition=[=($20, $4)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveJoin(condition=[=($10, $2)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveJoin(condition=[=($0, $5)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(ca_address_sk=[$0], ca_gmt_offset=[CAST(-7):DECIMAL(5, 2)]) + HiveAggregate(group=[{6, 7, 14, 15, 16}], agg#0=[sum($11)]) + HiveJoin(condition=[=($17, $3)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($9, $1)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($0, $4)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(ca_address_sk=[$0]) HiveFilter(condition=[AND(=($11, -7), IS NOT NULL($0))]) HiveTableScan(table=[[default, customer_address]], table:alias=[customer_address]) HiveJoin(condition=[=($4, $1)], joinType=[inner], algorithm=[none], cost=[not available]) @@ -92,19 +92,19 @@ HiveProject(call_center=[$0], call_center_name=[$1], manager=[$2], returns_loss= HiveProject(cd_demo_sk=[$0], cd_marital_status=[$2], cd_education_status=[$3]) HiveFilter(condition=[AND(IN($3, _UTF-16LE'Unknown', _UTF-16LE'Advanced Degree'), IN($2, _UTF-16LE'M', _UTF-16LE'W'), IN(ROW($2, $3), ROW(_UTF-16LE'M', _UTF-16LE'Unknown'), ROW(_UTF-16LE'W', _UTF-16LE'Advanced Degree')), IS NOT NULL($0))]) HiveTableScan(table=[[default, customer_demographics]], table:alias=[customer_demographics]) - HiveProject(cr_returned_date_sk=[$0], cr_returning_customer_sk=[$1], cr_call_center_sk=[$2], cr_net_loss=[$3], d_date_sk=[$4], d_year=[$5], d_moy=[$6], cc_call_center_sk=[$7], cc_call_center_id=[$8], cc_name=[$9], cc_manager=[$10]) - HiveJoin(condition=[=($2, $7)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(cr_returned_date_sk=[$0], cr_returning_customer_sk=[$1], cr_call_center_sk=[$2], cr_net_loss=[$3], d_date_sk=[$4], cc_call_center_sk=[$5], cc_call_center_id=[$6], cc_name=[$7], cc_manager=[$8]) + HiveJoin(condition=[=($2, $5)], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($0, $4)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(cr_returned_date_sk=[$0], cr_returning_customer_sk=[$7], cr_call_center_sk=[$11], cr_net_loss=[$26]) HiveFilter(condition=[AND(IS NOT NULL($11), IS NOT NULL($0), IS NOT NULL($7))]) HiveTableScan(table=[[default, catalog_returns]], table:alias=[catalog_returns]) - HiveProject(d_date_sk=[$0], d_year=[CAST(1999):INTEGER], d_moy=[CAST(11):INTEGER]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(=($6, 1999), =($8, 11), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) HiveProject(cc_call_center_sk=[$0], cc_call_center_id=[$1], cc_name=[$6], cc_manager=[$11]) HiveFilter(condition=[IS NOT NULL($0)]) HiveTableScan(table=[[default, call_center]], table:alias=[call_center]) - HiveProject(hd_demo_sk=[$0], hd_buy_potential=[$2]) + HiveProject(hd_demo_sk=[$0]) HiveFilter(condition=[AND(LIKE($2, _UTF-16LE'0-500%'), IS NOT NULL($0))]) HiveTableScan(table=[[default, household_demographics]], table:alias=[household_demographics]) diff --git ql/src/test/results/clientpositive/perf/tez/cbo_query92.q.out ql/src/test/results/clientpositive/perf/tez/cbo_query92.q.out index 5a0e1da5259..2a21fbaf4ea 100644 --- ql/src/test/results/clientpositive/perf/tez/cbo_query92.q.out +++ ql/src/test/results/clientpositive/perf/tez/cbo_query92.q.out @@ -69,26 +69,26 @@ HiveProject(excess discount amount=[$0]) HiveSortLimit(sort0=[$1], dir0=[ASC], fetch=[100]) HiveProject(excess discount amount=[$0], (tok_function sum (tok_table_or_col ws_ext_discount_amt))=[$0]) HiveAggregate(group=[{}], agg#0=[sum($2)]) - HiveJoin(condition=[AND(>($2, CAST(*(1.3, $6)):DECIMAL(14, 7)), =($7, $1))], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[AND(>($2, $5), =($6, $1))], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($3, $0)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(ws_sold_date_sk=[$0], ws_item_sk=[$3], ws_ext_discount_amt=[$22]) HiveFilter(condition=[AND(IS NOT NULL($3), IS NOT NULL($0))]) HiveTableScan(table=[[default, web_sales]], table:alias=[web_sales]) - HiveProject(d_date_sk=[$0], d_date=[$2]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(BETWEEN(false, CAST($2):TIMESTAMP(9), 1998-03-18 00:00:00, 1998-06-16 00:00:00), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) - HiveProject(ws_item_sk=[$0], $f1=[$1], i_item_sk=[$2], i_manufact_id=[$3]) + HiveProject(ws_item_sk=[$0], CAST=[$1], i_item_sk=[$2]) HiveJoin(condition=[=($0, $2)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(ws_item_sk=[$0], $f1=[/($1, $2)]) + HiveProject(ws_item_sk=[$0], CAST=[CAST(*(1.3, /($1, $2))):DECIMAL(14, 7)]) HiveAggregate(group=[{1}], agg#0=[sum($2)], agg#1=[count($2)]) HiveJoin(condition=[=($3, $0)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(ws_sold_date_sk=[$0], ws_item_sk=[$3], ws_ext_discount_amt=[$22]) HiveFilter(condition=[AND(IS NOT NULL($3), IS NOT NULL($0))]) HiveTableScan(table=[[default, web_sales]], table:alias=[web_sales]) - HiveProject(d_date_sk=[$0], d_date=[$2]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(BETWEEN(false, CAST($2):TIMESTAMP(9), 1998-03-18 00:00:00, 1998-06-16 00:00:00), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) - HiveProject(i_item_sk=[$0], i_manufact_id=[CAST(269):INTEGER]) + HiveProject(i_item_sk=[$0]) HiveFilter(condition=[AND(=($13, 269), IS NOT NULL($0))]) HiveTableScan(table=[[default, item]], table:alias=[item]) diff --git ql/src/test/results/clientpositive/perf/tez/cbo_query93.q.out ql/src/test/results/clientpositive/perf/tez/cbo_query93.q.out index 60b7557d4df..6a8ed39e298 100644 --- ql/src/test/results/clientpositive/perf/tez/cbo_query93.q.out +++ ql/src/test/results/clientpositive/perf/tez/cbo_query93.q.out @@ -44,16 +44,16 @@ CBO PLAN: HiveSortLimit(sort0=[$1], sort1=[$0], dir0=[ASC], dir1=[ASC], fetch=[100]) HiveProject(ss_customer_sk=[$0], $f1=[$1]) HiveAggregate(group=[{0}], agg#0=[sum($1)]) - HiveProject(ss_customer_sk=[$1], act_sales=[CASE(IS NOT NULL($8), *(CAST(-($3, $8)):DECIMAL(10, 0), $4), *(CAST($3):DECIMAL(10, 0), $4))]) - HiveJoin(condition=[AND(=($5, $0), =($7, $2))], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(ss_item_sk=[$2], ss_customer_sk=[$3], ss_ticket_number=[$9], ss_quantity=[$10], ss_sales_price=[$13]) + HiveProject(ss_customer_sk=[$1], act_sales=[CASE($10, *(CAST(-($3, $9)):DECIMAL(10, 0), $4), $5)]) + HiveJoin(condition=[AND(=($6, $0), =($8, $2))], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(ss_item_sk=[$2], ss_customer_sk=[$3], ss_ticket_number=[$9], ss_quantity=[$10], ss_sales_price=[$13], *=[*(CAST($10):DECIMAL(10, 0), $13)]) HiveFilter(condition=[AND(IS NOT NULL($2), IS NOT NULL($9))]) HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) - HiveJoin(condition=[=($1, $4)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(sr_item_sk=[$2], sr_reason_sk=[$8], sr_ticket_number=[$9], sr_return_quantity=[$10]) + HiveJoin(condition=[=($1, $5)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(sr_item_sk=[$2], sr_reason_sk=[$8], sr_ticket_number=[$9], sr_return_quantity=[$10], IS NOT NULL=[IS NOT NULL($10)]) HiveFilter(condition=[AND(IS NOT NULL($8), IS NOT NULL($2), IS NOT NULL($9))]) HiveTableScan(table=[[default, store_returns]], table:alias=[store_returns]) - HiveProject(r_reason_sk=[$0], r_reason_desc=[CAST(_UTF-16LE'Did not like the warranty'):VARCHAR(2147483647) CHARACTER SET "UTF-16LE" COLLATE "ISO-8859-1$en_US$primary"]) + HiveProject(r_reason_sk=[$0]) HiveFilter(condition=[AND(=($2, _UTF-16LE'Did not like the warranty'), IS NOT NULL($0))]) HiveTableScan(table=[[default, reason]], table:alias=[reason]) diff --git ql/src/test/results/clientpositive/perf/tez/cbo_query95.q.out ql/src/test/results/clientpositive/perf/tez/cbo_query95.q.out index c2488905157..6a201658df1 100644 --- ql/src/test/results/clientpositive/perf/tez/cbo_query95.q.out +++ ql/src/test/results/clientpositive/perf/tez/cbo_query95.q.out @@ -76,8 +76,8 @@ CBO PLAN: HiveProject(order count=[$0], total shipping cost=[$1], total net profit=[$2]) HiveSortLimit(sort0=[$3], dir0=[ASC], fetch=[100]) HiveProject(order count=[$0], total shipping cost=[$1], total net profit=[$2], (tok_functiondi count (tok_table_or_col ws_order_number))=[$0]) - HiveAggregate(group=[{}], agg#0=[count(DISTINCT $7)], agg#1=[sum($8)], agg#2=[sum($9)]) - HiveJoin(condition=[=($7, $0)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveAggregate(group=[{}], agg#0=[count(DISTINCT $6)], agg#1=[sum($7)], agg#2=[sum($8)]) + HiveJoin(condition=[=($6, $0)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(wr_order_number=[$0]) HiveAggregate(group=[{14}]) HiveJoin(condition=[=($14, $0)], joinType=[inner], algorithm=[none], cost=[not available]) @@ -92,7 +92,7 @@ HiveProject(order count=[$0], total shipping cost=[$1], total net profit=[$2]) HiveProject(wr_returned_date_sk=[$0], wr_returned_time_sk=[$1], wr_item_sk=[$2], wr_refunded_customer_sk=[$3], wr_refunded_cdemo_sk=[$4], wr_refunded_hdemo_sk=[$5], wr_refunded_addr_sk=[$6], wr_returning_customer_sk=[$7], wr_returning_cdemo_sk=[$8], wr_returning_hdemo_sk=[$9], wr_returning_addr_sk=[$10], wr_web_page_sk=[$11], wr_reason_sk=[$12], wr_order_number=[$13], wr_return_quantity=[$14], wr_return_amt=[$15], wr_return_tax=[$16], wr_return_amt_inc_tax=[$17], wr_fee=[$18], wr_return_ship_cost=[$19], wr_refunded_cash=[$20], wr_reversed_charge=[$21], wr_account_credit=[$22], wr_net_loss=[$23], BLOCK__OFFSET__INSIDE__FILE=[$24], INPUT__FILE__NAME=[$25], ROW__ID=[$26]) HiveFilter(condition=[IS NOT NULL($13)]) HiveTableScan(table=[[default, web_returns]], table:alias=[web_returns]) - HiveJoin(condition=[=($6, $0)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($5, $0)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(ws_order_number=[$0]) HiveAggregate(group=[{1}]) HiveJoin(condition=[AND(=($1, $3), <>($0, $2))], joinType=[inner], algorithm=[none], cost=[not available]) @@ -102,9 +102,9 @@ HiveProject(order count=[$0], total shipping cost=[$1], total net profit=[$2]) HiveProject(ws_warehouse_sk=[$15], ws_order_number=[$17]) HiveFilter(condition=[IS NOT NULL($17)]) HiveTableScan(table=[[default, web_sales]], table:alias=[ws2]) - HiveJoin(condition=[=($4, $10)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveJoin(condition=[=($3, $0)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(ca_address_sk=[$0], ca_state=[CAST(_UTF-16LE'TX'):VARCHAR(2147483647) CHARACTER SET "UTF-16LE" COLLATE "ISO-8859-1$en_US$primary"]) + HiveJoin(condition=[=($3, $9)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($2, $0)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(ca_address_sk=[$0]) HiveFilter(condition=[AND(=($8, _UTF-16LE'TX'), IS NOT NULL($0))]) HiveTableScan(table=[[default, customer_address]], table:alias=[customer_address]) HiveJoin(condition=[=($0, $6)], joinType=[inner], algorithm=[none], cost=[not available]) @@ -114,7 +114,7 @@ HiveProject(order count=[$0], total shipping cost=[$1], total net profit=[$2]) HiveProject(d_date_sk=[$0], d_date=[$2]) HiveFilter(condition=[AND(BETWEEN(false, CAST($2):TIMESTAMP(9), 1999-05-01 00:00:00, 1999-06-30 00:00:00), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) - HiveProject(web_site_sk=[$0], web_company_name=[CAST(_UTF-16LE'pri'):VARCHAR(2147483647) CHARACTER SET "UTF-16LE" COLLATE "ISO-8859-1$en_US$primary"]) + HiveProject(web_site_sk=[$0]) HiveFilter(condition=[AND(=($14, _UTF-16LE'pri'), IS NOT NULL($0))]) HiveTableScan(table=[[default, web_site]], table:alias=[web_site]) diff --git ql/src/test/results/clientpositive/perf/tez/cbo_query96.q.out ql/src/test/results/clientpositive/perf/tez/cbo_query96.q.out index 6367e9899c7..ca9a51f32b4 100644 --- ql/src/test/results/clientpositive/perf/tez/cbo_query96.q.out +++ ql/src/test/results/clientpositive/perf/tez/cbo_query96.q.out @@ -43,19 +43,19 @@ HiveProject(_o__c0=[$0]) HiveSortLimit(sort0=[$1], dir0=[ASC], fetch=[100]) HiveProject(_o__c0=[$0], (tok_functionstar count)=[$0]) HiveAggregate(group=[{}], agg#0=[count()]) - HiveJoin(condition=[=($2, $8)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveJoin(condition=[=($1, $6)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($2, $5)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($1, $4)], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($0, $3)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(ss_sold_time_sk=[$1], ss_hdemo_sk=[$5], ss_store_sk=[$7]) HiveFilter(condition=[AND(IS NOT NULL($5), IS NOT NULL($1), IS NOT NULL($7))]) HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) - HiveProject(t_time_sk=[$0], t_hour=[CAST(8):INTEGER], t_minute=[$4]) + HiveProject(t_time_sk=[$0]) HiveFilter(condition=[AND(=($3, 8), >=($4, 30), IS NOT NULL($0))]) HiveTableScan(table=[[default, time_dim]], table:alias=[time_dim]) - HiveProject(hd_demo_sk=[$0], hd_dep_count=[CAST(5):INTEGER]) + HiveProject(hd_demo_sk=[$0]) HiveFilter(condition=[AND(=($3, 5), IS NOT NULL($0))]) HiveTableScan(table=[[default, household_demographics]], table:alias=[household_demographics]) - HiveProject(s_store_sk=[$0], s_store_name=[CAST(_UTF-16LE'ese'):VARCHAR(2147483647) CHARACTER SET "UTF-16LE" COLLATE "ISO-8859-1$en_US$primary"]) + HiveProject(s_store_sk=[$0]) HiveFilter(condition=[AND(=($5, _UTF-16LE'ese'), IS NOT NULL($0))]) HiveTableScan(table=[[default, store]], table:alias=[store]) diff --git ql/src/test/results/clientpositive/perf/tez/cbo_query97.q.out ql/src/test/results/clientpositive/perf/tez/cbo_query97.q.out index 5cd85827db5..f79dffbdc86 100644 --- ql/src/test/results/clientpositive/perf/tez/cbo_query97.q.out +++ ql/src/test/results/clientpositive/perf/tez/cbo_query97.q.out @@ -66,7 +66,7 @@ HiveSortLimit(fetch=[100]) HiveProject(ss_sold_date_sk=[$0], ss_item_sk=[$2], ss_customer_sk=[$3]) HiveFilter(condition=[IS NOT NULL($0)]) HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) - HiveProject(d_date_sk=[$0], d_month_seq=[$3]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(BETWEEN(false, $3, 1212, 1223), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) HiveProject(cs_bill_customer_sk=[$0], cs_item_sk=[$1]) @@ -75,7 +75,7 @@ HiveSortLimit(fetch=[100]) HiveProject(cs_sold_date_sk=[$0], cs_bill_customer_sk=[$3], cs_item_sk=[$15]) HiveFilter(condition=[IS NOT NULL($0)]) HiveTableScan(table=[[default, catalog_sales]], table:alias=[catalog_sales]) - HiveProject(d_date_sk=[$0], d_month_seq=[$3]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(BETWEEN(false, $3, 1212, 1223), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) diff --git ql/src/test/results/clientpositive/perf/tez/cbo_query98.q.out ql/src/test/results/clientpositive/perf/tez/cbo_query98.q.out index 804885cc83a..374a6a06d63 100644 --- ql/src/test/results/clientpositive/perf/tez/cbo_query98.q.out +++ ql/src/test/results/clientpositive/perf/tez/cbo_query98.q.out @@ -81,7 +81,7 @@ HiveProject(i_item_desc=[$0], i_category=[$1], i_class=[$2], i_current_price=[$3 HiveProject(ss_sold_date_sk=[$0], ss_item_sk=[$2], ss_ext_sales_price=[$15]) HiveFilter(condition=[AND(IS NOT NULL($2), IS NOT NULL($0))]) HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) - HiveProject(d_date_sk=[$0], d_date=[$2]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(BETWEEN(false, CAST($2):TIMESTAMP(9), 2001-01-12 00:00:00, 2001-02-11 00:00:00), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) diff --git ql/src/test/results/clientpositive/perf/tez/cbo_query99.q.out ql/src/test/results/clientpositive/perf/tez/cbo_query99.q.out index 75d0e605d4a..8ca409d3c34 100644 --- ql/src/test/results/clientpositive/perf/tez/cbo_query99.q.out +++ ql/src/test/results/clientpositive/perf/tez/cbo_query99.q.out @@ -81,26 +81,25 @@ POSTHOOK: Output: hdfs://### HDFS PATH ### CBO PLAN: HiveProject(_o__c0=[$0], sm_type=[$1], cc_name=[$2], 30 days=[$3], 31-60 days=[$4], 61-90 days=[$5], 91-120 days=[$6], >120 days=[$7]) HiveSortLimit(sort0=[$8], sort1=[$1], sort2=[$2], dir0=[ASC], dir1=[ASC], dir2=[ASC], fetch=[100]) - HiveProject(_o__c0=[$0], sm_type=[$1], cc_name=[$2], 30 days=[$3], 31-60 days=[$4], 61-90 days=[$5], 91-120 days=[$6], >120 days=[$7], (tok_function substr (tok_table_or_col w_warehouse_name) 1 20)=[$0]) - HiveAggregate(group=[{0, 1, 2}], agg#0=[sum($3)], agg#1=[sum($4)], agg#2=[sum($5)], agg#3=[sum($6)], agg#4=[sum($7)]) - HiveProject($f0=[substr($10, 1, 20)], $f1=[$12], $f2=[$8], $f3=[CASE(<=(-($1, $0), 30), 1, 0)], $f4=[CASE(AND(>(-($1, $0), 30), <=(-($1, $0), 60)), 1, 0)], $f5=[CASE(AND(>(-($1, $0), 60), <=(-($1, $0), 90)), 1, 0)], $f6=[CASE(AND(>(-($1, $0), 90), <=(-($1, $0), 120)), 1, 0)], $f7=[CASE(>(-($1, $0), 120), 1, 0)]) - HiveJoin(condition=[=($3, $11)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveJoin(condition=[=($4, $9)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveJoin(condition=[=($2, $7)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveJoin(condition=[=($1, $5)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(cs_sold_date_sk=[$0], cs_ship_date_sk=[$2], cs_call_center_sk=[$11], cs_ship_mode_sk=[$13], cs_warehouse_sk=[$14]) - HiveFilter(condition=[AND(IS NOT NULL($14), IS NOT NULL($13), IS NOT NULL($11), IS NOT NULL($2))]) - HiveTableScan(table=[[default, catalog_sales]], table:alias=[catalog_sales]) - HiveProject(d_date_sk=[$0], d_month_seq=[$3]) - HiveFilter(condition=[AND(BETWEEN(false, $3, 1212, 1223), IS NOT NULL($0))]) - HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) - HiveProject(cc_call_center_sk=[$0], cc_name=[$6]) - HiveFilter(condition=[IS NOT NULL($0)]) - HiveTableScan(table=[[default, call_center]], table:alias=[call_center]) - HiveProject(w_warehouse_sk=[$0], w_warehouse_name=[$2]) + HiveProject(_o__c0=[$1], sm_type=[$2], cc_name=[$0], 30 days=[$3], 31-60 days=[$4], 61-90 days=[$5], 91-120 days=[$6], >120 days=[$7], (tok_function substr (tok_table_or_col w_warehouse_name) 1 20)=[$1]) + HiveAggregate(group=[{11, 13, 15}], agg#0=[sum($4)], agg#1=[sum($5)], agg#2=[sum($6)], agg#3=[sum($7)], agg#4=[sum($8)]) + HiveJoin(condition=[=($2, $14)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($3, $12)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($1, $10)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($0, $9)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(cs_ship_date_sk=[$2], cs_call_center_sk=[$11], cs_ship_mode_sk=[$13], cs_warehouse_sk=[$14], CASE=[CASE(<=(-($2, $0), 30), 1, 0)], CASE5=[CASE(AND(>(-($2, $0), 30), <=(-($2, $0), 60)), 1, 0)], CASE6=[CASE(AND(>(-($2, $0), 60), <=(-($2, $0), 90)), 1, 0)], CASE7=[CASE(AND(>(-($2, $0), 90), <=(-($2, $0), 120)), 1, 0)], CASE8=[CASE(>(-($2, $0), 120), 1, 0)]) + HiveFilter(condition=[AND(IS NOT NULL($14), IS NOT NULL($13), IS NOT NULL($11), IS NOT NULL($2))]) + HiveTableScan(table=[[default, catalog_sales]], table:alias=[catalog_sales]) + HiveProject(d_date_sk=[$0]) + HiveFilter(condition=[AND(BETWEEN(false, $3, 1212, 1223), IS NOT NULL($0))]) + HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) + HiveProject(cc_call_center_sk=[$0], cc_name=[$6]) HiveFilter(condition=[IS NOT NULL($0)]) - HiveTableScan(table=[[default, warehouse]], table:alias=[warehouse]) - HiveProject(sm_ship_mode_sk=[$0], sm_type=[$2]) + HiveTableScan(table=[[default, call_center]], table:alias=[call_center]) + HiveProject(w_warehouse_sk=[$0], substr=[substr($2, 1, 20)]) HiveFilter(condition=[IS NOT NULL($0)]) - HiveTableScan(table=[[default, ship_mode]], table:alias=[ship_mode]) + HiveTableScan(table=[[default, warehouse]], table:alias=[warehouse]) + HiveProject(sm_ship_mode_sk=[$0], sm_type=[$2]) + HiveFilter(condition=[IS NOT NULL($0)]) + HiveTableScan(table=[[default, ship_mode]], table:alias=[ship_mode]) diff --git ql/src/test/results/clientpositive/perf/tez/constraints/mv_query44.q.out ql/src/test/results/clientpositive/perf/tez/constraints/mv_query44.q.out new file mode 100644 index 00000000000..db9acc93cb2 --- /dev/null +++ ql/src/test/results/clientpositive/perf/tez/constraints/mv_query44.q.out @@ -0,0 +1,214 @@ +PREHOOK: query: CREATE MATERIALIZED VIEW mv_store_sales_item_customer PARTITIONED ON (ss_sold_date_sk) +AS + select ss_item_sk, ss_store_sk, ss_customer_sk, ss_sold_date_sk, count(*) cnt, sum(ss_quantity) as ss_quantity, sum(ss_ext_wholesale_cost) as ss_ext_wholesale_cost,sum(ss_net_paid) as ss_net_paid,sum(ss_net_profit) as ss_net_profit, sum(ss_ext_sales_price) as ss_ext_sales_price, sum(ss_coupon_amt) amt, sum(ss_sales_price) ss_sales_price, sum(ss_quantity*ss_sales_price) ssales + from store_sales + group by ss_store_sk, + ss_item_sk, ss_customer_sk, ss_sold_date_sk +PREHOOK: type: CREATE_MATERIALIZED_VIEW +PREHOOK: Input: default@store_sales +PREHOOK: Output: database:default +PREHOOK: Output: default@mv_store_sales_item_customer +PREHOOK: Output: default@mv_store_sales_item_customer +POSTHOOK: query: CREATE MATERIALIZED VIEW mv_store_sales_item_customer PARTITIONED ON (ss_sold_date_sk) +AS + select ss_item_sk, ss_store_sk, ss_customer_sk, ss_sold_date_sk, count(*) cnt, sum(ss_quantity) as ss_quantity, sum(ss_ext_wholesale_cost) as ss_ext_wholesale_cost,sum(ss_net_paid) as ss_net_paid,sum(ss_net_profit) as ss_net_profit, sum(ss_ext_sales_price) as ss_ext_sales_price, sum(ss_coupon_amt) amt, sum(ss_sales_price) ss_sales_price, sum(ss_quantity*ss_sales_price) ssales + from store_sales + group by ss_store_sk, + ss_item_sk, ss_customer_sk, ss_sold_date_sk +POSTHOOK: type: CREATE_MATERIALIZED_VIEW +POSTHOOK: Input: default@store_sales +POSTHOOK: Output: database:default +POSTHOOK: Output: default@mv_store_sales_item_customer +Warning: Shuffle Join MERGEJOIN[101][tables = [$hdt$_1, $hdt$_2]] in Stage 'Reducer 8' is a cross product +PREHOOK: query: explain +select asceding.rnk, i1.i_product_name best_performing, i2.i_product_name worst_performing +from(select * + from (select item_sk,rank() over (order by rank_col asc) rnk + from (select ss_item_sk item_sk,avg(ss_net_profit) rank_col + from store_sales ss1 + where ss_store_sk = 410 + group by ss_item_sk + having avg(ss_net_profit) > 0.9*(select avg(ss_net_profit) rank_col + from store_sales + where ss_store_sk = 410 + and ss_hdemo_sk is null + group by ss_store_sk))V1)V11 + where rnk < 11) asceding, + (select * + from (select item_sk,rank() over (order by rank_col desc) rnk + from (select ss_item_sk item_sk,avg(ss_net_profit) rank_col + from store_sales ss1 + where ss_store_sk = 410 + group by ss_item_sk + having avg(ss_net_profit) > 0.9*(select avg(ss_net_profit) rank_col + from store_sales + where ss_store_sk = 410 + and ss_hdemo_sk is null + group by ss_store_sk))V2)V21 + where rnk < 11) descending, +item i1, +item i2 +where asceding.rnk = descending.rnk + and i1.i_item_sk=asceding.item_sk + and i2.i_item_sk=descending.item_sk +order by asceding.rnk +limit 100 +PREHOOK: type: QUERY +PREHOOK: Input: default@item +PREHOOK: Input: default@store_sales +PREHOOK: Output: hdfs://### HDFS PATH ### +POSTHOOK: query: explain +select asceding.rnk, i1.i_product_name best_performing, i2.i_product_name worst_performing +from(select * + from (select item_sk,rank() over (order by rank_col asc) rnk + from (select ss_item_sk item_sk,avg(ss_net_profit) rank_col + from store_sales ss1 + where ss_store_sk = 410 + group by ss_item_sk + having avg(ss_net_profit) > 0.9*(select avg(ss_net_profit) rank_col + from store_sales + where ss_store_sk = 410 + and ss_hdemo_sk is null + group by ss_store_sk))V1)V11 + where rnk < 11) asceding, + (select * + from (select item_sk,rank() over (order by rank_col desc) rnk + from (select ss_item_sk item_sk,avg(ss_net_profit) rank_col + from store_sales ss1 + where ss_store_sk = 410 + group by ss_item_sk + having avg(ss_net_profit) > 0.9*(select avg(ss_net_profit) rank_col + from store_sales + where ss_store_sk = 410 + and ss_hdemo_sk is null + group by ss_store_sk))V2)V21 + where rnk < 11) descending, +item i1, +item i2 +where asceding.rnk = descending.rnk + and i1.i_item_sk=asceding.item_sk + and i2.i_item_sk=descending.item_sk +order by asceding.rnk +limit 100 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@item +POSTHOOK: Input: default@store_sales +POSTHOOK: Output: hdfs://### HDFS PATH ### +Plan optimized by CBO. + +Vertex dependency in root stage +Reducer 10 <- Reducer 8 (SIMPLE_EDGE) +Reducer 12 <- Map 11 (SIMPLE_EDGE) +Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 9 (SIMPLE_EDGE) +Reducer 3 <- Reducer 2 (SIMPLE_EDGE), Reducer 5 (SIMPLE_EDGE) +Reducer 4 <- Reducer 3 (SIMPLE_EDGE) +Reducer 5 <- Map 1 (SIMPLE_EDGE), Reducer 10 (SIMPLE_EDGE) +Reducer 7 <- Map 6 (SIMPLE_EDGE) +Reducer 8 <- Reducer 12 (CUSTOM_SIMPLE_EDGE), Reducer 7 (CUSTOM_SIMPLE_EDGE) +Reducer 9 <- Reducer 8 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:100 + Stage-1 + Reducer 4 vectorized + File Output Operator [FS_135] + Limit [LIM_134] (rows=100 width=218) + Number of rows:100 + Select Operator [SEL_133] (rows=6951 width=218) + Output:["_col0","_col1","_col2"] + <-Reducer 3 [SIMPLE_EDGE] + SHUFFLE [RS_67] + Select Operator [SEL_66] (rows=6951 width=218) + Output:["_col0","_col1","_col2"] + Merge Join Operator [MERGEJOIN_105] (rows=6951 width=218) + Conds:RS_63._col3=RS_64._col3(Inner),Output:["_col1","_col3","_col5"] + <-Reducer 2 [SIMPLE_EDGE] + SHUFFLE [RS_63] + PartitionCols:_col3 + Merge Join Operator [MERGEJOIN_102] (rows=6951 width=111) + Conds:RS_107._col0=RS_127._col0(Inner),Output:["_col1","_col3"] + <-Map 1 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_107] + PartitionCols:_col0 + Select Operator [SEL_106] (rows=462000 width=111) + Output:["_col0","_col1"] + TableScan [TS_0] (rows=462000 width=111) + default@item,i1,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_product_name"] + <-Reducer 9 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_127] + PartitionCols:_col0 + Select Operator [SEL_126] (rows=6951 width=8) + Output:["_col0","_col1"] + Filter Operator [FIL_125] (rows=6951 width=116) + predicate:(rank_window_0 < 11) + PTF Operator [PTF_124] (rows=20854 width=116) + Function definitions:[{},{"name:":"windowingtablefunction","order by:":"_col1 ASC NULLS FIRST","partition by:":"0"}] + Select Operator [SEL_123] (rows=20854 width=116) + Output:["_col0","_col1"] + <-Reducer 8 [SIMPLE_EDGE] + SHUFFLE [RS_21] + PartitionCols:0 + Filter Operator [FIL_20] (rows=20854 width=228) + predicate:(_col1 > (0.9 * _col2)) + Merge Join Operator [MERGEJOIN_101] (rows=62562 width=228) + Conds:(Inner),Output:["_col0","_col1","_col2"] + <-Reducer 12 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_122] + Select Operator [SEL_121] (rows=1 width=112) + Output:["_col0"] + Group By Operator [GBY_120] (rows=1 width=124) + Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)","count(VALUE._col1)"],keys:KEY._col0 + <-Map 11 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_119] + PartitionCols:_col0 + Group By Operator [GBY_118] (rows=258 width=124) + Output:["_col0","_col1","_col2"],aggregations:["sum(_col1)","count(_col1)"],keys:true + Select Operator [SEL_117] (rows=287946 width=114) + Output:["_col1"] + Filter Operator [FIL_116] (rows=287946 width=114) + predicate:((ss_store_sk = 410) and ss_hdemo_sk is null) + TableScan [TS_9] (rows=575995635 width=114) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_hdemo_sk","ss_store_sk","ss_net_profit"] + <-Reducer 7 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_115] + Select Operator [SEL_114] (rows=62562 width=116) + Output:["_col0","_col1"] + Group By Operator [GBY_113] (rows=62562 width=124) + Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)","count(VALUE._col1)"],keys:KEY._col0 + <-Map 6 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_112] + PartitionCols:_col0 + Group By Operator [GBY_111] (rows=3199976 width=124) + Output:["_col0","_col1","_col2"],aggregations:["sum(ss_net_profit)","count(ss_net_profit)"],keys:ss_item_sk + Select Operator [SEL_110] (rows=6399952 width=114) + Output:["ss_item_sk","ss_net_profit"] + Filter Operator [FIL_109] (rows=6399952 width=114) + predicate:(ss_store_sk = 410) + TableScan [TS_2] (rows=575995635 width=114) + default@store_sales,ss1,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_item_sk","ss_store_sk","ss_net_profit"] + <-Reducer 5 [SIMPLE_EDGE] + SHUFFLE [RS_64] + PartitionCols:_col3 + Merge Join Operator [MERGEJOIN_104] (rows=6951 width=111) + Conds:RS_108._col0=RS_132._col0(Inner),Output:["_col1","_col3"] + <-Map 1 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_108] + PartitionCols:_col0 + Please refer to the previous Select Operator [SEL_106] + <-Reducer 10 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_132] + PartitionCols:_col0 + Select Operator [SEL_131] (rows=6951 width=8) + Output:["_col0","_col1"] + Filter Operator [FIL_130] (rows=6951 width=116) + predicate:(rank_window_0 < 11) + PTF Operator [PTF_129] (rows=20854 width=116) + Function definitions:[{},{"name:":"windowingtablefunction","order by:":"_col1 DESC NULLS LAST","partition by:":"0"}] + Select Operator [SEL_128] (rows=20854 width=116) + Output:["_col0","_col1"] + <-Reducer 8 [SIMPLE_EDGE] + SHUFFLE [RS_49] + PartitionCols:0 + Please refer to the previous Filter Operator [FIL_20] + diff --git ql/src/test/results/clientpositive/perf/tez/query1.q.out ql/src/test/results/clientpositive/perf/tez/query1.q.out index a3de5c69456..532133600d1 100644 --- ql/src/test/results/clientpositive/perf/tez/query1.q.out +++ ql/src/test/results/clientpositive/perf/tez/query1.q.out @@ -83,14 +83,14 @@ Stage-0 Select Operator [SEL_49] (rows=816091 width=100) Output:["_col0"] Filter Operator [FIL_48] (rows=816091 width=324) - predicate:(_col2 > _col7) + predicate:(_col2 > _col6) Merge Join Operator [MERGEJOIN_134] (rows=2448274 width=324) - Conds:RS_45._col1=RS_158._col1(Inner),Output:["_col2","_col6","_col7"] + Conds:RS_45._col1=RS_158._col1(Inner),Output:["_col2","_col5","_col6"] <-Reducer 5 [SIMPLE_EDGE] SHUFFLE [RS_45] PartitionCols:_col1 Merge Join Operator [MERGEJOIN_132] (rows=2369298 width=213) - Conds:RS_42._col0=RS_153._col0(Inner),Output:["_col1","_col2","_col6"] + Conds:RS_42._col0=RS_153._col0(Inner),Output:["_col1","_col2","_col5"] <-Map 12 [SIMPLE_EDGE] vectorized SHUFFLE [RS_153] PartitionCols:_col0 @@ -108,7 +108,7 @@ Stage-0 <-Map 11 [SIMPLE_EDGE] vectorized SHUFFLE [RS_150] PartitionCols:_col0 - Select Operator [SEL_149] (rows=35 width=90) + Select Operator [SEL_149] (rows=35 width=4) Output:["_col0"] Filter Operator [FIL_148] (rows=35 width=90) predicate:((s_state = 'NM') and s_store_sk is not null) @@ -140,7 +140,7 @@ Stage-0 <-Map 10 [SIMPLE_EDGE] vectorized SHUFFLE [RS_143] PartitionCols:_col0 - Select Operator [SEL_142] (rows=652 width=8) + Select Operator [SEL_142] (rows=652 width=4) Output:["_col0"] Filter Operator [FIL_141] (rows=652 width=8) predicate:((d_year = 2000) and d_date_sk is not null) diff --git ql/src/test/results/clientpositive/perf/tez/query10.q.out ql/src/test/results/clientpositive/perf/tez/query10.q.out index d049b2f28ba..26447bdd390 100644 --- ql/src/test/results/clientpositive/perf/tez/query10.q.out +++ ql/src/test/results/clientpositive/perf/tez/query10.q.out @@ -243,7 +243,7 @@ Stage-0 <-Map 16 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_193] PartitionCols:_col0 - Select Operator [SEL_192] (rows=201 width=12) + Select Operator [SEL_192] (rows=201 width=4) Output:["_col0"] Filter Operator [FIL_191] (rows=201 width=12) predicate:((d_year = 2002) and d_date_sk is not null and d_moy BETWEEN 4 AND 7) diff --git ql/src/test/results/clientpositive/perf/tez/query11.q.out ql/src/test/results/clientpositive/perf/tez/query11.q.out index 2f453f3ab0d..da1c349ff06 100644 --- ql/src/test/results/clientpositive/perf/tez/query11.q.out +++ ql/src/test/results/clientpositive/perf/tez/query11.q.out @@ -189,249 +189,241 @@ Stage-0 limit:100 Stage-1 Reducer 8 vectorized - File Output Operator [FS_358] - Limit [LIM_357] (rows=100 width=85) + File Output Operator [FS_354] + Limit [LIM_353] (rows=100 width=85) Number of rows:100 - Select Operator [SEL_356] (rows=12248093 width=85) + Select Operator [SEL_352] (rows=12248093 width=85) Output:["_col0"] <-Reducer 7 [SIMPLE_EDGE] - SHUFFLE [RS_97] - Select Operator [SEL_96] (rows=12248093 width=85) + SHUFFLE [RS_93] + Select Operator [SEL_92] (rows=12248093 width=85) Output:["_col0"] - Filter Operator [FIL_95] (rows=12248093 width=533) - predicate:CASE WHEN (_col3 is not null) THEN (CASE WHEN (_col5 is not null) THEN (((_col1 / _col5) > (_col8 / _col3))) ELSE ((null > (_col8 / _col3))) END) ELSE (CASE WHEN (_col5 is not null) THEN (((_col1 / _col5) > null)) ELSE (null) END) END - Merge Join Operator [MERGEJOIN_291] (rows=24496186 width=533) - Conds:RS_92._col2=RS_355._col0(Inner),Output:["_col1","_col3","_col5","_col7","_col8"] + Filter Operator [FIL_91] (rows=12248093 width=537) + predicate:CASE WHEN (_col3 is not null) THEN (CASE WHEN (_col6) THEN (((_col1 / _col5) > (_col9 / _col3))) ELSE ((null > (_col9 / _col3))) END) ELSE (CASE WHEN (_col6) THEN (((_col1 / _col5) > null)) ELSE (null) END) END + Merge Join Operator [MERGEJOIN_287] (rows=24496186 width=537) + Conds:RS_88._col2=RS_351._col0(Inner),Output:["_col1","_col3","_col5","_col6","_col8","_col9"] <-Reducer 20 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_355] + SHUFFLE [RS_351] PartitionCols:_col0 - Select Operator [SEL_354] (rows=80000000 width=297) + Select Operator [SEL_350] (rows=80000000 width=297) Output:["_col0","_col1","_col2"] - Group By Operator [GBY_353] (rows=80000000 width=764) + Group By Operator [GBY_349] (rows=80000000 width=764) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4, KEY._col5, KEY._col6 <-Reducer 19 [SIMPLE_EDGE] - SHUFFLE [RS_83] + SHUFFLE [RS_79] PartitionCols:_col0, _col1, _col2, _col3, _col4, _col5, _col6 - Group By Operator [GBY_82] (rows=80000000 width=764) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"],aggregations:["sum(_col7)"],keys:_col0, _col1, _col2, _col3, _col4, _col5, _col6 - Select Operator [SEL_80] (rows=187573258 width=847) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] - Merge Join Operator [MERGEJOIN_288] (rows=187573258 width=847) - Conds:RS_77._col1=RS_321._col0(Inner),Output:["_col2","_col3","_col7","_col8","_col9","_col10","_col11","_col12","_col13"] - <-Map 26 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_321] - PartitionCols:_col0 - Select Operator [SEL_320] (rows=80000000 width=656) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] - Filter Operator [FIL_319] (rows=80000000 width=656) - predicate:(c_customer_id is not null and c_customer_sk is not null) - TableScan [TS_71] (rows=80000000 width=656) - default@customer,customer,Tbl:COMPLETE,Col:COMPLETE,Output:["c_customer_sk","c_customer_id","c_first_name","c_last_name","c_preferred_cust_flag","c_birth_country","c_login","c_email_address"] - <-Reducer 18 [SIMPLE_EDGE] - SHUFFLE [RS_77] - PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_287] (rows=187573258 width=199) - Conds:RS_352._col0=RS_298._col0(Inner),Output:["_col1","_col2","_col3"] - <-Map 21 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_298] - PartitionCols:_col0 - Select Operator [SEL_295] (rows=652 width=8) - Output:["_col0"] - Filter Operator [FIL_292] (rows=652 width=8) - predicate:((d_year = 2002) and d_date_sk is not null) - TableScan [TS_68] (rows=73049 width=8) - default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year"] - <-Map 17 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_352] - PartitionCols:_col0 - Select Operator [SEL_351] (rows=525327388 width=221) - Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_350] (rows=525327388 width=221) - predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_75_date_dim_d_date_sk_min) AND DynamicValue(RS_75_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_75_date_dim_d_date_sk_bloom_filter))) and ss_customer_sk is not null and ss_sold_date_sk is not null) - TableScan [TS_65] (rows=575995635 width=221) - default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_customer_sk","ss_ext_discount_amt","ss_ext_list_price"] - <-Reducer 22 [BROADCAST_EDGE] vectorized - BROADCAST [RS_349] - Group By Operator [GBY_348] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 21 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_310] - Group By Operator [GBY_306] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_299] (rows=652 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_295] + Group By Operator [GBY_78] (rows=80000000 width=764) + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"],aggregations:["sum(_col2)"],keys:_col5, _col6, _col7, _col8, _col9, _col10, _col11 + Merge Join Operator [MERGEJOIN_284] (rows=187573258 width=764) + Conds:RS_74._col1=RS_317._col0(Inner),Output:["_col2","_col5","_col6","_col7","_col8","_col9","_col10","_col11"] + <-Map 26 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_317] + PartitionCols:_col0 + Select Operator [SEL_316] (rows=80000000 width=656) + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] + Filter Operator [FIL_315] (rows=80000000 width=656) + predicate:(c_customer_id is not null and c_customer_sk is not null) + TableScan [TS_68] (rows=80000000 width=656) + default@customer,customer,Tbl:COMPLETE,Col:COMPLETE,Output:["c_customer_sk","c_customer_id","c_first_name","c_last_name","c_preferred_cust_flag","c_birth_country","c_login","c_email_address"] + <-Reducer 18 [SIMPLE_EDGE] + SHUFFLE [RS_74] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_283] (rows=187573258 width=115) + Conds:RS_348._col0=RS_294._col0(Inner),Output:["_col1","_col2"] + <-Map 21 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_294] + PartitionCols:_col0 + Select Operator [SEL_291] (rows=652 width=4) + Output:["_col0"] + Filter Operator [FIL_288] (rows=652 width=8) + predicate:((d_year = 2002) and d_date_sk is not null) + TableScan [TS_65] (rows=73049 width=8) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year"] + <-Map 17 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_348] + PartitionCols:_col0 + Select Operator [SEL_347] (rows=525327388 width=119) + Output:["_col0","_col1","_col2"] + Filter Operator [FIL_346] (rows=525327388 width=221) + predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_72_date_dim_d_date_sk_min) AND DynamicValue(RS_72_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_72_date_dim_d_date_sk_bloom_filter))) and ss_customer_sk is not null and ss_sold_date_sk is not null) + TableScan [TS_62] (rows=575995635 width=221) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_customer_sk","ss_ext_discount_amt","ss_ext_list_price"] + <-Reducer 22 [BROADCAST_EDGE] vectorized + BROADCAST [RS_345] + Group By Operator [GBY_344] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 21 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_306] + Group By Operator [GBY_302] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_295] (rows=652 width=4) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_291] <-Reducer 6 [ONE_TO_ONE_EDGE] - FORWARD [RS_92] + FORWARD [RS_88] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_290] (rows=20485011 width=436) - Conds:RS_89._col2=RS_347._col0(Inner),Output:["_col1","_col2","_col3","_col5"] + Merge Join Operator [MERGEJOIN_286] (rows=20485011 width=440) + Conds:RS_85._col2=RS_343._col0(Inner),Output:["_col1","_col2","_col3","_col5","_col6"] <-Reducer 16 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_347] + SHUFFLE [RS_343] PartitionCols:_col0 - Select Operator [SEL_346] (rows=17130654 width=212) - Output:["_col0","_col1"] - Filter Operator [FIL_345] (rows=17130654 width=212) + Select Operator [SEL_342] (rows=17130654 width=216) + Output:["_col0","_col1","_col2"] + Filter Operator [FIL_341] (rows=17130654 width=212) predicate:(_col7 > 0) - Select Operator [SEL_344] (rows=51391963 width=212) + Select Operator [SEL_340] (rows=51391963 width=212) Output:["_col0","_col7"] - Group By Operator [GBY_343] (rows=51391963 width=764) + Group By Operator [GBY_339] (rows=51391963 width=764) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4, KEY._col5, KEY._col6 <-Reducer 15 [SIMPLE_EDGE] - SHUFFLE [RS_61] + SHUFFLE [RS_58] PartitionCols:_col0, _col1, _col2, _col3, _col4, _col5, _col6 - Group By Operator [GBY_60] (rows=51391963 width=764) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"],aggregations:["sum(_col7)"],keys:_col0, _col1, _col2, _col3, _col4, _col5, _col6 - Select Operator [SEL_58] (rows=51391963 width=875) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] - Merge Join Operator [MERGEJOIN_286] (rows=51391963 width=875) - Conds:RS_55._col1=RS_324._col0(Inner),Output:["_col2","_col3","_col7","_col8","_col9","_col10","_col11","_col12","_col13"] - <-Map 26 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_324] - PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_320] - <-Reducer 14 [SIMPLE_EDGE] - SHUFFLE [RS_55] - PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_285] (rows=51391963 width=227) - Conds:RS_342._col0=RS_304._col0(Inner),Output:["_col1","_col2","_col3"] - <-Map 21 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_304] - PartitionCols:_col0 - Select Operator [SEL_297] (rows=652 width=8) - Output:["_col0"] - Filter Operator [FIL_294] (rows=652 width=8) - predicate:((d_year = 2001) and d_date_sk is not null) - Please refer to the previous TableScan [TS_68] - <-Map 13 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_342] - PartitionCols:_col0 - Select Operator [SEL_341] (rows=143930993 width=231) - Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_340] (rows=143930993 width=231) - predicate:((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_sold_date_sk is not null) - TableScan [TS_43] (rows=144002668 width=231) - default@web_sales,web_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_sold_date_sk","ws_bill_customer_sk","ws_ext_discount_amt","ws_ext_list_price"] - <-Reducer 25 [BROADCAST_EDGE] vectorized - BROADCAST [RS_339] - Group By Operator [GBY_338] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 21 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_313] - Group By Operator [GBY_309] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_305] (rows=652 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_297] + Group By Operator [GBY_57] (rows=51391963 width=764) + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"],aggregations:["sum(_col2)"],keys:_col5, _col6, _col7, _col8, _col9, _col10, _col11 + Merge Join Operator [MERGEJOIN_282] (rows=51391963 width=764) + Conds:RS_53._col1=RS_320._col0(Inner),Output:["_col2","_col5","_col6","_col7","_col8","_col9","_col10","_col11"] + <-Map 26 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_320] + PartitionCols:_col0 + Please refer to the previous Select Operator [SEL_316] + <-Reducer 14 [SIMPLE_EDGE] + SHUFFLE [RS_53] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_281] (rows=51391963 width=115) + Conds:RS_338._col0=RS_300._col0(Inner),Output:["_col1","_col2"] + <-Map 21 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_300] + PartitionCols:_col0 + Select Operator [SEL_293] (rows=652 width=4) + Output:["_col0"] + Filter Operator [FIL_290] (rows=652 width=8) + predicate:((d_year = 2001) and d_date_sk is not null) + Please refer to the previous TableScan [TS_65] + <-Map 13 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_338] + PartitionCols:_col0 + Select Operator [SEL_337] (rows=143930993 width=119) + Output:["_col0","_col1","_col2"] + Filter Operator [FIL_336] (rows=143930993 width=231) + predicate:((ws_sold_date_sk BETWEEN DynamicValue(RS_51_date_dim_d_date_sk_min) AND DynamicValue(RS_51_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_51_date_dim_d_date_sk_bloom_filter))) and ws_bill_customer_sk is not null and ws_sold_date_sk is not null) + TableScan [TS_41] (rows=144002668 width=231) + default@web_sales,web_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_sold_date_sk","ws_bill_customer_sk","ws_ext_discount_amt","ws_ext_list_price"] + <-Reducer 25 [BROADCAST_EDGE] vectorized + BROADCAST [RS_335] + Group By Operator [GBY_334] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 21 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_309] + 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_301] (rows=652 width=4) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_293] <-Reducer 5 [ONE_TO_ONE_EDGE] - FORWARD [RS_89] + FORWARD [RS_85] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_289] (rows=31888273 width=324) - Conds:RS_327._col0=RS_337._col0(Inner),Output:["_col1","_col2","_col3"] + Merge Join Operator [MERGEJOIN_285] (rows=31888273 width=324) + Conds:RS_323._col0=RS_333._col0(Inner),Output:["_col1","_col2","_col3"] <-Reducer 12 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_337] + SHUFFLE [RS_333] PartitionCols:_col0 - Select Operator [SEL_336] (rows=26666666 width=212) + Select Operator [SEL_332] (rows=26666666 width=212) Output:["_col0","_col1"] - Filter Operator [FIL_335] (rows=26666666 width=212) + Filter Operator [FIL_331] (rows=26666666 width=212) predicate:(_col7 > 0) - Select Operator [SEL_334] (rows=80000000 width=212) + Select Operator [SEL_330] (rows=80000000 width=212) Output:["_col0","_col7"] - Group By Operator [GBY_333] (rows=80000000 width=764) + Group By Operator [GBY_329] (rows=80000000 width=764) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4, KEY._col5, KEY._col6 <-Reducer 11 [SIMPLE_EDGE] - SHUFFLE [RS_39] + SHUFFLE [RS_37] PartitionCols:_col0, _col1, _col2, _col3, _col4, _col5, _col6 - Group By Operator [GBY_38] (rows=80000000 width=764) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"],aggregations:["sum(_col7)"],keys:_col0, _col1, _col2, _col3, _col4, _col5, _col6 - Select Operator [SEL_36] (rows=187573258 width=847) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] - Merge Join Operator [MERGEJOIN_284] (rows=187573258 width=847) - Conds:RS_33._col1=RS_323._col0(Inner),Output:["_col2","_col3","_col7","_col8","_col9","_col10","_col11","_col12","_col13"] - <-Map 26 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_323] - PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_320] - <-Reducer 10 [SIMPLE_EDGE] - SHUFFLE [RS_33] - PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_283] (rows=187573258 width=199) - Conds:RS_332._col0=RS_302._col0(Inner),Output:["_col1","_col2","_col3"] - <-Map 21 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_302] - PartitionCols:_col0 - Select Operator [SEL_296] (rows=652 width=8) - Output:["_col0"] - Filter Operator [FIL_293] (rows=652 width=8) - predicate:((d_year = 2001) and d_date_sk is not null) - Please refer to the previous TableScan [TS_68] - <-Map 9 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_332] - PartitionCols:_col0 - Select Operator [SEL_331] (rows=525327388 width=221) - Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_330] (rows=525327388 width=221) - predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_31_date_dim_d_date_sk_min) AND DynamicValue(RS_31_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_31_date_dim_d_date_sk_bloom_filter))) and ss_customer_sk is not null and ss_sold_date_sk is not null) - TableScan [TS_21] (rows=575995635 width=221) - default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_customer_sk","ss_ext_discount_amt","ss_ext_list_price"] - <-Reducer 24 [BROADCAST_EDGE] vectorized - BROADCAST [RS_329] - Group By Operator [GBY_328] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 21 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_312] - Group By Operator [GBY_308] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_303] (rows=652 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_296] + Group By Operator [GBY_36] (rows=80000000 width=764) + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"],aggregations:["sum(_col2)"],keys:_col5, _col6, _col7, _col8, _col9, _col10, _col11 + Merge Join Operator [MERGEJOIN_280] (rows=187573258 width=764) + Conds:RS_32._col1=RS_319._col0(Inner),Output:["_col2","_col5","_col6","_col7","_col8","_col9","_col10","_col11"] + <-Map 26 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_319] + PartitionCols:_col0 + Please refer to the previous Select Operator [SEL_316] + <-Reducer 10 [SIMPLE_EDGE] + SHUFFLE [RS_32] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_279] (rows=187573258 width=115) + Conds:RS_328._col0=RS_298._col0(Inner),Output:["_col1","_col2"] + <-Map 21 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_298] + PartitionCols:_col0 + Select Operator [SEL_292] (rows=652 width=4) + Output:["_col0"] + Filter Operator [FIL_289] (rows=652 width=8) + predicate:((d_year = 2001) and d_date_sk is not null) + Please refer to the previous TableScan [TS_65] + <-Map 9 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_328] + PartitionCols:_col0 + Select Operator [SEL_327] (rows=525327388 width=119) + Output:["_col0","_col1","_col2"] + Filter Operator [FIL_326] (rows=525327388 width=221) + predicate:((ss_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(ss_sold_date_sk, DynamicValue(RS_30_date_dim_d_date_sk_bloom_filter))) and ss_customer_sk is not null and ss_sold_date_sk is not null) + TableScan [TS_20] (rows=575995635 width=221) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_customer_sk","ss_ext_discount_amt","ss_ext_list_price"] + <-Reducer 24 [BROADCAST_EDGE] vectorized + BROADCAST [RS_325] + Group By Operator [GBY_324] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 21 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_308] + Group By Operator [GBY_304] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_299] (rows=652 width=4) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_292] <-Reducer 4 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_327] + SHUFFLE [RS_323] PartitionCols:_col0 - Select Operator [SEL_326] (rows=51391963 width=212) + Select Operator [SEL_322] (rows=51391963 width=212) Output:["_col0","_col1"] - Group By Operator [GBY_325] (rows=51391963 width=764) + Group By Operator [GBY_321] (rows=51391963 width=764) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4, KEY._col5, KEY._col6 <-Reducer 3 [SIMPLE_EDGE] - SHUFFLE [RS_18] + SHUFFLE [RS_17] PartitionCols:_col0, _col1, _col2, _col3, _col4, _col5, _col6 - Group By Operator [GBY_17] (rows=51391963 width=764) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"],aggregations:["sum(_col7)"],keys:_col0, _col1, _col2, _col3, _col4, _col5, _col6 - Select Operator [SEL_15] (rows=51391963 width=875) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] - Merge Join Operator [MERGEJOIN_282] (rows=51391963 width=875) - Conds:RS_12._col1=RS_322._col0(Inner),Output:["_col2","_col3","_col7","_col8","_col9","_col10","_col11","_col12","_col13"] - <-Map 26 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_322] - PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_320] - <-Reducer 2 [SIMPLE_EDGE] - SHUFFLE [RS_12] - PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_281] (rows=51391963 width=227) - Conds:RS_318._col0=RS_300._col0(Inner),Output:["_col1","_col2","_col3"] - <-Map 21 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_300] - PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_295] - <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_318] - PartitionCols:_col0 - Select Operator [SEL_317] (rows=143930993 width=231) - Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_316] (rows=143930993 width=231) - predicate:((ws_sold_date_sk BETWEEN DynamicValue(RS_10_date_dim_d_date_sk_min) AND DynamicValue(RS_10_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_10_date_dim_d_date_sk_bloom_filter))) and ws_bill_customer_sk is not null and ws_sold_date_sk is not null) - TableScan [TS_0] (rows=144002668 width=231) - default@web_sales,web_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_sold_date_sk","ws_bill_customer_sk","ws_ext_discount_amt","ws_ext_list_price"] - <-Reducer 23 [BROADCAST_EDGE] vectorized - BROADCAST [RS_315] - Group By Operator [GBY_314] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 21 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_311] - Group By Operator [GBY_307] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_301] (rows=652 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_295] + Group By Operator [GBY_16] (rows=51391963 width=764) + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"],aggregations:["sum(_col2)"],keys:_col5, _col6, _col7, _col8, _col9, _col10, _col11 + Merge Join Operator [MERGEJOIN_278] (rows=51391963 width=764) + Conds:RS_12._col1=RS_318._col0(Inner),Output:["_col2","_col5","_col6","_col7","_col8","_col9","_col10","_col11"] + <-Map 26 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_318] + PartitionCols:_col0 + Please refer to the previous Select Operator [SEL_316] + <-Reducer 2 [SIMPLE_EDGE] + SHUFFLE [RS_12] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_277] (rows=51391963 width=115) + Conds:RS_314._col0=RS_296._col0(Inner),Output:["_col1","_col2"] + <-Map 21 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_296] + PartitionCols:_col0 + Please refer to the previous Select Operator [SEL_291] + <-Map 1 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_314] + PartitionCols:_col0 + Select Operator [SEL_313] (rows=143930993 width=119) + Output:["_col0","_col1","_col2"] + Filter Operator [FIL_312] (rows=143930993 width=231) + predicate:((ws_sold_date_sk BETWEEN DynamicValue(RS_10_date_dim_d_date_sk_min) AND DynamicValue(RS_10_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_10_date_dim_d_date_sk_bloom_filter))) and ws_bill_customer_sk is not null and ws_sold_date_sk is not null) + TableScan [TS_0] (rows=144002668 width=231) + default@web_sales,web_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_sold_date_sk","ws_bill_customer_sk","ws_ext_discount_amt","ws_ext_list_price"] + <-Reducer 23 [BROADCAST_EDGE] vectorized + BROADCAST [RS_311] + Group By Operator [GBY_310] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 21 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_307] + Group By Operator [GBY_303] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_297] (rows=652 width=4) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_291] diff --git ql/src/test/results/clientpositive/perf/tez/query12.q.out ql/src/test/results/clientpositive/perf/tez/query12.q.out index 75156be9fdc..b6e499920ed 100644 --- ql/src/test/results/clientpositive/perf/tez/query12.q.out +++ ql/src/test/results/clientpositive/perf/tez/query12.q.out @@ -109,9 +109,9 @@ Stage-0 SHUFFLE [RS_17] PartitionCols:_col0, _col1, _col2, _col3, _col4 Group By Operator [GBY_16] (rows=138600 width=689) - Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(_col2)"],keys:_col10, _col9, _col6, _col7, _col8 + Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(_col2)"],keys:_col9, _col8, _col5, _col6, _col7 Merge Join Operator [MERGEJOIN_58] (rows=4798568 width=689) - Conds:RS_12._col1=RS_69._col0(Inner),Output:["_col2","_col6","_col7","_col8","_col9","_col10"] + Conds:RS_12._col1=RS_69._col0(Inner),Output:["_col2","_col5","_col6","_col7","_col8","_col9"] <-Map 9 [SIMPLE_EDGE] vectorized SHUFFLE [RS_69] PartitionCols:_col0 @@ -129,7 +129,7 @@ Stage-0 <-Map 7 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_61] PartitionCols:_col0 - Select Operator [SEL_60] (rows=8116 width=98) + Select Operator [SEL_60] (rows=8116 width=4) Output:["_col0"] Filter Operator [FIL_59] (rows=8116 width=98) predicate:(CAST( d_date AS TIMESTAMP) BETWEEN TIMESTAMP'2001-01-12 00:00:00' AND TIMESTAMP'2001-02-11 00:00:00' and d_date_sk is not null) diff --git ql/src/test/results/clientpositive/perf/tez/query13.q.out ql/src/test/results/clientpositive/perf/tez/query13.q.out index 0e02e9aaa15..d6e86c48298 100644 --- ql/src/test/results/clientpositive/perf/tez/query13.q.out +++ ql/src/test/results/clientpositive/perf/tez/query13.q.out @@ -115,17 +115,17 @@ POSTHOOK: Output: hdfs://### HDFS PATH ### Plan optimized by CBO. Vertex dependency in root stage -Map 8 <- Reducer 10 (BROADCAST_EDGE), Reducer 12 (BROADCAST_EDGE), Reducer 14 (BROADCAST_EDGE), Reducer 16 (BROADCAST_EDGE) -Reducer 10 <- Map 9 (CUSTOM_SIMPLE_EDGE) +Map 9 <- Reducer 12 (BROADCAST_EDGE), Reducer 14 (BROADCAST_EDGE), Reducer 16 (BROADCAST_EDGE), Reducer 8 (BROADCAST_EDGE) Reducer 12 <- Map 11 (CUSTOM_SIMPLE_EDGE) Reducer 14 <- Map 13 (CUSTOM_SIMPLE_EDGE) Reducer 16 <- Map 15 (CUSTOM_SIMPLE_EDGE) -Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) -Reducer 3 <- Map 9 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 9 (SIMPLE_EDGE) +Reducer 3 <- Map 10 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) Reducer 4 <- Map 11 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) Reducer 5 <- Map 13 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) Reducer 6 <- Map 15 (SIMPLE_EDGE), Reducer 5 (SIMPLE_EDGE) Reducer 7 <- Reducer 6 (CUSTOM_SIMPLE_EDGE) +Reducer 8 <- Map 1 (CUSTOM_SIMPLE_EDGE) Stage-0 Fetch Operator @@ -140,131 +140,131 @@ Stage-0 <-Reducer 6 [CUSTOM_SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_37] Group By Operator [GBY_36] (rows=1 width=256) - Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(_col6)","count(_col6)","sum(_col8)","count(_col8)","sum(_col9)","count(_col9)"] - Select Operator [SEL_35] (rows=4851 width=183) - Output:["_col6","_col8","_col9"] - Filter Operator [FIL_34] (rows=4851 width=183) - predicate:(((_col19 = 'D') and (_col20 = 'Primary') and _col7 BETWEEN 50 AND 100 and (_col14 = 1)) or ((_col19 = 'M') and (_col20 = '4 yr Degree') and _col7 BETWEEN 100 AND 150 and (_col14 = 3)) or ((_col19 = 'U') and (_col20 = 'Advanced Degree') and _col7 BETWEEN 150 AND 200 and (_col14 = 1))) - Merge Join Operator [MERGEJOIN_121] (rows=58239 width=183) - Conds:RS_31._col2=RS_151._col0(Inner),Output:["_col6","_col7","_col8","_col9","_col14","_col19","_col20"] + Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(_col6)","count(_col6)","sum(_col7)","count(_col7)","sum(_col8)","count(_col8)"] + Select Operator [SEL_35] (rows=40950 width=44) + Output:["_col6","_col7","_col8"] + Filter Operator [FIL_34] (rows=40950 width=44) + predicate:((_col24 and _col25 and _col12 and _col17) or (_col26 and _col27 and _col13 and _col18) or (_col28 and _col29 and _col14 and _col18)) + Merge Join Operator [MERGEJOIN_121] (rows=218403 width=44) + Conds:RS_31._col2=RS_148._col0(Inner),Output:["_col6","_col7","_col8","_col12","_col13","_col14","_col17","_col18","_col24","_col25","_col26","_col27","_col28","_col29"] <-Map 15 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_151] + SHUFFLE [RS_148] PartitionCols:_col0 - Select Operator [SEL_150] (rows=265971 width=183) - Output:["_col0","_col1","_col2"] - Filter Operator [FIL_149] (rows=265971 width=183) + Select Operator [SEL_147] (rows=265971 width=28) + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"] + Filter Operator [FIL_146] (rows=265971 width=183) predicate:((cd_education_status) IN ('4 yr Degree', 'Primary', 'Advanced Degree') and (cd_marital_status) IN ('M', 'D', 'U') and cd_demo_sk is not null) TableScan [TS_15] (rows=1861800 width=183) default@customer_demographics,customer_demographics,Tbl:COMPLETE,Col:COMPLETE,Output:["cd_demo_sk","cd_marital_status","cd_education_status"] <-Reducer 5 [SIMPLE_EDGE] SHUFFLE [RS_31] PartitionCols:_col2 - Filter Operator [FIL_30] (rows=58239 width=90) - predicate:(((_col16) IN ('KY', 'GA', 'NM') and _col10 BETWEEN 100 AND 200) or ((_col16) IN ('MT', 'OR', 'IN') and _col10 BETWEEN 150 AND 300) or ((_col16) IN ('WI', 'MO', 'WV') and _col10 BETWEEN 50 AND 250)) - Merge Join Operator [MERGEJOIN_120] (rows=291204 width=90) - Conds:RS_27._col4=RS_143._col0(Inner),Output:["_col2","_col6","_col7","_col8","_col9","_col10","_col14","_col16"] + Filter Operator [FIL_30] (rows=218403 width=44) + predicate:((_col20 and _col9) or (_col21 and _col10) or (_col22 and _col11)) + Merge Join Operator [MERGEJOIN_120] (rows=291204 width=44) + Conds:RS_27._col4=RS_140._col0(Inner),Output:["_col2","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col17","_col18","_col20","_col21","_col22"] <-Map 13 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_143] + SHUFFLE [RS_140] PartitionCols:_col0 - Select Operator [SEL_142] (rows=3529412 width=187) - Output:["_col0","_col1"] - Filter Operator [FIL_141] (rows=3529412 width=187) + Select Operator [SEL_139] (rows=3529412 width=16) + Output:["_col0","_col1","_col2","_col3"] + Filter Operator [FIL_138] (rows=3529412 width=187) predicate:((ca_country = 'United States') and (ca_state) IN ('KY', 'GA', 'NM', 'MT', 'OR', 'IN', 'WI', 'MO', 'WV') and ca_address_sk is not null) TableScan [TS_12] (rows=40000000 width=187) default@customer_address,customer_address,Tbl:COMPLETE,Col:COMPLETE,Output:["ca_address_sk","ca_state","ca_country"] <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_27] PartitionCols:_col4 - Merge Join Operator [MERGEJOIN_119] (rows=3300311 width=145) - Conds:RS_24._col3=RS_135._col0(Inner),Output:["_col2","_col4","_col6","_col7","_col8","_col9","_col10","_col14"] + Merge Join Operator [MERGEJOIN_119] (rows=3300311 width=104) + Conds:RS_24._col3=RS_132._col0(Inner),Output:["_col2","_col4","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col17","_col18"] <-Map 11 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_135] + SHUFFLE [RS_132] PartitionCols:_col0 - Select Operator [SEL_134] (rows=1309 width=8) - Output:["_col0","_col1"] - Filter Operator [FIL_133] (rows=1309 width=8) + Select Operator [SEL_131] (rows=1309 width=12) + Output:["_col0","_col1","_col2"] + Filter Operator [FIL_130] (rows=1309 width=8) predicate:((hd_dep_count) IN (3, 1) and hd_demo_sk is not null) TableScan [TS_9] (rows=7200 width=8) default@household_demographics,household_demographics,Tbl:COMPLETE,Col:COMPLETE,Output:["hd_demo_sk","hd_dep_count"] <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_24] PartitionCols:_col3 - Merge Join Operator [MERGEJOIN_118] (rows=18152968 width=405) - Conds:RS_21._col1=RS_127._col0(Inner),Output:["_col2","_col3","_col4","_col6","_col7","_col8","_col9","_col10"] - <-Map 9 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_127] + Merge Join Operator [MERGEJOIN_118] (rows=18152968 width=233) + Conds:RS_21._col5=RS_159._col0(Inner),Output:["_col2","_col3","_col4","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14"] + <-Map 10 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_159] PartitionCols:_col0 - Select Operator [SEL_126] (rows=652 width=8) + Select Operator [SEL_158] (rows=1704 width=4) Output:["_col0"] - Filter Operator [FIL_125] (rows=652 width=8) - predicate:((d_year = 2001) and d_date_sk is not null) - TableScan [TS_6] (rows=73049 width=8) - default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year"] + Filter Operator [FIL_157] (rows=1704 width=4) + predicate:s_store_sk is not null + TableScan [TS_6] (rows=1704 width=4) + default@store,store,Tbl:COMPLETE,Col:COMPLETE,Output:["s_store_sk"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_21] - PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_117] (rows=50840141 width=446) - Conds:RS_124._col0=RS_159._col4(Inner),Output:["_col1","_col2","_col3","_col4","_col6","_col7","_col8","_col9","_col10"] + PartitionCols:_col5 + Merge Join Operator [MERGEJOIN_117] (rows=18152968 width=237) + Conds:RS_124._col0=RS_156._col0(Inner),Output:["_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14"] <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_124] + PARTITION_ONLY_SHUFFLE [RS_124] PartitionCols:_col0 - Select Operator [SEL_123] (rows=1704 width=4) + Select Operator [SEL_123] (rows=652 width=4) Output:["_col0"] - Filter Operator [FIL_122] (rows=1704 width=4) - predicate:s_store_sk is not null - TableScan [TS_0] (rows=1704 width=4) - default@store,store,Tbl:COMPLETE,Col:COMPLETE,Output:["s_store_sk"] - <-Map 8 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_159] - PartitionCols:_col4 - Select Operator [SEL_158] (rows=50840141 width=450) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9"] - Filter Operator [FIL_157] (rows=50840141 width=450) - predicate:((ss_addr_sk BETWEEN DynamicValue(RS_28_customer_address_ca_address_sk_min) AND DynamicValue(RS_28_customer_address_ca_address_sk_max) and in_bloom_filter(ss_addr_sk, DynamicValue(RS_28_customer_address_ca_address_sk_bloom_filter))) and (ss_cdemo_sk BETWEEN DynamicValue(RS_32_customer_demographics_cd_demo_sk_min) AND DynamicValue(RS_32_customer_demographics_cd_demo_sk_max) and in_bloom_filter(ss_cdemo_sk, DynamicValue(RS_32_customer_demographics_cd_demo_sk_bloom_filter))) and (ss_hdemo_sk BETWEEN DynamicValue(RS_25_household_demographics_hd_demo_sk_min) AND DynamicValue(RS_25_household_demographics_hd_demo_sk_max) and in_bloom_filter(ss_hdemo_sk, DynamicValue(RS_25_household_demographics_hd_demo_sk_bloom_filter))) and (ss_net_profit BETWEEN 100 AND 200 or ss_net_profit BETWEEN 150 AND 300 or ss_net_profit BETWEEN 50 AND 250) and (ss_sales_price BETWEEN 100 AND 150 or ss_sales_price BETWEEN 50 AND 100 or ss_sales_price BETWEEN 150 AND 200) and (ss_sold_date_sk BETWEEN DynamicValue(RS_22_date_dim_d_date_sk_min) AND DynamicValue(RS_22_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_22_date_dim_d_date_sk_bloom_filter))) and ss_addr_sk is not null and ss_cdemo_sk is not null and ss_hdemo_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null) + Filter Operator [FIL_122] (rows=652 width=8) + predicate:((d_year = 2001) and d_date_sk is not null) + TableScan [TS_0] (rows=73049 width=8) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year"] + <-Map 9 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_156] + PartitionCols:_col0 + Select Operator [SEL_155] (rows=50840141 width=260) + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13"] + Filter Operator [FIL_154] (rows=50840141 width=450) + predicate:((ss_addr_sk BETWEEN DynamicValue(RS_28_customer_address_ca_address_sk_min) AND DynamicValue(RS_28_customer_address_ca_address_sk_max) and in_bloom_filter(ss_addr_sk, DynamicValue(RS_28_customer_address_ca_address_sk_bloom_filter))) and (ss_cdemo_sk BETWEEN DynamicValue(RS_32_customer_demographics_cd_demo_sk_min) AND DynamicValue(RS_32_customer_demographics_cd_demo_sk_max) and in_bloom_filter(ss_cdemo_sk, DynamicValue(RS_32_customer_demographics_cd_demo_sk_bloom_filter))) and (ss_hdemo_sk BETWEEN DynamicValue(RS_25_household_demographics_hd_demo_sk_min) AND DynamicValue(RS_25_household_demographics_hd_demo_sk_max) and in_bloom_filter(ss_hdemo_sk, DynamicValue(RS_25_household_demographics_hd_demo_sk_bloom_filter))) and (ss_net_profit BETWEEN 100 AND 200 or ss_net_profit BETWEEN 150 AND 300 or ss_net_profit BETWEEN 50 AND 250) and (ss_sales_price BETWEEN 100 AND 150 or ss_sales_price BETWEEN 50 AND 100 or ss_sales_price BETWEEN 150 AND 200) and (ss_sold_date_sk BETWEEN DynamicValue(RS_18_date_dim_d_date_sk_min) AND DynamicValue(RS_18_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_18_date_dim_d_date_sk_bloom_filter))) and ss_addr_sk is not null and ss_cdemo_sk is not null and ss_hdemo_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null) TableScan [TS_3] (rows=575995635 width=450) default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_cdemo_sk","ss_hdemo_sk","ss_addr_sk","ss_store_sk","ss_quantity","ss_sales_price","ss_ext_sales_price","ss_ext_wholesale_cost","ss_net_profit"] - <-Reducer 10 [BROADCAST_EDGE] vectorized - BROADCAST [RS_132] - Group By Operator [GBY_131] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 9 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_130] - Group By Operator [GBY_129] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_128] (rows=652 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_126] <-Reducer 12 [BROADCAST_EDGE] vectorized - BROADCAST [RS_140] - Group By Operator [GBY_139] (rows=1 width=12) + BROADCAST [RS_137] + Group By Operator [GBY_136] (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_138] - Group By Operator [GBY_137] (rows=1 width=12) + SHUFFLE [RS_135] + Group By Operator [GBY_134] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_136] (rows=1309 width=4) + Select Operator [SEL_133] (rows=1309 width=4) Output:["_col0"] - Please refer to the previous Select Operator [SEL_134] + Please refer to the previous Select Operator [SEL_131] <-Reducer 14 [BROADCAST_EDGE] vectorized - BROADCAST [RS_148] - Group By Operator [GBY_147] (rows=1 width=12) + BROADCAST [RS_145] + Group By Operator [GBY_144] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=3529412)"] <-Map 13 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_146] - Group By Operator [GBY_145] (rows=1 width=12) + SHUFFLE [RS_143] + Group By Operator [GBY_142] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=3529412)"] - Select Operator [SEL_144] (rows=3529412 width=4) + Select Operator [SEL_141] (rows=3529412 width=4) Output:["_col0"] - Please refer to the previous Select Operator [SEL_142] + Please refer to the previous Select Operator [SEL_139] <-Reducer 16 [BROADCAST_EDGE] vectorized - BROADCAST [RS_156] - Group By Operator [GBY_155] (rows=1 width=12) + BROADCAST [RS_153] + Group By Operator [GBY_152] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Map 15 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_154] - Group By Operator [GBY_153] (rows=1 width=12) + SHUFFLE [RS_151] + Group By Operator [GBY_150] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_149] (rows=265971 width=4) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_147] + <-Reducer 8 [BROADCAST_EDGE] vectorized + BROADCAST [RS_129] + Group By Operator [GBY_128] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 1 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_127] + Group By Operator [GBY_126] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_152] (rows=265971 width=4) + Select Operator [SEL_125] (rows=652 width=4) Output:["_col0"] - Please refer to the previous Select Operator [SEL_150] + Please refer to the previous Select Operator [SEL_123] diff --git ql/src/test/results/clientpositive/perf/tez/query14.q.out ql/src/test/results/clientpositive/perf/tez/query14.q.out index c078c271ecc..aa0d8cce9ea 100644 --- ql/src/test/results/clientpositive/perf/tez/query14.q.out +++ ql/src/test/results/clientpositive/perf/tez/query14.q.out @@ -382,7 +382,7 @@ Stage-0 <-Map 102 [SIMPLE_EDGE] vectorized SHUFFLE [RS_1629] PartitionCols:_col0 - Select Operator [SEL_1618] (rows=1957 width=8) + Select Operator [SEL_1618] (rows=1957 width=4) Output:["_col0"] Filter Operator [FIL_1617] (rows=1957 width=8) predicate:(d_date_sk is not null and d_year BETWEEN 1999 AND 2001) @@ -421,7 +421,7 @@ Stage-0 <-Map 24 [SIMPLE_EDGE] vectorized SHUFFLE [RS_1787] PartitionCols:_col0 - Select Operator [SEL_1782] (rows=1957 width=8) + Select Operator [SEL_1782] (rows=1957 width=4) Output:["_col0"] Filter Operator [FIL_1781] (rows=1957 width=8) predicate:(d_date_sk is not null and d_year BETWEEN 1998 AND 2000) @@ -460,7 +460,7 @@ Stage-0 <-Map 40 [SIMPLE_EDGE] vectorized SHUFFLE [RS_1815] PartitionCols:_col0 - Select Operator [SEL_1810] (rows=1957 width=8) + Select Operator [SEL_1810] (rows=1957 width=4) Output:["_col0"] Filter Operator [FIL_1809] (rows=1957 width=8) predicate:(d_date_sk is not null and d_year BETWEEN 1998 AND 2000) @@ -607,7 +607,7 @@ Stage-0 Select Operator [SEL_372] (rows=1 width=128) Output:["_col0","_col1","_col2","_col3"] Merge Join Operator [MERGEJOIN_1444] (rows=1 width=128) - Conds:RS_369._col1=RS_1743._col0(Inner),Output:["_col2","_col3","_col8","_col9","_col10"] + Conds:RS_369._col1=RS_1743._col0(Inner),Output:["_col2","_col3","_col6","_col7","_col8"] <-Reducer 82 [ONE_TO_ONE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_1743] PartitionCols:_col0 @@ -650,9 +650,9 @@ Stage-0 SHUFFLE [RS_304] PartitionCols:_col0, _col1, _col2 Group By Operator [GBY_303] (rows=121728 width=19) - Output:["_col0","_col1","_col2","_col3"],aggregations:["count()"],keys:_col5, _col6, _col7 + Output:["_col0","_col1","_col2","_col3"],aggregations:["count()"],keys:_col4, _col5, _col6 Merge Join Operator [MERGEJOIN_1422] (rows=14628613 width=11) - Conds:RS_299._col1=RS_1699._col0(Inner),Output:["_col5","_col6","_col7"] + Conds:RS_299._col1=RS_1699._col0(Inner),Output:["_col4","_col5","_col6"] <-Map 69 [SIMPLE_EDGE] vectorized SHUFFLE [RS_1699] PartitionCols:_col0 @@ -701,9 +701,9 @@ Stage-0 SHUFFLE [RS_324] PartitionCols:_col0, _col1, _col2 Group By Operator [GBY_323] (rows=121728 width=19) - Output:["_col0","_col1","_col2","_col3"],aggregations:["count()"],keys:_col5, _col6, _col7 + Output:["_col0","_col1","_col2","_col3"],aggregations:["count()"],keys:_col4, _col5, _col6 Merge Join Operator [MERGEJOIN_1424] (rows=7620440 width=11) - Conds:RS_319._col1=RS_1700._col0(Inner),Output:["_col5","_col6","_col7"] + Conds:RS_319._col1=RS_1700._col0(Inner),Output:["_col4","_col5","_col6"] <-Map 69 [SIMPLE_EDGE] vectorized SHUFFLE [RS_1700] PartitionCols:_col0 @@ -752,9 +752,9 @@ Stage-0 SHUFFLE [RS_345] PartitionCols:_col0, _col1, _col2 Group By Operator [GBY_344] (rows=121728 width=19) - Output:["_col0","_col1","_col2","_col3"],aggregations:["count()"],keys:_col5, _col6, _col7 + Output:["_col0","_col1","_col2","_col3"],aggregations:["count()"],keys:_col4, _col5, _col6 Merge Join Operator [MERGEJOIN_1426] (rows=3828623 width=11) - Conds:RS_340._col1=RS_1701._col0(Inner),Output:["_col5","_col6","_col7"] + Conds:RS_340._col1=RS_1701._col0(Inner),Output:["_col4","_col5","_col6"] <-Map 69 [SIMPLE_EDGE] vectorized SHUFFLE [RS_1701] PartitionCols:_col0 @@ -796,7 +796,7 @@ Stage-0 FORWARD [RS_369] PartitionCols:_col1 Merge Join Operator [MERGEJOIN_1420] (rows=7790806 width=110) - Conds:RS_366._col1=RS_1702._col0(Inner),Output:["_col1","_col2","_col3","_col8","_col9","_col10"] + Conds:RS_366._col1=RS_1702._col0(Inner),Output:["_col1","_col2","_col3","_col6","_col7","_col8"] <-Map 69 [SIMPLE_EDGE] vectorized SHUFFLE [RS_1702] PartitionCols:_col0 @@ -813,7 +813,7 @@ Stage-0 <-Map 57 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_1663] PartitionCols:_col0 - Select Operator [SEL_1660] (rows=50 width=12) + Select Operator [SEL_1660] (rows=50 width=4) Output:["_col0"] Filter Operator [FIL_1659] (rows=50 width=12) predicate:((d_moy = 11) and (d_year = 2000) and d_date_sk is not null) @@ -1005,7 +1005,7 @@ Stage-0 Select Operator [SEL_566] (rows=1 width=128) Output:["_col0","_col1","_col2","_col3"] Merge Join Operator [MERGEJOIN_1445] (rows=1 width=128) - Conds:RS_563._col1=RS_1770._col0(Inner),Output:["_col2","_col3","_col8","_col9","_col10"] + Conds:RS_563._col1=RS_1770._col0(Inner),Output:["_col2","_col3","_col6","_col7","_col8"] <-Reducer 92 [ONE_TO_ONE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_1770] PartitionCols:_col0 @@ -1073,7 +1073,7 @@ Stage-0 FORWARD [RS_563] PartitionCols:_col1 Merge Join Operator [MERGEJOIN_1435] (rows=3942084 width=130) - Conds:RS_560._col1=RS_1704._col0(Inner),Output:["_col1","_col2","_col3","_col8","_col9","_col10"] + Conds:RS_560._col1=RS_1704._col0(Inner),Output:["_col1","_col2","_col3","_col6","_col7","_col8"] <-Map 69 [SIMPLE_EDGE] vectorized SHUFFLE [RS_1704] PartitionCols:_col0 @@ -1277,7 +1277,7 @@ Stage-0 Select Operator [SEL_179] (rows=1 width=128) Output:["_col0","_col1","_col2","_col3"] Merge Join Operator [MERGEJOIN_1443] (rows=1 width=128) - Conds:RS_176._col1=RS_1710._col0(Inner),Output:["_col2","_col3","_col8","_col9","_col10"] + Conds:RS_176._col1=RS_1710._col0(Inner),Output:["_col2","_col3","_col6","_col7","_col8"] <-Reducer 71 [ONE_TO_ONE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_1710] PartitionCols:_col0 @@ -1319,9 +1319,9 @@ Stage-0 SHUFFLE [RS_111] PartitionCols:_col0, _col1, _col2 Group By Operator [GBY_110] (rows=121728 width=19) - Output:["_col0","_col1","_col2","_col3"],aggregations:["count()"],keys:_col5, _col6, _col7 + Output:["_col0","_col1","_col2","_col3"],aggregations:["count()"],keys:_col4, _col5, _col6 Merge Join Operator [MERGEJOIN_1407] (rows=14628613 width=11) - Conds:RS_106._col1=RS_1694._col0(Inner),Output:["_col5","_col6","_col7"] + Conds:RS_106._col1=RS_1694._col0(Inner),Output:["_col4","_col5","_col6"] <-Map 69 [SIMPLE_EDGE] vectorized SHUFFLE [RS_1694] PartitionCols:_col0 @@ -1341,9 +1341,9 @@ Stage-0 SHUFFLE [RS_131] PartitionCols:_col0, _col1, _col2 Group By Operator [GBY_130] (rows=121728 width=19) - Output:["_col0","_col1","_col2","_col3"],aggregations:["count()"],keys:_col5, _col6, _col7 + Output:["_col0","_col1","_col2","_col3"],aggregations:["count()"],keys:_col4, _col5, _col6 Merge Join Operator [MERGEJOIN_1409] (rows=7620440 width=11) - Conds:RS_126._col1=RS_1695._col0(Inner),Output:["_col5","_col6","_col7"] + Conds:RS_126._col1=RS_1695._col0(Inner),Output:["_col4","_col5","_col6"] <-Map 69 [SIMPLE_EDGE] vectorized SHUFFLE [RS_1695] PartitionCols:_col0 @@ -1363,9 +1363,9 @@ Stage-0 SHUFFLE [RS_152] PartitionCols:_col0, _col1, _col2 Group By Operator [GBY_151] (rows=121728 width=19) - Output:["_col0","_col1","_col2","_col3"],aggregations:["count()"],keys:_col5, _col6, _col7 + Output:["_col0","_col1","_col2","_col3"],aggregations:["count()"],keys:_col4, _col5, _col6 Merge Join Operator [MERGEJOIN_1411] (rows=3828623 width=11) - Conds:RS_147._col1=RS_1696._col0(Inner),Output:["_col5","_col6","_col7"] + Conds:RS_147._col1=RS_1696._col0(Inner),Output:["_col4","_col5","_col6"] <-Map 69 [SIMPLE_EDGE] vectorized SHUFFLE [RS_1696] PartitionCols:_col0 @@ -1378,7 +1378,7 @@ Stage-0 FORWARD [RS_176] PartitionCols:_col1 Merge Join Operator [MERGEJOIN_1405] (rows=15062131 width=15) - Conds:RS_173._col1=RS_1697._col0(Inner),Output:["_col1","_col2","_col3","_col8","_col9","_col10"] + Conds:RS_173._col1=RS_1697._col0(Inner),Output:["_col1","_col2","_col3","_col6","_col7","_col8"] <-Map 69 [SIMPLE_EDGE] vectorized SHUFFLE [RS_1697] PartitionCols:_col0 diff --git ql/src/test/results/clientpositive/perf/tez/query15.q.out ql/src/test/results/clientpositive/perf/tez/query15.q.out index 565f1019ea6..c3c08a1d6bd 100644 --- ql/src/test/results/clientpositive/perf/tez/query15.q.out +++ ql/src/test/results/clientpositive/perf/tez/query15.q.out @@ -74,21 +74,21 @@ Stage-0 <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_25] PartitionCols:_col0 - Group By Operator [GBY_24] (rows=56210 width=201) - Output:["_col0","_col1"],aggregations:["sum(_col7)"],keys:_col4 - Top N Key Operator [TNK_44] (rows=20154874 width=279) - keys:_col4,sort order:+,top n:100 - Select Operator [SEL_23] (rows=20154874 width=279) - Output:["_col4","_col7"] - Filter Operator [FIL_22] (rows=20154874 width=279) - predicate:((_col3) IN ('CA', 'WA', 'GA') or (_col7 > 500) or (substr(_col4, 1, 5)) IN ('85669', '86197', '88274', '83405', '86475', '85392', '85460', '80348', '81792')) - Merge Join Operator [MERGEJOIN_77] (rows=20154874 width=279) - Conds:RS_19._col0=RS_20._col1(Inner),Output:["_col3","_col4","_col7"] + Group By Operator [GBY_24] (rows=43435 width=201) + Output:["_col0","_col1"],aggregations:["sum(_col8)"],keys:_col3 + Top N Key Operator [TNK_44] (rows=20154874 width=205) + keys:_col3,sort order:+,top n:100 + Select Operator [SEL_23] (rows=20154874 width=205) + Output:["_col3","_col8"] + Filter Operator [FIL_22] (rows=20154874 width=205) + predicate:(_col4 or _col5 or _col9) + Merge Join Operator [MERGEJOIN_77] (rows=20154874 width=205) + Conds:RS_19._col0=RS_20._col1(Inner),Output:["_col3","_col4","_col5","_col8","_col9"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_19] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_75] (rows=80000000 width=179) - Conds:RS_80._col1=RS_83._col0(Inner),Output:["_col0","_col3","_col4"] + Merge Join Operator [MERGEJOIN_75] (rows=80000000 width=101) + Conds:RS_80._col1=RS_83._col0(Inner),Output:["_col0","_col3","_col4","_col5"] <-Map 1 [SIMPLE_EDGE] vectorized SHUFFLE [RS_80] PartitionCols:_col1 @@ -101,8 +101,8 @@ Stage-0 <-Map 6 [SIMPLE_EDGE] vectorized SHUFFLE [RS_83] PartitionCols:_col0 - Select Operator [SEL_82] (rows=40000000 width=179) - Output:["_col0","_col1","_col2"] + Select Operator [SEL_82] (rows=40000000 width=101) + Output:["_col0","_col1","_col2","_col3"] Filter Operator [FIL_81] (rows=40000000 width=179) predicate:ca_address_sk is not null TableScan [TS_3] (rows=40000000 width=179) @@ -110,12 +110,12 @@ Stage-0 <-Reducer 8 [SIMPLE_EDGE] SHUFFLE [RS_20] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_76] (rows=20154874 width=107) - Conds:RS_94._col0=RS_86._col0(Inner),Output:["_col1","_col2"] + Merge Join Operator [MERGEJOIN_76] (rows=20154874 width=111) + Conds:RS_94._col0=RS_86._col0(Inner),Output:["_col1","_col2","_col3"] <-Map 9 [SIMPLE_EDGE] vectorized SHUFFLE [RS_86] PartitionCols:_col0 - Select Operator [SEL_85] (rows=130 width=12) + Select Operator [SEL_85] (rows=130 width=4) Output:["_col0"] Filter Operator [FIL_84] (rows=130 width=12) predicate:((d_qoy = 2) and (d_year = 2000) and d_date_sk is not null) @@ -124,8 +124,8 @@ Stage-0 <-Map 7 [SIMPLE_EDGE] vectorized SHUFFLE [RS_94] PartitionCols:_col0 - Select Operator [SEL_93] (rows=285117831 width=119) - Output:["_col0","_col1","_col2"] + Select Operator [SEL_93] (rows=285117831 width=123) + Output:["_col0","_col1","_col2","_col3"] Filter Operator [FIL_92] (rows=285117831 width=119) predicate:((cs_sold_date_sk BETWEEN DynamicValue(RS_13_date_dim_d_date_sk_min) AND DynamicValue(RS_13_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_13_date_dim_d_date_sk_bloom_filter))) and cs_bill_customer_sk is not null and cs_sold_date_sk is not null) TableScan [TS_6] (rows=287989836 width=119) diff --git ql/src/test/results/clientpositive/perf/tez/query17.q.out ql/src/test/results/clientpositive/perf/tez/query17.q.out index fa576c3479d..d3002931604 100644 --- ql/src/test/results/clientpositive/perf/tez/query17.q.out +++ ql/src/test/results/clientpositive/perf/tez/query17.q.out @@ -147,7 +147,7 @@ Stage-0 Select Operator [SEL_47] (rows=4815969644 width=381) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11"] Merge Join Operator [MERGEJOIN_213] (rows=4815969644 width=381) - Conds:RS_44._col3=RS_257._col0(Inner),Output:["_col5","_col9","_col10","_col14","_col21","_col25"] + Conds:RS_44._col3=RS_257._col0(Inner),Output:["_col5","_col8","_col9","_col13","_col19","_col22"] <-Map 21 [SIMPLE_EDGE] vectorized SHUFFLE [RS_257] PartitionCols:_col0 @@ -161,12 +161,12 @@ Stage-0 SHUFFLE [RS_44] PartitionCols:_col3 Merge Join Operator [MERGEJOIN_212] (rows=4815969644 width=299) - Conds:RS_41._col1, _col2, _col4=RS_42._col7, _col8, _col9(Inner),Output:["_col3","_col5","_col9","_col10","_col14","_col21"] + Conds:RS_41._col1, _col2, _col4=RS_42._col6, _col7, _col8(Inner),Output:["_col3","_col5","_col8","_col9","_col13","_col19"] <-Reducer 11 [SIMPLE_EDGE] SHUFFLE [RS_42] - PartitionCols:_col7, _col8, _col9 + PartitionCols:_col6, _col7, _col8 Merge Join Operator [MERGEJOIN_211] (rows=540026342 width=19) - Conds:RS_28._col2, _col1=RS_29._col1, _col2(Inner),Output:["_col3","_col7","_col8","_col9","_col10"] + Conds:RS_28._col2, _col1=RS_29._col1, _col2(Inner),Output:["_col3","_col6","_col7","_col8","_col9"] <-Reducer 10 [SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_28] PartitionCols:_col2, _col1 @@ -175,7 +175,7 @@ Stage-0 <-Map 8 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_222] PartitionCols:_col0 - Select Operator [SEL_218] (rows=3652 width=94) + Select Operator [SEL_218] (rows=3652 width=4) Output:["_col0"] Filter Operator [FIL_215] (rows=3652 width=94) predicate:((d_quarter_name) IN ('2000Q1', '2000Q2', '2000Q3') and d_date_sk is not null) @@ -205,7 +205,7 @@ Stage-0 <-Map 8 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_224] PartitionCols:_col0 - Select Operator [SEL_219] (rows=3652 width=94) + Select Operator [SEL_219] (rows=3652 width=4) Output:["_col0"] Filter Operator [FIL_216] (rows=3652 width=94) predicate:((d_quarter_name) IN ('2000Q1', '2000Q2', '2000Q3') and d_date_sk is not null) @@ -249,7 +249,7 @@ Stage-0 SHUFFLE [RS_41] PartitionCols:_col1, _col2, _col4 Merge Join Operator [MERGEJOIN_208] (rows=27749405 width=294) - Conds:RS_38._col1=RS_254._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col9","_col10"] + Conds:RS_38._col1=RS_254._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col8","_col9"] <-Map 18 [SIMPLE_EDGE] vectorized SHUFFLE [RS_254] PartitionCols:_col0 @@ -267,7 +267,7 @@ Stage-0 <-Map 8 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_220] PartitionCols:_col0 - Select Operator [SEL_217] (rows=101 width=94) + Select Operator [SEL_217] (rows=101 width=4) Output:["_col0"] Filter Operator [FIL_214] (rows=101 width=94) predicate:((d_quarter_name = '2000Q1') and d_date_sk is not null) diff --git ql/src/test/results/clientpositive/perf/tez/query18.q.out ql/src/test/results/clientpositive/perf/tez/query18.q.out index 58fb7a79f52..f51e75b64e4 100644 --- ql/src/test/results/clientpositive/perf/tez/query18.q.out +++ ql/src/test/results/clientpositive/perf/tez/query18.q.out @@ -99,147 +99,145 @@ Stage-0 limit:100 Stage-1 Reducer 6 vectorized - File Output Operator [FS_182] - Limit [LIM_181] (rows=100 width=1165) + File Output Operator [FS_181] + Limit [LIM_180] (rows=100 width=1165) Number of rows:100 - Select Operator [SEL_180] (rows=10969055 width=1165) + Select Operator [SEL_179] (rows=10969055 width=1165) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10"] <-Reducer 5 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_179] - Select Operator [SEL_178] (rows=10969055 width=1165) + SHUFFLE [RS_178] + Select Operator [SEL_177] (rows=10969055 width=1165) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10"] - Group By Operator [GBY_177] (rows=10969055 width=1229) + Group By Operator [GBY_176] (rows=10969055 width=1229) Output:["_col0","_col1","_col2","_col3","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18"],aggregations:["sum(VALUE._col0)","count(VALUE._col1)","sum(VALUE._col2)","count(VALUE._col3)","sum(VALUE._col4)","count(VALUE._col5)","sum(VALUE._col6)","count(VALUE._col7)","sum(VALUE._col8)","count(VALUE._col9)","sum(VALUE._col10)","count(VALUE._col11)","sum(VALUE._col12)","count(VALUE._col13)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4 <-Reducer 4 [SIMPLE_EDGE] - SHUFFLE [RS_43] + SHUFFLE [RS_42] PartitionCols:_col0, _col1, _col2, _col3, _col4 - Group By Operator [GBY_42] (rows=10969055 width=1229) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18"],aggregations:["sum(_col4)","count(_col4)","sum(_col5)","count(_col5)","sum(_col6)","count(_col6)","sum(_col7)","count(_col7)","sum(_col8)","count(_col8)","sum(_col9)","count(_col9)","sum(_col10)","count(_col10)"],keys:_col0, _col1, _col2, _col3, 0L - Select Operator [SEL_40] (rows=2193811 width=618) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10"] - Merge Join Operator [MERGEJOIN_143] (rows=2193811 width=618) - Conds:RS_37._col0=RS_38._col3(Inner),Output:["_col4","_col6","_col7","_col8","_col11","_col16","_col17","_col18","_col19","_col20","_col26"] - <-Reducer 3 [SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_37] - PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_139] (rows=4959744 width=287) - Conds:RS_34._col1=RS_152._col0(Inner),Output:["_col0","_col4","_col6","_col7","_col8"] - <-Map 9 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_152] + Group By Operator [GBY_41] (rows=10969055 width=1229) + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18"],aggregations:["sum(_col15)","count(_col15)","sum(_col16)","count(_col16)","sum(_col17)","count(_col17)","sum(_col18)","count(_col18)","sum(_col19)","count(_col19)","sum(_col3)","count(_col3)","sum(_col22)","count(_col22)"],keys:_col5, _col6, _col7, _col10, 0L + Merge Join Operator [MERGEJOIN_142] (rows=2193811 width=811) + Conds:RS_37._col0=RS_38._col3(Inner),Output:["_col3","_col5","_col6","_col7","_col10","_col15","_col16","_col17","_col18","_col19","_col22"] + <-Reducer 3 [SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_37] + PartitionCols:_col0 + Merge Join Operator [MERGEJOIN_138] (rows=4959744 width=368) + Conds:RS_34._col1=RS_151._col0(Inner),Output:["_col0","_col3","_col5","_col6","_col7"] + <-Map 9 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_151] + PartitionCols:_col0 + Select Operator [SEL_150] (rows=1861800 width=4) + Output:["_col0"] + Filter Operator [FIL_149] (rows=1861800 width=4) + predicate:cd_demo_sk is not null + TableScan [TS_6] (rows=1861800 width=4) + default@customer_demographics,cd2,Tbl:COMPLETE,Col:COMPLETE,Output:["cd_demo_sk"] + <-Reducer 2 [SIMPLE_EDGE] + SHUFFLE [RS_34] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_137] (rows=4890586 width=371) + Conds:RS_145._col2=RS_148._col0(Inner),Output:["_col0","_col1","_col3","_col5","_col6","_col7"] + <-Map 1 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_145] + PartitionCols:_col2 + Select Operator [SEL_144] (rows=35631408 width=119) + Output:["_col0","_col1","_col2","_col3"] + Filter Operator [FIL_143] (rows=35631408 width=19) + predicate:((c_birth_month) IN (9, 5, 12, 4, 1, 10) and c_current_addr_sk is not null and c_current_cdemo_sk is not null and c_customer_sk is not null) + TableScan [TS_0] (rows=80000000 width=19) + default@customer,customer,Tbl:COMPLETE,Col:COMPLETE,Output:["c_customer_sk","c_current_cdemo_sk","c_current_addr_sk","c_birth_month","c_birth_year"] + <-Map 8 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_148] + PartitionCols:_col0 + Select Operator [SEL_147] (rows=5490196 width=285) + Output:["_col0","_col1","_col2","_col3"] + Filter Operator [FIL_146] (rows=5490196 width=285) + predicate:((ca_state) IN ('ND', 'WI', 'AL', 'NC', 'OK', 'MS', 'TN') and ca_address_sk is not null) + TableScan [TS_3] (rows=40000000 width=285) + default@customer_address,customer_address,Tbl:COMPLETE,Col:COMPLETE,Output:["ca_address_sk","ca_county","ca_state","ca_country"] + <-Reducer 13 [SIMPLE_EDGE] + SHUFFLE [RS_38] + PartitionCols:_col3 + Select Operator [SEL_30] (rows=15983481 width=735) + Output:["_col1","_col3","_col6","_col7","_col8","_col9","_col10","_col13"] + Merge Join Operator [MERGEJOIN_141] (rows=15983481 width=735) + Conds:RS_27._col3=RS_175._col0(Inner),Output:["_col1","_col4","_col5","_col6","_col7","_col8","_col11","_col13"] + <-Map 18 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_175] PartitionCols:_col0 - Select Operator [SEL_151] (rows=1861800 width=4) - Output:["_col0"] - Filter Operator [FIL_150] (rows=1861800 width=4) - predicate:cd_demo_sk is not null - TableScan [TS_6] (rows=1861800 width=4) - default@customer_demographics,cd2,Tbl:COMPLETE,Col:COMPLETE,Output:["cd_demo_sk"] - <-Reducer 2 [SIMPLE_EDGE] - SHUFFLE [RS_34] - PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_138] (rows=4890586 width=290) - Conds:RS_146._col2=RS_149._col0(Inner),Output:["_col0","_col1","_col4","_col6","_col7","_col8"] - <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_146] - PartitionCols:_col2 - Select Operator [SEL_145] (rows=35631408 width=19) - Output:["_col0","_col1","_col2","_col4"] - Filter Operator [FIL_144] (rows=35631408 width=19) - predicate:((c_birth_month) IN (9, 5, 12, 4, 1, 10) and c_current_addr_sk is not null and c_current_cdemo_sk is not null and c_customer_sk is not null) - TableScan [TS_0] (rows=80000000 width=19) - default@customer,customer,Tbl:COMPLETE,Col:COMPLETE,Output:["c_customer_sk","c_current_cdemo_sk","c_current_addr_sk","c_birth_month","c_birth_year"] - <-Map 8 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_149] + Select Operator [SEL_174] (rows=462000 width=104) + Output:["_col0","_col1"] + Filter Operator [FIL_173] (rows=462000 width=104) + predicate:i_item_sk is not null + TableScan [TS_18] (rows=462000 width=104) + default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_item_id"] + <-Reducer 12 [SIMPLE_EDGE] + SHUFFLE [RS_27] + PartitionCols:_col3 + Merge Join Operator [MERGEJOIN_140] (rows=15983481 width=639) + Conds:RS_24._col2=RS_162._col0(Inner),Output:["_col1","_col3","_col4","_col5","_col6","_col7","_col8","_col11"] + <-Map 16 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_162] PartitionCols:_col0 - Select Operator [SEL_148] (rows=5490196 width=285) - Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_147] (rows=5490196 width=285) - predicate:((ca_state) IN ('ND', 'WI', 'AL', 'NC', 'OK', 'MS', 'TN') and ca_address_sk is not null) - TableScan [TS_3] (rows=40000000 width=285) - default@customer_address,customer_address,Tbl:COMPLETE,Col:COMPLETE,Output:["ca_address_sk","ca_county","ca_state","ca_country"] - <-Reducer 13 [SIMPLE_EDGE] - SHUFFLE [RS_38] - PartitionCols:_col3 - Select Operator [SEL_30] (rows=15983481 width=529) - Output:["_col1","_col3","_col6","_col7","_col8","_col9","_col10","_col16"] - Merge Join Operator [MERGEJOIN_142] (rows=15983481 width=529) - Conds:RS_27._col3=RS_176._col0(Inner),Output:["_col1","_col4","_col5","_col6","_col7","_col8","_col14","_col16"] - <-Map 18 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_176] - PartitionCols:_col0 - Select Operator [SEL_175] (rows=462000 width=104) - Output:["_col0","_col1"] - Filter Operator [FIL_174] (rows=462000 width=104) - predicate:i_item_sk is not null - TableScan [TS_18] (rows=462000 width=104) - default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_item_id"] - <-Reducer 12 [SIMPLE_EDGE] - SHUFFLE [RS_27] - PartitionCols:_col3 - Merge Join Operator [MERGEJOIN_141] (rows=15983481 width=433) - Conds:RS_24._col2=RS_163._col0(Inner),Output:["_col1","_col3","_col4","_col5","_col6","_col7","_col8","_col14"] - <-Map 16 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_163] - PartitionCols:_col0 - Select Operator [SEL_162] (rows=103433 width=184) - Output:["_col0","_col3"] - Filter Operator [FIL_161] (rows=103433 width=187) - predicate:((cd_education_status = 'College') and (cd_gender = 'M') and cd_demo_sk is not null) - TableScan [TS_15] (rows=1861800 width=187) - default@customer_demographics,cd1,Tbl:COMPLETE,Col:COMPLETE,Output:["cd_demo_sk","cd_gender","cd_education_status","cd_dep_count"] - <-Reducer 11 [SIMPLE_EDGE] - SHUFFLE [RS_24] - PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_140] (rows=100578970 width=459) - Conds:RS_173._col0=RS_155._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"] - <-Map 14 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_155] - PartitionCols:_col0 - Select Operator [SEL_154] (rows=652 width=8) - Output:["_col0"] - Filter Operator [FIL_153] (rows=652 width=8) - predicate:((d_year = 2001) and d_date_sk is not null) - TableScan [TS_12] (rows=73049 width=8) - default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year"] - <-Map 10 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_173] - PartitionCols:_col0 - Select Operator [SEL_172] (rows=283692098 width=466) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"] - Filter Operator [FIL_171] (rows=283692098 width=466) - predicate:((cs_bill_cdemo_sk BETWEEN DynamicValue(RS_25_cd1_cd_demo_sk_min) AND DynamicValue(RS_25_cd1_cd_demo_sk_max) and in_bloom_filter(cs_bill_cdemo_sk, DynamicValue(RS_25_cd1_cd_demo_sk_bloom_filter))) and (cs_bill_customer_sk BETWEEN DynamicValue(RS_37_customer_c_customer_sk_min) AND DynamicValue(RS_37_customer_c_customer_sk_max) and in_bloom_filter(cs_bill_customer_sk, DynamicValue(RS_37_customer_c_customer_sk_bloom_filter))) and (cs_sold_date_sk BETWEEN DynamicValue(RS_22_date_dim_d_date_sk_min) AND DynamicValue(RS_22_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_22_date_dim_d_date_sk_bloom_filter))) and cs_bill_cdemo_sk is not null 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_9] (rows=287989836 width=466) - default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["cs_sold_date_sk","cs_bill_customer_sk","cs_bill_cdemo_sk","cs_item_sk","cs_quantity","cs_list_price","cs_sales_price","cs_coupon_amt","cs_net_profit"] - <-Reducer 15 [BROADCAST_EDGE] vectorized - BROADCAST [RS_160] - Group By Operator [GBY_159] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 14 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_158] - Group By Operator [GBY_157] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_156] (rows=652 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_154] - <-Reducer 17 [BROADCAST_EDGE] vectorized - BROADCAST [RS_168] - Group By Operator [GBY_167] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 16 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_166] - Group By Operator [GBY_165] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_164] (rows=103433 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_162] - <-Reducer 7 [BROADCAST_EDGE] vectorized - BROADCAST [RS_170] - Group By Operator [GBY_169] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=4890586)"] - <-Reducer 3 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_120] - Group By Operator [GBY_119] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=4890586)"] - Select Operator [SEL_118] (rows=4959744 width=4) - Output:["_col0"] - Please refer to the previous Merge Join Operator [MERGEJOIN_139] + Select Operator [SEL_161] (rows=103433 width=116) + Output:["_col0","_col1"] + Filter Operator [FIL_160] (rows=103433 width=187) + predicate:((cd_education_status = 'College') and (cd_gender = 'M') and cd_demo_sk is not null) + TableScan [TS_15] (rows=1861800 width=187) + default@customer_demographics,cd1,Tbl:COMPLETE,Col:COMPLETE,Output:["cd_demo_sk","cd_gender","cd_education_status","cd_dep_count"] + <-Reducer 11 [SIMPLE_EDGE] + SHUFFLE [RS_24] + PartitionCols:_col2 + Merge Join Operator [MERGEJOIN_139] (rows=100578970 width=565) + Conds:RS_172._col0=RS_154._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"] + <-Map 14 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_154] + PartitionCols:_col0 + Select Operator [SEL_153] (rows=652 width=4) + Output:["_col0"] + Filter Operator [FIL_152] (rows=652 width=8) + predicate:((d_year = 2001) and d_date_sk is not null) + TableScan [TS_12] (rows=73049 width=8) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year"] + <-Map 10 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_172] + PartitionCols:_col0 + Select Operator [SEL_171] (rows=283692098 width=573) + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"] + Filter Operator [FIL_170] (rows=283692098 width=466) + predicate:((cs_bill_cdemo_sk BETWEEN DynamicValue(RS_25_cd1_cd_demo_sk_min) AND DynamicValue(RS_25_cd1_cd_demo_sk_max) and in_bloom_filter(cs_bill_cdemo_sk, DynamicValue(RS_25_cd1_cd_demo_sk_bloom_filter))) and (cs_bill_customer_sk BETWEEN DynamicValue(RS_37_customer_c_customer_sk_min) AND DynamicValue(RS_37_customer_c_customer_sk_max) and in_bloom_filter(cs_bill_customer_sk, DynamicValue(RS_37_customer_c_customer_sk_bloom_filter))) and (cs_sold_date_sk BETWEEN DynamicValue(RS_22_date_dim_d_date_sk_min) AND DynamicValue(RS_22_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_22_date_dim_d_date_sk_bloom_filter))) and cs_bill_cdemo_sk is not null 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_9] (rows=287989836 width=466) + default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["cs_sold_date_sk","cs_bill_customer_sk","cs_bill_cdemo_sk","cs_item_sk","cs_quantity","cs_list_price","cs_sales_price","cs_coupon_amt","cs_net_profit"] + <-Reducer 15 [BROADCAST_EDGE] vectorized + BROADCAST [RS_159] + Group By Operator [GBY_158] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 14 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_157] + Group By Operator [GBY_156] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_155] (rows=652 width=4) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_153] + <-Reducer 17 [BROADCAST_EDGE] vectorized + BROADCAST [RS_167] + Group By Operator [GBY_166] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 16 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_165] + Group By Operator [GBY_164] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_163] (rows=103433 width=4) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_161] + <-Reducer 7 [BROADCAST_EDGE] vectorized + BROADCAST [RS_169] + Group By Operator [GBY_168] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=4890586)"] + <-Reducer 3 [CUSTOM_SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_119] + Group By Operator [GBY_118] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=4890586)"] + Select Operator [SEL_117] (rows=4959744 width=4) + Output:["_col0"] + Please refer to the previous Merge Join Operator [MERGEJOIN_138] diff --git ql/src/test/results/clientpositive/perf/tez/query19.q.out ql/src/test/results/clientpositive/perf/tez/query19.q.out index fd8578f4026..ebb4d17fdfc 100644 --- ql/src/test/results/clientpositive/perf/tez/query19.q.out +++ ql/src/test/results/clientpositive/perf/tez/query19.q.out @@ -94,17 +94,17 @@ Stage-0 SHUFFLE [RS_37] PartitionCols:_col0, _col1, _col2, _col3 Group By Operator [GBY_36] (rows=2098703 width=314) - Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["sum(_col8)"],keys:_col14, _col13, _col15, _col16 - Select Operator [SEL_35] (rows=2098703 width=380) - Output:["_col8","_col13","_col14","_col15","_col16"] - Filter Operator [FIL_34] (rows=2098703 width=380) - predicate:(substr(_col3, 1, 5) <> substr(_col19, 1, 5)) - Merge Join Operator [MERGEJOIN_123] (rows=2098703 width=380) - Conds:RS_31._col7=RS_151._col0(Inner),Output:["_col3","_col8","_col13","_col14","_col15","_col16","_col19"] + Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["sum(_col8)"],keys:_col12, _col11, _col13, _col14 + Select Operator [SEL_35] (rows=2098703 width=570) + Output:["_col8","_col11","_col12","_col13","_col14"] + Filter Operator [FIL_34] (rows=2098703 width=570) + predicate:(_col3 <> _col16) + Merge Join Operator [MERGEJOIN_123] (rows=2098703 width=570) + Conds:RS_31._col7=RS_151._col0(Inner),Output:["_col3","_col8","_col11","_col12","_col13","_col14","_col16"] <-Map 15 [SIMPLE_EDGE] vectorized SHUFFLE [RS_151] PartitionCols:_col0 - Select Operator [SEL_150] (rows=1704 width=93) + Select Operator [SEL_150] (rows=1704 width=188) Output:["_col0","_col1"] Filter Operator [FIL_149] (rows=1704 width=93) predicate:s_store_sk is not null @@ -113,17 +113,17 @@ Stage-0 <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_31] PartitionCols:_col7 - Merge Join Operator [MERGEJOIN_122] (rows=2098703 width=291) - Conds:RS_28._col0=RS_29._col2(Inner),Output:["_col3","_col7","_col8","_col13","_col14","_col15","_col16"] + Merge Join Operator [MERGEJOIN_122] (rows=2098703 width=386) + Conds:RS_28._col0=RS_29._col2(Inner),Output:["_col3","_col7","_col8","_col11","_col12","_col13","_col14"] <-Reducer 10 [SIMPLE_EDGE] SHUFFLE [RS_29] PartitionCols:_col2 Merge Join Operator [MERGEJOIN_121] (rows=2098703 width=202) - Conds:RS_18._col1=RS_140._col0(Inner),Output:["_col2","_col3","_col4","_col9","_col10","_col11","_col12"] + Conds:RS_18._col1=RS_140._col0(Inner),Output:["_col2","_col3","_col4","_col7","_col8","_col9","_col10"] <-Map 13 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_140] PartitionCols:_col0 - Select Operator [SEL_139] (rows=7333 width=210) + Select Operator [SEL_139] (rows=7333 width=206) Output:["_col0","_col1","_col2","_col3","_col4"] Filter Operator [FIL_138] (rows=7333 width=210) predicate:((i_manager_id = 7) and i_item_sk is not null) @@ -137,7 +137,7 @@ Stage-0 <-Map 11 [SIMPLE_EDGE] vectorized SHUFFLE [RS_132] PartitionCols:_col0 - Select Operator [SEL_131] (rows=50 width=12) + Select Operator [SEL_131] (rows=50 width=4) Output:["_col0"] Filter Operator [FIL_130] (rows=50 width=12) predicate:((d_moy = 11) and (d_year = 1999) and d_date_sk is not null) @@ -177,7 +177,7 @@ Stage-0 <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_28] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_119] (rows=80000000 width=93) + Merge Join Operator [MERGEJOIN_119] (rows=80000000 width=188) Conds:RS_126._col1=RS_129._col0(Inner),Output:["_col0","_col3"] <-Map 1 [SIMPLE_EDGE] vectorized SHUFFLE [RS_126] @@ -191,7 +191,7 @@ Stage-0 <-Map 7 [SIMPLE_EDGE] vectorized SHUFFLE [RS_129] PartitionCols:_col0 - Select Operator [SEL_128] (rows=40000000 width=93) + Select Operator [SEL_128] (rows=40000000 width=188) Output:["_col0","_col1"] Filter Operator [FIL_127] (rows=40000000 width=93) predicate:ca_address_sk is not null diff --git ql/src/test/results/clientpositive/perf/tez/query2.q.out ql/src/test/results/clientpositive/perf/tez/query2.q.out index f46b336f686..2bea1c7d15b 100644 --- ql/src/test/results/clientpositive/perf/tez/query2.q.out +++ ql/src/test/results/clientpositive/perf/tez/query2.q.out @@ -149,7 +149,7 @@ Stage-0 Select Operator [SEL_56] (rows=12881 width=788) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] Merge Join Operator [MERGEJOIN_146] (rows=12881 width=1572) - Conds:RS_53._col0=RS_54.(_col0 - 53)(Inner),Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col11","_col12","_col13","_col14","_col15","_col16","_col17"] + Conds:RS_53._col0=RS_54.(_col0 - 53)(Inner),Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col10","_col11","_col12","_col13","_col14","_col15","_col16"] <-Reducer 5 [ONE_TO_ONE_EDGE] FORWARD [RS_53] PartitionCols:_col0 @@ -158,7 +158,7 @@ Stage-0 <-Map 11 [SIMPLE_EDGE] vectorized SHUFFLE [RS_170] PartitionCols:_col0 - Select Operator [SEL_168] (rows=652 width=8) + Select Operator [SEL_168] (rows=652 width=4) Output:["_col0"] Filter Operator [FIL_166] (rows=652 width=8) predicate:((d_year = 2001) and d_week_seq is not null) @@ -172,17 +172,17 @@ Stage-0 <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_17] PartitionCols:_col0 - Group By Operator [GBY_16] (rows=4576896 width=788) + Group By Operator [GBY_16] (rows=3182784 width=788) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"],aggregations:["sum(_col1)","sum(_col2)","sum(_col3)","sum(_col4)","sum(_col5)","sum(_col6)","sum(_col7)"],keys:_col0 - Select Operator [SEL_14] (rows=430516591 width=206) + Select Operator [SEL_14] (rows=430516591 width=143) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] - Merge Join Operator [MERGEJOIN_142] (rows=430516591 width=206) - Conds:Union 2._col0=RS_162._col0(Inner),Output:["_col1","_col3","_col4"] + Merge Join Operator [MERGEJOIN_142] (rows=430516591 width=143) + Conds:Union 2._col0=RS_162._col0(Inner),Output:["_col1","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10"] <-Map 10 [SIMPLE_EDGE] vectorized SHUFFLE [RS_162] PartitionCols:_col0 - Select Operator [SEL_161] (rows=73049 width=99) - Output:["_col0","_col1","_col2"] + Select Operator [SEL_161] (rows=73049 width=36) + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"] Filter Operator [FIL_160] (rows=73049 width=99) predicate:(d_date_sk is not null and d_week_seq is not null) TableScan [TS_8] (rows=73049 width=99) @@ -214,7 +214,7 @@ Stage-0 <-Map 11 [SIMPLE_EDGE] vectorized SHUFFLE [RS_171] PartitionCols:_col0 - Select Operator [SEL_169] (rows=652 width=8) + Select Operator [SEL_169] (rows=652 width=4) Output:["_col0"] Filter Operator [FIL_167] (rows=652 width=8) predicate:((d_year = 2002) and d_week_seq is not null) diff --git ql/src/test/results/clientpositive/perf/tez/query20.q.out ql/src/test/results/clientpositive/perf/tez/query20.q.out index 892beb37cb3..0fa6f79e47f 100644 --- ql/src/test/results/clientpositive/perf/tez/query20.q.out +++ ql/src/test/results/clientpositive/perf/tez/query20.q.out @@ -101,9 +101,9 @@ Stage-0 SHUFFLE [RS_17] PartitionCols:_col0, _col1, _col2, _col3, _col4 Group By Operator [GBY_16] (rows=138600 width=689) - Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(_col2)"],keys:_col10, _col9, _col6, _col7, _col8 + Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(_col2)"],keys:_col9, _col8, _col5, _col6, _col7 Merge Join Operator [MERGEJOIN_58] (rows=9551005 width=673) - Conds:RS_12._col1=RS_69._col0(Inner),Output:["_col2","_col6","_col7","_col8","_col9","_col10"] + Conds:RS_12._col1=RS_69._col0(Inner),Output:["_col2","_col5","_col6","_col7","_col8","_col9"] <-Map 9 [SIMPLE_EDGE] vectorized SHUFFLE [RS_69] PartitionCols:_col0 @@ -121,7 +121,7 @@ Stage-0 <-Map 7 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_61] PartitionCols:_col0 - Select Operator [SEL_60] (rows=8116 width=98) + Select Operator [SEL_60] (rows=8116 width=4) Output:["_col0"] Filter Operator [FIL_59] (rows=8116 width=98) predicate:(CAST( d_date AS TIMESTAMP) BETWEEN TIMESTAMP'2001-01-12 00:00:00' AND TIMESTAMP'2001-02-11 00:00:00' and d_date_sk is not null) diff --git ql/src/test/results/clientpositive/perf/tez/query21.q.out ql/src/test/results/clientpositive/perf/tez/query21.q.out index be040df41ac..382775a8cc5 100644 --- ql/src/test/results/clientpositive/perf/tez/query21.q.out +++ ql/src/test/results/clientpositive/perf/tez/query21.q.out @@ -96,10 +96,10 @@ Stage-0 PartitionCols:_col0, _col1 Group By Operator [GBY_23] (rows=463966 width=216) Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(_col2)","sum(_col3)"],keys:_col0, _col1 - Select Operator [SEL_21] (rows=463966 width=294) + Select Operator [SEL_21] (rows=463966 width=208) Output:["_col0","_col1","_col2","_col3"] - Merge Join Operator [MERGEJOIN_77] (rows=463966 width=294) - Conds:RS_18._col2=RS_89._col0(Inner),Output:["_col3","_col5","_col7","_col10"] + Merge Join Operator [MERGEJOIN_77] (rows=463966 width=208) + Conds:RS_18._col2=RS_89._col0(Inner),Output:["_col3","_col5","_col6","_col8","_col10"] <-Map 9 [SIMPLE_EDGE] vectorized SHUFFLE [RS_89] PartitionCols:_col0 @@ -112,12 +112,12 @@ Stage-0 <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_18] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_76] (rows=463966 width=198) - Conds:RS_15._col1=RS_86._col0(Inner),Output:["_col2","_col3","_col5","_col7"] + Merge Join Operator [MERGEJOIN_76] (rows=463966 width=112) + Conds:RS_15._col1=RS_86._col0(Inner),Output:["_col2","_col3","_col5","_col6","_col8"] <-Map 8 [SIMPLE_EDGE] vectorized SHUFFLE [RS_86] PartitionCols:_col0 - Select Operator [SEL_85] (rows=51333 width=215) + Select Operator [SEL_85] (rows=51333 width=104) Output:["_col0","_col1"] Filter Operator [FIL_84] (rows=51333 width=215) predicate:(i_current_price BETWEEN 0.99 AND 1.49 and i_item_sk is not null) @@ -126,8 +126,8 @@ Stage-0 <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_15] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_75] (rows=4175715 width=104) - Conds:RS_80._col0=RS_83._col0(Inner),Output:["_col1","_col2","_col3","_col5"] + Merge Join Operator [MERGEJOIN_75] (rows=4175715 width=18) + Conds:RS_80._col0=RS_83._col0(Inner),Output:["_col1","_col2","_col3","_col5","_col6"] <-Map 1 [SIMPLE_EDGE] vectorized SHUFFLE [RS_80] PartitionCols:_col0 @@ -140,8 +140,8 @@ Stage-0 <-Map 7 [SIMPLE_EDGE] vectorized SHUFFLE [RS_83] PartitionCols:_col0 - Select Operator [SEL_82] (rows=8116 width=98) - Output:["_col0","_col1"] + Select Operator [SEL_82] (rows=8116 width=12) + Output:["_col0","_col1","_col2"] Filter Operator [FIL_81] (rows=8116 width=98) predicate:(CAST( d_date AS TIMESTAMP) BETWEEN TIMESTAMP'1998-03-09 00:00:00' AND TIMESTAMP'1998-05-08 00:00:00' and d_date_sk is not null) TableScan [TS_3] (rows=73049 width=98) diff --git ql/src/test/results/clientpositive/perf/tez/query22.q.out ql/src/test/results/clientpositive/perf/tez/query22.q.out index df6889b5ffb..2d88d8f6afa 100644 --- ql/src/test/results/clientpositive/perf/tez/query22.q.out +++ ql/src/test/results/clientpositive/perf/tez/query22.q.out @@ -79,9 +79,9 @@ Stage-0 SHUFFLE [RS_23] PartitionCols:_col0, _col1, _col2, _col3, _col4 Group By Operator [GBY_22] (rows=32730675 width=413) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"],aggregations:["sum(_col3)","count(_col3)"],keys:_col8, _col9, _col10, _col11, 0L + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"],aggregations:["sum(_col3)","count(_col3)"],keys:_col7, _col8, _col9, _col10, 0L Merge Join Operator [MERGEJOIN_75] (rows=6546135 width=391) - Conds:RS_18._col1=RS_87._col0(Inner),Output:["_col3","_col8","_col9","_col10","_col11"] + Conds:RS_18._col1=RS_87._col0(Inner),Output:["_col3","_col7","_col8","_col9","_col10"] <-Map 9 [SIMPLE_EDGE] vectorized SHUFFLE [RS_87] PartitionCols:_col0 @@ -122,7 +122,7 @@ Stage-0 <-Map 7 [SIMPLE_EDGE] vectorized SHUFFLE [RS_81] PartitionCols:_col0 - Select Operator [SEL_80] (rows=317 width=8) + Select Operator [SEL_80] (rows=317 width=4) Output:["_col0"] Filter Operator [FIL_79] (rows=317 width=8) predicate:(d_date_sk is not null and d_month_seq BETWEEN 1212 AND 1223) diff --git ql/src/test/results/clientpositive/perf/tez/query23.q.out ql/src/test/results/clientpositive/perf/tez/query23.q.out index 77847929b40..059195a8907 100644 --- ql/src/test/results/clientpositive/perf/tez/query23.q.out +++ ql/src/test/results/clientpositive/perf/tez/query23.q.out @@ -1,7 +1,7 @@ -Warning: Shuffle Join MERGEJOIN[593][tables = [$hdt$_1, $hdt$_2]] in Stage 'Reducer 29' is a cross product -Warning: Shuffle Join MERGEJOIN[594][tables = [$hdt$_1, $hdt$_2, $hdt$_0]] in Stage 'Reducer 30' is a cross product -Warning: Shuffle Join MERGEJOIN[596][tables = [$hdt$_1, $hdt$_2]] in Stage 'Reducer 33' is a cross product -Warning: Shuffle Join MERGEJOIN[597][tables = [$hdt$_1, $hdt$_2, $hdt$_0]] in Stage 'Reducer 34' is a cross product +Warning: Shuffle Join MERGEJOIN[583][tables = [$hdt$_1, $hdt$_2]] in Stage 'Reducer 29' is a cross product +Warning: Shuffle Join MERGEJOIN[584][tables = [$hdt$_1, $hdt$_2, $hdt$_0]] in Stage 'Reducer 30' is a cross product +Warning: Shuffle Join MERGEJOIN[586][tables = [$hdt$_1, $hdt$_2]] in Stage 'Reducer 33' is a cross product +Warning: Shuffle Join MERGEJOIN[587][tables = [$hdt$_1, $hdt$_2, $hdt$_0]] in Stage 'Reducer 34' is a cross product PREHOOK: query: explain with frequent_ss_items as (select substr(i_item_desc,1,30) itemdesc,i_item_sk item_sk,d_date solddate,count(*) cnt @@ -166,399 +166,391 @@ Stage-0 limit:100 Stage-1 Reducer 6 vectorized - File Output Operator [FS_699] - Limit [LIM_698] (rows=1 width=112) + File Output Operator [FS_689] + Limit [LIM_688] (rows=1 width=112) Number of rows:100 - Group By Operator [GBY_697] (rows=1 width=112) + Group By Operator [GBY_687] (rows=1 width=112) Output:["_col0"],aggregations:["sum(VALUE._col0)"] <-Union 5 [CUSTOM_SIMPLE_EDGE] <-Reducer 12 [CONTAINS] - Reduce Output Operator [RS_608] - Group By Operator [GBY_607] (rows=1 width=112) + Reduce Output Operator [RS_598] + Group By Operator [GBY_597] (rows=1 width=112) Output:["_col0"],aggregations:["sum(_col0)"] - Select Operator [SEL_605] (rows=1 width=112) + Select Operator [SEL_595] (rows=1 width=112) Output:["_col0"] - Merge Join Operator [MERGEJOIN_604] (rows=1 width=116) - Conds:RS_248._col2=RS_249._col0(Inner),Output:["_col3","_col4"] + Merge Join Operator [MERGEJOIN_594] (rows=1 width=116) + Conds:RS_240._col2=RS_241._col0(Inner),Output:["_col3","_col4"] <-Reducer 11 [SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_248] + PARTITION_ONLY_SHUFFLE [RS_240] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_592] (rows=155 width=0) - Conds:RS_245._col1=RS_642._col0(Inner),Output:["_col2","_col3","_col4"] + Merge Join Operator [MERGEJOIN_582] (rows=155 width=0) + Conds:RS_237._col1=RS_632._col0(Inner),Output:["_col2","_col3","_col4"] <-Reducer 18 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_642] + SHUFFLE [RS_632] PartitionCols:_col0 - Group By Operator [GBY_639] (rows=2235 width=4) + Group By Operator [GBY_629] (rows=2235 width=4) Output:["_col0"],keys:_col1 - Select Operator [SEL_638] (rows=6548799 width=12) + Select Operator [SEL_628] (rows=6548799 width=290) Output:["_col1"] - Filter Operator [FIL_637] (rows=6548799 width=12) + Filter Operator [FIL_627] (rows=6548799 width=290) predicate:(_col3 > 4L) - Select Operator [SEL_636] (rows=19646398 width=12) - Output:["_col0","_col3"] - Group By Operator [GBY_635] (rows=19646398 width=290) + Select Operator [SEL_626] (rows=19646398 width=290) + Output:["_col1","_col3"] + Group By Operator [GBY_625] (rows=19646398 width=290) Output:["_col0","_col1","_col2","_col3"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2 <-Reducer 17 [SIMPLE_EDGE] - SHUFFLE [RS_24] + SHUFFLE [RS_23] PartitionCols:_col0 - Group By Operator [GBY_23] (rows=19646398 width=290) - Output:["_col0","_col1","_col2","_col3"],aggregations:["count()"],keys:_col1, _col0, _col2 - Select Operator [SEL_21] (rows=19646398 width=282) - Output:["_col0","_col1","_col2"] - Merge Join Operator [MERGEJOIN_577] (rows=19646398 width=282) - Conds:RS_18._col1=RS_634._col0(Inner),Output:["_col3","_col5","_col6"] - <-Map 23 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_634] - PartitionCols:_col0 - Select Operator [SEL_633] (rows=462000 width=188) - Output:["_col0","_col1"] - Filter Operator [FIL_632] (rows=462000 width=188) - predicate:i_item_sk is not null - TableScan [TS_12] (rows=462000 width=188) - default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_item_desc"] - <-Reducer 16 [SIMPLE_EDGE] - SHUFFLE [RS_18] - PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_576] (rows=19646398 width=98) - Conds:RS_631._col0=RS_623._col0(Inner),Output:["_col1","_col3"] - <-Map 21 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_623] - PartitionCols:_col0 - Select Operator [SEL_622] (rows=2609 width=102) - Output:["_col0","_col1"] - Filter Operator [FIL_621] (rows=2609 width=102) - predicate:((d_year) IN (1999, 2000, 2001, 2002) and d_date_sk is not null) - TableScan [TS_9] (rows=73049 width=102) - default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_date","d_year"] - <-Map 15 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_631] - PartitionCols:_col0 - Select Operator [SEL_630] (rows=550076554 width=7) - Output:["_col0","_col1"] - Filter Operator [FIL_629] (rows=550076554 width=7) - predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_16_date_dim_d_date_sk_min) AND DynamicValue(RS_16_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_16_date_dim_d_date_sk_bloom_filter))) and ss_item_sk is not null and ss_sold_date_sk is not null) - TableScan [TS_6] (rows=575995635 width=7) - default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_item_sk"] - <-Reducer 22 [BROADCAST_EDGE] vectorized - BROADCAST [RS_628] - Group By Operator [GBY_627] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 21 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_626] - Group By Operator [GBY_625] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_624] (rows=2609 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_622] + Group By Operator [GBY_22] (rows=19646398 width=290) + Output:["_col0","_col1","_col2","_col3"],aggregations:["count()"],keys:_col4, _col3, _col5 + Merge Join Operator [MERGEJOIN_567] (rows=19646398 width=282) + Conds:RS_18._col1=RS_624._col0(Inner),Output:["_col3","_col4","_col5"] + <-Map 23 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_624] + PartitionCols:_col0 + Select Operator [SEL_623] (rows=462000 width=188) + Output:["_col0","_col1"] + Filter Operator [FIL_622] (rows=462000 width=188) + predicate:i_item_sk is not null + TableScan [TS_12] (rows=462000 width=188) + default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_item_desc"] + <-Reducer 16 [SIMPLE_EDGE] + SHUFFLE [RS_18] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_566] (rows=19646398 width=98) + Conds:RS_621._col0=RS_613._col0(Inner),Output:["_col1","_col3"] + <-Map 21 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_613] + PartitionCols:_col0 + Select Operator [SEL_612] (rows=2609 width=98) + Output:["_col0","_col1"] + Filter Operator [FIL_611] (rows=2609 width=102) + predicate:((d_year) IN (1999, 2000, 2001, 2002) and d_date_sk is not null) + TableScan [TS_9] (rows=73049 width=102) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_date","d_year"] + <-Map 15 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_621] + PartitionCols:_col0 + Select Operator [SEL_620] (rows=550076554 width=7) + Output:["_col0","_col1"] + Filter Operator [FIL_619] (rows=550076554 width=7) + predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_16_date_dim_d_date_sk_min) AND DynamicValue(RS_16_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_16_date_dim_d_date_sk_bloom_filter))) and ss_item_sk is not null and ss_sold_date_sk is not null) + TableScan [TS_6] (rows=575995635 width=7) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_item_sk"] + <-Reducer 22 [BROADCAST_EDGE] vectorized + BROADCAST [RS_618] + Group By Operator [GBY_617] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 21 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_616] + Group By Operator [GBY_615] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_614] (rows=2609 width=4) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_612] <-Reducer 10 [SIMPLE_EDGE] - SHUFFLE [RS_245] + SHUFFLE [RS_237] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_583] (rows=3941102 width=122) - Conds:RS_706._col0=RS_613._col0(Inner),Output:["_col1","_col2","_col3","_col4"] + Merge Join Operator [MERGEJOIN_573] (rows=3941102 width=122) + Conds:RS_696._col0=RS_603._col0(Inner),Output:["_col1","_col2","_col3","_col4"] <-Map 8 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_613] + PARTITION_ONLY_SHUFFLE [RS_603] PartitionCols:_col0 - Select Operator [SEL_610] (rows=50 width=12) + Select Operator [SEL_600] (rows=50 width=4) Output:["_col0"] - Filter Operator [FIL_609] (rows=50 width=12) + Filter Operator [FIL_599] (rows=50 width=12) predicate:((d_moy = 1) and (d_year = 1999) and d_date_sk is not null) TableScan [TS_3] (rows=73049 width=12) default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year","d_moy"] <-Map 44 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_706] + SHUFFLE [RS_696] PartitionCols:_col0 - Select Operator [SEL_705] (rows=143930993 width=127) + Select Operator [SEL_695] (rows=143930993 width=127) Output:["_col0","_col1","_col2","_col3","_col4"] - Filter Operator [FIL_704] (rows=143930993 width=127) - predicate:((ws_item_sk BETWEEN DynamicValue(RS_246_item_i_item_sk_min) AND DynamicValue(RS_246_item_i_item_sk_max) and in_bloom_filter(ws_item_sk, DynamicValue(RS_246_item_i_item_sk_bloom_filter))) and (ws_sold_date_sk BETWEEN DynamicValue(RS_243_date_dim_d_date_sk_min) AND DynamicValue(RS_243_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_243_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_126] (rows=144002668 width=127) + Filter Operator [FIL_694] (rows=143930993 width=127) + predicate:((ws_item_sk BETWEEN DynamicValue(RS_238_item_i_item_sk_min) AND DynamicValue(RS_238_item_i_item_sk_max) and in_bloom_filter(ws_item_sk, DynamicValue(RS_238_item_i_item_sk_bloom_filter))) and (ws_sold_date_sk BETWEEN DynamicValue(RS_235_date_dim_d_date_sk_min) AND DynamicValue(RS_235_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_235_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_122] (rows=144002668 width=127) default@web_sales,web_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_sold_date_sk","ws_item_sk","ws_bill_customer_sk","ws_quantity","ws_list_price"] <-Reducer 14 [BROADCAST_EDGE] vectorized - BROADCAST [RS_701] - Group By Operator [GBY_700] (rows=1 width=12) + BROADCAST [RS_691] + Group By Operator [GBY_690] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Map 8 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_618] - Group By Operator [GBY_616] (rows=1 width=12) + PARTITION_ONLY_SHUFFLE [RS_608] + Group By Operator [GBY_606] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_614] (rows=50 width=4) + Select Operator [SEL_604] (rows=50 width=4) Output:["_col0"] - Please refer to the previous Select Operator [SEL_610] + Please refer to the previous Select Operator [SEL_600] <-Reducer 20 [BROADCAST_EDGE] vectorized - BROADCAST [RS_703] - Group By Operator [GBY_702] (rows=1 width=12) + BROADCAST [RS_693] + Group By Operator [GBY_692] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Reducer 18 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_647] - Group By Operator [GBY_645] (rows=1 width=12) + SHUFFLE [RS_637] + Group By Operator [GBY_635] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_643] (rows=2235 width=4) + Select Operator [SEL_633] (rows=2235 width=4) Output:["_col0"] - Please refer to the previous Group By Operator [GBY_639] + Please refer to the previous Group By Operator [GBY_629] <-Reducer 34 [SIMPLE_EDGE] - SHUFFLE [RS_249] + SHUFFLE [RS_241] PartitionCols:_col0 - Select Operator [SEL_241] (rows=471875 width=4) + Select Operator [SEL_233] (rows=471875 width=4) Output:["_col0"] - Filter Operator [FIL_240] (rows=471875 width=228) + Filter Operator [FIL_232] (rows=471875 width=228) predicate:(_col3 > (0.95 * _col1)) - Merge Join Operator [MERGEJOIN_597] (rows=1415625 width=228) + Merge Join Operator [MERGEJOIN_587] (rows=1415625 width=228) Conds:(Inner),Output:["_col1","_col2","_col3"] <-Reducer 33 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_237] - Merge Join Operator [MERGEJOIN_596] (rows=1 width=112) + PARTITION_ONLY_SHUFFLE [RS_229] + Merge Join Operator [MERGEJOIN_586] (rows=1 width=112) Conds:(Inner),Output:["_col1"] <-Reducer 32 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_712] - Select Operator [SEL_711] (rows=1 width=8) - Filter Operator [FIL_710] (rows=1 width=8) + PARTITION_ONLY_SHUFFLE [RS_702] + Select Operator [SEL_701] (rows=1 width=8) + Filter Operator [FIL_700] (rows=1 width=8) predicate:(sq_count_check(_col0) <= 1) - Group By Operator [GBY_709] (rows=1 width=8) + Group By Operator [GBY_699] (rows=1 width=8) Output:["_col0"],aggregations:["count()"] - Select Operator [SEL_708] (rows=1 width=8) - Group By Operator [GBY_707] (rows=1 width=8) + Select Operator [SEL_698] (rows=1 width=8) + Group By Operator [GBY_697] (rows=1 width=8) Output:["_col0"],aggregations:["count(VALUE._col0)"] <-Reducer 27 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_680] - Group By Operator [GBY_676] (rows=1 width=8) + PARTITION_ONLY_SHUFFLE [RS_670] + Group By Operator [GBY_666] (rows=1 width=8) Output:["_col0"],aggregations:["count(_col0)"] - Select Operator [SEL_672] (rows=11859 width=116) + Select Operator [SEL_662] (rows=11859 width=116) Output:["_col0"] - Group By Operator [GBY_669] (rows=11859 width=116) + Group By Operator [GBY_659] (rows=11859 width=116) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 <-Reducer 26 [SIMPLE_EDGE] - SHUFFLE [RS_51] + SHUFFLE [RS_49] PartitionCols:_col0 - Group By Operator [GBY_50] (rows=11859 width=116) - Output:["_col0","_col1"],aggregations:["sum(_col1)"],keys:_col0 - Select Operator [SEL_48] (rows=18762463 width=4) - Output:["_col0","_col1"] - Merge Join Operator [MERGEJOIN_579] (rows=18762463 width=4) - Conds:RS_45._col1=RS_667._col0(Inner),Output:["_col2","_col3","_col6"] - <-Map 41 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_667] - PartitionCols:_col0 - Select Operator [SEL_665] (rows=80000000 width=4) - Output:["_col0"] - Filter Operator [FIL_664] (rows=80000000 width=4) - predicate:c_customer_sk is not null - TableScan [TS_96] (rows=80000000 width=4) - default@customer,customer,Tbl:COMPLETE,Col:COMPLETE,Output:["c_customer_sk"] - <-Reducer 25 [SIMPLE_EDGE] - SHUFFLE [RS_45] - PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_578] (rows=18762463 width=0) - Conds:RS_663._col0=RS_655._col0(Inner),Output:["_col1","_col2","_col3"] - <-Map 36 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_655] - PartitionCols:_col0 - Select Operator [SEL_654] (rows=2609 width=8) - Output:["_col0"] - Filter Operator [FIL_653] (rows=2609 width=8) - predicate:((d_year) IN (1999, 2000, 2001, 2002) and d_date_sk is not null) - TableScan [TS_36] (rows=73049 width=8) - default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year"] - <-Map 24 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_663] - PartitionCols:_col0 - Select Operator [SEL_662] (rows=525327388 width=118) - Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_661] (rows=525327388 width=118) - predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_43_date_dim_d_date_sk_min) AND DynamicValue(RS_43_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_43_date_dim_d_date_sk_bloom_filter))) and ss_customer_sk is not null and ss_sold_date_sk is not null) - TableScan [TS_33] (rows=575995635 width=118) - default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_customer_sk","ss_quantity","ss_sales_price"] - <-Reducer 37 [BROADCAST_EDGE] vectorized - BROADCAST [RS_660] - Group By Operator [GBY_659] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 36 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_658] - Group By Operator [GBY_657] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_656] (rows=2609 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_654] + Group By Operator [GBY_48] (rows=106731 width=116) + Output:["_col0","_col1"],aggregations:["sum(_col2)"],keys:_col4 + Merge Join Operator [MERGEJOIN_569] (rows=18762463 width=116) + Conds:RS_44._col1=RS_657._col0(Inner),Output:["_col2","_col4"] + <-Map 41 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_657] + PartitionCols:_col0 + Select Operator [SEL_655] (rows=80000000 width=4) + Output:["_col0"] + Filter Operator [FIL_654] (rows=80000000 width=4) + predicate:c_customer_sk is not null + TableScan [TS_93] (rows=80000000 width=4) + default@customer,customer,Tbl:COMPLETE,Col:COMPLETE,Output:["c_customer_sk"] + <-Reducer 25 [SIMPLE_EDGE] + SHUFFLE [RS_44] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_568] (rows=18762463 width=112) + Conds:RS_653._col0=RS_645._col0(Inner),Output:["_col1","_col2"] + <-Map 36 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_645] + PartitionCols:_col0 + Select Operator [SEL_644] (rows=2609 width=4) + Output:["_col0"] + Filter Operator [FIL_643] (rows=2609 width=8) + predicate:((d_year) IN (1999, 2000, 2001, 2002) and d_date_sk is not null) + TableScan [TS_35] (rows=73049 width=8) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year"] + <-Map 24 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_653] + PartitionCols:_col0 + Select Operator [SEL_652] (rows=525327388 width=119) + Output:["_col0","_col1","_col2"] + Filter Operator [FIL_651] (rows=525327388 width=118) + predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_42_date_dim_d_date_sk_min) AND DynamicValue(RS_42_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_42_date_dim_d_date_sk_bloom_filter))) and ss_customer_sk is not null and ss_sold_date_sk is not null) + TableScan [TS_32] (rows=575995635 width=118) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_customer_sk","ss_quantity","ss_sales_price"] + <-Reducer 37 [BROADCAST_EDGE] vectorized + BROADCAST [RS_650] + Group By Operator [GBY_649] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 36 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_648] + Group By Operator [GBY_647] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_646] (rows=2609 width=4) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_644] <-Reducer 35 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_714] - Group By Operator [GBY_713] (rows=1 width=112) + PARTITION_ONLY_SHUFFLE [RS_704] + Group By Operator [GBY_703] (rows=1 width=112) Output:["_col0"],aggregations:["max(VALUE._col0)"] <-Reducer 27 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_681] - Group By Operator [GBY_677] (rows=1 width=112) + PARTITION_ONLY_SHUFFLE [RS_671] + Group By Operator [GBY_667] (rows=1 width=112) Output:["_col0"],aggregations:["max(_col1)"] - Select Operator [SEL_673] (rows=11859 width=116) + Select Operator [SEL_663] (rows=11859 width=116) Output:["_col1"] - Please refer to the previous Group By Operator [GBY_669] + Please refer to the previous Group By Operator [GBY_659] <-Reducer 43 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_721] - Group By Operator [GBY_720] (rows=1415625 width=116) + PARTITION_ONLY_SHUFFLE [RS_711] + Group By Operator [GBY_710] (rows=1415625 width=116) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 <-Reducer 42 [SIMPLE_EDGE] - SHUFFLE [RS_231] + SHUFFLE [RS_223] PartitionCols:_col0 - Group By Operator [GBY_230] (rows=550080312 width=116) - Output:["_col0","_col1"],aggregations:["sum(_col1)"],keys:_col0 - Select Operator [SEL_228] (rows=550080312 width=114) - Output:["_col0","_col1"] - Merge Join Operator [MERGEJOIN_590] (rows=550080312 width=114) - Conds:RS_719._col0=RS_668._col0(Inner),Output:["_col1","_col2","_col3"] - <-Map 41 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_668] - PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_665] - <-Map 45 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_719] - PartitionCols:_col0 - Select Operator [SEL_718] (rows=550080312 width=114) - Output:["_col0","_col1","_col2"] - Filter Operator [FIL_717] (rows=550080312 width=114) - predicate:((ss_customer_sk BETWEEN DynamicValue(RS_248_web_sales_ws_bill_customer_sk_min) AND DynamicValue(RS_248_web_sales_ws_bill_customer_sk_max) and in_bloom_filter(ss_customer_sk, DynamicValue(RS_248_web_sales_ws_bill_customer_sk_bloom_filter))) and ss_customer_sk is not null) - TableScan [TS_219] (rows=575995635 width=114) - default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_customer_sk","ss_quantity","ss_sales_price"] - <-Reducer 13 [BROADCAST_EDGE] vectorized - BROADCAST [RS_716] - Group By Operator [GBY_715] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Reducer 11 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_570] - Group By Operator [GBY_569] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_568] (rows=155 width=0) - Output:["_col0"] - Please refer to the previous Merge Join Operator [MERGEJOIN_592] + Group By Operator [GBY_222] (rows=80000000 width=116) + Output:["_col0","_col1"],aggregations:["sum(_col1)"],keys:_col2 + Merge Join Operator [MERGEJOIN_580] (rows=550080312 width=116) + Conds:RS_709._col0=RS_658._col0(Inner),Output:["_col1","_col2"] + <-Map 41 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_658] + PartitionCols:_col0 + Please refer to the previous Select Operator [SEL_655] + <-Map 45 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_709] + PartitionCols:_col0 + Select Operator [SEL_708] (rows=550080312 width=115) + Output:["_col0","_col1"] + Filter Operator [FIL_707] (rows=550080312 width=114) + predicate:((ss_customer_sk BETWEEN DynamicValue(RS_240_web_sales_ws_bill_customer_sk_min) AND DynamicValue(RS_240_web_sales_ws_bill_customer_sk_max) and in_bloom_filter(ss_customer_sk, DynamicValue(RS_240_web_sales_ws_bill_customer_sk_bloom_filter))) and ss_customer_sk is not null) + TableScan [TS_212] (rows=575995635 width=114) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_customer_sk","ss_quantity","ss_sales_price"] + <-Reducer 13 [BROADCAST_EDGE] vectorized + BROADCAST [RS_706] + Group By Operator [GBY_705] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Reducer 11 [CUSTOM_SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_560] + Group By Operator [GBY_559] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_558] (rows=155 width=0) + Output:["_col0"] + Please refer to the previous Merge Join Operator [MERGEJOIN_582] <-Reducer 4 [CONTAINS] - Reduce Output Operator [RS_603] - Group By Operator [GBY_602] (rows=1 width=112) + Reduce Output Operator [RS_593] + Group By Operator [GBY_592] (rows=1 width=112) Output:["_col0"],aggregations:["sum(_col0)"] - Select Operator [SEL_600] (rows=1 width=112) + Select Operator [SEL_590] (rows=1 width=112) Output:["_col0"] - Merge Join Operator [MERGEJOIN_599] (rows=1 width=116) - Conds:RS_122._col1=RS_123._col0(Inner),Output:["_col3","_col4"] + Merge Join Operator [MERGEJOIN_589] (rows=1 width=116) + Conds:RS_118._col1=RS_119._col0(Inner),Output:["_col3","_col4"] <-Reducer 3 [SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_122] + PARTITION_ONLY_SHUFFLE [RS_118] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_591] (rows=304 width=0) - Conds:RS_119._col2=RS_640._col0(Inner),Output:["_col1","_col3","_col4"] + Merge Join Operator [MERGEJOIN_581] (rows=304 width=0) + Conds:RS_115._col2=RS_630._col0(Inner),Output:["_col1","_col3","_col4"] <-Reducer 18 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_640] + SHUFFLE [RS_630] PartitionCols:_col0 - Please refer to the previous Group By Operator [GBY_639] + Please refer to the previous Group By Operator [GBY_629] <-Reducer 2 [SIMPLE_EDGE] - SHUFFLE [RS_119] + SHUFFLE [RS_115] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_575] (rows=7751875 width=101) - Conds:RS_652._col0=RS_611._col0(Inner),Output:["_col1","_col2","_col3","_col4"] + Merge Join Operator [MERGEJOIN_565] (rows=7751875 width=101) + Conds:RS_642._col0=RS_601._col0(Inner),Output:["_col1","_col2","_col3","_col4"] <-Map 8 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_611] + PARTITION_ONLY_SHUFFLE [RS_601] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_610] + Please refer to the previous Select Operator [SEL_600] <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_652] + SHUFFLE [RS_642] PartitionCols:_col0 - Select Operator [SEL_651] (rows=285117831 width=127) + Select Operator [SEL_641] (rows=285117831 width=127) Output:["_col0","_col1","_col2","_col3","_col4"] - Filter Operator [FIL_650] (rows=285117831 width=127) - predicate:((cs_item_sk BETWEEN DynamicValue(RS_120_item_i_item_sk_min) AND DynamicValue(RS_120_item_i_item_sk_max) and in_bloom_filter(cs_item_sk, DynamicValue(RS_120_item_i_item_sk_bloom_filter))) and (cs_sold_date_sk BETWEEN DynamicValue(RS_117_date_dim_d_date_sk_min) AND DynamicValue(RS_117_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_117_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) + Filter Operator [FIL_640] (rows=285117831 width=127) + predicate:((cs_item_sk BETWEEN DynamicValue(RS_116_item_i_item_sk_min) AND DynamicValue(RS_116_item_i_item_sk_max) and in_bloom_filter(cs_item_sk, DynamicValue(RS_116_item_i_item_sk_bloom_filter))) and (cs_sold_date_sk BETWEEN DynamicValue(RS_113_date_dim_d_date_sk_min) AND DynamicValue(RS_113_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_113_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_0] (rows=287989836 width=127) default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["cs_sold_date_sk","cs_bill_customer_sk","cs_item_sk","cs_quantity","cs_list_price"] <-Reducer 19 [BROADCAST_EDGE] vectorized - BROADCAST [RS_649] - Group By Operator [GBY_648] (rows=1 width=12) + BROADCAST [RS_639] + Group By Operator [GBY_638] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Reducer 18 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_646] - Group By Operator [GBY_644] (rows=1 width=12) + SHUFFLE [RS_636] + Group By Operator [GBY_634] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_641] (rows=2235 width=4) + Select Operator [SEL_631] (rows=2235 width=4) Output:["_col0"] - Please refer to the previous Group By Operator [GBY_639] + Please refer to the previous Group By Operator [GBY_629] <-Reducer 9 [BROADCAST_EDGE] vectorized - BROADCAST [RS_620] - Group By Operator [GBY_619] (rows=1 width=12) + BROADCAST [RS_610] + Group By Operator [GBY_609] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Map 8 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_617] - Group By Operator [GBY_615] (rows=1 width=12) + PARTITION_ONLY_SHUFFLE [RS_607] + Group By Operator [GBY_605] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_612] (rows=50 width=4) + Select Operator [SEL_602] (rows=50 width=4) Output:["_col0"] - Please refer to the previous Select Operator [SEL_610] + Please refer to the previous Select Operator [SEL_600] <-Reducer 30 [SIMPLE_EDGE] - SHUFFLE [RS_123] + SHUFFLE [RS_119] PartitionCols:_col0 - Select Operator [SEL_115] (rows=471875 width=4) + Select Operator [SEL_111] (rows=471875 width=4) Output:["_col0"] - Filter Operator [FIL_114] (rows=471875 width=228) + Filter Operator [FIL_110] (rows=471875 width=228) predicate:(_col3 > (0.95 * _col1)) - Merge Join Operator [MERGEJOIN_594] (rows=1415625 width=228) + Merge Join Operator [MERGEJOIN_584] (rows=1415625 width=228) Conds:(Inner),Output:["_col1","_col2","_col3"] <-Reducer 29 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_111] - Merge Join Operator [MERGEJOIN_593] (rows=1 width=112) + PARTITION_ONLY_SHUFFLE [RS_107] + Merge Join Operator [MERGEJOIN_583] (rows=1 width=112) Conds:(Inner),Output:["_col1"] <-Reducer 28 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_687] - Select Operator [SEL_686] (rows=1 width=8) - Filter Operator [FIL_685] (rows=1 width=8) + PARTITION_ONLY_SHUFFLE [RS_677] + Select Operator [SEL_676] (rows=1 width=8) + Filter Operator [FIL_675] (rows=1 width=8) predicate:(sq_count_check(_col0) <= 1) - Group By Operator [GBY_684] (rows=1 width=8) + Group By Operator [GBY_674] (rows=1 width=8) Output:["_col0"],aggregations:["count()"] - Select Operator [SEL_683] (rows=1 width=8) - Group By Operator [GBY_682] (rows=1 width=8) + Select Operator [SEL_673] (rows=1 width=8) + Group By Operator [GBY_672] (rows=1 width=8) Output:["_col0"],aggregations:["count(VALUE._col0)"] <-Reducer 27 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_678] - Group By Operator [GBY_674] (rows=1 width=8) + PARTITION_ONLY_SHUFFLE [RS_668] + Group By Operator [GBY_664] (rows=1 width=8) Output:["_col0"],aggregations:["count(_col0)"] - Select Operator [SEL_670] (rows=11859 width=116) + Select Operator [SEL_660] (rows=11859 width=116) Output:["_col0"] - Please refer to the previous Group By Operator [GBY_669] + Please refer to the previous Group By Operator [GBY_659] <-Reducer 31 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_689] - Group By Operator [GBY_688] (rows=1 width=112) + PARTITION_ONLY_SHUFFLE [RS_679] + Group By Operator [GBY_678] (rows=1 width=112) Output:["_col0"],aggregations:["max(VALUE._col0)"] <-Reducer 27 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_679] - Group By Operator [GBY_675] (rows=1 width=112) + PARTITION_ONLY_SHUFFLE [RS_669] + Group By Operator [GBY_665] (rows=1 width=112) Output:["_col0"],aggregations:["max(_col1)"] - Select Operator [SEL_671] (rows=11859 width=116) + Select Operator [SEL_661] (rows=11859 width=116) Output:["_col1"] - Please refer to the previous Group By Operator [GBY_669] + Please refer to the previous Group By Operator [GBY_659] <-Reducer 40 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_696] - Group By Operator [GBY_695] (rows=1415625 width=116) + PARTITION_ONLY_SHUFFLE [RS_686] + Group By Operator [GBY_685] (rows=1415625 width=116) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 <-Reducer 39 [SIMPLE_EDGE] - SHUFFLE [RS_105] + SHUFFLE [RS_101] PartitionCols:_col0 - Group By Operator [GBY_104] (rows=550080312 width=116) - Output:["_col0","_col1"],aggregations:["sum(_col1)"],keys:_col0 - Select Operator [SEL_102] (rows=550080312 width=114) - Output:["_col0","_col1"] - Merge Join Operator [MERGEJOIN_582] (rows=550080312 width=114) - Conds:RS_694._col0=RS_666._col0(Inner),Output:["_col1","_col2","_col3"] - <-Map 41 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_666] - PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_665] - <-Map 38 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_694] - PartitionCols:_col0 - Select Operator [SEL_693] (rows=550080312 width=114) - Output:["_col0","_col1","_col2"] - Filter Operator [FIL_692] (rows=550080312 width=114) - predicate:((ss_customer_sk BETWEEN DynamicValue(RS_122_catalog_sales_cs_bill_customer_sk_min) AND DynamicValue(RS_122_catalog_sales_cs_bill_customer_sk_max) and in_bloom_filter(ss_customer_sk, DynamicValue(RS_122_catalog_sales_cs_bill_customer_sk_bloom_filter))) and ss_customer_sk is not null) - TableScan [TS_93] (rows=575995635 width=114) - default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_customer_sk","ss_quantity","ss_sales_price"] - <-Reducer 7 [BROADCAST_EDGE] vectorized - BROADCAST [RS_691] - Group By Operator [GBY_690] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Reducer 3 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_464] - Group By Operator [GBY_463] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_462] (rows=304 width=0) - Output:["_col0"] - Please refer to the previous Merge Join Operator [MERGEJOIN_591] + Group By Operator [GBY_100] (rows=80000000 width=116) + Output:["_col0","_col1"],aggregations:["sum(_col1)"],keys:_col2 + Merge Join Operator [MERGEJOIN_572] (rows=550080312 width=116) + Conds:RS_684._col0=RS_656._col0(Inner),Output:["_col1","_col2"] + <-Map 41 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_656] + PartitionCols:_col0 + Please refer to the previous Select Operator [SEL_655] + <-Map 38 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_684] + PartitionCols:_col0 + Select Operator [SEL_683] (rows=550080312 width=115) + Output:["_col0","_col1"] + Filter Operator [FIL_682] (rows=550080312 width=114) + predicate:((ss_customer_sk BETWEEN DynamicValue(RS_118_catalog_sales_cs_bill_customer_sk_min) AND DynamicValue(RS_118_catalog_sales_cs_bill_customer_sk_max) and in_bloom_filter(ss_customer_sk, DynamicValue(RS_118_catalog_sales_cs_bill_customer_sk_bloom_filter))) and ss_customer_sk is not null) + TableScan [TS_90] (rows=575995635 width=114) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_customer_sk","ss_quantity","ss_sales_price"] + <-Reducer 7 [BROADCAST_EDGE] vectorized + BROADCAST [RS_681] + Group By Operator [GBY_680] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Reducer 3 [CUSTOM_SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_454] + Group By Operator [GBY_453] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_452] (rows=304 width=0) + Output:["_col0"] + Please refer to the previous Merge Join Operator [MERGEJOIN_581] diff --git ql/src/test/results/clientpositive/perf/tez/query24.q.out ql/src/test/results/clientpositive/perf/tez/query24.q.out index 43ece852757..bd065ae5b16 100644 --- ql/src/test/results/clientpositive/perf/tez/query24.q.out +++ ql/src/test/results/clientpositive/perf/tez/query24.q.out @@ -166,9 +166,9 @@ Stage-0 SHUFFLE [RS_81] PartitionCols:_col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 Group By Operator [GBY_80] (rows=576061174 width=932) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10"],aggregations:["sum(_col18)"],keys:_col11, _col12, _col1, _col5, _col7, _col20, _col21, _col22, _col23, _col24 + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10"],aggregations:["sum(_col17)"],keys:_col10, _col11, _col1, _col5, _col6, _col19, _col20, _col21, _col22, _col23 Merge Join Operator [MERGEJOIN_300] (rows=589731269 width=928) - Conds:RS_76._col14, _col17=RS_332._col0, _col1(Inner),Output:["_col1","_col5","_col7","_col11","_col12","_col18","_col20","_col21","_col22","_col23","_col24"] + Conds:RS_76._col13, _col16=RS_332._col0, _col1(Inner),Output:["_col1","_col5","_col6","_col10","_col11","_col17","_col19","_col20","_col21","_col22","_col23"] <-Map 23 [SIMPLE_EDGE] vectorized SHUFFLE [RS_332] PartitionCols:_col0, _col1 @@ -180,9 +180,9 @@ Stage-0 default@store_returns,store_returns,Tbl:COMPLETE,Col:COMPLETE,Output:["sr_item_sk","sr_ticket_number"] <-Reducer 9 [SIMPLE_EDGE] SHUFFLE [RS_76] - PartitionCols:_col14, _col17 + PartitionCols:_col13, _col16 Merge Join Operator [MERGEJOIN_299] (rows=576061174 width=936) - Conds:RS_73._col14=RS_308._col0(Inner),Output:["_col1","_col5","_col7","_col11","_col12","_col14","_col17","_col18","_col20","_col21","_col22","_col23","_col24"] + Conds:RS_73._col13=RS_308._col0(Inner),Output:["_col1","_col5","_col6","_col10","_col11","_col13","_col16","_col17","_col19","_col20","_col21","_col22","_col23"] <-Map 7 [SIMPLE_EDGE] vectorized SHUFFLE [RS_308] PartitionCols:_col0 @@ -194,16 +194,16 @@ Stage-0 default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_current_price","i_size","i_color","i_units","i_manager_id"] <-Reducer 18 [SIMPLE_EDGE] SHUFFLE [RS_73] - PartitionCols:_col14 + PartitionCols:_col13 Merge Join Operator [MERGEJOIN_298] (rows=576061174 width=555) - Conds:RS_70._col9, _col4=RS_344._col1, _col2(Inner),Output:["_col1","_col5","_col7","_col11","_col12","_col14","_col17","_col18"] + Conds:RS_70._col8, _col4=RS_344._col1, _col2(Inner),Output:["_col1","_col5","_col6","_col10","_col11","_col13","_col16","_col17"] <-Reducer 15 [SIMPLE_EDGE] SHUFFLE [RS_70] - PartitionCols:_col9, _col4 - Filter Operator [FIL_21] (rows=7276996 width=637) - predicate:(_col13 <> upper(_col3)) - Merge Join Operator [MERGEJOIN_293] (rows=7276996 width=637) - Conds:RS_18._col0=RS_321._col1(Inner),Output:["_col1","_col3","_col4","_col5","_col7","_col9","_col11","_col12","_col13"] + PartitionCols:_col8, _col4 + Filter Operator [FIL_21] (rows=7276996 width=724) + predicate:(_col12 <> _col3) + Merge Join Operator [MERGEJOIN_293] (rows=7276996 width=724) + Conds:RS_18._col0=RS_321._col1(Inner),Output:["_col1","_col3","_col4","_col5","_col6","_col8","_col10","_col11","_col12"] <-Map 22 [SIMPLE_EDGE] vectorized SHUFFLE [RS_321] PartitionCols:_col1 @@ -216,12 +216,12 @@ Stage-0 <-Reducer 14 [SIMPLE_EDGE] SHUFFLE [RS_18] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_292] (rows=611379 width=365) - Conds:RS_315._col2=RS_318._col4(Inner),Output:["_col0","_col1","_col3","_col4","_col5","_col7"] + Merge Join Operator [MERGEJOIN_292] (rows=611379 width=452) + Conds:RS_315._col2=RS_318._col3(Inner),Output:["_col0","_col1","_col3","_col4","_col5","_col6"] <-Map 13 [SIMPLE_EDGE] vectorized SHUFFLE [RS_315] PartitionCols:_col2 - Select Operator [SEL_314] (rows=40000000 width=276) + Select Operator [SEL_314] (rows=40000000 width=363) Output:["_col0","_col1","_col2","_col3"] Filter Operator [FIL_313] (rows=40000000 width=276) predicate:(ca_address_sk is not null and ca_zip is not null) @@ -229,9 +229,9 @@ Stage-0 default@customer_address,customer_address,Tbl:COMPLETE,Col:COMPLETE,Output:["ca_address_sk","ca_state","ca_zip","ca_country"] <-Map 21 [SIMPLE_EDGE] vectorized SHUFFLE [RS_318] - PartitionCols:_col4 - Select Operator [SEL_317] (rows=155 width=271) - Output:["_col0","_col1","_col3","_col4"] + PartitionCols:_col3 + Select Operator [SEL_317] (rows=155 width=267) + Output:["_col0","_col1","_col2","_col3"] Filter Operator [FIL_316] (rows=155 width=271) predicate:((s_market_id = 7) and s_store_sk is not null and s_zip is not null) TableScan [TS_9] (rows=1704 width=270) @@ -281,9 +281,9 @@ Stage-0 SHUFFLE [RS_37] PartitionCols:_col0, _col1, _col2 Group By Operator [GBY_36] (rows=84010488 width=843) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9"],aggregations:["sum(_col4)"],keys:_col13, _col14, _col21, _col6, _col7, _col9, _col10, _col17, _col23 + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9"],aggregations:["sum(_col4)"],keys:_col12, _col13, _col20, _col6, _col7, _col8, _col9, _col16, _col21 Merge Join Operator [MERGEJOIN_295] (rows=138508741 width=824) - Conds:RS_32._col0, _col3=RS_331._col0, _col1(Inner),Output:["_col4","_col6","_col7","_col9","_col10","_col13","_col14","_col17","_col21","_col23"] + Conds:RS_32._col0, _col3=RS_331._col0, _col1(Inner),Output:["_col4","_col6","_col7","_col8","_col9","_col12","_col13","_col16","_col20","_col21"] <-Map 23 [SIMPLE_EDGE] vectorized SHUFFLE [RS_331] PartitionCols:_col0, _col1 @@ -292,23 +292,23 @@ Stage-0 SHUFFLE [RS_32] PartitionCols:_col0, _col3 Merge Join Operator [MERGEJOIN_294] (rows=84010488 width=820) - Conds:RS_29._col1, _col2=RS_30._col0, _col9(Inner),Output:["_col0","_col3","_col4","_col6","_col7","_col9","_col10","_col13","_col14","_col17","_col21","_col23"] + Conds:RS_29._col1, _col2=RS_30._col0, _col9(Inner),Output:["_col0","_col3","_col4","_col6","_col7","_col8","_col9","_col12","_col13","_col16","_col20","_col21"] <-Reducer 15 [SIMPLE_EDGE] SHUFFLE [RS_30] PartitionCols:_col0, _col9 - Select Operator [SEL_22] (rows=7276996 width=637) - Output:["_col0","_col2","_col3","_col6","_col9","_col10","_col12"] + Select Operator [SEL_22] (rows=7276996 width=724) + Output:["_col0","_col2","_col3","_col6","_col9","_col10","_col11"] Please refer to the previous Filter Operator [FIL_21] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_29] PartitionCols:_col1, _col2 Merge Join Operator [MERGEJOIN_291] (rows=76612563 width=382) - Conds:RS_328._col0=RS_306._col0(Inner),Output:["_col0","_col1","_col2","_col3","_col4","_col6","_col7","_col9","_col10"] + Conds:RS_328._col0=RS_306._col0(Inner),Output:["_col0","_col1","_col2","_col3","_col4","_col6","_col7","_col8","_col9"] <-Map 7 [SIMPLE_EDGE] vectorized SHUFFLE [RS_306] PartitionCols:_col0 - Select Operator [SEL_304] (rows=7000 width=385) - Output:["_col0","_col1","_col2","_col4","_col5"] + Select Operator [SEL_304] (rows=7000 width=295) + Output:["_col0","_col1","_col2","_col3","_col4"] Filter Operator [FIL_302] (rows=7000 width=384) predicate:((i_color = 'orchid') and i_item_sk is not null) Please refer to the previous TableScan [TS_3] diff --git ql/src/test/results/clientpositive/perf/tez/query25.q.out ql/src/test/results/clientpositive/perf/tez/query25.q.out index 5d1c9fc1dfd..0a0cfcc4865 100644 --- ql/src/test/results/clientpositive/perf/tez/query25.q.out +++ ql/src/test/results/clientpositive/perf/tez/query25.q.out @@ -145,11 +145,11 @@ Stage-0 SHUFFLE [RS_49] PartitionCols:_col0, _col1, _col2, _col3 Group By Operator [GBY_48] (rows=4248052806 width=808) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"],aggregations:["sum(_col5)","sum(_col20)","sum(_col12)"],keys:_col25, _col26, _col28, _col29 + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"],aggregations:["sum(_col5)","sum(_col16)","sum(_col10)"],keys:_col19, _col20, _col22, _col23 Top N Key Operator [TNK_95] (rows=4248052806 width=807) - keys:_col25, _col26, _col28, _col29,sort order:++++,top n:100 + keys:_col19, _col20, _col22, _col23,sort order:++++,top n:100 Merge Join Operator [MERGEJOIN_214] (rows=4248052806 width=807) - Conds:RS_44._col3=RS_258._col0(Inner),Output:["_col5","_col12","_col20","_col25","_col26","_col28","_col29"] + Conds:RS_44._col3=RS_258._col0(Inner),Output:["_col5","_col10","_col16","_col19","_col20","_col22","_col23"] <-Map 21 [SIMPLE_EDGE] vectorized SHUFFLE [RS_258] PartitionCols:_col0 @@ -163,7 +163,7 @@ Stage-0 SHUFFLE [RS_44] PartitionCols:_col3 Merge Join Operator [MERGEJOIN_213] (rows=4248052806 width=623) - Conds:RS_41._col1=RS_255._col0(Inner),Output:["_col3","_col5","_col12","_col20","_col25","_col26"] + Conds:RS_41._col1=RS_255._col0(Inner),Output:["_col3","_col5","_col10","_col16","_col19","_col20"] <-Map 20 [SIMPLE_EDGE] vectorized SHUFFLE [RS_255] PartitionCols:_col0 @@ -177,12 +177,12 @@ Stage-0 SHUFFLE [RS_41] PartitionCols:_col1 Merge Join Operator [MERGEJOIN_212] (rows=4248052806 width=343) - Conds:RS_38._col1, _col2, _col4=RS_39._col8, _col9, _col10(Inner),Output:["_col1","_col3","_col5","_col12","_col20"] + Conds:RS_38._col1, _col2, _col4=RS_39._col6, _col7, _col8(Inner),Output:["_col1","_col3","_col5","_col10","_col16"] <-Reducer 11 [SIMPLE_EDGE] SHUFFLE [RS_39] - PartitionCols:_col8, _col9, _col10 + PartitionCols:_col6, _col7, _col8 Merge Join Operator [MERGEJOIN_211] (rows=1893811716 width=235) - Conds:RS_25._col2, _col1=RS_26._col1, _col2(Inner),Output:["_col3","_col8","_col9","_col10","_col11"] + Conds:RS_25._col2, _col1=RS_26._col1, _col2(Inner),Output:["_col3","_col6","_col7","_col8","_col9"] <-Reducer 10 [SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_25] PartitionCols:_col2, _col1 @@ -191,7 +191,7 @@ Stage-0 <-Map 8 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_223] PartitionCols:_col0 - Select Operator [SEL_219] (rows=351 width=12) + Select Operator [SEL_219] (rows=351 width=4) Output:["_col0"] Filter Operator [FIL_216] (rows=351 width=12) predicate:((d_year = 2000) and d_date_sk is not null and d_moy BETWEEN 4 AND 10) @@ -221,7 +221,7 @@ Stage-0 <-Map 8 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_225] PartitionCols:_col0 - Select Operator [SEL_220] (rows=351 width=12) + Select Operator [SEL_220] (rows=351 width=4) Output:["_col0"] Filter Operator [FIL_217] (rows=351 width=12) predicate:((d_year = 2000) and d_date_sk is not null and d_moy BETWEEN 4 AND 10) @@ -269,7 +269,7 @@ Stage-0 <-Map 8 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_221] PartitionCols:_col0 - Select Operator [SEL_218] (rows=50 width=12) + Select Operator [SEL_218] (rows=50 width=4) Output:["_col0"] Filter Operator [FIL_215] (rows=50 width=12) predicate:((d_moy = 4) and (d_year = 2000) and d_date_sk is not null) diff --git ql/src/test/results/clientpositive/perf/tez/query26.q.out ql/src/test/results/clientpositive/perf/tez/query26.q.out index 7c42069758b..62bcbe8b095 100644 --- ql/src/test/results/clientpositive/perf/tez/query26.q.out +++ ql/src/test/results/clientpositive/perf/tez/query26.q.out @@ -83,11 +83,11 @@ Stage-0 SHUFFLE [RS_29] PartitionCols:_col0 Group By Operator [GBY_28] (rows=462000 width=476) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"],aggregations:["sum(_col4)","count(_col4)","sum(_col5)","count(_col5)","sum(_col7)","count(_col7)","sum(_col6)","count(_col6)"],keys:_col18 + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"],aggregations:["sum(_col4)","count(_col4)","sum(_col5)","count(_col5)","sum(_col7)","count(_col7)","sum(_col6)","count(_col6)"],keys:_col12 Top N Key Operator [TNK_55] (rows=809521 width=100) - keys:_col18,sort order:+,top n:100 + keys:_col12,sort order:+,top n:100 Merge Join Operator [MERGEJOIN_99] (rows=809521 width=100) - Conds:RS_24._col2=RS_124._col0(Inner),Output:["_col4","_col5","_col6","_col7","_col18"] + Conds:RS_24._col2=RS_124._col0(Inner),Output:["_col4","_col5","_col6","_col7","_col12"] <-Map 13 [SIMPLE_EDGE] vectorized SHUFFLE [RS_124] PartitionCols:_col0 @@ -105,7 +105,7 @@ Stage-0 <-Map 12 [SIMPLE_EDGE] vectorized SHUFFLE [RS_121] PartitionCols:_col0 - Select Operator [SEL_120] (rows=2300 width=174) + Select Operator [SEL_120] (rows=2300 width=4) Output:["_col0"] Filter Operator [FIL_119] (rows=2300 width=174) predicate:(((p_channel_email = 'N') or (p_channel_event = 'N')) and p_promo_sk is not null) @@ -119,7 +119,7 @@ Stage-0 <-Map 10 [SIMPLE_EDGE] vectorized SHUFFLE [RS_110] PartitionCols:_col0 - Select Operator [SEL_109] (rows=652 width=8) + Select Operator [SEL_109] (rows=652 width=4) Output:["_col0"] Filter Operator [FIL_108] (rows=652 width=8) predicate:((d_year = 1998) and d_date_sk is not null) @@ -133,7 +133,7 @@ Stage-0 <-Map 8 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_102] PartitionCols:_col0 - Select Operator [SEL_101] (rows=14776 width=265) + Select Operator [SEL_101] (rows=14776 width=4) Output:["_col0"] Filter Operator [FIL_100] (rows=14776 width=268) predicate:((cd_education_status = 'Primary') and (cd_gender = 'F') and (cd_marital_status = 'W') and cd_demo_sk is not null) diff --git ql/src/test/results/clientpositive/perf/tez/query27.q.out ql/src/test/results/clientpositive/perf/tez/query27.q.out index 59cca4f94f4..d7fd2eda677 100644 --- ql/src/test/results/clientpositive/perf/tez/query27.q.out +++ ql/src/test/results/clientpositive/perf/tez/query27.q.out @@ -94,7 +94,7 @@ Stage-0 Select Operator [SEL_27] (rows=1427275 width=186) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] Merge Join Operator [MERGEJOIN_100] (rows=1427275 width=186) - Conds:RS_24._col1=RS_130._col0(Inner),Output:["_col4","_col5","_col6","_col7","_col15","_col17"] + Conds:RS_24._col1=RS_130._col0(Inner),Output:["_col4","_col5","_col6","_col7","_col11","_col13"] <-Map 14 [SIMPLE_EDGE] vectorized SHUFFLE [RS_130] PartitionCols:_col0 @@ -108,7 +108,7 @@ Stage-0 SHUFFLE [RS_24] PartitionCols:_col1 Merge Join Operator [MERGEJOIN_99] (rows=1427275 width=90) - Conds:RS_21._col3=RS_119._col0(Inner),Output:["_col1","_col4","_col5","_col6","_col7","_col15"] + Conds:RS_21._col3=RS_119._col0(Inner),Output:["_col1","_col4","_col5","_col6","_col7","_col11"] <-Map 12 [SIMPLE_EDGE] vectorized SHUFFLE [RS_119] PartitionCols:_col0 @@ -126,7 +126,7 @@ Stage-0 <-Map 10 [SIMPLE_EDGE] vectorized SHUFFLE [RS_111] PartitionCols:_col0 - Select Operator [SEL_110] (rows=652 width=8) + Select Operator [SEL_110] (rows=652 width=4) Output:["_col0"] Filter Operator [FIL_109] (rows=652 width=8) predicate:((d_year = 2001) and d_date_sk is not null) @@ -140,7 +140,7 @@ Stage-0 <-Map 8 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_103] PartitionCols:_col0 - Select Operator [SEL_102] (rows=14776 width=269) + Select Operator [SEL_102] (rows=14776 width=4) Output:["_col0"] Filter Operator [FIL_101] (rows=14776 width=268) predicate:((cd_education_status = '2 yr Degree') and (cd_gender = 'M') and (cd_marital_status = 'U') and cd_demo_sk is not null) diff --git ql/src/test/results/clientpositive/perf/tez/query29.q.out ql/src/test/results/clientpositive/perf/tez/query29.q.out index a21c3c789e3..19f121e29bd 100644 --- ql/src/test/results/clientpositive/perf/tez/query29.q.out +++ ql/src/test/results/clientpositive/perf/tez/query29.q.out @@ -144,20 +144,20 @@ Stage-0 SHUFFLE [RS_49] PartitionCols:_col0, _col1, _col2, _col3 Group By Operator [GBY_48] (rows=21091879 width=496) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"],aggregations:["sum(_col14)","sum(_col22)","sum(_col3)"],keys:_col7, _col8, _col27, _col28 + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"],aggregations:["sum(_col13)","sum(_col19)","sum(_col3)"],keys:_col6, _col7, _col22, _col23 Top N Key Operator [TNK_93] (rows=4156223234 width=483) - keys:_col7, _col8, _col27, _col28,sort order:++++,top n:100 + keys:_col6, _col7, _col22, _col23,sort order:++++,top n:100 Merge Join Operator [MERGEJOIN_205] (rows=4156223234 width=483) - Conds:RS_44._col1, _col2=RS_45._col14, _col13(Inner),Output:["_col3","_col7","_col8","_col14","_col22","_col27","_col28"] + Conds:RS_44._col2, _col1=RS_45._col11, _col12(Inner),Output:["_col3","_col6","_col7","_col13","_col19","_col22","_col23"] <-Reducer 2 [SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_44] - PartitionCols:_col1, _col2 + PartitionCols:_col2, _col1 Merge Join Operator [MERGEJOIN_199] (rows=7638375 width=10) Conds:RS_216._col0=RS_208._col0(Inner),Output:["_col1","_col2","_col3"] <-Map 8 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_208] PartitionCols:_col0 - Select Operator [SEL_207] (rows=1957 width=8) + Select Operator [SEL_207] (rows=1957 width=4) Output:["_col0"] Filter Operator [FIL_206] (rows=1957 width=8) predicate:((d_year) IN (1999, 2000, 2001) and d_date_sk is not null) @@ -185,11 +185,11 @@ Stage-0 Please refer to the previous Select Operator [SEL_207] <-Reducer 14 [SIMPLE_EDGE] SHUFFLE [RS_45] - PartitionCols:_col14, _col13 + PartitionCols:_col11, _col12 Select Operator [SEL_40] (rows=21091879 width=484) - Output:["_col1","_col2","_col8","_col13","_col14","_col16","_col21","_col22"] + Output:["_col1","_col2","_col8","_col11","_col12","_col14","_col17","_col18"] Merge Join Operator [MERGEJOIN_204] (rows=21091879 width=484) - Conds:RS_37._col3=RS_249._col0(Inner),Output:["_col5","_col10","_col11","_col13","_col18","_col19","_col21","_col22"] + Conds:RS_37._col3=RS_249._col0(Inner),Output:["_col5","_col8","_col9","_col11","_col14","_col15","_col17","_col18"] <-Map 23 [SIMPLE_EDGE] vectorized SHUFFLE [RS_249] PartitionCols:_col0 @@ -203,7 +203,7 @@ Stage-0 SHUFFLE [RS_37] PartitionCols:_col3 Merge Join Operator [MERGEJOIN_203] (rows=21091879 width=298) - Conds:RS_34._col1=RS_246._col0(Inner),Output:["_col3","_col5","_col10","_col11","_col13","_col18","_col19"] + Conds:RS_34._col1=RS_246._col0(Inner),Output:["_col3","_col5","_col8","_col9","_col11","_col14","_col15"] <-Map 22 [SIMPLE_EDGE] vectorized SHUFFLE [RS_246] PartitionCols:_col0 @@ -217,7 +217,7 @@ Stage-0 SHUFFLE [RS_34] PartitionCols:_col1 Merge Join Operator [MERGEJOIN_202] (rows=21091879 width=18) - Conds:RS_31._col1, _col2, _col4=RS_32._col1, _col2, _col3(Inner),Output:["_col1","_col3","_col5","_col10","_col11","_col13"] + Conds:RS_31._col1, _col2, _col4=RS_32._col1, _col2, _col3(Inner),Output:["_col1","_col3","_col5","_col8","_col9","_col11"] <-Reducer 17 [SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_32] PartitionCols:_col1, _col2, _col3 @@ -226,7 +226,7 @@ Stage-0 <-Map 15 [SIMPLE_EDGE] vectorized SHUFFLE [RS_223] PartitionCols:_col0 - Select Operator [SEL_220] (rows=201 width=12) + Select Operator [SEL_220] (rows=201 width=4) Output:["_col0"] Filter Operator [FIL_218] (rows=201 width=12) predicate:((d_year = 1999) and d_date_sk is not null and d_moy BETWEEN 4 AND 7) @@ -249,7 +249,7 @@ Stage-0 <-Map 15 [SIMPLE_EDGE] vectorized SHUFFLE [RS_221] PartitionCols:_col0 - Select Operator [SEL_219] (rows=50 width=12) + Select Operator [SEL_219] (rows=50 width=4) Output:["_col0"] Filter Operator [FIL_217] (rows=50 width=12) predicate:((d_moy = 4) and (d_year = 1999) and d_date_sk is not null) @@ -315,7 +315,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_146] Group By Operator [GBY_145] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_144] (rows=7638375 width=6) + Select Operator [SEL_144] (rows=7638375 width=8) Output:["_col0"] Please refer to the previous Merge Join Operator [MERGEJOIN_199] <-Reducer 7 [BROADCAST_EDGE] vectorized @@ -326,7 +326,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_151] Group By Operator [GBY_150] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_149] (rows=7638375 width=8) + Select Operator [SEL_149] (rows=7638375 width=6) Output:["_col0"] Please refer to the previous Merge Join Operator [MERGEJOIN_199] diff --git ql/src/test/results/clientpositive/perf/tez/query3.q.out ql/src/test/results/clientpositive/perf/tez/query3.q.out index d4296cf3b23..e31c9948397 100644 --- ql/src/test/results/clientpositive/perf/tez/query3.q.out +++ ql/src/test/results/clientpositive/perf/tez/query3.q.out @@ -75,13 +75,13 @@ Stage-0 SHUFFLE [RS_17] PartitionCols:_col0, _col1, _col2 Group By Operator [GBY_16] (rows=274400 width=220) - Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(_col2)"],keys:_col8, _col4, _col5 + Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(_col2)"],keys:_col7, _col4, _col5 Merge Join Operator [MERGEJOIN_53] (rows=589741 width=108) - Conds:RS_12._col0=RS_64._col0(Inner),Output:["_col2","_col4","_col5","_col8"] + Conds:RS_12._col0=RS_64._col0(Inner),Output:["_col2","_col4","_col5","_col7"] <-Map 8 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_64] PartitionCols:_col0 - Select Operator [SEL_63] (rows=5619 width=12) + Select Operator [SEL_63] (rows=5619 width=8) Output:["_col0","_col1"] Filter Operator [FIL_62] (rows=5619 width=12) predicate:((d_moy = 12) and d_date_sk is not null) @@ -95,7 +95,7 @@ Stage-0 <-Map 6 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_56] PartitionCols:_col0 - Select Operator [SEL_55] (rows=669 width=111) + Select Operator [SEL_55] (rows=669 width=107) Output:["_col0","_col1","_col2"] Filter Operator [FIL_54] (rows=669 width=111) predicate:((i_manufact_id = 436) and i_item_sk is not null) diff --git ql/src/test/results/clientpositive/perf/tez/query30.q.out ql/src/test/results/clientpositive/perf/tez/query30.q.out index 9f9559e1e49..d3381b3b8f6 100644 --- ql/src/test/results/clientpositive/perf/tez/query30.q.out +++ ql/src/test/results/clientpositive/perf/tez/query30.q.out @@ -97,7 +97,7 @@ Stage-0 Select Operator [SEL_62] (rows=691171 width=942) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12"] Merge Join Operator [MERGEJOIN_177] (rows=691171 width=942) - Conds:RS_59._col0=RS_60._col0(Inner),Output:["_col1","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col18"] + Conds:RS_59._col0=RS_60._col0(Inner),Output:["_col1","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col17"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_59] PartitionCols:_col0 @@ -106,7 +106,7 @@ Stage-0 <-Map 5 [SIMPLE_EDGE] vectorized SHUFFLE [RS_187] PartitionCols:_col0 - Select Operator [SEL_184] (rows=784314 width=90) + Select Operator [SEL_184] (rows=784314 width=4) Output:["_col0"] Filter Operator [FIL_181] (rows=784314 width=90) predicate:((ca_state = 'IL') and ca_address_sk is not null) @@ -145,9 +145,9 @@ Stage-0 SHUFFLE [RS_43] PartitionCols:_col0 Group By Operator [GBY_42] (rows=3923529 width=201) - Output:["_col0","_col1","_col2"],aggregations:["sum(_col3)"],keys:_col7, _col1 + Output:["_col0","_col1","_col2"],aggregations:["sum(_col3)"],keys:_col6, _col1 Merge Join Operator [MERGEJOIN_175] (rows=3923529 width=184) - Conds:RS_38._col2=RS_189._col0(Inner),Output:["_col1","_col3","_col7"] + Conds:RS_38._col2=RS_189._col0(Inner),Output:["_col1","_col3","_col6"] <-Map 5 [SIMPLE_EDGE] vectorized SHUFFLE [RS_189] PartitionCols:_col0 @@ -173,7 +173,7 @@ Stage-0 <-Map 14 [SIMPLE_EDGE] vectorized SHUFFLE [RS_199] PartitionCols:_col0 - Select Operator [SEL_197] (rows=652 width=8) + Select Operator [SEL_197] (rows=652 width=4) Output:["_col0"] Filter Operator [FIL_196] (rows=652 width=8) predicate:((d_year = 2002) and d_date_sk is not null) @@ -190,9 +190,9 @@ Stage-0 SHUFFLE [RS_23] PartitionCols:_col0, _col1 Group By Operator [GBY_22] (rows=3746772 width=201) - Output:["_col0","_col1","_col2"],aggregations:["sum(_col3)"],keys:_col7, _col1 + Output:["_col0","_col1","_col2"],aggregations:["sum(_col3)"],keys:_col6, _col1 Merge Join Operator [MERGEJOIN_173] (rows=3746772 width=184) - Conds:RS_18._col2=RS_188._col0(Inner),Output:["_col1","_col3","_col7"] + Conds:RS_18._col2=RS_188._col0(Inner),Output:["_col1","_col3","_col6"] <-Map 5 [SIMPLE_EDGE] vectorized SHUFFLE [RS_188] PartitionCols:_col0 diff --git ql/src/test/results/clientpositive/perf/tez/query31.q.out ql/src/test/results/clientpositive/perf/tez/query31.q.out index 32d06b6db15..c0762b7bd47 100644 --- ql/src/test/results/clientpositive/perf/tez/query31.q.out +++ ql/src/test/results/clientpositive/perf/tez/query31.q.out @@ -157,32 +157,32 @@ Stage-0 File Output Operator [FS_139] Select Operator [SEL_138] (rows=110 width=550) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - Filter Operator [FIL_136] (rows=110 width=770) - predicate:(CASE WHEN ((_col1 > 0)) THEN (CASE WHEN ((_col9 > 0)) THEN (((_col11 / _col9) > (_col5 / _col1))) ELSE ((null > (_col5 / _col1))) END) ELSE (CASE WHEN ((_col9 > 0)) THEN (((_col11 / _col9) > null)) ELSE (null) END) END and CASE WHEN ((_col3 > 0)) THEN (CASE WHEN ((_col7 > 0)) THEN (((_col9 / _col7) > (_col1 / _col3))) ELSE ((null > (_col1 / _col3))) END) ELSE (CASE WHEN ((_col7 > 0)) THEN (((_col9 / _col7) > null)) ELSE (null) END) END) - Merge Join Operator [MERGEJOIN_450] (rows=440 width=770) - Conds:RS_133._col0=RS_134._col0(Inner),Output:["_col0","_col1","_col3","_col5","_col7","_col9","_col11"] + Filter Operator [FIL_136] (rows=110 width=778) + predicate:(CASE WHEN ((_col11 > 0)) THEN (CASE WHEN (_col2) THEN (((_col6 / _col1) > (_col9 / _col11))) ELSE ((null > (_col9 / _col11))) END) ELSE (CASE WHEN (_col2) THEN (((_col6 / _col1) > null)) ELSE (null) END) END and CASE WHEN ((_col9 > 0)) THEN (CASE WHEN (_col7) THEN (((_col4 / _col6) > (_col13 / _col9))) ELSE ((null > (_col13 / _col9))) END) ELSE (CASE WHEN (_col7) THEN (((_col4 / _col6) > null)) ELSE (null) END) END) + Merge Join Operator [MERGEJOIN_450] (rows=440 width=778) + Conds:RS_133._col0=RS_134._col0(Inner),Output:["_col1","_col2","_col4","_col6","_col7","_col8","_col9","_col11","_col13"] <-Reducer 22 [ONE_TO_ONE_EDGE] FORWARD [RS_134] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_449] (rows=440 width=434) - Conds:RS_123._col0=RS_536._col0(Inner),Output:["_col0","_col1","_col3","_col5"] + Merge Join Operator [MERGEJOIN_448] (rows=1605 width=434) + Conds:RS_123._col0=RS_538._col0(Inner),Output:["_col0","_col1","_col3","_col5"] <-Reducer 21 [ONE_TO_ONE_EDGE] FORWARD [RS_123] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_448] (rows=440 width=322) - Conds:RS_522._col0=RS_529._col0(Inner),Output:["_col0","_col1","_col3"] + Merge Join Operator [MERGEJOIN_447] (rows=1605 width=322) + Conds:RS_524._col0=RS_531._col0(Inner),Output:["_col0","_col1","_col3"] <-Reducer 20 [ONE_TO_ONE_EDGE] vectorized - FORWARD [RS_522] + FORWARD [RS_524] PartitionCols:_col0 - Group By Operator [GBY_521] (rows=440 width=210) + Group By Operator [GBY_523] (rows=1605 width=210) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 <-Reducer 19 [SIMPLE_EDGE] SHUFFLE [RS_77] PartitionCols:_col0 - Group By Operator [GBY_76] (rows=3960 width=210) - Output:["_col0","_col1"],aggregations:["sum(_col2)"],keys:_col7 - Merge Join Operator [MERGEJOIN_441] (rows=10246882 width=209) - Conds:RS_72._col1=RS_497._col0(Inner),Output:["_col2","_col7"] + Group By Operator [GBY_76] (rows=33705 width=210) + Output:["_col0","_col1"],aggregations:["sum(_col2)"],keys:_col5 + Merge Join Operator [MERGEJOIN_441] (rows=37399561 width=139) + Conds:RS_72._col1=RS_497._col0(Inner),Output:["_col2","_col5"] <-Map 32 [SIMPLE_EDGE] vectorized SHUFFLE [RS_497] PartitionCols:_col0 @@ -195,29 +195,29 @@ Stage-0 <-Reducer 18 [SIMPLE_EDGE] SHUFFLE [RS_72] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_440] (rows=10246882 width=115) - Conds:RS_520._col0=RS_469._col0(Inner),Output:["_col1","_col2"] + Merge Join Operator [MERGEJOIN_440] (rows=37399561 width=42) + Conds:RS_522._col0=RS_469._col0(Inner),Output:["_col1","_col2"] <-Map 8 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_469] PartitionCols:_col0 - Select Operator [SEL_460] (rows=130 width=12) + Select Operator [SEL_460] (rows=130 width=4) Output:["_col0"] Filter Operator [FIL_454] (rows=130 width=12) - predicate:((d_qoy = 1) and (d_year = 2000) and d_date_sk is not null) + predicate:((d_qoy = 2) and (d_year = 2000) and d_date_sk is not null) TableScan [TS_3] (rows=73049 width=12) default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year","d_qoy"] <-Map 35 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_520] + SHUFFLE [RS_522] PartitionCols:_col0 - Select Operator [SEL_519] (rows=143931246 width=119) + Select Operator [SEL_521] (rows=525327191 width=114) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_518] (rows=143931246 width=119) - predicate:((ws_sold_date_sk BETWEEN DynamicValue(RS_70_date_dim_d_date_sk_min) AND DynamicValue(RS_70_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_70_date_dim_d_date_sk_bloom_filter))) and ws_bill_addr_sk is not null and ws_sold_date_sk is not null) - TableScan [TS_60] (rows=144002668 width=119) - default@web_sales,web_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_sold_date_sk","ws_bill_addr_sk","ws_ext_sales_price"] + Filter Operator [FIL_520] (rows=525327191 width=114) + predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_70_date_dim_d_date_sk_min) AND DynamicValue(RS_70_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_70_date_dim_d_date_sk_bloom_filter))) and ss_addr_sk is not null and ss_sold_date_sk is not null) + TableScan [TS_60] (rows=575995635 width=114) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_addr_sk","ss_ext_sales_price"] <-Reducer 23 [BROADCAST_EDGE] vectorized - BROADCAST [RS_517] - Group By Operator [GBY_516] (rows=1 width=12) + BROADCAST [RS_519] + Group By Operator [GBY_518] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Map 8 [CUSTOM_SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_484] @@ -227,17 +227,17 @@ Stage-0 Output:["_col0"] Please refer to the previous Select Operator [SEL_460] <-Reducer 26 [ONE_TO_ONE_EDGE] vectorized - FORWARD [RS_529] + FORWARD [RS_531] PartitionCols:_col0 - Group By Operator [GBY_528] (rows=440 width=210) + Group By Operator [GBY_530] (rows=1605 width=210) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 <-Reducer 25 [SIMPLE_EDGE] SHUFFLE [RS_97] PartitionCols:_col0 - Group By Operator [GBY_96] (rows=3960 width=210) - Output:["_col0","_col1"],aggregations:["sum(_col2)"],keys:_col7 - Merge Join Operator [MERGEJOIN_443] (rows=10246882 width=209) - Conds:RS_92._col1=RS_498._col0(Inner),Output:["_col2","_col7"] + Group By Operator [GBY_96] (rows=33705 width=210) + Output:["_col0","_col1"],aggregations:["sum(_col2)"],keys:_col5 + Merge Join Operator [MERGEJOIN_443] (rows=37399561 width=139) + Conds:RS_92._col1=RS_498._col0(Inner),Output:["_col2","_col5"] <-Map 32 [SIMPLE_EDGE] vectorized SHUFFLE [RS_498] PartitionCols:_col0 @@ -245,28 +245,28 @@ Stage-0 <-Reducer 24 [SIMPLE_EDGE] SHUFFLE [RS_92] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_442] (rows=10246882 width=115) - Conds:RS_527._col0=RS_471._col0(Inner),Output:["_col1","_col2"] + Merge Join Operator [MERGEJOIN_442] (rows=37399561 width=42) + Conds:RS_529._col0=RS_471._col0(Inner),Output:["_col1","_col2"] <-Map 8 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_471] PartitionCols:_col0 - Select Operator [SEL_461] (rows=130 width=12) + Select Operator [SEL_461] (rows=130 width=4) Output:["_col0"] Filter Operator [FIL_455] (rows=130 width=12) - predicate:((d_qoy = 2) and (d_year = 2000) and d_date_sk is not null) + predicate:((d_qoy = 1) and (d_year = 2000) and d_date_sk is not null) Please refer to the previous TableScan [TS_3] <-Map 36 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_527] + SHUFFLE [RS_529] PartitionCols:_col0 - Select Operator [SEL_526] (rows=143931246 width=119) + Select Operator [SEL_528] (rows=525327191 width=114) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_525] (rows=143931246 width=119) - predicate:((ws_sold_date_sk BETWEEN DynamicValue(RS_90_date_dim_d_date_sk_min) AND DynamicValue(RS_90_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_90_date_dim_d_date_sk_bloom_filter))) and ws_bill_addr_sk is not null and ws_sold_date_sk is not null) - TableScan [TS_80] (rows=144002668 width=119) - default@web_sales,web_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_sold_date_sk","ws_bill_addr_sk","ws_ext_sales_price"] + Filter Operator [FIL_527] (rows=525327191 width=114) + predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_90_date_dim_d_date_sk_min) AND DynamicValue(RS_90_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_90_date_dim_d_date_sk_bloom_filter))) and ss_addr_sk is not null and ss_sold_date_sk is not null) + TableScan [TS_80] (rows=575995635 width=114) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_addr_sk","ss_ext_sales_price"] <-Reducer 27 [BROADCAST_EDGE] vectorized - BROADCAST [RS_524] - Group By Operator [GBY_523] (rows=1 width=12) + BROADCAST [RS_526] + Group By Operator [GBY_525] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Map 8 [CUSTOM_SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_485] @@ -276,17 +276,17 @@ Stage-0 Output:["_col0"] Please refer to the previous Select Operator [SEL_461] <-Reducer 30 [ONE_TO_ONE_EDGE] vectorized - FORWARD [RS_536] + FORWARD [RS_538] PartitionCols:_col0 - Group By Operator [GBY_535] (rows=440 width=210) + Group By Operator [GBY_537] (rows=1605 width=210) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 <-Reducer 29 [SIMPLE_EDGE] SHUFFLE [RS_117] PartitionCols:_col0 - Group By Operator [GBY_116] (rows=3960 width=210) - Output:["_col0","_col1"],aggregations:["sum(_col2)"],keys:_col7 - Merge Join Operator [MERGEJOIN_445] (rows=10246882 width=209) - Conds:RS_112._col1=RS_499._col0(Inner),Output:["_col2","_col7"] + Group By Operator [GBY_116] (rows=33705 width=210) + Output:["_col0","_col1"],aggregations:["sum(_col2)"],keys:_col5 + Merge Join Operator [MERGEJOIN_445] (rows=37399561 width=139) + Conds:RS_112._col1=RS_499._col0(Inner),Output:["_col2","_col5"] <-Map 32 [SIMPLE_EDGE] vectorized SHUFFLE [RS_499] PartitionCols:_col0 @@ -294,28 +294,28 @@ Stage-0 <-Reducer 28 [SIMPLE_EDGE] SHUFFLE [RS_112] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_444] (rows=10246882 width=115) - Conds:RS_534._col0=RS_473._col0(Inner),Output:["_col1","_col2"] + Merge Join Operator [MERGEJOIN_444] (rows=37399561 width=42) + Conds:RS_536._col0=RS_473._col0(Inner),Output:["_col1","_col2"] <-Map 8 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_473] PartitionCols:_col0 - Select Operator [SEL_462] (rows=130 width=12) + Select Operator [SEL_462] (rows=130 width=4) Output:["_col0"] Filter Operator [FIL_456] (rows=130 width=12) predicate:((d_qoy = 3) and (d_year = 2000) and d_date_sk is not null) Please refer to the previous TableScan [TS_3] <-Map 37 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_534] + SHUFFLE [RS_536] PartitionCols:_col0 - Select Operator [SEL_533] (rows=143931246 width=119) + Select Operator [SEL_535] (rows=525327191 width=114) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_532] (rows=143931246 width=119) - predicate:((ws_sold_date_sk BETWEEN DynamicValue(RS_110_date_dim_d_date_sk_min) AND DynamicValue(RS_110_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_110_date_dim_d_date_sk_bloom_filter))) and ws_bill_addr_sk is not null and ws_sold_date_sk is not null) - TableScan [TS_100] (rows=144002668 width=119) - default@web_sales,web_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_sold_date_sk","ws_bill_addr_sk","ws_ext_sales_price"] + Filter Operator [FIL_534] (rows=525327191 width=114) + predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_110_date_dim_d_date_sk_min) AND DynamicValue(RS_110_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_110_date_dim_d_date_sk_bloom_filter))) and ss_addr_sk is not null and ss_sold_date_sk is not null) + TableScan [TS_100] (rows=575995635 width=114) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_addr_sk","ss_ext_sales_price"] <-Reducer 31 [BROADCAST_EDGE] vectorized - BROADCAST [RS_531] - Group By Operator [GBY_530] (rows=1 width=12) + BROADCAST [RS_533] + Group By Operator [GBY_532] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Map 8 [CUSTOM_SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_486] @@ -327,74 +327,76 @@ Stage-0 <-Reducer 6 [ONE_TO_ONE_EDGE] FORWARD [RS_133] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_447] (rows=1605 width=434) - Conds:RS_130._col0=RS_515._col0(Inner),Output:["_col0","_col1","_col3","_col5"] + Merge Join Operator [MERGEJOIN_449] (rows=440 width=442) + Conds:RS_130._col0=RS_517._col0(Inner),Output:["_col0","_col1","_col2","_col4","_col6","_col7"] <-Reducer 16 [ONE_TO_ONE_EDGE] vectorized - FORWARD [RS_515] + FORWARD [RS_517] PartitionCols:_col0 - Group By Operator [GBY_514] (rows=1605 width=210) - Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 - <-Reducer 15 [SIMPLE_EDGE] - SHUFFLE [RS_57] - PartitionCols:_col0 - Group By Operator [GBY_56] (rows=33705 width=210) - Output:["_col0","_col1"],aggregations:["sum(_col2)"],keys:_col7 - Merge Join Operator [MERGEJOIN_439] (rows=37399561 width=139) - Conds:RS_52._col1=RS_496._col0(Inner),Output:["_col2","_col7"] - <-Map 32 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_496] - PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_493] - <-Reducer 14 [SIMPLE_EDGE] - SHUFFLE [RS_52] - PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_438] (rows=37399561 width=42) - Conds:RS_513._col0=RS_467._col0(Inner),Output:["_col1","_col2"] - <-Map 8 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_467] - PartitionCols:_col0 - Select Operator [SEL_459] (rows=130 width=12) - Output:["_col0"] - Filter Operator [FIL_453] (rows=130 width=12) - predicate:((d_qoy = 3) and (d_year = 2000) and d_date_sk is not null) - Please refer to the previous TableScan [TS_3] - <-Map 34 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_513] - PartitionCols:_col0 - Select Operator [SEL_512] (rows=525327191 width=114) - Output:["_col0","_col1","_col2"] - Filter Operator [FIL_511] (rows=525327191 width=114) - predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_50_date_dim_d_date_sk_min) AND DynamicValue(RS_50_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_50_date_dim_d_date_sk_bloom_filter))) and ss_addr_sk is not null and ss_sold_date_sk is not null) - TableScan [TS_40] (rows=575995635 width=114) - default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_addr_sk","ss_ext_sales_price"] - <-Reducer 17 [BROADCAST_EDGE] vectorized - BROADCAST [RS_510] - Group By Operator [GBY_509] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 8 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_483] - Group By Operator [GBY_477] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_468] (rows=130 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_459] + Select Operator [SEL_516] (rows=440 width=214) + Output:["_col0","_col1","_col2"] + Group By Operator [GBY_515] (rows=440 width=210) + Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 + <-Reducer 15 [SIMPLE_EDGE] + SHUFFLE [RS_57] + PartitionCols:_col0 + Group By Operator [GBY_56] (rows=3960 width=210) + Output:["_col0","_col1"],aggregations:["sum(_col2)"],keys:_col5 + Merge Join Operator [MERGEJOIN_439] (rows=10246882 width=209) + Conds:RS_52._col1=RS_496._col0(Inner),Output:["_col2","_col5"] + <-Map 32 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_496] + PartitionCols:_col0 + Please refer to the previous Select Operator [SEL_493] + <-Reducer 14 [SIMPLE_EDGE] + SHUFFLE [RS_52] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_438] (rows=10246882 width=115) + Conds:RS_514._col0=RS_467._col0(Inner),Output:["_col1","_col2"] + <-Map 8 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_467] + PartitionCols:_col0 + Select Operator [SEL_459] (rows=130 width=4) + Output:["_col0"] + Filter Operator [FIL_453] (rows=130 width=12) + predicate:((d_qoy = 2) and (d_year = 2000) and d_date_sk is not null) + Please refer to the previous TableScan [TS_3] + <-Map 34 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_514] + PartitionCols:_col0 + Select Operator [SEL_513] (rows=143931246 width=119) + Output:["_col0","_col1","_col2"] + Filter Operator [FIL_512] (rows=143931246 width=119) + predicate:((ws_sold_date_sk BETWEEN DynamicValue(RS_50_date_dim_d_date_sk_min) AND DynamicValue(RS_50_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_50_date_dim_d_date_sk_bloom_filter))) and ws_bill_addr_sk is not null and ws_sold_date_sk is not null) + TableScan [TS_40] (rows=144002668 width=119) + default@web_sales,web_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_sold_date_sk","ws_bill_addr_sk","ws_ext_sales_price"] + <-Reducer 17 [BROADCAST_EDGE] vectorized + BROADCAST [RS_511] + Group By Operator [GBY_510] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 8 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_483] + Group By Operator [GBY_477] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_468] (rows=130 width=4) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_459] <-Reducer 5 [ONE_TO_ONE_EDGE] FORWARD [RS_130] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_446] (rows=1605 width=322) - Conds:RS_501._col0=RS_508._col0(Inner),Output:["_col0","_col1","_col3"] + Merge Join Operator [MERGEJOIN_446] (rows=440 width=326) + Conds:RS_502._col0=RS_509._col0(Inner),Output:["_col0","_col1","_col2","_col4"] <-Reducer 12 [ONE_TO_ONE_EDGE] vectorized - FORWARD [RS_508] + FORWARD [RS_509] PartitionCols:_col0 - Group By Operator [GBY_507] (rows=1605 width=210) + Group By Operator [GBY_508] (rows=440 width=210) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 <-Reducer 11 [SIMPLE_EDGE] SHUFFLE [RS_37] PartitionCols:_col0 - Group By Operator [GBY_36] (rows=33705 width=210) - Output:["_col0","_col1"],aggregations:["sum(_col2)"],keys:_col7 - Merge Join Operator [MERGEJOIN_437] (rows=37399561 width=139) - Conds:RS_32._col1=RS_495._col0(Inner),Output:["_col2","_col7"] + Group By Operator [GBY_36] (rows=3960 width=210) + Output:["_col0","_col1"],aggregations:["sum(_col2)"],keys:_col5 + Merge Join Operator [MERGEJOIN_437] (rows=10246882 width=209) + Conds:RS_32._col1=RS_495._col0(Inner),Output:["_col2","_col5"] <-Map 32 [SIMPLE_EDGE] vectorized SHUFFLE [RS_495] PartitionCols:_col0 @@ -402,28 +404,28 @@ Stage-0 <-Reducer 10 [SIMPLE_EDGE] SHUFFLE [RS_32] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_436] (rows=37399561 width=42) - Conds:RS_506._col0=RS_465._col0(Inner),Output:["_col1","_col2"] + Merge Join Operator [MERGEJOIN_436] (rows=10246882 width=115) + Conds:RS_507._col0=RS_465._col0(Inner),Output:["_col1","_col2"] <-Map 8 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_465] PartitionCols:_col0 - Select Operator [SEL_458] (rows=130 width=12) + Select Operator [SEL_458] (rows=130 width=4) Output:["_col0"] Filter Operator [FIL_452] (rows=130 width=12) - predicate:((d_qoy = 1) and (d_year = 2000) and d_date_sk is not null) + predicate:((d_qoy = 3) and (d_year = 2000) and d_date_sk is not null) Please refer to the previous TableScan [TS_3] <-Map 33 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_506] + SHUFFLE [RS_507] PartitionCols:_col0 - Select Operator [SEL_505] (rows=525327191 width=114) + Select Operator [SEL_506] (rows=143931246 width=119) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_504] (rows=525327191 width=114) - predicate:((ss_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(ss_sold_date_sk, DynamicValue(RS_30_date_dim_d_date_sk_bloom_filter))) and ss_addr_sk is not null and ss_sold_date_sk is not null) - TableScan [TS_20] (rows=575995635 width=114) - default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_addr_sk","ss_ext_sales_price"] + Filter Operator [FIL_505] (rows=143931246 width=119) + predicate:((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_addr_sk is not null and ws_sold_date_sk is not null) + TableScan [TS_20] (rows=144002668 width=119) + default@web_sales,web_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_sold_date_sk","ws_bill_addr_sk","ws_ext_sales_price"] <-Reducer 13 [BROADCAST_EDGE] vectorized - BROADCAST [RS_503] - Group By Operator [GBY_502] (rows=1 width=12) + BROADCAST [RS_504] + Group By Operator [GBY_503] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Map 8 [CUSTOM_SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_482] @@ -433,52 +435,54 @@ Stage-0 Output:["_col0"] Please refer to the previous Select Operator [SEL_458] <-Reducer 4 [ONE_TO_ONE_EDGE] vectorized - FORWARD [RS_501] + FORWARD [RS_502] PartitionCols:_col0 - Group By Operator [GBY_500] (rows=1605 width=210) - Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 - <-Reducer 3 [SIMPLE_EDGE] - SHUFFLE [RS_17] - PartitionCols:_col0 - Group By Operator [GBY_16] (rows=33705 width=210) - Output:["_col0","_col1"],aggregations:["sum(_col2)"],keys:_col7 - Merge Join Operator [MERGEJOIN_435] (rows=37399561 width=139) - Conds:RS_12._col1=RS_494._col0(Inner),Output:["_col2","_col7"] - <-Map 32 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_494] - PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_493] - <-Reducer 2 [SIMPLE_EDGE] - SHUFFLE [RS_12] - PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_434] (rows=37399561 width=42) - Conds:RS_491._col0=RS_463._col0(Inner),Output:["_col1","_col2"] - <-Map 8 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_463] - PartitionCols:_col0 - Select Operator [SEL_457] (rows=130 width=12) - Output:["_col0"] - Filter Operator [FIL_451] (rows=130 width=12) - predicate:((d_qoy = 2) and (d_year = 2000) and d_date_sk is not null) - Please refer to the previous TableScan [TS_3] - <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_491] - PartitionCols:_col0 - Select Operator [SEL_490] (rows=525327191 width=114) - Output:["_col0","_col1","_col2"] - Filter Operator [FIL_489] (rows=525327191 width=114) - predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_10_date_dim_d_date_sk_min) AND DynamicValue(RS_10_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_10_date_dim_d_date_sk_bloom_filter))) and ss_addr_sk is not null and ss_sold_date_sk is not null) - TableScan [TS_0] (rows=575995635 width=114) - default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_addr_sk","ss_ext_sales_price"] - <-Reducer 9 [BROADCAST_EDGE] vectorized - BROADCAST [RS_488] - Group By Operator [GBY_487] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 8 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_481] - Group By Operator [GBY_475] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_464] (rows=130 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_457] + Select Operator [SEL_501] (rows=440 width=214) + Output:["_col0","_col1","_col2"] + Group By Operator [GBY_500] (rows=440 width=210) + Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 + <-Reducer 3 [SIMPLE_EDGE] + SHUFFLE [RS_17] + PartitionCols:_col0 + Group By Operator [GBY_16] (rows=3960 width=210) + Output:["_col0","_col1"],aggregations:["sum(_col2)"],keys:_col5 + Merge Join Operator [MERGEJOIN_435] (rows=10246882 width=209) + Conds:RS_12._col1=RS_494._col0(Inner),Output:["_col2","_col5"] + <-Map 32 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_494] + PartitionCols:_col0 + Please refer to the previous Select Operator [SEL_493] + <-Reducer 2 [SIMPLE_EDGE] + SHUFFLE [RS_12] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_434] (rows=10246882 width=115) + Conds:RS_491._col0=RS_463._col0(Inner),Output:["_col1","_col2"] + <-Map 8 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_463] + PartitionCols:_col0 + Select Operator [SEL_457] (rows=130 width=4) + Output:["_col0"] + Filter Operator [FIL_451] (rows=130 width=12) + predicate:((d_qoy = 1) and (d_year = 2000) and d_date_sk is not null) + Please refer to the previous TableScan [TS_3] + <-Map 1 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_491] + PartitionCols:_col0 + Select Operator [SEL_490] (rows=143931246 width=119) + Output:["_col0","_col1","_col2"] + Filter Operator [FIL_489] (rows=143931246 width=119) + predicate:((ws_sold_date_sk BETWEEN DynamicValue(RS_10_date_dim_d_date_sk_min) AND DynamicValue(RS_10_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_10_date_dim_d_date_sk_bloom_filter))) and ws_bill_addr_sk is not null and ws_sold_date_sk is not null) + TableScan [TS_0] (rows=144002668 width=119) + default@web_sales,web_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_sold_date_sk","ws_bill_addr_sk","ws_ext_sales_price"] + <-Reducer 9 [BROADCAST_EDGE] vectorized + BROADCAST [RS_488] + Group By Operator [GBY_487] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 8 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_481] + Group By Operator [GBY_475] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_464] (rows=130 width=4) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_457] diff --git ql/src/test/results/clientpositive/perf/tez/query32.q.out ql/src/test/results/clientpositive/perf/tez/query32.q.out index 1c1a2e7b5e1..2e52e0a02b8 100644 --- ql/src/test/results/clientpositive/perf/tez/query32.q.out +++ ql/src/test/results/clientpositive/perf/tez/query32.q.out @@ -93,9 +93,9 @@ Stage-0 Select Operator [SEL_34] (rows=2478 width=112) Output:["_col2"] Filter Operator [FIL_33] (rows=2478 width=112) - predicate:(_col2 > CAST( (1.3 * _col6) AS decimal(14,7))) + predicate:(_col2 > _col5) Merge Join Operator [MERGEJOIN_104] (rows=7434 width=112) - Conds:RS_30._col1=RS_31._col2(Inner),Output:["_col2","_col6"] + Conds:RS_30._col1=RS_31._col2(Inner),Output:["_col2","_col5"] <-Reducer 2 [SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_30] PartitionCols:_col1 @@ -104,7 +104,7 @@ Stage-0 <-Map 6 [SIMPLE_EDGE] vectorized SHUFFLE [RS_107] PartitionCols:_col0 - Select Operator [SEL_106] (rows=8116 width=98) + Select Operator [SEL_106] (rows=8116 width=4) Output:["_col0"] Filter Operator [FIL_105] (rows=8116 width=98) predicate:(CAST( d_date AS TIMESTAMP) BETWEEN TIMESTAMP'1998-03-18 00:00:00' AND TIMESTAMP'1998-06-16 00:00:00' and d_date_sk is not null) @@ -129,7 +129,7 @@ Stage-0 Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] Select Operator [SEL_120] (rows=669 width=4) Output:["_col0"] - Select Operator [SEL_118] (rows=669 width=8) + Select Operator [SEL_118] (rows=669 width=4) Output:["_col0"] Filter Operator [FIL_117] (rows=669 width=7) predicate:((i_manufact_id = 269) and i_item_sk is not null) diff --git ql/src/test/results/clientpositive/perf/tez/query33.q.out ql/src/test/results/clientpositive/perf/tez/query33.q.out index a76122c4edb..6c4798eed57 100644 --- ql/src/test/results/clientpositive/perf/tez/query33.q.out +++ ql/src/test/results/clientpositive/perf/tez/query33.q.out @@ -215,9 +215,9 @@ Stage-0 SHUFFLE [RS_109] PartitionCols:_col0 Group By Operator [GBY_108] (rows=19 width=115) - Output:["_col0","_col1"],aggregations:["sum(_col8)"],keys:_col1 + Output:["_col0","_col1"],aggregations:["sum(_col7)"],keys:_col1 Merge Join Operator [MERGEJOIN_304] (rows=11364 width=3) - Conds:RS_104._col0=RS_105._col3(Inner),Output:["_col1","_col8"] + Conds:RS_104._col0=RS_105._col2(Inner),Output:["_col1","_col7"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_104] PartitionCols:_col0 @@ -250,15 +250,15 @@ Stage-0 default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_category","i_manufact_id"] <-Reducer 23 [SIMPLE_EDGE] SHUFFLE [RS_105] - PartitionCols:_col3 + PartitionCols:_col2 Select Operator [SEL_100] (rows=788222 width=110) - Output:["_col3","_col5"] + Output:["_col2","_col4"] Merge Join Operator [MERGEJOIN_301] (rows=788222 width=110) Conds:RS_97._col2=RS_348._col0(Inner),Output:["_col1","_col3"] <-Map 25 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_348] PartitionCols:_col0 - Select Operator [SEL_343] (rows=8000000 width=116) + Select Operator [SEL_343] (rows=8000000 width=4) Output:["_col0"] Filter Operator [FIL_342] (rows=8000000 width=112) predicate:((ca_gmt_offset = -6) and ca_address_sk is not null) @@ -272,7 +272,7 @@ Stage-0 <-Map 17 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_332] PartitionCols:_col0 - Select Operator [SEL_327] (rows=50 width=12) + Select Operator [SEL_327] (rows=50 width=4) Output:["_col0"] Filter Operator [FIL_326] (rows=50 width=12) predicate:((d_moy = 3) and (d_year = 1999) and d_date_sk is not null) @@ -320,18 +320,18 @@ Stage-0 SHUFFLE [RS_34] PartitionCols:_col0 Group By Operator [GBY_33] (rows=64 width=115) - Output:["_col0","_col1"],aggregations:["sum(_col8)"],keys:_col1 + Output:["_col0","_col1"],aggregations:["sum(_col7)"],keys:_col1 Merge Join Operator [MERGEJOIN_302] (rows=41476 width=3) - Conds:RS_29._col0=RS_30._col3(Inner),Output:["_col1","_col8"] + Conds:RS_29._col0=RS_30._col2(Inner),Output:["_col1","_col7"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_29] PartitionCols:_col0 Please refer to the previous Merge Join Operator [MERGEJOIN_293] <-Reducer 16 [SIMPLE_EDGE] SHUFFLE [RS_30] - PartitionCols:_col3 + PartitionCols:_col2 Select Operator [SEL_25] (rows=2876890 width=4) - Output:["_col3","_col5"] + Output:["_col2","_col4"] Merge Join Operator [MERGEJOIN_295] (rows=2876890 width=4) Conds:RS_22._col2=RS_344._col0(Inner),Output:["_col1","_col3"] <-Map 25 [SIMPLE_EDGE] vectorized @@ -389,18 +389,18 @@ Stage-0 SHUFFLE [RS_71] PartitionCols:_col0 Group By Operator [GBY_70] (rows=35 width=115) - Output:["_col0","_col1"],aggregations:["sum(_col8)"],keys:_col1 + Output:["_col0","_col1"],aggregations:["sum(_col7)"],keys:_col1 Merge Join Operator [MERGEJOIN_303] (rows=22352 width=3) - Conds:RS_66._col0=RS_67._col4(Inner),Output:["_col1","_col8"] + Conds:RS_66._col0=RS_67._col3(Inner),Output:["_col1","_col7"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_66] PartitionCols:_col0 Please refer to the previous Merge Join Operator [MERGEJOIN_293] <-Reducer 20 [SIMPLE_EDGE] SHUFFLE [RS_67] - PartitionCols:_col4 + PartitionCols:_col3 Select Operator [SEL_62] (rows=1550375 width=13) - Output:["_col4","_col5"] + Output:["_col3","_col4"] Merge Join Operator [MERGEJOIN_298] (rows=1550375 width=13) Conds:RS_59._col1=RS_346._col0(Inner),Output:["_col2","_col3"] <-Map 25 [SIMPLE_EDGE] vectorized diff --git ql/src/test/results/clientpositive/perf/tez/query34.q.out ql/src/test/results/clientpositive/perf/tez/query34.q.out index fa40be9bb94..1e785dc2420 100644 --- ql/src/test/results/clientpositive/perf/tez/query34.q.out +++ ql/src/test/results/clientpositive/perf/tez/query34.q.out @@ -126,7 +126,7 @@ Stage-0 <-Map 13 [SIMPLE_EDGE] vectorized SHUFFLE [RS_122] PartitionCols:_col0 - Select Operator [SEL_121] (rows=112 width=102) + Select Operator [SEL_121] (rows=112 width=4) Output:["_col0"] Filter Operator [FIL_120] (rows=112 width=102) predicate:((s_county) IN ('Mobile County', 'Maverick County', 'Huron County', 'Kittitas County', 'Fairfield County', 'Jackson County', 'Barrow County', 'Pennington County') and s_store_sk is not null) @@ -140,7 +140,7 @@ Stage-0 <-Map 11 [SIMPLE_EDGE] vectorized SHUFFLE [RS_114] PartitionCols:_col0 - Select Operator [SEL_113] (rows=480 width=104) + Select Operator [SEL_113] (rows=480 width=4) Output:["_col0"] Filter Operator [FIL_112] (rows=480 width=104) predicate:((hd_buy_potential) IN ('>10000', 'unknown') and (hd_vehicle_count > 0) and CASE WHEN ((hd_vehicle_count > 0)) THEN (((UDFToDouble(hd_dep_count) / UDFToDouble(hd_vehicle_count)) > 1.2D)) ELSE (null) END and hd_demo_sk is not null) @@ -154,7 +154,7 @@ Stage-0 <-Map 9 [SIMPLE_EDGE] vectorized SHUFFLE [RS_106] PartitionCols:_col0 - Select Operator [SEL_105] (rows=595 width=12) + Select Operator [SEL_105] (rows=595 width=4) Output:["_col0"] Filter Operator [FIL_104] (rows=595 width=12) predicate:((d_dom BETWEEN 1 AND 3 or d_dom BETWEEN 25 AND 28) and (d_year) IN (2000, 2001, 2002) and d_date_sk is not null) diff --git ql/src/test/results/clientpositive/perf/tez/query35.q.out ql/src/test/results/clientpositive/perf/tez/query35.q.out index 44993831f41..f9e67b69df1 100644 --- ql/src/test/results/clientpositive/perf/tez/query35.q.out +++ ql/src/test/results/clientpositive/perf/tez/query35.q.out @@ -201,7 +201,7 @@ Stage-0 <-Map 15 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_194] PartitionCols:_col0 - Select Operator [SEL_193] (rows=217 width=12) + Select Operator [SEL_193] (rows=217 width=4) Output:["_col0"] Filter Operator [FIL_192] (rows=217 width=12) predicate:((d_qoy < 4) and (d_year = 1999) and d_date_sk is not null) diff --git ql/src/test/results/clientpositive/perf/tez/query36.q.out ql/src/test/results/clientpositive/perf/tez/query36.q.out index 4f4ce8a518f..a367f2ef617 100644 --- ql/src/test/results/clientpositive/perf/tez/query36.q.out +++ ql/src/test/results/clientpositive/perf/tez/query36.q.out @@ -112,7 +112,7 @@ Stage-0 Select Operator [SEL_21] (rows=30601888 width=232) Output:["_col0","_col1","_col2","_col3"] Merge Join Operator [MERGEJOIN_82] (rows=30601888 width=232) - Conds:RS_18._col1=RS_104._col0(Inner),Output:["_col3","_col4","_col10","_col11"] + Conds:RS_18._col1=RS_104._col0(Inner),Output:["_col3","_col4","_col8","_col9"] <-Map 12 [SIMPLE_EDGE] vectorized SHUFFLE [RS_104] PartitionCols:_col0 @@ -130,7 +130,7 @@ Stage-0 <-Map 10 [SIMPLE_EDGE] vectorized SHUFFLE [RS_93] PartitionCols:_col0 - Select Operator [SEL_92] (rows=278 width=90) + Select Operator [SEL_92] (rows=278 width=4) Output:["_col0"] Filter Operator [FIL_91] (rows=278 width=90) predicate:((s_state) IN ('SD', 'FL', 'MI', 'LA', 'MO', 'SC', 'AL', 'GA') and s_store_sk is not null) @@ -144,7 +144,7 @@ Stage-0 <-Map 8 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_85] PartitionCols:_col0 - Select Operator [SEL_84] (rows=652 width=8) + Select Operator [SEL_84] (rows=652 width=4) Output:["_col0"] Filter Operator [FIL_83] (rows=652 width=8) predicate:((d_year = 1999) and d_date_sk is not null) diff --git ql/src/test/results/clientpositive/perf/tez/query37.q.out ql/src/test/results/clientpositive/perf/tez/query37.q.out index 4407a489311..c7c29fbadd1 100644 --- ql/src/test/results/clientpositive/perf/tez/query37.q.out +++ ql/src/test/results/clientpositive/perf/tez/query37.q.out @@ -83,7 +83,7 @@ Stage-0 <-Map 11 [SIMPLE_EDGE] vectorized SHUFFLE [RS_93] PartitionCols:_col0 - Select Operator [SEL_92] (rows=8116 width=98) + Select Operator [SEL_92] (rows=8116 width=4) Output:["_col0"] Filter Operator [FIL_91] (rows=8116 width=98) predicate:(CAST( d_date AS TIMESTAMP) BETWEEN TIMESTAMP'2001-06-02 00:00:00' AND TIMESTAMP'2001-08-01 00:00:00' and d_date_sk is not null) @@ -92,7 +92,7 @@ Stage-0 <-Map 8 [SIMPLE_EDGE] vectorized SHUFFLE [RS_90] PartitionCols:_col0 - Select Operator [SEL_89] (rows=4176000 width=11) + Select Operator [SEL_89] (rows=4176000 width=8) Output:["_col0","_col1"] Filter Operator [FIL_88] (rows=4176000 width=11) predicate:(inv_date_sk is not null and inv_item_sk is not null and inv_quantity_on_hand BETWEEN 100 AND 500) @@ -106,7 +106,7 @@ Stage-0 <-Map 6 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_82] PartitionCols:_col0 - Select Operator [SEL_81] (rows=297 width=404) + Select Operator [SEL_81] (rows=297 width=400) Output:["_col0","_col1","_col2","_col3"] Filter Operator [FIL_80] (rows=297 width=404) predicate:((i_manufact_id) IN (678, 964, 918, 849) and i_current_price BETWEEN 22 AND 52 and i_item_sk is not null) diff --git ql/src/test/results/clientpositive/perf/tez/query38.q.out ql/src/test/results/clientpositive/perf/tez/query38.q.out index e91141d8364..ddf6e6e621d 100644 --- ql/src/test/results/clientpositive/perf/tez/query38.q.out +++ ql/src/test/results/clientpositive/perf/tez/query38.q.out @@ -112,9 +112,9 @@ Stage-0 SHUFFLE [RS_42] PartitionCols:_col0, _col1, _col2 Group By Operator [GBY_41] (rows=49146883 width=274) - Output:["_col0","_col1","_col2"],keys:_col7, _col6, _col3 + Output:["_col0","_col1","_col2"],keys:_col6, _col5, _col3 Merge Join Operator [MERGEJOIN_178] (rows=49146883 width=274) - Conds:RS_37._col1=RS_221._col0(Inner),Output:["_col3","_col6","_col7"] + Conds:RS_37._col1=RS_221._col0(Inner),Output:["_col3","_col5","_col6"] <-Map 18 [SIMPLE_EDGE] vectorized SHUFFLE [RS_221] PartitionCols:_col0 @@ -132,7 +132,7 @@ Stage-0 <-Map 8 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_203] PartitionCols:_col0 - Select Operator [SEL_200] (rows=317 width=102) + Select Operator [SEL_200] (rows=317 width=98) Output:["_col0","_col1"] Filter Operator [FIL_199] (rows=317 width=102) predicate:(d_date_sk is not null and d_month_seq BETWEEN 1212 AND 1223) @@ -173,9 +173,9 @@ Stage-0 SHUFFLE [RS_68] PartitionCols:_col0, _col1, _col2 Group By Operator [GBY_67] (rows=24986582 width=274) - Output:["_col0","_col1","_col2"],keys:_col7, _col6, _col3 + Output:["_col0","_col1","_col2"],keys:_col6, _col5, _col3 Merge Join Operator [MERGEJOIN_180] (rows=24986582 width=274) - Conds:RS_63._col1=RS_222._col0(Inner),Output:["_col3","_col6","_col7"] + Conds:RS_63._col1=RS_222._col0(Inner),Output:["_col3","_col5","_col6"] <-Map 18 [SIMPLE_EDGE] vectorized SHUFFLE [RS_222] PartitionCols:_col0 @@ -224,9 +224,9 @@ Stage-0 SHUFFLE [RS_17] PartitionCols:_col0, _col1, _col2 Group By Operator [GBY_16] (rows=91197425 width=274) - Output:["_col0","_col1","_col2"],keys:_col7, _col6, _col3 + Output:["_col0","_col1","_col2"],keys:_col6, _col5, _col3 Merge Join Operator [MERGEJOIN_176] (rows=91197425 width=274) - Conds:RS_12._col1=RS_220._col0(Inner),Output:["_col3","_col6","_col7"] + Conds:RS_12._col1=RS_220._col0(Inner),Output:["_col3","_col5","_col6"] <-Map 18 [SIMPLE_EDGE] vectorized SHUFFLE [RS_220] PartitionCols:_col0 diff --git ql/src/test/results/clientpositive/perf/tez/query39.q.out ql/src/test/results/clientpositive/perf/tez/query39.q.out index 103e921e70b..691e30109bb 100644 --- ql/src/test/results/clientpositive/perf/tez/query39.q.out +++ ql/src/test/results/clientpositive/perf/tez/query39.q.out @@ -105,7 +105,7 @@ Stage-0 Select Operator [SEL_49] (rows=1032514 width=108) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] Merge Join Operator [MERGEJOIN_201] (rows=1032514 width=108) - Conds:RS_46._col2=RS_220._col0(Inner),Output:["_col3","_col7","_col8","_col9"] + Conds:RS_46._col2=RS_220._col0(Inner),Output:["_col3","_col5","_col6","_col7"] <-Map 14 [SIMPLE_EDGE] vectorized SHUFFLE [RS_220] PartitionCols:_col0 @@ -119,7 +119,7 @@ Stage-0 SHUFFLE [RS_46] PartitionCols:_col2 Merge Join Operator [MERGEJOIN_200] (rows=1032514 width=8) - Conds:RS_43._col1=RS_216._col0(Inner),Output:["_col2","_col3","_col7"] + Conds:RS_43._col1=RS_216._col0(Inner),Output:["_col2","_col3","_col5"] <-Map 13 [SIMPLE_EDGE] vectorized SHUFFLE [RS_216] PartitionCols:_col0 @@ -146,7 +146,7 @@ Stage-0 <-Map 12 [SIMPLE_EDGE] vectorized SHUFFLE [RS_212] PartitionCols:_col0 - Select Operator [SEL_210] (rows=50 width=12) + Select Operator [SEL_210] (rows=50 width=4) Output:["_col0"] Filter Operator [FIL_208] (rows=50 width=12) predicate:((d_moy = 5) and (d_year = 1999) and d_date_sk is not null) @@ -171,7 +171,7 @@ Stage-0 Select Operator [SEL_21] (rows=1032514 width=108) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] Merge Join Operator [MERGEJOIN_198] (rows=1032514 width=108) - Conds:RS_18._col2=RS_219._col0(Inner),Output:["_col3","_col7","_col8","_col9"] + Conds:RS_18._col2=RS_219._col0(Inner),Output:["_col3","_col5","_col6","_col7"] <-Map 14 [SIMPLE_EDGE] vectorized SHUFFLE [RS_219] PartitionCols:_col0 @@ -180,7 +180,7 @@ Stage-0 SHUFFLE [RS_18] PartitionCols:_col2 Merge Join Operator [MERGEJOIN_197] (rows=1032514 width=8) - Conds:RS_15._col1=RS_215._col0(Inner),Output:["_col2","_col3","_col7"] + Conds:RS_15._col1=RS_215._col0(Inner),Output:["_col2","_col3","_col5"] <-Map 13 [SIMPLE_EDGE] vectorized SHUFFLE [RS_215] PartitionCols:_col0 @@ -197,7 +197,7 @@ Stage-0 <-Map 12 [SIMPLE_EDGE] vectorized SHUFFLE [RS_211] PartitionCols:_col0 - Select Operator [SEL_209] (rows=50 width=12) + Select Operator [SEL_209] (rows=50 width=4) Output:["_col0"] Filter Operator [FIL_207] (rows=50 width=12) predicate:((d_moy = 4) and (d_year = 1999) and d_date_sk is not null) diff --git ql/src/test/results/clientpositive/perf/tez/query4.q.out ql/src/test/results/clientpositive/perf/tez/query4.q.out index 27ce7b5b89b..bb0d7ba3f5f 100644 --- ql/src/test/results/clientpositive/perf/tez/query4.q.out +++ ql/src/test/results/clientpositive/perf/tez/query4.q.out @@ -271,367 +271,355 @@ Stage-0 limit:100 Stage-1 Reducer 10 vectorized - File Output Operator [FS_575] - Limit [LIM_574] (rows=100 width=85) + File Output Operator [FS_557] + Limit [LIM_556] (rows=100 width=85) Number of rows:100 - Select Operator [SEL_573] (rows=7323197 width=85) + Select Operator [SEL_555] (rows=7323197 width=85) Output:["_col0"] <-Reducer 9 [SIMPLE_EDGE] - SHUFFLE [RS_147] - Select Operator [SEL_146] (rows=7323197 width=85) + SHUFFLE [RS_141] + Select Operator [SEL_140] (rows=7323197 width=85) Output:["_col0"] - Filter Operator [FIL_145] (rows=7323197 width=533) - predicate:CASE WHEN (_col3 is not null) THEN (CASE WHEN (_col5 is not null) THEN (((_col9 / _col5) > (_col12 / _col3))) ELSE ((null > (_col12 / _col3))) END) ELSE (CASE WHEN (_col5 is not null) THEN (((_col9 / _col5) > null)) ELSE (null) END) END - Merge Join Operator [MERGEJOIN_478] (rows=14646395 width=533) - Conds:RS_142._col2=RS_572._col0(Inner),Output:["_col3","_col5","_col9","_col11","_col12"] + Filter Operator [FIL_139] (rows=7323197 width=537) + predicate:CASE WHEN (_col3 is not null) THEN (CASE WHEN (_col9) THEN (((_col11 / _col8) > (_col14 / _col3))) ELSE ((null > (_col14 / _col3))) END) ELSE (CASE WHEN (_col9) THEN (((_col11 / _col8) > null)) ELSE (null) END) END + Merge Join Operator [MERGEJOIN_472] (rows=14646395 width=537) + Conds:RS_136._col2=RS_554._col0(Inner),Output:["_col3","_col8","_col9","_col11","_col13","_col14"] <-Reducer 30 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_572] + SHUFFLE [RS_554] PartitionCols:_col0 - Select Operator [SEL_571] (rows=80000000 width=297) + Select Operator [SEL_553] (rows=80000000 width=297) Output:["_col0","_col1","_col2"] - Group By Operator [GBY_570] (rows=80000000 width=764) + Group By Operator [GBY_552] (rows=80000000 width=764) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4, KEY._col5, KEY._col6 <-Reducer 29 [SIMPLE_EDGE] - SHUFFLE [RS_126] + SHUFFLE [RS_120] PartitionCols:_col0, _col1, _col2, _col3, _col4, _col5, _col6 - Group By Operator [GBY_125] (rows=80000000 width=764) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"],aggregations:["sum(_col7)"],keys:_col0, _col1, _col2, _col3, _col4, _col5, _col6 - Select Operator [SEL_123] (rows=187573258 width=1043) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] - Merge Join Operator [MERGEJOIN_473] (rows=187573258 width=1043) - Conds:RS_120._col1=RS_518._col0(Inner),Output:["_col2","_col3","_col4","_col5","_col9","_col10","_col11","_col12","_col13","_col14","_col15"] - <-Map 38 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_518] - PartitionCols:_col0 - Select Operator [SEL_517] (rows=80000000 width=656) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] - Filter Operator [FIL_516] (rows=80000000 width=656) - predicate:(c_customer_id is not null and c_customer_sk is not null) - TableScan [TS_114] (rows=80000000 width=656) - default@customer,customer,Tbl:COMPLETE,Col:COMPLETE,Output:["c_customer_sk","c_customer_id","c_first_name","c_last_name","c_preferred_cust_flag","c_birth_country","c_login","c_email_address"] - <-Reducer 28 [SIMPLE_EDGE] - SHUFFLE [RS_120] - PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_472] (rows=187573258 width=395) - Conds:RS_569._col0=RS_487._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5"] - <-Map 31 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_487] - PartitionCols:_col0 - Select Operator [SEL_483] (rows=652 width=8) - Output:["_col0"] - Filter Operator [FIL_479] (rows=652 width=8) - predicate:((d_year = 2002) and d_date_sk is not null) - TableScan [TS_111] (rows=73049 width=8) - default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year"] - <-Map 27 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_569] - PartitionCols:_col0 - Select Operator [SEL_568] (rows=525327388 width=435) - Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - Filter Operator [FIL_567] (rows=525327388 width=435) - predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_118_date_dim_d_date_sk_min) AND DynamicValue(RS_118_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_118_date_dim_d_date_sk_bloom_filter))) and ss_customer_sk is not null and ss_sold_date_sk is not null) - TableScan [TS_108] (rows=575995635 width=435) - default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_customer_sk","ss_ext_discount_amt","ss_ext_sales_price","ss_ext_wholesale_cost","ss_ext_list_price"] - <-Reducer 32 [BROADCAST_EDGE] vectorized - BROADCAST [RS_566] - Group By Operator [GBY_565] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 31 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_505] - Group By Operator [GBY_499] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_488] (rows=652 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_483] + Group By Operator [GBY_119] (rows=80000000 width=764) + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"],aggregations:["sum(_col2)"],keys:_col5, _col6, _col7, _col8, _col9, _col10, _col11 + Merge Join Operator [MERGEJOIN_467] (rows=187573258 width=764) + Conds:RS_115._col1=RS_510._col0(Inner),Output:["_col2","_col5","_col6","_col7","_col8","_col9","_col10","_col11"] + <-Map 38 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_510] + PartitionCols:_col0 + Select Operator [SEL_509] (rows=80000000 width=656) + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] + Filter Operator [FIL_508] (rows=80000000 width=656) + predicate:(c_customer_id is not null and c_customer_sk is not null) + TableScan [TS_109] (rows=80000000 width=656) + default@customer,customer,Tbl:COMPLETE,Col:COMPLETE,Output:["c_customer_sk","c_customer_id","c_first_name","c_last_name","c_preferred_cust_flag","c_birth_country","c_login","c_email_address"] + <-Reducer 28 [SIMPLE_EDGE] + SHUFFLE [RS_115] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_466] (rows=187573258 width=115) + Conds:RS_112._col0=RS_481._col0(Inner),Output:["_col1","_col2"] + <-Map 31 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_481] + PartitionCols:_col0 + Select Operator [SEL_477] (rows=652 width=4) + Output:["_col0"] + Filter Operator [FIL_473] (rows=652 width=8) + predicate:((d_year = 2002) and d_date_sk is not null) + TableScan [TS_106] (rows=73049 width=8) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year"] + <-Map 27 [SIMPLE_EDGE] + SHUFFLE [RS_112] + PartitionCols:_col0 + Select Operator [SEL_105] (rows=525327388 width=119) + Output:["_col0","_col1","_col2"] + Filter Operator [FIL_250] (rows=525327388 width=435) + predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_113_date_dim_d_date_sk_min) AND DynamicValue(RS_113_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_113_date_dim_d_date_sk_bloom_filter))) and ss_customer_sk is not null and ss_sold_date_sk is not null) + TableScan [TS_103] (rows=575995635 width=435) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_customer_sk","ss_ext_discount_amt","ss_ext_sales_price","ss_ext_wholesale_cost","ss_ext_list_price"] + <-Reducer 32 [BROADCAST_EDGE] vectorized + BROADCAST [RS_550] + Group By Operator [GBY_549] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 31 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_499] + Group By Operator [GBY_493] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_482] (rows=652 width=4) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_477] <-Reducer 8 [ONE_TO_ONE_EDGE] - FORWARD [RS_142] + FORWARD [RS_136] PartitionCols:_col2 - Filter Operator [FIL_141] (rows=12248093 width=660) - predicate:CASE WHEN (_col7 is not null) THEN (CASE WHEN (_col5 is not null) THEN (((_col9 / _col5) > (_col1 / _col7))) ELSE ((null > (_col1 / _col7))) END) ELSE (CASE WHEN (_col5 is not null) THEN (((_col9 / _col5) > null)) ELSE (null) END) END - Merge Join Operator [MERGEJOIN_477] (rows=24496186 width=660) - Conds:RS_138._col2=RS_564._col0(Inner),Output:["_col1","_col2","_col3","_col5","_col7","_col9"] + Filter Operator [FIL_135] (rows=12248093 width=668) + predicate:CASE WHEN (_col6) THEN (CASE WHEN (_col9) THEN (((_col11 / _col8) > (_col1 / _col5))) ELSE ((null > (_col1 / _col5))) END) ELSE (CASE WHEN (_col9) THEN (((_col11 / _col8) > null)) ELSE (null) END) END + Merge Join Operator [MERGEJOIN_471] (rows=24496186 width=668) + Conds:RS_132._col2=RS_548._col0(Inner),Output:["_col1","_col2","_col3","_col5","_col6","_col8","_col9","_col11"] <-Reducer 26 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_564] + SHUFFLE [RS_548] PartitionCols:_col0 - Select Operator [SEL_563] (rows=80000000 width=212) + Select Operator [SEL_547] (rows=80000000 width=212) Output:["_col0","_col1"] - Group By Operator [GBY_562] (rows=80000000 width=764) + Group By Operator [GBY_546] (rows=80000000 width=764) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4, KEY._col5, KEY._col6 <-Reducer 25 [SIMPLE_EDGE] - SHUFFLE [RS_105] + SHUFFLE [RS_100] PartitionCols:_col0, _col1, _col2, _col3, _col4, _col5, _col6 - Group By Operator [GBY_104] (rows=80000000 width=764) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"],aggregations:["sum(_col7)"],keys:_col0, _col1, _col2, _col3, _col4, _col5, _col6 - Select Operator [SEL_102] (rows=101084444 width=1093) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] - Merge Join Operator [MERGEJOIN_471] (rows=101084444 width=1093) - Conds:RS_99._col1=RS_519._col0(Inner),Output:["_col2","_col3","_col4","_col5","_col9","_col10","_col11","_col12","_col13","_col14","_col15"] - <-Map 38 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_519] - PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_517] - <-Reducer 24 [SIMPLE_EDGE] - SHUFFLE [RS_99] - PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_470] (rows=101084444 width=445) - Conds:RS_561._col0=RS_489._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5"] - <-Map 31 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_489] - PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_483] - <-Map 23 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_561] - PartitionCols:_col0 - Select Operator [SEL_560] (rows=285117831 width=453) - Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - Filter Operator [FIL_559] (rows=285117831 width=453) - predicate:((cs_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(cs_sold_date_sk, DynamicValue(RS_97_date_dim_d_date_sk_bloom_filter))) and cs_bill_customer_sk is not null and cs_sold_date_sk is not null) - TableScan [TS_87] (rows=287989836 width=453) - default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["cs_sold_date_sk","cs_bill_customer_sk","cs_ext_discount_amt","cs_ext_sales_price","cs_ext_wholesale_cost","cs_ext_list_price"] - <-Reducer 33 [BROADCAST_EDGE] vectorized - BROADCAST [RS_558] - Group By Operator [GBY_557] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 31 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_506] - Group By Operator [GBY_500] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_490] (rows=652 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_483] + Group By Operator [GBY_99] (rows=80000000 width=764) + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"],aggregations:["sum(_col2)"],keys:_col5, _col6, _col7, _col8, _col9, _col10, _col11 + Merge Join Operator [MERGEJOIN_465] (rows=101084444 width=764) + Conds:RS_95._col1=RS_511._col0(Inner),Output:["_col2","_col5","_col6","_col7","_col8","_col9","_col10","_col11"] + <-Map 38 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_511] + PartitionCols:_col0 + Please refer to the previous Select Operator [SEL_509] + <-Reducer 24 [SIMPLE_EDGE] + SHUFFLE [RS_95] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_464] (rows=101084444 width=115) + Conds:RS_92._col0=RS_483._col0(Inner),Output:["_col1","_col2"] + <-Map 31 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_483] + PartitionCols:_col0 + Please refer to the previous Select Operator [SEL_477] + <-Map 23 [SIMPLE_EDGE] + SHUFFLE [RS_92] + PartitionCols:_col0 + Select Operator [SEL_85] (rows=285117831 width=119) + Output:["_col0","_col1","_col2"] + Filter Operator [FIL_247] (rows=285117831 width=453) + predicate:((cs_sold_date_sk BETWEEN DynamicValue(RS_93_date_dim_d_date_sk_min) AND DynamicValue(RS_93_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_93_date_dim_d_date_sk_bloom_filter))) and cs_bill_customer_sk is not null and cs_sold_date_sk is not null) + TableScan [TS_83] (rows=287989836 width=453) + default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["cs_sold_date_sk","cs_bill_customer_sk","cs_ext_discount_amt","cs_ext_sales_price","cs_ext_wholesale_cost","cs_ext_list_price"] + <-Reducer 33 [BROADCAST_EDGE] vectorized + BROADCAST [RS_544] + Group By Operator [GBY_543] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 31 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_500] + Group By Operator [GBY_494] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_484] (rows=652 width=4) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_477] <-Reducer 7 [ONE_TO_ONE_EDGE] - FORWARD [RS_138] + FORWARD [RS_132] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_476] (rows=20485011 width=548) - Conds:RS_135._col2=RS_556._col0(Inner),Output:["_col1","_col2","_col3","_col5","_col7"] + Merge Join Operator [MERGEJOIN_470] (rows=20485011 width=556) + Conds:RS_129._col2=RS_542._col0(Inner),Output:["_col1","_col2","_col3","_col5","_col6","_col8","_col9"] <-Reducer 22 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_556] + SHUFFLE [RS_542] PartitionCols:_col0 - Select Operator [SEL_555] (rows=17130654 width=212) - Output:["_col0","_col1"] - Filter Operator [FIL_554] (rows=17130654 width=212) + Select Operator [SEL_541] (rows=26666666 width=216) + Output:["_col0","_col1","_col2"] + Filter Operator [FIL_540] (rows=26666666 width=212) predicate:(_col7 > 0) - Select Operator [SEL_553] (rows=51391963 width=212) + Select Operator [SEL_539] (rows=80000000 width=212) Output:["_col0","_col7"] - Group By Operator [GBY_552] (rows=51391963 width=764) + Group By Operator [GBY_538] (rows=80000000 width=764) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4, KEY._col5, KEY._col6 <-Reducer 21 [SIMPLE_EDGE] - SHUFFLE [RS_83] + SHUFFLE [RS_79] PartitionCols:_col0, _col1, _col2, _col3, _col4, _col5, _col6 - Group By Operator [GBY_82] (rows=51391963 width=764) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"],aggregations:["sum(_col7)"],keys:_col0, _col1, _col2, _col3, _col4, _col5, _col6 - Select Operator [SEL_80] (rows=51391963 width=1099) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] - Merge Join Operator [MERGEJOIN_469] (rows=51391963 width=1099) - Conds:RS_77._col1=RS_523._col0(Inner),Output:["_col2","_col3","_col4","_col5","_col9","_col10","_col11","_col12","_col13","_col14","_col15"] - <-Map 38 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_523] - PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_517] - <-Reducer 20 [SIMPLE_EDGE] - SHUFFLE [RS_77] - PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_468] (rows=51391963 width=451) - Conds:RS_551._col0=RS_497._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5"] - <-Map 31 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_497] - PartitionCols:_col0 - Select Operator [SEL_486] (rows=652 width=8) - Output:["_col0"] - Filter Operator [FIL_482] (rows=652 width=8) - predicate:((d_year = 2001) and d_date_sk is not null) - Please refer to the previous TableScan [TS_111] - <-Map 19 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_551] - PartitionCols:_col0 - Select Operator [SEL_550] (rows=143930993 width=455) - Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - Filter Operator [FIL_549] (rows=143930993 width=455) - predicate:((ws_sold_date_sk BETWEEN DynamicValue(RS_75_date_dim_d_date_sk_min) AND DynamicValue(RS_75_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_75_date_dim_d_date_sk_bloom_filter))) and ws_bill_customer_sk is not null and ws_sold_date_sk is not null) - TableScan [TS_65] (rows=144002668 width=455) - default@web_sales,web_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_sold_date_sk","ws_bill_customer_sk","ws_ext_discount_amt","ws_ext_sales_price","ws_ext_wholesale_cost","ws_ext_list_price"] - <-Reducer 37 [BROADCAST_EDGE] vectorized - BROADCAST [RS_548] - Group By Operator [GBY_547] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 31 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_510] - Group By Operator [GBY_504] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_498] (rows=652 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_486] + Group By Operator [GBY_78] (rows=80000000 width=764) + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"],aggregations:["sum(_col2)"],keys:_col5, _col6, _col7, _col8, _col9, _col10, _col11 + Merge Join Operator [MERGEJOIN_463] (rows=101084444 width=764) + Conds:RS_74._col1=RS_515._col0(Inner),Output:["_col2","_col5","_col6","_col7","_col8","_col9","_col10","_col11"] + <-Map 38 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_515] + PartitionCols:_col0 + Please refer to the previous Select Operator [SEL_509] + <-Reducer 20 [SIMPLE_EDGE] + SHUFFLE [RS_74] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_462] (rows=101084444 width=115) + Conds:RS_71._col0=RS_491._col0(Inner),Output:["_col1","_col2"] + <-Map 31 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_491] + PartitionCols:_col0 + Select Operator [SEL_480] (rows=652 width=4) + Output:["_col0"] + Filter Operator [FIL_476] (rows=652 width=8) + predicate:((d_year = 2001) and d_date_sk is not null) + Please refer to the previous TableScan [TS_106] + <-Map 19 [SIMPLE_EDGE] + SHUFFLE [RS_71] + PartitionCols:_col0 + Select Operator [SEL_64] (rows=285117831 width=119) + Output:["_col0","_col1","_col2"] + Filter Operator [FIL_244] (rows=285117831 width=453) + predicate:((cs_sold_date_sk BETWEEN DynamicValue(RS_72_date_dim_d_date_sk_min) AND DynamicValue(RS_72_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_72_date_dim_d_date_sk_bloom_filter))) and cs_bill_customer_sk is not null and cs_sold_date_sk is not null) + TableScan [TS_62] (rows=287989836 width=453) + default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["cs_sold_date_sk","cs_bill_customer_sk","cs_ext_discount_amt","cs_ext_sales_price","cs_ext_wholesale_cost","cs_ext_list_price"] + <-Reducer 37 [BROADCAST_EDGE] vectorized + BROADCAST [RS_536] + Group By Operator [GBY_535] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 31 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_504] + Group By Operator [GBY_498] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_492] (rows=652 width=4) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_480] <-Reducer 6 [ONE_TO_ONE_EDGE] - FORWARD [RS_135] + FORWARD [RS_129] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_475] (rows=31888273 width=436) - Conds:RS_132._col2=RS_546._col0(Inner),Output:["_col1","_col2","_col3","_col5"] + Merge Join Operator [MERGEJOIN_469] (rows=20485011 width=440) + Conds:RS_126._col2=RS_534._col0(Inner),Output:["_col1","_col2","_col3","_col5","_col6"] <-Reducer 18 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_546] + SHUFFLE [RS_534] PartitionCols:_col0 - Select Operator [SEL_545] (rows=26666666 width=212) - Output:["_col0","_col1"] - Filter Operator [FIL_544] (rows=26666666 width=212) + Select Operator [SEL_533] (rows=17130654 width=216) + Output:["_col0","_col1","_col2"] + Filter Operator [FIL_532] (rows=17130654 width=212) predicate:(_col7 > 0) - Select Operator [SEL_543] (rows=80000000 width=212) + Select Operator [SEL_531] (rows=51391963 width=212) Output:["_col0","_col7"] - Group By Operator [GBY_542] (rows=80000000 width=764) + Group By Operator [GBY_530] (rows=51391963 width=764) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4, KEY._col5, KEY._col6 <-Reducer 17 [SIMPLE_EDGE] - SHUFFLE [RS_61] + SHUFFLE [RS_58] PartitionCols:_col0, _col1, _col2, _col3, _col4, _col5, _col6 - Group By Operator [GBY_60] (rows=80000000 width=764) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"],aggregations:["sum(_col7)"],keys:_col0, _col1, _col2, _col3, _col4, _col5, _col6 - Select Operator [SEL_58] (rows=101084444 width=1093) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] - Merge Join Operator [MERGEJOIN_467] (rows=101084444 width=1093) - Conds:RS_55._col1=RS_522._col0(Inner),Output:["_col2","_col3","_col4","_col5","_col9","_col10","_col11","_col12","_col13","_col14","_col15"] - <-Map 38 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_522] - PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_517] - <-Reducer 16 [SIMPLE_EDGE] - SHUFFLE [RS_55] - PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_466] (rows=101084444 width=445) - Conds:RS_541._col0=RS_495._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5"] - <-Map 31 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_495] - PartitionCols:_col0 - Select Operator [SEL_485] (rows=652 width=8) - Output:["_col0"] - Filter Operator [FIL_481] (rows=652 width=8) - predicate:((d_year = 2001) and d_date_sk is not null) - Please refer to the previous TableScan [TS_111] - <-Map 15 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_541] - PartitionCols:_col0 - Select Operator [SEL_540] (rows=285117831 width=453) - Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - Filter Operator [FIL_539] (rows=285117831 width=453) - predicate:((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_sold_date_sk is not null) - TableScan [TS_43] (rows=287989836 width=453) - default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["cs_sold_date_sk","cs_bill_customer_sk","cs_ext_discount_amt","cs_ext_sales_price","cs_ext_wholesale_cost","cs_ext_list_price"] - <-Reducer 36 [BROADCAST_EDGE] vectorized - BROADCAST [RS_538] - Group By Operator [GBY_537] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 31 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_509] - Group By Operator [GBY_503] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_496] (rows=652 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_485] + Group By Operator [GBY_57] (rows=51391963 width=764) + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"],aggregations:["sum(_col2)"],keys:_col5, _col6, _col7, _col8, _col9, _col10, _col11 + Merge Join Operator [MERGEJOIN_461] (rows=51391963 width=764) + Conds:RS_53._col1=RS_514._col0(Inner),Output:["_col2","_col5","_col6","_col7","_col8","_col9","_col10","_col11"] + <-Map 38 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_514] + PartitionCols:_col0 + Please refer to the previous Select Operator [SEL_509] + <-Reducer 16 [SIMPLE_EDGE] + SHUFFLE [RS_53] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_460] (rows=51391963 width=115) + Conds:RS_50._col0=RS_489._col0(Inner),Output:["_col1","_col2"] + <-Map 31 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_489] + PartitionCols:_col0 + Select Operator [SEL_479] (rows=652 width=4) + Output:["_col0"] + Filter Operator [FIL_475] (rows=652 width=8) + predicate:((d_year = 2001) and d_date_sk is not null) + Please refer to the previous TableScan [TS_106] + <-Map 15 [SIMPLE_EDGE] + SHUFFLE [RS_50] + PartitionCols:_col0 + Select Operator [SEL_43] (rows=143930993 width=119) + Output:["_col0","_col1","_col2"] + Filter Operator [FIL_241] (rows=143930993 width=455) + predicate:((ws_sold_date_sk BETWEEN DynamicValue(RS_51_date_dim_d_date_sk_min) AND DynamicValue(RS_51_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_51_date_dim_d_date_sk_bloom_filter))) and ws_bill_customer_sk is not null and ws_sold_date_sk is not null) + TableScan [TS_41] (rows=144002668 width=455) + default@web_sales,web_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_sold_date_sk","ws_bill_customer_sk","ws_ext_discount_amt","ws_ext_sales_price","ws_ext_wholesale_cost","ws_ext_list_price"] + <-Reducer 36 [BROADCAST_EDGE] vectorized + BROADCAST [RS_528] + Group By Operator [GBY_527] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 31 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_503] + Group By Operator [GBY_497] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_490] (rows=652 width=4) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_479] <-Reducer 5 [ONE_TO_ONE_EDGE] - FORWARD [RS_132] + FORWARD [RS_126] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_474] (rows=31888273 width=324) - Conds:RS_526._col0=RS_536._col0(Inner),Output:["_col1","_col2","_col3"] + Merge Join Operator [MERGEJOIN_468] (rows=31888273 width=324) + Conds:RS_518._col0=RS_526._col0(Inner),Output:["_col1","_col2","_col3"] <-Reducer 14 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_536] + SHUFFLE [RS_526] PartitionCols:_col0 - Select Operator [SEL_535] (rows=26666666 width=212) + Select Operator [SEL_525] (rows=26666666 width=212) Output:["_col0","_col1"] - Filter Operator [FIL_534] (rows=26666666 width=212) + Filter Operator [FIL_524] (rows=26666666 width=212) predicate:(_col7 > 0) - Select Operator [SEL_533] (rows=80000000 width=212) + Select Operator [SEL_523] (rows=80000000 width=212) Output:["_col0","_col7"] - Group By Operator [GBY_532] (rows=80000000 width=764) + Group By Operator [GBY_522] (rows=80000000 width=764) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4, KEY._col5, KEY._col6 <-Reducer 13 [SIMPLE_EDGE] - SHUFFLE [RS_39] + SHUFFLE [RS_37] PartitionCols:_col0, _col1, _col2, _col3, _col4, _col5, _col6 - Group By Operator [GBY_38] (rows=80000000 width=764) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"],aggregations:["sum(_col7)"],keys:_col0, _col1, _col2, _col3, _col4, _col5, _col6 - Select Operator [SEL_36] (rows=187573258 width=1043) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] - Merge Join Operator [MERGEJOIN_465] (rows=187573258 width=1043) - Conds:RS_33._col1=RS_521._col0(Inner),Output:["_col2","_col3","_col4","_col5","_col9","_col10","_col11","_col12","_col13","_col14","_col15"] - <-Map 38 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_521] - PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_517] - <-Reducer 12 [SIMPLE_EDGE] - SHUFFLE [RS_33] - PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_464] (rows=187573258 width=395) - Conds:RS_531._col0=RS_493._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5"] - <-Map 31 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_493] - PartitionCols:_col0 - Select Operator [SEL_484] (rows=652 width=8) - Output:["_col0"] - Filter Operator [FIL_480] (rows=652 width=8) - predicate:((d_year = 2001) and d_date_sk is not null) - Please refer to the previous TableScan [TS_111] - <-Map 11 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_531] - PartitionCols:_col0 - Select Operator [SEL_530] (rows=525327388 width=435) - Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - Filter Operator [FIL_529] (rows=525327388 width=435) - predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_31_date_dim_d_date_sk_min) AND DynamicValue(RS_31_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_31_date_dim_d_date_sk_bloom_filter))) and ss_customer_sk is not null and ss_sold_date_sk is not null) - TableScan [TS_21] (rows=575995635 width=435) - default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_customer_sk","ss_ext_discount_amt","ss_ext_sales_price","ss_ext_wholesale_cost","ss_ext_list_price"] - <-Reducer 35 [BROADCAST_EDGE] vectorized - BROADCAST [RS_528] - Group By Operator [GBY_527] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 31 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_508] - Group By Operator [GBY_502] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_494] (rows=652 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_484] + Group By Operator [GBY_36] (rows=80000000 width=764) + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"],aggregations:["sum(_col2)"],keys:_col5, _col6, _col7, _col8, _col9, _col10, _col11 + Merge Join Operator [MERGEJOIN_459] (rows=187573258 width=764) + Conds:RS_32._col1=RS_513._col0(Inner),Output:["_col2","_col5","_col6","_col7","_col8","_col9","_col10","_col11"] + <-Map 38 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_513] + PartitionCols:_col0 + Please refer to the previous Select Operator [SEL_509] + <-Reducer 12 [SIMPLE_EDGE] + SHUFFLE [RS_32] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_458] (rows=187573258 width=115) + Conds:RS_29._col0=RS_487._col0(Inner),Output:["_col1","_col2"] + <-Map 31 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_487] + PartitionCols:_col0 + Select Operator [SEL_478] (rows=652 width=4) + Output:["_col0"] + Filter Operator [FIL_474] (rows=652 width=8) + predicate:((d_year = 2001) and d_date_sk is not null) + Please refer to the previous TableScan [TS_106] + <-Map 11 [SIMPLE_EDGE] + SHUFFLE [RS_29] + PartitionCols:_col0 + Select Operator [SEL_22] (rows=525327388 width=119) + Output:["_col0","_col1","_col2"] + Filter Operator [FIL_238] (rows=525327388 width=435) + predicate:((ss_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(ss_sold_date_sk, DynamicValue(RS_30_date_dim_d_date_sk_bloom_filter))) and ss_customer_sk is not null and ss_sold_date_sk is not null) + TableScan [TS_20] (rows=575995635 width=435) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_customer_sk","ss_ext_discount_amt","ss_ext_sales_price","ss_ext_wholesale_cost","ss_ext_list_price"] + <-Reducer 35 [BROADCAST_EDGE] vectorized + BROADCAST [RS_520] + Group By Operator [GBY_519] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 31 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_502] + Group By Operator [GBY_496] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_488] (rows=652 width=4) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_478] <-Reducer 4 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_526] + SHUFFLE [RS_518] PartitionCols:_col0 - Select Operator [SEL_525] (rows=51391963 width=212) + Select Operator [SEL_517] (rows=51391963 width=212) Output:["_col0","_col1"] - Group By Operator [GBY_524] (rows=51391963 width=764) + Group By Operator [GBY_516] (rows=51391963 width=764) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4, KEY._col5, KEY._col6 <-Reducer 3 [SIMPLE_EDGE] - SHUFFLE [RS_18] + SHUFFLE [RS_17] PartitionCols:_col0, _col1, _col2, _col3, _col4, _col5, _col6 - Group By Operator [GBY_17] (rows=51391963 width=764) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"],aggregations:["sum(_col7)"],keys:_col0, _col1, _col2, _col3, _col4, _col5, _col6 - Select Operator [SEL_15] (rows=51391963 width=1099) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] - Merge Join Operator [MERGEJOIN_463] (rows=51391963 width=1099) - Conds:RS_12._col1=RS_520._col0(Inner),Output:["_col2","_col3","_col4","_col5","_col9","_col10","_col11","_col12","_col13","_col14","_col15"] - <-Map 38 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_520] - PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_517] - <-Reducer 2 [SIMPLE_EDGE] - SHUFFLE [RS_12] - PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_462] (rows=51391963 width=451) - Conds:RS_515._col0=RS_491._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5"] - <-Map 31 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_491] - PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_483] - <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_515] - PartitionCols:_col0 - Select Operator [SEL_514] (rows=143930993 width=455) - Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - Filter Operator [FIL_513] (rows=143930993 width=455) - predicate:((ws_sold_date_sk BETWEEN DynamicValue(RS_10_date_dim_d_date_sk_min) AND DynamicValue(RS_10_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_10_date_dim_d_date_sk_bloom_filter))) and ws_bill_customer_sk is not null and ws_sold_date_sk is not null) - TableScan [TS_0] (rows=144002668 width=455) - default@web_sales,web_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_sold_date_sk","ws_bill_customer_sk","ws_ext_discount_amt","ws_ext_sales_price","ws_ext_wholesale_cost","ws_ext_list_price"] - <-Reducer 34 [BROADCAST_EDGE] vectorized - BROADCAST [RS_512] - Group By Operator [GBY_511] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 31 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_507] - Group By Operator [GBY_501] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_492] (rows=652 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_483] + Group By Operator [GBY_16] (rows=51391963 width=764) + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"],aggregations:["sum(_col2)"],keys:_col5, _col6, _col7, _col8, _col9, _col10, _col11 + Merge Join Operator [MERGEJOIN_457] (rows=51391963 width=764) + Conds:RS_12._col1=RS_512._col0(Inner),Output:["_col2","_col5","_col6","_col7","_col8","_col9","_col10","_col11"] + <-Map 38 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_512] + PartitionCols:_col0 + Please refer to the previous Select Operator [SEL_509] + <-Reducer 2 [SIMPLE_EDGE] + SHUFFLE [RS_12] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_456] (rows=51391963 width=115) + Conds:RS_9._col0=RS_485._col0(Inner),Output:["_col1","_col2"] + <-Map 31 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_485] + PartitionCols:_col0 + Please refer to the previous Select Operator [SEL_477] + <-Map 1 [SIMPLE_EDGE] + SHUFFLE [RS_9] + PartitionCols:_col0 + Select Operator [SEL_2] (rows=143930993 width=119) + Output:["_col0","_col1","_col2"] + Filter Operator [FIL_235] (rows=143930993 width=455) + predicate:((ws_sold_date_sk BETWEEN DynamicValue(RS_10_date_dim_d_date_sk_min) AND DynamicValue(RS_10_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_10_date_dim_d_date_sk_bloom_filter))) and ws_bill_customer_sk is not null and ws_sold_date_sk is not null) + TableScan [TS_0] (rows=144002668 width=455) + default@web_sales,web_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_sold_date_sk","ws_bill_customer_sk","ws_ext_discount_amt","ws_ext_sales_price","ws_ext_wholesale_cost","ws_ext_list_price"] + <-Reducer 34 [BROADCAST_EDGE] vectorized + BROADCAST [RS_506] + Group By Operator [GBY_505] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 31 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_501] + Group By Operator [GBY_495] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_486] (rows=652 width=4) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_477] diff --git ql/src/test/results/clientpositive/perf/tez/query40.q.out ql/src/test/results/clientpositive/perf/tez/query40.q.out index 1cca18d3069..6e566e14b6b 100644 --- ql/src/test/results/clientpositive/perf/tez/query40.q.out +++ ql/src/test/results/clientpositive/perf/tez/query40.q.out @@ -96,12 +96,12 @@ Stage-0 PartitionCols:_col0, _col1 Group By Operator [GBY_29] (rows=5757278 width=410) Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(_col2)","sum(_col3)"],keys:_col0, _col1 - Top N Key Operator [TNK_55] (rows=5757278 width=364) + Top N Key Operator [TNK_55] (rows=5757278 width=278) keys:_col0, _col1,sort order:++,top n:100 - Select Operator [SEL_27] (rows=5757278 width=364) + Select Operator [SEL_27] (rows=5757278 width=278) Output:["_col0","_col1","_col2","_col3"] - Merge Join Operator [MERGEJOIN_101] (rows=5757278 width=364) - Conds:RS_24._col1=RS_126._col0(Inner),Output:["_col4","_col7","_col9","_col11","_col14"] + Merge Join Operator [MERGEJOIN_101] (rows=5757278 width=278) + Conds:RS_24._col1=RS_126._col0(Inner),Output:["_col4","_col7","_col9","_col10","_col12","_col14"] <-Map 13 [SIMPLE_EDGE] vectorized SHUFFLE [RS_126] PartitionCols:_col0 @@ -114,12 +114,12 @@ Stage-0 <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_24] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_100] (rows=5757278 width=281) - Conds:RS_21._col2=RS_112._col0(Inner),Output:["_col1","_col4","_col7","_col9","_col11"] + Merge Join Operator [MERGEJOIN_100] (rows=5757278 width=195) + Conds:RS_21._col2=RS_112._col0(Inner),Output:["_col1","_col4","_col7","_col9","_col10","_col12"] <-Map 11 [SIMPLE_EDGE] vectorized SHUFFLE [RS_112] PartitionCols:_col0 - Select Operator [SEL_111] (rows=51333 width=215) + Select Operator [SEL_111] (rows=51333 width=104) Output:["_col0","_col1"] Filter Operator [FIL_110] (rows=51333 width=215) predicate:(i_current_price BETWEEN 0.99 AND 1.49 and i_item_sk is not null) @@ -128,13 +128,13 @@ Stage-0 <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_21] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_99] (rows=51815831 width=210) - Conds:RS_18._col0=RS_104._col0(Inner),Output:["_col1","_col2","_col4","_col7","_col9"] + Merge Join Operator [MERGEJOIN_99] (rows=51815831 width=124) + Conds:RS_18._col0=RS_104._col0(Inner),Output:["_col1","_col2","_col4","_col7","_col9","_col10"] <-Map 9 [SIMPLE_EDGE] vectorized SHUFFLE [RS_104] PartitionCols:_col0 - Select Operator [SEL_103] (rows=8116 width=98) - Output:["_col0","_col1"] + Select Operator [SEL_103] (rows=8116 width=12) + Output:["_col0","_col1","_col2"] Filter Operator [FIL_102] (rows=8116 width=98) predicate:(CAST( d_date AS TIMESTAMP) BETWEEN TIMESTAMP'1998-03-09 00:00:00' AND TIMESTAMP'1998-05-08 00:00:00' and d_date_sk is not null) TableScan [TS_6] (rows=73049 width=98) diff --git ql/src/test/results/clientpositive/perf/tez/query42.q.out ql/src/test/results/clientpositive/perf/tez/query42.q.out index a458f5e095a..0a01d713db2 100644 --- ql/src/test/results/clientpositive/perf/tez/query42.q.out +++ ql/src/test/results/clientpositive/perf/tez/query42.q.out @@ -79,13 +79,13 @@ Stage-0 SHUFFLE [RS_17] PartitionCols:_col0, _col1 Group By Operator [GBY_16] (rows=120 width=206) - Output:["_col0","_col1","_col2"],aggregations:["sum(_col2)"],keys:_col7, _col8 + Output:["_col0","_col1","_col2"],aggregations:["sum(_col2)"],keys:_col5, _col6 Merge Join Operator [MERGEJOIN_54] (rows=2301098 width=94) - Conds:RS_12._col1=RS_65._col0(Inner),Output:["_col2","_col7","_col8"] + Conds:RS_12._col1=RS_65._col0(Inner),Output:["_col2","_col5","_col6"] <-Map 8 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_65] PartitionCols:_col0 - Select Operator [SEL_64] (rows=7333 width=101) + Select Operator [SEL_64] (rows=7333 width=97) Output:["_col0","_col1","_col2"] Filter Operator [FIL_63] (rows=7333 width=101) predicate:((i_manager_id = 1) and i_item_sk is not null) @@ -99,7 +99,7 @@ Stage-0 <-Map 6 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_57] PartitionCols:_col0 - Select Operator [SEL_56] (rows=50 width=12) + Select Operator [SEL_56] (rows=50 width=4) Output:["_col0"] Filter Operator [FIL_55] (rows=50 width=12) predicate:((d_moy = 12) and (d_year = 1998) and d_date_sk is not null) diff --git ql/src/test/results/clientpositive/perf/tez/query43.q.out ql/src/test/results/clientpositive/perf/tez/query43.q.out index f75929bbb75..66ded7d7f4f 100644 --- ql/src/test/results/clientpositive/perf/tez/query43.q.out +++ ql/src/test/results/clientpositive/perf/tez/query43.q.out @@ -70,18 +70,18 @@ Stage-0 <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_18] PartitionCols:_col0, _col1 - Group By Operator [GBY_17] (rows=176297 width=972) + Group By Operator [GBY_17] (rows=142538 width=972) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"],aggregations:["sum(_col2)","sum(_col3)","sum(_col4)","sum(_col5)","sum(_col6)","sum(_col7)","sum(_col8)"],keys:_col0, _col1 - Top N Key Operator [TNK_33] (rows=37536846 width=320) + Top N Key Operator [TNK_33] (rows=37536846 width=257) keys:_col0, _col1,sort order:++,top n:100 - Select Operator [SEL_15] (rows=37536846 width=320) + Select Operator [SEL_15] (rows=37536846 width=257) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"] - Merge Join Operator [MERGEJOIN_55] (rows=37536846 width=320) - Conds:RS_12._col1=RS_66._col0(Inner),Output:["_col2","_col5","_col7","_col8"] + Merge Join Operator [MERGEJOIN_55] (rows=37536846 width=257) + Conds:RS_12._col1=RS_66._col0(Inner),Output:["_col2","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col12","_col13"] <-Map 8 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_66] PartitionCols:_col0 - Select Operator [SEL_65] (rows=341 width=304) + Select Operator [SEL_65] (rows=341 width=192) Output:["_col0","_col1","_col2"] Filter Operator [FIL_64] (rows=341 width=303) predicate:((s_gmt_offset = -6) and s_store_sk is not null) @@ -90,13 +90,13 @@ Stage-0 <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_12] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_54] (rows=187574154 width=192) - Conds:RS_74._col0=RS_58._col0(Inner),Output:["_col1","_col2","_col5"] + Merge Join Operator [MERGEJOIN_54] (rows=187574154 width=129) + Conds:RS_74._col0=RS_58._col0(Inner),Output:["_col1","_col2","_col4","_col5","_col6","_col7","_col8","_col9","_col10"] <-Map 6 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_58] PartitionCols:_col0 - Select Operator [SEL_57] (rows=652 width=99) - Output:["_col0","_col2"] + Select Operator [SEL_57] (rows=652 width=32) + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] Filter Operator [FIL_56] (rows=652 width=99) predicate:((d_year = 1998) and d_date_sk is not null) TableScan [TS_3] (rows=73049 width=99) diff --git ql/src/test/results/clientpositive/perf/tez/query46.q.out ql/src/test/results/clientpositive/perf/tez/query46.q.out index 6d394e73175..1328437ac43 100644 --- ql/src/test/results/clientpositive/perf/tez/query46.q.out +++ ql/src/test/results/clientpositive/perf/tez/query46.q.out @@ -148,9 +148,9 @@ Stage-0 SHUFFLE [RS_35] PartitionCols:_col0, _col1, _col2, _col3 Group By Operator [GBY_34] (rows=20351707 width=321) - Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(_col6)","sum(_col7)"],keys:_col1, _col17, _col3, _col5 + Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(_col6)","sum(_col7)"],keys:_col1, _col12, _col3, _col5 Merge Join Operator [MERGEJOIN_144] (rows=20351707 width=97) - Conds:RS_30._col3=RS_152._col0(Inner),Output:["_col1","_col3","_col5","_col6","_col7","_col17"] + Conds:RS_30._col3=RS_152._col0(Inner),Output:["_col1","_col3","_col5","_col6","_col7","_col12"] <-Map 5 [SIMPLE_EDGE] vectorized SHUFFLE [RS_152] PartitionCols:_col0 @@ -163,7 +163,7 @@ Stage-0 <-Map 16 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_171] PartitionCols:_col0 - Select Operator [SEL_170] (rows=1855 width=12) + Select Operator [SEL_170] (rows=1855 width=4) Output:["_col0"] Filter Operator [FIL_169] (rows=1855 width=12) predicate:(((hd_dep_count = 2) or (hd_vehicle_count = 1)) and hd_demo_sk is not null) @@ -177,7 +177,7 @@ Stage-0 <-Map 14 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_163] PartitionCols:_col0 - Select Operator [SEL_162] (rows=85 width=97) + Select Operator [SEL_162] (rows=85 width=4) Output:["_col0"] Filter Operator [FIL_161] (rows=85 width=97) predicate:((s_city) IN ('Cedar Grove', 'Wildwood', 'Union', 'Salem', 'Highland Park') and s_store_sk is not null) @@ -191,7 +191,7 @@ Stage-0 <-Map 12 [SIMPLE_EDGE] vectorized SHUFFLE [RS_155] PartitionCols:_col0 - Select Operator [SEL_154] (rows=783 width=12) + Select Operator [SEL_154] (rows=783 width=4) Output:["_col0"] Filter Operator [FIL_153] (rows=783 width=12) predicate:((d_dow) IN (6, 0) and (d_year) IN (1998, 1999, 2000) and d_date_sk is not null) diff --git ql/src/test/results/clientpositive/perf/tez/query47.q.out ql/src/test/results/clientpositive/perf/tez/query47.q.out index 75ab3172dcf..04c64b405fa 100644 --- ql/src/test/results/clientpositive/perf/tez/query47.q.out +++ ql/src/test/results/clientpositive/perf/tez/query47.q.out @@ -139,10 +139,10 @@ Stage-0 Select Operator [SEL_109] (rows=241454 width=658) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] Merge Join Operator [MERGEJOIN_278] (rows=241454 width=546) - Conds:RS_106._col6, _col7, _col8, _col9, _col14=RS_306._col0, _col1, _col2, _col3, (_col5 - 1)(Inner),Output:["_col4","_col6","_col10","_col11","_col12","_col13","_col19"] + Conds:RS_106._col6, _col7, _col8, _col9, _col14=RS_306._col0, _col1, _col2, _col3, _col5(Inner),Output:["_col4","_col6","_col10","_col11","_col12","_col13","_col19"] <-Reducer 6 [SIMPLE_EDGE] vectorized SHUFFLE [RS_306] - PartitionCols:_col0, _col1, _col2, _col3, (_col5 - 1) + PartitionCols:_col0, _col1, _col2, _col3, _col5 Select Operator [SEL_304] (rows=162257387 width=485) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] Filter Operator [FIL_302] (rows=162257387 width=489) @@ -224,10 +224,10 @@ Stage-0 FORWARD [RS_106] PartitionCols:_col6, _col7, _col8, _col9, _col14 Merge Join Operator [MERGEJOIN_277] (rows=241454 width=717) - Conds:RS_307._col0, _col1, _col2, _col3, (_col5 + 1)=RS_318._col0, _col1, _col2, _col3, _col8(Inner),Output:["_col4","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14"] + Conds:RS_307._col0, _col1, _col2, _col3, _col5=RS_318._col0, _col1, _col2, _col3, _col8(Inner),Output:["_col4","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14"] <-Reducer 6 [SIMPLE_EDGE] vectorized SHUFFLE [RS_307] - PartitionCols:_col0, _col1, _col2, _col3, (_col5 + 1) + PartitionCols:_col0, _col1, _col2, _col3, _col5 Select Operator [SEL_305] (rows=162257387 width=485) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] Filter Operator [FIL_303] (rows=162257387 width=489) diff --git ql/src/test/results/clientpositive/perf/tez/query48.q.out ql/src/test/results/clientpositive/perf/tez/query48.q.out index 76b4ce1fe18..1f63e954853 100644 --- ql/src/test/results/clientpositive/perf/tez/query48.q.out +++ ql/src/test/results/clientpositive/perf/tez/query48.q.out @@ -143,15 +143,15 @@ POSTHOOK: Output: hdfs://### HDFS PATH ### Plan optimized by CBO. Vertex dependency in root stage -Map 7 <- Reducer 11 (BROADCAST_EDGE), Reducer 13 (BROADCAST_EDGE), Reducer 9 (BROADCAST_EDGE) -Reducer 11 <- Map 10 (CUSTOM_SIMPLE_EDGE) +Map 8 <- Reducer 10 (BROADCAST_EDGE), Reducer 13 (BROADCAST_EDGE), Reducer 7 (BROADCAST_EDGE) +Reducer 10 <- Map 9 (CUSTOM_SIMPLE_EDGE) Reducer 13 <- Map 12 (CUSTOM_SIMPLE_EDGE) -Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 7 (SIMPLE_EDGE) -Reducer 3 <- Map 8 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) -Reducer 4 <- Map 10 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) +Reducer 3 <- Map 9 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) +Reducer 4 <- Map 11 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) Reducer 5 <- Map 12 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) Reducer 6 <- Reducer 5 (CUSTOM_SIMPLE_EDGE) -Reducer 9 <- Map 8 (CUSTOM_SIMPLE_EDGE) +Reducer 7 <- Map 1 (CUSTOM_SIMPLE_EDGE) Stage-0 Fetch Operator @@ -165,103 +165,103 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_30] Group By Operator [GBY_29] (rows=1 width=8) Output:["_col0"],aggregations:["sum(_col5)"] - Select Operator [SEL_28] (rows=25203 width=86) + Select Operator [SEL_28] (rows=20247 width=24) Output:["_col5"] - Filter Operator [FIL_27] (rows=25203 width=86) - predicate:(((_col14) IN ('KY', 'GA', 'NM') and _col7 BETWEEN 0 AND 2000) or ((_col14) IN ('MT', 'OR', 'IN') and _col7 BETWEEN 150 AND 3000) or ((_col14) IN ('WI', 'MO', 'WV') and _col7 BETWEEN 50 AND 25000)) - Merge Join Operator [MERGEJOIN_96] (rows=75613 width=86) - Conds:RS_24._col3=RS_118._col0(Inner),Output:["_col5","_col7","_col14"] + Filter Operator [FIL_27] (rows=20247 width=24) + predicate:((_col12 and _col6) or (_col13 and _col7) or (_col14 and _col8)) + Merge Join Operator [MERGEJOIN_96] (rows=26999 width=24) + Conds:RS_24._col3=RS_115._col0(Inner),Output:["_col5","_col6","_col7","_col8","_col12","_col13","_col14"] <-Map 12 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_118] + SHUFFLE [RS_115] PartitionCols:_col0 - Select Operator [SEL_117] (rows=3529412 width=187) - Output:["_col0","_col1"] - Filter Operator [FIL_116] (rows=3529412 width=187) + Select Operator [SEL_114] (rows=3529412 width=16) + Output:["_col0","_col1","_col2","_col3"] + Filter Operator [FIL_113] (rows=3529412 width=187) predicate:((ca_country = 'United States') and (ca_state) IN ('KY', 'GA', 'NM', 'MT', 'OR', 'IN', 'WI', 'MO', 'WV') and ca_address_sk is not null) TableScan [TS_12] (rows=40000000 width=187) default@customer_address,customer_address,Tbl:COMPLETE,Col:COMPLETE,Output:["ca_address_sk","ca_state","ca_country"] <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_24] PartitionCols:_col3 - Merge Join Operator [MERGEJOIN_95] (rows=856941 width=0) - Conds:RS_21._col2=RS_110._col0(Inner),Output:["_col3","_col5","_col7"] - <-Map 10 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_110] + Merge Join Operator [MERGEJOIN_95] (rows=305980 width=12) + Conds:RS_21._col4=RS_126._col0(Inner),Output:["_col3","_col5","_col6","_col7","_col8"] + <-Map 11 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_126] PartitionCols:_col0 - Select Operator [SEL_109] (rows=29552 width=184) + Select Operator [SEL_125] (rows=1704 width=4) Output:["_col0"] - Filter Operator [FIL_108] (rows=29552 width=183) - predicate:((cd_education_status = '4 yr Degree') and (cd_marital_status = 'M') and cd_demo_sk is not null) - TableScan [TS_9] (rows=1861800 width=183) - default@customer_demographics,customer_demographics,Tbl:COMPLETE,Col:COMPLETE,Output:["cd_demo_sk","cd_marital_status","cd_education_status"] + Filter Operator [FIL_124] (rows=1704 width=4) + predicate:s_store_sk is not null + TableScan [TS_9] (rows=1704 width=4) + default@store,store,Tbl:COMPLETE,Col:COMPLETE,Output:["s_store_sk"] <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_21] - PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_94] (rows=19008181 width=108) - Conds:RS_18._col1=RS_102._col0(Inner),Output:["_col2","_col3","_col5","_col7"] - <-Map 8 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_102] + PartitionCols:_col4 + Merge Join Operator [MERGEJOIN_94] (rows=305980 width=12) + Conds:RS_18._col1=RS_107._col0(Inner),Output:["_col3","_col4","_col5","_col6","_col7","_col8"] + <-Map 9 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_107] PartitionCols:_col0 - Select Operator [SEL_101] (rows=652 width=8) + Select Operator [SEL_106] (rows=652 width=4) Output:["_col0"] - Filter Operator [FIL_100] (rows=652 width=8) + Filter Operator [FIL_105] (rows=652 width=8) predicate:((d_year = 1998) and d_date_sk is not null) TableScan [TS_6] (rows=73049 width=8) default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_18] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_93] (rows=53235296 width=122) - Conds:RS_99._col0=RS_126._col3(Inner),Output:["_col1","_col2","_col3","_col5","_col7"] + Merge Join Operator [MERGEJOIN_93] (rows=856943 width=12) + Conds:RS_99._col0=RS_123._col1(Inner),Output:["_col1","_col3","_col4","_col5","_col6","_col7","_col8"] <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_99] + PARTITION_ONLY_SHUFFLE [RS_99] PartitionCols:_col0 - Select Operator [SEL_98] (rows=1704 width=4) + Select Operator [SEL_98] (rows=29552 width=4) Output:["_col0"] - Filter Operator [FIL_97] (rows=1704 width=4) - predicate:s_store_sk is not null - TableScan [TS_0] (rows=1704 width=4) - default@store,store,Tbl:COMPLETE,Col:COMPLETE,Output:["s_store_sk"] - <-Map 7 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_126] - PartitionCols:_col3 - Select Operator [SEL_125] (rows=53235296 width=233) - Output:["_col0","_col1","_col2","_col3","_col4","_col6"] - Filter Operator [FIL_124] (rows=53235296 width=233) - predicate:((ss_addr_sk BETWEEN DynamicValue(RS_25_customer_address_ca_address_sk_min) AND DynamicValue(RS_25_customer_address_ca_address_sk_max) and in_bloom_filter(ss_addr_sk, DynamicValue(RS_25_customer_address_ca_address_sk_bloom_filter))) and (ss_cdemo_sk BETWEEN DynamicValue(RS_22_customer_demographics_cd_demo_sk_min) AND DynamicValue(RS_22_customer_demographics_cd_demo_sk_max) and in_bloom_filter(ss_cdemo_sk, DynamicValue(RS_22_customer_demographics_cd_demo_sk_bloom_filter))) and (ss_net_profit BETWEEN 0 AND 2000 or ss_net_profit BETWEEN 150 AND 3000 or ss_net_profit BETWEEN 50 AND 25000) and (ss_sales_price BETWEEN 100 AND 150 or ss_sales_price BETWEEN 50 AND 100 or ss_sales_price BETWEEN 150 AND 200) and (ss_sold_date_sk BETWEEN DynamicValue(RS_19_date_dim_d_date_sk_min) AND DynamicValue(RS_19_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_19_date_dim_d_date_sk_bloom_filter))) and ss_addr_sk is not null and ss_cdemo_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null) + Filter Operator [FIL_97] (rows=29552 width=183) + predicate:((cd_education_status = '4 yr Degree') and (cd_marital_status = 'M') and cd_demo_sk is not null) + TableScan [TS_0] (rows=1861800 width=183) + default@customer_demographics,customer_demographics,Tbl:COMPLETE,Col:COMPLETE,Output:["cd_demo_sk","cd_marital_status","cd_education_status"] + <-Map 8 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_123] + PartitionCols:_col1 + Select Operator [SEL_122] (rows=53235296 width=31) + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] + Filter Operator [FIL_121] (rows=53235296 width=233) + predicate:((ss_addr_sk BETWEEN DynamicValue(RS_25_customer_address_ca_address_sk_min) AND DynamicValue(RS_25_customer_address_ca_address_sk_max) and in_bloom_filter(ss_addr_sk, DynamicValue(RS_25_customer_address_ca_address_sk_bloom_filter))) and (ss_cdemo_sk BETWEEN DynamicValue(RS_15_customer_demographics_cd_demo_sk_min) AND DynamicValue(RS_15_customer_demographics_cd_demo_sk_max) and in_bloom_filter(ss_cdemo_sk, DynamicValue(RS_15_customer_demographics_cd_demo_sk_bloom_filter))) and (ss_net_profit BETWEEN 0 AND 2000 or ss_net_profit BETWEEN 150 AND 3000 or ss_net_profit BETWEEN 50 AND 25000) and (ss_sales_price BETWEEN 100 AND 150 or ss_sales_price BETWEEN 50 AND 100 or ss_sales_price BETWEEN 150 AND 200) and (ss_sold_date_sk BETWEEN DynamicValue(RS_19_date_dim_d_date_sk_min) AND DynamicValue(RS_19_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_19_date_dim_d_date_sk_bloom_filter))) and ss_addr_sk is not null and ss_cdemo_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null) TableScan [TS_3] (rows=575995635 width=233) default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_cdemo_sk","ss_addr_sk","ss_store_sk","ss_quantity","ss_sales_price","ss_net_profit"] - <-Reducer 11 [BROADCAST_EDGE] vectorized - BROADCAST [RS_115] - Group By Operator [GBY_114] (rows=1 width=12) + <-Reducer 10 [BROADCAST_EDGE] vectorized + BROADCAST [RS_112] + Group By Operator [GBY_111] (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_113] - Group By Operator [GBY_112] (rows=1 width=12) + <-Map 9 [CUSTOM_SIMPLE_EDGE] vectorized + SHUFFLE [RS_110] + Group By Operator [GBY_109] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_111] (rows=29552 width=4) + Select Operator [SEL_108] (rows=652 width=4) Output:["_col0"] - Please refer to the previous Select Operator [SEL_109] + Please refer to the previous Select Operator [SEL_106] <-Reducer 13 [BROADCAST_EDGE] vectorized - BROADCAST [RS_123] - Group By Operator [GBY_122] (rows=1 width=12) + BROADCAST [RS_120] + Group By Operator [GBY_119] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=3529412)"] <-Map 12 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_121] - Group By Operator [GBY_120] (rows=1 width=12) + SHUFFLE [RS_118] + Group By Operator [GBY_117] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=3529412)"] - Select Operator [SEL_119] (rows=3529412 width=4) + Select Operator [SEL_116] (rows=3529412 width=4) Output:["_col0"] - Please refer to the previous Select Operator [SEL_117] - <-Reducer 9 [BROADCAST_EDGE] vectorized - BROADCAST [RS_107] - Group By Operator [GBY_106] (rows=1 width=12) + Please refer to the previous Select Operator [SEL_114] + <-Reducer 7 [BROADCAST_EDGE] vectorized + BROADCAST [RS_104] + Group By Operator [GBY_103] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 8 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_105] - Group By Operator [GBY_104] (rows=1 width=12) + <-Map 1 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_102] + Group By Operator [GBY_101] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_103] (rows=652 width=4) + Select Operator [SEL_100] (rows=29552 width=4) Output:["_col0"] - Please refer to the previous Select Operator [SEL_101] + Please refer to the previous Select Operator [SEL_98] diff --git ql/src/test/results/clientpositive/perf/tez/query49.q.out ql/src/test/results/clientpositive/perf/tez/query49.q.out index 6fe8e9aa94f..31c98a778c7 100644 --- ql/src/test/results/clientpositive/perf/tez/query49.q.out +++ ql/src/test/results/clientpositive/perf/tez/query49.q.out @@ -299,257 +299,251 @@ Stage-0 limit:100 Stage-1 Reducer 11 vectorized - File Output Operator [FS_310] - Limit [LIM_309] (rows=100 width=215) + File Output Operator [FS_307] + Limit [LIM_306] (rows=100 width=215) Number of rows:100 - Select Operator [SEL_308] (rows=3418 width=215) + Select Operator [SEL_305] (rows=3418 width=215) Output:["_col0","_col1","_col2","_col3","_col4"] <-Reducer 10 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_307] - Select Operator [SEL_306] (rows=3418 width=215) + SHUFFLE [RS_304] + Select Operator [SEL_303] (rows=3418 width=215) Output:["_col0","_col1","_col2","_col3","_col4"] - Group By Operator [GBY_305] (rows=3418 width=215) + Group By Operator [GBY_302] (rows=3418 width=215) Output:["_col0","_col1","_col2","_col3","_col4"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4 <-Union 9 [SIMPLE_EDGE] <-Reducer 24 [CONTAINS] vectorized - Reduce Output Operator [RS_351] + Reduce Output Operator [RS_348] PartitionCols:_col0, _col1, _col2, _col3, _col4 - Group By Operator [GBY_350] (rows=3418 width=215) + Group By Operator [GBY_347] (rows=3418 width=215) Output:["_col0","_col1","_col2","_col3","_col4"],keys:_col0, _col3, _col4, _col1, _col2 - Top N Key Operator [TNK_349] (rows=3418 width=214) + Top N Key Operator [TNK_346] (rows=3418 width=214) keys:_col0, _col3, _col4, _col1, _col2,sort order:+++++,top n:100 - Select Operator [SEL_348] (rows=1142 width=213) + Select Operator [SEL_345] (rows=1142 width=213) Output:["_col0","_col1","_col2","_col3","_col4"] - Filter Operator [FIL_347] (rows=1142 width=248) + Filter Operator [FIL_344] (rows=1142 width=248) predicate:((_col0 <= 10) or (rank_window_1 <= 10)) - PTF Operator [PTF_346] (rows=1714 width=248) + PTF Operator [PTF_343] (rows=1714 width=248) Function definitions:[{},{"name:":"windowingtablefunction","order by:":"(CAST( _col4 AS decimal(15,4)) / CAST( _col5 AS decimal(15,4))) ASC NULLS LAST","partition by:":"0"}] - Select Operator [SEL_345] (rows=1714 width=248) + Select Operator [SEL_342] (rows=1714 width=248) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] <-Reducer 23 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_344] + SHUFFLE [RS_341] PartitionCols:0 - Select Operator [SEL_343] (rows=1714 width=244) + Select Operator [SEL_340] (rows=1714 width=244) Output:["rank_window_0","_col0","_col1","_col2","_col3","_col4"] - PTF Operator [PTF_342] (rows=1714 width=244) + PTF Operator [PTF_339] (rows=1714 width=244) Function definitions:[{},{"name:":"windowingtablefunction","order by:":"(CAST( _col1 AS decimal(15,4)) / CAST( _col2 AS decimal(15,4))) ASC NULLS LAST","partition by:":"0"}] - Select Operator [SEL_341] (rows=1714 width=244) + Select Operator [SEL_338] (rows=1714 width=244) Output:["_col0","_col1","_col2","_col3","_col4"] <-Reducer 22 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_340] + SHUFFLE [RS_337] PartitionCols:0 - Group By Operator [GBY_339] (rows=1714 width=244) + Group By Operator [GBY_336] (rows=1714 width=244) Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)","sum(VALUE._col3)"],keys:KEY._col0 <-Reducer 21 [SIMPLE_EDGE] - SHUFFLE [RS_89] + SHUFFLE [RS_86] PartitionCols:_col0 - Group By Operator [GBY_88] (rows=1714 width=244) - Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["sum(_col1)","sum(_col2)","sum(_col3)","sum(_col4)"],keys:_col0 - Select Operator [SEL_86] (rows=1673571 width=73) - Output:["_col0","_col1","_col2","_col3","_col4"] - Merge Join Operator [MERGEJOIN_237] (rows=1673571 width=73) - Conds:RS_83._col1, _col2=RS_338._col0, _col1(Inner),Output:["_col1","_col3","_col4","_col11","_col12"] - <-Map 30 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_338] - PartitionCols:_col0, _col1 - Select Operator [SEL_337] (rows=19197050 width=119) - Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_336] (rows=19197050 width=119) - predicate:((sr_return_amt > 10000) and sr_item_sk is not null and sr_ticket_number is not null) - TableScan [TS_77] (rows=57591150 width=119) - default@store_returns,sr,Tbl:COMPLETE,Col:COMPLETE,Output:["sr_item_sk","sr_ticket_number","sr_return_quantity","sr_return_amt"] - <-Reducer 20 [SIMPLE_EDGE] - SHUFFLE [RS_83] - PartitionCols:_col1, _col2 - Merge Join Operator [MERGEJOIN_236] (rows=1673571 width=8) - Conds:RS_335._col0=RS_272._col0(Inner),Output:["_col1","_col2","_col3","_col4"] - <-Map 12 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_272] - PartitionCols:_col0 - Select Operator [SEL_267] (rows=50 width=12) - Output:["_col0"] - Filter Operator [FIL_266] (rows=50 width=12) - predicate:((d_moy = 12) and (d_year = 2000) and d_date_sk is not null) - TableScan [TS_3] (rows=73049 width=12) - default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year","d_moy"] - <-Map 29 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_335] - PartitionCols:_col0 - Select Operator [SEL_334] (rows=61119617 width=229) - Output:["_col0","_col1","_col2","_col3","_col4"] - Filter Operator [FIL_333] (rows=61119617 width=229) - predicate:((ss_net_paid > 0) and (ss_net_profit > 1) and (ss_quantity > 0) and (ss_sold_date_sk BETWEEN DynamicValue(RS_81_date_dim_d_date_sk_min) AND DynamicValue(RS_81_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_81_date_dim_d_date_sk_bloom_filter))) and ss_item_sk is not null and ss_sold_date_sk is not null and ss_ticket_number is not null) - TableScan [TS_71] (rows=575995635 width=229) - default@store_sales,sts,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_item_sk","ss_ticket_number","ss_quantity","ss_net_paid","ss_net_profit"] - <-Reducer 25 [BROADCAST_EDGE] vectorized - BROADCAST [RS_332] - Group By Operator [GBY_331] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 12 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_279] - Group By Operator [GBY_276] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_273] (rows=50 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_267] + Group By Operator [GBY_85] (rows=3428 width=244) + Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["sum(_col8)","sum(_col3)","sum(_col9)","sum(_col4)"],keys:_col1 + Merge Join Operator [MERGEJOIN_234] (rows=1673571 width=236) + Conds:RS_81._col1, _col2=RS_335._col0, _col1(Inner),Output:["_col1","_col3","_col4","_col8","_col9"] + <-Map 30 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_335] + PartitionCols:_col0, _col1 + Select Operator [SEL_334] (rows=19197050 width=124) + Output:["_col0","_col1","_col2","_col3"] + Filter Operator [FIL_333] (rows=19197050 width=119) + predicate:((sr_return_amt > 10000) and sr_item_sk is not null and sr_ticket_number is not null) + TableScan [TS_75] (rows=57591150 width=119) + default@store_returns,sr,Tbl:COMPLETE,Col:COMPLETE,Output:["sr_item_sk","sr_ticket_number","sr_return_quantity","sr_return_amt"] + <-Reducer 20 [SIMPLE_EDGE] + SHUFFLE [RS_81] + PartitionCols:_col1, _col2 + Merge Join Operator [MERGEJOIN_233] (rows=1673571 width=124) + Conds:RS_332._col0=RS_269._col0(Inner),Output:["_col1","_col2","_col3","_col4"] + <-Map 12 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_269] + PartitionCols:_col0 + Select Operator [SEL_264] (rows=50 width=4) + Output:["_col0"] + Filter Operator [FIL_263] (rows=50 width=12) + predicate:((d_moy = 12) and (d_year = 2000) and d_date_sk is not null) + TableScan [TS_3] (rows=73049 width=12) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year","d_moy"] + <-Map 29 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_332] + PartitionCols:_col0 + Select Operator [SEL_331] (rows=61119617 width=127) + Output:["_col0","_col1","_col2","_col3","_col4"] + Filter Operator [FIL_330] (rows=61119617 width=229) + predicate:((ss_net_paid > 0) and (ss_net_profit > 1) and (ss_quantity > 0) and (ss_sold_date_sk BETWEEN DynamicValue(RS_79_date_dim_d_date_sk_min) AND DynamicValue(RS_79_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_79_date_dim_d_date_sk_bloom_filter))) and ss_item_sk is not null and ss_sold_date_sk is not null and ss_ticket_number is not null) + TableScan [TS_69] (rows=575995635 width=229) + default@store_sales,sts,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_item_sk","ss_ticket_number","ss_quantity","ss_net_paid","ss_net_profit"] + <-Reducer 25 [BROADCAST_EDGE] vectorized + BROADCAST [RS_329] + Group By Operator [GBY_328] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 12 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_276] + Group By Operator [GBY_273] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_270] (rows=50 width=4) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_264] <-Reducer 8 [CONTAINS] vectorized - Reduce Output Operator [RS_304] + Reduce Output Operator [RS_301] PartitionCols:_col0, _col1, _col2, _col3, _col4 - Group By Operator [GBY_303] (rows=3418 width=215) + Group By Operator [GBY_300] (rows=3418 width=215) Output:["_col0","_col1","_col2","_col3","_col4"],keys:_col0, _col3, _col4, _col1, _col2 - Top N Key Operator [TNK_302] (rows=3418 width=214) + Top N Key Operator [TNK_299] (rows=3418 width=214) keys:_col0, _col3, _col4, _col1, _col2,sort order:+++++,top n:100 - Select Operator [SEL_301] (rows=2276 width=215) + Select Operator [SEL_298] (rows=2276 width=215) Output:["_col0","_col1","_col2","_col3","_col4"] - Group By Operator [GBY_300] (rows=2276 width=215) + Group By Operator [GBY_297] (rows=2276 width=215) Output:["_col0","_col1","_col2","_col3","_col4"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4 <-Union 7 [SIMPLE_EDGE] <-Reducer 18 [CONTAINS] vectorized - Reduce Output Operator [RS_330] + Reduce Output Operator [RS_327] PartitionCols:_col0, _col1, _col2, _col3, _col4 - Group By Operator [GBY_329] (rows=2276 width=215) + Group By Operator [GBY_326] (rows=2276 width=215) Output:["_col0","_col1","_col2","_col3","_col4"],keys:_col0, _col3, _col4, _col1, _col2 - Select Operator [SEL_328] (rows=1134 width=215) + Select Operator [SEL_325] (rows=1134 width=215) Output:["_col0","_col1","_col2","_col3","_col4"] - Filter Operator [FIL_327] (rows=1134 width=248) + Filter Operator [FIL_324] (rows=1134 width=248) predicate:((_col0 <= 10) or (rank_window_1 <= 10)) - PTF Operator [PTF_326] (rows=1701 width=248) + PTF Operator [PTF_323] (rows=1701 width=248) Function definitions:[{},{"name:":"windowingtablefunction","order by:":"(CAST( _col4 AS decimal(15,4)) / CAST( _col5 AS decimal(15,4))) ASC NULLS LAST","partition by:":"0"}] - Select Operator [SEL_325] (rows=1701 width=248) + Select Operator [SEL_322] (rows=1701 width=248) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] <-Reducer 17 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_324] + SHUFFLE [RS_321] PartitionCols:0 - Select Operator [SEL_323] (rows=1701 width=244) + Select Operator [SEL_320] (rows=1701 width=244) Output:["rank_window_0","_col0","_col1","_col2","_col3","_col4"] - PTF Operator [PTF_322] (rows=1701 width=244) + PTF Operator [PTF_319] (rows=1701 width=244) Function definitions:[{},{"name:":"windowingtablefunction","order by:":"(CAST( _col1 AS decimal(15,4)) / CAST( _col2 AS decimal(15,4))) ASC NULLS LAST","partition by:":"0"}] - Select Operator [SEL_321] (rows=1701 width=244) + Select Operator [SEL_318] (rows=1701 width=244) Output:["_col0","_col1","_col2","_col3","_col4"] <-Reducer 16 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_320] + SHUFFLE [RS_317] PartitionCols:0 - Group By Operator [GBY_319] (rows=1701 width=244) + Group By Operator [GBY_316] (rows=1701 width=244) Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)","sum(VALUE._col3)"],keys:KEY._col0 <-Reducer 15 [SIMPLE_EDGE] - SHUFFLE [RS_50] + SHUFFLE [RS_48] PartitionCols:_col0 - Group By Operator [GBY_49] (rows=1701 width=244) - Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["sum(_col1)","sum(_col2)","sum(_col3)","sum(_col4)"],keys:_col0 - Select Operator [SEL_47] (rows=865646 width=188) - Output:["_col0","_col1","_col2","_col3","_col4"] - Merge Join Operator [MERGEJOIN_235] (rows=865646 width=188) - Conds:RS_44._col1, _col2=RS_318._col0, _col1(Inner),Output:["_col1","_col3","_col4","_col11","_col12"] - <-Map 28 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_318] - PartitionCols:_col0, _col1 - Select Operator [SEL_317] (rows=9599627 width=121) - Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_316] (rows=9599627 width=121) - predicate:((cr_return_amount > 10000) and cr_item_sk is not null and cr_order_number is not null) - TableScan [TS_38] (rows=28798881 width=121) - default@catalog_returns,cr,Tbl:COMPLETE,Col:COMPLETE,Output:["cr_item_sk","cr_order_number","cr_return_quantity","cr_return_amount"] - <-Reducer 14 [SIMPLE_EDGE] - SHUFFLE [RS_44] - PartitionCols:_col1, _col2 - Merge Join Operator [MERGEJOIN_234] (rows=865646 width=102) - Conds:RS_315._col0=RS_270._col0(Inner),Output:["_col1","_col2","_col3","_col4"] - <-Map 12 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_270] - PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_267] - <-Map 27 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_315] - PartitionCols:_col0 - Select Operator [SEL_314] (rows=31838858 width=239) - Output:["_col0","_col1","_col2","_col3","_col4"] - Filter Operator [FIL_313] (rows=31838858 width=239) - predicate:((cs_net_paid > 0) and (cs_net_profit > 1) and (cs_quantity > 0) and (cs_sold_date_sk BETWEEN DynamicValue(RS_42_date_dim_d_date_sk_min) AND DynamicValue(RS_42_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_42_date_dim_d_date_sk_bloom_filter))) and cs_item_sk is not null and cs_order_number is not null and cs_sold_date_sk is not null) - TableScan [TS_32] (rows=287989836 width=239) - default@catalog_sales,cs,Tbl:COMPLETE,Col:COMPLETE,Output:["cs_sold_date_sk","cs_item_sk","cs_order_number","cs_quantity","cs_net_paid","cs_net_profit"] - <-Reducer 19 [BROADCAST_EDGE] vectorized - BROADCAST [RS_312] - Group By Operator [GBY_311] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 12 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_278] - Group By Operator [GBY_275] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_271] (rows=50 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_267] + Group By Operator [GBY_47] (rows=1701 width=244) + Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["sum(_col8)","sum(_col3)","sum(_col9)","sum(_col4)"],keys:_col1 + Merge Join Operator [MERGEJOIN_232] (rows=865646 width=236) + Conds:RS_43._col1, _col2=RS_315._col0, _col1(Inner),Output:["_col1","_col3","_col4","_col8","_col9"] + <-Map 28 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_315] + PartitionCols:_col0, _col1 + Select Operator [SEL_314] (rows=9599627 width=124) + Output:["_col0","_col1","_col2","_col3"] + Filter Operator [FIL_313] (rows=9599627 width=121) + predicate:((cr_return_amount > 10000) and cr_item_sk is not null and cr_order_number is not null) + TableScan [TS_37] (rows=28798881 width=121) + default@catalog_returns,cr,Tbl:COMPLETE,Col:COMPLETE,Output:["cr_item_sk","cr_order_number","cr_return_quantity","cr_return_amount"] + <-Reducer 14 [SIMPLE_EDGE] + SHUFFLE [RS_43] + PartitionCols:_col1, _col2 + Merge Join Operator [MERGEJOIN_231] (rows=865646 width=124) + Conds:RS_312._col0=RS_267._col0(Inner),Output:["_col1","_col2","_col3","_col4"] + <-Map 12 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_267] + PartitionCols:_col0 + Please refer to the previous Select Operator [SEL_264] + <-Map 27 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_312] + PartitionCols:_col0 + Select Operator [SEL_311] (rows=31838858 width=127) + Output:["_col0","_col1","_col2","_col3","_col4"] + Filter Operator [FIL_310] (rows=31838858 width=239) + predicate:((cs_net_paid > 0) and (cs_net_profit > 1) and (cs_quantity > 0) and (cs_sold_date_sk BETWEEN DynamicValue(RS_41_date_dim_d_date_sk_min) AND DynamicValue(RS_41_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_41_date_dim_d_date_sk_bloom_filter))) and cs_item_sk is not null and cs_order_number is not null and cs_sold_date_sk is not null) + TableScan [TS_31] (rows=287989836 width=239) + default@catalog_sales,cs,Tbl:COMPLETE,Col:COMPLETE,Output:["cs_sold_date_sk","cs_item_sk","cs_order_number","cs_quantity","cs_net_paid","cs_net_profit"] + <-Reducer 19 [BROADCAST_EDGE] vectorized + BROADCAST [RS_309] + Group By Operator [GBY_308] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 12 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_275] + Group By Operator [GBY_272] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_268] (rows=50 width=4) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_264] <-Reducer 6 [CONTAINS] vectorized - Reduce Output Operator [RS_299] + Reduce Output Operator [RS_296] PartitionCols:_col0, _col1, _col2, _col3, _col4 - Group By Operator [GBY_298] (rows=2276 width=215) + Group By Operator [GBY_295] (rows=2276 width=215) Output:["_col0","_col1","_col2","_col3","_col4"],keys:_col0, _col3, _col4, _col1, _col2 - Select Operator [SEL_297] (rows=1142 width=211) + Select Operator [SEL_294] (rows=1142 width=211) Output:["_col0","_col1","_col2","_col3","_col4"] - Filter Operator [FIL_296] (rows=1142 width=248) + Filter Operator [FIL_293] (rows=1142 width=248) predicate:((_col0 <= 10) or (rank_window_1 <= 10)) - PTF Operator [PTF_295] (rows=1714 width=248) + PTF Operator [PTF_292] (rows=1714 width=248) Function definitions:[{},{"name:":"windowingtablefunction","order by:":"(CAST( _col4 AS decimal(15,4)) / CAST( _col5 AS decimal(15,4))) ASC NULLS LAST","partition by:":"0"}] - Select Operator [SEL_294] (rows=1714 width=248) + Select Operator [SEL_291] (rows=1714 width=248) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] <-Reducer 5 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_293] + SHUFFLE [RS_290] PartitionCols:0 - Select Operator [SEL_292] (rows=1714 width=244) + Select Operator [SEL_289] (rows=1714 width=244) Output:["rank_window_0","_col0","_col1","_col2","_col3","_col4"] - PTF Operator [PTF_291] (rows=1714 width=244) + PTF Operator [PTF_288] (rows=1714 width=244) Function definitions:[{},{"name:":"windowingtablefunction","order by:":"(CAST( _col1 AS decimal(15,4)) / CAST( _col2 AS decimal(15,4))) ASC NULLS LAST","partition by:":"0"}] - Select Operator [SEL_290] (rows=1714 width=244) + Select Operator [SEL_287] (rows=1714 width=244) Output:["_col0","_col1","_col2","_col3","_col4"] <-Reducer 4 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_289] + SHUFFLE [RS_286] PartitionCols:0 - Group By Operator [GBY_288] (rows=1714 width=244) + Group By Operator [GBY_285] (rows=1714 width=244) Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)","sum(VALUE._col3)"],keys:KEY._col0 <-Reducer 3 [SIMPLE_EDGE] - SHUFFLE [RS_18] + SHUFFLE [RS_17] PartitionCols:_col0 - Group By Operator [GBY_17] (rows=1714 width=244) - Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["sum(_col1)","sum(_col2)","sum(_col3)","sum(_col4)"],keys:_col0 - Select Operator [SEL_15] (rows=438010 width=177) - Output:["_col0","_col1","_col2","_col3","_col4"] - Merge Join Operator [MERGEJOIN_233] (rows=438010 width=177) - Conds:RS_12._col1, _col2=RS_287._col0, _col1(Inner),Output:["_col1","_col3","_col4","_col11","_col12"] - <-Map 26 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_287] - PartitionCols:_col0, _col1 - Select Operator [SEL_286] (rows=4799489 width=118) - Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_285] (rows=4799489 width=118) - predicate:((wr_return_amt > 10000) and wr_item_sk is not null and wr_order_number is not null) - TableScan [TS_6] (rows=14398467 width=118) - default@web_returns,wr,Tbl:COMPLETE,Col:COMPLETE,Output:["wr_item_sk","wr_order_number","wr_return_quantity","wr_return_amt"] - <-Reducer 2 [SIMPLE_EDGE] - SHUFFLE [RS_12] - PartitionCols:_col1, _col2 - Merge Join Operator [MERGEJOIN_232] (rows=438010 width=122) - Conds:RS_284._col0=RS_268._col0(Inner),Output:["_col1","_col2","_col3","_col4"] - <-Map 12 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_268] - PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_267] - <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_284] - PartitionCols:_col0 - Select Operator [SEL_283] (rows=15996318 width=239) - Output:["_col0","_col1","_col2","_col3","_col4"] - Filter Operator [FIL_282] (rows=15996318 width=239) - predicate:((ws_net_paid > 0) and (ws_net_profit > 1) and (ws_quantity > 0) and (ws_sold_date_sk BETWEEN DynamicValue(RS_10_date_dim_d_date_sk_min) AND DynamicValue(RS_10_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_10_date_dim_d_date_sk_bloom_filter))) and ws_item_sk is not null and ws_order_number is not null and ws_sold_date_sk is not null) - TableScan [TS_0] (rows=144002668 width=239) - default@web_sales,ws,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_sold_date_sk","ws_item_sk","ws_order_number","ws_quantity","ws_net_paid","ws_net_profit"] - <-Reducer 13 [BROADCAST_EDGE] vectorized - BROADCAST [RS_281] - Group By Operator [GBY_280] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 12 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_277] - Group By Operator [GBY_274] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_269] (rows=50 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_267] + Group By Operator [GBY_16] (rows=1714 width=244) + Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["sum(_col8)","sum(_col3)","sum(_col9)","sum(_col4)"],keys:_col1 + Merge Join Operator [MERGEJOIN_230] (rows=438010 width=236) + Conds:RS_12._col1, _col2=RS_284._col0, _col1(Inner),Output:["_col1","_col3","_col4","_col8","_col9"] + <-Map 26 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_284] + PartitionCols:_col0, _col1 + Select Operator [SEL_283] (rows=4799489 width=124) + Output:["_col0","_col1","_col2","_col3"] + Filter Operator [FIL_282] (rows=4799489 width=118) + predicate:((wr_return_amt > 10000) and wr_item_sk is not null and wr_order_number is not null) + TableScan [TS_6] (rows=14398467 width=118) + default@web_returns,wr,Tbl:COMPLETE,Col:COMPLETE,Output:["wr_item_sk","wr_order_number","wr_return_quantity","wr_return_amt"] + <-Reducer 2 [SIMPLE_EDGE] + SHUFFLE [RS_12] + PartitionCols:_col1, _col2 + Merge Join Operator [MERGEJOIN_229] (rows=438010 width=124) + Conds:RS_281._col0=RS_265._col0(Inner),Output:["_col1","_col2","_col3","_col4"] + <-Map 12 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_265] + PartitionCols:_col0 + Please refer to the previous Select Operator [SEL_264] + <-Map 1 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_281] + PartitionCols:_col0 + Select Operator [SEL_280] (rows=15996318 width=127) + Output:["_col0","_col1","_col2","_col3","_col4"] + Filter Operator [FIL_279] (rows=15996318 width=239) + predicate:((ws_net_paid > 0) and (ws_net_profit > 1) and (ws_quantity > 0) and (ws_sold_date_sk BETWEEN DynamicValue(RS_10_date_dim_d_date_sk_min) AND DynamicValue(RS_10_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_10_date_dim_d_date_sk_bloom_filter))) and ws_item_sk is not null and ws_order_number is not null and ws_sold_date_sk is not null) + TableScan [TS_0] (rows=144002668 width=239) + default@web_sales,ws,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_sold_date_sk","ws_item_sk","ws_order_number","ws_quantity","ws_net_paid","ws_net_profit"] + <-Reducer 13 [BROADCAST_EDGE] vectorized + BROADCAST [RS_278] + Group By Operator [GBY_277] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 12 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_274] + Group By Operator [GBY_271] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_266] (rows=50 width=4) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_264] diff --git ql/src/test/results/clientpositive/perf/tez/query5.q.out ql/src/test/results/clientpositive/perf/tez/query5.q.out index 31afb0ef17c..2ce689b1bb2 100644 --- ql/src/test/results/clientpositive/perf/tez/query5.q.out +++ ql/src/test/results/clientpositive/perf/tez/query5.q.out @@ -330,9 +330,9 @@ Stage-0 SHUFFLE [RS_47] PartitionCols:_col0 Group By Operator [GBY_46] (rows=46000 width=548) - Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["sum(_col2)","sum(_col4)","sum(_col3)","sum(_col5)"],keys:_col9 + Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["sum(_col2)","sum(_col4)","sum(_col3)","sum(_col5)"],keys:_col8 Merge Join Operator [MERGEJOIN_222] (rows=34813117 width=535) - Conds:RS_42._col0=RS_310._col0(Inner),Output:["_col2","_col3","_col4","_col5","_col9"] + Conds:RS_42._col0=RS_310._col0(Inner),Output:["_col2","_col3","_col4","_col5","_col8"] <-Map 24 [SIMPLE_EDGE] vectorized SHUFFLE [RS_310] PartitionCols:_col0 @@ -350,7 +350,7 @@ Stage-0 <-Map 10 [SIMPLE_EDGE] vectorized SHUFFLE [RS_276] PartitionCols:_col0 - Select Operator [SEL_273] (rows=8116 width=98) + Select Operator [SEL_273] (rows=8116 width=4) Output:["_col0"] Filter Operator [FIL_272] (rows=8116 width=98) predicate:(CAST( d_date AS TIMESTAMP) BETWEEN TIMESTAMP'1998-08-04 00:00:00' AND TIMESTAMP'1998-08-18 00:00:00' and d_date_sk is not null) @@ -401,9 +401,9 @@ Stage-0 SHUFFLE [RS_80] PartitionCols:_col0 Group By Operator [GBY_79] (rows=84 width=548) - Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["sum(_col2)","sum(_col4)","sum(_col3)","sum(_col5)"],keys:_col9 + Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["sum(_col2)","sum(_col4)","sum(_col3)","sum(_col5)"],keys:_col8 Merge Join Operator [MERGEJOIN_224] (rows=30966059 width=543) - Conds:RS_75._col0=RS_318._col0(Inner),Output:["_col2","_col3","_col4","_col5","_col9"] + Conds:RS_75._col0=RS_318._col0(Inner),Output:["_col2","_col3","_col4","_col5","_col8"] <-Map 30 [SIMPLE_EDGE] vectorized SHUFFLE [RS_318] PartitionCols:_col0 @@ -483,9 +483,9 @@ Stage-0 SHUFFLE [RS_22] PartitionCols:_col0 Group By Operator [GBY_21] (rows=1704 width=548) - Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["sum(_col2)","sum(_col4)","sum(_col3)","sum(_col5)"],keys:_col9 + Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["sum(_col2)","sum(_col4)","sum(_col3)","sum(_col5)"],keys:_col8 Merge Join Operator [MERGEJOIN_220] (rows=64325014 width=376) - Conds:RS_17._col0=RS_293._col0(Inner),Output:["_col2","_col3","_col4","_col5","_col9"] + Conds:RS_17._col0=RS_293._col0(Inner),Output:["_col2","_col3","_col4","_col5","_col8"] <-Map 20 [SIMPLE_EDGE] vectorized SHUFFLE [RS_293] PartitionCols:_col0 diff --git ql/src/test/results/clientpositive/perf/tez/query50.q.out ql/src/test/results/clientpositive/perf/tez/query50.q.out index ae6781ba58e..29b80b88023 100644 --- ql/src/test/results/clientpositive/perf/tez/query50.q.out +++ ql/src/test/results/clientpositive/perf/tez/query50.q.out @@ -162,7 +162,7 @@ Stage-0 Select Operator [SEL_27] (rows=11945216 width=821) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14"] Merge Join Operator [MERGEJOIN_120] (rows=11945216 width=821) - Conds:RS_24._col10=RS_141._col0(Inner),Output:["_col0","_col7","_col14","_col15","_col16","_col17","_col18","_col19","_col20","_col21","_col22","_col23"] + Conds:RS_24._col8=RS_141._col0(Inner),Output:["_col0","_col5","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col19","_col20","_col21"] <-Map 14 [SIMPLE_EDGE] vectorized SHUFFLE [RS_141] PartitionCols:_col0 @@ -174,9 +174,9 @@ Stage-0 default@store,store,Tbl:COMPLETE,Col:COMPLETE,Output:["s_store_sk","s_store_name","s_company_id","s_street_number","s_street_name","s_street_type","s_suite_number","s_city","s_county","s_state","s_zip"] <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_24] - PartitionCols:_col10 + PartitionCols:_col8 Merge Join Operator [MERGEJOIN_119] (rows=11945216 width=3) - Conds:RS_21._col7=RS_138._col0(Inner),Output:["_col0","_col7","_col10"] + Conds:RS_21._col5=RS_138._col0(Inner),Output:["_col0","_col5","_col8"] <-Map 13 [SIMPLE_EDGE] vectorized SHUFFLE [RS_138] PartitionCols:_col0 @@ -188,9 +188,9 @@ Stage-0 default@date_dim,d1,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk"] <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_21] - PartitionCols:_col7 + PartitionCols:_col5 Merge Join Operator [MERGEJOIN_118] (rows=11945216 width=3) - Conds:RS_18._col1, _col2, _col3=RS_135._col1, _col2, _col4(Inner),Output:["_col0","_col7","_col10"] + Conds:RS_18._col1, _col2, _col3=RS_135._col1, _col2, _col4(Inner),Output:["_col0","_col5","_col8"] <-Reducer 2 [SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_18] PartitionCols:_col1, _col2, _col3 @@ -208,7 +208,7 @@ Stage-0 <-Map 11 [SIMPLE_EDGE] vectorized SHUFFLE [RS_126] PartitionCols:_col0 - Select Operator [SEL_125] (rows=50 width=12) + Select Operator [SEL_125] (rows=50 width=4) Output:["_col0"] Filter Operator [FIL_124] (rows=50 width=12) predicate:((d_moy = 9) and (d_year = 2000) and d_date_sk is not null) diff --git ql/src/test/results/clientpositive/perf/tez/query51.q.out ql/src/test/results/clientpositive/perf/tez/query51.q.out index 23c23df1b76..a872cdedf04 100644 --- ql/src/test/results/clientpositive/perf/tez/query51.q.out +++ ql/src/test/results/clientpositive/perf/tez/query51.q.out @@ -153,7 +153,7 @@ Stage-0 <-Map 7 [SIMPLE_EDGE] vectorized SHUFFLE [RS_92] PartitionCols:_col0 - Select Operator [SEL_89] (rows=317 width=102) + Select Operator [SEL_89] (rows=317 width=98) Output:["_col0","_col1"] Filter Operator [FIL_88] (rows=317 width=102) predicate:(d_date_sk is not null and d_month_seq BETWEEN 1212 AND 1223) diff --git ql/src/test/results/clientpositive/perf/tez/query52.q.out ql/src/test/results/clientpositive/perf/tez/query52.q.out index bc932b2deca..30b39aa265c 100644 --- ql/src/test/results/clientpositive/perf/tez/query52.q.out +++ ql/src/test/results/clientpositive/perf/tez/query52.q.out @@ -79,13 +79,13 @@ Stage-0 SHUFFLE [RS_17] PartitionCols:_col0, _col1 Group By Operator [GBY_16] (rows=7333 width=216) - Output:["_col0","_col1","_col2"],aggregations:["sum(_col2)"],keys:_col7, _col8 + Output:["_col0","_col1","_col2"],aggregations:["sum(_col2)"],keys:_col5, _col6 Merge Join Operator [MERGEJOIN_54] (rows=2301098 width=104) - Conds:RS_12._col1=RS_65._col0(Inner),Output:["_col2","_col7","_col8"] + Conds:RS_12._col1=RS_65._col0(Inner),Output:["_col2","_col5","_col6"] <-Map 8 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_65] PartitionCols:_col0 - Select Operator [SEL_64] (rows=7333 width=111) + Select Operator [SEL_64] (rows=7333 width=107) Output:["_col0","_col1","_col2"] Filter Operator [FIL_63] (rows=7333 width=111) predicate:((i_manager_id = 1) and i_item_sk is not null) @@ -99,7 +99,7 @@ Stage-0 <-Map 6 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_57] PartitionCols:_col0 - Select Operator [SEL_56] (rows=50 width=12) + Select Operator [SEL_56] (rows=50 width=4) Output:["_col0"] Filter Operator [FIL_55] (rows=50 width=12) predicate:((d_moy = 12) and (d_year = 1998) and d_date_sk is not null) diff --git ql/src/test/results/clientpositive/perf/tez/query53.q.out ql/src/test/results/clientpositive/perf/tez/query53.q.out index d99529f1a55..8e4ace3a065 100644 --- ql/src/test/results/clientpositive/perf/tez/query53.q.out +++ ql/src/test/results/clientpositive/perf/tez/query53.q.out @@ -102,9 +102,9 @@ Stage-0 SHUFFLE [RS_23] PartitionCols:_col0 Group By Operator [GBY_22] (rows=60 width=120) - Output:["_col0","_col1","_col2"],aggregations:["sum(_col3)"],keys:_col8, _col11 + Output:["_col0","_col1","_col2"],aggregations:["sum(_col3)"],keys:_col5, _col7 Merge Join Operator [MERGEJOIN_84] (rows=129200 width=8) - Conds:RS_18._col2=RS_106._col0(Inner),Output:["_col3","_col8","_col11"] + Conds:RS_18._col2=RS_106._col0(Inner),Output:["_col3","_col5","_col7"] <-Map 11 [SIMPLE_EDGE] vectorized SHUFFLE [RS_106] PartitionCols:_col0 @@ -118,12 +118,12 @@ Stage-0 SHUFFLE [RS_18] PartitionCols:_col2 Merge Join Operator [MERGEJOIN_83] (rows=129200 width=8) - Conds:RS_15._col0=RS_95._col0(Inner),Output:["_col2","_col3","_col8","_col11"] + Conds:RS_15._col0=RS_95._col0(Inner),Output:["_col2","_col3","_col5","_col7"] <-Map 9 [SIMPLE_EDGE] vectorized SHUFFLE [RS_95] PartitionCols:_col0 - Select Operator [SEL_94] (rows=317 width=12) - Output:["_col0","_col2"] + Select Operator [SEL_94] (rows=317 width=8) + Output:["_col0","_col1"] Filter Operator [FIL_93] (rows=317 width=12) predicate:((d_month_seq) IN (1212, 1213, 1214, 1215, 1216, 1217, 1218, 1219, 1220, 1221, 1222, 1223) and d_date_sk is not null) TableScan [TS_6] (rows=73049 width=12) @@ -132,12 +132,12 @@ Stage-0 SHUFFLE [RS_15] PartitionCols:_col0 Merge Join Operator [MERGEJOIN_82] (rows=744232 width=4) - Conds:RS_103._col1=RS_87._col0(Inner),Output:["_col0","_col2","_col3","_col8"] + Conds:RS_103._col1=RS_87._col0(Inner),Output:["_col0","_col2","_col3","_col5"] <-Map 7 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_87] PartitionCols:_col0 - Select Operator [SEL_86] (rows=68 width=290) - Output:["_col0","_col4"] + Select Operator [SEL_86] (rows=68 width=8) + Output:["_col0","_col1"] Filter Operator [FIL_85] (rows=68 width=290) predicate:((((i_category) IN ('Books', 'Children', 'Electronics') and (i_class) IN ('personal', 'portable', 'reference', 'self-help') and (i_brand) IN ('scholaramalgamalg #14', 'scholaramalgamalg #7', 'exportiunivamalg #9', 'scholaramalgamalg #9')) or ((i_category) IN ('Women', 'Music', 'Men') and (i_class) IN ('accessories', 'classical', 'fragrances', 'pants') and (i_brand) IN ('amalgimporto #1', 'edu packscholar #1', 'exportiimporto #1', 'importoamalg #1'))) and (i_brand) IN ('scholaramalgamalg #14', 'scholaramalgamalg #7', 'exportiunivamalg #9', 'scholaramalgamalg #9', 'amalgimporto #1', 'edu packscholar #1', 'exportiimporto #1', 'importoamalg #1') and (i_category) IN ('Books', 'Children', 'Electronics', 'Women', 'Music', 'Men') and (i_class) IN ('personal', 'portable', 'reference', 'self-help', 'accessories', 'classical', 'fragrances', 'pants') and i_item_sk is not null) TableScan [TS_3] (rows=462000 width=289) diff --git ql/src/test/results/clientpositive/perf/tez/query54.q.out ql/src/test/results/clientpositive/perf/tez/query54.q.out index a32f264d8b7..ddc1ed851c5 100644 --- ql/src/test/results/clientpositive/perf/tez/query54.q.out +++ ql/src/test/results/clientpositive/perf/tez/query54.q.out @@ -304,9 +304,9 @@ Stage-0 SHUFFLE [RS_63] PartitionCols:_col0, _col1 Group By Operator [GBY_62] (rows=55046 width=8) - Output:["_col0","_col1"],keys:_col10, _col9 + Output:["_col0","_col1"],keys:_col6, _col5 Merge Join Operator [MERGEJOIN_267] (rows=110092 width=8) - Conds:RS_58._col1=RS_304._col0(Inner),Output:["_col9","_col10"] + Conds:RS_58._col1=RS_304._col0(Inner),Output:["_col5","_col6"] <-Map 27 [SIMPLE_EDGE] vectorized SHUFFLE [RS_304] PartitionCols:_col0 @@ -324,7 +324,7 @@ Stage-0 <-Map 25 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_298] PartitionCols:_col0 - Select Operator [SEL_297] (rows=453 width=190) + Select Operator [SEL_297] (rows=453 width=4) Output:["_col0"] Filter Operator [FIL_296] (rows=453 width=186) predicate:((i_category = 'Jewelry') and (i_class = 'consignment') and i_item_sk is not null) @@ -338,7 +338,7 @@ Stage-0 <-Map 23 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_292] PartitionCols:_col0 - Select Operator [SEL_291] (rows=50 width=12) + Select Operator [SEL_291] (rows=50 width=4) Output:["_col0"] Filter Operator [FIL_290] (rows=50 width=12) predicate:((d_moy = 3) and (d_year = 1999) and d_date_sk is not null) diff --git ql/src/test/results/clientpositive/perf/tez/query55.q.out ql/src/test/results/clientpositive/perf/tez/query55.q.out index ec30b92cc62..089094676cf 100644 --- ql/src/test/results/clientpositive/perf/tez/query55.q.out +++ ql/src/test/results/clientpositive/perf/tez/query55.q.out @@ -63,13 +63,13 @@ Stage-0 SHUFFLE [RS_17] PartitionCols:_col0, _col1 Group By Operator [GBY_16] (rows=7333 width=216) - Output:["_col0","_col1","_col2"],aggregations:["sum(_col2)"],keys:_col7, _col8 + Output:["_col0","_col1","_col2"],aggregations:["sum(_col2)"],keys:_col5, _col6 Merge Join Operator [MERGEJOIN_54] (rows=2301098 width=104) - Conds:RS_12._col1=RS_65._col0(Inner),Output:["_col2","_col7","_col8"] + Conds:RS_12._col1=RS_65._col0(Inner),Output:["_col2","_col5","_col6"] <-Map 8 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_65] PartitionCols:_col0 - Select Operator [SEL_64] (rows=7333 width=111) + Select Operator [SEL_64] (rows=7333 width=107) Output:["_col0","_col1","_col2"] Filter Operator [FIL_63] (rows=7333 width=111) predicate:((i_manager_id = 36) and i_item_sk is not null) @@ -83,7 +83,7 @@ Stage-0 <-Map 6 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_57] PartitionCols:_col0 - Select Operator [SEL_56] (rows=50 width=12) + Select Operator [SEL_56] (rows=50 width=4) Output:["_col0"] Filter Operator [FIL_55] (rows=50 width=12) predicate:((d_moy = 12) and (d_year = 2001) and d_date_sk is not null) diff --git ql/src/test/results/clientpositive/perf/tez/query56.q.out ql/src/test/results/clientpositive/perf/tez/query56.q.out index a6d3090c08c..318fb9d755a 100644 --- ql/src/test/results/clientpositive/perf/tez/query56.q.out +++ ql/src/test/results/clientpositive/perf/tez/query56.q.out @@ -204,9 +204,9 @@ Stage-0 SHUFFLE [RS_71] PartitionCols:_col0 Group By Operator [GBY_70] (rows=430 width=212) - Output:["_col0","_col1"],aggregations:["sum(_col8)"],keys:_col1 + Output:["_col0","_col1"],aggregations:["sum(_col7)"],keys:_col1 Merge Join Operator [MERGEJOIN_303] (rows=373066 width=100) - Conds:RS_66._col0=RS_67._col4(Inner),Output:["_col1","_col8"] + Conds:RS_66._col0=RS_67._col3(Inner),Output:["_col1","_col7"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_66] PartitionCols:_col0 @@ -239,15 +239,15 @@ Stage-0 default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_id","i_color"] <-Reducer 23 [SIMPLE_EDGE] SHUFFLE [RS_67] - PartitionCols:_col4 + PartitionCols:_col3 Select Operator [SEL_62] (rows=1550375 width=13) - Output:["_col4","_col5"] + Output:["_col3","_col4"] Merge Join Operator [MERGEJOIN_298] (rows=1550375 width=13) Conds:RS_59._col1=RS_346._col0(Inner),Output:["_col2","_col3"] <-Map 28 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_346] PartitionCols:_col0 - Select Operator [SEL_343] (rows=8000000 width=116) + Select Operator [SEL_343] (rows=8000000 width=4) Output:["_col0"] Filter Operator [FIL_342] (rows=8000000 width=112) predicate:((ca_gmt_offset = -8) and ca_address_sk is not null) @@ -261,7 +261,7 @@ Stage-0 <-Map 20 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_330] PartitionCols:_col0 - Select Operator [SEL_327] (rows=50 width=12) + Select Operator [SEL_327] (rows=50 width=4) Output:["_col0"] Filter Operator [FIL_326] (rows=50 width=12) predicate:((d_moy = 1) and (d_year = 2000) and d_date_sk is not null) @@ -320,18 +320,18 @@ Stage-0 SHUFFLE [RS_109] PartitionCols:_col0 Group By Operator [GBY_108] (rows=430 width=212) - Output:["_col0","_col1"],aggregations:["sum(_col8)"],keys:_col1 + Output:["_col0","_col1"],aggregations:["sum(_col7)"],keys:_col1 Merge Join Operator [MERGEJOIN_304] (rows=189670 width=190) - Conds:RS_104._col0=RS_105._col3(Inner),Output:["_col1","_col8"] + Conds:RS_104._col0=RS_105._col2(Inner),Output:["_col1","_col7"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_104] PartitionCols:_col0 Please refer to the previous Merge Join Operator [MERGEJOIN_293] <-Reducer 26 [SIMPLE_EDGE] SHUFFLE [RS_105] - PartitionCols:_col3 + PartitionCols:_col2 Select Operator [SEL_100] (rows=788222 width=110) - Output:["_col3","_col5"] + Output:["_col2","_col4"] Merge Join Operator [MERGEJOIN_301] (rows=788222 width=110) Conds:RS_97._col2=RS_348._col0(Inner),Output:["_col1","_col3"] <-Map 28 [SIMPLE_EDGE] vectorized @@ -400,18 +400,18 @@ Stage-0 SHUFFLE [RS_34] PartitionCols:_col0 Group By Operator [GBY_33] (rows=430 width=212) - Output:["_col0","_col1"],aggregations:["sum(_col8)"],keys:_col1 + Output:["_col0","_col1"],aggregations:["sum(_col7)"],keys:_col1 Merge Join Operator [MERGEJOIN_302] (rows=692265 width=100) - Conds:RS_29._col0=RS_30._col3(Inner),Output:["_col1","_col8"] + Conds:RS_29._col0=RS_30._col2(Inner),Output:["_col1","_col7"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_29] PartitionCols:_col0 Please refer to the previous Merge Join Operator [MERGEJOIN_293] <-Reducer 19 [SIMPLE_EDGE] SHUFFLE [RS_30] - PartitionCols:_col3 + PartitionCols:_col2 Select Operator [SEL_25] (rows=2876890 width=4) - Output:["_col3","_col5"] + Output:["_col2","_col4"] Merge Join Operator [MERGEJOIN_295] (rows=2876890 width=4) Conds:RS_22._col2=RS_344._col0(Inner),Output:["_col1","_col3"] <-Map 28 [SIMPLE_EDGE] vectorized diff --git ql/src/test/results/clientpositive/perf/tez/query57.q.out ql/src/test/results/clientpositive/perf/tez/query57.q.out index 39b95108e2b..4a18880260b 100644 --- ql/src/test/results/clientpositive/perf/tez/query57.q.out +++ ql/src/test/results/clientpositive/perf/tez/query57.q.out @@ -133,10 +133,10 @@ Stage-0 Select Operator [SEL_109] (rows=130121 width=758) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"] Merge Join Operator [MERGEJOIN_278] (rows=130121 width=646) - Conds:RS_106._col5, _col6, _col7, _col12=RS_306._col0, _col1, _col2, (_col4 - 1)(Inner),Output:["_col3","_col5","_col6","_col8","_col9","_col10","_col11","_col16"] + Conds:RS_106._col5, _col6, _col12, _col7=RS_306._col0, _col1, _col4, _col2(Inner),Output:["_col3","_col5","_col6","_col8","_col9","_col10","_col11","_col16"] <-Reducer 6 [SIMPLE_EDGE] vectorized SHUFFLE [RS_306] - PartitionCols:_col0, _col1, _col2, (_col4 - 1) + PartitionCols:_col0, _col1, _col4, _col2 Select Operator [SEL_304] (rows=87441185 width=404) Output:["_col0","_col1","_col2","_col3","_col4"] Filter Operator [FIL_302] (rows=87441185 width=408) @@ -216,12 +216,12 @@ Stage-0 Please refer to the previous Select Operator [SEL_280] <-Reducer 9 [ONE_TO_ONE_EDGE] FORWARD [RS_106] - PartitionCols:_col5, _col6, _col7, _col12 + PartitionCols:_col5, _col6, _col12, _col7 Merge Join Operator [MERGEJOIN_277] (rows=130121 width=636) - Conds:RS_307._col0, _col1, _col2, (_col4 + 1)=RS_318._col0, _col1, _col2, _col7(Inner),Output:["_col3","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12"] + Conds:RS_307._col0, _col1, _col4, _col2=RS_318._col0, _col1, _col7, _col2(Inner),Output:["_col3","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12"] <-Reducer 6 [SIMPLE_EDGE] vectorized SHUFFLE [RS_307] - PartitionCols:_col0, _col1, _col2, (_col4 + 1) + PartitionCols:_col0, _col1, _col4, _col2 Select Operator [SEL_305] (rows=87441185 width=404) Output:["_col0","_col1","_col2","_col3","_col4"] Filter Operator [FIL_303] (rows=87441185 width=408) @@ -231,7 +231,7 @@ Stage-0 Please refer to the previous Select Operator [SEL_299] <-Reducer 11 [SIMPLE_EDGE] vectorized SHUFFLE [RS_318] - PartitionCols:_col0, _col1, _col2, _col7 + PartitionCols:_col0, _col1, _col7, _col2 Select Operator [SEL_317] (rows=130121 width=524) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] Filter Operator [FIL_316] (rows=130121 width=524) diff --git ql/src/test/results/clientpositive/perf/tez/query58.q.out ql/src/test/results/clientpositive/perf/tez/query58.q.out index 9e71fc0a540..bff619a052d 100644 --- ql/src/test/results/clientpositive/perf/tez/query58.q.out +++ ql/src/test/results/clientpositive/perf/tez/query58.q.out @@ -171,223 +171,229 @@ Stage-0 limit:100 Stage-1 Reducer 7 vectorized - File Output Operator [FS_467] - Limit [LIM_466] (rows=1 width=884) + File Output Operator [FS_470] + Limit [LIM_469] (rows=1 width=884) Number of rows:100 - Select Operator [SEL_465] (rows=1 width=884) + Select Operator [SEL_468] (rows=1 width=884) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] <-Reducer 6 [SIMPLE_EDGE] SHUFFLE [RS_163] Select Operator [SEL_162] (rows=1 width=884) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] - Filter Operator [FIL_158] (rows=1 width=436) - predicate:(_col1 BETWEEN (0.9 * _col5) AND (1.1 * _col5) and _col3 BETWEEN (0.9 * _col5) AND (1.1 * _col5) and _col5 BETWEEN (0.9 * _col1) AND (1.1 * _col1) and _col5 BETWEEN (0.9 * _col3) AND (1.1 * _col3)) - Merge Join Operator [MERGEJOIN_419] (rows=1 width=436) - Conds:RS_155._col0=RS_464._col0(Inner),Output:["_col0","_col1","_col3","_col5"] + Filter Operator [FIL_158] (rows=1 width=1108) + predicate:(_col1 BETWEEN _col10 AND _col11 and _col5 BETWEEN _col10 AND _col11 and _col9 BETWEEN _col2 AND _col3 and _col9 BETWEEN _col6 AND _col7) + Merge Join Operator [MERGEJOIN_419] (rows=1 width=1108) + Conds:RS_155._col0=RS_467._col0(Inner),Output:["_col0","_col1","_col2","_col3","_col5","_col6","_col7","_col9","_col10","_col11"] <-Reducer 14 [ONE_TO_ONE_EDGE] vectorized - FORWARD [RS_464] + FORWARD [RS_467] PartitionCols:_col0 - Group By Operator [GBY_463] (rows=69 width=212) - Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 - <-Reducer 13 [SIMPLE_EDGE] - SHUFFLE [RS_147] - PartitionCols:_col0 - Group By Operator [GBY_146] (rows=69 width=212) - Output:["_col0","_col1"],aggregations:["sum(_col2)"],keys:_col4 - Merge Join Operator [MERGEJOIN_417] (rows=31537 width=100) - Conds:RS_142._col0=RS_143._col0(Inner),Output:["_col2","_col4"] - <-Reducer 16 [SIMPLE_EDGE] - SHUFFLE [RS_143] - PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_406] (rows=2 width=4) - Conds:RS_422._col1=RS_438._col0(Inner),Output:["_col0"] - <-Map 15 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_422] - PartitionCols:_col1 - Select Operator [SEL_421] (rows=73049 width=98) - Output:["_col0","_col1"] - Filter Operator [FIL_420] (rows=73049 width=98) - predicate:(d_date is not null and d_date_sk is not null) - TableScan [TS_6] (rows=73049 width=98) - default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_date"] - <-Reducer 24 [ONE_TO_ONE_EDGE] vectorized - FORWARD [RS_438] - PartitionCols:_col0 - Group By Operator [GBY_437] (rows=2 width=94) - Output:["_col0"],keys:KEY._col0 - <-Reducer 23 [SIMPLE_EDGE] - SHUFFLE [RS_32] - PartitionCols:_col0 - Group By Operator [GBY_31] (rows=2 width=94) - Output:["_col0"],keys:_col2 - Merge Join Operator [MERGEJOIN_405] (rows=5 width=94) - Conds:RS_27._col1=RS_435._col1(Inner),Output:["_col2"] - <-Map 25 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_435] - PartitionCols:_col1 - Select Operator [SEL_433] (rows=73049 width=98) - Output:["_col0","_col1"] - Filter Operator [FIL_431] (rows=73049 width=98) - predicate:(d_date is not null and d_week_seq is not null) - TableScan [TS_21] (rows=73049 width=98) - default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date","d_week_seq"] - <-Reducer 22 [SIMPLE_EDGE] - SHUFFLE [RS_27] - PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_404] (rows=1 width=4) - Conds:(Inner),Output:["_col1"] - <-Map 25 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_436] - Select Operator [SEL_434] (rows=1 width=4) - Output:["_col0"] - Filter Operator [FIL_432] (rows=1 width=98) - predicate:((d_date = '1998-02-19') and d_week_seq is not null) - Please refer to the previous TableScan [TS_21] - <-Reducer 21 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_430] - Select Operator [SEL_429] (rows=1 width=8) - Filter Operator [FIL_428] (rows=1 width=8) - predicate:(sq_count_check(_col0) <= 1) - Group By Operator [GBY_427] (rows=1 width=8) - Output:["_col0"],aggregations:["count(VALUE._col0)"] - <-Map 20 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_426] - Group By Operator [GBY_425] (rows=1 width=8) - Output:["_col0"],aggregations:["count()"] - Select Operator [SEL_424] (rows=1 width=94) - Filter Operator [FIL_423] (rows=1 width=94) - predicate:(d_date = '1998-02-19') - TableScan [TS_9] (rows=73049 width=94) - default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date"] - <-Reducer 12 [SIMPLE_EDGE] - SHUFFLE [RS_142] - PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_411] (rows=143966864 width=215) - Conds:RS_462._col1=RS_448._col0(Inner),Output:["_col0","_col2","_col4"] - <-Map 8 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_448] - PartitionCols:_col0 - Select Operator [SEL_445] (rows=462000 width=104) - Output:["_col0","_col1"] - Filter Operator [FIL_444] (rows=462000 width=104) - predicate:(i_item_id is not null and i_item_sk is not null) - TableScan [TS_3] (rows=462000 width=104) - default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_item_id"] - <-Map 27 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_462] - PartitionCols:_col1 - Select Operator [SEL_461] (rows=143966864 width=119) - Output:["_col0","_col1","_col2"] - Filter Operator [FIL_460] (rows=143966864 width=119) - predicate:((ws_sold_date_sk BETWEEN DynamicValue(RS_143_date_dim_d_date_sk_min) AND DynamicValue(RS_143_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_143_date_dim_d_date_sk_bloom_filter))) and ws_item_sk is not null and ws_sold_date_sk is not null) - TableScan [TS_100] (rows=144002668 width=119) - default@web_sales,web_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_sold_date_sk","ws_item_sk","ws_ext_sales_price"] - <-Reducer 19 [BROADCAST_EDGE] vectorized - BROADCAST [RS_459] - Group By Operator [GBY_458] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Reducer 16 [CUSTOM_SIMPLE_EDGE] - SHUFFLE [RS_363] - Group By Operator [GBY_362] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_361] (rows=2 width=4) - Output:["_col0"] - Please refer to the previous Merge Join Operator [MERGEJOIN_406] + Select Operator [SEL_466] (rows=69 width=436) + Output:["_col0","_col1","_col2","_col3"] + Group By Operator [GBY_465] (rows=69 width=212) + Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 + <-Reducer 13 [SIMPLE_EDGE] + SHUFFLE [RS_147] + PartitionCols:_col0 + Group By Operator [GBY_146] (rows=69 width=212) + Output:["_col0","_col1"],aggregations:["sum(_col2)"],keys:_col4 + Merge Join Operator [MERGEJOIN_417] (rows=31537 width=100) + Conds:RS_142._col0=RS_143._col0(Inner),Output:["_col2","_col4"] + <-Reducer 16 [SIMPLE_EDGE] + SHUFFLE [RS_143] + PartitionCols:_col0 + Merge Join Operator [MERGEJOIN_406] (rows=2 width=4) + Conds:RS_422._col1=RS_438._col0(Inner),Output:["_col0"] + <-Map 15 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_422] + PartitionCols:_col1 + Select Operator [SEL_421] (rows=73049 width=98) + Output:["_col0","_col1"] + Filter Operator [FIL_420] (rows=73049 width=98) + predicate:(d_date is not null and d_date_sk is not null) + TableScan [TS_6] (rows=73049 width=98) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_date"] + <-Reducer 24 [ONE_TO_ONE_EDGE] vectorized + FORWARD [RS_438] + PartitionCols:_col0 + Group By Operator [GBY_437] (rows=2 width=94) + Output:["_col0"],keys:KEY._col0 + <-Reducer 23 [SIMPLE_EDGE] + SHUFFLE [RS_32] + PartitionCols:_col0 + Group By Operator [GBY_31] (rows=2 width=94) + Output:["_col0"],keys:_col2 + Merge Join Operator [MERGEJOIN_405] (rows=5 width=94) + Conds:RS_27._col1=RS_435._col1(Inner),Output:["_col2"] + <-Map 25 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_435] + PartitionCols:_col1 + Select Operator [SEL_433] (rows=73049 width=98) + Output:["_col0","_col1"] + Filter Operator [FIL_431] (rows=73049 width=98) + predicate:(d_date is not null and d_week_seq is not null) + TableScan [TS_21] (rows=73049 width=98) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date","d_week_seq"] + <-Reducer 22 [SIMPLE_EDGE] + SHUFFLE [RS_27] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_404] (rows=1 width=4) + Conds:(Inner),Output:["_col1"] + <-Map 25 [CUSTOM_SIMPLE_EDGE] vectorized + SHUFFLE [RS_436] + Select Operator [SEL_434] (rows=1 width=4) + Output:["_col0"] + Filter Operator [FIL_432] (rows=1 width=98) + predicate:((d_date = '1998-02-19') and d_week_seq is not null) + Please refer to the previous TableScan [TS_21] + <-Reducer 21 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_430] + Select Operator [SEL_429] (rows=1 width=8) + Filter Operator [FIL_428] (rows=1 width=8) + predicate:(sq_count_check(_col0) <= 1) + Group By Operator [GBY_427] (rows=1 width=8) + Output:["_col0"],aggregations:["count(VALUE._col0)"] + <-Map 20 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_426] + Group By Operator [GBY_425] (rows=1 width=8) + Output:["_col0"],aggregations:["count()"] + Select Operator [SEL_424] (rows=1 width=94) + Filter Operator [FIL_423] (rows=1 width=94) + predicate:(d_date = '1998-02-19') + TableScan [TS_9] (rows=73049 width=94) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date"] + <-Reducer 12 [SIMPLE_EDGE] + SHUFFLE [RS_142] + PartitionCols:_col0 + Merge Join Operator [MERGEJOIN_411] (rows=143966864 width=215) + Conds:RS_464._col1=RS_448._col0(Inner),Output:["_col0","_col2","_col4"] + <-Map 8 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_448] + PartitionCols:_col0 + Select Operator [SEL_445] (rows=462000 width=104) + Output:["_col0","_col1"] + Filter Operator [FIL_444] (rows=462000 width=104) + predicate:(i_item_id is not null and i_item_sk is not null) + TableScan [TS_3] (rows=462000 width=104) + default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_item_id"] + <-Map 27 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_464] + PartitionCols:_col1 + Select Operator [SEL_463] (rows=143966864 width=119) + Output:["_col0","_col1","_col2"] + Filter Operator [FIL_462] (rows=143966864 width=119) + predicate:((ws_sold_date_sk BETWEEN DynamicValue(RS_143_date_dim_d_date_sk_min) AND DynamicValue(RS_143_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_143_date_dim_d_date_sk_bloom_filter))) and ws_item_sk is not null and ws_sold_date_sk is not null) + TableScan [TS_100] (rows=144002668 width=119) + default@web_sales,web_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_sold_date_sk","ws_item_sk","ws_ext_sales_price"] + <-Reducer 19 [BROADCAST_EDGE] vectorized + BROADCAST [RS_461] + Group By Operator [GBY_460] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Reducer 16 [CUSTOM_SIMPLE_EDGE] + SHUFFLE [RS_363] + Group By Operator [GBY_362] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_361] (rows=2 width=4) + Output:["_col0"] + Please refer to the previous Merge Join Operator [MERGEJOIN_406] <-Reducer 5 [ONE_TO_ONE_EDGE] FORWARD [RS_155] PartitionCols:_col0 - Filter Operator [FIL_153] (rows=1 width=324) - predicate:(_col1 BETWEEN (0.9 * _col3) AND (1.1 * _col3) and _col3 BETWEEN (0.9 * _col1) AND (1.1 * _col1)) - Merge Join Operator [MERGEJOIN_418] (rows=68 width=324) - Conds:RS_450._col0=RS_457._col0(Inner),Output:["_col0","_col1","_col3"] + Filter Operator [FIL_153] (rows=1 width=772) + predicate:(_col1 BETWEEN _col6 AND _col7 and _col5 BETWEEN _col2 AND _col3) + Merge Join Operator [MERGEJOIN_418] (rows=68 width=772) + Conds:RS_451._col0=RS_459._col0(Inner),Output:["_col0","_col1","_col2","_col3","_col5","_col6","_col7"] <-Reducer 11 [ONE_TO_ONE_EDGE] vectorized - FORWARD [RS_457] + FORWARD [RS_459] PartitionCols:_col0 - Group By Operator [GBY_456] (rows=69 width=212) - Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 - <-Reducer 10 [SIMPLE_EDGE] - SHUFFLE [RS_97] - PartitionCols:_col0 - Group By Operator [GBY_96] (rows=69 width=212) - Output:["_col0","_col1"],aggregations:["sum(_col2)"],keys:_col4 - Merge Join Operator [MERGEJOIN_416] (rows=120498 width=100) - Conds:RS_92._col0=RS_93._col0(Inner),Output:["_col2","_col4"] - <-Reducer 16 [SIMPLE_EDGE] - SHUFFLE [RS_93] - PartitionCols:_col0 - Please refer to the previous Merge Join Operator [MERGEJOIN_406] - <-Reducer 9 [SIMPLE_EDGE] - SHUFFLE [RS_92] - PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_407] (rows=550076554 width=210) - Conds:RS_455._col1=RS_447._col0(Inner),Output:["_col0","_col2","_col4"] - <-Map 8 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_447] - PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_445] - <-Map 26 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_455] - PartitionCols:_col1 - Select Operator [SEL_454] (rows=550076554 width=114) - Output:["_col0","_col1","_col2"] - Filter Operator [FIL_453] (rows=550076554 width=114) - predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_93_date_dim_d_date_sk_min) AND DynamicValue(RS_93_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_93_date_dim_d_date_sk_bloom_filter))) and ss_item_sk is not null and ss_sold_date_sk is not null) - TableScan [TS_50] (rows=575995635 width=114) - default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_item_sk","ss_ext_sales_price"] - <-Reducer 18 [BROADCAST_EDGE] vectorized - BROADCAST [RS_452] - Group By Operator [GBY_451] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Reducer 16 [CUSTOM_SIMPLE_EDGE] - SHUFFLE [RS_317] - Group By Operator [GBY_316] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_315] (rows=2 width=4) - Output:["_col0"] - Please refer to the previous Merge Join Operator [MERGEJOIN_406] + Select Operator [SEL_458] (rows=69 width=436) + Output:["_col0","_col1","_col2","_col3"] + Group By Operator [GBY_457] (rows=69 width=212) + Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 + <-Reducer 10 [SIMPLE_EDGE] + SHUFFLE [RS_97] + PartitionCols:_col0 + Group By Operator [GBY_96] (rows=69 width=212) + Output:["_col0","_col1"],aggregations:["sum(_col2)"],keys:_col4 + Merge Join Operator [MERGEJOIN_416] (rows=120498 width=100) + Conds:RS_92._col0=RS_93._col0(Inner),Output:["_col2","_col4"] + <-Reducer 16 [SIMPLE_EDGE] + SHUFFLE [RS_93] + PartitionCols:_col0 + Please refer to the previous Merge Join Operator [MERGEJOIN_406] + <-Reducer 9 [SIMPLE_EDGE] + SHUFFLE [RS_92] + PartitionCols:_col0 + Merge Join Operator [MERGEJOIN_407] (rows=550076554 width=210) + Conds:RS_456._col1=RS_447._col0(Inner),Output:["_col0","_col2","_col4"] + <-Map 8 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_447] + PartitionCols:_col0 + Please refer to the previous Select Operator [SEL_445] + <-Map 26 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_456] + PartitionCols:_col1 + Select Operator [SEL_455] (rows=550076554 width=114) + Output:["_col0","_col1","_col2"] + Filter Operator [FIL_454] (rows=550076554 width=114) + predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_93_date_dim_d_date_sk_min) AND DynamicValue(RS_93_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_93_date_dim_d_date_sk_bloom_filter))) and ss_item_sk is not null and ss_sold_date_sk is not null) + TableScan [TS_50] (rows=575995635 width=114) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_item_sk","ss_ext_sales_price"] + <-Reducer 18 [BROADCAST_EDGE] vectorized + BROADCAST [RS_453] + Group By Operator [GBY_452] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Reducer 16 [CUSTOM_SIMPLE_EDGE] + SHUFFLE [RS_317] + Group By Operator [GBY_316] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_315] (rows=2 width=4) + Output:["_col0"] + Please refer to the previous Merge Join Operator [MERGEJOIN_406] <-Reducer 4 [ONE_TO_ONE_EDGE] vectorized - FORWARD [RS_450] + FORWARD [RS_451] PartitionCols:_col0 - Group By Operator [GBY_449] (rows=68 width=212) - Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 - <-Reducer 3 [SIMPLE_EDGE] - SHUFFLE [RS_47] - PartitionCols:_col0 - Group By Operator [GBY_46] (rows=68 width=212) - Output:["_col0","_col1"],aggregations:["sum(_col2)"],keys:_col4 - Merge Join Operator [MERGEJOIN_415] (rows=62327 width=100) - Conds:RS_42._col0=RS_43._col0(Inner),Output:["_col2","_col4"] - <-Reducer 16 [SIMPLE_EDGE] - SHUFFLE [RS_43] - PartitionCols:_col0 - Please refer to the previous Merge Join Operator [MERGEJOIN_406] - <-Reducer 2 [SIMPLE_EDGE] - SHUFFLE [RS_42] - PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_403] (rows=286549727 width=215) - Conds:RS_443._col1=RS_446._col0(Inner),Output:["_col0","_col2","_col4"] - <-Map 8 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_446] - PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_445] - <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_443] - PartitionCols:_col1 - Select Operator [SEL_442] (rows=286549727 width=119) - Output:["_col0","_col1","_col2"] - Filter Operator [FIL_441] (rows=286549727 width=119) - predicate:((cs_sold_date_sk BETWEEN DynamicValue(RS_43_date_dim_d_date_sk_min) AND DynamicValue(RS_43_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_43_date_dim_d_date_sk_bloom_filter))) and cs_item_sk is not null and cs_sold_date_sk is not null) - TableScan [TS_0] (rows=287989836 width=119) - default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["cs_sold_date_sk","cs_item_sk","cs_ext_sales_price"] - <-Reducer 17 [BROADCAST_EDGE] vectorized - BROADCAST [RS_440] - Group By Operator [GBY_439] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Reducer 16 [CUSTOM_SIMPLE_EDGE] - SHUFFLE [RS_267] - Group By Operator [GBY_266] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_265] (rows=2 width=4) - Output:["_col0"] - Please refer to the previous Merge Join Operator [MERGEJOIN_406] + Select Operator [SEL_450] (rows=68 width=436) + Output:["_col0","_col1","_col2","_col3"] + Group By Operator [GBY_449] (rows=68 width=212) + Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 + <-Reducer 3 [SIMPLE_EDGE] + SHUFFLE [RS_47] + PartitionCols:_col0 + Group By Operator [GBY_46] (rows=68 width=212) + Output:["_col0","_col1"],aggregations:["sum(_col2)"],keys:_col4 + Merge Join Operator [MERGEJOIN_415] (rows=62327 width=100) + Conds:RS_42._col0=RS_43._col0(Inner),Output:["_col2","_col4"] + <-Reducer 16 [SIMPLE_EDGE] + SHUFFLE [RS_43] + PartitionCols:_col0 + Please refer to the previous Merge Join Operator [MERGEJOIN_406] + <-Reducer 2 [SIMPLE_EDGE] + SHUFFLE [RS_42] + PartitionCols:_col0 + Merge Join Operator [MERGEJOIN_403] (rows=286549727 width=215) + Conds:RS_443._col1=RS_446._col0(Inner),Output:["_col0","_col2","_col4"] + <-Map 8 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_446] + PartitionCols:_col0 + Please refer to the previous Select Operator [SEL_445] + <-Map 1 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_443] + PartitionCols:_col1 + Select Operator [SEL_442] (rows=286549727 width=119) + Output:["_col0","_col1","_col2"] + Filter Operator [FIL_441] (rows=286549727 width=119) + predicate:((cs_sold_date_sk BETWEEN DynamicValue(RS_43_date_dim_d_date_sk_min) AND DynamicValue(RS_43_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_43_date_dim_d_date_sk_bloom_filter))) and cs_item_sk is not null and cs_sold_date_sk is not null) + TableScan [TS_0] (rows=287989836 width=119) + default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["cs_sold_date_sk","cs_item_sk","cs_ext_sales_price"] + <-Reducer 17 [BROADCAST_EDGE] vectorized + BROADCAST [RS_440] + Group By Operator [GBY_439] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Reducer 16 [CUSTOM_SIMPLE_EDGE] + SHUFFLE [RS_267] + Group By Operator [GBY_266] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_265] (rows=2 width=4) + Output:["_col0"] + Please refer to the previous Merge Join Operator [MERGEJOIN_406] diff --git ql/src/test/results/clientpositive/perf/tez/query59.q.out ql/src/test/results/clientpositive/perf/tez/query59.q.out index 2ac474ab0ec..d325a95213b 100644 --- ql/src/test/results/clientpositive/perf/tez/query59.q.out +++ ql/src/test/results/clientpositive/perf/tez/query59.q.out @@ -95,78 +95,79 @@ POSTHOOK: Output: hdfs://### HDFS PATH ### Plan optimized by CBO. Vertex dependency in root stage -Reducer 10 <- Map 14 (SIMPLE_EDGE), Reducer 9 (SIMPLE_EDGE) -Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 11 (SIMPLE_EDGE) +Reducer 10 <- Map 13 (SIMPLE_EDGE), Reducer 9 (SIMPLE_EDGE) +Reducer 11 <- Map 15 (SIMPLE_EDGE), Reducer 10 (SIMPLE_EDGE) +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 12 (SIMPLE_EDGE) Reducer 3 <- Reducer 2 (SIMPLE_EDGE) -Reducer 4 <- Map 12 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) -Reducer 5 <- Map 13 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) -Reducer 6 <- Reducer 10 (SIMPLE_EDGE), Reducer 5 (SIMPLE_EDGE) +Reducer 4 <- Map 13 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) +Reducer 5 <- Map 14 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) +Reducer 6 <- Reducer 11 (SIMPLE_EDGE), Reducer 5 (SIMPLE_EDGE) Reducer 7 <- Reducer 6 (SIMPLE_EDGE) -Reducer 8 <- Reducer 2 (SIMPLE_EDGE) -Reducer 9 <- Map 12 (SIMPLE_EDGE), Reducer 8 (SIMPLE_EDGE) +Reducer 8 <- Map 1 (SIMPLE_EDGE), Map 12 (SIMPLE_EDGE) +Reducer 9 <- Reducer 8 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:100 Stage-1 Reducer 7 vectorized - File Output Operator [FS_208] - Limit [LIM_207] (rows=100 width=976) + File Output Operator [FS_211] + Limit [LIM_210] (rows=100 width=976) Number of rows:100 - Select Operator [SEL_206] (rows=1012347 width=976) + Select Operator [SEL_209] (rows=1012347 width=976) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9"] <-Reducer 6 [SIMPLE_EDGE] SHUFFLE [RS_59] Select Operator [SEL_58] (rows=1012347 width=976) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9"] Merge Join Operator [MERGEJOIN_183] (rows=1012347 width=1648) - Conds:RS_55._col12, _col0=RS_56._col1, (_col0 - 52)(Inner),Output:["_col0","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col12","_col13","_col16","_col17","_col18","_col19","_col20","_col21"] - <-Reducer 10 [SIMPLE_EDGE] + Conds:RS_55._col11, _col0=RS_56._col1, (_col0 - 52)(Inner),Output:["_col0","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col11","_col12","_col15","_col16","_col17","_col18","_col19","_col20"] + <-Reducer 11 [SIMPLE_EDGE] SHUFFLE [RS_56] PartitionCols:_col1, (_col0 - 52) Select Operator [SEL_48] (rows=28847 width=776) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] Merge Join Operator [MERGEJOIN_182] (rows=28847 width=776) - Conds:RS_45._col1=RS_205._col0(Inner),Output:["_col0","_col2","_col3","_col4","_col5","_col6","_col7","_col11"] - <-Map 14 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_205] + Conds:RS_45._col1=RS_208._col0(Inner),Output:["_col0","_col2","_col3","_col4","_col5","_col6","_col7","_col10"] + <-Map 15 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_208] PartitionCols:_col0 - Select Operator [SEL_204] (rows=1704 width=104) + Select Operator [SEL_207] (rows=1704 width=104) Output:["_col0","_col1"] - Filter Operator [FIL_203] (rows=1704 width=104) + Filter Operator [FIL_206] (rows=1704 width=104) predicate:(s_store_id is not null and s_store_sk is not null) TableScan [TS_39] (rows=1704 width=104) default@store,store,Tbl:COMPLETE,Col:COMPLETE,Output:["s_store_sk","s_store_id"] - <-Reducer 9 [SIMPLE_EDGE] + <-Reducer 10 [SIMPLE_EDGE] SHUFFLE [RS_45] PartitionCols:_col1 Merge Join Operator [MERGEJOIN_181] (rows=28847 width=676) - Conds:RS_202._col0=RS_197._col1(Inner),Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] - <-Map 12 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_197] - PartitionCols:_col1 - Select Operator [SEL_195] (rows=317 width=8) - Output:["_col1"] - Filter Operator [FIL_193] (rows=317 width=8) + Conds:RS_205._col0=RS_200._col0(Inner),Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] + <-Map 13 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_200] + PartitionCols:_col0 + Select Operator [SEL_198] (rows=317 width=4) + Output:["_col0"] + Filter Operator [FIL_196] (rows=317 width=8) predicate:(d_month_seq BETWEEN 1197 AND 1208 and d_week_seq is not null) TableScan [TS_15] (rows=73049 width=8) default@date_dim,d,Tbl:COMPLETE,Col:COMPLETE,Output:["d_month_seq","d_week_seq"] - <-Reducer 8 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_202] + <-Reducer 9 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_205] PartitionCols:_col0 - Group By Operator [GBY_201] (rows=1196832 width=679) + Group By Operator [GBY_204] (rows=1196832 width=679) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)","sum(VALUE._col3)","sum(VALUE._col4)","sum(VALUE._col5)"],keys:KEY._col0, KEY._col1 - <-Reducer 2 [SIMPLE_EDGE] + <-Reducer 8 [SIMPLE_EDGE] SHUFFLE [RS_33] PartitionCols:_col0, _col1 Group By Operator [GBY_32] (rows=525329897 width=679) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"],aggregations:["sum(_col2)","sum(_col3)","sum(_col5)","sum(_col6)","sum(_col7)","sum(_col8)"],keys:_col0, _col1 - Select Operator [SEL_30] (rows=525329897 width=205) + Select Operator [SEL_30] (rows=525329897 width=138) Output:["_col0","_col1","_col2","_col3","_col5","_col6","_col7","_col8"] - Merge Join Operator [MERGEJOIN_177] (rows=525329897 width=205) - Conds:RS_186._col0=RS_189._col0(Inner),Output:["_col1","_col2","_col4","_col5"] + Merge Join Operator [MERGEJOIN_180] (rows=525329897 width=138) + Conds:RS_187._col0=RS_192._col0(Inner),Output:["_col1","_col2","_col4","_col5","_col6","_col8","_col9","_col10","_col11"] <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_186] + SHUFFLE [RS_187] PartitionCols:_col0 Select Operator [SEL_185] (rows=525329897 width=114) Output:["_col0","_col1","_col2"] @@ -174,26 +175,26 @@ Stage-0 predicate:(ss_sold_date_sk is not null and ss_store_sk is not null) TableScan [TS_0] (rows=575995635 width=114) default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_store_sk","ss_sales_price"] - <-Map 11 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_189] + <-Map 12 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_192] PartitionCols:_col0 - Select Operator [SEL_188] (rows=73049 width=99) - Output:["_col0","_col1","_col2"] - Filter Operator [FIL_187] (rows=73049 width=99) + Select Operator [SEL_190] (rows=73049 width=36) + Output:["_col0","_col1","_col2","_col3","_col5","_col6","_col7","_col8"] + Filter Operator [FIL_188] (rows=73049 width=99) predicate:(d_date_sk is not null and d_week_seq is not null) TableScan [TS_3] (rows=73049 width=99) default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_week_seq","d_day_name"] <-Reducer 5 [SIMPLE_EDGE] SHUFFLE [RS_55] - PartitionCols:_col12, _col0 + PartitionCols:_col11, _col0 Merge Join Operator [MERGEJOIN_179] (rows=28847 width=976) - Conds:RS_52._col1=RS_200._col0(Inner),Output:["_col0","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col12","_col13"] - <-Map 13 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_200] + Conds:RS_52._col1=RS_203._col0(Inner),Output:["_col0","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col11","_col12"] + <-Map 14 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_203] PartitionCols:_col0 - Select Operator [SEL_199] (rows=1704 width=192) + Select Operator [SEL_202] (rows=1704 width=192) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_198] (rows=1704 width=192) + Filter Operator [FIL_201] (rows=1704 width=192) predicate:(s_store_id is not null and s_store_sk is not null) TableScan [TS_18] (rows=1704 width=192) default@store,store,Tbl:COMPLETE,Col:COMPLETE,Output:["s_store_sk","s_store_id","s_store_name"] @@ -201,26 +202,37 @@ Stage-0 SHUFFLE [RS_52] PartitionCols:_col1 Merge Join Operator [MERGEJOIN_178] (rows=28847 width=788) - Conds:RS_191._col0=RS_196._col1(Inner),Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"] - <-Map 12 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_196] - PartitionCols:_col1 - Select Operator [SEL_194] (rows=317 width=8) - Output:["_col1"] - Filter Operator [FIL_192] (rows=317 width=8) + Conds:RS_194._col0=RS_199._col0(Inner),Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"] + <-Map 13 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_199] + PartitionCols:_col0 + Select Operator [SEL_197] (rows=317 width=4) + Output:["_col0"] + Filter Operator [FIL_195] (rows=317 width=8) predicate:(d_month_seq BETWEEN 1185 AND 1196 and d_week_seq is not null) Please refer to the previous TableScan [TS_15] <-Reducer 3 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_191] + SHUFFLE [RS_194] PartitionCols:_col0 - Group By Operator [GBY_190] (rows=1196832 width=791) + Group By Operator [GBY_193] (rows=1196832 width=791) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)","sum(VALUE._col3)","sum(VALUE._col4)","sum(VALUE._col5)","sum(VALUE._col6)"],keys:KEY._col0, KEY._col1 <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_12] PartitionCols:_col0, _col1 Group By Operator [GBY_11] (rows=525329897 width=791) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"],aggregations:["sum(_col2)","sum(_col3)","sum(_col4)","sum(_col5)","sum(_col6)","sum(_col7)","sum(_col8)"],keys:_col0, _col1 - Select Operator [SEL_9] (rows=525329897 width=205) + Select Operator [SEL_9] (rows=525329897 width=142) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"] - Please refer to the previous Merge Join Operator [MERGEJOIN_177] + Merge Join Operator [MERGEJOIN_177] (rows=525329897 width=142) + Conds:RS_186._col0=RS_191._col0(Inner),Output:["_col1","_col2","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11"] + <-Map 1 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_186] + PartitionCols:_col0 + Please refer to the previous Select Operator [SEL_185] + <-Map 12 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_191] + PartitionCols:_col0 + Select Operator [SEL_189] (rows=73049 width=36) + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"] + Please refer to the previous Filter Operator [FIL_188] diff --git ql/src/test/results/clientpositive/perf/tez/query6.q.out ql/src/test/results/clientpositive/perf/tez/query6.q.out index 7de4229275c..0ca703911fa 100644 --- ql/src/test/results/clientpositive/perf/tez/query6.q.out +++ ql/src/test/results/clientpositive/perf/tez/query6.q.out @@ -107,12 +107,12 @@ Stage-0 Select Operator [SEL_212] (rows=154000 width=227) Output:["_col0"] Filter Operator [FIL_211] (rows=154000 width=227) - predicate:(_col4 > (1.2 * CAST( _col0 AS decimal(16,6)))) + predicate:(_col4 > _col1) Map Join Operator [MAPJOIN_210] (rows=462000 width=227) - Conds:RS_207._col1=SEL_209._col2(Inner),HybridGraceHashJoin:true,Output:["_col0","_col3","_col4"] + Conds:RS_207._col0=SEL_209._col2(Inner),HybridGraceHashJoin:true,Output:["_col1","_col3","_col4"] <-Reducer 15 [BROADCAST_EDGE] vectorized BROADCAST [RS_207] - PartitionCols:_col1 + PartitionCols:_col0 Map Join Operator [MAPJOIN_206] (rows=10 width=202) Conds:(Inner),Output:["_col0","_col1"] <-Reducer 5 [BROADCAST_EDGE] vectorized diff --git ql/src/test/results/clientpositive/perf/tez/query60.q.out ql/src/test/results/clientpositive/perf/tez/query60.q.out index f94101a4c7f..8a499c85c56 100644 --- ql/src/test/results/clientpositive/perf/tez/query60.q.out +++ ql/src/test/results/clientpositive/perf/tez/query60.q.out @@ -226,9 +226,9 @@ Stage-0 SHUFFLE [RS_71] PartitionCols:_col0 Group By Operator [GBY_70] (rows=1717 width=212) - Output:["_col0","_col1"],aggregations:["sum(_col8)"],keys:_col1 + Output:["_col0","_col1"],aggregations:["sum(_col7)"],keys:_col1 Merge Join Operator [MERGEJOIN_304] (rows=746132 width=100) - Conds:RS_66._col0=RS_67._col4(Inner),Output:["_col1","_col8"] + Conds:RS_66._col0=RS_67._col3(Inner),Output:["_col1","_col7"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_66] PartitionCols:_col0 @@ -261,15 +261,15 @@ Stage-0 default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_id","i_category"] <-Reducer 23 [SIMPLE_EDGE] SHUFFLE [RS_67] - PartitionCols:_col4 + PartitionCols:_col3 Select Operator [SEL_62] (rows=1550375 width=13) - Output:["_col4","_col5"] + Output:["_col3","_col4"] Merge Join Operator [MERGEJOIN_299] (rows=1550375 width=13) Conds:RS_59._col1=RS_350._col0(Inner),Output:["_col2","_col3"] <-Map 28 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_350] PartitionCols:_col0 - Select Operator [SEL_347] (rows=8000000 width=116) + Select Operator [SEL_347] (rows=8000000 width=4) Output:["_col0"] Filter Operator [FIL_346] (rows=8000000 width=112) predicate:((ca_gmt_offset = -6) and ca_address_sk is not null) @@ -283,7 +283,7 @@ Stage-0 <-Map 20 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_334] PartitionCols:_col0 - Select Operator [SEL_331] (rows=50 width=12) + Select Operator [SEL_331] (rows=50 width=4) Output:["_col0"] Filter Operator [FIL_330] (rows=50 width=12) predicate:((d_moy = 9) and (d_year = 1999) and d_date_sk is not null) @@ -344,18 +344,18 @@ Stage-0 SHUFFLE [RS_109] PartitionCols:_col0 Group By Operator [GBY_108] (rows=1717 width=212) - Output:["_col0","_col1"],aggregations:["sum(_col8)"],keys:_col1 + Output:["_col0","_col1"],aggregations:["sum(_col7)"],keys:_col1 Merge Join Operator [MERGEJOIN_305] (rows=379339 width=201) - Conds:RS_104._col0=RS_105._col3(Inner),Output:["_col1","_col8"] + Conds:RS_104._col0=RS_105._col2(Inner),Output:["_col1","_col7"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_104] PartitionCols:_col0 Please refer to the previous Merge Join Operator [MERGEJOIN_294] <-Reducer 26 [SIMPLE_EDGE] SHUFFLE [RS_105] - PartitionCols:_col3 + PartitionCols:_col2 Select Operator [SEL_100] (rows=788222 width=110) - Output:["_col3","_col5"] + Output:["_col2","_col4"] Merge Join Operator [MERGEJOIN_302] (rows=788222 width=110) Conds:RS_97._col2=RS_352._col0(Inner),Output:["_col1","_col3"] <-Map 28 [SIMPLE_EDGE] vectorized @@ -426,18 +426,18 @@ Stage-0 SHUFFLE [RS_34] PartitionCols:_col0 Group By Operator [GBY_33] (rows=1717 width=212) - Output:["_col0","_col1"],aggregations:["sum(_col8)"],keys:_col1 + Output:["_col0","_col1"],aggregations:["sum(_col7)"],keys:_col1 Merge Join Operator [MERGEJOIN_303] (rows=1384530 width=100) - Conds:RS_29._col0=RS_30._col3(Inner),Output:["_col1","_col8"] + Conds:RS_29._col0=RS_30._col2(Inner),Output:["_col1","_col7"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_29] PartitionCols:_col0 Please refer to the previous Merge Join Operator [MERGEJOIN_294] <-Reducer 19 [SIMPLE_EDGE] SHUFFLE [RS_30] - PartitionCols:_col3 + PartitionCols:_col2 Select Operator [SEL_25] (rows=2876890 width=4) - Output:["_col3","_col5"] + Output:["_col2","_col4"] Merge Join Operator [MERGEJOIN_296] (rows=2876890 width=4) Conds:RS_22._col2=RS_348._col0(Inner),Output:["_col1","_col3"] <-Map 28 [SIMPLE_EDGE] vectorized diff --git ql/src/test/results/clientpositive/perf/tez/query61.q.out ql/src/test/results/clientpositive/perf/tez/query61.q.out index dc18d84d46d..0e3ebf707f7 100644 --- ql/src/test/results/clientpositive/perf/tez/query61.q.out +++ ql/src/test/results/clientpositive/perf/tez/query61.q.out @@ -152,9 +152,9 @@ Stage-0 <-Reducer 3 [CUSTOM_SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_42] Group By Operator [GBY_41] (rows=1 width=112) - Output:["_col0"],aggregations:["sum(_col9)"] + Output:["_col0"],aggregations:["sum(_col8)"] Merge Join Operator [MERGEJOIN_264] (rows=505397 width=0) - Conds:RS_37._col0=RS_38._col2(Inner),Output:["_col9"] + Conds:RS_37._col0=RS_38._col2(Inner),Output:["_col8"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_37] PartitionCols:_col0 @@ -172,7 +172,7 @@ Stage-0 <-Map 11 [SIMPLE_EDGE] vectorized SHUFFLE [RS_272] PartitionCols:_col0 - Select Operator [SEL_271] (rows=8000000 width=116) + Select Operator [SEL_271] (rows=8000000 width=4) Output:["_col0"] Filter Operator [FIL_270] (rows=8000000 width=112) predicate:((ca_gmt_offset = -7) and ca_address_sk is not null) @@ -186,7 +186,7 @@ Stage-0 <-Map 29 [SIMPLE_EDGE] vectorized SHUFFLE [RS_316] PartitionCols:_col0 - Select Operator [SEL_315] (rows=2300 width=259) + Select Operator [SEL_315] (rows=2300 width=4) Output:["_col0"] Filter Operator [FIL_314] (rows=2300 width=259) predicate:(((p_channel_dmail = 'Y') or (p_channel_email = 'Y') or (p_channel_tv = 'Y')) and p_promo_sk is not null) @@ -200,7 +200,7 @@ Stage-0 <-Map 26 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_299] PartitionCols:_col0 - Select Operator [SEL_298] (rows=341 width=116) + Select Operator [SEL_298] (rows=341 width=4) Output:["_col0"] Filter Operator [FIL_297] (rows=341 width=115) predicate:((s_gmt_offset = -7) and s_store_sk is not null) @@ -214,7 +214,7 @@ Stage-0 <-Map 23 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_287] PartitionCols:_col0 - Select Operator [SEL_286] (rows=46200 width=99) + Select Operator [SEL_286] (rows=46200 width=4) Output:["_col0"] Filter Operator [FIL_285] (rows=46200 width=94) predicate:((i_category = 'Electronics') and i_item_sk is not null) @@ -228,7 +228,7 @@ Stage-0 <-Map 17 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_275] PartitionCols:_col0 - Select Operator [SEL_274] (rows=50 width=12) + Select Operator [SEL_274] (rows=50 width=4) Output:["_col0"] Filter Operator [FIL_273] (rows=50 width=12) predicate:((d_moy = 11) and (d_year = 1999) and d_date_sk is not null) @@ -294,9 +294,9 @@ Stage-0 <-Reducer 8 [CUSTOM_SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_81] Group By Operator [GBY_80] (rows=1 width=112) - Output:["_col0"],aggregations:["sum(_col8)"] + Output:["_col0"],aggregations:["sum(_col7)"] Merge Join Operator [MERGEJOIN_265] (rows=529208 width=0) - Conds:RS_76._col0=RS_77._col2(Inner),Output:["_col8"] + Conds:RS_76._col0=RS_77._col2(Inner),Output:["_col7"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_76] PartitionCols:_col0 diff --git ql/src/test/results/clientpositive/perf/tez/query63.q.out ql/src/test/results/clientpositive/perf/tez/query63.q.out index 6a6ffb7e3d2..c592009ddb6 100644 --- ql/src/test/results/clientpositive/perf/tez/query63.q.out +++ ql/src/test/results/clientpositive/perf/tez/query63.q.out @@ -104,9 +104,9 @@ Stage-0 SHUFFLE [RS_23] PartitionCols:_col0 Group By Operator [GBY_22] (rows=143 width=120) - Output:["_col0","_col1","_col2"],aggregations:["sum(_col3)"],keys:_col8, _col11 + Output:["_col0","_col1","_col2"],aggregations:["sum(_col3)"],keys:_col5, _col7 Merge Join Operator [MERGEJOIN_84] (rows=129200 width=8) - Conds:RS_18._col2=RS_106._col0(Inner),Output:["_col3","_col8","_col11"] + Conds:RS_18._col2=RS_106._col0(Inner),Output:["_col3","_col5","_col7"] <-Map 11 [SIMPLE_EDGE] vectorized SHUFFLE [RS_106] PartitionCols:_col0 @@ -120,12 +120,12 @@ Stage-0 SHUFFLE [RS_18] PartitionCols:_col2 Merge Join Operator [MERGEJOIN_83] (rows=129200 width=8) - Conds:RS_15._col0=RS_95._col0(Inner),Output:["_col2","_col3","_col8","_col11"] + Conds:RS_15._col0=RS_95._col0(Inner),Output:["_col2","_col3","_col5","_col7"] <-Map 9 [SIMPLE_EDGE] vectorized SHUFFLE [RS_95] PartitionCols:_col0 - Select Operator [SEL_94] (rows=317 width=12) - Output:["_col0","_col2"] + Select Operator [SEL_94] (rows=317 width=8) + Output:["_col0","_col1"] Filter Operator [FIL_93] (rows=317 width=12) predicate:((d_month_seq) IN (1212, 1213, 1214, 1215, 1216, 1217, 1218, 1219, 1220, 1221, 1222, 1223) and d_date_sk is not null) TableScan [TS_6] (rows=73049 width=12) @@ -134,12 +134,12 @@ Stage-0 SHUFFLE [RS_15] PartitionCols:_col0 Merge Join Operator [MERGEJOIN_82] (rows=744232 width=4) - Conds:RS_103._col1=RS_87._col0(Inner),Output:["_col0","_col2","_col3","_col8"] + Conds:RS_103._col1=RS_87._col0(Inner),Output:["_col0","_col2","_col3","_col5"] <-Map 7 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_87] PartitionCols:_col0 - Select Operator [SEL_86] (rows=68 width=290) - Output:["_col0","_col4"] + Select Operator [SEL_86] (rows=68 width=8) + Output:["_col0","_col1"] Filter Operator [FIL_85] (rows=68 width=290) predicate:((((i_category) IN ('Books', 'Children', 'Electronics') and (i_class) IN ('personal', 'portable', 'refernece', 'self-help') and (i_brand) IN ('scholaramalgamalg #14', 'scholaramalgamalg #7', 'exportiunivamalg #9', 'scholaramalgamalg #9')) or ((i_category) IN ('Women', 'Music', 'Men') and (i_class) IN ('accessories', 'classical', 'fragrances', 'pants') and (i_brand) IN ('amalgimporto #1', 'edu packscholar #1', 'exportiimporto #1', 'importoamalg #1'))) and (i_brand) IN ('scholaramalgamalg #14', 'scholaramalgamalg #7', 'exportiunivamalg #9', 'scholaramalgamalg #9', 'amalgimporto #1', 'edu packscholar #1', 'exportiimporto #1', 'importoamalg #1') and (i_category) IN ('Books', 'Children', 'Electronics', 'Women', 'Music', 'Men') and (i_class) IN ('personal', 'portable', 'refernece', 'self-help', 'accessories', 'classical', 'fragrances', 'pants') and i_item_sk is not null) TableScan [TS_3] (rows=462000 width=289) diff --git ql/src/test/results/clientpositive/perf/tez/query64.q.out ql/src/test/results/clientpositive/perf/tez/query64.q.out index f670c4f4e21..7c77e9fc557 100644 --- ql/src/test/results/clientpositive/perf/tez/query64.q.out +++ ql/src/test/results/clientpositive/perf/tez/query64.q.out @@ -265,9 +265,9 @@ POSTHOOK: Output: hdfs://### HDFS PATH ### Plan optimized by CBO. Vertex dependency in root stage -Map 37 <- Reducer 24 (BROADCAST_EDGE), Reducer 40 (BROADCAST_EDGE), Reducer 47 (BROADCAST_EDGE) -Map 44 <- Reducer 40 (BROADCAST_EDGE) -Map 55 <- Reducer 12 (BROADCAST_EDGE), Reducer 32 (BROADCAST_EDGE), Reducer 42 (BROADCAST_EDGE), Reducer 51 (BROADCAST_EDGE) +Map 37 <- Reducer 24 (BROADCAST_EDGE), Reducer 40 (BROADCAST_EDGE), Reducer 46 (BROADCAST_EDGE) +Map 43 <- Reducer 40 (BROADCAST_EDGE) +Map 55 <- Reducer 12 (BROADCAST_EDGE), Reducer 32 (BROADCAST_EDGE), Reducer 42 (BROADCAST_EDGE), Reducer 50 (BROADCAST_EDGE) Map 56 <- Reducer 42 (BROADCAST_EDGE) Reducer 10 <- Reducer 15 (SIMPLE_EDGE), Reducer 9 (SIMPLE_EDGE) Reducer 11 <- Reducer 10 (SIMPLE_EDGE) @@ -276,18 +276,18 @@ Reducer 13 <- Reducer 31 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE) Reducer 14 <- Map 54 (SIMPLE_EDGE), Reducer 13 (SIMPLE_EDGE) Reducer 15 <- Reducer 14 (SIMPLE_EDGE) Reducer 17 <- Map 16 (SIMPLE_EDGE), Reducer 38 (SIMPLE_EDGE) -Reducer 18 <- Map 43 (SIMPLE_EDGE), Reducer 17 (SIMPLE_EDGE) -Reducer 19 <- Reducer 18 (SIMPLE_EDGE), Reducer 34 (SIMPLE_EDGE) +Reducer 18 <- Reducer 17 (SIMPLE_EDGE), Reducer 45 (ONE_TO_ONE_EDGE) +Reducer 19 <- Map 51 (SIMPLE_EDGE), Reducer 18 (SIMPLE_EDGE) Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 16 (SIMPLE_EDGE) -Reducer 20 <- Reducer 19 (SIMPLE_EDGE), Reducer 46 (ONE_TO_ONE_EDGE) +Reducer 20 <- Reducer 19 (SIMPLE_EDGE), Reducer 34 (SIMPLE_EDGE) Reducer 21 <- Map 52 (SIMPLE_EDGE), Reducer 20 (SIMPLE_EDGE) Reducer 22 <- Map 36 (SIMPLE_EDGE), Reducer 21 (SIMPLE_EDGE) Reducer 23 <- Map 53 (SIMPLE_EDGE), Reducer 22 (SIMPLE_EDGE) Reducer 24 <- Map 16 (CUSTOM_SIMPLE_EDGE) Reducer 25 <- Map 16 (SIMPLE_EDGE), Reducer 41 (SIMPLE_EDGE) -Reducer 26 <- Map 43 (SIMPLE_EDGE), Reducer 25 (SIMPLE_EDGE) -Reducer 27 <- Reducer 26 (SIMPLE_EDGE), Reducer 34 (SIMPLE_EDGE) -Reducer 28 <- Reducer 27 (SIMPLE_EDGE), Reducer 50 (ONE_TO_ONE_EDGE) +Reducer 26 <- Reducer 25 (SIMPLE_EDGE), Reducer 49 (ONE_TO_ONE_EDGE) +Reducer 27 <- Map 51 (SIMPLE_EDGE), Reducer 26 (SIMPLE_EDGE) +Reducer 28 <- Reducer 27 (SIMPLE_EDGE), Reducer 34 (SIMPLE_EDGE) Reducer 29 <- Map 52 (SIMPLE_EDGE), Reducer 28 (SIMPLE_EDGE) Reducer 3 <- Map 16 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) Reducer 30 <- Map 36 (SIMPLE_EDGE), Reducer 29 (SIMPLE_EDGE) @@ -299,13 +299,13 @@ Reducer 4 <- Reducer 3 (SIMPLE_EDGE), Reducer 34 (SIMPLE_EDGE) Reducer 40 <- Map 39 (CUSTOM_SIMPLE_EDGE) Reducer 41 <- Map 39 (SIMPLE_EDGE), Map 55 (SIMPLE_EDGE) Reducer 42 <- Map 39 (CUSTOM_SIMPLE_EDGE) -Reducer 45 <- Map 44 (SIMPLE_EDGE), Map 48 (SIMPLE_EDGE) -Reducer 46 <- Reducer 45 (SIMPLE_EDGE) -Reducer 47 <- Reducer 46 (CUSTOM_SIMPLE_EDGE) -Reducer 49 <- Map 48 (SIMPLE_EDGE), Map 56 (SIMPLE_EDGE) +Reducer 44 <- Map 43 (SIMPLE_EDGE), Map 47 (SIMPLE_EDGE) +Reducer 45 <- Reducer 44 (SIMPLE_EDGE) +Reducer 46 <- Reducer 45 (CUSTOM_SIMPLE_EDGE) +Reducer 48 <- Map 47 (SIMPLE_EDGE), Map 56 (SIMPLE_EDGE) +Reducer 49 <- Reducer 48 (SIMPLE_EDGE) Reducer 5 <- Map 36 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) -Reducer 50 <- Reducer 49 (SIMPLE_EDGE) -Reducer 51 <- Reducer 50 (CUSTOM_SIMPLE_EDGE) +Reducer 50 <- Reducer 49 (CUSTOM_SIMPLE_EDGE) Reducer 6 <- Map 54 (SIMPLE_EDGE), Reducer 5 (SIMPLE_EDGE) Reducer 7 <- Reducer 23 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE) Reducer 8 <- Map 54 (SIMPLE_EDGE), Reducer 7 (SIMPLE_EDGE) @@ -320,10 +320,10 @@ Stage-0 Select Operator [SEL_1200] (rows=2169965329 width=1702) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col19","_col20"] <-Reducer 10 [SIMPLE_EDGE] - SHUFFLE [RS_259] - Select Operator [SEL_258] (rows=2169965329 width=1694) + SHUFFLE [RS_257] + Select Operator [SEL_256] (rows=2169965329 width=1694) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18"] - Filter Operator [FIL_257] (rows=2169965329 width=1694) + Filter Operator [FIL_255] (rows=2169965329 width=1694) predicate:(_col19 <= _col12) Merge Join Operator [MERGEJOIN_1087] (rows=6509895988 width=1694) Conds:RS_1171._col2, _col1, _col3=RS_1199._col1, _col0, _col2(Inner),Output:["_col0","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col19","_col20","_col21","_col22"] @@ -335,16 +335,16 @@ Stage-0 Group By Operator [GBY_1169] (rows=2299138 width=1362) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17"],aggregations:["count(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)","sum(VALUE._col3)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4, KEY._col5, KEY._col6, KEY._col7, KEY._col8, KEY._col9, KEY._col10, KEY._col11, KEY._col12, KEY._col13 <-Reducer 8 [SIMPLE_EDGE] - SHUFFLE [RS_124] + SHUFFLE [RS_123] PartitionCols:_col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 - Group By Operator [GBY_123] (rows=2299138 width=1362) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17"],aggregations:["count()","sum(_col43)","sum(_col44)","sum(_col45)"],keys:_col28, _col46, _col29, _col7, _col9, _col14, _col15, _col16, _col17, _col23, _col24, _col25, _col26, _col49 - Select Operator [SEL_122] (rows=2331650 width=1292) - Output:["_col7","_col9","_col14","_col15","_col16","_col17","_col23","_col24","_col25","_col26","_col28","_col29","_col43","_col44","_col45","_col46","_col49"] - Filter Operator [FIL_121] (rows=2331650 width=1292) - predicate:(_col56 <> _col19) + Group By Operator [GBY_122] (rows=2299138 width=1362) + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17"],aggregations:["count()","sum(_col43)","sum(_col44)","sum(_col45)"],keys:_col28, _col46, _col29, _col7, _col9, _col14, _col15, _col16, _col17, _col23, _col24, _col25, _col26, _col47 + Select Operator [SEL_121] (rows=2331650 width=1292) + Output:["_col7","_col9","_col14","_col15","_col16","_col17","_col23","_col24","_col25","_col26","_col28","_col29","_col43","_col44","_col45","_col46","_col47"] + Filter Operator [FIL_120] (rows=2331650 width=1292) + predicate:(_col51 <> _col19) Merge Join Operator [MERGEJOIN_1068] (rows=2331650 width=1292) - Conds:RS_118._col37=RS_1120._col0(Inner),Output:["_col7","_col9","_col14","_col15","_col16","_col17","_col19","_col23","_col24","_col25","_col26","_col28","_col29","_col43","_col44","_col45","_col46","_col49","_col56"] + Conds:RS_117._col37=RS_1120._col0(Inner),Output:["_col7","_col9","_col14","_col15","_col16","_col17","_col19","_col23","_col24","_col25","_col26","_col28","_col29","_col43","_col44","_col45","_col46","_col47","_col51"] <-Map 54 [SIMPLE_EDGE] vectorized SHUFFLE [RS_1120] PartitionCols:_col0 @@ -352,27 +352,27 @@ Stage-0 Output:["_col0","_col1"] Filter Operator [FIL_1118] (rows=1861800 width=89) predicate:cd_demo_sk is not null - TableScan [TS_97] (rows=1861800 width=89) + TableScan [TS_96] (rows=1861800 width=89) default@customer_demographics,cd1,Tbl:COMPLETE,Col:COMPLETE,Output:["cd_demo_sk","cd_marital_status"] <-Reducer 7 [SIMPLE_EDGE] - SHUFFLE [RS_118] + SHUFFLE [RS_117] PartitionCols:_col37 Merge Join Operator [MERGEJOIN_1067] (rows=2299138 width=1205) - Conds:RS_115._col0=RS_116._col16(Inner),Output:["_col7","_col9","_col14","_col15","_col16","_col17","_col19","_col23","_col24","_col25","_col26","_col28","_col29","_col37","_col43","_col44","_col45","_col46","_col49"] + Conds:RS_114._col0=RS_115._col16(Inner),Output:["_col7","_col9","_col14","_col15","_col16","_col17","_col19","_col23","_col24","_col25","_col26","_col28","_col29","_col37","_col43","_col44","_col45","_col46","_col47"] <-Reducer 6 [SIMPLE_EDGE] - SHUFFLE [RS_115] + SHUFFLE [RS_114] PartitionCols:_col0 Merge Join Operator [MERGEJOIN_1056] (rows=70357394 width=458) - Conds:RS_112._col1=RS_1121._col0(Inner),Output:["_col0","_col7","_col9","_col14","_col15","_col16","_col17","_col19"] + Conds:RS_111._col1=RS_1121._col0(Inner),Output:["_col0","_col7","_col9","_col14","_col15","_col16","_col17","_col19"] <-Map 54 [SIMPLE_EDGE] vectorized SHUFFLE [RS_1121] PartitionCols:_col0 Please refer to the previous Select Operator [SEL_1119] <-Reducer 5 [SIMPLE_EDGE] - SHUFFLE [RS_112] + SHUFFLE [RS_111] PartitionCols:_col1 Merge Join Operator [MERGEJOIN_1055] (rows=69376329 width=376) - Conds:RS_109._col3=RS_1115._col0(Inner),Output:["_col0","_col1","_col7","_col9","_col14","_col15","_col16","_col17"] + Conds:RS_108._col3=RS_1115._col0(Inner),Output:["_col0","_col1","_col7","_col9","_col14","_col15","_col16","_col17"] <-Map 36 [SIMPLE_EDGE] vectorized SHUFFLE [RS_1115] PartitionCols:_col0 @@ -383,12 +383,12 @@ Stage-0 TableScan [TS_19] (rows=40000000 width=365) default@customer_address,ad2,Tbl:COMPLETE,Col:COMPLETE,Output:["ca_address_sk","ca_street_number","ca_street_name","ca_city","ca_zip"] <-Reducer 4 [SIMPLE_EDGE] - SHUFFLE [RS_109] + SHUFFLE [RS_108] PartitionCols:_col3 Merge Join Operator [MERGEJOIN_1054] (rows=69376329 width=19) - Conds:RS_106._col2=RS_107._col0(Inner),Output:["_col0","_col1","_col3","_col7","_col9"] + Conds:RS_105._col2=RS_106._col0(Inner),Output:["_col0","_col1","_col3","_col7","_col9"] <-Reducer 34 [SIMPLE_EDGE] - SHUFFLE [RS_107] + SHUFFLE [RS_106] PartitionCols:_col0 Merge Join Operator [MERGEJOIN_1053] (rows=7200 width=4) Conds:RS_1109._col1=RS_1112._col0(Inner),Output:["_col0"] @@ -411,10 +411,10 @@ Stage-0 TableScan [TS_12] (rows=20 width=4) default@income_band,ib2,Tbl:COMPLETE,Col:COMPLETE,Output:["ib_income_band_sk"] <-Reducer 3 [SIMPLE_EDGE] - SHUFFLE [RS_106] + SHUFFLE [RS_105] PartitionCols:_col2 Merge Join Operator [MERGEJOIN_1052] (rows=69376329 width=23) - Conds:RS_103._col4=RS_1098._col0(Inner),Output:["_col0","_col1","_col2","_col3","_col7","_col9"] + Conds:RS_102._col4=RS_1098._col0(Inner),Output:["_col0","_col1","_col2","_col3","_col7","_col9"] <-Map 16 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_1098] PartitionCols:_col0 @@ -425,7 +425,7 @@ Stage-0 TableScan [TS_3] (rows=73049 width=8) default@date_dim,d2,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year"] <-Reducer 2 [SIMPLE_EDGE] - SHUFFLE [RS_103] + SHUFFLE [RS_102] PartitionCols:_col4 Merge Join Operator [MERGEJOIN_1051] (rows=69376329 width=23) Conds:RS_1090._col5=RS_1097._col0(Inner),Output:["_col0","_col1","_col2","_col3","_col4","_col7"] @@ -443,12 +443,12 @@ Stage-0 TableScan [TS_0] (rows=80000000 width=23) default@customer,customer,Tbl:COMPLETE,Col:COMPLETE,Output:["c_customer_sk","c_current_cdemo_sk","c_current_hdemo_sk","c_current_addr_sk","c_first_shipto_date_sk","c_first_sales_date_sk"] <-Reducer 23 [SIMPLE_EDGE] - SHUFFLE [RS_116] + SHUFFLE [RS_115] PartitionCols:_col16 - Select Operator [SEL_96] (rows=2651207 width=784) - Output:["_col3","_col4","_col5","_col6","_col8","_col9","_col16","_col17","_col23","_col24","_col25","_col26","_col29"] + Select Operator [SEL_95] (rows=2651207 width=784) + Output:["_col3","_col4","_col5","_col6","_col8","_col9","_col16","_col17","_col23","_col24","_col25","_col26","_col27"] Merge Join Operator [MERGEJOIN_1066] (rows=2651207 width=784) - Conds:RS_93._col5, _col12=RS_1167._col0, _col1(Inner),Output:["_col6","_col7","_col13","_col14","_col15","_col16","_col19","_col26","_col27","_col29","_col30","_col31","_col32"] + Conds:RS_92._col5, _col12=RS_1167._col0, _col1(Inner),Output:["_col6","_col7","_col13","_col14","_col15","_col16","_col17","_col21","_col22","_col24","_col25","_col26","_col27"] <-Map 53 [SIMPLE_EDGE] vectorized SHUFFLE [RS_1167] PartitionCols:_col0, _col1 @@ -456,22 +456,22 @@ Stage-0 Output:["_col0","_col1"] Filter Operator [FIL_1165] (rows=57591150 width=8) predicate:(sr_item_sk is not null and sr_ticket_number is not null) - TableScan [TS_75] (rows=57591150 width=8) + TableScan [TS_77] (rows=57591150 width=8) default@store_returns,store_returns,Tbl:COMPLETE,Col:COMPLETE,Output:["sr_item_sk","sr_ticket_number"] <-Reducer 22 [SIMPLE_EDGE] - SHUFFLE [RS_93] + SHUFFLE [RS_92] PartitionCols:_col5, _col12 Merge Join Operator [MERGEJOIN_1065] (rows=1608052 width=657) - Conds:RS_90._col9=RS_1116._col0(Inner),Output:["_col5","_col6","_col7","_col12","_col13","_col14","_col15","_col16","_col19","_col26","_col27","_col29","_col30","_col31","_col32"] + Conds:RS_89._col9=RS_1116._col0(Inner),Output:["_col5","_col6","_col7","_col12","_col13","_col14","_col15","_col16","_col17","_col21","_col22","_col24","_col25","_col26","_col27"] <-Map 36 [SIMPLE_EDGE] vectorized SHUFFLE [RS_1116] PartitionCols:_col0 Please refer to the previous Select Operator [SEL_1114] <-Reducer 21 [SIMPLE_EDGE] - SHUFFLE [RS_90] + SHUFFLE [RS_89] PartitionCols:_col9 Merge Join Operator [MERGEJOIN_1064] (rows=1608052 width=296) - Conds:RS_87._col10=RS_1163._col0(Inner),Output:["_col5","_col6","_col7","_col9","_col12","_col13","_col14","_col15","_col16","_col19","_col26","_col27"] + Conds:RS_86._col10=RS_1163._col0(Inner),Output:["_col5","_col6","_col7","_col9","_col12","_col13","_col14","_col15","_col16","_col17","_col21","_col22"] <-Map 52 [SIMPLE_EDGE] vectorized SHUFFLE [RS_1163] PartitionCols:_col0 @@ -479,108 +479,106 @@ Stage-0 Output:["_col0","_col1","_col2"] Filter Operator [FIL_1161] (rows=1704 width=181) predicate:(s_store_name is not null and s_store_sk is not null and s_zip is not null) - TableScan [TS_69] (rows=1704 width=181) + TableScan [TS_71] (rows=1704 width=181) default@store,store,Tbl:COMPLETE,Col:COMPLETE,Output:["s_store_sk","s_store_name","s_zip"] <-Reducer 20 [SIMPLE_EDGE] - SHUFFLE [RS_87] + SHUFFLE [RS_86] PartitionCols:_col10 Merge Join Operator [MERGEJOIN_1063] (rows=1608052 width=119) - Conds:RS_84._col5=RS_1148._col0(Inner),Output:["_col5","_col6","_col7","_col9","_col10","_col12","_col13","_col14","_col15","_col16","_col19"] - <-Reducer 46 [ONE_TO_ONE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_1148] + Conds:RS_83._col0=RS_84._col5(Inner),Output:["_col5","_col6","_col7","_col9","_col10","_col12","_col13","_col14","_col15","_col16","_col17"] + <-Reducer 34 [SIMPLE_EDGE] + SHUFFLE [RS_83] PartitionCols:_col0 - Select Operator [SEL_1147] (rows=13257 width=228) - Output:["_col0"] - Filter Operator [FIL_1146] (rows=13257 width=228) - predicate:(_col1 > (2 * _col2)) - Group By Operator [GBY_1145] (rows=39773 width=228) - Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"],keys:KEY._col0 - <-Reducer 45 [SIMPLE_EDGE] - SHUFFLE [RS_65] - PartitionCols:_col0 - Group By Operator [GBY_64] (rows=12806906 width=228) - Output:["_col0","_col1","_col2"],aggregations:["sum(_col1)","sum(_col2)"],keys:_col0 - Select Operator [SEL_62] (rows=183085709 width=450) - Output:["_col0","_col1","_col2"] - Merge Join Operator [MERGEJOIN_1061] (rows=183085709 width=450) - Conds:RS_1140._col0, _col1=RS_1143._col0, _col1(Inner),Output:["_col0","_col2","_col5","_col6","_col7"] - <-Map 48 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1143] - PartitionCols:_col0, _col1 - Select Operator [SEL_1142] (rows=28798881 width=337) - Output:["_col0","_col1","_col2","_col3","_col4"] - Filter Operator [FIL_1141] (rows=28798881 width=337) - predicate:(cr_item_sk is not null and cr_order_number is not null) - TableScan [TS_56] (rows=28798881 width=337) - default@catalog_returns,catalog_returns,Tbl:COMPLETE,Col:COMPLETE,Output:["cr_item_sk","cr_order_number","cr_refunded_cash","cr_reversed_charge","cr_store_credit"] - <-Map 44 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1140] - PartitionCols:_col0, _col1 - Select Operator [SEL_1139] (rows=287989836 width=119) - Output:["_col0","_col1","_col2"] - Filter Operator [FIL_1138] (rows=287989836 width=119) - predicate:((cs_item_sk BETWEEN DynamicValue(RS_44_item_i_item_sk_min) AND DynamicValue(RS_44_item_i_item_sk_max) and in_bloom_filter(cs_item_sk, DynamicValue(RS_44_item_i_item_sk_bloom_filter))) and cs_item_sk is not null and cs_order_number is not null) - TableScan [TS_53] (rows=287989836 width=119) - default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["cs_item_sk","cs_order_number","cs_ext_list_price"] - <-Reducer 40 [BROADCAST_EDGE] vectorized - BROADCAST [RS_1135] - Group By Operator [GBY_1133] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 39 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_1131] - Group By Operator [GBY_1129] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_1126] (rows=518 width=4) - Output:["_col0"] - Select Operator [SEL_1124] (rows=518 width=312) - Output:["_col0","_col3"] - Filter Operator [FIL_1123] (rows=518 width=312) - predicate:((i_color) IN ('maroon', 'burnished', 'dim', 'steel', 'navajo', 'chocolate') and i_current_price BETWEEN 35 AND 45 and i_current_price BETWEEN 36 AND 50 and i_item_sk is not null) - TableScan [TS_34] (rows=462000 width=311) - default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_current_price","i_color","i_product_name"] + Please refer to the previous Merge Join Operator [MERGEJOIN_1053] <-Reducer 19 [SIMPLE_EDGE] SHUFFLE [RS_84] PartitionCols:_col5 - Merge Join Operator [MERGEJOIN_1062] (rows=1608052 width=119) - Conds:RS_81._col0=RS_82._col5(Inner),Output:["_col5","_col6","_col7","_col9","_col10","_col12","_col13","_col14","_col15","_col16","_col19"] - <-Reducer 34 [SIMPLE_EDGE] - SHUFFLE [RS_81] - PartitionCols:_col0 - Please refer to the previous Merge Join Operator [MERGEJOIN_1053] - <-Reducer 18 [SIMPLE_EDGE] - SHUFFLE [RS_82] - PartitionCols:_col5 - Select Operator [SEL_52] (rows=1608052 width=119) - Output:["_col2","_col3","_col4","_col5","_col6","_col7","_col9","_col10","_col11","_col12","_col13","_col16"] - Merge Join Operator [MERGEJOIN_1060] (rows=1608052 width=119) - Conds:RS_49._col7=RS_1159._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col6","_col8","_col9","_col10","_col11","_col12","_col15"] - <-Map 43 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1159] + Select Operator [SEL_70] (rows=1608052 width=119) + Output:["_col2","_col3","_col4","_col5","_col6","_col7","_col9","_col10","_col11","_col12","_col13","_col14"] + Merge Join Operator [MERGEJOIN_1062] (rows=1608052 width=119) + Conds:RS_67._col7=RS_1159._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col6","_col8","_col9","_col10","_col11","_col12","_col13"] + <-Map 51 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_1159] + PartitionCols:_col0 + Select Operator [SEL_1158] (rows=2300 width=4) + Output:["_col0"] + Filter Operator [FIL_1157] (rows=2300 width=4) + predicate:p_promo_sk is not null + TableScan [TS_55] (rows=2300 width=4) + default@promotion,promotion,Tbl:COMPLETE,Col:COMPLETE,Output:["p_promo_sk"] + <-Reducer 18 [SIMPLE_EDGE] + SHUFFLE [RS_67] + PartitionCols:_col7 + Merge Join Operator [MERGEJOIN_1061] (rows=1608052 width=119) + Conds:RS_64._col1=RS_1148._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13"] + <-Reducer 45 [ONE_TO_ONE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_1148] PartitionCols:_col0 - Select Operator [SEL_1158] (rows=2300 width=4) + Select Operator [SEL_1147] (rows=13257 width=4) Output:["_col0"] - Filter Operator [FIL_1157] (rows=2300 width=4) - predicate:p_promo_sk is not null - TableScan [TS_40] (rows=2300 width=4) - default@promotion,promotion,Tbl:COMPLETE,Col:COMPLETE,Output:["p_promo_sk"] + Filter Operator [FIL_1146] (rows=13257 width=228) + predicate:(_col1 > (2 * _col2)) + Group By Operator [GBY_1145] (rows=39773 width=228) + Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"],keys:KEY._col0 + <-Reducer 44 [SIMPLE_EDGE] + SHUFFLE [RS_51] + PartitionCols:_col0 + Group By Operator [GBY_50] (rows=6482999 width=228) + Output:["_col0","_col1","_col2"],aggregations:["sum(_col2)","sum(_col5)"],keys:_col0 + Merge Join Operator [MERGEJOIN_1060] (rows=183085709 width=227) + Conds:RS_1140._col0, _col1=RS_1143._col0, _col1(Inner),Output:["_col0","_col2","_col5"] + <-Map 47 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_1143] + PartitionCols:_col0, _col1 + Select Operator [SEL_1142] (rows=28798881 width=120) + Output:["_col0","_col1","_col2"] + Filter Operator [FIL_1141] (rows=28798881 width=337) + predicate:(cr_item_sk is not null and cr_order_number is not null) + TableScan [TS_43] (rows=28798881 width=337) + default@catalog_returns,catalog_returns,Tbl:COMPLETE,Col:COMPLETE,Output:["cr_item_sk","cr_order_number","cr_refunded_cash","cr_reversed_charge","cr_store_credit"] + <-Map 43 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_1140] + PartitionCols:_col0, _col1 + Select Operator [SEL_1139] (rows=287989836 width=119) + Output:["_col0","_col1","_col2"] + Filter Operator [FIL_1138] (rows=287989836 width=119) + predicate:((cs_item_sk BETWEEN DynamicValue(RS_59_item_i_item_sk_min) AND DynamicValue(RS_59_item_i_item_sk_max) and in_bloom_filter(cs_item_sk, DynamicValue(RS_59_item_i_item_sk_bloom_filter))) and cs_item_sk is not null and cs_order_number is not null) + TableScan [TS_40] (rows=287989836 width=119) + default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["cs_item_sk","cs_order_number","cs_ext_list_price"] + <-Reducer 40 [BROADCAST_EDGE] vectorized + BROADCAST [RS_1135] + Group By Operator [GBY_1133] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 39 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_1131] + Group By Operator [GBY_1129] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_1126] (rows=518 width=4) + Output:["_col0"] + Select Operator [SEL_1124] (rows=518 width=111) + Output:["_col0","_col1"] + Filter Operator [FIL_1123] (rows=518 width=312) + predicate:((i_color) IN ('maroon', 'burnished', 'dim', 'steel', 'navajo', 'chocolate') and i_current_price BETWEEN 35 AND 45 and i_current_price BETWEEN 36 AND 50 and i_item_sk is not null) + TableScan [TS_34] (rows=462000 width=311) + default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_current_price","i_color","i_product_name"] <-Reducer 17 [SIMPLE_EDGE] - SHUFFLE [RS_49] - PartitionCols:_col7 + SHUFFLE [RS_64] + PartitionCols:_col1 Merge Join Operator [MERGEJOIN_1059] (rows=1608052 width=119) - Conds:RS_46._col0=RS_1099._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col15"] + Conds:RS_61._col0=RS_1099._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13"] <-Map 16 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_1099] PartitionCols:_col0 - Select Operator [SEL_1095] (rows=652 width=8) + Select Operator [SEL_1095] (rows=652 width=4) Output:["_col0"] Filter Operator [FIL_1092] (rows=652 width=8) predicate:((d_year = 2000) and d_date_sk is not null) Please refer to the previous TableScan [TS_3] <-Reducer 38 [SIMPLE_EDGE] - SHUFFLE [RS_46] + SHUFFLE [RS_61] PartitionCols:_col0 Merge Join Operator [MERGEJOIN_1058] (rows=4503592 width=119) - Conds:RS_1156._col1=RS_1125._col0(Inner),Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col15"] + Conds:RS_1156._col1=RS_1125._col0(Inner),Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13"] <-Map 39 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_1125] PartitionCols:_col0 @@ -591,7 +589,7 @@ Stage-0 Select Operator [SEL_1155] (rows=417313408 width=355) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11"] Filter Operator [FIL_1154] (rows=417313408 width=355) - predicate:((ss_item_sk BETWEEN DynamicValue(RS_44_item_i_item_sk_min) AND DynamicValue(RS_44_item_i_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_44_item_i_item_sk_bloom_filter))) and (ss_item_sk BETWEEN DynamicValue(RS_85_catalog_sales_cs_item_sk_min) AND DynamicValue(RS_85_catalog_sales_cs_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_85_catalog_sales_cs_item_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_47_d1_d_date_sk_min) AND DynamicValue(RS_47_d1_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_47_d1_d_date_sk_bloom_filter))) and ss_addr_sk is not null and ss_cdemo_sk is not null and ss_customer_sk is not null and ss_hdemo_sk is not null and ss_item_sk is not null and ss_promo_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null and ss_ticket_number is not null) + predicate:((ss_item_sk BETWEEN DynamicValue(RS_59_item_i_item_sk_min) AND DynamicValue(RS_59_item_i_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_59_item_i_item_sk_bloom_filter))) and (ss_item_sk BETWEEN DynamicValue(RS_65_catalog_sales_cs_item_sk_min) AND DynamicValue(RS_65_catalog_sales_cs_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_65_catalog_sales_cs_item_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_62_d1_d_date_sk_min) AND DynamicValue(RS_62_d1_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_62_d1_d_date_sk_bloom_filter))) and ss_addr_sk is not null and ss_cdemo_sk is not null and ss_customer_sk is not null and ss_hdemo_sk is not null and ss_item_sk is not null and ss_promo_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null and ss_ticket_number is not null) TableScan [TS_31] (rows=575995635 width=355) default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_item_sk","ss_customer_sk","ss_cdemo_sk","ss_hdemo_sk","ss_addr_sk","ss_store_sk","ss_promo_sk","ss_ticket_number","ss_wholesale_cost","ss_list_price","ss_coupon_amt"] <-Reducer 40 [BROADCAST_EDGE] vectorized @@ -608,11 +606,11 @@ Stage-0 Select Operator [SEL_1100] (rows=652 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_1095] - <-Reducer 47 [BROADCAST_EDGE] vectorized + <-Reducer 46 [BROADCAST_EDGE] vectorized BROADCAST [RS_1153] Group By Operator [GBY_1152] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Reducer 46 [CUSTOM_SIMPLE_EDGE] vectorized + <-Reducer 45 [CUSTOM_SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_1151] Group By Operator [GBY_1150] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] @@ -627,143 +625,141 @@ Stage-0 Group By Operator [GBY_1197] (rows=2299138 width=1362) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17"],aggregations:["count(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)","sum(VALUE._col3)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4, KEY._col5, KEY._col6, KEY._col7, KEY._col8, KEY._col9, KEY._col10, KEY._col11, KEY._col12, KEY._col13 <-Reducer 14 [SIMPLE_EDGE] - SHUFFLE [RS_251] + SHUFFLE [RS_249] PartitionCols:_col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 - Group By Operator [GBY_250] (rows=2299138 width=1362) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17"],aggregations:["count()","sum(_col43)","sum(_col44)","sum(_col45)"],keys:_col28, _col46, _col29, _col7, _col9, _col14, _col15, _col16, _col17, _col23, _col24, _col25, _col26, _col49 - Select Operator [SEL_249] (rows=2331650 width=1292) - Output:["_col7","_col9","_col14","_col15","_col16","_col17","_col23","_col24","_col25","_col26","_col28","_col29","_col43","_col44","_col45","_col46","_col49"] - Filter Operator [FIL_248] (rows=2331650 width=1292) - predicate:(_col56 <> _col19) + Group By Operator [GBY_248] (rows=2299138 width=1362) + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17"],aggregations:["count()","sum(_col43)","sum(_col44)","sum(_col45)"],keys:_col28, _col46, _col29, _col7, _col9, _col14, _col15, _col16, _col17, _col23, _col24, _col25, _col26, _col47 + Select Operator [SEL_247] (rows=2331650 width=1292) + Output:["_col7","_col9","_col14","_col15","_col16","_col17","_col23","_col24","_col25","_col26","_col28","_col29","_col43","_col44","_col45","_col46","_col47"] + Filter Operator [FIL_246] (rows=2331650 width=1292) + predicate:(_col51 <> _col19) Merge Join Operator [MERGEJOIN_1086] (rows=2331650 width=1292) - Conds:RS_245._col37=RS_1122._col0(Inner),Output:["_col7","_col9","_col14","_col15","_col16","_col17","_col19","_col23","_col24","_col25","_col26","_col28","_col29","_col43","_col44","_col45","_col46","_col49","_col56"] + Conds:RS_243._col37=RS_1122._col0(Inner),Output:["_col7","_col9","_col14","_col15","_col16","_col17","_col19","_col23","_col24","_col25","_col26","_col28","_col29","_col43","_col44","_col45","_col46","_col47","_col51"] <-Map 54 [SIMPLE_EDGE] vectorized SHUFFLE [RS_1122] PartitionCols:_col0 Please refer to the previous Select Operator [SEL_1119] <-Reducer 13 [SIMPLE_EDGE] - SHUFFLE [RS_245] + SHUFFLE [RS_243] PartitionCols:_col37 Merge Join Operator [MERGEJOIN_1085] (rows=2299138 width=1205) - Conds:RS_242._col0=RS_243._col16(Inner),Output:["_col7","_col9","_col14","_col15","_col16","_col17","_col19","_col23","_col24","_col25","_col26","_col28","_col29","_col37","_col43","_col44","_col45","_col46","_col49"] + Conds:RS_240._col0=RS_241._col16(Inner),Output:["_col7","_col9","_col14","_col15","_col16","_col17","_col19","_col23","_col24","_col25","_col26","_col28","_col29","_col37","_col43","_col44","_col45","_col46","_col47"] <-Reducer 6 [SIMPLE_EDGE] - SHUFFLE [RS_242] + SHUFFLE [RS_240] PartitionCols:_col0 Please refer to the previous Merge Join Operator [MERGEJOIN_1056] <-Reducer 31 [SIMPLE_EDGE] - SHUFFLE [RS_243] + SHUFFLE [RS_241] PartitionCols:_col16 - Select Operator [SEL_223] (rows=2651207 width=784) - Output:["_col3","_col4","_col5","_col6","_col8","_col9","_col16","_col17","_col23","_col24","_col25","_col26","_col29"] + Select Operator [SEL_221] (rows=2651207 width=784) + Output:["_col3","_col4","_col5","_col6","_col8","_col9","_col16","_col17","_col23","_col24","_col25","_col26","_col27"] Merge Join Operator [MERGEJOIN_1084] (rows=2651207 width=784) - Conds:RS_220._col5, _col12=RS_1168._col0, _col1(Inner),Output:["_col6","_col7","_col13","_col14","_col15","_col16","_col19","_col26","_col27","_col29","_col30","_col31","_col32"] + Conds:RS_218._col5, _col12=RS_1168._col0, _col1(Inner),Output:["_col6","_col7","_col13","_col14","_col15","_col16","_col17","_col21","_col22","_col24","_col25","_col26","_col27"] <-Map 53 [SIMPLE_EDGE] vectorized SHUFFLE [RS_1168] PartitionCols:_col0, _col1 Please refer to the previous Select Operator [SEL_1166] <-Reducer 30 [SIMPLE_EDGE] - SHUFFLE [RS_220] + SHUFFLE [RS_218] PartitionCols:_col5, _col12 Merge Join Operator [MERGEJOIN_1083] (rows=1608052 width=657) - Conds:RS_217._col9=RS_1117._col0(Inner),Output:["_col5","_col6","_col7","_col12","_col13","_col14","_col15","_col16","_col19","_col26","_col27","_col29","_col30","_col31","_col32"] + Conds:RS_215._col9=RS_1117._col0(Inner),Output:["_col5","_col6","_col7","_col12","_col13","_col14","_col15","_col16","_col17","_col21","_col22","_col24","_col25","_col26","_col27"] <-Map 36 [SIMPLE_EDGE] vectorized SHUFFLE [RS_1117] PartitionCols:_col0 Please refer to the previous Select Operator [SEL_1114] <-Reducer 29 [SIMPLE_EDGE] - SHUFFLE [RS_217] + SHUFFLE [RS_215] PartitionCols:_col9 Merge Join Operator [MERGEJOIN_1082] (rows=1608052 width=296) - Conds:RS_214._col10=RS_1164._col0(Inner),Output:["_col5","_col6","_col7","_col9","_col12","_col13","_col14","_col15","_col16","_col19","_col26","_col27"] + Conds:RS_212._col10=RS_1164._col0(Inner),Output:["_col5","_col6","_col7","_col9","_col12","_col13","_col14","_col15","_col16","_col17","_col21","_col22"] <-Map 52 [SIMPLE_EDGE] vectorized SHUFFLE [RS_1164] PartitionCols:_col0 Please refer to the previous Select Operator [SEL_1162] <-Reducer 28 [SIMPLE_EDGE] - SHUFFLE [RS_214] + SHUFFLE [RS_212] PartitionCols:_col10 Merge Join Operator [MERGEJOIN_1081] (rows=1608052 width=119) - Conds:RS_211._col5=RS_1186._col0(Inner),Output:["_col5","_col6","_col7","_col9","_col10","_col12","_col13","_col14","_col15","_col16","_col19"] - <-Reducer 50 [ONE_TO_ONE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_1186] + Conds:RS_209._col0=RS_210._col5(Inner),Output:["_col5","_col6","_col7","_col9","_col10","_col12","_col13","_col14","_col15","_col16","_col17"] + <-Reducer 34 [SIMPLE_EDGE] + SHUFFLE [RS_209] PartitionCols:_col0 - Select Operator [SEL_1185] (rows=13257 width=228) - Output:["_col0"] - Filter Operator [FIL_1184] (rows=13257 width=228) - predicate:(_col1 > (2 * _col2)) - Group By Operator [GBY_1183] (rows=39773 width=228) - Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"],keys:KEY._col0 - <-Reducer 49 [SIMPLE_EDGE] - SHUFFLE [RS_192] - PartitionCols:_col0 - Group By Operator [GBY_191] (rows=12806906 width=228) - Output:["_col0","_col1","_col2"],aggregations:["sum(_col1)","sum(_col2)"],keys:_col0 - Select Operator [SEL_189] (rows=183085709 width=450) - Output:["_col0","_col1","_col2"] - Merge Join Operator [MERGEJOIN_1079] (rows=183085709 width=450) - Conds:RS_1182._col0, _col1=RS_1144._col0, _col1(Inner),Output:["_col0","_col2","_col5","_col6","_col7"] - <-Map 48 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1144] - PartitionCols:_col0, _col1 - Please refer to the previous Select Operator [SEL_1142] - <-Map 56 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1182] - PartitionCols:_col0, _col1 - Select Operator [SEL_1181] (rows=287989836 width=119) - Output:["_col0","_col1","_col2"] - Filter Operator [FIL_1180] (rows=287989836 width=119) - predicate:((cs_item_sk BETWEEN DynamicValue(RS_171_item_i_item_sk_min) AND DynamicValue(RS_171_item_i_item_sk_max) and in_bloom_filter(cs_item_sk, DynamicValue(RS_171_item_i_item_sk_bloom_filter))) and cs_item_sk is not null and cs_order_number is not null) - TableScan [TS_180] (rows=287989836 width=119) - default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["cs_item_sk","cs_order_number","cs_ext_list_price"] - <-Reducer 42 [BROADCAST_EDGE] vectorized - BROADCAST [RS_1177] - Group By Operator [GBY_1175] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 39 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_1132] - Group By Operator [GBY_1130] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_1128] (rows=518 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_1124] + Please refer to the previous Merge Join Operator [MERGEJOIN_1053] <-Reducer 27 [SIMPLE_EDGE] - SHUFFLE [RS_211] + SHUFFLE [RS_210] PartitionCols:_col5 - Merge Join Operator [MERGEJOIN_1080] (rows=1608052 width=119) - Conds:RS_208._col0=RS_209._col5(Inner),Output:["_col5","_col6","_col7","_col9","_col10","_col12","_col13","_col14","_col15","_col16","_col19"] - <-Reducer 34 [SIMPLE_EDGE] - SHUFFLE [RS_208] - PartitionCols:_col0 - Please refer to the previous Merge Join Operator [MERGEJOIN_1053] - <-Reducer 26 [SIMPLE_EDGE] - SHUFFLE [RS_209] - PartitionCols:_col5 - Select Operator [SEL_179] (rows=1608052 width=119) - Output:["_col2","_col3","_col4","_col5","_col6","_col7","_col9","_col10","_col11","_col12","_col13","_col16"] - Merge Join Operator [MERGEJOIN_1078] (rows=1608052 width=119) - Conds:RS_176._col7=RS_1160._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col6","_col8","_col9","_col10","_col11","_col12","_col15"] - <-Map 43 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1160] + Select Operator [SEL_196] (rows=1608052 width=119) + Output:["_col2","_col3","_col4","_col5","_col6","_col7","_col9","_col10","_col11","_col12","_col13","_col14"] + Merge Join Operator [MERGEJOIN_1080] (rows=1608052 width=119) + Conds:RS_193._col7=RS_1160._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col6","_col8","_col9","_col10","_col11","_col12","_col13"] + <-Map 51 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_1160] + PartitionCols:_col0 + Please refer to the previous Select Operator [SEL_1158] + <-Reducer 26 [SIMPLE_EDGE] + SHUFFLE [RS_193] + PartitionCols:_col7 + Merge Join Operator [MERGEJOIN_1079] (rows=1608052 width=119) + Conds:RS_190._col1=RS_1186._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13"] + <-Reducer 49 [ONE_TO_ONE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_1186] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_1158] + Select Operator [SEL_1185] (rows=13257 width=4) + Output:["_col0"] + Filter Operator [FIL_1184] (rows=13257 width=228) + predicate:(_col1 > (2 * _col2)) + Group By Operator [GBY_1183] (rows=39773 width=228) + Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"],keys:KEY._col0 + <-Reducer 48 [SIMPLE_EDGE] + SHUFFLE [RS_177] + PartitionCols:_col0 + Group By Operator [GBY_176] (rows=6482999 width=228) + Output:["_col0","_col1","_col2"],aggregations:["sum(_col2)","sum(_col5)"],keys:_col0 + Merge Join Operator [MERGEJOIN_1078] (rows=183085709 width=227) + Conds:RS_1182._col0, _col1=RS_1144._col0, _col1(Inner),Output:["_col0","_col2","_col5"] + <-Map 47 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_1144] + PartitionCols:_col0, _col1 + Please refer to the previous Select Operator [SEL_1142] + <-Map 56 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_1182] + PartitionCols:_col0, _col1 + Select Operator [SEL_1181] (rows=287989836 width=119) + Output:["_col0","_col1","_col2"] + Filter Operator [FIL_1180] (rows=287989836 width=119) + predicate:((cs_item_sk BETWEEN DynamicValue(RS_185_item_i_item_sk_min) AND DynamicValue(RS_185_item_i_item_sk_max) and in_bloom_filter(cs_item_sk, DynamicValue(RS_185_item_i_item_sk_bloom_filter))) and cs_item_sk is not null and cs_order_number is not null) + TableScan [TS_166] (rows=287989836 width=119) + default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["cs_item_sk","cs_order_number","cs_ext_list_price"] + <-Reducer 42 [BROADCAST_EDGE] vectorized + BROADCAST [RS_1177] + Group By Operator [GBY_1175] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 39 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_1132] + Group By Operator [GBY_1130] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_1128] (rows=518 width=4) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_1124] <-Reducer 25 [SIMPLE_EDGE] - SHUFFLE [RS_176] - PartitionCols:_col7 + SHUFFLE [RS_190] + PartitionCols:_col1 Merge Join Operator [MERGEJOIN_1077] (rows=1608052 width=119) - Conds:RS_173._col0=RS_1101._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col15"] + Conds:RS_187._col0=RS_1101._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13"] <-Map 16 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_1101] PartitionCols:_col0 - Select Operator [SEL_1096] (rows=652 width=8) + Select Operator [SEL_1096] (rows=652 width=4) Output:["_col0"] Filter Operator [FIL_1093] (rows=652 width=8) predicate:((d_year = 2001) and d_date_sk is not null) Please refer to the previous TableScan [TS_3] <-Reducer 41 [SIMPLE_EDGE] - SHUFFLE [RS_173] + SHUFFLE [RS_187] PartitionCols:_col0 Merge Join Operator [MERGEJOIN_1076] (rows=4503592 width=119) - Conds:RS_1196._col1=RS_1127._col0(Inner),Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col15"] + Conds:RS_1196._col1=RS_1127._col0(Inner),Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13"] <-Map 39 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_1127] PartitionCols:_col0 @@ -774,8 +770,8 @@ Stage-0 Select Operator [SEL_1195] (rows=417313408 width=355) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11"] Filter Operator [FIL_1194] (rows=417313408 width=355) - predicate:((ss_item_sk BETWEEN DynamicValue(RS_171_item_i_item_sk_min) AND DynamicValue(RS_171_item_i_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_171_item_i_item_sk_bloom_filter))) and (ss_item_sk BETWEEN DynamicValue(RS_212_catalog_sales_cs_item_sk_min) AND DynamicValue(RS_212_catalog_sales_cs_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_212_catalog_sales_cs_item_sk_bloom_filter))) and (ss_item_sk BETWEEN DynamicValue(RS_254_item_i_item_sk_min) AND DynamicValue(RS_254_item_i_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_254_item_i_item_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_174_d1_d_date_sk_min) AND DynamicValue(RS_174_d1_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_174_d1_d_date_sk_bloom_filter))) and ss_addr_sk is not null and ss_cdemo_sk is not null and ss_customer_sk is not null and ss_hdemo_sk is not null and ss_item_sk is not null and ss_promo_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null and ss_ticket_number is not null) - TableScan [TS_158] (rows=575995635 width=355) + predicate:((ss_item_sk BETWEEN DynamicValue(RS_185_item_i_item_sk_min) AND DynamicValue(RS_185_item_i_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_185_item_i_item_sk_bloom_filter))) and (ss_item_sk BETWEEN DynamicValue(RS_191_catalog_sales_cs_item_sk_min) AND DynamicValue(RS_191_catalog_sales_cs_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_191_catalog_sales_cs_item_sk_bloom_filter))) and (ss_item_sk BETWEEN DynamicValue(RS_252_item_i_item_sk_min) AND DynamicValue(RS_252_item_i_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_252_item_i_item_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_188_d1_d_date_sk_min) AND DynamicValue(RS_188_d1_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_188_d1_d_date_sk_bloom_filter))) and ss_addr_sk is not null and ss_cdemo_sk is not null and ss_customer_sk is not null and ss_hdemo_sk is not null and ss_item_sk is not null and ss_promo_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null and ss_ticket_number is not null) + TableScan [TS_157] (rows=575995635 width=355) default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_item_sk","ss_customer_sk","ss_cdemo_sk","ss_hdemo_sk","ss_addr_sk","ss_store_sk","ss_promo_sk","ss_ticket_number","ss_wholesale_cost","ss_list_price","ss_coupon_amt"] <-Reducer 42 [BROADCAST_EDGE] vectorized BROADCAST [RS_1176] @@ -802,11 +798,11 @@ Stage-0 Select Operator [SEL_1102] (rows=652 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_1096] - <-Reducer 51 [BROADCAST_EDGE] vectorized + <-Reducer 50 [BROADCAST_EDGE] vectorized BROADCAST [RS_1191] Group By Operator [GBY_1190] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Reducer 50 [CUSTOM_SIMPLE_EDGE] vectorized + <-Reducer 49 [CUSTOM_SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_1189] Group By Operator [GBY_1188] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] diff --git ql/src/test/results/clientpositive/perf/tez/query65.q.out ql/src/test/results/clientpositive/perf/tez/query65.q.out index 4c3644b16a2..fc2a6c94365 100644 --- ql/src/test/results/clientpositive/perf/tez/query65.q.out +++ ql/src/test/results/clientpositive/perf/tez/query65.q.out @@ -124,7 +124,7 @@ Stage-0 FORWARD [RS_43] PartitionCols:_col0 Filter Operator [FIL_42] (rows=65392 width=231) - predicate:(_col2 <= (0.1 * _col4)) + predicate:(_col2 <= _col4) Merge Join Operator [MERGEJOIN_134] (rows=196176 width=231) Conds:RS_153._col0=RS_168._col0(Inner),Output:["_col0","_col1","_col2","_col4"] <-Reducer 3 [SIMPLE_EDGE] vectorized @@ -142,7 +142,7 @@ Stage-0 <-Map 9 [SIMPLE_EDGE] vectorized SHUFFLE [RS_139] PartitionCols:_col0 - Select Operator [SEL_138] (rows=317 width=8) + Select Operator [SEL_138] (rows=317 width=4) Output:["_col0"] Filter Operator [FIL_137] (rows=317 width=8) predicate:(d_date_sk is not null and d_month_seq BETWEEN 1212 AND 1223) diff --git ql/src/test/results/clientpositive/perf/tez/query66.q.out ql/src/test/results/clientpositive/perf/tez/query66.q.out index 225b62f7e26..767d47bcef8 100644 --- ql/src/test/results/clientpositive/perf/tez/query66.q.out +++ ql/src/test/results/clientpositive/perf/tez/query66.q.out @@ -511,10 +511,10 @@ Stage-0 PartitionCols:_col0, _col1, _col2, _col3, _col4, _col5 Group By Operator [GBY_62] (rows=5559759 width=3166) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col19","_col20","_col21","_col22","_col23","_col24","_col25","_col26","_col27","_col28","_col29"],aggregations:["sum(_col6)","sum(_col7)","sum(_col8)","sum(_col9)","sum(_col10)","sum(_col11)","sum(_col12)","sum(_col13)","sum(_col14)","sum(_col15)","sum(_col16)","sum(_col17)","sum(_col18)","sum(_col19)","sum(_col20)","sum(_col21)","sum(_col22)","sum(_col23)","sum(_col24)","sum(_col25)","sum(_col26)","sum(_col27)","sum(_col28)","sum(_col29)"],keys:_col0, _col1, _col2, _col3, _col4, _col5 - Select Operator [SEL_60] (rows=5559759 width=680) + Select Operator [SEL_60] (rows=5559759 width=750) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col19","_col20","_col21","_col22","_col23","_col24","_col25","_col26","_col27","_col28","_col29"] - Merge Join Operator [MERGEJOIN_204] (rows=5559759 width=680) - Conds:RS_57._col3=RS_259._col0(Inner),Output:["_col4","_col5","_col6","_col11","_col15","_col16","_col17","_col18","_col19","_col20"] + Merge Join Operator [MERGEJOIN_204] (rows=5559759 width=750) + Conds:RS_57._col3=RS_259._col0(Inner),Output:["_col4","_col5","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col19","_col22","_col23","_col24","_col25","_col26","_col27"] <-Map 24 [SIMPLE_EDGE] vectorized SHUFFLE [RS_259] PartitionCols:_col0 @@ -527,12 +527,12 @@ Stage-0 <-Reducer 14 [SIMPLE_EDGE] SHUFFLE [RS_57] PartitionCols:_col3 - Merge Join Operator [MERGEJOIN_203] (rows=5559759 width=205) - Conds:RS_54._col2=RS_245._col0(Inner),Output:["_col3","_col4","_col5","_col6","_col11"] + Merge Join Operator [MERGEJOIN_203] (rows=5559759 width=274) + Conds:RS_54._col2=RS_245._col0(Inner),Output:["_col3","_col4","_col5","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col19"] <-Map 21 [SIMPLE_EDGE] vectorized SHUFFLE [RS_245] PartitionCols:_col0 - Select Operator [SEL_242] (rows=1 width=88) + Select Operator [SEL_242] (rows=1 width=4) Output:["_col0"] Filter Operator [FIL_241] (rows=1 width=88) predicate:((sm_carrier) IN ('DIAMOND', 'AIRBORNE') and sm_ship_mode_sk is not null) @@ -541,13 +541,13 @@ Stage-0 <-Reducer 13 [SIMPLE_EDGE] SHUFFLE [RS_54] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_202] (rows=11119518 width=224) - Conds:RS_51._col0=RS_233._col0(Inner),Output:["_col2","_col3","_col4","_col5","_col6","_col11"] + Merge Join Operator [MERGEJOIN_202] (rows=11119518 width=278) + Conds:RS_51._col0=RS_233._col0(Inner),Output:["_col2","_col3","_col4","_col5","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col19"] <-Map 18 [SIMPLE_EDGE] vectorized SHUFFLE [RS_233] PartitionCols:_col0 - Select Operator [SEL_230] (rows=652 width=12) - Output:["_col0","_col2"] + Select Operator [SEL_230] (rows=652 width=52) + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12"] Filter Operator [FIL_229] (rows=652 width=12) predicate:((d_year = 2002) and d_date_sk is not null) TableScan [TS_6] (rows=73049 width=12) @@ -555,12 +555,12 @@ Stage-0 <-Reducer 12 [SIMPLE_EDGE] SHUFFLE [RS_51] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_201] (rows=31363607 width=234) - Conds:RS_279._col1=RS_221._col0(Inner),Output:["_col0","_col2","_col3","_col4","_col5","_col6"] + Merge Join Operator [MERGEJOIN_201] (rows=31363607 width=235) + Conds:RS_279._col1=RS_221._col0(Inner),Output:["_col0","_col2","_col3","_col4","_col5"] <-Map 10 [SIMPLE_EDGE] vectorized SHUFFLE [RS_221] PartitionCols:_col0 - Select Operator [SEL_218] (rows=9600 width=8) + Select Operator [SEL_218] (rows=9600 width=4) Output:["_col0"] Filter Operator [FIL_217] (rows=9600 width=8) predicate:(t_time BETWEEN 49530 AND 78330 and t_time_sk is not null) @@ -569,8 +569,8 @@ Stage-0 <-Map 25 [SIMPLE_EDGE] vectorized SHUFFLE [RS_279] PartitionCols:_col1 - Select Operator [SEL_278] (rows=282272460 width=243) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"] + Select Operator [SEL_278] (rows=282272460 width=239) + Output:["_col0","_col1","_col2","_col3","_col4","_col5"] Filter Operator [FIL_277] (rows=282272460 width=243) predicate:((cs_ship_mode_sk BETWEEN DynamicValue(RS_55_ship_mode_sm_ship_mode_sk_min) AND DynamicValue(RS_55_ship_mode_sm_ship_mode_sk_max) and in_bloom_filter(cs_ship_mode_sk, DynamicValue(RS_55_ship_mode_sm_ship_mode_sk_bloom_filter))) and (cs_sold_date_sk BETWEEN DynamicValue(RS_52_date_dim_d_date_sk_min) AND DynamicValue(RS_52_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_52_date_dim_d_date_sk_bloom_filter))) and (cs_sold_time_sk BETWEEN DynamicValue(RS_49_time_dim_t_time_sk_min) AND DynamicValue(RS_49_time_dim_t_time_sk_max) and in_bloom_filter(cs_sold_time_sk, DynamicValue(RS_49_time_dim_t_time_sk_bloom_filter))) and cs_ship_mode_sk is not null and cs_sold_date_sk is not null and cs_sold_time_sk is not null and cs_warehouse_sk is not null) TableScan [TS_33] (rows=287989836 width=243) @@ -624,10 +624,10 @@ Stage-0 PartitionCols:_col0, _col1, _col2, _col3, _col4, _col5 Group By Operator [GBY_29] (rows=27 width=3166) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col19","_col20","_col21","_col22","_col23","_col24","_col25","_col26","_col27","_col28","_col29"],aggregations:["sum(_col6)","sum(_col7)","sum(_col8)","sum(_col9)","sum(_col10)","sum(_col11)","sum(_col12)","sum(_col13)","sum(_col14)","sum(_col15)","sum(_col16)","sum(_col17)","sum(_col18)","sum(_col19)","sum(_col20)","sum(_col21)","sum(_col22)","sum(_col23)","sum(_col24)","sum(_col25)","sum(_col26)","sum(_col27)","sum(_col28)","sum(_col29)"],keys:_col0, _col1, _col2, _col3, _col4, _col5 - Select Operator [SEL_27] (rows=2853684 width=707) + Select Operator [SEL_27] (rows=2853684 width=750) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col19","_col20","_col21","_col22","_col23","_col24","_col25","_col26","_col27","_col28","_col29"] - Merge Join Operator [MERGEJOIN_200] (rows=2853684 width=707) - Conds:RS_24._col3=RS_258._col0(Inner),Output:["_col4","_col5","_col6","_col11","_col15","_col16","_col17","_col18","_col19","_col20"] + Merge Join Operator [MERGEJOIN_200] (rows=2853684 width=750) + Conds:RS_24._col3=RS_258._col0(Inner),Output:["_col4","_col5","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col19","_col22","_col23","_col24","_col25","_col26","_col27"] <-Map 24 [SIMPLE_EDGE] vectorized SHUFFLE [RS_258] PartitionCols:_col0 @@ -635,8 +635,8 @@ Stage-0 <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_24] PartitionCols:_col3 - Merge Join Operator [MERGEJOIN_199] (rows=2853684 width=233) - Conds:RS_21._col2=RS_243._col0(Inner),Output:["_col3","_col4","_col5","_col6","_col11"] + Merge Join Operator [MERGEJOIN_199] (rows=2853684 width=275) + Conds:RS_21._col2=RS_243._col0(Inner),Output:["_col3","_col4","_col5","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col19"] <-Map 21 [SIMPLE_EDGE] vectorized SHUFFLE [RS_243] PartitionCols:_col0 @@ -644,8 +644,8 @@ Stage-0 <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_21] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_198] (rows=5707369 width=238) - Conds:RS_18._col0=RS_231._col0(Inner),Output:["_col2","_col3","_col4","_col5","_col6","_col11"] + Merge Join Operator [MERGEJOIN_198] (rows=5707369 width=279) + Conds:RS_18._col0=RS_231._col0(Inner),Output:["_col2","_col3","_col4","_col5","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col19"] <-Map 18 [SIMPLE_EDGE] vectorized SHUFFLE [RS_231] PartitionCols:_col0 @@ -653,8 +653,8 @@ Stage-0 <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_18] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_197] (rows=15984351 width=239) - Conds:RS_255._col1=RS_219._col0(Inner),Output:["_col0","_col2","_col3","_col4","_col5","_col6"] + Merge Join Operator [MERGEJOIN_197] (rows=15984351 width=235) + Conds:RS_255._col1=RS_219._col0(Inner),Output:["_col0","_col2","_col3","_col4","_col5"] <-Map 10 [SIMPLE_EDGE] vectorized SHUFFLE [RS_219] PartitionCols:_col0 @@ -662,8 +662,8 @@ Stage-0 <-Map 1 [SIMPLE_EDGE] vectorized SHUFFLE [RS_255] PartitionCols:_col1 - Select Operator [SEL_254] (rows=143859154 width=243) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"] + Select Operator [SEL_254] (rows=143859154 width=239) + Output:["_col0","_col1","_col2","_col3","_col4","_col5"] Filter Operator [FIL_253] (rows=143859154 width=243) predicate:((ws_ship_mode_sk BETWEEN DynamicValue(RS_22_ship_mode_sm_ship_mode_sk_min) AND DynamicValue(RS_22_ship_mode_sm_ship_mode_sk_max) and in_bloom_filter(ws_ship_mode_sk, DynamicValue(RS_22_ship_mode_sm_ship_mode_sk_bloom_filter))) and (ws_sold_date_sk BETWEEN DynamicValue(RS_19_date_dim_d_date_sk_min) AND DynamicValue(RS_19_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_19_date_dim_d_date_sk_bloom_filter))) and (ws_sold_time_sk BETWEEN DynamicValue(RS_16_time_dim_t_time_sk_min) AND DynamicValue(RS_16_time_dim_t_time_sk_max) and in_bloom_filter(ws_sold_time_sk, DynamicValue(RS_16_time_dim_t_time_sk_bloom_filter))) and ws_ship_mode_sk is not null and ws_sold_date_sk is not null and ws_sold_time_sk is not null and ws_warehouse_sk is not null) TableScan [TS_0] (rows=144002668 width=243) diff --git ql/src/test/results/clientpositive/perf/tez/query67.q.out ql/src/test/results/clientpositive/perf/tez/query67.q.out index b2903311652..442abc8345e 100644 --- ql/src/test/results/clientpositive/perf/tez/query67.q.out +++ ql/src/test/results/clientpositive/perf/tez/query67.q.out @@ -111,92 +111,90 @@ Stage-0 limit:100 Stage-1 Reducer 7 vectorized - File Output Operator [FS_112] - Limit [LIM_111] (rows=100 width=617) + File Output Operator [FS_111] + Limit [LIM_110] (rows=100 width=617) Number of rows:100 - Select Operator [SEL_110] (rows=273593580 width=617) + Select Operator [SEL_109] (rows=273593580 width=617) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9"] <-Reducer 6 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_109] - Select Operator [SEL_108] (rows=273593580 width=617) + SHUFFLE [RS_108] + Select Operator [SEL_107] (rows=273593580 width=617) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9"] - Filter Operator [FIL_107] (rows=273593580 width=613) + Filter Operator [FIL_106] (rows=273593580 width=613) predicate:(rank_window_0 <= 100) - PTF Operator [PTF_106] (rows=820780740 width=613) - Function definitions:[{},{"name:":"windowingtablefunction","order by:":"_col8 DESC NULLS LAST","partition by:":"_col0"}] - Select Operator [SEL_105] (rows=820780740 width=613) + PTF Operator [PTF_105] (rows=820780740 width=613) + Function definitions:[{},{"name:":"windowingtablefunction","order by:":"_col8 DESC NULLS LAST","partition by:":"_col2"}] + Select Operator [SEL_104] (rows=820780740 width=613) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"] <-Reducer 5 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_104] - PartitionCols:_col0 - Select Operator [SEL_103] (rows=820780740 width=613) + SHUFFLE [RS_103] + PartitionCols:_col2 + Select Operator [SEL_102] (rows=820780740 width=613) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"] - Group By Operator [GBY_102] (rows=820780740 width=621) + Group By Operator [GBY_101] (rows=820780740 width=621) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col9"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4, KEY._col5, KEY._col6, KEY._col7, KEY._col8 <-Reducer 4 [SIMPLE_EDGE] - SHUFFLE [RS_24] + SHUFFLE [RS_23] PartitionCols:_col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Group By Operator [GBY_23] (rows=820780740 width=621) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9"],aggregations:["sum(_col8)"],keys:_col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, 0L - Select Operator [SEL_21] (rows=91197860 width=586) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"] - Merge Join Operator [MERGEJOIN_84] (rows=91197860 width=586) - Conds:RS_18._col1=RS_101._col0(Inner),Output:["_col3","_col4","_col7","_col8","_col9","_col11","_col13","_col14","_col15","_col16"] - <-Map 11 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_101] - PartitionCols:_col0 - Select Operator [SEL_100] (rows=462000 width=393) - Output:["_col0","_col1","_col2","_col3","_col4"] - Filter Operator [FIL_99] (rows=462000 width=393) - predicate:i_item_sk is not null - TableScan [TS_9] (rows=462000 width=393) - default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_brand","i_class","i_category","i_product_name"] - <-Reducer 3 [SIMPLE_EDGE] - SHUFFLE [RS_18] - PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_83] (rows=91197860 width=201) - Conds:RS_15._col2=RS_98._col0(Inner),Output:["_col1","_col3","_col4","_col7","_col8","_col9","_col11"] - <-Map 10 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_98] - PartitionCols:_col0 - Select Operator [SEL_97] (rows=1704 width=104) - Output:["_col0","_col1"] - Filter Operator [FIL_96] (rows=1704 width=104) - predicate:s_store_sk is not null - TableScan [TS_6] (rows=1704 width=104) - default@store,store,Tbl:COMPLETE,Col:COMPLETE,Output:["s_store_sk","s_store_id"] - <-Reducer 2 [SIMPLE_EDGE] - SHUFFLE [RS_15] - PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_82] (rows=91197860 width=104) - Conds:RS_95._col0=RS_87._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col7","_col8","_col9"] - <-Map 8 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_87] - PartitionCols:_col0 - Select Operator [SEL_86] (rows=317 width=20) - Output:["_col0","_col2","_col3","_col4"] - Filter Operator [FIL_85] (rows=317 width=20) - predicate:(d_date_sk is not null and d_month_seq BETWEEN 1212 AND 1223) - TableScan [TS_3] (rows=73049 width=20) - default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_month_seq","d_year","d_moy","d_qoy"] - <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_95] - PartitionCols:_col0 - Select Operator [SEL_94] (rows=525329897 width=122) - Output:["_col0","_col1","_col2","_col3","_col4"] - Filter Operator [FIL_93] (rows=525329897 width=122) - predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_13_date_dim_d_date_sk_min) AND DynamicValue(RS_13_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_13_date_dim_d_date_sk_bloom_filter))) and ss_item_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null) - TableScan [TS_0] (rows=575995635 width=122) - default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_item_sk","ss_store_sk","ss_quantity","ss_sales_price"] - <-Reducer 9 [BROADCAST_EDGE] vectorized - BROADCAST [RS_92] - Group By Operator [GBY_91] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 8 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_90] - Group By Operator [GBY_89] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_88] (rows=317 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_86] + Group By Operator [GBY_22] (rows=820780740 width=621) + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9"],aggregations:["sum(_col3)"],keys:_col11, _col12, _col13, _col14, _col5, _col6, _col7, _col9, 0L + Merge Join Operator [MERGEJOIN_83] (rows=91197860 width=613) + Conds:RS_18._col1=RS_100._col0(Inner),Output:["_col3","_col5","_col6","_col7","_col9","_col11","_col12","_col13","_col14"] + <-Map 11 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_100] + PartitionCols:_col0 + Select Operator [SEL_99] (rows=462000 width=393) + Output:["_col0","_col1","_col2","_col3","_col4"] + Filter Operator [FIL_98] (rows=462000 width=393) + predicate:i_item_sk is not null + TableScan [TS_9] (rows=462000 width=393) + default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_brand","i_class","i_category","i_product_name"] + <-Reducer 3 [SIMPLE_EDGE] + SHUFFLE [RS_18] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_82] (rows=91197860 width=228) + Conds:RS_15._col2=RS_97._col0(Inner),Output:["_col1","_col3","_col5","_col6","_col7","_col9"] + <-Map 10 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_97] + PartitionCols:_col0 + Select Operator [SEL_96] (rows=1704 width=104) + Output:["_col0","_col1"] + Filter Operator [FIL_95] (rows=1704 width=104) + predicate:s_store_sk is not null + TableScan [TS_6] (rows=1704 width=104) + default@store,store,Tbl:COMPLETE,Col:COMPLETE,Output:["s_store_sk","s_store_id"] + <-Reducer 2 [SIMPLE_EDGE] + SHUFFLE [RS_15] + PartitionCols:_col2 + Merge Join Operator [MERGEJOIN_81] (rows=91197860 width=130) + Conds:RS_94._col0=RS_86._col0(Inner),Output:["_col1","_col2","_col3","_col5","_col6","_col7"] + <-Map 8 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_86] + PartitionCols:_col0 + Select Operator [SEL_85] (rows=317 width=16) + Output:["_col0","_col1","_col2","_col3"] + Filter Operator [FIL_84] (rows=317 width=20) + predicate:(d_date_sk is not null and d_month_seq BETWEEN 1212 AND 1223) + TableScan [TS_3] (rows=73049 width=20) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_month_seq","d_year","d_moy","d_qoy"] + <-Map 1 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_94] + PartitionCols:_col0 + Select Operator [SEL_93] (rows=525329897 width=123) + Output:["_col0","_col1","_col2","_col3"] + Filter Operator [FIL_92] (rows=525329897 width=122) + predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_13_date_dim_d_date_sk_min) AND DynamicValue(RS_13_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_13_date_dim_d_date_sk_bloom_filter))) and ss_item_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null) + TableScan [TS_0] (rows=575995635 width=122) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_item_sk","ss_store_sk","ss_quantity","ss_sales_price"] + <-Reducer 9 [BROADCAST_EDGE] vectorized + BROADCAST [RS_91] + Group By Operator [GBY_90] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 8 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_89] + Group By Operator [GBY_88] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_87] (rows=317 width=4) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_85] diff --git ql/src/test/results/clientpositive/perf/tez/query68.q.out ql/src/test/results/clientpositive/perf/tez/query68.q.out index 7c94381d40f..1ce67a7225b 100644 --- ql/src/test/results/clientpositive/perf/tez/query68.q.out +++ ql/src/test/results/clientpositive/perf/tez/query68.q.out @@ -162,9 +162,9 @@ Stage-0 SHUFFLE [RS_35] PartitionCols:_col0, _col1, _col2, _col3 Group By Operator [GBY_34] (rows=4418634 width=433) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"],aggregations:["sum(_col6)","sum(_col7)","sum(_col8)"],keys:_col1, _col18, _col3, _col5 + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"],aggregations:["sum(_col6)","sum(_col7)","sum(_col8)"],keys:_col1, _col13, _col3, _col5 Merge Join Operator [MERGEJOIN_144] (rows=4418634 width=97) - Conds:RS_30._col3=RS_152._col0(Inner),Output:["_col1","_col3","_col5","_col6","_col7","_col8","_col18"] + Conds:RS_30._col3=RS_152._col0(Inner),Output:["_col1","_col3","_col5","_col6","_col7","_col8","_col13"] <-Map 5 [SIMPLE_EDGE] vectorized SHUFFLE [RS_152] PartitionCols:_col0 @@ -177,7 +177,7 @@ Stage-0 <-Map 16 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_171] PartitionCols:_col0 - Select Operator [SEL_170] (rows=1855 width=12) + Select Operator [SEL_170] (rows=1855 width=4) Output:["_col0"] Filter Operator [FIL_169] (rows=1855 width=12) predicate:(((hd_dep_count = 2) or (hd_vehicle_count = 1)) and hd_demo_sk is not null) @@ -191,7 +191,7 @@ Stage-0 <-Map 14 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_163] PartitionCols:_col0 - Select Operator [SEL_162] (rows=85 width=97) + Select Operator [SEL_162] (rows=85 width=4) Output:["_col0"] Filter Operator [FIL_161] (rows=85 width=97) predicate:((s_city) IN ('Cedar Grove', 'Wildwood') and s_store_sk is not null) @@ -205,7 +205,7 @@ Stage-0 <-Map 12 [SIMPLE_EDGE] vectorized SHUFFLE [RS_155] PartitionCols:_col0 - Select Operator [SEL_154] (rows=170 width=12) + Select Operator [SEL_154] (rows=170 width=4) Output:["_col0"] Filter Operator [FIL_153] (rows=170 width=12) predicate:((d_year) IN (1998, 1999, 2000) and d_date_sk is not null and d_dom BETWEEN 1 AND 2) diff --git ql/src/test/results/clientpositive/perf/tez/query69.q.out ql/src/test/results/clientpositive/perf/tez/query69.q.out index 65601d745c4..4da7a69fe2a 100644 --- ql/src/test/results/clientpositive/perf/tez/query69.q.out +++ ql/src/test/results/clientpositive/perf/tez/query69.q.out @@ -223,7 +223,7 @@ Stage-0 <-Map 16 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_196] PartitionCols:_col0 - Select Operator [SEL_195] (rows=150 width=12) + Select Operator [SEL_195] (rows=150 width=4) Output:["_col0"] Filter Operator [FIL_194] (rows=150 width=12) predicate:((d_year = 1999) and d_date_sk is not null and d_moy BETWEEN 1 AND 3) diff --git ql/src/test/results/clientpositive/perf/tez/query7.q.out ql/src/test/results/clientpositive/perf/tez/query7.q.out index 6cd8fb58f45..fece637352c 100644 --- ql/src/test/results/clientpositive/perf/tez/query7.q.out +++ ql/src/test/results/clientpositive/perf/tez/query7.q.out @@ -83,11 +83,11 @@ Stage-0 SHUFFLE [RS_29] PartitionCols:_col0 Group By Operator [GBY_28] (rows=462000 width=476) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"],aggregations:["sum(_col4)","count(_col4)","sum(_col5)","count(_col5)","sum(_col7)","count(_col7)","sum(_col6)","count(_col6)"],keys:_col18 + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"],aggregations:["sum(_col4)","count(_col4)","sum(_col5)","count(_col5)","sum(_col7)","count(_col7)","sum(_col6)","count(_col6)"],keys:_col12 Top N Key Operator [TNK_55] (rows=1441769 width=100) - keys:_col18,sort order:+,top n:100 + keys:_col12,sort order:+,top n:100 Merge Join Operator [MERGEJOIN_99] (rows=1441769 width=100) - Conds:RS_24._col1=RS_124._col0(Inner),Output:["_col4","_col5","_col6","_col7","_col18"] + Conds:RS_24._col1=RS_124._col0(Inner),Output:["_col4","_col5","_col6","_col7","_col12"] <-Map 13 [SIMPLE_EDGE] vectorized SHUFFLE [RS_124] PartitionCols:_col0 @@ -105,7 +105,7 @@ Stage-0 <-Map 12 [SIMPLE_EDGE] vectorized SHUFFLE [RS_121] PartitionCols:_col0 - Select Operator [SEL_120] (rows=2300 width=174) + Select Operator [SEL_120] (rows=2300 width=4) Output:["_col0"] Filter Operator [FIL_119] (rows=2300 width=174) predicate:(((p_channel_email = 'N') or (p_channel_event = 'N')) and p_promo_sk is not null) @@ -119,7 +119,7 @@ Stage-0 <-Map 10 [SIMPLE_EDGE] vectorized SHUFFLE [RS_110] PartitionCols:_col0 - Select Operator [SEL_109] (rows=652 width=8) + Select Operator [SEL_109] (rows=652 width=4) Output:["_col0"] Filter Operator [FIL_108] (rows=652 width=8) predicate:((d_year = 1998) and d_date_sk is not null) @@ -133,7 +133,7 @@ Stage-0 <-Map 8 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_102] PartitionCols:_col0 - Select Operator [SEL_101] (rows=14776 width=265) + Select Operator [SEL_101] (rows=14776 width=4) Output:["_col0"] Filter Operator [FIL_100] (rows=14776 width=268) predicate:((cd_education_status = 'Primary') and (cd_gender = 'F') and (cd_marital_status = 'W') and cd_demo_sk is not null) diff --git ql/src/test/results/clientpositive/perf/tez/query70.q.out ql/src/test/results/clientpositive/perf/tez/query70.q.out index e8743e32987..4650ef66fc0 100644 --- ql/src/test/results/clientpositive/perf/tez/query70.q.out +++ ql/src/test/results/clientpositive/perf/tez/query70.q.out @@ -149,9 +149,9 @@ Stage-0 SHUFFLE [RS_26] PartitionCols:_col0 Group By Operator [GBY_25] (rows=1704 width=198) - Output:["_col0","_col1"],aggregations:["sum(_col2)"],keys:_col6 + Output:["_col0","_col1"],aggregations:["sum(_col2)"],keys:_col5 Merge Join Operator [MERGEJOIN_133] (rows=91197860 width=168) - Conds:RS_21._col1=RS_151._col0(Inner),Output:["_col2","_col6"] + Conds:RS_21._col1=RS_151._col0(Inner),Output:["_col2","_col5"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_21] PartitionCols:_col1 diff --git ql/src/test/results/clientpositive/perf/tez/query71.q.out ql/src/test/results/clientpositive/perf/tez/query71.q.out index e031c3aa054..3654e998618 100644 --- ql/src/test/results/clientpositive/perf/tez/query71.q.out +++ ql/src/test/results/clientpositive/perf/tez/query71.q.out @@ -125,13 +125,13 @@ Stage-0 SHUFFLE [RS_46] PartitionCols:_col0, _col1, _col2, _col3 Group By Operator [GBY_45] (rows=1991967 width=223) - Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["sum(_col0)"],keys:_col4, _col8, _col9, _col5 + Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["sum(_col0)"],keys:_col4, _col7, _col8, _col5 Merge Join Operator [MERGEJOIN_140] (rows=1991967 width=112) - Conds:RS_41._col2=RS_173._col0(Inner),Output:["_col0","_col4","_col5","_col8","_col9"] + Conds:RS_41._col2=RS_173._col0(Inner),Output:["_col0","_col4","_col5","_col7","_col8"] <-Map 20 [SIMPLE_EDGE] vectorized SHUFFLE [RS_173] PartitionCols:_col0 - Select Operator [SEL_172] (rows=43200 width=99) + Select Operator [SEL_172] (rows=43200 width=12) Output:["_col0","_col1","_col2"] Filter Operator [FIL_171] (rows=43200 width=99) predicate:((t_meal_time) IN ('breakfast', 'dinner') and t_time_sk is not null) @@ -145,7 +145,7 @@ Stage-0 <-Map 18 [SIMPLE_EDGE] vectorized SHUFFLE [RS_163] PartitionCols:_col0 - Select Operator [SEL_162] (rows=7333 width=111) + Select Operator [SEL_162] (rows=7333 width=107) Output:["_col0","_col1","_col2"] Filter Operator [FIL_161] (rows=7333 width=111) predicate:((i_manager_id = 1) and i_item_sk is not null) @@ -162,7 +162,7 @@ Stage-0 <-Map 12 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_191] PartitionCols:_col0 - Select Operator [SEL_190] (rows=50 width=12) + Select Operator [SEL_190] (rows=50 width=4) Output:["_col0"] Filter Operator [FIL_189] (rows=50 width=12) predicate:((d_moy = 12) and (d_year = 2001) and d_date_sk is not null) @@ -220,7 +220,7 @@ Stage-0 <-Map 16 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_202] PartitionCols:_col0 - Select Operator [SEL_201] (rows=50 width=12) + Select Operator [SEL_201] (rows=50 width=4) Output:["_col0"] Filter Operator [FIL_200] (rows=50 width=12) predicate:((d_moy = 12) and (d_year = 2001) and d_date_sk is not null) @@ -262,7 +262,7 @@ Stage-0 <-Map 8 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_155] PartitionCols:_col0 - Select Operator [SEL_154] (rows=50 width=12) + Select Operator [SEL_154] (rows=50 width=4) Output:["_col0"] Filter Operator [FIL_153] (rows=50 width=12) predicate:((d_moy = 12) and (d_year = 2001) and d_date_sk is not null) diff --git ql/src/test/results/clientpositive/perf/tez/query72.q.out ql/src/test/results/clientpositive/perf/tez/query72.q.out index 700a8769a29..cffb09b3606 100644 --- ql/src/test/results/clientpositive/perf/tez/query72.q.out +++ ql/src/test/results/clientpositive/perf/tez/query72.q.out @@ -120,7 +120,7 @@ Stage-0 Select Operator [SEL_66] (rows=1574305390 width=292) Output:["_col0","_col1","_col2","_col3","_col4"] Merge Join Operator [MERGEJOIN_251] (rows=1574305390 width=292) - Conds:RS_63._col4, _col6=RS_298._col0, _col1(Left Outer),Output:["_col13","_col15","_col22","_col28"] + Conds:RS_63._col4, _col6=RS_298._col0, _col1(Left Outer),Output:["_col13","_col15","_col19","_col25"] <-Map 26 [SIMPLE_EDGE] vectorized SHUFFLE [RS_298] PartitionCols:_col0, _col1 @@ -134,9 +134,9 @@ Stage-0 SHUFFLE [RS_63] PartitionCols:_col4, _col6 Select Operator [SEL_59] (rows=610435044 width=300) - Output:["_col4","_col6","_col13","_col15","_col22","_col28"] + Output:["_col4","_col6","_col13","_col15","_col19","_col25"] Merge Join Operator [MERGEJOIN_250] (rows=610435044 width=300) - Conds:RS_56._col0, _col20=RS_295._col0, _col1(Inner),Output:["_col5","_col9","_col14","_col16","_col20","_col26"] + Conds:RS_56._col0, _col19=RS_295._col0, _col1(Inner),Output:["_col5","_col9","_col14","_col16","_col19","_col23"] <-Map 25 [SIMPLE_EDGE] vectorized SHUFFLE [RS_295] PartitionCols:_col0, _col1 @@ -148,24 +148,24 @@ Stage-0 default@date_dim,d2,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_week_seq"] <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_56] - PartitionCols:_col0, _col20 + PartitionCols:_col0, _col19 Filter Operator [FIL_55] (rows=545947820 width=311) predicate:(_col3 < _col17) Merge Join Operator [MERGEJOIN_249] (rows=1637843460 width=311) - Conds:RS_52._col1=RS_53._col8(Inner),Output:["_col0","_col3","_col5","_col9","_col14","_col16","_col17","_col20","_col26"] + Conds:RS_52._col1=RS_53._col8(Inner),Output:["_col0","_col3","_col5","_col9","_col14","_col16","_col17","_col19","_col23"] <-Reducer 15 [SIMPLE_EDGE] SHUFFLE [RS_53] PartitionCols:_col8 - Select Operator [SEL_45] (rows=2726340 width=391) - Output:["_col3","_col8","_col10","_col11","_col14","_col20"] - Filter Operator [FIL_44] (rows=2726340 width=391) - predicate:(UDFToDouble(_col20) > (UDFToDouble(_col9) + 5.0D)) - Merge Join Operator [MERGEJOIN_248] (rows=8179022 width=391) - Conds:RS_41._col1=RS_292._col0(Inner),Output:["_col4","_col6","_col7","_col9","_col10","_col16","_col18","_col20"] + Select Operator [SEL_45] (rows=2726340 width=219) + Output:["_col3","_col8","_col10","_col11","_col13","_col17"] + Filter Operator [FIL_44] (rows=2726340 width=219) + predicate:(_col17 > _col10) + Merge Join Operator [MERGEJOIN_248] (rows=8179022 width=219) + Conds:RS_41._col1=RS_292._col0(Inner),Output:["_col4","_col6","_col7","_col9","_col10","_col13","_col15","_col17"] <-Map 24 [SIMPLE_EDGE] vectorized SHUFFLE [RS_292] PartitionCols:_col0 - Select Operator [SEL_291] (rows=73049 width=98) + Select Operator [SEL_291] (rows=73049 width=12) Output:["_col0","_col1"] Filter Operator [FIL_290] (rows=73049 width=98) predicate:d_date_sk is not null @@ -174,8 +174,8 @@ Stage-0 <-Reducer 14 [SIMPLE_EDGE] SHUFFLE [RS_41] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_247] (rows=8179022 width=300) - Conds:RS_38._col4=RS_289._col0(Inner),Output:["_col1","_col4","_col6","_col7","_col9","_col10","_col16","_col18"] + Merge Join Operator [MERGEJOIN_247] (rows=8179022 width=214) + Conds:RS_38._col4=RS_289._col0(Inner),Output:["_col1","_col4","_col6","_col7","_col9","_col10","_col13","_col15"] <-Map 23 [SIMPLE_EDGE] vectorized SHUFFLE [RS_289] PartitionCols:_col0 @@ -188,8 +188,8 @@ Stage-0 <-Reducer 13 [SIMPLE_EDGE] SHUFFLE [RS_38] PartitionCols:_col4 - Merge Join Operator [MERGEJOIN_246] (rows=8179022 width=116) - Conds:RS_35._col5=RS_286._col0(Left Outer),Output:["_col1","_col4","_col6","_col7","_col9","_col10","_col16"] + Merge Join Operator [MERGEJOIN_246] (rows=8179022 width=30) + Conds:RS_35._col5=RS_286._col0(Left Outer),Output:["_col1","_col4","_col6","_col7","_col9","_col10","_col13"] <-Map 22 [SIMPLE_EDGE] vectorized SHUFFLE [RS_286] PartitionCols:_col0 @@ -200,12 +200,12 @@ Stage-0 <-Reducer 12 [SIMPLE_EDGE] SHUFFLE [RS_35] PartitionCols:_col5 - Merge Join Operator [MERGEJOIN_245] (rows=8179022 width=115) + Merge Join Operator [MERGEJOIN_245] (rows=8179022 width=29) Conds:RS_32._col3=RS_276._col0(Inner),Output:["_col1","_col4","_col5","_col6","_col7","_col9","_col10"] <-Map 20 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_276] PartitionCols:_col0 - Select Operator [SEL_275] (rows=1440 width=97) + Select Operator [SEL_275] (rows=1440 width=4) Output:["_col0"] Filter Operator [FIL_274] (rows=1440 width=96) predicate:((hd_buy_potential = '1001-5000') and hd_demo_sk is not null) @@ -214,12 +214,12 @@ Stage-0 <-Reducer 11 [SIMPLE_EDGE] SHUFFLE [RS_32] PartitionCols:_col3 - Merge Join Operator [MERGEJOIN_244] (rows=40895108 width=121) + Merge Join Operator [MERGEJOIN_244] (rows=40895108 width=35) Conds:RS_29._col2=RS_268._col0(Inner),Output:["_col1","_col3","_col4","_col5","_col6","_col7","_col9","_col10"] <-Map 18 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_268] PartitionCols:_col0 - Select Operator [SEL_267] (rows=265971 width=89) + Select Operator [SEL_267] (rows=265971 width=4) Output:["_col0"] Filter Operator [FIL_266] (rows=265971 width=89) predicate:((cd_marital_status = 'M') and cd_demo_sk is not null) @@ -228,12 +228,12 @@ Stage-0 <-Reducer 10 [SIMPLE_EDGE] SHUFFLE [RS_29] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_243] (rows=100076475 width=125) + Merge Join Operator [MERGEJOIN_243] (rows=100076475 width=39) Conds:RS_284._col0=RS_260._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col9","_col10"] <-Map 16 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_260] PartitionCols:_col0 - Select Operator [SEL_259] (rows=652 width=106) + Select Operator [SEL_259] (rows=652 width=16) Output:["_col0","_col1","_col2"] Filter Operator [FIL_258] (rows=652 width=106) predicate:((d_year = 2001) and d_date_sk is not null and d_week_seq is not null) diff --git ql/src/test/results/clientpositive/perf/tez/query73.q.out ql/src/test/results/clientpositive/perf/tez/query73.q.out index 7aafbcf61c2..fc87b648fb1 100644 --- ql/src/test/results/clientpositive/perf/tez/query73.q.out +++ ql/src/test/results/clientpositive/perf/tez/query73.q.out @@ -120,7 +120,7 @@ Stage-0 <-Map 13 [SIMPLE_EDGE] vectorized SHUFFLE [RS_122] PartitionCols:_col0 - Select Operator [SEL_121] (rows=85 width=102) + Select Operator [SEL_121] (rows=85 width=4) Output:["_col0"] Filter Operator [FIL_120] (rows=85 width=102) predicate:((s_county) IN ('Mobile County', 'Maverick County', 'Huron County', 'Kittitas County') and s_store_sk is not null) @@ -134,7 +134,7 @@ Stage-0 <-Map 11 [SIMPLE_EDGE] vectorized SHUFFLE [RS_114] PartitionCols:_col0 - Select Operator [SEL_113] (rows=480 width=104) + Select Operator [SEL_113] (rows=480 width=4) Output:["_col0"] Filter Operator [FIL_112] (rows=480 width=104) predicate:((hd_buy_potential) IN ('>10000', 'unknown') and (hd_vehicle_count > 0) and CASE WHEN ((hd_vehicle_count > 0)) THEN (((UDFToDouble(hd_dep_count) / UDFToDouble(hd_vehicle_count)) > 1.0D)) ELSE (null) END and hd_demo_sk is not null) @@ -148,7 +148,7 @@ Stage-0 <-Map 9 [SIMPLE_EDGE] vectorized SHUFFLE [RS_106] PartitionCols:_col0 - Select Operator [SEL_105] (rows=170 width=12) + Select Operator [SEL_105] (rows=170 width=4) Output:["_col0"] Filter Operator [FIL_104] (rows=170 width=12) predicate:((d_year) IN (2000, 2001, 2002) and d_date_sk is not null and d_dom BETWEEN 1 AND 2) diff --git ql/src/test/results/clientpositive/perf/tez/query74.q.out ql/src/test/results/clientpositive/perf/tez/query74.q.out index 4b174fe4d45..20aade29748 100644 --- ql/src/test/results/clientpositive/perf/tez/query74.q.out +++ ql/src/test/results/clientpositive/perf/tez/query74.q.out @@ -161,99 +161,97 @@ Stage-0 limit:100 Stage-1 Reducer 8 vectorized - File Output Operator [FS_354] - Limit [LIM_353] (rows=100 width=280) + File Output Operator [FS_353] + Limit [LIM_352] (rows=100 width=280) Number of rows:100 - Select Operator [SEL_352] (rows=12248093 width=280) + Select Operator [SEL_351] (rows=12248093 width=280) Output:["_col0","_col1","_col2"] <-Reducer 7 [SIMPLE_EDGE] SHUFFLE [RS_93] Select Operator [SEL_92] (rows=12248093 width=280) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_91] (rows=12248093 width=728) - predicate:CASE WHEN (_col3 is not null) THEN (CASE WHEN (_col5 is not null) THEN (((_col1 / _col5) > (_col9 / _col3))) ELSE ((null > (_col9 / _col3))) END) ELSE (CASE WHEN (_col5 is not null) THEN (((_col1 / _col5) > null)) ELSE (null) END) END - Merge Join Operator [MERGEJOIN_287] (rows=24496186 width=728) - Conds:RS_88._col2=RS_351._col0(Inner),Output:["_col1","_col3","_col5","_col6","_col7","_col8","_col9"] + Filter Operator [FIL_91] (rows=12248093 width=732) + predicate:CASE WHEN (_col3 is not null) THEN (CASE WHEN (_col6) THEN (((_col1 / _col5) > (_col10 / _col3))) ELSE ((null > (_col10 / _col3))) END) ELSE (CASE WHEN (_col6) THEN (((_col1 / _col5) > null)) ELSE (null) END) END + Merge Join Operator [MERGEJOIN_287] (rows=24496186 width=732) + Conds:RS_88._col2=RS_350._col0(Inner),Output:["_col1","_col3","_col5","_col6","_col7","_col8","_col9","_col10"] <-Reducer 20 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_351] + SHUFFLE [RS_350] PartitionCols:_col0 - Select Operator [SEL_350] (rows=80000000 width=392) - Output:["_col0","_col1","_col2","_col3"] - Group By Operator [GBY_349] (rows=80000000 width=396) - Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["max(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3 - <-Reducer 19 [SIMPLE_EDGE] - SHUFFLE [RS_79] - PartitionCols:_col0, _col1, _col2, _col3 - Group By Operator [GBY_78] (rows=80000000 width=396) - Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["max(_col2)"],keys:_col6, _col7, _col8, _col4 - Merge Join Operator [MERGEJOIN_284] (rows=187573258 width=381) - Conds:RS_74._col1=RS_317._col0(Inner),Output:["_col2","_col4","_col6","_col7","_col8"] - <-Map 26 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_317] - PartitionCols:_col0 - Select Operator [SEL_316] (rows=80000000 width=284) - Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_315] (rows=80000000 width=284) - predicate:(c_customer_id is not null and c_customer_sk is not null) - TableScan [TS_68] (rows=80000000 width=284) - default@customer,customer,Tbl:COMPLETE,Col:COMPLETE,Output:["c_customer_sk","c_customer_id","c_first_name","c_last_name"] - <-Reducer 18 [SIMPLE_EDGE] - SHUFFLE [RS_74] - PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_283] (rows=187573258 width=105) - Conds:RS_348._col0=RS_294._col0(Inner),Output:["_col1","_col2","_col4"] - <-Map 21 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_294] - PartitionCols:_col0 - Select Operator [SEL_291] (rows=652 width=8) - Output:["_col0","_col1"] - Filter Operator [FIL_288] (rows=652 width=8) - predicate:((d_year = 2002) and (d_year) IN (2001, 2002) and d_date_sk is not null) - TableScan [TS_65] (rows=73049 width=8) - default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year"] - <-Map 17 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_348] - PartitionCols:_col0 - Select Operator [SEL_347] (rows=525327388 width=114) - Output:["_col0","_col1","_col2"] - Filter Operator [FIL_346] (rows=525327388 width=114) - predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_72_date_dim_d_date_sk_min) AND DynamicValue(RS_72_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_72_date_dim_d_date_sk_bloom_filter))) and ss_customer_sk is not null and ss_sold_date_sk is not null) - TableScan [TS_62] (rows=575995635 width=114) - default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_customer_sk","ss_net_paid"] - <-Reducer 22 [BROADCAST_EDGE] vectorized - BROADCAST [RS_345] - Group By Operator [GBY_344] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 21 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_306] - Group By Operator [GBY_302] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_295] (rows=652 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_291] + Group By Operator [GBY_349] (rows=80000000 width=392) + Output:["_col0","_col1","_col2","_col3"],aggregations:["max(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2 + <-Reducer 19 [SIMPLE_EDGE] + SHUFFLE [RS_79] + PartitionCols:_col0, _col1, _col2 + Group By Operator [GBY_78] (rows=80000000 width=392) + Output:["_col0","_col1","_col2","_col3"],aggregations:["max(_col2)"],keys:_col5, _col6, _col7 + Merge Join Operator [MERGEJOIN_284] (rows=187573258 width=377) + Conds:RS_74._col1=RS_317._col0(Inner),Output:["_col2","_col5","_col6","_col7"] + <-Map 26 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_317] + PartitionCols:_col0 + Select Operator [SEL_316] (rows=80000000 width=284) + Output:["_col0","_col1","_col2","_col3"] + Filter Operator [FIL_315] (rows=80000000 width=284) + predicate:(c_customer_id is not null and c_customer_sk is not null) + TableScan [TS_68] (rows=80000000 width=284) + default@customer,customer,Tbl:COMPLETE,Col:COMPLETE,Output:["c_customer_sk","c_customer_id","c_first_name","c_last_name"] + <-Reducer 18 [SIMPLE_EDGE] + SHUFFLE [RS_74] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_283] (rows=187573258 width=101) + Conds:RS_348._col0=RS_294._col0(Inner),Output:["_col1","_col2"] + <-Map 21 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_294] + PartitionCols:_col0 + Select Operator [SEL_291] (rows=652 width=4) + Output:["_col0"] + Filter Operator [FIL_288] (rows=652 width=8) + predicate:((d_year = 2002) and (d_year) IN (2001, 2002) and d_date_sk is not null) + TableScan [TS_65] (rows=73049 width=8) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year"] + <-Map 17 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_348] + PartitionCols:_col0 + Select Operator [SEL_347] (rows=525327388 width=114) + Output:["_col0","_col1","_col2"] + Filter Operator [FIL_346] (rows=525327388 width=114) + predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_72_date_dim_d_date_sk_min) AND DynamicValue(RS_72_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_72_date_dim_d_date_sk_bloom_filter))) and ss_customer_sk is not null and ss_sold_date_sk is not null) + TableScan [TS_62] (rows=575995635 width=114) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_customer_sk","ss_net_paid"] + <-Reducer 22 [BROADCAST_EDGE] vectorized + BROADCAST [RS_345] + Group By Operator [GBY_344] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 21 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_306] + Group By Operator [GBY_302] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_295] (rows=652 width=4) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_291] <-Reducer 6 [ONE_TO_ONE_EDGE] FORWARD [RS_88] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_286] (rows=20485011 width=436) - Conds:RS_85._col2=RS_343._col0(Inner),Output:["_col1","_col2","_col3","_col5"] + Merge Join Operator [MERGEJOIN_286] (rows=20485011 width=440) + Conds:RS_85._col2=RS_343._col0(Inner),Output:["_col1","_col2","_col3","_col5","_col6"] <-Reducer 16 [SIMPLE_EDGE] vectorized SHUFFLE [RS_343] PartitionCols:_col0 - Select Operator [SEL_342] (rows=17130654 width=212) - Output:["_col0","_col1"] + Select Operator [SEL_342] (rows=17130654 width=216) + Output:["_col0","_col1","_col2"] Filter Operator [FIL_341] (rows=17130654 width=212) - predicate:(_col4 > 0) + predicate:(_col3 > 0) Select Operator [SEL_340] (rows=51391963 width=212) - Output:["_col0","_col4"] - Group By Operator [GBY_339] (rows=51391963 width=396) - Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["max(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3 + Output:["_col0","_col3"] + Group By Operator [GBY_339] (rows=51391963 width=392) + Output:["_col0","_col1","_col2","_col3"],aggregations:["max(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2 <-Reducer 15 [SIMPLE_EDGE] SHUFFLE [RS_58] - PartitionCols:_col0, _col1, _col2, _col3 - Group By Operator [GBY_57] (rows=51391963 width=396) - Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["max(_col2)"],keys:_col6, _col7, _col8, _col4 - Merge Join Operator [MERGEJOIN_282] (rows=51391963 width=395) - Conds:RS_53._col1=RS_320._col0(Inner),Output:["_col2","_col4","_col6","_col7","_col8"] + PartitionCols:_col0, _col1, _col2 + Group By Operator [GBY_57] (rows=51391963 width=392) + Output:["_col0","_col1","_col2","_col3"],aggregations:["max(_col2)"],keys:_col5, _col6, _col7 + Merge Join Operator [MERGEJOIN_282] (rows=51391963 width=391) + Conds:RS_53._col1=RS_320._col0(Inner),Output:["_col2","_col5","_col6","_col7"] <-Map 26 [SIMPLE_EDGE] vectorized SHUFFLE [RS_320] PartitionCols:_col0 @@ -261,13 +259,13 @@ Stage-0 <-Reducer 14 [SIMPLE_EDGE] SHUFFLE [RS_53] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_281] (rows=51391963 width=119) - Conds:RS_338._col0=RS_300._col0(Inner),Output:["_col1","_col2","_col4"] + Merge Join Operator [MERGEJOIN_281] (rows=51391963 width=115) + Conds:RS_338._col0=RS_300._col0(Inner),Output:["_col1","_col2"] <-Map 21 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_300] PartitionCols:_col0 - Select Operator [SEL_293] (rows=652 width=8) - Output:["_col0","_col1"] + Select Operator [SEL_293] (rows=652 width=4) + Output:["_col0"] Filter Operator [FIL_290] (rows=652 width=8) predicate:((d_year = 2001) and (d_year) IN (2001, 2002) and d_date_sk is not null) Please refer to the previous TableScan [TS_65] @@ -302,18 +300,18 @@ Stage-0 Select Operator [SEL_332] (rows=26666666 width=212) Output:["_col0","_col1"] Filter Operator [FIL_331] (rows=26666666 width=212) - predicate:(_col4 > 0) + predicate:(_col3 > 0) Select Operator [SEL_330] (rows=80000000 width=212) - Output:["_col0","_col4"] - Group By Operator [GBY_329] (rows=80000000 width=396) - Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["max(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3 + Output:["_col0","_col3"] + Group By Operator [GBY_329] (rows=80000000 width=392) + Output:["_col0","_col1","_col2","_col3"],aggregations:["max(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2 <-Reducer 11 [SIMPLE_EDGE] SHUFFLE [RS_37] - PartitionCols:_col0, _col1, _col2, _col3 - Group By Operator [GBY_36] (rows=80000000 width=396) - Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["max(_col2)"],keys:_col6, _col7, _col8, _col4 - Merge Join Operator [MERGEJOIN_280] (rows=187573258 width=381) - Conds:RS_32._col1=RS_319._col0(Inner),Output:["_col2","_col4","_col6","_col7","_col8"] + PartitionCols:_col0, _col1, _col2 + Group By Operator [GBY_36] (rows=80000000 width=392) + Output:["_col0","_col1","_col2","_col3"],aggregations:["max(_col2)"],keys:_col5, _col6, _col7 + Merge Join Operator [MERGEJOIN_280] (rows=187573258 width=377) + Conds:RS_32._col1=RS_319._col0(Inner),Output:["_col2","_col5","_col6","_col7"] <-Map 26 [SIMPLE_EDGE] vectorized SHUFFLE [RS_319] PartitionCols:_col0 @@ -321,13 +319,13 @@ Stage-0 <-Reducer 10 [SIMPLE_EDGE] SHUFFLE [RS_32] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_279] (rows=187573258 width=105) - Conds:RS_328._col0=RS_298._col0(Inner),Output:["_col1","_col2","_col4"] + Merge Join Operator [MERGEJOIN_279] (rows=187573258 width=101) + Conds:RS_328._col0=RS_298._col0(Inner),Output:["_col1","_col2"] <-Map 21 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_298] PartitionCols:_col0 - Select Operator [SEL_292] (rows=652 width=8) - Output:["_col0","_col1"] + Select Operator [SEL_292] (rows=652 width=4) + Output:["_col0"] Filter Operator [FIL_289] (rows=652 width=8) predicate:((d_year = 2001) and (d_year) IN (2001, 2002) and d_date_sk is not null) Please refer to the previous TableScan [TS_65] @@ -356,15 +354,15 @@ Stage-0 PartitionCols:_col0 Select Operator [SEL_322] (rows=51391963 width=212) Output:["_col0","_col1"] - Group By Operator [GBY_321] (rows=51391963 width=396) - Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["max(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3 + Group By Operator [GBY_321] (rows=51391963 width=392) + Output:["_col0","_col1","_col2","_col3"],aggregations:["max(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2 <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_17] - PartitionCols:_col0, _col1, _col2, _col3 - Group By Operator [GBY_16] (rows=51391963 width=396) - Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["max(_col2)"],keys:_col6, _col7, _col8, _col4 - Merge Join Operator [MERGEJOIN_278] (rows=51391963 width=395) - Conds:RS_12._col1=RS_318._col0(Inner),Output:["_col2","_col4","_col6","_col7","_col8"] + PartitionCols:_col0, _col1, _col2 + Group By Operator [GBY_16] (rows=51391963 width=392) + Output:["_col0","_col1","_col2","_col3"],aggregations:["max(_col2)"],keys:_col5, _col6, _col7 + Merge Join Operator [MERGEJOIN_278] (rows=51391963 width=391) + Conds:RS_12._col1=RS_318._col0(Inner),Output:["_col2","_col5","_col6","_col7"] <-Map 26 [SIMPLE_EDGE] vectorized SHUFFLE [RS_318] PartitionCols:_col0 @@ -372,8 +370,8 @@ Stage-0 <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_12] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_277] (rows=51391963 width=119) - Conds:RS_314._col0=RS_296._col0(Inner),Output:["_col1","_col2","_col4"] + Merge Join Operator [MERGEJOIN_277] (rows=51391963 width=115) + Conds:RS_314._col0=RS_296._col0(Inner),Output:["_col1","_col2"] <-Map 21 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_296] PartitionCols:_col0 diff --git ql/src/test/results/clientpositive/perf/tez/query75.q.out ql/src/test/results/clientpositive/perf/tez/query75.q.out index 9968adef414..f4bd0469b4a 100644 --- ql/src/test/results/clientpositive/perf/tez/query75.q.out +++ ql/src/test/results/clientpositive/perf/tez/query75.q.out @@ -244,7 +244,7 @@ Stage-0 Select Operator [SEL_539] (rows=170474971 width=131) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] Merge Join Operator [MERGEJOIN_538] (rows=170474971 width=234) - Conds:RS_103._col1, _col2=RS_625._col0, _col1(Left Outer),Output:["_col3","_col4","_col8","_col9","_col10","_col12","_col15","_col16"] + Conds:RS_103._col1, _col2=RS_625._col0, _col1(Left Outer),Output:["_col3","_col4","_col7","_col8","_col9","_col10","_col13","_col14"] <-Map 44 [SIMPLE_EDGE] vectorized SHUFFLE [RS_625] PartitionCols:_col0, _col1 @@ -258,12 +258,12 @@ Stage-0 SHUFFLE [RS_103] PartitionCols:_col1, _col2 Merge Join Operator [MERGEJOIN_510] (rows=96821196 width=138) - Conds:RS_100._col1=RS_599._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col8","_col9","_col10","_col12"] + Conds:RS_100._col1=RS_599._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col7","_col8","_col9","_col10"] <-Map 37 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_599] PartitionCols:_col0 - Select Operator [SEL_592] (rows=45745 width=109) - Output:["_col0","_col1","_col2","_col3","_col5"] + Select Operator [SEL_592] (rows=45745 width=19) + Output:["_col0","_col1","_col2","_col3","_col4"] Filter Operator [FIL_591] (rows=45745 width=109) predicate:((i_category = 'Sports') and i_brand_id is not null and i_category_id is not null and i_class_id is not null and i_item_sk is not null and i_manufact_id is not null) TableScan [TS_6] (rows=462000 width=109) @@ -276,7 +276,7 @@ Stage-0 <-Map 11 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_571] PartitionCols:_col0 - Select Operator [SEL_562] (rows=652 width=8) + Select Operator [SEL_562] (rows=652 width=4) Output:["_col0"] Filter Operator [FIL_558] (rows=652 width=8) predicate:((d_year = 2002) and d_date_sk is not null) @@ -321,7 +321,7 @@ Stage-0 Select Operator [SEL_548] (rows=450703984 width=131) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] Merge Join Operator [MERGEJOIN_547] (rows=450703984 width=204) - Conds:RS_125._col1, _col2=RS_649._col0, _col1(Left Outer),Output:["_col3","_col4","_col8","_col9","_col10","_col12","_col15","_col16"] + Conds:RS_125._col1, _col2=RS_649._col0, _col1(Left Outer),Output:["_col3","_col4","_col7","_col8","_col9","_col10","_col13","_col14"] <-Map 46 [SIMPLE_EDGE] vectorized SHUFFLE [RS_649] PartitionCols:_col0, _col1 @@ -335,7 +335,7 @@ Stage-0 SHUFFLE [RS_125] PartitionCols:_col1, _col2 Merge Join Operator [MERGEJOIN_513] (rows=187186493 width=124) - Conds:RS_122._col1=RS_601._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col8","_col9","_col10","_col12"] + Conds:RS_122._col1=RS_601._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col7","_col8","_col9","_col10"] <-Map 37 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_601] PartitionCols:_col0 @@ -348,7 +348,7 @@ Stage-0 <-Map 11 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_573] PartitionCols:_col0 - Select Operator [SEL_563] (rows=652 width=8) + Select Operator [SEL_563] (rows=652 width=4) Output:["_col0"] Filter Operator [FIL_559] (rows=652 width=8) predicate:((d_year = 2002) and d_date_sk is not null) @@ -392,7 +392,7 @@ Stage-0 Select Operator [SEL_553] (rows=115177968 width=131) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] Merge Join Operator [MERGEJOIN_552] (rows=115177968 width=220) - Conds:RS_154._col1, _col2=RS_660._col0, _col1(Left Outer),Output:["_col3","_col4","_col8","_col9","_col10","_col12","_col15","_col16"] + Conds:RS_154._col1, _col2=RS_660._col0, _col1(Left Outer),Output:["_col3","_col4","_col7","_col8","_col9","_col10","_col13","_col14"] <-Map 48 [SIMPLE_EDGE] vectorized SHUFFLE [RS_660] PartitionCols:_col0, _col1 @@ -406,7 +406,7 @@ Stage-0 SHUFFLE [RS_154] PartitionCols:_col1, _col2 Merge Join Operator [MERGEJOIN_516] (rows=48990732 width=139) - Conds:RS_151._col1=RS_603._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col8","_col9","_col10","_col12"] + Conds:RS_151._col1=RS_603._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col7","_col8","_col9","_col10"] <-Map 37 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_603] PartitionCols:_col0 @@ -419,7 +419,7 @@ Stage-0 <-Map 11 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_575] PartitionCols:_col0 - Select Operator [SEL_564] (rows=652 width=8) + Select Operator [SEL_564] (rows=652 width=4) Output:["_col0"] Filter Operator [FIL_560] (rows=652 width=8) predicate:((d_year = 2002) and d_date_sk is not null) @@ -471,7 +471,7 @@ Stage-0 Select Operator [SEL_534] (rows=115177968 width=131) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] Merge Join Operator [MERGEJOIN_533] (rows=115177968 width=220) - Conds:RS_69._col1, _col2=RS_659._col0, _col1(Left Outer),Output:["_col3","_col4","_col8","_col9","_col10","_col12","_col15","_col16"] + Conds:RS_69._col1, _col2=RS_659._col0, _col1(Left Outer),Output:["_col3","_col4","_col7","_col8","_col9","_col10","_col13","_col14"] <-Map 48 [SIMPLE_EDGE] vectorized SHUFFLE [RS_659] PartitionCols:_col0, _col1 @@ -480,7 +480,7 @@ Stage-0 SHUFFLE [RS_69] PartitionCols:_col1, _col2 Merge Join Operator [MERGEJOIN_507] (rows=48990732 width=139) - Conds:RS_66._col1=RS_597._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col8","_col9","_col10","_col12"] + Conds:RS_66._col1=RS_597._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col7","_col8","_col9","_col10"] <-Map 37 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_597] PartitionCols:_col0 @@ -493,7 +493,7 @@ Stage-0 <-Map 11 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_569] PartitionCols:_col0 - Select Operator [SEL_561] (rows=652 width=8) + Select Operator [SEL_561] (rows=652 width=4) Output:["_col0"] Filter Operator [FIL_557] (rows=652 width=8) predicate:((d_year = 2001) and d_date_sk is not null) @@ -545,7 +545,7 @@ Stage-0 Select Operator [SEL_529] (rows=450703984 width=131) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] Merge Join Operator [MERGEJOIN_528] (rows=450703984 width=204) - Conds:RS_40._col1, _col2=RS_648._col0, _col1(Left Outer),Output:["_col3","_col4","_col8","_col9","_col10","_col12","_col15","_col16"] + Conds:RS_40._col1, _col2=RS_648._col0, _col1(Left Outer),Output:["_col3","_col4","_col7","_col8","_col9","_col10","_col13","_col14"] <-Map 46 [SIMPLE_EDGE] vectorized SHUFFLE [RS_648] PartitionCols:_col0, _col1 @@ -554,7 +554,7 @@ Stage-0 SHUFFLE [RS_40] PartitionCols:_col1, _col2 Merge Join Operator [MERGEJOIN_504] (rows=187186493 width=124) - Conds:RS_37._col1=RS_595._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col8","_col9","_col10","_col12"] + Conds:RS_37._col1=RS_595._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col7","_col8","_col9","_col10"] <-Map 37 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_595] PartitionCols:_col0 @@ -607,7 +607,7 @@ Stage-0 Select Operator [SEL_520] (rows=170474971 width=131) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] Merge Join Operator [MERGEJOIN_519] (rows=170474971 width=234) - Conds:RS_18._col1, _col2=RS_624._col0, _col1(Left Outer),Output:["_col3","_col4","_col8","_col9","_col10","_col12","_col15","_col16"] + Conds:RS_18._col1, _col2=RS_624._col0, _col1(Left Outer),Output:["_col3","_col4","_col7","_col8","_col9","_col10","_col13","_col14"] <-Map 44 [SIMPLE_EDGE] vectorized SHUFFLE [RS_624] PartitionCols:_col0, _col1 @@ -616,7 +616,7 @@ Stage-0 SHUFFLE [RS_18] PartitionCols:_col1, _col2 Merge Join Operator [MERGEJOIN_501] (rows=96821196 width=138) - Conds:RS_15._col1=RS_593._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col8","_col9","_col10","_col12"] + Conds:RS_15._col1=RS_593._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col7","_col8","_col9","_col10"] <-Map 37 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_593] PartitionCols:_col0 diff --git ql/src/test/results/clientpositive/perf/tez/query76.q.out ql/src/test/results/clientpositive/perf/tez/query76.q.out index add01414bb9..2e426a21b19 100644 --- ql/src/test/results/clientpositive/perf/tez/query76.q.out +++ ql/src/test/results/clientpositive/perf/tez/query76.q.out @@ -93,7 +93,7 @@ Stage-0 Select Operator [SEL_163] (rows=1433911 width=399) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] Merge Join Operator [MERGEJOIN_162] (rows=1433911 width=209) - Conds:RS_45._col0=RS_195._col0(Inner),Output:["_col3","_col5","_col7","_col8"] + Conds:RS_45._col0=RS_195._col0(Inner),Output:["_col2","_col4","_col6","_col7"] <-Map 16 [SIMPLE_EDGE] vectorized SHUFFLE [RS_195] PartitionCols:_col0 @@ -107,7 +107,7 @@ Stage-0 SHUFFLE [RS_45] PartitionCols:_col0 Merge Join Operator [MERGEJOIN_148] (rows=1433911 width=205) - Conds:RS_192._col2=RS_172._col0(Inner),Output:["_col0","_col3","_col5"] + Conds:RS_192._col1=RS_172._col0(Inner),Output:["_col0","_col2","_col4"] <-Map 1 [SIMPLE_EDGE] vectorized SHUFFLE [RS_172] PartitionCols:_col0 @@ -119,9 +119,9 @@ Stage-0 default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_category"] <-Map 15 [SIMPLE_EDGE] vectorized SHUFFLE [RS_192] - PartitionCols:_col2 + PartitionCols:_col1 Select Operator [SEL_191] (rows=1433911 width=119) - Output:["_col0","_col2","_col3"] + Output:["_col0","_col1","_col2"] Filter Operator [FIL_190] (rows=1433911 width=123) predicate:(cs_item_sk is not null and cs_sold_date_sk is not null and cs_warehouse_sk is null) TableScan [TS_33] (rows=287989836 width=123) @@ -136,7 +136,7 @@ Stage-0 Select Operator [SEL_151] (rows=24749363 width=387) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] Merge Join Operator [MERGEJOIN_150] (rows=24749363 width=204) - Conds:RS_12._col2=RS_178._col0(Inner),Output:["_col1","_col5","_col7","_col8"] + Conds:RS_12._col2=RS_178._col0(Inner),Output:["_col1","_col4","_col6","_col7"] <-Map 12 [SIMPLE_EDGE] vectorized SHUFFLE [RS_178] PartitionCols:_col0 @@ -150,7 +150,7 @@ Stage-0 SHUFFLE [RS_12] PartitionCols:_col2 Merge Join Operator [MERGEJOIN_144] (rows=24749363 width=200) - Conds:RS_170._col0=RS_175._col1(Inner),Output:["_col1","_col2","_col5"] + Conds:RS_170._col0=RS_175._col1(Inner),Output:["_col1","_col2","_col4"] <-Map 1 [SIMPLE_EDGE] vectorized SHUFFLE [RS_170] PartitionCols:_col0 @@ -159,7 +159,7 @@ Stage-0 SHUFFLE [RS_175] PartitionCols:_col1 Select Operator [SEL_174] (rows=24749363 width=114) - Output:["_col0","_col1","_col3"] + Output:["_col0","_col1","_col2"] Filter Operator [FIL_173] (rows=24749363 width=118) predicate:(ss_addr_sk is null and ss_item_sk is not null and ss_sold_date_sk is not null) TableScan [TS_3] (rows=575995635 width=118) @@ -174,7 +174,7 @@ Stage-0 Select Operator [SEL_157] (rows=35728 width=394) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] Merge Join Operator [MERGEJOIN_156] (rows=35728 width=209) - Conds:RS_28._col0=RS_189._col0(Inner),Output:["_col3","_col5","_col7","_col8"] + Conds:RS_28._col0=RS_189._col0(Inner),Output:["_col2","_col4","_col6","_col7"] <-Map 14 [SIMPLE_EDGE] vectorized SHUFFLE [RS_189] PartitionCols:_col0 @@ -188,7 +188,7 @@ Stage-0 SHUFFLE [RS_28] PartitionCols:_col0 Merge Join Operator [MERGEJOIN_146] (rows=35728 width=205) - Conds:RS_186._col1=RS_171._col0(Inner),Output:["_col0","_col3","_col5"] + Conds:RS_186._col1=RS_171._col0(Inner),Output:["_col0","_col2","_col4"] <-Map 1 [SIMPLE_EDGE] vectorized SHUFFLE [RS_171] PartitionCols:_col0 @@ -197,7 +197,7 @@ Stage-0 SHUFFLE [RS_186] PartitionCols:_col1 Select Operator [SEL_185] (rows=35728 width=119) - Output:["_col0","_col1","_col3"] + Output:["_col0","_col1","_col2"] Filter Operator [FIL_184] (rows=35728 width=123) predicate:(ws_item_sk is not null and ws_sold_date_sk is not null and ws_web_page_sk is null) TableScan [TS_16] (rows=144002668 width=123) diff --git ql/src/test/results/clientpositive/perf/tez/query77.q.out ql/src/test/results/clientpositive/perf/tez/query77.q.out index ac1b0e4bad6..528c19cf613 100644 --- ql/src/test/results/clientpositive/perf/tez/query77.q.out +++ ql/src/test/results/clientpositive/perf/tez/query77.q.out @@ -304,7 +304,7 @@ Stage-0 <-Map 9 [SIMPLE_EDGE] vectorized SHUFFLE [RS_334] PartitionCols:_col0 - Select Operator [SEL_330] (rows=8116 width=98) + Select Operator [SEL_330] (rows=8116 width=4) Output:["_col0"] Filter Operator [FIL_329] (rows=8116 width=98) predicate:(CAST( d_date AS TIMESTAMP) BETWEEN TIMESTAMP'1998-08-04 00:00:00' AND TIMESTAMP'1998-09-03 00:00:00' and d_date_sk is not null) @@ -373,9 +373,9 @@ Stage-0 SHUFFLE [RS_94] PartitionCols:_col0 Group By Operator [GBY_93] (rows=345 width=228) - Output:["_col0","_col1","_col2"],aggregations:["sum(_col2)","sum(_col3)"],keys:_col6 + Output:["_col0","_col1","_col2"],aggregations:["sum(_col2)","sum(_col3)"],keys:_col5 Merge Join Operator [MERGEJOIN_305] (rows=15991254 width=227) - Conds:RS_89._col1=RS_387._col0(Inner),Output:["_col2","_col3","_col6"] + Conds:RS_89._col1=RS_387._col0(Inner),Output:["_col2","_col3","_col5"] <-Map 33 [SIMPLE_EDGE] vectorized SHUFFLE [RS_387] PartitionCols:_col0 @@ -423,9 +423,9 @@ Stage-0 SHUFFLE [RS_114] PartitionCols:_col0 Group By Operator [GBY_113] (rows=23 width=228) - Output:["_col0","_col1","_col2"],aggregations:["sum(_col2)","sum(_col3)"],keys:_col6 + Output:["_col0","_col1","_col2"],aggregations:["sum(_col2)","sum(_col3)"],keys:_col5 Merge Join Operator [MERGEJOIN_307] (rows=1458758 width=137) - Conds:RS_109._col1=RS_388._col0(Inner),Output:["_col2","_col3","_col6"] + Conds:RS_109._col1=RS_388._col0(Inner),Output:["_col2","_col3","_col5"] <-Map 33 [SIMPLE_EDGE] vectorized SHUFFLE [RS_388] PartitionCols:_col0 @@ -468,9 +468,9 @@ Stage-0 SHUFFLE [RS_37] PartitionCols:_col0 Group By Operator [GBY_36] (rows=40 width=228) - Output:["_col0","_col1","_col2"],aggregations:["sum(_col2)","sum(_col3)"],keys:_col6 + Output:["_col0","_col1","_col2"],aggregations:["sum(_col2)","sum(_col3)"],keys:_col5 Merge Join Operator [MERGEJOIN_301] (rows=5959021 width=157) - Conds:RS_32._col1=RS_354._col0(Inner),Output:["_col2","_col3","_col6"] + Conds:RS_32._col1=RS_354._col0(Inner),Output:["_col2","_col3","_col5"] <-Map 28 [SIMPLE_EDGE] vectorized SHUFFLE [RS_354] PartitionCols:_col0 @@ -507,9 +507,9 @@ Stage-0 SHUFFLE [RS_17] PartitionCols:_col0 Group By Operator [GBY_16] (rows=320 width=228) - Output:["_col0","_col1","_col2"],aggregations:["sum(_col2)","sum(_col3)"],keys:_col6 + Output:["_col0","_col1","_col2"],aggregations:["sum(_col2)","sum(_col3)"],keys:_col5 Merge Join Operator [MERGEJOIN_299] (rows=58365993 width=137) - Conds:RS_12._col1=RS_353._col0(Inner),Output:["_col2","_col3","_col6"] + Conds:RS_12._col1=RS_353._col0(Inner),Output:["_col2","_col3","_col5"] <-Map 28 [SIMPLE_EDGE] vectorized SHUFFLE [RS_353] PartitionCols:_col0 diff --git ql/src/test/results/clientpositive/perf/tez/query78.q.out ql/src/test/results/clientpositive/perf/tez/query78.q.out index 853759ff152..3d938e1c8e7 100644 --- ql/src/test/results/clientpositive/perf/tez/query78.q.out +++ ql/src/test/results/clientpositive/perf/tez/query78.q.out @@ -179,13 +179,13 @@ Stage-0 SHUFFLE [RS_65] PartitionCols:_col0, _col1 Group By Operator [GBY_64] (rows=50796051 width=239) - Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["sum(_col6)","sum(_col7)","sum(_col8)"],keys:_col3, _col4 + Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["sum(_col4)","sum(_col5)","sum(_col6)"],keys:_col2, _col3 Merge Join Operator [MERGEJOIN_189] (rows=50796051 width=233) - Conds:RS_198._col0=RS_61._col0(Inner),Output:["_col3","_col4","_col6","_col7","_col8"] + Conds:RS_198._col0=RS_61._col0(Inner),Output:["_col2","_col3","_col4","_col5","_col6"] <-Map 1 [SIMPLE_EDGE] vectorized SHUFFLE [RS_198] PartitionCols:_col0 - Select Operator [SEL_193] (rows=652 width=8) + Select Operator [SEL_193] (rows=652 width=4) Output:["_col0"] Filter Operator [FIL_192] (rows=652 width=8) predicate:((d_year = 2000) and d_date_sk is not null) @@ -194,8 +194,8 @@ Stage-0 <-Reducer 21 [SIMPLE_EDGE] SHUFFLE [RS_61] PartitionCols:_col0 - Select Operator [SEL_59] (rows=143274863 width=240) - Output:["_col0","_col1","_col2","_col4","_col5","_col6"] + Select Operator [SEL_59] (rows=143274863 width=239) + Output:["_col0","_col1","_col2","_col3","_col4","_col5"] Filter Operator [FIL_58] (rows=143274863 width=240) predicate:_col8 is null Merge Join Operator [MERGEJOIN_188] (rows=234359952 width=240) @@ -245,9 +245,9 @@ Stage-0 SHUFFLE [RS_18] PartitionCols:_col0, _col1 Group By Operator [GBY_17] (rows=114214965 width=239) - Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["sum(_col6)","sum(_col7)","sum(_col8)"],keys:_col4, _col3 + Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["sum(_col4)","sum(_col5)","sum(_col6)"],keys:_col3, _col2 Merge Join Operator [MERGEJOIN_185] (rows=114214965 width=217) - Conds:RS_194._col0=RS_14._col0(Inner),Output:["_col3","_col4","_col6","_col7","_col8"] + Conds:RS_194._col0=RS_14._col0(Inner),Output:["_col2","_col3","_col4","_col5","_col6"] <-Map 1 [SIMPLE_EDGE] vectorized SHUFFLE [RS_194] PartitionCols:_col0 @@ -255,8 +255,8 @@ Stage-0 <-Reducer 15 [SIMPLE_EDGE] SHUFFLE [RS_14] PartitionCols:_col0 - Select Operator [SEL_12] (rows=319876350 width=235) - Output:["_col0","_col1","_col2","_col4","_col5","_col6"] + Select Operator [SEL_12] (rows=319876350 width=233) + Output:["_col0","_col1","_col2","_col3","_col4","_col5"] Filter Operator [FIL_11] (rows=319876350 width=235) predicate:_col8 is null Merge Join Operator [MERGEJOIN_184] (rows=883006376 width=235) @@ -299,9 +299,9 @@ Stage-0 SHUFFLE [RS_39] PartitionCols:_col0, _col1 Group By Operator [GBY_38] (rows=40539971 width=239) - Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["sum(_col6)","sum(_col7)","sum(_col8)"],keys:_col4, _col3 + Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["sum(_col4)","sum(_col5)","sum(_col6)"],keys:_col3, _col2 Merge Join Operator [MERGEJOIN_187] (rows=40539971 width=235) - Conds:RS_196._col0=RS_35._col0(Inner),Output:["_col3","_col4","_col6","_col7","_col8"] + Conds:RS_196._col0=RS_35._col0(Inner),Output:["_col2","_col3","_col4","_col5","_col6"] <-Map 1 [SIMPLE_EDGE] vectorized SHUFFLE [RS_196] PartitionCols:_col0 @@ -309,8 +309,8 @@ Stage-0 <-Reducer 18 [SIMPLE_EDGE] SHUFFLE [RS_35] PartitionCols:_col0 - Select Operator [SEL_33] (rows=113538342 width=242) - Output:["_col0","_col1","_col2","_col4","_col5","_col6"] + Select Operator [SEL_33] (rows=113538342 width=239) + Output:["_col0","_col1","_col2","_col3","_col4","_col5"] Filter Operator [FIL_32] (rows=113538342 width=242) predicate:_col8 is null Merge Join Operator [MERGEJOIN_186] (rows=254679677 width=242) diff --git ql/src/test/results/clientpositive/perf/tez/query79.q.out ql/src/test/results/clientpositive/perf/tez/query79.q.out index f1538371a99..877ff7bc77e 100644 --- ql/src/test/results/clientpositive/perf/tez/query79.q.out +++ ql/src/test/results/clientpositive/perf/tez/query79.q.out @@ -80,9 +80,9 @@ Stage-0 <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_33] Select Operator [SEL_32] (rows=43530621 width=776) - Output:["_col0","_col1","_col3","_col4","_col5","_col6"] - Merge Join Operator [MERGEJOIN_100] (rows=43530621 width=501) - Conds:RS_103._col0=RS_128._col1(Inner),Output:["_col1","_col2","_col3","_col5","_col6","_col7"] + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"] + Merge Join Operator [MERGEJOIN_100] (rows=43530621 width=685) + Conds:RS_103._col0=RS_128._col1(Inner),Output:["_col1","_col2","_col3","_col5","_col6","_col7","_col8"] <-Map 1 [SIMPLE_EDGE] vectorized SHUFFLE [RS_103] PartitionCols:_col0 @@ -95,21 +95,21 @@ Stage-0 <-Reducer 8 [SIMPLE_EDGE] vectorized SHUFFLE [RS_128] PartitionCols:_col1 - Select Operator [SEL_127] (rows=43530621 width=323) - Output:["_col0","_col1","_col2","_col3","_col4"] + Select Operator [SEL_127] (rows=43530621 width=507) + Output:["_col0","_col1","_col2","_col3","_col4","_col5"] Group By Operator [GBY_126] (rows=43530621 width=325) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3 <-Reducer 7 [SIMPLE_EDGE] SHUFFLE [RS_26] PartitionCols:_col0, _col1, _col2, _col3 Group By Operator [GBY_25] (rows=43530621 width=325) - Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(_col6)","sum(_col7)"],keys:_col1, _col3, _col5, _col13 + Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(_col6)","sum(_col7)"],keys:_col1, _col3, _col5, _col10 Merge Join Operator [MERGEJOIN_99] (rows=43530621 width=214) - Conds:RS_21._col2=RS_114._col0(Inner),Output:["_col1","_col3","_col5","_col6","_col7","_col13"] + Conds:RS_21._col2=RS_114._col0(Inner),Output:["_col1","_col3","_col5","_col6","_col7","_col10"] <-Map 12 [SIMPLE_EDGE] vectorized SHUFFLE [RS_114] PartitionCols:_col0 - Select Operator [SEL_113] (rows=3055 width=12) + Select Operator [SEL_113] (rows=3055 width=4) Output:["_col0"] Filter Operator [FIL_112] (rows=3055 width=12) predicate:(((hd_dep_count = 8) or (hd_vehicle_count > 0)) and hd_demo_sk is not null) @@ -119,12 +119,12 @@ Stage-0 SHUFFLE [RS_21] PartitionCols:_col2 Merge Join Operator [MERGEJOIN_98] (rows=102592623 width=283) - Conds:RS_18._col4=RS_125._col0(Inner),Output:["_col1","_col2","_col3","_col5","_col6","_col7","_col13"] + Conds:RS_18._col4=RS_125._col0(Inner),Output:["_col1","_col2","_col3","_col5","_col6","_col7","_col10"] <-Map 11 [SIMPLE_EDGE] vectorized SHUFFLE [RS_125] PartitionCols:_col0 - Select Operator [SEL_124] (rows=1704 width=100) - Output:["_col0","_col2"] + Select Operator [SEL_124] (rows=1704 width=97) + Output:["_col0","_col1"] Filter Operator [FIL_123] (rows=1704 width=100) predicate:(s_number_employees BETWEEN 200 AND 295 and s_store_sk is not null) TableScan [TS_9] (rows=1704 width=100) @@ -137,7 +137,7 @@ Stage-0 <-Map 9 [SIMPLE_EDGE] vectorized SHUFFLE [RS_106] PartitionCols:_col0 - Select Operator [SEL_105] (rows=391 width=12) + Select Operator [SEL_105] (rows=391 width=4) Output:["_col0"] Filter Operator [FIL_104] (rows=391 width=12) predicate:((d_dow = 1) and (d_year) IN (1998, 1999, 2000) and d_date_sk is not null) diff --git ql/src/test/results/clientpositive/perf/tez/query8.q.out ql/src/test/results/clientpositive/perf/tez/query8.q.out index 8c245509ca7..5d6fad21e55 100644 --- ql/src/test/results/clientpositive/perf/tez/query8.q.out +++ ql/src/test/results/clientpositive/perf/tez/query8.q.out @@ -259,20 +259,20 @@ Stage-0 SHUFFLE [RS_57] PartitionCols:_col0 Group By Operator [GBY_56] (rows=1 width=200) - Output:["_col0","_col1"],aggregations:["sum(_col2)"],keys:_col8 + Output:["_col0","_col1"],aggregations:["sum(_col2)"],keys:_col6 Top N Key Operator [TNK_84] (rows=1 width=200) - keys:_col8,sort order:+,top n:100 + keys:_col6,sort order:+,top n:100 Merge Join Operator [MERGEJOIN_118] (rows=1 width=200) - Conds:RS_52._col1=RS_53._col1(Inner),Output:["_col2","_col8"] + Conds:RS_52._col1=RS_53._col1(Inner),Output:["_col2","_col6"] <-Reducer 12 [SIMPLE_EDGE] SHUFFLE [RS_53] PartitionCols:_col1 Merge Join Operator [MERGEJOIN_117] (rows=1 width=92) - Conds:RS_138.substr(_col0, 1, 2)=RS_141.substr(_col2, 1, 2)(Inner),Output:["_col1","_col2"] + Conds:RS_138._col0=RS_141._col2(Inner),Output:["_col1","_col2"] <-Map 19 [SIMPLE_EDGE] vectorized SHUFFLE [RS_141] - PartitionCols:substr(_col2, 1, 2) - Select Operator [SEL_140] (rows=1704 width=181) + PartitionCols:_col2 + Select Operator [SEL_140] (rows=1704 width=276) Output:["_col0","_col1","_col2"] Filter Operator [FIL_139] (rows=1704 width=181) predicate:(s_store_sk is not null and substr(s_zip, 1, 2) is not null) @@ -280,7 +280,7 @@ Stage-0 default@store,store,Tbl:COMPLETE,Col:COMPLETE,Output:["s_store_sk","s_store_name","s_zip"] <-Reducer 11 [SIMPLE_EDGE] vectorized SHUFFLE [RS_138] - PartitionCols:substr(_col0, 1, 2) + PartitionCols:_col0 Select Operator [SEL_137] (rows=1 width=184) Output:["_col0"] Filter Operator [FIL_136] (rows=1 width=192) @@ -325,7 +325,7 @@ Stage-0 <-Map 18 [SIMPLE_EDGE] vectorized SHUFFLE [RS_164] PartitionCols:_col0 - Select Operator [SEL_163] (rows=26666667 width=89) + Select Operator [SEL_163] (rows=26666667 width=4) Output:["_col0"] Filter Operator [FIL_162] (rows=26666667 width=89) predicate:((c_preferred_cust_flag = 'Y') and c_current_addr_sk is not null) @@ -357,7 +357,7 @@ Stage-0 <-Map 6 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_129] PartitionCols:_col0 - Select Operator [SEL_128] (rows=130 width=12) + Select Operator [SEL_128] (rows=130 width=4) Output:["_col0"] Filter Operator [FIL_127] (rows=130 width=12) predicate:((d_qoy = 1) and (d_year = 2002) and d_date_sk is not null) diff --git ql/src/test/results/clientpositive/perf/tez/query80.q.out ql/src/test/results/clientpositive/perf/tez/query80.q.out index ff26befbd41..223e61aa248 100644 --- ql/src/test/results/clientpositive/perf/tez/query80.q.out +++ ql/src/test/results/clientpositive/perf/tez/query80.q.out @@ -286,7 +286,7 @@ Stage-0 Select Operator [SEL_72] (rows=8592843 width=305) Output:["_col0","_col1","_col2","_col3"] Merge Join Operator [MERGEJOIN_369] (rows=8592843 width=305) - Conds:RS_69._col1=RS_475._col0(Inner),Output:["_col5","_col6","_col9","_col10","_col18"] + Conds:RS_69._col1=RS_475._col0(Inner),Output:["_col5","_col6","_col9","_col10","_col15"] <-Map 38 [SIMPLE_EDGE] vectorized SHUFFLE [RS_475] PartitionCols:_col0 @@ -304,7 +304,7 @@ Stage-0 <-Map 30 [SIMPLE_EDGE] vectorized SHUFFLE [RS_429] PartitionCols:_col0 - Select Operator [SEL_426] (rows=1150 width=89) + Select Operator [SEL_426] (rows=1150 width=4) Output:["_col0"] Filter Operator [FIL_425] (rows=1150 width=89) predicate:((p_channel_tv = 'N') and p_promo_sk is not null) @@ -318,7 +318,7 @@ Stage-0 <-Map 26 [SIMPLE_EDGE] vectorized SHUFFLE [RS_413] PartitionCols:_col0 - Select Operator [SEL_410] (rows=154000 width=115) + Select Operator [SEL_410] (rows=154000 width=4) Output:["_col0"] Filter Operator [FIL_409] (rows=154000 width=115) predicate:((i_current_price > 50) and i_item_sk is not null) @@ -332,7 +332,7 @@ Stage-0 <-Map 12 [SIMPLE_EDGE] vectorized SHUFFLE [RS_397] PartitionCols:_col0 - Select Operator [SEL_394] (rows=8116 width=98) + Select Operator [SEL_394] (rows=8116 width=4) Output:["_col0"] Filter Operator [FIL_393] (rows=8116 width=98) predicate:(CAST( d_date AS TIMESTAMP) BETWEEN TIMESTAMP'1998-08-04 00:00:00' AND TIMESTAMP'1998-09-03 00:00:00' and d_date_sk is not null) @@ -413,7 +413,7 @@ Stage-0 Select Operator [SEL_112] (rows=4714659 width=323) Output:["_col0","_col1","_col2","_col3"] Merge Join Operator [MERGEJOIN_374] (rows=4714659 width=323) - Conds:RS_109._col2=RS_495._col0(Inner),Output:["_col5","_col6","_col9","_col10","_col18"] + Conds:RS_109._col2=RS_495._col0(Inner),Output:["_col5","_col6","_col9","_col10","_col15"] <-Map 42 [SIMPLE_EDGE] vectorized SHUFFLE [RS_495] PartitionCols:_col0 @@ -525,7 +525,7 @@ Stage-0 Select Operator [SEL_33] (rows=15038783 width=100) Output:["_col0","_col1","_col2","_col3"] Merge Join Operator [MERGEJOIN_364] (rows=15038783 width=100) - Conds:RS_30._col2=RS_449._col0(Inner),Output:["_col5","_col6","_col9","_col10","_col18"] + Conds:RS_30._col2=RS_449._col0(Inner),Output:["_col5","_col6","_col9","_col10","_col15"] <-Map 34 [SIMPLE_EDGE] vectorized SHUFFLE [RS_449] PartitionCols:_col0 diff --git ql/src/test/results/clientpositive/perf/tez/query81.q.out ql/src/test/results/clientpositive/perf/tez/query81.q.out index b08ed9e24ba..94398cf891b 100644 --- ql/src/test/results/clientpositive/perf/tez/query81.q.out +++ ql/src/test/results/clientpositive/perf/tez/query81.q.out @@ -99,7 +99,7 @@ Stage-0 Select Operator [SEL_62] (rows=1577696 width=1418) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14"] Merge Join Operator [MERGEJOIN_178] (rows=1577696 width=1418) - Conds:RS_59._col0=RS_60._col0(Inner),Output:["_col1","_col3","_col4","_col5","_col7","_col8","_col9","_col10","_col11","_col12","_col14","_col15","_col16","_col17","_col20"] + Conds:RS_59._col0=RS_60._col0(Inner),Output:["_col1","_col3","_col4","_col5","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col19"] <-Reducer 10 [SIMPLE_EDGE] SHUFFLE [RS_60] PartitionCols:_col0 @@ -124,9 +124,9 @@ Stage-0 SHUFFLE [RS_43] PartitionCols:_col0 Group By Operator [GBY_42] (rows=8749496 width=201) - Output:["_col0","_col1","_col2"],aggregations:["sum(_col3)"],keys:_col7, _col1 + Output:["_col0","_col1","_col2"],aggregations:["sum(_col3)"],keys:_col6, _col1 Merge Join Operator [MERGEJOIN_176] (rows=8749496 width=194) - Conds:RS_38._col2=RS_198._col0(Inner),Output:["_col1","_col3","_col7"] + Conds:RS_38._col2=RS_198._col0(Inner),Output:["_col1","_col3","_col6"] <-Map 15 [SIMPLE_EDGE] vectorized SHUFFLE [RS_198] PartitionCols:_col0 @@ -144,7 +144,7 @@ Stage-0 <-Map 14 [SIMPLE_EDGE] vectorized SHUFFLE [RS_194] PartitionCols:_col0 - Select Operator [SEL_192] (rows=652 width=8) + Select Operator [SEL_192] (rows=652 width=4) Output:["_col0"] Filter Operator [FIL_191] (rows=652 width=8) predicate:((d_year = 1998) and d_date_sk is not null) @@ -170,9 +170,9 @@ Stage-0 SHUFFLE [RS_23] PartitionCols:_col0, _col1 Group By Operator [GBY_22] (rows=8574602 width=201) - Output:["_col0","_col1","_col2"],aggregations:["sum(_col3)"],keys:_col7, _col1 + Output:["_col0","_col1","_col2"],aggregations:["sum(_col3)"],keys:_col6, _col1 Merge Join Operator [MERGEJOIN_174] (rows=8574602 width=194) - Conds:RS_18._col2=RS_197._col0(Inner),Output:["_col1","_col3","_col7"] + Conds:RS_18._col2=RS_197._col0(Inner),Output:["_col1","_col3","_col6"] <-Map 15 [SIMPLE_EDGE] vectorized SHUFFLE [RS_197] PartitionCols:_col0 @@ -198,7 +198,7 @@ Stage-0 SHUFFLE [RS_59] PartitionCols:_col0 Merge Join Operator [MERGEJOIN_172] (rows=1568628 width=1310) - Conds:RS_181._col2=RS_184._col0(Inner),Output:["_col0","_col1","_col3","_col4","_col5","_col7","_col8","_col9","_col10","_col11","_col12","_col14","_col15","_col16","_col17"] + Conds:RS_181._col2=RS_184._col0(Inner),Output:["_col0","_col1","_col3","_col4","_col5","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16"] <-Map 1 [SIMPLE_EDGE] vectorized SHUFFLE [RS_181] PartitionCols:_col2 @@ -211,8 +211,8 @@ Stage-0 <-Map 5 [SIMPLE_EDGE] vectorized SHUFFLE [RS_184] PartitionCols:_col0 - Select Operator [SEL_183] (rows=784314 width=1027) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col8","_col9","_col10","_col11"] + Select Operator [SEL_183] (rows=784314 width=941) + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10"] Filter Operator [FIL_182] (rows=784314 width=1027) predicate:((ca_state = 'IL') and ca_address_sk is not null) TableScan [TS_3] (rows=40000000 width=1027) diff --git ql/src/test/results/clientpositive/perf/tez/query82.q.out ql/src/test/results/clientpositive/perf/tez/query82.q.out index 6bc9666784f..2cad36392a2 100644 --- ql/src/test/results/clientpositive/perf/tez/query82.q.out +++ ql/src/test/results/clientpositive/perf/tez/query82.q.out @@ -83,7 +83,7 @@ Stage-0 <-Map 11 [SIMPLE_EDGE] vectorized SHUFFLE [RS_93] PartitionCols:_col0 - Select Operator [SEL_92] (rows=8116 width=98) + Select Operator [SEL_92] (rows=8116 width=4) Output:["_col0"] Filter Operator [FIL_91] (rows=8116 width=98) predicate:(CAST( d_date AS TIMESTAMP) BETWEEN TIMESTAMP'2002-05-30 00:00:00' AND TIMESTAMP'2002-07-29 00:00:00' and d_date_sk is not null) @@ -92,7 +92,7 @@ Stage-0 <-Map 8 [SIMPLE_EDGE] vectorized SHUFFLE [RS_90] PartitionCols:_col0 - Select Operator [SEL_89] (rows=4176000 width=11) + Select Operator [SEL_89] (rows=4176000 width=8) Output:["_col0","_col1"] Filter Operator [FIL_88] (rows=4176000 width=11) predicate:(inv_date_sk is not null and inv_item_sk is not null and inv_quantity_on_hand BETWEEN 100 AND 500) @@ -106,7 +106,7 @@ Stage-0 <-Map 6 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_82] PartitionCols:_col0 - Select Operator [SEL_81] (rows=297 width=404) + Select Operator [SEL_81] (rows=297 width=400) Output:["_col0","_col1","_col2","_col3"] Filter Operator [FIL_80] (rows=297 width=404) predicate:((i_manufact_id) IN (437, 129, 727, 663) and i_current_price BETWEEN 30 AND 60 and i_item_sk is not null) diff --git ql/src/test/results/clientpositive/perf/tez/query83.q.out ql/src/test/results/clientpositive/perf/tez/query83.q.out index a99851f0800..fc662c5a5a5 100644 --- ql/src/test/results/clientpositive/perf/tez/query83.q.out +++ ql/src/test/results/clientpositive/perf/tez/query83.q.out @@ -166,169 +166,175 @@ Stage-0 limit:100 Stage-1 Reducer 7 vectorized - File Output Operator [FS_398] - Limit [LIM_397] (rows=100 width=260) + File Output Operator [FS_401] + Limit [LIM_400] (rows=100 width=260) Number of rows:100 - Select Operator [SEL_396] (rows=130021 width=260) + Select Operator [SEL_399] (rows=130021 width=260) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] <-Reducer 6 [SIMPLE_EDGE] SHUFFLE [RS_127] Select Operator [SEL_126] (rows=130021 width=260) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] - Merge Join Operator [MERGEJOIN_363] (rows=130021 width=124) - Conds:RS_123._col0=RS_395._col0(Inner),Output:["_col0","_col1","_col3","_col5"] + Merge Join Operator [MERGEJOIN_363] (rows=130021 width=148) + Conds:RS_123._col0=RS_398._col0(Inner),Output:["_col0","_col1","_col2","_col4","_col5","_col7","_col8"] <-Reducer 14 [ONE_TO_ONE_EDGE] vectorized - FORWARD [RS_395] + FORWARD [RS_398] PartitionCols:_col0 - Group By Operator [GBY_394] (rows=130021 width=108) - Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 - <-Reducer 13 [SIMPLE_EDGE] - SHUFFLE [RS_117] - PartitionCols:_col0 - Group By Operator [GBY_116] (rows=390063 width=108) - Output:["_col0","_col1"],aggregations:["sum(_col2)"],keys:_col4 - Merge Join Operator [MERGEJOIN_361] (rows=5752600 width=103) - Conds:RS_112._col0=RS_113._col0(Inner),Output:["_col2","_col4"] - <-Reducer 16 [SIMPLE_EDGE] - SHUFFLE [RS_113] - PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_352] (rows=5070 width=4) - Conds:RS_374._col1=RS_383._col0(Inner),Output:["_col0"] - <-Map 15 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_374] - PartitionCols:_col1 - Select Operator [SEL_373] (rows=73049 width=98) - Output:["_col0","_col1"] - Filter Operator [FIL_372] (rows=73049 width=98) - predicate:(d_date is not null and d_date_sk is not null) - TableScan [TS_6] (rows=73049 width=98) - default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_date"] - <-Reducer 19 [ONE_TO_ONE_EDGE] vectorized - FORWARD [RS_383] - PartitionCols:_col0 - Group By Operator [GBY_382] (rows=5070 width=94) - Output:["_col0"],keys:KEY._col0 - <-Reducer 18 [SIMPLE_EDGE] - SHUFFLE [RS_22] - PartitionCols:_col0 - Group By Operator [GBY_21] (rows=5070 width=94) - Output:["_col0"],keys:_col0 - Merge Join Operator [MERGEJOIN_351] (rows=10141 width=94) - Conds:RS_377._col1=RS_381._col0(Left Semi),Output:["_col0"] - <-Map 17 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_377] - PartitionCols:_col1 - Select Operator [SEL_376] (rows=73049 width=98) - Output:["_col0","_col1"] - Filter Operator [FIL_375] (rows=73049 width=98) - predicate:(d_date is not null and d_week_seq is not null) - TableScan [TS_9] (rows=73049 width=98) - default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date","d_week_seq"] - <-Map 20 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_381] - PartitionCols:_col0 - Group By Operator [GBY_380] (rows=1826 width=4) - Output:["_col0"],keys:_col0 - Select Operator [SEL_379] (rows=3652 width=4) - Output:["_col0"] - Filter Operator [FIL_378] (rows=3652 width=98) - predicate:((d_date) IN ('1998-01-02', '1998-10-15', '1998-11-10') and d_week_seq is not null) - TableScan [TS_12] (rows=73049 width=98) + Select Operator [SEL_397] (rows=130021 width=116) + Output:["_col0","_col1","_col2"] + Group By Operator [GBY_396] (rows=130021 width=108) + Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 + <-Reducer 13 [SIMPLE_EDGE] + SHUFFLE [RS_117] + PartitionCols:_col0 + Group By Operator [GBY_116] (rows=390063 width=108) + Output:["_col0","_col1"],aggregations:["sum(_col2)"],keys:_col4 + Merge Join Operator [MERGEJOIN_361] (rows=5752600 width=103) + Conds:RS_112._col0=RS_113._col0(Inner),Output:["_col2","_col4"] + <-Reducer 16 [SIMPLE_EDGE] + SHUFFLE [RS_113] + PartitionCols:_col0 + Merge Join Operator [MERGEJOIN_352] (rows=5070 width=4) + Conds:RS_374._col1=RS_383._col0(Inner),Output:["_col0"] + <-Map 15 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_374] + PartitionCols:_col1 + Select Operator [SEL_373] (rows=73049 width=98) + Output:["_col0","_col1"] + Filter Operator [FIL_372] (rows=73049 width=98) + predicate:(d_date is not null and d_date_sk is not null) + TableScan [TS_6] (rows=73049 width=98) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_date"] + <-Reducer 19 [ONE_TO_ONE_EDGE] vectorized + FORWARD [RS_383] + PartitionCols:_col0 + Group By Operator [GBY_382] (rows=5070 width=94) + Output:["_col0"],keys:KEY._col0 + <-Reducer 18 [SIMPLE_EDGE] + SHUFFLE [RS_22] + PartitionCols:_col0 + Group By Operator [GBY_21] (rows=5070 width=94) + Output:["_col0"],keys:_col0 + Merge Join Operator [MERGEJOIN_351] (rows=10141 width=94) + Conds:RS_377._col1=RS_381._col0(Left Semi),Output:["_col0"] + <-Map 17 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_377] + PartitionCols:_col1 + Select Operator [SEL_376] (rows=73049 width=98) + Output:["_col0","_col1"] + Filter Operator [FIL_375] (rows=73049 width=98) + predicate:(d_date is not null and d_week_seq is not null) + TableScan [TS_9] (rows=73049 width=98) default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date","d_week_seq"] - <-Reducer 12 [SIMPLE_EDGE] - SHUFFLE [RS_112] - PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_356] (rows=13749816 width=107) - Conds:RS_393._col1=RS_371._col0(Inner),Output:["_col0","_col2","_col4"] - <-Map 8 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_371] - PartitionCols:_col0 - Select Operator [SEL_368] (rows=462000 width=104) - Output:["_col0","_col1"] - Filter Operator [FIL_367] (rows=462000 width=104) - predicate:(i_item_id is not null and i_item_sk is not null) - TableScan [TS_3] (rows=462000 width=104) - default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_item_id"] - <-Map 22 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_393] - PartitionCols:_col1 - Select Operator [SEL_392] (rows=13749816 width=11) - Output:["_col0","_col1","_col2"] - Filter Operator [FIL_391] (rows=13749816 width=11) - predicate:(wr_item_sk is not null and wr_returned_date_sk is not null) - TableScan [TS_80] (rows=14398467 width=11) - default@web_returns,web_returns,Tbl:COMPLETE,Col:COMPLETE,Output:["wr_returned_date_sk","wr_item_sk","wr_return_quantity"] + <-Map 20 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_381] + PartitionCols:_col0 + Group By Operator [GBY_380] (rows=1826 width=4) + Output:["_col0"],keys:_col0 + Select Operator [SEL_379] (rows=3652 width=4) + Output:["_col0"] + Filter Operator [FIL_378] (rows=3652 width=98) + predicate:((d_date) IN ('1998-01-02', '1998-10-15', '1998-11-10') and d_week_seq is not null) + TableScan [TS_12] (rows=73049 width=98) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date","d_week_seq"] + <-Reducer 12 [SIMPLE_EDGE] + SHUFFLE [RS_112] + PartitionCols:_col0 + Merge Join Operator [MERGEJOIN_356] (rows=13749816 width=107) + Conds:RS_395._col1=RS_371._col0(Inner),Output:["_col0","_col2","_col4"] + <-Map 8 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_371] + PartitionCols:_col0 + Select Operator [SEL_368] (rows=462000 width=104) + Output:["_col0","_col1"] + Filter Operator [FIL_367] (rows=462000 width=104) + predicate:(i_item_id is not null and i_item_sk is not null) + TableScan [TS_3] (rows=462000 width=104) + default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_item_id"] + <-Map 22 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_395] + PartitionCols:_col1 + Select Operator [SEL_394] (rows=13749816 width=11) + Output:["_col0","_col1","_col2"] + Filter Operator [FIL_393] (rows=13749816 width=11) + predicate:(wr_item_sk is not null and wr_returned_date_sk is not null) + TableScan [TS_80] (rows=14398467 width=11) + default@web_returns,web_returns,Tbl:COMPLETE,Col:COMPLETE,Output:["wr_returned_date_sk","wr_item_sk","wr_return_quantity"] <-Reducer 5 [ONE_TO_ONE_EDGE] FORWARD [RS_123] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_362] (rows=134905 width=116) - Conds:RS_385._col0=RS_390._col0(Inner),Output:["_col0","_col1","_col3"] + Merge Join Operator [MERGEJOIN_362] (rows=134905 width=132) + Conds:RS_386._col0=RS_392._col0(Inner),Output:["_col0","_col1","_col2","_col4","_col5"] <-Reducer 11 [ONE_TO_ONE_EDGE] vectorized - FORWARD [RS_390] + FORWARD [RS_392] PartitionCols:_col0 - Group By Operator [GBY_389] (rows=141711 width=108) - Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 - <-Reducer 10 [SIMPLE_EDGE] - SHUFFLE [RS_77] - PartitionCols:_col0 - Group By Operator [GBY_76] (rows=462000 width=108) - Output:["_col0","_col1"],aggregations:["sum(_col2)"],keys:_col4 - Merge Join Operator [MERGEJOIN_360] (rows=25343167 width=103) - Conds:RS_72._col0=RS_73._col0(Inner),Output:["_col2","_col4"] - <-Reducer 16 [SIMPLE_EDGE] - SHUFFLE [RS_73] - PartitionCols:_col0 - Please refer to the previous Merge Join Operator [MERGEJOIN_352] - <-Reducer 9 [SIMPLE_EDGE] - SHUFFLE [RS_72] - PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_353] (rows=55578005 width=107) - Conds:RS_388._col1=RS_370._col0(Inner),Output:["_col0","_col2","_col4"] - <-Map 8 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_370] - PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_368] - <-Map 21 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_388] - PartitionCols:_col1 - Select Operator [SEL_387] (rows=55578005 width=11) - Output:["_col0","_col1","_col2"] - Filter Operator [FIL_386] (rows=55578005 width=11) - predicate:(sr_item_sk is not null and sr_returned_date_sk is not null) - TableScan [TS_40] (rows=57591150 width=11) - default@store_returns,store_returns,Tbl:COMPLETE,Col:COMPLETE,Output:["sr_returned_date_sk","sr_item_sk","sr_return_quantity"] + Select Operator [SEL_391] (rows=141711 width=116) + Output:["_col0","_col1","_col2"] + Group By Operator [GBY_390] (rows=141711 width=108) + Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 + <-Reducer 10 [SIMPLE_EDGE] + SHUFFLE [RS_77] + PartitionCols:_col0 + Group By Operator [GBY_76] (rows=462000 width=108) + Output:["_col0","_col1"],aggregations:["sum(_col2)"],keys:_col4 + Merge Join Operator [MERGEJOIN_360] (rows=25343167 width=103) + Conds:RS_72._col0=RS_73._col0(Inner),Output:["_col2","_col4"] + <-Reducer 16 [SIMPLE_EDGE] + SHUFFLE [RS_73] + PartitionCols:_col0 + Please refer to the previous Merge Join Operator [MERGEJOIN_352] + <-Reducer 9 [SIMPLE_EDGE] + SHUFFLE [RS_72] + PartitionCols:_col0 + Merge Join Operator [MERGEJOIN_353] (rows=55578005 width=107) + Conds:RS_389._col1=RS_370._col0(Inner),Output:["_col0","_col2","_col4"] + <-Map 8 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_370] + PartitionCols:_col0 + Please refer to the previous Select Operator [SEL_368] + <-Map 21 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_389] + PartitionCols:_col1 + Select Operator [SEL_388] (rows=55578005 width=11) + Output:["_col0","_col1","_col2"] + Filter Operator [FIL_387] (rows=55578005 width=11) + predicate:(sr_item_sk is not null and sr_returned_date_sk is not null) + TableScan [TS_40] (rows=57591150 width=11) + default@store_returns,store_returns,Tbl:COMPLETE,Col:COMPLETE,Output:["sr_returned_date_sk","sr_item_sk","sr_return_quantity"] <-Reducer 4 [ONE_TO_ONE_EDGE] vectorized - FORWARD [RS_385] + FORWARD [RS_386] PartitionCols:_col0 - Group By Operator [GBY_384] (rows=134905 width=108) - Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 - <-Reducer 3 [SIMPLE_EDGE] - SHUFFLE [RS_37] - PartitionCols:_col0 - Group By Operator [GBY_36] (rows=462000 width=108) - Output:["_col0","_col1"],aggregations:["sum(_col2)"],keys:_col4 - Merge Join Operator [MERGEJOIN_359] (rows=12501392 width=103) - Conds:RS_32._col0=RS_33._col0(Inner),Output:["_col2","_col4"] - <-Reducer 16 [SIMPLE_EDGE] - SHUFFLE [RS_33] - PartitionCols:_col0 - Please refer to the previous Merge Join Operator [MERGEJOIN_352] - <-Reducer 2 [SIMPLE_EDGE] - SHUFFLE [RS_32] - PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_350] (rows=28798881 width=107) - Conds:RS_366._col1=RS_369._col0(Inner),Output:["_col0","_col2","_col4"] - <-Map 8 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_369] - PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_368] - <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_366] - PartitionCols:_col1 - Select Operator [SEL_365] (rows=28798881 width=11) - Output:["_col0","_col1","_col2"] - Filter Operator [FIL_364] (rows=28798881 width=11) - predicate:(cr_item_sk is not null and cr_returned_date_sk is not null) - TableScan [TS_0] (rows=28798881 width=11) - default@catalog_returns,catalog_returns,Tbl:COMPLETE,Col:COMPLETE,Output:["cr_returned_date_sk","cr_item_sk","cr_return_quantity"] + Select Operator [SEL_385] (rows=134905 width=116) + Output:["_col0","_col1","_col2"] + Group By Operator [GBY_384] (rows=134905 width=108) + Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 + <-Reducer 3 [SIMPLE_EDGE] + SHUFFLE [RS_37] + PartitionCols:_col0 + Group By Operator [GBY_36] (rows=462000 width=108) + Output:["_col0","_col1"],aggregations:["sum(_col2)"],keys:_col4 + Merge Join Operator [MERGEJOIN_359] (rows=12501392 width=103) + Conds:RS_32._col0=RS_33._col0(Inner),Output:["_col2","_col4"] + <-Reducer 16 [SIMPLE_EDGE] + SHUFFLE [RS_33] + PartitionCols:_col0 + Please refer to the previous Merge Join Operator [MERGEJOIN_352] + <-Reducer 2 [SIMPLE_EDGE] + SHUFFLE [RS_32] + PartitionCols:_col0 + Merge Join Operator [MERGEJOIN_350] (rows=28798881 width=107) + Conds:RS_366._col1=RS_369._col0(Inner),Output:["_col0","_col2","_col4"] + <-Map 8 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_369] + PartitionCols:_col0 + Please refer to the previous Select Operator [SEL_368] + <-Map 1 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_366] + PartitionCols:_col1 + Select Operator [SEL_365] (rows=28798881 width=11) + Output:["_col0","_col1","_col2"] + Filter Operator [FIL_364] (rows=28798881 width=11) + predicate:(cr_item_sk is not null and cr_returned_date_sk is not null) + TableScan [TS_0] (rows=28798881 width=11) + default@catalog_returns,catalog_returns,Tbl:COMPLETE,Col:COMPLETE,Output:["cr_returned_date_sk","cr_item_sk","cr_return_quantity"] diff --git ql/src/test/results/clientpositive/perf/tez/query84.q.out ql/src/test/results/clientpositive/perf/tez/query84.q.out index d4c0125cfbd..9adcf860aba 100644 --- ql/src/test/results/clientpositive/perf/tez/query84.q.out +++ ql/src/test/results/clientpositive/perf/tez/query84.q.out @@ -76,8 +76,8 @@ Stage-0 SHUFFLE [RS_36] Select Operator [SEL_35] (rows=255285 width=384) Output:["_col1","_col2"] - Merge Join Operator [MERGEJOIN_120] (rows=255285 width=280) - Conds:RS_32._col1=RS_33._col1(Inner),Output:["_col2","_col6","_col7"] + Merge Join Operator [MERGEJOIN_120] (rows=255285 width=284) + Conds:RS_32._col1=RS_33._col1(Inner),Output:["_col2","_col6"] <-Reducer 2 [ONE_TO_ONE_EDGE] FORWARD [RS_32] PartitionCols:_col1 @@ -104,8 +104,8 @@ Stage-0 <-Reducer 8 [SIMPLE_EDGE] SHUFFLE [RS_33] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_119] (rows=8315 width=280) - Conds:RS_25._col2=RS_26._col0(Inner),Output:["_col0","_col1","_col4","_col5"] + Merge Join Operator [MERGEJOIN_119] (rows=8315 width=284) + Conds:RS_25._col2=RS_26._col0(Inner),Output:["_col0","_col1","_col4"] <-Reducer 11 [SIMPLE_EDGE] SHUFFLE [RS_26] PartitionCols:_col0 @@ -123,7 +123,7 @@ Stage-0 <-Map 12 [SIMPLE_EDGE] vectorized SHUFFLE [RS_138] PartitionCols:_col0 - Select Operator [SEL_137] (rows=2 width=12) + Select Operator [SEL_137] (rows=2 width=4) Output:["_col0"] Filter Operator [FIL_136] (rows=2 width=12) predicate:((ib_lower_bound >= 32287) and (ib_upper_bound <= 82287) and ib_income_band_sk is not null) @@ -132,13 +132,13 @@ Stage-0 <-Reducer 7 [SIMPLE_EDGE] SHUFFLE [RS_25] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_117] (rows=83148 width=280) - Conds:RS_129._col3=RS_132._col0(Inner),Output:["_col0","_col1","_col2","_col4","_col5"] + Merge Join Operator [MERGEJOIN_117] (rows=83148 width=284) + Conds:RS_129._col3=RS_132._col0(Inner),Output:["_col0","_col1","_col2","_col4"] <-Map 6 [SIMPLE_EDGE] vectorized SHUFFLE [RS_129] PartitionCols:_col3 - Select Operator [SEL_128] (rows=74500295 width=291) - Output:["_col0","_col1","_col2","_col3","_col4","_col5"] + Select Operator [SEL_128] (rows=74500295 width=295) + Output:["_col0","_col1","_col2","_col3","_col4"] Filter Operator [FIL_127] (rows=74500295 width=291) predicate:(c_current_addr_sk is not null and c_current_cdemo_sk is not null and c_current_hdemo_sk is not null) TableScan [TS_6] (rows=80000000 width=291) @@ -146,7 +146,7 @@ Stage-0 <-Map 9 [SIMPLE_EDGE] vectorized SHUFFLE [RS_132] PartitionCols:_col0 - Select Operator [SEL_131] (rows=44643 width=96) + Select Operator [SEL_131] (rows=44643 width=4) Output:["_col0"] Filter Operator [FIL_130] (rows=44643 width=97) predicate:((ca_city = 'Hopewell') and ca_address_sk is not null) diff --git ql/src/test/results/clientpositive/perf/tez/query85.q.out ql/src/test/results/clientpositive/perf/tez/query85.q.out index f5800b95ead..1ada3945fdd 100644 --- ql/src/test/results/clientpositive/perf/tez/query85.q.out +++ ql/src/test/results/clientpositive/perf/tez/query85.q.out @@ -183,15 +183,15 @@ POSTHOOK: Output: hdfs://### HDFS PATH ### Plan optimized by CBO. Vertex dependency in root stage -Map 11 <- Reducer 15 (BROADCAST_EDGE) +Map 11 <- Reducer 13 (BROADCAST_EDGE) Reducer 10 <- Reducer 9 (SIMPLE_EDGE) -Reducer 15 <- Map 14 (CUSTOM_SIMPLE_EDGE) +Reducer 13 <- Map 12 (CUSTOM_SIMPLE_EDGE) Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 11 (SIMPLE_EDGE) -Reducer 3 <- Map 12 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) -Reducer 4 <- Map 13 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) +Reducer 3 <- Map 17 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) +Reducer 4 <- Map 12 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) Reducer 5 <- Map 14 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) -Reducer 6 <- Map 16 (SIMPLE_EDGE), Reducer 5 (SIMPLE_EDGE) -Reducer 7 <- Map 17 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE) +Reducer 6 <- Map 15 (SIMPLE_EDGE), Reducer 5 (SIMPLE_EDGE) +Reducer 7 <- Map 16 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE) Reducer 8 <- Map 17 (SIMPLE_EDGE), Reducer 7 (SIMPLE_EDGE) Reducer 9 <- Reducer 8 (SIMPLE_EDGE) @@ -200,134 +200,138 @@ Stage-0 limit:-1 Stage-1 Reducer 10 vectorized - File Output Operator [FS_239] - Limit [LIM_238] (rows=72 width=832) + File Output Operator [FS_240] + Limit [LIM_239] (rows=7 width=832) Number of rows:100 - Select Operator [SEL_237] (rows=72 width=832) + Select Operator [SEL_238] (rows=7 width=832) Output:["_col0","_col1","_col2","_col3"] <-Reducer 9 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_236] - Select Operator [SEL_235] (rows=72 width=832) + SHUFFLE [RS_237] + Select Operator [SEL_236] (rows=7 width=832) Output:["_col4","_col5","_col6","_col7"] - Group By Operator [GBY_234] (rows=72 width=353) + Group By Operator [GBY_235] (rows=7 width=353) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"],aggregations:["sum(VALUE._col0)","count(VALUE._col1)","sum(VALUE._col2)","count(VALUE._col3)","sum(VALUE._col4)","count(VALUE._col5)"],keys:KEY._col0 <-Reducer 8 [SIMPLE_EDGE] SHUFFLE [RS_49] PartitionCols:_col0 - Group By Operator [GBY_48] (rows=72 width=353) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"],aggregations:["sum(_col12)","count(_col12)","sum(_col7)","count(_col7)","sum(_col6)","count(_col6)"],keys:_col22 - Merge Join Operator [MERGEJOIN_206] (rows=8055 width=100) - Conds:RS_44._col3, _col24, _col25=RS_232._col0, _col1, _col2(Inner),Output:["_col6","_col7","_col12","_col22"] - <-Map 17 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_232] - PartitionCols:_col0, _col1, _col2 - Select Operator [SEL_231] (rows=265971 width=183) - Output:["_col0","_col1","_col2"] - Filter Operator [FIL_230] (rows=265971 width=183) - predicate:((cd_education_status) IN ('4 yr Degree', 'Primary', 'Advanced Degree') and (cd_marital_status) IN ('M', 'D', 'U') and cd_demo_sk is not null) - TableScan [TS_21] (rows=1861800 width=183) - default@customer_demographics,cd2,Tbl:COMPLETE,Col:COMPLETE,Output:["cd_demo_sk","cd_marital_status","cd_education_status"] - <-Reducer 7 [SIMPLE_EDGE] - SHUFFLE [RS_44] - PartitionCols:_col3, _col24, _col25 - Filter Operator [FIL_43] (rows=8055 width=390) - predicate:(((_col24 = 'D') and (_col25 = 'Primary') and _col13 BETWEEN 50 AND 100) or ((_col24 = 'M') and (_col25 = '4 yr Degree') and _col13 BETWEEN 100 AND 150) or ((_col24 = 'U') and (_col25 = 'Advanced Degree') and _col13 BETWEEN 150 AND 200)) - Merge Join Operator [MERGEJOIN_205] (rows=24166 width=390) - Conds:RS_40._col1=RS_233._col0(Inner),Output:["_col3","_col6","_col7","_col12","_col13","_col22","_col24","_col25"] - <-Map 17 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_233] - PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_231] - <-Reducer 6 [SIMPLE_EDGE] - SHUFFLE [RS_40] - PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_204] (rows=24166 width=211) - Conds:RS_37._col4=RS_229._col0(Inner),Output:["_col1","_col3","_col6","_col7","_col12","_col13","_col22"] + Group By Operator [GBY_48] (rows=7 width=353) + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"],aggregations:["sum(_col12)","count(_col12)","sum(_col7)","count(_col7)","sum(_col6)","count(_col6)"],keys:_col25 + Select Operator [SEL_47] (rows=16740 width=136) + Output:["_col6","_col7","_col12","_col25"] + Filter Operator [FIL_46] (rows=16740 width=136) + predicate:((_col33 and _col34 and _col16) or (_col35 and _col36 and _col17) or (_col37 and _col38 and _col18)) + Merge Join Operator [MERGEJOIN_206] (rows=44640 width=136) + Conds:RS_43._col1, _col20, _col21=RS_224._col0, _col1, _col2(Inner),Output:["_col6","_col7","_col12","_col16","_col17","_col18","_col25","_col33","_col34","_col35","_col36","_col37","_col38"] + <-Map 17 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_224] + PartitionCols:_col0, _col1, _col2 + Select Operator [SEL_222] (rows=265971 width=207) + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"] + Filter Operator [FIL_221] (rows=265971 width=183) + predicate:((cd_education_status) IN ('4 yr Degree', 'Primary', 'Advanced Degree') and (cd_marital_status) IN ('M', 'D', 'U') and cd_demo_sk is not null) + TableScan [TS_21] (rows=1861800 width=183) + default@customer_demographics,cd1,Tbl:COMPLETE,Col:COMPLETE,Output:["cd_demo_sk","cd_marital_status","cd_education_status"] + <-Reducer 7 [SIMPLE_EDGE] + SHUFFLE [RS_43] + PartitionCols:_col1, _col20, _col21 + Filter Operator [FIL_42] (rows=44640 width=315) + predicate:((_col27 and _col13) or (_col28 and _col14) or (_col29 and _col15)) + Merge Join Operator [MERGEJOIN_205] (rows=59520 width=315) + Conds:RS_39._col2=RS_234._col0(Inner),Output:["_col1","_col6","_col7","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col20","_col21","_col25","_col27","_col28","_col29"] <-Map 16 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_229] + SHUFFLE [RS_234] PartitionCols:_col0 - Select Operator [SEL_228] (rows=72 width=101) - Output:["_col0","_col1"] - Filter Operator [FIL_227] (rows=72 width=101) - predicate:r_reason_sk is not null - TableScan [TS_15] (rows=72 width=101) - default@reason,reason,Tbl:COMPLETE,Col:COMPLETE,Output:["r_reason_sk","r_reason_desc"] - <-Reducer 5 [SIMPLE_EDGE] - SHUFFLE [RS_37] - PartitionCols:_col4 - Merge Join Operator [MERGEJOIN_203] (rows=24166 width=114) - Conds:RS_34._col8=RS_212._col0(Inner),Output:["_col1","_col3","_col4","_col6","_col7","_col12","_col13"] - <-Map 14 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_212] + Select Operator [SEL_233] (rows=3529412 width=16) + Output:["_col0","_col1","_col2","_col3"] + Filter Operator [FIL_232] (rows=3529412 width=187) + predicate:((ca_country = 'United States') and (ca_state) IN ('KY', 'GA', 'NM', 'MT', 'OR', 'IN', 'WI', 'MO', 'WV') and ca_address_sk is not null) + TableScan [TS_18] (rows=40000000 width=187) + default@customer_address,customer_address,Tbl:COMPLETE,Col:COMPLETE,Output:["ca_address_sk","ca_state","ca_country"] + <-Reducer 6 [SIMPLE_EDGE] + SHUFFLE [RS_39] + PartitionCols:_col2 + Merge Join Operator [MERGEJOIN_204] (rows=674551 width=350) + Conds:RS_36._col4=RS_231._col0(Inner),Output:["_col1","_col2","_col6","_col7","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col20","_col21","_col25"] + <-Map 15 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_231] PartitionCols:_col0 - Select Operator [SEL_211] (rows=652 width=8) - Output:["_col0"] - Filter Operator [FIL_210] (rows=652 width=8) - predicate:((d_year = 1998) and d_date_sk is not null) - TableScan [TS_12] (rows=73049 width=8) - default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year"] - <-Reducer 4 [SIMPLE_EDGE] - SHUFFLE [RS_34] - PartitionCols:_col8 - Merge Join Operator [MERGEJOIN_202] (rows=67680 width=244) - Conds:RS_31._col10=RS_226._col0(Inner),Output:["_col1","_col3","_col4","_col6","_col7","_col8","_col12","_col13"] - <-Map 13 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_226] + Select Operator [SEL_230] (rows=72 width=101) + Output:["_col0","_col1"] + Filter Operator [FIL_229] (rows=72 width=101) + predicate:r_reason_sk is not null + TableScan [TS_15] (rows=72 width=101) + default@reason,reason,Tbl:COMPLETE,Col:COMPLETE,Output:["r_reason_sk","r_reason_desc"] + <-Reducer 5 [SIMPLE_EDGE] + SHUFFLE [RS_36] + PartitionCols:_col4 + Merge Join Operator [MERGEJOIN_203] (rows=674551 width=254) + Conds:RS_33._col10=RS_228._col0(Inner),Output:["_col1","_col2","_col4","_col6","_col7","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col20","_col21"] + <-Map 14 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_228] PartitionCols:_col0 - Select Operator [SEL_225] (rows=4602 width=4) + Select Operator [SEL_227] (rows=4602 width=4) Output:["_col0"] - Filter Operator [FIL_224] (rows=4602 width=4) + Filter Operator [FIL_226] (rows=4602 width=4) predicate:wp_web_page_sk is not null - TableScan [TS_9] (rows=4602 width=4) + TableScan [TS_12] (rows=4602 width=4) default@web_page,web_page,Tbl:COMPLETE,Col:COMPLETE,Output:["wp_web_page_sk"] - <-Reducer 3 [SIMPLE_EDGE] - SHUFFLE [RS_31] + <-Reducer 4 [SIMPLE_EDGE] + SHUFFLE [RS_33] PartitionCols:_col10 - Filter Operator [FIL_30] (rows=67680 width=446) - predicate:(((_col16) IN ('KY', 'GA', 'NM') and _col14 BETWEEN 100 AND 200) or ((_col16) IN ('MT', 'OR', 'IN') and _col14 BETWEEN 150 AND 300) or ((_col16) IN ('WI', 'MO', 'WV') and _col14 BETWEEN 50 AND 250)) - Merge Join Operator [MERGEJOIN_201] (rows=1150579 width=446) - Conds:RS_27._col2=RS_223._col0(Inner),Output:["_col1","_col3","_col4","_col6","_col7","_col8","_col10","_col12","_col13","_col14","_col16"] - <-Map 12 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_223] - PartitionCols:_col0 - Select Operator [SEL_222] (rows=3529412 width=187) - Output:["_col0","_col1"] - Filter Operator [FIL_221] (rows=3529412 width=187) - predicate:((ca_country = 'United States') and (ca_state) IN ('KY', 'GA', 'NM', 'MT', 'OR', 'IN', 'WI', 'MO', 'WV') and ca_address_sk is not null) - TableScan [TS_6] (rows=40000000 width=187) - default@customer_address,customer_address,Tbl:COMPLETE,Col:COMPLETE,Output:["ca_address_sk","ca_state","ca_country"] - <-Reducer 2 [SIMPLE_EDGE] - SHUFFLE [RS_27] - PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_200] (rows=13039884 width=466) - Conds:RS_209._col0, _col5=RS_220._col1, _col3(Inner),Output:["_col1","_col2","_col3","_col4","_col6","_col7","_col8","_col10","_col12","_col13","_col14"] - <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_209] - PartitionCols:_col0, _col5 - Select Operator [SEL_208] (rows=11975292 width=237) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] - Filter Operator [FIL_207] (rows=11975292 width=237) - predicate:(wr_item_sk is not null and wr_order_number is not null and wr_reason_sk is not null and wr_refunded_addr_sk is not null and wr_refunded_cdemo_sk is not null and wr_returning_cdemo_sk is not null) - TableScan [TS_0] (rows=14398467 width=237) - default@web_returns,web_returns,Tbl:COMPLETE,Col:COMPLETE,Output:["wr_item_sk","wr_refunded_cdemo_sk","wr_refunded_addr_sk","wr_returning_cdemo_sk","wr_reason_sk","wr_order_number","wr_fee","wr_refunded_cash"] - <-Map 11 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_220] - PartitionCols:_col1, _col3 - Select Operator [SEL_219] (rows=15992347 width=243) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"] - Filter Operator [FIL_218] (rows=15992347 width=243) - predicate:((ws_net_profit BETWEEN 100 AND 200 or ws_net_profit BETWEEN 150 AND 300 or ws_net_profit BETWEEN 50 AND 250) and (ws_sales_price BETWEEN 100 AND 150 or ws_sales_price BETWEEN 50 AND 100 or ws_sales_price BETWEEN 150 AND 200) and (ws_sold_date_sk BETWEEN DynamicValue(RS_35_date_dim_d_date_sk_min) AND DynamicValue(RS_35_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_35_date_dim_d_date_sk_bloom_filter))) and ws_item_sk is not null and ws_order_number is not null and ws_sold_date_sk is not null and ws_web_page_sk is not null) - TableScan [TS_3] (rows=144002668 width=243) - default@web_sales,web_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_sold_date_sk","ws_item_sk","ws_web_page_sk","ws_order_number","ws_quantity","ws_sales_price","ws_net_profit"] - <-Reducer 15 [BROADCAST_EDGE] vectorized - BROADCAST [RS_217] - Group By Operator [GBY_216] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 14 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_215] - Group By Operator [GBY_214] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_213] (rows=652 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_211] + Merge Join Operator [MERGEJOIN_202] (rows=674551 width=258) + Conds:RS_30._col8=RS_212._col0(Inner),Output:["_col1","_col2","_col4","_col6","_col7","_col10","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col20","_col21"] + <-Map 12 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_212] + PartitionCols:_col0 + Select Operator [SEL_211] (rows=652 width=4) + Output:["_col0"] + Filter Operator [FIL_210] (rows=652 width=8) + predicate:((d_year = 1998) and d_date_sk is not null) + TableScan [TS_9] (rows=73049 width=8) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year"] + <-Reducer 3 [SIMPLE_EDGE] + SHUFFLE [RS_30] + PartitionCols:_col8 + Merge Join Operator [MERGEJOIN_201] (rows=1889180 width=383) + Conds:RS_27._col3=RS_225._col0(Inner),Output:["_col1","_col2","_col4","_col6","_col7","_col8","_col10","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col20","_col21"] + <-Map 17 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_225] + PartitionCols:_col0 + Select Operator [SEL_223] (rows=265971 width=183) + Output:["_col0","_col1","_col2"] + Please refer to the previous Filter Operator [FIL_221] + <-Reducer 2 [SIMPLE_EDGE] + SHUFFLE [RS_27] + PartitionCols:_col3 + Merge Join Operator [MERGEJOIN_200] (rows=13039884 width=266) + Conds:RS_209._col0, _col5=RS_220._col1, _col3(Inner),Output:["_col1","_col2","_col3","_col4","_col6","_col7","_col8","_col10","_col12","_col13","_col14","_col15","_col16","_col17","_col18"] + <-Map 1 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_209] + PartitionCols:_col0, _col5 + Select Operator [SEL_208] (rows=11975292 width=237) + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] + Filter Operator [FIL_207] (rows=11975292 width=237) + predicate:(wr_item_sk is not null and wr_order_number is not null and wr_reason_sk is not null and wr_refunded_addr_sk is not null and wr_refunded_cdemo_sk is not null and wr_returning_cdemo_sk is not null) + TableScan [TS_0] (rows=14398467 width=237) + default@web_returns,web_returns,Tbl:COMPLETE,Col:COMPLETE,Output:["wr_item_sk","wr_refunded_cdemo_sk","wr_refunded_addr_sk","wr_returning_cdemo_sk","wr_reason_sk","wr_order_number","wr_fee","wr_refunded_cash"] + <-Map 11 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_220] + PartitionCols:_col1, _col3 + Select Operator [SEL_219] (rows=15992347 width=43) + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10"] + Filter Operator [FIL_218] (rows=15992347 width=243) + predicate:((ws_net_profit BETWEEN 100 AND 200 or ws_net_profit BETWEEN 150 AND 300 or ws_net_profit BETWEEN 50 AND 250) and (ws_sales_price BETWEEN 100 AND 150 or ws_sales_price BETWEEN 50 AND 100 or ws_sales_price BETWEEN 150 AND 200) and (ws_sold_date_sk BETWEEN DynamicValue(RS_31_date_dim_d_date_sk_min) AND DynamicValue(RS_31_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_31_date_dim_d_date_sk_bloom_filter))) and ws_item_sk is not null and ws_order_number is not null and ws_sold_date_sk is not null and ws_web_page_sk is not null) + TableScan [TS_3] (rows=144002668 width=243) + default@web_sales,web_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_sold_date_sk","ws_item_sk","ws_web_page_sk","ws_order_number","ws_quantity","ws_sales_price","ws_net_profit"] + <-Reducer 13 [BROADCAST_EDGE] vectorized + BROADCAST [RS_217] + Group By Operator [GBY_216] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 12 [CUSTOM_SIMPLE_EDGE] vectorized + SHUFFLE [RS_215] + Group By Operator [GBY_214] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_213] (rows=652 width=4) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_211] diff --git ql/src/test/results/clientpositive/perf/tez/query86.q.out ql/src/test/results/clientpositive/perf/tez/query86.q.out index 22d494ba38f..2d6d545a5bd 100644 --- ql/src/test/results/clientpositive/perf/tez/query86.q.out +++ ql/src/test/results/clientpositive/perf/tez/query86.q.out @@ -100,7 +100,7 @@ Stage-0 Select Operator [SEL_15] (rows=24992810 width=293) Output:["_col0","_col1","_col2"] Merge Join Operator [MERGEJOIN_60] (rows=24992810 width=293) - Conds:RS_12._col1=RS_74._col0(Inner),Output:["_col2","_col6","_col7"] + Conds:RS_12._col1=RS_74._col0(Inner),Output:["_col2","_col5","_col6"] <-Map 9 [SIMPLE_EDGE] vectorized SHUFFLE [RS_74] PartitionCols:_col0 @@ -118,7 +118,7 @@ Stage-0 <-Map 7 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_63] PartitionCols:_col0 - Select Operator [SEL_62] (rows=317 width=8) + Select Operator [SEL_62] (rows=317 width=4) Output:["_col0"] Filter Operator [FIL_61] (rows=317 width=8) predicate:(d_date_sk is not null and d_month_seq BETWEEN 1212 AND 1223) diff --git ql/src/test/results/clientpositive/perf/tez/query87.q.out ql/src/test/results/clientpositive/perf/tez/query87.q.out index 4006cfb876d..5b59116741a 100644 --- ql/src/test/results/clientpositive/perf/tez/query87.q.out +++ ql/src/test/results/clientpositive/perf/tez/query87.q.out @@ -113,9 +113,9 @@ Stage-0 SHUFFLE [RS_80] PartitionCols:_col0, _col1, _col2 Group By Operator [GBY_79] (rows=24986582 width=274) - Output:["_col0","_col1","_col2"],keys:_col7, _col6, _col3 + Output:["_col0","_col1","_col2"],keys:_col6, _col5, _col3 Merge Join Operator [MERGEJOIN_192] (rows=24986582 width=274) - Conds:RS_75._col1=RS_249._col0(Inner),Output:["_col3","_col6","_col7"] + Conds:RS_75._col1=RS_249._col0(Inner),Output:["_col3","_col5","_col6"] <-Map 20 [SIMPLE_EDGE] vectorized SHUFFLE [RS_249] PartitionCols:_col0 @@ -133,7 +133,7 @@ Stage-0 <-Map 10 [SIMPLE_EDGE] vectorized SHUFFLE [RS_232] PartitionCols:_col0 - Select Operator [SEL_227] (rows=317 width=102) + Select Operator [SEL_227] (rows=317 width=98) Output:["_col0","_col1"] Filter Operator [FIL_226] (rows=317 width=102) predicate:(d_date_sk is not null and d_month_seq BETWEEN 1212 AND 1223) @@ -196,9 +196,9 @@ Stage-0 SHUFFLE [RS_42] PartitionCols:_col0, _col1, _col2 Group By Operator [GBY_41] (rows=49146883 width=274) - Output:["_col0","_col1","_col2"],keys:_col7, _col6, _col3 + Output:["_col0","_col1","_col2"],keys:_col6, _col5, _col3 Merge Join Operator [MERGEJOIN_190] (rows=49146883 width=274) - Conds:RS_37._col1=RS_248._col0(Inner),Output:["_col3","_col6","_col7"] + Conds:RS_37._col1=RS_248._col0(Inner),Output:["_col3","_col5","_col6"] <-Map 20 [SIMPLE_EDGE] vectorized SHUFFLE [RS_248] PartitionCols:_col0 @@ -251,9 +251,9 @@ Stage-0 SHUFFLE [RS_17] PartitionCols:_col0, _col1, _col2 Group By Operator [GBY_16] (rows=91197425 width=274) - Output:["_col0","_col1","_col2"],keys:_col7, _col6, _col3 + Output:["_col0","_col1","_col2"],keys:_col6, _col5, _col3 Merge Join Operator [MERGEJOIN_188] (rows=91197425 width=274) - Conds:RS_12._col1=RS_247._col0(Inner),Output:["_col3","_col6","_col7"] + Conds:RS_12._col1=RS_247._col0(Inner),Output:["_col3","_col5","_col6"] <-Map 20 [SIMPLE_EDGE] vectorized SHUFFLE [RS_247] PartitionCols:_col0 diff --git ql/src/test/results/clientpositive/perf/tez/query88.q.out ql/src/test/results/clientpositive/perf/tez/query88.q.out index 28a970755c7..249f7e37ce5 100644 --- ql/src/test/results/clientpositive/perf/tez/query88.q.out +++ ql/src/test/results/clientpositive/perf/tez/query88.q.out @@ -305,7 +305,7 @@ Stage-0 <-Map 59 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_704] PartitionCols:_col0 - Select Operator [SEL_693] (rows=155 width=91) + Select Operator [SEL_693] (rows=155 width=4) Output:["_col0"] Filter Operator [FIL_692] (rows=155 width=92) predicate:((s_store_name = 'ese') and s_store_sk is not null) @@ -319,7 +319,7 @@ Stage-0 <-Map 50 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_668] PartitionCols:_col0 - Select Operator [SEL_655] (rows=1515 width=12) + Select Operator [SEL_655] (rows=1515 width=4) Output:["_col0"] Filter Operator [FIL_647] (rows=1515 width=12) predicate:((t_hour = 10) and (t_minute < 30) and t_time_sk is not null) @@ -333,7 +333,7 @@ Stage-0 <-Map 13 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_618] PartitionCols:_col0 - Select Operator [SEL_607] (rows=817 width=12) + Select Operator [SEL_607] (rows=817 width=4) Output:["_col0"] Filter Operator [FIL_606] (rows=817 width=12) predicate:((((hd_dep_count = 3) and hd_vehicle_count is not null) or ((hd_dep_count = 0) and (hd_vehicle_count <= 2)) or ((hd_dep_count = 1) and (hd_vehicle_count <= 3))) and (hd_dep_count) IN (3, 0, 1) and (hd_vehicle_count <= 5) and hd_demo_sk is not null) @@ -407,7 +407,7 @@ Stage-0 <-Map 50 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_666] PartitionCols:_col0 - Select Operator [SEL_654] (rows=1515 width=12) + Select Operator [SEL_654] (rows=1515 width=4) Output:["_col0"] Filter Operator [FIL_646] (rows=1515 width=12) predicate:((t_hour = 10) and (t_minute >= 30) and t_time_sk is not null) @@ -489,7 +489,7 @@ Stage-0 <-Map 50 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_664] PartitionCols:_col0 - Select Operator [SEL_653] (rows=1515 width=12) + Select Operator [SEL_653] (rows=1515 width=4) Output:["_col0"] Filter Operator [FIL_645] (rows=1515 width=12) predicate:((t_hour = 11) and (t_minute < 30) and t_time_sk is not null) @@ -571,7 +571,7 @@ Stage-0 <-Map 50 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_662] PartitionCols:_col0 - Select Operator [SEL_652] (rows=1515 width=12) + Select Operator [SEL_652] (rows=1515 width=4) Output:["_col0"] Filter Operator [FIL_644] (rows=1515 width=12) predicate:((t_hour = 11) and (t_minute >= 30) and t_time_sk is not null) @@ -653,7 +653,7 @@ Stage-0 <-Map 50 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_660] PartitionCols:_col0 - Select Operator [SEL_651] (rows=1515 width=12) + Select Operator [SEL_651] (rows=1515 width=4) Output:["_col0"] Filter Operator [FIL_643] (rows=1515 width=12) predicate:((t_hour = 12) and (t_minute < 30) and t_time_sk is not null) @@ -731,7 +731,7 @@ Stage-0 <-Map 50 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_658] PartitionCols:_col0 - Select Operator [SEL_650] (rows=1515 width=12) + Select Operator [SEL_650] (rows=1515 width=4) Output:["_col0"] Filter Operator [FIL_642] (rows=1515 width=12) predicate:((t_hour = 8) and (t_minute >= 30) and t_time_sk is not null) @@ -809,7 +809,7 @@ Stage-0 <-Map 50 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_670] PartitionCols:_col0 - Select Operator [SEL_656] (rows=1515 width=12) + Select Operator [SEL_656] (rows=1515 width=4) Output:["_col0"] Filter Operator [FIL_648] (rows=1515 width=12) predicate:((t_hour = 9) and (t_minute >= 30) and t_time_sk is not null) @@ -887,7 +887,7 @@ Stage-0 <-Map 50 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_672] PartitionCols:_col0 - Select Operator [SEL_657] (rows=1515 width=12) + Select Operator [SEL_657] (rows=1515 width=4) Output:["_col0"] Filter Operator [FIL_649] (rows=1515 width=12) predicate:((t_hour = 9) and (t_minute < 30) and t_time_sk is not null) diff --git ql/src/test/results/clientpositive/perf/tez/query89.q.out ql/src/test/results/clientpositive/perf/tez/query89.q.out index 0844ca79a82..e79b9dd8db6 100644 --- ql/src/test/results/clientpositive/perf/tez/query89.q.out +++ ql/src/test/results/clientpositive/perf/tez/query89.q.out @@ -106,9 +106,9 @@ Stage-0 SHUFFLE [RS_23] PartitionCols:_col0, _col1, _col2, _col3, _col4, _col5 Group By Operator [GBY_22] (rows=27308180 width=577) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"],aggregations:["sum(_col3)"],keys:_col5, _col6, _col7, _col10, _col12, _col13 + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"],aggregations:["sum(_col3)"],keys:_col5, _col6, _col7, _col9, _col11, _col12 Merge Join Operator [MERGEJOIN_84] (rows=27308180 width=480) - Conds:RS_18._col2=RS_106._col0(Inner),Output:["_col3","_col5","_col6","_col7","_col10","_col12","_col13"] + Conds:RS_18._col2=RS_106._col0(Inner),Output:["_col3","_col5","_col6","_col7","_col9","_col11","_col12"] <-Map 12 [SIMPLE_EDGE] vectorized SHUFFLE [RS_106] PartitionCols:_col0 @@ -122,12 +122,12 @@ Stage-0 SHUFFLE [RS_18] PartitionCols:_col2 Merge Join Operator [MERGEJOIN_83] (rows=27308180 width=301) - Conds:RS_15._col0=RS_95._col0(Inner),Output:["_col2","_col3","_col5","_col6","_col7","_col10"] + Conds:RS_15._col0=RS_95._col0(Inner),Output:["_col2","_col3","_col5","_col6","_col7","_col9"] <-Map 10 [SIMPLE_EDGE] vectorized SHUFFLE [RS_95] PartitionCols:_col0 - Select Operator [SEL_94] (rows=652 width=12) - Output:["_col0","_col2"] + Select Operator [SEL_94] (rows=652 width=8) + Output:["_col0","_col1"] Filter Operator [FIL_93] (rows=652 width=12) predicate:((d_year = 2000) and d_date_sk is not null) TableScan [TS_6] (rows=73049 width=12) diff --git ql/src/test/results/clientpositive/perf/tez/query9.q.out ql/src/test/results/clientpositive/perf/tez/query9.q.out index eb1d3a58b43..ff156b535cd 100644 --- ql/src/test/results/clientpositive/perf/tez/query9.q.out +++ ql/src/test/results/clientpositive/perf/tez/query9.q.out @@ -159,150 +159,154 @@ Stage-0 File Output Operator [FS_154] Select Operator [SEL_153] (rows=2 width=560) Output:["_col0","_col1","_col2","_col3","_col4"] - Merge Join Operator [MERGEJOIN_185] (rows=2 width=1160) + Merge Join Operator [MERGEJOIN_185] (rows=2 width=1140) Conds:(Left Outer),Output:["_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15"] <-Reducer 15 [CUSTOM_SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_150] - Merge Join Operator [MERGEJOIN_184] (rows=2 width=1048) + Merge Join Operator [MERGEJOIN_184] (rows=2 width=1028) Conds:(Left Outer),Output:["_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14"] <-Reducer 14 [CUSTOM_SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_147] - Merge Join Operator [MERGEJOIN_183] (rows=2 width=936) + Merge Join Operator [MERGEJOIN_183] (rows=2 width=916) Conds:(Left Outer),Output:["_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13"] <-Reducer 13 [CUSTOM_SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_144] - Merge Join Operator [MERGEJOIN_182] (rows=2 width=928) + Merge Join Operator [MERGEJOIN_182] (rows=2 width=912) Conds:(Left Outer),Output:["_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12"] <-Reducer 12 [CUSTOM_SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_141] - Merge Join Operator [MERGEJOIN_181] (rows=2 width=816) + Merge Join Operator [MERGEJOIN_181] (rows=2 width=800) Conds:(Left Outer),Output:["_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11"] <-Reducer 11 [CUSTOM_SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_138] - Merge Join Operator [MERGEJOIN_180] (rows=2 width=704) + Merge Join Operator [MERGEJOIN_180] (rows=2 width=688) Conds:(Left Outer),Output:["_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10"] <-Reducer 10 [CUSTOM_SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_135] - Merge Join Operator [MERGEJOIN_179] (rows=2 width=696) + Merge Join Operator [MERGEJOIN_179] (rows=2 width=684) Conds:(Left Outer),Output:["_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9"] <-Reducer 34 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_272] - Select Operator [SEL_271] (rows=1 width=112) + PARTITION_ONLY_SHUFFLE [RS_275] + Select Operator [SEL_274] (rows=1 width=112) Output:["_col0"] - Group By Operator [GBY_270] (rows=1 width=120) + Group By Operator [GBY_273] (rows=1 width=120) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)","count(VALUE._col1)"] <-Map 29 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_253] - Group By Operator [GBY_248] (rows=1 width=120) + PARTITION_ONLY_SHUFFLE [RS_254] + Group By Operator [GBY_249] (rows=1 width=120) Output:["_col0","_col1"],aggregations:["sum(ss_net_paid_inc_tax)","count(ss_net_paid_inc_tax)"] - Select Operator [SEL_243] (rows=182855757 width=110) + Select Operator [SEL_244] (rows=182855757 width=110) Output:["ss_net_paid_inc_tax"] - Filter Operator [FIL_238] (rows=182855757 width=110) + Filter Operator [FIL_239] (rows=182855757 width=110) predicate:ss_quantity BETWEEN 41 AND 60 TableScan [TS_80] (rows=575995635 width=110) default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_quantity","ss_net_paid_inc_tax"] <-Reducer 9 [CUSTOM_SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_132] - Merge Join Operator [MERGEJOIN_178] (rows=2 width=584) + Merge Join Operator [MERGEJOIN_178] (rows=2 width=572) Conds:(Left Outer),Output:["_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"] <-Reducer 28 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_269] - Select Operator [SEL_268] (rows=1 width=112) + PARTITION_ONLY_SHUFFLE [RS_272] + Select Operator [SEL_271] (rows=1 width=112) Output:["_col0"] - Group By Operator [GBY_267] (rows=1 width=120) + Group By Operator [GBY_270] (rows=1 width=120) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)","count(VALUE._col1)"] <-Map 23 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_230] - Group By Operator [GBY_225] (rows=1 width=120) + PARTITION_ONLY_SHUFFLE [RS_231] + Group By Operator [GBY_226] (rows=1 width=120) Output:["_col0","_col1"],aggregations:["sum(ss_ext_list_price)","count(ss_ext_list_price)"] - Select Operator [SEL_220] (rows=182855757 width=110) + Select Operator [SEL_221] (rows=182855757 width=110) Output:["ss_ext_list_price"] - Filter Operator [FIL_215] (rows=182855757 width=110) + Filter Operator [FIL_216] (rows=182855757 width=110) predicate:ss_quantity BETWEEN 41 AND 60 TableScan [TS_73] (rows=575995635 width=110) default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_quantity","ss_ext_list_price"] <-Reducer 8 [CUSTOM_SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_129] - Merge Join Operator [MERGEJOIN_177] (rows=2 width=472) + Merge Join Operator [MERGEJOIN_177] (rows=2 width=460) Conds:(Left Outer),Output:["_col1","_col2","_col3","_col4","_col5","_col6","_col7"] <-Reducer 22 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_266] - Group By Operator [GBY_265] (rows=1 width=8) - Output:["_col0"],aggregations:["count(VALUE._col0)"] - <-Map 17 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_208] - Group By Operator [GBY_203] (rows=1 width=8) - Output:["_col0"],aggregations:["count()"] - Select Operator [SEL_198] (rows=182855757 width=3) - Filter Operator [FIL_193] (rows=182855757 width=3) - predicate:ss_quantity BETWEEN 41 AND 60 - TableScan [TS_66] (rows=575995635 width=3) - default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_quantity"] + PARTITION_ONLY_SHUFFLE [RS_269] + Select Operator [SEL_268] (rows=1 width=4) + Output:["_col0"] + Group By Operator [GBY_267] (rows=1 width=8) + Output:["_col0"],aggregations:["count(VALUE._col0)"] + <-Map 17 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_208] + Group By Operator [GBY_203] (rows=1 width=8) + Output:["_col0"],aggregations:["count()"] + Select Operator [SEL_198] (rows=182855757 width=3) + Filter Operator [FIL_193] (rows=182855757 width=3) + predicate:ss_quantity BETWEEN 41 AND 60 + TableScan [TS_66] (rows=575995635 width=3) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_quantity"] <-Reducer 7 [CUSTOM_SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_126] - Merge Join Operator [MERGEJOIN_176] (rows=2 width=464) + Merge Join Operator [MERGEJOIN_176] (rows=2 width=456) Conds:(Left Outer),Output:["_col1","_col2","_col3","_col4","_col5","_col6"] <-Reducer 33 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_264] - Select Operator [SEL_263] (rows=1 width=112) + PARTITION_ONLY_SHUFFLE [RS_266] + Select Operator [SEL_265] (rows=1 width=112) Output:["_col0"] - Group By Operator [GBY_262] (rows=1 width=120) + Group By Operator [GBY_264] (rows=1 width=120) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)","count(VALUE._col1)"] <-Map 29 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_252] - Group By Operator [GBY_247] (rows=1 width=120) + PARTITION_ONLY_SHUFFLE [RS_253] + Group By Operator [GBY_248] (rows=1 width=120) Output:["_col0","_col1"],aggregations:["sum(ss_net_paid_inc_tax)","count(ss_net_paid_inc_tax)"] - Select Operator [SEL_242] (rows=182855757 width=110) + Select Operator [SEL_243] (rows=182855757 width=110) Output:["ss_net_paid_inc_tax"] - Filter Operator [FIL_237] (rows=182855757 width=110) + Filter Operator [FIL_238] (rows=182855757 width=110) predicate:ss_quantity BETWEEN 21 AND 40 Please refer to the previous TableScan [TS_80] <-Reducer 6 [CUSTOM_SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_123] - Merge Join Operator [MERGEJOIN_175] (rows=2 width=352) + Merge Join Operator [MERGEJOIN_175] (rows=2 width=344) Conds:(Left Outer),Output:["_col1","_col2","_col3","_col4","_col5"] <-Reducer 27 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_261] - Select Operator [SEL_260] (rows=1 width=112) + PARTITION_ONLY_SHUFFLE [RS_263] + Select Operator [SEL_262] (rows=1 width=112) Output:["_col0"] - Group By Operator [GBY_259] (rows=1 width=120) + Group By Operator [GBY_261] (rows=1 width=120) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)","count(VALUE._col1)"] <-Map 23 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_229] - Group By Operator [GBY_224] (rows=1 width=120) + PARTITION_ONLY_SHUFFLE [RS_230] + Group By Operator [GBY_225] (rows=1 width=120) Output:["_col0","_col1"],aggregations:["sum(ss_ext_list_price)","count(ss_ext_list_price)"] - Select Operator [SEL_219] (rows=182855757 width=110) + Select Operator [SEL_220] (rows=182855757 width=110) Output:["ss_ext_list_price"] - Filter Operator [FIL_214] (rows=182855757 width=110) + Filter Operator [FIL_215] (rows=182855757 width=110) predicate:ss_quantity BETWEEN 21 AND 40 Please refer to the previous TableScan [TS_73] <-Reducer 5 [CUSTOM_SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_120] - Merge Join Operator [MERGEJOIN_174] (rows=2 width=240) + Merge Join Operator [MERGEJOIN_174] (rows=2 width=232) Conds:(Left Outer),Output:["_col1","_col2","_col3","_col4"] <-Reducer 21 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_258] - Group By Operator [GBY_257] (rows=1 width=8) - Output:["_col0"],aggregations:["count(VALUE._col0)"] - <-Map 17 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_207] - Group By Operator [GBY_202] (rows=1 width=8) - Output:["_col0"],aggregations:["count()"] - Select Operator [SEL_197] (rows=182855757 width=3) - Filter Operator [FIL_192] (rows=182855757 width=3) - predicate:ss_quantity BETWEEN 21 AND 40 - Please refer to the previous TableScan [TS_66] + PARTITION_ONLY_SHUFFLE [RS_260] + Select Operator [SEL_259] (rows=1 width=4) + Output:["_col0"] + Group By Operator [GBY_258] (rows=1 width=8) + Output:["_col0"],aggregations:["count(VALUE._col0)"] + <-Map 17 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_207] + Group By Operator [GBY_202] (rows=1 width=8) + Output:["_col0"],aggregations:["count()"] + Select Operator [SEL_197] (rows=182855757 width=3) + Filter Operator [FIL_192] (rows=182855757 width=3) + predicate:ss_quantity BETWEEN 21 AND 40 + Please refer to the previous TableScan [TS_66] <-Reducer 4 [CUSTOM_SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_117] - Merge Join Operator [MERGEJOIN_173] (rows=2 width=232) + Merge Join Operator [MERGEJOIN_173] (rows=2 width=228) Conds:(Left Outer),Output:["_col1","_col2","_col3"] <-Reducer 3 [CUSTOM_SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_114] - Merge Join Operator [MERGEJOIN_172] (rows=2 width=120) + Merge Join Operator [MERGEJOIN_172] (rows=2 width=116) Conds:(Left Outer),Output:["_col1","_col2"] <-Reducer 2 [CUSTOM_SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_111] - Merge Join Operator [MERGEJOIN_171] (rows=2 width=8) + Merge Join Operator [MERGEJOIN_171] (rows=2 width=4) Conds:(Left Outer),Output:["_col1"] <-Map 1 [CUSTOM_SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_188] @@ -312,129 +316,135 @@ Stage-0 TableScan [TS_0] (rows=72 width=4) default@reason,reason,Tbl:COMPLETE,Col:COMPLETE,Output:["r_reason_sk"] <-Reducer 20 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_210] - Group By Operator [GBY_209] (rows=1 width=8) - Output:["_col0"],aggregations:["count(VALUE._col0)"] - <-Map 17 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_206] - Group By Operator [GBY_201] (rows=1 width=8) - Output:["_col0"],aggregations:["count()"] - Select Operator [SEL_196] (rows=182855757 width=3) - Filter Operator [FIL_191] (rows=182855757 width=3) - predicate:ss_quantity BETWEEN 1 AND 20 - Please refer to the previous TableScan [TS_66] + PARTITION_ONLY_SHUFFLE [RS_211] + Select Operator [SEL_210] (rows=1 width=4) + Output:["_col0"] + Group By Operator [GBY_209] (rows=1 width=8) + Output:["_col0"],aggregations:["count(VALUE._col0)"] + <-Map 17 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_206] + Group By Operator [GBY_201] (rows=1 width=8) + Output:["_col0"],aggregations:["count()"] + Select Operator [SEL_196] (rows=182855757 width=3) + Filter Operator [FIL_191] (rows=182855757 width=3) + predicate:ss_quantity BETWEEN 1 AND 20 + Please refer to the previous TableScan [TS_66] <-Reducer 26 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_233] - Select Operator [SEL_232] (rows=1 width=112) + PARTITION_ONLY_SHUFFLE [RS_234] + Select Operator [SEL_233] (rows=1 width=112) Output:["_col0"] - Group By Operator [GBY_231] (rows=1 width=120) + Group By Operator [GBY_232] (rows=1 width=120) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)","count(VALUE._col1)"] <-Map 23 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_228] - Group By Operator [GBY_223] (rows=1 width=120) + PARTITION_ONLY_SHUFFLE [RS_229] + Group By Operator [GBY_224] (rows=1 width=120) Output:["_col0","_col1"],aggregations:["sum(ss_ext_list_price)","count(ss_ext_list_price)"] - Select Operator [SEL_218] (rows=182855757 width=110) + Select Operator [SEL_219] (rows=182855757 width=110) Output:["ss_ext_list_price"] - Filter Operator [FIL_213] (rows=182855757 width=110) + Filter Operator [FIL_214] (rows=182855757 width=110) predicate:ss_quantity BETWEEN 1 AND 20 Please refer to the previous TableScan [TS_73] <-Reducer 32 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_256] - Select Operator [SEL_255] (rows=1 width=112) + PARTITION_ONLY_SHUFFLE [RS_257] + Select Operator [SEL_256] (rows=1 width=112) Output:["_col0"] - Group By Operator [GBY_254] (rows=1 width=120) + Group By Operator [GBY_255] (rows=1 width=120) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)","count(VALUE._col1)"] <-Map 29 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_251] - Group By Operator [GBY_246] (rows=1 width=120) + PARTITION_ONLY_SHUFFLE [RS_252] + Group By Operator [GBY_247] (rows=1 width=120) Output:["_col0","_col1"],aggregations:["sum(ss_net_paid_inc_tax)","count(ss_net_paid_inc_tax)"] - Select Operator [SEL_241] (rows=182855757 width=110) + Select Operator [SEL_242] (rows=182855757 width=110) Output:["ss_net_paid_inc_tax"] - Filter Operator [FIL_236] (rows=182855757 width=110) + Filter Operator [FIL_237] (rows=182855757 width=110) predicate:ss_quantity BETWEEN 1 AND 20 Please refer to the previous TableScan [TS_80] <-Reducer 18 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_274] - Group By Operator [GBY_273] (rows=1 width=8) - Output:["_col0"],aggregations:["count(VALUE._col0)"] - <-Map 17 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_204] - Group By Operator [GBY_199] (rows=1 width=8) - Output:["_col0"],aggregations:["count()"] - Select Operator [SEL_194] (rows=182855757 width=3) - Filter Operator [FIL_189] (rows=182855757 width=3) - predicate:ss_quantity BETWEEN 61 AND 80 - Please refer to the previous TableScan [TS_66] + PARTITION_ONLY_SHUFFLE [RS_278] + Select Operator [SEL_277] (rows=1 width=4) + Output:["_col0"] + Group By Operator [GBY_276] (rows=1 width=8) + Output:["_col0"],aggregations:["count(VALUE._col0)"] + <-Map 17 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_204] + Group By Operator [GBY_199] (rows=1 width=8) + Output:["_col0"],aggregations:["count()"] + Select Operator [SEL_194] (rows=182855757 width=3) + Filter Operator [FIL_189] (rows=182855757 width=3) + predicate:ss_quantity BETWEEN 61 AND 80 + Please refer to the previous TableScan [TS_66] <-Reducer 24 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_277] - Select Operator [SEL_276] (rows=1 width=112) + PARTITION_ONLY_SHUFFLE [RS_281] + Select Operator [SEL_280] (rows=1 width=112) Output:["_col0"] - Group By Operator [GBY_275] (rows=1 width=120) + Group By Operator [GBY_279] (rows=1 width=120) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)","count(VALUE._col1)"] <-Map 23 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_226] - Group By Operator [GBY_221] (rows=1 width=120) + PARTITION_ONLY_SHUFFLE [RS_227] + Group By Operator [GBY_222] (rows=1 width=120) Output:["_col0","_col1"],aggregations:["sum(ss_ext_list_price)","count(ss_ext_list_price)"] - Select Operator [SEL_216] (rows=182855757 width=110) + Select Operator [SEL_217] (rows=182855757 width=110) Output:["ss_ext_list_price"] - Filter Operator [FIL_211] (rows=182855757 width=110) + Filter Operator [FIL_212] (rows=182855757 width=110) predicate:ss_quantity BETWEEN 61 AND 80 Please refer to the previous TableScan [TS_73] <-Reducer 30 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_280] - Select Operator [SEL_279] (rows=1 width=112) + PARTITION_ONLY_SHUFFLE [RS_284] + Select Operator [SEL_283] (rows=1 width=112) Output:["_col0"] - Group By Operator [GBY_278] (rows=1 width=120) + Group By Operator [GBY_282] (rows=1 width=120) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)","count(VALUE._col1)"] <-Map 29 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_249] - Group By Operator [GBY_244] (rows=1 width=120) + PARTITION_ONLY_SHUFFLE [RS_250] + Group By Operator [GBY_245] (rows=1 width=120) Output:["_col0","_col1"],aggregations:["sum(ss_net_paid_inc_tax)","count(ss_net_paid_inc_tax)"] - Select Operator [SEL_239] (rows=182855757 width=110) + Select Operator [SEL_240] (rows=182855757 width=110) Output:["ss_net_paid_inc_tax"] - Filter Operator [FIL_234] (rows=182855757 width=110) + Filter Operator [FIL_235] (rows=182855757 width=110) predicate:ss_quantity BETWEEN 61 AND 80 Please refer to the previous TableScan [TS_80] <-Reducer 19 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_282] - Group By Operator [GBY_281] (rows=1 width=8) - Output:["_col0"],aggregations:["count(VALUE._col0)"] - <-Map 17 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_205] - Group By Operator [GBY_200] (rows=1 width=8) - Output:["_col0"],aggregations:["count()"] - Select Operator [SEL_195] (rows=182855757 width=3) - Filter Operator [FIL_190] (rows=182855757 width=3) - predicate:ss_quantity BETWEEN 81 AND 100 - Please refer to the previous TableScan [TS_66] + PARTITION_ONLY_SHUFFLE [RS_287] + Select Operator [SEL_286] (rows=1 width=4) + Output:["_col0"] + Group By Operator [GBY_285] (rows=1 width=8) + Output:["_col0"],aggregations:["count(VALUE._col0)"] + <-Map 17 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_205] + Group By Operator [GBY_200] (rows=1 width=8) + Output:["_col0"],aggregations:["count()"] + Select Operator [SEL_195] (rows=182855757 width=3) + Filter Operator [FIL_190] (rows=182855757 width=3) + predicate:ss_quantity BETWEEN 81 AND 100 + Please refer to the previous TableScan [TS_66] <-Reducer 25 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_285] - Select Operator [SEL_284] (rows=1 width=112) + PARTITION_ONLY_SHUFFLE [RS_290] + Select Operator [SEL_289] (rows=1 width=112) Output:["_col0"] - Group By Operator [GBY_283] (rows=1 width=120) + Group By Operator [GBY_288] (rows=1 width=120) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)","count(VALUE._col1)"] <-Map 23 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_227] - Group By Operator [GBY_222] (rows=1 width=120) + PARTITION_ONLY_SHUFFLE [RS_228] + Group By Operator [GBY_223] (rows=1 width=120) Output:["_col0","_col1"],aggregations:["sum(ss_ext_list_price)","count(ss_ext_list_price)"] - Select Operator [SEL_217] (rows=182855757 width=110) + Select Operator [SEL_218] (rows=182855757 width=110) Output:["ss_ext_list_price"] - Filter Operator [FIL_212] (rows=182855757 width=110) + Filter Operator [FIL_213] (rows=182855757 width=110) predicate:ss_quantity BETWEEN 81 AND 100 Please refer to the previous TableScan [TS_73] <-Reducer 31 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_288] - Select Operator [SEL_287] (rows=1 width=112) + PARTITION_ONLY_SHUFFLE [RS_293] + Select Operator [SEL_292] (rows=1 width=112) Output:["_col0"] - Group By Operator [GBY_286] (rows=1 width=120) + Group By Operator [GBY_291] (rows=1 width=120) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)","count(VALUE._col1)"] <-Map 29 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_250] - Group By Operator [GBY_245] (rows=1 width=120) + PARTITION_ONLY_SHUFFLE [RS_251] + Group By Operator [GBY_246] (rows=1 width=120) Output:["_col0","_col1"],aggregations:["sum(ss_net_paid_inc_tax)","count(ss_net_paid_inc_tax)"] - Select Operator [SEL_240] (rows=182855757 width=110) + Select Operator [SEL_241] (rows=182855757 width=110) Output:["ss_net_paid_inc_tax"] - Filter Operator [FIL_235] (rows=182855757 width=110) + Filter Operator [FIL_236] (rows=182855757 width=110) predicate:ss_quantity BETWEEN 81 AND 100 Please refer to the previous TableScan [TS_80] diff --git ql/src/test/results/clientpositive/perf/tez/query90.q.out ql/src/test/results/clientpositive/perf/tez/query90.q.out index 653ce1a912b..916a23202d6 100644 --- ql/src/test/results/clientpositive/perf/tez/query90.q.out +++ ql/src/test/results/clientpositive/perf/tez/query90.q.out @@ -102,7 +102,7 @@ Stage-0 <-Map 18 [SIMPLE_EDGE] vectorized SHUFFLE [RS_183] PartitionCols:_col0 - Select Operator [SEL_180] (rows=655 width=8) + Select Operator [SEL_180] (rows=655 width=4) Output:["_col0"] Filter Operator [FIL_179] (rows=655 width=8) predicate:((hd_dep_count = 8) and hd_demo_sk is not null) @@ -116,7 +116,7 @@ Stage-0 <-Map 15 [SIMPLE_EDGE] vectorized SHUFFLE [RS_171] PartitionCols:_col0 - Select Operator [SEL_168] (rows=9095 width=8) + Select Operator [SEL_168] (rows=9095 width=4) Output:["_col0"] Filter Operator [FIL_166] (rows=9095 width=8) predicate:(t_hour BETWEEN 14 AND 15 and t_time_sk is not null) @@ -130,7 +130,7 @@ Stage-0 <-Map 8 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_157] PartitionCols:_col0 - Select Operator [SEL_154] (rows=511 width=7) + Select Operator [SEL_154] (rows=511 width=4) Output:["_col0"] Filter Operator [FIL_153] (rows=511 width=7) predicate:(wp_char_count BETWEEN 5000 AND 5200 and wp_web_page_sk is not null) @@ -200,7 +200,7 @@ Stage-0 <-Map 15 [SIMPLE_EDGE] vectorized SHUFFLE [RS_169] PartitionCols:_col0 - Select Operator [SEL_167] (rows=9095 width=8) + Select Operator [SEL_167] (rows=9095 width=4) Output:["_col0"] Filter Operator [FIL_165] (rows=9095 width=8) predicate:(t_hour BETWEEN 6 AND 7 and t_time_sk is not null) diff --git ql/src/test/results/clientpositive/perf/tez/query91.q.out ql/src/test/results/clientpositive/perf/tez/query91.q.out index 5b4952dbd44..98e8adf135f 100644 --- ql/src/test/results/clientpositive/perf/tez/query91.q.out +++ ql/src/test/results/clientpositive/perf/tez/query91.q.out @@ -104,13 +104,13 @@ Stage-0 SHUFFLE [RS_42] PartitionCols:_col0, _col1, _col2, _col3, _col4 Group By Operator [GBY_41] (rows=1 width=585) - Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(_col12)"],keys:_col5, _col6, _col17, _col18, _col19 + Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(_col11)"],keys:_col5, _col6, _col14, _col15, _col16 Merge Join Operator [MERGEJOIN_144] (rows=10438 width=473) - Conds:RS_37._col2=RS_165._col0(Inner),Output:["_col5","_col6","_col12","_col17","_col18","_col19"] + Conds:RS_37._col2=RS_165._col0(Inner),Output:["_col5","_col6","_col11","_col14","_col15","_col16"] <-Map 15 [SIMPLE_EDGE] vectorized SHUFFLE [RS_165] PartitionCols:_col0 - Select Operator [SEL_164] (rows=3600 width=96) + Select Operator [SEL_164] (rows=3600 width=4) Output:["_col0"] Filter Operator [FIL_163] (rows=3600 width=96) predicate:((hd_buy_potential like '0-500%') and hd_demo_sk is not null) @@ -120,12 +120,12 @@ Stage-0 SHUFFLE [RS_37] PartitionCols:_col2 Merge Join Operator [MERGEJOIN_143] (rows=20876 width=473) - Conds:RS_34._col0=RS_35._col1(Inner),Output:["_col2","_col5","_col6","_col12","_col17","_col18","_col19"] + Conds:RS_34._col0=RS_35._col1(Inner),Output:["_col2","_col5","_col6","_col11","_col14","_col15","_col16"] <-Reducer 12 [SIMPLE_EDGE] SHUFFLE [RS_35] PartitionCols:_col1 Merge Join Operator [MERGEJOIN_142] (rows=657590 width=312) - Conds:RS_21._col2=RS_162._col0(Inner),Output:["_col1","_col3","_col8","_col9","_col10"] + Conds:RS_21._col2=RS_162._col0(Inner),Output:["_col1","_col3","_col6","_col7","_col8"] <-Map 14 [SIMPLE_EDGE] vectorized SHUFFLE [RS_162] PartitionCols:_col0 @@ -152,7 +152,7 @@ Stage-0 <-Map 13 [SIMPLE_EDGE] vectorized SHUFFLE [RS_159] PartitionCols:_col0 - Select Operator [SEL_158] (rows=50 width=12) + Select Operator [SEL_158] (rows=50 width=4) Output:["_col0"] Filter Operator [FIL_157] (rows=50 width=12) predicate:((d_moy = 11) and (d_year = 1999) and d_date_sk is not null) @@ -166,7 +166,7 @@ Stage-0 <-Map 9 [SIMPLE_EDGE] vectorized SHUFFLE [RS_153] PartitionCols:_col0 - Select Operator [SEL_152] (rows=8000000 width=116) + Select Operator [SEL_152] (rows=8000000 width=4) Output:["_col0"] Filter Operator [FIL_151] (rows=8000000 width=112) predicate:((ca_gmt_offset = -7) and ca_address_sk is not null) diff --git ql/src/test/results/clientpositive/perf/tez/query92.q.out ql/src/test/results/clientpositive/perf/tez/query92.q.out index 50918f0966c..1f837ddf5b8 100644 --- ql/src/test/results/clientpositive/perf/tez/query92.q.out +++ ql/src/test/results/clientpositive/perf/tez/query92.q.out @@ -104,9 +104,9 @@ Stage-0 Select Operator [SEL_34] (rows=2478 width=112) Output:["_col2"] Filter Operator [FIL_33] (rows=2478 width=112) - predicate:(_col2 > CAST( (1.3 * _col6) AS decimal(14,7))) + predicate:(_col2 > _col5) Merge Join Operator [MERGEJOIN_107] (rows=7434 width=112) - Conds:RS_30._col1=RS_31._col2(Inner),Output:["_col2","_col6"] + Conds:RS_30._col1=RS_31._col2(Inner),Output:["_col2","_col5"] <-Reducer 2 [SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_30] PartitionCols:_col1 @@ -115,7 +115,7 @@ Stage-0 <-Map 7 [SIMPLE_EDGE] vectorized SHUFFLE [RS_110] PartitionCols:_col0 - Select Operator [SEL_109] (rows=8116 width=98) + Select Operator [SEL_109] (rows=8116 width=4) Output:["_col0"] Filter Operator [FIL_108] (rows=8116 width=98) predicate:(CAST( d_date AS TIMESTAMP) BETWEEN TIMESTAMP'1998-03-18 00:00:00' AND TIMESTAMP'1998-06-16 00:00:00' and d_date_sk is not null) @@ -140,7 +140,7 @@ Stage-0 Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] Select Operator [SEL_123] (rows=669 width=4) Output:["_col0"] - Select Operator [SEL_121] (rows=669 width=8) + Select Operator [SEL_121] (rows=669 width=4) Output:["_col0"] Filter Operator [FIL_120] (rows=669 width=7) predicate:((i_manufact_id = 269) and i_item_sk is not null) diff --git ql/src/test/results/clientpositive/perf/tez/query93.q.out ql/src/test/results/clientpositive/perf/tez/query93.q.out index 2891fccb3f5..45e6e9fa13f 100644 --- ql/src/test/results/clientpositive/perf/tez/query93.q.out +++ ql/src/test/results/clientpositive/perf/tez/query93.q.out @@ -68,22 +68,22 @@ Stage-0 <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_18] PartitionCols:_col0 - Group By Operator [GBY_17] (rows=38308 width=112) + Group By Operator [GBY_17] (rows=306464 width=112) Output:["_col0","_col1"],aggregations:["sum(_col1)"],keys:_col0 - Select Operator [SEL_15] (rows=15586502 width=3) + Select Operator [SEL_15] (rows=15586502 width=119) Output:["_col0","_col1"] - Merge Join Operator [MERGEJOIN_64] (rows=15586502 width=3) - Conds:RS_12._col0, _col2=RS_77._col0, _col2(Inner),Output:["_col3","_col7","_col9","_col10"] + Merge Join Operator [MERGEJOIN_64] (rows=15586502 width=119) + Conds:RS_12._col0, _col2=RS_77._col0, _col2(Inner),Output:["_col3","_col4","_col7","_col9","_col10","_col11"] <-Reducer 2 [SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_12] PartitionCols:_col0, _col2 - Merge Join Operator [MERGEJOIN_63] (rows=1522298 width=8) - Conds:RS_67._col1=RS_70._col0(Inner),Output:["_col0","_col2","_col3"] + Merge Join Operator [MERGEJOIN_63] (rows=1522298 width=12) + Conds:RS_67._col1=RS_70._col0(Inner),Output:["_col0","_col2","_col3","_col4"] <-Map 1 [SIMPLE_EDGE] vectorized SHUFFLE [RS_67] PartitionCols:_col1 - Select Operator [SEL_66] (rows=55574563 width=15) - Output:["_col0","_col1","_col2","_col3"] + Select Operator [SEL_66] (rows=55574563 width=19) + Output:["_col0","_col1","_col2","_col3","_col4"] Filter Operator [FIL_65] (rows=55574563 width=15) predicate:(sr_item_sk is not null and sr_reason_sk is not null and sr_ticket_number is not null) TableScan [TS_0] (rows=57591150 width=15) @@ -91,7 +91,7 @@ Stage-0 <-Map 8 [SIMPLE_EDGE] vectorized SHUFFLE [RS_70] PartitionCols:_col0 - Select Operator [SEL_69] (rows=1 width=113) + Select Operator [SEL_69] (rows=1 width=4) Output:["_col0"] Filter Operator [FIL_68] (rows=1 width=101) predicate:((r_reason_desc = 'Did not like the warranty') and r_reason_sk is not null) @@ -100,8 +100,8 @@ Stage-0 <-Map 9 [SIMPLE_EDGE] vectorized SHUFFLE [RS_77] PartitionCols:_col0, _col2 - Select Operator [SEL_76] (rows=575995635 width=122) - Output:["_col0","_col1","_col2","_col3","_col4"] + Select Operator [SEL_76] (rows=575995635 width=234) + Output:["_col0","_col1","_col2","_col3","_col4","_col5"] Filter Operator [FIL_75] (rows=575995635 width=122) predicate:((ss_item_sk BETWEEN DynamicValue(RS_12_store_returns_sr_item_sk_min) AND DynamicValue(RS_12_store_returns_sr_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_12_store_returns_sr_item_sk_bloom_filter))) and (ss_ticket_number BETWEEN DynamicValue(RS_12_store_returns_sr_ticket_number_min) AND DynamicValue(RS_12_store_returns_sr_ticket_number_max) and in_bloom_filter(ss_ticket_number, DynamicValue(RS_12_store_returns_sr_ticket_number_bloom_filter))) and ss_item_sk is not null and ss_ticket_number is not null) TableScan [TS_6] (rows=575995635 width=122) diff --git ql/src/test/results/clientpositive/perf/tez/query95.q.out ql/src/test/results/clientpositive/perf/tez/query95.q.out index 49e8e868c68..885e67012e1 100644 --- ql/src/test/results/clientpositive/perf/tez/query95.q.out +++ ql/src/test/results/clientpositive/perf/tez/query95.q.out @@ -141,7 +141,7 @@ Stage-0 <-Map 16 [SIMPLE_EDGE] vectorized SHUFFLE [RS_260] PartitionCols:_col0 - Select Operator [SEL_259] (rows=12 width=91) + Select Operator [SEL_259] (rows=12 width=4) Output:["_col0"] Filter Operator [FIL_258] (rows=12 width=92) predicate:((web_company_name = 'pri') and web_site_sk is not null) @@ -155,7 +155,7 @@ Stage-0 <-Map 14 [SIMPLE_EDGE] vectorized SHUFFLE [RS_252] PartitionCols:_col0 - Select Operator [SEL_251] (rows=784314 width=90) + Select Operator [SEL_251] (rows=784314 width=4) Output:["_col0"] Filter Operator [FIL_250] (rows=784314 width=90) predicate:((ca_state = 'TX') and ca_address_sk is not null) diff --git ql/src/test/results/clientpositive/perf/tez/query96.q.out ql/src/test/results/clientpositive/perf/tez/query96.q.out index d06ad6a611d..0c80233dcee 100644 --- ql/src/test/results/clientpositive/perf/tez/query96.q.out +++ ql/src/test/results/clientpositive/perf/tez/query96.q.out @@ -76,7 +76,7 @@ Stage-0 <-Map 11 [SIMPLE_EDGE] vectorized SHUFFLE [RS_95] PartitionCols:_col0 - Select Operator [SEL_94] (rows=155 width=91) + Select Operator [SEL_94] (rows=155 width=4) Output:["_col0"] Filter Operator [FIL_93] (rows=155 width=92) predicate:((s_store_name = 'ese') and s_store_sk is not null) @@ -90,7 +90,7 @@ Stage-0 <-Map 9 [SIMPLE_EDGE] vectorized SHUFFLE [RS_87] PartitionCols:_col0 - Select Operator [SEL_86] (rows=655 width=8) + Select Operator [SEL_86] (rows=655 width=4) Output:["_col0"] Filter Operator [FIL_85] (rows=655 width=8) predicate:((hd_dep_count = 5) and hd_demo_sk is not null) @@ -104,7 +104,7 @@ Stage-0 <-Map 7 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_79] PartitionCols:_col0 - Select Operator [SEL_78] (rows=1515 width=12) + Select Operator [SEL_78] (rows=1515 width=4) Output:["_col0"] Filter Operator [FIL_77] (rows=1515 width=12) predicate:((t_hour = 8) and (t_minute >= 30) and t_time_sk is not null) diff --git ql/src/test/results/clientpositive/perf/tez/query97.q.out ql/src/test/results/clientpositive/perf/tez/query97.q.out index 21daca3aed0..8cd15fb1a2b 100644 --- ql/src/test/results/clientpositive/perf/tez/query97.q.out +++ ql/src/test/results/clientpositive/perf/tez/query97.q.out @@ -101,7 +101,7 @@ Stage-0 <-Map 6 [SIMPLE_EDGE] vectorized SHUFFLE [RS_72] PartitionCols:_col0 - Select Operator [SEL_71] (rows=317 width=8) + Select Operator [SEL_71] (rows=317 width=4) Output:["_col0"] Filter Operator [FIL_70] (rows=317 width=8) predicate:(d_date_sk is not null and d_month_seq BETWEEN 1212 AND 1223) diff --git ql/src/test/results/clientpositive/perf/tez/query98.q.out ql/src/test/results/clientpositive/perf/tez/query98.q.out index 8403d20e704..5be1e37ec4d 100644 --- ql/src/test/results/clientpositive/perf/tez/query98.q.out +++ ql/src/test/results/clientpositive/perf/tez/query98.q.out @@ -105,9 +105,9 @@ Stage-0 SHUFFLE [RS_17] PartitionCols:_col0, _col1, _col2, _col3, _col4 Group By Operator [GBY_16] (rows=138600 width=689) - Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(_col2)"],keys:_col10, _col9, _col6, _col7, _col8 + Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(_col2)"],keys:_col9, _col8, _col5, _col6, _col7 Merge Join Operator [MERGEJOIN_57] (rows=18334631 width=577) - Conds:RS_12._col1=RS_68._col0(Inner),Output:["_col2","_col6","_col7","_col8","_col9","_col10"] + Conds:RS_12._col1=RS_68._col0(Inner),Output:["_col2","_col5","_col6","_col7","_col8","_col9"] <-Map 9 [SIMPLE_EDGE] vectorized SHUFFLE [RS_68] PartitionCols:_col0 @@ -125,7 +125,7 @@ Stage-0 <-Map 7 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_60] PartitionCols:_col0 - Select Operator [SEL_59] (rows=8116 width=98) + Select Operator [SEL_59] (rows=8116 width=4) Output:["_col0"] Filter Operator [FIL_58] (rows=8116 width=98) predicate:(CAST( d_date AS TIMESTAMP) BETWEEN TIMESTAMP'2001-01-12 00:00:00' AND TIMESTAMP'2001-02-11 00:00:00' and d_date_sk is not null) diff --git ql/src/test/results/clientpositive/perf/tez/query99.q.out ql/src/test/results/clientpositive/perf/tez/query99.q.out index 745c5a9c4b0..0d9d1f86b87 100644 --- ql/src/test/results/clientpositive/perf/tez/query99.q.out +++ ql/src/test/results/clientpositive/perf/tez/query99.q.out @@ -96,108 +96,106 @@ Stage-0 limit:-1 Stage-1 Reducer 7 vectorized - File Output Operator [FS_132] - Limit [LIM_131] (rows=100 width=590) + File Output Operator [FS_131] + Limit [LIM_130] (rows=100 width=590) Number of rows:100 - Select Operator [SEL_130] (rows=3869553 width=590) + Select Operator [SEL_129] (rows=3869553 width=590) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] <-Reducer 6 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_129] - Select Operator [SEL_128] (rows=3869553 width=590) + SHUFFLE [RS_128] + Select Operator [SEL_127] (rows=3869553 width=590) Output:["_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"] - Group By Operator [GBY_127] (rows=3869553 width=406) + Group By Operator [GBY_126] (rows=3869553 width=406) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)","sum(VALUE._col3)","sum(VALUE._col4)"],keys:KEY._col0, KEY._col1, KEY._col2 <-Reducer 5 [SIMPLE_EDGE] - SHUFFLE [RS_30] + SHUFFLE [RS_29] PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_29] (rows=7739106 width=406) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"],aggregations:["sum(_col3)","sum(_col4)","sum(_col5)","sum(_col6)","sum(_col7)"],keys:_col0, _col1, _col2 - Top N Key Operator [TNK_57] (rows=15478212 width=289) - keys:_col0, _col1, _col2,sort order:+++,top n:100 - Select Operator [SEL_27] (rows=15478212 width=289) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] - Merge Join Operator [MERGEJOIN_101] (rows=15478212 width=289) - Conds:RS_24._col3=RS_112._col0(Inner),Output:["_col0","_col1","_col8","_col10","_col12"] - <-Map 12 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_112] - PartitionCols:_col0 - Select Operator [SEL_111] (rows=1 width=88) - Output:["_col0","_col1"] - Filter Operator [FIL_110] (rows=1 width=88) - predicate:sm_ship_mode_sk is not null - TableScan [TS_12] (rows=1 width=88) - default@ship_mode,ship_mode,Tbl:COMPLETE,Col:COMPLETE,Output:["sm_ship_mode_sk","sm_type"] - <-Reducer 4 [SIMPLE_EDGE] - SHUFFLE [RS_24] - PartitionCols:_col3 - Merge Join Operator [MERGEJOIN_100] (rows=46434637 width=209) - Conds:RS_21._col4=RS_126._col0(Inner),Output:["_col0","_col1","_col3","_col8","_col10"] - <-Map 11 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_126] - PartitionCols:_col0 - Select Operator [SEL_125] (rows=27 width=104) - Output:["_col0","_col1"] - Filter Operator [FIL_124] (rows=27 width=104) - predicate:w_warehouse_sk is not null - TableScan [TS_9] (rows=27 width=104) - default@warehouse,warehouse,Tbl:COMPLETE,Col:COMPLETE,Output:["w_warehouse_sk","w_warehouse_name"] - <-Reducer 3 [SIMPLE_EDGE] - SHUFFLE [RS_21] - PartitionCols:_col4 - Merge Join Operator [MERGEJOIN_99] (rows=46434637 width=113) - Conds:RS_18._col2=RS_123._col0(Inner),Output:["_col0","_col1","_col3","_col4","_col8"] - <-Map 10 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_123] - PartitionCols:_col0 - Select Operator [SEL_122] (rows=60 width=102) - Output:["_col0","_col1"] - Filter Operator [FIL_121] (rows=60 width=102) - predicate:cc_call_center_sk is not null - TableScan [TS_6] (rows=60 width=102) - default@call_center,call_center,Tbl:COMPLETE,Col:COMPLETE,Output:["cc_call_center_sk","cc_name"] - <-Reducer 2 [SIMPLE_EDGE] - SHUFFLE [RS_18] - PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_98] (rows=46434637 width=19) - Conds:RS_120._col1=RS_104._col0(Inner),Output:["_col0","_col1","_col2","_col3","_col4"] - <-Map 8 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_104] - PartitionCols:_col0 - Select Operator [SEL_103] (rows=317 width=8) - Output:["_col0"] - Filter Operator [FIL_102] (rows=317 width=8) - predicate:(d_date_sk is not null and d_month_seq BETWEEN 1212 AND 1223) - TableScan [TS_3] (rows=73049 width=8) - default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_month_seq"] - <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_120] - PartitionCols:_col1 - Select Operator [SEL_119] (rows=282273729 width=19) - Output:["_col0","_col1","_col2","_col3","_col4"] - Filter Operator [FIL_118] (rows=282273729 width=19) - predicate:((cs_ship_date_sk BETWEEN DynamicValue(RS_16_date_dim_d_date_sk_min) AND DynamicValue(RS_16_date_dim_d_date_sk_max) and in_bloom_filter(cs_ship_date_sk, DynamicValue(RS_16_date_dim_d_date_sk_bloom_filter))) and (cs_ship_mode_sk BETWEEN DynamicValue(RS_25_ship_mode_sm_ship_mode_sk_min) AND DynamicValue(RS_25_ship_mode_sm_ship_mode_sk_max) and in_bloom_filter(cs_ship_mode_sk, DynamicValue(RS_25_ship_mode_sm_ship_mode_sk_bloom_filter))) and cs_call_center_sk is not null and cs_ship_date_sk is not null and cs_ship_mode_sk is not null and cs_warehouse_sk is not null) - TableScan [TS_0] (rows=287989836 width=19) - default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["cs_sold_date_sk","cs_ship_date_sk","cs_call_center_sk","cs_ship_mode_sk","cs_warehouse_sk"] - <-Reducer 13 [BROADCAST_EDGE] vectorized - BROADCAST [RS_117] - Group By Operator [GBY_116] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 12 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_115] - Group By Operator [GBY_114] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_113] (rows=1 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_111] - <-Reducer 9 [BROADCAST_EDGE] vectorized - BROADCAST [RS_109] - Group By Operator [GBY_108] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 8 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_107] - Group By Operator [GBY_106] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_105] (rows=317 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_103] + Group By Operator [GBY_28] (rows=7739106 width=406) + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"],aggregations:["sum(_col4)","sum(_col5)","sum(_col6)","sum(_col7)","sum(_col8)"],keys:_col13, _col15, _col11 + Top N Key Operator [TNK_56] (rows=15478212 width=386) + keys:_col13, _col15, _col11,sort order:+++,top n:100 + Merge Join Operator [MERGEJOIN_100] (rows=15478212 width=386) + Conds:RS_24._col2=RS_111._col0(Inner),Output:["_col4","_col5","_col6","_col7","_col8","_col11","_col13","_col15"] + <-Map 12 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_111] + PartitionCols:_col0 + Select Operator [SEL_110] (rows=1 width=88) + Output:["_col0","_col1"] + Filter Operator [FIL_109] (rows=1 width=88) + predicate:sm_ship_mode_sk is not null + TableScan [TS_12] (rows=1 width=88) + default@ship_mode,ship_mode,Tbl:COMPLETE,Col:COMPLETE,Output:["sm_ship_mode_sk","sm_type"] + <-Reducer 4 [SIMPLE_EDGE] + SHUFFLE [RS_24] + PartitionCols:_col2 + Merge Join Operator [MERGEJOIN_99] (rows=46434637 width=305) + Conds:RS_21._col3=RS_125._col0(Inner),Output:["_col2","_col4","_col5","_col6","_col7","_col8","_col11","_col13"] + <-Map 11 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_125] + PartitionCols:_col0 + Select Operator [SEL_124] (rows=27 width=188) + Output:["_col0","_col1"] + Filter Operator [FIL_123] (rows=27 width=104) + predicate:w_warehouse_sk is not null + TableScan [TS_9] (rows=27 width=104) + default@warehouse,warehouse,Tbl:COMPLETE,Col:COMPLETE,Output:["w_warehouse_sk","w_warehouse_name"] + <-Reducer 3 [SIMPLE_EDGE] + SHUFFLE [RS_21] + PartitionCols:_col3 + Merge Join Operator [MERGEJOIN_98] (rows=46434637 width=125) + Conds:RS_18._col1=RS_122._col0(Inner),Output:["_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col11"] + <-Map 10 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_122] + PartitionCols:_col0 + Select Operator [SEL_121] (rows=60 width=102) + Output:["_col0","_col1"] + Filter Operator [FIL_120] (rows=60 width=102) + predicate:cc_call_center_sk is not null + TableScan [TS_6] (rows=60 width=102) + default@call_center,call_center,Tbl:COMPLETE,Col:COMPLETE,Output:["cc_call_center_sk","cc_name"] + <-Reducer 2 [SIMPLE_EDGE] + SHUFFLE [RS_18] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_97] (rows=46434637 width=31) + Conds:RS_119._col0=RS_103._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"] + <-Map 8 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_103] + PartitionCols:_col0 + Select Operator [SEL_102] (rows=317 width=4) + Output:["_col0"] + Filter Operator [FIL_101] (rows=317 width=8) + predicate:(d_date_sk is not null and d_month_seq BETWEEN 1212 AND 1223) + TableScan [TS_3] (rows=73049 width=8) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_month_seq"] + <-Map 1 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_119] + PartitionCols:_col0 + Select Operator [SEL_118] (rows=282273729 width=35) + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"] + Filter Operator [FIL_117] (rows=282273729 width=19) + predicate:((cs_ship_date_sk BETWEEN DynamicValue(RS_16_date_dim_d_date_sk_min) AND DynamicValue(RS_16_date_dim_d_date_sk_max) and in_bloom_filter(cs_ship_date_sk, DynamicValue(RS_16_date_dim_d_date_sk_bloom_filter))) and (cs_ship_mode_sk BETWEEN DynamicValue(RS_25_ship_mode_sm_ship_mode_sk_min) AND DynamicValue(RS_25_ship_mode_sm_ship_mode_sk_max) and in_bloom_filter(cs_ship_mode_sk, DynamicValue(RS_25_ship_mode_sm_ship_mode_sk_bloom_filter))) and cs_call_center_sk is not null and cs_ship_date_sk is not null and cs_ship_mode_sk is not null and cs_warehouse_sk is not null) + TableScan [TS_0] (rows=287989836 width=19) + default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["cs_sold_date_sk","cs_ship_date_sk","cs_call_center_sk","cs_ship_mode_sk","cs_warehouse_sk"] + <-Reducer 13 [BROADCAST_EDGE] vectorized + BROADCAST [RS_116] + Group By Operator [GBY_115] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 12 [CUSTOM_SIMPLE_EDGE] vectorized + SHUFFLE [RS_114] + Group By Operator [GBY_113] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_112] (rows=1 width=4) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_110] + <-Reducer 9 [BROADCAST_EDGE] vectorized + BROADCAST [RS_108] + Group By Operator [GBY_107] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 8 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_106] + Group By Operator [GBY_105] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_104] (rows=317 width=4) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_102]