diff --git a/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/stats/HiveRelMdRowCount.java b/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/stats/HiveRelMdRowCount.java index 563260e415..a9f5f32a35 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/stats/HiveRelMdRowCount.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/stats/HiveRelMdRowCount.java @@ -57,6 +57,7 @@ protected static final Logger LOG = LoggerFactory.getLogger(HiveRelMdRowCount.class.getName()); + private static final Long HIVE_PK_FK_NO_FILTERING_COST_INCREASING_FACTOR = 1000000000000000L; public static final RelMetadataProvider SOURCE = ReflectiveRelMetadataProvider .reflectiveSource(BuiltInMethod.ROW_COUNT.method, new HiveRelMdRowCount()); @@ -75,7 +76,12 @@ public Double getRowCount(Join join, RelMetadataQuery mq) { double joinSelectivity = Math.min(1.0, constraintBasedResult.left.pkInfo.selectivity * constraintBasedResult.left.ndvScalingFactor); double residualSelectivity = RelMdUtil.guessSelectivity(constraintBasedResult.right); - double rowCount = constraintBasedResult.left.fkInfo.rowCount * joinSelectivity * residualSelectivity; + double rowCount; + if (constraintBasedResult.left.isPKSideSimple) { + rowCount = constraintBasedResult.left.pkInfo.rowCount + HIVE_PK_FK_NO_FILTERING_COST_INCREASING_FACTOR; + } else { + rowCount = constraintBasedResult.left.fkInfo.rowCount * joinSelectivity * residualSelectivity; + } if (LOG.isDebugEnabled()) { LOG.debug("Identified Primary - Foreign Key relation from constraints:\n {} {} Row count for join: {}\n" + " Join selectivity: {}\n Residual selectivity: {}\n", RelOptUtil.toString(join), constraintBasedResult.left, @@ -274,8 +280,8 @@ public static PKFKRelationInfo analyzeJoinForPKFK(Join joinRel, RelMetadataQuery } int pkSide = leftIsKey ? 0 : 1; - boolean isPKSideSimpleTree = leftIsKey ? SimpleTreeOnJoinKey.check(false, left, lBitSet, mq) : - SimpleTreeOnJoinKey.check(false, right, rBitSet, mq); + boolean isPKSideSimpleTree = leftIsKey ? SimpleTreeOnJoinKey.check(false, left, lBitSet, mq).left : + SimpleTreeOnJoinKey.check(false, right, rBitSet, mq).left; double leftNDV = isPKSideSimpleTree ? mq.getDistinctRowCount(left, lBitSet, leftPred) : -1; double rightNDV = isPKSideSimpleTree ? mq.getDistinctRowCount(right, rBitSet, rightPred) : -1; @@ -389,8 +395,10 @@ public static PKFKRelationInfo analyzeJoinForPKFK(Join joinRel, RelMetadataQuery // 4) Extract additional information on the PK-FK relationship int pkSide = leftIsKey ? 0 : 1; - boolean isPKSideSimpleTree = leftIsKey ? SimpleTreeOnJoinKey.check(true, left, lBitSet, mq) : + Pair simpleTree = leftIsKey ? SimpleTreeOnJoinKey.check(true, left, lBitSet, mq) : SimpleTreeOnJoinKey.check(true, right, rBitSet, mq); + boolean isPKSideSimpleTree = simpleTree.left; + boolean isNoFilteringPKSideTree = simpleTree.right; RexBuilder rexBuilder = join.getCluster().getRexBuilder(); RexNode leftPred = RexUtil.composeConjunction( rexBuilder, leftFilters, true); @@ -415,10 +423,7 @@ public static PKFKRelationInfo analyzeJoinForPKFK(Join joinRel, RelMetadataQuery join.getJoinType().generatesNullsOnRight() ? 1.0 : pkSelectivity); double ndvScalingFactor = isPKSideSimpleTree ? leftNDV/rightNDV : 1.0; - if (isPKSideSimpleTree) { - ndvScalingFactor = leftNDV/rightNDV; - } - return Pair.of(new PKFKRelationInfo(1, fkInfo, pkInfo, ndvScalingFactor, isPKSideSimpleTree), + return Pair.of(new PKFKRelationInfo(1, fkInfo, pkInfo, ndvScalingFactor, isNoFilteringPKSideTree), residualCond); } else { // pkSide == 1 FKSideInfo fkInfo = new FKSideInfo(leftRowCount, @@ -429,7 +434,7 @@ public static PKFKRelationInfo analyzeJoinForPKFK(Join joinRel, RelMetadataQuery join.getJoinType().generatesNullsOnLeft() ? 1.0 : pkSelectivity); double ndvScalingFactor = isPKSideSimpleTree ? rightNDV/leftNDV : 1.0; - return Pair.of(new PKFKRelationInfo(0, fkInfo, pkInfo, ndvScalingFactor, isPKSideSimpleTree), + return Pair.of(new PKFKRelationInfo(0, fkInfo, pkInfo, ndvScalingFactor, isNoFilteringPKSideTree), residualCond); } } @@ -531,12 +536,13 @@ private static boolean isKey(ImmutableBitSet c, RelNode rel, RelMetadataQuery mq boolean constraintsBased; ImmutableBitSet joinKey; boolean simpleTree; + boolean nonFilteringTree; RelMetadataQuery mq; - static boolean check(boolean constraintsBased, RelNode r, ImmutableBitSet joinKey, RelMetadataQuery mq) { + static Pair check(boolean constraintsBased, RelNode r, ImmutableBitSet joinKey, RelMetadataQuery mq) { SimpleTreeOnJoinKey v = new SimpleTreeOnJoinKey(constraintsBased, joinKey, mq); v.go(r); - return v.simpleTree; + return Pair.of(v.simpleTree, v.nonFilteringTree); } SimpleTreeOnJoinKey(boolean constraintsBased, ImmutableBitSet joinKey, RelMetadataQuery mq) { @@ -545,6 +551,7 @@ static boolean check(boolean constraintsBased, RelNode r, ImmutableBitSet joinKe this.joinKey = joinKey; this.mq = mq; simpleTree = true; + nonFilteringTree = true; } @Override @@ -558,10 +565,13 @@ public void visit(RelNode node, int ordinal, RelNode parent) { simpleTree = true; } else if (node instanceof Project) { simpleTree = isSimple((Project) node); + nonFilteringTree &= simpleTree; } else if (node instanceof Filter) { simpleTree = isSimple((Filter) node, mq); + nonFilteringTree = false; } else { simpleTree = false; + nonFilteringTree = false; } if (simpleTree) { diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query11.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query11.q.out index 24bd6fdec2..f315e3c455 100644 --- a/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query11.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query11.q.out @@ -159,7 +159,7 @@ 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($9, >(/($4, $8), /($2, $6)), >(null, /($2, $6))), CASE($9, >(/($4, $8), null), null)))], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[AND(=($0, $8), CASE(CAST(IS NOT NULL($9)):BOOLEAN, CASE($7, >(/($4, $6), /($2, $9)), >(null, /($2, $9))), CASE($7, >(/($4, $6), null), null)))], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject($f0=[$0], $f4=[$3], $f9=[$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]) @@ -172,20 +172,33 @@ HiveSortLimit(sort0=[$0], dir0=[ASC], fetch=[100]) HiveProject(d_date_sk=[$0]) HiveFilter(condition=[=($6, 2002)]) 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=[{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]) - 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=[=($6, 2002)]) - HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) + HiveJoin(condition=[=($5, $0)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject($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]) + 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=[=($6, 2002)]) + HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) + HiveJoin(condition=[=($3, $0)], joinType=[inner], algorithm=[none], cost=[not available]) + 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]) + 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=[=($6, 2001)]) + HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) HiveProject($f0=[$0], $f9=[$7]) HiveFilter(condition=[>($7, 0)]) HiveAggregate(group=[{1, 2, 3, 4, 5, 6, 7}], agg#0=[sum($10)]) @@ -199,17 +212,4 @@ HiveSortLimit(sort0=[$0], dir0=[ASC], fetch=[100]) HiveProject(d_date_sk=[$0]) HiveFilter(condition=[=($6, 2001)]) 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]) - 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=[=($6, 2001)]) - HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query14.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query14.q.out index 457cdce755..9abcb05bfa 100644 --- a/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query14.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query14.q.out @@ -1,9 +1,9 @@ -Warning: Shuffle Join MERGEJOIN[1431][tables = [$hdt$_1, $hdt$_2]] in Stage 'Reducer 5' is a cross product -Warning: Shuffle Join MERGEJOIN[1443][tables = [$hdt$_1, $hdt$_2, $hdt$_0]] in Stage 'Reducer 6' is a cross product -Warning: Shuffle Join MERGEJOIN[1433][tables = [$hdt$_1, $hdt$_2]] in Stage 'Reducer 13' is a cross product -Warning: Shuffle Join MERGEJOIN[1456][tables = [$hdt$_1, $hdt$_2, $hdt$_0]] in Stage 'Reducer 14' is a cross product -Warning: Shuffle Join MERGEJOIN[1435][tables = [$hdt$_2, $hdt$_3]] in Stage 'Reducer 18' is a cross product -Warning: Shuffle Join MERGEJOIN[1469][tables = [$hdt$_2, $hdt$_3, $hdt$_1]] in Stage 'Reducer 19' is a cross product +Warning: Shuffle Join MERGEJOIN[1458][tables = [$hdt$_1, $hdt$_2]] in Stage 'Reducer 5' is a cross product +Warning: Shuffle Join MERGEJOIN[1470][tables = [$hdt$_1, $hdt$_2, $hdt$_0]] in Stage 'Reducer 6' is a cross product +Warning: Shuffle Join MERGEJOIN[1460][tables = [$hdt$_1, $hdt$_2]] in Stage 'Reducer 13' is a cross product +Warning: Shuffle Join MERGEJOIN[1483][tables = [$hdt$_1, $hdt$_2, $hdt$_0]] in Stage 'Reducer 14' is a cross product +Warning: Shuffle Join MERGEJOIN[1462][tables = [$hdt$_2, $hdt$_3]] in Stage 'Reducer 18' is a cross product +Warning: Shuffle Join MERGEJOIN[1496][tables = [$hdt$_2, $hdt$_3, $hdt$_1]] in Stage 'Reducer 19' is a cross product PREHOOK: query: explain cbo with cross_items as (select i_item_sk ss_item_sk @@ -232,60 +232,60 @@ HiveSortLimit(sort0=[$0], sort1=[$1], sort2=[$2], sort3=[$3], dir0=[ASC], dir1=[ HiveJoin(condition=[>($3, $6)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject($f0=[$0], $f1=[$1], $f2=[$2], $f3=[$3], $f4=[$4]) HiveAggregate(group=[{0, 1, 2}], agg#0=[sum($3)], agg#1=[count()]) - HiveProject($f0=[$2], $f1=[$3], $f2=[$4], $f3=[*(CAST($7):DECIMAL(10, 0), $8)]) + HiveProject($f0=[$1], $f1=[$2], $f2=[$3], $f3=[*(CAST($7):DECIMAL(10, 0), $8)]) HiveJoin(condition=[=($6, $0)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(ss_item_sk=[$0]) - HiveJoin(condition=[AND(AND(=($1, $4), =($2, $5)), =($3, $6))], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(i_item_sk=[$0], i_brand_id=[$7], i_class_id=[$9], i_category_id=[$11]) - HiveFilter(condition=[AND(IS NOT NULL($7), IS NOT NULL($9), IS NOT NULL($11))]) - HiveTableScan(table=[[default, item]], table:alias=[item]) - HiveProject($f0=[$0], $f1=[$1], $f2=[$2]) - HiveFilter(condition=[=($3, 3)]) - HiveAggregate(group=[{0, 1, 2}], agg#0=[count($3)]) - 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=[{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=[IS NOT NULL($0)]) - HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) - HiveProject(d_date_sk=[$0]) - HiveFilter(condition=[BETWEEN(false, $6, 1999, 2001)]) - 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($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=[{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=[IS NOT NULL($0)]) - HiveTableScan(table=[[default, catalog_sales]], table:alias=[catalog_sales]) - HiveProject(d_date_sk=[$0]) - HiveFilter(condition=[BETWEEN(false, $6, 1999, 2001)]) - 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($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=[{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=[IS NOT NULL($0)]) - HiveTableScan(table=[[default, web_sales]], table:alias=[web_sales]) - HiveProject(d_date_sk=[$0]) - HiveFilter(condition=[BETWEEN(false, $6, 1999, 2001)]) - 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]) - HiveFilter(condition=[AND(IS NOT NULL($7), IS NOT NULL($9), IS NOT NULL($11))]) - HiveTableScan(table=[[default, item]], table:alias=[iws]) - HiveJoin(condition=[=($5, $0)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(i_item_sk=[$0], i_brand_id=[$7], i_class_id=[$9], i_category_id=[$11]) - HiveTableScan(table=[[default, item]], table:alias=[item]) + HiveProject(i_item_sk=[$0], i_brand_id=[$7], i_class_id=[$9], i_category_id=[$11]) + HiveTableScan(table=[[default, item]], table:alias=[item]) + HiveJoin(condition=[=($2, $0)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(ss_item_sk=[$0]) + HiveJoin(condition=[AND(AND(=($1, $4), =($2, $5)), =($3, $6))], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(i_item_sk=[$0], i_brand_id=[$7], i_class_id=[$9], i_category_id=[$11]) + HiveFilter(condition=[AND(IS NOT NULL($7), IS NOT NULL($9), IS NOT NULL($11))]) + HiveTableScan(table=[[default, item]], table:alias=[item]) + HiveProject($f0=[$0], $f1=[$1], $f2=[$2]) + HiveFilter(condition=[=($3, 3)]) + HiveAggregate(group=[{0, 1, 2}], agg#0=[count($3)]) + 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=[{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=[IS NOT NULL($0)]) + HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) + HiveProject(d_date_sk=[$0]) + HiveFilter(condition=[BETWEEN(false, $6, 1999, 2001)]) + 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($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=[{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=[IS NOT NULL($0)]) + HiveTableScan(table=[[default, catalog_sales]], table:alias=[catalog_sales]) + HiveProject(d_date_sk=[$0]) + HiveFilter(condition=[BETWEEN(false, $6, 1999, 2001)]) + 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($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=[{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=[IS NOT NULL($0)]) + HiveTableScan(table=[[default, web_sales]], table:alias=[web_sales]) + HiveProject(d_date_sk=[$0]) + HiveFilter(condition=[BETWEEN(false, $6, 1999, 2001)]) + 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]) + HiveFilter(condition=[AND(IS NOT NULL($7), IS NOT NULL($9), IS NOT NULL($11))]) + HiveTableScan(table=[[default, item]], table:alias=[iws]) HiveJoin(condition=[=($0, $4)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(ss_sold_date_sk=[$0], ss_item_sk=[$2], ss_quantity=[$10], ss_list_price=[$12]) HiveFilter(condition=[IS NOT NULL($0)]) @@ -359,60 +359,60 @@ HiveSortLimit(sort0=[$0], sort1=[$1], sort2=[$2], sort3=[$3], dir0=[ASC], dir1=[ HiveJoin(condition=[>($3, $6)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject($f0=[$0], $f1=[$1], $f2=[$2], $f3=[$3], $f4=[$4]) HiveAggregate(group=[{0, 1, 2}], agg#0=[sum($3)], agg#1=[count()]) - HiveProject($f0=[$2], $f1=[$3], $f2=[$4], $f3=[*(CAST($7):DECIMAL(10, 0), $8)]) + HiveProject($f0=[$1], $f1=[$2], $f2=[$3], $f3=[*(CAST($7):DECIMAL(10, 0), $8)]) HiveJoin(condition=[=($6, $0)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(ss_item_sk=[$0]) - HiveJoin(condition=[AND(AND(=($1, $4), =($2, $5)), =($3, $6))], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(i_item_sk=[$0], i_brand_id=[$7], i_class_id=[$9], i_category_id=[$11]) - HiveFilter(condition=[AND(IS NOT NULL($7), IS NOT NULL($9), IS NOT NULL($11))]) - HiveTableScan(table=[[default, item]], table:alias=[item]) - HiveProject($f0=[$0], $f1=[$1], $f2=[$2]) - HiveFilter(condition=[=($3, 3)]) - HiveAggregate(group=[{0, 1, 2}], agg#0=[count($3)]) - 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=[{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=[IS NOT NULL($0)]) - HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) - HiveProject(d_date_sk=[$0]) - HiveFilter(condition=[BETWEEN(false, $6, 1999, 2001)]) - 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($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=[{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=[IS NOT NULL($0)]) - HiveTableScan(table=[[default, catalog_sales]], table:alias=[catalog_sales]) - HiveProject(d_date_sk=[$0]) - HiveFilter(condition=[BETWEEN(false, $6, 1999, 2001)]) - 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($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=[{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=[IS NOT NULL($0)]) - HiveTableScan(table=[[default, web_sales]], table:alias=[web_sales]) - HiveProject(d_date_sk=[$0]) - HiveFilter(condition=[BETWEEN(false, $6, 1999, 2001)]) - 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]) - HiveFilter(condition=[AND(IS NOT NULL($7), IS NOT NULL($9), IS NOT NULL($11))]) - HiveTableScan(table=[[default, item]], table:alias=[iws]) - HiveJoin(condition=[=($5, $0)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(i_item_sk=[$0], i_brand_id=[$7], i_class_id=[$9], i_category_id=[$11]) - HiveTableScan(table=[[default, item]], table:alias=[item]) + HiveProject(i_item_sk=[$0], i_brand_id=[$7], i_class_id=[$9], i_category_id=[$11]) + HiveTableScan(table=[[default, item]], table:alias=[item]) + HiveJoin(condition=[=($2, $0)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(ss_item_sk=[$0]) + HiveJoin(condition=[AND(AND(=($1, $4), =($2, $5)), =($3, $6))], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(i_item_sk=[$0], i_brand_id=[$7], i_class_id=[$9], i_category_id=[$11]) + HiveFilter(condition=[AND(IS NOT NULL($7), IS NOT NULL($9), IS NOT NULL($11))]) + HiveTableScan(table=[[default, item]], table:alias=[item]) + HiveProject($f0=[$0], $f1=[$1], $f2=[$2]) + HiveFilter(condition=[=($3, 3)]) + HiveAggregate(group=[{0, 1, 2}], agg#0=[count($3)]) + 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=[{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=[IS NOT NULL($0)]) + HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) + HiveProject(d_date_sk=[$0]) + HiveFilter(condition=[BETWEEN(false, $6, 1999, 2001)]) + 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($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=[{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=[IS NOT NULL($0)]) + HiveTableScan(table=[[default, catalog_sales]], table:alias=[catalog_sales]) + HiveProject(d_date_sk=[$0]) + HiveFilter(condition=[BETWEEN(false, $6, 1999, 2001)]) + 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($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=[{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=[IS NOT NULL($0)]) + HiveTableScan(table=[[default, web_sales]], table:alias=[web_sales]) + HiveProject(d_date_sk=[$0]) + HiveFilter(condition=[BETWEEN(false, $6, 1999, 2001)]) + 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]) + HiveFilter(condition=[AND(IS NOT NULL($7), IS NOT NULL($9), IS NOT NULL($11))]) + HiveTableScan(table=[[default, item]], table:alias=[iws]) HiveJoin(condition=[=($0, $4)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(cs_sold_date_sk=[$0], cs_item_sk=[$15], cs_quantity=[$18], cs_list_price=[$20]) HiveFilter(condition=[IS NOT NULL($0)]) @@ -486,60 +486,60 @@ HiveSortLimit(sort0=[$0], sort1=[$1], sort2=[$2], sort3=[$3], dir0=[ASC], dir1=[ HiveJoin(condition=[>($3, $6)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject($f0=[$0], $f1=[$1], $f2=[$2], $f3=[$3], $f4=[$4]) HiveAggregate(group=[{0, 1, 2}], agg#0=[sum($3)], agg#1=[count()]) - HiveProject($f0=[$2], $f1=[$3], $f2=[$4], $f3=[*(CAST($7):DECIMAL(10, 0), $8)]) + HiveProject($f0=[$1], $f1=[$2], $f2=[$3], $f3=[*(CAST($7):DECIMAL(10, 0), $8)]) HiveJoin(condition=[=($6, $0)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(ss_item_sk=[$0]) - HiveJoin(condition=[AND(AND(=($1, $4), =($2, $5)), =($3, $6))], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(i_item_sk=[$0], i_brand_id=[$7], i_class_id=[$9], i_category_id=[$11]) - HiveFilter(condition=[AND(IS NOT NULL($7), IS NOT NULL($9), IS NOT NULL($11))]) - HiveTableScan(table=[[default, item]], table:alias=[item]) - HiveProject($f0=[$0], $f1=[$1], $f2=[$2]) - HiveFilter(condition=[=($3, 3)]) - HiveAggregate(group=[{0, 1, 2}], agg#0=[count($3)]) - 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=[{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=[IS NOT NULL($0)]) - HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) - HiveProject(d_date_sk=[$0]) - HiveFilter(condition=[BETWEEN(false, $6, 1999, 2001)]) - 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($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=[{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=[IS NOT NULL($0)]) - HiveTableScan(table=[[default, catalog_sales]], table:alias=[catalog_sales]) - HiveProject(d_date_sk=[$0]) - HiveFilter(condition=[BETWEEN(false, $6, 1999, 2001)]) - 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($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=[{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=[IS NOT NULL($0)]) - HiveTableScan(table=[[default, web_sales]], table:alias=[web_sales]) - HiveProject(d_date_sk=[$0]) - HiveFilter(condition=[BETWEEN(false, $6, 1999, 2001)]) - 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]) - HiveFilter(condition=[AND(IS NOT NULL($7), IS NOT NULL($9), IS NOT NULL($11))]) - HiveTableScan(table=[[default, item]], table:alias=[iws]) - HiveJoin(condition=[=($5, $0)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(i_item_sk=[$0], i_brand_id=[$7], i_class_id=[$9], i_category_id=[$11]) - HiveTableScan(table=[[default, item]], table:alias=[item]) + HiveProject(i_item_sk=[$0], i_brand_id=[$7], i_class_id=[$9], i_category_id=[$11]) + HiveTableScan(table=[[default, item]], table:alias=[item]) + HiveJoin(condition=[=($2, $0)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(ss_item_sk=[$0]) + HiveJoin(condition=[AND(AND(=($1, $4), =($2, $5)), =($3, $6))], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(i_item_sk=[$0], i_brand_id=[$7], i_class_id=[$9], i_category_id=[$11]) + HiveFilter(condition=[AND(IS NOT NULL($7), IS NOT NULL($9), IS NOT NULL($11))]) + HiveTableScan(table=[[default, item]], table:alias=[item]) + HiveProject($f0=[$0], $f1=[$1], $f2=[$2]) + HiveFilter(condition=[=($3, 3)]) + HiveAggregate(group=[{0, 1, 2}], agg#0=[count($3)]) + 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=[{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=[IS NOT NULL($0)]) + HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) + HiveProject(d_date_sk=[$0]) + HiveFilter(condition=[BETWEEN(false, $6, 1999, 2001)]) + 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($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=[{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=[IS NOT NULL($0)]) + HiveTableScan(table=[[default, catalog_sales]], table:alias=[catalog_sales]) + HiveProject(d_date_sk=[$0]) + HiveFilter(condition=[BETWEEN(false, $6, 1999, 2001)]) + 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($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=[{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=[IS NOT NULL($0)]) + HiveTableScan(table=[[default, web_sales]], table:alias=[web_sales]) + HiveProject(d_date_sk=[$0]) + HiveFilter(condition=[BETWEEN(false, $6, 1999, 2001)]) + 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]) + HiveFilter(condition=[AND(IS NOT NULL($7), IS NOT NULL($9), IS NOT NULL($11))]) + HiveTableScan(table=[[default, item]], table:alias=[iws]) HiveJoin(condition=[=($0, $4)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(ws_sold_date_sk=[$0], ws_item_sk=[$3], ws_quantity=[$18], ws_list_price=[$20]) HiveFilter(condition=[IS NOT NULL($0)]) diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query15.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query15.q.out index 32404b6209..0818355e00 100644 --- a/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query15.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query15.q.out @@ -49,15 +49,14 @@ POSTHOOK: Output: hdfs://### HDFS PATH ### CBO PLAN: HiveSortLimit(sort0=[$0], dir0=[ASC], fetch=[100]) HiveProject(ca_zip=[$0], $f1=[$1]) - HiveAggregate(group=[{3}], agg#0=[sum($8)]) - HiveJoin(condition=[AND(=($7, $0), OR($9, $4, $5))], joinType=[inner], algorithm=[none], cost=[not available]) - HiveJoin(condition=[=($1, $2)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveAggregate(group=[{1}], agg#0=[sum($8)]) + HiveJoin(condition=[AND(=($5, $0), OR($9, $2, $3))], joinType=[inner], algorithm=[none], cost=[not available]) + 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')]) + HiveTableScan(table=[[default, customer_address]], table:alias=[customer_address]) + HiveJoin(condition=[=($3, $0)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(c_customer_sk=[$0], c_current_addr_sk=[$4]) HiveFilter(condition=[IS NOT NULL($4)]) HiveTableScan(table=[[default, customer]], table:alias=[customer]) - 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')]) - HiveTableScan(table=[[default, customer_address]], table:alias=[customer_address]) - 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))]) diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query17.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query17.q.out index 3d190e3b68..120c8d28d1 100644 --- a/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query17.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query17.q.out @@ -104,20 +104,18 @@ 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=[$6], $f1=[$7], $f2=[$22], $f3=[$13], $f4=[$19], $f5=[$3], $f30=[CAST($13):DOUBLE], $f7=[*(CAST($13):DOUBLE, CAST($13):DOUBLE)], $f40=[CAST($19):DOUBLE], $f9=[*(CAST($19):DOUBLE, CAST($19):DOUBLE)], $f50=[CAST($3):DOUBLE], $f11=[*(CAST($3):DOUBLE, CAST($3):DOUBLE)]) - 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($0))]) - HiveTableScan(table=[[default, catalog_sales]], table:alias=[catalog_sales]) - HiveProject(d_date_sk=[$0]) - HiveFilter(condition=[IN($15, _UTF-16LE'2000Q1', _UTF-16LE'2000Q2', _UTF-16LE'2000Q3')]) - 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], 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_state=[$17]) - HiveJoin(condition=[=($0, $4)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(i_item_sk=[$0], i_item_id=[$1], i_item_desc=[$4]) - HiveTableScan(table=[[default, item]], table:alias=[item]) - HiveJoin(condition=[=($13, $3)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject($f0=[$21], $f1=[$22], $f2=[$19], $f3=[$10], $f4=[$16], $f5=[$3], $f30=[CAST($10):DOUBLE], $f7=[*(CAST($10):DOUBLE, CAST($10):DOUBLE)], $f40=[CAST($16):DOUBLE], $f9=[*(CAST($16):DOUBLE, CAST($16):DOUBLE)], $f50=[CAST($3):DOUBLE], $f11=[*(CAST($3):DOUBLE, CAST($3):DOUBLE)]) + HiveJoin(condition=[=($20, $6)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($18, $8)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[AND(=($14, $1), =($13, $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($0))]) + HiveTableScan(table=[[default, catalog_sales]], table:alias=[catalog_sales]) + HiveProject(d_date_sk=[$0]) + HiveFilter(condition=[IN($15, _UTF-16LE'2000Q1', _UTF-16LE'2000Q2', _UTF-16LE'2000Q3')]) + HiveTableScan(table=[[default, date_dim]], table:alias=[d3]) + HiveProject(ss_sold_date_sk=[$0], ss_item_sk=[$1], ss_customer_sk=[$2], ss_store_sk=[$3], ss_ticket_number=[$4], ss_quantity=[$5], d_date_sk=[$6], sr_returned_date_sk=[$7], sr_item_sk=[$8], sr_customer_sk=[$9], sr_ticket_number=[$10], sr_return_quantity=[$11], d_date_sk0=[$12]) 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]) @@ -134,6 +132,8 @@ HiveSortLimit(sort0=[$0], sort1=[$1], sort2=[$2], dir0=[ASC], dir1=[ASC], dir2=[ HiveProject(d_date_sk=[$0]) HiveFilter(condition=[IN($15, _UTF-16LE'2000Q1', _UTF-16LE'2000Q2', _UTF-16LE'2000Q3')]) HiveTableScan(table=[[default, date_dim]], table:alias=[d2]) - HiveProject(s_store_sk=[$0], s_state=[$24]) - HiveTableScan(table=[[default, store]], table:alias=[store]) + HiveProject(s_store_sk=[$0], s_state=[$24]) + HiveTableScan(table=[[default, store]], table:alias=[store]) + HiveProject(i_item_sk=[$0], i_item_id=[$1], i_item_desc=[$4]) + HiveTableScan(table=[[default, item]], table:alias=[item]) diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query18.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query18.q.out index 72c76288e7..1aeb29aaf6 100644 --- a/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query18.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query18.q.out @@ -80,32 +80,32 @@ 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=[$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($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=[IN($8, _UTF-16LE'ND', _UTF-16LE'WI', _UTF-16LE'AL', _UTF-16LE'NC', _UTF-16LE'OK', _UTF-16LE'MS', _UTF-16LE'TN')]) - HiveTableScan(table=[[default, customer_address]], table:alias=[customer_address]) - HiveProject(cd_demo_sk=[$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]) - 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))]) - HiveTableScan(table=[[default, catalog_sales]], table:alias=[catalog_sales]) - HiveProject(d_date_sk=[$0]) - HiveFilter(condition=[=($6, 2001)]) - 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'), =($3, _UTF-16LE'College'))]) - HiveTableScan(table=[[default, customer_demographics]], table:alias=[cd1]) + HiveProject($f0=[$0], $f1=[$3], $f2=[$2], $f3=[$1], $f4=[/($4, $5)], $f5=[/($6, $7)], $f6=[/($8, $9)], $f7=[/($10, $11)], $f8=[/($12, $13)], $f9=[/($14, $15)], $f10=[/($16, $17)]) + HiveAggregate(group=[{1, 7, 8, 9}], groups=[[{1, 7, 8, 9}, {1, 8, 9}, {1, 9}, {1}, {}]], agg#0=[sum($14)], agg#1=[count($14)], agg#2=[sum($15)], agg#3=[count($15)], agg#4=[sum($16)], agg#5=[count($16)], agg#6=[sum($17)], agg#7=[count($17)], agg#8=[sum($18)], agg#9=[count($18)], agg#10=[sum($5)], agg#11=[count($5)], agg#12=[sum($21)], agg#13=[count($21)]) + HiveJoin(condition=[=($3, $22)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($13, $0)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(i_item_sk=[$0], i_item_id=[$1]) + HiveTableScan(table=[[default, item]], table:alias=[item]) + HiveJoin(condition=[=($9, $0)], 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($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=[IN($8, _UTF-16LE'ND', _UTF-16LE'WI', _UTF-16LE'AL', _UTF-16LE'NC', _UTF-16LE'OK', _UTF-16LE'MS', _UTF-16LE'TN')]) + HiveTableScan(table=[[default, customer_address]], table:alias=[customer_address]) + HiveProject(cs_sold_date_sk=[$0], cs_bill_customer_sk=[$1], cs_bill_cdemo_sk=[$2], cs_item_sk=[$3], CAST=[$4], CAST5=[$5], CAST6=[$6], CAST7=[$7], CAST8=[$8], d_date_sk=[$9], cd_demo_sk=[$10], CAST0=[$11]) + 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))]) + HiveTableScan(table=[[default, catalog_sales]], table:alias=[catalog_sales]) + HiveProject(d_date_sk=[$0]) + HiveFilter(condition=[=($6, 2001)]) + 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'))]) + HiveTableScan(table=[[default, customer_demographics]], table:alias=[cd1]) + HiveProject(cd_demo_sk=[$0]) + HiveTableScan(table=[[default, customer_demographics]], table:alias=[cd2]) diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query19.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query19.q.out index 0027cf4c34..048bf4c16f 100644 --- a/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query19.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query19.q.out @@ -64,16 +64,13 @@ 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=[{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]) + HiveAggregate(group=[{9, 10, 11, 12}], agg#0=[sum($6)]) + HiveJoin(condition=[AND(<>($16, $14), =($1, $15))], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($5, $13)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($4, $0)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(c_customer_sk=[$0], c_current_addr_sk=[$4]) HiveFilter(condition=[IS NOT NULL($4)]) HiveTableScan(table=[[default, customer]], table:alias=[customer]) - HiveProject(ca_address_sk=[$0], substr=[substr($9, 1, 5)]) - 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], 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]) @@ -85,6 +82,8 @@ HiveProject(brand_id=[$0], brand=[$1], i_manufact_id=[$2], i_manufact=[$3], ext_ HiveProject(i_item_sk=[$0], i_brand_id=[$7], i_brand=[$8], i_manufact_id=[$13], i_manufact=[$14]) HiveFilter(condition=[=($20, 7)]) HiveTableScan(table=[[default, item]], table:alias=[item]) - HiveProject(s_store_sk=[$0], substr=[substr($25, 1, 5)]) - HiveTableScan(table=[[default, store]], table:alias=[store]) + HiveProject(s_store_sk=[$0], substr=[substr($25, 1, 5)]) + HiveTableScan(table=[[default, store]], table:alias=[store]) + HiveProject(ca_address_sk=[$0], substr=[substr($9, 1, 5)]) + HiveTableScan(table=[[default, customer_address]], table:alias=[customer_address]) diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query25.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query25.q.out index 658410cf13..958033e41b 100644 --- a/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query25.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query25.q.out @@ -108,21 +108,19 @@ POSTHOOK: Input: default@store_sales 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=[{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_net_profit=[$33]) - 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(BETWEEN(false, $8, 4, 10), =($6, 2000))]) - 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_net_profit=[$8], d_date_sk=[$9], sr_returned_date_sk=[$10], sr_item_sk=[$11], sr_customer_sk=[$12], sr_ticket_number=[$13], sr_net_loss=[$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]) + HiveProject(i_item_id=[$2], i_item_desc=[$3], s_store_id=[$0], s_store_name=[$1], $f4=[$4], $f5=[$5], $f6=[$6]) + HiveAggregate(group=[{19, 20, 22, 23}], agg#0=[sum($10)], agg#1=[sum($16)], agg#2=[sum($3)]) + HiveJoin(condition=[=($21, $6)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($18, $8)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[AND(=($14, $1), =($13, $2))], 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]) - HiveTableScan(table=[[default, item]], table:alias=[item]) + 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($0))]) + HiveTableScan(table=[[default, catalog_sales]], table:alias=[catalog_sales]) + HiveProject(d_date_sk=[$0]) + HiveFilter(condition=[AND(BETWEEN(false, $8, 4, 10), =($6, 2000))]) + HiveTableScan(table=[[default, date_dim]], table:alias=[d3]) + HiveProject(ss_sold_date_sk=[$0], ss_item_sk=[$1], ss_customer_sk=[$2], ss_store_sk=[$3], ss_ticket_number=[$4], ss_net_profit=[$5], d_date_sk=[$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]) 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_net_profit=[$22]) @@ -139,6 +137,8 @@ HiveSortLimit(sort0=[$0], sort1=[$1], sort2=[$2], sort3=[$3], dir0=[ASC], dir1=[ HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(BETWEEN(false, $8, 4, 10), =($6, 2000))]) HiveTableScan(table=[[default, date_dim]], table:alias=[d2]) - HiveProject(s_store_sk=[$0], s_store_id=[$1], s_store_name=[$5]) - HiveTableScan(table=[[default, store]], table:alias=[store]) + HiveProject(s_store_sk=[$0], s_store_id=[$1], s_store_name=[$5]) + HiveTableScan(table=[[default, store]], table:alias=[store]) + HiveProject(i_item_sk=[$0], i_item_id=[$1], i_item_desc=[$4]) + HiveTableScan(table=[[default, item]], table:alias=[item]) diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query29.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query29.q.out index 8134a46706..3e7c6805b2 100644 --- a/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query29.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query29.q.out @@ -106,21 +106,19 @@ POSTHOOK: Input: default@store_sales 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=[{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($0))]) - HiveTableScan(table=[[default, catalog_sales]], table:alias=[catalog_sales]) - HiveProject(d_date_sk=[$0]) - HiveFilter(condition=[IN($6, 1999, 2000, 2001)]) - 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], 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]) + HiveProject(i_item_id=[$2], i_item_desc=[$3], s_store_id=[$0], s_store_name=[$1], $f4=[$4], $f5=[$5], $f6=[$6]) + HiveAggregate(group=[{19, 20, 22, 23}], agg#0=[sum($10)], agg#1=[sum($16)], agg#2=[sum($3)]) + HiveJoin(condition=[=($21, $6)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($18, $8)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[AND(=($14, $1), =($13, $2))], 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]) - HiveTableScan(table=[[default, item]], table:alias=[item]) + 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($0))]) + HiveTableScan(table=[[default, catalog_sales]], table:alias=[catalog_sales]) + HiveProject(d_date_sk=[$0]) + HiveFilter(condition=[IN($6, 1999, 2000, 2001)]) + HiveTableScan(table=[[default, date_dim]], table:alias=[d3]) + HiveProject(ss_sold_date_sk=[$0], ss_item_sk=[$1], ss_customer_sk=[$2], ss_store_sk=[$3], ss_ticket_number=[$4], ss_quantity=[$5], d_date_sk=[$6], sr_returned_date_sk=[$7], sr_item_sk=[$8], sr_customer_sk=[$9], sr_ticket_number=[$10], sr_return_quantity=[$11], d_date_sk0=[$12]) 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]) @@ -137,6 +135,8 @@ HiveSortLimit(sort0=[$0], sort1=[$1], sort2=[$2], sort3=[$3], dir0=[ASC], dir1=[ HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(BETWEEN(false, $8, 4, 7), =($6, 1999))]) HiveTableScan(table=[[default, date_dim]], table:alias=[d2]) - HiveProject(s_store_sk=[$0], s_store_id=[$1], s_store_name=[$5]) - HiveTableScan(table=[[default, store]], table:alias=[store]) + HiveProject(s_store_sk=[$0], s_store_id=[$1], s_store_name=[$5]) + HiveTableScan(table=[[default, store]], table:alias=[store]) + HiveProject(i_item_sk=[$0], i_item_id=[$1], i_item_desc=[$4]) + HiveTableScan(table=[[default, item]], table:alias=[item]) diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query35.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query35.q.out index e79c6b7e51..e4346963f8 100644 --- a/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query35.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query35.q.out @@ -135,15 +135,16 @@ HiveProject(ca_state=[$0], cd_gender=[$1], cd_marital_status=[$2], cnt1=[$3], _o HiveJoin(condition=[=($0, $13)], joinType=[left], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($0, $11)], joinType=[left], algorithm=[none], cost=[not available]) HiveSemiJoin(condition=[=($0, $11)], joinType=[inner]) - HiveJoin(condition=[=($5, $1)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveJoin(condition=[=($2, $3)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(c_customer_sk=[$0], c_current_cdemo_sk=[$2], c_current_addr_sk=[$4]) - HiveFilter(condition=[AND(IS NOT NULL($4), IS NOT NULL($2))]) - HiveTableScan(table=[[default, customer]], table:alias=[c]) + HiveProject(c_customer_sk=[$0], c_current_cdemo_sk=[$1], c_current_addr_sk=[$2], ca_address_sk=[$9], ca_state=[$10], cd_demo_sk=[$3], cd_gender=[$4], cd_marital_status=[$5], cd_dep_count=[$6], cd_dep_employed_count=[$7], cd_dep_college_count=[$8]) + HiveJoin(condition=[=($2, $9)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($3, $1)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(c_customer_sk=[$0], c_current_cdemo_sk=[$2], c_current_addr_sk=[$4]) + HiveFilter(condition=[AND(IS NOT NULL($4), IS NOT NULL($2))]) + HiveTableScan(table=[[default, customer]], table:alias=[c]) + HiveProject(cd_demo_sk=[$0], cd_gender=[$1], cd_marital_status=[$2], cd_dep_count=[$6], cd_dep_employed_count=[$7], cd_dep_college_count=[$8]) + HiveTableScan(table=[[default, customer_demographics]], table:alias=[customer_demographics]) HiveProject(ca_address_sk=[$0], ca_state=[$8]) HiveTableScan(table=[[default, customer_address]], table:alias=[ca]) - HiveProject(cd_demo_sk=[$0], cd_gender=[$1], cd_marital_status=[$2], cd_dep_count=[$6], cd_dep_employed_count=[$7], cd_dep_college_count=[$8]) - HiveTableScan(table=[[default, customer_demographics]], table:alias=[customer_demographics]) HiveProject(ss_customer_sk0=[$1]) HiveJoin(condition=[=($0, $2)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(ss_sold_date_sk=[$0], ss_customer_sk=[$3]) diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query4.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query4.q.out index 9fb918eb58..9668e0f4a1 100644 --- a/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query4.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query4.q.out @@ -229,7 +229,7 @@ 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($14, >(/($4, $13), /($2, $8)), >(null, /($2, $8))), CASE($14, >(/($4, $13), null), null)))], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[AND(=($0, $10), CASE(CAST(IS NOT NULL($11)):BOOLEAN, CASE($14, >(/($6, $13), /($2, $11)), >(null, /($2, $11))), CASE($14, >(/($6, $13), null), null)))], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject($f0=[$0], $f3=[$3], $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]) @@ -242,34 +242,47 @@ HiveSortLimit(sort0=[$0], dir0=[ASC], fetch=[100]) HiveProject(d_date_sk=[$0]) HiveFilter(condition=[=($6, 2002)]) 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]) + HiveJoin(condition=[AND(=($7, $0), CASE($6, CASE($11, >(/($3, $10), /($1, $5)), >(null, /($1, $5))), CASE($11, >(/($3, $10), null), null)))], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject($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]) 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(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=[=($6, 2002)]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) - 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=[{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]) - 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=[=($6, 2002)]) - HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) + HiveJoin(condition=[=($5, $0)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject($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]) + 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=[=($6, 2002)]) + HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) + HiveJoin(condition=[=($3, $5)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($3, $0)], joinType=[inner], algorithm=[none], cost=[not available]) + 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]) + 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=[=($6, 2001)]) + HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) HiveProject($f0=[$0], $f8=[$7]) HiveFilter(condition=[>($7, 0)]) HiveAggregate(group=[{1, 2, 3, 4, 5, 6, 7}], agg#0=[sum($10)]) @@ -290,23 +303,10 @@ HiveSortLimit(sort0=[$0], dir0=[ASC], fetch=[100]) 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]) 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(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=[=($6, 2001)]) 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]) - 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=[=($6, 2001)]) - HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query46.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query46.q.out index df36f9ba14..9d21449b65 100644 --- a/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query46.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query46.q.out @@ -82,32 +82,32 @@ POSTHOOK: Input: default@store_sales POSTHOOK: Output: hdfs://### HDFS PATH ### CBO PLAN: HiveSortLimit(sort0=[$0], sort1=[$1], sort2=[$2], sort3=[$3], sort4=[$4], dir0=[ASC], dir1=[ASC], dir2=[ASC], dir3=[ASC], dir4=[ASC], fetch=[100]) - HiveProject(c_last_name=[$3], c_first_name=[$2], ca_city=[$5], bought_city=[$8], ss_ticket_number=[$6], amt=[$9], profit=[$10]) - HiveJoin(condition=[AND(<>($5, $8), =($7, $0))], joinType=[inner], algorithm=[none], cost=[not available]) - HiveJoin(condition=[=($1, $4)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(c_last_name=[$5], c_first_name=[$4], ca_city=[$1], bought_city=[$8], ss_ticket_number=[$6], amt=[$9], profit=[$10]) + HiveJoin(condition=[AND(=($3, $0), <>($1, $8))], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(ca_address_sk=[$0], ca_city=[$6]) + HiveTableScan(table=[[default, customer_address]], table:alias=[current_addr]) + HiveJoin(condition=[=($5, $0)], 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]) HiveFilter(condition=[IS NOT NULL($4)]) HiveTableScan(table=[[default, customer]], table:alias=[customer]) - HiveProject(ca_address_sk=[$0], ca_city=[$6]) - HiveTableScan(table=[[default, customer_address]], table:alias=[current_addr]) - HiveProject(ss_ticket_number=[$3], ss_customer_sk=[$1], bought_city=[$0], amt=[$4], profit=[$5]) - HiveAggregate(group=[{1, 3, 5, 7}], agg#0=[sum($8)], agg#1=[sum($9)]) - HiveJoin(condition=[=($5, $0)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(ca_address_sk=[$0], ca_city=[$6]) - HiveTableScan(table=[[default, customer_address]], table:alias=[customer_address]) - 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]) - HiveFilter(condition=[AND(IN($7, 6, 0), IN($6, 1998, 1999, 2000))]) - HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) - HiveProject(s_store_sk=[$0]) - HiveFilter(condition=[IN($22, _UTF-16LE'Cedar Grove', _UTF-16LE'Wildwood', _UTF-16LE'Union', _UTF-16LE'Salem', _UTF-16LE'Highland Park')]) - HiveTableScan(table=[[default, store]], table:alias=[store]) - HiveProject(hd_demo_sk=[$0]) - HiveFilter(condition=[OR(=($3, 2), =($4, 1))]) - HiveTableScan(table=[[default, household_demographics]], table:alias=[household_demographics]) + HiveProject(ss_ticket_number=[$3], ss_customer_sk=[$1], bought_city=[$0], amt=[$4], profit=[$5]) + HiveAggregate(group=[{1, 3, 5, 7}], agg#0=[sum($8)], agg#1=[sum($9)]) + HiveJoin(condition=[=($5, $0)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(ca_address_sk=[$0], ca_city=[$6]) + HiveTableScan(table=[[default, customer_address]], table:alias=[customer_address]) + 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]) + HiveFilter(condition=[AND(IN($7, 6, 0), IN($6, 1998, 1999, 2000))]) + HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) + HiveProject(s_store_sk=[$0]) + HiveFilter(condition=[IN($22, _UTF-16LE'Cedar Grove', _UTF-16LE'Wildwood', _UTF-16LE'Union', _UTF-16LE'Salem', _UTF-16LE'Highland Park')]) + HiveTableScan(table=[[default, store]], table:alias=[store]) + HiveProject(hd_demo_sk=[$0]) + HiveFilter(condition=[OR(=($3, 2), =($4, 1))]) + HiveTableScan(table=[[default, household_demographics]], table:alias=[household_demographics]) diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query54.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query54.q.out index 5d9dd17343..280ba926de 100644 --- a/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query54.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query54.q.out @@ -1,7 +1,7 @@ -Warning: Shuffle Join MERGEJOIN[264][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product -Warning: Shuffle Join MERGEJOIN[273][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3, $hdt$_4]] in Stage 'Reducer 5' is a cross product -Warning: Shuffle Join MERGEJOIN[272][tables = [$hdt$_1, $hdt$_2]] in Stage 'Reducer 14' is a cross product -Warning: Shuffle Join MERGEJOIN[274][tables = [$hdt$_1, $hdt$_2, $hdt$_0]] in Stage 'Reducer 6' is a cross product +Warning: Shuffle Join MERGEJOIN[270][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product +Warning: Shuffle Join MERGEJOIN[278][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3, $hdt$_4]] in Stage 'Reducer 5' is a cross product +Warning: Shuffle Join MERGEJOIN[279][tables = [$hdt$_1, $hdt$_2]] in Stage 'Reducer 14' is a cross product +Warning: Shuffle Join MERGEJOIN[280][tables = [$hdt$_1, $hdt$_2, $hdt$_0]] in Stage 'Reducer 6' is a cross product PREHOOK: query: explain cbo with my_customers as ( select distinct c_customer_sk @@ -139,10 +139,10 @@ HiveSortLimit(sort0=[$0], sort1=[$1], dir0=[ASC], dir1=[ASC], fetch=[100]) HiveFilter(condition=[BETWEEN(false, $2, $3, $4)]) HiveProject(c_customer_sk=[$0], ss_ext_sales_price=[$4], d_month_seq=[$11], _o__c0=[$13], $f0=[$14]) HiveJoin(condition=[true], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject($f0=[$11], $f1=[$12], ss_sold_date_sk=[$0], ss_customer_sk=[$1], ss_ext_sales_price=[$2], ca_address_sk=[$6], ca_county=[$7], ca_state=[$8], s_county=[$9], s_state=[$10], d_date_sk=[$4], d_month_seq=[$5], cnt=[$3], $f00=[$13]) + HiveProject($f0=[$9], $f1=[$10], ss_sold_date_sk=[$0], ss_customer_sk=[$1], ss_ext_sales_price=[$2], ca_address_sk=[$4], ca_county=[$5], ca_state=[$6], s_county=[$7], s_state=[$8], d_date_sk=[$11], d_month_seq=[$12], cnt=[$3], $f00=[$13]) HiveJoin(condition=[true], joinType=[left], algorithm=[none], cost=[not available]) - HiveJoin(condition=[=($11, $1)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveJoin(condition=[=($0, $4)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($0, $11)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($9, $1)], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[true], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(ss_sold_date_sk=[$0], ss_customer_sk=[$3], ss_ext_sales_price=[$15]) HiveFilter(condition=[AND(IS NOT NULL($3), IS NOT NULL($0))]) @@ -156,39 +156,39 @@ HiveSortLimit(sort0=[$0], sort1=[$1], dir0=[ASC], dir1=[ASC], fetch=[100]) HiveProject($f0=[+($3, 1)]) HiveFilter(condition=[AND(=($6, 1999), =($8, 3))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) - HiveProject(d_date_sk=[$0], d_month_seq=[$3]) - HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) - HiveProject(ca_address_sk=[$0], ca_county=[$1], ca_state=[$2], s_county=[$3], s_state=[$4], c_customer_sk=[$5], c_current_addr_sk=[$6]) - HiveJoin(condition=[=($6, $0)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveJoin(condition=[AND(=($1, $3), =($2, $4))], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(ca_address_sk=[$0], ca_county=[$7], ca_state=[$8]) - HiveFilter(condition=[AND(IS NOT NULL($7), IS NOT NULL($8))]) - HiveTableScan(table=[[default, customer_address]], table:alias=[customer_address]) - HiveProject(s_county=[$23], s_state=[$24]) - HiveFilter(condition=[AND(IS NOT NULL($23), IS NOT NULL($24))]) - HiveTableScan(table=[[default, store]], table:alias=[store]) - HiveProject(c_customer_sk=[$0], c_current_addr_sk=[$1]) - HiveAggregate(group=[{0, 1}]) - HiveJoin(condition=[=($0, $3)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(c_customer_sk=[$0], c_current_addr_sk=[$4]) - HiveFilter(condition=[IS NOT NULL($4)]) - HiveTableScan(table=[[default, customer]], table:alias=[customer]) - 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]) - HiveProject(cs_sold_date_sk=[$0], cs_bill_customer_sk=[$3], cs_item_sk=[$15]) - HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($3))]) - HiveTableScan(table=[[default, catalog_sales]], table:alias=[catalog_sales]) - HiveProject(sold_date_sk=[$0], customer_sk=[$4], item_sk=[$3]) - 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]) - HiveFilter(condition=[AND(=($8, 3), =($6, 1999))]) - HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) - HiveProject(i_item_sk=[$0]) - HiveFilter(condition=[AND(=($12, _UTF-16LE'Jewelry'), =($10, _UTF-16LE'consignment'))]) - HiveTableScan(table=[[default, item]], table:alias=[item]) + HiveProject(ca_address_sk=[$0], ca_county=[$1], ca_state=[$2], s_county=[$3], s_state=[$4], c_customer_sk=[$5], c_current_addr_sk=[$6]) + HiveJoin(condition=[=($6, $0)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[AND(=($1, $3), =($2, $4))], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(ca_address_sk=[$0], ca_county=[$7], ca_state=[$8]) + HiveFilter(condition=[AND(IS NOT NULL($7), IS NOT NULL($8))]) + HiveTableScan(table=[[default, customer_address]], table:alias=[customer_address]) + HiveProject(s_county=[$23], s_state=[$24]) + HiveFilter(condition=[AND(IS NOT NULL($23), IS NOT NULL($24))]) + HiveTableScan(table=[[default, store]], table:alias=[store]) + HiveProject(c_customer_sk=[$0], c_current_addr_sk=[$1]) + HiveAggregate(group=[{0, 1}]) + HiveJoin(condition=[=($0, $3)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(c_customer_sk=[$0], c_current_addr_sk=[$4]) + HiveFilter(condition=[IS NOT NULL($4)]) + HiveTableScan(table=[[default, customer]], table:alias=[customer]) + 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]) + HiveProject(cs_sold_date_sk=[$0], cs_bill_customer_sk=[$3], cs_item_sk=[$15]) + HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($3))]) + HiveTableScan(table=[[default, catalog_sales]], table:alias=[catalog_sales]) + HiveProject(sold_date_sk=[$0], customer_sk=[$4], item_sk=[$3]) + 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]) + HiveFilter(condition=[AND(=($8, 3), =($6, 1999))]) + HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) + HiveProject(i_item_sk=[$0]) + HiveFilter(condition=[AND(=($12, _UTF-16LE'Jewelry'), =($10, _UTF-16LE'consignment'))]) + HiveTableScan(table=[[default, item]], table:alias=[item]) + HiveProject(d_date_sk=[$0], d_month_seq=[$3]) + HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) HiveProject($f0=[$0]) HiveAggregate(group=[{0}]) HiveProject($f0=[+($3, 1)]) diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query58.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query58.q.out index a362c45780..3e89c2da75 100644 --- a/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query58.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query58.q.out @@ -1,4 +1,4 @@ -Warning: Shuffle Join MERGEJOIN[401][tables = [$hdt$_4, $hdt$_5]] in Stage 'Reducer 22' is a cross product +Warning: Shuffle Join MERGEJOIN[406][tables = [$hdt$_3, $hdt$_4]] in Stage 'Reducer 20' is a cross product PREHOOK: query: explain cbo with ss_items as (select i_item_id item_id @@ -145,15 +145,12 @@ HiveSortLimit(sort0=[$0], sort1=[$1], dir0=[ASC], dir1=[ASC], fetch=[100]) HiveJoin(condition=[AND(AND(AND(AND(=($0, $4), BETWEEN(false, $3, $6, $7)), BETWEEN(false, $1, $6, $7)), 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]) - 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]) + HiveAggregate(group=[{7}], agg#0=[sum($2)]) + HiveJoin(condition=[=($1, $6)], 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_item_sk=[$15], cs_ext_sales_price=[$23]) HiveFilter(condition=[IS NOT NULL($0)]) HiveTableScan(table=[[default, catalog_sales]], table:alias=[catalog_sales]) - HiveProject(i_item_sk=[$0], i_item_id=[$1]) - HiveTableScan(table=[[default, item]], table:alias=[item]) - HiveProject(d_date_sk=[$0], d_date=[$1], d_date0=[$2]) HiveJoin(condition=[=($1, $2)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(d_date_sk=[$0], d_date=[$2]) HiveFilter(condition=[IS NOT NULL($2)]) @@ -174,16 +171,15 @@ 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_sk=[$0], i_item_id=[$1]) + HiveTableScan(table=[[default, item]], table:alias=[item]) HiveProject(i_item_id=[$0], $f1=[$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]) + HiveAggregate(group=[{7}], agg#0=[sum($2)]) + HiveJoin(condition=[=($1, $6)], 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_item_sk=[$2], ss_ext_sales_price=[$15]) HiveFilter(condition=[IS NOT NULL($0)]) HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) - HiveProject(i_item_sk=[$0], i_item_id=[$1]) - HiveTableScan(table=[[default, item]], table:alias=[item]) - HiveProject(d_date_sk=[$0], d_date=[$1], d_date0=[$2]) HiveJoin(condition=[=($1, $2)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(d_date_sk=[$0], d_date=[$2]) HiveFilter(condition=[IS NOT NULL($2)]) @@ -204,16 +200,15 @@ 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_sk=[$0], i_item_id=[$1]) + HiveTableScan(table=[[default, item]], table:alias=[item]) HiveProject(item_id=[$0], ws_item_rev=[$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]) + HiveAggregate(group=[{7}], agg#0=[sum($2)]) + HiveJoin(condition=[=($1, $6)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($0, $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=[IS NOT NULL($0)]) HiveTableScan(table=[[default, web_sales]], table:alias=[web_sales]) - HiveProject(i_item_sk=[$0], i_item_id=[$1]) - HiveTableScan(table=[[default, item]], table:alias=[item]) - HiveProject(d_date_sk=[$0], d_date=[$1], d_date0=[$2]) HiveJoin(condition=[=($1, $2)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(d_date_sk=[$0], d_date=[$2]) HiveFilter(condition=[IS NOT NULL($2)]) @@ -234,4 +229,6 @@ 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_sk=[$0], i_item_id=[$1]) + HiveTableScan(table=[[default, item]], table:alias=[item]) diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query6.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query6.q.out index cbf372a753..a14c958c6f 100644 --- a/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query6.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query6.q.out @@ -1,4 +1,4 @@ -Warning: Map Join MAPJOIN[170][bigTable=?] in task 'Reducer 15' is a cross product +Warning: Map Join MAPJOIN[171][bigTable=?] in task 'Reducer 6' is a cross product PREHOOK: query: explain cbo select a.ca_state state, count(*) cnt from customer_address a @@ -65,44 +65,44 @@ CBO PLAN: HiveSortLimit(sort0=[$1], dir0=[ASC], fetch=[100]) HiveProject(ca_state=[$0], $f1=[$1]) HiveFilter(condition=[>=($1, 10)]) - HiveAggregate(group=[{9}], agg#0=[count()]) - HiveJoin(condition=[=($1, $10)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveJoin(condition=[=($6, $2)], 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_item_sk=[$2], ss_customer_sk=[$3]) - HiveFilter(condition=[AND(IS NOT NULL($3), IS NOT NULL($0))]) - HiveTableScan(table=[[default, store_sales]], table:alias=[s]) - HiveJoin(condition=[=($1, $2)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(d_date_sk=[$0], d_month_seq=[$3]) - HiveFilter(condition=[IS NOT NULL($3)]) - HiveTableScan(table=[[default, date_dim]], table:alias=[d]) - HiveProject(d_month_seq=[$0]) - HiveAggregate(group=[{3}]) - HiveFilter(condition=[AND(=($6, 2000), =($8, 2), IS NOT NULL($3))]) - HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) - HiveProject(c_customer_sk=[$0], c_current_addr_sk=[$1], ca_address_sk=[$2], ca_state=[$3]) - HiveJoin(condition=[=($2, $1)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveAggregate(group=[{12}], agg#0=[count()]) + HiveJoin(condition=[=($0, $13)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($11, $4)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($1, $5)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($3, $2)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(ss_sold_date_sk=[$0], ss_item_sk=[$2], ss_customer_sk=[$3]) + HiveFilter(condition=[AND(IS NOT NULL($3), IS NOT NULL($0))]) + HiveTableScan(table=[[default, store_sales]], table:alias=[s]) HiveProject(c_customer_sk=[$0], c_current_addr_sk=[$4]) HiveFilter(condition=[IS NOT NULL($4)]) HiveTableScan(table=[[default, customer]], table:alias=[c]) - HiveProject(ca_address_sk=[$0], ca_state=[$8]) - HiveTableScan(table=[[default, customer_address]], table:alias=[a]) - 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=[IS NOT NULL($12)]) - HiveTableScan(table=[[default, item]], table:alias=[i]) - HiveJoin(condition=[true], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(i_category=[$0], *=[*(1.2, CAST(/($1, $2)):DECIMAL(16, 6))]) - HiveAggregate(group=[{12}], agg#0=[sum($5)], agg#1=[count($5)]) + 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=[IS NOT NULL($12)]) - HiveTableScan(table=[[default, item]], table:alias=[j]) - HiveProject(cnt=[$0]) - HiveFilter(condition=[<=(sq_count_check($0), 1)]) + HiveTableScan(table=[[default, item]], table:alias=[i]) + HiveJoin(condition=[true], joinType=[inner], algorithm=[none], cost=[not available]) + 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]) HiveProject(cnt=[$0]) - HiveAggregate(group=[{}], cnt=[COUNT()]) - HiveProject(d_month_seq=[$0]) - HiveAggregate(group=[{3}]) - HiveFilter(condition=[AND(=($6, 2000), =($8, 2))]) - HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) + HiveFilter(condition=[<=(sq_count_check($0), 1)]) + HiveProject(cnt=[$0]) + HiveAggregate(group=[{}], cnt=[COUNT()]) + HiveProject(d_month_seq=[$0]) + HiveAggregate(group=[{3}]) + HiveFilter(condition=[AND(=($6, 2000), =($8, 2))]) + HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) + HiveProject(ca_address_sk=[$0], ca_state=[$8]) + HiveTableScan(table=[[default, customer_address]], table:alias=[a]) + HiveProject(d_date_sk=[$0], d_month_seq=[$1], d_month_seq0=[$2]) + HiveJoin(condition=[=($1, $2)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(d_date_sk=[$0], d_month_seq=[$3]) + HiveFilter(condition=[IS NOT NULL($3)]) + HiveTableScan(table=[[default, date_dim]], table:alias=[d]) + HiveProject(d_month_seq=[$0]) + HiveAggregate(group=[{3}]) + HiveFilter(condition=[AND(=($6, 2000), =($8, 2), IS NOT NULL($3))]) + HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query64.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query64.q.out index 103b67125c..d4556e87ae 100644 --- a/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query64.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query64.q.out @@ -267,124 +267,124 @@ HiveProject(product_name=[$0], store_name=[$1], store_zip=[$2], b_street_number= HiveSortLimit(sort0=[$0], sort1=[$1], sort2=[$18], dir0=[ASC], dir1=[ASC], dir2=[ASC]) 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=[$4], $f3=[$5], $f4=[$0], $f5=[$1], $f6=[$2], $f7=[$3], $f8=[$6], $f9=[$7], $f10=[$8], $f11=[$9], $f15=[$14], $f16=[$15], $f17=[$16], $f18=[$17]) - HiveAggregate(group=[{3, 4, 5, 6, 8, 9, 20, 21, 22, 23, 26, 28, 42, 43}], agg#0=[count()], agg#1=[sum($39)], agg#2=[sum($40)], agg#3=[sum($41)]) - HiveJoin(condition=[AND(=($32, $0), =($38, $1))], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(sr_item_sk=[$2], sr_ticket_number=[$9]) - HiveTableScan(table=[[default, store_returns]], table:alias=[store_returns]) - HiveJoin(condition=[=($34, $0)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject($f0=[$3], $f1=[$2], $f2=[$0], $f3=[$1], $f4=[$6], $f5=[$7], $f6=[$8], $f7=[$9], $f8=[$10], $f9=[$11], $f10=[$12], $f11=[$13], $f15=[$14], $f16=[$15], $f17=[$16], $f18=[$17]) + HiveAggregate(group=[{3, 4, 24, 25, 29, 31, 37, 38, 39, 40, 42, 43, 44, 45}], agg#0=[count()], agg#1=[sum($21)], agg#2=[sum($22)], agg#3=[sum($23)]) + HiveJoin(condition=[=($9, $41)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($18, $36)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[AND(=($7, $34), <>($33, $35))], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($16, $32)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($10, $30)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($11, $28)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[AND(=($14, $0), =($20, $1))], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(sr_item_sk=[$2], sr_ticket_number=[$9]) + HiveTableScan(table=[[default, store_returns]], table:alias=[store_returns]) + HiveJoin(condition=[=($17, $0)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(s_store_sk=[$0], s_store_name=[$5], s_zip=[$25]) + HiveFilter(condition=[AND(IS NOT NULL($5), IS NOT NULL($25))]) + HiveTableScan(table=[[default, store]], table:alias=[store]) + HiveJoin(condition=[=($12, $0)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(hd_demo_sk=[$0]) + HiveFilter(condition=[IS NOT NULL($1)]) + HiveTableScan(table=[[default, household_demographics]], table:alias=[hd1]) + HiveJoin(condition=[=($8, $21)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($9, $0)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($2, $6)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(c_customer_sk=[$0], c_current_cdemo_sk=[$2], c_current_hdemo_sk=[$3], c_current_addr_sk=[$4], c_first_shipto_date_sk=[$5], c_first_sales_date_sk=[$6]) + HiveFilter(condition=[AND(IS NOT NULL($6), IS NOT NULL($5), IS NOT NULL($2), IS NOT NULL($3), IS NOT NULL($4))]) + HiveTableScan(table=[[default, customer]], table:alias=[customer]) + HiveProject(hd_demo_sk=[$0]) + HiveFilter(condition=[IS NOT NULL($1)]) + HiveTableScan(table=[[default, household_demographics]], table:alias=[hd2]) + HiveProject(ss_sold_date_sk=[$0], ss_item_sk=[$1], ss_customer_sk=[$2], ss_cdemo_sk=[$3], ss_hdemo_sk=[$4], ss_addr_sk=[$5], ss_store_sk=[$6], ss_ticket_number=[$7], ss_wholesale_cost=[$8], ss_list_price=[$9], ss_coupon_amt=[$10], i_item_sk=[$11], i_product_name=[$12], d_date_sk=[$13]) + HiveJoin(condition=[=($0, $13)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($1, $11)], 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_ticket_number=[$9], ss_wholesale_cost=[$11], ss_list_price=[$12], ss_coupon_amt=[$19]) + HiveFilter(condition=[AND(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_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))]) + HiveTableScan(table=[[default, item]], table:alias=[item]) + HiveProject(d_date_sk=[$0]) + HiveFilter(condition=[=($6, 2000)]) + HiveTableScan(table=[[default, date_dim]], table:alias=[d1]) + HiveProject(cs_item_sk=[$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]) + HiveTableScan(table=[[default, catalog_sales]], table:alias=[catalog_sales]) + HiveProject(cr_item_sk=[$2], cr_order_number=[$16], +=[+(+($23, $24), $25)]) + HiveTableScan(table=[[default, catalog_returns]], table:alias=[catalog_returns]) + HiveProject(d_date_sk=[$0], d_year=[$6]) + HiveTableScan(table=[[default, date_dim]], table:alias=[d2]) + HiveProject(d_date_sk=[$0], d_year=[$6]) + HiveTableScan(table=[[default, date_dim]], table:alias=[d3]) + HiveProject(cd_demo_sk=[$0], cd_marital_status=[$2]) + HiveTableScan(table=[[default, customer_demographics]], table:alias=[cd1]) + HiveProject(cd_demo_sk=[$0], cd_marital_status=[$2]) + HiveTableScan(table=[[default, customer_demographics]], table:alias=[cd2]) HiveProject(ca_address_sk=[$0], ca_street_number=[$2], ca_street_name=[$3], ca_city=[$6], ca_zip=[$9]) HiveTableScan(table=[[default, customer_address]], table:alias=[ad1]) - HiveJoin(condition=[=($30, $0)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(s_store_sk=[$0], s_store_name=[$5], s_zip=[$25]) - HiveFilter(condition=[AND(IS NOT NULL($5), IS NOT NULL($25))]) - HiveTableScan(table=[[default, store]], table:alias=[store]) - HiveJoin(condition=[=($25, $0)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(hd_demo_sk=[$0]) - HiveFilter(condition=[IS NOT NULL($1)]) - HiveTableScan(table=[[default, household_demographics]], table:alias=[hd1]) - HiveJoin(condition=[=($21, $34)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveJoin(condition=[AND(=($3, $0), <>($19, $1))], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(cd_demo_sk=[$0], cd_marital_status=[$2]) - HiveTableScan(table=[[default, customer_demographics]], table:alias=[cd2]) - HiveJoin(condition=[=($20, $0)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveJoin(condition=[=($4, $14)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveJoin(condition=[=($5, $12)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveJoin(condition=[=($2, $11)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveJoin(condition=[=($3, $6)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(c_customer_sk=[$0], c_current_cdemo_sk=[$2], c_current_hdemo_sk=[$3], c_current_addr_sk=[$4], c_first_shipto_date_sk=[$5], c_first_sales_date_sk=[$6]) - HiveFilter(condition=[AND(IS NOT NULL($6), IS NOT NULL($5), IS NOT NULL($2), IS NOT NULL($3), IS NOT NULL($4))]) - HiveTableScan(table=[[default, customer]], table:alias=[customer]) - HiveProject(ca_address_sk=[$0], ca_street_number=[$2], ca_street_name=[$3], ca_city=[$6], ca_zip=[$9]) - HiveTableScan(table=[[default, customer_address]], table:alias=[ad2]) - HiveProject(hd_demo_sk=[$0]) - HiveFilter(condition=[IS NOT NULL($1)]) - HiveTableScan(table=[[default, household_demographics]], table:alias=[hd2]) - HiveProject(d_date_sk=[$0], d_year=[$6]) - HiveTableScan(table=[[default, date_dim]], table:alias=[d2]) - HiveProject(d_date_sk=[$0], d_year=[$6]) - HiveTableScan(table=[[default, date_dim]], table:alias=[d3]) - HiveProject(cd_demo_sk=[$0], cd_marital_status=[$1], ss_sold_date_sk=[$2], ss_item_sk=[$3], ss_customer_sk=[$4], ss_cdemo_sk=[$5], ss_hdemo_sk=[$6], ss_addr_sk=[$7], ss_store_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]) - HiveJoin(condition=[=($5, $0)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(cd_demo_sk=[$0], cd_marital_status=[$2]) - HiveTableScan(table=[[default, customer_demographics]], table:alias=[cd1]) - HiveJoin(condition=[=($0, $13)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveJoin(condition=[=($1, $11)], 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_ticket_number=[$9], ss_wholesale_cost=[$11], ss_list_price=[$12], ss_coupon_amt=[$19]) - HiveFilter(condition=[AND(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_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))]) - HiveTableScan(table=[[default, item]], table:alias=[item]) - HiveProject(d_date_sk=[$0]) - HiveFilter(condition=[=($6, 2000)]) - HiveTableScan(table=[[default, date_dim]], table:alias=[d1]) - HiveProject(cs_item_sk=[$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]) - HiveTableScan(table=[[default, catalog_sales]], table:alias=[catalog_sales]) - HiveProject(cr_item_sk=[$2], cr_order_number=[$16], +=[+(+($23, $24), $25)]) - HiveTableScan(table=[[default, catalog_returns]], table:alias=[catalog_returns]) - HiveProject($f1=[$12], $f2=[$4], $f3=[$5], $f15=[$14], $f16=[$15], $f17=[$16], $f18=[$17]) - HiveAggregate(group=[{3, 4, 5, 6, 8, 9, 20, 21, 22, 23, 26, 28, 42, 43}], agg#0=[count()], agg#1=[sum($39)], agg#2=[sum($40)], agg#3=[sum($41)]) - HiveJoin(condition=[AND(=($32, $0), =($38, $1))], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(sr_item_sk=[$2], sr_ticket_number=[$9]) - HiveTableScan(table=[[default, store_returns]], table:alias=[store_returns]) - HiveJoin(condition=[=($34, $0)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(ca_address_sk=[$0], ca_street_number=[$2], ca_street_name=[$3], ca_city=[$6], ca_zip=[$9]) + HiveTableScan(table=[[default, customer_address]], table:alias=[ad2]) + HiveProject($f1=[$2], $f2=[$0], $f3=[$1], $f15=[$14], $f16=[$15], $f17=[$16], $f18=[$17]) + HiveAggregate(group=[{3, 4, 24, 25, 29, 31, 37, 38, 39, 40, 42, 43, 44, 45}], agg#0=[count()], agg#1=[sum($21)], agg#2=[sum($22)], agg#3=[sum($23)]) + HiveJoin(condition=[=($9, $41)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($18, $36)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[AND(=($7, $34), <>($33, $35))], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($16, $32)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($10, $30)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($11, $28)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[AND(=($14, $0), =($20, $1))], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(sr_item_sk=[$2], sr_ticket_number=[$9]) + HiveTableScan(table=[[default, store_returns]], table:alias=[store_returns]) + HiveJoin(condition=[=($17, $0)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(s_store_sk=[$0], s_store_name=[$5], s_zip=[$25]) + HiveFilter(condition=[AND(IS NOT NULL($5), IS NOT NULL($25))]) + HiveTableScan(table=[[default, store]], table:alias=[store]) + HiveJoin(condition=[=($12, $0)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(hd_demo_sk=[$0]) + HiveFilter(condition=[IS NOT NULL($1)]) + HiveTableScan(table=[[default, household_demographics]], table:alias=[hd1]) + HiveJoin(condition=[=($8, $21)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($9, $0)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($2, $6)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(c_customer_sk=[$0], c_current_cdemo_sk=[$2], c_current_hdemo_sk=[$3], c_current_addr_sk=[$4], c_first_shipto_date_sk=[$5], c_first_sales_date_sk=[$6]) + HiveFilter(condition=[AND(IS NOT NULL($6), IS NOT NULL($5), IS NOT NULL($2), IS NOT NULL($3), IS NOT NULL($4))]) + HiveTableScan(table=[[default, customer]], table:alias=[customer]) + HiveProject(hd_demo_sk=[$0]) + HiveFilter(condition=[IS NOT NULL($1)]) + HiveTableScan(table=[[default, household_demographics]], table:alias=[hd2]) + HiveProject(ss_sold_date_sk=[$0], ss_item_sk=[$1], ss_customer_sk=[$2], ss_cdemo_sk=[$3], ss_hdemo_sk=[$4], ss_addr_sk=[$5], ss_store_sk=[$6], ss_ticket_number=[$7], ss_wholesale_cost=[$8], ss_list_price=[$9], ss_coupon_amt=[$10], i_item_sk=[$11], i_product_name=[$12], d_date_sk=[$13]) + HiveJoin(condition=[=($0, $13)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($1, $11)], 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_ticket_number=[$9], ss_wholesale_cost=[$11], ss_list_price=[$12], ss_coupon_amt=[$19]) + HiveFilter(condition=[AND(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_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))]) + HiveTableScan(table=[[default, item]], table:alias=[item]) + HiveProject(d_date_sk=[$0]) + HiveFilter(condition=[=($6, 2001)]) + HiveTableScan(table=[[default, date_dim]], table:alias=[d1]) + HiveProject(cs_item_sk=[$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]) + HiveTableScan(table=[[default, catalog_sales]], table:alias=[catalog_sales]) + HiveProject(cr_item_sk=[$2], cr_order_number=[$16], +=[+(+($23, $24), $25)]) + HiveTableScan(table=[[default, catalog_returns]], table:alias=[catalog_returns]) + HiveProject(d_date_sk=[$0], d_year=[$6]) + HiveTableScan(table=[[default, date_dim]], table:alias=[d2]) + HiveProject(d_date_sk=[$0], d_year=[$6]) + HiveTableScan(table=[[default, date_dim]], table:alias=[d3]) + HiveProject(cd_demo_sk=[$0], cd_marital_status=[$2]) + HiveTableScan(table=[[default, customer_demographics]], table:alias=[cd1]) + HiveProject(cd_demo_sk=[$0], cd_marital_status=[$2]) + HiveTableScan(table=[[default, customer_demographics]], table:alias=[cd2]) HiveProject(ca_address_sk=[$0], ca_street_number=[$2], ca_street_name=[$3], ca_city=[$6], ca_zip=[$9]) HiveTableScan(table=[[default, customer_address]], table:alias=[ad1]) - HiveJoin(condition=[=($30, $0)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(s_store_sk=[$0], s_store_name=[$5], s_zip=[$25]) - HiveFilter(condition=[AND(IS NOT NULL($5), IS NOT NULL($25))]) - HiveTableScan(table=[[default, store]], table:alias=[store]) - HiveJoin(condition=[=($25, $0)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(hd_demo_sk=[$0]) - HiveFilter(condition=[IS NOT NULL($1)]) - HiveTableScan(table=[[default, household_demographics]], table:alias=[hd1]) - HiveJoin(condition=[=($21, $34)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveJoin(condition=[AND(=($3, $0), <>($19, $1))], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(cd_demo_sk=[$0], cd_marital_status=[$2]) - HiveTableScan(table=[[default, customer_demographics]], table:alias=[cd2]) - HiveJoin(condition=[=($20, $0)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveJoin(condition=[=($4, $14)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveJoin(condition=[=($5, $12)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveJoin(condition=[=($2, $11)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveJoin(condition=[=($3, $6)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(c_customer_sk=[$0], c_current_cdemo_sk=[$2], c_current_hdemo_sk=[$3], c_current_addr_sk=[$4], c_first_shipto_date_sk=[$5], c_first_sales_date_sk=[$6]) - HiveFilter(condition=[AND(IS NOT NULL($6), IS NOT NULL($5), IS NOT NULL($2), IS NOT NULL($3), IS NOT NULL($4))]) - HiveTableScan(table=[[default, customer]], table:alias=[customer]) - HiveProject(ca_address_sk=[$0], ca_street_number=[$2], ca_street_name=[$3], ca_city=[$6], ca_zip=[$9]) - HiveTableScan(table=[[default, customer_address]], table:alias=[ad2]) - HiveProject(hd_demo_sk=[$0]) - HiveFilter(condition=[IS NOT NULL($1)]) - HiveTableScan(table=[[default, household_demographics]], table:alias=[hd2]) - HiveProject(d_date_sk=[$0], d_year=[$6]) - HiveTableScan(table=[[default, date_dim]], table:alias=[d2]) - HiveProject(d_date_sk=[$0], d_year=[$6]) - HiveTableScan(table=[[default, date_dim]], table:alias=[d3]) - HiveProject(cd_demo_sk=[$0], cd_marital_status=[$1], ss_sold_date_sk=[$2], ss_item_sk=[$3], ss_customer_sk=[$4], ss_cdemo_sk=[$5], ss_hdemo_sk=[$6], ss_addr_sk=[$7], ss_store_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]) - HiveJoin(condition=[=($5, $0)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(cd_demo_sk=[$0], cd_marital_status=[$2]) - HiveTableScan(table=[[default, customer_demographics]], table:alias=[cd1]) - HiveJoin(condition=[=($0, $13)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveJoin(condition=[=($1, $11)], 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_ticket_number=[$9], ss_wholesale_cost=[$11], ss_list_price=[$12], ss_coupon_amt=[$19]) - HiveFilter(condition=[AND(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_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))]) - HiveTableScan(table=[[default, item]], table:alias=[item]) - HiveProject(d_date_sk=[$0]) - HiveFilter(condition=[=($6, 2001)]) - HiveTableScan(table=[[default, date_dim]], table:alias=[d1]) - HiveProject(cs_item_sk=[$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]) - HiveTableScan(table=[[default, catalog_sales]], table:alias=[catalog_sales]) - HiveProject(cr_item_sk=[$2], cr_order_number=[$16], +=[+(+($23, $24), $25)]) - HiveTableScan(table=[[default, catalog_returns]], table:alias=[catalog_returns]) + HiveProject(ca_address_sk=[$0], ca_street_number=[$2], ca_street_name=[$3], ca_city=[$6], ca_zip=[$9]) + HiveTableScan(table=[[default, customer_address]], table:alias=[ad2]) diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query68.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query68.q.out index e5c182273b..1b25235c8a 100644 --- a/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query68.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query68.q.out @@ -96,32 +96,32 @@ POSTHOOK: Input: default@store_sales POSTHOOK: Output: hdfs://### HDFS PATH ### CBO PLAN: HiveSortLimit(sort0=[$0], sort1=[$4], dir0=[ASC], dir1=[ASC], fetch=[100]) - HiveProject(c_last_name=[$3], c_first_name=[$2], ca_city=[$5], bought_city=[$8], ss_ticket_number=[$6], extended_price=[$9], extended_tax=[$11], list_price=[$10]) - HiveJoin(condition=[AND(<>($5, $8), =($7, $0))], joinType=[inner], algorithm=[none], cost=[not available]) - HiveJoin(condition=[=($1, $4)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(c_last_name=[$5], c_first_name=[$4], ca_city=[$1], bought_city=[$8], ss_ticket_number=[$6], extended_price=[$9], extended_tax=[$11], list_price=[$10]) + HiveJoin(condition=[AND(=($3, $0), <>($1, $8))], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(ca_address_sk=[$0], ca_city=[$6]) + HiveTableScan(table=[[default, customer_address]], table:alias=[current_addr]) + HiveJoin(condition=[=($5, $0)], 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]) HiveFilter(condition=[IS NOT NULL($4)]) HiveTableScan(table=[[default, customer]], table:alias=[customer]) - HiveProject(ca_address_sk=[$0], ca_city=[$6]) - HiveTableScan(table=[[default, customer_address]], table:alias=[current_addr]) - HiveProject(ss_ticket_number=[$3], ss_customer_sk=[$1], bought_city=[$0], extended_price=[$4], list_price=[$5], extended_tax=[$6]) - HiveAggregate(group=[{1, 3, 5, 7}], agg#0=[sum($8)], agg#1=[sum($9)], agg#2=[sum($10)]) - HiveJoin(condition=[=($5, $0)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(ca_address_sk=[$0], ca_city=[$6]) - HiveTableScan(table=[[default, customer_address]], table:alias=[customer_address]) - 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]) - HiveFilter(condition=[AND(IN($6, 1998, 1999, 2000), BETWEEN(false, $9, 1, 2))]) - HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) - HiveProject(s_store_sk=[$0]) - HiveFilter(condition=[IN($22, _UTF-16LE'Cedar Grove', _UTF-16LE'Wildwood')]) - HiveTableScan(table=[[default, store]], table:alias=[store]) - HiveProject(hd_demo_sk=[$0]) - HiveFilter(condition=[OR(=($3, 2), =($4, 1))]) - HiveTableScan(table=[[default, household_demographics]], table:alias=[household_demographics]) + HiveProject(ss_ticket_number=[$3], ss_customer_sk=[$1], bought_city=[$0], extended_price=[$4], list_price=[$5], extended_tax=[$6]) + HiveAggregate(group=[{1, 3, 5, 7}], agg#0=[sum($8)], agg#1=[sum($9)], agg#2=[sum($10)]) + HiveJoin(condition=[=($5, $0)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(ca_address_sk=[$0], ca_city=[$6]) + HiveTableScan(table=[[default, customer_address]], table:alias=[customer_address]) + 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]) + HiveFilter(condition=[AND(IN($6, 1998, 1999, 2000), BETWEEN(false, $9, 1, 2))]) + HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) + HiveProject(s_store_sk=[$0]) + HiveFilter(condition=[IN($22, _UTF-16LE'Cedar Grove', _UTF-16LE'Wildwood')]) + HiveTableScan(table=[[default, store]], table:alias=[store]) + HiveProject(hd_demo_sk=[$0]) + HiveFilter(condition=[OR(=($3, 2), =($4, 1))]) + HiveTableScan(table=[[default, household_demographics]], table:alias=[household_demographics]) diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query72.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query72.q.out index c28c941213..550f1c38ef 100644 --- a/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query72.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query72.q.out @@ -82,44 +82,44 @@ 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=[$17], $f1=[$15], $f2=[$21], $f3=[CASE(IS NULL($27), 1, 0)], $f4=[CASE(IS NOT NULL($27), 1, 0)]) - HiveJoin(condition=[AND(=($0, $6), =($1, $8))], joinType=[right], algorithm=[none], cost=[not available]) - HiveProject(cr_item_sk=[$2], cr_order_number=[$16]) - HiveTableScan(table=[[default, catalog_returns]], table:alias=[catalog_returns]) - 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=[$6], i_item_desc=[$7], 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=[$8], CAST=[$9], 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]) - HiveTableScan(table=[[default, inventory]], table:alias=[inventory]) - HiveProject(w_warehouse_sk=[$0], w_warehouse_name=[$2]) - HiveTableScan(table=[[default, warehouse]], table:alias=[warehouse]) - HiveProject(i_item_sk=[$0], i_item_desc=[$1], d_date_sk=[$2], CAST=[$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=[=($0, $8)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(i_item_sk=[$0], i_item_desc=[$4]) - HiveTableScan(table=[[default, item]], table:alias=[item]) - HiveJoin(condition=[=($7, $15)], joinType=[left], algorithm=[none], cost=[not available]) - HiveJoin(condition=[AND(=($3, $0), >($1, $12))], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(d_date_sk=[$0], CAST=[CAST($2):DOUBLE]) - HiveTableScan(table=[[default, date_dim]], table:alias=[d3]) - 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, $8)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject($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=[$6], cs_ship_date_sk=[$7], cs_bill_cdemo_sk=[$8], cs_bill_hdemo_sk=[$9], cs_item_sk=[$10], cs_promo_sk=[$11], cs_order_number=[$12], cs_quantity=[$13], inv_date_sk=[$0], inv_item_sk=[$1], inv_warehouse_sk=[$2], inv_quantity_on_hand=[$3], w_warehouse_sk=[$24], w_warehouse_name=[$25], i_item_sk=[$22], i_item_desc=[$23], cd_demo_sk=[$14], hd_demo_sk=[$15], d_date_sk=[$19], d_week_seq=[$20], +=[$21], d_date_sk0=[$4], d_week_seq0=[$5], d_date_sk1=[$17], CAST=[$18], p_promo_sk=[$16]) + HiveJoin(condition=[=($24, $2)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($22, $10)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[AND(AND(>($18, $21), =($20, $5)), =($6, $19))], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($7, $17)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($11, $16)], joinType=[left], algorithm=[none], cost=[not available]) + HiveJoin(condition=[AND(=($10, $1), <($3, $13))], 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]) + HiveTableScan(table=[[default, inventory]], table:alias=[inventory]) + HiveProject(d_date_sk=[$0], d_week_seq=[$4]) + HiveFilter(condition=[IS NOT NULL($4)]) + HiveTableScan(table=[[default, date_dim]], table:alias=[d2]) + HiveProject(cs_sold_date_sk=[$0], cs_ship_date_sk=[$1], cs_bill_cdemo_sk=[$2], cs_bill_hdemo_sk=[$3], cs_item_sk=[$4], cs_promo_sk=[$5], cs_order_number=[$6], cs_quantity=[$7], cd_demo_sk=[$8], hd_demo_sk=[$9]) + HiveJoin(condition=[=($3, $9)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($2, $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($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_week_seq=[$4], +=[+(CAST($2):DOUBLE, 5)]) - HiveFilter(condition=[AND(=($6, 2001), IS NOT NULL($4))]) - HiveTableScan(table=[[default, date_dim]], table:alias=[d1]) - HiveProject(cd_demo_sk=[$0]) - HiveFilter(condition=[=($2, _UTF-16LE'M')]) - HiveTableScan(table=[[default, customer_demographics]], table:alias=[customer_demographics]) - HiveProject(hd_demo_sk=[$0]) - HiveFilter(condition=[=($2, _UTF-16LE'1001-5000')]) - HiveTableScan(table=[[default, household_demographics]], table:alias=[household_demographics]) + HiveProject(cd_demo_sk=[$0]) + HiveFilter(condition=[=($2, _UTF-16LE'M')]) + HiveTableScan(table=[[default, customer_demographics]], table:alias=[customer_demographics]) + HiveProject(hd_demo_sk=[$0]) + HiveFilter(condition=[=($2, _UTF-16LE'1001-5000')]) + HiveTableScan(table=[[default, household_demographics]], table:alias=[household_demographics]) HiveProject(p_promo_sk=[$0]) HiveTableScan(table=[[default, promotion]], table:alias=[promotion]) - HiveProject(d_date_sk=[$0], d_week_seq=[$4]) - HiveFilter(condition=[IS NOT NULL($4)]) - HiveTableScan(table=[[default, date_dim]], table:alias=[d2]) + HiveProject(d_date_sk=[$0], CAST=[CAST($2):DOUBLE]) + HiveTableScan(table=[[default, date_dim]], table:alias=[d3]) + HiveProject(d_date_sk=[$0], d_week_seq=[$4], +=[+(CAST($2):DOUBLE, 5)]) + HiveFilter(condition=[AND(=($6, 2001), IS NOT NULL($4))]) + HiveTableScan(table=[[default, date_dim]], table:alias=[d1]) + HiveProject(i_item_sk=[$0], i_item_desc=[$4]) + HiveTableScan(table=[[default, item]], table:alias=[item]) + HiveProject(w_warehouse_sk=[$0], w_warehouse_name=[$2]) + HiveTableScan(table=[[default, warehouse]], table:alias=[warehouse]) + HiveProject(cr_item_sk=[$2], cr_order_number=[$16]) + HiveTableScan(table=[[default, catalog_returns]], table:alias=[catalog_returns]) diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query74.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query74.q.out index 74a3a3f633..4a8f0b88f0 100644 --- a/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query74.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query74.q.out @@ -131,7 +131,7 @@ 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($10, >(/($5, $9), /($3, $7)), >(null, /($3, $7))), CASE($10, >(/($5, $9), null), null)))], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[AND(=($0, $9), CASE(CAST(IS NOT NULL($10)):BOOLEAN, CASE($8, >(/($5, $7), /($3, $10)), >(null, /($3, $10))), CASE($8, >(/($5, $7), 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]) @@ -144,20 +144,33 @@ HiveSortLimit(sort0=[$1], sort1=[$0], sort2=[$2], dir0=[ASC], dir1=[ASC], dir2=[ HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(IN($6, 2001, 2002), =($6, 2002))]) 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], $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]) - 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], 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]) - HiveFilter(condition=[AND(IN($6, 2001, 2002), =($6, 2002))]) - HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) + HiveJoin(condition=[=($5, $0)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject($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]) + 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], 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]) + HiveFilter(condition=[AND(IN($6, 2001, 2002), =($6, 2002))]) + HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) + HiveJoin(condition=[=($3, $0)], joinType=[inner], algorithm=[none], cost=[not available]) + 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]) + 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], 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]) + HiveFilter(condition=[AND(IN($6, 2001, 2002), =($6, 2001))]) + HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) HiveProject($f0=[$0], $f4=[$3]) HiveFilter(condition=[>($3, 0)]) HiveAggregate(group=[{1, 2, 3}], agg#0=[max($6)]) @@ -171,17 +184,4 @@ HiveSortLimit(sort0=[$1], sort1=[$0], sort2=[$2], dir0=[ASC], dir1=[ASC], dir2=[ HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(IN($6, 2001, 2002), =($6, 2001))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) - 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]) - 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], 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]) - HiveFilter(condition=[AND(IN($6, 2001, 2002), =($6, 2001))]) - HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query76.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query76.q.out index 1f8c55ad4f..a51a05ac00 100644 --- a/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query76.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query76.q.out @@ -62,34 +62,34 @@ 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=[$7]) - HiveJoin(condition=[=($5, $0)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(d_date_sk=[$0], d_year=[$6], d_qoy=[$10]) - HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) + HiveProject(channel=[_UTF-16LE'store'], col_name=[_UTF-16LE'ss_addr_sk'], d_year=[$1], d_qoy=[$2], i_category=[$7], ext_sales_price=[$5]) + HiveJoin(condition=[=($4, $6)], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($3, $0)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(i_item_sk=[$0], i_category=[$12]) - HiveTableScan(table=[[default, item]], table:alias=[item]) + HiveProject(d_date_sk=[$0], d_year=[$6], d_qoy=[$10]) + HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) HiveProject(ss_sold_date_sk=[$0], ss_item_sk=[$2], ss_ext_sales_price=[$15]) HiveFilter(condition=[AND(IS NULL($6), 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=[$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(i_item_sk=[$0], i_category=[$12]) + HiveTableScan(table=[[default, item]], table:alias=[item]) + HiveProject(channel=[_UTF-16LE'web'], col_name=[_UTF-16LE'ws_web_page_sk'], d_year=[$4], d_qoy=[$5], i_category=[$7], ext_sales_price=[$2]) + HiveJoin(condition=[=($1, $6)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($0, $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($0))]) HiveTableScan(table=[[default, web_sales]], table:alias=[web_sales]) - HiveProject(i_item_sk=[$0], i_category=[$12]) - HiveTableScan(table=[[default, item]], table:alias=[item]) - HiveProject(d_date_sk=[$0], d_year=[$6], d_qoy=[$10]) - HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) - 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(d_date_sk=[$0], d_year=[$6], d_qoy=[$10]) + HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) + HiveProject(i_item_sk=[$0], i_category=[$12]) + HiveTableScan(table=[[default, item]], table:alias=[item]) + HiveProject(channel=[_UTF-16LE'catalog'], col_name=[_UTF-16LE'cs_warehouse_sk'], d_year=[$4], d_qoy=[$5], i_category=[$7], ext_sales_price=[$2]) + HiveJoin(condition=[=($1, $6)], 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_item_sk=[$15], cs_ext_sales_price=[$23]) HiveFilter(condition=[AND(IS NULL($14), IS NOT NULL($0))]) HiveTableScan(table=[[default, catalog_sales]], table:alias=[catalog_sales]) - HiveProject(i_item_sk=[$0], i_category=[$12]) - HiveTableScan(table=[[default, item]], table:alias=[item]) - HiveProject(d_date_sk=[$0], d_year=[$6], d_qoy=[$10]) - HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) + HiveProject(d_date_sk=[$0], d_year=[$6], d_qoy=[$10]) + HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) + HiveProject(i_item_sk=[$0], i_category=[$12]) + HiveTableScan(table=[[default, item]], table:alias=[item]) diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query83.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query83.q.out index 2a5101533f..ef313ad874 100644 --- a/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query83.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query83.q.out @@ -148,15 +148,12 @@ HiveSortLimit(sort0=[$0], sort1=[$1], dir0=[ASC], dir1=[ASC], fetch=[100]) 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]) - 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]) + HiveAggregate(group=[{7}], agg#0=[sum($2)]) + HiveJoin(condition=[=($1, $6)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($0, $3)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(cr_returned_date_sk=[$0], cr_item_sk=[$2], cr_return_quantity=[$17]) HiveFilter(condition=[IS NOT NULL($0)]) HiveTableScan(table=[[default, catalog_returns]], table:alias=[catalog_returns]) - HiveProject(i_item_sk=[$0], i_item_id=[$1]) - HiveTableScan(table=[[default, item]], table:alias=[item]) - HiveProject(d_date_sk=[$0], d_date=[$1], d_date0=[$2]) HiveJoin(condition=[=($1, $2)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(d_date_sk=[$0], d_date=[$2]) HiveFilter(condition=[IS NOT NULL($2)]) @@ -170,16 +167,15 @@ 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_sk=[$0], i_item_id=[$1]) + HiveTableScan(table=[[default, item]], table:alias=[item]) HiveProject(i_item_id=[$0], $f1=[$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]) + HiveAggregate(group=[{7}], agg#0=[sum($2)]) + HiveJoin(condition=[=($1, $6)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($0, $3)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(sr_returned_date_sk=[$0], sr_item_sk=[$2], sr_return_quantity=[$10]) HiveFilter(condition=[IS NOT NULL($0)]) HiveTableScan(table=[[default, store_returns]], table:alias=[store_returns]) - HiveProject(i_item_sk=[$0], i_item_id=[$1]) - HiveTableScan(table=[[default, item]], table:alias=[item]) - HiveProject(d_date_sk=[$0], d_date=[$1], d_date0=[$2]) HiveJoin(condition=[=($1, $2)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(d_date_sk=[$0], d_date=[$2]) HiveFilter(condition=[IS NOT NULL($2)]) @@ -193,16 +189,15 @@ 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_sk=[$0], i_item_id=[$1]) + HiveTableScan(table=[[default, item]], table:alias=[item]) HiveProject(item_id=[$0], wr_item_qty=[$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]) + HiveAggregate(group=[{7}], agg#0=[sum($2)]) + HiveJoin(condition=[=($1, $6)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($0, $3)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(wr_returned_date_sk=[$0], wr_item_sk=[$2], wr_return_quantity=[$14]) HiveFilter(condition=[IS NOT NULL($0)]) HiveTableScan(table=[[default, web_returns]], table:alias=[web_returns]) - HiveProject(i_item_sk=[$0], i_item_id=[$1]) - HiveTableScan(table=[[default, item]], table:alias=[item]) - HiveProject(d_date_sk=[$0], d_date=[$1], d_date0=[$2]) HiveJoin(condition=[=($1, $2)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(d_date_sk=[$0], d_date=[$2]) HiveFilter(condition=[IS NOT NULL($2)]) @@ -216,4 +211,6 @@ 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_sk=[$0], i_item_id=[$1]) + HiveTableScan(table=[[default, item]], table:alias=[item]) diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query85.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query85.q.out index 1876936968..6471345141 100644 --- a/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query85.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query85.q.out @@ -184,18 +184,18 @@ 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=[{14}], agg#0=[sum($30)], agg#1=[count($30)], agg#2=[sum($26)], agg#3=[count($26)], agg#4=[sum($25)], agg#5=[count($25)]) - HiveJoin(condition=[AND(AND(AND(=($1, $17), =($2, $18)), =($0, $20)), OR(AND($3, $4, $34), AND($5, $6, $35), AND($7, $8, $36)))], 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'))]) - HiveTableScan(table=[[default, customer_demographics]], table:alias=[cd1]) - HiveJoin(condition=[AND(=($0, $12), OR(AND($1, $22), AND($2, $23), AND($3, $24)))], 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'))]) - HiveTableScan(table=[[default, customer_address]], table:alias=[customer_address]) - HiveJoin(condition=[=($0, $10)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(r_reason_sk=[$0], r_reason_desc=[$2]) - HiveTableScan(table=[[default, reason]], table:alias=[reason]) + HiveAggregate(group=[{1}], agg#0=[sum($30)], agg#1=[count($30)], agg#2=[sum($26)], agg#3=[count($26)], agg#4=[sum($25)], agg#5=[count($25)]) + HiveJoin(condition=[=($0, $23)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(r_reason_sk=[$0], r_reason_desc=[$2]) + HiveTableScan(table=[[default, reason]], table:alias=[reason]) + HiveJoin(condition=[AND(AND(AND(=($1, $15), =($2, $16)), =($0, $18)), OR(AND($3, $4, $32), AND($5, $6, $33), AND($7, $8, $34)))], 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'))]) + HiveTableScan(table=[[default, customer_demographics]], table:alias=[cd1]) + HiveJoin(condition=[AND(=($0, $10), OR(AND($1, $20), AND($2, $21), AND($3, $22)))], 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'))]) + HiveTableScan(table=[[default, customer_address]], table:alias=[customer_address]) HiveJoin(condition=[=($12, $0)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(d_date_sk=[$0]) HiveFilter(condition=[=($6, 1998)]) diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query91.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query91.q.out index 046a374e26..0017776216 100644 --- a/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query91.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query91.q.out @@ -78,22 +78,22 @@ 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=[{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=[=($11, -7)]) - HiveTableScan(table=[[default, customer_address]], table:alias=[customer_address]) - HiveJoin(condition=[=($4, $1)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(c_customer_sk=[$0], c_current_cdemo_sk=[$2], c_current_hdemo_sk=[$3], c_current_addr_sk=[$4]) - HiveFilter(condition=[AND(IS NOT NULL($4), IS NOT NULL($2), IS NOT NULL($3))]) - HiveTableScan(table=[[default, customer]], table:alias=[customer]) - 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')))]) - 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], 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]) + HiveAggregate(group=[{6, 7, 15, 16, 17}], agg#0=[sum($11)]) + HiveJoin(condition=[=($10, $14)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($13, $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=[=($11, -7)]) + HiveTableScan(table=[[default, customer_address]], table:alias=[customer_address]) + HiveJoin(condition=[=($4, $1)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(c_customer_sk=[$0], c_current_cdemo_sk=[$2], c_current_hdemo_sk=[$3], c_current_addr_sk=[$4]) + HiveFilter(condition=[AND(IS NOT NULL($4), IS NOT NULL($2), IS NOT NULL($3))]) + HiveTableScan(table=[[default, customer]], table:alias=[customer]) + 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')))]) + 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]) 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))]) @@ -101,9 +101,9 @@ HiveProject(call_center=[$0], call_center_name=[$1], manager=[$2], returns_loss= HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(=($6, 1999), =($8, 11))]) 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]) - HiveTableScan(table=[[default, call_center]], table:alias=[call_center]) - HiveProject(hd_demo_sk=[$0]) - HiveFilter(condition=[LIKE($2, _UTF-16LE'0-500%')]) - HiveTableScan(table=[[default, household_demographics]], table:alias=[household_demographics]) + HiveProject(hd_demo_sk=[$0]) + HiveFilter(condition=[LIKE($2, _UTF-16LE'0-500%')]) + HiveTableScan(table=[[default, household_demographics]], table:alias=[household_demographics]) + HiveProject(cc_call_center_sk=[$0], cc_call_center_id=[$1], cc_name=[$6], cc_manager=[$11]) + HiveTableScan(table=[[default, call_center]], table:alias=[call_center]) diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query99.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query99.q.out index 2dccdf2c90..1cc459c6bc 100644 --- a/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query99.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query99.q.out @@ -81,10 +81,10 @@ 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=[$2], sm_type=[$0], cc_name=[$1], 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)=[$2]) + HiveProject(_o__c0=[$1], sm_type=[$0], 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)=[$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=[=($3, $14)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveJoin(condition=[=($1, $12)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($1, $14)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($3, $12)], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($2, $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)]) @@ -95,8 +95,8 @@ HiveProject(_o__c0=[$0], sm_type=[$1], cc_name=[$2], 30 days=[$3], 31-60 days=[$ HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) HiveProject(sm_ship_mode_sk=[$0], sm_type=[$2]) HiveTableScan(table=[[default, ship_mode]], table:alias=[ship_mode]) - HiveProject(cc_call_center_sk=[$0], cc_name=[$6]) - HiveTableScan(table=[[default, call_center]], table:alias=[call_center]) - HiveProject(w_warehouse_sk=[$0], substr=[substr($2, 1, 20)]) - HiveTableScan(table=[[default, warehouse]], table:alias=[warehouse]) + HiveProject(w_warehouse_sk=[$0], substr=[substr($2, 1, 20)]) + HiveTableScan(table=[[default, warehouse]], table:alias=[warehouse]) + HiveProject(cc_call_center_sk=[$0], cc_name=[$6]) + HiveTableScan(table=[[default, call_center]], table:alias=[call_center]) diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/query11.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/query11.q.out index 00b6bcbe1a..7e0582e164 100644 --- a/ql/src/test/results/clientpositive/perf/tez/constraints/query11.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/query11.q.out @@ -159,10 +159,10 @@ POSTHOOK: Output: hdfs://### HDFS PATH ### Plan optimized by CBO. Vertex dependency in root stage -Map 1 <- Reducer 23 (BROADCAST_EDGE) -Map 13 <- Reducer 25 (BROADCAST_EDGE) +Map 1 <- Reducer 24 (BROADCAST_EDGE) +Map 13 <- Reducer 23 (BROADCAST_EDGE) Map 17 <- Reducer 22 (BROADCAST_EDGE) -Map 9 <- Reducer 24 (BROADCAST_EDGE) +Map 9 <- Reducer 25 (BROADCAST_EDGE) Reducer 10 <- Map 21 (SIMPLE_EDGE), Map 9 (SIMPLE_EDGE) Reducer 11 <- Map 26 (SIMPLE_EDGE), Reducer 10 (SIMPLE_EDGE) Reducer 12 <- Reducer 11 (SIMPLE_EDGE) @@ -192,16 +192,16 @@ Stage-0 File Output Operator [FS_349] Limit [LIM_348] (rows=100 width=85) Number of rows:100 - Select Operator [SEL_347] (rows=12248093 width=85) + Select Operator [SEL_347] (rows=12248094 width=85) Output:["_col0"] <-Reducer 7 [SIMPLE_EDGE] SHUFFLE [RS_89] - Select Operator [SEL_88] (rows=12248093 width=85) + Select Operator [SEL_88] (rows=12248094 width=85) Output:["_col0"] - Filter Operator [FIL_87] (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_283] (rows=24496186 width=537) - Conds:RS_84._col2=RS_346._col0(Inner),Output:["_col1","_col3","_col5","_col6","_col8","_col9"] + Filter Operator [FIL_87] (rows=12248094 width=537) + predicate:CASE WHEN (_col4 is not null) THEN (CASE WHEN (_col2) THEN (((_col6 / _col1) > (_col9 / _col4))) ELSE ((null > (_col9 / _col4))) END) ELSE (CASE WHEN (_col2) THEN (((_col6 / _col1) > null)) ELSE (null) END) END + Merge Join Operator [MERGEJOIN_283] (rows=24496188 width=537) + Conds:RS_84._col3=RS_346._col0(Inner),Output:["_col1","_col2","_col4","_col6","_col8","_col9"] <-Reducer 20 [SIMPLE_EDGE] vectorized SHUFFLE [RS_346] PartitionCols:_col0 @@ -259,96 +259,143 @@ Stage-0 Please refer to the previous Select Operator [SEL_287] <-Reducer 6 [ONE_TO_ONE_EDGE] FORWARD [RS_84] - PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_282] (rows=20485011 width=440) - Conds:RS_81._col2=RS_338._col0(Inner),Output:["_col1","_col2","_col3","_col5","_col6"] + PartitionCols:_col3 + Merge Join Operator [MERGEJOIN_282] (rows=20485012 width=440) + Conds:RS_81._col3=RS_338._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col6"] <-Reducer 16 [SIMPLE_EDGE] vectorized SHUFFLE [RS_338] PartitionCols:_col0 - Select Operator [SEL_337] (rows=17130654 width=216) - Output:["_col0","_col1","_col2"] - Filter Operator [FIL_336] (rows=17130654 width=212) - predicate:(_col7 > 0) - Select Operator [SEL_335] (rows=51391963 width=212) - Output:["_col0","_col7"] - Group By Operator [GBY_334] (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_55] - PartitionCols:_col0, _col1, _col2, _col3, _col4, _col5, _col6 - Group By Operator [GBY_54] (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_50._col1=RS_315._col0(Inner),Output:["_col2","_col5","_col6","_col7","_col8","_col9","_col10","_col11"] - <-Map 26 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_315] + Select Operator [SEL_337] (rows=51391963 width=212) + Output:["_col0","_col1"] + Group By Operator [GBY_336] (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_56] + PartitionCols:_col0, _col1, _col2, _col3, _col4, _col5, _col6 + Group By Operator [GBY_55] (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_51._col1=RS_313._col0(Inner),Output:["_col2","_col5","_col6","_col7","_col8","_col9","_col10","_col11"] + <-Map 26 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_313] + PartitionCols:_col0 + Please refer to the previous Select Operator [SEL_311] + <-Reducer 14 [SIMPLE_EDGE] + SHUFFLE [RS_51] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_277] (rows=51391963 width=115) + Conds:RS_335._col0=RS_292._col0(Inner),Output:["_col1","_col2"] + <-Map 21 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_292] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_311] - <-Reducer 14 [SIMPLE_EDGE] - SHUFFLE [RS_50] - PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_277] (rows=51391963 width=115) - Conds:RS_333._col0=RS_296._col0(Inner),Output:["_col1","_col2"] - <-Map 21 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_296] - PartitionCols:_col0 - Select Operator [SEL_289] (rows=652 width=4) - Output:["_col0"] - Filter Operator [FIL_286] (rows=652 width=8) - predicate:(d_year = 2001) - Please refer to the previous TableScan [TS_62] - <-Map 13 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_333] - PartitionCols:_col0 - Select Operator [SEL_332] (rows=143930993 width=119) - Output:["_col0","_col1","_col2"] - Filter Operator [FIL_331] (rows=143930993 width=231) - predicate:((ws_sold_date_sk BETWEEN DynamicValue(RS_48_date_dim_d_date_sk_min) AND DynamicValue(RS_48_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_48_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_39] (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_330] - Group By Operator [GBY_329] (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_305] - Group By Operator [GBY_301] (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_289] + Please refer to the previous Select Operator [SEL_287] + <-Map 13 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_335] + PartitionCols:_col0 + Select Operator [SEL_334] (rows=143930993 width=119) + Output:["_col0","_col1","_col2"] + Filter Operator [FIL_333] (rows=143930993 width=231) + predicate:((ws_sold_date_sk BETWEEN DynamicValue(RS_49_date_dim_d_date_sk_min) AND DynamicValue(RS_49_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_49_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_40] (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_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 21 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_303] + Group By Operator [GBY_299] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_293] (rows=652 width=4) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_287] <-Reducer 5 [ONE_TO_ONE_EDGE] FORWARD [RS_81] - PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_281] (rows=31888273 width=324) - Conds:RS_318._col0=RS_328._col0(Inner),Output:["_col1","_col2","_col3"] + PartitionCols:_col3 + Merge Join Operator [MERGEJOIN_281] (rows=17130654 width=328) + Conds:RS_320._col0=RS_330._col0(Inner),Output:["_col1","_col2","_col3","_col4"] <-Reducer 12 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_328] + SHUFFLE [RS_330] PartitionCols:_col0 - Select Operator [SEL_327] (rows=26666666 width=212) + Select Operator [SEL_329] (rows=26666666 width=212) Output:["_col0","_col1"] - Filter Operator [FIL_326] (rows=26666666 width=212) + Filter Operator [FIL_328] (rows=26666666 width=212) predicate:(_col7 > 0) - Select Operator [SEL_325] (rows=80000000 width=212) + Select Operator [SEL_327] (rows=80000000 width=212) Output:["_col0","_col7"] - Group By Operator [GBY_324] (rows=80000000 width=764) + Group By Operator [GBY_326] (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_35] + SHUFFLE [RS_36] PartitionCols:_col0, _col1, _col2, _col3, _col4, _col5, _col6 - Group By Operator [GBY_34] (rows=80000000 width=764) + Group By Operator [GBY_35] (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_276] (rows=187573258 width=764) - Conds:RS_30._col1=RS_314._col0(Inner),Output:["_col2","_col5","_col6","_col7","_col8","_col9","_col10","_col11"] + Conds:RS_31._col1=RS_315._col0(Inner),Output:["_col2","_col5","_col6","_col7","_col8","_col9","_col10","_col11"] <-Map 26 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_314] + SHUFFLE [RS_315] PartitionCols:_col0 Please refer to the previous Select Operator [SEL_311] <-Reducer 10 [SIMPLE_EDGE] - SHUFFLE [RS_30] + SHUFFLE [RS_31] PartitionCols:_col1 Merge Join Operator [MERGEJOIN_275] (rows=187573258 width=115) - Conds:RS_323._col0=RS_294._col0(Inner),Output:["_col1","_col2"] + Conds:RS_325._col0=RS_296._col0(Inner),Output:["_col1","_col2"] + <-Map 21 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_296] + PartitionCols:_col0 + Select Operator [SEL_289] (rows=652 width=4) + Output:["_col0"] + Filter Operator [FIL_286] (rows=652 width=8) + predicate:(d_year = 2001) + Please refer to the previous TableScan [TS_62] + <-Map 9 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_325] + PartitionCols:_col0 + Select Operator [SEL_324] (rows=525327388 width=119) + Output:["_col0","_col1","_col2"] + Filter Operator [FIL_323] (rows=525327388 width=221) + predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_29_date_dim_d_date_sk_min) AND DynamicValue(RS_29_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_29_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 25 [BROADCAST_EDGE] vectorized + BROADCAST [RS_322] + Group By Operator [GBY_321] (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_305] + Group By Operator [GBY_301] (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_289] + <-Reducer 4 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_320] + PartitionCols:_col0 + Select Operator [SEL_319] (rows=17130654 width=216) + Output:["_col0","_col1","_col2"] + Filter Operator [FIL_318] (rows=17130654 width=212) + predicate:(_col7 > 0) + Select Operator [SEL_317] (rows=51391963 width=212) + Output:["_col0","_col7"] + Group By Operator [GBY_316] (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_16] + PartitionCols:_col0, _col1, _col2, _col3, _col4, _col5, _col6 + Group By Operator [GBY_15] (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_274] (rows=51391963 width=764) + Conds:RS_11._col1=RS_314._col0(Inner),Output:["_col2","_col5","_col6","_col7","_col8","_col9","_col10","_col11"] + <-Map 26 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_314] + PartitionCols:_col0 + Please refer to the previous Select Operator [SEL_311] + <-Reducer 2 [SIMPLE_EDGE] + SHUFFLE [RS_11] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_273] (rows=51391963 width=115) + Conds:RS_310._col0=RS_294._col0(Inner),Output:["_col1","_col2"] <-Map 21 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_294] PartitionCols:_col0 @@ -357,18 +404,18 @@ Stage-0 Filter Operator [FIL_285] (rows=652 width=8) predicate:(d_year = 2001) Please refer to the previous TableScan [TS_62] - <-Map 9 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_323] + <-Map 1 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_310] PartitionCols:_col0 - Select Operator [SEL_322] (rows=525327388 width=119) + Select Operator [SEL_309] (rows=143930993 width=119) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_321] (rows=525327388 width=221) - predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_28_date_dim_d_date_sk_min) AND DynamicValue(RS_28_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_28_date_dim_d_date_sk_bloom_filter))) and ss_customer_sk is not null and ss_sold_date_sk is not null) - TableScan [TS_19] (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"] + Filter Operator [FIL_308] (rows=143930993 width=231) + predicate:((ws_sold_date_sk BETWEEN DynamicValue(RS_9_date_dim_d_date_sk_min) AND DynamicValue(RS_9_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_9_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 24 [BROADCAST_EDGE] vectorized - BROADCAST [RS_320] - Group By Operator [GBY_319] (rows=1 width=12) + BROADCAST [RS_307] + Group By Operator [GBY_306] (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_304] @@ -377,51 +424,4 @@ Stage-0 Select Operator [SEL_295] (rows=652 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_288] - <-Reducer 4 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_318] - PartitionCols:_col0 - Select Operator [SEL_317] (rows=51391963 width=212) - Output:["_col0","_col1"] - Group By Operator [GBY_316] (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_16] - PartitionCols:_col0, _col1, _col2, _col3, _col4, _col5, _col6 - Group By Operator [GBY_15] (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_274] (rows=51391963 width=764) - Conds:RS_11._col1=RS_313._col0(Inner),Output:["_col2","_col5","_col6","_col7","_col8","_col9","_col10","_col11"] - <-Map 26 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_313] - PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_311] - <-Reducer 2 [SIMPLE_EDGE] - SHUFFLE [RS_11] - PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_273] (rows=51391963 width=115) - Conds:RS_310._col0=RS_292._col0(Inner),Output:["_col1","_col2"] - <-Map 21 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_292] - PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_287] - <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_310] - PartitionCols:_col0 - Select Operator [SEL_309] (rows=143930993 width=119) - Output:["_col0","_col1","_col2"] - Filter Operator [FIL_308] (rows=143930993 width=231) - predicate:((ws_sold_date_sk BETWEEN DynamicValue(RS_9_date_dim_d_date_sk_min) AND DynamicValue(RS_9_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_9_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_307] - Group By Operator [GBY_306] (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_303] - Group By Operator [GBY_299] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_293] (rows=652 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_287] diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/query14.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/query14.q.out index e8a6eaa464..cf894a20f9 100644 --- a/ql/src/test/results/clientpositive/perf/tez/constraints/query14.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/query14.q.out @@ -1,9 +1,9 @@ -Warning: Shuffle Join MERGEJOIN[1431][tables = [$hdt$_1, $hdt$_2]] in Stage 'Reducer 5' is a cross product -Warning: Shuffle Join MERGEJOIN[1443][tables = [$hdt$_1, $hdt$_2, $hdt$_0]] in Stage 'Reducer 6' is a cross product -Warning: Shuffle Join MERGEJOIN[1433][tables = [$hdt$_1, $hdt$_2]] in Stage 'Reducer 13' is a cross product -Warning: Shuffle Join MERGEJOIN[1456][tables = [$hdt$_1, $hdt$_2, $hdt$_0]] in Stage 'Reducer 14' is a cross product -Warning: Shuffle Join MERGEJOIN[1435][tables = [$hdt$_2, $hdt$_3]] in Stage 'Reducer 18' is a cross product -Warning: Shuffle Join MERGEJOIN[1469][tables = [$hdt$_2, $hdt$_3, $hdt$_1]] in Stage 'Reducer 19' is a cross product +Warning: Shuffle Join MERGEJOIN[1458][tables = [$hdt$_1, $hdt$_2]] in Stage 'Reducer 5' is a cross product +Warning: Shuffle Join MERGEJOIN[1470][tables = [$hdt$_1, $hdt$_2, $hdt$_0]] in Stage 'Reducer 6' is a cross product +Warning: Shuffle Join MERGEJOIN[1460][tables = [$hdt$_1, $hdt$_2]] in Stage 'Reducer 13' is a cross product +Warning: Shuffle Join MERGEJOIN[1483][tables = [$hdt$_1, $hdt$_2, $hdt$_0]] in Stage 'Reducer 14' is a cross product +Warning: Shuffle Join MERGEJOIN[1462][tables = [$hdt$_2, $hdt$_3]] in Stage 'Reducer 18' is a cross product +Warning: Shuffle Join MERGEJOIN[1496][tables = [$hdt$_2, $hdt$_3, $hdt$_1]] in Stage 'Reducer 19' is a cross product PREHOOK: query: explain with cross_items as (select i_item_sk ss_item_sk @@ -225,34 +225,30 @@ POSTHOOK: Output: hdfs://### HDFS PATH ### Plan optimized by CBO. Vertex dependency in root stage -Map 1 <- Reducer 105 (BROADCAST_EDGE) -Map 107 <- Reducer 102 (BROADCAST_EDGE) -Map 108 <- Reducer 104 (BROADCAST_EDGE) -Map 109 <- Reducer 63 (BROADCAST_EDGE), Reducer 81 (BROADCAST_EDGE) -Map 110 <- Reducer 68 (BROADCAST_EDGE), Reducer 90 (BROADCAST_EDGE) +Map 1 <- Reducer 101 (BROADCAST_EDGE) +Map 103 <- Reducer 94 (BROADCAST_EDGE) +Map 104 <- Reducer 100 (BROADCAST_EDGE) +Map 106 <- Reducer 63 (BROADCAST_EDGE), Reducer 81 (BROADCAST_EDGE) +Map 107 <- Reducer 68 (BROADCAST_EDGE), Reducer 86 (BROADCAST_EDGE) Map 20 <- Reducer 25 (BROADCAST_EDGE) Map 36 <- Reducer 41 (BROADCAST_EDGE) -Map 46 <- Reducer 106 (BROADCAST_EDGE) +Map 46 <- Reducer 102 (BROADCAST_EDGE) Map 50 <- Reducer 29 (BROADCAST_EDGE) Map 51 <- Reducer 43 (BROADCAST_EDGE) -Map 52 <- Reducer 58 (BROADCAST_EDGE), Reducer 71 (BROADCAST_EDGE) -Map 97 <- Reducer 100 (BROADCAST_EDGE) -Reducer 10 <- Map 1 (SIMPLE_EDGE), Map 99 (SIMPLE_EDGE), Union 11 (CONTAINS) -Reducer 100 <- Map 99 (CUSTOM_SIMPLE_EDGE) -Reducer 101 <- Map 107 (SIMPLE_EDGE), Map 99 (SIMPLE_EDGE) -Reducer 102 <- Map 99 (CUSTOM_SIMPLE_EDGE) -Reducer 103 <- Map 108 (SIMPLE_EDGE), Map 99 (SIMPLE_EDGE) -Reducer 104 <- Map 99 (CUSTOM_SIMPLE_EDGE) -Reducer 105 <- Map 99 (CUSTOM_SIMPLE_EDGE) -Reducer 106 <- Map 99 (CUSTOM_SIMPLE_EDGE) +Map 52 <- Reducer 58 (BROADCAST_EDGE), Reducer 76 (BROADCAST_EDGE) +Map 69 <- Reducer 88 (BROADCAST_EDGE) +Reducer 10 <- Map 1 (SIMPLE_EDGE), Map 87 (SIMPLE_EDGE), Union 11 (CONTAINS) +Reducer 100 <- Map 87 (CUSTOM_SIMPLE_EDGE) +Reducer 101 <- Map 87 (CUSTOM_SIMPLE_EDGE) +Reducer 102 <- Map 87 (CUSTOM_SIMPLE_EDGE) Reducer 12 <- Union 11 (CUSTOM_SIMPLE_EDGE) Reducer 13 <- Reducer 12 (CUSTOM_SIMPLE_EDGE), Reducer 32 (CUSTOM_SIMPLE_EDGE) Reducer 14 <- Reducer 13 (CUSTOM_SIMPLE_EDGE), Reducer 62 (CUSTOM_SIMPLE_EDGE), Union 7 (CONTAINS) -Reducer 15 <- Map 1 (SIMPLE_EDGE), Map 99 (SIMPLE_EDGE), Union 16 (CONTAINS) +Reducer 15 <- Map 1 (SIMPLE_EDGE), Map 87 (SIMPLE_EDGE), Union 16 (CONTAINS) Reducer 17 <- Union 16 (CUSTOM_SIMPLE_EDGE) Reducer 18 <- Reducer 17 (CUSTOM_SIMPLE_EDGE), Reducer 35 (CUSTOM_SIMPLE_EDGE) Reducer 19 <- Reducer 18 (CUSTOM_SIMPLE_EDGE), Reducer 67 (CUSTOM_SIMPLE_EDGE), Union 7 (CONTAINS) -Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 99 (SIMPLE_EDGE), Union 3 (CONTAINS) +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 87 (SIMPLE_EDGE), Union 3 (CONTAINS) Reducer 21 <- Map 20 (SIMPLE_EDGE), Map 24 (SIMPLE_EDGE), Union 3 (CONTAINS) Reducer 22 <- Map 20 (SIMPLE_EDGE), Map 24 (SIMPLE_EDGE), Union 11 (CONTAINS) Reducer 23 <- Map 20 (SIMPLE_EDGE), Map 24 (SIMPLE_EDGE), Union 16 (CONTAINS) @@ -273,328 +269,329 @@ Reducer 42 <- Map 40 (SIMPLE_EDGE), Map 51 (SIMPLE_EDGE), Union 27 (CONTAINS) Reducer 43 <- Map 40 (CUSTOM_SIMPLE_EDGE) Reducer 44 <- Map 40 (SIMPLE_EDGE), Map 51 (SIMPLE_EDGE), Union 31 (CONTAINS) Reducer 45 <- Map 40 (SIMPLE_EDGE), Map 51 (SIMPLE_EDGE), Union 34 (CONTAINS) -Reducer 47 <- Map 46 (SIMPLE_EDGE), Map 99 (SIMPLE_EDGE), Union 27 (CONTAINS) -Reducer 48 <- Map 46 (SIMPLE_EDGE), Map 99 (SIMPLE_EDGE), Union 31 (CONTAINS) -Reducer 49 <- Map 46 (SIMPLE_EDGE), Map 99 (SIMPLE_EDGE), Union 34 (CONTAINS) +Reducer 47 <- Map 46 (SIMPLE_EDGE), Map 87 (SIMPLE_EDGE), Union 27 (CONTAINS) +Reducer 48 <- Map 46 (SIMPLE_EDGE), Map 87 (SIMPLE_EDGE), Union 31 (CONTAINS) +Reducer 49 <- Map 46 (SIMPLE_EDGE), Map 87 (SIMPLE_EDGE), Union 34 (CONTAINS) Reducer 5 <- Reducer 28 (CUSTOM_SIMPLE_EDGE), Reducer 4 (CUSTOM_SIMPLE_EDGE) Reducer 53 <- Map 52 (SIMPLE_EDGE), Map 57 (SIMPLE_EDGE) -Reducer 54 <- Map 69 (SIMPLE_EDGE), Reducer 53 (SIMPLE_EDGE) -Reducer 55 <- Reducer 54 (ONE_TO_ONE_EDGE), Reducer 70 (SIMPLE_EDGE) +Reducer 54 <- Reducer 53 (SIMPLE_EDGE), Reducer 75 (SIMPLE_EDGE) +Reducer 55 <- Map 105 (SIMPLE_EDGE), Reducer 54 (ONE_TO_ONE_EDGE) Reducer 56 <- Reducer 55 (SIMPLE_EDGE) Reducer 58 <- Map 57 (CUSTOM_SIMPLE_EDGE) -Reducer 59 <- Map 109 (SIMPLE_EDGE), Map 57 (SIMPLE_EDGE) +Reducer 59 <- Map 106 (SIMPLE_EDGE), Map 57 (SIMPLE_EDGE) Reducer 6 <- Reducer 5 (CUSTOM_SIMPLE_EDGE), Reducer 56 (CUSTOM_SIMPLE_EDGE), Union 7 (CONTAINS) -Reducer 60 <- Map 69 (SIMPLE_EDGE), Reducer 59 (SIMPLE_EDGE) -Reducer 61 <- Reducer 60 (ONE_TO_ONE_EDGE), Reducer 80 (SIMPLE_EDGE) +Reducer 60 <- Reducer 59 (SIMPLE_EDGE), Reducer 80 (SIMPLE_EDGE) +Reducer 61 <- Map 105 (SIMPLE_EDGE), Reducer 60 (ONE_TO_ONE_EDGE) Reducer 62 <- Reducer 61 (SIMPLE_EDGE) Reducer 63 <- Map 57 (CUSTOM_SIMPLE_EDGE) -Reducer 64 <- Map 110 (SIMPLE_EDGE), Map 57 (SIMPLE_EDGE) -Reducer 65 <- Map 69 (SIMPLE_EDGE), Reducer 64 (SIMPLE_EDGE) -Reducer 66 <- Reducer 65 (ONE_TO_ONE_EDGE), Reducer 89 (SIMPLE_EDGE) +Reducer 64 <- Map 107 (SIMPLE_EDGE), Map 57 (SIMPLE_EDGE) +Reducer 65 <- Reducer 64 (SIMPLE_EDGE), Reducer 85 (SIMPLE_EDGE) +Reducer 66 <- Map 105 (SIMPLE_EDGE), Reducer 65 (ONE_TO_ONE_EDGE) Reducer 67 <- Reducer 66 (SIMPLE_EDGE) Reducer 68 <- Map 57 (CUSTOM_SIMPLE_EDGE) -Reducer 70 <- Map 69 (SIMPLE_EDGE), Reducer 75 (ONE_TO_ONE_EDGE) -Reducer 71 <- Reducer 70 (CUSTOM_SIMPLE_EDGE) -Reducer 72 <- Map 69 (SIMPLE_EDGE), Reducer 98 (SIMPLE_EDGE) -Reducer 73 <- Reducer 72 (SIMPLE_EDGE), Union 74 (CONTAINS) -Reducer 75 <- Union 74 (SIMPLE_EDGE) -Reducer 76 <- Map 69 (SIMPLE_EDGE), Reducer 101 (SIMPLE_EDGE) -Reducer 77 <- Reducer 76 (SIMPLE_EDGE), Union 74 (CONTAINS) -Reducer 78 <- Map 69 (SIMPLE_EDGE), Reducer 103 (SIMPLE_EDGE) -Reducer 79 <- Reducer 78 (SIMPLE_EDGE), Union 74 (CONTAINS) +Reducer 70 <- Map 69 (SIMPLE_EDGE), Map 87 (SIMPLE_EDGE) +Reducer 71 <- Map 105 (SIMPLE_EDGE), Reducer 70 (SIMPLE_EDGE) +Reducer 72 <- Reducer 71 (SIMPLE_EDGE), Union 73 (CONTAINS) +Reducer 74 <- Union 73 (SIMPLE_EDGE) +Reducer 75 <- Map 105 (SIMPLE_EDGE), Reducer 74 (ONE_TO_ONE_EDGE) +Reducer 76 <- Reducer 75 (CUSTOM_SIMPLE_EDGE) +Reducer 77 <- Reducer 71 (SIMPLE_EDGE), Union 78 (CONTAINS) +Reducer 79 <- Union 78 (SIMPLE_EDGE) Reducer 8 <- Union 7 (SIMPLE_EDGE) -Reducer 80 <- Map 69 (SIMPLE_EDGE), Reducer 85 (ONE_TO_ONE_EDGE) +Reducer 80 <- Map 105 (SIMPLE_EDGE), Reducer 79 (ONE_TO_ONE_EDGE) Reducer 81 <- Reducer 80 (CUSTOM_SIMPLE_EDGE) -Reducer 82 <- Map 69 (SIMPLE_EDGE), Reducer 98 (SIMPLE_EDGE) -Reducer 83 <- Reducer 82 (SIMPLE_EDGE), Union 84 (CONTAINS) -Reducer 85 <- Union 84 (SIMPLE_EDGE) -Reducer 86 <- Reducer 82 (SIMPLE_EDGE), Union 87 (CONTAINS) -Reducer 88 <- Union 87 (SIMPLE_EDGE) -Reducer 89 <- Map 69 (SIMPLE_EDGE), Reducer 88 (ONE_TO_ONE_EDGE) +Reducer 82 <- Reducer 71 (SIMPLE_EDGE), Union 83 (CONTAINS) +Reducer 84 <- Union 83 (SIMPLE_EDGE) +Reducer 85 <- Map 105 (SIMPLE_EDGE), Reducer 84 (ONE_TO_ONE_EDGE) +Reducer 86 <- Reducer 85 (CUSTOM_SIMPLE_EDGE) +Reducer 88 <- Map 87 (CUSTOM_SIMPLE_EDGE) +Reducer 89 <- Map 103 (SIMPLE_EDGE), Map 87 (SIMPLE_EDGE) Reducer 9 <- Reducer 8 (SIMPLE_EDGE) -Reducer 90 <- Reducer 89 (CUSTOM_SIMPLE_EDGE) -Reducer 91 <- Map 69 (SIMPLE_EDGE), Reducer 101 (SIMPLE_EDGE) -Reducer 92 <- Reducer 91 (SIMPLE_EDGE), Union 84 (CONTAINS) -Reducer 93 <- Reducer 91 (SIMPLE_EDGE), Union 87 (CONTAINS) -Reducer 94 <- Map 69 (SIMPLE_EDGE), Reducer 103 (SIMPLE_EDGE) -Reducer 95 <- Reducer 94 (SIMPLE_EDGE), Union 84 (CONTAINS) -Reducer 96 <- Reducer 94 (SIMPLE_EDGE), Union 87 (CONTAINS) -Reducer 98 <- Map 97 (SIMPLE_EDGE), Map 99 (SIMPLE_EDGE) +Reducer 90 <- Map 105 (SIMPLE_EDGE), Reducer 89 (SIMPLE_EDGE) +Reducer 91 <- Reducer 90 (SIMPLE_EDGE), Union 73 (CONTAINS) +Reducer 92 <- Reducer 90 (SIMPLE_EDGE), Union 78 (CONTAINS) +Reducer 93 <- Reducer 90 (SIMPLE_EDGE), Union 83 (CONTAINS) +Reducer 94 <- Map 87 (CUSTOM_SIMPLE_EDGE) +Reducer 95 <- Map 104 (SIMPLE_EDGE), Map 87 (SIMPLE_EDGE) +Reducer 96 <- Map 105 (SIMPLE_EDGE), Reducer 95 (SIMPLE_EDGE) +Reducer 97 <- Reducer 96 (SIMPLE_EDGE), Union 73 (CONTAINS) +Reducer 98 <- Reducer 96 (SIMPLE_EDGE), Union 78 (CONTAINS) +Reducer 99 <- Reducer 96 (SIMPLE_EDGE), Union 83 (CONTAINS) Stage-0 Fetch Operator limit:100 Stage-1 Reducer 9 vectorized - File Output Operator [FS_1703] - Limit [LIM_1702] (rows=7 width=192) + File Output Operator [FS_1727] + Limit [LIM_1726] (rows=7 width=192) Number of rows:100 - Select Operator [SEL_1701] (rows=7 width=192) + Select Operator [SEL_1725] (rows=7 width=192) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] <-Reducer 8 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1700] - Select Operator [SEL_1699] (rows=7 width=192) + SHUFFLE [RS_1724] + Select Operator [SEL_1723] (rows=7 width=192) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - Group By Operator [GBY_1698] (rows=7 width=200) + Group By Operator [GBY_1722] (rows=7 width=200) Output:["_col0","_col1","_col2","_col3","_col5","_col6"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4 <-Union 7 [SIMPLE_EDGE] <-Reducer 14 [CONTAINS] - Reduce Output Operator [RS_1462] + Reduce Output Operator [RS_1489] PartitionCols:_col0, _col1, _col2, _col3, _col4 - Group By Operator [GBY_1461] (rows=7 width=200) + Group By Operator [GBY_1488] (rows=7 width=200) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"],aggregations:["sum(_col4)","sum(_col5)"],keys:_col0, _col1, _col2, _col3, 0L - Top N Key Operator [TNK_1460] (rows=3 width=221) + Top N Key Operator [TNK_1487] (rows=3 width=221) keys:_col0, _col1, _col2, _col3, 0L,sort order:+++++,top n:100 - Select Operator [SEL_1458] (rows=1 width=223) + Select Operator [SEL_1485] (rows=1 width=223) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - Filter Operator [FIL_1457] (rows=1 width=244) + Filter Operator [FIL_1484] (rows=1 width=244) predicate:(_col5 > _col1) - Merge Join Operator [MERGEJOIN_1456] (rows=1 width=244) + Merge Join Operator [MERGEJOIN_1483] (rows=1 width=244) Conds:(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col6"] <-Reducer 13 [CUSTOM_SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_371] - Merge Join Operator [MERGEJOIN_1433] (rows=1 width=112) + Merge Join Operator [MERGEJOIN_1460] (rows=1 width=112) Conds:(Inner),Output:["_col1"] <-Reducer 12 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_1709] - Select Operator [SEL_1708] (rows=1 width=8) - Filter Operator [FIL_1707] (rows=1 width=8) + PARTITION_ONLY_SHUFFLE [RS_1733] + Select Operator [SEL_1732] (rows=1 width=8) + Filter Operator [FIL_1731] (rows=1 width=8) predicate:(sq_count_check(_col0) <= 1) - Group By Operator [GBY_1706] (rows=1 width=8) + Group By Operator [GBY_1730] (rows=1 width=8) Output:["_col0"],aggregations:["count()"] - Select Operator [SEL_1705] (rows=1 width=8) - Group By Operator [GBY_1704] (rows=1 width=8) + Select Operator [SEL_1729] (rows=1 width=8) + Group By Operator [GBY_1728] (rows=1 width=8) Output:["_col0"],aggregations:["count(VALUE._col0)"] <-Union 11 [CUSTOM_SIMPLE_EDGE] <-Reducer 10 [CONTAINS] - Reduce Output Operator [RS_1455] - Group By Operator [GBY_1454] (rows=1 width=8) + Reduce Output Operator [RS_1482] + Group By Operator [GBY_1481] (rows=1 width=8) Output:["_col0"],aggregations:["count(_col0)"] - Select Operator [SEL_1453] (rows=26270325 width=1) + Select Operator [SEL_1480] (rows=26270325 width=1) Output:["_col0"] - Select Operator [SEL_1451] (rows=14736682 width=0) + Select Operator [SEL_1478] (rows=14736682 width=0) Output:["_col0"] - Merge Join Operator [MERGEJOIN_1450] (rows=14736682 width=0) - Conds:RS_1633._col0=RS_1614._col0(Inner),Output:["_col1"] - <-Map 99 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1614] + Merge Join Operator [MERGEJOIN_1477] (rows=14736682 width=0) + Conds:RS_1660._col0=RS_1641._col0(Inner),Output:["_col1"] + <-Map 87 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_1641] PartitionCols:_col0 - Select Operator [SEL_1603] (rows=1957 width=4) + Select Operator [SEL_1630] (rows=1957 width=4) Output:["_col0"] - Filter Operator [FIL_1602] (rows=1957 width=8) + Filter Operator [FIL_1629] (rows=1957 width=8) predicate:d_year BETWEEN 1999 AND 2001 - TableScan [TS_96] (rows=73049 width=8) + TableScan [TS_94] (rows=73049 width=8) default@date_dim,d1,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year"] <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1633] + SHUFFLE [RS_1660] PartitionCols:_col0 - Select Operator [SEL_1631] (rows=550076554 width=7) + Select Operator [SEL_1658] (rows=550076554 width=7) Output:["_col0","_col1"] - Filter Operator [FIL_1630] (rows=550076554 width=7) + Filter Operator [FIL_1657] (rows=550076554 width=7) predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_7_date_dim_d_date_sk_min) AND DynamicValue(RS_7_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_7_date_dim_d_date_sk_bloom_filter))) and ss_sold_date_sk is not null) TableScan [TS_0] (rows=575995635 width=7) default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_quantity"] - <-Reducer 105 [BROADCAST_EDGE] vectorized - BROADCAST [RS_1629] - Group By Operator [GBY_1628] (rows=1 width=12) + <-Reducer 101 [BROADCAST_EDGE] vectorized + BROADCAST [RS_1656] + Group By Operator [GBY_1655] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 99 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_1626] - Group By Operator [GBY_1621] (rows=1 width=12) + <-Map 87 [CUSTOM_SIMPLE_EDGE] vectorized + SHUFFLE [RS_1653] + Group By Operator [GBY_1648] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_1611] (rows=1957 width=4) + Select Operator [SEL_1638] (rows=1957 width=4) Output:["_col0"] - Please refer to the previous Select Operator [SEL_1603] + Please refer to the previous Select Operator [SEL_1630] <-Reducer 22 [CONTAINS] - Reduce Output Operator [RS_1487] - Group By Operator [GBY_1486] (rows=1 width=8) + Reduce Output Operator [RS_1514] + Group By Operator [GBY_1513] (rows=1 width=8) Output:["_col0"],aggregations:["count(_col0)"] - Select Operator [SEL_1485] (rows=26270325 width=1) + Select Operator [SEL_1512] (rows=26270325 width=1) Output:["_col0"] - Select Operator [SEL_1483] (rows=7676736 width=3) + Select Operator [SEL_1510] (rows=7676736 width=3) Output:["_col0"] - Merge Join Operator [MERGEJOIN_1482] (rows=7676736 width=3) - Conds:RS_1767._col0=RS_1754._col0(Inner),Output:["_col1"] + Merge Join Operator [MERGEJOIN_1509] (rows=7676736 width=3) + Conds:RS_1791._col0=RS_1778._col0(Inner),Output:["_col1"] <-Map 24 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1754] + SHUFFLE [RS_1778] PartitionCols:_col0 - Select Operator [SEL_1749] (rows=1957 width=4) + Select Operator [SEL_1773] (rows=1957 width=4) Output:["_col0"] - Filter Operator [FIL_1748] (rows=1957 width=8) + Filter Operator [FIL_1772] (rows=1957 width=8) predicate:d_year BETWEEN 1998 AND 2000 TableScan [TS_13] (rows=73049 width=8) default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year"] <-Map 20 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1767] + SHUFFLE [RS_1791] PartitionCols:_col0 - Select Operator [SEL_1765] (rows=286549727 width=7) + Select Operator [SEL_1789] (rows=286549727 width=7) Output:["_col0","_col1"] - Filter Operator [FIL_1764] (rows=286549727 width=7) + Filter Operator [FIL_1788] (rows=286549727 width=7) predicate:((cs_sold_date_sk BETWEEN DynamicValue(RS_17_date_dim_d_date_sk_min) AND DynamicValue(RS_17_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_17_date_dim_d_date_sk_bloom_filter))) and cs_sold_date_sk is not null) TableScan [TS_10] (rows=287989836 width=7) default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["cs_sold_date_sk","cs_quantity"] <-Reducer 25 [BROADCAST_EDGE] vectorized - BROADCAST [RS_1763] - Group By Operator [GBY_1762] (rows=1 width=12) + BROADCAST [RS_1787] + Group By Operator [GBY_1786] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Map 24 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_1760] - Group By Operator [GBY_1758] (rows=1 width=12) + SHUFFLE [RS_1784] + Group By Operator [GBY_1782] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_1751] (rows=1957 width=4) + Select Operator [SEL_1775] (rows=1957 width=4) Output:["_col0"] - Please refer to the previous Select Operator [SEL_1749] + Please refer to the previous Select Operator [SEL_1773] <-Reducer 38 [CONTAINS] - Reduce Output Operator [RS_1523] - Group By Operator [GBY_1522] (rows=1 width=8) + Reduce Output Operator [RS_1550] + Group By Operator [GBY_1549] (rows=1 width=8) Output:["_col0"],aggregations:["count(_col0)"] - Select Operator [SEL_1521] (rows=26270325 width=1) + Select Operator [SEL_1548] (rows=26270325 width=1) Output:["_col0"] - Select Operator [SEL_1519] (rows=3856907 width=3) + Select Operator [SEL_1546] (rows=3856907 width=3) Output:["_col0"] - Merge Join Operator [MERGEJOIN_1518] (rows=3856907 width=3) - Conds:RS_1795._col0=RS_1782._col0(Inner),Output:["_col1"] + Merge Join Operator [MERGEJOIN_1545] (rows=3856907 width=3) + Conds:RS_1819._col0=RS_1806._col0(Inner),Output:["_col1"] <-Map 40 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1782] + SHUFFLE [RS_1806] PartitionCols:_col0 - Select Operator [SEL_1777] (rows=1957 width=4) + Select Operator [SEL_1801] (rows=1957 width=4) Output:["_col0"] - Filter Operator [FIL_1776] (rows=1957 width=8) + Filter Operator [FIL_1800] (rows=1957 width=8) predicate:d_year BETWEEN 1998 AND 2000 TableScan [TS_24] (rows=73049 width=8) default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year"] <-Map 36 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1795] + SHUFFLE [RS_1819] PartitionCols:_col0 - Select Operator [SEL_1793] (rows=143966864 width=7) + Select Operator [SEL_1817] (rows=143966864 width=7) Output:["_col0","_col1"] - Filter Operator [FIL_1792] (rows=143966864 width=7) + Filter Operator [FIL_1816] (rows=143966864 width=7) predicate:((ws_sold_date_sk BETWEEN DynamicValue(RS_28_date_dim_d_date_sk_min) AND DynamicValue(RS_28_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_28_date_dim_d_date_sk_bloom_filter))) and ws_sold_date_sk is not null) TableScan [TS_21] (rows=144002668 width=7) default@web_sales,web_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_sold_date_sk","ws_quantity"] <-Reducer 41 [BROADCAST_EDGE] vectorized - BROADCAST [RS_1791] - Group By Operator [GBY_1790] (rows=1 width=12) + BROADCAST [RS_1815] + Group By Operator [GBY_1814] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Map 40 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_1788] - Group By Operator [GBY_1786] (rows=1 width=12) + SHUFFLE [RS_1812] + Group By Operator [GBY_1810] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_1779] (rows=1957 width=4) + Select Operator [SEL_1803] (rows=1957 width=4) Output:["_col0"] - Please refer to the previous Select Operator [SEL_1777] + Please refer to the previous Select Operator [SEL_1801] <-Reducer 32 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_1712] - Select Operator [SEL_1711] (rows=1 width=112) + PARTITION_ONLY_SHUFFLE [RS_1736] + Select Operator [SEL_1735] (rows=1 width=112) Output:["_col0"] - Group By Operator [GBY_1710] (rows=1 width=120) + Group By Operator [GBY_1734] (rows=1 width=120) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)","count(VALUE._col1)"] <-Union 31 [CUSTOM_SIMPLE_EDGE] <-Reducer 30 [CONTAINS] - Reduce Output Operator [RS_1505] - Group By Operator [GBY_1504] (rows=1 width=120) + Reduce Output Operator [RS_1532] + Group By Operator [GBY_1531] (rows=1 width=120) Output:["_col0","_col1"],aggregations:["sum(_col0)","count(_col0)"] - Select Operator [SEL_1503] (rows=26270325 width=44) + Select Operator [SEL_1530] (rows=26270325 width=44) Output:["_col0"] - Select Operator [SEL_1501] (rows=7676736 width=94) + Select Operator [SEL_1528] (rows=7676736 width=94) Output:["_col0","_col1"] - Merge Join Operator [MERGEJOIN_1500] (rows=7676736 width=94) - Conds:RS_1774._col0=RS_1755._col0(Inner),Output:["_col1","_col2"] + Merge Join Operator [MERGEJOIN_1527] (rows=7676736 width=94) + Conds:RS_1798._col0=RS_1779._col0(Inner),Output:["_col1","_col2"] <-Map 24 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1755] + SHUFFLE [RS_1779] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_1749] + Please refer to the previous Select Operator [SEL_1773] <-Map 50 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1774] + SHUFFLE [RS_1798] PartitionCols:_col0 - Select Operator [SEL_1772] (rows=286549727 width=119) + Select Operator [SEL_1796] (rows=286549727 width=119) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_1771] (rows=286549727 width=119) + Filter Operator [FIL_1795] (rows=286549727 width=119) predicate:((cs_sold_date_sk BETWEEN DynamicValue(RS_62_date_dim_d_date_sk_min) AND DynamicValue(RS_62_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_62_date_dim_d_date_sk_bloom_filter))) and cs_sold_date_sk is not null) TableScan [TS_55] (rows=287989836 width=119) default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["cs_sold_date_sk","cs_quantity","cs_list_price"] <-Reducer 29 [BROADCAST_EDGE] vectorized - BROADCAST [RS_1770] - Group By Operator [GBY_1769] (rows=1 width=12) + BROADCAST [RS_1794] + Group By Operator [GBY_1793] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Map 24 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_1761] - Group By Operator [GBY_1759] (rows=1 width=12) + SHUFFLE [RS_1785] + Group By Operator [GBY_1783] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_1753] (rows=1957 width=4) + Select Operator [SEL_1777] (rows=1957 width=4) Output:["_col0"] - Please refer to the previous Select Operator [SEL_1749] + Please refer to the previous Select Operator [SEL_1773] <-Reducer 44 [CONTAINS] - Reduce Output Operator [RS_1541] - Group By Operator [GBY_1540] (rows=1 width=120) + Reduce Output Operator [RS_1568] + Group By Operator [GBY_1567] (rows=1 width=120) Output:["_col0","_col1"],aggregations:["sum(_col0)","count(_col0)"] - Select Operator [SEL_1539] (rows=26270325 width=44) + Select Operator [SEL_1566] (rows=26270325 width=44) Output:["_col0"] - Select Operator [SEL_1537] (rows=3856907 width=114) + Select Operator [SEL_1564] (rows=3856907 width=114) Output:["_col0","_col1"] - Merge Join Operator [MERGEJOIN_1536] (rows=3856907 width=114) - Conds:RS_1802._col0=RS_1783._col0(Inner),Output:["_col1","_col2"] + Merge Join Operator [MERGEJOIN_1563] (rows=3856907 width=114) + Conds:RS_1826._col0=RS_1807._col0(Inner),Output:["_col1","_col2"] <-Map 40 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1783] + SHUFFLE [RS_1807] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_1777] + Please refer to the previous Select Operator [SEL_1801] <-Map 51 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1802] + SHUFFLE [RS_1826] PartitionCols:_col0 - Select Operator [SEL_1800] (rows=143966864 width=119) + Select Operator [SEL_1824] (rows=143966864 width=119) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_1799] (rows=143966864 width=119) + Filter Operator [FIL_1823] (rows=143966864 width=119) predicate:((ws_sold_date_sk BETWEEN DynamicValue(RS_73_date_dim_d_date_sk_min) AND DynamicValue(RS_73_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_73_date_dim_d_date_sk_bloom_filter))) and ws_sold_date_sk is not null) TableScan [TS_66] (rows=144002668 width=119) default@web_sales,web_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_sold_date_sk","ws_quantity","ws_list_price"] <-Reducer 43 [BROADCAST_EDGE] vectorized - BROADCAST [RS_1798] - Group By Operator [GBY_1797] (rows=1 width=12) + BROADCAST [RS_1822] + Group By Operator [GBY_1821] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Map 40 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_1789] - Group By Operator [GBY_1787] (rows=1 width=12) + SHUFFLE [RS_1813] + Group By Operator [GBY_1811] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_1781] (rows=1957 width=4) + Select Operator [SEL_1805] (rows=1957 width=4) Output:["_col0"] - Please refer to the previous Select Operator [SEL_1777] + Please refer to the previous Select Operator [SEL_1801] <-Reducer 48 [CONTAINS] - Reduce Output Operator [RS_1559] - Group By Operator [GBY_1558] (rows=1 width=120) + Reduce Output Operator [RS_1586] + Group By Operator [GBY_1585] (rows=1 width=120) Output:["_col0","_col1"],aggregations:["sum(_col0)","count(_col0)"] - Select Operator [SEL_1557] (rows=26270325 width=44) + Select Operator [SEL_1584] (rows=26270325 width=44) Output:["_col0"] - Select Operator [SEL_1555] (rows=14736682 width=0) + Select Operator [SEL_1582] (rows=14736682 width=0) Output:["_col0","_col1"] - Merge Join Operator [MERGEJOIN_1554] (rows=14736682 width=0) - Conds:RS_1809._col0=RS_1615._col0(Inner),Output:["_col1","_col2"] - <-Map 99 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1615] + Merge Join Operator [MERGEJOIN_1581] (rows=14736682 width=0) + Conds:RS_1833._col0=RS_1642._col0(Inner),Output:["_col1","_col2"] + <-Map 87 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_1642] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_1603] + Please refer to the previous Select Operator [SEL_1630] <-Map 46 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1809] + SHUFFLE [RS_1833] PartitionCols:_col0 - Select Operator [SEL_1807] (rows=550076554 width=114) + Select Operator [SEL_1831] (rows=550076554 width=114) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_1806] (rows=550076554 width=114) + Filter Operator [FIL_1830] (rows=550076554 width=114) predicate:((ss_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(ss_sold_date_sk, DynamicValue(RS_52_date_dim_d_date_sk_bloom_filter))) and ss_sold_date_sk is not null) TableScan [TS_45] (rows=575995635 width=114) default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_quantity","ss_list_price"] - <-Reducer 106 [BROADCAST_EDGE] vectorized - BROADCAST [RS_1805] - Group By Operator [GBY_1804] (rows=1 width=12) + <-Reducer 102 [BROADCAST_EDGE] vectorized + BROADCAST [RS_1829] + Group By Operator [GBY_1828] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 99 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_1627] - Group By Operator [GBY_1622] (rows=1 width=12) + <-Map 87 [CUSTOM_SIMPLE_EDGE] vectorized + SHUFFLE [RS_1654] + Group By Operator [GBY_1649] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_1613] (rows=1957 width=4) + Select Operator [SEL_1640] (rows=1957 width=4) Output:["_col0"] - Please refer to the previous Select Operator [SEL_1603] + Please refer to the previous Select Operator [SEL_1630] <-Reducer 62 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_1725] - Group By Operator [GBY_1724] (rows=1 width=132) + PARTITION_ONLY_SHUFFLE [RS_1749] + Group By Operator [GBY_1748] (rows=1 width=132) Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["sum(VALUE._col0)","count(VALUE._col1)"],keys:KEY._col0, KEY._col1, KEY._col2 <-Reducer 61 [SIMPLE_EDGE] SHUFFLE [RS_365] @@ -603,387 +600,387 @@ Stage-0 Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["sum(_col3)","count()"],keys:_col0, _col1, _col2 Select Operator [SEL_362] (rows=1 width=128) Output:["_col0","_col1","_col2","_col3"] - Merge Join Operator [MERGEJOIN_1429] (rows=1 width=128) - Conds:RS_359._col1=RS_360._col0(Inner),Output:["_col2","_col3","_col6","_col7","_col8"] - <-Reducer 80 [SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_360] + Merge Join Operator [MERGEJOIN_1441] (rows=1 width=128) + Conds:RS_359._col1=RS_1705._col0(Inner),Output:["_col2","_col3","_col7","_col8","_col9"] + <-Map 105 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_1705] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_1412] (rows=724 width=4) - Conds:RS_1682._col1, _col2, _col3=RS_1718._col0, _col1, _col2(Inner),Output:["_col0"] - <-Map 69 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1682] - PartitionCols:_col1, _col2, _col3 - Select Operator [SEL_1671] (rows=458612 width=15) - Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_1662] (rows=458612 width=15) - predicate:(i_brand_id is not null and i_category_id is not null and i_class_id is not null) - TableScan [TS_90] (rows=462000 width=15) - default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_brand_id","i_class_id","i_category_id"] - <-Reducer 85 [ONE_TO_ONE_EDGE] vectorized - FORWARD [RS_1718] - PartitionCols:_col0, _col1, _col2 - Select Operator [SEL_1717] (rows=1 width=12) - Output:["_col0","_col1","_col2"] - Filter Operator [FIL_1716] (rows=1 width=20) - predicate:(_col3 = 3L) - Group By Operator [GBY_1715] (rows=121728 width=19) - Output:["_col0","_col1","_col2","_col3"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2 - <-Union 84 [SIMPLE_EDGE] - <-Reducer 83 [CONTAINS] vectorized - Reduce Output Operator [RS_1837] - PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_1836] (rows=121728 width=19) - Output:["_col0","_col1","_col2","_col3"],aggregations:["count(_col3)"],keys:_col0, _col1, _col2 - Group By Operator [GBY_1835] (rows=121728 width=19) - Output:["_col0","_col1","_col2","_col3"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2 - <-Reducer 82 [SIMPLE_EDGE] - SHUFFLE [RS_298] - PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_297] (rows=121728 width=19) - Output:["_col0","_col1","_col2","_col3"],aggregations:["count()"],keys:_col4, _col5, _col6 - Merge Join Operator [MERGEJOIN_1407] (rows=14628613 width=11) - Conds:RS_293._col1=RS_1683._col0(Inner),Output:["_col4","_col5","_col6"] - <-Map 69 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1683] - PartitionCols:_col0 - Select Operator [SEL_1672] (rows=458612 width=15) - Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_1663] (rows=458612 width=15) - predicate:(i_brand_id is not null and i_category_id is not null and i_class_id is not null) - Please refer to the previous TableScan [TS_90] - <-Reducer 98 [SIMPLE_EDGE] - SHUFFLE [RS_293] - PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_1391] (rows=14736682 width=4) - Conds:RS_1815._col0=RS_1604._col0(Inner),Output:["_col1"] - <-Map 99 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1604] - PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_1603] - <-Map 97 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1815] - PartitionCols:_col0 - Select Operator [SEL_1814] (rows=550076554 width=7) - Output:["_col0","_col1"] - Filter Operator [FIL_1813] (rows=550076554 width=7) - predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_103_d1_d_date_sk_min) AND DynamicValue(RS_103_d1_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_103_d1_d_date_sk_bloom_filter))) and ss_sold_date_sk is not null) - TableScan [TS_93] (rows=575995635 width=7) - default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_item_sk"] - <-Reducer 100 [BROADCAST_EDGE] vectorized - BROADCAST [RS_1812] - Group By Operator [GBY_1811] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 99 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_1623] - Group By Operator [GBY_1618] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_1605] (rows=1957 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_1603] - <-Reducer 92 [CONTAINS] vectorized - Reduce Output Operator [RS_1843] - PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_1842] (rows=121728 width=19) - Output:["_col0","_col1","_col2","_col3"],aggregations:["count(_col3)"],keys:_col0, _col1, _col2 - Group By Operator [GBY_1841] (rows=121728 width=19) - Output:["_col0","_col1","_col2","_col3"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2 - <-Reducer 91 [SIMPLE_EDGE] - SHUFFLE [RS_318] - PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_317] (rows=121728 width=19) - Output:["_col0","_col1","_col2","_col3"],aggregations:["count()"],keys:_col4, _col5, _col6 - Merge Join Operator [MERGEJOIN_1409] (rows=7620440 width=11) - Conds:RS_313._col1=RS_1684._col0(Inner),Output:["_col4","_col5","_col6"] - <-Map 69 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1684] - PartitionCols:_col0 - Select Operator [SEL_1673] (rows=458612 width=15) - Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_1664] (rows=458612 width=15) - predicate:(i_brand_id is not null and i_category_id is not null and i_class_id is not null) - Please refer to the previous TableScan [TS_90] - <-Reducer 101 [SIMPLE_EDGE] - SHUFFLE [RS_313] - PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_1393] (rows=7676736 width=4) - Conds:RS_1823._col0=RS_1606._col0(Inner),Output:["_col1"] - <-Map 99 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1606] - PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_1603] - <-Map 107 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1823] - PartitionCols:_col0 - Select Operator [SEL_1822] (rows=286549727 width=7) - Output:["_col0","_col1"] - Filter Operator [FIL_1821] (rows=286549727 width=7) - predicate:((cs_sold_date_sk BETWEEN DynamicValue(RS_123_d2_d_date_sk_min) AND DynamicValue(RS_123_d2_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_123_d2_d_date_sk_bloom_filter))) and cs_sold_date_sk is not null) - TableScan [TS_113] (rows=287989836 width=7) - default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["cs_sold_date_sk","cs_item_sk"] - <-Reducer 102 [BROADCAST_EDGE] vectorized - BROADCAST [RS_1820] - Group By Operator [GBY_1819] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 99 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_1624] - Group By Operator [GBY_1619] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_1607] (rows=1957 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_1603] - <-Reducer 95 [CONTAINS] vectorized - Reduce Output Operator [RS_1849] - PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_1848] (rows=121728 width=19) - Output:["_col0","_col1","_col2","_col3"],aggregations:["count(_col3)"],keys:_col0, _col1, _col2 - Group By Operator [GBY_1847] (rows=121728 width=19) - Output:["_col0","_col1","_col2","_col3"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2 - <-Reducer 94 [SIMPLE_EDGE] - SHUFFLE [RS_339] - PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_338] (rows=121728 width=19) - Output:["_col0","_col1","_col2","_col3"],aggregations:["count()"],keys:_col4, _col5, _col6 - Merge Join Operator [MERGEJOIN_1411] (rows=3828623 width=11) - Conds:RS_334._col1=RS_1685._col0(Inner),Output:["_col4","_col5","_col6"] - <-Map 69 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1685] - PartitionCols:_col0 - Select Operator [SEL_1674] (rows=458612 width=15) - Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_1665] (rows=458612 width=15) - predicate:(i_brand_id is not null and i_category_id is not null and i_class_id is not null) - Please refer to the previous TableScan [TS_90] - <-Reducer 103 [SIMPLE_EDGE] - SHUFFLE [RS_334] - PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_1395] (rows=3856907 width=4) - Conds:RS_1831._col0=RS_1608._col0(Inner),Output:["_col1"] - <-Map 99 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1608] - PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_1603] - <-Map 108 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1831] - PartitionCols:_col0 - Select Operator [SEL_1830] (rows=143966864 width=7) - Output:["_col0","_col1"] - Filter Operator [FIL_1829] (rows=143966864 width=7) - predicate:((ws_sold_date_sk BETWEEN DynamicValue(RS_144_d3_d_date_sk_min) AND DynamicValue(RS_144_d3_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_144_d3_d_date_sk_bloom_filter))) and ws_sold_date_sk is not null) - TableScan [TS_134] (rows=144002668 width=7) - default@web_sales,web_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_sold_date_sk","ws_item_sk"] - <-Reducer 104 [BROADCAST_EDGE] vectorized - BROADCAST [RS_1828] - Group By Operator [GBY_1827] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 99 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_1625] - Group By Operator [GBY_1620] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_1609] (rows=1957 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_1603] + Select Operator [SEL_1696] (rows=462000 width=15) + Output:["_col0","_col1","_col2","_col3"] + TableScan [TS_163] (rows=462000 width=15) + default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_brand_id","i_class_id","i_category_id"] <-Reducer 60 [ONE_TO_ONE_EDGE] FORWARD [RS_359] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_1405] (rows=7790806 width=110) - Conds:RS_356._col1=RS_1675._col0(Inner),Output:["_col1","_col2","_col3","_col6","_col7","_col8"] - <-Map 69 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1675] + Merge Join Operator [MERGEJOIN_1440] (rows=1 width=120) + Conds:RS_356._col1=RS_357._col0(Inner),Output:["_col1","_col2","_col3"] + <-Reducer 80 [SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_357] PartitionCols:_col0 - Select Operator [SEL_1666] (rows=462000 width=15) - Output:["_col0","_col1","_col2","_col3"] - Please refer to the previous TableScan [TS_90] + Merge Join Operator [MERGEJOIN_1439] (rows=724 width=4) + Conds:RS_1713._col1, _col2, _col3=RS_1742._col0, _col1, _col2(Inner),Output:["_col0"] + <-Map 105 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_1713] + PartitionCols:_col1, _col2, _col3 + Select Operator [SEL_1706] (rows=458612 width=15) + Output:["_col0","_col1","_col2","_col3"] + Filter Operator [FIL_1697] (rows=458612 width=15) + predicate:(i_brand_id is not null and i_category_id is not null and i_class_id is not null) + Please refer to the previous TableScan [TS_163] + <-Reducer 79 [ONE_TO_ONE_EDGE] vectorized + FORWARD [RS_1742] + PartitionCols:_col0, _col1, _col2 + Select Operator [SEL_1741] (rows=1 width=12) + Output:["_col0","_col1","_col2"] + Filter Operator [FIL_1740] (rows=1 width=20) + predicate:(_col3 = 3L) + Group By Operator [GBY_1739] (rows=121728 width=19) + Output:["_col0","_col1","_col2","_col3"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2 + <-Union 78 [SIMPLE_EDGE] + <-Reducer 77 [CONTAINS] vectorized + Reduce Output Operator [RS_1845] + PartitionCols:_col0, _col1, _col2 + Group By Operator [GBY_1844] (rows=121728 width=19) + Output:["_col0","_col1","_col2","_col3"],aggregations:["count(_col3)"],keys:_col0, _col1, _col2 + Group By Operator [GBY_1843] (rows=121728 width=19) + Output:["_col0","_col1","_col2","_col3"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2 + <-Reducer 71 [SIMPLE_EDGE] + SHUFFLE [RS_296] + PartitionCols:_col0, _col1, _col2 + Group By Operator [GBY_107] (rows=121728 width=19) + Output:["_col0","_col1","_col2","_col3"],aggregations:["count()"],keys:_col4, _col5, _col6 + Merge Join Operator [MERGEJOIN_1418] (rows=14628613 width=11) + Conds:RS_103._col1=RS_1710._col0(Inner),Output:["_col4","_col5","_col6"] + <-Map 105 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_1710] + PartitionCols:_col0 + Select Operator [SEL_1702] (rows=458612 width=15) + Output:["_col0","_col1","_col2","_col3"] + Filter Operator [FIL_1693] (rows=458612 width=15) + predicate:(i_brand_id is not null and i_category_id is not null and i_class_id is not null) + Please refer to the previous TableScan [TS_163] + <-Reducer 70 [SIMPLE_EDGE] + SHUFFLE [RS_103] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_1417] (rows=14736682 width=4) + Conds:RS_1839._col0=RS_1631._col0(Inner),Output:["_col1"] + <-Map 87 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_1631] + PartitionCols:_col0 + Please refer to the previous Select Operator [SEL_1630] + <-Map 69 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_1839] + PartitionCols:_col0 + Select Operator [SEL_1838] (rows=550076554 width=7) + Output:["_col0","_col1"] + Filter Operator [FIL_1837] (rows=550076554 width=7) + predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_101_d1_d_date_sk_min) AND DynamicValue(RS_101_d1_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_101_d1_d_date_sk_bloom_filter))) and ss_sold_date_sk is not null) + TableScan [TS_91] (rows=575995635 width=7) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_item_sk"] + <-Reducer 88 [BROADCAST_EDGE] vectorized + BROADCAST [RS_1836] + Group By Operator [GBY_1835] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 87 [CUSTOM_SIMPLE_EDGE] vectorized + SHUFFLE [RS_1650] + Group By Operator [GBY_1645] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_1632] (rows=1957 width=4) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_1630] + <-Reducer 92 [CONTAINS] vectorized + Reduce Output Operator [RS_1859] + PartitionCols:_col0, _col1, _col2 + Group By Operator [GBY_1858] (rows=121728 width=19) + Output:["_col0","_col1","_col2","_col3"],aggregations:["count(_col3)"],keys:_col0, _col1, _col2 + Group By Operator [GBY_1857] (rows=121728 width=19) + Output:["_col0","_col1","_col2","_col3"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2 + <-Reducer 90 [SIMPLE_EDGE] + SHUFFLE [RS_316] + PartitionCols:_col0, _col1, _col2 + Group By Operator [GBY_127] (rows=121728 width=19) + Output:["_col0","_col1","_col2","_col3"],aggregations:["count()"],keys:_col4, _col5, _col6 + Merge Join Operator [MERGEJOIN_1420] (rows=7620440 width=11) + Conds:RS_123._col1=RS_1711._col0(Inner),Output:["_col4","_col5","_col6"] + <-Map 105 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_1711] + PartitionCols:_col0 + Select Operator [SEL_1703] (rows=458612 width=15) + Output:["_col0","_col1","_col2","_col3"] + Filter Operator [FIL_1694] (rows=458612 width=15) + predicate:(i_brand_id is not null and i_category_id is not null and i_class_id is not null) + Please refer to the previous TableScan [TS_163] + <-Reducer 89 [SIMPLE_EDGE] + SHUFFLE [RS_123] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_1419] (rows=7676736 width=4) + Conds:RS_1853._col0=RS_1633._col0(Inner),Output:["_col1"] + <-Map 87 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_1633] + PartitionCols:_col0 + Please refer to the previous Select Operator [SEL_1630] + <-Map 103 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_1853] + PartitionCols:_col0 + Select Operator [SEL_1852] (rows=286549727 width=7) + Output:["_col0","_col1"] + Filter Operator [FIL_1851] (rows=286549727 width=7) + predicate:((cs_sold_date_sk BETWEEN DynamicValue(RS_121_d2_d_date_sk_min) AND DynamicValue(RS_121_d2_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_121_d2_d_date_sk_bloom_filter))) and cs_sold_date_sk is not null) + TableScan [TS_111] (rows=287989836 width=7) + default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["cs_sold_date_sk","cs_item_sk"] + <-Reducer 94 [BROADCAST_EDGE] vectorized + BROADCAST [RS_1850] + Group By Operator [GBY_1849] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 87 [CUSTOM_SIMPLE_EDGE] vectorized + SHUFFLE [RS_1651] + Group By Operator [GBY_1646] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_1634] (rows=1957 width=4) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_1630] + <-Reducer 98 [CONTAINS] vectorized + Reduce Output Operator [RS_1873] + PartitionCols:_col0, _col1, _col2 + Group By Operator [GBY_1872] (rows=121728 width=19) + Output:["_col0","_col1","_col2","_col3"],aggregations:["count(_col3)"],keys:_col0, _col1, _col2 + Group By Operator [GBY_1871] (rows=121728 width=19) + Output:["_col0","_col1","_col2","_col3"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2 + <-Reducer 96 [SIMPLE_EDGE] + SHUFFLE [RS_337] + PartitionCols:_col0, _col1, _col2 + Group By Operator [GBY_148] (rows=121728 width=19) + Output:["_col0","_col1","_col2","_col3"],aggregations:["count()"],keys:_col4, _col5, _col6 + Merge Join Operator [MERGEJOIN_1422] (rows=3828623 width=11) + Conds:RS_144._col1=RS_1712._col0(Inner),Output:["_col4","_col5","_col6"] + <-Map 105 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_1712] + PartitionCols:_col0 + Select Operator [SEL_1704] (rows=458612 width=15) + Output:["_col0","_col1","_col2","_col3"] + Filter Operator [FIL_1695] (rows=458612 width=15) + predicate:(i_brand_id is not null and i_category_id is not null and i_class_id is not null) + Please refer to the previous TableScan [TS_163] + <-Reducer 95 [SIMPLE_EDGE] + SHUFFLE [RS_144] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_1421] (rows=3856907 width=4) + Conds:RS_1867._col0=RS_1635._col0(Inner),Output:["_col1"] + <-Map 87 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_1635] + PartitionCols:_col0 + Please refer to the previous Select Operator [SEL_1630] + <-Map 104 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_1867] + PartitionCols:_col0 + Select Operator [SEL_1866] (rows=143966864 width=7) + Output:["_col0","_col1"] + Filter Operator [FIL_1865] (rows=143966864 width=7) + predicate:((ws_sold_date_sk BETWEEN DynamicValue(RS_142_d3_d_date_sk_min) AND DynamicValue(RS_142_d3_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_142_d3_d_date_sk_bloom_filter))) and ws_sold_date_sk is not null) + TableScan [TS_132] (rows=144002668 width=7) + default@web_sales,web_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_sold_date_sk","ws_item_sk"] + <-Reducer 100 [BROADCAST_EDGE] vectorized + BROADCAST [RS_1864] + Group By Operator [GBY_1863] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 87 [CUSTOM_SIMPLE_EDGE] vectorized + SHUFFLE [RS_1652] + Group By Operator [GBY_1647] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_1636] (rows=1957 width=4) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_1630] <-Reducer 59 [SIMPLE_EDGE] SHUFFLE [RS_356] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_1404] (rows=7790806 width=98) - Conds:RS_1723._col0=RS_1648._col0(Inner),Output:["_col1","_col2","_col3"] + Merge Join Operator [MERGEJOIN_1432] (rows=7790806 width=98) + Conds:RS_1747._col0=RS_1675._col0(Inner),Output:["_col1","_col2","_col3"] <-Map 57 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_1648] + PARTITION_ONLY_SHUFFLE [RS_1675] PartitionCols:_col0 - Select Operator [SEL_1645] (rows=50 width=4) + Select Operator [SEL_1672] (rows=50 width=4) Output:["_col0"] - Filter Operator [FIL_1644] (rows=50 width=12) + Filter Operator [FIL_1671] (rows=50 width=12) predicate:((d_moy = 11) and (d_year = 2000)) TableScan [TS_85] (rows=73049 width=12) default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year","d_moy"] - <-Map 109 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1723] + <-Map 106 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_1747] PartitionCols:_col0 - Select Operator [SEL_1722] (rows=286549727 width=123) + Select Operator [SEL_1746] (rows=286549727 width=123) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_1721] (rows=286549727 width=123) - predicate:((cs_item_sk BETWEEN DynamicValue(RS_360_item_i_item_sk_min) AND DynamicValue(RS_360_item_i_item_sk_max) and in_bloom_filter(cs_item_sk, DynamicValue(RS_360_item_i_item_sk_bloom_filter))) and (cs_sold_date_sk BETWEEN DynamicValue(RS_354_date_dim_d_date_sk_min) AND DynamicValue(RS_354_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_354_date_dim_d_date_sk_bloom_filter))) and cs_sold_date_sk is not null) + Filter Operator [FIL_1745] (rows=286549727 width=123) + predicate:((cs_item_sk BETWEEN DynamicValue(RS_357_item_i_item_sk_min) AND DynamicValue(RS_357_item_i_item_sk_max) and in_bloom_filter(cs_item_sk, DynamicValue(RS_357_item_i_item_sk_bloom_filter))) and (cs_sold_date_sk BETWEEN DynamicValue(RS_354_date_dim_d_date_sk_min) AND DynamicValue(RS_354_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_354_date_dim_d_date_sk_bloom_filter))) and cs_sold_date_sk is not null) TableScan [TS_270] (rows=287989836 width=123) default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["cs_sold_date_sk","cs_item_sk","cs_quantity","cs_list_price"] <-Reducer 63 [BROADCAST_EDGE] vectorized - BROADCAST [RS_1714] - Group By Operator [GBY_1713] (rows=1 width=12) + BROADCAST [RS_1738] + Group By Operator [GBY_1737] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Map 57 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_1656] - Group By Operator [GBY_1653] (rows=1 width=12) + PARTITION_ONLY_SHUFFLE [RS_1683] + Group By Operator [GBY_1680] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_1649] (rows=50 width=4) + Select Operator [SEL_1676] (rows=50 width=4) Output:["_col0"] - Please refer to the previous Select Operator [SEL_1645] + Please refer to the previous Select Operator [SEL_1672] <-Reducer 81 [BROADCAST_EDGE] vectorized - BROADCAST [RS_1720] - Group By Operator [GBY_1719] (rows=1 width=12) + BROADCAST [RS_1744] + Group By Operator [GBY_1743] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Reducer 80 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_1077] - Group By Operator [GBY_1076] (rows=1 width=12) + PARTITION_ONLY_SHUFFLE [RS_1099] + Group By Operator [GBY_1098] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_1075] (rows=724 width=4) + Select Operator [SEL_1097] (rows=724 width=4) Output:["_col0"] - Please refer to the previous Merge Join Operator [MERGEJOIN_1412] + Please refer to the previous Merge Join Operator [MERGEJOIN_1439] <-Reducer 19 [CONTAINS] - Reduce Output Operator [RS_1475] + Reduce Output Operator [RS_1502] PartitionCols:_col0, _col1, _col2, _col3, _col4 - Group By Operator [GBY_1474] (rows=7 width=200) + Group By Operator [GBY_1501] (rows=7 width=200) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"],aggregations:["sum(_col4)","sum(_col5)"],keys:_col0, _col1, _col2, _col3, 0L - Top N Key Operator [TNK_1473] (rows=3 width=221) + Top N Key Operator [TNK_1500] (rows=3 width=221) keys:_col0, _col1, _col2, _col3, 0L,sort order:+++++,top n:100 - Select Operator [SEL_1471] (rows=1 width=219) + Select Operator [SEL_1498] (rows=1 width=219) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - Filter Operator [FIL_1470] (rows=1 width=244) + Filter Operator [FIL_1497] (rows=1 width=244) predicate:(_col5 > _col1) - Merge Join Operator [MERGEJOIN_1469] (rows=1 width=244) + Merge Join Operator [MERGEJOIN_1496] (rows=1 width=244) Conds:(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col6"] <-Reducer 18 [CUSTOM_SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_560] - Merge Join Operator [MERGEJOIN_1435] (rows=1 width=112) + Merge Join Operator [MERGEJOIN_1462] (rows=1 width=112) Conds:(Inner),Output:["_col1"] <-Reducer 17 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_1731] - Select Operator [SEL_1730] (rows=1 width=8) - Filter Operator [FIL_1729] (rows=1 width=8) + PARTITION_ONLY_SHUFFLE [RS_1755] + Select Operator [SEL_1754] (rows=1 width=8) + Filter Operator [FIL_1753] (rows=1 width=8) predicate:(sq_count_check(_col0) <= 1) - Group By Operator [GBY_1728] (rows=1 width=8) + Group By Operator [GBY_1752] (rows=1 width=8) Output:["_col0"],aggregations:["count()"] - Select Operator [SEL_1727] (rows=1 width=8) - Group By Operator [GBY_1726] (rows=1 width=8) + Select Operator [SEL_1751] (rows=1 width=8) + Group By Operator [GBY_1750] (rows=1 width=8) Output:["_col0"],aggregations:["count(VALUE._col0)"] <-Union 16 [CUSTOM_SIMPLE_EDGE] <-Reducer 15 [CONTAINS] - Reduce Output Operator [RS_1468] - Group By Operator [GBY_1467] (rows=1 width=8) + Reduce Output Operator [RS_1495] + Group By Operator [GBY_1494] (rows=1 width=8) Output:["_col0"],aggregations:["count(_col0)"] - Select Operator [SEL_1466] (rows=26270325 width=1) + Select Operator [SEL_1493] (rows=26270325 width=1) Output:["_col0"] - Select Operator [SEL_1464] (rows=14736682 width=0) + Select Operator [SEL_1491] (rows=14736682 width=0) Output:["_col0"] - Merge Join Operator [MERGEJOIN_1463] (rows=14736682 width=0) - Conds:RS_1634._col0=RS_1616._col0(Inner),Output:["_col1"] - <-Map 99 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1616] + Merge Join Operator [MERGEJOIN_1490] (rows=14736682 width=0) + Conds:RS_1661._col0=RS_1643._col0(Inner),Output:["_col1"] + <-Map 87 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_1643] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_1603] + Please refer to the previous Select Operator [SEL_1630] <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1634] + SHUFFLE [RS_1661] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_1631] + Please refer to the previous Select Operator [SEL_1658] <-Reducer 23 [CONTAINS] - Reduce Output Operator [RS_1493] - Group By Operator [GBY_1492] (rows=1 width=8) + Reduce Output Operator [RS_1520] + Group By Operator [GBY_1519] (rows=1 width=8) Output:["_col0"],aggregations:["count(_col0)"] - Select Operator [SEL_1491] (rows=26270325 width=1) + Select Operator [SEL_1518] (rows=26270325 width=1) Output:["_col0"] - Select Operator [SEL_1489] (rows=7676736 width=3) + Select Operator [SEL_1516] (rows=7676736 width=3) Output:["_col0"] - Merge Join Operator [MERGEJOIN_1488] (rows=7676736 width=3) - Conds:RS_1768._col0=RS_1756._col0(Inner),Output:["_col1"] + Merge Join Operator [MERGEJOIN_1515] (rows=7676736 width=3) + Conds:RS_1792._col0=RS_1780._col0(Inner),Output:["_col1"] <-Map 24 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1756] + SHUFFLE [RS_1780] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_1749] + Please refer to the previous Select Operator [SEL_1773] <-Map 20 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1768] + SHUFFLE [RS_1792] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_1765] + Please refer to the previous Select Operator [SEL_1789] <-Reducer 39 [CONTAINS] - Reduce Output Operator [RS_1529] - Group By Operator [GBY_1528] (rows=1 width=8) + Reduce Output Operator [RS_1556] + Group By Operator [GBY_1555] (rows=1 width=8) Output:["_col0"],aggregations:["count(_col0)"] - Select Operator [SEL_1527] (rows=26270325 width=1) + Select Operator [SEL_1554] (rows=26270325 width=1) Output:["_col0"] - Select Operator [SEL_1525] (rows=3856907 width=3) + Select Operator [SEL_1552] (rows=3856907 width=3) Output:["_col0"] - Merge Join Operator [MERGEJOIN_1524] (rows=3856907 width=3) - Conds:RS_1796._col0=RS_1784._col0(Inner),Output:["_col1"] + Merge Join Operator [MERGEJOIN_1551] (rows=3856907 width=3) + Conds:RS_1820._col0=RS_1808._col0(Inner),Output:["_col1"] <-Map 40 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1784] + SHUFFLE [RS_1808] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_1777] + Please refer to the previous Select Operator [SEL_1801] <-Map 36 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1796] + SHUFFLE [RS_1820] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_1793] + Please refer to the previous Select Operator [SEL_1817] <-Reducer 35 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_1734] - Select Operator [SEL_1733] (rows=1 width=112) + PARTITION_ONLY_SHUFFLE [RS_1758] + Select Operator [SEL_1757] (rows=1 width=112) Output:["_col0"] - Group By Operator [GBY_1732] (rows=1 width=120) + Group By Operator [GBY_1756] (rows=1 width=120) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)","count(VALUE._col1)"] <-Union 34 [CUSTOM_SIMPLE_EDGE] <-Reducer 33 [CONTAINS] - Reduce Output Operator [RS_1511] - Group By Operator [GBY_1510] (rows=1 width=120) + Reduce Output Operator [RS_1538] + Group By Operator [GBY_1537] (rows=1 width=120) Output:["_col0","_col1"],aggregations:["sum(_col0)","count(_col0)"] - Select Operator [SEL_1509] (rows=26270325 width=44) + Select Operator [SEL_1536] (rows=26270325 width=44) Output:["_col0"] - Select Operator [SEL_1507] (rows=7676736 width=94) + Select Operator [SEL_1534] (rows=7676736 width=94) Output:["_col0","_col1"] - Merge Join Operator [MERGEJOIN_1506] (rows=7676736 width=94) - Conds:RS_1775._col0=RS_1757._col0(Inner),Output:["_col1","_col2"] + Merge Join Operator [MERGEJOIN_1533] (rows=7676736 width=94) + Conds:RS_1799._col0=RS_1781._col0(Inner),Output:["_col1","_col2"] <-Map 24 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1757] + SHUFFLE [RS_1781] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_1749] + Please refer to the previous Select Operator [SEL_1773] <-Map 50 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1775] + SHUFFLE [RS_1799] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_1772] + Please refer to the previous Select Operator [SEL_1796] <-Reducer 45 [CONTAINS] - Reduce Output Operator [RS_1547] - Group By Operator [GBY_1546] (rows=1 width=120) + Reduce Output Operator [RS_1574] + Group By Operator [GBY_1573] (rows=1 width=120) Output:["_col0","_col1"],aggregations:["sum(_col0)","count(_col0)"] - Select Operator [SEL_1545] (rows=26270325 width=44) + Select Operator [SEL_1572] (rows=26270325 width=44) Output:["_col0"] - Select Operator [SEL_1543] (rows=3856907 width=114) + Select Operator [SEL_1570] (rows=3856907 width=114) Output:["_col0","_col1"] - Merge Join Operator [MERGEJOIN_1542] (rows=3856907 width=114) - Conds:RS_1803._col0=RS_1785._col0(Inner),Output:["_col1","_col2"] + Merge Join Operator [MERGEJOIN_1569] (rows=3856907 width=114) + Conds:RS_1827._col0=RS_1809._col0(Inner),Output:["_col1","_col2"] <-Map 40 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1785] + SHUFFLE [RS_1809] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_1777] + Please refer to the previous Select Operator [SEL_1801] <-Map 51 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1803] + SHUFFLE [RS_1827] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_1800] + Please refer to the previous Select Operator [SEL_1824] <-Reducer 49 [CONTAINS] - Reduce Output Operator [RS_1565] - Group By Operator [GBY_1564] (rows=1 width=120) + Reduce Output Operator [RS_1592] + Group By Operator [GBY_1591] (rows=1 width=120) Output:["_col0","_col1"],aggregations:["sum(_col0)","count(_col0)"] - Select Operator [SEL_1563] (rows=26270325 width=44) + Select Operator [SEL_1590] (rows=26270325 width=44) Output:["_col0"] - Select Operator [SEL_1561] (rows=14736682 width=0) + Select Operator [SEL_1588] (rows=14736682 width=0) Output:["_col0","_col1"] - Merge Join Operator [MERGEJOIN_1560] (rows=14736682 width=0) - Conds:RS_1810._col0=RS_1617._col0(Inner),Output:["_col1","_col2"] - <-Map 99 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1617] + Merge Join Operator [MERGEJOIN_1587] (rows=14736682 width=0) + Conds:RS_1834._col0=RS_1644._col0(Inner),Output:["_col1","_col2"] + <-Map 87 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_1644] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_1603] + Please refer to the previous Select Operator [SEL_1630] <-Map 46 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1810] + SHUFFLE [RS_1834] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_1807] + Please refer to the previous Select Operator [SEL_1831] <-Reducer 67 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_1747] - Group By Operator [GBY_1746] (rows=1 width=132) + PARTITION_ONLY_SHUFFLE [RS_1771] + Group By Operator [GBY_1770] (rows=1 width=132) Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["sum(VALUE._col0)","count(VALUE._col1)"],keys:KEY._col0, KEY._col1, KEY._col2 <-Reducer 66 [SIMPLE_EDGE] SHUFFLE [RS_554] @@ -992,261 +989,261 @@ Stage-0 Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["sum(_col3)","count()"],keys:_col0, _col1, _col2 Select Operator [SEL_551] (rows=1 width=128) Output:["_col0","_col1","_col2","_col3"] - Merge Join Operator [MERGEJOIN_1430] (rows=1 width=128) - Conds:RS_548._col1=RS_549._col0(Inner),Output:["_col2","_col3","_col6","_col7","_col8"] - <-Reducer 89 [SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_549] + Merge Join Operator [MERGEJOIN_1457] (rows=1 width=128) + Conds:RS_548._col1=RS_1707._col0(Inner),Output:["_col2","_col3","_col7","_col8","_col9"] + <-Map 105 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_1707] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_1427] (rows=724 width=4) - Conds:RS_1686._col1, _col2, _col3=RS_1740._col0, _col1, _col2(Inner),Output:["_col0"] - <-Map 69 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1686] - PartitionCols:_col1, _col2, _col3 - Select Operator [SEL_1676] (rows=458612 width=15) - Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_1667] (rows=458612 width=15) - predicate:(i_brand_id is not null and i_category_id is not null and i_class_id is not null) - Please refer to the previous TableScan [TS_90] - <-Reducer 88 [ONE_TO_ONE_EDGE] vectorized - FORWARD [RS_1740] - PartitionCols:_col0, _col1, _col2 - Select Operator [SEL_1739] (rows=1 width=12) - Output:["_col0","_col1","_col2"] - Filter Operator [FIL_1738] (rows=1 width=20) - predicate:(_col3 = 3L) - Group By Operator [GBY_1737] (rows=121728 width=19) - Output:["_col0","_col1","_col2","_col3"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2 - <-Union 87 [SIMPLE_EDGE] - <-Reducer 86 [CONTAINS] vectorized - Reduce Output Operator [RS_1840] - PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_1839] (rows=121728 width=19) - Output:["_col0","_col1","_col2","_col3"],aggregations:["count(_col3)"],keys:_col0, _col1, _col2 - Group By Operator [GBY_1838] (rows=121728 width=19) - Output:["_col0","_col1","_col2","_col3"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2 - <-Reducer 82 [SIMPLE_EDGE] - SHUFFLE [RS_487] - PartitionCols:_col0, _col1, _col2 - Please refer to the previous Group By Operator [GBY_297] - <-Reducer 93 [CONTAINS] vectorized - Reduce Output Operator [RS_1846] - PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_1845] (rows=121728 width=19) - Output:["_col0","_col1","_col2","_col3"],aggregations:["count(_col3)"],keys:_col0, _col1, _col2 - Group By Operator [GBY_1844] (rows=121728 width=19) - Output:["_col0","_col1","_col2","_col3"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2 - <-Reducer 91 [SIMPLE_EDGE] - SHUFFLE [RS_507] - PartitionCols:_col0, _col1, _col2 - Please refer to the previous Group By Operator [GBY_317] - <-Reducer 96 [CONTAINS] vectorized - Reduce Output Operator [RS_1852] - PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_1851] (rows=121728 width=19) - Output:["_col0","_col1","_col2","_col3"],aggregations:["count(_col3)"],keys:_col0, _col1, _col2 - Group By Operator [GBY_1850] (rows=121728 width=19) - Output:["_col0","_col1","_col2","_col3"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2 - <-Reducer 94 [SIMPLE_EDGE] - SHUFFLE [RS_528] - PartitionCols:_col0, _col1, _col2 - Please refer to the previous Group By Operator [GBY_338] + Select Operator [SEL_1698] (rows=462000 width=15) + Output:["_col0","_col1","_col2","_col3"] + Please refer to the previous TableScan [TS_163] <-Reducer 65 [ONE_TO_ONE_EDGE] FORWARD [RS_548] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_1420] (rows=3942084 width=130) - Conds:RS_545._col1=RS_1677._col0(Inner),Output:["_col1","_col2","_col3","_col6","_col7","_col8"] - <-Map 69 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1677] + Merge Join Operator [MERGEJOIN_1456] (rows=1 width=120) + Conds:RS_545._col1=RS_546._col0(Inner),Output:["_col1","_col2","_col3"] + <-Reducer 85 [SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_546] PartitionCols:_col0 - Select Operator [SEL_1668] (rows=462000 width=15) - Output:["_col0","_col1","_col2","_col3"] - Please refer to the previous TableScan [TS_90] + Merge Join Operator [MERGEJOIN_1455] (rows=724 width=4) + Conds:RS_1714._col1, _col2, _col3=RS_1764._col0, _col1, _col2(Inner),Output:["_col0"] + <-Map 105 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_1714] + PartitionCols:_col1, _col2, _col3 + Select Operator [SEL_1708] (rows=458612 width=15) + Output:["_col0","_col1","_col2","_col3"] + Filter Operator [FIL_1699] (rows=458612 width=15) + predicate:(i_brand_id is not null and i_category_id is not null and i_class_id is not null) + Please refer to the previous TableScan [TS_163] + <-Reducer 84 [ONE_TO_ONE_EDGE] vectorized + FORWARD [RS_1764] + PartitionCols:_col0, _col1, _col2 + Select Operator [SEL_1763] (rows=1 width=12) + Output:["_col0","_col1","_col2"] + Filter Operator [FIL_1762] (rows=1 width=20) + predicate:(_col3 = 3L) + Group By Operator [GBY_1761] (rows=121728 width=19) + Output:["_col0","_col1","_col2","_col3"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2 + <-Union 83 [SIMPLE_EDGE] + <-Reducer 82 [CONTAINS] vectorized + Reduce Output Operator [RS_1848] + PartitionCols:_col0, _col1, _col2 + Group By Operator [GBY_1847] (rows=121728 width=19) + Output:["_col0","_col1","_col2","_col3"],aggregations:["count(_col3)"],keys:_col0, _col1, _col2 + Group By Operator [GBY_1846] (rows=121728 width=19) + Output:["_col0","_col1","_col2","_col3"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2 + <-Reducer 71 [SIMPLE_EDGE] + SHUFFLE [RS_485] + PartitionCols:_col0, _col1, _col2 + Please refer to the previous Group By Operator [GBY_107] + <-Reducer 93 [CONTAINS] vectorized + Reduce Output Operator [RS_1862] + PartitionCols:_col0, _col1, _col2 + Group By Operator [GBY_1861] (rows=121728 width=19) + Output:["_col0","_col1","_col2","_col3"],aggregations:["count(_col3)"],keys:_col0, _col1, _col2 + Group By Operator [GBY_1860] (rows=121728 width=19) + Output:["_col0","_col1","_col2","_col3"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2 + <-Reducer 90 [SIMPLE_EDGE] + SHUFFLE [RS_505] + PartitionCols:_col0, _col1, _col2 + Please refer to the previous Group By Operator [GBY_127] + <-Reducer 99 [CONTAINS] vectorized + Reduce Output Operator [RS_1876] + PartitionCols:_col0, _col1, _col2 + Group By Operator [GBY_1875] (rows=121728 width=19) + Output:["_col0","_col1","_col2","_col3"],aggregations:["count(_col3)"],keys:_col0, _col1, _col2 + Group By Operator [GBY_1874] (rows=121728 width=19) + Output:["_col0","_col1","_col2","_col3"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2 + <-Reducer 96 [SIMPLE_EDGE] + SHUFFLE [RS_526] + PartitionCols:_col0, _col1, _col2 + Please refer to the previous Group By Operator [GBY_148] <-Reducer 64 [SIMPLE_EDGE] SHUFFLE [RS_545] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_1419] (rows=3942084 width=118) - Conds:RS_1745._col0=RS_1650._col0(Inner),Output:["_col1","_col2","_col3"] + Merge Join Operator [MERGEJOIN_1448] (rows=3942084 width=118) + Conds:RS_1769._col0=RS_1677._col0(Inner),Output:["_col1","_col2","_col3"] <-Map 57 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_1650] + PARTITION_ONLY_SHUFFLE [RS_1677] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_1645] - <-Map 110 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1745] + Please refer to the previous Select Operator [SEL_1672] + <-Map 107 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_1769] PartitionCols:_col0 - Select Operator [SEL_1744] (rows=143966864 width=123) + Select Operator [SEL_1768] (rows=143966864 width=123) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_1743] (rows=143966864 width=123) - predicate:((ws_item_sk BETWEEN DynamicValue(RS_549_item_i_item_sk_min) AND DynamicValue(RS_549_item_i_item_sk_max) and in_bloom_filter(ws_item_sk, DynamicValue(RS_549_item_i_item_sk_bloom_filter))) and (ws_sold_date_sk BETWEEN DynamicValue(RS_543_date_dim_d_date_sk_min) AND DynamicValue(RS_543_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_543_date_dim_d_date_sk_bloom_filter))) and ws_sold_date_sk is not null) + Filter Operator [FIL_1767] (rows=143966864 width=123) + predicate:((ws_item_sk BETWEEN DynamicValue(RS_546_item_i_item_sk_min) AND DynamicValue(RS_546_item_i_item_sk_max) and in_bloom_filter(ws_item_sk, DynamicValue(RS_546_item_i_item_sk_bloom_filter))) and (ws_sold_date_sk BETWEEN DynamicValue(RS_543_date_dim_d_date_sk_min) AND DynamicValue(RS_543_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_543_date_dim_d_date_sk_bloom_filter))) and ws_sold_date_sk is not null) TableScan [TS_459] (rows=144002668 width=123) default@web_sales,web_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_sold_date_sk","ws_item_sk","ws_quantity","ws_list_price"] <-Reducer 68 [BROADCAST_EDGE] vectorized - BROADCAST [RS_1736] - Group By Operator [GBY_1735] (rows=1 width=12) + BROADCAST [RS_1760] + Group By Operator [GBY_1759] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Map 57 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_1657] - Group By Operator [GBY_1654] (rows=1 width=12) + PARTITION_ONLY_SHUFFLE [RS_1684] + Group By Operator [GBY_1681] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_1651] (rows=50 width=4) + Select Operator [SEL_1678] (rows=50 width=4) Output:["_col0"] - Please refer to the previous Select Operator [SEL_1645] - <-Reducer 90 [BROADCAST_EDGE] vectorized - BROADCAST [RS_1742] - Group By Operator [GBY_1741] (rows=1 width=12) + Please refer to the previous Select Operator [SEL_1672] + <-Reducer 86 [BROADCAST_EDGE] vectorized + BROADCAST [RS_1766] + Group By Operator [GBY_1765] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Reducer 89 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_1266] - Group By Operator [GBY_1265] (rows=1 width=12) + <-Reducer 85 [CUSTOM_SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_1288] + Group By Operator [GBY_1287] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_1264] (rows=724 width=4) + Select Operator [SEL_1286] (rows=724 width=4) Output:["_col0"] - Please refer to the previous Merge Join Operator [MERGEJOIN_1427] + Please refer to the previous Merge Join Operator [MERGEJOIN_1455] <-Reducer 6 [CONTAINS] - Reduce Output Operator [RS_1449] + Reduce Output Operator [RS_1476] PartitionCols:_col0, _col1, _col2, _col3, _col4 - Group By Operator [GBY_1448] (rows=7 width=200) + Group By Operator [GBY_1475] (rows=7 width=200) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"],aggregations:["sum(_col4)","sum(_col5)"],keys:_col0, _col1, _col2, _col3, 0L - Top N Key Operator [TNK_1447] (rows=3 width=221) + Top N Key Operator [TNK_1474] (rows=3 width=221) keys:_col0, _col1, _col2, _col3, 0L,sort order:+++++,top n:100 - Select Operator [SEL_1445] (rows=1 width=221) + Select Operator [SEL_1472] (rows=1 width=221) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - Filter Operator [FIL_1444] (rows=1 width=244) + Filter Operator [FIL_1471] (rows=1 width=244) predicate:(_col5 > _col1) - Merge Join Operator [MERGEJOIN_1443] (rows=1 width=244) + Merge Join Operator [MERGEJOIN_1470] (rows=1 width=244) Conds:(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col6"] <-Reducer 5 [CUSTOM_SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_183] - Merge Join Operator [MERGEJOIN_1431] (rows=1 width=112) + Merge Join Operator [MERGEJOIN_1458] (rows=1 width=112) Conds:(Inner),Output:["_col1"] <-Reducer 28 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_1643] - Select Operator [SEL_1642] (rows=1 width=112) + PARTITION_ONLY_SHUFFLE [RS_1670] + Select Operator [SEL_1669] (rows=1 width=112) Output:["_col0"] - Group By Operator [GBY_1641] (rows=1 width=120) + Group By Operator [GBY_1668] (rows=1 width=120) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)","count(VALUE._col1)"] <-Union 27 [CUSTOM_SIMPLE_EDGE] <-Reducer 26 [CONTAINS] - Reduce Output Operator [RS_1499] - Group By Operator [GBY_1498] (rows=1 width=120) + Reduce Output Operator [RS_1526] + Group By Operator [GBY_1525] (rows=1 width=120) Output:["_col0","_col1"],aggregations:["sum(_col0)","count(_col0)"] - Select Operator [SEL_1497] (rows=26270325 width=44) + Select Operator [SEL_1524] (rows=26270325 width=44) Output:["_col0"] - Select Operator [SEL_1495] (rows=7676736 width=94) + Select Operator [SEL_1522] (rows=7676736 width=94) Output:["_col0","_col1"] - Merge Join Operator [MERGEJOIN_1494] (rows=7676736 width=94) - Conds:RS_1773._col0=RS_1752._col0(Inner),Output:["_col1","_col2"] + Merge Join Operator [MERGEJOIN_1521] (rows=7676736 width=94) + Conds:RS_1797._col0=RS_1776._col0(Inner),Output:["_col1","_col2"] <-Map 24 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1752] + SHUFFLE [RS_1776] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_1749] + Please refer to the previous Select Operator [SEL_1773] <-Map 50 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1773] + SHUFFLE [RS_1797] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_1772] + Please refer to the previous Select Operator [SEL_1796] <-Reducer 42 [CONTAINS] - Reduce Output Operator [RS_1535] - Group By Operator [GBY_1534] (rows=1 width=120) + Reduce Output Operator [RS_1562] + Group By Operator [GBY_1561] (rows=1 width=120) Output:["_col0","_col1"],aggregations:["sum(_col0)","count(_col0)"] - Select Operator [SEL_1533] (rows=26270325 width=44) + Select Operator [SEL_1560] (rows=26270325 width=44) Output:["_col0"] - Select Operator [SEL_1531] (rows=3856907 width=114) + Select Operator [SEL_1558] (rows=3856907 width=114) Output:["_col0","_col1"] - Merge Join Operator [MERGEJOIN_1530] (rows=3856907 width=114) - Conds:RS_1801._col0=RS_1780._col0(Inner),Output:["_col1","_col2"] + Merge Join Operator [MERGEJOIN_1557] (rows=3856907 width=114) + Conds:RS_1825._col0=RS_1804._col0(Inner),Output:["_col1","_col2"] <-Map 40 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1780] + SHUFFLE [RS_1804] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_1777] + Please refer to the previous Select Operator [SEL_1801] <-Map 51 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1801] + SHUFFLE [RS_1825] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_1800] + Please refer to the previous Select Operator [SEL_1824] <-Reducer 47 [CONTAINS] - Reduce Output Operator [RS_1553] - Group By Operator [GBY_1552] (rows=1 width=120) + Reduce Output Operator [RS_1580] + Group By Operator [GBY_1579] (rows=1 width=120) Output:["_col0","_col1"],aggregations:["sum(_col0)","count(_col0)"] - Select Operator [SEL_1551] (rows=26270325 width=44) + Select Operator [SEL_1578] (rows=26270325 width=44) Output:["_col0"] - Select Operator [SEL_1549] (rows=14736682 width=0) + Select Operator [SEL_1576] (rows=14736682 width=0) Output:["_col0","_col1"] - Merge Join Operator [MERGEJOIN_1548] (rows=14736682 width=0) - Conds:RS_1808._col0=RS_1612._col0(Inner),Output:["_col1","_col2"] - <-Map 99 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1612] + Merge Join Operator [MERGEJOIN_1575] (rows=14736682 width=0) + Conds:RS_1832._col0=RS_1639._col0(Inner),Output:["_col1","_col2"] + <-Map 87 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_1639] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_1603] + Please refer to the previous Select Operator [SEL_1630] <-Map 46 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1808] + SHUFFLE [RS_1832] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_1807] + Please refer to the previous Select Operator [SEL_1831] <-Reducer 4 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_1640] - Select Operator [SEL_1639] (rows=1 width=8) - Filter Operator [FIL_1638] (rows=1 width=8) + PARTITION_ONLY_SHUFFLE [RS_1667] + Select Operator [SEL_1666] (rows=1 width=8) + Filter Operator [FIL_1665] (rows=1 width=8) predicate:(sq_count_check(_col0) <= 1) - Group By Operator [GBY_1637] (rows=1 width=8) + Group By Operator [GBY_1664] (rows=1 width=8) Output:["_col0"],aggregations:["count()"] - Select Operator [SEL_1636] (rows=1 width=8) - Group By Operator [GBY_1635] (rows=1 width=8) + Select Operator [SEL_1663] (rows=1 width=8) + Group By Operator [GBY_1662] (rows=1 width=8) Output:["_col0"],aggregations:["count(VALUE._col0)"] <-Union 3 [CUSTOM_SIMPLE_EDGE] <-Reducer 2 [CONTAINS] - Reduce Output Operator [RS_1442] - Group By Operator [GBY_1441] (rows=1 width=8) + Reduce Output Operator [RS_1469] + Group By Operator [GBY_1468] (rows=1 width=8) Output:["_col0"],aggregations:["count(_col0)"] - Select Operator [SEL_1440] (rows=26270325 width=1) + Select Operator [SEL_1467] (rows=26270325 width=1) Output:["_col0"] - Select Operator [SEL_1438] (rows=14736682 width=0) + Select Operator [SEL_1465] (rows=14736682 width=0) Output:["_col0"] - Merge Join Operator [MERGEJOIN_1437] (rows=14736682 width=0) - Conds:RS_1632._col0=RS_1610._col0(Inner),Output:["_col1"] - <-Map 99 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1610] + Merge Join Operator [MERGEJOIN_1464] (rows=14736682 width=0) + Conds:RS_1659._col0=RS_1637._col0(Inner),Output:["_col1"] + <-Map 87 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_1637] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_1603] + Please refer to the previous Select Operator [SEL_1630] <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1632] + SHUFFLE [RS_1659] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_1631] + Please refer to the previous Select Operator [SEL_1658] <-Reducer 21 [CONTAINS] - Reduce Output Operator [RS_1481] - Group By Operator [GBY_1480] (rows=1 width=8) + Reduce Output Operator [RS_1508] + Group By Operator [GBY_1507] (rows=1 width=8) Output:["_col0"],aggregations:["count(_col0)"] - Select Operator [SEL_1479] (rows=26270325 width=1) + Select Operator [SEL_1506] (rows=26270325 width=1) Output:["_col0"] - Select Operator [SEL_1477] (rows=7676736 width=3) + Select Operator [SEL_1504] (rows=7676736 width=3) Output:["_col0"] - Merge Join Operator [MERGEJOIN_1476] (rows=7676736 width=3) - Conds:RS_1766._col0=RS_1750._col0(Inner),Output:["_col1"] + Merge Join Operator [MERGEJOIN_1503] (rows=7676736 width=3) + Conds:RS_1790._col0=RS_1774._col0(Inner),Output:["_col1"] <-Map 24 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1750] + SHUFFLE [RS_1774] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_1749] + Please refer to the previous Select Operator [SEL_1773] <-Map 20 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1766] + SHUFFLE [RS_1790] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_1765] + Please refer to the previous Select Operator [SEL_1789] <-Reducer 37 [CONTAINS] - Reduce Output Operator [RS_1517] - Group By Operator [GBY_1516] (rows=1 width=8) + Reduce Output Operator [RS_1544] + Group By Operator [GBY_1543] (rows=1 width=8) Output:["_col0"],aggregations:["count(_col0)"] - Select Operator [SEL_1515] (rows=26270325 width=1) + Select Operator [SEL_1542] (rows=26270325 width=1) Output:["_col0"] - Select Operator [SEL_1513] (rows=3856907 width=3) + Select Operator [SEL_1540] (rows=3856907 width=3) Output:["_col0"] - Merge Join Operator [MERGEJOIN_1512] (rows=3856907 width=3) - Conds:RS_1794._col0=RS_1778._col0(Inner),Output:["_col1"] + Merge Join Operator [MERGEJOIN_1539] (rows=3856907 width=3) + Conds:RS_1818._col0=RS_1802._col0(Inner),Output:["_col1"] <-Map 40 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1778] + SHUFFLE [RS_1802] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_1777] + Please refer to the previous Select Operator [SEL_1801] <-Map 36 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1794] + SHUFFLE [RS_1818] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_1793] + Please refer to the previous Select Operator [SEL_1817] <-Reducer 56 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_1697] - Group By Operator [GBY_1696] (rows=1 width=132) + PARTITION_ONLY_SHUFFLE [RS_1721] + Group By Operator [GBY_1720] (rows=1 width=132) Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["sum(VALUE._col0)","count(VALUE._col1)"],keys:KEY._col0, KEY._col1, KEY._col2 <-Reducer 55 [SIMPLE_EDGE] SHUFFLE [RS_177] @@ -1255,146 +1252,113 @@ Stage-0 Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["sum(_col3)","count()"],keys:_col0, _col1, _col2 Select Operator [SEL_174] (rows=1 width=128) Output:["_col0","_col1","_col2","_col3"] - Merge Join Operator [MERGEJOIN_1428] (rows=1 width=128) - Conds:RS_171._col1=RS_172._col0(Inner),Output:["_col2","_col3","_col6","_col7","_col8"] - <-Reducer 70 [SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_172] + Merge Join Operator [MERGEJOIN_1425] (rows=1 width=128) + Conds:RS_171._col1=RS_1700._col0(Inner),Output:["_col2","_col3","_col7","_col8","_col9"] + <-Map 105 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_1700] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_1397] (rows=724 width=4) - Conds:RS_1678._col1, _col2, _col3=RS_1690._col0, _col1, _col2(Inner),Output:["_col0"] - <-Map 69 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1678] - PartitionCols:_col1, _col2, _col3 - Select Operator [SEL_1669] (rows=458612 width=15) - Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_1660] (rows=458612 width=15) - predicate:(i_brand_id is not null and i_category_id is not null and i_class_id is not null) - Please refer to the previous TableScan [TS_90] - <-Reducer 75 [ONE_TO_ONE_EDGE] vectorized - FORWARD [RS_1690] - PartitionCols:_col0, _col1, _col2 - Select Operator [SEL_1689] (rows=1 width=12) - Output:["_col0","_col1","_col2"] - Filter Operator [FIL_1688] (rows=1 width=20) - predicate:(_col3 = 3L) - Group By Operator [GBY_1687] (rows=121728 width=19) - Output:["_col0","_col1","_col2","_col3"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2 - <-Union 74 [SIMPLE_EDGE] - <-Reducer 73 [CONTAINS] vectorized - Reduce Output Operator [RS_1818] - PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_1817] (rows=121728 width=19) - Output:["_col0","_col1","_col2","_col3"],aggregations:["count(_col3)"],keys:_col0, _col1, _col2 - Group By Operator [GBY_1816] (rows=121728 width=19) - Output:["_col0","_col1","_col2","_col3"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2 - <-Reducer 72 [SIMPLE_EDGE] - SHUFFLE [RS_110] - PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_109] (rows=121728 width=19) - Output:["_col0","_col1","_col2","_col3"],aggregations:["count()"],keys:_col4, _col5, _col6 - Merge Join Operator [MERGEJOIN_1392] (rows=14628613 width=11) - Conds:RS_105._col1=RS_1679._col0(Inner),Output:["_col4","_col5","_col6"] - <-Map 69 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1679] - PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_1669] - <-Reducer 98 [SIMPLE_EDGE] - SHUFFLE [RS_105] - PartitionCols:_col1 - Please refer to the previous Merge Join Operator [MERGEJOIN_1391] - <-Reducer 77 [CONTAINS] vectorized - Reduce Output Operator [RS_1826] - PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_1825] (rows=121728 width=19) - Output:["_col0","_col1","_col2","_col3"],aggregations:["count(_col3)"],keys:_col0, _col1, _col2 - Group By Operator [GBY_1824] (rows=121728 width=19) - Output:["_col0","_col1","_col2","_col3"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2 - <-Reducer 76 [SIMPLE_EDGE] - SHUFFLE [RS_130] - PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_129] (rows=121728 width=19) - Output:["_col0","_col1","_col2","_col3"],aggregations:["count()"],keys:_col4, _col5, _col6 - Merge Join Operator [MERGEJOIN_1394] (rows=7620440 width=11) - Conds:RS_125._col1=RS_1680._col0(Inner),Output:["_col4","_col5","_col6"] - <-Map 69 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1680] - PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_1669] - <-Reducer 101 [SIMPLE_EDGE] - SHUFFLE [RS_125] - PartitionCols:_col1 - Please refer to the previous Merge Join Operator [MERGEJOIN_1393] - <-Reducer 79 [CONTAINS] vectorized - Reduce Output Operator [RS_1834] - PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_1833] (rows=121728 width=19) - Output:["_col0","_col1","_col2","_col3"],aggregations:["count(_col3)"],keys:_col0, _col1, _col2 - Group By Operator [GBY_1832] (rows=121728 width=19) - Output:["_col0","_col1","_col2","_col3"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2 - <-Reducer 78 [SIMPLE_EDGE] - SHUFFLE [RS_151] - PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_150] (rows=121728 width=19) - Output:["_col0","_col1","_col2","_col3"],aggregations:["count()"],keys:_col4, _col5, _col6 - Merge Join Operator [MERGEJOIN_1396] (rows=3828623 width=11) - Conds:RS_146._col1=RS_1681._col0(Inner),Output:["_col4","_col5","_col6"] - <-Map 69 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1681] - PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_1669] - <-Reducer 103 [SIMPLE_EDGE] - SHUFFLE [RS_146] - PartitionCols:_col1 - Please refer to the previous Merge Join Operator [MERGEJOIN_1395] + Select Operator [SEL_1691] (rows=462000 width=15) + Output:["_col0","_col1","_col2","_col3"] + Please refer to the previous TableScan [TS_163] <-Reducer 54 [ONE_TO_ONE_EDGE] FORWARD [RS_171] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_1390] (rows=15062131 width=15) - Conds:RS_168._col1=RS_1670._col0(Inner),Output:["_col1","_col2","_col3","_col6","_col7","_col8"] - <-Map 69 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1670] + Merge Join Operator [MERGEJOIN_1424] (rows=1 width=120) + Conds:RS_168._col1=RS_169._col0(Inner),Output:["_col1","_col2","_col3"] + <-Reducer 75 [SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_169] PartitionCols:_col0 - Select Operator [SEL_1661] (rows=462000 width=15) - Output:["_col0","_col1","_col2","_col3"] - Please refer to the previous TableScan [TS_90] + Merge Join Operator [MERGEJOIN_1423] (rows=724 width=4) + Conds:RS_1709._col1, _col2, _col3=RS_1690._col0, _col1, _col2(Inner),Output:["_col0"] + <-Map 105 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_1709] + PartitionCols:_col1, _col2, _col3 + Select Operator [SEL_1701] (rows=458612 width=15) + Output:["_col0","_col1","_col2","_col3"] + Filter Operator [FIL_1692] (rows=458612 width=15) + predicate:(i_brand_id is not null and i_category_id is not null and i_class_id is not null) + Please refer to the previous TableScan [TS_163] + <-Reducer 74 [ONE_TO_ONE_EDGE] vectorized + FORWARD [RS_1690] + PartitionCols:_col0, _col1, _col2 + Select Operator [SEL_1689] (rows=1 width=12) + Output:["_col0","_col1","_col2"] + Filter Operator [FIL_1688] (rows=1 width=20) + predicate:(_col3 = 3L) + Group By Operator [GBY_1687] (rows=121728 width=19) + Output:["_col0","_col1","_col2","_col3"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2 + <-Union 73 [SIMPLE_EDGE] + <-Reducer 72 [CONTAINS] vectorized + Reduce Output Operator [RS_1842] + PartitionCols:_col0, _col1, _col2 + Group By Operator [GBY_1841] (rows=121728 width=19) + Output:["_col0","_col1","_col2","_col3"],aggregations:["count(_col3)"],keys:_col0, _col1, _col2 + Group By Operator [GBY_1840] (rows=121728 width=19) + Output:["_col0","_col1","_col2","_col3"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2 + <-Reducer 71 [SIMPLE_EDGE] + SHUFFLE [RS_108] + PartitionCols:_col0, _col1, _col2 + Please refer to the previous Group By Operator [GBY_107] + <-Reducer 91 [CONTAINS] vectorized + Reduce Output Operator [RS_1856] + PartitionCols:_col0, _col1, _col2 + Group By Operator [GBY_1855] (rows=121728 width=19) + Output:["_col0","_col1","_col2","_col3"],aggregations:["count(_col3)"],keys:_col0, _col1, _col2 + Group By Operator [GBY_1854] (rows=121728 width=19) + Output:["_col0","_col1","_col2","_col3"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2 + <-Reducer 90 [SIMPLE_EDGE] + SHUFFLE [RS_128] + PartitionCols:_col0, _col1, _col2 + Please refer to the previous Group By Operator [GBY_127] + <-Reducer 97 [CONTAINS] vectorized + Reduce Output Operator [RS_1870] + PartitionCols:_col0, _col1, _col2 + Group By Operator [GBY_1869] (rows=121728 width=19) + Output:["_col0","_col1","_col2","_col3"],aggregations:["count(_col3)"],keys:_col0, _col1, _col2 + Group By Operator [GBY_1868] (rows=121728 width=19) + Output:["_col0","_col1","_col2","_col3"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2 + <-Reducer 96 [SIMPLE_EDGE] + SHUFFLE [RS_149] + PartitionCols:_col0, _col1, _col2 + Please refer to the previous Group By Operator [GBY_148] <-Reducer 53 [SIMPLE_EDGE] SHUFFLE [RS_168] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_1389] (rows=15062131 width=4) - Conds:RS_1695._col0=RS_1646._col0(Inner),Output:["_col1","_col2","_col3"] + Merge Join Operator [MERGEJOIN_1416] (rows=15062131 width=4) + Conds:RS_1719._col0=RS_1673._col0(Inner),Output:["_col1","_col2","_col3"] <-Map 57 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_1646] + PARTITION_ONLY_SHUFFLE [RS_1673] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_1645] + Please refer to the previous Select Operator [SEL_1672] <-Map 52 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1695] + SHUFFLE [RS_1719] PartitionCols:_col0 - Select Operator [SEL_1694] (rows=550076554 width=118) + Select Operator [SEL_1718] (rows=550076554 width=118) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_1693] (rows=550076554 width=118) - predicate:((ss_item_sk BETWEEN DynamicValue(RS_172_item_i_item_sk_min) AND DynamicValue(RS_172_item_i_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_172_item_i_item_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_166_date_dim_d_date_sk_min) AND DynamicValue(RS_166_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_166_date_dim_d_date_sk_bloom_filter))) and ss_sold_date_sk is not null) + Filter Operator [FIL_1717] (rows=550076554 width=118) + predicate:((ss_item_sk BETWEEN DynamicValue(RS_169_item_i_item_sk_min) AND DynamicValue(RS_169_item_i_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_169_item_i_item_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_166_date_dim_d_date_sk_min) AND DynamicValue(RS_166_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_166_date_dim_d_date_sk_bloom_filter))) and ss_sold_date_sk is not null) TableScan [TS_82] (rows=575995635 width=118) default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_item_sk","ss_quantity","ss_list_price"] <-Reducer 58 [BROADCAST_EDGE] vectorized - BROADCAST [RS_1659] - Group By Operator [GBY_1658] (rows=1 width=12) + BROADCAST [RS_1686] + Group By Operator [GBY_1685] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Map 57 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_1655] - Group By Operator [GBY_1652] (rows=1 width=12) + PARTITION_ONLY_SHUFFLE [RS_1682] + Group By Operator [GBY_1679] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_1647] (rows=50 width=4) + Select Operator [SEL_1674] (rows=50 width=4) Output:["_col0"] - Please refer to the previous Select Operator [SEL_1645] - <-Reducer 71 [BROADCAST_EDGE] vectorized - BROADCAST [RS_1692] - Group By Operator [GBY_1691] (rows=1 width=12) + Please refer to the previous Select Operator [SEL_1672] + <-Reducer 76 [BROADCAST_EDGE] vectorized + BROADCAST [RS_1716] + Group By Operator [GBY_1715] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Reducer 70 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_888] - Group By Operator [GBY_887] (rows=1 width=12) + <-Reducer 75 [CUSTOM_SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_910] + Group By Operator [GBY_909] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_886] (rows=724 width=4) + Select Operator [SEL_908] (rows=724 width=4) Output:["_col0"] - Please refer to the previous Merge Join Operator [MERGEJOIN_1397] + Please refer to the previous Merge Join Operator [MERGEJOIN_1423] diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/query15.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/query15.q.out index b41b4e3f33..c3bbf1f104 100644 --- a/ql/src/test/results/clientpositive/perf/tez/constraints/query15.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/query15.q.out @@ -49,94 +49,94 @@ POSTHOOK: Output: hdfs://### HDFS PATH ### Plan optimized by CBO. Vertex dependency in root stage -Map 7 <- Reducer 10 (BROADCAST_EDGE) -Reducer 10 <- Map 9 (CUSTOM_SIMPLE_EDGE) -Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 6 (SIMPLE_EDGE) -Reducer 3 <- Reducer 2 (SIMPLE_EDGE), Reducer 8 (SIMPLE_EDGE) -Reducer 4 <- Reducer 3 (SIMPLE_EDGE) +Map 1 <- Reducer 8 (BROADCAST_EDGE) +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 7 (SIMPLE_EDGE) +Reducer 3 <- Map 9 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) +Reducer 4 <- Map 10 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) Reducer 5 <- Reducer 4 (SIMPLE_EDGE) -Reducer 8 <- Map 7 (SIMPLE_EDGE), Map 9 (SIMPLE_EDGE) +Reducer 6 <- Reducer 5 (SIMPLE_EDGE) +Reducer 8 <- Map 7 (CUSTOM_SIMPLE_EDGE) Stage-0 Fetch Operator limit:100 Stage-1 - Reducer 5 vectorized + Reducer 6 vectorized File Output Operator [FS_97] Limit [LIM_96] (rows=100 width=201) Number of rows:100 - Select Operator [SEL_95] (rows=2555 width=201) + Select Operator [SEL_95] (rows=5110 width=201) Output:["_col0","_col1"] - <-Reducer 4 [SIMPLE_EDGE] vectorized + <-Reducer 5 [SIMPLE_EDGE] vectorized SHUFFLE [RS_94] - Group By Operator [GBY_93] (rows=2555 width=201) + Group By Operator [GBY_93] (rows=5110 width=201) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 - <-Reducer 3 [SIMPLE_EDGE] - SHUFFLE [RS_24] + <-Reducer 4 [SIMPLE_EDGE] + SHUFFLE [RS_23] PartitionCols:_col0 - Group By Operator [GBY_23] (rows=43435 width=201) - Output:["_col0","_col1"],aggregations:["sum(_col8)"],keys:_col3 + Group By Operator [GBY_22] (rows=86870 width=201) + Output:["_col0","_col1"],aggregations:["sum(_col2)"],keys:_col8 Top N Key Operator [TNK_43] (rows=20154874 width=205) - keys:_col3,sort order:+,top n:100 - Select Operator [SEL_22] (rows=20154874 width=205) - Output:["_col3","_col8"] - Filter Operator [FIL_21] (rows=20154874 width=205) - predicate:(_col4 or _col5 or _col9) + keys:_col8,sort order:+,top n:100 + Select Operator [SEL_21] (rows=20154874 width=205) + Output:["_col2","_col8"] + Filter Operator [FIL_20] (rows=20154874 width=205) + predicate:(_col10 or _col3 or _col9) Merge Join Operator [MERGEJOIN_76] (rows=20154874 width=205) - Conds:RS_18._col0=RS_19._col1(Inner),Output:["_col3","_col4","_col5","_col8","_col9"] - <-Reducer 2 [SIMPLE_EDGE] - SHUFFLE [RS_18] + Conds:RS_17._col6=RS_92._col0(Inner),Output:["_col2","_col3","_col8","_col9","_col10"] + <-Map 10 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_92] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_74] (rows=80000000 width=101) - Conds:RS_79._col1=RS_81._col0(Inner),Output:["_col0","_col3","_col4","_col5"] - <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_79] - PartitionCols:_col1 - Select Operator [SEL_78] (rows=80000000 width=8) + Select Operator [SEL_91] (rows=40000000 width=101) + Output:["_col0","_col1","_col2","_col3"] + TableScan [TS_9] (rows=40000000 width=179) + default@customer_address,customer_address,Tbl:COMPLETE,Col:COMPLETE,Output:["ca_address_sk","ca_state","ca_zip"] + <-Reducer 3 [SIMPLE_EDGE] + SHUFFLE [RS_17] + PartitionCols:_col6 + Merge Join Operator [MERGEJOIN_75] (rows=20154874 width=112) + Conds:RS_14._col1=RS_90._col0(Inner),Output:["_col2","_col3","_col6"] + <-Map 9 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_90] + PartitionCols:_col0 + Select Operator [SEL_89] (rows=80000000 width=8) Output:["_col0","_col1"] - Filter Operator [FIL_77] (rows=80000000 width=8) + Filter Operator [FIL_88] (rows=80000000 width=8) predicate:c_current_addr_sk is not null - TableScan [TS_0] (rows=80000000 width=8) + TableScan [TS_6] (rows=80000000 width=8) default@customer,customer,Tbl:COMPLETE,Col:COMPLETE,Output:["c_customer_sk","c_current_addr_sk"] - <-Map 6 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_81] - PartitionCols:_col0 - Select Operator [SEL_80] (rows=40000000 width=101) - Output:["_col0","_col1","_col2","_col3"] - TableScan [TS_3] (rows=40000000 width=179) - default@customer_address,customer_address,Tbl:COMPLETE,Col:COMPLETE,Output:["ca_address_sk","ca_state","ca_zip"] - <-Reducer 8 [SIMPLE_EDGE] - SHUFFLE [RS_19] - PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_75] (rows=20154874 width=111) - Conds:RS_92._col0=RS_84._col0(Inner),Output:["_col1","_col2","_col3"] - <-Map 9 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_84] - PartitionCols:_col0 - Select Operator [SEL_83] (rows=130 width=4) - Output:["_col0"] - Filter Operator [FIL_82] (rows=130 width=12) - predicate:((d_qoy = 2) and (d_year = 2000)) - TableScan [TS_8] (rows=73049 width=12) - default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year","d_qoy"] - <-Map 7 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_92] - PartitionCols:_col0 - Select Operator [SEL_91] (rows=285117831 width=123) - Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_90] (rows=285117831 width=119) - predicate:((cs_sold_date_sk BETWEEN DynamicValue(RS_12_date_dim_d_date_sk_min) AND DynamicValue(RS_12_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_12_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_5] (rows=287989836 width=119) - default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["cs_sold_date_sk","cs_bill_customer_sk","cs_sales_price"] - <-Reducer 10 [BROADCAST_EDGE] vectorized - BROADCAST [RS_89] - Group By Operator [GBY_88] (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_87] - Group By Operator [GBY_86] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_85] (rows=130 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_83] + <-Reducer 2 [SIMPLE_EDGE] + SHUFFLE [RS_14] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_74] (rows=20154874 width=111) + Conds:RS_87._col0=RS_79._col0(Inner),Output:["_col1","_col2","_col3"] + <-Map 7 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_79] + PartitionCols:_col0 + Select Operator [SEL_78] (rows=130 width=4) + Output:["_col0"] + Filter Operator [FIL_77] (rows=130 width=12) + predicate:((d_qoy = 2) and (d_year = 2000)) + 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 1 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_87] + PartitionCols:_col0 + Select Operator [SEL_86] (rows=285117831 width=123) + Output:["_col0","_col1","_col2","_col3"] + Filter Operator [FIL_85] (rows=285117831 width=119) + predicate:((cs_sold_date_sk BETWEEN DynamicValue(RS_12_date_dim_d_date_sk_min) AND DynamicValue(RS_12_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_12_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_0] (rows=287989836 width=119) + default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["cs_sold_date_sk","cs_bill_customer_sk","cs_sales_price"] + <-Reducer 8 [BROADCAST_EDGE] vectorized + BROADCAST [RS_84] + Group By Operator [GBY_83] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 7 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_82] + Group By Operator [GBY_81] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_80] (rows=130 width=4) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_78] diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/query17.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/query17.q.out index 4e5c2a96d4..858fb05774 100644 --- a/ql/src/test/results/clientpositive/perf/tez/constraints/query17.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/query17.q.out @@ -103,225 +103,229 @@ POSTHOOK: Output: hdfs://### HDFS PATH ### Plan optimized by CBO. Vertex dependency in root stage -Map 1 <- Reducer 9 (BROADCAST_EDGE) -Map 19 <- Reducer 14 (BROADCAST_EDGE), Reducer 16 (BROADCAST_EDGE), Reducer 17 (BROADCAST_EDGE), Reducer 18 (BROADCAST_EDGE), Reducer 6 (BROADCAST_EDGE), Reducer 7 (BROADCAST_EDGE) -Reducer 10 <- Map 19 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) -Reducer 11 <- Reducer 10 (SIMPLE_EDGE), Reducer 15 (SIMPLE_EDGE) -Reducer 12 <- Map 21 (SIMPLE_EDGE), Reducer 11 (SIMPLE_EDGE) -Reducer 13 <- Map 22 (SIMPLE_EDGE), Reducer 12 (SIMPLE_EDGE) -Reducer 14 <- Map 8 (CUSTOM_SIMPLE_EDGE) -Reducer 15 <- Map 20 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) +Map 1 <- Reducer 11 (BROADCAST_EDGE), Reducer 16 (BROADCAST_EDGE), Reducer 17 (BROADCAST_EDGE) +Map 19 <- Reducer 14 (BROADCAST_EDGE), Reducer 16 (BROADCAST_EDGE), Reducer 17 (BROADCAST_EDGE), Reducer 18 (BROADCAST_EDGE), Reducer 8 (BROADCAST_EDGE), Reducer 9 (BROADCAST_EDGE) +Reducer 11 <- Map 10 (CUSTOM_SIMPLE_EDGE) +Reducer 12 <- Map 10 (SIMPLE_EDGE), Map 19 (SIMPLE_EDGE) +Reducer 13 <- Reducer 12 (SIMPLE_EDGE), Reducer 15 (SIMPLE_EDGE) +Reducer 14 <- Map 10 (CUSTOM_SIMPLE_EDGE) +Reducer 15 <- Map 10 (SIMPLE_EDGE), Map 20 (SIMPLE_EDGE) Reducer 16 <- Reducer 15 (CUSTOM_SIMPLE_EDGE) Reducer 17 <- Reducer 15 (CUSTOM_SIMPLE_EDGE) Reducer 18 <- Reducer 15 (CUSTOM_SIMPLE_EDGE) -Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 10 (SIMPLE_EDGE) Reducer 3 <- Reducer 13 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) -Reducer 4 <- Reducer 3 (SIMPLE_EDGE) -Reducer 5 <- Reducer 4 (SIMPLE_EDGE) -Reducer 6 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) -Reducer 7 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) -Reducer 9 <- Map 8 (CUSTOM_SIMPLE_EDGE) +Reducer 4 <- Map 21 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) +Reducer 5 <- Map 22 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) +Reducer 6 <- Reducer 5 (SIMPLE_EDGE) +Reducer 7 <- Reducer 6 (SIMPLE_EDGE) +Reducer 8 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) +Reducer 9 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) Stage-0 Fetch Operator limit:100 Stage-1 - Reducer 5 vectorized - File Output Operator [FS_252] - Limit [LIM_251] (rows=100 width=466) + Reducer 7 vectorized + File Output Operator [FS_260] + Limit [LIM_259] (rows=100 width=466) Number of rows:100 - Select Operator [SEL_250] (rows=8581091679 width=466) + Select Operator [SEL_258] (rows=8581091679 width=466) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14"] - <-Reducer 4 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_249] - Select Operator [SEL_248] (rows=8581091679 width=466) + <-Reducer 6 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_257] + Select Operator [SEL_256] (rows=8581091679 width=466) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13"] - Group By Operator [GBY_247] (rows=8581091679 width=466) + Group By Operator [GBY_255] (rows=8581091679 width=466) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14"],aggregations:["count(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)","sum(VALUE._col3)","count(VALUE._col4)","sum(VALUE._col5)","sum(VALUE._col6)","sum(VALUE._col7)","count(VALUE._col8)","sum(VALUE._col9)","sum(VALUE._col10)","sum(VALUE._col11)"],keys:KEY._col0, KEY._col1, KEY._col2 - <-Reducer 3 [SIMPLE_EDGE] + <-Reducer 5 [SIMPLE_EDGE] SHUFFLE [RS_48] PartitionCols:_col0, _col1, _col2 Group By Operator [GBY_47] (rows=8581091679 width=466) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14"],aggregations:["count(_col3)","sum(_col3)","sum(_col7)","sum(_col6)","count(_col4)","sum(_col4)","sum(_col9)","sum(_col8)","count(_col5)","sum(_col5)","sum(_col11)","sum(_col10)"],keys:_col0, _col1, _col2 - Top N Key Operator [TNK_92] (rows=8581091679 width=381) + Top N Key Operator [TNK_94] (rows=8581091679 width=381) keys:_col0, _col1, _col2,sort order:+++,top n:100 Select Operator [SEL_45] (rows=8581091679 width=381) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11"] - Merge Join Operator [MERGEJOIN_204] (rows=8581091679 width=381) - Conds:RS_42._col2, _col1=RS_43._col11, _col12(Inner),Output:["_col3","_col6","_col7","_col13","_col19","_col22"] - <-Reducer 2 [SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_42] - PartitionCols:_col2, _col1 - Merge Join Operator [MERGEJOIN_198] (rows=47131396 width=11) - Conds:RS_224._col0=RS_211._col0(Inner),Output:["_col1","_col2","_col3"] - <-Map 8 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_211] + Merge Join Operator [MERGEJOIN_210] (rows=8581091679 width=381) + Conds:RS_42._col6=RS_254._col0(Inner),Output:["_col3","_col10","_col16","_col19","_col21","_col22"] + <-Map 22 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_254] + PartitionCols:_col0 + Select Operator [SEL_253] (rows=462000 width=288) + Output:["_col0","_col1","_col2"] + TableScan [TS_31] (rows=462000 width=288) + default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_item_id","i_item_desc"] + <-Reducer 4 [SIMPLE_EDGE] + SHUFFLE [RS_42] + PartitionCols:_col6 + Merge Join Operator [MERGEJOIN_209] (rows=8581091679 width=101) + Conds:RS_39._col8=RS_252._col0(Inner),Output:["_col3","_col6","_col10","_col16","_col19"] + <-Map 21 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_252] PartitionCols:_col0 - Select Operator [SEL_208] (rows=304 width=4) - Output:["_col0"] - Filter Operator [FIL_205] (rows=304 width=94) - predicate:(d_quarter_name) IN ('2000Q1', '2000Q2', '2000Q3') - TableScan [TS_3] (rows=73049 width=94) - default@date_dim,d3,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_quarter_name"] - <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_224] - PartitionCols:_col0 - Select Operator [SEL_223] (rows=285117831 width=15) - Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_222] (rows=285117831 width=15) - predicate:((cs_sold_date_sk BETWEEN DynamicValue(RS_40_d3_d_date_sk_min) AND DynamicValue(RS_40_d3_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_40_d3_d_date_sk_bloom_filter))) and cs_bill_customer_sk is not null and cs_sold_date_sk is not null) - TableScan [TS_0] (rows=287989836 width=15) - default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["cs_sold_date_sk","cs_bill_customer_sk","cs_item_sk","cs_quantity"] - <-Reducer 9 [BROADCAST_EDGE] vectorized - BROADCAST [RS_221] - Group By Operator [GBY_220] (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_218] - Group By Operator [GBY_216] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_212] (rows=304 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_208] - <-Reducer 13 [SIMPLE_EDGE] - SHUFFLE [RS_43] - PartitionCols:_col11, _col12 - Select Operator [SEL_38] (rows=42605597 width=383) - Output:["_col1","_col2","_col8","_col11","_col12","_col14","_col17"] - Merge Join Operator [MERGEJOIN_203] (rows=42605597 width=383) - Conds:RS_35._col1=RS_246._col0(Inner),Output:["_col5","_col8","_col9","_col11","_col14","_col16","_col17"] - <-Map 22 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_246] - PartitionCols:_col0 - Select Operator [SEL_245] (rows=462000 width=288) - Output:["_col0","_col1","_col2"] - TableScan [TS_24] (rows=462000 width=288) - default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_item_id","i_item_desc"] - <-Reducer 12 [SIMPLE_EDGE] - SHUFFLE [RS_35] - PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_202] (rows=42605597 width=103) - Conds:RS_32._col3=RS_244._col0(Inner),Output:["_col1","_col5","_col8","_col9","_col11","_col14"] - <-Map 21 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_244] - PartitionCols:_col0 - Select Operator [SEL_243] (rows=1704 width=90) - Output:["_col0","_col1"] - TableScan [TS_22] (rows=1704 width=90) - default@store,store,Tbl:COMPLETE,Col:COMPLETE,Output:["s_store_sk","s_state"] - <-Reducer 11 [SIMPLE_EDGE] - SHUFFLE [RS_32] - PartitionCols:_col3 - Merge Join Operator [MERGEJOIN_201] (rows=42605597 width=19) - Conds:RS_29._col1, _col2, _col4=RS_30._col1, _col2, _col3(Inner),Output:["_col1","_col3","_col5","_col8","_col9","_col11"] - <-Reducer 15 [SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_30] - PartitionCols:_col1, _col2, _col3 - Merge Join Operator [MERGEJOIN_200] (rows=8143830 width=14) - Conds:RS_229._col0=RS_215._col0(Inner),Output:["_col1","_col2","_col3","_col4"] - <-Map 8 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_215] - PartitionCols:_col0 - Select Operator [SEL_210] (rows=304 width=4) - Output:["_col0"] - Filter Operator [FIL_207] (rows=304 width=94) - predicate:(d_quarter_name) IN ('2000Q1', '2000Q2', '2000Q3') - Please refer to the previous TableScan [TS_3] - <-Map 20 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_229] - PartitionCols:_col0 - Select Operator [SEL_228] (rows=53632139 width=19) - Output:["_col0","_col1","_col2","_col3","_col4"] - Filter Operator [FIL_227] (rows=53632139 width=19) - predicate:(sr_customer_sk is not null and sr_returned_date_sk is not null) - TableScan [TS_12] (rows=57591150 width=19) - default@store_returns,store_returns,Tbl:COMPLETE,Col:COMPLETE,Output:["sr_returned_date_sk","sr_item_sk","sr_customer_sk","sr_ticket_number","sr_return_quantity"] - <-Reducer 10 [SIMPLE_EDGE] - SHUFFLE [RS_29] - PartitionCols:_col1, _col2, _col4 - Merge Join Operator [MERGEJOIN_199] (rows=27749405 width=10) - Conds:RS_242._col0=RS_213._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5"] - <-Map 8 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_213] - PartitionCols:_col0 - Select Operator [SEL_209] (rows=101 width=4) - Output:["_col0"] - Filter Operator [FIL_206] (rows=101 width=94) - predicate:(d_quarter_name = '2000Q1') - Please refer to the previous TableScan [TS_3] - <-Map 19 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_242] - PartitionCols:_col0 - Select Operator [SEL_241] (rows=501694138 width=23) - Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - Filter Operator [FIL_240] (rows=501694138 width=23) - predicate:((ss_customer_sk BETWEEN DynamicValue(RS_30_store_returns_sr_customer_sk_min) AND DynamicValue(RS_30_store_returns_sr_customer_sk_max) and in_bloom_filter(ss_customer_sk, DynamicValue(RS_30_store_returns_sr_customer_sk_bloom_filter))) and (ss_customer_sk BETWEEN DynamicValue(RS_42_catalog_sales_cs_bill_customer_sk_min) AND DynamicValue(RS_42_catalog_sales_cs_bill_customer_sk_max) and in_bloom_filter(ss_customer_sk, DynamicValue(RS_42_catalog_sales_cs_bill_customer_sk_bloom_filter))) and (ss_item_sk BETWEEN DynamicValue(RS_30_store_returns_sr_item_sk_min) AND DynamicValue(RS_30_store_returns_sr_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_30_store_returns_sr_item_sk_bloom_filter))) and (ss_item_sk BETWEEN DynamicValue(RS_42_catalog_sales_cs_item_sk_min) AND DynamicValue(RS_42_catalog_sales_cs_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_42_catalog_sales_cs_item_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_27_d1_d_date_sk_min) AND DynamicValue(RS_27_d1_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_27_d1_d_date_sk_bloom_filter))) and (ss_ticket_number BETWEEN DynamicValue(RS_30_store_returns_sr_ticket_number_min) AND DynamicValue(RS_30_store_returns_sr_ticket_number_max) and in_bloom_filter(ss_ticket_number, DynamicValue(RS_30_store_returns_sr_ticket_number_bloom_filter))) and ss_customer_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null) - TableScan [TS_6] (rows=575995635 width=23) - default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_item_sk","ss_customer_sk","ss_store_sk","ss_ticket_number","ss_quantity"] - <-Reducer 14 [BROADCAST_EDGE] vectorized - BROADCAST [RS_226] - Group By Operator [GBY_225] (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_219] - Group By Operator [GBY_217] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_214] (rows=101 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_209] - <-Reducer 16 [BROADCAST_EDGE] vectorized - BROADCAST [RS_231] - Group By Operator [GBY_230] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Reducer 15 [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=1000000)"] - Select Operator [SEL_118] (rows=8143830 width=8) - Output:["_col0"] - Please refer to the previous Merge Join Operator [MERGEJOIN_200] - <-Reducer 17 [BROADCAST_EDGE] vectorized - BROADCAST [RS_233] - Group By Operator [GBY_232] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Reducer 15 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_125] - Group By Operator [GBY_124] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_123] (rows=8143830 width=6) - Output:["_col0"] - Please refer to the previous Merge Join Operator [MERGEJOIN_200] - <-Reducer 18 [BROADCAST_EDGE] vectorized - BROADCAST [RS_235] - Group By Operator [GBY_234] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=5304149)"] - <-Reducer 15 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_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=5304149)"] - Select Operator [SEL_128] (rows=8143830 width=8) - Output:["_col0"] - Please refer to the previous Merge Join Operator [MERGEJOIN_200] - <-Reducer 6 [BROADCAST_EDGE] vectorized - BROADCAST [RS_237] - Group By Operator [GBY_236] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Reducer 2 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_145] - Group By Operator [GBY_144] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_143] (rows=47131396 width=8) - Output:["_col0"] - Please refer to the previous Merge Join Operator [MERGEJOIN_198] - <-Reducer 7 [BROADCAST_EDGE] vectorized - BROADCAST [RS_239] - Group By Operator [GBY_238] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Reducer 2 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_150] - Group By Operator [GBY_149] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_148] (rows=47131396 width=7) + Select Operator [SEL_251] (rows=1704 width=90) + Output:["_col0","_col1"] + TableScan [TS_29] (rows=1704 width=90) + default@store,store,Tbl:COMPLETE,Col:COMPLETE,Output:["s_store_sk","s_state"] + <-Reducer 3 [SIMPLE_EDGE] + SHUFFLE [RS_39] + PartitionCols:_col8 + Merge Join Operator [MERGEJOIN_208] (rows=8581091679 width=19) + Conds:RS_36._col1, _col2=RS_37._col9, _col8(Inner),Output:["_col3","_col6","_col8","_col10","_col16"] + <-Reducer 2 [SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_36] + PartitionCols:_col1, _col2 + Merge Join Operator [MERGEJOIN_204] (rows=47131396 width=11) + Conds:RS_239._col0=RS_217._col0(Inner),Output:["_col1","_col2","_col3"] + <-Map 10 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_217] + PartitionCols:_col0 + Select Operator [SEL_214] (rows=304 width=4) + Output:["_col0"] + Filter Operator [FIL_211] (rows=304 width=94) + predicate:(d_quarter_name) IN ('2000Q1', '2000Q2', '2000Q3') + TableScan [TS_3] (rows=73049 width=94) + default@date_dim,d3,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_quarter_name"] + <-Map 1 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_239] + PartitionCols:_col0 + Select Operator [SEL_238] (rows=285117831 width=15) + Output:["_col0","_col1","_col2","_col3"] + Filter Operator [FIL_237] (rows=285117831 width=15) + predicate:((cs_bill_customer_sk BETWEEN DynamicValue(RS_26_store_returns_sr_customer_sk_min) AND DynamicValue(RS_26_store_returns_sr_customer_sk_max) and in_bloom_filter(cs_bill_customer_sk, DynamicValue(RS_26_store_returns_sr_customer_sk_bloom_filter))) and (cs_item_sk BETWEEN DynamicValue(RS_26_store_returns_sr_item_sk_min) AND DynamicValue(RS_26_store_returns_sr_item_sk_max) and in_bloom_filter(cs_item_sk, DynamicValue(RS_26_store_returns_sr_item_sk_bloom_filter))) and (cs_sold_date_sk BETWEEN DynamicValue(RS_34_d3_d_date_sk_min) AND DynamicValue(RS_34_d3_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_34_d3_d_date_sk_bloom_filter))) and cs_bill_customer_sk is not null and cs_sold_date_sk is not null) + TableScan [TS_0] (rows=287989836 width=15) + default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["cs_sold_date_sk","cs_bill_customer_sk","cs_item_sk","cs_quantity"] + <-Reducer 16 [BROADCAST_EDGE] vectorized + BROADCAST [RS_232] + Group By Operator [GBY_231] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Reducer 15 [CUSTOM_SIMPLE_EDGE] + 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=8143830 width=6) + Output:["_col0"] + Merge Join Operator [MERGEJOIN_206] (rows=8143830 width=14) + Conds:RS_230._col0=RS_221._col0(Inner),Output:["_col1","_col2","_col3","_col4"] + <-Map 10 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_221] + PartitionCols:_col0 + Select Operator [SEL_216] (rows=304 width=4) Output:["_col0"] - Please refer to the previous Merge Join Operator [MERGEJOIN_198] + Filter Operator [FIL_213] (rows=304 width=94) + predicate:(d_quarter_name) IN ('2000Q1', '2000Q2', '2000Q3') + Please refer to the previous TableScan [TS_3] + <-Map 20 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_230] + PartitionCols:_col0 + Select Operator [SEL_229] (rows=53632139 width=19) + Output:["_col0","_col1","_col2","_col3","_col4"] + Filter Operator [FIL_228] (rows=53632139 width=19) + predicate:(sr_customer_sk is not null and sr_returned_date_sk is not null) + TableScan [TS_12] (rows=57591150 width=19) + default@store_returns,store_returns,Tbl:COMPLETE,Col:COMPLETE,Output:["sr_returned_date_sk","sr_item_sk","sr_customer_sk","sr_ticket_number","sr_return_quantity"] + <-Reducer 17 [BROADCAST_EDGE] vectorized + BROADCAST [RS_235] + Group By Operator [GBY_234] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Reducer 15 [CUSTOM_SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_122] + Group By Operator [GBY_121] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_120] (rows=8143830 width=8) + Output:["_col0"] + Please refer to the previous Merge Join Operator [MERGEJOIN_206] + <-Reducer 11 [BROADCAST_EDGE] vectorized + BROADCAST [RS_227] + Group By Operator [GBY_226] (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_224] + Group By Operator [GBY_222] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_218] (rows=304 width=4) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_214] + <-Reducer 13 [SIMPLE_EDGE] + SHUFFLE [RS_37] + PartitionCols:_col9, _col8 + Merge Join Operator [MERGEJOIN_207] (rows=42605597 width=19) + Conds:RS_25._col2, _col1, _col4=RS_26._col2, _col1, _col3(Inner),Output:["_col1","_col3","_col5","_col8","_col9","_col11"] + <-Reducer 15 [SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_26] + PartitionCols:_col2, _col1, _col3 + Please refer to the previous Merge Join Operator [MERGEJOIN_206] + <-Reducer 12 [SIMPLE_EDGE] + SHUFFLE [RS_25] + PartitionCols:_col2, _col1, _col4 + Merge Join Operator [MERGEJOIN_205] (rows=27749405 width=10) + Conds:RS_250._col0=RS_219._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5"] + <-Map 10 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_219] + PartitionCols:_col0 + Select Operator [SEL_215] (rows=101 width=4) + Output:["_col0"] + Filter Operator [FIL_212] (rows=101 width=94) + predicate:(d_quarter_name = '2000Q1') + Please refer to the previous TableScan [TS_3] + <-Map 19 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_250] + PartitionCols:_col0 + Select Operator [SEL_249] (rows=501694138 width=23) + Output:["_col0","_col1","_col2","_col3","_col4","_col5"] + Filter Operator [FIL_248] (rows=501694138 width=23) + predicate:((ss_customer_sk BETWEEN DynamicValue(RS_26_store_returns_sr_customer_sk_min) AND DynamicValue(RS_26_store_returns_sr_customer_sk_max) and in_bloom_filter(ss_customer_sk, DynamicValue(RS_26_store_returns_sr_customer_sk_bloom_filter))) and (ss_customer_sk BETWEEN DynamicValue(RS_36_catalog_sales_cs_bill_customer_sk_min) AND DynamicValue(RS_36_catalog_sales_cs_bill_customer_sk_max) and in_bloom_filter(ss_customer_sk, DynamicValue(RS_36_catalog_sales_cs_bill_customer_sk_bloom_filter))) and (ss_item_sk BETWEEN DynamicValue(RS_26_store_returns_sr_item_sk_min) AND DynamicValue(RS_26_store_returns_sr_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_26_store_returns_sr_item_sk_bloom_filter))) and (ss_item_sk BETWEEN DynamicValue(RS_36_catalog_sales_cs_item_sk_min) AND DynamicValue(RS_36_catalog_sales_cs_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_36_catalog_sales_cs_item_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_23_d1_d_date_sk_min) AND DynamicValue(RS_23_d1_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_23_d1_d_date_sk_bloom_filter))) and (ss_ticket_number BETWEEN DynamicValue(RS_26_store_returns_sr_ticket_number_min) AND DynamicValue(RS_26_store_returns_sr_ticket_number_max) and in_bloom_filter(ss_ticket_number, DynamicValue(RS_26_store_returns_sr_ticket_number_bloom_filter))) and ss_customer_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null) + TableScan [TS_6] (rows=575995635 width=23) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_item_sk","ss_customer_sk","ss_store_sk","ss_ticket_number","ss_quantity"] + <-Reducer 16 [BROADCAST_EDGE] vectorized + BROADCAST [RS_233] + Please refer to the previous Group By Operator [GBY_231] + <-Reducer 17 [BROADCAST_EDGE] vectorized + BROADCAST [RS_236] + Please refer to the previous Group By Operator [GBY_234] + <-Reducer 14 [BROADCAST_EDGE] vectorized + BROADCAST [RS_241] + Group By Operator [GBY_240] (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_225] + Group By Operator [GBY_223] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_220] (rows=101 width=4) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_215] + <-Reducer 18 [BROADCAST_EDGE] vectorized + BROADCAST [RS_243] + Group By Operator [GBY_242] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=5304149)"] + <-Reducer 15 [CUSTOM_SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_144] + Group By Operator [GBY_143] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=5304149)"] + Select Operator [SEL_142] (rows=8143830 width=8) + Output:["_col0"] + Please refer to the previous Merge Join Operator [MERGEJOIN_206] + <-Reducer 8 [BROADCAST_EDGE] vectorized + BROADCAST [RS_245] + Group By Operator [GBY_244] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Reducer 2 [CUSTOM_SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_154] + Group By Operator [GBY_153] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_152] (rows=47131396 width=7) + Output:["_col0"] + Please refer to the previous Merge Join Operator [MERGEJOIN_204] + <-Reducer 9 [BROADCAST_EDGE] vectorized + BROADCAST [RS_247] + Group By Operator [GBY_246] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Reducer 2 [CUSTOM_SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_159] + Group By Operator [GBY_158] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_157] (rows=47131396 width=8) + Output:["_col0"] + Please refer to the previous Merge Join Operator [MERGEJOIN_204] diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/query18.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/query18.q.out index b7f97780c7..d38965ac5e 100644 --- a/ql/src/test/results/clientpositive/perf/tez/constraints/query18.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/query18.q.out @@ -81,159 +81,157 @@ POSTHOOK: Output: hdfs://### HDFS PATH ### Plan optimized by CBO. Vertex dependency in root stage -Map 10 <- Reducer 15 (BROADCAST_EDGE), Reducer 17 (BROADCAST_EDGE), Reducer 7 (BROADCAST_EDGE) -Reducer 11 <- Map 10 (SIMPLE_EDGE), Map 14 (SIMPLE_EDGE) -Reducer 12 <- Map 16 (SIMPLE_EDGE), Reducer 11 (SIMPLE_EDGE) -Reducer 13 <- Map 18 (SIMPLE_EDGE), Reducer 12 (SIMPLE_EDGE) -Reducer 15 <- Map 14 (CUSTOM_SIMPLE_EDGE) -Reducer 17 <- Map 16 (CUSTOM_SIMPLE_EDGE) -Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) -Reducer 3 <- Map 9 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) -Reducer 4 <- Reducer 13 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) -Reducer 5 <- Reducer 4 (SIMPLE_EDGE) +Map 10 <- Reducer 14 (BROADCAST_EDGE), Reducer 16 (BROADCAST_EDGE), Reducer 8 (BROADCAST_EDGE) +Reducer 11 <- Map 10 (SIMPLE_EDGE), Map 13 (SIMPLE_EDGE) +Reducer 12 <- Map 15 (SIMPLE_EDGE), Reducer 11 (SIMPLE_EDGE) +Reducer 14 <- Map 13 (CUSTOM_SIMPLE_EDGE) +Reducer 16 <- Map 15 (CUSTOM_SIMPLE_EDGE) +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 9 (SIMPLE_EDGE) +Reducer 3 <- Reducer 12 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) +Reducer 4 <- Map 17 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) +Reducer 5 <- Map 18 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) Reducer 6 <- Reducer 5 (SIMPLE_EDGE) -Reducer 7 <- Reducer 3 (CUSTOM_SIMPLE_EDGE) +Reducer 7 <- Reducer 6 (SIMPLE_EDGE) +Reducer 8 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) Stage-0 Fetch Operator limit:100 Stage-1 - Reducer 6 vectorized - File Output Operator [FS_177] - Limit [LIM_176] (rows=100 width=1165) + Reducer 7 vectorized + File Output Operator [FS_181] + Limit [LIM_180] (rows=100 width=1165) Number of rows:100 - Select Operator [SEL_175] (rows=10969055 width=1165) + Select Operator [SEL_179] (rows=11124170 width=1165) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10"] - <-Reducer 5 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_174] - Select Operator [SEL_173] (rows=10969055 width=1165) + <-Reducer 6 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_178] + Select Operator [SEL_177] (rows=11124170 width=1165) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10"] - Group By Operator [GBY_172] (rows=10969055 width=1229) + Group By Operator [GBY_176] (rows=11124170 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] + <-Reducer 5 [SIMPLE_EDGE] SHUFFLE [RS_40] PartitionCols:_col0, _col1, _col2, _col3, _col4 - Group By Operator [GBY_39] (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_140] (rows=2193811 width=811) - Conds:RS_35._col0=RS_36._col3(Inner),Output:["_col3","_col5","_col6","_col7","_col10","_col15","_col16","_col17","_col18","_col19","_col22"] - <-Reducer 3 [SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_35] + Group By Operator [GBY_39] (rows=11124170 width=1229) + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18"],aggregations:["sum(_col12)","count(_col12)","sum(_col13)","count(_col13)","sum(_col14)","count(_col14)","sum(_col15)","count(_col15)","sum(_col16)","count(_col16)","sum(_col3)","count(_col3)","sum(_col19)","count(_col19)"],keys:_col21, _col5, _col6, _col7, 0L + Merge Join Operator [MERGEJOIN_144] (rows=2224834 width=816) + Conds:RS_35._col1=RS_175._col0(Inner),Output:["_col3","_col5","_col6","_col7","_col12","_col13","_col14","_col15","_col16","_col19","_col21"] + <-Map 18 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_175] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_136] (rows=4959744 width=368) - Conds:RS_32._col1=RS_148._col0(Inner),Output:["_col0","_col3","_col5","_col6","_col7"] - <-Map 9 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_148] + Select Operator [SEL_174] (rows=1861800 width=4) + Output:["_col0"] + TableScan [TS_24] (rows=1861800 width=4) + default@customer_demographics,cd2,Tbl:COMPLETE,Col:COMPLETE,Output:["cd_demo_sk"] + <-Reducer 4 [SIMPLE_EDGE] + SHUFFLE [RS_35] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_143] (rows=2193811 width=813) + Conds:RS_32._col11=RS_173._col0(Inner),Output:["_col1","_col3","_col5","_col6","_col7","_col12","_col13","_col14","_col15","_col16","_col19","_col21"] + <-Map 17 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_173] PartitionCols:_col0 - Select Operator [SEL_147] (rows=1861800 width=4) - Output:["_col0"] - TableScan [TS_6] (rows=1861800 width=4) - default@customer_demographics,cd2,Tbl:COMPLETE,Col:COMPLETE,Output:["cd_demo_sk"] - <-Reducer 2 [SIMPLE_EDGE] + Select Operator [SEL_172] (rows=462000 width=104) + Output:["_col0","_col1"] + TableScan [TS_22] (rows=462000 width=104) + default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_item_id"] + <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_32] - PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_135] (rows=4890586 width=371) - Conds:RS_143._col2=RS_146._col0(Inner),Output:["_col0","_col1","_col3","_col5","_col6","_col7"] - <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_143] - PartitionCols:_col2 - Select Operator [SEL_142] (rows=35631408 width=119) - Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_141] (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) - 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_146] + PartitionCols:_col11 + Merge Join Operator [MERGEJOIN_142] (rows=2193811 width=717) + Conds:RS_29._col0=RS_30._col1(Inner),Output:["_col1","_col3","_col5","_col6","_col7","_col11","_col12","_col13","_col14","_col15","_col16","_col19"] + <-Reducer 2 [SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_29] PartitionCols:_col0 - Select Operator [SEL_145] (rows=5490196 width=285) - Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_144] (rows=5490196 width=285) - predicate:(ca_state) IN ('ND', 'WI', 'AL', 'NC', 'OK', 'MS', 'TN') - 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_36] - PartitionCols:_col3 - Select Operator [SEL_28] (rows=15983481 width=735) - Output:["_col1","_col3","_col6","_col7","_col8","_col9","_col10","_col13"] - Merge Join Operator [MERGEJOIN_139] (rows=15983481 width=735) - Conds:RS_25._col3=RS_171._col0(Inner),Output:["_col1","_col4","_col5","_col6","_col7","_col8","_col11","_col13"] - <-Map 18 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_171] - PartitionCols:_col0 - Select Operator [SEL_170] (rows=462000 width=104) - Output:["_col0","_col1"] - TableScan [TS_17] (rows=462000 width=104) - default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_item_id"] - <-Reducer 12 [SIMPLE_EDGE] - SHUFFLE [RS_25] - PartitionCols:_col3 - Merge Join Operator [MERGEJOIN_138] (rows=15983481 width=639) - Conds:RS_22._col2=RS_159._col0(Inner),Output:["_col1","_col3","_col4","_col5","_col6","_col7","_col8","_col11"] - <-Map 16 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_159] - PartitionCols:_col0 - Select Operator [SEL_158] (rows=103433 width=116) - Output:["_col0","_col1"] - Filter Operator [FIL_157] (rows=103433 width=187) - predicate:((cd_education_status = 'College') and (cd_gender = 'M')) - TableScan [TS_14] (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_22] - PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_137] (rows=100578970 width=565) - Conds:RS_169._col0=RS_151._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"] - <-Map 14 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_151] - PartitionCols:_col0 - Select Operator [SEL_150] (rows=652 width=4) - Output:["_col0"] - Filter Operator [FIL_149] (rows=652 width=8) - predicate:(d_year = 2001) - TableScan [TS_11] (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_169] - PartitionCols:_col0 - Select Operator [SEL_168] (rows=283692098 width=573) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"] - Filter Operator [FIL_167] (rows=283692098 width=466) - predicate:((cs_bill_cdemo_sk BETWEEN DynamicValue(RS_23_cd1_cd_demo_sk_min) AND DynamicValue(RS_23_cd1_cd_demo_sk_max) and in_bloom_filter(cs_bill_cdemo_sk, DynamicValue(RS_23_cd1_cd_demo_sk_bloom_filter))) and (cs_bill_customer_sk BETWEEN DynamicValue(RS_35_customer_c_customer_sk_min) AND DynamicValue(RS_35_customer_c_customer_sk_max) and in_bloom_filter(cs_bill_customer_sk, DynamicValue(RS_35_customer_c_customer_sk_bloom_filter))) and (cs_sold_date_sk BETWEEN DynamicValue(RS_20_date_dim_d_date_sk_min) AND DynamicValue(RS_20_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_20_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_sold_date_sk is not null) - TableScan [TS_8] (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_156] - Group By Operator [GBY_155] (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_154] - Group By Operator [GBY_153] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_152] (rows=652 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_150] - <-Reducer 17 [BROADCAST_EDGE] vectorized - BROADCAST [RS_164] - Group By Operator [GBY_163] (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_162] - Group By Operator [GBY_161] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_160] (rows=103433 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_158] - <-Reducer 7 [BROADCAST_EDGE] vectorized - BROADCAST [RS_166] - Group By Operator [GBY_165] (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_117] - Group By Operator [GBY_116] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=4890586)"] - Select Operator [SEL_115] (rows=4959744 width=4) - Output:["_col0"] - Please refer to the previous Merge Join Operator [MERGEJOIN_136] + Merge Join Operator [MERGEJOIN_139] (rows=4890586 width=371) + Conds:RS_147._col2=RS_150._col0(Inner),Output:["_col0","_col1","_col3","_col5","_col6","_col7"] + <-Map 1 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_147] + PartitionCols:_col2 + Select Operator [SEL_146] (rows=35631408 width=119) + Output:["_col0","_col1","_col2","_col3"] + Filter Operator [FIL_145] (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) + 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 9 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_150] + PartitionCols:_col0 + Select Operator [SEL_149] (rows=5490196 width=285) + Output:["_col0","_col1","_col2","_col3"] + Filter Operator [FIL_148] (rows=5490196 width=285) + predicate:(ca_state) IN ('ND', 'WI', 'AL', 'NC', 'OK', 'MS', 'TN') + 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 12 [SIMPLE_EDGE] + SHUFFLE [RS_30] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_141] (rows=15983481 width=639) + Conds:RS_18._col2=RS_161._col0(Inner),Output:["_col1","_col3","_col4","_col5","_col6","_col7","_col8","_col11"] + <-Map 15 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_161] + PartitionCols:_col0 + Select Operator [SEL_160] (rows=103433 width=116) + Output:["_col0","_col1"] + Filter Operator [FIL_159] (rows=103433 width=187) + predicate:((cd_education_status = 'College') and (cd_gender = 'M')) + TableScan [TS_12] (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_18] + PartitionCols:_col2 + Merge Join Operator [MERGEJOIN_140] (rows=100578970 width=565) + Conds:RS_171._col0=RS_153._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"] + <-Map 13 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_153] + PartitionCols:_col0 + Select Operator [SEL_152] (rows=652 width=4) + Output:["_col0"] + Filter Operator [FIL_151] (rows=652 width=8) + predicate:(d_year = 2001) + TableScan [TS_9] (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_171] + PartitionCols:_col0 + Select Operator [SEL_170] (rows=283692098 width=573) + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"] + Filter Operator [FIL_169] (rows=283692098 width=466) + predicate:((cs_bill_cdemo_sk BETWEEN DynamicValue(RS_19_cd1_cd_demo_sk_min) AND DynamicValue(RS_19_cd1_cd_demo_sk_max) and in_bloom_filter(cs_bill_cdemo_sk, DynamicValue(RS_19_cd1_cd_demo_sk_bloom_filter))) and (cs_bill_customer_sk BETWEEN DynamicValue(RS_29_customer_c_customer_sk_min) AND DynamicValue(RS_29_customer_c_customer_sk_max) and in_bloom_filter(cs_bill_customer_sk, DynamicValue(RS_29_customer_c_customer_sk_bloom_filter))) and (cs_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(cs_sold_date_sk, DynamicValue(RS_16_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_sold_date_sk is not null) + TableScan [TS_6] (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 14 [BROADCAST_EDGE] vectorized + BROADCAST [RS_158] + Group By Operator [GBY_157] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 13 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_156] + Group By Operator [GBY_155] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_154] (rows=652 width=4) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_152] + <-Reducer 16 [BROADCAST_EDGE] vectorized + BROADCAST [RS_166] + Group By Operator [GBY_165] (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 + PARTITION_ONLY_SHUFFLE [RS_164] + Group By Operator [GBY_163] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_162] (rows=103433 width=4) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_160] + <-Reducer 8 [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=4890586)"] + <-Reducer 2 [CUSTOM_SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_111] + Group By Operator [GBY_110] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=4890586)"] + Select Operator [SEL_109] (rows=4890586 width=4) + Output:["_col0"] + Please refer to the previous Merge Join Operator [MERGEJOIN_139] diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/query19.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/query19.q.out index 7eb52efbf4..c27347da3b 100644 --- a/ql/src/test/results/clientpositive/perf/tez/constraints/query19.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/query19.q.out @@ -63,134 +63,134 @@ POSTHOOK: Output: hdfs://### HDFS PATH ### Plan optimized by CBO. Vertex dependency in root stage -Map 8 <- Reducer 12 (BROADCAST_EDGE), Reducer 14 (BROADCAST_EDGE) -Reducer 10 <- Map 13 (SIMPLE_EDGE), Reducer 9 (SIMPLE_EDGE) +Map 1 <- Reducer 10 (BROADCAST_EDGE), Reducer 12 (BROADCAST_EDGE) +Reducer 10 <- Map 9 (CUSTOM_SIMPLE_EDGE) Reducer 12 <- Map 11 (CUSTOM_SIMPLE_EDGE) -Reducer 14 <- Map 13 (CUSTOM_SIMPLE_EDGE) -Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 7 (SIMPLE_EDGE) -Reducer 3 <- Reducer 10 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) -Reducer 4 <- Map 15 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) -Reducer 5 <- Reducer 4 (SIMPLE_EDGE) -Reducer 6 <- Reducer 5 (SIMPLE_EDGE) -Reducer 9 <- Map 11 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 9 (SIMPLE_EDGE) +Reducer 3 <- Map 11 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) +Reducer 4 <- Map 13 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) +Reducer 5 <- Map 14 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) +Reducer 6 <- Map 15 (SIMPLE_EDGE), Reducer 5 (SIMPLE_EDGE) +Reducer 7 <- Reducer 6 (SIMPLE_EDGE) +Reducer 8 <- Reducer 7 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 - Reducer 6 vectorized - File Output Operator [FS_153] - Limit [LIM_152] (rows=100 width=419) + Reducer 8 vectorized + File Output Operator [FS_154] + Limit [LIM_153] (rows=100 width=419) Number of rows:100 - Select Operator [SEL_151] (rows=2098703 width=418) + Select Operator [SEL_152] (rows=7333 width=419) Output:["_col0","_col1","_col2","_col3","_col4"] - <-Reducer 5 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_150] - Select Operator [SEL_149] (rows=2098703 width=418) + <-Reducer 7 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_151] + Select Operator [SEL_150] (rows=7333 width=419) Output:["_col2","_col3","_col4","_col5","_col6"] - Group By Operator [GBY_148] (rows=2098703 width=314) + Group By Operator [GBY_149] (rows=7333 width=315) Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3 - <-Reducer 4 [SIMPLE_EDGE] - SHUFFLE [RS_35] + <-Reducer 6 [SIMPLE_EDGE] + SHUFFLE [RS_34] PartitionCols:_col0, _col1, _col2, _col3 - Group By Operator [GBY_34] (rows=2098703 width=314) - Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["sum(_col8)"],keys:_col12, _col11, _col13, _col14 - Select Operator [SEL_33] (rows=2098703 width=570) - Output:["_col8","_col11","_col12","_col13","_col14"] - Filter Operator [FIL_32] (rows=2098703 width=570) - predicate:(_col3 <> _col16) - Merge Join Operator [MERGEJOIN_121] (rows=2098703 width=570) - Conds:RS_29._col7=RS_147._col0(Inner),Output:["_col3","_col8","_col11","_col12","_col13","_col14","_col16"] + Group By Operator [GBY_33] (rows=7333 width=315) + Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["sum(_col4)"],keys:_col8, _col7, _col9, _col10 + Select Operator [SEL_32] (rows=2098703 width=570) + Output:["_col4","_col7","_col8","_col9","_col10"] + Filter Operator [FIL_31] (rows=2098703 width=570) + predicate:(_col16 <> _col14) + Merge Join Operator [MERGEJOIN_122] (rows=2098703 width=570) + Conds:RS_28._col12=RS_148._col0(Inner),Output:["_col4","_col7","_col8","_col9","_col10","_col14","_col16"] <-Map 15 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_147] + SHUFFLE [RS_148] PartitionCols:_col0 - Select Operator [SEL_146] (rows=1704 width=188) + Select Operator [SEL_147] (rows=40000000 width=188) Output:["_col0","_col1"] - TableScan [TS_21] (rows=1704 width=93) - default@store,store,Tbl:COMPLETE,Col:COMPLETE,Output:["s_store_sk","s_zip"] - <-Reducer 3 [SIMPLE_EDGE] - SHUFFLE [RS_29] - PartitionCols:_col7 - Merge Join Operator [MERGEJOIN_120] (rows=2098703 width=386) - Conds:RS_26._col0=RS_27._col2(Inner),Output:["_col3","_col7","_col8","_col11","_col12","_col13","_col14"] - <-Reducer 10 [SIMPLE_EDGE] - SHUFFLE [RS_27] - PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_119] (rows=2098703 width=202) - Conds:RS_17._col1=RS_137._col0(Inner),Output:["_col2","_col3","_col4","_col7","_col8","_col9","_col10"] + TableScan [TS_14] (rows=40000000 width=93) + default@customer_address,customer_address,Tbl:COMPLETE,Col:COMPLETE,Output:["ca_address_sk","ca_zip"] + <-Reducer 5 [SIMPLE_EDGE] + SHUFFLE [RS_28] + PartitionCols:_col12 + Merge Join Operator [MERGEJOIN_121] (rows=2098703 width=390) + Conds:RS_25._col3=RS_146._col0(Inner),Output:["_col4","_col7","_col8","_col9","_col10","_col12","_col14"] + <-Map 14 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_146] + PartitionCols:_col0 + Select Operator [SEL_145] (rows=1704 width=188) + Output:["_col0","_col1"] + TableScan [TS_12] (rows=1704 width=93) + default@store,store,Tbl:COMPLETE,Col:COMPLETE,Output:["s_store_sk","s_zip"] + <-Reducer 4 [SIMPLE_EDGE] + SHUFFLE [RS_25] + PartitionCols:_col3 + Merge Join Operator [MERGEJOIN_120] (rows=2098703 width=206) + Conds:RS_22._col2=RS_144._col0(Inner),Output:["_col3","_col4","_col7","_col8","_col9","_col10","_col12"] <-Map 13 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_137] + SHUFFLE [RS_144] PartitionCols:_col0 - Select Operator [SEL_136] (rows=7333 width=206) - Output:["_col0","_col1","_col2","_col3","_col4"] - Filter Operator [FIL_135] (rows=7333 width=210) - predicate:(i_manager_id = 7) - TableScan [TS_11] (rows=462000 width=210) - default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_brand_id","i_brand","i_manufact_id","i_manufact","i_manager_id"] - <-Reducer 9 [SIMPLE_EDGE] - SHUFFLE [RS_17] - PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_118] (rows=13737330 width=4) - Conds:RS_145._col0=RS_129._col0(Inner),Output:["_col1","_col2","_col3","_col4"] - <-Map 11 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_129] - PartitionCols:_col0 - Select Operator [SEL_128] (rows=50 width=4) - Output:["_col0"] - Filter Operator [FIL_127] (rows=50 width=12) - predicate:((d_moy = 11) and (d_year = 1999)) - TableScan [TS_8] (rows=73049 width=12) - default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year","d_moy"] - <-Map 8 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_145] - PartitionCols:_col0 - Select Operator [SEL_144] (rows=501694138 width=122) - Output:["_col0","_col1","_col2","_col3","_col4"] - Filter Operator [FIL_143] (rows=501694138 width=122) - predicate:((ss_item_sk BETWEEN DynamicValue(RS_18_item_i_item_sk_min) AND DynamicValue(RS_18_item_i_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_18_item_i_item_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_15_date_dim_d_date_sk_min) AND DynamicValue(RS_15_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_15_date_dim_d_date_sk_bloom_filter))) and ss_customer_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null) - TableScan [TS_5] (rows=575995635 width=122) - default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_item_sk","ss_customer_sk","ss_store_sk","ss_ext_sales_price"] - <-Reducer 12 [BROADCAST_EDGE] vectorized - BROADCAST [RS_134] - Group By Operator [GBY_133] (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_132] - Group By Operator [GBY_131] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_130] (rows=50 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_128] - <-Reducer 14 [BROADCAST_EDGE] vectorized - BROADCAST [RS_142] - Group By Operator [GBY_141] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 13 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_140] - Group By Operator [GBY_139] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_138] (rows=7333 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_136] - <-Reducer 2 [SIMPLE_EDGE] - SHUFFLE [RS_26] - PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_117] (rows=80000000 width=188) - Conds:RS_124._col1=RS_126._col0(Inner),Output:["_col0","_col3"] - <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_124] - PartitionCols:_col1 - Select Operator [SEL_123] (rows=80000000 width=8) + Select Operator [SEL_143] (rows=80000000 width=8) Output:["_col0","_col1"] - Filter Operator [FIL_122] (rows=80000000 width=8) + Filter Operator [FIL_142] (rows=80000000 width=8) predicate:c_current_addr_sk is not null - TableScan [TS_0] (rows=80000000 width=8) + TableScan [TS_9] (rows=80000000 width=8) default@customer,customer,Tbl:COMPLETE,Col:COMPLETE,Output:["c_customer_sk","c_current_addr_sk"] - <-Map 7 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_126] - PartitionCols:_col0 - Select Operator [SEL_125] (rows=40000000 width=188) - Output:["_col0","_col1"] - TableScan [TS_3] (rows=40000000 width=93) - default@customer_address,customer_address,Tbl:COMPLETE,Col:COMPLETE,Output:["ca_address_sk","ca_zip"] + <-Reducer 3 [SIMPLE_EDGE] + SHUFFLE [RS_22] + PartitionCols:_col2 + Merge Join Operator [MERGEJOIN_119] (rows=2098703 width=202) + Conds:RS_19._col1=RS_133._col0(Inner),Output:["_col2","_col3","_col4","_col7","_col8","_col9","_col10"] + <-Map 11 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_133] + PartitionCols:_col0 + Select Operator [SEL_132] (rows=7333 width=206) + Output:["_col0","_col1","_col2","_col3","_col4"] + Filter Operator [FIL_131] (rows=7333 width=210) + predicate:(i_manager_id = 7) + TableScan [TS_6] (rows=462000 width=210) + default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_brand_id","i_brand","i_manufact_id","i_manufact","i_manager_id"] + <-Reducer 2 [SIMPLE_EDGE] + SHUFFLE [RS_19] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_118] (rows=13737330 width=4) + Conds:RS_141._col0=RS_125._col0(Inner),Output:["_col1","_col2","_col3","_col4"] + <-Map 9 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_125] + PartitionCols:_col0 + Select Operator [SEL_124] (rows=50 width=4) + Output:["_col0"] + Filter Operator [FIL_123] (rows=50 width=12) + predicate:((d_moy = 11) and (d_year = 1999)) + 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 1 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_141] + PartitionCols:_col0 + Select Operator [SEL_140] (rows=501694138 width=122) + Output:["_col0","_col1","_col2","_col3","_col4"] + Filter Operator [FIL_139] (rows=501694138 width=122) + predicate:((ss_item_sk BETWEEN DynamicValue(RS_20_item_i_item_sk_min) AND DynamicValue(RS_20_item_i_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_20_item_i_item_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_17_date_dim_d_date_sk_min) AND DynamicValue(RS_17_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_17_date_dim_d_date_sk_bloom_filter))) and ss_customer_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_customer_sk","ss_store_sk","ss_ext_sales_price"] + <-Reducer 10 [BROADCAST_EDGE] vectorized + BROADCAST [RS_130] + Group By Operator [GBY_129] (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_128] + Group By Operator [GBY_127] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_126] (rows=50 width=4) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_124] + <-Reducer 12 [BROADCAST_EDGE] vectorized + BROADCAST [RS_138] + Group By Operator [GBY_137] (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_136] + Group By Operator [GBY_135] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_134] (rows=7333 width=4) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_132] diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/query25.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/query25.q.out index 7325033557..a93c38b3dd 100644 --- a/ql/src/test/results/clientpositive/perf/tez/constraints/query25.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/query25.q.out @@ -109,221 +109,225 @@ POSTHOOK: Output: hdfs://### HDFS PATH ### Plan optimized by CBO. Vertex dependency in root stage -Map 1 <- Reducer 9 (BROADCAST_EDGE) -Map 19 <- Reducer 14 (BROADCAST_EDGE), Reducer 16 (BROADCAST_EDGE), Reducer 17 (BROADCAST_EDGE), Reducer 18 (BROADCAST_EDGE), Reducer 6 (BROADCAST_EDGE), Reducer 7 (BROADCAST_EDGE) -Reducer 10 <- Map 19 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) -Reducer 11 <- Reducer 10 (SIMPLE_EDGE), Reducer 15 (SIMPLE_EDGE) -Reducer 12 <- Map 21 (SIMPLE_EDGE), Reducer 11 (SIMPLE_EDGE) -Reducer 13 <- Map 22 (SIMPLE_EDGE), Reducer 12 (SIMPLE_EDGE) -Reducer 14 <- Map 8 (CUSTOM_SIMPLE_EDGE) -Reducer 15 <- Map 20 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) +Map 1 <- Reducer 11 (BROADCAST_EDGE), Reducer 16 (BROADCAST_EDGE), Reducer 17 (BROADCAST_EDGE) +Map 19 <- Reducer 14 (BROADCAST_EDGE), Reducer 16 (BROADCAST_EDGE), Reducer 17 (BROADCAST_EDGE), Reducer 18 (BROADCAST_EDGE), Reducer 8 (BROADCAST_EDGE), Reducer 9 (BROADCAST_EDGE) +Reducer 11 <- Map 10 (CUSTOM_SIMPLE_EDGE) +Reducer 12 <- Map 10 (SIMPLE_EDGE), Map 19 (SIMPLE_EDGE) +Reducer 13 <- Reducer 12 (SIMPLE_EDGE), Reducer 15 (SIMPLE_EDGE) +Reducer 14 <- Map 10 (CUSTOM_SIMPLE_EDGE) +Reducer 15 <- Map 10 (SIMPLE_EDGE), Map 20 (SIMPLE_EDGE) Reducer 16 <- Reducer 15 (CUSTOM_SIMPLE_EDGE) Reducer 17 <- Reducer 15 (CUSTOM_SIMPLE_EDGE) Reducer 18 <- Reducer 15 (CUSTOM_SIMPLE_EDGE) -Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 10 (SIMPLE_EDGE) Reducer 3 <- Reducer 13 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) -Reducer 4 <- Reducer 3 (SIMPLE_EDGE) -Reducer 5 <- Reducer 4 (SIMPLE_EDGE) -Reducer 6 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) -Reducer 7 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) -Reducer 9 <- Map 8 (CUSTOM_SIMPLE_EDGE) +Reducer 4 <- Map 21 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) +Reducer 5 <- Map 22 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) +Reducer 6 <- Reducer 5 (SIMPLE_EDGE) +Reducer 7 <- Reducer 6 (SIMPLE_EDGE) +Reducer 8 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) +Reducer 9 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) Stage-0 Fetch Operator limit:100 Stage-1 - Reducer 5 vectorized - File Output Operator [FS_250] - Limit [LIM_249] (rows=100 width=808) + Reducer 7 vectorized + File Output Operator [FS_258] + Limit [LIM_257] (rows=100 width=808) Number of rows:100 - Select Operator [SEL_248] (rows=21091882 width=808) + Select Operator [SEL_256] (rows=4248052730 width=808) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"] - <-Reducer 4 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_247] - Group By Operator [GBY_246] (rows=21091882 width=808) + <-Reducer 6 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_255] + Group By Operator [GBY_254] (rows=4248052730 width=808) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3 - <-Reducer 3 [SIMPLE_EDGE] + <-Reducer 5 [SIMPLE_EDGE] SHUFFLE [RS_47] PartitionCols:_col0, _col1, _col2, _col3 - Group By Operator [GBY_46] (rows=21091882 width=808) - 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_91] (rows=4248052730 width=807) - keys:_col6, _col7, _col22, _col23,sort order:++++,top n:100 - Merge Join Operator [MERGEJOIN_203] (rows=4248052730 width=807) - Conds:RS_42._col2, _col1=RS_43._col11, _col12(Inner),Output:["_col3","_col6","_col7","_col13","_col19","_col22","_col23"] - <-Reducer 2 [SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_42] - PartitionCols:_col2, _col1 - Merge Join Operator [MERGEJOIN_197] (rows=54418158 width=119) - Conds:RS_223._col0=RS_210._col0(Inner),Output:["_col1","_col2","_col3"] - <-Map 8 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_210] + Group By Operator [GBY_46] (rows=4248052730 width=808) + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"],aggregations:["sum(_col10)","sum(_col16)","sum(_col3)"],keys:_col22, _col23, _col19, _col20 + Top N Key Operator [TNK_93] (rows=4248052730 width=807) + keys:_col22, _col23, _col19, _col20,sort order:++++,top n:100 + Merge Join Operator [MERGEJOIN_209] (rows=4248052730 width=807) + Conds:RS_42._col6=RS_253._col0(Inner),Output:["_col3","_col10","_col16","_col19","_col20","_col22","_col23"] + <-Map 22 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_253] + PartitionCols:_col0 + Select Operator [SEL_252] (rows=462000 width=288) + Output:["_col0","_col1","_col2"] + TableScan [TS_31] (rows=462000 width=288) + default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_item_id","i_item_desc"] + <-Reducer 4 [SIMPLE_EDGE] + SHUFFLE [RS_42] + PartitionCols:_col6 + Merge Join Operator [MERGEJOIN_208] (rows=4248052730 width=527) + Conds:RS_39._col8=RS_251._col0(Inner),Output:["_col3","_col6","_col10","_col16","_col19","_col20"] + <-Map 21 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_251] PartitionCols:_col0 - Select Operator [SEL_207] (rows=351 width=4) - Output:["_col0"] - Filter Operator [FIL_204] (rows=351 width=12) - predicate:((d_year = 2000) and d_moy BETWEEN 4 AND 10) - TableScan [TS_3] (rows=73049 width=12) - default@date_dim,d3,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year","d_moy"] - <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_223] - PartitionCols:_col0 - Select Operator [SEL_222] (rows=285117831 width=123) - Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_221] (rows=285117831 width=123) - predicate:((cs_sold_date_sk BETWEEN DynamicValue(RS_40_d3_d_date_sk_min) AND DynamicValue(RS_40_d3_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_40_d3_d_date_sk_bloom_filter))) and cs_bill_customer_sk is not null and cs_sold_date_sk is not null) - TableScan [TS_0] (rows=287989836 width=123) - default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["cs_sold_date_sk","cs_bill_customer_sk","cs_item_sk","cs_net_profit"] - <-Reducer 9 [BROADCAST_EDGE] vectorized - BROADCAST [RS_220] - Group By Operator [GBY_219] (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_217] - Group By Operator [GBY_215] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_211] (rows=351 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_207] - <-Reducer 13 [SIMPLE_EDGE] - SHUFFLE [RS_43] - PartitionCols:_col11, _col12 - Select Operator [SEL_38] (rows=21091882 width=620) - Output:["_col1","_col2","_col8","_col11","_col12","_col14","_col17","_col18"] - Merge Join Operator [MERGEJOIN_202] (rows=21091882 width=620) - Conds:RS_35._col3=RS_245._col0(Inner),Output:["_col5","_col8","_col9","_col11","_col14","_col15","_col17","_col18"] - <-Map 22 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_245] - PartitionCols:_col0 - Select Operator [SEL_244] (rows=1704 width=192) - Output:["_col0","_col1","_col2"] - TableScan [TS_24] (rows=1704 width=192) - default@store,store,Tbl:COMPLETE,Col:COMPLETE,Output:["s_store_sk","s_store_id","s_store_name"] - <-Reducer 12 [SIMPLE_EDGE] - SHUFFLE [RS_35] - PartitionCols:_col3 - Merge Join Operator [MERGEJOIN_201] (rows=21091882 width=434) - Conds:RS_32._col1=RS_243._col0(Inner),Output:["_col3","_col5","_col8","_col9","_col11","_col14","_col15"] - <-Map 21 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_243] - PartitionCols:_col0 - Select Operator [SEL_242] (rows=462000 width=288) - Output:["_col0","_col1","_col2"] - TableScan [TS_22] (rows=462000 width=288) - default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_item_id","i_item_desc"] - <-Reducer 11 [SIMPLE_EDGE] - SHUFFLE [RS_32] - PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_200] (rows=21091882 width=154) - Conds:RS_29._col1, _col2, _col4=RS_30._col1, _col2, _col3(Inner),Output:["_col1","_col3","_col5","_col8","_col9","_col11"] - <-Reducer 15 [SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_30] - PartitionCols:_col1, _col2, _col3 - Merge Join Operator [MERGEJOIN_199] (rows=9402909 width=100) - Conds:RS_228._col0=RS_214._col0(Inner),Output:["_col1","_col2","_col3","_col4"] - <-Map 8 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_214] - PartitionCols:_col0 - Select Operator [SEL_209] (rows=351 width=4) - Output:["_col0"] - Filter Operator [FIL_206] (rows=351 width=12) - predicate:((d_year = 2000) and d_moy BETWEEN 4 AND 10) - Please refer to the previous TableScan [TS_3] - <-Map 20 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_228] - PartitionCols:_col0 - Select Operator [SEL_227] (rows=53632139 width=123) - Output:["_col0","_col1","_col2","_col3","_col4"] - Filter Operator [FIL_226] (rows=53632139 width=123) - predicate:(sr_customer_sk is not null and sr_returned_date_sk is not null) - TableScan [TS_12] (rows=57591150 width=123) - default@store_returns,store_returns,Tbl:COMPLETE,Col:COMPLETE,Output:["sr_returned_date_sk","sr_item_sk","sr_customer_sk","sr_ticket_number","sr_net_loss"] - <-Reducer 10 [SIMPLE_EDGE] - SHUFFLE [RS_29] - PartitionCols:_col1, _col2, _col4 - Merge Join Operator [MERGEJOIN_198] (rows=13737330 width=8) - Conds:RS_241._col0=RS_212._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5"] - <-Map 8 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_212] - PartitionCols:_col0 - Select Operator [SEL_208] (rows=50 width=4) - Output:["_col0"] - Filter Operator [FIL_205] (rows=50 width=12) - predicate:((d_moy = 4) and (d_year = 2000)) - Please refer to the previous TableScan [TS_3] - <-Map 19 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_241] - PartitionCols:_col0 - Select Operator [SEL_240] (rows=501694138 width=126) - Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - Filter Operator [FIL_239] (rows=501694138 width=126) - predicate:((ss_customer_sk BETWEEN DynamicValue(RS_30_store_returns_sr_customer_sk_min) AND DynamicValue(RS_30_store_returns_sr_customer_sk_max) and in_bloom_filter(ss_customer_sk, DynamicValue(RS_30_store_returns_sr_customer_sk_bloom_filter))) and (ss_customer_sk BETWEEN DynamicValue(RS_42_catalog_sales_cs_bill_customer_sk_min) AND DynamicValue(RS_42_catalog_sales_cs_bill_customer_sk_max) and in_bloom_filter(ss_customer_sk, DynamicValue(RS_42_catalog_sales_cs_bill_customer_sk_bloom_filter))) and (ss_item_sk BETWEEN DynamicValue(RS_30_store_returns_sr_item_sk_min) AND DynamicValue(RS_30_store_returns_sr_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_30_store_returns_sr_item_sk_bloom_filter))) and (ss_item_sk BETWEEN DynamicValue(RS_42_catalog_sales_cs_item_sk_min) AND DynamicValue(RS_42_catalog_sales_cs_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_42_catalog_sales_cs_item_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_27_d1_d_date_sk_min) AND DynamicValue(RS_27_d1_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_27_d1_d_date_sk_bloom_filter))) and (ss_ticket_number BETWEEN DynamicValue(RS_30_store_returns_sr_ticket_number_min) AND DynamicValue(RS_30_store_returns_sr_ticket_number_max) and in_bloom_filter(ss_ticket_number, DynamicValue(RS_30_store_returns_sr_ticket_number_bloom_filter))) and ss_customer_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null) - TableScan [TS_6] (rows=575995635 width=126) - default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_item_sk","ss_customer_sk","ss_store_sk","ss_ticket_number","ss_net_profit"] - <-Reducer 14 [BROADCAST_EDGE] vectorized - BROADCAST [RS_225] - Group By Operator [GBY_224] (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_218] - Group By Operator [GBY_216] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_213] (rows=50 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_208] - <-Reducer 16 [BROADCAST_EDGE] vectorized - BROADCAST [RS_230] - Group By Operator [GBY_229] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Reducer 15 [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=1000000)"] - Select Operator [SEL_117] (rows=9402909 width=8) - Output:["_col0"] - Please refer to the previous Merge Join Operator [MERGEJOIN_199] - <-Reducer 17 [BROADCAST_EDGE] vectorized - BROADCAST [RS_232] - Group By Operator [GBY_231] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Reducer 15 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_124] - Group By Operator [GBY_123] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_122] (rows=9402909 width=6) - Output:["_col0"] - Please refer to the previous Merge Join Operator [MERGEJOIN_199] - <-Reducer 18 [BROADCAST_EDGE] vectorized - BROADCAST [RS_234] - Group By Operator [GBY_233] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=6124198)"] - <-Reducer 15 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_129] - Group By Operator [GBY_128] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=6124198)"] - Select Operator [SEL_127] (rows=9402909 width=8) - Output:["_col0"] - Please refer to the previous Merge Join Operator [MERGEJOIN_199] - <-Reducer 6 [BROADCAST_EDGE] vectorized - BROADCAST [RS_236] - Group By Operator [GBY_235] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Reducer 2 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_144] - Group By Operator [GBY_143] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_142] (rows=54418158 width=8) - Output:["_col0"] - Please refer to the previous Merge Join Operator [MERGEJOIN_197] - <-Reducer 7 [BROADCAST_EDGE] vectorized - BROADCAST [RS_238] - Group By Operator [GBY_237] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Reducer 2 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_149] - Group By Operator [GBY_148] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_147] (rows=54418158 width=7) + Select Operator [SEL_250] (rows=1704 width=192) + Output:["_col0","_col1","_col2"] + TableScan [TS_29] (rows=1704 width=192) + default@store,store,Tbl:COMPLETE,Col:COMPLETE,Output:["s_store_sk","s_store_id","s_store_name"] + <-Reducer 3 [SIMPLE_EDGE] + SHUFFLE [RS_39] + PartitionCols:_col8 + Merge Join Operator [MERGEJOIN_207] (rows=4248052730 width=343) + Conds:RS_36._col1, _col2=RS_37._col9, _col8(Inner),Output:["_col3","_col6","_col8","_col10","_col16"] + <-Reducer 2 [SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_36] + PartitionCols:_col1, _col2 + Merge Join Operator [MERGEJOIN_203] (rows=54418158 width=119) + Conds:RS_238._col0=RS_216._col0(Inner),Output:["_col1","_col2","_col3"] + <-Map 10 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_216] + PartitionCols:_col0 + Select Operator [SEL_213] (rows=351 width=4) + Output:["_col0"] + Filter Operator [FIL_210] (rows=351 width=12) + predicate:((d_year = 2000) and d_moy BETWEEN 4 AND 10) + TableScan [TS_3] (rows=73049 width=12) + default@date_dim,d3,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year","d_moy"] + <-Map 1 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_238] + PartitionCols:_col0 + Select Operator [SEL_237] (rows=285117831 width=123) + Output:["_col0","_col1","_col2","_col3"] + Filter Operator [FIL_236] (rows=285117831 width=123) + predicate:((cs_bill_customer_sk BETWEEN DynamicValue(RS_26_store_returns_sr_customer_sk_min) AND DynamicValue(RS_26_store_returns_sr_customer_sk_max) and in_bloom_filter(cs_bill_customer_sk, DynamicValue(RS_26_store_returns_sr_customer_sk_bloom_filter))) and (cs_item_sk BETWEEN DynamicValue(RS_26_store_returns_sr_item_sk_min) AND DynamicValue(RS_26_store_returns_sr_item_sk_max) and in_bloom_filter(cs_item_sk, DynamicValue(RS_26_store_returns_sr_item_sk_bloom_filter))) and (cs_sold_date_sk BETWEEN DynamicValue(RS_34_d3_d_date_sk_min) AND DynamicValue(RS_34_d3_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_34_d3_d_date_sk_bloom_filter))) and cs_bill_customer_sk is not null and cs_sold_date_sk is not null) + TableScan [TS_0] (rows=287989836 width=123) + default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["cs_sold_date_sk","cs_bill_customer_sk","cs_item_sk","cs_net_profit"] + <-Reducer 16 [BROADCAST_EDGE] vectorized + BROADCAST [RS_231] + Group By Operator [GBY_230] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Reducer 15 [CUSTOM_SIMPLE_EDGE] + 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=9402909 width=6) + Output:["_col0"] + Merge Join Operator [MERGEJOIN_205] (rows=9402909 width=100) + Conds:RS_229._col0=RS_220._col0(Inner),Output:["_col1","_col2","_col3","_col4"] + <-Map 10 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_220] + PartitionCols:_col0 + Select Operator [SEL_215] (rows=351 width=4) Output:["_col0"] - Please refer to the previous Merge Join Operator [MERGEJOIN_197] + Filter Operator [FIL_212] (rows=351 width=12) + predicate:((d_year = 2000) and d_moy BETWEEN 4 AND 10) + Please refer to the previous TableScan [TS_3] + <-Map 20 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_229] + PartitionCols:_col0 + Select Operator [SEL_228] (rows=53632139 width=123) + Output:["_col0","_col1","_col2","_col3","_col4"] + Filter Operator [FIL_227] (rows=53632139 width=123) + predicate:(sr_customer_sk is not null and sr_returned_date_sk is not null) + TableScan [TS_12] (rows=57591150 width=123) + default@store_returns,store_returns,Tbl:COMPLETE,Col:COMPLETE,Output:["sr_returned_date_sk","sr_item_sk","sr_customer_sk","sr_ticket_number","sr_net_loss"] + <-Reducer 17 [BROADCAST_EDGE] vectorized + BROADCAST [RS_234] + Group By Operator [GBY_233] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Reducer 15 [CUSTOM_SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_121] + Group By Operator [GBY_120] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_119] (rows=9402909 width=8) + Output:["_col0"] + Please refer to the previous Merge Join Operator [MERGEJOIN_205] + <-Reducer 11 [BROADCAST_EDGE] vectorized + BROADCAST [RS_226] + Group By Operator [GBY_225] (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_223] + Group By Operator [GBY_221] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_217] (rows=351 width=4) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_213] + <-Reducer 13 [SIMPLE_EDGE] + SHUFFLE [RS_37] + PartitionCols:_col9, _col8 + Merge Join Operator [MERGEJOIN_206] (rows=21091882 width=154) + Conds:RS_25._col2, _col1, _col4=RS_26._col2, _col1, _col3(Inner),Output:["_col1","_col3","_col5","_col8","_col9","_col11"] + <-Reducer 15 [SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_26] + PartitionCols:_col2, _col1, _col3 + Please refer to the previous Merge Join Operator [MERGEJOIN_205] + <-Reducer 12 [SIMPLE_EDGE] + SHUFFLE [RS_25] + PartitionCols:_col2, _col1, _col4 + Merge Join Operator [MERGEJOIN_204] (rows=13737330 width=8) + Conds:RS_249._col0=RS_218._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5"] + <-Map 10 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_218] + PartitionCols:_col0 + Select Operator [SEL_214] (rows=50 width=4) + Output:["_col0"] + Filter Operator [FIL_211] (rows=50 width=12) + predicate:((d_moy = 4) and (d_year = 2000)) + Please refer to the previous TableScan [TS_3] + <-Map 19 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_249] + PartitionCols:_col0 + Select Operator [SEL_248] (rows=501694138 width=126) + Output:["_col0","_col1","_col2","_col3","_col4","_col5"] + Filter Operator [FIL_247] (rows=501694138 width=126) + predicate:((ss_customer_sk BETWEEN DynamicValue(RS_26_store_returns_sr_customer_sk_min) AND DynamicValue(RS_26_store_returns_sr_customer_sk_max) and in_bloom_filter(ss_customer_sk, DynamicValue(RS_26_store_returns_sr_customer_sk_bloom_filter))) and (ss_customer_sk BETWEEN DynamicValue(RS_36_catalog_sales_cs_bill_customer_sk_min) AND DynamicValue(RS_36_catalog_sales_cs_bill_customer_sk_max) and in_bloom_filter(ss_customer_sk, DynamicValue(RS_36_catalog_sales_cs_bill_customer_sk_bloom_filter))) and (ss_item_sk BETWEEN DynamicValue(RS_26_store_returns_sr_item_sk_min) AND DynamicValue(RS_26_store_returns_sr_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_26_store_returns_sr_item_sk_bloom_filter))) and (ss_item_sk BETWEEN DynamicValue(RS_36_catalog_sales_cs_item_sk_min) AND DynamicValue(RS_36_catalog_sales_cs_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_36_catalog_sales_cs_item_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_23_d1_d_date_sk_min) AND DynamicValue(RS_23_d1_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_23_d1_d_date_sk_bloom_filter))) and (ss_ticket_number BETWEEN DynamicValue(RS_26_store_returns_sr_ticket_number_min) AND DynamicValue(RS_26_store_returns_sr_ticket_number_max) and in_bloom_filter(ss_ticket_number, DynamicValue(RS_26_store_returns_sr_ticket_number_bloom_filter))) and ss_customer_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null) + TableScan [TS_6] (rows=575995635 width=126) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_item_sk","ss_customer_sk","ss_store_sk","ss_ticket_number","ss_net_profit"] + <-Reducer 16 [BROADCAST_EDGE] vectorized + BROADCAST [RS_232] + Please refer to the previous Group By Operator [GBY_230] + <-Reducer 17 [BROADCAST_EDGE] vectorized + BROADCAST [RS_235] + Please refer to the previous Group By Operator [GBY_233] + <-Reducer 14 [BROADCAST_EDGE] vectorized + BROADCAST [RS_240] + Group By Operator [GBY_239] (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_224] + Group By Operator [GBY_222] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_219] (rows=50 width=4) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_214] + <-Reducer 18 [BROADCAST_EDGE] vectorized + BROADCAST [RS_242] + Group By Operator [GBY_241] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=6124198)"] + <-Reducer 15 [CUSTOM_SIMPLE_EDGE] + PARTITION_ONLY_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=6124198)"] + Select Operator [SEL_141] (rows=9402909 width=8) + Output:["_col0"] + Please refer to the previous Merge Join Operator [MERGEJOIN_205] + <-Reducer 8 [BROADCAST_EDGE] vectorized + BROADCAST [RS_244] + Group By Operator [GBY_243] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Reducer 2 [CUSTOM_SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_153] + Group By Operator [GBY_152] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_151] (rows=54418158 width=7) + Output:["_col0"] + Please refer to the previous Merge Join Operator [MERGEJOIN_203] + <-Reducer 9 [BROADCAST_EDGE] vectorized + BROADCAST [RS_246] + Group By Operator [GBY_245] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Reducer 2 [CUSTOM_SIMPLE_EDGE] + 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=54418158 width=8) + Output:["_col0"] + Please refer to the previous Merge Join Operator [MERGEJOIN_203] diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/query29.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/query29.q.out index 715f1cef53..c6e95a09e0 100644 --- a/ql/src/test/results/clientpositive/perf/tez/constraints/query29.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/query29.q.out @@ -107,222 +107,226 @@ POSTHOOK: Output: hdfs://### HDFS PATH ### Plan optimized by CBO. Vertex dependency in root stage -Map 1 <- Reducer 9 (BROADCAST_EDGE) -Map 10 <- Reducer 16 (BROADCAST_EDGE), Reducer 18 (BROADCAST_EDGE), Reducer 19 (BROADCAST_EDGE), Reducer 20 (BROADCAST_EDGE), Reducer 6 (BROADCAST_EDGE), Reducer 7 (BROADCAST_EDGE) -Reducer 11 <- Map 10 (SIMPLE_EDGE), Map 15 (SIMPLE_EDGE) -Reducer 12 <- Reducer 11 (SIMPLE_EDGE), Reducer 17 (SIMPLE_EDGE) -Reducer 13 <- Map 22 (SIMPLE_EDGE), Reducer 12 (SIMPLE_EDGE) -Reducer 14 <- Map 23 (SIMPLE_EDGE), Reducer 13 (SIMPLE_EDGE) +Map 1 <- Reducer 11 (BROADCAST_EDGE), Reducer 18 (BROADCAST_EDGE), Reducer 19 (BROADCAST_EDGE) +Map 12 <- Reducer 16 (BROADCAST_EDGE), Reducer 18 (BROADCAST_EDGE), Reducer 19 (BROADCAST_EDGE), Reducer 20 (BROADCAST_EDGE), Reducer 8 (BROADCAST_EDGE), Reducer 9 (BROADCAST_EDGE) +Reducer 11 <- Map 10 (CUSTOM_SIMPLE_EDGE) +Reducer 13 <- Map 12 (SIMPLE_EDGE), Map 15 (SIMPLE_EDGE) +Reducer 14 <- Reducer 13 (SIMPLE_EDGE), Reducer 17 (SIMPLE_EDGE) Reducer 16 <- Map 15 (CUSTOM_SIMPLE_EDGE) Reducer 17 <- Map 15 (SIMPLE_EDGE), Map 21 (SIMPLE_EDGE) Reducer 18 <- Reducer 17 (CUSTOM_SIMPLE_EDGE) Reducer 19 <- Reducer 17 (CUSTOM_SIMPLE_EDGE) -Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 10 (SIMPLE_EDGE) Reducer 20 <- Reducer 17 (CUSTOM_SIMPLE_EDGE) Reducer 3 <- Reducer 14 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) -Reducer 4 <- Reducer 3 (SIMPLE_EDGE) -Reducer 5 <- Reducer 4 (SIMPLE_EDGE) -Reducer 6 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) -Reducer 7 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) -Reducer 9 <- Map 8 (CUSTOM_SIMPLE_EDGE) +Reducer 4 <- Map 22 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) +Reducer 5 <- Map 23 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) +Reducer 6 <- Reducer 5 (SIMPLE_EDGE) +Reducer 7 <- Reducer 6 (SIMPLE_EDGE) +Reducer 8 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) +Reducer 9 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) Stage-0 Fetch Operator limit:100 Stage-1 - Reducer 5 vectorized - File Output Operator [FS_250] - Limit [LIM_249] (rows=100 width=496) + Reducer 7 vectorized + File Output Operator [FS_258] + Limit [LIM_257] (rows=100 width=496) Number of rows:100 - Select Operator [SEL_248] (rows=21091879 width=496) + Select Operator [SEL_256] (rows=4156223234 width=496) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"] - <-Reducer 4 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_247] - Group By Operator [GBY_246] (rows=21091879 width=496) + <-Reducer 6 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_255] + Group By Operator [GBY_254] (rows=4156223234 width=496) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3 - <-Reducer 3 [SIMPLE_EDGE] + <-Reducer 5 [SIMPLE_EDGE] SHUFFLE [RS_47] PartitionCols:_col0, _col1, _col2, _col3 - Group By Operator [GBY_46] (rows=21091879 width=496) - 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_91] (rows=4156223234 width=483) - keys:_col6, _col7, _col22, _col23,sort order:++++,top n:100 - Merge Join Operator [MERGEJOIN_203] (rows=4156223234 width=483) - Conds:RS_42._col2, _col1=RS_43._col11, _col12(Inner),Output:["_col3","_col6","_col7","_col13","_col19","_col22","_col23"] - <-Reducer 2 [SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_42] - PartitionCols:_col2, _col1 - Merge Join Operator [MERGEJOIN_197] (rows=7638375 width=10) - Conds:RS_214._col0=RS_206._col0(Inner),Output:["_col1","_col2","_col3"] - <-Map 8 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_206] + Group By Operator [GBY_46] (rows=4156223234 width=496) + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"],aggregations:["sum(_col10)","sum(_col16)","sum(_col3)"],keys:_col22, _col23, _col19, _col20 + Top N Key Operator [TNK_93] (rows=4156223234 width=483) + keys:_col22, _col23, _col19, _col20,sort order:++++,top n:100 + Merge Join Operator [MERGEJOIN_209] (rows=4156223234 width=483) + Conds:RS_42._col6=RS_253._col0(Inner),Output:["_col3","_col10","_col16","_col19","_col20","_col22","_col23"] + <-Map 23 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_253] + PartitionCols:_col0 + Select Operator [SEL_252] (rows=462000 width=288) + Output:["_col0","_col1","_col2"] + TableScan [TS_31] (rows=462000 width=288) + default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_item_id","i_item_desc"] + <-Reducer 4 [SIMPLE_EDGE] + SHUFFLE [RS_42] + PartitionCols:_col6 + Merge Join Operator [MERGEJOIN_208] (rows=4156223234 width=203) + Conds:RS_39._col8=RS_251._col0(Inner),Output:["_col3","_col6","_col10","_col16","_col19","_col20"] + <-Map 22 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_251] PartitionCols:_col0 - Select Operator [SEL_205] (rows=1957 width=4) - Output:["_col0"] - Filter Operator [FIL_204] (rows=1957 width=8) - predicate:(d_year) IN (1999, 2000, 2001) - TableScan [TS_3] (rows=73049 width=8) - default@date_dim,d3,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year"] - <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_214] - PartitionCols:_col0 - Select Operator [SEL_213] (rows=285117831 width=15) - Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_212] (rows=285117831 width=15) - predicate:((cs_sold_date_sk BETWEEN DynamicValue(RS_40_d3_d_date_sk_min) AND DynamicValue(RS_40_d3_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_40_d3_d_date_sk_bloom_filter))) and cs_bill_customer_sk is not null and cs_sold_date_sk is not null) - TableScan [TS_0] (rows=287989836 width=15) - default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["cs_sold_date_sk","cs_bill_customer_sk","cs_item_sk","cs_quantity"] - <-Reducer 9 [BROADCAST_EDGE] vectorized - BROADCAST [RS_211] - Group By Operator [GBY_210] (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_209] - Group By Operator [GBY_208] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_207] (rows=1957 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_205] - <-Reducer 14 [SIMPLE_EDGE] - SHUFFLE [RS_43] - PartitionCols:_col11, _col12 - Select Operator [SEL_38] (rows=21091879 width=484) - Output:["_col1","_col2","_col8","_col11","_col12","_col14","_col17","_col18"] - Merge Join Operator [MERGEJOIN_202] (rows=21091879 width=484) - Conds:RS_35._col3=RS_245._col0(Inner),Output:["_col5","_col8","_col9","_col11","_col14","_col15","_col17","_col18"] - <-Map 23 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_245] - PartitionCols:_col0 - Select Operator [SEL_244] (rows=1704 width=192) - Output:["_col0","_col1","_col2"] - TableScan [TS_24] (rows=1704 width=192) - default@store,store,Tbl:COMPLETE,Col:COMPLETE,Output:["s_store_sk","s_store_id","s_store_name"] - <-Reducer 13 [SIMPLE_EDGE] - SHUFFLE [RS_35] - PartitionCols:_col3 - Merge Join Operator [MERGEJOIN_201] (rows=21091879 width=298) - Conds:RS_32._col1=RS_243._col0(Inner),Output:["_col3","_col5","_col8","_col9","_col11","_col14","_col15"] - <-Map 22 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_243] - PartitionCols:_col0 - Select Operator [SEL_242] (rows=462000 width=288) - Output:["_col0","_col1","_col2"] - TableScan [TS_22] (rows=462000 width=288) - default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_item_id","i_item_desc"] - <-Reducer 12 [SIMPLE_EDGE] - SHUFFLE [RS_32] - PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_200] (rows=21091879 width=18) - Conds:RS_29._col1, _col2, _col4=RS_30._col1, _col2, _col3(Inner),Output:["_col1","_col3","_col5","_col8","_col9","_col11"] - <-Reducer 17 [SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_30] - PartitionCols:_col1, _col2, _col3 - Merge Join Operator [MERGEJOIN_199] (rows=5384572 width=13) - Conds:RS_228._col0=RS_221._col0(Inner),Output:["_col1","_col2","_col3","_col4"] - <-Map 15 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_221] - PartitionCols:_col0 - Select Operator [SEL_218] (rows=201 width=4) - Output:["_col0"] - Filter Operator [FIL_216] (rows=201 width=12) - predicate:((d_year = 1999) and d_moy BETWEEN 4 AND 7) - TableScan [TS_9] (rows=73049 width=12) - default@date_dim,d1,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year","d_moy"] - <-Map 21 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_228] - PartitionCols:_col0 - Select Operator [SEL_227] (rows=53632139 width=19) - Output:["_col0","_col1","_col2","_col3","_col4"] - Filter Operator [FIL_226] (rows=53632139 width=19) - predicate:(sr_customer_sk is not null and sr_returned_date_sk is not null) - TableScan [TS_12] (rows=57591150 width=19) - default@store_returns,store_returns,Tbl:COMPLETE,Col:COMPLETE,Output:["sr_returned_date_sk","sr_item_sk","sr_customer_sk","sr_ticket_number","sr_return_quantity"] - <-Reducer 11 [SIMPLE_EDGE] - SHUFFLE [RS_29] - PartitionCols:_col1, _col2, _col4 - Merge Join Operator [MERGEJOIN_198] (rows=13737330 width=8) - Conds:RS_241._col0=RS_219._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5"] - <-Map 15 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_219] - PartitionCols:_col0 - Select Operator [SEL_217] (rows=50 width=4) - Output:["_col0"] - Filter Operator [FIL_215] (rows=50 width=12) - predicate:((d_moy = 4) and (d_year = 1999)) - Please refer to the previous TableScan [TS_9] - <-Map 10 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_241] - PartitionCols:_col0 - Select Operator [SEL_240] (rows=501694138 width=23) - Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - Filter Operator [FIL_239] (rows=501694138 width=23) - predicate:((ss_customer_sk BETWEEN DynamicValue(RS_30_store_returns_sr_customer_sk_min) AND DynamicValue(RS_30_store_returns_sr_customer_sk_max) and in_bloom_filter(ss_customer_sk, DynamicValue(RS_30_store_returns_sr_customer_sk_bloom_filter))) and (ss_customer_sk BETWEEN DynamicValue(RS_42_catalog_sales_cs_bill_customer_sk_min) AND DynamicValue(RS_42_catalog_sales_cs_bill_customer_sk_max) and in_bloom_filter(ss_customer_sk, DynamicValue(RS_42_catalog_sales_cs_bill_customer_sk_bloom_filter))) and (ss_item_sk BETWEEN DynamicValue(RS_30_store_returns_sr_item_sk_min) AND DynamicValue(RS_30_store_returns_sr_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_30_store_returns_sr_item_sk_bloom_filter))) and (ss_item_sk BETWEEN DynamicValue(RS_42_catalog_sales_cs_item_sk_min) AND DynamicValue(RS_42_catalog_sales_cs_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_42_catalog_sales_cs_item_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_27_d1_d_date_sk_min) AND DynamicValue(RS_27_d1_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_27_d1_d_date_sk_bloom_filter))) and (ss_ticket_number BETWEEN DynamicValue(RS_30_store_returns_sr_ticket_number_min) AND DynamicValue(RS_30_store_returns_sr_ticket_number_max) and in_bloom_filter(ss_ticket_number, DynamicValue(RS_30_store_returns_sr_ticket_number_bloom_filter))) and ss_customer_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null) - TableScan [TS_6] (rows=575995635 width=23) - default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_item_sk","ss_customer_sk","ss_store_sk","ss_ticket_number","ss_quantity"] - <-Reducer 16 [BROADCAST_EDGE] vectorized - BROADCAST [RS_225] - Group By Operator [GBY_224] (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_223] - Group By Operator [GBY_222] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_220] (rows=50 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_217] - <-Reducer 18 [BROADCAST_EDGE] vectorized - BROADCAST [RS_230] - Group By Operator [GBY_229] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Reducer 17 [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=1000000)"] - Select Operator [SEL_117] (rows=5384572 width=8) - Output:["_col0"] - Please refer to the previous Merge Join Operator [MERGEJOIN_199] - <-Reducer 19 [BROADCAST_EDGE] vectorized - BROADCAST [RS_232] - Group By Operator [GBY_231] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Reducer 17 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_124] - Group By Operator [GBY_123] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_122] (rows=5384572 width=5) - Output:["_col0"] - Please refer to the previous Merge Join Operator [MERGEJOIN_199] - <-Reducer 20 [BROADCAST_EDGE] vectorized - BROADCAST [RS_234] - Group By Operator [GBY_233] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=3507020)"] - <-Reducer 17 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_129] - Group By Operator [GBY_128] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=3507020)"] - Select Operator [SEL_127] (rows=5384572 width=8) - Output:["_col0"] - Please refer to the previous Merge Join Operator [MERGEJOIN_199] - <-Reducer 6 [BROADCAST_EDGE] vectorized - BROADCAST [RS_236] - Group By Operator [GBY_235] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Reducer 2 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_144] - Group By Operator [GBY_143] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_142] (rows=7638375 width=8) - Output:["_col0"] - Please refer to the previous Merge Join Operator [MERGEJOIN_197] - <-Reducer 7 [BROADCAST_EDGE] vectorized - BROADCAST [RS_238] - Group By Operator [GBY_237] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Reducer 2 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_149] - Group By Operator [GBY_148] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_147] (rows=7638375 width=6) + Select Operator [SEL_250] (rows=1704 width=192) + Output:["_col0","_col1","_col2"] + TableScan [TS_29] (rows=1704 width=192) + default@store,store,Tbl:COMPLETE,Col:COMPLETE,Output:["s_store_sk","s_store_id","s_store_name"] + <-Reducer 3 [SIMPLE_EDGE] + SHUFFLE [RS_39] + PartitionCols:_col8 + Merge Join Operator [MERGEJOIN_207] (rows=4156223234 width=19) + Conds:RS_36._col1, _col2=RS_37._col9, _col8(Inner),Output:["_col3","_col6","_col8","_col10","_col16"] + <-Reducer 2 [SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_36] + PartitionCols:_col1, _col2 + Merge Join Operator [MERGEJOIN_203] (rows=7638375 width=10) + Conds:RS_238._col0=RS_212._col0(Inner),Output:["_col1","_col2","_col3"] + <-Map 10 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_212] + PartitionCols:_col0 + Select Operator [SEL_211] (rows=1957 width=4) + Output:["_col0"] + Filter Operator [FIL_210] (rows=1957 width=8) + predicate:(d_year) IN (1999, 2000, 2001) + TableScan [TS_3] (rows=73049 width=8) + default@date_dim,d3,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year"] + <-Map 1 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_238] + PartitionCols:_col0 + Select Operator [SEL_237] (rows=285117831 width=15) + Output:["_col0","_col1","_col2","_col3"] + Filter Operator [FIL_236] (rows=285117831 width=15) + predicate:((cs_bill_customer_sk BETWEEN DynamicValue(RS_26_store_returns_sr_customer_sk_min) AND DynamicValue(RS_26_store_returns_sr_customer_sk_max) and in_bloom_filter(cs_bill_customer_sk, DynamicValue(RS_26_store_returns_sr_customer_sk_bloom_filter))) and (cs_item_sk BETWEEN DynamicValue(RS_26_store_returns_sr_item_sk_min) AND DynamicValue(RS_26_store_returns_sr_item_sk_max) and in_bloom_filter(cs_item_sk, DynamicValue(RS_26_store_returns_sr_item_sk_bloom_filter))) and (cs_sold_date_sk BETWEEN DynamicValue(RS_34_d3_d_date_sk_min) AND DynamicValue(RS_34_d3_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_34_d3_d_date_sk_bloom_filter))) and cs_bill_customer_sk is not null and cs_sold_date_sk is not null) + TableScan [TS_0] (rows=287989836 width=15) + default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["cs_sold_date_sk","cs_bill_customer_sk","cs_item_sk","cs_quantity"] + <-Reducer 18 [BROADCAST_EDGE] vectorized + BROADCAST [RS_231] + Group By Operator [GBY_230] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Reducer 17 [CUSTOM_SIMPLE_EDGE] + 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=5384572 width=5) + Output:["_col0"] + Merge Join Operator [MERGEJOIN_205] (rows=5384572 width=13) + Conds:RS_229._col0=RS_224._col0(Inner),Output:["_col1","_col2","_col3","_col4"] + <-Map 15 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_224] + PartitionCols:_col0 + Select Operator [SEL_221] (rows=201 width=4) Output:["_col0"] - Please refer to the previous Merge Join Operator [MERGEJOIN_197] + Filter Operator [FIL_219] (rows=201 width=12) + predicate:((d_year = 1999) and d_moy BETWEEN 4 AND 7) + TableScan [TS_9] (rows=73049 width=12) + default@date_dim,d1,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year","d_moy"] + <-Map 21 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_229] + PartitionCols:_col0 + Select Operator [SEL_228] (rows=53632139 width=19) + Output:["_col0","_col1","_col2","_col3","_col4"] + Filter Operator [FIL_227] (rows=53632139 width=19) + predicate:(sr_customer_sk is not null and sr_returned_date_sk is not null) + TableScan [TS_12] (rows=57591150 width=19) + default@store_returns,store_returns,Tbl:COMPLETE,Col:COMPLETE,Output:["sr_returned_date_sk","sr_item_sk","sr_customer_sk","sr_ticket_number","sr_return_quantity"] + <-Reducer 19 [BROADCAST_EDGE] vectorized + BROADCAST [RS_234] + Group By Operator [GBY_233] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Reducer 17 [CUSTOM_SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_121] + Group By Operator [GBY_120] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_119] (rows=5384572 width=8) + Output:["_col0"] + Please refer to the previous Merge Join Operator [MERGEJOIN_205] + <-Reducer 11 [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 10 [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=1957 width=4) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_211] + <-Reducer 14 [SIMPLE_EDGE] + SHUFFLE [RS_37] + PartitionCols:_col9, _col8 + Merge Join Operator [MERGEJOIN_206] (rows=21091879 width=18) + Conds:RS_25._col2, _col1, _col4=RS_26._col2, _col1, _col3(Inner),Output:["_col1","_col3","_col5","_col8","_col9","_col11"] + <-Reducer 17 [SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_26] + PartitionCols:_col2, _col1, _col3 + Please refer to the previous Merge Join Operator [MERGEJOIN_205] + <-Reducer 13 [SIMPLE_EDGE] + SHUFFLE [RS_25] + PartitionCols:_col2, _col1, _col4 + Merge Join Operator [MERGEJOIN_204] (rows=13737330 width=8) + Conds:RS_249._col0=RS_222._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5"] + <-Map 15 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_222] + PartitionCols:_col0 + Select Operator [SEL_220] (rows=50 width=4) + Output:["_col0"] + Filter Operator [FIL_218] (rows=50 width=12) + predicate:((d_moy = 4) and (d_year = 1999)) + Please refer to the previous TableScan [TS_9] + <-Map 12 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_249] + PartitionCols:_col0 + Select Operator [SEL_248] (rows=501694138 width=23) + Output:["_col0","_col1","_col2","_col3","_col4","_col5"] + Filter Operator [FIL_247] (rows=501694138 width=23) + predicate:((ss_customer_sk BETWEEN DynamicValue(RS_26_store_returns_sr_customer_sk_min) AND DynamicValue(RS_26_store_returns_sr_customer_sk_max) and in_bloom_filter(ss_customer_sk, DynamicValue(RS_26_store_returns_sr_customer_sk_bloom_filter))) and (ss_customer_sk BETWEEN DynamicValue(RS_36_catalog_sales_cs_bill_customer_sk_min) AND DynamicValue(RS_36_catalog_sales_cs_bill_customer_sk_max) and in_bloom_filter(ss_customer_sk, DynamicValue(RS_36_catalog_sales_cs_bill_customer_sk_bloom_filter))) and (ss_item_sk BETWEEN DynamicValue(RS_26_store_returns_sr_item_sk_min) AND DynamicValue(RS_26_store_returns_sr_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_26_store_returns_sr_item_sk_bloom_filter))) and (ss_item_sk BETWEEN DynamicValue(RS_36_catalog_sales_cs_item_sk_min) AND DynamicValue(RS_36_catalog_sales_cs_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_36_catalog_sales_cs_item_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_23_d1_d_date_sk_min) AND DynamicValue(RS_23_d1_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_23_d1_d_date_sk_bloom_filter))) and (ss_ticket_number BETWEEN DynamicValue(RS_26_store_returns_sr_ticket_number_min) AND DynamicValue(RS_26_store_returns_sr_ticket_number_max) and in_bloom_filter(ss_ticket_number, DynamicValue(RS_26_store_returns_sr_ticket_number_bloom_filter))) and ss_customer_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null) + TableScan [TS_6] (rows=575995635 width=23) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_item_sk","ss_customer_sk","ss_store_sk","ss_ticket_number","ss_quantity"] + <-Reducer 18 [BROADCAST_EDGE] vectorized + BROADCAST [RS_232] + Please refer to the previous Group By Operator [GBY_230] + <-Reducer 19 [BROADCAST_EDGE] vectorized + BROADCAST [RS_235] + Please refer to the previous Group By Operator [GBY_233] + <-Reducer 16 [BROADCAST_EDGE] vectorized + BROADCAST [RS_240] + Group By Operator [GBY_239] (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_226] + Group By Operator [GBY_225] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_223] (rows=50 width=4) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_220] + <-Reducer 20 [BROADCAST_EDGE] vectorized + BROADCAST [RS_242] + Group By Operator [GBY_241] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=3507020)"] + <-Reducer 17 [CUSTOM_SIMPLE_EDGE] + PARTITION_ONLY_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=3507020)"] + Select Operator [SEL_141] (rows=5384572 width=8) + Output:["_col0"] + Please refer to the previous Merge Join Operator [MERGEJOIN_205] + <-Reducer 8 [BROADCAST_EDGE] vectorized + BROADCAST [RS_244] + Group By Operator [GBY_243] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Reducer 2 [CUSTOM_SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_153] + Group By Operator [GBY_152] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_151] (rows=7638375 width=6) + Output:["_col0"] + Please refer to the previous Merge Join Operator [MERGEJOIN_203] + <-Reducer 9 [BROADCAST_EDGE] vectorized + BROADCAST [RS_246] + Group By Operator [GBY_245] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Reducer 2 [CUSTOM_SIMPLE_EDGE] + 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=7638375 width=8) + Output:["_col0"] + Please refer to the previous Merge Join Operator [MERGEJOIN_203] diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/query35.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/query35.q.out index 2501199e89..f454be9dd1 100644 --- a/ql/src/test/results/clientpositive/perf/tez/constraints/query35.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/query35.q.out @@ -155,207 +155,209 @@ Stage-0 limit:-1 Stage-1 Reducer 8 vectorized - File Output Operator [FS_232] - Limit [LIM_231] (rows=1 width=352) + File Output Operator [FS_233] + Limit [LIM_232] (rows=1 width=352) Number of rows:100 - Select Operator [SEL_230] (rows=1 width=352) + Select Operator [SEL_231] (rows=1 width=352) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16"] <-Reducer 7 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_229] - Select Operator [SEL_228] (rows=1 width=352) + SHUFFLE [RS_230] + Select Operator [SEL_229] (rows=1 width=352) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col9","_col10","_col11","_col12","_col14","_col15","_col16","_col17"] - Group By Operator [GBY_227] (rows=1 width=336) + Group By Operator [GBY_228] (rows=1 width=336) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15"],aggregations:["count(VALUE._col0)","sum(VALUE._col1)","count(VALUE._col2)","max(VALUE._col3)","sum(VALUE._col4)","count(VALUE._col5)","max(VALUE._col6)","sum(VALUE._col7)","count(VALUE._col8)","max(VALUE._col9)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4, KEY._col5 <-Reducer 6 [SIMPLE_EDGE] - SHUFFLE [RS_65] + SHUFFLE [RS_66] PartitionCols:_col0, _col1, _col2, _col3, _col4, _col5 - Group By Operator [GBY_64] (rows=1 width=336) + Group By Operator [GBY_65] (rows=1 width=336) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15"],aggregations:["count()","sum(_col8)","count(_col8)","max(_col8)","sum(_col9)","count(_col9)","max(_col9)","sum(_col10)","count(_col10)","max(_col10)"],keys:_col4, _col6, _col7, _col8, _col9, _col10 - Top N Key Operator [TNK_102] (rows=67 width=276) + Top N Key Operator [TNK_103] (rows=67 width=276) keys:_col4, _col6, _col7, _col8, _col9, _col10,sort order:++++++,top n:100 - Select Operator [SEL_63] (rows=67 width=276) + Select Operator [SEL_64] (rows=67 width=276) Output:["_col4","_col6","_col7","_col8","_col9","_col10"] - Filter Operator [FIL_62] (rows=67 width=276) + Filter Operator [FIL_63] (rows=67 width=276) predicate:(_col12 is not null or _col14 is not null) - Merge Join Operator [MERGEJOIN_180] (rows=67 width=276) - Conds:RS_59._col0=RS_226._col0(Left Outer),Output:["_col4","_col6","_col7","_col8","_col9","_col10","_col12","_col14"] + Merge Join Operator [MERGEJOIN_181] (rows=67 width=276) + Conds:RS_60._col0=RS_227._col0(Left Outer),Output:["_col4","_col6","_col7","_col8","_col9","_col10","_col12","_col14"] <-Reducer 5 [ONE_TO_ONE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_59] + PARTITION_ONLY_SHUFFLE [RS_60] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_179] (rows=68 width=276) - Conds:RS_56._col0=RS_216._col0(Left Outer),Output:["_col0","_col4","_col6","_col7","_col8","_col9","_col10","_col12"] + Merge Join Operator [MERGEJOIN_180] (rows=68 width=276) + Conds:RS_57._col0=RS_217._col0(Left Outer),Output:["_col0","_col4","_col6","_col7","_col8","_col9","_col10","_col12"] <-Reducer 4 [ONE_TO_ONE_EDGE] - FORWARD [RS_56] + FORWARD [RS_57] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_178] (rows=162346 width=272) - Conds:RS_53._col0=RS_54._col0(Left Semi),Output:["_col0","_col4","_col6","_col7","_col8","_col9","_col10"] + Merge Join Operator [MERGEJOIN_179] (rows=162346 width=272) + Conds:RS_54._col0=RS_55._col0(Left Semi),Output:["_col0","_col4","_col6","_col7","_col8","_col9","_col10"] <-Reducer 14 [SIMPLE_EDGE] - SHUFFLE [RS_54] + SHUFFLE [RS_55] PartitionCols:_col0 - Group By Operator [GBY_52] (rows=168231 width=2) + Group By Operator [GBY_53] (rows=168231 width=2) Output:["_col0"],keys:_col0 - Select Operator [SEL_16] (rows=62428523 width=2) + Select Operator [SEL_23] (rows=62428523 width=2) Output:["_col0"] - Merge Join Operator [MERGEJOIN_175] (rows=62428523 width=2) - Conds:RS_206._col0=RS_190._col0(Inner),Output:["_col1"] + Merge Join Operator [MERGEJOIN_176] (rows=62428523 width=2) + Conds:RS_207._col0=RS_191._col0(Inner),Output:["_col1"] <-Map 15 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_190] + PARTITION_ONLY_SHUFFLE [RS_191] PartitionCols:_col0 - Select Operator [SEL_189] (rows=217 width=4) + Select Operator [SEL_190] (rows=217 width=4) Output:["_col0"] - Filter Operator [FIL_188] (rows=217 width=12) + Filter Operator [FIL_189] (rows=217 width=12) predicate:((d_qoy < 4) and (d_year = 1999)) - TableScan [TS_10] (rows=73049 width=12) + TableScan [TS_17] (rows=73049 width=12) default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year","d_qoy"] <-Map 13 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_206] + SHUFFLE [RS_207] PartitionCols:_col0 - Select Operator [SEL_205] (rows=525327388 width=7) + Select Operator [SEL_206] (rows=525327388 width=7) Output:["_col0","_col1"] - Filter Operator [FIL_204] (rows=525327388 width=7) - predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_14_date_dim_d_date_sk_min) AND DynamicValue(RS_14_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_14_date_dim_d_date_sk_bloom_filter))) and ss_customer_sk is not null and ss_sold_date_sk is not null) - TableScan [TS_7] (rows=575995635 width=7) + Filter Operator [FIL_205] (rows=525327388 width=7) + predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_21_date_dim_d_date_sk_min) AND DynamicValue(RS_21_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_21_date_dim_d_date_sk_bloom_filter))) and ss_customer_sk is not null and ss_sold_date_sk is not null) + TableScan [TS_14] (rows=575995635 width=7) default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_customer_sk"] <-Reducer 16 [BROADCAST_EDGE] vectorized - BROADCAST [RS_203] - Group By Operator [GBY_202] (rows=1 width=12) + BROADCAST [RS_204] + Group By Operator [GBY_203] (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 - PARTITION_ONLY_SHUFFLE [RS_199] - Group By Operator [GBY_196] (rows=1 width=12) + PARTITION_ONLY_SHUFFLE [RS_200] + Group By Operator [GBY_197] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_191] (rows=217 width=4) + Select Operator [SEL_192] (rows=217 width=4) Output:["_col0"] - Please refer to the previous Select Operator [SEL_189] + Please refer to the previous Select Operator [SEL_190] <-Reducer 3 [SIMPLE_EDGE] - SHUFFLE [RS_53] + SHUFFLE [RS_54] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_174] (rows=78293105 width=272) - Conds:RS_48._col1=RS_187._col0(Inner),Output:["_col0","_col4","_col6","_col7","_col8","_col9","_col10"] - <-Map 12 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_187] - PartitionCols:_col0 - Select Operator [SEL_186] (rows=1861800 width=186) - Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - TableScan [TS_5] (rows=1861800 width=186) - default@customer_demographics,customer_demographics,Tbl:COMPLETE,Col:COMPLETE,Output:["cd_demo_sk","cd_gender","cd_marital_status","cd_dep_count","cd_dep_employed_count","cd_dep_college_count"] - <-Reducer 2 [SIMPLE_EDGE] - SHUFFLE [RS_48] - PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_173] (rows=77201384 width=93) - Conds:RS_183._col2=RS_185._col0(Inner),Output:["_col0","_col1","_col4"] - <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_183] - PartitionCols:_col2 - Select Operator [SEL_182] (rows=77201384 width=11) - Output:["_col0","_col1","_col2"] - Filter Operator [FIL_181] (rows=77201384 width=11) - predicate:(c_current_addr_sk is not null and c_current_cdemo_sk is not null) - TableScan [TS_0] (rows=80000000 width=11) - default@customer,c,Tbl:COMPLETE,Col:COMPLETE,Output:["c_customer_sk","c_current_cdemo_sk","c_current_addr_sk"] - <-Map 11 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_185] - PartitionCols:_col0 - Select Operator [SEL_184] (rows=40000000 width=90) - Output:["_col0","_col1"] - TableScan [TS_3] (rows=40000000 width=90) - default@customer_address,ca,Tbl:COMPLETE,Col:COMPLETE,Output:["ca_address_sk","ca_state"] + Select Operator [SEL_13] (rows=78293105 width=272) + Output:["_col0","_col4","_col6","_col7","_col8","_col9","_col10"] + Merge Join Operator [MERGEJOIN_175] (rows=78293105 width=272) + Conds:RS_10._col2=RS_188._col0(Inner),Output:["_col0","_col4","_col5","_col6","_col7","_col8","_col10"] + <-Map 12 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_188] + PartitionCols:_col0 + Select Operator [SEL_187] (rows=40000000 width=90) + Output:["_col0","_col1"] + TableScan [TS_5] (rows=40000000 width=90) + default@customer_address,ca,Tbl:COMPLETE,Col:COMPLETE,Output:["ca_address_sk","ca_state"] + <-Reducer 2 [SIMPLE_EDGE] + SHUFFLE [RS_10] + PartitionCols:_col2 + Merge Join Operator [MERGEJOIN_174] (rows=78293105 width=190) + Conds:RS_184._col1=RS_186._col0(Inner),Output:["_col0","_col2","_col4","_col5","_col6","_col7","_col8"] + <-Map 1 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_184] + PartitionCols:_col1 + Select Operator [SEL_183] (rows=77201384 width=11) + Output:["_col0","_col1","_col2"] + Filter Operator [FIL_182] (rows=77201384 width=11) + predicate:(c_current_addr_sk is not null and c_current_cdemo_sk is not null) + TableScan [TS_0] (rows=80000000 width=11) + default@customer,c,Tbl:COMPLETE,Col:COMPLETE,Output:["c_customer_sk","c_current_cdemo_sk","c_current_addr_sk"] + <-Map 11 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_186] + PartitionCols:_col0 + Select Operator [SEL_185] (rows=1861800 width=186) + Output:["_col0","_col1","_col2","_col3","_col4","_col5"] + TableScan [TS_3] (rows=1861800 width=186) + default@customer_demographics,customer_demographics,Tbl:COMPLETE,Col:COMPLETE,Output:["cd_demo_sk","cd_gender","cd_marital_status","cd_dep_count","cd_dep_employed_count","cd_dep_college_count"] <-Reducer 18 [ONE_TO_ONE_EDGE] vectorized - FORWARD [RS_216] + FORWARD [RS_217] PartitionCols:_col0 - Select Operator [SEL_215] (rows=168231 width=7) + Select Operator [SEL_216] (rows=168231 width=7) Output:["_col0","_col1"] - Group By Operator [GBY_214] (rows=168231 width=3) + Group By Operator [GBY_215] (rows=168231 width=3) Output:["_col0"],keys:KEY._col0 <-Reducer 17 [SIMPLE_EDGE] - SHUFFLE [RS_28] + SHUFFLE [RS_35] PartitionCols:_col0 - Group By Operator [GBY_27] (rows=168231 width=3) + Group By Operator [GBY_34] (rows=168231 width=3) Output:["_col0"],keys:_col1 - Merge Join Operator [MERGEJOIN_176] (rows=17104380 width=3) - Conds:RS_213._col0=RS_192._col0(Inner),Output:["_col1"] + Merge Join Operator [MERGEJOIN_177] (rows=17104380 width=3) + Conds:RS_214._col0=RS_193._col0(Inner),Output:["_col1"] <-Map 15 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_192] + PARTITION_ONLY_SHUFFLE [RS_193] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_189] + Please refer to the previous Select Operator [SEL_190] <-Map 23 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_213] + SHUFFLE [RS_214] PartitionCols:_col0 - Select Operator [SEL_212] (rows=143930993 width=7) + Select Operator [SEL_213] (rows=143930993 width=7) Output:["_col0","_col1"] - Filter Operator [FIL_211] (rows=143930993 width=7) - predicate:((ws_bill_customer_sk BETWEEN DynamicValue(RS_56_c_c_customer_sk_min) AND DynamicValue(RS_56_c_c_customer_sk_max) and in_bloom_filter(ws_bill_customer_sk, DynamicValue(RS_56_c_c_customer_sk_bloom_filter))) and (ws_sold_date_sk BETWEEN DynamicValue(RS_24_date_dim_d_date_sk_min) AND DynamicValue(RS_24_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_24_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_17] (rows=144002668 width=7) + Filter Operator [FIL_212] (rows=143930993 width=7) + predicate:((ws_bill_customer_sk BETWEEN DynamicValue(RS_57_c_c_customer_sk_min) AND DynamicValue(RS_57_c_c_customer_sk_max) and in_bloom_filter(ws_bill_customer_sk, DynamicValue(RS_57_c_c_customer_sk_bloom_filter))) 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_bill_customer_sk is not null and ws_sold_date_sk is not null) + TableScan [TS_24] (rows=144002668 width=7) default@web_sales,web_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_sold_date_sk","ws_bill_customer_sk"] <-Reducer 10 [BROADCAST_EDGE] vectorized - BROADCAST [RS_210] - Group By Operator [GBY_209] (rows=1 width=12) + BROADCAST [RS_211] + Group By Operator [GBY_210] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Reducer 4 [CUSTOM_SIMPLE_EDGE] - FORWARD [RS_150] - Group By Operator [GBY_149] (rows=1 width=12) + FORWARD [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_148] (rows=162346 width=4) + Select Operator [SEL_149] (rows=162346 width=4) Output:["_col0"] - Please refer to the previous Merge Join Operator [MERGEJOIN_178] + Please refer to the previous Merge Join Operator [MERGEJOIN_179] <-Reducer 19 [BROADCAST_EDGE] vectorized - BROADCAST [RS_208] - Group By Operator [GBY_207] (rows=1 width=12) + BROADCAST [RS_209] + Group By Operator [GBY_208] (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 - PARTITION_ONLY_SHUFFLE [RS_200] - Group By Operator [GBY_197] (rows=1 width=12) + PARTITION_ONLY_SHUFFLE [RS_201] + Group By Operator [GBY_198] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_193] (rows=217 width=4) + Select Operator [SEL_194] (rows=217 width=4) Output:["_col0"] - Please refer to the previous Select Operator [SEL_189] + Please refer to the previous Select Operator [SEL_190] <-Reducer 21 [ONE_TO_ONE_EDGE] vectorized - FORWARD [RS_226] + FORWARD [RS_227] PartitionCols:_col0 - Select Operator [SEL_225] (rows=167041 width=7) + Select Operator [SEL_226] (rows=167041 width=7) Output:["_col0","_col1"] - Group By Operator [GBY_224] (rows=167041 width=3) + Group By Operator [GBY_225] (rows=167041 width=3) Output:["_col0"],keys:KEY._col0 <-Reducer 20 [SIMPLE_EDGE] - SHUFFLE [RS_42] + SHUFFLE [RS_49] PartitionCols:_col0 - Group By Operator [GBY_41] (rows=167041 width=3) + Group By Operator [GBY_48] (rows=167041 width=3) Output:["_col0"],keys:_col1 - Merge Join Operator [MERGEJOIN_177] (rows=33642830 width=3) - Conds:RS_223._col0=RS_194._col0(Inner),Output:["_col1"] + Merge Join Operator [MERGEJOIN_178] (rows=33642830 width=3) + Conds:RS_224._col0=RS_195._col0(Inner),Output:["_col1"] <-Map 15 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_194] + PARTITION_ONLY_SHUFFLE [RS_195] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_189] + Please refer to the previous Select Operator [SEL_190] <-Map 24 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_223] + SHUFFLE [RS_224] PartitionCols:_col0 - Select Operator [SEL_222] (rows=285115246 width=7) + Select Operator [SEL_223] (rows=285115246 width=7) Output:["_col0","_col1"] - Filter Operator [FIL_221] (rows=285115246 width=7) - predicate:((cs_ship_customer_sk BETWEEN DynamicValue(RS_59_c_c_customer_sk_min) AND DynamicValue(RS_59_c_c_customer_sk_max) and in_bloom_filter(cs_ship_customer_sk, DynamicValue(RS_59_c_c_customer_sk_bloom_filter))) and (cs_sold_date_sk BETWEEN DynamicValue(RS_38_date_dim_d_date_sk_min) AND DynamicValue(RS_38_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_38_date_dim_d_date_sk_bloom_filter))) and cs_ship_customer_sk is not null and cs_sold_date_sk is not null) - TableScan [TS_31] (rows=287989836 width=7) + Filter Operator [FIL_222] (rows=285115246 width=7) + predicate:((cs_ship_customer_sk BETWEEN DynamicValue(RS_60_c_c_customer_sk_min) AND DynamicValue(RS_60_c_c_customer_sk_max) and in_bloom_filter(cs_ship_customer_sk, DynamicValue(RS_60_c_c_customer_sk_bloom_filter))) and (cs_sold_date_sk BETWEEN DynamicValue(RS_45_date_dim_d_date_sk_min) AND DynamicValue(RS_45_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_45_date_dim_d_date_sk_bloom_filter))) and cs_ship_customer_sk is not null and cs_sold_date_sk is not null) + TableScan [TS_38] (rows=287989836 width=7) default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["cs_sold_date_sk","cs_ship_customer_sk"] <-Reducer 22 [BROADCAST_EDGE] vectorized - BROADCAST [RS_218] - Group By Operator [GBY_217] (rows=1 width=12) + BROADCAST [RS_219] + Group By Operator [GBY_218] (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 - PARTITION_ONLY_SHUFFLE [RS_201] - Group By Operator [GBY_198] (rows=1 width=12) + PARTITION_ONLY_SHUFFLE [RS_202] + Group By Operator [GBY_199] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_195] (rows=217 width=4) + Select Operator [SEL_196] (rows=217 width=4) Output:["_col0"] - Please refer to the previous Select Operator [SEL_189] + Please refer to the previous Select Operator [SEL_190] <-Reducer 9 [BROADCAST_EDGE] vectorized - BROADCAST [RS_220] - Group By Operator [GBY_219] (rows=1 width=12) + BROADCAST [RS_221] + Group By Operator [GBY_220] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Reducer 5 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_165] - Group By Operator [GBY_164] (rows=1 width=12) + 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_163] (rows=68 width=4) + Select Operator [SEL_164] (rows=68 width=4) Output:["_col0"] - Please refer to the previous Merge Join Operator [MERGEJOIN_179] + Please refer to the previous Merge Join Operator [MERGEJOIN_180] diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/query4.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/query4.q.out index 2f8ab17bf0..e6558e99a9 100644 --- a/ql/src/test/results/clientpositive/perf/tez/constraints/query4.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/query4.q.out @@ -229,10 +229,10 @@ POSTHOOK: Output: hdfs://### HDFS PATH ### Plan optimized by CBO. Vertex dependency in root stage -Map 1 <- Reducer 34 (BROADCAST_EDGE) -Map 11 <- Reducer 35 (BROADCAST_EDGE) -Map 15 <- Reducer 36 (BROADCAST_EDGE) -Map 19 <- Reducer 37 (BROADCAST_EDGE) +Map 1 <- Reducer 35 (BROADCAST_EDGE) +Map 11 <- Reducer 36 (BROADCAST_EDGE) +Map 15 <- Reducer 37 (BROADCAST_EDGE) +Map 19 <- Reducer 34 (BROADCAST_EDGE) Map 23 <- Reducer 33 (BROADCAST_EDGE) Map 27 <- Reducer 32 (BROADCAST_EDGE) Reducer 10 <- Reducer 9 (SIMPLE_EDGE) @@ -281,9 +281,9 @@ Stage-0 Select Operator [SEL_134] (rows=7323197 width=85) Output:["_col0"] Filter Operator [FIL_133] (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 + predicate:CASE WHEN (_col4 is not null) THEN (CASE WHEN (_col7) THEN (((_col9 / _col6) > (_col14 / _col4))) ELSE ((null > (_col14 / _col4))) END) ELSE (CASE WHEN (_col7) THEN (((_col9 / _col6) > null)) ELSE (null) END) END Merge Join Operator [MERGEJOIN_466] (rows=14646395 width=537) - Conds:RS_130._col2=RS_547._col0(Inner),Output:["_col3","_col8","_col9","_col11","_col13","_col14"] + Conds:RS_130._col3=RS_547._col0(Inner),Output:["_col4","_col6","_col7","_col9","_col13","_col14"] <-Reducer 30 [SIMPLE_EDGE] vectorized SHUFFLE [RS_547] PartitionCols:_col0 @@ -341,24 +341,24 @@ Stage-0 Please refer to the previous Select Operator [SEL_471] <-Reducer 8 [ONE_TO_ONE_EDGE] FORWARD [RS_130] - PartitionCols:_col2 + PartitionCols:_col3 Filter Operator [FIL_129] (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_465] (rows=24496186 width=668) - Conds:RS_126._col2=RS_541._col0(Inner),Output:["_col1","_col2","_col3","_col5","_col6","_col8","_col9","_col11"] + predicate:CASE WHEN (_col2) THEN (CASE WHEN (_col7) THEN (((_col9 / _col6) > (_col11 / _col1))) ELSE ((null > (_col11 / _col1))) END) ELSE (CASE WHEN (_col7) THEN (((_col9 / _col6) > null)) ELSE (null) END) END + Merge Join Operator [MERGEJOIN_465] (rows=24496187 width=668) + Conds:RS_126._col3=RS_541._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col6","_col7","_col9","_col11"] <-Reducer 26 [SIMPLE_EDGE] vectorized SHUFFLE [RS_541] PartitionCols:_col0 - Select Operator [SEL_540] (rows=80000000 width=212) + Select Operator [SEL_540] (rows=51391963 width=212) Output:["_col0","_col1"] - Group By Operator [GBY_539] (rows=80000000 width=764) + Group By Operator [GBY_539] (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 25 [SIMPLE_EDGE] SHUFFLE [RS_95] PartitionCols:_col0, _col1, _col2, _col3, _col4, _col5, _col6 - Group By Operator [GBY_94] (rows=80000000 width=764) + Group By Operator [GBY_94] (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_459] (rows=101084444 width=764) + Merge Join Operator [MERGEJOIN_459] (rows=51391963 width=764) Conds:RS_90._col1=RS_504._col0(Inner),Output:["_col2","_col5","_col6","_col7","_col8","_col9","_col10","_col11"] <-Map 38 [SIMPLE_EDGE] vectorized SHUFFLE [RS_504] @@ -367,7 +367,7 @@ Stage-0 <-Reducer 24 [SIMPLE_EDGE] SHUFFLE [RS_90] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_458] (rows=101084444 width=115) + Merge Join Operator [MERGEJOIN_458] (rows=51391963 width=115) Conds:RS_87._col0=RS_477._col0(Inner),Output:["_col1","_col2"] <-Map 31 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_477] @@ -376,12 +376,12 @@ Stage-0 <-Map 23 [SIMPLE_EDGE] SHUFFLE [RS_87] PartitionCols:_col0 - Select Operator [SEL_81] (rows=285117831 width=119) + Select Operator [SEL_81] (rows=143930993 width=119) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_241] (rows=285117831 width=453) - predicate:((cs_sold_date_sk BETWEEN DynamicValue(RS_88_date_dim_d_date_sk_min) AND DynamicValue(RS_88_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_88_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_79] (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"] + Filter Operator [FIL_241] (rows=143930993 width=455) + predicate:((ws_sold_date_sk BETWEEN DynamicValue(RS_88_date_dim_d_date_sk_min) AND DynamicValue(RS_88_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_88_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_79] (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 33 [BROADCAST_EDGE] vectorized BROADCAST [RS_537] Group By Operator [GBY_536] (rows=1 width=12) @@ -395,176 +395,223 @@ Stage-0 Please refer to the previous Select Operator [SEL_471] <-Reducer 7 [ONE_TO_ONE_EDGE] FORWARD [RS_126] - PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_464] (rows=20485011 width=556) - Conds:RS_123._col2=RS_535._col0(Inner),Output:["_col1","_col2","_col3","_col5","_col6","_col8","_col9"] + PartitionCols:_col3 + Merge Join Operator [MERGEJOIN_464] (rows=20485012 width=556) + Conds:RS_123._col3=RS_535._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col6","_col7","_col9"] <-Reducer 22 [SIMPLE_EDGE] vectorized SHUFFLE [RS_535] PartitionCols:_col0 - Select Operator [SEL_534] (rows=26666666 width=216) - Output:["_col0","_col1","_col2"] - Filter Operator [FIL_533] (rows=26666666 width=212) - predicate:(_col7 > 0) - Select Operator [SEL_532] (rows=80000000 width=212) - Output:["_col0","_col7"] - Group By Operator [GBY_531] (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_75] - PartitionCols:_col0, _col1, _col2, _col3, _col4, _col5, _col6 - Group By Operator [GBY_74] (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_457] (rows=101084444 width=764) - Conds:RS_70._col1=RS_508._col0(Inner),Output:["_col2","_col5","_col6","_col7","_col8","_col9","_col10","_col11"] - <-Map 38 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_508] + Select Operator [SEL_534] (rows=80000000 width=212) + Output:["_col0","_col1"] + Group By Operator [GBY_533] (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_76] + PartitionCols:_col0, _col1, _col2, _col3, _col4, _col5, _col6 + Group By Operator [GBY_75] (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_457] (rows=101084444 width=764) + Conds:RS_71._col1=RS_505._col0(Inner),Output:["_col2","_col5","_col6","_col7","_col8","_col9","_col10","_col11"] + <-Map 38 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_505] + PartitionCols:_col0 + Please refer to the previous Select Operator [SEL_502] + <-Reducer 20 [SIMPLE_EDGE] + SHUFFLE [RS_71] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_456] (rows=101084444 width=115) + Conds:RS_68._col0=RS_479._col0(Inner),Output:["_col1","_col2"] + <-Map 31 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_479] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_502] - <-Reducer 20 [SIMPLE_EDGE] - SHUFFLE [RS_70] - PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_456] (rows=101084444 width=115) - Conds:RS_67._col0=RS_485._col0(Inner),Output:["_col1","_col2"] - <-Map 31 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_485] - PartitionCols:_col0 - Select Operator [SEL_474] (rows=652 width=4) - Output:["_col0"] - Filter Operator [FIL_470] (rows=652 width=8) - predicate:(d_year = 2001) - Please refer to the previous TableScan [TS_101] - <-Map 19 [SIMPLE_EDGE] - SHUFFLE [RS_67] - PartitionCols:_col0 - Select Operator [SEL_61] (rows=285117831 width=119) - Output:["_col0","_col1","_col2"] - Filter Operator [FIL_238] (rows=285117831 width=453) - predicate:((cs_sold_date_sk BETWEEN DynamicValue(RS_68_date_dim_d_date_sk_min) AND DynamicValue(RS_68_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_68_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_59] (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_529] - Group By Operator [GBY_528] (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_498] - Group By Operator [GBY_492] (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_474] + Please refer to the previous Select Operator [SEL_471] + <-Map 19 [SIMPLE_EDGE] + SHUFFLE [RS_68] + PartitionCols:_col0 + Select Operator [SEL_62] (rows=285117831 width=119) + Output:["_col0","_col1","_col2"] + Filter Operator [FIL_238] (rows=285117831 width=453) + predicate:((cs_sold_date_sk BETWEEN DynamicValue(RS_69_date_dim_d_date_sk_min) AND DynamicValue(RS_69_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_69_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_60] (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 34 [BROADCAST_EDGE] vectorized + BROADCAST [RS_531] + Group By Operator [GBY_530] (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_495] + Group By Operator [GBY_489] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_480] (rows=652 width=4) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_471] <-Reducer 6 [ONE_TO_ONE_EDGE] FORWARD [RS_123] - PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_463] (rows=20485011 width=440) - Conds:RS_120._col2=RS_527._col0(Inner),Output:["_col1","_col2","_col3","_col5","_col6"] + PartitionCols:_col3 + Merge Join Operator [MERGEJOIN_463] (rows=17130654 width=444) + Conds:RS_120._col3=RS_529._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col6","_col7"] <-Reducer 18 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_527] + SHUFFLE [RS_529] PartitionCols:_col0 - Select Operator [SEL_526] (rows=17130654 width=216) + Select Operator [SEL_528] (rows=26666666 width=216) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_525] (rows=17130654 width=212) + Filter Operator [FIL_527] (rows=26666666 width=212) predicate:(_col7 > 0) - Select Operator [SEL_524] (rows=51391963 width=212) + Select Operator [SEL_526] (rows=80000000 width=212) Output:["_col0","_col7"] - Group By Operator [GBY_523] (rows=51391963 width=764) + Group By Operator [GBY_525] (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 17 [SIMPLE_EDGE] - SHUFFLE [RS_55] + SHUFFLE [RS_56] PartitionCols:_col0, _col1, _col2, _col3, _col4, _col5, _col6 - Group By Operator [GBY_54] (rows=51391963 width=764) + Group By Operator [GBY_55] (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_455] (rows=51391963 width=764) - Conds:RS_50._col1=RS_507._col0(Inner),Output:["_col2","_col5","_col6","_col7","_col8","_col9","_col10","_col11"] + Merge Join Operator [MERGEJOIN_455] (rows=101084444 width=764) + Conds:RS_51._col1=RS_508._col0(Inner),Output:["_col2","_col5","_col6","_col7","_col8","_col9","_col10","_col11"] <-Map 38 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_507] + SHUFFLE [RS_508] PartitionCols:_col0 Please refer to the previous Select Operator [SEL_502] <-Reducer 16 [SIMPLE_EDGE] - SHUFFLE [RS_50] + SHUFFLE [RS_51] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_454] (rows=51391963 width=115) - Conds:RS_47._col0=RS_483._col0(Inner),Output:["_col1","_col2"] + Merge Join Operator [MERGEJOIN_454] (rows=101084444 width=115) + Conds:RS_48._col0=RS_485._col0(Inner),Output:["_col1","_col2"] <-Map 31 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_483] + PARTITION_ONLY_SHUFFLE [RS_485] PartitionCols:_col0 - Select Operator [SEL_473] (rows=652 width=4) + Select Operator [SEL_474] (rows=652 width=4) Output:["_col0"] - Filter Operator [FIL_469] (rows=652 width=8) + Filter Operator [FIL_470] (rows=652 width=8) predicate:(d_year = 2001) Please refer to the previous TableScan [TS_101] <-Map 15 [SIMPLE_EDGE] - SHUFFLE [RS_47] + SHUFFLE [RS_48] PartitionCols:_col0 - Select Operator [SEL_41] (rows=143930993 width=119) + Select Operator [SEL_42] (rows=285117831 width=119) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_235] (rows=143930993 width=455) - predicate:((ws_sold_date_sk BETWEEN DynamicValue(RS_48_date_dim_d_date_sk_min) AND DynamicValue(RS_48_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_48_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_39] (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_521] - Group By Operator [GBY_520] (rows=1 width=12) + Filter Operator [FIL_235] (rows=285117831 width=453) + predicate:((cs_sold_date_sk BETWEEN DynamicValue(RS_49_date_dim_d_date_sk_min) AND DynamicValue(RS_49_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_49_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_40] (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_523] + Group By Operator [GBY_522] (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_497] - Group By Operator [GBY_491] (rows=1 width=12) + PARTITION_ONLY_SHUFFLE [RS_498] + Group By Operator [GBY_492] (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) + Select Operator [SEL_486] (rows=652 width=4) Output:["_col0"] - Please refer to the previous Select Operator [SEL_473] + Please refer to the previous Select Operator [SEL_474] <-Reducer 5 [ONE_TO_ONE_EDGE] FORWARD [RS_120] - PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_462] (rows=31888273 width=324) - Conds:RS_511._col0=RS_519._col0(Inner),Output:["_col1","_col2","_col3"] + PartitionCols:_col3 + Merge Join Operator [MERGEJOIN_462] (rows=17130654 width=328) + Conds:RS_513._col0=RS_521._col0(Inner),Output:["_col1","_col2","_col3","_col4"] <-Reducer 14 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_519] + SHUFFLE [RS_521] PartitionCols:_col0 - Select Operator [SEL_518] (rows=26666666 width=212) + Select Operator [SEL_520] (rows=26666666 width=212) Output:["_col0","_col1"] - Filter Operator [FIL_517] (rows=26666666 width=212) + Filter Operator [FIL_519] (rows=26666666 width=212) predicate:(_col7 > 0) - Select Operator [SEL_516] (rows=80000000 width=212) + Select Operator [SEL_518] (rows=80000000 width=212) Output:["_col0","_col7"] - Group By Operator [GBY_515] (rows=80000000 width=764) + Group By Operator [GBY_517] (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_35] + SHUFFLE [RS_36] PartitionCols:_col0, _col1, _col2, _col3, _col4, _col5, _col6 - Group By Operator [GBY_34] (rows=80000000 width=764) + Group By Operator [GBY_35] (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_453] (rows=187573258 width=764) - Conds:RS_30._col1=RS_506._col0(Inner),Output:["_col2","_col5","_col6","_col7","_col8","_col9","_col10","_col11"] + Conds:RS_31._col1=RS_507._col0(Inner),Output:["_col2","_col5","_col6","_col7","_col8","_col9","_col10","_col11"] <-Map 38 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_506] + SHUFFLE [RS_507] PartitionCols:_col0 Please refer to the previous Select Operator [SEL_502] <-Reducer 12 [SIMPLE_EDGE] - SHUFFLE [RS_30] + SHUFFLE [RS_31] PartitionCols:_col1 Merge Join Operator [MERGEJOIN_452] (rows=187573258 width=115) - Conds:RS_27._col0=RS_481._col0(Inner),Output:["_col1","_col2"] + Conds:RS_28._col0=RS_483._col0(Inner),Output:["_col1","_col2"] <-Map 31 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_481] + PARTITION_ONLY_SHUFFLE [RS_483] PartitionCols:_col0 - Select Operator [SEL_472] (rows=652 width=4) + Select Operator [SEL_473] (rows=652 width=4) Output:["_col0"] - Filter Operator [FIL_468] (rows=652 width=8) + Filter Operator [FIL_469] (rows=652 width=8) predicate:(d_year = 2001) Please refer to the previous TableScan [TS_101] <-Map 11 [SIMPLE_EDGE] - SHUFFLE [RS_27] + SHUFFLE [RS_28] PartitionCols:_col0 - Select Operator [SEL_21] (rows=525327388 width=119) + Select Operator [SEL_22] (rows=525327388 width=119) Output:["_col0","_col1","_col2"] Filter Operator [FIL_232] (rows=525327388 width=435) - predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_28_date_dim_d_date_sk_min) AND DynamicValue(RS_28_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_28_date_dim_d_date_sk_bloom_filter))) and ss_customer_sk is not null and ss_sold_date_sk is not null) - TableScan [TS_19] (rows=575995635 width=435) + predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_29_date_dim_d_date_sk_min) AND DynamicValue(RS_29_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_29_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 36 [BROADCAST_EDGE] vectorized + BROADCAST [RS_515] + Group By Operator [GBY_514] (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_497] + Group By Operator [GBY_491] (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_473] + <-Reducer 4 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_513] + PartitionCols:_col0 + Select Operator [SEL_512] (rows=17130654 width=216) + Output:["_col0","_col1","_col2"] + Filter Operator [FIL_511] (rows=17130654 width=212) + predicate:(_col7 > 0) + Select Operator [SEL_510] (rows=51391963 width=212) + Output:["_col0","_col7"] + Group By Operator [GBY_509] (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_16] + PartitionCols:_col0, _col1, _col2, _col3, _col4, _col5, _col6 + Group By Operator [GBY_15] (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_451] (rows=51391963 width=764) + Conds:RS_11._col1=RS_506._col0(Inner),Output:["_col2","_col5","_col6","_col7","_col8","_col9","_col10","_col11"] + <-Map 38 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_506] + PartitionCols:_col0 + Please refer to the previous Select Operator [SEL_502] + <-Reducer 2 [SIMPLE_EDGE] + SHUFFLE [RS_11] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_450] (rows=51391963 width=115) + Conds:RS_8._col0=RS_481._col0(Inner),Output:["_col1","_col2"] + <-Map 31 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_481] + PartitionCols:_col0 + Select Operator [SEL_472] (rows=652 width=4) + Output:["_col0"] + Filter Operator [FIL_468] (rows=652 width=8) + predicate:(d_year = 2001) + Please refer to the previous TableScan [TS_101] + <-Map 1 [SIMPLE_EDGE] + SHUFFLE [RS_8] + PartitionCols:_col0 + Select Operator [SEL_2] (rows=143930993 width=119) + Output:["_col0","_col1","_col2"] + Filter Operator [FIL_229] (rows=143930993 width=455) + predicate:((ws_sold_date_sk BETWEEN DynamicValue(RS_9_date_dim_d_date_sk_min) AND DynamicValue(RS_9_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_9_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 35 [BROADCAST_EDGE] vectorized - BROADCAST [RS_513] - Group By Operator [GBY_512] (rows=1 width=12) + BROADCAST [RS_500] + Group By Operator [GBY_499] (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_496] @@ -573,51 +620,4 @@ Stage-0 Select Operator [SEL_482] (rows=652 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_472] - <-Reducer 4 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_511] - PartitionCols:_col0 - Select Operator [SEL_510] (rows=51391963 width=212) - Output:["_col0","_col1"] - Group By Operator [GBY_509] (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_16] - PartitionCols:_col0, _col1, _col2, _col3, _col4, _col5, _col6 - Group By Operator [GBY_15] (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_451] (rows=51391963 width=764) - Conds:RS_11._col1=RS_505._col0(Inner),Output:["_col2","_col5","_col6","_col7","_col8","_col9","_col10","_col11"] - <-Map 38 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_505] - PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_502] - <-Reducer 2 [SIMPLE_EDGE] - SHUFFLE [RS_11] - PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_450] (rows=51391963 width=115) - Conds:RS_8._col0=RS_479._col0(Inner),Output:["_col1","_col2"] - <-Map 31 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_479] - PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_471] - <-Map 1 [SIMPLE_EDGE] - SHUFFLE [RS_8] - PartitionCols:_col0 - Select Operator [SEL_2] (rows=143930993 width=119) - Output:["_col0","_col1","_col2"] - Filter Operator [FIL_229] (rows=143930993 width=455) - predicate:((ws_sold_date_sk BETWEEN DynamicValue(RS_9_date_dim_d_date_sk_min) AND DynamicValue(RS_9_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_9_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_500] - Group By Operator [GBY_499] (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_495] - Group By Operator [GBY_489] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_480] (rows=652 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_471] diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/query45.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/query45.q.out index bf620c8ed5..0abd4ceb1b 100644 --- a/ql/src/test/results/clientpositive/perf/tez/constraints/query45.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/query45.q.out @@ -51,133 +51,135 @@ POSTHOOK: Output: hdfs://### HDFS PATH ### Plan optimized by CBO. Vertex dependency in root stage -Map 11 <- Reducer 14 (BROADCAST_EDGE) -Reducer 10 <- Map 7 (SIMPLE_EDGE) -Reducer 12 <- Map 11 (SIMPLE_EDGE), Map 13 (SIMPLE_EDGE) -Reducer 14 <- Map 13 (CUSTOM_SIMPLE_EDGE) -Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 6 (SIMPLE_EDGE) -Reducer 3 <- Reducer 2 (SIMPLE_EDGE), Reducer 9 (SIMPLE_EDGE) -Reducer 4 <- Reducer 3 (SIMPLE_EDGE) +Map 8 <- Reducer 12 (BROADCAST_EDGE) +Reducer 10 <- Map 13 (SIMPLE_EDGE), Reducer 9 (SIMPLE_EDGE) +Reducer 12 <- Map 11 (CUSTOM_SIMPLE_EDGE) +Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 7 (ONE_TO_ONE_EDGE) +Reducer 3 <- Reducer 10 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) +Reducer 4 <- Map 14 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) Reducer 5 <- Reducer 4 (SIMPLE_EDGE) -Reducer 8 <- Map 7 (SIMPLE_EDGE), Reducer 10 (ONE_TO_ONE_EDGE) -Reducer 9 <- Reducer 12 (SIMPLE_EDGE), Reducer 8 (SIMPLE_EDGE) +Reducer 6 <- Reducer 5 (SIMPLE_EDGE) +Reducer 7 <- Map 1 (SIMPLE_EDGE) +Reducer 9 <- Map 11 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:100 Stage-1 - Reducer 5 vectorized - File Output Operator [FS_149] - Limit [LIM_148] (rows=100 width=299) + Reducer 6 vectorized + File Output Operator [FS_150] + Limit [LIM_149] (rows=100 width=299) Number of rows:100 - Select Operator [SEL_147] (rows=285780 width=299) + Select Operator [SEL_148] (rows=1143120 width=299) Output:["_col0","_col1","_col2"] - <-Reducer 4 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_146] - Group By Operator [GBY_145] (rows=285780 width=299) + <-Reducer 5 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_147] + Group By Operator [GBY_146] (rows=1143120 width=299) Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1 - <-Reducer 3 [SIMPLE_EDGE] - SHUFFLE [RS_41] + <-Reducer 4 [SIMPLE_EDGE] + SHUFFLE [RS_40] PartitionCols:_col0, _col1 - Group By Operator [GBY_40] (rows=3715140 width=299) + Group By Operator [GBY_39] (rows=10246864 width=299) Output:["_col0","_col1","_col2"],aggregations:["sum(_col3)"],keys:_col8, _col7 - Top N Key Operator [TNK_69] (rows=10246864 width=302) + Top N Key Operator [TNK_70] (rows=10246864 width=302) keys:_col8, _col7,sort order:++,top n:100 - Select Operator [SEL_39] (rows=10246864 width=302) + Select Operator [SEL_38] (rows=10246864 width=302) Output:["_col3","_col7","_col8"] - Filter Operator [FIL_38] (rows=10246864 width=302) + Filter Operator [FIL_37] (rows=10246864 width=302) predicate:((substr(_col8, 1, 5)) IN ('85669', '86197', '88274', '83405', '86475', '85392', '85460', '80348', '81792') or _col15 is not null) - Select Operator [SEL_37] (rows=10246864 width=302) + Select Operator [SEL_36] (rows=10246864 width=302) Output:["_col3","_col7","_col8","_col15"] - Merge Join Operator [MERGEJOIN_119] (rows=10246864 width=302) - Conds:RS_34._col0=RS_35._col6(Inner),Output:["_col3","_col4","_col8","_col12"] - <-Reducer 2 [SIMPLE_EDGE] - SHUFFLE [RS_34] + Merge Join Operator [MERGEJOIN_120] (rows=10246864 width=302) + Conds:RS_33._col5=RS_145._col0(Inner),Output:["_col3","_col9","_col14","_col15"] + <-Map 14 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_145] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_115] (rows=80000000 width=191) - Conds:RS_122._col1=RS_124._col0(Inner),Output:["_col0","_col3","_col4"] - <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_122] - PartitionCols:_col1 - Select Operator [SEL_121] (rows=80000000 width=8) - Output:["_col0","_col1"] - Filter Operator [FIL_120] (rows=80000000 width=8) - predicate:c_current_addr_sk is not null - TableScan [TS_0] (rows=80000000 width=8) - default@customer,customer,Tbl:COMPLETE,Col:COMPLETE,Output:["c_customer_sk","c_current_addr_sk"] - <-Map 6 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_124] - PartitionCols:_col0 - Select Operator [SEL_123] (rows=40000000 width=191) - Output:["_col0","_col1","_col2"] - TableScan [TS_3] (rows=40000000 width=191) - default@customer_address,customer_address,Tbl:COMPLETE,Col:COMPLETE,Output:["ca_address_sk","ca_county","ca_zip"] - <-Reducer 9 [SIMPLE_EDGE] - SHUFFLE [RS_35] - PartitionCols:_col6 - Merge Join Operator [MERGEJOIN_118] (rows=10246864 width=119) - Conds:RS_27._col0=RS_28._col1(Inner),Output:["_col3","_col6","_col7"] - <-Reducer 12 [SIMPLE_EDGE] - SHUFFLE [RS_28] - PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_117] (rows=10246864 width=119) - Conds:RS_144._col0=RS_136._col0(Inner),Output:["_col1","_col2","_col3"] - <-Map 13 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_136] - PartitionCols:_col0 - Select Operator [SEL_135] (rows=130 width=12) - Output:["_col0"] - Filter Operator [FIL_134] (rows=130 width=12) - predicate:((d_qoy = 2) and (d_year = 2000)) - TableScan [TS_17] (rows=73049 width=12) - default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year","d_qoy"] - <-Map 11 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_144] - PartitionCols:_col0 - Select Operator [SEL_143] (rows=143930993 width=123) - Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_142] (rows=143930993 width=123) - predicate:((ws_sold_date_sk BETWEEN DynamicValue(RS_21_date_dim_d_date_sk_min) AND DynamicValue(RS_21_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_21_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_14] (rows=144002668 width=123) - default@web_sales,web_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_sold_date_sk","ws_item_sk","ws_bill_customer_sk","ws_sales_price"] - <-Reducer 14 [BROADCAST_EDGE] vectorized - BROADCAST [RS_141] - Group By Operator [GBY_140] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 13 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_139] - Group By Operator [GBY_138] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_137] (rows=130 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_135] - <-Reducer 8 [SIMPLE_EDGE] - SHUFFLE [RS_27] + Select Operator [SEL_144] (rows=40000000 width=191) + Output:["_col0","_col1","_col2"] + TableScan [TS_25] (rows=40000000 width=191) + default@customer_address,customer_address,Tbl:COMPLETE,Col:COMPLETE,Output:["ca_address_sk","ca_county","ca_zip"] + <-Reducer 3 [SIMPLE_EDGE] + SHUFFLE [RS_33] + PartitionCols:_col5 + Merge Join Operator [MERGEJOIN_119] (rows=10246864 width=119) + Conds:RS_30._col0=RS_31._col3(Inner),Output:["_col3","_col5","_col9"] + <-Reducer 10 [SIMPLE_EDGE] + SHUFFLE [RS_31] + PartitionCols:_col3 + Select Operator [SEL_24] (rows=10246864 width=119) + Output:["_col1","_col3","_col5"] + Merge Join Operator [MERGEJOIN_118] (rows=10246864 width=119) + Conds:RS_21._col2=RS_143._col0(Inner),Output:["_col1","_col3","_col8"] + <-Map 13 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_143] + PartitionCols:_col0 + Select Operator [SEL_142] (rows=80000000 width=8) + Output:["_col0","_col1"] + Filter Operator [FIL_141] (rows=80000000 width=8) + predicate:c_current_addr_sk is not null + TableScan [TS_15] (rows=80000000 width=8) + default@customer,customer,Tbl:COMPLETE,Col:COMPLETE,Output:["c_customer_sk","c_current_addr_sk"] + <-Reducer 9 [SIMPLE_EDGE] + SHUFFLE [RS_21] + PartitionCols:_col2 + Merge Join Operator [MERGEJOIN_117] (rows=10246864 width=119) + Conds:RS_140._col0=RS_132._col0(Inner),Output:["_col1","_col2","_col3"] + <-Map 11 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_132] + PartitionCols:_col0 + Select Operator [SEL_131] (rows=130 width=12) + Output:["_col0"] + Filter Operator [FIL_130] (rows=130 width=12) + predicate:((d_qoy = 2) and (d_year = 2000)) + TableScan [TS_12] (rows=73049 width=12) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year","d_qoy"] + <-Map 8 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_140] + PartitionCols:_col0 + Select Operator [SEL_139] (rows=143930993 width=123) + Output:["_col0","_col1","_col2","_col3"] + Filter Operator [FIL_138] (rows=143930993 width=123) + predicate:((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_bill_customer_sk is not null and ws_sold_date_sk is not null) + TableScan [TS_9] (rows=144002668 width=123) + default@web_sales,web_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_sold_date_sk","ws_item_sk","ws_bill_customer_sk","ws_sales_price"] + <-Reducer 12 [BROADCAST_EDGE] vectorized + 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_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_133] (rows=130 width=4) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_131] + <-Reducer 2 [SIMPLE_EDGE] + SHUFFLE [RS_30] PartitionCols:_col0 Merge Join Operator [MERGEJOIN_116] (rows=462007 width=4) - Conds:RS_127._col1=RS_133._col0(Left Outer),Output:["_col0","_col3"] - <-Map 7 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_127] + Conds:RS_123._col1=RS_129._col0(Left Outer),Output:["_col0","_col3"] + <-Map 1 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_123] PartitionCols:_col1 - Select Operator [SEL_125] (rows=462000 width=104) + Select Operator [SEL_121] (rows=462000 width=104) Output:["_col0","_col1"] - TableScan [TS_5] (rows=462000 width=104) + TableScan [TS_0] (rows=462000 width=104) default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_item_id"] - <-Reducer 10 [ONE_TO_ONE_EDGE] vectorized - FORWARD [RS_133] + <-Reducer 7 [ONE_TO_ONE_EDGE] vectorized + FORWARD [RS_129] PartitionCols:_col0 - Select Operator [SEL_132] (rows=5 width=104) + Select Operator [SEL_128] (rows=5 width=104) Output:["_col0","_col1"] - Group By Operator [GBY_131] (rows=5 width=100) + Group By Operator [GBY_127] (rows=5 width=100) Output:["_col0"],keys:KEY._col0 - <-Map 7 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_130] + <-Map 1 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_126] PartitionCols:_col0 - Group By Operator [GBY_129] (rows=5 width=100) + Group By Operator [GBY_125] (rows=5 width=100) Output:["_col0"],keys:i_item_id - Select Operator [SEL_128] (rows=11 width=104) + Select Operator [SEL_124] (rows=11 width=104) Output:["i_item_id"] - Filter Operator [FIL_126] (rows=11 width=104) + Filter Operator [FIL_122] (rows=11 width=104) predicate:(i_item_sk) IN (2, 3, 5, 7, 11, 13, 17, 19, 23, 29) - Please refer to the previous TableScan [TS_5] + Please refer to the previous TableScan [TS_0] diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/query46.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/query46.q.out index 5d25eafc24..72a6b26c4d 100644 --- a/ql/src/test/results/clientpositive/perf/tez/constraints/query46.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/query46.q.out @@ -83,158 +83,158 @@ POSTHOOK: Output: hdfs://### HDFS PATH ### Plan optimized by CBO. Vertex dependency in root stage -Map 8 <- Reducer 13 (BROADCAST_EDGE), Reducer 15 (BROADCAST_EDGE), Reducer 17 (BROADCAST_EDGE) -Reducer 10 <- Map 14 (SIMPLE_EDGE), Reducer 9 (SIMPLE_EDGE) -Reducer 11 <- Map 16 (SIMPLE_EDGE), Reducer 10 (SIMPLE_EDGE) -Reducer 13 <- Map 12 (CUSTOM_SIMPLE_EDGE) -Reducer 15 <- Map 14 (CUSTOM_SIMPLE_EDGE) -Reducer 17 <- Map 16 (CUSTOM_SIMPLE_EDGE) -Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) -Reducer 3 <- Reducer 2 (SIMPLE_EDGE), Reducer 7 (SIMPLE_EDGE) +Map 5 <- Reducer 12 (BROADCAST_EDGE), Reducer 14 (BROADCAST_EDGE), Reducer 16 (BROADCAST_EDGE) +Reducer 10 <- Reducer 9 (SIMPLE_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), Reducer 10 (SIMPLE_EDGE) +Reducer 3 <- Map 17 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) Reducer 4 <- Reducer 3 (SIMPLE_EDGE) -Reducer 6 <- Map 5 (SIMPLE_EDGE), Reducer 11 (SIMPLE_EDGE) -Reducer 7 <- Reducer 6 (SIMPLE_EDGE) -Reducer 9 <- Map 12 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) +Reducer 6 <- Map 11 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) +Reducer 7 <- Map 13 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE) +Reducer 8 <- Map 15 (SIMPLE_EDGE), Reducer 7 (SIMPLE_EDGE) +Reducer 9 <- Map 17 (SIMPLE_EDGE), Reducer 8 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:100 Stage-1 Reducer 4 vectorized - File Output Operator [FS_182] - Limit [LIM_181] (rows=100 width=594) + File Output Operator [FS_186] + Limit [LIM_185] (rows=100 width=594) Number of rows:100 - Select Operator [SEL_180] (rows=8380115 width=594) + Select Operator [SEL_184] (rows=8380115 width=594) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"] <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_44] Select Operator [SEL_43] (rows=8380115 width=594) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"] Filter Operator [FIL_42] (rows=8380115 width=594) - predicate:(_col5 <> _col8) - Merge Join Operator [MERGEJOIN_143] (rows=8380115 width=594) - Conds:RS_39._col0=RS_179._col1(Inner),Output:["_col2","_col3","_col5","_col6","_col8","_col9","_col10"] + predicate:(_col10 <> _col6) + Merge Join Operator [MERGEJOIN_147] (rows=8380115 width=594) + Conds:RS_39._col1=RS_179._col0(Inner),Output:["_col2","_col3","_col4","_col6","_col7","_col8","_col10"] + <-Map 17 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_179] + PartitionCols:_col0 + Select Operator [SEL_178] (rows=40000000 width=97) + Output:["_col0","_col1"] + TableScan [TS_34] (rows=40000000 width=97) + default@customer_address,current_addr,Tbl:COMPLETE,Col:COMPLETE,Output:["ca_address_sk","ca_city"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_39] - PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_138] (rows=80000000 width=277) - Conds:RS_146._col1=RS_148._col0(Inner),Output:["_col0","_col2","_col3","_col5"] - <-Map 5 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_148] - PartitionCols:_col0 - Select Operator [SEL_147] (rows=40000000 width=97) - Output:["_col0","_col1"] - TableScan [TS_3] (rows=40000000 width=97) - default@customer_address,current_addr,Tbl:COMPLETE,Col:COMPLETE,Output:["ca_address_sk","ca_city"] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_146] (rows=8380115 width=505) + Conds:RS_150._col0=RS_183._col1(Inner),Output:["_col1","_col2","_col3","_col4","_col6","_col7","_col8"] <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_146] - PartitionCols:_col1 - Select Operator [SEL_145] (rows=80000000 width=188) + SHUFFLE [RS_150] + PartitionCols:_col0 + Select Operator [SEL_149] (rows=80000000 width=188) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_144] (rows=80000000 width=188) + Filter Operator [FIL_148] (rows=80000000 width=188) predicate:c_current_addr_sk is not null TableScan [TS_0] (rows=80000000 width=188) default@customer,customer,Tbl:COMPLETE,Col:COMPLETE,Output:["c_customer_sk","c_current_addr_sk","c_first_name","c_last_name"] - <-Reducer 7 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_179] - PartitionCols:_col1 - Select Operator [SEL_178] (rows=8380115 width=321) - Output:["_col0","_col1","_col2","_col3","_col4"] - Group By Operator [GBY_177] (rows=8380115 width=321) - Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3 - <-Reducer 6 [SIMPLE_EDGE] - SHUFFLE [RS_33] - PartitionCols:_col0, _col1, _col2, _col3 - Group By Operator [GBY_32] (rows=8380115 width=321) - Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(_col6)","sum(_col7)"],keys:_col1, _col12, _col3, _col5 - Merge Join Operator [MERGEJOIN_142] (rows=8380115 width=97) - Conds:RS_28._col3=RS_149._col0(Inner),Output:["_col1","_col3","_col5","_col6","_col7","_col12"] - <-Map 5 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_149] - PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_147] - <-Reducer 11 [SIMPLE_EDGE] - SHUFFLE [RS_28] - PartitionCols:_col3 - Merge Join Operator [MERGEJOIN_141] (rows=8380115 width=4) - Conds:RS_25._col2=RS_168._col0(Inner),Output:["_col1","_col3","_col5","_col6","_col7"] - <-Map 16 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_168] + <-Reducer 10 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_183] + PartitionCols:_col1 + Select Operator [SEL_182] (rows=8380115 width=321) + Output:["_col0","_col1","_col2","_col3","_col4"] + Group By Operator [GBY_181] (rows=8380115 width=321) + Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3 + <-Reducer 9 [SIMPLE_EDGE] + SHUFFLE [RS_31] + PartitionCols:_col0, _col1, _col2, _col3 + Group By Operator [GBY_30] (rows=8380115 width=321) + Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(_col6)","sum(_col7)"],keys:_col1, _col12, _col3, _col5 + Merge Join Operator [MERGEJOIN_145] (rows=8380115 width=97) + Conds:RS_26._col3=RS_180._col0(Inner),Output:["_col1","_col3","_col5","_col6","_col7","_col12"] + <-Map 17 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_180] PartitionCols:_col0 - Select Operator [SEL_167] (rows=1855 width=4) - Output:["_col0"] - Filter Operator [FIL_166] (rows=1855 width=12) - predicate:((hd_dep_count = 2) or (hd_vehicle_count = 1)) - TableScan [TS_14] (rows=7200 width=12) - default@household_demographics,household_demographics,Tbl:COMPLETE,Col:COMPLETE,Output:["hd_demo_sk","hd_dep_count","hd_vehicle_count"] - <-Reducer 10 [SIMPLE_EDGE] - SHUFFLE [RS_25] - PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_140] (rows=32526589 width=90) - Conds:RS_22._col4=RS_160._col0(Inner),Output:["_col1","_col2","_col3","_col5","_col6","_col7"] - <-Map 14 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_160] + Please refer to the previous Select Operator [SEL_178] + <-Reducer 8 [SIMPLE_EDGE] + SHUFFLE [RS_26] + PartitionCols:_col3 + Merge Join Operator [MERGEJOIN_144] (rows=8380115 width=4) + Conds:RS_23._col2=RS_169._col0(Inner),Output:["_col1","_col3","_col5","_col6","_col7"] + <-Map 15 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_169] PartitionCols:_col0 - Select Operator [SEL_159] (rows=35 width=4) + Select Operator [SEL_168] (rows=1855 width=4) Output:["_col0"] - Filter Operator [FIL_158] (rows=35 width=97) - predicate:(s_city) IN ('Cedar Grove', 'Wildwood', 'Union', 'Salem', 'Highland Park') - TableScan [TS_11] (rows=1704 width=97) - default@store,store,Tbl:COMPLETE,Col:COMPLETE,Output:["s_store_sk","s_city"] - <-Reducer 9 [SIMPLE_EDGE] - SHUFFLE [RS_22] - PartitionCols:_col4 - Merge Join Operator [MERGEJOIN_139] (rows=196204013 width=218) - Conds:RS_176._col0=RS_152._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col6","_col7"] - <-Map 12 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_152] + Filter Operator [FIL_167] (rows=1855 width=12) + predicate:((hd_dep_count = 2) or (hd_vehicle_count = 1)) + TableScan [TS_12] (rows=7200 width=12) + default@household_demographics,household_demographics,Tbl:COMPLETE,Col:COMPLETE,Output:["hd_demo_sk","hd_dep_count","hd_vehicle_count"] + <-Reducer 7 [SIMPLE_EDGE] + SHUFFLE [RS_23] + PartitionCols:_col2 + Merge Join Operator [MERGEJOIN_143] (rows=32526589 width=90) + Conds:RS_20._col4=RS_161._col0(Inner),Output:["_col1","_col2","_col3","_col5","_col6","_col7"] + <-Map 13 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_161] PartitionCols:_col0 - Select Operator [SEL_151] (rows=783 width=4) + Select Operator [SEL_160] (rows=35 width=4) Output:["_col0"] - Filter Operator [FIL_150] (rows=783 width=12) - predicate:((d_dow) IN (6, 0) and (d_year) IN (1998, 1999, 2000)) - TableScan [TS_8] (rows=73049 width=12) - default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year","d_dow"] - <-Map 8 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_176] - PartitionCols:_col0 - Select Operator [SEL_175] (rows=457565061 width=237) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] - Filter Operator [FIL_174] (rows=457565061 width=237) - predicate:((ss_hdemo_sk BETWEEN DynamicValue(RS_26_household_demographics_hd_demo_sk_min) AND DynamicValue(RS_26_household_demographics_hd_demo_sk_max) and in_bloom_filter(ss_hdemo_sk, DynamicValue(RS_26_household_demographics_hd_demo_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_20_date_dim_d_date_sk_min) AND DynamicValue(RS_20_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_20_date_dim_d_date_sk_bloom_filter))) and (ss_store_sk BETWEEN DynamicValue(RS_23_store_s_store_sk_min) AND DynamicValue(RS_23_store_s_store_sk_max) and in_bloom_filter(ss_store_sk, DynamicValue(RS_23_store_s_store_sk_bloom_filter))) and ss_addr_sk is not null and ss_customer_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_5] (rows=575995635 width=237) - default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_customer_sk","ss_hdemo_sk","ss_addr_sk","ss_store_sk","ss_ticket_number","ss_coupon_amt","ss_net_profit"] - <-Reducer 13 [BROADCAST_EDGE] vectorized - BROADCAST [RS_157] - Group By Operator [GBY_156] (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_155] - Group By Operator [GBY_154] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_153] (rows=783 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_151] - <-Reducer 15 [BROADCAST_EDGE] vectorized - BROADCAST [RS_165] - Group By Operator [GBY_164] (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_163] - Group By Operator [GBY_162] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_161] (rows=35 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_159] - <-Reducer 17 [BROADCAST_EDGE] vectorized - BROADCAST [RS_173] - Group By Operator [GBY_172] (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_171] - Group By Operator [GBY_170] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_169] (rows=1855 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_167] + Filter Operator [FIL_159] (rows=35 width=97) + predicate:(s_city) IN ('Cedar Grove', 'Wildwood', 'Union', 'Salem', 'Highland Park') + TableScan [TS_9] (rows=1704 width=97) + default@store,store,Tbl:COMPLETE,Col:COMPLETE,Output:["s_store_sk","s_city"] + <-Reducer 6 [SIMPLE_EDGE] + SHUFFLE [RS_20] + PartitionCols:_col4 + Merge Join Operator [MERGEJOIN_142] (rows=196204013 width=218) + Conds:RS_177._col0=RS_153._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col6","_col7"] + <-Map 11 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_153] + PartitionCols:_col0 + Select Operator [SEL_152] (rows=783 width=4) + Output:["_col0"] + Filter Operator [FIL_151] (rows=783 width=12) + predicate:((d_dow) IN (6, 0) and (d_year) IN (1998, 1999, 2000)) + TableScan [TS_6] (rows=73049 width=12) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year","d_dow"] + <-Map 5 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_177] + PartitionCols:_col0 + Select Operator [SEL_176] (rows=457565061 width=237) + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] + Filter Operator [FIL_175] (rows=457565061 width=237) + predicate:((ss_hdemo_sk BETWEEN DynamicValue(RS_24_household_demographics_hd_demo_sk_min) AND DynamicValue(RS_24_household_demographics_hd_demo_sk_max) and in_bloom_filter(ss_hdemo_sk, DynamicValue(RS_24_household_demographics_hd_demo_sk_bloom_filter))) 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_store_sk BETWEEN DynamicValue(RS_21_store_s_store_sk_min) AND DynamicValue(RS_21_store_s_store_sk_max) and in_bloom_filter(ss_store_sk, DynamicValue(RS_21_store_s_store_sk_bloom_filter))) and ss_addr_sk is not null and ss_customer_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=237) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_customer_sk","ss_hdemo_sk","ss_addr_sk","ss_store_sk","ss_ticket_number","ss_coupon_amt","ss_net_profit"] + <-Reducer 12 [BROADCAST_EDGE] vectorized + BROADCAST [RS_158] + Group By Operator [GBY_157] (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_156] + Group By Operator [GBY_155] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_154] (rows=783 width=4) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_152] + <-Reducer 14 [BROADCAST_EDGE] vectorized + BROADCAST [RS_166] + Group By Operator [GBY_165] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 13 [CUSTOM_SIMPLE_EDGE] vectorized + SHUFFLE [RS_164] + Group By Operator [GBY_163] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_162] (rows=35 width=4) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_160] + <-Reducer 16 [BROADCAST_EDGE] vectorized + BROADCAST [RS_174] + Group By Operator [GBY_173] (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_172] + Group By Operator [GBY_171] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_170] (rows=1855 width=4) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_168] diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/query54.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/query54.q.out index 21193d658d..285547de18 100644 --- a/ql/src/test/results/clientpositive/perf/tez/constraints/query54.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/query54.q.out @@ -1,7 +1,7 @@ -Warning: Shuffle Join MERGEJOIN[264][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product -Warning: Shuffle Join MERGEJOIN[273][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3, $hdt$_4]] in Stage 'Reducer 5' is a cross product -Warning: Shuffle Join MERGEJOIN[272][tables = [$hdt$_1, $hdt$_2]] in Stage 'Reducer 14' is a cross product -Warning: Shuffle Join MERGEJOIN[274][tables = [$hdt$_1, $hdt$_2, $hdt$_0]] in Stage 'Reducer 6' is a cross product +Warning: Shuffle Join MERGEJOIN[270][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product +Warning: Shuffle Join MERGEJOIN[278][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3, $hdt$_4]] in Stage 'Reducer 5' is a cross product +Warning: Shuffle Join MERGEJOIN[279][tables = [$hdt$_1, $hdt$_2]] in Stage 'Reducer 14' is a cross product +Warning: Shuffle Join MERGEJOIN[280][tables = [$hdt$_1, $hdt$_2, $hdt$_0]] in Stage 'Reducer 6' is a cross product PREHOOK: query: explain with my_customers as ( select distinct c_customer_sk @@ -133,27 +133,27 @@ POSTHOOK: Output: hdfs://### HDFS PATH ### Plan optimized by CBO. Vertex dependency in root stage -Map 1 <- Reducer 21 (BROADCAST_EDGE) -Map 23 <- Reducer 31 (BROADCAST_EDGE), Reducer 33 (BROADCAST_EDGE), Union 24 (CONTAINS) -Map 29 <- Reducer 31 (BROADCAST_EDGE), Reducer 33 (BROADCAST_EDGE), Union 24 (CONTAINS) +Map 1 <- Reducer 20 (BROADCAST_EDGE) +Map 22 <- Reducer 30 (BROADCAST_EDGE), Reducer 32 (BROADCAST_EDGE), Union 23 (CONTAINS) +Map 28 <- Reducer 30 (BROADCAST_EDGE), Reducer 32 (BROADCAST_EDGE), Union 23 (CONTAINS) Reducer 11 <- Map 10 (SIMPLE_EDGE) Reducer 12 <- Reducer 11 (CUSTOM_SIMPLE_EDGE) Reducer 13 <- Map 10 (SIMPLE_EDGE) Reducer 14 <- Reducer 13 (CUSTOM_SIMPLE_EDGE), Reducer 16 (CUSTOM_SIMPLE_EDGE) Reducer 15 <- Map 10 (SIMPLE_EDGE) Reducer 16 <- Reducer 15 (CUSTOM_SIMPLE_EDGE) -Reducer 19 <- Map 18 (SIMPLE_EDGE), Map 22 (SIMPLE_EDGE) +Reducer 18 <- Map 17 (SIMPLE_EDGE), Map 21 (SIMPLE_EDGE) +Reducer 19 <- Reducer 18 (SIMPLE_EDGE), Reducer 27 (SIMPLE_EDGE) Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE), Reducer 12 (CUSTOM_SIMPLE_EDGE) -Reducer 20 <- Reducer 19 (SIMPLE_EDGE), Reducer 28 (SIMPLE_EDGE) -Reducer 21 <- Reducer 20 (CUSTOM_SIMPLE_EDGE) -Reducer 25 <- Map 30 (SIMPLE_EDGE), Union 24 (SIMPLE_EDGE) -Reducer 26 <- Map 32 (SIMPLE_EDGE), Reducer 25 (SIMPLE_EDGE) -Reducer 27 <- Map 34 (SIMPLE_EDGE), Reducer 26 (SIMPLE_EDGE) -Reducer 28 <- Reducer 27 (SIMPLE_EDGE) -Reducer 3 <- Map 17 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) -Reducer 31 <- Map 30 (CUSTOM_SIMPLE_EDGE) -Reducer 33 <- Map 32 (CUSTOM_SIMPLE_EDGE) -Reducer 4 <- Reducer 20 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) +Reducer 20 <- Reducer 19 (CUSTOM_SIMPLE_EDGE) +Reducer 24 <- Map 29 (SIMPLE_EDGE), Union 23 (SIMPLE_EDGE) +Reducer 25 <- Map 31 (SIMPLE_EDGE), Reducer 24 (SIMPLE_EDGE) +Reducer 26 <- Map 33 (SIMPLE_EDGE), Reducer 25 (SIMPLE_EDGE) +Reducer 27 <- Reducer 26 (SIMPLE_EDGE) +Reducer 3 <- Reducer 19 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) +Reducer 30 <- Map 29 (CUSTOM_SIMPLE_EDGE) +Reducer 32 <- Map 31 (CUSTOM_SIMPLE_EDGE) +Reducer 4 <- Map 34 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) Reducer 5 <- Reducer 11 (CUSTOM_SIMPLE_EDGE), Reducer 4 (CUSTOM_SIMPLE_EDGE) Reducer 6 <- Reducer 14 (CUSTOM_SIMPLE_EDGE), Reducer 5 (CUSTOM_SIMPLE_EDGE) Reducer 7 <- Reducer 6 (SIMPLE_EDGE) @@ -165,25 +165,25 @@ Stage-0 limit:100 Stage-1 Reducer 9 vectorized - File Output Operator [FS_354] - Limit [LIM_353] (rows=1 width=16) + File Output Operator [FS_360] + Limit [LIM_359] (rows=1 width=16) Number of rows:100 - Select Operator [SEL_352] (rows=1 width=16) + Select Operator [SEL_358] (rows=1 width=16) Output:["_col0","_col1","_col2"] <-Reducer 8 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_351] - Select Operator [SEL_350] (rows=1 width=16) + SHUFFLE [RS_357] + Select Operator [SEL_356] (rows=1 width=16) Output:["_col0","_col1","_col2"] - Group By Operator [GBY_349] (rows=1 width=12) + Group By Operator [GBY_355] (rows=1 width=12) Output:["_col0","_col1"],aggregations:["count(VALUE._col0)"],keys:KEY._col0 <-Reducer 7 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_348] + SHUFFLE [RS_354] PartitionCols:_col0 - Group By Operator [GBY_347] (rows=1 width=12) + Group By Operator [GBY_353] (rows=1 width=12) Output:["_col0","_col1"],aggregations:["count()"],keys:_col0 - Select Operator [SEL_346] (rows=1 width=116) + Select Operator [SEL_352] (rows=1 width=116) Output:["_col0"] - Group By Operator [GBY_345] (rows=1 width=116) + Group By Operator [GBY_351] (rows=1 width=116) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 <-Reducer 6 [SIMPLE_EDGE] SHUFFLE [RS_118] @@ -196,244 +196,244 @@ Stage-0 predicate:_col2 BETWEEN _col3 AND _col4 Select Operator [SEL_114] (rows=5618315000 width=127) Output:["_col0","_col1","_col2","_col3","_col4"] - Merge Join Operator [MERGEJOIN_274] (rows=5618315000 width=127) + Merge Join Operator [MERGEJOIN_280] (rows=5618315000 width=127) Conds:(Inner),Output:["_col0","_col2","_col6","_col13","_col15"] <-Reducer 14 [CUSTOM_SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_111] - Merge Join Operator [MERGEJOIN_272] (rows=25 width=4) + Merge Join Operator [MERGEJOIN_279] (rows=25 width=4) Conds:(Right Outer),Output:["_col0"] <-Reducer 13 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_336] - Group By Operator [GBY_335] (rows=25 width=4) + PARTITION_ONLY_SHUFFLE [RS_342] + Group By Operator [GBY_341] (rows=25 width=4) Output:["_col0"],keys:KEY._col0 <-Map 10 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_322] + SHUFFLE [RS_328] PartitionCols:_col0 - Group By Operator [GBY_319] (rows=25 width=4) + Group By Operator [GBY_325] (rows=25 width=4) Output:["_col0"],keys:_col0 - Select Operator [SEL_316] (rows=50 width=12) + Select Operator [SEL_322] (rows=50 width=12) Output:["_col0"] - Filter Operator [FIL_314] (rows=50 width=12) + Filter Operator [FIL_320] (rows=50 width=12) predicate:((d_moy = 3) and (d_year = 1999)) TableScan [TS_26] (rows=73049 width=12) default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_month_seq","d_year","d_moy"] <-Reducer 16 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_344] - Select Operator [SEL_343] (rows=1 width=8) - Filter Operator [FIL_342] (rows=1 width=8) + PARTITION_ONLY_SHUFFLE [RS_350] + Select Operator [SEL_349] (rows=1 width=8) + Filter Operator [FIL_348] (rows=1 width=8) predicate:(sq_count_check(_col0) <= 1) - Group By Operator [GBY_341] (rows=1 width=8) + Group By Operator [GBY_347] (rows=1 width=8) Output:["_col0"],aggregations:["count(VALUE._col0)"] <-Reducer 15 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_340] - Group By Operator [GBY_339] (rows=1 width=8) + PARTITION_ONLY_SHUFFLE [RS_346] + Group By Operator [GBY_345] (rows=1 width=8) Output:["_col0"],aggregations:["count()"] - Select Operator [SEL_338] (rows=25 width=4) - Group By Operator [GBY_337] (rows=25 width=4) + Select Operator [SEL_344] (rows=25 width=4) + Group By Operator [GBY_343] (rows=25 width=4) Output:["_col0"],keys:KEY._col0 <-Map 10 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_323] + SHUFFLE [RS_329] PartitionCols:_col0 - Group By Operator [GBY_320] (rows=25 width=4) + Group By Operator [GBY_326] (rows=25 width=4) Output:["_col0"],keys:_col0 - Select Operator [SEL_317] (rows=50 width=12) + Select Operator [SEL_323] (rows=50 width=12) Output:["_col0"] - Please refer to the previous Filter Operator [FIL_314] + Please refer to the previous Filter Operator [FIL_320] <-Reducer 5 [CUSTOM_SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_112] Select Operator [SEL_107] (rows=224732600 width=119) Output:["_col0","_col4","_col11","_col13"] - Merge Join Operator [MERGEJOIN_273] (rows=224732600 width=119) - Conds:(Left Outer),Output:["_col2","_col5","_col11","_col13"] + Merge Join Operator [MERGEJOIN_278] (rows=224732600 width=119) + Conds:(Left Outer),Output:["_col2","_col9","_col12","_col13"] <-Reducer 11 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_326] - Group By Operator [GBY_324] (rows=25 width=4) + PARTITION_ONLY_SHUFFLE [RS_332] + Group By Operator [GBY_330] (rows=25 width=4) Output:["_col0"],keys:KEY._col0 <-Map 10 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_321] + SHUFFLE [RS_327] PartitionCols:_col0 - Group By Operator [GBY_318] (rows=25 width=4) + Group By Operator [GBY_324] (rows=25 width=4) Output:["_col0"],keys:_col0 - Select Operator [SEL_315] (rows=50 width=12) + Select Operator [SEL_321] (rows=50 width=12) Output:["_col0"] - Please refer to the previous Filter Operator [FIL_314] + Please refer to the previous Filter Operator [FIL_320] <-Reducer 4 [CUSTOM_SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_104] - Merge Join Operator [MERGEJOIN_271] (rows=8989304 width=8) - Conds:RS_101._col1=RS_102._col5(Inner),Output:["_col2","_col5","_col11"] - <-Reducer 20 [SIMPLE_EDGE] - SHUFFLE [RS_102] - PartitionCols:_col5 - Merge Join Operator [MERGEJOIN_270] (rows=55046 width=4) - Conds:RS_83._col0=RS_308._col1(Inner),Output:["_col5"] + Merge Join Operator [MERGEJOIN_277] (rows=8989304 width=8) + Conds:RS_101._col0=RS_340._col0(Inner),Output:["_col2","_col9","_col12"] + <-Map 34 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_340] + PartitionCols:_col0 + Select Operator [SEL_339] (rows=73049 width=8) + Output:["_col0","_col1"] + TableScan [TS_85] (rows=73049 width=8) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_month_seq"] + <-Reducer 3 [SIMPLE_EDGE] + SHUFFLE [RS_101] + PartitionCols:_col0 + Merge Join Operator [MERGEJOIN_276] (rows=8989304 width=4) + Conds:RS_98._col1=RS_99._col5(Inner),Output:["_col0","_col2","_col9"] <-Reducer 19 [SIMPLE_EDGE] - SHUFFLE [RS_83] - PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_266] (rows=39720279 width=4) - Conds:RS_287._col1, _col2=RS_290._col0, _col1(Inner),Output:["_col0"] - <-Map 18 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_287] - PartitionCols:_col1, _col2 - Select Operator [SEL_286] (rows=40000000 width=188) - Output:["_col0","_col1","_col2"] - Filter Operator [FIL_285] (rows=40000000 width=188) - predicate:(ca_county is not null and ca_state is not null) - TableScan [TS_43] (rows=40000000 width=188) - default@customer_address,customer_address,Tbl:COMPLETE,Col:COMPLETE,Output:["ca_address_sk","ca_county","ca_state"] - <-Map 22 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_290] - PartitionCols:_col0, _col1 - Select Operator [SEL_289] (rows=1704 width=184) + SHUFFLE [RS_99] + PartitionCols:_col5 + Merge Join Operator [MERGEJOIN_275] (rows=55046 width=4) + Conds:RS_81._col0=RS_314._col1(Inner),Output:["_col5"] + <-Reducer 18 [SIMPLE_EDGE] + SHUFFLE [RS_81] + PartitionCols:_col0 + Merge Join Operator [MERGEJOIN_271] (rows=39720279 width=4) + Conds:RS_293._col1, _col2=RS_296._col0, _col1(Inner),Output:["_col0"] + <-Map 17 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_293] + PartitionCols:_col1, _col2 + Select Operator [SEL_292] (rows=40000000 width=188) + Output:["_col0","_col1","_col2"] + Filter Operator [FIL_291] (rows=40000000 width=188) + predicate:(ca_county is not null and ca_state is not null) + TableScan [TS_41] (rows=40000000 width=188) + default@customer_address,customer_address,Tbl:COMPLETE,Col:COMPLETE,Output:["ca_address_sk","ca_county","ca_state"] + <-Map 21 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_296] + PartitionCols:_col0, _col1 + Select Operator [SEL_295] (rows=1704 width=184) + Output:["_col0","_col1"] + Filter Operator [FIL_294] (rows=1704 width=184) + predicate:(s_county is not null and s_state is not null) + TableScan [TS_44] (rows=1704 width=184) + default@store,store,Tbl:COMPLETE,Col:COMPLETE,Output:["s_county","s_state"] + <-Reducer 27 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_314] + PartitionCols:_col1 + Select Operator [SEL_313] (rows=55046 width=8) Output:["_col0","_col1"] - Filter Operator [FIL_288] (rows=1704 width=184) - predicate:(s_county is not null and s_state is not null) - TableScan [TS_46] (rows=1704 width=184) - default@store,store,Tbl:COMPLETE,Col:COMPLETE,Output:["s_county","s_state"] - <-Reducer 28 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_308] - PartitionCols:_col1 - Select Operator [SEL_307] (rows=55046 width=8) - Output:["_col0","_col1"] - Group By Operator [GBY_306] (rows=55046 width=8) - Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 - <-Reducer 27 [SIMPLE_EDGE] - SHUFFLE [RS_77] - PartitionCols:_col0, _col1 - Group By Operator [GBY_76] (rows=55046 width=8) - Output:["_col0","_col1"],keys:_col6, _col5 - Merge Join Operator [MERGEJOIN_269] (rows=110092 width=8) - Conds:RS_72._col1=RS_305._col0(Inner),Output:["_col5","_col6"] - <-Map 34 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_305] - PartitionCols:_col0 - Select Operator [SEL_304] (rows=80000000 width=8) - Output:["_col0","_col1"] - Filter Operator [FIL_303] (rows=80000000 width=8) - predicate:c_current_addr_sk is not null - TableScan [TS_63] (rows=80000000 width=8) - default@customer,customer,Tbl:COMPLETE,Col:COMPLETE,Output:["c_customer_sk","c_current_addr_sk"] - <-Reducer 26 [SIMPLE_EDGE] - SHUFFLE [RS_72] - PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_268] (rows=110092 width=0) - Conds:RS_69._col2=RS_299._col0(Inner),Output:["_col1"] - <-Map 32 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_299] + Group By Operator [GBY_312] (rows=55046 width=8) + Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 + <-Reducer 26 [SIMPLE_EDGE] + SHUFFLE [RS_75] + PartitionCols:_col0, _col1 + Group By Operator [GBY_74] (rows=55046 width=8) + Output:["_col0","_col1"],keys:_col6, _col5 + Merge Join Operator [MERGEJOIN_274] (rows=110092 width=8) + Conds:RS_70._col1=RS_311._col0(Inner),Output:["_col5","_col6"] + <-Map 33 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_311] PartitionCols:_col0 - Select Operator [SEL_298] (rows=453 width=4) - Output:["_col0"] - Filter Operator [FIL_297] (rows=453 width=186) - predicate:((i_category = 'Jewelry') and (i_class = 'consignment')) - TableScan [TS_60] (rows=462000 width=186) - default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_class","i_category"] + Select Operator [SEL_310] (rows=80000000 width=8) + Output:["_col0","_col1"] + Filter Operator [FIL_309] (rows=80000000 width=8) + predicate:c_current_addr_sk is not null + TableScan [TS_61] (rows=80000000 width=8) + default@customer,customer,Tbl:COMPLETE,Col:COMPLETE,Output:["c_customer_sk","c_current_addr_sk"] <-Reducer 25 [SIMPLE_EDGE] - SHUFFLE [RS_69] - PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_267] (rows=11665117 width=7) - Conds:Union 24._col0=RS_293._col0(Inner),Output:["_col1","_col2"] - <-Map 30 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_293] + SHUFFLE [RS_70] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_273] (rows=110092 width=0) + Conds:RS_67._col2=RS_305._col0(Inner),Output:["_col1"] + <-Map 31 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_305] PartitionCols:_col0 - Select Operator [SEL_292] (rows=50 width=4) + Select Operator [SEL_304] (rows=453 width=4) Output:["_col0"] - Filter Operator [FIL_291] (rows=50 width=12) - predicate:((d_moy = 3) and (d_year = 1999)) - TableScan [TS_57] (rows=73049 width=12) - default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year","d_moy"] - <-Union 24 [SIMPLE_EDGE] - <-Map 23 [CONTAINS] vectorized - Reduce Output Operator [RS_363] - PartitionCols:_col0 - Select Operator [SEL_362] (rows=285117831 width=11) - Output:["_col0","_col1","_col2"] - Filter Operator [FIL_361] (rows=285117831 width=11) - predicate:((cs_item_sk BETWEEN DynamicValue(RS_70_item_i_item_sk_min) AND DynamicValue(RS_70_item_i_item_sk_max) and in_bloom_filter(cs_item_sk, DynamicValue(RS_70_item_i_item_sk_bloom_filter))) and (cs_sold_date_sk BETWEEN DynamicValue(RS_67_date_dim_d_date_sk_min) AND DynamicValue(RS_67_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_67_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_275] (rows=287989836 width=11) - Output:["cs_sold_date_sk","cs_bill_customer_sk","cs_item_sk"] - <-Reducer 31 [BROADCAST_EDGE] vectorized - BROADCAST [RS_356] - Group By Operator [GBY_355] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 30 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_296] - Group By Operator [GBY_295] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_294] (rows=50 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_292] - <-Reducer 33 [BROADCAST_EDGE] vectorized - BROADCAST [RS_359] - Group By Operator [GBY_358] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 32 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_302] - Group By Operator [GBY_301] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_300] (rows=453 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_298] - <-Map 29 [CONTAINS] vectorized - Reduce Output Operator [RS_366] - PartitionCols:_col0 - Select Operator [SEL_365] (rows=143930993 width=11) - Output:["_col0","_col1","_col2"] - Filter Operator [FIL_364] (rows=143930993 width=11) - predicate:((ws_item_sk BETWEEN DynamicValue(RS_70_item_i_item_sk_min) AND DynamicValue(RS_70_item_i_item_sk_max) and in_bloom_filter(ws_item_sk, DynamicValue(RS_70_item_i_item_sk_bloom_filter))) and (ws_sold_date_sk BETWEEN DynamicValue(RS_67_date_dim_d_date_sk_min) AND DynamicValue(RS_67_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_67_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_280] (rows=144002668 width=11) - Output:["ws_sold_date_sk","ws_item_sk","ws_bill_customer_sk"] - <-Reducer 31 [BROADCAST_EDGE] vectorized - BROADCAST [RS_357] - Please refer to the previous Group By Operator [GBY_355] - <-Reducer 33 [BROADCAST_EDGE] vectorized - BROADCAST [RS_360] - Please refer to the previous Group By Operator [GBY_358] - <-Reducer 3 [SIMPLE_EDGE] - SHUFFLE [RS_101] - PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_265] (rows=525327388 width=114) - Conds:RS_98._col0=RS_334._col0(Inner),Output:["_col1","_col2","_col5"] - <-Map 17 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_334] - PartitionCols:_col0 - Select Operator [SEL_333] (rows=73049 width=8) - Output:["_col0","_col1"] - TableScan [TS_41] (rows=73049 width=8) - default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_month_seq"] + Filter Operator [FIL_303] (rows=453 width=186) + predicate:((i_category = 'Jewelry') and (i_class = 'consignment')) + TableScan [TS_58] (rows=462000 width=186) + default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_class","i_category"] + <-Reducer 24 [SIMPLE_EDGE] + SHUFFLE [RS_67] + PartitionCols:_col2 + Merge Join Operator [MERGEJOIN_272] (rows=11665117 width=7) + Conds:Union 23._col0=RS_299._col0(Inner),Output:["_col1","_col2"] + <-Map 29 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_299] + PartitionCols:_col0 + Select Operator [SEL_298] (rows=50 width=4) + Output:["_col0"] + Filter Operator [FIL_297] (rows=50 width=12) + predicate:((d_moy = 3) and (d_year = 1999)) + TableScan [TS_55] (rows=73049 width=12) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year","d_moy"] + <-Union 23 [SIMPLE_EDGE] + <-Map 22 [CONTAINS] vectorized + Reduce Output Operator [RS_369] + PartitionCols:_col0 + Select Operator [SEL_368] (rows=285117831 width=11) + Output:["_col0","_col1","_col2"] + Filter Operator [FIL_367] (rows=285117831 width=11) + predicate:((cs_item_sk BETWEEN DynamicValue(RS_68_item_i_item_sk_min) AND DynamicValue(RS_68_item_i_item_sk_max) and in_bloom_filter(cs_item_sk, DynamicValue(RS_68_item_i_item_sk_bloom_filter))) and (cs_sold_date_sk BETWEEN DynamicValue(RS_65_date_dim_d_date_sk_min) AND DynamicValue(RS_65_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_65_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_281] (rows=287989836 width=11) + Output:["cs_sold_date_sk","cs_bill_customer_sk","cs_item_sk"] + <-Reducer 30 [BROADCAST_EDGE] vectorized + BROADCAST [RS_362] + Group By Operator [GBY_361] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 29 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_302] + Group By Operator [GBY_301] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_300] (rows=50 width=4) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_298] + <-Reducer 32 [BROADCAST_EDGE] vectorized + BROADCAST [RS_365] + Group By Operator [GBY_364] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 31 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_308] + 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_306] (rows=453 width=4) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_304] + <-Map 28 [CONTAINS] vectorized + Reduce Output Operator [RS_372] + PartitionCols:_col0 + Select Operator [SEL_371] (rows=143930993 width=11) + Output:["_col0","_col1","_col2"] + Filter Operator [FIL_370] (rows=143930993 width=11) + predicate:((ws_item_sk BETWEEN DynamicValue(RS_68_item_i_item_sk_min) AND DynamicValue(RS_68_item_i_item_sk_max) and in_bloom_filter(ws_item_sk, DynamicValue(RS_68_item_i_item_sk_bloom_filter))) and (ws_sold_date_sk BETWEEN DynamicValue(RS_65_date_dim_d_date_sk_min) AND DynamicValue(RS_65_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_65_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_286] (rows=144002668 width=11) + Output:["ws_sold_date_sk","ws_item_sk","ws_bill_customer_sk"] + <-Reducer 30 [BROADCAST_EDGE] vectorized + BROADCAST [RS_363] + Please refer to the previous Group By Operator [GBY_361] + <-Reducer 32 [BROADCAST_EDGE] vectorized + BROADCAST [RS_366] + Please refer to the previous Group By Operator [GBY_364] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_98] - PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_264] (rows=525327388 width=114) + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_270] (rows=525327388 width=114) Conds:(Inner),Output:["_col0","_col1","_col2"] <-Map 1 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_313] - Select Operator [SEL_312] (rows=525327388 width=114) + PARTITION_ONLY_SHUFFLE [RS_319] + Select Operator [SEL_318] (rows=525327388 width=114) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_311] (rows=525327388 width=114) - predicate:((ss_customer_sk BETWEEN DynamicValue(RS_102_customer_c_customer_sk_min) AND DynamicValue(RS_102_customer_c_customer_sk_max) and in_bloom_filter(ss_customer_sk, DynamicValue(RS_102_customer_c_customer_sk_bloom_filter))) and ss_customer_sk is not null and ss_sold_date_sk is not null) + Filter Operator [FIL_317] (rows=525327388 width=114) + predicate:((ss_customer_sk BETWEEN DynamicValue(RS_99_customer_c_customer_sk_min) AND DynamicValue(RS_99_customer_c_customer_sk_max) and in_bloom_filter(ss_customer_sk, DynamicValue(RS_99_customer_c_customer_sk_bloom_filter))) and ss_customer_sk is not null and ss_sold_date_sk is not null) TableScan [TS_23] (rows=575995635 width=114) default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_customer_sk","ss_ext_sales_price"] - <-Reducer 21 [BROADCAST_EDGE] vectorized - BROADCAST [RS_310] - Group By Operator [GBY_309] (rows=1 width=12) + <-Reducer 20 [BROADCAST_EDGE] vectorized + BROADCAST [RS_316] + Group By Operator [GBY_315] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Reducer 20 [CUSTOM_SIMPLE_EDGE] - SHUFFLE [RS_184] - Group By Operator [GBY_183] (rows=1 width=12) + <-Reducer 19 [CUSTOM_SIMPLE_EDGE] + SHUFFLE [RS_185] + Group By Operator [GBY_184] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_182] (rows=55046 width=8) + Select Operator [SEL_183] (rows=55046 width=8) Output:["_col0"] - Please refer to the previous Merge Join Operator [MERGEJOIN_270] + Please refer to the previous Merge Join Operator [MERGEJOIN_275] <-Reducer 12 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_332] - Select Operator [SEL_331] (rows=1 width=8) - Filter Operator [FIL_330] (rows=1 width=8) + PARTITION_ONLY_SHUFFLE [RS_338] + Select Operator [SEL_337] (rows=1 width=8) + Filter Operator [FIL_336] (rows=1 width=8) predicate:(sq_count_check(_col0) <= 1) - Group By Operator [GBY_329] (rows=1 width=8) + Group By Operator [GBY_335] (rows=1 width=8) Output:["_col0"],aggregations:["count(VALUE._col0)"] <-Reducer 11 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_328] - Group By Operator [GBY_327] (rows=1 width=8) + PARTITION_ONLY_SHUFFLE [RS_334] + Group By Operator [GBY_333] (rows=1 width=8) Output:["_col0"],aggregations:["count()"] - Select Operator [SEL_325] (rows=25 width=4) - Please refer to the previous Group By Operator [GBY_324] + Select Operator [SEL_331] (rows=25 width=4) + Please refer to the previous Group By Operator [GBY_330] diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/query58.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/query58.q.out index 61342fa356..daeda3fdc6 100644 --- a/ql/src/test/results/clientpositive/perf/tez/constraints/query58.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/query58.q.out @@ -1,4 +1,4 @@ -Warning: Shuffle Join MERGEJOIN[401][tables = [$hdt$_4, $hdt$_5]] in Stage 'Reducer 22' is a cross product +Warning: Shuffle Join MERGEJOIN[406][tables = [$hdt$_3, $hdt$_4]] in Stage 'Reducer 20' is a cross product PREHOOK: query: explain with ss_items as (select i_item_id item_id @@ -142,252 +142,252 @@ POSTHOOK: Output: hdfs://### HDFS PATH ### Plan optimized by CBO. Vertex dependency in root stage -Map 1 <- Reducer 17 (BROADCAST_EDGE) -Map 26 <- Reducer 18 (BROADCAST_EDGE) -Map 27 <- Reducer 19 (BROADCAST_EDGE) -Reducer 10 <- Reducer 16 (SIMPLE_EDGE), Reducer 9 (SIMPLE_EDGE) -Reducer 11 <- Reducer 10 (SIMPLE_EDGE) -Reducer 12 <- Map 27 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) -Reducer 13 <- Reducer 12 (SIMPLE_EDGE), Reducer 16 (SIMPLE_EDGE) -Reducer 14 <- Reducer 13 (SIMPLE_EDGE) -Reducer 16 <- Map 15 (SIMPLE_EDGE), Reducer 24 (ONE_TO_ONE_EDGE) -Reducer 17 <- Reducer 16 (CUSTOM_SIMPLE_EDGE) -Reducer 18 <- Reducer 16 (CUSTOM_SIMPLE_EDGE) -Reducer 19 <- Reducer 16 (CUSTOM_SIMPLE_EDGE) -Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) -Reducer 21 <- Map 20 (CUSTOM_SIMPLE_EDGE) -Reducer 22 <- Map 25 (CUSTOM_SIMPLE_EDGE), Reducer 21 (CUSTOM_SIMPLE_EDGE) -Reducer 23 <- Map 25 (SIMPLE_EDGE), Reducer 22 (SIMPLE_EDGE) -Reducer 24 <- Reducer 23 (SIMPLE_EDGE) -Reducer 3 <- Reducer 16 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) -Reducer 4 <- Reducer 3 (SIMPLE_EDGE) -Reducer 5 <- Reducer 11 (ONE_TO_ONE_EDGE), Reducer 4 (ONE_TO_ONE_EDGE) -Reducer 6 <- Reducer 14 (ONE_TO_ONE_EDGE), Reducer 5 (ONE_TO_ONE_EDGE) -Reducer 7 <- Reducer 6 (SIMPLE_EDGE) -Reducer 9 <- Map 26 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) +Map 24 <- Reducer 9 (BROADCAST_EDGE) +Map 26 <- Reducer 13 (BROADCAST_EDGE) +Map 27 <- Reducer 17 (BROADCAST_EDGE) +Reducer 10 <- Map 26 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) +Reducer 11 <- Map 25 (SIMPLE_EDGE), Reducer 10 (SIMPLE_EDGE) +Reducer 12 <- Reducer 11 (SIMPLE_EDGE) +Reducer 13 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) +Reducer 14 <- Map 27 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) +Reducer 15 <- Map 25 (SIMPLE_EDGE), Reducer 14 (SIMPLE_EDGE) +Reducer 16 <- Reducer 15 (SIMPLE_EDGE) +Reducer 17 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) +Reducer 19 <- Map 18 (CUSTOM_SIMPLE_EDGE) +Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 22 (ONE_TO_ONE_EDGE) +Reducer 20 <- Map 23 (CUSTOM_SIMPLE_EDGE), Reducer 19 (CUSTOM_SIMPLE_EDGE) +Reducer 21 <- Map 23 (SIMPLE_EDGE), Reducer 20 (SIMPLE_EDGE) +Reducer 22 <- Reducer 21 (SIMPLE_EDGE) +Reducer 3 <- Map 24 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) +Reducer 4 <- Map 25 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) +Reducer 5 <- Reducer 4 (SIMPLE_EDGE) +Reducer 6 <- Reducer 12 (ONE_TO_ONE_EDGE), Reducer 5 (ONE_TO_ONE_EDGE) +Reducer 7 <- Reducer 16 (ONE_TO_ONE_EDGE), Reducer 6 (ONE_TO_ONE_EDGE) +Reducer 8 <- Reducer 7 (SIMPLE_EDGE) +Reducer 9 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) Stage-0 Fetch Operator limit:100 Stage-1 - Reducer 7 vectorized - File Output Operator [FS_464] - Limit [LIM_463] (rows=1 width=884) + Reducer 8 vectorized + File Output Operator [FS_470] + Limit [LIM_469] (rows=1 width=884) Number of rows:100 - Select Operator [SEL_462] (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_160] - Select Operator [SEL_159] (rows=1 width=884) + <-Reducer 7 [SIMPLE_EDGE] + SHUFFLE [RS_157] + Select Operator [SEL_156] (rows=1 width=884) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] - Filter Operator [FIL_155] (rows=1 width=660) + Filter Operator [FIL_152] (rows=1 width=660) predicate:(_col1 BETWEEN _col6 AND _col7 and _col3 BETWEEN _col6 AND _col7 and _col5 BETWEEN (0.9 * _col1) AND (1.1 * _col1) and _col5 BETWEEN (0.9 * _col3) AND (1.1 * _col3)) - Merge Join Operator [MERGEJOIN_416] (rows=1 width=660) - Conds:RS_152._col0=RS_461._col0(Inner),Output:["_col0","_col1","_col3","_col5","_col6","_col7"] - <-Reducer 14 [ONE_TO_ONE_EDGE] vectorized - FORWARD [RS_461] + Merge Join Operator [MERGEJOIN_422] (rows=384 width=660) + Conds:RS_149._col0=RS_467._col0(Inner),Output:["_col0","_col1","_col3","_col5","_col6","_col7"] + <-Reducer 16 [ONE_TO_ONE_EDGE] vectorized + FORWARD [RS_467] PartitionCols:_col0 - Select Operator [SEL_460] (rows=69 width=436) + Select Operator [SEL_466] (rows=15768 width=436) Output:["_col0","_col1","_col2","_col3"] - Group By Operator [GBY_459] (rows=69 width=212) + Group By Operator [GBY_465] (rows=15768 width=212) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 - <-Reducer 13 [SIMPLE_EDGE] - SHUFFLE [RS_144] + <-Reducer 15 [SIMPLE_EDGE] + SHUFFLE [RS_141] PartitionCols:_col0 - Group By Operator [GBY_143] (rows=69 width=212) - Output:["_col0","_col1"],aggregations:["sum(_col2)"],keys:_col4 - Merge Join Operator [MERGEJOIN_414] (rows=31537 width=100) - Conds:RS_139._col0=RS_140._col0(Inner),Output:["_col2","_col4"] - <-Reducer 16 [SIMPLE_EDGE] - SHUFFLE [RS_140] + Group By Operator [GBY_140] (rows=15768 width=212) + Output:["_col0","_col1"],aggregations:["sum(_col5)"],keys:_col7 + Merge Join Operator [MERGEJOIN_420] (rows=31537 width=100) + Conds:RS_136._col4=RS_450._col0(Inner),Output:["_col5","_col7"] + <-Map 25 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_450] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_403] (rows=2 width=4) - Conds:RS_419._col1=RS_435._col0(Inner),Output:["_col0"] - <-Map 15 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_419] - PartitionCols:_col1 - Select Operator [SEL_418] (rows=73049 width=98) - Output:["_col0","_col1"] - Filter Operator [FIL_417] (rows=73049 width=98) - predicate:d_date is not null - TableScan [TS_5] (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_435] + Select Operator [SEL_447] (rows=462000 width=104) + Output:["_col0","_col1"] + TableScan [TS_32] (rows=462000 width=104) + default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_item_id"] + <-Reducer 14 [SIMPLE_EDGE] + SHUFFLE [RS_136] + PartitionCols:_col4 + Merge Join Operator [MERGEJOIN_419] (rows=31537 width=4) + Conds:RS_133._col0=RS_464._col0(Inner),Output:["_col4","_col5"] + <-Reducer 2 [SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_133] PartitionCols:_col0 - Group By Operator [GBY_434] (rows=2 width=94) - Output:["_col0"],keys:KEY._col0 - <-Reducer 23 [SIMPLE_EDGE] - SHUFFLE [RS_31] + Merge Join Operator [MERGEJOIN_408] (rows=2 width=4) + Conds:RS_425._col1=RS_441._col0(Inner),Output:["_col0"] + <-Map 1 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_425] + PartitionCols:_col1 + Select Operator [SEL_424] (rows=73049 width=98) + Output:["_col0","_col1"] + Filter Operator [FIL_423] (rows=73049 width=98) + predicate:d_date is not null + TableScan [TS_0] (rows=73049 width=98) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_date"] + <-Reducer 22 [ONE_TO_ONE_EDGE] vectorized + FORWARD [RS_441] PartitionCols:_col0 - Group By Operator [GBY_30] (rows=2 width=94) - Output:["_col0"],keys:_col2 - Merge Join Operator [MERGEJOIN_402] (rows=5 width=94) - Conds:RS_26._col1=RS_432._col1(Inner),Output:["_col2"] - <-Map 25 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_432] - PartitionCols:_col1 - Select Operator [SEL_430] (rows=73049 width=98) - Output:["_col0","_col1"] - Filter Operator [FIL_428] (rows=73049 width=98) - predicate:(d_date is not null and d_week_seq is not null) - TableScan [TS_20] (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_26] - PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_401] (rows=1 width=4) - Conds:(Inner),Output:["_col1"] - <-Map 25 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_433] - Select Operator [SEL_431] (rows=1 width=4) - Output:["_col0"] - Filter Operator [FIL_429] (rows=1 width=98) - predicate:((d_date = '1998-02-19') and d_week_seq is not null) - Please refer to the previous TableScan [TS_20] - <-Reducer 21 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_427] - Select Operator [SEL_426] (rows=1 width=8) - Filter Operator [FIL_425] (rows=1 width=8) - predicate:(sq_count_check(_col0) <= 1) - Group By Operator [GBY_424] (rows=1 width=8) - Output:["_col0"],aggregations:["count(VALUE._col0)"] - <-Map 20 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_423] - Group By Operator [GBY_422] (rows=1 width=8) - Output:["_col0"],aggregations:["count()"] - Select Operator [SEL_421] (rows=1 width=94) - Filter Operator [FIL_420] (rows=1 width=94) - predicate:(d_date = '1998-02-19') - TableScan [TS_8] (rows=73049 width=94) - default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date"] - <-Reducer 12 [SIMPLE_EDGE] - SHUFFLE [RS_139] - PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_408] (rows=143966864 width=215) - Conds:RS_458._col1=RS_444._col0(Inner),Output:["_col0","_col2","_col4"] - <-Map 8 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_444] - PartitionCols:_col0 - Select Operator [SEL_441] (rows=462000 width=104) - Output:["_col0","_col1"] - TableScan [TS_3] (rows=462000 width=104) - default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_item_id"] + Group By Operator [GBY_440] (rows=2 width=94) + Output:["_col0"],keys:KEY._col0 + <-Reducer 21 [SIMPLE_EDGE] + SHUFFLE [RS_26] + PartitionCols:_col0 + Group By Operator [GBY_25] (rows=2 width=94) + Output:["_col0"],keys:_col2 + Merge Join Operator [MERGEJOIN_407] (rows=5 width=94) + Conds:RS_21._col1=RS_438._col1(Inner),Output:["_col2"] + <-Map 23 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_438] + PartitionCols:_col1 + Select Operator [SEL_436] (rows=73049 width=98) + Output:["_col0","_col1"] + Filter Operator [FIL_434] (rows=73049 width=98) + predicate:(d_date is not null and d_week_seq is not null) + TableScan [TS_15] (rows=73049 width=98) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date","d_week_seq"] + <-Reducer 20 [SIMPLE_EDGE] + SHUFFLE [RS_21] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_406] (rows=1 width=4) + Conds:(Inner),Output:["_col1"] + <-Map 23 [CUSTOM_SIMPLE_EDGE] vectorized + SHUFFLE [RS_439] + Select Operator [SEL_437] (rows=1 width=4) + Output:["_col0"] + Filter Operator [FIL_435] (rows=1 width=98) + predicate:((d_date = '1998-02-19') and d_week_seq is not null) + Please refer to the previous TableScan [TS_15] + <-Reducer 19 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_433] + Select Operator [SEL_432] (rows=1 width=8) + Filter Operator [FIL_431] (rows=1 width=8) + predicate:(sq_count_check(_col0) <= 1) + Group By Operator [GBY_430] (rows=1 width=8) + Output:["_col0"],aggregations:["count(VALUE._col0)"] + <-Map 18 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_429] + Group By Operator [GBY_428] (rows=1 width=8) + Output:["_col0"],aggregations:["count()"] + Select Operator [SEL_427] (rows=1 width=94) + Filter Operator [FIL_426] (rows=1 width=94) + predicate:(d_date = '1998-02-19') + TableScan [TS_3] (rows=73049 width=94) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date"] <-Map 27 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_458] - PartitionCols:_col1 - Select Operator [SEL_457] (rows=143966864 width=119) + SHUFFLE [RS_464] + PartitionCols:_col0 + Select Operator [SEL_463] (rows=143966864 width=119) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_456] (rows=143966864 width=119) - predicate:((ws_sold_date_sk BETWEEN DynamicValue(RS_140_date_dim_d_date_sk_min) AND DynamicValue(RS_140_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_140_date_dim_d_date_sk_bloom_filter))) and ws_sold_date_sk is not null) - TableScan [TS_98] (rows=144002668 width=119) + Filter Operator [FIL_462] (rows=143966864 width=119) + predicate:((ws_sold_date_sk BETWEEN DynamicValue(RS_133_date_dim_d_date_sk_min) AND DynamicValue(RS_133_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_133_date_dim_d_date_sk_bloom_filter))) and ws_sold_date_sk is not null) + TableScan [TS_125] (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_455] - Group By Operator [GBY_454] (rows=1 width=12) + <-Reducer 17 [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_360] - Group By Operator [GBY_359] (rows=1 width=12) + <-Reducer 2 [CUSTOM_SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_386] + Group By Operator [GBY_385] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_358] (rows=2 width=4) + Select Operator [SEL_384] (rows=2 width=4) Output:["_col0"] - Please refer to the previous Merge Join Operator [MERGEJOIN_403] - <-Reducer 5 [ONE_TO_ONE_EDGE] - FORWARD [RS_152] + Please refer to the previous Merge Join Operator [MERGEJOIN_408] + <-Reducer 6 [ONE_TO_ONE_EDGE] + FORWARD [RS_149] PartitionCols:_col0 - Filter Operator [FIL_150] (rows=1 width=324) + Filter Operator [FIL_147] (rows=384 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_415] (rows=68 width=324) - Conds:RS_446._col0=RS_453._col0(Inner),Output:["_col0","_col1","_col3"] - <-Reducer 11 [ONE_TO_ONE_EDGE] vectorized - FORWARD [RS_453] + Merge Join Operator [MERGEJOIN_421] (rows=31163 width=324) + Conds:RS_452._col0=RS_459._col0(Inner),Output:["_col0","_col1","_col3"] + <-Reducer 12 [ONE_TO_ONE_EDGE] vectorized + FORWARD [RS_459] PartitionCols:_col0 - Group By Operator [GBY_452] (rows=69 width=212) + Group By Operator [GBY_458] (rows=60249 width=212) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 - <-Reducer 10 [SIMPLE_EDGE] - SHUFFLE [RS_95] + <-Reducer 11 [SIMPLE_EDGE] + SHUFFLE [RS_93] PartitionCols:_col0 - Group By Operator [GBY_94] (rows=69 width=212) - Output:["_col0","_col1"],aggregations:["sum(_col2)"],keys:_col4 - Merge Join Operator [MERGEJOIN_413] (rows=120498 width=100) - Conds:RS_90._col0=RS_91._col0(Inner),Output:["_col2","_col4"] - <-Reducer 16 [SIMPLE_EDGE] - SHUFFLE [RS_91] + Group By Operator [GBY_92] (rows=60249 width=212) + Output:["_col0","_col1"],aggregations:["sum(_col5)"],keys:_col7 + Merge Join Operator [MERGEJOIN_415] (rows=120498 width=100) + Conds:RS_88._col4=RS_449._col0(Inner),Output:["_col5","_col7"] + <-Map 25 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_449] PartitionCols:_col0 - Please refer to the previous Merge Join Operator [MERGEJOIN_403] - <-Reducer 9 [SIMPLE_EDGE] - SHUFFLE [RS_90] - PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_404] (rows=550076554 width=210) - Conds:RS_451._col1=RS_443._col0(Inner),Output:["_col0","_col2","_col4"] - <-Map 8 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_443] + Please refer to the previous Select Operator [SEL_447] + <-Reducer 10 [SIMPLE_EDGE] + SHUFFLE [RS_88] + PartitionCols:_col4 + Merge Join Operator [MERGEJOIN_414] (rows=120498 width=4) + Conds:RS_85._col0=RS_457._col0(Inner),Output:["_col4","_col5"] + <-Reducer 2 [SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_85] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_441] + Please refer to the previous Merge Join Operator [MERGEJOIN_408] <-Map 26 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_451] - PartitionCols:_col1 - Select Operator [SEL_450] (rows=550076554 width=114) + SHUFFLE [RS_457] + PartitionCols:_col0 + Select Operator [SEL_456] (rows=550076554 width=114) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_449] (rows=550076554 width=114) - predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_91_date_dim_d_date_sk_min) AND DynamicValue(RS_91_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_91_date_dim_d_date_sk_bloom_filter))) and ss_sold_date_sk is not null) - TableScan [TS_49] (rows=575995635 width=114) + Filter Operator [FIL_455] (rows=550076554 width=114) + predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_85_date_dim_d_date_sk_min) AND DynamicValue(RS_85_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_85_date_dim_d_date_sk_bloom_filter))) and ss_sold_date_sk is not null) + TableScan [TS_77] (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_448] - Group By Operator [GBY_447] (rows=1 width=12) + <-Reducer 13 [BROADCAST_EDGE] vectorized + BROADCAST [RS_454] + Group By Operator [GBY_453] (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_314] - Group By Operator [GBY_313] (rows=1 width=12) + <-Reducer 2 [CUSTOM_SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_340] + Group By Operator [GBY_339] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_312] (rows=2 width=4) + Select Operator [SEL_338] (rows=2 width=4) Output:["_col0"] - Please refer to the previous Merge Join Operator [MERGEJOIN_403] - <-Reducer 4 [ONE_TO_ONE_EDGE] vectorized - FORWARD [RS_446] + Please refer to the previous Merge Join Operator [MERGEJOIN_408] + <-Reducer 5 [ONE_TO_ONE_EDGE] vectorized + FORWARD [RS_452] PartitionCols:_col0 - Group By Operator [GBY_445] (rows=68 width=212) + Group By Operator [GBY_451] (rows=31163 width=212) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 - <-Reducer 3 [SIMPLE_EDGE] - SHUFFLE [RS_46] + <-Reducer 4 [SIMPLE_EDGE] + SHUFFLE [RS_45] PartitionCols:_col0 - Group By Operator [GBY_45] (rows=68 width=212) - Output:["_col0","_col1"],aggregations:["sum(_col2)"],keys:_col4 - Merge Join Operator [MERGEJOIN_412] (rows=62327 width=100) - Conds:RS_41._col0=RS_42._col0(Inner),Output:["_col2","_col4"] - <-Reducer 16 [SIMPLE_EDGE] - SHUFFLE [RS_42] - PartitionCols:_col0 - Please refer to the previous Merge Join Operator [MERGEJOIN_403] - <-Reducer 2 [SIMPLE_EDGE] - SHUFFLE [RS_41] + Group By Operator [GBY_44] (rows=31163 width=212) + Output:["_col0","_col1"],aggregations:["sum(_col5)"],keys:_col7 + Merge Join Operator [MERGEJOIN_410] (rows=62327 width=100) + Conds:RS_40._col4=RS_448._col0(Inner),Output:["_col5","_col7"] + <-Map 25 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_448] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_400] (rows=286549727 width=215) - Conds:RS_440._col1=RS_442._col0(Inner),Output:["_col0","_col2","_col4"] - <-Map 8 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_442] + Please refer to the previous Select Operator [SEL_447] + <-Reducer 3 [SIMPLE_EDGE] + SHUFFLE [RS_40] + PartitionCols:_col4 + Merge Join Operator [MERGEJOIN_409] (rows=62327 width=4) + Conds:RS_37._col0=RS_446._col0(Inner),Output:["_col4","_col5"] + <-Reducer 2 [SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_37] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_441] - <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_440] - PartitionCols:_col1 - Select Operator [SEL_439] (rows=286549727 width=119) + Please refer to the previous Merge Join Operator [MERGEJOIN_408] + <-Map 24 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_446] + PartitionCols:_col0 + Select Operator [SEL_445] (rows=286549727 width=119) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_438] (rows=286549727 width=119) - predicate:((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_sold_date_sk is not null) - TableScan [TS_0] (rows=287989836 width=119) + Filter Operator [FIL_444] (rows=286549727 width=119) + predicate:((cs_sold_date_sk BETWEEN DynamicValue(RS_37_date_dim_d_date_sk_min) AND DynamicValue(RS_37_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_37_date_dim_d_date_sk_bloom_filter))) and cs_sold_date_sk is not null) + TableScan [TS_29] (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_437] - Group By Operator [GBY_436] (rows=1 width=12) + <-Reducer 9 [BROADCAST_EDGE] vectorized + BROADCAST [RS_443] + Group By Operator [GBY_442] (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_264] - Group By Operator [GBY_263] (rows=1 width=12) + <-Reducer 2 [CUSTOM_SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_290] + Group By Operator [GBY_289] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_262] (rows=2 width=4) + Select Operator [SEL_288] (rows=2 width=4) Output:["_col0"] - Please refer to the previous Merge Join Operator [MERGEJOIN_403] + Please refer to the previous Merge Join Operator [MERGEJOIN_408] diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/query6.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/query6.q.out index 74bec5cf17..137f898296 100644 --- a/ql/src/test/results/clientpositive/perf/tez/constraints/query6.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/query6.q.out @@ -1,4 +1,4 @@ -Warning: Map Join MAPJOIN[170][bigTable=?] in task 'Reducer 15' is a cross product +Warning: Map Join MAPJOIN[171][bigTable=?] in task 'Reducer 6' is a cross product PREHOOK: query: explain select a.ca_state state, count(*) cnt from customer_address a @@ -64,173 +64,175 @@ POSTHOOK: Output: hdfs://### HDFS PATH ### Plan optimized by CBO. Vertex dependency in root stage -Map 1 <- Reducer 3 (BROADCAST_EDGE) -Map 16 <- Reducer 15 (BROADCAST_EDGE) -Map 6 <- Map 1 (BROADCAST_EDGE), Reducer 17 (BROADCAST_EDGE) -Reducer 10 <- Reducer 9 (SIMPLE_EDGE) -Reducer 12 <- Map 11 (SIMPLE_EDGE), Map 13 (SIMPLE_EDGE) -Reducer 15 <- Map 14 (SIMPLE_EDGE), Reducer 5 (BROADCAST_EDGE) +Map 1 <- Reducer 12 (BROADCAST_EDGE), Reducer 17 (BROADCAST_EDGE) +Map 11 <- Reducer 6 (BROADCAST_EDGE) +Map 13 <- Map 16 (BROADCAST_EDGE), Reducer 3 (BROADCAST_EDGE) +Map 16 <- Reducer 10 (BROADCAST_EDGE) +Reducer 10 <- Map 7 (SIMPLE_EDGE) +Reducer 12 <- Map 11 (CUSTOM_SIMPLE_EDGE) +Reducer 14 <- Map 13 (SIMPLE_EDGE) +Reducer 15 <- Reducer 14 (SIMPLE_EDGE) Reducer 17 <- Map 16 (CUSTOM_SIMPLE_EDGE) -Reducer 3 <- Map 2 (SIMPLE_EDGE) -Reducer 4 <- Map 2 (SIMPLE_EDGE) -Reducer 5 <- Reducer 4 (CUSTOM_SIMPLE_EDGE) -Reducer 7 <- Map 6 (SIMPLE_EDGE), Reducer 12 (SIMPLE_EDGE) -Reducer 8 <- Map 16 (SIMPLE_EDGE), Reducer 7 (SIMPLE_EDGE) -Reducer 9 <- Reducer 8 (SIMPLE_EDGE) +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) +Reducer 3 <- Map 11 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) +Reducer 6 <- Map 5 (SIMPLE_EDGE), Reducer 9 (BROADCAST_EDGE) +Reducer 8 <- Map 7 (SIMPLE_EDGE) +Reducer 9 <- Reducer 8 (CUSTOM_SIMPLE_EDGE) Stage-0 Fetch Operator limit:100 Stage-1 - Reducer 10 vectorized - File Output Operator [FS_232] - Limit [LIM_231] (rows=1 width=94) + Reducer 15 vectorized + File Output Operator [FS_243] + Limit [LIM_242] (rows=1 width=94) Number of rows:100 - Select Operator [SEL_230] (rows=1 width=94) + Select Operator [SEL_241] (rows=1 width=94) Output:["_col0","_col1"] - <-Reducer 9 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_229] - Filter Operator [FIL_228] (rows=1 width=94) + <-Reducer 14 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_240] + Filter Operator [FIL_239] (rows=1 width=94) predicate:(_col1 >= 10L) - Group By Operator [GBY_227] (rows=1 width=94) + Group By Operator [GBY_238] (rows=1 width=94) Output:["_col0","_col1"],aggregations:["count(VALUE._col0)"],keys:KEY._col0 - <-Reducer 8 [SIMPLE_EDGE] - SHUFFLE [RS_68] + <-Map 13 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_237] PartitionCols:_col0 - Group By Operator [GBY_67] (rows=1 width=94) - Output:["_col0","_col1"],aggregations:["count()"],keys:_col9 - Merge Join Operator [MERGEJOIN_173] (rows=316 width=86) - Conds:RS_63._col4=RS_212._col0(Inner),Output:["_col9"] - <-Map 16 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_212] + Group By Operator [GBY_236] (rows=1 width=94) + Output:["_col0","_col1"],aggregations:["count()"],keys:_col12 + Map Join Operator [MAPJOIN_235] (rows=316 width=86) + Conds:MAPJOIN_234._col0=RS_221._col0(Inner),HybridGraceHashJoin:true,Output:["_col12"] + <-Map 16 [BROADCAST_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_221] PartitionCols:_col0 - Select Operator [SEL_211] (rows=154000 width=227) - Output:["_col0"] - Filter Operator [FIL_210] (rows=154000 width=227) - predicate:(_col4 > _col1) - Map Join Operator [MAPJOIN_209] (rows=462000 width=227) - Conds:RS_206._col0=SEL_208._col2(Inner),HybridGraceHashJoin:true,Output:["_col1","_col3","_col4"] - <-Reducer 15 [BROADCAST_EDGE] vectorized - BROADCAST [RS_206] - PartitionCols:_col0 - Map Join Operator [MAPJOIN_205] (rows=10 width=202) - Conds:(Inner),Output:["_col0","_col1"] - <-Reducer 5 [BROADCAST_EDGE] vectorized - BROADCAST [RS_202] - Select Operator [SEL_201] (rows=1 width=8) - Filter Operator [FIL_200] (rows=1 width=8) - predicate:(sq_count_check(_col0) <= 1) - Group By Operator [GBY_199] (rows=1 width=8) - Output:["_col0"],aggregations:["count(VALUE._col0)"] - <-Reducer 4 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_198] - Group By Operator [GBY_197] (rows=1 width=8) - Output:["_col0"],aggregations:["count()"] - Select Operator [SEL_196] (rows=25 width=4) - Group By Operator [GBY_195] (rows=25 width=4) - Output:["_col0"],keys:KEY._col0 - <-Map 2 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_185] - PartitionCols:_col0 - Group By Operator [GBY_183] (rows=25 width=4) - Output:["_col0"],keys:d_month_seq - Select Operator [SEL_181] (rows=50 width=12) - Output:["d_month_seq"] - Filter Operator [FIL_179] (rows=50 width=12) - predicate:((d_moy = 2) and (d_year = 2000)) - TableScan [TS_3] (rows=73049 width=12) - default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_month_seq","d_year","d_moy"] - <-Select Operator [SEL_204] (rows=10 width=202) - Output:["_col0","_col1"] - Group By Operator [GBY_203] (rows=10 width=210) - Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)","count(VALUE._col1)"],keys:KEY._col0 - <-Map 14 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_194] - PartitionCols:_col0 - Group By Operator [GBY_193] (rows=10 width=210) - Output:["_col0","_col1","_col2"],aggregations:["sum(i_current_price)","count(i_current_price)"],keys:i_category - Filter Operator [FIL_192] (rows=462000 width=201) - predicate:i_category is not null - TableScan [TS_22] (rows=462000 width=201) - default@item,j,Tbl:COMPLETE,Col:COMPLETE,Output:["i_current_price","i_category"] - <-Select Operator [SEL_208] (rows=462000 width=205) - Output:["_col0","_col1","_col2"] - Filter Operator [FIL_207] (rows=462000 width=205) - predicate:i_category is not null - TableScan [TS_43] (rows=462000 width=205) - default@item,i,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_current_price","i_category"] - <-Reducer 7 [SIMPLE_EDGE] - SHUFFLE [RS_63] - PartitionCols:_col4 - Merge Join Operator [MERGEJOIN_172] (rows=7192227 width=90) - Conds:RS_221._col5=RS_61._col0(Inner),Output:["_col4","_col9"] - <-Map 6 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_221] - PartitionCols:_col5 - Map Join Operator [MAPJOIN_220] (rows=7192227 width=4) - Conds:RS_191._col0=SEL_219._col0(Inner),HybridGraceHashJoin:true,Output:["_col4","_col5"] - <-Map 1 [BROADCAST_EDGE] vectorized - BROADCAST [RS_191] - PartitionCols:_col0 - Map Join Operator [MAPJOIN_190] (rows=660 width=4) - Conds:SEL_189._col1=RS_187._col0(Inner),HybridGraceHashJoin:true,Output:["_col0"] - <-Reducer 3 [BROADCAST_EDGE] vectorized - BROADCAST [RS_187] - PartitionCols:_col0 - Group By Operator [GBY_186] (rows=25 width=4) - Output:["_col0"],keys:KEY._col0 - <-Map 2 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_184] - PartitionCols:_col0 - Group By Operator [GBY_182] (rows=25 width=4) - Output:["_col0"],keys:d_month_seq - Select Operator [SEL_180] (rows=50 width=12) - Output:["d_month_seq"] - Filter Operator [FIL_178] (rows=50 width=12) - predicate:((d_moy = 2) and (d_year = 2000) and d_month_seq is not null) - Please refer to the previous TableScan [TS_3] - <-Select Operator [SEL_189] (rows=73049 width=8) - Output:["_col0","_col1"] - Filter Operator [FIL_188] (rows=73049 width=8) - predicate:d_month_seq is not null - TableScan [TS_0] (rows=73049 width=8) - default@date_dim,d,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_month_seq"] - <-Select Operator [SEL_219] (rows=525327388 width=11) - Output:["_col0","_col1","_col2"] - Filter Operator [FIL_218] (rows=525327388 width=11) - predicate:((ss_item_sk BETWEEN DynamicValue(RS_64_i_i_item_sk_min) AND DynamicValue(RS_64_i_i_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_64_i_i_item_sk_bloom_filter))) and ss_customer_sk is not null and ss_sold_date_sk is not null) - TableScan [TS_10] (rows=575995635 width=11) - default@store_sales,s,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_item_sk","ss_customer_sk"] - <-Reducer 17 [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 16 [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=154000 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_211] - <-Reducer 12 [SIMPLE_EDGE] - SHUFFLE [RS_61] + Map Join Operator [MAPJOIN_220] (rows=660 width=4) + Conds:SEL_219._col1=RS_217._col0(Inner),HybridGraceHashJoin:true,Output:["_col0"] + <-Reducer 10 [BROADCAST_EDGE] vectorized + BROADCAST [RS_217] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_169] (rows=80000000 width=90) - Conds:RS_224._col1=RS_226._col0(Inner),Output:["_col0","_col3"] - <-Map 11 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_224] - PartitionCols:_col1 - Select Operator [SEL_223] (rows=80000000 width=8) - Output:["_col0","_col1"] - Filter Operator [FIL_222] (rows=80000000 width=8) - predicate:c_current_addr_sk is not null - TableScan [TS_13] (rows=80000000 width=8) - default@customer,c,Tbl:COMPLETE,Col:COMPLETE,Output:["c_customer_sk","c_current_addr_sk"] - <-Map 13 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_226] + Group By Operator [GBY_216] (rows=25 width=4) + Output:["_col0"],keys:KEY._col0 + <-Map 7 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_192] PartitionCols:_col0 - Select Operator [SEL_225] (rows=40000000 width=90) - Output:["_col0","_col1"] - TableScan [TS_16] (rows=40000000 width=90) - default@customer_address,a,Tbl:COMPLETE,Col:COMPLETE,Output:["ca_address_sk","ca_state"] + Group By Operator [GBY_190] (rows=25 width=4) + Output:["_col0"],keys:d_month_seq + Select Operator [SEL_188] (rows=50 width=12) + Output:["d_month_seq"] + Filter Operator [FIL_186] (rows=50 width=12) + predicate:((d_moy = 2) and (d_year = 2000) and d_month_seq is not null) + TableScan [TS_13] (rows=73049 width=12) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_month_seq","d_year","d_moy"] + <-Select Operator [SEL_219] (rows=73049 width=8) + Output:["_col0","_col1"] + Filter Operator [FIL_218] (rows=73049 width=8) + predicate:d_month_seq is not null + TableScan [TS_40] (rows=73049 width=8) + default@date_dim,d,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_month_seq"] + <-Map Join Operator [MAPJOIN_234] (rows=23073 width=86) + Conds:RS_60._col4=SEL_233._col0(Inner),HybridGraceHashJoin:true,Output:["_col0","_col12"] + <-Reducer 3 [BROADCAST_EDGE] + BROADCAST [RS_60] + PartitionCols:_col4 + Merge Join Operator [MERGEJOIN_173] (rows=23073 width=4) + Conds:RS_57._col1=RS_210._col0(Inner),Output:["_col0","_col4"] + <-Map 11 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_210] + PartitionCols:_col0 + Select Operator [SEL_209] (rows=154000 width=227) + Output:["_col0"] + Filter Operator [FIL_208] (rows=154000 width=227) + predicate:(_col4 > _col1) + Map Join Operator [MAPJOIN_207] (rows=462000 width=227) + Conds:RS_204._col0=SEL_206._col2(Inner),HybridGraceHashJoin:true,Output:["_col1","_col3","_col4"] + <-Reducer 6 [BROADCAST_EDGE] vectorized + BROADCAST [RS_204] + PartitionCols:_col0 + Map Join Operator [MAPJOIN_203] (rows=10 width=202) + Conds:(Inner),Output:["_col0","_col1"] + <-Reducer 9 [BROADCAST_EDGE] vectorized + BROADCAST [RS_200] + Select Operator [SEL_199] (rows=1 width=8) + Filter Operator [FIL_198] (rows=1 width=8) + predicate:(sq_count_check(_col0) <= 1) + Group By Operator [GBY_197] (rows=1 width=8) + Output:["_col0"],aggregations:["count(VALUE._col0)"] + <-Reducer 8 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_196] + Group By Operator [GBY_195] (rows=1 width=8) + Output:["_col0"],aggregations:["count()"] + Select Operator [SEL_194] (rows=25 width=4) + Group By Operator [GBY_193] (rows=25 width=4) + Output:["_col0"],keys:KEY._col0 + <-Map 7 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_191] + PartitionCols:_col0 + Group By Operator [GBY_189] (rows=25 width=4) + Output:["_col0"],keys:d_month_seq + Select Operator [SEL_187] (rows=50 width=12) + Output:["d_month_seq"] + Filter Operator [FIL_185] (rows=50 width=12) + predicate:((d_moy = 2) and (d_year = 2000)) + Please refer to the previous TableScan [TS_13] + <-Select Operator [SEL_202] (rows=10 width=202) + Output:["_col0","_col1"] + Group By Operator [GBY_201] (rows=10 width=210) + Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)","count(VALUE._col1)"],keys:KEY._col0 + <-Map 5 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_184] + PartitionCols:_col0 + Group By Operator [GBY_183] (rows=10 width=210) + Output:["_col0","_col1","_col2"],aggregations:["sum(i_current_price)","count(i_current_price)"],keys:i_category + Filter Operator [FIL_182] (rows=462000 width=201) + predicate:i_category is not null + TableScan [TS_6] (rows=462000 width=201) + default@item,j,Tbl:COMPLETE,Col:COMPLETE,Output:["i_current_price","i_category"] + <-Select Operator [SEL_206] (rows=462000 width=205) + Output:["_col0","_col1","_col2"] + Filter Operator [FIL_205] (rows=462000 width=205) + predicate:i_category is not null + TableScan [TS_27] (rows=462000 width=205) + default@item,i,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_current_price","i_category"] + <-Reducer 2 [SIMPLE_EDGE] + SHUFFLE [RS_57] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_170] (rows=525327388 width=11) + Conds:RS_229._col2=RS_232._col0(Inner),Output:["_col0","_col1","_col4"] + <-Map 1 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_229] + PartitionCols:_col2 + Select Operator [SEL_228] (rows=525327388 width=11) + Output:["_col0","_col1","_col2"] + Filter Operator [FIL_227] (rows=525327388 width=11) + predicate:((ss_item_sk BETWEEN DynamicValue(RS_58_i_i_item_sk_min) AND DynamicValue(RS_58_i_i_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_58_i_i_item_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_64_d_d_date_sk_min) AND DynamicValue(RS_64_d_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_64_d_d_date_sk_bloom_filter))) and ss_customer_sk is not null and ss_sold_date_sk is not null) + TableScan [TS_0] (rows=575995635 width=11) + default@store_sales,s,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_item_sk","ss_customer_sk"] + <-Reducer 12 [BROADCAST_EDGE] vectorized + BROADCAST [RS_215] + Group By Operator [GBY_214] (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_213] + Group By Operator [GBY_212] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_211] (rows=154000 width=4) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_209] + <-Reducer 17 [BROADCAST_EDGE] vectorized + BROADCAST [RS_226] + Group By Operator [GBY_225] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 4 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_232] + PartitionCols:_col0 + Select Operator [SEL_231] (rows=80000000 width=8) + Output:["_col0","_col1"] + Filter Operator [FIL_230] (rows=80000000 width=8) + predicate:c_current_addr_sk is not null + TableScan [TS_3] (rows=80000000 width=8) + default@customer,c,Tbl:COMPLETE,Col:COMPLETE,Output:["c_customer_sk","c_current_addr_sk"] + <-Select Operator [SEL_233] (rows=40000000 width=90) + Output:["_col0","_col1"] + TableScan [TS_38] (rows=40000000 width=90) + default@customer_address,a,Tbl:COMPLETE,Col:COMPLETE,Output:["ca_address_sk","ca_state"] diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/query64.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/query64.q.out index d741dfd1ee..8f6da18182 100644 --- a/ql/src/test/results/clientpositive/perf/tez/constraints/query64.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/query64.q.out @@ -265,502 +265,532 @@ POSTHOOK: Output: hdfs://### HDFS PATH ### Plan optimized by CBO. Vertex dependency in root stage -Map 25 <- Reducer 30 (BROADCAST_EDGE), Reducer 36 (BROADCAST_EDGE), Reducer 42 (BROADCAST_EDGE) -Map 39 <- Reducer 30 (BROADCAST_EDGE) -Map 51 <- Reducer 16 (BROADCAST_EDGE), Reducer 34 (BROADCAST_EDGE), Reducer 37 (BROADCAST_EDGE), Reducer 46 (BROADCAST_EDGE) -Map 52 <- Reducer 34 (BROADCAST_EDGE) -Reducer 10 <- Map 48 (SIMPLE_EDGE), Reducer 9 (SIMPLE_EDGE) -Reducer 11 <- Map 49 (SIMPLE_EDGE), Reducer 10 (SIMPLE_EDGE) -Reducer 12 <- Map 50 (SIMPLE_EDGE), Reducer 11 (SIMPLE_EDGE) -Reducer 13 <- Reducer 12 (SIMPLE_EDGE) -Reducer 14 <- Reducer 13 (SIMPLE_EDGE), Reducer 24 (SIMPLE_EDGE) -Reducer 15 <- Reducer 14 (SIMPLE_EDGE) -Reducer 16 <- Reducer 13 (CUSTOM_SIMPLE_EDGE) -Reducer 17 <- Reducer 33 (SIMPLE_EDGE), Reducer 5 (SIMPLE_EDGE) -Reducer 18 <- Map 38 (SIMPLE_EDGE), Reducer 17 (SIMPLE_EDGE) -Reducer 19 <- Reducer 18 (SIMPLE_EDGE), Reducer 45 (ONE_TO_ONE_EDGE) +Map 30 <- Reducer 34 (BROADCAST_EDGE), Reducer 39 (BROADCAST_EDGE), Reducer 44 (BROADCAST_EDGE) +Map 41 <- Reducer 34 (BROADCAST_EDGE) +Map 54 <- Reducer 17 (BROADCAST_EDGE), Reducer 37 (BROADCAST_EDGE), Reducer 40 (BROADCAST_EDGE), Reducer 48 (BROADCAST_EDGE) +Map 55 <- Reducer 37 (BROADCAST_EDGE) +Reducer 10 <- Map 52 (SIMPLE_EDGE), Reducer 9 (SIMPLE_EDGE) +Reducer 11 <- Map 52 (SIMPLE_EDGE), Reducer 10 (SIMPLE_EDGE) +Reducer 12 <- Map 53 (SIMPLE_EDGE), Reducer 11 (SIMPLE_EDGE) +Reducer 13 <- Map 53 (SIMPLE_EDGE), Reducer 12 (SIMPLE_EDGE) +Reducer 14 <- Reducer 13 (SIMPLE_EDGE) +Reducer 15 <- Reducer 14 (SIMPLE_EDGE), Reducer 29 (SIMPLE_EDGE) +Reducer 16 <- Reducer 15 (SIMPLE_EDGE) +Reducer 17 <- Reducer 14 (CUSTOM_SIMPLE_EDGE) +Reducer 18 <- Reducer 2 (SIMPLE_EDGE), Reducer 36 (SIMPLE_EDGE) +Reducer 19 <- Reducer 18 (SIMPLE_EDGE), Reducer 47 (ONE_TO_ONE_EDGE) Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 49 (SIMPLE_EDGE) -Reducer 20 <- Map 47 (SIMPLE_EDGE), Reducer 19 (SIMPLE_EDGE) -Reducer 21 <- Map 48 (SIMPLE_EDGE), Reducer 20 (SIMPLE_EDGE) -Reducer 22 <- Map 49 (SIMPLE_EDGE), Reducer 21 (SIMPLE_EDGE) -Reducer 23 <- Map 50 (SIMPLE_EDGE), Reducer 22 (SIMPLE_EDGE) -Reducer 24 <- Reducer 23 (SIMPLE_EDGE) -Reducer 26 <- Map 25 (SIMPLE_EDGE), Map 29 (SIMPLE_EDGE) -Reducer 27 <- Map 35 (SIMPLE_EDGE), Reducer 26 (SIMPLE_EDGE) -Reducer 28 <- Map 38 (SIMPLE_EDGE), Reducer 27 (SIMPLE_EDGE) -Reducer 3 <- Map 47 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) -Reducer 30 <- Map 29 (CUSTOM_SIMPLE_EDGE) -Reducer 31 <- Map 29 (SIMPLE_EDGE), Map 51 (SIMPLE_EDGE) -Reducer 32 <- Map 35 (SIMPLE_EDGE), Reducer 31 (SIMPLE_EDGE) -Reducer 33 <- Map 38 (SIMPLE_EDGE), Reducer 32 (SIMPLE_EDGE) -Reducer 34 <- Map 29 (CUSTOM_SIMPLE_EDGE) -Reducer 36 <- Map 35 (CUSTOM_SIMPLE_EDGE) -Reducer 37 <- Map 35 (CUSTOM_SIMPLE_EDGE) -Reducer 4 <- Map 35 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) -Reducer 40 <- Map 39 (SIMPLE_EDGE), Map 43 (SIMPLE_EDGE) -Reducer 41 <- Reducer 40 (SIMPLE_EDGE) -Reducer 42 <- Reducer 41 (CUSTOM_SIMPLE_EDGE) -Reducer 44 <- Map 43 (SIMPLE_EDGE), Map 52 (SIMPLE_EDGE) -Reducer 45 <- Reducer 44 (SIMPLE_EDGE) -Reducer 46 <- Reducer 45 (CUSTOM_SIMPLE_EDGE) -Reducer 5 <- Map 35 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) -Reducer 6 <- Reducer 28 (SIMPLE_EDGE), Reducer 5 (SIMPLE_EDGE) -Reducer 7 <- Map 38 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE) -Reducer 8 <- Reducer 41 (ONE_TO_ONE_EDGE), Reducer 7 (SIMPLE_EDGE) -Reducer 9 <- Map 47 (SIMPLE_EDGE), Reducer 8 (SIMPLE_EDGE) +Reducer 20 <- Map 49 (SIMPLE_EDGE), Reducer 19 (SIMPLE_EDGE) +Reducer 21 <- Map 50 (SIMPLE_EDGE), Reducer 20 (SIMPLE_EDGE) +Reducer 22 <- Map 51 (SIMPLE_EDGE), Reducer 21 (SIMPLE_EDGE) +Reducer 23 <- Map 38 (SIMPLE_EDGE), Reducer 22 (SIMPLE_EDGE) +Reducer 24 <- Map 38 (SIMPLE_EDGE), Reducer 23 (SIMPLE_EDGE) +Reducer 25 <- Map 52 (SIMPLE_EDGE), Reducer 24 (SIMPLE_EDGE) +Reducer 26 <- Map 52 (SIMPLE_EDGE), Reducer 25 (SIMPLE_EDGE) +Reducer 27 <- Map 53 (SIMPLE_EDGE), Reducer 26 (SIMPLE_EDGE) +Reducer 28 <- Map 53 (SIMPLE_EDGE), Reducer 27 (SIMPLE_EDGE) +Reducer 29 <- Reducer 28 (SIMPLE_EDGE) +Reducer 3 <- Reducer 2 (SIMPLE_EDGE), Reducer 32 (SIMPLE_EDGE) +Reducer 31 <- Map 30 (SIMPLE_EDGE), Map 33 (SIMPLE_EDGE) +Reducer 32 <- Map 38 (SIMPLE_EDGE), Reducer 31 (SIMPLE_EDGE) +Reducer 34 <- Map 33 (CUSTOM_SIMPLE_EDGE) +Reducer 35 <- Map 33 (SIMPLE_EDGE), Map 54 (SIMPLE_EDGE) +Reducer 36 <- Map 38 (SIMPLE_EDGE), Reducer 35 (SIMPLE_EDGE) +Reducer 37 <- Map 33 (CUSTOM_SIMPLE_EDGE) +Reducer 39 <- Map 38 (CUSTOM_SIMPLE_EDGE) +Reducer 4 <- Reducer 3 (SIMPLE_EDGE), Reducer 43 (ONE_TO_ONE_EDGE) +Reducer 40 <- Map 38 (CUSTOM_SIMPLE_EDGE) +Reducer 42 <- Map 41 (SIMPLE_EDGE), Map 45 (SIMPLE_EDGE) +Reducer 43 <- Reducer 42 (SIMPLE_EDGE) +Reducer 44 <- Reducer 43 (CUSTOM_SIMPLE_EDGE) +Reducer 46 <- Map 45 (SIMPLE_EDGE), Map 55 (SIMPLE_EDGE) +Reducer 47 <- Reducer 46 (SIMPLE_EDGE) +Reducer 48 <- Reducer 47 (CUSTOM_SIMPLE_EDGE) +Reducer 5 <- Map 49 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) +Reducer 6 <- Map 50 (SIMPLE_EDGE), Reducer 5 (SIMPLE_EDGE) +Reducer 7 <- Map 51 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE) +Reducer 8 <- Map 38 (SIMPLE_EDGE), Reducer 7 (SIMPLE_EDGE) +Reducer 9 <- Map 38 (SIMPLE_EDGE), Reducer 8 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 - Reducer 15 vectorized - File Output Operator [FS_1045] - Select Operator [SEL_1044] (rows=732552381 width=1702) + Reducer 16 vectorized + File Output Operator [FS_1080] + Select Operator [SEL_1079] (rows=1991254249 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 14 [SIMPLE_EDGE] + <-Reducer 15 [SIMPLE_EDGE] SHUFFLE [RS_199] - Select Operator [SEL_198] (rows=732552381 width=1694) + Select Operator [SEL_198] (rows=1991254249 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_197] (rows=732552381 width=1694) + Filter Operator [FIL_197] (rows=1991254249 width=1694) predicate:(_col19 <= _col12) - Merge Join Operator [MERGEJOIN_939] (rows=2197657144 width=1694) - Conds:RS_1015._col2, _col1, _col3=RS_1043._col1, _col0, _col2(Inner),Output:["_col0","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col19","_col20","_col21","_col22"] - <-Reducer 13 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_1015] + Merge Join Operator [MERGEJOIN_969] (rows=5973762748 width=1694) + Conds:RS_1050._col2, _col1, _col3=RS_1078._col1, _col0, _col2(Inner),Output:["_col0","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col19","_col20","_col21","_col22"] + <-Reducer 14 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_1050] PartitionCols:_col2, _col1, _col3 - Select Operator [SEL_1014] (rows=1434227 width=1354) + Select Operator [SEL_1049] (rows=2364623 width=1354) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15"] - Group By Operator [GBY_1013] (rows=1434227 width=1362) + Group By Operator [GBY_1048] (rows=2364623 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 12 [SIMPLE_EDGE] + <-Reducer 13 [SIMPLE_EDGE] SHUFFLE [RS_94] PartitionCols:_col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 - Group By Operator [GBY_93] (rows=1434227 width=1362) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17"],aggregations:["count()","sum(_col26)","sum(_col27)","sum(_col28)"],keys:_col37, _col29, _col38, _col40, _col41, _col42, _col43, _col7, _col8, _col9, _col10, _col13, _col15, _col30 - Merge Join Operator [MERGEJOIN_923] (rows=2364621 width=1153) - Conds:RS_89._col19, _col25=RS_1011._col0, _col1(Inner),Output:["_col7","_col8","_col9","_col10","_col13","_col15","_col26","_col27","_col28","_col29","_col30","_col37","_col38","_col40","_col41","_col42","_col43"] - <-Map 50 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1011] - PartitionCols:_col0, _col1 - Select Operator [SEL_1010] (rows=57591150 width=8) - Output:["_col0","_col1"] - TableScan [TS_56] (rows=57591150 width=8) - default@store_returns,store_returns,Tbl:COMPLETE,Col:COMPLETE,Output:["sr_item_sk","sr_ticket_number"] - <-Reducer 11 [SIMPLE_EDGE] + Group By Operator [GBY_93] (rows=2364623 width=1362) + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17"],aggregations:["count()","sum(_col15)","sum(_col16)","sum(_col17)"],keys:_col24, _col18, _col25, _col19, _col29, _col31, _col37, _col38, _col39, _col40, _col42, _col43, _col44, _col45 + Merge Join Operator [MERGEJOIN_953] (rows=2364623 width=1155) + Conds:RS_89._col3=RS_1045._col0(Inner),Output:["_col15","_col16","_col17","_col18","_col19","_col24","_col25","_col29","_col31","_col37","_col38","_col39","_col40","_col42","_col43","_col44","_col45"] + <-Map 53 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_1045] + PartitionCols:_col0 + Select Operator [SEL_1043] (rows=40000000 width=365) + Output:["_col0","_col1","_col2","_col3","_col4"] + TableScan [TS_51] (rows=40000000 width=365) + default@customer_address,ad1,Tbl:COMPLETE,Col:COMPLETE,Output:["ca_address_sk","ca_street_number","ca_street_name","ca_city","ca_zip"] + <-Reducer 12 [SIMPLE_EDGE] SHUFFLE [RS_89] - PartitionCols:_col19, _col25 - Merge Join Operator [MERGEJOIN_922] (rows=1434227 width=1030) - Conds:RS_86._col23=RS_944._col0(Inner),Output:["_col7","_col8","_col9","_col10","_col13","_col15","_col19","_col25","_col26","_col27","_col28","_col29","_col30","_col37","_col38","_col40","_col41","_col42","_col43"] - <-Map 49 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_944] + PartitionCols:_col3 + Merge Join Operator [MERGEJOIN_952] (rows=2364623 width=798) + Conds:RS_86._col12=RS_1044._col0(Inner),Output:["_col3","_col15","_col16","_col17","_col18","_col19","_col24","_col25","_col29","_col31","_col37","_col38","_col39","_col40"] + <-Map 53 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_1044] PartitionCols:_col0 - Select Operator [SEL_943] (rows=40000000 width=365) - Output:["_col0","_col1","_col2","_col3","_col4"] - TableScan [TS_54] (rows=40000000 width=365) - default@customer_address,ad1,Tbl:COMPLETE,Col:COMPLETE,Output:["ca_address_sk","ca_street_number","ca_street_name","ca_city","ca_zip"] - <-Reducer 10 [SIMPLE_EDGE] + Please refer to the previous Select Operator [SEL_1043] + <-Reducer 11 [SIMPLE_EDGE] SHUFFLE [RS_86] - PartitionCols:_col23 - Merge Join Operator [MERGEJOIN_921] (rows=1434227 width=669) - Conds:RS_83._col24=RS_1008._col0(Inner),Output:["_col7","_col8","_col9","_col10","_col13","_col15","_col19","_col23","_col25","_col26","_col27","_col28","_col29","_col30","_col37","_col38"] - <-Map 48 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1008] - PartitionCols:_col0 - Select Operator [SEL_1007] (rows=1704 width=181) - Output:["_col0","_col1","_col2"] - Filter Operator [FIL_1006] (rows=1704 width=181) - predicate:(s_store_name is not null and s_zip is not null) - TableScan [TS_51] (rows=1704 width=181) - default@store,store,Tbl:COMPLETE,Col:COMPLETE,Output:["s_store_sk","s_store_name","s_zip"] - <-Reducer 9 [SIMPLE_EDGE] - SHUFFLE [RS_83] - PartitionCols:_col24 - Merge Join Operator [MERGEJOIN_920] (rows=1434227 width=492) - Conds:RS_80._col22=RS_949._col0(Inner),Output:["_col7","_col8","_col9","_col10","_col13","_col15","_col19","_col23","_col24","_col25","_col26","_col27","_col28","_col29","_col30"] - <-Map 47 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_949] - PartitionCols:_col0 - Select Operator [SEL_948] (rows=7200 width=4) - Output:["_col0"] - Filter Operator [FIL_947] (rows=7200 width=8) - predicate:hd_income_band_sk is not null - TableScan [TS_48] (rows=7200 width=8) - default@household_demographics,hd1,Tbl:COMPLETE,Col:COMPLETE,Output:["hd_demo_sk","hd_income_band_sk"] - <-Reducer 8 [SIMPLE_EDGE] - SHUFFLE [RS_80] - PartitionCols:_col22 - Merge Join Operator [MERGEJOIN_919] (rows=1434227 width=492) - Conds:RS_77._col19=RS_992._col0(Inner),Output:["_col7","_col8","_col9","_col10","_col13","_col15","_col19","_col22","_col23","_col24","_col25","_col26","_col27","_col28","_col29","_col30"] - <-Reducer 41 [ONE_TO_ONE_EDGE] vectorized - FORWARD [RS_992] - PartitionCols:_col0 - Select Operator [SEL_991] (rows=13257 width=4) - Output:["_col0"] - Filter Operator [FIL_990] (rows=13257 width=228) - predicate:(_col1 > (2 * _col2)) - Group By Operator [GBY_989] (rows=39773 width=228) - Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"],keys:KEY._col0 - <-Reducer 40 [SIMPLE_EDGE] - SHUFFLE [RS_44] - PartitionCols:_col0 - Group By Operator [GBY_43] (rows=6482999 width=228) - Output:["_col0","_col1","_col2"],aggregations:["sum(_col2)","sum(_col5)"],keys:_col0 - Merge Join Operator [MERGEJOIN_918] (rows=183085709 width=227) - Conds:RS_985._col0, _col1=RS_987._col0, _col1(Inner),Output:["_col0","_col2","_col5"] - <-Map 43 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_987] - PartitionCols:_col0, _col1 - Select Operator [SEL_986] (rows=28798881 width=120) - Output:["_col0","_col1","_col2"] - TableScan [TS_37] (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 39 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_985] - PartitionCols:_col0, _col1 - Select Operator [SEL_984] (rows=287989836 width=119) - Output:["_col0","_col1","_col2"] - Filter Operator [FIL_983] (rows=287989836 width=119) - predicate:(cs_item_sk BETWEEN DynamicValue(RS_24_item_i_item_sk_min) AND DynamicValue(RS_24_item_i_item_sk_max) and in_bloom_filter(cs_item_sk, DynamicValue(RS_24_item_i_item_sk_bloom_filter))) - TableScan [TS_35] (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 30 [BROADCAST_EDGE] vectorized - BROADCAST [RS_980] - Group By Operator [GBY_978] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 29 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_976] - Group By Operator [GBY_974] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_971] (rows=518 width=4) - Output:["_col0"] - Select Operator [SEL_969] (rows=518 width=111) - Output:["_col0","_col1"] - Filter Operator [FIL_968] (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) - TableScan [TS_15] (rows=462000 width=311) - default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_current_price","i_color","i_product_name"] - <-Reducer 7 [SIMPLE_EDGE] - SHUFFLE [RS_77] - PartitionCols:_col19 - Filter Operator [FIL_76] (rows=1434227 width=662) - predicate:(_col17 <> _col33) - Merge Join Operator [MERGEJOIN_917] (rows=1434227 width=662) - Conds:RS_73._col1=RS_1003._col0(Inner),Output:["_col7","_col8","_col9","_col10","_col13","_col15","_col17","_col19","_col22","_col23","_col24","_col25","_col26","_col27","_col28","_col29","_col30","_col33"] + PartitionCols:_col12 + Filter Operator [FIL_85] (rows=2364623 width=609) + predicate:(_col33 <> _col35) + Merge Join Operator [MERGEJOIN_951] (rows=2364623 width=609) + Conds:RS_82._col1=RS_1039._col0(Inner),Output:["_col3","_col12","_col15","_col16","_col17","_col18","_col19","_col24","_col25","_col29","_col31","_col33","_col35"] + <-Map 52 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_1039] + PartitionCols:_col0 + Select Operator [SEL_1038] (rows=1861800 width=89) + Output:["_col0","_col1"] + TableScan [TS_49] (rows=1861800 width=89) + default@customer_demographics,cd2,Tbl:COMPLETE,Col:COMPLETE,Output:["cd_demo_sk","cd_marital_status"] + <-Reducer 10 [SIMPLE_EDGE] + SHUFFLE [RS_82] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_950] (rows=2331651 width=523) + Conds:RS_79._col10=RS_1040._col0(Inner),Output:["_col1","_col3","_col12","_col15","_col16","_col17","_col18","_col19","_col24","_col25","_col29","_col31","_col33"] + <-Map 52 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_1040] + PartitionCols:_col0 + Please refer to the previous Select Operator [SEL_1038] + <-Reducer 9 [SIMPLE_EDGE] + SHUFFLE [RS_79] + PartitionCols:_col10 + Merge Join Operator [MERGEJOIN_949] (rows=2299139 width=436) + Conds:RS_76._col4=RS_999._col0(Inner),Output:["_col1","_col3","_col10","_col12","_col15","_col16","_col17","_col18","_col19","_col24","_col25","_col29","_col31"] + <-Map 38 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_999] + PartitionCols:_col0 + Select Operator [SEL_993] (rows=73049 width=8) + Output:["_col0","_col1"] + TableScan [TS_12] (rows=73049 width=8) + default@date_dim,d1,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year"] + <-Reducer 8 [SIMPLE_EDGE] + SHUFFLE [RS_76] + PartitionCols:_col4 + Merge Join Operator [MERGEJOIN_948] (rows=2299139 width=434) + Conds:RS_73._col5=RS_998._col0(Inner),Output:["_col1","_col3","_col4","_col10","_col12","_col15","_col16","_col17","_col18","_col19","_col24","_col25","_col29"] <-Map 38 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1003] + SHUFFLE [RS_998] PartitionCols:_col0 - Select Operator [SEL_1001] (rows=1861800 width=89) + Select Operator [SEL_992] (rows=73049 width=8) Output:["_col0","_col1"] - TableScan [TS_21] (rows=1861800 width=89) - default@customer_demographics,cd1,Tbl:COMPLETE,Col:COMPLETE,Output:["cd_demo_sk","cd_marital_status"] - <-Reducer 6 [SIMPLE_EDGE] + Please refer to the previous TableScan [TS_12] + <-Reducer 7 [SIMPLE_EDGE] SHUFFLE [RS_73] - PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_916] (rows=1414229 width=573) - Conds:RS_70._col0=RS_71._col4(Inner),Output:["_col1","_col7","_col8","_col9","_col10","_col13","_col15","_col17","_col19","_col22","_col23","_col24","_col25","_col26","_col27","_col28","_col29","_col30"] - <-Reducer 5 [SIMPLE_EDGE] + PartitionCols:_col5 + Merge Join Operator [MERGEJOIN_947] (rows=2299139 width=432) + Conds:RS_70._col8, _col14=RS_1036._col0, _col1(Inner),Output:["_col1","_col3","_col4","_col5","_col10","_col12","_col15","_col16","_col17","_col18","_col19","_col24","_col25"] + <-Map 51 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_1036] + PartitionCols:_col0, _col1 + Select Operator [SEL_1035] (rows=57591150 width=8) + Output:["_col0","_col1"] + TableScan [TS_41] (rows=57591150 width=8) + default@store_returns,store_returns,Tbl:COMPLETE,Col:COMPLETE,Output:["sr_item_sk","sr_ticket_number"] + <-Reducer 6 [SIMPLE_EDGE] SHUFFLE [RS_70] - PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_912] (rows=69376329 width=376) - Conds:RS_67._col4=RS_958._col0(Inner),Output:["_col0","_col1","_col7","_col8","_col9","_col10","_col13","_col15"] - <-Map 35 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_958] + PartitionCols:_col8, _col14 + Merge Join Operator [MERGEJOIN_946] (rows=1394510 width=300) + Conds:RS_67._col13=RS_1033._col0(Inner),Output:["_col1","_col3","_col4","_col5","_col8","_col10","_col12","_col14","_col15","_col16","_col17","_col18","_col19","_col24","_col25"] + <-Map 50 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_1033] PartitionCols:_col0 - Select Operator [SEL_954] (rows=73049 width=8) - Output:["_col0","_col1"] - TableScan [TS_18] (rows=73049 width=8) - default@date_dim,d1,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year"] - <-Reducer 4 [SIMPLE_EDGE] + Select Operator [SEL_1032] (rows=1704 width=181) + Output:["_col0","_col1","_col2"] + Filter Operator [FIL_1031] (rows=1704 width=181) + predicate:(s_store_name is not null and s_zip is not null) + TableScan [TS_38] (rows=1704 width=181) + default@store,store,Tbl:COMPLETE,Col:COMPLETE,Output:["s_store_sk","s_store_name","s_zip"] + <-Reducer 5 [SIMPLE_EDGE] SHUFFLE [RS_67] - PartitionCols:_col4 - Merge Join Operator [MERGEJOIN_911] (rows=69376329 width=376) - Conds:RS_64._col5=RS_957._col0(Inner),Output:["_col0","_col1","_col4","_col7","_col8","_col9","_col10","_col13"] - <-Map 35 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_957] + PartitionCols:_col13 + Merge Join Operator [MERGEJOIN_945] (rows=1394510 width=123) + Conds:RS_64._col11=RS_975._col0(Inner),Output:["_col1","_col3","_col4","_col5","_col8","_col10","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col19"] + <-Map 49 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_975] PartitionCols:_col0 - Select Operator [SEL_953] (rows=73049 width=8) - Output:["_col0","_col1"] - Please refer to the previous TableScan [TS_18] - <-Reducer 3 [SIMPLE_EDGE] + Select Operator [SEL_974] (rows=7200 width=4) + Output:["_col0"] + Filter Operator [FIL_973] (rows=7200 width=8) + predicate:hd_income_band_sk is not null + TableScan [TS_35] (rows=7200 width=8) + default@household_demographics,hd1,Tbl:COMPLETE,Col:COMPLETE,Output:["hd_demo_sk","hd_income_band_sk"] + <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_64] - PartitionCols:_col5 - Merge Join Operator [MERGEJOIN_910] (rows=69376329 width=376) - Conds:RS_61._col2=RS_950._col0(Inner),Output:["_col0","_col1","_col4","_col5","_col7","_col8","_col9","_col10"] - <-Map 47 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_950] + PartitionCols:_col11 + Merge Join Operator [MERGEJOIN_944] (rows=1394510 width=123) + Conds:RS_61._col8=RS_1022._col0(Inner),Output:["_col1","_col3","_col4","_col5","_col8","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col19"] + <-Reducer 43 [ONE_TO_ONE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_1022] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_948] - <-Reducer 2 [SIMPLE_EDGE] + Select Operator [SEL_1021] (rows=13257 width=4) + Output:["_col0"] + Filter Operator [FIL_1020] (rows=13257 width=228) + predicate:(_col1 > (2 * _col2)) + Group By Operator [GBY_1019] (rows=39773 width=228) + Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"],keys:KEY._col0 + <-Reducer 42 [SIMPLE_EDGE] + SHUFFLE [RS_31] + PartitionCols:_col0 + Group By Operator [GBY_30] (rows=6482999 width=228) + Output:["_col0","_col1","_col2"],aggregations:["sum(_col2)","sum(_col5)"],keys:_col0 + Merge Join Operator [MERGEJOIN_942] (rows=183085709 width=227) + Conds:RS_1015._col0, _col1=RS_1017._col0, _col1(Inner),Output:["_col0","_col2","_col5"] + <-Map 45 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_1017] + PartitionCols:_col0, _col1 + Select Operator [SEL_1016] (rows=28798881 width=120) + Output:["_col0","_col1","_col2"] + TableScan [TS_24] (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 41 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_1015] + PartitionCols:_col0, _col1 + Select Operator [SEL_1014] (rows=287989836 width=119) + Output:["_col0","_col1","_col2"] + Filter Operator [FIL_1013] (rows=287989836 width=119) + predicate:(cs_item_sk BETWEEN DynamicValue(RS_16_item_i_item_sk_min) AND DynamicValue(RS_16_item_i_item_sk_max) and in_bloom_filter(cs_item_sk, DynamicValue(RS_16_item_i_item_sk_bloom_filter))) + TableScan [TS_22] (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 34 [BROADCAST_EDGE] vectorized + BROADCAST [RS_990] + Group By Operator [GBY_988] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 33 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_986] + Group By Operator [GBY_984] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_981] (rows=518 width=4) + Output:["_col0"] + Select Operator [SEL_979] (rows=518 width=111) + Output:["_col0","_col1"] + Filter Operator [FIL_978] (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) + TableScan [TS_9] (rows=462000 width=311) + default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_current_price","i_color","i_product_name"] + <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_61] - PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_909] (rows=69376329 width=380) - Conds:RS_942._col3=RS_945._col0(Inner),Output:["_col0","_col1","_col2","_col4","_col5","_col7","_col8","_col9","_col10"] - <-Map 49 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_945] + PartitionCols:_col8 + Merge Join Operator [MERGEJOIN_943] (rows=1394510 width=123) + Conds:RS_58._col0=RS_59._col2(Inner),Output:["_col1","_col3","_col4","_col5","_col8","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col19"] + <-Reducer 2 [SIMPLE_EDGE] + SHUFFLE [RS_58] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_943] - <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_942] - PartitionCols:_col3 - Select Operator [SEL_941] (rows=69376329 width=23) - Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - Filter Operator [FIL_940] (rows=69376329 width=23) - predicate:(c_current_addr_sk is not null and c_current_cdemo_sk is not null and c_current_hdemo_sk is not null and c_first_sales_date_sk is not null and c_first_shipto_date_sk is not null) - 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 28 [SIMPLE_EDGE] - SHUFFLE [RS_71] - PartitionCols:_col4 - Select Operator [SEL_32] (rows=1630791 width=208) - Output:["_col1","_col3","_col4","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14"] - Merge Join Operator [MERGEJOIN_915] (rows=1630791 width=208) - Conds:RS_29._col3=RS_1002._col0(Inner),Output:["_col1","_col2","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col15"] - <-Map 38 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1002] - PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_1001] - <-Reducer 27 [SIMPLE_EDGE] - SHUFFLE [RS_29] - PartitionCols:_col3 - Merge Join Operator [MERGEJOIN_914] (rows=1608052 width=119) - Conds:RS_26._col0=RS_960._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12"] - <-Map 35 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_960] - PartitionCols:_col0 - Select Operator [SEL_956] (rows=652 width=4) - Output:["_col0"] - Filter Operator [FIL_952] (rows=652 width=8) - predicate:(d_year = 2000) - Please refer to the previous TableScan [TS_18] - <-Reducer 26 [SIMPLE_EDGE] - SHUFFLE [RS_26] - PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_913] (rows=4503592 width=119) - Conds:RS_1000._col1=RS_970._col0(Inner),Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12"] - <-Map 29 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_970] - PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_969] - <-Map 25 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1000] - PartitionCols:_col1 - Select Operator [SEL_999] (rows=417313408 width=351) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10"] - Filter Operator [FIL_998] (rows=417313408 width=355) - predicate:((ss_item_sk BETWEEN DynamicValue(RS_24_item_i_item_sk_min) AND DynamicValue(RS_24_item_i_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_24_item_i_item_sk_bloom_filter))) and (ss_item_sk BETWEEN DynamicValue(RS_78_catalog_sales_cs_item_sk_min) AND DynamicValue(RS_78_catalog_sales_cs_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_78_catalog_sales_cs_item_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_27_d1_d_date_sk_min) AND DynamicValue(RS_27_d1_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_27_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_promo_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null) - TableScan [TS_12] (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 30 [BROADCAST_EDGE] vectorized - BROADCAST [RS_979] - Please refer to the previous Group By Operator [GBY_978] - <-Reducer 36 [BROADCAST_EDGE] vectorized - BROADCAST [RS_982] - Group By Operator [GBY_981] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 35 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_966] - Group By Operator [GBY_964] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_961] (rows=652 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_956] - <-Reducer 42 [BROADCAST_EDGE] vectorized - BROADCAST [RS_997] - Group By Operator [GBY_996] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Reducer 41 [CUSTOM_SIMPLE_EDGE] vectorized - FORWARD [RS_995] - Group By Operator [GBY_994] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_993] (rows=13257 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_991] - <-Reducer 24 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1043] + Merge Join Operator [MERGEJOIN_939] (rows=69376329 width=19) + Conds:RS_972._col2=RS_976._col0(Inner),Output:["_col0","_col1","_col3","_col4","_col5"] + <-Map 49 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_976] + PartitionCols:_col0 + Please refer to the previous Select Operator [SEL_974] + <-Map 1 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_972] + PartitionCols:_col2 + Select Operator [SEL_971] (rows=69376329 width=23) + Output:["_col0","_col1","_col2","_col3","_col4","_col5"] + Filter Operator [FIL_970] (rows=69376329 width=23) + predicate:(c_current_addr_sk is not null and c_current_cdemo_sk is not null and c_current_hdemo_sk is not null and c_first_sales_date_sk is not null and c_first_shipto_date_sk is not null) + 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 32 [SIMPLE_EDGE] + SHUFFLE [RS_59] + PartitionCols:_col2 + Merge Join Operator [MERGEJOIN_941] (rows=1608052 width=119) + Conds:RS_18._col0=RS_1003._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12"] + <-Map 38 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_1003] + PartitionCols:_col0 + Select Operator [SEL_997] (rows=652 width=4) + Output:["_col0"] + Filter Operator [FIL_991] (rows=652 width=8) + predicate:(d_year = 2000) + Please refer to the previous TableScan [TS_12] + <-Reducer 31 [SIMPLE_EDGE] + SHUFFLE [RS_18] + PartitionCols:_col0 + Merge Join Operator [MERGEJOIN_940] (rows=4503592 width=119) + Conds:RS_1030._col1=RS_980._col0(Inner),Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12"] + <-Map 33 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_980] + PartitionCols:_col0 + Please refer to the previous Select Operator [SEL_979] + <-Map 30 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_1030] + PartitionCols:_col1 + Select Operator [SEL_1029] (rows=417313408 width=351) + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10"] + Filter Operator [FIL_1028] (rows=417313408 width=355) + predicate:((ss_item_sk BETWEEN DynamicValue(RS_16_item_i_item_sk_min) AND DynamicValue(RS_16_item_i_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_16_item_i_item_sk_bloom_filter))) and (ss_item_sk BETWEEN DynamicValue(RS_62_catalog_sales_cs_item_sk_min) AND DynamicValue(RS_62_catalog_sales_cs_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_62_catalog_sales_cs_item_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_19_d1_d_date_sk_min) AND DynamicValue(RS_19_d1_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_19_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_promo_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null) + TableScan [TS_6] (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 34 [BROADCAST_EDGE] vectorized + BROADCAST [RS_989] + Please refer to the previous Group By Operator [GBY_988] + <-Reducer 39 [BROADCAST_EDGE] vectorized + BROADCAST [RS_1012] + Group By Operator [GBY_1011] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 38 [CUSTOM_SIMPLE_EDGE] vectorized + SHUFFLE [RS_1009] + Group By Operator [GBY_1007] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_1004] (rows=652 width=4) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_997] + <-Reducer 44 [BROADCAST_EDGE] vectorized + BROADCAST [RS_1027] + Group By Operator [GBY_1026] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Reducer 43 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_1025] + Group By Operator [GBY_1024] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_1023] (rows=13257 width=4) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_1021] + <-Reducer 29 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_1078] PartitionCols:_col1, _col0, _col2 - Select Operator [SEL_1042] (rows=1434227 width=525) + Select Operator [SEL_1077] (rows=2364623 width=525) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"] - Group By Operator [GBY_1041] (rows=1434227 width=1362) + Group By Operator [GBY_1076] (rows=2364623 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 23 [SIMPLE_EDGE] + <-Reducer 28 [SIMPLE_EDGE] SHUFFLE [RS_191] PartitionCols:_col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 - Group By Operator [GBY_190] (rows=1434227 width=1362) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17"],aggregations:["count()","sum(_col26)","sum(_col27)","sum(_col28)"],keys:_col37, _col29, _col38, _col40, _col41, _col42, _col43, _col7, _col8, _col9, _col10, _col13, _col15, _col30 - Merge Join Operator [MERGEJOIN_938] (rows=2364621 width=1153) - Conds:RS_186._col19, _col25=RS_1012._col0, _col1(Inner),Output:["_col7","_col8","_col9","_col10","_col13","_col15","_col26","_col27","_col28","_col29","_col30","_col37","_col38","_col40","_col41","_col42","_col43"] - <-Map 50 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1012] - PartitionCols:_col0, _col1 - Please refer to the previous Select Operator [SEL_1010] - <-Reducer 22 [SIMPLE_EDGE] + Group By Operator [GBY_190] (rows=2364623 width=1362) + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17"],aggregations:["count()","sum(_col15)","sum(_col16)","sum(_col17)"],keys:_col24, _col18, _col25, _col19, _col29, _col31, _col37, _col38, _col39, _col40, _col42, _col43, _col44, _col45 + Merge Join Operator [MERGEJOIN_968] (rows=2364623 width=1155) + Conds:RS_186._col3=RS_1047._col0(Inner),Output:["_col15","_col16","_col17","_col18","_col19","_col24","_col25","_col29","_col31","_col37","_col38","_col39","_col40","_col42","_col43","_col44","_col45"] + <-Map 53 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_1047] + PartitionCols:_col0 + Please refer to the previous Select Operator [SEL_1043] + <-Reducer 27 [SIMPLE_EDGE] SHUFFLE [RS_186] - PartitionCols:_col19, _col25 - Merge Join Operator [MERGEJOIN_937] (rows=1434227 width=1030) - Conds:RS_183._col23=RS_946._col0(Inner),Output:["_col7","_col8","_col9","_col10","_col13","_col15","_col19","_col25","_col26","_col27","_col28","_col29","_col30","_col37","_col38","_col40","_col41","_col42","_col43"] - <-Map 49 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_946] + PartitionCols:_col3 + Merge Join Operator [MERGEJOIN_967] (rows=2364623 width=798) + Conds:RS_183._col12=RS_1046._col0(Inner),Output:["_col3","_col15","_col16","_col17","_col18","_col19","_col24","_col25","_col29","_col31","_col37","_col38","_col39","_col40"] + <-Map 53 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_1046] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_943] - <-Reducer 21 [SIMPLE_EDGE] + Please refer to the previous Select Operator [SEL_1043] + <-Reducer 26 [SIMPLE_EDGE] SHUFFLE [RS_183] - PartitionCols:_col23 - Merge Join Operator [MERGEJOIN_936] (rows=1434227 width=669) - Conds:RS_180._col24=RS_1009._col0(Inner),Output:["_col7","_col8","_col9","_col10","_col13","_col15","_col19","_col23","_col25","_col26","_col27","_col28","_col29","_col30","_col37","_col38"] - <-Map 48 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1009] - PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_1007] - <-Reducer 20 [SIMPLE_EDGE] - SHUFFLE [RS_180] - PartitionCols:_col24 - Merge Join Operator [MERGEJOIN_935] (rows=1434227 width=492) - Conds:RS_177._col22=RS_951._col0(Inner),Output:["_col7","_col8","_col9","_col10","_col13","_col15","_col19","_col23","_col24","_col25","_col26","_col27","_col28","_col29","_col30"] - <-Map 47 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_951] - PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_948] - <-Reducer 19 [SIMPLE_EDGE] - SHUFFLE [RS_177] - PartitionCols:_col22 - Merge Join Operator [MERGEJOIN_934] (rows=1434227 width=492) - Conds:RS_174._col19=RS_1030._col0(Inner),Output:["_col7","_col8","_col9","_col10","_col13","_col15","_col19","_col22","_col23","_col24","_col25","_col26","_col27","_col28","_col29","_col30"] - <-Reducer 45 [ONE_TO_ONE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_1030] - PartitionCols:_col0 - Select Operator [SEL_1029] (rows=13257 width=4) - Output:["_col0"] - Filter Operator [FIL_1028] (rows=13257 width=228) - predicate:(_col1 > (2 * _col2)) - Group By Operator [GBY_1027] (rows=39773 width=228) - Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"],keys:KEY._col0 - <-Reducer 44 [SIMPLE_EDGE] - SHUFFLE [RS_141] - PartitionCols:_col0 - Group By Operator [GBY_140] (rows=6482999 width=228) - Output:["_col0","_col1","_col2"],aggregations:["sum(_col2)","sum(_col5)"],keys:_col0 - Merge Join Operator [MERGEJOIN_933] (rows=183085709 width=227) - Conds:RS_1026._col0, _col1=RS_988._col0, _col1(Inner),Output:["_col0","_col2","_col5"] - <-Map 43 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_988] - PartitionCols:_col0, _col1 - Please refer to the previous Select Operator [SEL_986] - <-Map 52 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1026] - PartitionCols:_col0, _col1 - Select Operator [SEL_1025] (rows=287989836 width=119) - Output:["_col0","_col1","_col2"] - Filter Operator [FIL_1024] (rows=287989836 width=119) - predicate:(cs_item_sk BETWEEN DynamicValue(RS_121_item_i_item_sk_min) AND DynamicValue(RS_121_item_i_item_sk_max) and in_bloom_filter(cs_item_sk, DynamicValue(RS_121_item_i_item_sk_bloom_filter))) - TableScan [TS_132] (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 34 [BROADCAST_EDGE] vectorized - BROADCAST [RS_1021] - Group By Operator [GBY_1019] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 29 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_977] - Group By Operator [GBY_975] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_973] (rows=518 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_969] - <-Reducer 18 [SIMPLE_EDGE] - SHUFFLE [RS_174] - PartitionCols:_col19 - Filter Operator [FIL_173] (rows=1434227 width=662) - predicate:(_col17 <> _col33) - Merge Join Operator [MERGEJOIN_932] (rows=1434227 width=662) - Conds:RS_170._col1=RS_1005._col0(Inner),Output:["_col7","_col8","_col9","_col10","_col13","_col15","_col17","_col19","_col22","_col23","_col24","_col25","_col26","_col27","_col28","_col29","_col30","_col33"] + PartitionCols:_col12 + Filter Operator [FIL_182] (rows=2364623 width=609) + predicate:(_col33 <> _col35) + Merge Join Operator [MERGEJOIN_966] (rows=2364623 width=609) + Conds:RS_179._col1=RS_1042._col0(Inner),Output:["_col3","_col12","_col15","_col16","_col17","_col18","_col19","_col24","_col25","_col29","_col31","_col33","_col35"] + <-Map 52 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_1042] + PartitionCols:_col0 + Please refer to the previous Select Operator [SEL_1038] + <-Reducer 25 [SIMPLE_EDGE] + SHUFFLE [RS_179] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_965] (rows=2331651 width=523) + Conds:RS_176._col10=RS_1041._col0(Inner),Output:["_col1","_col3","_col12","_col15","_col16","_col17","_col18","_col19","_col24","_col25","_col29","_col31","_col33"] + <-Map 52 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_1041] + PartitionCols:_col0 + Please refer to the previous Select Operator [SEL_1038] + <-Reducer 24 [SIMPLE_EDGE] + SHUFFLE [RS_176] + PartitionCols:_col10 + Merge Join Operator [MERGEJOIN_964] (rows=2299139 width=436) + Conds:RS_173._col4=RS_1002._col0(Inner),Output:["_col1","_col3","_col10","_col12","_col15","_col16","_col17","_col18","_col19","_col24","_col25","_col29","_col31"] + <-Map 38 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_1002] + PartitionCols:_col0 + Select Operator [SEL_996] (rows=73049 width=8) + Output:["_col0","_col1"] + Please refer to the previous TableScan [TS_12] + <-Reducer 23 [SIMPLE_EDGE] + SHUFFLE [RS_173] + PartitionCols:_col4 + Merge Join Operator [MERGEJOIN_963] (rows=2299139 width=434) + Conds:RS_170._col5=RS_1001._col0(Inner),Output:["_col1","_col3","_col4","_col10","_col12","_col15","_col16","_col17","_col18","_col19","_col24","_col25","_col29"] <-Map 38 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1005] + SHUFFLE [RS_1001] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_1001] - <-Reducer 17 [SIMPLE_EDGE] + Select Operator [SEL_995] (rows=73049 width=8) + Output:["_col0","_col1"] + Please refer to the previous TableScan [TS_12] + <-Reducer 22 [SIMPLE_EDGE] SHUFFLE [RS_170] - PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_931] (rows=1414229 width=573) - Conds:RS_167._col0=RS_168._col4(Inner),Output:["_col1","_col7","_col8","_col9","_col10","_col13","_col15","_col17","_col19","_col22","_col23","_col24","_col25","_col26","_col27","_col28","_col29","_col30"] - <-Reducer 5 [SIMPLE_EDGE] + PartitionCols:_col5 + Merge Join Operator [MERGEJOIN_962] (rows=2299139 width=432) + Conds:RS_167._col8, _col14=RS_1037._col0, _col1(Inner),Output:["_col1","_col3","_col4","_col5","_col10","_col12","_col15","_col16","_col17","_col18","_col19","_col24","_col25"] + <-Map 51 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_1037] + PartitionCols:_col0, _col1 + Please refer to the previous Select Operator [SEL_1035] + <-Reducer 21 [SIMPLE_EDGE] SHUFFLE [RS_167] - PartitionCols:_col0 - Please refer to the previous Merge Join Operator [MERGEJOIN_912] - <-Reducer 33 [SIMPLE_EDGE] - SHUFFLE [RS_168] - PartitionCols:_col4 - Select Operator [SEL_129] (rows=1630791 width=208) - Output:["_col1","_col3","_col4","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14"] - Merge Join Operator [MERGEJOIN_930] (rows=1630791 width=208) - Conds:RS_126._col3=RS_1004._col0(Inner),Output:["_col1","_col2","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col15"] - <-Map 38 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1004] - PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_1001] - <-Reducer 32 [SIMPLE_EDGE] - SHUFFLE [RS_126] - PartitionCols:_col3 - Merge Join Operator [MERGEJOIN_929] (rows=1608052 width=119) - Conds:RS_123._col0=RS_962._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12"] - <-Map 35 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_962] - PartitionCols:_col0 - Select Operator [SEL_959] (rows=652 width=4) - Output:["_col0"] - Filter Operator [FIL_955] (rows=652 width=8) - predicate:(d_year = 2001) - Please refer to the previous TableScan [TS_18] - <-Reducer 31 [SIMPLE_EDGE] - SHUFFLE [RS_123] - PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_928] (rows=4503592 width=119) - Conds:RS_1040._col1=RS_972._col0(Inner),Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12"] - <-Map 29 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_972] - PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_969] - <-Map 51 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1040] - PartitionCols:_col1 - Select Operator [SEL_1039] (rows=417313408 width=351) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10"] - Filter Operator [FIL_1038] (rows=417313408 width=355) - predicate:((ss_item_sk BETWEEN DynamicValue(RS_121_item_i_item_sk_min) AND DynamicValue(RS_121_item_i_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_121_item_i_item_sk_bloom_filter))) and (ss_item_sk BETWEEN DynamicValue(RS_175_catalog_sales_cs_item_sk_min) AND DynamicValue(RS_175_catalog_sales_cs_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_175_catalog_sales_cs_item_sk_bloom_filter))) and (ss_item_sk BETWEEN DynamicValue(RS_194_item_i_item_sk_min) AND DynamicValue(RS_194_item_i_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_194_item_i_item_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_124_d1_d_date_sk_min) AND DynamicValue(RS_124_d1_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_124_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_promo_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null) - TableScan [TS_109] (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 34 [BROADCAST_EDGE] vectorized - BROADCAST [RS_1020] - Please refer to the previous Group By Operator [GBY_1019] - <-Reducer 16 [BROADCAST_EDGE] vectorized - BROADCAST [RS_1037] - Group By Operator [GBY_1036] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Reducer 13 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_1018] - Group By Operator [GBY_1017] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_1016] (rows=1434227 width=8) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_1014] - <-Reducer 37 [BROADCAST_EDGE] vectorized - BROADCAST [RS_1023] - Group By Operator [GBY_1022] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 35 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_967] - Group By Operator [GBY_965] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_963] (rows=652 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_959] - <-Reducer 46 [BROADCAST_EDGE] vectorized - BROADCAST [RS_1035] - Group By Operator [GBY_1034] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Reducer 45 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_1033] - Group By Operator [GBY_1032] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_1031] (rows=13257 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_1029] + PartitionCols:_col8, _col14 + Merge Join Operator [MERGEJOIN_961] (rows=1394510 width=300) + Conds:RS_164._col13=RS_1034._col0(Inner),Output:["_col1","_col3","_col4","_col5","_col8","_col10","_col12","_col14","_col15","_col16","_col17","_col18","_col19","_col24","_col25"] + <-Map 50 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_1034] + PartitionCols:_col0 + Please refer to the previous Select Operator [SEL_1032] + <-Reducer 20 [SIMPLE_EDGE] + SHUFFLE [RS_164] + PartitionCols:_col13 + Merge Join Operator [MERGEJOIN_960] (rows=1394510 width=123) + Conds:RS_161._col11=RS_977._col0(Inner),Output:["_col1","_col3","_col4","_col5","_col8","_col10","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col19"] + <-Map 49 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_977] + PartitionCols:_col0 + Please refer to the previous Select Operator [SEL_974] + <-Reducer 19 [SIMPLE_EDGE] + SHUFFLE [RS_161] + PartitionCols:_col11 + Merge Join Operator [MERGEJOIN_959] (rows=1394510 width=123) + Conds:RS_158._col8=RS_1065._col0(Inner),Output:["_col1","_col3","_col4","_col5","_col8","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col19"] + <-Reducer 47 [ONE_TO_ONE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_1065] + PartitionCols:_col0 + Select Operator [SEL_1064] (rows=13257 width=4) + Output:["_col0"] + Filter Operator [FIL_1063] (rows=13257 width=228) + predicate:(_col1 > (2 * _col2)) + Group By Operator [GBY_1062] (rows=39773 width=228) + Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"],keys:KEY._col0 + <-Reducer 46 [SIMPLE_EDGE] + SHUFFLE [RS_128] + PartitionCols:_col0 + Group By Operator [GBY_127] (rows=6482999 width=228) + Output:["_col0","_col1","_col2"],aggregations:["sum(_col2)","sum(_col5)"],keys:_col0 + Merge Join Operator [MERGEJOIN_957] (rows=183085709 width=227) + Conds:RS_1061._col0, _col1=RS_1018._col0, _col1(Inner),Output:["_col0","_col2","_col5"] + <-Map 45 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_1018] + PartitionCols:_col0, _col1 + Please refer to the previous Select Operator [SEL_1016] + <-Map 55 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_1061] + PartitionCols:_col0, _col1 + Select Operator [SEL_1060] (rows=287989836 width=119) + Output:["_col0","_col1","_col2"] + Filter Operator [FIL_1059] (rows=287989836 width=119) + predicate:(cs_item_sk BETWEEN DynamicValue(RS_113_item_i_item_sk_min) AND DynamicValue(RS_113_item_i_item_sk_max) and in_bloom_filter(cs_item_sk, DynamicValue(RS_113_item_i_item_sk_bloom_filter))) + TableScan [TS_119] (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 37 [BROADCAST_EDGE] vectorized + BROADCAST [RS_1056] + Group By Operator [GBY_1054] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 33 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_987] + Group By Operator [GBY_985] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_983] (rows=518 width=4) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_979] + <-Reducer 18 [SIMPLE_EDGE] + SHUFFLE [RS_158] + PartitionCols:_col8 + Merge Join Operator [MERGEJOIN_958] (rows=1394510 width=123) + Conds:RS_155._col0=RS_156._col2(Inner),Output:["_col1","_col3","_col4","_col5","_col8","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col19"] + <-Reducer 2 [SIMPLE_EDGE] + SHUFFLE [RS_155] + PartitionCols:_col0 + Please refer to the previous Merge Join Operator [MERGEJOIN_939] + <-Reducer 36 [SIMPLE_EDGE] + SHUFFLE [RS_156] + PartitionCols:_col2 + Merge Join Operator [MERGEJOIN_956] (rows=1608052 width=119) + Conds:RS_115._col0=RS_1005._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12"] + <-Map 38 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_1005] + PartitionCols:_col0 + Select Operator [SEL_1000] (rows=652 width=4) + Output:["_col0"] + Filter Operator [FIL_994] (rows=652 width=8) + predicate:(d_year = 2001) + Please refer to the previous TableScan [TS_12] + <-Reducer 35 [SIMPLE_EDGE] + SHUFFLE [RS_115] + PartitionCols:_col0 + Merge Join Operator [MERGEJOIN_955] (rows=4503592 width=119) + Conds:RS_1075._col1=RS_982._col0(Inner),Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12"] + <-Map 33 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_982] + PartitionCols:_col0 + Please refer to the previous Select Operator [SEL_979] + <-Map 54 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_1075] + PartitionCols:_col1 + Select Operator [SEL_1074] (rows=417313408 width=351) + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10"] + Filter Operator [FIL_1073] (rows=417313408 width=355) + predicate:((ss_item_sk BETWEEN DynamicValue(RS_113_item_i_item_sk_min) AND DynamicValue(RS_113_item_i_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_113_item_i_item_sk_bloom_filter))) and (ss_item_sk BETWEEN DynamicValue(RS_159_catalog_sales_cs_item_sk_min) AND DynamicValue(RS_159_catalog_sales_cs_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_159_catalog_sales_cs_item_sk_bloom_filter))) and (ss_item_sk BETWEEN DynamicValue(RS_194_item_i_item_sk_min) AND DynamicValue(RS_194_item_i_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_194_item_i_item_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_116_d1_d_date_sk_min) AND DynamicValue(RS_116_d1_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_116_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_promo_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null) + TableScan [TS_103] (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 37 [BROADCAST_EDGE] vectorized + BROADCAST [RS_1055] + Please refer to the previous Group By Operator [GBY_1054] + <-Reducer 17 [BROADCAST_EDGE] vectorized + BROADCAST [RS_1072] + Group By Operator [GBY_1071] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Reducer 14 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_1053] + Group By Operator [GBY_1052] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_1051] (rows=2364623 width=8) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_1049] + <-Reducer 40 [BROADCAST_EDGE] vectorized + BROADCAST [RS_1058] + Group By Operator [GBY_1057] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 38 [CUSTOM_SIMPLE_EDGE] vectorized + SHUFFLE [RS_1010] + Group By Operator [GBY_1008] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_1006] (rows=652 width=4) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_1000] + <-Reducer 48 [BROADCAST_EDGE] vectorized + BROADCAST [RS_1070] + Group By Operator [GBY_1069] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Reducer 47 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_1068] + Group By Operator [GBY_1067] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_1066] (rows=13257 width=4) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_1064] diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/query67.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/query67.q.out index 7abc9594b5..f629767368 100644 --- a/ql/src/test/results/clientpositive/perf/tez/constraints/query67.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/query67.q.out @@ -123,12 +123,12 @@ Stage-0 Filter Operator [FIL_102] (rows=273593580 width=613) predicate:(rank_window_0 <= 100) PTF Operator [PTF_101] (rows=820780740 width=613) - Function definitions:[{},{"name:":"windowingtablefunction","order by:":"_col8 DESC NULLS LAST","partition by:":"_col2"}] + Function definitions:[{},{"name:":"windowingtablefunction","order by:":"_col8 DESC NULLS LAST","partition by:":"_col6"}] Select Operator [SEL_100] (rows=820780740 width=613) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"] <-Reducer 5 [SIMPLE_EDGE] vectorized SHUFFLE [RS_99] - PartitionCols:_col2 + PartitionCols:_col6 Select Operator [SEL_98] (rows=820780740 width=613) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"] Group By Operator [GBY_97] (rows=820780740 width=621) @@ -137,7 +137,7 @@ Stage-0 SHUFFLE [RS_21] PartitionCols:_col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 Group By Operator [GBY_20] (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 + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9"],aggregations:["sum(_col3)"],keys:_col5, _col6, _col7, _col9, _col11, _col12, _col13, _col14, 0L Merge Join Operator [MERGEJOIN_81] (rows=91197860 width=613) Conds:RS_16._col1=RS_96._col0(Inner),Output:["_col3","_col5","_col6","_col7","_col9","_col11","_col12","_col13","_col14"] <-Map 11 [SIMPLE_EDGE] vectorized diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/query68.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/query68.q.out index 2ce705967b..582c7da5ff 100644 --- a/ql/src/test/results/clientpositive/perf/tez/constraints/query68.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/query68.q.out @@ -97,158 +97,158 @@ POSTHOOK: Output: hdfs://### HDFS PATH ### Plan optimized by CBO. Vertex dependency in root stage -Map 8 <- Reducer 13 (BROADCAST_EDGE), Reducer 15 (BROADCAST_EDGE), Reducer 17 (BROADCAST_EDGE) -Reducer 10 <- Map 14 (SIMPLE_EDGE), Reducer 9 (SIMPLE_EDGE) -Reducer 11 <- Map 16 (SIMPLE_EDGE), Reducer 10 (SIMPLE_EDGE) -Reducer 13 <- Map 12 (CUSTOM_SIMPLE_EDGE) -Reducer 15 <- Map 14 (CUSTOM_SIMPLE_EDGE) -Reducer 17 <- Map 16 (CUSTOM_SIMPLE_EDGE) -Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) -Reducer 3 <- Reducer 2 (SIMPLE_EDGE), Reducer 7 (SIMPLE_EDGE) +Map 5 <- Reducer 12 (BROADCAST_EDGE), Reducer 14 (BROADCAST_EDGE), Reducer 16 (BROADCAST_EDGE) +Reducer 10 <- Reducer 9 (SIMPLE_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), Reducer 10 (SIMPLE_EDGE) +Reducer 3 <- Map 17 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) Reducer 4 <- Reducer 3 (SIMPLE_EDGE) -Reducer 6 <- Map 5 (SIMPLE_EDGE), Reducer 11 (SIMPLE_EDGE) -Reducer 7 <- Reducer 6 (SIMPLE_EDGE) -Reducer 9 <- Map 12 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) +Reducer 6 <- Map 11 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) +Reducer 7 <- Map 13 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE) +Reducer 8 <- Map 15 (SIMPLE_EDGE), Reducer 7 (SIMPLE_EDGE) +Reducer 9 <- Map 17 (SIMPLE_EDGE), Reducer 8 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:100 Stage-1 Reducer 4 vectorized - File Output Operator [FS_182] - Limit [LIM_181] (rows=100 width=706) + File Output Operator [FS_186] + Limit [LIM_185] (rows=100 width=706) Number of rows:100 - Select Operator [SEL_180] (rows=727776 width=706) + Select Operator [SEL_184] (rows=727776 width=706) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_44] Select Operator [SEL_43] (rows=727776 width=706) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] Filter Operator [FIL_42] (rows=727776 width=706) - predicate:(_col5 <> _col8) - Merge Join Operator [MERGEJOIN_143] (rows=727776 width=706) - Conds:RS_39._col0=RS_179._col1(Inner),Output:["_col2","_col3","_col5","_col6","_col8","_col9","_col10","_col11"] + predicate:(_col11 <> _col6) + Merge Join Operator [MERGEJOIN_147] (rows=727776 width=706) + Conds:RS_39._col1=RS_179._col0(Inner),Output:["_col2","_col3","_col4","_col6","_col7","_col8","_col9","_col11"] + <-Map 17 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_179] + PartitionCols:_col0 + Select Operator [SEL_178] (rows=40000000 width=97) + Output:["_col0","_col1"] + TableScan [TS_34] (rows=40000000 width=97) + default@customer_address,current_addr,Tbl:COMPLETE,Col:COMPLETE,Output:["ca_address_sk","ca_city"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_39] - PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_138] (rows=80000000 width=277) - Conds:RS_146._col1=RS_148._col0(Inner),Output:["_col0","_col2","_col3","_col5"] - <-Map 5 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_148] - PartitionCols:_col0 - Select Operator [SEL_147] (rows=40000000 width=97) - Output:["_col0","_col1"] - TableScan [TS_3] (rows=40000000 width=97) - default@customer_address,current_addr,Tbl:COMPLETE,Col:COMPLETE,Output:["ca_address_sk","ca_city"] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_146] (rows=727776 width=617) + Conds:RS_150._col0=RS_183._col1(Inner),Output:["_col1","_col2","_col3","_col4","_col6","_col7","_col8","_col9"] <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_146] - PartitionCols:_col1 - Select Operator [SEL_145] (rows=80000000 width=188) + SHUFFLE [RS_150] + PartitionCols:_col0 + Select Operator [SEL_149] (rows=80000000 width=188) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_144] (rows=80000000 width=188) + Filter Operator [FIL_148] (rows=80000000 width=188) predicate:c_current_addr_sk is not null TableScan [TS_0] (rows=80000000 width=188) default@customer,customer,Tbl:COMPLETE,Col:COMPLETE,Output:["c_customer_sk","c_current_addr_sk","c_first_name","c_last_name"] - <-Reducer 7 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_179] - PartitionCols:_col1 - Select Operator [SEL_178] (rows=727776 width=433) - Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - Group By Operator [GBY_177] (rows=727776 width=433) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3 - <-Reducer 6 [SIMPLE_EDGE] - SHUFFLE [RS_33] - PartitionCols:_col0, _col1, _col2, _col3 - Group By Operator [GBY_32] (rows=727776 width=433) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"],aggregations:["sum(_col6)","sum(_col7)","sum(_col8)"],keys:_col1, _col13, _col3, _col5 - Merge Join Operator [MERGEJOIN_142] (rows=727776 width=97) - Conds:RS_28._col3=RS_149._col0(Inner),Output:["_col1","_col3","_col5","_col6","_col7","_col8","_col13"] - <-Map 5 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_149] - PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_147] - <-Reducer 11 [SIMPLE_EDGE] - SHUFFLE [RS_28] - PartitionCols:_col3 - Merge Join Operator [MERGEJOIN_141] (rows=727776 width=4) - Conds:RS_25._col2=RS_168._col0(Inner),Output:["_col1","_col3","_col5","_col6","_col7","_col8"] - <-Map 16 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_168] + <-Reducer 10 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_183] + PartitionCols:_col1 + Select Operator [SEL_182] (rows=727776 width=433) + Output:["_col0","_col1","_col2","_col3","_col4","_col5"] + Group By Operator [GBY_181] (rows=727776 width=433) + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3 + <-Reducer 9 [SIMPLE_EDGE] + SHUFFLE [RS_31] + PartitionCols:_col0, _col1, _col2, _col3 + Group By Operator [GBY_30] (rows=727776 width=433) + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"],aggregations:["sum(_col6)","sum(_col7)","sum(_col8)"],keys:_col1, _col13, _col3, _col5 + Merge Join Operator [MERGEJOIN_145] (rows=727776 width=97) + Conds:RS_26._col3=RS_180._col0(Inner),Output:["_col1","_col3","_col5","_col6","_col7","_col8","_col13"] + <-Map 17 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_180] PartitionCols:_col0 - Select Operator [SEL_167] (rows=1855 width=4) - Output:["_col0"] - Filter Operator [FIL_166] (rows=1855 width=12) - predicate:((hd_dep_count = 2) or (hd_vehicle_count = 1)) - TableScan [TS_14] (rows=7200 width=12) - default@household_demographics,household_demographics,Tbl:COMPLETE,Col:COMPLETE,Output:["hd_demo_sk","hd_dep_count","hd_vehicle_count"] - <-Reducer 10 [SIMPLE_EDGE] - SHUFFLE [RS_25] - PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_140] (rows=2824787 width=4) - Conds:RS_22._col4=RS_160._col0(Inner),Output:["_col1","_col2","_col3","_col5","_col6","_col7","_col8"] - <-Map 14 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_160] + Please refer to the previous Select Operator [SEL_178] + <-Reducer 8 [SIMPLE_EDGE] + SHUFFLE [RS_26] + PartitionCols:_col3 + Merge Join Operator [MERGEJOIN_144] (rows=727776 width=4) + Conds:RS_23._col2=RS_169._col0(Inner),Output:["_col1","_col3","_col5","_col6","_col7","_col8"] + <-Map 15 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_169] PartitionCols:_col0 - Select Operator [SEL_159] (rows=14 width=4) + Select Operator [SEL_168] (rows=1855 width=4) Output:["_col0"] - Filter Operator [FIL_158] (rows=14 width=97) - predicate:(s_city) IN ('Cedar Grove', 'Wildwood') - TableScan [TS_11] (rows=1704 width=97) - default@store,store,Tbl:COMPLETE,Col:COMPLETE,Output:["s_store_sk","s_city"] - <-Reducer 9 [SIMPLE_EDGE] - SHUFFLE [RS_22] - PartitionCols:_col4 - Merge Join Operator [MERGEJOIN_139] (rows=42598570 width=185) - Conds:RS_176._col0=RS_152._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"] - <-Map 12 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_152] + Filter Operator [FIL_167] (rows=1855 width=12) + predicate:((hd_dep_count = 2) or (hd_vehicle_count = 1)) + TableScan [TS_12] (rows=7200 width=12) + default@household_demographics,household_demographics,Tbl:COMPLETE,Col:COMPLETE,Output:["hd_demo_sk","hd_dep_count","hd_vehicle_count"] + <-Reducer 7 [SIMPLE_EDGE] + SHUFFLE [RS_23] + PartitionCols:_col2 + Merge Join Operator [MERGEJOIN_143] (rows=2824787 width=4) + Conds:RS_20._col4=RS_161._col0(Inner),Output:["_col1","_col2","_col3","_col5","_col6","_col7","_col8"] + <-Map 13 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_161] PartitionCols:_col0 - Select Operator [SEL_151] (rows=170 width=4) + Select Operator [SEL_160] (rows=14 width=4) Output:["_col0"] - Filter Operator [FIL_150] (rows=170 width=12) - predicate:((d_year) IN (1998, 1999, 2000) and d_dom BETWEEN 1 AND 2) - TableScan [TS_8] (rows=73049 width=12) - default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year","d_dom"] - <-Map 8 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_176] - PartitionCols:_col0 - Select Operator [SEL_175] (rows=457565061 width=343) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"] - Filter Operator [FIL_174] (rows=457565061 width=343) - predicate:((ss_hdemo_sk BETWEEN DynamicValue(RS_26_household_demographics_hd_demo_sk_min) AND DynamicValue(RS_26_household_demographics_hd_demo_sk_max) and in_bloom_filter(ss_hdemo_sk, DynamicValue(RS_26_household_demographics_hd_demo_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_20_date_dim_d_date_sk_min) AND DynamicValue(RS_20_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_20_date_dim_d_date_sk_bloom_filter))) and (ss_store_sk BETWEEN DynamicValue(RS_23_store_s_store_sk_min) AND DynamicValue(RS_23_store_s_store_sk_max) and in_bloom_filter(ss_store_sk, DynamicValue(RS_23_store_s_store_sk_bloom_filter))) and ss_addr_sk is not null and ss_customer_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_5] (rows=575995635 width=343) - default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_customer_sk","ss_hdemo_sk","ss_addr_sk","ss_store_sk","ss_ticket_number","ss_ext_sales_price","ss_ext_list_price","ss_ext_tax"] - <-Reducer 13 [BROADCAST_EDGE] vectorized - BROADCAST [RS_157] - Group By Operator [GBY_156] (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_155] - Group By Operator [GBY_154] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_153] (rows=170 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_151] - <-Reducer 15 [BROADCAST_EDGE] vectorized - BROADCAST [RS_165] - Group By Operator [GBY_164] (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_163] - Group By Operator [GBY_162] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_161] (rows=14 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_159] - <-Reducer 17 [BROADCAST_EDGE] vectorized - BROADCAST [RS_173] - Group By Operator [GBY_172] (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_171] - Group By Operator [GBY_170] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_169] (rows=1855 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_167] + Filter Operator [FIL_159] (rows=14 width=97) + predicate:(s_city) IN ('Cedar Grove', 'Wildwood') + TableScan [TS_9] (rows=1704 width=97) + default@store,store,Tbl:COMPLETE,Col:COMPLETE,Output:["s_store_sk","s_city"] + <-Reducer 6 [SIMPLE_EDGE] + SHUFFLE [RS_20] + PartitionCols:_col4 + Merge Join Operator [MERGEJOIN_142] (rows=42598570 width=185) + Conds:RS_177._col0=RS_153._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"] + <-Map 11 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_153] + PartitionCols:_col0 + Select Operator [SEL_152] (rows=170 width=4) + Output:["_col0"] + Filter Operator [FIL_151] (rows=170 width=12) + predicate:((d_year) IN (1998, 1999, 2000) and d_dom BETWEEN 1 AND 2) + TableScan [TS_6] (rows=73049 width=12) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year","d_dom"] + <-Map 5 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_177] + PartitionCols:_col0 + Select Operator [SEL_176] (rows=457565061 width=343) + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"] + Filter Operator [FIL_175] (rows=457565061 width=343) + predicate:((ss_hdemo_sk BETWEEN DynamicValue(RS_24_household_demographics_hd_demo_sk_min) AND DynamicValue(RS_24_household_demographics_hd_demo_sk_max) and in_bloom_filter(ss_hdemo_sk, DynamicValue(RS_24_household_demographics_hd_demo_sk_bloom_filter))) 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_store_sk BETWEEN DynamicValue(RS_21_store_s_store_sk_min) AND DynamicValue(RS_21_store_s_store_sk_max) and in_bloom_filter(ss_store_sk, DynamicValue(RS_21_store_s_store_sk_bloom_filter))) and ss_addr_sk is not null and ss_customer_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=343) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_customer_sk","ss_hdemo_sk","ss_addr_sk","ss_store_sk","ss_ticket_number","ss_ext_sales_price","ss_ext_list_price","ss_ext_tax"] + <-Reducer 12 [BROADCAST_EDGE] vectorized + BROADCAST [RS_158] + Group By Operator [GBY_157] (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_156] + Group By Operator [GBY_155] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_154] (rows=170 width=4) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_152] + <-Reducer 14 [BROADCAST_EDGE] vectorized + BROADCAST [RS_166] + Group By Operator [GBY_165] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 13 [CUSTOM_SIMPLE_EDGE] vectorized + SHUFFLE [RS_164] + Group By Operator [GBY_163] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_162] (rows=14 width=4) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_160] + <-Reducer 16 [BROADCAST_EDGE] vectorized + BROADCAST [RS_174] + Group By Operator [GBY_173] (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_172] + Group By Operator [GBY_171] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_170] (rows=1855 width=4) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_168] diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/query72.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/query72.q.out index c17750dcdb..7fdbc1f5e0 100644 --- a/ql/src/test/results/clientpositive/perf/tez/constraints/query72.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/query72.q.out @@ -81,217 +81,215 @@ POSTHOOK: Output: hdfs://### HDFS PATH ### Plan optimized by CBO. Vertex dependency in root stage -Map 10 <- Reducer 18 (BROADCAST_EDGE), Reducer 20 (BROADCAST_EDGE), Reducer 22 (BROADCAST_EDGE) -Reducer 11 <- Map 10 (SIMPLE_EDGE), Map 17 (SIMPLE_EDGE) -Reducer 12 <- Map 19 (SIMPLE_EDGE), Reducer 11 (SIMPLE_EDGE) -Reducer 13 <- Map 21 (SIMPLE_EDGE), Reducer 12 (SIMPLE_EDGE) -Reducer 14 <- Map 23 (SIMPLE_EDGE), Reducer 13 (SIMPLE_EDGE) -Reducer 15 <- Map 24 (SIMPLE_EDGE), Reducer 14 (SIMPLE_EDGE) -Reducer 16 <- Map 25 (SIMPLE_EDGE), Reducer 15 (SIMPLE_EDGE) -Reducer 18 <- Map 17 (CUSTOM_SIMPLE_EDGE) -Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 8 (SIMPLE_EDGE) -Reducer 20 <- Map 19 (CUSTOM_SIMPLE_EDGE) -Reducer 22 <- Map 21 (CUSTOM_SIMPLE_EDGE) -Reducer 3 <- Reducer 2 (SIMPLE_EDGE) -Reducer 4 <- Reducer 3 (SIMPLE_EDGE) -Reducer 6 <- Map 5 (SIMPLE_EDGE), Map 9 (SIMPLE_EDGE) -Reducer 7 <- Reducer 16 (ONE_TO_ONE_EDGE), Reducer 6 (SIMPLE_EDGE) -Reducer 8 <- Map 26 (SIMPLE_EDGE), Reducer 7 (SIMPLE_EDGE) +Map 13 <- Reducer 17 (BROADCAST_EDGE), Reducer 19 (BROADCAST_EDGE), Reducer 23 (BROADCAST_EDGE) +Reducer 10 <- Reducer 9 (SIMPLE_EDGE) +Reducer 11 <- Reducer 10 (SIMPLE_EDGE) +Reducer 14 <- Map 13 (SIMPLE_EDGE), Map 16 (SIMPLE_EDGE) +Reducer 15 <- Map 18 (SIMPLE_EDGE), Reducer 14 (SIMPLE_EDGE) +Reducer 17 <- Map 16 (CUSTOM_SIMPLE_EDGE) +Reducer 19 <- Map 18 (CUSTOM_SIMPLE_EDGE) +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 12 (SIMPLE_EDGE) +Reducer 23 <- Map 22 (CUSTOM_SIMPLE_EDGE) +Reducer 3 <- Reducer 15 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) +Reducer 4 <- Map 20 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) +Reducer 5 <- Map 21 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) +Reducer 6 <- Map 22 (SIMPLE_EDGE), Reducer 5 (SIMPLE_EDGE) +Reducer 7 <- Map 24 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE) +Reducer 8 <- Map 25 (SIMPLE_EDGE), Reducer 7 (SIMPLE_EDGE) +Reducer 9 <- Map 26 (SIMPLE_EDGE), Reducer 8 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:100 Stage-1 - Reducer 4 vectorized - File Output Operator [FS_294] - Limit [LIM_293] (rows=100 width=312) + Reducer 11 vectorized + File Output Operator [FS_298] + Limit [LIM_297] (rows=100 width=312) Number of rows:100 - Select Operator [SEL_292] (rows=384313734 width=312) + Select Operator [SEL_296] (rows=27064961 width=312) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - <-Reducer 3 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_291] - Group By Operator [GBY_290] (rows=384313734 width=312) + <-Reducer 10 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_295] + Group By Operator [GBY_294] (rows=27064961 width=312) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["count(VALUE._col0)","count(VALUE._col1)","count(VALUE._col2)"],keys:KEY._col0, KEY._col1, KEY._col2 - <-Reducer 2 [SIMPLE_EDGE] + <-Reducer 9 [SIMPLE_EDGE] SHUFFLE [RS_64] PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_63] (rows=1574305390 width=312) + Group By Operator [GBY_63] (rows=27064961 width=312) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["count(_col3)","count(_col4)","count()"],keys:_col0, _col1, _col2 - Select Operator [SEL_61] (rows=1574305390 width=292) + Select Operator [SEL_61] (rows=69800242 width=292) Output:["_col0","_col1","_col2","_col3","_col4"] - Merge Join Operator [MERGEJOIN_247] (rows=1574305390 width=292) - Conds:RS_249._col0, _col1=RS_59._col4, _col6(Right Outer),Output:["_col15","_col17","_col21","_col27"] - <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_249] + Merge Join Operator [MERGEJOIN_251] (rows=69800242 width=292) + Conds:RS_58._col4, _col6=RS_293._col0, _col1(Left Outer),Output:["_col13","_col15","_col19","_col25"] + <-Map 26 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_293] PartitionCols:_col0, _col1 - Select Operator [SEL_248] (rows=28798881 width=8) + Select Operator [SEL_292] (rows=28798881 width=8) Output:["_col0","_col1"] - TableScan [TS_0] (rows=28798881 width=8) + TableScan [TS_56] (rows=28798881 width=8) default@catalog_returns,catalog_returns,Tbl:COMPLETE,Col:COMPLETE,Output:["cr_item_sk","cr_order_number"] <-Reducer 8 [SIMPLE_EDGE] - SHUFFLE [RS_59] + SHUFFLE [RS_58] PartitionCols:_col4, _col6 - Select Operator [SEL_57] (rows=610435044 width=300) + Select Operator [SEL_55] (rows=27064961 width=300) Output:["_col4","_col6","_col13","_col15","_col19","_col25"] - Merge Join Operator [MERGEJOIN_246] (rows=610435044 width=300) - Conds:RS_54._col0, _col19=RS_289._col0, _col1(Inner),Output:["_col5","_col7","_col14","_col16","_col19","_col23"] - <-Map 26 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_289] - PartitionCols:_col0, _col1 - Select Operator [SEL_288] (rows=73049 width=8) + Merge Join Operator [MERGEJOIN_250] (rows=27064961 width=300) + Conds:RS_52._col2=RS_291._col0(Inner),Output:["_col10","_col12","_col16","_col20","_col23","_col25"] + <-Map 25 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_291] + PartitionCols:_col0 + Select Operator [SEL_290] (rows=27 width=104) Output:["_col0","_col1"] - Filter Operator [FIL_287] (rows=73049 width=8) - predicate:d_week_seq is not null - TableScan [TS_44] (rows=73049 width=8) - default@date_dim,d2,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_week_seq"] + TableScan [TS_30] (rows=27 width=104) + default@warehouse,warehouse,Tbl:COMPLETE,Col:COMPLETE,Output:["w_warehouse_sk","w_warehouse_name"] <-Reducer 7 [SIMPLE_EDGE] - SHUFFLE [RS_54] - PartitionCols:_col0, _col19 - Filter Operator [FIL_53] (rows=545947820 width=311) - predicate:(_col3 < _col17) - Merge Join Operator [MERGEJOIN_245] (rows=1637843460 width=311) - Conds:RS_50._col1=RS_51._col8(Inner),Output:["_col0","_col3","_col5","_col7","_col14","_col16","_col17","_col19","_col23"] - <-Reducer 16 [ONE_TO_ONE_EDGE] - FORWARD [RS_51] - PartitionCols:_col8 - Select Operator [SEL_43] (rows=2726340 width=203) - Output:["_col1","_col8","_col10","_col11","_col13","_col17"] - Merge Join Operator [MERGEJOIN_244] (rows=2726340 width=203) - Conds:RS_40._col4=RS_286._col0(Inner),Output:["_col4","_col6","_col7","_col9","_col15","_col17"] - <-Map 25 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_286] - PartitionCols:_col0 - Select Operator [SEL_285] (rows=462000 width=188) - Output:["_col0","_col1"] - TableScan [TS_22] (rows=462000 width=188) - default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_item_desc"] - <-Reducer 15 [SIMPLE_EDGE] - SHUFFLE [RS_40] - PartitionCols:_col4 - Merge Join Operator [MERGEJOIN_243] (rows=2726340 width=19) - Conds:RS_37._col5=RS_284._col0(Left Outer),Output:["_col4","_col6","_col7","_col9","_col15"] - <-Map 24 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_284] - PartitionCols:_col0 - Select Operator [SEL_283] (rows=2300 width=4) - Output:["_col0"] - TableScan [TS_20] (rows=2300 width=4) - default@promotion,promotion,Tbl:COMPLETE,Col:COMPLETE,Output:["p_promo_sk"] - <-Reducer 14 [SIMPLE_EDGE] - SHUFFLE [RS_37] - PartitionCols:_col5 - Filter Operator [FIL_36] (rows=2726340 width=34) - predicate:(_col14 > _col10) - Merge Join Operator [MERGEJOIN_242] (rows=8179022 width=34) - Conds:RS_33._col1=RS_282._col0(Inner),Output:["_col4","_col5","_col6","_col7","_col9","_col10","_col14"] - <-Map 23 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_282] - PartitionCols:_col0 - Select Operator [SEL_281] (rows=73049 width=12) - Output:["_col0","_col1"] - TableScan [TS_18] (rows=73049 width=98) - default@date_dim,d3,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_date"] - <-Reducer 13 [SIMPLE_EDGE] - SHUFFLE [RS_33] - PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_241] (rows=8179022 width=29) - Conds:RS_30._col3=RS_272._col0(Inner),Output:["_col1","_col4","_col5","_col6","_col7","_col9","_col10"] - <-Map 21 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_272] - PartitionCols:_col0 - Select Operator [SEL_271] (rows=1440 width=4) - Output:["_col0"] - Filter Operator [FIL_270] (rows=1440 width=96) - predicate:(hd_buy_potential = '1001-5000') - TableScan [TS_15] (rows=7200 width=96) - default@household_demographics,household_demographics,Tbl:COMPLETE,Col:COMPLETE,Output:["hd_demo_sk","hd_buy_potential"] - <-Reducer 12 [SIMPLE_EDGE] - SHUFFLE [RS_30] - PartitionCols:_col3 - Merge Join Operator [MERGEJOIN_240] (rows=40895108 width=35) - Conds:RS_27._col2=RS_264._col0(Inner),Output:["_col1","_col3","_col4","_col5","_col6","_col7","_col9","_col10"] - <-Map 19 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_264] - PartitionCols:_col0 - Select Operator [SEL_263] (rows=265971 width=4) - Output:["_col0"] - Filter Operator [FIL_262] (rows=265971 width=89) - predicate:(cd_marital_status = 'M') - TableScan [TS_12] (rows=1861800 width=89) - default@customer_demographics,customer_demographics,Tbl:COMPLETE,Col:COMPLETE,Output:["cd_demo_sk","cd_marital_status"] - <-Reducer 11 [SIMPLE_EDGE] - SHUFFLE [RS_27] - PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_239] (rows=100076475 width=39) - Conds:RS_280._col0=RS_256._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col9","_col10"] - <-Map 17 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_256] - PartitionCols:_col0 - Select Operator [SEL_255] (rows=652 width=16) - Output:["_col0","_col1","_col2"] - Filter Operator [FIL_254] (rows=652 width=106) - predicate:((d_year = 2001) and d_week_seq is not null) - TableScan [TS_9] (rows=73049 width=106) - default@date_dim,d1,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_date","d_week_seq","d_year"] - <-Map 10 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_280] - PartitionCols:_col0 - Select Operator [SEL_279] (rows=282274763 width=31) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] - Filter Operator [FIL_278] (rows=282274763 width=31) - predicate:((cs_bill_cdemo_sk BETWEEN DynamicValue(RS_28_customer_demographics_cd_demo_sk_min) AND DynamicValue(RS_28_customer_demographics_cd_demo_sk_max) and in_bloom_filter(cs_bill_cdemo_sk, DynamicValue(RS_28_customer_demographics_cd_demo_sk_bloom_filter))) and (cs_bill_hdemo_sk BETWEEN DynamicValue(RS_31_household_demographics_hd_demo_sk_min) AND DynamicValue(RS_31_household_demographics_hd_demo_sk_max) and in_bloom_filter(cs_bill_hdemo_sk, DynamicValue(RS_31_household_demographics_hd_demo_sk_bloom_filter))) and (cs_sold_date_sk BETWEEN DynamicValue(RS_25_d1_d_date_sk_min) AND DynamicValue(RS_25_d1_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_25_d1_d_date_sk_bloom_filter))) and cs_bill_cdemo_sk is not null and cs_bill_hdemo_sk is not null and cs_ship_date_sk is not null and cs_sold_date_sk is not null) - TableScan [TS_6] (rows=287989836 width=31) - default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["cs_sold_date_sk","cs_ship_date_sk","cs_bill_cdemo_sk","cs_bill_hdemo_sk","cs_item_sk","cs_promo_sk","cs_order_number","cs_quantity"] - <-Reducer 18 [BROADCAST_EDGE] vectorized - BROADCAST [RS_261] - Group By Operator [GBY_260] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 17 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_259] - Group By Operator [GBY_258] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_257] (rows=652 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_255] - <-Reducer 20 [BROADCAST_EDGE] vectorized - BROADCAST [RS_269] - Group By Operator [GBY_268] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 19 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_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=265971 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_263] - <-Reducer 22 [BROADCAST_EDGE] vectorized - BROADCAST [RS_277] - Group By Operator [GBY_276] (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_275] - 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_273] (rows=1440 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_271] - <-Reducer 6 [SIMPLE_EDGE] - SHUFFLE [RS_50] - PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_238] (rows=37584000 width=111) - Conds:RS_251._col2=RS_253._col0(Inner),Output:["_col0","_col1","_col3","_col5"] - <-Map 5 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_251] - PartitionCols:_col2 - Select Operator [SEL_250] (rows=37584000 width=15) - Output:["_col0","_col1","_col2","_col3"] - TableScan [TS_2] (rows=37584000 width=15) - default@inventory,inventory,Tbl:COMPLETE,Col:COMPLETE,Output:["inv_date_sk","inv_item_sk","inv_warehouse_sk","inv_quantity_on_hand"] - <-Map 9 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_253] - PartitionCols:_col0 - Select Operator [SEL_252] (rows=27 width=104) - Output:["_col0","_col1"] - TableScan [TS_4] (rows=27 width=104) - default@warehouse,warehouse,Tbl:COMPLETE,Col:COMPLETE,Output:["w_warehouse_sk","w_warehouse_name"] + SHUFFLE [RS_52] + PartitionCols:_col2 + Merge Join Operator [MERGEJOIN_249] (rows=27064961 width=204) + Conds:RS_49._col10=RS_289._col0(Inner),Output:["_col2","_col10","_col12","_col16","_col20","_col23"] + <-Map 24 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_289] + PartitionCols:_col0 + Select Operator [SEL_288] (rows=462000 width=188) + Output:["_col0","_col1"] + TableScan [TS_28] (rows=462000 width=188) + default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_item_desc"] + <-Reducer 6 [SIMPLE_EDGE] + SHUFFLE [RS_49] + PartitionCols:_col10 + Filter Operator [FIL_48] (rows=27064961 width=36) + predicate:(_col18 > _col21) + Merge Join Operator [MERGEJOIN_248] (rows=81194883 width=36) + Conds:RS_45._col6, _col5=RS_275._col0, _col1(Inner),Output:["_col2","_col10","_col12","_col16","_col18","_col20","_col21"] + <-Map 22 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_275] + PartitionCols:_col0, _col1 + Select Operator [SEL_274] (rows=652 width=16) + Output:["_col0","_col1","_col2"] + Filter Operator [FIL_273] (rows=652 width=106) + predicate:((d_year = 2001) and d_week_seq is not null) + TableScan [TS_25] (rows=73049 width=106) + default@date_dim,d1,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_date","d_week_seq","d_year"] + <-Reducer 5 [SIMPLE_EDGE] + SHUFFLE [RS_45] + PartitionCols:_col6, _col5 + Merge Join Operator [MERGEJOIN_247] (rows=1637845262 width=31) + Conds:RS_42._col7=RS_287._col0(Inner),Output:["_col2","_col5","_col6","_col10","_col12","_col16","_col18"] + <-Map 21 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_287] + PartitionCols:_col0 + Select Operator [SEL_286] (rows=73049 width=12) + Output:["_col0","_col1"] + TableScan [TS_23] (rows=73049 width=98) + default@date_dim,d3,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_date"] + <-Reducer 4 [SIMPLE_EDGE] + SHUFFLE [RS_42] + PartitionCols:_col7 + Merge Join Operator [MERGEJOIN_246] (rows=1637845262 width=27) + Conds:RS_39._col11=RS_285._col0(Left Outer),Output:["_col2","_col5","_col6","_col7","_col10","_col12","_col16"] + <-Map 20 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_285] + PartitionCols:_col0 + Select Operator [SEL_284] (rows=2300 width=4) + Output:["_col0"] + TableScan [TS_21] (rows=2300 width=4) + default@promotion,promotion,Tbl:COMPLETE,Col:COMPLETE,Output:["p_promo_sk"] + <-Reducer 3 [SIMPLE_EDGE] + SHUFFLE [RS_39] + PartitionCols:_col11 + Filter Operator [FIL_38] (rows=1637845262 width=35) + predicate:(_col3 < _col13) + Merge Join Operator [MERGEJOIN_245] (rows=4913535787 width=35) + Conds:RS_35._col1=RS_36._col4(Inner),Output:["_col2","_col3","_col5","_col6","_col7","_col10","_col11","_col12","_col13"] + <-Reducer 15 [SIMPLE_EDGE] + SHUFFLE [RS_36] + PartitionCols:_col4 + Merge Join Operator [MERGEJOIN_244] (rows=8179029 width=21) + Conds:RS_17._col3=RS_267._col0(Inner),Output:["_col0","_col1","_col4","_col5","_col6","_col7"] + <-Map 18 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_267] + PartitionCols:_col0 + Select Operator [SEL_266] (rows=1440 width=4) + Output:["_col0"] + Filter Operator [FIL_265] (rows=1440 width=96) + predicate:(hd_buy_potential = '1001-5000') + TableScan [TS_11] (rows=7200 width=96) + default@household_demographics,household_demographics,Tbl:COMPLETE,Col:COMPLETE,Output:["hd_demo_sk","hd_buy_potential"] + <-Reducer 14 [SIMPLE_EDGE] + SHUFFLE [RS_17] + PartitionCols:_col3 + Merge Join Operator [MERGEJOIN_243] (rows=40895144 width=27) + Conds:RS_283._col2=RS_259._col0(Inner),Output:["_col0","_col1","_col3","_col4","_col5","_col6","_col7"] + <-Map 16 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_259] + PartitionCols:_col0 + Select Operator [SEL_258] (rows=265971 width=4) + Output:["_col0"] + Filter Operator [FIL_257] (rows=265971 width=89) + predicate:(cd_marital_status = 'M') + TableScan [TS_8] (rows=1861800 width=89) + default@customer_demographics,customer_demographics,Tbl:COMPLETE,Col:COMPLETE,Output:["cd_demo_sk","cd_marital_status"] + <-Map 13 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_283] + PartitionCols:_col2 + Select Operator [SEL_282] (rows=282274763 width=31) + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] + Filter Operator [FIL_281] (rows=282274763 width=31) + predicate:((cs_bill_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(cs_bill_cdemo_sk, DynamicValue(RS_15_customer_demographics_cd_demo_sk_bloom_filter))) and (cs_bill_hdemo_sk BETWEEN DynamicValue(RS_18_household_demographics_hd_demo_sk_min) AND DynamicValue(RS_18_household_demographics_hd_demo_sk_max) and in_bloom_filter(cs_bill_hdemo_sk, DynamicValue(RS_18_household_demographics_hd_demo_sk_bloom_filter))) and (cs_sold_date_sk BETWEEN DynamicValue(RS_46_d1_d_date_sk_min) AND DynamicValue(RS_46_d1_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_46_d1_d_date_sk_bloom_filter))) and cs_bill_cdemo_sk is not null and cs_bill_hdemo_sk is not null and cs_ship_date_sk is not null and cs_sold_date_sk is not null) + TableScan [TS_5] (rows=287989836 width=31) + default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["cs_sold_date_sk","cs_ship_date_sk","cs_bill_cdemo_sk","cs_bill_hdemo_sk","cs_item_sk","cs_promo_sk","cs_order_number","cs_quantity"] + <-Reducer 17 [BROADCAST_EDGE] vectorized + BROADCAST [RS_264] + Group By Operator [GBY_263] (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_262] + Group By Operator [GBY_261] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_260] (rows=265971 width=4) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_258] + <-Reducer 19 [BROADCAST_EDGE] vectorized + BROADCAST [RS_272] + Group By Operator [GBY_271] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 18 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_270] + Group By Operator [GBY_269] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_268] (rows=1440 width=4) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_266] + <-Reducer 23 [BROADCAST_EDGE] vectorized + BROADCAST [RS_280] + Group By Operator [GBY_279] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 22 [CUSTOM_SIMPLE_EDGE] vectorized + SHUFFLE [RS_278] + Group By Operator [GBY_277] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_276] (rows=652 width=4) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_274] + <-Reducer 2 [SIMPLE_EDGE] + SHUFFLE [RS_35] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_242] (rows=37584000 width=15) + Conds:RS_253._col0=RS_256._col0(Inner),Output:["_col1","_col2","_col3","_col5"] + <-Map 1 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_253] + PartitionCols:_col0 + Select Operator [SEL_252] (rows=37584000 width=15) + Output:["_col0","_col1","_col2","_col3"] + TableScan [TS_0] (rows=37584000 width=15) + default@inventory,inventory,Tbl:COMPLETE,Col:COMPLETE,Output:["inv_date_sk","inv_item_sk","inv_warehouse_sk","inv_quantity_on_hand"] + <-Map 12 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_256] + PartitionCols:_col0 + Select Operator [SEL_255] (rows=73049 width=8) + Output:["_col0","_col1"] + Filter Operator [FIL_254] (rows=73049 width=8) + predicate:d_week_seq is not null + TableScan [TS_2] (rows=73049 width=8) + default@date_dim,d2,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_week_seq"] diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/query74.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/query74.q.out index 12ed5c8ecb..525217b526 100644 --- a/ql/src/test/results/clientpositive/perf/tez/constraints/query74.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/query74.q.out @@ -131,10 +131,10 @@ POSTHOOK: Output: hdfs://### HDFS PATH ### Plan optimized by CBO. Vertex dependency in root stage -Map 1 <- Reducer 23 (BROADCAST_EDGE) -Map 13 <- Reducer 25 (BROADCAST_EDGE) +Map 1 <- Reducer 24 (BROADCAST_EDGE) +Map 13 <- Reducer 23 (BROADCAST_EDGE) Map 17 <- Reducer 22 (BROADCAST_EDGE) -Map 9 <- Reducer 24 (BROADCAST_EDGE) +Map 9 <- Reducer 25 (BROADCAST_EDGE) Reducer 10 <- Map 21 (SIMPLE_EDGE), Map 9 (SIMPLE_EDGE) Reducer 11 <- Map 26 (SIMPLE_EDGE), Reducer 10 (SIMPLE_EDGE) Reducer 12 <- Reducer 11 (SIMPLE_EDGE) @@ -164,16 +164,16 @@ Stage-0 File Output Operator [FS_348] Limit [LIM_347] (rows=100 width=280) Number of rows:100 - Select Operator [SEL_346] (rows=12248093 width=280) + Select Operator [SEL_346] (rows=12248094 width=280) Output:["_col0","_col1","_col2"] <-Reducer 7 [SIMPLE_EDGE] SHUFFLE [RS_89] - Select Operator [SEL_88] (rows=12248093 width=280) + Select Operator [SEL_88] (rows=12248094 width=280) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_87] (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_283] (rows=24496186 width=732) - Conds:RS_84._col2=RS_345._col0(Inner),Output:["_col1","_col3","_col5","_col6","_col7","_col8","_col9","_col10"] + Filter Operator [FIL_87] (rows=12248094 width=732) + predicate:CASE WHEN (_col4 is not null) THEN (CASE WHEN (_col2) THEN (((_col6 / _col1) > (_col10 / _col4))) ELSE ((null > (_col10 / _col4))) END) ELSE (CASE WHEN (_col2) THEN (((_col6 / _col1) > null)) ELSE (null) END) END + Merge Join Operator [MERGEJOIN_283] (rows=24496188 width=732) + Conds:RS_84._col3=RS_345._col0(Inner),Output:["_col1","_col2","_col4","_col6","_col7","_col8","_col9","_col10"] <-Reducer 20 [SIMPLE_EDGE] vectorized SHUFFLE [RS_345] PartitionCols:_col0 @@ -229,96 +229,143 @@ Stage-0 Please refer to the previous Select Operator [SEL_287] <-Reducer 6 [ONE_TO_ONE_EDGE] FORWARD [RS_84] - PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_282] (rows=20485011 width=440) - Conds:RS_81._col2=RS_338._col0(Inner),Output:["_col1","_col2","_col3","_col5","_col6"] + PartitionCols:_col3 + Merge Join Operator [MERGEJOIN_282] (rows=20485012 width=440) + Conds:RS_81._col3=RS_338._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col6"] <-Reducer 16 [SIMPLE_EDGE] vectorized SHUFFLE [RS_338] PartitionCols:_col0 - Select Operator [SEL_337] (rows=17130654 width=216) - Output:["_col0","_col1","_col2"] - Filter Operator [FIL_336] (rows=17130654 width=212) - predicate:(_col3 > 0) - Select Operator [SEL_335] (rows=51391963 width=212) - Output:["_col0","_col3"] - Group By Operator [GBY_334] (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_55] - PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_54] (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_50._col1=RS_315._col0(Inner),Output:["_col2","_col5","_col6","_col7"] - <-Map 26 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_315] + Select Operator [SEL_337] (rows=51391963 width=212) + Output:["_col0","_col1"] + Group By Operator [GBY_336] (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_56] + PartitionCols:_col0, _col1, _col2 + Group By Operator [GBY_55] (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_51._col1=RS_313._col0(Inner),Output:["_col2","_col5","_col6","_col7"] + <-Map 26 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_313] + PartitionCols:_col0 + Please refer to the previous Select Operator [SEL_311] + <-Reducer 14 [SIMPLE_EDGE] + SHUFFLE [RS_51] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_277] (rows=51391963 width=115) + Conds:RS_335._col0=RS_292._col0(Inner),Output:["_col1","_col2"] + <-Map 21 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_292] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_311] - <-Reducer 14 [SIMPLE_EDGE] - SHUFFLE [RS_50] - PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_277] (rows=51391963 width=115) - Conds:RS_333._col0=RS_296._col0(Inner),Output:["_col1","_col2"] - <-Map 21 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_296] - PartitionCols:_col0 - Select Operator [SEL_289] (rows=652 width=4) - Output:["_col0"] - Filter Operator [FIL_286] (rows=652 width=8) - predicate:((d_year = 2001) and (d_year) IN (2001, 2002)) - Please refer to the previous TableScan [TS_62] - <-Map 13 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_333] - PartitionCols:_col0 - Select Operator [SEL_332] (rows=143930993 width=119) - Output:["_col0","_col1","_col2"] - Filter Operator [FIL_331] (rows=143930993 width=119) - predicate:((ws_sold_date_sk BETWEEN DynamicValue(RS_48_date_dim_d_date_sk_min) AND DynamicValue(RS_48_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_48_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_39] (rows=144002668 width=119) - default@web_sales,web_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_sold_date_sk","ws_bill_customer_sk","ws_net_paid"] - <-Reducer 25 [BROADCAST_EDGE] vectorized - BROADCAST [RS_330] - Group By Operator [GBY_329] (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_305] - Group By Operator [GBY_301] (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_289] + Please refer to the previous Select Operator [SEL_287] + <-Map 13 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_335] + PartitionCols:_col0 + Select Operator [SEL_334] (rows=143930993 width=119) + Output:["_col0","_col1","_col2"] + Filter Operator [FIL_333] (rows=143930993 width=119) + predicate:((ws_sold_date_sk BETWEEN DynamicValue(RS_49_date_dim_d_date_sk_min) AND DynamicValue(RS_49_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_49_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_40] (rows=144002668 width=119) + default@web_sales,web_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_sold_date_sk","ws_bill_customer_sk","ws_net_paid"] + <-Reducer 23 [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 21 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_303] + Group By Operator [GBY_299] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_293] (rows=652 width=4) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_287] <-Reducer 5 [ONE_TO_ONE_EDGE] FORWARD [RS_81] - PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_281] (rows=31888273 width=324) - Conds:RS_318._col0=RS_328._col0(Inner),Output:["_col1","_col2","_col3"] + PartitionCols:_col3 + Merge Join Operator [MERGEJOIN_281] (rows=17130654 width=328) + Conds:RS_320._col0=RS_330._col0(Inner),Output:["_col1","_col2","_col3","_col4"] <-Reducer 12 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_328] + SHUFFLE [RS_330] PartitionCols:_col0 - Select Operator [SEL_327] (rows=26666666 width=212) + Select Operator [SEL_329] (rows=26666666 width=212) Output:["_col0","_col1"] - Filter Operator [FIL_326] (rows=26666666 width=212) + Filter Operator [FIL_328] (rows=26666666 width=212) predicate:(_col3 > 0) - Select Operator [SEL_325] (rows=80000000 width=212) + Select Operator [SEL_327] (rows=80000000 width=212) Output:["_col0","_col3"] - Group By Operator [GBY_324] (rows=80000000 width=392) + Group By Operator [GBY_326] (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_35] + SHUFFLE [RS_36] PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_34] (rows=80000000 width=392) + Group By Operator [GBY_35] (rows=80000000 width=392) Output:["_col0","_col1","_col2","_col3"],aggregations:["max(_col2)"],keys:_col5, _col6, _col7 Merge Join Operator [MERGEJOIN_276] (rows=187573258 width=377) - Conds:RS_30._col1=RS_314._col0(Inner),Output:["_col2","_col5","_col6","_col7"] + Conds:RS_31._col1=RS_315._col0(Inner),Output:["_col2","_col5","_col6","_col7"] <-Map 26 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_314] + SHUFFLE [RS_315] PartitionCols:_col0 Please refer to the previous Select Operator [SEL_311] <-Reducer 10 [SIMPLE_EDGE] - SHUFFLE [RS_30] + SHUFFLE [RS_31] PartitionCols:_col1 Merge Join Operator [MERGEJOIN_275] (rows=187573258 width=101) - Conds:RS_323._col0=RS_294._col0(Inner),Output:["_col1","_col2"] + Conds:RS_325._col0=RS_296._col0(Inner),Output:["_col1","_col2"] + <-Map 21 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_296] + PartitionCols:_col0 + Select Operator [SEL_289] (rows=652 width=4) + Output:["_col0"] + Filter Operator [FIL_286] (rows=652 width=8) + predicate:((d_year = 2001) and (d_year) IN (2001, 2002)) + Please refer to the previous TableScan [TS_62] + <-Map 9 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_325] + PartitionCols:_col0 + Select Operator [SEL_324] (rows=525327388 width=114) + Output:["_col0","_col1","_col2"] + Filter Operator [FIL_323] (rows=525327388 width=114) + predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_29_date_dim_d_date_sk_min) AND DynamicValue(RS_29_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_29_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=114) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_customer_sk","ss_net_paid"] + <-Reducer 25 [BROADCAST_EDGE] vectorized + BROADCAST [RS_322] + Group By Operator [GBY_321] (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_305] + Group By Operator [GBY_301] (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_289] + <-Reducer 4 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_320] + PartitionCols:_col0 + Select Operator [SEL_319] (rows=17130654 width=216) + Output:["_col0","_col1","_col2"] + Filter Operator [FIL_318] (rows=17130654 width=212) + predicate:(_col3 > 0) + Select Operator [SEL_317] (rows=51391963 width=212) + Output:["_col0","_col3"] + Group By Operator [GBY_316] (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_16] + PartitionCols:_col0, _col1, _col2 + Group By Operator [GBY_15] (rows=51391963 width=392) + Output:["_col0","_col1","_col2","_col3"],aggregations:["max(_col2)"],keys:_col5, _col6, _col7 + Merge Join Operator [MERGEJOIN_274] (rows=51391963 width=391) + Conds:RS_11._col1=RS_314._col0(Inner),Output:["_col2","_col5","_col6","_col7"] + <-Map 26 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_314] + PartitionCols:_col0 + Please refer to the previous Select Operator [SEL_311] + <-Reducer 2 [SIMPLE_EDGE] + SHUFFLE [RS_11] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_273] (rows=51391963 width=115) + Conds:RS_310._col0=RS_294._col0(Inner),Output:["_col1","_col2"] <-Map 21 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_294] PartitionCols:_col0 @@ -327,18 +374,18 @@ Stage-0 Filter Operator [FIL_285] (rows=652 width=8) predicate:((d_year = 2001) and (d_year) IN (2001, 2002)) Please refer to the previous TableScan [TS_62] - <-Map 9 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_323] + <-Map 1 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_310] PartitionCols:_col0 - Select Operator [SEL_322] (rows=525327388 width=114) + Select Operator [SEL_309] (rows=143930993 width=119) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_321] (rows=525327388 width=114) - predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_28_date_dim_d_date_sk_min) AND DynamicValue(RS_28_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_28_date_dim_d_date_sk_bloom_filter))) and ss_customer_sk is not null and ss_sold_date_sk is not null) - TableScan [TS_19] (rows=575995635 width=114) - default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_customer_sk","ss_net_paid"] + Filter Operator [FIL_308] (rows=143930993 width=119) + predicate:((ws_sold_date_sk BETWEEN DynamicValue(RS_9_date_dim_d_date_sk_min) AND DynamicValue(RS_9_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_9_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=119) + default@web_sales,web_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_sold_date_sk","ws_bill_customer_sk","ws_net_paid"] <-Reducer 24 [BROADCAST_EDGE] vectorized - BROADCAST [RS_320] - Group By Operator [GBY_319] (rows=1 width=12) + BROADCAST [RS_307] + Group By Operator [GBY_306] (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_304] @@ -347,51 +394,4 @@ Stage-0 Select Operator [SEL_295] (rows=652 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_288] - <-Reducer 4 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_318] - PartitionCols:_col0 - Select Operator [SEL_317] (rows=51391963 width=212) - Output:["_col0","_col1"] - Group By Operator [GBY_316] (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_16] - PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_15] (rows=51391963 width=392) - Output:["_col0","_col1","_col2","_col3"],aggregations:["max(_col2)"],keys:_col5, _col6, _col7 - Merge Join Operator [MERGEJOIN_274] (rows=51391963 width=391) - Conds:RS_11._col1=RS_313._col0(Inner),Output:["_col2","_col5","_col6","_col7"] - <-Map 26 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_313] - PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_311] - <-Reducer 2 [SIMPLE_EDGE] - SHUFFLE [RS_11] - PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_273] (rows=51391963 width=115) - Conds:RS_310._col0=RS_292._col0(Inner),Output:["_col1","_col2"] - <-Map 21 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_292] - PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_287] - <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_310] - PartitionCols:_col0 - Select Operator [SEL_309] (rows=143930993 width=119) - Output:["_col0","_col1","_col2"] - Filter Operator [FIL_308] (rows=143930993 width=119) - predicate:((ws_sold_date_sk BETWEEN DynamicValue(RS_9_date_dim_d_date_sk_min) AND DynamicValue(RS_9_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_9_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=119) - default@web_sales,web_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_sold_date_sk","ws_bill_customer_sk","ws_net_paid"] - <-Reducer 23 [BROADCAST_EDGE] vectorized - BROADCAST [RS_307] - Group By Operator [GBY_306] (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_303] - Group By Operator [GBY_299] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_293] (rows=652 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_287] diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/query76.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/query76.q.out index 56d4500fa1..f6d78256e2 100644 --- a/ql/src/test/results/clientpositive/perf/tez/constraints/query76.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/query76.q.out @@ -93,29 +93,29 @@ Stage-0 Select Operator [SEL_157] (rows=1433911 width=399) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] Merge Join Operator [MERGEJOIN_156] (rows=1433911 width=209) - Conds:RS_39._col0=RS_185._col0(Inner),Output:["_col2","_col4","_col6","_col7"] + Conds:RS_39._col1=RS_185._col0(Inner),Output:["_col2","_col4","_col5","_col7"] <-Map 16 [SIMPLE_EDGE] vectorized SHUFFLE [RS_185] PartitionCols:_col0 - Select Operator [SEL_184] (rows=73049 width=12) - Output:["_col0","_col1","_col2"] - TableScan [TS_34] (rows=73049 width=12) - default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year","d_qoy"] + Select Operator [SEL_184] (rows=462000 width=94) + Output:["_col0","_col1"] + TableScan [TS_34] (rows=462000 width=94) + default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_category"] <-Reducer 9 [SIMPLE_EDGE] SHUFFLE [RS_39] - PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_142] (rows=1433911 width=205) - Conds:RS_183._col1=RS_165._col0(Inner),Output:["_col0","_col2","_col4"] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_142] (rows=1433911 width=123) + Conds:RS_183._col0=RS_165._col0(Inner),Output:["_col1","_col2","_col4","_col5"] <-Map 1 [SIMPLE_EDGE] vectorized SHUFFLE [RS_165] PartitionCols:_col0 - Select Operator [SEL_162] (rows=462000 width=94) - Output:["_col0","_col1"] - TableScan [TS_0] (rows=462000 width=94) - default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_category"] + Select Operator [SEL_162] (rows=73049 width=12) + Output:["_col0","_col1","_col2"] + TableScan [TS_0] (rows=73049 width=12) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year","d_qoy"] <-Map 15 [SIMPLE_EDGE] vectorized SHUFFLE [RS_183] - PartitionCols:_col1 + PartitionCols:_col0 Select Operator [SEL_182] (rows=1433911 width=119) Output:["_col0","_col1","_col2"] Filter Operator [FIL_181] (rows=1433911 width=123) @@ -132,26 +132,26 @@ Stage-0 Select Operator [SEL_145] (rows=24749363 width=387) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] Merge Join Operator [MERGEJOIN_144] (rows=24749363 width=204) - Conds:RS_10._col2=RS_170._col0(Inner),Output:["_col1","_col4","_col6","_col7"] + Conds:RS_10._col4=RS_170._col0(Inner),Output:["_col1","_col2","_col5","_col7"] <-Map 12 [SIMPLE_EDGE] vectorized SHUFFLE [RS_170] PartitionCols:_col0 - Select Operator [SEL_169] (rows=73049 width=12) - Output:["_col0","_col1","_col2"] - TableScan [TS_5] (rows=73049 width=12) - default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year","d_qoy"] + Select Operator [SEL_169] (rows=462000 width=94) + Output:["_col0","_col1"] + TableScan [TS_5] (rows=462000 width=94) + default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_category"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_10] - PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_138] (rows=24749363 width=200) - Conds:RS_163._col0=RS_168._col1(Inner),Output:["_col1","_col2","_col4"] + PartitionCols:_col4 + Merge Join Operator [MERGEJOIN_138] (rows=24749363 width=118) + Conds:RS_163._col0=RS_168._col0(Inner),Output:["_col1","_col2","_col4","_col5"] <-Map 1 [SIMPLE_EDGE] vectorized SHUFFLE [RS_163] PartitionCols:_col0 Please refer to the previous Select Operator [SEL_162] <-Map 11 [SIMPLE_EDGE] vectorized SHUFFLE [RS_168] - PartitionCols:_col1 + PartitionCols:_col0 Select Operator [SEL_167] (rows=24749363 width=114) Output:["_col0","_col1","_col2"] Filter Operator [FIL_166] (rows=24749363 width=118) @@ -168,26 +168,26 @@ Stage-0 Select Operator [SEL_151] (rows=35728 width=394) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] Merge Join Operator [MERGEJOIN_150] (rows=35728 width=209) - Conds:RS_24._col0=RS_180._col0(Inner),Output:["_col2","_col4","_col6","_col7"] + Conds:RS_24._col1=RS_180._col0(Inner),Output:["_col2","_col4","_col5","_col7"] <-Map 14 [SIMPLE_EDGE] vectorized SHUFFLE [RS_180] PartitionCols:_col0 - Select Operator [SEL_179] (rows=73049 width=12) - Output:["_col0","_col1","_col2"] - TableScan [TS_19] (rows=73049 width=12) - default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year","d_qoy"] + Select Operator [SEL_179] (rows=462000 width=94) + Output:["_col0","_col1"] + TableScan [TS_19] (rows=462000 width=94) + default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_category"] <-Reducer 7 [SIMPLE_EDGE] SHUFFLE [RS_24] - PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_140] (rows=35728 width=205) - Conds:RS_178._col1=RS_164._col0(Inner),Output:["_col0","_col2","_col4"] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_140] (rows=35728 width=123) + Conds:RS_178._col0=RS_164._col0(Inner),Output:["_col1","_col2","_col4","_col5"] <-Map 1 [SIMPLE_EDGE] vectorized SHUFFLE [RS_164] PartitionCols:_col0 Please refer to the previous Select Operator [SEL_162] <-Map 13 [SIMPLE_EDGE] vectorized SHUFFLE [RS_178] - PartitionCols:_col1 + PartitionCols:_col0 Select Operator [SEL_177] (rows=35728 width=119) Output:["_col0","_col1","_col2"] Filter Operator [FIL_176] (rows=35728 width=123) diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/query83.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/query83.q.out index 4dd50d17c2..16f85beb14 100644 --- a/ql/src/test/results/clientpositive/perf/tez/constraints/query83.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/query83.q.out @@ -145,190 +145,190 @@ POSTHOOK: Output: hdfs://### HDFS PATH ### Plan optimized by CBO. Vertex dependency in root stage -Reducer 10 <- Reducer 16 (SIMPLE_EDGE), Reducer 9 (SIMPLE_EDGE) +Reducer 10 <- Map 20 (SIMPLE_EDGE), Reducer 9 (SIMPLE_EDGE) Reducer 11 <- Reducer 10 (SIMPLE_EDGE) -Reducer 12 <- Map 22 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) -Reducer 13 <- Reducer 12 (SIMPLE_EDGE), Reducer 16 (SIMPLE_EDGE) +Reducer 12 <- Map 22 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) +Reducer 13 <- Map 20 (SIMPLE_EDGE), Reducer 12 (SIMPLE_EDGE) Reducer 14 <- Reducer 13 (SIMPLE_EDGE) -Reducer 16 <- Map 15 (SIMPLE_EDGE), Reducer 19 (ONE_TO_ONE_EDGE) -Reducer 18 <- Map 17 (SIMPLE_EDGE), Map 20 (SIMPLE_EDGE) -Reducer 19 <- Reducer 18 (SIMPLE_EDGE) -Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) -Reducer 3 <- Reducer 16 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) -Reducer 4 <- Reducer 3 (SIMPLE_EDGE) -Reducer 5 <- Reducer 11 (ONE_TO_ONE_EDGE), Reducer 4 (ONE_TO_ONE_EDGE) -Reducer 6 <- Reducer 14 (ONE_TO_ONE_EDGE), Reducer 5 (ONE_TO_ONE_EDGE) -Reducer 7 <- Reducer 6 (SIMPLE_EDGE) -Reducer 9 <- Map 21 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) +Reducer 16 <- Map 15 (SIMPLE_EDGE), Map 18 (SIMPLE_EDGE) +Reducer 17 <- Reducer 16 (SIMPLE_EDGE) +Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 17 (ONE_TO_ONE_EDGE) +Reducer 3 <- Map 19 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) +Reducer 4 <- Map 20 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) +Reducer 5 <- Reducer 4 (SIMPLE_EDGE) +Reducer 6 <- Reducer 11 (ONE_TO_ONE_EDGE), Reducer 5 (ONE_TO_ONE_EDGE) +Reducer 7 <- Reducer 14 (ONE_TO_ONE_EDGE), Reducer 6 (ONE_TO_ONE_EDGE) +Reducer 8 <- Reducer 7 (SIMPLE_EDGE) +Reducer 9 <- Map 21 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:100 Stage-1 - Reducer 7 vectorized - File Output Operator [FS_395] - Limit [LIM_394] (rows=57 width=260) + Reducer 8 vectorized + File Output Operator [FS_398] + Limit [LIM_397] (rows=100 width=260) Number of rows:100 - Select Operator [SEL_393] (rows=57 width=260) + Select Operator [SEL_396] (rows=1260 width=260) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] - <-Reducer 6 [SIMPLE_EDGE] - SHUFFLE [RS_124] - Select Operator [SEL_123] (rows=57 width=260) + <-Reducer 7 [SIMPLE_EDGE] + SHUFFLE [RS_121] + Select Operator [SEL_120] (rows=1260 width=260) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] - Merge Join Operator [MERGEJOIN_360] (rows=57 width=132) - Conds:RS_120._col0=RS_392._col0(Inner),Output:["_col0","_col1","_col3","_col5","_col6"] + Merge Join Operator [MERGEJOIN_363] (rows=1260 width=132) + Conds:RS_117._col0=RS_395._col0(Inner),Output:["_col0","_col1","_col3","_col5","_col6"] <-Reducer 14 [ONE_TO_ONE_EDGE] vectorized - FORWARD [RS_392] + FORWARD [RS_395] PartitionCols:_col0 - Select Operator [SEL_391] (rows=57 width=116) + Select Operator [SEL_394] (rows=1260 width=116) Output:["_col0","_col1","_col2"] - Group By Operator [GBY_390] (rows=57 width=108) + Group By Operator [GBY_393] (rows=1260 width=108) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 <-Reducer 13 [SIMPLE_EDGE] - SHUFFLE [RS_114] + SHUFFLE [RS_111] PartitionCols:_col0 - Group By Operator [GBY_113] (rows=57 width=108) - Output:["_col0","_col1"],aggregations:["sum(_col2)"],keys:_col4 - Merge Join Operator [MERGEJOIN_358] (rows=2521 width=100) - Conds:RS_109._col0=RS_110._col0(Inner),Output:["_col2","_col4"] - <-Reducer 16 [SIMPLE_EDGE] - SHUFFLE [RS_110] + Group By Operator [GBY_110] (rows=1260 width=108) + Output:["_col0","_col1"],aggregations:["sum(_col5)"],keys:_col7 + Merge Join Operator [MERGEJOIN_361] (rows=2521 width=100) + Conds:RS_106._col4=RS_382._col0(Inner),Output:["_col5","_col7"] + <-Map 20 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_382] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_349] (rows=2 width=4) - Conds:RS_370._col1=RS_379._col0(Inner),Output:["_col0"] - <-Map 15 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_370] - PartitionCols:_col1 - Select Operator [SEL_369] (rows=73049 width=98) - Output:["_col0","_col1"] - Filter Operator [FIL_368] (rows=73049 width=98) - predicate:d_date is not null - TableScan [TS_5] (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_379] - PartitionCols:_col0 - Group By Operator [GBY_378] (rows=2 width=94) - Output:["_col0"],keys:KEY._col0 - <-Reducer 18 [SIMPLE_EDGE] - SHUFFLE [RS_21] - PartitionCols:_col0 - Group By Operator [GBY_20] (rows=2 width=94) - Output:["_col0"],keys:_col0 - Merge Join Operator [MERGEJOIN_348] (rows=5 width=94) - Conds:RS_373._col1=RS_377._col0(Left Semi),Output:["_col0"] - <-Map 17 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_373] - PartitionCols:_col1 - Select Operator [SEL_372] (rows=73049 width=98) - Output:["_col0","_col1"] - Filter Operator [FIL_371] (rows=73049 width=98) - predicate:(d_date is not null and d_week_seq is not null) - TableScan [TS_8] (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_377] - PartitionCols:_col0 - Group By Operator [GBY_376] (rows=1 width=4) - Output:["_col0"],keys:_col0 - Select Operator [SEL_375] (rows=2 width=4) - Output:["_col0"] - Filter Operator [FIL_374] (rows=2 width=98) - predicate:((d_date) IN ('1998-01-02', '1998-10-15', '1998-11-10') and d_week_seq is not null) - TableScan [TS_11] (rows=73049 width=98) - default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date","d_week_seq"] + Select Operator [SEL_379] (rows=462000 width=104) + Output:["_col0","_col1"] + TableScan [TS_22] (rows=462000 width=104) + default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_item_id"] <-Reducer 12 [SIMPLE_EDGE] - SHUFFLE [RS_109] - PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_353] (rows=13749816 width=107) - Conds:RS_389._col1=RS_367._col0(Inner),Output:["_col0","_col2","_col4"] - <-Map 8 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_367] + SHUFFLE [RS_106] + PartitionCols:_col4 + Merge Join Operator [MERGEJOIN_360] (rows=2521 width=4) + Conds:RS_103._col0=RS_392._col0(Inner),Output:["_col4","_col5"] + <-Reducer 2 [SIMPLE_EDGE] + SHUFFLE [RS_103] PartitionCols:_col0 - Select Operator [SEL_364] (rows=462000 width=104) - Output:["_col0","_col1"] - TableScan [TS_3] (rows=462000 width=104) - default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_item_id"] + Merge Join Operator [MERGEJOIN_351] (rows=2 width=4) + Conds:RS_366._col1=RS_375._col0(Inner),Output:["_col0"] + <-Map 1 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_366] + PartitionCols:_col1 + Select Operator [SEL_365] (rows=73049 width=98) + Output:["_col0","_col1"] + Filter Operator [FIL_364] (rows=73049 width=98) + predicate:d_date is not null + TableScan [TS_0] (rows=73049 width=98) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_date"] + <-Reducer 17 [ONE_TO_ONE_EDGE] vectorized + FORWARD [RS_375] + PartitionCols:_col0 + Group By Operator [GBY_374] (rows=2 width=94) + Output:["_col0"],keys:KEY._col0 + <-Reducer 16 [SIMPLE_EDGE] + SHUFFLE [RS_16] + PartitionCols:_col0 + Group By Operator [GBY_15] (rows=2 width=94) + Output:["_col0"],keys:_col0 + Merge Join Operator [MERGEJOIN_350] (rows=5 width=94) + Conds:RS_369._col1=RS_373._col0(Left Semi),Output:["_col0"] + <-Map 15 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_369] + PartitionCols:_col1 + Select Operator [SEL_368] (rows=73049 width=98) + Output:["_col0","_col1"] + Filter Operator [FIL_367] (rows=73049 width=98) + predicate:(d_date is not null and d_week_seq is not null) + TableScan [TS_3] (rows=73049 width=98) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date","d_week_seq"] + <-Map 18 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_373] + PartitionCols:_col0 + Group By Operator [GBY_372] (rows=1 width=4) + Output:["_col0"],keys:_col0 + Select Operator [SEL_371] (rows=2 width=4) + Output:["_col0"] + Filter Operator [FIL_370] (rows=2 width=98) + predicate:((d_date) IN ('1998-01-02', '1998-10-15', '1998-11-10') and d_week_seq is not null) + TableScan [TS_6] (rows=73049 width=98) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date","d_week_seq"] <-Map 22 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_389] - PartitionCols:_col1 - Select Operator [SEL_388] (rows=13749816 width=11) + SHUFFLE [RS_392] + PartitionCols:_col0 + Select Operator [SEL_391] (rows=13749816 width=11) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_387] (rows=13749816 width=11) + Filter Operator [FIL_390] (rows=13749816 width=11) predicate:wr_returned_date_sk is not null - TableScan [TS_78] (rows=14398467 width=11) + TableScan [TS_95] (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_120] + <-Reducer 6 [ONE_TO_ONE_EDGE] + FORWARD [RS_117] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_359] (rows=60 width=116) - Conds:RS_381._col0=RS_386._col0(Inner),Output:["_col0","_col1","_col3"] + Merge Join Operator [MERGEJOIN_362] (rows=2739 width=116) + Conds:RS_384._col0=RS_389._col0(Inner),Output:["_col0","_col1","_col3"] <-Reducer 11 [ONE_TO_ONE_EDGE] vectorized - FORWARD [RS_386] + FORWARD [RS_389] PartitionCols:_col0 - Group By Operator [GBY_385] (rows=63 width=108) + Group By Operator [GBY_388] (rows=5552 width=108) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 <-Reducer 10 [SIMPLE_EDGE] - SHUFFLE [RS_75] + SHUFFLE [RS_73] PartitionCols:_col0 - Group By Operator [GBY_74] (rows=63 width=108) - Output:["_col0","_col1"],aggregations:["sum(_col2)"],keys:_col4 + Group By Operator [GBY_72] (rows=5552 width=108) + Output:["_col0","_col1"],aggregations:["sum(_col5)"],keys:_col7 Merge Join Operator [MERGEJOIN_357] (rows=11105 width=100) - Conds:RS_70._col0=RS_71._col0(Inner),Output:["_col2","_col4"] - <-Reducer 16 [SIMPLE_EDGE] - SHUFFLE [RS_71] + Conds:RS_68._col4=RS_381._col0(Inner),Output:["_col5","_col7"] + <-Map 20 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_381] PartitionCols:_col0 - Please refer to the previous Merge Join Operator [MERGEJOIN_349] + Please refer to the previous Select Operator [SEL_379] <-Reducer 9 [SIMPLE_EDGE] - SHUFFLE [RS_70] - PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_350] (rows=55578005 width=107) - Conds:RS_384._col1=RS_366._col0(Inner),Output:["_col0","_col2","_col4"] - <-Map 8 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_366] + SHUFFLE [RS_68] + PartitionCols:_col4 + Merge Join Operator [MERGEJOIN_356] (rows=11105 width=4) + Conds:RS_65._col0=RS_387._col0(Inner),Output:["_col4","_col5"] + <-Reducer 2 [SIMPLE_EDGE] + SHUFFLE [RS_65] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_364] + Please refer to the previous Merge Join Operator [MERGEJOIN_351] <-Map 21 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_384] - PartitionCols:_col1 - Select Operator [SEL_383] (rows=55578005 width=11) + SHUFFLE [RS_387] + PartitionCols:_col0 + Select Operator [SEL_386] (rows=55578005 width=11) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_382] (rows=55578005 width=11) + Filter Operator [FIL_385] (rows=55578005 width=11) predicate:sr_returned_date_sk is not null - TableScan [TS_39] (rows=57591150 width=11) + TableScan [TS_57] (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_381] + <-Reducer 5 [ONE_TO_ONE_EDGE] vectorized + FORWARD [RS_384] PartitionCols:_col0 - Group By Operator [GBY_380] (rows=60 width=108) + Group By Operator [GBY_383] (rows=2739 width=108) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 - <-Reducer 3 [SIMPLE_EDGE] - SHUFFLE [RS_36] + <-Reducer 4 [SIMPLE_EDGE] + SHUFFLE [RS_35] PartitionCols:_col0 - Group By Operator [GBY_35] (rows=60 width=108) - Output:["_col0","_col1"],aggregations:["sum(_col2)"],keys:_col4 - Merge Join Operator [MERGEJOIN_356] (rows=5478 width=100) - Conds:RS_31._col0=RS_32._col0(Inner),Output:["_col2","_col4"] - <-Reducer 16 [SIMPLE_EDGE] - SHUFFLE [RS_32] + Group By Operator [GBY_34] (rows=2739 width=108) + Output:["_col0","_col1"],aggregations:["sum(_col5)"],keys:_col7 + Merge Join Operator [MERGEJOIN_353] (rows=5478 width=100) + Conds:RS_30._col4=RS_380._col0(Inner),Output:["_col5","_col7"] + <-Map 20 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_380] PartitionCols:_col0 - Please refer to the previous Merge Join Operator [MERGEJOIN_349] - <-Reducer 2 [SIMPLE_EDGE] - SHUFFLE [RS_31] - PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_347] (rows=28798881 width=107) - Conds:RS_363._col1=RS_365._col0(Inner),Output:["_col0","_col2","_col4"] - <-Map 8 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_365] + Please refer to the previous Select Operator [SEL_379] + <-Reducer 3 [SIMPLE_EDGE] + SHUFFLE [RS_30] + PartitionCols:_col4 + Merge Join Operator [MERGEJOIN_352] (rows=5478 width=4) + Conds:RS_27._col0=RS_378._col0(Inner),Output:["_col4","_col5"] + <-Reducer 2 [SIMPLE_EDGE] + SHUFFLE [RS_27] + PartitionCols:_col0 + Please refer to the previous Merge Join Operator [MERGEJOIN_351] + <-Map 19 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_378] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_364] - <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_363] - PartitionCols:_col1 - Select Operator [SEL_362] (rows=28798881 width=11) + Select Operator [SEL_377] (rows=28798881 width=11) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_361] (rows=28798881 width=11) + Filter Operator [FIL_376] (rows=28798881 width=11) predicate:cr_returned_date_sk is not null - TableScan [TS_0] (rows=28798881 width=11) + TableScan [TS_19] (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 a/ql/src/test/results/clientpositive/perf/tez/constraints/query85.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/query85.q.out index ec5e4cf2a0..2aa27db1ef 100644 --- a/ql/src/test/results/clientpositive/perf/tez/constraints/query85.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/query85.q.out @@ -186,7 +186,7 @@ Vertex dependency in root stage Map 10 <- Reducer 12 (BROADCAST_EDGE) Reducer 12 <- Map 11 (CUSTOM_SIMPLE_EDGE) Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 10 (SIMPLE_EDGE) -Reducer 3 <- Map 15 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) +Reducer 3 <- Map 14 (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 14 (SIMPLE_EDGE), Reducer 5 (SIMPLE_EDGE) @@ -200,121 +200,119 @@ Stage-0 Stage-1 Reducer 9 vectorized File Output Operator [FS_209] - Limit [LIM_208] (rows=7 width=832) + Limit [LIM_208] (rows=72 width=832) Number of rows:100 - Select Operator [SEL_207] (rows=7 width=832) + Select Operator [SEL_207] (rows=72 width=832) Output:["_col0","_col1","_col2","_col3"] <-Reducer 8 [SIMPLE_EDGE] vectorized SHUFFLE [RS_206] - Select Operator [SEL_205] (rows=7 width=832) + Select Operator [SEL_205] (rows=72 width=832) Output:["_col4","_col5","_col6","_col7"] - Group By Operator [GBY_204] (rows=7 width=353) + Group By Operator [GBY_204] (rows=72 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 7 [SIMPLE_EDGE] SHUFFLE [RS_42] PartitionCols:_col0 - Group By Operator [GBY_41] (rows=7 width=353) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"],aggregations:["sum(_col11)","count(_col11)","sum(_col7)","count(_col7)","sum(_col6)","count(_col6)"],keys:_col23 - Select Operator [SEL_40] (rows=16740 width=136) - Output:["_col6","_col7","_col11","_col23"] - Filter Operator [FIL_39] (rows=16740 width=136) - predicate:((_col31 and _col32 and _col15) or (_col33 and _col34 and _col16) or (_col35 and _col36 and _col17)) - Merge Join Operator [MERGEJOIN_179] (rows=44640 width=136) - Conds:RS_36._col1, _col19, _col20=RS_197._col0, _col1, _col2(Inner),Output:["_col6","_col7","_col11","_col15","_col16","_col17","_col23","_col31","_col32","_col33","_col34","_col35","_col36"] - <-Map 15 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_197] - PartitionCols:_col0, _col1, _col2 - Select Operator [SEL_195] (rows=265971 width=207) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"] - Filter Operator [FIL_194] (rows=265971 width=183) - predicate:((cd_education_status) IN ('4 yr Degree', 'Primary', 'Advanced Degree') and (cd_marital_status) IN ('M', 'D', 'U')) - TableScan [TS_17] (rows=1861800 width=183) - default@customer_demographics,cd1,Tbl:COMPLETE,Col:COMPLETE,Output:["cd_demo_sk","cd_marital_status","cd_education_status"] - <-Reducer 6 [SIMPLE_EDGE] - SHUFFLE [RS_36] - PartitionCols:_col1, _col19, _col20 - Filter Operator [FIL_35] (rows=44640 width=315) - predicate:((_col25 and _col12) or (_col26 and _col13) or (_col27 and _col14)) - Merge Join Operator [MERGEJOIN_178] (rows=59520 width=315) - Conds:RS_32._col2=RS_203._col0(Inner),Output:["_col1","_col6","_col7","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col19","_col20","_col23","_col25","_col26","_col27"] - <-Map 14 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_203] - PartitionCols:_col0 - Select Operator [SEL_202] (rows=3529412 width=16) - Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_201] (rows=3529412 width=187) - predicate:((ca_country = 'United States') and (ca_state) IN ('KY', 'GA', 'NM', 'MT', 'OR', 'IN', 'WI', 'MO', 'WV')) - TableScan [TS_14] (rows=40000000 width=187) - default@customer_address,customer_address,Tbl:COMPLETE,Col:COMPLETE,Output:["ca_address_sk","ca_state","ca_country"] - <-Reducer 5 [SIMPLE_EDGE] - SHUFFLE [RS_32] - PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_177] (rows=674551 width=350) - Conds:RS_29._col4=RS_200._col0(Inner),Output:["_col1","_col2","_col6","_col7","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col19","_col20","_col23"] - <-Map 13 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_200] - PartitionCols:_col0 - Select Operator [SEL_199] (rows=72 width=101) - Output:["_col0","_col1"] - TableScan [TS_12] (rows=72 width=101) - default@reason,reason,Tbl:COMPLETE,Col:COMPLETE,Output:["r_reason_sk","r_reason_desc"] - <-Reducer 4 [SIMPLE_EDGE] - SHUFFLE [RS_29] - PartitionCols:_col4 - Merge Join Operator [MERGEJOIN_176] (rows=674551 width=254) - Conds:RS_26._col8=RS_185._col0(Inner),Output:["_col1","_col2","_col4","_col6","_col7","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col19","_col20"] - <-Map 11 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_185] - PartitionCols:_col0 - Select Operator [SEL_184] (rows=652 width=4) - Output:["_col0"] - Filter Operator [FIL_183] (rows=652 width=8) - predicate:(d_year = 1998) - 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_26] - PartitionCols:_col8 - Merge Join Operator [MERGEJOIN_175] (rows=1889180 width=379) - Conds:RS_23._col3=RS_198._col0(Inner),Output:["_col1","_col2","_col4","_col6","_col7","_col8","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col19","_col20"] - <-Map 15 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_198] - PartitionCols:_col0 - Select Operator [SEL_196] (rows=265971 width=183) - Output:["_col0","_col1","_col2"] - Please refer to the previous Filter Operator [FIL_194] - <-Reducer 2 [SIMPLE_EDGE] - SHUFFLE [RS_23] - PartitionCols:_col3 - Merge Join Operator [MERGEJOIN_174] (rows=13039884 width=262) - Conds:RS_182._col0, _col5=RS_193._col1, _col2(Inner),Output:["_col1","_col2","_col3","_col4","_col6","_col7","_col8","_col11","_col12","_col13","_col14","_col15","_col16","_col17"] - <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_182] - PartitionCols:_col0, _col5 - Select Operator [SEL_181] (rows=11975292 width=237) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] - Filter Operator [FIL_180] (rows=11975292 width=237) - predicate:(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 10 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_193] - PartitionCols:_col1, _col2 - Select Operator [SEL_192] (rows=15992347 width=39) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9"] - Filter Operator [FIL_191] (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_27_date_dim_d_date_sk_min) AND DynamicValue(RS_27_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_27_date_dim_d_date_sk_bloom_filter))) 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 12 [BROADCAST_EDGE] vectorized - BROADCAST [RS_190] - Group By Operator [GBY_189] (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_188] - Group By Operator [GBY_187] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_186] (rows=652 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_184] + Group By Operator [GBY_41] (rows=72 width=353) + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"],aggregations:["sum(_col11)","count(_col11)","sum(_col7)","count(_col7)","sum(_col6)","count(_col6)"],keys:_col36 + Merge Join Operator [MERGEJOIN_179] (rows=16740 width=100) + Conds:RS_37._col4=RS_203._col0(Inner),Output:["_col6","_col7","_col11","_col36"] + <-Map 15 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_203] + PartitionCols:_col0 + Select Operator [SEL_202] (rows=72 width=101) + Output:["_col0","_col1"] + TableScan [TS_18] (rows=72 width=101) + default@reason,reason,Tbl:COMPLETE,Col:COMPLETE,Output:["r_reason_sk","r_reason_desc"] + <-Reducer 6 [SIMPLE_EDGE] + SHUFFLE [RS_37] + PartitionCols:_col4 + Filter Operator [FIL_36] (rows=16740 width=39) + predicate:((_col29 and _col30 and _col15) or (_col31 and _col32 and _col16) or (_col33 and _col34 and _col17)) + Merge Join Operator [MERGEJOIN_178] (rows=44640 width=39) + Conds:RS_33._col20, _col1, _col19=RS_197._col2, _col0, _col1(Inner),Output:["_col4","_col6","_col7","_col11","_col15","_col16","_col17","_col29","_col30","_col31","_col32","_col33","_col34"] + <-Map 14 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_197] + PartitionCols:_col2, _col0, _col1 + Select Operator [SEL_195] (rows=265971 width=207) + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"] + Filter Operator [FIL_194] (rows=265971 width=183) + predicate:((cd_education_status) IN ('4 yr Degree', 'Primary', 'Advanced Degree') and (cd_marital_status) IN ('M', 'D', 'U')) + TableScan [TS_15] (rows=1861800 width=183) + default@customer_demographics,cd1,Tbl:COMPLETE,Col:COMPLETE,Output:["cd_demo_sk","cd_marital_status","cd_education_status"] + <-Reducer 5 [SIMPLE_EDGE] + SHUFFLE [RS_33] + PartitionCols:_col20, _col1, _col19 + Filter Operator [FIL_32] (rows=44640 width=218) + predicate:((_col23 and _col12) or (_col24 and _col13) or (_col25 and _col14)) + Merge Join Operator [MERGEJOIN_177] (rows=59520 width=218) + Conds:RS_29._col2=RS_201._col0(Inner),Output:["_col1","_col4","_col6","_col7","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col19","_col20","_col23","_col24","_col25"] + <-Map 13 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_201] + PartitionCols:_col0 + Select Operator [SEL_200] (rows=3529412 width=16) + Output:["_col0","_col1","_col2","_col3"] + Filter Operator [FIL_199] (rows=3529412 width=187) + predicate:((ca_country = 'United States') and (ca_state) IN ('KY', 'GA', 'NM', 'MT', 'OR', 'IN', 'WI', 'MO', 'WV')) + 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_29] + PartitionCols:_col2 + Merge Join Operator [MERGEJOIN_176] (rows=674551 width=254) + Conds:RS_26._col8=RS_185._col0(Inner),Output:["_col1","_col2","_col4","_col6","_col7","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col19","_col20"] + <-Map 11 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_185] + PartitionCols:_col0 + Select Operator [SEL_184] (rows=652 width=4) + Output:["_col0"] + Filter Operator [FIL_183] (rows=652 width=8) + predicate:(d_year = 1998) + 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_26] + PartitionCols:_col8 + Merge Join Operator [MERGEJOIN_175] (rows=1889180 width=379) + Conds:RS_23._col3=RS_198._col0(Inner),Output:["_col1","_col2","_col4","_col6","_col7","_col8","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col19","_col20"] + <-Map 14 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_198] + PartitionCols:_col0 + Select Operator [SEL_196] (rows=265971 width=183) + Output:["_col0","_col1","_col2"] + Please refer to the previous Filter Operator [FIL_194] + <-Reducer 2 [SIMPLE_EDGE] + SHUFFLE [RS_23] + PartitionCols:_col3 + Merge Join Operator [MERGEJOIN_174] (rows=13039884 width=262) + Conds:RS_182._col0, _col5=RS_193._col1, _col2(Inner),Output:["_col1","_col2","_col3","_col4","_col6","_col7","_col8","_col11","_col12","_col13","_col14","_col15","_col16","_col17"] + <-Map 1 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_182] + PartitionCols:_col0, _col5 + Select Operator [SEL_181] (rows=11975292 width=237) + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] + Filter Operator [FIL_180] (rows=11975292 width=237) + predicate:(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 10 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_193] + PartitionCols:_col1, _col2 + Select Operator [SEL_192] (rows=15992347 width=39) + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9"] + Filter Operator [FIL_191] (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_27_date_dim_d_date_sk_min) AND DynamicValue(RS_27_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_27_date_dim_d_date_sk_bloom_filter))) 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 12 [BROADCAST_EDGE] vectorized + BROADCAST [RS_190] + Group By Operator [GBY_189] (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_188] + Group By Operator [GBY_187] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_186] (rows=652 width=4) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_184] diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/query91.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/query91.q.out index 427bdd4a47..8e0790fcf3 100644 --- a/ql/src/test/results/clientpositive/perf/tez/constraints/query91.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/query91.q.out @@ -77,120 +77,120 @@ POSTHOOK: Output: hdfs://### HDFS PATH ### Plan optimized by CBO. Vertex dependency in root stage -Reducer 11 <- Map 10 (SIMPLE_EDGE), Map 13 (SIMPLE_EDGE) -Reducer 12 <- Map 14 (SIMPLE_EDGE), Reducer 11 (SIMPLE_EDGE) -Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) -Reducer 3 <- Map 9 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) +Reducer 12 <- Map 11 (SIMPLE_EDGE), Map 13 (SIMPLE_EDGE) +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 9 (SIMPLE_EDGE) +Reducer 3 <- Map 10 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) Reducer 4 <- Reducer 12 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) -Reducer 5 <- Map 15 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) -Reducer 6 <- Reducer 5 (SIMPLE_EDGE) +Reducer 5 <- Map 14 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) +Reducer 6 <- Map 15 (SIMPLE_EDGE), Reducer 5 (SIMPLE_EDGE) Reducer 7 <- Reducer 6 (SIMPLE_EDGE) +Reducer 8 <- Reducer 7 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 - Reducer 7 vectorized - File Output Operator [FS_168] - Select Operator [SEL_167] (rows=1 width=406) + Reducer 8 vectorized + File Output Operator [FS_170] + Select Operator [SEL_169] (rows=5219 width=406) Output:["_col0","_col1","_col2","_col3"] - <-Reducer 6 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_166] - Select Operator [SEL_165] (rows=1 width=518) + <-Reducer 7 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_168] + Select Operator [SEL_167] (rows=5219 width=518) Output:["_col0","_col1","_col2","_col4"] - Group By Operator [GBY_164] (rows=1 width=585) + Group By Operator [GBY_166] (rows=5219 width=585) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4 - <-Reducer 5 [SIMPLE_EDGE] + <-Reducer 6 [SIMPLE_EDGE] SHUFFLE [RS_41] PartitionCols:_col0, _col1, _col2, _col3, _col4 - Group By Operator [GBY_40] (rows=1 width=585) - Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(_col11)"],keys:_col5, _col6, _col14, _col15, _col16 - Merge Join Operator [MERGEJOIN_143] (rows=10438 width=473) - Conds:RS_36._col2=RS_163._col0(Inner),Output:["_col5","_col6","_col11","_col14","_col15","_col16"] + Group By Operator [GBY_40] (rows=5219 width=585) + Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(_col11)"],keys:_col5, _col6, _col15, _col16, _col17 + Merge Join Operator [MERGEJOIN_145] (rows=10438 width=473) + Conds:RS_36._col10=RS_165._col0(Inner),Output:["_col5","_col6","_col11","_col15","_col16","_col17"] <-Map 15 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_163] + SHUFFLE [RS_165] PartitionCols:_col0 - Select Operator [SEL_162] (rows=3600 width=4) - Output:["_col0"] - Filter Operator [FIL_161] (rows=3600 width=96) - predicate:(hd_buy_potential like '0-500%') - TableScan [TS_24] (rows=7200 width=96) - default@household_demographics,household_demographics,Tbl:COMPLETE,Col:COMPLETE,Output:["hd_demo_sk","hd_buy_potential"] - <-Reducer 4 [SIMPLE_EDGE] + Select Operator [SEL_164] (rows=60 width=298) + Output:["_col0","_col1","_col2","_col3"] + TableScan [TS_22] (rows=60 width=298) + default@call_center,call_center,Tbl:COMPLETE,Col:COMPLETE,Output:["cc_call_center_sk","cc_call_center_id","cc_name","cc_manager"] + <-Reducer 5 [SIMPLE_EDGE] SHUFFLE [RS_36] - PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_142] (rows=20876 width=473) - Conds:RS_33._col0=RS_34._col1(Inner),Output:["_col2","_col5","_col6","_col11","_col14","_col15","_col16"] - <-Reducer 12 [SIMPLE_EDGE] - SHUFFLE [RS_34] - PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_141] (rows=657590 width=312) - Conds:RS_20._col2=RS_160._col0(Inner),Output:["_col1","_col3","_col6","_col7","_col8"] - <-Map 14 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_160] - PartitionCols:_col0 - Select Operator [SEL_159] (rows=60 width=298) - Output:["_col0","_col1","_col2","_col3"] - TableScan [TS_15] (rows=60 width=298) - default@call_center,call_center,Tbl:COMPLETE,Col:COMPLETE,Output:["cc_call_center_sk","cc_call_center_id","cc_name","cc_manager"] - <-Reducer 11 [SIMPLE_EDGE] - SHUFFLE [RS_20] - PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_140] (rows=657590 width=19) - Conds:RS_155._col0=RS_158._col0(Inner),Output:["_col1","_col2","_col3"] - <-Map 10 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_155] + PartitionCols:_col10 + Merge Join Operator [MERGEJOIN_144] (rows=10438 width=179) + Conds:RS_33._col2=RS_163._col0(Inner),Output:["_col5","_col6","_col10","_col11"] + <-Map 14 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_163] + PartitionCols:_col0 + Select Operator [SEL_162] (rows=3600 width=4) + Output:["_col0"] + Filter Operator [FIL_161] (rows=3600 width=96) + predicate:(hd_buy_potential like '0-500%') + TableScan [TS_19] (rows=7200 width=96) + default@household_demographics,household_demographics,Tbl:COMPLETE,Col:COMPLETE,Output:["hd_demo_sk","hd_buy_potential"] + <-Reducer 4 [SIMPLE_EDGE] + SHUFFLE [RS_33] + PartitionCols:_col2 + Merge Join Operator [MERGEJOIN_143] (rows=20876 width=179) + Conds:RS_30._col0=RS_31._col1(Inner),Output:["_col2","_col5","_col6","_col10","_col11"] + <-Reducer 12 [SIMPLE_EDGE] + SHUFFLE [RS_31] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_142] (rows=657590 width=19) + Conds:RS_157._col0=RS_160._col0(Inner),Output:["_col1","_col2","_col3"] + <-Map 11 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_157] PartitionCols:_col0 - Select Operator [SEL_154] (rows=27658583 width=121) + Select Operator [SEL_156] (rows=27658583 width=121) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_153] (rows=27658583 width=121) + Filter Operator [FIL_155] (rows=27658583 width=121) predicate:(cr_call_center_sk is not null and cr_returned_date_sk is not null and cr_returning_customer_sk is not null) TableScan [TS_9] (rows=28798881 width=121) default@catalog_returns,catalog_returns,Tbl:COMPLETE,Col:COMPLETE,Output:["cr_returned_date_sk","cr_returning_customer_sk","cr_call_center_sk","cr_net_loss"] <-Map 13 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_158] + SHUFFLE [RS_160] PartitionCols:_col0 - Select Operator [SEL_157] (rows=50 width=4) + Select Operator [SEL_159] (rows=50 width=4) Output:["_col0"] - Filter Operator [FIL_156] (rows=50 width=12) + Filter Operator [FIL_158] (rows=50 width=12) predicate:((d_moy = 11) and (d_year = 1999)) TableScan [TS_12] (rows=73049 width=12) default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year","d_moy"] - <-Reducer 3 [SIMPLE_EDGE] - SHUFFLE [RS_33] - PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_139] (rows=479709 width=183) - Conds:RS_30._col3=RS_152._col0(Inner),Output:["_col0","_col2","_col5","_col6"] - <-Map 9 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_152] - PartitionCols:_col0 - Select Operator [SEL_151] (rows=8000000 width=4) - Output:["_col0"] - Filter Operator [FIL_150] (rows=8000000 width=112) - predicate:(ca_gmt_offset = -7) - TableScan [TS_6] (rows=40000000 width=112) - default@customer_address,customer_address,Tbl:COMPLETE,Col:COMPLETE,Output:["ca_address_sk","ca_gmt_offset"] - <-Reducer 2 [SIMPLE_EDGE] + <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_30] - PartitionCols:_col3 - Merge Join Operator [MERGEJOIN_138] (rows=2398543 width=187) - Conds:RS_146._col1=RS_149._col0(Inner),Output:["_col0","_col2","_col3","_col5","_col6"] - <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_146] - PartitionCols:_col1 - Select Operator [SEL_145] (rows=74500295 width=15) - Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_144] (rows=74500295 width=15) - 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_0] (rows=80000000 width=15) - default@customer,customer,Tbl:COMPLETE,Col:COMPLETE,Output:["c_customer_sk","c_current_cdemo_sk","c_current_hdemo_sk","c_current_addr_sk"] - <-Map 8 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_149] + PartitionCols:_col0 + Merge Join Operator [MERGEJOIN_141] (rows=479709 width=183) + Conds:RS_27._col3=RS_154._col0(Inner),Output:["_col0","_col2","_col5","_col6"] + <-Map 10 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_154] PartitionCols:_col0 - Select Operator [SEL_148] (rows=59105 width=183) - Output:["_col0","_col1","_col2"] - Filter Operator [FIL_147] (rows=59105 width=183) - predicate:((cd_education_status) IN ('Unknown', 'Advanced Degree') and (cd_marital_status) IN ('M', 'W') and (struct(cd_marital_status,cd_education_status)) IN (const struct('M','Unknown'), const struct('W','Advanced Degree'))) - TableScan [TS_3] (rows=1861800 width=183) - default@customer_demographics,customer_demographics,Tbl:COMPLETE,Col:COMPLETE,Output:["cd_demo_sk","cd_marital_status","cd_education_status"] + Select Operator [SEL_153] (rows=8000000 width=4) + Output:["_col0"] + Filter Operator [FIL_152] (rows=8000000 width=112) + predicate:(ca_gmt_offset = -7) + TableScan [TS_6] (rows=40000000 width=112) + default@customer_address,customer_address,Tbl:COMPLETE,Col:COMPLETE,Output:["ca_address_sk","ca_gmt_offset"] + <-Reducer 2 [SIMPLE_EDGE] + SHUFFLE [RS_27] + PartitionCols:_col3 + Merge Join Operator [MERGEJOIN_140] (rows=2398543 width=187) + Conds:RS_148._col1=RS_151._col0(Inner),Output:["_col0","_col2","_col3","_col5","_col6"] + <-Map 1 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_148] + PartitionCols:_col1 + Select Operator [SEL_147] (rows=74500295 width=15) + Output:["_col0","_col1","_col2","_col3"] + Filter Operator [FIL_146] (rows=74500295 width=15) + 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_0] (rows=80000000 width=15) + default@customer,customer,Tbl:COMPLETE,Col:COMPLETE,Output:["c_customer_sk","c_current_cdemo_sk","c_current_hdemo_sk","c_current_addr_sk"] + <-Map 9 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_151] + PartitionCols:_col0 + Select Operator [SEL_150] (rows=59105 width=183) + Output:["_col0","_col1","_col2"] + Filter Operator [FIL_149] (rows=59105 width=183) + predicate:((cd_education_status) IN ('Unknown', 'Advanced Degree') and (cd_marital_status) IN ('M', 'W') and (struct(cd_marital_status,cd_education_status)) IN (const struct('M','Unknown'), const struct('W','Advanced Degree'))) + TableScan [TS_3] (rows=1861800 width=183) + default@customer_demographics,customer_demographics,Tbl:COMPLETE,Col:COMPLETE,Output:["cd_demo_sk","cd_marital_status","cd_education_status"] diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/query99.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/query99.q.out index 9b8ebd20b2..e76bb8e074 100644 --- a/ql/src/test/results/clientpositive/perf/tez/constraints/query99.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/query99.q.out @@ -111,33 +111,33 @@ Stage-0 SHUFFLE [RS_26] PartitionCols:_col0, _col1, _col2 Group By Operator [GBY_25] (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:_col15, _col11, _col13 + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"],aggregations:["sum(_col4)","sum(_col5)","sum(_col6)","sum(_col7)","sum(_col8)"],keys:_col13, _col11, _col15 Top N Key Operator [TNK_53] (rows=15478212 width=386) - keys:_col15, _col11, _col13,sort order:+++,top n:100 + keys:_col13, _col11, _col15,sort order:+++,top n:100 Merge Join Operator [MERGEJOIN_97] (rows=15478212 width=386) - Conds:RS_21._col3=RS_119._col0(Inner),Output:["_col4","_col5","_col6","_col7","_col8","_col11","_col13","_col15"] + Conds:RS_21._col1=RS_119._col0(Inner),Output:["_col4","_col5","_col6","_col7","_col8","_col11","_col13","_col15"] <-Map 13 [SIMPLE_EDGE] vectorized SHUFFLE [RS_119] PartitionCols:_col0 - Select Operator [SEL_118] (rows=27 width=188) + Select Operator [SEL_118] (rows=60 width=102) Output:["_col0","_col1"] - TableScan [TS_10] (rows=27 width=104) - default@warehouse,warehouse,Tbl:COMPLETE,Col:COMPLETE,Output:["w_warehouse_sk","w_warehouse_name"] + TableScan [TS_10] (rows=60 width=102) + default@call_center,call_center,Tbl:COMPLETE,Col:COMPLETE,Output:["cc_call_center_sk","cc_name"] <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_21] - PartitionCols:_col3 - Merge Join Operator [MERGEJOIN_96] (rows=15478212 width=205) - Conds:RS_18._col1=RS_117._col0(Inner),Output:["_col3","_col4","_col5","_col6","_col7","_col8","_col11","_col13"] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_96] (rows=15478212 width=291) + Conds:RS_18._col3=RS_117._col0(Inner),Output:["_col1","_col4","_col5","_col6","_col7","_col8","_col11","_col13"] <-Map 12 [SIMPLE_EDGE] vectorized SHUFFLE [RS_117] PartitionCols:_col0 - Select Operator [SEL_116] (rows=60 width=102) + Select Operator [SEL_116] (rows=27 width=188) Output:["_col0","_col1"] - TableScan [TS_8] (rows=60 width=102) - default@call_center,call_center,Tbl:COMPLETE,Col:COMPLETE,Output:["cc_call_center_sk","cc_name"] + TableScan [TS_8] (rows=27 width=104) + default@warehouse,warehouse,Tbl:COMPLETE,Col:COMPLETE,Output:["w_warehouse_sk","w_warehouse_name"] <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_18] - PartitionCols:_col1 + PartitionCols:_col3 Merge Join Operator [MERGEJOIN_95] (rows=15478212 width=111) Conds:RS_15._col2=RS_107._col0(Inner),Output:["_col1","_col3","_col4","_col5","_col6","_col7","_col8","_col11"] <-Map 10 [SIMPLE_EDGE] vectorized