Skip to content

[fix] (inverted index) fix the error result in the query when using count on index #41375

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
airborne12 merged 1 commit into from
Oct 9, 2024
Merged

[fix] (inverted index) fix the error result in the query when using count on index #41375

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
101 changes: 71 additions & 30 deletions ...core/src/main/java/org/apache/doris/nereids/rules/implementation/AggregateStrategies.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -40,6 +40,7 @@
import org.apache.doris.nereids.trees.expressions.Expression;
import org.apache.doris.nereids.trees.expressions.IsNull;
import org.apache.doris.nereids.trees.expressions.NamedExpression;
import org.apache.doris.nereids.trees.expressions.Or;
import org.apache.doris.nereids.trees.expressions.OrderExpression;
import org.apache.doris.nereids.trees.expressions.Slot;
import org.apache.doris.nereids.trees.expressions.SlotReference;
Expand Down Expand Up @@ -111,42 +112,66 @@ public List<Rule> buildRules() {
logicalAggregate(
logicalFilter(
logicalOlapScan().when(this::isDupOrMowKeyTable).when(this::isInvertedIndexEnabledOnTable)
).when(filter -> !filter.getConjuncts().isEmpty()))
.when(agg -> enablePushDownCountOnIndex())
.when(agg -> agg.getGroupByExpressions().isEmpty())
.when(agg -> {
Set<AggregateFunction> funcs = agg.getAggregateFunctions();
return !funcs.isEmpty() && funcs.stream()
.allMatch(f -> f instanceof Count && !f.isDistinct() && (((Count) f).isCountStar()
|| f.child(0) instanceof Slot));
})
.thenApply(ctx -> {
LogicalAggregate<LogicalFilter<LogicalOlapScan>> agg = ctx.root;
LogicalFilter<LogicalOlapScan> filter = agg.child();
LogicalOlapScan olapScan = filter.child();
return pushdownCountOnIndex(agg, null, filter, olapScan, ctx.cascadesContext);
})
)
)
.when(agg -> enablePushDownCountOnIndex())
.when(agg -> agg.getGroupByExpressions().isEmpty())
.when(agg -> {
Set<AggregateFunction> funcs = agg.getAggregateFunctions();
if (funcs.isEmpty() || !funcs.stream().allMatch(f -> f instanceof Count && !f.isDistinct()
&& (((Count) f).isCountStar() || f.child(0) instanceof Slot))) {
return false;
}
Set<Expression> conjuncts = agg.child().getConjuncts();
if (conjuncts.isEmpty()) {
return false;
}

Set<Slot> aggSlots = funcs.stream()
.flatMap(f -> f.getInputSlots().stream())
.collect(Collectors.toSet());
return conjuncts.stream().allMatch(expr -> checkSlotInOrExpression(expr, aggSlots));
})
.thenApply(ctx -> {
LogicalAggregate<LogicalFilter<LogicalOlapScan>> agg = ctx.root;
LogicalFilter<LogicalOlapScan> filter = agg.child();
LogicalOlapScan olapScan = filter.child();
return pushdownCountOnIndex(agg, null, filter, olapScan, ctx.cascadesContext);
})
),
RuleType.COUNT_ON_INDEX.build(
logicalAggregate(
logicalProject(
logicalFilter(
logicalOlapScan().when(this::isDupOrMowKeyTable).when(this::isInvertedIndexEnabledOnTable)
).when(filter -> !filter.getConjuncts().isEmpty())))
.when(agg -> enablePushDownCountOnIndex())
.when(agg -> agg.getGroupByExpressions().isEmpty())
.when(agg -> {
Set<AggregateFunction> funcs = agg.getAggregateFunctions();
return !funcs.isEmpty() && funcs.stream().allMatch(f -> f instanceof Count && !f.isDistinct()
&& (((Count) f).isCountStar() || f.child(0) instanceof Slot));
})
.thenApply(ctx -> {
LogicalAggregate<LogicalProject<LogicalFilter<LogicalOlapScan>>> agg = ctx.root;
LogicalProject<LogicalFilter<LogicalOlapScan>> project = agg.child();
LogicalFilter<LogicalOlapScan> filter = project.child();
LogicalOlapScan olapScan = filter.child();
return pushdownCountOnIndex(agg, project, filter, olapScan, ctx.cascadesContext);
})
)
)
)
.when(agg -> enablePushDownCountOnIndex())
.when(agg -> agg.getGroupByExpressions().isEmpty())
.when(agg -> {
Set<AggregateFunction> funcs = agg.getAggregateFunctions();
if (funcs.isEmpty() || !funcs.stream().allMatch(f -> f instanceof Count && !f.isDistinct()
&& (((Count) f).isCountStar() || f.child(0) instanceof Slot))) {
return false;
}
Set<Expression> conjuncts = agg.child().child().getConjuncts();
if (conjuncts.isEmpty()) {
return false;
}

Set<Slot> aggSlots = funcs.stream()
.flatMap(f -> f.getInputSlots().stream())
.collect(Collectors.toSet());
return conjuncts.stream().allMatch(expr -> checkSlotInOrExpression(expr, aggSlots));
})
.thenApply(ctx -> {
LogicalAggregate<LogicalProject<LogicalFilter<LogicalOlapScan>>> agg = ctx.root;
LogicalProject<LogicalFilter<LogicalOlapScan>> project = agg.child();
LogicalFilter<LogicalOlapScan> filter = project.child();
LogicalOlapScan olapScan = filter.child();
return pushdownCountOnIndex(agg, project, filter, olapScan, ctx.cascadesContext);
})
),
RuleType.STORAGE_LAYER_AGGREGATE_MINMAX_ON_UNIQUE_WITHOUT_PROJECT.build(
logicalAggregate(
Expand Down Expand Up @@ -451,6 +476,22 @@ private boolean enablePushDownCountOnIndex() {
return connectContext != null && connectContext.getSessionVariable().isEnablePushDownCountOnIndex();
}

private boolean checkSlotInOrExpression(Expression expr, Set<Slot> aggSlots) {
if (expr instanceof Or) {
Set<Slot> slots = expr.getInputSlots();
if (!slots.stream().allMatch(aggSlots::contains)) {
return false;
}
} else {
for (Expression child : expr.children()) {
if (!checkSlotInOrExpression(child, aggSlots)) {
return false;
}
}
}
return true;
}

private boolean isDupOrMowKeyTable(LogicalOlapScan logicalScan) {
if (logicalScan != null) {
KeysType keysType = logicalScan.getTable().getKeysType();
Expand Down
9 changes: 9 additions & 0 deletions regression-test/data/inverted_index_p0/test_count_on_index_2.out
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -101,3 +101,12 @@
-- !sql --
3

-- !sql --
1

-- !sql --
1

-- !sql --
1

29 changes: 29 additions & 0 deletions regression-test/suites/inverted_index_p0/test_count_on_index_2.groovy
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -202,6 +202,35 @@ suite("test_count_on_index_2", "p0"){
qt_sql """ select count() from ${indexTbName3} where (a >= 10 and a < 20) and (b >= 5 and b < 14) and (c >= 16 and c < 25); """
qt_sql """ select count() from ${indexTbName3} where (a >= 10 and a < 20) and (b >= 5 and b < 16) and (c >= 13 and c < 25); """

sql """ DROP TABLE IF EXISTS tt """
sql """
CREATE TABLE `tt` (
`a` int NULL,
`b` int NULL,
`c` int NULL,
INDEX col_c (`b`) USING INVERTED,
INDEX col_b (`c`) USING INVERTED
) ENGINE=OLAP
DUPLICATE KEY(`a`)
COMMENT 'OLAP'
DISTRIBUTED BY RANDOM BUCKETS 1
PROPERTIES (
"replication_allocation" = "tag.location.default: 1"
);
"""

sql """ insert into tt values (20, 23, 30); """
sql """ insert into tt values (20, null, 30); """
qt_sql """ select count(b) from tt where b = 23 or c = 30; """
qt_sql """ select count(b) from tt where b = 23 and (c = 20 or c = 30); """
explain {
sql("select count(b) from tt where b = 23 and (c = 20 or c = 30);")
contains "COUNT_ON_INDEX"
}
explain {
sql("select count(b) from tt where b = 23 or b = 30;")
contains "COUNT_ON_INDEX"
}
} finally {
//try_sql("DROP TABLE IF EXISTS ${testTable}")
}
Expand Down