Skip to content

Skip optimizing IN predicate when it contains too many values #14670

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

Closed
Jackie-Jiang wants to merge 1 commit into from
Closed

Skip optimizing IN predicate when it contains too many values #14670

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
16 changes: 14 additions & 2 deletions .../src/main/java/org/apache/pinot/core/query/optimizer/filter/MergeEqInFilterOptimizer.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -47,6 +47,9 @@
* flattened.
*/
public class MergeEqInFilterOptimizer implements FilterOptimizer {
// Optimize IN predicate with up to 10 values (operands include lhs)
// TODO: Make it configurable
private static final int IN_OPERANDS_THRESHOLD = 11;

@Override
public Expression optimize(Expression filterExpression, @Nullable Schema schema) {
Expand Down Expand Up @@ -92,9 +95,14 @@ private Expression optimize(Expression filterExpression) {
}
} else if (childOperator.equals(FilterKind.IN.name())) {
List<Expression> operands = childFunction.getOperands();
int numOperands = operands.size();
if (numOperands > IN_OPERANDS_THRESHOLD) {
// Skip merging IN predicate with too many values
newChildren.add(child);
continue;
}
Expression lhs = operands.get(0);
Set<Expression> inPredicateValuesSet = new HashSet<>();
int numOperands = operands.size();
for (int i = 1; i < numOperands; i++) {
inPredicateValuesSet.add(operands.get(i));
}
Expand Down Expand Up @@ -138,9 +146,13 @@ private Expression optimize(Expression filterExpression) {
return filterExpression;
} else if (operator.equals(FilterKind.IN.name())) {
List<Expression> operands = function.getOperands();
int numOperands = operands.size();
if (numOperands > IN_OPERANDS_THRESHOLD) {
// Skip merging IN predicate with too many values
return filterExpression;
}
Expression lhs = operands.get(0);
Set<Expression> values = new HashSet<>();
int numOperands = operands.size();
for (int i = 1; i < numOperands; i++) {
values.add(operands.get(i));
}
Expand Down