Skip to content

perf(expr): resolve row group stats once per eq/in/starts_with leaf #3254

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
laskoviymishka merged 1 commit into from
Sep 21, 2026
Merged

perf(expr): resolve row group stats once per eq/in/starts_with leaf #3254

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
24 changes: 18 additions & 6 deletions crates/iceberg/src/expr/visitors/row_group_metrics_evaluator.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -297,7 +297,11 @@ impl BoundPredicateVisitor for RowGroupMetricsEvaluator<'_> {
return ROW_GROUP_CANT_MATCH;
}

if let Some(lower_bound) = self.min_value(field_id)? {
let Some((stats, primitive_type)) = self.stats_and_type_for_field_id(field_id)? else {
return ROW_GROUP_MIGHT_MATCH;
};

if let Some(lower_bound) = get_parquet_stat_min_as_datum(&primitive_type, stats)? {
if lower_bound.is_nan() {
// NaN indicates unreliable bounds.
// See the InclusiveMetricsEvaluator docs for more.
Expand All @@ -307,7 +311,7 @@ impl BoundPredicateVisitor for RowGroupMetricsEvaluator<'_> {
}
}

if let Some(upper_bound) = self.max_value(field_id)? {
if let Some(upper_bound) = get_parquet_stat_max_as_datum(&primitive_type, stats)? {
if upper_bound.is_nan() {
// NaN indicates unreliable bounds.
// See the InclusiveMetricsEvaluator docs for more.
Expand Down Expand Up @@ -351,7 +355,11 @@ impl BoundPredicateVisitor for RowGroupMetricsEvaluator<'_> {
));
};

if let Some(lower_bound) = self.min_value(field_id)? {
let Some((stats, primitive_type)) = self.stats_and_type_for_field_id(field_id)? else {
return ROW_GROUP_MIGHT_MATCH;
};

if let Some(lower_bound) = get_parquet_stat_min_as_datum(&primitive_type, stats)? {
let PrimitiveLiteral::String(lower_bound) = lower_bound.literal() else {
return Err(Error::new(
ErrorKind::Unexpected,
Expand All @@ -369,7 +377,7 @@ impl BoundPredicateVisitor for RowGroupMetricsEvaluator<'_> {
}
}

if let Some(upper_bound) = self.max_value(field_id)? {
if let Some(upper_bound) = get_parquet_stat_max_as_datum(&primitive_type, stats)? {
let PrimitiveLiteral::String(upper_bound) = upper_bound.literal() else {
return Err(Error::new(
ErrorKind::Unexpected,
Expand Down Expand Up @@ -476,7 +484,11 @@ impl BoundPredicateVisitor for RowGroupMetricsEvaluator<'_> {
return ROW_GROUP_MIGHT_MATCH;
}

if let Some(lower_bound) = self.min_value(field_id)? {
let Some((stats, primitive_type)) = self.stats_and_type_for_field_id(field_id)? else {
return ROW_GROUP_MIGHT_MATCH;
};

if let Some(lower_bound) = get_parquet_stat_min_as_datum(&primitive_type, stats)? {
if lower_bound.is_nan() {
// NaN indicates unreliable bounds. See the InclusiveMetricsEvaluator docs for more.
return ROW_GROUP_MIGHT_MATCH;
Expand All @@ -488,7 +500,7 @@ impl BoundPredicateVisitor for RowGroupMetricsEvaluator<'_> {
}
}

if let Some(upper_bound) = self.max_value(field_id)? {
if let Some(upper_bound) = get_parquet_stat_max_as_datum(&primitive_type, stats)? {
if upper_bound.is_nan() {
// NaN indicates unreliable bounds. See the InclusiveMetricsEvaluator docs for more.
return ROW_GROUP_MIGHT_MATCH;
Expand Down
Loading