2010YOUY01 commented on code in PR #11627:
URL: https://github.com/apache/datafusion/pull/11627#discussion_r1695416828
##########
datafusion/physical-plan/src/aggregates/row_hash.rs:
##########
@@ -90,6 +94,69 @@ struct SpillState {
merging_group_by: PhysicalGroupBy,
}
+struct SkipAggregationProbe {
+ /// Number of processed input rows
Review Comment:
```suggestion
/// Number of processed input rows (updates during probing)
```
##########
datafusion/physical-plan/src/aggregates/row_hash.rs:
##########
@@ -90,6 +94,69 @@ struct SpillState {
merging_group_by: PhysicalGroupBy,
}
+struct SkipAggregationProbe {
+ /// Number of processed input rows
+ input_rows: usize,
+ /// Number of total group values for `input_rows`
Review Comment:
```suggestion
/// Number of total group values for `input_rows` (updates during
probing)
```
##########
datafusion/physical-plan/src/aggregates/row_hash.rs:
##########
@@ -90,6 +94,69 @@ struct SpillState {
merging_group_by: PhysicalGroupBy,
}
+struct SkipAggregationProbe {
+ /// Number of processed input rows
+ input_rows: usize,
+ /// Number of total group values for `input_rows`
+ num_groups: usize,
+
+ /// Aggregation ratio check should be performed only when the
+ /// number of input rows exceeds this threshold
Review Comment:
```suggestion
/// number of input rows exceeds this threshold (from `SessionConfig`)
```
##########
datafusion/physical-plan/src/aggregates/row_hash.rs:
##########
@@ -90,6 +94,69 @@ struct SpillState {
merging_group_by: PhysicalGroupBy,
}
+struct SkipAggregationProbe {
+ /// Number of processed input rows
+ input_rows: usize,
+ /// Number of total group values for `input_rows`
+ num_groups: usize,
+
+ /// Aggregation ratio check should be performed only when the
+ /// number of input rows exceeds this threshold
+ probe_rows_threshold: usize,
+ /// Maximum allowed value of `input_rows` / `num_groups` to
+ /// continue aggregation
Review Comment:
```suggestion
/// continue aggregation (from `SessionConfig`)
```
##########
datafusion/physical-plan/src/aggregates/row_hash.rs:
##########
@@ -90,6 +94,69 @@ struct SpillState {
merging_group_by: PhysicalGroupBy,
}
+struct SkipAggregationProbe {
+ /// Number of processed input rows
+ input_rows: usize,
+ /// Number of total group values for `input_rows`
+ num_groups: usize,
+
+ /// Aggregation ratio check should be performed only when the
+ /// number of input rows exceeds this threshold
+ probe_rows_threshold: usize,
+ /// Maximum allowed value of `input_rows` / `num_groups` to
+ /// continue aggregation
+ probe_ratio_threshold: f64,
+
+ /// Flag indicating that further data aggregation mey be skipped
+ should_skip: bool,
+ /// Flag indicating that further updates of `SkipAggregationProbe`
+ /// state won't make any effect
Review Comment:
```suggestion
/// state won't make any effect (decision made when probing is done)
```
##########
datafusion/physical-plan/src/aggregates/row_hash.rs:
##########
@@ -90,6 +94,69 @@ struct SpillState {
merging_group_by: PhysicalGroupBy,
}
+struct SkipAggregationProbe {
+ /// Number of processed input rows
+ input_rows: usize,
+ /// Number of total group values for `input_rows`
+ num_groups: usize,
+
+ /// Aggregation ratio check should be performed only when the
+ /// number of input rows exceeds this threshold
+ probe_rows_threshold: usize,
+ /// Maximum allowed value of `input_rows` / `num_groups` to
+ /// continue aggregation
+ probe_ratio_threshold: f64,
+
+ /// Flag indicating that further data aggregation mey be skipped
Review Comment:
```suggestion
/// Flag indicating that further data aggregation may be skipped
(decision made when probing is done)
```
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: github-unsubscr...@datafusion.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: github-unsubscr...@datafusion.apache.org
For additional commands, e-mail: github-h...@datafusion.apache.org
