jackwener commented on code in PR #6645:
URL: https://github.com/apache/arrow-datafusion/pull/6645#discussion_r1226887782
##########
datafusion/core/src/physical_optimizer/optimizer.rs:
##########
@@ -42,3 +52,78 @@ pub trait PhysicalOptimizerRule {
/// and should disable the schema check.
fn schema_check(&self) -> bool;
}
+
+/// A rule-based physical optimizer.
+#[derive(Clone)]
+pub struct PhysicalOptimizer {
+ /// All rules to apply
+ pub rules: Vec<Arc<dyn PhysicalOptimizerRule + Send + Sync>>,
+}
+
+impl Default for PhysicalOptimizer {
+ fn default() -> Self {
+ Self::new()
+ }
+}
+
+impl PhysicalOptimizer {
+ /// Create a new optimizer using the recommended list of rules
+ pub fn new() -> Self {
+ let rules: Vec<Arc<dyn PhysicalOptimizerRule + Send + Sync>> = vec![
+ Arc::new(AggregateStatistics::new()),
+ // Statistics-based join selection will change the Auto mode to a
real join implementation,
+ // like collect left, or hash join, or future sort merge join,
which will influence the
+ // EnforceDistribution and EnforceSorting rules as they decide
whether to add additional
+ // repartitioning and local sorting steps to meet distribution and
ordering requirements.
+ // Therefore, it should run before EnforceDistribution and
EnforceSorting.
+ Arc::new(JoinSelection::new()),
+ // If the query is processing infinite inputs, the PipelineFixer
rule applies the
+ // necessary transformations to make the query runnable (if it is
not already runnable).
+ // If the query can not be made runnable, the rule emits an error
with a diagnostic message.
+ // Since the transformations it applies may alter output
partitioning properties of operators
+ // (e.g. by swapping hash join sides), this rule runs before
EnforceDistribution.
+ Arc::new(PipelineFixer::new()),
+ // In order to increase the parallelism, the Repartition rule will
change the
+ // output partitioning of some operators in the plan tree, which
will influence
+ // other rules. Therefore, it should run as soon as possible. It
is optional because:
+ // - It's not used for the distributed engine, Ballista.
+ // - It's conflicted with some parts of the EnforceDistribution,
since it will
+ // introduce additional repartitioning while EnforceDistribution
aims to
+ // reduce unnecessary repartitioning.
+ Arc::new(Repartition::new()),
+ // - Currently it will depend on the partition number to decide
whether to change the
+ // single node sort to parallel local sort and merge. Therefore,
GlobalSortSelection
+ // should run after the Repartition.
+ // - Since it will change the output ordering of some operators,
it should run
+ // before JoinSelection and EnforceSorting, which may depend on
that.
+ Arc::new(GlobalSortSelection::new()),
+ // The EnforceDistribution rule is for adding essential
repartition to satisfy the required
+ // distribution. Please make sure that the whole plan tree is
determined before this rule.
+ Arc::new(EnforceDistribution::new()),
+ // The CombinePartialFinalAggregate rule should be applied after
the EnforceDistribution rule
+ Arc::new(CombinePartialFinalAggregate::new()),
+ // The EnforceSorting rule is for adding essential local sorting
to satisfy the required
+ // ordering. Please make sure that the whole plan tree is
determined before this rule.
+ // Note that one should always run this rule after running the
EnforceDistribution rule
+ // as the latter may break local sorting requirements.
+ Arc::new(EnforceSorting::new()),
+ // The CoalesceBatches rule will not influence the distribution
and ordering of the
+ // whole plan tree. Therefore, to avoid influencing other rules,
it should run last.
+ Arc::new(CoalesceBatches::new()),
+ // The PipelineChecker rule will reject non-runnable query plans
that use
+ // pipeline-breaking operators on infinite input(s). The rule
generates a
+ // diagnostic error message when this happens. It makes no changes
to the
+ // given query plan; i.e. it only acts as a final gatekeeping rule.
+ Arc::new(PipelineChecker::new()),
+ ];
+
+ Self::with_rules(rules)
+ }
+
+ /// Create a new optimizer with the given rules
+ pub fn with_rules(rules: Vec<Arc<dyn PhysicalOptimizerRule + Send +
Sync>>) -> Self {
+ Self { rules }
+ }
+
Review Comment:
```suggestion
```
--
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: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
