Struct MergeScanExec 

pub struct MergeScanExec {

    table: TableName,
    regions: Vec<RegionId>,
    plan: LogicalPlan,
    arrow_schema: SchemaRef,
    region_query_handler: RegionQueryHandlerRef,
    metric: ExecutionPlanMetricsSet,
    properties: Arc<PlanProperties>,
    sub_stage_metrics: Arc<Mutex<HashMap<RegionId, RecordBatchMetrics>>>,
    partition_metrics: Arc<Mutex<HashMap<usize, PartitionMetrics>>>,
    query_ctx: QueryContextRef,
    remote_dyn_filter_producer_id: Option<RemoteDynFilterProducerId>,
    captured_remote_dyn_filters: Arc<Mutex<[Vec<CapturedDynFilter>; 2]>>,
    target_partition: usize,
    enable_per_region_metrics: bool,
}

Fields

table: TableName

regions: Vec<RegionId>

plan: LogicalPlan

arrow_schema: SchemaRef

region_query_handler: RegionQueryHandlerRef

metric: ExecutionPlanMetricsSet

properties: Arc<PlanProperties>

sub_stage_metrics: Arc<Mutex<HashMap<RegionId, RecordBatchMetrics>>>

Metrics from sub stages

partition_metrics: Arc<Mutex<HashMap<usize, PartitionMetrics>>>

Metrics for each partition

query_ctx: QueryContextRef

remote_dyn_filter_producer_id: Option<RemoteDynFilterProducerId>

Optional because RDF must fail open: missing ids skip RDF but keep normal query execution.

captured_remote_dyn_filters: Arc<Mutex<[Vec<CapturedDynFilter>; 2]>>

Filters captured by each filter pushdown phase, indexed by pushdown_phase_slot. The pre-optimization phase carries FilterExec predicates (e.g. scalar subquery filters) and the post-optimization phase carries dynamic filters from joins and TopK.

target_partition: usize

enable_per_region_metrics: bool

Implementations

impl MergeScanExec

pub fn new( session_state: &SessionState, table: TableName, regions: Vec<RegionId>, plan: LogicalPlan, arrow_schema: &ArrowSchema, region_query_handler: RegionQueryHandlerRef, query_ctx: QueryContextRef, target_partition: usize, remote_dyn_filter_producer_id: Option<RemoteDynFilterProducerId>, enable_per_region_metrics: bool, ) -> Result<Self>

fn estimated_num_rows(&self) -> Precision<usize>

Conservative row-count upper bound for all selected regions.

This is not an expected cardinality: DataFusion receives it as an inexact estimate only because Statistics has no upper-bound precision.

fn output_partition_count(num_regions: usize, target_partition: usize) -> usize

Number of partitions populated by the region striping in Self::to_stream.

pub fn to_stream( &self, context: Arc<TaskContext>, partition: usize, ) -> Result<SendableRecordBatchStream>

fn captured_remote_dyn_filters(&self) -> Vec<CapturedDynFilter>

pub fn sub_stage_metrics(&self) -> Vec<RecordBatchMetrics>

pub fn regions(&self) -> &[RegionId]

pub fn is_flow_sink_scan(&self) -> bool

pub fn partition_count(&self) -> usize

pub fn region_count(&self) -> usize

fn partition_metrics(&self) -> Vec<PartitionMetrics>

Trait Implementations

impl Clone for MergeScanExec

fn clone(&self) -> MergeScanExec

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for MergeScanExec

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl DisplayAs for MergeScanExec

fn fmt_as(&self, t: DisplayFormatType, f: &mut Formatter<'_>) -> Result

Format according to DisplayFormatType, used when verbose representation looks different from the default one

impl Drop for MergeScanExec

fn drop(&mut self)

Executes the destructor for this type.

fn pin_drop(self: Pin<&mut Self>)

🔬This is a nightly-only experimental API. (pin_ergonomics)

Execute the destructor for this type, but different to Drop::drop, it requires self to be pinned.

impl ExecutionPlan for MergeScanExec

fn schema(&self) -> ArrowSchemaRef

Get the schema for this execution plan

fn properties(&self) -> &Arc<PlanProperties>

Return properties of the output of the ExecutionPlan, such as output ordering(s), partitioning information etc.

fn children(&self) -> Vec<&Arc<dyn ExecutionPlan>>

Get a list of children ExecutionPlans that act as inputs to this plan. The returned list will be empty for leaf nodes such as scans, will contain a single value for unary nodes, or two values for binary nodes (such as joins).

fn apply_expressions( &self, f: &mut dyn FnMut(&Arc<dyn PhysicalExpr>) -> Result<TreeNodeRecursion>, ) -> Result<TreeNodeRecursion>

Apply a closure f to each root expression that this node owns and uses during execution, either by evaluating it or updating it dynamically.

fn with_new_children( self: Arc<Self>, _children: Vec<Arc<dyn ExecutionPlan>>, ) -> Result<Arc<dyn ExecutionPlan>>

👎Deprecated since 55.0.0:

Use ExecutionPlan::replace_children with ReplaceChildrenOptions

Deprecated.

fn handle_child_pushdown_result( &self, phase: FilterPushdownPhase, child_pushdown_result: ChildPushdownResult, _config: &ConfigOptions, ) -> Result<FilterPushdownPropagation<Arc<dyn ExecutionPlan>>>

Handle the result of a child pushdown.

fn execute( &self, partition: usize, context: Arc<TaskContext>, ) -> Result<SendableRecordBatchStream>

Begin execution of partition, returning a Stream of [RecordBatch]es.

fn metrics(&self) -> Option<MetricsSet>

Return a snapshot of the set of [Metric]s for this [ExecutionPlan]. If no Metrics are available, return None.

fn statistics_from_inputs( &self, _input_stats: &[Arc<Statistics>], args: &StatisticsArgs, ) -> Result<Arc<Statistics>>

Returns statistics for a specific partition of this ExecutionPlan node, given pre-computed child statistics.

fn name(&self) -> &str

Short name for the ExecutionPlan, such as ‘DataSourceExec’.

fn static_name() -> &'static str

where Self: Sized,

Short name for the ExecutionPlan, such as ‘DataSourceExec’. Like name but can be called without an instance.

fn downcast_delegate(&self) -> Option<&(dyn ExecutionPlan + 'static)>

Returns the plan that provides this plan’s public [ExecutionPlan] downcast identity.

fn check_invariants(&self, check: InvariantLevel) -> Result<(), DataFusionError>

Returns an error if this individual node does not conform to its invariants. These invariants are typically only checked in debug mode.

fn dynamic_expressions_produced(&self) -> Vec<Arc<dyn PhysicalExpr>>

Returns the dynamic expressions produced by this plan node.

fn required_input_distribution(&self) -> Vec<Distribution>

👎Deprecated since 55.0.0:

Use input_distribution_requirements

Specifies simple per-child input distribution requirements.

fn input_distribution_requirements(&self) -> InputDistributionRequirements

Specifies the input distribution requirements for this plan.

fn required_input_ordering(&self) -> Vec<Option<OrderingRequirements>>

Specifies the ordering required for all of the children of this ExecutionPlan.

fn maintains_input_order(&self) -> Vec<bool>

Returns false if this ExecutionPlan’s implementation may reorder rows within or between partitions.

fn benefits_from_input_partitioning(&self) -> Vec<bool>

Specifies whether the ExecutionPlan benefits from increased parallelization at its input for each child.

fn replace_children( self: Arc<Self>, children: Vec<Arc<dyn ExecutionPlan>>, options: ReplaceChildrenOptions, ) -> Result<Arc<dyn ExecutionPlan>, DataFusionError>

Returns a clone of the existing plan with the children replaced, skipping recomputation of plan properties when the options indicate the new children’s properties are unchanged.

fn with_new_children_and_same_properties( self: Arc<Self>, children: Vec<Arc<dyn ExecutionPlan>>, ) -> Result<Arc<dyn ExecutionPlan>, DataFusionError>

👎Deprecated since 55.0.0:

Use ExecutionPlan::replace_children with ReplaceChildrenOptions

Deprecated. Implement [ExecutionPlan::replace_children] instead.

fn reset_state( self: Arc<Self>, ) -> Result<Arc<dyn ExecutionPlan>, DataFusionError>

Reset any internal state within this [ExecutionPlan].

fn repartitioned( &self, _target_partitions: usize, _config: &ConfigOptions, ) -> Result<Option<Arc<dyn ExecutionPlan>>, DataFusionError>

If supported, attempt to increase the partitioning of this ExecutionPlan to produce target_partitions partitions.

fn partition_statistics( &self, partition: Option<usize>, ) -> Result<Arc<Statistics>, DataFusionError>

👎Deprecated since 55.0.0:

Use StatisticsContext::compute instead

Returns statistics for a specific partition of this ExecutionPlan node.

fn child_stats_requests(&self, _partition: Option<usize>) -> Vec<ChildStats>

Returns, per child, which statistics the StatisticsContext should resolve before calling [Self::statistics_from_inputs].

fn supports_limit_pushdown(&self) -> bool

Returns true if a limit can be safely pushed down through this ExecutionPlan node.

fn with_fetch(&self, _limit: Option<usize>) -> Option<Arc<dyn ExecutionPlan>>

Returns a fetching variant of this ExecutionPlan node, if it supports fetch limits. Returns None otherwise.

fn fetch(&self) -> Option<usize>

Gets the fetch count for the operator, None means there is no fetch.

fn cardinality_effect(&self) -> CardinalityEffect

Gets the effect on cardinality, if known

fn try_swapping_with_projection( &self, _projection: &ProjectionExec, ) -> Result<Option<Arc<dyn ExecutionPlan>>, DataFusionError>

Attempts to push down the given projection into the input of this ExecutionPlan.

fn gather_filters_for_pushdown( &self, _phase: FilterPushdownPhase, parent_filters: Vec<Arc<dyn PhysicalExpr>>, _config: &ConfigOptions, ) -> Result<FilterDescription, DataFusionError>

Collect filters that this node can push down to its children. Filters that are being pushed down from parents are passed in, and the node may generate additional filters to push down. For example, given the plan FilterExec -> HashJoinExec -> DataSourceExec, what will happen is that we recurse down the plan calling ExecutionPlan::gather_filters_for_pushdown:

fn with_new_state( &self, _state: Arc<dyn Any + Send + Sync>, ) -> Option<Arc<dyn ExecutionPlan>>

Injects arbitrary run-time state into this execution plan, returning a new plan instance that incorporates that state if it is relevant to the concrete node implementation.

fn try_pushdown_sort( &self, _order: &[PhysicalSortExpr], ) -> Result<SortOrderPushdownResult<Arc<dyn ExecutionPlan>>, DataFusionError>

Try to push down sort ordering requirements to this node.

fn with_preserve_order( &self, _preserve_order: bool, ) -> Option<Arc<dyn ExecutionPlan>>

Returns a variant of this ExecutionPlan that is aware of order-sensitivity.

fn try_to_proto( &self, _ctx: &ExecutionPlanEncodeCtx<'_>, ) -> Result<Option<PhysicalPlanNode>, DataFusionError>

Serialize this plan to its protobuf representation, if it knows how.