Consolidate sort and external_sort (#1596)

* Change SPMS to use heap sort, use SPMS instead of in-mem-sort as well

* Incorporate metrics, external_sort pass all sort tests

* Remove the original sort, substitute with external sort

* Fix different batch_size setting in SPMS test

* Change to use combine and sort for in memory N-way merge

* Resolve comments on async and doc

* Update sort to avoid deadlock during spilling

* Fix spill hanging

datafusion/src/execution/context.rs

@@ -1211,6 +1211,7 @@ impl FunctionRegistry for ExecutionContextState {
 #[cfg(test)]
 mod tests {
     use super::*;
+    use crate::execution::context::QueryPlanner;
     use crate::from_slice::FromSlice;
     use crate::logical_plan::plan::Projection;
     use crate::logical_plan::TableScan;

datafusion/src/physical_plan/common.rs

@@ -20,6 +20,7 @@
 use super::{RecordBatchStream, SendableRecordBatchStream};
 use crate::error::{DataFusionError, Result};
 use crate::execution::runtime_env::RuntimeEnv;
+use crate::physical_plan::metrics::BaselineMetrics;
 use crate::physical_plan::{ColumnStatistics, ExecutionPlan, Statistics};
 use arrow::compute::concat;
 use arrow::datatypes::{Schema, SchemaRef};
@@ -41,15 +42,21 @@ pub struct SizedRecordBatchStream {
     schema: SchemaRef,
     batches: Vec<Arc<RecordBatch>>,
     index: usize,
+    baseline_metrics: BaselineMetrics,
 }
 
 impl SizedRecordBatchStream {
     /// Create a new RecordBatchIterator
-    pub fn new(schema: SchemaRef, batches: Vec<Arc<RecordBatch>>) -> Self {
+    pub fn new(
+        schema: SchemaRef,
+        batches: Vec<Arc<RecordBatch>>,
+        baseline_metrics: BaselineMetrics,
+    ) -> Self {
         SizedRecordBatchStream {
             schema,
             index: 0,
             batches,
+            baseline_metrics,
         }
     }
 }
@@ -61,12 +68,13 @@ impl Stream for SizedRecordBatchStream {
         mut self: std::pin::Pin<&mut Self>,
         _: &mut Context<'_>,
     ) -> Poll<Option<Self::Item>> {
-        Poll::Ready(if self.index < self.batches.len() {
+        let poll = Poll::Ready(if self.index < self.batches.len() {
             self.index += 1;
             Some(Ok(self.batches[self.index - 1].as_ref().clone()))
         } else {
             None
-        })
+        });
+        self.baseline_metrics.record_poll(poll)
     }
 }
 

datafusion/src/physical_plan/explain.rs

@@ -32,6 +32,7 @@ use arrow::{array::StringBuilder, datatypes::SchemaRef, record_batch::RecordBatc
 
 use super::SendableRecordBatchStream;
 use crate::execution::runtime_env::RuntimeEnv;
+use crate::physical_plan::metrics::{BaselineMetrics, ExecutionPlanMetricsSet};
 use async_trait::async_trait;
 
 /// Explain execution plan operator. This operator contains the string
@@ -146,9 +147,13 @@ impl ExecutionPlan for ExplainExec {
             ],
         )?;
 
+        let metrics = ExecutionPlanMetricsSet::new();
+        let baseline_metrics = BaselineMetrics::new(&metrics, partition);
+
         Ok(Box::pin(SizedRecordBatchStream::new(
             self.schema.clone(),
             vec![Arc::new(record_batch)],
+            baseline_metrics,
         )))
     }