Support parallel bitmap heap scans.

The index is scanned by a single process, but then all cooperating
processes can iterate jointly over the resulting set of heap blocks.
In the future, we might also want to support using a parallel bitmap
index scan to set up for a parallel bitmap heap scan, but that's a
job for another day.

Dilip Kumar, with some corrections and cosmetic changes by me.  The
larger patch set of which this is a part has been reviewed and tested
by (at least) Andres Freund, Amit Khandekar, Tushar Ahuja, Rafia
Sabih, Haribabu Kommi, Thomas Munro, and me.

Discussion: http://postgr.es/m/CAFiTN-uc4=0WxRGfCzs-xfkMYcSEWUC-Fon6thkJGjkh9i=13A@mail.gmail.com

1 files changed, 15 insertions, 1 deletions

diff --git a/src/backend/optimizer/path/costsize.c b/src/backend/optimizer/path/costsize.c
index 3eaed5af7a5..627e3f1b954 100644
--- a/src/backend/optimizer/path/costsize.c
+++ b/src/backend/optimizer/path/costsize.c
@@ -860,6 +860,7 @@ cost_bitmap_heap_scan(Path *path, PlannerInfo *root, RelOptInfo *baserel,
 	QualCost	qpqual_cost;
 	Cost		cpu_per_tuple;
 	Cost		cost_per_page;
+	Cost		cpu_run_cost;
 	double		tuples_fetched;
 	double		pages_fetched;
 	double		spc_seq_page_cost,
@@ -921,8 +922,21 @@ cost_bitmap_heap_scan(Path *path, PlannerInfo *root, RelOptInfo *baserel,
 
 	startup_cost += qpqual_cost.startup;
 	cpu_per_tuple = cpu_tuple_cost + qpqual_cost.per_tuple;
+	cpu_run_cost = cpu_per_tuple * tuples_fetched;
+
+	/* Adjust costing for parallelism, if used. */
+	if (path->parallel_workers > 0)
+	{
+		double		parallel_divisor = get_parallel_divisor(path);
+
+		/* The CPU cost is divided among all the workers. */
+		cpu_run_cost /= parallel_divisor;
 
-	run_cost += cpu_per_tuple * tuples_fetched;
+		path->rows = clamp_row_est(path->rows / parallel_divisor);
+	}
+
+
+	run_cost += cpu_run_cost;
 
 	/* tlist eval costs are paid per output row, not per tuple scanned */
 	startup_cost += path->pathtarget->cost.startup;