tableam: Move heap specific logic from estimate_rel_size below tableam.

This just moves the table/matview[/toast] determination of relation
size to a callback, and uses a copy of the existing logic to implement
that callback for heap.

It probably would make sense to also move the index specific logic
into a callback, so the metapage handling (and probably more) can be
index specific. But that's a separate task.

Author: Andres Freund
Discussion: https://postgr.es/m/20180703070645.wchpu5muyto5n647@alap3.anarazel.de

1 files changed, 113 insertions, 0 deletions

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index 33dac14edc2..cf6e35670b0 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -19,6 +19,8 @@
  */
 #include "postgres.h"
 
+#include <math.h>
+
 #include "miscadmin.h"
 
 #include "access/genam.h"
@@ -33,6 +35,7 @@
 #include "catalog/storage_xlog.h"
 #include "commands/progress.h"
 #include "executor/executor.h"
+#include "optimizer/plancat.h"
 #include "pgstat.h"
 #include "storage/bufmgr.h"
 #include "storage/bufpage.h"
@@ -1871,6 +1874,114 @@ reform_and_rewrite_tuple(HeapTuple tuple,
 
 
 /* ------------------------------------------------------------------------
+ * Planner related callbacks for the heap AM
+ * ------------------------------------------------------------------------
+ */
+
+static void
+heapam_estimate_rel_size(Relation rel, int32 *attr_widths,
+						 BlockNumber *pages, double *tuples,
+						 double *allvisfrac)
+{
+	BlockNumber curpages;
+	BlockNumber relpages;
+	double		reltuples;
+	BlockNumber relallvisible;
+	double		density;
+
+	/* it has storage, ok to call the smgr */
+	curpages = RelationGetNumberOfBlocks(rel);
+
+	/* coerce values in pg_class to more desirable types */
+	relpages = (BlockNumber) rel->rd_rel->relpages;
+	reltuples = (double) rel->rd_rel->reltuples;
+	relallvisible = (BlockNumber) rel->rd_rel->relallvisible;
+
+	/*
+	 * HACK: if the relation has never yet been vacuumed, use a minimum size
+	 * estimate of 10 pages.  The idea here is to avoid assuming a
+	 * newly-created table is really small, even if it currently is, because
+	 * that may not be true once some data gets loaded into it.  Once a vacuum
+	 * or analyze cycle has been done on it, it's more reasonable to believe
+	 * the size is somewhat stable.
+	 *
+	 * (Note that this is only an issue if the plan gets cached and used again
+	 * after the table has been filled.  What we're trying to avoid is using a
+	 * nestloop-type plan on a table that has grown substantially since the
+	 * plan was made.  Normally, autovacuum/autoanalyze will occur once enough
+	 * inserts have happened and cause cached-plan invalidation; but that
+	 * doesn't happen instantaneously, and it won't happen at all for cases
+	 * such as temporary tables.)
+	 *
+	 * We approximate "never vacuumed" by "has relpages = 0", which means this
+	 * will also fire on genuinely empty relations.  Not great, but
+	 * fortunately that's a seldom-seen case in the real world, and it
+	 * shouldn't degrade the quality of the plan too much anyway to err in
+	 * this direction.
+	 *
+	 * If the table has inheritance children, we don't apply this heuristic.
+	 * Totally empty parent tables are quite common, so we should be willing
+	 * to believe that they are empty.
+	 */
+	if (curpages < 10 &&
+		relpages == 0 &&
+		!rel->rd_rel->relhassubclass)
+		curpages = 10;
+
+	/* report estimated # pages */
+	*pages = curpages;
+	/* quick exit if rel is clearly empty */
+	if (curpages == 0)
+	{
+		*tuples = 0;
+		*allvisfrac = 0;
+		return;
+	}
+
+	/* estimate number of tuples from previous tuple density */
+	if (relpages > 0)
+		density = reltuples / (double) relpages;
+	else
+	{
+		/*
+		 * When we have no data because the relation was truncated, estimate
+		 * tuple width from attribute datatypes.  We assume here that the
+		 * pages are completely full, which is OK for tables (since they've
+		 * presumably not been VACUUMed yet) but is probably an overestimate
+		 * for indexes.  Fortunately get_relation_info() can clamp the
+		 * overestimate to the parent table's size.
+		 *
+		 * Note: this code intentionally disregards alignment considerations,
+		 * because (a) that would be gilding the lily considering how crude
+		 * the estimate is, and (b) it creates platform dependencies in the
+		 * default plans which are kind of a headache for regression testing.
+		 */
+		int32		tuple_width;
+
+		tuple_width = get_rel_data_width(rel, attr_widths);
+		tuple_width += MAXALIGN(SizeofHeapTupleHeader);
+		tuple_width += sizeof(ItemIdData);
+		/* note: integer division is intentional here */
+		density = (BLCKSZ - SizeOfPageHeaderData) / tuple_width;
+	}
+	*tuples = rint(density * (double) curpages);
+
+	/*
+	 * We use relallvisible as-is, rather than scaling it up like we do for
+	 * the pages and tuples counts, on the theory that any pages added since
+	 * the last VACUUM are most likely not marked all-visible.  But costsize.c
+	 * wants it converted to a fraction.
+	 */
+	if (relallvisible == 0 || curpages <= 0)
+		*allvisfrac = 0;
+	else if ((double) relallvisible >= curpages)
+		*allvisfrac = 1;
+	else
+		*allvisfrac = (double) relallvisible / curpages;
+}
+
+
+/* ------------------------------------------------------------------------
  * Definition of the heap table access method.
  * ------------------------------------------------------------------------
  */
@@ -1915,6 +2026,8 @@ static const TableAmRoutine heapam_methods = {
 	.scan_analyze_next_tuple = heapam_scan_analyze_next_tuple,
 	.index_build_range_scan = heapam_index_build_range_scan,
 	.index_validate_scan = heapam_index_validate_scan,
+
+	.relation_estimate_size = heapam_estimate_rel_size,
 };