tableam: Don't assume that every AM uses md.c style storage.

Previously various parts of the code routed size requests through
RelationGetNumberOfBlocks[InFork]. That works if md.c is used by the
AM, but not otherwise.

Add a tableam callback to return the size of the table. As not every
AM will use postgres' BLCKSZ, have it return bytes, and have
RelationGetNumberOfBlocksInFork() round the byte size up into blocks.

To allow code outside of the AM to determine the actual relation size
map InvalidForkNumber the total size of a relation, as not every AM
might just need the postgres defined forks.

A few users of RelationGetNumberOfBlocks() ought to be converted away
from that. One case, the use of it to determine whether a tid is
valid, will be fixed in a follow up commit. Others will have to wait
for v13.

Author: Andres Freund
Discussion: https://postgr.es/m/20190423225201.3bbv6tbqzkb5w7cw@alap3.anarazel.de

src/backend/access/heap/heapam_handler.c

@@ -1975,6 +1975,31 @@ heapam_scan_get_blocks_done(HeapScanDesc hscan)
 }
 
 
+/* ------------------------------------------------------------------------
+ * Miscellaneous callbacks for the heap AM
+ * ------------------------------------------------------------------------
+ */
+
+static uint64
+heapam_relation_size(Relation rel, ForkNumber forkNumber)
+{
+	uint64		nblocks = 0;
+
+	/* Open it at the smgr level if not already done */
+	RelationOpenSmgr(rel);
+
+	/* InvalidForkNumber indicates returning the size for all forks */
+	if (forkNumber == InvalidForkNumber)
+	{
+		for (int i = 0; i < MAX_FORKNUM; i++)
+			nblocks += smgrnblocks(rel->rd_smgr, i);
+	}
+	else
+		nblocks = smgrnblocks(rel->rd_smgr, forkNumber);
+
+	return nblocks * BLCKSZ;
+}
+
 
 /* ------------------------------------------------------------------------
  * Planner related callbacks for the heap AM
@@ -2556,6 +2581,8 @@ static const TableAmRoutine heapam_methods = {
 	.index_build_range_scan = heapam_index_build_range_scan,
 	.index_validate_scan = heapam_index_validate_scan,
 
+	.relation_size = heapam_relation_size,
+
 	.relation_estimate_size = heapam_estimate_rel_size,
 
 	.scan_bitmap_next_block = heapam_scan_bitmap_next_block,

src/backend/access/table/tableamapi.c

@@ -86,6 +86,9 @@ GetTableAmRoutine(Oid amhandler)
 	Assert(routine->scan_analyze_next_tuple != NULL);
 	Assert(routine->index_build_range_scan != NULL);
 	Assert(routine->index_validate_scan != NULL);
+
+	Assert(routine->relation_size != NULL);
+
 	Assert(routine->relation_estimate_size != NULL);
 
 	/* optional, but one callback implies presence of hte other */

src/backend/storage/buffer/bufmgr.c

@@ -33,6 +33,7 @@
 #include <sys/file.h>
 #include <unistd.h>
 
+#include "access/tableam.h"
 #include "access/xlog.h"
 #include "catalog/catalog.h"
 #include "catalog/storage.h"
@@ -2789,14 +2790,50 @@ FlushBuffer(BufferDesc *buf, SMgrRelation reln)
 /*
  * RelationGetNumberOfBlocksInFork
  *		Determines the current number of pages in the specified relation fork.
+ *
+ * Note that the accuracy of the result will depend on the details of the
+ * relation's storage. For builtin AMs it'll be accurate, but for external AMs
+ * it might not be.
  */
 BlockNumber
 RelationGetNumberOfBlocksInFork(Relation relation, ForkNumber forkNum)
 {
-	/* Open it at the smgr level if not already done */
-	RelationOpenSmgr(relation);
+	switch (relation->rd_rel->relkind)
+	{
+		case RELKIND_SEQUENCE:
+		case RELKIND_INDEX:
+		case RELKIND_PARTITIONED_INDEX:
+			/* Open it at the smgr level if not already done */
+			RelationOpenSmgr(relation);
+
+			return smgrnblocks(relation->rd_smgr, forkNum);
+
+		case RELKIND_RELATION:
+		case RELKIND_TOASTVALUE:
+		case RELKIND_MATVIEW:
+			{
+				/*
+				 * Not every table AM uses BLCKSZ wide fixed size
+				 * blocks. Therefore tableam returns the size in bytes - but
+				 * for the purpose of this routine, we want the number of
+				 * blocks. Therefore divide, rounding up.
+				 */
+				uint64 szbytes;
+
+				szbytes = table_relation_size(relation, forkNum);
+
+				return (szbytes + (BLCKSZ - 1)) / BLCKSZ;
+			}
+		case RELKIND_VIEW:
+		case RELKIND_COMPOSITE_TYPE:
+		case RELKIND_FOREIGN_TABLE:
+		case RELKIND_PARTITIONED_TABLE:
+		default:
+			Assert(false);
+			break;
+	}
 
-	return smgrnblocks(relation->rd_smgr, forkNum);
+	return 0;					/* keep compiler quiet */
 }
 
 /*

src/include/access/tableam.h

@@ -540,6 +540,22 @@ typedef struct TableAmRoutine
 										struct ValidateIndexState *state);
 
 
+	/* ------------------------------------------------------------------------
+	 * Miscellaneous functions.
+	 * ------------------------------------------------------------------------
+	 */
+
+	/*
+	 * See table_relation_size().
+	 *
+	 * Note that currently a few callers use the MAIN_FORKNUM size to vet the
+	 * validity of tids (e.g. nodeTidscans.c), and others use it to figure out
+	 * the range of potentially interesting blocks (brin, analyze). The
+	 * abstraction around this will need to be improved in the near future.
+	 */
+	uint64		(*relation_size) (Relation rel, ForkNumber forkNumber);
+
+
 	/* ------------------------------------------------------------------------
 	 * Planner related functions.
 	 * ------------------------------------------------------------------------
@@ -550,6 +566,10 @@ typedef struct TableAmRoutine
 	 *
 	 * While block oriented, it shouldn't be too hard for an AM that doesn't
 	 * doesn't internally use blocks to convert into a usable representation.
+	 *
+	 * This differs from the relation_size callback by returning size
+	 * estimates (both relation size and tuple count) for planning purposes,
+	 * rather than returning a currently correct estimate.
 	 */
 	void		(*relation_estimate_size) (Relation rel, int32 *attr_widths,
 										   BlockNumber *pages, double *tuples,
@@ -1503,6 +1523,26 @@ table_index_validate_scan(Relation heap_rel,
 }
 
 
+/* ----------------------------------------------------------------------------
+ * Miscellaneous functionality
+ * ----------------------------------------------------------------------------
+ */
+
+/*
+ * Return the current size of `rel` in bytes. If `forkNumber` is
+ * InvalidForkNumber, return the relation's overall size, otherwise the size
+ * for the indicated fork.
+ *
+ * Note that the overall size might not be the equivalent of the sum of sizes
+ * for the individual forks for some AMs, e.g. because the AMs storage does
+ * not neatly map onto the builtin types of forks.
+ */
+static inline uint64
+table_relation_size(Relation rel, ForkNumber forkNumber)
+{
+	return rel->rd_tableam->relation_size(rel, forkNumber);
+}
+
 /* ----------------------------------------------------------------------------
  * Planner related functionality
  * ----------------------------------------------------------------------------