Fix CLUSTER progress reporting of number of blocks scanned.

Previously pg_stat_progress_cluster view reported the current block
number in heap scan as the number of heap blocks scanned (i.e.,
heap_blks_scanned). This reported number could be incorrect when
synchronize_seqscans is enabled, because it allowed the heap scan to
start at block in middle. This could result in wraparounds in the
heap_blks_scanned column when the heap scan wrapped around.
This commit fixes the bug by calculating the number of blocks from
the block that the heap scan starts at to the current block in scan,
and reporting that number in the heap_blks_scanned column.

Also, in pg_stat_progress_cluster view, previously heap_blks_scanned
could not reach heap_blks_total at the end of heap scan phase
if the last pages scanned were empty. This commit fixes the bug by
manually updating heap_blks_scanned to the same value as
heap_blks_total when the heap scan phase finishes.

Back-patch to v12 where pg_stat_progress_cluster view was introduced.

Reported-by: Matthias van de Meent
Author: Matthias van de Meent
Reviewed-by: Fujii Masao
Discussion: https://postgr.es/m/CAEze2WjCBWSGkVfYag001Rc4+-nNLDpWM7QbyD6yPvuhKs-gYQ@mail.gmail.com

1 files changed, 27 insertions, 2 deletions

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index dcaea7135fb..3eea215b852 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -698,6 +698,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	Datum	   *values;
 	bool	   *isnull;
 	BufferHeapTupleTableSlot *hslot;
+	BlockNumber prev_cblock = InvalidBlockNumber;
 
 	/* Remember if it's a system catalog */
 	is_system_catalog = IsSystemRelation(OldHeap);
@@ -793,14 +794,38 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 		else
 		{
 			if (!table_scan_getnextslot(tableScan, ForwardScanDirection, slot))
+			{
+				/*
+				 * If the last pages of the scan were empty, we would go to
+				 * the next phase while heap_blks_scanned != heap_blks_total.
+				 * Instead, to ensure that heap_blks_scanned is equivalent to
+				 * total_heap_blks after the table scan phase, this parameter
+				 * is manually updated to the correct value when the table
+				 * scan finishes.
+				 */
+				pgstat_progress_update_param(PROGRESS_CLUSTER_HEAP_BLKS_SCANNED,
+											 heapScan->rs_nblocks);
 				break;
+			}
 
 			/*
 			 * In scan-and-sort mode and also VACUUM FULL, set heap blocks
 			 * scanned
+			 *
+			 * Note that heapScan may start at an offset and wrap around, i.e.
+			 * rs_startblock may be >0, and rs_cblock may end with a number
+			 * below rs_startblock. To prevent showing this wraparound to the
+			 * user, we offset rs_cblock by rs_startblock (modulo rs_nblocks).
 			 */
-			pgstat_progress_update_param(PROGRESS_CLUSTER_HEAP_BLKS_SCANNED,
-										 heapScan->rs_cblock + 1);
+			if (prev_cblock != heapScan->rs_cblock)
+			{
+				pgstat_progress_update_param(PROGRESS_CLUSTER_HEAP_BLKS_SCANNED,
+											 (heapScan->rs_cblock +
+											  heapScan->rs_nblocks -
+											  heapScan->rs_startblock
+											  ) % heapScan->rs_nblocks + 1);
+				prev_cblock = heapScan->rs_cblock;
+			}
 		}
 
 		tuple = ExecFetchSlotHeapTuple(slot, false, NULL);