Use streaming read I/O in VACUUM's third phase

melanieplageman · macdice · melanieplageman · commit c3e775e608f2 · 2025-02-14T12:57:49.000-05:00
Make vacuum's third phase (its second pass over the heap), which reaps dead items collected in the first phase and marks them as reusable, use the read stream API. This commit adds a new read stream callback, vacuum_reap_lp_read_stream_next(), that looks ahead in the TidStore and returns the next block number to read for vacuum. Author: Melanie Plageman <melanieplageman@gmail.com> Co-authored-by: Thomas Munro <thomas.munro@gmail.com> Reviewed-by: Masahiko Sawada <sawada.mshk@gmail.com> Discussion: https://postgr.es/m/CA%2BhUKGKN3oy0bN_3yv8hd78a4%2BM1tJC9z7mD8%2Bf%2ByA%2BGeoFUwQ%40mail.gmail.com
diff --git a/src/backend/access/heap/vacuumlazy.c b/src/backend/access/heap/vacuumlazy.c
@@ -2640,6 +2640,32 @@ lazy_vacuum_all_indexes(LVRelState *vacrel)
 	return allindexes;
 }
 
+/*
+ * Read stream callback for vacuum's third phase (second pass over the heap).
+ * Gets the next block from the TID store and returns it or InvalidBlockNumber
+ * if there are no further blocks to vacuum.
+ */
+static BlockNumber
+vacuum_reap_lp_read_stream_next(ReadStream *stream,
+								void *callback_private_data,
+								void *per_buffer_data)
+{
+	TidStoreIter *iter = callback_private_data;
+	TidStoreIterResult *iter_result;
+
+	iter_result = TidStoreIterateNext(iter);
+	if (iter_result == NULL)
+		return InvalidBlockNumber;
+
+	/*
+	 * Save the TidStoreIterResult for later, so we can extract the offsets.
+	 * It is safe to copy the result, according to TidStoreIterateNext().
+	 */
+	memcpy(per_buffer_data, iter_result, sizeof(*iter_result));
+
+	return iter_result->blkno;
+}
+
 /*
  *	lazy_vacuum_heap_rel() -- second pass over the heap for two pass strategy
  *
@@ -2660,11 +2686,11 @@ lazy_vacuum_all_indexes(LVRelState *vacrel)
 static void
 lazy_vacuum_heap_rel(LVRelState *vacrel)
 {
+	ReadStream *stream;
 	BlockNumber vacuumed_pages = 0;
 	Buffer		vmbuffer = InvalidBuffer;
 	LVSavedErrInfo saved_err_info;
 	TidStoreIter *iter;
-	TidStoreIterResult *iter_result;
 
 	Assert(vacrel->do_index_vacuuming);
 	Assert(vacrel->do_index_cleanup);
@@ -2680,20 +2706,37 @@ lazy_vacuum_heap_rel(LVRelState *vacrel)
 							 InvalidBlockNumber, InvalidOffsetNumber);
 
 	iter = TidStoreBeginIterate(vacrel->dead_items);
-	while ((iter_result = TidStoreIterateNext(iter)) != NULL)
+
+	/* Set up the read stream for vacuum's second pass through the heap */
+	stream = read_stream_begin_relation(READ_STREAM_MAINTENANCE,
+										vacrel->bstrategy,
+										vacrel->rel,
+										MAIN_FORKNUM,
+										vacuum_reap_lp_read_stream_next,
+										iter,
+										sizeof(TidStoreIterResult));
+
+	while (true)
 	{
 		BlockNumber blkno;
 		Buffer		buf;
 		Page		page;
+		TidStoreIterResult *iter_result;
 		Size		freespace;
 		OffsetNumber offsets[MaxOffsetNumber];
 		int			num_offsets;
 
 		vacuum_delay_point(false);
 
-		blkno = iter_result->blkno;
-		vacrel->blkno = blkno;
+		buf = read_stream_next_buffer(stream, (void **) &iter_result);
 
+		/* The relation is exhausted */
+		if (!BufferIsValid(buf))
+			break;
+
+		vacrel->blkno = blkno = BufferGetBlockNumber(buf);
+
+		Assert(iter_result);
 		num_offsets = TidStoreGetBlockOffsets(iter_result, offsets, lengthof(offsets));
 		Assert(num_offsets <= lengthof(offsets));
 
@@ -2705,8 +2748,6 @@ lazy_vacuum_heap_rel(LVRelState *vacrel)
 		visibilitymap_pin(vacrel->rel, blkno, &vmbuffer);
 
 		/* We need a non-cleanup exclusive lock to mark dead_items unused */
-		buf = ReadBufferExtended(vacrel->rel, MAIN_FORKNUM, blkno, RBM_NORMAL,
-								 vacrel->bstrategy);
 		LockBuffer(buf, BUFFER_LOCK_EXCLUSIVE);
 		lazy_vacuum_heap_page(vacrel, blkno, buf, offsets,
 							  num_offsets, vmbuffer);
@@ -2719,6 +2760,8 @@ lazy_vacuum_heap_rel(LVRelState *vacrel)
 		RecordPageWithFreeSpace(vacrel->rel, blkno, freespace);
 		vacuumed_pages++;
 	}
+
+	read_stream_end(stream);
 	TidStoreEndIterate(iter);
 
 	vacrel->blkno = InvalidBlockNumber;
