v24-0009-Update-vacuum-integration-patch-from-v23.patch

From fd380a199f38545a56d7fa11c45ec088d62389f4 Mon Sep 17 00:00:00 2001
From: Masahiko Sawada <sawada.mshk@gmail.com>
Date: Tue, 31 Jan 2023 22:44:40 +0900
Subject: [PATCH v24 9/9] Update vacuum integration patch from v23.

---
 src/backend/access/heap/vacuumlazy.c  | 64 +++++++++++++--------------
 src/backend/commands/vacuumparallel.c | 11 +++--
 2 files changed, 37 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/vacuumlazy.c b/src/backend/access/heap/vacuumlazy.c
index 3537df16fd..b4e40423a8 100644
--- a/src/backend/access/heap/vacuumlazy.c
+++ b/src/backend/access/heap/vacuumlazy.c
@@ -3,18 +3,18 @@
  * vacuumlazy.c
  *	  Concurrent ("lazy") vacuuming.
  *
- * The major space usage for vacuuming is storage for the array of dead TIDs
+ * The major space usage for vacuuming is TidStore, a storage for dead TIDs
  * that are to be removed from indexes.  We want to ensure we can vacuum even
  * the very largest relations with finite memory space usage.  To do that, we
- * set upper bounds on the number of TIDs we can keep track of at once.
+ * set upper bounds on the maximum memory that can be used for keeping track
+ * of dead TIDs at once.
  *
  * We are willing to use at most maintenance_work_mem (or perhaps
  * autovacuum_work_mem) memory space to keep track of dead TIDs.  We initially
- * allocate an array of TIDs of that size, with an upper limit that depends on
- * table size (this limit ensures we don't allocate a huge area uselessly for
- * vacuuming small tables).  If the array threatens to overflow, we must call
- * lazy_vacuum to vacuum indexes (and to vacuum the pages that we've pruned).
- * This frees up the memory space dedicated to storing dead TIDs.
+ * create a TidStore with the maximum bytes that can be used by the TidStore.
+ * If the TidStore is full, we must call lazy_vacuum to vacuum indexes (and to
+ * vacuum the pages that we've pruned). This frees up the memory space dedicated
+ * to storing dead TIDs.
  *
  * In practice VACUUM will often complete its initial pass over the target
  * heap relation without ever running out of space to store TIDs.  This means
@@ -492,11 +492,11 @@ heap_vacuum_rel(Relation rel, VacuumParams *params,
 	}
 
 	/*
-	 * Allocate dead_items array memory using dead_items_alloc.  This handles
-	 * parallel VACUUM initialization as part of allocating shared memory
-	 * space used for dead_items.  (But do a failsafe precheck first, to
-	 * ensure that parallel VACUUM won't be attempted at all when relfrozenxid
-	 * is already dangerously old.)
+	 * Allocate dead_items memory using dead_items_alloc.  This handles parallel
+	 * VACUUM initialization as part of allocating shared memory space used for
+	 * dead_items.  (But do a failsafe precheck first, to ensure that parallel
+	 * VACUUM won't be attempted at all when relfrozenxid is already dangerously
+	 * old.)
 	 */
 	lazy_check_wraparound_failsafe(vacrel);
 	dead_items_alloc(vacrel, params->nworkers);
@@ -802,7 +802,7 @@ heap_vacuum_rel(Relation rel, VacuumParams *params,
  *		have collected the TIDs whose index tuples need to be removed.
  *
  *		Finally, invokes lazy_vacuum_heap_rel to vacuum heap pages, which
- *		largely consists of marking LP_DEAD items (from collected TID array)
+ *		largely consists of marking LP_DEAD items (from vacrel->dead_items)
  *		as LP_UNUSED.  This has to happen in a second, final pass over the
  *		heap, to preserve a basic invariant that all index AMs rely on: no
  *		extant index tuple can ever be allowed to contain a TID that points to
@@ -973,7 +973,7 @@ lazy_scan_heap(LVRelState *vacrel)
 				continue;
 			}
 
-			/* Collect LP_DEAD items in dead_items array, count tuples */
+			/* Collect LP_DEAD items in dead_items, count tuples */
 			if (lazy_scan_noprune(vacrel, buf, blkno, page, &hastup,
 								  &recordfreespace))
 			{
@@ -1015,10 +1015,10 @@ lazy_scan_heap(LVRelState *vacrel)
 		 * Prune, freeze, and count tuples.
 		 *
 		 * Accumulates details of remaining LP_DEAD line pointers on page in
-		 * dead_items array.  This includes LP_DEAD line pointers that we
-		 * pruned ourselves, as well as existing LP_DEAD line pointers that
-		 * were pruned some time earlier.  Also considers freezing XIDs in the
-		 * tuple headers of remaining items with storage.
+		 * dead_items.  This includes LP_DEAD line pointers that we pruned
+		 * ourselves, as well as existing LP_DEAD line pointers that were pruned
+		 * some time earlier.  Also considers freezing XIDs in the tuple headers
+		 * of remaining items with storage.
 		 */
 		lazy_scan_prune(vacrel, buf, blkno, page, &prunestate);
 
@@ -1084,7 +1084,7 @@ lazy_scan_heap(LVRelState *vacrel)
 		}
 		else if (prunestate.num_offsets > 0)
 		{
-			/* Save details of the LP_DEAD items from the page */
+			/* Save details of the LP_DEAD items from the page in dead_items */
 			tidstore_add_tids(dead_items, blkno, prunestate.deadoffsets,
 							  prunestate.num_offsets);
 
@@ -1535,9 +1535,9 @@ lazy_scan_new_or_empty(LVRelState *vacrel, Buffer buf, BlockNumber blkno,
  * The approach we take now is to restart pruning when the race condition is
  * detected.  This allows heap_page_prune() to prune the tuples inserted by
  * the now-aborted transaction.  This is a little crude, but it guarantees
- * that any items that make it into the dead_items array are simple LP_DEAD
- * line pointers, and that every remaining item with tuple storage is
- * considered as a candidate for freezing.
+ * that any items that make it into the dead_items are simple LP_DEAD line
+ * pointers, and that every remaining item with tuple storage is considered
+ * as a candidate for freezing.
  */
 static void
 lazy_scan_prune(LVRelState *vacrel,
@@ -1929,7 +1929,7 @@ retry:
  * lazy_scan_prune, which requires a full cleanup lock.  While pruning isn't
  * performed here, it's quite possible that an earlier opportunistic pruning
  * operation left LP_DEAD items behind.  We'll at least collect any such items
- * in the dead_items array for removal from indexes.
+ * in the dead_items for removal from indexes.
  *
  * For aggressive VACUUM callers, we may return false to indicate that a full
  * cleanup lock is required for processing by lazy_scan_prune.  This is only
@@ -2088,7 +2088,7 @@ lazy_scan_noprune(LVRelState *vacrel,
 	vacrel->NewRelfrozenXid = NoFreezePageRelfrozenXid;
 	vacrel->NewRelminMxid = NoFreezePageRelminMxid;
 
-	/* Save any LP_DEAD items found on the page in dead_items array */
+	/* Save any LP_DEAD items found on the page in dead_items */
 	if (vacrel->nindexes == 0)
 	{
 		/* Using one-pass strategy (since table has no indexes) */
@@ -2373,9 +2373,8 @@ lazy_vacuum_all_indexes(LVRelState *vacrel)
 /*
  *	lazy_vacuum_heap_rel() -- second pass over the heap for two pass strategy
  *
- * This routine marks LP_DEAD items in vacrel->dead_items array as LP_UNUSED.
- * Pages that never had lazy_scan_prune record LP_DEAD items are not visited
- * at all.
+ * This routine marks LP_DEAD items in vacrel->dead_items as LP_UNUSED. Pages
+ * that never had lazy_scan_prune record LP_DEAD items are not visited at all.
  *
  * We may also be able to truncate the line pointer array of the heap pages we
  * visit.  If there is a contiguous group of LP_UNUSED items at the end of the
@@ -2461,7 +2460,8 @@ lazy_vacuum_heap_rel(LVRelState *vacrel)
 
 	ereport(DEBUG2,
 			(errmsg("table \"%s\": removed " UINT64_FORMAT "dead item identifiers in %u pages",
-					vacrel->relname, tidstore_num_tids(vacrel->dead_items), vacuumed_pages)));
+					vacrel->relname, tidstore_num_tids(vacrel->dead_items),
+					vacuumed_pages)));
 
 	/* Revert to the previous phase information for error traceback */
 	restore_vacuum_error_info(vacrel, &saved_err_info);
@@ -2660,8 +2660,8 @@ lazy_cleanup_all_indexes(LVRelState *vacrel)
  *	lazy_vacuum_one_index() -- vacuum index relation.
  *
  *		Delete all the index tuples containing a TID collected in
- *		vacrel->dead_items array.  Also update running statistics.
- *		Exact details depend on index AM's ambulkdelete routine.
+ *		vacrel->dead_items.  Also update running statistics. Exact
+ *		details depend on index AM's ambulkdelete routine.
  *
  *		reltuples is the number of heap tuples to be passed to the
  *		bulkdelete callback.  It's always assumed to be estimated.
@@ -3067,8 +3067,8 @@ count_nondeletable_pages(LVRelState *vacrel, bool *lock_waiter_detected)
 }
 
 /*
- * Allocate dead_items (either using palloc, or in dynamic shared memory).
- * Sets dead_items in vacrel for caller.
+ * Allocate a (local or shared) TidStore for storing dead TIDs. Sets dead_items
+ * in vacrel for caller.
  *
  * Also handles parallel initialization as part of allocating dead_items in
  * DSM when required.
diff --git a/src/backend/commands/vacuumparallel.c b/src/backend/commands/vacuumparallel.c
index 5c7e6ed99c..d653683693 100644
--- a/src/backend/commands/vacuumparallel.c
+++ b/src/backend/commands/vacuumparallel.c
@@ -9,12 +9,11 @@
  * In a parallel vacuum, we perform both index bulk deletion and index cleanup
  * with parallel worker processes.  Individual indexes are processed by one
  * vacuum process.  ParalleVacuumState contains shared information as well as
- * the memory space for storing dead items allocated in the DSM segment.  We
- * launch parallel worker processes at the start of parallel index
- * bulk-deletion and index cleanup and once all indexes are processed, the
- * parallel worker processes exit.  Each time we process indexes in parallel,
- * the parallel context is re-initialized so that the same DSM can be used for
- * multiple passes of index bulk-deletion and index cleanup.
+ * the shared TidStore. We launch parallel worker processes at the start of
+ * parallel index bulk-deletion and index cleanup and once all indexes are
+ * processed, the parallel worker processes exit.  Each time we process indexes
+ * in parallel, the parallel context is re-initialized so that the same DSM can
+ * be used for multiple passes of index bulk-deletion and index cleanup.
  *
  * Portions Copyright (c) 1996-2023, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
-- 
2.31.1