v20-0001-Use-64-bit-multixact-offsets.patch

From 651dbd070e96059980c50d3dc414ffb7b590bb4b Mon Sep 17 00:00:00 2001
From: Maxim Orlov <orlovmg@gmail.com>
Date: Wed, 7 Aug 2024 16:35:22 +0300
Subject: [PATCH v20 1/5] Use 64-bit multixact offsets

Switching to 64-bit multitransaction offsets removes wraparound and the
2^32 limit on their total number.

Author: Maxim Orlov <orlovmg@gmail.com>
---
 src/backend/access/rmgrdesc/mxactdesc.c   |   4 +-
 src/backend/access/rmgrdesc/xlogdesc.c    |   2 +-
 src/backend/access/transam/multixact.c    | 312 ++++------------------
 src/backend/access/transam/xlogrecovery.c |   2 +-
 src/backend/commands/vacuum.c             |   2 +-
 src/backend/postmaster/autovacuum.c       |   4 +-
 src/bin/pg_controldata/pg_controldata.c   |   2 +-
 src/bin/pg_resetwal/pg_resetwal.c         |   6 +-
 src/bin/pg_resetwal/t/001_basic.pl        |   2 +-
 src/include/access/multixact.h            |   3 +-
 src/include/c.h                           |   2 +-
 11 files changed, 63 insertions(+), 278 deletions(-)

diff --git a/src/backend/access/rmgrdesc/mxactdesc.c b/src/backend/access/rmgrdesc/mxactdesc.c
index 3ca0582db36..052dd0a4ce5 100644
--- a/src/backend/access/rmgrdesc/mxactdesc.c
+++ b/src/backend/access/rmgrdesc/mxactdesc.c
@@ -65,7 +65,7 @@ multixact_desc(StringInfo buf, XLogReaderState *record)
 		xl_multixact_create *xlrec = (xl_multixact_create *) rec;
 		int			i;
 
-		appendStringInfo(buf, "%u offset %u nmembers %d: ", xlrec->mid,
+		appendStringInfo(buf, "%u offset %" PRIu64 " nmembers %d: ", xlrec->mid,
 						 xlrec->moff, xlrec->nmembers);
 		for (i = 0; i < xlrec->nmembers; i++)
 			out_member(buf, &xlrec->members[i]);
@@ -74,7 +74,7 @@ multixact_desc(StringInfo buf, XLogReaderState *record)
 	{
 		xl_multixact_truncate *xlrec = (xl_multixact_truncate *) rec;
 
-		appendStringInfo(buf, "offsets [%u, %u), members [%u, %u)",
+		appendStringInfo(buf, "offsets [%u, %u), members [%" PRIu64 ", %" PRIu64 ")",
 						 xlrec->startTruncOff, xlrec->endTruncOff,
 						 xlrec->startTruncMemb, xlrec->endTruncMemb);
 	}
diff --git a/src/backend/access/rmgrdesc/xlogdesc.c b/src/backend/access/rmgrdesc/xlogdesc.c
index cd6c2a2f650..441034f5929 100644
--- a/src/backend/access/rmgrdesc/xlogdesc.c
+++ b/src/backend/access/rmgrdesc/xlogdesc.c
@@ -66,7 +66,7 @@ xlog_desc(StringInfo buf, XLogReaderState *record)
 		CheckPoint *checkpoint = (CheckPoint *) rec;
 
 		appendStringInfo(buf, "redo %X/%08X; "
-						 "tli %u; prev tli %u; fpw %s; wal_level %s; xid %u:%u; oid %u; multi %u; offset %u; "
+						 "tli %u; prev tli %u; fpw %s; wal_level %s; xid %u:%u; oid %u; multi %u; offset %" PRIu64 "; "
 						 "oldest xid %u in DB %u; oldest multi %u in DB %u; "
 						 "oldest/newest commit timestamp xid: %u/%u; "
 						 "oldest running xid %u; %s",
diff --git a/src/backend/access/transam/multixact.c b/src/backend/access/transam/multixact.c
index 9d5f130af7e..93a1e4cfd2a 100644
--- a/src/backend/access/transam/multixact.c
+++ b/src/backend/access/transam/multixact.c
@@ -92,17 +92,9 @@
 /*
  * Defines for MultiXactOffset page sizes.  A page is the same BLCKSZ as is
  * used everywhere else in Postgres.
- *
- * Note: because MultiXactOffsets are 32 bits and wrap around at 0xFFFFFFFF,
- * MultiXact page numbering also wraps around at
- * 0xFFFFFFFF/MULTIXACT_OFFSETS_PER_PAGE, and segment numbering at
- * 0xFFFFFFFF/MULTIXACT_OFFSETS_PER_PAGE/SLRU_PAGES_PER_SEGMENT.  We need
- * take no explicit notice of that fact in this module, except when comparing
- * segment and page numbers in TruncateMultiXact (see
- * MultiXactOffsetPagePrecedes).
  */
 
-/* We need four bytes per offset */
+/* We need 8 bytes per offset */
 #define MULTIXACT_OFFSETS_PER_PAGE (BLCKSZ / sizeof(MultiXactOffset))
 
 static inline int64
@@ -208,10 +200,14 @@ MXOffsetToMemberOffset(MultiXactOffset offset)
 		member_in_group * sizeof(TransactionId);
 }
 
-/* Multixact members wraparound thresholds. */
-#define MULTIXACT_MEMBER_SAFE_THRESHOLD		(MaxMultiXactOffset / 2)
-#define MULTIXACT_MEMBER_DANGER_THRESHOLD	\
-	(MaxMultiXactOffset - MaxMultiXactOffset / 4)
+/*
+ * Multixact members warning threshold.
+ *
+ * If difference bettween nextOffset and oldestOffset exceed this value, we
+ * trigger autovacuumin order to release the disk space, reduce table bloat if
+ * possible.
+ */
+#define MULTIXACT_MEMBER_AUTOVAC_THRESHOLD		UINT64CONST(0xFFFFFFFF)
 
 static inline MultiXactId
 PreviousMultiXactId(MultiXactId multi)
@@ -228,6 +224,24 @@ static SlruCtlData MultiXactMemberCtlData;
 #define MultiXactOffsetCtl	(&MultiXactOffsetCtlData)
 #define MultiXactMemberCtl	(&MultiXactMemberCtlData)
 
+static inline MultiXactOffset
+MXOffsetRead(int entryno, int slotno)
+{
+	MultiXactOffset *offptr =
+		(MultiXactOffset *) MultiXactOffsetCtl->shared->page_buffer[slotno];
+
+	return offptr[entryno];
+}
+
+static inline void
+MXOffsetWrite(int entryno, int slotno, MultiXactOffset offset)
+{
+	MultiXactOffset *offptr =
+		(MultiXactOffset *) MultiXactOffsetCtl->shared->page_buffer[slotno];
+
+	offptr[entryno] = offset;
+}
+
 /*
  * MultiXact state shared across all backends.  All this state is protected
  * by MultiXactGenLock.  (We also use SLRU bank's lock of MultiXactOffset and
@@ -268,9 +282,6 @@ typedef struct MultiXactStateData
 	MultiXactId multiStopLimit;
 	MultiXactId multiWrapLimit;
 
-	/* support for members anti-wraparound measures */
-	MultiXactOffset offsetStopLimit;	/* known if oldestOffsetKnown */
-
 	/*
 	 * This is used to sleep until a multixact offset is written when we want
 	 * to create the next one.
@@ -401,8 +412,6 @@ static bool MultiXactOffsetPrecedes(MultiXactOffset offset1,
 									MultiXactOffset offset2);
 static void ExtendMultiXactOffset(MultiXactId multi);
 static void ExtendMultiXactMember(MultiXactOffset offset, int nmembers);
-static bool MultiXactOffsetWouldWrap(MultiXactOffset boundary,
-									 MultiXactOffset start, uint32 distance);
 static bool SetOffsetVacuumLimit(bool is_startup);
 static bool find_multixact_start(MultiXactId multi, MultiXactOffset *result);
 static void WriteMTruncateXlogRec(Oid oldestMultiDB,
@@ -911,7 +920,6 @@ RecordNewMultiXact(MultiXactId multi, MultiXactOffset offset,
 	int64		prev_pageno;
 	int			entryno;
 	int			slotno;
-	MultiXactOffset *offptr;
 	int			i;
 	LWLock	   *lock;
 	LWLock	   *prevlock = NULL;
@@ -930,10 +938,8 @@ RecordNewMultiXact(MultiXactId multi, MultiXactOffset offset,
 	 * take the trouble to generalize the slru.c error reporting code.
 	 */
 	slotno = SimpleLruReadPage(MultiXactOffsetCtl, pageno, true, multi);
-	offptr = (MultiXactOffset *) MultiXactOffsetCtl->shared->page_buffer[slotno];
-	offptr += entryno;
 
-	*offptr = offset;
+	MXOffsetWrite(entryno, slotno, offset);
 
 	MultiXactOffsetCtl->shared->page_dirty[slotno] = true;
 
@@ -1155,78 +1161,6 @@ GetNewMultiXactId(int nmembers, MultiXactOffset *offset)
 	else
 		*offset = nextOffset;
 
-	/*----------
-	 * Protect against overrun of the members space as well, with the
-	 * following rules:
-	 *
-	 * If we're past offsetStopLimit, refuse to generate more multis.
-	 * If we're close to offsetStopLimit, emit a warning.
-	 *
-	 * Arbitrarily, we start emitting warnings when we're 20 segments or less
-	 * from offsetStopLimit.
-	 *
-	 * Note we haven't updated the shared state yet, so if we fail at this
-	 * point, the multixact ID we grabbed can still be used by the next guy.
-	 *
-	 * Note that there is no point in forcing autovacuum runs here: the
-	 * multixact freeze settings would have to be reduced for that to have any
-	 * effect.
-	 *----------
-	 */
-#define OFFSET_WARN_SEGMENTS	20
-	if (MultiXactState->oldestOffsetKnown &&
-		MultiXactOffsetWouldWrap(MultiXactState->offsetStopLimit, nextOffset,
-								 nmembers))
-	{
-		/* see comment in the corresponding offsets wraparound case */
-		SendPostmasterSignal(PMSIGNAL_START_AUTOVAC_LAUNCHER);
-
-		ereport(ERROR,
-				(errcode(ERRCODE_PROGRAM_LIMIT_EXCEEDED),
-				 errmsg("multixact \"members\" limit exceeded"),
-				 errdetail_plural("This command would create a multixact with %u members, but the remaining space is only enough for %u member.",
-								  "This command would create a multixact with %u members, but the remaining space is only enough for %u members.",
-								  MultiXactState->offsetStopLimit - nextOffset - 1,
-								  nmembers,
-								  MultiXactState->offsetStopLimit - nextOffset - 1),
-				 errhint("Execute a database-wide VACUUM in database with OID %u with reduced \"vacuum_multixact_freeze_min_age\" and \"vacuum_multixact_freeze_table_age\" settings.",
-						 MultiXactState->oldestMultiXactDB)));
-	}
-
-	/*
-	 * Check whether we should kick autovacuum into action, to prevent members
-	 * wraparound. NB we use a much larger window to trigger autovacuum than
-	 * just the warning limit. The warning is just a measure of last resort -
-	 * this is in line with GetNewTransactionId's behaviour.
-	 */
-	if (!MultiXactState->oldestOffsetKnown ||
-		(MultiXactState->nextOffset - MultiXactState->oldestOffset
-		 > MULTIXACT_MEMBER_SAFE_THRESHOLD))
-	{
-		/*
-		 * To avoid swamping the postmaster with signals, we issue the autovac
-		 * request only when crossing a segment boundary. With default
-		 * compilation settings that's roughly after 50k members.  This still
-		 * gives plenty of chances before we get into real trouble.
-		 */
-		if ((MXOffsetToMemberPage(nextOffset) / SLRU_PAGES_PER_SEGMENT) !=
-			(MXOffsetToMemberPage(nextOffset + nmembers) / SLRU_PAGES_PER_SEGMENT))
-			SendPostmasterSignal(PMSIGNAL_START_AUTOVAC_LAUNCHER);
-	}
-
-	if (MultiXactState->oldestOffsetKnown &&
-		MultiXactOffsetWouldWrap(MultiXactState->offsetStopLimit,
-								 nextOffset,
-								 nmembers + MULTIXACT_MEMBERS_PER_PAGE * SLRU_PAGES_PER_SEGMENT * OFFSET_WARN_SEGMENTS))
-		ereport(WARNING,
-				(errcode(ERRCODE_PROGRAM_LIMIT_EXCEEDED),
-				 errmsg_plural("database with OID %u must be vacuumed before %d more multixact member is used",
-							   "database with OID %u must be vacuumed before %d more multixact members are used",
-							   MultiXactState->offsetStopLimit - nextOffset + nmembers,
-							   MultiXactState->oldestMultiXactDB,
-							   MultiXactState->offsetStopLimit - nextOffset + nmembers),
-				 errhint("Execute a database-wide VACUUM in that database with reduced \"vacuum_multixact_freeze_min_age\" and \"vacuum_multixact_freeze_table_age\" settings.")));
-
 	ExtendMultiXactMember(nextOffset, nmembers);
 
 	/*
@@ -1255,7 +1189,8 @@ GetNewMultiXactId(int nmembers, MultiXactOffset *offset)
 
 	LWLockRelease(MultiXactGenLock);
 
-	debug_elog4(DEBUG2, "GetNew: returning %u offset %u", result, *offset);
+	debug_elog4(DEBUG2, "GetNew: returning %u offset %" PRIu64, result,
+				*offset);
 	return result;
 }
 
@@ -1294,7 +1229,6 @@ GetMultiXactIdMembers(MultiXactId multi, MultiXactMember **members,
 	int64		prev_pageno;
 	int			entryno;
 	int			slotno;
-	MultiXactOffset *offptr;
 	MultiXactOffset offset;
 	int			length;
 	int			truelength;
@@ -1418,9 +1352,8 @@ retry:
 	LWLockAcquire(lock, LW_EXCLUSIVE);
 
 	slotno = SimpleLruReadPage(MultiXactOffsetCtl, pageno, true, multi);
-	offptr = (MultiXactOffset *) MultiXactOffsetCtl->shared->page_buffer[slotno];
-	offptr += entryno;
-	offset = *offptr;
+
+	offset = MXOffsetRead(entryno, slotno);
 
 	Assert(offset != 0);
 
@@ -1467,9 +1400,7 @@ retry:
 			slotno = SimpleLruReadPage(MultiXactOffsetCtl, pageno, true, tmpMXact);
 		}
 
-		offptr = (MultiXactOffset *) MultiXactOffsetCtl->shared->page_buffer[slotno];
-		offptr += entryno;
-		nextMXOffset = *offptr;
+		nextMXOffset = MXOffsetRead(entryno, slotno);
 
 		if (nextMXOffset == 0)
 		{
@@ -1973,7 +1904,7 @@ MultiXactShmemInit(void)
 				  "pg_multixact/members", LWTRANCHE_MULTIXACTMEMBER_BUFFER,
 				  LWTRANCHE_MULTIXACTMEMBER_SLRU,
 				  SYNC_HANDLER_MULTIXACT_MEMBER,
-				  false);
+				  true);
 	/* doesn't call SimpleLruTruncate() or meet criteria for unit tests */
 
 	/* Initialize our shared state struct */
@@ -2150,7 +2081,6 @@ TrimMultiXact(void)
 		slotno = SimpleLruReadPage(MultiXactOffsetCtl, pageno, true, nextMXact);
 		offptr = (MultiXactOffset *) MultiXactOffsetCtl->shared->page_buffer[slotno];
 		offptr += entryno;
-
 		MemSet(offptr, 0, BLCKSZ - (entryno * sizeof(MultiXactOffset)));
 
 		MultiXactOffsetCtl->shared->page_dirty[slotno] = true;
@@ -2223,7 +2153,7 @@ MultiXactGetCheckptMulti(bool is_shutdown,
 	LWLockRelease(MultiXactGenLock);
 
 	debug_elog6(DEBUG2,
-				"MultiXact: checkpoint is nextMulti %u, nextOffset %u, oldestMulti %u in DB %u",
+				"MultiXact: checkpoint is nextMulti %u, nextOffset %" PRIu64 ", oldestMulti %u in DB %u",
 				*nextMulti, *nextMultiOffset, *oldestMulti, *oldestMultiDB);
 }
 
@@ -2258,7 +2188,7 @@ void
 MultiXactSetNextMXact(MultiXactId nextMulti,
 					  MultiXactOffset nextMultiOffset)
 {
-	debug_elog4(DEBUG2, "MultiXact: setting next multi to %u offset %u",
+	debug_elog4(DEBUG2, "MultiXact: setting next multi to %u offset %" PRIu64,
 				nextMulti, nextMultiOffset);
 	LWLockAcquire(MultiXactGenLock, LW_EXCLUSIVE);
 	MultiXactState->nextMXact = nextMulti;
@@ -2449,7 +2379,7 @@ MultiXactAdvanceNextMXact(MultiXactId minMulti,
 	}
 	if (MultiXactOffsetPrecedes(MultiXactState->nextOffset, minMultiOffset))
 	{
-		debug_elog3(DEBUG2, "MultiXact: setting next offset to %u",
+		debug_elog3(DEBUG2, "MultiXact: setting next offset to %" PRIU64,
 					minMultiOffset);
 		MultiXactState->nextOffset = minMultiOffset;
 	}
@@ -2633,15 +2563,13 @@ GetOldestMultiXactId(void)
 }
 
 /*
- * Determine how aggressively we need to vacuum in order to prevent member
- * wraparound.
+ * Determine if we need to vacuum for member or not.
  *
  * To do so determine what's the oldest member offset and install the limit
  * info in MultiXactState, where it can be used to prevent overrun of old data
  * in the members SLRU area.
  *
- * The return value is true if emergency autovacuum is required and false
- * otherwise.
+ * The return value is true if autovacuum is required and false otherwise.
  */
 static bool
 SetOffsetVacuumLimit(bool is_startup)
@@ -2653,8 +2581,6 @@ SetOffsetVacuumLimit(bool is_startup)
 	MultiXactOffset nextOffset;
 	bool		oldestOffsetKnown = false;
 	bool		prevOldestOffsetKnown;
-	MultiXactOffset offsetStopLimit = 0;
-	MultiXactOffset prevOffsetStopLimit;
 
 	/*
 	 * NB: Have to prevent concurrent truncation, we might otherwise try to
@@ -2669,7 +2595,6 @@ SetOffsetVacuumLimit(bool is_startup)
 	nextOffset = MultiXactState->nextOffset;
 	prevOldestOffsetKnown = MultiXactState->oldestOffsetKnown;
 	prevOldestOffset = MultiXactState->oldestOffset;
-	prevOffsetStopLimit = MultiXactState->offsetStopLimit;
 	Assert(MultiXactState->finishedStartup);
 	LWLockRelease(MultiXactGenLock);
 
@@ -2700,11 +2625,7 @@ SetOffsetVacuumLimit(bool is_startup)
 		oldestOffsetKnown =
 			find_multixact_start(oldestMultiXactId, &oldestOffset);
 
-		if (oldestOffsetKnown)
-			ereport(DEBUG1,
-					(errmsg_internal("oldest MultiXactId member is at offset %u",
-									 oldestOffset)));
-		else
+		if (!oldestOffsetKnown)
 			ereport(LOG,
 					(errmsg("MultiXact member wraparound protections are disabled because oldest checkpointed MultiXact %u does not exist on disk",
 							oldestMultiXactId)));
@@ -2717,24 +2638,7 @@ SetOffsetVacuumLimit(bool is_startup)
 	 * overrun of old data in the members SLRU area. We can only do so if the
 	 * oldest offset is known though.
 	 */
-	if (oldestOffsetKnown)
-	{
-		/* move back to start of the corresponding segment */
-		offsetStopLimit = oldestOffset - (oldestOffset %
-										  (MULTIXACT_MEMBERS_PER_PAGE * SLRU_PAGES_PER_SEGMENT));
-
-		/* always leave one segment before the wraparound point */
-		offsetStopLimit -= (MULTIXACT_MEMBERS_PER_PAGE * SLRU_PAGES_PER_SEGMENT);
-
-		if (!prevOldestOffsetKnown && !is_startup)
-			ereport(LOG,
-					(errmsg("MultiXact member wraparound protections are now enabled")));
-
-		ereport(DEBUG1,
-				(errmsg_internal("MultiXact member stop limit is now %u based on MultiXact %u",
-								 offsetStopLimit, oldestMultiXactId)));
-	}
-	else if (prevOldestOffsetKnown)
+	if (prevOldestOffsetKnown)
 	{
 		/*
 		 * If we failed to get the oldest offset this time, but we have a
@@ -2744,69 +2648,19 @@ SetOffsetVacuumLimit(bool is_startup)
 		 */
 		oldestOffset = prevOldestOffset;
 		oldestOffsetKnown = true;
-		offsetStopLimit = prevOffsetStopLimit;
 	}
 
 	/* Install the computed values */
 	LWLockAcquire(MultiXactGenLock, LW_EXCLUSIVE);
 	MultiXactState->oldestOffset = oldestOffset;
 	MultiXactState->oldestOffsetKnown = oldestOffsetKnown;
-	MultiXactState->offsetStopLimit = offsetStopLimit;
 	LWLockRelease(MultiXactGenLock);
 
 	/*
-	 * Do we need an emergency autovacuum?	If we're not sure, assume yes.
+	 * Do we need autovacuum?	If we're not sure, assume yes.
 	 */
 	return !oldestOffsetKnown ||
-		(nextOffset - oldestOffset > MULTIXACT_MEMBER_SAFE_THRESHOLD);
-}
-
-/*
- * Return whether adding "distance" to "start" would move past "boundary".
- *
- * We use this to determine whether the addition is "wrapping around" the
- * boundary point, hence the name.  The reason we don't want to use the regular
- * 2^31-modulo arithmetic here is that we want to be able to use the whole of
- * the 2^32-1 space here, allowing for more multixacts than would fit
- * otherwise.
- */
-static bool
-MultiXactOffsetWouldWrap(MultiXactOffset boundary, MultiXactOffset start,
-						 uint32 distance)
-{
-	MultiXactOffset finish;
-
-	/*
-	 * Note that offset number 0 is not used (see GetMultiXactIdMembers), so
-	 * if the addition wraps around the UINT_MAX boundary, skip that value.
-	 */
-	finish = start + distance;
-	if (finish < start)
-		finish++;
-
-	/*-----------------------------------------------------------------------
-	 * When the boundary is numerically greater than the starting point, any
-	 * value numerically between the two is not wrapped:
-	 *
-	 *	<----S----B---->
-	 *	[---)			 = F wrapped past B (and UINT_MAX)
-	 *		 [---)		 = F not wrapped
-	 *			  [----] = F wrapped past B
-	 *
-	 * When the boundary is numerically less than the starting point (i.e. the
-	 * UINT_MAX wraparound occurs somewhere in between) then all values in
-	 * between are wrapped:
-	 *
-	 *	<----B----S---->
-	 *	[---)			 = F not wrapped past B (but wrapped past UINT_MAX)
-	 *		 [---)		 = F wrapped past B (and UINT_MAX)
-	 *			  [----] = F not wrapped
-	 *-----------------------------------------------------------------------
-	 */
-	if (start < boundary)
-		return finish >= boundary || finish < start;
-	else
-		return finish >= boundary && finish < start;
+		(nextOffset - oldestOffset > MULTIXACT_MEMBER_AUTOVAC_THRESHOLD);
 }
 
 /*
@@ -2825,7 +2679,6 @@ find_multixact_start(MultiXactId multi, MultiXactOffset *result)
 	int64		pageno;
 	int			entryno;
 	int			slotno;
-	MultiXactOffset *offptr;
 
 	Assert(MultiXactState->finishedStartup);
 
@@ -2843,9 +2696,9 @@ find_multixact_start(MultiXactId multi, MultiXactOffset *result)
 
 	/* lock is acquired by SimpleLruReadPage_ReadOnly */
 	slotno = SimpleLruReadPage_ReadOnly(MultiXactOffsetCtl, pageno, multi);
-	offptr = (MultiXactOffset *) MultiXactOffsetCtl->shared->page_buffer[slotno];
-	offptr += entryno;
-	offset = *offptr;
+
+	offset = MXOffsetRead(entryno, slotno);
+
 	LWLockRelease(SimpleLruGetBankLock(MultiXactOffsetCtl, pageno));
 
 	*result = offset;
@@ -2893,73 +2746,6 @@ GetMultiXactInfo(uint32 *multixacts, MultiXactOffset *members,
 	return true;
 }
 
-/*
- * Multixact members can be removed once the multixacts that refer to them
- * are older than every datminmxid.  autovacuum_multixact_freeze_max_age and
- * vacuum_multixact_freeze_table_age work together to make sure we never have
- * too many multixacts; we hope that, at least under normal circumstances,
- * this will also be sufficient to keep us from using too many offsets.
- * However, if the average multixact has many members, we might exhaust the
- * members space while still using few enough members that these limits fail
- * to trigger relminmxid advancement by VACUUM.  At that point, we'd have no
- * choice but to start failing multixact-creating operations with an error.
- *
- * To prevent that, if more than a threshold portion of the members space is
- * used, we effectively reduce autovacuum_multixact_freeze_max_age and
- * to a value just less than the number of multixacts in use.  We hope that
- * this will quickly trigger autovacuuming on the table or tables with the
- * oldest relminmxid, thus allowing datminmxid values to advance and removing
- * some members.
- *
- * As the fraction of the member space currently in use grows, we become
- * more aggressive in clamping this value.  That not only causes autovacuum
- * to ramp up, but also makes any manual vacuums the user issues more
- * aggressive.  This happens because vacuum_get_cutoffs() will clamp the
- * freeze table and the minimum freeze age cutoffs based on the effective
- * autovacuum_multixact_freeze_max_age this function returns.  In the worst
- * case, we'll claim the freeze_max_age to zero, and every vacuum of any
- * table will freeze every multixact.
- */
-int
-MultiXactMemberFreezeThreshold(void)
-{
-	MultiXactOffset members;
-	uint32		multixacts;
-	uint32		victim_multixacts;
-	double		fraction;
-	int			result;
-	MultiXactId oldestMultiXactId;
-	MultiXactOffset oldestOffset;
-
-	/* If we can't determine member space utilization, assume the worst. */
-	if (!GetMultiXactInfo(&multixacts, &members, &oldestMultiXactId, &oldestOffset))
-		return 0;
-
-	/* If member space utilization is low, no special action is required. */
-	if (members <= MULTIXACT_MEMBER_SAFE_THRESHOLD)
-		return autovacuum_multixact_freeze_max_age;
-
-	/*
-	 * Compute a target for relminmxid advancement.  The number of multixacts
-	 * we try to eliminate from the system is based on how far we are past
-	 * MULTIXACT_MEMBER_SAFE_THRESHOLD.
-	 */
-	fraction = (double) (members - MULTIXACT_MEMBER_SAFE_THRESHOLD) /
-		(MULTIXACT_MEMBER_DANGER_THRESHOLD - MULTIXACT_MEMBER_SAFE_THRESHOLD);
-	victim_multixacts = multixacts * fraction;
-
-	/* fraction could be > 1.0, but lowest possible freeze age is zero */
-	if (victim_multixacts > multixacts)
-		return 0;
-	result = multixacts - victim_multixacts;
-
-	/*
-	 * Clamp to autovacuum_multixact_freeze_max_age, so that we never make
-	 * autovacuum less aggressive than it would otherwise be.
-	 */
-	return Min(result, autovacuum_multixact_freeze_max_age);
-}
-
 typedef struct mxtruncinfo
 {
 	int64		earliestExistingPage;
@@ -3159,7 +2945,7 @@ TruncateMultiXact(MultiXactId newOldestMulti, Oid newOldestMultiDB)
 
 	elog(DEBUG1, "performing multixact truncation: "
 		 "offsets [%u, %u), offsets segments [%" PRIx64 ", %" PRIx64 "), "
-		 "members [%u, %u), members segments [%" PRIx64 ", %" PRIx64 ")",
+		 "members [%" PRIu64 ", %" PRIu64 "), members segments [%" PRIx64 ", %" PRIx64 ")",
 		 oldestMulti, newOldestMulti,
 		 MultiXactIdToOffsetSegment(oldestMulti),
 		 MultiXactIdToOffsetSegment(newOldestMulti),
@@ -3290,7 +3076,7 @@ MultiXactIdPrecedesOrEquals(MultiXactId multi1, MultiXactId multi2)
 static bool
 MultiXactOffsetPrecedes(MultiXactOffset offset1, MultiXactOffset offset2)
 {
-	int32		diff = (int32) (offset1 - offset2);
+	int64		diff = (int64) (offset1 - offset2);
 
 	return (diff < 0);
 }
@@ -3387,7 +3173,7 @@ multixact_redo(XLogReaderState *record)
 
 		elog(DEBUG1, "replaying multixact truncation: "
 			 "offsets [%u, %u), offsets segments [%" PRIx64 ", %" PRIx64 "), "
-			 "members [%u, %u), members segments [%" PRIx64 ", %" PRIx64 ")",
+			 "members [%" PRIu64 ", %" PRIu64 "), members segments [%" PRIx64 ", %" PRIx64 ")",
 			 xlrec.startTruncOff, xlrec.endTruncOff,
 			 MultiXactIdToOffsetSegment(xlrec.startTruncOff),
 			 MultiXactIdToOffsetSegment(xlrec.endTruncOff),
diff --git a/src/backend/access/transam/xlogrecovery.c b/src/backend/access/transam/xlogrecovery.c
index 3e3c4da01a2..3b2b0a522cb 100644
--- a/src/backend/access/transam/xlogrecovery.c
+++ b/src/backend/access/transam/xlogrecovery.c
@@ -885,7 +885,7 @@ InitWalRecovery(ControlFileData *ControlFile, bool *wasShutdown_ptr,
 							 U64FromFullTransactionId(checkPoint.nextXid),
 							 checkPoint.nextOid)));
 	ereport(DEBUG1,
-			(errmsg_internal("next MultiXactId: %u; next MultiXactOffset: %u",
+			(errmsg_internal("next MultiXactId: %u; next MultiXactOffset: %" PRIu64,
 							 checkPoint.nextMulti, checkPoint.nextMultiOffset)));
 	ereport(DEBUG1,
 			(errmsg_internal("oldest unfrozen transaction ID: %u, in database %u",
diff --git a/src/backend/commands/vacuum.c b/src/backend/commands/vacuum.c
index ed03e3bd50d..259ef60bd31 100644
--- a/src/backend/commands/vacuum.c
+++ b/src/backend/commands/vacuum.c
@@ -1147,7 +1147,7 @@ vacuum_get_cutoffs(Relation rel, const VacuumParams params,
 	 * normally autovacuum_multixact_freeze_max_age, but may be less if we are
 	 * short of multixact member space.
 	 */
-	effective_multixact_freeze_max_age = MultiXactMemberFreezeThreshold();
+	effective_multixact_freeze_max_age = autovacuum_multixact_freeze_max_age;
 
 	/*
 	 * Almost ready to set freeze output parameters; check if OldestXmin or
diff --git a/src/backend/postmaster/autovacuum.c b/src/backend/postmaster/autovacuum.c
index 5084af7dfb6..26385470c19 100644
--- a/src/backend/postmaster/autovacuum.c
+++ b/src/backend/postmaster/autovacuum.c
@@ -1151,7 +1151,7 @@ do_start_worker(void)
 
 	/* Also determine the oldest datminmxid we will consider. */
 	recentMulti = ReadNextMultiXactId();
-	multiForceLimit = recentMulti - MultiXactMemberFreezeThreshold();
+	multiForceLimit = recentMulti - autovacuum_multixact_freeze_max_age;
 	if (multiForceLimit < FirstMultiXactId)
 		multiForceLimit -= FirstMultiXactId;
 
@@ -1939,7 +1939,7 @@ do_autovacuum(void)
 	 * normally autovacuum_multixact_freeze_max_age, but may be less if we are
 	 * short of multixact member space.
 	 */
-	effective_multixact_freeze_max_age = MultiXactMemberFreezeThreshold();
+	effective_multixact_freeze_max_age = autovacuum_multixact_freeze_max_age;
 
 	/*
 	 * Find the pg_database entry and select the default freeze ages. We use
diff --git a/src/bin/pg_controldata/pg_controldata.c b/src/bin/pg_controldata/pg_controldata.c
index 10de058ce91..5295108ade3 100644
--- a/src/bin/pg_controldata/pg_controldata.c
+++ b/src/bin/pg_controldata/pg_controldata.c
@@ -264,7 +264,7 @@ main(int argc, char *argv[])
 		   ControlFile->checkPointCopy.nextOid);
 	printf(_("Latest checkpoint's NextMultiXactId:  %u\n"),
 		   ControlFile->checkPointCopy.nextMulti);
-	printf(_("Latest checkpoint's NextMultiOffset:  %u\n"),
+	printf(_("Latest checkpoint's NextMultiOffset:  %" PRIu64 "\n"),
 		   ControlFile->checkPointCopy.nextMultiOffset);
 	printf(_("Latest checkpoint's oldestXID:        %u\n"),
 		   ControlFile->checkPointCopy.oldestXid);
diff --git a/src/bin/pg_resetwal/pg_resetwal.c b/src/bin/pg_resetwal/pg_resetwal.c
index a89d72fc5cf..4e5eeced89d 100644
--- a/src/bin/pg_resetwal/pg_resetwal.c
+++ b/src/bin/pg_resetwal/pg_resetwal.c
@@ -267,7 +267,7 @@ main(int argc, char *argv[])
 
 			case 'O':
 				errno = 0;
-				set_mxoff = strtoul(optarg, &endptr, 0);
+				set_mxoff = strtou64(optarg, &endptr, 0);
 				if (endptr == optarg || *endptr != '\0' || errno != 0)
 				{
 					pg_log_error("invalid argument for option %s", "-O");
@@ -743,7 +743,7 @@ PrintControlValues(bool guessed)
 		   ControlFile.checkPointCopy.nextOid);
 	printf(_("Latest checkpoint's NextMultiXactId:  %u\n"),
 		   ControlFile.checkPointCopy.nextMulti);
-	printf(_("Latest checkpoint's NextMultiOffset:  %u\n"),
+	printf(_("Latest checkpoint's NextMultiOffset:  %" PRIu64 "\n"),
 		   ControlFile.checkPointCopy.nextMultiOffset);
 	printf(_("Latest checkpoint's oldestXID:        %u\n"),
 		   ControlFile.checkPointCopy.oldestXid);
@@ -817,7 +817,7 @@ PrintNewControlValues(void)
 
 	if (set_mxoff != -1)
 	{
-		printf(_("NextMultiOffset:                      %u\n"),
+		printf(_("NextMultiOffset:                      %" PRIu64 "\n"),
 			   ControlFile.checkPointCopy.nextMultiOffset);
 	}
 
diff --git a/src/bin/pg_resetwal/t/001_basic.pl b/src/bin/pg_resetwal/t/001_basic.pl
index d6bbbd0ceda..cc89e0764ae 100644
--- a/src/bin/pg_resetwal/t/001_basic.pl
+++ b/src/bin/pg_resetwal/t/001_basic.pl
@@ -213,7 +213,7 @@ push @cmd,
   sprintf("%d,%d", hex($files[0]) == 0 ? 3 : hex($files[0]), hex($files[-1]));
 
 @files = get_slru_files('pg_multixact/offsets');
-$mult = 32 * $blcksz / 4;
+$mult = 32 * $blcksz / 8;
 # --multixact-ids argument is "new,old"
 push @cmd,
   '--multixact-ids' => sprintf("%d,%d",
diff --git a/src/include/access/multixact.h b/src/include/access/multixact.h
index 82e4bb90dd5..16a07723088 100644
--- a/src/include/access/multixact.h
+++ b/src/include/access/multixact.h
@@ -28,7 +28,7 @@
 
 #define MultiXactIdIsValid(multi) ((multi) != InvalidMultiXactId)
 
-#define MaxMultiXactOffset	((MultiXactOffset) 0xFFFFFFFF)
+#define MaxMultiXactOffset	UINT64CONST(0xFFFFFFFFFFFFFFFF)
 
 /*
  * Possible multixact lock modes ("status").  The first four modes are for
@@ -147,7 +147,6 @@ extern void MultiXactSetNextMXact(MultiXactId nextMulti,
 extern void MultiXactAdvanceNextMXact(MultiXactId minMulti,
 									  MultiXactOffset minMultiOffset);
 extern void MultiXactAdvanceOldest(MultiXactId oldestMulti, Oid oldestMultiDB);
-extern int	MultiXactMemberFreezeThreshold(void);
 
 extern void multixact_twophase_recover(FullTransactionId fxid, uint16 info,
 									   void *recdata, uint32 len);
diff --git a/src/include/c.h b/src/include/c.h
index 757dfff4782..bc92a6f4565 100644
--- a/src/include/c.h
+++ b/src/include/c.h
@@ -670,7 +670,7 @@ typedef uint32 SubTransactionId;
 /* MultiXactId must be equivalent to TransactionId, to fit in t_xmax */
 typedef TransactionId MultiXactId;
 
-typedef uint32 MultiXactOffset;
+typedef uint64 MultiXactOffset;
 
 typedef uint32 CommandId;
 
-- 
2.43.0