v12-0002-Use-64-bit-multixact-offsets.patch

From b4db0517df2510bd452ae0e82d4b707e70fa29f5 Mon Sep 17 00:00:00 2001
From: Maxim Orlov <m.orlov@postgrespro.ru>
Date: Wed, 6 Mar 2024 11:11:33 +0300
Subject: [PATCH v12 2/7] Use 64-bit multixact offsets.

Author: Maxim Orlov <orlovmg@gmail.com>
---
 src/backend/access/transam/multixact.c  | 541 ++----------------------
 src/backend/access/transam/xlog.c       |   2 +-
 src/backend/commands/vacuum.c           |   2 +-
 src/backend/postmaster/autovacuum.c     |   4 +-
 src/bin/pg_resetwal/pg_resetwal.c       |   2 +-
 src/bin/pg_resetwal/t/001_basic.pl      |   2 +-
 src/include/access/multixact.h          |   3 +-
 src/include/access/multixact_internal.h | 115 +++++
 src/include/c.h                         |   2 +-
 9 files changed, 156 insertions(+), 517 deletions(-)
 create mode 100644 src/include/access/multixact_internal.h

diff --git a/src/backend/access/transam/multixact.c b/src/backend/access/transam/multixact.c
index 623fc8bdac..cd9db52e95 100644
--- a/src/backend/access/transam/multixact.c
+++ b/src/backend/access/transam/multixact.c
@@ -69,6 +69,7 @@
 #include "postgres.h"
 
 #include "access/multixact.h"
+#include "access/multixact_internal.h"
 #include "access/slru.h"
 #include "access/transam.h"
 #include "access/twophase.h"
@@ -92,130 +93,14 @@
 #include "utils/injection_point.h"
 #include "utils/memutils.h"
 
-
-/*
- * 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 */
-#define MULTIXACT_OFFSETS_PER_PAGE (BLCKSZ / sizeof(MultiXactOffset))
-
-static inline int64
-MultiXactIdToOffsetPage(MultiXactId multi)
-{
-	return multi / MULTIXACT_OFFSETS_PER_PAGE;
-}
-
-static inline int
-MultiXactIdToOffsetEntry(MultiXactId multi)
-{
-	return multi % MULTIXACT_OFFSETS_PER_PAGE;
-}
-
-static inline int64
-MultiXactIdToOffsetSegment(MultiXactId multi)
-{
-	return MultiXactIdToOffsetPage(multi) / SLRU_PAGES_PER_SEGMENT;
-}
-
-/*
- * The situation for members is a bit more complex: we store one byte of
- * additional flag bits for each TransactionId.  To do this without getting
- * into alignment issues, we store four bytes of flags, and then the
- * corresponding 4 Xids.  Each such 5-word (20-byte) set we call a "group", and
- * are stored as a whole in pages.  Thus, with 8kB BLCKSZ, we keep 409 groups
- * per page.  This wastes 12 bytes per page, but that's OK -- simplicity (and
- * performance) trumps space efficiency here.
- *
- * Note that the "offset" macros work with byte offset, not array indexes, so
- * arithmetic must be done using "char *" pointers.
- */
-/* We need eight bits per xact, so one xact fits in a byte */
-#define MXACT_MEMBER_BITS_PER_XACT			8
-#define MXACT_MEMBER_FLAGS_PER_BYTE			1
-#define MXACT_MEMBER_XACT_BITMASK	((1 << MXACT_MEMBER_BITS_PER_XACT) - 1)
-
-/* how many full bytes of flags are there in a group? */
-#define MULTIXACT_FLAGBYTES_PER_GROUP		4
-#define MULTIXACT_MEMBERS_PER_MEMBERGROUP	\
-	(MULTIXACT_FLAGBYTES_PER_GROUP * MXACT_MEMBER_FLAGS_PER_BYTE)
-/* size in bytes of a complete group */
-#define MULTIXACT_MEMBERGROUP_SIZE \
-	(sizeof(TransactionId) * MULTIXACT_MEMBERS_PER_MEMBERGROUP + MULTIXACT_FLAGBYTES_PER_GROUP)
-#define MULTIXACT_MEMBERGROUPS_PER_PAGE (BLCKSZ / MULTIXACT_MEMBERGROUP_SIZE)
-#define MULTIXACT_MEMBERS_PER_PAGE	\
-	(MULTIXACT_MEMBERGROUPS_PER_PAGE * MULTIXACT_MEMBERS_PER_MEMBERGROUP)
-
 /*
- * Because the number of items per page is not a divisor of the last item
- * number (member 0xFFFFFFFF), the last segment does not use the maximum number
- * of pages, and moreover the last used page therein does not use the same
- * number of items as previous pages.  (Another way to say it is that the
- * 0xFFFFFFFF member is somewhere in the middle of the last page, so the page
- * has some empty space after that item.)
- *
- * This constant is the number of members in the last page of the last segment.
+ * 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 MAX_MEMBERS_IN_LAST_MEMBERS_PAGE \
-		((uint32) ((0xFFFFFFFF % MULTIXACT_MEMBERS_PER_PAGE) + 1))
-
-/* page in which a member is to be found */
-static inline int64
-MXOffsetToMemberPage(MultiXactOffset offset)
-{
-	return offset / MULTIXACT_MEMBERS_PER_PAGE;
-}
-
-static inline int64
-MXOffsetToMemberSegment(MultiXactOffset offset)
-{
-	return MXOffsetToMemberPage(offset) / SLRU_PAGES_PER_SEGMENT;
-}
-
-/* Location (byte offset within page) of flag word for a given member */
-static inline int
-MXOffsetToFlagsOffset(MultiXactOffset offset)
-{
-	MultiXactOffset group = offset / MULTIXACT_MEMBERS_PER_MEMBERGROUP;
-	int			grouponpg = group % MULTIXACT_MEMBERGROUPS_PER_PAGE;
-	int			byteoff = grouponpg * MULTIXACT_MEMBERGROUP_SIZE;
-
-	return byteoff;
-}
-
-static inline int
-MXOffsetToFlagsBitShift(MultiXactOffset offset)
-{
-	int			member_in_group = offset % MULTIXACT_MEMBERS_PER_MEMBERGROUP;
-	int			bshift = member_in_group * MXACT_MEMBER_BITS_PER_XACT;
-
-	return bshift;
-}
-
-/* Location (byte offset within page) of TransactionId of given member */
-static inline int
-MXOffsetToMemberOffset(MultiXactOffset offset)
-{
-	int			member_in_group = offset % MULTIXACT_MEMBERS_PER_MEMBERGROUP;
-
-	return MXOffsetToFlagsOffset(offset) +
-		MULTIXACT_FLAGBYTES_PER_GROUP +
-		member_in_group * sizeof(TransactionId);
-}
-
-/* Multixact members wraparound thresholds. */
-#define MULTIXACT_MEMBER_SAFE_THRESHOLD		(MaxMultiXactOffset / 2)
-#define MULTIXACT_MEMBER_DANGER_THRESHOLD	\
-	(MaxMultiXactOffset - MaxMultiXactOffset / 4)
+#define MULTIXACT_MEMBER_AUTOVAC_THRESHOLD		UINT64CONST(0xFFFFFFFF)
 
 static inline MultiXactId
 PreviousMultiXactId(MultiXactId multi)
@@ -260,11 +145,9 @@ typedef struct MultiXactStateData
 
 	/*
 	 * Oldest multixact offset that is potentially referenced by a multixact
-	 * referenced by a relation.  We don't always know this value, so there's
-	 * a flag here to indicate whether or not we currently do.
+	 * referenced by a relation.
 	 */
 	MultiXactOffset oldestOffset;
-	bool		oldestOffsetKnown;
 
 	/* support for anti-wraparound measures */
 	MultiXactId multiVacLimit;
@@ -272,9 +155,6 @@ 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.
@@ -409,10 +289,8 @@ 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 MultiXactOffset find_multixact_start(MultiXactId multi);
 static void WriteMZeroPageXlogRec(int64 pageno, uint8 info);
 static void WriteMTruncateXlogRec(Oid oldestMultiDB,
 								  MultiXactId startTruncOff,
@@ -1054,9 +932,7 @@ GetNewMultiXactId(int nmembers, MultiXactOffset *offset)
 	 * against catastrophic data loss due to multixact wraparound.  The basic
 	 * rules are:
 	 *
-	 * If we're past multiVacLimit or the safe threshold for member storage
-	 * space, or we don't know what the safe threshold for member storage is,
-	 * start trying to force autovacuum cycles.
+	 * If we're past multiVacLimit, start trying to force autovacuum cycles.
 	 * If we're past multiWarnLimit, start issuing warnings.
 	 * If we're past multiStopLimit, refuse to create new MultiXactIds.
 	 *
@@ -1151,90 +1027,10 @@ GetNewMultiXactId(int nmembers, MultiXactOffset *offset)
 	ExtendMultiXactOffset(result);
 
 	/*
-	 * Reserve the members space, similarly to above.  Also, be careful not to
-	 * return zero as the starting offset for any multixact. See
-	 * GetMultiXactIdMembers() for motivation.
+	 * Reserve the members space, similarly to above.
 	 */
 	nextOffset = MultiXactState->nextOffset;
-	if (nextOffset == 0)
-	{
-		*offset = 1;
-		nmembers++;				/* allocate member slot 0 too */
-	}
-	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.")));
+	*offset = nextOffset;
 
 	ExtendMultiXactMember(nextOffset, nmembers);
 
@@ -2620,22 +2416,9 @@ ExtendMultiXactMember(MultiXactOffset offset, int nmembers)
 		}
 
 		/*
-		 * Compute the number of items till end of current page.  Careful: if
-		 * addition of unsigned ints wraps around, we're at the last page of
-		 * the last segment; since that page holds a different number of items
-		 * than other pages, we need to do it differently.
+		 * Compute the number of items till end of current page.
 		 */
-		if (offset + MAX_MEMBERS_IN_LAST_MEMBERS_PAGE < offset)
-		{
-			/*
-			 * This is the last page of the last segment; we can compute the
-			 * number of items left to allocate in it without modulo
-			 * arithmetic.
-			 */
-			difference = MaxMultiXactOffset - offset + 1;
-		}
-		else
-			difference = MULTIXACT_MEMBERS_PER_PAGE - offset % MULTIXACT_MEMBERS_PER_PAGE;
+		difference = MULTIXACT_MEMBERS_PER_PAGE - offset % MULTIXACT_MEMBERS_PER_PAGE;
 
 		/*
 		 * Advance to next page, taking care to properly handle the wraparound
@@ -2701,15 +2484,13 @@ 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)
@@ -2717,12 +2498,7 @@ SetOffsetVacuumLimit(bool is_startup)
 	MultiXactId oldestMultiXactId;
 	MultiXactId nextMXact;
 	MultiXactOffset oldestOffset = 0;	/* placate compiler */
-	MultiXactOffset prevOldestOffset;
 	MultiXactOffset nextOffset;
-	bool		oldestOffsetKnown = false;
-	bool		prevOldestOffsetKnown;
-	MultiXactOffset offsetStopLimit = 0;
-	MultiXactOffset prevOffsetStopLimit;
 
 	/*
 	 * NB: Have to prevent concurrent truncation, we might otherwise try to
@@ -2735,9 +2511,6 @@ SetOffsetVacuumLimit(bool is_startup)
 	oldestMultiXactId = MultiXactState->oldestMultiXactId;
 	nextMXact = MultiXactState->nextMXact;
 	nextOffset = MultiXactState->nextOffset;
-	prevOldestOffsetKnown = MultiXactState->oldestOffsetKnown;
-	prevOldestOffset = MultiXactState->oldestOffset;
-	prevOffsetStopLimit = MultiXactState->offsetStopLimit;
 	Assert(MultiXactState->finishedStartup);
 	LWLockRelease(MultiXactGenLock);
 
@@ -2755,139 +2528,31 @@ SetOffsetVacuumLimit(bool is_startup)
 		 * offset.
 		 */
 		oldestOffset = nextOffset;
-		oldestOffsetKnown = true;
 	}
 	else
-	{
-		/*
-		 * Figure out where the oldest existing multixact's offsets are
-		 * stored. Due to bugs in early release of PostgreSQL 9.3.X and 9.4.X,
-		 * the supposedly-earliest multixact might not really exist.  We are
-		 * careful not to fail in that case.
-		 */
-		oldestOffsetKnown =
-			find_multixact_start(oldestMultiXactId, &oldestOffset);
-
-		if (oldestOffsetKnown)
-			ereport(DEBUG1,
-					(errmsg_internal("oldest MultiXactId member is at offset %u",
-									 oldestOffset)));
-		else
-			ereport(LOG,
-					(errmsg("MultiXact member wraparound protections are disabled because oldest checkpointed MultiXact %u does not exist on disk",
-							oldestMultiXactId)));
-	}
+		oldestOffset = find_multixact_start(oldestMultiXactId);
 
 	LWLockRelease(MultiXactTruncationLock);
 
-	/*
-	 * If we can, compute limits (and install them MultiXactState) to prevent
-	 * 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 we failed to get the oldest offset this time, but we have a
-		 * value from a previous pass through this function, use the old
-		 * values rather than automatically forcing an emergency autovacuum
-		 * cycle again.
-		 */
-		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.
-	 */
-	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
-	 *-----------------------------------------------------------------------
+	 * Do we need autovacuum?
 	 */
-	if (start < boundary)
-		return finish >= boundary || finish < start;
-	else
-		return finish >= boundary && finish < start;
+	return (nextOffset - oldestOffset > MULTIXACT_MEMBER_AUTOVAC_THRESHOLD);
 }
 
 /*
  * Find the starting offset of the given MultiXactId.
  *
- * Returns false if the file containing the multi does not exist on disk.
- * Otherwise, returns true and sets *result to the starting member offset.
- *
  * This function does not prevent concurrent truncation, so if that's
  * required, the caller has to protect against that.
  */
-static bool
-find_multixact_start(MultiXactId multi, MultiXactOffset *result)
+static MultiXactOffset
+find_multixact_start(MultiXactId multi)
 {
 	MultiXactOffset offset;
 	int64		pageno;
@@ -2900,15 +2565,6 @@ find_multixact_start(MultiXactId multi, MultiXactOffset *result)
 	pageno = MultiXactIdToOffsetPage(multi);
 	entryno = MultiXactIdToOffsetEntry(multi);
 
-	/*
-	 * Write out dirty data, so PhysicalPageExists can work correctly.
-	 */
-	SimpleLruWriteAll(MultiXactOffsetCtl, true);
-	SimpleLruWriteAll(MultiXactMemberCtl, true);
-
-	if (!SimpleLruDoesPhysicalPageExist(MultiXactOffsetCtl, pageno))
-		return false;
-
 	/* lock is acquired by SimpleLruReadPage_ReadOnly */
 	slotno = SimpleLruReadPage_ReadOnly(MultiXactOffsetCtl, pageno, multi);
 	offptr = (MultiXactOffset *) MultiXactOffsetCtl->shared->page_buffer[slotno];
@@ -2916,102 +2572,7 @@ find_multixact_start(MultiXactId multi, MultiXactOffset *result)
 	offset = *offptr;
 	LWLockRelease(SimpleLruGetBankLock(MultiXactOffsetCtl, pageno));
 
-	*result = offset;
-	return true;
-}
-
-/*
- * Determine how many multixacts, and how many multixact members, currently
- * exist.  Return false if unable to determine.
- */
-static bool
-ReadMultiXactCounts(uint32 *multixacts, MultiXactOffset *members)
-{
-	MultiXactOffset nextOffset;
-	MultiXactOffset oldestOffset;
-	MultiXactId oldestMultiXactId;
-	MultiXactId nextMultiXactId;
-	bool		oldestOffsetKnown;
-
-	LWLockAcquire(MultiXactGenLock, LW_SHARED);
-	nextOffset = MultiXactState->nextOffset;
-	oldestMultiXactId = MultiXactState->oldestMultiXactId;
-	nextMultiXactId = MultiXactState->nextMXact;
-	oldestOffset = MultiXactState->oldestOffset;
-	oldestOffsetKnown = MultiXactState->oldestOffsetKnown;
-	LWLockRelease(MultiXactGenLock);
-
-	if (!oldestOffsetKnown)
-		return false;
-
-	*members = nextOffset - oldestOffset;
-	*multixacts = nextMultiXactId - oldestMultiXactId;
-	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;
-
-	/* If we can't determine member space utilization, assume the worst. */
-	if (!ReadMultiXactCounts(&multixacts, &members))
-		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);
+	return offset;
 }
 
 typedef struct mxtruncinfo
@@ -3039,37 +2600,13 @@ SlruScanDirCbFindEarliest(SlruCtl ctl, char *filename, int64 segpage, void *data
 
 
 /*
- * Delete members segments [oldest, newOldest)
- *
- * The members SLRU can, in contrast to the offsets one, be filled to almost
- * the full range at once. This means SimpleLruTruncate() can't trivially be
- * used - instead the to-be-deleted range is computed using the offsets
- * SLRU. C.f. TruncateMultiXact().
+ * Delete members segments before the newOldestOffset.
  */
 static void
-PerformMembersTruncation(MultiXactOffset oldestOffset, MultiXactOffset newOldestOffset)
+PerformMembersTruncation(MultiXactOffset newOldestOffset)
 {
-	const int64 maxsegment = MXOffsetToMemberSegment(MaxMultiXactOffset);
-	int64		startsegment = MXOffsetToMemberSegment(oldestOffset);
-	int64		endsegment = MXOffsetToMemberSegment(newOldestOffset);
-	int64		segment = startsegment;
-
-	/*
-	 * Delete all the segments but the last one. The last segment can still
-	 * contain, possibly partially, valid data.
-	 */
-	while (segment != endsegment)
-	{
-		elog(DEBUG2, "truncating multixact members segment %llx",
-			 (unsigned long long) segment);
-		SlruDeleteSegment(MultiXactMemberCtl, segment);
-
-		/* move to next segment, handling wraparound correctly */
-		if (segment == maxsegment)
-			segment = 0;
-		else
-			segment += 1;
-	}
+	SimpleLruTruncate(MultiXactMemberCtl,
+					  MXOffsetToMemberPage(newOldestOffset));
 }
 
 /*
@@ -3174,23 +2711,15 @@ TruncateMultiXact(MultiXactId newOldestMulti, Oid newOldestMultiDB)
 	/*
 	 * First, compute the safe truncation point for MultiXactMember. This is
 	 * the starting offset of the oldest multixact.
-	 *
-	 * Hopefully, find_multixact_start will always work here, because we've
-	 * already checked that it doesn't precede the earliest MultiXact on disk.
-	 * But if it fails, don't truncate anything, and log a message.
 	 */
 	if (oldestMulti == nextMulti)
 	{
 		/* there are NO MultiXacts */
 		oldestOffset = nextOffset;
 	}
-	else if (!find_multixact_start(oldestMulti, &oldestOffset))
+	else
 	{
-		ereport(LOG,
-				(errmsg("oldest MultiXact %u not found, earliest MultiXact %u, skipping truncation",
-						oldestMulti, earliest)));
-		LWLockRelease(MultiXactTruncationLock);
-		return;
+		oldestOffset = find_multixact_start(oldestMulti);
 	}
 
 	/*
@@ -3202,13 +2731,9 @@ TruncateMultiXact(MultiXactId newOldestMulti, Oid newOldestMultiDB)
 		/* there are NO MultiXacts */
 		newOldestOffset = nextOffset;
 	}
-	else if (!find_multixact_start(newOldestMulti, &newOldestOffset))
+	else
 	{
-		ereport(LOG,
-				(errmsg("cannot truncate up to MultiXact %u because it does not exist on disk, skipping truncation",
-						newOldestMulti)));
-		LWLockRelease(MultiXactTruncationLock);
-		return;
+		newOldestOffset = find_multixact_start(newOldestMulti);
 	}
 
 	elog(DEBUG1, "performing multixact truncation: "
@@ -3258,7 +2783,7 @@ TruncateMultiXact(MultiXactId newOldestMulti, Oid newOldestMultiDB)
 	LWLockRelease(MultiXactGenLock);
 
 	/* First truncate members */
-	PerformMembersTruncation(oldestOffset, newOldestOffset);
+	PerformMembersTruncation(newOldestOffset);
 
 	/* Then offsets */
 	PerformOffsetsTruncation(oldestMulti, newOldestMulti);
@@ -3345,7 +2870,7 @@ 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);
 }
@@ -3492,7 +3017,7 @@ multixact_redo(XLogReaderState *record)
 		 */
 		SetMultiXactIdLimit(xlrec.endTruncOff, xlrec.oldestMultiDB, false);
 
-		PerformMembersTruncation(xlrec.startTruncMemb, xlrec.endTruncMemb);
+		PerformMembersTruncation(xlrec.endTruncMemb);
 
 		/*
 		 * During XLOG replay, latest_page_number isn't necessarily set up
diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index bf3dbda901..a813a090fa 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -5083,7 +5083,7 @@ BootStrapXLOG(uint32 data_checksum_version)
 		FullTransactionIdFromEpochAndXid(0, FirstNormalTransactionId);
 	checkPoint.nextOid = FirstGenbkiObjectId;
 	checkPoint.nextMulti = FirstMultiXactId;
-	checkPoint.nextMultiOffset = 0;
+	checkPoint.nextMultiOffset = 1;
 	checkPoint.oldestXid = FirstNormalTransactionId;
 	checkPoint.oldestXidDB = Template1DbOid;
 	checkPoint.oldestMulti = FirstMultiXactId;
diff --git a/src/backend/commands/vacuum.c b/src/backend/commands/vacuum.c
index e6745e6145..c96fbf004d 100644
--- a/src/backend/commands/vacuum.c
+++ b/src/backend/commands/vacuum.c
@@ -1134,7 +1134,7 @@ 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 0ab921a169..ed5fc09c38 100644
--- a/src/backend/postmaster/autovacuum.c
+++ b/src/backend/postmaster/autovacuum.c
@@ -1134,7 +1134,7 @@ 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;
 
@@ -1922,7 +1922,7 @@ 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_resetwal/pg_resetwal.c b/src/bin/pg_resetwal/pg_resetwal.c
index fff401e469..4ad64cf1ed 100644
--- a/src/bin/pg_resetwal/pg_resetwal.c
+++ b/src/bin/pg_resetwal/pg_resetwal.c
@@ -264,7 +264,7 @@ 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");
diff --git a/src/bin/pg_resetwal/t/001_basic.pl b/src/bin/pg_resetwal/t/001_basic.pl
index d0bd1f7ace..79d03d79de 100644
--- a/src/bin/pg_resetwal/t/001_basic.pl
+++ b/src/bin/pg_resetwal/t/001_basic.pl
@@ -206,7 +206,7 @@ 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;
 # -m argument is "new,old"
 push @cmd, '-m',
   sprintf("%d,%d",
diff --git a/src/include/access/multixact.h b/src/include/access/multixact.h
index 4e6b0eec2f..5ee632dfe6 100644
--- a/src/include/access/multixact.h
+++ b/src/include/access/multixact.h
@@ -27,7 +27,7 @@
 
 #define MultiXactIdIsValid(multi) ((multi) != InvalidMultiXactId)
 
-#define MaxMultiXactOffset	((MultiXactOffset) 0xFFFFFFFF)
+#define MaxMultiXactOffset	UINT64CONST(0xFFFFFFFFFFFFFFFF)
 
 /*
  * Possible multixact lock modes ("status").  The first four modes are for
@@ -143,7 +143,6 @@ 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(TransactionId xid, uint16 info,
 									   void *recdata, uint32 len);
diff --git a/src/include/access/multixact_internal.h b/src/include/access/multixact_internal.h
new file mode 100644
index 0000000000..39e74a21c7
--- /dev/null
+++ b/src/include/access/multixact_internal.h
@@ -0,0 +1,115 @@
+/*
+ * multixact_internal.h
+ *
+ * Internal definitions for the on-disk format of multixact manager.
+ *
+ * Portions Copyright (c) 1996-2024, PostgreSQL Global Development Group
+ * Portions Copyright (c) 1994, Regents of the University of California
+ *
+ * src/include/access/multixact_internal.h
+ */
+#ifndef MULTIXACT_INTERNAL_H
+#define MULTIXACT_INTERNAL_H
+
+/* FIXME: had to duplicate this */
+#define SLRU_PAGES_PER_SEGMENT	32
+
+/*
+ * Defines for MultiXactOffset page sizes.  A page is the same BLCKSZ as is
+ * used everywhere else in Postgres.
+ */
+
+/* We need four bytes per offset */
+#define MULTIXACT_OFFSETS_PER_PAGE (BLCKSZ / sizeof(MultiXactOffset))
+
+static inline int64
+MultiXactIdToOffsetPage(MultiXactId multi)
+{
+	return multi / MULTIXACT_OFFSETS_PER_PAGE;
+}
+
+static inline int
+MultiXactIdToOffsetEntry(MultiXactId multi)
+{
+	return multi % MULTIXACT_OFFSETS_PER_PAGE;
+}
+
+static inline int64
+MultiXactIdToOffsetSegment(MultiXactId multi)
+{
+	return MultiXactIdToOffsetPage(multi) / SLRU_PAGES_PER_SEGMENT;
+}
+
+/*
+ * The situation for members is a bit more complex: we store one byte of
+ * additional flag bits for each TransactionId.  To do this without getting
+ * into alignment issues, we store four bytes of flags, and then the
+ * corresponding 4 Xids.  Each such 5-word (20-byte) set we call a "group", and
+ * are stored as a whole in pages.  Thus, with 8kB BLCKSZ, we keep 409 groups
+ * per page.  This wastes 12 bytes per page, but that's OK -- simplicity (and
+ * performance) trumps space efficiency here.
+ *
+ * Note that the "offset" macros work with byte offset, not array indexes, so
+ * arithmetic must be done using "char *" pointers.
+ */
+/* We need eight bits per xact, so one xact fits in a byte */
+#define MXACT_MEMBER_BITS_PER_XACT			8
+#define MXACT_MEMBER_FLAGS_PER_BYTE			1
+#define MXACT_MEMBER_XACT_BITMASK	((1 << MXACT_MEMBER_BITS_PER_XACT) - 1)
+
+/* how many full bytes of flags are there in a group? */
+#define MULTIXACT_FLAGBYTES_PER_GROUP		4
+#define MULTIXACT_MEMBERS_PER_MEMBERGROUP	\
+	(MULTIXACT_FLAGBYTES_PER_GROUP * MXACT_MEMBER_FLAGS_PER_BYTE)
+/* size in bytes of a complete group */
+#define MULTIXACT_MEMBERGROUP_SIZE \
+	(sizeof(TransactionId) * MULTIXACT_MEMBERS_PER_MEMBERGROUP + MULTIXACT_FLAGBYTES_PER_GROUP)
+#define MULTIXACT_MEMBERGROUPS_PER_PAGE (BLCKSZ / MULTIXACT_MEMBERGROUP_SIZE)
+#define MULTIXACT_MEMBERS_PER_PAGE	\
+	(MULTIXACT_MEMBERGROUPS_PER_PAGE * MULTIXACT_MEMBERS_PER_MEMBERGROUP)
+
+/* page in which a member is to be found */
+static inline int64
+MXOffsetToMemberPage(MultiXactOffset offset)
+{
+	return offset / MULTIXACT_MEMBERS_PER_PAGE;
+}
+
+static inline int64
+MXOffsetToMemberSegment(MultiXactOffset offset)
+{
+	return MXOffsetToMemberPage(offset) / SLRU_PAGES_PER_SEGMENT;
+}
+
+/* Location (byte offset within page) of flag word for a given member */
+static inline int
+MXOffsetToFlagsOffset(MultiXactOffset offset)
+{
+	MultiXactOffset group = offset / MULTIXACT_MEMBERS_PER_MEMBERGROUP;
+	int			grouponpg = group % MULTIXACT_MEMBERGROUPS_PER_PAGE;
+	int			byteoff = grouponpg * MULTIXACT_MEMBERGROUP_SIZE;
+
+	return byteoff;
+}
+
+static inline int
+MXOffsetToFlagsBitShift(MultiXactOffset offset)
+{
+	int			member_in_group = offset % MULTIXACT_MEMBERS_PER_MEMBERGROUP;
+	int			bshift = member_in_group * MXACT_MEMBER_BITS_PER_XACT;
+
+	return bshift;
+}
+
+/* Location (byte offset within page) of TransactionId of given member */
+static inline int
+MXOffsetToMemberOffset(MultiXactOffset offset)
+{
+	int			member_in_group = offset % MULTIXACT_MEMBERS_PER_MEMBERGROUP;
+
+	return MXOffsetToFlagsOffset(offset) +
+		MULTIXACT_FLAGBYTES_PER_GROUP +
+		member_in_group * sizeof(TransactionId);
+}
+
+#endif							/* MULTIXACT_INTERNAL_H */
diff --git a/src/include/c.h b/src/include/c.h
index a14c631516..318194f78d 100644
--- a/src/include/c.h
+++ b/src/include/c.h
@@ -618,7 +618,7 @@ 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