Track latest completed xid as a FullTransactionId.

The reason for doing so is that a subsequent commit will need that to
avoid wraparound issues. As the subsequent change is large this was
split out for easier review.

The reason this is not a perfect straight-forward change is that we do
not want track 64bit xids in the procarray or the WAL. Therefore we
need to advance lastestCompletedXid in relation to 32 bit xids. The
code for that is now centralized in MaintainLatestCompletedXid*.

Author: Andres Freund
Reviewed-By: Thomas Munro, Robert Haas, David Rowley
Discussion: https://postgr.es/m/20200301083601.ews6hz5dduc3w2se@alap3.anarazel.de

Author: anarazel

src/backend/access/transam/varsup.c

@@ -569,3 +569,53 @@ GetNewObjectId(void)
 
 	return result;
 }
+
+
+#ifdef USE_ASSERT_CHECKING
+
+/*
+ * Assert that xid is between [oldestXid, nextXid], which is the range we
+ * expect XIDs coming from tables etc to be in.
+ *
+ * As ShmemVariableCache->oldestXid could change just after this call without
+ * further precautions, and as a wrapped-around xid could again fall within
+ * the valid range, this assertion can only detect if something is definitely
+ * wrong, but not establish correctness.
+ *
+ * This intentionally does not expose a return value, to avoid code being
+ * introduced that depends on the return value.
+ */
+void
+AssertTransactionIdInAllowableRange(TransactionId xid)
+{
+	TransactionId oldest_xid;
+	TransactionId next_xid;
+
+	Assert(TransactionIdIsValid(xid));
+
+	/* we may see bootstrap / frozen */
+	if (!TransactionIdIsNormal(xid))
+		return;
+
+	/*
+	 * We can't acquire XidGenLock, as this may be called with XidGenLock
+	 * already held (or with other locks that don't allow XidGenLock to be
+	 * nested). That's ok for our purposes though, since we already rely on
+	 * 32bit reads to be atomic. While nextXid is 64 bit, we only look at
+	 * the lower 32bit, so a skewed read doesn't hurt.
+	 *
+	 * There's no increased danger of falling outside [oldest, next] by
+	 * accessing them without a lock. xid needs to have been created with
+	 * GetNewTransactionId() in the originating session, and the locks there
+	 * pair with the memory barrier below.  We do however accept xid to be <=
+	 * to next_xid, instead of just <, as xid could be from the procarray,
+	 * before we see the updated nextXid value.
+	 */
+	pg_memory_barrier();
+	oldest_xid = ShmemVariableCache->oldestXid;
+	next_xid = XidFromFullTransactionId(ShmemVariableCache->nextXid);
+
+	Assert(TransactionIdFollowsOrEquals(xid, oldest_xid) ||
+		   TransactionIdPrecedesOrEquals(xid, next_xid));
+}
+#endif

src/backend/access/transam/xlog.c

@@ -7865,8 +7865,8 @@ StartupXLOG(void)
 
 	/* also initialize latestCompletedXid, to nextXid - 1 */
 	LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE);
-	ShmemVariableCache->latestCompletedXid = XidFromFullTransactionId(ShmemVariableCache->nextXid);
-	TransactionIdRetreat(ShmemVariableCache->latestCompletedXid);
+	ShmemVariableCache->latestCompletedXid = ShmemVariableCache->nextXid;
+	FullTransactionIdRetreat(&ShmemVariableCache->latestCompletedXid);
 	LWLockRelease(ProcArrayLock);
 
 	/*

src/backend/storage/ipc/procarray.c

@@ -175,6 +175,11 @@ static void KnownAssignedXidsReset(void);
 static inline void ProcArrayEndTransactionInternal(PGPROC *proc,
 												   PGXACT *pgxact, TransactionId latestXid);
 static void ProcArrayGroupClearXid(PGPROC *proc, TransactionId latestXid);
+static void MaintainLatestCompletedXid(TransactionId latestXid);
+static void MaintainLatestCompletedXidRecovery(TransactionId latestXid);
+
+static inline FullTransactionId FullXidRelativeTo(FullTransactionId rel,
+												  TransactionId xid);
 
 /*
  * Report shared-memory space needed by CreateSharedProcArray.
@@ -349,9 +354,7 @@ ProcArrayRemove(PGPROC *proc, TransactionId latestXid)
 		Assert(TransactionIdIsValid(allPgXact[proc->pgprocno].xid));
 
 		/* Advance global latestCompletedXid while holding the lock */
-		if (TransactionIdPrecedes(ShmemVariableCache->latestCompletedXid,
-								  latestXid))
-			ShmemVariableCache->latestCompletedXid = latestXid;
+		MaintainLatestCompletedXid(latestXid);
 	}
 	else
 	{
@@ -464,9 +467,7 @@ ProcArrayEndTransactionInternal(PGPROC *proc, PGXACT *pgxact,
 	pgxact->overflowed = false;
 
 	/* Also advance global latestCompletedXid while holding the lock */
-	if (TransactionIdPrecedes(ShmemVariableCache->latestCompletedXid,
-							  latestXid))
-		ShmemVariableCache->latestCompletedXid = latestXid;
+	MaintainLatestCompletedXid(latestXid);
 }
 
 /*
@@ -621,6 +622,59 @@ ProcArrayClearTransaction(PGPROC *proc)
 	pgxact->overflowed = false;
 }
 
+/*
+ * Update ShmemVariableCache->latestCompletedXid to point to latestXid if
+ * currently older.
+ */
+static void
+MaintainLatestCompletedXid(TransactionId latestXid)
+{
+	FullTransactionId cur_latest = ShmemVariableCache->latestCompletedXid;
+
+	Assert(FullTransactionIdIsValid(cur_latest));
+	Assert(!RecoveryInProgress());
+	Assert(LWLockHeldByMe(ProcArrayLock));
+
+	if (TransactionIdPrecedes(XidFromFullTransactionId(cur_latest), latestXid))
+	{
+		ShmemVariableCache->latestCompletedXid =
+			FullXidRelativeTo(cur_latest, latestXid);
+	}
+
+	Assert(IsBootstrapProcessingMode() ||
+		   FullTransactionIdIsNormal(ShmemVariableCache->latestCompletedXid));
+}
+
+/*
+ * Same as MaintainLatestCompletedXid, except for use during WAL replay.
+ */
+static void
+MaintainLatestCompletedXidRecovery(TransactionId latestXid)
+{
+	FullTransactionId cur_latest = ShmemVariableCache->latestCompletedXid;
+	FullTransactionId rel;
+
+	Assert(AmStartupProcess() || !IsUnderPostmaster);
+	Assert(LWLockHeldByMe(ProcArrayLock));
+
+	/*
+	 * Need a FullTransactionId to compare latestXid with. Can't rely on
+	 * latestCompletedXid to be initialized in recovery. But in recovery it's
+	 * safe to access nextXid without a lock for the startup process.
+	 */
+	rel = ShmemVariableCache->nextXid;
+	Assert(FullTransactionIdIsValid(ShmemVariableCache->nextXid));
+
+	if (!FullTransactionIdIsValid(cur_latest) ||
+		TransactionIdPrecedes(XidFromFullTransactionId(cur_latest), latestXid))
+	{
+		ShmemVariableCache->latestCompletedXid =
+			FullXidRelativeTo(rel, latestXid);
+	}
+
+	Assert(FullTransactionIdIsNormal(ShmemVariableCache->latestCompletedXid));
+}
+
 /*
  * ProcArrayInitRecovery -- initialize recovery xid mgmt environment
  *
@@ -869,12 +923,9 @@ ProcArrayApplyRecoveryInfo(RunningTransactions running)
 	 * If a transaction wrote a commit record in the gap between taking and
 	 * logging the snapshot then latestCompletedXid may already be higher than
 	 * the value from the snapshot, so check before we use the incoming value.
+	 * It also might not yet be set at all.
 	 */
-	if (TransactionIdPrecedes(ShmemVariableCache->latestCompletedXid,
-							  running->latestCompletedXid))
-		ShmemVariableCache->latestCompletedXid = running->latestCompletedXid;
-
-	Assert(TransactionIdIsNormal(ShmemVariableCache->latestCompletedXid));
+	MaintainLatestCompletedXidRecovery(running->latestCompletedXid);
 
 	LWLockRelease(ProcArrayLock);
 
@@ -989,6 +1040,7 @@ TransactionIdIsInProgress(TransactionId xid)
 	int			nxids = 0;
 	ProcArrayStruct *arrayP = procArray;
 	TransactionId topxid;
+	TransactionId latestCompletedXid;
 	int			i,
 				j;
 
@@ -1051,7 +1103,9 @@ TransactionIdIsInProgress(TransactionId xid)
 	 * Now that we have the lock, we can check latestCompletedXid; if the
 	 * target Xid is after that, it's surely still running.
 	 */
-	if (TransactionIdPrecedes(ShmemVariableCache->latestCompletedXid, xid))
+	latestCompletedXid =
+		XidFromFullTransactionId(ShmemVariableCache->latestCompletedXid);
+	if (TransactionIdPrecedes(latestCompletedXid, xid))
 	{
 		LWLockRelease(ProcArrayLock);
 		xc_by_latest_xid_inc();
@@ -1330,9 +1384,9 @@ GetOldestXmin(Relation rel, int flags)
 	 * and so protects us against overestimating the result due to future
 	 * additions.
 	 */
-	result = ShmemVariableCache->latestCompletedXid;
-	Assert(TransactionIdIsNormal(result));
+	result = XidFromFullTransactionId(ShmemVariableCache->latestCompletedXid);
 	TransactionIdAdvance(result);
+	Assert(TransactionIdIsNormal(result));
 
 	for (index = 0; index < arrayP->numProcs; index++)
 	{
@@ -1511,6 +1565,7 @@ GetSnapshotData(Snapshot snapshot)
 	int			count = 0;
 	int			subcount = 0;
 	bool		suboverflowed = false;
+	FullTransactionId latest_completed;
 	TransactionId replication_slot_xmin = InvalidTransactionId;
 	TransactionId replication_slot_catalog_xmin = InvalidTransactionId;
 
@@ -1554,10 +1609,11 @@ GetSnapshotData(Snapshot snapshot)
 	 */
 	LWLockAcquire(ProcArrayLock, LW_SHARED);
 
+	latest_completed = ShmemVariableCache->latestCompletedXid;
 	/* xmax is always latestCompletedXid + 1 */
-	xmax = ShmemVariableCache->latestCompletedXid;
-	Assert(TransactionIdIsNormal(xmax));
+	xmax = XidFromFullTransactionId(latest_completed);
 	TransactionIdAdvance(xmax);
+	Assert(TransactionIdIsNormal(xmax));
 
 	/* initialize xmin calculation with xmax */
 	globalxmin = xmin = xmax;
@@ -1984,9 +2040,10 @@ GetRunningTransactionData(void)
 	LWLockAcquire(ProcArrayLock, LW_SHARED);
 	LWLockAcquire(XidGenLock, LW_SHARED);
 
-	latestCompletedXid = ShmemVariableCache->latestCompletedXid;
-
-	oldestRunningXid = XidFromFullTransactionId(ShmemVariableCache->nextXid);
+	latestCompletedXid =
+		XidFromFullTransactionId(ShmemVariableCache->latestCompletedXid);
+	oldestRunningXid =
+		XidFromFullTransactionId(ShmemVariableCache->nextXid);
 
 	/*
 	 * Spin over procArray collecting all xids
@@ -3207,9 +3264,7 @@ XidCacheRemoveRunningXids(TransactionId xid,
 		elog(WARNING, "did not find subXID %u in MyProc", xid);
 
 	/* Also advance global latestCompletedXid while holding the lock */
-	if (TransactionIdPrecedes(ShmemVariableCache->latestCompletedXid,
-							  latestXid))
-		ShmemVariableCache->latestCompletedXid = latestXid;
+	MaintainLatestCompletedXid(latestXid);
 
 	LWLockRelease(ProcArrayLock);
 }
@@ -3236,6 +3291,32 @@ DisplayXidCache(void)
 }
 #endif							/* XIDCACHE_DEBUG */
 
+/*
+ * Convert a 32 bit transaction id into 64 bit transaction id, by assuming it
+ * is within MaxTransactionId / 2 of XidFromFullTransactionId(rel).
+ *
+ * Be very careful about when to use this function. It can only safely be used
+ * when there is a guarantee that xid is within MaxTransactionId / 2 xids of
+ * rel. That e.g. can be guaranteed if the the caller assures a snapshot is
+ * held by the backend and xid is from a table (where vacuum/freezing ensures
+ * the xid has to be within that range), or if xid is from the procarray and
+ * prevents xid wraparound that way.
+ */
+static inline FullTransactionId
+FullXidRelativeTo(FullTransactionId rel, TransactionId xid)
+{
+	TransactionId rel_xid = XidFromFullTransactionId(rel);
+
+	Assert(TransactionIdIsValid(xid));
+	Assert(TransactionIdIsValid(rel_xid));
+
+	/* not guaranteed to find issues, but likely to catch mistakes */
+	AssertTransactionIdInAllowableRange(xid);
+
+	return FullTransactionIdFromU64(U64FromFullTransactionId(rel)
+									+ (int32) (xid - rel_xid));
+}
+
 
 /* ----------------------------------------------
  *		KnownAssignedTransactionIds sub-module
@@ -3388,9 +3469,7 @@ ExpireTreeKnownAssignedTransactionIds(TransactionId xid, int nsubxids,
 	KnownAssignedXidsRemoveTree(xid, nsubxids, subxids);
 
 	/* As in ProcArrayEndTransaction, advance latestCompletedXid */
-	if (TransactionIdPrecedes(ShmemVariableCache->latestCompletedXid,
-							  max_xid))
-		ShmemVariableCache->latestCompletedXid = max_xid;
+	MaintainLatestCompletedXidRecovery(max_xid);
 
 	LWLockRelease(ProcArrayLock);
 }

src/include/access/transam.h

@@ -54,6 +54,8 @@
 #define FullTransactionIdFollowsOrEquals(a, b) ((a).value >= (b).value)
 #define FullTransactionIdIsValid(x)		TransactionIdIsValid(XidFromFullTransactionId(x))
 #define InvalidFullTransactionId		FullTransactionIdFromEpochAndXid(0, InvalidTransactionId)
+#define FirstNormalFullTransactionId	FullTransactionIdFromEpochAndXid(0, FirstNormalTransactionId)
+#define FullTransactionIdIsNormal(x)	FullTransactionIdFollowsOrEquals(x, FirstNormalFullTransactionId)
 
 /*
  * A 64 bit value that contains an epoch and a TransactionId.  This is
@@ -102,6 +104,31 @@ FullTransactionIdAdvance(FullTransactionId *dest)
 		dest->value++;
 }
 
+/*
+ * Retreat a FullTransactionId variable, stepping over xids that would appear
+ * to be special only when viewed as 32bit XIDs.
+ */
+static inline void
+FullTransactionIdRetreat(FullTransactionId *dest)
+{
+	dest->value--;
+
+	/*
+	 * In contrast to 32bit XIDs don't step over the "actual" special xids.
+	 * For 64bit xids these can't be reached as part of a wraparound as they
+	 * can in the 32bit case.
+	 */
+	if (FullTransactionIdPrecedes(*dest, FirstNormalFullTransactionId))
+		return;
+
+	/*
+	 * But we do need to step over XIDs that'd appear special only for 32bit
+	 * XIDs.
+	 */
+	while (XidFromFullTransactionId(*dest) < FirstNormalTransactionId)
+		dest->value--;
+}
+
 /* back up a transaction ID variable, handling wraparound correctly */
 #define TransactionIdRetreat(dest)	\
 	do { \
@@ -193,8 +220,8 @@ typedef struct VariableCacheData
 	/*
 	 * These fields are protected by ProcArrayLock.
 	 */
-	TransactionId latestCompletedXid;	/* newest XID that has committed or
-										 * aborted */
+	FullTransactionId latestCompletedXid;	/* newest full XID that has
+											 * committed or aborted */
 
 	/*
 	 * These fields are protected by XactTruncationLock
@@ -244,6 +271,12 @@ extern void AdvanceOldestClogXid(TransactionId oldest_datfrozenxid);
 extern bool ForceTransactionIdLimitUpdate(void);
 extern Oid	GetNewObjectId(void);
 
+#ifdef USE_ASSERT_CHECKING
+extern void AssertTransactionIdInAllowableRange(TransactionId xid);
+#else
+#define AssertTransactionIdInAllowableRange(xid) ((void)true)
+#endif
+
 /*
  * Some frontend programs include this header.  For compilers that emit static
  * inline functions even when they're unused, that leads to unsatisfied