rebased
--
nathan
>From 407a7e91f09b657f048f4af7cff52f1b2f6cc29b Mon Sep 17 00:00:00 2001
From: Nathan Bossart <[email protected]>
Date: Fri, 14 Nov 2025 09:59:15 -0600
Subject: [PATCH v2 1/3] Add percentage of transaction IDs that are available
to wraparound warnings.
---
doc/src/sgml/maintenance.sgml | 1 +
src/backend/access/transam/multixact.c | 8 ++++++++
src/backend/access/transam/varsup.c | 8 ++++++++
3 files changed, 17 insertions(+)
diff --git a/doc/src/sgml/maintenance.sgml b/doc/src/sgml/maintenance.sgml
index 08e6489afb8..c8ba94303f1 100644
--- a/doc/src/sgml/maintenance.sgml
+++ b/doc/src/sgml/maintenance.sgml
@@ -674,6 +674,7 @@ SELECT datname, age(datfrozenxid) FROM pg_database;
<programlisting>
WARNING: database "mydb" must be vacuumed within 39985967 transactions
+DETAIL: Approximately 1.86% of transactions IDs are available for use.
HINT: To avoid XID assignment failures, execute a database-wide VACUUM in
that database.
</programlisting>
diff --git a/src/backend/access/transam/multixact.c
b/src/backend/access/transam/multixact.c
index 8ba2f4529dc..e1ac4bf4c0b 100644
--- a/src/backend/access/transam/multixact.c
+++ b/src/backend/access/transam/multixact.c
@@ -1040,6 +1040,8 @@ GetNewMultiXactId(int nmembers, MultiXactOffset *offset)
multiWrapLimit - result,
oldest_datname,
multiWrapLimit - result),
+ errdetail("Approximately
%.2f%% of MultiXactIds are available for use.",
+ (double)
(multiWrapLimit - result) / PG_INT32_MAX * 100),
errhint("Execute a
database-wide VACUUM in that database.\n"
"You might
also need to commit or roll back old prepared transactions, or drop stale
replication slots.")));
else
@@ -1049,6 +1051,8 @@ GetNewMultiXactId(int nmembers, MultiXactOffset *offset)
multiWrapLimit - result,
oldest_datoid,
multiWrapLimit - result),
+ errdetail("Approximately
%.2f%% of MultiXactIds are available for use.",
+ (double)
(multiWrapLimit - result) / PG_INT32_MAX * 100),
errhint("Execute a
database-wide VACUUM in that database.\n"
"You might
also need to commit or roll back old prepared transactions, or drop stale
replication slots.")));
}
@@ -2166,6 +2170,8 @@ SetMultiXactIdLimit(MultiXactId oldest_datminmxid, Oid
oldest_datoid)
multiWrapLimit - curMulti,
oldest_datname,
multiWrapLimit - curMulti),
+ errdetail("Approximately %.2f%% of
MultiXactIds are available for use.",
+ (double)
(multiWrapLimit - curMulti) / PG_INT32_MAX * 100),
errhint("To avoid MultiXactId
assignment failures, execute a database-wide VACUUM in that database.\n"
"You might also need
to commit or roll back old prepared transactions, or drop stale replication
slots.")));
else
@@ -2175,6 +2181,8 @@ SetMultiXactIdLimit(MultiXactId oldest_datminmxid, Oid
oldest_datoid)
multiWrapLimit - curMulti,
oldest_datoid,
multiWrapLimit - curMulti),
+ errdetail("Approximately %.2f%% of
MultiXactIds are available for use.",
+ (double)
(multiWrapLimit - curMulti) / PG_INT32_MAX * 100),
errhint("To avoid MultiXactId
assignment failures, execute a database-wide VACUUM in that database.\n"
"You might also need
to commit or roll back old prepared transactions, or drop stale replication
slots.")));
}
diff --git a/src/backend/access/transam/varsup.c
b/src/backend/access/transam/varsup.c
index f8c4dada7c9..962396bae10 100644
--- a/src/backend/access/transam/varsup.c
+++ b/src/backend/access/transam/varsup.c
@@ -175,6 +175,8 @@ GetNewTransactionId(bool isSubXact)
(errmsg("database \"%s\" must
be vacuumed within %u transactions",
oldest_datname,
xidWrapLimit -
xid),
+ errdetail("Approximately
%.2f%% of transaction IDs are available for use.",
+ (double)
(xidWrapLimit - xid) / PG_INT32_MAX * 100),
errhint("To avoid transaction
ID assignment failures, execute a database-wide VACUUM in that database.\n"
"You might
also need to commit or roll back old prepared transactions, or drop stale
replication slots.")));
else
@@ -182,6 +184,8 @@ GetNewTransactionId(bool isSubXact)
(errmsg("database with OID %u
must be vacuumed within %u transactions",
oldest_datoid,
xidWrapLimit -
xid),
+ errdetail("Approximately
%.2f%% of transaction IDs are available for use.",
+ (double)
(xidWrapLimit - xid) / PG_INT32_MAX * 100),
errhint("To avoid XID
assignment failures, execute a database-wide VACUUM in that database.\n"
"You might
also need to commit or roll back old prepared transactions, or drop stale
replication slots.")));
}
@@ -490,6 +494,8 @@ SetTransactionIdLimit(TransactionId oldest_datfrozenxid,
Oid oldest_datoid)
(errmsg("database \"%s\" must be
vacuumed within %u transactions",
oldest_datname,
xidWrapLimit - curXid),
+ errdetail("Approximately %.2f%% of
transaction IDs are available for use.",
+ (double)
(xidWrapLimit - curXid) / PG_INT32_MAX * 100),
errhint("To avoid XID assignment
failures, execute a database-wide VACUUM in that database.\n"
"You might also need
to commit or roll back old prepared transactions, or drop stale replication
slots.")));
else
@@ -497,6 +503,8 @@ SetTransactionIdLimit(TransactionId oldest_datfrozenxid,
Oid oldest_datoid)
(errmsg("database with OID %u must be
vacuumed within %u transactions",
oldest_datoid,
xidWrapLimit - curXid),
+ errdetail("Approximately %.2f%% of
transaction IDs are available for use.",
+ (double)
(xidWrapLimit - curXid) / PG_INT32_MAX * 100),
errhint("To avoid XID assignment
failures, execute a database-wide VACUUM in that database.\n"
"You might also need
to commit or roll back old prepared transactions, or drop stale replication
slots.")));
}
--
2.39.5 (Apple Git-154)
>From 0c87a24dba1730cf5a8e3d6d8bee8446863cff07 Mon Sep 17 00:00:00 2001
From: Nathan Bossart <[email protected]>
Date: Fri, 14 Nov 2025 10:28:52 -0600
Subject: [PATCH v2 2/3] Bump transaction ID limit to warn at 100M.
---
doc/src/sgml/maintenance.sgml | 4 ++--
src/backend/access/transam/multixact.c | 6 +++---
src/backend/access/transam/varsup.c | 6 +++---
3 files changed, 8 insertions(+), 8 deletions(-)
diff --git a/doc/src/sgml/maintenance.sgml b/doc/src/sgml/maintenance.sgml
index c8ba94303f1..c23e0a6e260 100644
--- a/doc/src/sgml/maintenance.sgml
+++ b/doc/src/sgml/maintenance.sgml
@@ -670,7 +670,7 @@ SELECT datname, age(datfrozenxid) FROM pg_database;
<para>
If for some reason autovacuum fails to clear old XIDs from a table, the
system will begin to emit warning messages like this when the database's
- oldest XIDs reach forty million transactions from the wraparound point:
+ oldest XIDs reach one hundred million transactions from the wraparound
point:
<programlisting>
WARNING: database "mydb" must be vacuumed within 39985967 transactions
@@ -824,7 +824,7 @@ HINT: Execute a database-wide VACUUM in that database.
<para>
Similar to the XID case, if autovacuum fails to clear old MXIDs from a
table, the
- system will begin to emit warning messages when the database's oldest
MXIDs reach forty
+ system will begin to emit warning messages when the database's oldest
MXIDs reach one hundred
million transactions from the wraparound point. And, just as in the XID
case, if these
warnings are ignored, the system will refuse to generate new MXIDs once
there are fewer
than three million left until wraparound.
diff --git a/src/backend/access/transam/multixact.c
b/src/backend/access/transam/multixact.c
index e1ac4bf4c0b..42bce35c887 100644
--- a/src/backend/access/transam/multixact.c
+++ b/src/backend/access/transam/multixact.c
@@ -2072,16 +2072,16 @@ SetMultiXactIdLimit(MultiXactId oldest_datminmxid, Oid
oldest_datoid)
multiStopLimit -= FirstMultiXactId;
/*
- * We'll start complaining loudly when we get within 40M multis of data
+ * We'll start complaining loudly when we get within 100M multis of data
* loss. This is kind of arbitrary, but if you let your gas gauge get
- * down to 2% of full, would you be looking for the next gas station?
We
+ * down to 5% of full, would you be looking for the next gas station?
We
* need to be fairly liberal about this number because there are lots of
* scenarios where most transactions are done by automatic clients that
* won't pay attention to warnings. (No, we're not gonna make this
* configurable. If you know enough to configure it, you know enough to
* not get in this kind of trouble in the first place.)
*/
- multiWarnLimit = multiWrapLimit - 40000000;
+ multiWarnLimit = multiWrapLimit - 100000000;
if (multiWarnLimit < FirstMultiXactId)
multiWarnLimit -= FirstMultiXactId;
diff --git a/src/backend/access/transam/varsup.c
b/src/backend/access/transam/varsup.c
index 962396bae10..5585381bc8c 100644
--- a/src/backend/access/transam/varsup.c
+++ b/src/backend/access/transam/varsup.c
@@ -411,16 +411,16 @@ SetTransactionIdLimit(TransactionId oldest_datfrozenxid,
Oid oldest_datoid)
xidStopLimit -= FirstNormalTransactionId;
/*
- * We'll start complaining loudly when we get within 40M transactions of
+ * We'll start complaining loudly when we get within 100M transactions
of
* data loss. This is kind of arbitrary, but if you let your gas gauge
- * get down to 2% of full, would you be looking for the next gas
station?
+ * get down to 5% of full, would you be looking for the next gas
station?
* We need to be fairly liberal about this number because there are lots
* of scenarios where most transactions are done by automatic clients
that
* won't pay attention to warnings. (No, we're not gonna make this
* configurable. If you know enough to configure it, you know enough to
* not get in this kind of trouble in the first place.)
*/
- xidWarnLimit = xidWrapLimit - 40000000;
+ xidWarnLimit = xidWrapLimit - 100000000;
if (xidWarnLimit < FirstNormalTransactionId)
xidWarnLimit -= FirstNormalTransactionId;
--
2.39.5 (Apple Git-154)
>From 0a00eb8bd7d45e915aa2accb279e12f3b925bffa Mon Sep 17 00:00:00 2001
From: Nathan Bossart <[email protected]>
Date: Fri, 14 Nov 2025 10:48:35 -0600
Subject: [PATCH v2 3/3] Perodically emit server logs when fewer than 500M
remaining transaction IDs.
---
src/backend/access/transam/multixact.c | 40 +++++++++++++++++++++++---
src/backend/access/transam/varsup.c | 40 +++++++++++++++++++++++---
src/include/access/transam.h | 5 ++--
3 files changed, 75 insertions(+), 10 deletions(-)
diff --git a/src/backend/access/transam/multixact.c
b/src/backend/access/transam/multixact.c
index 42bce35c887..1b53a4b222b 100644
--- a/src/backend/access/transam/multixact.c
+++ b/src/backend/access/transam/multixact.c
@@ -147,6 +147,7 @@ typedef struct MultiXactStateData
/* support for anti-wraparound measures */
MultiXactId multiVacLimit;
+ MultiXactId multiLogLimit;
MultiXactId multiWarnLimit;
MultiXactId multiStopLimit;
MultiXactId multiWrapLimit;
@@ -970,6 +971,7 @@ GetNewMultiXactId(int nmembers, MultiXactOffset *offset)
* 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 multiLogLimit, start issuing logs periodically.
* If we're past multiWarnLimit, start issuing warnings.
* If we're past multiStopLimit, refuse to create new MultiXactIds.
*
@@ -985,6 +987,7 @@ GetNewMultiXactId(int nmembers, MultiXactOffset *offset)
* possibility of deadlock while doing get_database_name().
First,
* copy all the shared values we'll need in this path.
*/
+ MultiXactId multiLogLimit = MultiXactState->multiLogLimit;
MultiXactId multiWarnLimit = MultiXactState->multiWarnLimit;
MultiXactId multiStopLimit = MultiXactState->multiStopLimit;
MultiXactId multiWrapLimit = MultiXactState->multiWrapLimit;
@@ -1028,13 +1031,27 @@ GetNewMultiXactId(int nmembers, MultiXactOffset *offset)
if (IsUnderPostmaster && (result % 65536) == 0)
SendPostmasterSignal(PMSIGNAL_START_AUTOVAC_LAUNCHER);
- if (!MultiXactIdPrecedes(result, multiWarnLimit))
+ if (!MultiXactIdPrecedes(result, multiWarnLimit) ||
+ (!MultiXactIdPrecedes(result, multiLogLimit) &&
+ result % 1000000 == 0))
{
char *oldest_datname =
get_database_name(oldest_datoid);
+ int elevel;
+
+ /*
+ * We only send the periodic warnings to the server log
in an
+ * attempt to avoid confusion from clients (since the
WARNING will
+ * disappear for 1M multis at a time). Once the
warning limit is
+ * reached, we emit a proper WARNING every time.
+ */
+ if (!MultiXactIdPrecedes(result, multiWarnLimit))
+ elevel = WARNING;
+ else
+ elevel = LOG_SERVER_ONLY;
/* complain even if that DB has disappeared */
if (oldest_datname)
- ereport(WARNING,
+ ereport(elevel,
(errmsg_plural("database \"%s\"
must be vacuumed before %u more MultiXactId is used",
"database \"%s\" must be vacuumed before %u more MultiXactIds are used",
multiWrapLimit - result,
@@ -1045,7 +1062,7 @@ GetNewMultiXactId(int nmembers, MultiXactOffset *offset)
errhint("Execute a
database-wide VACUUM in that database.\n"
"You might
also need to commit or roll back old prepared transactions, or drop stale
replication slots.")));
else
- ereport(WARNING,
+ ereport(elevel,
(errmsg_plural("database with
OID %u must be vacuumed before %u more MultiXactId is used",
"database with OID %u must be vacuumed before %u more MultiXactIds are used",
multiWrapLimit - result,
@@ -2047,6 +2064,7 @@ void
SetMultiXactIdLimit(MultiXactId oldest_datminmxid, Oid oldest_datoid)
{
MultiXactId multiVacLimit;
+ MultiXactId multiLogLimit;
MultiXactId multiWarnLimit;
MultiXactId multiStopLimit;
MultiXactId multiWrapLimit;
@@ -2085,6 +2103,15 @@ SetMultiXactIdLimit(MultiXactId oldest_datminmxid, Oid
oldest_datoid)
if (multiWarnLimit < FirstMultiXactId)
multiWarnLimit -= FirstMultiXactId;
+ /*
+ * We'll start complaining every 1M multis when we get within 500M
multis
+ * of data loss. The idea is to provide an early warning system that is
+ * less noisy than multiWarnLimit but provides ample time to react.
+ */
+ multiLogLimit = multiWrapLimit - 500000000;
+ if (multiLogLimit < FirstMultiXactId)
+ multiLogLimit -= FirstMultiXactId;
+
/*
* We'll start trying to force autovacuums when oldest_datminmxid gets
to
* be more than autovacuum_multixact_freeze_max_age mxids old.
@@ -2102,6 +2129,7 @@ SetMultiXactIdLimit(MultiXactId oldest_datminmxid, Oid
oldest_datoid)
MultiXactState->oldestMultiXactId = oldest_datminmxid;
MultiXactState->oldestMultiXactDB = oldest_datoid;
MultiXactState->multiVacLimit = multiVacLimit;
+ MultiXactState->multiLogLimit = multiLogLimit;
MultiXactState->multiWarnLimit = multiWarnLimit;
MultiXactState->multiStopLimit = multiStopLimit;
MultiXactState->multiWrapLimit = multiWrapLimit;
@@ -2144,7 +2172,11 @@ SetMultiXactIdLimit(MultiXactId oldest_datminmxid, Oid
oldest_datoid)
if (MultiXactIdPrecedes(multiVacLimit, curMulti) && IsUnderPostmaster)
SendPostmasterSignal(PMSIGNAL_START_AUTOVAC_LAUNCHER);
- /* Give an immediate warning if past the wrap warn point */
+ /*
+ * Give an immediate warning if past the wrap warn point. We don't
bother
+ * with multiLogLimit here, as it's unlikely to apply. We leave that
part
+ * to GetNewMultiXactId() instead.
+ */
if (MultiXactIdPrecedes(multiWarnLimit, curMulti))
{
char *oldest_datname;
diff --git a/src/backend/access/transam/varsup.c
b/src/backend/access/transam/varsup.c
index 5585381bc8c..74ba958eb7a 100644
--- a/src/backend/access/transam/varsup.c
+++ b/src/backend/access/transam/varsup.c
@@ -112,6 +112,7 @@ GetNewTransactionId(bool isSubXact)
* catastrophic data loss due to XID wraparound. The basic rules are:
*
* If we're past xidVacLimit, start trying to force autovacuum cycles.
+ * If we're past xidLogLimit, start issuing logs periodically.
* If we're past xidWarnLimit, start issuing warnings.
* If we're past xidStopLimit, refuse to execute transactions, unless
* we are running in single-user mode (which gives an escape hatch
@@ -129,6 +130,7 @@ GetNewTransactionId(bool isSubXact)
* possibility of deadlock while doing get_database_name().
First,
* copy all the shared values we'll need in this path.
*/
+ TransactionId xidLogLimit = TransamVariables->xidLogLimit;
TransactionId xidWarnLimit = TransamVariables->xidWarnLimit;
TransactionId xidStopLimit = TransamVariables->xidStopLimit;
TransactionId xidWrapLimit = TransamVariables->xidWrapLimit;
@@ -165,13 +167,27 @@ GetNewTransactionId(bool isSubXact)
errhint("Execute a
database-wide VACUUM in that database.\n"
"You might
also need to commit or roll back old prepared transactions, or drop stale
replication slots.")));
}
- else if (TransactionIdFollowsOrEquals(xid, xidWarnLimit))
+ else if (TransactionIdFollowsOrEquals(xid, xidWarnLimit) ||
+ (TransactionIdFollowsOrEquals(xid,
xidLogLimit) &&
+ xid % 1000000 == 0))
{
char *oldest_datname =
get_database_name(oldest_datoid);
+ int elevel;
+
+ /*
+ * We only send the periodic warnings to the server log
in an
+ * attempt to avoid confusion from clients (since the
WARNING will
+ * disappear for 1M transactions at a time). Once the
warning
+ * limit is reached, we emit a proper WARNING every
time.
+ */
+ if (TransactionIdFollowsOrEquals(xid, xidWarnLimit))
+ elevel = WARNING;
+ else
+ elevel = LOG_SERVER_ONLY;
/* complain even if that DB has disappeared */
if (oldest_datname)
- ereport(WARNING,
+ ereport(elevel,
(errmsg("database \"%s\" must
be vacuumed within %u transactions",
oldest_datname,
xidWrapLimit -
xid),
@@ -180,7 +196,7 @@ GetNewTransactionId(bool isSubXact)
errhint("To avoid transaction
ID assignment failures, execute a database-wide VACUUM in that database.\n"
"You might
also need to commit or roll back old prepared transactions, or drop stale
replication slots.")));
else
- ereport(WARNING,
+ ereport(elevel,
(errmsg("database with OID %u
must be vacuumed within %u transactions",
oldest_datoid,
xidWrapLimit -
xid),
@@ -376,6 +392,7 @@ void
SetTransactionIdLimit(TransactionId oldest_datfrozenxid, Oid oldest_datoid)
{
TransactionId xidVacLimit;
+ TransactionId xidLogLimit;
TransactionId xidWarnLimit;
TransactionId xidStopLimit;
TransactionId xidWrapLimit;
@@ -424,6 +441,16 @@ SetTransactionIdLimit(TransactionId oldest_datfrozenxid,
Oid oldest_datoid)
if (xidWarnLimit < FirstNormalTransactionId)
xidWarnLimit -= FirstNormalTransactionId;
+ /*
+ * We'll start complaining every 1M transactions when we get within 500M
+ * transactions of data loss. The idea is to provide an early warning
+ * system that is less noisy than xidWarnLimit but provides ample time
to
+ * react.
+ */
+ xidLogLimit = xidWrapLimit - 500000000;
+ if (xidLogLimit < FirstNormalTransactionId)
+ xidLogLimit -= FirstNormalTransactionId;
+
/*
* We'll start trying to force autovacuums when oldest_datfrozenxid gets
* to be more than autovacuum_freeze_max_age transactions old.
@@ -447,6 +474,7 @@ SetTransactionIdLimit(TransactionId oldest_datfrozenxid,
Oid oldest_datoid)
LWLockAcquire(XidGenLock, LW_EXCLUSIVE);
TransamVariables->oldestXid = oldest_datfrozenxid;
TransamVariables->xidVacLimit = xidVacLimit;
+ TransamVariables->xidLogLimit = xidLogLimit;
TransamVariables->xidWarnLimit = xidWarnLimit;
TransamVariables->xidStopLimit = xidStopLimit;
TransamVariables->xidWrapLimit = xidWrapLimit;
@@ -470,7 +498,11 @@ SetTransactionIdLimit(TransactionId oldest_datfrozenxid,
Oid oldest_datoid)
IsUnderPostmaster && !InRecovery)
SendPostmasterSignal(PMSIGNAL_START_AUTOVAC_LAUNCHER);
- /* Give an immediate warning if past the wrap warn point */
+ /*
+ * Give an immediate warning if past the wrap warn point. We don't
bother
+ * with xidLogLimit here, as it's unlikely to apply. We leave that part
+ * to GetNewTransactionId() instead.
+ */
if (TransactionIdFollowsOrEquals(curXid, xidWarnLimit) && !InRecovery)
{
char *oldest_datname;
diff --git a/src/include/access/transam.h b/src/include/access/transam.h
index c9e20418275..a1bd4259f86 100644
--- a/src/include/access/transam.h
+++ b/src/include/access/transam.h
@@ -203,8 +203,8 @@ FullTransactionIdAdvance(FullTransactionId *dest)
* LWLocks.
*
* Note: xidWrapLimit and oldestXidDB are not "active" values, but are
- * used just to generate useful messages when xidWarnLimit or xidStopLimit
- * are exceeded.
+ * used just to generate useful messages when xidLogLimit, xidWarnLimit, or
+ * xidStopLimit are exceeded.
*/
typedef struct TransamVariablesData
{
@@ -221,6 +221,7 @@ typedef struct TransamVariablesData
TransactionId oldestXid; /* cluster-wide minimum datfrozenxid */
TransactionId xidVacLimit; /* start forcing autovacuums here */
+ TransactionId xidLogLimit; /* start logging periodically here */
TransactionId xidWarnLimit; /* start complaining here */
TransactionId xidStopLimit; /* refuse to advance nextXid beyond here */
TransactionId xidWrapLimit; /* where the world ends */
--
2.39.5 (Apple Git-154)
