Sync Fork from Upstream Repo

contrib/hstore/Makefile

@@ -15,7 +15,7 @@ DATA = hstore--1.4.sql \
 	hstore--1.5--1.6.sql \
 	hstore--1.4--1.5.sql \
 	hstore--1.3--1.4.sql hstore--1.2--1.3.sql \
-	hstore--1.1--1.2.sql hstore--1.0--1.1.sql
+	hstore--1.1--1.2.sql
 PGFILEDESC = "hstore - key/value pair data type"
 
 HEADERS = hstore.h

doc/src/sgml/catalogs.sgml

@@ -10226,7 +10226,8 @@ SCRAM-SHA-256$<replaceable>&lt;iteration count&gt;</replaceable>:<replaceable>&l
    and general database objects (identified by class OID and object OID,
    in the same way as in <structname>pg_description</structname> or
    <structname>pg_depend</structname>).  Also, the right to extend a
-   relation is represented as a separate lockable object.
+   relation is represented as a separate lockable object, as is the right to
+   update <structname>pg_database</structname>.<structfield>datfrozenxid</structfield>.
    Also, <quote>advisory</quote> locks can be taken on numbers that have
    user-defined meanings.
   </para>
@@ -10254,6 +10255,7 @@ SCRAM-SHA-256$<replaceable>&lt;iteration count&gt;</replaceable>:<replaceable>&l
        Type of the lockable object:
        <literal>relation</literal>,
        <literal>extend</literal>,
+       <literal>frozenid</literal>,
        <literal>page</literal>,
        <literal>tuple</literal>,
        <literal>transactionid</literal>,

doc/src/sgml/monitoring.sgml

@@ -1742,6 +1742,12 @@ postgres   27093  0.0  0.0  30096  2752 ?        Ss   11:34   0:00 postgres: ser
       <entry><literal>extend</literal></entry>
       <entry>Waiting to extend a relation.</entry>
      </row>
+     <row>
+      <entry><literal>frozenid</literal></entry>
+      <entry>Waiting to
+       update <structname>pg_database</structname>.<structfield>datfrozenxid</structfield>
+       and <structname>pg_database</structname>.<structfield>datminmxid</structfield>.</entry>
+     </row>
      <row>
       <entry><literal>object</literal></entry>
       <entry>Waiting to acquire a lock on a non-relation database object.</entry>
@@ -1910,6 +1916,11 @@ postgres   27093  0.0  0.0  30096  2752 ?        Ss   11:34   0:00 postgres: ser
       <entry><literal>NotifyQueue</literal></entry>
       <entry>Waiting to read or update <command>NOTIFY</command> messages.</entry>
      </row>
+     <row>
+      <entry><literal>NotifyQueueTail</literal></entry>
+      <entry>Waiting to update limit on <command>NOTIFY</command> message
+       storage.</entry>
+     </row>
      <row>
       <entry><literal>NotifySLRU</literal></entry>
       <entry>Waiting to access the <command>NOTIFY</command> message SLRU
@@ -2086,6 +2097,11 @@ postgres   27093  0.0  0.0  30096  2752 ?        Ss   11:34   0:00 postgres: ser
       <entry><literal>WALWrite</literal></entry>
       <entry>Waiting for WAL buffers to be written to disk.</entry>
      </row>
+     <row>
+      <entry><literal>WrapLimitsVacuum</literal></entry>
+      <entry>Waiting to update limits on transaction id and multixact
+       consumption.</entry>
+     </row>
      <row>
       <entry><literal>XactBuffer</literal></entry>
       <entry>Waiting for I/O on a transaction status SLRU buffer.</entry>

src/backend/access/heap/heapam.c

@@ -6920,8 +6920,6 @@ HeapTupleHeaderAdvanceLatestRemovedXid(HeapTupleHeader tuple,
 	 * updated/deleted by the inserting transaction.
 	 *
 	 * Look for a committed hint bit, or if no xmin bit is set, check clog.
-	 * This needs to work on both primary and standby, where it is used to
-	 * assess btree delete records.
 	 */
 	if (HeapTupleHeaderXminCommitted(tuple) ||
 		(!HeapTupleHeaderXminInvalid(tuple) && TransactionIdDidCommit(xmin)))

src/backend/access/transam/README

@@ -635,12 +635,11 @@ be reconstructed later following a crash and the action is simply a way
 of optimising for performance. When a hint is written we use
 MarkBufferDirtyHint() to mark the block dirty.
 
-If the buffer is clean and checksums are in use then
-MarkBufferDirtyHint() inserts an XLOG_FPI record to ensure that we
-take a full page image that includes the hint. We do this to avoid
-a partial page write, when we write the dirtied page. WAL is not
-written during recovery, so we simply skip dirtying blocks because
-of hints when in recovery.
+If the buffer is clean and checksums are in use then MarkBufferDirtyHint()
+inserts an XLOG_FPI_FOR_HINT record to ensure that we take a full page image
+that includes the hint. We do this to avoid a partial page write, when we
+write the dirtied page. WAL is not written during recovery, so we simply skip
+dirtying blocks because of hints when in recovery.
 
 If you do decide to optimise away a WAL record, then any calls to
 MarkBufferDirty() must be replaced by MarkBufferDirtyHint(),

src/backend/access/transam/slru.c

@@ -1191,6 +1191,14 @@ SimpleLruFlush(SlruCtl ctl, bool allow_redirtied)
 
 /*
  * Remove all segments before the one holding the passed page number
+ *
+ * All SLRUs prevent concurrent calls to this function, either with an LWLock
+ * or by calling it only as part of a checkpoint.  Mutual exclusion must begin
+ * before computing cutoffPage.  Mutual exclusion must end after any limit
+ * update that would permit other backends to write fresh data into the
+ * segment immediately preceding the one containing cutoffPage.  Otherwise,
+ * when the SLRU is quite full, SimpleLruTruncate() might delete that segment
+ * after it has accrued freshly-written data.
  */
 void
 SimpleLruTruncate(SlruCtl ctl, int cutoffPage)

src/backend/access/transam/subtrans.c

@@ -349,8 +349,8 @@ ExtendSUBTRANS(TransactionId newestXact)
 /*
  * Remove all SUBTRANS segments before the one holding the passed transaction ID
  *
- * This is normally called during checkpoint, with oldestXact being the
- * oldest TransactionXmin of any running transaction.
+ * oldestXact is the oldest TransactionXmin of any running transaction.  This
+ * is called only during checkpoint.
  */
 void
 TruncateSUBTRANS(TransactionId oldestXact)

src/backend/access/transam/varsup.c

@@ -367,12 +367,13 @@ SetTransactionIdLimit(TransactionId oldest_datfrozenxid, Oid oldest_datoid)
 	 * We'll refuse to continue assigning XIDs in interactive mode once we get
 	 * within 3M transactions of data loss.  This leaves lots of room for the
 	 * DBA to fool around fixing things in a standalone backend, while not
-	 * being significant compared to total XID space. (Note that since
-	 * vacuuming requires one transaction per table cleaned, we had better be
-	 * sure there's lots of XIDs left...)  Also, at default BLCKSZ, this
-	 * leaves two completely-idle segments.  In the event of edge-case bugs
-	 * involving page or segment arithmetic, idle segments render the bugs
-	 * unreachable outside of single-user mode.
+	 * being significant compared to total XID space. (VACUUM requires an XID
+	 * if it truncates at wal_level!=minimal.  "VACUUM (ANALYZE)", which a DBA
+	 * might do by reflex, assigns an XID.  Hence, we had better be sure
+	 * there's lots of XIDs left...)  Also, at default BLCKSZ, this leaves two
+	 * completely-idle segments.  In the event of edge-case bugs involving
+	 * page or segment arithmetic, idle segments render the bugs unreachable
+	 * outside of single-user mode.
 	 */
 	xidStopLimit = xidWrapLimit - 3000000;
 	if (xidStopLimit < FirstNormalTransactionId)

src/backend/commands/async.c

@@ -244,19 +244,22 @@ typedef struct QueueBackendStatus
 /*
  * Shared memory state for LISTEN/NOTIFY (excluding its SLRU stuff)
  *
- * The AsyncQueueControl structure is protected by the NotifyQueueLock.
+ * The AsyncQueueControl structure is protected by the NotifyQueueLock and
+ * NotifyQueueTailLock.
  *
- * When holding the lock in SHARED mode, backends may only inspect their own
- * entries as well as the head and tail pointers. Consequently we can allow a
- * backend to update its own record while holding only SHARED lock (since no
- * other backend will inspect it).
+ * When holding NotifyQueueLock in SHARED mode, backends may only inspect
+ * their own entries as well as the head and tail pointers. Consequently we
+ * can allow a backend to update its own record while holding only SHARED lock
+ * (since no other backend will inspect it).
  *
- * When holding the lock in EXCLUSIVE mode, backends can inspect the entries
- * of other backends and also change the head and tail pointers.
+ * When holding NotifyQueueLock in EXCLUSIVE mode, backends can inspect the
+ * entries of other backends and also change the head pointer. When holding
+ * both NotifyQueueLock and NotifyQueueTailLock in EXCLUSIVE mode, backends
+ * can change the tail pointer.
  *
  * NotifySLRULock is used as the control lock for the pg_notify SLRU buffers.
- * In order to avoid deadlocks, whenever we need both locks, we always first
- * get NotifyQueueLock and then NotifySLRULock.
+ * In order to avoid deadlocks, whenever we need multiple locks, we first get
+ * NotifyQueueTailLock, then NotifyQueueLock, and lastly NotifySLRULock.
  *
  * Each backend uses the backend[] array entry with index equal to its
  * BackendId (which can range from 1 to MaxBackends).  We rely on this to make
@@ -299,13 +302,10 @@ static SlruCtlData NotifyCtlData;
 #define QUEUE_FULL_WARN_INTERVAL	5000	/* warn at most once every 5s */
 
 /*
- * slru.c currently assumes that all filenames are four characters of hex
- * digits. That means that we can use segments 0000 through FFFF.
- * Each segment contains SLRU_PAGES_PER_SEGMENT pages which gives us
- * the pages from 0 to SLRU_PAGES_PER_SEGMENT * 0x10000 - 1.
- *
- * It's of course possible to enhance slru.c, but this gives us so much
- * space already that it doesn't seem worth the trouble.
+ * Use segments 0000 through FFFF.  Each contains SLRU_PAGES_PER_SEGMENT pages
+ * which gives us the pages from 0 to SLRU_PAGES_PER_SEGMENT * 0x10000 - 1.
+ * We could use as many segments as SlruScanDirectory() allows, but this gives
+ * us so much space already that it doesn't seem worth the trouble.
  *
  * The most data we can have in the queue at a time is QUEUE_MAX_PAGE/2
  * pages, because more than that would confuse slru.c into thinking there
@@ -2177,6 +2177,10 @@ asyncQueueAdvanceTail(void)
 	int			newtailpage;
 	int			boundary;
 
+	/* Restrict task to one backend per cluster; see SimpleLruTruncate(). */
+	LWLockAcquire(NotifyQueueTailLock, LW_EXCLUSIVE);
+
+	/* Compute the new tail. */
 	LWLockAcquire(NotifyQueueLock, LW_EXCLUSIVE);
 	min = QUEUE_HEAD;
 	for (BackendId i = QUEUE_FIRST_LISTENER; i > 0; i = QUEUE_NEXT_LISTENER(i))
@@ -2185,7 +2189,6 @@ asyncQueueAdvanceTail(void)
 		min = QUEUE_POS_MIN(min, QUEUE_BACKEND_POS(i));
 	}
 	oldtailpage = QUEUE_POS_PAGE(QUEUE_TAIL);
-	QUEUE_TAIL = min;
 	LWLockRelease(NotifyQueueLock);
 
 	/*
@@ -2205,6 +2208,17 @@ asyncQueueAdvanceTail(void)
 		 */
 		SimpleLruTruncate(NotifyCtl, newtailpage);
 	}
+
+	/*
+	 * Advertise the new tail.  This changes asyncQueueIsFull()'s verdict for
+	 * the segment immediately prior to the new tail, allowing fresh data into
+	 * that segment.
+	 */
+	LWLockAcquire(NotifyQueueLock, LW_EXCLUSIVE);
+	QUEUE_TAIL = min;
+	LWLockRelease(NotifyQueueLock);
+
+	LWLockRelease(NotifyQueueTailLock);
 }
 
 /*

src/backend/commands/vacuum.c

@@ -949,11 +949,11 @@ vacuum_set_xid_limits(Relation rel,
 	/*
 	 * We can always ignore processes running lazy vacuum.  This is because we
 	 * use these values only for deciding which tuples we must keep in the
-	 * tables.  Since lazy vacuum doesn't write its XID anywhere, it's safe to
-	 * ignore it.  In theory it could be problematic to ignore lazy vacuums in
-	 * a full vacuum, but keep in mind that only one vacuum process can be
-	 * working on a particular table at any time, and that each vacuum is
-	 * always an independent transaction.
+	 * tables.  Since lazy vacuum doesn't write its XID anywhere (usually no
+	 * XID assigned), it's safe to ignore it.  In theory it could be
+	 * problematic to ignore lazy vacuums in a full vacuum, but keep in mind
+	 * that only one vacuum process can be working on a particular table at
+	 * any time, and that each vacuum is always an independent transaction.
 	 */
 	*oldestXmin = GetOldestNonRemovableTransactionId(rel);
 
@@ -1361,6 +1361,14 @@ vac_update_datfrozenxid(void)
 	bool		bogus = false;
 	bool		dirty = false;
 
+	/*
+	 * Restrict this task to one backend per database.  This avoids race
+	 * conditions that would move datfrozenxid or datminmxid backward.  It
+	 * avoids calling vac_truncate_clog() with a datfrozenxid preceding a
+	 * datfrozenxid passed to an earlier vac_truncate_clog() call.
+	 */
+	LockDatabaseFrozenIds(ExclusiveLock);
+
 	/*
 	 * Initialize the "min" calculation with
 	 * GetOldestNonRemovableTransactionId(), which is a reasonable
@@ -1551,6 +1559,9 @@ vac_truncate_clog(TransactionId frozenXID,
 	bool		bogus = false;
 	bool		frozenAlreadyWrapped = false;
 
+	/* Restrict task to one backend per cluster; see SimpleLruTruncate(). */
+	LWLockAcquire(WrapLimitsVacuumLock, LW_EXCLUSIVE);
+
 	/* init oldest datoids to sync with my frozenXID/minMulti values */
 	oldestxid_datoid = MyDatabaseId;
 	minmulti_datoid = MyDatabaseId;
@@ -1660,6 +1671,8 @@ vac_truncate_clog(TransactionId frozenXID,
 	 */
 	SetTransactionIdLimit(frozenXID, oldestxid_datoid);
 	SetMultiXactIdLimit(minMulti, minmulti_datoid, false);
+
+	LWLockRelease(WrapLimitsVacuumLock);
 }
 
 

src/backend/storage/buffer/bufmgr.c

@@ -3578,7 +3578,7 @@ IncrBufferRefCount(Buffer buffer)
  * This is essentially the same as MarkBufferDirty, except:
  *
  * 1. The caller does not write WAL; so if checksums are enabled, we may need
- *	  to write an XLOG_FPI WAL record to protect against torn pages.
+ *	  to write an XLOG_FPI_FOR_HINT WAL record to protect against torn pages.
  * 2. The caller might have only share-lock instead of exclusive-lock on the
  *	  buffer's content lock.
  * 3. This function does not guarantee that the buffer is always marked dirty

src/backend/storage/lmgr/lmgr.c

@@ -460,6 +460,21 @@ UnlockRelationForExtension(Relation relation, LOCKMODE lockmode)
 	LockRelease(&tag, lockmode, false);
 }
 
+/*
+ *		LockDatabaseFrozenIds
+ *
+ * This allows one backend per database to execute vac_update_datfrozenxid().
+ */
+void
+LockDatabaseFrozenIds(LOCKMODE lockmode)
+{
+	LOCKTAG		tag;
+
+	SET_LOCKTAG_DATABASE_FROZEN_IDS(tag, MyDatabaseId);
+
+	(void) LockAcquire(&tag, lockmode, false, false);
+}
+
 /*
  *		LockPage
  *
@@ -1098,6 +1113,11 @@ DescribeLockTag(StringInfo buf, const LOCKTAG *tag)
 							 tag->locktag_field2,
 							 tag->locktag_field1);
 			break;
+		case LOCKTAG_DATABASE_FROZEN_IDS:
+			appendStringInfo(buf,
+							 _("pg_database.datfrozenxid of database %u"),
+							 tag->locktag_field1);
+			break;
 		case LOCKTAG_PAGE:
 			appendStringInfo(buf,
 							 _("page %u of relation %u of database %u"),

src/backend/storage/lmgr/lwlocknames.txt

@@ -50,3 +50,6 @@ MultiXactTruncationLock				41
 OldSnapshotTimeMapLock				42
 LogicalRepWorkerLock				43
 XactTruncationLock					44
+# 45 was XactTruncationLock until removal of BackendRandomLock
+WrapLimitsVacuumLock				46
+NotifyQueueTailLock					47

src/backend/utils/adt/float.c

@@ -271,18 +271,6 @@ float4in(PG_FUNCTION_ARGS)
 					 errmsg("invalid input syntax for type %s: \"%s\"",
 							"real", orig_num)));
 	}
-#ifdef HAVE_BUGGY_SOLARIS_STRTOD
-	else
-	{
-		/*
-		 * Many versions of Solaris have a bug wherein strtod sets endptr to
-		 * point one byte beyond the end of the string when given "inf" or
-		 * "infinity".
-		 */
-		if (endptr != num && endptr[-1] == '\0')
-			endptr--;
-	}
-#endif							/* HAVE_BUGGY_SOLARIS_STRTOD */
 
 	/* skip trailing whitespace */
 	while (*endptr != '\0' && isspace((unsigned char) *endptr))
@@ -499,18 +487,6 @@ float8in_internal_opt_error(char *num, char **endptr_p,
 										 type_name, orig_string))),
 						 have_error);
 	}
-#ifdef HAVE_BUGGY_SOLARIS_STRTOD
-	else
-	{
-		/*
-		 * Many versions of Solaris have a bug wherein strtod sets endptr to
-		 * point one byte beyond the end of the string when given "inf" or
-		 * "infinity".
-		 */
-		if (endptr != num && endptr[-1] == '\0')
-			endptr--;
-	}
-#endif							/* HAVE_BUGGY_SOLARIS_STRTOD */
 
 	/* skip trailing whitespace */
 	while (*endptr != '\0' && isspace((unsigned char) *endptr))

src/backend/utils/adt/lockfuncs.c

@@ -29,6 +29,7 @@
 const char *const LockTagTypeNames[] = {
 	"relation",
 	"extend",
+	"frozenid",
 	"page",
 	"tuple",
 	"transactionid",
@@ -254,6 +255,17 @@ pg_lock_status(PG_FUNCTION_ARGS)
 				nulls[8] = true;
 				nulls[9] = true;
 				break;
+			case LOCKTAG_DATABASE_FROZEN_IDS:
+				values[1] = ObjectIdGetDatum(instance->locktag.locktag_field1);
+				nulls[2] = true;
+				nulls[3] = true;
+				nulls[4] = true;
+				nulls[5] = true;
+				nulls[6] = true;
+				nulls[7] = true;
+				nulls[8] = true;
+				nulls[9] = true;
+				break;
 			case LOCKTAG_PAGE:
 				values[1] = ObjectIdGetDatum(instance->locktag.locktag_field1);
 				values[2] = ObjectIdGetDatum(instance->locktag.locktag_field2);