[CF 5567] v6 - Change log level for notifying hot standby is waiting non-overflowed snapshot

This branch was automatically generated by a robot using patches from an
email thread registered at:

https://commitfest.postgresql.org/patch/5567

The branch will be overwritten each time a new patch version is posted to
the thread, and also periodically to check for bitrot caused by changes
on the master branch.

Patch(es): https://www.postgresql.org/message-id/[email protected]
Author(s): Atsushi Torikoshi

Author: Commitfest Bot

doc/src/sgml/high-availability.sgml

@@ -1535,7 +1535,8 @@ synchronous_standby_names = 'ANY 2 (s1, s2, s3)'
    <para>
     When the <xref linkend="guc-hot-standby"/> parameter is set to true on a
     standby server, it will begin accepting connections once the recovery has
-    brought the system to a consistent state.  All such connections are
+    brought the system to a consistent state and be ready for hot standby.
+    All such connections are
     strictly read-only; not even temporary tables may be written.
    </para>
 
@@ -1974,9 +1975,12 @@ LOG:  database system is ready to accept read-only connections
     Consistency information is recorded once per checkpoint on the primary.
     It is not possible to enable hot standby when reading WAL
     written during a period when <varname>wal_level</varname> was not set to
-    <literal>replica</literal> or <literal>logical</literal> on the primary.  Reaching
-    a consistent state can also be delayed in the presence of both of these
-    conditions:
+    <literal>replica</literal> or <literal>logical</literal> on the primary.
+    Even after reaching a consistent state, the recovery snapshot may not
+    be ready for hot standby if both of the following conditions are met,
+    delaying accepting read-only connections.  To enable hot standby,
+    long-lived write transactions with more than 64 subtransactions
+    need to be closed on the primary.
 
       <itemizedlist>
        <listitem>

src/backend/access/transam/xlogrecovery.c

@@ -291,6 +291,11 @@ static bool backupEndRequired = false;
  * Consistent state means that the system is internally consistent, all
  * the WAL has been replayed up to a certain point, and importantly, there
  * is no trace of later actions on disk.
+ *
+ * This flag is used only by the startup process and postmaster. When
+ * minRecoveryPoint is reached, the startup process sets it to true and
+ * sends a PMSIGNAL_RECOVERY_CONSISTENT signal to the postmaster,
+ * which then sets it to true upon receiving the signal.
  */
 bool		reachedConsistency = false;
 
@@ -2248,6 +2253,7 @@ CheckRecoveryConsistency(void)
 		CheckTablespaceDirectory();
 
 		reachedConsistency = true;
+		SendPostmasterSignal(PMSIGNAL_RECOVERY_CONSISTENT);
 		ereport(LOG,
 				(errmsg("consistent recovery state reached at %X/%X",
 						LSN_FORMAT_ARGS(lastReplayedEndRecPtr))));

src/backend/postmaster/postmaster.c

@@ -1825,8 +1825,7 @@ canAcceptConnections(BackendType backend_type)
 		else if (!FatalError && pmState == PM_STARTUP)
 			return CAC_STARTUP; /* normal startup */
 		else if (!FatalError && pmState == PM_RECOVERY)
-			return CAC_NOTCONSISTENT;	/* not yet at consistent recovery
-										 * state */
+			return CAC_NOTHOTSTANDBY;	/* not yet ready for hot standby */
 		else
 			return CAC_RECOVERY;	/* else must be crash recovery */
 	}
@@ -3699,6 +3698,7 @@ process_pm_pmsignal(void)
 		/* WAL redo has started. We're out of reinitialization. */
 		FatalError = false;
 		AbortStartTime = 0;
+		reachedConsistency = false;
 
 		/*
 		 * Start the archiver if we're responsible for (re-)archiving received
@@ -3724,8 +3724,14 @@ process_pm_pmsignal(void)
 		UpdatePMState(PM_RECOVERY);
 	}
 
-	if (CheckPostmasterSignal(PMSIGNAL_BEGIN_HOT_STANDBY) &&
+	if (CheckPostmasterSignal(PMSIGNAL_RECOVERY_CONSISTENT) &&
 		pmState == PM_RECOVERY && Shutdown == NoShutdown)
+	{
+		reachedConsistency = true;
+	}
+
+	if (CheckPostmasterSignal(PMSIGNAL_BEGIN_HOT_STANDBY) &&
+		(pmState == PM_RECOVERY && Shutdown == NoShutdown))
 	{
 		ereport(LOG,
 				(errmsg("database system is ready to accept read-only connections")));

src/backend/tcop/backend_startup.c

@@ -18,6 +18,7 @@
 #include <unistd.h>
 
 #include "access/xlog.h"
+#include "access/xlogrecovery.h"
 #include "common/ip.h"
 #include "common/string.h"
 #include "libpq/libpq.h"
@@ -306,17 +307,24 @@ BackendInitialize(ClientSocket *client_sock, CAC_state cac)
 						(errcode(ERRCODE_CANNOT_CONNECT_NOW),
 						 errmsg("the database system is starting up")));
 				break;
-			case CAC_NOTCONSISTENT:
-				if (EnableHotStandby)
+			case CAC_NOTHOTSTANDBY:
+				if (!EnableHotStandby)
+					ereport(FATAL,
+							(errcode(ERRCODE_CANNOT_CONNECT_NOW),
+							 errmsg("the database system is not accepting connections"),
+							 errdetail("Hot standby mode is disabled.")));
+				else if (reachedConsistency)
 					ereport(FATAL,
 							(errcode(ERRCODE_CANNOT_CONNECT_NOW),
 							 errmsg("the database system is not yet accepting connections"),
-							 errdetail("Consistent recovery state has not been yet reached.")));
+							 errdetail("Recovery snapshot is not yet ready for hot standby."),
+							 errhint("To enable hot standby, close write transactions with more than %d subtransactions on the primary server.",
+									 PGPROC_MAX_CACHED_SUBXIDS)));
 				else
 					ereport(FATAL,
 							(errcode(ERRCODE_CANNOT_CONNECT_NOW),
-							 errmsg("the database system is not accepting connections"),
-							 errdetail("Hot standby mode is disabled.")));
+							 errmsg("the database system is not yet accepting connections"),
+							 errdetail("Consistent recovery state has not been yet reached.")));
 				break;
 			case CAC_SHUTDOWN:
 				ereport(FATAL,

src/include/storage/pmsignal.h

@@ -33,6 +33,7 @@
 typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
+	PMSIGNAL_RECOVERY_CONSISTENT,	/* recovery has reached consistent state */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */

src/include/tcop/backend_startup.h

@@ -36,7 +36,7 @@ typedef enum CAC_state
 	CAC_STARTUP,
 	CAC_SHUTDOWN,
 	CAC_RECOVERY,
-	CAC_NOTCONSISTENT,
+	CAC_NOTHOTSTANDBY,
 	CAC_TOOMANY,
 } CAC_state;